TOP ACTIVATIONS
MAX = 0.028

." <|endoftext|> <|endoftext|> <|endoftext|> <|endoftext|> Anna and Ben are playing with
would take out a j igsaw puzzle and try to solve
proudly . She held the bookmark up to her face and
that the bird liked their song and they allowed the bird
. When I give the song to people , it makes
The cat picked up the folder with its paw . Inside
<|endoftext|> <|endoftext|> <|endoftext|> <|endoftext|> L ila and Ben are friends .
inside ! Scar lett and Jason were so proud
. He walked along the web and made tiny footprints on
, Tim my lost the diary while playing outside . He
" Let 's sing the song together ." Kate smiled
play . Tommy saw the diary and wanted to read it
dream called a " night mare ". She woke up crying
" What is this ?" Sara asks . "
<|endoftext|> <|endoftext|> <|endoftext|> <|endoftext|> <|endoftext|> L ila and Ben are friends
you break my egg ?" Wendy shouted . Her
came because they sang the song . From that day on
world and they loved their song . They cut the cake
out of the massage par lor as fast as he could
also find some clothes in Anna 's closet . They are

MIN ACTIVATIONS
MIN = -0.036

harder to push the wheel bar row . But her backyard
him a big red wheel bar row and filled it with
placed it onto the wheel bar row . John
the cat off the wheel bar row and put him back
light en up the wheel bar row . <|endoftext|> Once there
a big , spinning wheel bar row and put the pumpkin
was wheel ing the wheel bar row around she made sure
uffy had made the wheel bar row much lighter . The
. She saw a wheel bar row , a large sp
of soil into the wheel bar row . It was heavy
He jumped onto the wheel bar row and started rolling around
back with a big wheel bar row . He asked the
. He found a wheel bar row , a tr amp
flavors they liked and what topp ings would go best .
it away in a wheel bar row . Once
filled up lots of wheel bar rows with the waste and
He also saw some tasty seaw eed and decided to give
fun . Soon the wheel bar row was empty and all
The wheel bar row wheel ed the cup
dolls around in a wheel bar row she had found in

INTERVAL 0.012 - 0.028
CONTAINS 0.586%

boy who really valued his attic . He spent most of
. Fisher . " Look at that tree ,
to find that there was nobody else outside . He decided
, Daisy and Brad . Daisy was a boss y hen
Tim my went to the gift shop and bought a toy

INTERVAL -0.004 - 0.012
CONTAINS 82.786%

ily dropped the flag and fell off the swing . She
. They tell stories and laugh . <|endoftext|> L ily liked
was so happy he started to g iggle and splash his
Anna stops and looks at the mail man .
are still hugging and crying . They are not

INTERVAL -0.020 - -0.004
CONTAINS 16.624%

ly showed him to the neighbor . The
sell his meat , but he understood that Lily didn 't
tire while walking . John ran over and
both like , but in a different way ," Dad says
brilliant idea . She told Jack to stay with her grandma

INTERVAL -0.036 - -0.020
CONTAINS 0.004%

Maybe they could grow more av oc ados and share them
" Hello , Mr . Fisher man ! Would you like
of shells , rocks and seaw eed , but Jane was
Wow , Wally is 20 pounds !" Tom exclaimed . "
. The blue truck also stopped and the driver
Token."
Token ID526
Feature activation+3.85e-03

Pos logit contributions
 blush+0.007
Girls+0.006
ume+0.006
bs+0.006
 perfume+0.006
Neg logit contributions
 puck-0.004
wreck-0.004
 ship-0.004
 skate-0.004
 hockey-0.004
Token<|endoftext|>
Token ID50256
Feature activation-6.60e-03

Pos logit contributions
 blush+0.009
ume+0.009
Girls+0.009
 perfume+0.008
bs+0.008
Neg logit contributions
 puck-0.006
 his-0.006
 hockey-0.006
 skate-0.005
 ship-0.005
Token<|endoftext|>
Token ID50256
Feature activation-5.23e-03

Pos logit contributions
 puck+0.013
wreck+0.013
 skate+0.012
 ship+0.012
 motorcycle+0.012
Neg logit contributions
 blush-0.012
Girls-0.012
ume-0.012
 perfume-0.012
bs-0.011
Token<|endoftext|>
Token ID50256
Feature activation-3.09e-03

Pos logit contributions
 puck+0.011
wreck+0.011
 ship+0.011
 skate+0.011
 motorcycle+0.010
Neg logit contributions
 blush-0.009
Girls-0.009
ume-0.008
 perfume-0.008
bs-0.008
Token<|endoftext|>
Token ID50256
Feature activation-1.49e-03

Pos logit contributions
 puck+0.007
wreck+0.006
 ship+0.006
 skate+0.006
 motorcycle+0.006
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
bs-0.005
TokenAnna
Token ID31160
Feature activation+2.79e-02

Pos logit contributions
 puck+0.003
wreck+0.003
 ship+0.003
 skate+0.003
 motorcycle+0.003
Neg logit contributions
 blush-0.003
Girls-0.003
ume-0.002
 perfume-0.002
bs-0.002
Token and
Token ID290
Feature activation-1.06e-03

Pos logit contributions
 blush+0.070
Girls+0.068
ume+0.067
 perfume+0.065
 mascara+0.062
Neg logit contributions
 puck-0.036
 skate-0.036
 ship-0.036
wreck-0.035
 his-0.035
Token Ben
Token ID3932
Feature activation+8.55e-03

Pos logit contributions
 his+0.002
 sailing+0.002
 him+0.002
 sailed+0.001
 skate+0.001
Neg logit contributions
ume-0.002
Girls-0.002
 blush-0.002
 mascara-0.002
 perfume-0.002
Token are
Token ID389
Feature activation+7.56e-03

Pos logit contributions
 blush+0.018
Girls+0.017
ume+0.017
 perfume+0.017
bs+0.017
Neg logit contributions
 puck-0.015
wreck-0.015
 skate-0.014
 ship-0.014
 hockey-0.014
Token playing
Token ID2712
Feature activation-1.56e-03

Pos logit contributions
 blush+0.016
Girls+0.016
ume+0.015
 perfume+0.015
bs+0.014
Neg logit contributions
 puck-0.013
 sailing-0.013
 skate-0.013
wreck-0.012
 ship-0.012
Token with
Token ID351
Feature activation-1.14e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 motorcycle+0.003
Neg logit contributions
 blush-0.003
 perfume-0.003
Girls-0.003
ume-0.002
bs-0.002
Token would
Token ID561
Feature activation-3.51e-03

Pos logit contributions
 puck+0.011
wreck+0.010
 skate+0.010
 hockey+0.010
 ship+0.010
Neg logit contributions
 blush-0.012
Girls-0.012
ume-0.012
 perfume-0.011
bs-0.011
Token take
Token ID1011
Feature activation-5.48e-04

Pos logit contributions
 puck+0.006
wreck+0.006
 skate+0.006
 ship+0.006
 hockey+0.006
Neg logit contributions
 blush-0.008
ume-0.007
Girls-0.007
 perfume-0.007
bs-0.007
Token out
Token ID503
Feature activation+3.04e-03

Pos logit contributions
 puck+0.001
 skate+0.001
wreck+0.001
 ship+0.001
 motorcycle+0.001
Neg logit contributions
 blush-0.001
 perfume-0.001
bs-0.001
ume-0.001
Girls-0.001
Token a
Token ID257
Feature activation+9.17e-03

Pos logit contributions
 blush+0.007
ume+0.007
Girls+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 motorcycle-0.004
Token j
Token ID474
Feature activation+8.62e-03

Pos logit contributions
Girls+0.019
 blush+0.019
ume+0.019
 perfume+0.018
bs+0.017
Neg logit contributions
 puck-0.016
wreck-0.016
 ship-0.016
 skate-0.015
 hockey-0.015
Tokenigsaw
Token ID45636
Feature activation+2.58e-02

Pos logit contributions
 blush+0.008
ume+0.008
bs+0.008
Girls+0.007
 perfume+0.007
Neg logit contributions
wreck-0.025
 puck-0.025
 sailed-0.023
 skate-0.023
 ship-0.023
Token puzzle
Token ID15027
Feature activation+7.78e-03

Pos logit contributions
 blush+0.046
Girls+0.044
ume+0.043
 perfume+0.043
bs+0.042
Neg logit contributions
 puck-0.053
wreck-0.051
 skate-0.051
 ship-0.049
 hockey-0.049
Token and
Token ID290
Feature activation+2.90e-04

Pos logit contributions
 blush+0.014
ume+0.014
 perfume+0.014
bs+0.013
Girls+0.013
Neg logit contributions
 puck-0.015
wreck-0.014
 skate-0.014
 wre-0.014
 iceberg-0.014
Token try
Token ID1949
Feature activation+1.72e-03

Pos logit contributions
 blush+0.001
 perfume+0.001
Girls+0.001
ume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.000
 ship-0.000
 hockey-0.000
Token to
Token ID284
Feature activation-4.02e-03

Pos logit contributions
 blush+0.003
Girls+0.003
 perfume+0.003
ume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 wre-0.003
Token solve
Token ID8494
Feature activation-1.83e-03

Pos logit contributions
 puck+0.007
wreck+0.006
 skate+0.006
 camps+0.006
 ship+0.006
Neg logit contributions
 blush-0.009
Girls-0.008
ume-0.008
 perfume-0.008
bs-0.008
Token proudly
Token ID23017
Feature activation-1.27e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Token.
Token ID13
Feature activation-5.73e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token She
Token ID1375
Feature activation+2.24e-03

Pos logit contributions
 puck+0.010
wreck+0.010
 skate+0.010
 ship+0.010
 gear+0.009
Neg logit contributions
 blush-0.012
Girls-0.012
ume-0.011
 perfume-0.011
bs-0.011
Token held
Token ID2714
Feature activation+4.04e-03

Pos logit contributions
 blush+0.004
Girls+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 gear-0.004
Token the
Token ID262
Feature activation+2.41e-03

Pos logit contributions
 blush+0.009
Girls+0.008
ume+0.008
 perfume+0.008
bs+0.008
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.007
 ship-0.006
 hockey-0.006
Token bookmark
Token ID44007
Feature activation+2.54e-02

Pos logit contributions
Girls+0.004
 blush+0.004
ume+0.004
bs+0.004
Her+0.004
Neg logit contributions
 puck-0.005
 ship-0.005
 skate-0.005
 hockey-0.005
 gear-0.005
Token up
Token ID510
Feature activation-1.01e-03

Pos logit contributions
Girls+0.060
 blush+0.057
ume+0.055
 perfume+0.053
 mascara+0.052
Neg logit contributions
wreck-0.039
 ship-0.038
 puck-0.038
 skate-0.037
 his-0.036
Token to
Token ID284
Feature activation+2.49e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 motorcycle+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token her
Token ID607
Feature activation-4.97e-04

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.004
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.004
 ship-0.004
 hockey-0.004
Token face
Token ID1986
Feature activation+2.94e-03

Pos logit contributions
 puck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
wreck+0.001
Neg logit contributions
Girls-0.001
 blush-0.001
ume-0.001
bs-0.001
 perfume-0.001
Token and
Token ID290
Feature activation+4.59e-04

Pos logit contributions
Girls+0.007
 blush+0.007
ume+0.006
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.005
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token that
Token ID326
Feature activation-1.19e-03

Pos logit contributions
 puck+0.019
wreck+0.019
 skate+0.019
 ship+0.018
 camps+0.018
Neg logit contributions
 blush-0.017
Girls-0.016
 perfume-0.016
ume-0.016
bs-0.016
Token the
Token ID262
Feature activation+2.87e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 camps+0.002
 gear+0.002
Neg logit contributions
 blush-0.002
 perfume-0.002
Girls-0.002
ume-0.002
bs-0.002
Token bird
Token ID6512
Feature activation+7.22e-04

Pos logit contributions
 blush+0.006
Girls+0.006
ume+0.006
bs+0.005
 perfume+0.005
Neg logit contributions
 ship-0.005
 puck-0.005
wreck-0.005
 motorcycle-0.005
 skate-0.005
Token liked
Token ID8288
Feature activation-1.61e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
 mascara+0.002
Neg logit contributions
 ship-0.001
wreck-0.001
 puck-0.001
 sailed-0.001
 skate-0.001
Token their
Token ID511
Feature activation+5.74e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 motorcycle+0.003
Neg logit contributions
 blush-0.003
Girls-0.003
 perfume-0.003
ume-0.003
bs-0.003
Token song
Token ID3496
Feature activation+2.50e-02

Pos logit contributions
 blush+0.012
Girls+0.012
ume+0.011
bs+0.011
 perfume+0.011
Neg logit contributions
 puck-0.010
 ship-0.010
 skate-0.010
wreck-0.010
 sailing-0.010
Token and
Token ID290
Feature activation+3.64e-03

Pos logit contributions
 blush+0.059
Girls+0.059
ume+0.057
 perfume+0.054
bs+0.054
Neg logit contributions
 puck-0.037
wreck-0.036
 ship-0.035
 skate-0.035
 hockey-0.034
Token they
Token ID484
Feature activation-1.59e-03

Pos logit contributions
 blush+0.008
Girls+0.008
ume+0.008
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.006
 ship-0.006
wreck-0.006
 skate-0.006
 his-0.006
Token allowed
Token ID3142
Feature activation+2.49e-03

Pos logit contributions
 sailed+0.002
 ship+0.002
wreck+0.002
 puck+0.002
 sailing+0.002
Neg logit contributions
Girls-0.004
ume-0.004
 blush-0.004
 perfume-0.003
 mascara-0.003
Token the
Token ID262
Feature activation+3.27e-03

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token bird
Token ID6512
Feature activation+2.05e-03

Pos logit contributions
 blush+0.006
Girls+0.006
ume+0.006
bs+0.006
 perfume+0.006
Neg logit contributions
 puck-0.006
 ship-0.006
wreck-0.006
 skate-0.006
 motorcycle-0.006
Token.
Token ID13
Feature activation-4.05e-03

Pos logit contributions
 blush+0.011
Girls+0.010
ume+0.010
bs+0.010
 perfume+0.010
Neg logit contributions
 puck-0.008
wreck-0.008
 ship-0.008
 skate-0.007
 hockey-0.007
Token When
Token ID1649
Feature activation-5.46e-03

Pos logit contributions
 puck+0.008
wreck+0.008
 skate+0.008
 ship+0.008
 gear+0.008
Neg logit contributions
 blush-0.007
Girls-0.007
ume-0.007
 perfume-0.007
bs-0.006
Token I
Token ID314
Feature activation-3.66e-03

Pos logit contributions
 puck+0.012
wreck+0.011
 skate+0.011
 ship+0.011
 motorcycle+0.011
Neg logit contributions
 blush-0.009
Girls-0.009
 perfume-0.009
ume-0.009
bs-0.008
Token give
Token ID1577
Feature activation+7.84e-03

Pos logit contributions
wreck+0.006
 ship+0.006
 skate+0.006
 puck+0.006
 sailed+0.006
Neg logit contributions
Girls-0.008
 blush-0.008
 perfume-0.007
ume-0.007
 mascara-0.007
Token the
Token ID262
Feature activation+5.35e-03

Pos logit contributions
 blush+0.018
ume+0.018
Girls+0.018
bs+0.016
 mascara+0.016
Neg logit contributions
 his-0.012
 hockey-0.011
 ship-0.011
 puck-0.011
 motorcycle-0.011
Token song
Token ID3496
Feature activation+2.48e-02

Pos logit contributions
 blush+0.011
Girls+0.011
ume+0.010
bs+0.010
Her+0.010
Neg logit contributions
 puck-0.009
 ship-0.009
 motorcycle-0.009
 gear-0.009
 skate-0.009
Token to
Token ID284
Feature activation+3.33e-03

Pos logit contributions
Girls+0.062
 blush+0.061
ume+0.056
 mascara+0.055
 perfume+0.054
Neg logit contributions
 his-0.032
 ship-0.031
 puck-0.030
 hockey-0.030
 gear-0.030
Token people
Token ID661
Feature activation-1.15e-03

Pos logit contributions
 blush+0.006
Girls+0.006
ume+0.006
 perfume+0.006
bs+0.005
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.006
 ship-0.006
 gear-0.006
Token,
Token ID11
Feature activation-5.36e-03

Pos logit contributions
wreck+0.002
 puck+0.002
 ship+0.002
 skate+0.002
 hockey+0.002
Neg logit contributions
 blush-0.003
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token it
Token ID340
Feature activation+5.53e-04

Pos logit contributions
 puck+0.011
wreck+0.011
 skate+0.010
 ship+0.010
 camps+0.010
Neg logit contributions
 blush-0.010
Girls-0.009
ume-0.009
 perfume-0.009
bs-0.009
Token makes
Token ID1838
Feature activation+1.14e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
wreck-0.001
 puck-0.001
 ship-0.001
 skate-0.001
 sailed-0.001
Token The
Token ID383
Feature activation+3.96e-04

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
 skate-0.002
wreck-0.002
 hockey-0.002
 his-0.002
Token cat
Token ID3797
Feature activation+4.77e-03

Pos logit contributions
ume+0.001
Girls+0.001
 blush+0.001
bs+0.001
aney+0.001
Neg logit contributions
 ship-0.001
 puck-0.001
 gear-0.001
 hockey-0.001
 skate-0.001
Token picked
Token ID6497
Feature activation+9.47e-04

Pos logit contributions
ume+0.013
Girls+0.013
 blush+0.013
 perfume+0.012
bs+0.011
Neg logit contributions
 ship-0.006
 his-0.005
 puck-0.005
 skate-0.005
 gear-0.005
Token up
Token ID510
Feature activation-2.56e-04

Pos logit contributions
Girls+0.002
 blush+0.002
ume+0.002
bs+0.002
 perfume+0.002
Neg logit contributions
 his-0.001
 puck-0.001
 hockey-0.001
wreck-0.001
 gear-0.001
Token the
Token ID262
Feature activation+3.53e-03

Pos logit contributions
 his+0.000
 puck+0.000
 hockey+0.000
 ship+0.000
 gear+0.000
Neg logit contributions
Girls-0.001
 blush-0.001
ume-0.001
bs-0.001
 perfume-0.001
Token folder
Token ID9483
Feature activation+2.45e-02

Pos logit contributions
Girls+0.005
Her+0.005
ume+0.005
 blush+0.005
aney+0.005
Neg logit contributions
 ship-0.007
 gear-0.007
 puck-0.007
 tank-0.007
 weapon-0.007
Token with
Token ID351
Feature activation-2.48e-03

Pos logit contributions
Girls+0.064
 blush+0.061
ume+0.060
 perfume+0.057
bs+0.057
Neg logit contributions
wreck-0.031
 puck-0.031
 ship-0.031
 his-0.030
 skate-0.030
Token its
Token ID663
Feature activation+1.70e-03

Pos logit contributions
 puck+0.004
 his+0.004
wreck+0.004
 ship+0.004
 skate+0.004
Neg logit contributions
Girls-0.006
 blush-0.005
ume-0.005
 perfume-0.005
bs-0.005
Token paw
Token ID41827
Feature activation+5.60e-04

Pos logit contributions
Girls+0.004
ume+0.004
 blush+0.004
bs+0.003
 mascara+0.003
Neg logit contributions
 his-0.003
 ship-0.003
 puck-0.003
 gear-0.002
 sail-0.002
Token.
Token ID13
Feature activation+2.42e-03

Pos logit contributions
Girls+0.002
 blush+0.001
ume+0.001
Faith+0.001
 perfume+0.001
Neg logit contributions
 puck-0.001
 ship-0.001
 his-0.001
 skate-0.001
 gear-0.001
Token Inside
Token ID14384
Feature activation+6.55e-03

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token<|endoftext|>
Token ID50256
Feature activation-8.47e-03

Pos logit contributions
 puck+0.016
wreck+0.016
 skate+0.015
 ship+0.015
 hockey+0.015
Neg logit contributions
 blush-0.016
Girls-0.016
ume-0.016
 perfume-0.015
bs-0.015
Token<|endoftext|>
Token ID50256
Feature activation-6.19e-03

Pos logit contributions
 puck+0.018
wreck+0.018
 ship+0.017
 skate+0.017
 motorcycle+0.017
Neg logit contributions
 blush-0.014
Girls-0.014
ume-0.014
 perfume-0.013
bs-0.013
Token<|endoftext|>
Token ID50256
Feature activation-3.93e-03

Pos logit contributions
 puck+0.013
wreck+0.013
 ship+0.013
 skate+0.013
 motorcycle+0.013
Neg logit contributions
 blush-0.010
Girls-0.010
ume-0.010
 perfume-0.010
bs-0.009
Token<|endoftext|>
Token ID50256
Feature activation-2.29e-03

Pos logit contributions
 puck+0.008
wreck+0.008
 ship+0.008
 skate+0.008
 motorcycle+0.008
Neg logit contributions
 blush-0.007
Girls-0.007
ume-0.006
 perfume-0.006
bs-0.006
TokenL
Token ID43
Feature activation+2.39e-02

Pos logit contributions
 puck+0.005
wreck+0.005
 ship+0.005
 skate+0.005
 motorcycle+0.004
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
 perfume-0.004
bs-0.003
Tokenila
Token ID10102
Feature activation+2.44e-02

Pos logit contributions
 blush+0.043
Girls+0.041
ume+0.040
 perfume+0.039
bs+0.037
Neg logit contributions
 his-0.047
 skate-0.046
 puck-0.045
 ship-0.045
 gear-0.044
Token and
Token ID290
Feature activation-2.82e-03

Pos logit contributions
 blush+0.059
Girls+0.057
ume+0.057
 perfume+0.055
bs+0.053
Neg logit contributions
 puck-0.035
 skate-0.034
 ship-0.034
wreck-0.034
 his-0.032
Token Ben
Token ID3932
Feature activation+7.12e-03

Pos logit contributions
 his+0.005
 sailing+0.005
 sailed+0.005
 skate+0.005
wreck+0.005
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
 mascara-0.005
Token are
Token ID389
Feature activation+7.15e-03

Pos logit contributions
 blush+0.015
Girls+0.014
ume+0.014
 perfume+0.014
bs+0.014
Neg logit contributions
 puck-0.013
wreck-0.013
 skate-0.012
 ship-0.012
 hockey-0.012
Token friends
Token ID2460
Feature activation+1.07e-03

Pos logit contributions
 blush+0.015
Girls+0.015
ume+0.014
 perfume+0.014
bs+0.013
Neg logit contributions
 puck-0.012
 sailing-0.012
 skate-0.012
 hockey-0.012
 ship-0.012
Token.
Token ID13
Feature activation-1.40e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 hockey-0.002
Token inside
Token ID2641
Feature activation+4.18e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Token!
Token ID0
Feature activation+1.94e-03

Pos logit contributions
 blush+0.009
Girls+0.009
ume+0.008
 perfume+0.008
bs+0.008
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.007
 ship-0.007
 hockey-0.007
Token
Token ID198
Feature activation+3.63e-03

Pos logit contributions
 blush+0.004
Girls+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Token
Token ID198
Feature activation+5.81e-03

Pos logit contributions
 blush+0.008
Girls+0.008
ume+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.006
wreck-0.006
 skate-0.006
 ship-0.006
 hockey-0.006
TokenScar
Token ID44433
Feature activation+1.03e-02

Pos logit contributions
 blush+0.011
Girls+0.011
ume+0.011
 perfume+0.010
bs+0.010
Neg logit contributions
wreck-0.011
 puck-0.011
 skate-0.011
 ship-0.010
 hockey-0.010
Tokenlett
Token ID15503
Feature activation+2.42e-02

Pos logit contributions
 blush+0.016
Girls+0.015
ume+0.015
 perfume+0.014
bs+0.014
Neg logit contributions
 puck-0.024
wreck-0.023
 skate-0.023
 ship-0.023
 hockey-0.022
Token and
Token ID290
Feature activation+2.33e-03

Pos logit contributions
 blush+0.055
Girls+0.055
ume+0.055
 perfume+0.053
bs+0.052
Neg logit contributions
wreck-0.034
 ship-0.034
 puck-0.033
 sailed-0.033
 skate-0.032
Token Jason
Token ID8982
Feature activation+1.35e-03

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.004
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token were
Token ID547
Feature activation+5.66e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.002
wreck-0.002
 ship-0.002
 skate-0.002
 gear-0.002
Token so
Token ID523
Feature activation+7.55e-03

Pos logit contributions
 blush+0.013
Girls+0.012
ume+0.012
 perfume+0.012
bs+0.012
Neg logit contributions
 puck-0.009
wreck-0.009
 ship-0.009
 skate-0.009
 sailing-0.009
Token proud
Token ID6613
Feature activation-8.05e-03

Pos logit contributions
 blush+0.016
Girls+0.015
ume+0.015
 perfume+0.014
bs+0.014
Neg logit contributions
 puck-0.013
wreck-0.013
 skate-0.013
 sailing-0.013
 ship-0.013
Token.
Token ID13
Feature activation+3.45e-03

Pos logit contributions
 blush+0.014
ume+0.014
 perfume+0.013
Girls+0.013
bs+0.013
Neg logit contributions
 puck-0.013
wreck-0.013
 skate-0.013
 ship-0.012
 motorcycle-0.012
Token He
Token ID679
Feature activation-2.78e-03

Pos logit contributions
 blush+0.007
Girls+0.007
ume+0.006
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.006
wreck-0.006
 skate-0.006
 ship-0.006
 wre-0.006
Token walked
Token ID6807
Feature activation+1.80e-03

Pos logit contributions
 puck+0.006
wreck+0.006
 skate+0.006
 ship+0.005
 hockey+0.005
Neg logit contributions
 blush-0.005
Girls-0.005
bs-0.004
ume-0.004
 perfume-0.004
Token along
Token ID1863
Feature activation+8.86e-03

Pos logit contributions
 blush+0.003
Girls+0.003
bs+0.003
 perfume+0.003
Her+0.003
Neg logit contributions
 puck-0.004
wreck-0.004
 wre-0.004
 motorcycle-0.004
 skate-0.004
Token the
Token ID262
Feature activation+3.28e-03

Pos logit contributions
 blush+0.013
 perfume+0.012
Girls+0.011
bs+0.011
Her+0.011
Neg logit contributions
 puck-0.020
wreck-0.019
 motorcycle-0.019
 skate-0.019
 camps-0.019
Token web
Token ID3992
Feature activation+2.42e-02

Pos logit contributions
ume+0.006
 blush+0.006
bs+0.006
Girls+0.006
 perfume+0.005
Neg logit contributions
 skate-0.006
 puck-0.006
 gear-0.006
 ship-0.006
wreck-0.006
Token and
Token ID290
Feature activation+2.74e-03

Pos logit contributions
 blush+0.053
Girls+0.052
ume+0.051
 perfume+0.050
bs+0.049
Neg logit contributions
 puck-0.040
wreck-0.039
 skate-0.038
 ship-0.037
 hockey-0.036
Token made
Token ID925
Feature activation-7.46e-03

Pos logit contributions
 blush+0.005
Girls+0.005
bs+0.005
ume+0.005
 perfume+0.005
Neg logit contributions
 puck-0.006
wreck-0.005
 skate-0.005
 ship-0.005
 motorcycle-0.005
Token tiny
Token ID7009
Feature activation-2.48e-03

Pos logit contributions
wreck+0.016
 puck+0.015
 skate+0.015
 ship+0.015
 motorcycle+0.015
Neg logit contributions
 blush-0.013
 perfume-0.012
bs-0.012
Girls-0.012
ume-0.011
Token footprints
Token ID48012
Feature activation-4.13e-03

Pos logit contributions
 puck+0.005
 ship+0.005
 wre+0.005
 gear+0.005
 camps+0.005
Neg logit contributions
Girls-0.005
ume-0.004
 blush-0.004
bs-0.004
Her-0.004
Token on
Token ID319
Feature activation-4.34e-03

Pos logit contributions
 puck+0.008
wreck+0.008
 skate+0.008
 motorcycle+0.007
 camps+0.007
Neg logit contributions
 blush-0.008
 perfume-0.007
ume-0.007
bs-0.007
Girls-0.007
Token,
Token ID11
Feature activation-4.14e-03

Pos logit contributions
wreck+0.007
 puck+0.007
Ar+0.006
 skate+0.006
 camps+0.006
Neg logit contributions
 blush-0.005
bs-0.005
ume-0.004
 perfume-0.004
 makeup-0.004
Token Tim
Token ID5045
Feature activation-9.58e-03

Pos logit contributions
 puck+0.006
wreck+0.006
Ar+0.006
 camps+0.006
 skate+0.006
Neg logit contributions
 blush-0.010
 perfume-0.009
 makeup-0.009
 she-0.009
Her-0.009
Tokenmy
Token ID1820
Feature activation-6.88e-03

Pos logit contributions
 puck+0.021
wreck+0.020
 skate+0.020
 ship+0.020
 hockey+0.019
Neg logit contributions
 blush-0.016
Girls-0.016
ume-0.015
 perfume-0.015
bs-0.014
Token lost
Token ID2626
Feature activation-3.55e-03

Pos logit contributions
 puck+0.014
wreck+0.014
 skate+0.013
 hockey+0.013
 ship+0.013
Neg logit contributions
 blush-0.013
Girls-0.012
ume-0.012
 perfume-0.011
bs-0.011
Token the
Token ID262
Feature activation+5.13e-03

Pos logit contributions
wreck+0.004
 puck+0.003
 skate+0.003
Ar+0.003
 sailed+0.003
Neg logit contributions
 perfume-0.010
 blush-0.010
 makeup-0.009
ume-0.009
 purse-0.009
Token diary
Token ID26339
Feature activation+2.42e-02

Pos logit contributions
Girls+0.010
ume+0.009
 blush+0.009
bs+0.009
Her+0.008
Neg logit contributions
 ship-0.010
 gear-0.010
wreck-0.010
 puck-0.010
 motorcycle-0.010
Token while
Token ID981
Feature activation-2.30e-03

Pos logit contributions
 blush+0.043
ume+0.040
 perfume+0.039
bs+0.039
Girls+0.037
Neg logit contributions
 puck-0.048
 skate-0.046
 wre-0.046
wreck-0.045
Ar-0.045
Token playing
Token ID2712
Feature activation-5.82e-03

Pos logit contributions
 puck+0.003
wreck+0.003
Ar+0.003
 wre+0.003
 skate+0.003
Neg logit contributions
 blush-0.005
 perfume-0.005
 makeup-0.005
bs-0.005
ume-0.005
Token outside
Token ID2354
Feature activation-1.41e-03

Pos logit contributions
 puck+0.011
wreck+0.011
 skate+0.011
 camps+0.011
 wre+0.010
Neg logit contributions
 blush-0.011
 perfume-0.010
 makeup-0.010
bs-0.009
ume-0.009
Token.
Token ID13
Feature activation+2.10e-03

Pos logit contributions
 puck+0.003
wreck+0.003
Ar+0.003
 skate+0.003
 rev+0.003
Neg logit contributions
 blush-0.002
 perfume-0.002
ume-0.002
bs-0.002
Girls-0.002
Token He
Token ID679
Feature activation-6.48e-03

Pos logit contributions
 blush+0.005
Girls+0.005
 perfume+0.005
ume+0.005
 makeup+0.005
Neg logit contributions
wreck-0.003
 puck-0.002
 ship-0.002
 skate-0.002
 sailing-0.002
Token "
Token ID366
Feature activation+4.62e-03

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 ship+0.000
 hockey+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
 perfume-0.000
bs-0.000
TokenLet
Token ID5756
Feature activation+4.84e-03

Pos logit contributions
ume+0.009
 blush+0.009
 perfume+0.009
bs+0.008
ilies+0.008
Neg logit contributions
wreck-0.008
Ar-0.008
 puck-0.008
 skate-0.008
 his-0.008
Token's
Token ID338
Feature activation-3.65e-03

Pos logit contributions
 blush+0.012
ume+0.012
Girls+0.011
 perfume+0.011
bs+0.011
Neg logit contributions
 his-0.006
 ship-0.006
 skate-0.006
 gear-0.006
wreck-0.006
Token sing
Token ID1702
Feature activation+1.08e-02

Pos logit contributions
 skate+0.005
 ship+0.005
 puck+0.005
wreck+0.005
 sailing+0.005
Neg logit contributions
Girls-0.009
 blush-0.008
ume-0.008
bs-0.008
 perfume-0.008
Token the
Token ID262
Feature activation+4.83e-03

Pos logit contributions
 blush+0.025
Girls+0.025
ume+0.024
 perfume+0.023
bs+0.023
Neg logit contributions
 puck-0.015
wreck-0.015
 hockey-0.015
 ship-0.015
 his-0.015
Token song
Token ID3496
Feature activation+2.41e-02

Pos logit contributions
 blush+0.011
Girls+0.010
bs+0.010
ume+0.010
Her+0.009
Neg logit contributions
 ship-0.007
 sailing-0.007
wreck-0.007
 motorcycle-0.007
 skate-0.007
Token together
Token ID1978
Feature activation+8.21e-03

Pos logit contributions
Girls+0.057
 blush+0.056
ume+0.054
 perfume+0.052
bs+0.051
Neg logit contributions
 ship-0.034
wreck-0.034
 puck-0.033
 skate-0.033
 hockey-0.032
Token."
Token ID526
Feature activation+3.14e-03

Pos logit contributions
 blush+0.019
Girls+0.018
ume+0.017
 perfume+0.017
bs+0.017
Neg logit contributions
 puck-0.013
wreck-0.013
 skate-0.012
 ship-0.012
 hockey-0.012
Token
Token ID198
Feature activation-1.65e-04

Pos logit contributions
ume+0.006
Girls+0.006
 blush+0.006
 perfume+0.006
bs+0.005
Neg logit contributions
 his-0.006
 puck-0.006
 skate-0.006
 ship-0.006
 gear-0.006
TokenKate
Token ID45087
Feature activation+3.88e-03

Pos logit contributions
 puck+0.000
 skate+0.000
wreck+0.000
 his+0.000
 ship+0.000
Neg logit contributions
 blush-0.000
ume-0.000
 perfume-0.000
Girls-0.000
bs-0.000
Token smiled
Token ID13541
Feature activation-8.26e-04

Pos logit contributions
Girls+0.009
 blush+0.008
ume+0.008
 perfume+0.008
 mascara+0.008
Neg logit contributions
 sailed-0.006
 ship-0.006
 padd-0.005
 hon-0.005
 rev-0.005
Token play
Token ID711
Feature activation-5.83e-03

Pos logit contributions
 blush+0.007
Girls+0.006
 perfume+0.006
ume+0.006
bs+0.006
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.004
 ship-0.004
 gear-0.004
Token.
Token ID13
Feature activation-8.36e-04

Pos logit contributions
 puck+0.010
wreck+0.010
 skate+0.010
 ship+0.010
 camps+0.010
Neg logit contributions
 blush-0.012
Girls-0.012
 perfume-0.012
ume-0.011
bs-0.011
Token Tommy
Token ID19919
Feature activation+2.90e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token saw
Token ID2497
Feature activation+4.71e-03

Pos logit contributions
 blush+0.006
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.006
wreck-0.005
 skate-0.005
 ship-0.005
 hockey-0.005
Token the
Token ID262
Feature activation+4.89e-03

Pos logit contributions
ume+0.010
 blush+0.010
Girls+0.009
bs+0.009
 perfume+0.008
Neg logit contributions
 his-0.009
 puck-0.009
 hockey-0.008
 skate-0.008
 gear-0.008
Token diary
Token ID26339
Feature activation+2.40e-02

Pos logit contributions
Girls+0.008
ume+0.008
 blush+0.007
bs+0.007
aney+0.007
Neg logit contributions
 motorcycle-0.011
 ship-0.011
 gear-0.011
wreck-0.010
 his-0.010
Token and
Token ID290
Feature activation+4.06e-03

Pos logit contributions
 blush+0.050
ume+0.046
Girls+0.046
 perfume+0.046
bs+0.044
Neg logit contributions
 puck-0.043
wreck-0.041
 skate-0.041
 ship-0.040
 wre-0.039
Token wanted
Token ID2227
Feature activation-4.46e-03

Pos logit contributions
ume+0.008
 blush+0.008
Girls+0.008
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.008
 his-0.008
 ship-0.007
 skate-0.007
wreck-0.007
Token to
Token ID284
Feature activation+1.89e-03

Pos logit contributions
 his+0.007
 puck+0.007
 skate+0.007
 hockey+0.006
 gear+0.006
Neg logit contributions
ume-0.011
 blush-0.010
Girls-0.010
bs-0.010
 perfume-0.009
Token read
Token ID1100
Feature activation+2.05e-03

Pos logit contributions
Girls+0.005
ume+0.004
 blush+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.003
 skate-0.003
 ship-0.003
wreck-0.003
 his-0.003
Token it
Token ID340
Feature activation+3.12e-03

Pos logit contributions
 blush+0.004
Girls+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token dream
Token ID4320
Feature activation+6.93e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
 skate-0.002
wreck-0.002
 ship-0.002
 hockey-0.002
Token called
Token ID1444
Feature activation-8.10e-04

Pos logit contributions
 blush+0.015
Girls+0.014
ume+0.014
 perfume+0.014
bs+0.013
Neg logit contributions
 puck-0.012
wreck-0.012
 skate-0.011
 ship-0.011
 hockey-0.011
Token a
Token ID257
Feature activation-5.17e-03

Pos logit contributions
 skate+0.001
 his+0.001
 puck+0.001
 hockey+0.001
wreck+0.001
Neg logit contributions
Girls-0.002
 blush-0.002
bs-0.001
ume-0.001
 perfume-0.001
Token "
Token ID366
Feature activation+8.17e-03

Pos logit contributions
 puck+0.010
wreck+0.010
 skate+0.010
 wre+0.009
 sailed+0.009
Neg logit contributions
 blush-0.010
 perfume-0.009
Girls-0.009
ume-0.009
bs-0.008
Tokennight
Token ID3847
Feature activation+3.23e-03

Pos logit contributions
 blush+0.015
Girls+0.015
ume+0.015
 perfume+0.014
bs+0.014
Neg logit contributions
wreck-0.016
 puck-0.016
 skate-0.015
 hockey-0.015
 ship-0.014
Tokenmare
Token ID11449
Feature activation+2.39e-02

Pos logit contributions
 blush+0.006
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.007
 ship-0.007
 hockey-0.007
Token".
Token ID1911
Feature activation+1.83e-03

Pos logit contributions
 blush+0.057
Girls+0.057
 mascara+0.052
 perfume+0.052
bs+0.051
Neg logit contributions
wreck-0.034
 ship-0.034
 sailing-0.031
 skate-0.031
 his-0.031
Token She
Token ID1375
Feature activation+3.27e-03

Pos logit contributions
Girls+0.003
ume+0.003
 wil+0.003
bs+0.003
 roses+0.003
Neg logit contributions
 his-0.004
 He-0.004
 His-0.004
 hockey-0.004
 skate-0.004
Token woke
Token ID19092
Feature activation-2.41e-03

Pos logit contributions
 blush+0.006
Girls+0.006
ume+0.006
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.006
wreck-0.006
 skate-0.006
 ship-0.006
 hockey-0.006
Token up
Token ID510
Feature activation+2.92e-04

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 hockey+0.004
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
bs-0.005
Token crying
Token ID13774
Feature activation+4.98e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.000
 ship-0.000
 gear-0.000
Token"
Token ID1
Feature activation+1.08e-02

Pos logit contributions
 puck+0.012
wreck+0.012
 skate+0.012
 ship+0.011
 motorcycle+0.011
Neg logit contributions
 blush-0.007
Girls-0.006
ume-0.006
 perfume-0.006
bs-0.006
TokenWhat
Token ID2061
Feature activation+4.85e-03

Pos logit contributions
ume+0.022
bs+0.022
 blush+0.022
 perfume+0.021
Girls+0.020
Neg logit contributions
 puck-0.019
wreck-0.019
Ar-0.018
 skate-0.018
 hockey-0.017
Token is
Token ID318
Feature activation-1.74e-04

Pos logit contributions
 blush+0.010
Girls+0.009
ume+0.009
 perfume+0.009
bs+0.009
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.009
 ship-0.009
 hockey-0.008
Token this
Token ID428
Feature activation-3.00e-03

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 ship+0.000
 hockey+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
bs-0.000
 perfume-0.000
Token?"
Token ID1701
Feature activation+5.67e-03

Pos logit contributions
 ship+0.005
 puck+0.005
 skate+0.005
 his+0.005
wreck+0.005
Neg logit contributions
Girls-0.007
 blush-0.007
ume-0.006
bs-0.006
Her-0.006
Token Sara
Token ID24799
Feature activation+2.39e-02

Pos logit contributions
 blush+0.009
Girls+0.009
ume+0.009
 perfume+0.008
bs+0.008
Neg logit contributions
 puck-0.013
 his-0.012
 skate-0.012
 hockey-0.012
wreck-0.012
Token asks
Token ID7893
Feature activation+4.03e-03

Pos logit contributions
 blush+0.040
Girls+0.040
ume+0.039
 perfume+0.038
bs+0.036
Neg logit contributions
 puck-0.051
 skate-0.050
wreck-0.050
 ship-0.049
 hockey-0.048
Token.
Token ID13
Feature activation+1.28e-03

Pos logit contributions
 blush+0.008
ume+0.007
 perfume+0.007
Girls+0.007
bs+0.007
Neg logit contributions
 puck-0.008
wreck-0.008
 ship-0.007
 skate-0.007
 camps-0.007
Token
Token ID198
Feature activation-8.19e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
 skate-0.002
 hockey-0.002
wreck-0.002
 his-0.002
Token
Token ID198
Feature activation-6.37e-03

Pos logit contributions
 puck+0.015
wreck+0.015
 skate+0.014
 ship+0.014
 motorcycle+0.014
Neg logit contributions
 blush-0.017
Girls-0.016
ume-0.016
bs-0.015
 perfume-0.015
Token"
Token ID1
Feature activation+7.38e-03

Pos logit contributions
 puck+0.014
wreck+0.014
 skate+0.014
 ship+0.014
 hockey+0.013
Neg logit contributions
 blush-0.010
Girls-0.010
ume-0.010
 perfume-0.009
bs-0.009
Token<|endoftext|>
Token ID50256
Feature activation-8.46e-03

Pos logit contributions
 puck+0.012
wreck+0.011
 skate+0.011
 ship+0.011
 hockey+0.011
Neg logit contributions
 blush-0.016
Girls-0.016
ume-0.016
 perfume-0.015
bs-0.015
Token<|endoftext|>
Token ID50256
Feature activation-8.47e-03

Pos logit contributions
 puck+0.016
wreck+0.016
 skate+0.015
 ship+0.015
 hockey+0.015
Neg logit contributions
 blush-0.016
Girls-0.016
ume-0.016
 perfume-0.015
bs-0.015
Token<|endoftext|>
Token ID50256
Feature activation-6.19e-03

Pos logit contributions
 puck+0.018
wreck+0.018
 ship+0.017
 skate+0.017
 motorcycle+0.017
Neg logit contributions
 blush-0.014
Girls-0.014
ume-0.014
 perfume-0.013
bs-0.013
Token<|endoftext|>
Token ID50256
Feature activation-3.93e-03

Pos logit contributions
 puck+0.013
wreck+0.013
 ship+0.013
 skate+0.013
 motorcycle+0.013
Neg logit contributions
 blush-0.010
Girls-0.010
ume-0.010
 perfume-0.010
bs-0.009
Token<|endoftext|>
Token ID50256
Feature activation-2.29e-03

Pos logit contributions
 puck+0.008
wreck+0.008
 ship+0.008
 skate+0.008
 motorcycle+0.008
Neg logit contributions
 blush-0.007
Girls-0.007
ume-0.006
 perfume-0.006
bs-0.006
TokenL
Token ID43
Feature activation+2.39e-02

Pos logit contributions
 puck+0.005
wreck+0.005
 ship+0.005
 skate+0.005
 motorcycle+0.004
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
 perfume-0.004
bs-0.003
Tokenila
Token ID10102
Feature activation+2.44e-02

Pos logit contributions
 blush+0.043
Girls+0.041
ume+0.040
 perfume+0.039
bs+0.037
Neg logit contributions
 his-0.047
 skate-0.046
 puck-0.045
 ship-0.045
 gear-0.044
Token and
Token ID290
Feature activation-2.82e-03

Pos logit contributions
 blush+0.059
Girls+0.057
ume+0.057
 perfume+0.055
bs+0.053
Neg logit contributions
 puck-0.035
 skate-0.034
 ship-0.034
wreck-0.034
 his-0.032
Token Ben
Token ID3932
Feature activation+7.12e-03

Pos logit contributions
 his+0.005
 sailing+0.005
 sailed+0.005
 skate+0.005
wreck+0.005
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
 mascara-0.005
Token are
Token ID389
Feature activation+7.15e-03

Pos logit contributions
 blush+0.015
Girls+0.014
ume+0.014
 perfume+0.014
bs+0.014
Neg logit contributions
 puck-0.013
wreck-0.013
 skate-0.012
 ship-0.012
 hockey-0.012
Token friends
Token ID2460
Feature activation+1.07e-03

Pos logit contributions
 blush+0.015
Girls+0.015
ume+0.014
 perfume+0.014
bs+0.013
Neg logit contributions
 puck-0.012
 sailing-0.012
 skate-0.012
 hockey-0.012
 ship-0.012
Token you
Token ID345
Feature activation-1.34e-03

Pos logit contributions
 puck+0.014
wreck+0.014
 skate+0.013
 ship+0.013
 camps+0.013
Neg logit contributions
 blush-0.012
Girls-0.011
ume-0.011
 perfume-0.011
bs-0.011
Token break
Token ID2270
Feature activation+6.80e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 camps+0.002
 skate+0.002
 ship+0.002
Neg logit contributions
 blush-0.003
ume-0.003
Girls-0.003
 perfume-0.002
bs-0.002
Token my
Token ID616
Feature activation-1.99e-03

Pos logit contributions
 blush+0.015
ume+0.015
Girls+0.015
bs+0.014
 perfume+0.014
Neg logit contributions
 his-0.011
 puck-0.011
 hockey-0.010
 skate-0.010
 gear-0.010
Token egg
Token ID5935
Feature activation+3.62e-03

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 hockey+0.004
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.003
 perfume-0.003
bs-0.003
Token?"
Token ID1701
Feature activation+4.70e-03

Pos logit contributions
Girls+0.008
 blush+0.008
ume+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.006
wreck-0.006
 ship-0.006
 skate-0.006
 motorcycle-0.006
Token Wendy
Token ID28314
Feature activation+2.38e-02

Pos logit contributions
 blush+0.009
Girls+0.009
ume+0.009
 perfume+0.008
bs+0.008
Neg logit contributions
 his-0.009
 puck-0.009
 skate-0.009
 hockey-0.009
wreck-0.009
Token shouted
Token ID17293
Feature activation+7.26e-03

Pos logit contributions
Girls+0.044
 blush+0.044
ume+0.044
 perfume+0.042
bs+0.041
Neg logit contributions
 puck-0.045
 skate-0.044
wreck-0.044
 ship-0.043
 his-0.043
Token.
Token ID13
Feature activation-2.95e-03

Pos logit contributions
 blush+0.016
Girls+0.016
ume+0.015
 perfume+0.015
bs+0.015
Neg logit contributions
 puck-0.012
wreck-0.012
 skate-0.011
 ship-0.011
 hockey-0.011
Token
Token ID198
Feature activation-4.54e-03

Pos logit contributions
 puck+0.005
 skate+0.004
 hockey+0.004
 his+0.004
wreck+0.004
Neg logit contributions
 blush-0.007
Girls-0.007
ume-0.006
 perfume-0.006
bs-0.006
Token
Token ID198
Feature activation-2.58e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 skate+0.007
 ship+0.007
 hockey+0.007
Neg logit contributions
 blush-0.010
Girls-0.010
ume-0.010
 perfume-0.009
bs-0.009
TokenHer
Token ID9360
Feature activation+1.77e-03

Pos logit contributions
 puck+0.005
 skate+0.005
 hockey+0.005
wreck+0.005
 gear+0.005
Neg logit contributions
 blush-0.005
ume-0.004
 perfume-0.004
Girls-0.004
bs-0.004
Token came
Token ID1625
Feature activation-5.14e-03

Pos logit contributions
Girls+0.021
ume+0.021
 blush+0.020
bs+0.019
Her+0.019
Neg logit contributions
 ship-0.008
 sailed-0.008
 gear-0.007
 his-0.007
wreck-0.007
Token because
Token ID780
Feature activation-2.10e-03

Pos logit contributions
 puck+0.009
wreck+0.008
 skate+0.008
 ship+0.008
 hockey+0.008
Neg logit contributions
 blush-0.011
Girls-0.011
ume-0.011
 perfume-0.010
bs-0.010
Token they
Token ID484
Feature activation-3.29e-03

Pos logit contributions
 his+0.004
 he+0.003
 sailing+0.003
 ship+0.003
 hockey+0.003
Neg logit contributions
 blush-0.005
ume-0.005
Girls-0.005
bs-0.004
 perfume-0.004
Token sang
Token ID25889
Feature activation+8.29e-03

Pos logit contributions
 ship+0.005
 sailed+0.005
wreck+0.005
 skate+0.005
 puck+0.005
Neg logit contributions
Girls-0.008
ume-0.008
 blush-0.007
 perfume-0.007
 mascara-0.007
Token the
Token ID262
Feature activation+8.00e-03

Pos logit contributions
 blush+0.019
Girls+0.019
ume+0.018
 perfume+0.017
bs+0.017
Neg logit contributions
 puck-0.013
wreck-0.013
 ship-0.012
 hockey-0.012
 his-0.012
Token song
Token ID3496
Feature activation+2.38e-02

Pos logit contributions
 blush+0.016
Girls+0.016
ume+0.016
bs+0.015
 perfume+0.014
Neg logit contributions
 ship-0.014
wreck-0.014
 puck-0.014
 sailing-0.013
 skate-0.013
Token.
Token ID13
Feature activation-1.48e-03

Pos logit contributions
Girls+0.061
 blush+0.058
ume+0.057
 perfume+0.055
 mascara+0.053
Neg logit contributions
wreck-0.030
 ship-0.029
 his-0.028
 puck-0.028
 sailing-0.028
Token From
Token ID3574
Feature activation+3.45e-03

Pos logit contributions
 He+0.002
 his+0.002
 hockey+0.002
 puck+0.002
 His+0.002
Neg logit contributions
ume-0.004
 blush-0.004
Girls-0.004
 perfume-0.004
 veil-0.003
Token that
Token ID326
Feature activation-5.09e-03

Pos logit contributions
 blush+0.008
ume+0.008
Girls+0.008
bs+0.007
 mascara+0.007
Neg logit contributions
 ship-0.005
 sailing-0.005
 his-0.005
 gear-0.005
 skate-0.005
Token day
Token ID1110
Feature activation-3.37e-03

Pos logit contributions
 puck+0.008
wreck+0.008
 skate+0.008
 ship+0.008
 hockey+0.007
Neg logit contributions
 blush-0.012
Girls-0.011
ume-0.011
 perfume-0.011
bs-0.011
Token on
Token ID319
Feature activation-4.25e-04

Pos logit contributions
 puck+0.006
 skate+0.006
wreck+0.006
 ship+0.005
 his+0.005
Neg logit contributions
 blush-0.007
Girls-0.007
 perfume-0.007
ume-0.007
bs-0.006
Token world
Token ID995
Feature activation+1.17e-02

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
bs+0.001
 perfume+0.001
Neg logit contributions
 puck-0.001
 ship-0.001
wreck-0.001
 skate-0.001
 gear-0.001
Token and
Token ID290
Feature activation+1.81e-04

Pos logit contributions
 blush+0.026
Girls+0.026
ume+0.025
 perfume+0.025
bs+0.024
Neg logit contributions
 puck-0.018
wreck-0.018
 skate-0.018
 ship-0.018
 hockey-0.017
Token they
Token ID484
Feature activation-6.24e-04

Pos logit contributions
 blush+0.000
Girls+0.000
ume+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 ship-0.000
 hockey-0.000
Token loved
Token ID6151
Feature activation-9.75e-04

Pos logit contributions
wreck+0.001
 ship+0.001
 puck+0.001
 skate+0.001
 sailed+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
 mascara-0.001
Token their
Token ID511
Feature activation+2.48e-04

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 camps+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
 perfume-0.002
ume-0.002
bs-0.002
Token song
Token ID3496
Feature activation+2.37e-02

Pos logit contributions
 blush+0.001
Girls+0.000
ume+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 ship-0.000
 hockey-0.000
Token.
Token ID13
Feature activation-4.81e-03

Pos logit contributions
 blush+0.055
Girls+0.054
ume+0.053
 perfume+0.051
bs+0.050
Neg logit contributions
 puck-0.036
wreck-0.035
 ship-0.034
 skate-0.034
 hockey-0.033
Token They
Token ID1119
Feature activation+1.88e-03

Pos logit contributions
 puck+0.009
wreck+0.009
 skate+0.008
 ship+0.008
 gear+0.008
Neg logit contributions
 blush-0.010
Girls-0.010
ume-0.009
 perfume-0.009
bs-0.009
Token cut
Token ID2005
Feature activation-2.22e-03

Pos logit contributions
Girls+0.004
ume+0.004
 blush+0.004
 perfume+0.004
 mascara+0.004
Neg logit contributions
 ship-0.003
 sailed-0.003
 puck-0.003
wreck-0.003
 skate-0.003
Token the
Token ID262
Feature activation-1.73e-03

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 hockey+0.003
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.004
bs-0.004
Token cake
Token ID12187
Feature activation+8.31e-03

Pos logit contributions
 ship+0.003
 puck+0.003
 motorcycle+0.003
 gear+0.003
 hockey+0.003
Neg logit contributions
Girls-0.003
 blush-0.003
ume-0.003
bs-0.003
Her-0.003
Token out
Token ID503
Feature activation+3.59e-03

Pos logit contributions
wreck+0.010
 puck+0.010
 ship+0.010
 skate+0.010
 motorcycle+0.010
Neg logit contributions
 blush-0.009
Girls-0.008
 perfume-0.008
ume-0.008
bs-0.008
Token of
Token ID286
Feature activation+3.00e-03

Pos logit contributions
 blush+0.006
Girls+0.005
bs+0.005
ume+0.005
 perfume+0.005
Neg logit contributions
wreck-0.008
 puck-0.008
 ship-0.008
 skate-0.008
 motorcycle-0.008
Token the
Token ID262
Feature activation+1.07e-03

Pos logit contributions
 blush+0.007
Girls+0.007
 perfume+0.007
ume+0.007
bs+0.007
Neg logit contributions
wreck-0.004
 puck-0.004
 skate-0.004
 ship-0.004
 motorcycle-0.004
Token massage
Token ID26900
Feature activation+5.70e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
bs+0.002
 perfume+0.002
Neg logit contributions
 puck-0.002
 skate-0.002
 hockey-0.002
 gear-0.002
wreck-0.002
Token par
Token ID1582
Feature activation-1.43e-03

Pos logit contributions
 blush+0.011
Girls+0.011
ume+0.011
 perfume+0.011
bs+0.010
Neg logit contributions
 puck-0.010
wreck-0.010
 skate-0.010
 ship-0.010
 wre-0.010
Tokenlor
Token ID4685
Feature activation+2.36e-02

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 hockey+0.003
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token as
Token ID355
Feature activation-2.71e-03

Pos logit contributions
 blush+0.054
Girls+0.052
ume+0.051
 perfume+0.050
bs+0.049
Neg logit contributions
 puck-0.038
wreck-0.037
 ship-0.036
 skate-0.036
 hockey-0.034
Token fast
Token ID3049
Feature activation-9.72e-03

Pos logit contributions
wreck+0.004
 ship+0.004
 puck+0.004
 camps+0.004
 motorcycle+0.004
Neg logit contributions
bs-0.006
 she-0.006
 blush-0.006
 perfume-0.005
 herself-0.005
Token as
Token ID355
Feature activation-2.58e-03

Pos logit contributions
wreck+0.020
 ship+0.020
 skate+0.019
 puck+0.019
 motorcycle+0.019
Neg logit contributions
 blush-0.017
bs-0.016
 perfume-0.016
ume-0.015
Girls-0.015
Token he
Token ID339
Feature activation-9.25e-03

Pos logit contributions
wreck+0.003
oc+0.003
 motorcycle+0.003
 wre+0.003
 puck+0.003
Neg logit contributions
 she-0.006
bs-0.006
 blush-0.006
 perfume-0.005
 herself-0.005
Token could
Token ID714
Feature activation+1.44e-03

Pos logit contributions
 puck+0.019
wreck+0.018
 motorcycle+0.018
 skate+0.018
 wre+0.018
Neg logit contributions
 blush-0.017
bs-0.016
ume-0.015
Girls-0.015
 perfume-0.015
Token also
Token ID635
Feature activation+8.78e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
bs+0.002
 perfume+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 hockey-0.002
 ship-0.002
Token find
Token ID1064
Feature activation+5.01e-03

Pos logit contributions
 blush+0.018
Girls+0.017
ume+0.016
 perfume+0.016
bs+0.016
Neg logit contributions
 puck-0.016
wreck-0.016
 skate-0.016
 ship-0.015
 hockey-0.015
Token some
Token ID617
Feature activation+8.68e-04

Pos logit contributions
 blush+0.011
Girls+0.011
ume+0.011
 perfume+0.010
bs+0.010
Neg logit contributions
 puck-0.008
 gear-0.007
 his-0.007
 ship-0.007
wreck-0.007
Token clothes
Token ID8242
Feature activation+3.90e-03

Pos logit contributions
 blush+0.002
 perfume+0.002
Girls+0.002
ume+0.002
bs+0.001
Neg logit contributions
wreck-0.002
 puck-0.002
 skate-0.002
 ship-0.002
 motorcycle-0.002
Token in
Token ID287
Feature activation-1.65e-03

Pos logit contributions
Girls+0.009
 blush+0.009
ume+0.009
 perfume+0.008
bs+0.008
Neg logit contributions
wreck-0.006
 puck-0.006
 ship-0.006
 skate-0.006
 sailing-0.006
Token Anna
Token ID11735
Feature activation+2.36e-02

Pos logit contributions
 puck+0.003
 skate+0.002
wreck+0.002
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
bs-0.004
 perfume-0.003
Token's
Token ID338
Feature activation-1.17e-03

Pos logit contributions
Girls+0.058
 blush+0.056
ume+0.054
 perfume+0.052
 mascara+0.051
Neg logit contributions
 ship-0.032
 puck-0.031
 skate-0.031
 hockey-0.030
wreck-0.030
Token closet
Token ID21615
Feature activation+1.43e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token.
Token ID13
Feature activation-3.17e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 hockey-0.002
Token They
Token ID1119
Feature activation+9.09e-05

Pos logit contributions
 puck+0.006
 hockey+0.005
 his+0.005
 He+0.005
 skate+0.005
Neg logit contributions
 blush-0.007
ume-0.006
 perfume-0.006
Girls-0.006
bs-0.006
Token are
Token ID389
Feature activation+2.14e-03

Pos logit contributions
 blush+0.000
Girls+0.000
ume+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 ship-0.000
 hockey-0.000
Token harder
Token ID7069
Feature activation-8.63e-03

Pos logit contributions
 puck+0.004
 skate+0.004
wreck+0.004
 ship+0.004
 hockey+0.004
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.004
bs-0.004
Token to
Token ID284
Feature activation-1.30e-03

Pos logit contributions
 puck+0.015
wreck+0.015
 skate+0.014
 ship+0.014
 motorcycle+0.014
Neg logit contributions
 blush-0.018
Girls-0.017
ume-0.017
 perfume-0.017
bs-0.017
Token push
Token ID4574
Feature activation+8.13e-05

Pos logit contributions
 puck+0.002
wreck+0.002
 camps+0.002
 ship+0.002
 skate+0.002
Neg logit contributions
 blush-0.003
ume-0.002
 perfume-0.002
Girls-0.002
bs-0.002
Token the
Token ID262
Feature activation-2.51e-03

Pos logit contributions
 blush+0.000
Girls+0.000
ume+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 ship-0.000
 hockey-0.000
Token wheel
Token ID7825
Feature activation-9.29e-03

Pos logit contributions
wreck+0.005
 puck+0.004
 skate+0.004
 ship+0.004
 sailing+0.004
Neg logit contributions
 blush-0.005
ume-0.005
 perfume-0.005
Girls-0.005
bs-0.004
Tokenbar
Token ID5657
Feature activation-3.57e-02

Pos logit contributions
 puck+0.018
 camps+0.017
wreck+0.017
 ship+0.017
 polar+0.017
Neg logit contributions
 blush-0.017
ume-0.016
bs-0.015
Girls-0.014
 perfume-0.014
Tokenrow
Token ID808
Feature activation-1.74e-03

Pos logit contributions
wreck+0.063
 puck+0.061
 skate+0.060
 hockey+0.060
 camps+0.060
Neg logit contributions
ume-0.066
bs-0.063
 blush-0.063
 brushes-0.056
Her-0.055
Token.
Token ID13
Feature activation-3.38e-03

Pos logit contributions
 puck+0.003
 skate+0.003
wreck+0.003
 ship+0.003
 motorcycle+0.003
Neg logit contributions
 blush-0.003
ume-0.003
bs-0.003
Girls-0.003
 perfume-0.003
Token But
Token ID887
Feature activation-2.39e-03

Pos logit contributions
 puck+0.006
wreck+0.006
 skate+0.006
 ship+0.006
 hockey+0.005
Neg logit contributions
 blush-0.007
Girls-0.007
ume-0.007
 perfume-0.007
bs-0.007
Token her
Token ID607
Feature activation+8.95e-04

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 gear+0.004
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
bs-0.005
Token backyard
Token ID24296
Feature activation-1.68e-04

Pos logit contributions
 blush+0.001
 perfume+0.001
ume+0.001
Girls+0.001
bs+0.001
Neg logit contributions
wreck-0.002
 puck-0.002
 skate-0.002
 camps-0.002
 wre-0.002
Token him
Token ID683
Feature activation-4.02e-03

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 motorcycle-0.004
Token a
Token ID257
Feature activation+1.75e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 skate+0.007
 ship+0.007
 hockey+0.007
Neg logit contributions
 blush-0.008
Girls-0.008
ume-0.008
 perfume-0.008
bs-0.008
Token big
Token ID1263
Feature activation+1.03e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
wreck-0.003
 puck-0.003
 skate-0.003
 wre-0.003
 ship-0.003
Token red
Token ID2266
Feature activation-7.03e-03

Pos logit contributions
 blush+0.002
Girls+0.002
 perfume+0.002
ume+0.002
bs+0.002
Neg logit contributions
wreck-0.002
 puck-0.002
 skate-0.002
 wre-0.002
 ship-0.002
Token wheel
Token ID7825
Feature activation-1.27e-02

Pos logit contributions
wreck+0.012
 puck+0.011
 wre+0.011
 skate+0.011
 sailing+0.011
Neg logit contributions
 blush-0.015
 perfume-0.014
ume-0.014
Girls-0.014
 makeup-0.013
Tokenbar
Token ID5657
Feature activation-3.35e-02

Pos logit contributions
 puck+0.023
wreck+0.022
 skate+0.022
 wre+0.021
 camps+0.021
Neg logit contributions
 blush-0.026
ume-0.024
bs-0.023
 perfume-0.023
Girls-0.022
Tokenrow
Token ID808
Feature activation-4.78e-03

Pos logit contributions
 puck+0.073
wreck+0.072
 skate+0.070
 wre+0.069
 hockey+0.069
Neg logit contributions
 blush-0.053
ume-0.051
bs-0.048
 perfume-0.046
Girls-0.045
Token and
Token ID290
Feature activation+7.40e-04

Pos logit contributions
 puck+0.009
 skate+0.009
wreck+0.009
 wre+0.008
 ship+0.008
Neg logit contributions
 blush-0.009
ume-0.009
 perfume-0.008
Girls-0.008
bs-0.008
Token filled
Token ID5901
Feature activation+4.64e-03

Pos logit contributions
 blush+0.002
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
wreck-0.001
 puck-0.001
 skate-0.001
 ship-0.001
 wre-0.001
Token it
Token ID340
Feature activation-1.22e-03

Pos logit contributions
 blush+0.008
 perfume+0.007
Girls+0.007
 makeup+0.007
ume+0.006
Neg logit contributions
 puck-0.010
wreck-0.010
 ship-0.010
 camps-0.010
 skate-0.009
Token with
Token ID351
Feature activation-5.84e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 motorcycle+0.002
Neg logit contributions
 blush-0.002
 perfume-0.002
ume-0.002
Girls-0.002
bs-0.002
Token placed
Token ID4624
Feature activation+2.78e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Token it
Token ID340
Feature activation+2.08e-03

Pos logit contributions
 blush+0.005
Girls+0.005
 perfume+0.005
ume+0.005
bs+0.005
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.005
 ship-0.005
 motorcycle-0.005
Token onto
Token ID4291
Feature activation-2.72e-03

Pos logit contributions
 blush+0.004
Girls+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.003
Token the
Token ID262
Feature activation+1.16e-03

Pos logit contributions
 puck+0.005
 skate+0.005
wreck+0.005
 ship+0.005
 wre+0.005
Neg logit contributions
 blush-0.005
 perfume-0.005
 makeup-0.004
ume-0.004
Girls-0.004
Token wheel
Token ID7825
Feature activation-1.10e-02

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 hockey-0.002
Tokenbar
Token ID5657
Feature activation-3.33e-02

Pos logit contributions
 puck+0.020
 wre+0.019
 skate+0.019
 camps+0.019
wreck+0.019
Neg logit contributions
 blush-0.021
ume-0.020
bs-0.019
 perfume-0.019
Girls-0.018
Tokenrow
Token ID808
Feature activation-3.24e-03

Pos logit contributions
 puck+0.082
wreck+0.081
 skate+0.081
 hockey+0.079
 wre+0.078
Neg logit contributions
ume-0.041
 blush-0.041
bs-0.039
 perfume-0.035
Girls-0.034
Token.
Token ID13
Feature activation-6.05e-04

Pos logit contributions
 puck+0.006
 skate+0.006
wreck+0.006
 wre+0.006
 motorcycle+0.006
Neg logit contributions
 blush-0.006
ume-0.006
bs-0.006
 perfume-0.006
Girls-0.005
Token
Token ID198
Feature activation-1.84e-03

Pos logit contributions
wreck+0.001
 ship+0.001
 puck+0.001
 skate+0.001
 wre+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
bs-0.001
 perfume-0.001
Token
Token ID198
Feature activation+8.56e-06

Pos logit contributions
 puck+0.004
 ship+0.004
wreck+0.004
 skate+0.003
 motorcycle+0.003
Neg logit contributions
Girls-0.003
 blush-0.003
ume-0.003
bs-0.003
Her-0.003
TokenJohn
Token ID7554
Feature activation-7.60e-03

Feature not active on prev token;
no predictions were affected.
Token the
Token ID262
Feature activation+3.50e-03

Pos logit contributions
 blush+0.001
Girls+0.000
 perfume+0.000
ume+0.000
bs+0.000
Neg logit contributions
wreck-0.001
 puck-0.001
 ship-0.001
 skate-0.001
 motorcycle-0.001
Token cat
Token ID3797
Feature activation+1.63e-03

Pos logit contributions
 blush+0.007
Girls+0.007
ume+0.007
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.007
 ship-0.006
wreck-0.006
 skate-0.006
 gear-0.006
Token off
Token ID572
Feature activation-6.07e-04

Pos logit contributions
 blush+0.003
ume+0.003
 perfume+0.003
Girls+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 motorcycle-0.003
Token the
Token ID262
Feature activation-2.27e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 motorcycle+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token wheel
Token ID7825
Feature activation-1.18e-02

Pos logit contributions
wreck+0.004
 puck+0.004
 skate+0.004
 hockey+0.004
 wre+0.004
Neg logit contributions
 blush-0.004
 perfume-0.004
Girls-0.004
ume-0.004
 roses-0.004
Tokenbar
Token ID5657
Feature activation-3.19e-02

Pos logit contributions
 puck+0.023
 wre+0.023
 camps+0.022
wreck+0.022
 skate+0.022
Neg logit contributions
 blush-0.022
ume-0.020
bs-0.019
 perfume-0.019
Her-0.018
Tokenrow
Token ID808
Feature activation-1.70e-03

Pos logit contributions
 puck+0.080
wreck+0.080
 skate+0.078
 hockey+0.077
 wre+0.077
Neg logit contributions
 blush-0.038
ume-0.037
bs-0.036
 perfume-0.032
Her-0.031
Token and
Token ID290
Feature activation-5.29e-06

Pos logit contributions
 puck+0.003
 skate+0.003
wreck+0.003
 ship+0.003
 wre+0.003
Neg logit contributions
 blush-0.003
ume-0.003
Girls-0.003
 perfume-0.003
bs-0.003
Token put
Token ID1234
Feature activation+2.58e-03

Feature not active on prev token;
no predictions were affected.
Token him
Token ID683
Feature activation-1.19e-02

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.005
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token back
Token ID736
Feature activation-7.78e-03

Pos logit contributions
 puck+0.022
wreck+0.021
 skate+0.021
 ship+0.021
 hockey+0.020
Neg logit contributions
 blush-0.024
Girls-0.023
ume-0.023
 perfume-0.022
bs-0.022
Token light
Token ID1657
Feature activation-2.84e-03

Pos logit contributions
 camps+0.011
 puck+0.011
wreck+0.010
 tanks+0.010
 motorcycle+0.010
Neg logit contributions
 blush-0.011
 perfume-0.009
ume-0.009
bs-0.009
 makeup-0.009
Tokenen
Token ID268
Feature activation-5.99e-03

Pos logit contributions
 puck+0.006
wreck+0.005
 skate+0.005
 ship+0.005
 hockey+0.005
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
bs-0.005
Token up
Token ID510
Feature activation-9.85e-03

Pos logit contributions
 puck+0.011
wreck+0.011
 skate+0.011
 ship+0.011
 hockey+0.010
Neg logit contributions
 blush-0.012
Girls-0.011
ume-0.011
 perfume-0.011
bs-0.011
Token the
Token ID262
Feature activation+8.15e-04

Pos logit contributions
 puck+0.018
wreck+0.017
 skate+0.017
 ship+0.016
 motorcycle+0.016
Neg logit contributions
 blush-0.020
ume-0.019
Girls-0.019
 perfume-0.019
bs-0.019
Token wheel
Token ID7825
Feature activation-1.34e-02

Pos logit contributions
 blush+0.002
Girls+0.001
 perfume+0.001
ume+0.001
bs+0.001
Neg logit contributions
wreck-0.002
 puck-0.002
 skate-0.001
 hockey-0.001
 ship-0.001
Tokenbar
Token ID5657
Feature activation-3.18e-02

Pos logit contributions
 puck+0.024
 wre+0.023
 skate+0.023
wreck+0.022
 camps+0.022
Neg logit contributions
 blush-0.027
ume-0.026
bs-0.024
 perfume-0.024
Girls-0.023
Tokenrow
Token ID808
Feature activation-6.51e-03

Pos logit contributions
 puck+0.082
wreck+0.081
 skate+0.080
 hockey+0.079
 wre+0.078
Neg logit contributions
ume-0.036
 blush-0.036
bs-0.033
 perfume-0.030
Girls-0.029
Token.
Token ID13
Feature activation-1.24e-03

Pos logit contributions
 puck+0.012
 skate+0.012
wreck+0.012
 ship+0.011
 motorcycle+0.011
Neg logit contributions
 blush-0.012
ume-0.012
 perfume-0.012
Girls-0.011
bs-0.011
Token<|endoftext|>
Token ID50256
Feature activation-8.76e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.003
Girls-0.003
ume-0.003
 perfume-0.002
bs-0.002
TokenOnce
Token ID7454
Feature activation+5.27e-03

Pos logit contributions
 puck+0.019
wreck+0.018
 ship+0.018
 skate+0.018
 motorcycle+0.017
Neg logit contributions
 blush-0.015
Girls-0.015
ume-0.014
 perfume-0.014
bs-0.013
Token there
Token ID612
Feature activation-1.75e-03

Pos logit contributions
 blush+0.011
Girls+0.010
ume+0.010
 perfume+0.010
bs+0.009
Neg logit contributions
 puck-0.010
wreck-0.009
 skate-0.009
 ship-0.009
 his-0.009
Token a
Token ID257
Feature activation+1.82e-03

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Token big
Token ID1263
Feature activation+3.82e-04

Pos logit contributions
 blush+0.004
Girls+0.004
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Token,
Token ID11
Feature activation+7.29e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Token spinning
Token ID19493
Feature activation-6.15e-03

Pos logit contributions
 blush+0.014
Girls+0.013
ume+0.013
 perfume+0.013
bs+0.012
Neg logit contributions
 puck-0.014
wreck-0.014
 skate-0.014
 ship-0.013
 hockey-0.013
Token wheel
Token ID7825
Feature activation-1.37e-02

Pos logit contributions
 puck+0.011
wreck+0.011
 skate+0.010
 ship+0.010
 hockey+0.010
Neg logit contributions
 blush-0.013
Girls-0.012
ume-0.012
 perfume-0.012
bs-0.012
Tokenbar
Token ID5657
Feature activation-3.15e-02

Pos logit contributions
 puck+0.026
 camps+0.025
 wre+0.025
wreck+0.025
Ar+0.024
Neg logit contributions
 blush-0.025
ume-0.024
 perfume-0.022
bs-0.022
Girls-0.021
Tokenrow
Token ID808
Feature activation-1.38e-03

Pos logit contributions
 puck+0.074
wreck+0.074
 skate+0.073
 hockey+0.071
 camps+0.070
Neg logit contributions
 blush-0.044
ume-0.043
bs-0.041
Girls-0.039
 perfume-0.039
Token and
Token ID290
Feature activation+6.30e-03

Pos logit contributions
 puck+0.003
 skate+0.003
wreck+0.003
 wre+0.003
 ship+0.003
Neg logit contributions
 blush-0.002
ume-0.002
 perfume-0.002
Girls-0.002
bs-0.002
Token put
Token ID1234
Feature activation+5.32e-04

Pos logit contributions
 blush+0.012
Girls+0.011
ume+0.011
 perfume+0.011
bs+0.011
Neg logit contributions
 puck-0.012
wreck-0.012
 skate-0.012
 ship-0.011
 motorcycle-0.011
Token the
Token ID262
Feature activation+4.25e-03

Pos logit contributions
 blush+0.001
 perfume+0.001
Girls+0.001
ume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 camps-0.001
Token pumpkin
Token ID30089
Feature activation-6.52e-03

Pos logit contributions
 blush+0.008
Girls+0.007
ume+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.008
 ship-0.008
 hockey-0.008
Token was
Token ID373
Feature activation-2.78e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 hockey+0.001
 ship+0.001
Neg logit contributions
 blush-0.001
ume-0.001
Girls-0.001
bs-0.001
 perfume-0.001
Token wheel
Token ID7825
Feature activation-1.27e-02

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 ship+0.005
 hockey+0.005
Neg logit contributions
 blush-0.006
Girls-0.006
ume-0.005
 perfume-0.005
bs-0.005
Tokening
Token ID278
Feature activation-9.35e-03

Pos logit contributions
 puck+0.023
Ar+0.022
wreck+0.022
 camps+0.022
 skate+0.021
Neg logit contributions
 blush-0.024
ume-0.023
bs-0.023
 perfume-0.022
Girls-0.022
Token the
Token ID262
Feature activation+1.57e-03

Pos logit contributions
 puck+0.017
wreck+0.016
 skate+0.016
 ship+0.016
 motorcycle+0.015
Neg logit contributions
 blush-0.019
Girls-0.018
ume-0.018
 perfume-0.018
bs-0.017
Token wheel
Token ID7825
Feature activation-1.07e-02

Pos logit contributions
 blush+0.003
 perfume+0.003
ume+0.003
Girls+0.003
 makeup+0.003
Neg logit contributions
wreck-0.003
 puck-0.003
 skate-0.003
 wre-0.003
oc-0.003
Tokenbar
Token ID5657
Feature activation-3.07e-02

Pos logit contributions
 puck+0.019
 camps+0.018
 skate+0.018
 wre+0.018
wreck+0.018
Neg logit contributions
 blush-0.021
ume-0.020
bs-0.020
 perfume-0.019
Girls-0.019
Tokenrow
Token ID808
Feature activation-2.81e-03

Pos logit contributions
 puck+0.075
wreck+0.075
 skate+0.074
 camps+0.072
 hockey+0.072
Neg logit contributions
 blush-0.038
ume-0.038
bs-0.037
 perfume-0.033
Girls-0.032
Token around
Token ID1088
Feature activation+6.77e-04

Pos logit contributions
 puck+0.005
 skate+0.005
wreck+0.005
 ship+0.005
 motorcycle+0.005
Neg logit contributions
 blush-0.006
ume-0.005
Girls-0.005
 perfume-0.005
bs-0.005
Token she
Token ID673
Feature activation+2.08e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Token made
Token ID925
Feature activation-3.09e-03

Pos logit contributions
 blush+0.004
bs+0.003
Girls+0.003
ume+0.003
 perfume+0.003
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 hockey-0.004
 camps-0.004
Token sure
Token ID1654
Feature activation+2.07e-03

Pos logit contributions
 puck+0.006
wreck+0.006
 skate+0.006
 ship+0.006
 hockey+0.005
Neg logit contributions
 blush-0.006
Girls-0.006
ume-0.006
 perfume-0.006
bs-0.005
Tokenuffy
Token ID15352
Feature activation-2.25e-03

Pos logit contributions
 blush+0.012
Girls+0.011
ume+0.011
 perfume+0.010
bs+0.010
Neg logit contributions
 puck-0.029
wreck-0.028
 skate-0.028
 ship-0.028
 hockey-0.027
Token had
Token ID550
Feature activation-3.16e-03

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.003
 hockey+0.003
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
bs-0.005
Token made
Token ID925
Feature activation-6.11e-03

Pos logit contributions
 puck+0.006
wreck+0.006
 skate+0.006
 ship+0.006
 hockey+0.006
Neg logit contributions
 blush-0.006
Girls-0.006
ume-0.006
 perfume-0.006
bs-0.006
Token the
Token ID262
Feature activation+1.44e-03

Pos logit contributions
 puck+0.011
wreck+0.011
 skate+0.011
 ship+0.011
 motorcycle+0.010
Neg logit contributions
 blush-0.012
Girls-0.012
ume-0.012
 perfume-0.012
bs-0.011
Token wheel
Token ID7825
Feature activation-7.15e-03

Pos logit contributions
 blush+0.003
 perfume+0.002
Girls+0.002
ume+0.002
bs+0.002
Neg logit contributions
wreck-0.003
 puck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Tokenbar
Token ID5657
Feature activation-3.03e-02

Pos logit contributions
 puck+0.013
wreck+0.012
 camps+0.012
 skate+0.012
 hockey+0.012
Neg logit contributions
 blush-0.014
ume-0.013
 perfume-0.013
bs-0.013
Girls-0.013
Tokenrow
Token ID808
Feature activation-2.11e-03

Pos logit contributions
 puck+0.070
wreck+0.070
 skate+0.068
 camps+0.067
 hockey+0.067
Neg logit contributions
 blush-0.043
ume-0.041
bs-0.040
 perfume-0.038
Girls-0.037
Token much
Token ID881
Feature activation+2.93e-03

Pos logit contributions
 puck+0.004
 skate+0.004
wreck+0.004
 ship+0.004
 camps+0.004
Neg logit contributions
 blush-0.004
ume-0.004
 perfume-0.004
Girls-0.004
bs-0.004
Token lighter
Token ID14871
Feature activation-4.85e-03

Pos logit contributions
 blush+0.005
 perfume+0.005
Girls+0.005
bs+0.005
ume+0.005
Neg logit contributions
wreck-0.006
 puck-0.006
 skate-0.006
 ship-0.005
 motorcycle-0.005
Token.
Token ID13
Feature activation+4.51e-04

Pos logit contributions
 puck+0.009
wreck+0.009
 skate+0.009
 ship+0.008
 camps+0.008
Neg logit contributions
 blush-0.009
 perfume-0.009
Girls-0.009
ume-0.009
bs-0.009
Token The
Token ID383
Feature activation+2.15e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
 hockey-0.001
 skate-0.001
 his-0.001
wreck-0.001
Token.
Token ID13
Feature activation-9.91e-05

Pos logit contributions
 blush+0.003
 perfume+0.003
Girls+0.003
bs+0.003
ume+0.003
Neg logit contributions
 puck-0.004
wreck-0.003
 skate-0.003
 ship-0.003
 motorcycle-0.003
Token She
Token ID1375
Feature activation+2.59e-03

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 ship+0.000
 gear+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
 perfume-0.000
bs-0.000
Token saw
Token ID2497
Feature activation+2.26e-04

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.005
 ship-0.005
 hockey-0.005
Token a
Token ID257
Feature activation-3.28e-03

Pos logit contributions
 blush+0.000
Girls+0.000
ume+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 ship-0.000
 hockey-0.000
Token wheel
Token ID7825
Feature activation-1.12e-02

Pos logit contributions
 puck+0.006
wreck+0.006
 skate+0.006
 ship+0.006
 wre+0.006
Neg logit contributions
 blush-0.006
Girls-0.006
 perfume-0.006
ume-0.006
bs-0.005
Tokenbar
Token ID5657
Feature activation-3.03e-02

Pos logit contributions
 puck+0.021
 skate+0.020
wreck+0.020
 camps+0.019
 wre+0.019
Neg logit contributions
 blush-0.022
ume-0.020
 perfume-0.020
Girls-0.019
bs-0.019
Tokenrow
Token ID808
Feature activation-2.97e-03

Pos logit contributions
 puck+0.070
wreck+0.068
 skate+0.067
 hockey+0.066
 wre+0.064
Neg logit contributions
 blush-0.047
ume-0.044
Girls-0.042
bs-0.041
 perfume-0.041
Token,
Token ID11
Feature activation+3.69e-03

Pos logit contributions
 puck+0.006
 skate+0.005
wreck+0.005
 hockey+0.005
 ship+0.005
Neg logit contributions
 blush-0.006
ume-0.005
Girls-0.005
 perfume-0.005
bs-0.005
Token a
Token ID257
Feature activation-7.93e-03

Pos logit contributions
 blush+0.008
Girls+0.007
ume+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.007
wreck-0.006
 skate-0.006
 ship-0.006
 hockey-0.006
Token large
Token ID1588
Feature activation-3.71e-03

Pos logit contributions
wreck+0.015
 puck+0.015
 skate+0.014
 wre+0.014
 ship+0.014
Neg logit contributions
 blush-0.016
Girls-0.015
 perfume-0.015
ume-0.014
bs-0.013
Token sp
Token ID599
Feature activation-1.58e-02

Pos logit contributions
wreck+0.007
 puck+0.007
 skate+0.006
 wre+0.006
 camps+0.006
Neg logit contributions
 blush-0.008
 perfume-0.007
ume-0.007
Girls-0.007
 makeup-0.006
Token of
Token ID286
Feature activation+8.58e-04

Pos logit contributions
 blush+0.004
ume+0.004
bs+0.004
 perfume+0.004
Girls+0.004
Neg logit contributions
 puck-0.005
 skate-0.005
wreck-0.005
 wre-0.005
 camps-0.005
Token soil
Token ID9260
Feature activation-1.51e-03

Pos logit contributions
Girls+0.002
ume+0.002
 blush+0.002
bs+0.002
Her+0.002
Neg logit contributions
 puck-0.001
 gear-0.001
 ship-0.001
 his-0.001
 hockey-0.001
Token into
Token ID656
Feature activation+2.20e-04

Pos logit contributions
 puck+0.003
 skate+0.003
wreck+0.003
 motorcycle+0.003
 wre+0.003
Neg logit contributions
 blush-0.003
 perfume-0.002
ume-0.002
bs-0.002
Girls-0.002
Token the
Token ID262
Feature activation+1.48e-03

Pos logit contributions
 blush+0.000
Girls+0.000
 perfume+0.000
ume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 motorcycle-0.000
 ship-0.000
Token wheel
Token ID7825
Feature activation-1.09e-02

Pos logit contributions
 blush+0.003
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Tokenbar
Token ID5657
Feature activation-3.01e-02

Pos logit contributions
 puck+0.021
 wre+0.020
 skate+0.020
 camps+0.020
Ar+0.020
Neg logit contributions
 blush-0.019
ume-0.019
bs-0.018
 perfume-0.017
 makeup-0.016
Tokenrow
Token ID808
Feature activation-3.74e-03

Pos logit contributions
 puck+0.074
wreck+0.073
 skate+0.073
 hockey+0.071
 wre+0.070
Neg logit contributions
 blush-0.038
ume-0.038
bs-0.036
 perfume-0.034
Girls-0.033
Token.
Token ID13
Feature activation-2.47e-05

Pos logit contributions
 puck+0.008
 skate+0.008
 motorcycle+0.007
wreck+0.007
 camps+0.007
Neg logit contributions
 blush-0.006
ume-0.006
bs-0.006
 perfume-0.006
Girls-0.006
Token It
Token ID632
Feature activation+3.40e-03

Pos logit contributions
 ship+0.000
wreck+0.000
 puck+0.000
 sword+0.000
 skate+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
 brushes-0.000
 Her-0.000
Token was
Token ID373
Feature activation-1.29e-03

Pos logit contributions
 blush+0.006
Girls+0.006
 perfume+0.006
bs+0.006
ume+0.006
Neg logit contributions
wreck-0.006
 puck-0.006
 skate-0.006
 motorcycle-0.006
 hockey-0.006
Token heavy
Token ID4334
Feature activation-1.02e-02

Pos logit contributions
wreck+0.003
 puck+0.003
 skate+0.003
 motorcycle+0.003
 ship+0.003
Neg logit contributions
 blush-0.002
 perfume-0.002
ume-0.002
Girls-0.002
 makeup-0.002
Token He
Token ID679
Feature activation-7.34e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 hockey+0.005
 ship+0.005
Neg logit contributions
 blush-0.007
Girls-0.007
ume-0.007
 perfume-0.007
bs-0.007
Token jumped
Token ID11687
Feature activation+4.70e-04

Pos logit contributions
 puck+0.015
wreck+0.015
 skate+0.014
 ship+0.014
 hockey+0.014
Neg logit contributions
 blush-0.013
Girls-0.013
ume-0.012
 perfume-0.012
bs-0.012
Token onto
Token ID4291
Feature activation+1.38e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 motorcycle-0.001
Token the
Token ID262
Feature activation-2.00e-04

Pos logit contributions
 blush+0.003
 perfume+0.003
Girls+0.003
ume+0.002
bs+0.002
Neg logit contributions
wreck-0.003
 puck-0.003
 ship-0.003
 skate-0.002
 motorcycle-0.002
Token wheel
Token ID7825
Feature activation-9.37e-03

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 ship+0.000
 hockey+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
 perfume-0.000
ume-0.000
bs-0.000
Tokenbar
Token ID5657
Feature activation-2.98e-02

Pos logit contributions
 puck+0.019
 wre+0.018
 skate+0.018
wreck+0.018
 camps+0.018
Neg logit contributions
 blush-0.016
ume-0.015
bs-0.015
 perfume-0.014
Girls-0.014
Tokenrow
Token ID808
Feature activation-1.45e-03

Pos logit contributions
 puck+0.073
wreck+0.073
 skate+0.071
 hockey+0.071
 wre+0.071
Neg logit contributions
 blush-0.037
ume-0.037
bs-0.035
 perfume-0.031
Her-0.031
Token and
Token ID290
Feature activation-1.60e-04

Pos logit contributions
 puck+0.003
 skate+0.003
wreck+0.003
 wre+0.003
 ship+0.003
Neg logit contributions
 blush-0.003
ume-0.003
 perfume-0.002
Girls-0.002
bs-0.002
Token started
Token ID2067
Feature activation-2.36e-03

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 ship+0.000
 hockey+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
 perfume-0.000
bs-0.000
Token rolling
Token ID10708
Feature activation-7.64e-03

Pos logit contributions
wreck+0.005
 puck+0.005
 ship+0.005
 camps+0.004
 motorcycle+0.004
Neg logit contributions
 blush-0.004
 perfume-0.004
Girls-0.004
ume-0.004
bs-0.004
Token around
Token ID1088
Feature activation+1.36e-03

Pos logit contributions
wreck+0.017
 puck+0.016
 ship+0.016
 skate+0.016
 motorcycle+0.015
Neg logit contributions
 blush-0.013
Girls-0.012
 perfume-0.012
bs-0.011
ume-0.011
Token back
Token ID736
Feature activation+1.65e-03

Pos logit contributions
 puck+0.013
 motorcycle+0.013
wreck+0.013
 skate+0.013
 ship+0.012
Neg logit contributions
 blush-0.010
Girls-0.009
ume-0.009
 perfume-0.009
bs-0.009
Token with
Token ID351
Feature activation-4.22e-04

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 motorcycle-0.003
Token a
Token ID257
Feature activation+2.33e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 motorcycle+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token big
Token ID1263
Feature activation-1.83e-04

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token wheel
Token ID7825
Feature activation-1.05e-02

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 ship+0.000
 hockey+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
 perfume-0.000
bs-0.000
Tokenbar
Token ID5657
Feature activation-2.90e-02

Pos logit contributions
 puck+0.021
Ar+0.020
 camps+0.020
 skate+0.019
 wre+0.019
Neg logit contributions
 blush-0.019
ume-0.018
 perfume-0.017
bs-0.017
 makeup-0.016
Tokenrow
Token ID808
Feature activation-1.42e-03

Pos logit contributions
 puck+0.070
wreck+0.070
 skate+0.068
 hockey+0.067
 camps+0.067
Neg logit contributions
 blush-0.040
ume-0.038
bs-0.036
 perfume-0.034
Girls-0.034
Token.
Token ID13
Feature activation-2.04e-03

Pos logit contributions
 puck+0.003
 skate+0.003
wreck+0.003
 wre+0.003
 camps+0.003
Neg logit contributions
 blush-0.003
ume-0.003
 perfume-0.002
bs-0.002
Girls-0.002
Token He
Token ID679
Feature activation-4.91e-03

Pos logit contributions
wreck+0.003
 ship+0.003
 puck+0.003
 skate+0.003
 motorcycle+0.003
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.004
 perfume-0.004
bs-0.004
Token asked
Token ID1965
Feature activation+5.00e-03

Pos logit contributions
 puck+0.010
wreck+0.010
 skate+0.010
 wre+0.010
 motorcycle+0.009
Neg logit contributions
 blush-0.008
Girls-0.008
bs-0.008
 perfume-0.007
ume-0.007
Token the
Token ID262
Feature activation+3.84e-03

Pos logit contributions
 blush+0.011
Girls+0.011
 perfume+0.011
ume+0.010
bs+0.010
Neg logit contributions
 puck-0.008
wreck-0.008
 skate-0.008
 ship-0.007
 camps-0.007
Token.
Token ID13
Feature activation-2.55e-04

Pos logit contributions
 puck+0.002
wreck+0.002
 ship+0.002
 skate+0.002
 camps+0.002
Neg logit contributions
 blush-0.002
 perfume-0.002
ume-0.002
Girls-0.002
bs-0.002
Token He
Token ID679
Feature activation-5.37e-03

Pos logit contributions
 ship+0.000
wreck+0.000
 puck+0.000
 skate+0.000
 sailed+0.000
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
 mascara-0.001
Token found
Token ID1043
Feature activation+1.56e-03

Pos logit contributions
wreck+0.012
 puck+0.012
 motorcycle+0.012
 skate+0.011
 hockey+0.011
Neg logit contributions
 blush-0.008
Girls-0.008
bs-0.008
 perfume-0.007
ume-0.007
Token a
Token ID257
Feature activation-1.04e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 motorcycle-0.003
Token wheel
Token ID7825
Feature activation-9.33e-03

Pos logit contributions
wreck+0.002
 puck+0.002
 skate+0.002
 wre+0.002
 sailed+0.002
Neg logit contributions
 blush-0.002
 perfume-0.002
Girls-0.002
ume-0.002
 makeup-0.002
Tokenbar
Token ID5657
Feature activation-2.90e-02

Pos logit contributions
 puck+0.018
Ar+0.018
wreck+0.018
 wre+0.018
 camps+0.018
Neg logit contributions
 blush-0.016
ume-0.015
 perfume-0.015
Girls-0.014
 makeup-0.014
Tokenrow
Token ID808
Feature activation-1.78e-03

Pos logit contributions
wreck+0.069
 puck+0.068
 skate+0.066
 hockey+0.065
 camps+0.065
Neg logit contributions
 blush-0.039
ume-0.038
bs-0.035
 perfume-0.034
Girls-0.034
Token,
Token ID11
Feature activation+3.85e-03

Pos logit contributions
 puck+0.003
 skate+0.003
wreck+0.003
 wre+0.003
 camps+0.003
Neg logit contributions
 blush-0.003
ume-0.003
 perfume-0.003
Girls-0.003
bs-0.003
Token a
Token ID257
Feature activation-6.59e-03

Pos logit contributions
 blush+0.008
 perfume+0.007
Girls+0.007
ume+0.007
bs+0.007
Neg logit contributions
wreck-0.007
 puck-0.007
 skate-0.007
 ship-0.007
 motorcycle-0.007
Token tr
Token ID491
Feature activation-4.88e-03

Pos logit contributions
wreck+0.012
 puck+0.012
 wre+0.012
 skate+0.011
 sailed+0.011
Neg logit contributions
 blush-0.013
 perfume-0.012
Girls-0.012
ume-0.012
 makeup-0.011
Tokenamp
Token ID696
Feature activation-1.54e-05

Pos logit contributions
wreck+0.010
 puck+0.010
 ship+0.010
 his+0.010
 hockey+0.009
Neg logit contributions
 blush-0.008
Girls-0.008
ume-0.008
bs-0.007
 perfume-0.007
Token flavors
Token ID17361
Feature activation-9.91e-03

Pos logit contributions
 puck+0.016
wreck+0.015
 skate+0.015
 ship+0.015
 wre+0.014
Neg logit contributions
 blush-0.018
ume-0.017
Girls-0.017
 perfume-0.017
bs-0.016
Token they
Token ID484
Feature activation-2.00e-03

Pos logit contributions
 puck+0.018
wreck+0.017
 skate+0.017
 ship+0.017
 hockey+0.016
Neg logit contributions
 blush-0.020
Girls-0.020
ume-0.019
 perfume-0.019
bs-0.019
Token liked
Token ID8288
Feature activation-2.71e-03

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 hockey+0.003
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
 perfume-0.004
bs-0.004
Token and
Token ID290
Feature activation-6.66e-04

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 ship+0.005
 gear+0.004
Neg logit contributions
 blush-0.006
Girls-0.005
 perfume-0.005
ume-0.005
bs-0.005
Token what
Token ID644
Feature activation+9.42e-04

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token topp
Token ID23126
Feature activation-2.88e-02

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Tokenings
Token ID654
Feature activation+9.08e-04

Pos logit contributions
 puck+0.062
 skate+0.061
wreck+0.060
 ship+0.059
 camps+0.058
Neg logit contributions
 blush-0.048
ume-0.046
Girls-0.045
 perfume-0.044
bs-0.043
Token would
Token ID561
Feature activation-1.86e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Token go
Token ID467
Feature activation-1.02e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 camps+0.003
Neg logit contributions
 blush-0.004
Girls-0.003
ume-0.003
 perfume-0.003
bs-0.003
Token best
Token ID1266
Feature activation-4.37e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 gear+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token.
Token ID13
Feature activation-3.27e-03

Pos logit contributions
 puck+0.008
wreck+0.008
 skate+0.008
 ship+0.008
 camps+0.007
Neg logit contributions
 blush-0.008
ume-0.008
 perfume-0.008
Girls-0.008
bs-0.008
Token it
Token ID340
Feature activation+2.62e-03

Pos logit contributions
 puck+0.005
 skate+0.005
wreck+0.005
 ship+0.004
 motorcycle+0.004
Neg logit contributions
 blush-0.003
 perfume-0.003
bs-0.003
ume-0.003
 makeup-0.003
Token away
Token ID1497
Feature activation-6.09e-03

Pos logit contributions
 blush+0.005
ume+0.004
bs+0.004
 perfume+0.004
Girls+0.004
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.005
 ship-0.005
 motorcycle-0.005
Token in
Token ID287
Feature activation-3.94e-03

Pos logit contributions
 puck+0.014
 skate+0.013
 motorcycle+0.013
wreck+0.013
 ship+0.013
Neg logit contributions
 perfume-0.009
 blush-0.009
ume-0.008
bs-0.008
 bloom-0.008
Token a
Token ID257
Feature activation-5.32e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 skate+0.007
 motorcycle+0.007
 ship+0.007
Neg logit contributions
 perfume-0.007
 blush-0.007
Girls-0.007
ume-0.007
 makeup-0.006
Token wheel
Token ID7825
Feature activation-1.32e-02

Pos logit contributions
wreck+0.010
 puck+0.010
 skate+0.010
 ship+0.009
 wre+0.009
Neg logit contributions
 blush-0.010
Girls-0.009
 perfume-0.009
ume-0.009
bs-0.009
Tokenbar
Token ID5657
Feature activation-2.88e-02

Pos logit contributions
 puck+0.026
Ar+0.026
 wre+0.026
 camps+0.026
 skate+0.026
Neg logit contributions
 blush-0.022
ume-0.022
bs-0.020
 perfume-0.019
 makeup-0.018
Tokenrow
Token ID808
Feature activation-5.61e-03

Pos logit contributions
 puck+0.070
wreck+0.070
 skate+0.069
 hockey+0.066
 wre+0.066
Neg logit contributions
 blush-0.038
ume-0.038
bs-0.035
 perfume-0.033
Girls-0.033
Token.
Token ID13
Feature activation+4.82e-03

Pos logit contributions
 puck+0.012
 skate+0.011
 motorcycle+0.011
Ar+0.011
wreck+0.011
Neg logit contributions
ume-0.009
 blush-0.009
 perfume-0.008
bs-0.008
Girls-0.008
Token
Token ID198
Feature activation+1.71e-03

Pos logit contributions
 blush+0.008
Girls+0.007
bs+0.007
ume+0.007
 perfume+0.007
Neg logit contributions
wreck-0.011
 puck-0.011
 skate-0.010
 ship-0.010
 wre-0.010
Token
Token ID198
Feature activation+6.03e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
bs+0.003
 perfume+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 ship-0.003
 skate-0.003
 motorcycle-0.003
TokenOnce
Token ID7454
Feature activation+4.70e-03

Pos logit contributions
Her+0.009
Girls+0.009
ume+0.008
 blush+0.008
She+0.007
Neg logit contributions
 ship-0.014
 puck-0.014
 wre-0.013
 tanks-0.013
 motorcycle-0.013
Token filled
Token ID5901
Feature activation+6.11e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 skate+0.007
 hockey+0.007
 ship+0.007
Neg logit contributions
 blush-0.006
Girls-0.006
ume-0.006
bs-0.006
 perfume-0.005
Token up
Token ID510
Feature activation+9.32e-05

Pos logit contributions
 blush+0.011
 perfume+0.011
Girls+0.010
 makeup+0.010
Her+0.009
Neg logit contributions
 puck-0.012
wreck-0.011
 skate-0.011
 camps-0.011
 ship-0.011
Token lots
Token ID6041
Feature activation+7.95e-03

Pos logit contributions
 blush+0.000
 perfume+0.000
Girls+0.000
 makeup+0.000
ume+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 ship-0.000
 camps-0.000
Token of
Token ID286
Feature activation+2.88e-03

Pos logit contributions
 blush+0.014
Girls+0.013
ume+0.013
 perfume+0.013
bs+0.012
Neg logit contributions
 puck-0.017
wreck-0.017
 skate-0.016
 ship-0.016
 motorcycle-0.016
Token wheel
Token ID7825
Feature activation-1.09e-02

Pos logit contributions
 blush+0.006
ume+0.006
Girls+0.006
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.005
wreck-0.005
 ship-0.005
 skate-0.005
 gear-0.005
Tokenbar
Token ID5657
Feature activation-2.85e-02

Pos logit contributions
 puck+0.023
 camps+0.022
wreck+0.022
Ar+0.022
 skate+0.022
Neg logit contributions
 blush-0.017
ume-0.015
bs-0.015
 perfume-0.015
 brushes-0.014
Tokenrows
Token ID8516
Feature activation+3.38e-03

Pos logit contributions
wreck+0.068
 puck+0.068
 skate+0.067
 hockey+0.064
 camps+0.064
Neg logit contributions
 blush-0.039
ume-0.037
bs-0.036
Girls-0.036
 perfume-0.034
Token with
Token ID351
Feature activation-2.10e-03

Pos logit contributions
 blush+0.006
ume+0.006
 perfume+0.006
bs+0.006
Girls+0.006
Neg logit contributions
 puck-0.007
 skate-0.006
wreck-0.006
 camps-0.006
 wre-0.006
Token the
Token ID262
Feature activation+4.68e-03

Pos logit contributions
wreck+0.004
 puck+0.004
 skate+0.004
 ship+0.004
 motorcycle+0.004
Neg logit contributions
 blush-0.004
 perfume-0.004
bs-0.004
ume-0.004
Girls-0.004
Token waste
Token ID7030
Feature activation+2.19e-03

Pos logit contributions
 blush+0.009
Girls+0.009
ume+0.008
 perfume+0.008
bs+0.008
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.009
 ship-0.008
 hockey-0.008
Token and
Token ID290
Feature activation+2.82e-03

Pos logit contributions
 blush+0.004
ume+0.004
Girls+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token He
Token ID679
Feature activation-5.51e-03

Pos logit contributions
 puck+0.008
wreck+0.007
 skate+0.007
 ship+0.007
 hockey+0.007
Neg logit contributions
 blush-0.009
Girls-0.009
ume-0.008
 perfume-0.008
bs-0.008
Token also
Token ID635
Feature activation+6.71e-03

Pos logit contributions
 puck+0.010
wreck+0.010
 skate+0.009
 ship+0.009
 hockey+0.009
Neg logit contributions
 blush-0.011
Girls-0.011
ume-0.011
 perfume-0.010
bs-0.010
Token saw
Token ID2497
Feature activation+3.00e-03

Pos logit contributions
 blush+0.013
Girls+0.013
ume+0.013
 perfume+0.012
bs+0.012
Neg logit contributions
 puck-0.013
wreck-0.012
 skate-0.012
 ship-0.012
 his-0.012
Token some
Token ID617
Feature activation+3.98e-03

Pos logit contributions
 blush+0.006
Girls+0.006
 perfume+0.006
ume+0.006
bs+0.005
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.005
 ship-0.005
 motorcycle-0.005
Token tasty
Token ID25103
Feature activation-2.75e-03

Pos logit contributions
 blush+0.008
Girls+0.007
ume+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.008
wreck-0.008
 skate-0.007
 ship-0.007
 hockey-0.007
Token seaw
Token ID32085
Feature activation-2.78e-02

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 ship+0.005
 motorcycle+0.005
Neg logit contributions
 blush-0.005
 perfume-0.005
Girls-0.005
ume-0.005
bs-0.005
Tokeneed
Token ID2308
Feature activation-6.26e-03

Pos logit contributions
 his+0.050
 motorcycle+0.048
 skate+0.048
 puck+0.047
 wre+0.047
Neg logit contributions
 blush-0.052
ume-0.052
bs-0.049
 perfume-0.047
Girls-0.045
Token and
Token ID290
Feature activation+3.59e-03

Pos logit contributions
 puck+0.011
 skate+0.011
wreck+0.011
 ship+0.010
 hockey+0.010
Neg logit contributions
 blush-0.013
ume-0.012
Girls-0.012
 perfume-0.012
bs-0.012
Token decided
Token ID3066
Feature activation-3.94e-03

Pos logit contributions
 blush+0.007
Girls+0.007
 perfume+0.007
ume+0.007
bs+0.006
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.006
 ship-0.006
 motorcycle-0.006
Token to
Token ID284
Feature activation-1.37e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 skate+0.007
 ship+0.007
 camps+0.007
Neg logit contributions
 blush-0.008
Girls-0.007
ume-0.007
 perfume-0.007
bs-0.007
Token give
Token ID1577
Feature activation+7.27e-03

Pos logit contributions
 puck+0.003
wreck+0.002
 motorcycle+0.002
 skate+0.002
 camps+0.002
Neg logit contributions
 blush-0.003
ume-0.002
 perfume-0.002
Girls-0.002
bs-0.002
Token fun
Token ID1257
Feature activation-2.10e-03

Pos logit contributions
 blush+0.003
Girls+0.003
 perfume+0.003
ume+0.003
bs+0.003
Neg logit contributions
wreck-0.003
 puck-0.003
 ship-0.003
 skate-0.003
 motorcycle-0.002
Token.
Token ID13
Feature activation+5.11e-04

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 motorcycle+0.004
Neg logit contributions
 blush-0.004
Girls-0.004
 perfume-0.004
ume-0.004
bs-0.004
Token Soon
Token ID15894
Feature activation-4.77e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
bs+0.001
 perfume+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 ship-0.001
 skate-0.001
 motorcycle-0.001
Token the
Token ID262
Feature activation-2.40e-03

Pos logit contributions
wreck+0.009
 puck+0.009
 skate+0.009
 ship+0.009
 motorcycle+0.008
Neg logit contributions
 blush-0.009
Girls-0.009
ume-0.009
 perfume-0.009
bs-0.009
Token wheel
Token ID7825
Feature activation-1.05e-02

Pos logit contributions
wreck+0.004
 puck+0.004
 hockey+0.004
 wre+0.004
 camps+0.004
Neg logit contributions
 blush-0.005
Girls-0.004
 perfume-0.004
 makeup-0.004
ume-0.004
Tokenbar
Token ID5657
Feature activation-2.68e-02

Pos logit contributions
 puck+0.019
wreck+0.018
 skate+0.018
 camps+0.017
 hockey+0.017
Neg logit contributions
 blush-0.021
ume-0.020
Girls-0.020
 perfume-0.019
bs-0.019
Tokenrow
Token ID808
Feature activation+3.96e-04

Pos logit contributions
wreck+0.052
 puck+0.052
 skate+0.051
 hockey+0.050
 camps+0.050
Neg logit contributions
 blush-0.049
ume-0.046
bs-0.045
Girls-0.045
 perfume-0.043
Token was
Token ID373
Feature activation-3.01e-03

Pos logit contributions
 blush+0.001
ume+0.001
Girls+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
 skate-0.001
wreck-0.001
 ship-0.001
 motorcycle-0.001
Token empty
Token ID6565
Feature activation-3.75e-03

Pos logit contributions
 puck+0.006
wreck+0.006
 skate+0.005
 ship+0.005
 motorcycle+0.005
Neg logit contributions
 blush-0.006
ume-0.006
Girls-0.005
 perfume-0.005
bs-0.005
Token and
Token ID290
Feature activation+2.10e-03

Pos logit contributions
 puck+0.007
 skate+0.007
wreck+0.007
 ship+0.007
 motorcycle+0.007
Neg logit contributions
 blush-0.007
 perfume-0.007
ume-0.006
Girls-0.006
 makeup-0.006
Token all
Token ID477
Feature activation+8.57e-04

Pos logit contributions
 blush+0.004
Girls+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.004
Token
Token ID220
Feature activation-6.37e-04

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
bs+0.001
 perfume+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 motorcycle-0.001
Token
Token ID198
Feature activation-1.32e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 ship+0.001
 skate+0.001
 motorcycle+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
bs-0.001
 perfume-0.001
Token
Token ID198
Feature activation+1.41e-03

Pos logit contributions
 puck+0.003
 ship+0.002
wreck+0.002
 skate+0.002
 motorcycle+0.002
Neg logit contributions
Girls-0.003
 blush-0.002
ume-0.002
bs-0.002
 perfume-0.002
TokenThe
Token ID464
Feature activation+4.03e-03

Pos logit contributions
Girls+0.002
 blush+0.002
ume+0.002
bs+0.002
 perfume+0.002
Neg logit contributions
 puck-0.003
 ship-0.003
wreck-0.003
 skate-0.003
 motorcycle-0.003
Token wheel
Token ID7825
Feature activation-1.36e-02

Pos logit contributions
 blush+0.008
Girls+0.007
ume+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.008
wreck-0.008
 skate-0.008
 ship-0.008
 hockey-0.007
Tokenbar
Token ID5657
Feature activation-2.64e-02

Pos logit contributions
 puck+0.025
 skate+0.024
wreck+0.024
 camps+0.023
 hockey+0.023
Neg logit contributions
 blush-0.027
ume-0.026
Girls-0.025
bs-0.024
 perfume-0.024
Tokenrow
Token ID808
Feature activation+8.11e-05

Pos logit contributions
 puck+0.058
wreck+0.058
 skate+0.057
 hockey+0.055
 camps+0.055
Neg logit contributions
 blush-0.042
Girls-0.040
ume-0.040
bs-0.038
 perfume-0.038
Token wheel
Token ID7825
Feature activation-1.31e-02

Pos logit contributions
 blush+0.000
Girls+0.000
ume+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
 skate-0.000
wreck-0.000
 ship-0.000
 hockey-0.000
Tokened
Token ID276
Feature activation-3.39e-03

Pos logit contributions
 puck+0.026
 skate+0.025
 camps+0.025
wreck+0.025
 wre+0.024
Neg logit contributions
 blush-0.024
ume-0.022
Girls-0.022
bs-0.022
 perfume-0.021
Token the
Token ID262
Feature activation+3.26e-03

Pos logit contributions
 skate+0.007
 puck+0.007
wreck+0.007
 motorcycle+0.007
 ship+0.006
Neg logit contributions
 blush-0.006
 perfume-0.005
bs-0.005
Girls-0.005
ume-0.005
Token cup
Token ID6508
Feature activation+1.28e-03

Pos logit contributions
 blush+0.006
Girls+0.006
 perfume+0.005
ume+0.005
bs+0.005
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.006
 ship-0.006
 hockey-0.006
Token dolls
Token ID36062
Feature activation+3.19e-03

Pos logit contributions
Girls+0.003
 blush+0.003
ume+0.003
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.003
 skate-0.003
 ship-0.003
 gear-0.003
wreck-0.003
Token around
Token ID1088
Feature activation-5.41e-04

Pos logit contributions
 blush+0.006
ume+0.006
bs+0.006
Girls+0.005
 perfume+0.005
Neg logit contributions
 puck-0.006
wreck-0.006
 ship-0.006
 camps-0.006
 skate-0.006
Token in
Token ID287
Feature activation-1.76e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token a
Token ID257
Feature activation-2.79e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 hockey+0.003
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
 perfume-0.003
bs-0.003
Token wheel
Token ID7825
Feature activation-9.17e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 ship+0.005
 hockey+0.005
Neg logit contributions
 blush-0.006
Girls-0.005
ume-0.005
 perfume-0.005
bs-0.005
Tokenbar
Token ID5657
Feature activation-2.64e-02

Pos logit contributions
 puck+0.017
wreck+0.017
 camps+0.016
 wre+0.016
 skate+0.016
Neg logit contributions
 blush-0.018
ume-0.017
Girls-0.016
 perfume-0.016
bs-0.016
Tokenrow
Token ID808
Feature activation-1.40e-03

Pos logit contributions
 puck+0.060
wreck+0.060
 skate+0.058
 hockey+0.057
 wre+0.056
Neg logit contributions
 blush-0.039
ume-0.038
bs-0.035
 perfume-0.034
Girls-0.034
Token she
Token ID673
Feature activation+1.31e-03

Pos logit contributions
 puck+0.003
wreck+0.002
 skate+0.002
 ship+0.002
 wre+0.002
Neg logit contributions
 blush-0.003
ume-0.003
Girls-0.003
 perfume-0.003
bs-0.003
Token had
Token ID550
Feature activation-7.02e-04

Pos logit contributions
 blush+0.002
bs+0.002
Girls+0.002
ume+0.002
 perfume+0.002
Neg logit contributions
 puck-0.003
wreck-0.003
 camps-0.003
 skate-0.003
 hockey-0.003
Token found
Token ID1043
Feature activation-2.79e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 gear+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token in
Token ID287
Feature activation-2.52e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.004
 ship+0.004
 hockey+0.004
Neg logit contributions
 blush-0.006
Girls-0.006
ume-0.006
 perfume-0.005
bs-0.005
Token boy
Token ID2933
Feature activation-3.17e-03

Pos logit contributions
 blush+0.000
Girls+0.000
ume+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Token who
Token ID508
Feature activation-4.98e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 skate+0.007
 camps+0.007
 gear+0.007
Neg logit contributions
 blush-0.005
 perfume-0.005
bs-0.005
Girls-0.005
ume-0.005
Token really
Token ID1107
Feature activation-1.90e-03

Pos logit contributions
 puck+0.011
wreck+0.011
 ship+0.010
 camps+0.010
 skate+0.010
Neg logit contributions
 blush-0.008
 perfume-0.007
Girls-0.007
bs-0.007
ume-0.007
Token valued
Token ID17560
Feature activation-1.65e-03

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 hockey+0.004
Neg logit contributions
 blush-0.004
Girls-0.003
ume-0.003
 perfume-0.003
bs-0.003
Token his
Token ID465
Feature activation-2.73e-03

Pos logit contributions
wreck+0.001
 puck+0.001
 skate+0.001
 ship+0.001
 camps+0.001
Neg logit contributions
 blush-0.005
 perfume-0.005
Girls-0.005
 makeup-0.005
ume-0.005
Token attic
Token ID46113
Feature activation+1.28e-02

Pos logit contributions
wreck+0.005
 puck+0.005
 skate+0.005
 wre+0.005
 ship+0.005
Neg logit contributions
 blush-0.005
 perfume-0.005
Girls-0.005
ume-0.005
 makeup-0.005
Token.
Token ID13
Feature activation+1.55e-04

Pos logit contributions
 blush+0.022
 perfume+0.021
ume+0.020
bs+0.020
 makeup+0.019
Neg logit contributions
 puck-0.027
wreck-0.025
Ar-0.025
 skate-0.025
 wre-0.025
Token He
Token ID679
Feature activation-5.30e-03

Pos logit contributions
 blush+0.000
 Her+0.000
 She+0.000
Girls+0.000
 perfume+0.000
Neg logit contributions
wreck-0.000
 ship-0.000
 wre-0.000
 puck-0.000
 sailing-0.000
Token spent
Token ID3377
Feature activation+2.61e-04

Pos logit contributions
 puck+0.010
wreck+0.009
 skate+0.009
 ship+0.009
 gear+0.009
Neg logit contributions
 blush-0.011
Girls-0.011
ume-0.010
 perfume-0.010
bs-0.010
Token most
Token ID749
Feature activation+5.22e-03

Pos logit contributions
 blush+0.001
 perfume+0.001
Girls+0.001
bs+0.001
 makeup+0.001
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 ship-0.000
 motorcycle-0.000
Token of
Token ID286
Feature activation+1.68e-03

Pos logit contributions
 blush+0.010
Girls+0.009
 perfume+0.009
ume+0.009
bs+0.009
Neg logit contributions
 puck-0.010
wreck-0.010
 skate-0.010
 ship-0.010
 hockey-0.009
Token.
Token ID13
Feature activation-2.86e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
 skate-0.001
 ship-0.001
wreck-0.001
 hockey-0.001
Token Fisher
Token ID14388
Feature activation-1.84e-02

Pos logit contributions
 puck+0.005
wreck+0.005
 ship+0.005
 skate+0.005
 wre+0.005
Neg logit contributions
 blush-0.006
Girls-0.006
ume-0.005
 perfume-0.005
bs-0.005
Token.
Token ID13
Feature activation-3.47e-04

Pos logit contributions
 puck+0.031
 wre+0.030
wreck+0.029
 hockey+0.028
 skate+0.028
Neg logit contributions
 blush-0.036
ume-0.035
 perfume-0.035
Girls-0.034
bs-0.034
Token
Token ID198
Feature activation-6.32e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 ship+0.001
 skate+0.001
 wre+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token
Token ID198
Feature activation-1.74e-03

Pos logit contributions
 puck+0.012
wreck+0.011
 ship+0.011
 skate+0.011
 motorcycle+0.011
Neg logit contributions
 blush-0.013
Girls-0.013
ume-0.012
 perfume-0.012
bs-0.012
Token"
Token ID1
Feature activation+1.31e-02

Pos logit contributions
 puck+0.004
wreck+0.003
 ship+0.003
 skate+0.003
 hockey+0.003
Neg logit contributions
 blush-0.003
Girls-0.003
ume-0.003
 perfume-0.003
bs-0.003
TokenLook
Token ID8567
Feature activation+6.14e-03

Pos logit contributions
 blush+0.019
Girls+0.019
 perfume+0.016
ume+0.016
Her+0.016
Neg logit contributions
 ship-0.031
 puck-0.031
 wre-0.031
 skate-0.030
wreck-0.030
Token at
Token ID379
Feature activation-5.89e-04

Pos logit contributions
 blush+0.012
Girls+0.012
ume+0.012
 perfume+0.012
bs+0.011
Neg logit contributions
 puck-0.011
wreck-0.011
 skate-0.011
 ship-0.011
 hockey-0.010
Token that
Token ID326
Feature activation-5.34e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 sailed+0.001
Neg logit contributions
 perfume-0.001
 blush-0.001
Girls-0.001
ume-0.001
 makeup-0.001
Token tree
Token ID5509
Feature activation+2.22e-03

Pos logit contributions
wreck+0.011
 armour+0.011
 voy+0.011
 puck+0.011
 skate+0.010
Neg logit contributions
 perfume-0.006
 roses-0.006
 poppy-0.006
ume-0.006
 pastry-0.006
Token,
Token ID11
Feature activation-5.43e-03

Pos logit contributions
 blush+0.004
ume+0.004
Girls+0.004
 perfume+0.004
bs+0.003
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 gear-0.004
Token to
Token ID284
Feature activation+1.59e-03

Pos logit contributions
 puck+0.001
wreck+0.001
Ar+0.001
 skate+0.001
 ramp+0.001
Neg logit contributions
 blush-0.001
 perfume-0.001
bs-0.001
ume-0.001
 she-0.001
Token find
Token ID1064
Feature activation+2.61e-04

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 ship-0.003
 skate-0.003
 camps-0.003
Token that
Token ID326
Feature activation+1.25e-03

Pos logit contributions
 blush+0.001
 perfume+0.001
bs+0.001
ume+0.001
Girls+0.001
Neg logit contributions
wreck-0.000
 puck-0.000
 skate-0.000
 camps-0.000
 ship-0.000
Token there
Token ID612
Feature activation+9.11e-03

Pos logit contributions
 blush+0.003
 perfume+0.003
 makeup+0.003
Girls+0.003
bs+0.003
Neg logit contributions
wreck-0.001
 puck-0.001
 camps-0.001
 skate-0.001
Ar-0.001
Token was
Token ID373
Feature activation-3.20e-03

Pos logit contributions
 blush+0.013
 perfume+0.013
 bloom+0.012
 she+0.012
Girls+0.012
Neg logit contributions
 puck-0.020
 camps-0.020
wreck-0.019
Ar-0.019
 skate-0.019
Token nobody
Token ID8168
Feature activation+1.34e-02

Pos logit contributions
wreck+0.007
 skate+0.006
 puck+0.006
 ship+0.006
oc+0.006
Neg logit contributions
 perfume-0.005
 blush-0.005
Girls-0.005
 makeup-0.005
ume-0.004
Token else
Token ID2073
Feature activation+3.43e-03

Pos logit contributions
 blush+0.026
Girls+0.025
ume+0.024
 perfume+0.024
bs+0.023
Neg logit contributions
 puck-0.026
wreck-0.025
 skate-0.025
 ship-0.024
 hockey-0.024
Token outside
Token ID2354
Feature activation-2.71e-03

Pos logit contributions
 blush+0.006
Girls+0.006
ume+0.006
bs+0.006
 perfume+0.006
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.006
 camps-0.006
 ship-0.006
Token.
Token ID13
Feature activation+2.96e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 camps+0.005
Ar+0.005
Neg logit contributions
 blush-0.005
ume-0.005
Girls-0.005
 perfume-0.005
bs-0.005
Token He
Token ID679
Feature activation-6.38e-03

Pos logit contributions
 blush+0.006
Girls+0.006
 Her+0.006
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.005
wreck-0.004
 skate-0.004
 camps-0.004
 wre-0.004
Token decided
Token ID3066
Feature activation-1.07e-03

Pos logit contributions
wreck+0.013
 puck+0.013
 skate+0.013
 motorcycle+0.013
 hockey+0.013
Neg logit contributions
 blush-0.011
Girls-0.010
bs-0.010
 perfume-0.010
ume-0.010
Token,
Token ID11
Feature activation-3.94e-03

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 hockey+0.000
 ship+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
 perfume-0.000
bs-0.000
Token Daisy
Token ID40355
Feature activation+1.35e-02

Pos logit contributions
wreck+0.007
 puck+0.007
 skate+0.007
 wre+0.007
 ship+0.007
Neg logit contributions
 blush-0.008
Girls-0.008
 perfume-0.007
ume-0.007
bs-0.007
Token and
Token ID290
Feature activation-9.30e-03

Pos logit contributions
 blush+0.033
Girls+0.032
ume+0.031
 perfume+0.030
bs+0.029
Neg logit contributions
 puck-0.019
 ship-0.019
wreck-0.019
 skate-0.019
 hockey-0.018
Token Brad
Token ID8114
Feature activation+5.11e-04

Pos logit contributions
 puck+0.017
wreck+0.017
 skate+0.016
 ship+0.016
 hockey+0.015
Neg logit contributions
 blush-0.019
Girls-0.019
ume-0.018
 perfume-0.018
bs-0.017
Token.
Token ID13
Feature activation+1.80e-04

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 hockey-0.001
Token Daisy
Token ID40355
Feature activation+1.52e-02

Pos logit contributions
 blush+0.000
ume+0.000
Girls+0.000
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 hockey-0.000
 gear-0.000
Token was
Token ID373
Feature activation+6.07e-03

Pos logit contributions
 blush+0.037
ume+0.036
Girls+0.035
 perfume+0.033
 mascara+0.033
Neg logit contributions
 ship-0.022
 skate-0.021
 puck-0.021
 sailed-0.021
wreck-0.020
Token a
Token ID257
Feature activation+2.71e-03

Pos logit contributions
 blush+0.013
Girls+0.013
ume+0.013
 perfume+0.012
bs+0.012
Neg logit contributions
 puck-0.010
wreck-0.010
 skate-0.010
 ship-0.009
 hockey-0.009
Token boss
Token ID6478
Feature activation-1.14e-03

Pos logit contributions
 blush+0.005
Girls+0.005
 perfume+0.005
ume+0.005
bs+0.004
Neg logit contributions
wreck-0.005
 puck-0.005
 skate-0.005
 wre-0.005
 ship-0.005
Tokeny
Token ID88
Feature activation-1.55e-03

Pos logit contributions
 puck+0.003
wreck+0.002
 skate+0.002
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token hen
Token ID30963
Feature activation+1.19e-02

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 hockey+0.003
Neg logit contributions
 blush-0.003
Girls-0.003
ume-0.003
 perfume-0.003
bs-0.003
TokenTim
Token ID14967
Feature activation-6.43e-03

Pos logit contributions
 ship+0.004
 sailing+0.004
 puck+0.004
 shark+0.004
wreck+0.004
Neg logit contributions
Her-0.003
Girls-0.003
 blush-0.003
She-0.003
bs-0.003
Tokenmy
Token ID1820
Feature activation-1.35e-03

Pos logit contributions
 puck+0.014
wreck+0.014
 skate+0.014
 ship+0.013
 hockey+0.013
Neg logit contributions
 blush-0.011
Girls-0.010
ume-0.010
 perfume-0.010
bs-0.009
Token went
Token ID1816
Feature activation+1.17e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 hockey+0.003
 wre+0.003
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token to
Token ID284
Feature activation-1.54e-03

Pos logit contributions
 blush+0.002
Girls+0.002
 perfume+0.002
ume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 wre-0.002
Token the
Token ID262
Feature activation+6.72e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 camps+0.003
 rink+0.003
 ship+0.003
Neg logit contributions
 blush-0.003
 perfume-0.002
 her-0.002
Girls-0.002
Her-0.002
Token gift
Token ID6979
Feature activation+1.24e-02

Pos logit contributions
Girls+0.015
 blush+0.014
 perfume+0.014
Her+0.013
ume+0.013
Neg logit contributions
 puck-0.011
wreck-0.010
 skate-0.010
 wre-0.009
 hockey-0.009
Token shop
Token ID6128
Feature activation+1.30e-06

Pos logit contributions
 blush+0.020
 perfume+0.019
ume+0.019
Girls+0.018
Her+0.018
Neg logit contributions
 puck-0.025
 wre-0.025
 skate-0.024
wreck-0.023
 sailed-0.023
Token and
Token ID290
Feature activation+5.58e-03

Feature not active on prev token;
no predictions were affected.
Token bought
Token ID5839
Feature activation-4.73e-04

Pos logit contributions
 blush+0.009
Girls+0.009
 perfume+0.009
ume+0.008
bs+0.008
Neg logit contributions
 puck-0.012
wreck-0.012
 skate-0.012
 camps-0.011
 ship-0.011
Token a
Token ID257
Feature activation+3.55e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 camps+0.001
Neg logit contributions
 blush-0.001
 perfume-0.001
Girls-0.001
ume-0.001
bs-0.001
Token toy
Token ID13373
Feature activation-5.88e-03

Pos logit contributions
 blush+0.007
 perfume+0.007
Girls+0.006
ume+0.006
bs+0.006
Neg logit contributions
wreck-0.007
 puck-0.007
 skate-0.006
 wre-0.006
 ship-0.006
Tokenily
Token ID813
Feature activation+6.27e-03

Pos logit contributions
 blush+0.005
Girls+0.005
 perfume+0.004
ume+0.004
bs+0.004
Neg logit contributions
 puck-0.013
 skate-0.013
wreck-0.013
 his-0.013
 hockey-0.013
Token dropped
Token ID5710
Feature activation+1.25e-03

Pos logit contributions
 blush+0.013
Girls+0.013
ume+0.013
 perfume+0.012
bs+0.012
Neg logit contributions
 puck-0.011
 skate-0.011
wreck-0.011
 ship-0.010
 hockey-0.010
Token the
Token ID262
Feature activation-2.13e-03

Pos logit contributions
Girls+0.002
ume+0.002
 blush+0.002
bs+0.002
 perfume+0.002
Neg logit contributions
 his-0.002
 puck-0.002
 hockey-0.002
 skate-0.002
 gear-0.002
Token flag
Token ID6056
Feature activation+6.12e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 ship+0.003
 skate+0.003
 motorcycle+0.003
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.005
bs-0.004
Token and
Token ID290
Feature activation+3.10e-03

Pos logit contributions
 blush+0.013
ume+0.012
Girls+0.012
 perfume+0.012
bs+0.012
Neg logit contributions
 puck-0.011
wreck-0.011
 skate-0.010
 ship-0.010
 hockey-0.010
Token fell
Token ID3214
Feature activation-2.92e-04

Pos logit contributions
Girls+0.006
ume+0.006
 blush+0.006
 perfume+0.006
bs+0.005
Neg logit contributions
 puck-0.006
 skate-0.006
 ship-0.006
wreck-0.006
 his-0.005
Token off
Token ID572
Feature activation-8.21e-06

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.000
 hockey+0.000
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token the
Token ID262
Feature activation-3.71e-04

Feature not active on prev token;
no predictions were affected.
Token swing
Token ID9628
Feature activation-6.25e-04

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token.
Token ID13
Feature activation+3.51e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 gear+0.001
Neg logit contributions
 blush-0.001
ume-0.001
Girls-0.001
 perfume-0.001
bs-0.001
Token She
Token ID1375
Feature activation+1.85e-03

Pos logit contributions
Girls+0.005
ume+0.005
 blush+0.005
 perfume+0.004
bs+0.004
Neg logit contributions
 his-0.008
 He-0.008
 hockey-0.008
 puck-0.008
 skate-0.007
Token.
Token ID13
Feature activation-2.47e-03

Pos logit contributions
 blush+0.013
Girls+0.013
ume+0.013
 perfume+0.013
bs+0.012
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.009
 ship-0.009
 hockey-0.009
Token They
Token ID1119
Feature activation-7.95e-04

Pos logit contributions
 puck+0.004
 skate+0.004
 hockey+0.004
 his+0.004
wreck+0.004
Neg logit contributions
 blush-0.005
ume-0.005
Girls-0.005
 perfume-0.005
bs-0.005
Token tell
Token ID1560
Feature activation+2.19e-03

Pos logit contributions
 puck+0.002
wreck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.002
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token stories
Token ID3923
Feature activation+4.61e-03

Pos logit contributions
 blush+0.004
ume+0.004
Girls+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.004
 his-0.004
 skate-0.004
 ship-0.004
 gear-0.004
Token and
Token ID290
Feature activation+5.43e-03

Pos logit contributions
 blush+0.010
Girls+0.010
ume+0.010
 perfume+0.009
bs+0.009
Neg logit contributions
 puck-0.007
wreck-0.007
 skate-0.007
 ship-0.007
 gear-0.007
Token laugh
Token ID6487
Feature activation+5.47e-03

Pos logit contributions
 blush+0.011
Girls+0.011
ume+0.011
bs+0.010
 perfume+0.010
Neg logit contributions
 puck-0.010
 skate-0.010
 ship-0.010
wreck-0.010
 gear-0.009
Token.
Token ID13
Feature activation-1.63e-03

Pos logit contributions
 blush+0.012
Girls+0.012
ume+0.012
 perfume+0.011
bs+0.011
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.009
 ship-0.008
 hockey-0.008
Token<|endoftext|>
Token ID50256
Feature activation-7.95e-03

Pos logit contributions
 puck+0.002
 skate+0.002
 hockey+0.002
 his+0.002
wreck+0.002
Neg logit contributions
 blush-0.004
ume-0.004
Girls-0.004
 perfume-0.004
bs-0.004
TokenL
Token ID43
Feature activation+7.48e-03

Pos logit contributions
 puck+0.017
wreck+0.017
 skate+0.016
 ship+0.016
 motorcycle+0.016
Neg logit contributions
 blush-0.013
Girls-0.013
ume-0.013
 perfume-0.013
bs-0.012
Tokenily
Token ID813
Feature activation+8.78e-03

Pos logit contributions
 blush+0.010
Girls+0.009
 perfume+0.009
ume+0.009
bs+0.008
Neg logit contributions
 puck-0.019
 his-0.019
 ship-0.019
 skate-0.018
wreck-0.018
Token liked
Token ID8288
Feature activation-1.03e-02

Pos logit contributions
 blush+0.020
Girls+0.020
ume+0.020
 perfume+0.019
bs+0.019
Neg logit contributions
 puck-0.013
 skate-0.013
 ship-0.013
wreck-0.013
 gear-0.012
Token was
Token ID373
Feature activation+4.13e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 motorcycle+0.002
 wre+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
bs-0.002
 perfume-0.002
Token so
Token ID523
Feature activation+4.32e-03

Pos logit contributions
 blush+0.008
Girls+0.008
ume+0.008
 perfume+0.008
bs+0.008
Neg logit contributions
 puck-0.008
wreck-0.007
 skate-0.007
 ship-0.007
 hockey-0.007
Token happy
Token ID3772
Feature activation-2.25e-03

Pos logit contributions
 blush+0.007
Girls+0.007
ume+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.009
 ship-0.009
 gear-0.009
Token he
Token ID339
Feature activation-7.38e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.004
 camps+0.004
Ar+0.004
Neg logit contributions
 blush-0.004
 perfume-0.004
Girls-0.003
ume-0.003
bs-0.003
Token started
Token ID2067
Feature activation-2.93e-03

Pos logit contributions
 puck+0.016
wreck+0.015
 camps+0.015
 skate+0.015
 wre+0.015
Neg logit contributions
 blush-0.012
Girls-0.011
bs-0.011
ume-0.011
 perfume-0.011
Token to
Token ID284
Feature activation+1.67e-03

Pos logit contributions
 puck+0.006
wreck+0.006
 ship+0.005
 skate+0.005
 motorcycle+0.005
Neg logit contributions
 blush-0.006
ume-0.005
 perfume-0.005
Girls-0.005
bs-0.005
Token g
Token ID308
Feature activation+1.67e-03

Pos logit contributions
 blush+0.004
ume+0.003
 perfume+0.003
Girls+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 ship-0.003
 camps-0.003
 motorcycle-0.003
Tokeniggle
Token ID24082
Feature activation-2.76e-03

Pos logit contributions
 blush+0.003
ume+0.002
Girls+0.002
bs+0.002
 perfume+0.002
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 gear-0.004
 ship-0.004
Token and
Token ID290
Feature activation-5.74e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 ship+0.005
 motorcycle+0.005
Neg logit contributions
 blush-0.005
 perfume-0.005
ume-0.005
Girls-0.005
bs-0.005
Token splash
Token ID22870
Feature activation-3.71e-04

Pos logit contributions
wreck+0.010
 puck+0.010
 camps+0.009
 skate+0.009
 motorcycle+0.009
Neg logit contributions
 blush-0.012
 perfume-0.011
Girls-0.011
bs-0.011
ume-0.011
Token his
Token ID465
Feature activation-2.39e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 motorcycle+0.001
Neg logit contributions
 blush-0.001
 perfume-0.001
Girls-0.001
bs-0.001
ume-0.001
Token
Token ID198
Feature activation-4.32e-03

Pos logit contributions
ume+0.007
 blush+0.007
Girls+0.007
 perfume+0.007
bs+0.007
Neg logit contributions
 his-0.006
 hockey-0.005
 puck-0.005
 skate-0.005
 he-0.005
Token
Token ID198
Feature activation-1.21e-03

Pos logit contributions
 puck+0.006
 skate+0.006
 hockey+0.006
 his+0.006
wreck+0.006
Neg logit contributions
 blush-0.011
ume-0.010
Girls-0.010
 perfume-0.010
bs-0.009
TokenAnna
Token ID31160
Feature activation+1.27e-02

Pos logit contributions
 puck+0.003
 skate+0.003
 hockey+0.003
wreck+0.003
 his+0.002
Neg logit contributions
 blush-0.002
 perfume-0.002
ume-0.002
Girls-0.002
bs-0.002
Token stops
Token ID9911
Feature activation-1.06e-03

Pos logit contributions
 blush+0.024
Girls+0.023
ume+0.023
 perfume+0.022
bs+0.022
Neg logit contributions
 puck-0.025
wreck-0.024
 skate-0.024
 ship-0.024
 gear-0.023
Token and
Token ID290
Feature activation+1.01e-02

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token looks
Token ID3073
Feature activation+1.01e-03

Pos logit contributions
Girls+0.019
ume+0.018
 blush+0.018
 perfume+0.017
bs+0.016
Neg logit contributions
 puck-0.020
 skate-0.020
 his-0.019
 ship-0.019
wreck-0.019
Token at
Token ID379
Feature activation-3.16e-03

Pos logit contributions
Girls+0.002
ume+0.002
 blush+0.002
 perfume+0.002
 mascara+0.002
Neg logit contributions
 his-0.002
 puck-0.002
 ship-0.002
 gear-0.001
 hockey-0.001
Token the
Token ID262
Feature activation+4.55e-03

Pos logit contributions
 puck+0.005
 skate+0.005
 his+0.005
 hockey+0.005
wreck+0.005
Neg logit contributions
 blush-0.007
ume-0.007
Girls-0.007
 perfume-0.006
bs-0.006
Token mail
Token ID6920
Feature activation+9.26e-04

Pos logit contributions
Girls+0.008
 blush+0.008
ume+0.008
bs+0.007
 perfume+0.007
Neg logit contributions
 puck-0.009
wreck-0.009
 ship-0.009
 motorcycle-0.009
 skate-0.009
Tokenman
Token ID805
Feature activation-6.80e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 hockey-0.002
Token.
Token ID13
Feature activation-2.55e-03

Pos logit contributions
 puck+0.012
wreck+0.011
 skate+0.011
 ship+0.011
 gear+0.011
Neg logit contributions
 blush-0.015
ume-0.014
Girls-0.014
 perfume-0.013
bs-0.013
Token are
Token ID389
Feature activation-2.48e-03

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.006
 skate-0.006
wreck-0.006
 ship-0.006
 gear-0.006
Token still
Token ID991
Feature activation+6.46e-04

Pos logit contributions
 puck+0.005
 ship+0.004
 his+0.004
 sailing+0.004
 skate+0.004
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 perfume-0.004
bs-0.004
Token hugging
Token ID46292
Feature activation+5.09e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
bs+0.001
 perfume+0.001
Neg logit contributions
 puck-0.001
 ship-0.001
wreck-0.001
 hockey-0.001
 skate-0.001
Token and
Token ID290
Feature activation+1.81e-03

Pos logit contributions
 blush+0.010
Girls+0.010
 perfume+0.009
bs+0.009
ume+0.009
Neg logit contributions
wreck-0.010
 puck-0.010
 skate-0.009
 ship-0.009
 camps-0.009
Token crying
Token ID13774
Feature activation+4.31e-04

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.004
 skate-0.004
wreck-0.003
 ship-0.003
 hockey-0.003
Token.
Token ID13
Feature activation-2.83e-04

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
wreck-0.001
 skate-0.001
 ship-0.001
 motorcycle-0.001
Token
Token ID198
Feature activation-3.04e-03

Pos logit contributions
wreck+0.001
 puck+0.001
 ship+0.001
 skate+0.001
 motorcycle+0.001
Neg logit contributions
Girls-0.001
 blush-0.001
ume-0.001
bs-0.000
 perfume-0.000
Token
Token ID198
Feature activation-1.90e-03

Pos logit contributions
 puck+0.006
wreck+0.006
 ship+0.006
 skate+0.006
 motorcycle+0.006
Neg logit contributions
Girls-0.005
 blush-0.005
ume-0.005
bs-0.005
 perfume-0.005
TokenThey
Token ID2990
Feature activation+9.13e-04

Pos logit contributions
 puck+0.004
wreck+0.004
 ship+0.004
 skate+0.004
 motorcycle+0.004
Neg logit contributions
Girls-0.003
 blush-0.003
ume-0.003
bs-0.003
Her-0.003
Token are
Token ID389
Feature activation-4.02e-04

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 hockey-0.002
Token not
Token ID407
Feature activation-5.97e-03

Pos logit contributions
 puck+0.001
 his+0.001
 sailing+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Tokenly
Token ID306
Feature activation-1.37e-03

Pos logit contributions
ume+0.003
Girls+0.003
 blush+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 his-0.002
wreck-0.002
 ship-0.002
 puck-0.002
 skate-0.002
Token showed
Token ID3751
Feature activation+2.60e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.003
Girls-0.003
ume-0.003
 perfume-0.002
bs-0.002
Token him
Token ID683
Feature activation-7.76e-03

Pos logit contributions
 blush+0.006
Girls+0.006
ume+0.006
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 hockey-0.003
Token to
Token ID284
Feature activation-6.55e-03

Pos logit contributions
 puck+0.012
wreck+0.012
 skate+0.012
 ship+0.012
 hockey+0.011
Neg logit contributions
 blush-0.018
Girls-0.017
ume-0.017
 perfume-0.016
bs-0.016
Token the
Token ID262
Feature activation+4.24e-03

Pos logit contributions
 puck+0.012
wreck+0.012
 ship+0.011
 skate+0.011
 camps+0.011
Neg logit contributions
 blush-0.014
Girls-0.013
 perfume-0.013
ume-0.012
bs-0.012
Token neighbor
Token ID4780
Feature activation-7.88e-03

Pos logit contributions
 blush+0.007
Girls+0.007
ume+0.007
 perfume+0.007
bs+0.006
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.009
 ship-0.009
 hockey-0.009
Token.
Token ID13
Feature activation+2.44e-04

Pos logit contributions
 puck+0.014
wreck+0.013
 skate+0.013
 ship+0.013
 hockey+0.012
Neg logit contributions
 blush-0.017
Girls-0.016
ume-0.016
 perfume-0.015
bs-0.015
Token
Token ID220
Feature activation-9.24e-04

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.000
bs+0.000
Neg logit contributions
 puck-0.000
wreck-0.000
 skate-0.000
 hockey-0.000
 his-0.000
Token
Token ID198
Feature activation-1.64e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token
Token ID198
Feature activation+1.51e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.002
 hockey+0.002
 ship+0.002
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
 perfume-0.004
bs-0.003
TokenThe
Token ID464
Feature activation+5.57e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 hockey-0.003
 ship-0.002
Token sell
Token ID3677
Feature activation-1.43e-03

Pos logit contributions
 puck+0.009
wreck+0.009
 camps+0.008
 skate+0.008
 ship+0.008
Neg logit contributions
 blush-0.010
ume-0.009
Girls-0.009
 perfume-0.009
bs-0.009
Token his
Token ID465
Feature activation-1.88e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 sailing+0.002
Neg logit contributions
 blush-0.003
 perfume-0.003
Girls-0.003
ume-0.003
bs-0.003
Token meat
Token ID6174
Feature activation-7.79e-03

Pos logit contributions
wreck+0.003
 puck+0.003
 wre+0.003
 skate+0.003
 sailed+0.003
Neg logit contributions
 perfume-0.004
 blush-0.004
ume-0.003
Girls-0.003
bs-0.003
Token,
Token ID11
Feature activation-3.06e-03

Pos logit contributions
 puck+0.015
wreck+0.014
 skate+0.014
 wre+0.014
 sailed+0.014
Neg logit contributions
 blush-0.014
 perfume-0.014
ume-0.014
bs-0.013
Girls-0.012
Token but
Token ID475
Feature activation-1.05e-03

Pos logit contributions
wreck+0.005
 puck+0.005
 skate+0.005
 ship+0.005
 camps+0.005
Neg logit contributions
 blush-0.006
Girls-0.006
 perfume-0.006
ume-0.006
bs-0.006
Token he
Token ID339
Feature activation-6.53e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 camps+0.001
Neg logit contributions
 blush-0.003
Girls-0.003
 perfume-0.003
ume-0.003
bs-0.003
Token understood
Token ID7247
Feature activation+1.46e-03

Pos logit contributions
 puck+0.013
wreck+0.013
 skate+0.013
 ship+0.013
 hockey+0.012
Neg logit contributions
 blush-0.012
Girls-0.011
ume-0.011
 perfume-0.011
bs-0.010
Token that
Token ID326
Feature activation+2.72e-03

Pos logit contributions
 blush+0.003
Girls+0.003
 perfume+0.003
ume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 camps-0.002
Token Lily
Token ID20037
Feature activation+6.47e-03

Pos logit contributions
 blush+0.007
 perfume+0.007
Girls+0.007
ume+0.007
bs+0.007
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 camps-0.003
Token didn
Token ID1422
Feature activation-4.04e-03

Pos logit contributions
 blush+0.014
Girls+0.014
ume+0.014
 perfume+0.013
bs+0.013
Neg logit contributions
 puck-0.010
wreck-0.010
 ship-0.010
 skate-0.010
 gear-0.010
Token't
Token ID470
Feature activation+1.96e-04

Pos logit contributions
 puck+0.010
 ship+0.010
wreck+0.009
 gear+0.009
 camps+0.009
Neg logit contributions
 blush-0.006
Girls-0.005
ume-0.005
 perfume-0.005
Her-0.005
Token tire
Token ID15867
Feature activation-4.55e-03

Pos logit contributions
 blush+0.006
Girls+0.006
ume+0.006
 perfume+0.006
bs+0.005
Neg logit contributions
 puck-0.006
wreck-0.006
 skate-0.006
 ship-0.006
 hockey-0.006
Token while
Token ID981
Feature activation+3.87e-04

Pos logit contributions
 puck+0.009
 camps+0.008
 wre+0.008
wreck+0.008
Ar+0.008
Neg logit contributions
 blush-0.008
ume-0.008
 perfume-0.007
Girls-0.007
bs-0.007
Token walking
Token ID6155
Feature activation+2.03e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.001
 skate-0.001
wreck-0.001
 wre-0.001
 gear-0.001
Token.
Token ID13
Feature activation+1.89e-03

Pos logit contributions
 blush+0.004
Girls+0.003
bs+0.003
 perfume+0.003
ume+0.003
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.004
 camps-0.004
Token
Token ID220
Feature activation+2.55e-03

Pos logit contributions
Girls+0.004
 blush+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.003
 ship-0.003
 skate-0.003
wreck-0.003
 camps-0.003
Token
Token ID198
Feature activation-4.65e-03

Pos logit contributions
Girls+0.005
 blush+0.005
ume+0.005
bs+0.004
 perfume+0.004
Neg logit contributions
 puck-0.005
wreck-0.005
 ship-0.005
 skate-0.005
 motorcycle-0.005
Token
Token ID198
Feature activation+7.20e-05

Pos logit contributions
 puck+0.010
 ship+0.009
 skate+0.009
wreck+0.009
 camps+0.009
Neg logit contributions
Girls-0.008
ume-0.008
 blush-0.008
Her-0.008
bs-0.007
TokenJohn
Token ID7554
Feature activation-7.57e-03

Pos logit contributions
Girls+0.000
 blush+0.000
ume+0.000
bs+0.000
 perfume+0.000
Neg logit contributions
 puck-0.000
 skate-0.000
 ship-0.000
wreck-0.000
 hockey-0.000
Token ran
Token ID4966
Feature activation-6.36e-04

Pos logit contributions
 puck+0.016
wreck+0.016
 skate+0.015
 hockey+0.015
 camps+0.015
Neg logit contributions
 blush-0.013
Girls-0.012
ume-0.012
bs-0.012
 perfume-0.011
Token over
Token ID625
Feature activation+7.67e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 ship+0.001
 camps+0.001
 skate+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
 perfume-0.001
bs-0.001
ume-0.001
Token and
Token ID290
Feature activation+8.03e-03

Pos logit contributions
 blush+0.011
Girls+0.011
 perfume+0.010
bs+0.010
 makeup+0.010
Neg logit contributions
wreck-0.018
 puck-0.018
 ship-0.017
 skate-0.017
 camps-0.016
Token both
Token ID1111
Feature activation+5.85e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 hockey+0.003
Neg logit contributions
 blush-0.003
Girls-0.003
ume-0.002
 perfume-0.002
bs-0.002
Token like
Token ID588
Feature activation+5.00e-03

Pos logit contributions
 blush+0.012
Girls+0.012
ume+0.011
 perfume+0.011
bs+0.011
Neg logit contributions
 puck-0.011
wreck-0.011
 skate-0.010
 ship-0.010
 sailing-0.010
Token,
Token ID11
Feature activation-2.39e-04

Pos logit contributions
 blush+0.010
Girls+0.009
ume+0.009
 perfume+0.009
bs+0.009
Neg logit contributions
 puck-0.009
wreck-0.009
 skate-0.009
 ship-0.009
 hockey-0.009
Token but
Token ID475
Feature activation-2.33e-03

Pos logit contributions
 puck+0.000
 ship+0.000
wreck+0.000
 skate+0.000
 hockey+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
bs-0.000
 perfume-0.000
Token in
Token ID287
Feature activation-1.15e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 ship+0.004
 camps+0.004
Neg logit contributions
 blush-0.004
Girls-0.004
 perfume-0.004
ume-0.004
bs-0.004
Token a
Token ID257
Feature activation-6.37e-03

Pos logit contributions
 puck+0.002
wreck+0.002
 skate+0.002
 ship+0.002
 hockey+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
Token different
Token ID1180
Feature activation+1.91e-03

Pos logit contributions
 puck+0.012
wreck+0.012
 skate+0.012
 ship+0.012
 hockey+0.011
Neg logit contributions
 blush-0.012
Girls-0.012
ume-0.012
 perfume-0.011
bs-0.011
Token way
Token ID835
Feature activation-5.18e-04

Pos logit contributions
 blush+0.004
Girls+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Token,"
Token ID553
Feature activation+3.99e-03

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 hockey+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
ume-0.001
 perfume-0.001
bs-0.001
Token Dad
Token ID17415
Feature activation-1.06e-02

Pos logit contributions
 blush+0.008
ume+0.008
Girls+0.008
 perfume+0.007
bs+0.007
Neg logit contributions
 puck-0.007
 skate-0.007
 ship-0.007
 his-0.007
 hockey-0.007
Token says
Token ID1139
Feature activation+7.01e-03

Pos logit contributions
 puck+0.027
wreck+0.027
 skate+0.026
 ship+0.026
 hockey+0.026
Neg logit contributions
 blush-0.014
Girls-0.013
ume-0.013
 perfume-0.012
bs-0.012
Token brilliant
Token ID10457
Feature activation+1.22e-02

Pos logit contributions
 blush+0.019
Girls+0.018
 perfume+0.018
ume+0.018
bs+0.017
Neg logit contributions
 puck-0.019
wreck-0.019
 skate-0.018
 ship-0.018
 hockey-0.017
Token idea
Token ID2126
Feature activation-3.04e-03

Pos logit contributions
 blush+0.023
Girls+0.022
ume+0.022
 perfume+0.021
bs+0.021
Neg logit contributions
 puck-0.024
wreck-0.023
 skate-0.023
 ship-0.022
 hockey-0.022
Token.
Token ID13
Feature activation-1.54e-03

Pos logit contributions
 puck+0.005
wreck+0.005
 skate+0.005
 ship+0.005
 hockey+0.004
Neg logit contributions
 blush-0.007
Girls-0.007
ume-0.007
 perfume-0.006
bs-0.006
Token She
Token ID1375
Feature activation+3.55e-03

Pos logit contributions
 puck+0.004
 hockey+0.004
 his+0.004
wreck+0.004
 skate+0.004
Neg logit contributions
 blush-0.002
ume-0.002
Girls-0.002
 perfume-0.002
bs-0.002
Token told
Token ID1297
Feature activation+9.48e-03

Pos logit contributions
 blush+0.007
Girls+0.006
ume+0.006
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.007
wreck-0.007
 ship-0.007
 skate-0.007
 gear-0.007
Token Jack
Token ID3619
Feature activation-5.30e-03

Pos logit contributions
 blush+0.023
Girls+0.022
 perfume+0.022
ume+0.021
bs+0.021
Neg logit contributions
 puck-0.014
wreck-0.014
 skate-0.013
 ship-0.013
 sailed-0.012
Token to
Token ID284
Feature activation+1.71e-03

Pos logit contributions
 his+0.008
 puck+0.008
 ship+0.008
 skate+0.008
wreck+0.008
Neg logit contributions
 blush-0.012
Girls-0.012
ume-0.011
 perfume-0.011
 mascara-0.011
Token stay
Token ID2652
Feature activation+6.74e-03

Pos logit contributions
 blush+0.004
ume+0.003
Girls+0.003
 perfume+0.003
bs+0.003
Neg logit contributions
 puck-0.003
wreck-0.003
 camps-0.003
 skate-0.003
 ship-0.003
Token with
Token ID351
Feature activation+3.28e-03

Pos logit contributions
 blush+0.013
Girls+0.013
 perfume+0.012
ume+0.012
bs+0.012
Neg logit contributions
 puck-0.013
wreck-0.013
 skate-0.012
 ship-0.012
 motorcycle-0.012
Token her
Token ID607
Feature activation+8.25e-03

Pos logit contributions
 blush+0.009
 perfume+0.008
Girls+0.008
ume+0.008
 makeup+0.008
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 ship-0.003
 camps-0.003
Token grandma
Token ID49890
Feature activation+8.06e-03

Pos logit contributions
 blush+0.016
ume+0.015
Girls+0.015
 perfume+0.015
bs+0.014
Neg logit contributions
 puck-0.016
wreck-0.016
 skate-0.015
 ship-0.015
 sailed-0.015
Token Maybe
Token ID6674
Feature activation-4.79e-03

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 ship+0.004
 motorcycle+0.004
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
 perfume-0.004
bs-0.004
Token they
Token ID484
Feature activation-7.71e-04

Pos logit contributions
 puck+0.010
wreck+0.010
 skate+0.010
 motorcycle+0.009
 ship+0.009
Neg logit contributions
 blush-0.009
 perfume-0.008
Girls-0.008
ume-0.008
bs-0.008
Token could
Token ID714
Feature activation+2.08e-03

Pos logit contributions
wreck+0.001
 ship+0.001
 puck+0.001
 skate+0.001
 sailed+0.001
Neg logit contributions
Girls-0.002
 blush-0.002
ume-0.002
 perfume-0.002
 mascara-0.002
Token grow
Token ID1663
Feature activation+4.06e-03

Pos logit contributions
Girls+0.005
 blush+0.004
ume+0.004
 perfume+0.004
bs+0.004
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Token more
Token ID517
Feature activation-2.69e-03

Pos logit contributions
 blush+0.009
Girls+0.009
ume+0.009
 perfume+0.008
bs+0.008
Neg logit contributions
 puck-0.006
wreck-0.006
 ship-0.006
 skate-0.006
 hockey-0.006
Token av
Token ID1196
Feature activation-2.00e-02

Pos logit contributions
 ship+0.005
wreck+0.005
 puck+0.005
 his+0.005
 sailing+0.005
Neg logit contributions
 blush-0.005
Girls-0.005
ume-0.005
 mascara-0.004
 perfume-0.004
Tokenoc
Token ID420
Feature activation-1.71e-02

Pos logit contributions
 puck+0.012
 skate+0.010
wreck+0.010
 ship+0.009
 hockey+0.008
Neg logit contributions
 blush-0.065
Girls-0.063
ume-0.063
bs-0.063
 perfume-0.062
Tokenados
Token ID22484
Feature activation-9.05e-03

Pos logit contributions
 puck+0.049
 skate+0.048
wreck+0.048
 ship+0.047
 gear+0.047
Neg logit contributions
 blush-0.016
Girls-0.015
ume-0.015
 perfume-0.015
bs-0.013
Token and
Token ID290
Feature activation+1.03e-03

Pos logit contributions
 puck+0.015
wreck+0.015
 skate+0.014
 ship+0.014
 hockey+0.014
Neg logit contributions
 blush-0.020
Girls-0.019
ume-0.019
 perfume-0.018
bs-0.018
Token share
Token ID2648
Feature activation+1.23e-03

Pos logit contributions
Girls+0.002
 blush+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 ship-0.002
 skate-0.002
 hockey-0.002
Token them
Token ID606
Feature activation-1.43e-03

Pos logit contributions
 blush+0.003
Girls+0.003
ume+0.003
bs+0.003
 perfume+0.003
Neg logit contributions
wreck-0.002
 puck-0.002
 his-0.002
 ship-0.002
 hockey-0.002
Token "
Token ID366
Feature activation+4.49e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.003
 gear+0.003
Neg logit contributions
 blush-0.002
Girls-0.002
ume-0.002
 perfume-0.002
bs-0.002
TokenHello
Token ID15496
Feature activation-1.07e-03

Pos logit contributions
 blush+0.007
Girls+0.007
ume+0.007
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.010
 skate-0.010
 ship-0.010
wreck-0.010
 gear-0.010
Token,
Token ID11
Feature activation-4.59e-03

Pos logit contributions
 puck+0.002
 skate+0.002
wreck+0.002
 sailed+0.002
 wre+0.002
Neg logit contributions
ume-0.002
Girls-0.002
 perfume-0.002
 blush-0.002
 roses-0.001
Token Mr
Token ID1770
Feature activation+2.12e-03

Pos logit contributions
wreck+0.010
 puck+0.009
 skate+0.009
 sailed+0.009
Ar+0.009
Neg logit contributions
Girls-0.007
ume-0.007
 perfume-0.007
 blush-0.007
 roses-0.006
Token.
Token ID13
Feature activation-7.97e-03

Pos logit contributions
Girls+0.004
ume+0.003
 perfume+0.003
 blush+0.003
bs+0.003
Neg logit contributions
 puck-0.004
wreck-0.004
 skate-0.004
 wre-0.004
 sailing-0.004
Token Fisher
Token ID14388
Feature activation-2.06e-02

Pos logit contributions
 wre+0.010
 skate+0.009
 gear+0.009
wreck+0.008
 hon+0.008
Neg logit contributions
ume-0.017
Girls-0.017
 Belle-0.016
 Sasha-0.015
 Sophia-0.015
Tokenman
Token ID805
Feature activation-9.04e-03

Pos logit contributions
 puck+0.030
wreck+0.028
 skate+0.028
 camps+0.028
 wre+0.028
Neg logit contributions
ume-0.044
Girls-0.043
 perfume-0.043
 blush-0.042
bs-0.040
Token!
Token ID0
Feature activation-7.96e-03

Pos logit contributions
 puck+0.017
wreck+0.016
 skate+0.016
 ship+0.015
 gear+0.015
Neg logit contributions
 blush-0.018
Girls-0.018
ume-0.017
 perfume-0.017
bs-0.016
Token Would
Token ID10928
Feature activation+2.57e-03

Pos logit contributions
 puck+0.019
wreck+0.019
 ship+0.019
 gear+0.018
 camps+0.018
Neg logit contributions
Girls-0.010
ume-0.010
 blush-0.010
bs-0.009
 perfume-0.009
Token you
Token ID345
Feature activation+2.69e-03

Pos logit contributions
 blush+0.003
Girls+0.003
 perfume+0.003
Her+0.003
ume+0.003
Neg logit contributions
 puck-0.007
wreck-0.006
 camps-0.006
 skate-0.006
 ship-0.006
Token like
Token ID588
Feature activation+4.50e-03

Pos logit contributions
 blush+0.005
Girls+0.005
ume+0.005
 perfume+0.005
bs+0.005
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.005
 ship-0.005
 hockey-0.005
Token of
Token ID286
Feature activation-1.26e-03

Pos logit contributions
 blush+0.011
Girls+0.011
ume+0.011
 perfume+0.010
bs+0.010
Neg logit contributions
 puck-0.009
wreck-0.009
 ship-0.009
 skate-0.009
 sailing-0.009
Token shells
Token ID19679
Feature activation-4.12e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.003
 ship+0.002
 motorcycle+0.002
Neg logit contributions
 blush-0.002
Girls-0.002
 perfume-0.002
ume-0.002
bs-0.002
Token,
Token ID11
Feature activation-3.76e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 ship+0.006
 skate+0.006
 sailing+0.006
Neg logit contributions
 blush-0.009
Girls-0.009
ume-0.009
 perfume-0.008
bs-0.008
Token rocks
Token ID12586
Feature activation-1.14e-02

Pos logit contributions
 puck+0.007
wreck+0.007
 skate+0.007
 motorcycle+0.007
 ship+0.007
Neg logit contributions
 blush-0.007
 perfume-0.007
Girls-0.007
ume-0.007
bs-0.007
Token and
Token ID290
Feature activation-5.49e-04

Pos logit contributions
 puck+0.019
wreck+0.018
 skate+0.018
 ship+0.018
 hockey+0.017
Neg logit contributions
 blush-0.025
Girls-0.024
ume-0.024
 perfume-0.023
bs-0.023
Token seaw
Token ID32085
Feature activation-2.20e-02

Pos logit contributions
 puck+0.001
wreck+0.001
 skate+0.001
 ship+0.001
 motorcycle+0.001
Neg logit contributions
 blush-0.001
Girls-0.001
 perfume-0.001
ume-0.001
bs-0.001
Tokeneed
Token ID2308
Feature activation-8.40e-03

Pos logit contributions
wreck+0.036
 skate+0.035
 motorcycle+0.035
 puck+0.035
 ship+0.034
Neg logit contributions
 blush-0.047
ume-0.045
bs-0.043
 perfume-0.043
Girls-0.042
Token,
Token ID11
Feature activation-5.11e-03

Pos logit contributions
 puck+0.013
wreck+0.013
 skate+0.013
 ship+0.013
 hockey+0.012
Neg logit contributions
 blush-0.019
Girls-0.019
ume-0.018
 perfume-0.018
bs-0.017
Token but
Token ID475
Feature activation-1.10e-03

Pos logit contributions
 puck+0.009
wreck+0.009
 skate+0.009
 ship+0.009
 motorcycle+0.009
Neg logit contributions
 blush-0.010
 perfume-0.010
Girls-0.009
ume-0.009
bs-0.009
Token Jane
Token ID12091
Feature activation+1.14e-03

Pos logit contributions
 his+0.002
wreck+0.002
 he+0.002
 ship+0.002
 puck+0.002
Neg logit contributions
Girls-0.002
ume-0.002
 blush-0.002
 perfume-0.002
bs-0.002
Token was
Token ID373
Feature activation+3.92e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 gear-0.002
TokenWow
Token ID22017
Feature activation+4.58e-03

Pos logit contributions
 blush+0.016
Girls+0.015
ume+0.015
 perfume+0.014
bs+0.014
Neg logit contributions
 puck-0.021
wreck-0.020
 skate-0.020
 ship-0.020
 hockey-0.019
Token,
Token ID11
Feature activation-2.06e-03

Pos logit contributions
 blush+0.010
Girls+0.009
ume+0.009
 perfume+0.009
bs+0.009
Neg logit contributions
 puck-0.008
wreck-0.008
 skate-0.008
 ship-0.007
 hockey-0.007
Token Wally
Token ID50117
Feature activation-1.54e-04

Pos logit contributions
 puck+0.004
wreck+0.004
 skate+0.004
 camps+0.004
 hockey+0.004
Neg logit contributions
 blush-0.004
Girls-0.003
ume-0.003
 perfume-0.003
bs-0.003
Token is
Token ID318
Feature activation-1.74e-03

Pos logit contributions
 puck+0.000
wreck+0.000
 skate+0.000
 ship+0.000
 hockey+0.000
Neg logit contributions
 blush-0.000
Girls-0.000
ume-0.000
 perfume-0.000
bs-0.000
Token 20
Token ID1160
Feature activation-1.12e-02

Pos logit contributions
 puck+0.004
wreck+0.004
 camps+0.004
 skate+0.003
 motorcycle+0.003
Neg logit contributions
 blush-0.003
 perfume-0.003
 makeup-0.003
ume-0.003
Girls-0.002
Token pounds
Token ID8059
Feature activation-2.16e-02

Pos logit contributions
 puck+0.022
wreck+0.022
 ship+0.021
 skate+0.021
 motorcycle+0.020
Neg logit contributions
 blush-0.020
ume-0.019
Girls-0.019
 perfume-0.018
bs-0.018
Token!"
Token ID2474
Feature activation+3.32e-03

Pos logit contributions
 puck+0.046
wreck+0.046
 skate+0.045
 ship+0.045
 camps+0.044
Neg logit contributions
 blush-0.032
ume-0.032
Girls-0.030
bs-0.030
 perfume-0.029
Token Tom
Token ID4186
Feature activation+1.23e-03

Pos logit contributions
 blush+0.007
ume+0.007
Girls+0.006
 perfume+0.006
bs+0.006
Neg logit contributions
 puck-0.006
 his-0.006
 hockey-0.006
 skate-0.006
wreck-0.006
Token exclaimed
Token ID33552
Feature activation+5.25e-03

Pos logit contributions
 blush+0.002
Girls+0.002
ume+0.002
 perfume+0.002
bs+0.002
Neg logit contributions
 puck-0.003
wreck-0.003
 skate-0.003
 ship-0.003
 hockey-0.003
Token.
Token ID13
Feature activation-1.74e-03

Pos logit contributions
 blush+0.010
ume+0.010
bs+0.010
 perfume+0.009
Girls+0.009
Neg logit contributions
 puck-0.010
wreck-0.010
 skate-0.010
 camps-0.010
 ship-0.010
Token "
Token ID366
Feature activation-2.71e-03

Pos logit contributions
 puck+0.003
wreck+0.003
 skate+0.002
 ship+0.002
 gear+0.002
Neg logit contributions
 blush-0.004
Girls-0.004
ume-0.004
 perfume-0.004
bs-0.004
Token.
Token ID13
Feature activation-8.63e-04

Pos logit contributions
 blush+0.010
ume+0.010
 perfume+0.009
Girls+0.009
bs+0.009
Neg logit contributions
 puck-0.010
wreck-0.009
 skate-0.009
 ship-0.009
 camps-0.009
Token
Token ID198
Feature activation-3.68e-03

Pos logit contributions
wreck+0.001
 puck+0.001
 ship+0.001
 skate+0.001
 motorcycle+0.001
Neg logit contributions
 blush-0.002
Girls-0.002
bs-0.002
ume-0.002
 perfume-0.002
Token
Token ID198
Feature activation-2.46e-03

Pos logit contributions
 puck+0.007
wreck+0.007
 ship+0.007
 skate+0.007
 motorcycle+0.007
Neg logit contributions
Girls-0.007
 blush-0.006
bs-0.006
ume-0.006
 perfume-0.006
TokenThe
Token ID464
Feature activation-8.88e-04

Pos logit contributions
wreck+0.005
 puck+0.005
 sailing+0.005
 motorcycle+0.005
 ship+0.005
Neg logit contributions
Girls-0.004
 blush-0.004
bs-0.004
Her-0.004
ume-0.004
Token blue
Token ID4171
Feature activation-7.37e-04

Pos logit contributions
wreck+0.002
 puck+0.001
 voy+0.001
beard+0.001
 skate+0.001
Neg logit contributions
 blush-0.002
Girls-0.002
 perfume-0.002
ume-0.002
 makeup-0.002
Token truck
Token ID7779
Feature activation-2.00e-02

Pos logit contributions
wreck+0.001
 puck+0.001
 skate+0.001
 sailing+0.001
 wre+0.001
Neg logit contributions
 blush-0.002
ume-0.002
 perfume-0.002
Girls-0.002
bs-0.002
Token also
Token ID635
Feature activation+7.39e-04

Pos logit contributions
 puck+0.031
 skate+0.031
 hockey+0.030
wreck+0.029
 sailing+0.029
Neg logit contributions
 blush-0.042
 perfume-0.040
ume-0.039
bs-0.039
Girls-0.039
Token stopped
Token ID5025
Feature activation-7.32e-03

Pos logit contributions
 blush+0.001
Girls+0.001
ume+0.001
 perfume+0.001
bs+0.001
Neg logit contributions
 puck-0.002
wreck-0.002
 skate-0.002
 ship-0.002
 hockey-0.002
Token and
Token ID290
Feature activation+2.49e-03

Pos logit contributions
 puck+0.017
wreck+0.017
 rink+0.015
 gear+0.015
 skate+0.015
Neg logit contributions
 blush-0.011
 perfume-0.011
 makeup-0.010
bs-0.010
Her-0.010
Token the
Token ID262
Feature activation+1.12e-03

Pos logit contributions
 blush+0.005
Girls+0.004
 perfume+0.004
bs+0.004
ume+0.004
Neg logit contributions
 puck-0.005
wreck-0.005
 skate-0.005
 ship-0.005
 hockey-0.005
Token driver
Token ID4639
Feature activation-1.45e-02

Pos logit contributions
 blush+0.002
Girls+0.002
 perfume+0.002
ume+0.002
 mascara+0.002
Neg logit contributions
wreck-0.002
 puck-0.002
 skate-0.002
 ship-0.002
 camps-0.002