TOP ACTIVATIONS
MAX = 0.078

garden that said ' att ic '. He was excited to
She grabbed oven m itt s and carefully pulled out
skulls because they keep our brains safe and help us think
not know what " shr ink " meant . He thought
They put on oven m itt s and took out the
family called them ' K iss ers '. Everywhere they went
label that said " shr ink ". She did not know
He used to love po pp ies and always had them
her depend able oven m itt s and bake y ummy
" Okay , grand pa . We understand ,"
took off the oven m itt s and opened the oven
L ila and Tom take Max out of the jungle .
it went on the w ett est of adventures . After
and asked for some po pp ies . This time ,
the garden that said ' att ic '. He was excited
That 's very nice , Jude , but will it really
. She put on her modest dress and ran to the
word : " Sh r ink ". Tom and Jen were
So she took Ben ji to the garden to pick
put on her oven m itt s and z ipped open

MIN ACTIVATIONS
MIN = -0.063

swing . She saw Ben slide down again and waved at
shouts . They slide again and again . They
the pr une cookies . After a while
sad . She wanted to slide too , but Tom was
, Anna , I can slide very fast !" Tom says
mad . They want to slide . " Hey
Dog gy ! Let 's slide together !" So , Kitty
sad . He wanted to slide with Lily .
ay !" They slide again and again . They
, mom , I can slide !" she shouted as she
and did not want to slide down . He tried to
he and his dad could slide away from it !
. They played on the slide all day long , and
Ben . " We can slide on the floor . It
. I am going to slide ." He pushes himself and
ay !" They slide again and again . They
He does not want to slide anymore . He wants to
, mom , can we slide ? Just once ?" Their
and saw two kids fighting over a toy .
her . They started to slide down the stairs together .

INTERVAL 0.043 - 0.078
CONTAINS 0.038%

She put on her warm red coat , and stepped outside
from Grand ma and Grand pa '. It is a gift
a big black bird on the fence . " Let 's
have with others than to keep it for yourself and let
children to listen to their parents , follow the rules ,

INTERVAL 0.008 - 0.043
CONTAINS 25.725%

deserve respect and kindness from everyone ." Jack thought about this
need to read books and practice if you really want to
with all the animals in the forest . He wanted to
the box and thanking the mail man . They
ara and Ben nod . They say thank you and sorry

INTERVAL -0.028 - 0.008
CONTAINS 73.098%

. M imi cheered for her and showed her how to
the air . " Oh no !" Ben says
was happy to have helped fix the fence so the little
the door . He looked back and saw Lily laughing .
, Sally smiled and went back to playing in the garden

INTERVAL -0.063 - -0.028
CONTAINS 1.139%

After the cookies were baked and cooled , Lily 's mom
doing things like this ." J ill nodded
egg without being seen . He was so
he could do it . One day ,
tickets for the plane ," mom says . She holds Anna
Token garden
Token ID11376
Feature activation+5.61e-03

Pos logit contributions
ace+0.019
 story+0.017
igh+0.017
row+0.016
 Him+0.016
Neg logit contributions
Yeah-0.023
 kicking-0.020
 throwing-0.020
run-0.020
 Whe-0.020
Token that
Token ID326
Feature activation+1.88e-02

Pos logit contributions
ace+0.008
igh+0.008
row+0.008
 story+0.008
ery+0.008
Neg logit contributions
Yeah-0.010
 Whe-0.010
Really-0.009
 kicking-0.009
 throwing-0.009
Token said
Token ID531
Feature activation+6.39e-03

Pos logit contributions
ace+0.034
igh+0.032
 Him+0.031
ery+0.031
row+0.031
Neg logit contributions
Yeah-0.027
 kicking-0.025
 Whe-0.025
 throwing-0.024
run-0.024
Token '
Token ID705
Feature activation+4.60e-03

Pos logit contributions
ace+0.015
igh+0.014
 Him+0.014
aret+0.014
ery+0.014
Neg logit contributions
Yeah-0.006
 throwing-0.006
 Whe-0.006
 Tim-0.006
 Tom-0.006
Tokenatt
Token ID1078
Feature activation+6.34e-02

Pos logit contributions
ace+0.008
igh+0.008
row+0.007
ent+0.007
ery+0.007
Neg logit contributions
Yeah-0.007
 throwing-0.007
 kicking-0.007
 Tim-0.006
 Whe-0.006
Tokenic
Token ID291
Feature activation+7.81e-02

Pos logit contributions
 Him+0.072
ace+0.068
 wax+0.067
igh+0.066
 compass+0.065
Neg logit contributions
Yeah-0.119
 Tim-0.113
awed-0.112
run-0.109
 throwing-0.109
Token'.
Token ID4458
Feature activation+4.99e-03

Pos logit contributions
ace+0.100
 Him+0.099
 prayers+0.088
aret+0.088
 wax+0.087
Neg logit contributions
 Tom-0.130
Yeah-0.129
 throwing-0.128
 kid-0.128
 kicking-0.127
Token He
Token ID679
Feature activation+1.26e-02

Pos logit contributions
ace+0.009
 Him+0.008
igh+0.008
 story+0.008
aret+0.008
Neg logit contributions
Yeah-0.008
 throwing-0.007
 kicking-0.007
 Whe-0.007
awed-0.007
Token was
Token ID373
Feature activation+3.79e-03

Pos logit contributions
ace+0.021
row+0.019
este+0.019
aret+0.019
igh+0.018
Neg logit contributions
 Whe-0.020
Yeah-0.019
etchup-0.019
 kicking-0.018
 throwing-0.018
Token excited
Token ID6568
Feature activation+2.03e-02

Pos logit contributions
ace+0.006
igh+0.006
 Him+0.005
 story+0.005
aret+0.005
Neg logit contributions
Yeah-0.007
 Whe-0.006
awed-0.006
Really-0.006
etchup-0.006
Token to
Token ID284
Feature activation+1.54e-02

Pos logit contributions
ace+0.041
igh+0.038
ery+0.037
 Him+0.037
row+0.036
Neg logit contributions
Yeah-0.028
 throwing-0.025
 Whe-0.025
 kicking-0.025
 Tim-0.025
Token
Token ID220
Feature activation-1.85e-02

Pos logit contributions
ace+0.043
 Him+0.039
igh+0.038
aret+0.038
row+0.037
Neg logit contributions
Yeah-0.046
 throwing-0.043
 kicking-0.043
 Whe-0.043
awed-0.041
Token She
Token ID1375
Feature activation+5.93e-03

Pos logit contributions
Yeah+0.025
 pro+0.022
 kicking+0.021
Really+0.021
 throwing+0.021
Neg logit contributions
ace-0.039
 Him-0.035
igh-0.034
aret-0.034
ery-0.034
Token grabbed
Token ID13176
Feature activation+1.62e-02

Pos logit contributions
ace+0.011
igh+0.010
 Him+0.009
ery+0.009
row+0.009
Neg logit contributions
Yeah-0.009
 Whe-0.009
 throwing-0.008
 kicking-0.008
 Tim-0.008
Token oven
Token ID14361
Feature activation+1.40e-02

Pos logit contributions
ace+0.033
igh+0.031
 Him+0.030
ery+0.030
row+0.030
Neg logit contributions
Yeah-0.021
 Whe-0.019
 throwing-0.019
 kicking-0.019
 Tim-0.018
Token m
Token ID285
Feature activation+3.18e-03

Pos logit contributions
ace+0.029
igh+0.028
ery+0.027
 Him+0.026
amps+0.026
Neg logit contributions
 Tom-0.017
Yeah-0.017
 Tim-0.016
 throwing-0.016
 kicking-0.015
Tokenitt
Token ID715
Feature activation+7.32e-02

Pos logit contributions
ace+0.006
ery+0.005
aret+0.005
igh+0.005
 Him+0.005
Neg logit contributions
Yeah-0.005
 throwing-0.004
awed-0.004
 kicking-0.004
run-0.004
Tokens
Token ID82
Feature activation+2.40e-02

Pos logit contributions
ace+0.133
 narrative+0.130
 Amen+0.126
 password+0.125
 story+0.123
Neg logit contributions
 throwing-0.104
etchup-0.101
run-0.099
awed-0.099
 kicking-0.098
Token and
Token ID290
Feature activation+1.25e-02

Pos logit contributions
ace+0.047
 Him+0.045
igh+0.044
aret+0.043
ery+0.042
Neg logit contributions
Yeah-0.031
 throwing-0.030
 Tim-0.029
 kicking-0.029
 Tom-0.028
Token carefully
Token ID7773
Feature activation+1.82e-02

Pos logit contributions
ace+0.022
igh+0.020
 Him+0.020
ery+0.020
row+0.020
Neg logit contributions
Yeah-0.019
 Whe-0.018
 kicking-0.018
 throwing-0.017
Really-0.017
Token pulled
Token ID5954
Feature activation+1.29e-02

Pos logit contributions
ace+0.036
igh+0.034
 Him+0.033
ery+0.032
aret+0.032
Neg logit contributions
Yeah-0.025
 throwing-0.022
 Whe-0.022
 kicking-0.022
 Tim-0.022
Token out
Token ID503
Feature activation-5.62e-03

Pos logit contributions
ace+0.023
igh+0.021
 Him+0.021
row+0.021
ery+0.020
Neg logit contributions
Yeah-0.020
 Tim-0.019
 Tom-0.019
 throwing-0.018
 Whe-0.018
Token skulls
Token ID38556
Feature activation+3.01e-02

Pos logit contributions
ace+0.062
igh+0.058
row+0.057
 Him+0.056
aret+0.056
Neg logit contributions
Yeah-0.044
 throwing-0.041
 kicking-0.040
 Tim-0.040
 Whe-0.040
Token because
Token ID780
Feature activation+9.39e-03

Pos logit contributions
ace+0.055
igh+0.051
aret+0.051
 Him+0.051
ery+0.049
Neg logit contributions
Yeah-0.042
 throwing-0.040
 kicking-0.040
 Tim-0.039
 Tom-0.039
Token they
Token ID484
Feature activation+2.56e-02

Pos logit contributions
ace+0.020
igh+0.019
 Him+0.019
row+0.018
ery+0.018
Neg logit contributions
Yeah-0.011
 Whe-0.010
 throwing-0.010
 kicking-0.010
 Tim-0.009
Token keep
Token ID1394
Feature activation+4.63e-02

Pos logit contributions
ace+0.043
aret+0.041
row+0.039
 Him+0.039
ently+0.036
Neg logit contributions
Yeah-0.039
 Tim-0.039
 throwing-0.038
 Tom-0.037
 kicking-0.036
Token our
Token ID674
Feature activation+3.44e-02

Pos logit contributions
ace+0.088
row+0.082
igh+0.078
aret+0.078
ery+0.076
Neg logit contributions
 throwing-0.063
 Tim-0.063
Yeah-0.060
 kicking-0.060
 Tom-0.060
Token brains
Token ID14290
Feature activation+6.95e-02

Pos logit contributions
ace+0.052
row+0.051
igh+0.049
aret+0.047
at+0.047
Neg logit contributions
Yeah-0.056
 Tim-0.053
 throwing-0.052
 kicking-0.052
 Tom-0.052
Token safe
Token ID3338
Feature activation+4.59e-02

Pos logit contributions
 Him+0.140
ace+0.139
igh+0.138
aret+0.137
este+0.135
Neg logit contributions
 throwing-0.069
 kicking-0.066
Yeah-0.065
 Tim-0.062
 Lily-0.062
Token and
Token ID290
Feature activation+2.60e-02

Pos logit contributions
ace+0.085
igh+0.083
 Him+0.082
aret+0.080
iper+0.078
Neg logit contributions
Yeah-0.056
 Tim-0.055
 throwing-0.055
 kicking-0.053
 Tom-0.053
Token help
Token ID1037
Feature activation+4.55e-02

Pos logit contributions
ace+0.044
igh+0.041
row+0.039
 Him+0.039
ery+0.039
Neg logit contributions
Yeah-0.043
 throwing-0.039
 kicking-0.039
 Whe-0.039
 Tim-0.039
Token us
Token ID514
Feature activation+3.16e-02

Pos logit contributions
ace+0.073
igh+0.067
 Him+0.064
ery+0.064
row+0.064
Neg logit contributions
Yeah-0.078
 throwing-0.073
 Whe-0.072
 kicking-0.072
 Tim-0.072
Token think
Token ID892
Feature activation+1.62e-02

Pos logit contributions
ace+0.055
aret+0.053
igh+0.051
 Him+0.051
iper+0.050
Neg logit contributions
 throwing-0.043
Yeah-0.043
 Tim-0.042
 kicking-0.041
 Tom-0.039
Token not
Token ID407
Feature activation+3.51e-03

Pos logit contributions
ace+0.023
igh+0.021
 Him+0.021
ery+0.021
row+0.021
Neg logit contributions
Yeah-0.019
 Whe-0.017
 throwing-0.017
 kicking-0.017
 Tim-0.016
Token know
Token ID760
Feature activation-1.87e-03

Pos logit contributions
ently+0.006
igh+0.006
aret+0.006
 Him+0.006
apa+0.006
Neg logit contributions
 Lily-0.005
 Tom-0.005
 Tim-0.005
 Sara-0.005
 L-0.005
Token what
Token ID644
Feature activation-2.03e-03

Pos logit contributions
Yeah+0.003
 Whe+0.003
Really+0.003
awed+0.003
etchup+0.002
Neg logit contributions
ace-0.003
igh-0.003
row-0.003
 Him-0.003
ery-0.003
Token "
Token ID366
Feature activation-3.34e-03

Pos logit contributions
Yeah+0.003
 Whe+0.002
awed+0.002
 throwing+0.002
 kicking+0.002
Neg logit contributions
ace-0.004
igh-0.004
ery-0.004
 Him-0.004
row-0.004
Tokenshr
Token ID36007
Feature activation+2.22e-02

Pos logit contributions
Yeah+0.006
 kicking+0.005
 throwing+0.005
 Whe+0.005
 Tom+0.005
Neg logit contributions
ace-0.005
igh-0.005
row-0.005
ery-0.005
ent-0.005
Tokenink
Token ID676
Feature activation+6.84e-02

Pos logit contributions
ace+0.029
 Him+0.027
aret+0.025
igh+0.025
 prayers+0.024
Neg logit contributions
Yeah-0.043
 throwing-0.042
 kicking-0.041
awed-0.040
run-0.040
Token"
Token ID1
Feature activation-2.54e-03

Pos logit contributions
ace+0.110
 Him+0.100
 journals+0.097
 prayers+0.096
aret+0.096
Neg logit contributions
 Tom-0.099
 Lily-0.099
Yeah-0.098
 Tim-0.097
 throwing-0.094
Token meant
Token ID4001
Feature activation+2.75e-02

Pos logit contributions
Yeah+0.005
 kicking+0.005
 throwing+0.005
 Whe+0.004
Really+0.004
Neg logit contributions
ace-0.004
row-0.003
igh-0.003
ery-0.003
 Him-0.003
Token.
Token ID13
Feature activation+1.99e-03

Pos logit contributions
ace+0.055
igh+0.053
 Him+0.052
aret+0.051
este+0.050
Neg logit contributions
 throwing-0.036
 Tim-0.036
Yeah-0.035
 kicking-0.035
 Tom-0.035
Token He
Token ID679
Feature activation+1.02e-03

Pos logit contributions
ace+0.003
 story+0.003
row+0.003
 Him+0.003
 prayers+0.002
Neg logit contributions
Yeah-0.003
 kicking-0.003
 pro-0.003
 throwing-0.003
etchup-0.003
Token thought
Token ID1807
Feature activation+6.07e-03

Pos logit contributions
ace+0.002
ery+0.002
row+0.002
igh+0.002
este+0.002
Neg logit contributions
Yeah-0.002
 Whe-0.002
 kicking-0.001
 throwing-0.001
Really-0.001
Token They
Token ID1119
Feature activation+1.21e-02

Pos logit contributions
ace+0.019
 Him+0.018
 prayers+0.017
aret+0.017
amps+0.017
Neg logit contributions
Yeah-0.019
 kicking-0.018
 pro-0.018
 throwing-0.018
awed-0.017
Token put
Token ID1234
Feature activation-5.65e-03

Pos logit contributions
ace+0.025
igh+0.023
 Him+0.023
row+0.022
ery+0.022
Neg logit contributions
Yeah-0.016
 Whe-0.014
 kicking-0.014
 throwing-0.014
Really-0.013
Token on
Token ID319
Feature activation+1.67e-02

Pos logit contributions
Yeah+0.008
 Whe+0.008
 throwing+0.007
 kicking+0.007
 Tim+0.007
Neg logit contributions
ace-0.011
igh-0.010
 Him-0.010
row-0.010
ery-0.010
Token oven
Token ID14361
Feature activation+1.19e-03

Pos logit contributions
ace+0.036
igh+0.034
row+0.034
 Him+0.033
ery+0.032
Neg logit contributions
Yeah-0.020
 Tim-0.019
 Tom-0.019
 throwing-0.018
 Whe-0.018
Token m
Token ID285
Feature activation+1.13e-03

Pos logit contributions
ace+0.002
igh+0.002
ery+0.002
 Him+0.002
aret+0.002
Neg logit contributions
Yeah-0.002
 Tom-0.002
 throwing-0.002
 Tim-0.002
 Whe-0.001
Tokenitt
Token ID715
Feature activation+6.68e-02

Pos logit contributions
ace+0.002
ery+0.002
aret+0.002
este+0.002
igh+0.002
Neg logit contributions
Yeah-0.002
 Tom-0.001
 throwing-0.001
awed-0.001
 Tim-0.001
Tokens
Token ID82
Feature activation+2.05e-02

Pos logit contributions
ace+0.146
 narrative+0.140
 Amen+0.134
 prayers+0.131
 story+0.130
Neg logit contributions
 throwing-0.072
etchup-0.070
 Tom-0.069
awed-0.067
 kicking-0.065
Token and
Token ID290
Feature activation+1.65e-03

Pos logit contributions
ace+0.040
igh+0.038
 Him+0.038
aret+0.037
ery+0.036
Neg logit contributions
Yeah-0.027
 throwing-0.026
 Tom-0.025
 Tim-0.025
 kicking-0.025
Token took
Token ID1718
Feature activation+2.04e-02

Pos logit contributions
ace+0.003
igh+0.003
 Him+0.003
ery+0.003
row+0.003
Neg logit contributions
Yeah-0.003
 Whe-0.002
 kicking-0.002
awed-0.002
 throwing-0.002
Token out
Token ID503
Feature activation-4.39e-03

Pos logit contributions
ace+0.036
igh+0.034
 Him+0.033
row+0.033
ery+0.033
Neg logit contributions
Yeah-0.032
 Whe-0.029
 throwing-0.029
 Tim-0.029
 Tom-0.028
Token the
Token ID262
Feature activation+8.22e-03

Pos logit contributions
Yeah+0.005
 Tim+0.005
 Tom+0.005
 throwing+0.005
 Lily+0.004
Neg logit contributions
ace-0.009
igh-0.009
row-0.009
 Him-0.009
ery-0.009
Token family
Token ID1641
Feature activation+8.92e-05

Pos logit contributions
ace+0.009
igh+0.008
 Him+0.008
aret+0.008
 deeds+0.008
Neg logit contributions
Yeah-0.006
 Whe-0.005
awed-0.005
run-0.005
Really-0.005
Token called
Token ID1444
Feature activation+1.06e-02

Pos logit contributions
ace+0.000
igh+0.000
 Him+0.000
row+0.000
aret+0.000
Neg logit contributions
Yeah-0.000
 throwing-0.000
 Whe-0.000
 kicking-0.000
 Tim-0.000
Token them
Token ID606
Feature activation-2.14e-05

Pos logit contributions
ace+0.021
igh+0.019
 Him+0.019
row+0.019
ery+0.019
Neg logit contributions
Yeah-0.015
 Whe-0.013
 throwing-0.013
 kicking-0.013
 Tim-0.013
Token '
Token ID705
Feature activation-1.19e-02

Pos logit contributions
Yeah+0.000
 Whe+0.000
 throwing+0.000
 kicking+0.000
 Tim+0.000
Neg logit contributions
ace-0.000
igh-0.000
 Him-0.000
row-0.000
ery-0.000
TokenK
Token ID42
Feature activation+6.45e-03

Pos logit contributions
 kicking+0.018
 throwing+0.017
sed+0.017
 Whe+0.017
Yeah+0.016
Neg logit contributions
igh-0.021
ace-0.019
ent-0.019
at-0.018
ery-0.018
Tokeniss
Token ID747
Feature activation+6.62e-02

Pos logit contributions
ace+0.011
igh+0.010
row+0.010
 Him+0.010
ent+0.010
Neg logit contributions
Yeah-0.011
 Whe-0.010
 throwing-0.010
 kicking-0.009
Really-0.009
Tokeners
Token ID364
Feature activation+3.36e-02

Pos logit contributions
ace+0.082
 Him+0.074
aret+0.069
ery+0.068
row+0.068
Neg logit contributions
Yeah-0.126
 Tom-0.124
 throwing-0.123
 Tim-0.123
 kicking-0.122
Token'.
Token ID4458
Feature activation-7.09e-04

Pos logit contributions
ace+0.044
igh+0.040
 Him+0.038
ery+0.037
row+0.037
Neg logit contributions
Yeah-0.068
 Whe-0.064
 throwing-0.063
 kicking-0.062
 Tim-0.061
Token Everywhere
Token ID48201
Feature activation-1.10e-03

Pos logit contributions
awed+0.001
 throwing+0.001
ounced+0.001
 kicking+0.001
etchup+0.001
Neg logit contributions
ace-0.001
 Him-0.001
igh-0.001
 prayers-0.001
amps-0.001
Token they
Token ID484
Feature activation+1.90e-02

Pos logit contributions
Yeah+0.001
 Whe+0.001
awed+0.001
Really+0.001
 throwing+0.001
Neg logit contributions
ace-0.002
igh-0.002
 Him-0.002
aret-0.002
 story-0.002
Token went
Token ID1816
Feature activation+5.72e-03

Pos logit contributions
ace+0.037
aret+0.034
row+0.034
 Him+0.033
ery+0.033
Neg logit contributions
Yeah-0.026
 Tim-0.024
 Tom-0.023
 Whe-0.023
 Lily-0.023
Token label
Token ID6167
Feature activation+5.03e-03

Pos logit contributions
Yeah+0.002
 Whe+0.002
 throwing+0.002
 kicking+0.002
awed+0.002
Neg logit contributions
ace-0.002
igh-0.002
 story-0.002
ery-0.002
row-0.002
Token that
Token ID326
Feature activation+9.50e-03

Pos logit contributions
ace+0.009
igh+0.009
row+0.009
ery+0.008
 Him+0.008
Neg logit contributions
Yeah-0.008
 Whe-0.007
Really-0.006
 Tim-0.006
 kicking-0.006
Token said
Token ID531
Feature activation-4.45e-03

Pos logit contributions
ace+0.017
ery+0.016
igh+0.015
 story+0.015
 Him+0.015
Neg logit contributions
Yeah-0.014
 kicking-0.013
 Whe-0.013
 throwing-0.013
awed-0.012
Token "
Token ID366
Feature activation+1.04e-03

Pos logit contributions
Yeah+0.006
 Whe+0.005
 kicking+0.005
 throwing+0.005
awed+0.005
Neg logit contributions
ace-0.009
igh-0.009
 Him-0.008
ery-0.008
row-0.008
Tokenshr
Token ID36007
Feature activation+2.42e-02

Pos logit contributions
ace+0.002
row+0.002
ent+0.002
igh+0.002
ery+0.002
Neg logit contributions
Yeah-0.001
 throwing-0.001
 kicking-0.001
 Tim-0.001
 Whe-0.001
Tokenink
Token ID676
Feature activation+6.60e-02

Pos logit contributions
ace+0.029
 Him+0.029
igh+0.026
 prayers+0.026
aret+0.026
Neg logit contributions
Yeah-0.046
run-0.044
 throwing-0.044
awed-0.044
 kicking-0.044
Token".
Token ID1911
Feature activation+9.35e-03

Pos logit contributions
ace+0.107
 Him+0.101
father+0.096
 prayers+0.096
igh+0.096
Neg logit contributions
 Tom-0.089
 Lily-0.088
Yeah-0.086
 Tim-0.084
 throwing-0.084
Token She
Token ID1375
Feature activation-4.08e-04

Pos logit contributions
ace+0.016
 Him+0.015
igh+0.014
 story+0.014
amps+0.014
Neg logit contributions
Yeah-0.014
 kicking-0.013
 throwing-0.013
awed-0.012
 pro-0.012
Token did
Token ID750
Feature activation+1.42e-02

Pos logit contributions
 Whe+0.001
Yeah+0.001
 kicking+0.001
 throwing+0.001
etchup+0.001
Neg logit contributions
ace-0.001
ery-0.001
este-0.001
row-0.001
ian-0.001
Token not
Token ID407
Feature activation+1.25e-03

Pos logit contributions
ace+0.026
igh+0.024
 Him+0.024
ery+0.024
row+0.024
Neg logit contributions
Yeah-0.021
 Whe-0.019
 throwing-0.019
 kicking-0.019
 Tim-0.019
Token know
Token ID760
Feature activation-1.35e-03

Pos logit contributions
igh+0.002
ace+0.002
aret+0.002
 Him+0.002
ently+0.002
Neg logit contributions
 Lily-0.002
 Tom-0.002
Yeah-0.002
 Tim-0.002
 Whe-0.002
Token He
Token ID679
Feature activation+1.15e-02

Pos logit contributions
Yeah+0.001
 kicking+0.001
etchup+0.001
 throwing+0.001
 Whe+0.001
Neg logit contributions
ace-0.002
 Him-0.002
aret-0.002
 story-0.002
 prayers-0.002
Token used
Token ID973
Feature activation+2.35e-02

Pos logit contributions
ace+0.022
igh+0.021
 Him+0.020
row+0.020
ery+0.020
Neg logit contributions
Yeah-0.016
 Whe-0.015
 throwing-0.015
 kicking-0.015
 Tim-0.014
Token to
Token ID284
Feature activation+3.38e-02

Pos logit contributions
ace+0.047
igh+0.044
 Him+0.043
ery+0.043
row+0.043
Neg logit contributions
Yeah-0.031
 throwing-0.028
 Whe-0.028
 Tim-0.028
 kicking-0.028
Token love
Token ID1842
Feature activation+2.55e-03

Pos logit contributions
ace+0.055
igh+0.052
 Him+0.050
ery+0.050
row+0.049
Neg logit contributions
Yeah-0.056
 throwing-0.052
 kicking-0.052
 Tim-0.051
 Whe-0.051
Token po
Token ID745
Feature activation+2.85e-02

Pos logit contributions
ace+0.004
igh+0.004
 Him+0.004
row+0.004
ery+0.004
Neg logit contributions
Yeah-0.004
 Whe-0.004
Really-0.004
awed-0.004
 kicking-0.004
Tokenpp
Token ID381
Feature activation+6.59e-02

Pos logit contributions
ace+0.040
 Him+0.034
aret+0.034
ery+0.034
igh+0.034
Neg logit contributions
Yeah-0.054
awed-0.051
run-0.050
 throwing-0.050
 Whe-0.050
Tokenies
Token ID444
Feature activation+2.97e-02

Pos logit contributions
 Amen+0.129
 narrative+0.124
igh+0.117
 awoke+0.114
 prayers+0.112
Neg logit contributions
run-0.072
awed-0.072
Yeah-0.070
 Lily-0.066
 throwing-0.065
Token and
Token ID290
Feature activation+1.48e-02

Pos logit contributions
ace+0.062
aret+0.059
este+0.058
 Him+0.057
igh+0.057
Neg logit contributions
 Tim-0.033
 throwing-0.032
 Tom-0.032
 Lily-0.032
Yeah-0.032
Token always
Token ID1464
Feature activation+5.81e-03

Pos logit contributions
ace+0.024
 Him+0.022
igh+0.022
row+0.021
aret+0.021
Neg logit contributions
Yeah-0.025
 Whe-0.024
awed-0.023
 kicking-0.022
Really-0.022
Token had
Token ID550
Feature activation+8.46e-03

Pos logit contributions
ace+0.009
igh+0.009
 Him+0.008
row+0.008
ent+0.008
Neg logit contributions
Yeah-0.010
 Whe-0.010
awed-0.009
 throwing-0.009
 kicking-0.009
Token them
Token ID606
Feature activation+1.43e-02

Pos logit contributions
ace+0.015
 Him+0.013
igh+0.013
row+0.013
ery+0.013
Neg logit contributions
Yeah-0.014
 Whe-0.013
Really-0.012
 kicking-0.012
 throwing-0.011
Token her
Token ID607
Feature activation+3.43e-03

Pos logit contributions
ace+0.024
igh+0.023
row+0.023
aret+0.023
ides+0.023
Neg logit contributions
 Lily-0.010
 Tom-0.010
 Tim-0.009
 Sara-0.009
 Sue-0.009
Token depend
Token ID4745
Feature activation+8.54e-03

Pos logit contributions
ace+0.006
igh+0.005
 Him+0.005
ery+0.005
row+0.005
Neg logit contributions
Yeah-0.006
 Whe-0.005
 throwing-0.005
 kicking-0.005
 Tim-0.005
Tokenable
Token ID540
Feature activation+2.32e-02

Pos logit contributions
ace+0.013
 Him+0.012
igh+0.012
aret+0.012
ery+0.011
Neg logit contributions
Yeah-0.015
 Whe-0.014
 throwing-0.014
 kicking-0.014
 Tim-0.014
Token oven
Token ID14361
Feature activation+8.45e-03

Pos logit contributions
ace+0.039
igh+0.036
row+0.035
 Him+0.034
aret+0.034
Neg logit contributions
Yeah-0.037
 throwing-0.036
 kicking-0.035
 Whe-0.035
 Tim-0.035
Token m
Token ID285
Feature activation+6.54e-03

Pos logit contributions
ace+0.020
igh+0.019
ery+0.019
aret+0.018
 Him+0.018
Neg logit contributions
 Tom-0.008
Yeah-0.008
 Tim-0.008
 Lily-0.007
 throwing-0.007
Tokenitt
Token ID715
Feature activation+6.57e-02

Pos logit contributions
ace+0.012
ery+0.010
igh+0.010
aret+0.010
 Him+0.010
Neg logit contributions
Yeah-0.010
 throwing-0.009
awed-0.009
etchup-0.009
 Tom-0.009
Tokens
Token ID82
Feature activation+7.66e-03

Pos logit contributions
ace+0.133
 narrative+0.120
 prayers+0.117
 Amen+0.116
este+0.116
Neg logit contributions
etchup-0.078
 throwing-0.078
 Tom-0.072
awed-0.072
 kicking-0.072
Token and
Token ID290
Feature activation+1.05e-03

Pos logit contributions
ace+0.016
igh+0.015
 Him+0.015
aret+0.014
ery+0.014
Neg logit contributions
Yeah-0.009
 throwing-0.009
 Tim-0.009
 Tom-0.009
 kicking-0.008
Token bake
Token ID28450
Feature activation-1.03e-02

Pos logit contributions
ace+0.002
igh+0.002
 Him+0.002
ery+0.002
row+0.002
Neg logit contributions
Yeah-0.002
 Whe-0.002
 throwing-0.002
 kicking-0.002
 Tim-0.002
Token y
Token ID331
Feature activation+1.54e-02

Pos logit contributions
Yeah+0.016
 Whe+0.014
 throwing+0.014
 kicking+0.014
 Tim+0.013
Neg logit contributions
ace-0.019
igh-0.017
 Him-0.017
ery-0.017
row-0.017
Tokenummy
Token ID13513
Feature activation+2.15e-03

Pos logit contributions
ace+0.030
igh+0.028
aret+0.027
 Him+0.026
ery+0.025
Neg logit contributions
Yeah-0.022
 Tim-0.021
 throwing-0.020
awed-0.020
 Tom-0.020
Token
Token ID198
Feature activation-1.12e-02

Pos logit contributions
ace+0.022
 Him+0.022
 story+0.021
igh+0.020
aret+0.020
Neg logit contributions
Yeah-0.014
 throwing-0.013
 kicking-0.013
awed-0.013
 pro-0.012
Token
Token ID198
Feature activation-3.00e-03

Pos logit contributions
Yeah+0.018
 pro+0.016
 kicking+0.016
 throwing+0.015
awed+0.015
Neg logit contributions
 story-0.019
ace-0.019
 Him-0.019
aret-0.017
ery-0.017
Token"
Token ID1
Feature activation-4.34e-04

Pos logit contributions
Yeah+0.004
 Whe+0.004
 throwing+0.004
 kicking+0.004
 Tim+0.004
Neg logit contributions
ace-0.006
igh-0.005
 Him-0.005
row-0.005
aret-0.005
TokenOkay
Token ID16454
Feature activation+1.36e-02

Pos logit contributions
 throwing+0.001
run+0.000
 kicking+0.000
 Tim+0.000
awed+0.000
Neg logit contributions
ace-0.001
 Him-0.001
ent-0.001
ery-0.001
 prayers-0.001
Token,
Token ID11
Feature activation+2.58e-02

Pos logit contributions
ace+0.023
igh+0.022
ery+0.021
row+0.021
 Him+0.020
Neg logit contributions
Yeah-0.023
 Tim-0.022
 Tom-0.022
 Lily-0.021
 throwing-0.021
Token grand
Token ID4490
Feature activation+6.51e-02

Pos logit contributions
ace+0.055
ery+0.052
igh+0.051
row+0.051
at+0.048
Neg logit contributions
Yeah-0.032
 Tom-0.031
 Tim-0.030
 Lily-0.029
 Whe-0.028
Tokenpa
Token ID8957
Feature activation+9.21e-03

Pos logit contributions
ery+0.076
ace+0.070
sy+0.061
igh+0.061
nob+0.061
Neg logit contributions
 Tom-0.141
 Tim-0.133
Yeah-0.128
 Tommy-0.127
 kid-0.124
Token.
Token ID13
Feature activation-2.84e-03

Pos logit contributions
ace+0.016
igh+0.015
 Him+0.015
ery+0.014
row+0.014
Neg logit contributions
Yeah-0.014
 Whe-0.013
 throwing-0.013
 Tim-0.013
 kicking-0.013
Token We
Token ID775
Feature activation+1.63e-02

Pos logit contributions
Yeah+0.003
 throwing+0.003
 kicking+0.003
awed+0.003
 Whe+0.003
Neg logit contributions
ace-0.006
 Him-0.006
igh-0.006
 prayers-0.006
aret-0.005
Token understand
Token ID1833
Feature activation+1.07e-02

Pos logit contributions
 Him+0.032
aret+0.031
ace+0.030
ently+0.030
row+0.029
Neg logit contributions
 Tim-0.023
 Tom-0.022
Yeah-0.022
 Lily-0.021
 pro-0.020
Token,"
Token ID553
Feature activation+2.37e-03

Pos logit contributions
ace+0.019
igh+0.017
 Him+0.017
row+0.017
ery+0.017
Neg logit contributions
Yeah-0.017
 Whe-0.016
 throwing-0.015
 kicking-0.015
 Tim-0.015
Token took
Token ID1718
Feature activation+2.81e-02

Pos logit contributions
ace+0.029
igh+0.027
 Him+0.026
row+0.026
ery+0.026
Neg logit contributions
Yeah-0.022
 Whe-0.020
 throwing-0.019
 kicking-0.019
 Tim-0.019
Token off
Token ID572
Feature activation+1.38e-02

Pos logit contributions
ace+0.053
igh+0.051
row+0.051
ery+0.050
 Him+0.050
Neg logit contributions
 Tim-0.037
Yeah-0.037
 Tom-0.037
 Lily-0.037
 Whe-0.036
Token the
Token ID262
Feature activation+5.06e-03

Pos logit contributions
ace+0.030
igh+0.029
ery+0.029
 Him+0.028
row+0.028
Neg logit contributions
 Tim-0.016
 Tom-0.015
 throwing-0.015
Yeah-0.015
 Lily-0.015
Token oven
Token ID14361
Feature activation+1.54e-02

Pos logit contributions
ace+0.008
igh+0.008
 Him+0.007
row+0.007
aret+0.007
Neg logit contributions
Yeah-0.009
 Whe-0.008
 throwing-0.008
 Tom-0.008
 Lily-0.008
Token m
Token ID285
Feature activation+1.40e-03

Pos logit contributions
ace+0.035
ery+0.034
igh+0.034
 Him+0.033
este+0.032
Neg logit contributions
 Tom-0.016
 Tim-0.016
 throwing-0.015
 Lily-0.015
Yeah-0.014
Tokenitt
Token ID715
Feature activation+6.49e-02

Pos logit contributions
ace+0.002
ery+0.002
igh+0.002
aret+0.002
 Him+0.002
Neg logit contributions
Yeah-0.002
awed-0.002
 throwing-0.002
 Tom-0.002
 Whe-0.002
Tokens
Token ID82
Feature activation+1.81e-02

Pos logit contributions
ace+0.146
 narrative+0.138
 Amen+0.133
 prayers+0.132
ery+0.131
Neg logit contributions
 throwing-0.066
 Tom-0.065
 Tim-0.062
etchup-0.062
 kicking-0.059
Token and
Token ID290
Feature activation+9.36e-03

Pos logit contributions
ace+0.035
 Him+0.034
igh+0.034
aret+0.033
ery+0.032
Neg logit contributions
Yeah-0.023
 throwing-0.022
 Tom-0.022
 Tim-0.022
 kicking-0.021
Token opened
Token ID4721
Feature activation+7.12e-03

Pos logit contributions
ace+0.015
igh+0.015
 Him+0.014
row+0.014
aret+0.014
Neg logit contributions
Yeah-0.015
 Whe-0.014
 kicking-0.014
Really-0.013
 throwing-0.013
Token the
Token ID262
Feature activation+1.00e-02

Pos logit contributions
ace+0.017
igh+0.016
row+0.016
ery+0.016
 Him+0.016
Neg logit contributions
Yeah-0.007
 Tim-0.006
 Tom-0.006
 Whe-0.006
 throwing-0.006
Token oven
Token ID14361
Feature activation-6.12e-03

Pos logit contributions
ace+0.014
igh+0.013
row+0.013
 Him+0.013
aret+0.012
Neg logit contributions
Yeah-0.018
 Whe-0.018
 throwing-0.018
 Tom-0.018
 Lily-0.017
TokenL
Token ID43
Feature activation-3.80e-03

Pos logit contributions
Yeah+0.007
 Whe+0.007
awed+0.006
 throwing+0.006
 Tim+0.006
Neg logit contributions
ace-0.006
row-0.006
aret-0.006
ery-0.006
ent-0.006
Tokenila
Token ID10102
Feature activation+3.02e-03

Pos logit contributions
Yeah+0.005
 Whe+0.004
 throwing+0.004
 kicking+0.004
 Tim+0.004
Neg logit contributions
ace-0.008
igh-0.008
 Him-0.007
aret-0.007
ery-0.007
Token and
Token ID290
Feature activation-6.35e-03

Pos logit contributions
ace+0.006
igh+0.005
 Him+0.005
row+0.005
aret+0.005
Neg logit contributions
Yeah-0.004
 throwing-0.004
 Tom-0.004
 kicking-0.004
 Whe-0.004
Token Tom
Token ID4186
Feature activation+2.20e-02

Pos logit contributions
Yeah+0.005
run+0.004
Really+0.004
awed+0.004
 pro+0.004
Neg logit contributions
ace-0.016
 Him-0.015
igh-0.015
 story-0.014
aret-0.014
Token take
Token ID1011
Feature activation+2.30e-02

Pos logit contributions
aret+0.042
ace+0.042
row+0.041
 Him+0.040
ery+0.040
Neg logit contributions
 Tom-0.030
Yeah-0.028
 Tim-0.028
 throwing-0.027
 Lily-0.026
Token Max
Token ID5436
Feature activation+6.46e-02

Pos logit contributions
ace+0.049
igh+0.046
 Him+0.045
row+0.045
ery+0.045
Neg logit contributions
Yeah-0.028
 Whe-0.025
 throwing-0.025
 Tim-0.025
 kicking-0.024
Token out
Token ID503
Feature activation+1.10e-02

Pos logit contributions
ery+0.147
igh+0.144
 Him+0.143
at+0.142
aret+0.141
Neg logit contributions
 Tom-0.066
 throwing-0.065
 Tim-0.065
 Lily-0.065
 Spot-0.062
Token of
Token ID286
Feature activation-1.02e-02

Pos logit contributions
ace+0.022
igh+0.021
ery+0.021
 Him+0.021
aret+0.020
Neg logit contributions
Yeah-0.013
 throwing-0.013
 Tim-0.013
 Tom-0.013
 kicking-0.013
Token the
Token ID262
Feature activation+2.05e-02

Pos logit contributions
Yeah+0.019
Really+0.018
awed+0.017
 Whe+0.017
 pro+0.016
Neg logit contributions
ace-0.016
aret-0.015
igh-0.014
 Him-0.014
 story-0.014
Token jungle
Token ID20712
Feature activation+5.56e-03

Pos logit contributions
ace+0.034
igh+0.031
 Him+0.031
row+0.030
aret+0.030
Neg logit contributions
Yeah-0.035
 Whe-0.032
 throwing-0.031
 kicking-0.031
 Tim-0.030
Token.
Token ID13
Feature activation+5.98e-03

Pos logit contributions
ace+0.010
igh+0.010
 Him+0.010
aret+0.009
ery+0.009
Neg logit contributions
Yeah-0.008
 throwing-0.007
 kicking-0.007
 Tim-0.007
 Whe-0.007
Token it
Token ID340
Feature activation+1.14e-02

Pos logit contributions
ace+0.028
 Him+0.026
igh+0.026
ery+0.026
 wax+0.025
Neg logit contributions
Yeah-0.028
awed-0.027
run-0.027
 kicking-0.026
 throwing-0.025
Token went
Token ID1816
Feature activation+5.32e-03

Pos logit contributions
ace+0.025
igh+0.024
 Him+0.024
aret+0.023
 deeds+0.023
Neg logit contributions
Yeah-0.013
 Tim-0.012
 throwing-0.012
 Lily-0.012
 Tom-0.011
Token on
Token ID319
Feature activation+1.85e-02

Pos logit contributions
ace+0.011
igh+0.010
 Him+0.010
ery+0.010
aret+0.010
Neg logit contributions
Yeah-0.007
 throwing-0.007
 kicking-0.007
 Tim-0.007
 Whe-0.007
Token the
Token ID262
Feature activation+2.78e-02

Pos logit contributions
ace+0.035
 Him+0.032
igh+0.032
 story+0.032
aret+0.031
Neg logit contributions
Yeah-0.028
 Whe-0.024
run-0.023
Really-0.023
awed-0.023
Token w
Token ID266
Feature activation+2.62e-02

Pos logit contributions
ace+0.054
igh+0.051
 Him+0.049
ery+0.049
row+0.048
Neg logit contributions
Yeah-0.040
 throwing-0.037
 Whe-0.037
 kicking-0.036
 Tim-0.036
Tokenett
Token ID3087
Feature activation+6.45e-02

Pos logit contributions
ace+0.034
igh+0.032
 Him+0.030
aret+0.029
ery+0.028
Neg logit contributions
Yeah-0.051
 throwing-0.048
awed-0.047
 kicking-0.047
 Tim-0.047
Tokenest
Token ID395
Feature activation+1.06e-02

Pos logit contributions
igh+0.076
ace+0.076
 Him+0.073
 prayers+0.072
ery+0.069
Neg logit contributions
Yeah-0.124
 throwing-0.122
 Tim-0.121
 kicking-0.119
 Lily-0.117
Token of
Token ID286
Feature activation-5.83e-03

Pos logit contributions
ace+0.013
igh+0.012
row+0.012
 story+0.012
ent+0.011
Neg logit contributions
Yeah-0.023
 Whe-0.021
Really-0.020
 throwing-0.020
run-0.020
Token adventures
Token ID17545
Feature activation+7.00e-03

Pos logit contributions
Yeah+0.011
awed+0.009
Really+0.009
 pro+0.009
 Whe+0.009
Neg logit contributions
ace-0.009
igh-0.009
 story-0.009
 Him-0.009
amps-0.008
Token.
Token ID13
Feature activation+1.56e-02

Pos logit contributions
ace+0.011
igh+0.010
row+0.010
ery+0.010
 Him+0.009
Neg logit contributions
Yeah-0.013
Really-0.012
 Whe-0.012
awed-0.011
 pro-0.011
Token After
Token ID2293
Feature activation+4.00e-03

Pos logit contributions
ace+0.027
 Him+0.024
igh+0.024
aret+0.023
amps+0.022
Neg logit contributions
Yeah-0.025
 throwing-0.023
 kicking-0.023
awed-0.023
 pro-0.022
Token and
Token ID290
Feature activation-2.61e-02

Pos logit contributions
Yeah+0.028
 Whe+0.027
awed+0.025
Really+0.025
ounced+0.024
Neg logit contributions
ace-0.016
 story-0.015
 Him-0.015
row-0.014
igh-0.014
Token asked
Token ID1965
Feature activation+3.35e-03

Pos logit contributions
Yeah+0.042
�+0.042
run+0.041
 Whe+0.039
 kicking+0.039
Neg logit contributions
 Him-0.037
aret-0.036
ace-0.033
taker-0.032
leys-0.032
Token for
Token ID329
Feature activation-4.90e-03

Pos logit contributions
ace+0.006
igh+0.005
 Him+0.005
ery+0.005
row+0.005
Neg logit contributions
Yeah-0.005
 Whe-0.005
 throwing-0.005
 Tim-0.005
 kicking-0.005
Token some
Token ID617
Feature activation+2.02e-02

Pos logit contributions
Yeah+0.009
awed+0.009
 Whe+0.008
 kicking+0.008
Really+0.008
Neg logit contributions
ace-0.007
 Him-0.007
 permission-0.006
igh-0.006
row-0.006
Token po
Token ID745
Feature activation+2.49e-02

Pos logit contributions
ace+0.031
 Him+0.028
igh+0.028
row+0.028
ery+0.027
Neg logit contributions
Yeah-0.036
 Whe-0.034
 kicking-0.033
 throwing-0.033
 Tim-0.033
Tokenpp
Token ID381
Feature activation+6.40e-02

Pos logit contributions
ace+0.032
igh+0.028
 Him+0.027
ery+0.027
aret+0.027
Neg logit contributions
Yeah-0.051
 Whe-0.047
 throwing-0.047
 kicking-0.047
 Tim-0.046
Tokenies
Token ID444
Feature activation+4.58e-03

Pos logit contributions
 Amen+0.110
igh+0.110
 prayers+0.108
 awoke+0.106
 pray+0.104
Neg logit contributions
Yeah-0.075
run-0.074
awed-0.074
 Lily-0.071
 throwing-0.069
Token.
Token ID13
Feature activation-7.92e-04

Pos logit contributions
ace+0.009
igh+0.008
 Him+0.008
row+0.008
ery+0.008
Neg logit contributions
Yeah-0.007
 Whe-0.006
 throwing-0.006
 kicking-0.006
 Tim-0.006
Token This
Token ID770
Feature activation+1.49e-02

Pos logit contributions
Yeah+0.001
etchup+0.001
awed+0.001
ang+0.001
 kicking+0.001
Neg logit contributions
ace-0.002
 Him-0.002
aret-0.002
 story-0.002
 prayers-0.002
Token time
Token ID640
Feature activation-1.00e-02

Pos logit contributions
ace+0.029
igh+0.027
 Him+0.027
aret+0.026
row+0.026
Neg logit contributions
Yeah-0.020
 throwing-0.019
 Lily-0.019
 kicking-0.019
 Tom-0.018
Token,
Token ID11
Feature activation-1.47e-02

Pos logit contributions
Yeah+0.021
 Whe+0.019
awed+0.019
 kicking+0.019
 throwing+0.019
Neg logit contributions
ace-0.012
igh-0.011
 Him-0.011
row-0.010
 story-0.010
Token the
Token ID262
Feature activation+1.24e-02

Pos logit contributions
Yeah+0.003
 Whe+0.003
awed+0.003
 throwing+0.003
 kicking+0.003
Neg logit contributions
ace-0.004
igh-0.004
 story-0.004
 Him-0.004
aret-0.004
Token garden
Token ID11376
Feature activation+5.61e-03

Pos logit contributions
ace+0.019
 story+0.017
igh+0.017
row+0.016
 Him+0.016
Neg logit contributions
Yeah-0.023
 kicking-0.020
 throwing-0.020
run-0.020
 Whe-0.020
Token that
Token ID326
Feature activation+1.88e-02

Pos logit contributions
ace+0.008
igh+0.008
row+0.008
 story+0.008
ery+0.008
Neg logit contributions
Yeah-0.010
 Whe-0.010
Really-0.009
 kicking-0.009
 throwing-0.009
Token said
Token ID531
Feature activation+6.39e-03

Pos logit contributions
ace+0.034
igh+0.032
 Him+0.031
ery+0.031
row+0.031
Neg logit contributions
Yeah-0.027
 kicking-0.025
 Whe-0.025
 throwing-0.024
run-0.024
Token '
Token ID705
Feature activation+4.60e-03

Pos logit contributions
ace+0.015
igh+0.014
 Him+0.014
aret+0.014
ery+0.014
Neg logit contributions
Yeah-0.006
 throwing-0.006
 Whe-0.006
 Tim-0.006
 Tom-0.006
Tokenatt
Token ID1078
Feature activation+6.34e-02

Pos logit contributions
ace+0.008
igh+0.008
row+0.007
ent+0.007
ery+0.007
Neg logit contributions
Yeah-0.007
 throwing-0.007
 kicking-0.007
 Tim-0.006
 Whe-0.006
Tokenic
Token ID291
Feature activation+7.81e-02

Pos logit contributions
 Him+0.072
ace+0.068
 wax+0.067
igh+0.066
 compass+0.065
Neg logit contributions
Yeah-0.119
 Tim-0.113
awed-0.112
run-0.109
 throwing-0.109
Token'.
Token ID4458
Feature activation+4.99e-03

Pos logit contributions
ace+0.100
 Him+0.099
 prayers+0.088
aret+0.088
 wax+0.087
Neg logit contributions
 Tom-0.130
Yeah-0.129
 throwing-0.128
 kid-0.128
 kicking-0.127
Token He
Token ID679
Feature activation+1.26e-02

Pos logit contributions
ace+0.009
 Him+0.008
igh+0.008
 story+0.008
aret+0.008
Neg logit contributions
Yeah-0.008
 throwing-0.007
 kicking-0.007
 Whe-0.007
awed-0.007
Token was
Token ID373
Feature activation+3.79e-03

Pos logit contributions
ace+0.021
row+0.019
este+0.019
aret+0.019
igh+0.018
Neg logit contributions
 Whe-0.020
Yeah-0.019
etchup-0.019
 kicking-0.018
 throwing-0.018
Token excited
Token ID6568
Feature activation+2.03e-02

Pos logit contributions
ace+0.006
igh+0.006
 Him+0.005
 story+0.005
aret+0.005
Neg logit contributions
Yeah-0.007
 Whe-0.006
awed-0.006
Really-0.006
etchup-0.006
TokenThat
Token ID2504
Feature activation+3.96e-03

Pos logit contributions
Yeah+0.011
 throwing+0.010
 kicking+0.010
 Tim+0.010
 Whe+0.010
Neg logit contributions
ace-0.021
igh-0.019
ery-0.019
row-0.019
 Him-0.019
Token's
Token ID338
Feature activation-9.63e-03

Pos logit contributions
ace+0.005
igh+0.005
 Him+0.005
aret+0.005
row+0.005
Neg logit contributions
Yeah-0.008
 Whe-0.007
 throwing-0.007
 kicking-0.007
 Tim-0.007
Token very
Token ID845
Feature activation+9.19e-03

Pos logit contributions
Yeah+0.014
 Whe+0.013
 throwing+0.013
 kicking+0.013
awed+0.012
Neg logit contributions
ace-0.018
igh-0.017
 Him-0.016
ery-0.016
row-0.016
Token nice
Token ID3621
Feature activation+1.19e-02

Pos logit contributions
ace+0.015
ery+0.013
igh+0.013
row+0.013
 Him+0.013
Neg logit contributions
Yeah-0.016
 Whe-0.015
 throwing-0.014
awed-0.014
 kicking-0.014
Token,
Token ID11
Feature activation+2.69e-02

Pos logit contributions
ace+0.019
igh+0.018
 Him+0.017
row+0.017
ery+0.017
Neg logit contributions
Yeah-0.021
 Whe-0.019
 throwing-0.019
 kicking-0.019
 Tim-0.018
Token Jude
Token ID30044
Feature activation+6.23e-02

Pos logit contributions
ace+0.053
igh+0.049
 Him+0.048
ery+0.048
row+0.048
Neg logit contributions
Yeah-0.037
 throwing-0.033
 Whe-0.033
 kicking-0.033
 Tim-0.033
Token,
Token ID11
Feature activation+9.33e-05

Pos logit contributions
ace+0.122
 Him+0.120
igh+0.115
 prayers+0.109
aret+0.108
Neg logit contributions
Yeah-0.076
 Tim-0.073
 Tom-0.071
 Lily-0.070
 throwing-0.070
Token but
Token ID475
Feature activation+3.13e-03

Pos logit contributions
ace+0.000
igh+0.000
 Him+0.000
ery+0.000
row+0.000
Neg logit contributions
Yeah-0.000
 Whe-0.000
 throwing-0.000
 kicking-0.000
 Tim-0.000
Token will
Token ID481
Feature activation-1.33e-03

Pos logit contributions
ace+0.006
igh+0.006
 Him+0.006
row+0.006
ery+0.006
Neg logit contributions
Yeah-0.004
awed-0.004
 Whe-0.004
 throwing-0.004
 kicking-0.004
Token it
Token ID340
Feature activation-5.61e-03

Pos logit contributions
Yeah+0.002
 Whe+0.002
awed+0.002
 throwing+0.002
 kicking+0.002
Neg logit contributions
ace-0.002
igh-0.002
 Him-0.002
 story-0.002
aret-0.002
Token really
Token ID1107
Feature activation+4.34e-03

Pos logit contributions
Yeah+0.010
 Whe+0.010
awed+0.009
 kicking+0.009
 throwing+0.009
Neg logit contributions
ace-0.009
igh-0.008
ery-0.008
 Him-0.008
row-0.008
Token.
Token ID13
Feature activation+1.01e-02

Pos logit contributions
ace+0.036
igh+0.033
 Him+0.032
ery+0.032
row+0.032
Neg logit contributions
Yeah-0.030
 throwing-0.028
 Whe-0.028
 kicking-0.027
 Tim-0.027
Token She
Token ID1375
Feature activation+1.47e-02

Pos logit contributions
ace+0.015
 Him+0.013
aret+0.013
igh+0.013
row+0.012
Neg logit contributions
Yeah-0.019
 throwing-0.017
 kicking-0.017
 Whe-0.017
awed-0.017
Token put
Token ID1234
Feature activation+2.93e-03

Pos logit contributions
ace+0.027
igh+0.025
row+0.025
 Him+0.025
ery+0.024
Neg logit contributions
Yeah-0.021
 Whe-0.020
 kicking-0.020
 throwing-0.019
 Tim-0.019
Token on
Token ID319
Feature activation+3.07e-02

Pos logit contributions
ace+0.006
igh+0.006
 Him+0.006
row+0.005
aret+0.005
Neg logit contributions
Yeah-0.004
 Whe-0.003
 Tim-0.003
 Tom-0.003
 throwing-0.003
Token her
Token ID607
Feature activation+2.18e-02

Pos logit contributions
ace+0.061
row+0.060
igh+0.060
iness+0.058
ery+0.058
Neg logit contributions
 Tom-0.041
 Lily-0.041
 Tim-0.041
 throwing-0.038
Yeah-0.038
Token modest
Token ID12949
Feature activation+6.22e-02

Pos logit contributions
ace+0.040
igh+0.037
row+0.036
 Him+0.036
ery+0.036
Neg logit contributions
Yeah-0.033
 Whe-0.030
 throwing-0.030
 kicking-0.029
 Tim-0.029
Token dress
Token ID6576
Feature activation+1.49e-03

Pos logit contributions
ace+0.091
iness+0.087
ery+0.086
igh+0.084
taker+0.083
Neg logit contributions
 throwing-0.107
 kicking-0.105
Yeah-0.101
 soccer-0.101
 Tom-0.100
Token and
Token ID290
Feature activation+1.75e-02

Pos logit contributions
ace+0.003
igh+0.003
 Him+0.002
ery+0.002
row+0.002
Neg logit contributions
Yeah-0.002
 Whe-0.002
 throwing-0.002
 kicking-0.002
 Tim-0.002
Token ran
Token ID4966
Feature activation-2.28e-03

Pos logit contributions
ace+0.029
igh+0.027
 Him+0.027
aret+0.026
row+0.026
Neg logit contributions
Yeah-0.029
 Whe-0.026
 kicking-0.026
 throwing-0.026
run-0.025
Token to
Token ID284
Feature activation-5.77e-04

Pos logit contributions
Yeah+0.003
 Whe+0.003
 throwing+0.003
 Tim+0.003
 kicking+0.003
Neg logit contributions
ace-0.004
igh-0.004
 Him-0.004
ery-0.004
row-0.004
Token the
Token ID262
Feature activation+1.81e-02

Pos logit contributions
Yeah+0.001
awed+0.001
Really+0.001
ounced+0.001
run+0.001
Neg logit contributions
ace-0.001
 Him-0.001
igh-0.001
aret-0.001
 story-0.001
Token word
Token ID1573
Feature activation-5.10e-03

Pos logit contributions
ace+0.004
igh+0.004
 story+0.003
 Him+0.003
aret+0.003
Neg logit contributions
Yeah-0.006
 Whe-0.005
awed-0.005
 throwing-0.005
 kicking-0.005
Token:
Token ID25
Feature activation-4.55e-03

Pos logit contributions
Yeah+0.009
 Whe+0.008
 kicking+0.008
 throwing+0.008
awed+0.008
Neg logit contributions
ace-0.008
igh-0.008
 Him-0.007
row-0.007
ery-0.007
Token "
Token ID366
Feature activation-1.18e-02

Pos logit contributions
Yeah+0.008
awed+0.007
 Whe+0.007
 kicking+0.006
Really+0.006
Neg logit contributions
ace-0.008
 Him-0.007
 story-0.007
igh-0.007
 prayers-0.007
TokenSh
Token ID2484
Feature activation+1.44e-02

Pos logit contributions
Yeah+0.018
 kicking+0.017
 throwing+0.017
 Whe+0.016
 Tim+0.016
Neg logit contributions
ace-0.022
igh-0.020
row-0.019
 Him-0.019
ery-0.019
Tokenr
Token ID81
Feature activation+4.28e-02

Pos logit contributions
ace+0.016
igh+0.014
 Him+0.014
ery+0.013
row+0.013
Neg logit contributions
Yeah-0.032
 Whe-0.030
 throwing-0.030
 kicking-0.030
 Tim-0.030
Tokenink
Token ID676
Feature activation+6.21e-02

Pos logit contributions
ace+0.056
 Him+0.051
igh+0.049
ery+0.049
aret+0.048
Neg logit contributions
Yeah-0.082
 throwing-0.079
 kicking-0.079
 Tom-0.078
 Tim-0.076
Token".
Token ID1911
Feature activation-5.13e-03

Pos logit contributions
ace+0.101
 Him+0.095
aret+0.091
 journals+0.091
 deeds+0.091
Neg logit contributions
Yeah-0.084
 Tom-0.082
 throwing-0.081
 Lily-0.080
awed-0.080
Token Tom
Token ID4186
Feature activation-9.48e-03

Pos logit contributions
 kicking+0.005
Yeah+0.005
 pro+0.005
Really+0.005
 scoring+0.005
Neg logit contributions
ace-0.011
ered-0.010
amps-0.010
 story-0.009
aret-0.009
Token and
Token ID290
Feature activation-3.47e-03

Pos logit contributions
Yeah+0.016
 Whe+0.015
 throwing+0.014
 kicking+0.014
Really+0.014
Neg logit contributions
ace-0.017
igh-0.015
row-0.015
ery-0.014
aret-0.014
Token Jen
Token ID13364
Feature activation+1.51e-02

Pos logit contributions
Yeah+0.003
awed+0.003
 pro+0.003
Really+0.003
 kicking+0.003
Neg logit contributions
ace-0.008
aret-0.007
ered-0.007
row-0.007
ent-0.007
Token were
Token ID547
Feature activation-2.71e-04

Pos logit contributions
ace+0.031
 Him+0.029
igh+0.029
ery+0.029
aret+0.029
Neg logit contributions
Yeah-0.019
 Tim-0.017
 throwing-0.017
 Tom-0.016
 Whe-0.016
Token
Token ID198
Feature activation-2.89e-03

Pos logit contributions
Yeah+0.003
 throwing+0.003
awed+0.003
 kicking+0.003
 Whe+0.003
Neg logit contributions
ace-0.004
 story-0.004
igh-0.004
ent-0.004
 Him-0.004
TokenSo
Token ID2396
Feature activation+1.42e-02

Pos logit contributions
Yeah+0.005
 throwing+0.005
 Whe+0.005
 kicking+0.005
awed+0.005
Neg logit contributions
ace-0.004
igh-0.004
row-0.004
 Him-0.004
ery-0.004
Token she
Token ID673
Feature activation+4.79e-03

Pos logit contributions
ace+0.028
igh+0.026
 Him+0.026
ery+0.025
row+0.025
Neg logit contributions
Yeah-0.019
 Whe-0.018
 throwing-0.017
 kicking-0.017
 Tim-0.017
Token took
Token ID1718
Feature activation+2.31e-02

Pos logit contributions
ace+0.009
igh+0.008
ery+0.008
row+0.008
 Him+0.008
Neg logit contributions
Yeah-0.007
 Whe-0.007
 throwing-0.006
 kicking-0.006
 Tim-0.006
Token Ben
Token ID3932
Feature activation+4.47e-02

Pos logit contributions
ace+0.042
igh+0.039
 Him+0.038
ery+0.037
row+0.036
Neg logit contributions
Yeah-0.036
 kicking-0.032
 Whe-0.032
Really-0.032
 throwing-0.032
Tokenji
Token ID7285
Feature activation+6.16e-02

Pos logit contributions
ace+0.083
igh+0.077
 Him+0.077
aret+0.075
ery+0.075
Neg logit contributions
 throwing-0.061
 kicking-0.059
 Tom-0.059
 Tim-0.059
 Whe-0.058
Token to
Token ID284
Feature activation+3.84e-03

Pos logit contributions
ace+0.164
igh+0.152
eness+0.151
 narrative+0.150
 Amen+0.150
Neg logit contributions
 throwing-0.046
 kicking-0.041
 soccer-0.038
 Whe-0.035
 Tom-0.035
Token the
Token ID262
Feature activation-1.42e-03

Pos logit contributions
 Him+0.006
ace+0.006
igh+0.005
 story+0.005
aret+0.005
Neg logit contributions
Yeah-0.007
awed-0.007
Really-0.006
ounced-0.006
run-0.006
Token garden
Token ID11376
Feature activation+6.02e-03

Pos logit contributions
Yeah+0.003
run+0.003
awed+0.003
 Whe+0.003
 kicking+0.003
Neg logit contributions
 story-0.002
ace-0.002
 Him-0.002
ery-0.002
igh-0.001
Token to
Token ID284
Feature activation-4.25e-03

Pos logit contributions
ace+0.012
igh+0.011
 Him+0.011
aret+0.011
ery+0.011
Neg logit contributions
Yeah-0.008
 throwing-0.008
 kicking-0.008
 Whe-0.007
 Tim-0.007
Token pick
Token ID2298
Feature activation-4.10e-03

Pos logit contributions
Yeah+0.007
 Whe+0.007
awed+0.007
 kicking+0.007
 throwing+0.007
Neg logit contributions
ace-0.007
igh-0.006
 Him-0.006
ery-0.006
row-0.006
Token put
Token ID1234
Feature activation-4.14e-04

Pos logit contributions
ace+0.005
igh+0.005
 Him+0.005
row+0.005
ery+0.005
Neg logit contributions
Yeah-0.004
 Whe-0.004
 throwing-0.003
 kicking-0.003
 Tim-0.003
Token on
Token ID319
Feature activation+2.52e-02

Pos logit contributions
Yeah+0.001
 Whe+0.001
 throwing+0.001
 kicking+0.001
 Tim+0.001
Neg logit contributions
ace-0.001
igh-0.001
 Him-0.001
ery-0.001
row-0.001
Token her
Token ID607
Feature activation-5.09e-03

Pos logit contributions
ace+0.050
igh+0.047
row+0.046
 Him+0.046
ery+0.045
Neg logit contributions
Yeah-0.034
 throwing-0.031
 Whe-0.031
 Tim-0.031
 Tom-0.031
Token oven
Token ID14361
Feature activation+6.43e-03

Pos logit contributions
Yeah+0.009
 Whe+0.008
Really+0.008
awed+0.008
 throwing+0.008
Neg logit contributions
ace-0.008
 story-0.007
ery-0.007
igh-0.007
 Him-0.007
Token m
Token ID285
Feature activation-5.98e-03

Pos logit contributions
ace+0.013
igh+0.013
 Him+0.012
ery+0.012
aret+0.012
Neg logit contributions
Yeah-0.008
 Tom-0.008
 Tim-0.008
 throwing-0.008
 kicking-0.007
Tokenitt
Token ID715
Feature activation+6.16e-02

Pos logit contributions
Yeah+0.010
 Whe+0.009
 throwing+0.009
 kicking+0.009
 Tim+0.009
Neg logit contributions
ace-0.010
igh-0.009
 Him-0.009
ery-0.009
row-0.009
Tokens
Token ID82
Feature activation+2.16e-02

Pos logit contributions
ace+0.128
 narrative+0.116
 prayers+0.116
 Amen+0.115
 Him+0.114
Neg logit contributions
 throwing-0.068
run-0.066
etchup-0.065
 Tom-0.065
 kicking-0.063
Token and
Token ID290
Feature activation+9.80e-03

Pos logit contributions
ace+0.039
igh+0.036
 Him+0.036
aret+0.035
ery+0.035
Neg logit contributions
Yeah-0.033
 throwing-0.030
 Whe-0.030
 kicking-0.030
 Tim-0.030
Token z
Token ID1976
Feature activation-1.44e-02

Pos logit contributions
ace+0.017
 Him+0.016
igh+0.016
aret+0.015
 prayers+0.015
Neg logit contributions
Yeah-0.015
 Whe-0.014
 kicking-0.013
Really-0.013
awed-0.013
Tokenipped
Token ID3949
Feature activation+5.30e-03

Pos logit contributions
Yeah+0.023
 Whe+0.021
 throwing+0.021
 kicking+0.020
 Tim+0.020
Neg logit contributions
ace-0.026
igh-0.025
row-0.023
 Him-0.023
ery-0.023
Token open
Token ID1280
Feature activation-6.01e-03

Pos logit contributions
ace+0.009
igh+0.009
 Him+0.009
row+0.008
ery+0.008
Neg logit contributions
Yeah-0.008
 Whe-0.008
 throwing-0.008
 kicking-0.007
 Tim-0.007
Token swing
Token ID9628
Feature activation-5.19e-02

Pos logit contributions
Yeah+0.051
awed+0.047
 Whe+0.046
Really+0.044
run+0.044
Neg logit contributions
ace-0.064
igh-0.059
 story-0.057
aret-0.057
 Him-0.056
Token.
Token ID13
Feature activation+6.75e-03

Pos logit contributions
Yeah+0.106
Really+0.098
etchup+0.096
awed+0.095
 throwing+0.094
Neg logit contributions
ace-0.069
ery-0.053
row-0.052
 story-0.051
iece-0.050
Token She
Token ID1375
Feature activation-1.99e-02

Pos logit contributions
ace+0.008
 Him+0.008
 prayers+0.007
 story+0.007
aying+0.007
Neg logit contributions
Yeah-0.013
 pro-0.013
 throwing-0.012
awed-0.012
 kicking-0.012
Token saw
Token ID2497
Feature activation-2.66e-02

Pos logit contributions
Really+0.035
Yeah+0.035
run+0.034
etchup+0.033
 Whe+0.033
Neg logit contributions
ace-0.026
ered-0.021
ent-0.020
 awoke-0.020
ery-0.020
Token Ben
Token ID3932
Feature activation-1.56e-02

Pos logit contributions
Yeah+0.051
Really+0.048
run+0.047
�+0.047
awed+0.046
Neg logit contributions
ace-0.033
 Him-0.032
 wax-0.031
taker-0.029
ery-0.029
Token slide
Token ID10649
Feature activation-6.31e-02

Pos logit contributions
Yeah+0.026
 Whe+0.023
Really+0.022
 Tim+0.021
awed+0.021
Neg logit contributions
ace-0.027
igh-0.026
ery-0.024
 story-0.024
row-0.024
Token down
Token ID866
Feature activation-4.54e-02

Pos logit contributions
Yeah+0.134
Really+0.130
 Whe+0.125
etchup+0.119
run+0.118
Neg logit contributions
ace-0.067
row-0.057
 off-0.053
igh-0.052
 forward-0.052
Token again
Token ID757
Feature activation-1.81e-02

Pos logit contributions
Yeah+0.081
 Whe+0.077
run+0.075
awed+0.074
Really+0.072
Neg logit contributions
ace-0.065
igh-0.054
 story-0.053
row-0.053
ery-0.053
Token and
Token ID290
Feature activation-3.34e-02

Pos logit contributions
Yeah+0.042
 Whe+0.038
awed+0.038
Really+0.037
ounced+0.036
Neg logit contributions
ace-0.020
 story-0.017
row-0.016
ent-0.016
igh-0.015
Token waved
Token ID26834
Feature activation-9.63e-03

Pos logit contributions
�+0.058
Yeah+0.055
run+0.051
awed+0.049
Really+0.049
Neg logit contributions
iece-0.048
ace-0.044
ered-0.042
 off-0.041
 awoke-0.040
Token at
Token ID379
Feature activation-2.76e-02

Pos logit contributions
Yeah+0.017
 Whe+0.016
 throwing+0.016
 kicking+0.015
awed+0.015
Neg logit contributions
ace-0.015
 Him-0.014
igh-0.013
row-0.013
aret-0.013
Token shouts
Token ID34757
Feature activation-5.46e-03

Pos logit contributions
Yeah+0.043
run+0.039
Really+0.039
awed+0.038
 throwing+0.037
Neg logit contributions
ace-0.037
igh-0.034
 story-0.033
ery-0.032
 prayers-0.031
Token.
Token ID13
Feature activation-7.06e-03

Pos logit contributions
Yeah+0.008
 Whe+0.008
 throwing+0.008
 kicking+0.008
 Tim+0.008
Neg logit contributions
ace-0.010
igh-0.009
 Him-0.009
row-0.009
ery-0.009
Token
Token ID198
Feature activation-9.46e-03

Pos logit contributions
awed+0.011
Yeah+0.011
etchup+0.011
 kicking+0.010
 throwing+0.010
Neg logit contributions
ace-0.012
 Him-0.010
 story-0.010
aret-0.010
taker-0.010
Token
Token ID198
Feature activation-1.09e-02

Pos logit contributions
Yeah+0.016
awed+0.015
 kicking+0.014
 pro+0.014
 throwing+0.014
Neg logit contributions
ace-0.015
 Him-0.014
 story-0.014
aret-0.014
row-0.013
TokenThey
Token ID2990
Feature activation-4.67e-03

Pos logit contributions
Yeah+0.011
 throwing+0.011
 Whe+0.011
 kicking+0.010
awed+0.010
Neg logit contributions
ace-0.025
row-0.023
aret-0.022
ery-0.022
ent-0.022
Token slide
Token ID10649
Feature activation-6.14e-02

Pos logit contributions
Yeah+0.008
 Whe+0.007
 throwing+0.007
 kicking+0.007
 Tim+0.007
Neg logit contributions
ace-0.008
igh-0.007
 Him-0.007
ery-0.007
row-0.007
Token again
Token ID757
Feature activation-2.34e-02

Pos logit contributions
Yeah+0.133
Really+0.129
 Whe+0.121
 throwing+0.120
run+0.120
Neg logit contributions
ace-0.066
row-0.048
aret-0.048
igh-0.048
 off-0.047
Token and
Token ID290
Feature activation-3.76e-02

Pos logit contributions
Yeah+0.054
awed+0.051
Really+0.051
 Whe+0.050
ounced+0.049
Neg logit contributions
ace-0.024
 story-0.020
row-0.018
ent-0.018
igh-0.016
Token again
Token ID757
Feature activation-2.24e-02

Pos logit contributions
Yeah+0.061
run+0.058
awed+0.057
ounced+0.052
etchup+0.052
Neg logit contributions
ace-0.059
 Him-0.056
igh-0.055
iece-0.054
 story-0.053
Token.
Token ID13
Feature activation-6.22e-03

Pos logit contributions
awed+0.053
Yeah+0.053
Really+0.050
ounced+0.050
 Whe+0.048
Neg logit contributions
ace-0.019
 story-0.015
 Him-0.014
ent-0.013
 deeds-0.013
Token They
Token ID1119
Feature activation-1.59e-02

Pos logit contributions
awed+0.012
iw+0.012
etchup+0.012
ounced+0.012
rou+0.011
Neg logit contributions
ace-0.008
 prayers-0.007
 Him-0.007
 story-0.007
aret-0.006
Token the
Token ID262
Feature activation-2.23e-02

Pos logit contributions
Yeah+0.057
awed+0.052
Really+0.051
 Whe+0.049
ang+0.049
Neg logit contributions
 Him-0.040
 story-0.037
ace-0.037
igh-0.035
ery-0.035
Token pr
Token ID778
Feature activation-5.54e-03

Pos logit contributions
Yeah+0.034
 Whe+0.031
 throwing+0.031
 kicking+0.030
 Tim+0.030
Neg logit contributions
ace-0.041
igh-0.038
 Him-0.038
row-0.037
ery-0.037
Tokenune
Token ID1726
Feature activation-2.44e-02

Pos logit contributions
Yeah+0.011
 Whe+0.011
 throwing+0.010
 Tim+0.010
 kicking+0.010
Neg logit contributions
ace-0.007
igh-0.006
 Him-0.006
aret-0.006
ery-0.006
Token cookies
Token ID14746
Feature activation-1.84e-02

Pos logit contributions
Yeah+0.041
 Whe+0.038
 kicking+0.036
 throwing+0.036
Really+0.036
Neg logit contributions
ace-0.041
igh-0.037
ery-0.037
row-0.036
 Him-0.036
Token.
Token ID13
Feature activation-1.90e-02

Pos logit contributions
Yeah+0.030
 Whe+0.028
 throwing+0.027
 kicking+0.027
Really+0.027
Neg logit contributions
ace-0.031
igh-0.028
ery-0.028
 Him-0.028
row-0.028
Token
Token ID220
Feature activation-6.11e-02

Pos logit contributions
Yeah+0.029
 throwing+0.027
 kicking+0.027
run+0.027
 pro+0.026
Neg logit contributions
 Him-0.031
ace-0.031
 story-0.030
aret-0.030
 prayers-0.028
Token
Token ID198
Feature activation-1.69e-02

Pos logit contributions
Yeah+0.094
 kicking+0.085
 pro+0.085
 throwing+0.084
Really+0.080
Neg logit contributions
ace-0.113
ery-0.103
 Him-0.101
 story-0.100
igh-0.099
Token
Token ID198
Feature activation-1.04e-02

Pos logit contributions
Yeah+0.026
run+0.023
 kicking+0.022
 throwing+0.022
awed+0.022
Neg logit contributions
 story-0.029
ace-0.027
 Him-0.027
ery-0.026
aret-0.026
TokenAfter
Token ID3260
Feature activation-2.77e-02

Pos logit contributions
Yeah+0.017
 Whe+0.016
 kicking+0.016
 throwing+0.016
run+0.015
Neg logit contributions
ace-0.017
aret-0.015
igh-0.015
 Him-0.015
ery-0.015
Token a
Token ID257
Feature activation-2.02e-02

Pos logit contributions
Yeah+0.044
awed+0.039
run+0.038
Really+0.037
 Whe+0.035
Neg logit contributions
 story-0.047
 Him-0.046
igh-0.045
ace-0.042
 chores-0.041
Token while
Token ID981
Feature activation-1.78e-02

Pos logit contributions
Yeah+0.031
awed+0.031
run+0.030
etchup+0.029
idd+0.028
Neg logit contributions
 story-0.033
 Him-0.031
ace-0.030
aret-0.029
row-0.028
Token sad
Token ID6507
Feature activation-1.91e-02

Pos logit contributions
Really+0.029
Yeah+0.028
�+0.028
 Whe+0.027
run+0.027
Neg logit contributions
ace-0.016
taker-0.015
 trem-0.015
ered-0.014
row-0.014
Token.
Token ID13
Feature activation+8.31e-03

Pos logit contributions
Yeah+0.037
 Whe+0.034
 throwing+0.033
 kicking+0.033
awed+0.033
Neg logit contributions
ace-0.026
 Him-0.024
row-0.023
 story-0.023
ery-0.022
Token She
Token ID1375
Feature activation-1.17e-02

Pos logit contributions
ace+0.011
 Him+0.010
 story+0.009
aret+0.009
amps+0.009
Neg logit contributions
Yeah-0.016
 pro-0.015
etchup-0.014
awed-0.014
 throwing-0.014
Token wanted
Token ID2227
Feature activation-8.90e-03

Pos logit contributions
etchup+0.021
Yeah+0.020
run+0.020
 Whe+0.020
�+0.020
Neg logit contributions
ace-0.016
aret-0.014
ery-0.013
este-0.013
ered-0.013
Token to
Token ID284
Feature activation-3.60e-02

Pos logit contributions
Yeah+0.017
awed+0.016
ang+0.016
Really+0.016
run+0.015
Neg logit contributions
ace-0.012
 Him-0.012
 story-0.011
 permission-0.011
 chores-0.011
Token slide
Token ID10649
Feature activation-6.06e-02

Pos logit contributions
awed+0.074
Really+0.072
Yeah+0.070
etchup+0.069
run+0.068
Neg logit contributions
ace-0.048
 story-0.040
ent-0.039
 pray-0.039
ered-0.039
Token too
Token ID1165
Feature activation-2.54e-02

Pos logit contributions
Yeah+0.141
Really+0.135
awed+0.129
etchup+0.128
 throwing+0.128
Neg logit contributions
ace-0.052
 away-0.046
 forward-0.044
 off-0.044
est-0.040
Token,
Token ID11
Feature activation-3.25e-03

Pos logit contributions
Yeah+0.048
 Whe+0.044
Really+0.044
awed+0.043
 throwing+0.042
Neg logit contributions
ace-0.037
igh-0.031
 Him-0.030
row-0.030
 story-0.030
Token but
Token ID475
Feature activation-7.59e-03

Pos logit contributions
Yeah+0.005
awed+0.004
etchup+0.004
run+0.004
 Whe+0.004
Neg logit contributions
ace-0.006
 Him-0.005
igh-0.005
 story-0.005
row-0.005
Token Tom
Token ID4186
Feature activation-1.90e-02

Pos logit contributions
Yeah+0.012
run+0.011
awed+0.010
 pro+0.010
 Whe+0.010
Neg logit contributions
ace-0.013
 Him-0.012
igh-0.012
 story-0.011
aret-0.011
Token was
Token ID373
Feature activation-1.81e-02

Pos logit contributions
Yeah+0.033
 Whe+0.030
Really+0.030
run+0.028
 throwing+0.028
Neg logit contributions
ace-0.031
igh-0.028
ery-0.027
row-0.027
ent-0.026
Token,
Token ID11
Feature activation-2.22e-02

Pos logit contributions
Yeah+0.009
 Whe+0.008
 throwing+0.008
 kicking+0.008
 Tim+0.008
Neg logit contributions
ace-0.008
igh-0.007
 Him-0.007
row-0.007
ery-0.007
Token Anna
Token ID11735
Feature activation-1.45e-03

Pos logit contributions
Yeah+0.018
awed+0.015
 throwing+0.014
 kicking+0.013
run+0.012
Neg logit contributions
ace-0.056
igh-0.054
 Him-0.053
 story-0.053
 prayers-0.051
Token,
Token ID11
Feature activation-3.57e-02

Pos logit contributions
Yeah+0.003
 Whe+0.003
 throwing+0.003
 kicking+0.003
Really+0.003
Neg logit contributions
ace-0.002
igh-0.002
row-0.002
ery-0.002
 story-0.002
Token I
Token ID314
Feature activation-1.29e-02

Pos logit contributions
Yeah+0.049
awed+0.046
run+0.040
 throwing+0.040
etchup+0.040
Neg logit contributions
ace-0.067
igh-0.066
 story-0.064
 Him-0.062
 prayers-0.060
Token can
Token ID460
Feature activation-2.47e-02

Pos logit contributions
Yeah+0.022
 throwing+0.020
 Whe+0.020
 kicking+0.020
awed+0.020
Neg logit contributions
ace-0.021
igh-0.020
ery-0.019
row-0.018
 story-0.018
Token slide
Token ID10649
Feature activation-6.01e-02

Pos logit contributions
Yeah+0.044
awed+0.043
Really+0.042
 Whe+0.039
etchup+0.039
Neg logit contributions
ace-0.037
igh-0.034
 story-0.031
ent-0.030
ery-0.030
Token very
Token ID845
Feature activation-2.07e-02

Pos logit contributions
Yeah+0.130
Really+0.120
awed+0.118
run+0.117
 Whe+0.116
Neg logit contributions
ace-0.058
igh-0.052
 off-0.052
 story-0.050
row-0.050
Token fast
Token ID3049
Feature activation-4.16e-03

Pos logit contributions
Yeah+0.031
 Whe+0.029
 throwing+0.028
awed+0.027
 kicking+0.027
Neg logit contributions
ace-0.037
ery-0.033
row-0.032
igh-0.032
aret-0.032
Token!"
Token ID2474
Feature activation-7.73e-03

Pos logit contributions
Yeah+0.008
 Whe+0.008
Really+0.007
awed+0.007
run+0.007
Neg logit contributions
ace-0.006
igh-0.005
row-0.005
ery-0.005
ent-0.005
Token Tom
Token ID4186
Feature activation-2.24e-02

Pos logit contributions
Yeah+0.004
run+0.003
 throwing+0.003
 pro+0.003
 kicking+0.003
Neg logit contributions
ace-0.021
 Him-0.020
igh-0.020
aret-0.019
 story-0.019
Token says
Token ID1139
Feature activation+1.07e-02

Pos logit contributions
Yeah+0.036
 Whe+0.033
 throwing+0.032
 kicking+0.032
 Tim+0.031
Neg logit contributions
ace-0.039
igh-0.036
 Him-0.035
row-0.035
ery-0.034
Token mad
Token ID8805
Feature activation-1.99e-02

Pos logit contributions
Yeah+0.016
Really+0.016
 Whe+0.015
�+0.014
iw+0.014
Neg logit contributions
ace-0.014
ery-0.012
igh-0.011
 story-0.011
aret-0.011
Token.
Token ID13
Feature activation+1.79e-03

Pos logit contributions
Yeah+0.040
 Whe+0.038
Really+0.037
 kicking+0.035
run+0.035
Neg logit contributions
ace-0.025
 Him-0.022
 story-0.021
igh-0.021
iness-0.020
Token They
Token ID1119
Feature activation-9.02e-04

Pos logit contributions
ace+0.002
 Him+0.002
 story+0.002
amps+0.002
 prayers+0.002
Neg logit contributions
 pro-0.003
Yeah-0.003
awed-0.003
 throwing-0.003
 kicking-0.003
Token want
Token ID765
Feature activation+2.74e-03

Pos logit contributions
Yeah+0.002
 Whe+0.001
 throwing+0.001
 kicking+0.001
awed+0.001
Neg logit contributions
ace-0.001
igh-0.001
 Him-0.001
ery-0.001
aret-0.001
Token to
Token ID284
Feature activation-2.84e-02

Pos logit contributions
 Him+0.004
 story+0.004
ace+0.004
 permission+0.003
 prayers+0.003
Neg logit contributions
Yeah-0.005
awed-0.005
Really-0.005
ang-0.005
 pro-0.005
Token slide
Token ID10649
Feature activation-5.97e-02

Pos logit contributions
awed+0.063
Really+0.061
Yeah+0.059
run+0.059
etchup+0.057
Neg logit contributions
ace-0.033
 story-0.030
 pray-0.028
 answer-0.027
ent-0.027
Token.
Token ID13
Feature activation+1.28e-03

Pos logit contributions
Yeah+0.128
Really+0.125
 Whe+0.116
awed+0.116
 throwing+0.114
Neg logit contributions
ace-0.061
 away-0.057
 off-0.054
 forward-0.053
row-0.049
Token
Token ID198
Feature activation-8.97e-03

Pos logit contributions
ace+0.002
 Him+0.002
 story+0.002
 prayers+0.002
amps+0.002
Neg logit contributions
awed-0.002
 pro-0.002
 throwing-0.002
 kicking-0.002
ounced-0.002
Token
Token ID198
Feature activation+3.59e-04

Pos logit contributions
Yeah+0.015
 pro+0.014
awed+0.013
 kicking+0.013
Really+0.013
Neg logit contributions
 story-0.014
ace-0.014
 Him-0.013
amps-0.013
aret-0.013
Token"
Token ID1
Feature activation-1.63e-02

Pos logit contributions
ace+0.001
igh+0.001
 Him+0.001
ery+0.001
row+0.001
Neg logit contributions
Yeah-0.001
 Whe-0.001
 throwing-0.001
 kicking-0.001
 Tim-0.001
TokenHey
Token ID10814
Feature activation-4.38e-03

Pos logit contributions
run+0.025
awed+0.023
 Tim+0.023
 throwing+0.022
ounces+0.022
Neg logit contributions
ace-0.024
ent-0.023
 narrative-0.023
ery-0.022
kered-0.021
Token Dog
Token ID8532
Feature activation+1.24e-02

Pos logit contributions
ace+0.006
igh+0.006
 Him+0.006
row+0.006
aret+0.006
Neg logit contributions
Yeah-0.003
 Whe-0.003
 throwing-0.003
 kicking-0.002
awed-0.002
Tokengy
Token ID1360
Feature activation-4.45e-05

Pos logit contributions
ace+0.020
igh+0.018
 Him+0.018
ery+0.017
row+0.017
Neg logit contributions
Yeah-0.021
 Whe-0.020
 throwing-0.020
 kicking-0.019
 Tim-0.019
Token!
Token ID0
Feature activation-1.36e-02

Pos logit contributions
Yeah+0.000
Really+0.000
 Whe+0.000
 throwing+0.000
 kicking+0.000
Neg logit contributions
ace-0.000
igh-0.000
row-0.000
ent-0.000
ery-0.000
Token Let
Token ID3914
Feature activation+8.96e-03

Pos logit contributions
 throwing+0.019
awed+0.019
Yeah+0.018
 kicking+0.018
 pro+0.017
Neg logit contributions
ace-0.025
 Him-0.022
igh-0.022
 prayers-0.021
aying-0.021
Token's
Token ID338
Feature activation-2.27e-02

Pos logit contributions
ace+0.012
igh+0.012
 Him+0.011
ery+0.011
row+0.011
Neg logit contributions
 Tim-0.017
Yeah-0.017
 Tom-0.017
 Lily-0.017
 throwing-0.016
Token slide
Token ID10649
Feature activation-5.96e-02

Pos logit contributions
awed+0.044
Yeah+0.044
Really+0.042
 Whe+0.042
etchup+0.040
Neg logit contributions
ace-0.031
igh-0.028
ery-0.026
ent-0.025
 story-0.025
Token together
Token ID1978
Feature activation-8.70e-03

Pos logit contributions
Yeah+0.130
Really+0.129
awed+0.125
sed+0.123
joy+0.122
Neg logit contributions
 off-0.054
 away-0.048
ace-0.045
row-0.044
 forward-0.043
Token!"
Token ID2474
Feature activation+8.88e-03

Pos logit contributions
Yeah+0.018
Really+0.017
awed+0.017
 Whe+0.016
run+0.016
Neg logit contributions
ace-0.011
ery-0.009
ent-0.009
row-0.009
igh-0.009
Token So
Token ID1406
Feature activation-2.01e-03

Pos logit contributions
ace+0.018
igh+0.016
 Him+0.016
row+0.016
aret+0.016
Neg logit contributions
Yeah-0.012
 Whe-0.011
 throwing-0.011
 kicking-0.011
 Tim-0.010
Token,
Token ID11
Feature activation-6.23e-03

Pos logit contributions
Yeah+0.004
 Whe+0.003
 throwing+0.003
 kicking+0.003
 Tim+0.003
Neg logit contributions
ace-0.003
igh-0.003
 Him-0.003
row-0.003
ery-0.003
Token Kitty
Token ID21168
Feature activation-2.28e-02

Pos logit contributions
Yeah+0.008
awed+0.008
 kicking+0.008
Really+0.007
run+0.007
Neg logit contributions
ace-0.011
 Him-0.011
aret-0.010
 prayers-0.010
 story-0.010
Token sad
Token ID6507
Feature activation-1.36e-02

Pos logit contributions
Really+0.019
Yeah+0.018
�+0.017
iw+0.017
awed+0.017
Neg logit contributions
ace-0.013
ery-0.010
 forward-0.010
 answer-0.010
ered-0.009
Token.
Token ID13
Feature activation+4.03e-03

Pos logit contributions
Yeah+0.028
awed+0.027
Really+0.026
 Whe+0.026
etchup+0.025
Neg logit contributions
ace-0.017
 Him-0.015
 story-0.015
row-0.014
iness-0.014
Token He
Token ID679
Feature activation-1.20e-02

Pos logit contributions
ace+0.005
 Him+0.004
 story+0.004
amps+0.004
aret+0.004
Neg logit contributions
Yeah-0.008
 throwing-0.008
 pro-0.008
awed-0.008
 kicking-0.007
Token wanted
Token ID2227
Feature activation-1.59e-02

Pos logit contributions
Yeah+0.020
 Whe+0.018
 throwing+0.018
 kicking+0.018
 Tim+0.017
Neg logit contributions
ace-0.020
igh-0.019
 Him-0.018
ery-0.018
aret-0.017
Token to
Token ID284
Feature activation-3.37e-02

Pos logit contributions
Yeah+0.035
awed+0.034
ang+0.034
Really+0.033
�+0.032
Neg logit contributions
ace-0.016
 permission-0.016
 story-0.015
 Him-0.015
 chores-0.015
Token slide
Token ID10649
Feature activation-5.91e-02

Pos logit contributions
awed+0.079
Really+0.074
Yeah+0.073
etchup+0.072
ounced+0.070
Neg logit contributions
ace-0.038
 story-0.033
 answer-0.032
ered-0.032
ent-0.030
Token with
Token ID351
Feature activation+4.33e-03

Pos logit contributions
Yeah+0.130
Really+0.125
awed+0.121
etchup+0.120
sed+0.119
Neg logit contributions
ace-0.059
 forward-0.049
 off-0.049
 away-0.049
est-0.047
Token Lily
Token ID20037
Feature activation+8.12e-04

Pos logit contributions
ace+0.007
 Him+0.006
igh+0.006
ery+0.006
 story+0.006
Neg logit contributions
Yeah-0.007
Really-0.007
awed-0.007
 throwing-0.007
 pro-0.007
Token.
Token ID13
Feature activation+3.55e-04

Pos logit contributions
ace+0.001
igh+0.001
ery+0.001
row+0.001
 Him+0.001
Neg logit contributions
Yeah-0.001
 Whe-0.001
 throwing-0.001
Really-0.001
 kicking-0.001
Token
Token ID198
Feature activation-1.66e-03

Pos logit contributions
ace+0.001
 Him+0.000
 story+0.000
amps+0.000
aret+0.000
Neg logit contributions
 throwing-0.001
 kicking-0.001
awed-0.001
Yeah-0.001
 scoring-0.001
Token
Token ID198
Feature activation+3.76e-03

Pos logit contributions
Yeah+0.003
 pro+0.002
 kicking+0.002
 throwing+0.002
awed+0.002
Neg logit contributions
ace-0.003
 story-0.003
 Him-0.003
aret-0.003
row-0.003
Tokenay
Token ID323
Feature activation-1.46e-03

Pos logit contributions
Yeah+0.043
 Whe+0.040
 throwing+0.040
 kicking+0.039
Really+0.038
Neg logit contributions
ace-0.027
igh-0.024
row-0.023
 Him-0.023
ery-0.022
Token!"
Token ID2474
Feature activation-7.30e-04

Pos logit contributions
Yeah+0.002
 Whe+0.002
 throwing+0.002
 kicking+0.002
Really+0.002
Neg logit contributions
ace-0.003
igh-0.002
row-0.002
ery-0.002
 Him-0.002
Token
Token ID198
Feature activation-4.05e-03

Pos logit contributions
Yeah+0.001
 pro+0.001
Really+0.001
run+0.001
 scoring+0.001
Neg logit contributions
ace-0.001
 Him-0.001
 story-0.001
 prayers-0.001
aret-0.001
Token
Token ID198
Feature activation+1.99e-04

Pos logit contributions
Yeah+0.006
 pro+0.005
 kicking+0.005
Really+0.005
 throwing+0.005
Neg logit contributions
ace-0.007
 story-0.007
 Him-0.007
aret-0.007
row-0.007
TokenThey
Token ID2990
Feature activation-1.95e-03

Pos logit contributions
ace+0.000
igh+0.000
 Him+0.000
row+0.000
ery+0.000
Neg logit contributions
Yeah-0.000
 Whe-0.000
 throwing-0.000
 kicking-0.000
 Tim-0.000
Token slide
Token ID10649
Feature activation-5.88e-02

Pos logit contributions
Yeah+0.003
 Whe+0.003
 throwing+0.003
 kicking+0.003
 Tim+0.003
Neg logit contributions
ace-0.003
igh-0.003
 Him-0.003
ery-0.003
row-0.003
Token again
Token ID757
Feature activation-1.91e-02

Pos logit contributions
Yeah+0.128
Really+0.125
run+0.117
 throwing+0.116
 Whe+0.116
Neg logit contributions
ace-0.060
row-0.045
 off-0.044
aret-0.044
igh-0.043
Token and
Token ID290
Feature activation-3.03e-02

Pos logit contributions
Yeah+0.044
awed+0.041
Really+0.041
 Whe+0.040
ounced+0.039
Neg logit contributions
ace-0.020
 story-0.017
row-0.016
igh-0.015
ent-0.015
Token again
Token ID757
Feature activation-1.81e-02

Pos logit contributions
Yeah+0.047
run+0.046
awed+0.044
etchup+0.040
ounced+0.040
Neg logit contributions
ace-0.049
 Him-0.047
igh-0.047
iece-0.046
 story-0.044
Token.
Token ID13
Feature activation-3.99e-03

Pos logit contributions
awed+0.043
Yeah+0.042
ounced+0.040
Really+0.040
etchup+0.039
Neg logit contributions
ace-0.015
 story-0.012
 Him-0.012
 answer-0.011
iece-0.011
Token They
Token ID1119
Feature activation-1.41e-02

Pos logit contributions
 pro+0.007
rou+0.007
etchup+0.007
run+0.007
ang+0.007
Neg logit contributions
 prayers-0.004
ace-0.004
 Today-0.004
amps-0.004
aying-0.004
Token,
Token ID11
Feature activation-1.77e-02

Pos logit contributions
Yeah+0.005
 Tim+0.005
 Tom+0.005
 Whe+0.005
 throwing+0.005
Neg logit contributions
ace-0.005
igh-0.005
 Him-0.005
ery-0.005
row-0.005
Token mom
Token ID1995
Feature activation-1.25e-02

Pos logit contributions
Yeah+0.019
 Whe+0.017
 throwing+0.017
 kicking+0.017
 Tim+0.016
Neg logit contributions
ace-0.040
igh-0.038
 Him-0.037
ery-0.036
row-0.036
Token,
Token ID11
Feature activation-2.50e-02

Pos logit contributions
Yeah+0.030
 Whe+0.028
Really+0.027
 kicking+0.026
 throwing+0.025
Neg logit contributions
ace-0.013
igh-0.013
 story-0.012
row-0.012
pa-0.011
Token I
Token ID314
Feature activation-6.54e-03

Pos logit contributions
Yeah+0.031
 Whe+0.028
 throwing+0.028
 kicking+0.028
 Tim+0.027
Neg logit contributions
ace-0.052
igh-0.049
 Him-0.048
ery-0.047
row-0.047
Token can
Token ID460
Feature activation-1.95e-02

Pos logit contributions
Yeah+0.011
 throwing+0.010
 Whe+0.010
Really+0.010
awed+0.010
Neg logit contributions
ace-0.011
igh-0.010
ery-0.010
 story-0.010
row-0.010
Token slide
Token ID10649
Feature activation-5.88e-02

Pos logit contributions
Yeah+0.035
awed+0.034
Really+0.033
 Whe+0.032
run+0.031
Neg logit contributions
ace-0.029
igh-0.027
 story-0.024
ery-0.024
ent-0.024
Token!"
Token ID2474
Feature activation-8.12e-03

Pos logit contributions
Yeah+0.127
Really+0.117
awed+0.113
 Whe+0.113
run+0.112
Neg logit contributions
ace-0.057
igh-0.054
 off-0.052
 story-0.051
row-0.051
Token she
Token ID673
Feature activation-1.28e-02

Pos logit contributions
Yeah+0.007
 throwing+0.005
 kicking+0.005
run+0.005
awed+0.005
Neg logit contributions
ace-0.020
 Him-0.019
 story-0.018
igh-0.018
aret-0.018
Token shouted
Token ID17293
Feature activation+7.02e-03

Pos logit contributions
Yeah+0.019
 Whe+0.018
Really+0.018
 kicking+0.017
 throwing+0.017
Neg logit contributions
ace-0.022
row-0.020
aret-0.020
igh-0.019
ent-0.019
Token as
Token ID355
Feature activation+2.94e-03

Pos logit contributions
ace+0.012
igh+0.012
 Him+0.011
ery+0.011
row+0.011
Neg logit contributions
Yeah-0.011
 Whe-0.010
 throwing-0.010
 kicking-0.010
 Tim-0.010
Token she
Token ID673
Feature activation-2.96e-02

Pos logit contributions
ace+0.004
 Him+0.003
 prayers+0.003
 wax+0.003
taker+0.003
Neg logit contributions
Yeah-0.006
awed-0.005
run-0.005
Really-0.005
ounced-0.005
Token and
Token ID290
Feature activation-6.01e-03

Pos logit contributions
ace+0.001
 Him+0.001
row+0.001
 story+0.001
ent+0.001
Neg logit contributions
Yeah-0.002
 Whe-0.002
Really-0.002
awed-0.002
 pro-0.002
Token did
Token ID750
Feature activation+9.24e-03

Pos logit contributions
Yeah+0.010
 Whe+0.009
Really+0.009
etchup+0.009
�+0.009
Neg logit contributions
ace-0.009
row-0.008
 Him-0.008
aret-0.008
ered-0.008
Token not
Token ID407
Feature activation+1.46e-02

Pos logit contributions
ace+0.013
 Him+0.012
 story+0.012
igh+0.012
ery+0.011
Neg logit contributions
Yeah-0.017
awed-0.016
 Whe-0.016
Really-0.015
etchup-0.015
Token want
Token ID765
Feature activation-4.23e-03

Pos logit contributions
ace+0.023
igh+0.022
 Him+0.021
aret+0.021
row+0.020
Neg logit contributions
Yeah-0.025
 Whe-0.024
 throwing-0.024
 Tom-0.024
 Tim-0.024
Token to
Token ID284
Feature activation-1.97e-02

Pos logit contributions
Yeah+0.008
Really+0.007
awed+0.007
ang+0.007
 pro+0.007
Neg logit contributions
ace-0.006
 Him-0.006
 story-0.006
 prayers-0.006
 permission-0.006
Token slide
Token ID10649
Feature activation-5.84e-02

Pos logit contributions
Yeah+0.038
awed+0.036
Really+0.035
 Whe+0.035
run+0.034
Neg logit contributions
ace-0.029
ent-0.025
igh-0.025
 story-0.024
 Him-0.024
Token down
Token ID866
Feature activation-3.60e-02

Pos logit contributions
Really+0.129
Yeah+0.128
 Whe+0.121
awed+0.112
etchup+0.111
Neg logit contributions
ace-0.058
 away-0.054
 off-0.052
iness-0.051
 forward-0.050
Token.
Token ID13
Feature activation+7.03e-03

Pos logit contributions
Yeah+0.076
 Whe+0.074
Really+0.073
awed+0.070
ounced+0.067
Neg logit contributions
ace-0.044
 story-0.035
ent-0.034
igh-0.034
iness-0.033
Token He
Token ID679
Feature activation-1.65e-03

Pos logit contributions
ace+0.009
 Him+0.008
amps+0.008
 story+0.007
apa+0.007
Neg logit contributions
 throwing-0.013
 pro-0.013
Yeah-0.013
 kicking-0.013
 swinging-0.013
Token tried
Token ID3088
Feature activation-6.57e-03

Pos logit contributions
 Whe+0.003
Yeah+0.003
etchup+0.003
 throwing+0.003
 kicking+0.002
Neg logit contributions
ace-0.003
este-0.002
ered-0.002
row-0.002
aret-0.002
Token to
Token ID284
Feature activation-1.84e-02

Pos logit contributions
Yeah+0.013
Really+0.012
awed+0.012
idd+0.011
ang+0.011
Neg logit contributions
ace-0.008
 story-0.008
row-0.007
 permission-0.007
 Him-0.007
Token he
Token ID339
Feature activation+3.17e-03

Pos logit contributions
ace+0.034
igh+0.032
 Him+0.031
row+0.031
ery+0.031
Neg logit contributions
Yeah-0.022
 Whe-0.019
 throwing-0.019
 kicking-0.019
 Tim-0.018
Token and
Token ID290
Feature activation+2.03e-02

Pos logit contributions
ace+0.006
igh+0.005
row+0.005
ery+0.005
 Him+0.005
Neg logit contributions
Yeah-0.005
 Whe-0.005
 throwing-0.005
 kicking-0.005
Really-0.004
Token his
Token ID465
Feature activation+6.07e-03

Pos logit contributions
ace+0.035
igh+0.032
 Him+0.031
ery+0.031
row+0.031
Neg logit contributions
Yeah-0.034
 Whe-0.031
 throwing-0.031
 Tim-0.030
 kicking-0.030
Token dad
Token ID9955
Feature activation+2.59e-02

Pos logit contributions
ace+0.010
 story+0.009
igh+0.009
 Him+0.009
aret+0.008
Neg logit contributions
Yeah-0.010
 Whe-0.010
 throwing-0.009
awed-0.009
Really-0.009
Token could
Token ID714
Feature activation-4.68e-03

Pos logit contributions
ace+0.049
igh+0.045
 Him+0.045
ery+0.044
row+0.044
Neg logit contributions
Yeah-0.038
 Whe-0.034
 throwing-0.034
 kicking-0.034
 Tim-0.033
Token slide
Token ID10649
Feature activation-5.83e-02

Pos logit contributions
Yeah+0.008
 Whe+0.007
 throwing+0.007
 kicking+0.007
 Tim+0.007
Neg logit contributions
ace-0.008
igh-0.007
 Him-0.007
row-0.007
ery-0.007
Token away
Token ID1497
Feature activation-1.51e-02

Pos logit contributions
Yeah+0.132
Really+0.131
 Whe+0.123
awed+0.123
etchup+0.121
Neg logit contributions
ace-0.057
 away-0.048
row-0.046
ery-0.045
 off-0.045
Token from
Token ID422
Feature activation-1.75e-02

Pos logit contributions
Yeah+0.028
 Whe+0.028
Really+0.026
awed+0.026
etchup+0.025
Neg logit contributions
ace-0.022
row-0.019
ery-0.019
ent-0.018
igh-0.018
Token it
Token ID340
Feature activation-2.53e-03

Pos logit contributions
Yeah+0.033
awed+0.032
Really+0.032
 Whe+0.032
ounced+0.031
Neg logit contributions
pa-0.021
igh-0.021
ace-0.021
ered-0.021
 wax-0.019
Token!
Token ID0
Feature activation+6.63e-03

Pos logit contributions
Yeah+0.005
 Whe+0.005
Really+0.004
awed+0.004
 throwing+0.004
Neg logit contributions
ace-0.004
ery-0.003
row-0.003
igh-0.003
 story-0.003
Token
Token ID198
Feature activation+8.18e-03

Pos logit contributions
ace+0.011
igh+0.011
 Him+0.011
 story+0.010
amps+0.010
Neg logit contributions
Yeah-0.009
 throwing-0.009
 kicking-0.009
awed-0.009
 Whe-0.008
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
Yeah+0.043
 Whe+0.041
Really+0.040
etchup+0.039
awed+0.038
Neg logit contributions
ace-0.037
ery-0.031
igh-0.031
 story-0.031
row-0.030
Token They
Token ID1119
Feature activation-7.54e-03

Pos logit contributions
awed+0.023
Yeah+0.023
etchup+0.023
 pro+0.023
iw+0.022
Neg logit contributions
ace-0.019
 story-0.017
taker-0.016
aret-0.016
amps-0.016
Token played
Token ID2826
Feature activation-4.32e-02

Pos logit contributions
Yeah+0.012
 Whe+0.011
Really+0.011
run+0.011
 throwing+0.011
Neg logit contributions
ace-0.013
igh-0.012
ery-0.011
row-0.011
aret-0.011
Token on
Token ID319
Feature activation-4.20e-02

Pos logit contributions
Yeah+0.073
Really+0.069
run+0.068
etchup+0.068
ounced+0.066
Neg logit contributions
ace-0.064
ery-0.064
 story-0.062
igh-0.057
ent-0.057
Token the
Token ID262
Feature activation-2.05e-02

Pos logit contributions
ounced+0.097
Yeah+0.097
Really+0.096
run+0.095
elt+0.093
Neg logit contributions
 chores-0.034
 story-0.033
 stories-0.030
 end-0.029
 night-0.027
Token slide
Token ID10649
Feature activation-5.82e-02

Pos logit contributions
run+0.027
etchup+0.025
Yeah+0.023
awed+0.022
Really+0.022
Neg logit contributions
 story-0.040
ace-0.039
 chores-0.037
ent-0.036
ery-0.036
Token all
Token ID477
Feature activation-1.60e-02

Pos logit contributions
Really+0.126
Yeah+0.126
etchup+0.119
run+0.116
 Whe+0.115
Neg logit contributions
ace-0.059
est-0.052
 story-0.049
ery-0.047
igh-0.047
Token day
Token ID1110
Feature activation-6.56e-03

Pos logit contributions
Yeah+0.036
Really+0.034
awed+0.034
 Whe+0.034
run+0.034
Neg logit contributions
ace-0.017
ent-0.014
ery-0.013
aret-0.013
igh-0.013
Token long
Token ID890
Feature activation-5.44e-03

Pos logit contributions
Yeah+0.013
Really+0.012
 Whe+0.012
run+0.011
awed+0.011
Neg logit contributions
ace-0.009
 story-0.008
ent-0.008
igh-0.008
ery-0.008
Token,
Token ID11
Feature activation-3.98e-02

Pos logit contributions
Yeah+0.011
Really+0.011
 Whe+0.011
etchup+0.010
ounced+0.010
Neg logit contributions
ace-0.007
ent-0.006
igh-0.006
ery-0.006
 deeds-0.005
Token and
Token ID290
Feature activation-3.02e-02

Pos logit contributions
Really+0.068
run+0.068
Yeah+0.066
awed+0.063
etchup+0.063
Neg logit contributions
ace-0.051
 story-0.047
igh-0.047
ent-0.045
iece-0.045
Token Ben
Token ID3932
Feature activation+1.18e-02

Pos logit contributions
ace+0.001
 Him+0.001
igh+0.001
 story+0.001
row+0.001
Neg logit contributions
Yeah-0.002
 Whe-0.002
Really-0.002
 kicking-0.002
 throwing-0.002
Token.
Token ID13
Feature activation+3.53e-03

Pos logit contributions
ace+0.020
igh+0.018
 Him+0.018
ery+0.017
row+0.017
Neg logit contributions
Yeah-0.020
 Whe-0.018
 throwing-0.018
 kicking-0.018
 Tim-0.017
Token "
Token ID366
Feature activation-7.63e-03

Pos logit contributions
ace+0.006
 Him+0.005
 story+0.005
igh+0.005
aret+0.005
Neg logit contributions
Yeah-0.006
awed-0.006
 throwing-0.005
 kicking-0.005
 pro-0.005
TokenWe
Token ID1135
Feature activation+7.88e-03

Pos logit contributions
 throwing+0.009
 kicking+0.008
 Tim+0.008
Yeah+0.008
awed+0.008
Neg logit contributions
ace-0.016
ery-0.015
igh-0.015
 Him-0.014
ent-0.014
Token can
Token ID460
Feature activation-6.64e-03

Pos logit contributions
ace+0.013
 Him+0.012
igh+0.012
aret+0.011
row+0.011
Neg logit contributions
Yeah-0.014
 Whe-0.013
 throwing-0.012
 Tim-0.012
 kicking-0.012
Token slide
Token ID10649
Feature activation-5.81e-02

Pos logit contributions
Yeah+0.011
 Whe+0.011
awed+0.011
 throwing+0.010
Really+0.010
Neg logit contributions
ace-0.010
igh-0.010
 Him-0.009
ery-0.009
ent-0.009
Token on
Token ID319
Feature activation-1.07e-02

Pos logit contributions
Yeah+0.117
Really+0.111
awed+0.110
sed+0.109
run+0.105
Neg logit contributions
igh-0.058
 story-0.057
 off-0.057
ace-0.056
 forward-0.055
Token the
Token ID262
Feature activation+1.09e-02

Pos logit contributions
Yeah+0.020
awed+0.019
 Whe+0.019
run+0.019
Really+0.018
Neg logit contributions
ace-0.014
igh-0.014
 story-0.013
ery-0.013
ent-0.013
Token floor
Token ID4314
Feature activation+4.92e-03

Pos logit contributions
ace+0.023
 story+0.022
ery+0.022
igh+0.021
aret+0.021
Neg logit contributions
Yeah-0.013
awed-0.011
 Whe-0.011
Really-0.011
run-0.011
Token.
Token ID13
Feature activation-1.93e-02

Pos logit contributions
ace+0.007
igh+0.006
row+0.006
ery+0.006
ent+0.006
Neg logit contributions
Yeah-0.009
 Whe-0.009
Really-0.009
awed-0.008
 kicking-0.008
Token It
Token ID632
Feature activation-2.96e-02

Pos logit contributions
awed+0.028
 throwing+0.026
Yeah+0.026
 kicking+0.025
 pro+0.024
Neg logit contributions
ace-0.036
 Him-0.033
igh-0.033
 prayers-0.032
aying-0.030
Token.
Token ID13
Feature activation-2.63e-02

Pos logit contributions
Yeah+0.006
 Whe+0.006
 throwing+0.005
 kicking+0.005
Really+0.005
Neg logit contributions
ace-0.006
igh-0.005
ery-0.005
row-0.005
 Him-0.005
Token I
Token ID314
Feature activation-8.38e-03

Pos logit contributions
Yeah+0.034
awed+0.033
 throwing+0.032
 kicking+0.031
 pro+0.030
Neg logit contributions
ace-0.052
igh-0.049
 Him-0.046
 story-0.045
 prayers-0.045
Token am
Token ID716
Feature activation-8.24e-03

Pos logit contributions
Yeah+0.015
 throwing+0.013
 Whe+0.013
 kicking+0.013
 Tim+0.013
Neg logit contributions
ace-0.013
igh-0.013
ery-0.012
row-0.012
 Him-0.012
Token going
Token ID1016
Feature activation-3.19e-02

Pos logit contributions
Yeah+0.014
Really+0.014
awed+0.014
run+0.013
 Whe+0.012
Neg logit contributions
ace-0.013
igh-0.011
ery-0.011
 Him-0.011
 story-0.011
Token to
Token ID284
Feature activation-3.33e-02

Pos logit contributions
Yeah+0.061
Really+0.059
awed+0.057
 Whe+0.055
run+0.052
Neg logit contributions
ace-0.043
row-0.039
 story-0.038
igh-0.038
ent-0.037
Token slide
Token ID10649
Feature activation-5.80e-02

Pos logit contributions
awed+0.073
Yeah+0.068
Really+0.065
ounced+0.063
run+0.061
Neg logit contributions
 story-0.042
ace-0.041
 pray-0.040
 answer-0.039
igh-0.037
Token."
Token ID526
Feature activation-5.06e-04

Pos logit contributions
Yeah+0.125
Really+0.121
awed+0.116
sed+0.115
run+0.114
Neg logit contributions
ace-0.054
 forward-0.050
 off-0.050
 away-0.047
igh-0.047
Token He
Token ID679
Feature activation-2.43e-02

Pos logit contributions
Yeah+0.001
 pro+0.000
 throwing+0.000
 kicking+0.000
awed+0.000
Neg logit contributions
ace-0.001
 story-0.001
 Him-0.001
amps-0.001
 prayers-0.001
Token pushes
Token ID20070
Feature activation-1.09e-02

Pos logit contributions
Yeah+0.041
Really+0.037
run+0.037
 Tim+0.037
 Whe+0.036
Neg logit contributions
ace-0.035
igh-0.033
 story-0.032
ery-0.031
 prayers-0.031
Token himself
Token ID2241
Feature activation-3.09e-03

Pos logit contributions
Yeah+0.009
 Whe+0.007
 throwing+0.007
Really+0.007
 kicking+0.007
Neg logit contributions
ace-0.028
igh-0.026
 Him-0.026
ery-0.025
row-0.025
Token and
Token ID290
Feature activation-2.29e-02

Pos logit contributions
Yeah+0.005
 Whe+0.005
 throwing+0.005
 kicking+0.005
 Tim+0.005
Neg logit contributions
ace-0.005
igh-0.005
 Him-0.005
ery-0.005
row-0.005
Tokenay
Token ID323
Feature activation-1.63e-03

Pos logit contributions
Yeah+0.040
 Whe+0.037
 throwing+0.037
 kicking+0.037
 Tim+0.036
Neg logit contributions
ace-0.025
igh-0.023
row-0.022
 Him-0.021
ery-0.021
Token!"
Token ID2474
Feature activation-4.84e-03

Pos logit contributions
Yeah+0.003
 Whe+0.002
 throwing+0.002
 kicking+0.002
Really+0.002
Neg logit contributions
ace-0.003
igh-0.003
row-0.003
ery-0.002
 Him-0.002
Token
Token ID198
Feature activation-6.29e-03

Pos logit contributions
Really+0.009
rou+0.008
awed+0.008
idd+0.008
ounced+0.008
Neg logit contributions
 story-0.005
ace-0.005
 Him-0.005
taker-0.005
apa-0.004
Token
Token ID198
Feature activation-3.67e-03

Pos logit contributions
Yeah+0.010
 pro+0.009
 kicking+0.009
Really+0.009
 throwing+0.009
Neg logit contributions
ace-0.010
 story-0.010
row-0.010
 Him-0.009
aret-0.009
TokenThey
Token ID2990
Feature activation-1.19e-03

Pos logit contributions
Yeah+0.005
 Whe+0.005
 throwing+0.005
 kicking+0.005
run+0.005
Neg logit contributions
ace-0.006
row-0.006
ent-0.006
ery-0.006
aret-0.006
Token slide
Token ID10649
Feature activation-5.80e-02

Pos logit contributions
Yeah+0.002
 Whe+0.002
 throwing+0.002
 kicking+0.002
awed+0.002
Neg logit contributions
ace-0.002
igh-0.002
 Him-0.002
ery-0.002
row-0.002
Token again
Token ID757
Feature activation-1.79e-02

Pos logit contributions
Yeah+0.125
Really+0.123
run+0.115
 Whe+0.114
 throwing+0.113
Neg logit contributions
ace-0.059
row-0.045
 off-0.044
aret-0.044
igh-0.043
Token and
Token ID290
Feature activation-2.74e-02

Pos logit contributions
Yeah+0.041
Really+0.038
awed+0.038
 Whe+0.037
ounced+0.036
Neg logit contributions
ace-0.019
 story-0.016
row-0.015
igh-0.014
ent-0.014
Token again
Token ID757
Feature activation-1.68e-02

Pos logit contributions
Yeah+0.042
run+0.041
awed+0.039
Really+0.036
etchup+0.036
Neg logit contributions
ace-0.044
igh-0.043
 Him-0.042
iece-0.041
 story-0.040
Token.
Token ID13
Feature activation-2.51e-03

Pos logit contributions
awed+0.040
Yeah+0.040
Really+0.038
ounced+0.038
 Whe+0.036
Neg logit contributions
ace-0.013
 story-0.011
 Him-0.010
 answer-0.010
iece-0.009
Token They
Token ID1119
Feature activation-1.24e-02

Pos logit contributions
 pro+0.004
rou+0.004
awed+0.004
iw+0.004
etchup+0.004
Neg logit contributions
 prayers-0.003
amps-0.003
 Today-0.003
ace-0.003
aying-0.002
Token He
Token ID679
Feature activation-1.16e-02

Pos logit contributions
ace+0.007
 Him+0.006
 story+0.006
 prayers+0.006
row+0.006
Neg logit contributions
Yeah-0.009
 throwing-0.009
 kicking-0.009
 pro-0.009
awed-0.008
Token does
Token ID857
Feature activation+9.90e-03

Pos logit contributions
Yeah+0.021
 Whe+0.019
 Tim+0.018
run+0.018
 throwing+0.018
Neg logit contributions
ace-0.017
igh-0.016
 story-0.015
ery-0.015
 Him-0.015
Token not
Token ID407
Feature activation-4.86e-04

Pos logit contributions
ace+0.015
 Him+0.014
ery+0.014
igh+0.013
 story+0.013
Neg logit contributions
Yeah-0.017
awed-0.016
 Whe-0.016
Really-0.015
 Tim-0.015
Token want
Token ID765
Feature activation-4.35e-03

Pos logit contributions
Yeah+0.001
 Whe+0.001
 throwing+0.001
 Tim+0.001
 kicking+0.001
Neg logit contributions
ace-0.001
igh-0.001
 Him-0.001
aret-0.001
row-0.001
Token to
Token ID284
Feature activation-2.64e-02

Pos logit contributions
Yeah+0.009
awed+0.008
Really+0.008
ang+0.008
 pro+0.008
Neg logit contributions
ace-0.006
 Him-0.005
 permission-0.005
 story-0.005
 prayers-0.005
Token slide
Token ID10649
Feature activation-5.77e-02

Pos logit contributions
awed+0.055
Yeah+0.054
Really+0.053
run+0.052
 Whe+0.050
Neg logit contributions
ace-0.032
 story-0.029
ent-0.029
igh-0.027
 pray-0.026
Token anymore
Token ID7471
Feature activation-2.54e-02

Pos logit contributions
Yeah+0.120
Really+0.116
 Whe+0.109
awed+0.104
sed+0.103
Neg logit contributions
ace-0.064
 away-0.059
 off-0.059
iness-0.059
 forward-0.056
Token.
Token ID13
Feature activation+8.16e-03

Pos logit contributions
Yeah+0.062
awed+0.056
Really+0.055
 Whe+0.055
etchup+0.053
Neg logit contributions
 story-0.022
ace-0.022
row-0.018
ent-0.018
ery-0.018
Token He
Token ID679
Feature activation-1.23e-02

Pos logit contributions
ace+0.012
 Him+0.010
 story+0.009
amps+0.009
row+0.009
Neg logit contributions
Yeah-0.016
 throwing-0.015
 kicking-0.015
 pro-0.015
awed-0.015
Token wants
Token ID3382
Feature activation-1.10e-02

Pos logit contributions
Yeah+0.022
 Whe+0.021
 Tim+0.020
 throwing+0.020
 kicking+0.019
Neg logit contributions
ace-0.018
igh-0.017
ery-0.016
 story-0.016
 Him-0.016
Token to
Token ID284
Feature activation-3.67e-02

Pos logit contributions
Yeah+0.023
awed+0.022
Really+0.021
ang+0.021
�+0.021
Neg logit contributions
 permission-0.012
ace-0.012
 Him-0.012
 story-0.011
 prayers-0.011
Token,
Token ID11
Feature activation-1.77e-02

Pos logit contributions
ace+0.004
 Him+0.004
igh+0.004
aret+0.004
ery+0.004
Neg logit contributions
Yeah-0.005
 Tim-0.005
 Tom-0.004
 throwing-0.004
 kicking-0.004
Token mom
Token ID1995
Feature activation-1.29e-03

Pos logit contributions
awed+0.025
Yeah+0.023
 throwing+0.020
 kicking+0.020
 Whe+0.019
Neg logit contributions
ace-0.034
 story-0.033
igh-0.033
 Him-0.032
 prayers-0.031
Token,
Token ID11
Feature activation-1.60e-02

Pos logit contributions
Yeah+0.002
 Whe+0.002
 kicking+0.002
 throwing+0.002
Really+0.002
Neg logit contributions
ace-0.002
igh-0.002
 Him-0.002
row-0.002
aret-0.002
Token can
Token ID460
Feature activation-1.63e-02

Pos logit contributions
Yeah+0.025
 Whe+0.023
 throwing+0.023
 kicking+0.023
awed+0.022
Neg logit contributions
ace-0.028
igh-0.026
 Him-0.026
ery-0.025
row-0.025
Token we
Token ID356
Feature activation-1.39e-02

Pos logit contributions
Yeah+0.019
awed+0.019
 Whe+0.018
 throwing+0.017
 pro+0.017
Neg logit contributions
ace-0.033
igh-0.032
 Him-0.031
 story-0.030
aret-0.030
Token slide
Token ID10649
Feature activation-5.76e-02

Pos logit contributions
Yeah+0.023
 Whe+0.021
 throwing+0.021
 kicking+0.021
 Tim+0.021
Neg logit contributions
ace-0.023
igh-0.021
 Him-0.021
ery-0.020
row-0.020
Token?
Token ID30
Feature activation-2.40e-02

Pos logit contributions
Yeah+0.120
Really+0.112
awed+0.110
 Whe+0.109
run+0.103
Neg logit contributions
igh-0.060
ace-0.059
 away-0.058
 off-0.055
ery-0.054
Token Just
Token ID2329
Feature activation-1.35e-02

Pos logit contributions
awed+0.035
Yeah+0.033
 throwing+0.032
 kicking+0.032
 pro+0.031
Neg logit contributions
ace-0.041
igh-0.040
 Him-0.039
 prayers-0.037
aying-0.036
Token once
Token ID1752
Feature activation-1.88e-02

Pos logit contributions
awed+0.028
Yeah+0.027
 Whe+0.024
Really+0.024
Nice+0.024
Neg logit contributions
ace-0.019
igh-0.016
 pray-0.015
ery-0.015
ent-0.015
Token?"
Token ID1701
Feature activation+1.01e-03

Pos logit contributions
Yeah+0.043
awed+0.042
 Whe+0.039
Really+0.039
etchup+0.037
Neg logit contributions
ace-0.022
 story-0.019
row-0.018
ery-0.017
igh-0.016
Token Their
Token ID5334
Feature activation+4.55e-03

Pos logit contributions
 Him+0.002
ace+0.002
 story+0.002
aret+0.002
 prayers+0.002
Neg logit contributions
awed-0.002
Yeah-0.001
 pro-0.001
 kicking-0.001
run-0.001
Token and
Token ID290
Feature activation-2.48e-02

Pos logit contributions
Yeah+0.011
 Whe+0.010
 kicking+0.010
 throwing+0.010
Really+0.010
Neg logit contributions
ace-0.011
igh-0.010
 Him-0.010
row-0.010
ery-0.010
Token saw
Token ID2497
Feature activation-2.75e-02

Pos logit contributions
etchup+0.040
 kicking+0.039
�+0.039
Yeah+0.038
iw+0.038
Neg logit contributions
ace-0.037
 Him-0.036
taker-0.035
aret-0.034
 prayers-0.034
Token two
Token ID734
Feature activation-1.82e-02

Pos logit contributions
Yeah+0.042
Really+0.041
iw+0.040
ounced+0.037
etchup+0.037
Neg logit contributions
ace-0.045
 story-0.043
 Him-0.043
taker-0.043
ery-0.042
Token kids
Token ID3988
Feature activation-1.90e-02

Pos logit contributions
Yeah+0.034
 Whe+0.033
Really+0.032
iw+0.030
run+0.030
Neg logit contributions
 story-0.026
ace-0.023
igh-0.023
eness-0.021
amps-0.021
Token fighting
Token ID4330
Feature activation-1.96e-02

Pos logit contributions
Yeah+0.025
Really+0.024
 Whe+0.023
awed+0.020
etchup+0.019
Neg logit contributions
igh-0.036
ace-0.036
 story-0.035
row-0.034
ent-0.033
Token over
Token ID625
Feature activation-5.71e-02

Pos logit contributions
Yeah+0.040
Really+0.040
iw+0.039
 Whe+0.038
etchup+0.038
Neg logit contributions
ace-0.022
 story-0.020
ent-0.019
igh-0.019
ery-0.019
Token a
Token ID257
Feature activation-1.92e-02

Pos logit contributions
Yeah+0.116
Really+0.112
ounced+0.106
 Whe+0.106
awed+0.102
Neg logit contributions
 story-0.063
ace-0.062
 stories-0.056
 deeds-0.056
igh-0.055
Token toy
Token ID13373
Feature activation-3.54e-02

Pos logit contributions
awed+0.038
Yeah+0.037
Really+0.036
run+0.034
etchup+0.034
Neg logit contributions
 story-0.026
 letter-0.021
 compass-0.021
 telescope-0.020
 shield-0.020
Token.
Token ID13
Feature activation-1.65e-02

Pos logit contributions
Yeah+0.070
Really+0.069
 Whe+0.067
run+0.064
etchup+0.064
Neg logit contributions
 story-0.041
ace-0.041
igh-0.039
row-0.038
ent-0.037
Token
Token ID198
Feature activation-8.01e-03

Pos logit contributions
Yeah+0.026
 kicking+0.025
awed+0.024
 throwing+0.024
ang+0.024
Neg logit contributions
 story-0.023
ace-0.023
 Him-0.023
aret-0.021
 prayers-0.021
Token
Token ID198
Feature activation-1.01e-03

Pos logit contributions
Yeah+0.012
Really+0.011
 kicking+0.011
awed+0.010
 throwing+0.010
Neg logit contributions
ace-0.014
 story-0.013
 Him-0.013
aret-0.013
ery-0.012
Token her
Token ID607
Feature activation-2.99e-02

Pos logit contributions
awed+0.038
ounced+0.037
Yeah+0.036
run+0.035
ang+0.034
Neg logit contributions
 Him-0.025
ace-0.023
 pray-0.023
 prayers-0.021
 answer-0.020
Token.
Token ID13
Feature activation+6.78e-03

Pos logit contributions
Yeah+0.058
 Whe+0.054
awed+0.053
Really+0.052
run+0.051
Neg logit contributions
ace-0.043
 story-0.039
 prayers-0.036
aret-0.035
ery-0.035
Token They
Token ID1119
Feature activation+4.65e-04

Pos logit contributions
ace+0.010
 Him+0.010
 prayers+0.009
aret+0.009
 story+0.009
Neg logit contributions
Yeah-0.011
 kicking-0.010
 throwing-0.010
awed-0.010
 pro-0.010
Token started
Token ID2067
Feature activation-1.30e-02

Pos logit contributions
ace+0.001
igh+0.001
 Him+0.001
ery+0.001
row+0.001
Neg logit contributions
Yeah-0.001
 Whe-0.001
 throwing-0.001
 kicking-0.001
 Tim-0.000
Token to
Token ID284
Feature activation-3.42e-02

Pos logit contributions
Yeah+0.019
Really+0.017
 Whe+0.017
awed+0.016
 kicking+0.016
Neg logit contributions
ace-0.024
igh-0.022
 Him-0.022
row-0.021
aret-0.021
Token slide
Token ID10649
Feature activation-5.70e-02

Pos logit contributions
Yeah+0.047
 Whe+0.043
 throwing+0.043
 kicking+0.042
 Tim+0.042
Neg logit contributions
ace-0.067
igh-0.063
 Him-0.062
row-0.061
ery-0.060
Token down
Token ID866
Feature activation-3.82e-02

Pos logit contributions
Yeah+0.124
Really+0.118
run+0.115
awed+0.111
etchup+0.110
Neg logit contributions
ace-0.064
aret-0.049
row-0.048
ery-0.047
ent-0.046
Token the
Token ID262
Feature activation-9.87e-03

Pos logit contributions
Yeah+0.067
 Whe+0.062
Really+0.061
awed+0.061
run+0.060
Neg logit contributions
ace-0.059
 story-0.049
igh-0.049
ery-0.048
row-0.048
Token stairs
Token ID16046
Feature activation-1.66e-02

Pos logit contributions
Yeah+0.014
 Whe+0.013
 throwing+0.013
 kicking+0.012
 Tim+0.012
Neg logit contributions
ace-0.019
igh-0.017
 Him-0.017
ery-0.017
row-0.017
Token together
Token ID1978
Feature activation-9.44e-04

Pos logit contributions
Yeah+0.032
Really+0.031
 Whe+0.031
awed+0.029
run+0.028
Neg logit contributions
ace-0.023
igh-0.019
row-0.019
ent-0.019
ery-0.018
Token.
Token ID13
Feature activation-9.96e-04

Pos logit contributions
Yeah+0.002
 Whe+0.002
Really+0.002
awed+0.002
 throwing+0.002
Neg logit contributions
ace-0.001
ery-0.001
igh-0.001
row-0.001
ent-0.001
Token She
Token ID1375
Feature activation+2.09e-02

Pos logit contributions
ace+0.028
igh+0.025
 Him+0.024
aret+0.024
row+0.024
Neg logit contributions
Yeah-0.031
 throwing-0.029
 kicking-0.028
 Whe-0.028
awed-0.027
Token put
Token ID1234
Feature activation+1.50e-02

Pos logit contributions
ace+0.040
igh+0.037
row+0.036
 Him+0.036
ery+0.036
Neg logit contributions
Yeah-0.030
 Whe-0.027
 throwing-0.027
 kicking-0.027
 Tim-0.026
Token on
Token ID319
Feature activation+5.30e-02

Pos logit contributions
ace+0.029
 Him+0.028
aret+0.028
igh+0.028
ides+0.028
Neg logit contributions
 Lily-0.019
 Tom-0.019
 Tim-0.019
 Whe-0.019
 Sara-0.018
Token her
Token ID607
Feature activation+2.74e-02

Pos logit contributions
igh+0.116
iness+0.113
ery+0.110
eness+0.109
ace+0.109
Neg logit contributions
 Lily-0.066
 Tom-0.064
 Tim-0.063
 throwing-0.061
 swinging-0.061
Token warm
Token ID5814
Feature activation+4.99e-02

Pos logit contributions
ace+0.049
igh+0.047
 Him+0.046
aret+0.045
row+0.045
Neg logit contributions
Yeah-0.041
 Whe-0.039
 kicking-0.038
 throwing-0.038
 Tim-0.037
Token red
Token ID2266
Feature activation+4.59e-02

Pos logit contributions
igh+0.099
 Him+0.094
ery+0.091
ace+0.091
 narrative+0.091
Neg logit contributions
 kicking-0.062
 Tim-0.061
 Lily-0.061
 swinging-0.059
 throwing-0.059
Token coat
Token ID13209
Feature activation+1.77e-02

Pos logit contributions
 Him+0.095
ace+0.093
igh+0.092
aret+0.091
amps+0.089
Neg logit contributions
 soccer-0.052
 kicking-0.051
 Tim-0.050
 Whe-0.050
 Lily-0.050
Token,
Token ID11
Feature activation+1.50e-02

Pos logit contributions
ace+0.036
 Him+0.035
igh+0.034
ery+0.034
aret+0.033
Neg logit contributions
Yeah-0.021
 Tim-0.021
 Tom-0.021
 throwing-0.020
 kicking-0.020
Token and
Token ID290
Feature activation+2.89e-02

Pos logit contributions
ace+0.028
igh+0.026
 Him+0.025
ery+0.025
row+0.025
Neg logit contributions
Yeah-0.023
 Whe-0.021
 throwing-0.021
 kicking-0.020
 Tim-0.020
Token stepped
Token ID10764
Feature activation-4.19e-03

Pos logit contributions
ace+0.052
igh+0.049
 Him+0.047
ery+0.046
row+0.046
Neg logit contributions
Yeah-0.045
 Whe-0.041
 throwing-0.041
 kicking-0.040
 Tim-0.040
Token outside
Token ID2354
Feature activation+1.10e-02

Pos logit contributions
Yeah+0.005
 kicking+0.005
 throwing+0.005
 Whe+0.005
 Lily+0.004
Neg logit contributions
ace-0.009
aret-0.009
igh-0.009
iness-0.008
 deeds-0.008
Token from
Token ID422
Feature activation-5.49e-03

Pos logit contributions
ace+0.006
igh+0.005
 Him+0.005
ery+0.005
row+0.005
Neg logit contributions
Yeah-0.004
awed-0.004
 Whe-0.004
 throwing-0.004
 kicking-0.004
Token Grand
Token ID5675
Feature activation+1.84e-02

Pos logit contributions
awed+0.009
Yeah+0.009
 Whe+0.009
�+0.008
Really+0.008
Neg logit contributions
ace-0.009
 Him-0.008
aret-0.008
igh-0.008
 permission-0.008
Tokenma
Token ID2611
Feature activation+3.69e-02

Pos logit contributions
ace+0.025
ery+0.022
row+0.021
este+0.020
 Him+0.020
Neg logit contributions
 Tom-0.035
Yeah-0.034
 throwing-0.034
 Tim-0.034
 kicking-0.033
Token and
Token ID290
Feature activation+1.91e-03

Pos logit contributions
ace+0.055
igh+0.050
 Him+0.049
ery+0.048
row+0.048
Neg logit contributions
Yeah-0.067
 throwing-0.062
 Whe-0.062
 kicking-0.062
 Tim-0.061
Token Grand
Token ID5675
Feature activation+2.50e-02

Pos logit contributions
ace+0.004
igh+0.003
 Him+0.003
aret+0.003
 prayers+0.003
Neg logit contributions
Yeah-0.003
awed-0.003
 throwing-0.002
 kicking-0.002
 Whe-0.002
Tokenpa
Token ID8957
Feature activation+4.73e-02

Pos logit contributions
ace+0.027
ery+0.024
row+0.023
este+0.021
 compass+0.021
Neg logit contributions
 Tom-0.054
Yeah-0.052
 Tim-0.052
 throwing-0.051
 kicking-0.050
Token'.
Token ID4458
Feature activation-4.72e-03

Pos logit contributions
ace+0.069
igh+0.062
 Him+0.061
ery+0.060
row+0.060
Neg logit contributions
Yeah-0.087
 throwing-0.081
 Whe-0.081
 kicking-0.080
 Tim-0.080
Token It
Token ID632
Feature activation-4.02e-04

Pos logit contributions
 kicking+0.007
Yeah+0.007
 throwing+0.007
awed+0.007
 pro+0.006
Neg logit contributions
ace-0.008
 Him-0.008
aret-0.007
igh-0.007
 prayers-0.007
Token is
Token ID318
Feature activation+3.33e-03

Pos logit contributions
Yeah+0.001
 Whe+0.001
 throwing+0.001
 kicking+0.001
 Tim+0.001
Neg logit contributions
ace-0.001
igh-0.001
 Him-0.001
row-0.001
ery-0.001
Token a
Token ID257
Feature activation-2.31e-02

Pos logit contributions
ace+0.006
ery+0.005
 Him+0.005
 story+0.005
aret+0.005
Neg logit contributions
Yeah-0.005
awed-0.005
Really-0.005
 Whe-0.005
 pro-0.004
Token gift
Token ID6979
Feature activation+3.18e-03

Pos logit contributions
awed+0.042
Yeah+0.042
run+0.039
 Tim+0.037
 Whe+0.036
Neg logit contributions
 story-0.035
ace-0.030
ery-0.029
igh-0.029
 prayers-0.029
Token a
Token ID257
Feature activation+1.02e-02

Pos logit contributions
Yeah+0.011
awed+0.011
ounced+0.010
etchup+0.010
Really+0.010
Neg logit contributions
 Him-0.010
ace-0.010
 story-0.009
igh-0.009
 prayers-0.009
Token big
Token ID1263
Feature activation+1.36e-02

Pos logit contributions
 story+0.015
ace+0.013
igh+0.013
ery+0.013
 compass+0.013
Neg logit contributions
Yeah-0.020
awed-0.018
 Whe-0.017
Really-0.017
 Tim-0.017
Token black
Token ID2042
Feature activation+1.53e-02

Pos logit contributions
ace+0.020
igh+0.019
 story+0.018
row+0.018
ery+0.018
Neg logit contributions
Yeah-0.026
 Whe-0.023
awed-0.022
Really-0.022
 throwing-0.022
Token bird
Token ID6512
Feature activation+6.06e-03

Pos logit contributions
ace+0.025
igh+0.023
 Him+0.022
row+0.022
ery+0.022
Neg logit contributions
Yeah-0.027
 Whe-0.024
 throwing-0.024
 kicking-0.024
 Tim-0.024
Token on
Token ID319
Feature activation+8.44e-03

Pos logit contributions
ace+0.011
igh+0.010
 Him+0.010
row+0.010
ery+0.010
Neg logit contributions
Yeah-0.009
 Whe-0.008
 throwing-0.008
 kicking-0.008
 Tim-0.008
Token the
Token ID262
Feature activation+4.64e-02

Pos logit contributions
ace+0.017
igh+0.016
 Him+0.016
ery+0.015
aret+0.015
Neg logit contributions
Yeah-0.011
 Whe-0.010
 throwing-0.010
 kicking-0.010
awed-0.009
Token fence
Token ID13990
Feature activation+1.54e-02

Pos logit contributions
igh+0.072
ace+0.069
 Him+0.068
row+0.063
ery+0.063
Neg logit contributions
 throwing-0.079
 kicking-0.078
Yeah-0.077
 Tom-0.076
 Whe-0.075
Token.
Token ID13
Feature activation-7.65e-03

Pos logit contributions
ace+0.026
igh+0.024
 Him+0.024
row+0.023
ery+0.023
Neg logit contributions
Yeah-0.025
 Whe-0.023
 throwing-0.022
 kicking-0.022
 Tim-0.022
Token "
Token ID366
Feature activation-9.38e-03

Pos logit contributions
Yeah+0.010
run+0.009
ang+0.009
Really+0.009
ounced+0.009
Neg logit contributions
 Him-0.012
ace-0.012
 prayers-0.011
 story-0.011
apa-0.011
TokenLet
Token ID5756
Feature activation+1.34e-02

Pos logit contributions
Yeah+0.011
 throwing+0.011
 kicking+0.011
 Tim+0.010
 Whe+0.010
Neg logit contributions
ace-0.018
igh-0.017
 Him-0.017
ery-0.017
ent-0.017
Token's
Token ID338
Feature activation+3.50e-03

Pos logit contributions
ace+0.021
igh+0.020
ery+0.019
 Him+0.019
row+0.019
Neg logit contributions
 Tim-0.025
 Tom-0.025
 Lily-0.024
 Spot-0.023
 throwing-0.023
Token have
Token ID423
Feature activation+1.17e-02

Pos logit contributions
ace+0.042
aret+0.039
 Him+0.039
row+0.039
igh+0.038
Neg logit contributions
Yeah-0.030
 Tom-0.027
 throwing-0.027
 Tim-0.027
 kicking-0.027
Token with
Token ID351
Feature activation+3.82e-02

Pos logit contributions
ace+0.022
igh+0.020
 Him+0.020
aret+0.020
row+0.019
Neg logit contributions
Yeah-0.017
 throwing-0.016
 kicking-0.016
 Whe-0.016
 Tim-0.015
Token others
Token ID1854
Feature activation+2.07e-02

Pos logit contributions
ace+0.065
igh+0.060
 Him+0.058
row+0.058
ery+0.057
Neg logit contributions
Yeah-0.062
 Whe-0.057
 throwing-0.057
 kicking-0.057
 Tim-0.056
Token than
Token ID621
Feature activation+1.76e-02

Pos logit contributions
ace+0.037
igh+0.035
 Him+0.034
row+0.034
aret+0.034
Neg logit contributions
Yeah-0.031
 throwing-0.029
 Whe-0.028
 kicking-0.028
 Tim-0.028
Token to
Token ID284
Feature activation+8.89e-03

Pos logit contributions
ace+0.030
 Him+0.029
igh+0.028
ent+0.026
 story+0.026
Neg logit contributions
Yeah-0.029
 Whe-0.027
awed-0.026
Really-0.025
 pro-0.024
Token keep
Token ID1394
Feature activation+4.61e-02

Pos logit contributions
ace+0.013
 story+0.012
igh+0.012
 Him+0.012
ent+0.012
Neg logit contributions
Yeah-0.016
 Whe-0.015
awed-0.015
run-0.015
Really-0.014
Token it
Token ID340
Feature activation+2.98e-02

Pos logit contributions
ace+0.084
igh+0.077
row+0.076
ery+0.074
aret+0.073
Neg logit contributions
 throwing-0.067
Yeah-0.066
 Tim-0.065
 kicking-0.064
 Tom-0.064
Token for
Token ID329
Feature activation+3.75e-02

Pos logit contributions
ace+0.062
igh+0.061
aret+0.060
 Him+0.060
este+0.058
Neg logit contributions
 throwing-0.032
 Tim-0.032
 Lily-0.031
 kicking-0.031
 Tom-0.031
Token yourself
Token ID3511
Feature activation+2.08e-02

Pos logit contributions
ace+0.062
igh+0.057
 Him+0.056
ery+0.055
row+0.055
Neg logit contributions
Yeah-0.063
 Whe-0.058
 throwing-0.057
 kicking-0.057
 Tim-0.056
Token and
Token ID290
Feature activation-5.22e-03

Pos logit contributions
ace+0.038
igh+0.035
 Him+0.035
aret+0.034
ery+0.034
Neg logit contributions
Yeah-0.030
 throwing-0.028
 kicking-0.028
 Whe-0.028
 Tim-0.027
Token let
Token ID1309
Feature activation+3.74e-02

Pos logit contributions
Yeah+0.009
awed+0.009
 Whe+0.008
 kicking+0.008
run+0.008
Neg logit contributions
ace-0.008
 Him-0.008
igh-0.007
 deeds-0.007
 prayers-0.007
Token children
Token ID1751
Feature activation+3.41e-02

Pos logit contributions
ace+0.011
igh+0.010
 Him+0.010
row+0.010
aret+0.009
Neg logit contributions
Yeah-0.023
 Whe-0.021
 throwing-0.021
 kicking-0.021
 Tim-0.021
Token to
Token ID284
Feature activation+2.32e-02

Pos logit contributions
ace+0.071
aret+0.068
igh+0.067
 Him+0.067
row+0.067
Neg logit contributions
Yeah-0.039
 throwing-0.037
 kicking-0.036
 Tom-0.035
 Tim-0.035
Token listen
Token ID6004
Feature activation+2.94e-02

Pos logit contributions
ace+0.040
igh+0.037
row+0.036
 Him+0.036
ery+0.035
Neg logit contributions
Yeah-0.037
 throwing-0.034
 Tim-0.034
 kicking-0.034
 Tom-0.034
Token to
Token ID284
Feature activation+3.30e-02

Pos logit contributions
ace+0.062
igh+0.059
ery+0.056
row+0.056
 Him+0.056
Neg logit contributions
Yeah-0.036
 throwing-0.032
 kicking-0.032
 Whe-0.031
 Tim-0.031
Token their
Token ID511
Feature activation+1.98e-02

Pos logit contributions
ace+0.057
igh+0.052
 Him+0.052
ery+0.050
aret+0.050
Neg logit contributions
Yeah-0.054
 Whe-0.050
 throwing-0.049
 kicking-0.049
 Tim-0.048
Token parents
Token ID3397
Feature activation+4.37e-02

Pos logit contributions
ace+0.030
igh+0.029
row+0.027
ery+0.027
 Him+0.026
Neg logit contributions
Yeah-0.036
 throwing-0.033
 kicking-0.033
 Whe-0.033
 Tom-0.032
Token,
Token ID11
Feature activation+1.17e-02

Pos logit contributions
ace+0.086
igh+0.079
aret+0.078
row+0.078
ery+0.078
Neg logit contributions
Yeah-0.055
 throwing-0.053
 kicking-0.053
 Tom-0.052
 Tim-0.051
Token follow
Token ID1061
Feature activation+4.30e-02

Pos logit contributions
ace+0.021
 Him+0.020
igh+0.020
ery+0.019
row+0.019
Neg logit contributions
Yeah-0.018
 Whe-0.016
awed-0.016
 throwing-0.016
 kicking-0.016
Token the
Token ID262
Feature activation+3.24e-02

Pos logit contributions
ace+0.084
igh+0.079
ery+0.077
row+0.077
 Him+0.075
Neg logit contributions
Yeah-0.057
 throwing-0.052
 Tim-0.052
 Tom-0.052
 Whe-0.052
Token rules
Token ID3173
Feature activation+2.61e-02

Pos logit contributions
ace+0.051
row+0.045
igh+0.045
ery+0.043
aret+0.041
Neg logit contributions
Yeah-0.058
 throwing-0.056
 kicking-0.056
 Whe-0.055
 Tom-0.053
Token,
Token ID11
Feature activation+1.62e-02

Pos logit contributions
ace+0.045
igh+0.041
 Him+0.040
row+0.039
ery+0.039
Neg logit contributions
Yeah-0.042
 Whe-0.039
 throwing-0.038
 kicking-0.038
 Tim-0.038
Token deserve
Token ID10925
Feature activation+2.20e-02

Pos logit contributions
Yeah+0.003
 Whe+0.003
 throwing+0.003
 kicking+0.003
 Tim+0.003
Neg logit contributions
ace-0.003
igh-0.003
 Him-0.003
ery-0.003
row-0.003
Token respect
Token ID2461
Feature activation+2.12e-02

Pos logit contributions
ace+0.040
igh+0.037
 Him+0.037
ery+0.035
row+0.035
Neg logit contributions
Yeah-0.034
 Whe-0.031
 kicking-0.030
 throwing-0.030
awed-0.029
Token and
Token ID290
Feature activation+6.83e-03

Pos logit contributions
ace+0.037
igh+0.034
row+0.033
 Him+0.033
ery+0.033
Neg logit contributions
Yeah-0.033
 throwing-0.030
 Whe-0.030
 kicking-0.030
 Tim-0.030
Token kindness
Token ID23887
Feature activation+2.53e-02

Pos logit contributions
ace+0.010
igh+0.009
 Him+0.009
ery+0.008
row+0.008
Neg logit contributions
Yeah-0.013
 Whe-0.012
 throwing-0.012
 kicking-0.012
 Tim-0.012
Token from
Token ID422
Feature activation+1.96e-02

Pos logit contributions
ace+0.044
igh+0.041
 Him+0.040
aret+0.040
row+0.040
Neg logit contributions
Yeah-0.038
 throwing-0.035
 Whe-0.035
 kicking-0.035
 Tim-0.035
Token everyone
Token ID2506
Feature activation+1.72e-02

Pos logit contributions
ace+0.032
 Him+0.031
igh+0.030
aret+0.029
ent+0.027
Neg logit contributions
Yeah-0.034
 Whe-0.033
awed-0.033
 kicking-0.030
 throwing-0.030
Token."
Token ID526
Feature activation-1.20e-03

Pos logit contributions
ace+0.030
igh+0.028
 Him+0.027
row+0.027
ery+0.027
Neg logit contributions
Yeah-0.027
 Whe-0.025
 throwing-0.025
 kicking-0.025
 Tim-0.024
Token Jack
Token ID3619
Feature activation+2.02e-02

Pos logit contributions
Yeah+0.002
 throwing+0.002
 kicking+0.002
awed+0.002
 Whe+0.002
Neg logit contributions
ace-0.002
 Him-0.002
igh-0.002
 story-0.002
aret-0.002
Token thought
Token ID1807
Feature activation+2.51e-03

Pos logit contributions
ace+0.041
 Him+0.039
igh+0.039
ery+0.038
row+0.038
Neg logit contributions
Yeah-0.026
 kicking-0.022
 throwing-0.022
 Tim-0.022
 Tom-0.022
Token about
Token ID546
Feature activation-1.53e-02

Pos logit contributions
ace+0.005
igh+0.005
row+0.005
ery+0.005
 Him+0.005
Neg logit contributions
Yeah-0.003
 throwing-0.003
 kicking-0.003
 Tim-0.003
 Whe-0.003
Token this
Token ID428
Feature activation+1.02e-02

Pos logit contributions
Yeah+0.024
awed+0.022
 Whe+0.021
etchup+0.020
run+0.020
Neg logit contributions
 story-0.027
 Him-0.026
igh-0.026
ace-0.025
 prayers-0.024
Token need
Token ID761
Feature activation+1.15e-02

Pos logit contributions
ace+0.003
 Him+0.003
aret+0.003
row+0.003
ery+0.003
Neg logit contributions
Yeah-0.003
 Tim-0.003
 throwing-0.003
 Tom-0.003
 Whe-0.003
Token to
Token ID284
Feature activation+1.71e-02

Pos logit contributions
ace+0.020
igh+0.018
 Him+0.018
row+0.018
ery+0.017
Neg logit contributions
Yeah-0.019
awed-0.017
 Whe-0.017
Really-0.016
 throwing-0.016
Token read
Token ID1100
Feature activation-3.00e-03

Pos logit contributions
ace+0.028
igh+0.027
 Him+0.026
row+0.025
ery+0.025
Neg logit contributions
Yeah-0.028
 throwing-0.026
 kicking-0.026
 Tim-0.026
 Tom-0.026
Token books
Token ID3835
Feature activation-1.32e-02

Pos logit contributions
Yeah+0.005
awed+0.004
 Whe+0.004
 throwing+0.004
 kicking+0.004
Neg logit contributions
ace-0.005
 Him-0.005
igh-0.005
ery-0.005
 story-0.005
Token and
Token ID290
Feature activation+3.62e-03

Pos logit contributions
Yeah+0.020
 Whe+0.018
 throwing+0.018
 kicking+0.018
 Tim+0.017
Neg logit contributions
ace-0.024
igh-0.022
 Him-0.022
ery-0.021
row-0.021
Token practice
Token ID3357
Feature activation+1.61e-02

Pos logit contributions
ace+0.005
 Him+0.005
igh+0.005
 story+0.005
aret+0.004
Neg logit contributions
Yeah-0.007
awed-0.006
 Whe-0.006
 throwing-0.006
 kicking-0.006
Token if
Token ID611
Feature activation+6.87e-03

Pos logit contributions
ace+0.027
igh+0.025
 Him+0.025
ery+0.024
aret+0.023
Neg logit contributions
Yeah-0.027
awed-0.024
 Whe-0.024
 throwing-0.024
 Tim-0.024
Token you
Token ID345
Feature activation+5.04e-03

Pos logit contributions
ace+0.011
 Him+0.011
igh+0.011
 story+0.010
ery+0.010
Neg logit contributions
Yeah-0.012
awed-0.011
 Whe-0.010
 throwing-0.010
 kicking-0.010
Token really
Token ID1107
Feature activation+5.42e-03

Pos logit contributions
ace+0.008
aret+0.008
 Him+0.008
row+0.008
igh+0.008
Neg logit contributions
Yeah-0.008
 Whe-0.007
 Tom-0.007
 Tim-0.007
 kicking-0.007
Token want
Token ID765
Feature activation+2.57e-02

Pos logit contributions
ace+0.009
igh+0.008
 Him+0.008
ery+0.008
row+0.008
Neg logit contributions
Yeah-0.009
 Whe-0.009
 throwing-0.009
 kicking-0.009
 Tim-0.008
Token to
Token ID284
Feature activation+2.73e-03

Pos logit contributions
ace+0.047
igh+0.044
 Him+0.043
row+0.042
ery+0.042
Neg logit contributions
Yeah-0.038
 Whe-0.035
 throwing-0.035
 kicking-0.035
 Tim-0.034
Token with
Token ID351
Feature activation+1.14e-02

Pos logit contributions
Yeah+0.011
 Whe+0.010
Really+0.010
 pro+0.010
awed+0.010
Neg logit contributions
ace-0.009
 story-0.009
row-0.009
igh-0.008
ent-0.008
Token all
Token ID477
Feature activation-3.15e-03

Pos logit contributions
ace+0.015
 Him+0.013
igh+0.013
 story+0.012
aret+0.012
Neg logit contributions
Yeah-0.024
Really-0.022
 pro-0.021
awed-0.021
 Whe-0.021
Token the
Token ID262
Feature activation+2.71e-03

Pos logit contributions
Yeah+0.004
 Tim+0.004
 Tom+0.004
 throwing+0.004
 Whe+0.004
Neg logit contributions
ace-0.007
igh-0.006
 Him-0.006
row-0.006
ery-0.006
Token animals
Token ID4695
Feature activation+3.26e-03

Pos logit contributions
ace+0.004
igh+0.004
 Him+0.004
 story+0.004
aret+0.004
Neg logit contributions
Yeah-0.005
 Whe-0.004
 kicking-0.004
Really-0.004
 throwing-0.004
Token in
Token ID287
Feature activation-1.37e-02

Pos logit contributions
ace+0.006
igh+0.005
 Him+0.005
ery+0.005
row+0.005
Neg logit contributions
Yeah-0.005
 Whe-0.005
 throwing-0.005
 kicking-0.004
 Tim-0.004
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
Yeah+0.023
Really+0.021
awed+0.021
 pro+0.020
 Whe+0.020
Neg logit contributions
ace-0.024
 story-0.022
igh-0.022
 Him-0.020
aret-0.020
Token forest
Token ID8222
Feature activation-1.36e-03

Pos logit contributions
ace+0.024
igh+0.022
 Him+0.021
 story+0.021
row+0.021
Neg logit contributions
Yeah-0.019
 Whe-0.017
 throwing-0.017
 kicking-0.017
 Tim-0.017
Token.
Token ID13
Feature activation-1.48e-02

Pos logit contributions
Yeah+0.003
 Whe+0.002
Really+0.002
 kicking+0.002
 pro+0.002
Neg logit contributions
ace-0.002
igh-0.002
row-0.002
 story-0.002
 Him-0.002
Token He
Token ID679
Feature activation-5.18e-04

Pos logit contributions
Yeah+0.028
 pro+0.026
etchup+0.026
idd+0.026
ounced+0.025
Neg logit contributions
 story-0.017
ace-0.016
amps-0.015
 Him-0.014
 prayers-0.013
Token wanted
Token ID2227
Feature activation-1.40e-03

Pos logit contributions
Yeah+0.001
 Whe+0.001
etchup+0.001
run+0.001
 kicking+0.001
Neg logit contributions
ace-0.001
aret-0.001
este-0.001
row-0.001
 story-0.001
Token to
Token ID284
Feature activation-1.31e-02

Pos logit contributions
Yeah+0.002
Really+0.002
awed+0.002
 Whe+0.002
 kicking+0.002
Neg logit contributions
ace-0.002
 Him-0.002
 story-0.002
igh-0.002
row-0.002
Token the
Token ID262
Feature activation+1.14e-02

Pos logit contributions
ace+0.061
igh+0.059
row+0.059
ery+0.058
 Him+0.057
Neg logit contributions
Yeah-0.033
 Tom-0.032
 Tim-0.032
 Lily-0.031
 Whe-0.031
Token box
Token ID3091
Feature activation+2.63e-02

Pos logit contributions
ace+0.021
aret+0.018
 Him+0.018
amps+0.018
row+0.018
Neg logit contributions
 Tim-0.018
 Tom-0.018
 Whe-0.017
 throwing-0.017
 Lily-0.017
Token and
Token ID290
Feature activation-1.42e-02

Pos logit contributions
igh+0.057
 Him+0.056
ery+0.054
ace+0.054
este+0.053
Neg logit contributions
 Tim-0.028
 Tom-0.028
 Lily-0.026
 throwing-0.026
 Sue-0.025
Token thanking
Token ID41892
Feature activation+2.27e-02

Pos logit contributions
Yeah+0.021
 Whe+0.018
awed+0.018
Really+0.017
run+0.016
Neg logit contributions
ace-0.025
igh-0.024
 Him-0.023
 prayers-0.023
row-0.023
Token the
Token ID262
Feature activation+4.57e-03

Pos logit contributions
ace+0.048
row+0.046
ery+0.046
igh+0.045
este+0.042
Neg logit contributions
 Tom-0.028
 Tim-0.028
Yeah-0.027
 Lily-0.027
 Sara-0.026
Token mail
Token ID6920
Feature activation+1.69e-02

Pos logit contributions
ace+0.006
igh+0.005
 Him+0.005
row+0.005
ery+0.005
Neg logit contributions
Yeah-0.010
 Whe-0.009
 throwing-0.009
 kicking-0.009
 Tim-0.009
Tokenman
Token ID805
Feature activation+9.09e-03

Pos logit contributions
ace+0.024
igh+0.022
ery+0.021
amps+0.021
aret+0.021
Neg logit contributions
 Tom-0.030
 Tim-0.030
Yeah-0.029
 Lily-0.029
 Sue-0.028
Token.
Token ID13
Feature activation+1.45e-02

Pos logit contributions
ace+0.018
igh+0.016
ery+0.016
aret+0.016
row+0.016
Neg logit contributions
Yeah-0.012
 Tom-0.011
 Tim-0.011
 throwing-0.011
 Lily-0.011
Token
Token ID198
Feature activation+5.01e-04

Pos logit contributions
 Him+0.024
ace+0.023
aret+0.022
 prayers+0.021
 story+0.021
Neg logit contributions
awed-0.023
 kicking-0.022
Yeah-0.022
 throwing-0.022
ounced-0.021
Token
Token ID198
Feature activation+7.69e-03

Pos logit contributions
ace+0.001
 Him+0.001
 story+0.001
aret+0.001
igh+0.001
Neg logit contributions
Yeah-0.001
 kicking-0.001
 pro-0.001
 throwing-0.001
awed-0.001
TokenThey
Token ID2990
Feature activation+2.59e-02

Pos logit contributions
ace+0.015
igh+0.014
 Him+0.014
ery+0.014
row+0.013
Neg logit contributions
Yeah-0.011
 throwing-0.010
 Whe-0.010
 kicking-0.010
 Tom-0.009
Tokenara
Token ID3301
Feature activation-1.13e-02

Pos logit contributions
Yeah+0.004
 Whe+0.003
 throwing+0.003
 kicking+0.003
 Tim+0.003
Neg logit contributions
ace-0.014
igh-0.013
 Him-0.013
aret-0.013
row-0.013
Token and
Token ID290
Feature activation+9.77e-03

Pos logit contributions
Yeah+0.018
 Whe+0.017
 throwing+0.017
 kicking+0.016
 Tim+0.016
Neg logit contributions
ace-0.019
igh-0.018
 Him-0.018
row-0.017
ery-0.017
Token Ben
Token ID3932
Feature activation+2.70e-02

Pos logit contributions
ace+0.020
 Him+0.020
igh+0.020
 story+0.018
 deeds+0.018
Neg logit contributions
Yeah-0.012
run-0.010
awed-0.010
Really-0.010
 Whe-0.010
Token nod
Token ID18666
Feature activation+2.66e-03

Pos logit contributions
ace+0.046
row+0.045
aret+0.045
ery+0.042
 Him+0.041
Neg logit contributions
Yeah-0.043
 Tom-0.041
 Tim-0.038
 kicking-0.038
 throwing-0.038
Token.
Token ID13
Feature activation+2.63e-02

Pos logit contributions
ace+0.005
igh+0.005
ery+0.005
aret+0.005
row+0.005
Neg logit contributions
Yeah-0.003
 Tim-0.003
 Lily-0.003
 Tom-0.003
 throwing-0.003
Token They
Token ID1119
Feature activation+1.66e-02

Pos logit contributions
ace+0.039
 Him+0.036
 prayers+0.035
amps+0.034
 deeds+0.033
Neg logit contributions
 throwing-0.045
 kicking-0.045
Yeah-0.044
awed-0.044
run-0.043
Token say
Token ID910
Feature activation+1.40e-02

Pos logit contributions
ace+0.028
row+0.027
igh+0.026
aret+0.026
 Him+0.026
Neg logit contributions
Yeah-0.026
 Tom-0.026
 Tim-0.025
 Lily-0.024
 Whe-0.023
Token thank
Token ID5875
Feature activation+1.73e-02

Pos logit contributions
ace+0.030
igh+0.027
row+0.027
aret+0.027
este+0.026
Neg logit contributions
Yeah-0.018
 Tom-0.017
 Tim-0.017
 throwing-0.017
 Lily-0.017
Token you
Token ID345
Feature activation+2.19e-02

Pos logit contributions
ace+0.033
igh+0.031
 Him+0.030
ery+0.030
row+0.030
Neg logit contributions
Yeah-0.025
 Whe-0.022
 throwing-0.022
 kicking-0.022
 Tim-0.022
Token and
Token ID290
Feature activation+8.04e-03

Pos logit contributions
igh+0.053
ace+0.053
ery+0.052
este+0.050
aret+0.049
Neg logit contributions
 Tom-0.020
 Lily-0.019
 Tim-0.018
 Sara-0.018
 throwing-0.017
Token sorry
Token ID7926
Feature activation+7.27e-03

Pos logit contributions
ace+0.011
igh+0.010
 Him+0.010
ery+0.010
aret+0.010
Neg logit contributions
Yeah-0.015
 Whe-0.014
 throwing-0.014
 kicking-0.014
awed-0.014
Token.
Token ID13
Feature activation-1.35e-02

Pos logit contributions
Yeah+0.062
 Whe+0.059
Really+0.056
awed+0.053
 throwing+0.053
Neg logit contributions
ace-0.050
row-0.045
igh-0.045
 story-0.044
ery-0.044
Token M
Token ID337
Feature activation-1.65e-02

Pos logit contributions
Yeah+0.025
 throwing+0.024
awed+0.024
 kicking+0.024
 scoring+0.023
Neg logit contributions
ace-0.019
 Him-0.016
igh-0.015
apa-0.015
 story-0.015
Tokenimi
Token ID25236
Feature activation-1.42e-02

Pos logit contributions
Yeah+0.034
 Whe+0.033
 throwing+0.032
 kicking+0.032
 pro+0.031
Neg logit contributions
ace-0.023
igh-0.019
 Him-0.019
row-0.019
ery-0.019
Token cheered
Token ID34767
Feature activation+5.62e-03

Pos logit contributions
Yeah+0.022
 Whe+0.021
Really+0.019
 throwing+0.019
 kicking+0.019
Neg logit contributions
ace-0.025
igh-0.023
ery-0.022
row-0.022
 story-0.021
Token for
Token ID329
Feature activation-3.17e-03

Pos logit contributions
ace+0.011
igh+0.010
ery+0.010
row+0.010
 Him+0.010
Neg logit contributions
Yeah-0.008
 Tim-0.007
 Tom-0.007
 throwing-0.007
 Whe-0.007
Token her
Token ID607
Feature activation-1.57e-02

Pos logit contributions
Yeah+0.006
 Whe+0.006
awed+0.006
 throwing+0.006
 kicking+0.006
Neg logit contributions
ace-0.004
 Him-0.004
igh-0.004
aret-0.004
row-0.004
Token and
Token ID290
Feature activation+1.10e-03

Pos logit contributions
Yeah+0.027
 Whe+0.025
awed+0.025
Really+0.024
 throwing+0.024
Neg logit contributions
ace-0.026
igh-0.023
 story-0.022
 Him-0.022
ery-0.022
Token showed
Token ID3751
Feature activation+1.02e-02

Pos logit contributions
ace+0.001
ered+0.001
row+0.001
aret+0.001
igh+0.001
Neg logit contributions
Yeah-0.002
 Whe-0.002
Really-0.002
etchup-0.002
Whe-0.002
Token her
Token ID607
Feature activation-1.73e-02

Pos logit contributions
ace+0.015
igh+0.013
 Him+0.013
aret+0.013
row+0.013
Neg logit contributions
Yeah-0.020
 Whe-0.018
 throwing-0.018
 kicking-0.018
Really-0.017
Token how
Token ID703
Feature activation-1.55e-02

Pos logit contributions
Yeah+0.028
 Whe+0.025
Really+0.025
awed+0.025
 throwing+0.023
Neg logit contributions
ace-0.030
 story-0.028
igh-0.028
ery-0.027
 prayers-0.027
Token to
Token ID284
Feature activation-7.29e-03

Pos logit contributions
Yeah+0.024
 Whe+0.023
 throwing+0.022
 kicking+0.022
Really+0.022
Neg logit contributions
ace-0.026
 Him-0.024
row-0.023
igh-0.023
 story-0.023
Token the
Token ID262
Feature activation+1.04e-03

Pos logit contributions
Yeah+0.029
 Whe+0.027
awed+0.026
run+0.026
Really+0.025
Neg logit contributions
ace-0.030
 wax-0.026
 story-0.026
ent-0.025
este-0.025
Token air
Token ID1633
Feature activation+9.90e-03

Pos logit contributions
ace+0.001
row+0.001
igh+0.001
ery+0.001
 story+0.001
Neg logit contributions
Yeah-0.002
 Whe-0.002
 kicking-0.002
 throwing-0.002
run-0.002
Token.
Token ID13
Feature activation+7.57e-03

Pos logit contributions
ace+0.017
igh+0.016
 Him+0.015
row+0.015
ery+0.015
Neg logit contributions
Yeah-0.016
 Whe-0.015
 throwing-0.014
 kicking-0.014
 Tim-0.014
Token
Token ID198
Feature activation-5.80e-04

Pos logit contributions
ace+0.010
 Him+0.010
 story+0.009
 prayers+0.009
aying+0.009
Neg logit contributions
Yeah-0.013
awed-0.012
ounced-0.012
 carn-0.012
 scoring-0.012
Token
Token ID198
Feature activation+3.61e-03

Pos logit contributions
Yeah+0.001
 pro+0.001
awed+0.001
 throwing+0.001
 kicking+0.001
Neg logit contributions
ace-0.001
 Him-0.001
 story-0.001
igh-0.001
aret-0.001
Token"
Token ID1
Feature activation-1.73e-02

Pos logit contributions
ace+0.005
igh+0.005
 Him+0.005
ery+0.004
row+0.004
Neg logit contributions
Yeah-0.007
 Whe-0.006
 throwing-0.006
 kicking-0.006
 Tom-0.006
TokenOh
Token ID5812
Feature activation-1.20e-02

Pos logit contributions
run+0.026
 kicking+0.024
 throwing+0.024
 Tim+0.024
ounces+0.023
Neg logit contributions
ace-0.028
ery-0.026
 narrative-0.026
ent-0.025
 wax-0.025
Token no
Token ID645
Feature activation-5.14e-03

Pos logit contributions
Yeah+0.021
 Whe+0.020
 throwing+0.019
 kicking+0.019
awed+0.018
Neg logit contributions
ace-0.019
igh-0.018
 Him-0.017
ery-0.017
 story-0.017
Token!"
Token ID2474
Feature activation-2.85e-03

Pos logit contributions
Yeah+0.011
 Whe+0.010
Really+0.010
awed+0.010
run+0.010
Neg logit contributions
ace-0.006
 story-0.005
igh-0.005
ent-0.005
row-0.005
Token Ben
Token ID3932
Feature activation-7.89e-03

Pos logit contributions
Yeah+0.003
run+0.003
awed+0.003
 throwing+0.003
 kicking+0.003
Neg logit contributions
ace-0.006
 Him-0.006
 story-0.006
igh-0.006
 prayers-0.005
Token says
Token ID1139
Feature activation-8.66e-04

Pos logit contributions
Yeah+0.013
 Whe+0.012
 throwing+0.011
 kicking+0.011
 Tim+0.011
Neg logit contributions
ace-0.014
igh-0.013
 Him-0.012
row-0.012
ery-0.012
Token was
Token ID373
Feature activation-8.80e-03

Pos logit contributions
Yeah+0.006
 Whe+0.006
run+0.005
 kicking+0.005
 throwing+0.005
Neg logit contributions
ace-0.005
ery-0.005
este-0.005
igh-0.005
row-0.005
Token happy
Token ID3772
Feature activation-1.80e-02

Pos logit contributions
Yeah+0.015
 Whe+0.014
Really+0.014
awed+0.013
run+0.013
Neg logit contributions
ace-0.015
igh-0.013
 story-0.012
ery-0.012
 Him-0.012
Token to
Token ID284
Feature activation+1.48e-02

Pos logit contributions
Yeah+0.031
run+0.028
 Whe+0.028
awed+0.027
Really+0.027
Neg logit contributions
 Him-0.025
 story-0.025
ace-0.025
 deeds-0.023
 prayers-0.023
Token have
Token ID423
Feature activation-4.19e-03

Pos logit contributions
ace+0.030
igh+0.029
ery+0.028
aret+0.028
row+0.028
Neg logit contributions
Yeah-0.019
 throwing-0.017
 Tim-0.017
 Whe-0.017
 kicking-0.017
Token helped
Token ID4193
Feature activation+1.47e-02

Pos logit contributions
Yeah+0.008
Really+0.007
 Whe+0.007
run+0.007
 kicking+0.007
Neg logit contributions
ace-0.007
ery-0.006
igh-0.006
row-0.006
ent-0.006
Token fix
Token ID4259
Feature activation+6.09e-04

Pos logit contributions
ace+0.028
igh+0.026
 Him+0.026
row+0.025
ery+0.025
Neg logit contributions
Yeah-0.022
 Whe-0.019
 throwing-0.019
 kicking-0.019
 Tim-0.018
Token the
Token ID262
Feature activation+4.37e-03

Pos logit contributions
ace+0.001
igh+0.001
 Him+0.001
ery+0.001
aret+0.001
Neg logit contributions
Yeah-0.001
 Whe-0.001
Really-0.001
 kicking-0.001
run-0.001
Token fence
Token ID13990
Feature activation-1.08e-03

Pos logit contributions
ace+0.007
 story+0.007
igh+0.006
ery+0.006
row+0.006
Neg logit contributions
Yeah-0.008
 Whe-0.007
run-0.007
 kicking-0.007
 throwing-0.006
Token so
Token ID523
Feature activation-2.10e-03

Pos logit contributions
Yeah+0.002
 Whe+0.002
 kicking+0.002
 throwing+0.002
Really+0.002
Neg logit contributions
ace-0.002
igh-0.002
row-0.002
 Him-0.002
ery-0.002
Token the
Token ID262
Feature activation-3.29e-03

Pos logit contributions
Yeah+0.004
 Whe+0.003
 kicking+0.003
 throwing+0.003
 carn+0.003
Neg logit contributions
 Him-0.003
ace-0.003
ery-0.003
 prayers-0.003
 wax-0.003
Token little
Token ID1310
Feature activation-8.44e-03

Pos logit contributions
Yeah+0.005
 Whe+0.005
 kicking+0.005
 throwing+0.005
run+0.005
Neg logit contributions
ace-0.006
igh-0.005
 story-0.005
 Him-0.005
ery-0.005
Token the
Token ID262
Feature activation+7.17e-04

Pos logit contributions
awed+0.033
Yeah+0.031
Really+0.031
ounced+0.031
etchup+0.028
Neg logit contributions
ace-0.022
 answer-0.020
 story-0.019
 Him-0.019
aret-0.019
Token door
Token ID3420
Feature activation-1.78e-02

Pos logit contributions
ace+0.001
 story+0.001
ery+0.001
 Him+0.001
igh+0.001
Neg logit contributions
Yeah-0.002
awed-0.001
run-0.001
 throwing-0.001
 Whe-0.001
Token.
Token ID13
Feature activation-1.48e-03

Pos logit contributions
Yeah+0.028
 Whe+0.026
 throwing+0.026
 kicking+0.026
 Tim+0.025
Neg logit contributions
ace-0.031
igh-0.028
 Him-0.028
row-0.027
ery-0.027
Token He
Token ID679
Feature activation+1.02e-04

Pos logit contributions
awed+0.003
Yeah+0.003
ounced+0.003
 throwing+0.003
etchup+0.003
Neg logit contributions
ace-0.002
 prayers-0.002
 Him-0.002
 story-0.001
aret-0.001
Token looked
Token ID3114
Feature activation+4.69e-03

Pos logit contributions
ace+0.000
row+0.000
este+0.000
igh+0.000
aret+0.000
Neg logit contributions
Yeah-0.000
 Whe-0.000
 throwing-0.000
 kicking-0.000
Really-0.000
Token back
Token ID736
Feature activation-1.08e-02

Pos logit contributions
ace+0.008
igh+0.008
row+0.008
 Him+0.008
ery+0.008
Neg logit contributions
Yeah-0.007
 Tim-0.007
 Whe-0.007
 throwing-0.007
 kicking-0.007
Token and
Token ID290
Feature activation+3.63e-03

Pos logit contributions
Yeah+0.022
 Whe+0.021
Really+0.020
 pro+0.019
 throwing+0.019
Neg logit contributions
ace-0.014
igh-0.013
row-0.012
 Him-0.012
 story-0.012
Token saw
Token ID2497
Feature activation-2.29e-02

Pos logit contributions
 Him+0.006
ace+0.006
igh+0.006
aret+0.006
pa+0.006
Neg logit contributions
Yeah-0.005
�-0.005
 Whe-0.005
etchup-0.004
run-0.004
Token Lily
Token ID20037
Feature activation-6.43e-03

Pos logit contributions
Yeah+0.044
Really+0.040
awed+0.040
 Whe+0.039
�+0.038
Neg logit contributions
taker-0.030
ace-0.029
 wax-0.029
 Him-0.029
ery-0.028
Token laughing
Token ID14376
Feature activation-1.81e-02

Pos logit contributions
Yeah+0.010
 Whe+0.009
 throwing+0.008
 Tim+0.008
 kicking+0.008
Neg logit contributions
ace-0.012
igh-0.011
 Him-0.011
row-0.011
ery-0.011
Token.
Token ID13
Feature activation-8.43e-04

Pos logit contributions
Yeah+0.029
 Whe+0.026
 throwing+0.026
 kicking+0.026
 Tim+0.025
Neg logit contributions
ace-0.032
igh-0.029
 Him-0.029
ery-0.028
row-0.028
Token,
Token ID11
Feature activation-1.66e-02

Pos logit contributions
ace+0.003
 Him+0.003
igh+0.003
row+0.003
ery+0.003
Neg logit contributions
Yeah-0.004
 throwing-0.003
 kicking-0.003
 Tim-0.003
 Whe-0.003
Token Sally
Token ID25737
Feature activation+1.22e-02

Pos logit contributions
awed+0.018
Yeah+0.018
 kicking+0.015
 throwing+0.015
run+0.015
Neg logit contributions
ace-0.037
 Him-0.035
igh-0.034
 story-0.034
aret-0.033
Token smiled
Token ID13541
Feature activation-8.21e-03

Pos logit contributions
ace+0.023
 Him+0.021
igh+0.021
row+0.021
aret+0.020
Neg logit contributions
Yeah-0.017
 throwing-0.016
 kicking-0.016
 Tim-0.016
 Tom-0.016
Token and
Token ID290
Feature activation+6.54e-03

Pos logit contributions
Yeah+0.012
 Whe+0.011
 throwing+0.011
 Tim+0.011
 kicking+0.011
Neg logit contributions
ace-0.015
igh-0.014
row-0.014
 Him-0.014
ery-0.014
Token went
Token ID1816
Feature activation+8.33e-04

Pos logit contributions
ace+0.011
igh+0.009
 prayers+0.009
ery+0.009
row+0.009
Neg logit contributions
Yeah-0.010
 Whe-0.010
Really-0.010
 throwing-0.010
 kicking-0.010
Token back
Token ID736
Feature activation-6.87e-03

Pos logit contributions
ace+0.001
igh+0.001
 Him+0.001
row+0.001
ery+0.001
Neg logit contributions
Yeah-0.002
 Whe-0.001
 throwing-0.001
 kicking-0.001
 Tim-0.001
Token to
Token ID284
Feature activation-1.63e-03

Pos logit contributions
Yeah+0.013
Really+0.012
 Whe+0.011
awed+0.011
 pro+0.011
Neg logit contributions
ace-0.011
igh-0.009
 Him-0.009
row-0.009
 story-0.009
Token playing
Token ID2712
Feature activation-1.51e-02

Pos logit contributions
Yeah+0.003
awed+0.003
Really+0.003
ounced+0.002
run+0.002
Neg logit contributions
 Him-0.003
ace-0.003
 story-0.003
igh-0.003
aret-0.002
Token in
Token ID287
Feature activation-1.92e-02

Pos logit contributions
Yeah+0.023
Really+0.020
run+0.020
awed+0.020
 Whe+0.020
Neg logit contributions
ace-0.027
ery-0.025
 story-0.024
igh-0.024
ent-0.024
Token the
Token ID262
Feature activation+3.15e-03

Pos logit contributions
Yeah+0.042
awed+0.042
ounced+0.041
Really+0.040
 Whe+0.037
Neg logit contributions
ace-0.023
 story-0.020
 wax-0.019
aret-0.017
ent-0.017
Token garden
Token ID11376
Feature activation+4.15e-04

Pos logit contributions
ace+0.005
 story+0.005
ery+0.005
igh+0.005
 Him+0.004
Neg logit contributions
Yeah-0.005
run-0.005
 Whe-0.005
awed-0.005
 throwing-0.005
TokenAfter
Token ID3260
Feature activation-2.83e-02

Pos logit contributions
ace+0.004
ery+0.004
row+0.004
igh+0.004
aret+0.004
Neg logit contributions
Yeah-0.003
 Whe-0.003
 throwing-0.003
 kicking-0.002
awed-0.002
Token the
Token ID262
Feature activation-2.27e-02

Pos logit contributions
Yeah+0.044
awed+0.041
Really+0.040
run+0.040
 Whe+0.038
Neg logit contributions
 story-0.045
igh-0.041
 Him-0.041
 chores-0.041
 wax-0.040
Token cookies
Token ID14746
Feature activation-8.44e-03

Pos logit contributions
Yeah+0.034
 Whe+0.031
awed+0.030
run+0.030
 Tim+0.029
Neg logit contributions
ace-0.041
 story-0.038
ery-0.038
igh-0.038
 Him-0.037
Token were
Token ID547
Feature activation-1.54e-03

Pos logit contributions
Yeah+0.014
 Whe+0.013
Really+0.012
 kicking+0.012
 throwing+0.012
Neg logit contributions
ace-0.014
igh-0.013
ery-0.013
row-0.013
 Him-0.012
Token baked
Token ID22979
Feature activation-1.48e-02

Pos logit contributions
Yeah+0.003
 Whe+0.003
Really+0.003
 kicking+0.003
 throwing+0.003
Neg logit contributions
ace-0.002
igh-0.002
ery-0.002
row-0.002
 Him-0.002
Token and
Token ID290
Feature activation-3.41e-02

Pos logit contributions
Yeah+0.030
 Whe+0.028
 kicking+0.027
 throwing+0.027
Really+0.027
Neg logit contributions
ace-0.019
igh-0.017
ery-0.017
 Him-0.017
row-0.017
Token cooled
Token ID32162
Feature activation-1.02e-02

Pos logit contributions
awed+0.054
ang+0.053
Yeah+0.052
run+0.052
 Whe+0.050
Neg logit contributions
 wax-0.053
ery-0.048
 invitations-0.047
 story-0.047
 sheets-0.047
Token,
Token ID11
Feature activation-1.34e-02

Pos logit contributions
Yeah+0.019
 Whe+0.017
Really+0.017
 kicking+0.017
 throwing+0.017
Neg logit contributions
ace-0.015
 Him-0.014
aret-0.014
row-0.014
igh-0.013
Token Lily
Token ID20037
Feature activation-6.18e-03

Pos logit contributions
run+0.016
awed+0.016
Yeah+0.014
ounced+0.014
ang+0.014
Neg logit contributions
 Him-0.024
 wax-0.024
ace-0.024
 prayers-0.023
aret-0.023
Token's
Token ID338
Feature activation-2.27e-02

Pos logit contributions
Yeah+0.012
 Whe+0.012
 throwing+0.011
 kicking+0.011
 Tim+0.011
Neg logit contributions
ace-0.008
igh-0.008
ery-0.007
row-0.007
 Him-0.007
Token mom
Token ID1995
Feature activation-2.69e-02

Pos logit contributions
Yeah+0.040
 Whe+0.039
awed+0.036
Really+0.036
run+0.036
Neg logit contributions
ace-0.034
 story-0.033
ery-0.031
 prayers-0.031
aret-0.030
Token doing
Token ID1804
Feature activation-4.51e-03

Pos logit contributions
Yeah+0.019
 Whe+0.017
awed+0.017
Really+0.017
run+0.016
Neg logit contributions
ace-0.016
igh-0.016
 Him-0.015
 story-0.015
ent-0.014
Token things
Token ID1243
Feature activation-1.50e-02

Pos logit contributions
Yeah+0.007
 Whe+0.007
awed+0.006
Really+0.006
 throwing+0.006
Neg logit contributions
ace-0.008
igh-0.007
 Him-0.007
ery-0.007
 story-0.007
Token like
Token ID588
Feature activation-7.68e-03

Pos logit contributions
Yeah+0.026
 Whe+0.024
Really+0.023
awed+0.022
 kicking+0.022
Neg logit contributions
ace-0.024
igh-0.023
ery-0.022
 Him-0.022
row-0.022
Token this
Token ID428
Feature activation-1.18e-02

Pos logit contributions
Yeah+0.013
 Whe+0.012
awed+0.011
Really+0.011
 kicking+0.010
Neg logit contributions
ace-0.013
igh-0.012
 story-0.012
 Him-0.012
ery-0.012
Token."
Token ID526
Feature activation-2.49e-02

Pos logit contributions
Yeah+0.023
 Whe+0.021
awed+0.021
 throwing+0.020
 kicking+0.020
Neg logit contributions
ace-0.017
 story-0.016
ery-0.015
igh-0.015
row-0.015
Token
Token ID220
Feature activation-3.63e-02

Pos logit contributions
awed+0.036
Yeah+0.036
 throwing+0.034
ounced+0.034
 kicking+0.033
Neg logit contributions
ace-0.042
 Him-0.038
 story-0.037
igh-0.037
aret-0.036
Token
Token ID198
Feature activation-1.82e-02

Pos logit contributions
Yeah+0.051
 throwing+0.045
 kicking+0.045
 pro+0.044
Really+0.044
Neg logit contributions
ace-0.071
 Him-0.065
igh-0.065
 story-0.063
ery-0.063
Token
Token ID198
Feature activation-9.97e-03

Pos logit contributions
Yeah+0.026
 throwing+0.025
awed+0.025
 kicking+0.025
 pro+0.024
Neg logit contributions
ace-0.032
 story-0.030
 Him-0.029
aret-0.029
igh-0.028
TokenJ
Token ID41
Feature activation+3.62e-03

Pos logit contributions
Yeah+0.014
 throwing+0.014
awed+0.014
 Whe+0.014
 kicking+0.014
Neg logit contributions
ace-0.018
igh-0.016
aret-0.016
 story-0.016
ery-0.016
Tokenill
Token ID359
Feature activation+5.41e-03

Pos logit contributions
ace+0.006
igh+0.006
 Him+0.006
row+0.006
ery+0.006
Neg logit contributions
Yeah-0.006
 Whe-0.005
 throwing-0.005
 kicking-0.005
 Tim-0.005
Token nodded
Token ID14464
Feature activation+5.80e-03

Pos logit contributions
ace+0.011
igh+0.010
 Him+0.010
ery+0.010
row+0.009
Neg logit contributions
Yeah-0.007
 Whe-0.007
 throwing-0.007
 kicking-0.007
 Tim-0.006
Token egg
Token ID5935
Feature activation+1.50e-02

Pos logit contributions
ace+0.040
igh+0.038
amps+0.036
leys+0.036
ides+0.035
Neg logit contributions
 throwing-0.039
 kid-0.039
Yeah-0.038
 Sara-0.038
 Tim-0.038
Token without
Token ID1231
Feature activation+2.69e-02

Pos logit contributions
 Him+0.029
igh+0.029
ace+0.029
aret+0.027
 prayers+0.027
Neg logit contributions
 Tim-0.019
 throwing-0.018
 Tom-0.017
 Sue-0.017
 Lily-0.017
Token being
Token ID852
Feature activation+7.05e-03

Pos logit contributions
ace+0.044
igh+0.042
 Him+0.041
ery+0.039
row+0.039
Neg logit contributions
Yeah-0.047
 Whe-0.042
awed-0.040
Really-0.040
 kicking-0.038
Token seen
Token ID1775
Feature activation-6.18e-03

Pos logit contributions
ace+0.012
igh+0.011
row+0.011
ery+0.011
 story+0.010
Neg logit contributions
Yeah-0.012
 Whe-0.011
Really-0.011
 Tim-0.010
 kicking-0.010
Token.
Token ID13
Feature activation-7.20e-04

Pos logit contributions
Yeah+0.011
 Whe+0.010
Really+0.009
 throwing+0.009
 kicking+0.009
Neg logit contributions
ace-0.010
igh-0.009
ery-0.009
row-0.009
 Him-0.009
Token
Token ID220
Feature activation-3.65e-02

Pos logit contributions
Yeah+0.001
 throwing+0.001
 kicking+0.001
awed+0.001
ounced+0.001
Neg logit contributions
ace-0.001
 Him-0.001
igh-0.001
 story-0.001
 prayers-0.001
Token
Token ID198
Feature activation+3.31e-03

Pos logit contributions
Yeah+0.057
 pro+0.050
 kicking+0.049
 throwing+0.049
Really+0.049
Neg logit contributions
ace-0.067
ery-0.060
igh-0.060
 Him-0.059
amps-0.059
Token
Token ID198
Feature activation+7.39e-03

Pos logit contributions
ace+0.006
 story+0.006
row+0.006
igh+0.006
ery+0.005
Neg logit contributions
Yeah-0.005
 throwing-0.004
awed-0.004
 kicking-0.004
Really-0.004
TokenHe
Token ID1544
Feature activation+6.70e-03

Pos logit contributions
ace+0.015
igh+0.015
 Him+0.015
aret+0.014
row+0.014
Neg logit contributions
Yeah-0.010
 Whe-0.009
 kicking-0.008
 throwing-0.008
 Tim-0.008
Token was
Token ID373
Feature activation-3.99e-05

Pos logit contributions
ace+0.011
igh+0.010
row+0.010
ery+0.010
aret+0.010
Neg logit contributions
Yeah-0.011
 Whe-0.011
 kicking-0.010
 throwing-0.010
run-0.010
Token so
Token ID523
Feature activation+4.08e-03

Pos logit contributions
Yeah+0.000
 Whe+0.000
Really+0.000
awed+0.000
etchup+0.000
Neg logit contributions
ace-0.000
igh-0.000
ery-0.000
 story-0.000
row-0.000
Token he
Token ID339
Feature activation-4.36e-03

Pos logit contributions
Yeah+0.001
 Whe+0.001
awed+0.001
 throwing+0.001
 kicking+0.001
Neg logit contributions
ace-0.001
igh-0.001
 Him-0.001
row-0.001
ery-0.001
Token could
Token ID714
Feature activation-1.06e-02

Pos logit contributions
Yeah+0.007
 Whe+0.006
 throwing+0.006
 kicking+0.006
 Tim+0.006
Neg logit contributions
ace-0.008
igh-0.007
row-0.007
ery-0.007
 Him-0.006
Token do
Token ID466
Feature activation+1.25e-02

Pos logit contributions
 kicking+0.016
 throwing+0.016
Yeah+0.016
 Whe+0.016
 Tim+0.016
Neg logit contributions
igh-0.017
 Him-0.017
ace-0.017
aret-0.016
ery-0.016
Token it
Token ID340
Feature activation-9.34e-03

Pos logit contributions
ace+0.021
igh+0.019
 Him+0.019
ery+0.018
row+0.018
Neg logit contributions
Yeah-0.021
 Whe-0.019
 throwing-0.019
 kicking-0.018
 Tim-0.018
Token.
Token ID13
Feature activation+1.83e-03

Pos logit contributions
Yeah+0.014
 Whe+0.013
 throwing+0.013
 kicking+0.013
 Tim+0.013
Neg logit contributions
ace-0.017
igh-0.016
 Him-0.016
aret-0.015
ery-0.015
Token
Token ID220
Feature activation-3.90e-02

Pos logit contributions
ace+0.003
 story+0.003
igh+0.003
row+0.003
 Him+0.003
Neg logit contributions
Yeah-0.003
 throwing-0.002
 pro-0.002
 kicking-0.002
awed-0.002
Token
Token ID198
Feature activation+1.37e-03

Pos logit contributions
Yeah+0.056
 throwing+0.049
 kicking+0.049
 pro+0.048
Really+0.048
Neg logit contributions
ace-0.077
ery-0.069
 Him-0.069
igh-0.069
 story-0.069
Token
Token ID198
Feature activation+6.41e-03

Pos logit contributions
ace+0.002
 story+0.002
row+0.002
igh+0.002
 Him+0.002
Neg logit contributions
Yeah-0.002
Really-0.002
 throwing-0.002
 pro-0.002
 kicking-0.002
TokenOne
Token ID3198
Feature activation-2.84e-03

Pos logit contributions
ace+0.012
igh+0.011
 Him+0.011
ery+0.010
row+0.010
Neg logit contributions
Yeah-0.010
 Whe-0.009
 throwing-0.009
 kicking-0.009
 Tim-0.009
Token day
Token ID1110
Feature activation+4.27e-03

Pos logit contributions
Yeah+0.005
 Whe+0.005
 throwing+0.005
 kicking+0.005
 Tim+0.005
Neg logit contributions
ace-0.004
igh-0.004
 Him-0.004
ery-0.004
row-0.004
Token,
Token ID11
Feature activation+6.27e-03

Pos logit contributions
ace+0.007
igh+0.006
 Him+0.006
aret+0.006
ery+0.006
Neg logit contributions
Yeah-0.007
 Tim-0.007
 throwing-0.007
 kicking-0.007
 Whe-0.007
Token tickets
Token ID8587
Feature activation+1.52e-02

Pos logit contributions
ace+0.091
igh+0.088
aret+0.088
row+0.085
ery+0.084
Neg logit contributions
 Tom-0.048
Yeah-0.048
 Lily-0.048
 Tim-0.047
 Sara-0.047
Token for
Token ID329
Feature activation+2.28e-02

Pos logit contributions
ace+0.029
igh+0.028
aret+0.027
 Him+0.027
ery+0.027
Neg logit contributions
Yeah-0.020
 Tom-0.019
 Tim-0.018
 throwing-0.018
 Whe-0.018
Token the
Token ID262
Feature activation+8.51e-03

Pos logit contributions
ace+0.036
 Him+0.034
igh+0.033
aret+0.031
 story+0.031
Neg logit contributions
Yeah-0.041
 Whe-0.038
awed-0.037
 kicking-0.036
 throwing-0.036
Token plane
Token ID6614
Feature activation+1.40e-02

Pos logit contributions
ace+0.013
igh+0.012
 Him+0.012
 story+0.011
ery+0.011
Neg logit contributions
Yeah-0.016
 Whe-0.014
 throwing-0.014
 kicking-0.014
 Tim-0.014
Token,"
Token ID553
Feature activation-7.37e-03

Pos logit contributions
ace+0.025
igh+0.023
 Him+0.023
ery+0.022
aret+0.022
Neg logit contributions
Yeah-0.021
 throwing-0.019
 Whe-0.019
 Tim-0.019
 kicking-0.019
Token mom
Token ID1995
Feature activation-2.83e-02

Pos logit contributions
Yeah+0.011
run+0.010
awed+0.010
ounced+0.010
 kicking+0.010
Neg logit contributions
 Him-0.013
ace-0.012
 story-0.011
igh-0.011
pa-0.011
Token says
Token ID1139
Feature activation+1.05e-02

Pos logit contributions
Yeah+0.038
 Tom+0.037
 Tim+0.035
 throwing+0.035
 Lily+0.034
Neg logit contributions
ace-0.056
igh-0.052
ery-0.051
row-0.051
 Him-0.050
Token.
Token ID13
Feature activation+5.33e-03

Pos logit contributions
ace+0.019
igh+0.018
 Him+0.017
ery+0.017
row+0.017
Neg logit contributions
Yeah-0.016
 throwing-0.015
 Whe-0.014
 kicking-0.014
 Tim-0.014
Token She
Token ID1375
Feature activation-8.28e-03

Pos logit contributions
ace+0.009
 Him+0.009
 story+0.009
aret+0.008
 prayers+0.008
Neg logit contributions
Yeah-0.008
 kicking-0.007
awed-0.007
 throwing-0.007
 scoring-0.007
Token holds
Token ID6622
Feature activation+1.19e-03

Pos logit contributions
Yeah+0.016
 Whe+0.015
 Tim+0.014
 throwing+0.014
 kicking+0.014
Neg logit contributions
ace-0.012
igh-0.011
 Him-0.011
ery-0.010
 story-0.010
Token Anna
Token ID11735
Feature activation+2.58e-02

Pos logit contributions
ace+0.002
igh+0.002
 Him+0.002
aret+0.002
ery+0.002
Neg logit contributions
Yeah-0.002
 kicking-0.002
 throwing-0.002
 Whe-0.002
Really-0.002