TOP ACTIVATIONS
MAX = 3.920

and looked at the ost ric hes . They saw one
too close . The ost ric hes might pe ck you
and run to the ost ric hes . "
cried . " The ost ric hes are mean ! They
They do not pack ost ric hes anymore . They pack
should not tease the ost ric hes . They are not
ie . Unlike other ost ric hes , his feathers gl
but be careful . Ost ric hes can be gr umpy
wanted to touch the ost ric hes . They reached out
mom and to the ost ric hes . They learned their
. They were called ost ric hes . Lily and Ben
you count how many ost ric hes there are ?"
girl who didn 't like av oc ados . She always
ostr ich pen . Ost ric hes are big birds with
was very naughty and always mis beh aving . One day
ostr ich pen . Ost ric hes are big birds with
shouted . " The ost ric hes are so funny !"
Yes , they are ost ric hes ," mom said .
he could be and never mis beh aved . <|endoftext|> Once
did not know what ost ric hes were . They looked

MIN ACTIVATIONS
MIN = -3.195

help me ?" T oby was excited to serve
okay ." T oby thanked them , said
lightning ! T ina loved Lightning and she
noticed before . T ina wanted to explore the
want to play with our toy rockets . We like our
helping the other creatures . L ola and Lex had learned
learn today ?" T ina smiled proudly and said
thought it should work . D ina was so happy ,
her ! V iv ian enjoyed playing with
god mother flew away . D olly was so happy that
record her voice with her toy phone . She would say
rag toy was free ! D olly was so excited and
it . I like your toy microphone too . It is
sorry , Lilly ," said D alia , " but I
deer named D olly . D olly saw that Benny was
good at fixing things . D olly told Crab by about
river . T oby and the duck soon
by himself ." T ami smiled and said ,
thin . T oby was very curious and
â € T oby and M illy divided

INTERVAL 2.141 - 3.920
CONTAINS 0.014%

, raised his arm and SH OT !
any bad dreams or scary gor illas . <|endoftext|> Once upon
tall and bright , it lit up the sky .
wished they had never qu arre led . They missed their
w , ow , ow ! That goose is mean and

INTERVAL 0.362 - 2.141
CONTAINS 23.090%

The lawyer was surprised . She asked the man
they were lucky to have each other , and that they
One day , Tim my and Max were playing in
world We love you , we love you , we
Tom was a cricket who liked to drink juice . He

INTERVAL -1.417 - 0.362
CONTAINS 76.289%

pushing Sammy in the st roller , and they were having
with beautiful colors and patterns . Everyone loved it !
was so excited to see it , and wanted to know
ting in the other direction . The farmer shook
it disgusting !" Lily said , sob bing .

INTERVAL -3.195 - -1.417
CONTAINS 0.607%

like you !" B ub bles replied , "
help Tommy . L ily 's mom my was
toy . " Ro ar !" Tom said ,
big . L ily said , " Wow
would be very expensive . Su zy felt a bit sad
Token and
Token ID290
Feature activation+5.67e-01

Pos logit contributions
orry+0.040
oke+0.039
aint+0.039
ence+0.037
isel+0.037
Neg logit contributions
 Woo-0.026
rob-0.026
amb-0.021
bur-0.020
 from-0.020
Token looked
Token ID3114
Feature activation+3.35e-01

Pos logit contributions
orry+0.018
oke+0.017
run+0.017
ence+0.017
aint+0.016
Neg logit contributions
rob-0.022
 Woo-0.019
amb-0.016
 Pink-0.015
bur-0.015
Token at
Token ID379
Feature activation+6.10e-01

Pos logit contributions
orry+0.010
oke+0.010
run+0.010
aint+0.010
ence+0.009
Neg logit contributions
rob-0.012
 Woo-0.011
amb-0.009
 Pink-0.009
 Cindy-0.009
Token the
Token ID262
Feature activation+1.27e-01

Pos logit contributions
orry+0.015
run+0.015
oke+0.014
ence+0.014
aint+0.013
Neg logit contributions
rob-0.028
 Woo-0.024
amb-0.021
bur-0.020
thank-0.020
Token ost
Token ID23619
Feature activation+9.08e-01

Pos logit contributions
run+0.004
orry+0.004
oke+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.005
 Woo-0.004
amb-0.003
bur-0.003
 Pink-0.003
Tokenric
Token ID1173
Feature activation+3.92e+00

Pos logit contributions
run+0.022
orry+0.022
 tug+0.021
oke+0.021
 gust+0.021
Neg logit contributions
rob-0.041
 Woo-0.033
bur-0.032
amb-0.032
igi-0.029
Tokenhes
Token ID956
Feature activation+1.22e+00

Pos logit contributions
run+0.156
aint+0.152
ence+0.150
 tug+0.150
ever+0.148
Neg logit contributions
rob-0.116
 Woo-0.081
amb-0.067
bur-0.064
oto-0.061
Token.
Token ID13
Feature activation-5.59e-01

Pos logit contributions
orry+0.042
oke+0.040
run+0.040
ence+0.040
aint+0.038
Neg logit contributions
rob-0.042
 Woo-0.037
amb-0.030
 Pink-0.029
bur-0.028
Token They
Token ID1119
Feature activation-7.49e-01

Pos logit contributions
 Woo+0.017
rob+0.015
 Pink+0.014
 Sebastian+0.013
 Cindy+0.012
Neg logit contributions
orry-0.021
run-0.020
oke-0.020
ence-0.019
ever-0.019
Token saw
Token ID2497
Feature activation+2.26e-01

Pos logit contributions
rob+0.034
 Woo+0.029
amb+0.026
bur+0.024
 Pink+0.024
Neg logit contributions
orry-0.019
oke-0.019
run-0.018
ence-0.018
aint-0.017
Token one
Token ID530
Feature activation-2.01e-01

Pos logit contributions
orry+0.007
oke+0.007
run+0.007
ence+0.007
aint+0.007
Neg logit contributions
rob-0.009
 Woo-0.007
amb-0.006
bur-0.006
thank-0.006
Token too
Token ID1165
Feature activation-2.69e-01

Pos logit contributions
run+0.011
orry+0.011
oke+0.011
ence+0.010
aint+0.010
Neg logit contributions
rob-0.017
 Woo-0.014
amb-0.012
 Pink-0.011
thank-0.011
Token close
Token ID1969
Feature activation+8.87e-01

Pos logit contributions
rob+0.013
 Woo+0.010
amb+0.009
 Pink+0.009
thank+0.009
Neg logit contributions
orry-0.007
run-0.007
oke-0.006
ence-0.006
 tower-0.006
Token.
Token ID13
Feature activation+3.01e-01

Pos logit contributions
run+0.023
orry+0.023
oke+0.023
ence+0.022
aint+0.021
Neg logit contributions
rob-0.040
 Woo-0.033
amb-0.029
 Pink-0.028
thank-0.027
Token The
Token ID383
Feature activation+1.78e-01

Pos logit contributions
orry+0.008
ence+0.007
run+0.007
 tower+0.007
 gust+0.007
Neg logit contributions
 Woo-0.012
rob-0.012
 Pink-0.011
amb-0.011
 Sim-0.010
Token ost
Token ID23619
Feature activation+9.82e-01

Pos logit contributions
run+0.006
orry+0.006
oke+0.006
ence+0.006
aint+0.006
Neg logit contributions
rob-0.006
 Woo-0.006
 Pink-0.004
bur-0.004
amb-0.004
Tokenric
Token ID1173
Feature activation+3.86e+00

Pos logit contributions
run+0.024
 tug+0.024
orry+0.024
 gust+0.023
oke+0.022
Neg logit contributions
rob-0.043
 Woo-0.035
bur-0.034
amb-0.033
igi-0.030
Tokenhes
Token ID956
Feature activation+6.38e-01

Pos logit contributions
run+0.154
 tug+0.154
aint+0.153
ence+0.151
 gust+0.150
Neg logit contributions
rob-0.110
 Woo-0.073
amb-0.060
bur-0.059
oto-0.054
Token might
Token ID1244
Feature activation-2.96e-01

Pos logit contributions
orry+0.019
run+0.019
oke+0.019
ence+0.018
aint+0.018
Neg logit contributions
rob-0.025
 Woo-0.022
amb-0.018
 Pink-0.017
bur-0.017
Token pe
Token ID613
Feature activation+2.11e+00

Pos logit contributions
rob+0.016
 Woo+0.013
amb+0.012
 Sebastian+0.011
rev+0.011
Neg logit contributions
run-0.006
orry-0.006
ence-0.005
oke-0.005
aint-0.005
Tokenck
Token ID694
Feature activation+5.55e-01

Pos logit contributions
orry+0.063
oke+0.061
run+0.061
aint+0.058
 gust+0.058
Neg logit contributions
rob-0.083
 Woo-0.067
amb-0.060
bur-0.060
igi-0.055
Token you
Token ID345
Feature activation+6.30e-01

Pos logit contributions
orry+0.019
oke+0.019
run+0.018
ence+0.018
aint+0.018
Neg logit contributions
rob-0.020
 Woo-0.017
amb-0.014
 Pink-0.013
bur-0.013
Token and
Token ID290
Feature activation+5.68e-01

Pos logit contributions
orry+0.012
oke+0.012
run+0.012
ence+0.011
aint+0.011
Neg logit contributions
rob-0.007
 Woo-0.006
amb-0.005
 Pink-0.004
bur-0.004
Token run
Token ID1057
Feature activation-4.82e-01

Pos logit contributions
oke+0.020
orry+0.019
run+0.019
ever+0.018
ence+0.017
Neg logit contributions
rob-0.020
 Woo-0.017
 Pink-0.015
bur-0.014
amb-0.014
Token to
Token ID284
Feature activation-3.04e-01

Pos logit contributions
rob+0.021
 Woo+0.018
amb+0.016
bur+0.015
 Pink+0.015
Neg logit contributions
orry-0.013
run-0.012
oke-0.012
ence-0.012
aint-0.011
Token the
Token ID262
Feature activation+2.03e-01

Pos logit contributions
rob+0.011
 Woo+0.010
 Pink+0.008
bur+0.008
amb+0.008
Neg logit contributions
oke-0.010
orry-0.010
run-0.010
ence-0.010
aint-0.010
Token ost
Token ID23619
Feature activation+1.02e+00

Pos logit contributions
run+0.007
oke+0.007
orry+0.007
isel+0.007
aint+0.006
Neg logit contributions
rob-0.008
 Woo-0.007
 Pink-0.005
bur-0.005
 Snow-0.005
Tokenric
Token ID1173
Feature activation+3.84e+00

Pos logit contributions
run+0.024
orry+0.024
oke+0.023
 tug+0.023
 gust+0.022
Neg logit contributions
rob-0.046
 Woo-0.038
bur-0.036
amb-0.036
igi-0.033
Tokenhes
Token ID956
Feature activation+1.42e+00

Pos logit contributions
run+0.149
aint+0.146
ence+0.144
 tug+0.144
orry+0.143
Neg logit contributions
rob-0.118
 Woo-0.085
amb-0.071
bur-0.067
oto-0.064
Token.
Token ID13
Feature activation+3.50e-02

Pos logit contributions
orry+0.048
oke+0.047
run+0.046
ence+0.045
aint+0.044
Neg logit contributions
rob-0.050
 Woo-0.044
amb-0.036
 Pink-0.035
bur-0.034
Token
Token ID198
Feature activation+1.21e-01

Pos logit contributions
orry+0.001
ence+0.001
oke+0.001
run+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
 Pink-0.001
amb-0.001
 Sebastian-0.001
Token
Token ID198
Feature activation+3.34e-01

Pos logit contributions
orry+0.004
oke+0.003
run+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.005
 Woo-0.004
amb-0.004
bur-0.003
burn-0.003
Token"
Token ID1
Feature activation+1.07e-01

Pos logit contributions
orry+0.010
run+0.010
oke+0.010
ence+0.009
aint+0.009
Neg logit contributions
rob-0.014
 Woo-0.012
amb-0.010
 Pink-0.009
bur-0.009
Token cried
Token ID16896
Feature activation-6.73e-02

Pos logit contributions
orry+0.017
run+0.017
oke+0.017
ence+0.017
aint+0.016
Neg logit contributions
rob-0.016
 Woo-0.014
amb-0.012
 Pink-0.011
bur-0.011
Token.
Token ID13
Feature activation+1.08e-01

Pos logit contributions
rob+0.003
 Woo+0.002
amb+0.002
 Pink+0.002
bur+0.002
Neg logit contributions
orry-0.002
run-0.002
oke-0.002
ence-0.002
aint-0.002
Token "
Token ID366
Feature activation-2.35e-03

Pos logit contributions
orry+0.003
run+0.003
oke+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.005
 Woo-0.004
amb-0.003
 Pink-0.003
bur-0.003
TokenThe
Token ID464
Feature activation-1.61e-01

Pos logit contributions
rob+0.000
 Woo+0.000
amb+0.000
bur+0.000
 Pink+0.000
Neg logit contributions
orry-0.000
run-0.000
oke-0.000
ence-0.000
aint-0.000
Token ost
Token ID23619
Feature activation+1.15e+00

Pos logit contributions
rob+0.007
 Woo+0.006
amb+0.005
 Pink+0.005
bur+0.005
Neg logit contributions
run-0.005
orry-0.005
oke-0.005
ence-0.005
aint-0.004
Tokenric
Token ID1173
Feature activation+3.83e+00

Pos logit contributions
 gust+0.032
 tug+0.032
run+0.031
orry+0.031
aint+0.030
Neg logit contributions
rob-0.048
bur-0.038
 Woo-0.036
amb-0.034
burn-0.033
Tokenhes
Token ID956
Feature activation+7.68e-01

Pos logit contributions
run+0.151
aint+0.151
ence+0.150
orry+0.146
ever+0.144
Neg logit contributions
rob-0.114
 Woo-0.080
amb-0.063
bur-0.060
oto-0.058
Token are
Token ID389
Feature activation+8.34e-02

Pos logit contributions
orry+0.025
run+0.024
ence+0.024
oke+0.024
aint+0.023
Neg logit contributions
rob-0.029
 Woo-0.025
amb-0.020
 Pink-0.019
bur-0.019
Token mean
Token ID1612
Feature activation-1.45e-01

Pos logit contributions
orry+0.003
oke+0.003
ence+0.003
aint+0.002
run+0.002
Neg logit contributions
 Woo-0.003
rob-0.003
 Pink-0.002
bur-0.002
burn-0.002
Token!
Token ID0
Feature activation+1.58e+00

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.003
 Pink+0.003
bur+0.003
Neg logit contributions
orry-0.005
oke-0.005
run-0.005
ence-0.005
aint-0.005
Token They
Token ID1119
Feature activation-5.26e-01

Pos logit contributions
orry+0.041
ence+0.040
run+0.037
aint+0.037
isel+0.036
Neg logit contributions
rob-0.065
 Woo-0.064
amb-0.054
 Pink-0.053
 Sebastian-0.049
Token They
Token ID1119
Feature activation+3.29e-01

Pos logit contributions
orry+0.003
run+0.003
oke+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.005
 Woo-0.004
amb-0.004
 Pink-0.003
bur-0.003
Token do
Token ID466
Feature activation+2.20e-01

Pos logit contributions
orry+0.008
oke+0.008
ence+0.007
run+0.007
aint+0.007
Neg logit contributions
rob-0.015
 Woo-0.013
amb-0.012
bur-0.011
 Pink-0.011
Token not
Token ID407
Feature activation+7.51e-01

Pos logit contributions
run+0.007
orry+0.007
oke+0.007
ence+0.007
aint+0.007
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
bur-0.005
 Pink-0.005
Token pack
Token ID2353
Feature activation+2.88e-01

Pos logit contributions
oke+0.026
run+0.026
orry+0.025
ence+0.025
pieces+0.023
Neg logit contributions
 Woo-0.024
rob-0.024
 Pink-0.019
bur-0.019
thank-0.019
Token ost
Token ID23619
Feature activation+1.01e+00

Pos logit contributions
orry+0.009
run+0.009
oke+0.009
ence+0.008
aint+0.008
Neg logit contributions
rob-0.011
 Woo-0.010
amb-0.008
bur-0.008
 Pink-0.008
Tokenric
Token ID1173
Feature activation+3.74e+00

Pos logit contributions
orry+0.025
oke+0.025
run+0.024
 gust+0.024
 tug+0.023
Neg logit contributions
rob-0.045
 Woo-0.038
bur-0.036
amb-0.035
burn-0.032
Tokenhes
Token ID956
Feature activation+1.24e+00

Pos logit contributions
 tug+0.154
 gust+0.154
aint+0.153
 attempts+0.153
run+0.152
Neg logit contributions
rob-0.104
 Woo-0.070
bur-0.056
amb-0.051
oto-0.050
Token anymore
Token ID7471
Feature activation-8.80e-01

Pos logit contributions
orry+0.040
oke+0.039
run+0.039
ence+0.038
aint+0.037
Neg logit contributions
rob-0.047
 Woo-0.040
amb-0.033
 Pink-0.032
bur-0.032
Token.
Token ID13
Feature activation+2.18e-01

Pos logit contributions
rob+0.027
 Woo+0.023
 Pink+0.018
amb+0.017
bur+0.016
Neg logit contributions
orry-0.034
ence-0.033
oke-0.033
isel-0.033
run-0.032
Token They
Token ID1119
Feature activation+5.36e-01

Pos logit contributions
orry+0.006
run+0.006
oke+0.006
ence+0.006
aint+0.006
Neg logit contributions
rob-0.009
 Woo-0.008
amb-0.007
 Pink-0.006
bur-0.006
Token pack
Token ID2353
Feature activation-1.27e-01

Pos logit contributions
run+0.015
orry+0.015
oke+0.014
ence+0.014
aint+0.013
Neg logit contributions
rob-0.023
 Woo-0.020
amb-0.017
 Pink-0.016
bur-0.016
Token should
Token ID815
Feature activation-1.31e+00

Pos logit contributions
orry+0.010
oke+0.009
run+0.009
ence+0.009
aint+0.009
Neg logit contributions
rob-0.020
 Woo-0.017
amb-0.015
oto-0.014
ippy-0.014
Token not
Token ID407
Feature activation+8.74e-01

Pos logit contributions
rob+0.066
 Woo+0.052
amb+0.048
bur+0.044
thank+0.044
Neg logit contributions
orry-0.029
aint-0.026
ence-0.026
oke-0.026
run-0.026
Token tease
Token ID34691
Feature activation+5.36e-01

Pos logit contributions
oke+0.026
orry+0.025
run+0.024
ence+0.024
pieces+0.022
Neg logit contributions
rob-0.033
 Woo-0.032
amb-0.027
 Pink-0.026
bur-0.026
Token the
Token ID262
Feature activation-2.56e-01

Pos logit contributions
orry+0.016
run+0.016
oke+0.016
ence+0.015
aint+0.015
Neg logit contributions
rob-0.022
 Woo-0.018
amb-0.016
bur-0.015
 Pink-0.015
Token ost
Token ID23619
Feature activation+8.00e-01

Pos logit contributions
rob+0.009
 Woo+0.007
bur+0.006
amb+0.006
 Pink+0.006
Neg logit contributions
run-0.009
orry-0.009
oke-0.009
ence-0.009
aint-0.009
Tokenric
Token ID1173
Feature activation+3.67e+00

Pos logit contributions
run+0.020
orry+0.019
 tug+0.019
 gust+0.019
isel+0.019
Neg logit contributions
rob-0.035
 Woo-0.029
bur-0.028
amb-0.027
burn-0.025
Tokenhes
Token ID956
Feature activation+1.08e+00

Pos logit contributions
 tug+0.145
run+0.145
aint+0.144
 attempts+0.144
 gust+0.143
Neg logit contributions
rob-0.108
 Woo-0.074
bur-0.059
amb-0.059
oto-0.057
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
orry+0.036
run+0.035
oke+0.035
ence+0.035
aint+0.034
Neg logit contributions
rob-0.038
 Woo-0.034
amb-0.027
 Pink-0.026
bur-0.026
Token They
Token ID1119
Feature activation-9.56e-01

Pos logit contributions
orry+0.009
run+0.008
oke+0.008
ence+0.008
aint+0.008
Neg logit contributions
rob-0.016
 Woo-0.014
amb-0.012
 Pink-0.012
bur-0.012
Token are
Token ID389
Feature activation-1.90e-01

Pos logit contributions
rob+0.039
 Woo+0.034
amb+0.029
 Pink+0.027
bur+0.027
Neg logit contributions
orry-0.028
run-0.027
oke-0.027
ence-0.027
aint-0.026
Token not
Token ID407
Feature activation+2.47e-01

Pos logit contributions
 Woo+0.006
rob+0.006
 Pink+0.005
bur+0.004
 Rudolph+0.004
Neg logit contributions
orry-0.007
oke-0.007
aint-0.006
run-0.006
isel-0.006
Tokenie
Token ID494
Feature activation+4.28e-01

Pos logit contributions
rob+0.021
 Woo+0.017
amb+0.014
bur+0.013
 Pink+0.013
Neg logit contributions
orry-0.021
run-0.021
oke-0.021
ence-0.020
aint-0.020
Token.
Token ID13
Feature activation-2.25e-01

Pos logit contributions
orry+0.014
oke+0.014
run+0.014
ence+0.013
aint+0.013
Neg logit contributions
rob-0.016
 Woo-0.014
amb-0.012
 Pink-0.011
bur-0.011
Token Unlike
Token ID12101
Feature activation+2.80e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
bur+0.006
thank+0.006
Neg logit contributions
run-0.007
orry-0.006
oke-0.006
ence-0.006
aint-0.006
Token other
Token ID584
Feature activation-1.11e+00

Pos logit contributions
orry+0.009
oke+0.008
run+0.008
ence+0.008
aint+0.008
Neg logit contributions
rob-0.011
 Woo-0.009
amb-0.008
thank-0.008
burn-0.008
Token ost
Token ID23619
Feature activation+1.24e+00

Pos logit contributions
rob+0.042
 Woo+0.036
amb+0.030
 Pink+0.028
bur+0.028
Neg logit contributions
orry-0.036
oke-0.035
run-0.035
ence-0.035
aint-0.034
Tokenric
Token ID1173
Feature activation+3.57e+00

Pos logit contributions
run+0.028
orry+0.028
oke+0.027
 tug+0.025
aint+0.025
Neg logit contributions
rob-0.058
 Woo-0.049
bur-0.046
amb-0.045
oto-0.042
Tokenhes
Token ID956
Feature activation+1.18e+00

Pos logit contributions
run+0.135
aint+0.132
 tug+0.131
ence+0.130
oke+0.129
Neg logit contributions
rob-0.112
 Woo-0.082
bur-0.067
amb-0.066
oto-0.062
Token,
Token ID11
Feature activation-7.37e-01

Pos logit contributions
orry+0.037
run+0.036
oke+0.036
ence+0.035
aint+0.034
Neg logit contributions
rob-0.046
 Woo-0.039
amb-0.033
 Pink-0.031
bur-0.031
Token his
Token ID465
Feature activation+4.64e-01

Pos logit contributions
rob+0.026
 Woo+0.023
 Pink+0.019
amb+0.018
 Sim+0.017
Neg logit contributions
orry-0.025
oke-0.025
run-0.025
ence-0.024
aint-0.024
Token feathers
Token ID27400
Feature activation+1.45e-01

Pos logit contributions
oke+0.016
orry+0.016
run+0.016
isel+0.015
ence+0.015
Neg logit contributions
rob-0.015
 Woo-0.013
amb-0.012
bur-0.011
 Pink-0.011
Token gl
Token ID1278
Feature activation+6.81e-01

Pos logit contributions
run+0.004
oke+0.004
orry+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.006
 Woo-0.005
amb-0.004
 Gloria-0.004
 Pink-0.004
Token but
Token ID475
Feature activation+1.02e+00

Pos logit contributions
rob+0.021
 Woo+0.019
amb+0.015
 Pink+0.015
bur+0.015
Neg logit contributions
orry-0.015
ence-0.014
run-0.014
oke-0.014
aint-0.014
Token be
Token ID307
Feature activation+7.31e-01

Pos logit contributions
orry+0.031
oke+0.030
run+0.030
ence+0.029
aint+0.028
Neg logit contributions
rob-0.039
 Woo-0.036
 Pink-0.031
bur-0.030
amb-0.030
Token careful
Token ID8161
Feature activation+4.33e-01

Pos logit contributions
orry+0.015
oke+0.014
run+0.014
ence+0.013
aint+0.013
Neg logit contributions
rob-0.036
 Woo-0.033
bur-0.028
 Pink-0.028
amb-0.028
Token.
Token ID13
Feature activation+3.32e-01

Pos logit contributions
orry+0.015
oke+0.015
run+0.015
ence+0.015
aint+0.014
Neg logit contributions
rob-0.014
 Woo-0.013
amb-0.010
 Pink-0.010
bur-0.010
Token Ost
Token ID38919
Feature activation+9.10e-01

Pos logit contributions
orry+0.008
run+0.008
oke+0.008
ence+0.007
aint+0.007
Neg logit contributions
rob-0.015
 Woo-0.014
amb-0.012
 Pink-0.012
bur-0.011
Tokenric
Token ID1173
Feature activation+3.56e+00

Pos logit contributions
orry+0.014
oke+0.013
ence+0.013
run+0.012
aint+0.011
Neg logit contributions
rob-0.049
 Woo-0.046
amb-0.040
 Pink-0.039
 Cindy-0.039
Tokenhes
Token ID956
Feature activation+1.04e+00

Pos logit contributions
run+0.141
aint+0.137
ence+0.137
 gust+0.136
 tug+0.136
Neg logit contributions
rob-0.107
 Woo-0.073
bur-0.060
amb-0.058
oto-0.056
Token can
Token ID460
Feature activation-4.45e-01

Pos logit contributions
orry+0.033
run+0.032
oke+0.032
ence+0.032
aint+0.030
Neg logit contributions
rob-0.039
 Woo-0.034
amb-0.028
 Pink-0.027
bur-0.027
Token be
Token ID307
Feature activation+1.31e+00

Pos logit contributions
rob+0.022
 Woo+0.018
amb+0.016
rev+0.016
 Natalie+0.015
Neg logit contributions
 tug-0.009
orry-0.009
run-0.009
ence-0.009
aint-0.009
Token gr
Token ID1036
Feature activation+1.39e+00

Pos logit contributions
orry+0.043
oke+0.041
isel+0.040
ence+0.038
 structure+0.038
Neg logit contributions
rob-0.043
 Woo-0.042
 Pink-0.036
bur-0.036
igi-0.033
Tokenumpy
Token ID32152
Feature activation-3.44e-01

Pos logit contributions
orry+0.041
run+0.040
oke+0.039
ence+0.039
aint+0.037
Neg logit contributions
rob-0.057
 Woo-0.049
amb-0.042
bur-0.039
 Pink-0.039
Token wanted
Token ID2227
Feature activation-1.33e-01

Pos logit contributions
rob+0.024
 Woo+0.021
amb+0.018
 Pink+0.017
bur+0.017
Neg logit contributions
orry-0.015
oke-0.014
run-0.014
ence-0.014
aint-0.013
Token to
Token ID284
Feature activation-6.79e-01

Pos logit contributions
rob+0.006
 Woo+0.005
 Pink+0.004
amb+0.004
bur+0.004
Neg logit contributions
orry-0.004
oke-0.004
run-0.004
ence-0.004
aint-0.003
Token touch
Token ID3638
Feature activation-1.82e-01

Pos logit contributions
rob+0.033
 Woo+0.028
amb+0.025
bur+0.024
 Pink+0.023
Neg logit contributions
orry-0.015
run-0.014
ence-0.014
aint-0.014
oke-0.014
Token the
Token ID262
Feature activation-6.08e-02

Pos logit contributions
rob+0.008
 Woo+0.006
amb+0.006
bur+0.005
 Pink+0.005
Neg logit contributions
orry-0.005
run-0.005
oke-0.005
ence-0.005
aint-0.005
Token ost
Token ID23619
Feature activation+5.82e-01

Pos logit contributions
rob+0.002
 Woo+0.002
amb+0.001
bur+0.001
 Pink+0.001
Neg logit contributions
run-0.002
orry-0.002
oke-0.002
ence-0.002
aint-0.002
Tokenric
Token ID1173
Feature activation+3.55e+00

Pos logit contributions
orry+0.013
run+0.013
oke+0.012
aint+0.012
ence+0.012
Neg logit contributions
rob-0.027
 Woo-0.023
amb-0.021
bur-0.021
 Pink-0.020
Tokenhes
Token ID956
Feature activation+1.04e+00

Pos logit contributions
run+0.135
ence+0.133
aint+0.132
orry+0.131
 tug+0.129
Neg logit contributions
rob-0.111
 Woo-0.083
amb-0.069
bur-0.065
oto-0.063
Token.
Token ID13
Feature activation-4.12e-02

Pos logit contributions
orry+0.035
oke+0.034
run+0.034
ence+0.033
aint+0.032
Neg logit contributions
rob-0.038
 Woo-0.033
amb-0.027
 Pink-0.026
bur-0.025
Token They
Token ID1119
Feature activation-4.96e-01

Pos logit contributions
rob+0.001
 Woo+0.001
amb+0.001
 Pink+0.001
 Sebastian+0.001
Neg logit contributions
orry-0.001
oke-0.001
run-0.001
ence-0.001
aint-0.001
Token reached
Token ID4251
Feature activation-1.74e-01

Pos logit contributions
rob+0.022
 Woo+0.019
amb+0.016
 Pink+0.016
bur+0.015
Neg logit contributions
orry-0.013
oke-0.013
run-0.013
ence-0.012
aint-0.012
Token out
Token ID503
Feature activation+3.43e-01

Pos logit contributions
rob+0.005
 Woo+0.004
bur+0.003
 Pink+0.003
amb+0.003
Neg logit contributions
oke-0.007
orry-0.007
run-0.007
ever-0.006
aint-0.006
Token mom
Token ID1995
Feature activation-4.41e-01

Pos logit contributions
rob+0.000
 Woo+0.000
amb+0.000
 Pink+0.000
bur+0.000
Neg logit contributions
orry-0.000
run-0.000
oke-0.000
ence-0.000
aint-0.000
Token and
Token ID290
Feature activation-2.15e-01

Pos logit contributions
rob+0.013
 Woo+0.011
amb+0.009
 Pink+0.009
bur+0.009
Neg logit contributions
orry-0.017
run-0.017
ence-0.017
oke-0.016
aint-0.016
Token to
Token ID284
Feature activation+8.80e-02

Pos logit contributions
rob+0.007
 Woo+0.007
 Pink+0.006
amb+0.006
bur+0.006
Neg logit contributions
orry-0.007
oke-0.007
ence-0.007
run-0.007
aint-0.007
Token the
Token ID262
Feature activation-6.22e-01

Pos logit contributions
oke+0.003
orry+0.003
run+0.003
ence+0.003
aint+0.003
Neg logit contributions
 Woo-0.003
rob-0.003
 Pink-0.002
bur-0.002
 Snow-0.002
Token ost
Token ID23619
Feature activation+5.60e-01

Pos logit contributions
rob+0.022
 Woo+0.018
amb+0.014
bur+0.014
 Pink+0.014
Neg logit contributions
run-0.023
orry-0.022
oke-0.021
ence-0.021
aint-0.021
Tokenric
Token ID1173
Feature activation+3.41e+00

Pos logit contributions
run+0.014
orry+0.013
oke+0.013
 tug+0.013
 gust+0.013
Neg logit contributions
rob-0.025
 Woo-0.021
bur-0.020
amb-0.019
burn-0.018
Tokenhes
Token ID956
Feature activation+1.22e+00

Pos logit contributions
run+0.132
aint+0.132
ence+0.131
orry+0.129
 gust+0.126
Neg logit contributions
rob-0.104
 Woo-0.078
amb-0.062
bur-0.061
oto-0.056
Token.
Token ID13
Feature activation-2.54e-01

Pos logit contributions
orry+0.038
run+0.037
oke+0.037
ence+0.036
aint+0.035
Neg logit contributions
rob-0.047
 Woo-0.041
amb-0.034
 Pink-0.033
bur-0.033
Token They
Token ID1119
Feature activation-1.04e-01

Pos logit contributions
rob+0.011
 Woo+0.010
amb+0.008
bur+0.008
 Pink+0.008
Neg logit contributions
orry-0.007
run-0.007
oke-0.007
ence-0.007
aint-0.006
Token learned
Token ID4499
Feature activation-5.02e-02

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.004
igi+0.003
ippy+0.003
Neg logit contributions
orry-0.002
 tug-0.002
oke-0.002
run-0.002
ence-0.002
Token their
Token ID511
Feature activation+8.27e-01

Pos logit contributions
rob+0.003
 Woo+0.002
amb+0.002
bur+0.002
thank+0.002
Neg logit contributions
run-0.001
orry-0.001
ence-0.001
oke-0.001
 tower-0.001
Token.
Token ID13
Feature activation-5.68e-01

Pos logit contributions
rob+0.014
 Woo+0.012
amb+0.010
 Pink+0.010
bur+0.010
Neg logit contributions
orry-0.010
run-0.010
oke-0.010
ence-0.010
aint-0.009
Token They
Token ID1119
Feature activation-7.71e-01

Pos logit contributions
 Woo+0.020
rob+0.020
 Pink+0.017
 Sebastian+0.015
 Cindy+0.015
Neg logit contributions
orry-0.018
ence-0.017
run-0.017
isel-0.017
oke-0.017
Token were
Token ID547
Feature activation-6.05e-01

Pos logit contributions
rob+0.033
 Woo+0.028
amb+0.024
bur+0.023
 Pink+0.023
Neg logit contributions
orry-0.021
oke-0.021
run-0.021
ence-0.020
aint-0.019
Token called
Token ID1444
Feature activation+5.38e-01

Pos logit contributions
rob+0.024
 Woo+0.021
amb+0.018
 Pink+0.017
bur+0.017
Neg logit contributions
orry-0.018
oke-0.018
run-0.018
ence-0.017
aint-0.017
Token ost
Token ID23619
Feature activation+1.02e+00

Pos logit contributions
orry+0.018
run+0.017
oke+0.017
ence+0.016
aint+0.016
Neg logit contributions
rob-0.019
 Woo-0.018
 Pink-0.015
amb-0.014
 Gloria-0.014
Tokenric
Token ID1173
Feature activation+3.39e+00

Pos logit contributions
orry+0.025
run+0.025
oke+0.024
 gust+0.023
 tug+0.023
Neg logit contributions
rob-0.045
 Woo-0.037
bur-0.036
amb-0.035
oto-0.032
Tokenhes
Token ID956
Feature activation+1.18e+00

Pos logit contributions
run+0.128
aint+0.125
orry+0.123
 tug+0.122
 gust+0.121
Neg logit contributions
rob-0.105
 Woo-0.076
bur-0.063
amb-0.061
 Pink-0.058
Token.
Token ID13
Feature activation-4.28e-01

Pos logit contributions
orry+0.040
run+0.039
oke+0.039
ence+0.038
aint+0.037
Neg logit contributions
rob-0.042
 Woo-0.036
amb-0.029
 Pink-0.028
bur-0.028
Token Lily
Token ID20037
Feature activation-4.54e-01

Pos logit contributions
rob+0.016
 Woo+0.015
 Pink+0.013
amb+0.012
 Sebastian+0.012
Neg logit contributions
orry-0.013
run-0.012
ence-0.012
oke-0.012
aint-0.012
Token and
Token ID290
Feature activation+6.58e-01

Pos logit contributions
rob+0.019
 Woo+0.016
amb+0.014
bur+0.013
 Pink+0.013
Neg logit contributions
orry-0.013
oke-0.013
ence-0.012
run-0.012
aint-0.012
Token Ben
Token ID3932
Feature activation-1.65e-03

Pos logit contributions
orry+0.018
run+0.018
oke+0.018
ence+0.017
aint+0.017
Neg logit contributions
rob-0.028
 Woo-0.025
amb-0.021
 Pink-0.021
bur-0.020
Token you
Token ID345
Feature activation+2.55e-01

Pos logit contributions
orry+0.024
run+0.024
isel+0.024
ence+0.023
oke+0.023
Neg logit contributions
rob-0.027
 Woo-0.026
 Pink-0.022
bur-0.020
amb-0.019
Token count
Token ID954
Feature activation+1.34e-01

Pos logit contributions
orry+0.007
oke+0.007
run+0.007
ence+0.006
aint+0.006
Neg logit contributions
rob-0.011
 Woo-0.010
amb-0.008
 Pink-0.008
bur-0.008
Token how
Token ID703
Feature activation+3.89e-01

Pos logit contributions
orry+0.004
oke+0.004
run+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.005
 Woo-0.004
amb-0.004
bur-0.004
 Pink-0.004
Token many
Token ID867
Feature activation-5.98e-01

Pos logit contributions
oke+0.015
orry+0.014
run+0.014
 fists+0.014
 tug+0.014
Neg logit contributions
rob-0.010
 Woo-0.010
 Pink-0.008
amb-0.008
 Gloria-0.007
Token ost
Token ID23619
Feature activation+6.25e-01

Pos logit contributions
rob+0.023
 Woo+0.019
amb+0.016
 Pink+0.015
bur+0.015
Neg logit contributions
orry-0.019
run-0.019
oke-0.019
ence-0.018
aint-0.018
Tokenric
Token ID1173
Feature activation+3.37e+00

Pos logit contributions
orry+0.013
run+0.013
oke+0.013
ence+0.012
aint+0.012
Neg logit contributions
rob-0.030
 Woo-0.026
amb-0.023
bur-0.023
 Pink-0.022
Tokenhes
Token ID956
Feature activation+7.22e-02

Pos logit contributions
run+0.119
 tug+0.117
aint+0.114
orry+0.114
ence+0.113
Neg logit contributions
rob-0.112
 Woo-0.080
amb-0.070
bur-0.068
 Pink-0.064
Token there
Token ID612
Feature activation-3.24e-01

Pos logit contributions
orry+0.002
run+0.002
oke+0.002
ence+0.002
aint+0.002
Neg logit contributions
rob-0.003
 Woo-0.002
amb-0.002
 Pink-0.002
bur-0.002
Token are
Token ID389
Feature activation-5.34e-01

Pos logit contributions
rob+0.012
 Woo+0.010
amb+0.008
 Sebastian+0.007
 Pink+0.007
Neg logit contributions
run-0.011
oke-0.011
orry-0.011
ence-0.011
aint-0.010
Token?"
Token ID1701
Feature activation-2.17e-01

Pos logit contributions
rob+0.018
 Woo+0.015
 Pink+0.013
bur+0.012
amb+0.012
Neg logit contributions
orry-0.019
oke-0.018
run-0.018
ence-0.017
isel-0.017
Token
Token ID198
Feature activation-7.05e-02

Pos logit contributions
rob+0.008
 Woo+0.007
 Pink+0.007
amb+0.006
 herself+0.006
Neg logit contributions
ence-0.007
run-0.006
orry-0.006
isel-0.006
oke-0.006
Token girl
Token ID2576
Feature activation+6.58e-01

Pos logit contributions
run+0.020
orry+0.019
ence+0.019
oke+0.019
aint+0.018
Neg logit contributions
rob-0.022
 Woo-0.020
 Pink-0.017
amb-0.016
bur-0.015
Token who
Token ID508
Feature activation+1.28e+00

Pos logit contributions
oke+0.027
orry+0.026
run+0.026
ence+0.026
isel+0.025
Neg logit contributions
rob-0.018
 Woo-0.016
amb-0.013
 Pink-0.012
bur-0.011
Token didn
Token ID1422
Feature activation+6.89e-01

Pos logit contributions
oke+0.044
orry+0.044
run+0.043
ence+0.042
aint+0.040
Neg logit contributions
rob-0.045
 Woo-0.039
 Pink-0.032
amb-0.031
thank-0.030
Token't
Token ID470
Feature activation+4.58e-02

Pos logit contributions
orry+0.021
run+0.021
aint+0.019
oke+0.019
ence+0.019
Neg logit contributions
rob-0.030
 Woo-0.023
bur-0.020
amb-0.020
thank-0.019
Token like
Token ID588
Feature activation+1.12e+00

Pos logit contributions
oke+0.001
orry+0.001
run+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.002
 Woo-0.002
amb-0.001
 Pink-0.001
bur-0.001
Token av
Token ID1196
Feature activation+3.36e+00

Pos logit contributions
oke+0.037
orry+0.037
run+0.036
ence+0.035
isel+0.033
Neg logit contributions
rob-0.040
 Woo-0.039
 Pink-0.031
 Gloria-0.028
 Rudolph-0.028
Tokenoc
Token ID420
Feature activation+1.16e+00

Pos logit contributions
orry+0.081
oke+0.080
run+0.079
ence+0.076
aint+0.076
Neg logit contributions
rob-0.150
 Woo-0.135
amb-0.116
 Pink-0.111
bur-0.108
Tokenados
Token ID22484
Feature activation+1.24e+00

Pos logit contributions
orry+0.033
run+0.032
oke+0.032
ence+0.031
aint+0.030
Neg logit contributions
rob-0.049
 Woo-0.042
amb-0.036
 Pink-0.034
bur-0.034
Token.
Token ID13
Feature activation+8.12e-01

Pos logit contributions
orry+0.036
oke+0.035
run+0.035
ence+0.034
aint+0.033
Neg logit contributions
rob-0.051
 Woo-0.044
amb-0.038
bur-0.036
 Pink-0.035
Token She
Token ID1375
Feature activation+1.65e-01

Pos logit contributions
oke+0.037
orry+0.037
run+0.036
ence+0.035
isel+0.035
Neg logit contributions
 Woo-0.017
rob-0.017
 Pink-0.014
 Cindy-0.012
 herself-0.012
Token always
Token ID1464
Feature activation-7.04e-01

Pos logit contributions
run+0.005
oke+0.005
orry+0.005
ence+0.005
aint+0.005
Neg logit contributions
rob-0.006
 Woo-0.005
amb-0.005
 Pink-0.004
bur-0.004
Token ostr
Token ID42387
Feature activation-2.73e-01

Pos logit contributions
rob+0.002
 Woo+0.002
 Pink+0.001
bur+0.001
 Rudolph+0.001
Neg logit contributions
run-0.003
orry-0.003
oke-0.003
isel-0.003
ence-0.003
Tokenich
Token ID488
Feature activation+3.48e-01

Pos logit contributions
rob+0.009
 Woo+0.007
amb+0.006
bur+0.005
 Pink+0.005
Neg logit contributions
orry-0.010
run-0.010
oke-0.010
ence-0.010
aint-0.010
Token pen
Token ID3112
Feature activation-1.47e-01

Pos logit contributions
orry+0.013
oke+0.012
run+0.012
isel+0.012
ence+0.012
Neg logit contributions
rob-0.011
 Woo-0.010
amb-0.008
 Pink-0.008
bur-0.008
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
rob+0.006
 Woo+0.005
amb+0.004
bur+0.004
 Cindy+0.004
Neg logit contributions
 tower-0.004
run-0.004
oke-0.004
orry-0.004
ence-0.004
Token Ost
Token ID38919
Feature activation+6.55e-01

Pos logit contributions
rob+0.017
 Woo+0.015
amb+0.013
 Pink+0.013
 Sebastian+0.012
Neg logit contributions
orry-0.013
oke-0.012
ence-0.012
run-0.012
aint-0.011
Tokenric
Token ID1173
Feature activation+3.35e+00

Pos logit contributions
orry+0.009
oke+0.009
ence+0.009
run+0.008
aint+0.007
Neg logit contributions
rob-0.035
 Woo-0.034
amb-0.030
 Pink-0.029
 Cindy-0.029
Tokenhes
Token ID956
Feature activation+1.20e+00

Pos logit contributions
run+0.126
aint+0.123
ence+0.123
orry+0.122
 tug+0.120
Neg logit contributions
rob-0.108
 Woo-0.078
amb-0.063
bur-0.063
oto-0.059
Token are
Token ID389
Feature activation+3.56e-01

Pos logit contributions
orry+0.039
run+0.038
oke+0.038
ence+0.038
aint+0.036
Neg logit contributions
rob-0.044
 Woo-0.038
amb-0.031
 Pink-0.031
bur-0.030
Token big
Token ID1263
Feature activation-5.33e-01

Pos logit contributions
orry+0.012
oke+0.011
run+0.011
isel+0.011
aint+0.011
Neg logit contributions
rob-0.013
 Woo-0.012
 Pink-0.010
bur-0.010
 Rudolph-0.009
Token birds
Token ID10087
Feature activation+1.37e+00

Pos logit contributions
rob+0.016
 Woo+0.013
 Pink+0.010
amb+0.010
bur+0.009
Neg logit contributions
orry-0.022
run-0.021
ence-0.020
isel-0.020
oke-0.020
Token with
Token ID351
Feature activation+2.87e-01

Pos logit contributions
orry+0.049
run+0.048
ence+0.047
oke+0.047
isel+0.046
Neg logit contributions
rob-0.045
 Woo-0.039
amb-0.032
 Pink-0.032
bur-0.030
Token was
Token ID373
Feature activation-1.44e-01

Pos logit contributions
orry+0.018
run+0.018
oke+0.018
ence+0.017
aint+0.017
Neg logit contributions
rob-0.024
 Woo-0.021
amb-0.018
 Pink-0.017
bur-0.017
Token very
Token ID845
Feature activation+1.58e-01

Pos logit contributions
rob+0.005
 Woo+0.005
 Pink+0.004
 Cindy+0.003
amb+0.003
Neg logit contributions
oke-0.005
run-0.005
orry-0.005
ence-0.005
isel-0.005
Token naughty
Token ID45128
Feature activation-1.16e-01

Pos logit contributions
run+0.004
oke+0.004
orry+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.006
 Woo-0.006
 Pink-0.005
amb-0.005
 Cindy-0.004
Token and
Token ID290
Feature activation+9.20e-01

Pos logit contributions
rob+0.003
 Woo+0.003
amb+0.002
 Pink+0.002
bur+0.002
Neg logit contributions
orry-0.005
run-0.005
ence-0.005
oke-0.005
isel-0.004
Token always
Token ID1464
Feature activation-1.49e-01

Pos logit contributions
oke+0.032
run+0.031
ence+0.030
orry+0.030
ever+0.030
Neg logit contributions
rob-0.030
 Woo-0.030
 Pink-0.024
 herself-0.022
 Cindy-0.021
Token mis
Token ID2984
Feature activation+3.34e+00

Pos logit contributions
rob+0.005
 Woo+0.005
 Pink+0.004
thank+0.004
bur+0.004
Neg logit contributions
orry-0.005
oke-0.005
ence-0.005
isel-0.005
run-0.005
Tokenbeh
Token ID20709
Feature activation+2.58e+00

Pos logit contributions
oke+0.094
orry+0.094
ence+0.088
 tower+0.088
run+0.084
Neg logit contributions
rob-0.128
 Woo-0.113
amb-0.104
bur-0.099
thank-0.094
Tokenaving
Token ID2703
Feature activation+7.59e-01

Pos logit contributions
orry+0.065
oke+0.064
run+0.062
ence+0.061
aint+0.058
Neg logit contributions
rob-0.114
 Woo-0.099
amb-0.087
bur-0.082
 Pink-0.081
Token.
Token ID13
Feature activation+6.36e-01

Pos logit contributions
orry+0.027
oke+0.027
ence+0.026
run+0.026
isel+0.025
Neg logit contributions
rob-0.025
 Woo-0.023
 Pink-0.017
amb-0.017
 Cindy-0.016
Token One
Token ID1881
Feature activation+5.19e-01

Pos logit contributions
orry+0.022
oke+0.021
run+0.021
ence+0.021
isel+0.020
Neg logit contributions
rob-0.022
 Woo-0.020
amb-0.016
 Pink-0.016
bur-0.015
Token day
Token ID1110
Feature activation+2.96e-01

Pos logit contributions
ence+0.020
oke+0.020
run+0.020
isel+0.019
aint+0.019
Neg logit contributions
rob-0.015
 Woo-0.014
 Pink-0.011
amb-0.010
burn-0.010
Token ostr
Token ID42387
Feature activation-1.85e-01

Pos logit contributions
run+0.016
orry+0.015
oke+0.015
ence+0.015
aint+0.015
Neg logit contributions
rob-0.013
 Woo-0.011
 Pink-0.008
bur-0.008
amb-0.008
Tokenich
Token ID488
Feature activation+6.05e-01

Pos logit contributions
rob+0.006
 Woo+0.005
amb+0.004
bur+0.004
 Pink+0.003
Neg logit contributions
run-0.007
orry-0.007
oke-0.007
ence-0.007
aint-0.007
Token pen
Token ID3112
Feature activation-1.25e-01

Pos logit contributions
orry+0.022
isel+0.022
oke+0.021
run+0.021
ence+0.020
Neg logit contributions
rob-0.020
 Woo-0.017
amb-0.014
 Pink-0.014
bur-0.014
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.004
bur+0.004
 Sebastian+0.004
Neg logit contributions
run-0.003
orry-0.003
oke-0.003
 tower-0.003
ence-0.003
Token Ost
Token ID38919
Feature activation+7.73e-01

Pos logit contributions
rob+0.013
 Woo+0.013
 Pink+0.011
amb+0.011
 Sebastian+0.010
Neg logit contributions
orry-0.010
ence-0.009
oke-0.009
run-0.009
aint-0.009
Tokenric
Token ID1173
Feature activation+3.31e+00

Pos logit contributions
orry+0.011
oke+0.011
ence+0.011
run+0.009
aint+0.009
Neg logit contributions
rob-0.041
 Woo-0.040
amb-0.035
 Pink-0.034
 Cindy-0.033
Tokenhes
Token ID956
Feature activation+9.72e-01

Pos logit contributions
run+0.124
aint+0.121
ence+0.121
orry+0.120
 tug+0.117
Neg logit contributions
rob-0.107
 Woo-0.078
bur-0.063
amb-0.063
oto-0.059
Token are
Token ID389
Feature activation+3.39e-01

Pos logit contributions
orry+0.031
run+0.030
oke+0.030
ence+0.030
aint+0.029
Neg logit contributions
rob-0.037
 Woo-0.031
amb-0.026
 Pink-0.025
bur-0.025
Token big
Token ID1263
Feature activation-6.08e-01

Pos logit contributions
orry+0.011
oke+0.010
run+0.010
ence+0.010
aint+0.010
Neg logit contributions
rob-0.013
 Woo-0.011
 Pink-0.009
bur-0.009
amb-0.009
Token birds
Token ID10087
Feature activation+1.24e+00

Pos logit contributions
rob+0.019
 Woo+0.015
 Pink+0.011
amb+0.011
bur+0.011
Neg logit contributions
orry-0.024
run-0.024
ence-0.023
oke-0.023
aint-0.023
Token with
Token ID351
Feature activation+2.41e-01

Pos logit contributions
orry+0.046
run+0.044
oke+0.043
ence+0.043
isel+0.042
Neg logit contributions
rob-0.041
 Woo-0.035
amb-0.029
 Pink-0.028
bur-0.027
Token shouted
Token ID17293
Feature activation-3.58e-01

Pos logit contributions
rob+0.027
 Woo+0.022
amb+0.018
bur+0.017
 Pink+0.017
Neg logit contributions
oke-0.024
run-0.024
orry-0.024
ence-0.023
aint-0.022
Token.
Token ID13
Feature activation-4.43e-01

Pos logit contributions
rob+0.010
 Woo+0.010
 Pink+0.008
amb+0.008
 Sebastian+0.007
Neg logit contributions
orry-0.013
oke-0.013
ence-0.013
run-0.013
aint-0.012
Token "
Token ID366
Feature activation-4.92e-01

Pos logit contributions
rob+0.020
 Woo+0.018
amb+0.015
 Pink+0.015
bur+0.014
Neg logit contributions
orry-0.011
oke-0.011
run-0.011
ence-0.011
aint-0.010
TokenThe
Token ID464
Feature activation-5.69e-01

Pos logit contributions
rob+0.019
 Woo+0.016
amb+0.014
 Pink+0.013
bur+0.013
Neg logit contributions
orry-0.016
oke-0.016
run-0.015
ence-0.015
aint-0.015
Token ost
Token ID23619
Feature activation+7.06e-01

Pos logit contributions
rob+0.024
 Woo+0.020
amb+0.017
bur+0.016
 Pink+0.016
Neg logit contributions
orry-0.016
oke-0.016
run-0.016
ence-0.016
aint-0.015
Tokenric
Token ID1173
Feature activation+3.25e+00

Pos logit contributions
run+0.016
orry+0.016
oke+0.015
 tug+0.015
aint+0.015
Neg logit contributions
rob-0.033
 Woo-0.027
bur-0.025
amb-0.025
igi-0.023
Tokenhes
Token ID956
Feature activation+4.88e-01

Pos logit contributions
run+0.125
aint+0.122
ence+0.122
orry+0.120
 tug+0.119
Neg logit contributions
rob-0.101
 Woo-0.072
amb-0.060
bur-0.057
oto-0.055
Token are
Token ID389
Feature activation+3.45e-02

Pos logit contributions
orry+0.016
run+0.016
ence+0.015
oke+0.015
aint+0.015
Neg logit contributions
rob-0.018
 Woo-0.015
amb-0.013
 Pink-0.012
bur-0.012
Token so
Token ID523
Feature activation-2.38e-01

Pos logit contributions
orry+0.001
oke+0.001
isel+0.001
run+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
 Pink-0.001
bur-0.001
 Gloria-0.001
Token funny
Token ID8258
Feature activation-1.78e-01

Pos logit contributions
rob+0.008
 Woo+0.008
 Pink+0.006
amb+0.006
 Gloria+0.006
Neg logit contributions
run-0.007
orry-0.007
oke-0.007
aint-0.007
isel-0.007
Token!"
Token ID2474
Feature activation-3.08e-01

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.003
 Pink+0.003
bur+0.003
Neg logit contributions
orry-0.007
run-0.007
oke-0.007
ence-0.007
aint-0.007
TokenYes
Token ID5297
Feature activation+2.50e-02

Pos logit contributions
rob+0.024
 Woo+0.020
amb+0.018
bur+0.017
ippy+0.016
Neg logit contributions
orry-0.015
oke-0.015
ence-0.015
run-0.014
aint-0.014
Token,
Token ID11
Feature activation-5.41e-01

Pos logit contributions
run+0.001
orry+0.001
oke+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
 Pink-0.000
amb-0.000
 Cindy-0.000
Token they
Token ID484
Feature activation-8.38e-02

Pos logit contributions
 Woo+0.016
rob+0.015
 Pink+0.014
 Dod+0.013
 Gloria+0.012
Neg logit contributions
run-0.019
aint-0.018
ence-0.018
orry-0.018
oke-0.018
Token are
Token ID389
Feature activation-2.85e-01

Pos logit contributions
rob+0.003
 Woo+0.002
amb+0.002
 Pink+0.002
bur+0.002
Neg logit contributions
run-0.003
oke-0.003
orry-0.003
ence-0.003
aint-0.003
Token ost
Token ID23619
Feature activation+9.37e-01

Pos logit contributions
rob+0.010
 Woo+0.009
amb+0.007
bur+0.007
 Pink+0.007
Neg logit contributions
orry-0.010
oke-0.010
run-0.010
ence-0.009
aint-0.009
Tokenric
Token ID1173
Feature activation+3.24e+00

Pos logit contributions
run+0.022
orry+0.021
oke+0.021
 tug+0.020
aint+0.020
Neg logit contributions
rob-0.043
 Woo-0.037
amb-0.034
bur-0.034
oto-0.031
Tokenhes
Token ID956
Feature activation+8.54e-01

Pos logit contributions
run+0.122
aint+0.117
orry+0.116
ence+0.115
 tug+0.115
Neg logit contributions
rob-0.104
 Woo-0.077
amb-0.064
 Pink-0.061
bur-0.060
Token,"
Token ID553
Feature activation-2.77e-02

Pos logit contributions
orry+0.028
run+0.027
oke+0.027
ence+0.027
aint+0.026
Neg logit contributions
rob-0.032
 Woo-0.027
amb-0.022
 Pink-0.021
bur-0.021
Token mom
Token ID1995
Feature activation-8.89e-01

Pos logit contributions
rob+0.001
 Woo+0.001
 Pink+0.001
amb+0.001
 Gloria+0.001
Neg logit contributions
run-0.001
orry-0.001
oke-0.001
ence-0.001
aint-0.001
Token said
Token ID531
Feature activation+1.88e-01

Pos logit contributions
rob+0.029
 Woo+0.023
amb+0.019
 Pink+0.017
bur+0.017
Neg logit contributions
orry-0.034
run-0.033
oke-0.033
ence-0.033
aint-0.032
Token.
Token ID13
Feature activation-9.51e-02

Pos logit contributions
orry+0.008
ence+0.007
oke+0.007
isel+0.007
run+0.007
Neg logit contributions
 Woo-0.005
rob-0.005
 Pink-0.004
amb-0.003
 Lib-0.003
Token he
Token ID339
Feature activation+4.18e-01

Pos logit contributions
rob+0.000
 Woo+0.000
amb+0.000
 Pink+0.000
 Sebastian+0.000
Neg logit contributions
ence-0.000
oke-0.000
run-0.000
orry-0.000
aint-0.000
Token could
Token ID714
Feature activation+8.31e-02

Pos logit contributions
orry+0.011
run+0.011
oke+0.011
ence+0.011
aint+0.010
Neg logit contributions
rob-0.018
 Woo-0.016
amb-0.013
bur-0.013
 Pink-0.013
Token be
Token ID307
Feature activation+1.04e+00

Pos logit contributions
orry+0.002
oke+0.002
run+0.002
ence+0.002
aint+0.002
Neg logit contributions
rob-0.004
 Woo-0.003
amb-0.003
 Pink-0.003
bur-0.003
Token and
Token ID290
Feature activation+2.52e-01

Pos logit contributions
oke+0.033
orry+0.033
ence+0.032
run+0.031
aint+0.031
Neg logit contributions
rob-0.038
 Woo-0.033
thank-0.027
 Pink-0.027
bur-0.026
Token never
Token ID1239
Feature activation+1.17e-02

Pos logit contributions
oke+0.009
orry+0.009
ence+0.009
aint+0.008
run+0.008
Neg logit contributions
rob-0.008
 Woo-0.007
 Pink-0.006
amb-0.006
thank-0.006
Token mis
Token ID2984
Feature activation+3.22e+00

Pos logit contributions
orry+0.000
ence+0.000
oke+0.000
isel+0.000
icker+0.000
Neg logit contributions
 Woo-0.000
rob-0.000
 Pink-0.000
thank-0.000
 Cindy-0.000
Tokenbeh
Token ID20709
Feature activation+2.79e+00

Pos logit contributions
orry+0.088
oke+0.085
 tower+0.080
ence+0.080
 structure+0.076
Neg logit contributions
rob-0.124
 Woo-0.112
amb-0.105
bur-0.098
burn-0.095
Tokenaved
Token ID9586
Feature activation+5.51e-01

Pos logit contributions
orry+0.067
oke+0.065
 tower+0.062
ence+0.062
run+0.060
Neg logit contributions
rob-0.120
 Woo-0.108
amb-0.096
thank-0.087
bur-0.087
Token.
Token ID13
Feature activation+2.37e-01

Pos logit contributions
orry+0.019
oke+0.019
ence+0.018
run+0.018
aint+0.017
Neg logit contributions
rob-0.019
 Woo-0.017
amb-0.013
 Pink-0.013
thank-0.013
Token<|endoftext|>
Token ID50256
Feature activation+7.89e-02

Pos logit contributions
orry+0.009
ence+0.008
oke+0.008
run+0.008
aint+0.008
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.005
 Pink-0.005
bur-0.005
TokenOnce
Token ID7454
Feature activation-8.00e-01

Pos logit contributions
oke+0.002
run+0.002
orry+0.002
aint+0.002
ence+0.002
Neg logit contributions
rob-0.003
 Woo-0.003
amb-0.002
bur-0.002
burn-0.002
Token did
Token ID750
Feature activation+1.68e-01

Pos logit contributions
run+0.000
orry+0.000
oke+0.000
ence+0.000
isel+0.000
Neg logit contributions
rob-0.000
 Woo-0.000
amb-0.000
 Pink-0.000
bur-0.000
Token not
Token ID407
Feature activation-1.56e-01

Pos logit contributions
oke+0.007
run+0.007
orry+0.006
aint+0.006
ence+0.006
Neg logit contributions
rob-0.005
 Woo-0.004
 Lib-0.003
 herself-0.003
 Pink-0.003
Token know
Token ID760
Feature activation-2.40e-01

Pos logit contributions
rob+0.007
 Woo+0.006
amb+0.005
bur+0.005
 Pink+0.005
Neg logit contributions
orry-0.004
oke-0.004
run-0.004
ence-0.004
aint-0.004
Token what
Token ID644
Feature activation+9.70e-01

Pos logit contributions
rob+0.010
 Woo+0.009
 Pink+0.007
 Sim+0.007
 Lib+0.007
Neg logit contributions
orry-0.006
run-0.006
aint-0.006
ence-0.006
isel-0.006
Token ost
Token ID23619
Feature activation+6.44e-01

Pos logit contributions
orry+0.034
run+0.033
oke+0.033
isel+0.032
ence+0.032
Neg logit contributions
rob-0.032
 Woo-0.028
 Pink-0.023
 Gloria-0.022
 Rudolph-0.022
Tokenric
Token ID1173
Feature activation+3.20e+00

Pos logit contributions
orry+0.015
run+0.014
 tug+0.014
oke+0.014
 gust+0.013
Neg logit contributions
rob-0.030
 Woo-0.025
amb-0.023
bur-0.023
 Pink-0.021
Tokenhes
Token ID956
Feature activation+9.75e-01

Pos logit contributions
 tug+0.118
run+0.117
orry+0.113
 gust+0.113
aint+0.112
Neg logit contributions
rob-0.100
 Woo-0.073
bur-0.060
amb-0.060
 Pink-0.057
Token were
Token ID547
Feature activation+2.15e-01

Pos logit contributions
orry+0.031
run+0.030
oke+0.029
ence+0.029
aint+0.028
Neg logit contributions
rob-0.037
 Woo-0.032
amb-0.026
 Pink-0.026
bur-0.026
Token.
Token ID13
Feature activation+4.23e-01

Pos logit contributions
orry+0.007
run+0.007
oke+0.007
ence+0.007
aint+0.007
Neg logit contributions
rob-0.008
 Woo-0.006
amb-0.005
bur-0.005
 Pink-0.005
Token They
Token ID1119
Feature activation-6.43e-01

Pos logit contributions
orry+0.014
run+0.014
oke+0.013
ence+0.013
isel+0.013
Neg logit contributions
rob-0.015
 Woo-0.014
amb-0.011
 Pink-0.011
 Lib-0.011
Token looked
Token ID3114
Feature activation-1.71e-01

Pos logit contributions
rob+0.022
 Woo+0.020
amb+0.017
 Pink+0.016
bur+0.016
Neg logit contributions
oke-0.021
run-0.021
orry-0.021
ence-0.019
aint-0.019
Token help
Token ID1037
Feature activation-9.09e-02

Pos logit contributions
rob+0.003
 Woo+0.003
amb+0.002
 Pink+0.002
bur+0.002
Neg logit contributions
orry-0.002
run-0.002
oke-0.002
ence-0.002
aint-0.002
Token me
Token ID502
Feature activation-5.73e-01

Pos logit contributions
rob+0.004
 Woo+0.003
amb+0.003
thank+0.003
 Pink+0.003
Neg logit contributions
orry-0.003
run-0.002
aint-0.002
ence-0.002
oke-0.002
Token?"
Token ID1701
Feature activation-6.42e-01

Pos logit contributions
rob+0.023
 Woo+0.019
amb+0.016
bur+0.015
 Pink+0.015
Neg logit contributions
orry-0.018
run-0.018
oke-0.017
ence-0.017
aint-0.017
Token
Token ID198
Feature activation-2.76e-01

Pos logit contributions
rob+0.023
 Woo+0.020
amb+0.016
 Pink+0.015
bur+0.014
Neg logit contributions
orry-0.023
oke-0.022
run-0.022
ence-0.022
aint-0.021
Token
Token ID198
Feature activation-1.96e-01

Pos logit contributions
rob+0.010
 Woo+0.009
amb+0.007
bur+0.007
 Pink+0.007
Neg logit contributions
orry-0.009
run-0.009
oke-0.009
ence-0.009
aint-0.008
TokenT
Token ID51
Feature activation-3.20e+00

Pos logit contributions
rob+0.006
 Woo+0.005
amb+0.004
 Pink+0.004
bur+0.004
Neg logit contributions
orry-0.008
run-0.008
oke-0.008
ence-0.007
aint-0.007
Tokenoby
Token ID26730
Feature activation-2.50e-01

Pos logit contributions
rob+0.148
 Woo+0.130
 Pink+0.115
 Lib+0.111
thank+0.111
Neg logit contributions
oke-0.083
orry-0.081
run-0.076
ever-0.070
ence-0.067
Token was
Token ID373
Feature activation-4.19e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
 Pink+0.006
bur+0.006
Neg logit contributions
orry-0.008
run-0.008
oke-0.008
ence-0.008
aint-0.008
Token excited
Token ID6568
Feature activation+7.37e-02

Pos logit contributions
rob+0.015
 Woo+0.013
amb+0.011
 Pink+0.010
bur+0.010
Neg logit contributions
orry-0.014
oke-0.014
run-0.014
ence-0.014
aint-0.013
Token to
Token ID284
Feature activation-2.28e-01

Pos logit contributions
orry+0.003
oke+0.003
run+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.002
 Woo-0.002
amb-0.002
 Pink-0.001
thank-0.001
Token serve
Token ID4691
Feature activation-1.68e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
 Pink+0.007
thank+0.007
Neg logit contributions
oke-0.006
orry-0.006
run-0.006
ence-0.006
aint-0.006
Token okay
Token ID8788
Feature activation+5.17e-01

Pos logit contributions
orry+0.031
oke+0.030
run+0.029
ence+0.029
aint+0.028
Neg logit contributions
rob-0.045
 Woo-0.041
bur-0.034
 Pink-0.034
amb-0.033
Token."
Token ID526
Feature activation-5.41e-01

Pos logit contributions
orry+0.020
ence+0.019
oke+0.019
run+0.018
aint+0.018
Neg logit contributions
rob-0.016
 Woo-0.014
amb-0.011
 Pink-0.011
bur-0.011
Token
Token ID220
Feature activation+2.44e-01

Pos logit contributions
rob+0.020
 Woo+0.017
amb+0.014
 Pink+0.014
bur+0.013
Neg logit contributions
orry-0.018
oke-0.018
ence-0.018
run-0.018
aint-0.017
Token
Token ID198
Feature activation-3.23e-01

Pos logit contributions
orry+0.008
run+0.008
oke+0.008
ence+0.008
aint+0.007
Neg logit contributions
rob-0.009
 Woo-0.008
amb-0.006
bur-0.006
 Pink-0.006
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
rob+0.012
 Woo+0.010
amb+0.009
bur+0.008
 Pink+0.008
Neg logit contributions
orry-0.010
run-0.010
oke-0.010
ence-0.010
aint-0.009
TokenT
Token ID51
Feature activation-3.18e+00

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.003
 Pink+0.003
bur+0.003
Neg logit contributions
orry-0.005
oke-0.005
run-0.005
ence-0.005
aint-0.005
Tokenoby
Token ID26730
Feature activation+1.63e-01

Pos logit contributions
rob+0.144
 Woo+0.123
 Pink+0.110
 Lib+0.108
thank+0.105
Neg logit contributions
oke-0.086
orry-0.085
run-0.083
ever-0.076
ence-0.073
Token thanked
Token ID26280
Feature activation-2.13e-01

Pos logit contributions
orry+0.005
run+0.005
oke+0.005
ence+0.005
aint+0.005
Neg logit contributions
rob-0.007
 Woo-0.006
amb-0.005
bur-0.004
 Pink-0.004
Token them
Token ID606
Feature activation+2.32e-02

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
 Pink+0.006
bur+0.006
Neg logit contributions
orry-0.006
oke-0.006
run-0.006
ence-0.006
aint-0.006
Token,
Token ID11
Feature activation+6.45e-01

Pos logit contributions
orry+0.001
run+0.001
oke+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
amb-0.001
bur-0.000
 Pink-0.000
Token said
Token ID531
Feature activation+4.86e-01

Pos logit contributions
orry+0.025
oke+0.024
run+0.024
ence+0.024
aint+0.023
Neg logit contributions
rob-0.020
 Woo-0.017
amb-0.014
 Pink-0.013
bur-0.013
Token lightning
Token ID14357
Feature activation+1.06e-01

Pos logit contributions
orry+0.020
run+0.019
oke+0.019
ence+0.019
aint+0.018
Neg logit contributions
rob-0.029
 Woo-0.025
amb-0.022
bur-0.020
 Pink-0.020
Token!
Token ID0
Feature activation+8.73e-02

Pos logit contributions
orry+0.004
run+0.004
ence+0.004
oke+0.003
isel+0.003
Neg logit contributions
rob-0.004
 Woo-0.003
 Pink-0.002
thank-0.002
amb-0.002
Token
Token ID220
Feature activation+7.16e-01

Pos logit contributions
run+0.002
orry+0.002
aint+0.002
oke+0.002
ence+0.002
Neg logit contributions
rob-0.004
 Woo-0.003
bur-0.003
igi-0.003
amb-0.003
Token
Token ID198
Feature activation-3.78e-01

Pos logit contributions
orry+0.024
run+0.023
oke+0.023
ence+0.022
aint+0.022
Neg logit contributions
rob-0.027
 Woo-0.022
amb-0.019
bur-0.018
 Pink-0.018
Token
Token ID198
Feature activation-3.02e-01

Pos logit contributions
rob+0.016
 Woo+0.013
bur+0.012
amb+0.012
thank+0.011
Neg logit contributions
orry-0.010
run-0.010
oke-0.010
aint-0.010
ence-0.009
TokenT
Token ID51
Feature activation-3.18e+00

Pos logit contributions
rob+0.012
 Woo+0.010
amb+0.008
bur+0.008
 Pink+0.008
Neg logit contributions
orry-0.010
run-0.009
oke-0.009
ence-0.009
aint-0.009
Tokenina
Token ID1437
Feature activation-4.89e-02

Pos logit contributions
rob+0.118
 Woo+0.091
 Lib+0.082
 Crab+0.082
 Rudolph+0.080
Neg logit contributions
orry-0.111
oke-0.110
ever-0.103
run-0.103
ence-0.098
Token loved
Token ID6151
Feature activation+3.41e-01

Pos logit contributions
rob+0.002
 Woo+0.002
amb+0.001
bur+0.001
 Pink+0.001
Neg logit contributions
orry-0.002
oke-0.001
run-0.001
ence-0.001
aint-0.001
Token Lightning
Token ID12469
Feature activation+7.14e-02

Pos logit contributions
oke+0.013
orry+0.013
ence+0.012
run+0.012
aint+0.012
Neg logit contributions
rob-0.011
 Woo-0.011
 Pink-0.009
 Cindy-0.008
bur-0.008
Token and
Token ID290
Feature activation-1.27e-01

Pos logit contributions
orry+0.002
run+0.002
ence+0.002
oke+0.002
isel+0.002
Neg logit contributions
rob-0.003
 Woo-0.002
amb-0.002
 Pink-0.002
 Sim-0.002
Token she
Token ID673
Feature activation+2.27e-01

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.003
 Pink+0.003
bur+0.003
Neg logit contributions
orry-0.004
oke-0.004
run-0.004
ence-0.004
aint-0.004
Token noticed
Token ID6810
Feature activation+1.02e+00

Pos logit contributions
rob+0.018
 Woo+0.015
amb+0.013
 Pink+0.012
bur+0.012
Neg logit contributions
orry-0.014
run-0.014
oke-0.014
ence-0.013
aint-0.013
Token before
Token ID878
Feature activation+2.92e-01

Pos logit contributions
orry+0.029
run+0.029
oke+0.029
ence+0.028
aint+0.027
Neg logit contributions
rob-0.042
 Woo-0.036
amb-0.031
bur-0.029
 Pink-0.029
Token.
Token ID13
Feature activation-3.18e-01

Pos logit contributions
run+0.008
orry+0.008
oke+0.007
ence+0.007
aint+0.007
Neg logit contributions
rob-0.013
 Woo-0.011
amb-0.010
bur-0.009
 Pink-0.009
Token
Token ID198
Feature activation-5.76e-01

Pos logit contributions
rob+0.013
 Woo+0.011
amb+0.009
bur+0.009
thank+0.009
Neg logit contributions
run-0.009
orry-0.009
oke-0.009
ence-0.009
aint-0.009
Token
Token ID198
Feature activation-3.16e-01

Pos logit contributions
rob+0.023
 Woo+0.019
amb+0.017
bur+0.016
thank+0.016
Neg logit contributions
run-0.018
oke-0.017
orry-0.017
ence-0.016
aint-0.016
TokenT
Token ID51
Feature activation-3.17e+00

Pos logit contributions
rob+0.011
 Woo+0.009
amb+0.008
bur+0.007
 Pink+0.007
Neg logit contributions
orry-0.011
run-0.011
oke-0.011
ence-0.011
aint-0.010
Tokenina
Token ID1437
Feature activation+1.80e-01

Pos logit contributions
rob+0.137
 Woo+0.103
 Lib+0.092
bur+0.091
 Rudolph+0.089
Neg logit contributions
oke-0.101
orry-0.100
run-0.094
ence-0.092
ever-0.088
Token wanted
Token ID2227
Feature activation-3.12e-01

Pos logit contributions
orry+0.006
run+0.006
oke+0.006
ence+0.006
aint+0.006
Neg logit contributions
rob-0.006
 Woo-0.005
amb-0.004
 Pink-0.004
bur-0.004
Token to
Token ID284
Feature activation-4.80e-01

Pos logit contributions
rob+0.014
 Woo+0.013
amb+0.011
bur+0.010
 Pink+0.010
Neg logit contributions
orry-0.008
run-0.007
oke-0.007
ence-0.007
aint-0.007
Token explore
Token ID7301
Feature activation-5.07e-01

Pos logit contributions
rob+0.023
 Woo+0.019
amb+0.017
bur+0.016
 Pink+0.016
Neg logit contributions
orry-0.012
run-0.011
oke-0.011
ence-0.011
aint-0.010
Token the
Token ID262
Feature activation-7.38e-02

Pos logit contributions
rob+0.023
 Woo+0.020
amb+0.018
thank+0.017
bur+0.017
Neg logit contributions
run-0.013
orry-0.013
ence-0.012
oke-0.012
aint-0.011
Token want
Token ID765
Feature activation-3.89e-01

Pos logit contributions
rob+0.016
 Woo+0.015
amb+0.013
 Pink+0.012
bur+0.012
Neg logit contributions
orry-0.009
run-0.009
oke-0.009
ence-0.008
aint-0.008
Token to
Token ID284
Feature activation-7.15e-01

Pos logit contributions
rob+0.019
 Woo+0.016
amb+0.014
bur+0.014
thank+0.013
Neg logit contributions
orry-0.009
run-0.009
oke-0.008
ence-0.008
aint-0.008
Token play
Token ID711
Feature activation-8.44e-01

Pos logit contributions
rob+0.040
 Woo+0.032
amb+0.029
igi+0.028
bur+0.027
Neg logit contributions
orry-0.012
aint-0.012
 tower-0.012
ence-0.011
 tug-0.011
Token with
Token ID351
Feature activation-6.38e-01

Pos logit contributions
rob+0.033
 Woo+0.027
amb+0.024
bur+0.023
igi+0.022
Neg logit contributions
orry-0.026
run-0.026
oke-0.025
ence-0.025
 tower-0.024
Token our
Token ID674
Feature activation-7.27e-01

Pos logit contributions
rob+0.027
 Woo+0.023
amb+0.020
bur+0.019
 Pink+0.019
Neg logit contributions
orry-0.018
run-0.017
oke-0.017
ence-0.017
aint-0.016
Token toy
Token ID13373
Feature activation-3.15e+00

Pos logit contributions
rob+0.027
 Woo+0.023
amb+0.019
 Pink+0.018
bur+0.018
Neg logit contributions
run-0.024
orry-0.024
oke-0.024
ence-0.023
aint-0.022
Token rockets
Token ID20293
Feature activation-2.34e-01

Pos logit contributions
rob+0.133
 Woo+0.117
amb+0.099
bur+0.097
thank+0.095
Neg logit contributions
orry-0.084
oke-0.081
 tower-0.080
run-0.080
ence-0.078
Token.
Token ID13
Feature activation-1.55e-04

Pos logit contributions
rob+0.010
 Woo+0.009
amb+0.007
bur+0.007
 Pink+0.007
Neg logit contributions
run-0.006
orry-0.006
oke-0.006
ence-0.006
 tower-0.006
Token We
Token ID775
Feature activation-3.40e-01

Pos logit contributions
rob+0.000
 Woo+0.000
amb+0.000
 Pink+0.000
bur+0.000
Neg logit contributions
orry-0.000
oke-0.000
run-0.000
ence-0.000
aint-0.000
Token like
Token ID588
Feature activation+4.62e-01

Pos logit contributions
rob+0.015
 Woo+0.014
amb+0.012
 Pink+0.012
bur+0.011
Neg logit contributions
run-0.008
orry-0.008
oke-0.008
ence-0.008
aint-0.007
Token our
Token ID674
Feature activation-2.76e-01

Pos logit contributions
orry+0.015
oke+0.015
run+0.015
ence+0.014
aint+0.014
Neg logit contributions
rob-0.017
 Woo-0.015
 Pink-0.012
amb-0.012
 Rudolph-0.012
Token helping
Token ID5742
Feature activation+3.21e-01

Pos logit contributions
rob+0.003
 Woo+0.003
amb+0.002
bur+0.002
 Pink+0.002
Neg logit contributions
orry-0.002
run-0.002
oke-0.002
ence-0.002
aint-0.002
Token the
Token ID262
Feature activation-3.47e-01

Pos logit contributions
orry+0.011
oke+0.011
run+0.011
ence+0.011
aint+0.011
Neg logit contributions
rob-0.010
 Woo-0.009
 Pink-0.007
amb-0.007
bur-0.007
Token other
Token ID584
Feature activation-1.64e+00

Pos logit contributions
rob+0.012
 Woo+0.010
amb+0.008
 Pink+0.008
bur+0.008
Neg logit contributions
run-0.012
orry-0.012
oke-0.012
ence-0.012
aint-0.011
Token creatures
Token ID8109
Feature activation+2.83e-02

Pos logit contributions
rob+0.062
 Woo+0.052
amb+0.044
bur+0.041
 Pink+0.041
Neg logit contributions
orry-0.054
oke-0.052
run-0.052
ence-0.051
aint-0.050
Token.
Token ID13
Feature activation-2.41e-01

Pos logit contributions
orry+0.001
oke+0.001
run+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
amb-0.001
 Pink-0.001
bur-0.001
Token L
Token ID406
Feature activation-3.13e+00

Pos logit contributions
rob+0.011
 Woo+0.009
bur+0.008
amb+0.008
thank+0.008
Neg logit contributions
oke-0.006
orry-0.006
run-0.006
ence-0.006
aint-0.005
Tokenola
Token ID5708
Feature activation-6.56e-01

Pos logit contributions
rob+0.146
 Woo+0.125
 Pink+0.106
bur+0.106
thank+0.106
Neg logit contributions
oke-0.087
orry-0.083
run-0.074
ence-0.069
aint-0.064
Token and
Token ID290
Feature activation+3.87e-01

Pos logit contributions
rob+0.026
 Woo+0.022
bur+0.017
amb+0.017
burn+0.017
Neg logit contributions
orry-0.021
oke-0.021
ence-0.020
run-0.020
aint-0.019
Token Lex
Token ID17210
Feature activation-1.61e-01

Pos logit contributions
orry+0.013
 tug+0.012
ence+0.012
oke+0.012
aint+0.012
Neg logit contributions
rob-0.014
 Woo-0.010
robe-0.009
thank-0.008
amb-0.008
Token had
Token ID550
Feature activation-5.39e-01

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.003
thank+0.003
burn+0.003
Neg logit contributions
orry-0.006
oke-0.006
ence-0.006
run-0.006
aint-0.006
Token learned
Token ID4499
Feature activation-8.14e-02

Pos logit contributions
rob+0.017
 Woo+0.015
amb+0.011
 Pink+0.011
bur+0.011
Neg logit contributions
orry-0.021
oke-0.021
run-0.020
ence-0.020
aint-0.019
Token learn
Token ID2193
Feature activation-3.68e-01

Pos logit contributions
run+0.009
orry+0.009
oke+0.009
ence+0.008
aint+0.008
Neg logit contributions
rob-0.015
 Woo-0.014
amb-0.012
 Pink-0.012
bur-0.011
Token today
Token ID1909
Feature activation-8.22e-01

Pos logit contributions
rob+0.014
 Woo+0.012
amb+0.011
bur+0.010
 Pink+0.010
Neg logit contributions
run-0.011
oke-0.011
orry-0.011
ence-0.011
aint-0.011
Token?"
Token ID1701
Feature activation-6.23e-01

Pos logit contributions
rob+0.028
 Woo+0.023
amb+0.019
bur+0.017
 Pink+0.017
Neg logit contributions
oke-0.030
orry-0.030
run-0.030
ence-0.029
aint-0.029
Token
Token ID198
Feature activation-8.79e-03

Pos logit contributions
rob+0.021
 Woo+0.019
amb+0.015
 Pink+0.014
 Gloria+0.014
Neg logit contributions
orry-0.022
oke-0.022
run-0.022
ence-0.021
 tower-0.020
Token
Token ID198
Feature activation-3.70e-02

Pos logit contributions
rob+0.000
 Woo+0.000
amb+0.000
 Pink+0.000
bur+0.000
Neg logit contributions
orry-0.000
oke-0.000
run-0.000
ence-0.000
aint-0.000
TokenT
Token ID51
Feature activation-3.10e+00

Pos logit contributions
rob+0.001
 Woo+0.001
amb+0.001
 Pink+0.001
bur+0.001
Neg logit contributions
orry-0.001
oke-0.001
run-0.001
ence-0.001
aint-0.001
Tokenina
Token ID1437
Feature activation-3.81e-01

Pos logit contributions
rob+0.111
 Woo+0.095
 Lib+0.082
 Pink+0.082
 Rudolph+0.074
Neg logit contributions
oke-0.112
orry-0.109
run-0.105
ence-0.102
ever-0.102
Token smiled
Token ID13541
Feature activation-7.66e-01

Pos logit contributions
rob+0.015
 Woo+0.013
amb+0.011
bur+0.010
 Pink+0.010
Neg logit contributions
orry-0.012
oke-0.012
run-0.012
ence-0.011
aint-0.011
Token proudly
Token ID23017
Feature activation-1.79e+00

Pos logit contributions
rob+0.035
 Woo+0.027
bur+0.023
igi+0.022
amb+0.021
Neg logit contributions
run-0.022
ence-0.022
aint-0.021
orry-0.021
oke-0.020
Token and
Token ID290
Feature activation-1.63e-01

Pos logit contributions
rob+0.062
 Woo+0.052
amb+0.043
 Pink+0.040
bur+0.040
Neg logit contributions
orry-0.063
oke-0.062
run-0.062
ence-0.060
aint-0.059
Token said
Token ID531
Feature activation-2.09e-01

Pos logit contributions
rob+0.006
 Woo+0.005
amb+0.004
bur+0.004
igi+0.004
Neg logit contributions
orry-0.005
run-0.005
ence-0.005
oke-0.005
aint-0.005
Token thought
Token ID1807
Feature activation+7.27e-01

Pos logit contributions
rob+0.002
 Woo+0.002
amb+0.001
bur+0.001
 Pink+0.001
Neg logit contributions
orry-0.001
run-0.001
oke-0.001
ence-0.001
aint-0.001
Token it
Token ID340
Feature activation-7.77e-01

Pos logit contributions
orry+0.024
ence+0.024
oke+0.024
aint+0.023
isel+0.023
Neg logit contributions
rob-0.023
 Woo-0.022
 Pink-0.017
 Sim-0.016
 Cindy-0.016
Token should
Token ID815
Feature activation-1.26e+00

Pos logit contributions
rob+0.028
 Woo+0.023
amb+0.019
 Pink+0.019
bur+0.019
Neg logit contributions
orry-0.026
oke-0.026
run-0.025
ence-0.025
aint-0.024
Token work
Token ID670
Feature activation+5.62e-01

Pos logit contributions
rob+0.064
 Woo+0.055
amb+0.048
bur+0.046
burn+0.045
Neg logit contributions
orry-0.026
run-0.025
oke-0.025
ence-0.024
aint-0.023
Token.
Token ID13
Feature activation-3.50e-03

Pos logit contributions
run+0.015
orry+0.015
oke+0.015
ence+0.015
aint+0.014
Neg logit contributions
rob-0.024
 Woo-0.021
amb-0.018
bur-0.017
 Pink-0.017
Token D
Token ID360
Feature activation-3.09e+00

Pos logit contributions
rob+0.000
 Woo+0.000
amb+0.000
 Pink+0.000
bur+0.000
Neg logit contributions
orry-0.000
ence-0.000
oke-0.000
run-0.000
aint-0.000
Tokenina
Token ID1437
Feature activation-3.64e-01

Pos logit contributions
rob+0.098
 Woo+0.075
bur+0.058
 Pink+0.056
 Lib+0.056
Neg logit contributions
orry-0.128
oke-0.126
run-0.122
ence-0.120
aint-0.117
Token was
Token ID373
Feature activation-4.32e-01

Pos logit contributions
rob+0.013
 Woo+0.011
amb+0.010
 Pink+0.009
bur+0.009
Neg logit contributions
orry-0.012
run-0.012
oke-0.012
ence-0.011
aint-0.011
Token so
Token ID523
Feature activation-1.33e-01

Pos logit contributions
rob+0.018
 Woo+0.016
amb+0.014
 Pink+0.013
bur+0.013
Neg logit contributions
orry-0.012
oke-0.012
run-0.012
ence-0.011
aint-0.011
Token happy
Token ID3772
Feature activation+7.51e-01

Pos logit contributions
rob+0.006
 Woo+0.005
amb+0.005
 Pink+0.004
thank+0.004
Neg logit contributions
orry-0.003
oke-0.003
run-0.003
ence-0.003
aint-0.003
Token,
Token ID11
Feature activation+7.69e-02

Pos logit contributions
orry+0.027
oke+0.026
run+0.026
ence+0.026
aint+0.025
Neg logit contributions
rob-0.026
 Woo-0.022
amb-0.018
 Pink-0.017
bur-0.016
Token her
Token ID607
Feature activation-4.65e-01

Pos logit contributions
rob+0.003
 Woo+0.003
amb+0.002
bur+0.002
 Pink+0.002
Neg logit contributions
orry-0.003
run-0.003
oke-0.003
ence-0.003
aint-0.003
Token!
Token ID0
Feature activation+3.79e-01

Pos logit contributions
rob+0.014
 Woo+0.013
 Pink+0.011
amb+0.011
 Rudolph+0.010
Neg logit contributions
orry-0.017
isel-0.017
oke-0.016
ence-0.016
run-0.016
Token
Token ID220
Feature activation+5.94e-01

Pos logit contributions
run+0.011
oke+0.011
orry+0.011
aint+0.010
ence+0.010
Neg logit contributions
rob-0.016
 Woo-0.013
bur-0.011
amb-0.011
thank-0.011
Token
Token ID198
Feature activation+9.73e-02

Pos logit contributions
run+0.019
orry+0.019
oke+0.019
ence+0.018
aint+0.018
Neg logit contributions
rob-0.023
 Woo-0.019
amb-0.016
bur-0.015
 Pink-0.015
Token
Token ID198
Feature activation+2.95e-01

Pos logit contributions
run+0.003
oke+0.003
orry+0.003
aint+0.002
ence+0.002
Neg logit contributions
rob-0.004
 Woo-0.004
bur-0.003
amb-0.003
burn-0.003
TokenV
Token ID53
Feature activation-3.06e+00

Pos logit contributions
run+0.009
orry+0.009
oke+0.009
ence+0.008
aint+0.008
Neg logit contributions
rob-0.011
 Woo-0.010
amb-0.008
bur-0.008
 Pink-0.008
Tokeniv
Token ID452
Feature activation-1.03e+00

Pos logit contributions
rob+0.116
 Woo+0.107
 Pink+0.091
 Lib+0.088
 Gloria+0.086
Neg logit contributions
orry-0.093
oke-0.093
run-0.088
ever-0.085
aint-0.084
Tokenian
Token ID666
Feature activation-4.38e-01

Pos logit contributions
rob+0.034
 Woo+0.027
amb+0.021
bur+0.021
 Pink+0.020
Neg logit contributions
orry-0.039
oke-0.039
run-0.039
ence-0.038
aint-0.037
Token enjoyed
Token ID8359
Feature activation-2.51e-01

Pos logit contributions
rob+0.018
 Woo+0.015
amb+0.012
bur+0.012
burn+0.012
Neg logit contributions
orry-0.013
oke-0.013
run-0.013
ence-0.012
aint-0.012
Token playing
Token ID2712
Feature activation-4.32e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.006
 Pink+0.006
bur+0.006
Neg logit contributions
orry-0.009
oke-0.009
run-0.009
ence-0.008
aint-0.008
Token with
Token ID351
Feature activation-3.69e-01

Pos logit contributions
rob+0.014
 Woo+0.012
amb+0.009
 Pink+0.009
thank+0.009
Neg logit contributions
oke-0.016
orry-0.016
run-0.016
ence-0.016
aint-0.015
Token god
Token ID5770
Feature activation+1.10e-01

Pos logit contributions
orry+0.010
run+0.010
oke+0.010
ence+0.010
aint+0.010
Neg logit contributions
rob-0.012
 Woo-0.010
amb-0.008
bur-0.008
 Pink-0.007
Tokenmother
Token ID13552
Feature activation+7.38e-01

Pos logit contributions
orry+0.004
oke+0.004
run+0.004
ence+0.004
aint+0.003
Neg logit contributions
rob-0.004
 Woo-0.003
amb-0.003
 Sebastian-0.003
bur-0.003
Token flew
Token ID13112
Feature activation+4.17e-01

Pos logit contributions
orry+0.024
run+0.024
oke+0.024
ence+0.023
aint+0.022
Neg logit contributions
rob-0.028
 Woo-0.024
amb-0.019
bur-0.019
 Pink-0.018
Token away
Token ID1497
Feature activation-1.31e+00

Pos logit contributions
run+0.011
orry+0.011
ence+0.010
aint+0.010
oke+0.010
Neg logit contributions
rob-0.019
 Woo-0.015
amb-0.013
bur-0.012
oto-0.012
Token.
Token ID13
Feature activation-2.31e-01

Pos logit contributions
rob+0.056
 Woo+0.047
amb+0.040
bur+0.039
 Pink+0.037
Neg logit contributions
run-0.037
orry-0.037
oke-0.036
ence-0.036
aint-0.034
Token D
Token ID360
Feature activation-3.05e+00

Pos logit contributions
rob+0.011
 Woo+0.008
bur+0.008
oto+0.007
amb+0.007
Neg logit contributions
run-0.006
orry-0.006
oke-0.005
aint-0.005
ence-0.005
Tokenolly
Token ID5098
Feature activation-2.34e-01

Pos logit contributions
rob+0.146
 Woo+0.124
bur+0.107
amb+0.104
 Sebastian+0.104
Neg logit contributions
orry-0.076
oke-0.074
run-0.070
ence-0.067
aint-0.066
Token was
Token ID373
Feature activation-3.59e-01

Pos logit contributions
rob+0.010
 Woo+0.008
amb+0.007
bur+0.007
oto+0.006
Neg logit contributions
orry-0.007
run-0.007
oke-0.007
ence-0.007
aint-0.006
Token so
Token ID523
Feature activation-2.29e-01

Pos logit contributions
rob+0.019
 Woo+0.015
amb+0.014
oto+0.013
bur+0.013
Neg logit contributions
run-0.008
orry-0.008
ence-0.007
oke-0.007
 gust-0.006
Token happy
Token ID3772
Feature activation+8.60e-01

Pos logit contributions
rob+0.013
 Woo+0.011
amb+0.010
bur+0.009
 Pink+0.009
Neg logit contributions
orry-0.004
run-0.004
oke-0.004
ence-0.003
aint-0.003
Token that
Token ID326
Feature activation+7.25e-01

Pos logit contributions
orry+0.027
run+0.026
oke+0.026
ence+0.025
aint+0.025
Neg logit contributions
rob-0.034
 Woo-0.028
amb-0.024
bur-0.023
 Pink-0.022
Token record
Token ID1700
Feature activation-5.06e-01

Pos logit contributions
rob+0.014
 Woo+0.012
amb+0.010
 Pink+0.010
thank+0.010
Neg logit contributions
oke-0.011
orry-0.011
run-0.010
ence-0.010
aint-0.009
Token her
Token ID607
Feature activation-6.79e-01

Pos logit contributions
rob+0.018
 Woo+0.015
amb+0.012
 Pink+0.011
bur+0.011
Neg logit contributions
orry-0.018
oke-0.018
run-0.017
ence-0.017
aint-0.017
Token voice
Token ID3809
Feature activation+3.83e-02

Pos logit contributions
rob+0.025
 Woo+0.021
amb+0.018
 Pink+0.017
oto+0.016
Neg logit contributions
oke-0.024
orry-0.023
run-0.022
isel-0.021
ence-0.021
Token with
Token ID351
Feature activation-8.50e-01

Pos logit contributions
orry+0.001
oke+0.001
run+0.001
isel+0.001
ence+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
amb-0.001
 Pink-0.001
thank-0.001
Token her
Token ID607
Feature activation-7.10e-01

Pos logit contributions
rob+0.023
 Woo+0.019
amb+0.014
 Pink+0.013
bur+0.013
Neg logit contributions
orry-0.036
oke-0.036
run-0.035
ence-0.035
aint-0.034
Token toy
Token ID13373
Feature activation-3.05e+00

Pos logit contributions
rob+0.029
 Woo+0.025
amb+0.021
 Pink+0.021
bur+0.020
Neg logit contributions
orry-0.021
oke-0.021
run-0.020
ence-0.020
aint-0.019
Token phone
Token ID3072
Feature activation-9.07e-01

Pos logit contributions
rob+0.123
 Woo+0.108
amb+0.093
 Pink+0.089
bur+0.086
Neg logit contributions
orry-0.090
oke-0.088
run-0.088
ence-0.084
aint-0.081
Token.
Token ID13
Feature activation-3.87e-02

Pos logit contributions
rob+0.033
 Woo+0.028
amb+0.024
 Pink+0.023
bur+0.022
Neg logit contributions
orry-0.030
oke-0.029
run-0.029
ence-0.028
isel-0.027
Token She
Token ID1375
Feature activation-6.13e-01

Pos logit contributions
rob+0.001
 Woo+0.001
 Pink+0.001
amb+0.001
 Cindy+0.001
Neg logit contributions
orry-0.001
oke-0.001
run-0.001
ence-0.001
isel-0.001
Token would
Token ID561
Feature activation-9.13e-01

Pos logit contributions
rob+0.027
 Woo+0.023
amb+0.020
bur+0.019
 Pink+0.019
Neg logit contributions
orry-0.016
run-0.016
oke-0.016
ence-0.016
aint-0.015
Token say
Token ID910
Feature activation-1.06e-01

Pos logit contributions
rob+0.032
 Woo+0.029
amb+0.024
 Pink+0.023
thank+0.023
Neg logit contributions
oke-0.031
orry-0.030
run-0.030
ence-0.028
aint-0.027
Token rag
Token ID34232
Feature activation-9.35e-01

Pos logit contributions
rob+0.020
 Woo+0.017
 Pink+0.013
amb+0.013
 Gloria+0.012
Neg logit contributions
run-0.027
oke-0.027
orry-0.027
ence-0.026
aint-0.025
Token toy
Token ID13373
Feature activation-2.10e+00

Pos logit contributions
rob+0.032
 Woo+0.027
amb+0.022
 Pink+0.022
bur+0.021
Neg logit contributions
orry-0.032
oke-0.032
run-0.032
ence-0.031
aint-0.030
Token was
Token ID373
Feature activation+9.29e-02

Pos logit contributions
rob+0.079
 Woo+0.067
amb+0.056
bur+0.052
 Pink+0.052
Neg logit contributions
orry-0.068
run-0.067
oke-0.067
ence-0.065
aint-0.063
Token free
Token ID1479
Feature activation+5.94e-01

Pos logit contributions
orry+0.003
run+0.003
oke+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.004
 Woo-0.003
amb-0.003
bur-0.003
 Pink-0.003
Token!
Token ID0
Feature activation-2.81e-02

Pos logit contributions
orry+0.018
run+0.018
oke+0.017
ence+0.017
aint+0.016
Neg logit contributions
rob-0.024
 Woo-0.020
amb-0.017
bur-0.016
 Pink-0.016
Token D
Token ID360
Feature activation-3.03e+00

Pos logit contributions
rob+0.001
 Woo+0.001
amb+0.001
 Pink+0.001
bur+0.001
Neg logit contributions
orry-0.001
oke-0.001
run-0.001
ence-0.001
aint-0.001
Tokenolly
Token ID5098
Feature activation-5.68e-01

Pos logit contributions
rob+0.137
 Woo+0.117
bur+0.096
 Sebastian+0.095
amb+0.094
Neg logit contributions
orry-0.084
oke-0.083
run-0.079
ence-0.076
aint-0.074
Token was
Token ID373
Feature activation-4.86e-01

Pos logit contributions
rob+0.020
 Woo+0.017
amb+0.015
 Pink+0.014
bur+0.014
Neg logit contributions
orry-0.019
oke-0.018
run-0.018
ence-0.018
aint-0.017
Token so
Token ID523
Feature activation-2.08e-01

Pos logit contributions
rob+0.020
 Woo+0.016
amb+0.014
bur+0.013
 Pink+0.013
Neg logit contributions
orry-0.016
run-0.015
oke-0.015
ence-0.015
aint-0.014
Token excited
Token ID6568
Feature activation-1.03e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
 Pink+0.007
bur+0.007
Neg logit contributions
orry-0.005
oke-0.005
run-0.005
ence-0.005
aint-0.005
Token and
Token ID290
Feature activation-6.70e-03

Pos logit contributions
rob+0.004
 Woo+0.003
amb+0.003
bur+0.003
 Pink+0.003
Neg logit contributions
orry-0.003
run-0.003
oke-0.003
ence-0.003
aint-0.003
Token it
Token ID340
Feature activation+4.26e-02

Pos logit contributions
rob+0.028
amb+0.022
 Woo+0.022
igi+0.021
bur+0.021
Neg logit contributions
run-0.013
orry-0.012
 triangle-0.012
ence-0.011
aint-0.011
Token.
Token ID13
Feature activation-6.01e-02

Pos logit contributions
run+0.001
orry+0.001
oke+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.002
 Woo-0.002
amb-0.001
bur-0.001
 Sebastian-0.001
Token I
Token ID314
Feature activation-1.32e-01

Pos logit contributions
rob+0.003
 Woo+0.003
amb+0.002
 Pink+0.002
bur+0.002
Neg logit contributions
orry-0.001
run-0.001
oke-0.001
ence-0.001
aint-0.001
Token like
Token ID588
Feature activation+6.18e-01

Pos logit contributions
rob+0.006
 Woo+0.005
amb+0.005
bur+0.005
 Gloria+0.004
Neg logit contributions
orry-0.003
oke-0.003
run-0.003
ence-0.003
aint-0.003
Token your
Token ID534
Feature activation-7.55e-01

Pos logit contributions
orry+0.020
oke+0.020
run+0.020
ence+0.019
aint+0.019
Neg logit contributions
rob-0.023
 Woo-0.020
amb-0.016
 Pink-0.016
bur-0.015
Token toy
Token ID13373
Feature activation-3.02e+00

Pos logit contributions
rob+0.034
 Woo+0.029
amb+0.025
bur+0.025
igi+0.024
Neg logit contributions
orry-0.019
run-0.018
oke-0.018
ence-0.018
 tower-0.017
Token microphone
Token ID21822
Feature activation-4.27e-01

Pos logit contributions
rob+0.134
 Woo+0.115
igi+0.104
bur+0.103
 Lib+0.102
Neg logit contributions
 tower-0.070
orry-0.069
oke-0.068
run-0.066
ence-0.065
Token too
Token ID1165
Feature activation+3.04e-01

Pos logit contributions
rob+0.020
 Woo+0.017
amb+0.015
bur+0.014
 Sebastian+0.014
Neg logit contributions
run-0.011
oke-0.010
orry-0.010
 tower-0.010
ence-0.010
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
orry+0.009
oke+0.009
run+0.009
ence+0.009
aint+0.008
Neg logit contributions
rob-0.013
 Woo-0.011
amb-0.009
bur-0.009
 Pink-0.009
Token It
Token ID632
Feature activation-6.40e-01

Pos logit contributions
rob+0.006
 Woo+0.005
amb+0.005
bur+0.005
 Pink+0.005
Neg logit contributions
orry-0.003
run-0.003
oke-0.003
ence-0.002
aint-0.002
Token is
Token ID318
Feature activation-1.87e-01

Pos logit contributions
rob+0.030
 Woo+0.026
amb+0.023
bur+0.022
 Pink+0.021
Neg logit contributions
orry-0.015
oke-0.015
run-0.015
ence-0.014
aint-0.014
Token sorry
Token ID7926
Feature activation-5.36e-01

Pos logit contributions
orry+0.009
oke+0.009
run+0.009
ence+0.008
aint+0.008
Neg logit contributions
rob-0.026
 Woo-0.023
amb-0.020
 Pink-0.020
bur-0.020
Token,
Token ID11
Feature activation+2.66e-01

Pos logit contributions
rob+0.021
 Woo+0.017
amb+0.015
bur+0.014
 Pink+0.014
Neg logit contributions
orry-0.017
run-0.017
oke-0.017
ence-0.016
aint-0.016
Token Lilly
Token ID35134
Feature activation+7.00e-02

Pos logit contributions
orry+0.009
oke+0.009
run+0.009
ence+0.008
aint+0.008
Neg logit contributions
rob-0.010
 Woo-0.008
amb-0.007
bur-0.007
thank-0.007
Token,"
Token ID553
Feature activation+1.96e-01

Pos logit contributions
orry+0.003
run+0.003
ence+0.003
oke+0.003
aint+0.002
Neg logit contributions
rob-0.002
 Woo-0.002
amb-0.002
 Pink-0.001
bur-0.001
Token said
Token ID531
Feature activation-5.24e-01

Pos logit contributions
orry+0.006
run+0.006
oke+0.006
 tug+0.006
aint+0.006
Neg logit contributions
rob-0.008
 Woo-0.006
amb-0.005
bur-0.005
burn-0.005
Token D
Token ID360
Feature activation-3.01e+00

Pos logit contributions
rob+0.020
 Woo+0.014
amb+0.012
bur+0.012
thank+0.011
Neg logit contributions
orry-0.018
run-0.018
oke-0.017
ence-0.017
aint-0.017
Tokenalia
Token ID9752
Feature activation+2.39e-01

Pos logit contributions
rob+0.108
 Woo+0.086
bur+0.067
amb+0.066
 Pink+0.066
Neg logit contributions
orry-0.108
oke-0.108
run-0.106
ence-0.102
aint-0.101
Token,
Token ID11
Feature activation+5.59e-01

Pos logit contributions
orry+0.008
ence+0.007
oke+0.007
run+0.007
aint+0.007
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
 Pink-0.006
 Gloria-0.006
Token "
Token ID366
Feature activation+2.11e-01

Pos logit contributions
orry+0.018
oke+0.018
ence+0.016
run+0.016
aint+0.016
Neg logit contributions
rob-0.020
 Woo-0.019
 Pink-0.016
amb-0.015
thank-0.015
Tokenbut
Token ID4360
Feature activation+1.41e+00

Pos logit contributions
orry+0.007
oke+0.007
run+0.007
ence+0.007
aint+0.007
Neg logit contributions
rob-0.007
 Woo-0.006
amb-0.005
bur-0.005
 Pink-0.005
Token I
Token ID314
Feature activation-3.45e-02

Pos logit contributions
orry+0.047
oke+0.045
ence+0.045
run+0.044
aint+0.044
Neg logit contributions
rob-0.046
 Woo-0.046
 Pink-0.039
 Cindy-0.036
bur-0.036
Token deer
Token ID20096
Feature activation-5.97e-02

Pos logit contributions
orry+0.015
run+0.015
oke+0.015
ence+0.014
aint+0.014
Neg logit contributions
rob-0.018
 Woo-0.016
amb-0.013
 Pink-0.013
bur-0.012
Token named
Token ID3706
Feature activation-5.58e-01

Pos logit contributions
rob+0.002
 Woo+0.002
 Pink+0.001
amb+0.001
 Sim+0.001
Neg logit contributions
orry-0.002
ence-0.002
aint-0.002
isel-0.002
oke-0.002
Token D
Token ID360
Feature activation-2.04e+00

Pos logit contributions
rob+0.024
amb+0.018
thank+0.017
hat+0.016
 Woo+0.016
Neg logit contributions
run-0.014
orry-0.013
oke-0.013
 Sam-0.013
 eight-0.013
Tokenolly
Token ID5098
Feature activation+5.81e-01

Pos logit contributions
rob+0.083
 Woo+0.065
 Lib+0.054
amb+0.054
thank+0.054
Neg logit contributions
run-0.063
oke-0.063
orry-0.063
aint-0.058
ence-0.057
Token.
Token ID13
Feature activation-4.13e-01

Pos logit contributions
orry+0.023
isel+0.022
ence+0.022
 hour+0.021
oke+0.021
Neg logit contributions
rob-0.015
 Woo-0.015
 Pink-0.013
 Gloria-0.011
 Cindy-0.011
Token D
Token ID360
Feature activation-3.00e+00

Pos logit contributions
rob+0.017
 Woo+0.014
amb+0.012
bur+0.012
thank+0.011
Neg logit contributions
run-0.012
orry-0.012
oke-0.012
ence-0.012
aint-0.011
Tokenolly
Token ID5098
Feature activation+1.60e-01

Pos logit contributions
rob+0.130
 Woo+0.107
bur+0.091
 Lib+0.091
amb+0.091
Neg logit contributions
orry-0.083
oke-0.083
run-0.082
aint-0.074
ence-0.072
Token saw
Token ID2497
Feature activation-2.66e-01

Pos logit contributions
orry+0.005
run+0.005
oke+0.005
ence+0.005
aint+0.005
Neg logit contributions
rob-0.006
 Woo-0.005
amb-0.004
 Pink-0.004
bur-0.004
Token that
Token ID326
Feature activation-6.87e-02

Pos logit contributions
rob+0.012
amb+0.010
thank+0.010
bur+0.009
burn+0.009
Neg logit contributions
run-0.006
orry-0.006
oke-0.006
 ï¿½-0.006
 gust-0.005
Token Benny
Token ID44275
Feature activation-3.62e-02

Pos logit contributions
rob+0.003
amb+0.002
ippy+0.002
lor+0.002
bur+0.002
Neg logit contributions
run-0.002
 ï¿½-0.002
 gust-0.002
oke-0.002
 Sam-0.002
Token was
Token ID373
Feature activation-2.40e-01

Pos logit contributions
rob+0.001
 Woo+0.001
 Pink+0.001
amb+0.001
bur+0.001
Neg logit contributions
orry-0.001
oke-0.001
run-0.001
ence-0.001
aint-0.001
Token good
Token ID922
Feature activation-4.63e-01

Pos logit contributions
rob+0.020
 Woo+0.016
amb+0.016
bur+0.014
oto+0.014
Neg logit contributions
run-0.007
orry-0.007
ence-0.007
oke-0.007
 eight-0.006
Token at
Token ID379
Feature activation+9.14e-01

Pos logit contributions
rob+0.024
 Woo+0.021
bur+0.018
amb+0.018
 Pink+0.018
Neg logit contributions
orry-0.009
run-0.009
oke-0.009
ence-0.008
aint-0.008
Token fixing
Token ID18682
Feature activation+2.13e-01

Pos logit contributions
orry+0.027
oke+0.027
run+0.026
ence+0.026
aint+0.025
Neg logit contributions
rob-0.037
 Woo-0.033
amb-0.027
 Pink-0.027
bur-0.026
Token things
Token ID1243
Feature activation-1.17e-01

Pos logit contributions
run+0.005
orry+0.005
 triangle+0.005
 tug+0.005
 fists+0.005
Neg logit contributions
rob-0.009
 Woo-0.008
amb-0.007
burn-0.007
thank-0.007
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.004
bur+0.004
burn+0.003
Neg logit contributions
run-0.003
oke-0.003
orry-0.003
ence-0.003
aint-0.003
Token D
Token ID360
Feature activation-2.99e+00

Pos logit contributions
oke+0.005
run+0.005
orry+0.005
aint+0.004
ence+0.004
Neg logit contributions
rob-0.011
 Woo-0.008
bur-0.008
burn-0.008
oto-0.007
Tokenolly
Token ID5098
Feature activation-7.74e-03

Pos logit contributions
rob+0.148
 Woo+0.126
bur+0.110
amb+0.109
 Sim+0.106
Neg logit contributions
orry-0.066
oke-0.065
run-0.063
ence-0.058
aint-0.057
Token told
Token ID1297
Feature activation-4.39e-01

Pos logit contributions
rob+0.000
 Woo+0.000
amb+0.000
bur+0.000
burn+0.000
Neg logit contributions
orry-0.000
oke-0.000
run-0.000
ence-0.000
aint-0.000
Token Crab
Token ID32379
Feature activation-5.32e-01

Pos logit contributions
rob+0.020
burn+0.014
robe+0.013
amb+0.013
 therapist+0.013
Neg logit contributions
orry-0.010
 gust-0.010
 ï¿½-0.010
oke-0.010
 eight-0.010
Tokenby
Token ID1525
Feature activation-9.39e-01

Pos logit contributions
rob+0.020
 Woo+0.018
amb+0.015
 Pink+0.014
bur+0.014
Neg logit contributions
orry-0.016
run-0.016
ence-0.016
oke-0.016
aint-0.015
Token about
Token ID546
Feature activation+2.06e-01

Pos logit contributions
rob+0.023
 Woo+0.023
 Pink+0.020
 Rudolph+0.017
 Gloria+0.017
Neg logit contributions
isel-0.036
orry-0.036
ence-0.035
oke-0.035
 gust-0.035
Token river
Token ID7850
Feature activation+4.26e-01

Pos logit contributions
rob+0.000
 Woo+0.000
 Pink+0.000
bur+0.000
amb+0.000
Neg logit contributions
orry-0.000
run-0.000
oke-0.000
ence-0.000
aint-0.000
Token.
Token ID13
Feature activation-3.45e-01

Pos logit contributions
orry+0.016
oke+0.015
ence+0.015
aint+0.015
run+0.015
Neg logit contributions
rob-0.013
 Woo-0.011
thank-0.009
amb-0.009
 Pink-0.009
Token
Token ID220
Feature activation+7.62e-01

Pos logit contributions
rob+0.014
 Woo+0.012
amb+0.010
bur+0.009
 Pink+0.009
Neg logit contributions
orry-0.011
run-0.010
oke-0.010
ence-0.010
aint-0.010
Token
Token ID198
Feature activation-7.00e-01

Pos logit contributions
run+0.025
orry+0.024
oke+0.024
ence+0.023
aint+0.023
Neg logit contributions
rob-0.029
 Woo-0.024
amb-0.020
bur-0.019
 Pink-0.019
Token
Token ID198
Feature activation-4.47e-01

Pos logit contributions
rob+0.028
 Woo+0.024
amb+0.020
bur+0.020
thank+0.019
Neg logit contributions
orry-0.021
oke-0.021
run-0.020
aint-0.019
ence-0.019
TokenT
Token ID51
Feature activation-2.98e+00

Pos logit contributions
rob+0.015
 Woo+0.012
amb+0.010
bur+0.009
 Pink+0.009
Neg logit contributions
orry-0.016
run-0.016
oke-0.016
ence-0.016
aint-0.015
Tokenoby
Token ID26730
Feature activation-1.99e-01

Pos logit contributions
rob+0.123
 Woo+0.105
 Lib+0.093
 Pink+0.091
 Cindy+0.088
Neg logit contributions
oke-0.093
orry-0.085
run-0.082
ever-0.082
 triangle-0.074
Token and
Token ID290
Feature activation+4.75e-01

Pos logit contributions
rob+0.008
 Woo+0.007
amb+0.005
bur+0.005
 Pink+0.005
Neg logit contributions
orry-0.006
oke-0.006
run-0.006
ence-0.006
aint-0.006
Token the
Token ID262
Feature activation-4.65e-01

Pos logit contributions
orry+0.017
oke+0.017
ence+0.017
run+0.016
aint+0.016
Neg logit contributions
rob-0.017
 Woo-0.015
 Pink-0.012
amb-0.012
 Sebastian-0.012
Token duck
Token ID22045
Feature activation+2.12e-01

Pos logit contributions
rob+0.020
 Woo+0.016
amb+0.015
bur+0.014
thank+0.013
Neg logit contributions
orry-0.012
oke-0.012
run-0.012
 tower-0.011
 triangle-0.011
Token soon
Token ID2582
Feature activation+8.27e-03

Pos logit contributions
orry+0.007
oke+0.007
run+0.007
ence+0.007
aint+0.006
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
bur-0.005
 Pink-0.005
Token by
Token ID416
Feature activation+1.14e-01

Pos logit contributions
orry+0.001
run+0.001
ence+0.001
oke+0.000
aint+0.000
Neg logit contributions
rob-0.001
 Woo-0.000
bur-0.000
amb-0.000
thank-0.000
Token himself
Token ID2241
Feature activation-4.67e-01

Pos logit contributions
orry+0.005
run+0.005
oke+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.003
 Woo-0.003
amb-0.002
bur-0.002
 Pink-0.002
Token."
Token ID526
Feature activation-7.19e-01

Pos logit contributions
rob+0.015
 Woo+0.012
amb+0.010
 Pink+0.009
bur+0.009
Neg logit contributions
orry-0.018
run-0.017
oke-0.017
ence-0.017
aint-0.016
Token
Token ID198
Feature activation-4.22e-01

Pos logit contributions
rob+0.028
 Woo+0.024
amb+0.020
 Pink+0.019
bur+0.019
Neg logit contributions
orry-0.023
oke-0.022
run-0.022
ence-0.022
aint-0.021
Token
Token ID198
Feature activation-2.63e-01

Pos logit contributions
rob+0.014
 Woo+0.012
amb+0.010
 Pink+0.009
bur+0.009
Neg logit contributions
orry-0.015
ence-0.015
run-0.015
oke-0.015
aint-0.014
TokenT
Token ID51
Feature activation-2.98e+00

Pos logit contributions
rob+0.008
 Woo+0.006
amb+0.005
 Pink+0.004
bur+0.004
Neg logit contributions
orry-0.011
oke-0.011
run-0.011
ence-0.011
aint-0.010
Tokenami
Token ID6277
Feature activation+1.11e-01

Pos logit contributions
rob+0.123
 Woo+0.106
amb+0.090
 Pink+0.086
bur+0.086
Neg logit contributions
orry-0.086
run-0.085
oke-0.084
ence-0.082
aint-0.079
Token smiled
Token ID13541
Feature activation-4.08e-01

Pos logit contributions
run+0.004
orry+0.004
oke+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.004
 Woo-0.003
amb-0.003
 Pink-0.003
bur-0.003
Token and
Token ID290
Feature activation-1.58e-01

Pos logit contributions
rob+0.018
 Woo+0.014
bur+0.012
igi+0.011
amb+0.011
Neg logit contributions
run-0.012
orry-0.012
ence-0.012
oke-0.012
aint-0.012
Token said
Token ID531
Feature activation-1.66e-01

Pos logit contributions
rob+0.006
 Woo+0.005
bur+0.004
amb+0.004
ippy+0.004
Neg logit contributions
orry-0.005
run-0.005
oke-0.004
 tug-0.004
ence-0.004
Token,
Token ID11
Feature activation-2.12e-01

Pos logit contributions
rob+0.005
 Woo+0.004
 Pink+0.003
amb+0.003
 Lib+0.003
Neg logit contributions
orry-0.007
ence-0.006
oke-0.006
run-0.006
aint-0.006
Token thin
Token ID7888
Feature activation-7.36e-01

Pos logit contributions
rob+0.015
 Woo+0.013
amb+0.011
 Pink+0.011
bur+0.011
Neg logit contributions
orry-0.013
oke-0.013
run-0.013
ence-0.012
aint-0.012
Token.
Token ID13
Feature activation-4.22e-01

Pos logit contributions
rob+0.026
 Woo+0.021
amb+0.018
 Pink+0.017
bur+0.016
Neg logit contributions
orry-0.026
oke-0.026
run-0.025
ence-0.025
aint-0.024
Token
Token ID220
Feature activation+6.48e-01

Pos logit contributions
rob+0.016
 Woo+0.014
amb+0.011
 Pink+0.011
bur+0.011
Neg logit contributions
orry-0.014
oke-0.013
run-0.013
ence-0.013
aint-0.013
Token
Token ID198
Feature activation-8.16e-01

Pos logit contributions
orry+0.023
oke+0.022
run+0.022
ence+0.022
aint+0.021
Neg logit contributions
rob-0.023
 Woo-0.019
amb-0.016
 Pink-0.015
bur-0.015
Token
Token ID198
Feature activation-6.28e-01

Pos logit contributions
rob+0.033
 Woo+0.028
amb+0.024
bur+0.023
 Pink+0.023
Neg logit contributions
orry-0.025
run-0.024
oke-0.024
aint-0.023
ence-0.023
TokenT
Token ID51
Feature activation-2.97e+00

Pos logit contributions
rob+0.022
 Woo+0.018
amb+0.015
bur+0.014
 Pink+0.014
Neg logit contributions
orry-0.022
run-0.022
oke-0.022
ence-0.021
aint-0.021
Tokenoby
Token ID26730
Feature activation-3.11e-01

Pos logit contributions
rob+0.129
 Woo+0.114
 Pink+0.102
 Lib+0.101
 Cindy+0.094
Neg logit contributions
oke-0.084
orry-0.084
run-0.079
ever-0.077
ence-0.072
Token was
Token ID373
Feature activation-3.33e-01

Pos logit contributions
rob+0.012
 Woo+0.010
amb+0.009
bur+0.008
 Pink+0.008
Neg logit contributions
orry-0.010
run-0.010
oke-0.009
ence-0.009
aint-0.009
Token very
Token ID845
Feature activation-1.80e-01

Pos logit contributions
rob+0.012
 Woo+0.011
amb+0.009
 Pink+0.008
bur+0.008
Neg logit contributions
orry-0.011
oke-0.011
run-0.011
ence-0.010
aint-0.010
Token curious
Token ID11040
Feature activation-7.89e-02

Pos logit contributions
rob+0.008
 Woo+0.007
amb+0.006
 Pink+0.006
thank+0.006
Neg logit contributions
orry-0.005
oke-0.005
run-0.005
ence-0.004
aint-0.004
Token and
Token ID290
Feature activation+1.64e-01

Pos logit contributions
rob+0.002
 Woo+0.001
amb+0.001
 Pink+0.001
 Gloria+0.001
Neg logit contributions
orry-0.004
oke-0.003
ence-0.003
isel-0.003
run-0.003
Tokenâ
Token ID22940
Feature activation-1.37e+00

Pos logit contributions
orry+0.006
run+0.005
oke+0.005
ence+0.005
aint+0.005
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
bur-0.006
 Pink-0.006
Token€
Token ID26391
Feature activation-1.05e+00

Pos logit contributions
rob+0.055
 Woo+0.047
amb+0.040
bur+0.038
 Pink+0.038
Neg logit contributions
orry-0.041
run-0.041
oke-0.040
ence-0.039
aint-0.038
Token
Token ID220
Feature activation+8.02e-01

Pos logit contributions
rob+0.041
 Woo+0.036
amb+0.030
bur+0.028
 Pink+0.028
Neg logit contributions
orry-0.032
run-0.031
oke-0.031
ence-0.030
aint-0.029
Token
Token ID198
Feature activation-2.34e-01

Pos logit contributions
orry+0.026
run+0.026
oke+0.026
ence+0.025
aint+0.024
Neg logit contributions
rob-0.030
 Woo-0.025
amb-0.021
bur-0.020
 Pink-0.020
Token
Token ID198
Feature activation-2.57e-01

Pos logit contributions
rob+0.010
 Woo+0.008
amb+0.007
bur+0.007
thank+0.007
Neg logit contributions
run-0.007
oke-0.007
orry-0.006
aint-0.006
ence-0.006
TokenT
Token ID51
Feature activation-2.97e+00

Pos logit contributions
rob+0.010
 Woo+0.009
amb+0.007
bur+0.007
 Pink+0.007
Neg logit contributions
orry-0.008
run-0.008
oke-0.008
ence-0.007
aint-0.007
Tokenoby
Token ID26730
Feature activation-2.85e-01

Pos logit contributions
rob+0.126
 Woo+0.108
 Pink+0.093
 Lib+0.092
bur+0.085
Neg logit contributions
oke-0.086
orry-0.084
run-0.078
ever-0.076
ence-0.075
Token and
Token ID290
Feature activation-9.20e-02

Pos logit contributions
rob+0.010
 Woo+0.008
amb+0.007
thank+0.006
 Pink+0.006
Neg logit contributions
orry-0.010
run-0.010
oke-0.010
ence-0.009
isel-0.009
Token M
Token ID337
Feature activation-1.75e+00

Pos logit contributions
rob+0.004
 Woo+0.003
amb+0.003
 Pink+0.002
bur+0.002
Neg logit contributions
orry-0.003
oke-0.003
run-0.003
ence-0.003
aint-0.003
Tokenilly
Token ID6548
Feature activation+2.23e-01

Pos logit contributions
rob+0.055
 Woo+0.045
amb+0.035
 Pink+0.033
bur+0.033
Neg logit contributions
orry-0.069
oke-0.067
run-0.067
ence-0.066
aint-0.064
Token divided
Token ID9086
Feature activation-4.39e-01

Pos logit contributions
run+0.007
orry+0.007
oke+0.007
ence+0.007
aint+0.007
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
thank-0.005
bur-0.005
Token,
Token ID11
Feature activation+1.00e+00

Pos logit contributions
run+0.004
oke+0.004
orry+0.004
ence+0.004
 tower+0.004
Neg logit contributions
rob-0.006
 Woo-0.005
bur-0.004
 Pink-0.004
igi-0.004
Token raised
Token ID4376
Feature activation+5.33e-01

Pos logit contributions
orry+0.041
oke+0.040
aint+0.039
run+0.038
ence+0.038
Neg logit contributions
rob-0.029
 Woo-0.025
amb-0.018
 Pink-0.018
thank-0.017
Token his
Token ID465
Feature activation+1.73e-01

Pos logit contributions
oke+0.024
orry+0.023
ence+0.022
aint+0.021
run+0.021
Neg logit contributions
rob-0.013
 Woo-0.012
amb-0.008
 Pink-0.008
 Sebastian-0.008
Token arm
Token ID3211
Feature activation-1.19e+00

Pos logit contributions
oke+0.006
orry+0.005
ence+0.005
run+0.005
icker+0.005
Neg logit contributions
rob-0.006
 Woo-0.005
 Pink-0.005
bur-0.004
 brid-0.004
Token and
Token ID290
Feature activation+3.15e-01

Pos logit contributions
rob+0.038
 Woo+0.031
amb+0.026
 Pink+0.023
bur+0.022
Neg logit contributions
orry-0.045
oke-0.045
ence-0.043
run-0.043
aint-0.042
Token SH
Token ID6006
Feature activation+2.70e+00

Pos logit contributions
orry+0.010
oke+0.010
run+0.010
ence+0.010
aint+0.010
Neg logit contributions
rob-0.012
 Woo-0.010
amb-0.008
 Pink-0.008
bur-0.008
TokenOT
Token ID2394
Feature activation+9.65e-01

Pos logit contributions
orry+0.087
oke+0.086
run+0.086
ence+0.083
aint+0.080
Neg logit contributions
rob-0.103
 Woo-0.088
amb-0.073
bur-0.070
 Pink-0.069
Token!
Token ID0
Feature activation+6.56e-01

Pos logit contributions
orry+0.035
oke+0.035
run+0.034
ence+0.034
isel+0.033
Neg logit contributions
rob-0.030
 Woo-0.027
amb-0.021
 Pink-0.020
bur-0.020
Token
Token ID220
Feature activation+1.23e+00

Pos logit contributions
orry+0.019
oke+0.019
ence+0.018
run+0.018
aint+0.017
Neg logit contributions
rob-0.026
 Woo-0.024
amb-0.020
 Pink-0.020
 Sim-0.019
Token
Token ID198
Feature activation+1.15e-01

Pos logit contributions
orry+0.045
ence+0.044
oke+0.044
run+0.044
aint+0.042
Neg logit contributions
rob-0.040
 Woo-0.034
amb-0.027
 Pink-0.025
bur-0.025
Token
Token ID198
Feature activation+3.96e-01

Pos logit contributions
orry+0.004
run+0.004
oke+0.004
ence+0.003
aint+0.003
Neg logit contributions
rob-0.004
 Woo-0.004
amb-0.003
bur-0.003
 Pink-0.003
Token any
Token ID597
Feature activation-7.52e-01

Pos logit contributions
oke+0.014
orry+0.014
run+0.013
ence+0.013
aint+0.013
Neg logit contributions
rob-0.016
 Woo-0.014
 Pink-0.011
bur-0.011
amb-0.011
Token bad
Token ID2089
Feature activation-7.32e-01

Pos logit contributions
rob+0.027
 Woo+0.024
 Pink+0.019
bur+0.018
thank+0.018
Neg logit contributions
oke-0.025
orry-0.025
ence-0.024
run-0.024
aint-0.023
Token dreams
Token ID10625
Feature activation+1.08e+00

Pos logit contributions
rob+0.028
 Woo+0.024
 Pink+0.019
amb+0.019
bur+0.018
Neg logit contributions
run-0.024
orry-0.024
oke-0.024
ence-0.023
aint-0.022
Token or
Token ID393
Feature activation-5.34e-01

Pos logit contributions
orry+0.032
run+0.031
oke+0.031
ence+0.030
aint+0.029
Neg logit contributions
rob-0.044
 Woo-0.037
amb-0.032
bur-0.030
 Pink-0.030
Token scary
Token ID14343
Feature activation-6.23e-01

Pos logit contributions
rob+0.019
 Woo+0.018
 Pink+0.015
bur+0.014
thank+0.014
Neg logit contributions
orry-0.017
oke-0.017
ence-0.016
run-0.016
aint-0.016
Token gor
Token ID30344
Feature activation+2.23e+00

Pos logit contributions
rob+0.023
 Woo+0.020
 Pink+0.016
amb+0.016
thank+0.015
Neg logit contributions
orry-0.021
oke-0.020
ence-0.020
run-0.020
aint-0.019
Tokenillas
Token ID25314
Feature activation+8.86e-01

Pos logit contributions
run+0.067
orry+0.066
aint+0.066
isel+0.062
ence+0.062
Neg logit contributions
rob-0.089
 Woo-0.068
bur-0.067
amb-0.061
ba-0.059
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
orry+0.030
ence+0.029
oke+0.029
run+0.029
isel+0.028
Neg logit contributions
rob-0.031
 Woo-0.027
 Pink-0.022
bur-0.021
amb-0.021
Token<|endoftext|>
Token ID50256
Feature activation-2.49e-01

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.003
 Pink+0.003
bur+0.003
Neg logit contributions
orry-0.005
ence-0.005
oke-0.005
run-0.005
aint-0.004
TokenOnce
Token ID7454
Feature activation-8.55e-01

Pos logit contributions
rob+0.010
 Woo+0.009
amb+0.008
bur+0.007
burn+0.007
Neg logit contributions
oke-0.007
run-0.007
orry-0.007
aint-0.006
ence-0.006
Token upon
Token ID2402
Feature activation-6.06e-01

Pos logit contributions
rob+0.032
 Woo+0.029
amb+0.024
bur+0.024
 Pink+0.024
Neg logit contributions
ence-0.025
orry-0.024
aint-0.024
run-0.023
ever-0.023
Token tall
Token ID7331
Feature activation+7.75e-01

Pos logit contributions
rob+0.021
 Woo+0.018
amb+0.015
 Pink+0.015
bur+0.014
Neg logit contributions
orry-0.015
run-0.015
oke-0.015
ence-0.014
aint-0.014
Token and
Token ID290
Feature activation+8.36e-01

Pos logit contributions
orry+0.024
oke+0.024
run+0.024
ence+0.023
aint+0.022
Neg logit contributions
rob-0.030
 Woo-0.026
amb-0.022
bur-0.020
 Pink-0.020
Token bright
Token ID6016
Feature activation+5.31e-01

Pos logit contributions
oke+0.028
orry+0.028
run+0.027
aint+0.026
ence+0.026
Neg logit contributions
rob-0.030
 Woo-0.026
 Pink-0.022
bur-0.021
 Sim-0.020
Token,
Token ID11
Feature activation+5.86e-01

Pos logit contributions
orry+0.019
oke+0.018
run+0.018
ence+0.018
aint+0.017
Neg logit contributions
rob-0.019
 Woo-0.016
amb-0.014
 Pink-0.013
thank-0.012
Token it
Token ID340
Feature activation+2.90e-02

Pos logit contributions
orry+0.018
oke+0.018
run+0.018
ence+0.018
aint+0.017
Neg logit contributions
rob-0.023
 Woo-0.020
 Pink-0.016
amb-0.016
bur-0.015
Token lit
Token ID6578
Feature activation+2.52e+00

Pos logit contributions
run+0.001
oke+0.001
orry+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
amb-0.001
 Pink-0.001
bur-0.001
Token up
Token ID510
Feature activation+7.58e-01

Pos logit contributions
orry+0.091
ence+0.089
run+0.088
oke+0.087
aint+0.086
Neg logit contributions
rob-0.086
 Woo-0.071
amb-0.058
bur-0.054
 Pink-0.053
Token the
Token ID262
Feature activation+3.44e-01

Pos logit contributions
oke+0.031
run+0.029
orry+0.029
isel+0.028
aint+0.028
Neg logit contributions
rob-0.020
 Woo-0.019
 Pink-0.015
amb-0.014
thank-0.014
Token sky
Token ID6766
Feature activation+9.51e-01

Pos logit contributions
run+0.016
oke+0.014
orry+0.013
aint+0.013
ence+0.013
Neg logit contributions
rob-0.010
 Woo-0.007
 North-0.007
bur-0.006
 Sim-0.006
Token.
Token ID13
Feature activation+5.93e-01

Pos logit contributions
orry+0.037
run+0.037
oke+0.037
isel+0.035
ence+0.034
Neg logit contributions
rob-0.028
 Woo-0.023
amb-0.019
 Pink-0.019
thank-0.019
Token
Token ID198
Feature activation-2.72e-01

Pos logit contributions
orry+0.016
oke+0.016
run+0.016
ence+0.015
aint+0.014
Neg logit contributions
rob-0.025
 Woo-0.023
 Pink-0.019
amb-0.019
 Rudolph-0.018
Token wished
Token ID16555
Feature activation-4.49e-01

Pos logit contributions
orry+0.007
ence+0.007
aint+0.007
run+0.007
ever+0.007
Neg logit contributions
rob-0.009
 Woo-0.009
 Pink-0.007
 Cindy-0.007
 Sim-0.007
Token they
Token ID484
Feature activation-6.50e-01

Pos logit contributions
rob+0.013
 Woo+0.012
 Pink+0.009
 Sim+0.008
 herself+0.008
Neg logit contributions
aint-0.017
orry-0.017
ence-0.017
isel-0.017
oke-0.016
Token had
Token ID550
Feature activation+5.08e-01

Pos logit contributions
rob+0.026
 Woo+0.024
 Pink+0.019
bur+0.019
amb+0.019
Neg logit contributions
oke-0.019
orry-0.019
ence-0.018
run-0.018
aint-0.018
Token never
Token ID1239
Feature activation+2.24e-02

Pos logit contributions
oke+0.018
orry+0.018
run+0.017
ence+0.017
aint+0.016
Neg logit contributions
rob-0.017
 Woo-0.015
bur-0.012
 Pink-0.012
thank-0.012
Token qu
Token ID627
Feature activation+2.82e+00

Pos logit contributions
orry+0.001
oke+0.001
run+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
amb-0.001
bur-0.001
 Pink-0.001
Tokenarre
Token ID9624
Feature activation+2.94e+00

Pos logit contributions
oke+0.081
ence+0.080
 figuring+0.079
 drill+0.079
 tower+0.077
Neg logit contributions
rob-0.100
 Woo-0.089
amb-0.080
burn-0.076
ippy-0.076
Tokenled
Token ID992
Feature activation+1.50e+00

Pos logit contributions
orry+0.120
ence+0.118
run+0.117
oke+0.116
aint+0.115
Neg logit contributions
rob-0.088
 Woo-0.066
amb-0.053
thank-0.052
bur-0.049
Token.
Token ID13
Feature activation+5.73e-01

Pos logit contributions
orry+0.052
oke+0.050
ence+0.049
aint+0.048
run+0.048
Neg logit contributions
rob-0.051
 Woo-0.047
 Pink-0.038
amb-0.037
bur-0.036
Token They
Token ID1119
Feature activation-1.56e-01

Pos logit contributions
run+0.018
oke+0.018
orry+0.018
ence+0.017
isel+0.017
Neg logit contributions
rob-0.020
 Woo-0.019
 Pink-0.016
amb-0.016
 Sim-0.015
Token missed
Token ID6825
Feature activation+1.04e-01

Pos logit contributions
rob+0.005
 Woo+0.005
amb+0.004
 Pink+0.004
bur+0.004
Neg logit contributions
run-0.005
oke-0.005
orry-0.005
ence-0.005
aint-0.005
Token their
Token ID511
Feature activation+3.72e-01

Pos logit contributions
oke+0.004
run+0.004
orry+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.003
 Woo-0.003
 Pink-0.002
 Sebastian-0.002
 Rudolph-0.002
Tokenw
Token ID86
Feature activation-5.38e-01

Pos logit contributions
rob+0.049
 Woo+0.041
amb+0.033
 Pink+0.032
bur+0.031
Neg logit contributions
orry-0.054
oke-0.053
run-0.052
ence-0.051
aint-0.049
Token,
Token ID11
Feature activation-6.15e-02

Pos logit contributions
rob+0.019
 Woo+0.016
amb+0.013
bur+0.012
 Pink+0.012
Neg logit contributions
orry-0.019
run-0.018
oke-0.018
ence-0.018
aint-0.017
Token ow
Token ID12334
Feature activation-6.96e-01

Pos logit contributions
rob+0.002
 Woo+0.002
 Pink+0.002
bur+0.001
 Sebastian+0.001
Neg logit contributions
ence-0.002
run-0.002
orry-0.002
aint-0.002
oke-0.002
Token,
Token ID11
Feature activation+6.65e-01

Pos logit contributions
rob+0.021
 Woo+0.016
amb+0.013
bur+0.012
 Pink+0.012
Neg logit contributions
ence-0.027
run-0.027
orry-0.027
aint-0.026
oke-0.025
Token ow
Token ID12334
Feature activation-4.07e-01

Pos logit contributions
ence+0.024
run+0.024
aint+0.023
orry+0.023
oke+0.023
Neg logit contributions
rob-0.021
 Woo-0.020
 Pink-0.016
bur-0.014
 Dod-0.014
Token!
Token ID0
Feature activation+2.20e+00

Pos logit contributions
rob+0.011
 Woo+0.009
amb+0.007
bur+0.006
 Pink+0.006
Neg logit contributions
ence-0.017
run-0.017
orry-0.017
aint-0.017
oke-0.016
Token That
Token ID1320
Feature activation+5.50e-01

Pos logit contributions
ence+0.073
orry+0.067
pieces+0.064
 hour+0.064
 attempts+0.063
Neg logit contributions
 Woo-0.079
rob-0.069
 Pink-0.065
amb-0.060
 Snow-0.058
Token goose
Token ID37246
Feature activation+1.74e+00

Pos logit contributions
orry+0.015
run+0.015
oke+0.015
ence+0.015
aint+0.014
Neg logit contributions
rob-0.023
 Woo-0.020
amb-0.017
bur-0.016
 Pink-0.016
Token is
Token ID318
Feature activation+7.21e-01

Pos logit contributions
ence+0.065
run+0.062
orry+0.061
aint+0.061
2+0.059
Neg logit contributions
rob-0.054
 Woo-0.045
bur-0.035
 Pink-0.034
amb-0.033
Token mean
Token ID1612
Feature activation-1.98e-01

Pos logit contributions
ence+0.022
run+0.022
oke+0.022
orry+0.022
aint+0.022
Neg logit contributions
rob-0.026
 Woo-0.025
 Pink-0.021
bur-0.020
 Sebastian-0.018
Token and
Token ID290
Feature activation+1.68e-01

Pos logit contributions
rob+0.007
 Woo+0.006
amb+0.005
 Pink+0.005
bur+0.005
Neg logit contributions
run-0.007
orry-0.007
oke-0.007
ence-0.006
aint-0.006
Token
Token ID198
Feature activation-2.13e-01

Pos logit contributions
run+0.023
oke+0.023
orry+0.023
ence+0.022
aint+0.021
Neg logit contributions
rob-0.029
 Woo-0.025
amb-0.021
 Pink-0.020
bur-0.020
Token
Token ID198
Feature activation+4.68e-01

Pos logit contributions
rob+0.009
 Woo+0.007
amb+0.006
burn+0.006
bur+0.006
Neg logit contributions
oke-0.006
run-0.006
orry-0.006
aint-0.006
ence-0.005
TokenThe
Token ID464
Feature activation-4.18e-01

Pos logit contributions
orry+0.015
run+0.015
oke+0.015
ence+0.015
aint+0.014
Neg logit contributions
rob-0.018
 Woo-0.015
amb-0.013
 Pink-0.012
thank-0.012
Token lawyer
Token ID6853
Feature activation+8.26e-01

Pos logit contributions
rob+0.015
 Woo+0.013
thank+0.012
 Lib+0.011
 Pink+0.011
Neg logit contributions
run-0.014
ence-0.014
isel-0.013
orry-0.013
aint-0.013
Token was
Token ID373
Feature activation+1.45e-01

Pos logit contributions
run+0.030
orry+0.030
ence+0.029
oke+0.029
aint+0.028
Neg logit contributions
rob-0.027
 Woo-0.022
amb-0.018
 Pink-0.017
bur-0.017
Token surprised
Token ID6655
Feature activation+6.29e-01

Pos logit contributions
orry+0.004
oke+0.004
run+0.004
ence+0.004
aint+0.004
Neg logit contributions
rob-0.006
 Woo-0.005
amb-0.004
 Pink-0.004
bur-0.004
Token.
Token ID13
Feature activation+3.69e-02

Pos logit contributions
orry+0.024
ence+0.023
oke+0.022
isel+0.022
aint+0.022
Neg logit contributions
rob-0.018
 Woo-0.017
amb-0.015
oto-0.014
 Pink-0.013
Token She
Token ID1375
Feature activation-6.30e-01

Pos logit contributions
orry+0.002
isel+0.001
ence+0.001
oke+0.001
run+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
 Pink-0.001
 Lib-0.001
 Cindy-0.001
Token asked
Token ID1965
Feature activation-4.14e-01

Pos logit contributions
rob+0.024
 Woo+0.020
amb+0.016
bur+0.016
 Pink+0.015
Neg logit contributions
orry-0.021
oke-0.021
run-0.020
ence-0.020
aint-0.019
Token the
Token ID262
Feature activation+4.52e-01

Pos logit contributions
rob+0.014
 Woo+0.012
 Pink+0.010
bur+0.009
 Sim+0.009
Neg logit contributions
orry-0.015
ence-0.014
run-0.014
oke-0.014
aint-0.014
Token man
Token ID582
Feature activation+4.65e-01

Pos logit contributions
run+0.017
isel+0.016
ence+0.016
orry+0.016
aint+0.015
Neg logit contributions
rob-0.013
 Woo-0.011
thank-0.011
 waitress-0.011
 Lib-0.011
Token they
Token ID484
Feature activation-9.66e-01

Pos logit contributions
orry+0.008
oke+0.007
ence+0.007
run+0.007
aint+0.007
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
 Pink-0.006
bur-0.005
Token were
Token ID547
Feature activation-3.66e-01

Pos logit contributions
rob+0.043
 Woo+0.037
amb+0.032
 Pink+0.031
bur+0.031
Neg logit contributions
orry-0.025
run-0.024
oke-0.024
ence-0.024
aint-0.023
Token lucky
Token ID9670
Feature activation+1.73e-01

Pos logit contributions
rob+0.014
 Woo+0.013
 Pink+0.011
amb+0.010
bur+0.010
Neg logit contributions
orry-0.011
oke-0.011
run-0.011
ence-0.011
aint-0.011
Token to
Token ID284
Feature activation+1.38e-01

Pos logit contributions
orry+0.006
ence+0.006
isel+0.006
oke+0.006
run+0.006
Neg logit contributions
rob-0.006
 Woo-0.005
 Pink-0.004
amb-0.004
 Rudolph-0.004
Token have
Token ID423
Feature activation-6.30e-01

Pos logit contributions
orry+0.003
run+0.002
oke+0.002
ence+0.002
aint+0.002
Neg logit contributions
rob-0.007
 Woo-0.006
amb-0.006
thank-0.005
burn-0.005
Token each
Token ID1123
Feature activation+1.36e+00

Pos logit contributions
rob+0.026
 Woo+0.022
amb+0.020
bur+0.018
burn+0.018
Neg logit contributions
run-0.018
orry-0.018
oke-0.017
ence-0.017
aint-0.017
Token other
Token ID584
Feature activation-2.47e-01

Pos logit contributions
orry+0.047
oke+0.046
run+0.046
ence+0.045
aint+0.044
Neg logit contributions
rob-0.049
 Woo-0.041
amb-0.034
bur-0.032
 Pink-0.032
Token,
Token ID11
Feature activation+9.89e-02

Pos logit contributions
rob+0.008
 Woo+0.007
amb+0.006
 Pink+0.006
bur+0.006
Neg logit contributions
orry-0.009
oke-0.009
ence-0.008
run-0.008
aint-0.008
Token and
Token ID290
Feature activation+3.74e-02

Pos logit contributions
orry+0.003
run+0.003
oke+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.004
 Woo-0.003
amb-0.002
bur-0.002
 Pink-0.002
Token that
Token ID326
Feature activation+7.59e-02

Pos logit contributions
orry+0.001
oke+0.001
ence+0.001
aint+0.001
run+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
 Pink-0.001
amb-0.001
 Sebastian-0.001
Token they
Token ID484
Feature activation-8.19e-01

Pos logit contributions
orry+0.003
ence+0.003
oke+0.002
run+0.002
aint+0.002
Neg logit contributions
rob-0.003
 Woo-0.002
 Pink-0.002
amb-0.002
bur-0.002
Token
Token ID198
Feature activation-1.54e-01

Pos logit contributions
rob+0.024
 Woo+0.021
amb+0.018
 Pink+0.017
bur+0.016
Neg logit contributions
orry-0.020
run-0.020
oke-0.020
ence-0.019
aint-0.019
TokenOne
Token ID3198
Feature activation+2.34e-01

Pos logit contributions
rob+0.005
 Woo+0.004
amb+0.003
bur+0.003
 Pink+0.003
Neg logit contributions
oke-0.006
orry-0.006
run-0.006
ence-0.006
aint-0.006
Token day
Token ID1110
Feature activation+8.09e-02

Pos logit contributions
oke+0.008
ence+0.008
run+0.008
orry+0.008
isel+0.008
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
oto-0.005
 Pink-0.005
Token,
Token ID11
Feature activation+9.51e-01

Pos logit contributions
orry+0.003
oke+0.003
run+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.003
 Woo-0.002
amb-0.002
 Pink-0.002
bur-0.002
Token Tim
Token ID5045
Feature activation-2.06e-01

Pos logit contributions
oke+0.028
orry+0.028
ence+0.027
run+0.027
aint+0.026
Neg logit contributions
rob-0.040
 Woo-0.036
 Pink-0.029
amb-0.028
bur-0.028
Tokenmy
Token ID1820
Feature activation+7.99e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.006
 Pink+0.006
 Lib+0.006
Neg logit contributions
orry-0.006
oke-0.006
run-0.005
ence-0.005
aint-0.005
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
orry+0.018
oke+0.018
run+0.016
 tower+0.016
aint+0.016
Neg logit contributions
rob-0.039
 Woo-0.032
amb-0.028
igi-0.028
bur-0.027
Token Max
Token ID5436
Feature activation+4.24e-01

Pos logit contributions
orry+0.032
oke+0.032
run+0.031
ence+0.031
aint+0.029
Neg logit contributions
rob-0.055
 Woo-0.049
amb-0.041
 Pink-0.040
bur-0.040
Token were
Token ID547
Feature activation-3.72e-01

Pos logit contributions
orry+0.009
 tug+0.009
aint+0.009
oke+0.008
ence+0.008
Neg logit contributions
rob-0.022
 Woo-0.016
amb-0.015
igi-0.015
lor-0.015
Token playing
Token ID2712
Feature activation+1.81e-01

Pos logit contributions
rob+0.016
 Woo+0.014
amb+0.012
 Pink+0.012
bur+0.011
Neg logit contributions
oke-0.010
orry-0.010
run-0.010
ence-0.010
aint-0.009
Token in
Token ID287
Feature activation-1.38e-01

Pos logit contributions
oke+0.007
ence+0.007
run+0.007
aint+0.007
orry+0.007
Neg logit contributions
rob-0.006
 Woo-0.005
amb-0.004
 Pink-0.004
thank-0.004
Token world
Token ID995
Feature activation+1.46e+00

Pos logit contributions
rob+0.022
 Woo+0.018
 Pink+0.014
amb+0.014
bur+0.014
Neg logit contributions
run-0.022
orry-0.021
oke-0.021
ence-0.020
isel-0.020
Token
Token ID198
Feature activation+4.76e-02

Pos logit contributions
orry+0.050
run+0.048
oke+0.048
ence+0.048
aint+0.046
Neg logit contributions
rob-0.053
 Woo-0.044
amb-0.036
 Pink-0.034
bur-0.034
TokenWe
Token ID1135
Feature activation-2.03e-01

Pos logit contributions
orry+0.001
oke+0.001
run+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.002
 Woo-0.002
amb-0.002
 Pink-0.002
bur-0.002
Token love
Token ID1842
Feature activation+2.89e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
 Sebastian+0.007
bur+0.007
Neg logit contributions
orry-0.005
ence-0.005
oke-0.005
aint-0.005
run-0.005
Token you
Token ID345
Feature activation+8.55e-01

Pos logit contributions
orry+0.010
oke+0.009
run+0.009
isel+0.009
ence+0.009
Neg logit contributions
rob-0.011
 Woo-0.010
amb-0.008
 Pink-0.008
bur-0.007
Token,
Token ID11
Feature activation+5.24e-01

Pos logit contributions
orry+0.026
oke+0.026
run+0.026
ence+0.025
aint+0.024
Neg logit contributions
rob-0.034
 Woo-0.029
amb-0.024
bur-0.023
 Pink-0.022
Token we
Token ID356
Feature activation+2.57e-01

Pos logit contributions
orry+0.017
run+0.016
oke+0.016
ence+0.016
aint+0.015
Neg logit contributions
rob-0.020
 Woo-0.017
amb-0.014
 Pink-0.014
bur-0.014
Token love
Token ID1842
Feature activation+9.97e-02

Pos logit contributions
orry+0.006
ence+0.006
oke+0.006
aint+0.006
run+0.006
Neg logit contributions
rob-0.012
 Woo-0.010
amb-0.009
bur-0.008
igi-0.008
Token you
Token ID345
Feature activation+8.56e-01

Pos logit contributions
orry+0.003
oke+0.003
run+0.003
ence+0.003
aint+0.003
Neg logit contributions
rob-0.004
 Woo-0.003
amb-0.003
 Pink-0.003
bur-0.003
Token,
Token ID11
Feature activation+6.90e-01

Pos logit contributions
orry+0.025
oke+0.025
run+0.025
ence+0.024
aint+0.024
Neg logit contributions
rob-0.035
 Woo-0.029
amb-0.025
bur-0.024
 Pink-0.023
Token we
Token ID356
Feature activation+3.50e-01

Pos logit contributions
orry+0.023
oke+0.022
run+0.022
ence+0.022
aint+0.021
Neg logit contributions
rob-0.026
 Woo-0.021
amb-0.018
bur-0.017
 Pink-0.017
TokenTom
Token ID13787
Feature activation-3.21e-01

Pos logit contributions
oke+0.007
orry+0.007
run+0.007
aint+0.007
ence+0.007
Neg logit contributions
rob-0.008
 Woo-0.006
amb-0.005
bur-0.005
 Pink-0.005
Token was
Token ID373
Feature activation-5.08e-01

Pos logit contributions
rob+0.015
 Woo+0.012
amb+0.010
 Cindy+0.010
lor+0.010
Neg logit contributions
oke-0.008
orry-0.008
aint-0.007
 tower-0.007
ence-0.007
Token a
Token ID257
Feature activation+2.40e-01

Pos logit contributions
rob+0.025
 Woo+0.021
amb+0.019
bur+0.018
 Pink+0.018
Neg logit contributions
orry-0.012
run-0.011
oke-0.011
ence-0.011
aint-0.010
Token cricket
Token ID18836
Feature activation+3.20e-01

Pos logit contributions
run+0.010
oke+0.008
aint+0.008
orry+0.008
isel+0.008
Neg logit contributions
 Woo-0.008
rob-0.007
 Pink-0.007
 Rudolph-0.006
amb-0.006
Token who
Token ID508
Feature activation+4.25e-01

Pos logit contributions
orry+0.011
run+0.011
oke+0.011
ence+0.010
isel+0.010
Neg logit contributions
rob-0.012
 Woo-0.010
amb-0.008
 Pink-0.008
 Rudolph-0.008
Token liked
Token ID8288
Feature activation+5.92e-01

Pos logit contributions
orry+0.011
run+0.010
oke+0.010
ence+0.010
aint+0.010
Neg logit contributions
rob-0.019
 Woo-0.016
amb-0.014
bur-0.014
burn-0.014
Token to
Token ID284
Feature activation-3.96e-02

Pos logit contributions
oke+0.026
orry+0.025
ence+0.023
isel+0.023
aint+0.022
Neg logit contributions
 Woo-0.016
rob-0.016
 Pink-0.013
oto-0.011
amb-0.011
Token drink
Token ID4144
Feature activation-7.85e-01

Pos logit contributions
rob+0.002
 Woo+0.002
amb+0.001
bur+0.001
 Pink+0.001
Neg logit contributions
orry-0.001
run-0.001
oke-0.001
ence-0.001
aint-0.001
Token juice
Token ID13135
Feature activation-3.77e-01

Pos logit contributions
rob+0.035
 Woo+0.027
bur+0.025
amb+0.025
lor+0.024
Neg logit contributions
run-0.020
aint-0.019
orry-0.019
 tower-0.018
 triangle-0.018
Token.
Token ID13
Feature activation+4.78e-01

Pos logit contributions
rob+0.020
 Woo+0.017
bur+0.016
 Sim+0.016
igi+0.015
Neg logit contributions
 tower-0.005
run-0.005
aint-0.005
oke-0.005
 triangle-0.005
Token He
Token ID679
Feature activation-3.00e-01

Pos logit contributions
orry+0.016
oke+0.016
run+0.015
ence+0.015
aint+0.014
Neg logit contributions
rob-0.017
 Woo-0.015
amb-0.012
 Pink-0.012
 Sebastian-0.012
Token pushing
Token ID7796
Feature activation+2.95e-01

Pos logit contributions
orry+0.004
run+0.004
oke+0.004
ence+0.004
aint+0.003
Neg logit contributions
rob-0.007
 Woo-0.005
amb-0.005
bur-0.005
 Pink-0.005
Token Sammy
Token ID44067
Feature activation+7.07e-01

Pos logit contributions
oke+0.010
orry+0.010
run+0.010
ence+0.010
aint+0.010
Neg logit contributions
rob-0.010
 Woo-0.009
amb-0.007
 Pink-0.007
bur-0.007
Token in
Token ID287
Feature activation+2.49e-01

Pos logit contributions
orry+0.024
oke+0.024
ence+0.023
run+0.023
isel+0.022
Neg logit contributions
rob-0.025
 Woo-0.022
amb-0.018
bur-0.017
 Pink-0.017
Token the
Token ID262
Feature activation+8.19e-01

Pos logit contributions
oke+0.010
orry+0.010
ence+0.009
aint+0.009
isel+0.009
Neg logit contributions
rob-0.007
 Woo-0.007
 Cindy-0.005
 Pink-0.005
 herself-0.005
Token st
Token ID336
Feature activation+1.29e+00

Pos logit contributions
oke+0.040
run+0.039
orry+0.038
ence+0.038
isel+0.037
Neg logit contributions
rob-0.020
 Woo-0.017
 Pink-0.010
bur-0.010
 Cindy-0.009
Tokenroller
Token ID10646
Feature activation-3.29e-01

Pos logit contributions
orry+0.041
ence+0.040
run+0.040
oke+0.039
aint+0.039
Neg logit contributions
rob-0.053
 Woo-0.044
 Pink-0.037
amb-0.036
thank-0.036
Token,
Token ID11
Feature activation+5.15e-01

Pos logit contributions
rob+0.013
 Woo+0.011
amb+0.010
 Pink+0.009
bur+0.009
Neg logit contributions
orry-0.010
run-0.010
oke-0.010
ence-0.010
aint-0.009
Token and
Token ID290
Feature activation+4.15e-01

Pos logit contributions
orry+0.019
oke+0.019
aint+0.018
run+0.018
ence+0.018
Neg logit contributions
rob-0.016
 Woo-0.016
 Pink-0.012
bur-0.011
 Cindy-0.011
Token they
Token ID484
Feature activation-2.39e-01

Pos logit contributions
orry+0.011
run+0.011
oke+0.011
ence+0.011
aint+0.010
Neg logit contributions
rob-0.018
 Woo-0.015
amb-0.013
bur-0.012
 Pink-0.012
Token were
Token ID547
Feature activation-4.56e-01

Pos logit contributions
rob+0.010
 Woo+0.009
amb+0.007
 Pink+0.007
bur+0.007
Neg logit contributions
orry-0.007
run-0.007
oke-0.007
ence-0.006
aint-0.006
Token having
Token ID1719
Feature activation-2.37e-02

Pos logit contributions
rob+0.016
 Woo+0.015
bur+0.012
 Pink+0.012
amb+0.011
Neg logit contributions
oke-0.015
orry-0.015
run-0.014
ence-0.014
aint-0.014
Token with
Token ID351
Feature activation-2.91e-01

Pos logit contributions
rob+0.011
 Woo+0.009
amb+0.007
 Pink+0.007
bur+0.007
Neg logit contributions
orry-0.011
oke-0.011
run-0.011
ence-0.011
aint-0.010
Token beautiful
Token ID4950
Feature activation+2.47e-01

Pos logit contributions
rob+0.011
 Woo+0.009
amb+0.008
bur+0.008
igi+0.007
Neg logit contributions
run-0.009
orry-0.009
ence-0.009
oke-0.009
aint-0.009
Token colors
Token ID7577
Feature activation-6.52e-01

Pos logit contributions
orry+0.008
oke+0.008
run+0.008
ence+0.007
aint+0.007
Neg logit contributions
rob-0.010
 Woo-0.008
amb-0.007
 Pink-0.007
bur-0.006
Token and
Token ID290
Feature activation-3.93e-01

Pos logit contributions
rob+0.024
 Woo+0.020
amb+0.017
bur+0.016
 Pink+0.015
Neg logit contributions
run-0.022
orry-0.022
oke-0.022
ence-0.021
aint-0.020
Token patterns
Token ID7572
Feature activation-7.80e-01

Pos logit contributions
rob+0.015
 Woo+0.013
amb+0.011
 Pink+0.010
bur+0.010
Neg logit contributions
orry-0.012
oke-0.012
run-0.012
ence-0.012
aint-0.011
Token.
Token ID13
Feature activation+4.41e-03

Pos logit contributions
rob+0.032
 Woo+0.028
amb+0.024
bur+0.023
 Pink+0.022
Neg logit contributions
orry-0.022
run-0.022
oke-0.022
ence-0.021
aint-0.021
Token Everyone
Token ID11075
Feature activation+2.74e-01

Pos logit contributions
orry+0.000
ence+0.000
oke+0.000
run+0.000
aint+0.000
Neg logit contributions
rob-0.000
 Woo-0.000
amb-0.000
 Pink-0.000
 Sebastian-0.000
Token loved
Token ID6151
Feature activation+8.62e-02

Pos logit contributions
ence+0.010
aint+0.010
orry+0.010
isel+0.010
run+0.010
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
 dressed-0.005
thank-0.005
Token it
Token ID340
Feature activation-7.92e-01

Pos logit contributions
orry+0.003
oke+0.003
ence+0.003
aint+0.003
isel+0.003
Neg logit contributions
rob-0.003
 Woo-0.002
 Pink-0.002
 Sebastian-0.002
 Cindy-0.002
Token!
Token ID0
Feature activation+9.47e-02

Pos logit contributions
rob+0.028
 Woo+0.023
amb+0.019
bur+0.018
 Pink+0.018
Neg logit contributions
orry-0.028
run-0.027
oke-0.027
ence-0.027
aint-0.026
Token
Token ID220
Feature activation+5.30e-01

Pos logit contributions
orry+0.003
ence+0.003
oke+0.003
run+0.003
aint+0.003
Neg logit contributions
rob-0.003
 Woo-0.003
amb-0.002
 Pink-0.002
bur-0.002
Token was
Token ID373
Feature activation-3.50e-01

Pos logit contributions
oke+0.009
run+0.009
orry+0.009
ence+0.009
aint+0.008
Neg logit contributions
rob-0.010
 Woo-0.008
amb-0.007
 Pink-0.007
bur-0.007
Token so
Token ID523
Feature activation-1.82e-01

Pos logit contributions
rob+0.011
 Woo+0.011
 Pink+0.009
amb+0.008
 Sim+0.008
Neg logit contributions
oke-0.012
run-0.011
orry-0.011
aint-0.011
isel-0.011
Token excited
Token ID6568
Feature activation+3.59e-01

Pos logit contributions
rob+0.008
 Woo+0.007
amb+0.006
 Pink+0.006
bur+0.005
Neg logit contributions
orry-0.005
run-0.005
oke-0.005
ence-0.005
aint-0.005
Token to
Token ID284
Feature activation+5.48e-02

Pos logit contributions
orry+0.010
oke+0.010
run+0.010
ence+0.010
aint+0.009
Neg logit contributions
rob-0.015
 Woo-0.013
amb-0.011
bur-0.011
 Pink-0.010
Token see
Token ID766
Feature activation-2.33e-01

Pos logit contributions
oke+0.002
run+0.002
orry+0.002
ence+0.002
aint+0.002
Neg logit contributions
rob-0.002
 Woo-0.002
amb-0.002
 Pink-0.001
thank-0.001
Token it
Token ID340
Feature activation-4.58e-01

Pos logit contributions
rob+0.013
 Woo+0.011
amb+0.011
thank+0.010
bur+0.010
Neg logit contributions
orry-0.003
run-0.003
oke-0.003
ence-0.003
aint-0.003
Token,
Token ID11
Feature activation-3.13e-01

Pos logit contributions
rob+0.014
 Woo+0.012
 Pink+0.009
amb+0.009
bur+0.009
Neg logit contributions
orry-0.017
oke-0.017
run-0.017
ence-0.016
aint-0.016
Token and
Token ID290
Feature activation+5.25e-01

Pos logit contributions
rob+0.010
 Woo+0.009
 Pink+0.007
amb+0.007
 Cindy+0.007
Neg logit contributions
orry-0.012
oke-0.012
run-0.011
ence-0.011
aint-0.011
Token wanted
Token ID2227
Feature activation-7.86e-01

Pos logit contributions
oke+0.021
orry+0.020
run+0.020
ence+0.020
aint+0.019
Neg logit contributions
rob-0.015
 Woo-0.013
 Pink-0.010
amb-0.010
 Lib-0.010
Token to
Token ID284
Feature activation-6.54e-01

Pos logit contributions
rob+0.033
 Woo+0.029
 Pink+0.024
amb+0.024
bur+0.024
Neg logit contributions
oke-0.022
orry-0.022
run-0.021
ence-0.021
aint-0.020
Token know
Token ID760
Feature activation-8.39e-01

Pos logit contributions
rob+0.028
 Woo+0.024
amb+0.021
 Pink+0.020
bur+0.020
Neg logit contributions
orry-0.018
oke-0.018
run-0.018
ence-0.017
aint-0.016
Tokenting
Token ID889
Feature activation+8.24e-01

Pos logit contributions
rob+0.020
 Woo+0.017
bur+0.014
thank+0.014
amb+0.014
Neg logit contributions
orry-0.020
oke-0.019
aint-0.019
ence-0.019
isel-0.018
Token in
Token ID287
Feature activation-2.89e-02

Pos logit contributions
oke+0.029
orry+0.029
ence+0.027
run+0.027
aint+0.027
Neg logit contributions
rob-0.029
 Woo-0.025
amb-0.020
 Pink-0.020
bur-0.019
Token the
Token ID262
Feature activation+5.91e-01

Pos logit contributions
rob+0.001
 Woo+0.001
 Pink+0.001
amb+0.001
bur+0.001
Neg logit contributions
orry-0.001
oke-0.001
ence-0.001
aint-0.001
run-0.001
Token other
Token ID584
Feature activation-8.87e-01

Pos logit contributions
oke+0.024
run+0.023
orry+0.023
ence+0.021
ever+0.021
Neg logit contributions
rob-0.018
 Woo-0.015
bur-0.012
 Pink-0.011
 North-0.011
Token direction
Token ID4571
Feature activation-5.52e-01

Pos logit contributions
rob+0.032
 Woo+0.027
amb+0.023
bur+0.023
 Pink+0.022
Neg logit contributions
oke-0.029
orry-0.028
run-0.028
ence-0.027
isel-0.026
Token.
Token ID13
Feature activation+1.06e-01

Pos logit contributions
rob+0.016
 Woo+0.014
 Pink+0.011
amb+0.011
 Cindy+0.010
Neg logit contributions
orry-0.021
oke-0.020
ence-0.020
isel-0.019
aint-0.019
Token
Token ID198
Feature activation-2.70e-01

Pos logit contributions
orry+0.004
ence+0.004
oke+0.004
isel+0.004
aint+0.004
Neg logit contributions
rob-0.003
 Woo-0.003
 Pink-0.002
amb-0.002
 Sebastian-0.002
Token
Token ID198
Feature activation+4.03e-03

Pos logit contributions
rob+0.008
 Woo+0.007
amb+0.006
 Pink+0.005
bur+0.005
Neg logit contributions
orry-0.010
ence-0.010
oke-0.010
aint-0.010
run-0.010
TokenThe
Token ID464
Feature activation-1.94e-01

Pos logit contributions
oke+0.000
ence+0.000
orry+0.000
aint+0.000
isel+0.000
Neg logit contributions
rob-0.000
 Woo-0.000
G-0.000
amb-0.000
 Pink-0.000
Token farmer
Token ID18739
Feature activation+9.95e-01

Pos logit contributions
rob+0.006
 Woo+0.005
oto+0.005
bur+0.004
 waitress+0.004
Neg logit contributions
run-0.008
aint-0.007
ence-0.007
oke-0.007
orry-0.007
Token shook
Token ID14682
Feature activation-1.26e-01

Pos logit contributions
orry+0.035
run+0.034
ence+0.034
oke+0.034
aint+0.033
Neg logit contributions
rob-0.033
 Woo-0.027
amb-0.023
bur-0.022
 Pink-0.022
Token it
Token ID340
Feature activation-6.48e-01

Pos logit contributions
oke+0.014
ence+0.014
orry+0.014
run+0.013
aint+0.013
Neg logit contributions
rob-0.012
 Woo-0.011
 Pink-0.008
amb-0.008
bur-0.008
Token disgusting
Token ID23374
Feature activation-6.66e-01

Pos logit contributions
rob+0.024
 Woo+0.022
amb+0.018
 Pink+0.017
burn+0.017
Neg logit contributions
oke-0.021
orry-0.021
ence-0.019
run-0.019
aint-0.019
Token!"
Token ID2474
Feature activation-3.01e-01

Pos logit contributions
rob+0.022
 Woo+0.019
amb+0.015
bur+0.014
 Pink+0.014
Neg logit contributions
orry-0.024
run-0.024
oke-0.024
ence-0.023
aint-0.023
Token Lily
Token ID20037
Feature activation-4.86e-01

Pos logit contributions
rob+0.011
 Woo+0.010
amb+0.008
 Pink+0.008
bur+0.007
Neg logit contributions
orry-0.010
oke-0.010
run-0.010
ence-0.010
aint-0.009
Token said
Token ID531
Feature activation+2.58e-01

Pos logit contributions
rob+0.020
 Woo+0.016
amb+0.014
bur+0.013
 Pink+0.013
Neg logit contributions
orry-0.015
run-0.015
oke-0.014
ence-0.014
aint-0.014
Token,
Token ID11
Feature activation+1.47e-01

Pos logit contributions
orry+0.009
oke+0.009
ence+0.009
run+0.009
aint+0.008
Neg logit contributions
rob-0.009
 Woo-0.008
amb-0.006
 Pink-0.006
bur-0.006
Token sob
Token ID27355
Feature activation+6.57e-01

Pos logit contributions
orry+0.005
oke+0.005
run+0.005
ence+0.004
aint+0.004
Neg logit contributions
rob-0.005
 Woo-0.005
 Pink-0.004
amb-0.004
thank-0.004
Tokenbing
Token ID4623
Feature activation-6.18e-01

Pos logit contributions
orry+0.023
run+0.022
oke+0.022
ence+0.022
aint+0.021
Neg logit contributions
rob-0.023
 Woo-0.020
amb-0.016
 Pink-0.015
bur-0.015
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
rob+0.018
 Woo+0.017
 Pink+0.013
amb+0.013
 herself+0.012
Neg logit contributions
orry-0.024
oke-0.024
ence-0.024
isel-0.023
run-0.023
Token
Token ID198
Feature activation+3.41e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
 Pink+0.007
bur+0.007
Neg logit contributions
orry-0.007
oke-0.007
run-0.007
ence-0.007
aint-0.007
Token
Token ID198
Feature activation+5.40e-01

Pos logit contributions
orry+0.010
oke+0.010
run+0.010
ence+0.010
aint+0.010
Neg logit contributions
rob-0.014
 Woo-0.011
amb-0.010
bur-0.009
 Pink-0.009
Token like
Token ID588
Feature activation-4.02e-02

Pos logit contributions
rob+0.018
 Woo+0.015
amb+0.013
bur+0.012
 Pink+0.012
Neg logit contributions
run-0.011
orry-0.011
oke-0.011
ence-0.011
aint-0.010
Token you
Token ID345
Feature activation+1.35e-01

Pos logit contributions
rob+0.002
 Woo+0.001
amb+0.001
bur+0.001
 Pink+0.001
Neg logit contributions
orry-0.001
run-0.001
oke-0.001
ence-0.001
aint-0.001
Token!"
Token ID2474
Feature activation+3.76e-01

Pos logit contributions
orry+0.005
run+0.005
oke+0.005
ence+0.004
aint+0.004
Neg logit contributions
rob-0.005
 Woo-0.004
amb-0.003
bur-0.003
 Pink-0.003
Token
Token ID198
Feature activation+1.81e-01

Pos logit contributions
orry+0.012
run+0.011
oke+0.011
ence+0.011
aint+0.011
Neg logit contributions
rob-0.015
 Woo-0.013
amb-0.011
 Pink-0.011
bur-0.010
Token
Token ID198
Feature activation+3.74e-01

Pos logit contributions
orry+0.006
oke+0.006
run+0.005
ence+0.005
aint+0.005
Neg logit contributions
rob-0.007
 Woo-0.006
amb-0.005
bur-0.005
 Pink-0.005
TokenB
Token ID33
Feature activation-1.46e+00

Pos logit contributions
orry+0.012
run+0.012
oke+0.012
ence+0.011
aint+0.011
Neg logit contributions
rob-0.015
 Woo-0.013
amb-0.011
 Pink-0.010
bur-0.010
Tokenub
Token ID549
Feature activation-1.25e+00

Pos logit contributions
rob+0.059
 Woo+0.053
amb+0.047
 Pink+0.043
bur+0.043
Neg logit contributions
orry-0.041
ence-0.039
oke-0.039
run-0.038
aint-0.037
Tokenbles
Token ID7689
Feature activation+4.75e-01

Pos logit contributions
rob+0.043
 Woo+0.035
amb+0.028
bur+0.026
 Pink+0.026
Neg logit contributions
orry-0.046
oke-0.045
run-0.045
ence-0.044
aint-0.042
Token replied
Token ID8712
Feature activation-5.04e-01

Pos logit contributions
orry+0.014
oke+0.014
run+0.014
ence+0.014
aint+0.013
Neg logit contributions
rob-0.019
 Woo-0.017
 Pink-0.013
amb-0.013
bur-0.013
Token,
Token ID11
Feature activation-1.99e-01

Pos logit contributions
rob+0.015
 Woo+0.013
 Pink+0.010
amb+0.010
 Gloria+0.009
Neg logit contributions
orry-0.020
oke-0.019
run-0.019
ence-0.019
aint-0.018
Token "
Token ID366
Feature activation-9.50e-02

Pos logit contributions
rob+0.009
 Woo+0.009
 Pink+0.007
amb+0.007
 Rudolph+0.007
Neg logit contributions
orry-0.005
oke-0.004
run-0.004
ence-0.004
aint-0.004
Token help
Token ID1037
Feature activation+3.61e-01

Pos logit contributions
oke+0.001
orry+0.001
ence+0.001
run+0.001
aint+0.001
Neg logit contributions
rob-0.002
 Woo-0.002
amb-0.001
bur-0.001
 Pink-0.001
Token Tommy
Token ID19919
Feature activation-2.20e-01

Pos logit contributions
orry+0.015
oke+0.015
run+0.015
ence+0.014
aint+0.014
Neg logit contributions
rob-0.010
 Woo-0.009
amb-0.007
 Pink-0.006
bur-0.006
Token.
Token ID13
Feature activation+3.52e-01

Pos logit contributions
rob+0.007
 Woo+0.007
amb+0.005
bur+0.005
 Pink+0.005
Neg logit contributions
orry-0.008
oke-0.008
ence-0.007
run-0.007
aint-0.007
Token
Token ID198
Feature activation+3.97e-02

Pos logit contributions
orry+0.010
run+0.010
oke+0.010
ence+0.009
aint+0.009
Neg logit contributions
rob-0.015
 Woo-0.012
amb-0.011
bur-0.010
 Pink-0.010
Token
Token ID198
Feature activation+6.24e-01

Pos logit contributions
oke+0.001
run+0.001
orry+0.001
aint+0.001
ence+0.001
Neg logit contributions
rob-0.002
 Woo-0.001
amb-0.001
thank-0.001
 Pink-0.001
TokenL
Token ID43
Feature activation-1.80e+00

Pos logit contributions
orry+0.018
oke+0.018
run+0.018
ence+0.017
aint+0.017
Neg logit contributions
rob-0.026
 Woo-0.022
amb-0.018
bur-0.018
 Pink-0.018
Tokenily
Token ID813
Feature activation-1.03e-01

Pos logit contributions
rob+0.088
 Woo+0.076
 Pink+0.066
bur+0.066
 Sim+0.066
Neg logit contributions
orry-0.044
oke-0.044
run-0.041
ence-0.034
aint-0.033
Token's
Token ID338
Feature activation+5.08e-01

Pos logit contributions
rob+0.004
 Woo+0.004
amb+0.003
 Pink+0.003
bur+0.003
Neg logit contributions
orry-0.003
oke-0.003
run-0.003
ence-0.003
aint-0.003
Token mom
Token ID1995
Feature activation-7.30e-01

Pos logit contributions
oke+0.017
ence+0.016
run+0.016
orry+0.016
aint+0.015
Neg logit contributions
rob-0.017
 Woo-0.017
burn-0.013
amb-0.013
 Pink-0.013
Tokenmy
Token ID1820
Feature activation+2.33e-01

Pos logit contributions
rob+0.020
 Woo+0.016
bur+0.013
amb+0.012
burn+0.012
Neg logit contributions
orry-0.030
ence-0.030
oke-0.029
aint-0.029
run-0.029
Token was
Token ID373
Feature activation+2.41e-01

Pos logit contributions
orry+0.008
run+0.007
oke+0.007
ence+0.007
aint+0.007
Neg logit contributions
rob-0.009
 Woo-0.007
amb-0.006
 Pink-0.006
bur-0.006
Token toy
Token ID13373
Feature activation-2.42e+00

Pos logit contributions
rob+0.020
 Woo+0.018
amb+0.015
 Pink+0.015
bur+0.013
Neg logit contributions
oke-0.022
orry-0.022
ence-0.022
isel-0.021
run-0.021
Token.
Token ID13
Feature activation+3.49e-01

Pos logit contributions
rob+0.096
 Woo+0.082
amb+0.070
 Pink+0.067
bur+0.065
Neg logit contributions
orry-0.074
oke-0.072
run-0.072
ence-0.070
aint-0.068
Token
Token ID198
Feature activation-8.15e-01

Pos logit contributions
orry+0.012
ence+0.012
run+0.011
oke+0.011
aint+0.011
Neg logit contributions
rob-0.012
 Woo-0.011
amb-0.008
 Pink-0.008
bur-0.008
Token
Token ID198
Feature activation-2.02e-01

Pos logit contributions
rob+0.034
 Woo+0.029
amb+0.025
 Pink+0.024
bur+0.024
Neg logit contributions
oke-0.023
run-0.023
orry-0.022
aint-0.021
ence-0.020
Token"
Token ID1
Feature activation-4.05e-01

Pos logit contributions
rob+0.009
 Woo+0.007
amb+0.006
 Pink+0.006
bur+0.006
Neg logit contributions
orry-0.006
oke-0.006
run-0.005
ence-0.005
aint-0.005
TokenRo
Token ID15450
Feature activation-1.72e+00

Pos logit contributions
rob+0.015
 Woo+0.012
amb+0.011
ippy+0.010
igi+0.010
Neg logit contributions
oke-0.012
orry-0.011
run-0.011
 triangle-0.011
2-0.011
Tokenar
Token ID283
Feature activation+3.16e-01

Pos logit contributions
rob+0.072
 Woo+0.062
amb+0.053
bur+0.051
 Pink+0.051
Neg logit contributions
orry-0.049
run-0.048
oke-0.048
ence-0.046
aint-0.045
Token!"
Token ID2474
Feature activation-7.38e-02

Pos logit contributions
run+0.014
orry+0.014
aint+0.013
ence+0.013
isel+0.013
Neg logit contributions
rob-0.008
 Woo-0.006
amb-0.005
bur-0.004
oto-0.004
Token Tom
Token ID4186
Feature activation-7.80e-01

Pos logit contributions
rob+0.003
 Woo+0.003
amb+0.002
 Pink+0.002
bur+0.002
Neg logit contributions
orry-0.002
run-0.002
oke-0.002
ence-0.002
aint-0.002
Token said
Token ID531
Feature activation+3.68e-01

Pos logit contributions
rob+0.027
 Woo+0.023
amb+0.019
 Pink+0.017
bur+0.017
Neg logit contributions
orry-0.028
oke-0.027
run-0.027
ence-0.027
aint-0.026
Token,
Token ID11
Feature activation+2.88e-01

Pos logit contributions
orry+0.015
oke+0.014
ence+0.014
isel+0.013
aint+0.013
Neg logit contributions
rob-0.009
 Woo-0.009
 Pink-0.007
amb-0.007
 Cindy-0.007
Token big
Token ID1263
Feature activation-6.97e-01

Pos logit contributions
rob+0.008
 Woo+0.008
 Pink+0.006
amb+0.006
 Gloria+0.006
Neg logit contributions
orry-0.006
oke-0.006
run-0.006
ence-0.006
aint-0.006
Token.
Token ID13
Feature activation-1.62e-01

Pos logit contributions
rob+0.022
 Woo+0.018
amb+0.014
 Pink+0.013
bur+0.013
Neg logit contributions
orry-0.027
oke-0.026
run-0.026
ence-0.026
aint-0.025
Token
Token ID220
Feature activation+4.93e-01

Pos logit contributions
rob+0.005
 Woo+0.005
amb+0.004
 Pink+0.004
 Cindy+0.004
Neg logit contributions
orry-0.006
oke-0.006
ence-0.006
run-0.006
isel-0.005
Token
Token ID198
Feature activation-3.52e-01

Pos logit contributions
orry+0.018
oke+0.017
ence+0.017
run+0.017
aint+0.016
Neg logit contributions
rob-0.017
 Woo-0.014
amb-0.011
 Pink-0.011
bur-0.011
Token
Token ID198
Feature activation-8.36e-02

Pos logit contributions
rob+0.013
 Woo+0.011
amb+0.009
 Pink+0.009
bur+0.009
Neg logit contributions
orry-0.012
run-0.012
oke-0.012
ence-0.011
aint-0.011
TokenL
Token ID43
Feature activation-1.78e+00

Pos logit contributions
rob+0.002
 Woo+0.002
amb+0.002
thank+0.002
G+0.002
Neg logit contributions
oke-0.003
run-0.003
orry-0.003
ence-0.003
isel-0.003
Tokenily
Token ID813
Feature activation+6.82e-02

Pos logit contributions
rob+0.071
 Woo+0.060
amb+0.051
bur+0.048
 Pink+0.048
Neg logit contributions
orry-0.054
run-0.053
oke-0.053
ence-0.052
aint-0.050
Token said
Token ID531
Feature activation+3.08e-01

Pos logit contributions
orry+0.002
run+0.002
oke+0.002
ence+0.002
aint+0.002
Neg logit contributions
rob-0.003
 Woo-0.002
amb-0.002
 Pink-0.002
bur-0.002
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
orry+0.013
run+0.013
ence+0.013
oke+0.013
isel+0.012
Neg logit contributions
 Woo-0.007
rob-0.007
 Pink-0.006
 Cindy-0.005
amb-0.005
Token "
Token ID366
Feature activation+2.09e-01

Pos logit contributions
orry+0.000
isel+0.000
 fears+0.000
ence+0.000
oke+0.000
Neg logit contributions
 Woo-0.000
rob-0.000
 Pink-0.000
 Cindy-0.000
 Gab-0.000
TokenWow
Token ID22017
Feature activation+1.66e-01

Pos logit contributions
orry+0.006
run+0.006
oke+0.006
ence+0.006
aint+0.006
Neg logit contributions
rob-0.008
 Woo-0.007
amb-0.006
bur-0.006
 Pink-0.006
Token would
Token ID561
Feature activation-6.83e-01

Pos logit contributions
orry+0.001
run+0.001
oke+0.001
ence+0.001
aint+0.001
Neg logit contributions
rob-0.001
 Woo-0.001
amb-0.001
bur-0.001
 Pink-0.001
Token be
Token ID307
Feature activation+4.98e-01

Pos logit contributions
rob+0.036
 Woo+0.030
amb+0.026
bur+0.025
igi+0.024
Neg logit contributions
run-0.014
orry-0.013
aint-0.013
ence-0.013
 tug-0.013
Token very
Token ID845
Feature activation-2.29e-01

Pos logit contributions
run+0.014
orry+0.014
ence+0.014
aint+0.013
oke+0.013
Neg logit contributions
rob-0.021
 Woo-0.018
amb-0.016
 Pink-0.014
bur-0.014
Token expensive
Token ID5789
Feature activation-1.42e-01

Pos logit contributions
rob+0.009
 Woo+0.008
amb+0.007
 Pink+0.007
bur+0.007
Neg logit contributions
orry-0.007
oke-0.006
run-0.006
ence-0.006
aint-0.006
Token.
Token ID13
Feature activation+1.26e-01

Pos logit contributions
rob+0.007
 Woo+0.006
amb+0.005
bur+0.005
igi+0.005
Neg logit contributions
run-0.003
oke-0.003
ence-0.003
 tower-0.003
orry-0.003
Token Su
Token ID1778
Feature activation-1.84e+00

Pos logit contributions
orry+0.004
oke+0.004
ence+0.004
run+0.004
isel+0.004
Neg logit contributions
rob-0.004
 Woo-0.004
amb-0.003
 Cindy-0.003
 Pink-0.003
Tokenzy
Token ID7357
Feature activation+6.95e-01

Pos logit contributions
rob+0.064
 Woo+0.053
amb+0.044
bur+0.041
 Pink+0.041
Neg logit contributions
orry-0.065
run-0.064
oke-0.064
ence-0.063
aint-0.061
Token felt
Token ID2936
Feature activation-3.00e-01

Pos logit contributions
orry+0.024
oke+0.024
run+0.024
ence+0.023
isel+0.022
Neg logit contributions
rob-0.024
 Woo-0.020
amb-0.017
 Pink-0.016
bur-0.016
Token a
Token ID257
Feature activation+8.46e-01

Pos logit contributions
rob+0.015
 Woo+0.013
amb+0.012
bur+0.011
igi+0.011
Neg logit contributions
orry-0.006
run-0.006
oke-0.006
ence-0.006
aint-0.006
Token bit
Token ID1643
Feature activation+1.91e-01

Pos logit contributions
oke+0.021
orry+0.020
run+0.020
ence+0.019
aint+0.018
Neg logit contributions
rob-0.037
 Woo-0.034
amb-0.029
 Pink-0.028
thank-0.028
Token sad
Token ID6507
Feature activation-6.95e-01

Pos logit contributions
orry+0.005
ence+0.004
oke+0.004
run+0.004
 tower+0.004
Neg logit contributions
rob-0.008
 Woo-0.008
 Pink-0.007
amb-0.007
thank-0.006