TOP ACTIVATIONS
MAX = 0.113

two squirrel s kept qu arre ling until finally Sammy said
mum and understood that qu arre lling was not a good
them and never threw a tant rum again . <|endoftext|> Once
love to have a new hairst yle ". The
In fact , the special bal m made her ankle look
wanted to have a cool hairst yle , but he didn
together . They never qu arre led again . <|endoftext|> Once
on , they never qu arre led again over clothes .
ribbon for being the best bal ancer in the competition .
heal you with a special bal m ". She ran to
on , they never qu arre led again and played together
but today they were qu arre ling . Jenna wanted to
temper and often threw temper tant rums . One day ,
alone , without a cool hairst yle and without a solution
the store and got the bal m . She carefully rubbed
Lily and Jack never qu arre led again . They learned
she was sorry for qu arre ling . From that day
the story is : Qu arre lling over small things is
good friends and never qu arre led again . <|endoftext|> Once
kept crying and throwing a tant rum . Finally

MIN ACTIVATIONS
MIN = -0.116

They said , " L adies and gentlemen , welcome to
. He says " L adies and gentlemen , boys and
they had been there for centuries . The dragon looked at
hurt . He thanked the poss um and hopped away ,
said ' R ever se Mass age '. She pressed the
with lots of food . Them ouse 's mouth watered ,
a few days when the renovations were done . Everyone could
a few days when the renovations were done . Everyone could
olly was a three - year old girl who loved to
oy , mate y ! Land ho !" But
?" asked a three - year - old girl .
day , a three - year - old boy decided to
was an eager 3 - year - old boy who loved
sign that said " F estival Today !" She was very
my was a three - year - old boy who loved
mom and her 3 - year - old daughter decided to
!" shouted her three - year - old son , happy
cube and the 3 - year - old girl were very
. " Ro aaa ar !" she shouted .
said to her 3 - year - old son , "

INTERVAL 0.056 - 0.113
CONTAINS 0.132%

your friend ." S ara is not sure .
very happy . They took turns to sit in the pumpkin
Her dad asked , " Why are you crying ?". Mary
. I don 't like brushes ." L
There was a big shiny crane , with two people operating

INTERVAL -0.002 - 0.056
CONTAINS 55.456%

was playing near the door when his mom my told him
waving her hand and saw some dolphins swimming by in the
sad but he was also excited because he knew his dad
I 'll help you ." Roc co pulled the carrot out
no worry in the world . <|endoftext|> Once upon a time

INTERVAL -0.059 - -0.002
CONTAINS 44.322%

grabbed her arm . Jen started to cry and said "
each other and hug . Fighting is not good . It
Let me go ! Please , I want to go home
day on , Lily learned that it 's okay to make
the cold waves . After a while of ro wing ,

INTERVAL -0.116 - -0.059
CONTAINS 0.089%

her folder ! It was tucked away in the back of
bust le . G illy and Jack looked up
, a little girl was sitting on a seat . She
how . After a few days , Stamp started to like
bird . After a few weeks of rest , the bird
Token two
Token ID734
Feature activation+3.54e-02

Pos logit contributions
bur+0.005
 fourteen+0.005
 blew+0.005
eling+0.005
ps+0.005
Neg logit contributions
and-0.006
urry-0.005
 Follow-0.005
apping-0.005
 Nice-0.005
Token squirrel
Token ID33039
Feature activation-5.90e-04

Pos logit contributions
eling+0.057
 blew+0.055
bur+0.055
 fourteen+0.054
ck+0.053
Neg logit contributions
and-0.054
 Follow-0.046
urry-0.045
 Nice-0.041
 Today-0.040
Tokens
Token ID82
Feature activation-9.64e-03

Pos logit contributions
and+0.001
urry+0.001
 Follow+0.001
 of+0.001
 tum+0.001
Neg logit contributions
bur-0.001
 fourteen-0.001
ps-0.001
eling-0.001
IT-0.001
Token kept
Token ID4030
Feature activation+1.14e-02

Pos logit contributions
and+0.017
 Follow+0.015
urry+0.015
 Nice+0.014
 Today+0.013
Neg logit contributions
bur-0.013
 fourteen-0.012
ps-0.012
 blew-0.012
eling-0.012
Token qu
Token ID627
Feature activation+8.26e-03

Pos logit contributions
 fourteen+0.020
ami+0.019
IT+0.018
ible+0.018
bur+0.018
Neg logit contributions
and-0.014
urry-0.012
 Go-0.012
 Stay-0.012
 of-0.012
Tokenarre
Token ID9624
Feature activation+9.94e-02

Pos logit contributions
bur+0.011
eling+0.011
 fourteen+0.011
ps+0.010
 blew+0.010
Neg logit contributions
and-0.015
 Follow-0.013
urry-0.013
 Nice-0.012
 tum-0.012
Tokenling
Token ID1359
Feature activation+1.29e-02

Pos logit contributions
bur+0.113
 fourteen+0.110
ps+0.100
eling+0.099
 blew+0.099
Neg logit contributions
and-0.201
urry-0.172
 Follow-0.171
apping-0.158
 Nice-0.154
Token until
Token ID1566
Feature activation+1.62e-02

Pos logit contributions
bur+0.017
 fourteen+0.017
eling+0.016
ps+0.016
 blew+0.016
Neg logit contributions
and-0.023
urry-0.020
 Follow-0.020
 Nice-0.018
 tum-0.018
Token finally
Token ID3443
Feature activation+2.18e-02

Pos logit contributions
ps+0.025
cking+0.023
eling+0.023
bur+0.023
ible+0.023
Neg logit contributions
and-0.024
urry-0.023
 tum-0.023
 of-0.022
 birthday-0.021
Token Sammy
Token ID44067
Feature activation+3.99e-02

Pos logit contributions
bur+0.034
eling+0.034
ps+0.034
cking+0.033
 fourteen+0.032
Neg logit contributions
and-0.032
urry-0.030
 Follow-0.027
 tum-0.027
 of-0.027
Token said
Token ID531
Feature activation-2.24e-03

Pos logit contributions
ps+0.059
cking+0.059
bur+0.058
ries+0.058
 fourteen+0.058
Neg logit contributions
and-0.062
urry-0.054
 Follow-0.051
 of-0.049
 tum-0.048
Token mum
Token ID25682
Feature activation+1.05e-02

Pos logit contributions
 fourteen+0.015
ps+0.015
bur+0.014
ck+0.014
 blew+0.014
Neg logit contributions
and-0.019
 Follow-0.016
urry-0.016
 Nice-0.015
apping-0.014
Token and
Token ID290
Feature activation+5.64e-04

Pos logit contributions
bur+0.016
 fourteen+0.016
eling+0.015
ps+0.015
 blew+0.015
Neg logit contributions
and-0.017
urry-0.014
 Follow-0.014
 Nice-0.013
 tum-0.013
Token understood
Token ID7247
Feature activation+1.01e-02

Pos logit contributions
bur+0.001
 fourteen+0.001
eling+0.001
ps+0.001
ible+0.001
Neg logit contributions
and-0.001
urry-0.001
 Follow-0.001
 tum-0.001
 Stay-0.001
Token that
Token ID326
Feature activation-7.70e-03

Pos logit contributions
bur+0.014
 fourteen+0.013
ps+0.013
IT+0.013
rob+0.013
Neg logit contributions
and-0.018
 of-0.015
urry-0.015
 story-0.015
 tum-0.014
Token qu
Token ID627
Feature activation+5.06e-03

Pos logit contributions
and+0.016
 Follow+0.014
urry+0.014
 Nice+0.013
apping+0.013
Neg logit contributions
bur-0.008
 blew-0.007
 fourteen-0.007
eling-0.007
ps-0.007
Tokenarre
Token ID9624
Feature activation+9.79e-02

Pos logit contributions
bur+0.006
eling+0.006
 fourteen+0.006
ps+0.006
 blew+0.006
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
 Nice-0.008
 tum-0.008
Tokenlling
Token ID2680
Feature activation+2.02e-02

Pos logit contributions
bur+0.102
 fourteen+0.099
abi+0.087
ps+0.087
IT+0.086
Neg logit contributions
and-0.208
 Follow-0.178
urry-0.178
 of-0.165
apping-0.165
Token was
Token ID373
Feature activation+1.76e-02

Pos logit contributions
bur+0.032
 fourteen+0.031
eling+0.030
ps+0.029
ck+0.029
Neg logit contributions
and-0.031
urry-0.026
 Follow-0.026
 tum-0.023
 Nice-0.023
Token not
Token ID407
Feature activation+3.14e-02

Pos logit contributions
rob+0.029
bur+0.028
ami+0.026
 fourteen+0.025
ries+0.025
Neg logit contributions
and-0.023
 of-0.022
 welcome-0.022
urry-0.021
 Stay-0.021
Token a
Token ID257
Feature activation-1.76e-03

Pos logit contributions
rob+0.050
bur+0.050
 fourteen+0.047
ami+0.047
eling+0.046
Neg logit contributions
and-0.047
 of-0.042
urry-0.040
 welcome-0.039
 birthday-0.038
Token good
Token ID922
Feature activation+3.38e-02

Pos logit contributions
and+0.003
urry+0.002
 Follow+0.002
 tum+0.002
 Nice+0.002
Neg logit contributions
bur-0.003
eling-0.003
 fourteen-0.003
ps-0.003
ck-0.003
Token them
Token ID606
Feature activation-7.26e-03

Pos logit contributions
and+0.061
urry+0.052
 Follow+0.050
 birthday+0.050
 tum+0.050
Neg logit contributions
bur-0.035
 fourteen-0.034
 blew-0.032
ps-0.031
IT-0.031
Token and
Token ID290
Feature activation-3.36e-03

Pos logit contributions
and+0.013
 Follow+0.011
urry+0.011
 Nice+0.011
 tum+0.010
Neg logit contributions
bur-0.009
 fourteen-0.009
ps-0.009
eling-0.009
 blew-0.008
Token never
Token ID1239
Feature activation-1.25e-02

Pos logit contributions
and+0.006
 Follow+0.005
urry+0.005
 tum+0.005
 Stay+0.005
Neg logit contributions
bur-0.004
 fourteen-0.004
eling-0.004
ps-0.004
ible-0.004
Token threw
Token ID9617
Feature activation+2.99e-02

Pos logit contributions
and+0.022
urry+0.019
 Follow+0.019
 tum+0.017
 Nice+0.017
Neg logit contributions
bur-0.017
 fourteen-0.017
eling-0.016
ps-0.016
ible-0.015
Token a
Token ID257
Feature activation-1.06e-02

Pos logit contributions
bur+0.031
eling+0.031
 fourteen+0.030
 blew+0.030
IT+0.028
Neg logit contributions
and-0.061
urry-0.051
 Follow-0.051
 tum-0.051
 of-0.049
Token tant
Token ID24246
Feature activation+9.69e-02

Pos logit contributions
and+0.020
 Follow+0.019
urry+0.018
 School+0.017
 Today+0.017
Neg logit contributions
bur-0.012
 blew-0.012
 fourteen-0.011
ck-0.011
 comb-0.011
Tokenrum
Token ID6582
Feature activation-3.24e-03

Pos logit contributions
bur+0.150
 fourteen+0.148
 blew+0.148
eling+0.140
IT+0.139
Neg logit contributions
and-0.157
urry-0.126
 Follow-0.116
aring-0.114
apping-0.114
Token again
Token ID757
Feature activation-2.18e-02

Pos logit contributions
and+0.006
urry+0.005
 Follow+0.005
 Nice+0.005
 tum+0.005
Neg logit contributions
bur-0.004
 fourteen-0.004
eling-0.004
ps-0.004
 blew-0.004
Token.
Token ID13
Feature activation+5.87e-03

Pos logit contributions
and+0.036
urry+0.031
 Follow+0.029
 tum+0.028
 of+0.028
Neg logit contributions
bur-0.032
 fourteen-0.031
ps-0.031
eling-0.030
lled-0.030
Token<|endoftext|>
Token ID50256
Feature activation-1.33e-03

Pos logit contributions
bur+0.010
 fourteen+0.010
eling+0.010
ps+0.010
 blew+0.010
Neg logit contributions
and-0.008
urry-0.007
 Follow-0.007
 Nice-0.006
 tum-0.006
TokenOnce
Token ID7454
Feature activation+3.63e-02

Pos logit contributions
and+0.002
urry+0.002
 Follow+0.002
aring+0.002
 tum+0.002
Neg logit contributions
bur-0.002
 fourteen-0.002
ps-0.002
 blew-0.002
IT-0.002
Token love
Token ID1842
Feature activation-1.11e-02

Pos logit contributions
and+0.018
urry+0.015
 Follow+0.015
 Nice+0.014
apping+0.013
Neg logit contributions
bur-0.015
 fourteen-0.015
eling-0.015
ps-0.015
 blew-0.014
Token to
Token ID284
Feature activation+1.96e-02

Pos logit contributions
and+0.018
urry+0.015
 Follow+0.015
 tum+0.013
 Nice+0.013
Neg logit contributions
bur-0.017
 fourteen-0.016
eling-0.016
ps-0.016
 blew-0.016
Token have
Token ID423
Feature activation+1.60e-02

Pos logit contributions
bur+0.029
 fourteen+0.028
eling+0.028
ps+0.028
 blew+0.027
Neg logit contributions
and-0.032
urry-0.027
 Follow-0.027
 Nice-0.024
 tum-0.024
Token a
Token ID257
Feature activation-8.33e-03

Pos logit contributions
bur+0.021
 fourteen+0.020
eling+0.020
ps+0.020
 blew+0.019
Neg logit contributions
and-0.028
 Follow-0.024
urry-0.024
 tum-0.023
 story-0.022
Token new
Token ID649
Feature activation+1.08e-02

Pos logit contributions
and+0.015
 Follow+0.013
urry+0.013
apping+0.012
 Go+0.011
Neg logit contributions
bur-0.011
 blew-0.010
 fourteen-0.010
abi-0.010
ible-0.010
Token hairst
Token ID42658
Feature activation+9.66e-02

Pos logit contributions
bur+0.015
 fourteen+0.014
 blew+0.014
ible+0.014
ps+0.014
Neg logit contributions
and-0.019
urry-0.016
 Follow-0.016
rav-0.015
aring-0.014
Tokenyle
Token ID2349
Feature activation-6.20e-03

Pos logit contributions
 fourteen+0.136
IT+0.133
bur+0.132
 blew+0.130
ps+0.129
Neg logit contributions
and-0.166
apping-0.138
urry-0.134
 Follow-0.131
 of-0.130
Token".
Token ID1911
Feature activation-7.29e-04

Pos logit contributions
and+0.010
urry+0.008
 Follow+0.008
 Nice+0.007
 tum+0.007
Neg logit contributions
bur-0.010
 fourteen-0.009
eling-0.009
ps-0.009
 blew-0.009
Token
Token ID198
Feature activation-1.24e-03

Pos logit contributions
and+0.001
 Follow+0.001
urry+0.001
 Today+0.001
 tum+0.001
Neg logit contributions
eling-0.001
ps-0.001
bur-0.001
cking-0.001
ck-0.001
Token
Token ID198
Feature activation+1.60e-04

Pos logit contributions
and+0.002
 Follow+0.002
urry+0.002
 tum+0.002
 Nice+0.002
Neg logit contributions
bur-0.002
 fourteen-0.002
ck-0.002
eling-0.002
 blew-0.002
TokenThe
Token ID464
Feature activation-5.18e-03

Pos logit contributions
bur+0.000
ps+0.000
 fourteen+0.000
eling+0.000
ible+0.000
Neg logit contributions
and-0.000
 Follow-0.000
urry-0.000
apping-0.000
 Nice-0.000
Token In
Token ID554
Feature activation+3.93e-03

Pos logit contributions
bur+0.022
eling+0.022
ps+0.022
 fourteen+0.022
ck+0.021
Neg logit contributions
and-0.020
urry-0.017
 Follow-0.017
 tum-0.016
 Nice-0.015
Token fact
Token ID1109
Feature activation+2.01e-02

Pos logit contributions
eling+0.005
IT+0.005
ck+0.005
bur+0.005
cking+0.005
Neg logit contributions
 of-0.006
 tum-0.006
and-0.006
 story-0.006
urry-0.006
Token,
Token ID11
Feature activation-3.33e-03

Pos logit contributions
bur+0.047
 fourteen+0.044
ps+0.044
IT+0.044
eling+0.044
Neg logit contributions
and-0.016
urry-0.014
 Follow-0.012
 of-0.011
 tum-0.011
Token the
Token ID262
Feature activation+6.48e-03

Pos logit contributions
and+0.005
 of+0.005
urry+0.005
 tum+0.005
 Follow+0.005
Neg logit contributions
ps-0.005
 fourteen-0.005
bur-0.005
eling-0.005
IT-0.004
Token special
Token ID2041
Feature activation+2.01e-02

Pos logit contributions
bur+0.008
eling+0.008
 blew+0.008
ps+0.008
 fourteen+0.008
Neg logit contributions
and-0.012
urry-0.011
 Follow-0.011
 Nice-0.010
apping-0.010
Token bal
Token ID3652
Feature activation+9.51e-02

Pos logit contributions
 blew+0.025
bur+0.025
eling+0.024
ps+0.023
ible+0.022
Neg logit contributions
and-0.038
 Follow-0.033
urry-0.033
izza-0.030
 Nice-0.030
Tokenm
Token ID76
Feature activation-1.58e-02

Pos logit contributions
bur+0.168
 fourteen+0.161
eling+0.159
 blew+0.157
ps+0.156
Neg logit contributions
and-0.125
 Follow-0.106
urry-0.104
 tum-0.098
 Nice-0.092
Token made
Token ID925
Feature activation-3.28e-03

Pos logit contributions
and+0.025
urry+0.021
 tum+0.020
 Follow+0.019
apping+0.019
Neg logit contributions
 fourteen-0.025
bur-0.024
eling-0.023
IT-0.023
ck-0.023
Token her
Token ID607
Feature activation+6.43e-03

Pos logit contributions
and+0.006
 of+0.006
urry+0.005
 story+0.005
ay+0.005
Neg logit contributions
 fourteen-0.004
bur-0.004
rob-0.004
eling-0.004
ps-0.003
Token ankle
Token ID19847
Feature activation-1.38e-02

Pos logit contributions
bur+0.010
 fourteen+0.010
eling+0.010
ps+0.010
 blew+0.010
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
 Nice-0.007
 tum-0.007
Token look
Token ID804
Feature activation+2.25e-02

Pos logit contributions
and+0.022
urry+0.019
 Follow+0.019
 Nice+0.017
 tum+0.017
Neg logit contributions
bur-0.020
 fourteen-0.020
eling-0.019
ps-0.019
 blew-0.019
Token wanted
Token ID2227
Feature activation-5.77e-03

Pos logit contributions
 fourteen+0.014
bur+0.014
ps+0.013
eling+0.013
cking+0.013
Neg logit contributions
and-0.015
urry-0.013
 Follow-0.013
 tum-0.012
 School-0.012
Token to
Token ID284
Feature activation+2.04e-02

Pos logit contributions
and+0.008
urry+0.007
 Follow+0.007
 Nice+0.006
 tum+0.006
Neg logit contributions
bur-0.010
 fourteen-0.010
eling-0.010
ps-0.010
 blew-0.009
Token have
Token ID423
Feature activation+1.49e-02

Pos logit contributions
bur+0.034
 fourteen+0.034
eling+0.033
ps+0.033
ible+0.032
Neg logit contributions
and-0.029
urry-0.025
 Follow-0.024
 tum-0.022
 Stay-0.022
Token a
Token ID257
Feature activation-7.02e-03

Pos logit contributions
bur+0.020
 fourteen+0.019
eling+0.018
ps+0.018
ami+0.018
Neg logit contributions
and-0.027
 tum-0.023
 story-0.022
 birthday-0.022
urry-0.022
Token cool
Token ID3608
Feature activation+1.13e-02

Pos logit contributions
and+0.012
 Follow+0.010
urry+0.010
 Nice+0.009
apping+0.009
Neg logit contributions
bur-0.010
 fourteen-0.010
eling-0.010
 blew-0.010
ps-0.009
Token hairst
Token ID42658
Feature activation+9.48e-02

Pos logit contributions
bur+0.015
 blew+0.015
ible+0.014
 fourteen+0.014
IT+0.014
Neg logit contributions
and-0.020
 Follow-0.017
urry-0.017
vere-0.016
rav-0.015
Tokenyle
Token ID2349
Feature activation-8.70e-03

Pos logit contributions
 fourteen+0.137
ps+0.132
IT+0.132
 blew+0.130
bur+0.129
Neg logit contributions
and-0.154
apping-0.128
 of-0.125
urry-0.121
 Follow-0.119
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
and+0.015
urry+0.013
 Follow+0.012
 Nice+0.011
 tum+0.011
Neg logit contributions
bur-0.013
 fourteen-0.013
eling-0.012
ps-0.012
 blew-0.012
Token but
Token ID475
Feature activation-4.04e-03

Pos logit contributions
and+0.019
urry+0.017
 Follow+0.017
rav+0.015
apping+0.015
Neg logit contributions
bur-0.016
 fourteen-0.015
eling-0.015
 blew-0.015
ps-0.015
Token he
Token ID339
Feature activation+8.36e-03

Pos logit contributions
and+0.009
urry+0.008
 Follow+0.008
apping+0.007
 Nice+0.007
Neg logit contributions
bur-0.004
 fourteen-0.003
eling-0.003
 blew-0.003
ps-0.003
Token didn
Token ID1422
Feature activation-7.55e-03

Pos logit contributions
 fourteen+0.013
ps+0.013
bur+0.013
eling+0.012
cking+0.012
Neg logit contributions
and-0.013
urry-0.011
 Follow-0.011
 tum-0.010
 Stay-0.010
Token together
Token ID1978
Feature activation+6.83e-03

Pos logit contributions
bur+0.017
 fourteen+0.017
eling+0.016
ps+0.016
 blew+0.016
Neg logit contributions
and-0.027
urry-0.024
 Follow-0.023
 tum-0.022
 Nice-0.022
Token.
Token ID13
Feature activation+1.03e-02

Pos logit contributions
bur+0.010
 fourteen+0.009
eling+0.009
ps+0.009
 blew+0.009
Neg logit contributions
and-0.012
urry-0.010
 Follow-0.010
 tum-0.009
 of-0.009
Token They
Token ID1119
Feature activation+2.04e-02

Pos logit contributions
bur+0.016
 fourteen+0.016
eling+0.015
ps+0.015
 blew+0.015
Neg logit contributions
and-0.016
urry-0.014
 Follow-0.013
 tum-0.012
 Nice-0.012
Token never
Token ID1239
Feature activation-9.08e-03

Pos logit contributions
bur+0.029
 fourteen+0.029
ps+0.028
eling+0.028
ries+0.027
Neg logit contributions
and-0.033
urry-0.029
 Follow-0.029
 tum-0.026
 of-0.026
Token qu
Token ID627
Feature activation+4.21e-03

Pos logit contributions
and+0.018
urry+0.016
 Follow+0.015
 Nice+0.014
 tum+0.014
Neg logit contributions
bur-0.011
 fourteen-0.010
eling-0.010
ps-0.010
 blew-0.010
Tokenarre
Token ID9624
Feature activation+9.46e-02

Pos logit contributions
bur+0.005
 fourteen+0.005
eling+0.005
ps+0.005
 blew+0.005
Neg logit contributions
and-0.008
urry-0.007
 Follow-0.007
 tum-0.006
 Nice-0.006
Tokenled
Token ID992
Feature activation+2.33e-02

Pos logit contributions
bur+0.075
 fourteen+0.070
abi+0.062
eling+0.057
ps+0.057
Neg logit contributions
and-0.228
 Follow-0.197
urry-0.196
apping-0.186
 of-0.185
Token again
Token ID757
Feature activation-2.23e-02

Pos logit contributions
bur+0.034
 fourteen+0.033
eling+0.033
ps+0.032
 blew+0.032
Neg logit contributions
and-0.039
urry-0.033
 Follow-0.032
 Nice-0.030
 tum-0.029
Token.
Token ID13
Feature activation+1.14e-02

Pos logit contributions
and+0.031
urry+0.026
 Follow+0.024
 of+0.023
 story+0.023
Neg logit contributions
bur-0.039
 fourteen-0.038
ps-0.038
eling-0.037
ck-0.036
Token<|endoftext|>
Token ID50256
Feature activation+5.99e-03

Pos logit contributions
bur+0.018
 fourteen+0.018
eling+0.017
ps+0.017
ible+0.017
Neg logit contributions
and-0.017
urry-0.014
 Follow-0.014
 tum-0.013
 Nice-0.013
TokenOnce
Token ID7454
Feature activation+3.79e-02

Pos logit contributions
bur+0.008
 fourteen+0.007
ps+0.007
 blew+0.007
eling+0.007
Neg logit contributions
and-0.011
urry-0.009
 Follow-0.009
 tum-0.009
 Nice-0.008
Token on
Token ID319
Feature activation-7.14e-03

Pos logit contributions
bur+0.017
 fourteen+0.017
ps+0.016
 blew+0.016
eling+0.016
Neg logit contributions
and-0.027
 Follow-0.023
urry-0.023
 Nice-0.021
 tum-0.021
Token,
Token ID11
Feature activation-1.02e-02

Pos logit contributions
and+0.008
urry+0.006
 Follow+0.006
 tum+0.005
 Nice+0.005
Neg logit contributions
bur-0.014
 fourteen-0.014
eling-0.014
ps-0.014
ck-0.014
Token they
Token ID484
Feature activation+2.89e-03

Pos logit contributions
and+0.017
urry+0.014
 of+0.014
 Follow+0.014
 Nice+0.013
Neg logit contributions
bur-0.016
ps-0.015
eling-0.015
cking-0.014
ck-0.014
Token never
Token ID1239
Feature activation-1.23e-02

Pos logit contributions
 fourteen+0.005
ries+0.005
ps+0.005
cking+0.005
eling+0.005
Neg logit contributions
and-0.003
urry-0.003
 of-0.003
 story-0.003
 Follow-0.003
Token qu
Token ID627
Feature activation+1.15e-03

Pos logit contributions
and+0.023
urry+0.021
 Follow+0.020
 tum+0.019
 Nice+0.019
Neg logit contributions
bur-0.015
 fourteen-0.014
ps-0.014
eling-0.014
ck-0.013
Tokenarre
Token ID9624
Feature activation+9.44e-02

Pos logit contributions
bur+0.002
 fourteen+0.002
eling+0.001
ps+0.001
 blew+0.001
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
apping-0.002
 tum-0.002
Tokenled
Token ID992
Feature activation+2.04e-02

Pos logit contributions
bur+0.094
 fourteen+0.089
abi+0.081
ps+0.074
IT+0.072
Neg logit contributions
and-0.213
 Follow-0.176
urry-0.175
 of-0.171
apping-0.170
Token again
Token ID757
Feature activation-2.37e-02

Pos logit contributions
bur+0.031
eling+0.030
 fourteen+0.030
ps+0.030
 blew+0.029
Neg logit contributions
and-0.033
urry-0.027
 Follow-0.027
 of-0.025
 Nice-0.025
Token over
Token ID625
Feature activation+1.12e-02

Pos logit contributions
and+0.037
urry+0.030
 of+0.028
 Follow+0.028
 tum+0.027
Neg logit contributions
bur-0.039
 fourteen-0.038
ps-0.037
eling-0.036
IT-0.035
Token clothes
Token ID8242
Feature activation-1.37e-02

Pos logit contributions
bur+0.015
 fourteen+0.014
ck+0.014
eling+0.014
ps+0.014
Neg logit contributions
and-0.020
urry-0.017
 of-0.016
 tum-0.016
 birthday-0.016
Token.
Token ID13
Feature activation+5.53e-03

Pos logit contributions
and+0.022
urry+0.019
 Follow+0.017
 tum+0.017
apping+0.017
Neg logit contributions
bur-0.021
eling-0.020
 fourteen-0.020
ps-0.020
ck-0.020
Token ribbon
Token ID29092
Feature activation-1.16e-02

Pos logit contributions
 fourteen+0.022
bur+0.022
 blew+0.021
ps+0.021
eling+0.020
Neg logit contributions
and-0.033
urry-0.029
 Follow-0.028
aring-0.025
ooters-0.025
Token for
Token ID329
Feature activation-2.38e-02

Pos logit contributions
and+0.018
urry+0.015
 Follow+0.014
 tum+0.013
 of+0.013
Neg logit contributions
eling-0.018
bur-0.018
 fourteen-0.018
ps-0.017
ible-0.017
Token being
Token ID852
Feature activation-3.45e-02

Pos logit contributions
and+0.051
urry+0.044
 Follow+0.043
 of+0.042
 story+0.042
Neg logit contributions
bur-0.024
 fourteen-0.022
ible-0.021
eling-0.021
 blew-0.021
Token the
Token ID262
Feature activation+8.88e-04

Pos logit contributions
and+0.060
 Follow+0.050
 of+0.048
urry+0.048
 welcome+0.046
Neg logit contributions
bur-0.049
eling-0.048
 fourteen-0.048
IT-0.045
ible-0.044
Token best
Token ID1266
Feature activation+2.25e-02

Pos logit contributions
bur+0.001
 fourteen+0.001
eling+0.001
ps+0.001
ck+0.001
Neg logit contributions
and-0.001
 Follow-0.001
urry-0.001
 tum-0.001
 Nice-0.001
Token bal
Token ID3652
Feature activation+9.43e-02

Pos logit contributions
bur+0.034
 fourteen+0.033
eling+0.033
ps+0.033
ck+0.032
Neg logit contributions
and-0.036
urry-0.031
 Follow-0.030
 tum-0.027
 Nice-0.027
Tokenancer
Token ID8250
Feature activation-5.30e-02

Pos logit contributions
bur+0.182
 fourteen+0.176
eling+0.174
ps+0.171
 blew+0.171
Neg logit contributions
and-0.108
 Follow-0.090
urry-0.088
 tum-0.083
 Nice-0.077
Token in
Token ID287
Feature activation-3.30e-02

Pos logit contributions
and+0.091
urry+0.079
 Follow+0.078
 Nice+0.071
 tum+0.070
Neg logit contributions
bur-0.073
 fourteen-0.071
eling-0.070
ps-0.069
 blew-0.067
Token the
Token ID262
Feature activation+1.44e-03

Pos logit contributions
and+0.062
 of+0.056
urry+0.053
 story+0.052
 welcome+0.052
Neg logit contributions
bur-0.040
eling-0.038
 fourteen-0.037
cking-0.037
ck-0.037
Token competition
Token ID5449
Feature activation+1.70e-02

Pos logit contributions
 blew+0.003
eling+0.002
bur+0.002
ible+0.002
 fourteen+0.002
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
 Nice-0.001
aring-0.001
Token.
Token ID13
Feature activation+2.54e-03

Pos logit contributions
bur+0.022
 fourteen+0.021
eling+0.021
ps+0.021
ck+0.020
Neg logit contributions
and-0.031
urry-0.027
 Follow-0.027
 Nice-0.024
 tum-0.024
Token heal
Token ID12035
Feature activation+8.48e-04

Pos logit contributions
and+0.013
 Follow+0.011
urry+0.011
 Nice+0.010
 tum+0.010
Neg logit contributions
bur-0.017
eling-0.016
 fourteen-0.016
ps-0.016
ck-0.016
Token you
Token ID345
Feature activation-2.03e-02

Pos logit contributions
 fourteen+0.001
bur+0.001
lled+0.001
 blew+0.001
eling+0.001
Neg logit contributions
and-0.001
 Follow-0.001
urry-0.001
 Go-0.001
 Stay-0.001
Token with
Token ID351
Feature activation+9.09e-03

Pos logit contributions
and+0.037
 Follow+0.033
urry+0.032
 Nice+0.031
rav+0.030
Neg logit contributions
ps-0.025
bur-0.025
eling-0.024
 fourteen-0.023
ck-0.023
Token a
Token ID257
Feature activation-6.46e-03

Pos logit contributions
 fourteen+0.012
bur+0.012
lled+0.012
ami+0.012
ps+0.012
Neg logit contributions
and-0.015
urry-0.013
 Follow-0.013
 tum-0.013
 Stay-0.012
Token special
Token ID2041
Feature activation+1.81e-02

Pos logit contributions
and+0.014
 Follow+0.012
urry+0.012
 Nice+0.011
 Go+0.011
Neg logit contributions
bur-0.006
 blew-0.006
eling-0.006
 fourteen-0.006
ps-0.006
Token bal
Token ID3652
Feature activation+9.42e-02

Pos logit contributions
 blew+0.020
bur+0.020
ps+0.019
eling+0.019
 fourteen+0.018
Neg logit contributions
and-0.036
 Follow-0.032
urry-0.031
 Nice-0.029
engu-0.029
Tokenm
Token ID76
Feature activation-1.55e-02

Pos logit contributions
bur+0.160
eling+0.145
ries+0.142
 fourteen+0.142
 blew+0.141
Neg logit contributions
and-0.134
 Follow-0.122
urry-0.114
 tum-0.113
 Nice-0.108
Token".
Token ID1911
Feature activation+5.54e-03

Pos logit contributions
and+0.024
urry+0.021
 Follow+0.020
 tum+0.019
apping+0.019
Neg logit contributions
 fourteen-0.024
bur-0.024
eling-0.022
IT-0.022
ps-0.022
Token She
Token ID1375
Feature activation+1.53e-02

Pos logit contributions
eling+0.010
bur+0.010
ps+0.010
 fourteen+0.010
ck+0.010
Neg logit contributions
and-0.008
urry-0.006
 Follow-0.006
 Today-0.006
 Nice-0.006
Token ran
Token ID4966
Feature activation-2.81e-03

Pos logit contributions
 fourteen+0.018
bur+0.018
eling+0.018
ps+0.017
ible+0.017
Neg logit contributions
and-0.029
 Follow-0.026
urry-0.026
 tum-0.024
 of-0.023
Token to
Token ID284
Feature activation+2.07e-02

Pos logit contributions
and+0.004
urry+0.003
 Follow+0.003
 Nice+0.003
 of+0.003
Neg logit contributions
eling-0.005
bur-0.005
 fourteen-0.005
ible-0.005
cking-0.005
Token on
Token ID319
Feature activation-6.98e-03

Pos logit contributions
bur+0.014
 fourteen+0.014
 blew+0.014
ps+0.013
cking+0.012
Neg logit contributions
and-0.030
 Follow-0.027
engu-0.025
urry-0.025
 Nice-0.025
Token,
Token ID11
Feature activation-7.15e-03

Pos logit contributions
and+0.009
 Follow+0.007
urry+0.007
 Nice+0.006
 Stay+0.006
Neg logit contributions
bur-0.013
 fourteen-0.013
 blew-0.012
eling-0.012
ps-0.012
Token they
Token ID484
Feature activation+1.75e-03

Pos logit contributions
and+0.011
urry+0.010
 of+0.009
 tum+0.009
 birthday+0.009
Neg logit contributions
ps-0.012
eling-0.011
cking-0.011
ck-0.011
bur-0.011
Token never
Token ID1239
Feature activation-1.11e-02

Pos logit contributions
ps+0.003
 fourteen+0.003
ries+0.003
eling+0.003
cking+0.003
Neg logit contributions
and-0.002
urry-0.002
 of-0.002
 Follow-0.002
rav-0.002
Token qu
Token ID627
Feature activation+3.84e-03

Pos logit contributions
and+0.023
 Follow+0.020
urry+0.020
 Nice+0.018
vere+0.018
Neg logit contributions
bur-0.012
 blew-0.011
 fourteen-0.011
eling-0.011
ps-0.011
Tokenarre
Token ID9624
Feature activation+9.42e-02

Pos logit contributions
bur+0.005
 fourteen+0.005
eling+0.005
ps+0.005
 blew+0.004
Neg logit contributions
and-0.007
urry-0.006
 Follow-0.006
 tum-0.006
 Nice-0.006
Tokenled
Token ID992
Feature activation+2.30e-02

Pos logit contributions
bur+0.095
 fourteen+0.092
abi+0.083
ps+0.076
ible+0.075
Neg logit contributions
and-0.210
 Follow-0.174
urry-0.173
apping-0.167
 of-0.167
Token again
Token ID757
Feature activation-2.40e-02

Pos logit contributions
bur+0.036
eling+0.035
 fourteen+0.035
ps+0.034
IT+0.034
Neg logit contributions
and-0.037
urry-0.030
 Follow-0.030
 of-0.028
apping-0.027
Token and
Token ID290
Feature activation-3.96e-03

Pos logit contributions
and+0.037
urry+0.030
 of+0.027
 Follow+0.027
 tum+0.027
Neg logit contributions
bur-0.040
 fourteen-0.039
ps-0.038
eling-0.038
IT-0.036
Token played
Token ID2826
Feature activation+1.07e-02

Pos logit contributions
and+0.007
urry+0.006
 tum+0.006
 Follow+0.006
 Stay+0.006
Neg logit contributions
ps-0.005
bur-0.005
 fourteen-0.005
eling-0.005
cking-0.005
Token together
Token ID1978
Feature activation+3.07e-03

Pos logit contributions
bur+0.016
 fourteen+0.015
eling+0.015
ps+0.014
 blew+0.014
Neg logit contributions
and-0.018
 Follow-0.015
urry-0.015
 tum-0.014
apping-0.014
Token but
Token ID475
Feature activation+4.77e-05

Pos logit contributions
and+0.018
urry+0.015
 Follow+0.014
 Nice+0.014
 tum+0.013
Neg logit contributions
bur-0.017
eling-0.017
ps-0.017
 fourteen-0.017
ck-0.016
Token today
Token ID1909
Feature activation-5.65e-02

Pos logit contributions
ps+0.000
bur+0.000
eling+0.000
 fourteen+0.000
cking+0.000
Neg logit contributions
and-0.000
urry-0.000
 Follow-0.000
 Today-0.000
 Nice-0.000
Token they
Token ID484
Feature activation+8.34e-03

Pos logit contributions
and+0.093
urry+0.083
 of+0.079
 Follow+0.079
 tum+0.078
Neg logit contributions
bur-0.081
ps-0.080
 fourteen-0.078
eling-0.078
cking-0.075
Token were
Token ID547
Feature activation+6.38e-03

Pos logit contributions
bur+0.014
 fourteen+0.014
ps+0.014
cking+0.013
eling+0.013
Neg logit contributions
and-0.011
urry-0.010
 Follow-0.009
 tum-0.009
 of-0.009
Token qu
Token ID627
Feature activation+2.19e-03

Pos logit contributions
bur+0.009
 fourteen+0.009
eling+0.008
ible+0.008
ps+0.008
Neg logit contributions
and-0.011
urry-0.009
 Follow-0.009
 of-0.009
apping-0.009
Tokenarre
Token ID9624
Feature activation+9.40e-02

Pos logit contributions
bur+0.003
 fourteen+0.003
ps+0.003
eling+0.003
 blew+0.003
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
apping-0.003
aring-0.003
Tokenling
Token ID1359
Feature activation+5.21e-03

Pos logit contributions
bur+0.108
 fourteen+0.105
abi+0.094
IT+0.090
ible+0.089
Neg logit contributions
and-0.194
urry-0.160
 Follow-0.159
apping-0.155
 of-0.154
Token.
Token ID13
Feature activation+4.83e-03

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
 blew+0.006
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
 tum-0.008
 Nice-0.008
Token Jenna
Token ID45377
Feature activation+8.28e-03

Pos logit contributions
bur+0.008
ps+0.008
eling+0.008
 fourteen+0.008
ck+0.008
Neg logit contributions
and-0.007
urry-0.006
 Follow-0.006
 Today-0.005
 Nice-0.005
Token wanted
Token ID2227
Feature activation-8.15e-03

Pos logit contributions
ps+0.012
bur+0.012
 fourteen+0.011
cking+0.011
eling+0.011
Neg logit contributions
and-0.013
urry-0.012
 Follow-0.011
 tum-0.011
 of-0.011
Token to
Token ID284
Feature activation+1.99e-02

Pos logit contributions
and+0.010
urry+0.008
 Follow+0.007
 tum+0.007
 of+0.007
Neg logit contributions
eling-0.015
bur-0.015
ps-0.015
 fourteen-0.015
cking-0.015
Token temper
Token ID4124
Feature activation+2.09e-02

Pos logit contributions
bur+0.022
 fourteen+0.021
eling+0.021
ps+0.021
 blew+0.020
Neg logit contributions
and-0.022
urry-0.019
 Follow-0.019
 Nice-0.017
 tum-0.017
Token and
Token ID290
Feature activation-9.85e-05

Pos logit contributions
bur+0.029
 fourteen+0.028
eling+0.028
ps+0.028
 blew+0.027
Neg logit contributions
and-0.035
urry-0.031
 Follow-0.031
 Nice-0.028
 tum-0.028
Token often
Token ID1690
Feature activation-1.57e-02

Pos logit contributions
and+0.000
urry+0.000
 Follow+0.000
 tum+0.000
 Nice+0.000
Neg logit contributions
bur-0.000
 fourteen-0.000
eling-0.000
ps-0.000
 blew-0.000
Token threw
Token ID9617
Feature activation+3.32e-02

Pos logit contributions
and+0.029
urry+0.025
 Follow+0.025
 tum+0.023
 Stay+0.023
Neg logit contributions
bur-0.020
 fourteen-0.019
ps-0.018
eling-0.018
cking-0.018
Token temper
Token ID4124
Feature activation+2.12e-02

Pos logit contributions
bur+0.039
 fourteen+0.038
eling+0.037
ps+0.036
 blew+0.036
Neg logit contributions
and-0.065
urry-0.055
 Follow-0.055
 tum-0.052
 Nice-0.051
Token tant
Token ID24246
Feature activation+9.38e-02

Pos logit contributions
bur+0.032
 fourteen+0.031
eling+0.030
ps+0.029
 blew+0.029
Neg logit contributions
and-0.035
urry-0.029
 Follow-0.029
 tum-0.026
 Nice-0.026
Tokenrums
Token ID45241
Feature activation+5.10e-03

Pos logit contributions
bur+0.146
 blew+0.146
 fourteen+0.145
eling+0.134
IT+0.133
Neg logit contributions
and-0.152
urry-0.120
 Follow-0.113
aring-0.108
apping-0.105
Token.
Token ID13
Feature activation+3.55e-03

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
 blew+0.005
Neg logit contributions
and-0.010
urry-0.009
 Follow-0.009
 Nice-0.008
 tum-0.008
Token One
Token ID1881
Feature activation-2.64e-02

Pos logit contributions
 fourteen+0.005
bur+0.005
eling+0.005
IT+0.005
ps+0.005
Neg logit contributions
and-0.005
urry-0.005
 Follow-0.005
rav-0.004
apping-0.004
Token day
Token ID1110
Feature activation+1.50e-02

Pos logit contributions
and+0.037
 Follow+0.032
urry+0.030
vere+0.029
rav+0.027
Neg logit contributions
 blew-0.045
bur-0.044
eling-0.042
 fourteen-0.042
ible-0.042
Token,
Token ID11
Feature activation-5.22e-03

Pos logit contributions
bur+0.026
 fourteen+0.026
eling+0.025
ps+0.025
 blew+0.025
Neg logit contributions
and-0.020
urry-0.017
 Follow-0.017
 tum-0.015
 Nice-0.015
Token alone
Token ID3436
Feature activation-6.94e-03

Pos logit contributions
and+0.065
urry+0.057
 Follow+0.056
 Nice+0.051
 tum+0.051
Neg logit contributions
bur-0.052
 fourteen-0.051
eling-0.050
ps-0.049
 blew-0.048
Token,
Token ID11
Feature activation-7.13e-03

Pos logit contributions
and+0.011
urry+0.009
 Follow+0.009
 tum+0.008
 Nice+0.008
Neg logit contributions
bur-0.010
 fourteen-0.010
eling-0.010
ps-0.010
 blew-0.010
Token without
Token ID1231
Feature activation+3.38e-02

Pos logit contributions
and+0.012
urry+0.010
 Follow+0.010
 tum+0.009
 Nice+0.009
Neg logit contributions
bur-0.010
 fourteen-0.010
eling-0.010
ps-0.010
ible-0.010
Token a
Token ID257
Feature activation-8.32e-03

Pos logit contributions
bur+0.038
 fourteen+0.036
IT+0.034
ami+0.034
 blew+0.034
Neg logit contributions
and-0.065
urry-0.057
 tum-0.055
 Stay-0.054
 Follow-0.054
Token cool
Token ID3608
Feature activation+9.08e-03

Pos logit contributions
and+0.014
 Follow+0.012
urry+0.012
 Go+0.011
 School+0.011
Neg logit contributions
 blew-0.011
bur-0.011
 fourteen-0.011
ps-0.010
eling-0.010
Token hairst
Token ID42658
Feature activation+9.37e-02

Pos logit contributions
bur+0.014
 blew+0.013
 fourteen+0.013
ps+0.013
ck+0.012
Neg logit contributions
and-0.015
 Follow-0.013
urry-0.012
vere-0.011
 Go-0.011
Tokenyle
Token ID2349
Feature activation-1.10e-03

Pos logit contributions
IT+0.141
 fourteen+0.139
ible+0.135
bur+0.133
 blew+0.132
Neg logit contributions
and-0.149
apping-0.129
 of-0.121
urry-0.117
vere-0.113
Token and
Token ID290
Feature activation-9.50e-03

Pos logit contributions
and+0.002
urry+0.002
 Follow+0.002
 Nice+0.001
 tum+0.001
Neg logit contributions
bur-0.002
 fourteen-0.002
eling-0.001
ps-0.001
 blew-0.001
Token without
Token ID1231
Feature activation+3.74e-02

Pos logit contributions
and+0.017
 Follow+0.015
 tum+0.015
urry+0.015
 of+0.014
Neg logit contributions
bur-0.012
 fourteen-0.011
eling-0.011
ami-0.010
ible-0.010
Token a
Token ID257
Feature activation-9.76e-03

Pos logit contributions
bur+0.043
 fourteen+0.041
ami+0.041
rob+0.040
IT+0.040
Neg logit contributions
and-0.068
urry-0.059
 welcome-0.058
 tum-0.058
 Stay-0.056
Token solution
Token ID4610
Feature activation+2.44e-02

Pos logit contributions
and+0.015
urry+0.013
 Follow+0.012
 tum+0.011
 Nice+0.011
Neg logit contributions
bur-0.015
 fourteen-0.015
eling-0.015
ps-0.015
ck-0.014
Token the
Token ID262
Feature activation+3.68e-03

Pos logit contributions
 fourteen+0.032
ible+0.031
rob+0.030
cking+0.029
lled+0.029
Neg logit contributions
and-0.034
urry-0.031
 welcome-0.029
 Follow-0.029
 of-0.028
Token store
Token ID3650
Feature activation+9.27e-03

Pos logit contributions
bur+0.005
eling+0.005
 blew+0.005
 fourteen+0.004
ps+0.004
Neg logit contributions
and-0.007
urry-0.006
 Follow-0.006
 Nice-0.005
rav-0.005
Token and
Token ID290
Feature activation-4.00e-03

Pos logit contributions
bur+0.012
 fourteen+0.011
 blew+0.011
ps+0.011
eling+0.010
Neg logit contributions
and-0.017
 Follow-0.015
urry-0.015
 Nice-0.014
rav-0.014
Token got
Token ID1392
Feature activation+2.85e-02

Pos logit contributions
and+0.007
urry+0.006
 Follow+0.006
 tum+0.006
 of+0.006
Neg logit contributions
 fourteen-0.005
ps-0.005
eling-0.005
ible-0.005
bur-0.005
Token the
Token ID262
Feature activation+4.47e-03

Pos logit contributions
bur+0.027
 fourteen+0.026
eling+0.025
ps+0.025
 blew+0.024
Neg logit contributions
and-0.061
urry-0.055
 Follow-0.055
 Nice-0.051
 tum-0.051
Token bal
Token ID3652
Feature activation+9.37e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.005
ps+0.005
 blew+0.005
Neg logit contributions
and-0.008
urry-0.007
 Follow-0.007
 tum-0.006
 Nice-0.006
Tokenm
Token ID76
Feature activation-1.66e-02

Pos logit contributions
bur+0.129
eling+0.117
 fourteen+0.115
 blew+0.115
ries+0.112
Neg logit contributions
and-0.160
 Follow-0.147
urry-0.143
 tum-0.140
 Nice-0.134
Token.
Token ID13
Feature activation+6.48e-03

Pos logit contributions
and+0.025
urry+0.022
 Follow+0.020
 tum+0.020
apping+0.019
Neg logit contributions
bur-0.026
 fourteen-0.026
eling-0.025
ps-0.025
IT-0.025
Token She
Token ID1375
Feature activation+1.35e-02

Pos logit contributions
bur+0.010
eling+0.010
 fourteen+0.010
ps+0.010
ck+0.010
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
 tum-0.008
 Nice-0.007
Token carefully
Token ID7773
Feature activation+7.72e-05

Pos logit contributions
 fourteen+0.016
bur+0.015
ps+0.015
eling+0.015
IT+0.014
Neg logit contributions
and-0.026
urry-0.023
 Follow-0.023
 tum-0.022
 Stay-0.021
Token rubbed
Token ID31862
Feature activation+4.19e-02

Pos logit contributions
 fourteen+0.000
bur+0.000
eling+0.000
ible+0.000
cks+0.000
Neg logit contributions
and-0.000
urry-0.000
 tum-0.000
 Follow-0.000
 of-0.000
Token Lily
Token ID20037
Feature activation+1.57e-02

Pos logit contributions
and+0.005
 of+0.005
urry+0.005
 Follow+0.004
 tum+0.004
Neg logit contributions
bur-0.006
ps-0.006
eling-0.006
cking-0.005
ck-0.005
Token and
Token ID290
Feature activation-2.30e-03

Pos logit contributions
eling+0.027
cking+0.026
bur+0.026
 fourteen+0.026
ck+0.026
Neg logit contributions
and-0.021
 Follow-0.018
urry-0.017
 of-0.017
 story-0.016
Token Jack
Token ID3619
Feature activation+1.08e-02

Pos logit contributions
and+0.002
urry+0.002
 Stay+0.002
 School+0.002
 Today+0.002
Neg logit contributions
ps-0.004
cking-0.004
bur-0.004
 fourteen-0.004
ck-0.004
Token never
Token ID1239
Feature activation-9.57e-03

Pos logit contributions
eling+0.019
ries+0.019
cking+0.019
bur+0.019
 fourteen+0.018
Neg logit contributions
and-0.013
urry-0.011
 of-0.011
 Follow-0.010
 story-0.010
Token qu
Token ID627
Feature activation+5.53e-03

Pos logit contributions
and+0.019
urry+0.017
 Follow+0.017
 tum+0.015
 Nice+0.015
Neg logit contributions
bur-0.011
 fourteen-0.010
eling-0.010
ps-0.010
ck-0.010
Tokenarre
Token ID9624
Feature activation+9.36e-02

Pos logit contributions
bur+0.008
 fourteen+0.007
eling+0.007
ps+0.007
 blew+0.007
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
apping-0.008
 tum-0.008
Tokenled
Token ID992
Feature activation+2.26e-02

Pos logit contributions
bur+0.097
 fourteen+0.092
abi+0.084
 afar+0.076
ps+0.076
Neg logit contributions
and-0.208
urry-0.170
 Follow-0.170
 of-0.168
apping-0.167
Token again
Token ID757
Feature activation-2.24e-02

Pos logit contributions
bur+0.038
eling+0.037
 fourteen+0.036
ps+0.036
IT+0.035
Neg logit contributions
and-0.035
urry-0.027
 of-0.027
 Follow-0.027
apping-0.025
Token.
Token ID13
Feature activation+9.59e-03

Pos logit contributions
and+0.034
urry+0.027
 of+0.025
apping+0.025
 story+0.024
Neg logit contributions
bur-0.040
 fourteen-0.038
ps-0.037
eling-0.037
rob-0.035
Token They
Token ID1119
Feature activation+1.81e-02

Pos logit contributions
eling+0.019
bur+0.019
ps+0.018
ck+0.018
cking+0.018
Neg logit contributions
and-0.013
urry-0.010
 Follow-0.009
 Nice-0.009
 Today-0.008
Token learned
Token ID4499
Feature activation-2.14e-02

Pos logit contributions
ries+0.035
ps+0.033
cking+0.033
 fourteen+0.033
bur+0.033
Neg logit contributions
and-0.019
urry-0.018
 Follow-0.016
 of-0.016
 Stay-0.016
Token she
Token ID673
Feature activation+6.79e-03

Pos logit contributions
and+0.063
 Follow+0.057
urry+0.056
 Today+0.052
suits+0.052
Neg logit contributions
 fourteen-0.028
ps-0.027
eling-0.026
bur-0.026
 blew-0.025
Token was
Token ID373
Feature activation+1.77e-02

Pos logit contributions
bur+0.011
 fourteen+0.010
eling+0.010
ps+0.010
cking+0.010
Neg logit contributions
and-0.011
urry-0.009
 Follow-0.009
 tum-0.008
 Stay-0.008
Token sorry
Token ID7926
Feature activation-1.74e-03

Pos logit contributions
rob+0.035
bur+0.034
ible+0.034
ami+0.033
IT+0.033
Neg logit contributions
 welcome-0.018
and-0.017
 of-0.017
urry-0.016
 Stay-0.015
Token for
Token ID329
Feature activation-2.32e-02

Pos logit contributions
and+0.003
urry+0.003
 Follow+0.003
 tum+0.002
 Nice+0.002
Neg logit contributions
bur-0.002
 fourteen-0.002
eling-0.002
ps-0.002
 blew-0.002
Token qu
Token ID627
Feature activation+1.44e-03

Pos logit contributions
and+0.038
urry+0.032
 birthday+0.030
 story+0.030
vere+0.030
Neg logit contributions
bur-0.034
 fourteen-0.033
ible-0.032
rob-0.031
 blew-0.030
Tokenarre
Token ID9624
Feature activation+9.35e-02

Pos logit contributions
bur+0.002
 fourteen+0.002
eling+0.002
ps+0.002
 blew+0.002
Neg logit contributions
and-0.003
urry-0.002
 Follow-0.002
 tum-0.002
 Nice-0.002
Tokenling
Token ID1359
Feature activation+3.64e-03

Pos logit contributions
bur+0.121
 fourteen+0.115
abi+0.104
IT+0.102
ible+0.101
Neg logit contributions
and-0.184
urry-0.151
 Follow-0.149
apping-0.142
 of-0.142
Token.
Token ID13
Feature activation+1.42e-03

Pos logit contributions
bur+0.005
 fourteen+0.004
eling+0.004
ps+0.004
 blew+0.004
Neg logit contributions
and-0.007
urry-0.006
 Follow-0.006
 Nice-0.005
 tum-0.005
Token From
Token ID3574
Feature activation+1.18e-03

Pos logit contributions
bur+0.003
eling+0.003
ck+0.003
ps+0.003
cking+0.002
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
 Nice-0.001
 Today-0.001
Token that
Token ID326
Feature activation-8.99e-03

Pos logit contributions
ps+0.002
ible+0.002
 fourteen+0.002
bur+0.002
eling+0.002
Neg logit contributions
urry-0.002
 of-0.001
and-0.001
 Follow-0.001
 welcome-0.001
Token day
Token ID1110
Feature activation+1.54e-02

Pos logit contributions
and+0.013
 Follow+0.011
urry+0.010
ooters+0.010
vere+0.009
Neg logit contributions
 blew-0.015
bur-0.015
 fourteen-0.015
ible-0.014
eling-0.014
Token the
Token ID262
Feature activation+4.19e-03

Pos logit contributions
bur+0.004
 fourteen+0.004
eling+0.003
ps+0.003
 blew+0.003
Neg logit contributions
and-0.009
urry-0.008
 Follow-0.008
 story-0.007
 Stay-0.007
Token story
Token ID1621
Feature activation-5.81e-03

Pos logit contributions
 blew+0.008
ps+0.008
 fourteen+0.008
bur+0.008
ck+0.008
Neg logit contributions
and-0.005
suits-0.004
urry-0.004
 Follow-0.004
apping-0.004
Token is
Token ID318
Feature activation+1.29e-02

Pos logit contributions
and+0.011
adows+0.010
urry+0.009
 tum+0.009
 Follow+0.009
Neg logit contributions
 fourteen-0.006
ps-0.006
 blew-0.006
mill-0.006
 blows-0.006
Token:
Token ID25
Feature activation-1.59e-02

Pos logit contributions
 fourteen+0.009
bur+0.009
 blew+0.009
ps+0.009
eling+0.009
Neg logit contributions
and-0.030
 Follow-0.026
suits-0.026
urry-0.025
 tum-0.025
Token Qu
Token ID2264
Feature activation-2.03e-02

Pos logit contributions
and+0.025
suits+0.022
 tum+0.021
urry+0.021
 Follow+0.020
Neg logit contributions
 fourteen-0.023
 blew-0.022
ck-0.021
bur-0.021
Why-0.021
Tokenarre
Token ID9624
Feature activation+9.34e-02

Pos logit contributions
and+0.033
 Follow+0.029
urry+0.029
 tum+0.028
 Nice+0.027
Neg logit contributions
bur-0.028
eling-0.028
ps-0.027
 fourteen-0.027
ible-0.027
Tokenlling
Token ID2680
Feature activation+1.55e-02

Pos logit contributions
eling+0.081
lled+0.079
ps+0.079
 blew+0.076
bur+0.075
Neg logit contributions
and-0.204
urry-0.190
 Follow-0.187
 tum-0.183
 Nice-0.179
Token over
Token ID625
Feature activation+1.14e-02

Pos logit contributions
ps+0.025
 fourteen+0.024
 blew+0.024
eling+0.024
ible+0.023
Neg logit contributions
and-0.023
urry-0.019
 Follow-0.019
 tum-0.017
 Nice-0.017
Token small
Token ID1402
Feature activation+2.81e-03

Pos logit contributions
 fourteen+0.015
ps+0.015
eling+0.015
ible+0.015
bur+0.014
Neg logit contributions
and-0.019
 Follow-0.017
urry-0.017
 tum-0.016
 Nice-0.016
Token things
Token ID1243
Feature activation+2.90e-02

Pos logit contributions
ible+0.003
eling+0.003
ps+0.003
 blew+0.003
 fourteen+0.003
Neg logit contributions
and-0.005
urry-0.005
 Follow-0.005
 Nice-0.004
rav-0.004
Token is
Token ID318
Feature activation+1.18e-02

Pos logit contributions
bur+0.052
 fourteen+0.051
eling+0.050
ps+0.050
ck+0.049
Neg logit contributions
and-0.037
urry-0.031
 Follow-0.030
 Nice-0.027
 tum-0.026
Token good
Token ID922
Feature activation+3.26e-02

Pos logit contributions
bur+0.014
IT+0.014
 fourteen+0.014
rob+0.013
ami+0.013
Neg logit contributions
and-0.009
 of-0.008
urry-0.008
 tum-0.008
 welcome-0.007
Token friends
Token ID2460
Feature activation+2.59e-02

Pos logit contributions
bur+0.053
 fourteen+0.052
ps+0.051
eling+0.051
 blew+0.050
Neg logit contributions
and-0.048
 Follow-0.040
urry-0.040
 Nice-0.036
 tum-0.035
Token and
Token ID290
Feature activation-3.06e-03

Pos logit contributions
bur+0.034
 fourteen+0.033
eling+0.033
ps+0.033
 blew+0.032
Neg logit contributions
and-0.047
urry-0.040
 Follow-0.040
 Nice-0.037
 tum-0.036
Token never
Token ID1239
Feature activation-8.36e-03

Pos logit contributions
and+0.006
urry+0.005
 Follow+0.005
 Nice+0.004
 tum+0.004
Neg logit contributions
bur-0.004
 fourteen-0.004
eling-0.004
ps-0.004
 blew-0.004
Token qu
Token ID627
Feature activation+5.35e-03

Pos logit contributions
and+0.017
urry+0.015
 Follow+0.015
 Nice+0.014
 tum+0.014
Neg logit contributions
bur-0.009
 fourteen-0.009
eling-0.009
ps-0.009
 blew-0.008
Tokenarre
Token ID9624
Feature activation+9.32e-02

Pos logit contributions
bur+0.007
 fourteen+0.007
eling+0.007
ps+0.007
 blew+0.007
Neg logit contributions
and-0.009
urry-0.008
 Follow-0.008
apping-0.007
aring-0.007
Tokenled
Token ID992
Feature activation+2.25e-02

Pos logit contributions
bur+0.105
 fourteen+0.101
abi+0.094
ami+0.084
 afar+0.084
Neg logit contributions
and-0.202
urry-0.161
 Follow-0.161
 of-0.159
apping-0.158
Token again
Token ID757
Feature activation-2.45e-02

Pos logit contributions
bur+0.034
 fourteen+0.033
eling+0.033
ps+0.032
 blew+0.032
Neg logit contributions
and-0.037
urry-0.031
 Follow-0.031
 Nice-0.028
 tum-0.028
Token.
Token ID13
Feature activation+5.17e-03

Pos logit contributions
and+0.040
urry+0.032
 of+0.031
 Follow+0.030
 birthday+0.029
Neg logit contributions
bur-0.040
 fourteen-0.038
ps-0.037
eling-0.037
IT-0.035
Token<|endoftext|>
Token ID50256
Feature activation+7.34e-04

Pos logit contributions
bur+0.009
eling+0.009
ps+0.009
ck+0.009
 blew+0.009
Neg logit contributions
and-0.007
urry-0.006
 Follow-0.006
 Nice-0.005
 Today-0.005
TokenOnce
Token ID7454
Feature activation+3.70e-02

Pos logit contributions
bur+0.001
 fourteen+0.001
ps+0.001
 blew+0.001
eling+0.001
Neg logit contributions
and-0.001
urry-0.001
 Follow-0.001
 tum-0.001
 Nice-0.001
Token kept
Token ID4030
Feature activation+4.69e-03

Pos logit contributions
 fourteen+0.014
bur+0.014
ps+0.014
cking+0.013
eling+0.013
Neg logit contributions
and-0.020
urry-0.018
 Follow-0.018
 tum-0.018
 Stay-0.017
Token crying
Token ID13774
Feature activation-4.69e-03

Pos logit contributions
 fourteen+0.008
lled+0.007
ami+0.007
ible+0.007
rob+0.007
Neg logit contributions
and-0.006
 story-0.005
 tum-0.005
 Stay-0.005
urry-0.005
Token and
Token ID290
Feature activation-4.73e-03

Pos logit contributions
and+0.007
urry+0.006
 Follow+0.006
 tum+0.006
apping+0.006
Neg logit contributions
bur-0.007
 fourteen-0.007
eling-0.007
ps-0.007
 blew-0.007
Token throwing
Token ID9644
Feature activation+2.29e-02

Pos logit contributions
and+0.009
urry+0.008
 Follow+0.008
 tum+0.008
 Stay+0.007
Neg logit contributions
bur-0.005
 fourteen-0.005
ps-0.005
ible-0.005
eling-0.005
Token a
Token ID257
Feature activation-6.14e-03

Pos logit contributions
bur+0.026
ami+0.025
eling+0.025
 fourteen+0.025
cking+0.024
Neg logit contributions
and-0.043
 tum-0.039
 of-0.038
 Stay-0.035
 welcome-0.034
Token tant
Token ID24246
Feature activation+9.31e-02

Pos logit contributions
and+0.011
 Follow+0.011
urry+0.010
 School+0.010
 Nice+0.010
Neg logit contributions
 blew-0.007
bur-0.007
 fourteen-0.007
ps-0.006
ck-0.006
Tokenrum
Token ID6582
Feature activation-7.02e-03

Pos logit contributions
bur+0.131
 fourteen+0.129
eling+0.126
 blew+0.123
ps+0.123
Neg logit contributions
and-0.159
urry-0.136
 Follow-0.133
 Nice-0.121
 tum-0.120
Token.
Token ID13
Feature activation+5.60e-03

Pos logit contributions
and+0.013
urry+0.012
 Follow+0.011
 tum+0.011
 Nice+0.011
Neg logit contributions
bur-0.009
 fourteen-0.008
eling-0.008
ps-0.008
 blew-0.008
Token
Token ID198
Feature activation+2.59e-03

Pos logit contributions
 fourteen+0.007
bur+0.007
IT+0.007
 blew+0.007
ps+0.007
Neg logit contributions
and-0.009
 Follow-0.008
urry-0.008
rav-0.007
vere-0.007
Token
Token ID198
Feature activation+2.99e-03

Pos logit contributions
bur+0.003
 fourteen+0.003
ck+0.003
 blew+0.003
lled+0.003
Neg logit contributions
and-0.004
 Follow-0.004
urry-0.004
 tum-0.004
 Nice-0.004
TokenFinally
Token ID11158
Feature activation+1.76e-02

Pos logit contributions
 fourteen+0.003
bur+0.003
eling+0.003
 blew+0.003
ck+0.003
Neg logit contributions
and-0.006
 Follow-0.005
urry-0.005
 Nice-0.005
 tum-0.005
Token They
Token ID1119
Feature activation+1.35e-02

Pos logit contributions
and+0.002
urry+0.002
 Follow+0.002
vere+0.001
rav+0.001
Neg logit contributions
 fourteen-0.002
bur-0.002
ps-0.002
 blew-0.002
eling-0.002
Token said
Token ID531
Feature activation-1.65e-02

Pos logit contributions
bur+0.018
 fourteen+0.018
eling+0.017
ps+0.017
IT+0.017
Neg logit contributions
and-0.023
urry-0.020
 Follow-0.020
 tum-0.019
suits-0.019
Token,
Token ID11
Feature activation-1.58e-02

Pos logit contributions
and+0.031
 Follow+0.029
urry+0.028
case+0.025
ney+0.025
Neg logit contributions
 her-0.021
 fourteen-0.020
 blew-0.019
ps-0.019
 how-0.018
Token "
Token ID366
Feature activation-1.20e-02

Pos logit contributions
and+0.025
urry+0.022
 Follow+0.021
 tum+0.019
vere+0.019
Neg logit contributions
 fourteen-0.023
 blew-0.023
bur-0.022
ps-0.022
abi-0.020
TokenL
Token ID43
Feature activation+1.03e-02

Pos logit contributions
and+0.024
 Follow+0.020
urry+0.019
 School+0.019
rav+0.019
Neg logit contributions
eling-0.015
bur-0.014
ps-0.014
cking-0.013
ck-0.013
Tokenadies
Token ID50192
Feature activation-1.07e-01

Pos logit contributions
bur+0.018
eling+0.018
 fourteen+0.017
 blew+0.017
ps+0.017
Neg logit contributions
and-0.014
urry-0.012
 Follow-0.011
apping-0.010
 Go-0.010
Token and
Token ID290
Feature activation-7.55e-03

Pos logit contributions
and+0.185
urry+0.162
 Follow+0.162
 Nice+0.146
 tum+0.145
Neg logit contributions
bur-0.145
 fourteen-0.142
ps-0.138
eling-0.135
 blew-0.134
Token gentlemen
Token ID28527
Feature activation-6.77e-02

Pos logit contributions
and+0.010
urry+0.008
 Follow+0.008
 tum+0.007
 Nice+0.007
Neg logit contributions
 fourteen-0.013
bur-0.013
 blew-0.013
ck-0.013
eling-0.013
Token,
Token ID11
Feature activation-1.39e-02

Pos logit contributions
and+0.101
 Follow+0.082
urry+0.082
 tum+0.075
 Nice+0.072
Neg logit contributions
 fourteen-0.112
 blew-0.106
bur-0.105
ps-0.105
eling-0.103
Token welcome
Token ID7062
Feature activation-4.22e-02

Pos logit contributions
and+0.024
urry+0.021
 Follow+0.020
 tum+0.020
 Nice+0.019
Neg logit contributions
 fourteen-0.019
 blew-0.019
ps-0.018
bur-0.018
eling-0.017
Token to
Token ID284
Feature activation+1.94e-02

Pos logit contributions
and+0.066
urry+0.057
 Follow+0.056
 tum+0.050
 Nice+0.050
Neg logit contributions
bur-0.064
 fourteen-0.063
ps-0.062
eling-0.061
 blew-0.060
Token.
Token ID13
Feature activation-4.94e-03

Pos logit contributions
bur+0.019
 fourteen+0.018
ps+0.018
eling+0.018
 blew+0.017
Neg logit contributions
and-0.033
urry-0.030
 Follow-0.029
 Nice-0.027
 tum-0.027
Token He
Token ID679
Feature activation+5.45e-04

Pos logit contributions
and+0.008
urry+0.007
 Follow+0.006
rav+0.006
apping+0.006
Neg logit contributions
 fourteen-0.007
ps-0.007
bur-0.007
 blew-0.007
eling-0.007
Token says
Token ID1139
Feature activation-2.36e-02

Pos logit contributions
bur+0.001
 fourteen+0.001
eling+0.001
ps+0.001
lled+0.001
Neg logit contributions
and-0.001
 Follow-0.001
urry-0.001
 tum-0.001
 Stay-0.001
Token "
Token ID366
Feature activation-1.46e-02

Pos logit contributions
and+0.044
urry+0.039
 Follow+0.039
uggle+0.036
anny+0.036
Neg logit contributions
 fourteen-0.029
 blew-0.026
 her-0.026
ps-0.026
 how-0.024
TokenL
Token ID43
Feature activation+1.26e-02

Pos logit contributions
and+0.026
 Follow+0.022
urry+0.021
 Nice+0.020
rav+0.019
Neg logit contributions
eling-0.021
ps-0.021
bur-0.020
 fourteen-0.020
cking-0.019
Tokenadies
Token ID50192
Feature activation-1.03e-01

Pos logit contributions
bur+0.023
eling+0.022
 blew+0.022
 fourteen+0.022
cking+0.021
Neg logit contributions
and-0.018
urry-0.015
 Follow-0.014
 Go-0.012
 of-0.012
Token and
Token ID290
Feature activation-6.30e-03

Pos logit contributions
and+0.181
urry+0.159
 Follow+0.159
 Nice+0.143
 tum+0.142
Neg logit contributions
bur-0.138
 fourteen-0.135
ps-0.132
eling-0.128
 blew-0.126
Token gentlemen
Token ID28527
Feature activation-6.79e-02

Pos logit contributions
and+0.008
urry+0.007
 Follow+0.006
 tum+0.006
 Nice+0.006
Neg logit contributions
 fourteen-0.011
bur-0.011
 blew-0.011
eling-0.011
ck-0.011
Token,
Token ID11
Feature activation-1.07e-02

Pos logit contributions
and+0.099
urry+0.081
 Follow+0.080
 tum+0.075
 Nice+0.070
Neg logit contributions
 fourteen-0.114
bur-0.108
ps-0.108
 blew-0.107
eling-0.105
Token boys
Token ID6510
Feature activation-1.35e-02

Pos logit contributions
and+0.019
urry+0.017
 Follow+0.016
 tum+0.016
 Nice+0.015
Neg logit contributions
 fourteen-0.014
 blew-0.013
ps-0.013
bur-0.013
eling-0.012
Token and
Token ID290
Feature activation-5.80e-03

Pos logit contributions
and+0.019
urry+0.016
 Follow+0.016
 Go+0.014
 story+0.014
Neg logit contributions
bur-0.023
eling-0.022
 fourteen-0.022
ps-0.021
lled-0.021
Token they
Token ID484
Feature activation+4.60e-03

Pos logit contributions
bur+0.000
eling+0.000
 fourteen+0.000
ck+0.000
ps+0.000
Neg logit contributions
and-0.000
 Follow-0.000
urry-0.000
 tum-0.000
 Nice-0.000
Token had
Token ID550
Feature activation-1.65e-02

Pos logit contributions
 fourteen+0.009
bur+0.009
IT+0.009
ami+0.009
abi+0.009
Neg logit contributions
and-0.005
urry-0.004
 Follow-0.004
 of-0.004
 Stay-0.003
Token been
Token ID587
Feature activation-2.07e-02

Pos logit contributions
and+0.026
urry+0.021
 of+0.020
 Follow+0.020
 birthday+0.019
Neg logit contributions
bur-0.026
eling-0.025
 fourteen-0.024
IT-0.024
ami-0.024
Token there
Token ID612
Feature activation-1.80e-02

Pos logit contributions
and+0.032
urry+0.028
 Follow+0.026
 of+0.025
apping+0.024
Neg logit contributions
 fourteen-0.032
bur-0.031
IT-0.030
eling-0.030
ami-0.029
Token for
Token ID329
Feature activation-2.31e-02

Pos logit contributions
and+0.033
 Follow+0.029
urry+0.029
 tum+0.026
 Nice+0.026
Neg logit contributions
bur-0.022
 fourteen-0.022
ps-0.021
eling-0.021
 blew-0.021
Token centuries
Token ID10675
Feature activation-9.36e-02

Pos logit contributions
and+0.048
urry+0.041
 Follow+0.040
 birthday+0.038
 tum+0.038
Neg logit contributions
bur-0.026
 fourteen-0.024
eling-0.024
 blew-0.023
ps-0.022
Token.
Token ID13
Feature activation+9.63e-03

Pos logit contributions
and+0.193
 Follow+0.188
 tum+0.178
urry+0.176
rav+0.173
Neg logit contributions
ps-0.074
 fourteen-0.071
et-0.069
bur-0.068
ible-0.066
Token The
Token ID383
Feature activation+1.57e-04

Pos logit contributions
 fourteen+0.012
bur+0.012
ps+0.012
eling+0.011
 blew+0.011
Neg logit contributions
and-0.017
urry-0.015
 Follow-0.015
 Nice-0.014
rav-0.013
Token dragon
Token ID10441
Feature activation+2.06e-03

Pos logit contributions
ps+0.000
 fourteen+0.000
bur+0.000
eling+0.000
 blew+0.000
Neg logit contributions
and-0.000
urry-0.000
 Follow-0.000
 Nice-0.000
apping-0.000
Token looked
Token ID3114
Feature activation+2.23e-02

Pos logit contributions
bur+0.003
 fourteen+0.003
eling+0.003
ps+0.003
IT+0.003
Neg logit contributions
and-0.003
 Follow-0.003
urry-0.003
 tum-0.003
 of-0.003
Token at
Token ID379
Feature activation+1.34e-02

Pos logit contributions
bur+0.032
 fourteen+0.032
eling+0.031
ps+0.031
 blew+0.030
Neg logit contributions
and-0.037
urry-0.032
 Follow-0.031
 tum-0.028
 Nice-0.028
Token hurt
Token ID5938
Feature activation+3.30e-02

Pos logit contributions
bur+0.021
 fourteen+0.021
eling+0.020
ps+0.020
 blew+0.019
Neg logit contributions
and-0.027
urry-0.024
 Follow-0.023
 tum-0.021
 Nice-0.021
Token.
Token ID13
Feature activation+1.11e-02

Pos logit contributions
bur+0.042
 fourteen+0.041
eling+0.040
ps+0.040
 blew+0.039
Neg logit contributions
and-0.060
urry-0.052
 Follow-0.052
 tum-0.048
 Nice-0.048
Token He
Token ID679
Feature activation+1.17e-02

Pos logit contributions
 fourteen+0.017
bur+0.017
eling+0.016
 blew+0.016
ps+0.016
Neg logit contributions
and-0.017
urry-0.014
 Follow-0.014
 tum-0.013
vere-0.012
Token thanked
Token ID26280
Feature activation+1.82e-02

Pos logit contributions
bur+0.017
 fourteen+0.016
IT+0.015
ries+0.015
cking+0.015
Neg logit contributions
and-0.019
 Follow-0.017
urry-0.017
 tum-0.016
 Stay-0.016
Token the
Token ID262
Feature activation+1.15e-02

Pos logit contributions
 fourteen+0.018
eling+0.018
bur+0.018
 blew+0.017
ible+0.017
Neg logit contributions
and-0.038
urry-0.033
 Follow-0.033
 story-0.032
 Nice-0.032
Token poss
Token ID1184
Feature activation-9.05e-02

Pos logit contributions
bur+0.014
 blew+0.014
 fourteen+0.014
ps+0.014
eling+0.014
Neg logit contributions
and-0.021
urry-0.018
 Follow-0.018
 Nice-0.016
apping-0.016
Tokenum
Token ID388
Feature activation+4.20e-03

Pos logit contributions
and+0.127
 Follow+0.112
urry+0.102
 Nice+0.101
 School+0.097
Neg logit contributions
bur-0.155
ps-0.147
 fourteen-0.147
ck-0.145
ami-0.141
Token and
Token ID290
Feature activation+6.44e-03

Pos logit contributions
bur+0.008
 fourteen+0.007
eling+0.007
ps+0.007
ck+0.007
Neg logit contributions
and-0.005
urry-0.004
 Follow-0.004
 Nice-0.004
 tum-0.004
Token hopped
Token ID45230
Feature activation-2.06e-03

Pos logit contributions
 fourteen+0.009
ible+0.008
bur+0.008
ps+0.008
eling+0.008
Neg logit contributions
and-0.011
 Follow-0.010
urry-0.010
 tum-0.009
 Stay-0.009
Token away
Token ID1497
Feature activation+2.45e-02

Pos logit contributions
and+0.004
urry+0.004
 Follow+0.004
 Nice+0.003
 School+0.003
Neg logit contributions
bur-0.002
ps-0.002
 fourteen-0.002
 blew-0.002
ck-0.002
Token,
Token ID11
Feature activation-4.29e-03

Pos logit contributions
bur+0.040
eling+0.039
 fourteen+0.039
ible+0.038
IT+0.037
Neg logit contributions
and-0.037
urry-0.031
 Follow-0.030
 tum-0.029
 of-0.028
Token said
Token ID531
Feature activation-1.33e-02

Pos logit contributions
and+0.023
 Follow+0.020
urry+0.020
 tum+0.018
 of+0.018
Neg logit contributions
bur-0.019
 fourteen-0.019
ps-0.018
eling-0.018
cking-0.018
Token '
Token ID705
Feature activation+1.18e-02

Pos logit contributions
and+0.020
 Follow+0.017
urry+0.017
 Today+0.015
 Stay+0.015
Neg logit contributions
 fourteen-0.020
ps-0.020
 blew-0.020
bur-0.019
eling-0.019
TokenR
Token ID49
Feature activation-4.09e-02

Pos logit contributions
ps+0.017
 fourteen+0.016
eling+0.015
cking+0.015
ck+0.014
Neg logit contributions
and-0.022
 Follow-0.018
urry-0.017
rav-0.016
 Go-0.016
Tokenever
Token ID964
Feature activation+3.88e-03

Pos logit contributions
and+0.061
 Follow+0.052
urry+0.050
 Nice+0.049
 tum+0.048
Neg logit contributions
bur-0.064
ible-0.063
 fourteen-0.062
eling-0.062
ps-0.061
Tokense
Token ID325
Feature activation+3.55e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
ps+0.006
eling+0.006
 blew+0.005
Neg logit contributions
and-0.006
urry-0.005
 Follow-0.005
 tum-0.005
 Nice-0.005
Token Mass
Token ID5674
Feature activation-8.92e-02

Pos logit contributions
bur+0.063
 fourteen+0.061
eling+0.060
ps+0.060
 blew+0.059
Neg logit contributions
and-0.047
urry-0.039
 Follow-0.038
 tum-0.033
 Nice-0.033
Tokenage
Token ID496
Feature activation+1.64e-02

Pos logit contributions
and+0.138
 Nice+0.121
 tum+0.118
urry+0.114
 Follow+0.114
Neg logit contributions
bur-0.125
ps-0.123
ible-0.121
 fourteen-0.120
IT-0.118
Token'.
Token ID4458
Feature activation-1.39e-02

Pos logit contributions
bur+0.025
 fourteen+0.024
ps+0.024
eling+0.024
 blew+0.023
Neg logit contributions
and-0.026
urry-0.022
 Follow-0.022
 Nice-0.020
 tum-0.020
Token She
Token ID1375
Feature activation+1.39e-02

Pos logit contributions
and+0.020
 Follow+0.017
urry+0.017
 Nice+0.015
 tum+0.015
Neg logit contributions
bur-0.023
eling-0.023
 fourteen-0.022
ps-0.022
ck-0.022
Token pressed
Token ID12070
Feature activation+3.17e-02

Pos logit contributions
bur+0.019
 fourteen+0.018
eling+0.018
ps+0.017
cking+0.017
Neg logit contributions
and-0.024
 Follow-0.021
urry-0.021
 of-0.020
 tum-0.019
Token the
Token ID262
Feature activation+3.06e-03

Pos logit contributions
bur+0.041
eling+0.038
IT+0.035
cking+0.035
 fourteen+0.035
Neg logit contributions
and-0.060
 of-0.052
urry-0.051
 Follow-0.051
 tum-0.048
Token with
Token ID351
Feature activation+8.30e-03

Pos logit contributions
bur+0.001
 fourteen+0.001
eling+0.001
ps+0.001
 blew+0.001
Neg logit contributions
and-0.003
urry-0.003
 Follow-0.003
 Nice-0.002
 tum-0.002
Token lots
Token ID6041
Feature activation-2.32e-02

Pos logit contributions
bur+0.009
 fourteen+0.009
eling+0.009
ps+0.008
IT+0.008
Neg logit contributions
and-0.017
 Follow-0.015
urry-0.015
 tum-0.014
 Stay-0.014
Token of
Token ID286
Feature activation+2.03e-03

Pos logit contributions
and+0.024
 Follow+0.022
urry+0.021
rav+0.020
 School+0.019
Neg logit contributions
ries-0.044
ps-0.044
 fourteen-0.044
 her-0.043
 colored-0.042
Token food
Token ID2057
Feature activation-2.32e-02

Pos logit contributions
ps+0.002
eling+0.002
 colored+0.002
 blew+0.002
 her+0.002
Neg logit contributions
and-0.004
urry-0.004
 Follow-0.004
aring-0.003
apping-0.003
Token.
Token ID13
Feature activation+4.44e-03

Pos logit contributions
and+0.044
urry+0.039
 Follow+0.038
 Nice+0.035
 tum+0.035
Neg logit contributions
bur-0.028
 fourteen-0.027
eling-0.026
ps-0.026
 blew-0.026
Token Them
Token ID26460
Feature activation-8.87e-02

Pos logit contributions
 fourteen+0.005
bur+0.005
IT+0.005
 blew+0.005
ible+0.005
Neg logit contributions
and-0.008
urry-0.007
rav-0.007
 Follow-0.007
vere-0.007
Tokenouse
Token ID1076
Feature activation+2.53e-03

Pos logit contributions
and+0.153
 School+0.132
vere+0.131
 Nice+0.131
 Follow+0.130
Neg logit contributions
 blew-0.104
bur-0.098
ck-0.095
ps-0.094
lled-0.092
Token's
Token ID338
Feature activation-2.26e-02

Pos logit contributions
bur+0.004
 fourteen+0.004
eling+0.003
ps+0.003
 blew+0.003
Neg logit contributions
and-0.004
urry-0.004
 Follow-0.004
 tum-0.003
 Nice-0.003
Token mouth
Token ID5422
Feature activation-1.82e-02

Pos logit contributions
and+0.040
urry+0.034
 Follow+0.033
rav+0.031
ooters+0.030
Neg logit contributions
bur-0.031
ps-0.030
 fourteen-0.030
 blew-0.029
eling-0.029
Token watered
Token ID48024
Feature activation-8.26e-03

Pos logit contributions
and+0.031
 Follow+0.027
urry+0.027
rav+0.024
 School+0.024
Neg logit contributions
bur-0.025
 fourteen-0.025
 blew-0.025
ps-0.025
eling-0.024
Token,
Token ID11
Feature activation-9.57e-03

Pos logit contributions
and+0.015
urry+0.014
 Follow+0.013
 tum+0.012
apping+0.012
Neg logit contributions
bur-0.010
 fourteen-0.010
ps-0.010
eling-0.010
ible-0.010
Token a
Token ID257
Feature activation-3.48e-03

Pos logit contributions
and+0.055
urry+0.049
 Follow+0.049
 tum+0.045
 Nice+0.045
Neg logit contributions
bur-0.030
 fourteen-0.029
eling-0.029
ps-0.028
 blew-0.027
Token few
Token ID1178
Feature activation+2.51e-02

Pos logit contributions
and+0.006
 Follow+0.005
urry+0.005
 Nice+0.005
apping+0.005
Neg logit contributions
eling-0.004
 blew-0.004
bur-0.004
 sc-0.004
cking-0.004
Token days
Token ID1528
Feature activation-6.27e-02

Pos logit contributions
eling+0.035
 fourteen+0.032
ps+0.032
 blew+0.032
ck+0.032
Neg logit contributions
and-0.043
urry-0.039
 Follow-0.038
 Nice-0.037
rav-0.035
Token when
Token ID618
Feature activation+2.32e-02

Pos logit contributions
and+0.106
 Follow+0.092
urry+0.091
 Nice+0.084
 tum+0.083
Neg logit contributions
bur-0.087
 fourteen-0.086
eling-0.084
ps-0.083
 blew-0.082
Token the
Token ID262
Feature activation+4.12e-03

Pos logit contributions
bur+0.029
 fourteen+0.027
ps+0.027
eling+0.027
ck+0.026
Neg logit contributions
and-0.043
urry-0.038
 Follow-0.038
 Nice-0.036
 tum-0.035
Token renovations
Token ID44481
Feature activation-8.85e-02

Pos logit contributions
bur+0.006
 blew+0.006
ps+0.005
eling+0.005
 fourteen+0.005
Neg logit contributions
and-0.007
urry-0.006
 Follow-0.006
apping-0.005
 Nice-0.005
Token were
Token ID547
Feature activation+8.38e-03

Pos logit contributions
and+0.134
urry+0.113
 Follow+0.112
 tum+0.102
 Nice+0.101
Neg logit contributions
bur-0.140
 fourteen-0.136
ps-0.134
eling-0.133
 blew-0.132
Token done
Token ID1760
Feature activation-2.02e-03

Pos logit contributions
bur+0.011
 fourteen+0.010
ps+0.010
eling+0.010
 blew+0.010
Neg logit contributions
and-0.015
 Follow-0.014
urry-0.014
 Nice-0.013
 tum-0.012
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
and+0.004
urry+0.003
 Follow+0.003
 tum+0.003
 Nice+0.003
Neg logit contributions
bur-0.003
 fourteen-0.002
eling-0.002
ps-0.002
 blew-0.002
Token Everyone
Token ID11075
Feature activation+3.91e-02

Pos logit contributions
bur+0.021
eling+0.020
 fourteen+0.020
ps+0.020
ck+0.019
Neg logit contributions
and-0.015
 Follow-0.013
urry-0.013
 Nice-0.011
 tum-0.011
Token could
Token ID714
Feature activation-3.84e-02

Pos logit contributions
bur+0.062
 fourteen+0.060
ps+0.056
eling+0.056
IT+0.055
Neg logit contributions
and-0.063
 Follow-0.054
urry-0.053
 of-0.050
apping-0.048
Token a
Token ID257
Feature activation-7.69e-03

Pos logit contributions
and+0.068
urry+0.060
 Follow+0.059
 story+0.057
 Today+0.056
Neg logit contributions
bur-0.034
 fourteen-0.033
eling-0.032
ps-0.031
 blew-0.031
Token few
Token ID1178
Feature activation+2.25e-02

Pos logit contributions
and+0.013
 Follow+0.012
urry+0.011
 Nice+0.011
rav+0.011
Neg logit contributions
 blew-0.010
bur-0.010
eling-0.010
 sc-0.009
 afar-0.009
Token days
Token ID1528
Feature activation-6.74e-02

Pos logit contributions
eling+0.033
 fourteen+0.032
ps+0.032
bur+0.032
ck+0.032
Neg logit contributions
and-0.036
urry-0.032
 Follow-0.031
 Nice-0.029
rav-0.028
Token when
Token ID618
Feature activation+2.26e-02

Pos logit contributions
and+0.118
 Follow+0.102
urry+0.102
 Nice+0.094
 tum+0.093
Neg logit contributions
bur-0.090
 fourteen-0.088
eling-0.086
ps-0.085
 blew-0.084
Token the
Token ID262
Feature activation+2.59e-03

Pos logit contributions
bur+0.029
ps+0.027
 fourteen+0.027
eling+0.027
ck+0.026
Neg logit contributions
and-0.041
urry-0.036
 Follow-0.035
 Nice-0.033
 tum-0.033
Token renovations
Token ID44481
Feature activation-8.83e-02

Pos logit contributions
bur+0.004
 fourteen+0.004
 blew+0.003
ps+0.003
eling+0.003
Neg logit contributions
and-0.005
urry-0.004
 Follow-0.004
 Nice-0.003
apping-0.003
Token were
Token ID547
Feature activation+8.50e-03

Pos logit contributions
and+0.136
urry+0.116
 Follow+0.115
 tum+0.105
 Nice+0.103
Neg logit contributions
bur-0.136
 fourteen-0.133
ps-0.131
eling-0.129
 blew-0.128
Token done
Token ID1760
Feature activation-1.13e-03

Pos logit contributions
bur+0.012
 fourteen+0.011
eling+0.011
ps+0.011
 blew+0.011
Neg logit contributions
and-0.015
urry-0.013
 Follow-0.013
 tum-0.012
 Nice-0.012
Token.
Token ID13
Feature activation+3.31e-03

Pos logit contributions
and+0.002
urry+0.002
 Follow+0.002
 tum+0.002
 Nice+0.002
Neg logit contributions
bur-0.001
 fourteen-0.001
eling-0.001
ps-0.001
 blew-0.001
Token Everyone
Token ID11075
Feature activation+4.11e-02

Pos logit contributions
bur+0.006
eling+0.005
ps+0.005
 fourteen+0.005
ck+0.005
Neg logit contributions
and-0.005
urry-0.004
 Follow-0.004
 Nice-0.004
 tum-0.004
Token could
Token ID714
Feature activation-4.03e-02

Pos logit contributions
bur+0.065
 fourteen+0.063
ps+0.059
IT+0.059
eling+0.059
Neg logit contributions
and-0.066
 Follow-0.056
urry-0.055
 of-0.052
apping-0.050
Tokenolly
Token ID5098
Feature activation-6.37e-03

Pos logit contributions
bur+0.023
 fourteen+0.023
eling+0.022
ps+0.022
 blew+0.022
Neg logit contributions
and-0.018
urry-0.015
 Follow-0.015
 Nice-0.013
 tum-0.013
Token was
Token ID373
Feature activation+4.08e-03

Pos logit contributions
and+0.011
urry+0.009
 Follow+0.009
 Nice+0.008
 tum+0.008
Neg logit contributions
bur-0.009
 fourteen-0.009
eling-0.009
ps-0.009
 blew-0.008
Token a
Token ID257
Feature activation-1.27e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
ible+0.005
Neg logit contributions
and-0.007
urry-0.006
 Follow-0.006
 tum-0.005
apping-0.005
Token three
Token ID1115
Feature activation-2.63e-02

Pos logit contributions
and+0.018
urry+0.016
 Follow+0.016
 tum+0.014
 Nice+0.014
Neg logit contributions
bur-0.021
 fourteen-0.020
ps-0.020
eling-0.020
lled-0.020
Token-
Token ID12
Feature activation-5.10e-03

Pos logit contributions
and+0.035
 Follow+0.030
urry+0.030
 Nice+0.027
rav+0.026
Neg logit contributions
eling-0.045
bur-0.044
ps-0.043
 fourteen-0.043
ck-0.043
Tokenyear
Token ID1941
Feature activation-8.74e-02

Pos logit contributions
and+0.005
urry+0.004
 Follow+0.004
 tum+0.003
 Nice+0.003
Neg logit contributions
bur-0.010
 fourteen-0.010
eling-0.010
ps-0.010
 blew-0.010
Token old
Token ID1468
Feature activation-1.52e-02

Pos logit contributions
and+0.156
 Follow+0.144
 Nice+0.138
urry+0.138
 School+0.133
Neg logit contributions
ps-0.102
ck-0.102
bur-0.101
 fourteen-0.099
eling-0.097
Token girl
Token ID2576
Feature activation-9.91e-03

Pos logit contributions
and+0.024
urry+0.020
 Follow+0.020
 Nice+0.018
 tum+0.018
Neg logit contributions
bur-0.023
 fourteen-0.023
eling-0.022
ps-0.022
 blew-0.022
Token who
Token ID508
Feature activation-1.19e-02

Pos logit contributions
and+0.019
urry+0.017
 Follow+0.017
 Nice+0.016
rav+0.015
Neg logit contributions
bur-0.011
 fourteen-0.011
 blew-0.011
eling-0.011
ps-0.010
Token loved
Token ID6151
Feature activation-7.95e-04

Pos logit contributions
and+0.015
 Follow+0.013
urry+0.013
 School+0.011
 Stay+0.011
Neg logit contributions
bur-0.022
 fourteen-0.022
ps-0.021
cking-0.020
eling-0.020
Token to
Token ID284
Feature activation+1.46e-02

Pos logit contributions
and+0.001
urry+0.001
 Follow+0.001
 tum+0.001
 Nice+0.001
Neg logit contributions
bur-0.001
 fourteen-0.001
eling-0.001
ps-0.001
ck-0.001
Tokenoy
Token ID726
Feature activation-1.31e-02

Pos logit contributions
and+0.016
 Follow+0.014
urry+0.013
 Nice+0.012
 Today+0.012
Neg logit contributions
 fourteen-0.017
bur-0.016
eling-0.016
ck-0.016
ps-0.016
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
and+0.022
 Follow+0.019
urry+0.018
 tum+0.017
 Nice+0.016
Neg logit contributions
bur-0.019
 fourteen-0.018
ps-0.018
ible-0.017
ami-0.017
Token mate
Token ID16133
Feature activation-2.65e-02

Pos logit contributions
and+0.019
urry+0.016
 Follow+0.016
apping+0.015
vere+0.014
Neg logit contributions
 fourteen-0.017
 blew-0.016
ps-0.016
bur-0.016
ck-0.015
Tokeny
Token ID88
Feature activation-1.34e-02

Pos logit contributions
and+0.044
urry+0.038
 Follow+0.037
 Nice+0.034
 tum+0.034
Neg logit contributions
bur-0.038
 fourteen-0.037
eling-0.037
ps-0.036
 blew-0.035
Token!
Token ID0
Feature activation-9.61e-03

Pos logit contributions
and+0.026
urry+0.023
 Follow+0.023
 tum+0.021
 Nice+0.021
Neg logit contributions
 fourteen-0.015
bur-0.015
ps-0.015
 blew-0.014
ible-0.014
Token Land
Token ID6379
Feature activation-8.73e-02

Pos logit contributions
and+0.013
urry+0.009
 tum+0.009
vere+0.009
 story+0.009
Neg logit contributions
 fourteen-0.017
 blew-0.016
bur-0.016
ps-0.015
IT-0.015
Token ho
Token ID8169
Feature activation-5.47e-02

Pos logit contributions
and+0.144
 tum+0.126
urry+0.124
 Follow+0.123
vere+0.110
Neg logit contributions
ps-0.121
 fourteen-0.119
 blew-0.113
lled-0.109
bur-0.108
Token!"
Token ID2474
Feature activation-1.17e-03

Pos logit contributions
and+0.089
 Follow+0.078
 tum+0.075
urry+0.071
 Nice+0.070
Neg logit contributions
 fourteen-0.084
bur-0.083
ps-0.082
ck-0.076
 blew-0.074
Token
Token ID198
Feature activation+1.40e-03

Pos logit contributions
and+0.002
urry+0.001
 Follow+0.001
 tum+0.001
 Nice+0.001
Neg logit contributions
bur-0.002
 fourteen-0.002
eling-0.002
ps-0.002
 blew-0.002
Token
Token ID198
Feature activation+1.85e-03

Pos logit contributions
 fourteen+0.002
bur+0.002
ck+0.002
 blew+0.002
ps+0.002
Neg logit contributions
and-0.002
 Follow-0.002
urry-0.002
 Nice-0.002
 School-0.002
TokenBut
Token ID1537
Feature activation+2.35e-03

Pos logit contributions
bur+0.002
 fourteen+0.002
eling+0.002
ps+0.002
ible+0.002
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
 tum-0.003
 Nice-0.003
Token?"
Token ID1701
Feature activation+4.88e-02

Pos logit contributions
and+0.000
urry+0.000
 Follow+0.000
 tum+0.000
 Nice+0.000
Neg logit contributions
bur-0.000
 fourteen-0.000
eling-0.000
ps-0.000
 blew-0.000
Token asked
Token ID1965
Feature activation+4.51e-03

Pos logit contributions
ps+0.069
 fourteen+0.069
bur+0.069
lled+0.065
ible+0.064
Neg logit contributions
and-0.078
 Follow-0.074
 tum-0.073
urry-0.072
 of-0.071
Token a
Token ID257
Feature activation-7.15e-03

Pos logit contributions
 fourteen+0.007
eling+0.007
cking+0.007
bur+0.006
ps+0.006
Neg logit contributions
and-0.007
 of-0.006
urry-0.006
 Stay-0.006
 tum-0.006
Token three
Token ID1115
Feature activation-2.08e-02

Pos logit contributions
and+0.013
urry+0.011
 Follow+0.011
 Go+0.011
 Nice+0.010
Neg logit contributions
 blew-0.009
bur-0.008
 comb-0.008
 fourteen-0.008
 pressed-0.008
Token-
Token ID12
Feature activation+3.32e-03

Pos logit contributions
and+0.027
 Follow+0.023
urry+0.023
 Nice+0.020
 Stay+0.019
Neg logit contributions
bur-0.036
 fourteen-0.036
eling-0.036
ps-0.035
ck-0.035
Tokenyear
Token ID1941
Feature activation-8.69e-02

Pos logit contributions
bur+0.007
eling+0.007
 fourteen+0.007
ps+0.007
 blew+0.007
Neg logit contributions
and-0.003
urry-0.002
 Follow-0.002
 of-0.002
 Nice-0.002
Token-
Token ID12
Feature activation+3.28e-03

Pos logit contributions
and+0.159
 Follow+0.145
 Nice+0.137
urry+0.137
 School+0.132
Neg logit contributions
ck-0.103
ps-0.100
bur-0.099
 fourteen-0.094
eling-0.094
Tokenold
Token ID727
Feature activation+3.86e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
ck+0.006
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
 tum-0.003
 Nice-0.003
Token girl
Token ID2576
Feature activation-1.28e-02

Pos logit contributions
bur+0.059
 fourteen+0.058
eling+0.056
ps+0.056
 blew+0.055
Neg logit contributions
and-0.061
urry-0.052
 Follow-0.052
 tum-0.046
 Nice-0.046
Token.
Token ID13
Feature activation+2.03e-03

Pos logit contributions
and+0.025
urry+0.022
 Follow+0.022
 Nice+0.021
 tum+0.021
Neg logit contributions
bur-0.014
eling-0.013
 fourteen-0.013
ps-0.013
ck-0.013
Token
Token ID198
Feature activation-1.17e-03

Pos logit contributions
bur+0.003
 fourteen+0.003
 blew+0.003
ps+0.003
eling+0.003
Neg logit contributions
and-0.003
urry-0.003
 Follow-0.003
 tum-0.002
vere-0.002
Token day
Token ID1110
Feature activation+1.32e-02

Pos logit contributions
and+0.045
 Follow+0.037
vere+0.035
urry+0.035
 Go+0.033
Neg logit contributions
 blew-0.050
bur-0.050
eling-0.049
ck-0.048
 fourteen-0.048
Token,
Token ID11
Feature activation-7.32e-03

Pos logit contributions
bur+0.025
 fourteen+0.024
eling+0.024
ps+0.024
 blew+0.024
Neg logit contributions
and-0.016
urry-0.013
 Follow-0.013
 tum-0.011
 Nice-0.011
Token a
Token ID257
Feature activation-7.40e-03

Pos logit contributions
and+0.012
urry+0.011
 Follow+0.011
 Nice+0.010
 of+0.010
Neg logit contributions
ps-0.010
eling-0.010
cking-0.010
bur-0.010
 fourteen-0.010
Token three
Token ID1115
Feature activation-2.19e-02

Pos logit contributions
and+0.015
 Follow+0.012
urry+0.012
 Go+0.012
 Today+0.011
Neg logit contributions
 blew-0.009
bur-0.008
 pin-0.008
 sc-0.008
abi-0.008
Token-
Token ID12
Feature activation-4.95e-04

Pos logit contributions
and+0.027
 Follow+0.022
urry+0.021
 Nice+0.019
rav+0.018
Neg logit contributions
eling-0.040
ck-0.039
 blew-0.039
bur-0.039
 fourteen-0.039
Tokenyear
Token ID1941
Feature activation-8.64e-02

Pos logit contributions
and+0.001
urry+0.000
 Follow+0.000
 tum+0.000
 Nice+0.000
Neg logit contributions
bur-0.001
 fourteen-0.001
eling-0.001
ps-0.001
 blew-0.001
Token-
Token ID12
Feature activation-1.02e-03

Pos logit contributions
and+0.155
 Follow+0.138
 Nice+0.131
urry+0.130
 School+0.127
Neg logit contributions
ck-0.107
ps-0.106
bur-0.105
 fourteen-0.105
eling-0.100
Tokenold
Token ID727
Feature activation+3.98e-02

Pos logit contributions
and+0.001
 Follow+0.001
urry+0.001
 tum+0.001
 Nice+0.001
Neg logit contributions
bur-0.002
 fourteen-0.002
ck-0.002
eling-0.002
ps-0.002
Token boy
Token ID2933
Feature activation-5.40e-03

Pos logit contributions
bur+0.062
 fourteen+0.061
eling+0.060
ps+0.059
 blew+0.058
Neg logit contributions
and-0.061
urry-0.052
 Follow-0.052
 Nice-0.046
 tum-0.046
Token decided
Token ID3066
Feature activation-1.70e-02

Pos logit contributions
and+0.009
urry+0.008
 Follow+0.008
 tum+0.007
 Nice+0.007
Neg logit contributions
bur-0.007
 fourteen-0.007
eling-0.007
ps-0.007
ck-0.007
Token to
Token ID284
Feature activation+2.08e-02

Pos logit contributions
and+0.022
urry+0.018
 Follow+0.018
 Nice+0.016
 tum+0.016
Neg logit contributions
bur-0.031
 fourteen-0.030
eling-0.030
ps-0.030
ible-0.029
Token was
Token ID373
Feature activation+6.87e-03

Pos logit contributions
and+0.019
urry+0.016
 Follow+0.016
 of+0.015
 tum+0.015
Neg logit contributions
 fourteen-0.024
ps-0.024
cking-0.023
bur-0.023
eling-0.023
Token an
Token ID281
Feature activation-2.74e-02

Pos logit contributions
bur+0.010
 fourteen+0.010
eling+0.010
ps+0.010
ible+0.009
Neg logit contributions
and-0.011
urry-0.010
 Follow-0.010
 tum-0.009
apping-0.009
Token eager
Token ID11069
Feature activation-6.22e-03

Pos logit contributions
and+0.046
 Follow+0.040
urry+0.039
 Nice+0.036
rav+0.036
Neg logit contributions
bur-0.039
eling-0.037
 fourteen-0.037
ps-0.036
ck-0.036
Token 3
Token ID513
Feature activation-4.30e-02

Pos logit contributions
and+0.011
 Follow+0.010
vere+0.009
urry+0.009
adows+0.008
Neg logit contributions
bur-0.008
 blew-0.008
 her-0.007
ami-0.007
 comb-0.007
Token-
Token ID12
Feature activation+3.87e-03

Pos logit contributions
and+0.049
 Follow+0.041
urry+0.040
 Nice+0.035
 tum+0.034
Neg logit contributions
bur-0.082
eling-0.080
 fourteen-0.080
ps-0.079
 blew-0.078
Tokenyear
Token ID1941
Feature activation-8.64e-02

Pos logit contributions
bur+0.008
 fourteen+0.007
eling+0.007
ck+0.007
ps+0.007
Neg logit contributions
and-0.004
 Follow-0.003
urry-0.003
 tum-0.003
 Nice-0.003
Token-
Token ID12
Feature activation+3.91e-03

Pos logit contributions
and+0.158
 Follow+0.142
urry+0.136
 Nice+0.134
 Today+0.128
Neg logit contributions
bur-0.100
ps-0.099
ck-0.099
eling-0.097
 fourteen-0.096
Tokenold
Token ID727
Feature activation+3.86e-02

Pos logit contributions
bur+0.007
eling+0.007
 fourteen+0.007
ck+0.007
ps+0.007
Neg logit contributions
and-0.004
 Follow-0.004
urry-0.004
 Nice-0.003
 tum-0.003
Token boy
Token ID2933
Feature activation-1.01e-02

Pos logit contributions
bur+0.053
 fourteen+0.053
eling+0.051
ps+0.051
 blew+0.049
Neg logit contributions
and-0.067
urry-0.057
 Follow-0.057
 Nice-0.052
 tum-0.052
Token who
Token ID508
Feature activation-1.54e-02

Pos logit contributions
and+0.018
urry+0.016
 Follow+0.016
apping+0.014
 Nice+0.014
Neg logit contributions
bur-0.013
 fourteen-0.013
eling-0.013
ps-0.013
lled-0.012
Token loved
Token ID6151
Feature activation+3.32e-04

Pos logit contributions
and+0.018
 Follow+0.016
urry+0.016
 School+0.014
 Stay+0.014
Neg logit contributions
 fourteen-0.029
bur-0.028
cking-0.028
ps-0.028
ck-0.027
Token sign
Token ID1051
Feature activation+1.63e-02

Pos logit contributions
 blew+0.016
bur+0.016
 fourteen+0.015
ible+0.015
ries+0.015
Neg logit contributions
and-0.027
 Follow-0.021
urry-0.021
vere-0.019
anny-0.019
Token that
Token ID326
Feature activation-1.51e-02

Pos logit contributions
bur+0.017
 fourteen+0.016
eling+0.016
ps+0.016
ible+0.015
Neg logit contributions
and-0.033
urry-0.030
 Follow-0.030
 tum-0.028
 Nice-0.028
Token said
Token ID531
Feature activation-1.12e-02

Pos logit contributions
and+0.026
 Follow+0.024
urry+0.023
 tum+0.023
 story+0.022
Neg logit contributions
 fourteen-0.020
bur-0.019
eling-0.019
ps-0.018
ible-0.018
Token "
Token ID366
Feature activation-1.07e-02

Pos logit contributions
and+0.019
 Follow+0.016
urry+0.016
ooters+0.014
suits+0.014
Neg logit contributions
 fourteen-0.016
 blew-0.015
ps-0.015
 her-0.014
bur-0.014
TokenF
Token ID37
Feature activation-6.93e-02

Pos logit contributions
and+0.019
urry+0.016
 Follow+0.016
 Nice+0.015
 tum+0.015
Neg logit contributions
bur-0.014
 fourteen-0.014
eling-0.014
ps-0.014
 blew-0.013
Tokenestival
Token ID6743
Feature activation-8.64e-02

Pos logit contributions
and+0.107
 Follow+0.088
vere+0.087
 tum+0.086
 Nice+0.085
Neg logit contributions
bur-0.105
 fourteen-0.103
ck-0.102
IT-0.100
ps-0.099
Token Today
Token ID6288
Feature activation-3.89e-02

Pos logit contributions
vere+0.112
 villains+0.103
and+0.097
 Follow+0.096
 tum+0.092
Neg logit contributions
 fourteen-0.134
IT-0.132
bur-0.126
et-0.116
 least-0.115
Token!"
Token ID2474
Feature activation+2.94e-03

Pos logit contributions
and+0.075
 Follow+0.066
urry+0.062
ooters+0.060
rav+0.058
Neg logit contributions
 fourteen-0.044
 blew-0.042
ps-0.039
IT-0.038
bur-0.038
Token She
Token ID1375
Feature activation+1.20e-02

Pos logit contributions
bur+0.005
 fourteen+0.005
eling+0.005
ps+0.005
ck+0.005
Neg logit contributions
and-0.004
urry-0.004
 Follow-0.003
 tum-0.003
 Nice-0.003
Token was
Token ID373
Feature activation+6.76e-03

Pos logit contributions
bur+0.015
 fourteen+0.015
eling+0.015
ps+0.015
cking+0.014
Neg logit contributions
and-0.021
urry-0.019
 Follow-0.019
 tum-0.018
 Stay-0.017
Token very
Token ID845
Feature activation+1.60e-02

Pos logit contributions
bur+0.010
ps+0.010
 fourteen+0.010
eling+0.010
 blew+0.010
Neg logit contributions
and-0.011
urry-0.009
 Follow-0.009
 Nice-0.008
rav-0.008
Tokenmy
Token ID1820
Feature activation+1.55e-02

Pos logit contributions
 fourteen+0.010
cking+0.010
ck+0.010
eling+0.010
ps+0.009
Neg logit contributions
and-0.009
urry-0.008
 Follow-0.007
 Today-0.007
 tum-0.007
Token was
Token ID373
Feature activation+5.41e-03

Pos logit contributions
bur+0.024
 fourteen+0.024
ps+0.023
eling+0.023
ck+0.022
Neg logit contributions
and-0.023
urry-0.020
 Follow-0.020
 tum-0.018
 Stay-0.018
Token a
Token ID257
Feature activation-8.36e-03

Pos logit contributions
bur+0.008
 fourteen+0.008
eling+0.008
ible+0.008
ps+0.008
Neg logit contributions
and-0.009
urry-0.008
 Follow-0.007
 tum-0.007
apping-0.007
Token three
Token ID1115
Feature activation-2.30e-02

Pos logit contributions
and+0.012
urry+0.010
 Follow+0.010
 tum+0.009
 Nice+0.009
Neg logit contributions
bur-0.014
 fourteen-0.014
ps-0.013
eling-0.013
lled-0.013
Token-
Token ID12
Feature activation+3.40e-03

Pos logit contributions
and+0.030
urry+0.025
 Follow+0.025
 Nice+0.021
 tum+0.021
Neg logit contributions
bur-0.041
 fourteen-0.040
eling-0.040
ps-0.039
 blew-0.039
Tokenyear
Token ID1941
Feature activation-8.64e-02

Pos logit contributions
bur+0.007
 fourteen+0.007
eling+0.007
ps+0.007
ck+0.007
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
 tum-0.003
 Nice-0.003
Token-
Token ID12
Feature activation+3.46e-03

Pos logit contributions
and+0.164
 Follow+0.149
 Nice+0.145
urry+0.141
 Today+0.137
Neg logit contributions
ck-0.090
ps-0.090
eling-0.088
bur-0.087
et-0.086
Tokenold
Token ID727
Feature activation+3.82e-02

Pos logit contributions
bur+0.006
ck+0.006
eling+0.006
 fourteen+0.006
cking+0.006
Neg logit contributions
and-0.004
 Follow-0.004
urry-0.004
 Nice-0.003
 tum-0.003
Token boy
Token ID2933
Feature activation-1.18e-02

Pos logit contributions
bur+0.055
 fourteen+0.054
eling+0.053
ps+0.053
 blew+0.051
Neg logit contributions
and-0.063
urry-0.054
 Follow-0.054
 tum-0.049
 Nice-0.049
Token who
Token ID508
Feature activation-1.76e-02

Pos logit contributions
and+0.022
urry+0.019
 Follow+0.019
 tum+0.018
 Nice+0.018
Neg logit contributions
bur-0.015
 fourteen-0.014
eling-0.014
ps-0.014
lled-0.013
Token loved
Token ID6151
Feature activation-2.09e-05

Pos logit contributions
and+0.022
urry+0.019
 Follow+0.018
 School+0.017
 Stay+0.017
Neg logit contributions
 fourteen-0.033
bur-0.032
ps-0.031
cking-0.031
ries-0.031
Token mom
Token ID1995
Feature activation+1.44e-03

Pos logit contributions
and+0.017
 Follow+0.015
urry+0.014
 Nice+0.013
 tum+0.013
Neg logit contributions
bur-0.016
 fourteen-0.016
 blew-0.016
eling-0.015
ps-0.015
Token and
Token ID290
Feature activation-2.05e-03

Pos logit contributions
 fourteen+0.002
eling+0.002
ps+0.002
bur+0.002
cking+0.002
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
 of-0.002
 story-0.002
Token her
Token ID607
Feature activation+7.34e-03

Pos logit contributions
and+0.004
urry+0.004
 Follow+0.004
 birthday+0.004
 tum+0.004
Neg logit contributions
 fourteen-0.002
ps-0.002
eling-0.002
bur-0.002
ible-0.002
Token 3
Token ID513
Feature activation-4.52e-02

Pos logit contributions
bur+0.012
 fourteen+0.012
eling+0.012
ps+0.011
 blew+0.011
Neg logit contributions
and-0.011
urry-0.009
 Follow-0.009
 tum-0.008
 Nice-0.008
Token-
Token ID12
Feature activation-2.09e-03

Pos logit contributions
and+0.050
 Follow+0.041
urry+0.040
 Nice+0.036
vere+0.033
Neg logit contributions
bur-0.088
eling-0.087
ps-0.086
 fourteen-0.085
ck-0.085
Tokenyear
Token ID1941
Feature activation-8.62e-02

Pos logit contributions
and+0.002
 Follow+0.002
urry+0.002
 Nice+0.002
 tum+0.002
Neg logit contributions
bur-0.004
 fourteen-0.004
ps-0.004
eling-0.004
ck-0.004
Token-
Token ID12
Feature activation-2.54e-03

Pos logit contributions
and+0.156
 Follow+0.143
 Nice+0.137
urry+0.135
 Today+0.130
Neg logit contributions
ps-0.104
ck-0.102
bur-0.102
 fourteen-0.098
eling-0.096
Tokenold
Token ID727
Feature activation+3.75e-02

Pos logit contributions
and+0.003
 Follow+0.002
urry+0.002
 Nice+0.002
 tum+0.002
Neg logit contributions
bur-0.005
 fourteen-0.005
eling-0.005
ps-0.005
ck-0.005
Token daughter
Token ID4957
Feature activation-1.64e-02

Pos logit contributions
bur+0.059
 fourteen+0.058
eling+0.057
ps+0.056
 blew+0.055
Neg logit contributions
and-0.057
urry-0.049
 Follow-0.048
 Nice-0.043
 tum-0.043
Token decided
Token ID3066
Feature activation-1.80e-02

Pos logit contributions
and+0.029
urry+0.025
 Follow+0.025
 Nice+0.023
vere+0.022
Neg logit contributions
bur-0.022
 blew-0.022
 fourteen-0.022
ible-0.021
ps-0.021
Token to
Token ID284
Feature activation+1.84e-02

Pos logit contributions
and+0.023
urry+0.019
 Follow+0.019
 tum+0.017
 Nice+0.017
Neg logit contributions
bur-0.033
 fourteen-0.032
eling-0.032
ps-0.031
ible-0.031
Token!"
Token ID2474
Feature activation+2.85e-02

Pos logit contributions
and+0.030
urry+0.025
 Follow+0.025
 tum+0.021
 Nice+0.021
Neg logit contributions
bur-0.043
 fourteen-0.042
eling-0.041
ps-0.041
 blew-0.040
Token shouted
Token ID17293
Feature activation-1.88e-02

Pos logit contributions
bur+0.044
 fourteen+0.044
ps+0.044
eling+0.043
lled+0.042
Neg logit contributions
and-0.042
urry-0.038
 Follow-0.038
 tum-0.038
 of-0.035
Token her
Token ID607
Feature activation+2.25e-03

Pos logit contributions
and+0.026
urry+0.024
 tum+0.024
 Follow+0.023
 Stay+0.021
Neg logit contributions
eling-0.031
bur-0.031
 fourteen-0.030
cking-0.029
lled-0.029
Token three
Token ID1115
Feature activation-2.29e-02

Pos logit contributions
bur+0.003
 fourteen+0.003
eling+0.003
ps+0.003
ck+0.003
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
 tum-0.003
 Nice-0.003
Token-
Token ID12
Feature activation-1.66e-03

Pos logit contributions
and+0.034
urry+0.029
 Follow+0.029
 Nice+0.026
 tum+0.025
Neg logit contributions
bur-0.036
 fourteen-0.036
eling-0.035
ps-0.035
 blew-0.034
Tokenyear
Token ID1941
Feature activation-8.62e-02

Pos logit contributions
and+0.002
urry+0.001
 Follow+0.001
 of+0.001
 Go+0.001
Neg logit contributions
bur-0.004
eling-0.004
 fourteen-0.004
ps-0.004
ible-0.003
Token-
Token ID12
Feature activation-1.64e-03

Pos logit contributions
and+0.143
 Follow+0.126
urry+0.123
 Nice+0.116
 Stay+0.112
Neg logit contributions
bur-0.119
 fourteen-0.118
ps-0.117
eling-0.115
ck-0.114
Tokenold
Token ID727
Feature activation+3.82e-02

Pos logit contributions
and+0.002
urry+0.002
 Follow+0.002
 Nice+0.001
 tum+0.001
Neg logit contributions
bur-0.003
 fourteen-0.003
eling-0.003
ps-0.003
ck-0.003
Token son
Token ID3367
Feature activation-6.95e-03

Pos logit contributions
bur+0.056
 fourteen+0.054
eling+0.053
ps+0.053
 blew+0.052
Neg logit contributions
and-0.062
urry-0.054
 Follow-0.053
 Nice-0.048
 tum-0.048
Token,
Token ID11
Feature activation-1.09e-02

Pos logit contributions
and+0.013
urry+0.011
 Follow+0.011
 Nice+0.010
 tum+0.010
Neg logit contributions
bur-0.009
 fourteen-0.008
eling-0.008
ps-0.008
 blew-0.008
Token happy
Token ID3772
Feature activation+1.34e-02

Pos logit contributions
and+0.014
 Follow+0.012
urry+0.012
 Stay+0.012
 tum+0.012
Neg logit contributions
bur-0.019
lled-0.018
ible-0.018
 fourteen-0.018
rob-0.018
Token cube
Token ID23441
Feature activation+5.50e-02

Pos logit contributions
and+0.000
urry+0.000
 Follow+0.000
 Nice+0.000
 tum+0.000
Neg logit contributions
bur-0.000
 fourteen-0.000
eling-0.000
ps-0.000
 blew-0.000
Token and
Token ID290
Feature activation-5.62e-03

Pos logit contributions
 fourteen+0.073
eling+0.073
bur+0.072
ps+0.070
IT+0.070
Neg logit contributions
and-0.094
 Follow-0.082
urry-0.082
 tum-0.081
 story-0.079
Token the
Token ID262
Feature activation+2.41e-04

Pos logit contributions
and+0.011
 Follow+0.010
 of+0.009
 tum+0.009
urry+0.009
Neg logit contributions
bur-0.007
 fourteen-0.007
ps-0.006
eling-0.006
ible-0.006
Token 3
Token ID513
Feature activation-4.40e-02

Pos logit contributions
bur+0.000
 fourteen+0.000
eling+0.000
ps+0.000
 blew+0.000
Neg logit contributions
and-0.000
urry-0.000
 Follow-0.000
 Nice-0.000
 tum-0.000
Token-
Token ID12
Feature activation+4.10e-03

Pos logit contributions
and+0.044
urry+0.034
 Follow+0.033
 Nice+0.028
 tum+0.027
Neg logit contributions
bur-0.092
 fourteen-0.091
eling-0.090
ps-0.089
 blew-0.088
Tokenyear
Token ID1941
Feature activation-8.61e-02

Pos logit contributions
bur+0.008
 fourteen+0.008
eling+0.008
ps+0.008
ck+0.008
Neg logit contributions
and-0.005
urry-0.004
 Follow-0.004
 Nice-0.003
 tum-0.003
Token-
Token ID12
Feature activation+4.21e-03

Pos logit contributions
and+0.161
 Follow+0.145
 Nice+0.140
urry+0.136
 Today+0.133
Neg logit contributions
ck-0.106
ps-0.105
 fourteen-0.096
eling-0.094
bur-0.094
Tokenold
Token ID727
Feature activation+3.85e-02

Pos logit contributions
bur+0.007
ck+0.007
 fourteen+0.007
eling+0.007
ps+0.007
Neg logit contributions
and-0.005
 Follow-0.004
urry-0.004
 Nice-0.004
 Today-0.004
Token girl
Token ID2576
Feature activation-1.55e-02

Pos logit contributions
bur+0.049
 fourteen+0.047
eling+0.046
ps+0.046
 blew+0.045
Neg logit contributions
and-0.070
urry-0.062
 Follow-0.061
 Nice-0.056
 tum-0.056
Token were
Token ID547
Feature activation+3.21e-03

Pos logit contributions
and+0.027
urry+0.024
 Follow+0.024
 tum+0.022
 Stay+0.022
Neg logit contributions
bur-0.020
 fourteen-0.020
eling-0.020
ps-0.019
IT-0.019
Token very
Token ID845
Feature activation+1.79e-02

Pos logit contributions
 fourteen+0.005
bur+0.005
eling+0.005
ible+0.005
IT+0.005
Neg logit contributions
and-0.005
urry-0.004
 Follow-0.004
 tum-0.004
 of-0.004
Token.
Token ID13
Feature activation+4.21e-04

Pos logit contributions
bur+0.024
 fourteen+0.023
eling+0.022
ps+0.022
 blew+0.022
Neg logit contributions
and-0.046
urry-0.041
 Follow-0.040
 Nice-0.038
 tum-0.038
Token
Token ID198
Feature activation-3.61e-03

Pos logit contributions
eling+0.001
bur+0.001
cking+0.001
ck+0.001
lled+0.001
Neg logit contributions
and-0.001
 Follow-0.000
urry-0.000
 Today-0.000
 Nice-0.000
Token
Token ID198
Feature activation-2.57e-03

Pos logit contributions
and+0.005
urry+0.004
 Follow+0.004
 Nice+0.004
 tum+0.004
Neg logit contributions
bur-0.006
 fourteen-0.006
eling-0.006
ps-0.006
 blew-0.006
Token"
Token ID1
Feature activation+3.19e-02

Pos logit contributions
and+0.005
urry+0.004
 Follow+0.004
 Stay+0.004
 Go+0.004
Neg logit contributions
bur-0.004
ps-0.003
 fourteen-0.003
eling-0.003
ible-0.003
TokenRo
Token ID15450
Feature activation-2.64e-02

Pos logit contributions
eling+0.049
ries+0.048
ps+0.048
abi+0.047
ible+0.047
Neg logit contributions
and-0.047
 Follow-0.040
 Stay-0.039
 Go-0.039
 Watch-0.038
Tokenaaa
Token ID46071
Feature activation-8.61e-02

Pos logit contributions
and+0.038
urry+0.032
 Follow+0.032
 tum+0.028
 Nice+0.028
Neg logit contributions
bur-0.044
 fourteen-0.043
eling-0.042
ps-0.042
 blew-0.041
Tokenar
Token ID283
Feature activation+3.92e-03

Pos logit contributions
and+0.145
 Follow+0.127
vere+0.123
 halls+0.117
urry+0.116
Neg logit contributions
bur-0.110
 fourteen-0.109
ible-0.103
et-0.103
 blew-0.101
Token!"
Token ID2474
Feature activation+2.77e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
 blew+0.006
Neg logit contributions
and-0.006
urry-0.005
 Follow-0.005
 Nice-0.005
 tum-0.005
Token she
Token ID673
Feature activation+6.78e-03

Pos logit contributions
bur+0.045
eling+0.042
cking+0.041
lled+0.041
ps+0.041
Neg logit contributions
and-0.042
 Follow-0.038
 tum-0.037
 of-0.036
urry-0.036
Token shouted
Token ID17293
Feature activation-1.75e-02

Pos logit contributions
bur+0.009
 fourteen+0.009
eling+0.008
ps+0.008
IT+0.008
Neg logit contributions
and-0.012
 Follow-0.011
urry-0.011
 tum-0.010
 Stay-0.010
Token.
Token ID13
Feature activation-7.15e-03

Pos logit contributions
and+0.033
urry+0.029
 Follow+0.029
 Nice+0.026
 tum+0.026
Neg logit contributions
bur-0.021
 fourteen-0.021
ps-0.020
eling-0.020
 blew-0.020
Token said
Token ID531
Feature activation-1.29e-02

Pos logit contributions
and+0.012
urry+0.011
 Follow+0.011
 tum+0.010
 Stay+0.010
Neg logit contributions
 fourteen-0.008
bur-0.008
ps-0.007
ible-0.007
lled-0.007
Token to
Token ID284
Feature activation+1.92e-02

Pos logit contributions
and+0.024
 Follow+0.023
urry+0.020
suits+0.020
ooters+0.019
Neg logit contributions
 her-0.017
 fourteen-0.016
 blew-0.015
 how-0.014
 just-0.014
Token her
Token ID607
Feature activation+8.41e-04

Pos logit contributions
cking+0.019
 fourteen+0.019
lled+0.018
 blew+0.018
ps+0.018
Neg logit contributions
and-0.036
 School-0.035
 Stay-0.035
urry-0.034
 Go-0.033
Token 3
Token ID513
Feature activation-4.36e-02

Pos logit contributions
bur+0.001
 fourteen+0.001
eling+0.001
ps+0.001
 blew+0.001
Neg logit contributions
and-0.001
urry-0.001
 Follow-0.001
 Nice-0.001
 tum-0.001
Token-
Token ID12
Feature activation+3.28e-03

Pos logit contributions
and+0.058
 Follow+0.051
urry+0.048
 Nice+0.043
rav+0.043
Neg logit contributions
eling-0.074
bur-0.073
ps-0.073
ck-0.072
 fourteen-0.071
Tokenyear
Token ID1941
Feature activation-8.60e-02

Pos logit contributions
bur+0.007
 fourteen+0.007
ps+0.007
eling+0.007
 blew+0.007
Neg logit contributions
and-0.003
urry-0.002
 Follow-0.002
 Stay-0.002
aring-0.002
Token-
Token ID12
Feature activation+3.23e-03

Pos logit contributions
and+0.156
 Follow+0.141
urry+0.133
 Nice+0.131
rav+0.127
Neg logit contributions
ps-0.104
ck-0.102
bur-0.102
eling-0.100
 fourteen-0.098
Tokenold
Token ID727
Feature activation+3.77e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
ck+0.006
Neg logit contributions
and-0.004
 Follow-0.003
urry-0.003
 Nice-0.003
 tum-0.003
Token son
Token ID3367
Feature activation-8.78e-03

Pos logit contributions
bur+0.061
 fourteen+0.060
eling+0.059
ps+0.059
 blew+0.057
Neg logit contributions
and-0.056
urry-0.047
 Follow-0.047
 tum-0.042
 Nice-0.042
Token,
Token ID11
Feature activation-9.97e-03

Pos logit contributions
and+0.012
 Follow+0.010
urry+0.010
 tum+0.008
vere+0.008
Neg logit contributions
bur-0.015
 fourteen-0.015
ps-0.014
eling-0.014
ible-0.014
Token "
Token ID366
Feature activation-1.13e-02

Pos logit contributions
and+0.015
urry+0.013
 Follow+0.012
 Stay+0.012
 Nice+0.011
Neg logit contributions
ps-0.016
bur-0.016
eling-0.016
 fourteen-0.016
lled-0.016
Token your
Token ID534
Feature activation-1.90e-02

Pos logit contributions
IT+0.024
ries+0.023
 fourteen+0.023
ami+0.023
ible+0.023
Neg logit contributions
and-0.021
 welcome-0.020
urry-0.019
 of-0.018
 Follow-0.018
Token friend
Token ID1545
Feature activation+1.97e-02

Pos logit contributions
and+0.028
urry+0.024
 Follow+0.023
 tum+0.021
 Nice+0.021
Neg logit contributions
bur-0.031
 fourteen-0.031
eling-0.031
ps-0.030
 blew-0.029
Token."
Token ID526
Feature activation+8.86e-03

Pos logit contributions
bur+0.023
 fourteen+0.022
ps+0.022
eling+0.021
 blew+0.021
Neg logit contributions
and-0.038
urry-0.033
 Follow-0.033
 Nice-0.030
 tum-0.030
Token
Token ID198
Feature activation+3.55e-05

Pos logit contributions
bur+0.014
 fourteen+0.014
eling+0.013
ps+0.013
 blew+0.013
Neg logit contributions
and-0.013
urry-0.011
 Follow-0.011
 Nice-0.010
 tum-0.010
Token
Token ID198
Feature activation+2.57e-04

Pos logit contributions
bur+0.000
 fourteen+0.000
eling+0.000
ps+0.000
 blew+0.000
Neg logit contributions
and-0.000
 Follow-0.000
urry-0.000
 Nice-0.000
 tum-0.000
TokenS
Token ID50
Feature activation+6.70e-02

Pos logit contributions
ps+0.000
bur+0.000
ible+0.000
 fourteen+0.000
IT+0.000
Neg logit contributions
and-0.000
urry-0.000
 Follow-0.000
 Stay-0.000
 Go-0.000
Tokenara
Token ID3301
Feature activation-1.66e-02

Pos logit contributions
bur+0.089
lled+0.088
ps+0.088
 fourteen+0.087
cking+0.086
Neg logit contributions
and-0.111
urry-0.100
 Follow-0.095
 story-0.092
 tum-0.092
Token is
Token ID318
Feature activation+1.63e-02

Pos logit contributions
and+0.026
 Follow+0.022
urry+0.022
 tum+0.020
 Stay+0.020
Neg logit contributions
bur-0.025
 fourteen-0.025
eling-0.024
ps-0.023
 blew-0.023
Token not
Token ID407
Feature activation+2.79e-02

Pos logit contributions
bur+0.029
 fourteen+0.029
ible+0.029
eling+0.028
ami+0.028
Neg logit contributions
and-0.021
urry-0.018
 Follow-0.018
 tum-0.016
 Stay-0.016
Token sure
Token ID1654
Feature activation+2.16e-02

Pos logit contributions
 fourteen+0.057
IT+0.055
neath+0.055
eling+0.054
ible+0.053
Neg logit contributions
and-0.033
 welcome-0.027
urry-0.026
 of-0.023
 story-0.023
Token.
Token ID13
Feature activation+1.66e-03

Pos logit contributions
bur+0.027
 fourteen+0.026
ps+0.025
eling+0.025
 blew+0.025
Neg logit contributions
and-0.041
urry-0.036
 Follow-0.035
 tum-0.033
 Nice-0.033
Token very
Token ID845
Feature activation+5.31e-03

Pos logit contributions
bur+0.008
 fourteen+0.008
ible+0.008
eling+0.008
IT+0.008
Neg logit contributions
and-0.006
urry-0.005
 Follow-0.005
apping-0.004
 tum-0.004
Token happy
Token ID3772
Feature activation+1.24e-02

Pos logit contributions
bur+0.009
 fourteen+0.009
eling+0.009
ps+0.008
 blew+0.008
Neg logit contributions
and-0.008
urry-0.006
 Follow-0.006
 tum-0.006
 Nice-0.006
Token.
Token ID13
Feature activation-3.99e-03

Pos logit contributions
bur+0.019
eling+0.018
 fourteen+0.018
ps+0.017
IT+0.017
Neg logit contributions
and-0.021
urry-0.017
 of-0.017
 birthday-0.017
apping-0.016
Token They
Token ID1119
Feature activation+1.18e-02

Pos logit contributions
and+0.005
urry+0.004
 Follow+0.004
 Nice+0.004
 tum+0.004
Neg logit contributions
bur-0.007
eling-0.007
 fourteen-0.007
ps-0.007
ck-0.007
Token took
Token ID1718
Feature activation+3.26e-02

Pos logit contributions
bur+0.018
eling+0.017
 fourteen+0.017
ries+0.017
ps+0.016
Neg logit contributions
and-0.018
urry-0.016
 Follow-0.016
 tum-0.015
 of-0.015
Token turns
Token ID4962
Feature activation+5.80e-02

Pos logit contributions
eling+0.043
bur+0.043
IT+0.039
ami+0.039
rob+0.038
Neg logit contributions
and-0.056
 tum-0.052
 of-0.051
urry-0.049
 Follow-0.048
Token to
Token ID284
Feature activation+1.70e-02

Pos logit contributions
bur+0.097
eling+0.095
 fourteen+0.094
ps+0.091
ible+0.091
Neg logit contributions
and-0.085
urry-0.070
 Follow-0.067
 tum-0.063
apping-0.061
Token sit
Token ID1650
Feature activation-1.32e-02

Pos logit contributions
elle+0.032
rob+0.032
ible+0.032
awed+0.031
eling+0.031
Neg logit contributions
 birthday-0.016
 of-0.016
 welcome-0.016
 tum-0.015
 please-0.014
Token in
Token ID287
Feature activation-3.75e-02

Pos logit contributions
and+0.019
urry+0.016
 Follow+0.016
apping+0.015
 tum+0.014
Neg logit contributions
 fourteen-0.021
eling-0.021
bur-0.020
ps-0.020
lled-0.020
Token the
Token ID262
Feature activation-2.93e-03

Pos logit contributions
and+0.061
 of+0.056
 birthday+0.056
 story+0.054
 tum+0.052
Neg logit contributions
eling-0.053
bur-0.050
ible-0.048
 fourteen-0.047
cking-0.047
Token pumpkin
Token ID30089
Feature activation+3.07e-02

Pos logit contributions
and+0.005
urry+0.004
 Follow+0.004
 tum+0.004
 birthday+0.004
Neg logit contributions
bur-0.004
eling-0.004
 fourteen-0.004
ps-0.004
lled-0.004
Token Her
Token ID2332
Feature activation+1.28e-02

Pos logit contributions
and+0.003
urry+0.002
 Follow+0.002
 Nice+0.002
 tum+0.002
Neg logit contributions
bur-0.003
 fourteen-0.003
ps-0.003
eling-0.003
 blew-0.002
Token dad
Token ID9955
Feature activation+9.69e-04

Pos logit contributions
bur+0.018
ps+0.017
 fourteen+0.017
 blew+0.017
eling+0.017
Neg logit contributions
and-0.022
 Follow-0.019
urry-0.019
 Nice-0.018
 Stay-0.017
Token asked
Token ID1965
Feature activation+5.76e-03

Pos logit contributions
 fourteen+0.001
bur+0.001
ps+0.001
eling+0.001
IT+0.001
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
 tum-0.001
 Stay-0.001
Token,
Token ID11
Feature activation-9.05e-03

Pos logit contributions
bur+0.002
 fourteen+0.002
ps+0.002
eling+0.002
 her+0.002
Neg logit contributions
and-0.015
 Follow-0.014
urry-0.014
 tum-0.013
 Nice-0.013
Token "
Token ID366
Feature activation-1.03e-02

Pos logit contributions
and+0.012
urry+0.010
 Follow+0.010
 tum+0.008
 Nice+0.008
Neg logit contributions
bur-0.016
 fourteen-0.016
eling-0.016
ps-0.016
 blew-0.015
TokenWhy
Token ID5195
Feature activation+5.73e-02

Pos logit contributions
and+0.022
 Follow+0.018
 Stay+0.017
urry+0.017
 Come+0.017
Neg logit contributions
ps-0.011
ible-0.010
 fourteen-0.010
 pointer-0.010
abi-0.009
Token are
Token ID389
Feature activation+3.18e-03

Pos logit contributions
 blew+0.091
bur+0.090
ps+0.088
eling+0.087
 fourteen+0.087
Neg logit contributions
and-0.089
 Follow-0.074
urry-0.071
 Nice-0.066
apping-0.063
Token you
Token ID345
Feature activation-2.22e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
 blew+0.006
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
 tum-0.003
 Nice-0.003
Token crying
Token ID13774
Feature activation-3.95e-03

Pos logit contributions
and+0.034
urry+0.030
 Follow+0.029
 tum+0.026
 Nice+0.026
Neg logit contributions
bur-0.034
 fourteen-0.034
eling-0.033
ps-0.032
ible-0.032
Token?".
Token ID43634
Feature activation+7.15e-03

Pos logit contributions
and+0.007
 Follow+0.006
urry+0.006
rav+0.005
engu+0.005
Neg logit contributions
bur-0.006
 fourteen-0.005
 blew-0.005
ps-0.005
eling-0.005
Token Mary
Token ID5335
Feature activation-3.47e-03

Pos logit contributions
bur+0.012
ps+0.011
eling+0.011
cking+0.011
 fourteen+0.011
Neg logit contributions
and-0.011
 Follow-0.009
urry-0.009
 Today-0.009
 Stay-0.009
Token.
Token ID13
Feature activation-1.36e-03

Pos logit contributions
and+0.048
 Follow+0.044
urry+0.040
 halls+0.040
uggle+0.040
Neg logit contributions
 fourteen-0.022
ps-0.021
bur-0.021
 just-0.020
 her-0.020
Token I
Token ID314
Feature activation-3.02e-02

Pos logit contributions
and+0.002
 halls+0.001
suits+0.001
vere+0.001
 story+0.001
Neg logit contributions
 fourteen-0.002
bur-0.002
IT-0.002
 blew-0.002
ps-0.002
Token don
Token ID836
Feature activation-2.39e-02

Pos logit contributions
and+0.044
urry+0.039
 Follow+0.037
 tum+0.034
 Stay+0.033
Neg logit contributions
bur-0.049
 fourteen-0.049
eling-0.047
ps-0.047
ries-0.046
Token't
Token ID470
Feature activation+1.49e-02

Pos logit contributions
and+0.047
 Follow+0.041
urry+0.040
 tum+0.038
 Nice+0.037
Neg logit contributions
bur-0.027
 fourteen-0.027
ps-0.027
 blew-0.027
eling-0.026
Token like
Token ID588
Feature activation-2.84e-03

Pos logit contributions
bur+0.025
 fourteen+0.024
eling+0.024
ps+0.024
 blew+0.023
Neg logit contributions
and-0.021
 Follow-0.018
urry-0.018
 Nice-0.016
 tum-0.016
Token brushes
Token ID36377
Feature activation+5.65e-02

Pos logit contributions
and+0.005
urry+0.004
 Follow+0.004
 tum+0.004
 Go+0.004
Neg logit contributions
bur-0.004
 fourteen-0.004
eling-0.003
lled-0.003
ps-0.003
Token."
Token ID526
Feature activation+7.85e-03

Pos logit contributions
bur+0.086
eling+0.084
 fourteen+0.083
ps+0.081
 blew+0.081
Neg logit contributions
and-0.088
urry-0.074
 Follow-0.072
 tum-0.068
 Nice-0.067
Token
Token ID220
Feature activation-6.07e-03

Pos logit contributions
eling+0.016
lled+0.016
ps+0.015
 fourteen+0.015
bur+0.015
Neg logit contributions
and-0.009
urry-0.007
 Follow-0.007
 tum-0.007
 Nice-0.006
Token
Token ID198
Feature activation+6.36e-04

Pos logit contributions
and+0.009
urry+0.007
 Follow+0.007
 tum+0.007
 Nice+0.006
Neg logit contributions
bur-0.010
 fourteen-0.010
eling-0.010
ps-0.010
 blew-0.009
Token
Token ID198
Feature activation+1.85e-03

Pos logit contributions
bur+0.001
 fourteen+0.001
eling+0.001
ps+0.001
 blew+0.001
Neg logit contributions
and-0.001
urry-0.001
 Follow-0.001
 tum-0.001
 Nice-0.001
TokenL
Token ID43
Feature activation+1.64e-02

Pos logit contributions
ps+0.002
 fourteen+0.002
bur+0.002
eling+0.002
ible+0.002
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
 Stay-0.003
 tum-0.003
Token There
Token ID1318
Feature activation+3.89e-03

Pos logit contributions
 her+0.013
IT+0.011
neath+0.010
Why+0.010
 fourteen+0.010
Neg logit contributions
and-0.027
vere-0.023
ye-0.022
rav-0.022
urry-0.022
Token was
Token ID373
Feature activation+9.71e-03

Pos logit contributions
 blew+0.004
 her+0.004
bur+0.004
lled+0.004
ck+0.004
Neg logit contributions
and-0.008
 Follow-0.007
urry-0.007
aring-0.007
ooters-0.007
Token a
Token ID257
Feature activation-4.33e-03

Pos logit contributions
bur+0.010
eling+0.009
 fourteen+0.009
ps+0.009
ck+0.009
Neg logit contributions
and-0.020
 Follow-0.018
urry-0.018
 tum-0.017
 Nice-0.017
Token big
Token ID1263
Feature activation+1.63e-02

Pos logit contributions
and+0.009
urry+0.007
 Follow+0.007
 Go+0.007
aring+0.007
Neg logit contributions
 blew-0.005
bur-0.005
 comb-0.005
 pin-0.005
 sc-0.005
Token shiny
Token ID22441
Feature activation+2.21e-02

Pos logit contributions
 blew+0.021
bur+0.021
 fourteen+0.021
ible+0.020
et+0.019
Neg logit contributions
and-0.033
 Follow-0.026
urry-0.026
rav-0.024
anny-0.024
Token crane
Token ID41175
Feature activation+5.66e-02

Pos logit contributions
bur+0.028
 fourteen+0.027
 blew+0.027
ps+0.026
eling+0.026
Neg logit contributions
and-0.041
urry-0.036
 Follow-0.036
 Nice-0.032
 Stay-0.032
Token,
Token ID11
Feature activation-1.23e-03

Pos logit contributions
bur+0.072
 fourteen+0.072
ps+0.070
eling+0.069
ible+0.066
Neg logit contributions
and-0.102
urry-0.090
 Follow-0.088
 Nice-0.081
 tum-0.081
Token with
Token ID351
Feature activation+1.07e-02

Pos logit contributions
and+0.002
 Follow+0.002
urry+0.002
 Nice+0.002
 Stay+0.002
Neg logit contributions
bur-0.002
eling-0.002
 fourteen-0.002
ps-0.002
ible-0.002
Token two
Token ID734
Feature activation+2.51e-02

Pos logit contributions
bur+0.015
eling+0.014
 fourteen+0.014
IT+0.013
ps+0.013
Neg logit contributions
and-0.019
 Follow-0.016
 of-0.015
urry-0.015
 tum-0.015
Token people
Token ID661
Feature activation+7.23e-04

Pos logit contributions
 fourteen+0.032
ps+0.031
bur+0.031
eling+0.031
ible+0.031
Neg logit contributions
and-0.046
 Follow-0.041
urry-0.041
 School-0.037
uggle-0.036
Token operating
Token ID5361
Feature activation+2.49e-03

Pos logit contributions
bur+0.001
 fourteen+0.001
eling+0.001
ps+0.001
IT+0.001
Neg logit contributions
and-0.001
urry-0.001
 Follow-0.001
apping-0.001
 Nice-0.001
Token was
Token ID373
Feature activation+1.01e-02

Pos logit contributions
and+0.003
 Follow+0.003
urry+0.003
 story+0.003
 tum+0.003
Neg logit contributions
 fourteen-0.004
eling-0.003
cking-0.003
ps-0.003
bur-0.003
Token playing
Token ID2712
Feature activation-1.69e-02

Pos logit contributions
bur+0.013
eling+0.013
 fourteen+0.013
ps+0.013
 blew+0.013
Neg logit contributions
and-0.018
 Follow-0.016
urry-0.016
 Nice-0.015
rav-0.014
Token near
Token ID1474
Feature activation-3.55e-02

Pos logit contributions
and+0.026
 Follow+0.021
urry+0.021
 tum+0.019
 Stay+0.018
Neg logit contributions
bur-0.028
 fourteen-0.027
eling-0.026
ps-0.026
ible-0.026
Token the
Token ID262
Feature activation+1.33e-03

Pos logit contributions
and+0.060
 of+0.052
 tum+0.049
 Stay+0.049
 story+0.048
Neg logit contributions
 fourteen-0.050
bur-0.046
ps-0.046
eling-0.045
rob-0.045
Token door
Token ID3420
Feature activation-4.54e-02

Pos logit contributions
bur+0.002
 fourteen+0.002
 blew+0.002
ps+0.002
eling+0.002
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
 Nice-0.002
rav-0.002
Token when
Token ID618
Feature activation+1.95e-02

Pos logit contributions
and+0.077
urry+0.069
 Follow+0.069
rav+0.064
 Nice+0.063
Neg logit contributions
 fourteen-0.059
bur-0.059
eling-0.057
ps-0.057
 blew-0.056
Token his
Token ID465
Feature activation+1.21e-02

Pos logit contributions
ps+0.025
 fourteen+0.025
bur+0.024
ck+0.023
eling+0.023
Neg logit contributions
and-0.034
urry-0.031
 tum-0.030
 Follow-0.030
 Stay-0.029
Token mom
Token ID1995
Feature activation-4.57e-03

Pos logit contributions
bur+0.013
 blew+0.013
ps+0.013
 sc+0.012
 comb+0.012
Neg logit contributions
and-0.023
 Follow-0.021
urry-0.020
 Nice-0.019
aring-0.019
Tokenmy
Token ID1820
Feature activation+1.01e-02

Pos logit contributions
and+0.008
urry+0.007
 Follow+0.007
 tum+0.006
 Nice+0.006
Neg logit contributions
bur-0.006
 fourteen-0.006
eling-0.006
ps-0.006
 blew-0.006
Token told
Token ID1297
Feature activation-1.91e-02

Pos logit contributions
 fourteen+0.013
bur+0.013
eling+0.012
ps+0.012
ck+0.011
Neg logit contributions
and-0.019
urry-0.016
 Follow-0.016
 tum-0.015
 Nice-0.015
Token him
Token ID683
Feature activation-3.04e-02

Pos logit contributions
and+0.034
urry+0.030
 tum+0.030
 Stay+0.029
 story+0.029
Neg logit contributions
 fourteen-0.025
bur-0.024
cking-0.023
 blew-0.023
ps-0.023
Token waving
Token ID25849
Feature activation-1.66e-02

Pos logit contributions
ible+0.006
 fourteen+0.006
ami+0.006
IT+0.006
wy+0.006
Neg logit contributions
and-0.004
 welcome-0.004
 story-0.004
 birthday-0.004
apping-0.004
Token her
Token ID607
Feature activation+1.28e-03

Pos logit contributions
and+0.043
urry+0.040
 Follow+0.040
aring+0.037
engu+0.037
Neg logit contributions
 fourteen-0.008
ps-0.007
bur-0.007
 blew-0.007
eling-0.006
Token hand
Token ID1021
Feature activation-2.15e-02

Pos logit contributions
ps+0.002
bur+0.002
 blew+0.002
 fourteen+0.002
eling+0.002
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
 Nice-0.001
 Stay-0.001
Token and
Token ID290
Feature activation-5.91e-03

Pos logit contributions
and+0.037
 Follow+0.034
urry+0.033
rav+0.031
 Nice+0.031
Neg logit contributions
bur-0.027
 fourteen-0.027
ps-0.027
 blew-0.026
ible-0.025
Token saw
Token ID2497
Feature activation-7.39e-03

Pos logit contributions
and+0.011
urry+0.010
 Follow+0.010
 Nice+0.009
 tum+0.009
Neg logit contributions
bur-0.007
 fourteen-0.007
eling-0.007
ps-0.007
 blew-0.007
Token some
Token ID617
Feature activation+5.07e-03

Pos logit contributions
and+0.016
 Follow+0.013
urry+0.013
 tum+0.013
 of+0.013
Neg logit contributions
bur-0.008
 fourteen-0.007
eling-0.007
ps-0.007
ck-0.007
Token dolphins
Token ID36798
Feature activation-3.95e-02

Pos logit contributions
 blew+0.006
eling+0.006
ps+0.006
 fourteen+0.005
lled+0.005
Neg logit contributions
and-0.010
urry-0.009
 Follow-0.009
 Today-0.008
 Nice-0.008
Token swimming
Token ID14899
Feature activation-3.39e-02

Pos logit contributions
and+0.076
urry+0.066
 Follow+0.066
 tum+0.062
rav+0.061
Neg logit contributions
bur-0.044
ps-0.044
 fourteen-0.043
 blew-0.043
eling-0.043
Token by
Token ID416
Feature activation-9.43e-03

Pos logit contributions
and+0.064
urry+0.060
 Follow+0.058
 tum+0.056
rav+0.055
Neg logit contributions
ps-0.036
bur-0.036
 blew-0.035
lled-0.035
 fourteen-0.033
Token in
Token ID287
Feature activation-3.11e-02

Pos logit contributions
and+0.016
urry+0.013
 of+0.012
 birthday+0.012
 Follow+0.012
Neg logit contributions
bur-0.015
 fourteen-0.014
eling-0.013
 blew-0.013
ible-0.013
Token the
Token ID262
Feature activation-1.13e-03

Pos logit contributions
and+0.056
 of+0.050
 story+0.049
 welcome+0.048
 birthday+0.048
Neg logit contributions
bur-0.038
 fourteen-0.037
eling-0.037
ible-0.036
 blew-0.036
Token sad
Token ID6507
Feature activation+1.93e-02

Pos logit contributions
bur+0.030
eling+0.029
 blew+0.029
 fourteen+0.029
ck+0.029
Neg logit contributions
and-0.030
 Follow-0.025
urry-0.024
 Nice-0.023
 Today-0.022
Token but
Token ID475
Feature activation-1.68e-03

Pos logit contributions
bur+0.032
eling+0.030
 fourteen+0.030
ps+0.030
ck+0.029
Neg logit contributions
and-0.030
urry-0.025
 Follow-0.023
 tum-0.023
 of-0.022
Token he
Token ID339
Feature activation+5.32e-03

Pos logit contributions
and+0.003
urry+0.003
 Follow+0.003
 Nice+0.003
 tum+0.003
Neg logit contributions
bur-0.002
eling-0.002
 fourteen-0.002
 blew-0.002
ps-0.002
Token was
Token ID373
Feature activation+1.26e-02

Pos logit contributions
 fourteen+0.008
bur+0.008
ps+0.007
eling+0.007
ries+0.007
Neg logit contributions
and-0.009
 Follow-0.008
urry-0.008
 tum-0.007
 Stay-0.007
Token also
Token ID635
Feature activation+6.48e-03

Pos logit contributions
 fourteen+0.021
bur+0.021
ible+0.020
eling+0.020
IT+0.020
Neg logit contributions
and-0.018
urry-0.016
 Follow-0.015
 tum-0.014
apping-0.014
Token excited
Token ID6568
Feature activation+1.89e-02

Pos logit contributions
bur+0.010
 fourteen+0.010
eling+0.010
ps+0.010
 blew+0.010
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
 Nice-0.007
 tum-0.007
Token because
Token ID780
Feature activation+8.64e-03

Pos logit contributions
bur+0.034
 fourteen+0.033
eling+0.033
ps+0.033
 blew+0.032
Neg logit contributions
and-0.026
urry-0.021
 Follow-0.020
 tum-0.018
 Nice-0.018
Token he
Token ID339
Feature activation+5.37e-03

Pos logit contributions
bur+0.009
 fourteen+0.008
eling+0.008
 blew+0.008
ps+0.008
Neg logit contributions
and-0.018
urry-0.016
 Follow-0.016
 tum-0.015
 Nice-0.015
Token knew
Token ID2993
Feature activation-7.33e-03

Pos logit contributions
 fourteen+0.009
bur+0.009
ps+0.009
ries+0.008
eling+0.008
Neg logit contributions
and-0.008
 Follow-0.007
urry-0.007
 tum-0.006
 Stay-0.006
Token his
Token ID465
Feature activation+1.07e-02

Pos logit contributions
and+0.013
urry+0.012
 Follow+0.011
 of+0.011
 tum+0.011
Neg logit contributions
 fourteen-0.009
bur-0.009
ps-0.009
eling-0.009
IT-0.009
Token dad
Token ID9955
Feature activation-2.08e-04

Pos logit contributions
bur+0.013
 fourteen+0.012
ps+0.012
 blew+0.012
eling+0.012
Neg logit contributions
and-0.021
 Follow-0.018
urry-0.017
 Nice-0.017
 Go-0.016
Token I
Token ID314
Feature activation-2.75e-02

Pos logit contributions
 fourteen+0.004
bur+0.004
 blew+0.004
ps+0.004
IT+0.004
Neg logit contributions
and-0.004
suits-0.003
 halls-0.002
urry-0.002
 story-0.002
Token'll
Token ID1183
Feature activation-2.20e-02

Pos logit contributions
and+0.036
urry+0.030
 Follow+0.029
 tum+0.026
 Nice+0.026
Neg logit contributions
bur-0.049
 fourteen-0.048
eling-0.048
ps-0.047
 blew-0.047
Token help
Token ID1037
Feature activation-9.82e-03

Pos logit contributions
urry+0.024
and+0.023
 Follow+0.022
 Stay+0.020
 tum+0.019
Neg logit contributions
 fourteen-0.041
ries-0.040
bur-0.040
rob-0.040
lled-0.040
Token you
Token ID345
Feature activation-2.20e-02

Pos logit contributions
and+0.014
urry+0.012
 Follow+0.012
 Nice+0.011
 tum+0.011
Neg logit contributions
bur-0.016
eling-0.016
 fourteen-0.016
ps-0.016
ck-0.015
Token."
Token ID526
Feature activation+9.11e-03

Pos logit contributions
and+0.035
urry+0.030
 Follow+0.030
 tum+0.027
 Nice+0.027
Neg logit contributions
bur-0.033
 fourteen-0.032
eling-0.032
ps-0.031
 blew-0.031
Token Roc
Token ID13545
Feature activation+7.46e-03

Pos logit contributions
bur+0.016
 fourteen+0.016
eling+0.016
ps+0.015
 blew+0.015
Neg logit contributions
and-0.012
urry-0.010
 Follow-0.010
 tum-0.009
 Nice-0.009
Tokenco
Token ID1073
Feature activation+2.59e-02

Pos logit contributions
 fourteen+0.008
bur+0.008
ps+0.008
 blew+0.008
lled+0.008
Neg logit contributions
and-0.015
urry-0.013
 Follow-0.013
aring-0.012
 Nice-0.012
Token pulled
Token ID5954
Feature activation+3.50e-02

Pos logit contributions
bur+0.034
 fourteen+0.033
ps+0.033
eling+0.032
IT+0.031
Neg logit contributions
and-0.046
urry-0.041
 Follow-0.039
 of-0.036
 Stay-0.035
Token the
Token ID262
Feature activation+6.44e-04

Pos logit contributions
bur+0.042
 fourteen+0.042
eling+0.041
 blew+0.039
ps+0.039
Neg logit contributions
and-0.067
urry-0.059
 Follow-0.058
 Nice-0.053
 Stay-0.053
Token carrot
Token ID40562
Feature activation-3.33e-03

Pos logit contributions
bur+0.001
 fourteen+0.001
ps+0.001
eling+0.001
 blew+0.001
Neg logit contributions
and-0.001
urry-0.001
 Follow-0.001
apping-0.001
 School-0.001
Token out
Token ID503
Feature activation+3.03e-03

Pos logit contributions
and+0.006
urry+0.005
 Follow+0.005
 Nice+0.004
 tum+0.004
Neg logit contributions
bur-0.005
 fourteen-0.005
ps-0.004
eling-0.004
 blew-0.004
Token no
Token ID645
Feature activation-1.68e-02

Pos logit contributions
and+0.003
 Follow+0.003
urry+0.003
 Nice+0.002
 tum+0.002
Neg logit contributions
bur-0.001
eling-0.001
ps-0.001
 fourteen-0.001
ck-0.001
Token worry
Token ID5490
Feature activation-2.77e-02

Pos logit contributions
and+0.034
urry+0.031
 tum+0.030
 of+0.030
 Follow+0.030
Neg logit contributions
bur-0.017
ps-0.016
 fourteen-0.016
eling-0.016
IT-0.015
Token in
Token ID287
Feature activation-2.89e-02

Pos logit contributions
and+0.050
urry+0.044
 Follow+0.044
 Nice+0.040
 tum+0.040
Neg logit contributions
bur-0.035
 fourteen-0.034
eling-0.033
ps-0.033
 blew-0.033
Token the
Token ID262
Feature activation+6.24e-03

Pos logit contributions
and+0.050
 of+0.045
urry+0.044
 birthday+0.044
 story+0.044
Neg logit contributions
bur-0.037
 fourteen-0.035
rob-0.035
eling-0.034
ami-0.033
Token world
Token ID995
Feature activation-4.43e-02

Pos logit contributions
bur+0.009
 fourteen+0.009
eling+0.009
ps+0.009
 blew+0.009
Neg logit contributions
and-0.010
urry-0.009
 Follow-0.009
 Nice-0.008
apping-0.008
Token.
Token ID13
Feature activation+7.76e-03

Pos logit contributions
and+0.080
urry+0.070
 Follow+0.068
 Nice+0.063
 of+0.063
Neg logit contributions
bur-0.058
 fourteen-0.056
eling-0.055
ps-0.054
ck-0.052
Token<|endoftext|>
Token ID50256
Feature activation+3.87e-03

Pos logit contributions
 fourteen+0.012
bur+0.012
ible+0.011
eling+0.011
IT+0.011
Neg logit contributions
and-0.012
urry-0.010
 Follow-0.010
vere-0.009
 tum-0.009
TokenOnce
Token ID7454
Feature activation+3.79e-02

Pos logit contributions
bur+0.004
 fourteen+0.004
ps+0.004
 blew+0.004
eling+0.004
Neg logit contributions
and-0.007
urry-0.007
 Follow-0.007
 tum-0.006
 Nice-0.006
Token upon
Token ID2402
Feature activation-3.70e-02

Pos logit contributions
bur+0.065
 fourteen+0.062
 blew+0.061
eling+0.061
ck+0.060
Neg logit contributions
and-0.051
 Follow-0.046
urry-0.038
 Go-0.037
 Stay-0.037
Token a
Token ID257
Feature activation-5.27e-03

Pos logit contributions
and+0.074
urry+0.063
 Follow+0.062
 Stay+0.060
 of+0.059
Neg logit contributions
bur-0.044
 fourteen-0.043
eling-0.041
ible-0.040
ps-0.040
Token time
Token ID640
Feature activation+1.79e-02

Pos logit contributions
and+0.008
 Follow+0.007
urry+0.007
 Nice+0.006
 tum+0.006
Neg logit contributions
bur-0.008
 fourteen-0.008
eling-0.008
ps-0.007
 blew-0.007
Token grabbed
Token ID13176
Feature activation+5.04e-02

Pos logit contributions
and+0.007
 Follow+0.006
urry+0.006
 tum+0.006
 Stay+0.006
Neg logit contributions
bur-0.005
 fourteen-0.005
ps-0.005
eling-0.004
ible-0.004
Token her
Token ID607
Feature activation+6.26e-03

Pos logit contributions
bur+0.046
eling+0.044
 blew+0.044
 fourteen+0.044
IT+0.042
Neg logit contributions
and-0.107
 Follow-0.096
urry-0.094
 tum-0.092
 of-0.091
Token arm
Token ID3211
Feature activation-1.85e-02

Pos logit contributions
bur+0.010
 fourteen+0.010
eling+0.009
ps+0.009
 blew+0.009
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
 tum-0.008
 Nice-0.007
Token.
Token ID13
Feature activation-3.38e-03

Pos logit contributions
and+0.034
 Follow+0.032
urry+0.031
rav+0.030
 Nice+0.029
Neg logit contributions
bur-0.021
 fourteen-0.020
ps-0.020
 blew-0.019
eling-0.019
Token Jen
Token ID13364
Feature activation+2.24e-02

Pos logit contributions
and+0.005
 Follow+0.004
urry+0.004
 Nice+0.004
 tum+0.004
Neg logit contributions
bur-0.006
eling-0.006
ps-0.006
 fourteen-0.006
ck-0.005
Token started
Token ID2067
Feature activation-2.91e-03

Pos logit contributions
 fourteen+0.034
bur+0.032
cking+0.031
ps+0.031
IT+0.031
Neg logit contributions
and-0.035
urry-0.031
 Follow-0.030
 of-0.028
 tum-0.028
Token to
Token ID284
Feature activation+1.70e-02

Pos logit contributions
and+0.003
urry+0.003
 Follow+0.002
 tum+0.002
 Stay+0.002
Neg logit contributions
 fourteen-0.006
bur-0.006
eling-0.006
ible-0.006
ps-0.005
Token cry
Token ID3960
Feature activation-3.21e-02

Pos logit contributions
 fourteen+0.032
bur+0.030
ible+0.029
ami+0.029
ps+0.029
Neg logit contributions
and-0.021
urry-0.019
 Follow-0.018
 Stay-0.017
 tum-0.016
Token and
Token ID290
Feature activation-8.02e-03

Pos logit contributions
and+0.053
urry+0.046
 Follow+0.045
 Nice+0.041
 tum+0.041
Neg logit contributions
bur-0.046
 fourteen-0.045
eling-0.044
ps-0.044
 blew-0.043
Token said
Token ID531
Feature activation-1.76e-02

Pos logit contributions
and+0.014
 Follow+0.013
urry+0.013
 tum+0.012
 Stay+0.012
Neg logit contributions
bur-0.010
 fourteen-0.010
ps-0.010
ible-0.010
eling-0.010
Token "
Token ID366
Feature activation-1.12e-02

Pos logit contributions
and+0.027
 Follow+0.023
urry+0.023
 Today+0.020
 Nice+0.019
Neg logit contributions
 fourteen-0.028
ps-0.027
 blew-0.027
eling-0.026
bur-0.026
Token each
Token ID1123
Feature activation-1.45e-02

Pos logit contributions
lled+0.026
bur+0.026
 fourteen+0.025
ps+0.025
eling+0.025
Neg logit contributions
and-0.032
urry-0.028
 tum-0.027
 Stay-0.026
 Follow-0.026
Token other
Token ID584
Feature activation-3.88e-03

Pos logit contributions
and+0.024
urry+0.020
 Follow+0.020
 tum+0.018
 Stay+0.018
Neg logit contributions
bur-0.021
 fourteen-0.021
eling-0.021
ps-0.020
 blew-0.020
Token and
Token ID290
Feature activation-7.88e-03

Pos logit contributions
and+0.007
urry+0.006
 Follow+0.006
 tum+0.006
 Nice+0.006
Neg logit contributions
bur-0.005
 fourteen-0.005
eling-0.005
ps-0.005
 blew-0.004
Token hug
Token ID16225
Feature activation-6.91e-03

Pos logit contributions
and+0.013
urry+0.011
 Follow+0.011
 Nice+0.011
 Today+0.010
Neg logit contributions
bur-0.011
 fourteen-0.011
ps-0.011
 blew-0.011
eling-0.011
Token.
Token ID13
Feature activation-5.74e-03

Pos logit contributions
and+0.014
urry+0.012
 Follow+0.012
 Nice+0.011
 tum+0.011
Neg logit contributions
bur-0.008
 fourteen-0.007
ps-0.007
eling-0.007
 blew-0.007
Token Fighting
Token ID19098
Feature activation-3.52e-03

Pos logit contributions
and+0.008
urry+0.007
rav+0.006
 Follow+0.006
suits+0.006
Neg logit contributions
 fourteen-0.009
bur-0.009
ps-0.009
ible-0.009
abi-0.008
Token is
Token ID318
Feature activation+1.11e-02

Pos logit contributions
and+0.005
urry+0.005
 Follow+0.005
 tum+0.004
 Nice+0.004
Neg logit contributions
ps-0.005
 blew-0.005
bur-0.005
 fourteen-0.005
mill-0.005
Token not
Token ID407
Feature activation+2.38e-02

Pos logit contributions
bur+0.018
ami+0.018
rob+0.018
ible+0.017
IT+0.017
Neg logit contributions
and-0.014
urry-0.013
 Stay-0.013
 Follow-0.013
 of-0.013
Token good
Token ID922
Feature activation+2.66e-02

Pos logit contributions
bur+0.043
eling+0.042
 fourteen+0.042
ami+0.041
IT+0.040
Neg logit contributions
and-0.031
urry-0.025
 Follow-0.024
 Stay-0.023
 of-0.023
Token.
Token ID13
Feature activation-4.38e-03

Pos logit contributions
bur+0.038
 fourteen+0.037
eling+0.037
ps+0.036
ck+0.035
Neg logit contributions
and-0.044
urry-0.038
 Follow-0.038
 tum-0.035
 Nice-0.034
Token It
Token ID632
Feature activation-1.75e-02

Pos logit contributions
and+0.005
urry+0.004
 Follow+0.004
 tum+0.004
 Nice+0.004
Neg logit contributions
bur-0.008
 fourteen-0.008
eling-0.008
ps-0.008
 blew-0.008
TokenLet
Token ID5756
Feature activation+1.12e-02

Pos logit contributions
and+0.011
 Follow+0.009
 Go+0.008
 Stay+0.008
urry+0.008
Neg logit contributions
ps-0.009
ries-0.009
eling-0.009
 fourteen-0.009
ible-0.008
Token me
Token ID502
Feature activation-3.90e-02

Pos logit contributions
 fourteen+0.021
bur+0.021
ps+0.021
eling+0.021
cking+0.020
Neg logit contributions
and-0.013
urry-0.011
 Follow-0.010
 tum-0.009
 Stay-0.009
Token go
Token ID467
Feature activation-1.14e-02

Pos logit contributions
and+0.062
 Follow+0.051
urry+0.051
 Nice+0.049
 tum+0.047
Neg logit contributions
bur-0.059
 fourteen-0.056
ps-0.056
eling-0.055
 blew-0.055
Token!
Token ID0
Feature activation-3.96e-03

Pos logit contributions
and+0.018
urry+0.015
 Follow+0.015
 Nice+0.014
 tum+0.014
Neg logit contributions
bur-0.017
 fourteen-0.017
eling-0.017
ps-0.017
 blew-0.016
Token Please
Token ID4222
Feature activation-4.71e-02

Pos logit contributions
and+0.005
 halls+0.004
urry+0.004
suits+0.004
 tum+0.004
Neg logit contributions
 fourteen-0.007
bur-0.007
IT-0.007
 blew-0.006
ps-0.006
Token,
Token ID11
Feature activation-6.83e-03

Pos logit contributions
and+0.079
 Follow+0.063
urry+0.063
 Nice+0.060
 tum+0.060
Neg logit contributions
bur-0.072
ps-0.068
 fourteen-0.067
 blew-0.066
eling-0.066
Token I
Token ID314
Feature activation-2.72e-02

Pos logit contributions
and+0.011
 halls+0.009
apping+0.009
urry+0.009
 Follow+0.009
Neg logit contributions
bur-0.010
 blew-0.009
 fourteen-0.009
ps-0.009
ck-0.009
Token want
Token ID765
Feature activation-1.83e-02

Pos logit contributions
and+0.040
 Follow+0.032
urry+0.032
 Nice+0.029
 tum+0.029
Neg logit contributions
bur-0.045
 fourteen-0.044
eling-0.043
 blew-0.043
ps-0.043
Token to
Token ID284
Feature activation+2.02e-02

Pos logit contributions
and+0.029
urry+0.026
 Follow+0.026
apping+0.024
 Today+0.023
Neg logit contributions
bur-0.027
 fourteen-0.026
 blew-0.025
ps-0.025
ck-0.024
Token go
Token ID467
Feature activation-1.27e-02

Pos logit contributions
 fourteen+0.036
bur+0.035
eling+0.035
ible+0.035
lled+0.034
Neg logit contributions
and-0.025
urry-0.022
 Follow-0.021
 Stay-0.020
 tum-0.020
Token home
Token ID1363
Feature activation-3.90e-02

Pos logit contributions
and+0.021
urry+0.018
 Follow+0.018
 tum+0.016
 Nice+0.016
Neg logit contributions
bur-0.019
 fourteen-0.018
ps-0.018
eling-0.018
 blew-0.017
Token day
Token ID1110
Feature activation+1.56e-02

Pos logit contributions
and+0.014
 Follow+0.013
urry+0.012
ooters+0.011
vere+0.011
Neg logit contributions
bur-0.017
 blew-0.017
 fourteen-0.017
ible-0.016
eling-0.016
Token on
Token ID319
Feature activation-4.98e-03

Pos logit contributions
bur+0.017
 fourteen+0.017
 blew+0.017
ps+0.017
eling+0.016
Neg logit contributions
and-0.031
 Follow-0.027
urry-0.026
 Nice-0.025
engu-0.025
Token,
Token ID11
Feature activation-5.02e-03

Pos logit contributions
and+0.006
urry+0.005
 Follow+0.005
 Nice+0.004
 tum+0.004
Neg logit contributions
bur-0.010
 fourteen-0.009
eling-0.009
ps-0.009
 blew-0.009
Token Lily
Token ID20037
Feature activation+1.46e-02

Pos logit contributions
and+0.007
 of+0.006
 tum+0.006
urry+0.006
 birthday+0.006
Neg logit contributions
bur-0.009
ps-0.009
eling-0.009
cking-0.008
ible-0.008
Token learned
Token ID4499
Feature activation-2.19e-02

Pos logit contributions
 fourteen+0.022
eling+0.022
bur+0.022
cking+0.021
ck+0.021
Neg logit contributions
and-0.023
urry-0.019
 Follow-0.019
 tum-0.018
 of-0.018
Token that
Token ID326
Feature activation-1.20e-02

Pos logit contributions
and+0.030
 of+0.024
urry+0.022
 story+0.022
 birthday+0.021
Neg logit contributions
bur-0.042
eling-0.042
ible-0.041
 fourteen-0.040
ps-0.039
Token it
Token ID340
Feature activation-8.44e-03

Pos logit contributions
and+0.026
 Follow+0.025
suits+0.025
urry+0.025
ari+0.024
Neg logit contributions
 blew-0.011
 her-0.010
Why-0.009
bur-0.009
mill-0.009
Token's
Token ID338
Feature activation-2.10e-02

Pos logit contributions
and+0.011
urry+0.009
 Follow+0.009
 tum+0.008
 Nice+0.008
Neg logit contributions
bur-0.015
 fourteen-0.015
eling-0.014
ps-0.014
 blew-0.014
Token okay
Token ID8788
Feature activation-1.97e-02

Pos logit contributions
and+0.020
urry+0.017
 Follow+0.015
 Stay+0.014
 story+0.014
Neg logit contributions
 fourteen-0.044
ries-0.042
eling-0.042
rob-0.042
ps-0.042
Token to
Token ID284
Feature activation+2.07e-02

Pos logit contributions
and+0.031
 Follow+0.029
urry+0.028
vere+0.027
engu+0.026
Neg logit contributions
 blew-0.027
bur-0.027
ps-0.025
 fourteen-0.025
ible-0.025
Token make
Token ID787
Feature activation+1.88e-02

Pos logit contributions
bur+0.032
 fourteen+0.032
ps+0.031
eling+0.031
lled+0.030
Neg logit contributions
and-0.031
urry-0.028
 Follow-0.026
 Stay-0.024
 tum-0.024
Token the
Token ID262
Feature activation+5.91e-04

Pos logit contributions
bur+0.021
ible+0.020
 fourteen+0.020
eling+0.020
rob+0.019
Neg logit contributions
and-0.025
 of-0.023
urry-0.022
 tum-0.022
 Today-0.022
Token cold
Token ID4692
Feature activation-2.54e-02

Pos logit contributions
bur+0.001
ps+0.001
ck+0.001
 blew+0.001
cking+0.001
Neg logit contributions
and-0.001
urry-0.001
apping-0.001
 Follow-0.001
rav-0.001
Token waves
Token ID9813
Feature activation-8.11e-03

Pos logit contributions
and+0.050
 Follow+0.047
urry+0.045
vere+0.043
rav+0.042
Neg logit contributions
bur-0.029
 fourteen-0.026
 blew-0.026
ps-0.026
ible-0.025
Token.
Token ID13
Feature activation+1.80e-03

Pos logit contributions
and+0.016
 Follow+0.014
urry+0.014
 Nice+0.013
 tum+0.013
Neg logit contributions
bur-0.009
 fourteen-0.009
ps-0.008
eling-0.008
 blew-0.008
Token After
Token ID2293
Feature activation+1.37e-02

Pos logit contributions
IT+0.002
 fourteen+0.002
 her+0.002
ps+0.002
 pressed+0.002
Neg logit contributions
and-0.003
urry-0.003
vere-0.003
ye-0.003
 Follow-0.003
Token a
Token ID257
Feature activation-7.15e-03

Pos logit contributions
bur+0.012
 fourteen+0.012
eling+0.011
ps+0.011
 blew+0.011
Neg logit contributions
and-0.030
urry-0.027
 Follow-0.027
 Nice-0.025
 tum-0.025
Token while
Token ID981
Feature activation-2.43e-03

Pos logit contributions
and+0.011
 Follow+0.010
urry+0.009
 Go+0.009
 Stay+0.008
Neg logit contributions
bur-0.011
 fourteen-0.011
 blew-0.010
eling-0.010
ck-0.010
Token of
Token ID286
Feature activation+2.01e-03

Pos logit contributions
and+0.004
 Follow+0.003
urry+0.003
aring+0.003
ooters+0.003
Neg logit contributions
 fourteen-0.004
bur-0.004
 blew-0.004
ps-0.004
eling-0.004
Token ro
Token ID686
Feature activation-2.55e-03

Pos logit contributions
bur+0.002
 fourteen+0.002
ible+0.002
IT+0.002
eling+0.002
Neg logit contributions
and-0.004
urry-0.003
 Follow-0.003
 of-0.003
 story-0.003
Tokenwing
Token ID5469
Feature activation-4.50e-03

Pos logit contributions
and+0.003
 Nice+0.003
 Follow+0.003
 birthday+0.003
urry+0.003
Neg logit contributions
bur-0.005
eling-0.005
ck-0.004
ps-0.004
lled-0.004
Token,
Token ID11
Feature activation-8.34e-03

Pos logit contributions
and+0.007
 Follow+0.006
urry+0.006
aring+0.005
 Nice+0.005
Neg logit contributions
bur-0.007
 fourteen-0.007
ps-0.007
 blew-0.007
eling-0.007
Token her
Token ID607
Feature activation+1.50e-03

Pos logit contributions
and+0.054
 Follow+0.046
urry+0.045
 of+0.045
 tum+0.045
Neg logit contributions
bur-0.031
eling-0.029
 fourteen-0.029
 blew-0.028
IT-0.028
Token folder
Token ID9483
Feature activation+5.95e-03

Pos logit contributions
bur+0.002
 fourteen+0.002
eling+0.002
ps+0.002
 blew+0.002
Neg logit contributions
and-0.002
urry-0.002
 Follow-0.002
 tum-0.002
 Nice-0.002
Token!
Token ID0
Feature activation-6.39e-03

Pos logit contributions
bur+0.007
 fourteen+0.007
ps+0.007
 blew+0.006
eling+0.006
Neg logit contributions
and-0.011
urry-0.010
 Follow-0.010
 Nice-0.009
 Stay-0.009
Token It
Token ID632
Feature activation-1.34e-02

Pos logit contributions
and+0.010
urry+0.009
 Follow+0.008
 tum+0.008
rav+0.008
Neg logit contributions
bur-0.009
 fourteen-0.009
 blew-0.008
ps-0.008
IT-0.008
Token was
Token ID373
Feature activation+5.39e-03

Pos logit contributions
and+0.018
 Follow+0.016
urry+0.015
 of+0.014
case+0.014
Neg logit contributions
bur-0.023
 fourteen-0.022
eling-0.021
ps-0.021
cking-0.021
Token tucked
Token ID29779
Feature activation-6.26e-02

Pos logit contributions
bur+0.007
eling+0.007
 fourteen+0.007
ible+0.007
ps+0.007
Neg logit contributions
and-0.009
urry-0.008
 Follow-0.008
 tum-0.008
 Nice-0.007
Token away
Token ID1497
Feature activation+1.50e-02

Pos logit contributions
and+0.128
urry+0.114
 Follow+0.113
 tum+0.104
 Nice+0.104
Neg logit contributions
bur-0.066
 fourteen-0.064
eling-0.062
ps-0.062
 blew-0.060
Token in
Token ID287
Feature activation-3.58e-02

Pos logit contributions
bur+0.021
 fourteen+0.021
ps+0.020
eling+0.020
 blew+0.020
Neg logit contributions
and-0.025
urry-0.022
 Follow-0.022
 Nice-0.020
 tum-0.019
Token the
Token ID262
Feature activation-1.38e-03

Pos logit contributions
and+0.076
urry+0.067
 Follow+0.066
 tum+0.063
 Nice+0.062
Neg logit contributions
bur-0.035
 fourteen-0.034
eling-0.033
ps-0.032
 blew-0.031
Token back
Token ID736
Feature activation-3.00e-02

Pos logit contributions
and+0.002
urry+0.002
rav+0.002
aring+0.002
apping+0.002
Neg logit contributions
ps-0.002
 blew-0.002
 fourteen-0.002
 her-0.002
 afar-0.002
Token of
Token ID286
Feature activation-1.32e-03

Pos logit contributions
and+0.039
 Follow+0.038
urry+0.038
rav+0.037
vere+0.035
Neg logit contributions
 her-0.046
ps-0.044
ries-0.042
bur-0.042
 colored-0.042
Token bust
Token ID13076
Feature activation+8.14e-03

Pos logit contributions
and+0.004
urry+0.003
 Follow+0.003
apping+0.003
 Today+0.003
Neg logit contributions
 blew-0.002
eling-0.002
bur-0.002
 fourteen-0.002
lled-0.002
Tokenle
Token ID293
Feature activation+2.74e-03

Pos logit contributions
bur+0.011
 fourteen+0.011
abi+0.010
ps+0.009
IT+0.009
Neg logit contributions
and-0.015
 of-0.012
 Follow-0.012
urry-0.012
 halls-0.012
Token.
Token ID13
Feature activation+6.18e-03

Pos logit contributions
bur+0.004
 fourteen+0.003
eling+0.003
ps+0.003
 blew+0.003
Neg logit contributions
and-0.005
urry-0.004
 Follow-0.004
 tum-0.004
 Nice-0.004
Token
Token ID198
Feature activation+1.85e-03

Pos logit contributions
bur+0.010
 fourteen+0.010
eling+0.010
ps+0.010
ck+0.010
Neg logit contributions
and-0.009
urry-0.008
 Follow-0.007
 Nice-0.007
 tum-0.007
Token
Token ID198
Feature activation+2.73e-03

Pos logit contributions
bur+0.002
ck+0.002
 blew+0.002
 fourteen+0.002
lled+0.002
Neg logit contributions
and-0.003
 Follow-0.003
 tum-0.003
urry-0.003
 birthday-0.003
TokenG
Token ID38
Feature activation-5.90e-02

Pos logit contributions
ps+0.003
eling+0.003
bur+0.003
 fourteen+0.003
ries+0.003
Neg logit contributions
and-0.005
urry-0.005
 Follow-0.004
 Nice-0.004
 Today-0.004
Tokenilly
Token ID6548
Feature activation-2.71e-02

Pos logit contributions
and+0.100
urry+0.087
 Follow+0.080
rav+0.074
 Today+0.074
Neg logit contributions
 fourteen-0.083
ps-0.080
 blew-0.080
eling-0.079
bur-0.079
Token and
Token ID290
Feature activation-9.58e-04

Pos logit contributions
and+0.054
urry+0.048
 Follow+0.047
 tum+0.044
 Nice+0.044
Neg logit contributions
bur-0.030
 fourteen-0.029
eling-0.028
ps-0.028
 blew-0.027
Token Jack
Token ID3619
Feature activation+7.62e-03

Pos logit contributions
and+0.001
urry+0.001
 Today+0.001
 Nice+0.001
 Follow+0.001
Neg logit contributions
cking-0.002
eling-0.002
 fourteen-0.002
ps-0.002
ck-0.002
Token looked
Token ID3114
Feature activation+2.35e-02

Pos logit contributions
 fourteen+0.010
ps+0.010
bur+0.010
eling+0.010
abi+0.010
Neg logit contributions
and-0.013
urry-0.012
 Follow-0.011
 Stay-0.010
 of-0.010
Token up
Token ID510
Feature activation+4.26e-02

Pos logit contributions
bur+0.030
eling+0.029
 fourteen+0.029
ps+0.029
 blew+0.028
Neg logit contributions
and-0.043
urry-0.037
 Follow-0.037
 Nice-0.034
 tum-0.033
Token,
Token ID11
Feature activation-7.55e-03

Pos logit contributions
 blew+0.040
 fourteen+0.037
eling+0.036
et+0.036
ps+0.036
Neg logit contributions
and-0.068
 Follow-0.062
urry-0.062
 Nice-0.061
rav-0.057
Token a
Token ID257
Feature activation-9.22e-03

Pos logit contributions
and+0.017
aring+0.016
urry+0.015
 Follow+0.015
 Nice+0.014
Neg logit contributions
 blew-0.007
 her-0.006
ries-0.006
 fourteen-0.006
eling-0.006
Token little
Token ID1310
Feature activation+1.10e-02

Pos logit contributions
and+0.018
 Follow+0.016
urry+0.016
 Go+0.015
 Nice+0.014
Neg logit contributions
 blew-0.011
bur-0.010
 sc-0.010
 fourteen-0.009
abi-0.009
Token girl
Token ID2576
Feature activation-9.57e-03

Pos logit contributions
 blew+0.013
bur+0.013
ible+0.012
 fourteen+0.012
mill+0.012
Neg logit contributions
and-0.022
urry-0.019
 Follow-0.018
vere-0.017
 Nice-0.017
Token was
Token ID373
Feature activation+6.76e-03

Pos logit contributions
and+0.018
urry+0.016
 Follow+0.016
vere+0.015
 Nice+0.015
Neg logit contributions
 blew-0.011
bur-0.011
ck-0.010
eling-0.010
ible-0.010
Token sitting
Token ID5586
Feature activation-6.23e-02

Pos logit contributions
bur+0.011
 fourteen+0.011
eling+0.011
ps+0.011
ible+0.011
Neg logit contributions
and-0.010
urry-0.008
 Follow-0.008
 tum-0.007
apping-0.007
Token on
Token ID319
Feature activation-7.13e-03

Pos logit contributions
and+0.103
urry+0.089
 Follow+0.088
 tum+0.080
 Nice+0.080
Neg logit contributions
bur-0.090
 fourteen-0.088
eling-0.086
ps-0.086
 blew-0.084
Token a
Token ID257
Feature activation-9.15e-03

Pos logit contributions
and+0.010
 birthday+0.010
 story+0.009
 School+0.009
 halls+0.009
Neg logit contributions
cking-0.011
eling-0.011
ck-0.011
bur-0.011
 fourteen-0.010
Token seat
Token ID5852
Feature activation+1.87e-02

Pos logit contributions
and+0.014
 Follow+0.012
urry+0.012
 Nice+0.011
rav+0.011
Neg logit contributions
bur-0.014
 fourteen-0.014
 blew-0.014
eling-0.013
ck-0.013
Token.
Token ID13
Feature activation+2.17e-03

Pos logit contributions
bur+0.026
 fourteen+0.026
eling+0.026
ps+0.025
ck+0.025
Neg logit contributions
and-0.031
urry-0.027
 Follow-0.026
 tum-0.025
apping-0.024
Token She
Token ID1375
Feature activation+1.44e-02

Pos logit contributions
 her+0.002
bur+0.002
IT+0.002
 fourteen+0.002
 blew+0.002
Neg logit contributions
and-0.004
urry-0.004
vere-0.004
rav-0.004
 Follow-0.004
Token how
Token ID703
Feature activation+1.70e-02

Pos logit contributions
and+0.039
 of+0.034
 story+0.032
 Stay+0.031
 School+0.030
Neg logit contributions
bur-0.033
cking-0.031
eling-0.031
ck-0.030
 fourteen-0.030
Token.
Token ID13
Feature activation+4.76e-03

Pos logit contributions
bur+0.029
 fourteen+0.029
eling+0.028
ps+0.028
 blew+0.028
Neg logit contributions
and-0.023
urry-0.019
 Follow-0.019
 Nice-0.017
 tum-0.017
Token After
Token ID2293
Feature activation+1.81e-02

Pos logit contributions
bur+0.009
eling+0.009
ck+0.009
 fourteen+0.009
cking+0.009
Neg logit contributions
and-0.006
 Follow-0.005
urry-0.005
 Nice-0.004
 Today-0.004
Token a
Token ID257
Feature activation-8.16e-03

Pos logit contributions
bur+0.026
ible+0.024
lled+0.023
ps+0.023
IT+0.023
Neg logit contributions
and-0.031
urry-0.027
 story-0.027
 of-0.027
 birthday-0.026
Token few
Token ID1178
Feature activation+2.26e-02

Pos logit contributions
and+0.011
urry+0.009
 Follow+0.009
 Nice+0.008
 tum+0.008
Neg logit contributions
bur-0.014
 fourteen-0.014
eling-0.014
ps-0.013
 blew-0.013
Token days
Token ID1528
Feature activation-6.76e-02

Pos logit contributions
bur+0.036
 fourteen+0.034
ps+0.034
eling+0.034
 blew+0.033
Neg logit contributions
and-0.034
urry-0.029
 Follow-0.029
 tum-0.026
 Nice-0.026
Token,
Token ID11
Feature activation-7.27e-03

Pos logit contributions
and+0.074
urry+0.063
 Follow+0.057
 of+0.055
 tum+0.051
Neg logit contributions
bur-0.135
ps-0.133
 fourteen-0.130
eling-0.129
cking-0.128
Token Stamp
Token ID40694
Feature activation-1.56e-02

Pos logit contributions
and+0.011
 of+0.010
 School+0.009
 tum+0.009
urry+0.009
Neg logit contributions
ps-0.011
cking-0.011
bur-0.011
eling-0.011
ck-0.011
Token started
Token ID2067
Feature activation+8.78e-04

Pos logit contributions
and+0.025
 Follow+0.022
urry+0.022
 of+0.021
apping+0.020
Neg logit contributions
bur-0.022
 fourteen-0.021
eling-0.021
cking-0.020
IT-0.020
Token to
Token ID284
Feature activation+2.04e-02

Pos logit contributions
bur+0.002
 fourteen+0.002
eling+0.002
ck+0.002
ps+0.002
Neg logit contributions
and-0.001
 tum-0.001
 story-0.001
 of-0.001
urry-0.001
Token like
Token ID588
Feature activation-1.20e-03

Pos logit contributions
 fourteen+0.035
bur+0.035
ries+0.033
ps+0.033
rob+0.033
Neg logit contributions
and-0.024
 story-0.023
urry-0.021
 birthday-0.021
 Follow-0.021
Token bird
Token ID6512
Feature activation+8.93e-03

Pos logit contributions
bur+0.011
 fourteen+0.011
eling+0.010
ps+0.010
lled+0.010
Neg logit contributions
and-0.011
urry-0.010
 Follow-0.010
 tum-0.009
 story-0.009
Token.
Token ID13
Feature activation+1.20e-02

Pos logit contributions
 fourteen+0.014
bur+0.014
eling+0.013
ps+0.013
 blew+0.013
Neg logit contributions
and-0.014
urry-0.012
 Follow-0.012
 tum-0.011
 Nice-0.010
Token After
Token ID2293
Feature activation+1.95e-02

Pos logit contributions
bur+0.019
 fourteen+0.018
eling+0.018
ps+0.018
 blew+0.018
Neg logit contributions
and-0.018
urry-0.016
 Follow-0.016
 Nice-0.014
 tum-0.014
Token a
Token ID257
Feature activation-4.12e-03

Pos logit contributions
bur+0.024
ible+0.022
eling+0.022
IT+0.022
 fourteen+0.022
Neg logit contributions
and-0.036
urry-0.032
 of-0.031
 Follow-0.031
 tum-0.031
Token few
Token ID1178
Feature activation+2.34e-02

Pos logit contributions
and+0.006
 Follow+0.006
urry+0.005
 Go+0.005
 Stay+0.005
Neg logit contributions
 fourteen-0.006
 blew-0.006
bur-0.006
ck-0.006
eling-0.006
Token weeks
Token ID2745
Feature activation-6.41e-02

Pos logit contributions
eling+0.037
 fourteen+0.036
ps+0.036
ck+0.035
bur+0.035
Neg logit contributions
and-0.037
urry-0.031
 Follow-0.030
 Nice-0.028
apping-0.027
Token of
Token ID286
Feature activation+4.73e-03

Pos logit contributions
and+0.075
urry+0.061
 Follow+0.060
 tum+0.051
 Nice+0.051
Neg logit contributions
bur-0.123
 fourteen-0.121
eling-0.119
ps-0.118
 blew-0.117
Token rest
Token ID1334
Feature activation-1.30e-02

Pos logit contributions
bur+0.006
 fourteen+0.006
eling+0.006
ps+0.006
 blew+0.006
Neg logit contributions
and-0.008
urry-0.007
 Follow-0.007
 Nice-0.007
 tum-0.007
Token,
Token ID11
Feature activation-3.20e-03

Pos logit contributions
and+0.017
 Follow+0.014
urry+0.014
 Nice+0.012
 School+0.012
Neg logit contributions
bur-0.023
 fourteen-0.023
eling-0.023
ps-0.022
 blew-0.022
Token the
Token ID262
Feature activation+6.05e-03

Pos logit contributions
and+0.006
urry+0.005
 Follow+0.005
 tum+0.005
 of+0.005
Neg logit contributions
bur-0.004
ps-0.004
eling-0.004
 fourteen-0.004
ck-0.004
Token bird
Token ID6512
Feature activation+8.99e-03

Pos logit contributions
bur+0.009
 fourteen+0.008
eling+0.008
ps+0.008
 blew+0.008
Neg logit contributions
and-0.010
urry-0.009
 Follow-0.009
 tum-0.008
 Nice-0.008