TOP ACTIVATIONS
MAX = 5.907

with a big smile on her face . After
with a cheerful smile on her face . She knew it
got a big stain on her dress . She started crying
a shiny h alo on her head . "
She put Anna on her bed and picked up the
Jane went home and brushed her hair . But something tasted
She gently scrub bed and scrub bed until the penny was
, and she always brushed her hair . One day ,
had a big smile on her face . One day ,
my asked her to brush her hair before going to school
a brush . She gently scrub bed and scrub bed until
. Julie started to comb her own hair . She was
with a big smile on her face . <|endoftext|> Once upon
's order . She brushed her hair with the brush very
After her mom my brushed her hair , Lily and her
After he brushed his hair , Jack would brush
and put on his p aj amas . Then he sn
with a big smile on her face . <|endoftext|> Once upon
When Julie finished comb ing her hair , she showed her
straight ened the dress on her body . It was beautiful

MIN ACTIVATIONS
MIN = -7.434

worry , kids !" the zo oke eper said . "
sorry , sorry !" the zo oke ep ers said .
Suddenly , a big tank came out of the bushes
One day , the two teams decided to enter a race
But then , a big truck comes . It drives on
while , but then a truck passed it . The car
Suddenly , a big truck came out of nowhere .
Suddenly a big boat came to save her .
Just then , a big boat came by and saved the
two teams . The two teams wanted to have a bouncing
sad . A cop sees them . He is
castle . Suddenly a big truck drove up and stopped in
. Suddenly , a big truck drove by with its horn
!" So the ships started their race . Little
now ." The zo oke eper catches the crocod
, Spot and the other dogs ran very fast . They
cookie . The zo oke eper saw what Tom
Suddenly , a big boat appeared . It was a
had killed them . The zo oke ep ers shot the
you doing here ?" the zo oke eper asked . "

INTERVAL 2.572 - 5.907
CONTAINS 1.268%

â € � � Let â € ™
Sus ie happily ate her apple . Later ,
day when she decided to share it with her family .
always keep her violin clean , so that she could play
It was a squ ishy , sm elly gift â €

INTERVAL -0.764 - 2.572
CONTAINS 72.504%

was so happy and hugged the puppy tight , thanking the
right thing to do . So , he said , "
and Dad too . They go inside and play with their
so pleased with her spark ly seat and her block decorations
says . " Can I have one , Tom

INTERVAL -4.099 - -0.764
CONTAINS 26.205%

ams . You will not go to the park today ,
his friend , a little bird named Sally , to help
, there was a surprise for Peter - a big delicious
excited ! She said to her mom , " Look ,
very popular among their friends . <|endoftext|> Once upon a time

INTERVAL -7.434 - -4.099
CONTAINS 0.023%

. Suddenly , a big wave came and hit the boat
one day , a small animal came along . It was
One day , the two friends started to quarrel . They
They said he was a little snack for them . Ben
One day , a big truck stops in front of their
Token with
Token ID351
Feature activation+1.41e+00

Pos logit contributions
 blonde+0.107
oph+0.095
 blush+0.093
 Her+0.089
uct+0.088
Neg logit contributions
 boat-0.080
 boats-0.076
 bridge-0.075
boat-0.075
 sailors-0.073
Token a
Token ID257
Feature activation+2.40e+00

Pos logit contributions
 blonde+0.043
oph+0.040
uct+0.037
 blush+0.037
 Her+0.036
Neg logit contributions
 sailors-0.041
 boats-0.041
 boat-0.041
 sail-0.038
 sharks-0.038
Token big
Token ID1263
Feature activation+1.95e+00

Pos logit contributions
 blonde+0.079
oph+0.076
uct+0.076
 Her+0.070
omm+0.068
Neg logit contributions
 boat-0.066
 sail-0.062
 bridge-0.059
 raft-0.057
 sailors-0.057
Token smile
Token ID8212
Feature activation+1.76e+00

Pos logit contributions
 blonde+0.059
oph+0.053
uct+0.052
 Her+0.051
 blush+0.050
Neg logit contributions
 boat-0.059
 sail-0.055
 sailors-0.054
 bridge-0.054
 boats-0.053
Token on
Token ID319
Feature activation+3.99e+00

Pos logit contributions
 blonde+0.069
oph+0.061
uct+0.060
 blush+0.059
 fru+0.059
Neg logit contributions
 boat-0.037
 sailors-0.037
boat-0.036
 boats-0.034
ug-0.034
Token her
Token ID607
Feature activation+5.91e+00

Pos logit contributions
 blonde+0.082
oph+0.070
uct+0.063
 blush+0.060
 fru+0.059
Neg logit contributions
 boat-0.150
 sail-0.149
 boats-0.148
 sailors-0.147
aro-0.142
Token face
Token ID1986
Feature activation+3.56e+00

Pos logit contributions
 blonde+0.174
oph+0.171
uct+0.157
 Could+0.146
 blush+0.139
Neg logit contributions
 boat-0.174
 sailors-0.170
 sail-0.167
 boats-0.164
 ship-0.154
Token.
Token ID13
Feature activation+1.75e+00

Pos logit contributions
 blonde+0.143
oph+0.134
uct+0.130
 fru+0.125
 blush+0.124
Neg logit contributions
 boat-0.064
 sailors-0.062
 boats-0.059
 sail-0.058
boat-0.055
Token
Token ID198
Feature activation+1.62e+00

Pos logit contributions
 blonde+0.058
oph+0.055
 fru+0.052
pron+0.052
 blush+0.052
Neg logit contributions
 sail-0.040
 sailors-0.040
 boats-0.040
ug-0.039
ull-0.038
Token
Token ID198
Feature activation+2.22e+00

Pos logit contributions
 blonde+0.053
 blush+0.046
 brist+0.045
oph+0.043
 fru+0.042
Neg logit contributions
 sailors-0.047
aro-0.045
 boat-0.044
 boats-0.044
ug-0.044
TokenAfter
Token ID3260
Feature activation+1.70e-01

Pos logit contributions
 blonde+0.063
 blush+0.054
oph+0.051
 brist+0.051
 fru+0.051
Neg logit contributions
 sailors-0.072
aro-0.070
 boats-0.068
ug-0.068
 captains-0.067
Token with
Token ID351
Feature activation+1.43e+00

Pos logit contributions
 blonde+0.132
oph+0.120
 fru+0.111
 blush+0.111
uct+0.109
Neg logit contributions
 boat-0.062
boat-0.060
ug-0.059
 boats-0.058
 sailors-0.057
Token a
Token ID257
Feature activation+2.75e+00

Pos logit contributions
oph+0.043
 blonde+0.043
uct+0.040
anna+0.037
 Her+0.037
Neg logit contributions
 boats-0.039
 boat-0.039
 sailors-0.038
 sail-0.036
 sharks-0.036
Token cheerful
Token ID37999
Feature activation+3.53e+00

Pos logit contributions
uct+0.098
oph+0.096
 blonde+0.085
omm+0.083
 meanings+0.081
Neg logit contributions
 boat-0.067
 sail-0.062
 fish-0.057
 crane-0.055
 boom-0.053
Token smile
Token ID8212
Feature activation+1.65e+00

Pos logit contributions
uct+0.114
oph+0.104
she+0.094
omm+0.092
 blonde+0.091
Neg logit contributions
 boat-0.093
 sail-0.091
 fish-0.084
 boom-0.081
ull-0.079
Token on
Token ID319
Feature activation+3.96e+00

Pos logit contributions
 blonde+0.067
oph+0.060
uct+0.057
 brist+0.057
 fru+0.057
Neg logit contributions
 sailors-0.033
 boat-0.032
boat-0.032
aro-0.030
ug-0.030
Token her
Token ID607
Feature activation+5.69e+00

Pos logit contributions
 blonde+0.082
oph+0.070
uct+0.064
 Could+0.063
 pad+0.062
Neg logit contributions
 boat-0.142
 sail-0.140
 boats-0.139
 sailors-0.138
aro-0.136
Token face
Token ID1986
Feature activation+3.38e+00

Pos logit contributions
 blonde+0.180
oph+0.176
uct+0.160
 Could+0.156
aman+0.149
Neg logit contributions
 sailors-0.148
 boat-0.147
 sail-0.140
 boats-0.133
 ship-0.133
Token.
Token ID13
Feature activation+2.26e+00

Pos logit contributions
 blonde+0.143
oph+0.132
 fru+0.125
uct+0.125
 brist+0.124
Neg logit contributions
 boat-0.053
 sailors-0.053
aro-0.049
 boats-0.049
boat-0.047
Token She
Token ID1375
Feature activation+3.65e+00

Pos logit contributions
ited+0.066
 blonde+0.061
 fru+0.058
uct+0.057
oph+0.057
Neg logit contributions
 boats-0.052
 they-0.050
 They-0.050
 bridge-0.047
 Fin-0.046
Token knew
Token ID2993
Feature activation+2.33e+00

Pos logit contributions
 blonde+0.129
amas+0.104
oph+0.103
 blond+0.103
uct+0.103
Neg logit contributions
 boat-0.085
 boats-0.081
 sailors-0.079
 sailed-0.077
 fish-0.075
Token it
Token ID340
Feature activation+3.85e+00

Pos logit contributions
 blonde+0.085
 brist+0.072
 blush+0.071
oph+0.069
amas+0.068
Neg logit contributions
 sailors-0.061
aro-0.060
 boat-0.059
 boats-0.058
 sharks-0.057
Token got
Token ID1392
Feature activation-8.12e-01

Pos logit contributions
 blonde+0.092
oph+0.092
omm+0.085
osa+0.079
 fru+0.078
Neg logit contributions
 boat-0.033
aro-0.031
 boats-0.029
 boom-0.029
 sail-0.029
Token a
Token ID257
Feature activation+1.97e+00

Pos logit contributions
 sailors+0.020
 boats+0.020
 boat+0.020
 sharks+0.019
aro+0.019
Neg logit contributions
 blonde-0.029
oph-0.027
 blush-0.025
 brist-0.024
pron-0.024
Token big
Token ID1263
Feature activation+1.37e+00

Pos logit contributions
 blonde+0.067
 Her+0.059
uct+0.059
oph+0.058
 blush+0.057
Neg logit contributions
 boat-0.055
 sail-0.051
 bridge-0.049
 raft-0.049
 crane-0.048
Token stain
Token ID18746
Feature activation+1.15e+00

Pos logit contributions
 blonde+0.040
 Her+0.033
oph+0.033
 blush+0.033
uct+0.032
Neg logit contributions
 boat-0.044
 sailors-0.042
 boats-0.041
 sail-0.041
 bridge-0.041
Token on
Token ID319
Feature activation+2.97e+00

Pos logit contributions
 blonde+0.046
oph+0.040
 blush+0.039
 Her+0.038
 fru+0.038
Neg logit contributions
 boat-0.025
 sailors-0.025
boat-0.023
ug-0.023
 boats-0.023
Token her
Token ID607
Feature activation+5.58e+00

Pos logit contributions
 blonde+0.088
aj+0.076
oph+0.073
anna+0.072
uct+0.071
Neg logit contributions
 boat-0.085
 sail-0.081
 boats-0.081
 boom-0.077
 bridge-0.077
Token dress
Token ID6576
Feature activation+2.64e+00

Pos logit contributions
 blonde+0.175
oph+0.162
uct+0.150
 fru+0.147
 Could+0.142
Neg logit contributions
 boat-0.165
 ship-0.148
 boats-0.147
 sail-0.147
 sailors-0.144
Token.
Token ID13
Feature activation+2.44e+00

Pos logit contributions
 blonde+0.120
 fru+0.104
 blond+0.102
oph+0.102
 blush+0.100
Neg logit contributions
 boat-0.040
boat-0.039
 bridge-0.033
boats-0.033
ug-0.033
Token She
Token ID1375
Feature activation+3.28e+00

Pos logit contributions
ited+0.086
 blonde+0.086
iously+0.082
oph+0.080
 brow+0.079
Neg logit contributions
 Fin-0.039
 they-0.037
 boat-0.035
 sail-0.033
 crane-0.033
Token started
Token ID2067
Feature activation+2.65e+00

Pos logit contributions
 blonde+0.116
oph+0.107
aman+0.099
omm+0.097
 Deal+0.094
Neg logit contributions
 boat-0.078
 boats-0.073
 sailors-0.071
 ship-0.071
 sailed-0.071
Token crying
Token ID13774
Feature activation+2.34e+00

Pos logit contributions
oph+0.098
 blonde+0.096
uct+0.087
 fru+0.084
omm+0.083
Neg logit contributions
 boats-0.056
 boat-0.053
 sail-0.051
 bridge-0.050
 boom-0.048
Token a
Token ID257
Feature activation+1.41e+00

Pos logit contributions
oph+0.060
omm+0.058
uct+0.057
 blonde+0.056
amas+0.056
Neg logit contributions
 sailors-0.044
 boat-0.042
 boats-0.042
 sail-0.042
aro-0.041
Token shiny
Token ID22441
Feature activation+1.68e+00

Pos logit contributions
 blonde+0.044
uct+0.044
oph+0.043
 Her+0.041
 blush+0.040
Neg logit contributions
 boat-0.039
 sail-0.037
 sailors-0.037
 bridge-0.036
 ship-0.035
Token h
Token ID289
Feature activation+1.84e+00

Pos logit contributions
uct+0.052
 blonde+0.051
oph+0.050
 Her+0.046
 blush+0.045
Neg logit contributions
 boat-0.049
 sail-0.047
 bridge-0.044
 ship-0.044
 crane-0.043
Tokenalo
Token ID7335
Feature activation+9.01e-01

Pos logit contributions
 blonde+0.050
 blush+0.042
 fru+0.041
uct+0.041
oph+0.041
Neg logit contributions
aro-0.060
ug-0.058
 sailors-0.058
 boat-0.057
boat-0.056
Token on
Token ID319
Feature activation+1.51e+00

Pos logit contributions
 blonde+0.036
oph+0.033
 brist+0.031
 blush+0.031
 fru+0.031
Neg logit contributions
aro-0.018
boat-0.018
 sailors-0.018
 boat-0.017
ug-0.017
Token her
Token ID607
Feature activation+5.45e+00

Pos logit contributions
 blonde+0.034
aj+0.030
oph+0.030
uct+0.028
amas+0.028
Neg logit contributions
 sail-0.052
 boat-0.052
 boats-0.050
 sailors-0.050
 boom-0.050
Token head
Token ID1182
Feature activation+1.59e+00

Pos logit contributions
 blonde+0.175
oph+0.171
uct+0.162
 fru+0.149
 blush+0.144
Neg logit contributions
 boat-0.151
 sailors-0.144
 ship-0.140
 sail-0.138
 boats-0.135
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
 blonde+0.062
oph+0.058
uct+0.055
 fru+0.055
 brist+0.055
Neg logit contributions
 boat-0.031
boat-0.031
 sailors-0.030
aro-0.030
 sail-0.029
Token
Token ID198
Feature activation+9.69e-01

Pos logit contributions
 blonde+0.063
pron+0.058
 brist+0.057
 brow+0.057
 eyel+0.056
Neg logit contributions
 Fin-0.028
 boats-0.027
 they-0.027
 boat-0.026
 bridge-0.024
Token
Token ID198
Feature activation+1.81e+00

Pos logit contributions
 blonde+0.035
 blush+0.031
 brist+0.030
 brow+0.028
oph+0.028
Neg logit contributions
 sailors-0.024
 boat-0.024
aro-0.023
 boats-0.023
ug-0.023
Token"
Token ID1
Feature activation+1.47e+00

Pos logit contributions
 blonde+0.068
 blush+0.061
 brow+0.059
omm+0.058
 brist+0.058
Neg logit contributions
 boat-0.036
 boats-0.034
 sailors-0.034
 bridge-0.034
boat-0.033
Token
Token ID198
Feature activation+1.12e+00

Pos logit contributions
 blonde+0.012
 blush+0.010
 brist+0.010
oph+0.010
 Her+0.009
Neg logit contributions
 sailors-0.013
 boat-0.012
aro-0.012
 boats-0.012
 sharks-0.012
TokenShe
Token ID3347
Feature activation+2.14e+00

Pos logit contributions
 blonde+0.038
 blush+0.033
 brist+0.032
oph+0.031
 fru+0.031
Neg logit contributions
 sailors-0.031
 boat-0.030
 boats-0.029
aro-0.029
 captains-0.029
Token put
Token ID1234
Feature activation+1.14e+00

Pos logit contributions
 blonde+0.069
 Her+0.057
amas+0.056
oph+0.055
omm+0.055
Neg logit contributions
 boat-0.058
 sailors-0.057
 sailed-0.056
 ship-0.055
 boats-0.054
Token Anna
Token ID11735
Feature activation+1.79e+00

Pos logit contributions
 blonde+0.040
oph+0.036
 blush+0.034
 brist+0.034
 Her+0.034
Neg logit contributions
 sailors-0.029
 boat-0.028
 boats-0.028
aro-0.028
boats-0.027
Token on
Token ID319
Feature activation+2.75e+00

Pos logit contributions
 blonde+0.067
oph+0.061
 brist+0.058
 blush+0.058
 fru+0.056
Neg logit contributions
 sailors-0.042
 boat-0.042
 boats-0.040
aro-0.039
boat-0.039
Token her
Token ID607
Feature activation+5.44e+00

Pos logit contributions
 blonde+0.087
uct+0.085
oph+0.084
elt+0.079
 fru+0.077
Neg logit contributions
 boat-0.066
 boats-0.065
 sail-0.061
 sailors-0.060
 sharks-0.059
Token bed
Token ID3996
Feature activation+2.58e+00

Pos logit contributions
oph+0.178
 blonde+0.140
uct+0.138
aman+0.133
elt+0.130
Neg logit contributions
 boat-0.158
 boats-0.138
 sail-0.137
 bridge-0.136
 sailors-0.132
Token and
Token ID290
Feature activation+1.66e+00

Pos logit contributions
 blonde+0.095
 blush+0.084
oph+0.083
 brist+0.081
uct+0.079
Neg logit contributions
 boat-0.061
boat-0.058
 sailors-0.057
 ship-0.055
 boats-0.055
Token picked
Token ID6497
Feature activation+2.12e+00

Pos logit contributions
 blonde+0.049
omm+0.040
oph+0.040
 brist+0.039
 Her+0.039
Neg logit contributions
 boat-0.053
 sailors-0.053
 boats-0.051
 sail-0.050
 ship-0.049
Token up
Token ID510
Feature activation+1.22e+00

Pos logit contributions
 blonde+0.066
uct+0.054
oph+0.054
 brist+0.053
 blush+0.053
Neg logit contributions
 sailors-0.063
 boat-0.062
 boats-0.062
 sharks-0.060
aro-0.058
Token the
Token ID262
Feature activation+3.16e+00

Pos logit contributions
 blonde+0.030
oph+0.026
uct+0.025
 brist+0.025
 blush+0.025
Neg logit contributions
 sailors-0.042
 boats-0.041
 boat-0.041
 sharks-0.041
aro-0.040
TokenJane
Token ID41083
Feature activation+1.60e+00

Pos logit contributions
 blonde+0.048
 brist+0.043
 blush+0.042
 brow+0.040
 fru+0.038
Neg logit contributions
 sailors-0.044
ull-0.043
boat-0.043
 bridge-0.042
 boats-0.042
Token went
Token ID1816
Feature activation+1.22e+00

Pos logit contributions
 blonde+0.049
 blush+0.043
 brist+0.042
oph+0.041
 fru+0.039
Neg logit contributions
 boat-0.048
 boats-0.046
 sailors-0.045
 ship-0.044
ug-0.043
Token home
Token ID1363
Feature activation+1.56e+00

Pos logit contributions
 blonde+0.037
 brist+0.031
 blush+0.030
oph+0.030
 fru+0.029
Neg logit contributions
 sailors-0.040
 boat-0.039
 boats-0.039
aro-0.037
 captains-0.037
Token and
Token ID290
Feature activation+2.12e+00

Pos logit contributions
 blonde+0.058
 blush+0.051
oph+0.050
 brist+0.049
 fru+0.047
Neg logit contributions
 sailors-0.039
 boat-0.037
 boats-0.036
 bridge-0.034
 sail-0.034
Token brushed
Token ID31782
Feature activation+3.29e+00

Pos logit contributions
 blonde+0.072
omm+0.067
 brist+0.065
 Deal+0.064
oph+0.062
Neg logit contributions
 boat-0.051
 sailed-0.049
 ship-0.049
 boats-0.048
 sail-0.047
Token her
Token ID607
Feature activation+5.43e+00

Pos logit contributions
 blonde+0.088
oph+0.080
pron+0.077
uct+0.076
 fru+0.072
Neg logit contributions
 boats-0.095
ug-0.095
 sailors-0.094
 boat-0.093
aro-0.091
Token hair
Token ID4190
Feature activation+3.76e+00

Pos logit contributions
oph+0.165
 blonde+0.145
aman+0.134
uct+0.128
ited+0.125
Neg logit contributions
 boat-0.135
 boats-0.135
 bridge-0.130
 sail-0.122
 cross-0.121
Token.
Token ID13
Feature activation+3.01e+00

Pos logit contributions
 blonde+0.153
oph+0.144
 fru+0.132
uct+0.130
omm+0.129
Neg logit contributions
 boat-0.069
boat-0.064
 boats-0.063
 sail-0.060
ug-0.059
Token But
Token ID887
Feature activation+2.16e+00

Pos logit contributions
pron+0.083
ppa+0.074
oph+0.074
 cavity+0.072
 fru+0.072
Neg logit contributions
 bridge-0.070
 nation-0.067
 sail-0.065
 drivers-0.065
 boats-0.065
Token something
Token ID1223
Feature activation+1.21e+00

Pos logit contributions
 blonde+0.080
oph+0.073
 fru+0.071
 brist+0.070
amas+0.069
Neg logit contributions
 boat-0.045
aro-0.043
 sailors-0.042
 bridge-0.041
 boats-0.041
Token tasted
Token ID29187
Feature activation+2.02e+00

Pos logit contributions
 blonde+0.041
oph+0.035
amas+0.034
 blush+0.034
 brist+0.034
Neg logit contributions
 boat-0.033
aro-0.032
 boats-0.031
 bridge-0.030
boat-0.030
Token She
Token ID1375
Feature activation+2.92e+00

Pos logit contributions
pron+0.049
oph+0.048
 blonde+0.047
 blush+0.046
ited+0.045
Neg logit contributions
 crane-0.048
 Fin-0.047
 boats-0.046
 bridge-0.046
 sail-0.045
Token gently
Token ID15165
Feature activation+3.28e+00

Pos logit contributions
 blonde+0.092
 blush+0.077
oph+0.076
 Her+0.075
omm+0.073
Neg logit contributions
 boat-0.086
 boats-0.082
 sailors-0.080
 ship-0.076
 raft-0.076
Token scrub
Token ID27268
Feature activation+5.28e+00

Pos logit contributions
 blonde+0.095
omm+0.086
oph+0.084
uct+0.079
 meanings+0.078
Neg logit contributions
 boat-0.098
 boats-0.094
 sail-0.092
 sailors-0.089
 raft-0.089
Tokenbed
Token ID3077
Feature activation+4.68e+00

Pos logit contributions
 blonde+0.178
oph+0.156
 blush+0.145
 Her+0.144
 fru+0.142
Neg logit contributions
ug-0.142
 sailors-0.136
 boats-0.133
aro-0.132
 boat-0.129
Token and
Token ID290
Feature activation+2.99e+00

Pos logit contributions
 blonde+0.175
oph+0.161
uct+0.151
 blush+0.149
 Her+0.147
Neg logit contributions
 boats-0.103
 sailors-0.101
 boat-0.101
ug-0.099
aro-0.095
Token scrub
Token ID27268
Feature activation+5.39e+00

Pos logit contributions
 blonde+0.090
oph+0.082
omm+0.079
 Her+0.078
uct+0.071
Neg logit contributions
 sailors-0.087
 boat-0.086
 boats-0.084
 sail-0.082
ug-0.080
Tokenbed
Token ID3077
Feature activation+4.67e+00

Pos logit contributions
 blonde+0.176
oph+0.157
 blush+0.146
 Her+0.144
uct+0.140
Neg logit contributions
ug-0.151
 sailors-0.145
 boats-0.140
aro-0.139
 boat-0.136
Token until
Token ID1566
Feature activation+1.74e+00

Pos logit contributions
 blonde+0.166
oph+0.152
uct+0.141
 blush+0.141
 Her+0.138
Neg logit contributions
 sailors-0.112
 boats-0.112
ug-0.112
 boat-0.110
aro-0.107
Token the
Token ID262
Feature activation+1.61e+00

Pos logit contributions
 blonde+0.060
oph+0.053
 brist+0.050
 blush+0.050
uct+0.049
Neg logit contributions
 boat-0.044
 boats-0.041
 sail-0.040
aro-0.039
 sailors-0.038
Token penny
Token ID26369
Feature activation+1.71e+00

Pos logit contributions
 blonde+0.052
oph+0.048
 Her+0.047
 blush+0.046
uct+0.044
Neg logit contributions
 boat-0.048
 sail-0.044
 boats-0.044
 sailors-0.043
 raft-0.043
Token was
Token ID373
Feature activation+1.45e+00

Pos logit contributions
 blonde+0.054
 blush+0.045
 Her+0.045
oph+0.044
 brist+0.043
Neg logit contributions
 boat-0.052
boat-0.050
 boats-0.048
 sailors-0.047
aro-0.047
Token,
Token ID11
Feature activation+2.02e+00

Pos logit contributions
 blonde+0.032
oph+0.029
 blush+0.028
 brist+0.028
 fru+0.028
Neg logit contributions
 sailors-0.019
 boat-0.019
boat-0.018
 boats-0.018
aro-0.018
Token and
Token ID290
Feature activation+2.39e+00

Pos logit contributions
oph+0.067
omm+0.062
uct+0.061
amas+0.058
 blonde+0.058
Neg logit contributions
 boat-0.049
 sailors-0.049
 boats-0.049
 sail-0.047
 ship-0.044
Token she
Token ID673
Feature activation+2.08e+00

Pos logit contributions
oph+0.060
amas+0.060
 blonde+0.058
uct+0.058
omm+0.055
Neg logit contributions
 sailors-0.072
 boat-0.072
 boats-0.071
 sail-0.066
 whales-0.066
Token always
Token ID1464
Feature activation+1.34e+00

Pos logit contributions
 blonde+0.068
oph+0.065
 blush+0.061
uct+0.060
amas+0.059
Neg logit contributions
 sailors-0.054
 boat-0.054
 boats-0.053
 sailed-0.051
 ship-0.051
Token brushed
Token ID31782
Feature activation+3.44e+00

Pos logit contributions
 blonde+0.036
oph+0.034
uct+0.032
omm+0.032
 blush+0.031
Neg logit contributions
 sailors-0.043
 boat-0.041
boat-0.040
 sail-0.040
 boats-0.040
Token her
Token ID607
Feature activation+5.35e+00

Pos logit contributions
 blonde+0.090
oph+0.084
uct+0.080
pron+0.076
 fru+0.073
Neg logit contributions
 sailors-0.110
 boats-0.108
ug-0.106
aro-0.105
 boat-0.105
Token hair
Token ID4190
Feature activation+4.24e+00

Pos logit contributions
oph+0.178
 blonde+0.144
uct+0.141
cake+0.140
Da+0.132
Neg logit contributions
 boat-0.151
 boats-0.143
 sail-0.136
 sailors-0.134
 crew-0.124
Token.
Token ID13
Feature activation+1.62e+00

Pos logit contributions
 blonde+0.163
oph+0.154
 fru+0.140
uct+0.138
 blond+0.135
Neg logit contributions
 boat-0.089
 boats-0.085
boat-0.083
ug-0.081
aro-0.079
Token One
Token ID1881
Feature activation+1.61e+00

Pos logit contributions
 blonde+0.050
pron+0.050
 brist+0.049
oph+0.049
 blush+0.048
Neg logit contributions
 boats-0.033
 crane-0.033
 Fin-0.032
 boat-0.031
 sail-0.031
Token day
Token ID1110
Feature activation+1.43e+00

Pos logit contributions
 blonde+0.065
 blush+0.058
 brist+0.057
oph+0.056
 Her+0.056
Neg logit contributions
 sailors-0.034
 boat-0.032
aro-0.031
 boats-0.031
boat-0.031
Token,
Token ID11
Feature activation+1.60e+00

Pos logit contributions
 blonde+0.059
uct+0.054
 blush+0.054
oph+0.054
 brist+0.054
Neg logit contributions
aro-0.025
 boat-0.024
 sailors-0.024
 boats-0.023
 sharks-0.022
Token had
Token ID550
Feature activation+1.17e+00

Pos logit contributions
oph+0.052
 blonde+0.051
uct+0.048
omm+0.048
amas+0.046
Neg logit contributions
 sailors-0.058
 sail-0.053
 captains-0.053
 boat-0.053
 boats-0.052
Token a
Token ID257
Feature activation+9.13e-01

Pos logit contributions
 blonde+0.034
uct+0.033
omm+0.033
 brist+0.032
oph+0.032
Neg logit contributions
 sailors-0.035
 boats-0.034
 boat-0.032
 captains-0.031
 sharks-0.031
Token big
Token ID1263
Feature activation+5.12e-01

Pos logit contributions
uct+0.028
 blonde+0.027
oph+0.026
 brist+0.024
 Her+0.024
Neg logit contributions
 boat-0.028
 boats-0.026
 sail-0.025
 sailors-0.025
 captains-0.024
Token smile
Token ID8212
Feature activation+1.32e+00

Pos logit contributions
 blonde+0.014
uct+0.013
oph+0.012
 blush+0.012
 Her+0.012
Neg logit contributions
 boat-0.017
 sailors-0.016
 boats-0.016
 ship-0.016
 sail-0.015
Token on
Token ID319
Feature activation+2.62e+00

Pos logit contributions
 blonde+0.054
oph+0.049
uct+0.049
 fru+0.048
 brist+0.047
Neg logit contributions
 sailors-0.027
 boat-0.026
boat-0.025
 boats-0.024
 sail-0.023
Token her
Token ID607
Feature activation+5.34e+00

Pos logit contributions
 blonde+0.047
oph+0.039
uct+0.038
 fru+0.036
 brow+0.036
Neg logit contributions
 boats-0.108
 sailors-0.107
 boat-0.105
 sail-0.104
 captains-0.099
Token face
Token ID1986
Feature activation+2.88e+00

Pos logit contributions
 blonde+0.150
oph+0.147
uct+0.137
 Could+0.127
 cavity+0.123
Neg logit contributions
 sailors-0.168
 boat-0.167
 boats-0.164
 sail-0.159
 ship-0.156
Token.
Token ID13
Feature activation+1.82e+00

Pos logit contributions
 blonde+0.118
oph+0.110
 fru+0.108
uct+0.106
 brist+0.105
Neg logit contributions
 sailors-0.051
 boat-0.050
 boats-0.048
boat-0.044
 sail-0.044
Token One
Token ID1881
Feature activation+1.74e+00

Pos logit contributions
 blonde+0.064
 brist+0.060
 blush+0.057
 spat+0.056
 brow+0.056
Neg logit contributions
 boats-0.040
 boat-0.039
 sail-0.035
 bridge-0.035
 Fin-0.034
Token day
Token ID1110
Feature activation+1.30e+00

Pos logit contributions
 blonde+0.068
 blush+0.061
 brist+0.060
oph+0.059
 Her+0.058
Neg logit contributions
 sailors-0.039
 boat-0.037
aro-0.036
 boats-0.036
boat-0.035
Token,
Token ID11
Feature activation+1.61e+00

Pos logit contributions
 blonde+0.052
uct+0.046
oph+0.046
 blush+0.046
 brist+0.046
Neg logit contributions
 sailors-0.026
 boat-0.026
aro-0.026
 boats-0.025
ug-0.025
Tokenmy
Token ID1820
Feature activation+8.78e-01

Pos logit contributions
 blonde+0.029
 blush+0.024
 brist+0.024
oph+0.022
 Her+0.022
Neg logit contributions
 sailors-0.035
 boat-0.034
 boats-0.033
boat-0.033
 captains-0.033
Token asked
Token ID1965
Feature activation+1.64e+00

Pos logit contributions
 blonde+0.024
 blush+0.020
 brist+0.019
oph+0.019
 Her+0.018
Neg logit contributions
 sailors-0.031
 boat-0.029
 boats-0.029
aro-0.029
boat-0.029
Token her
Token ID607
Feature activation+1.55e+00

Pos logit contributions
 blonde+0.041
 brist+0.034
 blush+0.034
oph+0.033
uct+0.032
Neg logit contributions
 sailors-0.058
 boats-0.056
 boat-0.055
 sharks-0.054
ug-0.054
Token to
Token ID284
Feature activation-1.51e-01

Pos logit contributions
 blonde+0.043
 blush+0.036
 brist+0.036
oph+0.035
 Her+0.033
Neg logit contributions
 sailors-0.053
 boat-0.051
 boats-0.050
aro-0.049
 captains-0.049
Token brush
Token ID14093
Feature activation+2.19e+00

Pos logit contributions
 sailors+0.004
aro+0.004
 boat+0.004
 boats+0.004
 sharks+0.004
Neg logit contributions
 blonde-0.005
 blush-0.004
 brist-0.004
oph-0.004
 Her-0.004
Token her
Token ID607
Feature activation+5.34e+00

Pos logit contributions
 blonde+0.066
oph+0.056
 blush+0.054
 brist+0.054
uct+0.052
Neg logit contributions
 boat-0.067
 sailors-0.067
 boats-0.066
aro-0.064
 sharks-0.063
Token hair
Token ID4190
Feature activation+3.42e+00

Pos logit contributions
oph+0.165
 blonde+0.127
uct+0.127
omm+0.115
atisf+0.111
Neg logit contributions
 boat-0.164
 boats-0.155
 raft-0.142
 sail-0.141
 crane-0.141
Token before
Token ID878
Feature activation+6.64e-01

Pos logit contributions
 blonde+0.129
oph+0.118
 fru+0.108
uct+0.107
 brist+0.106
Neg logit contributions
 boat-0.075
boat-0.072
 boats-0.070
aro-0.067
boats-0.066
Token going
Token ID1016
Feature activation+2.69e+00

Pos logit contributions
 blonde+0.018
oph+0.016
 brist+0.015
uct+0.015
 blush+0.015
Neg logit contributions
 boat-0.021
 boats-0.021
 sailors-0.021
 sail-0.020
 sharks-0.020
Token to
Token ID284
Feature activation+2.77e+00

Pos logit contributions
 blonde+0.092
oph+0.081
 brist+0.077
 blush+0.076
 fru+0.075
Neg logit contributions
 sailors-0.074
 boats-0.073
 boat-0.073
aro-0.071
 bridge-0.069
Token school
Token ID1524
Feature activation+1.57e+00

Pos logit contributions
 blonde+0.103
oph+0.089
 brow+0.087
 blush+0.086
 brist+0.085
Neg logit contributions
 boat-0.064
 boats-0.063
 sailors-0.063
 sail-0.062
 bridge-0.061
Token a
Token ID257
Feature activation+1.58e+00

Pos logit contributions
 blonde+0.048
oph+0.044
uct+0.041
 Her+0.040
omm+0.040
Neg logit contributions
 sailors-0.046
 boat-0.046
 boats-0.046
 sail-0.044
 raft-0.043
Token brush
Token ID14093
Feature activation+1.16e+00

Pos logit contributions
 blonde+0.048
oph+0.044
uct+0.044
 Her+0.041
 blush+0.041
Neg logit contributions
 boat-0.049
 sail-0.045
 sailors-0.045
 raft-0.044
 bridge-0.044
Token.
Token ID13
Feature activation+1.92e+00

Pos logit contributions
 blonde+0.043
oph+0.038
 blush+0.037
 brist+0.036
 Her+0.035
Neg logit contributions
 boat-0.028
 sailors-0.027
 boats-0.027
boat-0.026
aro-0.026
Token She
Token ID1375
Feature activation+2.92e+00

Pos logit contributions
pron+0.049
oph+0.048
 blonde+0.047
 blush+0.046
ited+0.045
Neg logit contributions
 crane-0.048
 Fin-0.047
 boats-0.046
 bridge-0.046
 sail-0.045
Token gently
Token ID15165
Feature activation+3.28e+00

Pos logit contributions
 blonde+0.092
 blush+0.077
oph+0.076
 Her+0.075
omm+0.073
Neg logit contributions
 boat-0.086
 boats-0.082
 sailors-0.080
 ship-0.076
 raft-0.076
Token scrub
Token ID27268
Feature activation+5.28e+00

Pos logit contributions
 blonde+0.095
omm+0.086
oph+0.084
uct+0.079
 meanings+0.078
Neg logit contributions
 boat-0.098
 boats-0.094
 sail-0.092
 sailors-0.089
 raft-0.089
Tokenbed
Token ID3077
Feature activation+4.68e+00

Pos logit contributions
 blonde+0.178
oph+0.156
 blush+0.145
 Her+0.144
 fru+0.142
Neg logit contributions
ug-0.142
 sailors-0.136
 boats-0.133
aro-0.132
 boat-0.129
Token and
Token ID290
Feature activation+2.99e+00

Pos logit contributions
 blonde+0.175
oph+0.161
uct+0.151
 blush+0.149
 Her+0.147
Neg logit contributions
 boats-0.103
 sailors-0.101
 boat-0.101
ug-0.099
aro-0.095
Token scrub
Token ID27268
Feature activation+5.39e+00

Pos logit contributions
 blonde+0.090
oph+0.082
omm+0.079
 Her+0.078
uct+0.071
Neg logit contributions
 sailors-0.087
 boat-0.086
 boats-0.084
 sail-0.082
ug-0.080
Tokenbed
Token ID3077
Feature activation+4.67e+00

Pos logit contributions
 blonde+0.176
oph+0.157
 blush+0.146
 Her+0.144
uct+0.140
Neg logit contributions
ug-0.151
 sailors-0.145
 boats-0.140
aro-0.139
 boat-0.136
Token until
Token ID1566
Feature activation+1.74e+00

Pos logit contributions
 blonde+0.166
oph+0.152
uct+0.141
 blush+0.141
 Her+0.138
Neg logit contributions
 sailors-0.112
 boats-0.112
ug-0.112
 boat-0.110
aro-0.107
Token.
Token ID13
Feature activation+9.12e-01

Pos logit contributions
 blonde+0.046
 blush+0.041
 brist+0.039
oph+0.039
 Her+0.038
Neg logit contributions
 sailors-0.034
aro-0.032
 boats-0.032
 boat-0.032
ug-0.031
Token Julie
Token ID21946
Feature activation+3.39e+00

Pos logit contributions
 blonde+0.024
 blush+0.020
pron+0.020
 brist+0.020
 fru+0.019
Neg logit contributions
 sailors-0.031
 boats-0.030
 boat-0.029
 whales-0.029
 bridge-0.029
Token started
Token ID2067
Feature activation+2.93e+00

Pos logit contributions
 blonde+0.101
 blush+0.085
oph+0.081
 Her+0.080
amas+0.079
Neg logit contributions
 boat-0.100
 sailors-0.098
 boats-0.098
aro-0.097
ug-0.094
Token to
Token ID284
Feature activation+2.88e+00

Pos logit contributions
oph+0.096
 blonde+0.089
uct+0.089
amas+0.081
 fru+0.081
Neg logit contributions
 boats-0.074
 boat-0.071
 sailors-0.070
 bridge-0.069
 sail-0.068
Token comb
Token ID1974
Feature activation+3.29e+00

Pos logit contributions
oph+0.084
 blonde+0.083
omm+0.080
amas+0.077
 Her+0.075
Neg logit contributions
 sail-0.080
 boat-0.076
 bridge-0.074
 boats-0.073
 sailors-0.073
Token her
Token ID607
Feature activation+5.23e+00

Pos logit contributions
 blonde+0.107
oph+0.092
 blush+0.092
uct+0.089
 Her+0.088
Neg logit contributions
 sailors-0.088
aro-0.087
 boats-0.086
 boat-0.085
ug-0.085
Token own
Token ID898
Feature activation+4.80e+00

Pos logit contributions
oph+0.160
uct+0.131
Da+0.126
 blonde+0.123
Acc+0.116
Neg logit contributions
 boat-0.150
 boats-0.136
 crane-0.131
 sail-0.131
 bridge-0.123
Token hair
Token ID4190
Feature activation+3.56e+00

Pos logit contributions
oph+0.124
uct+0.112
 blonde+0.103
auldron+0.094
 fru+0.093
Neg logit contributions
 boat-0.150
 boats-0.142
 sail-0.136
 crane-0.135
 sailors-0.135
Token.
Token ID13
Feature activation+1.76e+00

Pos logit contributions
 blonde+0.132
oph+0.120
uct+0.116
 fru+0.113
 blush+0.112
Neg logit contributions
 boat-0.076
boat-0.073
 boats-0.071
boats-0.069
 bridge-0.069
Token She
Token ID1375
Feature activation+4.37e+00

Pos logit contributions
 blonde+0.046
 fru+0.041
oph+0.041
pron+0.040
uct+0.040
Neg logit contributions
 sailors-0.053
 boats-0.052
ug-0.052
 bridge-0.051
aro-0.050
Token was
Token ID373
Feature activation+2.29e+00

Pos logit contributions
 blonde+0.135
amas+0.127
omm+0.123
oph+0.120
 Deal+0.115
Neg logit contributions
 boat-0.108
 boats-0.106
 sailed-0.101
 sailors-0.101
aro-0.099
Token with
Token ID351
Feature activation+3.20e-01

Pos logit contributions
 blonde+0.033
 blush+0.029
oph+0.029
 brist+0.028
 Her+0.028
Neg logit contributions
 sailors-0.028
 boat-0.026
 boats-0.026
aro-0.026
boat-0.025
Token a
Token ID257
Feature activation+1.44e+00

Pos logit contributions
 blonde+0.009
 blush+0.008
 brist+0.008
oph+0.008
uct+0.008
Neg logit contributions
 sailors-0.010
 boat-0.009
 boats-0.009
 sharks-0.009
 whales-0.009
Token big
Token ID1263
Feature activation+1.00e+00

Pos logit contributions
 blonde+0.047
 blush+0.041
oph+0.041
 Her+0.041
 brist+0.041
Neg logit contributions
 boat-0.040
 sailors-0.039
 sail-0.037
boat-0.036
 boats-0.036
Token smile
Token ID8212
Feature activation+5.93e-01

Pos logit contributions
 blonde+0.028
 blush+0.024
oph+0.024
 brist+0.024
 Her+0.023
Neg logit contributions
 sailors-0.032
 boat-0.032
 boats-0.031
boat-0.030
 sharks-0.030
Token on
Token ID319
Feature activation+3.14e+00

Pos logit contributions
 blonde+0.023
oph+0.020
 blush+0.020
 brist+0.020
 Her+0.019
Neg logit contributions
 sailors-0.013
 boat-0.013
boat-0.013
aro-0.012
 boats-0.012
Token her
Token ID607
Feature activation+5.23e+00

Pos logit contributions
 blonde+0.061
oph+0.052
 fru+0.051
uct+0.050
elt+0.049
Neg logit contributions
 sail-0.116
 boat-0.114
 sailors-0.114
 boats-0.109
aro-0.107
Token face
Token ID1986
Feature activation+2.56e+00

Pos logit contributions
 blonde+0.141
oph+0.127
uct+0.115
 blush+0.113
 brist+0.109
Neg logit contributions
 sailors-0.174
 boat-0.172
 sail-0.167
 boats-0.164
 ship-0.160
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
 blonde+0.100
oph+0.092
 brist+0.088
 fru+0.088
uct+0.087
Neg logit contributions
 boat-0.050
 sailors-0.049
boat-0.046
 sail-0.046
aro-0.045
Token<|endoftext|>
Token ID50256
Feature activation-8.17e-01

Pos logit contributions
 blonde+0.057
 blush+0.055
 fru+0.055
 brist+0.054
 brow+0.052
Neg logit contributions
 sailors-0.026
 drivers-0.022
 sail-0.022
 they-0.022
 boom-0.021
TokenOnce
Token ID7454
Feature activation+2.70e-01

Pos logit contributions
 sailors+0.025
 boat+0.024
aro+0.023
 boats+0.023
 sharks+0.023
Neg logit contributions
 blonde-0.025
 blush-0.022
 brist-0.022
oph-0.021
 Her-0.021
Token upon
Token ID2402
Feature activation+1.24e+00

Pos logit contributions
 blonde+0.005
 blush+0.004
 Her+0.004
 brist+0.004
oph+0.004
Neg logit contributions
 sailors-0.011
aro-0.011
 boat-0.011
 boats-0.011
 captains-0.011
Token's
Token ID338
Feature activation+2.77e+00

Pos logit contributions
 blonde+0.054
 blush+0.048
 brist+0.046
oph+0.046
 Her+0.045
Neg logit contributions
 sailors-0.040
 boat-0.039
aro-0.038
 boats-0.038
boat-0.038
Token order
Token ID1502
Feature activation-3.67e-01

Pos logit contributions
oph+0.089
 blonde+0.087
uct+0.079
 blush+0.078
 fru+0.074
Neg logit contributions
 boat-0.075
 sailors-0.074
 bridge-0.070
ug-0.068
 boats-0.068
Token.
Token ID13
Feature activation+2.91e-01

Pos logit contributions
 sailors+0.010
 boat+0.009
 boats+0.009
aro+0.009
boat+0.009
Neg logit contributions
 blonde-0.013
 blush-0.011
oph-0.011
 brist-0.011
 Her-0.011
Token She
Token ID1375
Feature activation+3.11e+00

Pos logit contributions
 blonde+0.011
 blush+0.010
 brist+0.010
oph+0.009
 fru+0.009
Neg logit contributions
 sailors-0.006
 boat-0.006
 boats-0.006
ug-0.006
boat-0.006
Token brushed
Token ID31782
Feature activation+2.69e+00

Pos logit contributions
 blonde+0.101
omm+0.087
amas+0.086
oph+0.085
 Deal+0.082
Neg logit contributions
 boat-0.079
 boats-0.077
 sailors-0.073
 sailed-0.072
ug-0.070
Token her
Token ID607
Feature activation+5.21e+00

Pos logit contributions
 blonde+0.078
oph+0.068
 blush+0.066
uct+0.065
 fru+0.061
Neg logit contributions
 sailors-0.083
 boat-0.081
 boats-0.081
ug-0.080
boat-0.078
Token hair
Token ID4190
Feature activation+4.01e+00

Pos logit contributions
oph+0.178
uct+0.141
 blonde+0.139
assy+0.128
Em+0.127
Neg logit contributions
 boat-0.135
 boats-0.129
 sail-0.118
 bridge-0.113
 paddle-0.112
Token with
Token ID351
Feature activation+1.20e+00

Pos logit contributions
 blonde+0.152
oph+0.141
uct+0.130
 fru+0.127
 blush+0.125
Neg logit contributions
 boat-0.085
boat-0.080
 boats-0.079
ug-0.076
 sail-0.075
Token the
Token ID262
Feature activation+2.66e+00

Pos logit contributions
 blonde+0.035
oph+0.034
uct+0.032
 blush+0.031
 Her+0.030
Neg logit contributions
 sailors-0.035
 boats-0.035
 boat-0.034
 sail-0.033
 sharks-0.032
Token brush
Token ID14093
Feature activation+2.40e+00

Pos logit contributions
oph+0.075
uct+0.066
 blonde+0.062
anna+0.055
omm+0.054
Neg logit contributions
 boat-0.082
 crane-0.079
 bridge-0.078
 sail-0.076
 boats-0.076
Token very
Token ID845
Feature activation+2.47e+00

Pos logit contributions
 blonde+0.081
oph+0.074
uct+0.070
 blush+0.069
 brist+0.068
Neg logit contributions
 boat-0.062
 boats-0.059
boat-0.058
 sailors-0.058
 sail-0.057
TokenAfter
Token ID3260
Feature activation-5.12e-01

Pos logit contributions
 blonde+0.058
 blush+0.051
 brist+0.048
 fru+0.047
 blond+0.047
Neg logit contributions
 sailors-0.043
 boats-0.042
 boat-0.042
 captains-0.041
ug-0.041
Token her
Token ID607
Feature activation+3.44e+00

Pos logit contributions
 sailors+0.014
 boat+0.013
aro+0.013
 boats+0.013
 sharks+0.013
Neg logit contributions
 blonde-0.018
 blush-0.015
 brist-0.015
oph-0.015
 Her-0.015
Token mom
Token ID1995
Feature activation+2.69e+00

Pos logit contributions
 blonde+0.111
oph+0.107
uct+0.099
 fru+0.097
 brow+0.091
Neg logit contributions
 boat-0.088
 boats-0.085
 bridge-0.080
 sailors-0.079
 sail-0.079
Tokenmy
Token ID1820
Feature activation+2.78e+00

Pos logit contributions
 blonde+0.085
 brist+0.068
oph+0.068
 fru+0.068
 brow+0.066
Neg logit contributions
ug-0.073
 boat-0.073
 sailors-0.072
 boats-0.071
 ship-0.068
Token brushed
Token ID31782
Feature activation+2.79e+00

Pos logit contributions
 blonde+0.082
 blush+0.065
oph+0.065
 fru+0.064
 brist+0.064
Neg logit contributions
 boat-0.084
 sailors-0.082
ug-0.081
 boats-0.081
aro-0.077
Token her
Token ID607
Feature activation+5.21e+00

Pos logit contributions
 blonde+0.071
oph+0.061
uct+0.058
 blush+0.056
 fru+0.054
Neg logit contributions
 boat-0.096
 boats-0.095
ug-0.094
 sailors-0.093
aro-0.092
Token hair
Token ID4190
Feature activation+3.59e+00

Pos logit contributions
oph+0.187
uct+0.146
 blonde+0.146
Da+0.143
 fru+0.131
Neg logit contributions
 boat-0.139
 boats-0.130
 sail-0.117
 train-0.116
 bridge-0.114
Token,
Token ID11
Feature activation+1.72e+00

Pos logit contributions
 blonde+0.148
oph+0.137
uct+0.130
 fru+0.125
 blush+0.123
Neg logit contributions
 boat-0.070
ug-0.065
 boats-0.064
boat-0.064
aro-0.061
Token Lily
Token ID20037
Feature activation+3.64e+00

Pos logit contributions
 blonde+0.053
oph+0.046
 brist+0.045
uct+0.044
 brow+0.043
Neg logit contributions
 boat-0.051
 boats-0.051
 sailors-0.050
 sail-0.047
 sharks-0.046
Token and
Token ID290
Feature activation+1.89e+00

Pos logit contributions
 blonde+0.124
omm+0.109
 Deal+0.107
oph+0.106
 fru+0.106
Neg logit contributions
 boat-0.093
 boats-0.086
 ship-0.082
 sailors-0.081
 sailed-0.081
Token her
Token ID607
Feature activation+2.34e+00

Pos logit contributions
 blonde+0.041
 brist+0.032
oph+0.030
 blush+0.029
 blond+0.028
Neg logit contributions
 sailors-0.078
 boats-0.076
 boat-0.076
 ship-0.071
 sail-0.070
Token
Token ID198
Feature activation-2.43e-01

Pos logit contributions
 sailors+0.045
 boat+0.043
aro+0.043
 boats+0.043
 sharks+0.042
Neg logit contributions
 blonde-0.038
 blush-0.033
 brist-0.032
oph-0.031
 Her-0.031
Token
Token ID198
Feature activation-1.60e-01

Pos logit contributions
 sailors+0.009
 captains+0.009
 boat+0.008
aro+0.008
boats+0.008
Neg logit contributions
 blonde-0.006
 Her-0.005
 blush-0.005
oph-0.005
 brist-0.005
TokenAfter
Token ID3260
Feature activation-1.29e+00

Pos logit contributions
 sailors+0.006
aro+0.005
 boat+0.005
 boats+0.005
 captains+0.005
Neg logit contributions
 blonde-0.004
 blush-0.004
oph-0.003
 brist-0.003
 Her-0.003
Token he
Token ID339
Feature activation+2.53e+00

Pos logit contributions
 sailors+0.041
boat+0.041
boats+0.041
aro+0.041
 captains+0.040
Neg logit contributions
 blonde-0.037
 blush-0.033
 brist-0.031
 Her-0.031
 makeup-0.030
Token brushed
Token ID31782
Feature activation+1.66e+00

Pos logit contributions
 blonde+0.075
 Her+0.061
amas+0.061
oph+0.061
 brist+0.059
Neg logit contributions
 boat-0.075
 sailors-0.072
 boats-0.071
 sail-0.071
aro-0.069
Token his
Token ID465
Feature activation+5.20e+00

Pos logit contributions
 blonde+0.061
 blush+0.055
 brist+0.053
oph+0.053
 Her+0.052
Neg logit contributions
 sailors-0.041
 boat-0.039
 boats-0.038
aro-0.038
boat-0.037
Token hair
Token ID4190
Feature activation+3.20e+00

Pos logit contributions
oph+0.183
Da+0.147
uct+0.145
enny+0.137
 blonde+0.136
Neg logit contributions
 boat-0.135
 boats-0.128
 sail-0.123
 crane-0.119
 sailors-0.119
Token,
Token ID11
Feature activation-8.51e-01

Pos logit contributions
 blonde+0.124
oph+0.116
uct+0.110
 blush+0.105
 fru+0.105
Neg logit contributions
 boat-0.070
boat-0.066
 boats-0.064
ug-0.062
 sail-0.062
Token Jack
Token ID3619
Feature activation+1.90e+00

Pos logit contributions
aro+0.024
 sailors+0.024
ug+0.023
boat+0.023
 captains+0.023
Neg logit contributions
 blonde-0.028
 blush-0.024
 brist-0.023
 Her-0.023
oph-0.023
Token would
Token ID561
Feature activation+3.54e+00

Pos logit contributions
 blonde+0.056
oph+0.047
 blush+0.047
 brist+0.046
 Her+0.045
Neg logit contributions
 boat-0.060
 sailors-0.059
 boats-0.058
boat-0.056
 ship-0.056
Token brush
Token ID14093
Feature activation+1.66e+00

Pos logit contributions
 blonde+0.118
oph+0.113
 fru+0.100
omm+0.100
uct+0.100
Neg logit contributions
 sail-0.094
 boat-0.091
 sailors-0.085
 bridge-0.084
 boats-0.083
Token and
Token ID290
Feature activation+2.83e+00

Pos logit contributions
 blonde+0.090
oph+0.080
 blush+0.078
 brist+0.075
 fru+0.074
Neg logit contributions
boat-0.061
 boat-0.061
ug-0.059
 boats-0.058
 sailors-0.058
Token put
Token ID1234
Feature activation+1.03e+00

Pos logit contributions
 blonde+0.080
oph+0.078
omm+0.073
uct+0.071
 Her+0.068
Neg logit contributions
 boat-0.087
 sailors-0.085
 sail-0.084
 boats-0.082
 sailed-0.079
Token on
Token ID319
Feature activation+1.25e+00

Pos logit contributions
 blonde+0.039
oph+0.035
 blush+0.034
 Her+0.034
 brist+0.033
Neg logit contributions
 sailors-0.025
 boat-0.024
 boats-0.023
aro-0.023
 sharks-0.022
Token his
Token ID465
Feature activation+3.39e+00

Pos logit contributions
 blonde+0.050
oph+0.047
 blush+0.046
 brist+0.044
 Her+0.044
Neg logit contributions
 boat-0.025
 sailors-0.025
 boats-0.025
 sharks-0.023
aro-0.023
Token p
Token ID279
Feature activation+3.32e+00

Pos logit contributions
oph+0.111
uct+0.094
 blonde+0.086
aman+0.085
 Her+0.080
Neg logit contributions
 boat-0.104
 boats-0.097
 sailors-0.093
 sail-0.092
 fish-0.091
Tokenaj
Token ID1228
Feature activation+5.19e+00

Pos logit contributions
 blonde+0.080
oph+0.070
 blush+0.069
uct+0.067
 brist+0.064
Neg logit contributions
ug-0.110
aro-0.109
 boat-0.108
 boats-0.106
 bridge-0.106
Tokenamas
Token ID17485
Feature activation+5.18e-01

Pos logit contributions
uct+0.102
 blonde+0.096
 fru+0.092
 blush+0.092
 Could+0.090
Neg logit contributions
ug-0.170
 sailors-0.164
 boats-0.163
 boat-0.159
 sail-0.157
Token.
Token ID13
Feature activation+7.88e-01

Pos logit contributions
 blonde+0.018
 blush+0.016
 brist+0.016
oph+0.016
 Her+0.015
Neg logit contributions
 sailors-0.014
 boat-0.013
aro-0.013
boat-0.013
 boats-0.013
Token Then
Token ID3244
Feature activation-2.68e-01

Pos logit contributions
 blonde+0.028
 blush+0.027
oph+0.027
 brist+0.026
uct+0.026
Neg logit contributions
 sailors-0.016
 sail-0.016
 boats-0.015
 boat-0.015
 bridge-0.015
Token he
Token ID339
Feature activation+2.14e+00

Pos logit contributions
 sailors+0.007
 boat+0.006
aro+0.006
 boats+0.006
 sharks+0.006
Neg logit contributions
 blonde-0.010
 blush-0.009
 brist-0.009
oph-0.008
 Her-0.008
Token sn
Token ID3013
Feature activation+2.66e+00

Pos logit contributions
 blonde+0.067
uct+0.057
 Her+0.055
oph+0.055
 blush+0.055
Neg logit contributions
 boat-0.063
 sailors-0.060
 boats-0.059
 ship-0.059
 sail-0.058
Token with
Token ID351
Feature activation+3.58e-02

Pos logit contributions
 blonde+0.085
 blush+0.074
oph+0.072
 brist+0.071
 fru+0.069
Neg logit contributions
 boat-0.071
 sailors-0.070
 boats-0.067
ug-0.066
aro-0.065
Token a
Token ID257
Feature activation+7.72e-01

Pos logit contributions
 blonde+0.001
oph+0.001
 blush+0.001
 brist+0.001
uct+0.001
Neg logit contributions
 sailors-0.001
 boat-0.001
 boats-0.001
 sharks-0.001
 sail-0.001
Token big
Token ID1263
Feature activation+1.06e+00

Pos logit contributions
 blonde+0.027
oph+0.024
uct+0.024
 brist+0.023
 blush+0.023
Neg logit contributions
 boat-0.021
 sail-0.019
 sailors-0.019
 bridge-0.018
boat-0.018
Token smile
Token ID8212
Feature activation+2.74e-01

Pos logit contributions
 blonde+0.031
oph+0.026
 blush+0.026
 brist+0.025
 Her+0.025
Neg logit contributions
 boat-0.033
 sailors-0.033
 boats-0.032
boat-0.031
 sail-0.031
Token on
Token ID319
Feature activation+2.58e+00

Pos logit contributions
 blonde+0.011
 blush+0.009
oph+0.009
 brist+0.009
 Her+0.009
Neg logit contributions
 sailors-0.006
 boat-0.006
boat-0.006
aro-0.006
 boats-0.006
Token her
Token ID607
Feature activation+5.18e+00

Pos logit contributions
 blonde+0.053
oph+0.042
 pad+0.038
uct+0.038
 fru+0.037
Neg logit contributions
 sail-0.099
 boat-0.098
 sailors-0.097
 boats-0.096
aro-0.091
Token face
Token ID1986
Feature activation+2.18e+00

Pos logit contributions
 blonde+0.150
oph+0.136
 blush+0.118
 fru+0.115
uct+0.115
Neg logit contributions
 boat-0.161
 sailors-0.161
 sail-0.156
 boats-0.151
 ship-0.148
Token.
Token ID13
Feature activation+1.16e+00

Pos logit contributions
 blonde+0.088
oph+0.080
 brist+0.077
 fru+0.077
 blush+0.075
Neg logit contributions
 boat-0.041
 sailors-0.040
boat-0.038
 sail-0.038
aro-0.038
Token<|endoftext|>
Token ID50256
Feature activation-4.29e-01

Pos logit contributions
 blonde+0.048
 blush+0.043
 blond+0.041
 brist+0.041
 brow+0.040
Neg logit contributions
 sailors-0.020
 boat-0.019
 boats-0.019
 sail-0.019
 Fin-0.017
TokenOnce
Token ID7454
Feature activation-2.12e-02

Pos logit contributions
 sailors+0.014
 boat+0.013
aro+0.013
 boats+0.013
 sharks+0.013
Neg logit contributions
 blonde-0.013
 blush-0.011
 brist-0.011
oph-0.010
 Her-0.010
Token upon
Token ID2402
Feature activation+1.02e+00

Pos logit contributions
 sailors+0.001
aro+0.001
 boat+0.001
 captains+0.001
 boats+0.001
Neg logit contributions
 blonde-0.000
 blush-0.000
 Her-0.000
oph-0.000
 brist-0.000
TokenWhen
Token ID2215
Feature activation-4.73e-02

Pos logit contributions
 blonde+0.047
 blush+0.040
 brist+0.038
oph+0.037
 fru+0.037
Neg logit contributions
 sailors-0.054
aro-0.051
 boat-0.051
 boats-0.050
 captains-0.050
Token Julie
Token ID21946
Feature activation+3.01e+00

Pos logit contributions
 sailors+0.002
 boat+0.002
 boats+0.002
aro+0.002
 sharks+0.002
Neg logit contributions
 blonde-0.001
 blush-0.001
 brist-0.001
oph-0.001
 Her-0.001
Token finished
Token ID5201
Feature activation+3.16e+00

Pos logit contributions
 blonde+0.095
amas+0.080
 brist+0.079
omm+0.077
 brow+0.076
Neg logit contributions
 boat-0.082
 boats-0.076
 sailed-0.075
 sail-0.074
aro-0.073
Token comb
Token ID1974
Feature activation+2.62e+00

Pos logit contributions
 blonde+0.096
oph+0.085
 brow+0.082
uct+0.082
 fru+0.077
Neg logit contributions
 boat-0.090
 boats-0.089
aro-0.086
 sail-0.085
 bridge-0.081
Tokening
Token ID278
Feature activation+2.36e+00

Pos logit contributions
 blonde+0.087
oph+0.075
 blush+0.074
uct+0.073
 brist+0.072
Neg logit contributions
 boat-0.069
aro-0.069
 sailors-0.067
 boats-0.067
ug-0.066
Token her
Token ID607
Feature activation+5.17e+00

Pos logit contributions
 blonde+0.072
oph+0.061
 blush+0.061
 brist+0.059
uct+0.058
Neg logit contributions
 sailors-0.071
aro-0.070
 boat-0.069
 boats-0.069
ug-0.066
Token hair
Token ID4190
Feature activation+3.25e+00

Pos logit contributions
oph+0.169
Da+0.147
uct+0.143
 blonde+0.127
riet+0.124
Neg logit contributions
 boat-0.132
 boats-0.123
 sail-0.122
 crane-0.115
 train-0.110
Token,
Token ID11
Feature activation+1.34e+00

Pos logit contributions
 blonde+0.131
uct+0.123
oph+0.123
 fru+0.115
 cavity+0.115
Neg logit contributions
 boat-0.057
boat-0.050
 boats-0.047
 sail-0.046
aro-0.045
Token she
Token ID673
Feature activation+2.95e+00

Pos logit contributions
 blonde+0.029
oph+0.023
 brist+0.023
 blush+0.023
 fru+0.021
Neg logit contributions
 sailors-0.054
 boat-0.052
 boats-0.052
aro-0.051
 sharks-0.050
Token showed
Token ID3751
Feature activation+1.59e+00

Pos logit contributions
 blonde+0.096
omm+0.081
amas+0.079
 Her+0.078
 brist+0.076
Neg logit contributions
 boat-0.077
 sailors-0.075
 boats-0.074
 sailed-0.072
 sail-0.072
Token her
Token ID607
Feature activation+2.22e+00

Pos logit contributions
 blonde+0.034
 brist+0.025
 blush+0.025
oph+0.024
pron+0.024
Neg logit contributions
 sailors-0.065
 boat-0.063
 boats-0.063
aro-0.062
 whales-0.061
Token straight
Token ID3892
Feature activation+5.24e-01

Pos logit contributions
 blonde+0.008
 blush+0.007
 brist+0.007
 Her+0.007
oph+0.007
Neg logit contributions
 sailors-0.010
 boat-0.010
 boats-0.010
aro-0.009
boat-0.009
Tokenened
Token ID2945
Feature activation+9.75e-01

Pos logit contributions
 blonde+0.014
 blush+0.012
 Her+0.011
oph+0.011
 brist+0.011
Neg logit contributions
 sailors-0.018
 boat-0.018
 boats-0.017
aro-0.017
ug-0.017
Token the
Token ID262
Feature activation+2.91e+00

Pos logit contributions
 blonde+0.035
 blush+0.031
 brist+0.031
oph+0.030
 Her+0.030
Neg logit contributions
 sailors-0.025
 boat-0.023
aro-0.023
 boats-0.023
 sharks-0.023
Token dress
Token ID6576
Feature activation+1.53e+00

Pos logit contributions
 blonde+0.085
oph+0.077
 Her+0.073
uct+0.071
 fru+0.068
Neg logit contributions
 boat-0.089
 sail-0.081
 bridge-0.080
 boats-0.080
 ship-0.077
Token on
Token ID319
Feature activation+1.97e+00

Pos logit contributions
 blonde+0.049
 blush+0.043
 brist+0.042
oph+0.041
 Her+0.040
Neg logit contributions
 sailors-0.044
 boat-0.043
aro-0.042
 boats-0.042
boat-0.042
Token her
Token ID607
Feature activation+5.16e+00

Pos logit contributions
 blonde+0.072
 blush+0.064
 brist+0.062
oph+0.061
 Her+0.061
Neg logit contributions
 sailors-0.048
 boat-0.046
 boats-0.045
aro-0.044
 sharks-0.043
Token body
Token ID1767
Feature activation+1.07e+00

Pos logit contributions
 blonde+0.143
oph+0.132
uct+0.122
 cavity+0.122
 fru+0.120
Neg logit contributions
 boat-0.170
 sail-0.158
 boats-0.156
 ship-0.155
 sailors-0.151
Token.
Token ID13
Feature activation+1.29e+00

Pos logit contributions
 blonde+0.036
 blush+0.031
 brist+0.031
oph+0.030
 Her+0.030
Neg logit contributions
 sailors-0.030
 boat-0.028
aro-0.028
 boats-0.028
 sharks-0.027
Token It
Token ID632
Feature activation+1.66e+00

Pos logit contributions
 blonde+0.038
pron+0.036
 blush+0.035
 cavity+0.034
 brist+0.033
Neg logit contributions
 whales-0.034
 sailors-0.034
 boats-0.032
 bridge-0.031
aro-0.031
Token was
Token ID373
Feature activation+2.05e+00

Pos logit contributions
 blonde+0.046
 blush+0.039
 brist+0.037
oph+0.037
 Her+0.037
Neg logit contributions
 sailors-0.055
 boat-0.054
aro-0.053
 boats-0.053
boat-0.053
Token beautiful
Token ID4950
Feature activation+1.62e+00

Pos logit contributions
 blonde+0.065
 blush+0.061
oph+0.059
 Her+0.059
 brist+0.057
Neg logit contributions
 sailors-0.053
 boats-0.050
 boat-0.050
 sharks-0.048
 sail-0.048
Token worry
Token ID5490
Feature activation-2.20e+00

Pos logit contributions
 sailors+0.037
aro+0.036
boats+0.036
ug+0.036
boat+0.035
Neg logit contributions
 blonde-0.021
 Her-0.018
 blush-0.018
 brist-0.016
 makeup-0.016
Token,
Token ID11
Feature activation-2.65e+00

Pos logit contributions
 sailors+0.079
 captains+0.077
boat+0.076
aro+0.075
boats+0.074
Neg logit contributions
 blonde-0.051
oph-0.048
 Her-0.045
 blush-0.042
omm-0.041
Token kids
Token ID3988
Feature activation-3.09e+00

Pos logit contributions
ug+0.089
boat+0.087
 afloat+0.085
aro+0.085
ull+0.083
Neg logit contributions
 blonde-0.066
oph-0.060
 blush-0.056
uct-0.056
 Her-0.055
Token!"
Token ID2474
Feature activation-2.78e+00

Pos logit contributions
 sailors+0.109
 captains+0.106
 boats+0.103
aro+0.102
 whales+0.102
Neg logit contributions
 blonde-0.070
 Her-0.062
 unw-0.061
 blush-0.060
oph-0.058
Token the
Token ID262
Feature activation-3.51e+00

Pos logit contributions
 sailors+0.082
ug+0.081
aro+0.081
boat+0.080
 captains+0.079
Neg logit contributions
 blonde-0.087
 Her-0.078
 blush-0.076
 brist-0.071
 She-0.071
Token zo
Token ID40565
Feature activation-5.95e+00

Pos logit contributions
 afloat+0.097
aro+0.095
ug+0.095
boat+0.088
boats+0.087
Neg logit contributions
 blonde-0.104
 Her-0.092
 l-0.089
 brist-0.088
 me-0.087
Tokenoke
Token ID2088
Feature activation-4.06e+00

Pos logit contributions
 afloat+0.220
 raft+0.217
 sail+0.199
 boats+0.195
 sailors+0.192
Neg logit contributions
 Her-0.110
 She-0.099
 blush-0.099
 blonde-0.096
anna-0.091
Tokeneper
Token ID5723
Feature activation-2.52e+00

Pos logit contributions
 afloat+0.101
 port+0.100
 flood+0.099
 raft+0.096
 sail+0.095
Neg logit contributions
 brow-0.108
 Her-0.108
 her-0.106
 herself-0.102
uct-0.100
Token said
Token ID531
Feature activation-3.87e-01

Pos logit contributions
 sailors+0.101
 sharks+0.099
 captains+0.099
boats+0.098
 boats+0.098
Neg logit contributions
 blonde-0.044
 Her-0.040
 blush-0.039
 brushed-0.036
 unw-0.036
Token.
Token ID13
Feature activation-1.52e+00

Pos logit contributions
 sailors+0.012
aro+0.012
 captains+0.012
 sharks+0.012
boat+0.012
Neg logit contributions
 blonde-0.011
 Her-0.010
 blush-0.010
 brist-0.009
 brow-0.009
Token "
Token ID366
Feature activation-7.07e-02

Pos logit contributions
 sailors+0.061
 boat+0.059
aro+0.059
 boats+0.058
 sharks+0.058
Neg logit contributions
 blonde-0.033
 blush-0.027
 brist-0.025
oph-0.024
 Her-0.024
Token sorry
Token ID7926
Feature activation-1.76e+00

Pos logit contributions
ug+0.046
boat+0.045
boats+0.045
aro+0.043
 captains+0.042
Neg logit contributions
 blonde-0.041
 blush-0.036
 makeup-0.034
 fru-0.034
oph-0.034
Token,
Token ID11
Feature activation-1.21e+00

Pos logit contributions
aro+0.053
boat+0.052
 sailors+0.052
boats+0.050
 captains+0.050
Neg logit contributions
 blonde-0.051
 blush-0.046
oph-0.046
 Her-0.045
 brist-0.045
Token sorry
Token ID7926
Feature activation-1.84e+00

Pos logit contributions
ug+0.037
boat+0.037
boats+0.036
aro+0.035
 captains+0.034
Neg logit contributions
 blonde-0.032
 blush-0.028
 makeup-0.028
 honey-0.028
 fru-0.028
Token!"
Token ID2474
Feature activation-1.93e+00

Pos logit contributions
aro+0.056
 sailors+0.054
boat+0.054
 captains+0.052
ug+0.052
Neg logit contributions
 blonde-0.053
 blush-0.048
 brist-0.048
 Her-0.047
oph-0.047
Token the
Token ID262
Feature activation-2.93e+00

Pos logit contributions
 sailors+0.059
aro+0.057
boat+0.056
 captains+0.056
boats+0.056
Neg logit contributions
 blonde-0.059
 blush-0.052
 Her-0.051
 brist-0.050
oph-0.048
Token zo
Token ID40565
Feature activation-5.94e+00

Pos logit contributions
ug+0.068
aro+0.064
boats+0.060
 afloat+0.059
boat+0.058
Neg logit contributions
 blonde-0.098
 makeup-0.087
 brow-0.086
 brist-0.086
 blush-0.086
Tokenoke
Token ID2088
Feature activation-3.75e+00

Pos logit contributions
 raft+0.209
 afloat+0.204
 sail+0.188
boat+0.185
 boat+0.183
Neg logit contributions
 blush-0.114
 Her-0.110
 blonde-0.108
 spat-0.105
oph-0.104
Tokenep
Token ID538
Feature activation-3.01e+00

Pos logit contributions
 port+0.090
 planet+0.086
 afloat+0.086
 flood+0.085
 raft+0.085
Neg logit contributions
 brow-0.104
uct-0.100
 her-0.098
 Her-0.097
 herself-0.097
Tokeners
Token ID364
Feature activation-3.08e+00

Pos logit contributions
 sailors+0.102
aro+0.099
 raft+0.099
 sharks+0.099
 boats+0.098
Neg logit contributions
 blonde-0.060
oph-0.060
 Her-0.059
uct-0.058
 blush-0.058
Token said
Token ID531
Feature activation+2.05e-01

Pos logit contributions
aro+0.117
 sailors+0.117
ug+0.112
boats+0.111
boat+0.111
Neg logit contributions
 blonde-0.066
 blush-0.060
 Her-0.057
oph-0.053
 spat-0.052
Token.
Token ID13
Feature activation-1.75e+00

Pos logit contributions
 blonde+0.007
 blush+0.006
 brist+0.006
 Her+0.006
oph+0.005
Neg logit contributions
 sailors-0.006
aro-0.006
 boat-0.006
 boats-0.006
 sharks-0.006
Token
Token ID198
Feature activation-8.19e-01

Pos logit contributions
 sailors+0.049
 boats+0.047
aro+0.046
 boat+0.046
 sharks+0.046
Neg logit contributions
 blonde-0.039
 Her-0.033
oph-0.033
 blush-0.032
uct-0.031
TokenSuddenly
Token ID38582
Feature activation-1.81e+00

Pos logit contributions
 sailors+0.027
 boats+0.026
aro+0.025
 boat+0.025
 sharks+0.025
Neg logit contributions
 blonde-0.024
oph-0.020
 Her-0.020
 blush-0.020
 brist-0.019
Token,
Token ID11
Feature activation-2.09e+00

Pos logit contributions
 sailors+0.061
aro+0.059
 captains+0.058
 boats+0.058
ug+0.057
Neg logit contributions
 blonde-0.050
 Her-0.041
 blush-0.040
oph-0.040
 brist-0.038
Token a
Token ID257
Feature activation-7.59e-01

Pos logit contributions
ug+0.064
 sailors+0.063
aro+0.063
 boats+0.061
 captains+0.061
Neg logit contributions
 blonde-0.062
 blush-0.053
oph-0.052
 Her-0.052
 brow-0.049
Token big
Token ID1263
Feature activation-9.82e-01

Pos logit contributions
 sailors+0.023
aro+0.023
 boats+0.022
 captains+0.022
boats+0.022
Neg logit contributions
 blonde-0.024
 blush-0.020
 brist-0.020
 Her-0.019
oph-0.018
Token tank
Token ID6873
Feature activation-5.87e+00

Pos logit contributions
aro+0.029
 sailors+0.029
 captains+0.028
boats+0.027
ug+0.027
Neg logit contributions
 blonde-0.032
 blush-0.027
 brist-0.027
 makeup-0.025
 Her-0.025
Token came
Token ID1625
Feature activation-2.28e+00

Pos logit contributions
aro+0.243
 sailors+0.239
ug+0.236
 captains+0.229
 boats+0.227
Neg logit contributions
 spat-0.080
 blonde-0.079
 blush-0.067
 unw-0.063
 brow-0.062
Token out
Token ID503
Feature activation-2.01e+00

Pos logit contributions
aro+0.076
 sailors+0.074
 captains+0.072
 boat+0.072
boats+0.072
Neg logit contributions
 blonde-0.060
 Her-0.051
 brow-0.050
 brist-0.049
 blush-0.048
Token of
Token ID286
Feature activation-1.72e+00

Pos logit contributions
aro+0.060
 captains+0.060
boats+0.060
 sailors+0.058
boat+0.058
Neg logit contributions
 blonde-0.056
 Her-0.050
 blush-0.049
 She-0.048
 brist-0.048
Token the
Token ID262
Feature activation-1.86e+00

Pos logit contributions
 sailors+0.047
aro+0.045
 boat+0.044
 captains+0.044
 boats+0.044
Neg logit contributions
 blonde-0.059
 blush-0.051
 brist-0.051
 Her-0.049
oph-0.049
Token bushes
Token ID37413
Feature activation-3.16e+00

Pos logit contributions
aro+0.041
ug+0.038
 sailors+0.033
 whales+0.031
ull+0.031
Neg logit contributions
 blonde-0.073
 makeup-0.066
 blush-0.065
 brow-0.065
 brist-0.065
TokenOne
Token ID3198
Feature activation-1.45e+00

Pos logit contributions
 sailors+0.045
 boat+0.043
 boats+0.043
 sharks+0.042
 whales+0.042
Neg logit contributions
 blonde-0.030
 Her-0.024
oph-0.024
uct-0.024
 blush-0.023
Token day
Token ID1110
Feature activation-1.84e+00

Pos logit contributions
aro+0.047
 sailors+0.046
 captains+0.044
boats+0.043
ug+0.043
Neg logit contributions
 blonde-0.041
pron-0.034
 Her-0.034
 blush-0.033
oph-0.032
Token,
Token ID11
Feature activation-1.66e+00

Pos logit contributions
 sailors+0.058
boat+0.057
boats+0.057
 captains+0.056
aro+0.055
Neg logit contributions
 blonde-0.054
 blush-0.045
 Her-0.045
 brist-0.042
 makeup-0.041
Token the
Token ID262
Feature activation-3.62e+00

Pos logit contributions
 sailors+0.048
boat+0.047
ug+0.047
boats+0.046
aro+0.046
Neg logit contributions
 blonde-0.053
 blush-0.045
 Her-0.044
 brist-0.043
oph-0.042
Token two
Token ID734
Feature activation-4.01e+00

Pos logit contributions
aro+0.114
ug+0.112
boat+0.103
boats+0.099
 afloat+0.099
Neg logit contributions
 blonde-0.106
 blush-0.092
 makeup-0.088
oph-0.085
pron-0.085
Token teams
Token ID3466
Feature activation-5.81e+00

Pos logit contributions
aro+0.119
boat+0.114
 afloat+0.113
 boom+0.109
boats+0.107
Neg logit contributions
 blonde-0.122
oph-0.111
 Her-0.104
 blush-0.102
 makeup-0.095
Token decided
Token ID3066
Feature activation-5.42e-01

Pos logit contributions
aro+0.227
 sailors+0.220
 sharks+0.214
ug+0.210
 whales+0.210
Neg logit contributions
 blonde-0.110
 blush-0.094
 Her-0.087
oph-0.084
 brushed-0.083
Token to
Token ID284
Feature activation-2.52e+00

Pos logit contributions
 sailors+0.021
aro+0.021
ug+0.020
 boat+0.020
boat+0.020
Neg logit contributions
 blonde-0.012
 blush-0.009
 Her-0.009
 brist-0.009
oph-0.009
Token enter
Token ID3802
Feature activation-2.22e+00

Pos logit contributions
aro+0.080
 sailors+0.079
 sharks+0.078
ug+0.077
boats+0.076
Neg logit contributions
 blonde-0.072
 blush-0.064
 Her-0.062
 makeup-0.059
 unw-0.058
Token a
Token ID257
Feature activation-1.66e+00

Pos logit contributions
aro+0.069
 sailors+0.068
boat+0.067
 captains+0.066
ug+0.066
Neg logit contributions
 blonde-0.063
 makeup-0.052
 blush-0.052
 Her-0.052
 brist-0.049
Token race
Token ID3234
Feature activation-3.85e+00

Pos logit contributions
aro+0.050
 sailors+0.048
ug+0.048
ull+0.043
boat+0.043
Neg logit contributions
 blonde-0.052
oph-0.045
pron-0.045
 makeup-0.044
 blush-0.044
TokenBut
Token ID1537
Feature activation-1.83e+00

Pos logit contributions
 sailors+0.048
aro+0.047
 boat+0.047
 boats+0.046
ug+0.046
Neg logit contributions
 blonde-0.021
Just-0.017
 brist-0.017
 Her-0.016
oph-0.016
Token then
Token ID788
Feature activation-1.40e+00

Pos logit contributions
 sailors+0.061
boat+0.060
boats+0.059
ug+0.059
 captains+0.058
Neg logit contributions
 blonde-0.047
 blush-0.042
 Her-0.039
 brist-0.039
oph-0.038
Token,
Token ID11
Feature activation-1.66e+00

Pos logit contributions
boat+0.048
boats+0.045
aro+0.044
ug+0.044
 sailors+0.043
Neg logit contributions
 blonde-0.039
 blush-0.034
 Her-0.033
 makeup-0.031
 She-0.031
Token a
Token ID257
Feature activation-1.25e+00

Pos logit contributions
boat+0.044
ug+0.044
boats+0.043
aro+0.042
 sailors+0.042
Neg logit contributions
 blonde-0.055
 blush-0.051
 Her-0.048
 makeup-0.047
oph-0.045
Token big
Token ID1263
Feature activation-1.15e+00

Pos logit contributions
 sailors+0.037
aro+0.036
ug+0.035
 captains+0.034
boats+0.034
Neg logit contributions
 blonde-0.040
 blush-0.035
 brist-0.034
pron-0.032
 fru-0.032
Token truck
Token ID7779
Feature activation-5.76e+00

Pos logit contributions
aro+0.032
 sailors+0.031
 captains+0.031
boats+0.030
ug+0.030
Neg logit contributions
 blonde-0.037
 blush-0.034
 brist-0.033
 makeup-0.031
 fru-0.030
Token comes
Token ID2058
Feature activation-2.80e+00

Pos logit contributions
 sailors+0.212
 afloat+0.210
aro+0.209
ug+0.209
 crew+0.200
Neg logit contributions
 blonde-0.095
 blush-0.094
 spat-0.092
 Her-0.092
 She-0.090
Token.
Token ID13
Feature activation-2.20e+00

Pos logit contributions
aro+0.106
boat+0.101
boats+0.101
 sailors+0.100
 captains+0.098
Neg logit contributions
 blonde-0.057
 brow-0.052
 Her-0.050
 brist-0.047
 She-0.045
Token It
Token ID632
Feature activation-2.78e+00

Pos logit contributions
 sailors+0.084
aro+0.083
boats+0.082
boat+0.082
 captains+0.082
Neg logit contributions
 blonde-0.050
 Her-0.043
 blush-0.040
 brist-0.039
oph-0.036
Token drives
Token ID10182
Feature activation-2.45e+00

Pos logit contributions
 sailors+0.106
ug+0.105
aro+0.104
boat+0.102
 captains+0.099
Neg logit contributions
 blonde-0.058
 blush-0.047
 Her-0.046
 brist-0.046
 fru-0.045
Token on
Token ID319
Feature activation-9.49e-01

Pos logit contributions
 sailors+0.079
aro+0.077
 boat+0.075
 captains+0.075
 boats+0.074
Neg logit contributions
 blonde-0.069
 blush-0.059
 Her-0.057
 brist-0.057
oph-0.055
Token while
Token ID981
Feature activation-1.83e+00

Pos logit contributions
aro+0.048
 sailors+0.047
ug+0.046
ull+0.044
 whales+0.044
Neg logit contributions
 blonde-0.042
 blush-0.034
pron-0.034
 brushed-0.033
 Her-0.032
Token,
Token ID11
Feature activation+2.10e-01

Pos logit contributions
boat+0.064
boats+0.063
 captains+0.063
 sailors+0.063
aro+0.062
Neg logit contributions
 blonde-0.046
 Her-0.036
 blush-0.034
 brow-0.034
 brist-0.033
Token but
Token ID475
Feature activation-1.37e+00

Pos logit contributions
 blonde+0.005
 blush+0.004
 brist+0.004
 Her+0.003
 brow+0.003
Neg logit contributions
aro-0.008
 sailors-0.008
boat-0.008
boats-0.008
ug-0.008
Token then
Token ID788
Feature activation-6.17e-01

Pos logit contributions
 sailors+0.043
 captains+0.041
aro+0.040
boats+0.040
boat+0.040
Neg logit contributions
 blonde-0.039
 blush-0.033
 Her-0.033
 brist-0.032
 brow-0.031
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
boat+0.020
aro+0.020
boats+0.020
 sailors+0.020
ug+0.019
Neg logit contributions
 blonde-0.017
 blush-0.015
 Her-0.014
 brist-0.014
oph-0.013
Token truck
Token ID7779
Feature activation-5.74e+00

Pos logit contributions
aro+0.046
 sailors+0.044
ug+0.043
 boats+0.043
boats+0.042
Neg logit contributions
 blonde-0.041
 blush-0.035
 brist-0.034
pron-0.034
 makeup-0.032
Token passed
Token ID3804
Feature activation-2.29e+00

Pos logit contributions
aro+0.215
 sailors+0.212
 sharks+0.211
 whales+0.209
ug+0.203
Neg logit contributions
 blonde-0.093
 Her-0.084
 spat-0.083
 blush-0.082
 brushed-0.081
Token it
Token ID340
Feature activation-2.10e+00

Pos logit contributions
 sailors+0.076
aro+0.074
 boat+0.073
 captains+0.072
 boats+0.072
Neg logit contributions
 blonde-0.064
 blush-0.054
 brist-0.053
 Her-0.052
oph-0.052
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
 sailors+0.070
aro+0.067
 whales+0.065
 captains+0.065
 sharks+0.064
Neg logit contributions
 blonde-0.058
 blush-0.049
 Her-0.049
 brist-0.047
uct-0.045
Token The
Token ID383
Feature activation-2.66e+00

Pos logit contributions
 sailors+0.044
 boat+0.042
aro+0.042
 boats+0.042
 sharks+0.041
Neg logit contributions
 blonde-0.040
 blush-0.035
 brist-0.034
oph-0.033
 Her-0.033
Token car
Token ID1097
Feature activation-3.32e+00

Pos logit contributions
aro+0.080
ull+0.076
ug+0.075
 whales+0.072
boat+0.071
Neg logit contributions
 blonde-0.079
 makeup-0.066
pron-0.065
 blush-0.065
 brow-0.063
Token
Token ID198
Feature activation-5.47e-01

Pos logit contributions
 sailors+0.028
 boat+0.027
 captains+0.027
boats+0.026
 boats+0.026
Neg logit contributions
 blonde-0.017
 Her-0.015
 blush-0.014
 brist-0.014
oph-0.013
TokenSuddenly
Token ID38582
Feature activation-3.98e-01

Pos logit contributions
 sailors+0.019
 boat+0.018
 boats+0.018
 sharks+0.018
 whales+0.018
Neg logit contributions
 blonde-0.015
 Her-0.012
 blush-0.012
 brist-0.012
oph-0.012
Token,
Token ID11
Feature activation-4.10e-01

Pos logit contributions
 sailors+0.013
boat+0.012
aro+0.012
 captains+0.012
boats+0.012
Neg logit contributions
 blonde-0.012
 blush-0.011
 Her-0.010
 brist-0.010
 makeup-0.010
Token a
Token ID257
Feature activation-1.67e+00

Pos logit contributions
 sailors+0.013
aro+0.012
 boat+0.012
boat+0.012
ug+0.012
Neg logit contributions
 blonde-0.012
 blush-0.011
 brist-0.010
 Her-0.010
oph-0.010
Token big
Token ID1263
Feature activation-1.43e+00

Pos logit contributions
aro+0.049
 sailors+0.049
ug+0.046
 boats+0.046
 captains+0.046
Neg logit contributions
 blonde-0.054
 blush-0.046
 brist-0.045
pron-0.044
 makeup-0.042
Token truck
Token ID7779
Feature activation-5.71e+00

Pos logit contributions
aro+0.041
 sailors+0.040
 captains+0.039
boats+0.037
boat+0.037
Neg logit contributions
 blonde-0.046
 blush-0.042
 brist-0.041
 makeup-0.039
 lipstick-0.037
Token came
Token ID1625
Feature activation-2.66e+00

Pos logit contributions
 sailors+0.225
aro+0.220
ug+0.216
 sharks+0.215
 afloat+0.214
Neg logit contributions
 blonde-0.089
 blush-0.085
 Her-0.085
 spat-0.082
 She-0.077
Token out
Token ID503
Feature activation-2.03e+00

Pos logit contributions
aro+0.096
 sailors+0.093
boats+0.092
boat+0.092
 captains+0.091
Neg logit contributions
 blonde-0.059
 Her-0.053
 brow-0.050
 brist-0.049
 She-0.047
Token of
Token ID286
Feature activation-1.60e+00

Pos logit contributions
boat+0.063
boats+0.062
aro+0.062
 captains+0.061
 boat+0.060
Neg logit contributions
 blonde-0.052
 She-0.049
 Her-0.049
 brist-0.046
 her-0.046
Token nowhere
Token ID12062
Feature activation-1.02e+00

Pos logit contributions
 sailors+0.040
aro+0.038
 boat+0.038
 boats+0.037
 captains+0.037
Neg logit contributions
 blonde-0.058
 blush-0.051
 brist-0.050
 Her-0.049
oph-0.049
Token.
Token ID13
Feature activation-9.44e-01

Pos logit contributions
 sailors+0.036
 captains+0.035
aro+0.034
 boats+0.034
 boat+0.034
Neg logit contributions
 blonde-0.025
 blush-0.021
 Her-0.021
 brist-0.021
 makeup-0.021
Token
Token ID198
Feature activation+1.20e+00

Pos logit contributions
 blonde+0.063
pron+0.061
 wrapper+0.060
oph+0.059
 sweets+0.057
Neg logit contributions
 boats-0.056
 boat-0.055
ug-0.053
 sailors-0.053
 sail-0.052
Token
Token ID198
Feature activation+2.05e+00

Pos logit contributions
 blonde+0.040
 blush+0.034
 brist+0.033
oph+0.033
 fru+0.032
Neg logit contributions
 sailors-0.034
aro-0.034
 boat-0.033
 boats-0.032
ug-0.032
TokenSuddenly
Token ID38582
Feature activation+1.41e+00

Pos logit contributions
 blonde+0.060
 blush+0.051
oph+0.049
 brist+0.048
 fru+0.048
Neg logit contributions
 sailors-0.064
aro-0.064
 boat-0.063
ug-0.062
 boats-0.061
Token a
Token ID257
Feature activation-1.47e+00

Pos logit contributions
 blonde+0.053
 blush+0.047
oph+0.046
 brist+0.046
uct+0.046
Neg logit contributions
 sailors-0.033
 boat-0.032
 boats-0.031
aro-0.031
ug-0.030
Token big
Token ID1263
Feature activation-1.33e+00

Pos logit contributions
aro+0.048
 sailors+0.046
ug+0.045
boats+0.045
 boats+0.045
Neg logit contributions
 blonde-0.042
 blush-0.036
 brist-0.035
pron-0.034
 fru-0.033
Token boat
Token ID8848
Feature activation-5.70e+00

Pos logit contributions
aro+0.036
 captains+0.033
boats+0.033
ug+0.032
 sailors+0.032
Neg logit contributions
 blonde-0.044
 blush-0.040
 brist-0.039
 fru-0.037
 makeup-0.037
Token came
Token ID1625
Feature activation-1.85e+00

Pos logit contributions
 sailors+0.214
 sharks+0.212
ug+0.209
aro+0.208
 whales+0.203
Neg logit contributions
 blonde-0.075
 unw-0.073
 spat-0.073
 brow-0.069
 brushed-0.068
Token to
Token ID284
Feature activation+2.33e-01

Pos logit contributions
aro+0.061
 sailors+0.060
boats+0.059
 sharks+0.058
 boat+0.058
Neg logit contributions
 blonde-0.049
 Her-0.044
 brist-0.041
 blush-0.041
 brow-0.040
Token save
Token ID3613
Feature activation+9.17e-01

Pos logit contributions
 blonde+0.007
 blush+0.006
 brist+0.005
oph+0.005
 Her+0.005
Neg logit contributions
 sailors-0.008
 boat-0.007
aro-0.007
 boats-0.007
 sharks-0.007
Token her
Token ID607
Feature activation+2.68e-01

Pos logit contributions
 blonde+0.025
 blush+0.020
 brist+0.019
oph+0.019
pron+0.018
Neg logit contributions
 sailors-0.033
aro-0.032
 boats-0.032
 boat-0.031
 sharks-0.031
Token.
Token ID13
Feature activation+3.28e-01

Pos logit contributions
 blonde+0.007
 blush+0.006
 Her+0.006
 brist+0.006
 makeup+0.006
Neg logit contributions
aro-0.009
 sailors-0.008
boats-0.008
ug-0.008
boat-0.008
TokenJust
Token ID5703
Feature activation+6.37e-01

Pos logit contributions
 blonde+0.016
 blush+0.014
 brist+0.013
oph+0.013
 Her+0.013
Neg logit contributions
 sailors-0.016
 boat-0.015
aro-0.015
 boats-0.015
 captains-0.014
Token then
Token ID788
Feature activation+9.96e-02

Pos logit contributions
 blonde+0.018
 blush+0.015
 brist+0.015
oph+0.014
 Her+0.014
Neg logit contributions
 sailors-0.021
aro-0.021
 captains-0.020
boats-0.020
 boat-0.020
Token,
Token ID11
Feature activation-2.97e-01

Pos logit contributions
 blonde+0.003
 blush+0.003
 brist+0.003
 Her+0.003
oph+0.003
Neg logit contributions
 sailors-0.003
aro-0.003
 boat-0.003
boat-0.003
 boats-0.003
Token a
Token ID257
Feature activation-1.52e+00

Pos logit contributions
 sailors+0.009
 boat+0.008
aro+0.008
 boats+0.008
 sharks+0.008
Neg logit contributions
 blonde-0.010
 blush-0.008
 brist-0.008
oph-0.008
 Her-0.008
Token big
Token ID1263
Feature activation-1.71e+00

Pos logit contributions
aro+0.052
ug+0.049
 sailors+0.049
boats+0.048
 boats+0.048
Neg logit contributions
 blonde-0.042
 blush-0.035
 brist-0.034
pron-0.033
 makeup-0.032
Token boat
Token ID8848
Feature activation-5.67e+00

Pos logit contributions
aro+0.053
 captains+0.048
 sailors+0.048
boats+0.047
ug+0.047
Neg logit contributions
 blonde-0.050
 blush-0.045
 brist-0.043
 makeup-0.043
 fru-0.041
Token came
Token ID1625
Feature activation-2.24e+00

Pos logit contributions
 sailors+0.207
 sharks+0.207
aro+0.202
 whales+0.198
ug+0.195
Neg logit contributions
 spat-0.074
 blonde-0.074
 brushed-0.069
 wasn-0.068
 brow-0.067
Token by
Token ID416
Feature activation+2.99e-01

Pos logit contributions
aro+0.078
 sailors+0.076
 sharks+0.075
boats+0.074
 captains+0.074
Neg logit contributions
 blonde-0.052
 Her-0.046
 brow-0.045
 brist-0.042
 She-0.041
Token and
Token ID290
Feature activation-1.11e+00

Pos logit contributions
 blonde+0.009
 blush+0.008
 brist+0.008
 Her+0.007
oph+0.007
Neg logit contributions
 sailors-0.009
aro-0.009
 boat-0.009
 boats-0.009
 captains-0.009
Token saved
Token ID7448
Feature activation-2.59e-01

Pos logit contributions
 sailors+0.033
ug+0.031
aro+0.031
 captains+0.031
 boats+0.031
Neg logit contributions
 blonde-0.034
 blush-0.030
 brist-0.029
 Her-0.029
oph-0.028
Token the
Token ID262
Feature activation-2.10e+00

Pos logit contributions
 sailors+0.006
 boats+0.006
 boat+0.006
aro+0.006
 sharks+0.006
Neg logit contributions
 blonde-0.010
 blush-0.009
 brist-0.008
 Her-0.008
oph-0.008
Token two
Token ID734
Feature activation-1.83e+00

Pos logit contributions
aro+0.033
 sailors+0.033
boat+0.033
boats+0.033
 boat+0.032
Neg logit contributions
 blonde-0.038
 blush-0.032
 Her-0.032
oph-0.031
 brist-0.031
Token teams
Token ID3466
Feature activation-4.95e+00

Pos logit contributions
boat+0.057
aro+0.054
boats+0.052
 sailors+0.050
 afloat+0.049
Neg logit contributions
 blonde-0.062
 blush-0.050
 Her-0.050
 brist-0.049
 brow-0.048
Token.
Token ID13
Feature activation-3.24e+00

Pos logit contributions
aro+0.177
 sailors+0.168
 afloat+0.167
 sharks+0.166
boats+0.165
Neg logit contributions
 blonde-0.115
 Her-0.105
 blush-0.097
 makeup-0.093
 She-0.089
Token The
Token ID383
Feature activation-3.89e+00

Pos logit contributions
aro+0.124
 sailors+0.124
boat+0.122
 boat+0.121
ug+0.119
Neg logit contributions
 blonde-0.081
 Her-0.068
 blush-0.062
 blond-0.058
 She-0.057
Token two
Token ID734
Feature activation-4.56e+00

Pos logit contributions
aro+0.120
ug+0.102
ull+0.096
boat+0.092
aroo+0.090
Neg logit contributions
 blonde-0.129
 blush-0.115
 Her-0.111
 makeup-0.107
oph-0.107
Token teams
Token ID3466
Feature activation-5.66e+00

Pos logit contributions
aro+0.147
boat+0.130
 afloat+0.130
 explode+0.127
 ferry+0.125
Neg logit contributions
 blonde-0.131
 Her-0.112
 blush-0.110
oph-0.102
 makeup-0.102
Token wanted
Token ID2227
Feature activation-3.05e+00

Pos logit contributions
aro+0.225
 sailors+0.213
 sharks+0.211
ug+0.209
 whales+0.207
Neg logit contributions
 blonde-0.107
 blush-0.095
 Her-0.092
 brushed-0.081
 makeup-0.081
Token to
Token ID284
Feature activation-3.51e+00

Pos logit contributions
aro+0.146
ug+0.140
boat+0.140
 sailors+0.136
 afloat+0.133
Neg logit contributions
 blonde-0.035
 Her-0.024
 makeup-0.023
 blush-0.021
 brushed-0.018
Token have
Token ID423
Feature activation-3.30e+00

Pos logit contributions
aro+0.118
ug+0.113
 sailors+0.113
boats+0.110
 sharks+0.109
Neg logit contributions
 blonde-0.086
 blush-0.082
 Her-0.082
 unw-0.073
 makeup-0.071
Token a
Token ID257
Feature activation-3.27e+00

Pos logit contributions
aro+0.121
boat+0.119
ug+0.117
boats+0.112
 sailors+0.111
Neg logit contributions
 blonde-0.082
 makeup-0.065
 blush-0.063
 blond-0.060
 Her-0.058
Token bouncing
Token ID30713
Feature activation-1.91e+00

Pos logit contributions
aro+0.088
ug+0.083
 sailors+0.083
ull+0.077
boat+0.076
Neg logit contributions
 blonde-0.112
pron-0.102
 blush-0.100
 makeup-0.098
 Her-0.094
Token sad
Token ID6507
Feature activation-1.28e+00

Pos logit contributions
 sailors+0.043
aro+0.042
 boat+0.041
 boats+0.041
boat+0.041
Neg logit contributions
 blonde-0.045
 blush-0.039
 brist-0.038
 Her-0.037
oph-0.036
Token.
Token ID13
Feature activation-2.50e+00

Pos logit contributions
 sailors+0.039
aro+0.039
boat+0.038
 captains+0.037
 boat+0.037
Neg logit contributions
 blonde-0.038
 blush-0.034
 brist-0.033
 Her-0.033
 makeup-0.031
Token
Token ID198
Feature activation-1.83e+00

Pos logit contributions
 sailors+0.077
boat+0.075
aro+0.074
 boat+0.074
boats+0.073
Neg logit contributions
 blonde-0.077
 Her-0.069
 blush-0.064
 brist-0.064
 She-0.062
Token
Token ID198
Feature activation-1.94e+00

Pos logit contributions
 sailors+0.079
boats+0.078
 captains+0.078
boat+0.078
 boat+0.076
Neg logit contributions
 Her-0.030
 blonde-0.028
 She-0.023
 brist-0.023
 blush-0.022
TokenA
Token ID32
Feature activation-1.76e+00

Pos logit contributions
 sharks+0.079
 sailors+0.078
 ship+0.077
boats+0.077
 boat+0.077
Neg logit contributions
Just-0.030
 blonde-0.030
Her-0.028
 Her-0.028
 brist-0.028
Token cop
Token ID2243
Feature activation-5.59e+00

Pos logit contributions
 sailors+0.057
aro+0.056
 boats+0.054
 sharks+0.053
ug+0.053
Neg logit contributions
 blonde-0.050
 blush-0.044
 brist-0.042
pron-0.042
oph-0.040
Token sees
Token ID7224
Feature activation-3.05e+00

Pos logit contributions
ug+0.192
 sailors+0.191
boat+0.189
aro+0.189
ull+0.184
Neg logit contributions
 blonde-0.136
 blush-0.129
 Her-0.123
 makeup-0.112
 unw-0.109
Token them
Token ID606
Feature activation-1.02e+00

Pos logit contributions
boat+0.105
 afloat+0.101
 captains+0.096
 sailors+0.096
boats+0.095
Neg logit contributions
 blonde-0.077
 blush-0.073
 makeup-0.073
 Her-0.073
 her-0.070
Token.
Token ID13
Feature activation-2.76e+00

Pos logit contributions
 sailors+0.035
aro+0.034
boat+0.033
 captains+0.033
ug+0.032
Neg logit contributions
 blonde-0.027
 blush-0.025
 Her-0.024
 brist-0.023
 makeup-0.022
Token He
Token ID679
Feature activation-1.16e+00

Pos logit contributions
 sailors+0.104
 captains+0.099
aro+0.099
 boat+0.098
 boats+0.098
Neg logit contributions
 blonde-0.068
 Her-0.059
 blush-0.055
 brist-0.053
 She-0.052
Token is
Token ID318
Feature activation-1.89e+00

Pos logit contributions
 sailors+0.036
 boat+0.034
aro+0.034
 boats+0.034
 sharks+0.034
Neg logit contributions
 blonde-0.036
 blush-0.031
 brist-0.030
oph-0.030
 Her-0.029
Token castle
Token ID16669
Feature activation+1.35e-01

Pos logit contributions
 blonde+0.017
 blush+0.015
 brist+0.014
oph+0.014
 Her+0.014
Neg logit contributions
 sailors-0.015
 boat-0.015
aro-0.014
 boats-0.014
 sharks-0.014
Token.
Token ID13
Feature activation-4.42e-01

Pos logit contributions
 blonde+0.004
 blush+0.004
 brist+0.004
oph+0.004
 Her+0.004
Neg logit contributions
 sailors-0.004
 boat-0.004
aro-0.004
 boats-0.004
 sharks-0.004
Token Suddenly
Token ID24975
Feature activation-3.69e-01

Pos logit contributions
 sailors+0.016
aro+0.015
 boat+0.015
 boats+0.015
 sharks+0.015
Neg logit contributions
 blonde-0.011
 blush-0.010
 brist-0.009
oph-0.009
pron-0.008
Token a
Token ID257
Feature activation-1.11e+00

Pos logit contributions
 sailors+0.011
aro+0.010
boat+0.010
 captains+0.010
 boat+0.010
Neg logit contributions
 blonde-0.012
 blush-0.010
 brist-0.010
 Her-0.010
oph-0.010
Token big
Token ID1263
Feature activation-1.17e+00

Pos logit contributions
 sailors+0.032
aro+0.031
 boats+0.030
ug+0.030
 captains+0.029
Neg logit contributions
 blonde-0.037
 blush-0.032
 brist-0.031
oph-0.030
pron-0.030
Token truck
Token ID7779
Feature activation-5.56e+00

Pos logit contributions
 sailors+0.032
aro+0.032
 captains+0.031
ug+0.030
 boats+0.030
Neg logit contributions
 blonde-0.039
 blush-0.035
 brist-0.034
 makeup-0.032
pron-0.032
Token drove
Token ID10357
Feature activation-2.34e+00

Pos logit contributions
 sailors+0.202
aro+0.197
ug+0.193
 sharks+0.192
 captains+0.190
Neg logit contributions
 blonde-0.109
 blush-0.105
 Her-0.100
 spat-0.095
 unw-0.095
Token up
Token ID510
Feature activation-1.77e+00

Pos logit contributions
 sailors+0.076
aro+0.073
 boat+0.072
 boats+0.071
 sharks+0.071
Neg logit contributions
 blonde-0.068
 blush-0.058
 brist-0.056
 Her-0.055
oph-0.055
Token and
Token ID290
Feature activation-9.31e-01

Pos logit contributions
 sailors+0.060
aro+0.058
 boat+0.057
 captains+0.057
 boats+0.056
Neg logit contributions
 blonde-0.049
 blush-0.041
 brist-0.040
 Her-0.039
oph-0.039
Token stopped
Token ID5025
Feature activation-1.48e+00

Pos logit contributions
 sailors+0.029
aro+0.028
 boat+0.028
 boats+0.027
 sharks+0.027
Neg logit contributions
 blonde-0.028
 blush-0.024
 brist-0.023
oph-0.023
 Her-0.023
Token in
Token ID287
Feature activation-3.89e-01

Pos logit contributions
boat+0.048
aro+0.047
boats+0.046
 sailors+0.046
 captains+0.046
Neg logit contributions
 blonde-0.040
 Her-0.033
 blush-0.033
 brist-0.032
 makeup-0.032
Token.
Token ID13
Feature activation-1.79e+00

Pos logit contributions
 blonde+0.002
 blush+0.002
 Her+0.002
 makeup+0.002
oph+0.002
Neg logit contributions
aro-0.003
 sailors-0.003
 captains-0.003
 whales-0.003
 sharks-0.003
Token Suddenly
Token ID24975
Feature activation-1.87e+00

Pos logit contributions
 sailors+0.056
 boat+0.053
 boats+0.052
aro+0.052
 sharks+0.052
Neg logit contributions
 blonde-0.055
 blush-0.048
 brist-0.047
oph-0.045
 Her-0.044
Token,
Token ID11
Feature activation-1.89e+00

Pos logit contributions
boat+0.071
aro+0.071
boats+0.070
 sailors+0.068
amer+0.068
Neg logit contributions
 blonde-0.039
 Her-0.031
 blush-0.028
 brist-0.027
 brow-0.027
Token a
Token ID257
Feature activation-1.21e+00

Pos logit contributions
ug+0.063
ile+0.062
aro+0.062
boats+0.059
boat+0.058
Neg logit contributions
 blonde-0.045
 her-0.041
 blush-0.040
 Her-0.038
 brow-0.037
Token big
Token ID1263
Feature activation-1.28e+00

Pos logit contributions
aro+0.037
 sailors+0.036
ug+0.035
 boats+0.034
boats+0.034
Neg logit contributions
 blonde-0.038
 blush-0.032
 brist-0.031
pron-0.031
 fru-0.029
Token truck
Token ID7779
Feature activation-5.52e+00

Pos logit contributions
aro+0.038
 sailors+0.035
 captains+0.034
boats+0.033
ug+0.033
Neg logit contributions
 blonde-0.043
 blush-0.037
 brist-0.037
 makeup-0.035
 fru-0.034
Token drove
Token ID10357
Feature activation-2.78e+00

Pos logit contributions
 sailors+0.196
aro+0.195
 sharks+0.191
 whales+0.190
 captains+0.186
Neg logit contributions
 blonde-0.113
 blush-0.101
 unw-0.098
 brushed-0.095
 spat-0.094
Token by
Token ID416
Feature activation-6.77e-01

Pos logit contributions
 sailors+0.096
aro+0.096
 whales+0.092
 sharks+0.092
 captains+0.091
Neg logit contributions
 blonde-0.069
 blush-0.056
 brow-0.055
 brist-0.055
 Her-0.055
Token with
Token ID351
Feature activation-3.31e+00

Pos logit contributions
 sailors+0.024
 captains+0.024
aro+0.024
boats+0.024
boat+0.023
Neg logit contributions
 blonde-0.016
 brist-0.013
 brow-0.012
 blush-0.012
 Her-0.012
Token its
Token ID663
Feature activation-1.43e+00

Pos logit contributions
aro+0.113
boat+0.109
ug+0.108
 sailors+0.108
 captains+0.105
Neg logit contributions
 blonde-0.093
 blush-0.072
 brist-0.070
 Her-0.070
 brow-0.069
Token horn
Token ID12718
Feature activation-3.05e+00

Pos logit contributions
aro+0.046
ug+0.044
boat+0.044
 sailors+0.043
boats+0.042
Neg logit contributions
 blonde-0.042
 Her-0.034
 brow-0.034
 brist-0.033
 blush-0.033
Token!"
Token ID2474
Feature activation-3.79e-01

Pos logit contributions
 sailors+0.005
boat+0.005
 boats+0.005
 whales+0.005
 sharks+0.005
Neg logit contributions
 blonde-0.005
 Her-0.004
 blush-0.004
 brist-0.004
 makeup-0.004
Token
Token ID198
Feature activation-3.61e-01

Pos logit contributions
 sailors+0.013
aro+0.012
 boat+0.012
 boats+0.012
 captains+0.012
Neg logit contributions
 blonde-0.010
 blush-0.009
 brist-0.009
 Her-0.009
oph-0.008
Token
Token ID198
Feature activation+9.20e-02

Pos logit contributions
 sailors+0.014
 captains+0.014
boats+0.013
 boats+0.013
 boat+0.013
Neg logit contributions
 blonde-0.008
 Her-0.007
 brist-0.006
oph-0.006
 blush-0.006
TokenSo
Token ID2396
Feature activation-1.10e+00

Pos logit contributions
 blonde+0.003
 brist+0.002
 Her+0.002
oph+0.002
 blush+0.002
Neg logit contributions
 sailors-0.003
aro-0.003
 boats-0.003
 boat-0.003
boats-0.003
Token the
Token ID262
Feature activation-2.74e+00

Pos logit contributions
 sailors+0.034
 captains+0.033
boats+0.033
boat+0.032
aro+0.032
Neg logit contributions
 blonde-0.032
 Her-0.027
 brist-0.026
 blush-0.026
 brow-0.025
Token ships
Token ID7937
Feature activation-5.52e+00

Pos logit contributions
ug+0.095
aro+0.095
boat+0.088
boats+0.087
ites+0.087
Neg logit contributions
 blonde-0.060
 Tooth-0.048
 me-0.048
 makeup-0.047
 brist-0.045
Token started
Token ID2067
Feature activation-2.49e+00

Pos logit contributions
 sharks+0.154
aro+0.148
 polar+0.144
 whales+0.141
 sailors+0.140
Neg logit contributions
 brushed-0.128
 blonde-0.117
 chose-0.116
 unw-0.111
 blush-0.111
Token their
Token ID511
Feature activation-2.39e+00

Pos logit contributions
boat+0.103
aro+0.102
ile+0.102
 sailors+0.101
boats+0.100
Neg logit contributions
 blonde-0.039
 Her-0.030
 blush-0.025
 brushed-0.024
 brist-0.024
Token race
Token ID3234
Feature activation-3.38e+00

Pos logit contributions
ull+0.061
aro+0.061
ile+0.054
boat+0.053
 sailors+0.052
Neg logit contributions
 blonde-0.080
 brow-0.070
 unw-0.066
 Her-0.064
 blond-0.063
Token.
Token ID13
Feature activation-8.53e-01

Pos logit contributions
aro+0.127
 whales+0.122
 sharks+0.118
ull+0.116
 polar+0.116
Neg logit contributions
 blonde-0.064
 Her-0.052
 brow-0.051
 unw-0.048
 She-0.048
Token Little
Token ID7703
Feature activation-8.73e-01

Pos logit contributions
 sailors+0.027
aro+0.026
boat+0.026
 boat+0.026
boats+0.026
Neg logit contributions
 blonde-0.026
 Her-0.022
 blush-0.021
 brist-0.021
oph-0.020
Token now
Token ID783
Feature activation-4.59e-01

Pos logit contributions
 sailors+0.043
aro+0.041
 captains+0.041
ug+0.041
boat+0.040
Neg logit contributions
 blonde-0.029
 Her-0.024
 blush-0.024
 makeup-0.023
 brist-0.023
Token."
Token ID526
Feature activation-1.58e+00

Pos logit contributions
 sailors+0.013
aro+0.012
 boat+0.012
 boats+0.012
 sharks+0.012
Neg logit contributions
 blonde-0.016
 blush-0.014
 brist-0.013
 Her-0.013
oph-0.013
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
 sailors+0.050
 boat+0.048
aro+0.048
 boats+0.047
 sharks+0.047
Neg logit contributions
 blonde-0.047
 blush-0.041
 brist-0.040
oph-0.039
 Her-0.037
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
 sailors+0.052
 captains+0.051
 boats+0.050
boats+0.050
 boat+0.050
Neg logit contributions
 blonde-0.029
 Her-0.026
 blush-0.024
 brist-0.023
oph-0.022
TokenThe
Token ID464
Feature activation-3.03e+00

Pos logit contributions
 sailors+0.059
 boats+0.059
 boat+0.057
 whales+0.057
 sharks+0.057
Neg logit contributions
 blonde-0.037
 Her-0.032
 blush-0.030
 brist-0.030
 She-0.028
Token zo
Token ID40565
Feature activation-5.51e+00

Pos logit contributions
ug+0.088
boat+0.084
 afloat+0.083
aro+0.082
boats+0.081
Neg logit contributions
 blonde-0.083
 makeup-0.078
 fru-0.077
 blush-0.076
 brist-0.076
Tokenoke
Token ID2088
Feature activation-2.65e+00

Pos logit contributions
 afloat+0.193
 raft+0.185
 sail+0.171
 dock+0.168
 sailors+0.167
Neg logit contributions
 Her-0.116
 blush-0.112
 blonde-0.108
 She-0.105
omm-0.099
Tokeneper
Token ID5723
Feature activation-2.66e+00

Pos logit contributions
 afloat+0.057
 sail+0.053
 boats+0.052
 raft+0.052
 dock+0.052
Neg logit contributions
 blonde-0.086
 Her-0.085
 brist-0.084
omm-0.083
 brow-0.083
Token catches
Token ID17591
Feature activation-1.77e+00

Pos logit contributions
 sailors+0.095
aro+0.092
boat+0.091
boats+0.090
ug+0.090
Neg logit contributions
 blonde-0.064
 blush-0.059
 Her-0.055
 brist-0.054
oph-0.052
Token the
Token ID262
Feature activation-2.57e+00

Pos logit contributions
 sailors+0.054
boat+0.053
aro+0.052
 captains+0.052
ug+0.050
Neg logit contributions
 blonde-0.050
 blush-0.045
 Her-0.043
 brist-0.043
oph-0.043
Token crocod
Token ID37565
Feature activation-3.42e+00

Pos logit contributions
ug+0.052
aro+0.049
boat+0.045
 sailors+0.044
boats+0.042
Neg logit contributions
 blonde-0.091
 fru-0.088
 spat-0.086
 makeup-0.085
 brist-0.085
Token,
Token ID11
Feature activation-1.59e+00

Pos logit contributions
 sailors+0.115
 whales+0.112
aro+0.109
ull+0.107
 sharks+0.107
Neg logit contributions
 blonde-0.059
 Her-0.055
 She-0.052
 blush-0.045
oph-0.043
Token Spot
Token ID15899
Feature activation-1.45e+00

Pos logit contributions
 sailors+0.048
 captains+0.045
aro+0.044
boat+0.044
ug+0.044
Neg logit contributions
 blonde-0.050
 Her-0.042
 blush-0.042
 brow-0.040
 brist-0.040
Token and
Token ID290
Feature activation-1.27e+00

Pos logit contributions
 sailors+0.055
aro+0.054
boats+0.052
boat+0.052
 sharks+0.051
Neg logit contributions
 blonde-0.033
 blush-0.026
 Her-0.026
 brist-0.026
oph-0.025
Token the
Token ID262
Feature activation-2.68e+00

Pos logit contributions
 sailors+0.034
aro+0.032
 boat+0.031
 captains+0.031
 boats+0.031
Neg logit contributions
 blonde-0.044
 blush-0.039
 Her-0.038
 brist-0.038
oph-0.037
Token other
Token ID584
Feature activation-3.41e+00

Pos logit contributions
aro+0.074
ug+0.070
 sailors+0.069
 whales+0.067
ull+0.067
Neg logit contributions
 blonde-0.085
 brist-0.073
 blush-0.071
 brow-0.069
 Her-0.068
Token dogs
Token ID6844
Feature activation-5.50e+00

Pos logit contributions
aro+0.108
ull+0.100
 afloat+0.098
boat+0.096
 sailors+0.095
Neg logit contributions
 blonde-0.084
 She-0.073
 Her-0.068
 me-0.067
 curls-0.067
Token ran
Token ID4966
Feature activation-2.39e+00

Pos logit contributions
 sailors+0.210
 sharks+0.205
ull+0.204
aro+0.203
 whales+0.203
Neg logit contributions
 blonde-0.100
 blush-0.092
 brushed-0.087
 Her-0.087
 brow-0.077
Token very
Token ID845
Feature activation-2.11e+00

Pos logit contributions
 sailors+0.087
 whales+0.086
aro+0.086
ull+0.084
 whale+0.081
Neg logit contributions
 blonde-0.053
 brow-0.043
 blush-0.043
 Her-0.043
 She-0.041
Token fast
Token ID3049
Feature activation-2.64e+00

Pos logit contributions
 whales+0.074
ull+0.073
 sailors+0.073
 crew+0.069
boat+0.069
Neg logit contributions
 blonde-0.041
 brow-0.040
 wrink-0.037
 unw-0.034
 brushed-0.034
Token.
Token ID13
Feature activation-1.83e+00

Pos logit contributions
 sailors+0.085
aro+0.084
boat+0.082
 boat+0.081
 captains+0.080
Neg logit contributions
 blonde-0.072
 blush-0.061
 brist-0.059
 Her-0.058
 makeup-0.056
Token They
Token ID1119
Feature activation-2.46e+00

Pos logit contributions
 sailors+0.052
 boat+0.049
aro+0.049
 boats+0.049
 sharks+0.048
Neg logit contributions
 blonde-0.061
 blush-0.053
 brist-0.052
 Her-0.051
oph-0.051
Token cookie
Token ID19751
Feature activation-1.17e+00

Pos logit contributions
 sailors+0.018
aro+0.017
ug+0.017
 captains+0.017
 boats+0.017
Neg logit contributions
 blonde-0.013
 blush-0.011
 brist-0.010
 Her-0.010
oph-0.010
Token.
Token ID13
Feature activation-1.69e+00

Pos logit contributions
 sailors+0.036
aro+0.034
 captains+0.034
 whales+0.033
ug+0.033
Neg logit contributions
 blonde-0.035
 blush-0.031
 brist-0.030
 Her-0.029
oph-0.029
Token
Token ID198
Feature activation-1.65e+00

Pos logit contributions
 sailors+0.049
aro+0.046
 boat+0.046
 sharks+0.046
 boats+0.046
Neg logit contributions
 blonde-0.054
 blush-0.048
oph-0.047
 brist-0.047
pron-0.044
Token
Token ID198
Feature activation-1.69e+00

Pos logit contributions
 sailors+0.065
 captains+0.064
boats+0.063
 boat+0.062
 boats+0.062
Neg logit contributions
 Her-0.032
 blonde-0.032
 brist-0.027
 She-0.027
 blush-0.027
TokenThe
Token ID464
Feature activation-3.08e+00

Pos logit contributions
 sailors+0.066
 boats+0.066
 boat+0.063
 whales+0.063
 captains+0.062
Neg logit contributions
 blonde-0.033
 Her-0.031
Just-0.030
Fe-0.028
uct-0.028
Token zo
Token ID40565
Feature activation-5.49e+00

Pos logit contributions
ug+0.085
aro+0.084
boat+0.071
boats+0.068
 sailors+0.063
Neg logit contributions
pron-0.094
 blonde-0.094
 fru-0.090
 spat-0.089
 brist-0.088
Tokenoke
Token ID2088
Feature activation-3.31e+00

Pos logit contributions
 afloat+0.198
 raft+0.193
 dock+0.171
 sail+0.171
 boats+0.167
Neg logit contributions
 blush-0.095
 Her-0.095
 spat-0.095
 blonde-0.093
cake-0.093
Tokeneper
Token ID5723
Feature activation-2.69e+00

Pos logit contributions
 afloat+0.079
 raft+0.074
 sail+0.071
 dock+0.071
 port+0.070
Neg logit contributions
 brow-0.092
 spat-0.091
 blonde-0.090
omm-0.089
 wrapper-0.087
Token saw
Token ID2497
Feature activation-2.53e+00

Pos logit contributions
 sailors+0.105
aro+0.104
boats+0.102
boat+0.101
 sharks+0.101
Neg logit contributions
 blonde-0.052
 blush-0.047
 brushed-0.044
 Her-0.042
 spat-0.042
Token what
Token ID644
Feature activation-2.44e+00

Pos logit contributions
boat+0.085
 sailors+0.085
 afloat+0.083
ug+0.083
 captains+0.083
Neg logit contributions
 blonde-0.059
 blush-0.056
 Her-0.055
 makeup-0.054
 her-0.053
Token Tom
Token ID4186
Feature activation-1.38e-02

Pos logit contributions
 sailors+0.098
aro+0.095
 captains+0.095
ug+0.094
 boat+0.094
Neg logit contributions
 blonde-0.049
 Her-0.040
 blush-0.039
oph-0.037
 brushed-0.037
Token
Token ID198
Feature activation-3.89e-01

Pos logit contributions
 sailors+0.031
 boat+0.030
 captains+0.030
 boats+0.030
boats+0.029
Neg logit contributions
 blonde-0.020
 Her-0.017
 blush-0.017
 brist-0.016
oph-0.016
TokenSuddenly
Token ID38582
Feature activation-9.84e-01

Pos logit contributions
 sailors+0.014
 boat+0.013
 boats+0.013
 sharks+0.013
aro+0.013
Neg logit contributions
 blonde-0.010
 blush-0.008
 brist-0.008
 Her-0.008
oph-0.008
Token,
Token ID11
Feature activation-1.23e+00

Pos logit contributions
 sailors+0.035
boat+0.034
boats+0.034
 captains+0.034
aro+0.032
Neg logit contributions
 blonde-0.026
 Her-0.021
 blush-0.021
 brist-0.021
 makeup-0.019
Token a
Token ID257
Feature activation-1.21e+00

Pos logit contributions
 sailors+0.039
boat+0.039
boats+0.038
 captains+0.038
aro+0.037
Neg logit contributions
 blonde-0.036
 blush-0.031
 brist-0.029
 Her-0.029
 makeup-0.028
Token big
Token ID1263
Feature activation-1.35e+00

Pos logit contributions
aro+0.040
 sailors+0.037
boats+0.037
ug+0.037
boat+0.036
Neg logit contributions
 blonde-0.035
pron-0.029
 blush-0.028
 brist-0.028
 fru-0.027
Token boat
Token ID8848
Feature activation-5.48e+00

Pos logit contributions
aro+0.039
 captains+0.036
boats+0.036
 sailors+0.036
ug+0.035
Neg logit contributions
 blonde-0.042
 blush-0.037
 brist-0.036
 makeup-0.035
 fru-0.035
Token appeared
Token ID4120
Feature activation-1.57e+00

Pos logit contributions
 sailors+0.235
 sharks+0.229
ug+0.223
 captains+0.222
aro+0.222
Neg logit contributions
 blonde-0.051
 spat-0.046
 Her-0.044
 brushed-0.043
 unw-0.040
Token.
Token ID13
Feature activation-1.69e+00

Pos logit contributions
 sailors+0.052
aro+0.052
 boat+0.050
 captains+0.050
 boats+0.049
Neg logit contributions
 blonde-0.042
 blush-0.036
 brist-0.036
 Her-0.035
oph-0.034
Token It
Token ID632
Feature activation-1.99e+00

Pos logit contributions
 sailors+0.060
aro+0.058
 boat+0.057
boat+0.057
 captains+0.057
Neg logit contributions
 blonde-0.045
 blush-0.036
 brist-0.036
 Her-0.036
oph-0.034
Token was
Token ID373
Feature activation-1.41e+00

Pos logit contributions
 sailors+0.083
aro+0.082
ug+0.082
 captains+0.079
boats+0.079
Neg logit contributions
 blonde-0.032
 brushed-0.025
oph-0.023
uct-0.023
 fru-0.023
Token a
Token ID257
Feature activation-1.36e+00

Pos logit contributions
aro+0.045
 sailors+0.045
boat+0.044
ug+0.043
boats+0.043
Neg logit contributions
 blonde-0.041
 brist-0.033
 blush-0.033
 Her-0.032
 brow-0.031
Token had
Token ID550
Feature activation-2.77e+00

Pos logit contributions
 sailors+0.145
aro+0.138
 captains+0.136
ug+0.136
 boats+0.135
Neg logit contributions
 blonde-0.074
 blush-0.059
 Her-0.055
 brist-0.055
 brushed-0.053
Token killed
Token ID2923
Feature activation-1.84e+00

Pos logit contributions
 sailors+0.086
aro+0.083
 boat+0.082
boat+0.081
 boats+0.081
Neg logit contributions
 blonde-0.085
 blush-0.072
 brist-0.070
 Her-0.069
oph-0.067
Token them
Token ID606
Feature activation-7.87e-01

Pos logit contributions
 sailors+0.052
 captains+0.050
aro+0.049
 boat+0.048
boat+0.048
Neg logit contributions
 blonde-0.059
 blush-0.050
 brist-0.049
 Her-0.049
oph-0.048
Token.
Token ID13
Feature activation-2.43e+00

Pos logit contributions
 sailors+0.027
aro+0.026
boat+0.025
 captains+0.025
 whales+0.025
Neg logit contributions
 blonde-0.020
 Her-0.017
 blush-0.017
 brist-0.016
 makeup-0.016
Token The
Token ID383
Feature activation-3.26e+00

Pos logit contributions
 sailors+0.081
 boat+0.078
aro+0.078
 boats+0.077
boat+0.077
Neg logit contributions
 blonde-0.068
 blush-0.057
 Her-0.057
 brist-0.055
oph-0.054
Token zo
Token ID40565
Feature activation-5.45e+00

Pos logit contributions
ug+0.089
aro+0.085
boat+0.082
 sailors+0.078
boats+0.078
Neg logit contributions
 blonde-0.104
 blush-0.091
 brist-0.090
 brow-0.088
 makeup-0.087
Tokenoke
Token ID2088
Feature activation-3.46e+00

Pos logit contributions
 afloat+0.185
 raft+0.180
 sail+0.165
 dock+0.161
 boats+0.160
Neg logit contributions
 blonde-0.119
 Her-0.109
 blush-0.106
anna-0.103
 spat-0.101
Tokenep
Token ID538
Feature activation-2.07e+00

Pos logit contributions
 afloat+0.084
 raft+0.078
 sail+0.078
 port+0.077
 dock+0.075
Neg logit contributions
 blonde-0.097
 brow-0.094
 refused-0.092
 Her-0.090
 spat-0.090
Tokeners
Token ID364
Feature activation-1.99e+00

Pos logit contributions
 sailors+0.080
aro+0.077
 boats+0.076
 sharks+0.076
 boat+0.076
Neg logit contributions
 blonde-0.042
 blush-0.034
 brist-0.034
 Her-0.033
oph-0.033
Token shot
Token ID2823
Feature activation-2.34e+00

Pos logit contributions
 sailors+0.071
aro+0.068
 boat+0.067
 boats+0.067
 sharks+0.066
Neg logit contributions
 blonde-0.051
 blush-0.043
 brist-0.041
 Her-0.040
oph-0.040
Token the
Token ID262
Feature activation-1.44e+00

Pos logit contributions
 sailors+0.067
aro+0.065
boat+0.064
 boat+0.064
 captains+0.064
Neg logit contributions
 blonde-0.073
 blush-0.063
 brist-0.062
 Her-0.061
oph-0.059
Token you
Token ID345
Feature activation-2.03e-01

Pos logit contributions
boat+0.072
 sailors+0.071
ull+0.070
 afloat+0.069
boats+0.068
Neg logit contributions
 blonde-0.049
 Her-0.041
 makeup-0.040
 blush-0.040
 brist-0.037
Token doing
Token ID1804
Feature activation-6.01e-01

Pos logit contributions
 sailors+0.007
aro+0.007
 boat+0.007
boat+0.007
 boats+0.007
Neg logit contributions
 blonde-0.005
 blush-0.004
 brist-0.004
 Her-0.004
oph-0.004
Token here
Token ID994
Feature activation-7.20e-01

Pos logit contributions
 sailors+0.019
aro+0.019
boat+0.018
 captains+0.018
 boats+0.018
Neg logit contributions
 blonde-0.017
 blush-0.015
 makeup-0.014
 brist-0.014
oph-0.014
Token?"
Token ID1701
Feature activation-7.33e-01

Pos logit contributions
 sailors+0.021
aro+0.020
 boat+0.019
 boats+0.019
 captains+0.019
Neg logit contributions
 blonde-0.023
 blush-0.021
 brist-0.020
oph-0.020
 Her-0.020
Token the
Token ID262
Feature activation-3.43e+00

Pos logit contributions
 sailors+0.021
aro+0.020
 boat+0.020
 boats+0.020
boat+0.020
Neg logit contributions
 blonde-0.024
 blush-0.021
 brist-0.021
 Her-0.020
oph-0.020
Token zo
Token ID40565
Feature activation-5.44e+00

Pos logit contributions
ug+0.099
 afloat+0.095
boats+0.092
boat+0.092
aro+0.091
Neg logit contributions
 blonde-0.101
 Her-0.092
 blush-0.091
 brist-0.087
 makeup-0.085
Tokenoke
Token ID2088
Feature activation-3.58e+00

Pos logit contributions
 raft+0.193
 afloat+0.192
 sail+0.181
 boats+0.180
 sailors+0.180
Neg logit contributions
 Her-0.107
 blush-0.106
 spat-0.098
 blonde-0.097
 She-0.097
Tokeneper
Token ID5723
Feature activation-2.26e+00

Pos logit contributions
 port+0.083
 afloat+0.082
 sail+0.081
 raft+0.080
 flood+0.079
Neg logit contributions
 Her-0.104
 brow-0.102
omm-0.100
 her-0.098
 blush-0.098
Token asked
Token ID1965
Feature activation-7.50e-01

Pos logit contributions
 sailors+0.087
aro+0.084
 boat+0.084
 boats+0.083
 sharks+0.083
Neg logit contributions
 blonde-0.050
 blush-0.042
 Her-0.040
 brist-0.039
oph-0.037
Token.
Token ID13
Feature activation-9.79e-01

Pos logit contributions
 sailors+0.022
aro+0.021
 boat+0.021
boat+0.021
 captains+0.021
Neg logit contributions
 blonde-0.024
 blush-0.021
 Her-0.020
 brist-0.020
oph-0.019
Token "
Token ID366
Feature activation-3.95e-01

Pos logit contributions
 sailors+0.033
 boat+0.032
 boats+0.031
aro+0.030
 sharks+0.030
Neg logit contributions
 blonde-0.028
 blush-0.024
oph-0.023
 brist-0.023
uct-0.022
Token
Token ID220
Feature activation+1.98e+00

Pos logit contributions
 blonde+0.062
 blush+0.062
 brist+0.059
 fru+0.058
pron+0.057
Neg logit contributions
 boat-0.030
 Fin-0.029
 sail-0.028
 raft-0.028
 boats-0.028
Token
Token ID198
Feature activation+1.04e+00

Pos logit contributions
 blonde+0.071
 blush+0.064
 brist+0.063
oph+0.061
 fru+0.059
Neg logit contributions
 sailors-0.048
aro-0.047
ug-0.047
 boats-0.046
 boat-0.046
Token
Token ID198
Feature activation+1.75e+00

Pos logit contributions
 blonde+0.033
 blush+0.030
 brist+0.029
oph+0.027
 fru+0.027
Neg logit contributions
 sailors-0.030
aro-0.029
 boat-0.029
 boats-0.029
boat-0.028
Tokenâ
Token ID22940
Feature activation+2.24e+00

Pos logit contributions
 blonde+0.052
 blush+0.047
 brist+0.045
 fru+0.044
oph+0.042
Neg logit contributions
 sailors-0.052
 boat-0.051
aro-0.050
boat-0.049
 boats-0.049
Token€
Token ID26391
Feature activation+1.92e+00

Pos logit contributions
 blonde+0.061
 blush+0.051
 brist+0.048
oph+0.046
 makeup+0.045
Neg logit contributions
boat-0.074
 sailors-0.073
ug-0.072
aro-0.071
 boat-0.071
Token�
Token ID129
Feature activation+3.47e+00

Pos logit contributions
 blonde+0.053
 blush+0.047
 brist+0.045
oph+0.042
 Her+0.041
Neg logit contributions
 sailors-0.061
 boat-0.060
 boats-0.059
aro-0.059
ug-0.058
Token�
Token ID241
Feature activation+1.98e+00

Pos logit contributions
 blonde+0.097
 blush+0.086
 brist+0.079
oph+0.078
 fru+0.076
Neg logit contributions
 sailors-0.112
 boat-0.111
 boats-0.111
aro-0.109
ug-0.107
TokenLet
Token ID5756
Feature activation+2.29e+00

Pos logit contributions
 blonde+0.052
 blush+0.047
oph+0.045
 brist+0.044
 Her+0.042
Neg logit contributions
 sailors-0.066
boat-0.063
 boat-0.062
aro-0.060
 boats-0.060
Tokenâ
Token ID22940
Feature activation+1.63e+00

Pos logit contributions
 blonde+0.070
 blush+0.060
 brist+0.059
 brow+0.054
pron+0.054
Neg logit contributions
 boat-0.071
 sailors-0.071
 boats-0.069
aro-0.067
boat-0.066
Token€
Token ID26391
Feature activation+8.36e-01

Pos logit contributions
 blonde+0.048
 blush+0.041
 brist+0.040
oph+0.039
 Her+0.039
Neg logit contributions
 sailors-0.052
aro-0.049
 boat-0.049
boat-0.049
 boats-0.049
Tokenâ„¢
Token ID8151
Feature activation-7.03e-01

Pos logit contributions
 blonde+0.023
 blush+0.020
 brist+0.019
oph+0.018
 Her+0.018
Neg logit contributions
 sailors-0.028
 boat-0.027
aro-0.027
 boats-0.027
 sharks-0.026
Token
Token ID198
Feature activation+1.02e+00

Pos logit contributions
 blonde+0.027
 blush+0.024
 brist+0.023
oph+0.022
 Her+0.022
Neg logit contributions
 sailors-0.030
 boat-0.029
aro-0.029
 boats-0.028
ug-0.028
Token
Token ID198
Feature activation+1.19e+00

Pos logit contributions
 blonde+0.032
 blush+0.027
 brist+0.027
oph+0.026
 Her+0.025
Neg logit contributions
 sailors-0.031
aro-0.030
 boat-0.030
 boats-0.029
 sharks-0.029
TokenSus
Token ID30746
Feature activation+2.08e+00

Pos logit contributions
 blonde+0.035
 blush+0.031
 brist+0.030
oph+0.029
 Her+0.029
Neg logit contributions
 sailors-0.038
 boat-0.036
aro-0.036
 boats-0.036
 sharks-0.036
Tokenie
Token ID494
Feature activation+1.27e+00

Pos logit contributions
 blonde+0.081
 blush+0.071
 brist+0.070
 Her+0.068
 fru+0.067
Neg logit contributions
 sailors-0.048
ug-0.046
boat-0.046
aro-0.046
 boat-0.044
Token happily
Token ID18177
Feature activation-7.72e-01

Pos logit contributions
 blonde+0.036
 blush+0.031
 brist+0.030
oph+0.029
 Her+0.028
Neg logit contributions
 sailors-0.041
 boat-0.041
aro-0.040
 boats-0.039
boat-0.039
Token ate
Token ID15063
Feature activation+2.70e+00

Pos logit contributions
 sailors+0.027
 boat+0.026
aro+0.026
boat+0.026
 boats+0.026
Neg logit contributions
 blonde-0.020
 blush-0.017
 brist-0.017
 Her-0.016
oph-0.016
Token her
Token ID607
Feature activation+2.30e+00

Pos logit contributions
 blonde+0.100
oph+0.083
 blush+0.083
 brist+0.082
 Her+0.081
Neg logit contributions
 boat-0.065
 boats-0.065
 sailors-0.063
 sharks-0.061
 sail-0.059
Token apple
Token ID17180
Feature activation+1.57e+00

Pos logit contributions
 blonde+0.076
oph+0.068
 blush+0.066
 brist+0.065
uct+0.062
Neg logit contributions
 boat-0.064
 sail-0.060
 fish-0.060
 raft-0.060
 boats-0.058
Token.
Token ID13
Feature activation+1.62e+00

Pos logit contributions
 blonde+0.057
 blush+0.049
 brist+0.048
oph+0.047
 Her+0.046
Neg logit contributions
 boat-0.040
boat-0.038
 boats-0.038
 sailors-0.038
aro-0.037
Token Later
Token ID11450
Feature activation+1.74e-01

Pos logit contributions
 blonde+0.036
 blush+0.033
pron+0.031
oph+0.031
 brist+0.031
Neg logit contributions
 sailors-0.056
ug-0.054
aro-0.054
 sail-0.053
boat-0.053
Token,
Token ID11
Feature activation+8.62e-01

Pos logit contributions
 blonde+0.006
 blush+0.006
 brist+0.006
oph+0.005
 Her+0.005
Neg logit contributions
 sailors-0.004
 boat-0.004
aro-0.004
 boats-0.004
 sharks-0.004
Token day
Token ID1110
Feature activation+9.39e-01

Pos logit contributions
 blonde+0.065
 blush+0.058
 brist+0.057
 Her+0.056
oph+0.056
Neg logit contributions
 sailors-0.035
 boat-0.033
boat-0.032
aro-0.032
 boats-0.032
Token when
Token ID618
Feature activation+8.23e-01

Pos logit contributions
 blonde+0.031
 blush+0.027
 brist+0.026
oph+0.026
uct+0.025
Neg logit contributions
 sailors-0.026
 boat-0.025
 boats-0.025
aro-0.024
ug-0.024
Token she
Token ID673
Feature activation+8.51e-01

Pos logit contributions
 blonde+0.024
 blush+0.021
 brist+0.021
oph+0.020
 Her+0.019
Neg logit contributions
 sailors-0.026
 boat-0.025
 boats-0.025
aro-0.025
 sharks-0.025
Token decided
Token ID3066
Feature activation+2.12e+00

Pos logit contributions
 blonde+0.026
 brist+0.023
 blush+0.022
 Her+0.021
uct+0.021
Neg logit contributions
 boat-0.026
 boats-0.025
 sailors-0.025
 whales-0.024
 sharks-0.024
Token to
Token ID284
Feature activation+7.21e-01

Pos logit contributions
 blonde+0.071
 brist+0.064
 brow+0.061
 blush+0.061
oph+0.060
Neg logit contributions
 boat-0.058
 boats-0.057
 sailors-0.056
aro-0.054
 sharks-0.053
Token share
Token ID2648
Feature activation+2.58e+00

Pos logit contributions
 blonde+0.025
 blush+0.022
 brist+0.022
oph+0.021
 Her+0.021
Neg logit contributions
 sailors-0.019
aro-0.018
 boat-0.018
 boats-0.018
 sharks-0.018
Token it
Token ID340
Feature activation+1.64e+00

Pos logit contributions
 blonde+0.077
 brow+0.067
omm+0.065
 brist+0.064
oph+0.064
Neg logit contributions
 sailors-0.077
 boats-0.076
 sharks-0.075
 boat-0.075
 whales-0.073
Token with
Token ID351
Feature activation+5.15e-01

Pos logit contributions
 blonde+0.053
 blush+0.046
 brist+0.045
oph+0.044
 Her+0.044
Neg logit contributions
 sailors-0.048
 boat-0.045
aro-0.045
 boats-0.045
 sharks-0.044
Token her
Token ID607
Feature activation+5.05e-01

Pos logit contributions
 blonde+0.011
oph+0.008
uct+0.008
pron+0.008
 brist+0.008
Neg logit contributions
 sailors-0.020
aro-0.020
 boats-0.020
 sharks-0.020
 boat-0.019
Token family
Token ID1641
Feature activation-1.37e-01

Pos logit contributions
 blonde+0.020
 blush+0.018
oph+0.018
 brist+0.018
 Her+0.017
Neg logit contributions
 sailors-0.011
 boat-0.010
 boats-0.010
aro-0.010
 sharks-0.009
Token.
Token ID13
Feature activation-1.13e-01

Pos logit contributions
 sailors+0.004
aro+0.004
ug+0.004
 sharks+0.004
 captains+0.004
Neg logit contributions
 blonde-0.004
 blush-0.004
 Her-0.003
 brist-0.003
oph-0.003
Token always
Token ID1464
Feature activation+6.01e-01

Pos logit contributions
 blonde+0.038
 blush+0.033
 brist+0.032
oph+0.031
 Her+0.031
Neg logit contributions
 sailors-0.038
 boat-0.037
aro-0.036
 boats-0.036
boat-0.036
Token keep
Token ID1394
Feature activation+2.17e+00

Pos logit contributions
 blonde+0.021
 blush+0.018
oph+0.018
 brist+0.018
 Her+0.017
Neg logit contributions
 sailors-0.016
 boat-0.016
 boats-0.015
 captains-0.015
 sail-0.015
Token her
Token ID607
Feature activation+2.22e+00

Pos logit contributions
 blonde+0.065
 blush+0.056
oph+0.055
 brist+0.054
 Her+0.053
Neg logit contributions
 sailors-0.071
 boat-0.067
 boats-0.066
aro-0.065
 sharks-0.064
Token violin
Token ID38283
Feature activation+1.60e+00

Pos logit contributions
 blonde+0.068
 blush+0.059
oph+0.058
 brist+0.057
 Her+0.056
Neg logit contributions
 sailors-0.069
 boat-0.067
 boats-0.065
 captains-0.063
aro-0.063
Token clean
Token ID3424
Feature activation+3.35e+00

Pos logit contributions
 blonde+0.049
 blush+0.042
 brist+0.041
 Her+0.040
oph+0.040
Neg logit contributions
 sailors-0.050
aro-0.048
 boat-0.047
 boats-0.047
 sharks-0.046
Token,
Token ID11
Feature activation+2.96e+00

Pos logit contributions
 blonde+0.108
 blush+0.094
 brist+0.092
oph+0.090
 Her+0.090
Neg logit contributions
 sailors-0.098
 boat-0.095
 boats-0.093
boat-0.092
boats-0.091
Token so
Token ID523
Feature activation+5.31e-01

Pos logit contributions
 blonde+0.090
oph+0.084
 blush+0.080
 brist+0.078
 Her+0.076
Neg logit contributions
 sailors-0.089
 boat-0.087
 boats-0.085
 sail-0.082
 captains-0.080
Token that
Token ID326
Feature activation+1.39e+00

Pos logit contributions
 blonde+0.013
 blush+0.011
 brist+0.010
oph+0.010
 Her+0.010
Neg logit contributions
 sailors-0.020
 boat-0.019
aro-0.019
 boats-0.019
boat-0.019
Token she
Token ID673
Feature activation+1.68e+00

Pos logit contributions
 blonde+0.041
 blush+0.035
 brist+0.034
oph+0.034
 Her+0.033
Neg logit contributions
 sailors-0.044
 boat-0.043
aro-0.042
 boats-0.042
 sharks-0.042
Token could
Token ID714
Feature activation+1.26e+00

Pos logit contributions
 blonde+0.046
 blush+0.039
oph+0.037
 brist+0.037
 Her+0.035
Neg logit contributions
 sailors-0.059
 boat-0.058
boat-0.056
 boats-0.056
aro-0.056
Token play
Token ID711
Feature activation+2.51e+00

Pos logit contributions
 blonde+0.037
 blush+0.032
 brist+0.031
 Her+0.030
oph+0.030
Neg logit contributions
 sailors-0.041
aro-0.039
 sharks-0.038
 boat-0.038
 boats-0.038
Token It
Token ID632
Feature activation+8.45e-01

Pos logit contributions
pron+0.040
 cavity+0.036
 brushed+0.035
oph+0.035
 brist+0.035
Neg logit contributions
 boats-0.042
 Fin-0.039
 boat-0.039
 sailors-0.038
 sail-0.038
Token was
Token ID373
Feature activation+1.62e+00

Pos logit contributions
 blonde+0.026
 brist+0.023
 blush+0.022
oph+0.022
 brow+0.021
Neg logit contributions
 boat-0.025
 sailors-0.025
 boats-0.025
 ship-0.024
boat-0.024
Token a
Token ID257
Feature activation+4.68e-01

Pos logit contributions
 blonde+0.053
oph+0.049
 blush+0.049
 brist+0.048
uct+0.048
Neg logit contributions
 sailors-0.041
 boats-0.040
 boat-0.039
 sharks-0.038
 sail-0.037
Token squ
Token ID2809
Feature activation+9.85e-01

Pos logit contributions
 blonde+0.015
 blush+0.013
 brist+0.013
 Her+0.012
oph+0.012
Neg logit contributions
 sailors-0.014
 boat-0.014
 boats-0.013
 sharks-0.013
 captains-0.013
Tokenishy
Token ID49785
Feature activation+1.86e+00

Pos logit contributions
 blonde+0.028
 blush+0.024
 brist+0.023
 Her+0.023
oph+0.023
Neg logit contributions
 sailors-0.032
 boat-0.031
 boats-0.031
ug-0.030
aro-0.030
Token,
Token ID11
Feature activation+3.02e+00

Pos logit contributions
 blonde+0.058
uct+0.050
 blush+0.049
 Her+0.049
oph+0.049
Neg logit contributions
 boat-0.055
 sailors-0.054
 boats-0.052
boat-0.051
 sail-0.051
Token sm
Token ID895
Feature activation-3.95e-02

Pos logit contributions
 blonde+0.093
oph+0.091
omm+0.086
uct+0.085
 Her+0.085
Neg logit contributions
 boat-0.081
 sailors-0.080
 boats-0.079
 sail-0.076
 ship-0.074
Tokenelly
Token ID6148
Feature activation+8.70e-01

Pos logit contributions
 sailors+0.001
aro+0.001
 boat+0.001
 boats+0.001
boat+0.001
Neg logit contributions
 blonde-0.001
 blush-0.001
 brist-0.001
 Her-0.001
oph-0.001
Token gift
Token ID6979
Feature activation-7.80e-01

Pos logit contributions
 blonde+0.027
 blush+0.023
 brist+0.023
oph+0.023
uct+0.023
Neg logit contributions
 sailors-0.026
 boat-0.026
 boats-0.025
 sharks-0.024
aro-0.024
Tokenâ
Token ID22940
Feature activation+2.29e+00

Pos logit contributions
 sailors+0.021
 boat+0.020
aro+0.020
 boats+0.020
 sharks+0.019
Neg logit contributions
 blonde-0.027
 blush-0.024
 brist-0.023
oph-0.023
 Her-0.022
Token€
Token ID26391
Feature activation+1.02e+00

Pos logit contributions
 blonde+0.061
 blush+0.052
 brist+0.049
oph+0.046
 Her+0.046
Neg logit contributions
boat-0.075
ug-0.074
 sailors-0.074
aro-0.074
 boat-0.073
Token was
Token ID373
Feature activation-1.00e-01

Pos logit contributions
 blonde+0.006
 blush+0.005
 brist+0.005
oph+0.005
 makeup+0.005
Neg logit contributions
 sailors-0.007
 boat-0.007
 boats-0.007
aro-0.006
 ship-0.006
Token so
Token ID523
Feature activation-2.52e-02

Pos logit contributions
 sailors+0.004
 boat+0.003
aro+0.003
 boats+0.003
 captains+0.003
Neg logit contributions
 blonde-0.002
 blush-0.002
 brist-0.002
oph-0.002
 Her-0.002
Token happy
Token ID3772
Feature activation+6.10e-02

Pos logit contributions
 sailors+0.001
 boat+0.001
aro+0.001
 boats+0.001
 captains+0.001
Neg logit contributions
 blonde-0.001
 blush-0.001
 brist-0.001
oph-0.001
 Her-0.001
Token and
Token ID290
Feature activation+8.02e-01

Pos logit contributions
 blonde+0.002
 blush+0.002
 brist+0.002
oph+0.002
uct+0.002
Neg logit contributions
 sailors-0.002
 boat-0.002
 boats-0.002
 sharks-0.002
aro-0.002
Token hugged
Token ID41130
Feature activation+1.65e+00

Pos logit contributions
 blonde+0.024
 brist+0.021
 blush+0.021
oph+0.021
omm+0.020
Neg logit contributions
 sailors-0.025
 boat-0.024
 sail-0.023
 boats-0.022
 captains-0.022
Token the
Token ID262
Feature activation+1.20e-01

Pos logit contributions
 blonde+0.056
 blush+0.048
 brist+0.047
oph+0.047
pron+0.046
Neg logit contributions
 sailors-0.045
 boat-0.043
 boats-0.042
aro-0.042
 sharks-0.040
Token puppy
Token ID26188
Feature activation+3.68e-01

Pos logit contributions
 blonde+0.004
 blush+0.003
 brist+0.003
oph+0.003
 Her+0.003
Neg logit contributions
 sailors-0.004
 boat-0.003
 boats-0.003
boat-0.003
 sail-0.003
Token tight
Token ID5381
Feature activation+4.37e-01

Pos logit contributions
 blonde+0.010
 blush+0.008
 brist+0.008
oph+0.008
 Her+0.008
Neg logit contributions
 sailors-0.013
 boat-0.012
aro-0.012
 boats-0.012
 sharks-0.012
Token,
Token ID11
Feature activation+1.87e+00

Pos logit contributions
 blonde+0.016
 blush+0.015
oph+0.015
 brist+0.014
 Her+0.014
Neg logit contributions
 boat-0.010
 sailors-0.010
 boats-0.009
boat-0.009
boats-0.009
Token thanking
Token ID41892
Feature activation+1.76e+00

Pos logit contributions
 blonde+0.056
oph+0.051
 blush+0.049
 brist+0.049
omm+0.048
Neg logit contributions
 sailors-0.055
 boat-0.054
 sail-0.052
 boats-0.051
 raft-0.049
Token the
Token ID262
Feature activation-2.79e-01

Pos logit contributions
 blonde+0.057
 blush+0.049
 brist+0.048
oph+0.046
 Her+0.045
Neg logit contributions
 sailors-0.053
 boat-0.049
aro-0.048
 boats-0.048
 sharks-0.047
Token right
Token ID826
Feature activation-3.21e-01

Pos logit contributions
aro+0.041
 sailors+0.041
ug+0.040
 sharks+0.038
 captains+0.038
Neg logit contributions
 blonde-0.046
 blush-0.039
 brist-0.038
 Her-0.037
 makeup-0.037
Token thing
Token ID1517
Feature activation-7.95e-01

Pos logit contributions
 sailors+0.009
aro+0.009
 boats+0.008
 boat+0.008
 sharks+0.008
Neg logit contributions
 blonde-0.011
 blush-0.010
 brist-0.009
oph-0.009
 Her-0.009
Token to
Token ID284
Feature activation+3.69e-01

Pos logit contributions
 sailors+0.027
 boat+0.025
aro+0.025
 boats+0.025
 captains+0.025
Neg logit contributions
 blonde-0.022
 blush-0.019
 brist-0.018
 Her-0.018
oph-0.018
Token do
Token ID466
Feature activation+1.00e+00

Pos logit contributions
 blonde+0.014
 brist+0.012
 blush+0.012
oph+0.011
 Her+0.011
Neg logit contributions
 sailors-0.009
 boat-0.009
 boats-0.009
aro-0.008
boat-0.008
Token.
Token ID13
Feature activation-6.27e-01

Pos logit contributions
 blonde+0.036
 blush+0.032
 brist+0.031
oph+0.031
 Her+0.030
Neg logit contributions
 sailors-0.026
 boat-0.024
aro-0.024
 boats-0.024
 sharks-0.024
Token So
Token ID1406
Feature activation-5.24e-01

Pos logit contributions
 sailors+0.017
 boat+0.016
 boats+0.016
aro+0.016
boat+0.016
Neg logit contributions
 blonde-0.021
 blush-0.019
 brist-0.018
oph-0.017
pron-0.017
Token,
Token ID11
Feature activation-3.34e-01

Pos logit contributions
 sailors+0.014
aro+0.013
 boat+0.013
 boats+0.013
 sharks+0.013
Neg logit contributions
 blonde-0.018
 blush-0.016
 brist-0.016
 Her-0.016
oph-0.016
Token he
Token ID339
Feature activation-3.04e-01

Pos logit contributions
 sailors+0.009
aro+0.008
 boat+0.008
 boats+0.008
 sharks+0.008
Neg logit contributions
 blonde-0.012
 blush-0.011
 brist-0.010
 Her-0.010
oph-0.010
Token said
Token ID531
Feature activation+4.71e-01

Pos logit contributions
 sailors+0.011
 boat+0.010
 boats+0.010
aro+0.010
 captains+0.010
Neg logit contributions
 blonde-0.008
 blush-0.007
 brist-0.007
 Her-0.006
oph-0.006
Token,
Token ID11
Feature activation+2.10e+00

Pos logit contributions
 blonde+0.016
 blush+0.015
 brist+0.014
oph+0.014
 Her+0.014
Neg logit contributions
 sailors-0.013
 boat-0.012
aro-0.012
 boats-0.012
 sharks-0.012
Token "
Token ID366
Feature activation+1.05e+00

Pos logit contributions
 blonde+0.063
oph+0.054
 blush+0.052
 brist+0.050
 makeup+0.048
Neg logit contributions
 sailors-0.069
 boat-0.066
aro-0.064
 sail-0.063
 boats-0.063
Token and
Token ID290
Feature activation-5.43e-01

Pos logit contributions
 blonde+0.017
 blush+0.015
 brist+0.015
oph+0.014
 Her+0.014
Neg logit contributions
 sailors-0.017
 boat-0.016
 boats-0.016
aro-0.016
 sharks-0.016
Token Dad
Token ID17415
Feature activation-5.04e-01

Pos logit contributions
 sailors+0.015
 boat+0.014
 boats+0.014
 sharks+0.013
 whales+0.013
Neg logit contributions
 blonde-0.020
 blush-0.017
 brist-0.017
oph-0.016
 Her-0.016
Token too
Token ID1165
Feature activation+3.20e-01

Pos logit contributions
 sailors+0.014
 boat+0.013
 boats+0.013
 sharks+0.013
aro+0.013
Neg logit contributions
 blonde-0.018
 blush-0.015
 brist-0.015
oph-0.015
 Her-0.014
Token.
Token ID13
Feature activation-2.65e+00

Pos logit contributions
 blonde+0.010
 blush+0.009
 brist+0.009
 Her+0.009
oph+0.009
Neg logit contributions
 sailors-0.009
aro-0.009
 boat-0.009
boat-0.009
 boats-0.009
Token They
Token ID1119
Feature activation-1.58e+00

Pos logit contributions
 sailors+0.066
 boat+0.061
 boats+0.061
 sharks+0.060
aro+0.059
Neg logit contributions
 blonde-0.098
 blush-0.088
 brist-0.086
oph-0.084
uct-0.081
Token go
Token ID467
Feature activation-7.02e-01

Pos logit contributions
 sailors+0.044
aro+0.043
ug+0.041
 sharks+0.041
boats+0.041
Neg logit contributions
 blonde-0.052
 blush-0.048
 brist-0.046
 Her-0.045
oph-0.044
Token inside
Token ID2641
Feature activation-3.80e-03

Pos logit contributions
 sailors+0.025
aro+0.025
 sharks+0.025
 whales+0.025
ug+0.025
Neg logit contributions
 blonde-0.016
 blush-0.014
 Her-0.014
 brist-0.013
 makeup-0.013
Token and
Token ID290
Feature activation-1.40e+00

Pos logit contributions
 sailors+0.000
 boat+0.000
 boats+0.000
aro+0.000
 sharks+0.000
Neg logit contributions
 blonde-0.000
 blush-0.000
 brist-0.000
oph-0.000
 Her-0.000
Token play
Token ID711
Feature activation+8.84e-02

Pos logit contributions
 sailors+0.037
 boat+0.035
aro+0.035
 boats+0.034
 sharks+0.034
Neg logit contributions
 blonde-0.049
 blush-0.044
 brist-0.043
oph-0.042
 Her-0.042
Token with
Token ID351
Feature activation-1.69e+00

Pos logit contributions
 blonde+0.003
 blush+0.002
 brist+0.002
 Her+0.002
oph+0.002
Neg logit contributions
 sailors-0.003
aro-0.003
 boat-0.003
boat-0.003
 boats-0.003
Token their
Token ID511
Feature activation-8.20e-01

Pos logit contributions
 sailors+0.041
boat+0.040
aro+0.040
ug+0.039
 captains+0.038
Neg logit contributions
 blonde-0.063
 blush-0.056
 Her-0.054
 brist-0.054
 makeup-0.054
Token so
Token ID523
Feature activation+7.54e-01

Pos logit contributions
 blonde+0.008
 blush+0.007
oph+0.007
 brist+0.007
 Her+0.007
Neg logit contributions
 sailors-0.008
 boat-0.008
 boats-0.008
aro-0.008
 captains-0.008
Token pleased
Token ID10607
Feature activation+2.59e-01

Pos logit contributions
 blonde+0.024
 blush+0.022
oph+0.022
 brist+0.022
 Her+0.020
Neg logit contributions
 sailors-0.021
 boat-0.020
aro-0.020
 boats-0.019
 captains-0.019
Token with
Token ID351
Feature activation-2.12e-01

Pos logit contributions
 blonde+0.009
 blush+0.007
 brist+0.007
oph+0.007
 Her+0.007
Neg logit contributions
 sailors-0.008
 boat-0.007
aro-0.007
 boats-0.007
 sharks-0.007
Token her
Token ID607
Feature activation+1.02e+00

Pos logit contributions
 sailors+0.008
aro+0.008
 sharks+0.008
 boat+0.008
 boats+0.008
Neg logit contributions
 blonde-0.004
oph-0.004
 brist-0.004
 blush-0.004
amas-0.003
Token spark
Token ID9009
Feature activation+1.02e+00

Pos logit contributions
 blonde+0.031
 blush+0.026
 brist+0.026
oph+0.025
 Her+0.025
Neg logit contributions
 sailors-0.032
 boat-0.031
aro-0.030
 boats-0.030
 sharks-0.030
Tokenly
Token ID306
Feature activation+1.24e+00

Pos logit contributions
 blonde+0.027
 blush+0.022
 brist+0.022
oph+0.022
 Her+0.022
Neg logit contributions
 sailors-0.035
 boat-0.035
 boats-0.034
boat-0.034
aro-0.034
Token seat
Token ID5852
Feature activation+4.61e-01

Pos logit contributions
 blonde+0.037
oph+0.032
 blush+0.032
 Her+0.031
 brist+0.031
Neg logit contributions
 sailors-0.039
 boat-0.039
 boats-0.037
boat-0.037
 sail-0.036
Token and
Token ID290
Feature activation+7.65e-01

Pos logit contributions
 blonde+0.015
 blush+0.013
 brist+0.013
oph+0.013
 Her+0.013
Neg logit contributions
 sailors-0.013
 boat-0.013
aro-0.012
 boats-0.012
boat-0.012
Token her
Token ID607
Feature activation+1.30e+00

Pos logit contributions
 blonde+0.021
 brist+0.018
oph+0.018
 blush+0.017
 Her+0.017
Neg logit contributions
 sailors-0.026
 boat-0.025
 boats-0.025
aro-0.024
 captains-0.024
Token block
Token ID2512
Feature activation-2.68e-01

Pos logit contributions
 blonde+0.040
 blush+0.035
oph+0.035
 brist+0.034
 Her+0.033
Neg logit contributions
 sailors-0.039
 boat-0.039
 boats-0.038
aro-0.037
 sail-0.036
Token decorations
Token ID39011
Feature activation-9.71e-01

Pos logit contributions
 sailors+0.009
 boat+0.009
aro+0.008
 boats+0.008
boat+0.008
Neg logit contributions
 blonde-0.008
 blush-0.006
 brist-0.006
oph-0.006
 Her-0.006
Token says
Token ID1139
Feature activation+1.82e-01

Pos logit contributions
 blonde+0.034
oph+0.031
pron+0.030
 blush+0.028
uct+0.028
Neg logit contributions
 boats-0.020
 sailors-0.020
 boat-0.020
 sharks-0.019
 sail-0.018
Token.
Token ID13
Feature activation-1.56e+00

Pos logit contributions
 blonde+0.006
 blush+0.005
 brist+0.005
 Her+0.005
oph+0.005
Neg logit contributions
 sailors-0.006
aro-0.005
 boat-0.005
 captains-0.005
 boats-0.005
Token
Token ID198
Feature activation-1.08e+00

Pos logit contributions
 sailors+0.047
 boat+0.046
aro+0.045
 boats+0.044
 sharks+0.044
Neg logit contributions
 blonde-0.049
 blush-0.043
 brist-0.042
oph-0.042
 makeup-0.039
Token
Token ID198
Feature activation-3.24e-01

Pos logit contributions
 sailors+0.039
 boat+0.037
aro+0.037
 captains+0.036
 boats+0.036
Neg logit contributions
 blonde-0.028
 Her-0.023
 blush-0.023
 brist-0.023
oph-0.022
Token"
Token ID1
Feature activation+9.27e-01

Pos logit contributions
 sailors+0.011
aro+0.011
 boat+0.011
 boats+0.010
 sharks+0.010
Neg logit contributions
 blonde-0.009
 blush-0.008
 brist-0.007
 Her-0.007
oph-0.007
TokenCan
Token ID6090
Feature activation+6.53e-01

Pos logit contributions
 blonde+0.023
 blush+0.018
oph+0.018
 Her+0.018
 brist+0.018
Neg logit contributions
 sailors-0.034
aro-0.032
 boat-0.032
boat-0.032
 captains-0.032
Token I
Token ID314
Feature activation+1.00e+00

Pos logit contributions
 blonde+0.023
 blush+0.021
 Her+0.020
 brist+0.020
oph+0.020
Neg logit contributions
 sailors-0.017
boat-0.015
aro-0.015
 captains-0.015
 boat-0.015
Token have
Token ID423
Feature activation-4.90e-01

Pos logit contributions
 blonde+0.036
 blush+0.032
 brist+0.031
oph+0.031
 Her+0.030
Neg logit contributions
 sailors-0.025
 boat-0.024
aro-0.024
 boats-0.024
boat-0.023
Token one
Token ID530
Feature activation-4.11e-01

Pos logit contributions
 sailors+0.014
 boat+0.013
aro+0.013
 boats+0.013
 sharks+0.013
Neg logit contributions
 blonde-0.016
 blush-0.014
 brist-0.014
oph-0.014
 Her-0.014
Token,
Token ID11
Feature activation-1.45e-01

Pos logit contributions
 sailors+0.011
 boat+0.010
aro+0.010
 boats+0.010
boat+0.010
Neg logit contributions
 blonde-0.015
 blush-0.013
 brist-0.013
oph-0.012
 Her-0.012
Token Tom
Token ID4186
Feature activation-1.35e+00

Pos logit contributions
 sailors+0.005
 boat+0.004
 boats+0.004
 sharks+0.004
aro+0.004
Neg logit contributions
 blonde-0.004
 blush-0.004
 brist-0.004
oph-0.004
 Her-0.004
Tokenams
Token ID4105
Feature activation-5.92e-01

Pos logit contributions
 sailors+0.010
 boat+0.010
aro+0.009
 boats+0.009
 sharks+0.009
Neg logit contributions
 blonde-0.013
 blush-0.012
 brist-0.012
oph-0.011
 Her-0.011
Token.
Token ID13
Feature activation-4.53e-01

Pos logit contributions
 sailors+0.017
aro+0.017
 boat+0.016
 boats+0.016
 captains+0.016
Neg logit contributions
 blonde-0.019
 blush-0.016
 brist-0.016
 Her-0.016
oph-0.016
Token You
Token ID921
Feature activation-1.18e+00

Pos logit contributions
 sailors+0.016
 boat+0.015
aro+0.015
 boats+0.015
 sharks+0.015
Neg logit contributions
 blonde-0.012
 blush-0.010
 brist-0.010
 Her-0.010
oph-0.010
Token will
Token ID481
Feature activation-5.17e-01

Pos logit contributions
 sailors+0.037
aro+0.037
boats+0.036
ug+0.035
 boat+0.035
Neg logit contributions
 blonde-0.033
 blush-0.029
 brushed-0.028
 brist-0.027
 Her-0.027
Token not
Token ID407
Feature activation-1.89e+00

Pos logit contributions
 sailors+0.016
aro+0.015
 boat+0.015
 boats+0.015
ug+0.015
Neg logit contributions
 blonde-0.016
 blush-0.014
 brist-0.013
 Her-0.013
oph-0.013
Token go
Token ID467
Feature activation-1.12e+00

Pos logit contributions
 sailors+0.058
aro+0.058
boats+0.055
ug+0.055
 boats+0.054
Neg logit contributions
 blonde-0.056
 blush-0.052
 brist-0.048
 Her-0.047
 brushed-0.046
Token to
Token ID284
Feature activation-7.74e-01

Pos logit contributions
 sailors+0.038
aro+0.037
boat+0.036
ug+0.036
 boat+0.036
Neg logit contributions
 blonde-0.029
 blush-0.025
 makeup-0.023
 Her-0.023
 brist-0.023
Token the
Token ID262
Feature activation-2.29e-01

Pos logit contributions
boat+0.024
boats+0.023
 sailors+0.023
aro+0.023
ug+0.023
Neg logit contributions
 blonde-0.023
 blush-0.020
 Her-0.020
 makeup-0.019
 brist-0.019
Token park
Token ID3952
Feature activation-2.71e-01

Pos logit contributions
 sailors+0.007
aro+0.007
ug+0.007
boat+0.007
boats+0.007
Neg logit contributions
 blonde-0.007
 blush-0.006
 brist-0.006
 Her-0.006
oph-0.006
Token today
Token ID1909
Feature activation+3.48e-01

Pos logit contributions
 sailors+0.009
aro+0.009
ug+0.008
 captains+0.008
boat+0.008
Neg logit contributions
 blonde-0.007
 blush-0.006
oph-0.006
 Her-0.006
 brist-0.006
Token,
Token ID11
Feature activation+9.36e-01

Pos logit contributions
 blonde+0.012
 blush+0.011
 brist+0.010
oph+0.010
 Her+0.010
Neg logit contributions
 sailors-0.009
 boat-0.009
aro-0.009
 boats-0.009
 sharks-0.009
Token his
Token ID465
Feature activation-4.75e-01

Pos logit contributions
 sailors+0.023
aro+0.021
 boat+0.021
 boats+0.021
 captains+0.021
Neg logit contributions
 blonde-0.029
 blush-0.025
 Her-0.025
 brist-0.025
oph-0.024
Token friend
Token ID1545
Feature activation-1.56e+00

Pos logit contributions
boat+0.014
aro+0.014
boats+0.014
 sailors+0.014
ug+0.014
Neg logit contributions
 blonde-0.014
 blush-0.013
 brist-0.012
 Her-0.012
 makeup-0.012
Token,
Token ID11
Feature activation-4.19e-01

Pos logit contributions
 sailors+0.050
boat+0.049
aro+0.049
boats+0.048
ug+0.048
Neg logit contributions
 blonde-0.043
 Her-0.041
 blush-0.039
oph-0.037
 makeup-0.036
Token a
Token ID257
Feature activation-7.13e-01

Pos logit contributions
 sailors+0.013
aro+0.012
boat+0.012
ug+0.012
boats+0.012
Neg logit contributions
 blonde-0.013
 blush-0.011
 Her-0.011
 brist-0.011
 makeup-0.011
Token little
Token ID1310
Feature activation-1.79e+00

Pos logit contributions
 sailors+0.022
aro+0.022
ug+0.021
 boats+0.021
boats+0.021
Neg logit contributions
 blonde-0.022
 blush-0.019
 brist-0.018
 Her-0.018
 makeup-0.017
Token bird
Token ID6512
Feature activation-1.73e+00

Pos logit contributions
aro+0.057
 sailors+0.055
ug+0.053
boat+0.052
boats+0.052
Neg logit contributions
 blonde-0.052
 blush-0.046
 Her-0.044
 brist-0.044
 makeup-0.043
Token named
Token ID3706
Feature activation+1.41e-01

Pos logit contributions
 sailors+0.049
 captains+0.046
 boats+0.045
 sharks+0.045
 fishermen+0.045
Neg logit contributions
 blonde-0.054
 Her-0.053
 blush-0.051
 makeup-0.047
 brist-0.046
Token Sally
Token ID25737
Feature activation+3.24e-02

Pos logit contributions
 blonde+0.005
 blush+0.004
 Her+0.004
 brist+0.004
oph+0.004
Neg logit contributions
 sailors-0.004
 boat-0.004
aro-0.004
boat-0.004
 boats-0.004
Token,
Token ID11
Feature activation+4.99e-02

Pos logit contributions
 blonde+0.001
 blush+0.001
 Her+0.001
 brist+0.001
 makeup+0.001
Neg logit contributions
 sailors-0.001
aro-0.001
 captains-0.001
boat-0.001
 sharks-0.001
Token to
Token ID284
Feature activation-6.82e-01

Pos logit contributions
 blonde+0.002
 blush+0.001
 brist+0.001
oph+0.001
pron+0.001
Neg logit contributions
 sailors-0.002
 boat-0.001
 boats-0.001
 sharks-0.001
 whales-0.001
Token help
Token ID1037
Feature activation+2.79e-01

Pos logit contributions
 sailors+0.019
aro+0.018
boats+0.018
boat+0.018
 boat+0.018
Neg logit contributions
 blonde-0.022
 blush-0.020
 Her-0.020
 makeup-0.019
 brist-0.019
Token,
Token ID11
Feature activation-2.51e-01

Pos logit contributions
 sailors+0.023
 boat+0.022
boat+0.022
 boats+0.022
aro+0.022
Neg logit contributions
 blonde-0.023
 blush-0.020
 brist-0.020
oph-0.019
 Her-0.019
Token there
Token ID612
Feature activation-1.12e-01

Pos logit contributions
 sailors+0.007
aro+0.007
 boat+0.007
ug+0.007
boat+0.007
Neg logit contributions
 blonde-0.008
 blush-0.007
 brist-0.007
 Her-0.007
oph-0.007
Token was
Token ID373
Feature activation+1.14e+00

Pos logit contributions
 sailors+0.004
aro+0.003
 boat+0.003
 boats+0.003
 sharks+0.003
Neg logit contributions
 blonde-0.003
 blush-0.003
 brist-0.003
 Her-0.003
oph-0.003
Token a
Token ID257
Feature activation+1.17e+00

Pos logit contributions
 blonde+0.038
 blush+0.035
 brist+0.034
oph+0.034
 Her+0.033
Neg logit contributions
 sailors-0.029
 boat-0.028
 boats-0.028
 sharks-0.027
 whales-0.026
Token surprise
Token ID5975
Feature activation-1.13e+00

Pos logit contributions
 blonde+0.036
 blush+0.031
 Her+0.031
 brist+0.031
oph+0.030
Neg logit contributions
 sailors-0.035
 boat-0.034
 boats-0.033
 sharks-0.032
 captains-0.032
Token for
Token ID329
Feature activation-1.82e+00

Pos logit contributions
 sailors+0.034
aro+0.033
 boat+0.032
 boats+0.032
 captains+0.032
Neg logit contributions
 blonde-0.035
 blush-0.031
 brist-0.030
oph-0.029
 Her-0.029
Token Peter
Token ID5613
Feature activation+1.33e-01

Pos logit contributions
 sailors+0.054
 boat+0.051
aro+0.051
 boats+0.051
boat+0.050
Neg logit contributions
 blonde-0.058
 blush-0.050
 brist-0.048
 Her-0.048
oph-0.048
Token -
Token ID532
Feature activation+6.99e-01

Pos logit contributions
 blonde+0.004
 blush+0.004
 brist+0.004
oph+0.003
 Her+0.003
Neg logit contributions
 sailors-0.004
 boat-0.004
aro-0.004
 boats-0.004
 sharks-0.004
Token a
Token ID257
Feature activation+6.75e-01

Pos logit contributions
 blonde+0.023
 blush+0.020
 brist+0.020
oph+0.019
 Her+0.019
Neg logit contributions
 sailors-0.020
 boat-0.019
 boats-0.019
aro-0.019
 sharks-0.019
Token big
Token ID1263
Feature activation-1.21e-01

Pos logit contributions
 blonde+0.020
 blush+0.018
 brist+0.017
 Her+0.017
oph+0.017
Neg logit contributions
 boat-0.021
 sailors-0.020
 boats-0.019
 sharks-0.019
 sail-0.019
Token delicious
Token ID12625
Feature activation+1.38e+00

Pos logit contributions
 sailors+0.004
aro+0.004
 boat+0.003
 boats+0.003
 sharks+0.003
Neg logit contributions
 blonde-0.004
 blush-0.003
 brist-0.003
oph-0.003
 Her-0.003
Token excited
Token ID6568
Feature activation+7.97e-01

Pos logit contributions
boat+0.038
aro+0.038
 sailors+0.038
boats+0.038
 boat+0.037
Neg logit contributions
 blonde-0.024
 Her-0.020
 blush-0.018
 brist-0.018
 fru-0.018
Token!
Token ID0
Feature activation+1.35e+00

Pos logit contributions
 blonde+0.030
 blush+0.026
 brist+0.026
 brow+0.024
pron+0.024
Neg logit contributions
 sailors-0.020
 boat-0.019
 boats-0.019
 sharks-0.019
 whales-0.018
Token She
Token ID1375
Feature activation-5.62e-01

Pos logit contributions
 blonde+0.036
pron+0.034
ited+0.033
 cavity+0.032
 brist+0.031
Neg logit contributions
 boats-0.037
 Fin-0.037
 crane-0.036
 boat-0.035
 bridge-0.035
Token said
Token ID531
Feature activation+1.38e+00

Pos logit contributions
 sailors+0.019
 boat+0.018
 boats+0.018
 captains+0.018
 sharks+0.018
Neg logit contributions
 blonde-0.016
 blush-0.014
 brist-0.013
oph-0.013
 Her-0.013
Token to
Token ID284
Feature activation+1.35e+00

Pos logit contributions
 blonde+0.047
 blush+0.041
 brist+0.040
oph+0.040
 Her+0.039
Neg logit contributions
 sailors-0.038
 boat-0.036
aro-0.036
 boats-0.036
 sharks-0.035
Token her
Token ID607
Feature activation-1.20e+00

Pos logit contributions
 blonde+0.038
 brist+0.030
oph+0.030
 blush+0.030
 fru+0.029
Neg logit contributions
 sailors-0.046
 boats-0.044
 boat-0.043
aro-0.043
 whales-0.043
Token mom
Token ID1995
Feature activation+2.22e+00

Pos logit contributions
ug+0.043
boat+0.043
aro+0.043
boats+0.042
 sailors+0.041
Neg logit contributions
 blonde-0.029
 blush-0.026
 Her-0.026
 makeup-0.024
 brist-0.023
Token,
Token ID11
Feature activation+1.88e+00

Pos logit contributions
 blonde+0.078
 blush+0.069
 brist+0.067
oph+0.066
 Her+0.065
Neg logit contributions
 sailors-0.059
 boat-0.056
aro-0.055
 boats-0.055
 sharks-0.054
Token "
Token ID366
Feature activation+4.39e-01

Pos logit contributions
 blonde+0.056
oph+0.049
 blush+0.047
 brist+0.047
uct+0.043
Neg logit contributions
 sailors-0.061
 boat-0.059
aro-0.057
 boats-0.056
 whales-0.055
TokenLook
Token ID8567
Feature activation+3.00e+00

Pos logit contributions
 blonde+0.012
 blush+0.010
 brist+0.010
oph+0.010
 Her+0.010
Neg logit contributions
 sailors-0.015
 boat-0.015
aro-0.015
 boats-0.014
 sharks-0.014
Token,
Token ID11
Feature activation-2.15e-01

Pos logit contributions
 blonde+0.106
 blush+0.091
 brist+0.091
oph+0.087
 Her+0.087
Neg logit contributions
 sailors-0.079
 boat-0.076
aro-0.075
 boats-0.074
 sharks-0.072
Token very
Token ID845
Feature activation-4.61e-01

Pos logit contributions
 sailors+0.020
aro+0.019
 boat+0.019
boat+0.019
 boats+0.019
Neg logit contributions
 blonde-0.019
 blush-0.017
 brist-0.016
oph-0.016
 Her-0.016
Token popular
Token ID2968
Feature activation-5.17e-01

Pos logit contributions
 sailors+0.015
aro+0.015
boat+0.015
ug+0.015
boats+0.015
Neg logit contributions
 blonde-0.013
 blush-0.010
 fru-0.010
 brist-0.010
oph-0.010
Token among
Token ID1871
Feature activation-9.92e-01

Pos logit contributions
 sailors+0.015
aro+0.015
 boat+0.015
boat+0.014
 captains+0.014
Neg logit contributions
 blonde-0.016
 blush-0.014
 brist-0.014
oph-0.013
 Her-0.013
Token their
Token ID511
Feature activation+4.39e-01

Pos logit contributions
 sailors+0.026
 boat+0.025
boat+0.025
 captains+0.024
boats+0.024
Neg logit contributions
 blonde-0.034
 blush-0.030
 Her-0.029
 brist-0.029
oph-0.029
Token friends
Token ID2460
Feature activation-9.18e-01

Pos logit contributions
 blonde+0.013
 blush+0.012
 brist+0.011
 Her+0.011
oph+0.011
Neg logit contributions
 sailors-0.014
aro-0.013
 boat-0.013
boat-0.013
 boats-0.013
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
 sailors+0.028
aro+0.026
 boat+0.026
 sharks+0.026
 captains+0.026
Neg logit contributions
 blonde-0.028
 blush-0.025
 Her-0.024
 brist-0.023
oph-0.023
Token<|endoftext|>
Token ID50256
Feature activation-5.19e-01

Pos logit contributions
 sailors+0.050
 boat+0.048
aro+0.048
 boats+0.047
 sharks+0.047
Neg logit contributions
 blonde-0.041
 blush-0.035
 brist-0.034
oph-0.033
 Her-0.033
TokenOnce
Token ID7454
Feature activation-1.44e+00

Pos logit contributions
 sailors+0.016
aro+0.016
 boat+0.016
 boats+0.015
 sharks+0.015
Neg logit contributions
 blonde-0.015
 blush-0.013
 brist-0.013
oph-0.013
 Her-0.012
Token upon
Token ID2402
Feature activation+5.22e-01

Pos logit contributions
 sailors+0.064
 captains+0.061
aro+0.061
 boat+0.061
 boats+0.060
Neg logit contributions
 blonde-0.024
 Her-0.019
 blush-0.018
oph-0.017
 brist-0.016
Token a
Token ID257
Feature activation+1.09e+00

Pos logit contributions
 blonde+0.017
 blush+0.016
 brist+0.015
oph+0.015
 Her+0.015
Neg logit contributions
 sailors-0.014
 boat-0.014
 sharks-0.013
 boats-0.013
aro-0.013
Token time
Token ID640
Feature activation+7.97e-01

Pos logit contributions
 blonde+0.030
 blush+0.026
 brist+0.025
 Her+0.024
oph+0.024
Neg logit contributions
 sailors-0.036
 boat-0.035
 boats-0.035
 sharks-0.034
aro-0.034
Token.
Token ID13
Feature activation+1.24e-01

Pos logit contributions
 sailors+0.015
 captains+0.014
aro+0.014
 whales+0.014
 boat+0.014
Neg logit contributions
 blonde-0.013
 blush-0.011
 brist-0.010
 Her-0.010
 makeup-0.010
Token Suddenly
Token ID24975
Feature activation-7.15e-01

Pos logit contributions
 blonde+0.004
 blush+0.004
oph+0.004
 brist+0.004
pron+0.003
Neg logit contributions
 boat-0.003
 sailors-0.003
 boats-0.003
ug-0.003
 sharks-0.003
Token,
Token ID11
Feature activation-6.09e-01

Pos logit contributions
 sailors+0.024
boat+0.023
boats+0.023
aro+0.023
 captains+0.023
Neg logit contributions
 blonde-0.020
 Her-0.016
 brist-0.016
 blush-0.016
oph-0.015
Token a
Token ID257
Feature activation-9.24e-01

Pos logit contributions
aro+0.019
 sailors+0.019
boats+0.019
 captains+0.019
boat+0.019
Neg logit contributions
 blonde-0.017
 blush-0.014
 brist-0.014
 Her-0.014
 brow-0.013
Token big
Token ID1263
Feature activation-1.07e+00

Pos logit contributions
aro+0.030
 sailors+0.028
boats+0.028
ug+0.027
 boats+0.027
Neg logit contributions
 blonde-0.027
 brist-0.022
pron-0.022
 blush-0.022
 fru-0.021
Token wave
Token ID6769
Feature activation-4.19e+00

Pos logit contributions
aro+0.033
 sailors+0.030
 captains+0.030
boats+0.029
ug+0.029
Neg logit contributions
 blonde-0.033
 blush-0.028
 brist-0.028
 fru-0.027
 makeup-0.026
Token came
Token ID1625
Feature activation-1.61e+00

Pos logit contributions
 sailors+0.178
 captains+0.172
aro+0.171
 boats+0.171
 afloat+0.170
Neg logit contributions
 blonde-0.053
 blush-0.047
 brushed-0.043
 spat-0.042
 Her-0.041
Token and
Token ID290
Feature activation-1.16e+00

Pos logit contributions
aro+0.058
 sailors+0.058
boats+0.056
 captains+0.056
 sharks+0.056
Neg logit contributions
 blonde-0.037
 Her-0.032
 brist-0.030
 brow-0.029
 blush-0.029
Token hit
Token ID2277
Feature activation-5.72e-01

Pos logit contributions
 sailors+0.038
ug+0.038
 captains+0.037
aro+0.037
boats+0.037
Neg logit contributions
 blonde-0.027
 brushed-0.025
 blush-0.023
 brist-0.023
 fru-0.022
Token the
Token ID262
Feature activation-9.83e-01

Pos logit contributions
 sailors+0.016
 captains+0.016
aro+0.015
boat+0.015
boats+0.015
Neg logit contributions
 blonde-0.019
 brist-0.016
 blush-0.016
 Her-0.016
 brow-0.015
Token boat
Token ID8848
Feature activation-2.86e+00

Pos logit contributions
aro+0.023
ug+0.021
boats+0.020
boat+0.018
ull+0.018
Neg logit contributions
 blonde-0.034
 brist-0.031
 brow-0.031
 spat-0.029
 fru-0.029
Token one
Token ID530
Feature activation-1.76e+00

Pos logit contributions
 sailors+0.024
 boat+0.023
aro+0.023
 boats+0.023
 sharks+0.023
Neg logit contributions
 blonde-0.034
 blush-0.030
 brist-0.030
oph-0.029
 Her-0.029
Token day
Token ID1110
Feature activation-9.52e-01

Pos logit contributions
 sailors+0.049
aro+0.048
 captains+0.047
boats+0.046
 boats+0.046
Neg logit contributions
 blonde-0.059
 blush-0.052
 Her-0.051
 brist-0.050
oph-0.048
Token,
Token ID11
Feature activation-2.23e+00

Pos logit contributions
 sailors+0.024
 boat+0.022
aro+0.022
 sharks+0.022
 boats+0.022
Neg logit contributions
 blonde-0.035
 blush-0.031
 brist-0.030
oph-0.030
 Her-0.029
Token a
Token ID257
Feature activation-8.27e-01

Pos logit contributions
 sailors+0.069
aro+0.066
 boat+0.066
 boats+0.065
 captains+0.064
Neg logit contributions
 blonde-0.068
 blush-0.059
 brist-0.057
 Her-0.056
oph-0.056
Token small
Token ID1402
Feature activation-1.58e+00

Pos logit contributions
aro+0.026
 sailors+0.026
ug+0.025
boats+0.025
 boats+0.025
Neg logit contributions
 blonde-0.025
 blush-0.021
 brist-0.020
 Her-0.019
 makeup-0.019
Token animal
Token ID5044
Feature activation-4.13e+00

Pos logit contributions
aro+0.044
 sailors+0.043
 captains+0.041
boats+0.041
ug+0.040
Neg logit contributions
 blonde-0.054
 blush-0.047
 brist-0.046
 Her-0.044
 makeup-0.044
Token came
Token ID1625
Feature activation-1.90e+00

Pos logit contributions
 sailors+0.162
ug+0.156
 afloat+0.155
 captains+0.155
boats+0.154
Neg logit contributions
 blonde-0.082
 Her-0.073
 blush-0.071
 makeup-0.063
 spat-0.062
Token along
Token ID1863
Feature activation-1.27e+00

Pos logit contributions
 sailors+0.068
aro+0.065
 boat+0.065
 boats+0.064
 captains+0.064
Neg logit contributions
 blonde-0.048
 blush-0.040
 Her-0.040
 brist-0.039
oph-0.037
Token.
Token ID13
Feature activation-1.40e+00

Pos logit contributions
 sailors+0.042
aro+0.040
 captains+0.040
 boat+0.039
boats+0.039
Neg logit contributions
 blonde-0.035
 Her-0.030
 blush-0.029
 brist-0.029
oph-0.028
Token It
Token ID632
Feature activation-6.93e-01

Pos logit contributions
 boat+0.040
 sailors+0.040
 sharks+0.039
 boats+0.038
 sail+0.038
Neg logit contributions
 blonde-0.042
 blush-0.039
 brist-0.038
oph-0.037
pron-0.035
Token was
Token ID373
Feature activation-6.33e-01

Pos logit contributions
 sailors+0.023
 boat+0.023
 boats+0.023
aro+0.022
 sharks+0.022
Neg logit contributions
 blonde-0.019
 blush-0.017
 brist-0.016
oph-0.016
 Her-0.015
TokenOne
Token ID3198
Feature activation-1.12e+00

Pos logit contributions
 sailors+0.033
 boat+0.031
aro+0.031
 sharks+0.030
 boats+0.030
Neg logit contributions
 blonde-0.023
 Her-0.019
oph-0.019
 blush-0.018
 brist-0.018
Token day
Token ID1110
Feature activation-1.30e+00

Pos logit contributions
aro+0.039
 sailors+0.038
 captains+0.037
boats+0.037
 boats+0.035
Neg logit contributions
 blonde-0.029
 Her-0.027
 blush-0.025
pron-0.025
oph-0.024
Token,
Token ID11
Feature activation-1.62e+00

Pos logit contributions
 sailors+0.043
boat+0.041
aro+0.041
 boat+0.040
boats+0.040
Neg logit contributions
 blonde-0.037
 blush-0.033
 Her-0.032
oph-0.030
 brist-0.030
Token the
Token ID262
Feature activation-2.38e+00

Pos logit contributions
 sailors+0.046
aro+0.045
boat+0.044
 boat+0.044
ug+0.044
Neg logit contributions
 blonde-0.053
 blush-0.047
 Her-0.046
oph-0.045
 brist-0.045
Token two
Token ID734
Feature activation-3.78e+00

Pos logit contributions
aro+0.072
ug+0.071
 sailors+0.070
boat+0.067
 sharks+0.067
Neg logit contributions
 blonde-0.076
 blush-0.068
 Her-0.066
 makeup-0.064
 brist-0.064
Token friends
Token ID2460
Feature activation-4.40e+00

Pos logit contributions
aro+0.115
boat+0.113
 afloat+0.112
 dock+0.107
 sailors+0.107
Neg logit contributions
 blonde-0.114
 Her-0.105
 blush-0.103
oph-0.098
 makeup-0.095
Token started
Token ID2067
Feature activation-1.73e+00

Pos logit contributions
aro+0.176
 sailors+0.174
boats+0.171
 sharks+0.170
boat+0.169
Neg logit contributions
 blonde-0.086
 blush-0.075
 Her-0.073
oph-0.066
 makeup-0.065
Token to
Token ID284
Feature activation-1.20e+00

Pos logit contributions
 sailors+0.064
aro+0.061
 boat+0.061
 boats+0.060
boat+0.060
Neg logit contributions
 blonde-0.042
 blush-0.035
 brist-0.034
 Her-0.033
oph-0.033
Token quarrel
Token ID41998
Feature activation-1.53e+00

Pos logit contributions
 sailors+0.032
aro+0.030
 boat+0.029
boat+0.029
 sharks+0.029
Neg logit contributions
 blonde-0.043
 blush-0.038
 brist-0.037
 Her-0.036
oph-0.036
Token.
Token ID13
Feature activation-1.35e+00

Pos logit contributions
 sailors+0.050
aro+0.047
 boat+0.047
 captains+0.046
 whales+0.046
Neg logit contributions
 blonde-0.044
 blush-0.039
 Her-0.038
 brist-0.038
 makeup-0.036
Token They
Token ID1119
Feature activation-2.36e+00

Pos logit contributions
 sailors+0.035
 boat+0.033
aro+0.033
 boats+0.032
 sharks+0.032
Neg logit contributions
 blonde-0.048
 blush-0.043
 brist-0.042
oph-0.041
 Her-0.040
Token They
Token ID1119
Feature activation-3.20e+00

Pos logit contributions
 boats+0.020
 sailors+0.020
 boat+0.019
 sharks+0.019
 fishermen+0.018
Neg logit contributions
 blonde-0.029
 blush-0.027
 brist-0.026
oph-0.026
uct-0.026
Token said
Token ID531
Feature activation-1.31e+00

Pos logit contributions
aro+0.130
ug+0.129
boats+0.122
boat+0.120
 afloat+0.117
Neg logit contributions
 blonde-0.059
 blush-0.050
 brushed-0.050
 spat-0.045
 unw-0.044
Token he
Token ID339
Feature activation+2.24e-01

Pos logit contributions
boat+0.042
 sailors+0.041
boats+0.040
 afloat+0.040
aro+0.040
Neg logit contributions
 blonde-0.037
 Her-0.032
 blush-0.032
 makeup-0.029
 brist-0.029
Token was
Token ID373
Feature activation-2.41e+00

Pos logit contributions
 blonde+0.005
 blush+0.004
 brist+0.004
 Her+0.004
oph+0.004
Neg logit contributions
 sailors-0.009
aro-0.009
 boat-0.008
 boats-0.008
ug-0.008
Token a
Token ID257
Feature activation-3.57e+00

Pos logit contributions
boat+0.081
ug+0.080
aro+0.079
boats+0.077
 boat+0.075
Neg logit contributions
 blonde-0.059
 makeup-0.049
 blush-0.048
 Her-0.047
 her-0.045
Token little
Token ID1310
Feature activation-4.38e+00

Pos logit contributions
aro+0.114
ug+0.114
boats+0.101
boat+0.100
 afloat+0.097
Neg logit contributions
 blonde-0.092
pron-0.088
 fru-0.082
 makeup-0.080
 l-0.079
Token snack
Token ID26906
Feature activation-1.93e+00

Pos logit contributions
aro+0.131
ug+0.121
boat+0.114
boats+0.110
ull+0.110
Neg logit contributions
 blonde-0.128
 fru-0.116
 spat-0.109
 blush-0.109
 makeup-0.108
Token for
Token ID329
Feature activation-2.38e+00

Pos logit contributions
aro+0.066
 sailors+0.065
 captains+0.063
ug+0.062
 boats+0.061
Neg logit contributions
 blonde-0.043
 blush-0.040
 makeup-0.038
oph-0.038
 Her-0.037
Token them
Token ID606
Feature activation-1.67e+00

Pos logit contributions
boat+0.069
aro+0.067
 sailors+0.067
boats+0.066
 boat+0.065
Neg logit contributions
 blonde-0.074
 blush-0.065
 Her-0.063
 makeup-0.061
 brist-0.061
Token.
Token ID13
Feature activation-1.28e+00

Pos logit contributions
 sailors+0.052
aro+0.051
boat+0.049
ug+0.049
 boat+0.049
Neg logit contributions
 blonde-0.048
 blush-0.042
 Her-0.041
 brist-0.039
 makeup-0.039
Token Ben
Token ID3932
Feature activation-8.87e-01

Pos logit contributions
 sailors+0.031
 boats+0.031
 boat+0.030
 sharks+0.030
 captains+0.028
Neg logit contributions
 blonde-0.047
 blush-0.042
 brist-0.042
oph-0.039
uct-0.039
TokenOne
Token ID3198
Feature activation+3.18e-01

Pos logit contributions
 blonde+0.032
 blush+0.028
 brist+0.028
oph+0.027
 Her+0.026
Neg logit contributions
 sailors-0.027
 boat-0.026
 boats-0.025
aro-0.025
 sharks-0.025
Token day
Token ID1110
Feature activation+5.42e-01

Pos logit contributions
 blonde+0.010
 Her+0.008
 blush+0.008
 brist+0.008
 brushed+0.008
Neg logit contributions
 sailors-0.010
 captains-0.010
aro-0.010
boats-0.009
 boats-0.009
Token,
Token ID11
Feature activation+1.24e+00

Pos logit contributions
 blonde+0.021
 blush+0.019
 brist+0.019
uct+0.019
oph+0.019
Neg logit contributions
 sailors-0.012
 boat-0.011
 sharks-0.011
 boats-0.011
aro-0.011
Token a
Token ID257
Feature activation-9.22e-01

Pos logit contributions
 blonde+0.038
uct+0.035
 brist+0.035
oph+0.034
 blush+0.032
Neg logit contributions
 boat-0.033
 sharks-0.033
 sailors-0.033
 boats-0.032
 they-0.030
Token big
Token ID1263
Feature activation-6.32e-01

Pos logit contributions
aro+0.029
 sailors+0.029
ug+0.028
boat+0.028
boats+0.028
Neg logit contributions
 blonde-0.027
 blush-0.024
 brist-0.022
pron-0.022
 Her-0.022
Token truck
Token ID7779
Feature activation-5.16e+00

Pos logit contributions
aro+0.017
 sailors+0.017
 captains+0.017
boats+0.016
ug+0.016
Neg logit contributions
 blonde-0.021
 blush-0.019
 brist-0.018
 makeup-0.018
 fru-0.017
Token stops
Token ID9911
Feature activation-6.56e-01

Pos logit contributions
 sailors+0.208
 afloat+0.207
ug+0.204
aro+0.204
 sharks+0.196
Neg logit contributions
 Her-0.079
 blonde-0.077
 She-0.073
 blush-0.072
 spat-0.068
Token in
Token ID287
Feature activation+3.49e-01

Pos logit contributions
 sailors+0.020
aro+0.020
 captains+0.019
boat+0.019
 boat+0.019
Neg logit contributions
 blonde-0.019
 brist-0.017
 blush-0.017
 Her-0.016
 makeup-0.016
Token front
Token ID2166
Feature activation-1.12e+00

Pos logit contributions
 blonde+0.013
 blush+0.011
 brist+0.011
oph+0.011
 Her+0.011
Neg logit contributions
 sailors-0.009
 boat-0.008
 boats-0.008
aro-0.008
 sharks-0.008
Token of
Token ID286
Feature activation-2.39e-01

Pos logit contributions
 sailors+0.027
aro+0.025
 captains+0.025
 sharks+0.024
boat+0.024
Neg logit contributions
 blonde-0.042
 blush-0.038
 Her-0.038
 brist-0.037
 makeup-0.035
Token their
Token ID511
Feature activation-1.26e+00

Pos logit contributions
 sailors+0.007
 boats+0.007
 boat+0.007
 sharks+0.007
 whales+0.007
Neg logit contributions
 blonde-0.007
 blush-0.006
 brist-0.006
oph-0.006
uct-0.006