TOP ACTIVATIONS
MAX = 0.087

M um heard Jos ie and came in to
ally ate all the y ummy cookies , and then lay
They both enjoyed the y ummy cake and had a great
stars , hearts , flowers , and animals . She saw
They both enjoyed the y ummy dessert . After
his mom ate the y ummy cake together . Tim felt
happy and loved as they finished reading the story together .
games , ate the y ummy cake , and had lots
He took out the finished dough and showed everyone .
down and ate the y ummy pasta together . Lucy 's
the hill . <|endoftext|> M omm a and Tom were on
They ate the y ummy pasta together . Dad smiled
played games , ate y ummy cake , and had lots
started to pack all of Jos ie â s
. He ate the y ummy cookie and then put his
eager to eat the y ummy cookies . She ate one
. It looked even y umm ier . Lily wanted to
porch , ate the y ummy cookies , and had a
help and enjoy the y ummy cake . <|endoftext|> Once upon
books , toys , clothes , and candy . They smiled

MIN ACTIVATIONS
MIN = -0.112

hands too . He says brav o . Tom and Anna
and nig ella and f enn el and an ise and
agreed to give her her kay ak in exchange for the
loud noise . He sc run ched his eyes tightly and
Why did you take my kay ak ?" L
" What is this big cross ?" Lily said , "
and always tried to out run everyone else . One day
! Cl ang ! Cl ang !" the shovel goes .
. He tried to out run the train but he was
Why did you take my kay ak ?" he asked .
if he could take his kay ak out for a ride
that might fit in your kay ak . We can play
at each other and shout each time they pointed .
" Thank you for my kay ak , it was so
you ?" B run o said , " Of
we please have one carrot each ?" Far mer
man stepped closer and said gru ff ly , " You
" Cl ang ! Cl ang ! Cl ang !" the
to have fun with their kay ak . They
Can I play with your kay ak ?" asked Lily .

INTERVAL 0.037 - 0.087
CONTAINS 1.576%

red flowers , blue flowers , and yellow flowers . Lily
join them . They poured tea and served cookies . They
aunt gave her for her birthday . She did not want
was so excited to see what the day would bring !
Mom my , I look nice in my suit !"

INTERVAL -0.012 - 0.037
CONTAINS 75.857%

was all covered . Next , Mama brought out
she heard laughter coming from a nearby park . She turned
his groceries home . He put them away and made a
Tom nods . He does not want to be
so much fun together until the sun went down and it

INTERVAL -0.062 - -0.012
CONTAINS 22.541%

ak . It flies to the p uddle . It sees
his cars . She asked him if he took her cr
anything too big again . <|endoftext|> Once upon a time ,
They knew that pistols were dangerous and they should never touch
was a very special deer that looked very fragile . It

INTERVAL -0.112 - -0.062
CONTAINS 0.027%

, Mia wanted to go kay aking . She thought it
, but his mother said no . So there it stayed
it , but she said no . He was so sad
, " Can you lend me your toy truck ?" Tom
wanted to play with the kay ak but they couldn 't
Token
Token ID198
Feature activation+1.72e-03

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
ued+0.001
ulously+0.001
Neg logit contributions
bows-0.001
 queens-0.001
head-0.001
 germ-0.001
 smell-0.001
Token
Token ID198
Feature activation+2.26e-02

Pos logit contributions
head+0.002
bows+0.002
 she+0.002
isha+0.002
 queens+0.002
Neg logit contributions
roads-0.003
stack-0.003
vered-0.003
ishly-0.002
 tal-0.002
TokenM
Token ID44
Feature activation+4.97e-02

Pos logit contributions
bows+0.038
head+0.034
 queens+0.034
 germ+0.033
 smell+0.032
Neg logit contributions
roads-0.031
vered-0.029
ued-0.025
stack-0.025
ulously-0.025
Tokenum
Token ID388
Feature activation+3.67e-02

Pos logit contributions
bows+0.065
head+0.061
 queens+0.060
 Elsa+0.056
 Hanna+0.055
Neg logit contributions
am-0.079
roads-0.076
vered-0.071
ulously-0.069
ement-0.068
Token heard
Token ID2982
Feature activation+2.25e-02

Pos logit contributions
bows+0.046
head+0.046
 queens+0.044
isha+0.042
issy+0.041
Neg logit contributions
roads-0.062
vered-0.057
stack-0.056
ued-0.052
 tal-0.050
Token Jos
Token ID22568
Feature activation+8.73e-02

Pos logit contributions
bows+0.035
 queens+0.031
 germ+0.029
head+0.028
 spill+0.027
Neg logit contributions
roads-0.032
vered-0.029
ered-0.027
ulously-0.027
am-0.026
Tokenie
Token ID494
Feature activation+3.13e-02

Pos logit contributions
bows+0.095
head+0.087
 queens+0.084
 germ+0.078
isha+0.075
Neg logit contributions
roads-0.166
vered-0.157
stack-0.151
ued-0.142
ulously-0.138
Token and
Token ID290
Feature activation+1.30e-02

Pos logit contributions
bows+0.040
head+0.038
 queens+0.036
 smell+0.035
 germ+0.035
Neg logit contributions
roads-0.052
vered-0.049
stack-0.047
ued-0.044
ulously-0.043
Token came
Token ID1625
Feature activation+7.16e-03

Pos logit contributions
bows+0.020
head+0.017
 queens+0.017
 germ+0.016
 spill+0.015
Neg logit contributions
roads-0.020
vered-0.018
stack-0.017
ued-0.016
used-0.016
Token in
Token ID287
Feature activation-9.26e-03

Pos logit contributions
bows+0.009
head+0.008
 queens+0.008
isha+0.008
 smell+0.008
Neg logit contributions
roads-0.012
vered-0.012
stack-0.011
ued-0.010
 tal-0.010
Token to
Token ID284
Feature activation-4.31e-03

Pos logit contributions
roads+0.015
vered+0.014
stack+0.014
ued+0.013
 tal+0.013
Neg logit contributions
bows-0.012
head-0.011
 queens-0.011
 germ-0.010
isha-0.010
Tokenally
Token ID453
Feature activation+2.58e-02

Pos logit contributions
head+0.055
bows+0.055
 queens+0.054
 germ+0.053
isha+0.053
Neg logit contributions
roads-0.048
vered-0.044
am-0.044
ieved-0.043
ulously-0.042
Token ate
Token ID15063
Feature activation+2.41e-02

Pos logit contributions
bows+0.036
head+0.034
 queens+0.033
 smell+0.031
isha+0.031
Neg logit contributions
roads-0.041
vered-0.037
stack-0.036
ued-0.034
 tal-0.032
Token all
Token ID477
Feature activation+1.64e-02

Pos logit contributions
bows+0.025
 she+0.025
 smell+0.024
head+0.024
 queens+0.023
Neg logit contributions
roads-0.046
vered-0.044
stack-0.041
ued-0.040
am-0.039
Token the
Token ID262
Feature activation+3.56e-02

Pos logit contributions
bows+0.026
head+0.025
 queens+0.025
 germ+0.024
isha+0.023
Neg logit contributions
roads-0.022
vered-0.021
stack-0.019
ulously-0.018
ued-0.018
Token y
Token ID331
Feature activation+3.56e-02

Pos logit contributions
bows+0.039
 queens+0.038
head+0.038
 germ+0.035
isha+0.035
Neg logit contributions
roads-0.063
vered-0.060
ued-0.056
stack-0.054
ulously-0.053
Tokenummy
Token ID13513
Feature activation+8.71e-02

Pos logit contributions
isha+0.056
 queens+0.053
bows+0.053
 germ+0.052
issy+0.052
Neg logit contributions
am-0.049
vered-0.046
ulously-0.044
ement-0.043
ised-0.043
Token cookies
Token ID14746
Feature activation+2.32e-02

Pos logit contributions
issy+0.120
isha+0.118
 queens+0.118
yt+0.110
ina+0.109
Neg logit contributions
vered-0.118
roads-0.115
ued-0.103
ulously-0.097
 pole-0.096
Token,
Token ID11
Feature activation+1.95e-02

Pos logit contributions
bows+0.029
head+0.028
 queens+0.027
 germ+0.026
isha+0.025
Neg logit contributions
roads-0.039
vered-0.037
stack-0.036
ued-0.033
 tal-0.032
Token and
Token ID290
Feature activation-1.37e-03

Pos logit contributions
bows+0.023
head+0.021
 queens+0.021
 germ+0.019
 smell+0.018
Neg logit contributions
roads-0.036
vered-0.034
stack-0.032
ued-0.030
 tal-0.029
Token then
Token ID788
Feature activation-9.58e-03

Pos logit contributions
roads+0.003
vered+0.002
stack+0.002
ued+0.002
 tal+0.002
Neg logit contributions
bows-0.002
head-0.001
 queens-0.001
 she-0.001
 smell-0.001
Token lay
Token ID3830
Feature activation-1.87e-04

Pos logit contributions
roads+0.021
vered+0.020
stack+0.020
ued+0.019
 tal+0.018
Neg logit contributions
bows-0.007
head-0.007
 queens-0.006
 she-0.006
 smell-0.006
Token They
Token ID1119
Feature activation+1.90e-02

Pos logit contributions
roads+0.014
vered+0.013
stack+0.012
ued+0.011
 tal+0.011
Neg logit contributions
bows-0.014
head-0.013
 queens-0.012
 germ-0.012
isha-0.011
Token both
Token ID1111
Feature activation-1.27e-02

Pos logit contributions
bows+0.024
head+0.022
 queens+0.022
 germ+0.021
 smell+0.020
Neg logit contributions
roads-0.033
vered-0.030
stack-0.029
ued-0.027
 tal-0.026
Token enjoyed
Token ID8359
Feature activation+5.95e-02

Pos logit contributions
roads+0.023
vered+0.021
stack+0.020
ued+0.019
 tal+0.018
Neg logit contributions
bows-0.016
head-0.014
 queens-0.014
 smell-0.014
 she-0.013
Token the
Token ID262
Feature activation+1.78e-02

Pos logit contributions
bows+0.087
head+0.082
 queens+0.081
 germ+0.076
isha+0.074
Neg logit contributions
roads-0.091
vered-0.085
stack-0.081
ued-0.075
 tal-0.072
Token y
Token ID331
Feature activation+3.23e-02

Pos logit contributions
bows+0.021
head+0.021
 queens+0.021
isha+0.019
issy+0.019
Neg logit contributions
roads-0.030
vered-0.027
stack-0.027
ued-0.026
ulously-0.025
Tokenummy
Token ID13513
Feature activation+8.71e-02

Pos logit contributions
isha+0.056
 Hanna+0.054
 queens+0.054
 germ+0.053
issy+0.052
Neg logit contributions
am-0.038
ement-0.036
ulously-0.033
vered-0.032
ised-0.032
Token cake
Token ID12187
Feature activation+4.45e-02

Pos logit contributions
issy+0.120
 queens+0.114
isha+0.113
head+0.106
bows+0.106
Neg logit contributions
roads-0.125
vered-0.116
 pole-0.109
ued-0.108
ement-0.107
Token and
Token ID290
Feature activation+1.27e-02

Pos logit contributions
head+0.073
 germ+0.071
 queens+0.070
bows+0.069
isha+0.067
Neg logit contributions
roads-0.049
stack-0.048
vered-0.045
 atop-0.039
 tal-0.039
Token had
Token ID550
Feature activation-2.39e-03

Pos logit contributions
bows+0.018
head+0.016
 queens+0.016
 germ+0.015
 smell+0.015
Neg logit contributions
roads-0.021
vered-0.019
stack-0.018
ued-0.017
 tal-0.016
Token a
Token ID257
Feature activation+2.89e-03

Pos logit contributions
roads+0.004
vered+0.003
stack+0.003
ulously+0.003
ued+0.003
Neg logit contributions
bows-0.003
head-0.003
 queens-0.003
 germ-0.003
isha-0.003
Token great
Token ID1049
Feature activation+2.55e-02

Pos logit contributions
bows+0.005
head+0.004
 queens+0.004
issy+0.004
angers+0.004
Neg logit contributions
vered-0.003
roads-0.003
<|endoftext|>-0.003
 pole-0.003
 net-0.003
Token stars
Token ID5788
Feature activation+2.80e-02

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
ued+0.001
ulously+0.001
Neg logit contributions
bows-0.001
head-0.001
 queens-0.001
 germ-0.001
isha-0.001
Token,
Token ID11
Feature activation+7.11e-02

Pos logit contributions
head+0.042
bows+0.042
 germ+0.042
 queens+0.041
issy+0.040
Neg logit contributions
roads-0.036
vered-0.034
stack-0.033
 atop-0.031
ued-0.029
Token hearts
Token ID11954
Feature activation+4.14e-02

Pos logit contributions
bows+0.084
head+0.082
 queens+0.073
 germ+0.073
isha+0.073
Neg logit contributions
roads-0.120
vered-0.111
stack-0.104
ued-0.097
ulously-0.097
Token,
Token ID11
Feature activation+7.57e-02

Pos logit contributions
head+0.063
 germ+0.061
 queens+0.061
isha+0.058
bows+0.058
Neg logit contributions
roads-0.050
vered-0.048
stack-0.046
 atop-0.044
ued-0.041
Token flowers
Token ID12734
Feature activation+3.14e-02

Pos logit contributions
head+0.098
bows+0.092
isha+0.089
 germ+0.088
issy+0.087
Neg logit contributions
roads-0.111
vered-0.103
stack-0.096
 atop-0.092
cks-0.091
Token,
Token ID11
Feature activation+8.70e-02

Pos logit contributions
head+0.046
bows+0.044
 germ+0.044
 queens+0.044
isha+0.042
Neg logit contributions
roads-0.042
stack-0.040
vered-0.039
 atop-0.034
ued-0.034
Token and
Token ID290
Feature activation+3.87e-02

Pos logit contributions
head+0.124
isha+0.113
bows+0.112
 germ+0.112
issy+0.111
Neg logit contributions
roads-0.108
vered-0.102
stack-0.095
 atop-0.094
cks-0.092
Token animals
Token ID4695
Feature activation+1.19e-02

Pos logit contributions
bows+0.042
head+0.041
 queens+0.037
isha+0.036
 germ+0.036
Neg logit contributions
roads-0.070
vered-0.066
stack-0.062
ued-0.058
 tal-0.058
Token.
Token ID13
Feature activation+1.30e-02

Pos logit contributions
bows+0.016
head+0.016
 queens+0.015
 germ+0.014
isha+0.014
Neg logit contributions
roads-0.019
vered-0.017
stack-0.017
ued-0.015
 tal-0.015
Token She
Token ID1375
Feature activation+2.19e-02

Pos logit contributions
bows+0.013
head+0.012
 queens+0.011
 germ+0.011
 spill+0.011
Neg logit contributions
roads-0.025
stack-0.023
vered-0.023
ued-0.020
 edge-0.020
Token saw
Token ID2497
Feature activation-3.98e-03

Pos logit contributions
bows+0.033
head+0.031
 queens+0.031
 germ+0.029
isha+0.029
Neg logit contributions
roads-0.032
vered-0.030
stack-0.029
ued-0.027
 tal-0.025
Token They
Token ID1119
Feature activation+2.87e-02

Pos logit contributions
stack+0.006
roads+0.006
 Fortunately+0.006
vered+0.006
am+0.006
Neg logit contributions
 queens-0.004
 germ-0.004
bows-0.004
head-0.004
 spill-0.003
Token both
Token ID1111
Feature activation-8.36e-03

Pos logit contributions
bows+0.047
head+0.043
 queens+0.041
 germ+0.041
isha+0.037
Neg logit contributions
roads-0.038
stack-0.037
vered-0.036
ued-0.033
ulously-0.032
Token enjoyed
Token ID8359
Feature activation+5.96e-02

Pos logit contributions
roads+0.014
vered+0.013
stack+0.013
ued+0.012
 tal+0.011
Neg logit contributions
bows-0.011
head-0.010
 queens-0.010
 smell-0.009
isha-0.009
Token the
Token ID262
Feature activation+2.83e-02

Pos logit contributions
bows+0.099
head+0.093
 queens+0.089
issy+0.088
 germ+0.087
Neg logit contributions
roads-0.078
vered-0.073
stack-0.071
ued-0.063
ulously-0.061
Token y
Token ID331
Feature activation+3.68e-02

Pos logit contributions
bows+0.032
head+0.030
 queens+0.030
issy+0.028
 germ+0.028
Neg logit contributions
roads-0.051
vered-0.047
stack-0.045
ued-0.044
ulously-0.043
Tokenummy
Token ID13513
Feature activation+8.69e-02

Pos logit contributions
 Hanna+0.062
bows+0.062
isha+0.061
 queens+0.061
issy+0.060
Neg logit contributions
am-0.044
ement-0.040
vered-0.037
ulously-0.036
ised-0.036
Token dessert
Token ID23084
Feature activation+3.60e-02

Pos logit contributions
issy+0.119
 queens+0.111
bows+0.110
isha+0.109
 germ+0.103
Neg logit contributions
roads-0.130
vered-0.125
ued-0.116
ulously-0.110
stack-0.107
Token.
Token ID13
Feature activation-1.66e-02

Pos logit contributions
head+0.060
 germ+0.059
bows+0.058
COM+0.058
issy+0.057
Neg logit contributions
stack-0.037
roads-0.036
vered-0.035
 pole-0.031
 atop-0.029
Token
Token ID198
Feature activation-4.98e-03

Pos logit contributions
roads+0.021
stack+0.020
vered+0.020
ued+0.019
ulously+0.018
Neg logit contributions
 queens-0.026
bows-0.026
 germ-0.026
head-0.025
 spill-0.024
Token
Token ID198
Feature activation+1.30e-02

Pos logit contributions
roads+0.007
vered+0.007
stack+0.006
ishly+0.006
used+0.006
Neg logit contributions
bows-0.007
head-0.007
 she-0.007
isha-0.007
 queens-0.007
TokenAfter
Token ID3260
Feature activation+2.62e-02

Pos logit contributions
bows+0.022
 germ+0.020
head+0.020
 queens+0.020
isha+0.019
Neg logit contributions
roads-0.017
vered-0.016
ued-0.015
stack-0.015
ulously-0.014
Token his
Token ID465
Feature activation-1.89e-02

Pos logit contributions
roads+0.000
vered+0.000
ued+0.000
stack+0.000
used+0.000
Neg logit contributions
 she-0.000
 smell-0.000
 germ-0.000
bows-0.000
head-0.000
Token mom
Token ID1995
Feature activation+1.51e-02

Pos logit contributions
roads+0.046
vered+0.042
ued+0.039
stack+0.039
ieved+0.038
Neg logit contributions
 smell-0.014
 germ-0.012
 queens-0.012
bows-0.012
 princess-0.012
Token ate
Token ID15063
Feature activation+3.21e-02

Pos logit contributions
bows+0.020
head+0.019
 queens+0.019
 germ+0.018
isha+0.017
Neg logit contributions
roads-0.024
vered-0.023
stack-0.022
ued-0.020
ulously-0.020
Token the
Token ID262
Feature activation+4.76e-02

Pos logit contributions
 smell+0.033
 she+0.031
bows+0.030
head+0.030
 tea+0.029
Neg logit contributions
roads-0.064
vered-0.061
stack-0.057
ued-0.057
used-0.055
Token y
Token ID331
Feature activation+2.97e-02

Pos logit contributions
bows+0.048
head+0.044
 queens+0.043
 germ+0.039
isha+0.038
Neg logit contributions
roads-0.094
vered-0.089
stack-0.086
ued-0.081
 tal-0.079
Tokenummy
Token ID13513
Feature activation+8.65e-02

Pos logit contributions
 queens+0.046
bows+0.045
isha+0.045
 Hanna+0.044
 germ+0.043
Neg logit contributions
am-0.039
ement-0.038
vered-0.037
ulously-0.036
ised-0.035
Token cake
Token ID12187
Feature activation+4.67e-02

Pos logit contributions
 queens+0.109
bows+0.106
issy+0.102
head+0.096
 germ+0.094
Neg logit contributions
roads-0.139
vered-0.132
 pole-0.123
ued-0.122
stack-0.118
Token together
Token ID1978
Feature activation+1.68e-02

Pos logit contributions
bows+0.066
head+0.062
 queens+0.061
 germ+0.058
isha+0.056
Neg logit contributions
roads-0.072
vered-0.067
stack-0.065
ued-0.060
 tal-0.058
Token.
Token ID13
Feature activation+7.52e-03

Pos logit contributions
bows+0.015
 she+0.014
 smell+0.013
head+0.013
 because+0.012
Neg logit contributions
roads-0.036
vered-0.033
stack-0.032
ulously-0.031
ued-0.031
Token Tim
Token ID5045
Feature activation+3.78e-03

Pos logit contributions
bows+0.009
head+0.008
 queens+0.008
 germ+0.007
isha+0.007
Neg logit contributions
roads-0.014
vered-0.013
stack-0.012
ued-0.012
 tal-0.011
Token felt
Token ID2936
Feature activation+2.40e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
isha+0.005
 germ+0.005
Neg logit contributions
roads-0.006
vered-0.005
stack-0.005
ued-0.005
 tal-0.005
Token happy
Token ID3772
Feature activation+2.16e-02

Pos logit contributions
bows+0.024
head+0.022
 queens+0.021
isha+0.020
 germ+0.020
Neg logit contributions
roads-0.027
vered-0.025
stack-0.024
ued-0.023
ulously-0.022
Token and
Token ID290
Feature activation-1.10e-02

Pos logit contributions
bows+0.037
head+0.034
issy+0.033
isha+0.032
 queens+0.032
Neg logit contributions
roads-0.026
vered-0.024
stack-0.023
 tal-0.021
 triumph-0.020
Token loved
Token ID6151
Feature activation+3.20e-02

Pos logit contributions
roads+0.015
vered+0.014
stack+0.014
ued+0.013
am+0.012
Neg logit contributions
bows-0.017
head-0.016
 queens-0.016
isha-0.015
 germ-0.015
Token as
Token ID355
Feature activation+5.34e-03

Pos logit contributions
bows+0.041
head+0.038
 queens+0.036
issy+0.035
 germ+0.034
Neg logit contributions
roads-0.053
vered-0.050
stack-0.048
ued-0.043
 tal-0.043
Token they
Token ID484
Feature activation+2.11e-02

Pos logit contributions
bows+0.006
head+0.005
COM+0.005
 smell+0.005
 germ+0.005
Neg logit contributions
vered-0.009
roads-0.008
 other-0.008
aroo-0.008
 inner-0.008
Token finished
Token ID5201
Feature activation+8.63e-02

Pos logit contributions
bows+0.028
head+0.026
 queens+0.026
 germ+0.024
isha+0.024
Neg logit contributions
roads-0.035
vered-0.032
stack-0.031
ued-0.029
 tal-0.028
Token reading
Token ID3555
Feature activation+2.98e-02

Pos logit contributions
head+0.114
bows+0.114
 queens+0.107
 germ+0.099
issy+0.097
Neg logit contributions
roads-0.139
vered-0.130
stack-0.122
ued-0.113
am-0.113
Token the
Token ID262
Feature activation+3.19e-02

Pos logit contributions
bows+0.038
head+0.033
 queens+0.033
 germ+0.030
 smell+0.030
Neg logit contributions
roads-0.053
vered-0.050
stack-0.048
ued-0.046
ulously-0.044
Token story
Token ID1621
Feature activation+5.20e-02

Pos logit contributions
bows+0.038
head+0.034
 queens+0.033
 germ+0.032
 smell+0.031
Neg logit contributions
roads-0.058
vered-0.056
stack-0.054
ued-0.050
ulously-0.049
Token together
Token ID1978
Feature activation+1.44e-02

Pos logit contributions
head+0.076
 queens+0.076
bows+0.075
 germ+0.075
isha+0.071
Neg logit contributions
roads-0.069
vered-0.062
stack-0.060
ued-0.057
am-0.052
Token.
Token ID13
Feature activation-7.09e-03

Pos logit contributions
bows+0.015
 she+0.013
head+0.012
 queens+0.012
 smell+0.012
Neg logit contributions
roads-0.030
vered-0.027
stack-0.026
ued-0.025
ulously-0.025
Token games
Token ID1830
Feature activation+2.91e-02

Pos logit contributions
bows+0.017
head+0.016
 smell+0.016
 fashion+0.015
 queens+0.015
Neg logit contributions
roads-0.023
vered-0.021
stack-0.021
 tal-0.020
ulously-0.019
Token,
Token ID11
Feature activation+3.16e-02

Pos logit contributions
bows+0.036
head+0.032
 queens+0.032
 smell+0.029
 she+0.029
Neg logit contributions
roads-0.052
vered-0.049
stack-0.047
ued-0.044
ulously-0.044
Token ate
Token ID15063
Feature activation+5.11e-02

Pos logit contributions
bows+0.042
head+0.040
 queens+0.039
 germ+0.037
isha+0.036
Neg logit contributions
roads-0.051
vered-0.048
stack-0.046
ued-0.043
ulously-0.041
Token the
Token ID262
Feature activation+3.73e-02

Pos logit contributions
bows+0.057
head+0.052
 queens+0.051
 smell+0.047
 germ+0.046
Neg logit contributions
roads-0.097
vered-0.091
stack-0.088
ued-0.083
 tal-0.080
Token y
Token ID331
Feature activation+2.90e-02

Pos logit contributions
bows+0.031
head+0.026
 queens+0.025
 smell+0.025
 germ+0.021
Neg logit contributions
roads-0.083
vered-0.081
stack-0.078
 tal-0.073
ued-0.072
Tokenummy
Token ID13513
Feature activation+8.62e-02

Pos logit contributions
isha+0.046
issy+0.044
 germ+0.044
 queens+0.043
 Hanna+0.043
Neg logit contributions
am-0.037
ement-0.035
vered-0.034
ulously-0.033
ised-0.032
Token cake
Token ID12187
Feature activation+4.94e-02

Pos logit contributions
issy+0.097
bows+0.097
 queens+0.096
isha+0.094
head+0.093
Neg logit contributions
roads-0.145
vered-0.134
ued-0.126
stack-0.123
 pole-0.120
Token,
Token ID11
Feature activation+3.68e-02

Pos logit contributions
bows+0.068
head+0.067
 queens+0.065
 germ+0.063
isha+0.061
Neg logit contributions
roads-0.075
vered-0.069
stack-0.068
ued-0.061
 tal-0.059
Token and
Token ID290
Feature activation+1.20e-02

Pos logit contributions
bows+0.045
head+0.042
 queens+0.040
 germ+0.038
isha+0.037
Neg logit contributions
roads-0.064
vered-0.060
stack-0.059
ued-0.054
ulously-0.053
Token had
Token ID550
Feature activation+2.54e-03

Pos logit contributions
bows+0.016
head+0.015
 queens+0.014
 germ+0.013
isha+0.013
Neg logit contributions
roads-0.020
vered-0.019
stack-0.018
ued-0.017
 tal-0.016
Token lots
Token ID6041
Feature activation+4.27e-02

Pos logit contributions
bows+0.004
head+0.003
 queens+0.003
 germ+0.003
isha+0.003
Neg logit contributions
roads-0.004
vered-0.004
stack-0.003
ued-0.003
ulously-0.003
Token
Token ID198
Feature activation+1.22e-02

Pos logit contributions
vered+0.006
roads+0.006
stack+0.006
ishly+0.006
iped+0.006
Neg logit contributions
 she-0.005
head-0.005
 She-0.005
isha-0.005
L-0.004
TokenHe
Token ID1544
Feature activation-1.48e-04

Pos logit contributions
head+0.017
bows+0.017
 queens+0.017
isha+0.016
 she+0.016
Neg logit contributions
roads-0.017
vered-0.017
stack-0.016
ued-0.015
 tal-0.015
Token took
Token ID1718
Feature activation-1.46e-03

Pos logit contributions
roads+0.000
vered+0.000
stack+0.000
ued+0.000
used+0.000
Neg logit contributions
bows-0.000
head-0.000
 smell-0.000
 queens-0.000
isha-0.000
Token out
Token ID503
Feature activation+9.88e-03

Pos logit contributions
roads+0.002
stack+0.002
vered+0.002
ued+0.002
ishly+0.002
Neg logit contributions
bows-0.002
head-0.002
 queens-0.002
 smell-0.002
isha-0.002
Token the
Token ID262
Feature activation+3.20e-02

Pos logit contributions
bows+0.016
head+0.015
 queens+0.015
 germ+0.014
isha+0.014
Neg logit contributions
roads-0.014
vered-0.013
stack-0.012
ued-0.011
 tal-0.011
Token finished
Token ID5201
Feature activation+8.61e-02

Pos logit contributions
bows+0.038
 smell+0.035
head+0.035
 spill+0.032
 queens+0.032
Neg logit contributions
roads-0.059
vered-0.057
stack-0.054
 tal-0.050
am-0.049
Token dough
Token ID15756
Feature activation+1.66e-02

Pos logit contributions
bows+0.095
head+0.089
 queens+0.085
 germ+0.080
 smell+0.079
Neg logit contributions
roads-0.161
vered-0.153
stack-0.148
ued-0.138
ulously-0.134
Token and
Token ID290
Feature activation+1.65e-04

Pos logit contributions
bows+0.019
head+0.017
 queens+0.017
 germ+0.015
 smell+0.015
Neg logit contributions
roads-0.031
vered-0.029
stack-0.027
ued-0.026
ulously-0.026
Token showed
Token ID3751
Feature activation-9.88e-03

Pos logit contributions
bows+0.000
head+0.000
 queens+0.000
 smell+0.000
 she+0.000
Neg logit contributions
roads-0.000
vered-0.000
stack-0.000
ued-0.000
 tal-0.000
Token everyone
Token ID2506
Feature activation+2.87e-02

Pos logit contributions
roads+0.020
stack+0.019
vered+0.018
 afloat+0.017
ued+0.016
Neg logit contributions
head-0.010
 she-0.009
 queens-0.009
 smell-0.009
bows-0.009
Token.
Token ID13
Feature activation+2.72e-03

Pos logit contributions
bows+0.047
head+0.044
 queens+0.043
 germ+0.041
isha+0.040
Neg logit contributions
roads-0.039
vered-0.036
stack-0.034
ued-0.031
ulously-0.029
Token down
Token ID866
Feature activation+1.43e-02

Pos logit contributions
bows+0.024
head+0.023
 queens+0.023
 smell+0.022
 she+0.022
Neg logit contributions
roads-0.027
vered-0.025
ued-0.023
stack-0.023
 tal-0.023
Token and
Token ID290
Feature activation-9.46e-04

Pos logit contributions
bows+0.021
head+0.020
 queens+0.020
 germ+0.019
issy+0.018
Neg logit contributions
roads-0.021
vered-0.019
stack-0.019
ued-0.017
ulously-0.016
Token ate
Token ID15063
Feature activation+3.93e-02

Pos logit contributions
roads+0.002
vered+0.002
stack+0.001
ued+0.001
 tal+0.001
Neg logit contributions
bows-0.001
head-0.001
 queens-0.001
 smell-0.001
 she-0.001
Token the
Token ID262
Feature activation+3.81e-02

Pos logit contributions
bows+0.055
head+0.052
 queens+0.051
 smell+0.048
 germ+0.047
Neg logit contributions
roads-0.063
vered-0.058
stack-0.056
ued-0.052
 tal-0.050
Token y
Token ID331
Feature activation+2.93e-02

Pos logit contributions
bows+0.034
head+0.031
 queens+0.030
 germ+0.027
isha+0.026
Neg logit contributions
roads-0.079
vered-0.075
stack-0.073
ued-0.069
 tal-0.067
Tokenummy
Token ID13513
Feature activation+8.61e-02

Pos logit contributions
bows+0.046
 Hanna+0.046
 queens+0.044
 Margaret+0.042
aila+0.042
Neg logit contributions
am-0.041
ulously-0.035
vered-0.035
ement-0.034
 tal-0.034
Token pasta
Token ID26296
Feature activation+3.04e-02

Pos logit contributions
bows+0.113
 queens+0.106
 Hanna+0.104
issy+0.104
head+0.097
Neg logit contributions
roads-0.129
vered-0.120
 pole-0.115
am-0.112
 edge-0.111
Token together
Token ID1978
Feature activation+1.89e-02

Pos logit contributions
bows+0.048
head+0.047
 queens+0.046
 germ+0.046
isha+0.045
Neg logit contributions
roads-0.038
stack-0.035
vered-0.035
ued-0.031
am-0.030
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
bows+0.023
head+0.020
 queens+0.020
 she+0.019
 smell+0.019
Neg logit contributions
roads-0.035
vered-0.032
stack-0.031
ued-0.029
ulously-0.029
Token Lucy
Token ID22162
Feature activation+1.47e-02

Pos logit contributions
roads+0.019
vered+0.018
stack+0.017
ued+0.016
ulously+0.015
Neg logit contributions
bows-0.021
head-0.020
 queens-0.020
 germ-0.020
isha-0.018
Token's
Token ID338
Feature activation-1.23e-02

Pos logit contributions
bows+0.021
head+0.019
 queens+0.019
 germ+0.018
isha+0.018
Neg logit contributions
roads-0.023
vered-0.021
stack-0.020
ued-0.019
 tal-0.018
Token the
Token ID262
Feature activation-2.38e-03

Pos logit contributions
 she+0.010
bows+0.010
 queens+0.009
 fashion+0.009
head+0.009
Neg logit contributions
roads-0.015
vered-0.015
stack-0.014
ued-0.014
iped-0.014
Token hill
Token ID12788
Feature activation-1.65e-02

Pos logit contributions
vered+0.004
roads+0.004
iped+0.004
am+0.004
ulously+0.004
Neg logit contributions
bows-0.003
 smell-0.002
head-0.002
 queens-0.002
 fashion-0.002
Token.
Token ID13
Feature activation-2.29e-02

Pos logit contributions
vered+0.033
roads+0.032
 wounds+0.030
ulously+0.030
iped+0.030
Neg logit contributions
bows-0.016
 she-0.014
head-0.014
 queens-0.012
 because-0.012
Token<|endoftext|>
Token ID50256
Feature activation-8.65e-03

Pos logit contributions
roads+0.037
vered+0.036
stack+0.032
ued+0.031
iped+0.030
Neg logit contributions
bows-0.030
head-0.029
isha-0.027
 she-0.027
 She-0.027
TokenM
Token ID44
Feature activation+2.15e-02

Pos logit contributions
roads+0.016
vered+0.016
 wounds+0.015
stack+0.014
iped+0.014
Neg logit contributions
bows-0.010
head-0.009
 She-0.009
 she-0.009
isha-0.008
Tokenomm
Token ID2002
Feature activation+8.60e-02

Pos logit contributions
bows+0.029
head+0.029
 queens+0.028
isha+0.027
issy+0.027
Neg logit contributions
roads-0.034
vered-0.033
stack-0.030
ued-0.027
iped-0.027
Tokena
Token ID64
Feature activation+1.40e-02

Pos logit contributions
bows+0.110
head+0.100
 queens+0.096
 germ+0.092
 smell+0.087
Neg logit contributions
roads-0.146
vered-0.140
stack-0.132
ued-0.127
am-0.124
Token and
Token ID290
Feature activation-6.29e-03

Pos logit contributions
bows+0.016
head+0.015
 queens+0.014
isha+0.013
 she+0.013
Neg logit contributions
roads-0.026
vered-0.024
stack-0.023
ued-0.022
ulously-0.022
Token Tom
Token ID4186
Feature activation+3.67e-03

Pos logit contributions
roads+0.011
vered+0.010
stack+0.010
 tal+0.009
ued+0.009
Neg logit contributions
bows-0.008
 queens-0.007
head-0.007
 germ-0.006
isha-0.006
Token were
Token ID547
Feature activation+2.63e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.006
vered-0.005
stack-0.005
ued-0.005
ulously-0.005
Token on
Token ID319
Feature activation-9.35e-03

Pos logit contributions
bows+0.033
head+0.032
 queens+0.031
isha+0.030
 she+0.029
Neg logit contributions
roads-0.044
vered-0.042
stack-0.040
 tal-0.037
ued-0.037
Token
Token ID198
Feature activation+1.58e-02

Pos logit contributions
vered+0.012
roads+0.012
stack+0.011
ishly+0.011
iped+0.011
Neg logit contributions
 She-0.005
 she-0.005
head-0.005
isha-0.005
 Lilly-0.005
TokenThey
Token ID2990
Feature activation+2.57e-02

Pos logit contributions
bows+0.022
head+0.021
 queens+0.021
isha+0.019
 germ+0.019
Neg logit contributions
roads-0.025
vered-0.024
stack-0.023
ued-0.021
 tal-0.020
Token ate
Token ID15063
Feature activation+3.42e-02

Pos logit contributions
bows+0.029
head+0.028
 queens+0.027
 smell+0.026
isha+0.026
Neg logit contributions
roads-0.047
vered-0.044
stack-0.042
ued-0.039
 tal-0.038
Token the
Token ID262
Feature activation+4.01e-02

Pos logit contributions
bows+0.039
head+0.038
 smell+0.037
 she+0.036
 queens+0.035
Neg logit contributions
roads-0.064
vered-0.059
stack-0.056
ued-0.054
used-0.053
Token y
Token ID331
Feature activation+2.91e-02

Pos logit contributions
bows+0.036
head+0.033
 queens+0.032
 germ+0.028
isha+0.028
Neg logit contributions
roads-0.083
vered-0.079
stack-0.076
ued-0.072
ulously-0.070
Tokenummy
Token ID13513
Feature activation+8.59e-02

Pos logit contributions
bows+0.046
 Hanna+0.045
 queens+0.044
isha+0.042
aila+0.042
Neg logit contributions
am-0.039
ulously-0.036
vered-0.035
ement-0.033
ised-0.033
Token pasta
Token ID26296
Feature activation+2.86e-02

Pos logit contributions
bows+0.113
 queens+0.107
 Hanna+0.104
issy+0.102
isha+0.097
Neg logit contributions
roads-0.127
vered-0.120
 pole-0.116
am-0.112
 tal-0.112
Token together
Token ID1978
Feature activation+1.61e-02

Pos logit contributions
bows+0.040
head+0.038
 queens+0.038
 germ+0.036
isha+0.035
Neg logit contributions
roads-0.043
vered-0.040
stack-0.039
ued-0.036
 tal-0.035
Token.
Token ID13
Feature activation-1.37e-03

Pos logit contributions
bows+0.015
head+0.014
 she+0.013
 smell+0.013
 queens+0.013
Neg logit contributions
roads-0.034
vered-0.031
stack-0.030
ued-0.029
ulously-0.028
Token Dad
Token ID17415
Feature activation+2.28e-02

Pos logit contributions
roads+0.002
vered+0.002
stack+0.002
ued+0.002
ulously+0.002
Neg logit contributions
bows-0.002
head-0.002
 queens-0.002
 germ-0.002
isha-0.002
Token smiled
Token ID13541
Feature activation+2.52e-02

Pos logit contributions
bows+0.033
head+0.031
 queens+0.030
 germ+0.029
isha+0.029
Neg logit contributions
roads-0.035
vered-0.032
stack-0.031
ued-0.029
 tal-0.027
Token played
Token ID2826
Feature activation+1.26e-02

Pos logit contributions
bows+0.033
 queens+0.030
 smell+0.029
head+0.028
 she+0.028
Neg logit contributions
roads-0.052
vered-0.049
stack-0.045
 tal-0.044
ued-0.043
Token games
Token ID1830
Feature activation+2.76e-02

Pos logit contributions
bows+0.017
head+0.016
 queens+0.015
 smell+0.015
 she+0.014
Neg logit contributions
roads-0.021
vered-0.020
stack-0.019
 tal-0.018
used-0.018
Token,
Token ID11
Feature activation+5.01e-02

Pos logit contributions
bows+0.032
head+0.029
 queens+0.028
 germ+0.026
isha+0.025
Neg logit contributions
roads-0.051
vered-0.048
stack-0.046
ued-0.044
ulously-0.043
Token ate
Token ID15063
Feature activation+5.38e-02

Pos logit contributions
bows+0.065
head+0.062
 queens+0.059
 germ+0.057
isha+0.057
Neg logit contributions
roads-0.081
vered-0.075
stack-0.075
ued-0.067
ulously-0.064
Token y
Token ID331
Feature activation+2.81e-02

Pos logit contributions
bows+0.065
head+0.061
 queens+0.059
 germ+0.056
isha+0.055
Neg logit contributions
roads-0.094
vered-0.089
stack-0.085
ued-0.080
ulously-0.077
Tokenummy
Token ID13513
Feature activation+8.54e-02

Pos logit contributions
 writer+0.044
isha+0.044
aila+0.044
 germ+0.043
issy+0.043
Neg logit contributions
am-0.040
vered-0.031
ised-0.030
ement-0.030
aded-0.029
Token cake
Token ID12187
Feature activation+6.03e-02

Pos logit contributions
issy+0.140
aila+0.130
illian+0.129
ina+0.125
isha+0.125
Neg logit contributions
vered-0.088
roads-0.086
am-0.081
 skills-0.077
ued-0.077
Token,
Token ID11
Feature activation+4.90e-02

Pos logit contributions
head+0.088
 germ+0.086
 queens+0.085
bows+0.082
issy+0.081
Neg logit contributions
roads-0.075
stack-0.073
vered-0.067
am-0.063
 pole-0.062
Token and
Token ID290
Feature activation+8.20e-03

Pos logit contributions
bows+0.061
head+0.059
 queens+0.055
 germ+0.054
isha+0.054
Neg logit contributions
roads-0.080
stack-0.075
vered-0.074
ued-0.067
ulously-0.065
Token had
Token ID550
Feature activation+3.34e-03

Pos logit contributions
bows+0.011
head+0.010
 queens+0.010
 germ+0.009
isha+0.009
Neg logit contributions
roads-0.014
vered-0.013
stack-0.012
ued-0.011
ulously-0.011
Token lots
Token ID6041
Feature activation+4.55e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.004
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.005
vered-0.005
stack-0.004
ued-0.004
ulously-0.004
Token started
Token ID2067
Feature activation+2.13e-02

Pos logit contributions
bows+0.017
head+0.016
issy+0.015
 smell+0.015
isha+0.015
Neg logit contributions
roads-0.028
vered-0.025
stack-0.024
 tal-0.023
cks-0.023
Token to
Token ID284
Feature activation+6.27e-04

Pos logit contributions
bows+0.026
head+0.024
 queens+0.024
 germ+0.022
isha+0.022
Neg logit contributions
roads-0.037
vered-0.035
stack-0.034
ued-0.032
 tal-0.031
Token pack
Token ID2353
Feature activation+9.98e-03

Pos logit contributions
bows+0.001
 smell+0.001
 spill+0.001
head+0.001
 fashion+0.001
Neg logit contributions
roads-0.001
vered-0.001
stack-0.001
 tal-0.001
ued-0.001
Token all
Token ID477
Feature activation+1.48e-02

Pos logit contributions
bows+0.011
head+0.010
 smell+0.010
 fashion+0.010
 she+0.010
Neg logit contributions
roads-0.019
stack-0.018
vered-0.017
ued-0.016
used-0.016
Token of
Token ID286
Feature activation+2.26e-02

Pos logit contributions
bows+0.021
head+0.020
 queens+0.020
 germ+0.019
isha+0.018
Neg logit contributions
roads-0.023
vered-0.021
stack-0.020
ued-0.019
 tal-0.018
Token Jos
Token ID22568
Feature activation+8.45e-02

Pos logit contributions
bows+0.033
head+0.032
 queens+0.031
 germ+0.029
isha+0.029
Neg logit contributions
roads-0.034
vered-0.032
stack-0.030
ued-0.028
ulously-0.027
Tokenie
Token ID494
Feature activation+3.35e-02

Pos logit contributions
bows+0.092
head+0.088
 queens+0.083
isha+0.081
issy+0.078
Neg logit contributions
roads-0.155
stack-0.153
vered-0.149
 tal-0.135
ued-0.134
Tokenâ
Token ID22940
Feature activation+5.31e-03

Pos logit contributions
bows+0.045
head+0.044
 she+0.041
 queens+0.041
isha+0.041
Neg logit contributions
roads-0.052
stack-0.049
vered-0.047
ulously-0.044
ued-0.043
Token
Token ID26391
Feature activation+2.12e-02

Pos logit contributions
bows+0.008
head+0.008
 queens+0.007
 germ+0.007
isha+0.007
Neg logit contributions
roads-0.007
vered-0.007
stack-0.007
ued-0.006
 tal-0.006
Token
Token ID8151
Feature activation-6.69e-03

Pos logit contributions
 queens+0.029
bows+0.028
 germ+0.028
head+0.027
 smell+0.026
Neg logit contributions
roads-0.032
vered-0.030
stack-0.028
am-0.027
ued-0.026
Tokens
Token ID82
Feature activation+1.28e-02

Pos logit contributions
roads+0.013
vered+0.013
stack+0.012
 tal+0.011
ulously+0.011
Neg logit contributions
bows-0.007
 she-0.006
head-0.006
isha-0.005
 queens-0.005
Token.
Token ID13
Feature activation-8.73e-03

Pos logit contributions
 she+0.005
bows+0.005
 because+0.005
head+0.005
 smell+0.004
Neg logit contributions
roads-0.014
vered-0.012
stack-0.012
ulously-0.012
ued-0.012
Token He
Token ID679
Feature activation+2.13e-04

Pos logit contributions
roads+0.014
vered+0.014
stack+0.012
ued+0.012
cut+0.011
Neg logit contributions
head-0.011
bows-0.011
 She-0.011
 she-0.010
 Lilly-0.010
Token ate
Token ID15063
Feature activation+2.51e-02

Pos logit contributions
bows+0.000
head+0.000
 smell+0.000
 queens+0.000
 she+0.000
Neg logit contributions
roads-0.000
vered-0.000
stack-0.000
ued-0.000
 tal-0.000
Token the
Token ID262
Feature activation+4.00e-02

Pos logit contributions
head+0.025
 smell+0.025
bows+0.024
 she+0.024
 queens+0.024
Neg logit contributions
roads-0.050
vered-0.047
stack-0.045
ued-0.042
used-0.041
Token y
Token ID331
Feature activation+2.16e-02

Pos logit contributions
bows+0.040
head+0.035
 smell+0.034
 queens+0.033
 spill+0.030
Neg logit contributions
roads-0.084
vered-0.079
stack-0.077
 tal-0.071
ued-0.071
Tokenummy
Token ID13513
Feature activation+8.44e-02

Pos logit contributions
isha+0.032
bows+0.031
 queens+0.030
issy+0.029
 Hanna+0.029
Neg logit contributions
am-0.030
vered-0.030
ulously-0.030
 tal-0.029
iped-0.027
Token cookie
Token ID19751
Feature activation+1.67e-02

Pos logit contributions
isha+0.117
 queens+0.116
bows+0.115
issy+0.113
head+0.109
Neg logit contributions
roads-0.118
vered-0.115
ued-0.103
stack-0.102
ulously-0.099
Token and
Token ID290
Feature activation+1.20e-03

Pos logit contributions
bows+0.019
head+0.017
 queens+0.017
 she+0.015
 smell+0.015
Neg logit contributions
roads-0.031
vered-0.029
stack-0.028
ued-0.027
ulously-0.026
Token then
Token ID788
Feature activation-1.56e-03

Pos logit contributions
bows+0.001
head+0.001
 queens+0.001
 she+0.001
 smell+0.001
Neg logit contributions
roads-0.002
vered-0.002
stack-0.002
ued-0.002
used-0.002
Token put
Token ID1234
Feature activation+1.46e-03

Pos logit contributions
roads+0.003
vered+0.003
stack+0.003
ued+0.003
 tal+0.002
Neg logit contributions
 she-0.002
bows-0.002
 smell-0.002
head-0.002
 queens-0.002
Token his
Token ID465
Feature activation-2.67e-02

Pos logit contributions
head+0.001
 smell+0.001
bows+0.001
 she+0.001
 queens+0.001
Neg logit contributions
roads-0.003
vered-0.003
stack-0.003
ued-0.003
used-0.002
Token eager
Token ID11069
Feature activation-9.32e-03

Pos logit contributions
roads+0.002
vered+0.002
stack+0.002
ued+0.002
am+0.002
Neg logit contributions
bows-0.002
head-0.002
 queens-0.002
 germ-0.002
issy-0.002
Token to
Token ID284
Feature activation+4.79e-03

Pos logit contributions
roads+0.013
vered+0.011
stack+0.011
 tal+0.010
am+0.010
Neg logit contributions
bows-0.014
isha-0.013
 queens-0.013
head-0.013
issy-0.013
Token eat
Token ID4483
Feature activation+2.59e-02

Pos logit contributions
bows+0.006
head+0.006
 queens+0.005
 germ+0.005
isha+0.005
Neg logit contributions
roads-0.008
vered-0.008
stack-0.008
ued-0.007
ulously-0.007
Token the
Token ID262
Feature activation+4.17e-02

Pos logit contributions
bows+0.032
head+0.029
 queens+0.029
 germ+0.027
isha+0.026
Neg logit contributions
roads-0.045
vered-0.043
stack-0.041
ued-0.039
 tal-0.037
Token y
Token ID331
Feature activation+2.38e-02

Pos logit contributions
bows+0.042
head+0.038
 queens+0.037
 germ+0.034
isha+0.033
Neg logit contributions
roads-0.082
vered-0.078
stack-0.075
ued-0.071
ulously-0.069
Tokenummy
Token ID13513
Feature activation+8.43e-02

Pos logit contributions
isha+0.039
bows+0.037
issy+0.037
 queens+0.036
 Hanna+0.036
Neg logit contributions
am-0.031
ement-0.027
vered-0.027
ulously-0.026
roads-0.026
Token cookies
Token ID14746
Feature activation+1.92e-02

Pos logit contributions
issy+0.108
bows+0.103
isha+0.101
 queens+0.099
head+0.094
Neg logit contributions
roads-0.135
vered-0.126
ued-0.117
stack-0.114
 edge-0.110
Token.
Token ID13
Feature activation-1.83e-02

Pos logit contributions
bows+0.024
head+0.022
 queens+0.021
 smell+0.020
 she+0.020
Neg logit contributions
roads-0.033
vered-0.032
stack-0.030
ued-0.028
ulously-0.028
Token She
Token ID1375
Feature activation+1.03e-02

Pos logit contributions
roads+0.042
vered+0.040
 afloat+0.037
cut+0.037
stack+0.036
Neg logit contributions
 She-0.013
bows-0.012
 she-0.012
head-0.010
 smell-0.010
Token ate
Token ID15063
Feature activation+2.73e-02

Pos logit contributions
bows+0.013
head+0.013
 queens+0.012
 germ+0.012
isha+0.012
Neg logit contributions
roads-0.017
vered-0.016
stack-0.015
ued-0.014
 tal-0.014
Token one
Token ID530
Feature activation-1.37e-02

Pos logit contributions
bows+0.037
head+0.035
 queens+0.033
 smell+0.032
 she+0.031
Neg logit contributions
roads-0.045
vered-0.042
stack-0.040
ued-0.037
 tal-0.036
Token.
Token ID13
Feature activation-3.87e-03

Pos logit contributions
bows+0.029
head+0.028
 queens+0.027
 germ+0.027
isha+0.026
Neg logit contributions
roads-0.023
vered-0.022
stack-0.021
ued-0.019
 tal-0.018
Token It
Token ID632
Feature activation+2.14e-02

Pos logit contributions
roads+0.008
vered+0.008
stack+0.008
ued+0.007
ulously+0.007
Neg logit contributions
bows-0.003
head-0.003
 queens-0.003
 germ-0.002
isha-0.002
Token looked
Token ID3114
Feature activation+3.56e-02

Pos logit contributions
bows+0.032
head+0.030
 queens+0.029
 germ+0.027
isha+0.027
Neg logit contributions
roads-0.032
vered-0.030
stack-0.029
ued-0.026
ulously-0.026
Token even
Token ID772
Feature activation+1.99e-02

Pos logit contributions
bows+0.046
head+0.042
 queens+0.042
issy+0.039
isha+0.039
Neg logit contributions
roads-0.059
vered-0.057
stack-0.052
ued-0.052
 tal-0.050
Token y
Token ID331
Feature activation+1.77e-02

Pos logit contributions
bows+0.025
 queens+0.024
head+0.024
 smell+0.024
 smells+0.022
Neg logit contributions
stack-0.034
roads-0.033
vered-0.033
ued-0.030
aroo-0.029
Tokenumm
Token ID13929
Feature activation+8.41e-02

Pos logit contributions
 germ+0.030
isha+0.030
 Hanna+0.029
bows+0.028
 writer+0.028
Neg logit contributions
am-0.022
ement-0.020
vered-0.019
iped-0.018
ised-0.018
Tokenier
Token ID959
Feature activation+2.48e-02

Pos logit contributions
 queens+0.127
bows+0.127
 germ+0.126
head+0.122
isha+0.121
Neg logit contributions
vered-0.100
roads-0.097
am-0.090
stack-0.089
 atop-0.085
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
bows+0.029
head+0.028
 queens+0.027
 germ+0.026
issy+0.026
Neg logit contributions
roads-0.042
vered-0.040
stack-0.039
 tal-0.035
ued-0.035
Token Lily
Token ID20037
Feature activation+1.21e-02

Pos logit contributions
roads+0.039
vered+0.037
stack+0.036
ued+0.034
 tal+0.033
Neg logit contributions
bows-0.009
head-0.008
 queens-0.007
 she-0.006
 germ-0.006
Token wanted
Token ID2227
Feature activation-1.94e-02

Pos logit contributions
bows+0.016
head+0.015
 queens+0.015
 smell+0.014
isha+0.014
Neg logit contributions
roads-0.020
vered-0.018
stack-0.018
ued-0.016
 tal-0.016
Token to
Token ID284
Feature activation-3.70e-03

Pos logit contributions
roads+0.031
vered+0.029
stack+0.028
ued+0.025
ulously+0.025
Neg logit contributions
bows-0.027
head-0.025
 queens-0.023
 germ-0.022
issy-0.022
Token porch
Token ID33179
Feature activation+3.51e-02

Pos logit contributions
bows+0.035
head+0.032
 queens+0.031
 germ+0.029
 smell+0.029
Neg logit contributions
roads-0.064
vered-0.062
stack-0.057
ued-0.054
 tal-0.053
Token,
Token ID11
Feature activation+2.99e-02

Pos logit contributions
bows+0.038
head+0.034
 she+0.031
 queens+0.031
 smell+0.029
Neg logit contributions
roads-0.068
vered-0.067
stack-0.060
 tal-0.059
ued-0.059
Token ate
Token ID15063
Feature activation+4.36e-02

Pos logit contributions
bows+0.040
head+0.037
 queens+0.036
 germ+0.034
isha+0.033
Neg logit contributions
roads-0.049
vered-0.046
stack-0.045
ued-0.041
ulously-0.040
Token the
Token ID262
Feature activation+3.36e-02

Pos logit contributions
bows+0.056
head+0.053
 queens+0.051
 smell+0.049
 she+0.047
Neg logit contributions
roads-0.075
vered-0.071
stack-0.067
ued-0.063
 tal-0.061
Token y
Token ID331
Feature activation+3.22e-02

Pos logit contributions
bows+0.031
head+0.028
 queens+0.027
 germ+0.025
isha+0.024
Neg logit contributions
roads-0.069
vered-0.066
stack-0.064
ued-0.060
 tal-0.058
Tokenummy
Token ID13513
Feature activation+8.40e-02

Pos logit contributions
 queens+0.052
isha+0.051
aila+0.051
issy+0.049
 Hanna+0.049
Neg logit contributions
am-0.038
ement-0.036
ulously-0.034
vered-0.033
ised-0.033
Token cookies
Token ID14746
Feature activation+3.10e-02

Pos logit contributions
 queens+0.112
issy+0.107
isha+0.106
head+0.101
bows+0.099
Neg logit contributions
roads-0.122
vered-0.112
ued-0.107
stack-0.103
 pole-0.102
Token,
Token ID11
Feature activation+4.43e-02

Pos logit contributions
bows+0.042
head+0.040
 queens+0.039
 germ+0.037
isha+0.036
Neg logit contributions
roads-0.050
vered-0.046
stack-0.045
ued-0.042
 tal-0.040
Token and
Token ID290
Feature activation+1.81e-02

Pos logit contributions
bows+0.055
head+0.051
 queens+0.049
 germ+0.047
isha+0.046
Neg logit contributions
roads-0.075
vered-0.071
stack-0.069
ued-0.063
ulously-0.062
Token had
Token ID550
Feature activation+1.82e-03

Pos logit contributions
bows+0.023
head+0.021
 queens+0.021
 germ+0.020
 smell+0.019
Neg logit contributions
roads-0.031
vered-0.029
stack-0.028
ued-0.026
 tal-0.025
Token a
Token ID257
Feature activation+2.48e-03

Pos logit contributions
bows+0.002
head+0.002
 queens+0.002
 germ+0.002
isha+0.002
Neg logit contributions
roads-0.003
vered-0.003
stack-0.003
ued-0.003
 tal-0.002
Token help
Token ID1037
Feature activation-1.13e-02

Pos logit contributions
roads+0.021
vered+0.019
stack+0.019
ued+0.017
 tal+0.017
Neg logit contributions
bows-0.015
head-0.014
 queens-0.013
 germ-0.013
 smell-0.012
Token and
Token ID290
Feature activation-2.72e-03

Pos logit contributions
roads+0.016
vered+0.014
stack+0.014
 side+0.013
ulously+0.013
Neg logit contributions
bows-0.018
 queens-0.016
head-0.016
 germ-0.014
 designers-0.014
Token enjoy
Token ID2883
Feature activation+4.81e-02

Pos logit contributions
roads+0.005
vered+0.005
stack+0.005
ued+0.004
 tal+0.004
Neg logit contributions
bows-0.003
head-0.003
 she-0.003
 queens-0.003
 smell-0.003
Token the
Token ID262
Feature activation+2.58e-02

Pos logit contributions
bows+0.055
head+0.051
 queens+0.049
 germ+0.046
isha+0.044
Neg logit contributions
roads-0.089
vered-0.084
stack-0.081
ued-0.075
 tal-0.073
Token y
Token ID331
Feature activation+2.90e-02

Pos logit contributions
bows+0.023
head+0.021
 queens+0.020
 germ+0.018
isha+0.017
Neg logit contributions
roads-0.054
vered-0.051
stack-0.050
ued-0.047
 tal-0.046
Tokenummy
Token ID13513
Feature activation+8.38e-02

Pos logit contributions
bows+0.043
 Hanna+0.043
isha+0.043
issy+0.042
 queens+0.041
Neg logit contributions
am-0.040
ement-0.037
roads-0.036
vered-0.036
ulously-0.035
Token cake
Token ID12187
Feature activation+4.29e-02

Pos logit contributions
issy+0.106
bows+0.100
 queens+0.099
isha+0.097
head+0.096
Neg logit contributions
roads-0.133
vered-0.120
ued-0.112
stack-0.110
 pole-0.110
Token.
Token ID13
Feature activation-2.07e-03

Pos logit contributions
bows+0.064
head+0.062
 queens+0.060
 germ+0.059
isha+0.057
Neg logit contributions
roads-0.061
vered-0.055
stack-0.055
ued-0.048
 tal-0.046
Token<|endoftext|>
Token ID50256
Feature activation-9.83e-03

Pos logit contributions
stack+0.002
roads+0.001
ulously+0.001
am+0.001
 tal+0.001
Neg logit contributions
 queens-0.004
bows-0.004
head-0.004
 germ-0.004
 spill-0.004
TokenOnce
Token ID7454
Feature activation-2.86e-03

Pos logit contributions
roads+0.018
vered+0.018
stack+0.016
ishly+0.015
ued+0.015
Neg logit contributions
bows-0.012
head-0.011
 she-0.010
 She-0.010
 queens-0.010
Token upon
Token ID2402
Feature activation-2.53e-02

Pos logit contributions
roads+0.006
vered+0.006
stack+0.005
ued+0.005
iped+0.005
Neg logit contributions
bows-0.003
head-0.002
 she-0.002
 queens-0.002
isha-0.002
Token books
Token ID3835
Feature activation+2.34e-02

Pos logit contributions
bows+0.006
head+0.006
 queens+0.006
 smell+0.005
 germ+0.005
Neg logit contributions
roads-0.009
vered-0.008
stack-0.008
ued-0.007
ieved-0.007
Token,
Token ID11
Feature activation+6.76e-02

Pos logit contributions
bows+0.033
 queens+0.032
 germ+0.032
head+0.032
isha+0.031
Neg logit contributions
roads-0.035
stack-0.031
vered-0.031
ued-0.029
 atop-0.027
Token toys
Token ID14958
Feature activation+3.69e-02

Pos logit contributions
head+0.081
bows+0.081
isha+0.075
issy+0.073
 germ+0.072
Neg logit contributions
roads-0.107
vered-0.097
stack-0.087
 wounds-0.086
cut-0.084
Token,
Token ID11
Feature activation+7.85e-02

Pos logit contributions
head+0.056
 germ+0.056
bows+0.056
 queens+0.055
isha+0.055
Neg logit contributions
roads-0.047
stack-0.044
vered-0.043
ued-0.037
 atop-0.036
Token clothes
Token ID8242
Feature activation+4.18e-02

Pos logit contributions
head+0.101
isha+0.097
bows+0.095
issy+0.093
 germ+0.091
Neg logit contributions
roads-0.112
vered-0.104
 wounds-0.093
stack-0.091
cut-0.088
Token,
Token ID11
Feature activation+8.38e-02

Pos logit contributions
 queens+0.065
head+0.064
 germ+0.064
bows+0.062
isha+0.061
Neg logit contributions
roads-0.051
stack-0.048
vered-0.047
ued-0.042
 atop-0.041
Token and
Token ID290
Feature activation+3.44e-02

Pos logit contributions
head+0.117
isha+0.112
issy+0.108
bows+0.108
omm+0.105
Neg logit contributions
roads-0.106
vered-0.101
 wounds-0.091
stack-0.086
pe-0.086
Token candy
Token ID18550
Feature activation+5.34e-02

Pos logit contributions
bows+0.040
head+0.039
 queens+0.035
isha+0.035
issy+0.034
Neg logit contributions
roads-0.059
vered-0.056
stack-0.051
ued-0.049
 tal-0.048
Token.
Token ID13
Feature activation+3.51e-03

Pos logit contributions
head+0.086
 queens+0.083
bows+0.083
 germ+0.082
issy+0.080
Neg logit contributions
roads-0.062
vered-0.058
stack-0.055
ued-0.049
am-0.048
Token They
Token ID1119
Feature activation+2.38e-02

Pos logit contributions
bows+0.003
head+0.003
 queens+0.003
 germ+0.002
isha+0.002
Neg logit contributions
roads-0.007
vered-0.007
stack-0.007
ued-0.006
 tal-0.006
Token smiled
Token ID13541
Feature activation+2.89e-02

Pos logit contributions
bows+0.034
head+0.032
 queens+0.030
 germ+0.030
isha+0.028
Neg logit contributions
roads-0.037
vered-0.034
stack-0.033
ued-0.030
ulously-0.029
Token hands
Token ID2832
Feature activation-1.69e-02

Pos logit contributions
roads+0.044
stack+0.038
vered+0.034
ieved+0.032
ued+0.031
Neg logit contributions
bows-0.045
 smell-0.042
 spill-0.040
head-0.039
 fashion-0.038
Token too
Token ID1165
Feature activation-1.71e-02

Pos logit contributions
roads+0.035
vered+0.033
stack+0.033
 tal+0.030
ued+0.030
Neg logit contributions
bows-0.017
head-0.014
 smell-0.013
 queens-0.013
 she-0.013
Token.
Token ID13
Feature activation+1.51e-02

Pos logit contributions
roads+0.024
vered+0.023
stack+0.021
ued+0.020
 tal+0.019
Neg logit contributions
bows-0.026
head-0.024
 queens-0.024
 germ-0.023
isha-0.023
Token He
Token ID679
Feature activation+2.95e-03

Pos logit contributions
bows+0.013
head+0.013
 She+0.012
 she+0.012
 smell+0.011
Neg logit contributions
vered-0.033
roads-0.032
stack-0.030
ued-0.029
ieved-0.028
Token says
Token ID1139
Feature activation+7.58e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 smell+0.004
 germ+0.004
Neg logit contributions
roads-0.005
vered-0.004
stack-0.004
ued-0.004
 tal-0.004
Token brav
Token ID49025
Feature activation-8.92e-02

Pos logit contributions
head+0.008
bows+0.008
 queens+0.008
 she+0.008
 germ+0.007
Neg logit contributions
roads-0.015
stack-0.014
vered-0.014
ulously-0.013
ieved-0.012
Tokeno
Token ID78
Feature activation-1.82e-02

Pos logit contributions
roads+0.154
stack+0.142
vered+0.137
ued+0.130
used+0.121
Neg logit contributions
bows-0.120
head-0.110
 queens-0.104
 germ-0.099
 smell-0.095
Token.
Token ID13
Feature activation+1.74e-02

Pos logit contributions
roads+0.029
vered+0.027
stack+0.026
ued+0.024
 tal+0.023
Neg logit contributions
bows-0.026
head-0.024
 queens-0.023
 germ-0.022
isha-0.022
Token Tom
Token ID4186
Feature activation+1.04e-02

Pos logit contributions
head+0.019
 She+0.019
bows+0.018
 she+0.018
 queens+0.017
Neg logit contributions
vered-0.034
roads-0.032
stack-0.030
ulously-0.029
ued-0.029
Token and
Token ID290
Feature activation+8.01e-03

Pos logit contributions
bows+0.012
head+0.011
 queens+0.011
 germ+0.010
isha+0.010
Neg logit contributions
roads-0.019
vered-0.018
stack-0.017
ued-0.016
 tal-0.015
Token Anna
Token ID11735
Feature activation+1.04e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
 she+0.004
 smell+0.004
Neg logit contributions
roads-0.019
vered-0.018
stack-0.018
 tal-0.017
ued-0.017
Token and
Token ID290
Feature activation-5.70e-03

Pos logit contributions
roads+0.005
vered+0.005
stack+0.005
ued+0.005
ulously+0.004
Neg logit contributions
bows-0.004
head-0.004
 queens-0.004
 she-0.003
 smell-0.003
Token nig
Token ID44873
Feature activation-1.90e-02

Pos logit contributions
roads+0.010
vered+0.009
ued+0.009
ieved+0.008
stack+0.008
Neg logit contributions
bows-0.008
 smell-0.007
 queens-0.007
 she-0.007
head-0.007
Tokenella
Token ID12627
Feature activation-8.83e-03

Pos logit contributions
roads+0.032
vered+0.029
stack+0.028
ued+0.026
ulously+0.026
Neg logit contributions
bows-0.026
head-0.024
 queens-0.023
isha-0.022
 germ-0.021
Token and
Token ID290
Feature activation-3.83e-02

Pos logit contributions
roads+0.018
vered+0.016
stack+0.016
 afloat+0.015
ulously+0.015
Neg logit contributions
bows-0.008
head-0.008
 she-0.007
isha-0.007
 smell-0.006
Token f
Token ID277
Feature activation-2.37e-04

Pos logit contributions
roads+0.068
vered+0.064
stack+0.061
ued+0.058
ulously+0.057
Neg logit contributions
bows-0.043
head-0.043
 smell-0.042
 she-0.042
 queens-0.041
Tokenenn
Token ID1697
Feature activation-8.72e-02

Pos logit contributions
roads+0.000
stack+0.000
vered+0.000
 tal+0.000
 gru+0.000
Neg logit contributions
bows-0.000
head-0.000
isha-0.000
 queens-0.000
issy-0.000
Tokenel
Token ID417
Feature activation-4.41e-02

Pos logit contributions
roads+0.154
stack+0.139
 gru+0.131
 afloat+0.128
jack+0.123
Neg logit contributions
ina-0.103
isha-0.092
bows-0.091
 Nina-0.091
issy-0.091
Token and
Token ID290
Feature activation-3.59e-02

Pos logit contributions
roads+0.080
stack+0.069
vered+0.065
 afloat+0.065
ieved+0.062
Neg logit contributions
bows-0.054
head-0.049
isha-0.047
 she-0.046
issy-0.045
Token an
Token ID281
Feature activation-5.61e-02

Pos logit contributions
roads+0.064
vered+0.060
stack+0.057
ued+0.055
ulously+0.053
Neg logit contributions
bows-0.041
head-0.040
 smell-0.039
 she-0.039
 queens-0.038
Tokenise
Token ID786
Feature activation-3.49e-02

Pos logit contributions
roads+0.108
stack+0.104
vered+0.093
 afloat+0.088
 atop+0.085
Neg logit contributions
bows-0.056
head-0.056
 queens-0.054
isha-0.053
issy-0.051
Token and
Token ID290
Feature activation-3.41e-02

Pos logit contributions
roads+0.067
stack+0.060
vered+0.060
ued+0.055
ieved+0.054
Neg logit contributions
bows-0.036
head-0.035
 she-0.033
isha-0.032
 queens-0.030
Token agreed
Token ID4987
Feature activation-5.81e-04

Pos logit contributions
roads+0.028
vered+0.025
stack+0.025
ulously+0.022
cks+0.022
Neg logit contributions
bows-0.026
head-0.025
 queens-0.024
 she-0.023
 smell-0.023
Token to
Token ID284
Feature activation-1.84e-02

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
ued+0.001
 tal+0.001
Neg logit contributions
bows-0.001
head-0.001
 queens-0.001
 germ-0.001
 smell-0.001
Token give
Token ID1577
Feature activation-1.34e-02

Pos logit contributions
roads+0.035
vered+0.033
stack+0.030
ued+0.030
 tal+0.029
Neg logit contributions
 smell-0.019
bows-0.018
 she-0.017
 queens-0.017
head-0.017
Token her
Token ID607
Feature activation-1.76e-02

Pos logit contributions
roads+0.026
stack+0.024
vered+0.023
ued+0.023
cut+0.021
Neg logit contributions
 she-0.014
bows-0.014
 smell-0.013
head-0.012
 Lilly-0.012
Token her
Token ID607
Feature activation-1.20e-02

Pos logit contributions
roads+0.032
stack+0.030
vered+0.028
ued+0.027
iped+0.026
Neg logit contributions
bows-0.021
 smell-0.019
 queens-0.019
 fashion-0.019
 germ-0.019
Token kay
Token ID34681
Feature activation-8.68e-02

Pos logit contributions
roads+0.023
stack+0.022
vered+0.021
ued+0.020
iped+0.019
Neg logit contributions
bows-0.013
 smell-0.012
 fashion-0.011
 queens-0.011
 she-0.011
Tokenak
Token ID461
Feature activation-3.23e-02

Pos logit contributions
stack+0.130
roads+0.129
vered+0.118
ishly+0.112
used+0.109
Neg logit contributions
head-0.116
bows-0.114
 queens-0.112
issy-0.100
 germ-0.099
Token in
Token ID287
Feature activation-3.15e-02

Pos logit contributions
roads+0.060
vered+0.054
stack+0.053
ued+0.050
ulously+0.049
Neg logit contributions
bows-0.038
head-0.034
 queens-0.032
 she-0.032
 smell-0.031
Token exchange
Token ID5163
Feature activation-2.64e-02

Pos logit contributions
roads+0.072
vered+0.067
stack+0.067
am+0.065
ued+0.065
Neg logit contributions
 she-0.020
bows-0.020
 smell-0.020
 Lilly-0.017
 Emmy-0.017
Token for
Token ID329
Feature activation-1.61e-02

Pos logit contributions
roads+0.057
vered+0.051
stack+0.049
ulously+0.048
ued+0.048
Neg logit contributions
 she-0.025
bows-0.021
 smell-0.020
 Lilly-0.020
head-0.019
Token the
Token ID262
Feature activation+1.89e-03

Pos logit contributions
roads+0.029
vered+0.027
stack+0.026
ued+0.025
ulously+0.024
Neg logit contributions
bows-0.018
 queens-0.018
head-0.017
 she-0.017
 smell-0.017
Token loud
Token ID7812
Feature activation-1.28e-02

Pos logit contributions
roads+0.002
stack+0.002
vered+0.002
iped+0.001
ulously+0.001
Neg logit contributions
 queens-0.001
bows-0.001
 germ-0.001
head-0.001
 spill-0.001
Token noise
Token ID7838
Feature activation+1.54e-02

Pos logit contributions
roads+0.024
vered+0.024
stack+0.022
ued+0.021
ieved+0.021
Neg logit contributions
bows-0.014
head-0.014
 smell-0.012
 germ-0.012
 she-0.011
Token.
Token ID13
Feature activation-3.91e-03

Pos logit contributions
bows+0.017
head+0.017
 queens+0.015
 smell+0.015
 she+0.015
Neg logit contributions
roads-0.028
vered-0.028
stack-0.026
ued-0.025
ulously-0.024
Token He
Token ID679
Feature activation-9.01e-04

Pos logit contributions
roads+0.008
vered+0.007
stack+0.007
ued+0.007
ulously+0.006
Neg logit contributions
head-0.004
bows-0.004
 she-0.004
 She-0.004
 Emmy-0.003
Token sc
Token ID629
Feature activation-1.53e-02

Pos logit contributions
roads+0.002
stack+0.001
vered+0.001
ued+0.001
 tal+0.001
Neg logit contributions
bows-0.001
 smell-0.001
head-0.001
 she-0.001
 smells-0.001
Tokenrun
Token ID5143
Feature activation-8.56e-02

Pos logit contributions
roads+0.029
vered+0.027
stack+0.027
 atop+0.026
 afloat+0.026
Neg logit contributions
bows-0.012
issy-0.012
 she-0.011
lic-0.011
 She-0.011
Tokenched
Token ID1740
Feature activation-2.68e-02

Pos logit contributions
roads+0.127
stack+0.124
 predicament+0.111
vered+0.108
 wounds+0.108
Neg logit contributions
bows-0.115
head-0.114
issy-0.112
 Lilly-0.106
 she-0.106
Token his
Token ID465
Feature activation-3.27e-02

Pos logit contributions
roads+0.048
vered+0.045
stack+0.043
ued+0.041
ieved+0.040
Neg logit contributions
head-0.031
 she-0.029
bows-0.029
 Lilly-0.028
 smell-0.027
Token eyes
Token ID2951
Feature activation+1.62e-02

Pos logit contributions
roads+0.061
vered+0.052
ued+0.051
ieved+0.051
ulously+0.047
Neg logit contributions
 smell-0.042
 germ-0.039
 princess-0.037
 perfume-0.037
 fashion-0.037
Token tightly
Token ID17707
Feature activation-2.06e-02

Pos logit contributions
bows+0.016
head+0.015
 queens+0.013
 she+0.013
 smell+0.013
Neg logit contributions
roads-0.032
vered-0.030
stack-0.030
ued-0.027
ulously-0.027
Token and
Token ID290
Feature activation-1.26e-02

Pos logit contributions
roads+0.047
vered+0.041
stack+0.041
ieved+0.040
ulously+0.040
Neg logit contributions
bows-0.016
 she-0.014
head-0.014
 because-0.013
 smell-0.012
TokenWhy
Token ID5195
Feature activation+2.75e-03

Pos logit contributions
bows+0.006
head+0.006
 queens+0.005
 germ+0.005
isha+0.005
Neg logit contributions
roads-0.008
vered-0.008
stack-0.007
ued-0.007
ulously-0.007
Token did
Token ID750
Feature activation+1.85e-02

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 germ+0.003
isha+0.003
Neg logit contributions
roads-0.004
vered-0.004
stack-0.004
ued-0.004
ulously-0.003
Token you
Token ID345
Feature activation+1.18e-03

Pos logit contributions
bows+0.026
head+0.022
isha+0.022
 queens+0.021
issy+0.021
Neg logit contributions
roads-0.030
vered-0.027
ued-0.026
stack-0.025
aroo-0.024
Token take
Token ID1011
Feature activation-2.10e-02

Pos logit contributions
bows+0.001
head+0.001
 smell+0.001
 spill+0.001
 queens+0.001
Neg logit contributions
roads-0.002
vered-0.002
stack-0.002
ued-0.002
ulously-0.002
Token my
Token ID616
Feature activation-5.56e-03

Pos logit contributions
roads+0.033
vered+0.031
stack+0.029
ued+0.028
 tal+0.027
Neg logit contributions
bows-0.030
head-0.027
 queens-0.026
isha-0.025
 germ-0.025
Token kay
Token ID34681
Feature activation-8.31e-02

Pos logit contributions
roads+0.008
ieved+0.007
stack+0.007
vered+0.007
ulously+0.006
Neg logit contributions
 smell-0.009
head-0.009
 germ-0.009
bows-0.009
 spill-0.008
Tokenak
Token ID461
Feature activation-3.17e-02

Pos logit contributions
stack+0.138
roads+0.129
vered+0.126
ishly+0.124
used+0.117
Neg logit contributions
head-0.103
 queens-0.097
bows-0.096
akers-0.093
COM-0.090
Token?"
Token ID1701
Feature activation-8.52e-03

Pos logit contributions
vered+0.060
roads+0.059
stack+0.055
ued+0.053
ulously+0.050
Neg logit contributions
bows-0.035
head-0.033
 queens-0.030
 smell-0.029
 spill-0.028
Token
Token ID198
Feature activation-1.41e-02

Pos logit contributions
vered+0.017
roads+0.016
stack+0.016
ulously+0.015
iped+0.015
Neg logit contributions
 she-0.010
 She-0.009
head-0.009
 queens-0.008
 Lily-0.008
Token
Token ID198
Feature activation-2.02e-03

Pos logit contributions
vered+0.027
stack+0.027
roads+0.026
ishly+0.025
iped+0.024
Neg logit contributions
head-0.015
 queens-0.014
 she-0.014
L-0.014
 She-0.013
TokenL
Token ID43
Feature activation+3.35e-02

Pos logit contributions
roads+0.004
vered+0.003
stack+0.003
ued+0.003
ulously+0.003
Neg logit contributions
bows-0.002
head-0.002
 queens-0.002
 germ-0.002
isha-0.002
Token "
Token ID366
Feature activation+3.96e-03

Pos logit contributions
 she+0.004
head+0.003
bows+0.003
 queens+0.003
 smell+0.003
Neg logit contributions
roads-0.009
vered-0.008
ulously-0.008
ued-0.007
stack-0.007
TokenWhat
Token ID2061
Feature activation+9.62e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.007
vered-0.007
stack-0.007
ued-0.006
 tal-0.006
Token is
Token ID318
Feature activation+2.53e-02

Pos logit contributions
bows+0.016
head+0.015
 queens+0.015
isha+0.014
 germ+0.014
Neg logit contributions
roads-0.012
vered-0.012
stack-0.010
ued-0.010
am-0.010
Token this
Token ID428
Feature activation-2.41e-02

Pos logit contributions
bows+0.040
head+0.037
 queens+0.036
isha+0.034
 germ+0.033
Neg logit contributions
roads-0.037
vered-0.033
stack-0.033
ued-0.030
 tal-0.029
Token big
Token ID1263
Feature activation-2.39e-02

Pos logit contributions
vered+0.044
roads+0.041
stack+0.039
ishly+0.038
eled+0.038
Neg logit contributions
bows-0.030
 smell-0.029
 germ-0.027
head-0.027
 spill-0.026
Token cross
Token ID3272
Feature activation-8.31e-02

Pos logit contributions
vered+0.034
ieved+0.034
roads+0.033
stack+0.032
ued+0.032
Neg logit contributions
 smell-0.035
bows-0.034
head-0.034
 germ-0.033
 spill-0.033
Token?"
Token ID1701
Feature activation-4.89e-03

Pos logit contributions
vered+0.208
eled+0.186
 tal+0.183
 wounds+0.180
ulously+0.178
Neg logit contributions
head-0.055
 smell-0.055
 because-0.053
bows-0.046
 boring-0.046
Token Lily
Token ID20037
Feature activation-7.35e-03

Pos logit contributions
roads+0.011
vered+0.010
stack+0.010
ued+0.009
 tal+0.009
Neg logit contributions
bows-0.004
head-0.003
 queens-0.003
 germ-0.003
isha-0.003
Token said
Token ID531
Feature activation+7.44e-04

Pos logit contributions
roads+0.012
vered+0.011
stack+0.010
ued+0.009
 tal+0.009
Neg logit contributions
bows-0.011
 smell-0.010
 she-0.010
isha-0.009
head-0.009
Token,
Token ID11
Feature activation-3.88e-04

Pos logit contributions
bows+0.001
head+0.001
 she+0.001
 queens+0.001
 smell+0.001
Neg logit contributions
roads-0.002
vered-0.001
stack-0.001
 tal-0.001
ulously-0.001
Token "
Token ID366
Feature activation-7.75e-04

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
 tal+0.001
ued+0.001
Neg logit contributions
bows-0.000
head-0.000
 queens-0.000
 smell-0.000
 she-0.000
Token and
Token ID290
Feature activation-5.32e-04

Pos logit contributions
vered+0.045
stack+0.044
roads+0.043
 tal+0.043
ulously+0.041
Neg logit contributions
bows-0.023
 she-0.020
head-0.017
 because-0.017
 smell-0.017
Token always
Token ID1464
Feature activation-1.34e-02

Pos logit contributions
 tal+0.001
vered+0.001
roads+0.001
stack+0.001
ieved+0.001
Neg logit contributions
bows-0.001
 she-0.001
 queens-0.001
 smell-0.001
head-0.001
Token tried
Token ID3088
Feature activation-1.06e-02

Pos logit contributions
roads+0.025
stack+0.025
vered+0.024
 tal+0.024
ulously+0.023
Neg logit contributions
bows-0.016
 smell-0.013
head-0.013
 queens-0.012
 she-0.012
Token to
Token ID284
Feature activation-1.01e-02

Pos logit contributions
roads+0.020
stack+0.020
vered+0.019
ued+0.018
 tal+0.017
Neg logit contributions
bows-0.012
 queens-0.010
head-0.010
 she-0.010
 smell-0.009
Token out
Token ID503
Feature activation-1.31e-02

Pos logit contributions
stack+0.021
 tal+0.021
eled+0.020
vered+0.020
ement+0.019
Neg logit contributions
 smell-0.009
 spill-0.008
bows-0.008
 taste-0.008
 fashion-0.008
Tokenrun
Token ID5143
Feature activation-8.26e-02

Pos logit contributions
stack+0.024
roads+0.023
vered+0.021
 tal+0.021
ued+0.020
Neg logit contributions
bows-0.015
 queens-0.015
head-0.014
 she-0.013
 fashion-0.013
Token everyone
Token ID2506
Feature activation+2.34e-02

Pos logit contributions
stack+0.152
roads+0.150
vered+0.133
used+0.132
ued+0.132
Neg logit contributions
bows-0.086
head-0.083
 she-0.081
issy-0.076
 Min-0.073
Token else
Token ID2073
Feature activation-7.44e-03

Pos logit contributions
bows+0.028
 she+0.026
head+0.026
 queens+0.025
 fashion+0.023
Neg logit contributions
roads-0.041
stack-0.040
vered-0.038
 tal-0.037
ulously-0.037
Token.
Token ID13
Feature activation-9.23e-03

Pos logit contributions
roads+0.014
stack+0.014
vered+0.013
 tal+0.013
ulously+0.012
Neg logit contributions
bows-0.008
head-0.007
 she-0.007
 queens-0.007
 smell-0.007
Token One
Token ID1881
Feature activation-3.23e-02

Pos logit contributions
vered+0.018
roads+0.017
stack+0.016
ued+0.015
ieved+0.015
Neg logit contributions
bows-0.010
 She-0.010
head-0.009
 she-0.008
 Eve-0.008
Token day
Token ID1110
Feature activation+1.95e-03

Pos logit contributions
vered+0.067
roads+0.065
stack+0.064
iped+0.060
ishly+0.060
Neg logit contributions
head-0.030
bows-0.028
 smell-0.026
 germ-0.026
 she-0.026
Token!
Token ID0
Feature activation+1.26e-02

Pos logit contributions
roads+0.075
 afloat+0.070
ieved+0.067
athed+0.066
vered+0.065
Neg logit contributions
head-0.113
 she-0.110
ina-0.104
 smell-0.103
isha-0.099
Token Cl
Token ID1012
Feature activation-8.89e-03

Pos logit contributions
bows+0.014
head+0.014
 queens+0.013
isha+0.012
 germ+0.012
Neg logit contributions
roads-0.023
vered-0.022
stack-0.021
ued-0.020
ulously-0.019
Tokenang
Token ID648
Feature activation-7.90e-02

Pos logit contributions
roads+0.012
vered+0.011
stack+0.011
ued+0.010
 tal+0.010
Neg logit contributions
bows-0.014
head-0.013
 queens-0.013
 germ-0.013
isha-0.012
Token!
Token ID0
Feature activation+4.30e-03

Pos logit contributions
roads+0.083
vered+0.073
ieved+0.072
ulously+0.071
 afloat+0.071
Neg logit contributions
head-0.133
 she-0.133
 smell-0.123
bows-0.122
ina-0.120
Token Cl
Token ID1012
Feature activation-1.10e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
isha+0.004
 germ+0.004
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ued-0.007
ulously-0.006
Tokenang
Token ID648
Feature activation-8.11e-02

Pos logit contributions
roads+0.016
vered+0.015
stack+0.014
ued+0.013
 tal+0.013
Neg logit contributions
bows-0.017
head-0.016
 queens-0.015
 germ-0.014
isha-0.014
Token!"
Token ID2474
Feature activation-1.05e-02

Pos logit contributions
roads+0.088
vered+0.077
ulously+0.075
ieved+0.075
 afloat+0.074
Neg logit contributions
 she-0.136
head-0.135
bows-0.127
 smell-0.125
ina-0.121
Token the
Token ID262
Feature activation-2.19e-02

Pos logit contributions
vered+0.021
roads+0.020
stack+0.019
ulously+0.018
ieved+0.017
Neg logit contributions
head-0.010
 she-0.010
bows-0.010
 queens-0.009
 Hanna-0.009
Token shovel
Token ID33677
Feature activation-4.79e-03

Pos logit contributions
roads+0.039
vered+0.039
ieved+0.037
ved+0.036
stack+0.036
Neg logit contributions
head-0.022
 smell-0.022
 princess-0.021
 fashion-0.021
isha-0.021
Token goes
Token ID2925
Feature activation-6.81e-03

Pos logit contributions
roads+0.008
stack+0.008
vered+0.008
 tal+0.007
ieved+0.007
Neg logit contributions
 she-0.006
bows-0.006
head-0.006
 smell-0.005
 spill-0.005
Token.
Token ID13
Feature activation-7.93e-03

Pos logit contributions
roads+0.008
stack+0.007
vered+0.007
ued+0.006
cut+0.006
Neg logit contributions
bows-0.012
 queens-0.012
head-0.011
 germ-0.011
isha-0.011
Token.
Token ID13
Feature activation+7.35e-04

Pos logit contributions
 she+0.007
bows+0.006
 smell+0.006
head+0.005
 because+0.005
Neg logit contributions
roads-0.020
vered-0.018
ulously-0.017
stack-0.017
ieved-0.017
Token He
Token ID679
Feature activation-5.73e-03

Pos logit contributions
bows+0.001
head+0.001
 She+0.001
 smell+0.001
 she+0.001
Neg logit contributions
roads-0.001
vered-0.001
stack-0.001
cks-0.001
cut-0.001
Token tried
Token ID3088
Feature activation-1.16e-02

Pos logit contributions
roads+0.011
stack+0.010
vered+0.010
cut+0.009
cks+0.009
Neg logit contributions
head-0.005
 she-0.005
 smell-0.005
 queens-0.005
bows-0.005
Token to
Token ID284
Feature activation-1.14e-02

Pos logit contributions
roads+0.023
vered+0.022
stack+0.022
ued+0.020
ulously+0.020
Neg logit contributions
bows-0.011
 queens-0.010
head-0.010
 she-0.010
 smell-0.009
Token out
Token ID503
Feature activation-1.24e-02

Pos logit contributions
roads+0.022
vered+0.021
ement+0.021
ued+0.020
am+0.020
Neg logit contributions
 smell-0.011
 spill-0.010
 queens-0.009
 wake-0.009
 she-0.009
Tokenrun
Token ID5143
Feature activation-8.09e-02

Pos logit contributions
roads+0.022
stack+0.022
vered+0.020
ued+0.019
ieved+0.019
Neg logit contributions
head-0.013
bows-0.013
 queens-0.013
 she-0.013
 smell-0.012
Token the
Token ID262
Feature activation+7.96e-03

Pos logit contributions
roads+0.148
stack+0.139
 predicament+0.130
vered+0.130
athed+0.128
Neg logit contributions
 she-0.080
head-0.080
issy-0.077
bows-0.074
 Min-0.072
Token train
Token ID4512
Feature activation-4.73e-03

Pos logit contributions
bows+0.012
head+0.011
 queens+0.011
 smell+0.011
 germ+0.010
Neg logit contributions
roads-0.012
vered-0.011
stack-0.011
ued-0.010
 tal-0.010
Token but
Token ID475
Feature activation-3.19e-02

Pos logit contributions
vered+0.009
roads+0.009
ulously+0.009
eled+0.009
cks+0.009
Neg logit contributions
bows-0.005
head-0.004
 she-0.004
 smell-0.003
 because-0.003
Token he
Token ID339
Feature activation-2.67e-02

Pos logit contributions
roads+0.067
vered+0.066
cks+0.064
 tal+0.062
iped+0.062
Neg logit contributions
 she-0.030
 because-0.021
head-0.021
 smell-0.019
 spill-0.016
Token was
Token ID373
Feature activation-2.75e-02

Pos logit contributions
roads+0.060
ags+0.052
stack+0.052
vered+0.052
ued+0.051
Neg logit contributions
 she-0.019
head-0.017
 because-0.017
 smell-0.016
issy-0.015
TokenWhy
Token ID5195
Feature activation+6.96e-03

Pos logit contributions
bows+0.020
head+0.020
 queens+0.019
 germ+0.017
 spill+0.017
Neg logit contributions
roads-0.029
vered-0.028
stack-0.027
ued-0.026
 tal-0.025
Token did
Token ID750
Feature activation+2.70e-02

Pos logit contributions
bows+0.010
head+0.009
 queens+0.009
 germ+0.008
isha+0.008
Neg logit contributions
roads-0.011
vered-0.010
stack-0.010
ued-0.009
ulously-0.009
Token you
Token ID345
Feature activation+9.35e-03

Pos logit contributions
bows+0.038
head+0.032
 queens+0.032
isha+0.032
issy+0.031
Neg logit contributions
roads-0.044
vered-0.039
ued-0.038
stack-0.037
aroo-0.036
Token take
Token ID1011
Feature activation-1.76e-02

Pos logit contributions
 smell+0.011
bows+0.010
 spill+0.010
head+0.010
 germ+0.009
Neg logit contributions
roads-0.017
vered-0.017
stack-0.015
ued-0.014
ulously-0.014
Token my
Token ID616
Feature activation-3.07e-03

Pos logit contributions
roads+0.029
vered+0.027
stack+0.026
ued+0.024
 tal+0.024
Neg logit contributions
bows-0.024
head-0.022
 queens-0.021
 germ-0.020
isha-0.020
Token kay
Token ID34681
Feature activation-8.08e-02

Pos logit contributions
roads+0.005
stack+0.004
vered+0.004
ieved+0.004
ued+0.004
Neg logit contributions
head-0.005
 germ-0.005
 smell-0.005
 queens-0.005
bows-0.005
Tokenak
Token ID461
Feature activation-3.49e-02

Pos logit contributions
stack+0.137
roads+0.127
vered+0.126
ishly+0.122
used+0.116
Neg logit contributions
head-0.099
 queens-0.093
bows-0.091
akers-0.089
COM-0.085
Token?"
Token ID1701
Feature activation-9.98e-03

Pos logit contributions
vered+0.069
roads+0.066
stack+0.063
ued+0.061
cks+0.058
Neg logit contributions
bows-0.036
head-0.034
 smell-0.032
 queens-0.030
 spill-0.029
Token he
Token ID339
Feature activation-2.15e-02

Pos logit contributions
vered+0.023
stack+0.021
roads+0.020
ieved+0.020
 tal+0.020
Neg logit contributions
 she-0.010
 She-0.008
 Mrs-0.008
 smell-0.008
head-0.008
Token asked
Token ID1965
Feature activation-3.50e-02

Pos logit contributions
roads+0.037
stack+0.037
vered+0.036
ued+0.031
ieved+0.031
Neg logit contributions
head-0.026
 she-0.025
isha-0.025
 smell-0.024
 queens-0.024
Token.
Token ID13
Feature activation-2.92e-03

Pos logit contributions
roads+0.078
stack+0.077
vered+0.075
 tal+0.071
ued+0.069
Neg logit contributions
 she-0.031
 She-0.024
 Lily-0.023
head-0.023
 Mrs-0.023
Token if
Token ID611
Feature activation-1.06e-02

Pos logit contributions
roads+0.004
vered+0.004
stack+0.004
ued+0.003
 tal+0.003
Neg logit contributions
bows-0.003
head-0.003
 queens-0.002
 germ-0.002
isha-0.002
Token he
Token ID339
Feature activation+1.12e-02

Pos logit contributions
roads+0.021
vered+0.020
stack+0.019
ued+0.018
ulously+0.017
Neg logit contributions
bows-0.011
head-0.010
 queens-0.009
isha-0.008
 germ-0.008
Token could
Token ID714
Feature activation+3.57e-03

Pos logit contributions
bows+0.016
head+0.015
 queens+0.014
 germ+0.013
isha+0.013
Neg logit contributions
roads-0.017
vered-0.017
stack-0.016
ued-0.015
 tal-0.014
Token take
Token ID1011
Feature activation-1.20e-02

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 germ+0.004
 smell+0.004
Neg logit contributions
roads-0.006
vered-0.006
stack-0.006
ued-0.005
 tal-0.005
Token his
Token ID465
Feature activation-5.00e-04

Pos logit contributions
roads+0.014
vered+0.013
 tal+0.012
am+0.012
ulously+0.011
Neg logit contributions
bows-0.022
 queens-0.019
head-0.019
isha-0.018
yt-0.018
Token kay
Token ID34681
Feature activation-8.08e-02

Pos logit contributions
roads+0.001
stack+0.001
vered+0.001
ulously+0.001
ieved+0.001
Neg logit contributions
bows-0.001
 smell-0.000
head-0.000
 germ-0.000
 fashion-0.000
Tokenak
Token ID461
Feature activation-2.35e-02

Pos logit contributions
stack+0.123
vered+0.116
roads+0.115
ishly+0.108
used+0.103
Neg logit contributions
head-0.110
bows-0.106
 queens-0.104
COM-0.096
 fashion-0.094
Token out
Token ID503
Feature activation-1.12e-03

Pos logit contributions
vered+0.048
roads+0.048
stack+0.045
ued+0.043
ulously+0.042
Neg logit contributions
bows-0.022
head-0.020
 she-0.018
 queens-0.018
 smell-0.017
Token for
Token ID329
Feature activation-1.50e-02

Pos logit contributions
roads+0.002
stack+0.002
vered+0.002
ued+0.002
iped+0.002
Neg logit contributions
 she-0.001
head-0.001
 queens-0.001
bows-0.001
 because-0.001
Token a
Token ID257
Feature activation-9.30e-04

Pos logit contributions
roads+0.027
vered+0.025
stack+0.025
ued+0.023
cut+0.022
Neg logit contributions
head-0.017
 queens-0.017
bows-0.017
 germ-0.015
 smell-0.015
Token ride
Token ID6594
Feature activation-2.88e-02

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
ued+0.001
ulously+0.001
Neg logit contributions
bows-0.001
head-0.001
 queens-0.001
 germ-0.001
isha-0.001
Token that
Token ID326
Feature activation-2.00e-02

Pos logit contributions
roads+0.020
vered+0.019
stack+0.018
ued+0.017
ulously+0.016
Neg logit contributions
bows-0.014
head-0.013
 queens-0.013
 germ-0.012
 smell-0.011
Token might
Token ID1244
Feature activation-8.93e-03

Pos logit contributions
roads+0.038
vered+0.036
stack+0.035
ued+0.033
 tal+0.032
Neg logit contributions
bows-0.022
head-0.020
 queens-0.019
 smell-0.018
 germ-0.018
Token fit
Token ID4197
Feature activation-5.06e-03

Pos logit contributions
roads+0.016
vered+0.015
stack+0.014
ued+0.013
ulously+0.013
Neg logit contributions
bows-0.011
head-0.010
 queens-0.010
 smell-0.010
 germ-0.009
Token in
Token ID287
Feature activation-6.91e-03

Pos logit contributions
roads+0.009
vered+0.008
stack+0.008
ued+0.007
ulously+0.007
Neg logit contributions
bows-0.006
head-0.006
 queens-0.006
 she-0.005
 germ-0.005
Token your
Token ID534
Feature activation-2.33e-02

Pos logit contributions
roads+0.013
stack+0.012
vered+0.012
ued+0.012
ishly+0.012
Neg logit contributions
 queens-0.008
head-0.007
 fashion-0.007
 spill-0.007
bows-0.006
Token kay
Token ID34681
Feature activation-8.08e-02

Pos logit contributions
roads+0.038
stack+0.033
ued+0.033
ieved+0.032
vered+0.032
Neg logit contributions
 fashion-0.032
 smell-0.030
 germ-0.030
head-0.030
 queens-0.030
Tokenak
Token ID461
Feature activation-2.45e-02

Pos logit contributions
stack+0.139
ishly+0.133
vered+0.133
roads+0.126
used+0.123
Neg logit contributions
head-0.093
bows-0.087
 queens-0.086
COM-0.086
akers-0.083
Token.
Token ID13
Feature activation-2.63e-03

Pos logit contributions
vered+0.049
roads+0.047
stack+0.046
eled+0.045
ulously+0.043
Neg logit contributions
bows-0.026
head-0.024
 queens-0.022
 because-0.019
 she-0.019
Token We
Token ID775
Feature activation-1.47e-02

Pos logit contributions
roads+0.005
vered+0.005
stack+0.004
ued+0.004
 tal+0.004
Neg logit contributions
bows-0.003
head-0.003
 queens-0.003
isha-0.002
 smell-0.002
Token can
Token ID460
Feature activation+1.54e-03

Pos logit contributions
roads+0.029
vered+0.027
stack+0.026
ued+0.025
 tal+0.024
Neg logit contributions
bows-0.015
head-0.013
 queens-0.013
 germ-0.012
 smell-0.012
Token play
Token ID711
Feature activation-9.49e-03

Pos logit contributions
bows+0.002
 smell+0.002
head+0.002
 spill+0.002
 queens+0.002
Neg logit contributions
roads-0.003
vered-0.003
stack-0.002
 tal-0.002
ued-0.002
Token at
Token ID379
Feature activation-2.90e-02

Pos logit contributions
roads+0.012
vered+0.011
stack+0.011
ued+0.010
 tal+0.010
Neg logit contributions
bows-0.010
head-0.009
 queens-0.009
 germ-0.008
isha-0.008
Token each
Token ID1123
Feature activation-6.28e-02

Pos logit contributions
roads+0.066
stack+0.060
ued+0.059
ieved+0.059
used+0.057
Neg logit contributions
 smell-0.020
 fashion-0.020
 because-0.020
 she-0.020
bows-0.019
Token other
Token ID584
Feature activation-2.43e-02

Pos logit contributions
stack+0.106
roads+0.097
vered+0.088
 tal+0.088
cut+0.087
Neg logit contributions
 spill-0.085
 smell-0.085
 princess-0.085
 she-0.084
 queens-0.084
Token and
Token ID290
Feature activation-2.42e-02

Pos logit contributions
roads+0.045
vered+0.042
stack+0.042
ued+0.038
 tal+0.038
Neg logit contributions
bows-0.029
head-0.025
 queens-0.024
 smell-0.023
 germ-0.023
Token shout
Token ID9191
Feature activation-4.07e-03

Pos logit contributions
roads+0.044
vered+0.042
ement+0.040
 tal+0.039
ued+0.039
Neg logit contributions
 she-0.027
 smell-0.027
bows-0.026
 spill-0.024
head-0.022
Token each
Token ID1123
Feature activation-8.00e-02

Pos logit contributions
roads+0.006
vered+0.006
stack+0.006
ued+0.005
 tal+0.005
Neg logit contributions
bows-0.006
head-0.005
 queens-0.005
 germ-0.005
isha-0.005
Token time
Token ID640
Feature activation-3.70e-04

Pos logit contributions
stack+0.153
roads+0.135
cut+0.123
ishly+0.119
 tal+0.119
Neg logit contributions
 smell-0.107
 like-0.101
 spill-0.098
 taste-0.097
head-0.096
Token they
Token ID484
Feature activation+3.81e-03

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
ulously+0.001
 tal+0.001
Neg logit contributions
bows-0.000
head-0.000
 she-0.000
 smell-0.000
 spill-0.000
Token pointed
Token ID6235
Feature activation-2.21e-02

Pos logit contributions
bows+0.004
 spill+0.004
 queens+0.004
 smell+0.004
head+0.004
Neg logit contributions
roads-0.007
stack-0.007
vered-0.007
 tal-0.006
ulously-0.006
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
stack+0.045
roads+0.044
vered+0.041
cut+0.040
aroo+0.038
Neg logit contributions
bows-0.020
 fashion-0.019
 she-0.019
 smell-0.019
 because-0.018
Token
Token ID198
Feature activation-4.55e-03

Pos logit contributions
roads+0.021
vered+0.020
stack+0.019
cut+0.018
 tal+0.018
Neg logit contributions
bows-0.011
head-0.009
 She-0.009
 Emmy-0.009
isha-0.008
Token "
Token ID366
Feature activation+4.25e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 she+0.003
isha+0.003
Neg logit contributions
roads-0.006
vered-0.006
stack-0.005
ulously-0.005
ued-0.005
TokenThank
Token ID10449
Feature activation+4.06e-02

Pos logit contributions
bows+0.006
head+0.005
 queens+0.005
 germ+0.005
isha+0.005
Neg logit contributions
roads-0.007
vered-0.007
stack-0.006
ued-0.006
 tal-0.006
Token you
Token ID345
Feature activation-2.94e-02

Pos logit contributions
bows+0.041
head+0.037
 queens+0.036
 germ+0.033
isha+0.032
Neg logit contributions
roads-0.081
vered-0.076
stack-0.074
ued-0.070
 tal-0.068
Token for
Token ID329
Feature activation+1.61e-04

Pos logit contributions
roads+0.041
stack+0.039
vered+0.036
 tal+0.034
ued+0.034
Neg logit contributions
bows-0.046
head-0.040
 queens-0.039
 germ-0.039
 spill-0.038
Token my
Token ID616
Feature activation-1.12e-02

Pos logit contributions
 queens+0.000
 fashion+0.000
head+0.000
 smell+0.000
 germ+0.000
Neg logit contributions
roads-0.000
vered-0.000
ued-0.000
stack-0.000
ement-0.000
Token kay
Token ID34681
Feature activation-8.00e-02

Pos logit contributions
roads+0.022
vered+0.020
stack+0.019
iped+0.018
ulously+0.018
Neg logit contributions
bows-0.012
 smell-0.012
head-0.012
 germ-0.012
 queens-0.012
Tokenak
Token ID461
Feature activation-2.96e-02

Pos logit contributions
stack+0.130
roads+0.124
vered+0.123
ishly+0.113
used+0.111
Neg logit contributions
head-0.100
bows-0.098
 queens-0.095
akers-0.093
COM-0.084
Token,
Token ID11
Feature activation+2.78e-03

Pos logit contributions
roads+0.055
vered+0.052
stack+0.049
ued+0.047
ulously+0.046
Neg logit contributions
bows-0.034
head-0.031
 queens-0.030
 smell-0.028
 germ-0.027
Token it
Token ID340
Feature activation+2.36e-03

Pos logit contributions
bows+0.003
head+0.003
 queens+0.003
 germ+0.003
isha+0.003
Neg logit contributions
roads-0.005
vered-0.005
stack-0.004
ued-0.004
ulously-0.004
Token was
Token ID373
Feature activation-1.18e-02

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 germ+0.003
isha+0.003
Neg logit contributions
roads-0.003
vered-0.003
stack-0.003
ued-0.003
ulously-0.002
Token so
Token ID523
Feature activation-1.40e-02

Pos logit contributions
roads+0.023
vered+0.022
stack+0.021
ued+0.020
used+0.019
Neg logit contributions
bows-0.012
head-0.011
 queens-0.011
 smell-0.010
 germ-0.010
Token you
Token ID345
Feature activation-4.80e-02

Pos logit contributions
roads+0.029
vered+0.027
stack+0.026
ued+0.024
ulously+0.023
Neg logit contributions
bows-0.016
head-0.016
 queens-0.015
 germ-0.014
 smell-0.014
Token?"
Token ID1701
Feature activation-1.65e-02

Pos logit contributions
roads+0.096
vered+0.094
stack+0.087
iped+0.083
ulously+0.083
Neg logit contributions
 queens-0.050
bows-0.048
head-0.047
isha-0.047
 she-0.046
Token
Token ID198
Feature activation-1.50e-02

Pos logit contributions
roads+0.027
vered+0.025
stack+0.024
ued+0.022
ulously+0.022
Neg logit contributions
bows-0.023
 she-0.022
head-0.022
 She-0.020
 queens-0.020
Token
Token ID198
Feature activation-9.85e-04

Pos logit contributions
roads+0.033
vered+0.031
stack+0.031
iped+0.028
used+0.028
Neg logit contributions
 she-0.014
L-0.013
 She-0.013
 Eve-0.013
 Chick-0.012
TokenB
Token ID33
Feature activation+4.96e-03

Pos logit contributions
roads+0.002
stack+0.001
vered+0.001
ued+0.001
ulously+0.001
Neg logit contributions
bows-0.001
head-0.001
 queens-0.001
 she-0.001
isha-0.001
Tokenrun
Token ID5143
Feature activation-7.97e-02

Pos logit contributions
bows+0.005
 queens+0.005
 smell+0.004
 germ+0.004
head+0.004
Neg logit contributions
vered-0.010
roads-0.009
stack-0.009
am-0.008
ued-0.008
Tokeno
Token ID78
Feature activation-2.30e-02

Pos logit contributions
roads+0.122
stack+0.112
vered+0.101
used+0.100
ued+0.096
Neg logit contributions
bows-0.119
head-0.111
issy-0.107
 Lilly-0.099
 Chick-0.098
Token said
Token ID531
Feature activation+3.79e-03

Pos logit contributions
roads+0.043
stack+0.037
vered+0.036
ued+0.034
 footing+0.034
Neg logit contributions
bows-0.028
head-0.025
 smell-0.025
isha-0.024
 smells-0.023
Token,
Token ID11
Feature activation+4.15e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.003
 she+0.003
 smell+0.003
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ulously-0.006
 tal-0.006
Token "
Token ID366
Feature activation+7.91e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 she+0.004
 smell+0.004
Neg logit contributions
roads-0.008
vered-0.008
stack-0.007
ulously-0.007
 tal-0.007
TokenOf
Token ID5189
Feature activation-2.54e-02

Pos logit contributions
bows+0.012
head+0.011
 queens+0.011
 germ+0.010
isha+0.010
Neg logit contributions
roads-0.012
vered-0.011
stack-0.010
ued-0.010
 tal-0.009
Token we
Token ID356
Feature activation-1.50e-02

Pos logit contributions
bows+0.003
head+0.003
 queens+0.003
 she+0.003
 smell+0.002
Neg logit contributions
roads-0.014
vered-0.013
stack-0.013
 tal-0.012
ued-0.012
Token please
Token ID3387
Feature activation-1.79e-02

Pos logit contributions
roads+0.026
vered+0.024
stack+0.023
ued+0.022
 tal+0.021
Neg logit contributions
bows-0.019
head-0.018
 queens-0.017
 germ-0.016
isha-0.016
Token have
Token ID423
Feature activation-5.98e-03

Pos logit contributions
roads+0.034
vered+0.033
stack+0.030
ued+0.029
 tal+0.028
Neg logit contributions
bows-0.019
 smell-0.018
head-0.018
 queens-0.017
 spill-0.017
Token one
Token ID530
Feature activation-4.84e-02

Pos logit contributions
roads+0.011
stack+0.010
vered+0.010
iped+0.009
ued+0.009
Neg logit contributions
 queens-0.007
head-0.007
 smell-0.007
 she-0.007
 tea-0.007
Token carrot
Token ID40562
Feature activation-3.36e-02

Pos logit contributions
vered+0.106
roads+0.103
stack+0.098
iped+0.097
alled+0.093
Neg logit contributions
 smell-0.041
head-0.040
 she-0.040
 spill-0.038
 queens-0.038
Token each
Token ID1123
Feature activation-7.95e-02

Pos logit contributions
roads+0.067
vered+0.065
ued+0.060
ulously+0.056
stack+0.056
Neg logit contributions
bows-0.036
 queens-0.034
head-0.034
 smell-0.032
 she-0.031
Token?"
Token ID1701
Feature activation-3.27e-02

Pos logit contributions
roads+0.194
vered+0.193
iped+0.176
stack+0.176
cks+0.175
Neg logit contributions
 smell-0.050
 because-0.048
 she-0.048
 taste-0.044
 like-0.042
Token
Token ID198
Feature activation-2.45e-02

Pos logit contributions
vered+0.064
roads+0.061
ieved+0.057
ued+0.056
iped+0.055
Neg logit contributions
 she-0.040
 She-0.037
 Chick-0.031
 smell-0.030
 Lilly-0.030
Token
Token ID198
Feature activation-9.46e-03

Pos logit contributions
vered+0.057
roads+0.054
iped+0.052
ieved+0.050
 footing+0.049
Neg logit contributions
 Chick-0.019
 she-0.018
 She-0.018
Grand-0.017
isha-0.016
TokenFar
Token ID21428
Feature activation-2.92e-02

Pos logit contributions
roads+0.016
vered+0.016
iped+0.015
ieved+0.015
ued+0.015
Neg logit contributions
head-0.010
 she-0.010
isha-0.010
 Chick-0.009
Grand-0.009
Tokenmer
Token ID647
Feature activation-5.79e-02

Pos logit contributions
roads+0.042
 tal+0.039
 footing+0.038
vered+0.038
 goals+0.038
Neg logit contributions
bows-0.040
head-0.037
 queens-0.033
 smells-0.033
 smell-0.032
Token man
Token ID582
Feature activation-7.08e-03

Pos logit contributions
vered+0.009
roads+0.009
stack+0.008
cks+0.008
 tal+0.008
Neg logit contributions
head-0.005
bows-0.005
 queens-0.005
 smell-0.005
 germ-0.005
Token stepped
Token ID10764
Feature activation-1.07e-02

Pos logit contributions
roads+0.013
stack+0.012
cks+0.011
vered+0.011
 afloat+0.011
Neg logit contributions
 she-0.008
head-0.007
 smell-0.007
bows-0.007
isha-0.007
Token closer
Token ID5699
Feature activation-7.60e-03

Pos logit contributions
roads+0.017
stack+0.017
vered+0.016
cks+0.016
 tal+0.016
Neg logit contributions
head-0.013
 Lilly-0.012
 she-0.012
 Nina-0.012
 She-0.011
Token and
Token ID290
Feature activation-1.56e-02

Pos logit contributions
roads+0.019
stack+0.017
vered+0.017
cks+0.017
ulously+0.017
Neg logit contributions
 she-0.005
bows-0.004
head-0.004
 because-0.003
 smell-0.003
Token said
Token ID531
Feature activation+1.21e-02

Pos logit contributions
roads+0.025
vered+0.024
stack+0.023
ulously+0.022
 tal+0.022
Neg logit contributions
head-0.021
 she-0.021
bows-0.019
 queens-0.019
 smell-0.019
Token gru
Token ID22848
Feature activation-7.93e-02

Pos logit contributions
head+0.010
 she+0.010
bows+0.010
 queens+0.009
 smell+0.008
Neg logit contributions
roads-0.026
stack-0.023
vered-0.023
ulously-0.023
cks-0.022
Tokenff
Token ID487
Feature activation-1.83e-02

Pos logit contributions
roads+0.157
stack+0.151
vered+0.140
ued+0.137
cut+0.130
Neg logit contributions
bows-0.080
head-0.073
 queens-0.070
 germ-0.063
isha-0.062
Tokenly
Token ID306
Feature activation-2.89e-02

Pos logit contributions
roads+0.036
vered+0.033
stack+0.033
ulously+0.030
ued+0.030
Neg logit contributions
bows-0.019
head-0.018
 queens-0.016
isha-0.016
 germ-0.015
Token,
Token ID11
Feature activation+1.00e-02

Pos logit contributions
roads+0.060
stack+0.053
vered+0.053
ulously+0.050
ieved+0.049
Neg logit contributions
bows-0.028
head-0.026
 she-0.024
 queens-0.024
isha-0.023
Token "
Token ID366
Feature activation+4.30e-03

Pos logit contributions
 she+0.008
head+0.008
bows+0.008
 smell+0.008
isha+0.007
Neg logit contributions
roads-0.021
vered-0.020
ulously-0.019
 tal-0.018
stack-0.018
TokenYou
Token ID1639
Feature activation-1.86e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.008
stack-0.007
vered-0.007
 tal-0.007
ued-0.007
Token"
Token ID1
Feature activation+1.42e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ued-0.006
 tal-0.006
TokenCl
Token ID2601
Feature activation+1.72e-02

Pos logit contributions
bows+0.017
head+0.017
 queens+0.016
 germ+0.014
isha+0.014
Neg logit contributions
roads-0.024
vered-0.024
stack-0.023
am-0.022
 tal-0.022
Tokenang
Token ID648
Feature activation-7.07e-02

Pos logit contributions
bows+0.024
 queens+0.023
 germ+0.022
head+0.021
isha+0.021
Neg logit contributions
vered-0.025
roads-0.025
am-0.024
used-0.022
 tal-0.022
Token!
Token ID0
Feature activation+1.26e-02

Pos logit contributions
roads+0.075
 afloat+0.070
ieved+0.067
athed+0.066
vered+0.065
Neg logit contributions
head-0.113
 she-0.110
ina-0.104
 smell-0.103
isha-0.099
Token Cl
Token ID1012
Feature activation-8.89e-03

Pos logit contributions
bows+0.014
head+0.014
 queens+0.013
isha+0.012
 germ+0.012
Neg logit contributions
roads-0.023
vered-0.022
stack-0.021
ued-0.020
ulously-0.019
Tokenang
Token ID648
Feature activation-7.90e-02

Pos logit contributions
roads+0.012
vered+0.011
stack+0.011
ued+0.010
 tal+0.010
Neg logit contributions
bows-0.014
head-0.013
 queens-0.013
 germ-0.013
isha-0.012
Token!
Token ID0
Feature activation+4.30e-03

Pos logit contributions
roads+0.083
vered+0.073
ieved+0.072
ulously+0.071
 afloat+0.071
Neg logit contributions
head-0.133
 she-0.133
 smell-0.123
bows-0.122
ina-0.120
Token Cl
Token ID1012
Feature activation-1.10e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
isha+0.004
 germ+0.004
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ued-0.007
ulously-0.006
Tokenang
Token ID648
Feature activation-8.11e-02

Pos logit contributions
roads+0.016
vered+0.015
stack+0.014
ued+0.013
 tal+0.013
Neg logit contributions
bows-0.017
head-0.016
 queens-0.015
 germ-0.014
isha-0.014
Token!"
Token ID2474
Feature activation-1.05e-02

Pos logit contributions
roads+0.088
vered+0.077
ulously+0.075
ieved+0.075
 afloat+0.074
Neg logit contributions
 she-0.136
head-0.135
bows-0.127
 smell-0.125
ina-0.121
Token the
Token ID262
Feature activation-2.19e-02

Pos logit contributions
vered+0.021
roads+0.020
stack+0.019
ulously+0.018
ieved+0.017
Neg logit contributions
head-0.010
 she-0.010
bows-0.010
 queens-0.009
 Hanna-0.009
Token to
Token ID284
Feature activation+2.32e-03

Pos logit contributions
roads+0.019
vered+0.018
stack+0.017
ued+0.016
ulously+0.016
Neg logit contributions
bows-0.013
head-0.012
 queens-0.012
 germ-0.011
isha-0.011
Token have
Token ID423
Feature activation+8.71e-03

Pos logit contributions
 smell+0.002
bows+0.002
 spill+0.002
head+0.002
 taste+0.002
Neg logit contributions
roads-0.005
vered-0.004
stack-0.004
ued-0.004
 atop-0.004
Token fun
Token ID1257
Feature activation+2.53e-02

Pos logit contributions
bows+0.006
 queens+0.005
head+0.005
 smell+0.005
 fashion+0.004
Neg logit contributions
roads-0.021
stack-0.021
vered-0.020
ued-0.019
cut-0.019
Token with
Token ID351
Feature activation+1.54e-02

Pos logit contributions
bows+0.030
head+0.027
 queens+0.026
 fashion+0.025
 she+0.025
Neg logit contributions
stack-0.045
roads-0.045
vered-0.043
ulously-0.042
 tal-0.041
Token their
Token ID511
Feature activation-1.07e-03

Pos logit contributions
bows+0.016
 smell+0.016
 she+0.016
head+0.015
 queens+0.015
Neg logit contributions
roads-0.029
vered-0.027
stack-0.026
ued-0.025
 tal-0.024
Token kay
Token ID34681
Feature activation-7.89e-02

Pos logit contributions
roads+0.002
vered+0.002
stack+0.002
ieved+0.002
ued+0.002
Neg logit contributions
bows-0.001
 fashion-0.001
 smell-0.001
 queens-0.001
 germ-0.001
Tokenak
Token ID461
Feature activation-2.13e-02

Pos logit contributions
stack+0.121
roads+0.118
vered+0.114
ishly+0.108
used+0.102
Neg logit contributions
bows-0.108
head-0.107
 queens-0.103
akers-0.095
 germ-0.093
Token.
Token ID13
Feature activation-5.67e-03

Pos logit contributions
roads+0.044
vered+0.042
stack+0.039
ued+0.039
ulously+0.039
Neg logit contributions
bows-0.023
head-0.018
 she-0.018
 queens-0.018
 because-0.016
Token
Token ID198
Feature activation-1.19e-02

Pos logit contributions
roads+0.009
vered+0.008
stack+0.007
ued+0.007
 tal+0.007
Neg logit contributions
bows-0.008
head-0.008
 queens-0.008
 germ-0.007
isha-0.007
Token
Token ID198
Feature activation+6.12e-03

Pos logit contributions
vered+0.026
roads+0.025
ishly+0.024
stack+0.023
used+0.022
Neg logit contributions
 she-0.010
 She-0.010
head-0.009
L-0.009
Grand-0.009
TokenThey
Token ID2990
Feature activation+1.22e-02

Pos logit contributions
bows+0.009
head+0.008
 queens+0.008
 germ+0.008
isha+0.008
Neg logit contributions
roads-0.009
vered-0.009
stack-0.008
 tal-0.008
ued-0.008
TokenCan
Token ID6090
Feature activation-1.03e-02

Pos logit contributions
bows+0.023
head+0.022
 queens+0.021
 she+0.019
isha+0.019
Neg logit contributions
roads-0.034
vered-0.032
stack-0.031
 tal-0.030
am-0.030
Token I
Token ID314
Feature activation-1.22e-02

Pos logit contributions
roads+0.027
vered+0.026
stack+0.025
eled+0.025
 tal+0.025
Neg logit contributions
 she-0.004
 queens-0.003
head-0.003
bows-0.003
 Emmy-0.002
Token play
Token ID711
Feature activation-1.85e-02

Pos logit contributions
roads+0.022
vered+0.021
stack+0.020
ued+0.019
ulously+0.018
Neg logit contributions
bows-0.014
head-0.013
 queens-0.013
 smell-0.013
 spill-0.012
Token with
Token ID351
Feature activation+4.85e-03

Pos logit contributions
vered+0.036
roads+0.036
stack+0.036
 tal+0.033
ulously+0.033
Neg logit contributions
head-0.018
 fashion-0.017
 smell-0.017
 queens-0.016
bows-0.016
Token your
Token ID534
Feature activation-8.76e-03

Pos logit contributions
 queens+0.004
head+0.004
 she+0.004
bows+0.004
 Emmy+0.003
Neg logit contributions
roads-0.010
vered-0.010
stack-0.010
ued-0.009
iped-0.009
Token kay
Token ID34681
Feature activation-7.89e-02

Pos logit contributions
roads+0.019
vered+0.018
stack+0.017
ued+0.017
ieved+0.017
Neg logit contributions
 fashion-0.008
 princess-0.007
 makeup-0.007
 smell-0.007
 tea-0.007
Tokenak
Token ID461
Feature activation-4.64e-02

Pos logit contributions
stack+0.134
vered+0.129
ishly+0.125
roads+0.125
used+0.119
Neg logit contributions
head-0.093
bows-0.092
 queens-0.090
akers-0.085
COM-0.081
Token?"
Token ID1701
Feature activation-1.72e-02

Pos logit contributions
vered+0.095
roads+0.090
stack+0.089
cks+0.086
ued+0.083
Neg logit contributions
bows-0.043
head-0.042
 smell-0.037
 because-0.037
 she-0.036
Token asked
Token ID1965
Feature activation-2.87e-02

Pos logit contributions
vered+0.039
stack+0.038
roads+0.037
cks+0.035
 footing+0.034
Neg logit contributions
 she-0.018
 Lilly-0.014
 Emmy-0.014
 Jenny-0.014
 She-0.014
Token Lily
Token ID20037
Feature activation-1.07e-02

Pos logit contributions
roads+0.076
stack+0.074
vered+0.073
cks+0.070
 enclosure+0.068
Neg logit contributions
 Lilly-0.017
 Emmy-0.017
 Jenny-0.016
 Emma-0.016
 she-0.016
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
roads+0.022
stack+0.022
vered+0.021
ulously+0.020
 tal+0.020
Neg logit contributions
 she-0.009
bows-0.008
 because-0.008
head-0.008
 She-0.008
Token red
Token ID2266
Feature activation+1.11e-02

Pos logit contributions
bows+0.028
head+0.027
 queens+0.025
 germ+0.025
isha+0.025
Neg logit contributions
roads-0.030
vered-0.028
stack-0.027
ued-0.025
ulously-0.024
Token flowers
Token ID12734
Feature activation+1.59e-03

Pos logit contributions
isha+0.019
issy+0.018
head+0.017
 germ+0.017
 writer+0.017
Neg logit contributions
vered-0.012
roads-0.012
stack-0.011
 edge-0.011
am-0.011
Token,
Token ID11
Feature activation+4.20e-02

Pos logit contributions
head+0.002
isha+0.002
 germ+0.002
bows+0.002
 queens+0.002
Neg logit contributions
roads-0.002
stack-0.002
vered-0.002
 atop-0.002
ued-0.002
Token blue
Token ID4171
Feature activation+7.30e-03

Pos logit contributions
head+0.058
bows+0.057
isha+0.057
issy+0.056
 germ+0.055
Neg logit contributions
roads-0.060
vered-0.055
stack-0.052
 edge-0.048
ued-0.048
Token flowers
Token ID12734
Feature activation+9.05e-03

Pos logit contributions
isha+0.011
head+0.011
 germ+0.011
issy+0.011
 queens+0.010
Neg logit contributions
roads-0.009
vered-0.009
stack-0.009
 edge-0.008
am-0.008
Token,
Token ID11
Feature activation+5.31e-02

Pos logit contributions
head+0.014
 germ+0.013
bows+0.013
 queens+0.013
isha+0.013
Neg logit contributions
roads-0.012
stack-0.012
vered-0.011
ued-0.010
 atop-0.010
Token and
Token ID290
Feature activation+1.11e-02

Pos logit contributions
head+0.075
issy+0.074
isha+0.074
 germ+0.073
bows+0.072
Neg logit contributions
roads-0.070
vered-0.066
stack-0.064
 edge-0.060
 atop-0.057
Token yellow
Token ID7872
Feature activation-1.66e-03

Pos logit contributions
bows+0.015
head+0.014
 queens+0.013
 germ+0.013
isha+0.013
Neg logit contributions
roads-0.018
vered-0.017
stack-0.016
ued-0.015
ulously-0.014
Token flowers
Token ID12734
Feature activation+5.59e-03

Pos logit contributions
roads+0.002
vered+0.002
stack+0.002
 tal+0.002
ued+0.002
Neg logit contributions
head-0.002
bows-0.002
isha-0.002
 queens-0.002
issy-0.002
Token.
Token ID13
Feature activation-5.63e-03

Pos logit contributions
bows+0.008
head+0.008
 queens+0.008
 germ+0.008
isha+0.008
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ued-0.007
am-0.006
Token Lily
Token ID20037
Feature activation+1.47e-02

Pos logit contributions
roads+0.011
vered+0.011
stack+0.011
ued+0.010
am+0.010
Neg logit contributions
bows-0.005
 queens-0.005
head-0.004
 germ-0.004
isha-0.004
Token join
Token ID4654
Feature activation-1.22e-02

Pos logit contributions
bows+0.014
head+0.013
 queens+0.013
 smell+0.013
 germ+0.012
Neg logit contributions
roads-0.024
vered-0.024
stack-0.022
ued-0.021
 tal-0.021
Token them
Token ID606
Feature activation+2.75e-02

Pos logit contributions
roads+0.020
vered+0.018
stack+0.018
ued+0.017
 tal+0.016
Neg logit contributions
bows-0.017
head-0.016
 queens-0.015
 germ-0.014
isha-0.014
Token.
Token ID13
Feature activation+8.27e-03

Pos logit contributions
head+0.041
bows+0.041
 germ+0.039
 queens+0.038
isha+0.038
Neg logit contributions
roads-0.037
vered-0.034
stack-0.033
ued-0.030
am-0.029
Token They
Token ID1119
Feature activation+2.46e-02

Pos logit contributions
bows+0.007
head+0.007
 queens+0.006
 germ+0.006
isha+0.006
Neg logit contributions
roads-0.017
vered-0.017
stack-0.016
ued-0.015
 tal-0.015
Token poured
Token ID19036
Feature activation+1.86e-02

Pos logit contributions
bows+0.032
 queens+0.029
head+0.029
 smell+0.027
 germ+0.026
Neg logit contributions
roads-0.042
vered-0.040
stack-0.037
ued-0.036
 tal-0.035
Token tea
Token ID8887
Feature activation+5.93e-02

Pos logit contributions
bows+0.030
head+0.028
 queens+0.027
isha+0.027
 germ+0.026
Neg logit contributions
roads-0.025
vered-0.023
stack-0.022
ued-0.020
ulously-0.020
Token and
Token ID290
Feature activation+1.82e-02

Pos logit contributions
 queens+0.096
isha+0.096
 germ+0.095
head+0.093
bows+0.092
Neg logit contributions
roads-0.063
stack-0.060
vered-0.056
ued-0.054
 edge-0.051
Token served
Token ID4983
Feature activation+2.20e-02

Pos logit contributions
bows+0.018
head+0.017
 queens+0.015
isha+0.015
issy+0.015
Neg logit contributions
roads-0.035
vered-0.033
stack-0.032
ued-0.030
 tal-0.030
Token cookies
Token ID14746
Feature activation+2.85e-02

Pos logit contributions
bows+0.030
head+0.028
 queens+0.028
 germ+0.026
isha+0.026
Neg logit contributions
roads-0.036
vered-0.033
stack-0.032
ued-0.030
 tal-0.029
Token.
Token ID13
Feature activation+5.90e-03

Pos logit contributions
bows+0.040
head+0.039
 queens+0.038
 germ+0.037
isha+0.036
Neg logit contributions
roads-0.041
stack-0.039
vered-0.038
ued-0.034
 tal-0.033
Token They
Token ID1119
Feature activation+2.36e-02

Pos logit contributions
bows+0.006
head+0.005
 queens+0.005
 germ+0.005
isha+0.004
Neg logit contributions
roads-0.012
vered-0.011
stack-0.011
ued-0.010
 tal-0.010
Token aunt
Token ID25949
Feature activation+3.31e-03

Pos logit contributions
roads+0.024
vered+0.022
ued+0.020
stack+0.020
ulously+0.020
Neg logit contributions
bows-0.014
 she-0.012
 smell-0.012
 fashion-0.011
 queens-0.011
Token gave
Token ID2921
Feature activation+1.07e-02

Pos logit contributions
bows+0.005
head+0.004
 queens+0.004
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.005
vered-0.005
stack-0.005
ued-0.004
 tal-0.004
Token her
Token ID607
Feature activation-7.71e-03

Pos logit contributions
bows+0.009
head+0.008
 queens+0.007
 germ+0.007
isha+0.006
Neg logit contributions
roads-0.023
vered-0.022
stack-0.021
ued-0.020
ulously-0.020
Token for
Token ID329
Feature activation+4.56e-04

Pos logit contributions
roads+0.015
vered+0.014
stack+0.014
ued+0.013
ulously+0.013
Neg logit contributions
bows-0.008
 smell-0.007
 queens-0.007
head-0.007
 fashion-0.007
Token her
Token ID607
Feature activation+1.94e-03

Pos logit contributions
bows+0.000
head+0.000
 queens+0.000
 germ+0.000
 smell+0.000
Neg logit contributions
roads-0.001
vered-0.001
stack-0.001
ued-0.001
ulously-0.001
Token birthday
Token ID10955
Feature activation+3.79e-02

Pos logit contributions
bows+0.002
 smell+0.002
 queens+0.002
head+0.002
 she+0.002
Neg logit contributions
roads-0.004
vered-0.004
stack-0.003
ulously-0.003
ued-0.003
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
bows+0.055
head+0.052
 queens+0.051
 germ+0.049
isha+0.047
Neg logit contributions
roads-0.055
vered-0.051
stack-0.049
ued-0.045
 tal-0.044
Token She
Token ID1375
Feature activation+1.33e-02

Pos logit contributions
 queens+0.014
bows+0.014
head+0.012
 germ+0.012
isha+0.011
Neg logit contributions
roads-0.018
vered-0.016
stack-0.016
ued-0.015
 edge-0.015
Token did
Token ID750
Feature activation+1.49e-02

Pos logit contributions
bows+0.017
head+0.016
 queens+0.015
isha+0.015
 germ+0.015
Neg logit contributions
roads-0.023
vered-0.021
stack-0.021
ued-0.019
 tal-0.019
Token not
Token ID407
Feature activation+2.86e-03

Pos logit contributions
head+0.024
bows+0.023
issy+0.023
 queens+0.023
isha+0.022
Neg logit contributions
roads-0.020
vered-0.019
ued-0.017
ered-0.016
ieved-0.016
Token want
Token ID765
Feature activation-1.02e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
isha+0.004
omm+0.004
Neg logit contributions
roads-0.004
vered-0.003
 prove-0.003
ued-0.003
 pleaded-0.003
Token was
Token ID373
Feature activation-7.48e-03

Pos logit contributions
bows+0.028
head+0.027
 queens+0.026
 germ+0.024
isha+0.023
Neg logit contributions
roads-0.030
vered-0.029
stack-0.027
ued-0.025
ulously-0.024
Token so
Token ID523
Feature activation+1.46e-04

Pos logit contributions
roads+0.011
vered+0.011
stack+0.010
ued+0.010
used+0.009
Neg logit contributions
bows-0.011
head-0.010
 queens-0.009
 germ-0.009
issy-0.009
Token excited
Token ID6568
Feature activation+1.92e-02

Pos logit contributions
bows+0.000
head+0.000
 queens+0.000
issy+0.000
 germ+0.000
Neg logit contributions
roads-0.000
vered-0.000
ued-0.000
used-0.000
stack-0.000
Token to
Token ID284
Feature activation+3.66e-03

Pos logit contributions
 queens+0.033
bows+0.032
 germ+0.032
isha+0.031
issy+0.031
Neg logit contributions
roads-0.021
am-0.016
vered-0.015
 replied-0.015
ued-0.015
Token see
Token ID766
Feature activation-6.03e-03

Pos logit contributions
bows+0.005
head+0.005
 queens+0.004
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.006
vered-0.006
stack-0.005
ued-0.005
ulously-0.005
Token what
Token ID644
Feature activation+3.98e-02

Pos logit contributions
roads+0.011
vered+0.011
stack+0.010
ued+0.010
 tal+0.009
Neg logit contributions
bows-0.007
head-0.006
 queens-0.006
 she-0.006
 smell-0.006
Token the
Token ID262
Feature activation+1.17e-02

Pos logit contributions
bows+0.052
head+0.049
 queens+0.047
 germ+0.044
isha+0.043
Neg logit contributions
roads-0.066
vered-0.061
stack-0.057
ued-0.054
ulously-0.053
Token day
Token ID1110
Feature activation+1.11e-02

Pos logit contributions
bows+0.014
head+0.013
 queens+0.013
isha+0.012
 germ+0.011
Neg logit contributions
roads-0.021
vered-0.019
stack-0.019
ued-0.017
ulously-0.017
Token would
Token ID561
Feature activation+3.38e-02

Pos logit contributions
bows+0.018
 queens+0.017
head+0.017
 germ+0.016
isha+0.016
Neg logit contributions
roads-0.015
vered-0.014
stack-0.013
ued-0.012
ulously-0.011
Token bring
Token ID2222
Feature activation+1.57e-03

Pos logit contributions
bows+0.048
head+0.045
 queens+0.044
isha+0.042
 germ+0.041
Neg logit contributions
roads-0.053
vered-0.049
stack-0.047
ued-0.044
ulously-0.042
Token!
Token ID0
Feature activation-1.71e-02

Pos logit contributions
bows+0.002
head+0.002
 queens+0.002
isha+0.002
 germ+0.002
Neg logit contributions
roads-0.003
vered-0.002
stack-0.002
ued-0.002
 tal-0.002
TokenMom
Token ID29252
Feature activation+4.28e-03

Pos logit contributions
bows+0.007
head+0.007
 queens+0.007
isha+0.006
 Emmy+0.006
Neg logit contributions
roads-0.010
vered-0.010
stack-0.010
ued-0.009
 tal-0.009
Tokenmy
Token ID1820
Feature activation+7.53e-03

Pos logit contributions
bows+0.005
 queens+0.005
head+0.005
 germ+0.005
isha+0.004
Neg logit contributions
roads-0.007
vered-0.007
stack-0.006
am-0.006
ulously-0.006
Token,
Token ID11
Feature activation+2.48e-02

Pos logit contributions
 queens+0.012
bows+0.011
head+0.011
 germ+0.010
isha+0.010
Neg logit contributions
vered-0.010
roads-0.009
stack-0.009
am-0.008
ued-0.008
Token I
Token ID314
Feature activation-7.63e-03

Pos logit contributions
bows+0.032
 queens+0.027
head+0.027
 germ+0.025
issy+0.024
Neg logit contributions
roads-0.042
vered-0.040
stack-0.038
ued-0.036
ulously-0.035
Token look
Token ID804
Feature activation+3.85e-02

Pos logit contributions
roads+0.014
vered+0.013
stack+0.012
ued+0.012
ulously+0.011
Neg logit contributions
bows-0.009
head-0.008
 queens-0.008
 germ-0.007
isha-0.007
Token nice
Token ID3621
Feature activation+3.91e-02

Pos logit contributions
bows+0.056
head+0.052
 queens+0.051
 germ+0.048
isha+0.047
Neg logit contributions
roads-0.059
vered-0.055
stack-0.052
ued-0.049
 tal-0.047
Token in
Token ID287
Feature activation+4.61e-03

Pos logit contributions
bows+0.055
head+0.049
 queens+0.048
 germ+0.048
issy+0.047
Neg logit contributions
roads-0.060
vered-0.056
stack-0.052
ued-0.050
ulously-0.048
Token my
Token ID616
Feature activation+3.15e-03

Pos logit contributions
bows+0.006
head+0.006
 queens+0.006
 germ+0.005
isha+0.005
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ued-0.007
 tal-0.006
Token suit
Token ID6050
Feature activation-2.97e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.003
 germ+0.003
 smell+0.003
Neg logit contributions
roads-0.006
vered-0.005
stack-0.005
ued-0.005
ulously-0.005
Token!"
Token ID2474
Feature activation-7.74e-03

Pos logit contributions
roads+0.005
vered+0.005
stack+0.005
ued+0.004
 tal+0.004
Neg logit contributions
bows-0.004
head-0.003
 queens-0.003
isha-0.003
 germ-0.003
Token
Token ID198
Feature activation-9.86e-03

Pos logit contributions
roads+0.012
vered+0.012
stack+0.011
ued+0.010
 tal+0.009
Neg logit contributions
head-0.011
bows-0.010
 she-0.010
isha-0.010
 Emmy-0.010
Token was
Token ID373
Feature activation+6.34e-03

Pos logit contributions
bows+0.035
head+0.033
 queens+0.030
 smell+0.030
 she+0.029
Neg logit contributions
roads-0.041
vered-0.038
stack-0.036
ued-0.033
 tal-0.033
Token all
Token ID477
Feature activation+1.53e-03

Pos logit contributions
bows+0.008
head+0.007
 queens+0.007
 germ+0.007
isha+0.006
Neg logit contributions
roads-0.011
vered-0.010
stack-0.010
ued-0.009
 tal-0.009
Token covered
Token ID5017
Feature activation+8.59e-03

Pos logit contributions
bows+0.002
head+0.002
 queens+0.002
 smell+0.002
 she+0.002
Neg logit contributions
roads-0.003
vered-0.003
stack-0.003
ued-0.002
 tal-0.002
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
bows+0.012
head+0.011
 queens+0.011
 she+0.010
 smell+0.010
Neg logit contributions
roads-0.014
vered-0.013
stack-0.012
ued-0.012
 tal-0.012
Token
Token ID198
Feature activation-5.22e-03

Pos logit contributions
roads+0.023
vered+0.022
stack+0.020
ued+0.019
ulously+0.018
Neg logit contributions
bows-0.021
head-0.021
 queens-0.019
 she-0.019
isha-0.019
Token
Token ID198
Feature activation+8.93e-03

Pos logit contributions
roads+0.010
vered+0.010
stack+0.009
iped+0.009
ishly+0.008
Neg logit contributions
 she-0.005
 She-0.005
 Hanna-0.005
 Lilly-0.005
head-0.005
TokenNext
Token ID10019
Feature activation-8.38e-03

Pos logit contributions
head+0.009
bows+0.009
 queens+0.009
isha+0.008
 she+0.008
Neg logit contributions
roads-0.016
vered-0.016
stack-0.015
 tal-0.014
ued-0.014
Token,
Token ID11
Feature activation-7.82e-03

Pos logit contributions
roads+0.015
vered+0.014
stack+0.014
ued+0.013
 tal+0.012
Neg logit contributions
bows-0.010
head-0.009
 queens-0.009
 germ-0.008
isha-0.008
Token Mama
Token ID40084
Feature activation+2.40e-02

Pos logit contributions
roads+0.014
vered+0.013
stack+0.013
ued+0.012
ulously+0.012
Neg logit contributions
bows-0.009
head-0.008
 queens-0.008
 germ-0.008
isha-0.007
Token brought
Token ID3181
Feature activation+5.91e-03

Pos logit contributions
bows+0.036
head+0.034
 queens+0.033
 germ+0.031
isha+0.031
Neg logit contributions
roads-0.035
vered-0.033
stack-0.032
ued-0.029
 tal-0.028
Token out
Token ID503
Feature activation-2.04e-03

Pos logit contributions
bows+0.008
head+0.007
 queens+0.007
 germ+0.007
isha+0.006
Neg logit contributions
roads-0.010
vered-0.009
stack-0.009
ued-0.008
 tal-0.008
Token she
Token ID673
Feature activation+1.02e-02

Pos logit contributions
bows+0.003
head+0.003
 queens+0.003
 germ+0.003
isha+0.002
Neg logit contributions
roads-0.004
vered-0.004
stack-0.004
ued-0.003
 tal-0.003
Token heard
Token ID2982
Feature activation-4.86e-03

Pos logit contributions
head+0.011
bows+0.011
 queens+0.011
isha+0.011
 smell+0.010
Neg logit contributions
roads-0.019
stack-0.018
vered-0.017
ued-0.016
cut-0.016
Token laughter
Token ID20263
Feature activation+3.68e-02

Pos logit contributions
roads+0.009
vered+0.009
stack+0.008
ued+0.008
 tal+0.007
Neg logit contributions
bows-0.005
head-0.005
 queens-0.005
 smell-0.005
 germ-0.005
Token coming
Token ID2406
Feature activation+4.55e-03

Pos logit contributions
bows+0.054
 queens+0.054
 germ+0.053
issy+0.051
head+0.050
Neg logit contributions
roads-0.050
vered-0.043
stack-0.040
 edge-0.039
ued-0.039
Token from
Token ID422
Feature activation-2.10e-02

Pos logit contributions
bows+0.007
head+0.006
 queens+0.006
 germ+0.006
isha+0.006
Neg logit contributions
roads-0.006
stack-0.006
vered-0.006
 edge-0.005
ued-0.005
Token a
Token ID257
Feature activation+8.78e-03

Pos logit contributions
vered+0.036
roads+0.035
ued+0.034
ieved+0.034
am+0.034
Neg logit contributions
head-0.023
bows-0.023
 smell-0.023
 she-0.023
 queens-0.021
Token nearby
Token ID6716
Feature activation-2.58e-02

Pos logit contributions
bows+0.013
head+0.013
 queens+0.012
 germ+0.012
isha+0.011
Neg logit contributions
roads-0.013
vered-0.012
stack-0.011
ued-0.011
ulously-0.010
Token park
Token ID3952
Feature activation+8.76e-03

Pos logit contributions
roads+0.035
vered+0.034
stack+0.030
ued+0.029
ulously+0.028
Neg logit contributions
bows-0.041
head-0.040
 queens-0.038
 smell-0.037
 germ-0.037
Token.
Token ID13
Feature activation+1.49e-03

Pos logit contributions
bows+0.010
head+0.009
 she+0.009
 smell+0.008
 queens+0.008
Neg logit contributions
vered-0.016
roads-0.015
ulously-0.014
ued-0.014
 tal-0.014
Token She
Token ID1375
Feature activation+2.20e-02

Pos logit contributions
bows+0.001
head+0.001
 queens+0.001
 germ+0.001
isha+0.001
Neg logit contributions
roads-0.003
vered-0.003
stack-0.003
ued-0.003
 tal-0.003
Token turned
Token ID2900
Feature activation+2.57e-02

Pos logit contributions
head+0.024
bows+0.024
 queens+0.023
 smell+0.023
 she+0.023
Neg logit contributions
roads-0.040
stack-0.037
vered-0.036
ued-0.033
cut-0.033
Token his
Token ID465
Feature activation-5.36e-04

Pos logit contributions
roads+0.007
vered+0.007
stack+0.007
ued+0.006
 tal+0.006
Neg logit contributions
bows-0.006
head-0.006
 queens-0.005
 smell-0.005
 germ-0.005
Token groceries
Token ID38464
Feature activation-3.97e-03

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
ued+0.001
ulously+0.001
Neg logit contributions
 smell-0.000
bows-0.000
 she-0.000
 spill-0.000
 germ-0.000
Token home
Token ID1363
Feature activation+2.95e-02

Pos logit contributions
roads+0.006
vered+0.006
stack+0.006
ued+0.005
 tal+0.005
Neg logit contributions
bows-0.006
head-0.005
 queens-0.005
 germ-0.005
isha-0.005
Token.
Token ID13
Feature activation+1.57e-02

Pos logit contributions
bows+0.032
head+0.029
 queens+0.028
 germ+0.026
 smell+0.026
Neg logit contributions
roads-0.056
vered-0.053
stack-0.050
ued-0.048
ulously-0.047
Token He
Token ID679
Feature activation+7.13e-03

Pos logit contributions
bows+0.022
head+0.021
 queens+0.020
 germ+0.019
isha+0.019
Neg logit contributions
roads-0.025
vered-0.023
stack-0.022
ued-0.020
 tal-0.020
Token put
Token ID1234
Feature activation+8.51e-03

Pos logit contributions
bows+0.008
head+0.008
 queens+0.008
 smell+0.008
isha+0.008
Neg logit contributions
roads-0.013
vered-0.012
stack-0.011
ued-0.011
used-0.010
Token them
Token ID606
Feature activation+2.06e-02

Pos logit contributions
bows+0.012
head+0.012
 queens+0.011
 smell+0.011
 germ+0.010
Neg logit contributions
roads-0.013
vered-0.012
stack-0.012
ued-0.011
 tal-0.011
Token away
Token ID1497
Feature activation+1.72e-02

Pos logit contributions
bows+0.035
head+0.033
 queens+0.033
 germ+0.031
isha+0.031
Neg logit contributions
roads-0.026
vered-0.024
stack-0.023
ued-0.021
 tal-0.020
Token and
Token ID290
Feature activation+2.21e-03

Pos logit contributions
bows+0.017
head+0.015
 queens+0.015
 she+0.014
 smell+0.014
Neg logit contributions
roads-0.035
vered-0.032
stack-0.031
ued-0.030
ulously-0.029
Token made
Token ID925
Feature activation+2.67e-02

Pos logit contributions
bows+0.002
head+0.002
 she+0.002
 queens+0.002
 smell+0.002
Neg logit contributions
roads-0.004
vered-0.004
ued-0.004
stack-0.004
used-0.003
Token a
Token ID257
Feature activation+8.70e-04

Pos logit contributions
bows+0.036
head+0.034
 queens+0.033
 germ+0.031
 smell+0.030
Neg logit contributions
roads-0.044
vered-0.041
stack-0.040
ued-0.037
 tal-0.035
Token
Token ID198
Feature activation-1.38e-02

Pos logit contributions
 she+0.001
head+0.001
 She+0.001
bows+0.001
 queens+0.001
Neg logit contributions
vered-0.002
roads-0.002
stack-0.001
ulously-0.001
ued-0.001
Token
Token ID198
Feature activation+6.18e-04

Pos logit contributions
vered+0.027
stack+0.027
roads+0.027
ishly+0.026
ued+0.024
Neg logit contributions
 she-0.013
head-0.013
 She-0.013
L-0.013
 queens-0.012
TokenTom
Token ID13787
Feature activation+2.62e-03

Pos logit contributions
bows+0.001
head+0.001
 queens+0.001
 she+0.001
 germ+0.001
Neg logit contributions
roads-0.001
vered-0.001
stack-0.001
ued-0.001
 tal-0.001
Token nods
Token ID34833
Feature activation-1.53e-02

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 smell+0.004
 germ+0.004
Neg logit contributions
roads-0.004
vered-0.003
stack-0.003
ued-0.003
 tal-0.003
Token.
Token ID13
Feature activation+7.75e-03

Pos logit contributions
roads+0.028
stack+0.027
vered+0.027
ued+0.025
ulously+0.024
Neg logit contributions
bows-0.017
head-0.016
 queens-0.016
 she-0.015
 smell-0.015
Token He
Token ID679
Feature activation-7.38e-03

Pos logit contributions
bows+0.009
head+0.008
 she+0.008
 queens+0.007
 She+0.007
Neg logit contributions
roads-0.015
vered-0.014
stack-0.013
ued-0.013
ulously-0.013
Token does
Token ID857
Feature activation+4.75e-03

Pos logit contributions
roads+0.010
vered+0.010
stack+0.009
ued+0.009
 tal+0.008
Neg logit contributions
bows-0.011
head-0.011
 queens-0.011
 germ-0.010
isha-0.010
Token not
Token ID407
Feature activation-1.20e-02

Pos logit contributions
bows+0.005
head+0.004
 queens+0.004
 germ+0.004
 smell+0.004
Neg logit contributions
roads-0.009
vered-0.009
stack-0.009
ued-0.008
 tal-0.008
Token want
Token ID765
Feature activation-1.59e-02

Pos logit contributions
roads+0.018
vered+0.016
ued+0.015
stack+0.014
 prove+0.014
Neg logit contributions
bows-0.015
head-0.015
isha-0.015
 queens-0.015
omm-0.014
Token to
Token ID284
Feature activation-3.23e-03

Pos logit contributions
roads+0.031
vered+0.030
stack+0.029
ued+0.028
ieved+0.026
Neg logit contributions
bows-0.016
head-0.015
 queens-0.015
 germ-0.014
 smell-0.013
Token be
Token ID307
Feature activation-2.23e-02

Pos logit contributions
roads+0.005
vered+0.005
stack+0.005
ued+0.004
 tal+0.004
Neg logit contributions
bows-0.004
head-0.004
 queens-0.004
 germ-0.004
isha-0.004
Token so
Token ID523
Feature activation-1.83e-02

Pos logit contributions
roads+0.008
vered+0.008
stack+0.007
ued+0.007
 tal+0.007
Neg logit contributions
bows-0.006
head-0.006
 queens-0.005
 germ-0.005
isha-0.005
Token much
Token ID881
Feature activation+2.22e-02

Pos logit contributions
vered+0.035
roads+0.034
ued+0.032
 tal+0.030
am+0.030
Neg logit contributions
bows-0.018
head-0.017
isha-0.017
 germ-0.017
 queens-0.016
Token fun
Token ID1257
Feature activation+2.97e-02

Pos logit contributions
bows+0.025
head+0.024
isha+0.023
 queens+0.023
issy+0.021
Neg logit contributions
roads-0.040
vered-0.038
stack-0.034
ued-0.034
 tal-0.034
Token together
Token ID1978
Feature activation+9.48e-03

Pos logit contributions
bows+0.038
head+0.035
 queens+0.034
 she+0.032
 smell+0.032
Neg logit contributions
roads-0.051
vered-0.047
stack-0.046
ued-0.043
ulously-0.042
Token until
Token ID1566
Feature activation+1.36e-02

Pos logit contributions
bows+0.009
 she+0.009
head+0.008
 queens+0.008
 smell+0.008
Neg logit contributions
roads-0.019
vered-0.017
stack-0.017
ued-0.016
ulously-0.016
Token the
Token ID262
Feature activation-1.85e-04

Pos logit contributions
bows+0.021
head+0.020
 queens+0.019
 germ+0.019
isha+0.019
Neg logit contributions
roads-0.019
vered-0.018
stack-0.017
ued-0.016
ulously-0.015
Token sun
Token ID4252
Feature activation+4.02e-02

Pos logit contributions
roads+0.000
vered+0.000
stack+0.000
ued+0.000
 tal+0.000
Neg logit contributions
bows-0.000
head-0.000
 queens-0.000
 germ-0.000
isha-0.000
Token went
Token ID1816
Feature activation+2.10e-02

Pos logit contributions
bows+0.052
head+0.048
 queens+0.048
 germ+0.044
isha+0.043
Neg logit contributions
roads-0.068
vered-0.063
stack-0.061
ued-0.057
ulously-0.055
Token down
Token ID866
Feature activation+1.00e-02

Pos logit contributions
bows+0.043
 queens+0.042
head+0.041
isha+0.040
 germ+0.040
Neg logit contributions
roads-0.019
stack-0.016
vered-0.015
ued-0.014
 atop-0.013
Token and
Token ID290
Feature activation-2.18e-03

Pos logit contributions
bows+0.013
head+0.012
 queens+0.012
 germ+0.011
 smell+0.011
Neg logit contributions
roads-0.017
vered-0.016
stack-0.015
ued-0.015
 tal-0.014
Token it
Token ID340
Feature activation+1.23e-02

Pos logit contributions
roads+0.004
vered+0.004
stack+0.003
ued+0.003
 tal+0.003
Neg logit contributions
bows-0.003
head-0.003
 queens-0.003
 she-0.003
 smell-0.003
Tokenak
Token ID461
Feature activation-2.14e-02

Pos logit contributions
roads+0.022
vered+0.020
stack+0.020
ued+0.018
ishly+0.017
Neg logit contributions
bows-0.031
head-0.029
 queens-0.028
 germ-0.027
isha-0.027
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
roads+0.037
vered+0.035
stack+0.034
ued+0.032
ulously+0.031
Neg logit contributions
bows-0.027
head-0.025
 queens-0.024
 germ-0.022
 smell-0.022
Token It
Token ID632
Feature activation+1.40e-02

Pos logit contributions
bows+0.016
head+0.016
 queens+0.015
 germ+0.013
isha+0.013
Neg logit contributions
roads-0.027
vered-0.026
stack-0.024
ued-0.024
ulously-0.022
Token flies
Token ID17607
Feature activation-2.81e-02

Pos logit contributions
bows+0.019
head+0.017
 smell+0.017
 queens+0.017
 germ+0.016
Neg logit contributions
roads-0.023
vered-0.021
stack-0.021
ued-0.019
ieved-0.018
Token to
Token ID284
Feature activation-2.05e-03

Pos logit contributions
roads+0.038
vered+0.035
stack+0.033
ued+0.030
ulously+0.029
Neg logit contributions
bows-0.046
head-0.043
 queens-0.043
 germ-0.041
isha-0.040
Token the
Token ID262
Feature activation-1.50e-02

Pos logit contributions
roads+0.004
vered+0.004
ued+0.004
ieved+0.004
am+0.004
Neg logit contributions
 smell-0.002
head-0.002
 queens-0.002
 spill-0.002
 she-0.002
Token p
Token ID279
Feature activation+1.82e-02

Pos logit contributions
vered+0.027
roads+0.026
ued+0.024
ieved+0.024
used+0.023
Neg logit contributions
bows-0.019
 smell-0.019
head-0.018
 queens-0.018
 germ-0.018
Tokenuddle
Token ID24500
Feature activation+6.74e-03

Pos logit contributions
bows+0.030
head+0.028
 queens+0.028
 germ+0.026
isha+0.026
Neg logit contributions
roads-0.024
vered-0.022
stack-0.021
ued-0.019
 tal-0.019
Token.
Token ID13
Feature activation+9.78e-03

Pos logit contributions
head+0.007
bows+0.007
 she+0.006
 queens+0.005
 smell+0.005
Neg logit contributions
vered-0.013
roads-0.013
ued-0.012
 tal-0.012
ieved-0.012
Token It
Token ID632
Feature activation+1.23e-02

Pos logit contributions
head+0.010
bows+0.010
 queens+0.009
 she+0.008
 She+0.008
Neg logit contributions
roads-0.019
vered-0.019
stack-0.017
ued-0.017
ieved-0.016
Token sees
Token ID7224
Feature activation-1.59e-02

Pos logit contributions
bows+0.017
head+0.015
 smell+0.015
 queens+0.015
 germ+0.014
Neg logit contributions
roads-0.020
vered-0.019
stack-0.018
ued-0.017
 tal-0.016
Token his
Token ID465
Feature activation-3.37e-03

Pos logit contributions
bows+0.017
 queens+0.016
head+0.016
 smell+0.015
 she+0.015
Neg logit contributions
roads-0.022
vered-0.021
stack-0.020
ued-0.019
 tal-0.018
Token cars
Token ID5006
Feature activation-1.09e-02

Pos logit contributions
roads+0.008
vered+0.007
stack+0.007
ued+0.007
ieved+0.006
Neg logit contributions
bows-0.003
 queens-0.002
 smell-0.002
head-0.002
 germ-0.002
Token.
Token ID13
Feature activation+2.18e-02

Pos logit contributions
roads+0.022
vered+0.021
stack+0.020
ued+0.020
ulously+0.019
Neg logit contributions
bows-0.012
head-0.010
 she-0.009
 queens-0.009
 spill-0.009
Token She
Token ID1375
Feature activation+1.76e-02

Pos logit contributions
bows+0.022
head+0.020
 queens+0.020
 germ+0.018
isha+0.018
Neg logit contributions
roads-0.043
vered-0.040
stack-0.039
ued-0.037
ulously-0.035
Token asked
Token ID1965
Feature activation-2.80e-02

Pos logit contributions
bows+0.023
 queens+0.022
head+0.022
isha+0.020
 germ+0.020
Neg logit contributions
roads-0.030
vered-0.028
stack-0.027
ued-0.025
 tal-0.024
Token him
Token ID683
Feature activation-3.60e-02

Pos logit contributions
roads+0.049
vered+0.046
stack+0.045
ued+0.042
 tal+0.041
Neg logit contributions
bows-0.035
head-0.033
 queens-0.032
 germ-0.030
 she-0.030
Token if
Token ID611
Feature activation-1.52e-02

Pos logit contributions
roads+0.056
vered+0.052
stack+0.050
ued+0.046
am+0.044
Neg logit contributions
bows-0.051
head-0.048
 queens-0.046
 germ-0.044
isha-0.043
Token he
Token ID339
Feature activation+4.31e-03

Pos logit contributions
roads+0.028
vered+0.027
stack+0.026
ued+0.024
ulously+0.023
Neg logit contributions
bows-0.017
head-0.016
 queens-0.015
 germ-0.014
isha-0.014
Token took
Token ID1718
Feature activation-2.17e-03

Pos logit contributions
bows+0.006
head+0.005
 queens+0.005
 germ+0.005
 smell+0.005
Neg logit contributions
roads-0.007
vered-0.007
stack-0.007
ued-0.006
 tal-0.006
Token her
Token ID607
Feature activation+1.93e-02

Pos logit contributions
roads+0.003
vered+0.003
stack+0.003
ued+0.003
ulously+0.003
Neg logit contributions
bows-0.003
head-0.003
 queens-0.003
 germ-0.003
isha-0.003
Token cr
Token ID1067
Feature activation+1.04e-02

Pos logit contributions
bows+0.020
head+0.017
 queens+0.017
 germ+0.016
 smell+0.016
Neg logit contributions
roads-0.039
vered-0.037
stack-0.036
ued-0.034
ulously-0.032
Token anything
Token ID1997
Feature activation+8.41e-03

Pos logit contributions
roads+0.033
vered+0.030
stack+0.030
ued+0.028
iped+0.027
Neg logit contributions
 queens-0.022
bows-0.022
head-0.021
 she-0.020
 germ-0.020
Token too
Token ID1165
Feature activation-8.02e-03

Pos logit contributions
bows+0.009
 she+0.009
 queens+0.009
head+0.008
 germ+0.007
Neg logit contributions
roads-0.016
stack-0.015
vered-0.015
ulously-0.014
ued-0.014
Token big
Token ID1263
Feature activation-2.61e-02

Pos logit contributions
roads+0.015
stack+0.014
vered+0.014
ued+0.013
ulously+0.013
Neg logit contributions
bows-0.009
head-0.008
 queens-0.008
 she-0.008
 smell-0.008
Token again
Token ID757
Feature activation+6.49e-03

Pos logit contributions
roads+0.051
stack+0.048
vered+0.047
ued+0.045
ulously+0.044
Neg logit contributions
bows-0.027
head-0.027
 she-0.025
 queens-0.024
 germ-0.023
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
 she+0.005
bows+0.005
 because+0.005
head+0.005
 queens+0.004
Neg logit contributions
roads-0.014
stack-0.014
ued-0.013
vered-0.013
iped-0.012
Token<|endoftext|>
Token ID50256
Feature activation-1.33e-02

Pos logit contributions
roads+0.035
vered+0.033
ued+0.030
stack+0.029
iped+0.028
Neg logit contributions
bows-0.028
head-0.027
 queens-0.026
 she-0.025
isha-0.025
TokenOnce
Token ID7454
Feature activation-1.68e-02

Pos logit contributions
roads+0.024
vered+0.024
stack+0.022
 wounds+0.022
iped+0.021
Neg logit contributions
head-0.015
bows-0.015
 She-0.014
 she-0.013
isha-0.012
Token upon
Token ID2402
Feature activation-3.37e-02

Pos logit contributions
roads+0.037
vered+0.036
stack+0.034
iped+0.032
ued+0.031
Neg logit contributions
 she-0.013
bows-0.012
head-0.012
issy-0.011
 Emmy-0.011
Token a
Token ID257
Feature activation-4.08e-03

Pos logit contributions
roads+0.055
vered+0.051
stack+0.048
ued+0.046
ulously+0.044
Neg logit contributions
bows-0.045
head-0.042
 queens-0.041
 germ-0.039
isha-0.038
Token time
Token ID640
Feature activation-9.29e-04

Pos logit contributions
roads+0.007
vered+0.007
stack+0.007
ued+0.006
 tal+0.006
Neg logit contributions
bows-0.005
head-0.004
 queens-0.004
 germ-0.004
isha-0.004
Token,
Token ID11
Feature activation+6.55e-03

Pos logit contributions
roads+0.002
vered+0.001
stack+0.001
ued+0.001
 tal+0.001
Neg logit contributions
bows-0.001
head-0.001
 queens-0.001
 germ-0.001
isha-0.001
Token They
Token ID1119
Feature activation+1.70e-02

Pos logit contributions
bows+0.003
head+0.003
 queens+0.003
 germ+0.002
isha+0.002
Neg logit contributions
roads-0.004
vered-0.004
stack-0.004
ulously-0.003
ued-0.003
Token knew
Token ID2993
Feature activation+5.75e-04

Pos logit contributions
bows+0.019
 queens+0.017
 smell+0.017
issy+0.017
 she+0.017
Neg logit contributions
roads-0.032
vered-0.029
stack-0.028
ued-0.027
used-0.026
Token that
Token ID326
Feature activation-3.76e-02

Pos logit contributions
 she+0.000
 queens+0.000
bows+0.000
 Lilly+0.000
 because+0.000
Neg logit contributions
roads-0.001
vered-0.001
ued-0.001
stack-0.001
ieved-0.001
Token pistols
Token ID34793
Feature activation-3.45e-02

Pos logit contributions
roads+0.077
vered+0.073
stack+0.071
ued+0.071
ieved+0.067
Neg logit contributions
bows-0.035
 queens-0.034
 she-0.034
head-0.033
 germ-0.032
Token were
Token ID547
Feature activation+9.32e-03

Pos logit contributions
roads+0.064
vered+0.060
stack+0.058
 tal+0.054
ued+0.054
Neg logit contributions
bows-0.040
head-0.034
 smell-0.033
 queens-0.033
 she-0.032
Token dangerous
Token ID4923
Feature activation-4.38e-02

Pos logit contributions
bows+0.010
 queens+0.009
head+0.009
 germ+0.008
 smell+0.008
Neg logit contributions
roads-0.018
vered-0.017
stack-0.016
ued-0.015
 tal-0.015
Token and
Token ID290
Feature activation-4.27e-03

Pos logit contributions
roads+0.081
vered+0.076
stack+0.074
ued+0.069
 tal+0.067
Neg logit contributions
bows-0.050
head-0.046
 queens-0.045
 germ-0.041
isha-0.040
Token they
Token ID484
Feature activation-6.63e-03

Pos logit contributions
roads+0.009
vered+0.008
stack+0.008
ued+0.007
 tal+0.007
Neg logit contributions
bows-0.004
head-0.004
 queens-0.004
 germ-0.004
 she-0.003
Token should
Token ID815
Feature activation+5.06e-06

Pos logit contributions
roads+0.011
vered+0.011
stack+0.010
ued+0.009
 tal+0.009
Neg logit contributions
bows-0.008
head-0.008
 queens-0.008
 smell-0.007
 germ-0.007
Token never
Token ID1239
Feature activation-1.25e-02

Feature not active on prev token;
no predictions were affected.
Token touch
Token ID3638
Feature activation-1.73e-02

Pos logit contributions
roads+0.026
stack+0.025
vered+0.025
ement+0.023
ued+0.022
Neg logit contributions
 smell-0.012
bows-0.012
 spill-0.012
 taste-0.010
 germ-0.010
Token was
Token ID373
Feature activation+6.48e-03

Pos logit contributions
bows+0.017
 she+0.017
 smell+0.017
head+0.016
 queens+0.015
Neg logit contributions
roads-0.029
vered-0.028
stack-0.027
 tal-0.025
ued-0.025
Token a
Token ID257
Feature activation-2.10e-03

Pos logit contributions
bows+0.006
head+0.006
 queens+0.006
 smell+0.006
 germ+0.005
Neg logit contributions
roads-0.013
vered-0.012
stack-0.011
ued-0.011
iped-0.010
Token very
Token ID845
Feature activation+1.35e-02

Pos logit contributions
roads+0.004
vered+0.003
stack+0.003
ued+0.003
 tal+0.003
Neg logit contributions
bows-0.003
head-0.002
 queens-0.002
 germ-0.002
issy-0.002
Token special
Token ID2041
Feature activation+1.35e-02

Pos logit contributions
bows+0.014
head+0.013
 queens+0.013
 germ+0.012
 smell+0.012
Neg logit contributions
roads-0.026
vered-0.025
stack-0.024
ued-0.022
ulously-0.022
Token deer
Token ID20096
Feature activation-2.47e-02

Pos logit contributions
bows+0.017
head+0.016
 smell+0.015
 germ+0.015
 queens+0.015
Neg logit contributions
roads-0.023
vered-0.023
ulously-0.020
stack-0.020
ieved-0.020
Token that
Token ID326
Feature activation-3.09e-02

Pos logit contributions
roads+0.045
vered+0.043
ulously+0.040
stack+0.039
ued+0.039
Neg logit contributions
bows-0.028
head-0.026
 she-0.025
 queens-0.024
 smell-0.024
Token looked
Token ID3114
Feature activation+3.25e-02

Pos logit contributions
roads+0.051
vered+0.049
stack+0.045
ued+0.044
ieved+0.042
Neg logit contributions
bows-0.040
head-0.038
 queens-0.037
 she-0.036
 smell-0.035
Token very
Token ID845
Feature activation+4.71e-03

Pos logit contributions
bows+0.036
head+0.033
 queens+0.032
 germ+0.029
isha+0.029
Neg logit contributions
roads-0.061
vered-0.058
stack-0.056
ued-0.053
 tal-0.051
Token fragile
Token ID21049
Feature activation-2.59e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.005
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.009
vered-0.008
stack-0.008
ued-0.008
 tal-0.007
Token.
Token ID13
Feature activation-4.88e-03

Pos logit contributions
roads+0.051
stack+0.047
vered+0.047
ulously+0.044
ued+0.044
Neg logit contributions
bows-0.027
head-0.024
 she-0.022
 queens-0.022
 smell-0.022
Token It
Token ID632
Feature activation+1.34e-02

Pos logit contributions
roads+0.008
vered+0.008
stack+0.007
ued+0.007
ulously+0.007
Neg logit contributions
head-0.006
bows-0.006
 queens-0.005
 she-0.005
isha-0.005
Token,
Token ID11
Feature activation-1.85e-02

Pos logit contributions
roads+0.013
vered+0.012
stack+0.012
ued+0.011
ulously+0.011
Neg logit contributions
bows-0.007
head-0.007
 queens-0.006
 she-0.006
 smell-0.006
Token Mia
Token ID32189
Feature activation+1.59e-02

Pos logit contributions
roads+0.034
vered+0.032
stack+0.031
ued+0.030
 tal+0.029
Neg logit contributions
bows-0.021
head-0.019
 queens-0.019
 germ-0.017
 smell-0.017
Token wanted
Token ID2227
Feature activation-1.65e-02

Pos logit contributions
bows+0.018
head+0.016
 queens+0.015
isha+0.015
 germ+0.015
Neg logit contributions
roads-0.030
vered-0.028
stack-0.027
ued-0.026
ulously-0.025
Token to
Token ID284
Feature activation-2.95e-03

Pos logit contributions
roads+0.028
vered+0.026
stack+0.025
ued+0.023
 tal+0.023
Neg logit contributions
bows-0.021
head-0.019
 queens-0.019
 germ-0.017
isha-0.017
Token go
Token ID467
Feature activation-8.46e-03

Pos logit contributions
roads+0.006
vered+0.006
stack+0.005
iped+0.005
ued+0.005
Neg logit contributions
 smell-0.003
bows-0.003
 taste-0.003
 spill-0.003
 fashion-0.002
Token kay
Token ID34681
Feature activation-6.32e-02

Pos logit contributions
roads+0.011
vered+0.011
stack+0.011
ued+0.010
ulously+0.010
Neg logit contributions
bows-0.013
head-0.013
 queens-0.013
 smell-0.012
 germ-0.012
Tokenaking
Token ID868
Feature activation-1.08e-02

Pos logit contributions
stack+0.116
vered+0.105
ishly+0.101
roads+0.100
 tal+0.099
Neg logit contributions
head-0.070
 queens-0.065
bows-0.063
COM-0.061
akers-0.057
Token.
Token ID13
Feature activation-1.02e-02

Pos logit contributions
roads+0.019
vered+0.018
stack+0.018
ulously+0.017
ued+0.017
Neg logit contributions
bows-0.012
head-0.012
 she-0.011
 queens-0.011
 smell-0.010
Token She
Token ID1375
Feature activation+3.66e-03

Pos logit contributions
roads+0.024
vered+0.022
stack+0.022
ued+0.021
ulously+0.020
Neg logit contributions
bows-0.007
head-0.006
 queens-0.006
 germ-0.005
isha-0.005
Token thought
Token ID1807
Feature activation+1.13e-02

Pos logit contributions
isha+0.003
 planned+0.003
 smell+0.003
 she+0.003
bows+0.003
Neg logit contributions
roads-0.007
stack-0.007
vered-0.007
used-0.006
cks-0.006
Token it
Token ID340
Feature activation-2.53e-03

Pos logit contributions
bows+0.014
head+0.013
 queens+0.012
 germ+0.012
 she+0.011
Neg logit contributions
roads-0.020
vered-0.019
stack-0.018
ued-0.017
 tal-0.016
Token,
Token ID11
Feature activation+1.55e-03

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 she+0.004
 smell+0.004
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ued-0.007
ulously-0.007
Token but
Token ID475
Feature activation-4.61e-02

Pos logit contributions
bows+0.001
head+0.001
 she+0.001
 queens+0.001
 smell+0.001
Neg logit contributions
roads-0.003
vered-0.003
stack-0.003
ued-0.003
ulously-0.003
Token his
Token ID465
Feature activation-4.49e-02

Pos logit contributions
vered+0.099
roads+0.098
ued+0.097
cks+0.093
ags+0.090
Neg logit contributions
 she-0.049
 because-0.036
 Lilly-0.030
 Lily-0.029
 smell-0.028
Token mother
Token ID2802
Feature activation-1.36e-02

Pos logit contributions
roads+0.101
vered+0.087
ieved+0.085
ued+0.085
stack+0.083
Neg logit contributions
 smell-0.043
bows-0.039
 germ-0.038
 fashion-0.038
 princess-0.038
Token said
Token ID531
Feature activation+1.18e-02

Pos logit contributions
roads+0.026
vered+0.024
stack+0.023
 tal+0.022
ued+0.022
Neg logit contributions
 she-0.015
bows-0.014
issy-0.013
 smell-0.013
head-0.013
Token no
Token ID645
Feature activation-6.42e-02

Pos logit contributions
bows+0.015
head+0.014
 queens+0.013
 germ+0.012
isha+0.012
Neg logit contributions
roads-0.020
vered-0.019
stack-0.018
ued-0.017
 tal-0.017
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
roads+0.093
vered+0.088
stack+0.076
ulously+0.075
am+0.075
Neg logit contributions
bows-0.095
head-0.090
 queens-0.090
isha-0.083
 germ-0.082
Token So
Token ID1406
Feature activation-3.17e-02

Pos logit contributions
roads+0.030
vered+0.029
stack+0.027
ued+0.027
cut+0.026
Neg logit contributions
bows-0.013
 She-0.011
head-0.011
 she-0.011
 Lilly-0.010
Token there
Token ID612
Feature activation-3.50e-02

Pos logit contributions
roads+0.060
vered+0.057
stack+0.054
ued+0.053
 tal+0.049
Neg logit contributions
bows-0.033
head-0.032
 she-0.032
 queens-0.031
 smell-0.029
Token it
Token ID340
Feature activation+1.67e-02

Pos logit contributions
roads+0.071
stack+0.067
cks+0.067
 tal+0.066
ieved+0.064
Neg logit contributions
 she-0.036
 She-0.028
 smell-0.027
bows-0.025
 because-0.024
Token stayed
Token ID9658
Feature activation-8.94e-03

Pos logit contributions
 she+0.016
head+0.015
bows+0.015
 smell+0.014
 germ+0.014
Neg logit contributions
roads-0.033
vered-0.031
stack-0.031
cks-0.030
 tal-0.029
Token it
Token ID340
Feature activation+7.16e-03

Pos logit contributions
roads+0.022
vered+0.021
stack+0.020
ued+0.019
 tal+0.018
Neg logit contributions
bows-0.016
head-0.015
 queens-0.015
 germ-0.014
 smell-0.013
Token,
Token ID11
Feature activation+4.19e-03

Pos logit contributions
bows+0.008
head+0.007
 queens+0.007
 she+0.007
 germ+0.007
Neg logit contributions
roads-0.013
vered-0.013
stack-0.012
ued-0.011
ulously-0.011
Token but
Token ID475
Feature activation-2.97e-02

Pos logit contributions
bows+0.005
head+0.005
 queens+0.004
 germ+0.004
 she+0.004
Neg logit contributions
roads-0.008
vered-0.007
stack-0.007
ued-0.007
ulously-0.006
Token she
Token ID673
Feature activation-5.45e-04

Pos logit contributions
roads+0.068
vered+0.066
stack+0.063
ued+0.061
 tal+0.060
Neg logit contributions
bows-0.019
head-0.018
 queens-0.017
 she-0.016
 germ-0.015
Token said
Token ID531
Feature activation+2.67e-03

Pos logit contributions
roads+0.001
vered+0.001
stack+0.001
ued+0.001
 tal+0.001
Neg logit contributions
 she-0.001
bows-0.001
head-0.001
 smell-0.001
 germ-0.001
Token no
Token ID645
Feature activation-6.37e-02

Pos logit contributions
bows+0.004
head+0.004
 queens+0.004
 germ+0.004
isha+0.004
Neg logit contributions
roads-0.004
vered-0.004
stack-0.003
ued-0.003
ulously-0.003
Token.
Token ID13
Feature activation-4.85e-03

Pos logit contributions
roads+0.091
vered+0.086
stack+0.078
am+0.077
 tal+0.075
Neg logit contributions
bows-0.092
head-0.088
 queens-0.085
isha-0.080
issy-0.079
Token He
Token ID679
Feature activation-2.96e-03

Pos logit contributions
roads+0.009
vered+0.009
stack+0.008
ued+0.008
 tal+0.008
Neg logit contributions
bows-0.006
head-0.005
 queens-0.005
 she-0.005
isha-0.004
Token was
Token ID373
Feature activation-1.41e-02

Pos logit contributions
roads+0.005
stack+0.005
vered+0.005
ued+0.004
cks+0.004
Neg logit contributions
bows-0.003
head-0.003
 smell-0.003
 she-0.003
 germ-0.003
Token so
Token ID523
Feature activation-1.01e-02

Pos logit contributions
roads+0.024
vered+0.022
stack+0.021
ued+0.020
 tal+0.019
Neg logit contributions
bows-0.019
head-0.017
 queens-0.017
 germ-0.016
isha-0.015
Token sad
Token ID6507
Feature activation-1.30e-02

Pos logit contributions
roads+0.018
vered+0.017
stack+0.016
 tal+0.015
ulously+0.014
Neg logit contributions
bows-0.012
head-0.012
 queens-0.012
 smell-0.011
 germ-0.011
Token,
Token ID11
Feature activation+1.87e-03

Pos logit contributions
roads+0.060
vered+0.056
stack+0.055
 tal+0.055
ued+0.052
Neg logit contributions
 she-0.024
bows-0.020
head-0.019
 queens-0.019
 She-0.018
Token "
Token ID366
Feature activation+5.68e-03

Pos logit contributions
 she+0.002
bows+0.002
head+0.002
 queens+0.002
 smell+0.002
Neg logit contributions
roads-0.004
vered-0.004
ulously-0.003
 tal-0.003
stack-0.003
TokenCan
Token ID6090
Feature activation-9.58e-03

Pos logit contributions
bows+0.006
head+0.006
 queens+0.006
 germ+0.005
isha+0.005
Neg logit contributions
roads-0.010
vered-0.010
stack-0.010
ued-0.009
 tal-0.009
Token you
Token ID345
Feature activation-1.12e-02

Pos logit contributions
roads+0.023
vered+0.023
stack+0.021
 tal+0.021
ued+0.021
Neg logit contributions
bows-0.005
 she-0.005
head-0.005
 queens-0.005
 smell-0.004
Token lend
Token ID22096
Feature activation-4.62e-02

Pos logit contributions
roads+0.020
vered+0.018
stack+0.018
ued+0.016
 tal+0.016
Neg logit contributions
bows-0.014
head-0.013
 queens-0.013
 smell-0.013
 germ-0.012
Token me
Token ID502
Feature activation-6.45e-02

Pos logit contributions
roads+0.085
stack+0.079
vered+0.079
ued+0.072
cut+0.068
Neg logit contributions
bows-0.052
head-0.051
 queens-0.050
 germ-0.046
 smell-0.045
Token your
Token ID534
Feature activation-3.57e-02

Pos logit contributions
roads+0.124
stack+0.118
vered+0.116
ued+0.106
iped+0.100
Neg logit contributions
 queens-0.067
head-0.064
bows-0.064
 germ-0.060
 fashion-0.059
Token toy
Token ID13373
Feature activation-5.58e-02

Pos logit contributions
roads+0.069
stack+0.064
ishly+0.058
ued+0.057
vered+0.057
Neg logit contributions
 smell-0.042
 fashion-0.041
 germ-0.039
 princess-0.039
 queens-0.038
Token truck
Token ID7779
Feature activation-4.82e-02

Pos logit contributions
roads+0.104
vered+0.096
stack+0.089
ued+0.089
ieved+0.086
Neg logit contributions
 queens-0.062
head-0.060
bows-0.058
 germ-0.056
 smell-0.056
Token?"
Token ID1701
Feature activation-1.29e-02

Pos logit contributions
roads+0.093
vered+0.091
stack+0.085
ued+0.082
ulously+0.078
Neg logit contributions
bows-0.053
head-0.049
 queens-0.048
 smell-0.045
 germ-0.043
Token Tom
Token ID4186
Feature activation-1.14e-02

Pos logit contributions
roads+0.025
vered+0.025
stack+0.024
ued+0.023
 afloat+0.022
Neg logit contributions
bows-0.014
 she-0.012
head-0.012
 She-0.011
 smell-0.011
Token wanted
Token ID2227
Feature activation-2.43e-02

Pos logit contributions
roads+0.002
stack+0.001
vered+0.001
ulously+0.001
 tal+0.001
Neg logit contributions
bows-0.001
 smell-0.001
head-0.001
 queens-0.001
 she-0.001
Token to
Token ID284
Feature activation-9.50e-03

Pos logit contributions
roads+0.054
stack+0.050
vered+0.050
ued+0.047
ieved+0.046
Neg logit contributions
bows-0.019
 queens-0.019
head-0.018
 smell-0.017
 germ-0.017
Token play
Token ID711
Feature activation-1.79e-02

Pos logit contributions
roads+0.020
vered+0.018
stack+0.018
ement+0.017
iped+0.017
Neg logit contributions
 smell-0.010
 taste-0.009
 spill-0.008
bows-0.008
 fashion-0.007
Token with
Token ID351
Feature activation-3.01e-03

Pos logit contributions
stack+0.039
ulously+0.038
roads+0.037
vered+0.035
iped+0.035
Neg logit contributions
 because-0.014
 like-0.014
 smell-0.014
 fashion-0.013
head-0.013
Token the
Token ID262
Feature activation-9.58e-04

Pos logit contributions
roads+0.005
stack+0.005
vered+0.005
ued+0.004
ieved+0.004
Neg logit contributions
bows-0.004
head-0.004
 queens-0.003
 smell-0.003
 germ-0.003
Token kay
Token ID34681
Feature activation-7.12e-02

Pos logit contributions
roads+0.001
stack+0.001
vered+0.001
ieved+0.001
ued+0.001
Neg logit contributions
bows-0.001
 smell-0.001
 queens-0.001
head-0.001
 germ-0.001
Tokenak
Token ID461
Feature activation-2.21e-02

Pos logit contributions
stack+0.101
vered+0.100
roads+0.099
ishly+0.092
ulously+0.086
Neg logit contributions
head-0.101
bows-0.100
 queens-0.096
COM-0.089
 germ-0.087
Token but
Token ID475
Feature activation-3.53e-02

Pos logit contributions
roads+0.049
vered+0.045
stack+0.045
ulously+0.044
ieved+0.044
Neg logit contributions
bows-0.018
 she-0.017
 because-0.016
head-0.015
 queens-0.013
Token they
Token ID484
Feature activation-4.98e-03

Pos logit contributions
roads+0.077
vered+0.071
stack+0.070
ued+0.066
 tal+0.064
Neg logit contributions
 she-0.028
head-0.026
bows-0.025
 Lilly-0.024
 queens-0.024
Token couldn
Token ID3521
Feature activation-5.77e-03

Pos logit contributions
roads+0.011
vered+0.010
stack+0.009
 tal+0.009
 gru+0.009
Neg logit contributions
 she-0.004
 smell-0.004
 spill-0.004
 because-0.003
 planned-0.003
Token't
Token ID470
Feature activation+5.12e-03

Pos logit contributions
roads+0.013
vered+0.013
stack+0.012
 tal+0.011
ued+0.011
Neg logit contributions
bows-0.004
head-0.004
 queens-0.003
 she-0.003
 smell-0.003