TOP ACTIVATIONS
MAX = 0.081

a fun ride at the carn ival . Twe ety thought
She loved to eat av oc ados . One day ,
shape . C urious , Amelia tried to
She loved to eat av oc ados because they were y
who liked to collect or nam ents . Everywhere she went
and they walked through the carn ival gates , while Max
went she searched for or nam ents , and the more
, Lily went to a carn ival with her mom my
, Lily went to a carn ival with her family .
So Jack and St itch started to play together
bitter and made her face scr unch up .
ongo loved to eat av oc ados . One day ,
and play with your or nam ents . Maybe you can
Max loved being at the carn ival so much that he
ummy cotton candy and play carn ival games .
lived in a warm and c udd ly home . Every
has lettuce and tomatoes and cuc umbers . And it has
John chose some carrots and cuc umbers to take home .
, Max , to the carn ival . Everywhere they looked
One day , Tommy and St itch went to the park

MIN ACTIVATIONS
MIN = -0.086

." She gives them a new tap . The tap is
and said , " Let me help you . I will
she gave Teddy a brand new sc ooter . He was
mess and gave her a new cup . Sara thanked her
he gave the boy the biggest hug . Together
Yes , but be very careful .
taught her how to use the f auc et . Now
can help ." He took out a fishing rod and swoop
said , " Please let me march , it is so
He would still take his long stroll s through the park
the bear showed everyone his new boots . Everyone was so
park . Timothy gave a final loud blow on the whistle
's mom said , " This is a magic f auc
If we use this oil , we can make
to his work and removes the tube . Tim and Mia
" Mom my , let me support you so you don
understand . We will share the tube . We will be
ran off with her shiny new pipe . <|endoftext|> Once upon
's mom gave her a new toy . It was a
saf ari . Please let me go , mum ."

INTERVAL 0.040 - 0.081
CONTAINS 0.238%

beautiful toy . Lily felt en vious and wanted the toy
replied , " It 's c heddar cheese ."
a big chamber . Inside the chamber there were many things
invite all his friends to his palace for a big party
. <|endoftext|> L ila was a little girl who loved to

INTERVAL -0.002 - 0.040
CONTAINS 57.523%

was bored and restless . She f idget ed and wh
together in the park , running and laughing .
space . <|endoftext|> Once there were two kids , Sam and
some pe aches . They were juicy and sweet . They
and milk . You will feel safe and warm ."

INTERVAL -0.044 - -0.002
CONTAINS 42.084%

. She smiled and waved her arms around the classroom .
wanted some seeds in return . Twe ety agreed and the
down . When he got to the beach , he saw
you learn to be polite . â Mo
. They decided it was a good idea to

INTERVAL -0.086 - -0.044
CONTAINS 0.156%

, what shall you do now ?" one of them asked
" Let 's take this ash and build something with
set , with a train , tracks , and stations .
. He gave Bob a big hug and said " Well
Her mom showed Julie how to use the comb
Token a
Token ID257
Feature activation+5.49e-03

Pos logit contributions
nob+0.015
 dial+0.014
 peek+0.014
 Looking+0.013
 peaked+0.013
Neg logit contributions
rier-0.010
working-0.010
istered-0.009
 bored-0.008
nam-0.008
Token fun
Token ID1257
Feature activation-2.41e-02

Pos logit contributions
working+0.007
rier+0.007
istered+0.007
 kicker+0.006
 runner+0.006
Neg logit contributions
nob-0.009
ad-0.009
 dial-0.009
ered-0.008
 Looking-0.008
Token ride
Token ID6594
Feature activation+1.69e-02

Pos logit contributions
 Looking+0.045
ran+0.045
nob+0.045
 dial+0.044
ad+0.044
Neg logit contributions
working-0.027
 runner-0.023
 guys-0.021
 kicker-0.021
 rainy-0.019
Token at
Token ID379
Feature activation+1.12e-02

Pos logit contributions
istered+0.040
rier+0.040
ishy+0.037
working+0.036
ivery+0.036
Neg logit contributions
 peek-0.013
nob-0.012
 called-0.011
 dial-0.011
ad-0.011
Token the
Token ID262
Feature activation+1.57e-02

Pos logit contributions
rier+0.023
istered+0.023
working+0.022
ishy+0.021
attered+0.020
Neg logit contributions
 peek-0.012
 dial-0.011
nob-0.011
ad-0.010
 turned-0.010
Token carn
Token ID18466
Feature activation+8.14e-02

Pos logit contributions
rier+0.031
istered+0.031
working+0.030
ishy+0.028
ivery+0.027
Neg logit contributions
 peek-0.018
 dial-0.018
 turned-0.016
nob-0.016
ad-0.015
Tokenival
Token ID2473
Feature activation+2.71e-02

Pos logit contributions
rier+0.125
working+0.119
istered+0.117
ishy+0.106
 goals+0.101
Neg logit contributions
 peek-0.130
nob-0.122
 dial-0.119
ad-0.114
 Looking-0.113
Token.
Token ID13
Feature activation-1.04e-02

Pos logit contributions
istered+0.063
rier+0.062
ishy+0.060
working+0.058
ivery+0.058
Neg logit contributions
 peek-0.024
 dial-0.022
nob-0.021
 turned-0.019
 called-0.019
Token Twe
Token ID24205
Feature activation+1.98e-02

Pos logit contributions
nob+0.012
 dial+0.012
 peek+0.011
ad+0.011
 fore+0.010
Neg logit contributions
rier-0.019
working-0.019
istered-0.018
 bored-0.017
ishy-0.017
Tokenety
Token ID2963
Feature activation+5.44e-03

Pos logit contributions
istered+0.026
rier+0.026
working+0.026
ishy+0.024
attered+0.022
Neg logit contributions
 dial-0.034
 peek-0.033
nob-0.032
 turned-0.031
 Looking-0.031
Token thought
Token ID1807
Feature activation+1.46e-02

Pos logit contributions
working+0.011
rier+0.011
istered+0.011
ishy+0.010
 goals+0.010
Neg logit contributions
 dial-0.005
 peek-0.005
nob-0.005
ad-0.005
 Looking-0.004
Token She
Token ID1375
Feature activation-1.38e-02

Pos logit contributions
rier+0.023
working+0.023
istered+0.023
ishy+0.020
 goals+0.020
Neg logit contributions
 peek-0.019
 dial-0.019
nob-0.018
 turned-0.018
 Looking-0.018
Token loved
Token ID6151
Feature activation+5.05e-03

Pos logit contributions
 dial+0.021
nob+0.021
 peek+0.021
ad+0.019
 Looking+0.019
Neg logit contributions
working-0.020
istered-0.019
rier-0.019
ishy-0.017
 goals-0.017
Token to
Token ID284
Feature activation+8.61e-03

Pos logit contributions
rier+0.011
istered+0.011
working+0.010
ishy+0.010
 goals+0.009
Neg logit contributions
 dial-0.005
 peek-0.005
nob-0.004
 turned-0.004
ad-0.004
Token eat
Token ID4483
Feature activation+2.00e-02

Pos logit contributions
working+0.015
istered+0.014
rier+0.014
ishy+0.013
 goals+0.013
Neg logit contributions
 dial-0.011
nob-0.010
 peek-0.010
 Looking-0.010
 Turning-0.010
Token av
Token ID1196
Feature activation+4.63e-02

Pos logit contributions
rier+0.030
istered+0.030
working+0.029
 kicker+0.026
ishy+0.025
Neg logit contributions
 peek-0.031
 dial-0.031
 turned-0.029
nob-0.029
ad-0.028
Tokenoc
Token ID420
Feature activation+7.78e-02

Pos logit contributions
rier+0.086
istered+0.083
working+0.080
ishy+0.073
 sweaty+0.072
Neg logit contributions
 dial-0.055
 peek-0.055
nob-0.054
ad-0.051
 turned-0.048
Tokenados
Token ID22484
Feature activation+1.51e-02

Pos logit contributions
istered+0.089
rier+0.078
working+0.075
ishy+0.072
ivery+0.071
Neg logit contributions
ad-0.152
 dial-0.147
nob-0.144
 peek-0.139
p-0.136
Token.
Token ID13
Feature activation+9.02e-03

Pos logit contributions
istered+0.029
rier+0.029
working+0.027
ishy+0.026
 goals+0.025
Neg logit contributions
 peek-0.017
 dial-0.017
nob-0.016
 turned-0.015
ad-0.015
Token One
Token ID1881
Feature activation+1.46e-02

Pos logit contributions
rier+0.016
working+0.016
istered+0.016
ishy+0.014
 goals+0.014
Neg logit contributions
 dial-0.011
 peek-0.011
nob-0.011
 turned-0.010
ad-0.010
Token day
Token ID1110
Feature activation+1.54e-03

Pos logit contributions
rier+0.024
istered+0.023
working+0.022
 goals+0.020
ishy+0.020
Neg logit contributions
 peek-0.021
 dial-0.021
nob-0.020
 turned-0.020
ad-0.019
Token,
Token ID11
Feature activation+6.96e-03

Pos logit contributions
rier+0.003
istered+0.003
working+0.003
ishy+0.003
 goals+0.003
Neg logit contributions
 peek-0.002
 dial-0.002
nob-0.001
 turned-0.001
 Looking-0.001
Token shape
Token ID5485
Feature activation-8.52e-03

Pos logit contributions
 dial+0.022
nob+0.022
 peek+0.021
 Looking+0.020
ad+0.020
Neg logit contributions
rier-0.026
working-0.026
istered-0.024
ishy-0.023
 goals-0.023
Token.
Token ID13
Feature activation+2.79e-02

Pos logit contributions
 dial+0.010
 peek+0.010
nob+0.010
 Looking+0.009
 turned+0.009
Neg logit contributions
rier-0.016
working-0.015
istered-0.015
ishy-0.014
 goals-0.014
Token
Token ID220
Feature activation+4.46e-03

Pos logit contributions
rier+0.045
working+0.043
istered+0.042
 goals+0.039
nam+0.037
Neg logit contributions
 dial-0.038
 peek-0.038
nob-0.037
ad-0.036
 turned-0.035
Token
Token ID198
Feature activation+1.87e-02

Pos logit contributions
rier+0.011
istered+0.010
working+0.010
 goals+0.010
ishy+0.010
Neg logit contributions
 dial-0.003
 peek-0.003
nob-0.003
 turned-0.002
ad-0.002
Token
Token ID198
Feature activation+2.07e-02

Pos logit contributions
rier+0.036
working+0.036
 goals+0.033
istered+0.033
 kicker+0.032
Neg logit contributions
 dial-0.017
nob-0.016
 turned-0.016
 peek-0.015
ad-0.015
TokenC
Token ID34
Feature activation+7.76e-02

Pos logit contributions
rier+0.036
working+0.036
istered+0.034
 goals+0.032
 kicker+0.031
Neg logit contributions
 dial-0.025
 peek-0.025
nob-0.025
 turned-0.024
ad-0.023
Tokenurious
Token ID16421
Feature activation+1.38e-02

Pos logit contributions
rier+0.109
istered+0.105
working+0.102
ishy+0.091
 sweaty+0.089
Neg logit contributions
 peek-0.130
 dial-0.129
nob-0.125
ad-0.121
 turned-0.119
Token,
Token ID11
Feature activation+1.19e-02

Pos logit contributions
rier+0.027
istered+0.027
working+0.027
ishy+0.025
 goals+0.024
Neg logit contributions
 peek-0.015
 dial-0.015
nob-0.014
 turned-0.013
ad-0.013
Token Amelia
Token ID49769
Feature activation-2.00e-04

Pos logit contributions
rier+0.018
working+0.018
istered+0.018
ishy+0.016
 goals+0.016
Neg logit contributions
 dial-0.018
 peek-0.018
nob-0.017
 turned-0.016
ad-0.016
Token tried
Token ID3088
Feature activation-2.18e-02

Pos logit contributions
nob+0.000
 dial+0.000
 Looking+0.000
ad+0.000
 Turning+0.000
Neg logit contributions
working-0.000
istered-0.000
rier-0.000
ishy-0.000
 goals-0.000
Token to
Token ID284
Feature activation-1.99e-02

Pos logit contributions
 dial+0.028
nob+0.028
izer+0.027
ad+0.026
 Looking+0.026
Neg logit contributions
working-0.034
 bored-0.031
 goals-0.031
rier-0.030
istered-0.029
Token She
Token ID1375
Feature activation-7.12e-03

Pos logit contributions
rier+0.020
working+0.019
istered+0.019
ishy+0.017
 goals+0.017
Neg logit contributions
 peek-0.016
 dial-0.016
nob-0.015
 turned-0.015
 Looking-0.015
Token loved
Token ID6151
Feature activation+7.25e-03

Pos logit contributions
 dial+0.011
nob+0.011
 peek+0.011
ad+0.010
 Looking+0.010
Neg logit contributions
working-0.010
istered-0.010
rier-0.010
ishy-0.009
 goals-0.009
Token to
Token ID284
Feature activation+8.24e-03

Pos logit contributions
rier+0.016
istered+0.015
working+0.015
ishy+0.014
 goals+0.014
Neg logit contributions
 dial-0.007
 peek-0.006
nob-0.006
 turned-0.006
ad-0.005
Token eat
Token ID4483
Feature activation+1.95e-02

Pos logit contributions
working+0.014
istered+0.012
rier+0.012
ishy+0.012
 goals+0.012
Neg logit contributions
 dial-0.011
nob-0.011
 peek-0.010
 Looking-0.010
 Turning-0.010
Token av
Token ID1196
Feature activation+4.44e-02

Pos logit contributions
rier+0.030
istered+0.029
working+0.029
 kicker+0.025
ivery+0.025
Neg logit contributions
 peek-0.030
 dial-0.030
 turned-0.028
nob-0.028
ad-0.027
Tokenoc
Token ID420
Feature activation+7.61e-02

Pos logit contributions
rier+0.083
istered+0.080
working+0.076
ishy+0.070
 sweaty+0.069
Neg logit contributions
 dial-0.053
 peek-0.053
nob-0.052
ad-0.049
 turned-0.047
Tokenados
Token ID22484
Feature activation+1.73e-02

Pos logit contributions
istered+0.088
rier+0.077
working+0.075
ishy+0.071
ivery+0.070
Neg logit contributions
ad-0.148
 dial-0.143
nob-0.140
 peek-0.135
p-0.131
Token because
Token ID780
Feature activation+1.51e-02

Pos logit contributions
istered+0.034
rier+0.034
working+0.032
ishy+0.030
ivery+0.029
Neg logit contributions
 peek-0.019
 dial-0.019
nob-0.018
 turned-0.017
ad-0.017
Token they
Token ID484
Feature activation+3.26e-02

Pos logit contributions
istered+0.033
ishy+0.028
rier+0.028
ivery+0.028
 goals+0.027
Neg logit contributions
 turned-0.016
 opened-0.015
 dial-0.015
 Inside-0.014
 called-0.014
Token were
Token ID547
Feature activation+2.58e-02

Pos logit contributions
rier+0.067
istered+0.063
 goals+0.057
working+0.057
ishy+0.057
Neg logit contributions
 peek-0.039
 turned-0.039
 dial-0.038
 opened-0.037
ad-0.034
Token y
Token ID331
Feature activation+4.72e-02

Pos logit contributions
istered+0.045
rier+0.043
working+0.042
ishy+0.041
ivery+0.041
Neg logit contributions
 dial-0.034
 peek-0.033
 turned-0.032
 opened-0.032
 called-0.032
Token who
Token ID508
Feature activation+5.35e-03

Pos logit contributions
 dial+0.020
nob+0.019
 peek+0.018
 Looking+0.018
ad+0.016
Neg logit contributions
working-0.054
istered-0.052
rier-0.051
ishy-0.048
 bored-0.048
Token liked
Token ID8288
Feature activation+1.44e-02

Pos logit contributions
rier+0.009
istered+0.008
working+0.008
 goals+0.007
ishy+0.007
Neg logit contributions
 peek-0.008
 dial-0.008
nob-0.008
 turned-0.008
 opened-0.007
Token to
Token ID284
Feature activation+6.67e-03

Pos logit contributions
rier+0.034
istered+0.033
working+0.032
ishy+0.031
 goals+0.030
Neg logit contributions
 peek-0.011
 dial-0.010
nob-0.009
 turned-0.009
ad-0.008
Token collect
Token ID2824
Feature activation+1.56e-03

Pos logit contributions
working+0.011
istered+0.010
rier+0.010
ishy+0.009
 sweaty+0.009
Neg logit contributions
 dial-0.009
nob-0.008
 Looking-0.008
ran-0.008
 fore-0.008
Token or
Token ID393
Feature activation+2.80e-02

Pos logit contributions
rier+0.002
working+0.002
istered+0.002
ishy+0.002
 goals+0.002
Neg logit contributions
 dial-0.003
nob-0.003
 peek-0.003
 Looking-0.002
 turned-0.002
Tokennam
Token ID7402
Feature activation+7.61e-02

Pos logit contributions
rier+0.021
istered+0.021
working+0.018
ishy+0.016
ivery+0.014
Neg logit contributions
 peek-0.069
 dial-0.067
 turned-0.064
 opened-0.063
nob-0.062
Tokenents
Token ID658
Feature activation+5.43e-03

Pos logit contributions
rier+0.129
working+0.127
istered+0.125
ishy+0.116
obb+0.113
Neg logit contributions
 peek-0.099
 dial-0.097
ad-0.094
nob-0.090
 opened-0.088
Token.
Token ID13
Feature activation+1.18e-02

Pos logit contributions
istered+0.012
rier+0.011
working+0.011
ishy+0.011
 goals+0.010
Neg logit contributions
 peek-0.005
 dial-0.005
nob-0.005
 turned-0.004
ad-0.004
Token Everywhere
Token ID48201
Feature activation+1.82e-02

Pos logit contributions
rier+0.016
working+0.016
istered+0.016
 goals+0.014
ishy+0.014
Neg logit contributions
 dial-0.019
 peek-0.019
nob-0.018
ad-0.017
 turned-0.017
Token she
Token ID673
Feature activation+3.76e-05

Pos logit contributions
rier+0.033
istered+0.032
ivery+0.028
working+0.027
ishy+0.027
Neg logit contributions
 peek-0.027
 turned-0.027
 opened-0.027
 dial-0.026
 called-0.025
Token went
Token ID1816
Feature activation+2.17e-02

Pos logit contributions
working+0.000
rier+0.000
istered+0.000
ishy+0.000
attered+0.000
Neg logit contributions
 dial-0.000
nob-0.000
 peek-0.000
ad-0.000
 Looking-0.000
Token and
Token ID290
Feature activation+1.89e-03

Pos logit contributions
 dial+0.012
 peek+0.012
nob+0.011
 turned+0.010
ad+0.010
Neg logit contributions
rier-0.027
working-0.026
istered-0.026
ishy-0.024
 goals-0.024
Token they
Token ID484
Feature activation+1.25e-02

Pos logit contributions
working+0.004
rier+0.004
istered+0.004
nam+0.003
 bored+0.003
Neg logit contributions
nob-0.002
 dial-0.002
 peek-0.002
ad-0.002
 Looking-0.002
Token walked
Token ID6807
Feature activation+9.18e-03

Pos logit contributions
rier+0.026
istered+0.025
working+0.024
ishy+0.023
 goals+0.022
Neg logit contributions
 peek-0.014
 dial-0.014
 turned-0.013
nob-0.012
 opened-0.012
Token through
Token ID832
Feature activation+4.67e-03

Pos logit contributions
rier+0.016
working+0.016
istered+0.016
 bored+0.014
 goals+0.014
Neg logit contributions
 dial-0.011
nob-0.011
 peek-0.011
ad-0.010
 Looking-0.010
Token the
Token ID262
Feature activation+3.95e-04

Pos logit contributions
rier+0.010
istered+0.010
working+0.010
ishy+0.009
ivery+0.009
Neg logit contributions
 dial-0.005
 peek-0.005
nob-0.004
 turned-0.004
ad-0.004
Token carn
Token ID18466
Feature activation+7.56e-02

Pos logit contributions
working+0.001
istered+0.001
rier+0.001
 goals+0.001
 bored+0.001
Neg logit contributions
nob-0.001
 dial-0.001
 peek-0.001
 pat-0.001
p-0.001
Tokenival
Token ID2473
Feature activation+2.68e-02

Pos logit contributions
rier+0.112
working+0.108
istered+0.105
ishy+0.096
 goals+0.090
Neg logit contributions
 peek-0.122
 dial-0.117
nob-0.116
 turned-0.110
 Looking-0.109
Token gates
Token ID17435
Feature activation+1.15e-02

Pos logit contributions
istered+0.058
rier+0.057
ishy+0.054
working+0.054
ivery+0.052
Neg logit contributions
 peek-0.028
 dial-0.027
 turned-0.023
nob-0.023
 opened-0.022
Token,
Token ID11
Feature activation-2.13e-02

Pos logit contributions
rier+0.023
istered+0.022
working+0.022
ishy+0.021
 goals+0.020
Neg logit contributions
 peek-0.012
 dial-0.012
nob-0.012
 turned-0.011
ad-0.011
Token while
Token ID981
Feature activation+8.51e-03

Pos logit contributions
nob+0.024
 dial+0.023
ad+0.022
 peek+0.022
 Looking+0.021
Neg logit contributions
rier-0.038
working-0.038
istered-0.037
 bored-0.035
 sweaty-0.035
Token Max
Token ID5436
Feature activation+1.21e-02

Pos logit contributions
rier+0.015
ishy+0.014
istered+0.014
working+0.013
attered+0.013
Neg logit contributions
 dial-0.012
 peek-0.012
 turned-0.011
 opened-0.011
 called-0.011
Token went
Token ID1816
Feature activation+2.17e-02

Pos logit contributions
working+0.000
rier+0.000
istered+0.000
ishy+0.000
attered+0.000
Neg logit contributions
 dial-0.000
nob-0.000
 peek-0.000
ad-0.000
 Looking-0.000
Token she
Token ID673
Feature activation+6.69e-03

Pos logit contributions
rier+0.041
istered+0.041
working+0.039
ishy+0.037
 goals+0.036
Neg logit contributions
 peek-0.026
 dial-0.025
nob-0.024
 turned-0.023
ad-0.023
Token searched
Token ID16499
Feature activation+1.64e-02

Pos logit contributions
rier+0.014
istered+0.013
working+0.013
ishy+0.012
 goals+0.012
Neg logit contributions
 peek-0.007
 dial-0.007
nob-0.006
 turned-0.006
ad-0.006
Token for
Token ID329
Feature activation+2.50e-02

Pos logit contributions
rier+0.031
istered+0.030
working+0.030
ishy+0.027
 goals+0.026
Neg logit contributions
 peek-0.019
 dial-0.019
nob-0.018
 turned-0.018
ad-0.017
Token or
Token ID393
Feature activation+3.53e-02

Pos logit contributions
rier+0.037
working+0.036
istered+0.036
ishy+0.032
 goals+0.031
Neg logit contributions
 dial-0.039
 peek-0.039
nob-0.038
 turned-0.036
ad-0.035
Tokennam
Token ID7402
Feature activation+7.54e-02

Pos logit contributions
rier+0.018
istered+0.016
working+0.015
ishy+0.011
 goals+0.009
Neg logit contributions
 peek-0.091
 dial-0.091
nob-0.088
 turned-0.087
 opened-0.085
Tokenents
Token ID658
Feature activation+1.58e-02

Pos logit contributions
rier+0.131
working+0.129
istered+0.126
ishy+0.118
obb+0.115
Neg logit contributions
 peek-0.095
 dial-0.092
ad-0.089
nob-0.087
 opened-0.085
Token,
Token ID11
Feature activation+9.85e-03

Pos logit contributions
istered+0.035
rier+0.035
working+0.033
ishy+0.032
ivery+0.031
Neg logit contributions
 peek-0.013
nob-0.012
 dial-0.012
 turned-0.012
 opened-0.011
Token and
Token ID290
Feature activation+1.06e-02

Pos logit contributions
rier+0.017
istered+0.017
working+0.016
ishy+0.015
 goals+0.014
Neg logit contributions
 peek-0.013
 dial-0.013
nob-0.013
 turned-0.012
ad-0.012
Token the
Token ID262
Feature activation+3.19e-02

Pos logit contributions
istered+0.018
rier+0.018
ishy+0.016
working+0.015
ivery+0.015
Neg logit contributions
 peek-0.016
 dial-0.016
 turned-0.015
 opened-0.015
nob-0.015
Token more
Token ID517
Feature activation+2.74e-02

Pos logit contributions
istered+0.055
working+0.052
rier+0.049
ishy+0.049
attered+0.047
Neg logit contributions
 peek-0.045
 dial-0.045
 turned-0.041
nob-0.041
 opened-0.040
Token,
Token ID11
Feature activation+1.18e-02

Pos logit contributions
rier+0.015
istered+0.014
working+0.014
ishy+0.013
 goals+0.013
Neg logit contributions
 peek-0.007
 dial-0.006
 turned-0.006
nob-0.006
 opened-0.006
Token Lily
Token ID20037
Feature activation+4.09e-03

Pos logit contributions
rier+0.023
istered+0.022
working+0.021
 goals+0.020
ishy+0.019
Neg logit contributions
 peek-0.016
 dial-0.015
 turned-0.015
 opened-0.014
 called-0.013
Token went
Token ID1816
Feature activation-6.74e-03

Pos logit contributions
rier+0.008
working+0.008
istered+0.008
ishy+0.007
 goals+0.007
Neg logit contributions
 dial-0.004
 peek-0.004
nob-0.004
 turned-0.004
ad-0.004
Token to
Token ID284
Feature activation+1.35e-03

Pos logit contributions
ad+0.010
 dial+0.010
 Looking+0.009
nob+0.009
ran+0.009
Neg logit contributions
working-0.011
 bored-0.009
rier-0.008
istered-0.008
 tired-0.008
Token a
Token ID257
Feature activation+3.42e-02

Pos logit contributions
working+0.002
nam+0.002
 bored+0.002
 kicker+0.001
 sweaty+0.001
Neg logit contributions
nob-0.002
ran-0.002
ad-0.002
 fore-0.002
 Looking-0.002
Token carn
Token ID18466
Feature activation+7.51e-02

Pos logit contributions
rier+0.052
working+0.052
istered+0.051
ishy+0.045
 goals+0.045
Neg logit contributions
 dial-0.051
 peek-0.050
nob-0.049
ad-0.046
 turned-0.046
Tokenival
Token ID2473
Feature activation+5.49e-03

Pos logit contributions
rier+0.098
working+0.095
istered+0.094
ishy+0.082
 goals+0.080
Neg logit contributions
 peek-0.130
 dial-0.129
nob-0.126
 turned-0.120
ad-0.119
Token with
Token ID351
Feature activation+6.07e-03

Pos logit contributions
rier+0.012
working+0.012
istered+0.012
 goals+0.011
ishy+0.011
Neg logit contributions
 dial-0.005
 peek-0.004
nob-0.004
 turned-0.004
ad-0.004
Token her
Token ID607
Feature activation+1.08e-02

Pos logit contributions
rier+0.011
istered+0.011
working+0.011
ishy+0.010
ivery+0.010
Neg logit contributions
 peek-0.008
 dial-0.008
 turned-0.008
ad-0.007
nob-0.007
Token mom
Token ID1995
Feature activation-2.90e-02

Pos logit contributions
rier+0.016
working+0.015
istered+0.015
ishy+0.014
 goals+0.013
Neg logit contributions
 dial-0.017
 peek-0.017
nob-0.016
 turned-0.016
ad-0.016
Tokenmy
Token ID1820
Feature activation-1.82e-02

Pos logit contributions
nob+0.038
 Looking+0.037
 peek+0.036
 dial+0.036
AAAA+0.035
Neg logit contributions
working-0.049
istered-0.042
rier-0.042
 bored-0.042
ishy-0.040
Token,
Token ID11
Feature activation+4.69e-03

Pos logit contributions
 dial+0.001
 peek+0.001
nob+0.000
 turned+0.000
ad+0.000
Neg logit contributions
rier-0.001
istered-0.001
working-0.001
ishy-0.001
 goals-0.001
Token Lily
Token ID20037
Feature activation-2.11e-03

Pos logit contributions
rier+0.008
istered+0.008
working+0.007
ishy+0.007
 goals+0.007
Neg logit contributions
 peek-0.007
 dial-0.007
nob-0.006
 turned-0.006
 opened-0.006
Token went
Token ID1816
Feature activation-8.15e-03

Pos logit contributions
 peek+0.002
 dial+0.002
nob+0.002
 turned+0.002
 opened+0.002
Neg logit contributions
rier-0.004
istered-0.004
working-0.004
ishy-0.004
 goals-0.004
Token to
Token ID284
Feature activation+1.09e-03

Pos logit contributions
 dial+0.012
ad+0.012
 Looking+0.012
nob+0.012
AAAA+0.011
Neg logit contributions
working-0.012
 bored-0.011
rier-0.010
 forward-0.010
 tired-0.010
Token a
Token ID257
Feature activation+2.70e-02

Pos logit contributions
working+0.001
 bored+0.001
nam+0.001
 kicker+0.001
 goals+0.001
Neg logit contributions
nob-0.002
 fore-0.002
ad-0.002
ran-0.002
 dial-0.002
Token carn
Token ID18466
Feature activation+7.44e-02

Pos logit contributions
rier+0.040
working+0.040
istered+0.039
ishy+0.035
 goals+0.034
Neg logit contributions
 dial-0.041
nob-0.040
 peek-0.040
ad-0.038
 turned-0.037
Tokenival
Token ID2473
Feature activation+3.00e-03

Pos logit contributions
rier+0.095
working+0.092
istered+0.091
ishy+0.079
 goals+0.078
Neg logit contributions
 peek-0.131
 dial-0.130
nob-0.127
 turned-0.121
ad-0.120
Token with
Token ID351
Feature activation+3.63e-03

Pos logit contributions
rier+0.006
working+0.006
istered+0.006
ishy+0.006
 goals+0.006
Neg logit contributions
 dial-0.003
 peek-0.003
nob-0.002
 turned-0.002
ad-0.002
Token her
Token ID607
Feature activation+6.70e-03

Pos logit contributions
rier+0.007
istered+0.007
working+0.007
ishy+0.007
ivery+0.006
Neg logit contributions
 peek-0.005
 dial-0.005
ad-0.004
 turned-0.004
 opened-0.004
Token family
Token ID1641
Feature activation-1.29e-02

Pos logit contributions
rier+0.009
working+0.009
istered+0.009
ishy+0.008
 goals+0.008
Neg logit contributions
 dial-0.011
 peek-0.011
nob-0.011
 turned-0.010
ad-0.010
Token.
Token ID13
Feature activation+2.48e-03

Pos logit contributions
 dial+0.016
nob+0.016
 peek+0.015
 Looking+0.014
 turned+0.014
Neg logit contributions
working-0.023
rier-0.023
istered-0.022
 goals-0.020
ishy-0.020
Token
Token ID198
Feature activation-1.10e-02

Pos logit contributions
nob+0.022
 dial+0.020
 peek+0.019
ad+0.018
 question+0.017
Neg logit contributions
rier-0.029
istered-0.026
working-0.026
 goals-0.025
 bored-0.025
Token
Token ID198
Feature activation-5.02e-03

Pos logit contributions
nob+0.013
 dial+0.013
 peek+0.012
 fore+0.011
 turned+0.011
Neg logit contributions
rier-0.018
working-0.018
istered-0.018
 goals-0.017
opy-0.016
TokenSo
Token ID2396
Feature activation-5.91e-03

Pos logit contributions
 dial+0.006
 peek+0.006
nob+0.006
 turned+0.006
ad+0.005
Neg logit contributions
rier-0.009
istered-0.009
working-0.009
 goals-0.008
ishy-0.008
Token Jack
Token ID3619
Feature activation-1.33e-02

Pos logit contributions
 dial+0.007
 peek+0.007
nob+0.007
 turned+0.007
ad+0.007
Neg logit contributions
rier-0.011
istered-0.011
working-0.010
ishy-0.009
 goals-0.009
Token and
Token ID290
Feature activation+1.33e-02

Pos logit contributions
nob+0.013
 dial+0.013
 peek+0.013
 Looking+0.012
ad+0.012
Neg logit contributions
working-0.026
rier-0.025
istered-0.024
ishy-0.024
 goals-0.023
Token St
Token ID520
Feature activation+7.36e-02

Pos logit contributions
working+0.023
rier+0.023
istered+0.022
ishy+0.020
 goals+0.020
Neg logit contributions
nob-0.017
 dial-0.017
 peek-0.017
ad-0.015
 turned-0.015
Tokenitch
Token ID2007
Feature activation+2.02e-03

Pos logit contributions
rier+0.090
working+0.081
istered+0.078
nam+0.071
 sweaty+0.069
Neg logit contributions
 dial-0.137
ad-0.136
 peek-0.135
 turned-0.131
nob-0.129
Token started
Token ID2067
Feature activation-2.75e-02

Pos logit contributions
rier+0.004
istered+0.004
working+0.004
ishy+0.004
 goals+0.003
Neg logit contributions
 dial-0.002
 peek-0.002
nob-0.002
 turned-0.002
ad-0.002
Token to
Token ID284
Feature activation-1.29e-02

Pos logit contributions
nob+0.039
 dial+0.037
 peek+0.036
ad+0.036
 Looking+0.035
Neg logit contributions
working-0.043
istered-0.039
 bored-0.038
rier-0.038
 sweaty-0.037
Token play
Token ID711
Feature activation-1.96e-03

Pos logit contributions
nob+0.017
 dial+0.017
 peek+0.016
 Looking+0.016
ad+0.016
Neg logit contributions
working-0.021
istered-0.019
rier-0.019
ishy-0.018
 goals-0.018
Token together
Token ID1978
Feature activation-5.14e-04

Pos logit contributions
 peek+0.002
 dial+0.002
nob+0.002
 turned+0.002
ad+0.002
Neg logit contributions
rier-0.004
istered-0.004
working-0.004
ishy-0.004
attered-0.003
Token bitter
Token ID12922
Feature activation+1.79e-02

Pos logit contributions
rier+0.043
istered+0.040
working+0.039
ivery+0.037
onel+0.036
Neg logit contributions
 turned-0.031
 peek-0.031
 opened-0.029
 dial-0.029
 called-0.028
Token and
Token ID290
Feature activation+3.37e-02

Pos logit contributions
istered+0.041
working+0.039
rier+0.039
nam+0.038
ivery+0.037
Neg logit contributions
 peek-0.013
 turned-0.013
 dial-0.013
nob-0.012
 called-0.011
Token made
Token ID925
Feature activation+3.14e-02

Pos logit contributions
rier+0.063
istered+0.058
ivery+0.057
working+0.057
 runner+0.054
Neg logit contributions
 turned-0.045
 peek-0.043
 opened-0.042
 called-0.040
 dial-0.040
Token her
Token ID607
Feature activation+2.46e-02

Pos logit contributions
working+0.058
istered+0.057
rier+0.056
ishy+0.052
ivery+0.051
Neg logit contributions
 peek-0.038
 dial-0.038
 turned-0.036
ad-0.036
nob-0.034
Token face
Token ID1986
Feature activation+2.22e-02

Pos logit contributions
working+0.043
rier+0.042
istered+0.040
ivery+0.037
attered+0.036
Neg logit contributions
 peek-0.034
 dial-0.031
 turned-0.030
 pat-0.030
 call-0.029
Token scr
Token ID6040
Feature activation+7.34e-02

Pos logit contributions
working+0.037
rier+0.036
istered+0.035
 kicker+0.034
 runner+0.033
Neg logit contributions
 peek-0.031
 turned-0.030
 dial-0.030
nob-0.028
 opened-0.027
Tokenunch
Token ID3316
Feature activation+2.90e-02

Pos logit contributions
working+0.114
rier+0.107
nam+0.102
istered+0.098
 happiest+0.097
Neg logit contributions
ad-0.107
 peek-0.100
p-0.098
nob-0.092
 turned-0.091
Token up
Token ID510
Feature activation+1.01e-02

Pos logit contributions
istered+0.064
working+0.062
 Majesty+0.061
nam+0.061
 kicker+0.060
Neg logit contributions
p-0.024
 turned-0.024
nob-0.022
 peek-0.020
ad-0.019
Token.
Token ID13
Feature activation+7.27e-03

Pos logit contributions
working+0.021
istered+0.021
rier+0.021
 kicker+0.020
ivery+0.019
Neg logit contributions
 peek-0.009
 turned-0.008
 dial-0.008
nob-0.008
 opened-0.008
Token
Token ID198
Feature activation-1.09e-03

Pos logit contributions
rier+0.016
working+0.016
istered+0.016
ishy+0.015
 goals+0.015
Neg logit contributions
 dial-0.006
 peek-0.006
nob-0.005
 turned-0.005
ad-0.005
Token
Token ID198
Feature activation+4.63e-03

Pos logit contributions
 dial+0.001
nob+0.001
 peek+0.001
 turned+0.001
 opened+0.001
Neg logit contributions
working-0.002
istered-0.002
rier-0.002
 goals-0.002
 kicker-0.002
Tokenongo
Token ID25162
Feature activation+9.08e-03

Pos logit contributions
rier+0.023
working+0.022
istered+0.022
ishy+0.019
 goals+0.018
Neg logit contributions
 dial-0.038
 peek-0.038
nob-0.037
 turned-0.036
ad-0.035
Token loved
Token ID6151
Feature activation+5.68e-03

Pos logit contributions
working+0.014
rier+0.014
istered+0.013
ishy+0.012
 goals+0.012
Neg logit contributions
 dial-0.014
 peek-0.013
nob-0.013
ad-0.012
 turned-0.012
Token to
Token ID284
Feature activation+1.11e-02

Pos logit contributions
working+0.011
rier+0.009
 bored+0.009
 goals+0.009
nam+0.009
Neg logit contributions
nob-0.007
 dial-0.006
 peek-0.006
 Looking-0.006
 Turning-0.006
Token eat
Token ID4483
Feature activation+2.02e-02

Pos logit contributions
working+0.018
rier+0.015
istered+0.015
 goals+0.015
ishy+0.015
Neg logit contributions
 Looking-0.015
 dial-0.015
nob-0.014
 fore-0.014
 Turning-0.014
Token av
Token ID1196
Feature activation+4.32e-02

Pos logit contributions
rier+0.027
working+0.026
istered+0.025
ishy+0.022
 goals+0.022
Neg logit contributions
 dial-0.035
 peek-0.034
nob-0.034
 turned-0.032
ad-0.032
Tokenoc
Token ID420
Feature activation+7.28e-02

Pos logit contributions
rier+0.082
istered+0.077
working+0.075
ishy+0.069
 sweaty+0.067
Neg logit contributions
 peek-0.051
 dial-0.051
nob-0.050
ad-0.048
 turned-0.045
Tokenados
Token ID22484
Feature activation+2.03e-02

Pos logit contributions
istered+0.077
rier+0.069
working+0.068
ishy+0.062
 sweaty+0.060
Neg logit contributions
ad-0.148
 dial-0.143
nob-0.141
 peek-0.139
p-0.134
Token.
Token ID13
Feature activation-1.54e-02

Pos logit contributions
rier+0.044
istered+0.044
working+0.041
ishy+0.040
ivery+0.039
Neg logit contributions
 peek-0.019
 dial-0.018
nob-0.017
 turned-0.016
 called-0.016
Token One
Token ID1881
Feature activation+9.54e-03

Pos logit contributions
 dial+0.022
 peek+0.021
nob+0.021
ad+0.020
 turned+0.020
Neg logit contributions
rier-0.024
working-0.024
istered-0.022
ishy-0.021
 goals-0.021
Token day
Token ID1110
Feature activation-1.47e-02

Pos logit contributions
working+0.013
rier+0.012
istered+0.012
ishy+0.011
 goals+0.010
Neg logit contributions
 dial-0.016
 peek-0.016
nob-0.016
ad-0.015
 Looking-0.015
Token,
Token ID11
Feature activation-2.31e-02

Pos logit contributions
 dial+0.017
 peek+0.017
nob+0.016
 turned+0.015
ad+0.015
Neg logit contributions
rier-0.028
working-0.027
istered-0.027
ishy-0.025
 goals-0.024
Token and
Token ID290
Feature activation+1.65e-02

Pos logit contributions
 peek+0.006
 dial+0.005
nob+0.005
 turned+0.005
 opened+0.005
Neg logit contributions
rier-0.013
istered-0.013
working-0.013
ishy-0.012
 goals-0.012
Token play
Token ID711
Feature activation+2.01e-02

Pos logit contributions
rier+0.034
istered+0.032
working+0.032
ishy+0.030
ivery+0.029
Neg logit contributions
 peek-0.020
 dial-0.019
 turned-0.018
 opened-0.017
nob-0.017
Token with
Token ID351
Feature activation+2.80e-03

Pos logit contributions
working+0.050
istered+0.050
rier+0.048
ishy+0.047
attered+0.046
Neg logit contributions
 peek-0.015
nob-0.014
 dial-0.012
 called-0.010
 call-0.010
Token your
Token ID534
Feature activation+1.99e-02

Pos logit contributions
working+0.006
rier+0.006
istered+0.006
ishy+0.006
ivery+0.006
Neg logit contributions
 peek-0.003
 dial-0.003
nob-0.002
 turned-0.002
 called-0.002
Token or
Token ID393
Feature activation+3.25e-02

Pos logit contributions
rier+0.030
working+0.030
istered+0.029
ishy+0.026
ivery+0.025
Neg logit contributions
 peek-0.030
 dial-0.030
nob-0.029
 turned-0.028
ad-0.027
Tokennam
Token ID7402
Feature activation+7.27e-02

Pos logit contributions
rier+0.062
istered+0.061
working+0.058
ishy+0.056
ivery+0.054
Neg logit contributions
 peek-0.043
 dial-0.041
 turned-0.037
 call-0.036
nob-0.036
Tokenents
Token ID658
Feature activation+2.09e-02

Pos logit contributions
rier+0.128
working+0.124
istered+0.121
ishy+0.114
obb+0.113
Neg logit contributions
 peek-0.090
 dial-0.088
ad-0.086
nob-0.083
 opened-0.079
Token.
Token ID13
Feature activation+1.19e-02

Pos logit contributions
istered+0.049
rier+0.047
ishy+0.045
working+0.045
ivery+0.043
Neg logit contributions
 peek-0.016
nob-0.015
 turned-0.014
 opened-0.014
 dial-0.014
Token Maybe
Token ID6674
Feature activation+1.72e-03

Pos logit contributions
rier+0.020
istered+0.020
working+0.019
 goals+0.018
ishy+0.018
Neg logit contributions
 dial-0.016
 peek-0.016
nob-0.015
 turned-0.015
ad-0.014
Token you
Token ID345
Feature activation+6.86e-03

Pos logit contributions
rier+0.002
working+0.002
istered+0.002
nam+0.002
 goals+0.002
Neg logit contributions
nob-0.003
 dial-0.003
 peek-0.003
 Looking-0.003
ad-0.003
Token can
Token ID460
Feature activation+4.90e-03

Pos logit contributions
rier+0.014
istered+0.013
working+0.013
ishy+0.012
ivery+0.011
Neg logit contributions
 peek-0.008
 dial-0.008
nob-0.007
 turned-0.007
 opened-0.007
Token Max
Token ID5436
Feature activation+9.01e-04

Pos logit contributions
rier+0.012
working+0.012
istered+0.012
ishy+0.011
 goals+0.011
Neg logit contributions
 dial-0.005
 peek-0.005
nob-0.005
 turned-0.004
 Looking-0.004
Token loved
Token ID6151
Feature activation+3.18e-03

Pos logit contributions
rier+0.002
istered+0.002
working+0.002
ishy+0.002
 goals+0.002
Neg logit contributions
 dial-0.001
 peek-0.001
nob-0.001
 turned-0.001
ad-0.001
Token being
Token ID852
Feature activation+1.06e-02

Pos logit contributions
working+0.006
rier+0.005
istered+0.005
 goals+0.005
 bored+0.005
Neg logit contributions
nob-0.004
 peek-0.004
 dial-0.004
 Looking-0.004
ad-0.004
Token at
Token ID379
Feature activation+9.00e-04

Pos logit contributions
rier+0.020
istered+0.020
working+0.019
ishy+0.018
 goals+0.018
Neg logit contributions
 dial-0.013
 peek-0.013
nob-0.011
 turned-0.011
 opened-0.011
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
rier+0.002
working+0.002
istered+0.002
ishy+0.001
 goals+0.001
Neg logit contributions
 dial-0.001
 peek-0.001
nob-0.001
 turned-0.001
ad-0.001
Token carn
Token ID18466
Feature activation+7.25e-02

Pos logit contributions
rier+0.024
istered+0.024
working+0.023
ishy+0.022
ivery+0.021
Neg logit contributions
 dial-0.016
 peek-0.016
nob-0.014
 turned-0.014
ad-0.014
Tokenival
Token ID2473
Feature activation+1.80e-02

Pos logit contributions
rier+0.118
istered+0.114
working+0.110
ishy+0.102
nam+0.098
Neg logit contributions
 peek-0.107
nob-0.100
 dial-0.098
ad-0.095
 Turning-0.093
Token so
Token ID523
Feature activation+2.06e-02

Pos logit contributions
rier+0.038
istered+0.038
working+0.036
ishy+0.035
ivery+0.034
Neg logit contributions
 dial-0.017
 peek-0.017
nob-0.016
 turned-0.015
ad-0.014
Token much
Token ID881
Feature activation+3.96e-03

Pos logit contributions
rier+0.035
ivery+0.033
istered+0.032
ishy+0.030
working+0.029
Neg logit contributions
 peek-0.030
ad-0.030
 turned-0.029
 dial-0.028
 opened-0.027
Token that
Token ID326
Feature activation+1.05e-02

Pos logit contributions
istered+0.008
rier+0.008
working+0.008
ishy+0.008
ivery+0.008
Neg logit contributions
 dial-0.004
 peek-0.004
 turned-0.003
nob-0.003
ad-0.003
Token he
Token ID339
Feature activation+5.98e-03

Pos logit contributions
istered+0.020
rier+0.019
ivery+0.018
ishy+0.018
working+0.017
Neg logit contributions
 peek-0.014
 turned-0.014
 dial-0.014
 opened-0.013
 called-0.013
Tokenummy
Token ID13513
Feature activation-2.60e-02

Pos logit contributions
rier+0.029
istered+0.028
working+0.028
nam+0.022
 kicker+0.022
Neg logit contributions
 peek-0.056
ad-0.055
 dial-0.055
 turned-0.053
nob-0.053
Token cotton
Token ID15985
Feature activation+1.23e-02

Pos logit contributions
nob+0.045
 peek+0.044
 dial+0.044
 Looking+0.043
 turned+0.041
Neg logit contributions
working-0.032
rier-0.032
istered-0.029
ishy-0.028
 goals-0.028
Token candy
Token ID18550
Feature activation+1.32e-02

Pos logit contributions
rier+0.019
istered+0.019
working+0.019
ivery+0.017
ishy+0.017
Neg logit contributions
 dial-0.018
 peek-0.018
 turned-0.017
nob-0.016
ad-0.016
Token and
Token ID290
Feature activation+5.99e-03

Pos logit contributions
istered+0.033
rier+0.032
ivery+0.031
working+0.031
ishy+0.030
Neg logit contributions
 peek-0.008
 dial-0.008
 turned-0.007
nob-0.007
 opened-0.007
Token play
Token ID711
Feature activation+1.92e-02

Pos logit contributions
rier+0.011
istered+0.011
working+0.010
ishy+0.010
ivery+0.010
Neg logit contributions
 dial-0.008
 peek-0.008
 turned-0.007
 opened-0.007
nob-0.007
Token carn
Token ID18466
Feature activation+7.22e-02

Pos logit contributions
istered+0.045
working+0.045
rier+0.045
ishy+0.042
attered+0.041
Neg logit contributions
 peek-0.015
 dial-0.014
nob-0.013
ad-0.011
 turned-0.011
Tokenival
Token ID2473
Feature activation+7.81e-03

Pos logit contributions
rier+0.106
working+0.103
istered+0.103
ishy+0.092
 goals+0.088
Neg logit contributions
 peek-0.114
nob-0.110
 dial-0.109
ad-0.103
 Looking-0.102
Token games
Token ID1830
Feature activation+8.34e-03

Pos logit contributions
istered+0.018
rier+0.018
ishy+0.017
working+0.017
ivery+0.017
Neg logit contributions
 peek-0.006
 dial-0.006
nob-0.006
ad-0.005
 turned-0.005
Token.
Token ID13
Feature activation-8.45e-04

Pos logit contributions
rier+0.018
istered+0.018
working+0.017
ishy+0.017
ivery+0.017
Neg logit contributions
 peek-0.008
 dial-0.007
nob-0.007
 turned-0.006
ad-0.006
Token
Token ID198
Feature activation-6.75e-03

Pos logit contributions
 peek+0.001
 dial+0.001
 Looking+0.001
nob+0.001
 turned+0.001
Neg logit contributions
rier-0.002
istered-0.002
working-0.002
ishy-0.002
 goals-0.002
Token
Token ID198
Feature activation-1.34e-03

Pos logit contributions
 dial+0.005
 peek+0.005
nob+0.005
ad+0.004
 turned+0.004
Neg logit contributions
working-0.015
istered-0.015
rier-0.015
 goals-0.014
 kicker-0.014
Token lived
Token ID5615
Feature activation+1.58e-02

Pos logit contributions
 dial+0.005
nob+0.005
 peek+0.005
 Looking+0.005
ad+0.005
Neg logit contributions
working-0.003
istered-0.003
rier-0.003
 goals-0.003
ishy-0.003
Token in
Token ID287
Feature activation+9.28e-05

Pos logit contributions
rier+0.032
working+0.032
istered+0.031
ishy+0.029
 goals+0.029
Neg logit contributions
 dial-0.016
 peek-0.015
nob-0.015
 turned-0.014
ad-0.014
Token a
Token ID257
Feature activation+4.45e-02

Pos logit contributions
rier+0.000
working+0.000
istered+0.000
ishy+0.000
 goals+0.000
Neg logit contributions
 dial-0.000
 peek-0.000
nob-0.000
 turned-0.000
ad-0.000
Token warm
Token ID5814
Feature activation+1.28e-02

Pos logit contributions
rier+0.106
working+0.097
istered+0.097
ier+0.096
der+0.094
Neg logit contributions
 peek-0.050
 dial-0.038
 turned-0.037
 story-0.037
 opened-0.036
Token and
Token ID290
Feature activation+4.92e-03

Pos logit contributions
rier+0.021
working+0.021
istered+0.020
ishy+0.019
 goals+0.018
Neg logit contributions
 dial-0.017
 peek-0.017
nob-0.017
ad-0.016
 turned-0.016
Token c
Token ID269
Feature activation+7.21e-02

Pos logit contributions
rier+0.009
istered+0.008
working+0.007
ivery+0.007
ishy+0.007
Neg logit contributions
 peek-0.007
 turned-0.007
 dial-0.007
 opened-0.007
nob-0.006
Tokenudd
Token ID4185
Feature activation+3.95e-02

Pos logit contributions
nam+0.113
working+0.106
rier+0.101
 neither+0.100
istered+0.100
Neg logit contributions
 peek-0.100
 turned-0.093
ad-0.091
yl-0.090
 story-0.088
Tokenly
Token ID306
Feature activation+9.91e-03

Pos logit contributions
istered+0.065
nam+0.054
working+0.051
 kicker+0.051
 goals+0.051
Neg logit contributions
 peek-0.059
 dial-0.058
 turned-0.056
ad-0.056
nob-0.055
Token home
Token ID1363
Feature activation+1.55e-02

Pos logit contributions
istered+0.019
rier+0.018
working+0.017
ishy+0.017
 sweaty+0.016
Neg logit contributions
 peek-0.012
 dial-0.012
 turned-0.011
 called-0.010
 call-0.010
Token.
Token ID13
Feature activation+1.75e-02

Pos logit contributions
rier+0.033
istered+0.033
working+0.032
ishy+0.031
 goals+0.030
Neg logit contributions
 peek-0.014
 dial-0.014
nob-0.013
 turned-0.013
 opened-0.012
Token Every
Token ID3887
Feature activation+1.08e-02

Pos logit contributions
working+0.025
 goals+0.023
rier+0.023
istered+0.022
 bored+0.021
Neg logit contributions
 dial-0.026
nob-0.025
 peek-0.024
 fore-0.024
ran-0.024
Token has
Token ID468
Feature activation+1.41e-02

Pos logit contributions
rier+0.016
istered+0.016
working+0.016
 goals+0.015
ishy+0.014
Neg logit contributions
 dial-0.007
 peek-0.007
nob-0.006
 Looking-0.006
ad-0.006
Token lettuce
Token ID39406
Feature activation+6.37e-03

Pos logit contributions
rier+0.026
working+0.026
istered+0.026
ishy+0.023
ivery+0.023
Neg logit contributions
 peek-0.017
 dial-0.017
nob-0.016
 turned-0.016
ad-0.015
Token and
Token ID290
Feature activation+1.36e-02

Pos logit contributions
working+0.016
rier+0.015
istered+0.015
ishy+0.014
ivery+0.014
Neg logit contributions
 peek-0.004
 dial-0.003
 turned-0.003
nob-0.003
 opened-0.003
Token tomatoes
Token ID23972
Feature activation+6.41e-03

Pos logit contributions
istered+0.022
rier+0.022
working+0.021
ivery+0.020
ishy+0.019
Neg logit contributions
 peek-0.020
 dial-0.020
 turned-0.019
 opened-0.018
nob-0.018
Token and
Token ID290
Feature activation+1.61e-02

Pos logit contributions
rier+0.014
working+0.014
istered+0.014
ishy+0.012
ivery+0.012
Neg logit contributions
 peek-0.006
 dial-0.005
nob-0.005
 turned-0.005
 opened-0.005
Token cuc
Token ID38421
Feature activation+7.21e-02

Pos logit contributions
rier+0.025
istered+0.025
working+0.025
ivery+0.023
ishy+0.022
Neg logit contributions
 peek-0.025
 dial-0.024
 turned-0.023
 opened-0.022
nob-0.022
Tokenumbers
Token ID17024
Feature activation-3.52e-03

Pos logit contributions
working+0.083
istered+0.075
 sweaty+0.072
rier+0.071
 bored+0.068
Neg logit contributions
 peek-0.126
 dial-0.123
ad-0.123
p-0.119
nob-0.117
Token.
Token ID13
Feature activation+6.08e-03

Pos logit contributions
 peek+0.003
 dial+0.003
 turned+0.003
nob+0.003
ad+0.003
Neg logit contributions
istered-0.007
working-0.007
rier-0.007
ishy-0.007
ivery-0.007
Token And
Token ID843
Feature activation+1.52e-03

Pos logit contributions
rier+0.010
istered+0.009
working+0.009
 goals+0.009
ishy+0.008
Neg logit contributions
 dial-0.009
nob-0.009
 peek-0.009
ad-0.008
 turned-0.008
Token it
Token ID340
Feature activation+9.06e-03

Pos logit contributions
rier+0.003
working+0.003
istered+0.003
ivery+0.002
ishy+0.002
Neg logit contributions
 peek-0.002
 dial-0.002
 turned-0.002
 opened-0.002
nob-0.002
Token has
Token ID468
Feature activation+8.36e-03

Pos logit contributions
rier+0.020
working+0.019
istered+0.019
ishy+0.018
 goals+0.018
Neg logit contributions
 dial-0.008
 peek-0.008
nob-0.007
ad-0.006
 Looking-0.006
Token John
Token ID1757
Feature activation+1.58e-02

Pos logit contributions
rier+0.039
istered+0.037
working+0.037
ishy+0.034
 goals+0.033
Neg logit contributions
 dial-0.029
 peek-0.029
nob-0.027
 turned-0.026
ad-0.026
Token chose
Token ID7690
Feature activation-2.47e-03

Pos logit contributions
rier+0.032
working+0.032
istered+0.031
ishy+0.029
 goals+0.028
Neg logit contributions
 dial-0.016
 peek-0.015
nob-0.015
 turned-0.013
ad-0.013
Token some
Token ID617
Feature activation-2.24e-03

Pos logit contributions
 dial+0.003
 peek+0.003
nob+0.003
 turned+0.002
ad+0.002
Neg logit contributions
rier-0.005
working-0.005
istered-0.005
ishy-0.004
 goals-0.004
Token carrots
Token ID34397
Feature activation+6.50e-03

Pos logit contributions
 dial+0.003
 peek+0.003
nob+0.003
 turned+0.003
ad+0.003
Neg logit contributions
rier-0.003
working-0.003
istered-0.003
ishy-0.003
 goals-0.003
Token and
Token ID290
Feature activation+1.24e-02

Pos logit contributions
istered+0.015
rier+0.014
working+0.014
ishy+0.013
ivery+0.013
Neg logit contributions
 peek-0.005
 dial-0.005
nob-0.005
 turned-0.005
ad-0.004
Token cuc
Token ID38421
Feature activation+7.19e-02

Pos logit contributions
istered+0.023
rier+0.023
ivery+0.021
working+0.021
ishy+0.020
Neg logit contributions
 peek-0.016
 dial-0.016
 turned-0.015
 opened-0.015
 pat-0.014
Tokenumbers
Token ID17024
Feature activation+6.66e-03

Pos logit contributions
istered+0.081
working+0.078
 sweaty+0.073
rier+0.072
 bored+0.071
Neg logit contributions
 dial-0.124
 peek-0.124
ad-0.122
p-0.120
nob-0.118
Token to
Token ID284
Feature activation+2.97e-02

Pos logit contributions
istered+0.013
working+0.013
rier+0.013
ishy+0.012
 goals+0.012
Neg logit contributions
 peek-0.007
 dial-0.006
 turned-0.006
nob-0.006
ad-0.006
Token take
Token ID1011
Feature activation+1.95e-02

Pos logit contributions
rier+0.062
istered+0.062
working+0.059
ishy+0.056
 goals+0.055
Neg logit contributions
 peek-0.030
 dial-0.030
nob-0.027
 turned-0.026
ad-0.026
Token home
Token ID1363
Feature activation-3.43e-03

Pos logit contributions
rier+0.035
istered+0.035
working+0.034
ishy+0.031
ivery+0.031
Neg logit contributions
 dial-0.024
 peek-0.024
nob-0.023
 turned-0.022
ad-0.022
Token.
Token ID13
Feature activation+9.12e-03

Pos logit contributions
 dial+0.003
 peek+0.003
nob+0.003
 turned+0.003
ad+0.003
Neg logit contributions
istered-0.007
rier-0.007
working-0.007
ishy-0.007
 kicker-0.007
Token,
Token ID11
Feature activation-1.86e-02

Pos logit contributions
 dial+0.014
 peek+0.014
nob+0.013
 turned+0.013
ad+0.012
Neg logit contributions
rier-0.012
istered-0.012
working-0.012
ishy-0.011
 goals-0.010
Token Max
Token ID5436
Feature activation-1.45e-02

Pos logit contributions
 peek+0.027
 dial+0.027
nob+0.026
 turned+0.025
 opened+0.024
Neg logit contributions
rier-0.030
istered-0.029
working-0.029
ishy-0.025
 goals-0.025
Token,
Token ID11
Feature activation-1.28e-02

Pos logit contributions
 dial+0.014
 peek+0.013
nob+0.013
ad+0.012
 turned+0.012
Neg logit contributions
rier-0.030
working-0.030
istered-0.029
ishy-0.027
 goals-0.027
Token to
Token ID284
Feature activation+1.56e-02

Pos logit contributions
 dial+0.013
 peek+0.013
nob+0.012
 turned+0.011
ad+0.011
Neg logit contributions
rier-0.026
working-0.025
istered-0.025
ishy-0.023
 goals-0.023
Token the
Token ID262
Feature activation+2.35e-02

Pos logit contributions
working+0.027
rier+0.025
istered+0.024
 goals+0.024
 kicker+0.024
Neg logit contributions
nob-0.019
 dial-0.019
 peek-0.018
 Looking-0.017
 turned-0.017
Token carn
Token ID18466
Feature activation+7.18e-02

Pos logit contributions
rier+0.044
istered+0.043
working+0.043
ishy+0.040
 goals+0.037
Neg logit contributions
 peek-0.029
 dial-0.029
nob-0.026
 turned-0.025
ad-0.025
Tokenival
Token ID2473
Feature activation+1.31e-02

Pos logit contributions
rier+0.102
working+0.098
istered+0.097
ishy+0.087
 goals+0.083
Neg logit contributions
 peek-0.119
 dial-0.116
nob-0.112
 turned-0.107
ad-0.107
Token.
Token ID13
Feature activation+4.24e-03

Pos logit contributions
rier+0.026
istered+0.026
working+0.026
ishy+0.024
 goals+0.023
Neg logit contributions
 peek-0.014
 dial-0.014
nob-0.013
 turned-0.012
ad-0.012
Token Everywhere
Token ID48201
Feature activation+2.14e-02

Pos logit contributions
rier+0.007
istered+0.007
working+0.007
ishy+0.006
 goals+0.006
Neg logit contributions
 dial-0.006
 peek-0.006
nob-0.006
 turned-0.005
 Looking-0.005
Token they
Token ID484
Feature activation+1.08e-02

Pos logit contributions
rier+0.049
istered+0.047
ivery+0.045
onel+0.043
ishy+0.042
Neg logit contributions
 dial-0.024
 opened-0.024
 was-0.023
 turned-0.023
 peek-0.023
Token looked
Token ID3114
Feature activation+1.56e-04

Pos logit contributions
rier+0.028
istered+0.027
ivery+0.024
 goals+0.024
working+0.024
Neg logit contributions
 peek-0.009
 dial-0.008
 turned-0.008
 opened-0.008
 called-0.006
TokenOne
Token ID3198
Feature activation+1.21e-02

Pos logit contributions
 dial+0.004
 peek+0.004
nob+0.004
 turned+0.004
ad+0.004
Neg logit contributions
rier-0.007
working-0.007
istered-0.007
ishy-0.006
 goals-0.006
Token day
Token ID1110
Feature activation+1.01e-03

Pos logit contributions
working+0.016
rier+0.016
istered+0.015
ishy+0.014
 goals+0.013
Neg logit contributions
 dial-0.021
nob-0.020
 peek-0.020
ad-0.019
 Looking-0.019
Token,
Token ID11
Feature activation-2.80e-03

Pos logit contributions
rier+0.002
istered+0.002
working+0.002
ishy+0.002
 goals+0.002
Neg logit contributions
 dial-0.001
 peek-0.001
nob-0.001
 turned-0.001
ad-0.001
Token Tommy
Token ID19919
Feature activation+1.51e-02

Pos logit contributions
 dial+0.004
 peek+0.004
 turned+0.004
 opened+0.004
 Looking+0.003
Neg logit contributions
rier-0.005
istered-0.005
working-0.004
ishy-0.004
ivery-0.004
Token and
Token ID290
Feature activation+1.36e-03

Pos logit contributions
working+0.028
istered+0.027
rier+0.027
 bored+0.025
ishy+0.025
Neg logit contributions
 dial-0.016
nob-0.016
 peek-0.015
ad-0.015
 Looking-0.015
Token St
Token ID520
Feature activation+7.17e-02

Pos logit contributions
working+0.002
rier+0.002
istered+0.002
 goals+0.002
 bored+0.002
Neg logit contributions
nob-0.002
 peek-0.002
 dial-0.002
ad-0.002
 Looking-0.002
Tokenitch
Token ID2007
Feature activation+2.50e-02

Pos logit contributions
rier+0.092
working+0.084
nam+0.080
istered+0.078
chard+0.076
Neg logit contributions
 dial-0.126
ad-0.122
 peek-0.122
 turned-0.120
 Looking-0.113
Token went
Token ID1816
Feature activation+2.42e-03

Pos logit contributions
rier+0.056
istered+0.052
working+0.052
ishy+0.048
 goals+0.047
Neg logit contributions
 peek-0.025
 dial-0.024
 turned-0.023
nob-0.021
 opened-0.021
Token to
Token ID284
Feature activation+1.02e-02

Pos logit contributions
working+0.004
rier+0.004
istered+0.004
 bored+0.004
 goals+0.004
Neg logit contributions
 dial-0.003
nob-0.003
 peek-0.003
ad-0.003
 Looking-0.003
Token the
Token ID262
Feature activation+2.38e-02

Pos logit contributions
rier+0.019
working+0.019
istered+0.019
ishy+0.017
 goals+0.017
Neg logit contributions
 dial-0.012
 peek-0.011
nob-0.011
 turned-0.010
ad-0.010
Token park
Token ID3952
Feature activation-1.15e-03

Pos logit contributions
rier+0.048
istered+0.046
working+0.046
ishy+0.043
ivery+0.041
Neg logit contributions
 peek-0.028
 dial-0.027
nob-0.025
 turned-0.024
 call-0.023
Token."
Token ID526
Feature activation-5.71e-03

Pos logit contributions
istered+0.007
rier+0.007
working+0.007
ishy+0.007
nam+0.006
Neg logit contributions
 dial-0.006
 peek-0.006
 turned-0.005
 call-0.005
ad-0.005
Token She
Token ID1375
Feature activation-2.37e-02

Pos logit contributions
 dial+0.008
 peek+0.008
nob+0.007
 turned+0.007
ad+0.007
Neg logit contributions
rier-0.010
istered-0.009
working-0.009
 goals-0.008
ishy-0.008
Token gives
Token ID3607
Feature activation+1.57e-03

Pos logit contributions
nob+0.027
 peek+0.025
ad+0.024
eway+0.024
 peaked+0.024
Neg logit contributions
 goals-0.042
rier-0.040
istered-0.040
working-0.039
 bored-0.038
Token them
Token ID606
Feature activation-1.70e-02

Pos logit contributions
istered+0.003
working+0.003
rier+0.003
ishy+0.003
ivery+0.003
Neg logit contributions
 dial-0.002
 peek-0.002
 turned-0.002
ad-0.002
nob-0.002
Token a
Token ID257
Feature activation-2.69e-02

Pos logit contributions
 peek+0.022
 dial+0.021
nob+0.020
 turned+0.019
ad+0.019
Neg logit contributions
rier-0.032
working-0.031
istered-0.030
ishy-0.027
ivery-0.027
Token new
Token ID649
Feature activation-8.58e-02

Pos logit contributions
nob+0.037
ad+0.036
ered+0.032
p+0.032
ran+0.032
Neg logit contributions
istered-0.044
working-0.043
rier-0.041
 bored-0.039
ishy-0.039
Token tap
Token ID9814
Feature activation-2.73e-02

Pos logit contributions
nob+0.135
ad+0.127
 Looking+0.120
 unlocked+0.119
ran+0.118
Neg logit contributions
working-0.121
rier-0.108
 kicker-0.106
 favorite-0.103
ishy-0.103
Token.
Token ID13
Feature activation+9.67e-03

Pos logit contributions
 dial+0.028
 peek+0.027
nob+0.026
 Looking+0.025
ad+0.023
Neg logit contributions
rier-0.055
working-0.053
istered-0.053
ishy-0.049
 goals-0.049
Token The
Token ID383
Feature activation-4.32e-02

Pos logit contributions
rier+0.016
working+0.016
istered+0.016
ishy+0.014
 goals+0.014
Neg logit contributions
 dial-0.013
 peek-0.013
nob-0.013
 turned-0.012
ad-0.012
Token tap
Token ID9814
Feature activation-1.89e-02

Pos logit contributions
nob+0.054
 dial+0.052
 peek+0.051
ad+0.048
 Looking+0.047
Neg logit contributions
rier-0.078
working-0.076
istered-0.074
 goals-0.070
ishy-0.070
Token is
Token ID318
Feature activation-1.19e-02

Pos logit contributions
nob+0.019
 dial+0.019
 peek+0.018
 Looking+0.017
ad+0.016
Neg logit contributions
rier-0.037
working-0.036
istered-0.036
 goals-0.035
ishy-0.034
Token and
Token ID290
Feature activation-1.72e-02

Pos logit contributions
 peek+0.000
 dial+0.000
 turned+0.000
nob+0.000
 opened+0.000
Neg logit contributions
working-0.001
istered-0.001
rier-0.001
ishy-0.001
 goals-0.001
Token said
Token ID531
Feature activation+4.37e-03

Pos logit contributions
nob+0.018
 dial+0.016
 peek+0.016
ad+0.015
 Looking+0.014
Neg logit contributions
working-0.034
rier-0.033
istered-0.033
ishy-0.031
 sweaty-0.030
Token,
Token ID11
Feature activation-2.41e-02

Pos logit contributions
istered+0.010
working+0.010
rier+0.010
ivery+0.010
ishy+0.009
Neg logit contributions
 peek-0.003
 dial-0.003
 turned-0.003
 opened-0.003
nob-0.003
Token "
Token ID366
Feature activation-6.65e-03

Pos logit contributions
 dial+0.034
nob+0.034
 peek+0.034
ad+0.032
 turned+0.030
Neg logit contributions
rier-0.040
working-0.037
istered-0.036
 bored-0.032
ishy-0.032
TokenLet
Token ID5756
Feature activation-2.78e-03

Pos logit contributions
 dial+0.009
 peek+0.009
nob+0.008
 turned+0.008
ad+0.008
Neg logit contributions
rier-0.011
working-0.011
istered-0.011
ishy-0.010
 kicker-0.010
Token me
Token ID502
Feature activation-8.34e-02

Pos logit contributions
 peek+0.003
 dial+0.003
nob+0.003
 turned+0.003
ad+0.003
Neg logit contributions
rier-0.006
istered-0.005
working-0.005
ishy-0.005
 goals-0.005
Token help
Token ID1037
Feature activation+1.53e-03

Pos logit contributions
nob+0.108
 dial+0.102
 Looking+0.099
ad+0.095
 Turning+0.093
Neg logit contributions
working-0.142
istered-0.130
ishy-0.130
rier-0.129
 bored-0.120
Token you
Token ID345
Feature activation-4.97e-02

Pos logit contributions
rier+0.002
istered+0.002
working+0.002
ishy+0.002
 goals+0.002
Neg logit contributions
 peek-0.002
 dial-0.002
nob-0.002
 turned-0.002
ad-0.002
Token.
Token ID13
Feature activation-2.15e-03

Pos logit contributions
 peek+0.060
 dial+0.059
nob+0.056
 turned+0.054
ad+0.052
Neg logit contributions
rier-0.092
istered-0.091
working-0.090
ishy-0.082
 goals-0.080
Token I
Token ID314
Feature activation-4.79e-02

Pos logit contributions
 dial+0.003
nob+0.003
 peek+0.003
ad+0.003
 turned+0.003
Neg logit contributions
rier-0.003
working-0.003
istered-0.003
ishy-0.003
 goals-0.003
Token will
Token ID481
Feature activation-4.20e-02

Pos logit contributions
nob+0.073
 dial+0.072
ad+0.068
 peek+0.068
 Looking+0.067
Neg logit contributions
working-0.069
istered-0.068
rier-0.065
ishy-0.064
 kicker-0.058
Token she
Token ID673
Feature activation-5.87e-03

Pos logit contributions
 peek+0.010
 dial+0.010
 turned+0.009
nob+0.009
 opened+0.009
Neg logit contributions
rier-0.010
istered-0.010
working-0.010
ishy-0.009
 goals-0.009
Token gave
Token ID2921
Feature activation+1.46e-02

Pos logit contributions
nob+0.006
 dial+0.006
 peek+0.006
ad+0.005
 Looking+0.005
Neg logit contributions
rier-0.011
istered-0.011
working-0.011
ishy-0.010
 bored-0.010
Token Teddy
Token ID29345
Feature activation-3.42e-02

Pos logit contributions
istered+0.024
rier+0.024
working+0.022
ishy+0.021
 goals+0.021
Neg logit contributions
 dial-0.022
 peek-0.021
nob-0.021
 turned-0.020
ad-0.020
Token a
Token ID257
Feature activation-3.70e-02

Pos logit contributions
 dial+0.032
 peek+0.032
nob+0.031
 turned+0.028
ad+0.028
Neg logit contributions
rier-0.073
istered-0.071
working-0.070
ishy-0.065
 goals-0.064
Token brand
Token ID4508
Feature activation+3.84e-03

Pos logit contributions
nob+0.063
ad+0.061
 dial+0.057
ran+0.057
p+0.057
Neg logit contributions
working-0.047
istered-0.047
rier-0.042
ishy-0.042
 sweaty-0.040
Token new
Token ID649
Feature activation-8.23e-02

Pos logit contributions
rier+0.005
working+0.004
istered+0.004
ishy+0.004
 goals+0.004
Neg logit contributions
nob-0.007
 dial-0.007
 peek-0.007
ad-0.006
 opened-0.006
Token sc
Token ID629
Feature activation-1.99e-02

Pos logit contributions
nob+0.120
Agent+0.111
r+0.110
 dial+0.108
p+0.107
Neg logit contributions
working-0.123
rier-0.108
 favorite-0.103
 runner-0.102
 kicker-0.100
Tokenooter
Token ID25141
Feature activation-1.49e-02

Pos logit contributions
 dial+0.027
 peek+0.026
nob+0.026
 turned+0.024
 Looking+0.023
Neg logit contributions
rier-0.034
working-0.033
istered-0.032
ishy-0.030
 goals-0.028
Token.
Token ID13
Feature activation-7.29e-03

Pos logit contributions
 peek+0.015
 dial+0.014
nob+0.014
 turned+0.013
ad+0.013
Neg logit contributions
rier-0.031
istered-0.030
working-0.029
ishy-0.028
 goals-0.028
Token He
Token ID679
Feature activation-2.11e-02

Pos logit contributions
 dial+0.011
 peek+0.011
nob+0.010
 Looking+0.010
 turned+0.010
Neg logit contributions
rier-0.012
working-0.011
istered-0.011
ishy-0.010
 goals-0.010
Token was
Token ID373
Feature activation+1.91e-03

Pos logit contributions
nob+0.020
 dial+0.019
 peek+0.018
ad+0.018
 Looking+0.018
Neg logit contributions
working-0.042
istered-0.041
rier-0.040
ishy-0.037
 kicker-0.037
Token mess
Token ID2085
Feature activation-2.03e-03

Pos logit contributions
nob+0.059
 dial+0.059
ad+0.059
 Looking+0.058
 peek+0.057
Neg logit contributions
istered-0.052
rier-0.050
working-0.049
ishy-0.046
 sweaty-0.046
Token and
Token ID290
Feature activation+7.42e-03

Pos logit contributions
 dial+0.001
 peek+0.001
nob+0.001
 turned+0.001
ad+0.001
Neg logit contributions
rier-0.005
working-0.005
istered-0.005
ishy-0.005
 kicker-0.005
Token gave
Token ID2921
Feature activation+2.26e-02

Pos logit contributions
rier+0.015
working+0.015
istered+0.014
 bored+0.013
 goals+0.013
Neg logit contributions
nob-0.007
 dial-0.007
 peek-0.007
ad-0.007
 Looking-0.006
Token her
Token ID607
Feature activation-3.30e-02

Pos logit contributions
istered+0.047
working+0.046
rier+0.046
ivery+0.045
ishy+0.042
Neg logit contributions
 dial-0.026
 peek-0.024
 turned-0.022
nob-0.022
ad-0.022
Token a
Token ID257
Feature activation-2.51e-02

Pos logit contributions
 dial+0.036
 peek+0.035
nob+0.034
 turned+0.032
ad+0.031
Neg logit contributions
rier-0.065
working-0.063
istered-0.063
ishy-0.058
 goals-0.057
Token new
Token ID649
Feature activation-8.14e-02

Pos logit contributions
nob+0.036
ad+0.034
ered+0.031
ran+0.031
p+0.031
Neg logit contributions
istered-0.040
working-0.039
ishy-0.036
rier-0.036
 bored-0.035
Token cup
Token ID6508
Feature activation-1.25e-02

Pos logit contributions
nob+0.143
ran+0.134
ad+0.133
 Looking+0.129
 dial+0.127
Neg logit contributions
istered-0.092
working-0.091
ishy-0.090
 favorite-0.089
rier-0.082
Token.
Token ID13
Feature activation+5.94e-03

Pos logit contributions
 dial+0.015
 peek+0.015
nob+0.014
 Looking+0.013
 turned+0.013
Neg logit contributions
rier-0.023
istered-0.022
working-0.022
ishy-0.020
 goals-0.020
Token Sara
Token ID24799
Feature activation+3.80e-03

Pos logit contributions
rier+0.009
istered+0.009
working+0.009
ishy+0.008
 goals+0.008
Neg logit contributions
 dial-0.009
 peek-0.009
nob-0.008
ad-0.008
 turned-0.008
Token thanked
Token ID26280
Feature activation+1.34e-02

Pos logit contributions
istered+0.008
rier+0.007
working+0.007
 goals+0.007
ishy+0.007
Neg logit contributions
nob-0.003
 dial-0.003
 peek-0.003
 Looking-0.003
ad-0.003
Token her
Token ID607
Feature activation-1.26e-02

Pos logit contributions
rier+0.019
working+0.018
istered+0.018
 goals+0.016
ishy+0.016
Neg logit contributions
 peek-0.021
 dial-0.021
nob-0.021
 turned-0.020
 Looking-0.020
Token he
Token ID339
Feature activation-5.18e-03

Pos logit contributions
 dial+0.001
 peek+0.001
 turned+0.001
ad+0.001
nob+0.001
Neg logit contributions
istered-0.001
rier-0.001
working-0.001
ishy-0.001
ivery-0.001
Token gave
Token ID2921
Feature activation+1.13e-02

Pos logit contributions
nob+0.006
 dial+0.005
 peek+0.005
ad+0.005
 Looking+0.005
Neg logit contributions
rier-0.010
working-0.009
istered-0.009
ishy-0.009
 kicker-0.008
Token the
Token ID262
Feature activation-4.75e-02

Pos logit contributions
rier+0.021
working+0.021
istered+0.021
ishy+0.019
 goals+0.019
Neg logit contributions
 dial-0.013
 peek-0.013
nob-0.013
 turned-0.012
ad-0.012
Token boy
Token ID2933
Feature activation-3.55e-02

Pos logit contributions
nob+0.080
 dial+0.075
ad+0.073
 peek+0.072
 Looking+0.072
Neg logit contributions
rier-0.064
working-0.061
istered-0.055
 bored-0.054
ishy-0.054
Token the
Token ID262
Feature activation-6.01e-02

Pos logit contributions
 dial+0.038
 peek+0.037
nob+0.036
 turned+0.033
ad+0.033
Neg logit contributions
rier-0.070
working-0.068
istered-0.068
ishy-0.062
 goals-0.061
Token biggest
Token ID4094
Feature activation-7.86e-02

Pos logit contributions
nob+0.093
 dial+0.088
ad+0.086
 Looking+0.083
 peek+0.082
Neg logit contributions
rier-0.087
working-0.080
istered-0.079
ishy-0.078
 sweaty-0.076
Token hug
Token ID16225
Feature activation-6.30e-03

Pos logit contributions
nob+0.124
 dial+0.118
 Looking+0.113
p+0.109
Agent+0.109
Neg logit contributions
rier-0.108
istered-0.102
working-0.102
ishy-0.101
 sweaty-0.097
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
 peek+0.005
 dial+0.005
nob+0.005
 turned+0.005
ad+0.005
Neg logit contributions
rier-0.014
istered-0.014
working-0.014
ishy-0.013
 goals-0.012
Token
Token ID198
Feature activation-1.58e-02

Pos logit contributions
 dial+0.012
nob+0.012
 peek+0.012
ad+0.010
 turned+0.010
Neg logit contributions
rier-0.021
working-0.020
istered-0.020
 goals-0.019
 kicker-0.019
Token
Token ID198
Feature activation-4.41e-03

Pos logit contributions
 dial+0.021
nob+0.019
 peek+0.018
 turned+0.016
bul+0.016
Neg logit contributions
istered-0.024
 goals-0.024
working-0.024
rier-0.024
dd-0.022
TokenTogether
Token ID41631
Feature activation-2.00e-03

Pos logit contributions
 dial+0.006
 peek+0.006
nob+0.006
 turned+0.005
 call+0.005
Neg logit contributions
rier-0.007
istered-0.007
working-0.007
 goals-0.007
 kicker-0.006
Token
Token ID95
Feature activation+3.60e-03

Pos logit contributions
rier+0.037
working+0.037
istered+0.036
ishy+0.032
 goals+0.031
Neg logit contributions
 dial-0.035
 peek-0.035
nob-0.034
 turned-0.033
ad-0.032
Token
Token ID26391
Feature activation-1.15e-02

Pos logit contributions
working+0.006
istered+0.006
rier+0.005
ivery+0.005
ishy+0.005
Neg logit contributions
 peek-0.005
 dial-0.005
 turned-0.004
 opened-0.004
 pat-0.004
Token
Token ID129
Feature activation+1.69e-02

Pos logit contributions
 dial+0.017
 peek+0.016
nob+0.016
 turned+0.015
ad+0.015
Neg logit contributions
rier-0.019
working-0.018
istered-0.018
ishy-0.016
 goals-0.016
Token
Token ID241
Feature activation-4.44e-02

Pos logit contributions
rier+0.022
working+0.021
istered+0.021
ishy+0.018
 goals+0.017
Neg logit contributions
 dial-0.030
 peek-0.030
nob-0.029
 turned-0.028
ad-0.028
TokenYes
Token ID5297
Feature activation-1.31e-02

Pos logit contributions
 dial+0.059
nob+0.058
 peek+0.057
 turned+0.052
ad+0.051
Neg logit contributions
working-0.076
rier-0.072
istered-0.072
ishy-0.065
 kicker-0.064
Token,
Token ID11
Feature activation-7.85e-02

Pos logit contributions
 dial+0.015
 peek+0.015
nob+0.014
 turned+0.013
ad+0.013
Neg logit contributions
rier-0.025
working-0.024
istered-0.024
ishy-0.022
 goals-0.022
Token but
Token ID475
Feature activation-3.40e-02

Pos logit contributions
nob+0.124
 dial+0.109
 peek+0.102
 Looking+0.100
 Turning+0.098
Neg logit contributions
working-0.112
rier-0.106
 guys-0.096
nam-0.095
 sweaty-0.095
Token be
Token ID307
Feature activation-1.56e-02

Pos logit contributions
nob+0.057
 dial+0.053
 Looking+0.049
ad+0.049
 peek+0.048
Neg logit contributions
working-0.048
rier-0.045
nam-0.041
 neither-0.040
 none-0.040
Token very
Token ID845
Feature activation+5.50e-03

Pos logit contributions
 dial+0.033
 peek+0.033
nob+0.032
ad+0.031
 turned+0.031
Neg logit contributions
rier-0.014
istered-0.014
working-0.013
ishy-0.011
 goals-0.011
Token careful
Token ID8161
Feature activation-1.38e-02

Pos logit contributions
rier+0.008
istered+0.008
working+0.008
ishy+0.007
 goals+0.007
Neg logit contributions
 peek-0.009
 dial-0.009
 turned-0.008
nob-0.008
 opened-0.008
Token.
Token ID13
Feature activation-2.99e-02

Pos logit contributions
nob+0.012
 peek+0.012
 dial+0.012
ad+0.011
 turned+0.011
Neg logit contributions
istered-0.030
rier-0.029
working-0.029
ishy-0.028
 goals-0.026
Token taught
Token ID7817
Feature activation+1.60e-02

Pos logit contributions
nob+0.009
eway+0.009
 Looking+0.008
 Turning+0.008
izer+0.008
Neg logit contributions
istered-0.012
working-0.011
 bored-0.011
 sweaty-0.011
rier-0.011
Token her
Token ID607
Feature activation-3.82e-02

Pos logit contributions
rier+0.020
working+0.019
istered+0.019
 goals+0.018
ishy+0.017
Neg logit contributions
 dial-0.027
nob-0.027
 peek-0.027
 Looking-0.025
 peaked-0.025
Token how
Token ID703
Feature activation+5.19e-03

Pos logit contributions
 dial+0.044
 peek+0.043
nob+0.041
 turned+0.038
ad+0.038
Neg logit contributions
rier-0.072
working-0.071
istered-0.070
 goals-0.064
ishy-0.064
Token to
Token ID284
Feature activation-3.37e-02

Pos logit contributions
rier+0.012
istered+0.011
working+0.011
ishy+0.011
 goals+0.010
Neg logit contributions
 peek-0.004
 dial-0.004
nob-0.004
 turned-0.004
ad-0.003
Token use
Token ID779
Feature activation-4.80e-02

Pos logit contributions
 Looking+0.039
nob+0.036
 dial+0.036
 Isn+0.035
 Turning+0.035
Neg logit contributions
working-0.059
istered-0.053
ishy-0.051
ivery-0.050
rier-0.049
Token the
Token ID262
Feature activation-7.82e-02

Pos logit contributions
nob+0.065
 dial+0.064
 peek+0.064
 Looking+0.063
 Turning+0.060
Neg logit contributions
rier-0.074
working-0.073
istered-0.070
 goals-0.069
ishy-0.065
Token f
Token ID277
Feature activation-5.06e-02

Pos logit contributions
nob+0.127
ad+0.112
 unlocked+0.109
 Looking+0.108
Ell+0.108
Neg logit contributions
rier-0.112
 bored-0.104
ishy-0.100
obb-0.099
working-0.098
Tokenauc
Token ID14272
Feature activation-3.08e-02

Pos logit contributions
 dial+0.089
 peek+0.088
nob+0.087
 Looking+0.082
 opened+0.081
Neg logit contributions
rier-0.069
istered-0.063
working-0.063
ishy-0.063
attered-0.057
Tokenet
Token ID316
Feature activation-5.22e-02

Pos logit contributions
 dial+0.051
 peek+0.050
nob+0.047
 Looking+0.047
 opened+0.046
Neg logit contributions
rier-0.042
working-0.041
ishy-0.040
istered-0.040
 goals-0.036
Token.
Token ID13
Feature activation+8.10e-03

Pos logit contributions
 dial+0.062
 peek+0.060
nob+0.058
 Looking+0.055
ad+0.052
Neg logit contributions
rier-0.097
working-0.096
istered-0.091
ishy-0.086
 goals-0.085
Token Now
Token ID2735
Feature activation+5.98e-03

Pos logit contributions
rier+0.013
istered+0.013
working+0.013
ishy+0.011
 goals+0.011
Neg logit contributions
 dial-0.012
 peek-0.011
nob-0.011
ad-0.010
 turned-0.010
Token can
Token ID460
Feature activation-1.36e-02

Pos logit contributions
nob+0.060
 dial+0.060
 peek+0.055
ad+0.055
 Looking+0.054
Neg logit contributions
working-0.057
istered-0.057
rier-0.054
ishy-0.052
 kicker-0.049
Token help
Token ID1037
Feature activation-1.03e-02

Pos logit contributions
 peek+0.013
 dial+0.013
nob+0.012
 turned+0.011
ad+0.011
Neg logit contributions
rier-0.028
istered-0.028
working-0.028
ishy-0.026
 goals-0.025
Token."
Token ID526
Feature activation-5.13e-02

Pos logit contributions
 peek+0.017
 dial+0.017
nob+0.017
 turned+0.016
ad+0.016
Neg logit contributions
rier-0.014
istered-0.014
working-0.014
ishy-0.012
 goals-0.012
Token He
Token ID679
Feature activation-2.92e-02

Pos logit contributions
nob+0.080
 dial+0.074
 spell+0.074
 flap+0.073
 grant+0.070
Neg logit contributions
rier-0.069
 sweaty-0.064
working-0.063
attered-0.063
 bored-0.062
Token took
Token ID1718
Feature activation-3.57e-02

Pos logit contributions
nob+0.038
ad+0.034
 ey+0.032
 Looking+0.031
 Turning+0.030
Neg logit contributions
working-0.047
rier-0.045
 kicker-0.042
istered-0.041
der-0.041
Token out
Token ID503
Feature activation-7.79e-02

Pos logit contributions
nob+0.048
 dial+0.047
 peek+0.046
 Turning+0.045
 story+0.044
Neg logit contributions
working-0.054
rier-0.053
ishy-0.049
istered-0.049
 bored-0.045
Token a
Token ID257
Feature activation-4.87e-02

Pos logit contributions
nob+0.120
 dial+0.108
 Turning+0.107
 peek+0.107
 Looking+0.106
Neg logit contributions
working-0.104
rier-0.101
istered-0.098
nam-0.094
 bored-0.093
Token fishing
Token ID12478
Feature activation-2.77e-02

Pos logit contributions
nob+0.078
ad+0.076
 dial+0.070
p+0.067
 Looking+0.067
Neg logit contributions
working-0.068
rier-0.067
istered-0.066
ishy-0.060
 sweaty-0.058
Token rod
Token ID15299
Feature activation-1.73e-02

Pos logit contributions
 dial+0.047
nob+0.047
 Looking+0.045
 peek+0.044
ad+0.043
Neg logit contributions
rier-0.038
working-0.035
 goals-0.032
istered-0.031
 kicker-0.030
Token and
Token ID290
Feature activation-1.24e-02

Pos logit contributions
 dial+0.012
 peek+0.012
nob+0.011
 turned+0.010
ad+0.010
Neg logit contributions
rier-0.040
working-0.039
istered-0.039
ishy-0.036
 goals-0.036
Token swoop
Token ID38527
Feature activation-1.84e-03

Pos logit contributions
 dial+0.014
 peek+0.014
nob+0.014
ad+0.013
 Looking+0.013
Neg logit contributions
rier-0.023
working-0.023
istered-0.022
ishy-0.020
 goals-0.020
Token said
Token ID531
Feature activation+8.85e-03

Pos logit contributions
rier+0.020
working+0.020
istered+0.019
ishy+0.018
 kicker+0.018
Neg logit contributions
nob-0.010
 dial-0.010
 peek-0.010
ad-0.009
 Looking-0.009
Token,
Token ID11
Feature activation-1.46e-02

Pos logit contributions
istered+0.018
working+0.018
rier+0.017
ishy+0.016
 goals+0.016
Neg logit contributions
 peek-0.009
 dial-0.009
nob-0.009
 turned-0.008
ad-0.008
Token "
Token ID366
Feature activation+7.85e-03

Pos logit contributions
nob+0.022
 dial+0.021
 peek+0.021
ad+0.021
 turned+0.019
Neg logit contributions
rier-0.023
working-0.021
istered-0.020
 bored-0.018
der-0.018
TokenPlease
Token ID5492
Feature activation-2.05e-02

Pos logit contributions
rier+0.013
working+0.013
istered+0.013
ishy+0.012
 goals+0.011
Neg logit contributions
 dial-0.011
 peek-0.010
nob-0.010
 turned-0.010
ad-0.009
Token let
Token ID1309
Feature activation-3.58e-03

Pos logit contributions
 dial+0.029
nob+0.028
 peek+0.028
 Looking+0.026
ad+0.026
Neg logit contributions
rier-0.032
working-0.031
istered-0.031
 goals-0.027
ishy-0.027
Token me
Token ID502
Feature activation-7.76e-02

Pos logit contributions
 peek+0.003
 dial+0.003
nob+0.003
 turned+0.003
ad+0.003
Neg logit contributions
rier-0.008
istered-0.008
working-0.008
ishy-0.007
nam-0.007
Token march
Token ID9960
Feature activation-7.54e-03

Pos logit contributions
nob+0.098
 dial+0.095
 Looking+0.090
ad+0.088
 peek+0.084
Neg logit contributions
working-0.132
rier-0.124
istered-0.119
ishy-0.116
 bored-0.115
Token,
Token ID11
Feature activation-2.28e-02

Pos logit contributions
 peek+0.008
 dial+0.008
nob+0.008
 turned+0.008
ad+0.007
Neg logit contributions
istered-0.015
rier-0.014
working-0.014
ishy-0.013
 goals-0.013
Token it
Token ID340
Feature activation-2.50e-02

Pos logit contributions
 dial+0.032
 peek+0.031
nob+0.031
 turned+0.029
ad+0.029
Neg logit contributions
rier-0.037
working-0.036
istered-0.036
ishy-0.033
 goals-0.032
Token is
Token ID318
Feature activation-2.74e-02

Pos logit contributions
 dial+0.032
 peek+0.032
nob+0.030
 turned+0.029
ad+0.028
Neg logit contributions
rier-0.044
working-0.043
istered-0.043
ishy-0.039
 goals-0.038
Token so
Token ID523
Feature activation-7.33e-04

Pos logit contributions
 dial+0.040
 peek+0.040
nob+0.039
 turned+0.037
ad+0.037
Neg logit contributions
rier-0.043
working-0.042
istered-0.041
ishy-0.037
 goals-0.037
TokenHe
Token ID1544
Feature activation-7.92e-03

Pos logit contributions
 dial+0.003
 peek+0.003
nob+0.003
 turned+0.003
 opened+0.003
Neg logit contributions
working-0.004
rier-0.004
istered-0.004
 goals-0.004
 kicker-0.003
Token would
Token ID561
Feature activation+4.60e-03

Pos logit contributions
nob+0.010
 dial+0.009
 peek+0.009
 Looking+0.009
ad+0.009
Neg logit contributions
working-0.013
rier-0.013
istered-0.013
 goals-0.012
ishy-0.012
Token still
Token ID991
Feature activation-1.88e-02

Pos logit contributions
working+0.008
rier+0.008
istered+0.008
 goals+0.007
ishy+0.007
Neg logit contributions
 dial-0.006
nob-0.005
 peek-0.005
 Looking-0.005
 turned-0.005
Token take
Token ID1011
Feature activation+5.33e-03

Pos logit contributions
 dial+0.023
nob+0.023
 Looking+0.021
 peek+0.020
 Turning+0.020
Neg logit contributions
working-0.032
rier-0.031
istered-0.031
 goals-0.029
ishy-0.029
Token his
Token ID465
Feature activation-5.71e-02

Pos logit contributions
rier+0.009
working+0.008
istered+0.008
 goals+0.008
ishy+0.007
Neg logit contributions
 dial-0.007
 peek-0.007
nob-0.007
 Looking-0.007
 turned-0.006
Token long
Token ID890
Feature activation-7.68e-02

Pos logit contributions
nob+0.081
 dial+0.076
ad+0.075
 Looking+0.072
 peek+0.070
Neg logit contributions
working-0.093
ishy-0.082
istered-0.081
rier-0.079
 bored-0.078
Token stroll
Token ID41360
Feature activation-2.82e-03

Pos logit contributions
nob+0.108
 dial+0.108
 Looking+0.105
 Turning+0.102
Turn+0.100
Neg logit contributions
working-0.126
ishy-0.105
 guys-0.100
 muscles-0.097
 rainy-0.095
Tokens
Token ID82
Feature activation-2.16e-02

Pos logit contributions
 peek+0.003
 dial+0.002
 turned+0.002
nob+0.002
 opened+0.002
Neg logit contributions
istered-0.006
rier-0.006
working-0.006
ivery-0.006
ishy-0.005
Token through
Token ID832
Feature activation-5.15e-03

Pos logit contributions
 dial+0.025
nob+0.024
 peek+0.024
 Looking+0.022
ad+0.022
Neg logit contributions
rier-0.040
working-0.039
istered-0.038
 goals-0.036
ishy-0.036
Token the
Token ID262
Feature activation-7.56e-03

Pos logit contributions
 dial+0.006
 peek+0.006
nob+0.006
 turned+0.005
ad+0.005
Neg logit contributions
rier-0.010
working-0.010
istered-0.009
 goals-0.009
ishy-0.009
Token park
Token ID3952
Feature activation+1.77e-02

Pos logit contributions
nob+0.012
 dial+0.012
 peek+0.011
ad+0.010
 Looking+0.010
Neg logit contributions
working-0.011
 goals-0.010
rier-0.010
istered-0.010
ishy-0.010
Token the
Token ID262
Feature activation-3.01e-02

Pos logit contributions
istered+0.019
working+0.018
rier+0.018
ivery+0.018
ishy+0.017
Neg logit contributions
 peek-0.007
 opened-0.006
 turned-0.006
:-0.006
 dial-0.005
Token bear
Token ID6842
Feature activation-6.05e-03

Pos logit contributions
 dial+0.041
 peek+0.040
nob+0.038
 turned+0.037
ad+0.036
Neg logit contributions
rier-0.053
istered-0.051
working-0.050
ishy-0.045
 goals-0.045
Token showed
Token ID3751
Feature activation+2.40e-02

Pos logit contributions
 dial+0.006
 peek+0.006
nob+0.005
ad+0.005
 turned+0.005
Neg logit contributions
rier-0.012
working-0.012
istered-0.012
ishy-0.011
 goals-0.011
Token everyone
Token ID2506
Feature activation-3.35e-02

Pos logit contributions
istered+0.040
working+0.038
rier+0.037
ivery+0.036
ishy+0.035
Neg logit contributions
 dial-0.036
 peek-0.036
ad-0.034
nob-0.033
 turned-0.033
Token his
Token ID465
Feature activation-5.34e-02

Pos logit contributions
 dial+0.039
 peek+0.039
nob+0.037
 turned+0.035
ad+0.034
Neg logit contributions
rier-0.063
working-0.061
istered-0.061
ishy-0.055
 goals-0.055
Token new
Token ID649
Feature activation-7.56e-02

Pos logit contributions
 dial+0.080
 peek+0.079
nob+0.079
 Looking+0.074
ad+0.074
Neg logit contributions
working-0.079
rier-0.078
istered-0.078
ishy-0.072
 goals-0.069
Token boots
Token ID14412
Feature activation-1.86e-03

Pos logit contributions
 dial+0.112
nob+0.112
 peek+0.109
 Looking+0.107
 Turning+0.105
Neg logit contributions
working-0.108
rier-0.104
istered-0.100
ishy-0.096
 goals-0.096
Token.
Token ID13
Feature activation+9.18e-03

Pos logit contributions
 peek+0.001
 dial+0.001
nob+0.001
 turned+0.001
 opened+0.001
Neg logit contributions
rier-0.004
istered-0.004
working-0.004
ishy-0.004
 goals-0.004
Token Everyone
Token ID11075
Feature activation-7.27e-04

Pos logit contributions
rier+0.016
working+0.015
istered+0.015
ishy+0.014
 goals+0.014
Neg logit contributions
 dial-0.012
 peek-0.012
nob-0.012
 turned-0.011
ad-0.011
Token was
Token ID373
Feature activation-1.03e-03

Pos logit contributions
nob+0.001
 dial+0.001
 peek+0.001
ad+0.001
 Looking+0.001
Neg logit contributions
working-0.001
rier-0.001
istered-0.001
 bored-0.001
 goals-0.001
Token so
Token ID523
Feature activation+1.47e-02

Pos logit contributions
 dial+0.001
 peek+0.001
nob+0.001
 turned+0.001
ad+0.001
Neg logit contributions
rier-0.002
working-0.002
istered-0.002
ishy-0.001
 goals-0.001
Token park
Token ID3952
Feature activation+1.39e-02

Pos logit contributions
rier+0.005
working+0.005
istered+0.005
ishy+0.004
ivery+0.004
Neg logit contributions
 peek-0.003
 dial-0.003
 turned-0.003
nob-0.003
ad-0.003
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
istered+0.028
rier+0.028
working+0.028
ishy+0.026
ivery+0.026
Neg logit contributions
 peek-0.015
 dial-0.014
 turned-0.013
nob-0.013
ad-0.013
Token Timothy
Token ID22283
Feature activation-2.30e-03

Pos logit contributions
nob+0.027
 dial+0.027
 peek+0.027
 spell+0.024
ad+0.024
Neg logit contributions
working-0.032
rier-0.032
istered-0.032
 goals-0.030
attered-0.029
Token gave
Token ID2921
Feature activation+8.73e-03

Pos logit contributions
 dial+0.002
 peek+0.002
nob+0.002
ad+0.002
 Looking+0.002
Neg logit contributions
working-0.005
rier-0.005
istered-0.005
ishy-0.004
 goals-0.004
Token a
Token ID257
Feature activation-4.55e-02

Pos logit contributions
rier+0.014
working+0.013
istered+0.013
ishy+0.012
 goals+0.011
Neg logit contributions
 dial-0.013
 peek-0.013
nob-0.013
 turned-0.012
ad-0.012
Token final
Token ID2457
Feature activation-7.52e-02

Pos logit contributions
nob+0.081
ad+0.073
 dial+0.073
ran+0.067
 Looking+0.067
Neg logit contributions
working-0.058
istered-0.057
rier-0.056
ishy-0.053
 kicker-0.051
Token loud
Token ID7812
Feature activation-5.29e-02

Pos logit contributions
nob+0.108
 dial+0.092
ran+0.086
 unlocks+0.086
ad+0.084
Neg logit contributions
working-0.121
ishy-0.112
rier-0.111
 kicker-0.108
istered-0.106
Token blow
Token ID6611
Feature activation-2.83e-02

Pos logit contributions
nob+0.071
 dial+0.066
 peek+0.059
ran+0.057
 unlocked+0.057
Neg logit contributions
rier-0.092
working-0.087
ishy-0.077
istered-0.076
 kicker-0.074
Token on
Token ID319
Feature activation+3.43e-04

Pos logit contributions
 dial+0.036
nob+0.035
 peek+0.035
 Looking+0.031
 turned+0.031
Neg logit contributions
rier-0.052
working-0.048
istered-0.047
ishy-0.045
 goals-0.044
Token the
Token ID262
Feature activation-1.30e-02

Pos logit contributions
istered+0.001
rier+0.001
working+0.001
ishy+0.001
ivery+0.001
Neg logit contributions
 dial-0.000
 peek-0.000
 turned-0.000
nob-0.000
ad-0.000
Token whistle
Token ID16121
Feature activation-1.04e-02

Pos logit contributions
 peek+0.017
 dial+0.017
nob+0.016
 turned+0.015
ad+0.015
Neg logit contributions
rier-0.023
working-0.023
istered-0.023
ishy-0.020
 goals-0.020
Token's
Token ID338
Feature activation-1.75e-02

Pos logit contributions
 dial+0.003
 peek+0.003
nob+0.003
ad+0.003
 turned+0.003
Neg logit contributions
rier-0.006
working-0.006
istered-0.006
ishy-0.006
 goals-0.006
Token mom
Token ID1995
Feature activation-1.70e-02

Pos logit contributions
nob+0.031
 dial+0.030
 peek+0.029
 Looking+0.028
ad+0.028
Neg logit contributions
rier-0.023
istered-0.022
working-0.021
ishy-0.019
 goals-0.019
Token said
Token ID531
Feature activation+4.24e-03

Pos logit contributions
nob+0.018
 dial+0.017
 Looking+0.016
ad+0.016
 peek+0.016
Neg logit contributions
istered-0.031
working-0.031
rier-0.029
 bored-0.029
 sweaty-0.028
Token,
Token ID11
Feature activation-1.77e-02

Pos logit contributions
istered+0.010
working+0.010
rier+0.010
ivery+0.009
ishy+0.009
Neg logit contributions
 peek-0.003
 dial-0.003
 turned-0.003
 opened-0.003
ad-0.003
Token "
Token ID366
Feature activation-2.62e-03

Pos logit contributions
nob+0.026
 dial+0.026
 peek+0.026
ad+0.025
 turned+0.023
Neg logit contributions
rier-0.027
working-0.026
istered-0.025
 bored-0.022
 goals-0.022
TokenThis
Token ID1212
Feature activation-7.48e-02

Pos logit contributions
 dial+0.004
nob+0.004
 peek+0.004
 turned+0.003
 call+0.003
Neg logit contributions
working-0.004
rier-0.004
istered-0.004
attered-0.004
ishy-0.004
Token is
Token ID318
Feature activation-2.94e-02

Pos logit contributions
nob+0.091
 pat+0.082
wit+0.082
 dial+0.082
 Looking+0.080
Neg logit contributions
rier-0.119
working-0.117
 bored-0.109
ishy-0.107
 guys-0.107
Token a
Token ID257
Feature activation-3.29e-02

Pos logit contributions
 peek+0.041
 dial+0.041
nob+0.040
ad+0.038
 Looking+0.037
Neg logit contributions
working-0.047
rier-0.046
istered-0.045
 bored-0.042
 goals-0.041
Token magic
Token ID5536
Feature activation-6.19e-02

Pos logit contributions
nob+0.055
 dial+0.051
ad+0.051
 peek+0.048
 Looking+0.048
Neg logit contributions
rier-0.045
working-0.044
istered-0.044
 bored-0.040
ishy-0.039
Token f
Token ID277
Feature activation-1.53e-02

Pos logit contributions
nob+0.084
 Looking+0.079
ad+0.076
 dial+0.076
 peek+0.074
Neg logit contributions
rier-0.106
working-0.103
istered-0.087
ishy-0.087
 guys-0.086
Tokenauc
Token ID14272
Feature activation-6.74e-03

Pos logit contributions
 dial+0.024
 peek+0.024
nob+0.023
 turned+0.022
 Looking+0.022
Neg logit contributions
rier-0.023
working-0.022
istered-0.022
ishy-0.020
attered-0.019
Token
Token ID129
Feature activation+3.39e-03

Pos logit contributions
 peek+0.031
 dial+0.030
nob+0.029
 turned+0.028
 Looking+0.027
Neg logit contributions
rier-0.042
working-0.039
istered-0.038
ishy-0.036
 goals-0.035
Token
Token ID241
Feature activation-1.86e-02

Pos logit contributions
rier+0.004
istered+0.004
working+0.004
nam+0.004
ishy+0.004
Neg logit contributions
 dial-0.006
 peek-0.006
nob-0.006
ad-0.006
 turned-0.006
TokenIf
Token ID1532
Feature activation-1.61e-02

Pos logit contributions
 dial+0.024
 peek+0.023
nob+0.023
 turned+0.021
ad+0.021
Neg logit contributions
working-0.032
rier-0.032
istered-0.031
ishy-0.028
 goals-0.028
Token we
Token ID356
Feature activation-2.40e-02

Pos logit contributions
 dial+0.028
 peek+0.027
nob+0.027
 turned+0.025
 Looking+0.025
Neg logit contributions
rier-0.021
working-0.021
istered-0.020
 goals-0.017
ishy-0.017
Token use
Token ID779
Feature activation-5.04e-02

Pos logit contributions
 peek+0.031
 dial+0.030
nob+0.029
 turned+0.028
ad+0.027
Neg logit contributions
rier-0.044
working-0.042
istered-0.042
ishy-0.037
 goals-0.037
Token this
Token ID428
Feature activation-7.46e-02

Pos logit contributions
 peek+0.066
 dial+0.065
nob+0.065
ad+0.060
 Looking+0.060
Neg logit contributions
rier-0.084
working-0.082
istered-0.082
 goals-0.075
ishy-0.074
Token oil
Token ID3056
Feature activation-1.10e-02

Pos logit contributions
 peek+0.107
ad+0.106
nob+0.106
 dial+0.105
 Looking+0.101
Neg logit contributions
working-0.113
rier-0.110
istered-0.107
ishy-0.102
 goals-0.094
Token,
Token ID11
Feature activation-4.10e-02

Pos logit contributions
 peek+0.010
 dial+0.010
nob+0.010
 turned+0.010
ad+0.009
Neg logit contributions
rier-0.023
istered-0.023
working-0.022
ishy-0.021
ivery-0.021
Token we
Token ID356
Feature activation-1.83e-02

Pos logit contributions
 dial+0.063
 peek+0.063
nob+0.061
ad+0.058
 turned+0.058
Neg logit contributions
rier-0.061
working-0.059
istered-0.058
ishy-0.052
 goals-0.051
Token can
Token ID460
Feature activation-2.15e-02

Pos logit contributions
 peek+0.023
 dial+0.023
nob+0.021
 turned+0.021
ad+0.020
Neg logit contributions
rier-0.034
istered-0.032
working-0.032
ishy-0.029
 goals-0.029
Token make
Token ID787
Feature activation-2.02e-02

Pos logit contributions
 peek+0.022
 dial+0.022
nob+0.020
 turned+0.019
ad+0.019
Neg logit contributions
rier-0.045
working-0.043
istered-0.043
ishy-0.040
 goals-0.039
Token to
Token ID284
Feature activation+4.53e-03

Pos logit contributions
 dial+0.028
ad+0.028
 Looking+0.027
nob+0.027
 peek+0.026
Neg logit contributions
working-0.040
 bored-0.035
rier-0.035
istered-0.034
ishy-0.032
Token his
Token ID465
Feature activation-1.83e-02

Pos logit contributions
rier+0.007
working+0.007
istered+0.006
 bored+0.006
 sweaty+0.006
Neg logit contributions
nob-0.006
 dial-0.006
 Looking-0.006
 peek-0.006
 Turning-0.006
Token work
Token ID670
Feature activation-5.75e-04

Pos logit contributions
 dial+0.027
nob+0.026
 peek+0.026
ad+0.025
 Looking+0.025
Neg logit contributions
rier-0.028
working-0.028
istered-0.028
 goals-0.025
ishy-0.025
Token and
Token ID290
Feature activation-1.16e-02

Pos logit contributions
 dial+0.001
 peek+0.001
nob+0.001
 Looking+0.000
ad+0.000
Neg logit contributions
rier-0.001
working-0.001
istered-0.001
 goals-0.001
ishy-0.001
Token removes
Token ID20694
Feature activation-3.67e-03

Pos logit contributions
nob+0.011
ad+0.011
 dial+0.011
 peek+0.011
 Looking+0.010
Neg logit contributions
working-0.022
rier-0.022
istered-0.022
 bored-0.021
 goals-0.020
Token the
Token ID262
Feature activation-7.43e-02

Pos logit contributions
 dial+0.004
 peek+0.004
nob+0.004
 turned+0.004
ad+0.004
Neg logit contributions
rier-0.007
working-0.007
istered-0.006
ishy-0.006
 goals-0.006
Token tube
Token ID12403
Feature activation-8.58e-03

Pos logit contributions
ad+0.100
nob+0.099
 dial+0.098
 Looking+0.095
 peek+0.095
Neg logit contributions
rier-0.119
working-0.116
istered-0.113
ishy-0.108
 bored-0.107
Token.
Token ID13
Feature activation+3.66e-03

Pos logit contributions
 dial+0.009
 peek+0.009
nob+0.008
ad+0.008
 Looking+0.008
Neg logit contributions
rier-0.017
working-0.017
istered-0.017
ishy-0.015
 goals-0.015
Token Tim
Token ID5045
Feature activation-1.59e-02

Pos logit contributions
rier+0.005
working+0.005
istered+0.005
 goals+0.005
ishy+0.004
Neg logit contributions
 dial-0.006
 peek-0.006
nob-0.006
ad-0.005
 turned-0.005
Token and
Token ID290
Feature activation-1.38e-02

Pos logit contributions
 peek+0.014
 dial+0.014
nob+0.014
 Looking+0.013
ad+0.013
Neg logit contributions
working-0.032
rier-0.031
istered-0.031
 goals-0.030
ishy-0.029
Token Mia
Token ID32189
Feature activation-1.01e-02

Pos logit contributions
 dial+0.015
nob+0.015
 peek+0.014
 Looking+0.013
 Turning+0.013
Neg logit contributions
working-0.025
rier-0.025
istered-0.024
 goals-0.024
 kicker-0.023
Token "
Token ID366
Feature activation+1.41e-02

Pos logit contributions
nob+0.032
 dial+0.032
 peek+0.031
ad+0.031
 turned+0.028
Neg logit contributions
rier-0.036
working-0.033
istered-0.032
 bored-0.029
 goals-0.029
TokenMom
Token ID29252
Feature activation-2.79e-02

Pos logit contributions
rier+0.022
working+0.022
istered+0.022
attered+0.020
ishy+0.020
Neg logit contributions
 dial-0.020
 peek-0.019
nob-0.018
ad-0.018
 turned-0.018
Tokenmy
Token ID1820
Feature activation-1.83e-02

Pos logit contributions
 dial+0.031
nob+0.031
 peek+0.030
 Looking+0.028
ad+0.027
Neg logit contributions
working-0.052
rier-0.051
istered-0.050
ishy-0.046
 kicker-0.045
Token,
Token ID11
Feature activation-2.92e-02

Pos logit contributions
 dial+0.020
 peek+0.020
nob+0.019
 turned+0.018
ad+0.018
Neg logit contributions
rier-0.035
working-0.034
istered-0.034
ishy-0.031
 goals-0.031
Token let
Token ID1309
Feature activation-1.19e-02

Pos logit contributions
nob+0.038
 dial+0.038
ad+0.036
 peek+0.036
 Looking+0.035
Neg logit contributions
rier-0.048
working-0.045
istered-0.045
ishy-0.041
 goals-0.041
Token me
Token ID502
Feature activation-7.40e-02

Pos logit contributions
 peek+0.013
 dial+0.013
nob+0.012
 turned+0.011
 call+0.011
Neg logit contributions
rier-0.025
working-0.025
istered-0.024
ishy-0.023
 goals-0.022
Token support
Token ID1104
Feature activation-5.99e-03

Pos logit contributions
nob+0.084
 dial+0.083
ad+0.080
 Looking+0.077
 fore+0.075
Neg logit contributions
working-0.131
istered-0.126
rier-0.126
ishy-0.120
 kicker-0.115
Token you
Token ID345
Feature activation-3.34e-02

Pos logit contributions
 dial+0.009
 peek+0.009
nob+0.009
 turned+0.009
ad+0.009
Neg logit contributions
rier-0.009
working-0.009
istered-0.008
ishy-0.008
 goals-0.007
Token so
Token ID523
Feature activation+7.15e-03

Pos logit contributions
 peek+0.039
 dial+0.039
nob+0.037
 turned+0.034
 call+0.033
Neg logit contributions
istered-0.063
rier-0.062
working-0.061
ishy-0.058
 goals-0.056
Token you
Token ID345
Feature activation-2.69e-02

Pos logit contributions
istered+0.015
ishy+0.014
rier+0.014
working+0.014
wy+0.013
Neg logit contributions
 peek-0.008
 be-0.007
 turned-0.007
 called-0.006
 opened-0.006
Token don
Token ID836
Feature activation-2.28e-02

Pos logit contributions
 peek+0.033
 dial+0.032
 turned+0.030
nob+0.030
 call+0.029
Neg logit contributions
rier-0.051
istered-0.050
working-0.049
nam-0.045
ishy-0.044
Token understand
Token ID1833
Feature activation+2.47e-03

Pos logit contributions
rier+0.002
working+0.002
istered+0.002
nam+0.002
 goals+0.002
Neg logit contributions
 peek-0.001
 dial-0.001
 turned-0.001
 call-0.001
nob-0.001
Token.
Token ID13
Feature activation+2.06e-02

Pos logit contributions
working+0.006
rier+0.006
istered+0.005
ishy+0.005
attered+0.005
Neg logit contributions
 dial-0.002
 peek-0.002
 turned-0.002
nob-0.002
ad-0.002
Token We
Token ID775
Feature activation+1.48e-04

Pos logit contributions
rier+0.034
working+0.033
istered+0.033
ishy+0.030
 goals+0.029
Neg logit contributions
 dial-0.029
 peek-0.029
nob-0.027
 turned-0.026
ad-0.026
Token will
Token ID481
Feature activation-5.10e-03

Pos logit contributions
rier+0.000
working+0.000
istered+0.000
ishy+0.000
 goals+0.000
Neg logit contributions
 peek-0.000
 dial-0.000
 turned-0.000
nob-0.000
 call-0.000
Token share
Token ID2648
Feature activation+9.23e-04

Pos logit contributions
 dial+0.005
nob+0.005
 peek+0.005
 Looking+0.005
ad+0.005
Neg logit contributions
rier-0.010
working-0.010
istered-0.010
 goals-0.009
ishy-0.009
Token the
Token ID262
Feature activation-7.37e-02

Pos logit contributions
working+0.002
rier+0.002
istered+0.002
ishy+0.002
ivery+0.002
Neg logit contributions
 dial-0.001
 peek-0.001
nob-0.001
 turned-0.001
ad-0.001
Token tube
Token ID12403
Feature activation-1.02e-03

Pos logit contributions
nob+0.109
 dial+0.107
p+0.103
 peek+0.102
 pat+0.102
Neg logit contributions
 goals-0.099
working-0.096
rier-0.096
 bored-0.094
istered-0.093
Token.
Token ID13
Feature activation+2.50e-02

Pos logit contributions
 peek+0.001
nob+0.001
 dial+0.001
 turned+0.000
ad+0.000
Neg logit contributions
istered-0.002
working-0.002
rier-0.002
ivery-0.002
ishy-0.002
Token We
Token ID775
Feature activation+1.17e-03

Pos logit contributions
rier+0.042
working+0.040
istered+0.040
ishy+0.036
 goals+0.036
Neg logit contributions
 dial-0.034
 peek-0.034
nob-0.033
 turned-0.031
ad-0.031
Token will
Token ID481
Feature activation-4.37e-03

Pos logit contributions
rier+0.002
istered+0.002
working+0.002
nam+0.002
ishy+0.002
Neg logit contributions
 peek-0.001
 dial-0.001
 turned-0.001
nob-0.001
 call-0.001
Token be
Token ID307
Feature activation+2.93e-03

Pos logit contributions
 dial+0.004
nob+0.004
 peek+0.004
 Looking+0.004
ad+0.004
Neg logit contributions
rier-0.009
working-0.009
istered-0.008
 goals-0.008
ishy-0.008
Token ran
Token ID4966
Feature activation+1.05e-02

Pos logit contributions
rier+0.000
istered+0.000
working+0.000
ishy+0.000
 goals+0.000
Neg logit contributions
 peek-0.000
 dial-0.000
nob-0.000
 turned-0.000
ad-0.000
Token off
Token ID572
Feature activation-3.71e-04

Pos logit contributions
rier+0.017
working+0.016
istered+0.016
ishy+0.014
 goals+0.014
Neg logit contributions
 dial-0.015
 peek-0.015
nob-0.015
 turned-0.014
ad-0.014
Token with
Token ID351
Feature activation+1.25e-02

Pos logit contributions
 dial+0.000
 peek+0.000
nob+0.000
 turned+0.000
ad+0.000
Neg logit contributions
rier-0.001
working-0.001
istered-0.001
ishy-0.001
 goals-0.001
Token her
Token ID607
Feature activation-2.49e-02

Pos logit contributions
working+0.029
rier+0.029
istered+0.028
attered+0.027
ishy+0.026
Neg logit contributions
 peek-0.012
ad-0.011
 dial-0.011
 turned-0.010
 call-0.010
Token shiny
Token ID22441
Feature activation-5.91e-02

Pos logit contributions
nob+0.038
 dial+0.038
 peek+0.037
 Looking+0.035
ad+0.035
Neg logit contributions
working-0.037
rier-0.037
istered-0.036
 goals-0.032
ishy-0.032
Token new
Token ID649
Feature activation-7.35e-02

Pos logit contributions
nob+0.079
 dial+0.077
 peek+0.075
 Looking+0.073
Turn+0.068
Neg logit contributions
working-0.099
rier-0.094
ishy-0.091
istered-0.085
 goals-0.083
Token pipe
Token ID12656
Feature activation+7.04e-03

Pos logit contributions
nob+0.108
 dial+0.102
 Looking+0.094
 peek+0.094
 grant+0.094
Neg logit contributions
working-0.116
ishy-0.105
rier-0.101
istered-0.099
 goals-0.094
Token.
Token ID13
Feature activation-6.87e-03

Pos logit contributions
rier+0.014
istered+0.014
working+0.014
ishy+0.013
 goals+0.012
Neg logit contributions
 peek-0.007
 dial-0.007
nob-0.007
 turned-0.007
ad-0.006
Token<|endoftext|>
Token ID50256
Feature activation-1.22e-02

Pos logit contributions
 dial+0.006
 peek+0.006
nob+0.005
 turned+0.005
ad+0.005
Neg logit contributions
rier-0.015
working-0.015
istered-0.015
 goals-0.013
ishy-0.013
TokenOnce
Token ID7454
Feature activation+1.04e-02

Pos logit contributions
 dial+0.015
 peek+0.013
nob+0.013
 call+0.012
ad+0.011
Neg logit contributions
working-0.021
rier-0.020
 goals-0.020
istered-0.020
 bored-0.019
Token upon
Token ID2402
Feature activation+4.79e-03

Pos logit contributions
rier+0.024
istered+0.023
working+0.022
ishy+0.021
ivery+0.021
Neg logit contributions
 peek-0.009
 turned-0.008
 opened-0.008
 dial-0.007
ad-0.007
Token's
Token ID338
Feature activation-2.68e-03

Pos logit contributions
 peek+0.006
 dial+0.006
 turned+0.005
nob+0.005
 opened+0.005
Neg logit contributions
rier-0.012
istered-0.011
working-0.011
ishy-0.010
 goals-0.010
Token mom
Token ID1995
Feature activation-2.10e-02

Pos logit contributions
nob+0.005
 dial+0.004
 peek+0.004
 Looking+0.004
ad+0.004
Neg logit contributions
rier-0.004
working-0.003
istered-0.003
ishy-0.003
 goals-0.003
Token gave
Token ID2921
Feature activation+4.33e-03

Pos logit contributions
nob+0.024
 Looking+0.023
 dial+0.022
ad+0.022
 peek+0.021
Neg logit contributions
working-0.039
istered-0.035
 bored-0.034
rier-0.034
 sweaty-0.033
Token her
Token ID607
Feature activation-4.73e-02

Pos logit contributions
rier+0.007
working+0.007
istered+0.007
ishy+0.006
 goals+0.006
Neg logit contributions
 dial-0.006
 peek-0.006
nob-0.006
 turned-0.006
ad-0.006
Token a
Token ID257
Feature activation-3.57e-02

Pos logit contributions
 dial+0.056
nob+0.056
 peek+0.054
ad+0.052
 Looking+0.052
Neg logit contributions
working-0.082
rier-0.080
istered-0.079
ishy-0.075
 goals-0.074
Token new
Token ID649
Feature activation-7.34e-02

Pos logit contributions
nob+0.065
ad+0.062
ran+0.058
p+0.056
 dial+0.055
Neg logit contributions
working-0.042
istered-0.041
rier-0.038
ishy-0.038
 handsome-0.037
Token toy
Token ID13373
Feature activation-1.95e-02

Pos logit contributions
nob+0.122
 Looking+0.110
ran+0.109
 dial+0.109
 Turning+0.107
Neg logit contributions
working-0.098
rier-0.091
 favorite-0.087
 kicker-0.086
ishy-0.085
Token.
Token ID13
Feature activation-6.81e-03

Pos logit contributions
 dial+0.025
nob+0.025
 peek+0.024
 Looking+0.023
ad+0.022
Neg logit contributions
rier-0.034
working-0.033
istered-0.032
ishy-0.029
 goals-0.029
Token It
Token ID632
Feature activation-2.22e-02

Pos logit contributions
 dial+0.010
nob+0.010
ad+0.010
 peek+0.010
p+0.009
Neg logit contributions
rier-0.010
istered-0.010
working-0.010
ishy-0.009
 goals-0.009
Token was
Token ID373
Feature activation-1.89e-02

Pos logit contributions
 dial+0.017
nob+0.016
 peek+0.015
ad+0.015
 Looking+0.014
Neg logit contributions
istered-0.047
working-0.047
rier-0.046
ishy-0.043
 bored-0.043
Token a
Token ID257
Feature activation-1.19e-02

Pos logit contributions
 dial+0.027
nob+0.027
 peek+0.026
 Looking+0.025
 Turning+0.024
Neg logit contributions
istered-0.028
rier-0.028
working-0.028
 bored-0.025
 goals-0.025
Token saf
Token ID1932
Feature activation+2.45e-02

Pos logit contributions
 dial+0.020
 Looking+0.020
nob+0.020
 Turning+0.020
Turn+0.019
Neg logit contributions
working-0.018
 guys-0.016
 goals-0.015
rier-0.014
 favorite-0.014
Tokenari
Token ID2743
Feature activation+1.14e-02

Pos logit contributions
rier+0.042
working+0.042
istered+0.040
 goals+0.037
ishy+0.036
Neg logit contributions
 dial-0.032
 peek-0.031
nob-0.030
 turned-0.029
 Looking-0.028
Token.
Token ID13
Feature activation+1.66e-02

Pos logit contributions
istered+0.024
rier+0.022
working+0.022
ishy+0.021
ivery+0.021
Neg logit contributions
 peek-0.013
 dial-0.012
nob-0.012
 called-0.011
 call-0.011
Token Please
Token ID4222
Feature activation-1.34e-02

Pos logit contributions
rier+0.025
working+0.024
istered+0.024
 goals+0.021
ishy+0.021
Neg logit contributions
 dial-0.024
 peek-0.024
nob-0.024
ad-0.023
 turned-0.023
Token let
Token ID1309
Feature activation+1.11e-02

Pos logit contributions
 dial+0.014
 peek+0.013
nob+0.013
 Looking+0.012
ad+0.012
Neg logit contributions
rier-0.026
working-0.026
istered-0.026
ishy-0.024
 goals-0.023
Token me
Token ID502
Feature activation-7.34e-02

Pos logit contributions
istered+0.029
rier+0.028
ishy+0.027
working+0.027
nam+0.026
Neg logit contributions
 peek-0.009
 dial-0.008
nob-0.007
 call-0.007
 turned-0.007
Token go
Token ID467
Feature activation-2.71e-02

Pos logit contributions
nob+0.089
 dial+0.087
 Looking+0.084
ad+0.082
 Turning+0.078
Neg logit contributions
working-0.127
rier-0.121
istered-0.116
ishy-0.113
 bored-0.111
Token,
Token ID11
Feature activation-1.27e-02

Pos logit contributions
 dial+0.041
 Looking+0.040
nob+0.040
 peek+0.039
ad+0.038
Neg logit contributions
working-0.040
rier-0.038
istered-0.034
 bored-0.033
ishy-0.033
Token mum
Token ID25682
Feature activation-3.03e-02

Pos logit contributions
 peek+0.016
 dial+0.016
nob+0.015
 turned+0.015
ad+0.014
Neg logit contributions
rier-0.022
working-0.022
istered-0.022
ishy-0.020
 goals-0.019
Token."
Token ID526
Feature activation+4.65e-03

Pos logit contributions
 dial+0.044
 peek+0.044
nob+0.042
 turned+0.040
ad+0.040
Neg logit contributions
rier-0.048
working-0.047
istered-0.046
ishy-0.042
 goals-0.041
Token
Token ID198
Feature activation-5.37e-03

Pos logit contributions
istered+0.009
working+0.009
rier+0.009
 goals+0.008
 bored+0.008
Neg logit contributions
nob-0.004
 peek-0.004
 dial-0.004
ad-0.004
p-0.004
Token beautiful
Token ID4950
Feature activation-4.21e-02

Pos logit contributions
 dial+0.034
nob+0.033
 peek+0.033
ad+0.032
 turned+0.031
Neg logit contributions
rier-0.035
istered-0.034
working-0.034
ishy-0.030
 goals-0.029
Token toy
Token ID13373
Feature activation-2.23e-02

Pos logit contributions
nob+0.060
 dial+0.060
 peek+0.058
ad+0.055
 Looking+0.054
Neg logit contributions
working-0.065
rier-0.062
istered-0.057
ishy-0.055
 kicker-0.052
Token.
Token ID13
Feature activation-3.41e-03

Pos logit contributions
 dial+0.029
 peek+0.029
nob+0.028
ad+0.026
 turned+0.026
Neg logit contributions
rier-0.038
working-0.037
istered-0.037
ishy-0.034
 goals-0.033
Token Lily
Token ID20037
Feature activation-5.98e-03

Pos logit contributions
 dial+0.005
 peek+0.004
nob+0.004
 turned+0.004
 Looking+0.004
Neg logit contributions
rier-0.006
working-0.006
istered-0.006
ishy-0.005
 goals-0.005
Token felt
Token ID2936
Feature activation-4.60e-03

Pos logit contributions
nob+0.006
 dial+0.006
 peek+0.006
ad+0.005
 Looking+0.005
Neg logit contributions
working-0.011
istered-0.011
rier-0.011
 goals-0.010
ishy-0.010
Token en
Token ID551
Feature activation+3.98e-02

Pos logit contributions
 peek+0.007
 turned+0.006
 dial+0.006
 Looking+0.006
 opened+0.006
Neg logit contributions
working-0.008
rier-0.007
istered-0.007
ishy-0.007
 kicker-0.007
Tokenvious
Token ID1442
Feature activation+1.29e-02

Pos logit contributions
rier+0.038
istered+0.036
working+0.036
 goals+0.028
ishy+0.028
Neg logit contributions
 peek-0.083
 dial-0.083
nob-0.080
 turned-0.079
ad-0.078
Token and
Token ID290
Feature activation+2.16e-02

Pos logit contributions
rier+0.029
istered+0.029
working+0.028
nam+0.026
ishy+0.026
Neg logit contributions
 peek-0.010
 dial-0.010
 turned-0.010
ad-0.009
nob-0.009
Token wanted
Token ID2227
Feature activation+7.71e-03

Pos logit contributions
rier+0.048
istered+0.045
working+0.043
avored+0.042
umm+0.040
Neg logit contributions
 turned-0.024
 peek-0.024
 opened-0.023
 dial-0.022
 called-0.021
Token the
Token ID262
Feature activation-1.66e-02

Pos logit contributions
working+0.015
rier+0.015
istered+0.014
 goals+0.013
 bored+0.013
Neg logit contributions
 peek-0.008
 dial-0.008
nob-0.008
 Looking-0.007
ad-0.007
Token toy
Token ID13373
Feature activation+5.89e-03

Pos logit contributions
 dial+0.025
 peek+0.025
nob+0.024
ad+0.023
 turned+0.023
Neg logit contributions
rier-0.026
working-0.025
istered-0.025
ishy-0.022
 goals-0.022
Token replied
Token ID8712
Feature activation+6.83e-03

Pos logit contributions
nob+0.007
 dial+0.006
 peek+0.006
 Looking+0.006
AAAA+0.005
Neg logit contributions
working-0.011
rier-0.010
istered-0.010
 bored-0.010
ishy-0.010
Token,
Token ID11
Feature activation-1.81e-02

Pos logit contributions
istered+0.016
working+0.016
rier+0.015
ishy+0.015
 goals+0.014
Neg logit contributions
 peek-0.005
 dial-0.005
 turned-0.005
nob-0.004
 opened-0.004
Token "
Token ID366
Feature activation+1.85e-02

Pos logit contributions
 dial+0.024
 peek+0.024
nob+0.024
ad+0.022
 turned+0.022
Neg logit contributions
rier-0.031
working-0.030
istered-0.029
ishy-0.026
 goals-0.026
TokenIt
Token ID1026
Feature activation-6.31e-03

Pos logit contributions
rier+0.031
working+0.031
istered+0.029
ishy+0.027
 goals+0.027
Neg logit contributions
 dial-0.025
 peek-0.025
nob-0.024
 turned-0.023
 Looking-0.022
Token's
Token ID338
Feature activation-1.38e-03

Pos logit contributions
 dial+0.006
 peek+0.006
nob+0.006
 turned+0.005
ad+0.005
Neg logit contributions
rier-0.013
working-0.013
istered-0.013
ishy-0.012
 goals-0.011
Token c
Token ID269
Feature activation+4.17e-02

Pos logit contributions
 dial+0.002
 peek+0.002
nob+0.002
 Looking+0.002
ad+0.002
Neg logit contributions
rier-0.002
working-0.002
istered-0.002
ishy-0.002
 goals-0.002
Tokenheddar
Token ID44937
Feature activation+2.09e-02

Pos logit contributions
nam+0.050
working+0.049
rier+0.049
istered+0.047
 kicker+0.044
Neg logit contributions
nob-0.069
 peek-0.069
ad-0.068
 dial-0.068
 turned-0.067
Token cheese
Token ID9891
Feature activation+3.14e-02

Pos logit contributions
rier+0.033
istered+0.033
working+0.032
ivery+0.030
nam+0.030
Neg logit contributions
 peek-0.030
 dial-0.030
nob-0.028
 turned-0.028
ad-0.027
Token."
Token ID526
Feature activation-3.83e-03

Pos logit contributions
istered+0.066
rier+0.066
working+0.063
ishy+0.061
nam+0.060
Neg logit contributions
 peek-0.029
 dial-0.028
nob-0.028
 turned-0.026
 opened-0.025
Token
Token ID198
Feature activation-2.17e-03

Pos logit contributions
 dial+0.005
 peek+0.005
nob+0.005
 turned+0.004
ad+0.004
Neg logit contributions
rier-0.007
working-0.007
istered-0.007
ishy-0.006
 goals-0.006
Token
Token ID198
Feature activation+7.90e-03

Pos logit contributions
 dial+0.002
nob+0.002
 peek+0.002
 turned+0.001
ad+0.001
Neg logit contributions
istered-0.005
rier-0.005
working-0.005
 goals-0.004
ishy-0.004
Token a
Token ID257
Feature activation+2.00e-02

Pos logit contributions
 peek+0.003
 dial+0.002
nob+0.002
 turned+0.002
ad+0.002
Neg logit contributions
rier-0.008
istered-0.008
working-0.007
ishy-0.007
 goals-0.007
Token big
Token ID1263
Feature activation+3.05e-03

Pos logit contributions
rier+0.040
istered+0.039
working+0.038
 goals+0.036
attered+0.036
Neg logit contributions
 peek-0.023
 dial-0.022
 turned-0.020
 call-0.019
 opened-0.018
Token chamber
Token ID11847
Feature activation+1.00e-02

Pos logit contributions
rier+0.006
istered+0.006
working+0.005
ishy+0.005
ivery+0.005
Neg logit contributions
 peek-0.004
 dial-0.004
 turned-0.003
ad-0.003
nob-0.003
Token.
Token ID13
Feature activation+4.98e-03

Pos logit contributions
working+0.017
rier+0.016
istered+0.015
 bored+0.014
 kicker+0.014
Neg logit contributions
 dial-0.014
nob-0.013
 Looking-0.012
 peek-0.012
ad-0.012
Token Inside
Token ID14384
Feature activation-5.38e-03

Pos logit contributions
working+0.008
istered+0.007
rier+0.007
 goals+0.006
 kicker+0.006
Neg logit contributions
 dial-0.007
 fore-0.006
 peek-0.006
ran-0.006
nob-0.006
Token the
Token ID262
Feature activation+4.21e-02

Pos logit contributions
 peek+0.005
 dial+0.005
nob+0.004
 turned+0.004
ad+0.004
Neg logit contributions
rier-0.012
istered-0.012
working-0.011
ishy-0.011
 goals-0.010
Token chamber
Token ID11847
Feature activation+1.47e-02

Pos logit contributions
rier+0.086
istered+0.085
working+0.084
ishy+0.079
 kicker+0.077
Neg logit contributions
 peek-0.049
nob-0.044
 dial-0.043
 opened-0.042
 turned-0.040
Token there
Token ID612
Feature activation+1.20e-02

Pos logit contributions
rier+0.029
working+0.029
istered+0.028
 goals+0.026
ishy+0.026
Neg logit contributions
 dial-0.015
 peek-0.014
nob-0.014
ad-0.013
 Looking-0.012
Token were
Token ID547
Feature activation+8.42e-03

Pos logit contributions
rier+0.026
working+0.026
istered+0.025
ishy+0.024
 goals+0.023
Neg logit contributions
 dial-0.010
 peek-0.010
nob-0.010
 turned-0.009
ad-0.009
Token many
Token ID867
Feature activation+2.17e-02

Pos logit contributions
rier+0.011
working+0.010
istered+0.010
ishy+0.009
ivery+0.008
Neg logit contributions
 peek-0.016
 dial-0.015
 turned-0.015
nob-0.015
 opened-0.015
Token things
Token ID1243
Feature activation-1.71e-02

Pos logit contributions
rier+0.038
istered+0.037
working+0.037
ivery+0.034
ishy+0.033
Neg logit contributions
 peek-0.030
 dial-0.030
 opened-0.028
 turned-0.027
 called-0.027
Token invite
Token ID14037
Feature activation+1.58e-02

Pos logit contributions
 dial+0.001
nob+0.001
 Looking+0.001
 peek+0.001
 Turning+0.001
Neg logit contributions
working-0.001
rier-0.001
istered-0.001
 goals-0.001
 kicker-0.001
Token all
Token ID477
Feature activation-3.61e-02

Pos logit contributions
rier+0.025
working+0.024
istered+0.023
 goals+0.022
ishy+0.021
Neg logit contributions
 dial-0.022
 peek-0.022
nob-0.022
 Looking-0.020
 turned-0.020
Token his
Token ID465
Feature activation+1.47e-02

Pos logit contributions
 dial+0.051
nob+0.049
 peek+0.049
 Looking+0.046
 Turning+0.046
Neg logit contributions
working-0.057
rier-0.055
istered-0.051
 goals-0.051
ishy-0.049
Token friends
Token ID2460
Feature activation-1.07e-02

Pos logit contributions
rier+0.019
istered+0.018
working+0.018
ishy+0.016
 goals+0.015
Neg logit contributions
 dial-0.026
 peek-0.026
nob-0.025
 turned-0.024
ad-0.024
Token to
Token ID284
Feature activation+1.64e-02

Pos logit contributions
 dial+0.011
 peek+0.011
nob+0.010
 turned+0.010
ad+0.009
Neg logit contributions
rier-0.022
istered-0.021
working-0.021
ishy-0.019
 goals-0.019
Token his
Token ID465
Feature activation+5.17e-02

Pos logit contributions
working+0.030
rier+0.030
istered+0.028
 goals+0.027
 kicker+0.026
Neg logit contributions
 dial-0.018
nob-0.018
 peek-0.018
 Looking-0.017
 turned-0.016
Token palace
Token ID20562
Feature activation+1.63e-02

Pos logit contributions
rier+0.089
istered+0.087
working+0.083
ishy+0.080
ivery+0.077
Neg logit contributions
 peek-0.076
 dial-0.073
 turned-0.066
nob-0.066
 call-0.066
Token for
Token ID329
Feature activation+4.38e-03

Pos logit contributions
rier+0.033
istered+0.032
working+0.032
ishy+0.030
 goals+0.029
Neg logit contributions
 peek-0.017
 dial-0.017
nob-0.016
 turned-0.015
ad-0.014
Token a
Token ID257
Feature activation+1.91e-02

Pos logit contributions
rier+0.008
working+0.008
istered+0.008
 goals+0.007
ishy+0.007
Neg logit contributions
 dial-0.005
 peek-0.005
nob-0.005
 turned-0.005
 Looking-0.004
Token big
Token ID1263
Feature activation+1.20e-03

Pos logit contributions
working+0.026
rier+0.025
istered+0.024
 bored+0.021
ishy+0.021
Neg logit contributions
nob-0.031
 dial-0.031
ad-0.030
 peek-0.029
 Looking-0.029
Token party
Token ID2151
Feature activation+6.34e-03

Pos logit contributions
working+0.002
rier+0.001
istered+0.001
ishy+0.001
 goals+0.001
Neg logit contributions
 dial-0.002
nob-0.002
 peek-0.002
 Looking-0.002
 turned-0.002
Token.
Token ID13
Feature activation+1.73e-02

Pos logit contributions
rier+0.005
istered+0.005
ishy+0.005
working+0.005
attered+0.005
Neg logit contributions
 dial-0.001
 peek-0.001
 turned-0.001
 called-0.001
 call-0.001
Token<|endoftext|>
Token ID50256
Feature activation-2.05e-03

Pos logit contributions
rier+0.035
working+0.034
istered+0.034
ishy+0.031
 goals+0.030
Neg logit contributions
 dial-0.018
 peek-0.018
nob-0.017
 turned-0.016
 Looking-0.016
TokenL
Token ID43
Feature activation+1.03e-02

Pos logit contributions
 dial+0.002
nob+0.002
 peek+0.002
 turned+0.002
 call+0.002
Neg logit contributions
working-0.004
rier-0.004
istered-0.004
 goals-0.004
 kicker-0.003
Tokenila
Token ID10102
Feature activation-2.71e-02

Pos logit contributions
rier+0.017
working+0.017
istered+0.017
ishy+0.015
 goals+0.015
Neg logit contributions
 dial-0.014
 peek-0.014
nob-0.014
 turned-0.013
ad-0.013
Token was
Token ID373
Feature activation+3.53e-02

Pos logit contributions
 dial+0.019
 peek+0.019
nob+0.018
 turned+0.016
ad+0.016
Neg logit contributions
rier-0.062
working-0.062
istered-0.061
ishy-0.057
 goals-0.056
Token a
Token ID257
Feature activation+4.57e-02

Pos logit contributions
rier+0.051
working+0.050
istered+0.050
ishy+0.044
 goals+0.043
Neg logit contributions
 dial-0.056
 peek-0.056
nob-0.054
 turned-0.052
ad-0.051
Token little
Token ID1310
Feature activation+3.96e-02

Pos logit contributions
istered+0.084
rier+0.083
ivery+0.075
attered+0.075
 goals+0.074
Neg logit contributions
 peek-0.065
 dial-0.058
 turned-0.056
 call-0.054
 called-0.053
Token girl
Token ID2576
Feature activation-7.87e-03

Pos logit contributions
istered+0.076
rier+0.069
 responsibly+0.068
ivery+0.068
ops+0.067
Neg logit contributions
 peek-0.050
 dial-0.045
 called-0.044
 pe-0.044
 call-0.042
Token who
Token ID508
Feature activation+1.73e-02

Pos logit contributions
 dial+0.009
 peek+0.008
nob+0.008
 turned+0.008
ad+0.008
Neg logit contributions
rier-0.015
working-0.015
istered-0.015
ishy-0.013
 goals-0.013
Token loved
Token ID6151
Feature activation+1.94e-02

Pos logit contributions
rier+0.031
istered+0.027
working+0.026
 goals+0.024
ishy+0.024
Neg logit contributions
 peek-0.026
 dial-0.025
 turned-0.024
nob-0.024
 opened-0.023
Token to
Token ID284
Feature activation+4.65e-03

Pos logit contributions
rier+0.043
istered+0.042
working+0.041
ishy+0.038
ivery+0.037
Neg logit contributions
 dial-0.018
 peek-0.017
nob-0.016
 turned-0.015
ad-0.015
Token was
Token ID373
Feature activation+1.57e-02

Pos logit contributions
rier+0.050
working+0.048
istered+0.047
ishy+0.044
 goals+0.044
Neg logit contributions
 peek-0.023
 dial-0.022
 turned-0.021
nob-0.020
 opened-0.020
Token bored
Token ID17533
Feature activation+1.65e-02

Pos logit contributions
rier+0.027
working+0.027
istered+0.026
ishy+0.025
 goals+0.024
Neg logit contributions
 peek-0.021
 dial-0.021
 turned-0.020
nob-0.020
 opened-0.019
Token and
Token ID290
Feature activation+3.39e-02

Pos logit contributions
rier+0.036
working+0.035
istered+0.035
ishy+0.033
ivery+0.032
Neg logit contributions
 peek-0.015
 dial-0.015
nob-0.014
 turned-0.014
 opened-0.013
Token restless
Token ID42537
Feature activation+2.38e-02

Pos logit contributions
rier+0.055
umm+0.052
istered+0.051
avored+0.049
 kicker+0.049
Neg logit contributions
 turned-0.055
 peek-0.055
 opened-0.055
 called-0.051
 dial-0.049
Token.
Token ID13
Feature activation+2.73e-02

Pos logit contributions
istered+0.055
rier+0.054
working+0.054
ishy+0.051
ivery+0.051
Neg logit contributions
 peek-0.018
 dial-0.017
nob-0.017
 turned-0.016
 opened-0.015
Token She
Token ID1375
Feature activation+3.62e-03

Pos logit contributions
rier+0.046
working+0.045
istered+0.044
ishy+0.040
 goals+0.039
Neg logit contributions
 dial-0.037
 peek-0.037
nob-0.036
 turned-0.034
ad-0.033
Token f
Token ID277
Feature activation+2.29e-02

Pos logit contributions
rier+0.006
working+0.006
istered+0.006
ishy+0.006
 goals+0.006
Neg logit contributions
 dial-0.004
 peek-0.004
nob-0.004
ad-0.004
 Looking-0.004
Tokenidget
Token ID17484
Feature activation-3.38e-03

Pos logit contributions
rier+0.034
istered+0.033
working+0.033
ishy+0.030
 goals+0.028
Neg logit contributions
 dial-0.036
 peek-0.036
nob-0.034
 turned-0.033
ad-0.033
Tokened
Token ID276
Feature activation+1.39e-02

Pos logit contributions
 peek+0.005
 dial+0.005
 turned+0.005
 opened+0.005
nob+0.004
Neg logit contributions
rier-0.006
istered-0.005
working-0.005
 goals-0.005
ivery-0.005
Token and
Token ID290
Feature activation+5.84e-03

Pos logit contributions
working+0.032
rier+0.032
istered+0.032
ishy+0.030
 kicker+0.029
Neg logit contributions
 peek-0.011
 dial-0.011
 turned-0.010
nob-0.010
 opened-0.009
Token wh
Token ID348
Feature activation+2.36e-02

Pos logit contributions
rier+0.013
working+0.012
istered+0.012
ishy+0.011
 goals+0.011
Neg logit contributions
 dial-0.006
 peek-0.006
 turned-0.005
nob-0.005
 opened-0.005
Token together
Token ID1978
Feature activation+3.18e-03

Pos logit contributions
rier+0.002
working+0.002
istered+0.002
ishy+0.002
 goals+0.002
Neg logit contributions
 peek-0.002
 dial-0.002
nob-0.002
 turned-0.002
ad-0.002
Token in
Token ID287
Feature activation-1.85e-02

Pos logit contributions
rier+0.007
istered+0.007
working+0.007
ishy+0.007
ivery+0.006
Neg logit contributions
 peek-0.003
 dial-0.003
nob-0.002
 turned-0.002
 opened-0.002
Token the
Token ID262
Feature activation+8.22e-03

Pos logit contributions
 peek+0.019
 dial+0.019
nob+0.018
 turned+0.017
ad+0.017
Neg logit contributions
rier-0.039
istered-0.037
working-0.037
ishy-0.034
 goals-0.033
Token park
Token ID3952
Feature activation+1.07e-02

Pos logit contributions
rier+0.018
istered+0.017
working+0.016
nam+0.015
der+0.014
Neg logit contributions
 peek-0.010
 turned-0.008
nob-0.008
 dial-0.008
ad-0.008
Token,
Token ID11
Feature activation-3.86e-03

Pos logit contributions
rier+0.026
istered+0.026
ishy+0.024
working+0.024
ivery+0.023
Neg logit contributions
 peek-0.009
 turned-0.007
 dial-0.007
nob-0.007
 called-0.007
Token running
Token ID2491
Feature activation+3.57e-05

Pos logit contributions
 peek+0.004
 dial+0.004
nob+0.004
 turned+0.004
 opened+0.004
Neg logit contributions
rier-0.008
istered-0.007
working-0.007
ishy-0.007
 goals-0.007
Token and
Token ID290
Feature activation+3.82e-03

Pos logit contributions
rier+0.000
istered+0.000
working+0.000
ivery+0.000
ishy+0.000
Neg logit contributions
 peek-0.000
 dial-0.000
nob-0.000
 turned-0.000
 opened-0.000
Token laughing
Token ID14376
Feature activation+2.87e-02

Pos logit contributions
rier+0.008
istered+0.007
working+0.007
ishy+0.007
 goals+0.007
Neg logit contributions
 peek-0.005
 dial-0.004
nob-0.004
 turned-0.004
 opened-0.004
Token.
Token ID13
Feature activation-1.53e-02

Pos logit contributions
istered+0.076
rier+0.074
working+0.073
ivery+0.072
ishy+0.070
Neg logit contributions
 and-0.014
 peek-0.014
 turned-0.012
 dial-0.011
 called-0.010
Token
Token ID198
Feature activation-1.55e-02

Pos logit contributions
 dial+0.012
 peek+0.012
nob+0.011
ad+0.010
 turned+0.010
Neg logit contributions
rier-0.034
working-0.034
istered-0.034
ishy-0.031
 goals-0.031
Token
Token ID198
Feature activation-1.33e-02

Pos logit contributions
 dial+0.013
nob+0.013
 peek+0.012
ad+0.011
 turned+0.011
Neg logit contributions
working-0.032
istered-0.032
rier-0.032
 goals-0.030
 bored-0.029
Token space
Token ID2272
Feature activation+1.34e-03

Pos logit contributions
 dial+0.005
 peek+0.005
nob+0.005
 Looking+0.005
ad+0.005
Neg logit contributions
rier-0.009
working-0.009
istered-0.009
 goals-0.008
ishy-0.008
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
istered+0.003
rier+0.003
working+0.003
ishy+0.003
ivery+0.003
Neg logit contributions
 peek-0.001
 dial-0.001
nob-0.001
 turned-0.001
ad-0.001
Token<|endoftext|>
Token ID50256
Feature activation-9.74e-03

Pos logit contributions
 dial+0.009
 peek+0.009
nob+0.008
 turned+0.007
ad+0.007
Neg logit contributions
rier-0.024
working-0.024
istered-0.024
 goals-0.022
ishy-0.022
TokenOnce
Token ID7454
Feature activation+9.13e-03

Pos logit contributions
 dial+0.012
 peek+0.010
nob+0.010
 call+0.010
 knock+0.010
Neg logit contributions
working-0.015
 goals-0.015
rier-0.015
istered-0.014
 bored-0.014
Token there
Token ID612
Feature activation+2.35e-03

Pos logit contributions
rier+0.020
istered+0.020
working+0.019
ishy+0.018
ivery+0.018
Neg logit contributions
 peek-0.008
 turned-0.008
 opened-0.007
 dial-0.007
ad-0.007
Token were
Token ID547
Feature activation+1.18e-02

Pos logit contributions
rier+0.006
working+0.005
istered+0.005
ishy+0.005
 goals+0.005
Neg logit contributions
 dial-0.001
 peek-0.001
nob-0.001
ad-0.001
 turned-0.001
Token two
Token ID734
Feature activation+1.56e-02

Pos logit contributions
rier+0.025
istered+0.023
working+0.023
ivery+0.020
ishy+0.020
Neg logit contributions
 peek-0.013
ad-0.012
 turned-0.012
 opened-0.012
 dial-0.012
Token kids
Token ID3988
Feature activation-2.21e-02

Pos logit contributions
rier+0.024
working+0.024
istered+0.022
ivery+0.020
ishy+0.020
Neg logit contributions
 peek-0.024
 dial-0.023
 turned-0.023
ad-0.022
 call-0.022
Token,
Token ID11
Feature activation-3.34e-02

Pos logit contributions
 dial+0.028
nob+0.027
 peek+0.026
 Looking+0.025
 turned+0.024
Neg logit contributions
working-0.039
istered-0.037
rier-0.037
 bored-0.034
ishy-0.034
Token Sam
Token ID3409
Feature activation-3.39e-02

Pos logit contributions
nob+0.047
 dial+0.045
 peek+0.042
ad+0.041
 Looking+0.041
Neg logit contributions
working-0.053
istered-0.050
rier-0.048
nam-0.048
 bored-0.046
Token and
Token ID290
Feature activation+1.55e-03

Pos logit contributions
 dial+0.036
nob+0.036
 Looking+0.034
 peek+0.033
 peaked+0.031
Neg logit contributions
working-0.065
rier-0.060
istered-0.059
ishy-0.057
 goals-0.056
Token some
Token ID617
Feature activation-1.88e-02

Pos logit contributions
istered+0.006
working+0.006
rier+0.006
ivery+0.006
ishy+0.006
Neg logit contributions
 peek-0.005
 dial-0.004
nob-0.004
 turned-0.004
ad-0.004
Token pe
Token ID613
Feature activation-1.61e-02

Pos logit contributions
nob+0.022
 dial+0.021
 Looking+0.021
 peek+0.020
ad+0.019
Neg logit contributions
rier-0.036
working-0.033
istered-0.032
 goals-0.032
ishy-0.032
Tokenaches
Token ID3694
Feature activation-7.17e-03

Pos logit contributions
 dial+0.025
 peek+0.025
 Looking+0.025
nob+0.024
 call+0.023
Neg logit contributions
rier-0.025
working-0.022
istered-0.022
ishy-0.021
 goals-0.020
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
 peek+0.005
 dial+0.005
 turned+0.005
nob+0.005
 opened+0.005
Neg logit contributions
istered-0.016
working-0.016
rier-0.015
ivery-0.015
 kicker-0.015
Token They
Token ID1119
Feature activation+1.50e-02

Pos logit contributions
 dial+0.017
nob+0.017
ad+0.016
 peek+0.016
 god+0.015
Neg logit contributions
rier-0.014
working-0.014
istered-0.013
 goals-0.013
ishy-0.013
Token were
Token ID547
Feature activation+2.32e-02

Pos logit contributions
rier+0.034
istered+0.031
working+0.031
 goals+0.029
ivery+0.029
Neg logit contributions
 peek-0.016
 turned-0.015
 dial-0.015
 opened-0.015
nob-0.013
Token juicy
Token ID35075
Feature activation-5.26e-03

Pos logit contributions
working+0.038
rier+0.037
istered+0.036
ishy+0.032
ivery+0.032
Neg logit contributions
 peek-0.034
 dial-0.033
 turned-0.033
 opened-0.032
nob-0.031
Token and
Token ID290
Feature activation+1.52e-02

Pos logit contributions
 peek+0.003
 dial+0.003
nob+0.003
 turned+0.003
ad+0.002
Neg logit contributions
working-0.013
rier-0.013
istered-0.013
ishy-0.012
ivery-0.012
Token sweet
Token ID6029
Feature activation+4.81e-03

Pos logit contributions
rier+0.025
working+0.024
istered+0.023
 goals+0.021
ivery+0.021
Neg logit contributions
 peek-0.023
 dial-0.022
 turned-0.022
 opened-0.021
nob-0.020
Token.
Token ID13
Feature activation-1.81e-02

Pos logit contributions
rier+0.010
istered+0.010
working+0.010
ishy+0.009
ivery+0.009
Neg logit contributions
 peek-0.005
 dial-0.005
nob-0.004
 turned-0.004
ad-0.004
Token They
Token ID1119
Feature activation+2.12e-02

Pos logit contributions
nob+0.032
 dial+0.031
ad+0.029
 peek+0.029
 god+0.028
Neg logit contributions
working-0.021
rier-0.021
 goals-0.020
istered-0.020
 bored-0.020
Token and
Token ID290
Feature activation-4.13e-03

Pos logit contributions
 peek+0.001
 dial+0.001
 turned+0.001
nob+0.001
 opened+0.001
Neg logit contributions
rier-0.002
istered-0.002
working-0.002
ishy-0.002
ivery-0.002
Token milk
Token ID7545
Feature activation-3.15e-03

Pos logit contributions
 dial+0.006
 peek+0.006
 turned+0.005
nob+0.005
 opened+0.005
Neg logit contributions
rier-0.007
istered-0.007
working-0.007
ishy-0.006
ivery-0.006
Token.
Token ID13
Feature activation+2.72e-02

Pos logit contributions
 dial+0.003
 peek+0.003
 turned+0.003
nob+0.002
 call+0.002
Neg logit contributions
istered-0.007
working-0.007
rier-0.007
ishy-0.006
nam-0.006
Token You
Token ID921
Feature activation+7.74e-03

Pos logit contributions
rier+0.049
working+0.048
istered+0.047
ishy+0.043
 goals+0.042
Neg logit contributions
 dial-0.034
 peek-0.034
nob-0.032
 turned-0.031
 Looking-0.030
Token will
Token ID481
Feature activation+3.28e-03

Pos logit contributions
rier+0.014
istered+0.014
working+0.014
ishy+0.012
attered+0.012
Neg logit contributions
 peek-0.010
 dial-0.010
nob-0.009
 turned-0.009
 opened-0.009
Token feel
Token ID1254
Feature activation+1.75e-02

Pos logit contributions
rier+0.006
working+0.006
istered+0.006
ishy+0.006
 goals+0.006
Neg logit contributions
 dial-0.004
 peek-0.004
nob-0.003
 turned-0.003
 Looking-0.003
Token safe
Token ID3338
Feature activation-5.28e-03

Pos logit contributions
working+0.034
istered+0.032
rier+0.031
attered+0.030
ops+0.029
Neg logit contributions
 peek-0.020
 turned-0.020
 dial-0.019
 called-0.019
 pat-0.019
Token and
Token ID290
Feature activation+3.06e-02

Pos logit contributions
 and+0.003
 peek+0.003
nob+0.002
 called+0.002
 dial+0.002
Neg logit contributions
istered-0.013
working-0.013
ishy-0.012
attered-0.012
nam-0.012
Token warm
Token ID5814
Feature activation-6.07e-03

Pos logit contributions
rier+0.048
working+0.047
istered+0.046
attered+0.043
 kicker+0.041
Neg logit contributions
 peek-0.048
 turned-0.044
 dial-0.043
 opened-0.043
 call-0.042
Token."
Token ID526
Feature activation-5.62e-03

Pos logit contributions
 peek+0.005
nob+0.005
 dial+0.005
 turned+0.005
p+0.005
Neg logit contributions
istered-0.014
working-0.013
rier-0.012
 kicker-0.012
 goals-0.012
Token
Token ID198
Feature activation-6.31e-03

Pos logit contributions
 dial+0.004
nob+0.004
 peek+0.004
ad+0.003
 turned+0.003
Neg logit contributions
rier-0.013
istered-0.013
working-0.013
 goals-0.012
ishy-0.012
Token.
Token ID13
Feature activation+1.31e-03

Pos logit contributions
rier+0.006
working+0.006
istered+0.006
ishy+0.005
 goals+0.005
Neg logit contributions
 dial-0.004
 peek-0.004
nob-0.004
 turned-0.003
ad-0.003
Token She
Token ID1375
Feature activation-2.11e-02

Pos logit contributions
rier+0.003
working+0.003
istered+0.003
ishy+0.002
 goals+0.002
Neg logit contributions
 dial-0.001
 peek-0.001
nob-0.001
ad-0.001
 turned-0.001
Token smiled
Token ID13541
Feature activation+5.88e-03

Pos logit contributions
nob+0.021
 dial+0.019
 peek+0.018
ad+0.018
 Looking+0.017
Neg logit contributions
working-0.041
rier-0.039
istered-0.039
 kicker-0.037
 bored-0.036
Token and
Token ID290
Feature activation-4.78e-03

Pos logit contributions
istered+0.015
working+0.015
rier+0.014
ishy+0.014
ivery+0.014
Neg logit contributions
 peek-0.003
 dial-0.003
 turned-0.003
 opened-0.003
 Looking-0.002
Token waved
Token ID26834
Feature activation+2.00e-02

Pos logit contributions
 dial+0.004
 peek+0.004
nob+0.004
 turned+0.003
ad+0.003
Neg logit contributions
rier-0.010
working-0.010
istered-0.010
ishy-0.009
 goals-0.009
Token her
Token ID607
Feature activation-8.93e-03

Pos logit contributions
working+0.038
istered+0.038
ivery+0.037
rier+0.036
 kicker+0.034
Neg logit contributions
 peek-0.024
 dial-0.023
 turned-0.022
 opened-0.021
 pat-0.021
Token arms
Token ID5101
Feature activation+1.53e-02

Pos logit contributions
 dial+0.012
nob+0.012
 peek+0.012
ad+0.012
 Looking+0.011
Neg logit contributions
rier-0.015
working-0.014
istered-0.014
 goals-0.013
ishy-0.013
Token around
Token ID1088
Feature activation+1.28e-02

Pos logit contributions
istered+0.032
rier+0.031
working+0.030
 kicker+0.029
ishy+0.029
Neg logit contributions
 peek-0.015
 dial-0.015
 turned-0.014
 opened-0.013
nob-0.013
Token the
Token ID262
Feature activation+1.54e-02

Pos logit contributions
rier+0.022
working+0.022
istered+0.022
ishy+0.020
 goals+0.019
Neg logit contributions
 dial-0.017
 peek-0.016
nob-0.016
 turned-0.015
ad-0.015
Token classroom
Token ID15806
Feature activation+1.90e-02

Pos logit contributions
rier+0.028
istered+0.027
working+0.027
ishy+0.025
 goals+0.024
Neg logit contributions
 peek-0.020
 dial-0.019
nob-0.018
 turned-0.018
ad-0.017
Token.
Token ID13
Feature activation+3.15e-03

Pos logit contributions
rier+0.039
istered+0.038
working+0.038
ishy+0.036
ivery+0.034
Neg logit contributions
 peek-0.020
 dial-0.019
nob-0.018
 turned-0.017
 opened-0.017
Token wanted
Token ID2227
Feature activation+3.16e-03

Pos logit contributions
rier+0.030
istered+0.029
working+0.029
ishy+0.026
 goals+0.026
Neg logit contributions
 peek-0.020
 dial-0.019
 turned-0.018
nob-0.018
 opened-0.017
Token some
Token ID617
Feature activation+2.84e-03

Pos logit contributions
rier+0.006
working+0.006
istered+0.006
 bored+0.005
 goals+0.005
Neg logit contributions
 dial-0.004
 peek-0.003
nob-0.003
 Looking-0.003
ad-0.003
Token seeds
Token ID11904
Feature activation+6.29e-03

Pos logit contributions
rier+0.004
working+0.004
istered+0.004
ishy+0.003
 goals+0.003
Neg logit contributions
 dial-0.005
 peek-0.005
nob-0.005
 Looking-0.004
ad-0.004
Token in
Token ID287
Feature activation-3.31e-03

Pos logit contributions
rier+0.014
istered+0.014
working+0.014
ishy+0.013
 goals+0.013
Neg logit contributions
 peek-0.005
nob-0.004
 dial-0.004
 turned-0.004
 opened-0.004
Token return
Token ID1441
Feature activation+1.92e-02

Pos logit contributions
 dial+0.004
 peek+0.004
nob+0.004
 Looking+0.004
 turned+0.004
Neg logit contributions
rier-0.006
working-0.006
istered-0.006
 goals-0.005
ishy-0.005
Token.
Token ID13
Feature activation-4.47e-03

Pos logit contributions
istered+0.042
working+0.041
rier+0.041
ishy+0.038
ivery+0.038
Neg logit contributions
 peek-0.017
nob-0.016
 dial-0.016
 turned-0.015
ad-0.015
Token Twe
Token ID24205
Feature activation+1.21e-02

Pos logit contributions
 dial+0.007
 peek+0.007
nob+0.007
ad+0.007
 turned+0.006
Neg logit contributions
rier-0.007
working-0.006
istered-0.006
ishy-0.006
 goals-0.005
Tokenety
Token ID2963
Feature activation+5.71e-03

Pos logit contributions
working+0.014
rier+0.014
istered+0.014
ishy+0.013
attered+0.012
Neg logit contributions
 dial-0.023
 peek-0.022
nob-0.021
 turned-0.021
 Looking-0.020
Token agreed
Token ID4987
Feature activation+3.48e-03

Pos logit contributions
rier+0.012
istered+0.011
working+0.011
ishy+0.010
 goals+0.010
Neg logit contributions
 dial-0.006
 peek-0.006
nob-0.005
 turned-0.005
ad-0.005
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
rier+0.007
working+0.007
istered+0.007
 goals+0.006
 bored+0.006
Neg logit contributions
 dial-0.003
nob-0.003
 peek-0.003
ad-0.003
 Looking-0.003
Token the
Token ID262
Feature activation-6.31e-03

Pos logit contributions
rier+0.023
istered+0.023
working+0.022
ishy+0.021
 goals+0.021
Neg logit contributions
 peek-0.013
 dial-0.013
 turned-0.012
nob-0.011
 opened-0.011
Token down
Token ID866
Feature activation-6.09e-03

Pos logit contributions
 dial+0.011
 peek+0.011
nob+0.011
 turned+0.011
ad+0.010
Neg logit contributions
rier-0.012
working-0.012
istered-0.012
ishy-0.010
 goals-0.010
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
 dial+0.007
nob+0.007
 peek+0.007
ad+0.006
 Looking+0.006
Neg logit contributions
rier-0.012
working-0.011
istered-0.011
 goals-0.010
ishy-0.010
Token When
Token ID1649
Feature activation-6.50e-03

Pos logit contributions
nob+0.015
 dial+0.015
 peek+0.015
ad+0.014
p+0.013
Neg logit contributions
rier-0.015
working-0.014
istered-0.014
 goals-0.013
attered-0.013
Token he
Token ID339
Feature activation-1.34e-02

Pos logit contributions
 peek+0.010
 dial+0.010
 turned+0.010
nob+0.010
ad+0.009
Neg logit contributions
rier-0.010
istered-0.009
working-0.009
ishy-0.008
 goals-0.008
Token got
Token ID1392
Feature activation-3.11e-03

Pos logit contributions
nob+0.018
 dial+0.016
ad+0.015
p+0.015
 Turning+0.015
Neg logit contributions
working-0.021
istered-0.020
 bored-0.019
 sweaty-0.019
ishy-0.019
Token to
Token ID284
Feature activation-1.72e-02

Pos logit contributions
 dial+0.004
 peek+0.004
nob+0.004
ad+0.003
 turned+0.003
Neg logit contributions
rier-0.006
working-0.006
istered-0.005
ishy-0.005
 goals-0.005
Token the
Token ID262
Feature activation-4.13e-03

Pos logit contributions
nob+0.023
 dial+0.022
 peek+0.021
 Turning+0.021
 Looking+0.021
Neg logit contributions
working-0.027
rier-0.026
istered-0.025
 goals-0.025
 sweaty-0.024
Token beach
Token ID10481
Feature activation-2.81e-03

Pos logit contributions
 peek+0.006
 dial+0.005
 turned+0.005
 call+0.005
 opened+0.005
Neg logit contributions
istered-0.008
working-0.007
rier-0.007
ishy-0.007
ivery-0.007
Token,
Token ID11
Feature activation-1.06e-02

Pos logit contributions
 peek+0.003
 dial+0.003
 turned+0.003
nob+0.002
 opened+0.002
Neg logit contributions
istered-0.006
rier-0.006
working-0.006
ishy-0.005
ivery-0.005
Token he
Token ID339
Feature activation-2.37e-03

Pos logit contributions
 peek+0.016
 dial+0.016
 turned+0.015
 opened+0.014
 Looking+0.014
Neg logit contributions
istered-0.017
rier-0.017
working-0.016
ishy-0.015
ivery-0.015
Token saw
Token ID2497
Feature activation-1.46e-02

Pos logit contributions
 dial+0.002
 peek+0.002
nob+0.002
ad+0.002
 turned+0.002
Neg logit contributions
rier-0.005
working-0.005
istered-0.005
ishy-0.004
 goals-0.004
Token you
Token ID345
Feature activation+1.03e-02

Pos logit contributions
 peek+0.015
 dial+0.014
 turned+0.014
 opened+0.013
 call+0.013
Neg logit contributions
istered-0.023
rier-0.022
working-0.022
ishy-0.021
attered-0.020
Token learn
Token ID2193
Feature activation+5.12e-03

Pos logit contributions
rier+0.018
istered+0.017
working+0.017
ishy+0.015
nam+0.015
Neg logit contributions
 peek-0.015
 dial-0.015
 turned-0.014
nob-0.014
ad-0.013
Token to
Token ID284
Feature activation-8.68e-04

Pos logit contributions
rier+0.010
working+0.009
istered+0.009
ishy+0.009
 goals+0.008
Neg logit contributions
 dial-0.006
 peek-0.006
nob-0.006
 turned-0.005
ad-0.005
Token be
Token ID307
Feature activation+5.25e-03

Pos logit contributions
 dial+0.001
 peek+0.001
nob+0.001
 turned+0.001
ad+0.001
Neg logit contributions
rier-0.002
working-0.002
istered-0.002
ishy-0.002
 goals-0.002
Token polite
Token ID23507
Feature activation+3.98e-03

Pos logit contributions
rier+0.008
istered+0.008
working+0.008
ishy+0.007
umm+0.007
Neg logit contributions
 dial-0.008
 peek-0.008
 turned-0.008
 called-0.007
 opened-0.007
Token.
Token ID13
Feature activation-1.52e-02

Pos logit contributions
istered+0.008
rier+0.008
working+0.008
ishy+0.007
ivery+0.007
Neg logit contributions
 dial-0.004
 peek-0.004
nob-0.004
 turned-0.004
 called-0.003
Tokenâ
Token ID22940
Feature activation+8.41e-03

Pos logit contributions
nob+0.024
 peek+0.023
 dial+0.023
ad+0.023
 turned+0.022
Neg logit contributions
rier-0.021
istered-0.019
working-0.019
 goals-0.018
 bored-0.017
Token
Token ID26391
Feature activation-1.13e-02

Pos logit contributions
working+0.012
rier+0.010
ivery+0.010
ishy+0.010
istered+0.009
Neg logit contributions
 dial-0.015
 peek-0.014
 turned-0.013
 pat-0.013
 opened-0.013
Token
Token ID198
Feature activation-1.90e-02

Pos logit contributions
 peek+0.016
 dial+0.016
nob+0.015
 turned+0.014
 Turning+0.014
Neg logit contributions
rier-0.020
working-0.018
istered-0.018
ishy-0.017
nam-0.016
Token
Token ID198
Feature activation-3.41e-02

Pos logit contributions
 dial+0.028
bul+0.025
nob+0.024
 peek+0.023
 extingu+0.023
Neg logit contributions
working-0.026
istered-0.025
 goals-0.025
dd-0.024
ivery-0.023
TokenMo
Token ID16632
Feature activation-1.01e-02

Pos logit contributions
 dial+0.056
nob+0.055
 peek+0.054
 opens+0.053
 pat+0.052
Neg logit contributions
dd-0.041
working-0.040
istered-0.038
ivery-0.037
 goals-0.034
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
working+0.030
istered+0.029
rier+0.028
ivery+0.027
ishy+0.027
Neg logit contributions
 peek-0.016
 turned-0.014
 dial-0.014
 pat-0.014
 opened-0.013
Token
Token ID220
Feature activation+5.74e-03

Pos logit contributions
 dial+0.025
nob+0.024
 peek+0.023
ad+0.021
 opened+0.020
Neg logit contributions
rier-0.024
working-0.024
istered-0.023
 goals-0.023
ishy-0.022
Token
Token ID198
Feature activation-1.70e-02

Pos logit contributions
rier+0.013
istered+0.013
working+0.013
 goals+0.012
ishy+0.012
Neg logit contributions
 dial-0.004
 peek-0.004
nob-0.004
ad-0.003
 turned-0.003
TokenThey
Token ID2990
Feature activation+4.39e-03

Pos logit contributions
 dial+0.022
nob+0.020
 peek+0.020
 call+0.018
 turned+0.018
Neg logit contributions
working-0.028
rier-0.028
istered-0.028
 goals-0.026
ivery-0.026
Token decided
Token ID3066
Feature activation-4.98e-03

Pos logit contributions
rier+0.010
istered+0.009
working+0.009
ishy+0.008
ivery+0.008
Neg logit contributions
 peek-0.005
 turned-0.005
 dial-0.005
 opened-0.005
ad-0.004
Token it
Token ID340
Feature activation-1.04e-02

Pos logit contributions
 dial+0.004
 peek+0.004
nob+0.004
 turned+0.004
ad+0.004
Neg logit contributions
rier-0.011
working-0.010
istered-0.010
ishy-0.010
 goals-0.010
Token was
Token ID373
Feature activation-1.47e-02

Pos logit contributions
 dial+0.007
 peek+0.007
nob+0.007
 turned+0.006
ad+0.006
Neg logit contributions
rier-0.024
working-0.024
istered-0.024
ishy-0.022
 goals-0.022
Token a
Token ID257
Feature activation+8.74e-03

Pos logit contributions
 dial+0.016
 peek+0.016
nob+0.015
 turned+0.014
ad+0.014
Neg logit contributions
rier-0.029
istered-0.028
working-0.028
ishy-0.026
 goals-0.025
Token good
Token ID922
Feature activation-2.99e-03

Pos logit contributions
rier+0.012
working+0.012
istered+0.011
ishy+0.010
 goals+0.010
Neg logit contributions
 dial-0.015
 peek-0.015
nob-0.014
ad-0.014
 turned-0.014
Token idea
Token ID2126
Feature activation-3.39e-02

Pos logit contributions
 dial+0.004
 peek+0.004
nob+0.004
ad+0.004
 turned+0.004
Neg logit contributions
working-0.005
rier-0.005
istered-0.005
ishy-0.004
 goals-0.004
Token to
Token ID284
Feature activation+8.95e-03

Pos logit contributions
 dial+0.047
 peek+0.043
nob+0.043
 Looking+0.042
 Turning+0.040
Neg logit contributions
working-0.054
rier-0.053
istered-0.051
 goals-0.046
 anymore-0.046
Token,
Token ID11
Feature activation-2.36e-02

Pos logit contributions
 dial+0.011
 peek+0.011
nob+0.010
 turned+0.010
ad+0.010
Neg logit contributions
rier-0.016
working-0.016
istered-0.016
ishy-0.015
 goals-0.014
Token what
Token ID644
Feature activation+4.88e-03

Pos logit contributions
 dial+0.034
 peek+0.034
nob+0.032
 turned+0.031
ad+0.031
Neg logit contributions
rier-0.038
working-0.037
istered-0.037
ishy-0.033
 goals-0.032
Token shall
Token ID2236
Feature activation-9.18e-03

Pos logit contributions
rier+0.010
istered+0.009
working+0.009
ishy+0.009
ivery+0.009
Neg logit contributions
 peek-0.006
 dial-0.005
 turned-0.005
nob-0.005
 opened-0.005
Token you
Token ID345
Feature activation-4.17e-02

Pos logit contributions
 peek+0.015
 dial+0.015
nob+0.014
 turned+0.014
ad+0.014
Neg logit contributions
rier-0.013
istered-0.013
working-0.013
ishy-0.011
 goals-0.011
Token do
Token ID466
Feature activation-1.54e-02

Pos logit contributions
 dial+0.057
nob+0.055
 peek+0.053
 Looking+0.051
 turned+0.050
Neg logit contributions
working-0.070
rier-0.068
istered-0.064
ishy-0.060
ivery-0.059
Token now
Token ID783
Feature activation-4.44e-02

Pos logit contributions
 dial+0.016
 peek+0.016
nob+0.015
 turned+0.014
 Looking+0.014
Neg logit contributions
rier-0.030
working-0.030
istered-0.029
ishy-0.027
 goals-0.026
Token?"
Token ID1701
Feature activation-1.47e-03

Pos logit contributions
 dial+0.047
 peek+0.046
nob+0.045
 Looking+0.041
 turned+0.041
Neg logit contributions
rier-0.087
working-0.087
istered-0.082
ishy-0.077
 goals-0.076
Token one
Token ID530
Feature activation+1.11e-02

Pos logit contributions
 dial+0.002
 peek+0.002
nob+0.002
ad+0.002
 turned+0.002
Neg logit contributions
rier-0.003
working-0.003
istered-0.003
ishy-0.002
 goals-0.002
Token of
Token ID286
Feature activation-7.54e-03

Pos logit contributions
rier+0.019
working+0.018
istered+0.017
ishy+0.016
 kicker+0.016
Neg logit contributions
nob-0.015
 dial-0.015
 peek-0.013
 Looking-0.013
ad-0.013
Token them
Token ID606
Feature activation+3.92e-03

Pos logit contributions
 dial+0.010
 peek+0.009
nob+0.009
 turned+0.009
ad+0.008
Neg logit contributions
rier-0.013
working-0.013
istered-0.013
ishy-0.012
 goals-0.012
Token asked
Token ID1965
Feature activation+1.62e-02

Pos logit contributions
rier+0.008
working+0.008
istered+0.008
ishy+0.008
 goals+0.008
Neg logit contributions
 dial-0.003
 peek-0.003
nob-0.003
ad-0.003
 turned-0.003
Token
Token ID198
Feature activation-7.15e-03

Pos logit contributions
rier+0.027
working+0.027
istered+0.027
ishy+0.025
 goals+0.025
Neg logit contributions
 dial-0.007
 peek-0.006
nob-0.006
 turned-0.005
ad-0.005
Token"
Token ID1
Feature activation+9.36e-03

Pos logit contributions
 dial+0.008
 peek+0.007
 turned+0.007
nob+0.007
 call+0.006
Neg logit contributions
rier-0.013
istered-0.013
working-0.013
ivery-0.012
 goals-0.012
TokenLet
Token ID5756
Feature activation-3.33e-03

Pos logit contributions
working+0.014
rier+0.014
istered+0.013
 kicker+0.012
nam+0.012
Neg logit contributions
 dial-0.014
nob-0.014
 peek-0.014
 call-0.013
 turned-0.013
Token's
Token ID338
Feature activation-1.83e-02

Pos logit contributions
 peek+0.004
 dial+0.004
nob+0.004
 turned+0.004
ad+0.003
Neg logit contributions
rier-0.006
istered-0.006
working-0.006
ishy-0.006
 goals-0.006
Token take
Token ID1011
Feature activation-1.71e-02

Pos logit contributions
 dial+0.020
nob+0.020
 peek+0.020
 Looking+0.018
 turned+0.018
Neg logit contributions
rier-0.034
working-0.034
istered-0.033
ishy-0.031
 goals-0.030
Token this
Token ID428
Feature activation-4.83e-02

Pos logit contributions
nob+0.021
 dial+0.021
 peek+0.021
 Looking+0.019
 turned+0.019
Neg logit contributions
working-0.029
rier-0.029
istered-0.027
ishy-0.026
 goals-0.026
Token ash
Token ID12530
Feature activation-2.33e-02

Pos logit contributions
 dial+0.074
 Looking+0.074
ad+0.073
Agent+0.071
Turn+0.068
Neg logit contributions
rier-0.065
working-0.065
ishy-0.058
istered-0.056
 bored-0.054
Token and
Token ID290
Feature activation-1.63e-02

Pos logit contributions
 dial+0.025
 peek+0.024
 Looking+0.023
ad+0.023
nob+0.022
Neg logit contributions
rier-0.046
working-0.045
istered-0.043
ishy-0.040
 goals-0.039
Token build
Token ID1382
Feature activation-1.24e-02

Pos logit contributions
 dial+0.016
 peek+0.015
nob+0.015
 turned+0.013
ad+0.013
Neg logit contributions
rier-0.034
working-0.033
istered-0.033
ishy-0.031
 goals-0.030
Token something
Token ID1223
Feature activation+1.84e-02

Pos logit contributions
 dial+0.015
 peek+0.015
nob+0.014
 turned+0.013
ad+0.013
Neg logit contributions
rier-0.023
working-0.022
istered-0.022
ishy-0.020
 goals-0.020
Token with
Token ID351
Feature activation-1.99e-02

Pos logit contributions
working+0.030
rier+0.029
istered+0.029
ishy+0.026
ivery+0.026
Neg logit contributions
 peek-0.026
 dial-0.026
nob-0.024
 turned-0.024
 opened-0.023
Token set
Token ID900
Feature activation-1.45e-02

Pos logit contributions
rier+0.007
working+0.007
istered+0.006
 goals+0.006
ishy+0.006
Neg logit contributions
 dial-0.004
 peek-0.004
 Looking-0.004
nob-0.004
 Turning-0.003
Token,
Token ID11
Feature activation-2.52e-02

Pos logit contributions
 dial+0.020
 peek+0.020
nob+0.019
 Looking+0.019
 Turning+0.018
Neg logit contributions
rier-0.025
working-0.023
istered-0.022
 goals-0.020
ishy-0.020
Token with
Token ID351
Feature activation-4.24e-03

Pos logit contributions
 dial+0.027
nob+0.027
 peek+0.027
ad+0.025
 Looking+0.025
Neg logit contributions
rier-0.048
working-0.047
istered-0.046
 goals-0.042
ishy-0.042
Token a
Token ID257
Feature activation-2.22e-02

Pos logit contributions
 dial+0.004
 peek+0.004
 turned+0.004
ad+0.004
 opened+0.004
Neg logit contributions
rier-0.009
istered-0.009
working-0.009
ivery-0.009
ishy-0.008
Token train
Token ID4512
Feature activation-6.82e-03

Pos logit contributions
nob+0.031
 dial+0.030
 peek+0.029
ad+0.029
 Looking+0.028
Neg logit contributions
rier-0.036
istered-0.035
working-0.035
ishy-0.031
 goals-0.031
Token,
Token ID11
Feature activation-4.48e-02

Pos logit contributions
 dial+0.007
 peek+0.007
nob+0.007
 Looking+0.007
 turned+0.006
Neg logit contributions
rier-0.013
working-0.013
istered-0.013
 goals-0.012
ishy-0.011
Token tracks
Token ID8339
Feature activation-2.97e-03

Pos logit contributions
nob+0.049
 peek+0.047
 dial+0.046
 Looking+0.046
ad+0.044
Neg logit contributions
rier-0.083
working-0.082
istered-0.078
 goals-0.075
 kicker-0.073
Token,
Token ID11
Feature activation-4.12e-02

Pos logit contributions
 dial+0.003
 peek+0.003
nob+0.003
 turned+0.003
ad+0.003
Neg logit contributions
rier-0.006
istered-0.006
working-0.006
ishy-0.006
 goals-0.005
Token and
Token ID290
Feature activation-2.64e-02

Pos logit contributions
nob+0.038
 Looking+0.037
 peek+0.036
 dial+0.035
ad+0.034
Neg logit contributions
rier-0.083
working-0.082
istered-0.077
 goals-0.075
 bored-0.073
Token stations
Token ID8985
Feature activation+1.31e-02

Pos logit contributions
 dial+0.034
 peek+0.034
nob+0.032
 turned+0.031
ad+0.030
Neg logit contributions
rier-0.046
working-0.045
istered-0.045
ishy-0.041
 goals-0.040
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
istered+0.027
rier+0.027
working+0.026
ishy+0.025
ivery+0.024
Neg logit contributions
 dial-0.013
 peek-0.013
nob-0.012
 turned-0.012
ad-0.011
Token.
Token ID13
Feature activation+3.38e-03

Pos logit contributions
rier+0.016
working+0.016
istered+0.016
ishy+0.015
 goals+0.014
Neg logit contributions
 dial-0.007
 peek-0.007
nob-0.006
 turned-0.006
ad-0.006
Token He
Token ID679
Feature activation-1.89e-02

Pos logit contributions
rier+0.006
working+0.005
istered+0.005
 goals+0.005
ishy+0.005
Neg logit contributions
 dial-0.005
nob-0.004
 peek-0.004
ad-0.004
 turned-0.004
Token gave
Token ID2921
Feature activation+2.18e-02

Pos logit contributions
nob+0.021
 dial+0.020
 peek+0.018
ad+0.018
 Looking+0.018
Neg logit contributions
working-0.034
rier-0.033
istered-0.033
 goals-0.031
ishy-0.031
Token Bob
Token ID5811
Feature activation-4.33e-02

Pos logit contributions
rier+0.035
working+0.034
istered+0.034
ishy+0.031
 goals+0.030
Neg logit contributions
 dial-0.031
 peek-0.031
nob-0.030
 turned-0.028
ad-0.028
Token a
Token ID257
Feature activation-4.11e-02

Pos logit contributions
 dial+0.045
 peek+0.044
nob+0.042
 turned+0.039
ad+0.039
Neg logit contributions
rier-0.086
working-0.085
istered-0.084
ishy-0.077
 goals-0.076
Token big
Token ID1263
Feature activation-5.15e-02

Pos logit contributions
nob+0.071
ad+0.067
 dial+0.065
ran+0.062
 peek+0.060
Neg logit contributions
working-0.053
istered-0.051
rier-0.050
ishy-0.048
 kicker-0.046
Token hug
Token ID16225
Feature activation-1.89e-02

Pos logit contributions
nob+0.060
 dial+0.056
 peek+0.050
ad+0.048
 Looking+0.048
Neg logit contributions
rier-0.095
working-0.094
istered-0.090
ishy-0.090
 kicker-0.088
Token and
Token ID290
Feature activation-1.22e-02

Pos logit contributions
 dial+0.014
 peek+0.014
nob+0.013
 turned+0.011
ad+0.011
Neg logit contributions
rier-0.044
working-0.043
istered-0.043
ishy-0.040
 goals-0.039
Token said
Token ID531
Feature activation+1.75e-02

Pos logit contributions
 dial+0.012
nob+0.012
 peek+0.012
ad+0.011
 turned+0.010
Neg logit contributions
rier-0.025
working-0.024
istered-0.024
ishy-0.022
 goals-0.022
Token "
Token ID366
Feature activation+1.28e-03

Pos logit contributions
istered+0.036
working+0.035
rier+0.034
ishy+0.033
ivery+0.032
Neg logit contributions
 peek-0.018
 dial-0.017
 turned-0.016
nob-0.016
ad-0.016
TokenWell
Token ID5779
Feature activation-2.39e-02

Pos logit contributions
working+0.002
rier+0.002
istered+0.002
ishy+0.002
 kicker+0.002
Neg logit contributions
 dial-0.002
 peek-0.002
nob-0.002
 turned-0.002
 Looking-0.002
Token
Token ID198
Feature activation-1.71e-02

Pos logit contributions
nob+0.044
 dial+0.044
izer+0.041
 x+0.041
p+0.039
Neg logit contributions
 goals-0.050
rier-0.046
 whenever-0.046
 forward-0.043
 bored-0.043
Token
Token ID198
Feature activation-1.40e-02

Pos logit contributions
 dial+0.022
nob+0.021
 peek+0.018
 extingu+0.018
bul+0.018
Neg logit contributions
 goals-0.027
working-0.024
istered-0.024
rier-0.024
 both-0.023
TokenHer
Token ID9360
Feature activation-8.28e-03

Pos logit contributions
 dial+0.016
nob+0.016
 peek+0.015
 pat+0.015
 call+0.014
Neg logit contributions
 goals-0.024
rier-0.023
working-0.023
istered-0.023
 kicker-0.021
Token mom
Token ID1995
Feature activation-1.08e-02

Pos logit contributions
nob+0.017
ad+0.016
p+0.016
 peek+0.016
 Looking+0.016
Neg logit contributions
istered-0.008
rier-0.007
working-0.007
 goals-0.007
ishy-0.006
Token showed
Token ID3751
Feature activation-2.60e-04

Pos logit contributions
nob+0.012
AAAA+0.012
eway+0.012
 Looking+0.012
izer+0.011
Neg logit contributions
working-0.018
 kicker-0.016
rier-0.015
ishy-0.015
istered-0.015
Token Julie
Token ID21946
Feature activation-5.37e-02

Pos logit contributions
 dial+0.000
 peek+0.000
nob+0.000
 Looking+0.000
 turned+0.000
Neg logit contributions
rier-0.000
working-0.000
istered-0.000
 goals-0.000
ishy-0.000
Token how
Token ID703
Feature activation+5.83e-03

Pos logit contributions
 dial+0.060
 peek+0.059
nob+0.058
ad+0.053
 turned+0.053
Neg logit contributions
rier-0.100
working-0.098
istered-0.096
 goals-0.090
ishy-0.088
Token to
Token ID284
Feature activation-1.64e-02

Pos logit contributions
rier+0.015
istered+0.014
working+0.014
ivery+0.013
ishy+0.013
Neg logit contributions
 peek-0.004
 dial-0.003
 turned-0.003
nob-0.003
 opened-0.003
Token use
Token ID779
Feature activation-2.86e-02

Pos logit contributions
 Looking+0.019
nob+0.019
 fore+0.017
 dial+0.017
 Turning+0.017
Neg logit contributions
working-0.029
rier-0.026
istered-0.026
ishy-0.025
ivery-0.024
Token the
Token ID262
Feature activation-2.48e-02

Pos logit contributions
 peek+0.037
 dial+0.036
nob+0.036
 Looking+0.034
ad+0.033
Neg logit contributions
rier-0.049
working-0.048
istered-0.047
 goals-0.043
ishy-0.043
Token comb
Token ID1974
Feature activation-1.12e-03

Pos logit contributions
 Looking+0.034
nob+0.034
ad+0.034
 peek+0.033
 dial+0.032
Neg logit contributions
rier-0.040
working-0.038
istered-0.035
 goals-0.034
ishy-0.033