TOP ACTIVATIONS
MAX = 0.131

, thick curtain in the living room . She loved it
, red laser in the living room . She wanted to
a big jar in the living room . It had a
saw a computer in the living room and was very curious
a big box in the living room . It had a
a glimpse of something furry out of the corner of her
a big box in the living room . " What 's
when he spotted something far out in the water . He
a big box in the living room . It had a
cried , dropping the magn ifying glass . "
a big screen in the living room . He was curious
a big box in the living room . He was very
. Suddenly a voice shouted out : " I want that
bedroom . Suddenly , something out of the window caught her
a fake plant in the living room . Lily didn 't
was the television in the living room . It was on
the rock was actually a living creature called a Rock Monster
a big box in the living room . It had a
big eyes and a tongue out . He w ags his
a big box in the living room . She asked her

MIN ACTIVATIONS
MIN = -0.104

. Are you ready to board ?" Mom asked .
it and wished she could board it .
" Now you can golf !" she said happily .
you want to share my shirt ? We can take turns
Hey , can I play basketball with you ?" Tim my
" Can we bounce on the bed ?" Anna
mom , " Can I bat he with my boat ?"
and rest . You can bounce again tomorrow , but not
you want to try my bike ?" Anna says , "
But we want to play baseball !" they cry .
dad , can we play baseball today ?" they ask .
't worry , we can bat he it together ".
" Can I try your cap ?" Sam asks Ben .
. Can we come on board ?" Lily asked politely .
day , Tim wanted to bat he in the tub with
a game ! We can bounce high and try to touch
fake bunny . You can bounce it like a ball !"
. She says they can bounce some more when they get
his friends . He can bounce the ball , pass the
, to ot , to ot !" they shouted .

INTERVAL 0.072 - 0.131
CONTAINS 0.344%

sharp teeth . It jumped out of the bush and ran
noticed a light in the dark . He followed the light
?" one of the people in the crowd asked .
the bird were the best of friends . <|endoftext|> One day
saw some nice warm food inside . She smiled and quickly

INTERVAL 0.013 - 0.072
CONTAINS 26.792%

! What are you doing ?" " I am
. He is nice . He offers his toy train to
herself . She sat down with her string and read the
ready ?" Lily nodded and said , " By e ,
piece of string ," Jack said . The boys

INTERVAL -0.045 - 0.013
CONTAINS 70.203%

lit up as she saw the colorful gear on the back
. You are brave ." Tom took a deep
more sugar to the lemon ade . Lily took another sip
the car until you â € ™ re big enough to
funny and make me laugh ." Next , they

INTERVAL -0.104 - -0.045
CONTAINS 2.662%

house again . <|endoftext|> T eddy was a very tidy bear
and they both wanted to kick it . Lily said ,
me feel better ." <|endoftext|> Once upon a time , there
Ben agreed . He told Rex to sit on the floor
's friends loved to come and sit around the fireplace ,
Token,
Token ID11
Feature activation+5.48e-02

Pos logit contributions
apy+0.022
 Nick+0.021
 Mam+0.020
 Megan+0.020
 Liz+0.019
Neg logit contributions
ercise-0.016
isi-0.016
ock-0.015
iable-0.015
orn-0.014
Token thick
Token ID6546
Feature activation+2.96e-02

Pos logit contributions
apy+0.098
 Nick+0.096
 Mam+0.093
 Megan+0.089
 Liz+0.089
Neg logit contributions
ercise-0.089
isi-0.087
iable-0.086
ock-0.085
off-0.080
Token curtain
Token ID29461
Feature activation+4.63e-02

Pos logit contributions
apy+0.057
 Nick+0.056
 Mam+0.054
 Liz+0.052
 Megan+0.052
Neg logit contributions
ercise-0.043
isi-0.042
ock-0.042
iable-0.040
orn-0.039
Token in
Token ID287
Feature activation+9.53e-02

Pos logit contributions
apy+0.087
 Nick+0.086
 Mam+0.086
 Mick+0.081
 Madd+0.081
Neg logit contributions
ercise-0.067
isi-0.066
ock-0.066
iable-0.064
off-0.062
Token the
Token ID262
Feature activation+1.68e-02

Pos logit contributions
apy+0.209
 Nick+0.187
 Mam+0.186
sed+0.186
 ankles+0.185
Neg logit contributions
ock-0.121
 course-0.112
isi-0.109
off-0.104
ty-0.099
Token living
Token ID2877
Feature activation+1.31e-01

Pos logit contributions
apy+0.026
 Nick+0.025
 Mam+0.025
 Liz+0.023
 Megan+0.023
Neg logit contributions
ercise-0.032
isi-0.031
iable-0.031
ock-0.031
off-0.029
Token room
Token ID2119
Feature activation+7.35e-02

Pos logit contributions
apy+0.219
 Madd+0.196
 Nick+0.195
 Mam+0.195
 Kel+0.195
Neg logit contributions
off-0.232
les-0.224
up-0.223
ock-0.218
ercise-0.214
Token.
Token ID13
Feature activation+4.89e-03

Pos logit contributions
apy+0.158
 Madd+0.150
 Nick+0.149
 Mam+0.149
 Mick+0.146
Neg logit contributions
ock-0.089
iable-0.086
up-0.085
off-0.085
isi-0.084
Token She
Token ID1375
Feature activation+2.49e-02

Pos logit contributions
apy+0.009
 Mick+0.009
udge+0.009
uzz+0.009
bers+0.009
Neg logit contributions
ercise-0.006
isi-0.006
off-0.006
ometime-0.005
night-0.005
Token loved
Token ID6151
Feature activation-7.90e-03

Pos logit contributions
apy+0.038
 Nick+0.037
 Mam+0.036
 Liz+0.034
 Megan+0.034
Neg logit contributions
ercise-0.046
isi-0.045
iable-0.044
ock-0.043
off-0.042
Token it
Token ID340
Feature activation-2.24e-02

Pos logit contributions
ercise+0.010
isi+0.009
ock+0.009
iable+0.009
off+0.009
Neg logit contributions
apy-0.017
 Nick-0.016
 Mam-0.016
 Mick-0.016
 Megan-0.015
Token,
Token ID11
Feature activation+5.43e-02

Pos logit contributions
apy+0.040
 Nick+0.039
 Mam+0.039
 Liz+0.036
 Megan+0.036
Neg logit contributions
ercise-0.040
isi-0.039
iable-0.038
ock-0.038
off-0.036
Token red
Token ID2266
Feature activation+1.38e-02

Pos logit contributions
apy+0.093
 Nick+0.092
 Mam+0.090
 Liz+0.085
 Megan+0.085
Neg logit contributions
ercise-0.091
isi-0.090
iable-0.088
ock-0.088
off-0.083
Token laser
Token ID12855
Feature activation-2.61e-03

Pos logit contributions
apy+0.024
 Nick+0.024
 Mam+0.023
 Liz+0.022
 Megan+0.022
Neg logit contributions
ercise-0.023
isi-0.022
iable-0.022
ock-0.022
off-0.021
Token in
Token ID287
Feature activation+9.23e-02

Pos logit contributions
ercise+0.004
isi+0.004
iable+0.004
ock+0.004
off+0.004
Neg logit contributions
apy-0.005
 Nick-0.004
 Mam-0.004
 Liz-0.004
 Megan-0.004
Token the
Token ID262
Feature activation+1.32e-02

Pos logit contributions
apy+0.196
 Nick+0.179
 Mam+0.175
 ankles+0.170
 Madd+0.167
Neg logit contributions
ock-0.128
isi-0.120
 course-0.114
ercise-0.112
off-0.110
Token living
Token ID2877
Feature activation+1.27e-01

Pos logit contributions
apy+0.023
 Mam+0.023
 Nick+0.023
 Liz+0.022
 Megan+0.021
Neg logit contributions
ercise-0.021
isi-0.021
iable-0.021
ock-0.020
at-0.019
Token room
Token ID2119
Feature activation+6.90e-02

Pos logit contributions
apy+0.209
 Nick+0.188
 Megan+0.188
 Mam+0.187
 Madd+0.187
Neg logit contributions
off-0.225
les-0.218
ock-0.217
ont-0.213
up-0.213
Token.
Token ID13
Feature activation+1.33e-03

Pos logit contributions
apy+0.147
 Nick+0.143
 Madd+0.142
 Mam+0.140
 Mick+0.139
Neg logit contributions
ock-0.083
iable-0.079
up-0.078
off-0.078
at-0.077
Token She
Token ID1375
Feature activation+2.18e-02

Pos logit contributions
apy+0.002
 Nick+0.002
 Mam+0.002
 Liz+0.002
 Megan+0.002
Neg logit contributions
ercise-0.003
isi-0.003
iable-0.003
ock-0.003
off-0.002
Token wanted
Token ID2227
Feature activation-3.77e-02

Pos logit contributions
apy+0.033
 Nick+0.032
 Mam+0.032
 Megan+0.030
 Liz+0.030
Neg logit contributions
ercise-0.041
isi-0.039
iable-0.039
ock-0.038
off-0.037
Token to
Token ID284
Feature activation+6.59e-03

Pos logit contributions
isi+0.065
ercise+0.064
iable+0.063
at+0.062
ock+0.060
Neg logit contributions
 Nick-0.065
 Liz-0.065
apy-0.064
 Mam-0.063
 Mike-0.062
Token a
Token ID257
Feature activation+4.50e-03

Pos logit contributions
isi+0.000
ercise+0.000
ock+0.000
iable+0.000
vious+0.000
Neg logit contributions
apy-0.001
 Nick-0.001
 Mam-0.001
 Mick-0.001
 Liz-0.001
Token big
Token ID1263
Feature activation+8.69e-03

Pos logit contributions
 Nick+0.009
uzz+0.009
apy+0.009
ges+0.009
 Liz+0.008
Neg logit contributions
isi-0.006
ercise-0.006
iable-0.006
 poem-0.006
ock-0.005
Token jar
Token ID17379
Feature activation+9.42e-03

Pos logit contributions
apy+0.016
 Nick+0.016
 Mam+0.015
 Megan+0.015
 Liz+0.015
Neg logit contributions
ercise-0.013
isi-0.013
ock-0.013
iable-0.013
orn-0.012
Token in
Token ID287
Feature activation+8.75e-02

Pos logit contributions
apy+0.014
 Nick+0.013
 Mam+0.013
 holding+0.013
 Liz+0.012
Neg logit contributions
ercise-0.018
isi-0.018
iable-0.017
ock-0.016
off-0.016
Token the
Token ID262
Feature activation+1.17e-02

Pos logit contributions
apy+0.182
 Nick+0.167
 Mick+0.165
 toes+0.163
 ankles+0.162
Neg logit contributions
isi-0.115
ock-0.112
 course-0.111
ercise-0.104
off-0.101
Token living
Token ID2877
Feature activation+1.25e-01

Pos logit contributions
apy+0.020
 Nick+0.020
 Mam+0.020
 Megan+0.019
 Liz+0.019
Neg logit contributions
ercise-0.020
isi-0.019
iable-0.019
ock-0.019
off-0.018
Token room
Token ID2119
Feature activation+6.43e-02

Pos logit contributions
apy+0.198
 Nick+0.183
 Madd+0.179
 Mam+0.179
 Kel+0.178
Neg logit contributions
off-0.227
ercise-0.222
les-0.221
up-0.220
ock-0.213
Token.
Token ID13
Feature activation+1.15e-03

Pos logit contributions
apy+0.136
 Nick+0.131
 Madd+0.129
 Mam+0.129
 Mick+0.128
Neg logit contributions
ock-0.077
up-0.077
off-0.077
iable-0.075
ercise-0.074
Token It
Token ID632
Feature activation-9.99e-04

Pos logit contributions
apy+0.002
 Nick+0.002
 Mam+0.001
 Mick+0.001
uzz+0.001
Neg logit contributions
ercise-0.002
isi-0.002
vious-0.002
iable-0.002
off-0.002
Token had
Token ID550
Feature activation-3.48e-03

Pos logit contributions
ercise+0.002
isi+0.002
iable+0.002
ock+0.002
ches+0.002
Neg logit contributions
apy-0.002
 Nick-0.002
 Mam-0.002
 toes-0.001
 Liz-0.001
Token a
Token ID257
Feature activation+1.43e-02

Pos logit contributions
ercise+0.006
isi+0.005
iable+0.005
ock+0.005
off+0.005
Neg logit contributions
apy-0.006
 Nick-0.006
 Mam-0.006
 Liz-0.006
 Megan-0.006
Token saw
Token ID2497
Feature activation-6.16e-03

Pos logit contributions
apy+0.004
 Nick+0.004
 Mam+0.004
 Liz+0.004
 Megan+0.004
Neg logit contributions
ercise-0.004
isi-0.004
iable-0.004
ock-0.004
off-0.004
Token a
Token ID257
Feature activation+7.52e-03

Pos logit contributions
ercise+0.011
isi+0.010
iable+0.010
ock+0.010
off+0.010
Neg logit contributions
apy-0.010
 Nick-0.010
 Mam-0.010
 Liz-0.010
 Megan-0.009
Token computer
Token ID3644
Feature activation+8.43e-05

Pos logit contributions
 Nick+0.015
apy+0.015
 Megan+0.014
 Liz+0.014
 Mam+0.014
Neg logit contributions
ercise-0.010
isi-0.010
iable-0.010
ock-0.010
orn-0.009
Token in
Token ID287
Feature activation+8.67e-02

Pos logit contributions
apy+0.000
 Nick+0.000
 Mam+0.000
 Liz+0.000
 Megan+0.000
Neg logit contributions
ercise-0.000
isi-0.000
iable-0.000
ock-0.000
off-0.000
Token the
Token ID262
Feature activation+9.67e-03

Pos logit contributions
apy+0.204
 Madd+0.184
 Nick+0.173
sed+0.173
 ankles+0.171
Neg logit contributions
ock-0.108
off-0.096
 course-0.096
isi-0.095
ercise-0.092
Token living
Token ID2877
Feature activation+1.24e-01

Pos logit contributions
 Mam+0.012
 Nick+0.012
apy+0.011
 Liz+0.011
 Megan+0.010
Neg logit contributions
isi-0.021
ercise-0.021
iable-0.020
ock-0.020
at-0.019
Token room
Token ID2119
Feature activation+7.21e-02

Pos logit contributions
apy+0.219
 Madd+0.206
 Kel+0.199
 Nick+0.198
 Mam+0.189
Neg logit contributions
off-0.216
ercise-0.200
up-0.199
les-0.198
ock-0.194
Token and
Token ID290
Feature activation-2.83e-02

Pos logit contributions
apy+0.153
 Madd+0.150
 Nick+0.148
 Mam+0.144
 Kel+0.143
Neg logit contributions
ock-0.089
off-0.086
iable-0.084
at-0.084
up-0.083
Token was
Token ID373
Feature activation+9.04e-03

Pos logit contributions
ercise+0.046
iable+0.044
isi+0.042
up+0.042
ock+0.041
Neg logit contributions
apy-0.050
 Nick-0.047
 Mam-0.047
 spe-0.046
uzz-0.046
Token very
Token ID845
Feature activation+2.48e-02

Pos logit contributions
apy+0.020
 Nick+0.019
 Madd+0.018
 Mick+0.018
ges+0.018
Neg logit contributions
ercise-0.009
iable-0.009
vious-0.009
 exam-0.008
 better-0.008
Token curious
Token ID11040
Feature activation+1.08e-02

Pos logit contributions
 Nick+0.048
ges+0.048
 unison+0.048
 extingu+0.047
 ah+0.045
Neg logit contributions
iable-0.030
up-0.029
ercise-0.029
 important-0.028
vious-0.028
Token a
Token ID257
Feature activation+5.85e-04

Pos logit contributions
isi+0.009
iable+0.009
ock+0.009
ercise+0.009
up+0.008
Neg logit contributions
apy-0.013
 Nick-0.013
 spe-0.013
 Mam-0.012
 ankles-0.012
Token big
Token ID1263
Feature activation+1.28e-02

Pos logit contributions
 Nick+0.001
apy+0.001
 Mam+0.001
uzz+0.001
 Megan+0.001
Neg logit contributions
isi-0.001
iable-0.001
ercise-0.001
ock-0.001
 poem-0.001
Token box
Token ID3091
Feature activation+2.95e-02

Pos logit contributions
apy+0.025
 Nick+0.024
 Mam+0.023
uzz+0.023
 Mick+0.023
Neg logit contributions
ercise-0.018
isi-0.018
ock-0.017
iable-0.017
les-0.016
Token in
Token ID287
Feature activation+8.98e-02

Pos logit contributions
apy+0.052
 Nick+0.051
 Mam+0.050
 Liz+0.047
 Megan+0.047
Neg logit contributions
ercise-0.048
isi-0.048
ock-0.047
iable-0.047
off-0.045
Token the
Token ID262
Feature activation+7.45e-03

Pos logit contributions
apy+0.196
 Nick+0.176
 Mick+0.170
 toes+0.170
sed+0.169
Neg logit contributions
ock-0.114
isi-0.111
off-0.106
 course-0.102
up-0.099
Token living
Token ID2877
Feature activation+1.24e-01

Pos logit contributions
apy+0.012
 Nick+0.012
 Mam+0.011
 Megan+0.011
 Liz+0.011
Neg logit contributions
ercise-0.013
isi-0.013
ock-0.013
iable-0.013
off-0.013
Token room
Token ID2119
Feature activation+6.67e-02

Pos logit contributions
apy+0.234
 Madd+0.215
 Kel+0.209
 Nick+0.206
 Mam+0.200
Neg logit contributions
off-0.205
up-0.195
les-0.191
ock-0.182
ercise-0.179
Token.
Token ID13
Feature activation+1.10e-02

Pos logit contributions
apy+0.146
 Madd+0.143
 Nick+0.142
 Mick+0.139
 Mam+0.138
Neg logit contributions
up-0.075
off-0.073
ock-0.071
iable-0.071
les-0.069
Token It
Token ID632
Feature activation-2.20e-03

Pos logit contributions
apy+0.023
 ah+0.022
 Mick+0.021
 Liz+0.021
 dodging+0.021
Neg logit contributions
vious-0.011
ercise-0.011
off-0.011
isi-0.011
up-0.011
Token had
Token ID550
Feature activation-6.91e-03

Pos logit contributions
ercise+0.004
isi+0.004
iable+0.004
ock+0.004
off+0.004
Neg logit contributions
apy-0.004
 Nick-0.003
 Mam-0.003
 Megan-0.003
 toes-0.003
Token a
Token ID257
Feature activation+1.44e-02

Pos logit contributions
ercise+0.010
isi+0.010
ock+0.010
iable+0.010
off+0.009
Neg logit contributions
apy-0.013
 Nick-0.013
 Mam-0.013
 Mick-0.012
 Megan-0.012
Token a
Token ID257
Feature activation+1.22e-02

Pos logit contributions
ercise+0.011
isi+0.011
iable+0.011
ock+0.011
at+0.010
Neg logit contributions
apy-0.015
 Nick-0.015
 Mam-0.014
 Megan-0.014
 Liz-0.014
Token glimpse
Token ID19350
Feature activation+3.30e-02

Pos logit contributions
 Nick+0.024
apy+0.023
 Megan+0.023
 Mam+0.022
 Liz+0.022
Neg logit contributions
isi-0.016
ercise-0.016
iable-0.016
ock-0.016
 poem-0.016
Token of
Token ID286
Feature activation+5.12e-02

Pos logit contributions
apy+0.065
 Nick+0.064
 Mam+0.063
 Liz+0.060
 Megan+0.060
Neg logit contributions
ercise-0.047
ock-0.047
isi-0.046
iable-0.045
off-0.043
Token something
Token ID1223
Feature activation+2.75e-02

Pos logit contributions
apy+0.110
 Nick+0.105
 Mam+0.103
uzz+0.102
 Mick+0.101
Neg logit contributions
isi-0.060
ock-0.059
ercise-0.057
iable-0.056
 course-0.056
Token furry
Token ID40857
Feature activation+3.41e-02

Pos logit contributions
apy+0.054
 Nick+0.053
 Mam+0.052
 Liz+0.050
 Megan+0.050
Neg logit contributions
iable-0.037
ercise-0.036
ock-0.036
isi-0.035
up-0.033
Token out
Token ID503
Feature activation+1.23e-01

Pos logit contributions
apy+0.065
 Mam+0.064
 Nick+0.063
 Liz+0.059
 Megan+0.059
Neg logit contributions
ercise-0.050
isi-0.050
ock-0.049
les-0.047
orn-0.046
Token of
Token ID286
Feature activation+7.69e-02

Pos logit contributions
apy+0.246
 Nick+0.245
 Mam+0.240
 Megan+0.228
 Mil+0.226
Neg logit contributions
ock-0.168
ercise-0.167
isi-0.166
iable-0.158
off-0.154
Token the
Token ID262
Feature activation+1.63e-02

Pos logit contributions
apy+0.164
 Nick+0.147
 Mam+0.146
 Mick+0.142
 Mil+0.142
Neg logit contributions
 course-0.104
isi-0.102
ock-0.101
ercise-0.095
iable-0.092
Token corner
Token ID5228
Feature activation+7.07e-02

Pos logit contributions
apy+0.025
 Nick+0.025
 Mam+0.024
 Liz+0.023
 Megan+0.023
Neg logit contributions
ercise-0.030
isi-0.030
iable-0.029
ock-0.029
off-0.028
Token of
Token ID286
Feature activation+7.17e-02

Pos logit contributions
apy+0.140
 Nick+0.137
 Mam+0.134
 Mick+0.128
 Madd+0.126
Neg logit contributions
ock-0.099
isi-0.096
ercise-0.095
off-0.094
iable-0.093
Token her
Token ID607
Feature activation+5.38e-02

Pos logit contributions
apy+0.162
 Nick+0.142
 Mam+0.139
 ankles+0.139
 toes+0.138
Neg logit contributions
ock-0.091
isi-0.090
 course-0.087
ty-0.080
orn-0.077
Token a
Token ID257
Feature activation+2.66e-03

Pos logit contributions
ercise+0.015
isi+0.015
iable+0.015
ock+0.015
off+0.014
Neg logit contributions
apy-0.015
 Nick-0.015
 Mam-0.015
 Liz-0.014
 Megan-0.014
Token big
Token ID1263
Feature activation+1.11e-02

Pos logit contributions
 Nick+0.005
apy+0.005
 Megan+0.005
 Mam+0.005
 Liz+0.005
Neg logit contributions
ercise-0.003
isi-0.003
iable-0.003
ock-0.003
orn-0.003
Token box
Token ID3091
Feature activation+2.89e-02

Pos logit contributions
apy+0.020
 Nick+0.020
 Mam+0.019
 Megan+0.019
 Liz+0.018
Neg logit contributions
ercise-0.018
ock-0.017
isi-0.017
iable-0.017
les-0.016
Token in
Token ID287
Feature activation+8.65e-02

Pos logit contributions
apy+0.045
 Nick+0.044
 Mam+0.043
 Liz+0.041
 Megan+0.040
Neg logit contributions
ercise-0.054
isi-0.053
iable-0.052
ock-0.051
off-0.049
Token the
Token ID262
Feature activation+8.77e-03

Pos logit contributions
apy+0.165
 Nick+0.152
 Mam+0.145
 Mick+0.141
 toes+0.140
Neg logit contributions
ock-0.137
isi-0.134
ercise-0.128
off-0.127
iable-0.126
Token living
Token ID2877
Feature activation+1.22e-01

Pos logit contributions
apy+0.013
 Nick+0.013
 Mam+0.012
 Liz+0.012
 Megan+0.012
Neg logit contributions
ercise-0.017
isi-0.017
iable-0.017
ock-0.017
off-0.016
Token room
Token ID2119
Feature activation+6.37e-02

Pos logit contributions
apy+0.204
 Nick+0.189
 Madd+0.184
 Kel+0.182
 Mam+0.179
Neg logit contributions
off-0.219
up-0.210
ock-0.207
les-0.206
ercise-0.204
Token.
Token ID13
Feature activation-3.06e-03

Pos logit contributions
apy+0.131
 Nick+0.129
 Mam+0.124
 Madd+0.124
 Mick+0.122
Neg logit contributions
ock-0.082
iable-0.080
off-0.080
isi-0.078
ercise-0.078
Token "
Token ID366
Feature activation+9.14e-03

Pos logit contributions
ercise+0.004
isi+0.004
off+0.004
iable+0.004
ock+0.004
Neg logit contributions
apy-0.006
 Nick-0.006
 Mam-0.005
 Mick-0.005
 spe-0.005
TokenWhat
Token ID2061
Feature activation+2.21e-02

Pos logit contributions
apy+0.014
 Nick+0.014
 Mam+0.014
 Liz+0.013
 Megan+0.013
Neg logit contributions
ercise-0.017
isi-0.017
ock-0.016
iable-0.016
off-0.016
Token's
Token ID338
Feature activation+3.01e-02

Pos logit contributions
apy+0.052
 Nick+0.051
 Mam+0.051
 Megan+0.048
 Liz+0.048
Neg logit contributions
ercise-0.023
isi-0.022
iable-0.022
ock-0.022
off-0.020
Token when
Token ID618
Feature activation+3.46e-02

Pos logit contributions
ercise+0.038
isi+0.038
iable+0.037
ock+0.035
off+0.034
Neg logit contributions
apy-0.041
 Nick-0.041
 Mam-0.040
 Liz-0.037
 Mike-0.037
Token he
Token ID339
Feature activation-9.05e-03

Pos logit contributions
 Mam+0.070
 Megan+0.069
 Nick+0.069
uzz+0.069
 extingu+0.068
Neg logit contributions
ercise-0.042
iable-0.038
ock-0.036
isi-0.036
orn-0.035
Token spotted
Token ID13489
Feature activation-5.08e-03

Pos logit contributions
ercise+0.018
isi+0.018
iable+0.017
ock+0.017
off+0.017
Neg logit contributions
apy-0.013
 Nick-0.013
 Mam-0.012
 Liz-0.012
 Megan-0.012
Token something
Token ID1223
Feature activation+2.65e-02

Pos logit contributions
ercise+0.008
isi+0.008
ock+0.008
iable+0.008
off+0.007
Neg logit contributions
apy-0.009
 Nick-0.009
 Mam-0.009
 Megan-0.008
 Liz-0.008
Token far
Token ID1290
Feature activation+2.30e-02

Pos logit contributions
apy+0.051
 Nick+0.051
 Mam+0.050
 Megan+0.050
 Liz+0.049
Neg logit contributions
ercise-0.035
iable-0.034
ock-0.034
isi-0.033
up-0.031
Token out
Token ID503
Feature activation+1.22e-01

Pos logit contributions
 Nick+0.043
apy+0.042
 Mike+0.041
 Mam+0.041
 spe+0.040
Neg logit contributions
isi-0.034
ercise-0.033
iable-0.032
at-0.030
off-0.028
Token in
Token ID287
Feature activation+1.05e-01

Pos logit contributions
apy+0.254
 Nick+0.251
 Mam+0.249
 Megan+0.239
 Liz+0.234
Neg logit contributions
ock-0.159
ercise-0.153
isi-0.149
les-0.145
off-0.144
Token the
Token ID262
Feature activation+2.66e-02

Pos logit contributions
apy+0.198
 Nick+0.179
 Mam+0.176
 toes+0.172
 Liz+0.170
Neg logit contributions
ock-0.164
isi-0.158
ercise-0.157
off-0.154
vious-0.152
Token water
Token ID1660
Feature activation+3.38e-02

Pos logit contributions
 Nick+0.039
 Mam+0.038
apy+0.037
 Mick+0.035
 Mil+0.035
Neg logit contributions
isi-0.053
ercise-0.052
iable-0.051
ock-0.048
off-0.046
Token.
Token ID13
Feature activation+2.35e-03

Pos logit contributions
apy+0.063
 Nick+0.060
 Mam+0.059
 Liz+0.058
 Megan+0.057
Neg logit contributions
ock-0.053
ercise-0.052
iable-0.050
isi-0.050
off-0.049
Token He
Token ID679
Feature activation+1.69e-02

Pos logit contributions
apy+0.004
 Nick+0.004
 Mam+0.004
 Megan+0.004
 Mil+0.004
Neg logit contributions
ercise-0.004
isi-0.004
iable-0.004
ock-0.004
off-0.004
Token a
Token ID257
Feature activation+3.40e-03

Pos logit contributions
ercise+0.014
ock+0.013
isi+0.013
iable+0.013
up+0.012
Neg logit contributions
apy-0.019
 Nick-0.019
 Mam-0.018
 Megan-0.018
 Liz-0.017
Token big
Token ID1263
Feature activation+1.20e-02

Pos logit contributions
 Nick+0.007
apy+0.007
 Mam+0.006
 Megan+0.006
 Liz+0.006
Neg logit contributions
ercise-0.005
iable-0.005
isi-0.005
ock-0.004
orn-0.004
Token box
Token ID3091
Feature activation+3.26e-02

Pos logit contributions
apy+0.022
 Nick+0.021
 Mam+0.021
 Megan+0.020
 Liz+0.020
Neg logit contributions
ercise-0.019
isi-0.018
iable-0.018
ock-0.018
off-0.016
Token in
Token ID287
Feature activation+8.74e-02

Pos logit contributions
apy+0.057
 Nick+0.057
 Mam+0.055
 Megan+0.053
 Liz+0.053
Neg logit contributions
ercise-0.053
isi-0.052
ock-0.051
iable-0.051
off-0.049
Token the
Token ID262
Feature activation+1.15e-02

Pos logit contributions
apy+0.203
sed+0.182
 Nick+0.176
 Madd+0.174
 ah+0.174
Neg logit contributions
ock-0.104
off-0.095
 course-0.093
isi-0.090
ercise-0.087
Token living
Token ID2877
Feature activation+1.22e-01

Pos logit contributions
apy+0.017
 Nick+0.017
 Mam+0.017
 Liz+0.016
 Megan+0.016
Neg logit contributions
ercise-0.022
isi-0.022
iable-0.021
ock-0.021
off-0.020
Token room
Token ID2119
Feature activation+7.06e-02

Pos logit contributions
apy+0.211
 Madd+0.195
 Nick+0.194
 Kel+0.191
 Mam+0.184
Neg logit contributions
off-0.212
up-0.203
les-0.198
ercise-0.195
ock-0.192
Token.
Token ID13
Feature activation+2.34e-03

Pos logit contributions
apy+0.158
 Madd+0.154
 Nick+0.153
 Mick+0.149
 Mam+0.147
Neg logit contributions
up-0.074
ock-0.074
off-0.071
iable-0.070
les-0.068
Token It
Token ID632
Feature activation+9.83e-04

Pos logit contributions
 spe+0.004
 ah+0.004
apy+0.004
 extingu+0.004
 dodging+0.004
Neg logit contributions
ercise-0.003
off-0.003
les-0.003
um-0.003
vious-0.003
Token had
Token ID550
Feature activation-5.35e-03

Pos logit contributions
apy+0.002
 Nick+0.002
 toes+0.002
 ankles+0.002
 Mam+0.002
Neg logit contributions
ercise-0.001
isi-0.001
ches-0.001
ty-0.001
up-0.001
Token a
Token ID257
Feature activation+1.28e-02

Pos logit contributions
ercise+0.007
isi+0.007
ock+0.007
iable+0.007
up+0.007
Neg logit contributions
apy-0.011
 Nick-0.011
 Mam-0.010
 Mick-0.010
 Madd-0.010
Token cried
Token ID16896
Feature activation+4.85e-02

Pos logit contributions
apy+0.030
 Nick+0.029
 Mam+0.028
 Megan+0.027
 Liz+0.027
Neg logit contributions
ercise-0.028
isi-0.028
iable-0.027
ock-0.027
off-0.026
Token,
Token ID11
Feature activation+6.13e-02

Pos logit contributions
apy+0.092
 Nick+0.091
 Mam+0.086
 Megan+0.085
 ah+0.081
Neg logit contributions
ock-0.070
isi-0.069
ercise-0.069
iable-0.068
vious-0.063
Token dropping
Token ID12047
Feature activation+8.07e-03

Pos logit contributions
apy+0.106
 Nick+0.100
uzz+0.099
 Liz+0.098
obby+0.097
Neg logit contributions
iable-0.086
ty-0.085
 up-0.084
's-0.079
ches-0.078
Token the
Token ID262
Feature activation-5.09e-03

Pos logit contributions
apy+0.016
 Nick+0.015
 haven+0.015
 ago+0.014
 gasped+0.014
Neg logit contributions
ercise-0.010
ock-0.009
isi-0.009
vious-0.009
up-0.009
Token magn
Token ID7842
Feature activation+5.92e-02

Pos logit contributions
ercise+0.009
isi+0.009
iable+0.009
ock+0.009
off+0.009
Neg logit contributions
apy-0.008
 Nick-0.008
 Mam-0.008
 Liz-0.007
 Megan-0.007
Tokenifying
Token ID4035
Feature activation+1.22e-01

Pos logit contributions
apy+0.045
 Nick+0.044
 Mam+0.041
 Liz+0.036
 Megan+0.036
Neg logit contributions
ercise-0.158
isi-0.155
iable-0.154
ock-0.152
off-0.148
Token glass
Token ID5405
Feature activation+7.95e-03

Pos logit contributions
apy+0.160
 Nick+0.157
 Mam+0.153
 Megan+0.141
 Liz+0.141
Neg logit contributions
isi-0.245
ercise-0.244
ock-0.242
iable-0.234
off-0.233
Token.
Token ID13
Feature activation+3.22e-02

Pos logit contributions
apy+0.015
 Nick+0.014
 Mam+0.014
 Liz+0.013
 Megan+0.013
Neg logit contributions
ock-0.012
ercise-0.012
isi-0.012
iable-0.012
off-0.011
Token
Token ID198
Feature activation+5.76e-03

Pos logit contributions
 spe+0.054
apy+0.054
 toes+0.053
 Esk+0.053
 Nick+0.051
Neg logit contributions
isi-0.046
iable-0.046
ercise-0.044
orting-0.042
ometime-0.041
Token
Token ID198
Feature activation+3.46e-03

Pos logit contributions
 Nick+0.010
apy+0.010
 spe+0.010
 Mam+0.010
 toes+0.010
Neg logit contributions
isi-0.009
ercise-0.009
iable-0.009
ock-0.008
off-0.008
Token"
Token ID1
Feature activation+2.60e-02

Pos logit contributions
 Nick+0.008
 Mam+0.008
apy+0.007
 spe+0.007
 Madd+0.007
Neg logit contributions
ercise-0.004
iable-0.004
isi-0.004
off-0.004
up-0.004
Token a
Token ID257
Feature activation+4.06e-03

Pos logit contributions
ercise+0.029
isi+0.028
iable+0.028
ock+0.028
off+0.026
Neg logit contributions
apy-0.034
 Nick-0.034
 Mam-0.033
 Megan-0.032
 Liz-0.032
Token big
Token ID1263
Feature activation+1.02e-02

Pos logit contributions
apy+0.008
 Nick+0.008
 Mam+0.008
 Liz+0.007
 Megan+0.007
Neg logit contributions
ercise-0.006
isi-0.006
ock-0.006
iable-0.006
off-0.006
Token screen
Token ID3159
Feature activation+1.21e-02

Pos logit contributions
apy+0.018
 Nick+0.018
 Mam+0.017
 Liz+0.017
 Megan+0.017
Neg logit contributions
ercise-0.016
isi-0.016
iable-0.016
ock-0.016
off-0.015
Token in
Token ID287
Feature activation+8.57e-02

Pos logit contributions
apy+0.022
 Nick+0.021
 Mam+0.021
 Liz+0.020
 Megan+0.020
Neg logit contributions
ercise-0.020
isi-0.019
iable-0.019
ock-0.019
off-0.018
Token the
Token ID262
Feature activation+8.01e-03

Pos logit contributions
apy+0.180
 Madd+0.169
 Nick+0.169
 ankles+0.165
 Mil+0.164
Neg logit contributions
ock-0.106
ercise-0.102
 course-0.100
off-0.097
isi-0.097
Token living
Token ID2877
Feature activation+1.22e-01

Pos logit contributions
 Mam+0.012
 Nick+0.012
apy+0.012
 Liz+0.011
 Megan+0.011
Neg logit contributions
isi-0.015
ercise-0.015
iable-0.015
ock-0.015
at-0.014
Token room
Token ID2119
Feature activation+6.40e-02

Pos logit contributions
apy+0.214
 Madd+0.201
 Kel+0.196
 Nick+0.193
 Megan+0.190
Neg logit contributions
off-0.213
les-0.200
up-0.197
ercise-0.193
ont-0.193
Token.
Token ID13
Feature activation-6.48e-04

Pos logit contributions
apy+0.128
 Nick+0.123
 Madd+0.120
 Mam+0.119
 Megan+0.117
Neg logit contributions
ock-0.087
iable-0.086
ercise-0.085
off-0.083
up-0.082
Token He
Token ID679
Feature activation+1.16e-02

Pos logit contributions
ercise+0.001
off+0.001
iable+0.001
ometime+0.001
isi+0.001
Neg logit contributions
apy-0.001
 spe-0.001
 ah-0.001
uzz-0.001
 Madd-0.001
Token was
Token ID373
Feature activation+7.53e-03

Pos logit contributions
apy+0.019
 Nick+0.019
 Mam+0.018
 Megan+0.018
 Liz+0.017
Neg logit contributions
ercise-0.020
iable-0.019
isi-0.019
ock-0.019
up-0.018
Token curious
Token ID11040
Feature activation+6.54e-03

Pos logit contributions
apy+0.017
 Nick+0.016
 ankles+0.015
 Mick+0.015
 Megan+0.015
Neg logit contributions
iable-0.009
ercise-0.008
isi-0.007
vious-0.007
ock-0.007
Token a
Token ID257
Feature activation+1.78e-03

Pos logit contributions
ercise+0.019
isi+0.019
iable+0.018
ock+0.018
off+0.017
Neg logit contributions
apy-0.021
 Nick-0.021
 Mam-0.020
 Megan-0.019
 Liz-0.019
Token big
Token ID1263
Feature activation+1.11e-02

Pos logit contributions
 Nick+0.004
apy+0.004
 Megan+0.003
 Mam+0.003
 Liz+0.003
Neg logit contributions
ercise-0.002
isi-0.002
iable-0.002
ock-0.002
orn-0.002
Token box
Token ID3091
Feature activation+2.76e-02

Pos logit contributions
apy+0.020
 Nick+0.020
 Mam+0.019
 Megan+0.019
 Liz+0.018
Neg logit contributions
ercise-0.017
isi-0.017
ock-0.017
iable-0.017
off-0.015
Token in
Token ID287
Feature activation+8.62e-02

Pos logit contributions
apy+0.043
 Nick+0.042
 Mam+0.041
 Liz+0.039
 Megan+0.039
Neg logit contributions
ercise-0.051
isi-0.050
iable-0.049
ock-0.048
off-0.046
Token the
Token ID262
Feature activation+7.77e-03

Pos logit contributions
apy+0.191
 Madd+0.168
 Nick+0.166
 toes+0.163
 Mam+0.162
Neg logit contributions
ock-0.114
isi-0.104
off-0.102
 course-0.101
ercise-0.099
Token living
Token ID2877
Feature activation+1.21e-01

Pos logit contributions
apy+0.011
 Nick+0.011
 Mam+0.011
 Liz+0.010
 Megan+0.010
Neg logit contributions
ercise-0.015
isi-0.015
iable-0.015
ock-0.015
off-0.014
Token room
Token ID2119
Feature activation+6.48e-02

Pos logit contributions
apy+0.211
 Madd+0.195
 Nick+0.194
 Kel+0.192
 Mam+0.187
Neg logit contributions
off-0.211
up-0.200
les-0.198
ercise-0.194
ock-0.194
Token.
Token ID13
Feature activation+1.32e-03

Pos logit contributions
apy+0.135
 Nick+0.131
 Madd+0.131
 Mam+0.129
 Kel+0.126
Neg logit contributions
ock-0.082
off-0.079
iable-0.079
ercise-0.078
at-0.077
Token He
Token ID679
Feature activation+1.60e-02

Pos logit contributions
apy+0.002
 Nick+0.002
 Mam+0.002
 Madd+0.002
 Mick+0.002
Neg logit contributions
ercise-0.002
isi-0.002
iable-0.002
off-0.002
ock-0.002
Token was
Token ID373
Feature activation+1.04e-02

Pos logit contributions
apy+0.021
 Nick+0.021
 Mam+0.020
 Liz+0.019
 Megan+0.019
Neg logit contributions
ercise-0.033
isi-0.033
iable-0.033
ock-0.032
off-0.031
Token very
Token ID845
Feature activation+2.50e-02

Pos logit contributions
apy+0.022
 Nick+0.020
 Mick+0.019
 ah+0.019
ges+0.019
Neg logit contributions
vious-0.012
iable-0.012
 up-0.012
 better-0.011
ercise-0.011
Token.
Token ID13
Feature activation+1.30e-02

Pos logit contributions
ock+0.008
ercise+0.008
off+0.008
les+0.008
up+0.007
Neg logit contributions
apy-0.014
 Mam-0.014
 Nick-0.013
 Mick-0.013
 Megan-0.013
Token Suddenly
Token ID24975
Feature activation+9.47e-03

Pos logit contributions
apy+0.021
 Nick+0.020
 Mam+0.020
 Mick+0.019
 spe+0.019
Neg logit contributions
ercise-0.023
isi-0.022
off-0.021
iable-0.021
vious-0.021
Token a
Token ID257
Feature activation+1.04e-02

Pos logit contributions
apy+0.021
 Mam+0.021
 Nick+0.020
uzz+0.020
 Mick+0.020
Neg logit contributions
ercise-0.009
isi-0.009
iable-0.009
up-0.009
ock-0.009
Token voice
Token ID3809
Feature activation+5.11e-02

Pos logit contributions
 Nick+0.021
uzz+0.020
apy+0.020
 Megan+0.020
 Mam+0.020
Neg logit contributions
isi-0.014
ercise-0.013
ock-0.013
up-0.013
iable-0.013
Token shouted
Token ID17293
Feature activation+3.56e-02

Pos logit contributions
apy+0.094
 Nick+0.091
 Mam+0.090
 toes+0.086
 Megan+0.085
Neg logit contributions
ock-0.078
isi-0.078
ercise-0.077
iable-0.075
up-0.072
Token out
Token ID503
Feature activation+1.21e-01

Pos logit contributions
apy+0.083
 Nick+0.077
 Mam+0.076
 spe+0.076
 Mick+0.073
Neg logit contributions
isi-0.037
ercise-0.036
iable-0.034
ock-0.034
up-0.033
Token:
Token ID25
Feature activation+5.84e-02

Pos logit contributions
 Nick+0.274
apy+0.271
 Mam+0.266
 ankles+0.265
 Mick+0.264
Neg logit contributions
isi-0.105
ercise-0.097
ock-0.096
que-0.093
ly-0.093
Token "
Token ID366
Feature activation+2.94e-02

Pos logit contributions
 toes+0.095
apy+0.095
 bedrooms+0.090
 ankles+0.089
 shovel+0.085
Neg logit contributions
isi-0.089
iable-0.089
ercise-0.088
 story-0.082
que-0.079
TokenI
Token ID40
Feature activation+3.21e-02

Pos logit contributions
apy+0.050
 Nick+0.049
 Mam+0.048
 Megan+0.046
 Liz+0.046
Neg logit contributions
ercise-0.050
isi-0.049
iable-0.049
ock-0.048
off-0.046
Token want
Token ID765
Feature activation-2.79e-02

Pos logit contributions
apy+0.052
 Nick+0.050
 Mam+0.049
 toes+0.047
 Megan+0.047
Neg logit contributions
ercise-0.056
iable-0.054
vious-0.054
isi-0.054
ock-0.054
Token that
Token ID326
Feature activation-6.63e-03

Pos logit contributions
isi+0.043
ercise+0.043
iable+0.042
at+0.042
ock+0.040
Neg logit contributions
 Nick-0.052
 Mam-0.051
 Liz-0.049
apy-0.049
 Mike-0.049
Token bedroom
Token ID14043
Feature activation+4.67e-02

Pos logit contributions
 Nick+0.053
apy+0.052
 Megan+0.049
 Mike+0.049
 ah+0.048
Neg logit contributions
ercise-0.059
off-0.056
iable-0.055
isi-0.054
up-0.054
Token.
Token ID13
Feature activation+2.14e-03

Pos logit contributions
apy+0.096
 Nick+0.092
 Madd+0.088
 Mam+0.088
 Mick+0.086
Neg logit contributions
ock-0.062
iable-0.061
ercise-0.060
up-0.059
isi-0.059
Token Suddenly
Token ID24975
Feature activation-3.36e-04

Pos logit contributions
apy+0.004
 spe+0.004
 ah+0.004
 Mick+0.004
 extingu+0.004
Neg logit contributions
ercise-0.003
isi-0.003
off-0.003
ometime-0.003
iable-0.003
Token,
Token ID11
Feature activation+7.99e-03

Pos logit contributions
ercise+0.000
isi+0.000
iable+0.000
ock+0.000
up+0.000
Neg logit contributions
 Nick-0.001
apy-0.001
 Mam-0.001
 Mick-0.001
uzz-0.001
Token something
Token ID1223
Feature activation+4.17e-02

Pos logit contributions
 ankles+0.017
 Nick+0.016
 Mick+0.016
 Mam+0.016
 spe+0.016
Neg logit contributions
ercise-0.008
isi-0.008
iable-0.008
ock-0.008
vious-0.008
Token out
Token ID503
Feature activation+1.21e-01

Pos logit contributions
 Nick+0.079
 Mam+0.077
apy+0.075
 Megan+0.074
uzz+0.074
Neg logit contributions
ercise-0.061
isi-0.059
ock-0.058
iable-0.058
up-0.055
Token of
Token ID286
Feature activation+6.94e-02

Pos logit contributions
apy+0.235
 Nick+0.235
 Mam+0.231
 Megan+0.218
 ankles+0.217
Neg logit contributions
ercise-0.168
ock-0.168
isi-0.167
iable-0.159
off-0.156
Token the
Token ID262
Feature activation+2.37e-03

Pos logit contributions
apy+0.134
 Nick+0.126
 ankles+0.125
 Mam+0.124
bers+0.121
Neg logit contributions
ock-0.102
 course-0.096
isi-0.095
ercise-0.091
iable-0.090
Token window
Token ID4324
Feature activation+7.94e-02

Pos logit contributions
apy+0.003
 Nick+0.003
 Mam+0.003
 Megan+0.003
 Liz+0.003
Neg logit contributions
ercise-0.005
isi-0.005
ock-0.005
iable-0.005
off-0.005
Token caught
Token ID4978
Feature activation+2.48e-02

Pos logit contributions
 Nick+0.140
apy+0.134
 Mam+0.132
uzz+0.128
 Megan+0.128
Neg logit contributions
ock-0.121
up-0.121
les-0.118
ercise-0.118
isi-0.117
Token her
Token ID607
Feature activation+4.80e-02

Pos logit contributions
apy+0.048
 Nick+0.046
 Mam+0.045
 Liz+0.043
 Megan+0.043
Neg logit contributions
ock-0.037
isi-0.037
ercise-0.037
iable-0.036
at-0.034
Token a
Token ID257
Feature activation+1.94e-02

Pos logit contributions
ercise+0.005
isi+0.005
iable+0.005
ock+0.005
off+0.005
Neg logit contributions
apy-0.006
 Nick-0.006
 Mam-0.006
 Megan-0.005
 Liz-0.005
Token fake
Token ID8390
Feature activation+2.06e-02

Pos logit contributions
 Nick+0.037
apy+0.037
 Mam+0.035
 Megan+0.035
 Liz+0.034
Neg logit contributions
ercise-0.029
isi-0.028
iable-0.028
ock-0.027
off-0.025
Token plant
Token ID4618
Feature activation+2.84e-03

Pos logit contributions
apy+0.036
 Nick+0.035
 Mam+0.035
 Liz+0.033
 Megan+0.033
Neg logit contributions
ercise-0.034
isi-0.033
iable-0.033
ock-0.033
off-0.031
Token in
Token ID287
Feature activation+8.96e-02

Pos logit contributions
apy+0.006
 Nick+0.006
 Mam+0.005
 Liz+0.005
 Megan+0.005
Neg logit contributions
ercise-0.004
isi-0.004
iable-0.004
ock-0.004
off-0.004
Token the
Token ID262
Feature activation+1.11e-02

Pos logit contributions
apy+0.185
 Nick+0.182
 ankles+0.175
 Mick+0.173
 Esk+0.173
Neg logit contributions
isi-0.105
ercise-0.100
ock-0.100
 course-0.095
orn-0.095
Token living
Token ID2877
Feature activation+1.21e-01

Pos logit contributions
apy+0.017
 Nick+0.016
 Mam+0.016
 Liz+0.015
 Megan+0.015
Neg logit contributions
ercise-0.021
isi-0.021
iable-0.021
ock-0.020
off-0.020
Token room
Token ID2119
Feature activation+6.31e-02

Pos logit contributions
apy+0.201
 Nick+0.190
 Mam+0.177
 Madd+0.176
 Kel+0.175
Neg logit contributions
off-0.212
up-0.208
les-0.208
ercise-0.201
orn-0.196
Token.
Token ID13
Feature activation-3.99e-03

Pos logit contributions
apy+0.127
 Nick+0.123
 Mam+0.120
 Madd+0.116
 Mick+0.116
Neg logit contributions
iable-0.085
ock-0.084
isi-0.083
ercise-0.082
up-0.080
Token Lily
Token ID20037
Feature activation-7.33e-03

Pos logit contributions
ercise+0.007
iable+0.007
isi+0.007
off+0.006
vious+0.006
Neg logit contributions
apy-0.006
 Nick-0.006
 Mam-0.006
 Mick-0.006
 toes-0.006
Token didn
Token ID1422
Feature activation-4.09e-02

Pos logit contributions
ercise+0.013
isi+0.013
iable+0.012
ock+0.012
off+0.012
Neg logit contributions
apy-0.012
 Nick-0.012
 Mam-0.012
 Liz-0.011
 Megan-0.011
Token't
Token ID470
Feature activation-2.14e-02

Pos logit contributions
ercise+0.075
isi+0.067
ock+0.065
iable+0.065
les+0.064
Neg logit contributions
apy-0.073
 Nick-0.069
 Mam-0.069
 Liz-0.066
 Megan-0.064
Token was
Token ID373
Feature activation+2.39e-02

Pos logit contributions
 Nick+0.007
 Mam+0.007
apy+0.007
 toes+0.006
 Mick+0.006
Neg logit contributions
ercise-0.007
isi-0.007
ock-0.007
ches-0.007
iable-0.007
Token the
Token ID262
Feature activation+2.44e-02

Pos logit contributions
apy+0.053
 Nick+0.051
days+0.050
 ah+0.049
obby+0.049
Neg logit contributions
 better-0.024
isi-0.024
ock-0.023
ty-0.023
ercise-0.022
Token television
Token ID5581
Feature activation+2.78e-02

Pos logit contributions
apy+0.044
 Nick+0.044
 Mam+0.044
 Megan+0.041
 Liz+0.041
Neg logit contributions
ercise-0.039
isi-0.037
iable-0.037
ock-0.037
off-0.035
Token in
Token ID287
Feature activation+9.47e-02

Pos logit contributions
 Mam+0.054
 Nick+0.054
uzz+0.053
apy+0.053
 Madd+0.053
Neg logit contributions
ock-0.038
iable-0.036
les-0.036
ercise-0.035
ches-0.035
Token the
Token ID262
Feature activation+1.39e-02

Pos logit contributions
apy+0.195
 ankles+0.180
bers+0.180
 Mam+0.178
 Madd+0.177
Neg logit contributions
 course-0.117
ock-0.116
isi-0.103
off-0.098
ty-0.096
Token living
Token ID2877
Feature activation+1.21e-01

Pos logit contributions
apy+0.025
 Nick+0.024
 Mam+0.023
 Liz+0.022
 Megan+0.022
Neg logit contributions
ercise-0.023
isi-0.023
ock-0.022
iable-0.022
off-0.021
Token room
Token ID2119
Feature activation+6.45e-02

Pos logit contributions
apy+0.212
 Madd+0.204
 Kel+0.202
 Mam+0.192
 Nick+0.191
Neg logit contributions
off-0.205
les-0.201
up-0.198
ont-0.192
ock-0.188
Token.
Token ID13
Feature activation+1.51e-02

Pos logit contributions
apy+0.143
 Madd+0.139
 Mam+0.137
 Nick+0.134
 Kel+0.133
Neg logit contributions
ock-0.071
les-0.070
up-0.070
iable-0.067
ty-0.065
Token It
Token ID632
Feature activation+4.05e-03

Pos logit contributions
 toes+0.031
 Kel+0.031
 bedrooms+0.030
 spe+0.030
 sweating+0.030
Neg logit contributions
ercise-0.014
vious-0.013
isi-0.013
orting-0.013
ometime-0.012
Token was
Token ID373
Feature activation+2.43e-02

Pos logit contributions
 Mam+0.008
 Nick+0.007
apy+0.007
 toes+0.007
uzz+0.007
Neg logit contributions
ches-0.006
ercise-0.006
ock-0.005
isi-0.005
ty-0.005
Token on
Token ID319
Feature activation+3.64e-02

Pos logit contributions
 Nick+0.050
apy+0.050
 Madd+0.048
 Mick+0.047
 Mam+0.047
Neg logit contributions
ercise-0.026
ock-0.026
 better-0.025
 poems-0.025
isi-0.025
Token the
Token ID262
Feature activation+2.44e-03

Pos logit contributions
apy+0.000
 Nick+0.000
 Mam+0.000
 Mick+0.000
 Megan+0.000
Neg logit contributions
ercise-0.000
ock-0.000
iable-0.000
isi-0.000
off-0.000
Token rock
Token ID3881
Feature activation-6.85e-03

Pos logit contributions
apy+0.005
 Nick+0.005
 Mam+0.005
 Liz+0.005
 Megan+0.005
Neg logit contributions
ercise-0.003
isi-0.003
ock-0.003
iable-0.003
off-0.003
Token was
Token ID373
Feature activation+2.81e-02

Pos logit contributions
ercise+0.013
isi+0.013
iable+0.012
ock+0.012
off+0.012
Neg logit contributions
apy-0.010
 Nick-0.010
 Mam-0.010
 Megan-0.009
 Liz-0.009
Token actually
Token ID1682
Feature activation+3.77e-02

Pos logit contributions
apy+0.055
 Nick+0.055
 Mam+0.053
 Megan+0.051
 Mick+0.050
Neg logit contributions
ercise-0.040
iable-0.039
isi-0.038
ock-0.038
at-0.035
Token a
Token ID257
Feature activation+3.60e-02

Pos logit contributions
apy+0.078
 Nick+0.075
 Mam+0.075
 ankles+0.071
 Mick+0.070
Neg logit contributions
ercise-0.049
iable-0.048
ock-0.047
ty-0.046
isi-0.045
Token living
Token ID2877
Feature activation+1.21e-01

Pos logit contributions
apy+0.071
 Nick+0.070
 Megan+0.067
 Mam+0.067
 Liz+0.066
Neg logit contributions
ercise-0.050
iable-0.048
isi-0.048
ock-0.047
orn-0.045
Token creature
Token ID7185
Feature activation+1.86e-02

Pos logit contributions
apy+0.238
 Kel+0.224
 Megan+0.216
 Liz+0.213
 Nick+0.209
Neg logit contributions
orn-0.176
ock-0.172
les-0.168
vious-0.166
off-0.165
Token called
Token ID1444
Feature activation+5.80e-02

Pos logit contributions
apy+0.039
 Mam+0.038
 Nick+0.037
 Megan+0.036
 Liz+0.035
Neg logit contributions
ercise-0.023
ock-0.023
isi-0.023
iable-0.023
ches-0.022
Token a
Token ID257
Feature activation+1.88e-02

Pos logit contributions
apy+0.111
 Mam+0.101
 Nick+0.100
 Megan+0.097
 ankles+0.095
Neg logit contributions
ercise-0.087
isi-0.085
ock-0.084
iable-0.082
off-0.080
Token Rock
Token ID4631
Feature activation+2.21e-02

Pos logit contributions
apy+0.037
 Nick+0.036
 Megan+0.035
 Mam+0.034
 Liz+0.034
Neg logit contributions
ercise-0.026
isi-0.026
ock-0.025
iable-0.025
orn-0.024
Token Monster
Token ID12635
Feature activation+3.67e-02

Pos logit contributions
apy+0.044
 Mam+0.041
 Nick+0.039
 Megan+0.038
 Liz+0.038
Neg logit contributions
ock-0.033
ercise-0.032
isi-0.031
ches-0.031
les-0.031
Token a
Token ID257
Feature activation-2.41e-03

Pos logit contributions
ercise+0.017
iable+0.017
ock+0.016
isi+0.016
up+0.015
Neg logit contributions
 Nick-0.025
apy-0.025
 Mam-0.025
 Megan-0.024
 Mick-0.023
Token big
Token ID1263
Feature activation+1.11e-02

Pos logit contributions
ercise+0.003
isi+0.003
iable+0.003
ock+0.003
off+0.003
Neg logit contributions
apy-0.005
 Nick-0.005
 Mam-0.005
 Megan-0.004
 Liz-0.004
Token box
Token ID3091
Feature activation+2.73e-02

Pos logit contributions
apy+0.021
 Nick+0.020
 Mam+0.020
 Megan+0.019
 Liz+0.019
Neg logit contributions
ercise-0.017
isi-0.017
iable-0.017
ock-0.016
off-0.015
Token in
Token ID287
Feature activation+8.77e-02

Pos logit contributions
apy+0.047
 Nick+0.046
 Mam+0.045
 Liz+0.042
 Megan+0.042
Neg logit contributions
ercise-0.046
isi-0.045
ock-0.045
iable-0.045
off-0.042
Token the
Token ID262
Feature activation+9.68e-03

Pos logit contributions
apy+0.196
sed+0.171
 Nick+0.170
 toes+0.168
 ah+0.167
Neg logit contributions
ock-0.109
off-0.101
isi-0.099
 course-0.098
ty-0.094
Token living
Token ID2877
Feature activation+1.21e-01

Pos logit contributions
 Mam+0.013
apy+0.013
 Nick+0.013
 Liz+0.012
 Megan+0.012
Neg logit contributions
ercise-0.019
isi-0.019
iable-0.019
ock-0.018
at-0.018
Token room
Token ID2119
Feature activation+6.69e-02

Pos logit contributions
apy+0.206
 Madd+0.189
 Nick+0.189
 Kel+0.184
 Mam+0.180
Neg logit contributions
off-0.217
up-0.206
ercise-0.204
les-0.201
ock-0.200
Token.
Token ID13
Feature activation+5.76e-03

Pos logit contributions
apy+0.151
 Madd+0.147
 Nick+0.145
 Mick+0.141
 Mam+0.141
Neg logit contributions
off-0.072
ock-0.071
up-0.071
iable-0.068
at-0.066
Token It
Token ID632
Feature activation-2.32e-03

Pos logit contributions
 dodging+0.012
 ah+0.011
 toes+0.011
istered+0.011
 unison+0.011
Neg logit contributions
off-0.005
um-0.005
up-0.005
ade-0.005
 One-0.005
Token had
Token ID550
Feature activation-7.08e-03

Pos logit contributions
ercise+0.004
isi+0.004
iable+0.004
ches+0.003
ock+0.003
Neg logit contributions
apy-0.004
 Nick-0.004
 Mam-0.004
 toes-0.004
 Mick-0.004
Token a
Token ID257
Feature activation+1.27e-02

Pos logit contributions
ercise+0.010
isi+0.010
ock+0.010
iable+0.009
off+0.009
Neg logit contributions
apy-0.014
 Nick-0.014
 Mam-0.013
 Mick-0.013
 Megan-0.013
Token big
Token ID1263
Feature activation+2.46e-02

Pos logit contributions
 Nick+0.076
 Mam+0.074
 Megan+0.072
 Mick+0.070
 Mil+0.069
Neg logit contributions
ercise-0.057
isi-0.055
ock-0.053
vious-0.051
 course-0.051
Token eyes
Token ID2951
Feature activation+6.01e-02

Pos logit contributions
apy+0.037
 Nick+0.036
 Mam+0.035
 Madd+0.034
 Megan+0.033
Neg logit contributions
ercise-0.047
isi-0.045
vious-0.044
ock-0.044
les-0.044
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
apy+0.105
 Nick+0.104
 Mam+0.102
 Liz+0.097
 Megan+0.096
Neg logit contributions
ercise-0.098
isi-0.096
ock-0.096
iable-0.095
off-0.090
Token a
Token ID257
Feature activation+4.42e-02

Pos logit contributions
ercise+0.019
isi+0.017
vious+0.017
iable+0.016
les+0.016
Neg logit contributions
 Nick-0.020
 Mam-0.019
apy-0.019
 Mick-0.018
 Megan-0.018
Token tongue
Token ID11880
Feature activation+2.21e-02

Pos logit contributions
 Nick+0.086
 Mam+0.080
 Megan+0.079
 Liz+0.078
 Mike+0.078
Neg logit contributions
ercise-0.065
isi-0.065
iable-0.061
ock-0.060
 poem-0.058
Token out
Token ID503
Feature activation+1.20e-01

Pos logit contributions
apy+0.038
 Nick+0.038
 Mam+0.037
 Megan+0.035
 Liz+0.035
Neg logit contributions
ercise-0.037
isi-0.036
ock-0.036
iable-0.035
off-0.034
Token.
Token ID13
Feature activation+1.38e-02

Pos logit contributions
 Nick+0.222
 Mam+0.219
apy+0.208
 Mick+0.204
 Megan+0.203
Neg logit contributions
ock-0.184
ercise-0.177
isi-0.173
les-0.172
vious-0.170
Token He
Token ID679
Feature activation+2.55e-02

Pos logit contributions
apy+0.024
 Mam+0.024
 toes+0.023
 Nick+0.023
 sweating+0.023
Neg logit contributions
ercise-0.020
isi-0.020
orting-0.018
vious-0.018
ock-0.018
Token w
Token ID266
Feature activation+2.13e-02

Pos logit contributions
apy+0.049
 Nick+0.048
 Mam+0.047
 Megan+0.045
 Liz+0.045
Neg logit contributions
ercise-0.038
isi-0.038
ock-0.037
iable-0.037
off-0.035
Tokenags
Token ID3775
Feature activation+4.49e-02

Pos logit contributions
apy+0.045
 Nick+0.044
 Mam+0.043
 Megan+0.042
 Liz+0.042
Neg logit contributions
ercise-0.028
isi-0.027
iable-0.026
ock-0.026
off-0.024
Token his
Token ID465
Feature activation+6.08e-02

Pos logit contributions
apy+0.094
 Mam+0.093
 bedrooms+0.088
 Nick+0.087
 Mick+0.085
Neg logit contributions
ock-0.053
isi-0.051
ercise-0.050
ty-0.049
iable-0.045
Token a
Token ID257
Feature activation+9.06e-04

Pos logit contributions
ercise+0.013
isi+0.013
ock+0.013
iable+0.013
up+0.012
Neg logit contributions
apy-0.017
 Nick-0.017
 Mam-0.016
 Megan-0.015
 spe-0.015
Token big
Token ID1263
Feature activation+9.93e-03

Pos logit contributions
apy+0.002
 Nick+0.002
 Mam+0.002
 Megan+0.002
 Liz+0.002
Neg logit contributions
isi-0.001
ercise-0.001
iable-0.001
ock-0.001
orn-0.001
Token box
Token ID3091
Feature activation+2.36e-02

Pos logit contributions
apy+0.019
 Nick+0.018
 Mam+0.018
 Megan+0.017
 Liz+0.017
Neg logit contributions
ercise-0.015
isi-0.015
ock-0.014
iable-0.014
orn-0.013
Token in
Token ID287
Feature activation+8.65e-02

Pos logit contributions
apy+0.039
 Nick+0.038
 Mam+0.037
 Liz+0.035
 Megan+0.035
Neg logit contributions
ercise-0.042
isi-0.041
iable-0.040
ock-0.040
off-0.038
Token the
Token ID262
Feature activation+8.25e-03

Pos logit contributions
apy+0.190
 Nick+0.169
sed+0.165
 toes+0.164
 ankles+0.162
Neg logit contributions
ock-0.113
isi-0.109
 course-0.102
off-0.100
ty-0.097
Token living
Token ID2877
Feature activation+1.20e-01

Pos logit contributions
apy+0.015
 Nick+0.015
 Mam+0.014
 Liz+0.014
 Megan+0.014
Neg logit contributions
ercise-0.013
isi-0.013
iable-0.013
ock-0.013
off-0.012
Token room
Token ID2119
Feature activation+6.32e-02

Pos logit contributions
apy+0.211
 Madd+0.195
 Kel+0.191
 Nick+0.191
 Mam+0.186
Neg logit contributions
off-0.207
up-0.197
les-0.196
ercise-0.191
ock-0.188
Token.
Token ID13
Feature activation-3.63e-06

Pos logit contributions
apy+0.134
 Nick+0.129
 Madd+0.127
 Mam+0.125
 Mick+0.124
Neg logit contributions
ock-0.078
iable-0.076
off-0.075
up-0.075
isi-0.074
Token She
Token ID1375
Feature activation+2.12e-02

Feature not active on prev token;
no predictions were affected.
Token asked
Token ID1965
Feature activation+1.96e-02

Pos logit contributions
apy+0.032
 Nick+0.031
 Mam+0.030
 Megan+0.029
 Liz+0.029
Neg logit contributions
ercise-0.040
isi-0.039
iable-0.038
ock-0.037
off-0.037
Token her
Token ID607
Feature activation+8.94e-03

Pos logit contributions
apy+0.039
 Nick+0.037
 Mam+0.036
 Megan+0.035
 spe+0.035
Neg logit contributions
ercise-0.028
isi-0.028
ock-0.027
iable-0.027
off-0.025
Token.
Token ID13
Feature activation+3.62e-04

Pos logit contributions
apy+0.035
 Nick+0.034
 Mam+0.033
 Liz+0.032
 Megan+0.032
Neg logit contributions
ercise-0.034
isi-0.033
iable-0.032
ock-0.032
off-0.031
Token Are
Token ID4231
Feature activation-1.41e-02

Pos logit contributions
apy+0.001
 Nick+0.001
 shovel+0.001
 toes+0.001
 Mam+0.001
Neg logit contributions
ercise-0.001
isi-0.001
ock-0.001
off-0.001
iable-0.001
Token you
Token ID345
Feature activation-1.19e-02

Pos logit contributions
ercise+0.016
isi+0.016
ock+0.016
iable+0.015
off+0.014
Neg logit contributions
 Nick-0.032
apy-0.032
 Mam-0.031
 Megan-0.030
 Liz-0.030
Token ready
Token ID3492
Feature activation-2.11e-02

Pos logit contributions
ercise+0.019
isi+0.019
iable+0.018
ock+0.018
off+0.017
Neg logit contributions
apy-0.022
 Nick-0.021
 Mam-0.021
 Liz-0.020
 Megan-0.020
Token to
Token ID284
Feature activation+1.34e-02

Pos logit contributions
isi+0.027
ercise+0.027
iable+0.025
ock+0.025
vious+0.024
Neg logit contributions
 Nick-0.045
 Mam-0.045
apy-0.044
 Liz-0.042
 Mike-0.042
Token board
Token ID3096
Feature activation-1.04e-01

Pos logit contributions
 Nick+0.024
 Mam+0.023
apy+0.023
 Liz+0.022
 Mike+0.022
Neg logit contributions
ercise-0.023
iable-0.022
isi-0.022
ock-0.021
vious-0.020
Token?"
Token ID1701
Feature activation+2.59e-02

Pos logit contributions
isi+0.171
ercise+0.156
elling+0.150
affe+0.143
iable+0.142
Neg logit contributions
 Nick-0.176
 L-0.174
 Liz-0.171
apy-0.171
 Mam-0.171
Token Mom
Token ID11254
Feature activation+1.09e-02

Pos logit contributions
apy+0.036
 Nick+0.034
uzz+0.033
 tad+0.033
 shovel+0.033
Neg logit contributions
isi-0.045
iable-0.045
ercise-0.044
ock-0.042
off-0.041
Token asked
Token ID1965
Feature activation+6.83e-02

Pos logit contributions
apy+0.020
 Nick+0.020
 Mam+0.019
 Liz+0.018
 Megan+0.018
Neg logit contributions
ercise-0.017
isi-0.017
iable-0.017
ock-0.017
off-0.016
Token.
Token ID13
Feature activation+4.40e-02

Pos logit contributions
apy+0.161
 spe+0.144
 Mam+0.141
 Mick+0.141
 Liz+0.139
Neg logit contributions
isi-0.069
ock-0.068
iable-0.067
up-0.067
que-0.065
Token
Token ID198
Feature activation+1.25e-02

Pos logit contributions
 toes+0.100
apy+0.099
 ah+0.098
 bedrooms+0.094
 Esk+0.094
Neg logit contributions
isi-0.040
One-0.032
que-0.031
ometime-0.030
ercise-0.029
Token it
Token ID340
Feature activation-7.15e-03

Pos logit contributions
apy+0.133
 Mam+0.113
 ankles+0.113
 bedrooms+0.113
suits+0.113
Neg logit contributions
ock-0.083
iable-0.082
 course-0.081
ercise-0.078
isi-0.077
Token and
Token ID290
Feature activation-3.19e-02

Pos logit contributions
ercise+0.011
isi+0.011
iable+0.011
ock+0.011
off+0.010
Neg logit contributions
apy-0.013
 Nick-0.013
 Mam-0.013
 Liz-0.012
 Megan-0.012
Token wished
Token ID16555
Feature activation-1.71e-02

Pos logit contributions
ercise+0.050
iable+0.048
isi+0.045
ock+0.045
les+0.044
Neg logit contributions
apy-0.057
 Mam-0.055
 Nick-0.055
 Megan-0.052
uzz-0.052
Token she
Token ID673
Feature activation-2.38e-02

Pos logit contributions
ercise+0.023
iable+0.023
isi+0.023
ock+0.023
off+0.020
Neg logit contributions
apy-0.034
 Nick-0.033
 Mam-0.033
 Megan-0.032
 Liz-0.031
Token could
Token ID714
Feature activation-2.80e-02

Pos logit contributions
ercise+0.039
iable+0.038
isi+0.037
ches+0.036
up+0.036
Neg logit contributions
apy-0.043
 Mam-0.040
 Nick-0.039
 Mil-0.037
 Liz-0.037
Token board
Token ID3096
Feature activation-1.01e-01

Pos logit contributions
ercise+0.049
isi+0.048
iable+0.047
ock+0.047
off+0.044
Neg logit contributions
apy-0.047
 Nick-0.047
 Mam-0.046
 Liz-0.043
 Megan-0.043
Token it
Token ID340
Feature activation-5.77e-02

Pos logit contributions
isi+0.161
ercise+0.159
iable+0.144
ock+0.142
at+0.142
Neg logit contributions
 Nick-0.181
apy-0.179
 Liz-0.174
 Mam-0.174
 Mike-0.170
Token.
Token ID13
Feature activation+1.13e-03

Pos logit contributions
isi+0.098
ercise+0.098
iable+0.093
ock+0.092
off+0.089
Neg logit contributions
 Nick-0.097
apy-0.096
 Mam-0.094
 Liz-0.093
 Megan-0.089
Token
Token ID220
Feature activation-3.80e-03

Pos logit contributions
apy+0.002
 Nick+0.002
 Mam+0.002
 Liz+0.002
 Megan+0.002
Neg logit contributions
ercise-0.002
isi-0.002
iable-0.002
ock-0.002
off-0.002
Token
Token ID198
Feature activation+2.59e-03

Pos logit contributions
isi+0.006
iable+0.006
ercise+0.006
ock+0.006
off+0.006
Neg logit contributions
apy-0.007
 Nick-0.006
 spe-0.006
 Mam-0.006
 toes-0.006
Token
Token ID198
Feature activation+1.55e-03

Pos logit contributions
apy+0.004
 Nick+0.004
 Mam+0.004
 Liz+0.004
 Megan+0.004
Neg logit contributions
ercise-0.005
isi-0.005
iable-0.005
ock-0.005
off-0.005
Token
Token ID198
Feature activation-3.07e-03

Pos logit contributions
isi+0.001
ercise+0.001
ock+0.001
iable+0.001
off+0.001
Neg logit contributions
apy-0.001
 Nick-0.001
 Mam-0.001
 Megan-0.001
 Liz-0.001
Token"
Token ID1
Feature activation+1.17e-02

Pos logit contributions
isi+0.005
ercise+0.005
ock+0.005
iable+0.005
at+0.005
Neg logit contributions
apy-0.005
 Nick-0.005
 Mam-0.005
 Megan-0.005
 Liz-0.005
TokenNow
Token ID3844
Feature activation-3.17e-02

Pos logit contributions
apy+0.020
 Nick+0.019
 Mam+0.019
 Liz+0.018
 Megan+0.018
Neg logit contributions
ercise-0.021
isi-0.020
iable-0.020
ock-0.020
off-0.019
Token you
Token ID345
Feature activation+3.45e-03

Pos logit contributions
ercise+0.050
isi+0.049
iable+0.048
ock+0.048
off+0.045
Neg logit contributions
apy-0.058
 Nick-0.057
 Mam-0.056
 Liz-0.053
 Megan-0.053
Token can
Token ID460
Feature activation-2.80e-02

Pos logit contributions
 Nick+0.004
apy+0.004
 Mam+0.004
 shovel+0.004
 Liz+0.004
Neg logit contributions
isi-0.007
ercise-0.007
ock-0.007
iable-0.007
at-0.006
Token golf
Token ID13126
Feature activation-9.85e-02

Pos logit contributions
ercise+0.057
isi+0.056
ock+0.054
iable+0.053
vious+0.052
Neg logit contributions
apy-0.038
 Mam-0.037
 Nick-0.037
 Liz-0.035
 Mike-0.035
Token!"
Token ID2474
Feature activation+5.41e-03

Pos logit contributions
isi+0.194
at+0.187
ock+0.180
ercise+0.177
night+0.175
Neg logit contributions
 L-0.127
 Nick-0.122
 Mike-0.120
apy-0.117
 shovel-0.116
Token she
Token ID673
Feature activation+2.46e-03

Pos logit contributions
apy+0.008
 Nick+0.008
 Mam+0.008
 Megan+0.008
 Liz+0.008
Neg logit contributions
ercise-0.010
isi-0.010
iable-0.010
ock-0.009
off-0.009
Token said
Token ID531
Feature activation+3.67e-02

Pos logit contributions
apy+0.004
 Nick+0.004
 Mam+0.004
 Liz+0.004
 Megan+0.004
Neg logit contributions
ercise-0.004
isi-0.004
iable-0.004
ock-0.004
off-0.004
Token happily
Token ID18177
Feature activation-1.99e-03

Pos logit contributions
apy+0.080
 bedrooms+0.076
 Nick+0.076
 Mam+0.075
 spe+0.075
Neg logit contributions
iable-0.037
night-0.036
isi-0.036
ercise-0.034
ly-0.033
Token.
Token ID13
Feature activation+2.20e-02

Pos logit contributions
ercise+0.003
isi+0.003
iable+0.003
ock+0.003
off+0.003
Neg logit contributions
apy-0.003
 Nick-0.003
 Mam-0.003
 Liz-0.003
 Megan-0.003
Token you
Token ID345
Feature activation-1.70e-02

Pos logit contributions
at+0.073
les+0.073
ercise+0.072
ock+0.072
isi+0.069
Neg logit contributions
apy-0.078
 Liz-0.077
 Nick-0.076
 Jen-0.076
 Megan-0.075
Token want
Token ID765
Feature activation-5.66e-02

Pos logit contributions
ercise+0.034
isi+0.034
iable+0.033
ock+0.032
off+0.031
Neg logit contributions
apy-0.023
 Nick-0.023
 Mam-0.023
 Liz-0.023
 Jen-0.022
Token to
Token ID284
Feature activation+3.41e-03

Pos logit contributions
isi+0.095
iable+0.093
ercise+0.091
at+0.090
ock+0.086
Neg logit contributions
 Nick-0.103
apy-0.099
 Mam-0.098
 Liz-0.095
 L-0.094
Token share
Token ID2648
Feature activation-5.14e-02

Pos logit contributions
apy+0.005
 Mam+0.005
 Nick+0.005
 Liz+0.005
 L+0.005
Neg logit contributions
ercise-0.006
isi-0.006
iable-0.006
ock-0.006
at-0.006
Token my
Token ID616
Feature activation-5.51e-03

Pos logit contributions
isi+0.085
ercise+0.083
iable+0.080
ock+0.078
at+0.077
Neg logit contributions
 Nick-0.090
apy-0.089
 Mam-0.088
 Liz-0.085
 L-0.084
Token shirt
Token ID10147
Feature activation-9.82e-02

Pos logit contributions
ercise+0.009
isi+0.009
iable+0.009
ock+0.009
off+0.008
Neg logit contributions
apy-0.010
 Nick-0.009
 Mam-0.009
 Megan-0.009
 Liz-0.009
Token?
Token ID30
Feature activation-6.61e-03

Pos logit contributions
ercise+0.206
isi+0.199
iable+0.193
ience+0.185
ock+0.185
Neg logit contributions
 Liz-0.129
 Mam-0.128
 L-0.126
 Nick-0.126
apy-0.124
Token We
Token ID775
Feature activation+5.07e-03

Pos logit contributions
ercise+0.012
isi+0.011
iable+0.011
ock+0.011
off+0.010
Neg logit contributions
apy-0.011
 Nick-0.010
 Mam-0.010
 Megan-0.010
 Madd-0.010
Token can
Token ID460
Feature activation-2.14e-02

Pos logit contributions
apy+0.008
 Nick+0.008
 Mam+0.008
 Liz+0.007
 Megan+0.007
Neg logit contributions
isi-0.009
ercise-0.009
ock-0.009
iable-0.009
at-0.008
Token take
Token ID1011
Feature activation-4.51e-02

Pos logit contributions
ercise+0.040
isi+0.039
ock+0.038
iable+0.037
vious+0.037
Neg logit contributions
 Nick-0.034
apy-0.033
 Mam-0.033
 Mike-0.030
 Liz-0.030
Token turns
Token ID4962
Feature activation-3.14e-02

Pos logit contributions
isi+0.090
iable+0.085
ercise+0.083
at+0.082
ock+0.082
Neg logit contributions
apy-0.069
 Nick-0.068
 Mam-0.064
 Liz-0.063
 L-0.063
TokenHey
Token ID10814
Feature activation+3.54e-03

Pos logit contributions
apy+0.003
 Mam+0.003
 Nick+0.003
 Liz+0.003
 Mike+0.003
Neg logit contributions
isi-0.005
ercise-0.005
iable-0.005
at-0.005
ches-0.004
Token,
Token ID11
Feature activation+3.10e-02

Pos logit contributions
apy+0.006
 Nick+0.006
 Mam+0.006
 Megan+0.005
 Mick+0.005
Neg logit contributions
ercise-0.006
iable-0.006
isi-0.006
ock-0.006
off-0.006
Token can
Token ID460
Feature activation-2.19e-02

Pos logit contributions
apy+0.041
 Nick+0.039
 Mam+0.038
 Megan+0.035
 Mil+0.034
Neg logit contributions
ercise-0.066
iable-0.065
isi-0.064
ock-0.064
off-0.062
Token I
Token ID314
Feature activation-3.14e-02

Pos logit contributions
ercise+0.030
iable+0.029
isi+0.028
ock+0.028
off+0.026
Neg logit contributions
apy-0.044
 Nick-0.044
 Mam-0.043
 Megan-0.041
 Liz-0.041
Token play
Token ID711
Feature activation-5.12e-02

Pos logit contributions
ercise+0.055
isi+0.055
iable+0.053
ock+0.053
off+0.050
Neg logit contributions
apy-0.052
 Nick-0.051
 Mam-0.050
 Liz-0.048
 Megan-0.047
Token basketball
Token ID9669
Feature activation-9.82e-02

Pos logit contributions
isi+0.119
at+0.109
ock+0.108
ercise+0.108
iable+0.107
Neg logit contributions
apy-0.060
 Nick-0.054
 L-0.054
 Liz-0.053
 Mam-0.050
Token with
Token ID351
Feature activation+9.19e-03

Pos logit contributions
isi+0.206
ercise+0.182
erence+0.179
elling+0.179
ully+0.177
Neg logit contributions
 L-0.123
apy-0.117
 Liz-0.116
 Nick-0.112
 holding-0.110
Token you
Token ID345
Feature activation-6.23e-03

Pos logit contributions
apy+0.018
 Nick+0.017
 Liz+0.016
 L+0.016
 Mam+0.016
Neg logit contributions
isi-0.014
ercise-0.013
at-0.013
iable-0.012
ock-0.012
Token?"
Token ID1701
Feature activation+1.37e-02

Pos logit contributions
isi+0.008
ercise+0.007
off+0.007
ock+0.007
iable+0.007
Neg logit contributions
 Nick-0.013
apy-0.013
 L-0.012
 Liz-0.012
 Mam-0.012
Token Tim
Token ID5045
Feature activation-1.37e-02

Pos logit contributions
apy+0.014
 Nick+0.014
 Mam+0.013
 Megan+0.013
 toes+0.013
Neg logit contributions
ercise-0.032
iable-0.031
isi-0.031
ock-0.031
off-0.030
Tokenmy
Token ID1820
Feature activation-5.45e-03

Pos logit contributions
ercise+0.014
isi+0.013
iable+0.013
ock+0.013
off+0.012
Neg logit contributions
 Liz-0.032
 Mam-0.032
 Nick-0.032
 gasped-0.030
 Megan-0.030
Token
Token ID198
Feature activation-1.93e-02

Pos logit contributions
 spe+0.001
apy+0.001
 ah+0.001
 Esk+0.001
 extingu+0.001
Neg logit contributions
ercise-0.000
isi-0.000
off-0.000
ches-0.000
les-0.000
Token
Token ID198
Feature activation-1.19e-02

Pos logit contributions
isi+0.030
ock+0.029
ercise+0.028
off+0.028
iable+0.027
Neg logit contributions
apy-0.035
 Mam-0.033
 Nick-0.033
 spe-0.032
 ankles-0.032
Token"
Token ID1
Feature activation+1.54e-02

Pos logit contributions
ercise+0.015
isi+0.014
ock+0.014
iable+0.014
off+0.013
Neg logit contributions
apy-0.026
 Nick-0.025
 Mam-0.025
 Liz-0.025
 Madd-0.024
TokenCan
Token ID6090
Feature activation-1.92e-02

Pos logit contributions
apy+0.027
 Nick+0.025
 Mam+0.025
 Liz+0.024
 Mick+0.023
Neg logit contributions
ercise-0.026
isi-0.026
ock-0.025
iable-0.025
off-0.024
Token we
Token ID356
Feature activation-4.82e-02

Pos logit contributions
ercise+0.035
isi+0.034
iable+0.034
ock+0.033
off+0.032
Neg logit contributions
apy-0.030
 Nick-0.029
 Mam-0.029
 Liz-0.027
 Megan-0.027
Token bounce
Token ID20110
Feature activation-9.82e-02

Pos logit contributions
ercise+0.071
isi+0.070
iable+0.069
ock+0.068
off+0.063
Neg logit contributions
apy-0.092
 Nick-0.092
 Mam-0.091
 Liz-0.086
 Mike-0.085
Token on
Token ID319
Feature activation+2.35e-02

Pos logit contributions
isi+0.187
ercise+0.176
iable+0.174
ock+0.170
at+0.167
Neg logit contributions
 Nick-0.159
apy-0.154
 Liz-0.147
 Mam-0.146
 Mike-0.144
Token the
Token ID262
Feature activation-4.94e-02

Pos logit contributions
apy+0.037
 Nick+0.036
 Mam+0.035
 Liz+0.033
 Megan+0.033
Neg logit contributions
ercise-0.043
isi-0.043
iable-0.042
ock-0.042
off-0.040
Token bed
Token ID3996
Feature activation+2.14e-02

Pos logit contributions
ercise+0.091
isi+0.091
iable+0.088
vious+0.083
ock+0.083
Neg logit contributions
 Nick-0.077
 Mam-0.076
apy-0.075
 toes-0.071
 Liz-0.070
Token?"
Token ID1701
Feature activation+3.26e-02

Pos logit contributions
 Nick+0.043
apy+0.042
 Mam+0.041
 Megan+0.040
 Liz+0.040
Neg logit contributions
ercise-0.032
isi-0.031
iable-0.029
ock-0.029
off-0.027
Token Anna
Token ID11735
Feature activation+2.39e-02

Pos logit contributions
apy+0.041
uzz+0.041
 Esk+0.040
 spe+0.040
 extingu+0.039
Neg logit contributions
ercise-0.062
isi-0.060
up-0.057
les-0.057
vious-0.056
Token mom
Token ID1995
Feature activation-7.08e-03

Pos logit contributions
apy+0.009
 Nick+0.008
 Mam+0.008
 Megan+0.008
 Liz+0.008
Neg logit contributions
ercise-0.009
isi-0.009
ock-0.009
iable-0.009
off-0.009
Token,
Token ID11
Feature activation+3.99e-02

Pos logit contributions
ercise+0.013
isi+0.012
iable+0.012
ock+0.012
off+0.011
Neg logit contributions
 Nick-0.012
 Mam-0.012
apy-0.011
 Liz-0.011
 Megan-0.011
Token "
Token ID366
Feature activation+6.44e-03

Pos logit contributions
apy+0.067
 ankles+0.060
 bedrooms+0.060
 spe+0.059
 Nick+0.057
Neg logit contributions
ercise-0.068
isi-0.066
iable-0.065
ock-0.061
ty-0.059
TokenCan
Token ID6090
Feature activation-2.26e-02

Pos logit contributions
 Mam+0.008
 Nick+0.008
apy+0.008
 Liz+0.007
 Mike+0.007
Neg logit contributions
isi-0.014
iable-0.014
ercise-0.013
ock-0.013
ches-0.013
Token I
Token ID314
Feature activation-3.18e-02

Pos logit contributions
isi+0.045
ercise+0.045
ock+0.044
iable+0.043
at+0.042
Neg logit contributions
apy-0.033
 Nick-0.032
 Mam-0.031
 Liz-0.030
 Megan-0.029
Token bat
Token ID7365
Feature activation-9.80e-02

Pos logit contributions
isi+0.060
ercise+0.059
iable+0.058
ock+0.056
off+0.054
Neg logit contributions
apy-0.050
 Nick-0.048
 Mam-0.048
 Liz-0.045
 Mick-0.044
Tokenhe
Token ID258
Feature activation+1.34e-02

Pos logit contributions
ercise+0.190
isi+0.189
iable+0.182
ience+0.175
erence+0.171
Neg logit contributions
apy-0.145
 Nick-0.142
 L-0.130
 Mike-0.127
 Mam-0.124
Token with
Token ID351
Feature activation+1.53e-02

Pos logit contributions
apy+0.027
 Nick+0.027
 Mam+0.026
 Liz+0.025
 Megan+0.025
Neg logit contributions
isi-0.019
ercise-0.019
iable-0.018
ock-0.018
off-0.017
Token my
Token ID616
Feature activation+1.95e-02

Pos logit contributions
apy+0.029
 Nick+0.028
 Mam+0.027
 Liz+0.026
 L+0.026
Neg logit contributions
isi-0.025
ercise-0.023
iable-0.023
ock-0.022
at-0.022
Token boat
Token ID8848
Feature activation-4.93e-02

Pos logit contributions
apy+0.036
 Nick+0.035
 Megan+0.035
 Mam+0.034
 Liz+0.034
Neg logit contributions
ercise-0.030
ock-0.029
iable-0.028
isi-0.028
off-0.027
Token?"
Token ID1701
Feature activation+2.05e-02

Pos logit contributions
isi+0.063
ercise+0.061
iable+0.059
ock+0.058
off+0.056
Neg logit contributions
 Mam-0.102
 Nick-0.102
apy-0.100
 Liz-0.100
 shovel-0.098
Token and
Token ID290
Feature activation-4.84e-02

Pos logit contributions
apy+0.003
 Nick+0.003
 Mam+0.002
 Liz+0.002
 Megan+0.002
Neg logit contributions
ercise-0.002
isi-0.002
iable-0.002
ock-0.002
off-0.002
Token rest
Token ID1334
Feature activation+1.70e-02

Pos logit contributions
ercise+0.077
isi+0.074
iable+0.073
ock+0.071
off+0.069
Neg logit contributions
apy-0.088
 Nick-0.087
 Mam-0.085
 Liz-0.081
 Megan-0.081
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
apy+0.036
 Mam+0.035
 Nick+0.035
 Liz+0.034
 Kel+0.033
Neg logit contributions
ock-0.021
ercise-0.021
iable-0.020
isi-0.020
off-0.020
Token You
Token ID921
Feature activation-6.88e-03

Pos logit contributions
ercise+0.022
isi+0.022
ock+0.021
iable+0.021
off+0.020
Neg logit contributions
apy-0.020
 Nick-0.019
 Mam-0.018
 Megan-0.017
 toes-0.017
Token can
Token ID460
Feature activation-2.73e-02

Pos logit contributions
ercise+0.014
isi+0.014
iable+0.014
ock+0.014
at+0.013
Neg logit contributions
 Nick-0.009
apy-0.008
 Mam-0.008
 spe-0.008
 shovel-0.008
Token bounce
Token ID20110
Feature activation-9.80e-02

Pos logit contributions
ercise+0.053
isi+0.049
iable+0.049
vious+0.049
ock+0.049
Neg logit contributions
 Nick-0.044
 Mam-0.041
apy-0.040
 Megan-0.038
 Mike-0.038
Token again
Token ID757
Feature activation-1.13e-02

Pos logit contributions
isi+0.184
ercise+0.174
iable+0.169
at+0.164
off+0.163
Neg logit contributions
 Nick-0.161
 L-0.152
apy-0.151
 Megan-0.148
 Madd-0.145
Token tomorrow
Token ID9439
Feature activation-5.93e-03

Pos logit contributions
isi+0.017
ercise+0.017
iable+0.016
ock+0.016
off+0.015
Neg logit contributions
 Nick-0.021
apy-0.021
 Mam-0.020
 Megan-0.020
 Liz-0.019
Token,
Token ID11
Feature activation+5.43e-03

Pos logit contributions
ercise+0.010
isi+0.010
iable+0.010
ock+0.009
at+0.009
Neg logit contributions
 Nick-0.010
 Mam-0.010
apy-0.010
 Megan-0.009
 Mike-0.009
Token but
Token ID475
Feature activation-5.53e-03

Pos logit contributions
apy+0.009
 Nick+0.009
 Mam+0.009
 Liz+0.008
 Megan+0.008
Neg logit contributions
ercise-0.010
isi-0.010
iable-0.009
ock-0.009
off-0.009
Token not
Token ID407
Feature activation-4.17e-03

Pos logit contributions
ercise+0.008
isi+0.008
iable+0.008
ock+0.008
off+0.008
Neg logit contributions
apy-0.010
 Nick-0.010
 Mam-0.010
 Liz-0.010
 Megan-0.010
Token you
Token ID345
Feature activation-1.54e-02

Pos logit contributions
les+0.064
at+0.064
ock+0.062
ercise+0.061
isi+0.060
Neg logit contributions
apy-0.065
 Liz-0.065
 Jen-0.064
 L-0.062
 Nick-0.062
Token want
Token ID765
Feature activation-5.90e-02

Pos logit contributions
isi+0.034
ercise+0.034
at+0.033
iable+0.032
ches+0.032
Neg logit contributions
 L-0.017
 Jen-0.017
 Mam-0.017
 Liz-0.017
 Nick-0.016
Token to
Token ID284
Feature activation-1.96e-03

Pos logit contributions
at+0.127
isi+0.115
les+0.113
ches+0.113
iable+0.111
Neg logit contributions
 L-0.081
 Mike-0.080
 Nick-0.076
 holding-0.075
 Liz-0.075
Token try
Token ID1949
Feature activation-6.77e-02

Pos logit contributions
at+0.004
ches+0.004
les+0.004
ercise+0.004
ience+0.003
Neg logit contributions
 Mike-0.003
 L-0.003
 Jen-0.003
 Mam-0.003
 holding-0.003
Token my
Token ID616
Feature activation-3.71e-02

Pos logit contributions
at+0.125
isi+0.125
ercise+0.118
vious+0.116
off+0.114
Neg logit contributions
 L-0.105
 Nick-0.104
 Mike-0.102
 holding-0.102
 Liz-0.101
Token bike
Token ID7161
Feature activation-9.78e-02

Pos logit contributions
at+0.074
isi+0.072
ock+0.069
ches+0.069
ercise+0.067
Neg logit contributions
 Mam-0.052
 toes-0.052
 holding-0.050
apy-0.049
 feet-0.049
Token?"
Token ID1701
Feature activation+2.12e-02

Pos logit contributions
isi+0.173
ience+0.173
ercise+0.168
les+0.168
isy+0.167
Neg logit contributions
 L-0.147
 Liz-0.141
 Jen-0.138
 holding-0.138
 Mike-0.131
Token Anna
Token ID11735
Feature activation+1.59e-02

Pos logit contributions
apy+0.030
 Nick+0.027
 Mam+0.027
 shovel+0.026
 spe+0.026
Neg logit contributions
isi-0.041
ercise-0.041
ock-0.040
iable-0.038
off-0.038
Token says
Token ID1139
Feature activation+3.69e-02

Pos logit contributions
 Nick+0.030
 Mam+0.028
 Megan+0.027
 Mil+0.027
apy+0.027
Neg logit contributions
isi-0.026
ercise-0.025
iable-0.024
ock-0.024
at-0.023
Token,
Token ID11
Feature activation+4.10e-02

Pos logit contributions
apy+0.066
 Nick+0.064
 Mam+0.062
 Liz+0.060
 Megan+0.060
Neg logit contributions
ercise-0.061
isi-0.061
ock-0.058
iable-0.058
off-0.056
Token "
Token ID366
Feature activation+6.74e-03

Pos logit contributions
apy+0.056
 Mam+0.053
 Nick+0.053
 Liz+0.050
 Madd+0.050
Neg logit contributions
ercise-0.080
iable-0.079
isi-0.076
ock-0.076
vious-0.072
TokenBut
Token ID1537
Feature activation+1.55e-02

Pos logit contributions
 Nick+0.036
apy+0.036
 Mam+0.035
 Liz+0.034
 toes+0.034
Neg logit contributions
ercise-0.030
isi-0.029
ock-0.028
iable-0.027
off-0.026
Token we
Token ID356
Feature activation-2.14e-03

Pos logit contributions
apy+0.030
uzz+0.029
 gasped+0.028
ges+0.028
 sweating+0.028
Neg logit contributions
ercise-0.021
 course-0.020
iable-0.020
ock-0.018
isi-0.017
Token want
Token ID765
Feature activation-5.49e-02

Pos logit contributions
ercise+0.004
isi+0.004
iable+0.004
ock+0.004
off+0.004
Neg logit contributions
apy-0.004
 Nick-0.003
 Mam-0.003
 Megan-0.003
 Liz-0.003
Token to
Token ID284
Feature activation-2.65e-03

Pos logit contributions
isi+0.081
ercise+0.079
iable+0.078
ock+0.074
at+0.073
Neg logit contributions
 Nick-0.108
apy-0.108
 Mam-0.106
 Liz-0.102
 Megan-0.100
Token play
Token ID711
Feature activation-5.32e-02

Pos logit contributions
ercise+0.004
isi+0.004
ock+0.004
iable+0.004
off+0.004
Neg logit contributions
apy-0.005
 Nick-0.005
 Mam-0.004
 Megan-0.004
 Liz-0.004
Token baseball
Token ID9283
Feature activation-9.77e-02

Pos logit contributions
ercise+0.080
isi+0.079
iable+0.077
ock+0.076
off+0.072
Neg logit contributions
apy-0.102
 Nick-0.100
 Mam-0.098
 Liz-0.094
 Megan-0.093
Token!"
Token ID2474
Feature activation+1.30e-02

Pos logit contributions
isi+0.186
ercise+0.182
iable+0.173
ock+0.169
off+0.163
Neg logit contributions
 Nick-0.150
apy-0.148
 Liz-0.139
 Mam-0.138
 Megan-0.138
Token they
Token ID484
Feature activation+7.53e-03

Pos logit contributions
 Esk+0.019
apy+0.018
 spe+0.018
 sweating+0.018
 Nick+0.018
Neg logit contributions
isi-0.022
ercise-0.021
up-0.020
iable-0.020
ock-0.020
Token cry
Token ID3960
Feature activation+2.86e-02

Pos logit contributions
apy+0.016
 Nick+0.015
 Mam+0.015
 Liz+0.014
 Megan+0.014
Neg logit contributions
ercise-0.010
isi-0.010
iable-0.010
ock-0.010
off-0.009
Token.
Token ID13
Feature activation+4.33e-02

Pos logit contributions
apy+0.051
 Nick+0.051
 Mam+0.049
 Megan+0.047
 Liz+0.046
Neg logit contributions
ercise-0.045
ock-0.044
isi-0.044
iable-0.043
off-0.041
Token
Token ID198
Feature activation+5.56e-03

Pos logit contributions
 ah+0.088
 Nick+0.088
 Esk+0.086
 toes+0.085
apy+0.084
Neg logit contributions
isi-0.047
ercise-0.047
 lessons-0.042
One-0.042
ometime-0.042
Token dad
Token ID9955
Feature activation-2.11e-02

Pos logit contributions
apy+0.086
 Nick+0.075
uzz+0.075
 sweating+0.073
 Megan+0.072
Neg logit contributions
ercise-0.090
iable-0.086
ock-0.083
isi-0.083
 exam-0.082
Token,
Token ID11
Feature activation+5.48e-02

Pos logit contributions
ercise+0.028
isi+0.028
iable+0.027
ock+0.027
off+0.026
Neg logit contributions
apy-0.044
 Nick-0.042
 Mam-0.042
 Megan-0.040
 Liz-0.040
Token can
Token ID460
Feature activation-1.72e-02

Pos logit contributions
apy+0.110
uzz+0.098
 Nick+0.097
 ankles+0.096
 sweating+0.096
Neg logit contributions
ercise-0.074
ock-0.071
iable-0.070
off-0.069
 exam-0.067
Token we
Token ID356
Feature activation-4.19e-02

Pos logit contributions
ercise+0.025
iable+0.024
ock+0.022
isi+0.022
off+0.022
Neg logit contributions
apy-0.031
 Nick-0.031
uzz-0.031
 Mam-0.031
 bedrooms-0.029
Token play
Token ID711
Feature activation-5.01e-02

Pos logit contributions
ercise+0.059
isi+0.058
iable+0.057
ock+0.056
off+0.053
Neg logit contributions
apy-0.084
 Nick-0.083
 Mam-0.081
 Liz-0.078
 Megan-0.077
Token baseball
Token ID9283
Feature activation-9.76e-02

Pos logit contributions
isi+0.084
ercise+0.081
iable+0.079
ock+0.078
off+0.074
Neg logit contributions
apy-0.090
 Nick-0.087
 Mam-0.084
 Liz-0.082
 Megan-0.080
Token today
Token ID1909
Feature activation+9.54e-03

Pos logit contributions
isi+0.157
ercise+0.143
iable+0.138
ock+0.133
elling+0.133
Neg logit contributions
 Nick-0.175
apy-0.174
 Liz-0.165
 L-0.162
 Megan-0.160
Token?"
Token ID1701
Feature activation+4.04e-02

Pos logit contributions
 Nick+0.023
apy+0.023
 Mam+0.023
 Megan+0.022
 Liz+0.022
Neg logit contributions
ercise-0.010
isi-0.009
iable-0.009
ock-0.009
off-0.008
Token they
Token ID484
Feature activation+2.32e-02

Pos logit contributions
 Esk+0.070
uzz+0.069
run+0.069
illed+0.068
istered+0.068
Neg logit contributions
 that-0.047
up-0.046
 me-0.046
?"-0.045
isi-0.043
Token ask
Token ID1265
Feature activation+6.12e-02

Pos logit contributions
apy+0.051
 Nick+0.045
 Mam+0.044
 Liz+0.043
uzz+0.043
Neg logit contributions
ock-0.029
isi-0.029
ercise-0.028
iable-0.028
vious-0.027
Token.
Token ID13
Feature activation+4.16e-02

Pos logit contributions
apy+0.143
 spe+0.142
 sweating+0.133
 ah+0.132
 Nick+0.132
Neg logit contributions
que-0.052
ock-0.052
 better-0.050
up-0.049
isi-0.047
Token't
Token ID470
Feature activation-2.56e-02

Pos logit contributions
ercise+0.091
ock+0.084
at+0.084
iable+0.084
isi+0.083
Neg logit contributions
apy-0.057
 Mam-0.056
 Nick-0.055
 Liz-0.054
 Mike-0.052
Token worry
Token ID5490
Feature activation-8.46e-03

Pos logit contributions
ercise+0.058
isi+0.057
iable+0.057
ock+0.057
off+0.055
Neg logit contributions
apy-0.030
 Nick-0.028
 Mam-0.027
 Megan-0.025
 Liz-0.025
Token,
Token ID11
Feature activation+1.23e-02

Pos logit contributions
ock+0.010
ercise+0.009
iable+0.009
isi+0.009
ches+0.009
Neg logit contributions
apy-0.019
 Nick-0.017
 Mam-0.017
 sweating-0.017
 gasped-0.017
Token we
Token ID356
Feature activation-1.54e-02

Pos logit contributions
apy+0.024
 Mam+0.022
 Nick+0.022
uzz+0.022
 Megan+0.021
Neg logit contributions
ercise-0.018
ock-0.017
iable-0.017
isi-0.016
off-0.015
Token can
Token ID460
Feature activation-2.81e-02

Pos logit contributions
ercise+0.021
iable+0.020
ock+0.020
isi+0.020
off+0.018
Neg logit contributions
apy-0.032
 Nick-0.031
 Mam-0.031
 Megan-0.030
 Liz-0.030
Token bat
Token ID7365
Feature activation-9.70e-02

Pos logit contributions
isi+0.048
ercise+0.048
iable+0.046
ock+0.046
off+0.043
Neg logit contributions
apy-0.048
 Nick-0.048
 Mam-0.047
 Liz-0.044
 Mick-0.043
Tokenhe
Token ID258
Feature activation+8.63e-03

Pos logit contributions
ercise+0.172
isi+0.170
iable+0.157
ometime+0.147
elling+0.147
Neg logit contributions
 Nick-0.157
apy-0.155
 Mike-0.143
 Megan-0.141
 Mam-0.137
Token it
Token ID340
Feature activation-5.96e-02

Pos logit contributions
apy+0.017
 Mam+0.017
 Nick+0.017
 Liz+0.016
 Megan+0.016
Neg logit contributions
ercise-0.012
ock-0.012
iable-0.011
isi-0.011
at-0.011
Token together
Token ID1978
Feature activation-3.18e-03

Pos logit contributions
isi+0.092
ercise+0.089
iable+0.084
ock+0.082
off+0.079
Neg logit contributions
apy-0.114
 Nick-0.113
 Mam-0.109
 Liz-0.106
 Megan-0.105
Token".
Token ID1911
Feature activation-6.28e-03

Pos logit contributions
ercise+0.004
isi+0.004
iable+0.004
ock+0.004
off+0.004
Neg logit contributions
apy-0.006
 Nick-0.006
 Mam-0.006
 Liz-0.006
 Megan-0.006
Token
Token ID220
Feature activation-5.77e-04

Pos logit contributions
ercise+0.011
off+0.011
isi+0.010
iable+0.010
ock+0.010
Neg logit contributions
apy-0.010
 Nick-0.010
 Mam-0.010
 spe-0.009
 Megan-0.009
Token"
Token ID1
Feature activation+1.79e-02

Pos logit contributions
isi+0.023
ercise+0.023
iable+0.023
ock+0.022
at+0.022
Neg logit contributions
apy-0.027
 Nick-0.026
 Mam-0.026
 Liz-0.025
 Megan-0.025
TokenCan
Token ID6090
Feature activation-3.02e-02

Pos logit contributions
apy+0.026
 Nick+0.026
 Mam+0.025
 Megan+0.024
 Mil+0.024
Neg logit contributions
iable-0.034
isi-0.034
ercise-0.034
ock-0.033
at-0.032
Token I
Token ID314
Feature activation-3.22e-02

Pos logit contributions
isi+0.061
ercise+0.060
ock+0.060
iable+0.058
at+0.057
Neg logit contributions
apy-0.043
 Nick-0.043
 Mam-0.041
 Liz-0.040
 Megan-0.039
Token try
Token ID1949
Feature activation-7.39e-02

Pos logit contributions
ercise+0.061
isi+0.060
iable+0.059
ock+0.059
off+0.056
Neg logit contributions
apy-0.049
 Mam-0.048
 Nick-0.048
 Liz-0.046
 Jen-0.044
Token your
Token ID534
Feature activation-4.42e-02

Pos logit contributions
isi+0.148
ercise+0.137
vious+0.137
bye+0.134
off+0.134
Neg logit contributions
 L-0.116
 Liz-0.115
 Nick-0.114
apy-0.111
 Mam-0.108
Token cap
Token ID1451
Feature activation-9.68e-02

Pos logit contributions
isi+0.081
iable+0.081
ercise+0.079
ock+0.079
off+0.076
Neg logit contributions
 L-0.073
 Liz-0.072
 Mam-0.069
 Jen-0.068
 Mil-0.068
Token?"
Token ID1701
Feature activation+2.31e-02

Pos logit contributions
ercise+0.189
isi+0.186
off+0.180
ock+0.178
ience+0.173
Neg logit contributions
 Liz-0.132
 L-0.127
apy-0.125
 Jen-0.123
 shovel-0.115
Token Sam
Token ID3409
Feature activation+5.51e-03

Pos logit contributions
apy+0.035
 spe+0.033
uzz+0.032
 extingu+0.032
 Mam+0.031
Neg logit contributions
ercise-0.040
isi-0.039
vious-0.037
iable-0.037
up-0.036
Token asks
Token ID7893
Feature activation+6.42e-02

Pos logit contributions
 Nick+0.008
 Megan+0.007
 gasped+0.007
 Mam+0.007
 Mil+0.007
Neg logit contributions
isi-0.011
ercise-0.011
iable-0.011
at-0.011
ock-0.011
Token Ben
Token ID3932
Feature activation-2.63e-02

Pos logit contributions
apy+0.136
 spe+0.129
 Nick+0.124
 Mam+0.122
 Kel+0.120
Neg logit contributions
ock-0.079
isi-0.078
iable-0.075
que-0.074
ercise-0.073
Token.
Token ID13
Feature activation+4.35e-02

Pos logit contributions
ercise+0.047
isi+0.046
iable+0.045
ock+0.045
off+0.043
Neg logit contributions
apy-0.042
 Nick-0.042
 Mam-0.041
 Liz-0.039
 Megan-0.038
Token.
Token ID13
Feature activation+7.15e-03

Pos logit contributions
apy+0.015
 Nick+0.015
 Mam+0.015
 Megan+0.014
 Liz+0.014
Neg logit contributions
ercise-0.014
isi-0.014
iable-0.014
ock-0.013
at-0.012
Token Can
Token ID1680
Feature activation-2.13e-02

Pos logit contributions
apy+0.012
 Nick+0.011
 Mam+0.011
 Megan+0.011
 gasped+0.011
Neg logit contributions
ercise-0.012
isi-0.012
ock-0.011
off-0.011
iable-0.011
Token we
Token ID356
Feature activation-4.39e-02

Pos logit contributions
isi+0.047
ercise+0.046
ock+0.045
at+0.045
iable+0.044
Neg logit contributions
apy-0.028
 Nick-0.028
 Mam-0.026
 Liz-0.026
 Megan-0.025
Token come
Token ID1282
Feature activation-2.56e-02

Pos logit contributions
ercise+0.079
isi+0.079
ock+0.078
iable+0.076
les+0.075
Neg logit contributions
 Mam-0.068
 Nick-0.067
apy-0.067
 Mike-0.064
 shovel-0.063
Token on
Token ID319
Feature activation+2.95e-04

Pos logit contributions
isi+0.047
ercise+0.046
iable+0.046
ock+0.045
vious+0.044
Neg logit contributions
 Nick-0.041
apy-0.039
 Mam-0.039
 Liz-0.038
 Mike-0.038
Token board
Token ID3096
Feature activation-9.62e-02

Pos logit contributions
 Nick+0.000
 Mike+0.000
 Mam+0.000
 shovel+0.000
apy+0.000
Neg logit contributions
isi-0.001
at-0.001
iable-0.001
ercise-0.001
ock-0.001
Token?"
Token ID1701
Feature activation+2.37e-02

Pos logit contributions
isi+0.174
ercise+0.159
elling+0.158
isy+0.153
orn+0.151
Neg logit contributions
 L-0.143
 Nick-0.143
 Mike-0.140
 their-0.138
 Liz-0.133
Token Lily
Token ID20037
Feature activation+1.50e-02

Pos logit contributions
apy+0.031
 Nick+0.031
 Mam+0.030
 toes+0.028
 Megan+0.028
Neg logit contributions
ercise-0.048
isi-0.047
iable-0.046
ock-0.046
off-0.044
Token asked
Token ID1965
Feature activation+4.00e-02

Pos logit contributions
 Nick+0.024
 Mam+0.023
apy+0.023
 Megan+0.022
 Liz+0.022
Neg logit contributions
ercise-0.027
isi-0.026
iable-0.026
ock-0.026
at-0.025
Token politely
Token ID34313
Feature activation+2.46e-02

Pos logit contributions
apy+0.082
 Mam+0.078
 Nick+0.078
 Megan+0.074
 Madd+0.074
Neg logit contributions
iable-0.053
ercise-0.052
ock-0.051
isi-0.051
orting-0.047
Token.
Token ID13
Feature activation+2.23e-02

Pos logit contributions
apy+0.048
 Nick+0.045
 Mam+0.044
 Liz+0.042
 Madd+0.042
Neg logit contributions
ercise-0.036
isi-0.036
ock-0.035
iable-0.035
off-0.034
Token day
Token ID1110
Feature activation+4.28e-03

Pos logit contributions
ercise+0.002
isi+0.002
iable+0.002
ock+0.002
off+0.002
Neg logit contributions
apy-0.005
 Nick-0.004
 Mam-0.004
 Liz-0.004
 Megan-0.004
Token,
Token ID11
Feature activation-5.26e-03

Pos logit contributions
 Nick+0.010
 Mam+0.010
 Megan+0.009
 Mick+0.009
 Mil+0.009
Neg logit contributions
ercise-0.005
iable-0.004
ock-0.004
isi-0.004
que-0.004
Token Tim
Token ID5045
Feature activation-2.12e-02

Pos logit contributions
ercise+0.011
iable+0.011
isi+0.011
ock+0.010
 course+0.010
Neg logit contributions
 Nick-0.006
 Mam-0.006
uzz-0.006
 Megan-0.006
 ankles-0.006
Token wanted
Token ID2227
Feature activation-4.75e-02

Pos logit contributions
isi+0.042
ercise+0.041
iable+0.040
ock+0.040
at+0.037
Neg logit contributions
 Nick-0.030
 Mam-0.029
apy-0.029
 Liz-0.028
 gasped-0.027
Token to
Token ID284
Feature activation-1.58e-05

Pos logit contributions
isi+0.067
ercise+0.067
iable+0.065
ock+0.063
at+0.060
Neg logit contributions
 Nick-0.096
apy-0.095
 Mam-0.094
 Liz-0.090
 Megan-0.089
Token bat
Token ID7365
Feature activation-9.58e-02

Pos logit contributions
ercise+0.000
isi+0.000
iable+0.000
ock+0.000
at+0.000
Neg logit contributions
apy-0.000
 Nick-0.000
 Mam-0.000
 Liz-0.000
 Megan-0.000
Tokenhe
Token ID258
Feature activation+1.52e-02

Pos logit contributions
ercise+0.212
ience+0.202
isi+0.195
iable+0.193
elling+0.179
Neg logit contributions
apy-0.121
 Nick-0.117
 L-0.113
 Mike-0.106
 holding-0.104
Token in
Token ID287
Feature activation+5.05e-02

Pos logit contributions
apy+0.026
 Nick+0.026
 Mam+0.025
 Liz+0.024
 Megan+0.024
Neg logit contributions
ercise-0.025
isi-0.025
iable-0.025
ock-0.024
off-0.023
Token the
Token ID262
Feature activation-1.25e-02

Pos logit contributions
apy+0.094
 Nick+0.089
 Madd+0.086
 Megan+0.085
uzz+0.085
Neg logit contributions
ock-0.078
ercise-0.077
iable-0.074
off-0.073
isi-0.072
Token tub
Token ID12202
Feature activation-1.86e-03

Pos logit contributions
isi+0.027
iable+0.025
ercise+0.025
ock+0.024
at+0.023
Neg logit contributions
apy-0.017
 Mam-0.017
 Nick-0.017
 Mick-0.015
 shovel-0.015
Token with
Token ID351
Feature activation+2.73e-02

Pos logit contributions
ercise+0.003
ock+0.003
isi+0.003
iable+0.003
off+0.003
Neg logit contributions
apy-0.003
 Nick-0.003
 Mam-0.003
 Megan-0.003
 Liz-0.003
Token a
Token ID257
Feature activation-4.12e-02

Pos logit contributions
isi+0.091
ercise+0.090
iable+0.088
ock+0.086
off+0.083
Neg logit contributions
apy-0.080
 Nick-0.079
 Mam-0.075
 Liz-0.073
 Megan-0.073
Token game
Token ID983
Feature activation-3.55e-02

Pos logit contributions
ercise+0.067
isi+0.065
iable+0.062
at+0.062
ock+0.062
Neg logit contributions
apy-0.074
 Nick-0.074
 Mam-0.071
 Megan-0.069
 Liz-0.068
Token!
Token ID0
Feature activation-8.53e-03

Pos logit contributions
ercise+0.051
isi+0.050
ock+0.050
iable+0.049
off+0.047
Neg logit contributions
apy-0.070
 Nick-0.067
 Mam-0.067
 Megan-0.063
 Liz-0.063
Token We
Token ID775
Feature activation+4.54e-03

Pos logit contributions
ercise+0.016
isi+0.015
iable+0.015
ock+0.015
off+0.015
Neg logit contributions
apy-0.013
 Nick-0.012
 Mam-0.012
 Megan-0.011
 toes-0.011
Token can
Token ID460
Feature activation-1.93e-02

Pos logit contributions
apy+0.008
 Nick+0.008
 Mam+0.008
 Liz+0.007
 Megan+0.007
Neg logit contributions
ercise-0.007
isi-0.007
iable-0.007
ock-0.007
off-0.007
Token bounce
Token ID20110
Feature activation-9.56e-02

Pos logit contributions
ercise+0.034
isi+0.034
ock+0.033
iable+0.033
off+0.032
Neg logit contributions
 Nick-0.031
apy-0.031
 Mam-0.030
 Liz-0.029
 Megan-0.029
Token high
Token ID1029
Feature activation-9.94e-03

Pos logit contributions
isi+0.195
at+0.178
iable+0.178
ercise+0.175
up+0.169
Neg logit contributions
 Nick-0.142
 L-0.138
apy-0.137
 Liz-0.134
 Megan-0.127
Token and
Token ID290
Feature activation-2.89e-02

Pos logit contributions
isi+0.019
iable+0.018
ercise+0.017
ock+0.017
up+0.016
Neg logit contributions
 Nick-0.017
 Megan-0.015
 toes-0.015
 Mike-0.015
 spe-0.015
Token try
Token ID1949
Feature activation-5.81e-02

Pos logit contributions
ercise+0.050
isi+0.048
iable+0.048
ock+0.047
off+0.045
Neg logit contributions
apy-0.049
 Nick-0.048
 Mam-0.047
 Liz-0.045
 Megan-0.045
Token to
Token ID284
Feature activation+3.46e-03

Pos logit contributions
isi+0.098
ercise+0.093
iable+0.089
ock+0.088
at+0.087
Neg logit contributions
 Nick-0.106
apy-0.102
 Mam-0.098
 Megan-0.097
 Liz-0.096
Token touch
Token ID3638
Feature activation-4.89e-03

Pos logit contributions
apy+0.006
 Nick+0.006
 Mam+0.006
 Liz+0.005
 Megan+0.005
Neg logit contributions
ercise-0.006
isi-0.006
iable-0.006
ock-0.006
at-0.005
Token fake
Token ID8390
Feature activation+2.53e-02

Pos logit contributions
apy+0.039
 Nick+0.038
 Mam+0.037
 Megan+0.036
 Liz+0.036
Neg logit contributions
ercise-0.029
isi-0.029
iable-0.028
ock-0.028
off-0.026
Token bunny
Token ID44915
Feature activation-2.48e-03

Pos logit contributions
apy+0.047
 Nick+0.045
 Mam+0.044
 Megan+0.043
 Liz+0.043
Neg logit contributions
ercise-0.039
isi-0.038
ock-0.038
iable-0.037
off-0.035
Token.
Token ID13
Feature activation+3.44e-03

Pos logit contributions
ercise+0.004
ock+0.004
isi+0.004
iable+0.003
off+0.003
Neg logit contributions
apy-0.005
 Mam-0.005
 Nick-0.005
 Megan-0.004
 Liz-0.004
Token You
Token ID921
Feature activation+1.71e-03

Pos logit contributions
apy+0.006
 Nick+0.005
 Mam+0.005
 toes+0.005
 shovel+0.005
Neg logit contributions
ercise-0.006
isi-0.006
ock-0.005
iable-0.005
off-0.005
Token can
Token ID460
Feature activation-2.07e-02

Pos logit contributions
apy+0.003
 Nick+0.003
 Mam+0.003
 Liz+0.003
 Megan+0.002
Neg logit contributions
ercise-0.003
isi-0.003
ock-0.003
iable-0.003
off-0.003
Token bounce
Token ID20110
Feature activation-9.56e-02

Pos logit contributions
ercise+0.035
isi+0.033
iable+0.033
ock+0.033
off+0.031
Neg logit contributions
 Nick-0.037
apy-0.036
 Mam-0.035
 Madd-0.033
 Mike-0.033
Token it
Token ID340
Feature activation-4.22e-02

Pos logit contributions
isi+0.219
at+0.206
ercise+0.205
iable+0.202
ometime+0.196
Neg logit contributions
 Nick-0.113
 L-0.112
apy-0.107
 Liz-0.105
 Madd-0.101
Token like
Token ID588
Feature activation+4.61e-03

Pos logit contributions
isi+0.085
ercise+0.081
iable+0.075
ock+0.072
up+0.072
Neg logit contributions
 Nick-0.062
 toes-0.058
 L-0.057
 Megan-0.057
apy-0.057
Token a
Token ID257
Feature activation+5.43e-03

Pos logit contributions
 Nick+0.009
apy+0.009
 Mam+0.008
 Liz+0.008
 Megan+0.008
Neg logit contributions
isi-0.007
ercise-0.007
iable-0.007
ock-0.007
at-0.006
Token ball
Token ID2613
Feature activation-3.55e-02

Pos logit contributions
apy+0.010
 Nick+0.010
 Mam+0.010
 Liz+0.009
 Megan+0.009
Neg logit contributions
ercise-0.009
isi-0.008
iable-0.008
ock-0.008
off-0.008
Token!"
Token ID2474
Feature activation+1.35e-03

Pos logit contributions
ercise+0.065
isi+0.065
iable+0.062
at+0.058
ock+0.058
Neg logit contributions
 Nick-0.055
apy-0.054
 L-0.052
 Liz-0.051
 Mam-0.051
Token.
Token ID13
Feature activation+1.20e-02

Pos logit contributions
 Nick+0.001
apy+0.001
 Mam+0.001
 Megan+0.001
 Liz+0.001
Neg logit contributions
ercise-0.001
iable-0.001
isi-0.001
ock-0.001
off-0.001
Token She
Token ID1375
Feature activation+2.14e-02

Pos logit contributions
apy+0.020
 Nick+0.020
 Mam+0.019
 spe+0.018
 toes+0.018
Neg logit contributions
isi-0.020
ercise-0.019
ock-0.018
vious-0.018
iable-0.018
Token says
Token ID1139
Feature activation+1.15e-02

Pos logit contributions
 Nick+0.032
 L+0.031
 gasped+0.030
 Mil+0.030
 Liz+0.029
Neg logit contributions
iable-0.041
ercise-0.039
isi-0.039
ock-0.039
at-0.038
Token they
Token ID484
Feature activation-5.31e-03

Pos logit contributions
apy+0.015
 Nick+0.015
 Mam+0.014
 Megan+0.013
 Liz+0.013
Neg logit contributions
ercise-0.024
isi-0.024
iable-0.023
ock-0.023
off-0.022
Token can
Token ID460
Feature activation-3.00e-02

Pos logit contributions
isi+0.011
ercise+0.010
iable+0.010
ock+0.010
off+0.009
Neg logit contributions
 Nick-0.007
apy-0.007
 Mam-0.007
 Liz-0.007
 gasped-0.006
Token bounce
Token ID20110
Feature activation-9.54e-02

Pos logit contributions
ercise+0.058
isi+0.057
vious+0.056
iable+0.056
ock+0.053
Neg logit contributions
 Nick-0.045
apy-0.044
 Mam-0.043
 Mike-0.040
 Liz-0.040
Token some
Token ID617
Feature activation-1.85e-03

Pos logit contributions
isi+0.172
ercise+0.167
iable+0.164
at+0.161
off+0.156
Neg logit contributions
 Nick-0.158
apy-0.156
 L-0.151
 Liz-0.149
 Megan-0.149
Token more
Token ID517
Feature activation+1.28e-02

Pos logit contributions
isi+0.003
iable+0.003
ercise+0.003
at+0.003
ock+0.003
Neg logit contributions
apy-0.003
 Nick-0.003
 Mam-0.003
 shovel-0.003
 toes-0.003
Token when
Token ID618
Feature activation+4.81e-02

Pos logit contributions
apy+0.022
 Nick+0.021
 toes+0.020
 Mam+0.020
 Megan+0.020
Neg logit contributions
isi-0.022
iable-0.022
ercise-0.021
at-0.020
ock-0.020
Token they
Token ID484
Feature activation+1.55e-02

Pos logit contributions
 extingu+0.077
 Mam+0.077
apy+0.076
 Nick+0.075
uzz+0.074
Neg logit contributions
ercise-0.072
iable-0.069
ock-0.068
isi-0.068
 poems-0.066
Token get
Token ID651
Feature activation-1.70e-02

Pos logit contributions
apy+0.024
 Nick+0.023
 Mam+0.022
 Mil+0.021
 L+0.021
Neg logit contributions
isi-0.029
ercise-0.028
ock-0.028
iable-0.027
off-0.026
Token his
Token ID465
Feature activation+1.57e-02

Pos logit contributions
isi+0.072
ercise+0.071
ock+0.070
iable+0.070
at+0.068
Neg logit contributions
apy-0.070
 Nick-0.069
 Mam-0.068
 Liz-0.065
 Megan-0.063
Token friends
Token ID2460
Feature activation-1.52e-02

Pos logit contributions
apy+0.026
 Nick+0.026
 Mam+0.024
 Megan+0.024
 Liz+0.024
Neg logit contributions
ercise-0.028
isi-0.027
iable-0.026
ock-0.025
off-0.025
Token.
Token ID13
Feature activation-1.48e-02

Pos logit contributions
ercise+0.025
iable+0.025
isi+0.024
ock+0.024
off+0.023
Neg logit contributions
apy-0.027
 Nick-0.026
 Mam-0.026
 Liz-0.025
 Megan-0.025
Token He
Token ID679
Feature activation+2.49e-03

Pos logit contributions
ercise+0.023
isi+0.023
iable+0.022
ock+0.022
off+0.021
Neg logit contributions
apy-0.027
 Nick-0.027
 Mam-0.026
 Megan-0.025
 Liz-0.025
Token can
Token ID460
Feature activation-2.30e-02

Pos logit contributions
 Nick+0.004
 Mam+0.004
apy+0.004
 Mil+0.004
 L+0.004
Neg logit contributions
isi-0.005
ock-0.004
iable-0.004
ercise-0.004
at-0.004
Token bounce
Token ID20110
Feature activation-9.54e-02

Pos logit contributions
isi+0.044
ock+0.043
ercise+0.043
at+0.042
orn+0.041
Neg logit contributions
apy-0.034
 Nick-0.033
 Mam-0.032
 Mike-0.030
 Liz-0.030
Token the
Token ID262
Feature activation-2.42e-02

Pos logit contributions
isi+0.206
at+0.197
ercise+0.193
iable+0.189
ometime+0.181
Neg logit contributions
 L-0.131
 Nick-0.124
 Liz-0.117
apy-0.116
 Mike-0.114
Token ball
Token ID2613
Feature activation-4.65e-02

Pos logit contributions
isi+0.049
ercise+0.048
iable+0.046
at+0.045
ock+0.045
Neg logit contributions
 shovel-0.033
apy-0.032
 Nick-0.032
 toes-0.032
 Mam-0.031
Token,
Token ID11
Feature activation+5.33e-03

Pos logit contributions
isi+0.102
ercise+0.096
iable+0.093
off+0.087
erence+0.087
Neg logit contributions
 Nick-0.060
 shovel-0.060
apy-0.060
 L-0.059
 Liz-0.058
Token pass
Token ID1208
Feature activation-2.65e-02

Pos logit contributions
 Nick+0.008
apy+0.008
 Mam+0.008
 Liz+0.008
 shovel+0.008
Neg logit contributions
isi-0.010
ercise-0.010
iable-0.009
ock-0.009
at-0.009
Token the
Token ID262
Feature activation-1.96e-02

Pos logit contributions
ercise+0.050
isi+0.050
iable+0.049
ock+0.048
at+0.046
Neg logit contributions
apy-0.040
 Nick-0.040
 Mam-0.038
 Liz-0.037
 Megan-0.036
Token,
Token ID11
Feature activation+4.28e-02

Pos logit contributions
ercise+0.007
isi+0.007
iable+0.006
ock+0.006
off+0.006
Neg logit contributions
apy-0.009
 Nick-0.009
 Mam-0.009
 Liz-0.009
 Megan-0.008
Token to
Token ID284
Feature activation+3.17e-02

Pos logit contributions
apy+0.076
 Nick+0.075
 Mam+0.074
 Megan+0.072
 Madd+0.068
Neg logit contributions
ercise-0.068
ock-0.068
iable-0.066
isi-0.063
off-0.062
Tokenot
Token ID313
Feature activation-8.63e-02

Pos logit contributions
apy+0.055
 Nick+0.054
 Mam+0.053
 Liz+0.050
 Megan+0.050
Neg logit contributions
ercise-0.053
isi-0.052
iable-0.051
ock-0.051
off-0.048
Token,
Token ID11
Feature activation+2.55e-02

Pos logit contributions
isi+0.136
ercise+0.136
iable+0.129
ock+0.122
off+0.122
Neg logit contributions
 Nick-0.156
apy-0.154
 Liz-0.147
 Mam-0.147
 Mike-0.143
Token to
Token ID284
Feature activation+2.18e-02

Pos logit contributions
apy+0.045
 Nick+0.044
 Mam+0.043
 Megan+0.041
 Liz+0.040
Neg logit contributions
ercise-0.042
ock-0.041
iable-0.041
isi-0.040
off-0.038
Tokenot
Token ID313
Feature activation-9.54e-02

Pos logit contributions
apy+0.038
 Nick+0.038
 Mam+0.037
 Megan+0.035
 Liz+0.035
Neg logit contributions
ercise-0.036
isi-0.035
iable-0.035
ock-0.035
off-0.033
Token!"
Token ID2474
Feature activation-4.17e-03

Pos logit contributions
isi+0.152
ercise+0.152
iable+0.144
ock+0.135
off+0.135
Neg logit contributions
 Nick-0.172
apy-0.170
 Mam-0.162
 Liz-0.162
 Mike-0.158
Token they
Token ID484
Feature activation-4.66e-04

Pos logit contributions
ercise+0.006
isi+0.006
ock+0.005
up+0.005
iable+0.005
Neg logit contributions
 Nick-0.008
apy-0.008
 Mam-0.008
 spe-0.007
 Megan-0.007
Token shouted
Token ID17293
Feature activation+1.27e-02

Pos logit contributions
ercise+0.001
ock+0.001
isi+0.001
iable+0.001
ches+0.001
Neg logit contributions
apy-0.001
 Mam-0.001
 Nick-0.001
 Megan-0.001
 Madd-0.001
Token.
Token ID13
Feature activation+1.86e-02

Pos logit contributions
apy+0.026
 Nick+0.026
 Mam+0.026
 Megan+0.025
 Mick+0.024
Neg logit contributions
ercise-0.015
ock-0.015
iable-0.014
les-0.014
ches-0.014
Token
Token ID198
Feature activation-3.81e-03

Pos logit contributions
 Nick+0.035
 spe+0.034
apy+0.034
 Megan+0.033
 Esk+0.033
Neg logit contributions
ercise-0.023
isi-0.022
off-0.021
ock-0.021
ches-0.021
Token sharp
Token ID7786
Feature activation+2.83e-02

Pos logit contributions
ercise+0.003
isi+0.003
ock+0.003
iable+0.003
vious+0.003
Neg logit contributions
 Nick-0.004
 Mam-0.004
apy-0.004
 Mick-0.004
 Megan-0.004
Token teeth
Token ID9941
Feature activation+2.51e-02

Pos logit contributions
 Nick+0.041
 Mam+0.040
apy+0.039
 Megan+0.038
 Mick+0.037
Neg logit contributions
ercise-0.054
les-0.052
ock-0.051
isi-0.051
vious-0.050
Token.
Token ID13
Feature activation+2.71e-02

Pos logit contributions
apy+0.047
 Nick+0.047
 Mam+0.046
 Madd+0.044
 Megan+0.043
Neg logit contributions
ock-0.038
ercise-0.037
iable-0.037
isi-0.037
off-0.035
Token It
Token ID632
Feature activation+7.07e-03

Pos logit contributions
apy+0.051
 toes+0.050
 Mam+0.050
 Kel+0.050
 Nick+0.049
Neg logit contributions
ercise-0.033
vious-0.033
isi-0.033
orn-0.032
ock-0.032
Token jumped
Token ID11687
Feature activation-2.38e-02

Pos logit contributions
 Mam+0.012
apy+0.012
 Nick+0.012
 Mick+0.011
 Mike+0.011
Neg logit contributions
ercise-0.011
ches-0.011
isi-0.011
iable-0.010
ock-0.010
Token out
Token ID503
Feature activation+9.31e-02

Pos logit contributions
ercise+0.041
isi+0.041
iable+0.040
ock+0.038
off+0.037
Neg logit contributions
apy-0.041
 Nick-0.041
 Mam-0.039
 Liz-0.038
 Megan-0.038
Token of
Token ID286
Feature activation+5.29e-02

Pos logit contributions
apy+0.208
 Nick+0.207
 Mam+0.205
 Megan+0.193
 Kel+0.193
Neg logit contributions
ock-0.111
isi-0.095
les-0.093
vious-0.092
ches-0.087
Token the
Token ID262
Feature activation-4.22e-03

Pos logit contributions
apy+0.118
spe+0.110
bers+0.108
 Nick+0.107
 Mam+0.105
Neg logit contributions
 course-0.066
ock-0.063
isi-0.057
ty-0.056
 me-0.054
Token bush
Token ID24484
Feature activation+3.57e-02

Pos logit contributions
ercise+0.008
isi+0.008
iable+0.008
ock+0.008
at+0.007
Neg logit contributions
apy-0.007
 Nick-0.006
 Mam-0.006
 Liz-0.006
 Megan-0.006
Token and
Token ID290
Feature activation-2.23e-02

Pos logit contributions
apy+0.076
 Nick+0.074
 Mam+0.073
 Liz+0.070
 Megan+0.070
Neg logit contributions
ercise-0.046
isi-0.045
iable-0.044
ock-0.044
off-0.041
Token ran
Token ID4966
Feature activation-2.18e-02

Pos logit contributions
ercise+0.034
ches+0.032
les+0.029
iable+0.029
ty+0.029
Neg logit contributions
 Mam-0.041
apy-0.039
uzz-0.039
 Nick-0.039
obby-0.039
Token noticed
Token ID6810
Feature activation-3.92e-03

Pos logit contributions
ercise+0.003
isi+0.003
iable+0.003
ock+0.003
off+0.002
Neg logit contributions
apy-0.002
 Nick-0.002
 Mam-0.002
 Liz-0.002
 Megan-0.002
Token a
Token ID257
Feature activation+5.28e-03

Pos logit contributions
ercise+0.006
isi+0.005
ock+0.005
iable+0.005
off+0.005
Neg logit contributions
apy-0.008
 Nick-0.007
 Mam-0.007
 Megan-0.007
 Liz-0.007
Token light
Token ID1657
Feature activation+3.25e-02

Pos logit contributions
 Nick+0.010
apy+0.010
 Liz+0.010
 Megan+0.010
 Mam+0.010
Neg logit contributions
ercise-0.007
iable-0.007
isi-0.007
ock-0.007
 poem-0.007
Token in
Token ID287
Feature activation+8.65e-02

Pos logit contributions
apy+0.059
 Nick+0.058
 Mam+0.057
 Liz+0.055
 Megan+0.055
Neg logit contributions
ercise-0.051
ock-0.050
isi-0.049
iable-0.048
off-0.046
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
apy+0.181
 Nick+0.157
 Mam+0.156
 ankles+0.154
 toes+0.152
Neg logit contributions
ock-0.123
 course-0.118
isi-0.114
ercise-0.112
off-0.106
Token dark
Token ID3223
Feature activation+8.05e-02

Pos logit contributions
apy+0.024
 Nick+0.024
 Mam+0.024
 Liz+0.022
 Megan+0.022
Neg logit contributions
ercise-0.019
isi-0.019
iable-0.019
ock-0.018
off-0.017
Token.
Token ID13
Feature activation+6.29e-03

Pos logit contributions
apy+0.170
 Nick+0.159
 Mam+0.156
 Megan+0.151
 Liz+0.149
Neg logit contributions
ock-0.113
isi-0.102
ercise-0.101
off-0.100
les-0.100
Token He
Token ID679
Feature activation+1.23e-02

Pos logit contributions
apy+0.013
 spe+0.012
 toes+0.012
 dripping+0.011
 ankles+0.011
Neg logit contributions
isi-0.007
ercise-0.007
orn-0.007
ometime-0.007
iable-0.006
Token followed
Token ID3940
Feature activation-5.12e-03

Pos logit contributions
apy+0.021
 Nick+0.020
 Mam+0.020
 Liz+0.019
 Megan+0.019
Neg logit contributions
ercise-0.020
isi-0.019
iable-0.019
ock-0.019
ches-0.019
Token the
Token ID262
Feature activation-3.42e-02

Pos logit contributions
ercise+0.009
isi+0.009
ock+0.008
iable+0.008
off+0.008
Neg logit contributions
apy-0.009
 Nick-0.008
 Mam-0.008
 Megan-0.008
 Liz-0.008
Token light
Token ID1657
Feature activation+1.01e-02

Pos logit contributions
ock+0.048
ercise+0.046
isi+0.044
up+0.043
iable+0.043
Neg logit contributions
apy-0.067
 Nick-0.064
 Mam-0.063
 Liz-0.061
 Megan-0.061
Token?"
Token ID1701
Feature activation+3.14e-02

Pos logit contributions
isi+0.004
ercise+0.004
ock+0.004
iable+0.004
off+0.003
Neg logit contributions
 Nick-0.004
apy-0.004
 Mam-0.004
 Mike-0.004
 Megan-0.004
Token one
Token ID530
Feature activation+5.43e-03

Pos logit contributions
apy+0.048
 Nick+0.047
 Mam+0.046
 Liz+0.043
 Megan+0.043
Neg logit contributions
ercise-0.059
isi-0.058
iable-0.057
ock-0.057
off-0.055
Token of
Token ID286
Feature activation+6.77e-02

Pos logit contributions
apy+0.010
 Nick+0.010
 Mam+0.010
 Liz+0.010
 Megan+0.009
Neg logit contributions
ercise-0.008
isi-0.008
ock-0.008
iable-0.008
off-0.007
Token the
Token ID262
Feature activation-7.69e-03

Pos logit contributions
apy+0.122
 Mam+0.114
 shovel+0.110
 Liz+0.109
 Nick+0.109
Neg logit contributions
ock-0.111
isi-0.111
ercise-0.107
iable-0.103
les-0.103
Token people
Token ID661
Feature activation+3.97e-02

Pos logit contributions
ercise+0.013
isi+0.013
iable+0.013
ock+0.013
off+0.012
Neg logit contributions
apy-0.013
 Nick-0.013
 Mam-0.013
 Liz-0.012
 Megan-0.012
Token in
Token ID287
Feature activation+7.44e-02

Pos logit contributions
apy+0.069
 Mam+0.066
 Nick+0.064
 Liz+0.063
 spe+0.062
Neg logit contributions
ock-0.066
iable-0.064
isi-0.062
ercise-0.062
les-0.061
Token the
Token ID262
Feature activation-7.05e-04

Pos logit contributions
apy+0.149
 Nick+0.138
 Madd+0.136
 Mam+0.136
 Kel+0.134
Neg logit contributions
isi-0.105
ock-0.099
ercise-0.099
vious-0.097
 course-0.096
Token crowd
Token ID4315
Feature activation+2.54e-02

Pos logit contributions
ercise+0.001
isi+0.001
iable+0.001
ock+0.001
off+0.001
Neg logit contributions
apy-0.001
 Nick-0.001
 Mam-0.001
 Liz-0.001
 Megan-0.001
Token asked
Token ID1965
Feature activation+5.20e-02

Pos logit contributions
apy+0.047
 Mam+0.047
 Nick+0.046
 Liz+0.044
 Mick+0.044
Neg logit contributions
ock-0.037
ercise-0.037
iable-0.036
isi-0.036
les-0.036
Token.
Token ID13
Feature activation+1.51e-02

Pos logit contributions
apy+0.107
 Mam+0.100
 Nick+0.098
 shovel+0.097
 Liz+0.096
Neg logit contributions
isi-0.068
ercise-0.068
ock-0.067
iable-0.066
les-0.065
Token
Token ID198
Feature activation+5.62e-03

Pos logit contributions
apy+0.023
 Mam+0.022
 Liz+0.021
 Nick+0.021
 shovel+0.020
Neg logit contributions
ercise-0.028
isi-0.027
ock-0.026
iable-0.026
off-0.026
Token the
Token ID262
Feature activation-1.75e-02

Pos logit contributions
ercise+0.039
isi+0.038
ock+0.038
iable+0.037
off+0.036
Neg logit contributions
apy-0.035
 Nick-0.034
 Mam-0.033
 Megan-0.031
 Mil-0.030
Token bird
Token ID6512
Feature activation-1.63e-02

Pos logit contributions
ercise+0.027
iable+0.027
ock+0.026
isi+0.026
at+0.025
Neg logit contributions
apy-0.033
 Nick-0.032
 Mam-0.032
 Megan-0.030
 shovel-0.030
Token were
Token ID547
Feature activation-6.64e-03

Pos logit contributions
ercise+0.031
isi+0.031
iable+0.030
ock+0.029
off+0.028
Neg logit contributions
apy-0.025
 Nick-0.023
 Mam-0.023
 Liz-0.022
 spe-0.022
Token the
Token ID262
Feature activation+1.33e-02

Pos logit contributions
ercise+0.011
isi+0.011
ock+0.011
iable+0.011
off+0.010
Neg logit contributions
apy-0.012
 Nick-0.011
 Mam-0.011
 Liz-0.011
 Megan-0.011
Token best
Token ID1266
Feature activation+5.32e-03

Pos logit contributions
 Mam+0.022
 shovel+0.021
 spe+0.021
 Nick+0.021
 tad+0.021
Neg logit contributions
les-0.022
ercise-0.021
at-0.021
ches-0.021
ock-0.020
Token of
Token ID286
Feature activation+7.20e-02

Pos logit contributions
apy+0.011
 Nick+0.010
 Mam+0.010
 Megan+0.010
 Liz+0.010
Neg logit contributions
isi-0.007
ercise-0.007
ock-0.007
iable-0.007
off-0.007
Token friends
Token ID2460
Feature activation-2.37e-03

Pos logit contributions
apy+0.125
 Nick+0.124
 Mam+0.122
 Megan+0.115
 Liz+0.115
Neg logit contributions
ercise-0.121
isi-0.119
ock-0.116
iable-0.115
off-0.110
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
ercise+0.003
isi+0.003
ock+0.003
iable+0.003
off+0.003
Neg logit contributions
apy-0.005
 Mam-0.004
 Nick-0.004
 Megan-0.004
 Liz-0.004
Token<|endoftext|>
Token ID50256
Feature activation-1.01e-02

Pos logit contributions
ercise+0.023
isi+0.023
iable+0.022
ock+0.022
off+0.021
Neg logit contributions
apy-0.016
 Nick-0.015
 Mam-0.015
 Liz-0.014
 Megan-0.014
TokenOne
Token ID3198
Feature activation-2.10e-02

Pos logit contributions
isi+0.015
ock+0.015
ercise+0.014
off+0.014
orn+0.014
Neg logit contributions
apy-0.019
 Mam-0.018
 Nick-0.017
 toes-0.017
 ankles-0.017
Token day
Token ID1110
Feature activation-2.00e-02

Pos logit contributions
ercise+0.031
iable+0.031
isi+0.030
ock+0.029
les+0.028
Neg logit contributions
apy-0.040
 Nick-0.039
 Mam-0.039
 Megan-0.038
 Liz-0.037
Token saw
Token ID2497
Feature activation-9.60e-03

Pos logit contributions
ercise+0.059
up+0.056
les+0.054
iable+0.054
ches+0.053
Neg logit contributions
apy-0.071
uzz-0.070
 Nick-0.069
 Mam-0.069
 Liz-0.067
Token some
Token ID617
Feature activation+1.26e-02

Pos logit contributions
ercise+0.010
ock+0.010
iable+0.010
up+0.010
isi+0.010
Neg logit contributions
apy-0.020
 Nick-0.020
 ankles-0.019
 Mam-0.019
 Liz-0.019
Token nice
Token ID3621
Feature activation-1.12e-03

Pos logit contributions
 Nick+0.025
apy+0.025
uzz+0.025
 Liz+0.025
 Mam+0.025
Neg logit contributions
ock-0.016
les-0.016
ercise-0.015
up-0.015
isi-0.015
Token warm
Token ID5814
Feature activation+2.53e-02

Pos logit contributions
les+0.001
ock+0.001
up+0.001
ercise+0.001
off+0.001
Neg logit contributions
apy-0.002
 Nick-0.002
 Liz-0.002
 Mam-0.002
uzz-0.002
Token food
Token ID2057
Feature activation+2.02e-02

Pos logit contributions
apy+0.053
 Liz+0.050
 Nick+0.050
 Mam+0.050
uzz+0.049
Neg logit contributions
les-0.033
ock-0.031
ercise-0.031
up-0.029
at-0.028
Token inside
Token ID2641
Feature activation+7.91e-02

Pos logit contributions
apy+0.043
 Mam+0.040
 Liz+0.040
 Nick+0.039
 Kel+0.039
Neg logit contributions
ock-0.024
isi-0.024
ercise-0.024
iable-0.024
ty-0.024
Token.
Token ID13
Feature activation+9.15e-04

Pos logit contributions
apy+0.170
 ankles+0.160
 Nick+0.158
 Mam+0.158
uzz+0.158
Neg logit contributions
ock-0.091
les-0.085
 course-0.085
iable-0.083
ty-0.082
Token She
Token ID1375
Feature activation+1.50e-02

Pos logit contributions
apy+0.002
 spe+0.002
 Nick+0.002
 Esk+0.002
 sweating+0.001
Neg logit contributions
isi-0.001
ercise-0.001
off-0.001
orn-0.001
ock-0.001
Token smiled
Token ID13541
Feature activation+2.51e-03

Pos logit contributions
apy+0.026
 Nick+0.025
 Mam+0.025
 Liz+0.025
 Kel+0.024
Neg logit contributions
ercise-0.023
isi-0.022
iable-0.022
ches-0.022
up-0.022
Token and
Token ID290
Feature activation-2.56e-02

Pos logit contributions
apy+0.006
 Nick+0.005
 Mam+0.005
 Liz+0.005
 Megan+0.005
Neg logit contributions
ercise-0.003
isi-0.003
ock-0.003
iable-0.003
off-0.003
Token quickly
Token ID2952
Feature activation-4.08e-04

Pos logit contributions
ercise+0.033
isi+0.031
up+0.030
iable+0.029
les+0.029
Neg logit contributions
apy-0.047
uzz-0.047
ges-0.047
 bedrooms-0.047
 Nick-0.047
Token!
Token ID0
Feature activation+7.52e-03

Pos logit contributions
ercise+0.015
isi+0.015
ock+0.015
iable+0.014
off+0.014
Neg logit contributions
apy-0.027
 Mam-0.026
 Nick-0.025
 Megan-0.024
 Madd-0.024
Token What
Token ID1867
Feature activation+1.77e-02

Pos logit contributions
apy+0.013
 Mam+0.012
 toes+0.012
 Nick+0.012
 ankles+0.011
Neg logit contributions
ercise-0.013
isi-0.012
ock-0.012
off-0.012
iable-0.012
Token are
Token ID389
Feature activation+3.33e-02

Pos logit contributions
apy+0.031
 Nick+0.031
 Mam+0.030
 Liz+0.029
 Megan+0.028
Neg logit contributions
ercise-0.029
isi-0.029
iable-0.028
ock-0.028
off-0.027
Token you
Token ID345
Feature activation+3.43e-02

Pos logit contributions
 Nick+0.074
apy+0.074
 Mam+0.072
 Liz+0.070
 Megan+0.070
Neg logit contributions
ercise-0.039
isi-0.038
ock-0.037
iable-0.036
at-0.034
Token doing
Token ID1804
Feature activation-4.37e-03

Pos logit contributions
 Nick+0.045
 Mam+0.045
 holding+0.043
 L+0.041
 Liz+0.041
Neg logit contributions
ercise-0.072
isi-0.070
ock-0.067
up-0.067
iable-0.066
Token?"
Token ID1701
Feature activation+2.27e-02

Pos logit contributions
isi+0.007
ercise+0.007
iable+0.007
ock+0.007
vious+0.007
Neg logit contributions
 Nick-0.008
 Mam-0.007
apy-0.007
 Mike-0.007
 Liz-0.007
Token
Token ID198
Feature activation+1.40e-02

Pos logit contributions
apy+0.032
 Nick+0.032
 Mam+0.031
 Liz+0.029
 Megan+0.029
Neg logit contributions
ercise-0.046
isi-0.045
iable-0.044
ock-0.044
off-0.042
Token
Token ID198
Feature activation+7.82e-03

Pos logit contributions
apy+0.018
 Nick+0.018
 Mam+0.017
 Liz+0.016
 Megan+0.016
Neg logit contributions
ercise-0.030
iable-0.029
isi-0.029
ock-0.029
vious-0.028
Token"
Token ID1
Feature activation+2.63e-02

Pos logit contributions
apy+0.014
 Nick+0.014
 Mam+0.013
 Megan+0.013
 Liz+0.013
Neg logit contributions
ercise-0.013
isi-0.012
ock-0.012
iable-0.012
at-0.012
TokenI
Token ID40
Feature activation+3.03e-02

Pos logit contributions
apy+0.046
 Nick+0.045
 Mam+0.044
 Liz+0.042
 Megan+0.042
Neg logit contributions
ercise-0.044
isi-0.043
iable-0.042
ock-0.042
off-0.040
Token am
Token ID716
Feature activation+2.73e-02

Pos logit contributions
apy+0.040
 Nick+0.040
 Mam+0.039
 Megan+0.037
 Liz+0.036
Neg logit contributions
ercise-0.062
isi-0.061
iable-0.060
ock-0.060
off-0.058
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
apy+0.015
 Nick+0.014
 Mam+0.014
 Liz+0.014
 Megan+0.014
Neg logit contributions
ercise-0.009
isi-0.009
iable-0.009
ock-0.009
off-0.008
Token He
Token ID679
Feature activation+7.74e-03

Pos logit contributions
apy+0.018
 Nick+0.017
 Mam+0.017
 toes+0.016
 spe+0.016
Neg logit contributions
ercise-0.026
isi-0.026
ock-0.025
vious-0.025
iable-0.024
Token is
Token ID318
Feature activation+1.02e-02

Pos logit contributions
 Nick+0.014
apy+0.013
 Mam+0.013
 Megan+0.013
 L+0.013
Neg logit contributions
isi-0.012
iable-0.012
ock-0.012
ercise-0.012
at-0.012
Token nice
Token ID3621
Feature activation-6.96e-04

Pos logit contributions
apy+0.020
 Mam+0.017
 Nick+0.017
 Mick+0.017
 shovel+0.017
Neg logit contributions
isi-0.015
iable-0.014
ock-0.014
ercise-0.014
 better-0.013
Token.
Token ID13
Feature activation+1.50e-02

Pos logit contributions
ock+0.001
isi+0.001
ercise+0.001
off+0.001
up+0.001
Neg logit contributions
apy-0.001
 Mam-0.001
 Nick-0.001
 Madd-0.001
 Kel-0.001
Token He
Token ID679
Feature activation+1.35e-02

Pos logit contributions
apy+0.020
 Nick+0.020
 Mam+0.019
 toes+0.018
 spe+0.018
Neg logit contributions
ercise-0.030
isi-0.030
ock-0.029
iable-0.028
vious-0.028
Token offers
Token ID4394
Feature activation-1.13e-02

Pos logit contributions
 Nick+0.024
apy+0.023
 L+0.023
 Mam+0.022
 Mil+0.022
Neg logit contributions
isi-0.022
iable-0.022
ock-0.021
ercise-0.021
at-0.021
Token his
Token ID465
Feature activation-1.38e-02

Pos logit contributions
ercise+0.020
isi+0.020
iable+0.019
ock+0.019
off+0.018
Neg logit contributions
apy-0.019
 Nick-0.018
 Mam-0.018
 Liz-0.017
 Megan-0.017
Token toy
Token ID13373
Feature activation-4.86e-02

Pos logit contributions
ercise+0.022
isi+0.021
ock+0.021
iable+0.021
off+0.020
Neg logit contributions
apy-0.025
 Nick-0.025
 Mam-0.024
 Megan-0.023
 Madd-0.023
Token train
Token ID4512
Feature activation-5.90e-02

Pos logit contributions
isi+0.083
ercise+0.081
iable+0.081
ock+0.078
at+0.076
Neg logit contributions
apy-0.083
 Nick-0.081
 Liz-0.080
 Mam-0.080
 L-0.076
Token to
Token ID284
Feature activation+4.86e-02

Pos logit contributions
ercise+0.109
iable+0.109
isi+0.108
ock+0.106
at+0.102
Neg logit contributions
 Nick-0.087
 Liz-0.087
 L-0.085
 Jen-0.084
apy-0.083
Token herself
Token ID5223
Feature activation-9.74e-03

Pos logit contributions
apy+0.101
 Nick+0.098
 Mam+0.093
 Mick+0.091
 Megan+0.089
Neg logit contributions
isi-0.088
iable-0.086
ock-0.086
ercise-0.085
off-0.079
Token.
Token ID13
Feature activation-1.54e-02

Pos logit contributions
ercise+0.020
isi+0.019
iable+0.019
ock+0.019
at+0.018
Neg logit contributions
 Nick-0.013
apy-0.013
 Mam-0.013
 Liz-0.012
 Megan-0.012
Token She
Token ID1375
Feature activation+6.15e-03

Pos logit contributions
ock+0.035
iable+0.035
ercise+0.035
isi+0.035
at+0.035
Neg logit contributions
apy-0.018
 Mam-0.018
 Nick-0.018
 Liz-0.017
 L-0.017
Token sat
Token ID3332
Feature activation+1.72e-04

Pos logit contributions
 gasped+0.009
 Mam+0.008
 Nick+0.008
 L+0.008
apy+0.008
Neg logit contributions
ock-0.013
ercise-0.013
iable-0.012
off-0.012
at-0.012
Token down
Token ID866
Feature activation+2.17e-02

Pos logit contributions
apy+0.000
 Nick+0.000
 Mam+0.000
 Liz+0.000
 Megan+0.000
Neg logit contributions
isi-0.000
ercise-0.000
ock-0.000
iable-0.000
off-0.000
Token with
Token ID351
Feature activation+2.38e-02

Pos logit contributions
apy+0.034
 Nick+0.033
 holding+0.033
 Mam+0.033
 L+0.032
Neg logit contributions
ercise-0.041
isi-0.040
iable-0.040
ock-0.038
at-0.036
Token her
Token ID607
Feature activation+2.45e-02

Pos logit contributions
apy+0.039
 Nick+0.039
 Mam+0.038
 Liz+0.036
 Megan+0.036
Neg logit contributions
ercise-0.042
isi-0.041
iable-0.041
ock-0.041
off-0.039
Token string
Token ID4731
Feature activation-2.62e-02

Pos logit contributions
apy+0.036
 Nick+0.036
 Mam+0.034
 Megan+0.033
 Mick+0.032
Neg logit contributions
isi-0.047
ercise-0.046
iable-0.045
ock-0.044
off-0.042
Token and
Token ID290
Feature activation-3.55e-02

Pos logit contributions
ercise+0.041
iable+0.039
isi+0.039
ock+0.037
off+0.036
Neg logit contributions
apy-0.050
 Nick-0.049
 Mam-0.048
 toes-0.046
 Liz-0.046
Token read
Token ID1100
Feature activation-2.27e-02

Pos logit contributions
ercise+0.055
isi+0.054
iable+0.052
ock+0.052
off+0.049
Neg logit contributions
apy-0.067
 Nick-0.065
 Mam-0.064
 Liz-0.061
 Megan-0.061
Token the
Token ID262
Feature activation-4.03e-02

Pos logit contributions
ercise+0.042
isi+0.041
iable+0.040
ock+0.040
off+0.038
Neg logit contributions
apy-0.036
 Nick-0.036
 Mam-0.035
 Liz-0.033
 Megan-0.033
Token ready
Token ID3492
Feature activation-2.23e-02

Pos logit contributions
ercise+0.018
isi+0.018
iable+0.017
ock+0.017
at+0.016
Neg logit contributions
apy-0.020
 Nick-0.020
 Mam-0.019
 Megan-0.018
 Liz-0.018
Token?"
Token ID1701
Feature activation+2.59e-02

Pos logit contributions
isi+0.028
ercise+0.027
iable+0.026
ock+0.025
off+0.024
Neg logit contributions
 Nick-0.049
 Mam-0.049
apy-0.047
 Liz-0.046
 Megan-0.046
Token Lily
Token ID20037
Feature activation+7.93e-03

Pos logit contributions
 Nick+0.034
apy+0.034
 Mam+0.032
uzz+0.031
 toes+0.031
Neg logit contributions
ercise-0.051
isi-0.051
iable-0.049
ock-0.048
vious-0.048
Token nodded
Token ID14464
Feature activation+2.54e-02

Pos logit contributions
apy+0.015
 Nick+0.014
 Mam+0.014
 Liz+0.014
 Megan+0.013
Neg logit contributions
ercise-0.012
isi-0.012
iable-0.012
ock-0.011
off-0.011
Token and
Token ID290
Feature activation-2.84e-02

Pos logit contributions
apy+0.055
 Nick+0.053
 Mam+0.052
 Liz+0.050
 Megan+0.050
Neg logit contributions
ercise-0.032
isi-0.032
ock-0.031
iable-0.030
off-0.028
Token said
Token ID531
Feature activation+2.09e-02

Pos logit contributions
ercise+0.039
up+0.037
isi+0.037
ock+0.036
iable+0.035
Neg logit contributions
apy-0.055
 Mam-0.052
 Nick-0.051
uzz-0.051
ges-0.051
Token,
Token ID11
Feature activation+3.17e-02

Pos logit contributions
 Mam+0.044
 Nick+0.043
apy+0.043
 Liz+0.041
 Mick+0.041
Neg logit contributions
ercise-0.024
iable-0.024
ock-0.024
isi-0.023
up-0.022
Token "
Token ID366
Feature activation+9.16e-03

Pos logit contributions
apy+0.043
 Nick+0.040
 Mam+0.039
 Liz+0.038
 Madd+0.037
Neg logit contributions
ercise-0.063
iable-0.062
isi-0.061
ock-0.059
ches-0.057
TokenBy
Token ID3886
Feature activation+1.96e-02

Pos logit contributions
apy+0.014
 Nick+0.014
 Mam+0.013
 Liz+0.013
 Megan+0.013
Neg logit contributions
ercise-0.017
isi-0.017
ock-0.017
iable-0.016
off-0.016
Tokene
Token ID68
Feature activation-3.80e-02

Pos logit contributions
apy+0.036
 Nick+0.035
 Mam+0.034
 Liz+0.033
 Megan+0.032
Neg logit contributions
ercise-0.031
ock-0.030
isi-0.030
iable-0.030
off-0.029
Token,
Token ID11
Feature activation+1.03e-02

Pos logit contributions
ercise+0.055
isi+0.054
iable+0.053
ock+0.052
off+0.050
Neg logit contributions
apy-0.074
 Nick-0.073
 Mam-0.071
 Megan-0.068
 Liz-0.068
Token piece
Token ID3704
Feature activation-1.39e-02

Pos logit contributions
apy+0.013
 Nick+0.013
 Mam+0.013
 Liz+0.012
 Megan+0.012
Neg logit contributions
ercise-0.013
isi-0.013
iable-0.012
ock-0.012
off-0.012
Token of
Token ID286
Feature activation+5.32e-02

Pos logit contributions
ercise+0.024
isi+0.024
iable+0.023
ock+0.021
off+0.021
Neg logit contributions
apy-0.024
 Nick-0.023
 Mam-0.023
 Liz-0.022
 shovel-0.022
Token string
Token ID4731
Feature activation-1.79e-02

Pos logit contributions
apy+0.094
 Nick+0.091
 Mam+0.090
 Liz+0.085
 shovel+0.084
Neg logit contributions
isi-0.089
ercise-0.088
iable-0.086
ock-0.085
off-0.081
Token,"
Token ID553
Feature activation+2.61e-02

Pos logit contributions
isi+0.029
ercise+0.029
iable+0.027
ock+0.027
off+0.026
Neg logit contributions
apy-0.032
 Nick-0.032
 Mam-0.031
 Liz-0.030
 shovel-0.029
Token Jack
Token ID3619
Feature activation-8.11e-03

Pos logit contributions
apy+0.051
 Mam+0.051
 spe+0.050
 ankles+0.050
 Nick+0.050
Neg logit contributions
ercise-0.035
isi-0.032
ock-0.031
iable-0.030
off-0.030
Token said
Token ID531
Feature activation+4.08e-02

Pos logit contributions
ercise+0.013
isi+0.013
ock+0.013
iable+0.013
off+0.012
Neg logit contributions
 Nick-0.014
apy-0.014
 Mam-0.014
 Liz-0.014
 Megan-0.013
Token.
Token ID13
Feature activation+3.28e-02

Pos logit contributions
apy+0.083
 Nick+0.082
 bedrooms+0.081
 Mam+0.080
 spe+0.079
Neg logit contributions
iable-0.046
up-0.045
ercise-0.045
night-0.045
ly-0.044
Token
Token ID198
Feature activation+7.43e-03

Pos logit contributions
apy+0.063
 spe+0.061
 Mam+0.059
 toes+0.059
 ankles+0.059
Neg logit contributions
ercise-0.042
ches-0.040
off-0.040
isi-0.039
ock-0.039
Token
Token ID198
Feature activation+3.12e-03

Pos logit contributions
apy+0.012
 Nick+0.012
 Mam+0.011
 Megan+0.011
 toes+0.011
Neg logit contributions
ercise-0.013
isi-0.013
ock-0.013
iable-0.013
off-0.012
TokenThe
Token ID464
Feature activation-2.11e-02

Pos logit contributions
apy+0.006
 Nick+0.006
 Mam+0.006
 Megan+0.006
 Liz+0.006
Neg logit contributions
ercise-0.004
isi-0.004
ock-0.004
iable-0.004
off-0.004
Token boys
Token ID6510
Feature activation+1.17e-02

Pos logit contributions
iable+0.045
ock+0.044
ercise+0.044
at+0.044
isi+0.044
Neg logit contributions
 shovel-0.027
 Nick-0.027
 gasped-0.026
 Mam-0.026
 toes-0.025
Token lit
Token ID6578
Feature activation-5.92e-03

Pos logit contributions
apy+0.087
 Nick+0.084
 Mam+0.082
 Liz+0.077
 Megan+0.077
Neg logit contributions
ercise-0.105
isi-0.104
iable-0.101
ock-0.100
off-0.097
Token up
Token ID510
Feature activation+4.54e-02

Pos logit contributions
isi+0.007
ercise+0.006
iable+0.006
ock+0.006
vious+0.005
Neg logit contributions
 Nick-0.014
apy-0.014
 Mam-0.014
 Mike-0.013
 Megan-0.013
Token as
Token ID355
Feature activation+4.62e-02

Pos logit contributions
apy+0.085
 Nick+0.083
 Mam+0.083
 Liz+0.079
 Megan+0.078
Neg logit contributions
ercise-0.073
isi-0.070
iable-0.068
ock-0.067
off-0.065
Token she
Token ID673
Feature activation+7.70e-03

Pos logit contributions
apy+0.084
 Nick+0.084
 Mam+0.082
 Megan+0.078
 ankles+0.077
Neg logit contributions
isi-0.070
ercise-0.069
ock-0.068
iable-0.067
orn-0.061
Token saw
Token ID2497
Feature activation+8.15e-03

Pos logit contributions
apy+0.012
 Nick+0.012
 Mam+0.012
 Megan+0.011
 Madd+0.011
Neg logit contributions
ercise-0.014
iable-0.013
isi-0.013
ock-0.013
up-0.013
Token the
Token ID262
Feature activation-6.19e-03

Pos logit contributions
apy+0.016
 Nick+0.016
 Mam+0.015
 Megan+0.015
 Mick+0.014
Neg logit contributions
ock-0.011
isi-0.011
ercise-0.011
iable-0.011
up-0.010
Token colorful
Token ID20239
Feature activation+2.19e-02

Pos logit contributions
ercise+0.010
isi+0.010
ock+0.009
iable+0.009
off+0.009
Neg logit contributions
apy-0.011
 Nick-0.011
 Mam-0.011
 Megan-0.011
 Liz-0.010
Token gear
Token ID7733
Feature activation-5.95e-03

Pos logit contributions
 Nick+0.044
apy+0.043
 Mil+0.043
 Mam+0.043
 Madd+0.042
Neg logit contributions
ock-0.031
ercise-0.030
les-0.029
isi-0.028
iable-0.027
Token on
Token ID319
Feature activation+6.58e-02

Pos logit contributions
ercise+0.009
iable+0.009
ock+0.009
isi+0.009
off+0.008
Neg logit contributions
apy-0.011
 Nick-0.011
 Mam-0.011
 Megan-0.010
 Liz-0.010
Token the
Token ID262
Feature activation-2.09e-02

Pos logit contributions
apy+0.118
 Nick+0.112
 Mam+0.108
 Megan+0.104
 Madd+0.104
Neg logit contributions
isi-0.107
ock-0.106
ercise-0.105
iable-0.101
off-0.095
Token back
Token ID736
Feature activation+4.39e-02

Pos logit contributions
ercise+0.037
isi+0.036
iable+0.036
ock+0.036
off+0.034
Neg logit contributions
apy-0.034
 Nick-0.034
 Mam-0.033
 Liz-0.031
 Megan-0.031
Token.
Token ID13
Feature activation+1.80e-03

Pos logit contributions
ercise+0.078
isi+0.076
iable+0.075
ock+0.074
off+0.071
Neg logit contributions
apy-0.068
 Nick-0.068
 Mam-0.066
 Liz-0.063
 Megan-0.062
Token You
Token ID921
Feature activation+2.98e-03

Pos logit contributions
apy+0.003
 Nick+0.003
 Mam+0.003
 gasped+0.003
 Megan+0.003
Neg logit contributions
ercise-0.003
isi-0.003
ock-0.003
iable-0.003
off-0.003
Token are
Token ID389
Feature activation+1.26e-02

Pos logit contributions
 Nick+0.004
apy+0.004
 Mam+0.004
 shovel+0.004
 Liz+0.004
Neg logit contributions
isi-0.006
ercise-0.006
ock-0.006
iable-0.006
off-0.006
Token brave
Token ID14802
Feature activation-5.20e-04

Pos logit contributions
apy+0.025
 Nick+0.024
 Mam+0.023
 Megan+0.022
 Liz+0.022
Neg logit contributions
ercise-0.019
isi-0.018
iable-0.018
ock-0.018
off-0.017
Token."
Token ID526
Feature activation+6.57e-04

Pos logit contributions
ercise+0.001
ock+0.001
isi+0.001
iable+0.001
off+0.001
Neg logit contributions
apy-0.001
 Nick-0.001
 Mam-0.001
 Liz-0.001
 Megan-0.001
Token
Token ID198
Feature activation-6.84e-03

Pos logit contributions
apy+0.001
 Nick+0.001
 Mam+0.001
 Liz+0.001
 Megan+0.001
Neg logit contributions
ercise-0.001
isi-0.001
iable-0.001
ock-0.001
off-0.001
Token
Token ID198
Feature activation-5.90e-03

Pos logit contributions
ercise+0.013
isi+0.013
iable+0.013
ock+0.013
off+0.012
Neg logit contributions
apy-0.010
 Nick-0.010
 Mam-0.010
 Liz-0.009
 Megan-0.009
TokenTom
Token ID13787
Feature activation-2.15e-02

Pos logit contributions
ercise+0.012
isi+0.012
at+0.011
iable+0.011
ock+0.011
Neg logit contributions
apy-0.008
 Nick-0.007
 Mam-0.007
 Liz-0.007
 Megan-0.007
Token took
Token ID1718
Feature activation-3.79e-02

Pos logit contributions
ercise+0.043
isi+0.042
iable+0.042
ock+0.041
off+0.039
Neg logit contributions
 Nick-0.031
apy-0.030
 Mam-0.029
 Liz-0.028
 gasped-0.028
Token a
Token ID257
Feature activation-1.84e-02

Pos logit contributions
ercise+0.090
iable+0.089
isi+0.088
ock+0.086
at+0.084
Neg logit contributions
 Nick-0.040
 Liz-0.040
 Jen-0.039
 Mam-0.039
 L-0.039
Token deep
Token ID2769
Feature activation+2.41e-02

Pos logit contributions
ercise+0.032
isi+0.032
iable+0.031
ock+0.031
off+0.030
Neg logit contributions
apy-0.030
 Nick-0.030
 Mam-0.029
 Liz-0.028
 Megan-0.028
Token more
Token ID517
Feature activation+1.15e-02

Pos logit contributions
ercise+0.065
isi+0.063
iable+0.062
ock+0.062
off+0.058
Neg logit contributions
apy-0.085
 Nick-0.084
 Mam-0.082
 Liz-0.078
 Megan-0.078
Token sugar
Token ID7543
Feature activation-2.01e-02

Pos logit contributions
apy+0.021
 Nick+0.021
 Mam+0.021
 Liz+0.020
 Megan+0.020
Neg logit contributions
ercise-0.017
ock-0.017
isi-0.016
iable-0.016
off-0.016
Token to
Token ID284
Feature activation+4.68e-02

Pos logit contributions
ercise+0.032
isi+0.031
iable+0.030
ock+0.030
off+0.028
Neg logit contributions
apy-0.037
 Nick-0.037
 Mam-0.036
 Liz-0.034
 Megan-0.034
Token the
Token ID262
Feature activation-2.63e-02

Pos logit contributions
 Nick+0.088
apy+0.087
 Mam+0.082
uzz+0.082
 Megan+0.081
Neg logit contributions
iable-0.066
ercise-0.066
ock-0.066
isi-0.065
off-0.060
Token lemon
Token ID18873
Feature activation-3.69e-02

Pos logit contributions
ercise+0.043
isi+0.042
iable+0.041
ock+0.041
off+0.039
Neg logit contributions
apy-0.047
 Nick-0.046
 Mam-0.044
 Liz-0.043
 Megan-0.042
Tokenade
Token ID671
Feature activation-2.37e-02

Pos logit contributions
ercise+0.047
isi+0.045
iable+0.042
ock+0.040
off+0.038
Neg logit contributions
apy-0.081
 Nick-0.078
 Mam-0.078
 Megan-0.076
 Liz-0.075
Token.
Token ID13
Feature activation-1.61e-02

Pos logit contributions
ercise+0.040
isi+0.039
iable+0.038
ock+0.038
off+0.036
Neg logit contributions
apy-0.041
 Nick-0.040
 Mam-0.039
 Liz-0.037
 Megan-0.037
Token Lily
Token ID20037
Feature activation-1.63e-02

Pos logit contributions
ercise+0.028
isi+0.028
iable+0.027
ock+0.026
off+0.026
Neg logit contributions
apy-0.026
 Nick-0.025
 Mam-0.024
 toes-0.023
 spe-0.023
Token took
Token ID1718
Feature activation-4.15e-02

Pos logit contributions
ercise+0.031
isi+0.031
ock+0.030
iable+0.030
off+0.028
Neg logit contributions
apy-0.025
 Nick-0.025
 Mam-0.024
 Megan-0.022
 Liz-0.022
Token another
Token ID1194
Feature activation+1.44e-03

Pos logit contributions
isi+0.081
ercise+0.081
iable+0.080
ock+0.078
off+0.075
Neg logit contributions
apy-0.064
 Mam-0.061
 Nick-0.060
 Liz-0.057
 Megan-0.056
Token sip
Token ID31145
Feature activation+7.85e-03

Pos logit contributions
apy+0.002
 Nick+0.002
 Mam+0.002
 Liz+0.002
 Megan+0.002
Neg logit contributions
ercise-0.003
isi-0.002
iable-0.002
ock-0.002
off-0.002
Token the
Token ID262
Feature activation-2.93e-02

Pos logit contributions
ercise+0.054
isi+0.053
iable+0.052
ock+0.052
off+0.049
Neg logit contributions
apy-0.060
 Nick-0.059
 Mam-0.058
 Liz-0.055
 Megan-0.055
Token car
Token ID1097
Feature activation-3.81e-02

Pos logit contributions
ock+0.039
ercise+0.039
isi+0.037
iable+0.037
off+0.035
Neg logit contributions
apy-0.061
 Nick-0.060
 Mam-0.058
 Megan-0.057
 Madd-0.056
Token until
Token ID1566
Feature activation+9.92e-03

Pos logit contributions
ercise+0.059
isi+0.058
iable+0.055
ock+0.055
off+0.053
Neg logit contributions
apy-0.070
 Nick-0.070
 Mam-0.068
 Liz-0.066
 Megan-0.065
Token you
Token ID345
Feature activation+1.26e-02

Pos logit contributions
apy+0.019
 Nick+0.018
 Mam+0.018
 Liz+0.018
 Megan+0.017
Neg logit contributions
ercise-0.014
iable-0.014
isi-0.014
ock-0.014
off-0.013
Tokenâ
Token ID22940
Feature activation-5.23e-02

Pos logit contributions
 Nick+0.021
apy+0.021
 Mam+0.020
 Liz+0.019
 Megan+0.019
Neg logit contributions
ercise-0.022
isi-0.022
iable-0.021
ock-0.021
off-0.020
Token€
Token ID26391
Feature activation-3.68e-02

Pos logit contributions
isi+0.071
ercise+0.068
iable+0.067
ock+0.065
orn+0.063
Neg logit contributions
 Nick-0.099
 Mam-0.096
 Mike-0.095
 Megan-0.094
apy-0.092
Tokenâ„¢
Token ID8151
Feature activation-6.10e-02

Pos logit contributions
ercise+0.062
isi+0.060
iable+0.060
ock+0.058
off+0.057
Neg logit contributions
apy-0.063
 Nick-0.061
 Mam-0.060
 Madd-0.057
 Megan-0.056
Tokenre
Token ID260
Feature activation+1.45e-02

Pos logit contributions
isi+0.090
ercise+0.089
iable+0.088
ock+0.088
off+0.082
Neg logit contributions
apy-0.116
 Nick-0.114
 Mam-0.112
 Liz-0.106
 Megan-0.106
Token big
Token ID1263
Feature activation-1.47e-03

Pos logit contributions
apy+0.030
 Nick+0.028
 Mam+0.027
 spe+0.026
 Megan+0.026
Neg logit contributions
iable-0.019
ercise-0.019
ock-0.019
off-0.018
at-0.018
Token enough
Token ID1576
Feature activation+2.65e-02

Pos logit contributions
ercise+0.002
isi+0.002
iable+0.002
ock+0.002
off+0.002
Neg logit contributions
 Nick-0.003
apy-0.003
 Mam-0.003
 Liz-0.003
 Megan-0.003
Token to
Token ID284
Feature activation+3.79e-02

Pos logit contributions
apy+0.056
 Nick+0.054
 Mam+0.053
 Liz+0.051
 Megan+0.051
Neg logit contributions
ercise-0.035
ock-0.034
isi-0.034
iable-0.033
off-0.032
Token funny
Token ID8258
Feature activation-9.76e-03

Pos logit contributions
ercise+0.001
isi+0.001
iable+0.001
ock+0.001
off+0.001
Neg logit contributions
apy-0.001
 Nick-0.001
 Mam-0.001
 ankles-0.001
 Liz-0.001
Token and
Token ID290
Feature activation-3.13e-02

Pos logit contributions
ercise+0.011
ock+0.011
isi+0.011
iable+0.011
off+0.010
Neg logit contributions
apy-0.022
 Mam-0.021
 Nick-0.021
 Liz-0.020
 Megan-0.020
Token make
Token ID787
Feature activation-4.44e-02

Pos logit contributions
ercise+0.047
iable+0.044
ock+0.042
isi+0.041
off+0.040
Neg logit contributions
apy-0.060
 Mam-0.059
 Nick-0.058
uzz-0.055
 Megan-0.055
Token me
Token ID502
Feature activation-1.79e-02

Pos logit contributions
ercise+0.067
isi+0.067
iable+0.064
ock+0.064
at+0.060
Neg logit contributions
apy-0.084
 Nick-0.083
 Mam-0.081
 Liz-0.078
 Megan-0.078
Token laugh
Token ID6487
Feature activation-1.76e-02

Pos logit contributions
ercise+0.037
isi+0.036
iable+0.035
ock+0.035
off+0.034
Neg logit contributions
apy-0.024
 Nick-0.024
 Mam-0.023
 Liz-0.022
 Megan-0.022
Token."
Token ID526
Feature activation-7.21e-04

Pos logit contributions
isi+0.032
ercise+0.032
iable+0.030
at+0.030
ock+0.029
Neg logit contributions
 Nick-0.028
apy-0.028
 Megan-0.026
 Mam-0.026
 Liz-0.026
Token
Token ID198
Feature activation+1.03e-03

Pos logit contributions
ercise+0.001
isi+0.001
iable+0.001
ock+0.001
off+0.001
Neg logit contributions
apy-0.001
 Nick-0.001
 Mam-0.001
 Mick-0.001
 Liz-0.001
Token
Token ID198
Feature activation-1.45e-03

Pos logit contributions
apy+0.001
 Nick+0.001
 Mam+0.001
 Liz+0.001
 Megan+0.001
Neg logit contributions
ercise-0.002
isi-0.002
iable-0.002
ock-0.002
off-0.002
TokenNext
Token ID10019
Feature activation-1.11e-02

Pos logit contributions
ercise+0.002
isi+0.002
ock+0.002
iable+0.002
at+0.002
Neg logit contributions
apy-0.003
 Nick-0.003
 Mam-0.003
 Megan-0.002
 Liz-0.002
Token,
Token ID11
Feature activation-4.34e-03

Pos logit contributions
ercise+0.019
ock+0.019
iable+0.019
isi+0.019
at+0.018
Neg logit contributions
apy-0.019
 Nick-0.018
 Mam-0.018
 Megan-0.017
 Liz-0.017
Token they
Token ID484
Feature activation-4.54e-03

Pos logit contributions
ercise+0.008
isi+0.007
iable+0.007
ock+0.007
 course+0.007
Neg logit contributions
 Nick-0.006
uzz-0.006
 Mam-0.006
 spe-0.006
 Esk-0.006
Token house
Token ID2156
Feature activation+8.23e-03

Pos logit contributions
apy+0.015
 Nick+0.015
 Mam+0.014
 Megan+0.014
 Liz+0.014
Neg logit contributions
ercise-0.016
isi-0.016
iable-0.015
ock-0.015
off-0.015
Token again
Token ID757
Feature activation+1.39e-03

Pos logit contributions
apy+0.018
 Nick+0.017
 Mam+0.017
 Liz+0.016
 Megan+0.016
Neg logit contributions
ercise-0.010
isi-0.010
iable-0.010
ock-0.010
off-0.009
Token.
Token ID13
Feature activation-3.33e-03

Pos logit contributions
apy+0.003
 Nick+0.003
 Mam+0.003
 Megan+0.002
 Liz+0.002
Neg logit contributions
ercise-0.002
isi-0.002
ock-0.002
iable-0.002
off-0.002
Token<|endoftext|>
Token ID50256
Feature activation-2.59e-03

Pos logit contributions
isi+0.005
ercise+0.005
ock+0.005
off+0.005
iable+0.005
Neg logit contributions
apy-0.006
 Nick-0.006
 spe-0.006
 toes-0.006
 Mam-0.005
TokenT
Token ID51
Feature activation-5.55e-02

Pos logit contributions
orn+0.003
isi+0.003
ock+0.003
les+0.003
off+0.003
Neg logit contributions
apy-0.006
 toes-0.005
 ankles-0.005
 Mam-0.005
 spe-0.005
Tokeneddy
Token ID21874
Feature activation-4.80e-02

Pos logit contributions
ercise+0.080
iable+0.074
isi+0.072
vious+0.069
off+0.062
Neg logit contributions
 Nick-0.111
 Mam-0.108
 Liz-0.104
 Mick-0.104
 Mike-0.104
Token was
Token ID373
Feature activation-9.41e-03

Pos logit contributions
isi+0.092
iable+0.091
ercise+0.090
ock+0.088
off+0.084
Neg logit contributions
 Nick-0.073
 Mam-0.069
apy-0.067
 Liz-0.066
 Mick-0.064
Token a
Token ID257
Feature activation+2.07e-02

Pos logit contributions
ercise+0.015
iable+0.015
isi+0.015
ock+0.015
at+0.014
Neg logit contributions
apy-0.016
 Nick-0.016
 Mam-0.015
 Megan-0.015
 Liz-0.015
Token very
Token ID845
Feature activation+3.53e-02

Pos logit contributions
apy+0.038
 Nick+0.036
uzz+0.035
 Megan+0.035
 Liz+0.035
Neg logit contributions
ercise-0.032
iable-0.030
isi-0.030
ock-0.029
vious-0.027
Token tidy
Token ID43044
Feature activation+2.53e-02

Pos logit contributions
 Nick+0.060
apy+0.060
 Mam+0.057
 Megan+0.056
 Liz+0.056
Neg logit contributions
ercise-0.057
iable-0.055
vious-0.052
isi-0.052
ock-0.052
Token bear
Token ID6842
Feature activation-4.64e-04

Pos logit contributions
apy+0.043
 Nick+0.041
 Mam+0.039
 Megan+0.038
 Liz+0.038
Neg logit contributions
ercise-0.044
ock-0.043
isi-0.043
iable-0.042
off-0.040
Token and
Token ID290
Feature activation-1.89e-02

Pos logit contributions
apy+0.066
 Nick+0.065
 Mam+0.064
 Megan+0.061
 Liz+0.061
Neg logit contributions
ercise-0.044
iable-0.043
isi-0.042
ock-0.042
vious-0.039
Token they
Token ID484
Feature activation+6.39e-03

Pos logit contributions
ercise+0.029
iable+0.028
isi+0.026
ock+0.025
vious+0.024
Neg logit contributions
apy-0.034
 Nick-0.033
 Mam-0.033
 Mick-0.031
 ankles-0.031
Token both
Token ID1111
Feature activation+8.85e-03

Pos logit contributions
apy+0.012
 Mam+0.012
 Nick+0.012
 Megan+0.011
 Kel+0.011
Neg logit contributions
iable-0.009
ercise-0.009
les-0.008
isi-0.008
ock-0.008
Token wanted
Token ID2227
Feature activation-4.10e-02

Pos logit contributions
 extingu+0.017
apy+0.017
 Mam+0.017
 Kel+0.017
 Madd+0.017
Neg logit contributions
vious-0.011
les-0.011
ah-0.010
iable-0.010
ock-0.010
Token to
Token ID284
Feature activation+8.67e-03

Pos logit contributions
ercise+0.042
iable+0.039
isi+0.039
ock+0.038
off+0.037
Neg logit contributions
apy-0.099
 Nick-0.094
 Mam-0.094
 Megan-0.090
 Liz-0.090
Token kick
Token ID4829
Feature activation-5.36e-02

Pos logit contributions
apy+0.016
 Nick+0.016
 Mam+0.016
 Liz+0.015
 Megan+0.015
Neg logit contributions
ercise-0.013
isi-0.013
iable-0.013
ock-0.013
off-0.012
Token it
Token ID340
Feature activation-4.41e-02

Pos logit contributions
ercise+0.101
isi+0.099
iable+0.097
ock+0.097
off+0.093
Neg logit contributions
apy-0.082
 Nick-0.081
 Mam-0.079
 Liz-0.074
 Megan-0.074
Token.
Token ID13
Feature activation+1.25e-04

Pos logit contributions
isi+0.091
ercise+0.090
at+0.085
iable+0.085
ock+0.083
Neg logit contributions
 Nick-0.058
apy-0.058
 Liz-0.057
 L-0.055
 Mam-0.054
Token Lily
Token ID20037
Feature activation-4.82e-03

Pos logit contributions
apy+0.000
 spe+0.000
 Esk+0.000
 ah+0.000
 Nick+0.000
Neg logit contributions
ercise-0.000
off-0.000
vious-0.000
iable-0.000
up-0.000
Token said
Token ID531
Feature activation+1.11e-02

Pos logit contributions
ercise+0.008
isi+0.008
iable+0.008
ock+0.008
off+0.008
Neg logit contributions
apy-0.008
 Nick-0.008
 Mam-0.008
 Liz-0.007
 Megan-0.007
Token,
Token ID11
Feature activation+2.75e-02

Pos logit contributions
apy+0.021
 Nick+0.021
 Mam+0.020
 Liz+0.019
 Megan+0.019
Neg logit contributions
ercise-0.017
isi-0.016
iable-0.016
ock-0.016
off-0.015
Token me
Token ID502
Feature activation-3.48e-02

Pos logit contributions
ercise+0.007
isi+0.007
iable+0.007
ock+0.007
off+0.007
Neg logit contributions
apy-0.010
 Nick-0.010
 Mam-0.010
 Liz-0.010
 Megan-0.010
Token feel
Token ID1254
Feature activation+2.92e-03

Pos logit contributions
ercise+0.060
isi+0.059
iable+0.057
ock+0.056
off+0.054
Neg logit contributions
apy-0.059
 Nick-0.058
 Mam-0.057
 Liz-0.054
 Megan-0.054
Token better
Token ID1365
Feature activation+1.12e-02

Pos logit contributions
apy+0.008
 Nick+0.008
 Mam+0.008
 Megan+0.008
 Liz+0.008
Neg logit contributions
ercise-0.002
ock-0.002
iable-0.002
isi-0.002
off-0.001
Token."
Token ID526
Feature activation-1.16e-02

Pos logit contributions
apy+0.021
 Nick+0.020
 Mam+0.020
 Megan+0.019
 Liz+0.019
Neg logit contributions
ercise-0.017
isi-0.017
iable-0.017
ock-0.017
off-0.016
Token<|endoftext|>
Token ID50256
Feature activation-1.37e-02

Pos logit contributions
ercise+0.022
isi+0.021
iable+0.021
ock+0.021
off+0.020
Neg logit contributions
apy-0.017
 Nick-0.017
 Mam-0.016
 spe-0.016
 Megan-0.016
TokenOnce
Token ID7454
Feature activation-4.64e-02

Pos logit contributions
isi+0.021
ock+0.020
ercise+0.020
off+0.019
orn+0.019
Neg logit contributions
apy-0.026
 Mam-0.024
 toes-0.024
 Nick-0.024
 ankles-0.023
Token upon
Token ID2402
Feature activation-6.36e-03

Pos logit contributions
ercise+0.099
isi+0.099
ock+0.098
iable+0.097
off+0.093
Neg logit contributions
apy-0.056
 Nick-0.055
 Mam-0.053
 Megan-0.049
 Liz-0.048
Token a
Token ID257
Feature activation-3.93e-02

Pos logit contributions
ercise+0.011
isi+0.010
iable+0.010
ock+0.010
off+0.010
Neg logit contributions
apy-0.011
 Nick-0.011
 Mam-0.011
 Liz-0.010
 Megan-0.010
Token time
Token ID640
Feature activation-2.95e-02

Pos logit contributions
ercise+0.058
isi+0.054
iable+0.054
ock+0.054
off+0.050
Neg logit contributions
apy-0.076
 Nick-0.075
 Mam-0.075
 Megan-0.072
 Liz-0.070
Token,
Token ID11
Feature activation-2.07e-02

Pos logit contributions
iable+0.031
isi+0.031
ock+0.030
ercise+0.030
que+0.028
Neg logit contributions
apy-0.065
 Mam-0.063
 Nick-0.063
 ankles-0.061
 Mick-0.061
Token there
Token ID612
Feature activation+1.25e-02

Pos logit contributions
orn+0.030
ercise+0.030
iable+0.030
ock+0.029
que+0.028
Neg logit contributions
 ankles-0.035
 Mam-0.035
 Nick-0.035
apy-0.034
 Mick-0.033
TokenBen
Token ID11696
Feature activation-1.23e-02

Pos logit contributions
apy+0.003
 Nick+0.003
 Mam+0.003
 Liz+0.002
 Megan+0.002
Neg logit contributions
ercise-0.003
isi-0.003
iable-0.003
ock-0.003
off-0.003
Token agreed
Token ID4987
Feature activation-1.96e-02

Pos logit contributions
ercise+0.023
isi+0.023
ock+0.023
iable+0.023
off+0.022
Neg logit contributions
apy-0.018
 Nick-0.018
 Mam-0.018
 Megan-0.017
 Liz-0.017
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
ercise+0.029
isi+0.029
ock+0.028
iable+0.028
off+0.026
Neg logit contributions
apy-0.038
 Nick-0.037
 Mam-0.036
 Liz-0.034
 Megan-0.034
Token He
Token ID679
Feature activation+3.73e-03

Pos logit contributions
apy+0.021
 spe+0.020
 Nick+0.020
 Mam+0.020
 ah+0.019
Neg logit contributions
ercise-0.014
isi-0.014
ock-0.013
vious-0.013
up-0.012
Token told
Token ID1297
Feature activation+2.30e-03

Pos logit contributions
apy+0.006
 Nick+0.006
 Mam+0.005
 Megan+0.005
 Liz+0.005
Neg logit contributions
ercise-0.007
ock-0.007
isi-0.007
iable-0.007
off-0.006
Token Rex
Token ID17853
Feature activation-5.39e-02

Pos logit contributions
apy+0.002
 Nick+0.002
 Mam+0.002
 Megan+0.002
 Liz+0.002
Neg logit contributions
ercise-0.006
isi-0.006
ock-0.006
iable-0.006
off-0.005
Token to
Token ID284
Feature activation+1.97e-02

Pos logit contributions
ercise+0.076
isi+0.074
iable+0.073
ock+0.072
off+0.068
Neg logit contributions
apy-0.108
 Nick-0.105
 Mam-0.104
 Liz-0.099
 Megan-0.098
Token sit
Token ID1650
Feature activation+6.36e-03

Pos logit contributions
apy+0.036
 Nick+0.035
 Mam+0.035
 Liz+0.033
 Megan+0.033
Neg logit contributions
ercise-0.031
isi-0.031
ock-0.030
iable-0.030
off-0.028
Token on
Token ID319
Feature activation+2.55e-02

Pos logit contributions
apy+0.013
 Nick+0.013
 Mam+0.012
 Liz+0.012
 Megan+0.012
Neg logit contributions
ercise-0.009
isi-0.009
iable-0.009
ock-0.009
off-0.008
Token the
Token ID262
Feature activation-5.92e-02

Pos logit contributions
apy+0.042
 Nick+0.040
 Mam+0.039
 Madd+0.037
 Megan+0.037
Neg logit contributions
ercise-0.045
isi-0.044
ock-0.044
iable-0.043
off-0.041
Token floor
Token ID4314
Feature activation+1.80e-02

Pos logit contributions
ercise+0.131
isi+0.130
iable+0.128
ock+0.125
vious+0.122
Neg logit contributions
apy-0.066
 Nick-0.066
 Mam-0.064
 toes-0.064
 Liz-0.062
Token's
Token ID338
Feature activation+3.12e-02

Pos logit contributions
apy+0.008
 Mam+0.008
 Nick+0.008
 Liz+0.007
 Megan+0.007
Neg logit contributions
ock-0.008
ercise-0.008
off-0.007
les-0.007
iable-0.007
Token friends
Token ID2460
Feature activation+1.44e-02

Pos logit contributions
apy+0.058
 Nick+0.057
 Mil+0.056
 Mam+0.056
 Liz+0.055
Neg logit contributions
ercise-0.046
ock-0.044
off-0.044
isi-0.042
up-0.042
Token loved
Token ID6151
Feature activation-1.12e-02

Pos logit contributions
apy+0.024
 Mam+0.023
 Nick+0.023
 Liz+0.022
 Megan+0.022
Neg logit contributions
ercise-0.024
ock-0.024
iable-0.024
les-0.023
off-0.023
Token to
Token ID284
Feature activation+2.10e-02

Pos logit contributions
ercise+0.014
ock+0.013
 poems+0.013
 course+0.013
iable+0.013
Neg logit contributions
apy-0.023
 ankles-0.021
 Mam-0.021
 Megan-0.021
uzz-0.021
Token come
Token ID1282
Feature activation-8.08e-03

Pos logit contributions
apy+0.038
 Nick+0.038
 Mam+0.037
 Megan+0.036
 Liz+0.036
Neg logit contributions
ercise-0.032
ock-0.031
isi-0.031
iable-0.030
off-0.029
Token and
Token ID290
Feature activation-5.55e-02

Pos logit contributions
ercise+0.011
isi+0.011
iable+0.011
ock+0.011
off+0.010
Neg logit contributions
apy-0.016
 Nick-0.016
 Mam-0.016
 Liz-0.015
 Megan-0.015
Token sit
Token ID1650
Feature activation+1.44e-02

Pos logit contributions
ercise+0.084
isi+0.080
iable+0.079
ock+0.079
off+0.075
Neg logit contributions
apy-0.103
 Nick-0.102
 Mam-0.100
 Megan-0.097
 Liz-0.095
Token around
Token ID1088
Feature activation+1.36e-02

Pos logit contributions
apy+0.028
 Nick+0.028
 Mam+0.028
 Liz+0.027
 Megan+0.027
Neg logit contributions
ercise-0.019
iable-0.018
ock-0.017
at-0.017
les-0.017
Token the
Token ID262
Feature activation-2.63e-02

Pos logit contributions
apy+0.029
 Megan+0.028
uzz+0.028
 Mam+0.028
 Jen+0.028
Neg logit contributions
ock-0.014
les-0.014
ercise-0.014
ches-0.014
 course-0.013
Token fireplace
Token ID44250
Feature activation+3.75e-02

Pos logit contributions
ercise+0.057
ock+0.056
iable+0.055
isi+0.055
off+0.054
Neg logit contributions
apy-0.033
 Nick-0.031
 Mam-0.029
 Megan-0.029
 Mil-0.028
Token,
Token ID11
Feature activation+1.88e-02

Pos logit contributions
apy+0.076
 Mam+0.073
 Nick+0.072
 Liz+0.070
 Megan+0.069
Neg logit contributions
ock-0.048
ercise-0.048
iable-0.046
les-0.045
off-0.045