TOP ACTIVATIONS
MAX = 0.071

they had never seen the av oc ados . They wished
something new ! She thought av oc ados were the most
store and forgot to buy av oc ados . Lily was
every day to supply the av oc ados . And the
" I will buy more av oc ados tomorrow . You
happy that it produced more av oc ados than ever before
says , " They are av oc ados . My mom
said , " I love av oc ados ! They are
away . She learned that av oc ados are good for
the tree if they were av oc ados , and they
still couldn 't find any av oc ados . Finally ,
the tree knew that the av oc ados would be back
something new ! She thought av oc ados were the most
on , whenever they wanted av oc ados , they would
so happy and brought the av oc ados home to share
Maybe they could grow more av oc ados and share them
recommendation and picked the right av oc ados .
tree could see lots of av oc ados that the supplier
ongo didn 't like wet av oc ados , so he
sign that said " RE VERS E ". L ila and

MIN ACTIVATIONS
MIN = -0.072

big slide and a sand pit . The children
on the ground and an idea popped into her head .
a snow man and a snowball and a snow angel .
snow man and have a snowball fight . They put on
kids fighting and had an idea to improve the situation .
replied Jim . Days passed and Bob noticed something
, Sam , you dropped your
, a slide and a sandbox . Sometimes they pretend to
in the back of his pickup truck . He drove to
, and she had an idea . " Let
around and made a big snowball . He laughed and played
, a slide and a sandbox . They are very organized
feel better ?" Then an idea popped into his head .
snow man and had a snowball fight with her friends .
find her . Days went by and Tim my
your vegetables ." Days went by , and Tim
and Tim had a huge snowball . Just then
will be ." Days and weeks slowly passed and
and Sam have a big idea . They want to make
little girls , Sally and Sue . They were very good

INTERVAL 0.036 - 0.071
CONTAINS 0.031%

They give Spot more or nam ents . Spot leads them
the floor and made a cozy spot on the carpet .
red . They were very cozy . Then Mom my and
. Bob sn ugg led up on the cushion
relief . The rh in oc eros was so happy to

INTERVAL -0.000 - 0.036
CONTAINS 52.955%

so exciting ! One day , Melody decided that she wanted
it ," Mom says . " That 's not
the story is not to follow strangers , no matter how
forgotten to bat he before going near the water . He
Peter never pin ched the to ad 's toe again

INTERVAL -0.036 - -0.000
CONTAINS 46.909%

She filled a cup with water and poured it in the
tick led the oy ster and suddenly it opened and Jack
. He closed one eye and pulled the trigger .
rock was too slippery , and the goat slipped .
was soft and warm . " Can I pet

INTERVAL -0.072 - -0.036
CONTAINS 0.105%

balloon . " Where are you , Anna ?"
, That , my darling ,
box . " Where is my treasure ?" he
Sarah came up with an idea . She said excited ly
. Let â s
Token they
Token ID484
Feature activation+1.65e-02

Pos logit contributions
 Oliver+0.013
smart+0.013
 court+0.012
oc+0.012
oon+0.012
Neg logit contributions
outed-0.013
packs-0.012
by-0.012
 outfits-0.012
 hats-0.012
Token had
Token ID550
Feature activation+2.51e-03

Pos logit contributions
 Oliver+0.018
oc+0.017
 defeated+0.017
smart+0.017
oon+0.017
Neg logit contributions
outed-0.027
 hats-0.027
 absolute-0.026
 outfits-0.026
 luck-0.026
Token never
Token ID1239
Feature activation-5.36e-03

Pos logit contributions
 Oliver+0.003
 defeated+0.003
 court+0.003
smart+0.003
 defeat+0.003
Neg logit contributions
outed-0.004
packs-0.004
 absolute-0.004
ays-0.004
 outfits-0.004
Token seen
Token ID1775
Feature activation-3.07e-03

Pos logit contributions
outed+0.008
 hats+0.008
 absolute+0.007
 outfits+0.007
 favorite+0.007
Neg logit contributions
smart-0.007
 court-0.007
 Oliver-0.007
oc-0.007
 defeated-0.007
Token the
Token ID262
Feature activation+1.00e-02

Pos logit contributions
outed+0.004
 hats+0.004
 luck+0.004
packs+0.004
by+0.004
Neg logit contributions
oc-0.004
 Oliver-0.004
oon-0.004
smart-0.004
 court-0.004
Token av
Token ID1196
Feature activation+7.15e-02

Pos logit contributions
 Oliver+0.015
oc+0.015
oon+0.014
smart+0.014
 court+0.013
Neg logit contributions
 hats-0.014
 luck-0.014
outed-0.013
 favorite-0.013
by-0.013
Tokenoc
Token ID420
Feature activation+5.99e-02

Pos logit contributions
oon+0.062
 Oliver+0.059
 Monster+0.048
 Emily+0.048
 congratulated+0.048
Neg logit contributions
by-0.150
 luck-0.133
 ones-0.131
ishes-0.130
ies-0.127
Tokenados
Token ID22484
Feature activation+1.66e-02

Pos logit contributions
oon+0.096
 Oliver+0.093
smart+0.085
 Rupert+0.084
 battlefield+0.084
Neg logit contributions
 luck-0.076
by-0.072
outed-0.071
ries-0.067
fl-0.067
Token.
Token ID13
Feature activation+3.13e-03

Pos logit contributions
oc+0.026
 Oliver+0.026
Mic+0.025
oon+0.025
smart+0.024
Neg logit contributions
 luck-0.021
 best-0.020
 favorite-0.020
 hats-0.019
 happened-0.019
Token They
Token ID1119
Feature activation+4.86e-03

Pos logit contributions
 Oliver+0.005
oc+0.005
oon+0.005
 court+0.005
smart+0.005
Neg logit contributions
outed-0.004
 hats-0.004
 luck-0.004
by-0.004
packs-0.004
Token wished
Token ID16555
Feature activation+1.45e-02

Pos logit contributions
 Oliver+0.007
oc+0.007
oon+0.007
smart+0.007
 court+0.007
Neg logit contributions
outed-0.006
 hats-0.006
 luck-0.006
packs-0.006
by-0.006
Token something
Token ID1223
Feature activation+6.79e-03

Pos logit contributions
oc+0.012
oon+0.012
 Oliver+0.012
 battlefield+0.011
smart+0.011
Neg logit contributions
 hats-0.011
 luck-0.011
outed-0.011
 favorite-0.010
by-0.010
Token new
Token ID649
Feature activation+2.58e-03

Pos logit contributions
oc+0.011
 Oliver+0.011
oon+0.011
smart+0.011
 court+0.011
Neg logit contributions
outed-0.008
 hats-0.008
 luck-0.007
 favorite-0.007
by-0.007
Token!
Token ID0
Feature activation+5.95e-03

Pos logit contributions
 Oliver+0.003
oc+0.003
oon+0.003
smart+0.003
 court+0.003
Neg logit contributions
outed-0.004
 hats-0.004
 luck-0.004
packs-0.004
by-0.004
Token She
Token ID1375
Feature activation+5.93e-03

Pos logit contributions
oc+0.008
oon+0.007
 Oliver+0.007
smart+0.007
 battlefield+0.007
Neg logit contributions
outed-0.009
packs-0.009
 hats-0.009
by-0.009
 luck-0.008
Token thought
Token ID1807
Feature activation+1.10e-02

Pos logit contributions
oon+0.010
smart+0.009
 battlefield+0.009
 Oliver+0.009
oc+0.009
Neg logit contributions
by-0.007
outed-0.007
 hats-0.007
 favorite-0.007
 luck-0.007
Token av
Token ID1196
Feature activation+6.95e-02

Pos logit contributions
oc+0.016
oon+0.014
Mic+0.014
 battlefield+0.014
 Oliver+0.014
Neg logit contributions
 hats-0.016
 luck-0.016
 favorite-0.016
 happened-0.015
 best-0.015
Tokenoc
Token ID420
Feature activation+5.19e-02

Pos logit contributions
 court+0.032
 battlefield+0.030
 Oliver+0.029
oon+0.026
ner+0.025
Neg logit contributions
by-0.170
 luck-0.162
packs-0.156
outed-0.155
 favorite-0.155
Tokenados
Token ID22484
Feature activation+2.16e-02

Pos logit contributions
oon+0.080
 battlefield+0.078
oc+0.076
 court+0.075
 Oliver+0.075
Neg logit contributions
 luck-0.068
outed-0.064
by-0.063
fl-0.060
 hats-0.059
Token were
Token ID547
Feature activation-1.96e-03

Pos logit contributions
oc+0.042
 Oliver+0.042
oon+0.040
smart+0.040
 battlefield+0.040
Neg logit contributions
outed-0.018
 hats-0.018
 luck-0.017
packs-0.017
by-0.017
Token the
Token ID262
Feature activation+1.46e-02

Pos logit contributions
outed+0.003
 hats+0.003
 luck+0.003
packs+0.003
by+0.003
Neg logit contributions
oc-0.003
 Oliver-0.003
oon-0.003
smart-0.003
 court-0.003
Token most
Token ID749
Feature activation+2.64e-04

Pos logit contributions
 Oliver+0.031
 court+0.030
oc+0.029
Mic+0.029
oon+0.029
Neg logit contributions
outed-0.011
packs-0.010
 hats-0.009
 coats-0.009
 outfits-0.008
Token store
Token ID3650
Feature activation-1.09e-03

Pos logit contributions
 hats+0.004
outed+0.004
 luck+0.004
by+0.004
 favorite+0.004
Neg logit contributions
oc-0.004
 Oliver-0.004
oon-0.004
smart-0.004
 court-0.003
Token and
Token ID290
Feature activation-4.84e-03

Pos logit contributions
 hats+0.002
outed+0.002
packs+0.002
 favorite+0.002
 coats+0.002
Neg logit contributions
 Oliver-0.001
oc-0.001
oon-0.001
smart-0.001
Mic-0.001
Token forgot
Token ID16453
Feature activation-1.53e-02

Pos logit contributions
outed+0.006
 hats+0.006
 favorite+0.006
by+0.006
 coats+0.006
Neg logit contributions
oc-0.008
oon-0.008
smart-0.007
 Oliver-0.007
 battlefield-0.007
Token to
Token ID284
Feature activation+4.24e-03

Pos logit contributions
 hats+0.022
 luck+0.020
 favorite+0.020
outed+0.020
 coats+0.020
Neg logit contributions
oc-0.024
oon-0.023
 Oliver-0.022
Mic-0.021
 battlefield-0.021
Token buy
Token ID2822
Feature activation+1.02e-02

Pos logit contributions
 Oliver+0.006
oc+0.006
oon+0.006
smart+0.006
 court+0.005
Neg logit contributions
outed-0.006
 hats-0.006
 luck-0.006
packs-0.006
by-0.006
Token av
Token ID1196
Feature activation+6.93e-02

Pos logit contributions
 Oliver+0.015
oc+0.014
smart+0.014
 court+0.014
oon+0.014
Neg logit contributions
outed-0.014
 hats-0.013
packs-0.013
by-0.013
 absolute-0.013
Tokenoc
Token ID420
Feature activation+4.81e-02

Pos logit contributions
oon+0.040
 Oliver+0.035
 battlefield+0.033
ner+0.030
 court+0.029
Neg logit contributions
by-0.166
 luck-0.155
packs-0.153
 favorite-0.151
 favorites-0.149
Tokenados
Token ID22484
Feature activation+1.28e-02

Pos logit contributions
oon+0.076
 Oliver+0.072
oc+0.069
 battlefield+0.069
smart+0.066
Neg logit contributions
 luck-0.063
outed-0.061
by-0.059
 hats-0.058
ries-0.056
Token.
Token ID13
Feature activation+4.29e-03

Pos logit contributions
oc+0.020
oon+0.019
 Oliver+0.019
 battlefield+0.019
smart+0.018
Neg logit contributions
packs-0.017
 hats-0.017
 luck-0.017
 favorite-0.017
 best-0.016
Token Lily
Token ID20037
Feature activation+1.49e-02

Pos logit contributions
oc+0.005
oon+0.005
 Oliver+0.005
smart+0.005
 battlefield+0.005
Neg logit contributions
outed-0.007
 hats-0.007
 favorite-0.006
 coats-0.006
 absolute-0.006
Token was
Token ID373
Feature activation-3.61e-03

Pos logit contributions
smart+0.029
oon+0.028
 Oliver+0.027
 battlefield+0.027
oc+0.026
Neg logit contributions
outed-0.016
 favorite-0.015
by-0.014
 hats-0.013
 happened-0.012
Token every
Token ID790
Feature activation+2.54e-03

Pos logit contributions
packs+0.007
 favorite+0.007
by+0.007
 best+0.007
 luck+0.007
Neg logit contributions
 Oliver-0.007
oon-0.007
Mic-0.007
oc-0.006
smart-0.006
Token day
Token ID1110
Feature activation-1.08e-02

Pos logit contributions
 Oliver+0.005
oc+0.005
oon+0.005
smart+0.005
 court+0.005
Neg logit contributions
outed-0.002
 hats-0.002
 luck-0.002
by-0.002
packs-0.002
Token to
Token ID284
Feature activation-6.66e-03

Pos logit contributions
 hats+0.014
 luck+0.014
 favorite+0.014
packs+0.014
 best+0.014
Neg logit contributions
oc-0.016
 Oliver-0.016
oon-0.016
Mic-0.015
smart-0.015
Token supply
Token ID5127
Feature activation+1.31e-02

Pos logit contributions
 luck+0.009
 hats+0.008
 absolute+0.008
 dreams+0.007
 names+0.007
Neg logit contributions
oon-0.011
 Oliver-0.010
oc-0.010
Mic-0.010
 Monster-0.009
Token the
Token ID262
Feature activation+1.68e-02

Pos logit contributions
oon+0.021
 Oliver+0.020
 battlefield+0.019
oc+0.019
ner+0.018
Neg logit contributions
 luck-0.017
 best-0.017
by-0.016
 hats-0.016
 favorite-0.016
Token av
Token ID1196
Feature activation+6.89e-02

Pos logit contributions
 Oliver+0.026
oon+0.026
oc+0.025
smart+0.025
 battlefield+0.023
Neg logit contributions
 luck-0.022
 favorite-0.022
 best-0.021
 hats-0.021
by-0.021
Tokenoc
Token ID420
Feature activation+5.00e-02

Pos logit contributions
 Oliver+0.052
 Monster+0.046
ner+0.045
oon+0.044
 battlefield+0.044
Neg logit contributions
by-0.157
ies-0.139
bi-0.138
 luck-0.137
fl-0.135
Tokenados
Token ID22484
Feature activation+1.75e-02

Pos logit contributions
 Oliver+0.080
oon+0.080
 battlefield+0.074
smart+0.072
 Rupert+0.072
Neg logit contributions
 luck-0.062
by-0.059
outed-0.059
ries-0.055
fl-0.055
Token.
Token ID13
Feature activation+5.48e-03

Pos logit contributions
 Oliver+0.025
oc+0.025
oon+0.024
Mic+0.024
 battlefield+0.023
Neg logit contributions
 luck-0.025
 favorite-0.024
packs-0.024
 hats-0.024
 best-0.024
Token And
Token ID843
Feature activation-3.68e-03

Pos logit contributions
oon+0.008
smart+0.007
oc+0.007
 Oliver+0.007
 battlefield+0.007
Neg logit contributions
 de-0.007
outed-0.007
 absolute-0.007
 favorite-0.007
packs-0.007
Token the
Token ID262
Feature activation+8.13e-05

Pos logit contributions
 luck+0.006
by+0.005
 favorite+0.005
 hats+0.005
 absolute+0.005
Neg logit contributions
oon-0.005
oc-0.005
 Oliver-0.005
Mic-0.004
 battlefield-0.004
Token "
Token ID366
Feature activation-4.21e-03

Pos logit contributions
oc+0.024
 battlefield+0.023
oon+0.022
Mic+0.021
 court+0.021
Neg logit contributions
 de-0.018
 hats-0.018
outed-0.018
 favorite-0.016
 best-0.016
TokenI
Token ID40
Feature activation-5.07e-03

Pos logit contributions
outed+0.006
 hats+0.006
 luck+0.006
packs+0.006
by+0.005
Neg logit contributions
oc-0.006
 Oliver-0.006
oon-0.006
smart-0.006
 court-0.006
Token will
Token ID481
Feature activation+2.01e-02

Pos logit contributions
by+0.006
outed+0.006
 luck+0.006
 happened+0.006
 favorite+0.006
Neg logit contributions
 battlefield-0.008
oon-0.008
 Oliver-0.008
Mic-0.008
 court-0.008
Token buy
Token ID2822
Feature activation+1.17e-02

Pos logit contributions
oon+0.034
oc+0.033
Mic+0.032
 battlefield+0.032
 Oliver+0.031
Neg logit contributions
 hats-0.025
 luck-0.024
 absolute-0.023
 favorite-0.023
 names-0.023
Token more
Token ID517
Feature activation+4.09e-03

Pos logit contributions
oc+0.013
 Oliver+0.013
oon+0.013
smart+0.012
 court+0.012
Neg logit contributions
 hats-0.019
outed-0.019
 luck-0.019
by-0.018
packs-0.018
Token av
Token ID1196
Feature activation+6.68e-02

Pos logit contributions
 Oliver+0.008
oon+0.008
 battlefield+0.008
oc+0.008
Mic+0.008
Neg logit contributions
 hats-0.004
 luck-0.004
packs-0.004
 coats-0.004
 favorite-0.004
Tokenoc
Token ID420
Feature activation+5.61e-02

Pos logit contributions
 Oliver+0.043
oon+0.040
 battlefield+0.036
 Monster+0.032
 court+0.031
Neg logit contributions
by-0.157
 luck-0.146
packs-0.145
 hats-0.138
ies-0.138
Tokenados
Token ID22484
Feature activation+7.92e-03

Pos logit contributions
oon+0.095
 Oliver+0.090
 battlefield+0.086
 Rupert+0.082
 court+0.082
Neg logit contributions
 luck-0.069
by-0.064
outed-0.063
ries-0.062
 hats-0.060
Token tomorrow
Token ID9439
Feature activation-5.01e-03

Pos logit contributions
 Oliver+0.012
oc+0.012
 battlefield+0.012
Mic+0.012
oon+0.012
Neg logit contributions
 luck-0.010
packs-0.010
 hats-0.010
 favorite-0.010
 best-0.010
Token.
Token ID13
Feature activation-1.05e-03

Pos logit contributions
 hats+0.008
outed+0.008
packs+0.008
 luck+0.008
by+0.008
Neg logit contributions
 Oliver-0.006
oc-0.006
oon-0.006
smart-0.006
Mic-0.005
Token You
Token ID921
Feature activation+1.16e-02

Pos logit contributions
 names+0.001
 hats+0.001
 absolute+0.001
 favorite+0.001
outed+0.001
Neg logit contributions
oon-0.002
 battlefield-0.001
 court-0.001
smart-0.001
 defeated-0.001
Token happy
Token ID3772
Feature activation+7.01e-03

Pos logit contributions
 Oliver+0.007
oon+0.007
oc+0.007
 battlefield+0.007
 court+0.007
Neg logit contributions
 luck-0.008
outed-0.007
 favorite-0.007
 best-0.007
 absolute-0.007
Token that
Token ID326
Feature activation+1.28e-03

Pos logit contributions
oc+0.008
 Oliver+0.008
oon+0.007
smart+0.007
 court+0.007
Neg logit contributions
 hats-0.012
outed-0.012
 luck-0.012
by-0.011
packs-0.011
Token it
Token ID340
Feature activation+6.52e-03

Pos logit contributions
oc+0.002
oon+0.002
Mic+0.002
 battlefield+0.002
smart+0.002
Neg logit contributions
 best-0.002
 luck-0.002
 happened-0.002
 absolute-0.002
 favorite-0.002
Token produced
Token ID4635
Feature activation+3.38e-03

Pos logit contributions
oc+0.011
 Oliver+0.011
 court+0.011
 battlefield+0.011
smart+0.010
Neg logit contributions
 happened-0.007
 luck-0.007
outed-0.007
by-0.006
 absolute-0.006
Token more
Token ID517
Feature activation+1.57e-02

Pos logit contributions
oc+0.005
 Oliver+0.005
oon+0.005
smart+0.005
 battlefield+0.004
Neg logit contributions
 luck-0.005
 hats-0.005
outed-0.005
by-0.004
 favorite-0.004
Token av
Token ID1196
Feature activation+6.66e-02

Pos logit contributions
 Oliver+0.026
oon+0.025
oc+0.025
 battlefield+0.024
smart+0.023
Neg logit contributions
 luck-0.020
 favorite-0.019
by-0.018
 hats-0.018
outed-0.018
Tokenoc
Token ID420
Feature activation+5.26e-02

Pos logit contributions
 Oliver+0.047
oon+0.044
 battlefield+0.042
 court+0.041
 Monster+0.041
Neg logit contributions
by-0.152
 luck-0.142
ies-0.135
packs-0.133
ishes-0.132
Tokenados
Token ID22484
Feature activation+1.88e-02

Pos logit contributions
oon+0.084
 Oliver+0.082
 battlefield+0.077
 court+0.075
oc+0.075
Neg logit contributions
 luck-0.068
outed-0.064
by-0.064
ries-0.059
 hats-0.059
Token than
Token ID621
Feature activation-4.31e-03

Pos logit contributions
oc+0.025
 Oliver+0.024
oon+0.024
 battlefield+0.023
Mic+0.023
Neg logit contributions
 luck-0.028
 hats-0.027
packs-0.027
 best-0.026
by-0.026
Token ever
Token ID1683
Feature activation-5.39e-03

Pos logit contributions
 luck+0.006
 happened+0.006
by+0.006
 best+0.006
 hats+0.005
Neg logit contributions
oc-0.007
oon-0.007
 Oliver-0.006
Mic-0.006
smart-0.006
Token before
Token ID878
Feature activation-1.05e-02

Pos logit contributions
 luck+0.009
by+0.009
outed+0.009
 hats+0.009
packs+0.009
Neg logit contributions
 Oliver-0.006
oc-0.006
oon-0.006
Mic-0.005
smart-0.005
Token says
Token ID1139
Feature activation+4.50e-03

Pos logit contributions
oc+0.013
 Oliver+0.013
oon+0.013
smart+0.012
 court+0.012
Neg logit contributions
outed-0.006
 hats-0.006
 luck-0.005
packs-0.005
by-0.005
Token,
Token ID11
Feature activation+8.74e-03

Pos logit contributions
oc+0.003
 Oliver+0.003
oon+0.003
smart+0.003
 court+0.003
Neg logit contributions
outed-0.009
 hats-0.009
 luck-0.009
by-0.009
packs-0.009
Token "
Token ID366
Feature activation-1.32e-03

Pos logit contributions
oc+0.009
oon+0.008
 Oliver+0.008
 battlefield+0.008
smart+0.008
Neg logit contributions
 hats-0.016
outed-0.016
 de-0.015
 favorite-0.015
 happened-0.015
TokenThey
Token ID2990
Feature activation+7.03e-03

Pos logit contributions
outed+0.002
 luck+0.002
 hats+0.002
packs+0.002
by+0.002
Neg logit contributions
oc-0.002
 Oliver-0.002
oon-0.002
 court-0.002
smart-0.002
Token are
Token ID389
Feature activation-1.72e-03

Pos logit contributions
 Oliver+0.013
oc+0.013
oon+0.013
smart+0.013
 court+0.012
Neg logit contributions
 hats-0.007
outed-0.007
 luck-0.006
packs-0.006
by-0.006
Token av
Token ID1196
Feature activation+6.66e-02

Pos logit contributions
 hats+0.003
 best+0.002
 favorite+0.002
 coats+0.002
 luck+0.002
Neg logit contributions
oc-0.003
oon-0.003
smart-0.002
 Oliver-0.002
 battlefield-0.002
Tokenoc
Token ID420
Feature activation+4.75e-02

Pos logit contributions
 Oliver+0.036
oon+0.034
 court+0.033
 battlefield+0.033
ner+0.030
Neg logit contributions
by-0.151
packs-0.147
 luck-0.145
 hats-0.143
ies-0.141
Tokenados
Token ID22484
Feature activation+1.32e-02

Pos logit contributions
oon+0.070
oc+0.069
 Oliver+0.068
 battlefield+0.065
smart+0.064
Neg logit contributions
 luck-0.063
 hats-0.061
outed-0.060
by-0.058
 coats-0.057
Token.
Token ID13
Feature activation+5.42e-03

Pos logit contributions
oc+0.021
 Oliver+0.020
smart+0.020
oon+0.020
Mic+0.020
Neg logit contributions
 hats-0.017
 luck-0.016
 best-0.016
packs-0.016
 favorite-0.015
Token My
Token ID2011
Feature activation-2.05e-02

Pos logit contributions
oon+0.010
 Oliver+0.009
oc+0.009
 defeated+0.009
smart+0.009
Neg logit contributions
 hats-0.006
 names-0.005
 favorite-0.005
packs-0.005
 coats-0.005
Token mom
Token ID1995
Feature activation+9.61e-04

Pos logit contributions
outed+0.022
 hats+0.022
 luck+0.021
packs+0.021
by+0.021
Neg logit contributions
 Oliver-0.035
oc-0.035
oon-0.035
smart-0.034
 court-0.033
Token said
Token ID531
Feature activation+7.25e-03

Pos logit contributions
oc+0.019
smart+0.019
oon+0.019
 Oliver+0.018
 battlefield+0.018
Neg logit contributions
outed-0.013
by-0.012
 hats-0.011
 happened-0.011
 favorite-0.011
Token,
Token ID11
Feature activation+1.36e-02

Pos logit contributions
oc+0.010
oon+0.010
 battlefield+0.010
Mic+0.009
 Oliver+0.009
Neg logit contributions
 luck-0.011
 happened-0.011
 hats-0.010
 favorite-0.010
outed-0.010
Token "
Token ID366
Feature activation-1.63e-03

Pos logit contributions
oc+0.021
oon+0.020
 battlefield+0.019
 arrest+0.018
 court+0.018
Neg logit contributions
 de-0.018
 hats-0.017
 favorite-0.017
 happened-0.017
outed-0.017
TokenI
Token ID40
Feature activation-5.51e-03

Pos logit contributions
 hats+0.002
outed+0.002
packs+0.002
 luck+0.002
 coats+0.002
Neg logit contributions
oc-0.002
 Oliver-0.002
oon-0.002
smart-0.002
 court-0.002
Token love
Token ID1842
Feature activation+4.02e-03

Pos logit contributions
by+0.007
outed+0.007
 luck+0.007
 favorite+0.007
 happened+0.007
Neg logit contributions
oon-0.008
 Oliver-0.008
 battlefield-0.008
smart-0.008
Mic-0.008
Token av
Token ID1196
Feature activation+6.64e-02

Pos logit contributions
oon+0.007
oc+0.007
 battlefield+0.006
smart+0.006
Offic+0.006
Neg logit contributions
 luck-0.005
 favorite-0.005
 hats-0.005
 vanilla-0.005
 best-0.005
Tokenoc
Token ID420
Feature activation+5.17e-02

Pos logit contributions
oon+0.044
 Oliver+0.042
 battlefield+0.041
 court+0.039
ner+0.038
Neg logit contributions
by-0.152
 luck-0.139
packs-0.133
ishes-0.133
 favorites-0.132
Tokenados
Token ID22484
Feature activation+1.25e-02

Pos logit contributions
oon+0.089
 battlefield+0.083
 Oliver+0.082
oc+0.078
 court+0.076
Neg logit contributions
 luck-0.062
by-0.058
ries-0.056
outed-0.056
fl-0.051
Token!
Token ID0
Feature activation-1.91e-03

Pos logit contributions
oc+0.018
Offic+0.018
 battlefield+0.018
 courtroom+0.018
Mic+0.018
Neg logit contributions
 luck-0.017
 best-0.017
 favorite-0.016
 hats-0.016
ies-0.015
Token They
Token ID1119
Feature activation+7.13e-03

Pos logit contributions
 favorite+0.002
 names+0.002
Deal+0.002
 absolute+0.002
 de+0.002
Neg logit contributions
oon-0.003
 battlefield-0.003
 court-0.003
pping-0.003
 defeated-0.003
Token are
Token ID389
Feature activation-6.58e-03

Pos logit contributions
 Oliver+0.013
oon+0.013
oc+0.013
smart+0.012
 court+0.012
Neg logit contributions
outed-0.007
 hats-0.007
 luck-0.007
by-0.007
 favorite-0.007
Token away
Token ID1497
Feature activation-4.76e-03

Pos logit contributions
 hats+0.009
by+0.008
 luck+0.008
 coats+0.008
 favorite+0.008
Neg logit contributions
oc-0.014
oon-0.013
 Oliver-0.013
cess-0.012
Mic-0.012
Token.
Token ID13
Feature activation+6.01e-03

Pos logit contributions
 luck+0.005
 favorite+0.005
 best+0.005
 de+0.005
ies+0.004
Neg logit contributions
Mic-0.009
 Oliver-0.009
oc-0.008
oon-0.008
 battlefield-0.008
Token She
Token ID1375
Feature activation+3.17e-03

Pos logit contributions
oon+0.008
oc+0.007
smart+0.007
 battlefield+0.007
 defeat+0.007
Neg logit contributions
outed-0.010
 favorite-0.009
 de-0.009
by-0.009
 absolute-0.009
Token learned
Token ID4499
Feature activation+3.28e-03

Pos logit contributions
 Oliver+0.005
oc+0.005
smart+0.005
oon+0.005
 court+0.005
Neg logit contributions
outed-0.004
 hats-0.004
by-0.004
 favorite-0.004
 luck-0.003
Token that
Token ID326
Feature activation+4.59e-04

Pos logit contributions
oc+0.005
oon+0.004
 Oliver+0.004
 battlefield+0.004
Mic+0.004
Neg logit contributions
 luck-0.005
 hats-0.005
 favorite-0.005
outed-0.005
 best-0.005
Token av
Token ID1196
Feature activation+6.60e-02

Pos logit contributions
oc+0.001
oon+0.001
smart+0.001
 Oliver+0.001
 battlefield+0.001
Neg logit contributions
 luck-0.001
 best-0.001
 hats-0.001
 favorite-0.001
 happened-0.001
Tokenoc
Token ID420
Feature activation+4.42e-02

Pos logit contributions
 court+0.035
 Oliver+0.031
 battlefield+0.030
ner+0.030
oon+0.028
Neg logit contributions
by-0.159
 luck-0.148
packs-0.143
ies-0.142
 favorite-0.141
Tokenados
Token ID22484
Feature activation+2.05e-02

Pos logit contributions
oon+0.066
 Oliver+0.064
oc+0.064
 battlefield+0.063
smart+0.061
Neg logit contributions
 luck-0.060
outed-0.056
by-0.055
 hats-0.052
fl-0.051
Token are
Token ID389
Feature activation-3.78e-03

Pos logit contributions
oc+0.039
 Oliver+0.038
oon+0.037
Mic+0.037
 battlefield+0.037
Neg logit contributions
 luck-0.018
outed-0.018
 hats-0.018
packs-0.017
 happened-0.017
Token good
Token ID922
Feature activation-5.87e-03

Pos logit contributions
 luck+0.005
 best+0.005
 hats+0.004
 favorite+0.004
 prett+0.004
Neg logit contributions
oc-0.007
oon-0.006
 Oliver-0.006
 battlefield-0.006
 court-0.006
Token for
Token ID329
Feature activation+1.52e-02

Pos logit contributions
outed+0.010
 hats+0.010
 luck+0.009
packs+0.009
by+0.009
Neg logit contributions
oc-0.007
 Oliver-0.007
oon-0.007
smart-0.006
 court-0.006
Token the
Token ID262
Feature activation+1.03e-02

Pos logit contributions
oc+0.008
oon+0.008
 battlefield+0.007
smart+0.007
 Oliver+0.007
Neg logit contributions
 luck-0.003
 hats-0.003
 best-0.003
 favorite-0.003
by-0.003
Token tree
Token ID5509
Feature activation+1.82e-02

Pos logit contributions
oc+0.014
oon+0.014
 Oliver+0.014
smart+0.014
 battlefield+0.012
Neg logit contributions
 luck-0.015
 hats-0.015
 favorite-0.015
 best-0.015
outed-0.014
Token if
Token ID611
Feature activation-6.05e-03

Pos logit contributions
oon+0.021
 Oliver+0.020
oc+0.020
Mic+0.020
 battlefield+0.019
Neg logit contributions
 hats-0.030
packs-0.030
 favorite-0.030
by-0.030
outed-0.030
Token they
Token ID484
Feature activation+8.46e-03

Pos logit contributions
outed+0.008
 hats+0.008
 luck+0.007
packs+0.007
by+0.007
Neg logit contributions
oc-0.009
 Oliver-0.009
oon-0.009
smart-0.009
 court-0.008
Token were
Token ID547
Feature activation+1.13e-03

Pos logit contributions
 Oliver+0.012
oc+0.012
oon+0.011
smart+0.011
 battlefield+0.011
Neg logit contributions
outed-0.012
 hats-0.012
 luck-0.012
by-0.012
packs-0.012
Token av
Token ID1196
Feature activation+6.57e-02

Pos logit contributions
oc+0.002
oon+0.002
 Oliver+0.002
Mic+0.002
 battlefield+0.002
Neg logit contributions
 luck-0.002
 hats-0.002
 best-0.002
 favorite-0.002
outed-0.001
Tokenoc
Token ID420
Feature activation+4.80e-02

Pos logit contributions
 Oliver+0.033
oon+0.032
 battlefield+0.028
 court+0.027
ner+0.025
Neg logit contributions
by-0.157
 luck-0.153
packs-0.152
 hats-0.144
 favorites-0.143
Tokenados
Token ID22484
Feature activation+2.13e-02

Pos logit contributions
oon+0.072
 Oliver+0.070
oc+0.067
 battlefield+0.066
 court+0.064
Neg logit contributions
 luck-0.065
outed-0.063
 hats-0.061
by-0.061
 coats-0.056
Token,
Token ID11
Feature activation+3.16e-03

Pos logit contributions
oc+0.024
oon+0.022
 Oliver+0.022
 battlefield+0.021
smart+0.021
Neg logit contributions
 luck-0.037
 hats-0.037
packs-0.036
 best-0.035
 favorite-0.035
Token and
Token ID290
Feature activation-7.33e-03

Pos logit contributions
oc+0.004
oon+0.004
 battlefield+0.004
Mic+0.004
 Oliver+0.004
Neg logit contributions
 hats-0.005
 favorite-0.005
 coats-0.005
 best-0.005
 luck-0.004
Token they
Token ID484
Feature activation-3.12e-03

Pos logit contributions
 hats+0.009
outed+0.009
 luck+0.008
packs+0.008
 favorite+0.008
Neg logit contributions
oc-0.012
oon-0.012
 Oliver-0.011
smart-0.011
 battlefield-0.011
Token still
Token ID991
Feature activation-5.06e-03

Pos logit contributions
oc+0.003
oon+0.003
smart+0.003
 battlefield+0.003
Mic+0.003
Neg logit contributions
outed-0.002
 hats-0.002
 favorite-0.002
 luck-0.002
by-0.002
Token couldn
Token ID3521
Feature activation+1.49e-02

Pos logit contributions
outed+0.007
 luck+0.007
by+0.007
packs+0.007
 hats+0.007
Neg logit contributions
oc-0.008
oon-0.007
 Oliver-0.007
Mic-0.007
 battlefield-0.007
Token't
Token ID470
Feature activation+1.41e-03

Pos logit contributions
oc+0.010
 Oliver+0.009
oon+0.008
smart+0.008
 battlefield+0.008
Neg logit contributions
outed-0.032
 hats-0.031
 luck-0.031
 absolute-0.031
 happened-0.031
Token find
Token ID1064
Feature activation+1.95e-03

Pos logit contributions
oc+0.002
oon+0.002
 Oliver+0.002
smart+0.002
 battlefield+0.002
Neg logit contributions
 luck-0.002
by-0.002
 absolute-0.002
 hats-0.002
 favorite-0.002
Token any
Token ID597
Feature activation+8.80e-03

Pos logit contributions
 Oliver+0.002
smart+0.002
oc+0.002
 court+0.002
 Owl+0.002
Neg logit contributions
outed-0.003
 hats-0.003
packs-0.003
 outfits-0.003
by-0.003
Token av
Token ID1196
Feature activation+6.56e-02

Pos logit contributions
oc+0.012
 Oliver+0.012
smart+0.012
oon+0.011
 court+0.011
Neg logit contributions
outed-0.013
 hats-0.012
packs-0.012
by-0.012
 absolute-0.012
Tokenoc
Token ID420
Feature activation+5.52e-02

Pos logit contributions
 Oliver+0.037
oon+0.035
 battlefield+0.028
 court+0.028
cess+0.027
Neg logit contributions
by-0.157
 luck-0.147
packs-0.146
bi-0.138
 favorites-0.137
Tokenados
Token ID22484
Feature activation+1.31e-02

Pos logit contributions
oon+0.093
 Oliver+0.087
 battlefield+0.082
 Rupert+0.080
 court+0.079
Neg logit contributions
 luck-0.068
by-0.064
outed-0.061
ries-0.061
 hats-0.058
Token.
Token ID13
Feature activation+4.63e-03

Pos logit contributions
oc+0.020
 Oliver+0.019
oon+0.018
smart+0.018
 battlefield+0.018
Neg logit contributions
packs-0.017
 hats-0.017
outed-0.017
 luck-0.017
by-0.016
Token Finally
Token ID9461
Feature activation-1.46e-02

Pos logit contributions
oc+0.006
oon+0.006
smart+0.005
 Oliver+0.005
 battlefield+0.005
Neg logit contributions
outed-0.007
 hats-0.007
 favorite-0.007
packs-0.007
 absolute-0.007
Token,
Token ID11
Feature activation+1.71e-02

Pos logit contributions
 hats+0.029
outed+0.029
 luck+0.029
packs+0.028
by+0.028
Neg logit contributions
oc-0.012
 Oliver-0.011
oon-0.011
smart-0.010
 court-0.010
Token the
Token ID262
Feature activation-2.51e-03

Pos logit contributions
 luck+0.008
by+0.007
 best+0.007
 hats+0.007
 absolute+0.007
Neg logit contributions
oon-0.006
Mic-0.006
smart-0.006
 battlefield-0.006
oc-0.005
Token tree
Token ID5509
Feature activation-4.96e-03

Pos logit contributions
 luck+0.003
 hats+0.003
 best+0.003
 favorite+0.003
outed+0.003
Neg logit contributions
oc-0.004
oon-0.004
smart-0.004
 Oliver-0.004
 battlefield-0.003
Token knew
Token ID2993
Feature activation+3.73e-03

Pos logit contributions
outed+0.006
 hats+0.006
by+0.006
 luck+0.006
packs+0.006
Neg logit contributions
 Oliver-0.008
oc-0.008
oon-0.007
smart-0.007
 court-0.007
Token that
Token ID326
Feature activation-1.54e-03

Pos logit contributions
oc+0.005
oon+0.005
 battlefield+0.004
Mic+0.004
 Oliver+0.004
Neg logit contributions
 luck-0.006
 hats-0.006
outed-0.006
 best-0.005
by-0.005
Token the
Token ID262
Feature activation+4.17e-03

Pos logit contributions
 luck+0.002
 best+0.002
 happened+0.002
 hats+0.002
 favorite+0.002
Neg logit contributions
oon-0.002
oc-0.002
Mic-0.002
 battlefield-0.002
 Oliver-0.002
Token av
Token ID1196
Feature activation+6.56e-02

Pos logit contributions
oon+0.006
oc+0.006
 Oliver+0.006
smart+0.006
 battlefield+0.005
Neg logit contributions
 luck-0.006
 favorite-0.006
 hats-0.006
 best-0.006
outed-0.006
Tokenoc
Token ID420
Feature activation+4.85e-02

Pos logit contributions
 Oliver+0.038
oon+0.035
 court+0.033
 battlefield+0.032
cess+0.030
Neg logit contributions
by-0.155
 luck-0.143
ies-0.138
bi-0.137
fl-0.136
Tokenados
Token ID22484
Feature activation+2.25e-02

Pos logit contributions
oon+0.079
 Oliver+0.077
 battlefield+0.072
smart+0.070
 Rupert+0.070
Neg logit contributions
 luck-0.059
by-0.057
outed-0.056
ries-0.053
fl-0.053
Token would
Token ID561
Feature activation+1.41e-02

Pos logit contributions
 Oliver+0.040
oc+0.039
oon+0.038
smart+0.038
 battlefield+0.037
Neg logit contributions
outed-0.023
 hats-0.022
 luck-0.022
by-0.022
packs-0.021
Token be
Token ID307
Feature activation+9.28e-04

Pos logit contributions
oc+0.023
 Oliver+0.023
oon+0.023
smart+0.022
 battlefield+0.021
Neg logit contributions
 luck-0.017
 hats-0.016
 absolute-0.015
by-0.015
 favorite-0.015
Token back
Token ID736
Feature activation-2.20e-03

Pos logit contributions
oc+0.001
 Oliver+0.001
oon+0.001
smart+0.001
 court+0.001
Neg logit contributions
outed-0.001
 hats-0.001
 luck-0.001
packs-0.001
by-0.001
Token something
Token ID1223
Feature activation+4.26e-03

Pos logit contributions
oc+0.009
oon+0.009
 Oliver+0.009
 battlefield+0.008
smart+0.008
Neg logit contributions
 luck-0.008
 hats-0.007
outed-0.007
 favorite-0.007
by-0.007
Token new
Token ID649
Feature activation+8.93e-05

Pos logit contributions
oc+0.007
 Oliver+0.007
oon+0.007
smart+0.007
 court+0.007
Neg logit contributions
outed-0.005
 hats-0.005
 luck-0.005
by-0.005
 favorite-0.005
Token!
Token ID0
Feature activation+4.72e-03

Pos logit contributions
 Oliver+0.000
oc+0.000
oon+0.000
smart+0.000
 court+0.000
Neg logit contributions
outed-0.000
 hats-0.000
 luck-0.000
packs-0.000
by-0.000
Token She
Token ID1375
Feature activation+3.00e-03

Pos logit contributions
oc+0.006
oon+0.006
 Oliver+0.006
 battlefield+0.005
smart+0.005
Neg logit contributions
outed-0.007
packs-0.007
by-0.007
 hats-0.007
 luck-0.007
Token thought
Token ID1807
Feature activation+9.01e-03

Pos logit contributions
oon+0.005
smart+0.005
 battlefield+0.005
 Oliver+0.005
oc+0.005
Neg logit contributions
by-0.004
outed-0.003
 favorite-0.003
 luck-0.003
 hats-0.003
Token av
Token ID1196
Feature activation+6.47e-02

Pos logit contributions
oc+0.014
Mic+0.012
oon+0.012
 battlefield+0.012
 Oliver+0.011
Neg logit contributions
 hats-0.013
 luck-0.013
 favorite-0.013
 happened-0.012
 best-0.012
Tokenoc
Token ID420
Feature activation+4.93e-02

Pos logit contributions
 court+0.030
 battlefield+0.027
 Oliver+0.027
oon+0.024
ner+0.024
Neg logit contributions
by-0.159
 luck-0.151
 favorite-0.145
outed-0.145
packs-0.145
Tokenados
Token ID22484
Feature activation+1.77e-02

Pos logit contributions
oon+0.076
 battlefield+0.075
oc+0.073
 court+0.072
 Oliver+0.071
Neg logit contributions
 luck-0.064
outed-0.060
by-0.059
fl-0.057
 hats-0.055
Token were
Token ID547
Feature activation-4.28e-03

Pos logit contributions
oc+0.035
 Oliver+0.034
oon+0.033
smart+0.033
 battlefield+0.033
Neg logit contributions
outed-0.015
 hats-0.014
 luck-0.014
packs-0.014
by-0.014
Token the
Token ID262
Feature activation+1.32e-02

Pos logit contributions
outed+0.006
 hats+0.006
 luck+0.006
packs+0.005
by+0.005
Neg logit contributions
oc-0.006
 Oliver-0.006
oon-0.006
smart-0.006
 court-0.006
Token most
Token ID749
Feature activation-2.21e-03

Pos logit contributions
 Oliver+0.028
 court+0.027
oc+0.026
Mic+0.026
oon+0.026
Neg logit contributions
outed-0.010
packs-0.010
 hats-0.009
 coats-0.008
 outfits-0.008
Token on
Token ID319
Feature activation-7.58e-04

Pos logit contributions
 Oliver+0.021
oon+0.021
oc+0.021
 battlefield+0.020
 court+0.020
Neg logit contributions
 luck-0.018
 hats-0.018
 best-0.017
outed-0.017
packs-0.017
Token,
Token ID11
Feature activation+1.39e-02

Pos logit contributions
 hats+0.002
outed+0.002
 luck+0.001
by+0.001
packs+0.001
Neg logit contributions
oc-0.001
 Oliver-0.001
oon-0.001
smart-0.001
 battlefield-0.001
Token whenever
Token ID8797
Feature activation-7.07e-03

Pos logit contributions
oon+0.022
oc+0.021
 Oliver+0.021
smart+0.020
 battlefield+0.020
Neg logit contributions
 hats-0.017
 favorite-0.017
by-0.017
outed-0.017
 absolute-0.017
Token they
Token ID484
Feature activation+4.91e-03

Pos logit contributions
outed+0.011
 hats+0.011
packs+0.011
 luck+0.011
by+0.010
Neg logit contributions
 Oliver-0.009
oc-0.009
oon-0.008
 court-0.008
smart-0.008
Token wanted
Token ID2227
Feature activation+6.31e-03

Pos logit contributions
oon+0.009
 Oliver+0.009
oc+0.008
smart+0.008
cess+0.008
Neg logit contributions
outed-0.005
by-0.005
 luck-0.005
packs-0.005
 happened-0.005
Token av
Token ID1196
Feature activation+6.44e-02

Pos logit contributions
oon+0.009
oc+0.009
 Oliver+0.009
 battlefield+0.008
cess+0.008
Neg logit contributions
 luck-0.009
 favorite-0.009
 hats-0.009
 best-0.009
by-0.009
Tokenoc
Token ID420
Feature activation+4.27e-02

Pos logit contributions
oon+0.027
 Oliver+0.024
 court+0.022
 battlefield+0.022
ner+0.020
Neg logit contributions
by-0.160
 luck-0.154
packs-0.151
 favorite-0.148
 hats-0.147
Tokenados
Token ID22484
Feature activation+1.66e-02

Pos logit contributions
oon+0.062
 Oliver+0.059
oc+0.058
 battlefield+0.056
smart+0.055
Neg logit contributions
 luck-0.060
outed-0.058
 hats-0.057
by-0.057
 favorite-0.053
Token,
Token ID11
Feature activation+6.57e-03

Pos logit contributions
oc+0.016
 Oliver+0.015
oon+0.015
smart+0.013
 battlefield+0.013
Neg logit contributions
 hats-0.031
 luck-0.031
outed-0.031
packs-0.030
by-0.030
Token they
Token ID484
Feature activation+1.45e-04

Pos logit contributions
 Oliver+0.010
oc+0.010
oon+0.010
smart+0.010
 court+0.010
Neg logit contributions
outed-0.008
 hats-0.008
packs-0.008
 luck-0.008
by-0.007
Token would
Token ID561
Feature activation+5.05e-03

Pos logit contributions
oc+0.000
oon+0.000
 Oliver+0.000
smart+0.000
 battlefield+0.000
Neg logit contributions
outed-0.000
by-0.000
 luck-0.000
 hats-0.000
 favorite-0.000
Token so
Token ID523
Feature activation+9.39e-03

Pos logit contributions
 best+0.000
 favorite+0.000
 luck+0.000
 absolute+0.000
outed+0.000
Neg logit contributions
oc-0.000
 Oliver-0.000
oon-0.000
Mic-0.000
smart-0.000
Token happy
Token ID3772
Feature activation+8.83e-03

Pos logit contributions
 Oliver+0.015
 battlefield+0.014
oc+0.014
oon+0.014
smart+0.013
Neg logit contributions
outed-0.013
 favorite-0.013
 absolute-0.013
 luck-0.013
 best-0.012
Token and
Token ID290
Feature activation-2.89e-03

Pos logit contributions
oc+0.009
 Oliver+0.009
oon+0.009
smart+0.008
 battlefield+0.008
Neg logit contributions
 hats-0.016
outed-0.016
 luck-0.015
by-0.015
packs-0.015
Token brought
Token ID3181
Feature activation+3.87e-04

Pos logit contributions
 hats+0.003
 favorite+0.003
outed+0.003
 luck+0.003
 prett+0.003
Neg logit contributions
oon-0.005
oc-0.005
smart-0.005
 battlefield-0.005
Mic-0.005
Token the
Token ID262
Feature activation+1.71e-02

Pos logit contributions
 Oliver+0.000
oc+0.000
oon+0.000
smart+0.000
 court+0.000
Neg logit contributions
outed-0.001
 hats-0.001
 luck-0.001
packs-0.001
by-0.001
Token av
Token ID1196
Feature activation+6.41e-02

Pos logit contributions
 Oliver+0.026
oc+0.026
oon+0.026
smart+0.024
 battlefield+0.023
Neg logit contributions
 hats-0.022
 luck-0.022
outed-0.022
 favorite-0.021
by-0.021
Tokenoc
Token ID420
Feature activation+4.98e-02

Pos logit contributions
 Oliver+0.039
oon+0.037
 battlefield+0.035
 court+0.032
ner+0.032
Neg logit contributions
by-0.152
 luck-0.136
bi-0.136
ies-0.135
fl-0.133
Tokenados
Token ID22484
Feature activation+1.78e-02

Pos logit contributions
oon+0.082
 Oliver+0.079
 battlefield+0.074
smart+0.072
 Rupert+0.072
Neg logit contributions
 luck-0.060
by-0.058
outed-0.058
ries-0.055
fl-0.055
Token home
Token ID1363
Feature activation+2.41e-03

Pos logit contributions
oc+0.023
 Oliver+0.023
oon+0.022
smart+0.021
 court+0.021
Neg logit contributions
outed-0.027
 hats-0.027
 luck-0.026
packs-0.026
by-0.026
Token to
Token ID284
Feature activation-3.69e-03

Pos logit contributions
 Oliver+0.003
oc+0.003
oon+0.003
smart+0.003
 battlefield+0.003
Neg logit contributions
 hats-0.003
outed-0.003
 luck-0.003
packs-0.003
by-0.003
Token share
Token ID2648
Feature activation+9.70e-03

Pos logit contributions
 luck+0.004
 hats+0.004
 absolute+0.004
 choice+0.004
 best+0.004
Neg logit contributions
oc-0.006
oon-0.006
smart-0.006
ner-0.006
 battlefield-0.006
Token Maybe
Token ID6674
Feature activation+8.02e-03

Pos logit contributions
 Oliver+0.000
oc+0.000
oon+0.000
smart+0.000
 court+0.000
Neg logit contributions
outed-0.000
 hats-0.000
 luck-0.000
by-0.000
packs-0.000
Token they
Token ID484
Feature activation+1.62e-03

Pos logit contributions
 Oliver+0.009
oc+0.009
 court+0.008
smart+0.008
oon+0.008
Neg logit contributions
outed-0.014
 hats-0.013
by-0.013
packs-0.013
 outfits-0.013
Token could
Token ID714
Feature activation-2.39e-03

Pos logit contributions
 Oliver+0.003
oc+0.003
oon+0.003
smart+0.003
 court+0.003
Neg logit contributions
outed-0.002
 hats-0.002
packs-0.002
 luck-0.002
by-0.002
Token grow
Token ID1663
Feature activation+1.19e-02

Pos logit contributions
 hats+0.004
 luck+0.004
outed+0.004
 favorite+0.004
by+0.003
Neg logit contributions
oc-0.003
 Oliver-0.003
oon-0.003
smart-0.003
 battlefield-0.003
Token more
Token ID517
Feature activation+3.25e-03

Pos logit contributions
oc+0.014
 Oliver+0.014
oon+0.014
smart+0.014
 court+0.013
Neg logit contributions
outed-0.019
 hats-0.018
 coats-0.018
 absolute-0.018
packs-0.018
Token av
Token ID1196
Feature activation+6.40e-02

Pos logit contributions
 Oliver+0.006
oon+0.006
oc+0.006
smart+0.006
 battlefield+0.006
Neg logit contributions
 hats-0.003
 luck-0.003
 favorite-0.003
packs-0.003
by-0.003
Tokenoc
Token ID420
Feature activation+5.48e-02

Pos logit contributions
 Oliver+0.037
oon+0.032
 court+0.031
 Monster+0.028
 battlefield+0.027
Neg logit contributions
by-0.150
 luck-0.141
packs-0.140
ies-0.139
 hats-0.138
Tokenados
Token ID22484
Feature activation+7.76e-03

Pos logit contributions
 Oliver+0.080
oon+0.079
oc+0.075
 battlefield+0.073
smart+0.072
Neg logit contributions
 luck-0.075
outed-0.073
 hats-0.071
by-0.071
 favorite-0.066
Token and
Token ID290
Feature activation-1.40e-02

Pos logit contributions
 Oliver+0.011
oc+0.011
Mic+0.010
smart+0.010
oon+0.010
Neg logit contributions
 hats-0.011
packs-0.011
 luck-0.011
 favorite-0.010
 best-0.010
Token share
Token ID2648
Feature activation-1.30e-03

Pos logit contributions
 hats+0.020
outed+0.019
 luck+0.019
 favorite+0.019
by+0.019
Neg logit contributions
 Oliver-0.020
oon-0.019
oc-0.019
smart-0.018
 court-0.017
Token them
Token ID606
Feature activation-2.02e-02

Pos logit contributions
 hats+0.002
 favorite+0.001
 luck+0.001
packs+0.001
 names+0.001
Neg logit contributions
 Oliver-0.002
oon-0.002
 battlefield-0.002
oc-0.002
Mic-0.002
Token recommendation
Token ID15602
Feature activation-1.18e-02

Pos logit contributions
 luck+0.002
 hats+0.002
outed+0.002
by+0.002
 favorite+0.002
Neg logit contributions
oon-0.002
 Oliver-0.002
oc-0.002
smart-0.002
 court-0.002
Token and
Token ID290
Feature activation-4.45e-03

Pos logit contributions
 hats+0.016
 luck+0.016
outed+0.016
packs+0.016
by+0.016
Neg logit contributions
oc-0.017
 Oliver-0.016
Mic-0.016
oon-0.016
 battlefield-0.015
Token picked
Token ID6497
Feature activation-2.29e-03

Pos logit contributions
 hats+0.006
 luck+0.006
outed+0.006
by+0.006
packs+0.006
Neg logit contributions
oc-0.006
oon-0.006
 Oliver-0.006
smart-0.006
Mic-0.006
Token the
Token ID262
Feature activation+1.49e-02

Pos logit contributions
outed+0.003
 hats+0.003
packs+0.003
 luck+0.003
by+0.003
Neg logit contributions
 Oliver-0.004
oc-0.004
oon-0.003
smart-0.003
 court-0.003
Token right
Token ID826
Feature activation-2.16e-02

Pos logit contributions
 Oliver+0.021
oc+0.021
oon+0.021
smart+0.020
 court+0.019
Neg logit contributions
outed-0.021
 hats-0.020
 luck-0.020
by-0.019
 favorite-0.019
Token av
Token ID1196
Feature activation+6.38e-02

Pos logit contributions
outed+0.025
 hats+0.023
packs+0.022
 absolute+0.022
 coats+0.021
Neg logit contributions
oc-0.037
smart-0.036
 Oliver-0.035
 court-0.035
oon-0.034
Tokenoc
Token ID420
Feature activation+5.18e-02

Pos logit contributions
oon+0.050
 Oliver+0.050
ner+0.046
 battlefield+0.045
 court+0.044
Neg logit contributions
by-0.148
 luck-0.125
bi-0.120
ishes-0.119
ies-0.119
Tokenados
Token ID22484
Feature activation+1.04e-02

Pos logit contributions
oon+0.081
 Oliver+0.079
 battlefield+0.073
 Rupert+0.071
smart+0.070
Neg logit contributions
 luck-0.067
by-0.066
outed-0.065
 hats-0.060
ries-0.059
Token.
Token ID13
Feature activation+3.59e-03

Pos logit contributions
oc+0.017
 Oliver+0.016
oon+0.016
Mic+0.016
 battlefield+0.015
Neg logit contributions
 luck-0.013
packs-0.013
 hats-0.013
 best-0.012
 favorite-0.012
Token
Token ID198
Feature activation+1.46e-03

Pos logit contributions
oon+0.004
 battlefield+0.004
smart+0.004
pping+0.004
oc+0.004
Neg logit contributions
outed-0.006
 de-0.006
 favorite-0.005
packs-0.005
 hats-0.005
Token
Token ID198
Feature activation-1.90e-03

Pos logit contributions
 Oliver+0.002
 battlefield+0.002
oc+0.002
 court+0.002
smart+0.002
Neg logit contributions
by-0.002
outed-0.002
 hats-0.002
add-0.002
 de-0.002
Token tree
Token ID5509
Feature activation-1.56e-02

Pos logit contributions
oc+0.001
 Oliver+0.001
oon+0.001
smart+0.001
 court+0.001
Neg logit contributions
outed-0.001
 hats-0.001
 luck-0.001
packs-0.001
by-0.001
Token could
Token ID714
Feature activation-9.55e-03

Pos logit contributions
outed+0.020
 hats+0.019
 luck+0.019
packs+0.018
by+0.018
Neg logit contributions
 Oliver-0.024
oc-0.024
oon-0.023
smart-0.023
 court-0.022
Token see
Token ID766
Feature activation-7.76e-03

Pos logit contributions
 luck+0.013
 hats+0.013
 favorite+0.013
outed+0.012
 absolute+0.012
Neg logit contributions
oc-0.014
 Oliver-0.014
oon-0.013
smart-0.013
 battlefield-0.013
Token lots
Token ID6041
Feature activation+1.21e-02

Pos logit contributions
 hats+0.012
 luck+0.011
outed+0.011
by+0.011
packs+0.011
Neg logit contributions
 Oliver-0.010
oon-0.010
oc-0.009
 battlefield-0.009
 court-0.009
Token of
Token ID286
Feature activation+3.95e-03

Pos logit contributions
 Oliver+0.016
 battlefield+0.015
Mic+0.015
oon+0.015
oc+0.014
Neg logit contributions
 luck-0.019
by-0.018
 hats-0.018
ies-0.018
 de-0.018
Token av
Token ID1196
Feature activation+6.37e-02

Pos logit contributions
 Oliver+0.007
oon+0.007
oc+0.007
smart+0.006
 battlefield+0.006
Neg logit contributions
 luck-0.004
 hats-0.004
outed-0.004
by-0.004
 favorite-0.004
Tokenoc
Token ID420
Feature activation+4.74e-02

Pos logit contributions
 Oliver+0.042
oon+0.039
 Monster+0.036
 battlefield+0.032
 court+0.031
Neg logit contributions
by-0.144
 luck-0.137
packs-0.133
ies-0.132
ishes-0.129
Tokenados
Token ID22484
Feature activation+1.14e-02

Pos logit contributions
oon+0.076
 Oliver+0.074
 battlefield+0.069
oc+0.069
smart+0.067
Neg logit contributions
 luck-0.060
by-0.056
outed-0.056
ries-0.053
 hats-0.053
Token that
Token ID326
Feature activation+2.17e-03

Pos logit contributions
 Oliver+0.017
oc+0.017
oon+0.016
smart+0.016
Mic+0.015
Neg logit contributions
 luck-0.015
 hats-0.015
packs-0.014
by-0.014
outed-0.014
Token the
Token ID262
Feature activation-8.93e-03

Pos logit contributions
oc+0.003
oon+0.003
 Oliver+0.003
smart+0.003
 court+0.003
Neg logit contributions
outed-0.002
 hats-0.002
 luck-0.002
by-0.002
 favorite-0.002
Token supplier
Token ID22693
Feature activation+4.79e-03

Pos logit contributions
 luck+0.012
 hats+0.012
 favorite+0.012
 best+0.012
by+0.012
Neg logit contributions
oon-0.013
oc-0.013
smart-0.013
 Oliver-0.013
cess-0.012
Tokenongo
Token ID25162
Feature activation+2.55e-02

Pos logit contributions
 Oliver+0.004
oc+0.004
oon+0.004
smart+0.003
 court+0.003
Neg logit contributions
outed-0.004
 hats-0.003
 luck-0.003
by-0.003
packs-0.003
Token didn
Token ID1422
Feature activation+1.74e-02

Pos logit contributions
smart+0.046
 Oliver+0.045
oon+0.045
oc+0.044
 battlefield+0.044
Neg logit contributions
outed-0.028
by-0.026
 favorite-0.025
 hats-0.024
ies-0.023
Token't
Token ID470
Feature activation+7.41e-03

Pos logit contributions
oc+0.017
 battlefield+0.015
 Oliver+0.015
smart+0.014
cess+0.014
Neg logit contributions
outed-0.031
 absolute-0.031
 happened-0.030
 favorite-0.030
 best-0.030
Token like
Token ID588
Feature activation+6.07e-03

Pos logit contributions
 Oliver+0.009
oc+0.009
oon+0.009
 battlefield+0.008
 court+0.008
Neg logit contributions
 hats-0.011
 luck-0.011
by-0.011
packs-0.011
outed-0.011
Token wet
Token ID9583
Feature activation+8.48e-03

Pos logit contributions
oc+0.010
oon+0.010
cess+0.009
 Oliver+0.009
 battlefield+0.008
Neg logit contributions
 happened-0.008
 hats-0.008
 favorite-0.008
 coats-0.007
 luck-0.007
Token av
Token ID1196
Feature activation+6.29e-02

Pos logit contributions
 Oliver+0.013
oc+0.013
oon+0.013
smart+0.013
 court+0.013
Neg logit contributions
outed-0.010
 hats-0.010
 luck-0.010
packs-0.010
by-0.010
Tokenoc
Token ID420
Feature activation+5.18e-02

Pos logit contributions
 Oliver+0.033
oon+0.032
 court+0.029
 battlefield+0.028
ner+0.026
Neg logit contributions
by-0.145
 luck-0.138
ies-0.134
 favorite-0.134
 hats-0.133
Tokenados
Token ID22484
Feature activation+1.01e-02

Pos logit contributions
oon+0.080
 Oliver+0.076
oc+0.075
 battlefield+0.073
smart+0.071
Neg logit contributions
 luck-0.070
outed-0.065
by-0.063
 hats-0.062
 favorite-0.060
Token,
Token ID11
Feature activation+9.60e-03

Pos logit contributions
oc+0.014
oon+0.013
 Oliver+0.013
smart+0.012
 battlefield+0.012
Neg logit contributions
 hats-0.015
 luck-0.015
 favorite-0.014
 happened-0.014
 best-0.014
Token so
Token ID523
Feature activation-1.83e-02

Pos logit contributions
oc+0.009
 Oliver+0.009
oon+0.008
smart+0.008
 court+0.008
Neg logit contributions
outed-0.018
 hats-0.018
 luck-0.017
packs-0.017
by-0.017
Token he
Token ID339
Feature activation+5.07e-03

Pos logit contributions
outed+0.036
packs+0.035
 hats+0.034
 outfits+0.034
 absolute+0.034
Neg logit contributions
 Oliver-0.017
oc-0.016
smart-0.014
oon-0.013
 court-0.013
Token sign
Token ID1051
Feature activation+3.13e-03

Pos logit contributions
 hats+0.004
 favorite+0.004
 luck+0.004
 coats+0.004
 best+0.004
Neg logit contributions
oon-0.006
smart-0.005
 Oliver-0.005
oc-0.005
cess-0.005
Token that
Token ID326
Feature activation-2.75e-04

Pos logit contributions
 Oliver+0.003
oc+0.003
oon+0.003
smart+0.003
 court+0.003
Neg logit contributions
 hats-0.006
outed-0.006
 luck-0.005
packs-0.005
 coats-0.005
Token said
Token ID531
Feature activation+1.01e-02

Pos logit contributions
 hats+0.000
outed+0.000
 happened+0.000
packs+0.000
 coats+0.000
Neg logit contributions
oc-0.000
 Oliver-0.000
smart-0.000
oon-0.000
Mic-0.000
Token "
Token ID366
Feature activation+2.33e-02

Pos logit contributions
oc+0.013
Mic+0.013
 Oliver+0.011
 battlefield+0.011
oon+0.010
Neg logit contributions
 hats-0.017
 happened-0.017
 luck-0.016
 best-0.016
 names-0.016
TokenRE
Token ID2200
Feature activation+1.75e-02

Pos logit contributions
 Oliver+0.033
oc+0.033
oon+0.032
smart+0.031
 court+0.030
Neg logit contributions
outed-0.032
 hats-0.032
 luck-0.031
packs-0.031
by-0.030
TokenVERS
Token ID28884
Feature activation+6.25e-02

Pos logit contributions
 Oliver+0.025
Mic+0.025
ner+0.024
smart+0.024
 although+0.024
Neg logit contributions
 luck-0.023
 hats-0.023
 de-0.021
aws-0.021
 favorite-0.021
TokenE
Token ID36
Feature activation-5.40e-03

Pos logit contributions
 Oliver+0.094
oc+0.093
oon+0.090
smart+0.088
 court+0.087
Neg logit contributions
outed-0.082
 hats-0.079
by-0.076
 luck-0.076
packs-0.076
Token".
Token ID1911
Feature activation+7.12e-03

Pos logit contributions
 luck+0.008
by+0.008
 hats+0.008
outed+0.008
ies+0.008
Neg logit contributions
 Oliver-0.007
smart-0.006
 battlefield-0.006
oc-0.006
 court-0.006
Token L
Token ID406
Feature activation-1.66e-02

Pos logit contributions
oc+0.010
oon+0.009
 Oliver+0.009
smart+0.009
Mic+0.009
Neg logit contributions
 hats-0.010
outed-0.010
packs-0.010
 coats-0.009
 favorite-0.009
Tokenila
Token ID10102
Feature activation+8.56e-03

Pos logit contributions
 hats+0.016
 luck+0.015
outed+0.015
 coats+0.015
 absolute+0.015
Neg logit contributions
oon-0.031
 Oliver-0.030
oc-0.030
smart-0.030
 court-0.029
Token and
Token ID290
Feature activation+1.04e-02

Pos logit contributions
 Oliver+0.015
 battlefield+0.015
Mic+0.014
smart+0.014
 Mickey+0.014
Neg logit contributions
outed-0.010
 hats-0.009
 favorite-0.009
 happened-0.008
 nods-0.008
Token big
Token ID1263
Feature activation-1.05e-02

Pos logit contributions
 hats+0.020
 luck+0.019
 favorite+0.018
outed+0.018
 coats+0.018
Neg logit contributions
 Oliver-0.027
oc-0.027
oon-0.026
smart-0.026
 battlefield-0.024
Token slide
Token ID10649
Feature activation-3.79e-02

Pos logit contributions
 hats+0.013
 coats+0.012
 luck+0.012
 favorite+0.012
packs+0.011
Neg logit contributions
 Oliver-0.017
oon-0.017
oc-0.017
smart-0.017
Mic-0.016
Token and
Token ID290
Feature activation-1.46e-02

Pos logit contributions
outed+0.071
 hats+0.070
 luck+0.069
by+0.068
packs+0.068
Neg logit contributions
oc-0.035
 Oliver-0.034
oon-0.033
smart-0.032
 court-0.031
Token a
Token ID257
Feature activation-2.58e-02

Pos logit contributions
outed+0.021
 hats+0.020
 luck+0.020
packs+0.020
by+0.019
Neg logit contributions
 Oliver-0.020
oc-0.020
oon-0.019
smart-0.019
 court-0.019
Token sand
Token ID6450
Feature activation-4.38e-02

Pos logit contributions
 hats+0.029
outed+0.028
 luck+0.028
by+0.027
 favorite+0.027
Neg logit contributions
 Oliver-0.044
oc-0.043
oon-0.042
smart-0.042
 court-0.039
Tokenpit
Token ID15544
Feature activation-5.66e-02

Pos logit contributions
outed+0.057
 absolute+0.054
by+0.050
 luck+0.049
Sounds+0.048
Neg logit contributions
 court-0.066
oc-0.065
oon-0.065
 Oliver-0.060
smart-0.059
Token.
Token ID13
Feature activation+4.86e-03

Pos logit contributions
outed+0.104
 absolute+0.101
by+0.100
 hats+0.099
 luck+0.098
Neg logit contributions
oc-0.049
 court-0.049
oon-0.046
smart-0.046
 Oliver-0.044
Token
Token ID198
Feature activation+4.66e-03

Pos logit contributions
oc+0.007
smart+0.007
oon+0.007
 Oliver+0.007
pping+0.007
Neg logit contributions
outed-0.006
 favorite-0.006
 hats-0.006
 names-0.006
 absolute-0.006
Token
Token ID198
Feature activation+1.96e-03

Pos logit contributions
 Oliver+0.007
 battlefield+0.007
smart+0.007
oc+0.007
pping+0.007
Neg logit contributions
outed-0.005
by-0.005
 favorite-0.005
packs-0.005
 hats-0.005
TokenThe
Token ID464
Feature activation+2.82e-03

Pos logit contributions
 Oliver+0.003
smart+0.003
oc+0.003
 Owl+0.003
cess+0.003
Neg logit contributions
Sounds-0.002
 hats-0.002
We-0.002
OK-0.002
outed-0.002
Token children
Token ID1751
Feature activation-2.51e-03

Pos logit contributions
 Oliver+0.005
oc+0.004
oon+0.004
smart+0.004
Mic+0.004
Neg logit contributions
 hats-0.004
outed-0.004
 favorite-0.004
 luck-0.004
 best-0.004
Token on
Token ID319
Feature activation+4.97e-03

Pos logit contributions
outed+0.008
 hats+0.007
by+0.007
 luck+0.007
 absolute+0.007
Neg logit contributions
oon-0.005
oc-0.005
 Oliver-0.004
 court-0.004
smart-0.004
Token the
Token ID262
Feature activation-8.89e-03

Pos logit contributions
oc+0.005
 Oliver+0.005
oon+0.005
smart+0.004
 battlefield+0.004
Neg logit contributions
 hats-0.009
outed-0.009
 luck-0.009
packs-0.009
 coats-0.009
Token ground
Token ID2323
Feature activation-1.29e-02

Pos logit contributions
outed+0.012
 hats+0.012
 luck+0.011
packs+0.011
by+0.011
Neg logit contributions
 Oliver-0.013
oc-0.013
oon-0.013
smart-0.012
 court-0.012
Token and
Token ID290
Feature activation-9.06e-03

Pos logit contributions
outed+0.019
 hats+0.019
 luck+0.018
packs+0.018
by+0.018
Neg logit contributions
 Oliver-0.017
oc-0.017
oon-0.017
smart-0.016
 court-0.016
Token an
Token ID281
Feature activation-1.07e-02

Pos logit contributions
 hats+0.011
outed+0.011
 favorite+0.010
packs+0.010
 luck+0.010
Neg logit contributions
oc-0.015
oon-0.014
 Oliver-0.014
smart-0.014
Mic-0.013
Token idea
Token ID2126
Feature activation-5.20e-02

Pos logit contributions
outed+0.014
 hats+0.014
 luck+0.013
packs+0.013
by+0.013
Neg logit contributions
 Oliver-0.016
oc-0.016
oon-0.016
smart-0.015
 court-0.015
Token popped
Token ID22928
Feature activation-1.83e-02

Pos logit contributions
outed+0.086
 prett+0.081
 coolest+0.081
by+0.080
 absolute+0.080
Neg logit contributions
smart-0.062
 Oliver-0.057
 court-0.057
oon-0.056
oc-0.056
Token into
Token ID656
Feature activation+9.20e-04

Pos logit contributions
outed+0.026
 hats+0.026
 luck+0.025
packs+0.025
by+0.025
Neg logit contributions
oc-0.025
 Oliver-0.025
oon-0.024
smart-0.024
 court-0.023
Token her
Token ID607
Feature activation-4.84e-03

Pos logit contributions
 Oliver+0.001
oc+0.001
oon+0.001
smart+0.001
 court+0.001
Neg logit contributions
 hats-0.001
outed-0.001
 luck-0.001
packs-0.001
 coats-0.001
Token head
Token ID1182
Feature activation-1.49e-02

Pos logit contributions
outed+0.007
 hats+0.007
 luck+0.006
by+0.006
 absolute+0.006
Neg logit contributions
oc-0.007
 Oliver-0.006
 court-0.006
oon-0.006
smart-0.006
Token.
Token ID13
Feature activation+2.05e-03

Pos logit contributions
outed+0.020
 hats+0.020
packs+0.019
 luck+0.019
by+0.019
Neg logit contributions
 Oliver-0.022
oc-0.022
oon-0.021
smart-0.021
 court-0.020
Token a
Token ID257
Feature activation-3.40e-03

Pos logit contributions
outed+0.002
packs+0.002
Deal+0.002
bi+0.002
 absolute+0.002
Neg logit contributions
 Oliver-0.001
oc-0.001
 defeat-0.001
 free-0.001
 defeated-0.001
Token snow
Token ID6729
Feature activation-1.17e-02

Pos logit contributions
outed+0.005
packs+0.004
 hats+0.004
 luck+0.004
 absolute+0.004
Neg logit contributions
oc-0.005
 Oliver-0.005
 court-0.005
oon-0.005
 battlefield-0.005
Tokenman
Token ID805
Feature activation-3.83e-03

Pos logit contributions
outed+0.020
 absolute+0.018
packs+0.018
 passports+0.017
 luck+0.017
Neg logit contributions
oc-0.016
oon-0.014
 Oliver-0.013
 fetch-0.012
 defeat-0.012
Token and
Token ID290
Feature activation-9.69e-03

Pos logit contributions
outed+0.008
 hats+0.008
 luck+0.007
packs+0.007
by+0.007
Neg logit contributions
oc-0.003
 Oliver-0.003
oon-0.003
smart-0.003
 court-0.003
Token a
Token ID257
Feature activation-2.05e-02

Pos logit contributions
outed+0.014
 luck+0.013
by+0.013
 hats+0.013
packs+0.013
Neg logit contributions
 Oliver-0.013
oc-0.013
oon-0.012
smart-0.012
 court-0.012
Token snowball
Token ID46275
Feature activation-5.18e-02

Pos logit contributions
outed+0.021
 hats+0.020
 luck+0.019
packs+0.019
by+0.019
Neg logit contributions
oc-0.036
 Oliver-0.036
oon-0.035
smart-0.035
 court-0.034
Token and
Token ID290
Feature activation-1.71e-02

Pos logit contributions
outed+0.093
 absolute+0.087
packs+0.087
 luck+0.086
 hats+0.085
Neg logit contributions
oc-0.058
 Oliver-0.053
oon-0.051
smart-0.050
 court-0.050
Token a
Token ID257
Feature activation-2.89e-02

Pos logit contributions
outed+0.026
 luck+0.024
by+0.024
packs+0.024
 hats+0.024
Neg logit contributions
 Oliver-0.022
oc-0.022
smart-0.020
oon-0.020
 court-0.020
Token snow
Token ID6729
Feature activation-3.21e-02

Pos logit contributions
outed+0.031
 hats+0.029
packs+0.028
 luck+0.028
by+0.028
Neg logit contributions
oc-0.051
 Oliver-0.051
oon-0.049
smart-0.048
 court-0.048
Token angel
Token ID18304
Feature activation-1.44e-02

Pos logit contributions
outed+0.056
 absolute+0.054
packs+0.050
 luck+0.050
 passports+0.049
Neg logit contributions
oc-0.043
oon-0.035
 Oliver-0.033
 Owl-0.031
 fetch-0.031
Token.
Token ID13
Feature activation-1.77e-03

Pos logit contributions
outed+0.026
 absolute+0.024
 luck+0.024
 hats+0.024
 coats+0.023
Neg logit contributions
oc-0.017
 Oliver-0.014
oon-0.014
smart-0.014
 court-0.013
Token snow
Token ID6729
Feature activation-1.40e-02

Pos logit contributions
oc+0.006
 Oliver+0.005
 court+0.005
 defeat+0.005
 battlefield+0.005
Neg logit contributions
outed-0.004
packs-0.003
anced-0.003
 hats-0.003
 absolute-0.003
Tokenman
Token ID805
Feature activation-3.39e-03

Pos logit contributions
outed+0.025
 absolute+0.022
packs+0.021
 passports+0.021
 outfits+0.021
Neg logit contributions
oc-0.019
 Oliver-0.017
oon-0.017
 fetch-0.015
 Owl-0.015
Token and
Token ID290
Feature activation-1.62e-02

Pos logit contributions
 hats+0.006
 luck+0.006
outed+0.006
packs+0.006
by+0.005
Neg logit contributions
 Oliver-0.004
oc-0.004
oon-0.004
smart-0.003
 court-0.003
Token have
Token ID423
Feature activation-3.61e-03

Pos logit contributions
 hats+0.023
outed+0.022
 coats+0.022
packs+0.022
 luck+0.022
Neg logit contributions
oc-0.023
oon-0.022
 Oliver-0.022
smart-0.021
 court-0.021
Token a
Token ID257
Feature activation-1.25e-02

Pos logit contributions
outed+0.007
uttered+0.006
uffy+0.006
ies+0.006
by+0.006
Neg logit contributions
 defeated-0.004
 Oliver-0.004
oc-0.004
 fetch-0.004
smart-0.004
Token snowball
Token ID46275
Feature activation-5.12e-02

Pos logit contributions
outed+0.016
packs+0.014
ays+0.013
 absolute+0.013
anced+0.013
Neg logit contributions
oc-0.021
 Oliver-0.020
 court-0.019
 fetch-0.018
 battlefield-0.018
Token fight
Token ID1907
Feature activation-2.10e-02

Pos logit contributions
outed+0.090
 absolute+0.086
 luck+0.083
 hats+0.082
packs+0.082
Neg logit contributions
oc-0.057
 Oliver-0.054
 court-0.052
smart-0.050
oon-0.050
Token.
Token ID13
Feature activation-2.01e-03

Pos logit contributions
 hats+0.029
 luck+0.027
outed+0.027
packs+0.027
by+0.027
Neg logit contributions
oc-0.031
 Oliver-0.030
oon-0.030
Mic-0.029
smart-0.028
Token They
Token ID1119
Feature activation-1.01e-03

Pos logit contributions
outed+0.004
 luck+0.004
 hats+0.004
packs+0.004
by+0.004
Neg logit contributions
 Oliver-0.002
oc-0.002
oon-0.001
 court-0.001
smart-0.001
Token put
Token ID1234
Feature activation+1.66e-03

Pos logit contributions
outed+0.001
 hats+0.001
by+0.001
 coats+0.001
 absolute+0.001
Neg logit contributions
oc-0.002
oon-0.002
smart-0.002
 Oliver-0.002
 battlefield-0.002
Token on
Token ID319
Feature activation-9.37e-03

Pos logit contributions
 Oliver+0.002
oc+0.001
 fetch+0.001
smart+0.001
on+0.001
Neg logit contributions
outed-0.003
 absolute-0.003
by-0.003
 outfits-0.003
 fault-0.003
Token kids
Token ID3988
Feature activation+3.68e-04

Pos logit contributions
 Oliver+0.011
oc+0.011
oon+0.011
 court+0.011
smart+0.010
Neg logit contributions
outed-0.012
packs-0.011
 hats-0.011
by-0.011
 coats-0.011
Token fighting
Token ID4330
Feature activation-1.44e-02

Pos logit contributions
oc+0.000
 Oliver+0.000
oon+0.000
Mic+0.000
smart+0.000
Neg logit contributions
outed-0.001
 hats-0.001
packs-0.001
 luck-0.001
 coats-0.001
Token and
Token ID290
Feature activation-9.44e-03

Pos logit contributions
outed+0.026
 hats+0.025
 luck+0.025
packs+0.025
 coats+0.024
Neg logit contributions
oc-0.016
 Oliver-0.015
oon-0.014
smart-0.014
Mic-0.013
Token had
Token ID550
Feature activation-4.67e-03

Pos logit contributions
outed+0.012
 hats+0.011
 happened+0.011
ies+0.011
by+0.010
Neg logit contributions
oc-0.017
oon-0.015
Mic-0.015
 battlefield-0.015
 Oliver-0.014
Token an
Token ID281
Feature activation-1.98e-03

Pos logit contributions
outed+0.007
 hats+0.007
 luck+0.007
packs+0.007
by+0.007
Neg logit contributions
oc-0.006
 Oliver-0.006
oon-0.006
smart-0.006
 court-0.005
Token idea
Token ID2126
Feature activation-5.06e-02

Pos logit contributions
outed+0.001
by+0.001
packs+0.001
 hats+0.001
 outfits+0.001
Neg logit contributions
 Oliver-0.004
 court-0.004
oc-0.004
oon-0.004
smart-0.004
Token to
Token ID284
Feature activation-4.08e-03

Pos logit contributions
outed+0.085
 hats+0.081
by+0.081
 absolute+0.080
 luck+0.079
Neg logit contributions
 Oliver-0.058
smart-0.057
oc-0.057
oon-0.056
 court-0.055
Token improve
Token ID2987
Feature activation+9.80e-03

Pos logit contributions
 hats+0.005
 choice+0.005
 luck+0.005
 coats+0.005
 idea+0.005
Neg logit contributions
oc-0.007
smart-0.006
oon-0.006
 Oliver-0.006
 battlefield-0.006
Token the
Token ID262
Feature activation-2.58e-03

Pos logit contributions
oc+0.016
oon+0.015
Mic+0.015
 Oliver+0.015
 battlefield+0.014
Neg logit contributions
 hats-0.013
 luck-0.012
packs-0.012
 coats-0.012
 outfits-0.012
Token situation
Token ID3074
Feature activation-1.38e-02

Pos logit contributions
outed+0.004
packs+0.004
 hats+0.004
 absolute+0.004
 coats+0.004
Neg logit contributions
 court-0.003
oc-0.003
 Oliver-0.003
oon-0.003
 battlefield-0.003
Token.
Token ID13
Feature activation+4.42e-03

Pos logit contributions
 hats+0.017
packs+0.017
 luck+0.017
outed+0.017
by+0.016
Neg logit contributions
oc-0.022
 Oliver-0.022
oon-0.021
Mic-0.020
 battlefield-0.020
Token replied
Token ID8712
Feature activation-1.45e-02

Pos logit contributions
oc+0.007
oon+0.007
 Oliver+0.007
smart+0.007
 battlefield+0.006
Neg logit contributions
outed-0.007
 hats-0.007
 luck-0.006
by-0.006
 absolute-0.006
Token Jim
Token ID5395
Feature activation-1.11e-02

Pos logit contributions
outed+0.023
 hats+0.023
 luck+0.022
by+0.022
packs+0.022
Neg logit contributions
oc-0.018
oon-0.017
 Oliver-0.017
smart-0.016
 court-0.015
Token.
Token ID13
Feature activation+5.67e-03

Pos logit contributions
outed+0.014
by+0.014
 hats+0.014
 luck+0.014
 favorite+0.013
Neg logit contributions
oon-0.017
 Oliver-0.016
oc-0.016
 battlefield-0.016
 court-0.016
Token
Token ID198
Feature activation-1.67e-03

Pos logit contributions
oc+0.008
oon+0.008
smart+0.008
pping+0.008
 defeat+0.007
Neg logit contributions
outed-0.008
 hats-0.007
bi-0.007
 de-0.007
 nods-0.007
Token
Token ID198
Feature activation-4.09e-03

Pos logit contributions
by+0.002
ara+0.002
outed+0.002
 hats+0.002
aws+0.002
Neg logit contributions
 Oliver-0.002
smart-0.002
 battlefield-0.002
pping-0.002
 courtroom-0.002
TokenDays
Token ID38770
Feature activation-5.02e-02

Pos logit contributions
Deal+0.004
OK+0.004
by+0.004
aws+0.004
ara+0.004
Neg logit contributions
 Oliver-0.007
smart-0.006
ner-0.006
 battlefield-0.006
oon-0.006
Token passed
Token ID3804
Feature activation+1.91e-02

Pos logit contributions
 absolute+0.075
 outfits+0.074
packs+0.072
 hats+0.072
 coats+0.071
Neg logit contributions
 defeated-0.067
 Oliver-0.064
"-0.062
oon-0.062
 court-0.061
Token and
Token ID290
Feature activation-1.08e-03

Pos logit contributions
oc+0.025
 Oliver+0.024
oon+0.024
smart+0.023
Mic+0.023
Neg logit contributions
by-0.029
outed-0.029
 hats-0.028
 luck-0.028
packs-0.027
Token Bob
Token ID5811
Feature activation-9.55e-03

Pos logit contributions
outed+0.002
 hats+0.002
 luck+0.002
by+0.002
 coats+0.002
Neg logit contributions
oc-0.001
 Oliver-0.001
oon-0.001
smart-0.001
 court-0.001
Token noticed
Token ID6810
Feature activation-1.87e-03

Pos logit contributions
outed+0.010
by+0.010
 hats+0.009
 favorite+0.009
 luck+0.009
Neg logit contributions
smart-0.017
oc-0.017
oon-0.017
 Oliver-0.016
Mic-0.016
Token something
Token ID1223
Feature activation-9.82e-03

Pos logit contributions
outed+0.003
 hats+0.003
 luck+0.003
by+0.003
 favorite+0.003
Neg logit contributions
oc-0.002
 Oliver-0.002
oon-0.002
smart-0.002
Mic-0.002
Token,
Token ID11
Feature activation+8.31e-03

Pos logit contributions
 hats+0.010
outed+0.010
 luck+0.010
by+0.010
packs+0.010
Neg logit contributions
oc-0.005
oon-0.005
 Oliver-0.005
 battlefield-0.005
Mic-0.005
Token
Token ID6184
Feature activation-1.53e-02

Pos logit contributions
oc+0.012
oon+0.011
 Oliver+0.011
smart+0.011
 battlefield+0.011
Neg logit contributions
 hats-0.012
outed-0.011
packs-0.011
 coats-0.011
 luck-0.011
Token
Token ID95
Feature activation-1.46e-02

Pos logit contributions
 hats+0.022
outed+0.021
 coats+0.021
 absolute+0.020
 favorite+0.019
Neg logit contributions
 Oliver-0.020
oc-0.020
smart-0.020
oon-0.019
 battlefield-0.018
Token
Token ID26391
Feature activation-1.44e-02

Pos logit contributions
 hats+0.020
Deal+0.019
bows+0.019
 coats+0.019
outed+0.019
Neg logit contributions
 Oliver-0.019
smart-0.018
oc-0.017
 battlefield-0.017
 Owl-0.016
Token
Token ID129
Feature activation+5.05e-03

Pos logit contributions
 hats+0.018
packs+0.018
outed+0.017
 coats+0.017
by+0.017
Neg logit contributions
 Oliver-0.022
 battlefield-0.021
smart-0.021
 court-0.021
oon-0.021
Token
Token ID241
Feature activation-5.01e-02

Pos logit contributions
 Oliver+0.007
smart+0.007
oon+0.007
oc+0.007
 Owl+0.007
Neg logit contributions
 hats-0.007
 coats-0.006
aws-0.006
 favorite-0.006
outed-0.006
TokenSam
Token ID16305
Feature activation-2.32e-03

Pos logit contributions
outed+0.088
 luck+0.086
packs+0.082
ishes+0.082
by+0.081
Neg logit contributions
oc-0.062
"-0.054
oon-0.054
 Oliver-0.050
smart-0.049
Token,
Token ID11
Feature activation-4.29e-03

Pos logit contributions
 hats+0.004
by+0.004
outed+0.004
 coats+0.003
 luck+0.003
Neg logit contributions
 battlefield-0.003
 Oliver-0.003
 court-0.003
oon-0.003
oc-0.003
Token you
Token ID345
Feature activation+2.04e-03

Pos logit contributions
 hats+0.006
outed+0.006
 luck+0.006
 coats+0.006
 favorite+0.006
Neg logit contributions
oc-0.006
 Oliver-0.006
oon-0.006
smart-0.005
 battlefield-0.005
Token dropped
Token ID5710
Feature activation-1.05e-02

Pos logit contributions
 battlefield+0.004
 court+0.004
oc+0.003
oon+0.003
smart+0.003
Neg logit contributions
 hats-0.002
 coats-0.002
 luck-0.002
 names-0.002
 absolute-0.002
Token your
Token ID534
Feature activation-5.90e-03

Pos logit contributions
 hats+0.016
 coats+0.015
 luck+0.015
 favorite+0.014
outed+0.014
Neg logit contributions
oc-0.016
oon-0.016
cess-0.014
 battlefield-0.014
Mic-0.014
Token,
Token ID11
Feature activation-8.04e-03

Pos logit contributions
outed+0.054
 hats+0.053
 luck+0.052
packs+0.052
by+0.052
Neg logit contributions
oc-0.028
 Oliver-0.028
oon-0.026
smart-0.025
 court-0.025
Token a
Token ID257
Feature activation-1.64e-02

Pos logit contributions
 hats+0.011
outed+0.011
packs+0.010
 luck+0.010
 coats+0.010
Neg logit contributions
oc-0.012
 Oliver-0.012
oon-0.011
smart-0.011
 court-0.011
Token slide
Token ID10649
Feature activation-3.91e-02

Pos logit contributions
 hats+0.020
outed+0.018
 luck+0.018
 coats+0.018
packs+0.018
Neg logit contributions
 Oliver-0.027
oc-0.027
smart-0.026
oon-0.026
 battlefield-0.024
Token and
Token ID290
Feature activation-2.28e-02

Pos logit contributions
outed+0.086
 luck+0.084
 hats+0.083
 absolute+0.083
by+0.083
Neg logit contributions
oc-0.024
 Oliver-0.021
oon-0.021
smart-0.020
 court-0.020
Token a
Token ID257
Feature activation-2.82e-02

Pos logit contributions
outed+0.039
by+0.036
 luck+0.035
packs+0.035
 absolute+0.034
Neg logit contributions
 Oliver-0.027
 court-0.026
oc-0.025
oon-0.024
smart-0.024
Token sandbox
Token ID35204
Feature activation-5.01e-02

Pos logit contributions
outed+0.031
 hats+0.030
 luck+0.029
packs+0.029
by+0.028
Neg logit contributions
oc-0.048
 Oliver-0.048
oon-0.046
smart-0.045
 court-0.045
Token.
Token ID13
Feature activation-5.26e-03

Pos logit contributions
outed+0.093
 absolute+0.089
by+0.088
xc+0.085
 luck+0.084
Neg logit contributions
oc-0.048
 court-0.047
oon-0.044
smart-0.042
"-0.041
Token Sometimes
Token ID8975
Feature activation+2.47e-03

Pos logit contributions
 luck+0.009
by+0.009
outed+0.009
 hats+0.008
 outfits+0.008
Neg logit contributions
oc-0.006
 court-0.006
 Oliver-0.006
smart-0.005
oon-0.005
Token they
Token ID484
Feature activation+4.43e-03

Pos logit contributions
 Oliver+0.003
 court+0.003
oc+0.003
"+0.003
smart+0.003
Neg logit contributions
outed-0.004
by-0.004
 absolute-0.004
 luck-0.004
add-0.004
Token pretend
Token ID16614
Feature activation-1.08e-02

Pos logit contributions
oc+0.007
oon+0.007
 Oliver+0.007
smart+0.007
cess+0.007
Neg logit contributions
 hats-0.005
packs-0.005
by-0.005
 favorite-0.005
outed-0.005
Token to
Token ID284
Feature activation-3.41e-03

Pos logit contributions
outed+0.018
 luck+0.017
 absolute+0.017
by+0.017
 hats+0.017
Neg logit contributions
 Oliver-0.012
oc-0.012
smart-0.012
 court-0.012
oon-0.012
Token in
Token ID287
Feature activation-4.45e-03

Pos logit contributions
outed+0.019
 hats+0.019
 luck+0.018
packs+0.018
by+0.018
Neg logit contributions
 Oliver-0.015
oc-0.015
oon-0.015
smart-0.014
 court-0.014
Token the
Token ID262
Feature activation-1.35e-02

Pos logit contributions
 hats+0.007
 luck+0.006
packs+0.006
 coats+0.006
by+0.006
Neg logit contributions
oon-0.006
 Oliver-0.006
 battlefield-0.006
oc-0.005
ner-0.005
Token back
Token ID736
Feature activation-2.97e-02

Pos logit contributions
outed+0.018
 hats+0.017
packs+0.016
 luck+0.016
by+0.016
Neg logit contributions
oc-0.020
 Oliver-0.020
oon-0.019
 court-0.019
smart-0.019
Token of
Token ID286
Feature activation-3.52e-03

Pos logit contributions
outed+0.047
 hats+0.047
packs+0.045
 luck+0.045
by+0.045
Neg logit contributions
 Oliver-0.036
oc-0.036
oon-0.035
smart-0.034
 court-0.033
Token his
Token ID465
Feature activation-1.11e-02

Pos logit contributions
 hats+0.005
outed+0.005
 luck+0.005
packs+0.005
by+0.005
Neg logit contributions
oc-0.005
 Oliver-0.005
oon-0.004
smart-0.004
 court-0.004
Token pickup
Token ID19422
Feature activation-4.98e-02

Pos logit contributions
outed+0.016
 hats+0.015
 luck+0.015
packs+0.015
by+0.014
Neg logit contributions
oc-0.016
 Oliver-0.016
oon-0.015
smart-0.015
 court-0.015
Token truck
Token ID7779
Feature activation-3.73e-02

Pos logit contributions
outed+0.061
 hats+0.059
 luck+0.057
packs+0.056
by+0.056
Neg logit contributions
oc-0.079
 Oliver-0.079
oon-0.076
 court-0.074
smart-0.074
Token.
Token ID13
Feature activation-8.34e-04

Pos logit contributions
 hats+0.051
outed+0.051
packs+0.049
by+0.048
 luck+0.048
Neg logit contributions
 Oliver-0.053
oc-0.052
oon-0.052
smart-0.051
 court-0.048
Token He
Token ID679
Feature activation-8.95e-04

Pos logit contributions
 hats+0.001
 coats+0.001
 favorite+0.001
 names+0.001
outed+0.001
Neg logit contributions
oon-0.001
smart-0.001
Mic-0.001
ner-0.001
 defeated-0.001
Token drove
Token ID10357
Feature activation+5.20e-03

Pos logit contributions
outed+0.001
 hats+0.001
 luck+0.001
packs+0.001
by+0.001
Neg logit contributions
oc-0.001
 Oliver-0.001
oon-0.001
smart-0.001
 court-0.001
Token to
Token ID284
Feature activation-5.99e-03

Pos logit contributions
oon+0.009
 Oliver+0.008
oc+0.008
Mic+0.008
cess+0.008
Neg logit contributions
 hats-0.007
 favorite-0.007
 coats-0.007
 luck-0.007
by-0.007
Token,
Token ID11
Feature activation+5.10e-03

Pos logit contributions
 Oliver+0.002
 court+0.002
oc+0.002
smart+0.002
oon+0.002
Neg logit contributions
outed-0.011
 absolute-0.010
packs-0.010
 hats-0.010
by-0.010
Token and
Token ID290
Feature activation-9.98e-03

Pos logit contributions
oc+0.005
 Oliver+0.005
oon+0.004
smart+0.004
 court+0.004
Neg logit contributions
outed-0.010
 hats-0.010
 luck-0.009
packs-0.009
by-0.009
Token she
Token ID673
Feature activation-9.76e-03

Pos logit contributions
outed+0.015
 hats+0.015
packs+0.015
 luck+0.015
by+0.014
Neg logit contributions
 Oliver-0.013
oc-0.013
oon-0.012
smart-0.012
 court-0.012
Token had
Token ID550
Feature activation-3.55e-03

Pos logit contributions
outed+0.015
 hats+0.015
packs+0.015
 luck+0.015
 absolute+0.014
Neg logit contributions
 Oliver-0.012
oc-0.012
oon-0.011
smart-0.011
 court-0.011
Token an
Token ID281
Feature activation-5.29e-03

Pos logit contributions
outed+0.005
 hats+0.005
packs+0.005
 luck+0.005
by+0.005
Neg logit contributions
 Oliver-0.005
oc-0.005
oon-0.005
smart-0.004
 court-0.004
Token idea
Token ID2126
Feature activation-4.96e-02

Pos logit contributions
by+0.004
packs+0.004
outed+0.004
 hats+0.004
fl+0.003
Neg logit contributions
 court-0.010
oc-0.010
 Oliver-0.010
oon-0.010
smart-0.010
Token.
Token ID13
Feature activation+3.80e-04

Pos logit contributions
outed+0.082
 hats+0.078
by+0.077
 absolute+0.077
 luck+0.076
Neg logit contributions
 Oliver-0.059
oc-0.058
smart-0.058
oon-0.056
 court-0.054
Token
Token ID198
Feature activation-9.00e-03

Pos logit contributions
oc+0.000
oon+0.000
 Oliver+0.000
smart+0.000
 battlefield+0.000
Neg logit contributions
outed-0.001
 hats-0.001
packs-0.001
 favorite-0.001
 coats-0.001
Token
Token ID198
Feature activation-1.04e-02

Pos logit contributions
outed+0.017
 hats+0.017
by+0.016
packs+0.016
 favorite+0.016
Neg logit contributions
 Oliver-0.008
oc-0.008
oon-0.008
smart-0.007
 battlefield-0.007
Token"
Token ID1
Feature activation-1.63e-02

Pos logit contributions
 hats+0.015
outed+0.014
 coats+0.014
 favorite+0.014
packs+0.014
Neg logit contributions
 Oliver-0.015
oc-0.015
smart-0.014
oon-0.014
 battlefield-0.013
TokenLet
Token ID5756
Feature activation+2.08e-03

Pos logit contributions
outed+0.021
 luck+0.020
 hats+0.020
packs+0.020
by+0.020
Neg logit contributions
 Oliver-0.025
oc-0.025
oon-0.025
 court-0.023
smart-0.023
Token around
Token ID1088
Feature activation+5.35e-03

Pos logit contributions
 Oliver+0.014
oc+0.014
oon+0.013
smart+0.013
 court+0.013
Neg logit contributions
outed-0.019
 hats-0.018
by-0.018
 luck-0.018
packs-0.018
Token and
Token ID290
Feature activation-1.08e-02

Pos logit contributions
Mic+0.008
smart+0.007
oon+0.007
oc+0.007
 Oliver+0.007
Neg logit contributions
 hats-0.007
 ones-0.007
 favorite-0.007
by-0.007
 luck-0.007
Token made
Token ID925
Feature activation-8.60e-03

Pos logit contributions
 hats+0.014
 favorite+0.013
by+0.013
 coats+0.012
 prett+0.012
Neg logit contributions
oon-0.018
oc-0.018
smart-0.018
Mic-0.017
 court-0.016
Token a
Token ID257
Feature activation-6.92e-03

Pos logit contributions
packs+0.016
outed+0.016
 absolute+0.015
bi+0.014
by+0.014
Neg logit contributions
oc-0.008
 Oliver-0.008
 defeated-0.008
oon-0.007
 defeat-0.007
Token big
Token ID1263
Feature activation-8.55e-04

Pos logit contributions
outed+0.010
 hats+0.010
packs+0.009
 luck+0.009
 coats+0.009
Neg logit contributions
oc-0.010
 Oliver-0.009
oon-0.009
 court-0.009
smart-0.009
Token snowball
Token ID46275
Feature activation-4.96e-02

Pos logit contributions
 hats+0.001
outed+0.001
 luck+0.001
by+0.001
 coats+0.001
Neg logit contributions
 Oliver-0.001
oon-0.001
oc-0.001
smart-0.001
 court-0.001
Token.
Token ID13
Feature activation-8.39e-05

Pos logit contributions
outed+0.085
packs+0.079
 absolute+0.078
 hats+0.078
 luck+0.077
Neg logit contributions
oc-0.059
 Oliver-0.056
 court-0.052
oon-0.052
smart-0.052
Token He
Token ID679
Feature activation+1.65e-03

Pos logit contributions
outed+0.000
 favorite+0.000
 hats+0.000
 coats+0.000
 de+0.000
Neg logit contributions
oon-0.000
smart-0.000
oc-0.000
 battlefield-0.000
 Oliver-0.000
Token laughed
Token ID13818
Feature activation-1.04e-02

Pos logit contributions
 Oliver+0.003
smart+0.003
oon+0.003
oc+0.003
 court+0.003
Neg logit contributions
 hats-0.002
 favorite-0.002
outed-0.002
by-0.002
 coats-0.002
Token and
Token ID290
Feature activation+7.27e-04

Pos logit contributions
 favorite+0.017
 hats+0.017
 luck+0.017
outed+0.016
 best+0.016
Neg logit contributions
oc-0.013
 Oliver-0.013
oon-0.012
smart-0.012
 court-0.012
Token played
Token ID2826
Feature activation-3.11e-04

Pos logit contributions
oon+0.001
oc+0.001
smart+0.001
 battlefield+0.001
 court+0.001
Neg logit contributions
 hats-0.001
outed-0.001
 favorite-0.001
 coats-0.001
 luck-0.001
Token,
Token ID11
Feature activation-8.41e-03

Pos logit contributions
outed+0.056
 hats+0.055
 luck+0.054
packs+0.054
by+0.053
Neg logit contributions
 Oliver-0.029
oc-0.029
oon-0.028
smart-0.027
 court-0.026
Token a
Token ID257
Feature activation-1.67e-02

Pos logit contributions
 hats+0.012
outed+0.011
packs+0.011
 coats+0.011
 luck+0.011
Neg logit contributions
oc-0.012
 Oliver-0.012
oon-0.012
smart-0.011
 court-0.011
Token slide
Token ID10649
Feature activation-3.92e-02

Pos logit contributions
 hats+0.019
outed+0.018
 luck+0.017
 coats+0.017
packs+0.017
Neg logit contributions
 Oliver-0.028
oc-0.028
smart-0.028
oon-0.027
 battlefield-0.026
Token and
Token ID290
Feature activation-2.56e-02

Pos logit contributions
outed+0.083
 luck+0.081
 hats+0.081
by+0.080
 absolute+0.080
Neg logit contributions
oc-0.027
 Oliver-0.025
oon-0.024
smart-0.023
 court-0.023
Token a
Token ID257
Feature activation-2.78e-02

Pos logit contributions
outed+0.048
by+0.044
 luck+0.043
 fault+0.042
uffy+0.042
Neg logit contributions
 Oliver-0.026
 court-0.026
 fetch-0.024
oc-0.023
oon-0.022
Token sandbox
Token ID35204
Feature activation-4.96e-02

Pos logit contributions
outed+0.028
 hats+0.026
packs+0.025
 luck+0.025
by+0.025
Neg logit contributions
oc-0.050
 Oliver-0.050
oon-0.049
 court-0.048
smart-0.047
Token.
Token ID13
Feature activation-1.00e-03

Pos logit contributions
outed+0.093
 absolute+0.090
by+0.088
xc+0.085
 luck+0.084
Neg logit contributions
oc-0.047
 court-0.045
oon-0.044
"-0.040
smart-0.040
Token They
Token ID1119
Feature activation+3.84e-04

Pos logit contributions
outed+0.002
 luck+0.002
 hats+0.001
by+0.001
packs+0.001
Neg logit contributions
 Oliver-0.001
oc-0.001
oon-0.001
 court-0.001
 battlefield-0.001
Token are
Token ID389
Feature activation-1.37e-02

Pos logit contributions
 Oliver+0.001
oc+0.001
oon+0.001
smart+0.000
 court+0.000
Neg logit contributions
outed-0.001
 hats-0.001
 luck-0.001
packs-0.001
by-0.001
Token very
Token ID845
Feature activation+1.05e-03

Pos logit contributions
outed+0.022
 hats+0.021
by+0.021
packs+0.021
 luck+0.021
Neg logit contributions
 Oliver-0.017
oc-0.016
oon-0.016
smart-0.015
 court-0.015
Token organized
Token ID8389
Feature activation+3.89e-03

Pos logit contributions
oc+0.001
 Oliver+0.001
oon+0.001
smart+0.001
 battlefield+0.001
Neg logit contributions
outed-0.002
 hats-0.002
 luck-0.001
 favorite-0.001
packs-0.001
Token feel
Token ID1254
Feature activation+1.12e-02

Pos logit contributions
oc+0.005
smart+0.005
 Oliver+0.005
oon+0.005
Mic+0.005
Neg logit contributions
 hats-0.004
 luck-0.004
 absolute-0.004
 favorite-0.004
 outfits-0.004
Token better
Token ID1365
Feature activation+6.51e-03

Pos logit contributions
oc+0.022
Offic+0.020
Mic+0.020
oon+0.020
 Oliver+0.019
Neg logit contributions
 luck-0.013
 best-0.013
 favorite-0.012
 prett-0.012
 coolest-0.011
Token?"
Token ID1701
Feature activation-5.95e-04

Pos logit contributions
Mic+0.010
 Oliver+0.010
oc+0.010
smart+0.010
oon+0.009
Neg logit contributions
 luck-0.009
 favorite-0.008
 best-0.008
 hats-0.008
ies-0.008
Token Then
Token ID3244
Feature activation-1.50e-02

Pos logit contributions
 hats+0.001
outed+0.001
 favorite+0.001
by+0.001
 coats+0.001
Neg logit contributions
oon-0.001
 Oliver-0.001
oc-0.001
 battlefield-0.001
smart-0.001
Token an
Token ID281
Feature activation-7.82e-03

Pos logit contributions
outed+0.026
 hats+0.025
packs+0.024
by+0.024
 luck+0.024
Neg logit contributions
 Oliver-0.017
oc-0.017
smart-0.016
oon-0.015
 court-0.015
Token idea
Token ID2126
Feature activation-4.93e-02

Pos logit contributions
outed+0.010
 hats+0.010
 luck+0.010
 absolute+0.009
 favorite+0.009
Neg logit contributions
 Oliver-0.012
oc-0.012
oon-0.012
smart-0.011
 battlefield-0.011
Token popped
Token ID22928
Feature activation-1.81e-02

Pos logit contributions
outed+0.084
 absolute+0.081
packs+0.081
by+0.081
 hats+0.080
Neg logit contributions
 Oliver-0.057
smart-0.056
oc-0.056
oon-0.055
 defeated-0.050
Token into
Token ID656
Feature activation+1.85e-03

Pos logit contributions
 hats+0.021
outed+0.021
 luck+0.020
by+0.019
 coats+0.019
Neg logit contributions
oc-0.030
 Oliver-0.029
oon-0.029
smart-0.029
 court-0.028
Token his
Token ID465
Feature activation-5.97e-03

Pos logit contributions
oc+0.002
oon+0.002
 battlefield+0.002
smart+0.002
 Oliver+0.002
Neg logit contributions
 hats-0.003
 coats-0.003
packs-0.003
 luck-0.003
outed-0.003
Token head
Token ID1182
Feature activation-1.50e-02

Pos logit contributions
outed+0.008
 hats+0.008
packs+0.008
 luck+0.008
by+0.008
Neg logit contributions
 Oliver-0.008
oc-0.008
oon-0.008
 court-0.008
smart-0.008
Token.
Token ID13
Feature activation+2.17e-03

Pos logit contributions
outed+0.020
 hats+0.020
packs+0.019
 favorite+0.019
 luck+0.019
Neg logit contributions
oc-0.022
 Oliver-0.022
Mic-0.022
 battlefield-0.021
oon-0.021
Token snow
Token ID6729
Feature activation-1.41e-02

Pos logit contributions
 hats+0.001
outed+0.001
 luck+0.001
by+0.001
 favorite+0.001
Neg logit contributions
 Oliver-0.001
oc-0.001
oon-0.001
smart-0.001
 court-0.001
Tokenman
Token ID805
Feature activation-6.43e-03

Pos logit contributions
outed+0.021
packs+0.020
 luck+0.019
 absolute+0.019
 hats+0.019
Neg logit contributions
oc-0.020
oon-0.019
 Oliver-0.019
smart-0.017
 court-0.017
Token and
Token ID290
Feature activation-1.06e-02

Pos logit contributions
 hats+0.012
 favorite+0.011
packs+0.011
by+0.011
 luck+0.011
Neg logit contributions
 Oliver-0.007
oon-0.006
smart-0.006
Mic-0.006
oc-0.006
Token had
Token ID550
Feature activation+1.87e-03

Pos logit contributions
 hats+0.014
outed+0.014
 coats+0.013
packs+0.013
by+0.013
Neg logit contributions
oc-0.016
 Oliver-0.015
oon-0.015
smart-0.015
 court-0.015
Token a
Token ID257
Feature activation-1.24e-02

Pos logit contributions
 Oliver+0.002
oc+0.002
 defeated+0.002
 court+0.002
smart+0.001
Neg logit contributions
outed-0.004
packs-0.003
uttered-0.003
by-0.003
ies-0.003
Token snowball
Token ID46275
Feature activation-4.93e-02

Pos logit contributions
outed+0.019
packs+0.017
ays+0.016
uttered+0.016
 luck+0.016
Neg logit contributions
oc-0.018
 Oliver-0.017
 court-0.016
Mic-0.016
oon-0.015
Token fight
Token ID1907
Feature activation-1.90e-02

Pos logit contributions
outed+0.080
 hats+0.075
 absolute+0.075
packs+0.075
 luck+0.075
Neg logit contributions
oc-0.061
 Oliver-0.059
oon-0.056
smart-0.055
 court-0.055
Token with
Token ID351
Feature activation+2.84e-04

Pos logit contributions
 hats+0.024
 luck+0.022
 favorite+0.022
outed+0.021
 happened+0.021
Neg logit contributions
oc-0.031
 Oliver-0.031
oon-0.030
Mic-0.029
 battlefield-0.028
Token her
Token ID607
Feature activation-3.28e-03

Pos logit contributions
oon+0.001
oc+0.001
 battlefield+0.001
 Oliver+0.001
smart+0.001
Neg logit contributions
 hats-0.000
 coats-0.000
 favorite-0.000
outed-0.000
 luck-0.000
Token friends
Token ID2460
Feature activation-2.00e-02

Pos logit contributions
outed+0.005
 hats+0.005
packs+0.005
 luck+0.005
 absolute+0.004
Neg logit contributions
oc-0.004
 Oliver-0.004
oon-0.004
smart-0.004
 court-0.004
Token.
Token ID13
Feature activation+6.05e-03

Pos logit contributions
packs+0.019
 hats+0.018
 favorite+0.017
 best+0.017
 names+0.016
Neg logit contributions
oc-0.039
Mic-0.038
oon-0.038
 Oliver-0.037
 battlefield-0.036
Token find
Token ID1064
Feature activation-2.20e-03

Pos logit contributions
by+0.012
 favorite+0.012
 luck+0.012
 absolute+0.012
 hats+0.011
Neg logit contributions
oc-0.014
smart-0.013
oon-0.012
 Oliver-0.012
Mic-0.012
Token her
Token ID607
Feature activation+1.39e-02

Pos logit contributions
outed+0.004
 hats+0.003
packs+0.003
 coats+0.003
 outfits+0.003
Neg logit contributions
 Oliver-0.003
smart-0.003
oc-0.002
 court-0.002
 Mickey-0.002
Token.
Token ID13
Feature activation+5.72e-03

Pos logit contributions
 Oliver+0.016
oc+0.015
 court+0.015
smart+0.015
oon+0.015
Neg logit contributions
outed-0.023
 hats-0.022
by-0.021
 coats-0.021
 absolute-0.021
Token
Token ID198
Feature activation-5.27e-03

Pos logit contributions
oc+0.007
oon+0.007
smart+0.007
 Oliver+0.006
pping+0.006
Neg logit contributions
outed-0.009
 favorite-0.009
 hats-0.009
by-0.008
 absolute-0.008
Token
Token ID198
Feature activation-8.49e-03

Pos logit contributions
outed+0.008
by+0.008
packs+0.008
 favorite+0.008
 hats+0.008
Neg logit contributions
 battlefield-0.006
 Oliver-0.006
oon-0.006
oc-0.006
smart-0.006
TokenDays
Token ID38770
Feature activation-4.92e-02

Pos logit contributions
outed+0.012
 hats+0.011
 favorite+0.011
by+0.010
aws+0.010
Neg logit contributions
 Oliver-0.013
ner-0.012
smart-0.012
oon-0.012
 battlefield-0.012
Token went
Token ID1816
Feature activation+8.14e-03

Pos logit contributions
 absolute+0.067
 outfits+0.066
outed+0.066
 hats+0.064
packs+0.064
Neg logit contributions
 Oliver-0.072
 defeated-0.070
 court-0.067
oc-0.067
"-0.066
Token by
Token ID416
Feature activation+3.33e-03

Pos logit contributions
oc+0.009
 Oliver+0.009
oon+0.009
smart+0.009
 court+0.008
Neg logit contributions
outed-0.014
 hats-0.013
 luck-0.013
packs-0.013
by-0.013
Token and
Token ID290
Feature activation-1.10e-03

Pos logit contributions
oc+0.004
Mic+0.004
 Oliver+0.004
 battlefield+0.004
ner+0.004
Neg logit contributions
 hats-0.005
 favorite-0.005
packs-0.005
 luck-0.005
 happened-0.005
Token Tim
Token ID5045
Feature activation-1.25e-02

Pos logit contributions
outed+0.002
 hats+0.002
 luck+0.002
by+0.002
 favorite+0.002
Neg logit contributions
oc-0.001
oon-0.001
smart-0.001
 Oliver-0.001
 battlefield-0.001
Tokenmy
Token ID1820
Feature activation+8.46e-03

Pos logit contributions
 hats+0.017
outed+0.017
 luck+0.016
 absolute+0.016
packs+0.016
Neg logit contributions
 Oliver-0.019
oc-0.018
oon-0.018
smart-0.017
 court-0.017
Token your
Token ID534
Feature activation+9.79e-04

Pos logit contributions
 Oliver+0.011
oon+0.011
Offic+0.010
oc+0.010
smart+0.010
Neg logit contributions
 hats-0.008
 luck-0.008
 favorite-0.008
 best-0.008
 sandwiches-0.007
Token vegetables
Token ID13701
Feature activation+5.36e-03

Pos logit contributions
oc+0.002
 Oliver+0.002
oon+0.002
smart+0.002
 court+0.002
Neg logit contributions
 hats-0.001
outed-0.001
 luck-0.001
 favorite-0.001
by-0.001
Token."
Token ID526
Feature activation+6.61e-03

Pos logit contributions
Offic+0.009
Mic+0.009
 Oliver+0.009
oc+0.009
smart+0.008
Neg logit contributions
 best-0.007
 favorite-0.007
 luck-0.007
 hats-0.006
ies-0.006
Token
Token ID198
Feature activation-8.36e-03

Pos logit contributions
 Oliver+0.006
oc+0.006
oon+0.006
smart+0.006
 battlefield+0.005
Neg logit contributions
outed-0.012
 hats-0.012
packs-0.012
by-0.012
 coats-0.012
Token
Token ID198
Feature activation-7.86e-03

Pos logit contributions
outed+0.016
 hats+0.015
by+0.015
packs+0.015
 favorite+0.015
Neg logit contributions
 Oliver-0.008
oc-0.007
oon-0.007
smart-0.007
 court-0.007
TokenDays
Token ID38770
Feature activation-4.90e-02

Pos logit contributions
outed+0.013
 hats+0.013
 favorite+0.012
 coats+0.012
by+0.012
Neg logit contributions
 Oliver-0.010
oc-0.009
oon-0.009
smart-0.009
 court-0.009
Token went
Token ID1816
Feature activation+8.10e-03

Pos logit contributions
 absolute+0.063
outed+0.062
 hats+0.061
 outfits+0.061
packs+0.060
Neg logit contributions
 Oliver-0.072
oc-0.072
 defeated-0.072
oon-0.070
 court-0.069
Token by
Token ID416
Feature activation+4.72e-03

Pos logit contributions
oc+0.012
oon+0.011
 Oliver+0.011
smart+0.010
 court+0.010
Neg logit contributions
outed-0.012
 hats-0.011
 luck-0.011
by-0.011
 best-0.011
Token,
Token ID11
Feature activation+1.42e-02

Pos logit contributions
Mic+0.006
 battlefield+0.006
 Oliver+0.006
oc+0.006
Offic+0.006
Neg logit contributions
ies-0.007
 best-0.007
 happened-0.007
 fault-0.007
 favorite-0.007
Token and
Token ID290
Feature activation-1.24e-03

Pos logit contributions
oc+0.021
Mic+0.020
 Oliver+0.020
oon+0.020
smart+0.019
Neg logit contributions
outed-0.020
 hats-0.020
 favorite-0.020
 de-0.019
 prett-0.018
Token Tim
Token ID5045
Feature activation-1.01e-02

Pos logit contributions
outed+0.002
 hats+0.002
 favorite+0.002
by+0.002
 luck+0.002
Neg logit contributions
oon-0.002
oc-0.002
smart-0.002
 Oliver-0.002
 battlefield-0.001
Token and
Token ID290
Feature activation-4.95e-03

Pos logit contributions
oc+0.009
 Oliver+0.008
oon+0.008
Mic+0.008
smart+0.008
Neg logit contributions
 hats-0.011
outed-0.011
 favorite-0.011
 luck-0.011
 de-0.011
Token Tim
Token ID5045
Feature activation-1.29e-02

Pos logit contributions
 hats+0.007
outed+0.007
 luck+0.007
 favorite+0.007
 happened+0.007
Neg logit contributions
oon-0.007
oc-0.007
smart-0.006
 Oliver-0.006
 court-0.006
Token had
Token ID550
Feature activation+5.50e-03

Pos logit contributions
outed+0.013
by+0.012
 hats+0.012
 favorite+0.011
ies+0.011
Neg logit contributions
smart-0.024
 Oliver-0.024
oon-0.023
oc-0.023
 court-0.023
Token a
Token ID257
Feature activation-1.04e-02

Pos logit contributions
oc+0.008
 Oliver+0.008
oon+0.008
smart+0.007
 court+0.007
Neg logit contributions
 hats-0.008
outed-0.008
 luck-0.008
 favorite-0.007
 coats-0.007
Token huge
Token ID3236
Feature activation-1.25e-02

Pos logit contributions
outed+0.016
packs+0.015
 hats+0.015
 outfits+0.014
by+0.014
Neg logit contributions
oc-0.014
 Oliver-0.013
 court-0.013
 defeated-0.012
smart-0.012
Token snowball
Token ID46275
Feature activation-4.90e-02

Pos logit contributions
outed+0.017
packs+0.016
 hats+0.016
by+0.016
 outfits+0.015
Neg logit contributions
oc-0.019
 Oliver-0.018
 court-0.017
oon-0.017
smart-0.017
Token.
Token ID13
Feature activation+5.90e-03

Pos logit contributions
outed+0.081
 hats+0.077
 absolute+0.076
packs+0.076
 luck+0.076
Neg logit contributions
oc-0.058
 Oliver-0.057
oon-0.054
smart-0.054
 court-0.053
Token
Token ID198
Feature activation-2.44e-03

Pos logit contributions
oon+0.009
pping+0.009
oc+0.009
smart+0.008
 battlefield+0.008
Neg logit contributions
outed-0.007
 favorite-0.007
 happened-0.007
 names-0.007
 de-0.007
Token
Token ID198
Feature activation-6.15e-03

Pos logit contributions
 hats+0.003
by+0.003
 favorite+0.003
 happened+0.003
outed+0.003
Neg logit contributions
 Oliver-0.003
 battlefield-0.003
cess-0.003
 courtroom-0.003
 court-0.003
TokenJust
Token ID5703
Feature activation+1.38e-03

Pos logit contributions
 hats+0.006
OK+0.006
Deal+0.006
outed+0.006
 favorite+0.006
Neg logit contributions
 Oliver-0.011
cess-0.010
 battlefield-0.010
 Owl-0.010
ner-0.010
Token then
Token ID788
Feature activation-2.22e-03

Pos logit contributions
 Oliver+0.002
oc+0.002
oon+0.002
smart+0.002
 court+0.002
Neg logit contributions
outed-0.002
 hats-0.002
 luck-0.002
 favorite-0.002
 coats-0.002
Token will
Token ID481
Feature activation+2.32e-02

Pos logit contributions
oc+0.017
 battlefield+0.016
 Oliver+0.016
smart+0.016
oon+0.016
Neg logit contributions
 luck-0.008
outed-0.008
packs-0.008
by-0.008
 hats-0.008
Token be
Token ID307
Feature activation-6.75e-03

Pos logit contributions
Mic+0.040
 Oliver+0.039
oc+0.039
 battlefield+0.038
oon+0.038
Neg logit contributions
 luck-0.029
 names-0.026
 best-0.026
 hats-0.026
by-0.024
Token."
Token ID526
Feature activation+1.26e-02

Pos logit contributions
 hats+0.010
 luck+0.010
outed+0.010
packs+0.010
 favorite+0.010
Neg logit contributions
oc-0.009
 Oliver-0.009
oon-0.009
 court-0.009
smart-0.008
Token
Token ID198
Feature activation+1.72e-03

Pos logit contributions
oc+0.014
 battlefield+0.014
oon+0.014
smart+0.014
 court+0.013
Neg logit contributions
outed-0.021
 hats-0.021
by-0.020
 favorite-0.020
 de-0.020
Token
Token ID198
Feature activation+5.16e-04

Pos logit contributions
 battlefield+0.003
 Oliver+0.003
 court+0.003
smart+0.003
 courtroom+0.003
Neg logit contributions
 hats-0.002
by-0.002
outed-0.002
add-0.002
 best-0.002
TokenDays
Token ID38770
Feature activation-4.88e-02

Pos logit contributions
 Oliver+0.001
 battlefield+0.001
 court+0.001
smart+0.001
 defeated+0.001
Neg logit contributions
 hats-0.001
outed-0.001
by-0.001
Sounds-0.001
 absolute-0.001
Token and
Token ID290
Feature activation+2.79e-04

Pos logit contributions
 absolute+0.065
outed+0.064
 favorite+0.062
packs+0.062
 hats+0.061
Neg logit contributions
 Oliver-0.071
oon-0.070
oc-0.069
"-0.067
 defeated-0.065
Token weeks
Token ID2745
Feature activation-1.75e-02

Pos logit contributions
oc+0.000
smart+0.000
oon+0.000
 Oliver+0.000
 court+0.000
Neg logit contributions
 hats-0.000
outed-0.000
 luck-0.000
by-0.000
 coats-0.000
Token slowly
Token ID6364
Feature activation-1.32e-02

Pos logit contributions
outed+0.022
 hats+0.021
packs+0.020
 luck+0.020
by+0.020
Neg logit contributions
oc-0.027
 Oliver-0.027
oon-0.027
smart-0.026
 court-0.026
Token passed
Token ID3804
Feature activation+1.41e-02

Pos logit contributions
outed+0.018
 hats+0.017
 luck+0.017
packs+0.017
by+0.017
Neg logit contributions
 Oliver-0.019
oc-0.019
oon-0.018
smart-0.018
 court-0.017
Token and
Token ID290
Feature activation-4.87e-03

Pos logit contributions
oc+0.016
 Oliver+0.016
oon+0.015
smart+0.015
 court+0.014
Neg logit contributions
outed-0.024
 hats-0.024
 luck-0.023
by-0.023
packs-0.023
Token and
Token ID290
Feature activation+1.09e-02

Pos logit contributions
outed+0.009
 hats+0.009
packs+0.008
 luck+0.008
by+0.008
Neg logit contributions
oc-0.010
 Oliver-0.010
oon-0.010
smart-0.010
 court-0.010
Token Sam
Token ID3409
Feature activation-1.64e-02

Pos logit contributions
oc+0.011
oon+0.011
smart+0.010
 Oliver+0.010
 battlefield+0.009
Neg logit contributions
 hats-0.020
outed-0.019
 coats-0.019
 luck-0.019
packs-0.019
Token have
Token ID423
Feature activation+7.28e-03

Pos logit contributions
outed+0.019
 hats+0.019
 luck+0.018
packs+0.018
by+0.018
Neg logit contributions
 Oliver-0.027
oc-0.027
oon-0.026
smart-0.026
 court-0.025
Token a
Token ID257
Feature activation-9.37e-03

Pos logit contributions
 Oliver+0.010
oc+0.010
oon+0.010
 court+0.009
smart+0.009
Neg logit contributions
outed-0.010
 hats-0.010
 luck-0.010
by-0.010
packs-0.010
Token big
Token ID1263
Feature activation-7.06e-03

Pos logit contributions
outed+0.014
packs+0.013
 hats+0.013
 luck+0.013
 coats+0.012
Neg logit contributions
 Oliver-0.013
 court-0.012
oc-0.012
 battlefield-0.012
oon-0.011
Token idea
Token ID2126
Feature activation-4.87e-02

Pos logit contributions
outed+0.010
 hats+0.009
packs+0.009
 luck+0.009
 absolute+0.009
Neg logit contributions
 Oliver-0.010
oc-0.010
 court-0.010
oon-0.010
 battlefield-0.009
Token.
Token ID13
Feature activation+1.54e-03

Pos logit contributions
outed+0.093
by+0.089
 absolute+0.088
 luck+0.086
 prett+0.086
Neg logit contributions
smart-0.046
 Oliver-0.045
oc-0.044
oon-0.044
 court-0.042
Token They
Token ID1119
Feature activation-2.67e-03

Pos logit contributions
oc+0.003
oon+0.003
 Oliver+0.003
smart+0.003
Mic+0.003
Neg logit contributions
outed-0.002
 hats-0.002
packs-0.001
 coats-0.001
 favorite-0.001
Token want
Token ID765
Feature activation-9.75e-03

Pos logit contributions
 hats+0.004
outed+0.004
 luck+0.003
packs+0.003
by+0.003
Neg logit contributions
oc-0.004
 Oliver-0.004
oon-0.004
smart-0.004
 court-0.004
Token to
Token ID284
Feature activation+4.73e-03

Pos logit contributions
 hats+0.015
outed+0.014
 favorite+0.014
packs+0.014
 luck+0.014
Neg logit contributions
oc-0.014
oon-0.013
 Oliver-0.012
Mic-0.012
smart-0.012
Token make
Token ID787
Feature activation+1.92e-03

Pos logit contributions
oc+0.007
oon+0.007
 Oliver+0.007
smart+0.006
Mic+0.006
Neg logit contributions
 hats-0.007
 outfits-0.006
packs-0.006
 coats-0.006
 absolute-0.006
Token little
Token ID1310
Feature activation-1.25e-02

Pos logit contributions
 Oliver+0.009
oc+0.009
oon+0.008
smart+0.008
 court+0.008
Neg logit contributions
outed-0.009
 hats-0.009
packs-0.009
 luck-0.009
by-0.009
Token girls
Token ID4813
Feature activation+8.90e-03

Pos logit contributions
outed+0.020
 absolute+0.018
packs+0.018
 hats+0.018
 luck+0.017
Neg logit contributions
 Oliver-0.017
oc-0.016
 court-0.015
oon-0.015
 Owl-0.015
Token,
Token ID11
Feature activation+2.52e-03

Pos logit contributions
 Oliver+0.009
oon+0.008
oc+0.008
 battlefield+0.008
smart+0.008
Neg logit contributions
packs-0.016
 hats-0.016
outed-0.016
by-0.016
 favorite-0.016
Token Sally
Token ID25737
Feature activation-2.03e-02

Pos logit contributions
 Oliver+0.003
 court+0.002
smart+0.002
oc+0.002
oon+0.002
Neg logit contributions
outed-0.005
 luck-0.005
 hats-0.005
by-0.004
 outfits-0.004
Token and
Token ID290
Feature activation-1.35e-02

Pos logit contributions
 hats+0.032
packs+0.032
by+0.032
ies+0.031
 de+0.030
Neg logit contributions
 Oliver-0.026
smart-0.025
 battlefield-0.025
oon-0.024
oc-0.024
Token Sue
Token ID26089
Feature activation-4.86e-02

Pos logit contributions
outed+0.023
 hats+0.022
packs+0.022
 luck+0.021
by+0.021
Neg logit contributions
 Oliver-0.016
oc-0.015
 court-0.014
oon-0.014
smart-0.014
Token.
Token ID13
Feature activation-8.62e-03

Pos logit contributions
outed+0.096
 hats+0.090
 luck+0.088
 absolute+0.087
 passports+0.087
Neg logit contributions
oc-0.046
smart-0.041
 Oliver-0.039
"-0.039
 court-0.039
Token They
Token ID1119
Feature activation-1.70e-03

Pos logit contributions
outed+0.013
 luck+0.013
 hats+0.013
by+0.013
 outfits+0.012
Neg logit contributions
 court-0.011
 Oliver-0.011
oc-0.010
oon-0.010
smart-0.010
Token were
Token ID547
Feature activation-1.05e-02

Pos logit contributions
outed+0.002
 hats+0.002
 luck+0.002
packs+0.002
by+0.002
Neg logit contributions
 Oliver-0.003
oc-0.003
oon-0.003
smart-0.003
 court-0.003
Token very
Token ID845
Feature activation+6.02e-04

Pos logit contributions
outed+0.016
 hats+0.015
packs+0.015
by+0.015
 luck+0.015
Neg logit contributions
 Oliver-0.014
oc-0.013
oon-0.013
 court-0.013
smart-0.013
Token good
Token ID922
Feature activation-1.67e-02

Pos logit contributions
oc+0.001
oon+0.001
 Oliver+0.001
smart+0.001
 battlefield+0.001
Neg logit contributions
outed-0.001
 favorite-0.001
 hats-0.001
 best-0.001
 luck-0.001
Token They
Token ID1119
Feature activation+3.78e-03

Pos logit contributions
oon+0.007
oc+0.007
 Oliver+0.007
smart+0.007
 court+0.007
Neg logit contributions
 hats-0.004
outed-0.004
packs-0.004
 coats-0.004
 favorite-0.004
Token give
Token ID1577
Feature activation+8.73e-03

Pos logit contributions
oc+0.006
oon+0.006
smart+0.006
 Oliver+0.006
 battlefield+0.006
Neg logit contributions
 hats-0.004
 luck-0.004
 names-0.004
 absolute-0.004
by-0.004
Token Spot
Token ID15899
Feature activation+2.08e-02

Pos logit contributions
 Oliver+0.009
oc+0.009
 court+0.008
 defeated+0.008
smart+0.008
Neg logit contributions
outed-0.016
packs-0.015
 absolute-0.015
 outfits-0.015
 hats-0.015
Token more
Token ID517
Feature activation+8.74e-03

Pos logit contributions
 Oliver+0.025
oc+0.024
 court+0.023
smart+0.022
oon+0.021
Neg logit contributions
outed-0.035
 absolute-0.032
packs-0.032
 hats-0.031
 luck-0.031
Token or
Token ID393
Feature activation-9.57e-03

Pos logit contributions
oc+0.011
smart+0.011
 court+0.010
oon+0.010
"+0.010
Neg logit contributions
outed-0.014
 absolute-0.012
by-0.012
Sounds-0.012
xc-0.012
Tokennam
Token ID7402
Feature activation+5.32e-02

Pos logit contributions
outed+0.014
by+0.013
packs+0.013
 hats+0.012
 absolute+0.012
Neg logit contributions
 Oliver-0.013
oc-0.013
smart-0.013
 court-0.012
oon-0.012
Tokenents
Token ID658
Feature activation+7.88e-03

Pos logit contributions
 Oliver+0.040
oc+0.037
oon+0.037
smart+0.035
 court+0.034
Neg logit contributions
outed-0.111
 hats-0.108
packs-0.108
by-0.107
 luck-0.106
Token.
Token ID13
Feature activation+4.73e-03

Pos logit contributions
smart+0.008
oc+0.007
 Oliver+0.007
oon+0.007
 court+0.007
Neg logit contributions
outed-0.015
 absolute-0.014
 hats-0.013
 outfits-0.013
by-0.013
Token Spot
Token ID15899
Feature activation+6.53e-03

Pos logit contributions
oon+0.008
oc+0.008
 Oliver+0.008
smart+0.007
 court+0.007
Neg logit contributions
 hats-0.006
outed-0.006
packs-0.005
 coats-0.005
 favorite-0.005
Token leads
Token ID5983
Feature activation+1.54e-03

Pos logit contributions
 Oliver+0.011
oc+0.011
oon+0.011
smart+0.010
 court+0.010
Neg logit contributions
outed-0.007
 hats-0.007
packs-0.007
 luck-0.007
by-0.007
Token them
Token ID606
Feature activation-2.18e-03

Pos logit contributions
 Oliver+0.002
smart+0.002
oc+0.002
 court+0.002
 Owl+0.002
Neg logit contributions
outed-0.002
 absolute-0.002
packs-0.002
 luck-0.002
 outfits-0.002
Token the
Token ID262
Feature activation-3.17e-03

Pos logit contributions
oc+0.005
smart+0.005
oon+0.005
 Oliver+0.005
 battlefield+0.005
Neg logit contributions
 hats-0.006
 coats-0.006
 favorite-0.005
 absolute-0.005
 de-0.005
Token floor
Token ID4314
Feature activation+4.49e-03

Pos logit contributions
 hats+0.004
outed+0.004
 coats+0.004
 favorite+0.004
 luck+0.004
Neg logit contributions
 Oliver-0.005
oc-0.005
smart-0.005
oon-0.005
 court-0.004
Token and
Token ID290
Feature activation-9.75e-03

Pos logit contributions
oc+0.005
 Oliver+0.005
Mic+0.005
oon+0.004
smart+0.004
Neg logit contributions
 hats-0.008
outed-0.008
 luck-0.008
packs-0.008
 favorite-0.008
Token made
Token ID925
Feature activation-6.67e-03

Pos logit contributions
 hats+0.013
outed+0.012
 coats+0.012
packs+0.012
by+0.012
Neg logit contributions
oc-0.015
oon-0.015
smart-0.014
 Oliver-0.014
 court-0.014
Token a
Token ID257
Feature activation+1.06e-04

Pos logit contributions
outed+0.012
packs+0.012
Deal+0.011
 absolute+0.011
bi+0.011
Neg logit contributions
 Oliver-0.007
oc-0.006
oon-0.005
 defeat-0.005
 defeated-0.005
Token cozy
Token ID37438
Feature activation+4.00e-02

Pos logit contributions
 Oliver+0.000
oc+0.000
oon+0.000
smart+0.000
 court+0.000
Neg logit contributions
outed-0.000
 hats-0.000
 luck-0.000
by-0.000
packs-0.000
Token spot
Token ID4136
Feature activation-9.63e-03

Pos logit contributions
 Oliver+0.070
smart+0.068
oon+0.067
oc+0.066
 court+0.064
Neg logit contributions
 hats-0.044
by-0.043
 coats-0.041
outed-0.041
 luck-0.041
Token on
Token ID319
Feature activation+1.80e-03

Pos logit contributions
outed+0.017
 absolute+0.016
by+0.016
 hats+0.016
 luck+0.016
Neg logit contributions
smart-0.009
oon-0.009
 Oliver-0.009
oc-0.009
 court-0.009
Token the
Token ID262
Feature activation-8.06e-03

Pos logit contributions
oc+0.002
 Oliver+0.002
oon+0.002
smart+0.002
Mic+0.002
Neg logit contributions
 hats-0.003
 coats-0.003
packs-0.003
 favorite-0.003
outed-0.003
Token carpet
Token ID20710
Feature activation-6.22e-04

Pos logit contributions
 hats+0.011
 favorite+0.011
 coats+0.011
outed+0.010
 luck+0.010
Neg logit contributions
 Oliver-0.012
smart-0.012
oc-0.012
oon-0.012
 court-0.010
Token.
Token ID13
Feature activation+5.53e-03

Pos logit contributions
 hats+0.001
packs+0.001
outed+0.001
 luck+0.001
 favorite+0.001
Neg logit contributions
 Oliver-0.001
oc-0.001
oon-0.001
smart-0.001
Mic-0.001
Tokenred
Token ID445
Feature activation-1.58e-02

Pos logit contributions
oc+0.008
 Oliver+0.008
oon+0.008
smart+0.008
 court+0.007
Neg logit contributions
outed-0.006
 hats-0.006
 luck-0.006
packs-0.006
by-0.005
Token.
Token ID13
Feature activation+3.14e-03

Pos logit contributions
 hats+0.024
outed+0.023
 favorite+0.023
 luck+0.023
by+0.023
Neg logit contributions
 Oliver-0.021
oc-0.021
oon-0.021
smart-0.020
 court-0.019
Token They
Token ID1119
Feature activation-2.56e-03

Pos logit contributions
oc+0.005
oon+0.005
smart+0.005
 Oliver+0.004
 court+0.004
Neg logit contributions
outed-0.004
 hats-0.004
 favorite-0.004
 absolute-0.004
 coats-0.004
Token were
Token ID547
Feature activation-4.24e-03

Pos logit contributions
 hats+0.003
outed+0.003
by+0.003
 coats+0.003
packs+0.003
Neg logit contributions
oon-0.005
smart-0.005
oc-0.004
 battlefield-0.004
 Oliver-0.004
Token very
Token ID845
Feature activation+1.24e-02

Pos logit contributions
 hats+0.007
outed+0.007
 luck+0.007
 absolute+0.007
 favorite+0.007
Neg logit contributions
oc-0.005
 Oliver-0.005
oon-0.005
smart-0.005
 court-0.005
Token cozy
Token ID37438
Feature activation+3.65e-02

Pos logit contributions
oon+0.020
oc+0.019
 Oliver+0.019
 battlefield+0.019
Mic+0.019
Neg logit contributions
 favorite-0.017
outed-0.017
 best-0.017
 luck-0.017
 hats-0.017
Token.
Token ID13
Feature activation+6.01e-03

Pos logit contributions
 Oliver+0.036
oc+0.035
oon+0.034
smart+0.033
 court+0.031
Neg logit contributions
 hats-0.067
outed-0.066
 luck-0.066
packs-0.065
 coats-0.065
Token Then
Token ID3244
Feature activation-7.49e-03

Pos logit contributions
oon+0.008
smart+0.008
oc+0.008
 Oliver+0.008
 court+0.008
Neg logit contributions
outed-0.009
 favorite-0.009
 hats-0.009
 absolute-0.008
 coats-0.008
Token Mom
Token ID11254
Feature activation-1.53e-02

Pos logit contributions
outed+0.013
packs+0.012
 hats+0.012
by+0.011
 absolute+0.011
Neg logit contributions
 Oliver-0.009
oc-0.008
oon-0.008
smart-0.008
 court-0.008
Tokenmy
Token ID1820
Feature activation+5.40e-03

Pos logit contributions
outed+0.017
 hats+0.016
by+0.016
packs+0.015
 luck+0.015
Neg logit contributions
oc-0.027
 Oliver-0.026
oon-0.026
smart-0.025
 court-0.025
Token and
Token ID290
Feature activation+1.01e-02

Pos logit contributions
oc+0.008
 court+0.008
smart+0.007
 battlefield+0.007
oon+0.007
Neg logit contributions
 hats-0.008
by-0.007
outed-0.007
 coats-0.007
ies-0.007
Token.
Token ID13
Feature activation+4.94e-03

Pos logit contributions
oc+0.001
 Oliver+0.001
oon+0.001
smart+0.001
 court+0.001
Neg logit contributions
outed-0.001
 hats-0.001
 luck-0.001
by-0.001
packs-0.001
Token
Token ID198
Feature activation+4.20e-03

Pos logit contributions
oon+0.006
 battlefield+0.006
 Oliver+0.006
pping+0.006
smart+0.006
Neg logit contributions
outed-0.007
 de-0.007
 hats-0.007
packs-0.007
 favorite-0.007
Token
Token ID198
Feature activation+5.67e-04

Pos logit contributions
 battlefield+0.006
 Oliver+0.006
 court+0.006
smart+0.005
 courtroom+0.005
Neg logit contributions
by-0.005
outed-0.005
 hats-0.005
packs-0.005
add-0.005
TokenBob
Token ID18861
Feature activation+1.92e-03

Pos logit contributions
 Oliver+0.001
 battlefield+0.001
 court+0.001
 courtroom+0.001
 Rupert+0.001
Neg logit contributions
Sounds-0.001
Deal-0.001
 hats-0.001
OK-0.001
outed-0.001
Token sn
Token ID3013
Feature activation+2.20e-02

Pos logit contributions
 Oliver+0.003
smart+0.003
oon+0.003
 court+0.003
Mic+0.003
Neg logit contributions
by-0.002
outed-0.002
 hats-0.002
 favorite-0.002
 absolute-0.002
Tokenugg
Token ID6837
Feature activation+3.71e-02

Pos logit contributions
oc+0.033
 Oliver+0.032
oon+0.031
smart+0.031
 court+0.030
Neg logit contributions
 hats-0.030
outed-0.029
 luck-0.028
packs-0.028
 absolute-0.028
Tokenled
Token ID992
Feature activation+6.92e-03

Pos logit contributions
 Oliver+0.083
oc+0.083
oon+0.082
smart+0.079
 court+0.077
Neg logit contributions
outed-0.020
 hats-0.020
packs-0.019
 absolute-0.019
 luck-0.019
Token up
Token ID510
Feature activation-4.89e-03

Pos logit contributions
 Oliver+0.012
oc+0.012
oon+0.012
smart+0.011
 court+0.011
Neg logit contributions
 hats-0.008
 luck-0.008
outed-0.008
by-0.008
 favorite-0.008
Token on
Token ID319
Feature activation+1.65e-03

Pos logit contributions
 hats+0.007
 luck+0.007
outed+0.007
 favorite+0.007
by+0.007
Neg logit contributions
oc-0.007
oon-0.007
 Oliver-0.007
Mic-0.006
 battlefield-0.006
Token the
Token ID262
Feature activation-5.12e-03

Pos logit contributions
oon+0.003
Mic+0.003
smart+0.003
oc+0.003
ner+0.002
Neg logit contributions
 hats-0.002
 luck-0.002
 favorite-0.002
 coats-0.002
by-0.002
Token cushion
Token ID33579
Feature activation-6.22e-03

Pos logit contributions
 hats+0.007
 coats+0.007
 favorite+0.007
 luck+0.007
 outfits+0.006
Neg logit contributions
oc-0.008
 Oliver-0.007
smart-0.007
oon-0.007
 defeated-0.007
Token relief
Token ID8259
Feature activation+4.88e-03

Pos logit contributions
 Oliver+0.001
oon+0.001
oc+0.001
smart+0.001
 battlefield+0.001
Neg logit contributions
 luck-0.001
 hats-0.001
outed-0.001
 absolute-0.001
packs-0.001
Token.
Token ID13
Feature activation+4.96e-03

Pos logit contributions
Mic+0.006
oc+0.006
 Oliver+0.006
oon+0.006
 battlefield+0.006
Neg logit contributions
 hats-0.007
 luck-0.007
outed-0.007
 de-0.007
by-0.007
Token The
Token ID383
Feature activation+2.96e-03

Pos logit contributions
oon+0.007
pping+0.007
oc+0.007
 defeat+0.007
smart+0.007
Neg logit contributions
outed-0.007
 de-0.006
 favorite-0.006
 absolute-0.006
 names-0.006
Token rh
Token ID9529
Feature activation+3.28e-02

Pos logit contributions
oon+0.005
 Oliver+0.005
smart+0.004
oc+0.004
 battlefield+0.004
Neg logit contributions
 luck-0.004
 hats-0.004
outed-0.004
 favorite-0.004
by-0.004
Tokenin
Token ID259
Feature activation+2.13e-02

Pos logit contributions
 Oliver+0.060
 court+0.056
 battlefield+0.056
smart+0.055
oon+0.055
Neg logit contributions
outed-0.034
by-0.032
ies-0.030
 luck-0.029
 hats-0.028
Tokenoc
Token ID420
Feature activation+4.74e-02

Pos logit contributions
 Oliver+0.010
 court+0.009
oon+0.009
 battlefield+0.008
ner+0.008
Neg logit contributions
by-0.051
outed-0.050
 favorite-0.047
 hats-0.047
 de-0.047
Tokeneros
Token ID27498
Feature activation+2.04e-02

Pos logit contributions
 Oliver+0.072
oon+0.072
smart+0.067
oc+0.067
 court+0.066
Neg logit contributions
outed-0.061
 luck-0.060
by-0.059
 hats-0.059
 favorite-0.055
Token was
Token ID373
Feature activation-1.68e-03

Pos logit contributions
 Oliver+0.035
oon+0.034
smart+0.034
Mic+0.034
 court+0.034
Neg logit contributions
outed-0.022
by-0.022
 luck-0.020
 hats-0.020
 favorite-0.020
Token so
Token ID523
Feature activation+9.78e-03

Pos logit contributions
 luck+0.002
outed+0.002
 best+0.002
 favorite+0.002
 absolute+0.002
Neg logit contributions
oc-0.002
 Oliver-0.002
oon-0.002
 court-0.002
Mic-0.002
Token happy
Token ID3772
Feature activation+8.80e-03

Pos logit contributions
 Oliver+0.013
oc+0.013
oon+0.013
Mic+0.012
 battlefield+0.012
Neg logit contributions
outed-0.015
 luck-0.015
by-0.014
 favorite-0.014
 best-0.014
Token to
Token ID284
Feature activation-1.18e-02

Pos logit contributions
oc+0.010
 Oliver+0.009
oon+0.009
smart+0.009
Mic+0.009
Neg logit contributions
 hats-0.015
outed-0.015
 luck-0.015
by-0.015
packs-0.014
Token so
Token ID523
Feature activation+5.23e-03

Pos logit contributions
oc+0.002
 Oliver+0.002
oon+0.002
 court+0.002
Mic+0.002
Neg logit contributions
 hats-0.002
 luck-0.002
outed-0.002
 best-0.002
 favorite-0.002
Token exciting
Token ID7895
Feature activation-1.41e-03

Pos logit contributions
oc+0.008
 Oliver+0.008
Mic+0.008
oon+0.008
 battlefield+0.008
Neg logit contributions
outed-0.007
 luck-0.007
 favorite-0.007
 best-0.007
 absolute-0.007
Token!
Token ID0
Feature activation+1.00e-03

Pos logit contributions
 hats+0.003
 luck+0.002
outed+0.002
by+0.002
packs+0.002
Neg logit contributions
oc-0.001
 Oliver-0.001
oon-0.001
smart-0.001
 court-0.001
Token One
Token ID1881
Feature activation+3.88e-03

Pos logit contributions
oc+0.001
oon+0.001
smart+0.001
 Oliver+0.001
 battlefield+0.001
Neg logit contributions
outed-0.002
packs-0.002
 absolute-0.002
 hats-0.002
 favorite-0.001
Token day
Token ID1110
Feature activation+9.44e-04

Pos logit contributions
 Oliver+0.007
oc+0.007
oon+0.007
smart+0.007
 court+0.007
Neg logit contributions
outed-0.004
 hats-0.004
 luck-0.004
packs-0.004
by-0.004
Token,
Token ID11
Feature activation+1.65e-02

Pos logit contributions
oc+0.001
 battlefield+0.001
smart+0.001
oon+0.001
 Oliver+0.001
Neg logit contributions
 hats-0.002
 luck-0.001
 happened-0.001
by-0.001
 coats-0.001
Token Melody
Token ID38906
Feature activation+1.85e-02

Pos logit contributions
oc+0.025
oon+0.024
smart+0.023
 Oliver+0.023
 battlefield+0.023
Neg logit contributions
 hats-0.022
outed-0.021
by-0.021
 favorite-0.021
 luck-0.021
Token decided
Token ID3066
Feature activation+1.87e-03

Pos logit contributions
 Oliver+0.029
oc+0.029
smart+0.028
oon+0.028
 court+0.027
Neg logit contributions
outed-0.023
 hats-0.022
by-0.022
packs-0.021
 luck-0.021
Token that
Token ID326
Feature activation-1.60e-03

Pos logit contributions
oc+0.003
oon+0.002
 Oliver+0.002
smart+0.002
 battlefield+0.002
Neg logit contributions
 hats-0.003
 luck-0.003
outed-0.003
by-0.003
 favorite-0.003
Token she
Token ID673
Feature activation+1.38e-02

Pos logit contributions
 hats+0.002
 luck+0.002
packs+0.002
 favorite+0.002
outed+0.002
Neg logit contributions
oc-0.003
oon-0.003
 Oliver-0.003
smart-0.003
 battlefield-0.002
Token wanted
Token ID2227
Feature activation+2.45e-03

Pos logit contributions
 Oliver+0.021
oc+0.021
oon+0.021
smart+0.020
 court+0.020
Neg logit contributions
outed-0.017
 hats-0.017
packs-0.017
 luck-0.016
by-0.016
Token it
Token ID340
Feature activation-1.31e-02

Pos logit contributions
 hats+0.004
packs+0.004
 coats+0.003
outed+0.003
 luck+0.003
Neg logit contributions
oc-0.005
oon-0.005
 Oliver-0.005
Mic-0.004
smart-0.004
Token,"
Token ID553
Feature activation+3.38e-03

Pos logit contributions
outed+0.019
 hats+0.019
packs+0.019
 luck+0.019
 favorite+0.018
Neg logit contributions
 Oliver-0.018
oc-0.018
oon-0.017
smart-0.016
 court-0.016
Token Mom
Token ID11254
Feature activation-2.92e-02

Pos logit contributions
 Oliver+0.004
oc+0.004
oon+0.004
smart+0.004
 court+0.004
Neg logit contributions
outed-0.005
 hats-0.005
 luck-0.005
packs-0.005
by-0.005
Token says
Token ID1139
Feature activation-1.24e-02

Pos logit contributions
outed+0.029
 hats+0.029
packs+0.028
 luck+0.028
by+0.028
Neg logit contributions
 Oliver-0.053
oc-0.051
oon-0.051
smart-0.050
 court-0.049
Token.
Token ID13
Feature activation-1.07e-03

Pos logit contributions
outed+0.017
 hats+0.017
 luck+0.016
packs+0.016
by+0.016
Neg logit contributions
oc-0.018
 Oliver-0.018
oon-0.017
smart-0.016
 court-0.016
Token
Token ID198
Feature activation-2.94e-04

Pos logit contributions
 hats+0.002
outed+0.002
 de+0.002
 favorite+0.001
 happened+0.001
Neg logit contributions
oc-0.002
pping-0.001
oon-0.001
 defeat-0.001
 battlefield-0.001
Token
Token ID198
Feature activation-1.95e-03

Pos logit contributions
 hats+0.000
packs+0.000
outed+0.000
by+0.000
ara+0.000
Neg logit contributions
oc-0.000
 battlefield-0.000
 Oliver-0.000
oon-0.000
pping-0.000
Token"
Token ID1
Feature activation-4.95e-03

Pos logit contributions
 hats+0.003
packs+0.003
ara+0.003
outed+0.003
 coats+0.003
Neg logit contributions
 Oliver-0.003
oc-0.003
 battlefield-0.002
 defeated-0.002
oon-0.002
TokenThat
Token ID2504
Feature activation-1.75e-02

Pos logit contributions
outed+0.006
packs+0.006
by+0.006
 luck+0.006
 hats+0.006
Neg logit contributions
 Oliver-0.007
oon-0.007
oc-0.007
smart-0.007
 court-0.007
Token's
Token ID338
Feature activation-2.14e-03

Pos logit contributions
outed+0.025
 hats+0.025
 luck+0.024
packs+0.024
by+0.024
Neg logit contributions
 Oliver-0.024
oc-0.024
oon-0.023
smart-0.023
 court-0.022
Token not
Token ID407
Feature activation-4.93e-03

Pos logit contributions
 luck+0.003
 hats+0.003
outed+0.003
 favorite+0.003
 best+0.003
Neg logit contributions
oc-0.003
oon-0.003
 Oliver-0.003
smart-0.003
 court-0.003
Token the
Token ID262
Feature activation+1.51e-03

Pos logit contributions
by+0.013
 absolute+0.013
 luck+0.013
 best+0.013
 hats+0.013
Neg logit contributions
 battlefield-0.010
oc-0.010
oon-0.009
smart-0.009
 court-0.009
Token story
Token ID1621
Feature activation-2.65e-04

Pos logit contributions
oc+0.003
 Oliver+0.003
oon+0.003
smart+0.003
 battlefield+0.002
Neg logit contributions
 luck-0.002
 hats-0.002
 best-0.001
 favorite-0.001
 absolute-0.001
Token is
Token ID318
Feature activation+8.68e-03

Pos logit contributions
outed+0.000
 luck+0.000
packs+0.000
by+0.000
 hats+0.000
Neg logit contributions
 Oliver-0.001
Mic-0.001
oc-0.001
oon-0.001
 court-0.001
Token not
Token ID407
Feature activation-1.58e-03

Pos logit contributions
oc+0.015
Mic+0.014
oon+0.013
 battlefield+0.012
Offic+0.012
Neg logit contributions
 luck-0.012
 best-0.011
by-0.011
 happened-0.011
outed-0.010
Token to
Token ID284
Feature activation+2.50e-03

Pos logit contributions
 luck+0.002
by+0.002
 hats+0.002
 happened+0.002
 best+0.002
Neg logit contributions
oc-0.002
oon-0.002
 Oliver-0.002
Mic-0.002
 battlefield-0.002
Token follow
Token ID1061
Feature activation+1.27e-02

Pos logit contributions
oc+0.004
oon+0.004
 Oliver+0.004
smart+0.004
 battlefield+0.004
Neg logit contributions
 luck-0.003
by-0.003
 hats-0.003
 absolute-0.003
outed-0.003
Token strangers
Token ID18981
Feature activation+2.37e-02

Pos logit contributions
oon+0.022
oc+0.022
Mic+0.019
ner+0.019
Offic+0.019
Neg logit contributions
 luck-0.017
 hats-0.017
 best-0.016
 coats-0.015
 names-0.015
Token,
Token ID11
Feature activation+5.59e-03

Pos logit contributions
Mic+0.035
oon+0.033
oc+0.033
Offic+0.033
 Oliver+0.032
Neg logit contributions
 best-0.031
packs-0.031
by-0.031
 luck-0.030
 hats-0.029
Token no
Token ID645
Feature activation-1.68e-02

Pos logit contributions
oon+0.008
oc+0.008
Mic+0.007
 Oliver+0.007
ner+0.007
Neg logit contributions
 hats-0.008
 favorite-0.008
 luck-0.008
 best-0.008
 absolute-0.007
Token matter
Token ID2300
Feature activation-1.46e-02

Pos logit contributions
outed+0.013
 hats+0.012
packs+0.011
 luck+0.011
by+0.011
Neg logit contributions
 Oliver-0.035
oc-0.035
oon-0.034
smart-0.034
 court-0.033
Token how
Token ID703
Feature activation-3.81e-03

Pos logit contributions
 luck+0.017
packs+0.016
 hats+0.016
outed+0.016
 best+0.015
Neg logit contributions
oc-0.025
oon-0.024
 Oliver-0.024
Mic-0.024
 battlefield-0.023
Token forgotten
Token ID11564
Feature activation+2.58e-05

Pos logit contributions
oc+0.012
oon+0.011
 Oliver+0.011
smart+0.011
Mic+0.010
Neg logit contributions
 hats-0.009
outed-0.009
 luck-0.009
 coats-0.009
 favorite-0.009
Token to
Token ID284
Feature activation+1.67e-03

Pos logit contributions
oc+0.000
oon+0.000
Mic+0.000
cess+0.000
ner+0.000
Neg logit contributions
 hats-0.000
 luck-0.000
 favorite-0.000
 coats-0.000
 happened-0.000
Token bat
Token ID7365
Feature activation+2.47e-02

Pos logit contributions
oc+0.003
 Oliver+0.003
oon+0.002
smart+0.002
 battlefield+0.002
Neg logit contributions
 hats-0.002
 luck-0.002
outed-0.002
 coats-0.002
by-0.002
Tokenhe
Token ID258
Feature activation+2.02e-02

Pos logit contributions
oc+0.034
 Oliver+0.033
smart+0.031
 battlefield+0.031
Mic+0.030
Neg logit contributions
outed-0.035
by-0.034
 luck-0.034
 hats-0.033
 best-0.032
Token before
Token ID878
Feature activation-7.56e-03

Pos logit contributions
oc+0.029
Mic+0.028
 Oliver+0.027
 battlefield+0.026
Offic+0.026
Neg logit contributions
 hats-0.029
 luck-0.028
 best-0.027
 favorite-0.027
outed-0.026
Token going
Token ID1016
Feature activation+1.16e-02

Pos logit contributions
 hats+0.011
 luck+0.011
 happened+0.011
 coats+0.011
outed+0.010
Neg logit contributions
oc-0.011
oon-0.010
smart-0.010
Mic-0.009
 Oliver-0.009
Token near
Token ID1474
Feature activation-3.74e-03

Pos logit contributions
 Oliver+0.015
oc+0.014
oon+0.014
smart+0.014
 court+0.013
Neg logit contributions
outed-0.018
 hats-0.018
packs-0.017
 luck-0.017
by-0.017
Token the
Token ID262
Feature activation+2.34e-03

Pos logit contributions
 hats+0.006
 luck+0.005
 best+0.005
 coats+0.005
 favorite+0.005
Neg logit contributions
oc-0.005
Mic-0.005
oon-0.005
cess-0.005
Offic-0.005
Token water
Token ID1660
Feature activation-1.39e-03

Pos logit contributions
smart+0.003
oon+0.003
 Oliver+0.003
oc+0.003
cess+0.003
Neg logit contributions
 hats-0.003
 luck-0.003
 favorite-0.003
 best-0.003
by-0.003
Token.
Token ID13
Feature activation+3.24e-03

Pos logit contributions
 hats+0.002
outed+0.002
 luck+0.002
packs+0.002
by+0.002
Neg logit contributions
oc-0.002
 Oliver-0.002
oon-0.002
Mic-0.002
smart-0.002
Token He
Token ID679
Feature activation+2.19e-03

Pos logit contributions
smart+0.005
oon+0.005
pping+0.005
oc+0.005
wheel+0.005
Neg logit contributions
outed-0.004
 nods-0.003
 favorite-0.003
 absolute-0.003
 de-0.003
Token
Token ID198
Feature activation+5.23e-03

Pos logit contributions
oon+0.008
 Oliver+0.008
oc+0.007
Mic+0.007
smart+0.007
Neg logit contributions
outed-0.008
 luck-0.008
 favorite-0.008
 hats-0.007
 best-0.007
TokenPeter
Token ID19727
Feature activation+9.66e-03

Pos logit contributions
 Oliver+0.006
oc+0.005
oon+0.005
smart+0.005
 battlefield+0.005
Neg logit contributions
outed-0.009
packs-0.009
 hats-0.008
by-0.008
 absolute-0.008
Token never
Token ID1239
Feature activation-3.73e-04

Pos logit contributions
 Oliver+0.015
oc+0.015
oon+0.015
smart+0.014
 court+0.014
Neg logit contributions
outed-0.012
 hats-0.012
by-0.011
 luck-0.011
packs-0.011
Token pin
Token ID6757
Feature activation+2.42e-02

Pos logit contributions
outed+0.001
 hats+0.001
 coats+0.001
packs+0.001
 outfits+0.001
Neg logit contributions
 Oliver-0.000
oc-0.000
smart-0.000
 court-0.000
oon-0.000
Tokenched
Token ID1740
Feature activation+1.69e-02

Pos logit contributions
oc+0.029
 Oliver+0.028
oon+0.027
 court+0.027
 battlefield+0.026
Neg logit contributions
outed-0.039
 luck-0.038
 hats-0.038
by-0.038
 favorite-0.037
Token the
Token ID262
Feature activation+7.63e-03

Pos logit contributions
oc+0.027
oon+0.026
smart+0.024
 battlefield+0.024
 Oliver+0.024
Neg logit contributions
 luck-0.022
 hats-0.021
 favorite-0.021
by-0.020
 best-0.020
Token to
Token ID284
Feature activation+7.42e-03

Pos logit contributions
 Oliver+0.011
oc+0.011
oon+0.010
smart+0.010
 court+0.010
Neg logit contributions
outed-0.010
 hats-0.010
 luck-0.010
packs-0.010
by-0.010
Tokenad
Token ID324
Feature activation-2.68e-03

Pos logit contributions
oc+0.011
oon+0.011
 battlefield+0.010
 Oliver+0.010
Mic+0.009
Neg logit contributions
 hats-0.009
 absolute-0.009
 favorite-0.009
 luck-0.009
 happened-0.009
Token's
Token ID338
Feature activation+2.45e-04

Pos logit contributions
outed+0.004
 hats+0.003
by+0.003
packs+0.003
 luck+0.003
Neg logit contributions
 Oliver-0.004
oc-0.004
oon-0.004
 court-0.004
smart-0.004
Token toe
Token ID21189
Feature activation-4.32e-03

Pos logit contributions
 Oliver+0.000
oc+0.000
oon+0.000
smart+0.000
 court+0.000
Neg logit contributions
outed-0.000
 hats-0.000
 luck-0.000
by-0.000
packs-0.000
Token again
Token ID757
Feature activation+8.50e-04

Pos logit contributions
outed+0.007
 hats+0.007
 luck+0.006
 favorite+0.006
by+0.006
Neg logit contributions
 Oliver-0.005
oc-0.005
oon-0.005
smart-0.005
 court-0.005
Token She
Token ID1375
Feature activation+1.96e-03

Pos logit contributions
oc+0.009
 Oliver+0.009
oon+0.009
smart+0.008
 battlefield+0.008
Neg logit contributions
outed-0.020
 hats-0.019
packs-0.019
by-0.019
 favorite-0.018
Token filled
Token ID5901
Feature activation+1.25e-02

Pos logit contributions
oc+0.003
 Oliver+0.003
smart+0.003
oon+0.003
 court+0.003
Neg logit contributions
outed-0.003
 hats-0.002
 favorite-0.002
 coats-0.002
 luck-0.002
Token a
Token ID257
Feature activation-6.65e-03

Pos logit contributions
 Oliver+0.015
oc+0.015
oon+0.014
smart+0.014
 court+0.014
Neg logit contributions
outed-0.020
 hats-0.020
packs-0.019
 luck-0.019
by-0.019
Token cup
Token ID6508
Feature activation-5.82e-03

Pos logit contributions
 hats+0.007
 favorite+0.007
 coats+0.006
outed+0.006
by+0.006
Neg logit contributions
 Oliver-0.013
smart-0.013
oon-0.012
cess-0.012
pping-0.012
Token with
Token ID351
Feature activation+5.92e-03

Pos logit contributions
 hats+0.011
outed+0.010
 luck+0.010
 favorite+0.010
 coats+0.010
Neg logit contributions
 Oliver-0.006
oc-0.006
Mic-0.005
 battlefield-0.005
smart-0.005
Token water
Token ID1660
Feature activation-1.93e-03

Pos logit contributions
 Oliver+0.009
oc+0.008
oon+0.008
smart+0.008
 court+0.008
Neg logit contributions
outed-0.008
packs-0.007
by-0.007
 hats-0.007
 absolute-0.007
Token and
Token ID290
Feature activation-1.42e-02

Pos logit contributions
outed+0.004
 hats+0.004
 luck+0.004
packs+0.004
by+0.004
Neg logit contributions
oc-0.002
 Oliver-0.002
oon-0.002
smart-0.002
 court-0.002
Token poured
Token ID19036
Feature activation-4.25e-04

Pos logit contributions
outed+0.019
packs+0.018
 absolute+0.017
by+0.017
 luck+0.017
Neg logit contributions
 Oliver-0.021
oc-0.020
oon-0.019
 court-0.019
smart-0.019
Token it
Token ID340
Feature activation-1.21e-02

Pos logit contributions
outed+0.001
packs+0.001
 absolute+0.001
 outfits+0.001
by+0.001
Neg logit contributions
 Oliver-0.000
oc-0.000
oon-0.000
smart-0.000
 court-0.000
Token in
Token ID287
Feature activation-1.24e-03

Pos logit contributions
outed+0.023
 absolute+0.023
 outfits+0.022
 passports+0.022
 hats+0.022
Neg logit contributions
smart-0.010
 Oliver-0.010
oon-0.009
 court-0.009
oc-0.009
Token the
Token ID262
Feature activation-1.45e-02

Pos logit contributions
 hats+0.002
 luck+0.002
 coats+0.002
packs+0.002
outed+0.002
Neg logit contributions
oc-0.002
 Oliver-0.002
oon-0.002
smart-0.001
 battlefield-0.001
Token tick
Token ID4378
Feature activation+9.23e-03

Pos logit contributions
 Oliver+0.020
 battlefield+0.020
 court+0.019
oon+0.019
ner+0.019
Neg logit contributions
outed-0.013
by-0.012
 hats-0.012
 favorite-0.012
 happened-0.011
Tokenled
Token ID992
Feature activation-3.13e-03

Pos logit contributions
oc+0.020
 Oliver+0.020
oon+0.020
smart+0.019
 court+0.018
Neg logit contributions
 hats-0.006
packs-0.006
outed-0.006
 absolute-0.006
 favorite-0.005
Token the
Token ID262
Feature activation+2.21e-04

Pos logit contributions
 hats+0.005
outed+0.005
 luck+0.004
by+0.004
 favorite+0.004
Neg logit contributions
oc-0.004
oon-0.004
 Oliver-0.004
smart-0.004
 court-0.004
Token oy
Token ID35104
Feature activation+7.15e-03

Pos logit contributions
oc+0.000
 Oliver+0.000
oon+0.000
smart+0.000
 court+0.000
Neg logit contributions
outed-0.000
 hats-0.000
 luck-0.000
by-0.000
packs-0.000
Tokenster
Token ID1706
Feature activation+9.74e-03

Pos logit contributions
 Oliver+0.011
oon+0.011
smart+0.011
oc+0.011
 court+0.010
Neg logit contributions
outed-0.009
 luck-0.009
 hats-0.009
by-0.009
 favorite-0.008
Token and
Token ID290
Feature activation-3.00e-03

Pos logit contributions
 Oliver+0.013
Mic+0.012
oon+0.011
 court+0.011
oc+0.011
Neg logit contributions
 hats-0.015
 favorite-0.015
 luck-0.015
by-0.014
 best-0.014
Token suddenly
Token ID6451
Feature activation-8.97e-03

Pos logit contributions
 hats+0.004
outed+0.003
 luck+0.003
by+0.003
 happened+0.003
Neg logit contributions
oon-0.005
oc-0.005
Mic-0.005
smart-0.005
 court-0.005
Token it
Token ID340
Feature activation-1.10e-02

Pos logit contributions
 luck+0.014
 hats+0.014
 happened+0.014
by+0.014
outed+0.013
Neg logit contributions
oc-0.012
Mic-0.011
oon-0.011
smart-0.011
 Oliver-0.011
Token opened
Token ID4721
Feature activation-1.03e-02

Pos logit contributions
outed+0.013
 hats+0.012
 happened+0.012
by+0.012
 luck+0.012
Neg logit contributions
oc-0.018
 Oliver-0.018
 court-0.018
oon-0.017
smart-0.017
Token and
Token ID290
Feature activation+3.33e-03

Pos logit contributions
 hats+0.015
outed+0.015
 luck+0.015
by+0.015
 favorite+0.015
Neg logit contributions
 Oliver-0.014
oc-0.014
oon-0.013
smart-0.013
 court-0.013
Token Jack
Token ID3619
Feature activation+2.96e-03

Pos logit contributions
oc+0.005
oon+0.005
smart+0.005
 court+0.005
 Oliver+0.004
Neg logit contributions
by-0.004
 hats-0.004
outed-0.004
 luck-0.004
 prett-0.004
Token.
Token ID13
Feature activation+6.83e-03

Pos logit contributions
 hats+0.016
outed+0.016
 luck+0.016
 favorite+0.015
packs+0.015
Neg logit contributions
oc-0.017
 Oliver-0.017
oon-0.016
Mic-0.015
 court-0.015
Token He
Token ID679
Feature activation+6.29e-03

Pos logit contributions
oc+0.011
oon+0.010
pping+0.010
Mic+0.010
cess+0.010
Neg logit contributions
outed-0.008
 hats-0.008
 names-0.008
 favorite-0.008
 brushes-0.008
Token closed
Token ID4838
Feature activation+1.41e-02

Pos logit contributions
oon+0.011
Mic+0.011
 Oliver+0.011
smart+0.011
 court+0.010
Neg logit contributions
 hats-0.007
 favorite-0.007
outed-0.007
 happened-0.006
by-0.006
Token one
Token ID530
Feature activation-1.74e-03

Pos logit contributions
oc+0.022
oon+0.021
Mic+0.020
smart+0.020
 battlefield+0.019
Neg logit contributions
 hats-0.021
 coats-0.019
outed-0.019
 favorite-0.018
 luck-0.018
Token eye
Token ID4151
Feature activation-8.06e-03

Pos logit contributions
 hats+0.002
by+0.002
 luck+0.002
 favorite+0.002
packs+0.002
Neg logit contributions
 Oliver-0.003
oon-0.003
Mic-0.002
oc-0.002
cess-0.002
Token and
Token ID290
Feature activation-6.86e-04

Pos logit contributions
 hats+0.011
outed+0.011
 favorite+0.010
 luck+0.010
 best+0.010
Neg logit contributions
Mic-0.013
 Oliver-0.012
oon-0.012
oc-0.012
 battlefield-0.012
Token pulled
Token ID5954
Feature activation-3.79e-03

Pos logit contributions
 hats+0.001
 happened+0.001
 luck+0.001
outed+0.001
by+0.001
Neg logit contributions
oon-0.001
oc-0.001
Mic-0.001
smart-0.001
 Oliver-0.001
Token the
Token ID262
Feature activation+7.14e-03

Pos logit contributions
 luck+0.005
 best+0.005
 hats+0.005
by+0.005
 favorite+0.004
Neg logit contributions
oon-0.006
 battlefield-0.006
Mic-0.006
cess-0.006
oc-0.006
Token trigger
Token ID7616
Feature activation-1.08e-02

Pos logit contributions
oon+0.011
 Oliver+0.011
smart+0.011
oc+0.011
cess+0.010
Neg logit contributions
 hats-0.009
 luck-0.009
outed-0.008
 favorite-0.008
by-0.008
Token.
Token ID13
Feature activation+3.85e-03

Pos logit contributions
 luck+0.013
outed+0.013
 hats+0.013
by+0.013
 favorite+0.013
Neg logit contributions
oc-0.017
 Oliver-0.017
oon-0.017
Mic-0.016
 battlefield-0.016
Token
Token ID198
Feature activation+8.38e-03

Pos logit contributions
oc+0.006
pping+0.005
oon+0.005
cess+0.005
Mic+0.005
Neg logit contributions
outed-0.005
 hats-0.005
 names-0.005
 favorite-0.005
 brushes-0.004
Token rock
Token ID3881
Feature activation+3.09e-03

Pos logit contributions
 hats+0.003
 luck+0.003
outed+0.003
 favorite+0.003
 coats+0.002
Neg logit contributions
oc-0.003
 Oliver-0.003
smart-0.002
oon-0.002
 court-0.002
Token was
Token ID373
Feature activation+4.98e-03

Pos logit contributions
 Oliver+0.005
oc+0.005
oon+0.005
smart+0.005
 court+0.005
Neg logit contributions
outed-0.004
 hats-0.003
by-0.003
 luck-0.003
 favorite-0.003
Token too
Token ID1165
Feature activation+1.53e-02

Pos logit contributions
oc+0.010
 Oliver+0.009
oon+0.008
cess+0.008
 court+0.008
Neg logit contributions
outed-0.006
 luck-0.006
 favorite-0.006
 best-0.006
 hats-0.005
Token slippery
Token ID32911
Feature activation-2.11e-03

Pos logit contributions
oc+0.024
 Oliver+0.024
 battlefield+0.023
smart+0.023
cess+0.022
Neg logit contributions
outed-0.021
 favorite-0.019
 luck-0.019
by-0.019
 hats-0.019
Token,
Token ID11
Feature activation+5.90e-03

Pos logit contributions
 hats+0.003
outed+0.003
 luck+0.003
packs+0.003
by+0.003
Neg logit contributions
oc-0.003
 Oliver-0.003
oon-0.003
smart-0.002
 court-0.002
Token and
Token ID290
Feature activation-2.47e-03

Pos logit contributions
oc+0.006
 Oliver+0.006
oon+0.006
smart+0.006
 court+0.005
Neg logit contributions
 hats-0.011
outed-0.010
 luck-0.010
 favorite-0.010
 coats-0.010
Token the
Token ID262
Feature activation-7.06e-03

Pos logit contributions
outed+0.004
 hats+0.004
 happened+0.004
 luck+0.004
 favorite+0.004
Neg logit contributions
oc-0.003
oon-0.003
Mic-0.003
smart-0.003
 court-0.003
Token goat
Token ID26917
Feature activation+1.13e-02

Pos logit contributions
 hats+0.010
 luck+0.009
outed+0.009
 favorite+0.009
 coats+0.009
Neg logit contributions
oon-0.011
oc-0.011
smart-0.011
 Oliver-0.010
 court-0.010
Token slipped
Token ID18859
Feature activation-1.12e-02

Pos logit contributions
 Oliver+0.021
smart+0.021
Mic+0.020
oc+0.020
oon+0.020
Neg logit contributions
outed-0.011
 favorite-0.011
 happened-0.010
by-0.010
 hats-0.010
Token.
Token ID13
Feature activation+5.56e-03

Pos logit contributions
 hats+0.015
 luck+0.015
outed+0.014
 coats+0.014
 best+0.014
Neg logit contributions
oc-0.017
 Oliver-0.016
 court-0.016
 battlefield-0.016
oon-0.015
Token
Token ID198
Feature activation+2.13e-04

Pos logit contributions
oc+0.008
oon+0.008
smart+0.008
pping+0.008
 defeat+0.008
Neg logit contributions
outed-0.008
 de-0.007
 favorite-0.007
 hats-0.007
 happened-0.007
Token was
Token ID373
Feature activation-1.38e-02

Pos logit contributions
 Oliver+0.010
oc+0.010
oon+0.010
smart+0.009
 court+0.009
Neg logit contributions
outed-0.009
 hats-0.009
 luck-0.009
by-0.009
 favorite-0.009
Token soft
Token ID2705
Feature activation+7.37e-03

Pos logit contributions
outed+0.023
 hats+0.023
 luck+0.022
packs+0.022
by+0.022
Neg logit contributions
oc-0.016
 Oliver-0.016
oon-0.016
smart-0.015
 court-0.015
Token and
Token ID290
Feature activation-6.95e-04

Pos logit contributions
oc+0.005
 Oliver+0.005
oon+0.004
smart+0.004
 court+0.004
Neg logit contributions
outed-0.016
 hats-0.015
packs-0.015
 absolute-0.015
by-0.015
Token warm
Token ID5814
Feature activation-5.74e-04

Pos logit contributions
outed+0.001
 hats+0.001
packs+0.001
 luck+0.001
by+0.001
Neg logit contributions
 Oliver-0.001
oc-0.001
oon-0.001
smart-0.001
 court-0.001
Token.
Token ID13
Feature activation-1.95e-03

Pos logit contributions
outed+0.001
packs+0.001
 absolute+0.001
 passports+0.001
 outfits+0.001
Neg logit contributions
oc-0.000
 Oliver-0.000
smart-0.000
oon-0.000
 since-0.000
Token
Token ID198
Feature activation-9.82e-04

Pos logit contributions
outed+0.003
 hats+0.003
 de+0.002
 favorite+0.002
aws+0.002
Neg logit contributions
oon-0.003
oc-0.003
pping-0.003
 battlefield-0.003
 Oliver-0.003
Token
Token ID198
Feature activation-5.18e-03

Pos logit contributions
 hats+0.001
outed+0.001
packs+0.001
by+0.001
 happened+0.001
Neg logit contributions
 battlefield-0.001
 Oliver-0.001
oc-0.001
pping-0.001
 courtroom-0.001
Token"
Token ID1
Feature activation-1.39e-02

Pos logit contributions
 hats+0.008
OK+0.008
outed+0.008
Deal+0.008
ara+0.007
Neg logit contributions
 Oliver-0.007
 battlefield-0.006
 Monster-0.006
 Owl-0.006
oon-0.006
TokenCan
Token ID6090
Feature activation-3.86e-03

Pos logit contributions
packs+0.022
outed+0.021
by+0.021
 luck+0.020
 hats+0.020
Neg logit contributions
oc-0.018
 Oliver-0.018
oon-0.018
Mic-0.018
smart-0.017
Token I
Token ID314
Feature activation-3.62e-03

Pos logit contributions
outed+0.007
 hats+0.006
 luck+0.006
packs+0.006
by+0.006
Neg logit contributions
oc-0.004
 Oliver-0.004
oon-0.004
smart-0.004
 court-0.004
Token pet
Token ID4273
Feature activation-6.46e-03

Pos logit contributions
 hats+0.004
by+0.004
 favorite+0.004
 luck+0.004
 coats+0.004
Neg logit contributions
oon-0.006
 battlefield-0.006
 Oliver-0.006
oc-0.006
smart-0.006
Token balloon
Token ID21190
Feature activation+2.23e-03

Pos logit contributions
 court+0.005
oon+0.005
 Oliver+0.005
 battlefield+0.005
oc+0.005
Neg logit contributions
outed-0.006
add-0.006
Sounds-0.006
 absolute-0.006
by-0.005
Token.
Token ID13
Feature activation+5.23e-04

Pos logit contributions
 court+0.002
 Oliver+0.002
oc+0.002
oon+0.002
smart+0.002
Neg logit contributions
outed-0.004
add-0.004
 absolute-0.004
 outfits-0.004
by-0.004
Token
Token ID198
Feature activation+2.98e-03

Pos logit contributions
oc+0.001
oon+0.001
 Oliver+0.001
 battlefield+0.001
smart+0.001
Neg logit contributions
outed-0.001
 hats-0.001
packs-0.001
 favorite-0.001
 absolute-0.001
Token
Token ID198
Feature activation-1.49e-03

Pos logit contributions
 Oliver+0.004
oon+0.003
 battlefield+0.003
smart+0.003
oc+0.003
Neg logit contributions
 hats-0.005
outed-0.005
by-0.004
packs-0.004
 favorite-0.004
Token"
Token ID1
Feature activation-8.73e-03

Pos logit contributions
 hats+0.002
outed+0.002
ara+0.002
by+0.002
packs+0.002
Neg logit contributions
 Oliver-0.002
 Owl-0.002
smart-0.002
oc-0.002
 battlefield-0.002
TokenWhere
Token ID8496
Feature activation-3.71e-02

Pos logit contributions
outed+0.013
 luck+0.013
by+0.013
 hats+0.013
 favorite+0.013
Neg logit contributions
oon-0.011
oc-0.011
 Oliver-0.011
smart-0.011
 court-0.010
Token are
Token ID389
Feature activation+1.08e-02

Pos logit contributions
outed+0.043
 hats+0.042
 outfits+0.040
by+0.039
 coats+0.039
Neg logit contributions
oc-0.062
 Oliver-0.061
smart-0.060
oon-0.060
 court-0.057
Token you
Token ID345
Feature activation+9.33e-03

Pos logit contributions
 Oliver+0.008
 court+0.007
 Mickey+0.007
"+0.007
ner+0.006
Neg logit contributions
outed-0.023
by-0.022
 outfits-0.022
packs-0.022
 fault-0.022
Token,
Token ID11
Feature activation-2.23e-03

Pos logit contributions
oc+0.013
 Oliver+0.012
smart+0.012
oon+0.012
 battlefield+0.011
Neg logit contributions
 luck-0.014
 hats-0.014
 best-0.014
outed-0.014
packs-0.013
Token Anna
Token ID11735
Feature activation+1.32e-02

Pos logit contributions
 hats+0.003
 luck+0.003
outed+0.003
 coats+0.003
 favorite+0.003
Neg logit contributions
oc-0.003
smart-0.003
oon-0.003
 Oliver-0.003
 battlefield-0.003
Token?"
Token ID1701
Feature activation+4.60e-03

Pos logit contributions
 Oliver+0.018
smart+0.017
 court+0.017
 battlefield+0.016
oon+0.016
Neg logit contributions
by-0.019
packs-0.019
 hats-0.018
outed-0.018
 happened-0.018
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
oc+0.006
 battlefield+0.006
oon+0.006
 Oliver+0.005
Mic+0.005
Neg logit contributions
 hats-0.009
 luck-0.009
 happened-0.009
outed-0.009
by-0.009
Token
Token ID6184
Feature activation-1.36e-02

Pos logit contributions
oc+0.021
 battlefield+0.020
oon+0.019
 defeat+0.019
Mic+0.018
Neg logit contributions
 de-0.014
 hats-0.013
outed-0.013
 favorite-0.012
 happened-0.012
Token
Token ID95
Feature activation-1.05e-02

Pos logit contributions
 hats+0.019
outed+0.019
 luck+0.018
 favorite+0.018
 coats+0.018
Neg logit contributions
oc-0.018
 Oliver-0.018
smart-0.018
oon-0.017
Mic-0.017
Token
Token ID26391
Feature activation-5.33e-03

Pos logit contributions
 hats+0.013
bows+0.013
Deal+0.013
outed+0.013
 absolute+0.012
Neg logit contributions
 Oliver-0.015
oc-0.014
smart-0.014
Mic-0.013
 Owl-0.013
Token
Token ID129
Feature activation+9.76e-03

Pos logit contributions
 hats+0.007
packs+0.007
outed+0.006
by+0.006
 favorite+0.006
Neg logit contributions
 Oliver-0.008
smart-0.008
oon-0.008
oc-0.008
 battlefield-0.008
Token
Token ID241
Feature activation-4.23e-02

Pos logit contributions
 Oliver+0.016
smart+0.016
oc+0.016
oon+0.015
Mic+0.015
Neg logit contributions
 hats-0.012
outed-0.011
 favorite-0.011
 absolute-0.010
 coats-0.010
TokenThat
Token ID2504
Feature activation-2.34e-02

Pos logit contributions
outed+0.070
 luck+0.068
 hats+0.068
packs+0.066
by+0.066
Neg logit contributions
oc-0.050
 Oliver-0.049
oon-0.049
 court-0.046
smart-0.045
Token,
Token ID11
Feature activation+3.68e-04

Pos logit contributions
outed+0.031
 hats+0.031
 luck+0.030
by+0.029
packs+0.029
Neg logit contributions
 Oliver-0.035
oc-0.035
oon-0.033
smart-0.033
 court-0.032
Token my
Token ID616
Feature activation-2.62e-02

Pos logit contributions
oc+0.001
Mic+0.000
 battlefield+0.000
smart+0.000
oon+0.000
Neg logit contributions
 hats-0.001
 luck-0.001
 best-0.001
 happened-0.001
 favorite-0.001
Token darling
Token ID40003
Feature activation+1.03e-02

Pos logit contributions
outed+0.032
 hats+0.031
packs+0.030
 luck+0.029
 coats+0.029
Neg logit contributions
oc-0.042
 Oliver-0.041
oon-0.040
 court-0.039
smart-0.039
Token,
Token ID11
Feature activation-6.83e-03

Pos logit contributions
oc+0.011
oon+0.010
 Oliver+0.010
smart+0.010
 battlefield+0.010
Neg logit contributions
 hats-0.018
outed-0.018
 luck-0.017
by-0.017
packs-0.017
Token box
Token ID3091
Feature activation+6.28e-03

Pos logit contributions
 Oliver+0.006
oc+0.006
 court+0.006
oon+0.006
smart+0.006
Neg logit contributions
outed-0.005
packs-0.005
 hats-0.005
by-0.005
 absolute-0.005
Token.
Token ID13
Feature activation-3.07e-03

Pos logit contributions
 Oliver+0.008
oc+0.008
oon+0.008
smart+0.008
 court+0.008
Neg logit contributions
outed-0.009
 hats-0.009
 luck-0.009
packs-0.009
by-0.009
Token
Token ID198
Feature activation+5.90e-03

Pos logit contributions
outed+0.004
 hats+0.004
packs+0.004
 de+0.004
 favorite+0.004
Neg logit contributions
pping-0.004
oon-0.004
 Oliver-0.004
 battlefield-0.004
oc-0.004
Token
Token ID198
Feature activation+7.16e-04

Pos logit contributions
 Oliver+0.008
 battlefield+0.008
oon+0.008
pping+0.008
cess+0.008
Neg logit contributions
 hats-0.008
outed-0.008
packs-0.007
 de-0.007
by-0.007
Token"
Token ID1
Feature activation-9.19e-03

Pos logit contributions
 Oliver+0.001
 battlefield+0.001
pping+0.001
cess+0.001
oon+0.001
Neg logit contributions
 hats-0.001
OK-0.001
 jackets-0.001
ara-0.001
packs-0.001
TokenWhere
Token ID8496
Feature activation-3.67e-02

Pos logit contributions
outed+0.013
 luck+0.013
 hats+0.013
by+0.013
 favorite+0.013
Neg logit contributions
oc-0.013
 Oliver-0.013
oon-0.012
smart-0.012
 court-0.012
Token is
Token ID318
Feature activation+1.17e-02

Pos logit contributions
outed+0.042
 hats+0.040
 outfits+0.038
by+0.038
 luck+0.038
Neg logit contributions
oc-0.062
 Oliver-0.062
smart-0.060
oon-0.060
 court-0.058
Token my
Token ID616
Feature activation-6.91e-03

Pos logit contributions
oc+0.011
 Oliver+0.011
oon+0.011
smart+0.010
 court+0.010
Neg logit contributions
outed-0.022
 hats-0.022
 luck-0.021
packs-0.021
by-0.021
Token treasure
Token ID14068
Feature activation+9.20e-03

Pos logit contributions
outed+0.009
 hats+0.008
by+0.008
packs+0.008
 absolute+0.008
Neg logit contributions
 Oliver-0.011
oc-0.011
oon-0.011
 court-0.011
smart-0.010
Token?"
Token ID1701
Feature activation+6.48e-03

Pos logit contributions
 Oliver+0.010
oc+0.010
oon+0.010
smart+0.009
 court+0.009
Neg logit contributions
outed-0.016
 hats-0.015
 luck-0.015
packs-0.015
by-0.015
Token he
Token ID339
Feature activation-7.64e-03

Pos logit contributions
oon+0.009
oc+0.009
 Oliver+0.008
smart+0.008
Mic+0.008
Neg logit contributions
 hats-0.010
outed-0.009
 coats-0.009
 favorite-0.009
packs-0.009
Token Sarah
Token ID10490
Feature activation-2.25e-04

Pos logit contributions
oc+0.012
oon+0.011
 Oliver+0.011
smart+0.011
 court+0.010
Neg logit contributions
 hats-0.020
outed-0.020
 coats-0.019
 luck-0.019
packs-0.019
Token came
Token ID1625
Feature activation+1.01e-02

Pos logit contributions
 hats+0.000
outed+0.000
by+0.000
 happened+0.000
packs+0.000
Neg logit contributions
oc-0.000
smart-0.000
oon-0.000
 Oliver-0.000
Mic-0.000
Token up
Token ID510
Feature activation-3.89e-03

Pos logit contributions
oc+0.017
oon+0.015
 Oliver+0.015
smart+0.014
Mic+0.014
Neg logit contributions
by-0.014
packs-0.014
 luck-0.013
outed-0.013
 favorite-0.013
Token with
Token ID351
Feature activation+3.00e-03

Pos logit contributions
outed+0.005
by+0.005
 favorite+0.005
 luck+0.005
packs+0.005
Neg logit contributions
oc-0.006
oon-0.006
Mic-0.006
 Oliver-0.006
 battlefield-0.005
Token an
Token ID281
Feature activation+4.00e-03

Pos logit contributions
oc+0.004
 Oliver+0.004
oon+0.004
smart+0.004
 court+0.004
Neg logit contributions
outed-0.004
 hats-0.004
 luck-0.004
packs-0.004
by-0.004
Token idea
Token ID2126
Feature activation-4.22e-02

Pos logit contributions
oc+0.008
 Oliver+0.008
oon+0.008
smart+0.008
 court+0.008
Neg logit contributions
outed-0.003
 hats-0.003
by-0.003
packs-0.003
 luck-0.003
Token.
Token ID13
Feature activation+6.01e-03

Pos logit contributions
 hats+0.056
outed+0.056
packs+0.054
 luck+0.054
 coats+0.052
Neg logit contributions
 Oliver-0.061
oc-0.061
oon-0.059
 battlefield-0.057
 court-0.056
Token She
Token ID1375
Feature activation+1.28e-04

Pos logit contributions
oc+0.011
oon+0.011
pping+0.010
 defeated+0.010
 defeat+0.010
Neg logit contributions
outed-0.006
 hats-0.006
packs-0.006
 coats-0.006
 favorite-0.006
Token said
Token ID531
Feature activation+8.71e-03

Pos logit contributions
oon+0.000
oc+0.000
smart+0.000
 Oliver+0.000
 court+0.000
Neg logit contributions
outed-0.000
 hats-0.000
by-0.000
 favorite-0.000
 coats-0.000
Token excited
Token ID6568
Feature activation-1.53e-03

Pos logit contributions
oc+0.012
oon+0.011
 battlefield+0.010
 Oliver+0.009
Mic+0.009
Neg logit contributions
 luck-0.015
 hats-0.014
 favorite-0.014
 best-0.014
 happened-0.014
Tokenly
Token ID306
Feature activation-2.09e-03

Pos logit contributions
outed+0.002
packs+0.002
 absolute+0.002
 hats+0.002
 luck+0.002
Neg logit contributions
 Oliver-0.003
oc-0.002
smart-0.002
oon-0.002
 court-0.002
Token.
Token ID13
Feature activation+4.33e-03

Pos logit contributions
 hats+0.058
outed+0.057
packs+0.056
 luck+0.055
 coats+0.054
Neg logit contributions
 Oliver-0.063
oc-0.063
oon-0.060
 battlefield-0.058
smart-0.058
Token
Token ID6184
Feature activation-1.20e-02

Pos logit contributions
oon+0.008
pping+0.007
oc+0.007
smart+0.007
 defeated+0.007
Neg logit contributions
outed-0.005
 hats-0.005
 favorite-0.005
 names-0.004
 de-0.004
Token
Token ID95
Feature activation-8.17e-03

Pos logit contributions
 hats+0.016
Deal+0.015
bows+0.015
 favorite+0.015
 luck+0.015
Neg logit contributions
 Oliver-0.016
smart-0.016
oc-0.015
oon-0.015
 since-0.014
Token
Token ID26391
Feature activation-4.36e-03

Pos logit contributions
 absolute+0.010
 hats+0.010
bows+0.010
Deal+0.010
 favorite+0.010
Neg logit contributions
 Oliver-0.011
smart-0.011
 impressed-0.010
oc-0.010
ner-0.010
Token
Token ID129
Feature activation+7.92e-03

Pos logit contributions
packs+0.006
 hats+0.006
 favorite+0.006
uffy+0.006
bows+0.006
Neg logit contributions
 Oliver-0.006
smart-0.005
ner-0.005
 shar-0.005
oon-0.005
Token
Token ID241
Feature activation-4.11e-02

Pos logit contributions
smart+0.013
 Oliver+0.012
oon+0.012
oc+0.012
ner+0.011
Neg logit contributions
 hats-0.010
 favorite-0.010
 names-0.009
 absolute-0.009
aws-0.009
TokenLet
Token ID5756
Feature activation-2.83e-03

Pos logit contributions
outed+0.067
 luck+0.065
 hats+0.062
ishes+0.061
 coats+0.061
Neg logit contributions
oc-0.057
oon-0.049
"-0.049
 Oliver-0.047
smart-0.047
Tokenâ
Token ID22940
Feature activation-1.82e-02

Pos logit contributions
outed+0.006
packs+0.005
 hats+0.005
 luck+0.005
 coats+0.005
Neg logit contributions
oc-0.003
 Oliver-0.003
oon-0.002
"-0.002
smart-0.002
Token
Token ID26391
Feature activation-7.57e-03

Pos logit contributions
 hats+0.031
 luck+0.031
outed+0.031
by+0.031
 absolute+0.030
Neg logit contributions
 Oliver-0.019
oc-0.017
oon-0.017
smart-0.016
 battlefield-0.016
Token
Token ID8151
Feature activation+5.91e-03

Pos logit contributions
packs+0.010
 hats+0.010
 favorite+0.009
 coats+0.009
by+0.009
Neg logit contributions
 Oliver-0.011
oon-0.011
smart-0.010
 battlefield-0.010
ner-0.010
Tokens
Token ID82
Feature activation-5.41e-03

Pos logit contributions
 Oliver+0.009
 battlefield+0.009
oon+0.009
oc+0.009
Mic+0.008
Neg logit contributions
outed-0.008
packs-0.007
by-0.007
 favorite-0.007
aws-0.007