TOP ACTIVATIONS
MAX = 0.106

came back . THE <|endoftext|> Once upon a time
again tomorrow . THE <|endoftext|> Once upon a time
so happy . THE <|endoftext|> Once upon a time
was . THE <|endoftext|> T ina was feeling
arm chair . THE <|endoftext|> Once upon a time
available . THE <|endoftext|> Once upon a time
delicious ! THE <|endoftext|> Elsa was playing chess
a brave girl named Let icia . She lived on a
happy . THE <|endoftext|> Once upon a time
. One day , Let icia had a big idea .
. THE <|endoftext|> Once upon a time
collecting . THE <|endoftext|> Once upon a time
restless . THE <|endoftext|> Dad smiled at his
cloth and wiped the dirt off of her knee . But
special talent . THE <|endoftext|> Once upon a time
Sam 's kind gesture made Ms . Smith feel much better
feel better . THE <|endoftext|> John and his mother
out a cloth and wiped off the dirt from Mia 's
face . THE <|endoftext|> Once upon a time
a big cloth and wiped off the mud from the child

MIN ACTIVATIONS
MIN = -0.108

it away in a wheel bar row . Once
dolls around in a wheel bar row she had found in
back with a big wheel bar row . He asked the
sund ae with lots of topp ings . They
. He found a wheel bar row , a tr amp
to Mom my one by one . Once they
â That one costs more , â
the cand ies one by one and enjoyed them all .
, this time adding an ult im atum . She said
rag for a shiny new one , she had made her
shining brightly in the sky one day . But then ,
him a big red wheel bar row and filled it with
. She saw a wheel bar row , a large sp
â This one please , â said
The wheel bar row wheel ed the cup
Sam 's friends one by one and made them surrender .
t an expensive one . He smiled and said
him he would grant her one wish . The little girl
" But this one is the best !" Tom
sund ae with lots of topp ings . Tim my was

INTERVAL 0.052 - 0.106
CONTAINS 0.124%

liked to display and show off to her friends . Tom
hugged his mother before running off again . He would always
sweep the flour and throw away the jar . Then they
able to watch the little girl smile and to remember when
So they ran off to the garden and the

INTERVAL -0.001 - 0.052
CONTAINS 52.243%

. The smart thing spun higher and higher
him to school , holding his hand all the way .
field , over the mountains and the sea . Everywhere the
looked pale and sad . She saw his teeth and they
to go to the park to play . She saw a

INTERVAL -0.054 - -0.001
CONTAINS 47.488%

!" Sam shouted as he threw the red rocket as high
The little girl listened . She heard the birds singing
sad . Joe felt bad and he apologised to Sam for
of tag . Lily was scared to be " it "
Mom hugged her and said , " Okay ,

INTERVAL -0.108 - -0.054
CONTAINS 0.144%

many toys , but their favorite was a big , soft
make a difference . <|endoftext|> One day , Jack was in
The refrigerator was his new favorite thing . He was so
over to it and with one bite , he slur ped
. The tray broke in half and the shapes and colors
Token came
Token ID1625
Feature activation-1.63e-02

Pos logit contributions
P+0.012
 best+0.011
joy+0.011
rob+0.011
robat+0.011
Neg logit contributions
plets-0.012
 runway-0.012
ramids-0.012
ifying-0.012
umes-0.011
Token back
Token ID736
Feature activation-1.30e-02

Pos logit contributions
P+0.022
 best+0.021
joy+0.019
my+0.019
 seeker+0.018
Neg logit contributions
plets-0.030
 runway-0.029
ramids-0.028
mic-0.028
umes-0.027
Token.
Token ID13
Feature activation+3.07e-03

Pos logit contributions
P+0.018
 best+0.015
joy+0.015
rob+0.015
robat+0.015
Neg logit contributions
plets-0.023
 runway-0.023
ramids-0.023
ifying-0.022
umes-0.022
Token
Token ID198
Feature activation-3.29e-03

Pos logit contributions
plets+0.006
 runway+0.006
ramids+0.006
ifying+0.006
umes+0.005
Neg logit contributions
P-0.004
joy-0.003
 best-0.003
rob-0.003
 seeker-0.003
Token
Token ID198
Feature activation-1.55e-03

Pos logit contributions
P+0.005
 best+0.005
rob+0.005
robat+0.005
joy+0.005
Neg logit contributions
plets-0.005
ramids-0.005
 runway-0.005
ifying-0.005
umes-0.005
TokenTHE
Token ID10970
Feature activation+1.00e-01

Pos logit contributions
P+0.002
 best+0.002
joy+0.002
rob+0.002
robat+0.002
Neg logit contributions
plets-0.002
 runway-0.002
ramids-0.002
ifying-0.002
umes-0.002
Token<|endoftext|>
Token ID50256
Feature activation-6.70e-03

Pos logit contributions
ifying+0.225
plets+0.225
 runway+0.219
umes+0.219
ramids+0.218
Neg logit contributions
P-0.083
 best-0.075
rob-0.072
 seeker-0.070
joy-0.068
TokenOnce
Token ID7454
Feature activation+1.05e-02

Pos logit contributions
P+0.008
Deal+0.008
 best+0.008
 seeker+0.008
 moderation+0.008
Neg logit contributions
plets-0.012
ifying-0.011
ramids-0.011
 runway-0.010
umes-0.010
Token upon
Token ID2402
Feature activation+2.37e-02

Pos logit contributions
plets+0.019
ramids+0.019
 runway+0.019
ifying+0.019
umes+0.018
Neg logit contributions
P-0.013
rob-0.012
robat-0.011
 seeker-0.011
 best-0.011
Token a
Token ID257
Feature activation-7.49e-03

Pos logit contributions
plets+0.040
 runway+0.039
ramids+0.039
ifying+0.038
umes+0.037
Neg logit contributions
P-0.035
rob-0.030
 best-0.030
joy-0.030
robat-0.030
Token time
Token ID640
Feature activation-1.14e-02

Pos logit contributions
rob+0.011
robat+0.010
joy+0.010
ests+0.010
 seeker+0.010
Neg logit contributions
 runway-0.011
ifying-0.010
plets-0.010
 cum-0.010
inated-0.010
Token again
Token ID757
Feature activation-1.40e-02

Pos logit contributions
P+0.023
 moderation+0.021
Deal+0.021
rob+0.020
joy+0.020
Neg logit contributions
 runway-0.019
uring-0.019
plets-0.019
ured-0.019
ramids-0.018
Token tomorrow
Token ID9439
Feature activation+4.54e-03

Pos logit contributions
P+0.022
rob+0.019
robat+0.019
Deal+0.018
joy+0.018
Neg logit contributions
 runway-0.022
plets-0.021
ifying-0.021
ramids-0.021
uring-0.020
Token.
Token ID13
Feature activation-4.58e-04

Pos logit contributions
plets+0.008
 runway+0.008
ramids+0.008
ifying+0.008
umes+0.008
Neg logit contributions
P-0.006
rob-0.005
 best-0.005
robat-0.005
joy-0.005
Token
Token ID198
Feature activation-5.16e-04

Pos logit contributions
P+0.001
joy+0.000
 best+0.000
rob+0.000
robat+0.000
Neg logit contributions
plets-0.001
 runway-0.001
ramids-0.001
ifying-0.001
umes-0.001
Token
Token ID198
Feature activation-1.79e-04

Pos logit contributions
P+0.001
 best+0.001
rob+0.001
joy+0.001
robat+0.001
Neg logit contributions
plets-0.001
 runway-0.001
ramids-0.001
ifying-0.001
umes-0.001
TokenTHE
Token ID10970
Feature activation+9.93e-02

Pos logit contributions
P+0.000
 best+0.000
robat+0.000
joy+0.000
rob+0.000
Neg logit contributions
plets-0.000
ramids-0.000
 runway-0.000
ifying-0.000
umes-0.000
Token<|endoftext|>
Token ID50256
Feature activation-6.57e-03

Pos logit contributions
plets+0.210
ifying+0.210
 runway+0.205
ramids+0.204
umes+0.204
Neg logit contributions
P-0.097
 best-0.087
rob-0.087
robat-0.083
 seeker-0.080
TokenOnce
Token ID7454
Feature activation+1.01e-02

Pos logit contributions
P+0.008
Deal+0.008
 best+0.008
 seeker+0.008
 moderation+0.008
Neg logit contributions
plets-0.011
ifying-0.011
ramids-0.010
 runway-0.010
umes-0.009
Token upon
Token ID2402
Feature activation+2.25e-02

Pos logit contributions
ramids+0.017
plets+0.017
 runway+0.017
ifying+0.017
umes+0.016
Neg logit contributions
P-0.014
rob-0.012
robat-0.012
Deal-0.012
 moderation-0.012
Token a
Token ID257
Feature activation-8.19e-03

Pos logit contributions
plets+0.038
 runway+0.037
ramids+0.037
ifying+0.036
umes+0.035
Neg logit contributions
P-0.033
 best-0.028
rob-0.028
joy-0.028
robat-0.028
Token time
Token ID640
Feature activation-1.16e-02

Pos logit contributions
rob+0.012
robat+0.011
ests+0.011
joy+0.011
 seeker+0.011
Neg logit contributions
ifying-0.011
 runway-0.011
plets-0.011
 cum-0.011
inated-0.011
Token so
Token ID523
Feature activation+1.46e-02

Pos logit contributions
plets+0.018
ramids+0.017
 runway+0.017
ifying+0.017
umes+0.016
Neg logit contributions
P-0.014
 best-0.014
joy-0.013
my-0.013
 seeker-0.012
Token happy
Token ID3772
Feature activation+1.41e-02

Pos logit contributions
plets+0.028
ramids+0.028
 runway+0.028
ifying+0.026
umes+0.026
Neg logit contributions
P-0.019
 best-0.018
joy-0.016
my-0.015
 moderation-0.015
Token.
Token ID13
Feature activation-1.08e-03

Pos logit contributions
plets+0.025
ramids+0.024
 runway+0.024
ifying+0.024
umes+0.023
Neg logit contributions
P-0.020
 best-0.018
joy-0.018
rob-0.017
robat-0.017
Token
Token ID198
Feature activation+4.13e-03

Pos logit contributions
P+0.002
 best+0.001
joy+0.001
rob+0.001
robat+0.001
Neg logit contributions
plets-0.002
 runway-0.002
ramids-0.002
ifying-0.002
umes-0.002
Token
Token ID198
Feature activation+3.56e-03

Pos logit contributions
plets+0.007
 runway+0.007
ramids+0.007
ifying+0.007
umes+0.007
Neg logit contributions
P-0.006
 best-0.005
joy-0.005
rob-0.005
robat-0.005
TokenTHE
Token ID10970
Feature activation+9.91e-02

Pos logit contributions
plets+0.005
ramids+0.005
 runway+0.005
ifying+0.005
umes+0.005
Neg logit contributions
P-0.006
 best-0.005
rob-0.005
robat-0.005
joy-0.005
Token<|endoftext|>
Token ID50256
Feature activation-4.88e-04

Pos logit contributions
plets+0.230
ifying+0.227
umes+0.218
ramids+0.215
lights+0.214
Neg logit contributions
P-0.079
 best-0.072
rob-0.069
joy-0.064
robat-0.064
TokenOnce
Token ID7454
Feature activation+8.40e-03

Pos logit contributions
P+0.001
Deal+0.001
 best+0.001
 moderation+0.001
 seeker+0.001
Neg logit contributions
plets-0.001
ifying-0.001
ramids-0.001
 runway-0.001
umes-0.001
Token upon
Token ID2402
Feature activation+2.16e-02

Pos logit contributions
 runway+0.014
ramids+0.014
plets+0.014
ifying+0.014
umes+0.013
Neg logit contributions
P-0.012
rob-0.011
robat-0.010
Deal-0.010
 moderation-0.010
Token a
Token ID257
Feature activation-1.32e-02

Pos logit contributions
plets+0.037
 runway+0.037
ramids+0.036
ifying+0.035
umes+0.035
Neg logit contributions
P-0.031
 best-0.026
rob-0.026
joy-0.026
robat-0.026
Token time
Token ID640
Feature activation-1.90e-02

Pos logit contributions
rob+0.019
robat+0.018
ests+0.017
P+0.017
 seeker+0.016
Neg logit contributions
ifying-0.019
 runway-0.019
inated-0.018
 cum-0.018
mic-0.018
Token was
Token ID373
Feature activation+5.30e-03

Pos logit contributions
P+0.046
rob+0.040
joy+0.040
 best+0.040
robat+0.040
Neg logit contributions
plets-0.042
 runway-0.041
ramids-0.041
ifying-0.040
umes-0.039
Token.
Token ID13
Feature activation-8.65e-03

Pos logit contributions
ramids+0.011
plets+0.011
 runway+0.010
ifying+0.010
umes+0.010
Neg logit contributions
P-0.006
 best-0.006
my-0.005
joy-0.005
 moderation-0.005
Token
Token ID220
Feature activation-3.71e-03

Pos logit contributions
P+0.011
rob+0.009
robat+0.009
 seeker+0.009
 best+0.009
Neg logit contributions
ramids-0.016
plets-0.016
ifying-0.015
 runway-0.015
umes-0.015
Token
Token ID198
Feature activation-1.16e-03

Pos logit contributions
P+0.004
 best+0.003
joy+0.003
rob+0.003
robat+0.003
Neg logit contributions
plets-0.008
 runway-0.008
ramids-0.008
ifying-0.008
umes-0.007
Token
Token ID198
Feature activation+8.70e-04

Pos logit contributions
P+0.002
 best+0.002
 seeker+0.002
rob+0.002
joy+0.002
Neg logit contributions
plets-0.002
ramids-0.002
 runway-0.002
ifying-0.002
umes-0.002
TokenTHE
Token ID10970
Feature activation+9.78e-02

Pos logit contributions
plets+0.001
 runway+0.001
ramids+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.002
 best-0.001
joy-0.001
rob-0.001
robat-0.001
Token<|endoftext|>
Token ID50256
Feature activation-2.97e-03

Pos logit contributions
plets+0.215
ifying+0.210
 runway+0.208
ramids+0.207
umes+0.206
Neg logit contributions
P-0.091
 best-0.079
rob-0.078
joy-0.076
robat-0.075
TokenT
Token ID51
Feature activation+1.48e-02

Pos logit contributions
P+0.004
Deal+0.004
 best+0.004
 seeker+0.004
 moderation+0.003
Neg logit contributions
plets-0.005
ifying-0.005
ramids-0.005
 runway-0.005
umes-0.004
Tokenina
Token ID1437
Feature activation+2.58e-02

Pos logit contributions
ramids+0.025
plets+0.025
 runway+0.025
ifying+0.024
umes+0.023
Neg logit contributions
P-0.021
 best-0.018
 seeker-0.018
joy-0.018
rob-0.018
Token was
Token ID373
Feature activation+3.05e-03

Pos logit contributions
plets+0.049
ramids+0.048
ifying+0.047
 runway+0.047
umes+0.047
Neg logit contributions
P-0.034
 best-0.029
my-0.028
joy-0.028
rob-0.028
Token feeling
Token ID4203
Feature activation+1.26e-02

Pos logit contributions
 runway+0.005
plets+0.005
ramids+0.005
ifying+0.004
umes+0.004
Neg logit contributions
P-0.005
rob-0.004
robat-0.004
joy-0.004
Deal-0.004
Token arm
Token ID3211
Feature activation+2.17e-02

Pos logit contributions
P+0.006
 best+0.005
joy+0.005
robat+0.005
 seeker+0.005
Neg logit contributions
plets-0.009
ramids-0.008
 runway-0.008
ifying-0.008
umes-0.008
Tokenchair
Token ID16337
Feature activation+3.05e-02

Pos logit contributions
ramids+0.040
plets+0.039
 runway+0.038
ifying+0.038
umes+0.038
Neg logit contributions
P-0.027
 best-0.026
my-0.025
rob-0.024
robat-0.024
Token.
Token ID13
Feature activation-3.86e-03

Pos logit contributions
plets+0.055
ramids+0.054
 runway+0.054
ifying+0.052
umes+0.051
Neg logit contributions
P-0.041
 best-0.036
rob-0.035
joy-0.035
robat-0.035
Token
Token ID198
Feature activation-6.58e-03

Pos logit contributions
P+0.005
joy+0.004
 best+0.004
 moderation+0.004
my+0.004
Neg logit contributions
plets-0.007
 runway-0.007
ramids-0.007
ifying-0.007
umes-0.007
Token
Token ID198
Feature activation-3.14e-03

Pos logit contributions
P+0.008
 best+0.007
rob+0.007
robat+0.007
joy+0.007
Neg logit contributions
plets-0.012
 runway-0.012
ramids-0.012
ifying-0.011
umes-0.011
TokenTHE
Token ID10970
Feature activation+9.75e-02

Pos logit contributions
P+0.005
 moderation+0.004
joy+0.004
robat+0.004
 best+0.004
Neg logit contributions
plets-0.006
ramids-0.005
 runway-0.005
ifying-0.005
umes-0.005
Token<|endoftext|>
Token ID50256
Feature activation-6.45e-03

Pos logit contributions
plets+0.199
ifying+0.198
ramids+0.194
 runway+0.194
umes+0.193
Neg logit contributions
P-0.103
 best-0.093
rob-0.092
robat-0.089
 seeker-0.088
TokenOnce
Token ID7454
Feature activation+9.52e-03

Pos logit contributions
P+0.008
Deal+0.008
 best+0.008
 seeker+0.008
 moderation+0.007
Neg logit contributions
plets-0.011
ifying-0.010
ramids-0.010
 runway-0.010
umes-0.009
Token upon
Token ID2402
Feature activation+2.21e-02

Pos logit contributions
plets+0.017
ramids+0.017
 runway+0.017
ifying+0.017
umes+0.016
Neg logit contributions
P-0.012
rob-0.011
robat-0.010
 best-0.010
joy-0.010
Token a
Token ID257
Feature activation-6.29e-03

Pos logit contributions
plets+0.036
 runway+0.035
ramids+0.035
ifying+0.034
umes+0.033
Neg logit contributions
P-0.033
rob-0.029
joy-0.029
robat-0.029
 best-0.028
Token time
Token ID640
Feature activation-1.35e-02

Pos logit contributions
rob+0.009
robat+0.009
ests+0.008
joy+0.008
 seeker+0.008
Neg logit contributions
 runway-0.009
ifying-0.009
plets-0.009
 cum-0.008
keys-0.008
Token available
Token ID1695
Feature activation-1.37e-02

Pos logit contributions
P+0.043
 best+0.042
joy+0.039
 seeker+0.037
my+0.037
Neg logit contributions
plets-0.056
ramids-0.054
 runway-0.053
ifying-0.051
umes-0.051
Token.
Token ID13
Feature activation-6.01e-03

Pos logit contributions
P+0.019
 best+0.016
joy+0.016
rob+0.016
robat+0.015
Neg logit contributions
plets-0.025
 runway-0.024
ramids-0.024
ifying-0.023
umes-0.023
Token
Token ID220
Feature activation-2.72e-03

Pos logit contributions
P+0.007
 best+0.006
joy+0.006
rob+0.006
robat+0.006
Neg logit contributions
plets-0.012
 runway-0.012
ramids-0.012
ifying-0.011
umes-0.011
Token
Token ID198
Feature activation-3.04e-03

Pos logit contributions
P+0.003
 best+0.002
joy+0.002
rob+0.002
robat+0.002
Neg logit contributions
plets-0.006
 runway-0.006
ramids-0.006
ifying-0.006
ured-0.006
Token
Token ID198
Feature activation-7.22e-05

Pos logit contributions
P+0.004
 seeker+0.004
 best+0.004
joy+0.004
rob+0.004
Neg logit contributions
ramids-0.005
plets-0.005
 runway-0.005
umes-0.005
uring-0.005
TokenTHE
Token ID10970
Feature activation+9.67e-02

Pos logit contributions
P+0.000
 best+0.000
joy+0.000
robat+0.000
rob+0.000
Neg logit contributions
plets-0.000
ramids-0.000
 runway-0.000
ifying-0.000
umes-0.000
Token<|endoftext|>
Token ID50256
Feature activation-4.80e-03

Pos logit contributions
plets+0.220
ifying+0.218
 runway+0.214
ramids+0.212
umes+0.211
Neg logit contributions
P-0.080
 best-0.071
rob-0.069
robat-0.066
 seeker-0.065
TokenOnce
Token ID7454
Feature activation+7.75e-03

Pos logit contributions
P+0.006
Deal+0.006
 best+0.006
 seeker+0.006
 moderation+0.006
Neg logit contributions
plets-0.008
ifying-0.008
ramids-0.008
 runway-0.007
umes-0.007
Token upon
Token ID2402
Feature activation+2.21e-02

Pos logit contributions
plets+0.014
ramids+0.014
 runway+0.014
ifying+0.014
umes+0.013
Neg logit contributions
P-0.010
rob-0.009
robat-0.008
joy-0.008
 seeker-0.008
Token a
Token ID257
Feature activation-9.50e-03

Pos logit contributions
plets+0.035
 runway+0.035
ramids+0.034
ifying+0.034
umes+0.032
Neg logit contributions
P-0.033
rob-0.029
robat-0.029
joy-0.029
 best-0.029
Token time
Token ID640
Feature activation-1.44e-02

Pos logit contributions
rob+0.015
robat+0.014
ests+0.013
 seeker+0.013
joy+0.013
Neg logit contributions
ifying-0.012
 cum-0.012
inated-0.012
 runway-0.012
plets-0.012
Token delicious
Token ID12625
Feature activation+3.22e-03

Pos logit contributions
P+0.003
 best+0.003
 moderation+0.003
joy+0.003
my+0.003
Neg logit contributions
 runway-0.004
plets-0.004
ramids-0.004
umes-0.004
mic-0.004
Token!
Token ID0
Feature activation-1.80e-03

Pos logit contributions
plets+0.005
ramids+0.005
ifying+0.005
 runway+0.005
umes+0.005
Neg logit contributions
P-0.005
rob-0.004
 seeker-0.004
robat-0.004
joy-0.004
Token
Token ID220
Feature activation-7.95e-04

Pos logit contributions
P+0.002
my+0.002
joy+0.002
 best+0.002
ossible+0.002
Neg logit contributions
 runway-0.004
plets-0.003
mic-0.003
ured-0.003
uring-0.003
Token
Token ID198
Feature activation+3.78e-03

Pos logit contributions
P+0.001
 best+0.001
joy+0.000
my+0.000
rob+0.000
Neg logit contributions
 runway-0.002
plets-0.002
ramids-0.002
ifying-0.002
ured-0.002
Token
Token ID198
Feature activation+5.02e-03

Pos logit contributions
 runway+0.009
plets+0.009
ramids+0.009
ifying+0.009
umes+0.009
Neg logit contributions
P-0.003
rob-0.002
 best-0.002
robat-0.002
my-0.002
TokenTHE
Token ID10970
Feature activation+9.45e-02

Pos logit contributions
plets+0.009
ramids+0.009
 runway+0.009
ifying+0.009
umes+0.009
Neg logit contributions
P-0.008
Deal-0.006
my-0.006
robat-0.005
 best-0.005
Token<|endoftext|>
Token ID50256
Feature activation-1.04e-03

Pos logit contributions
ifying+0.231
plets+0.229
 runway+0.225
umes+0.221
ramids+0.220
Neg logit contributions
P-0.061
 best-0.055
rob-0.052
joy-0.052
Deal-0.051
TokenElsa
Token ID49050
Feature activation+1.57e-02

Pos logit contributions
P+0.001
Deal+0.001
 moderation+0.001
 best+0.001
 seeker+0.001
Neg logit contributions
plets-0.002
ifying-0.002
ramids-0.002
 runway-0.001
umes-0.001
Token was
Token ID373
Feature activation+3.50e-03

Pos logit contributions
plets+0.030
 runway+0.029
ramids+0.029
ifying+0.029
umes+0.028
Neg logit contributions
P-0.020
 best-0.016
joy-0.016
rob-0.016
robat-0.016
Token playing
Token ID2712
Feature activation-1.07e-02

Pos logit contributions
plets+0.006
 runway+0.006
ramids+0.006
ifying+0.006
umes+0.006
Neg logit contributions
P-0.005
rob-0.004
robat-0.004
joy-0.004
 best-0.004
Token chess
Token ID19780
Feature activation+9.59e-03

Pos logit contributions
rob+0.019
P+0.019
joy+0.019
robat+0.019
 moderation+0.018
Neg logit contributions
 runway-0.012
uring-0.011
ured-0.011
inated-0.011
plets-0.011
Token a
Token ID257
Feature activation+3.82e-03

Pos logit contributions
plets+0.010
 runway+0.010
ramids+0.010
ifying+0.010
umes+0.009
Neg logit contributions
P-0.010
robat-0.009
rob-0.009
joy-0.009
 best-0.009
Token brave
Token ID14802
Feature activation-3.37e-03

Pos logit contributions
 runway+0.006
plets+0.006
ramids+0.005
ifying+0.005
umes+0.005
Neg logit contributions
P-0.006
rob-0.006
robat-0.006
joy-0.005
 moderation-0.005
Token girl
Token ID2576
Feature activation+7.96e-03

Pos logit contributions
P+0.005
rob+0.004
 moderation+0.004
robat+0.004
 best+0.004
Neg logit contributions
plets-0.006
 runway-0.006
ramids-0.006
ifying-0.005
umes-0.005
Token named
Token ID3706
Feature activation+1.75e-02

Pos logit contributions
plets+0.014
ramids+0.013
 runway+0.013
ifying+0.013
mic+0.013
Neg logit contributions
P-0.012
 best-0.010
my-0.010
 seeker-0.010
joy-0.010
Token Let
Token ID3914
Feature activation-1.20e-02

Pos logit contributions
plets+0.031
 runway+0.030
ramids+0.030
ifying+0.029
umes+0.029
Neg logit contributions
P-0.025
 best-0.021
joy-0.021
rob-0.021
 seeker-0.020
Tokenicia
Token ID33577
Feature activation+9.44e-02

Pos logit contributions
P+0.015
 best+0.013
my+0.012
rob+0.012
robat+0.011
Neg logit contributions
plets-0.024
ifying-0.024
ramids-0.024
 runway-0.023
umes-0.023
Token.
Token ID13
Feature activation+1.13e-02

Pos logit contributions
plets+0.219
ramids+0.203
 runway+0.198
ifying+0.197
umes+0.194
Neg logit contributions
P-0.098
 best-0.089
my-0.080
 seeker-0.078
ossible-0.076
Token She
Token ID1375
Feature activation+2.43e-02

Pos logit contributions
plets+0.020
 runway+0.020
ramids+0.020
ifying+0.019
umes+0.019
Neg logit contributions
P-0.016
 best-0.014
joy-0.014
 seeker-0.013
rob-0.013
Token lived
Token ID5615
Feature activation+2.26e-02

Pos logit contributions
plets+0.045
ifying+0.044
ramids+0.044
umes+0.043
 runway+0.042
Neg logit contributions
P-0.036
 best-0.031
rob-0.029
 seeker-0.029
my-0.028
Token on
Token ID319
Feature activation+2.31e-02

Pos logit contributions
uring+0.018
umes+0.018
 runway+0.018
 capt+0.017
through+0.017
Neg logit contributions
rob-0.047
robat-0.046
ah-0.044
 moderation-0.042
P-0.041
Token a
Token ID257
Feature activation-1.27e-02

Pos logit contributions
plets+0.046
ramids+0.045
ifying+0.044
 runway+0.044
umes+0.044
Neg logit contributions
P-0.029
 best-0.025
rob-0.024
 seeker-0.023
 moderation-0.023
Token happy
Token ID3772
Feature activation+2.05e-02

Pos logit contributions
P+0.000
 best+0.000
joy+0.000
 moderation+0.000
rob+0.000
Neg logit contributions
plets-0.000
ramids-0.000
 runway-0.000
ifying-0.000
umes-0.000
Token.
Token ID13
Feature activation-6.40e-03

Pos logit contributions
plets+0.040
ramids+0.039
 runway+0.039
ifying+0.038
umes+0.038
Neg logit contributions
P-0.025
 best-0.022
joy-0.022
robat-0.020
rob-0.020
Token
Token ID220
Feature activation-1.25e-03

Pos logit contributions
P+0.007
 best+0.006
joy+0.006
rob+0.006
robat+0.006
Neg logit contributions
plets-0.013
 runway-0.013
ramids-0.013
ifying-0.012
umes-0.012
Token
Token ID198
Feature activation+1.35e-04

Pos logit contributions
P+0.001
 best+0.001
joy+0.001
rob+0.001
robat+0.001
Neg logit contributions
plets-0.003
 runway-0.003
ramids-0.003
ifying-0.003
umes-0.003
Token
Token ID198
Feature activation+1.73e-03

Pos logit contributions
plets+0.000
 runway+0.000
ramids+0.000
umes+0.000
ifying+0.000
Neg logit contributions
P-0.000
 seeker-0.000
joy-0.000
 best-0.000
robat-0.000
TokenTHE
Token ID10970
Feature activation+9.44e-02

Pos logit contributions
plets+0.002
ramids+0.002
 runway+0.002
ifying+0.002
umes+0.002
Neg logit contributions
P-0.003
 best-0.003
rob-0.003
robat-0.003
joy-0.003
Token<|endoftext|>
Token ID50256
Feature activation-4.09e-03

Pos logit contributions
plets+0.224
ifying+0.221
umes+0.216
ramids+0.215
 runway+0.214
Neg logit contributions
P-0.067
 best-0.065
rob-0.059
joy-0.058
Deal-0.056
TokenOnce
Token ID7454
Feature activation+5.86e-03

Pos logit contributions
P+0.006
Deal+0.006
 seeker+0.005
 best+0.005
 moderation+0.005
Neg logit contributions
plets-0.006
ifying-0.006
ramids-0.006
 runway-0.006
umes-0.005
Token upon
Token ID2402
Feature activation+2.13e-02

Pos logit contributions
ramids+0.010
 runway+0.010
plets+0.010
ifying+0.009
umes+0.009
Neg logit contributions
P-0.009
rob-0.008
robat-0.007
Deal-0.007
 moderation-0.007
Token a
Token ID257
Feature activation-1.37e-02

Pos logit contributions
plets+0.035
 runway+0.034
ramids+0.034
ifying+0.033
umes+0.033
Neg logit contributions
P-0.031
rob-0.027
robat-0.027
joy-0.027
 best-0.027
Token time
Token ID640
Feature activation-1.86e-02

Pos logit contributions
rob+0.021
robat+0.019
ests+0.018
P+0.018
 seeker+0.018
Neg logit contributions
ifying-0.019
 runway-0.019
inated-0.018
 cum-0.018
mic-0.018
Token.
Token ID13
Feature activation+4.43e-03

Pos logit contributions
P+0.011
 best+0.010
joy+0.009
robat+0.009
my+0.009
Neg logit contributions
plets-0.019
 runway-0.018
ramids-0.018
ifying-0.018
umes-0.017
Token One
Token ID1881
Feature activation-4.29e-02

Pos logit contributions
plets+0.007
 runway+0.007
ifying+0.007
ramids+0.007
umes+0.007
Neg logit contributions
P-0.007
joy-0.006
 best-0.006
 moderation-0.006
 seeker-0.006
Token day
Token ID1110
Feature activation+1.80e-02

Pos logit contributions
P+0.031
 best+0.023
rob+0.021
joy+0.021
robat+0.021
Neg logit contributions
plets-0.106
ramids-0.104
 runway-0.104
ifying-0.102
umes-0.101
Token,
Token ID11
Feature activation-9.07e-04

Pos logit contributions
 runway+0.048
plets+0.046
mic+0.046
ramids+0.045
uring+0.045
Neg logit contributions
P-0.012
 best-0.009
 seeker-0.008
joy-0.007
my-0.006
Token Let
Token ID3914
Feature activation+1.64e-04

Pos logit contributions
P+0.001
 best+0.001
 seeker+0.001
joy+0.001
 boy+0.001
Neg logit contributions
plets-0.001
 runway-0.001
mic-0.001
ramids-0.001
ifying-0.001
Tokenicia
Token ID33577
Feature activation+9.30e-02

Pos logit contributions
plets+0.000
ifying+0.000
 runway+0.000
ramids+0.000
umes+0.000
Neg logit contributions
P-0.000
 best-0.000
my-0.000
rob-0.000
 moderation-0.000
Token had
Token ID550
Feature activation+2.78e-02

Pos logit contributions
plets+0.190
 runway+0.182
ramids+0.179
lights+0.178
ifying+0.175
Neg logit contributions
P-0.111
 best-0.105
 seeker-0.098
my-0.097
 idea-0.090
Token a
Token ID257
Feature activation-3.03e-03

Pos logit contributions
plets+0.058
ramids+0.056
 runway+0.055
ifying+0.054
umes+0.054
Neg logit contributions
P-0.034
 best-0.029
joy-0.027
 moderation-0.026
 seeker-0.026
Token big
Token ID1263
Feature activation+4.98e-03

Pos logit contributions
P+0.004
rob+0.004
robat+0.004
joy+0.004
 moderation+0.003
Neg logit contributions
 runway-0.005
plets-0.005
ramids-0.005
ifying-0.005
umes-0.005
Token idea
Token ID2126
Feature activation-5.14e-03

Pos logit contributions
 runway+0.008
 cum+0.007
ramids+0.006
mic+0.006
inated+0.006
Neg logit contributions
P-0.008
rob-0.007
ests-0.007
joy-0.007
robat-0.007
Token.
Token ID13
Feature activation+4.56e-03

Pos logit contributions
P+0.006
 best+0.005
robat+0.005
joy+0.005
rob+0.005
Neg logit contributions
plets-0.011
 runway-0.010
ramids-0.010
ifying-0.010
umes-0.010
Token.
Token ID13
Feature activation-6.32e-04

Pos logit contributions
P+0.031
 best+0.026
rob+0.026
joy+0.026
robat+0.026
Neg logit contributions
plets-0.040
 runway-0.040
ramids-0.040
ifying-0.039
umes-0.038
Token
Token ID220
Feature activation+2.26e-03

Pos logit contributions
P+0.001
rob+0.001
robat+0.001
 seeker+0.001
 best+0.001
Neg logit contributions
plets-0.001
ramids-0.001
ifying-0.001
 runway-0.001
umes-0.001
Token
Token ID198
Feature activation+3.28e-03

Pos logit contributions
plets+0.005
ramids+0.004
 runway+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.003
rob-0.002
 best-0.002
robat-0.002
joy-0.002
Token
Token ID220
Feature activation+3.83e-03

Pos logit contributions
plets+0.005
ramids+0.004
 runway+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.005
 seeker-0.005
joy-0.005
rob-0.005
robat-0.005
Token
Token ID198
Feature activation+5.19e-03

Pos logit contributions
plets+0.008
ramids+0.007
 runway+0.007
ifying+0.007
umes+0.007
Neg logit contributions
P-0.005
rob-0.004
robat-0.004
 best-0.004
joy-0.004
TokenTHE
Token ID10970
Feature activation+9.27e-02

Pos logit contributions
plets+0.008
 runway+0.008
ramids+0.008
ifying+0.008
umes+0.008
Neg logit contributions
P-0.007
 seeker-0.007
joy-0.007
rob-0.007
robat-0.007
Token<|endoftext|>
Token ID50256
Feature activation+1.07e-03

Pos logit contributions
plets+0.187
 runway+0.184
ramids+0.183
ifying+0.180
umes+0.177
Neg logit contributions
P-0.105
 best-0.089
joy-0.087
rob-0.087
robat-0.086
TokenOnce
Token ID7454
Feature activation+1.05e-02

Pos logit contributions
plets+0.002
ifying+0.002
ramids+0.002
 runway+0.001
umes+0.001
Neg logit contributions
Deal-0.002
P-0.001
 seeker-0.001
 moderation-0.001
 best-0.001
Token upon
Token ID2402
Feature activation+2.31e-02

Pos logit contributions
ramids+0.017
 runway+0.017
plets+0.017
ifying+0.017
lights+0.016
Neg logit contributions
P-0.016
rob-0.014
robat-0.014
Deal-0.013
 seeker-0.013
Token a
Token ID257
Feature activation-1.47e-02

Pos logit contributions
plets+0.036
 runway+0.036
ramids+0.035
ifying+0.035
umes+0.034
Neg logit contributions
P-0.035
rob-0.031
robat-0.031
joy-0.031
 best-0.030
Token time
Token ID640
Feature activation-2.26e-02

Pos logit contributions
rob+0.022
robat+0.021
P+0.020
 seeker+0.020
ests+0.020
Neg logit contributions
inated-0.020
ifying-0.020
 runway-0.020
 cum-0.020
mic-0.019
Token collecting
Token ID13157
Feature activation-1.38e-02

Pos logit contributions
 runway+0.001
plets+0.001
ramids+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.001
rob-0.001
robat-0.001
joy-0.000
 seeker-0.000
Token.
Token ID13
Feature activation-1.14e-02

Pos logit contributions
P+0.020
rob+0.018
 seeker+0.018
robat+0.018
joy+0.017
Neg logit contributions
plets-0.022
 runway-0.022
ifying-0.022
ramids-0.022
umes-0.021
Token
Token ID220
Feature activation-4.75e-03

Pos logit contributions
P+0.016
rob+0.015
robat+0.014
 seeker+0.014
 best+0.014
Neg logit contributions
plets-0.019
ramids-0.019
ifying-0.019
 runway-0.018
umes-0.018
Token
Token ID198
Feature activation-2.27e-03

Pos logit contributions
P+0.005
 best+0.004
rob+0.004
joy+0.004
robat+0.004
Neg logit contributions
plets-0.010
ramids-0.010
 runway-0.010
ifying-0.009
umes-0.009
Token
Token ID198
Feature activation-9.10e-04

Pos logit contributions
P+0.003
 seeker+0.003
 best+0.003
rob+0.003
joy+0.003
Neg logit contributions
plets-0.004
ramids-0.004
 runway-0.004
umes-0.004
ifying-0.004
TokenTHE
Token ID10970
Feature activation+9.22e-02

Pos logit contributions
P+0.002
 best+0.001
rob+0.001
joy+0.001
 seeker+0.001
Neg logit contributions
plets-0.001
 runway-0.001
ramids-0.001
ifying-0.001
umes-0.001
Token<|endoftext|>
Token ID50256
Feature activation-1.89e-03

Pos logit contributions
plets+0.204
ifying+0.199
 runway+0.198
ramids+0.198
umes+0.194
Neg logit contributions
P-0.087
 best-0.074
joy-0.071
rob-0.071
robat-0.070
TokenOnce
Token ID7454
Feature activation+8.85e-03

Pos logit contributions
Deal+0.003
P+0.003
 seeker+0.003
 moderation+0.003
 best+0.003
Neg logit contributions
plets-0.003
ifying-0.003
ramids-0.003
 runway-0.003
umes-0.002
Token upon
Token ID2402
Feature activation+2.29e-02

Pos logit contributions
ramids+0.014
 runway+0.014
plets+0.014
ifying+0.014
umes+0.013
Neg logit contributions
P-0.013
rob-0.012
robat-0.012
Deal-0.011
 moderation-0.011
Token a
Token ID257
Feature activation-1.34e-02

Pos logit contributions
plets+0.036
 runway+0.036
ramids+0.035
ifying+0.035
umes+0.034
Neg logit contributions
P-0.035
rob-0.031
robat-0.030
joy-0.030
 best-0.030
Token time
Token ID640
Feature activation-2.05e-02

Pos logit contributions
rob+0.022
robat+0.020
ests+0.019
P+0.019
 seeker+0.019
Neg logit contributions
ifying-0.017
inated-0.017
 cum-0.017
mic-0.016
ln-0.016
Token restless
Token ID42537
Feature activation+3.57e-02

Pos logit contributions
plets+0.004
 runway+0.004
ramids+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.004
rob-0.004
 best-0.003
joy-0.003
robat-0.003
Token.
Token ID13
Feature activation+3.21e-04

Pos logit contributions
plets+0.064
ramids+0.064
 runway+0.062
umes+0.061
ifying+0.060
Neg logit contributions
P-0.047
joy-0.044
 best-0.044
 seeker-0.040
robat-0.040
Token
Token ID220
Feature activation+4.03e-03

Pos logit contributions
plets+0.001
ramids+0.001
ifying+0.001
 runway+0.001
umes+0.001
Neg logit contributions
P-0.000
 seeker-0.000
robat-0.000
rob-0.000
 best-0.000
Token
Token ID198
Feature activation+4.58e-03

Pos logit contributions
 runway+0.009
plets+0.009
ramids+0.009
ifying+0.008
umes+0.008
Neg logit contributions
P-0.004
 best-0.003
joy-0.003
rob-0.003
robat-0.003
Token
Token ID198
Feature activation+6.00e-03

Pos logit contributions
plets+0.008
ramids+0.008
 runway+0.008
ifying+0.008
umes+0.008
Neg logit contributions
P-0.006
 seeker-0.005
joy-0.005
 best-0.005
robat-0.005
TokenTHE
Token ID10970
Feature activation+9.20e-02

Pos logit contributions
plets+0.007
 runway+0.007
ramids+0.006
ifying+0.006
umes+0.006
Neg logit contributions
P-0.011
joy-0.011
 seeker-0.011
 best-0.011
rob-0.011
Token<|endoftext|>
Token ID50256
Feature activation+3.82e-03

Pos logit contributions
plets+0.191
 runway+0.187
ramids+0.187
ifying+0.184
umes+0.181
Neg logit contributions
P-0.099
 best-0.083
rob-0.083
joy-0.082
robat-0.081
TokenDad
Token ID46270
Feature activation-2.91e-02

Pos logit contributions
plets+0.006
ifying+0.006
ramids+0.006
 runway+0.005
umes+0.005
Neg logit contributions
Deal-0.005
P-0.005
 moderation-0.005
 seeker-0.005
 best-0.005
Token smiled
Token ID13541
Feature activation-3.94e-03

Pos logit contributions
P+0.035
 best+0.030
joy+0.029
rob+0.029
robat+0.029
Neg logit contributions
plets-0.056
 runway-0.056
ramids-0.055
ifying-0.054
umes-0.053
Token at
Token ID379
Feature activation-4.16e-04

Pos logit contributions
P+0.005
 best+0.004
joy+0.004
rob+0.004
robat+0.004
Neg logit contributions
plets-0.007
 runway-0.007
ramids-0.007
ifying-0.007
umes-0.007
Token his
Token ID465
Feature activation+1.37e-03

Pos logit contributions
P+0.001
 best+0.001
joy+0.001
rob+0.001
robat+0.001
Neg logit contributions
plets-0.001
 runway-0.001
ramids-0.001
ifying-0.001
umes-0.001
Token cloth
Token ID16270
Feature activation-2.83e-03

Pos logit contributions
plets+0.015
 runway+0.015
ramids+0.014
ifying+0.014
umes+0.014
Neg logit contributions
P-0.011
rob-0.010
joy-0.010
 best-0.009
robat-0.009
Token and
Token ID290
Feature activation+1.13e-02

Pos logit contributions
P+0.004
 best+0.003
joy+0.003
rob+0.003
robat+0.003
Neg logit contributions
plets-0.005
ramids-0.005
 runway-0.005
ifying-0.005
umes-0.005
Token wiped
Token ID21122
Feature activation+1.52e-02

Pos logit contributions
ramids+0.019
 runway+0.019
plets+0.019
ifying+0.019
uring+0.018
Neg logit contributions
P-0.017
 best-0.014
my-0.014
rob-0.014
 vest-0.014
Token the
Token ID262
Feature activation+3.66e-02

Pos logit contributions
plets+0.020
ramids+0.019
 runway+0.019
ifying+0.019
umes+0.018
Neg logit contributions
P-0.028
 best-0.025
joy-0.025
rob-0.025
robat-0.025
Token dirt
Token ID13647
Feature activation+5.51e-02

Pos logit contributions
plets+0.063
ramids+0.062
 runway+0.062
ifying+0.060
umes+0.059
Neg logit contributions
P-0.053
 best-0.046
rob-0.045
joy-0.045
robat-0.045
Token off
Token ID572
Feature activation+9.16e-02

Pos logit contributions
ramids+0.063
plets+0.063
 runway+0.061
ifying+0.059
umes+0.058
Neg logit contributions
P-0.111
 best-0.102
robat-0.096
rob-0.095
my-0.095
Token of
Token ID286
Feature activation+5.50e-02

Pos logit contributions
plets+0.177
ramids+0.176
 runway+0.176
keys+0.174
mic+0.172
Neg logit contributions
P-0.107
 best-0.099
my-0.091
 right-0.088
 gum-0.082
Token her
Token ID607
Feature activation+2.15e-02

Pos logit contributions
plets+0.087
 runway+0.085
ramids+0.085
ifying+0.082
umes+0.081
Neg logit contributions
P-0.087
 best-0.077
 moderation-0.076
joy-0.075
rob-0.075
Token knee
Token ID10329
Feature activation-3.72e-03

Pos logit contributions
 runway+0.037
plets+0.037
ramids+0.036
ifying+0.035
umes+0.035
Neg logit contributions
P-0.031
rob-0.026
joy-0.026
robat-0.026
 seeker-0.025
Token.
Token ID13
Feature activation+5.88e-03

Pos logit contributions
P+0.005
joy+0.005
rob+0.005
robat+0.004
 best+0.004
Neg logit contributions
plets-0.006
 runway-0.006
ramids-0.006
ifying-0.006
umes-0.006
Token But
Token ID887
Feature activation+1.28e-02

Pos logit contributions
keys+0.013
 runway+0.012
plets+0.012
ifying+0.012
aro+0.012
Neg logit contributions
joy-0.006
P-0.005
my-0.005
 best-0.005
 right-0.005
Token special
Token ID2041
Feature activation-1.19e-02

Pos logit contributions
plets+0.020
ramids+0.020
 runway+0.020
ifying+0.019
umes+0.019
Neg logit contributions
P-0.014
 best-0.012
joy-0.012
robat-0.011
rob-0.011
Token talent
Token ID7401
Feature activation-2.31e-02

Pos logit contributions
P+0.018
rob+0.015
 seeker+0.015
robat+0.014
Deal+0.014
Neg logit contributions
 runway-0.020
plets-0.019
ramids-0.019
ifying-0.019
mic-0.018
Token.
Token ID13
Feature activation-8.23e-03

Pos logit contributions
P+0.031
rob+0.026
 best+0.026
joy+0.026
robat+0.026
Neg logit contributions
plets-0.041
 runway-0.041
ramids-0.041
ifying-0.040
umes-0.039
Token
Token ID198
Feature activation+5.42e-04

Pos logit contributions
P+0.008
 best+0.007
joy+0.007
rob+0.007
robat+0.006
Neg logit contributions
plets-0.018
 runway-0.017
ramids-0.017
ifying-0.017
umes-0.017
Token
Token ID198
Feature activation+3.44e-03

Pos logit contributions
plets+0.001
 runway+0.001
ramids+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.001
 best-0.001
rob-0.001
joy-0.001
robat-0.001
TokenTHE
Token ID10970
Feature activation+9.09e-02

Pos logit contributions
plets+0.006
ramids+0.006
 runway+0.005
ifying+0.005
umes+0.005
Neg logit contributions
P-0.006
 best-0.005
robat-0.005
rob-0.005
Deal-0.004
Token<|endoftext|>
Token ID50256
Feature activation-9.39e-04

Pos logit contributions
plets+0.213
ifying+0.208
 runway+0.203
ramids+0.203
umes+0.202
Neg logit contributions
P-0.071
 best-0.065
rob-0.061
joy-0.061
Deal-0.060
TokenOnce
Token ID7454
Feature activation+1.10e-02

Pos logit contributions
Deal+0.001
P+0.001
 moderation+0.001
 seeker+0.001
 best+0.001
Neg logit contributions
plets-0.001
ifying-0.001
ramids-0.001
 runway-0.001
 cum-0.001
Token upon
Token ID2402
Feature activation+2.46e-02

Pos logit contributions
ramids+0.018
 runway+0.018
plets+0.018
ifying+0.018
umes+0.017
Neg logit contributions
P-0.016
rob-0.014
robat-0.014
Deal-0.013
 moderation-0.013
Token a
Token ID257
Feature activation-1.39e-02

Pos logit contributions
plets+0.040
 runway+0.040
ramids+0.039
ifying+0.038
umes+0.037
Neg logit contributions
P-0.037
rob-0.032
robat-0.032
joy-0.032
 best-0.031
Token time
Token ID640
Feature activation-1.96e-02

Pos logit contributions
rob+0.022
robat+0.021
P+0.020
ests+0.019
 seeker+0.019
Neg logit contributions
ifying-0.018
inated-0.018
 cum-0.018
mic-0.018
 runway-0.018
Token Sam
Token ID3409
Feature activation-2.30e-03

Pos logit contributions
P+0.005
 best+0.005
joy+0.005
rob+0.004
 seeker+0.004
Neg logit contributions
plets-0.004
ramids-0.004
 runway-0.004
ifying-0.004
umes-0.004
Token's
Token ID338
Feature activation+2.68e-03

Pos logit contributions
 best+0.003
P+0.003
my+0.003
robat+0.002
joy+0.002
Neg logit contributions
plets-0.004
ifying-0.004
ramids-0.004
 runway-0.004
umes-0.004
Token kind
Token ID1611
Feature activation-2.50e-03

Pos logit contributions
 runway+0.005
ramids+0.004
plets+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.004
rob-0.003
robat-0.003
 seeker-0.003
 moderation-0.003
Token gesture
Token ID18342
Feature activation+1.33e-03

Pos logit contributions
P+0.004
rob+0.003
robat+0.003
 seeker+0.003
 best+0.003
Neg logit contributions
plets-0.004
 runway-0.004
ramids-0.004
ifying-0.004
umes-0.004
Token made
Token ID925
Feature activation+1.03e-02

Pos logit contributions
plets+0.003
ramids+0.003
 runway+0.003
umes+0.002
ifying+0.002
Neg logit contributions
P-0.002
 best-0.001
joy-0.001
robat-0.001
rob-0.001
Token Ms
Token ID6997
Feature activation+9.07e-02

Pos logit contributions
plets+0.014
ramids+0.014
 runway+0.014
umes+0.014
ifying+0.014
Neg logit contributions
P-0.018
 seeker-0.016
rob-0.016
robat-0.016
joy-0.015
Token.
Token ID13
Feature activation+1.16e-02

Pos logit contributions
plets+0.158
ramids+0.157
 runway+0.156
ifying+0.152
umes+0.150
Neg logit contributions
P-0.127
rob-0.107
robat-0.106
 best-0.105
joy-0.105
Token Smith
Token ID4176
Feature activation+1.67e-02

Pos logit contributions
ramids+0.020
plets+0.019
 runway+0.018
ifying+0.018
umes+0.018
Neg logit contributions
P-0.018
 best-0.015
rob-0.015
robat-0.015
Deal-0.015
Token feel
Token ID1254
Feature activation+2.34e-02

Pos logit contributions
plets+0.035
ramids+0.034
 runway+0.033
ifying+0.032
umes+0.031
Neg logit contributions
 best-0.019
my-0.018
P-0.016
 idea-0.016
joy-0.016
Token much
Token ID881
Feature activation+2.72e-02

Pos logit contributions
ramids+0.048
 runway+0.047
plets+0.046
umes+0.044
ants+0.043
Neg logit contributions
P-0.030
 best-0.029
joy-0.025
 moderation-0.025
 right-0.023
Token better
Token ID1365
Feature activation+8.14e-03

Pos logit contributions
plets+0.040
 runway+0.038
ifying+0.037
ured+0.037
mic+0.036
Neg logit contributions
P-0.046
rob-0.042
robat-0.042
 seeker-0.040
icer-0.037
Token feel
Token ID1254
Feature activation+2.29e-02

Pos logit contributions
P+0.007
 best+0.006
rob+0.006
joy+0.006
robat+0.006
Neg logit contributions
plets-0.007
ramids-0.007
 runway-0.007
ifying-0.007
umes-0.007
Token better
Token ID1365
Feature activation+9.64e-03

Pos logit contributions
ramids+0.052
plets+0.051
 runway+0.050
umes+0.048
ifying+0.048
Neg logit contributions
 best-0.023
P-0.023
 moderation-0.020
joy-0.019
 idea-0.019
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
plets+0.016
 runway+0.016
ifying+0.015
ramids+0.015
ured+0.015
Neg logit contributions
P-0.015
rob-0.013
robat-0.012
joy-0.012
 seeker-0.012
Token
Token ID198
Feature activation+6.55e-04

Pos logit contributions
P+0.014
rob+0.012
robat+0.011
 best+0.011
 seeker+0.011
Neg logit contributions
plets-0.021
ramids-0.021
 runway-0.021
ifying-0.020
umes-0.020
Token
Token ID198
Feature activation+2.05e-03

Pos logit contributions
plets+0.001
 runway+0.001
ramids+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.001
 best-0.001
joy-0.001
rob-0.001
robat-0.001
TokenTHE
Token ID10970
Feature activation+8.93e-02

Pos logit contributions
plets+0.004
 runway+0.004
ramids+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.003
 best-0.002
rob-0.002
joy-0.002
robat-0.002
Token<|endoftext|>
Token ID50256
Feature activation-9.26e-04

Pos logit contributions
plets+0.203
ifying+0.199
 runway+0.194
ramids+0.194
umes+0.190
Neg logit contributions
P-0.076
 best-0.070
joy-0.065
Deal-0.064
rob-0.062
TokenJohn
Token ID7554
Feature activation-2.30e-02

Pos logit contributions
Deal+0.001
P+0.001
 seeker+0.001
 moderation+0.001
 best+0.001
Neg logit contributions
plets-0.001
ifying-0.001
ramids-0.001
 runway-0.001
 cum-0.001
Token and
Token ID290
Feature activation-5.45e-03

Pos logit contributions
P+0.031
 best+0.027
joy+0.026
rob+0.026
robat+0.026
Neg logit contributions
plets-0.041
 runway-0.041
ramids-0.040
ifying-0.039
umes-0.039
Token his
Token ID465
Feature activation+6.67e-04

Pos logit contributions
P+0.006
rob+0.004
robat+0.004
joy+0.004
 best+0.004
Neg logit contributions
 runway-0.011
plets-0.011
ramids-0.011
ifying-0.011
umes-0.011
Token mother
Token ID2802
Feature activation+1.07e-03

Pos logit contributions
plets+0.001
ramids+0.001
 runway+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.001
 best-0.001
joy-0.001
rob-0.001
robat-0.001
Token out
Token ID503
Feature activation+2.51e-02

Pos logit contributions
P+0.010
rob+0.009
robat+0.009
joy+0.009
Deal+0.008
Neg logit contributions
ramids-0.007
plets-0.007
 runway-0.007
ifying-0.007
ured-0.007
Token a
Token ID257
Feature activation-9.43e-03

Pos logit contributions
plets+0.044
 runway+0.043
ramids+0.043
ifying+0.041
umes+0.040
Neg logit contributions
P-0.036
 best-0.032
joy-0.031
rob-0.030
 moderation-0.030
Token cloth
Token ID16270
Feature activation-1.38e-02

Pos logit contributions
P+0.013
rob+0.012
robat+0.012
 moderation+0.012
Deal+0.011
Neg logit contributions
 runway-0.016
plets-0.016
ifying-0.015
umes-0.015
ramids-0.015
Token and
Token ID290
Feature activation+9.62e-03

Pos logit contributions
P+0.019
rob+0.017
joy+0.016
 best+0.016
robat+0.016
Neg logit contributions
plets-0.024
 runway-0.024
ramids-0.024
ifying-0.023
umes-0.023
Token wiped
Token ID21122
Feature activation+1.33e-02

Pos logit contributions
ramids+0.017
plets+0.017
 runway+0.017
ifying+0.016
umes+0.015
Neg logit contributions
P-0.014
 best-0.012
my-0.011
 vest-0.011
 seeker-0.011
Token off
Token ID572
Feature activation+8.81e-02

Pos logit contributions
plets+0.017
ramids+0.017
 runway+0.017
ifying+0.016
umes+0.016
Neg logit contributions
P-0.025
joy-0.022
rob-0.022
 best-0.022
robat-0.022
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
plets+0.154
 runway+0.153
ramids+0.149
ifying+0.142
umes+0.141
Neg logit contributions
P-0.123
 best-0.115
joy-0.103
my-0.102
 right-0.098
Token dirt
Token ID13647
Feature activation+4.03e-02

Pos logit contributions
plets+0.039
ramids+0.039
 runway+0.038
ifying+0.038
umes+0.037
Neg logit contributions
P-0.028
 best-0.025
joy-0.024
robat-0.023
rob-0.023
Token from
Token ID422
Feature activation+3.97e-02

Pos logit contributions
plets+0.064
ramids+0.063
 runway+0.063
ifying+0.061
umes+0.060
Neg logit contributions
P-0.062
 best-0.056
robat-0.053
rob-0.053
joy-0.053
Token Mia
Token ID32189
Feature activation-1.50e-02

Pos logit contributions
plets+0.059
ramids+0.057
 runway+0.056
ifying+0.055
umes+0.054
Neg logit contributions
P-0.067
 best-0.060
joy-0.059
rob-0.059
 seeker-0.059
Token's
Token ID338
Feature activation-1.78e-03

Pos logit contributions
P+0.019
 best+0.017
joy+0.016
my+0.016
robat+0.015
Neg logit contributions
plets-0.028
ramids-0.028
 runway-0.028
ifying-0.027
umes-0.026
Token face
Token ID1986
Feature activation-3.51e-02

Pos logit contributions
P+0.021
 best+0.020
joy+0.019
 vest+0.018
robat+0.017
Neg logit contributions
plets-0.029
ramids-0.029
umes-0.028
 runway-0.028
ifying-0.027
Token.
Token ID13
Feature activation-5.49e-03

Pos logit contributions
P+0.041
 best+0.036
joy+0.035
robat+0.033
rob+0.033
Neg logit contributions
plets-0.068
 runway-0.068
ramids-0.068
ifying-0.065
umes-0.065
Token
Token ID220
Feature activation-5.68e-03

Pos logit contributions
P+0.007
robat+0.006
rob+0.006
 seeker+0.006
 best+0.006
Neg logit contributions
plets-0.010
ramids-0.010
ifying-0.010
 runway-0.009
inated-0.009
Token
Token ID198
Feature activation+7.98e-05

Pos logit contributions
P+0.006
 best+0.005
rob+0.005
joy+0.005
robat+0.005
Neg logit contributions
plets-0.012
ramids-0.012
 runway-0.012
ifying-0.011
umes-0.011
Token
Token ID198
Feature activation+2.63e-03

Pos logit contributions
plets+0.000
ramids+0.000
 runway+0.000
ifying+0.000
umes+0.000
Neg logit contributions
P-0.000
 seeker-0.000
joy-0.000
 best-0.000
robat-0.000
TokenTHE
Token ID10970
Feature activation+8.80e-02

Pos logit contributions
plets+0.003
ramids+0.003
 runway+0.003
ifying+0.003
ured+0.003
Neg logit contributions
P-0.005
joy-0.005
 seeker-0.005
 best-0.005
robat-0.004
Token<|endoftext|>
Token ID50256
Feature activation-3.40e-03

Pos logit contributions
plets+0.185
 runway+0.181
ifying+0.180
ramids+0.180
umes+0.178
Neg logit contributions
P-0.092
 best-0.080
joy-0.077
rob-0.077
robat-0.073
TokenOnce
Token ID7454
Feature activation+7.94e-03

Pos logit contributions
Deal+0.005
P+0.005
 moderation+0.005
 seeker+0.005
robat+0.005
Neg logit contributions
plets-0.005
ifying-0.005
ramids-0.005
 runway-0.004
through-0.004
Token upon
Token ID2402
Feature activation+1.98e-02

Pos logit contributions
ramids+0.012
 runway+0.012
ifying+0.012
plets+0.012
lights+0.012
Neg logit contributions
P-0.012
rob-0.012
robat-0.011
Deal-0.011
 moderation-0.010
Token a
Token ID257
Feature activation-1.35e-02

Pos logit contributions
plets+0.030
 runway+0.030
ifying+0.029
ramids+0.029
umes+0.028
Neg logit contributions
P-0.031
rob-0.028
robat-0.028
joy-0.027
 best-0.027
Token time
Token ID640
Feature activation-2.21e-02

Pos logit contributions
rob+0.022
robat+0.021
ests+0.020
 seeker+0.019
P+0.019
Neg logit contributions
ifying-0.017
inated-0.017
 cum-0.016
ln-0.016
mic-0.016
Token a
Token ID257
Feature activation-8.49e-03

Pos logit contributions
plets+0.045
 runway+0.045
ramids+0.045
ifying+0.043
umes+0.042
Neg logit contributions
P-0.038
 best-0.033
rob-0.033
joy-0.033
robat-0.032
Token big
Token ID1263
Feature activation-1.79e-03

Pos logit contributions
rob+0.012
P+0.012
Deal+0.011
 seeker+0.011
robat+0.011
Neg logit contributions
 runway-0.014
plets-0.014
ifying-0.013
umes-0.013
mic-0.013
Token cloth
Token ID16270
Feature activation-1.67e-02

Pos logit contributions
Deal+0.003
rob+0.003
P+0.003
ests+0.003
 best+0.002
Neg logit contributions
 runway-0.003
plets-0.003
 rubble-0.002
mic-0.002
 cum-0.002
Token and
Token ID290
Feature activation+3.73e-03

Pos logit contributions
P+0.023
rob+0.020
joy+0.020
 best+0.019
robat+0.019
Neg logit contributions
plets-0.030
 runway-0.029
ramids-0.029
ifying-0.028
umes-0.028
Token wiped
Token ID21122
Feature activation+1.24e-02

Pos logit contributions
ramids+0.006
 runway+0.006
plets+0.006
ifying+0.006
umes+0.006
Neg logit contributions
P-0.006
 best-0.005
rob-0.005
my-0.005
joy-0.005
Token off
Token ID572
Feature activation+8.57e-02

Pos logit contributions
plets+0.016
 runway+0.016
ramids+0.016
ifying+0.015
umes+0.015
Neg logit contributions
P-0.023
 best-0.020
joy-0.020
rob-0.020
robat-0.020
Token the
Token ID262
Feature activation+2.18e-02

Pos logit contributions
 runway+0.160
plets+0.159
ramids+0.156
keys+0.149
mic+0.147
Neg logit contributions
P-0.111
 best-0.101
my-0.092
joy-0.092
 right-0.091
Token mud
Token ID17492
Feature activation+3.62e-02

Pos logit contributions
plets+0.031
 runway+0.031
ramids+0.030
ifying+0.029
umes+0.029
Neg logit contributions
P-0.037
rob-0.033
robat-0.033
joy-0.033
 best-0.033
Token from
Token ID422
Feature activation+3.72e-02

Pos logit contributions
plets+0.060
 runway+0.059
ramids+0.059
ifying+0.057
umes+0.056
Neg logit contributions
P-0.054
 best-0.047
joy-0.047
rob-0.047
robat-0.046
Token the
Token ID262
Feature activation-5.57e-03

Pos logit contributions
plets+0.056
ramids+0.054
 runway+0.054
ifying+0.052
umes+0.051
Neg logit contributions
P-0.062
 best-0.055
joy-0.055
rob-0.054
robat-0.054
Token child
Token ID1200
Feature activation+1.37e-02

Pos logit contributions
P+0.009
rob+0.008
 best+0.008
robat+0.008
joy+0.008
Neg logit contributions
plets-0.009
 runway-0.009
ramids-0.008
ifying-0.008
umes-0.008
Token it
Token ID340
Feature activation+3.16e-02

Pos logit contributions
plets+0.013
 runway+0.012
ramids+0.012
ifying+0.012
umes+0.011
Neg logit contributions
P-0.020
 best-0.018
joy-0.018
rob-0.018
robat-0.018
Token away
Token ID1497
Feature activation+3.83e-02

Pos logit contributions
plets+0.052
ramids+0.051
 runway+0.051
ifying+0.049
umes+0.048
Neg logit contributions
P-0.048
 best-0.042
joy-0.041
robat-0.041
rob-0.040
Token in
Token ID287
Feature activation-3.70e-03

Pos logit contributions
plets+0.074
ramids+0.072
 runway+0.072
ifying+0.069
umes+0.069
Neg logit contributions
P-0.046
 best-0.042
joy-0.040
 seeker-0.038
robat-0.038
Token a
Token ID257
Feature activation-3.22e-02

Pos logit contributions
P+0.007
rob+0.007
Deal+0.007
robat+0.007
 seeker+0.006
Neg logit contributions
 runway-0.004
ifying-0.004
ramids-0.004
plets-0.004
 sealed-0.004
Token wheel
Token ID7825
Feature activation-3.56e-02

Pos logit contributions
P+0.046
rob+0.041
robat+0.040
 best+0.040
joy+0.039
Neg logit contributions
plets-0.055
 runway-0.054
ramids-0.053
ifying-0.053
umes-0.051
Tokenbar
Token ID5657
Feature activation-1.08e-01

Pos logit contributions
P+0.055
joy+0.047
rob+0.047
 moderation+0.046
 best+0.045
Neg logit contributions
plets-0.059
 runway-0.058
ramids-0.057
ifying-0.056
umes-0.054
Tokenrow
Token ID808
Feature activation-1.34e-02

Pos logit contributions
joy+0.243
P+0.231
 seeker+0.221
rob+0.221
Deal+0.218
Neg logit contributions
plets-0.089
oves-0.087
lights-0.085
ric-0.082
 runway-0.080
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
P+0.021
rob+0.018
robat+0.018
 moderation+0.017
joy+0.017
Neg logit contributions
plets-0.022
 runway-0.021
ramids-0.021
ifying-0.021
ured-0.020
Token
Token ID198
Feature activation-7.29e-04

Pos logit contributions
P+0.022
 seeker+0.019
robat+0.019
rob+0.018
 best+0.018
Neg logit contributions
ramids-0.024
plets-0.023
 runway-0.022
inated-0.022
ifying-0.021
Token
Token ID198
Feature activation+1.65e-03

Pos logit contributions
P+0.001
 seeker+0.001
joy+0.001
 best+0.001
rob+0.001
Neg logit contributions
ramids-0.001
 runway-0.001
plets-0.001
uring-0.001
inated-0.001
TokenOnce
Token ID7454
Feature activation+3.62e-02

Pos logit contributions
plets+0.002
ramids+0.002
 runway+0.002
ifying+0.002
umes+0.002
Neg logit contributions
P-0.003
robat-0.003
 best-0.003
 moderation-0.003
Deal-0.002
Token dolls
Token ID36062
Feature activation+1.66e-02

Pos logit contributions
plets+0.053
ramids+0.052
 runway+0.051
ifying+0.050
umes+0.049
Neg logit contributions
P-0.041
 best-0.038
robat-0.035
 seeker-0.035
joy-0.035
Token around
Token ID1088
Feature activation+9.55e-03

Pos logit contributions
 runway+0.026
plets+0.025
ramids+0.025
uring+0.024
ifying+0.024
Neg logit contributions
P-0.027
rob-0.024
joy-0.024
 moderation-0.023
Deal-0.022
Token in
Token ID287
Feature activation-5.46e-03

Pos logit contributions
 runway+0.013
ramids+0.013
uring+0.012
plets+0.012
ured+0.012
Neg logit contributions
P-0.017
rob-0.015
robat-0.014
Deal-0.014
orn-0.014
Token a
Token ID257
Feature activation-2.07e-02

Pos logit contributions
P+0.011
rob+0.010
Deal+0.010
robat+0.010
orn+0.009
Neg logit contributions
 runway-0.007
ramids-0.006
ifying-0.006
plets-0.006
uring-0.006
Token wheel
Token ID7825
Feature activation-3.66e-02

Pos logit contributions
P+0.027
rob+0.025
joy+0.024
robat+0.024
 best+0.023
Neg logit contributions
 runway-0.037
plets-0.036
ramids-0.035
ifying-0.035
umes-0.034
Tokenbar
Token ID5657
Feature activation-9.96e-02

Pos logit contributions
P+0.059
joy+0.053
 moderation+0.052
rob+0.050
 best+0.049
Neg logit contributions
 runway-0.057
plets-0.055
ramids-0.054
ifying-0.052
ents-0.050
Tokenrow
Token ID808
Feature activation-1.41e-02

Pos logit contributions
joy+0.212
P+0.187
Deal+0.186
 seeker+0.182
 moderation+0.182
Neg logit contributions
ric-0.100
 runway-0.097
lights-0.097
oves-0.096
plets-0.092
Token she
Token ID673
Feature activation-7.32e-03

Pos logit contributions
P+0.023
rob+0.020
robat+0.019
joy+0.019
 moderation+0.019
Neg logit contributions
 runway-0.022
plets-0.022
ramids-0.021
ifying-0.021
uring-0.021
Token had
Token ID550
Feature activation-6.90e-03

Pos logit contributions
P+0.013
joy+0.012
rob+0.012
 moderation+0.012
robat+0.011
Neg logit contributions
 runway-0.010
plets-0.010
ramids-0.009
ifying-0.009
umes-0.009
Token found
Token ID1043
Feature activation-2.17e-02

Pos logit contributions
P+0.010
 best+0.009
my+0.008
joy+0.008
 seeker+0.008
Neg logit contributions
plets-0.012
ramids-0.012
 runway-0.012
inated-0.011
ifying-0.011
Token in
Token ID287
Feature activation+5.73e-03

Pos logit contributions
P+0.030
 best+0.026
joy+0.025
rob+0.025
robat+0.025
Neg logit contributions
plets-0.038
 runway-0.038
ramids-0.038
ifying-0.037
umes-0.036
Token back
Token ID736
Feature activation-4.73e-03

Pos logit contributions
plets+0.021
 runway+0.020
ramids+0.020
ifying+0.020
umes+0.019
Neg logit contributions
P-0.020
 best-0.018
joy-0.018
 seeker-0.017
robat-0.017
Token with
Token ID351
Feature activation-4.82e-04

Pos logit contributions
P+0.006
 best+0.006
joy+0.006
rob+0.005
robat+0.005
Neg logit contributions
plets-0.008
 runway-0.008
ramids-0.008
ifying-0.008
umes-0.008
Token a
Token ID257
Feature activation-2.13e-02

Pos logit contributions
P+0.001
rob+0.001
robat+0.001
Deal+0.001
 seeker+0.001
Neg logit contributions
ifying-0.001
 runway-0.001
ured-0.001
 wil-0.001
 flashing-0.001
Token big
Token ID1263
Feature activation-1.22e-02

Pos logit contributions
P+0.033
rob+0.032
robat+0.029
Deal+0.028
ests+0.027
Neg logit contributions
 runway-0.034
plets-0.034
ifying-0.033
umes-0.032
mic-0.032
Token wheel
Token ID7825
Feature activation-3.68e-02

Pos logit contributions
P+0.022
rob+0.020
Deal+0.018
robat+0.017
ests+0.017
Neg logit contributions
 runway-0.019
plets-0.018
 flashing-0.016
mic-0.016
ifying-0.016
Tokenbar
Token ID5657
Feature activation-9.92e-02

Pos logit contributions
P+0.049
 best+0.042
joy+0.042
rob+0.041
robat+0.041
Neg logit contributions
plets-0.066
ramids-0.065
 runway-0.065
ifying-0.063
umes-0.062
Tokenrow
Token ID808
Feature activation-1.38e-02

Pos logit contributions
P+0.214
joy+0.212
rob+0.200
 moderation+0.198
Deal+0.198
Neg logit contributions
plets-0.092
oves-0.083
ants-0.079
lights-0.079
 runway-0.078
Token.
Token ID13
Feature activation+8.13e-05

Pos logit contributions
P+0.021
rob+0.018
robat+0.017
 moderation+0.017
 best+0.017
Neg logit contributions
plets-0.023
 runway-0.023
ramids-0.023
ifying-0.022
umes-0.022
Token He
Token ID679
Feature activation-6.48e-03

Pos logit contributions
plets+0.000
 runway+0.000
ramids+0.000
ifying+0.000
umes+0.000
Neg logit contributions
P-0.000
joy-0.000
 best-0.000
rob-0.000
robat-0.000
Token asked
Token ID1965
Feature activation-1.96e-02

Pos logit contributions
P+0.010
 best+0.009
joy+0.008
rob+0.008
robat+0.008
Neg logit contributions
plets-0.011
 runway-0.010
ramids-0.010
ifying-0.010
umes-0.010
Token the
Token ID262
Feature activation-3.99e-03

Pos logit contributions
P+0.036
rob+0.033
robat+0.032
 seeker+0.031
joy+0.030
Neg logit contributions
ramids-0.025
ured-0.025
 runway-0.024
uring-0.024
plets-0.023
Token sund
Token ID37437
Feature activation-5.18e-02

Pos logit contributions
P+0.002
rob+0.002
robat+0.002
 moderation+0.002
joy+0.002
Neg logit contributions
plets-0.003
ifying-0.003
 runway-0.003
ramids-0.002
umes-0.002
Tokenae
Token ID3609
Feature activation+8.59e-03

Pos logit contributions
P+0.080
joy+0.079
rob+0.076
 seeker+0.073
robat+0.071
Neg logit contributions
ifying-0.078
plets-0.078
umes-0.074
 runway-0.074
keys-0.073
Token with
Token ID351
Feature activation-4.52e-03

Pos logit contributions
plets+0.016
ramids+0.016
 runway+0.016
ifying+0.015
umes+0.015
Neg logit contributions
P-0.011
 best-0.009
joy-0.009
robat-0.009
rob-0.009
Token lots
Token ID6041
Feature activation+5.26e-03

Pos logit contributions
P+0.006
 best+0.006
joy+0.005
rob+0.005
robat+0.005
Neg logit contributions
plets-0.008
 runway-0.008
ramids-0.008
ifying-0.007
umes-0.007
Token of
Token ID286
Feature activation+4.11e-04

Pos logit contributions
ramids+0.010
 runway+0.010
plets+0.009
ifying+0.009
umes+0.009
Neg logit contributions
P-0.007
 best-0.006
joy-0.006
my-0.006
 moderation-0.006
Token topp
Token ID23126
Feature activation-9.43e-02

Pos logit contributions
ramids+0.001
plets+0.001
 runway+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.001
 seeker-0.001
robat-0.001
joy-0.001
rob-0.001
Tokenings
Token ID654
Feature activation+2.65e-05

Pos logit contributions
P+0.170
joy+0.156
rob+0.156
 seeker+0.155
 moderation+0.153
Neg logit contributions
ramids-0.126
plets-0.124
ifying-0.118
ured-0.115
umes-0.114
Token.
Token ID13
Feature activation-7.33e-03

Pos logit contributions
plets+0.000
 runway+0.000
ramids+0.000
ifying+0.000
umes+0.000
Neg logit contributions
P-0.000
 best-0.000
joy-0.000
robat-0.000
rob-0.000
Token
Token ID198
Feature activation-5.17e-03

Pos logit contributions
P+0.010
joy+0.008
 best+0.008
rob+0.008
 moderation+0.008
Neg logit contributions
plets-0.013
 runway-0.013
ramids-0.013
ifying-0.013
umes-0.013
Token
Token ID198
Feature activation-1.31e-03

Pos logit contributions
P+0.006
 best+0.005
joy+0.005
rob+0.005
robat+0.004
Neg logit contributions
plets-0.011
ramids-0.011
 runway-0.011
ifying-0.010
umes-0.010
TokenThey
Token ID2990
Feature activation+2.32e-02

Pos logit contributions
P+0.002
Ben+0.002
my+0.002
ossible+0.001
Today+0.001
Neg logit contributions
flies-0.002
plets-0.002
lights-0.002
ric-0.002
ramids-0.002
Token.
Token ID13
Feature activation-4.78e-04

Pos logit contributions
plets+0.034
 runway+0.033
ramids+0.033
ifying+0.032
umes+0.031
Neg logit contributions
P-0.022
 best-0.020
rob-0.019
joy-0.019
robat-0.019
Token He
Token ID679
Feature activation-7.71e-03

Pos logit contributions
P+0.000
 best+0.000
joy+0.000
rob+0.000
 seeker+0.000
Neg logit contributions
plets-0.001
 runway-0.001
ramids-0.001
ifying-0.001
umes-0.001
Token found
Token ID1043
Feature activation-1.21e-02

Pos logit contributions
P+0.010
 best+0.009
joy+0.009
rob+0.009
robat+0.008
Neg logit contributions
plets-0.014
 runway-0.014
ramids-0.014
ifying-0.014
umes-0.013
Token a
Token ID257
Feature activation-7.59e-03

Pos logit contributions
P+0.019
robat+0.016
rob+0.016
joy+0.016
 seeker+0.016
Neg logit contributions
plets-0.019
ramids-0.019
 runway-0.019
ifying-0.018
umes-0.018
Token wheel
Token ID7825
Feature activation-2.20e-02

Pos logit contributions
P+0.010
rob+0.009
joy+0.009
robat+0.009
 best+0.008
Neg logit contributions
plets-0.014
 runway-0.013
ramids-0.013
ifying-0.013
umes-0.013
Tokenbar
Token ID5657
Feature activation-9.43e-02

Pos logit contributions
P+0.031
 best+0.027
rob+0.026
joy+0.026
robat+0.026
Neg logit contributions
plets-0.038
 runway-0.037
ramids-0.037
ifying-0.036
umes-0.036
Tokenrow
Token ID808
Feature activation-1.37e-03

Pos logit contributions
joy+0.189
P+0.185
 moderation+0.173
Deal+0.167
rob+0.162
Neg logit contributions
plets-0.107
lights-0.100
ric-0.095
ramids-0.094
 runway-0.091
Token,
Token ID11
Feature activation+3.00e-03

Pos logit contributions
P+0.002
rob+0.002
 moderation+0.002
robat+0.002
joy+0.002
Neg logit contributions
plets-0.002
ramids-0.002
 runway-0.002
ifying-0.002
umes-0.002
Token a
Token ID257
Feature activation-1.01e-02

Pos logit contributions
plets+0.006
ramids+0.005
 runway+0.005
ifying+0.005
umes+0.005
Neg logit contributions
P-0.004
 best-0.003
joy-0.003
rob-0.003
robat-0.003
Token tr
Token ID491
Feature activation-1.65e-02

Pos logit contributions
P+0.013
rob+0.011
joy+0.011
 best+0.011
robat+0.011
Neg logit contributions
plets-0.019
 runway-0.019
ramids-0.018
ifying-0.018
umes-0.018
Tokenamp
Token ID696
Feature activation+6.16e-03

Pos logit contributions
P+0.023
 best+0.021
joy+0.020
rob+0.019
 moderation+0.019
Neg logit contributions
plets-0.029
ramids-0.028
 runway-0.028
ifying-0.028
umes-0.027
Token to
Token ID284
Feature activation+3.25e-03

Pos logit contributions
plets+0.056
 runway+0.053
mic+0.051
ller+0.050
ramids+0.049
Neg logit contributions
P-0.026
 best-0.025
my-0.023
 right-0.021
ossible-0.021
Token Mom
Token ID11254
Feature activation-2.05e-02

Pos logit contributions
plets+0.006
 runway+0.006
ramids+0.006
ifying+0.005
keys+0.005
Neg logit contributions
P-0.004
 best-0.004
joy-0.004
 moderation-0.004
 seeker-0.004
Tokenmy
Token ID1820
Feature activation-1.05e-02

Pos logit contributions
P+0.011
rob+0.007
robat+0.006
joy+0.006
 seeker+0.006
Neg logit contributions
ramids-0.054
plets-0.053
 runway-0.053
umes-0.053
ifying-0.052
Token one
Token ID530
Feature activation-7.12e-02

Pos logit contributions
P+0.011
 best+0.010
my+0.010
joy+0.009
 moderation+0.009
Neg logit contributions
plets-0.022
 runway-0.021
ramids-0.021
ifying-0.020
mic-0.020
Token by
Token ID416
Feature activation-1.06e-02

Pos logit contributions
P+0.094
rob+0.079
 best+0.079
joy+0.079
robat+0.078
Neg logit contributions
plets-0.131
 runway-0.129
ramids-0.128
ifying-0.125
umes-0.123
Token one
Token ID530
Feature activation-9.37e-02

Pos logit contributions
P+0.011
 best+0.009
joy+0.009
rob+0.008
robat+0.008
Neg logit contributions
plets-0.023
 runway-0.023
ramids-0.023
ifying-0.022
umes-0.022
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
P+0.140
rob+0.127
robat+0.120
 seeker+0.119
joy+0.117
Neg logit contributions
plets-0.156
 runway-0.154
ramids-0.153
ifying-0.153
umes-0.149
Token
Token ID198
Feature activation-4.06e-03

Pos logit contributions
P+0.010
joy+0.009
 best+0.008
ossible+0.007
 seeker+0.007
Neg logit contributions
 runway-0.024
plets-0.024
keys-0.023
ifying-0.022
mic-0.022
Token
Token ID198
Feature activation-2.62e-03

Pos logit contributions
P+0.003
 best+0.002
joy+0.002
rob+0.002
ossible+0.002
Neg logit contributions
plets-0.010
 runway-0.010
ifying-0.010
ramids-0.009
umes-0.009
TokenOnce
Token ID7454
Feature activation+3.43e-02

Pos logit contributions
P+0.004
 best+0.002
ossible+0.002
m+0.002
Ben+0.002
Neg logit contributions
plets-0.005
 runway-0.005
flies-0.005
 rubble-0.005
lights-0.005
Token they
Token ID484
Feature activation-1.55e-02

Pos logit contributions
plets+0.057
 runway+0.055
ramids+0.054
mic+0.053
ifying+0.052
Neg logit contributions
P-0.052
 best-0.051
joy-0.047
 seeker-0.046
m-0.045
Tokenâ
Token ID22940
Feature activation-2.82e-03

Pos logit contributions
plets+0.009
 runway+0.009
ramids+0.008
ifying+0.008
umes+0.008
Neg logit contributions
P-0.007
 best-0.006
joy-0.006
rob-0.006
robat-0.006
Token
Token ID26391
Feature activation+1.83e-02

Pos logit contributions
P+0.004
joy+0.004
 best+0.004
 moderation+0.004
 seeker+0.004
Neg logit contributions
plets-0.005
ramids-0.004
ured-0.004
 runway-0.004
uring-0.004
Token
Token ID129
Feature activation+6.04e-03

Pos logit contributions
plets+0.029
ramids+0.029
 runway+0.029
ifying+0.027
umes+0.027
Neg logit contributions
P-0.029
 best-0.025
rob-0.024
robat-0.024
 seeker-0.024
Token
Token ID241
Feature activation+2.13e-03

Pos logit contributions
plets+0.009
ifying+0.008
lights+0.008
 runway+0.008
umes+0.007
Neg logit contributions
P-0.011
 best-0.010
Deal-0.010
robat-0.009
rob-0.009
TokenThat
Token ID2504
Feature activation-1.41e-02

Pos logit contributions
plets+0.004
ifying+0.004
ramids+0.004
 runway+0.003
umes+0.003
Neg logit contributions
P-0.003
 best-0.003
rob-0.003
robat-0.003
joy-0.003
Token one
Token ID530
Feature activation-9.21e-02

Pos logit contributions
P+0.020
joy+0.017
rob+0.017
 best+0.017
robat+0.017
Neg logit contributions
plets-0.025
 runway-0.024
ramids-0.024
ifying-0.024
umes-0.023
Token costs
Token ID3484
Feature activation-4.25e-02

Pos logit contributions
P+0.132
rob+0.116
joy+0.116
robat+0.113
 seeker+0.112
Neg logit contributions
plets-0.154
 runway-0.150
ramids-0.149
umes-0.147
ifying-0.147
Token more
Token ID517
Feature activation-4.00e-02

Pos logit contributions
P+0.062
rob+0.055
robat+0.054
joy+0.053
 seeker+0.052
Neg logit contributions
plets-0.070
ramids-0.069
 runway-0.069
ifying-0.068
umes-0.067
Token,
Token ID11
Feature activation-8.37e-03

Pos logit contributions
P+0.054
 best+0.048
joy+0.045
robat+0.044
 seeker+0.044
Neg logit contributions
plets-0.073
ramids-0.072
 runway-0.071
ifying-0.070
umes-0.067
Tokenâ
Token ID22940
Feature activation-5.09e-03

Pos logit contributions
P+0.013
 best+0.012
joy+0.012
rob+0.011
 seeker+0.011
Neg logit contributions
plets-0.013
 runway-0.013
ramids-0.013
ifying-0.012
umes-0.012
Token
Token ID26391
Feature activation+2.42e-02

Pos logit contributions
joy+0.007
P+0.007
 best+0.007
 seeker+0.007
 moderation+0.007
Neg logit contributions
plets-0.008
ured-0.008
uring-0.008
 runway-0.007
inated-0.007
Token the
Token ID262
Feature activation-1.32e-02

Pos logit contributions
plets+0.007
 runway+0.007
ramids+0.007
ifying+0.007
umes+0.007
Neg logit contributions
P-0.009
 best-0.008
rob-0.008
joy-0.008
robat-0.008
Token cand
Token ID2658
Feature activation-1.09e-02

Pos logit contributions
P+0.022
joy+0.020
 seeker+0.020
rob+0.019
robat+0.019
Neg logit contributions
plets-0.019
ramids-0.019
 runway-0.018
ifying-0.018
umes-0.018
Tokenies
Token ID444
Feature activation+3.43e-02

Pos logit contributions
P+0.020
 best+0.018
joy+0.017
robat+0.017
rob+0.017
Neg logit contributions
plets-0.015
 runway-0.014
ramids-0.014
ifying-0.014
umes-0.013
Token one
Token ID530
Feature activation-7.56e-02

Pos logit contributions
plets+0.063
 runway+0.062
ramids+0.062
ifying+0.059
umes+0.058
Neg logit contributions
P-0.045
 best-0.040
joy-0.038
robat-0.037
 moderation-0.037
Token by
Token ID416
Feature activation-1.91e-02

Pos logit contributions
P+0.128
rob+0.123
 seeker+0.117
joy+0.116
robat+0.112
Neg logit contributions
plets-0.104
ifying-0.103
umes-0.100
 runway-0.099
ender-0.098
Token one
Token ID530
Feature activation-9.20e-02

Pos logit contributions
P+0.027
rob+0.023
robat+0.023
joy+0.022
 best+0.022
Neg logit contributions
ramids-0.033
 runway-0.033
plets-0.033
ured-0.033
inated-0.032
Token and
Token ID290
Feature activation+5.67e-03

Pos logit contributions
P+0.145
rob+0.135
joy+0.123
 seeker+0.121
robat+0.120
Neg logit contributions
 runway-0.146
ifying-0.146
plets-0.145
ramids-0.145
umes-0.141
Token enjoyed
Token ID8359
Feature activation+8.76e-03

Pos logit contributions
plets+0.008
 runway+0.008
ramids+0.008
ifying+0.007
umes+0.007
Neg logit contributions
P-0.010
 best-0.009
rob-0.009
joy-0.009
robat-0.009
Token them
Token ID606
Feature activation-4.06e-03

Pos logit contributions
plets+0.013
 runway+0.013
ramids+0.012
ifying+0.012
mic+0.012
Neg logit contributions
P-0.015
 best-0.014
joy-0.014
 moderation-0.013
rob-0.013
Token all
Token ID477
Feature activation-1.78e-03

Pos logit contributions
P+0.006
rob+0.006
robat+0.006
joy+0.006
 seeker+0.005
Neg logit contributions
 runway-0.006
ramids-0.006
plets-0.006
umes-0.006
ifying-0.006
Token.
Token ID13
Feature activation-1.35e-02

Pos logit contributions
P+0.003
rob+0.002
 seeker+0.002
robat+0.002
joy+0.002
Neg logit contributions
ramids-0.003
plets-0.003
 runway-0.003
ifying-0.003
umes-0.003
Token,
Token ID11
Feature activation-4.69e-03

Pos logit contributions
P+0.021
rob+0.018
 best+0.018
joy+0.018
robat+0.018
Neg logit contributions
plets-0.028
 runway-0.027
ramids-0.027
ifying-0.026
umes-0.026
Token this
Token ID428
Feature activation-1.17e-02

Pos logit contributions
P+0.006
joy+0.006
 best+0.006
my+0.006
 moderation+0.005
Neg logit contributions
plets-0.008
 runway-0.008
ramids-0.008
ifying-0.008
umes-0.007
Token time
Token ID640
Feature activation+6.93e-03

Pos logit contributions
P+0.014
 best+0.012
joy+0.012
robat+0.012
rob+0.011
Neg logit contributions
ramids-0.023
plets-0.023
 runway-0.023
ifying-0.022
umes-0.022
Token adding
Token ID4375
Feature activation-3.34e-02

Pos logit contributions
plets+0.013
 runway+0.013
ramids+0.013
ifying+0.012
umes+0.012
Neg logit contributions
P-0.009
 best-0.008
joy-0.008
 seeker-0.007
robat-0.007
Token an
Token ID281
Feature activation-3.69e-03

Pos logit contributions
P+0.054
rob+0.048
robat+0.047
 seeker+0.047
joy+0.046
Neg logit contributions
plets-0.050
 runway-0.050
ramids-0.049
ifying-0.048
umes-0.047
Token ult
Token ID3789
Feature activation-9.10e-02

Pos logit contributions
P+0.005
 best+0.005
joy+0.005
rob+0.005
robat+0.005
Neg logit contributions
plets-0.006
 runway-0.006
ramids-0.006
ifying-0.006
umes-0.006
Tokenim
Token ID320
Feature activation-8.60e-03

Pos logit contributions
P+0.126
 best+0.120
rob+0.117
joy+0.117
robat+0.111
Neg logit contributions
ramids-0.155
inated-0.143
ured-0.141
ric-0.141
uring-0.139
Tokenatum
Token ID21307
Feature activation-1.92e-02

Pos logit contributions
P+0.013
 best+0.012
robat+0.011
rob+0.011
joy+0.011
Neg logit contributions
 runway-0.014
plets-0.014
ramids-0.014
ifying-0.013
umes-0.013
Token.
Token ID13
Feature activation-6.62e-03

Pos logit contributions
P+0.030
rob+0.026
 moderation+0.025
joy+0.025
robat+0.025
Neg logit contributions
plets-0.030
 runway-0.030
ramids-0.029
ifying-0.029
ured-0.029
Token She
Token ID1375
Feature activation+1.65e-02

Pos logit contributions
P+0.009
rob+0.008
robat+0.008
 best+0.008
 seeker+0.008
Neg logit contributions
plets-0.012
ramids-0.011
ifying-0.011
 runway-0.011
umes-0.011
Token said
Token ID531
Feature activation+3.11e-03

Pos logit contributions
plets+0.030
 runway+0.030
ramids+0.030
ifying+0.029
umes+0.028
Neg logit contributions
P-0.022
 best-0.019
rob-0.018
joy-0.018
robat-0.018
Token rag
Token ID34232
Feature activation+1.65e-03

Pos logit contributions
P+0.001
rob+0.001
robat+0.001
joy+0.001
Deal+0.001
Neg logit contributions
 runway-0.001
plets-0.001
ramids-0.001
umes-0.001
ured-0.001
Token for
Token ID329
Feature activation-2.36e-02

Pos logit contributions
plets+0.003
ramids+0.003
 runway+0.003
ifying+0.003
umes+0.003
Neg logit contributions
P-0.002
 best-0.002
joy-0.002
robat-0.002
rob-0.002
Token a
Token ID257
Feature activation-3.40e-02

Pos logit contributions
P+0.032
 best+0.030
 moderation+0.029
joy+0.029
 seeker+0.027
Neg logit contributions
plets-0.044
ramids-0.043
ifying-0.041
 runway-0.041
umes-0.040
Token shiny
Token ID22441
Feature activation-3.74e-02

Pos logit contributions
P+0.044
 best+0.040
joy+0.039
 seeker+0.036
robat+0.036
Neg logit contributions
plets-0.063
ramids-0.063
 runway-0.061
umes-0.059
ifying-0.059
Token new
Token ID649
Feature activation-3.45e-02

Pos logit contributions
P+0.054
rob+0.047
robat+0.045
joy+0.043
 best+0.042
Neg logit contributions
 runway-0.064
plets-0.063
ifying-0.062
ramids-0.062
ured-0.060
Token one
Token ID530
Feature activation-9.08e-02

Pos logit contributions
P+0.049
rob+0.046
robat+0.041
Deal+0.039
 moderation+0.039
Neg logit contributions
 runway-0.060
inated-0.055
ured-0.054
plets-0.054
ramids-0.054
Token,
Token ID11
Feature activation-1.06e-02

Pos logit contributions
P+0.126
rob+0.111
joy+0.106
robat+0.105
 seeker+0.104
Neg logit contributions
plets-0.160
 runway-0.157
ifying-0.154
ramids-0.153
umes-0.150
Token she
Token ID673
Feature activation-1.80e-03

Pos logit contributions
P+0.018
 best+0.016
joy+0.016
rob+0.016
robat+0.015
Neg logit contributions
plets-0.015
ramids-0.015
 runway-0.015
ifying-0.014
umes-0.014
Token had
Token ID550
Feature activation-2.02e-03

Pos logit contributions
P+0.003
 best+0.002
my+0.002
joy+0.002
robat+0.002
Neg logit contributions
plets-0.003
ramids-0.003
 runway-0.003
ifying-0.003
umes-0.003
Token made
Token ID925
Feature activation-4.48e-03

Pos logit contributions
P+0.003
 best+0.002
joy+0.002
 moderation+0.002
 seeker+0.002
Neg logit contributions
plets-0.004
ramids-0.004
 runway-0.004
ifying-0.004
keys-0.004
Token her
Token ID607
Feature activation+1.57e-02

Pos logit contributions
P+0.007
 best+0.006
joy+0.006
 moderation+0.006
rob+0.006
Neg logit contributions
plets-0.007
ramids-0.007
 runway-0.007
ifying-0.007
umes-0.007
Token shining
Token ID22751
Feature activation-8.92e-03

Pos logit contributions
P+0.012
robat+0.011
rob+0.011
joy+0.011
 seeker+0.011
Neg logit contributions
plets-0.012
ramids-0.012
 runway-0.012
ifying-0.012
umes-0.011
Token brightly
Token ID35254
Feature activation-1.50e-02

Pos logit contributions
P+0.012
 best+0.010
joy+0.010
rob+0.009
robat+0.009
Neg logit contributions
plets-0.016
 runway-0.016
ramids-0.016
umes-0.016
ifying-0.015
Token in
Token ID287
Feature activation-2.05e-02

Pos logit contributions
P+0.019
 best+0.017
joy+0.016
rob+0.016
robat+0.016
Neg logit contributions
plets-0.028
 runway-0.028
ramids-0.027
umes-0.027
ifying-0.026
Token the
Token ID262
Feature activation-2.04e-02

Pos logit contributions
P+0.037
rob+0.033
robat+0.033
 best+0.033
joy+0.032
Neg logit contributions
plets-0.027
 runway-0.027
ramids-0.027
ifying-0.026
umes-0.025
Token sky
Token ID6766
Feature activation-4.17e-02

Pos logit contributions
P+0.030
 best+0.026
joy+0.025
 seeker+0.024
my+0.024
Neg logit contributions
plets-0.035
ramids-0.035
 runway-0.034
umes-0.034
ured-0.033
Token one
Token ID530
Feature activation-9.07e-02

Pos logit contributions
P+0.050
 best+0.043
joy+0.041
robat+0.040
rob+0.040
Neg logit contributions
plets-0.081
 runway-0.080
ramids-0.080
ifying-0.077
umes-0.077
Token day
Token ID1110
Feature activation-1.87e-02

Pos logit contributions
P+0.106
 best+0.087
rob+0.087
joy+0.087
robat+0.086
Neg logit contributions
plets-0.180
 runway-0.178
ramids-0.177
ifying-0.173
umes-0.170
Token.
Token ID13
Feature activation+2.47e-03

Pos logit contributions
P+0.020
 best+0.017
joy+0.016
 seeker+0.015
my+0.014
Neg logit contributions
ramids-0.039
 runway-0.039
plets-0.038
umes-0.037
ifying-0.037
Token But
Token ID887
Feature activation+3.46e-03

Pos logit contributions
plets+0.004
 runway+0.004
ramids+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.003
joy-0.003
 best-0.003
rob-0.003
 seeker-0.003
Token then
Token ID788
Feature activation-2.42e-02

Pos logit contributions
plets+0.005
 runway+0.005
ramids+0.005
ifying+0.005
umes+0.005
Neg logit contributions
P-0.006
 best-0.005
joy-0.005
 seeker-0.005
 moderation-0.005
Token,
Token ID11
Feature activation-1.80e-02

Pos logit contributions
P+0.034
 best+0.029
rob+0.029
joy+0.029
robat+0.029
Neg logit contributions
plets-0.042
 runway-0.041
ramids-0.041
ifying-0.040
umes-0.039
Token him
Token ID683
Feature activation+4.99e-03

Pos logit contributions
P+0.011
rob+0.010
 seeker+0.010
robat+0.010
 moderation+0.010
Neg logit contributions
ramids-0.008
ifying-0.008
plets-0.008
 runway-0.008
umes-0.008
Token a
Token ID257
Feature activation-5.68e-03

Pos logit contributions
plets+0.009
 runway+0.009
ramids+0.009
ifying+0.009
umes+0.008
Neg logit contributions
P-0.007
 best-0.006
joy-0.006
rob-0.006
robat-0.006
Token big
Token ID1263
Feature activation-1.98e-03

Pos logit contributions
P+0.008
rob+0.007
robat+0.007
 moderation+0.007
joy+0.007
Neg logit contributions
 runway-0.010
ramids-0.009
plets-0.009
ifying-0.009
umes-0.009
Token red
Token ID2266
Feature activation-2.55e-02

Pos logit contributions
P+0.003
rob+0.003
 moderation+0.002
Deal+0.002
robat+0.002
Neg logit contributions
 runway-0.004
plets-0.003
ifying-0.003
ramids-0.003
mic-0.003
Token wheel
Token ID7825
Feature activation-2.38e-02

Pos logit contributions
P+0.034
rob+0.029
joy+0.029
 moderation+0.029
 best+0.029
Neg logit contributions
 runway-0.046
ramids-0.046
plets-0.046
ifying-0.045
umes-0.043
Tokenbar
Token ID5657
Feature activation-9.06e-02

Pos logit contributions
P+0.034
joy+0.029
rob+0.029
 moderation+0.028
 best+0.028
Neg logit contributions
plets-0.041
 runway-0.041
ramids-0.041
ifying-0.039
umes-0.039
Tokenrow
Token ID808
Feature activation+3.72e-03

Pos logit contributions
joy+0.170
P+0.164
 moderation+0.157
 seeker+0.149
rob+0.147
Neg logit contributions
plets-0.115
lights-0.111
 runway-0.110
ramids-0.106
drops-0.102
Token and
Token ID290
Feature activation+1.10e-02

Pos logit contributions
plets+0.006
 runway+0.006
ramids+0.006
ifying+0.006
umes+0.006
Neg logit contributions
P-0.006
rob-0.005
joy-0.005
robat-0.005
 best-0.005
Token filled
Token ID5901
Feature activation+4.10e-02

Pos logit contributions
plets+0.019
ramids+0.019
 runway+0.019
ifying+0.018
umes+0.018
Neg logit contributions
P-0.016
 best-0.014
rob-0.013
joy-0.013
 seeker-0.013
Token it
Token ID340
Feature activation+1.94e-02

Pos logit contributions
plets+0.044
ramids+0.044
 runway+0.043
ifying+0.041
umes+0.040
Neg logit contributions
P-0.084
 best-0.076
joy-0.076
rob-0.076
robat-0.075
Token with
Token ID351
Feature activation-8.54e-03

Pos logit contributions
plets+0.035
 runway+0.035
ramids+0.035
ifying+0.034
umes+0.033
Neg logit contributions
P-0.026
 best-0.022
joy-0.021
rob-0.021
robat-0.021
Token.
Token ID13
Feature activation-7.31e-03

Pos logit contributions
P+0.003
 seeker+0.002
rob+0.002
robat+0.002
joy+0.002
Neg logit contributions
 runway-0.002
ramids-0.002
ifying-0.002
plets-0.002
uring-0.002
Token She
Token ID1375
Feature activation+1.59e-02

Pos logit contributions
P+0.009
rob+0.008
robat+0.008
 best+0.008
 seeker+0.008
Neg logit contributions
plets-0.014
ramids-0.014
 runway-0.014
ifying-0.013
ured-0.013
Token saw
Token ID2497
Feature activation-1.13e-02

Pos logit contributions
plets+0.028
ramids+0.027
 runway+0.027
ifying+0.026
umes+0.026
Neg logit contributions
P-0.023
 best-0.020
joy-0.020
rob-0.019
robat-0.019
Token a
Token ID257
Feature activation-3.38e-03

Pos logit contributions
P+0.017
 best+0.015
joy+0.015
rob+0.015
robat+0.015
Neg logit contributions
plets-0.018
 runway-0.018
ramids-0.018
ifying-0.017
umes-0.017
Token wheel
Token ID7825
Feature activation-1.86e-02

Pos logit contributions
P+0.005
rob+0.004
robat+0.004
joy+0.004
 best+0.004
Neg logit contributions
 runway-0.006
plets-0.006
ramids-0.006
ifying-0.005
umes-0.005
Tokenbar
Token ID5657
Feature activation-9.04e-02

Pos logit contributions
P+0.027
 best+0.025
rob+0.024
robat+0.024
joy+0.024
Neg logit contributions
plets-0.030
ramids-0.030
 runway-0.030
ifying-0.029
umes-0.028
Tokenrow
Token ID808
Feature activation+9.42e-06

Pos logit contributions
P+0.180
joy+0.178
 moderation+0.163
 seeker+0.162
rob+0.160
Neg logit contributions
plets-0.101
lights-0.093
ric-0.091
 runway-0.090
oves-0.089
Token,
Token ID11
Feature activation+5.35e-03

Feature not active on prev token;
no predictions were affected.
Token a
Token ID257
Feature activation-1.07e-02

Pos logit contributions
plets+0.010
ramids+0.009
 runway+0.009
ifying+0.009
umes+0.009
Neg logit contributions
P-0.007
 best-0.007
joy-0.007
my-0.006
 moderation-0.006
Token large
Token ID1588
Feature activation-1.26e-04

Pos logit contributions
P+0.015
rob+0.012
 best+0.012
joy+0.012
robat+0.012
Neg logit contributions
plets-0.019
 runway-0.019
ramids-0.019
ifying-0.018
umes-0.018
Token sp
Token ID599
Feature activation-1.38e-02

Pos logit contributions
P+0.000
rob+0.000
robat+0.000
Deal+0.000
 moderation+0.000
Neg logit contributions
 runway-0.000
plets-0.000
ramids-0.000
ifying-0.000
umes-0.000
Tokenâ
Token ID22940
Feature activation-5.84e-03

Pos logit contributions
P+0.001
joy+0.001
 best+0.001
 moderation+0.001
my+0.001
Neg logit contributions
plets-0.001
 runway-0.001
ramids-0.001
ifying-0.001
flies-0.001
Token
Token ID26391
Feature activation+1.96e-02

Pos logit contributions
P+0.008
 best+0.007
joy+0.007
 seeker+0.007
rob+0.007
Neg logit contributions
plets-0.010
ramids-0.010
 runway-0.010
ifying-0.009
ured-0.009
Token
Token ID129
Feature activation+3.68e-03

Pos logit contributions
 runway+0.033
ifying+0.033
ured+0.032
plets+0.032
ramids+0.032
Neg logit contributions
P-0.027
joy-0.026
my-0.024
rob-0.023
 best-0.023
Token
Token ID241
Feature activation-2.11e-03

Pos logit contributions
ifying+0.006
plets+0.006
lights+0.006
 runway+0.005
umes+0.005
Neg logit contributions
P-0.006
 right-0.005
Deal-0.005
robat-0.005
 best-0.005
TokenThis
Token ID1212
Feature activation-2.44e-02

Pos logit contributions
P+0.003
 best+0.003
rob+0.003
joy+0.003
robat+0.003
Neg logit contributions
plets-0.004
ramids-0.004
 runway-0.004
ifying-0.003
umes-0.003
Token one
Token ID530
Feature activation-9.02e-02

Pos logit contributions
P+0.036
joy+0.033
Deal+0.032
 moderation+0.032
 seeker+0.030
Neg logit contributions
 runway-0.039
plets-0.036
ramids-0.036
ifying-0.035
umes-0.035
Token please
Token ID3387
Feature activation-2.15e-02

Pos logit contributions
P+0.126
joy+0.107
rob+0.107
robat+0.105
 best+0.105
Neg logit contributions
plets-0.157
 runway-0.155
ramids-0.154
ifying-0.150
umes-0.148
Token,
Token ID11
Feature activation-6.92e-03

Pos logit contributions
P+0.030
 best+0.026
rob+0.025
joy+0.025
robat+0.025
Neg logit contributions
plets-0.037
 runway-0.037
ramids-0.037
ifying-0.036
umes-0.035
Tokenâ
Token ID22940
Feature activation-7.00e-03

Pos logit contributions
P+0.011
 best+0.010
my+0.009
joy+0.009
 seeker+0.009
Neg logit contributions
plets-0.011
 runway-0.011
ramids-0.011
ifying-0.010
umes-0.010
Token
Token ID26391
Feature activation+2.16e-02

Pos logit contributions
P+0.010
joy+0.009
 best+0.009
 seeker+0.009
rob+0.009
Neg logit contributions
plets-0.012
 runway-0.011
ramids-0.011
ured-0.011
ifying-0.011
Token said
Token ID531
Feature activation-1.21e-02

Pos logit contributions
 runway+0.034
plets+0.033
ramids+0.033
ifying+0.032
ured+0.032
Neg logit contributions
P-0.034
joy-0.031
 seeker-0.029
 best-0.029
rob-0.029
Token
Token ID220
Feature activation-3.79e-03

Pos logit contributions
P+0.012
 best+0.010
rob+0.010
robat+0.010
joy+0.010
Neg logit contributions
plets-0.019
ramids-0.018
 runway-0.018
ifying-0.018
umes-0.018
Token
Token ID198
Feature activation-1.20e-03

Pos logit contributions
P+0.004
 best+0.003
rob+0.003
joy+0.003
robat+0.003
Neg logit contributions
plets-0.008
ramids-0.008
 runway-0.008
ifying-0.008
umes-0.007
Token
Token ID198
Feature activation+1.54e-03

Pos logit contributions
P+0.002
 seeker+0.001
 best+0.001
joy+0.001
rob+0.001
Neg logit contributions
plets-0.002
ramids-0.002
 runway-0.002
uring-0.002
umes-0.002
TokenThe
Token ID464
Feature activation-1.25e-02

Pos logit contributions
 runway+0.002
ramids+0.002
plets+0.002
ifying+0.002
umes+0.002
Neg logit contributions
P-0.003
robat-0.002
 best-0.002
rob-0.002
 moderation-0.002
Token wheel
Token ID7825
Feature activation-2.54e-02

Pos logit contributions
P+0.019
rob+0.016
robat+0.016
joy+0.016
 best+0.016
Neg logit contributions
plets-0.021
 runway-0.021
ramids-0.020
ifying-0.020
umes-0.020
Tokenbar
Token ID5657
Feature activation-9.00e-02

Pos logit contributions
P+0.040
 best+0.035
joy+0.034
robat+0.034
rob+0.034
Neg logit contributions
plets-0.040
ramids-0.039
 runway-0.039
ifying-0.038
umes-0.038
Tokenrow
Token ID808
Feature activation-2.31e-03

Pos logit contributions
P+0.171
joy+0.164
 seeker+0.156
 moderation+0.154
rob+0.151
Neg logit contributions
plets-0.109
ramids-0.099
 runway-0.098
lights-0.098
ric-0.094
Token wheel
Token ID7825
Feature activation-2.27e-02

Pos logit contributions
P+0.003
 best+0.003
joy+0.003
my+0.003
robat+0.003
Neg logit contributions
 runway-0.004
ramids-0.004
plets-0.004
ifying-0.004
umes-0.004
Tokened
Token ID276
Feature activation+3.53e-04

Pos logit contributions
P+0.035
 best+0.032
robat+0.031
joy+0.030
my+0.030
Neg logit contributions
plets-0.035
 runway-0.035
ramids-0.035
ifying-0.034
umes-0.033
Token the
Token ID262
Feature activation-5.36e-03

Pos logit contributions
plets+0.001
 runway+0.001
ramids+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.001
 best-0.000
joy-0.000
rob-0.000
robat-0.000
Token cup
Token ID6508
Feature activation+2.72e-02

Pos logit contributions
P+0.008
rob+0.006
 best+0.006
joy+0.006
robat+0.006
Neg logit contributions
plets-0.009
 runway-0.009
ramids-0.009
ifying-0.009
umes-0.009
Token Sam
Token ID3409
Feature activation+2.33e-04

Pos logit contributions
P+0.036
Deal+0.032
rob+0.032
robat+0.032
 seeker+0.031
Neg logit contributions
ramids-0.028
 runway-0.026
plets-0.026
ifying-0.026
ured-0.025
Token's
Token ID338
Feature activation+3.22e-03

Pos logit contributions
plets+0.000
ramids+0.000
 runway+0.000
ifying+0.000
umes+0.000
Neg logit contributions
P-0.000
 best-0.000
my-0.000
robat-0.000
joy-0.000
Token friends
Token ID2460
Feature activation-1.28e-02

Pos logit contributions
 runway+0.005
ramids+0.005
plets+0.005
ifying+0.005
umes+0.005
Neg logit contributions
P-0.005
rob-0.005
robat-0.004
joy-0.004
 moderation-0.004
Token one
Token ID530
Feature activation-6.86e-02

Pos logit contributions
P+0.014
 best+0.012
joy+0.012
robat+0.012
 seeker+0.011
Neg logit contributions
plets-0.026
ramids-0.025
 runway-0.025
ifying-0.025
umes-0.024
Token by
Token ID416
Feature activation-1.48e-02

Pos logit contributions
P+0.108
rob+0.094
joy+0.092
robat+0.091
 seeker+0.091
Neg logit contributions
plets-0.110
 runway-0.108
ramids-0.106
ifying-0.105
umes-0.101
Token one
Token ID530
Feature activation-8.98e-02

Pos logit contributions
P+0.021
rob+0.018
robat+0.017
 best+0.017
joy+0.017
Neg logit contributions
 runway-0.026
plets-0.026
ramids-0.026
ifying-0.025
ured-0.025
Token and
Token ID290
Feature activation+7.62e-03

Pos logit contributions
P+0.135
rob+0.118
joy+0.110
 seeker+0.110
robat+0.109
Neg logit contributions
 runway-0.153
plets-0.152
ifying-0.149
ramids-0.149
ured-0.142
Token made
Token ID925
Feature activation+8.13e-03

Pos logit contributions
plets+0.012
 runway+0.011
ramids+0.011
ifying+0.011
umes+0.011
Neg logit contributions
P-0.012
 best-0.011
rob-0.011
joy-0.011
robat-0.011
Token them
Token ID606
Feature activation+2.15e-02

Pos logit contributions
plets+0.014
 runway+0.013
ramids+0.013
ifying+0.013
umes+0.013
Neg logit contributions
P-0.012
 best-0.011
joy-0.010
rob-0.010
robat-0.010
Token surrender
Token ID16908
Feature activation-1.94e-02

Pos logit contributions
plets+0.041
ramids+0.039
umes+0.037
 runway+0.037
ifying+0.037
Neg logit contributions
 best-0.027
P-0.026
joy-0.024
 seeker-0.024
 idea-0.024
Token.
Token ID13
Feature activation-8.35e-03

Pos logit contributions
P+0.027
 best+0.023
joy+0.023
rob+0.022
robat+0.022
Neg logit contributions
plets-0.034
 runway-0.034
ramids-0.034
ifying-0.033
umes-0.032
Token
Token ID26391
Feature activation+2.97e-02

Pos logit contributions
joy+0.010
P+0.010
 best+0.009
 seeker+0.009
rob+0.009
Neg logit contributions
plets-0.010
uring-0.010
ured-0.010
 runway-0.010
ifying-0.009
Token
Token ID8151
Feature activation-1.34e-02

Pos logit contributions
plets+0.038
 runway+0.038
ramids+0.037
ifying+0.036
umes+0.035
Neg logit contributions
P-0.055
joy-0.050
 best-0.050
 seeker-0.049
robat-0.048
Tokent
Token ID83
Feature activation-9.36e-03

Pos logit contributions
P+0.023
 best+0.020
joy+0.020
rob+0.020
robat+0.020
Neg logit contributions
 runway-0.019
plets-0.019
ramids-0.019
ifying-0.018
umes-0.018
Token an
Token ID281
Feature activation-2.23e-02

Pos logit contributions
P+0.013
 best+0.012
joy+0.011
my+0.011
 seeker+0.011
Neg logit contributions
ramids-0.017
plets-0.017
ifying-0.016
 runway-0.016
umes-0.016
Token expensive
Token ID5789
Feature activation-1.98e-02

Pos logit contributions
P+0.032
rob+0.028
joy+0.027
robat+0.027
 best+0.026
Neg logit contributions
 runway-0.039
plets-0.038
ramids-0.037
uring-0.036
ured-0.036
Token one
Token ID530
Feature activation-8.97e-02

Pos logit contributions
P+0.028
rob+0.023
 moderation+0.022
robat+0.022
Deal+0.022
Neg logit contributions
 runway-0.036
plets-0.034
ramids-0.034
ured-0.033
uring-0.033
Token.
Token ID13
Feature activation-9.96e-03

Pos logit contributions
P+0.131
rob+0.113
joy+0.110
robat+0.109
 seeker+0.108
Neg logit contributions
plets-0.152
 runway-0.149
ramids-0.148
ifying-0.146
umes-0.143
Token He
Token ID679
Feature activation-8.67e-03

Pos logit contributions
P+0.012
 best+0.010
rob+0.010
robat+0.010
joy+0.010
Neg logit contributions
plets-0.020
ramids-0.019
 runway-0.019
ifying-0.019
umes-0.018
Token smiled
Token ID13541
Feature activation-9.22e-03

Pos logit contributions
P+0.013
 best+0.012
joy+0.011
my+0.011
 seeker+0.011
Neg logit contributions
plets-0.015
ramids-0.014
ifying-0.014
 runway-0.014
umes-0.014
Token and
Token ID290
Feature activation-1.36e-02

Pos logit contributions
P+0.013
rob+0.011
robat+0.011
 moderation+0.011
 best+0.010
Neg logit contributions
plets-0.016
ramids-0.016
 runway-0.016
ifying-0.016
umes-0.015
Token said
Token ID531
Feature activation+4.20e-03

Pos logit contributions
P+0.018
 best+0.016
rob+0.015
joy+0.015
 seeker+0.015
Neg logit contributions
plets-0.025
ramids-0.025
 runway-0.025
ifying-0.024
umes-0.024
Token him
Token ID683
Feature activation-3.60e-03

Pos logit contributions
P+0.008
rob+0.007
 best+0.007
joy+0.007
robat+0.007
Neg logit contributions
plets-0.008
 runway-0.008
ramids-0.008
ifying-0.007
umes-0.007
Token he
Token ID339
Feature activation-1.54e-02

Pos logit contributions
P+0.005
 best+0.004
my+0.004
 seeker+0.004
 moderation+0.004
Neg logit contributions
plets-0.007
ramids-0.007
 runway-0.006
ifying-0.006
umes-0.006
Token would
Token ID561
Feature activation+2.10e-02

Pos logit contributions
P+0.023
 best+0.021
robat+0.019
joy+0.019
 seeker+0.019
Neg logit contributions
plets-0.026
ramids-0.025
 runway-0.025
ifying-0.024
umes-0.024
Token grant
Token ID7264
Feature activation-1.10e-02

Pos logit contributions
plets+0.034
ramids+0.033
 runway+0.032
ifying+0.032
umes+0.031
Neg logit contributions
P-0.033
 best-0.029
 seeker-0.028
joy-0.028
robat-0.028
Token her
Token ID607
Feature activation-1.87e-02

Pos logit contributions
P+0.014
 best+0.012
joy+0.012
rob+0.012
 moderation+0.012
Neg logit contributions
plets-0.021
ramids-0.021
 runway-0.020
ifying-0.020
umes-0.020
Token one
Token ID530
Feature activation-8.97e-02

Pos logit contributions
P+0.029
rob+0.026
robat+0.026
joy+0.024
 seeker+0.024
Neg logit contributions
ifying-0.030
 runway-0.029
plets-0.029
ramids-0.029
umes-0.028
Token wish
Token ID4601
Feature activation-1.87e-03

Pos logit contributions
P+0.151
rob+0.142
robat+0.131
joy+0.127
 seeker+0.124
Neg logit contributions
ifying-0.134
 runway-0.129
plets-0.129
ured-0.122
umes-0.121
Token.
Token ID13
Feature activation-5.19e-03

Pos logit contributions
P+0.002
rob+0.002
joy+0.002
 best+0.002
robat+0.002
Neg logit contributions
plets-0.003
 runway-0.003
ramids-0.003
ifying-0.003
umes-0.003
Token The
Token ID383
Feature activation-7.67e-03

Pos logit contributions
P+0.009
rob+0.008
robat+0.008
 seeker+0.008
 best+0.008
Neg logit contributions
plets-0.008
ramids-0.008
 runway-0.008
ifying-0.007
umes-0.007
Token little
Token ID1310
Feature activation+2.30e-02

Pos logit contributions
P+0.013
rob+0.011
robat+0.011
 seeker+0.011
joy+0.011
Neg logit contributions
 runway-0.011
plets-0.011
ramids-0.011
ifying-0.011
ured-0.011
Token girl
Token ID2576
Feature activation+1.09e-02

Pos logit contributions
 runway+0.033
plets+0.031
inated+0.031
 as+0.031
bell+0.030
Neg logit contributions
P-0.037
rob-0.036
robat-0.035
Deal-0.031
ossible-0.030
Token
Token ID198
Feature activation+1.01e-02

Pos logit contributions
P+0.022
robat+0.022
rob+0.021
ah+0.020
 seeker+0.020
Neg logit contributions
ramids-0.021
plets-0.020
 runway-0.019
ents-0.019
umes-0.019
Token
Token ID198
Feature activation+9.86e-03

Pos logit contributions
plets+0.021
 runway+0.021
ramids+0.021
ifying+0.021
umes+0.020
Neg logit contributions
P-0.010
 best-0.008
joy-0.008
rob-0.008
robat-0.008
Token"
Token ID1
Feature activation+1.39e-02

Pos logit contributions
plets+0.022
 runway+0.021
ramids+0.021
ifying+0.021
umes+0.020
Neg logit contributions
P-0.010
 best-0.008
joy-0.008
rob-0.008
robat-0.008
TokenBut
Token ID1537
Feature activation+1.46e-03

Pos logit contributions
plets+0.023
ramids+0.022
 runway+0.022
ifying+0.021
umes+0.021
Neg logit contributions
P-0.020
joy-0.019
 best-0.019
robat-0.018
 seeker-0.018
Token this
Token ID428
Feature activation-4.16e-02

Pos logit contributions
plets+0.002
 runway+0.002
ramids+0.002
ifying+0.002
umes+0.002
Neg logit contributions
P-0.002
 best-0.002
 seeker-0.002
joy-0.002
 moderation-0.002
Token one
Token ID530
Feature activation-8.95e-02

Pos logit contributions
P+0.062
joy+0.054
rob+0.051
robat+0.051
 moderation+0.050
Neg logit contributions
 runway-0.069
plets-0.069
ramids-0.068
umes-0.065
ifying-0.064
Token is
Token ID318
Feature activation-2.63e-02

Pos logit contributions
P+0.139
joy+0.125
rob+0.119
 seeker+0.114
robat+0.113
Neg logit contributions
plets-0.140
 runway-0.138
ramids-0.133
ifying-0.132
keys-0.131
Token the
Token ID262
Feature activation-7.65e-03

Pos logit contributions
 best+0.036
P+0.035
 seeker+0.031
 moderation+0.030
my+0.030
Neg logit contributions
plets-0.049
 runway-0.046
ramids-0.045
ifying-0.044
mic-0.043
Token best
Token ID1266
Feature activation-2.07e-02

Pos logit contributions
P+0.010
joy+0.009
rob+0.009
robat+0.008
ability+0.008
Neg logit contributions
 runway-0.014
ifying-0.013
ramids-0.013
umes-0.013
plets-0.013
Token!"
Token ID2474
Feature activation-2.44e-02

Pos logit contributions
P+0.031
rob+0.027
joy+0.027
robat+0.026
 moderation+0.026
Neg logit contributions
 runway-0.034
plets-0.034
ramids-0.034
ifying-0.032
umes-0.032
Token Tom
Token ID4186
Feature activation-1.96e-02

Pos logit contributions
P+0.028
 best+0.023
joy+0.023
rob+0.022
 seeker+0.022
Neg logit contributions
plets-0.050
 runway-0.049
ramids-0.049
ifying-0.048
umes-0.047
Token sund
Token ID37437
Feature activation-4.68e-02

Pos logit contributions
P+0.029
joy+0.028
 moderation+0.026
ability+0.025
irrel+0.025
Neg logit contributions
plets-0.032
ramids-0.031
ifying-0.030
 runway-0.030
drops-0.030
Tokenae
Token ID3609
Feature activation+1.38e-02

Pos logit contributions
joy+0.079
rob+0.073
P+0.072
irk+0.067
 vest+0.067
Neg logit contributions
ifying-0.065
plets-0.063
keys-0.060
umes-0.060
 runway-0.059
Token with
Token ID351
Feature activation-2.96e-03

Pos logit contributions
plets+0.024
 runway+0.024
ramids+0.023
ifying+0.023
umes+0.023
Neg logit contributions
P-0.019
rob-0.017
joy-0.016
 seeker-0.016
robat-0.016
Token lots
Token ID6041
Feature activation+1.30e-02

Pos logit contributions
P+0.004
 best+0.003
joy+0.003
rob+0.003
robat+0.003
Neg logit contributions
plets-0.005
 runway-0.005
ramids-0.005
ifying-0.005
umes-0.005
Token of
Token ID286
Feature activation+9.74e-03

Pos logit contributions
 runway+0.023
ramids+0.023
plets+0.023
umes+0.022
mic+0.022
Neg logit contributions
P-0.018
 best-0.016
joy-0.015
 moderation-0.015
robat-0.015
Token topp
Token ID23126
Feature activation-8.94e-02

Pos logit contributions
ramids+0.016
plets+0.016
ifying+0.015
 runway+0.015
umes+0.015
Neg logit contributions
P-0.014
 seeker-0.013
robat-0.012
joy-0.012
rob-0.012
Tokenings
Token ID654
Feature activation+7.25e-03

Pos logit contributions
P+0.159
rob+0.152
joy+0.151
 seeker+0.148
 moderation+0.147
Neg logit contributions
ramids-0.118
plets-0.115
ifying-0.109
ants-0.106
ured-0.105
Token.
Token ID13
Feature activation+2.57e-03

Pos logit contributions
plets+0.013
ramids+0.013
 runway+0.012
ifying+0.012
umes+0.012
Neg logit contributions
P-0.010
joy-0.009
 best-0.009
rob-0.008
robat-0.008
Token Tim
Token ID5045
Feature activation-2.39e-02

Pos logit contributions
ramids+0.004
plets+0.004
 runway+0.004
inated+0.004
ifying+0.004
Neg logit contributions
P-0.004
robat-0.003
 best-0.003
rob-0.003
 seeker-0.003
Tokenmy
Token ID1820
Feature activation-6.95e-03

Pos logit contributions
P+0.029
joy+0.028
rob+0.026
 seeker+0.025
robat+0.024
Neg logit contributions
 couldn-0.042
ric-0.042
ents-0.040
llers-0.040
ller-0.040
Token was
Token ID373
Feature activation+2.05e-03

Pos logit contributions
P+0.011
joy+0.010
rob+0.010
robat+0.010
 seeker+0.010
Neg logit contributions
plets-0.010
ramids-0.010
 runway-0.010
inated-0.010
ifying-0.009
Token liked
Token ID8288
Feature activation-1.08e-02

Pos logit contributions
P+0.005
 best+0.005
rob+0.004
robat+0.004
 seeker+0.004
Neg logit contributions
plets-0.006
 runway-0.005
ramids-0.005
ifying-0.005
umes-0.005
Token to
Token ID284
Feature activation-2.21e-02

Pos logit contributions
P+0.014
 best+0.013
joy+0.012
robat+0.011
my+0.011
Neg logit contributions
plets-0.021
ramids-0.020
 runway-0.020
ifying-0.019
umes-0.019
Token display
Token ID3359
Feature activation-9.87e-03

Pos logit contributions
P+0.033
joy+0.029
 best+0.029
rob+0.028
robat+0.028
Neg logit contributions
plets-0.036
 runway-0.036
ramids-0.036
ifying-0.035
umes-0.034
Token and
Token ID290
Feature activation-2.85e-03

Pos logit contributions
P+0.016
 best+0.015
joy+0.014
robat+0.014
rob+0.014
Neg logit contributions
plets-0.015
 runway-0.015
ramids-0.014
ifying-0.014
umes-0.014
Token show
Token ID905
Feature activation+3.88e-03

Pos logit contributions
P+0.004
 best+0.004
my+0.003
 vest+0.003
 moderation+0.003
Neg logit contributions
plets-0.005
ramids-0.005
ifying-0.005
umes-0.005
 runway-0.005
Token off
Token ID572
Feature activation+7.00e-02

Pos logit contributions
plets+0.006
 runway+0.005
ifying+0.005
ramids+0.005
ulus+0.005
Neg logit contributions
 best-0.007
P-0.007
my-0.006
joy-0.006
 idea-0.006
Token to
Token ID284
Feature activation+7.37e-03

Pos logit contributions
plets+0.174
mic+0.153
 runway+0.152
ifying+0.151
ender+0.150
Neg logit contributions
joy-0.060
 best-0.055
P-0.055
 his-0.053
my-0.045
Token her
Token ID607
Feature activation+1.71e-02

Pos logit contributions
 runway+0.011
ramids+0.010
plets+0.010
ured+0.010
ifying+0.010
Neg logit contributions
P-0.013
rob-0.011
joy-0.011
robat-0.011
 seeker-0.011
Token friends
Token ID2460
Feature activation-1.89e-03

Pos logit contributions
 runway+0.035
ramids+0.034
plets+0.033
umes+0.033
ifying+0.033
Neg logit contributions
P-0.019
rob-0.016
robat-0.015
joy-0.015
 moderation-0.015
Token.
Token ID13
Feature activation-1.98e-03

Pos logit contributions
P+0.002
 best+0.002
joy+0.002
robat+0.002
rob+0.002
Neg logit contributions
plets-0.004
 runway-0.004
ramids-0.004
ifying-0.003
umes-0.003
Token Tom
Token ID4186
Feature activation-1.65e-02

Pos logit contributions
P+0.004
robat+0.003
rob+0.003
 seeker+0.003
 best+0.003
Neg logit contributions
ramids-0.003
inated-0.003
plets-0.002
 runway-0.002
umes-0.002
Token hugged
Token ID41130
Feature activation+2.11e-04

Pos logit contributions
P+0.021
 best+0.018
joy+0.017
rob+0.017
robat+0.016
Neg logit contributions
 runway-0.031
plets-0.031
ramids-0.031
ifying-0.030
umes-0.029
Token his
Token ID465
Feature activation+4.88e-03

Pos logit contributions
ramids+0.000
 runway+0.000
ured+0.000
uring+0.000
lights+0.000
Neg logit contributions
P-0.000
rob-0.000
robat-0.000
Deal-0.000
 seeker-0.000
Token mother
Token ID2802
Feature activation+5.41e-03

Pos logit contributions
 runway+0.004
ramids+0.004
inated+0.004
ifying+0.004
ller+0.004
Neg logit contributions
P-0.011
rob-0.011
robat-0.010
 moderation-0.010
Deal-0.010
Token before
Token ID878
Feature activation+2.20e-02

Pos logit contributions
plets+0.010
 runway+0.009
ramids+0.009
ifying+0.009
umes+0.009
Neg logit contributions
P-0.007
rob-0.006
 best-0.006
joy-0.006
robat-0.006
Token running
Token ID2491
Feature activation-5.70e-03

Pos logit contributions
plets+0.035
 runway+0.034
ramids+0.034
ifying+0.033
umes+0.033
Neg logit contributions
P-0.035
 best-0.030
joy-0.030
rob-0.030
robat-0.030
Token off
Token ID572
Feature activation+5.30e-02

Pos logit contributions
P+0.008
joy+0.007
 best+0.007
robat+0.007
 seeker+0.007
Neg logit contributions
plets-0.010
ramids-0.010
 runway-0.010
umes-0.010
keys-0.009
Token again
Token ID757
Feature activation-3.48e-02

Pos logit contributions
plets+0.095
 runway+0.094
ramids+0.093
ifying+0.091
umes+0.089
Neg logit contributions
P-0.072
 best-0.062
joy-0.061
rob-0.061
robat-0.060
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
P+0.052
rob+0.045
robat+0.044
 seeker+0.043
 best+0.043
Neg logit contributions
 runway-0.058
plets-0.058
ramids-0.057
ifying-0.056
ured-0.054
Token He
Token ID679
Feature activation-6.29e-03

Pos logit contributions
P+0.011
joy+0.009
 best+0.009
rob+0.008
robat+0.008
Neg logit contributions
plets-0.021
 runway-0.021
ramids-0.021
ifying-0.020
umes-0.020
Token would
Token ID561
Feature activation+2.41e-02

Pos logit contributions
P+0.009
 best+0.008
joy+0.008
rob+0.007
robat+0.007
Neg logit contributions
plets-0.011
ramids-0.011
 runway-0.011
ifying-0.011
umes-0.011
Token always
Token ID1464
Feature activation-6.92e-04

Pos logit contributions
plets+0.045
ramids+0.043
umes+0.042
 runway+0.042
ifying+0.041
Neg logit contributions
P-0.031
 best-0.029
my-0.028
 seeker-0.028
joy-0.027
Token sweep
Token ID16085
Feature activation+2.66e-02

Pos logit contributions
plets+0.015
 runway+0.015
ramids+0.015
ifying+0.015
umes+0.014
Neg logit contributions
P-0.014
 best-0.012
joy-0.012
rob-0.012
robat-0.012
Token the
Token ID262
Feature activation+2.10e-02

Pos logit contributions
plets+0.038
 runway+0.038
ramids+0.037
ifying+0.036
umes+0.035
Neg logit contributions
P-0.046
 best-0.041
rob-0.040
robat-0.040
joy-0.040
Token flour
Token ID10601
Feature activation+1.98e-02

Pos logit contributions
plets+0.036
ramids+0.035
 runway+0.035
ifying+0.034
umes+0.034
Neg logit contributions
P-0.031
 best-0.027
joy-0.026
rob-0.026
robat-0.026
Token and
Token ID290
Feature activation+2.43e-02

Pos logit contributions
plets+0.034
 runway+0.034
ramids+0.034
ifying+0.033
umes+0.032
Neg logit contributions
P-0.028
joy-0.024
rob-0.024
 best-0.024
robat-0.024
Token throw
Token ID3714
Feature activation-6.42e-03

Pos logit contributions
plets+0.043
ramids+0.043
 runway+0.042
ifying+0.041
inated+0.041
Neg logit contributions
P-0.032
 moderation-0.029
 best-0.029
my-0.028
joy-0.026
Token away
Token ID1497
Feature activation+5.63e-02

Pos logit contributions
P+0.011
 best+0.010
 moderation+0.009
joy+0.009
rob+0.009
Neg logit contributions
 runway-0.010
plets-0.010
ramids-0.009
ifying-0.009
umes-0.009
Token the
Token ID262
Feature activation+1.44e-02

Pos logit contributions
 runway+0.099
plets+0.098
mic+0.096
ramids+0.094
ured+0.093
Neg logit contributions
P-0.079
 best-0.074
 moderation-0.066
my-0.065
joy-0.063
Token jar
Token ID17379
Feature activation+2.18e-02

Pos logit contributions
plets+0.025
 runway+0.025
ramids+0.025
ifying+0.024
umes+0.024
Neg logit contributions
P-0.020
rob-0.017
joy-0.017
robat-0.017
 best-0.017
Token.
Token ID13
Feature activation-6.34e-04

Pos logit contributions
plets+0.041
ramids+0.040
 runway+0.040
ifying+0.039
umes+0.038
Neg logit contributions
P-0.028
 best-0.024
joy-0.023
rob-0.023
robat-0.023
Token Then
Token ID3244
Feature activation+6.55e-04

Pos logit contributions
P+0.001
 best+0.001
joy+0.001
 seeker+0.001
 moderation+0.001
Neg logit contributions
keys-0.001
plets-0.001
 runway-0.001
ured-0.001
umes-0.001
Token they
Token ID484
Feature activation+2.18e-02

Pos logit contributions
plets+0.001
 runway+0.001
mic+0.001
ifying+0.001
inated+0.001
Neg logit contributions
 best-0.001
P-0.001
 seeker-0.001
joy-0.001
my-0.001
Token able
Token ID1498
Feature activation+7.47e-03

Pos logit contributions
P+0.013
rob+0.011
robat+0.011
joy+0.011
 moderation+0.011
Neg logit contributions
plets-0.013
 runway-0.013
ramids-0.013
ifying-0.013
umes-0.013
Token to
Token ID284
Feature activation+6.40e-03

Pos logit contributions
plets+0.015
ramids+0.015
 runway+0.015
ifying+0.014
inated+0.014
Neg logit contributions
 best-0.009
P-0.008
joy-0.008
my-0.008
 moderation-0.007
Token watch
Token ID2342
Feature activation+4.31e-03

Pos logit contributions
plets+0.012
ramids+0.012
umes+0.012
ifying+0.012
lights+0.011
Neg logit contributions
P-0.008
 best-0.007
 seeker-0.007
my-0.007
robat-0.007
Token the
Token ID262
Feature activation+2.42e-02

Pos logit contributions
plets+0.007
ramids+0.007
 runway+0.007
ifying+0.007
umes+0.006
Neg logit contributions
P-0.006
 best-0.006
joy-0.006
robat-0.006
rob-0.006
Token little
Token ID1310
Feature activation+5.93e-02

Pos logit contributions
ramids+0.039
plets+0.038
ifying+0.036
ured+0.036
 runway+0.036
Neg logit contributions
P-0.037
 best-0.037
joy-0.033
robat-0.033
 seeker-0.032
Token girl
Token ID2576
Feature activation+5.61e-02

Pos logit contributions
plets+0.133
 runway+0.132
ramids+0.130
ifying+0.127
umes+0.126
Neg logit contributions
P-0.055
rob-0.042
robat-0.041
 best-0.040
joy-0.039
Token smile
Token ID8212
Feature activation-2.50e-03

Pos logit contributions
plets+0.110
ramids+0.107
 runway+0.103
ifying+0.101
inated+0.099
Neg logit contributions
 best-0.064
P-0.062
joy-0.060
my-0.059
robat-0.054
Token and
Token ID290
Feature activation+2.53e-03

Pos logit contributions
P+0.003
rob+0.003
 best+0.003
joy+0.003
robat+0.003
Neg logit contributions
plets-0.005
 runway-0.004
ramids-0.004
ifying-0.004
umes-0.004
Token to
Token ID284
Feature activation+5.07e-03

Pos logit contributions
plets+0.005
ramids+0.005
 runway+0.004
umes+0.004
ifying+0.004
Neg logit contributions
P-0.003
 best-0.003
joy-0.003
 seeker-0.003
robat-0.003
Token remember
Token ID3505
Feature activation+1.79e-02

Pos logit contributions
plets+0.009
ramids+0.009
 runway+0.009
umes+0.008
ifying+0.008
Neg logit contributions
P-0.007
 best-0.006
joy-0.006
my-0.006
 moderation-0.006
Token when
Token ID618
Feature activation+2.76e-02

Pos logit contributions
plets+0.029
ramids+0.027
 runway+0.027
ifying+0.025
umes+0.025
Neg logit contributions
P-0.029
 best-0.028
joy-0.027
 moderation-0.026
my-0.026
Token
Token ID198
Feature activation+1.22e-02

Pos logit contributions
P+0.032
 seeker+0.031
 best+0.029
joy+0.028
rob+0.028
Neg logit contributions
plets-0.039
ramids-0.038
inated-0.037
 runway-0.036
uring-0.035
Token
Token ID198
Feature activation+1.06e-02

Pos logit contributions
ramids+0.019
plets+0.019
 runway+0.018
keys+0.018
inated+0.018
Neg logit contributions
 seeker-0.018
P-0.017
joy-0.017
 best-0.016
 moderation-0.016
TokenSo
Token ID2396
Feature activation+4.73e-03

Pos logit contributions
plets+0.017
ramids+0.017
ifying+0.017
 runway+0.017
umes+0.016
Neg logit contributions
P-0.018
Deal-0.015
robat-0.014
 best-0.014
rob-0.014
Token they
Token ID484
Feature activation+1.20e-02

Pos logit contributions
plets+0.010
 runway+0.010
ramids+0.010
umes+0.009
ifying+0.009
Neg logit contributions
P-0.005
 best-0.005
joy-0.004
 seeker-0.004
rob-0.004
Token ran
Token ID4966
Feature activation-2.30e-03

Pos logit contributions
plets+0.020
ramids+0.019
 runway+0.018
ifying+0.018
umes+0.018
Neg logit contributions
P-0.020
 best-0.017
 seeker-0.017
robat-0.016
my-0.016
Token off
Token ID572
Feature activation+6.61e-02

Pos logit contributions
P+0.003
 best+0.003
 seeker+0.003
joy+0.003
my+0.003
Neg logit contributions
plets-0.004
ifying-0.004
keys-0.004
ramids-0.004
umes-0.004
Token to
Token ID284
Feature activation+2.92e-03

Pos logit contributions
plets+0.116
ramids+0.112
 runway+0.111
ifying+0.111
umes+0.108
Neg logit contributions
P-0.094
joy-0.084
 best-0.083
rob-0.079
 seeker-0.079
Token the
Token ID262
Feature activation-1.46e-03

Pos logit contributions
 runway+0.005
plets+0.005
ramids+0.005
ifying+0.005
umes+0.005
Neg logit contributions
P-0.004
rob-0.003
 best-0.003
joy-0.003
robat-0.003
Token garden
Token ID11376
Feature activation+1.63e-02

Pos logit contributions
P+0.002
rob+0.002
robat+0.002
joy+0.002
 moderation+0.002
Neg logit contributions
 runway-0.002
ramids-0.002
ured-0.002
ifying-0.002
plets-0.002
Token and
Token ID290
Feature activation+5.84e-03

Pos logit contributions
 runway+0.028
ramids+0.027
plets+0.027
uring+0.026
umes+0.026
Neg logit contributions
P-0.024
rob-0.021
robat-0.021
 seeker-0.020
 best-0.019
Token the
Token ID262
Feature activation+1.40e-02

Pos logit contributions
plets+0.012
ramids+0.011
 runway+0.011
ifying+0.011
umes+0.011
Neg logit contributions
P-0.007
 best-0.006
 seeker-0.006
my-0.005
joy-0.005
Token.
Token ID13
Feature activation-5.29e-03

Pos logit contributions
P+0.019
 best+0.018
joy+0.017
my+0.016
robat+0.016
Neg logit contributions
ramids-0.033
plets-0.033
 runway-0.033
umes-0.032
ifying-0.032
Token
Token ID220
Feature activation+3.67e-03

Pos logit contributions
P+0.007
joy+0.006
 best+0.006
 moderation+0.006
rob+0.006
Neg logit contributions
 runway-0.009
plets-0.009
ramids-0.009
ifying-0.009
umes-0.009
Token
Token ID198
Feature activation+1.33e-03

Pos logit contributions
 runway+0.009
plets+0.009
ramids+0.008
ifying+0.008
ured+0.008
Neg logit contributions
P-0.003
 best-0.002
joy-0.002
my-0.002
 moderation-0.002
Token
Token ID198
Feature activation+2.53e-03

Pos logit contributions
plets+0.003
ramids+0.003
 runway+0.002
ifying+0.002
umes+0.002
Neg logit contributions
P-0.002
 best-0.001
rob-0.001
robat-0.001
 seeker-0.001
TokenThe
Token ID464
Feature activation-6.25e-03

Pos logit contributions
plets+0.004
 runway+0.004
ramids+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.005
joy-0.004
robat-0.003
 best-0.003
 moderation-0.003
Token smart
Token ID4451
Feature activation+6.05e-03

Pos logit contributions
P+0.009
 best+0.008
joy+0.007
 seeker+0.007
robat+0.007
Neg logit contributions
plets-0.011
ramids-0.011
 runway-0.011
ifying-0.011
umes-0.010
Token thing
Token ID1517
Feature activation-8.68e-03

Pos logit contributions
plets+0.012
ramids+0.012
 runway+0.011
ifying+0.011
umes+0.011
Neg logit contributions
P-0.007
 best-0.006
joy-0.006
 seeker-0.006
robat-0.006
Token spun
Token ID26843
Feature activation-3.88e-03

Pos logit contributions
 best+0.011
P+0.011
my+0.010
joy+0.009
robat+0.009
Neg logit contributions
ramids-0.016
plets-0.016
 runway-0.016
ifying-0.015
umes-0.015
Token higher
Token ID2440
Feature activation-8.74e-03

Pos logit contributions
P+0.005
 best+0.005
joy+0.005
robat+0.005
my+0.005
Neg logit contributions
ramids-0.007
plets-0.007
 runway-0.006
umes-0.006
keys-0.006
Token and
Token ID290
Feature activation-4.07e-03

Pos logit contributions
P+0.011
 best+0.009
joy+0.009
rob+0.009
robat+0.009
Neg logit contributions
plets-0.016
 runway-0.016
ramids-0.016
ifying-0.016
umes-0.015
Token higher
Token ID2440
Feature activation+6.11e-03

Pos logit contributions
P+0.006
 best+0.006
rob+0.006
joy+0.006
robat+0.005
Neg logit contributions
plets-0.006
 runway-0.006
ramids-0.006
ifying-0.006
umes-0.006
Token him
Token ID683
Feature activation-1.75e-02

Pos logit contributions
 runway+0.031
ramids+0.031
ifying+0.030
plets+0.029
 flashing+0.029
Neg logit contributions
P-0.029
rob-0.026
robat-0.026
Deal-0.026
 seeker-0.025
Token to
Token ID284
Feature activation-5.57e-03

Pos logit contributions
P+0.029
rob+0.026
robat+0.025
 moderation+0.024
joy+0.024
Neg logit contributions
 runway-0.026
ramids-0.026
plets-0.025
umes-0.025
ifying-0.025
Token school
Token ID1524
Feature activation+1.16e-02

Pos logit contributions
P+0.011
rob+0.010
robat+0.010
orn+0.010
Deal+0.010
Neg logit contributions
 runway-0.007
ramids-0.006
uring-0.006
ured-0.006
mic-0.006
Token,
Token ID11
Feature activation+2.57e-03

Pos logit contributions
plets+0.022
 runway+0.022
ramids+0.022
ifying+0.021
umes+0.021
Neg logit contributions
P-0.015
 best-0.012
joy-0.012
rob-0.012
robat-0.012
Token holding
Token ID4769
Feature activation-2.72e-03

Pos logit contributions
plets+0.005
ramids+0.005
 runway+0.005
ifying+0.005
umes+0.004
Neg logit contributions
P-0.003
 best-0.003
joy-0.003
rob-0.003
robat-0.003
Token his
Token ID465
Feature activation+7.02e-03

Pos logit contributions
P+0.004
rob+0.003
Deal+0.003
robat+0.003
joy+0.003
Neg logit contributions
ifying-0.005
ramids-0.005
ured-0.004
umes-0.004
 runway-0.004
Token hand
Token ID1021
Feature activation-1.11e-02

Pos logit contributions
 runway+0.011
ifying+0.011
ramids+0.011
plets+0.011
umes+0.011
Neg logit contributions
P-0.011
rob-0.010
robat-0.009
orn-0.009
Deal-0.009
Token all
Token ID477
Feature activation+1.10e-02

Pos logit contributions
P+0.012
 best+0.011
my+0.011
 vest+0.010
 seeker+0.010
Neg logit contributions
plets-0.023
 runway-0.022
ramids-0.021
mic-0.020
umes-0.020
Token the
Token ID262
Feature activation+4.96e-03

Pos logit contributions
plets+0.018
 runway+0.018
ramids+0.018
ifying+0.017
umes+0.017
Neg logit contributions
P-0.017
 best-0.015
joy-0.014
rob-0.014
robat-0.014
Token way
Token ID835
Feature activation+2.61e-02

Pos logit contributions
 runway+0.008
ramids+0.008
ifying+0.008
umes+0.007
 boarding+0.007
Neg logit contributions
P-0.007
rob-0.007
joy-0.006
robat-0.006
Deal-0.006
Token.
Token ID13
Feature activation-3.16e-03

Pos logit contributions
plets+0.052
ramids+0.049
 runway+0.049
umes+0.048
ifying+0.048
Neg logit contributions
P-0.030
 best-0.028
my-0.027
joy-0.026
 seeker-0.025
Token field
Token ID2214
Feature activation+1.51e-02

Pos logit contributions
plets+0.001
ifying+0.001
umes+0.001
ured+0.001
ramids+0.001
Neg logit contributions
P-0.001
 best-0.001
 vest-0.001
my-0.001
joy-0.001
Token,
Token ID11
Feature activation+3.41e-03

Pos logit contributions
plets+0.026
 runway+0.026
ramids+0.026
ifying+0.025
umes+0.024
Neg logit contributions
P-0.022
rob-0.019
robat-0.018
 best-0.018
joy-0.018
Token over
Token ID625
Feature activation+1.60e-02

Pos logit contributions
plets+0.007
ifying+0.006
ramids+0.006
 runway+0.006
umes+0.006
Neg logit contributions
P-0.004
 best-0.004
joy-0.004
 seeker-0.003
rob-0.003
Token the
Token ID262
Feature activation+5.71e-03

Pos logit contributions
 runway+0.020
plets+0.020
ramids+0.020
ifying+0.019
umes+0.018
Neg logit contributions
P-0.029
robat-0.027
rob-0.027
 seeker-0.026
 best-0.026
Token mountains
Token ID12269
Feature activation-5.04e-03

Pos logit contributions
plets+0.009
ramids+0.009
ifying+0.009
ured+0.009
umes+0.009
Neg logit contributions
P-0.009
 best-0.008
 seeker-0.007
joy-0.007
my-0.007
Token and
Token ID290
Feature activation+2.08e-02

Pos logit contributions
P+0.005
 best+0.004
joy+0.004
my+0.004
robat+0.004
Neg logit contributions
plets-0.011
ramids-0.011
ifying-0.011
 runway-0.010
umes-0.010
Token the
Token ID262
Feature activation+2.14e-02

Pos logit contributions
plets+0.033
ifying+0.033
ramids+0.032
 runway+0.032
umes+0.031
Neg logit contributions
P-0.032
 best-0.029
rob-0.028
joy-0.028
my-0.028
Token sea
Token ID5417
Feature activation+1.21e-02

Pos logit contributions
plets+0.032
ramids+0.032
 runway+0.031
ifying+0.031
umes+0.030
Neg logit contributions
P-0.035
 best-0.032
joy-0.031
robat-0.030
rob-0.030
Token.
Token ID13
Feature activation+6.89e-03

Pos logit contributions
ifying+0.027
ramids+0.026
plets+0.026
 runway+0.026
umes+0.025
Neg logit contributions
 best-0.011
P-0.010
joy-0.009
my-0.009
m-0.008
Token Everywhere
Token ID48201
Feature activation+2.00e-02

Pos logit contributions
ifying+0.012
plets+0.012
umes+0.012
 runway+0.012
ramids+0.011
Neg logit contributions
P-0.009
joy-0.008
 best-0.008
 seeker-0.008
my-0.008
Token the
Token ID262
Feature activation+9.40e-04

Pos logit contributions
plets+0.031
ramids+0.031
umes+0.031
 runway+0.031
ifying+0.031
Neg logit contributions
P-0.032
 best-0.030
joy-0.028
rob-0.027
 moderation-0.027
Token looked
Token ID3114
Feature activation+1.23e-02

Pos logit contributions
P+0.010
 best+0.008
rob+0.008
joy+0.008
robat+0.008
Neg logit contributions
plets-0.013
 runway-0.013
ramids-0.013
ifying-0.013
umes-0.013
Token pale
Token ID14005
Feature activation+1.14e-02

Pos logit contributions
plets+0.021
ramids+0.020
 runway+0.020
ifying+0.020
umes+0.019
Neg logit contributions
P-0.018
rob-0.016
 best-0.015
robat-0.015
joy-0.015
Token and
Token ID290
Feature activation-8.65e-03

Pos logit contributions
plets+0.019
ramids+0.019
ifying+0.019
 runway+0.019
umes+0.018
Neg logit contributions
P-0.017
rob-0.014
robat-0.014
 moderation-0.014
 seeker-0.013
Token sad
Token ID6507
Feature activation+2.07e-02

Pos logit contributions
P+0.014
rob+0.012
robat+0.012
 best+0.012
joy+0.012
Neg logit contributions
plets-0.013
 runway-0.013
ramids-0.013
ifying-0.013
umes-0.013
Token.
Token ID13
Feature activation-3.90e-03

Pos logit contributions
plets+0.035
 runway+0.035
ramids+0.035
ifying+0.034
umes+0.033
Neg logit contributions
P-0.030
rob-0.026
robat-0.025
joy-0.025
 seeker-0.025
Token She
Token ID1375
Feature activation+1.27e-02

Pos logit contributions
P+0.005
robat+0.005
rob+0.005
ah+0.004
 best+0.004
Neg logit contributions
ramids-0.007
ifying-0.007
plets-0.007
 runway-0.007
inated-0.006
Token saw
Token ID2497
Feature activation-5.12e-03

Pos logit contributions
plets+0.024
 runway+0.024
ramids+0.023
ifying+0.023
umes+0.023
Neg logit contributions
P-0.017
 best-0.014
my-0.014
rob-0.014
joy-0.013
Token his
Token ID465
Feature activation-2.89e-03

Pos logit contributions
P+0.006
 best+0.005
rob+0.005
joy+0.005
robat+0.005
Neg logit contributions
plets-0.010
 runway-0.010
ramids-0.010
ifying-0.010
umes-0.010
Token teeth
Token ID9941
Feature activation+1.41e-02

Pos logit contributions
P+0.005
rob+0.004
robat+0.004
Deal+0.004
joy+0.004
Neg logit contributions
 runway-0.005
ramids-0.004
plets-0.004
ifying-0.004
umes-0.004
Token and
Token ID290
Feature activation-2.39e-03

Pos logit contributions
plets+0.026
ramids+0.025
 runway+0.025
ifying+0.024
umes+0.024
Neg logit contributions
P-0.018
 best-0.016
joy-0.015
rob-0.015
robat-0.015
Token they
Token ID484
Feature activation+1.27e-02

Pos logit contributions
P+0.002
 best+0.002
 vest+0.002
joy+0.002
my+0.002
Neg logit contributions
plets-0.005
ramids-0.005
 runway-0.005
umes-0.005
ifying-0.005
Token to
Token ID284
Feature activation+1.67e-02

Pos logit contributions
plets+0.013
ifying+0.012
ramids+0.012
 runway+0.012
lights+0.012
Neg logit contributions
P-0.005
 best-0.005
joy-0.004
my-0.004
 right-0.004
Token go
Token ID467
Feature activation-1.26e-02

Pos logit contributions
plets+0.030
ramids+0.028
ifying+0.027
 runway+0.027
umes+0.027
Neg logit contributions
P-0.025
 best-0.022
 seeker-0.021
 moderation-0.021
 vest-0.020
Token to
Token ID284
Feature activation+2.48e-02

Pos logit contributions
P+0.020
Deal+0.019
 moderation+0.019
joy+0.019
robat+0.018
Neg logit contributions
 runway-0.018
uring-0.017
umes-0.017
ramids-0.017
plets-0.017
Token the
Token ID262
Feature activation+8.78e-03

Pos logit contributions
plets+0.040
ramids+0.037
ifying+0.037
 runway+0.036
umes+0.036
Neg logit contributions
P-0.040
 best-0.036
joy-0.036
 seeker-0.035
rob-0.035
Token park
Token ID3952
Feature activation+2.42e-03

Pos logit contributions
plets+0.020
ramids+0.019
 runway+0.019
ifying+0.019
umes+0.018
Neg logit contributions
P-0.008
 best-0.007
rob-0.006
 seeker-0.006
joy-0.006
Token to
Token ID284
Feature activation+3.72e-03

Pos logit contributions
 runway+0.004
ramids+0.004
uring+0.003
plets+0.003
umes+0.003
Neg logit contributions
P-0.004
rob-0.004
robat-0.004
joy-0.003
 moderation-0.003
Token play
Token ID711
Feature activation-1.01e-02

Pos logit contributions
 runway+0.006
ramids+0.006
plets+0.006
ifying+0.006
umes+0.006
Neg logit contributions
P-0.005
joy-0.005
 best-0.005
rob-0.005
robat-0.005
Token.
Token ID13
Feature activation+7.12e-03

Pos logit contributions
joy+0.018
 moderation+0.017
icer+0.017
rev+0.017
P+0.017
Neg logit contributions
 as-0.011
uring-0.011
ured-0.011
 runway-0.010
plets-0.010
Token She
Token ID1375
Feature activation+2.29e-02

Pos logit contributions
plets+0.015
keys+0.014
 runway+0.014
ifying+0.014
ramids+0.014
Neg logit contributions
P-0.008
my-0.007
joy-0.007
 vest-0.006
 seeker-0.006
Token saw
Token ID2497
Feature activation-2.28e-03

Pos logit contributions
plets+0.040
ramids+0.039
 runway+0.039
ifying+0.038
umes+0.037
Neg logit contributions
P-0.033
 best-0.028
rob-0.028
joy-0.028
robat-0.027
Token a
Token ID257
Feature activation+6.62e-03

Pos logit contributions
P+0.003
 best+0.003
joy+0.003
rob+0.003
robat+0.003
Neg logit contributions
plets-0.004
ramids-0.004
 runway-0.004
ifying-0.004
umes-0.004
Token!"
Token ID2474
Feature activation-2.94e-02

Pos logit contributions
P+0.027
 best+0.023
rob+0.023
robat+0.023
joy+0.023
Neg logit contributions
plets-0.025
ramids-0.025
 runway-0.025
ifying-0.024
umes-0.024
Token Sam
Token ID3409
Feature activation-2.57e-04

Pos logit contributions
P+0.032
 best+0.025
rob+0.024
robat+0.024
joy+0.023
Neg logit contributions
 runway-0.062
plets-0.062
ramids-0.061
ifying-0.061
umes-0.059
Token shouted
Token ID17293
Feature activation-1.34e-02

Pos logit contributions
P+0.000
 best+0.000
joy+0.000
rob+0.000
robat+0.000
Neg logit contributions
plets-0.000
 runway-0.000
ramids-0.000
ifying-0.000
umes-0.000
Token as
Token ID355
Feature activation+8.56e-03

Pos logit contributions
P+0.017
 best+0.015
joy+0.015
 seeker+0.014
my+0.014
Neg logit contributions
plets-0.025
 runway-0.024
ramids-0.024
ifying-0.024
umes-0.023
Token he
Token ID339
Feature activation-1.30e-02

Pos logit contributions
plets+0.015
 runway+0.015
ramids+0.014
ifying+0.014
umes+0.014
Neg logit contributions
P-0.012
rob-0.010
robat-0.010
 best-0.010
joy-0.010
Token threw
Token ID9617
Feature activation-3.21e-02

Pos logit contributions
P+0.022
 best+0.019
rob+0.019
robat+0.019
joy+0.019
Neg logit contributions
plets-0.019
ramids-0.019
 runway-0.019
ifying-0.018
umes-0.018
Token the
Token ID262
Feature activation+1.49e-02

Pos logit contributions
P+0.051
rob+0.044
joy+0.044
robat+0.043
 best+0.043
Neg logit contributions
 runway-0.050
plets-0.050
ramids-0.050
ifying-0.048
umes-0.046
Token red
Token ID2266
Feature activation+1.17e-02

Pos logit contributions
plets+0.022
 runway+0.022
ramids+0.021
ifying+0.021
umes+0.020
Neg logit contributions
P-0.025
joy-0.022
rob-0.022
 best-0.022
robat-0.022
Token rocket
Token ID10701
Feature activation+6.07e-03

Pos logit contributions
plets+0.019
ramids+0.019
 runway+0.018
umes+0.018
ifying+0.018
Neg logit contributions
P-0.018
 best-0.016
robat-0.015
rob-0.015
joy-0.015
Token as
Token ID355
Feature activation+2.75e-02

Pos logit contributions
plets+0.011
ramids+0.011
umes+0.011
 runway+0.010
ifying+0.010
Neg logit contributions
P-0.008
 best-0.007
my-0.007
 vest-0.007
robat-0.006
Token high
Token ID1029
Feature activation+2.08e-02

Pos logit contributions
plets+0.046
ramids+0.045
 runway+0.045
ifying+0.044
umes+0.043
Neg logit contributions
P-0.041
rob-0.035
robat-0.035
joy-0.035
 best-0.035
Token
Token ID198
Feature activation-1.44e-03

Pos logit contributions
P+0.006
 best+0.006
rob+0.005
joy+0.005
 seeker+0.005
Neg logit contributions
plets-0.010
ramids-0.010
 runway-0.010
ifying-0.010
umes-0.010
TokenThe
Token ID464
Feature activation-6.05e-03

Pos logit contributions
P+0.002
 best+0.002
joy+0.002
rob+0.002
robat+0.002
Neg logit contributions
plets-0.002
 runway-0.002
ramids-0.002
ifying-0.002
umes-0.002
Token little
Token ID1310
Feature activation+1.63e-02

Pos logit contributions
P+0.008
rob+0.007
joy+0.007
 best+0.007
robat+0.007
Neg logit contributions
plets-0.011
 runway-0.010
ramids-0.010
ifying-0.010
umes-0.010
Token girl
Token ID2576
Feature activation+6.47e-03

Pos logit contributions
 runway+0.026
plets+0.026
ifying+0.025
drops+0.024
umes+0.024
Neg logit contributions
P-0.022
rob-0.021
robat-0.020
 moderation-0.019
Deal-0.019
Token listened
Token ID16399
Feature activation+1.30e-02

Pos logit contributions
plets+0.012
ramids+0.012
 runway+0.012
ifying+0.012
umes+0.012
Neg logit contributions
P-0.008
 best-0.007
joy-0.007
my-0.007
 seeker-0.006
Token.
Token ID13
Feature activation-6.33e-03

Pos logit contributions
plets+0.025
 runway+0.024
ramids+0.023
ifying+0.023
umes+0.023
Neg logit contributions
P-0.016
 best-0.015
joy-0.014
my-0.013
 right-0.012
Token She
Token ID1375
Feature activation+1.81e-02

Pos logit contributions
P+0.008
joy+0.008
 best+0.007
my+0.007
 seeker+0.007
Neg logit contributions
plets-0.012
 runway-0.011
ramids-0.011
keys-0.011
ifying-0.011
Token heard
Token ID2982
Feature activation+4.56e-03

Pos logit contributions
plets+0.033
ramids+0.032
 runway+0.032
ifying+0.031
umes+0.031
Neg logit contributions
P-0.024
 best-0.022
my-0.021
joy-0.020
robat-0.020
Token the
Token ID262
Feature activation+5.16e-03

Pos logit contributions
plets+0.009
ramids+0.008
 runway+0.008
ifying+0.008
inated+0.008
Neg logit contributions
 best-0.006
P-0.005
joy-0.005
my-0.005
 vest-0.005
Token birds
Token ID10087
Feature activation+1.76e-02

Pos logit contributions
plets+0.008
 runway+0.008
ramids+0.008
ifying+0.007
umes+0.007
Neg logit contributions
P-0.008
 best-0.007
rob-0.007
joy-0.007
robat-0.007
Token singing
Token ID13777
Feature activation+2.98e-02

Pos logit contributions
ramids+0.027
plets+0.027
ifying+0.026
umes+0.025
 runway+0.025
Neg logit contributions
my-0.026
 best-0.025
m-0.025
P-0.024
joy-0.023
Token sad
Token ID6507
Feature activation+1.17e-02

Pos logit contributions
P+0.014
 best+0.013
joy+0.012
 moderation+0.011
my+0.011
Neg logit contributions
ramids-0.018
 runway-0.018
plets-0.018
umes-0.017
ifying-0.017
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
plets+0.023
 runway+0.023
ramids+0.023
ifying+0.022
umes+0.022
Neg logit contributions
P-0.014
 best-0.012
joy-0.012
robat-0.011
rob-0.011
Token Joe
Token ID5689
Feature activation-1.32e-02

Pos logit contributions
P+0.015
rob+0.013
robat+0.013
 seeker+0.013
 best+0.012
Neg logit contributions
ramids-0.022
plets-0.021
inated-0.020
 runway-0.020
ifying-0.020
Token felt
Token ID2936
Feature activation+6.32e-03

Pos logit contributions
P+0.017
 best+0.015
my+0.015
joy+0.014
rob+0.014
Neg logit contributions
plets-0.025
ramids-0.024
 runway-0.024
ifying-0.024
umes-0.023
Token bad
Token ID2089
Feature activation+9.90e-03

Pos logit contributions
ramids+0.013
 runway+0.013
plets+0.012
umes+0.012
mic+0.011
Neg logit contributions
P-0.008
 best-0.007
 moderation-0.007
joy-0.007
 right-0.006
Token and
Token ID290
Feature activation-1.79e-02

Pos logit contributions
plets+0.015
 runway+0.014
ured+0.014
ramids+0.014
uring+0.014
Neg logit contributions
P-0.017
 moderation-0.014
rob-0.014
robat-0.014
 seeker-0.013
Token he
Token ID339
Feature activation-2.87e-02

Pos logit contributions
P+0.023
 best+0.021
my+0.019
Deal+0.019
joy+0.019
Neg logit contributions
plets-0.035
ramids-0.034
 runway-0.034
ifying-0.034
umes-0.033
Token apologised
Token ID46397
Feature activation+4.05e-03

Pos logit contributions
P+0.038
 best+0.034
my+0.032
Deal+0.031
 che+0.030
Neg logit contributions
plets-0.057
ramids-0.056
 runway-0.056
ifying-0.055
umes-0.053
Token to
Token ID284
Feature activation-2.71e-03

Pos logit contributions
ramids+0.006
plets+0.006
ured+0.006
 runway+0.006
ifying+0.006
Neg logit contributions
P-0.007
rob-0.006
robat-0.006
 seeker-0.006
 moderation-0.006
Token Sam
Token ID3409
Feature activation-5.20e-03

Pos logit contributions
P+0.004
rob+0.003
robat+0.003
 seeker+0.003
Deal+0.003
Neg logit contributions
ramids-0.005
 runway-0.005
plets-0.005
uring-0.004
ured-0.004
Token for
Token ID329
Feature activation-1.37e-02

Pos logit contributions
P+0.009
rob+0.008
robat+0.007
 seeker+0.007
joy+0.007
Neg logit contributions
ramids-0.008
 runway-0.008
umes-0.008
ured-0.008
plets-0.008
Token of
Token ID286
Feature activation+2.76e-02

Pos logit contributions
P+0.000
joy+0.000
rob+0.000
robat+0.000
 best+0.000
Neg logit contributions
plets-0.000
 runway-0.000
ramids-0.000
ifying-0.000
umes-0.000
Token tag
Token ID7621
Feature activation+4.47e-03

Pos logit contributions
 runway+0.043
uring+0.041
plets+0.041
mic+0.041
ramids+0.040
Neg logit contributions
P-0.042
joy-0.037
 moderation-0.036
rob-0.036
orn-0.035
Token.
Token ID13
Feature activation+5.52e-03

Pos logit contributions
plets+0.009
ramids+0.009
 runway+0.008
ifying+0.008
umes+0.008
Neg logit contributions
P-0.005
 best-0.005
rob-0.005
robat-0.005
 seeker-0.004
Token Lily
Token ID20037
Feature activation+8.61e-03

Pos logit contributions
plets+0.012
keys+0.012
 runway+0.012
ifying+0.011
ramids+0.011
Neg logit contributions
P-0.006
my-0.005
 best-0.005
joy-0.004
ossible-0.004
Token was
Token ID373
Feature activation+2.90e-04

Pos logit contributions
plets+0.014
 runway+0.014
ramids+0.014
umes+0.013
ifying+0.013
Neg logit contributions
P-0.013
joy-0.011
rob-0.011
 best-0.011
robat-0.011
Token scared
Token ID12008
Feature activation-3.39e-03

Pos logit contributions
plets+0.001
ifying+0.000
ramids+0.000
 runway+0.000
lights+0.000
Neg logit contributions
 best-0.000
P-0.000
 seeker-0.000
joy-0.000
my-0.000
Token to
Token ID284
Feature activation-2.35e-02

Pos logit contributions
P+0.005
rob+0.005
robat+0.005
joy+0.005
 best+0.004
Neg logit contributions
plets-0.005
 runway-0.005
ramids-0.005
ifying-0.005
umes-0.005
Token be
Token ID307
Feature activation-2.28e-02

Pos logit contributions
P+0.037
 best+0.033
joy+0.032
rob+0.032
robat+0.032
Neg logit contributions
plets-0.037
 runway-0.036
ramids-0.036
ifying-0.035
umes-0.034
Token "
Token ID366
Feature activation-6.41e-03

Pos logit contributions
P+0.034
rob+0.030
robat+0.029
joy+0.029
 best+0.029
Neg logit contributions
plets-0.038
 runway-0.037
ramids-0.037
ifying-0.036
umes-0.035
Tokenit
Token ID270
Feature activation-1.11e-02

Pos logit contributions
P+0.010
joy+0.009
rob+0.009
 best+0.009
robat+0.008
Neg logit contributions
plets-0.010
 runway-0.010
ramids-0.010
ifying-0.010
umes-0.009
Token"
Token ID1
Feature activation-1.15e-02

Pos logit contributions
P+0.015
 best+0.014
my+0.013
 seeker+0.013
robat+0.012
Neg logit contributions
 runway-0.020
plets-0.020
ramids-0.019
lights-0.019
umes-0.018
Token
Token ID198
Feature activation+7.46e-03

Pos logit contributions
P+0.028
rob+0.024
robat+0.024
 best+0.023
 seeker+0.023
Neg logit contributions
plets-0.044
ramids-0.044
 runway-0.043
ifying-0.042
umes-0.042
Token
Token ID198
Feature activation+5.84e-03

Pos logit contributions
plets+0.016
 runway+0.016
ramids+0.016
ifying+0.016
umes+0.015
Neg logit contributions
P-0.008
 best-0.006
joy-0.006
rob-0.006
robat-0.006
TokenMom
Token ID29252
Feature activation-8.06e-03

Pos logit contributions
plets+0.009
ramids+0.009
ifying+0.009
 runway+0.009
umes+0.009
Neg logit contributions
P-0.010
 best-0.008
my-0.008
 moderation-0.008
robat-0.008
Token hugged
Token ID41130
Feature activation+1.78e-02

Pos logit contributions
P+0.012
 moderation+0.011
 seeker+0.011
 best+0.011
joy+0.011
Neg logit contributions
plets-0.013
ramids-0.013
 runway-0.013
umes-0.012
ifying-0.012
Token her
Token ID607
Feature activation+2.34e-02

Pos logit contributions
ramids+0.024
plets+0.023
 runway+0.023
ifying+0.022
umes+0.022
Neg logit contributions
P-0.032
robat-0.029
rob-0.029
 best-0.028
joy-0.028
Token and
Token ID290
Feature activation-6.54e-03

Pos logit contributions
ramids+0.039
plets+0.039
 runway+0.039
ifying+0.038
umes+0.038
Neg logit contributions
P-0.035
rob-0.030
robat-0.029
 moderation-0.028
joy-0.028
Token said
Token ID531
Feature activation+1.03e-02

Pos logit contributions
P+0.008
robat+0.007
joy+0.007
 best+0.007
 seeker+0.007
Neg logit contributions
plets-0.012
ramids-0.012
 runway-0.012
umes-0.012
ifying-0.012
Token,
Token ID11
Feature activation+1.13e-02

Pos logit contributions
plets+0.019
ramids+0.019
 runway+0.018
umes+0.018
ured+0.018
Neg logit contributions
P-0.013
robat-0.011
rob-0.011
 moderation-0.011
 seeker-0.011
Token "
Token ID366
Feature activation+1.86e-02

Pos logit contributions
plets+0.018
 runway+0.018
ifying+0.017
ramids+0.017
umes+0.017
Neg logit contributions
P-0.017
 best-0.016
joy-0.016
rob-0.015
robat-0.015
TokenOkay
Token ID16454
Feature activation-1.10e-02

Pos logit contributions
plets+0.028
 runway+0.026
ramids+0.026
ifying+0.024
umes+0.024
Neg logit contributions
 seeker-0.028
 best-0.027
P-0.027
joy-0.027
 idea-0.027
Token,
Token ID11
Feature activation+1.70e-02

Pos logit contributions
P+0.012
 best+0.010
rob+0.010
joy+0.010
robat+0.010
Neg logit contributions
plets-0.023
 runway-0.022
ramids-0.022
ifying-0.022
umes-0.021
Token many
Token ID867
Feature activation-1.10e-02

Pos logit contributions
plets+0.022
ramids+0.021
 runway+0.020
umes+0.020
ifying+0.020
Neg logit contributions
P-0.013
 best-0.012
 seeker-0.010
joy-0.010
 moderation-0.010
Token toys
Token ID14958
Feature activation-1.98e-03

Pos logit contributions
P+0.017
robat+0.015
rob+0.015
 seeker+0.015
joy+0.015
Neg logit contributions
 runway-0.017
lights-0.016
ramids-0.016
ifying-0.015
plets-0.015
Token,
Token ID11
Feature activation+8.95e-03

Pos logit contributions
P+0.002
 best+0.002
rob+0.002
joy+0.002
robat+0.002
Neg logit contributions
plets-0.004
ramids-0.004
 runway-0.004
ifying-0.004
umes-0.004
Token but
Token ID475
Feature activation-7.92e-03

Pos logit contributions
plets+0.018
 runway+0.018
ramids+0.018
ifying+0.017
umes+0.017
Neg logit contributions
P-0.011
joy-0.009
rob-0.009
robat-0.009
 best-0.008
Token their
Token ID511
Feature activation-4.65e-03

Pos logit contributions
P+0.015
 best+0.014
 seeker+0.013
joy+0.013
 moderation+0.013
Neg logit contributions
plets-0.011
 runway-0.010
ramids-0.010
ifying-0.009
umes-0.009
Token favorite
Token ID4004
Feature activation-5.78e-02

Pos logit contributions
P+0.006
rob+0.005
robat+0.005
joy+0.005
 best+0.005
Neg logit contributions
 runway-0.008
ramids-0.008
plets-0.008
ifying-0.008
umes-0.008
Token was
Token ID373
Feature activation-1.03e-02

Pos logit contributions
P+0.082
joy+0.069
rob+0.068
robat+0.067
 best+0.066
Neg logit contributions
 runway-0.100
ramids-0.100
plets-0.099
ifying-0.096
umes-0.094
Token a
Token ID257
Feature activation-7.31e-03

Pos logit contributions
P+0.014
 best+0.013
my+0.012
joy+0.012
 seeker+0.012
Neg logit contributions
plets-0.019
 runway-0.018
ramids-0.018
ifying-0.018
ured-0.017
Token big
Token ID1263
Feature activation+7.27e-03

Pos logit contributions
P+0.010
rob+0.009
robat+0.009
joy+0.008
 moderation+0.008
Neg logit contributions
 runway-0.013
ramids-0.013
plets-0.013
ifying-0.012
umes-0.012
Token,
Token ID11
Feature activation+1.23e-02

Pos logit contributions
 runway+0.013
ramids+0.011
ifying+0.010
 cum+0.010
plets+0.010
Neg logit contributions
P-0.012
rob-0.010
robat-0.009
Deal-0.009
ability-0.009
Token soft
Token ID2705
Feature activation+6.97e-03

Pos logit contributions
 runway+0.021
plets+0.021
ramids+0.021
ifying+0.021
umes+0.020
Neg logit contributions
P-0.017
rob-0.015
robat-0.015
joy-0.015
 seeker-0.014
Token make
Token ID787
Feature activation-3.75e-03

Pos logit contributions
P+0.031
rob+0.028
joy+0.028
 best+0.028
robat+0.028
Neg logit contributions
plets-0.020
 runway-0.020
ramids-0.019
ifying-0.019
umes-0.018
Token a
Token ID257
Feature activation+3.33e-03

Pos logit contributions
P+0.006
 best+0.005
joy+0.005
rob+0.005
robat+0.005
Neg logit contributions
plets-0.006
ramids-0.006
 runway-0.006
ifying-0.006
umes-0.006
Token difference
Token ID3580
Feature activation-2.24e-02

Pos logit contributions
plets+0.006
ramids+0.006
 runway+0.006
ifying+0.006
umes+0.006
Neg logit contributions
P-0.005
 best-0.004
joy-0.004
robat-0.004
 seeker-0.004
Token.
Token ID13
Feature activation-8.02e-03

Pos logit contributions
P+0.034
rob+0.030
joy+0.029
robat+0.029
 best+0.029
Neg logit contributions
plets-0.036
 runway-0.036
ramids-0.035
ifying-0.035
umes-0.034
Token<|endoftext|>
Token ID50256
Feature activation-1.36e-03

Pos logit contributions
P+0.011
rob+0.010
robat+0.010
 best+0.009
 seeker+0.009
Neg logit contributions
plets-0.014
ramids-0.014
ifying-0.014
 runway-0.014
umes-0.013
TokenOne
Token ID3198
Feature activation-5.52e-02

Pos logit contributions
P+0.002
Deal+0.002
 moderation+0.002
 seeker+0.002
robat+0.002
Neg logit contributions
plets-0.002
ifying-0.002
ramids-0.002
 runway-0.002
umes-0.002
Token day
Token ID1110
Feature activation+1.74e-03

Pos logit contributions
P+0.048
rob+0.039
robat+0.037
joy+0.036
 seeker+0.035
Neg logit contributions
plets-0.124
 runway-0.123
ramids-0.122
ifying-0.121
umes-0.118
Token,
Token ID11
Feature activation+2.65e-03

Pos logit contributions
 runway+0.004
plets+0.004
ramids+0.004
ifying+0.004
umes+0.004
Neg logit contributions
P-0.002
 best-0.001
joy-0.001
 seeker-0.001
rob-0.001
Token Jack
Token ID3619
Feature activation-8.64e-03

Pos logit contributions
 runway+0.005
plets+0.005
ramids+0.005
umes+0.005
mic+0.005
Neg logit contributions
P-0.003
 best-0.003
joy-0.003
 seeker-0.003
my-0.003
Token was
Token ID373
Feature activation+1.24e-02

Pos logit contributions
P+0.012
 best+0.010
joy+0.010
rob+0.010
robat+0.010
Neg logit contributions
plets-0.015
 runway-0.015
ramids-0.015
ifying-0.014
umes-0.014
Token in
Token ID287
Feature activation+7.10e-03

Pos logit contributions
 runway+0.017
plets+0.016
uring+0.016
ifying+0.016
umes+0.016
Neg logit contributions
robat-0.020
rob-0.020
P-0.020
Deal-0.019
orn-0.018
Token The
Token ID383
Feature activation-9.53e-03

Pos logit contributions
P+0.004
rob+0.003
 best+0.003
robat+0.003
joy+0.003
Neg logit contributions
plets-0.009
ramids-0.009
 runway-0.009
ifying-0.009
umes-0.008
Token refrigerator
Token ID30500
Feature activation+1.10e-02

Pos logit contributions
P+0.014
rob+0.012
robat+0.012
 best+0.012
joy+0.012
Neg logit contributions
plets-0.016
 runway-0.016
ramids-0.016
ifying-0.015
umes-0.015
Token was
Token ID373
Feature activation-8.07e-03

Pos logit contributions
plets+0.017
ramids+0.017
 runway+0.017
ifying+0.016
umes+0.016
Neg logit contributions
P-0.017
 best-0.015
joy-0.015
rob-0.015
robat-0.015
Token his
Token ID465
Feature activation-1.16e-02

Pos logit contributions
 best+0.011
P+0.010
joy+0.010
my+0.009
 seeker+0.009
Neg logit contributions
plets-0.015
ramids-0.014
 runway-0.014
umes-0.014
ifying-0.013
Token new
Token ID649
Feature activation-1.69e-02

Pos logit contributions
P+0.015
rob+0.013
robat+0.013
joy+0.013
 best+0.012
Neg logit contributions
plets-0.021
 runway-0.021
ramids-0.021
ifying-0.021
umes-0.020
Token favorite
Token ID4004
Feature activation-5.57e-02

Pos logit contributions
P+0.024
rob+0.022
robat+0.020
Deal+0.018
 moderation+0.017
Neg logit contributions
 runway-0.030
ramids-0.029
ifying-0.028
inated-0.028
plets-0.028
Token thing
Token ID1517
Feature activation-2.30e-02

Pos logit contributions
P+0.071
rob+0.059
joy+0.057
robat+0.057
 best+0.057
Neg logit contributions
plets-0.104
 runway-0.104
ramids-0.103
ifying-0.101
umes-0.099
Token.
Token ID13
Feature activation-6.74e-03

Pos logit contributions
P+0.033
 best+0.029
joy+0.028
rob+0.028
robat+0.028
Neg logit contributions
plets-0.040
 runway-0.039
ramids-0.039
ifying-0.037
umes-0.037
Token He
Token ID679
Feature activation-1.33e-02

Pos logit contributions
P+0.009
rob+0.007
 best+0.007
robat+0.007
joy+0.007
Neg logit contributions
plets-0.013
ramids-0.012
 runway-0.012
ifying-0.012
umes-0.012
Token was
Token ID373
Feature activation-2.24e-03

Pos logit contributions
P+0.019
 best+0.017
my+0.016
joy+0.016
 vest+0.015
Neg logit contributions
plets-0.024
ramids-0.023
ifying-0.023
 runway-0.023
umes-0.022
Token so
Token ID523
Feature activation+2.80e-04

Pos logit contributions
 best+0.003
joy+0.003
P+0.003
my+0.003
 seeker+0.003
Neg logit contributions
plets-0.004
ramids-0.004
 runway-0.004
ifying-0.004
keys-0.004
Token over
Token ID625
Feature activation+2.38e-02

Pos logit contributions
plets+0.001
ramids+0.001
 runway+0.001
ifying+0.001
umes+0.001
Neg logit contributions
P-0.002
rob-0.002
 best-0.002
robat-0.002
joy-0.002
Token to
Token ID284
Feature activation-7.64e-04

Pos logit contributions
ifying+0.023
ramids+0.023
 runway+0.022
 as+0.022
shaped+0.021
Neg logit contributions
P-0.049
rob-0.047
robat-0.046
 seeker-0.044
Deal-0.044
Token it
Token ID340
Feature activation+2.16e-04

Pos logit contributions
P+0.002
rob+0.001
robat+0.001
ests+0.001
 best+0.001
Neg logit contributions
ured-0.001
ramids-0.001
 runway-0.001
uring-0.001
ifying-0.001
Token and
Token ID290
Feature activation-1.24e-02

Pos logit contributions
plets+0.000
 runway+0.000
ramids+0.000
ifying+0.000
umes+0.000
Neg logit contributions
P-0.000
rob-0.000
robat-0.000
 seeker-0.000
joy-0.000
Token with
Token ID351
Feature activation-3.08e-03

Pos logit contributions
P+0.019
 best+0.016
joy+0.016
rob+0.015
my+0.015
Neg logit contributions
plets-0.021
 runway-0.021
ramids-0.020
ifying-0.020
umes-0.019
Token one
Token ID530
Feature activation-7.15e-02

Pos logit contributions
P+0.005
rob+0.005
robat+0.005
Deal+0.005
 seeker+0.005
Neg logit contributions
ifying-0.004
plets-0.004
 runway-0.004
ramids-0.004
ured-0.004
Token bite
Token ID13197
Feature activation-4.31e-02

Pos logit contributions
P+0.127
rob+0.127
robat+0.113
 seeker+0.110
ests+0.101
Neg logit contributions
ifying-0.106
plets-0.096
ured-0.090
 as-0.090
inated-0.090
Token,
Token ID11
Feature activation-1.48e-02

Pos logit contributions
P+0.058
rob+0.051
robat+0.049
 seeker+0.049
joy+0.048
Neg logit contributions
plets-0.078
ramids-0.076
ifying-0.075
 runway-0.074
umes-0.073
Token he
Token ID339
Feature activation-2.63e-02

Pos logit contributions
P+0.020
rob+0.017
robat+0.017
 best+0.016
 seeker+0.016
Neg logit contributions
plets-0.027
ramids-0.027
 runway-0.027
ifying-0.026
umes-0.026
Token slur
Token ID40066
Feature activation-1.16e-02

Pos logit contributions
P+0.042
 best+0.037
joy+0.036
rob+0.035
robat+0.035
Neg logit contributions
plets-0.041
 runway-0.041
ramids-0.041
ifying-0.039
umes-0.038
Tokenped
Token ID9124
Feature activation-5.02e-03

Pos logit contributions
P+0.024
 best+0.022
rob+0.022
robat+0.022
joy+0.022
Neg logit contributions
 runway-0.012
plets-0.012
ramids-0.012
ifying-0.011
umes-0.011
Token.
Token ID13
Feature activation-5.30e-03

Pos logit contributions
plets+0.022
 runway+0.022
ramids+0.022
ifying+0.021
umes+0.021
Neg logit contributions
P-0.019
rob-0.016
joy-0.016
robat-0.016
 best-0.016
Token The
Token ID383
Feature activation-9.55e-03

Pos logit contributions
P+0.010
rob+0.009
 best+0.009
robat+0.009
joy+0.009
Neg logit contributions
plets-0.007
ramids-0.007
 runway-0.007
ifying-0.007
umes-0.006
Token tray
Token ID26473
Feature activation+1.14e-02

Pos logit contributions
P+0.013
 best+0.011
robat+0.011
 seeker+0.011
joy+0.011
Neg logit contributions
plets-0.017
ramids-0.017
 runway-0.017
ifying-0.016
umes-0.016
Token broke
Token ID6265
Feature activation-1.27e-02

Pos logit contributions
ramids+0.018
plets+0.018
 runway+0.018
umes+0.017
ifying+0.017
Neg logit contributions
P-0.018
 best-0.016
robat-0.015
 seeker-0.015
rob-0.015
Token in
Token ID287
Feature activation-3.25e-02

Pos logit contributions
P+0.015
 best+0.013
joy+0.013
my+0.012
 seeker+0.012
Neg logit contributions
 runway-0.025
plets-0.024
ramids-0.024
mic-0.024
umes-0.024
Token half
Token ID2063
Feature activation-5.65e-02

Pos logit contributions
P+0.038
rob+0.032
robat+0.032
 best+0.032
joy+0.031
Neg logit contributions
ramids-0.064
plets-0.064
 runway-0.063
ifying-0.062
umes-0.060
Token and
Token ID290
Feature activation+5.96e-04

Pos logit contributions
P+0.075
rob+0.064
 best+0.063
joy+0.063
robat+0.063
Neg logit contributions
plets-0.103
 runway-0.101
ramids-0.101
ifying-0.099
umes-0.097
Token the
Token ID262
Feature activation-1.00e-02

Pos logit contributions
ramids+0.001
plets+0.001
 runway+0.001
mic+0.001
umes+0.001
Neg logit contributions
P-0.001
 best-0.001
 seeker-0.001
joy-0.001
my-0.001
Token shapes
Token ID15268
Feature activation+3.50e-03

Pos logit contributions
P+0.014
 best+0.012
joy+0.012
rob+0.012
robat+0.012
Neg logit contributions
plets-0.018
ramids-0.018
 runway-0.018
ifying-0.017
umes-0.017
Token and
Token ID290
Feature activation+1.82e-02

Pos logit contributions
ramids+0.007
umes+0.006
 runway+0.006
plets+0.006
ulus+0.006
Neg logit contributions
P-0.004
 best-0.004
 idea-0.003
m-0.003
joy-0.003
Token colors
Token ID7577
Feature activation+1.68e-02

Pos logit contributions
plets+0.031
ramids+0.031
umes+0.030
mic+0.030
 runway+0.030
Neg logit contributions
P-0.025
 best-0.024
my-0.022
joy-0.022
 moderation-0.021