TOP ACTIVATIONS
MAX = 5.501

. " Come on mom ", said Brad .
. " Wait , Brad ," she said . " Let
an oy ster inside . Oy sters are y ummy and
finally left the shop , Cornel ius was feeling much better
a passport . His mom gave him a big smile and
She shows her paper to R avi . "
for your mom 's birthday ," said grandma .
them at the market . Oy sters are very valuable .
idea !" But T erence didn 't want to
then walking away . Little Cornel ius was so proud that
so high . However , T erence really wanted to explore
so big and special . Fel icity was so proud of
an old tower . Sir T erence was brave and curious
rockets . Laura and Connor were so proud of
smiled . " Sure thing ," she said .
it on the chickens . Fel icity blinked and saw that
" Mom my ," asked Charlie , " Can
to explore the woods near their home . As
could lift a car ! Fel icity 's mom my and
fork that big before ! Fel icity was so excited !

MIN ACTIVATIONS
MIN = -4.469

not want to play with each other anymore . They sit
sister yelled , " Look out !" A big fish jumped
had fun . They made each other happy . <|endoftext|> L
my and the kid loved each other very much . They
I 'm sorry " to each other . They hug and
They had fun and made each other laugh . Mom smiled
'm sorry " and hugged each other . They
. " Look out , dog !" Ben shouts
share and be nice to each other ." Lily and Ben
She said , " Come out , crab , come out
Anna . They also liked each other . They had a
. Now say sorry to each other ." Lily and Anna
Daisy accidentally broke Ph oe be 's favourite toy , a
very stubborn . They made each other sad and angry .
. " You are hurting each other and the car .
and daddy who both loved each other very much . Every
Mitt ens . " Look out , Tim my !" yelled
. He was a mis chie vous little baby and always
to the kitchen and mixed a spicy and a gray juice
's okay " and hugged each other . Then they decided

INTERVAL 3.009 - 5.501
CONTAINS 0.011%

to explore the forest near his house . One day ,
mom write a letter to Grand ma and put it in
play in the field near their house . They had a
Sally heard strange noises coming from nearby . She followed the
go on an adventure on his boat . He went swimming

INTERVAL 0.516 - 3.009
CONTAINS 24.780%

They hold hands and walk into the cave . They see
The end . <|endoftext|> Once upon a time there was a
. Suddenly , the yarn became slippery and
the poem by heart . On a bright and
, and the bird and his friends put their plan to

INTERVAL -1.976 - 0.516
CONTAINS 74.422%

happy for it ." L ily nodded and they
's friend , Tim my , saw her and asked ,
! It was a noise , but it was far away
And I want to draw a picture of us ," Lily
twins . They like to play in the park with their

INTERVAL -4.469 - -1.976
CONTAINS 0.787%

the apple and ran back outside to play with his friends
a naughty face every time she had to take it .
. It was a messy day because it r ained a
didn 't mean to bite you ." M ittens
. They both get wet , and so do their toys
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
 Help+0.015
 tearing+0.014
 What+0.013
 smashing+0.013
free+0.013
Neg logit contributions
rey-0.041
asha-0.039
aleb-0.039
onia-0.038
iri-0.037
Token "
Token ID366
Feature activation+5.54e-02

Pos logit contributions
rey+0.059
aleb+0.058
iper+0.057
asha+0.057
i+0.057
Neg logit contributions
 What-0.020
 Help-0.020
 Whe-0.018
 Where-0.018
 Was-0.017
TokenCome
Token ID16773
Feature activation+3.79e-01

Pos logit contributions
iper+0.002
rey+0.002
asha+0.002
i+0.002
ishment+0.002
Neg logit contributions
 What-0.001
 Help-0.001
 Was-0.001
 Do-0.001
 Where-0.001
Token on
Token ID319
Feature activation-1.09e+00

Pos logit contributions
rey+0.013
aleb+0.012
iper+0.012
asha+0.012
i+0.012
Neg logit contributions
 Help-0.007
 Was-0.007
 smashing-0.007
 tearing-0.007
 What-0.006
Token mom
Token ID1995
Feature activation-2.12e-01

Pos logit contributions
 Help+0.018
 What+0.017
 Was+0.017
 Do+0.017
 smashing+0.016
Neg logit contributions
rey-0.040
aleb-0.039
asha-0.038
iper-0.038
aman-0.038
Token",
Token ID1600
Feature activation+4.39e+00

Pos logit contributions
 Help+0.003
 Do+0.003
 What+0.003
 Was+0.003
 Where+0.003
Neg logit contributions
rey-0.008
aleb-0.008
asha-0.008
iper-0.008
onia-0.007
Token said
Token ID531
Feature activation+3.20e+00

Pos logit contributions
otton+0.182
aleb+0.179
ust+0.178
wy+0.177
athy+0.167
Neg logit contributions
 "-0.070
 pulling-0.056
 pushing-0.055
 to-0.054
 The-0.054
Token Brad
Token ID8114
Feature activation+5.70e-01

Pos logit contributions
aman+0.110
asha+0.109
ust+0.109
aleb+0.108
otton+0.108
Neg logit contributions
 Help-0.059
 What-0.054
 Where-0.054
 Whe-0.052
 "-0.051
Token.
Token ID13
Feature activation+1.86e+00

Pos logit contributions
rey+0.021
aleb+0.020
asha+0.020
aman+0.020
iper+0.019
Neg logit contributions
 Help-0.010
 What-0.009
 Was-0.009
 Where-0.009
 Do-0.009
Token
Token ID198
Feature activation+1.35e+00

Pos logit contributions
aleb+0.074
rey+0.074
iper+0.074
asha+0.073
aman+0.072
Neg logit contributions
 Help-0.026
 What-0.025
 Was-0.023
 Where-0.023
 Do-0.023
Token
Token ID198
Feature activation+2.02e+00

Pos logit contributions
rey+0.049
aleb+0.047
asha+0.046
iper+0.046
aman+0.045
Neg logit contributions
 Help-0.023
 What-0.022
 Was-0.022
 Do-0.022
 smashing-0.021
Token.
Token ID13
Feature activation+2.39e+00

Pos logit contributions
rey+0.010
asha+0.009
aleb+0.009
iper+0.009
iri+0.009
Neg logit contributions
 Help-0.004
 tearing-0.004
 What-0.004
 knocking-0.004
 destroying-0.004
Token "
Token ID366
Feature activation+9.94e-01

Pos logit contributions
rey+0.107
aleb+0.106
asha+0.104
iper+0.103
aman+0.103
Neg logit contributions
 What-0.024
 Help-0.022
 Where-0.020
 Was-0.020
 Do-0.019
TokenWait
Token ID21321
Feature activation+2.07e-02

Pos logit contributions
iper+0.037
ishment+0.035
rey+0.034
i+0.034
icity+0.034
Neg logit contributions
 What-0.018
 Help-0.017
Are-0.017
 Was-0.017
 Do-0.016
Token,
Token ID11
Feature activation+1.24e+00

Pos logit contributions
rey+0.001
aleb+0.001
iper+0.001
asha+0.001
aman+0.001
Neg logit contributions
 Help-0.000
 What-0.000
 Was-0.000
 Do-0.000
 smashing-0.000
Token Brad
Token ID8114
Feature activation+9.71e-02

Pos logit contributions
ishment+0.041
onia+0.041
asha+0.041
aman+0.040
andra+0.040
Neg logit contributions
 Help-0.027
 What-0.026
 Do-0.025
 Where-0.024
 Whe-0.023
Token,"
Token ID553
Feature activation+4.23e+00

Pos logit contributions
rey+0.004
aleb+0.004
asha+0.004
aman+0.004
iper+0.004
Neg logit contributions
 Help-0.001
 What-0.001
 Was-0.001
 Do-0.001
 Where-0.001
Token she
Token ID673
Feature activation+2.15e+00

Pos logit contributions
iri+0.149
otton+0.149
aleb+0.147
ust+0.147
wy+0.144
Neg logit contributions
 What-0.083
 Help-0.079
 "-0.078
 Are-0.077
 Where-0.074
Token said
Token ID531
Feature activation+1.83e+00

Pos logit contributions
aleb+0.075
ishment+0.072
aman+0.070
rey+0.070
 Him+0.070
Neg logit contributions
 bumped-0.038
 Help-0.038
 Was-0.036
 "-0.036
 v-0.035
Token.
Token ID13
Feature activation+2.81e+00

Pos logit contributions
rey+0.064
aleb+0.063
asha+0.061
iper+0.061
aman+0.060
Neg logit contributions
 Help-0.035
 What-0.033
 Was-0.032
 tearing-0.031
 smashing-0.031
Token "
Token ID366
Feature activation+7.57e-01

Pos logit contributions
rey+0.130
aleb+0.129
asha+0.127
iper+0.126
iri+0.124
Neg logit contributions
 Help-0.024
 What-0.024
 Where-0.020
 Was-0.020
 Do-0.020
TokenLet
Token ID5756
Feature activation+9.29e-01

Pos logit contributions
iper+0.026
rey+0.026
aman+0.025
asha+0.025
aleb+0.025
Neg logit contributions
 Help-0.015
 What-0.015
 Do-0.014
 Was-0.014
 Whe-0.014
Token an
Token ID281
Feature activation+7.98e-01

Pos logit contributions
rey+0.005
aleb+0.005
asha+0.005
iper+0.005
aman+0.005
Neg logit contributions
 Help-0.003
 What-0.003
 Do-0.003
 Was-0.003
 Where-0.003
Token oy
Token ID35104
Feature activation+2.57e+00

Pos logit contributions
rey+0.021
asha+0.020
aleb+0.020
iper+0.020
aman+0.019
Neg logit contributions
 Help-0.021
 What-0.021
 Do-0.020
 tearing-0.020
 Where-0.020
Tokenster
Token ID1706
Feature activation+4.07e-01

Pos logit contributions
rey+0.069
aleb+0.067
iper+0.066
aman+0.066
asha+0.065
Neg logit contributions
 Help-0.067
 What-0.065
 Was-0.065
 Do-0.064
 Where-0.063
Token inside
Token ID2641
Feature activation-9.38e-01

Pos logit contributions
rey+0.013
aleb+0.012
asha+0.012
iper+0.012
aman+0.012
Neg logit contributions
 Help-0.009
 What-0.009
 Do-0.008
 Was-0.008
 Where-0.008
Token.
Token ID13
Feature activation-4.43e-02

Pos logit contributions
 Help+0.017
 What+0.017
 Do+0.016
 Was+0.016
 Where+0.016
Neg logit contributions
rey-0.033
aleb-0.032
iper-0.031
asha-0.031
aman-0.031
Token Oy
Token ID39447
Feature activation+4.21e+00

Pos logit contributions
 Help+0.001
 What+0.001
 smashing+0.001
 Was+0.001
 tearing+0.001
Neg logit contributions
rey-0.002
aleb-0.002
iper-0.002
asha-0.002
aman-0.002
Tokensters
Token ID5937
Feature activation+1.47e+00

Pos logit contributions
rey+0.105
iper+0.104
aleb+0.102
aman+0.101
asha+0.097
Neg logit contributions
 Help-0.116
 What-0.115
 Do-0.112
 Was-0.111
 Where-0.110
Token are
Token ID389
Feature activation+8.76e-01

Pos logit contributions
rey+0.054
aleb+0.054
asha+0.053
aman+0.052
iper+0.051
Neg logit contributions
 Help-0.025
 What-0.025
 Do-0.025
 Was-0.024
 tearing-0.023
Token y
Token ID331
Feature activation+1.31e+00

Pos logit contributions
aleb+0.030
rey+0.030
asha+0.030
aman+0.030
iper+0.029
Neg logit contributions
 Help-0.017
 tearing-0.016
 Do-0.016
 What-0.016
 smashing-0.016
Tokenummy
Token ID13513
Feature activation+5.42e-01

Pos logit contributions
rey+0.033
aleb+0.032
asha+0.031
iper+0.031
aman+0.030
Neg logit contributions
 Help-0.037
 What-0.036
 Was-0.035
 Do-0.035
 smashing-0.034
Token and
Token ID290
Feature activation+4.20e-01

Pos logit contributions
rey+0.020
aleb+0.020
aman+0.020
iper+0.020
asha+0.019
Neg logit contributions
 Help-0.009
 Do-0.009
 What-0.009
 Was-0.008
 Where-0.008
Token finally
Token ID3443
Feature activation-5.74e-01

Pos logit contributions
rey+0.021
iper+0.021
ishment+0.021
aleb+0.021
ita+0.021
Neg logit contributions
 Help-0.009
 Was-0.009
 What-0.009
 Where-0.008
 tearing-0.007
Token left
Token ID1364
Feature activation-9.15e-03

Pos logit contributions
 Help+0.008
 Was+0.008
 tearing+0.008
 What+0.007
 smashing+0.007
Neg logit contributions
aleb-0.021
rey-0.021
ishment-0.021
iper-0.021
 Him-0.020
Token the
Token ID262
Feature activation+5.95e-01

Pos logit contributions
 Help+0.000
 What+0.000
 Was+0.000
 smashing+0.000
 tearing+0.000
Neg logit contributions
rey-0.000
aleb-0.000
asha-0.000
iper-0.000
isi-0.000
Token shop
Token ID6128
Feature activation+4.65e-01

Pos logit contributions
rey+0.017
aleb+0.016
asha+0.016
iper+0.016
onia+0.015
Neg logit contributions
 Help-0.015
 What-0.015
 Was-0.014
 smashing-0.014
 tearing-0.014
Token,
Token ID11
Feature activation+1.42e+00

Pos logit contributions
rey+0.019
aleb+0.019
iper+0.018
iri+0.018
asha+0.018
Neg logit contributions
 Help-0.006
 Was-0.006
 What-0.006
 Where-0.005
 tearing-0.005
Token Cornel
Token ID48214
Feature activation+4.18e+00

Pos logit contributions
aleb+0.046
iper+0.046
isi+0.046
asha+0.045
onia+0.045
Neg logit contributions
 Help-0.030
 What-0.030
 Where-0.027
 Was-0.027
 Whe-0.027
Tokenius
Token ID3754
Feature activation-5.39e-01

Pos logit contributions
iper+0.077
isi+0.076
asha+0.071
ita+0.070
hel+0.068
Neg logit contributions
 Help-0.134
 What-0.131
 Was-0.129
 smashing-0.126
 Where-0.124
Token was
Token ID373
Feature activation-4.45e-02

Pos logit contributions
 Help+0.010
 Was+0.010
 What+0.009
 tearing+0.009
 smashing+0.009
Neg logit contributions
rey-0.018
aleb-0.018
aman-0.017
asha-0.017
isi-0.017
Token feeling
Token ID4203
Feature activation-7.42e-01

Pos logit contributions
 Help+0.001
 What+0.001
 smashing+0.001
 tearing+0.001
 Was+0.001
Neg logit contributions
rey-0.001
aleb-0.001
iper-0.001
asha-0.001
aman-0.001
Token much
Token ID881
Feature activation+1.21e+00

Pos logit contributions
 Help+0.017
 What+0.017
 Do+0.017
 Was+0.016
 smashing+0.016
Neg logit contributions
rey-0.021
aleb-0.021
iper-0.020
asha-0.020
aman-0.020
Token better
Token ID1365
Feature activation+1.83e-01

Pos logit contributions
rey+0.031
aleb+0.031
asha+0.030
iper+0.030
aman+0.029
Neg logit contributions
 Help-0.032
 What-0.031
 Do-0.030
 Was-0.030
 Where-0.030
Token a
Token ID257
Feature activation+9.83e-01

Pos logit contributions
rey+0.037
asha+0.036
aman+0.036
iper+0.035
icity+0.035
Neg logit contributions
 Help-0.013
 What-0.012
 to-0.012
 Do-0.011
 v-0.011
Token passport
Token ID17981
Feature activation+2.54e+00

Pos logit contributions
rey+0.028
aleb+0.027
asha+0.026
iper+0.026
aman+0.025
Neg logit contributions
 Help-0.025
 What-0.023
 Was-0.023
 Do-0.023
 smashing-0.023
Token.
Token ID13
Feature activation+2.47e+00

Pos logit contributions
asha+0.119
aleb+0.118
rey+0.117
iri+0.116
iper+0.114
Neg logit contributions
 to-0.024
 Help-0.020
 v-0.017
 Do-0.016
 fixing-0.015
Token His
Token ID2399
Feature activation+2.67e+00

Pos logit contributions
aleb+0.097
asha+0.096
i+0.095
aman+0.095
iper+0.095
Neg logit contributions
 Help-0.038
 What-0.037
 Was-0.033
 Where-0.033
 This-0.032
Token mom
Token ID1995
Feature activation+9.09e-01

Pos logit contributions
asha+0.085
aman+0.084
hel+0.084
onia+0.081
isi+0.080
Neg logit contributions
 Help-0.064
 What-0.056
 Where-0.055
 drawing-0.054
 Was-0.054
Token gave
Token ID2921
Feature activation+4.12e+00

Pos logit contributions
ishment+0.029
icity+0.029
rey+0.029
 avail+0.028
aleb+0.028
Neg logit contributions
 Was-0.017
 Help-0.017
 to-0.017
 What-0.016
 poking-0.016
Token him
Token ID683
Feature activation+5.25e-01

Pos logit contributions
ust+0.133
aman+0.126
asha+0.124
iri+0.123
ishment+0.121
Neg logit contributions
 What-0.089
 Do-0.084
 Help-0.082
 Where-0.079
 to-0.077
Token a
Token ID257
Feature activation+3.45e-01

Pos logit contributions
rey+0.020
aman+0.020
asha+0.019
onia+0.019
ishment+0.019
Neg logit contributions
 What-0.008
 Help-0.008
 Was-0.007
 Where-0.007
 This-0.006
Token big
Token ID1263
Feature activation+1.38e+00

Pos logit contributions
rey+0.010
aleb+0.010
asha+0.010
iper+0.009
aman+0.009
Neg logit contributions
 Help-0.008
 What-0.008
 Was-0.008
 Do-0.008
 Where-0.008
Token smile
Token ID8212
Feature activation-1.17e+00

Pos logit contributions
rey+0.041
aleb+0.039
asha+0.039
iper+0.038
aman+0.038
Neg logit contributions
 Help-0.033
 What-0.031
 Was-0.031
 Do-0.031
 smashing-0.030
Token and
Token ID290
Feature activation+9.28e-01

Pos logit contributions
 Help+0.020
 What+0.020
free+0.019
 Was+0.019
 Do+0.019
Neg logit contributions
rey-0.042
aleb-0.041
asha-0.040
iper-0.039
aman-0.039
Token She
Token ID1375
Feature activation+8.06e-01

Pos logit contributions
rey+0.073
aleb+0.072
iper+0.070
aman+0.069
asha+0.069
Neg logit contributions
 Help-0.038
 What-0.036
 Do-0.035
 Where-0.034
 Was-0.034
Token shows
Token ID2523
Feature activation+1.90e+00

Pos logit contributions
rey+0.027
aleb+0.027
asha+0.026
iper+0.026
aman+0.026
Neg logit contributions
 What-0.016
 Help-0.016
 Was-0.015
 Do-0.015
 tearing-0.015
Token her
Token ID607
Feature activation+1.34e-01

Pos logit contributions
aleb+0.059
aman+0.057
rey+0.056
iper+0.056
ishment+0.055
Neg logit contributions
 Help-0.043
 What-0.041
 Where-0.039
 Do-0.038
 Was-0.038
Token paper
Token ID3348
Feature activation+1.68e+00

Pos logit contributions
rey+0.004
aleb+0.004
iper+0.004
asha+0.004
aman+0.004
Neg logit contributions
 Help-0.003
 What-0.003
 Was-0.003
 Do-0.003
 smashing-0.003
Token to
Token ID284
Feature activation+1.02e+00

Pos logit contributions
aleb+0.067
rey+0.065
aman+0.065
asha+0.063
iper+0.063
Neg logit contributions
 Help-0.025
 What-0.025
 Was-0.023
 tearing-0.022
 Do-0.022
Token R
Token ID371
Feature activation+4.11e+00

Pos logit contributions
aleb+0.036
iper+0.035
ust+0.033
aman+0.033
asha+0.033
Neg logit contributions
 Help-0.021
 What-0.019
 Do-0.018
 Whe-0.018
 Where-0.018
Tokenavi
Token ID15820
Feature activation+3.92e-01

Pos logit contributions
aleb+0.064
iper+0.062
rey+0.062
aman+0.061
ishment+0.060
Neg logit contributions
 Help-0.144
 What-0.137
 Was-0.132
 Do-0.131
 Where-0.129
Token.
Token ID13
Feature activation+9.79e-01

Pos logit contributions
aleb+0.016
rey+0.015
aman+0.015
asha+0.015
iper+0.015
Neg logit contributions
 Help-0.006
 What-0.005
 Do-0.005
 tearing-0.005
smart-0.005
Token
Token ID198
Feature activation+8.10e-01

Pos logit contributions
rey+0.033
aleb+0.033
iper+0.032
asha+0.032
aman+0.032
Neg logit contributions
 Help-0.019
 What-0.019
 Do-0.018
 Was-0.018
 Where-0.018
Token
Token ID198
Feature activation+5.46e-01

Pos logit contributions
rey+0.029
aleb+0.028
asha+0.027
iper+0.027
aman+0.027
Neg logit contributions
 Help-0.014
 What-0.014
 smashing-0.013
 Was-0.013
 Do-0.013
Token"
Token ID1
Feature activation-5.93e-02

Pos logit contributions
aleb+0.017
rey+0.017
iper+0.017
aman+0.017
asha+0.017
Neg logit contributions
 Help-0.012
 What-0.011
 Do-0.011
 Was-0.011
 Where-0.010
Token for
Token ID329
Feature activation+2.09e-01

Pos logit contributions
aleb+0.094
rey+0.091
asha+0.088
aman+0.086
iper+0.084
Neg logit contributions
free-0.021
 Help-0.021
 v-0.021
 poking-0.019
 destroying-0.019
Token your
Token ID534
Feature activation+9.88e-01

Pos logit contributions
aleb+0.007
rey+0.007
asha+0.006
aman+0.006
onia+0.006
Neg logit contributions
 Help-0.005
 tearing-0.005
 What-0.004
 Do-0.004
 destroying-0.004
Token mom
Token ID1995
Feature activation+1.60e-01

Pos logit contributions
rey+0.030
aleb+0.029
asha+0.029
aman+0.028
onia+0.028
Neg logit contributions
 Help-0.024
 What-0.023
 Was-0.022
 Do-0.022
 tearing-0.022
Token's
Token ID338
Feature activation+1.20e+00

Pos logit contributions
rey+0.006
aleb+0.006
asha+0.006
icity+0.005
aman+0.005
Neg logit contributions
 Do-0.003
 Help-0.003
 What-0.003
 cutting-0.002
 tearing-0.002
Token birthday
Token ID10955
Feature activation+1.29e+00

Pos logit contributions
rey+0.038
aleb+0.037
asha+0.036
onia+0.035
aman+0.035
Neg logit contributions
 Help-0.028
 What-0.027
 Do-0.026
 Was-0.026
 v-0.026
Token,"
Token ID553
Feature activation+4.11e+00

Pos logit contributions
rey+0.058
aleb+0.057
asha+0.056
iri+0.054
iper+0.053
Neg logit contributions
 Help-0.011
 v-0.010
 Was-0.009
 What-0.009
 Do-0.009
Token said
Token ID531
Feature activation+3.29e+00

Pos logit contributions
aleb+0.133
ust+0.129
ishment+0.129
iper+0.129
iet+0.124
Neg logit contributions
 Help-0.093
 What-0.090
 Are-0.086
 Was-0.084
 Where-0.082
Token grandma
Token ID49890
Feature activation+3.12e-02

Pos logit contributions
aleb+0.091
iper+0.086
iet+0.085
asha+0.085
ishment+0.083
Neg logit contributions
 Help-0.091
 What-0.083
 Where-0.082
 "-0.078
 Was-0.077
Token.
Token ID13
Feature activation+2.56e+00

Pos logit contributions
rey+0.001
aleb+0.001
asha+0.001
iper+0.001
aman+0.001
Neg logit contributions
 Help-0.001
 What-0.001
 Was-0.001
 Do-0.001
 tearing-0.001
Token
Token ID198
Feature activation+2.40e+00

Pos logit contributions
aleb+0.118
iper+0.114
rey+0.112
ishment+0.111
asha+0.111
Neg logit contributions
 Help-0.029
 What-0.027
 Do-0.024
 Was-0.023
 Where-0.023
Token
Token ID198
Feature activation+2.72e+00

Pos logit contributions
aleb+0.100
ishment+0.100
iper+0.098
i+0.097
rey+0.096
Neg logit contributions
 Help-0.032
 What-0.028
 Was-0.026
 Do-0.025
 Where-0.024
Token them
Token ID606
Feature activation+7.64e-01

Pos logit contributions
rey+0.022
iper+0.022
aleb+0.022
asha+0.021
aman+0.021
Neg logit contributions
 What-0.013
 Help-0.012
 Do-0.012
 Was-0.012
 Where-0.011
Token at
Token ID379
Feature activation+1.93e+00

Pos logit contributions
rey+0.033
asha+0.033
aman+0.032
aleb+0.032
onia+0.031
Neg logit contributions
 Help-0.010
 What-0.009
 Do-0.008
 Was-0.007
 v-0.007
Token the
Token ID262
Feature activation+1.06e+00

Pos logit contributions
aleb+0.070
rey+0.070
iper+0.069
asha+0.069
aman+0.067
Neg logit contributions
 Help-0.033
 What-0.031
 Do-0.031
 Was-0.029
 Where-0.029
Token market
Token ID1910
Feature activation+2.33e-01

Pos logit contributions
iper+0.028
rey+0.028
aleb+0.027
asha+0.026
aman+0.026
Neg logit contributions
 Help-0.028
 What-0.027
 Do-0.027
 Was-0.027
 Where-0.026
Token.
Token ID13
Feature activation+1.53e-01

Pos logit contributions
rey+0.009
aleb+0.009
iper+0.009
asha+0.009
aman+0.009
Neg logit contributions
 Help-0.003
 What-0.003
 Do-0.003
 Was-0.003
 Where-0.003
Token Oy
Token ID39447
Feature activation+4.11e+00

Pos logit contributions
rey+0.007
aleb+0.006
asha+0.006
aman+0.006
iper+0.006
Neg logit contributions
 What-0.002
 Do-0.002
 Help-0.002
 Where-0.002
 Was-0.002
Tokensters
Token ID5937
Feature activation+1.32e+00

Pos logit contributions
iper+0.112
rey+0.112
aman+0.108
aleb+0.106
asha+0.103
Neg logit contributions
 What-0.103
 Help-0.102
 Do-0.098
 Was-0.098
 Where-0.097
Token are
Token ID389
Feature activation+6.58e-01

Pos logit contributions
aleb+0.050
rey+0.049
asha+0.048
aman+0.048
iper+0.047
Neg logit contributions
 Help-0.022
 What-0.021
 Was-0.020
 Do-0.020
 tearing-0.019
Token very
Token ID845
Feature activation+1.43e-02

Pos logit contributions
aman+0.024
aleb+0.024
asha+0.024
rey+0.024
iper+0.023
Neg logit contributions
 Do-0.011
 Help-0.011
 What-0.011
 tearing-0.011
 destroying-0.010
Token valuable
Token ID8119
Feature activation+1.36e+00

Pos logit contributions
rey+0.000
asha+0.000
aman+0.000
aleb+0.000
iper+0.000
Neg logit contributions
 Help-0.000
 Do-0.000
 Was-0.000
 What-0.000
 tearing-0.000
Token.
Token ID13
Feature activation+1.68e-01

Pos logit contributions
rey+0.052
aleb+0.050
asha+0.050
aman+0.050
iper+0.049
Neg logit contributions
 Help-0.022
 What-0.021
 Do-0.021
 Was-0.020
 Where-0.019
Token idea
Token ID2126
Feature activation+4.09e-01

Pos logit contributions
rey+0.029
aleb+0.028
asha+0.027
iper+0.027
aman+0.026
Neg logit contributions
 Help-0.042
 What-0.041
 Was-0.040
 Do-0.040
 smashing-0.040
Token!"
Token ID2474
Feature activation+1.75e+00

Pos logit contributions
rey+0.015
aleb+0.014
asha+0.014
iper+0.014
aman+0.014
Neg logit contributions
 Help-0.007
 What-0.007
 Was-0.007
 Do-0.007
 smashing-0.006
Token
Token ID198
Feature activation+8.87e-01

Pos logit contributions
aleb+0.074
rey+0.072
asha+0.070
iper+0.068
ust+0.068
Neg logit contributions
 What-0.023
 Help-0.022
 Was-0.021
 Do-0.021
 Where-0.019
Token
Token ID198
Feature activation+5.30e-01

Pos logit contributions
rey+0.030
aleb+0.028
asha+0.028
iper+0.028
aman+0.027
Neg logit contributions
 smashing-0.017
 Help-0.017
 What-0.017
 destroying-0.017
 tearing-0.016
TokenBut
Token ID1537
Feature activation+1.21e+00

Pos logit contributions
rey+0.013
aleb+0.013
asha+0.012
iper+0.012
aman+0.012
Neg logit contributions
 Help-0.015
 What-0.015
 Was-0.015
 Do-0.015
 smashing-0.014
Token T
Token ID309
Feature activation+4.10e+00

Pos logit contributions
aleb+0.041
asha+0.040
rey+0.039
iper+0.039
aman+0.038
Neg logit contributions
 Help-0.023
 What-0.023
 Do-0.022
 tearing-0.021
 Was-0.021
Tokenerence
Token ID1945
Feature activation+5.95e-01

Pos logit contributions
aleb+0.065
aman+0.064
ishment+0.063
rey+0.062
asha+0.060
Neg logit contributions
 Help-0.135
 What-0.134
 Was-0.129
smart-0.126
 tearing-0.126
Token didn
Token ID1422
Feature activation+1.83e+00

Pos logit contributions
aleb+0.020
rey+0.019
aman+0.018
iper+0.018
oto+0.018
Neg logit contributions
 Help-0.011
 Was-0.011
 tearing-0.011
 smashing-0.011
 What-0.010
Token't
Token ID470
Feature activation-1.46e-01

Pos logit contributions
rey+0.072
aleb+0.071
iper+0.070
asha+0.070
aman+0.069
Neg logit contributions
 Help-0.025
 What-0.023
 Do-0.022
 Was-0.022
 Where-0.022
Token want
Token ID765
Feature activation-7.04e-01

Pos logit contributions
 Help+0.004
 What+0.004
 Was+0.004
 Do+0.004
 smashing+0.004
Neg logit contributions
rey-0.004
aleb-0.004
asha-0.004
iper-0.004
i-0.004
Token to
Token ID284
Feature activation-1.34e-01

Pos logit contributions
 Help+0.010
 Was+0.009
 smashing+0.009
 What+0.009
 Do+0.009
Neg logit contributions
rey-0.027
aleb-0.027
asha-0.026
iper-0.026
i-0.025
Token then
Token ID788
Feature activation-7.76e-01

Pos logit contributions
aleb+0.012
rey+0.012
asha+0.012
iper+0.011
aman+0.011
Neg logit contributions
 What-0.007
 Help-0.007
 Was-0.007
 Do-0.007
 Where-0.007
Token walking
Token ID6155
Feature activation-1.49e+00

Pos logit contributions
 Help+0.017
 Was+0.017
 What+0.017
 smashing+0.016
 tearing+0.016
Neg logit contributions
rey-0.025
aleb-0.024
iper-0.023
asha-0.023
iri-0.023
Token away
Token ID1497
Feature activation-1.09e+00

Pos logit contributions
 Help+0.027
 What+0.026
 Was+0.025
free+0.025
 Where+0.024
Neg logit contributions
aleb-0.053
rey-0.053
iper-0.051
asha-0.051
aman-0.050
Token.
Token ID13
Feature activation+6.73e-01

Pos logit contributions
 Help+0.019
 What+0.018
 Was+0.017
 smashing+0.017
 Where+0.017
Neg logit contributions
aleb-0.040
rey-0.040
iper-0.039
asha-0.038
aman-0.037
Token Little
Token ID7703
Feature activation+1.73e+00

Pos logit contributions
rey+0.025
aleb+0.025
asha+0.024
iper+0.024
aman+0.024
Neg logit contributions
 Help-0.011
 What-0.011
 Was-0.011
 Where-0.010
 Do-0.010
Token Cornel
Token ID48214
Feature activation+4.09e+00

Pos logit contributions
rey+0.045
iper+0.044
aleb+0.042
aman+0.041
icity+0.041
Neg logit contributions
 What-0.047
 Was-0.045
 Help-0.045
 Where-0.044
 Do-0.044
Tokenius
Token ID3754
Feature activation-3.76e-01

Pos logit contributions
isi+0.077
iper+0.076
asha+0.072
hel+0.070
ita+0.069
Neg logit contributions
 Help-0.130
 What-0.127
 Was-0.126
 smashing-0.122
 bulldo-0.120
Token was
Token ID373
Feature activation-4.74e-02

Pos logit contributions
 Help+0.007
 Was+0.007
 What+0.006
 tearing+0.006
 smashing+0.006
Neg logit contributions
rey-0.013
aleb-0.013
aman-0.012
asha-0.012
oto-0.012
Token so
Token ID523
Feature activation-1.20e-01

Pos logit contributions
 Help+0.001
 What+0.001
 tearing+0.001
 smashing+0.001
 Was+0.001
Neg logit contributions
rey-0.002
aleb-0.002
iper-0.002
asha-0.002
aman-0.002
Token proud
Token ID6613
Feature activation+9.52e-01

Pos logit contributions
 Help+0.002
 What+0.002
 Was+0.002
 tearing+0.002
 Where+0.002
Neg logit contributions
rey-0.004
asha-0.004
aleb-0.004
iper-0.004
aman-0.004
Token that
Token ID326
Feature activation+4.15e-01

Pos logit contributions
rey+0.041
aleb+0.039
iper+0.039
onia+0.038
icity+0.038
Neg logit contributions
 What-0.012
 Help-0.011
 Was-0.010
 Do-0.010
 tearing-0.010
Token so
Token ID523
Feature activation+2.40e-01

Pos logit contributions
 Help+0.002
 What+0.002
 Do+0.001
 tearing+0.001
 Was+0.001
Neg logit contributions
aleb-0.003
rey-0.003
iper-0.003
asha-0.003
aman-0.003
Token high
Token ID1029
Feature activation+7.57e-01

Pos logit contributions
rey+0.007
aleb+0.007
iper+0.007
asha+0.007
aman+0.007
Neg logit contributions
 Help-0.006
 What-0.006
 Do-0.005
 smashing-0.005
 Where-0.005
Token.
Token ID13
Feature activation+5.15e-01

Pos logit contributions
aleb+0.029
rey+0.029
iper+0.029
asha+0.028
aman+0.028
Neg logit contributions
 What-0.010
 destroying-0.010
free-0.010
 tearing-0.010
 v-0.010
Token However
Token ID2102
Feature activation-1.31e-01

Pos logit contributions
rey+0.018
aleb+0.018
asha+0.017
iper+0.017
aman+0.017
Neg logit contributions
 Help-0.009
 What-0.009
 Was-0.009
 Do-0.009
 Where-0.009
Token,
Token ID11
Feature activation+6.81e-01

Pos logit contributions
 Help+0.001
 What+0.001
 Do+0.001
 Where+0.001
 Was+0.001
Neg logit contributions
aleb-0.006
rey-0.006
asha-0.006
iper-0.005
isi-0.005
Token T
Token ID309
Feature activation+4.05e+00

Pos logit contributions
aleb+0.021
rey+0.020
asha+0.020
iper+0.020
aman+0.019
Neg logit contributions
 Help-0.016
 What-0.015
 Do-0.015
 Was-0.015
 Where-0.015
Tokenerence
Token ID1945
Feature activation+6.40e-01

Pos logit contributions
aleb+0.062
aman+0.061
rey+0.060
ishment+0.058
asha+0.058
Neg logit contributions
 What-0.136
 Help-0.135
 Was-0.129
 Do-0.127
 tearing-0.127
Token really
Token ID1107
Feature activation-1.17e-01

Pos logit contributions
aleb+0.023
aman+0.022
rey+0.022
oto+0.021
ishment+0.021
Neg logit contributions
 Help-0.011
 Was-0.011
 tearing-0.010
 smashing-0.010
 What-0.010
Token wanted
Token ID2227
Feature activation+3.23e-01

Pos logit contributions
 Help+0.002
 Was+0.002
 What+0.002
 tearing+0.002
 smashing+0.001
Neg logit contributions
aleb-0.004
rey-0.004
aman-0.004
onia-0.004
asha-0.004
Token to
Token ID284
Feature activation+7.32e-01

Pos logit contributions
rey+0.014
aleb+0.013
asha+0.013
iper+0.013
aman+0.013
Neg logit contributions
 Help-0.003
 What-0.003
 Was-0.003
 Do-0.003
 smashing-0.003
Token explore
Token ID7301
Feature activation+8.74e-01

Pos logit contributions
aleb+0.026
rey+0.025
iper+0.025
aman+0.025
asha+0.025
Neg logit contributions
 Help-0.015
 tearing-0.013
 What-0.013
 crash-0.013
 Where-0.012
Token so
Token ID523
Feature activation+5.53e-01

Pos logit contributions
rey+0.024
aleb+0.023
iper+0.023
asha+0.023
aman+0.023
Neg logit contributions
 What-0.014
 Do-0.014
 Help-0.014
 Was-0.014
 tearing-0.014
Token big
Token ID1263
Feature activation+2.07e+00

Pos logit contributions
rey+0.020
aman+0.019
asha+0.019
aleb+0.018
isi+0.018
Neg logit contributions
 What-0.011
 Help-0.010
 Where-0.010
 Was-0.010
 Do-0.010
Token and
Token ID290
Feature activation+4.06e-01

Pos logit contributions
rey+0.083
aleb+0.082
iri+0.081
asha+0.080
onia+0.080
Neg logit contributions
 What-0.031
 Do-0.031
 Was-0.028
 Where-0.028
 Help-0.027
Token special
Token ID2041
Feature activation+1.35e+00

Pos logit contributions
rey+0.013
aleb+0.013
asha+0.013
iper+0.013
aman+0.013
Neg logit contributions
 Do-0.009
 What-0.009
 Was-0.009
 tearing-0.009
 Help-0.009
Token.
Token ID13
Feature activation+1.03e+00

Pos logit contributions
rey+0.052
aleb+0.051
iper+0.050
asha+0.050
aman+0.050
Neg logit contributions
 What-0.022
 Help-0.021
 Was-0.020
 Do-0.020
 Where-0.020
Token Fel
Token ID13937
Feature activation+4.04e+00

Pos logit contributions
rey+0.032
aleb+0.032
asha+0.031
iper+0.031
aman+0.030
Neg logit contributions
 Help-0.022
 What-0.021
 Was-0.021
 Do-0.021
 Where-0.021
Tokenicity
Token ID8467
Feature activation-1.97e-01

Pos logit contributions
asha+0.042
aman+0.040
aleb+0.039
isi+0.037
rey+0.036
Neg logit contributions
 Help-0.154
 What-0.154
 Was-0.151
 Where-0.150
 tearing-0.149
Token was
Token ID373
Feature activation+2.24e-01

Pos logit contributions
 Help+0.004
 Was+0.004
 What+0.003
 tearing+0.003
 smashing+0.003
Neg logit contributions
aleb-0.007
aman-0.007
rey-0.007
asha-0.007
isi-0.006
Token so
Token ID523
Feature activation+6.02e-01

Pos logit contributions
rey+0.007
aleb+0.007
iper+0.006
asha+0.006
aman+0.006
Neg logit contributions
 Help-0.005
 What-0.005
 Was-0.005
 Do-0.005
 smashing-0.005
Token proud
Token ID6613
Feature activation+1.24e+00

Pos logit contributions
rey+0.019
aleb+0.018
asha+0.018
iper+0.018
aman+0.018
Neg logit contributions
 Help-0.014
 What-0.013
 Was-0.013
 Do-0.013
 Where-0.013
Token of
Token ID286
Feature activation+1.43e+00

Pos logit contributions
rey+0.053
aleb+0.051
iper+0.050
onia+0.050
asha+0.050
Neg logit contributions
 What-0.015
 Help-0.014
 Do-0.013
 Was-0.013
 Where-0.013
Token an
Token ID281
Feature activation+1.48e+00

Pos logit contributions
rey+0.072
aleb+0.072
iper+0.070
asha+0.070
aman+0.069
Neg logit contributions
 Help-0.046
 What-0.044
 tearing-0.042
 Do-0.042
 smashing-0.042
Token old
Token ID1468
Feature activation+1.94e+00

Pos logit contributions
rey+0.042
asha+0.041
aleb+0.040
aman+0.040
iper+0.039
Neg logit contributions
 Help-0.035
 tearing-0.034
 What-0.034
 destroying-0.034
 Where-0.033
Token tower
Token ID10580
Feature activation+5.90e-02

Pos logit contributions
aleb+0.050
rey+0.050
iper+0.048
asha+0.047
aman+0.046
Neg logit contributions
 Help-0.054
 What-0.051
 Was-0.051
 tearing-0.051
 smashing-0.051
Token.
Token ID13
Feature activation+3.97e-01

Pos logit contributions
rey+0.002
aleb+0.002
iper+0.002
asha+0.002
aman+0.002
Neg logit contributions
 Help-0.001
 What-0.001
 Was-0.001
 smashing-0.001
 tearing-0.001
Token Sir
Token ID7361
Feature activation+1.83e+00

Pos logit contributions
rey+0.013
aleb+0.013
iper+0.013
asha+0.013
aman+0.012
Neg logit contributions
 Help-0.008
 smashing-0.007
 tearing-0.007
 What-0.007
 Was-0.007
Token T
Token ID309
Feature activation+3.99e+00

Pos logit contributions
rey+0.044
aleb+0.043
asha+0.041
iper+0.041
aman+0.040
Neg logit contributions
 Help-0.053
 What-0.052
 Was-0.051
 Do-0.051
 Where-0.050
Tokenerence
Token ID1945
Feature activation+2.18e-01

Pos logit contributions
aleb+0.058
rey+0.058
aman+0.055
ishment+0.053
iper+0.053
Neg logit contributions
 What-0.140
 Help-0.138
 Was-0.135
 Do-0.133
 tearing-0.133
Token was
Token ID373
Feature activation+5.73e-01

Pos logit contributions
aleb+0.008
rey+0.008
iper+0.007
aman+0.007
asha+0.007
Neg logit contributions
 Help-0.004
 Was-0.004
 tearing-0.004
 smashing-0.004
 What-0.004
Token brave
Token ID14802
Feature activation+1.44e+00

Pos logit contributions
rey+0.019
aleb+0.018
asha+0.018
iper+0.018
aman+0.017
Neg logit contributions
 Help-0.012
 What-0.011
 Was-0.011
 Do-0.011
 Where-0.011
Token and
Token ID290
Feature activation+3.01e-01

Pos logit contributions
rey+0.045
aleb+0.044
asha+0.043
iper+0.043
aman+0.043
Neg logit contributions
 What-0.031
 Help-0.031
 Do-0.030
 tearing-0.030
 smashing-0.030
Token curious
Token ID11040
Feature activation+6.18e-01

Pos logit contributions
rey+0.009
aleb+0.009
aman+0.009
asha+0.009
iper+0.009
Neg logit contributions
 Help-0.007
 What-0.007
 Do-0.007
 Was-0.007
 smashing-0.006
Token rockets
Token ID20293
Feature activation+7.81e-01

Pos logit contributions
 Help+0.009
 What+0.008
 Do+0.008
 destroying+0.008
 tearing+0.008
Neg logit contributions
aleb-0.016
rey-0.016
asha-0.016
aman-0.016
iper-0.015
Token.
Token ID13
Feature activation+1.14e+00

Pos logit contributions
aleb+0.030
rey+0.030
asha+0.029
iper+0.029
aman+0.028
Neg logit contributions
 Help-0.012
 tearing-0.012
 smashing-0.012
 destroying-0.012
 What-0.012
Token
Token ID198
Feature activation+1.29e+00

Pos logit contributions
rey+0.040
aleb+0.040
asha+0.039
aman+0.038
i+0.038
Neg logit contributions
 What-0.021
 Help-0.021
 Was-0.020
 Where-0.020
 Do-0.020
Token
Token ID198
Feature activation+1.53e+00

Pos logit contributions
rey+0.048
aleb+0.048
asha+0.047
iper+0.047
aman+0.046
Neg logit contributions
 Help-0.020
 What-0.019
 Was-0.018
 Do-0.018
 Where-0.018
TokenLaura
Token ID43687
Feature activation-3.84e-01

Pos logit contributions
i+0.049
ishment+0.046
aman+0.045
aleb+0.045
iper+0.044
Neg logit contributions
 Help-0.032
 What-0.032
 Was-0.032
 Where-0.030
 Do-0.029
Token and
Token ID290
Feature activation+3.98e+00

Pos logit contributions
 Help+0.008
 Was+0.007
 What+0.007
 tearing+0.007
 smashing+0.007
Neg logit contributions
aleb-0.012
aman-0.012
rey-0.012
asha-0.012
iper-0.012
Token Connor
Token ID27599
Feature activation-4.28e-01

Pos logit contributions
ust+0.107
lights+0.096
argo+0.095
rig+0.093
rily+0.091
Neg logit contributions
 What-0.109
 Do-0.102
 Help-0.097
 "-0.097
 This-0.096
Token were
Token ID547
Feature activation-2.97e-01

Pos logit contributions
 Help+0.009
 What+0.009
 Was+0.009
 tearing+0.008
 smashing+0.008
Neg logit contributions
rey-0.013
aman-0.013
asha-0.013
aleb-0.013
iper-0.013
Token so
Token ID523
Feature activation-3.44e-01

Pos logit contributions
 Help+0.006
 What+0.006
 smashing+0.006
 tearing+0.006
 Do+0.006
Neg logit contributions
rey-0.010
aleb-0.010
asha-0.009
iper-0.009
aman-0.009
Token proud
Token ID6613
Feature activation+7.12e-01

Pos logit contributions
 Help+0.008
 What+0.007
 Was+0.007
 Do+0.007
 smashing+0.007
Neg logit contributions
rey-0.011
aleb-0.010
asha-0.010
iper-0.010
aman-0.010
Token of
Token ID286
Feature activation+1.09e+00

Pos logit contributions
rey+0.031
aleb+0.030
asha+0.030
iper+0.030
aman+0.029
Neg logit contributions
 Help-0.008
 What-0.008
 Do-0.007
 Was-0.007
 Where-0.007
Token smiled
Token ID13541
Feature activation+1.63e+00

Pos logit contributions
aleb+0.041
rey+0.040
aman+0.040
asha+0.039
iper+0.039
Neg logit contributions
 Help-0.035
 Was-0.033
 What-0.033
 tearing-0.033
 smashing-0.032
Token.
Token ID13
Feature activation+2.73e+00

Pos logit contributions
aleb+0.063
rey+0.062
iper+0.061
asha+0.061
icity+0.061
Neg logit contributions
 Help-0.025
 What-0.025
 "-0.022
 Was-0.022
joy-0.022
Token "
Token ID366
Feature activation+7.15e-01

Pos logit contributions
rey+0.134
aleb+0.132
i+0.130
iper+0.130
iri+0.129
Neg logit contributions
 What-0.019
 Help-0.017
 Was-0.015
 Do-0.014
 Where-0.014
TokenSure
Token ID19457
Feature activation+5.14e-01

Pos logit contributions
rey+0.022
aleb+0.021
iper+0.021
asha+0.021
aman+0.021
Neg logit contributions
 Help-0.016
 What-0.016
 Do-0.015
 Was-0.015
 Where-0.015
Token thing
Token ID1517
Feature activation+1.23e+00

Pos logit contributions
rey+0.020
aleb+0.019
asha+0.019
iper+0.019
aman+0.019
Neg logit contributions
 Help-0.008
 What-0.007
 Do-0.007
 Was-0.007
 Where-0.007
Token,"
Token ID553
Feature activation+3.97e+00

Pos logit contributions
rey+0.052
aleb+0.050
ishment+0.049
asha+0.049
aman+0.049
Neg logit contributions
 Help-0.016
 What-0.015
 Do-0.015
 Was-0.013
 Where-0.013
Token she
Token ID673
Feature activation+1.70e+00

Pos logit contributions
aleb+0.142
rey+0.141
iri+0.141
ust+0.138
icity+0.136
Neg logit contributions
 What-0.078
 "-0.077
 Help-0.076
 Was-0.071
 Do-0.068
Token said
Token ID531
Feature activation+1.35e+00

Pos logit contributions
aleb+0.046
aman+0.046
rey+0.045
iri+0.044
asha+0.043
Neg logit contributions
 Help-0.045
 Was-0.045
 What-0.043
 Where-0.041
 v-0.041
Token.
Token ID13
Feature activation+2.01e+00

Pos logit contributions
rey+0.037
iper+0.036
aleb+0.036
i+0.035
asha+0.034
Neg logit contributions
 What-0.032
 Was-0.032
 Do-0.032
 Help-0.031
 Where-0.031
Token
Token ID198
Feature activation+2.00e+00

Pos logit contributions
rey+0.090
aleb+0.089
asha+0.087
iper+0.086
i+0.085
Neg logit contributions
 Help-0.020
 What-0.020
 Do-0.018
 Was-0.017
 Where-0.017
Token
Token ID198
Feature activation+2.47e+00

Pos logit contributions
aleb+0.080
rey+0.080
i+0.078
iper+0.077
ishment+0.077
Neg logit contributions
 Help-0.027
 What-0.025
 Was-0.024
 Do-0.023
 Where-0.022
Token it
Token ID340
Feature activation-1.27e-01

Pos logit contributions
 Help+0.023
 What+0.022
 Was+0.021
 Do+0.021
 smashing+0.021
Neg logit contributions
rey-0.035
aleb-0.034
asha-0.033
iper-0.033
aman-0.033
Token on
Token ID319
Feature activation-9.85e-02

Pos logit contributions
 Help+0.003
 What+0.003
 Was+0.003
 Do+0.003
 smashing+0.003
Neg logit contributions
rey-0.004
aleb-0.004
asha-0.004
iper-0.004
aman-0.003
Token the
Token ID262
Feature activation+2.35e-01

Pos logit contributions
 Help+0.003
 What+0.003
 Was+0.003
 Do+0.003
 smashing+0.003
Neg logit contributions
rey-0.002
aleb-0.002
asha-0.002
iper-0.002
aman-0.002
Token chickens
Token ID25972
Feature activation-2.31e-01

Pos logit contributions
rey+0.006
aleb+0.006
asha+0.005
iper+0.005
aman+0.005
Neg logit contributions
 Help-0.007
 What-0.007
 Was-0.006
 smashing-0.006
 Do-0.006
Token.
Token ID13
Feature activation+2.94e-01

Pos logit contributions
 Help+0.004
 What+0.004
 tearing+0.004
 smashing+0.004
 Was+0.004
Neg logit contributions
rey-0.008
aleb-0.008
asha-0.008
iper-0.008
aman-0.008
Token Fel
Token ID13937
Feature activation+3.96e+00

Pos logit contributions
iper+0.008
rey+0.008
asha+0.007
aleb+0.007
ita+0.007
Neg logit contributions
 Help-0.007
 destroying-0.007
 smashing-0.007
 tearing-0.007
 Do-0.007
Tokenicity
Token ID8467
Feature activation-1.81e+00

Pos logit contributions
asha+0.034
rey+0.033
aleb+0.033
aman+0.033
onia+0.029
Neg logit contributions
 Help-0.160
 What-0.159
 tearing-0.157
 Was-0.156
 Where-0.155
Token blinked
Token ID40360
Feature activation-8.44e-01

Pos logit contributions
 Help+0.042
 What+0.041
 Do+0.040
 Was+0.039
 Where+0.039
Neg logit contributions
rey-0.054
aleb-0.052
iper-0.051
asha-0.051
aman-0.050
Token and
Token ID290
Feature activation+8.30e-01

Pos logit contributions
 Help+0.020
 What+0.020
 Was+0.019
 smashing+0.018
 tearing+0.018
Neg logit contributions
rey-0.025
aleb-0.025
iper-0.024
asha-0.024
aman-0.024
Token saw
Token ID2497
Feature activation-2.82e-01

Pos logit contributions
aleb+0.025
rey+0.025
iper+0.024
asha+0.024
aman+0.023
Neg logit contributions
 Help-0.019
 What-0.019
 Was-0.018
 Do-0.018
 tearing-0.018
Token that
Token ID326
Feature activation-8.00e-01

Pos logit contributions
 Help+0.006
 What+0.006
 Was+0.006
 Do+0.006
 Where+0.006
Neg logit contributions
rey-0.009
aleb-0.009
iper-0.009
asha-0.009
aman-0.008
Token
Token ID198
Feature activation+1.74e+00

Pos logit contributions
rey+0.085
aleb+0.083
aman+0.082
i+0.082
iper+0.082
Neg logit contributions
 What-0.048
 Help-0.047
 Where-0.045
 Was-0.044
 Do-0.043
Token
Token ID198
Feature activation+2.34e+00

Pos logit contributions
rey+0.066
aleb+0.065
iper+0.064
asha+0.064
aman+0.063
Neg logit contributions
 Help-0.027
 What-0.025
 Was-0.024
 Do-0.024
 Where-0.024
Token"
Token ID1
Feature activation+8.00e-01

Pos logit contributions
i+0.066
ishment+0.064
rey+0.062
aman+0.062
iper+0.061
Neg logit contributions
 Help-0.065
 What-0.062
 Was-0.059
 Where-0.059
 Do-0.058
TokenMom
Token ID29252
Feature activation-5.55e-01

Pos logit contributions
iper+0.031
i+0.030
aleb+0.029
ishment+0.029
rey+0.029
Neg logit contributions
 Help-0.014
 What-0.014
 Was-0.014
 Where-0.013
 Do-0.012
Tokenmy
Token ID1820
Feature activation+1.31e-02

Pos logit contributions
 Help+0.015
 What+0.015
 smashing+0.015
 Was+0.015
 Where+0.015
Neg logit contributions
rey-0.014
aleb-0.013
iper-0.013
aman-0.013
asha-0.013
Token,"
Token ID553
Feature activation+3.96e+00

Pos logit contributions
rey+0.000
aleb+0.000
iper+0.000
asha+0.000
aman+0.000
Neg logit contributions
 Help-0.000
 What-0.000
 Was-0.000
 Do-0.000
 smashing-0.000
Token asked
Token ID1965
Feature activation+2.17e+00

Pos logit contributions
ind+0.144
ust+0.142
iet+0.142
la+0.140
iri+0.139
Neg logit contributions
 Are-0.075
 What-0.075
 Help-0.074
 Do-0.070
 "-0.070
Token Charlie
Token ID11526
Feature activation+4.20e-01

Pos logit contributions
iri+0.061
ust+0.061
aman+0.061
asha+0.060
iet+0.059
Neg logit contributions
 Help-0.054
 What-0.051
 Where-0.049
 "-0.048
 The-0.047
Token,
Token ID11
Feature activation-5.84e-01

Pos logit contributions
rey+0.014
aleb+0.014
asha+0.013
iper+0.013
aman+0.013
Neg logit contributions
 Help-0.008
 What-0.008
 Was-0.008
 Do-0.008
 smashing-0.008
Token "
Token ID366
Feature activation+3.78e-01

Pos logit contributions
 Help+0.008
 What+0.007
 Was+0.007
 Do+0.007
 smashing+0.007
Neg logit contributions
rey-0.023
aleb-0.023
asha-0.022
iper-0.022
aman-0.022
TokenCan
Token ID6090
Feature activation+9.17e-01

Pos logit contributions
rey+0.013
aleb+0.012
iper+0.012
asha+0.012
aman+0.012
Neg logit contributions
 Help-0.008
 What-0.007
 Was-0.007
 Do-0.007
 Where-0.007
Token to
Token ID284
Feature activation+7.15e-01

Pos logit contributions
rey+0.074
aleb+0.073
iper+0.072
asha+0.071
aman+0.070
Neg logit contributions
 Help-0.013
 What-0.012
 Do-0.011
 Was-0.010
 Where-0.010
Token explore
Token ID7301
Feature activation+1.27e+00

Pos logit contributions
aleb+0.027
aman+0.027
ishment+0.027
asha+0.027
iper+0.026
Neg logit contributions
 Help-0.013
 This-0.011
 Where-0.011
 What-0.010
 have-0.010
Token the
Token ID262
Feature activation+1.92e+00

Pos logit contributions
aleb+0.047
rey+0.047
asha+0.046
iper+0.046
aman+0.046
Neg logit contributions
 Help-0.020
 What-0.020
 Do-0.019
 tearing-0.018
 destroying-0.018
Token woods
Token ID16479
Feature activation+6.52e-01

Pos logit contributions
iper+0.062
aleb+0.062
asha+0.061
rey+0.061
iri+0.059
Neg logit contributions
 Help-0.038
 What-0.037
 v-0.037
 Was-0.036
 building-0.035
Token near
Token ID1474
Feature activation+8.66e-01

Pos logit contributions
aleb+0.024
rey+0.024
asha+0.023
iper+0.023
aman+0.023
Neg logit contributions
 Help-0.011
 What-0.011
 Do-0.011
 tearing-0.010
 smashing-0.010
Token their
Token ID511
Feature activation+3.95e+00

Pos logit contributions
aleb+0.030
rey+0.030
iper+0.029
asha+0.029
aman+0.029
Neg logit contributions
 Help-0.017
 What-0.016
 Was-0.015
 Do-0.015
 tearing-0.015
Token home
Token ID1363
Feature activation-4.25e-01

Pos logit contributions
asha+0.134
onia+0.132
isi+0.131
iper+0.131
rey+0.129
Neg logit contributions
 Help-0.081
 What-0.074
 Was-0.069
 Where-0.068
 building-0.066
Token.
Token ID13
Feature activation+2.12e-01

Pos logit contributions
 Help+0.006
 What+0.005
 Was+0.005
 tearing+0.005
 Do+0.005
Neg logit contributions
aleb-0.018
rey-0.018
iper-0.017
asha-0.017
onia-0.017
Token
Token ID198
Feature activation+2.50e-01

Pos logit contributions
rey+0.008
aleb+0.008
asha+0.008
iper+0.008
i+0.007
Neg logit contributions
 What-0.004
 Help-0.004
 Where-0.003
 Was-0.003
 Do-0.003
Token
Token ID198
Feature activation+3.21e-01

Pos logit contributions
rey+0.009
aleb+0.009
asha+0.008
iper+0.008
aman+0.008
Neg logit contributions
 Help-0.004
 What-0.004
 smashing-0.004
 Do-0.004
 Was-0.004
TokenAs
Token ID1722
Feature activation+4.94e-01

Pos logit contributions
rey+0.009
aleb+0.009
iper+0.008
asha+0.008
i+0.008
Neg logit contributions
 Help-0.009
 What-0.008
 Was-0.008
 Do-0.008
 Where-0.008
Token could
Token ID714
Feature activation-5.61e-01

Pos logit contributions
 tearing+0.003
 Was+0.003
 What+0.002
 smashing+0.002
 destroying+0.002
Neg logit contributions
aleb-0.009
iper-0.008
rey-0.008
aman-0.008
iri-0.008
Token lift
Token ID10303
Feature activation+7.23e-02

Pos logit contributions
 Help+0.011
 Was+0.010
 What+0.010
 tearing+0.010
 Do+0.010
Neg logit contributions
aleb-0.020
rey-0.019
iper-0.019
aman-0.019
asha-0.019
Token a
Token ID257
Feature activation-5.78e-01

Pos logit contributions
aleb+0.002
rey+0.002
asha+0.002
aman+0.002
iper+0.002
Neg logit contributions
 What-0.001
 Help-0.001
 Do-0.001
 Was-0.001
 smashing-0.001
Token car
Token ID1097
Feature activation+7.96e-02

Pos logit contributions
 Help+0.015
smart+0.015
 What+0.014
 Do+0.014
 Where+0.014
Neg logit contributions
rey-0.015
aleb-0.014
asha-0.014
aman-0.014
iper-0.013
Token!
Token ID0
Feature activation+9.36e-01

Pos logit contributions
aleb+0.003
asha+0.003
rey+0.003
iper+0.003
iri+0.003
Neg logit contributions
 Help-0.001
 tearing-0.001
 What-0.001
 smashing-0.001
 knocking-0.001
Token Fel
Token ID13937
Feature activation+3.95e+00

Pos logit contributions
rey+0.029
aleb+0.029
asha+0.028
iper+0.027
aman+0.027
Neg logit contributions
 Help-0.021
 What-0.021
 Was-0.020
 Do-0.020
 Where-0.020
Tokenicity
Token ID8467
Feature activation-4.08e-01

Pos logit contributions
asha+0.038
aman+0.036
aleb+0.036
rey+0.035
isi+0.033
Neg logit contributions
 Help-0.154
 What-0.154
 Was-0.152
 tearing-0.151
 Where-0.150
Token's
Token ID338
Feature activation+1.48e+00

Pos logit contributions
 Help+0.008
 Was+0.008
 What+0.008
 tearing+0.008
 smashing+0.008
Neg logit contributions
rey-0.013
aleb-0.013
asha-0.013
aman-0.013
iper-0.013
Token mom
Token ID1995
Feature activation+1.98e-01

Pos logit contributions
rey+0.035
asha+0.034
aleb+0.033
aman+0.033
iper+0.032
Neg logit contributions
 Help-0.045
 What-0.043
 Was-0.043
 Where-0.042
 tearing-0.042
Tokenmy
Token ID1820
Feature activation+8.46e-01

Pos logit contributions
rey+0.006
aleb+0.006
asha+0.005
icity+0.005
iri+0.005
Neg logit contributions
 tearing-0.005
 Help-0.005
 What-0.004
 Was-0.004
 smashing-0.004
Token and
Token ID290
Feature activation+2.79e+00

Pos logit contributions
aleb+0.027
rey+0.027
asha+0.026
iri+0.026
icity+0.026
Neg logit contributions
 Help-0.016
 tearing-0.016
 Was-0.016
 smashing-0.016
 What-0.016
Token fork
Token ID15563
Feature activation+1.40e-01

Pos logit contributions
rey+0.004
aleb+0.004
asha+0.004
onia+0.003
iper+0.003
Neg logit contributions
smart-0.008
 Help-0.008
 What-0.008
 Do-0.008
 Those-0.008
Token that
Token ID326
Feature activation-4.47e-01

Pos logit contributions
rey+0.004
aleb+0.004
asha+0.004
i+0.004
aman+0.004
Neg logit contributions
 Help-0.003
 What-0.003
 Was-0.003
 Do-0.003
 Whe-0.003
Token big
Token ID1263
Feature activation+1.32e+00

Pos logit contributions
 What+0.009
 Was+0.009
 Help+0.009
 Where+0.008
 Do+0.008
Neg logit contributions
aleb-0.015
rey-0.015
iper-0.015
asha-0.015
aman-0.015
Token before
Token ID878
Feature activation+2.02e+00

Pos logit contributions
rey+0.037
aleb+0.036
asha+0.035
iper+0.035
aman+0.034
Neg logit contributions
 Help-0.032
 What-0.031
 Was-0.031
 Do-0.031
 Where-0.030
Token!
Token ID0
Feature activation+9.44e-01

Pos logit contributions
aleb+0.079
rey+0.077
iper+0.074
asha+0.073
onia+0.071
Neg logit contributions
 Help-0.033
 What-0.031
 tearing-0.031
 Do-0.030
 Was-0.029
Token Fel
Token ID13937
Feature activation+3.93e+00

Pos logit contributions
rey+0.031
aleb+0.030
asha+0.029
iper+0.029
aman+0.029
Neg logit contributions
 Help-0.019
 What-0.019
 Was-0.018
 Do-0.018
 Where-0.018
Tokenicity
Token ID8467
Feature activation-9.63e-01

Pos logit contributions
asha+0.035
aleb+0.034
aman+0.034
rey+0.033
isi+0.031
Neg logit contributions
 Help-0.158
 What-0.157
 tearing-0.155
 Was-0.155
 Where-0.153
Token was
Token ID373
Feature activation+5.28e-01

Pos logit contributions
 Help+0.020
 Was+0.019
 What+0.018
 tearing+0.018
 smashing+0.017
Neg logit contributions
rey-0.032
aleb-0.032
aman-0.031
asha-0.031
iper-0.030
Token so
Token ID523
Feature activation+1.00e+00

Pos logit contributions
rey+0.015
aleb+0.014
iper+0.014
asha+0.014
aman+0.014
Neg logit contributions
 Help-0.013
 What-0.012
 Do-0.012
 Was-0.012
 Where-0.012
Token excited
Token ID6568
Feature activation+1.91e+00

Pos logit contributions
rey+0.029
aleb+0.028
asha+0.028
iper+0.028
aman+0.027
Neg logit contributions
 Help-0.025
 What-0.024
 Was-0.024
 Do-0.023
 Where-0.023
Token!
Token ID0
Feature activation+1.04e+00

Pos logit contributions
rey+0.085
aleb+0.084
iper+0.080
otton+0.080
iri+0.078
Neg logit contributions
 What-0.020
 to-0.018
 Do-0.015
 tearing-0.015
 Help-0.015
Token not
Token ID407
Feature activation-1.51e+00

Pos logit contributions
 Was+0.007
 Help+0.007
 Where+0.007
 bulldo+0.007
 Whe+0.007
Neg logit contributions
rey-0.004
oto-0.003
aleb-0.003
hel-0.003
pa-0.003
Token want
Token ID765
Feature activation-8.45e-01

Pos logit contributions
 Help+0.046
 Was+0.045
 What+0.044
 Want+0.044
 Where+0.043
Neg logit contributions
aleb-0.030
rey-0.029
oto-0.029
isi-0.028
i-0.028
Token to
Token ID284
Feature activation-2.00e+00

Pos logit contributions
 Help+0.013
 What+0.012
 Was+0.012
 Do+0.012
 smashing+0.012
Neg logit contributions
rey-0.032
aleb-0.031
iper-0.030
asha-0.030
aman-0.029
Token play
Token ID711
Feature activation-2.22e+00

Pos logit contributions
 Was+0.055
joy+0.054
 What+0.054
 Want+0.053
 Do+0.052
Neg logit contributions
rey-0.049
aleb-0.046
pa-0.046
i-0.044
oto-0.043
Token with
Token ID351
Feature activation+2.51e-01

Pos logit contributions
 Want+0.050
 Help+0.049
 Was+0.049
 What+0.049
 Do+0.048
Neg logit contributions
rey-0.057
hel-0.055
aleb-0.054
aman-0.053
 jackets-0.052
Token each
Token ID1123
Feature activation-4.47e+00

Pos logit contributions
rey+0.009
asha+0.009
aman+0.009
iper+0.009
aleb+0.009
Neg logit contributions
 Help-0.004
 What-0.004
 tearing-0.004
 smashing-0.004
 Do-0.004
Token other
Token ID584
Feature activation-1.42e+00

Pos logit contributions
onna+0.151
 Was+0.149
 Want+0.146
joy+0.142
 What+0.142
Neg logit contributions
pa-0.067
rey-0.065
 uncle-0.064
aleb-0.063
i-0.059
Token anymore
Token ID7471
Feature activation-1.03e+00

Pos logit contributions
 Help+0.025
 What+0.025
 Do+0.024
 Was+0.024
 smashing+0.023
Neg logit contributions
rey-0.051
asha-0.050
aleb-0.050
iper-0.049
aman-0.049
Token.
Token ID13
Feature activation-5.42e-02

Pos logit contributions
 Help+0.024
 What+0.023
 Was+0.023
 Do+0.023
 smashing+0.023
Neg logit contributions
rey-0.030
aleb-0.028
asha-0.028
iper-0.027
i-0.027
Token They
Token ID1119
Feature activation+8.68e-01

Pos logit contributions
 smashing+0.001
 Help+0.001
 tearing+0.001
 destroying+0.001
free+0.001
Neg logit contributions
rey-0.001
aleb-0.001
asha-0.001
iper-0.001
aman-0.001
Token sit
Token ID1650
Feature activation-9.16e-01

Pos logit contributions
rey+0.030
asha+0.029
aman+0.029
aleb+0.028
iper+0.028
Neg logit contributions
 What-0.017
 Help-0.017
 Was-0.017
 tearing-0.016
 Do-0.016
Token sister
Token ID6621
Feature activation-1.22e+00

Pos logit contributions
rey+0.013
asha+0.013
aleb+0.012
iper+0.012
aman+0.012
Neg logit contributions
 Help-0.028
 What-0.027
 Was-0.026
 smashing-0.026
 tearing-0.026
Token yelled
Token ID22760
Feature activation-9.08e-01

Pos logit contributions
 Help+0.022
 What+0.021
 Was+0.021
 Do+0.020
 smashing+0.020
Neg logit contributions
rey-0.043
aleb-0.042
asha-0.041
iper-0.041
aman-0.041
Token,
Token ID11
Feature activation-1.25e+00

Pos logit contributions
 Help+0.021
 Was+0.020
 What+0.020
 Do+0.020
 Where+0.019
Neg logit contributions
rey-0.027
aleb-0.026
iper-0.025
asha-0.025
aman-0.025
Token "
Token ID366
Feature activation-9.60e-01

Pos logit contributions
 Help+0.013
 Was+0.012
 What+0.011
 Do+0.011
 Where+0.011
Neg logit contributions
rey-0.051
aleb-0.049
aman-0.049
asha-0.049
iper-0.049
TokenLook
Token ID8567
Feature activation-1.16e+00

Pos logit contributions
 What+0.018
 Help+0.018
 Was+0.017
 Do+0.017
 smashing+0.017
Neg logit contributions
rey-0.033
iper-0.033
aleb-0.032
asha-0.032
icity-0.031
Token out
Token ID503
Feature activation-4.33e+00

Pos logit contributions
 Help+0.024
 What+0.024
 Was+0.022
 Do+0.022
 Where+0.022
Neg logit contributions
rey-0.038
aleb-0.037
asha-0.036
iper-0.036
aman-0.035
Token!"
Token ID2474
Feature activation-3.09e-01

Pos logit contributions
 Whe+0.110
 Was+0.109
 Do+0.106
 Blood+0.103
 Did+0.102
Neg logit contributions
rey-0.104
aleb-0.100
i-0.096
aman-0.094
iper-0.093
Token A
Token ID317
Feature activation-8.35e-01

Pos logit contributions
 Help+0.006
 Do+0.006
 smashing+0.006
 What+0.006
 Was+0.006
Neg logit contributions
rey-0.009
aman-0.009
aleb-0.009
asha-0.009
iper-0.009
Token big
Token ID1263
Feature activation+5.19e-01

Pos logit contributions
 What+0.021
 Help+0.021
 Do+0.021
 Where+0.021
 Was+0.020
Neg logit contributions
rey-0.023
aleb-0.021
asha-0.021
iper-0.020
onia-0.019
Token fish
Token ID5916
Feature activation+2.69e-01

Pos logit contributions
rey+0.015
aleb+0.014
asha+0.014
iper+0.013
aman+0.013
Neg logit contributions
 Help-0.013
 What-0.013
 Was-0.013
 Do-0.012
 Where-0.012
Token jumped
Token ID11687
Feature activation+4.05e-01

Pos logit contributions
rey+0.009
aleb+0.009
iper+0.009
asha+0.009
aman+0.009
Neg logit contributions
 Help-0.005
 What-0.005
 Was-0.005
 Do-0.005
 smashing-0.005
Token had
Token ID550
Feature activation-1.32e+00

Pos logit contributions
 Help+0.027
 What+0.026
 Was+0.025
 Do+0.025
 Where+0.025
Neg logit contributions
rey-0.040
aleb-0.038
iper-0.037
asha-0.037
aman-0.036
Token fun
Token ID1257
Feature activation-1.36e+00

Pos logit contributions
 Help+0.031
 What+0.031
 Do+0.030
 Was+0.030
 smashing+0.029
Neg logit contributions
rey-0.039
aleb-0.038
asha-0.037
iper-0.037
aman-0.036
Token.
Token ID13
Feature activation-2.56e-01

Pos logit contributions
 Help+0.040
 Was+0.040
 Where+0.040
 What+0.038
 Do+0.038
Neg logit contributions
rey-0.029
i-0.026
aleb-0.026
pa-0.025
ita-0.025
Token They
Token ID1119
Feature activation-9.70e-01

Pos logit contributions
 Help+0.006
 smashing+0.005
 tearing+0.005
 Was+0.005
 destroying+0.005
Neg logit contributions
rey-0.008
aleb-0.008
asha-0.007
iper-0.007
aman-0.007
Token made
Token ID925
Feature activation-1.77e-01

Pos logit contributions
 Was+0.014
 Help+0.014
 tearing+0.014
 What+0.014
 Do+0.013
Neg logit contributions
aman-0.035
aleb-0.035
rey-0.035
iper-0.035
asha-0.035
Token each
Token ID1123
Feature activation-4.30e+00

Pos logit contributions
 Help+0.004
 What+0.004
 smashing+0.004
 tearing+0.003
 Do+0.003
Neg logit contributions
rey-0.006
aleb-0.006
asha-0.006
iper-0.005
aman-0.005
Token other
Token ID584
Feature activation-1.21e+00

Pos logit contributions
 Was+0.129
 Help+0.129
 Where+0.129
 Do+0.126
 What+0.126
Neg logit contributions
rey-0.094
aleb-0.084
ita-0.079
iper-0.079
pa-0.077
Token happy
Token ID3772
Feature activation-6.31e-01

Pos logit contributions
 Help+0.025
 What+0.024
 Do+0.023
 Was+0.023
 smashing+0.023
Neg logit contributions
rey-0.039
aleb-0.039
asha-0.038
iper-0.038
aman-0.037
Token.
Token ID13
Feature activation-6.24e-02

Pos logit contributions
 Help+0.015
 Was+0.015
 Do+0.015
 Where+0.015
 What+0.015
Neg logit contributions
rey-0.018
aleb-0.017
asha-0.016
i-0.016
iper-0.016
Token<|endoftext|>
Token ID50256
Feature activation-8.43e-01

Pos logit contributions
 Help+0.001
 smashing+0.001
 tearing+0.001
 Was+0.001
 destroying+0.001
Neg logit contributions
rey-0.002
aleb-0.002
asha-0.002
iper-0.002
aman-0.002
TokenL
Token ID43
Feature activation-4.13e-01

Pos logit contributions
 smashing+0.021
 Help+0.020
 tearing+0.019
 destroying+0.019
 knocking+0.019
Neg logit contributions
rey-0.024
aleb-0.022
hel-0.021
asha-0.021
onia-0.020
Tokenmy
Token ID1820
Feature activation-9.72e-01

Pos logit contributions
 What+0.016
 tearing+0.015
 Help+0.015
 Was+0.015
 Do+0.015
Neg logit contributions
asha-0.020
rey-0.019
iper-0.019
aleb-0.019
ishment-0.019
Token and
Token ID290
Feature activation-8.14e-02

Pos logit contributions
 Help+0.016
 What+0.016
 Was+0.016
 tearing+0.015
 Do+0.015
Neg logit contributions
rey-0.034
aleb-0.034
asha-0.034
aman-0.034
ishment-0.033
Token the
Token ID262
Feature activation-1.84e+00

Pos logit contributions
 Help+0.002
 What+0.002
 Do+0.002
 Whe+0.002
 tearing+0.002
Neg logit contributions
rey-0.002
asha-0.002
iper-0.002
onia-0.002
aman-0.002
Token kid
Token ID5141
Feature activation-9.55e-01

Pos logit contributions
 Help+0.046
 Do+0.045
 What+0.045
 smashing+0.044
 Was+0.044
Neg logit contributions
rey-0.051
aleb-0.050
asha-0.047
iper-0.047
aman-0.046
Token loved
Token ID6151
Feature activation-1.88e-01

Pos logit contributions
 What+0.019
 Help+0.019
 Was+0.019
 Do+0.018
 tearing+0.017
Neg logit contributions
rey-0.032
asha-0.031
aleb-0.031
aman-0.030
iper-0.030
Token each
Token ID1123
Feature activation-4.27e+00

Pos logit contributions
 Help+0.002
 What+0.002
 Was+0.002
 Do+0.002
 Where+0.002
Neg logit contributions
rey-0.008
aleb-0.007
iper-0.007
asha-0.007
aman-0.007
Token other
Token ID584
Feature activation-1.58e+00

Pos logit contributions
 Was+0.126
 Help+0.125
 Do+0.123
smart+0.121
 smashing+0.119
Neg logit contributions
aleb-0.094
rey-0.093
ita-0.087
iper-0.085
asha-0.084
Token very
Token ID845
Feature activation-5.85e-01

Pos logit contributions
 Help+0.034
 What+0.032
 Was+0.032
 Do+0.032
 smashing+0.031
Neg logit contributions
rey-0.050
aleb-0.049
iper-0.047
asha-0.047
aman-0.046
Token much
Token ID881
Feature activation+7.91e-01

Pos logit contributions
 Help+0.007
 What+0.007
 Was+0.006
 Do+0.006
 tearing+0.006
Neg logit contributions
rey-0.024
asha-0.023
aleb-0.023
iper-0.023
aman-0.023
Token.
Token ID13
Feature activation-2.18e-01

Pos logit contributions
rey+0.032
asha+0.031
iper+0.031
aleb+0.031
aman+0.030
Neg logit contributions
 What-0.010
 Help-0.010
 Was-0.009
 Do-0.009
free-0.009
Token They
Token ID1119
Feature activation+9.15e-02

Pos logit contributions
 What+0.004
 Help+0.004
 Do+0.003
 Was+0.003
 Where+0.003
Neg logit contributions
rey-0.008
iper-0.008
aleb-0.008
asha-0.008
i-0.008
TokenI
Token ID40
Feature activation-9.38e-01

Pos logit contributions
rey+0.006
aleb+0.006
asha+0.006
iper+0.005
aman+0.005
Neg logit contributions
 Help-0.005
 What-0.005
 Do-0.005
 Was-0.005
 smashing-0.005
Token'm
Token ID1101
Feature activation-4.11e-01

Pos logit contributions
 smashing+0.021
 tearing+0.021
 Blood+0.021
 Glass+0.021
smart+0.020
Neg logit contributions
aleb-0.023
rey-0.023
ust-0.022
hel-0.022
i-0.022
Token sorry
Token ID7926
Feature activation-1.00e+00

Pos logit contributions
 Was+0.007
 Help+0.007
 What+0.007
 Where+0.007
 Do+0.007
Neg logit contributions
rey-0.014
aleb-0.013
iper-0.013
aman-0.013
asha-0.013
Token"
Token ID1
Feature activation+6.61e-01

Pos logit contributions
 Was+0.021
 smashing+0.021
 Help+0.021
 tearing+0.020
 destroying+0.020
Neg logit contributions
rey-0.029
aleb-0.028
i-0.028
iper-0.027
oto-0.027
Token to
Token ID284
Feature activation-1.26e+00

Pos logit contributions
iper+0.023
aleb+0.023
rey+0.023
aman+0.023
asha+0.022
Neg logit contributions
 What-0.012
 Help-0.011
 Do-0.011
 Was-0.011
 Where-0.011
Token each
Token ID1123
Feature activation-4.15e+00

Pos logit contributions
 Was+0.030
 Help+0.030
 What+0.029
 Where+0.029
free+0.028
Neg logit contributions
rey-0.036
aleb-0.033
iper-0.032
aman-0.032
asha-0.032
Token other
Token ID584
Feature activation-1.86e+00

Pos logit contributions
 Was+0.126
 What+0.122
onna+0.121
 Where+0.120
 Do+0.120
Neg logit contributions
rey-0.088
aleb-0.086
pa-0.075
aman-0.075
isi-0.074
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
 Help+0.044
 Was+0.043
 What+0.042
 Do+0.042
 Where+0.041
Neg logit contributions
rey-0.053
aleb-0.052
iper-0.050
asha-0.049
aman-0.048
Token They
Token ID1119
Feature activation-1.75e-01

Pos logit contributions
rey+0.004
aman+0.004
aleb+0.004
asha+0.003
 Charles+0.003
Neg logit contributions
 destroying-0.006
 smashing-0.006
 bulldo-0.006
free-0.006
 tearing-0.005
Token hug
Token ID16225
Feature activation-5.89e-01

Pos logit contributions
 Help+0.004
 What+0.004
 Was+0.004
 tearing+0.004
 smashing+0.004
Neg logit contributions
rey-0.006
asha-0.005
aleb-0.005
aman-0.005
iper-0.005
Token and
Token ID290
Feature activation-5.07e-01

Pos logit contributions
 Help+0.014
 What+0.014
 Do+0.014
 Was+0.013
 smashing+0.013
Neg logit contributions
rey-0.017
aleb-0.017
iper-0.017
asha-0.017
aman-0.016
Token They
Token ID1119
Feature activation-9.68e-01

Pos logit contributions
 Help+0.019
 smashing+0.019
 tearing+0.018
 destroying+0.018
 Was+0.018
Neg logit contributions
rey-0.019
aleb-0.019
asha-0.018
aman-0.018
iper-0.018
Token had
Token ID550
Feature activation-6.55e-01

Pos logit contributions
 Help+0.018
 Was+0.018
 tearing+0.018
 smashing+0.017
 What+0.017
Neg logit contributions
rey-0.033
aman-0.032
aleb-0.032
asha-0.032
iper-0.032
Token fun
Token ID1257
Feature activation-1.13e+00

Pos logit contributions
 Help+0.019
 What+0.018
 Was+0.018
 Where+0.018
 Do+0.018
Neg logit contributions
rey-0.015
aleb-0.015
asha-0.014
iper-0.014
aman-0.014
Token and
Token ID290
Feature activation-1.07e+00

Pos logit contributions
 Where+0.040
 Was+0.039
 Help+0.038
 Want+0.037
 What+0.037
Neg logit contributions
rey-0.014
hel-0.013
pa-0.011
ishment-0.011
i-0.011
Token made
Token ID925
Feature activation-3.44e-01

Pos logit contributions
 Help+0.025
 What+0.024
 Was+0.024
 Do+0.023
 Where+0.023
Neg logit contributions
rey-0.031
aleb-0.030
iper-0.030
asha-0.029
aman-0.029
Token each
Token ID1123
Feature activation-4.15e+00

Pos logit contributions
 What+0.007
 Help+0.007
 tearing+0.007
 smashing+0.007
 Do+0.007
Neg logit contributions
rey-0.011
aleb-0.011
asha-0.011
iper-0.011
aman-0.011
Token other
Token ID584
Feature activation-1.42e+00

Pos logit contributions
 Help+0.130
 Was+0.128
onna+0.125
 Where+0.125
smart+0.124
Neg logit contributions
rey-0.082
aleb-0.075
ita-0.070
iper-0.067
asha-0.065
Token laugh
Token ID6487
Feature activation-8.93e-01

Pos logit contributions
 Help+0.031
 What+0.029
 Was+0.029
 Do+0.029
 Where+0.028
Neg logit contributions
rey-0.044
aleb-0.043
iper-0.042
asha-0.042
aman-0.041
Token.
Token ID13
Feature activation-4.48e-01

Pos logit contributions
 Help+0.017
 What+0.017
 Do+0.016
 Was+0.016
 smashing+0.016
Neg logit contributions
rey-0.030
aleb-0.030
asha-0.030
iper-0.030
aman-0.029
Token Mom
Token ID11254
Feature activation-7.95e-01

Pos logit contributions
 smashing+0.011
 Help+0.010
 tearing+0.010
 destroying+0.010
smart+0.010
Neg logit contributions
rey-0.012
aleb-0.012
asha-0.012
aman-0.011
iper-0.011
Token smiled
Token ID13541
Feature activation+1.36e-01

Pos logit contributions
 Help+0.015
 What+0.015
 Was+0.015
 tearing+0.015
 smashing+0.015
Neg logit contributions
rey-0.026
aleb-0.026
iper-0.025
asha-0.025
aman-0.025
Token'm
Token ID1101
Feature activation-6.78e-01

Pos logit contributions
 Help+0.032
 What+0.031
 Do+0.030
 smashing+0.030
 tearing+0.030
Neg logit contributions
rey-0.046
aleb-0.045
asha-0.043
iper-0.043
aman-0.042
Token sorry
Token ID7926
Feature activation-1.22e+00

Pos logit contributions
 Help+0.009
 What+0.009
 Do+0.009
 tearing+0.008
 Was+0.008
Neg logit contributions
rey-0.027
aleb-0.027
asha-0.026
iper-0.026
aman-0.026
Token"
Token ID1
Feature activation-1.22e-01

Pos logit contributions
 Help+0.024
 Was+0.023
 smashing+0.023
 tearing+0.023
 What+0.023
Neg logit contributions
rey-0.039
aleb-0.038
iper-0.037
asha-0.037
i-0.036
Token and
Token ID290
Feature activation-9.25e-01

Pos logit contributions
 What+0.002
 Do+0.002
 Was+0.002
 Help+0.002
 Where+0.002
Neg logit contributions
aleb-0.004
rey-0.004
iper-0.004
aman-0.004
asha-0.004
Token hugged
Token ID41130
Feature activation-1.36e+00

Pos logit contributions
 Help+0.014
 smashing+0.014
 Was+0.014
 destroying+0.013
free+0.013
Neg logit contributions
rey-0.029
aleb-0.029
i-0.028
iper-0.027
aman-0.027
Token each
Token ID1123
Feature activation-4.13e+00

Pos logit contributions
 Help+0.025
 What+0.025
 Do+0.024
 Was+0.023
 Where+0.023
Neg logit contributions
rey-0.047
aleb-0.047
aman-0.046
iper-0.046
asha-0.046
Token other
Token ID584
Feature activation-1.97e+00

Pos logit contributions
 tearing+0.117
 Help+0.117
 destroying+0.116
 smashing+0.116
 Was+0.116
Neg logit contributions
rey-0.093
aleb-0.091
iper-0.084
asha-0.083
oto-0.083
Token.
Token ID13
Feature activation-3.82e-01

Pos logit contributions
 Help+0.037
 What+0.036
 Do+0.034
 Was+0.034
 smashing+0.033
Neg logit contributions
rey-0.069
aleb-0.067
asha-0.067
iper-0.066
aman-0.066
Token
Token ID198
Feature activation-7.59e-01

Pos logit contributions
 smashing+0.009
 destroying+0.009
 tearing+0.009
 bulldo+0.009
 knocking+0.009
Neg logit contributions
rey-0.010
aleb-0.009
aman-0.009
asha-0.009
onia-0.009
Token
Token ID198
Feature activation-4.88e-01

Pos logit contributions
 smashing+0.016
 Help+0.016
 tearing+0.015
 destroying+0.015
 Want+0.015
Neg logit contributions
rey-0.024
aleb-0.022
iper-0.022
oto-0.022
asha-0.022
TokenThey
Token ID2990
Feature activation-9.39e-01

Pos logit contributions
 Help+0.015
 What+0.014
 Was+0.014
 Do+0.014
 smashing+0.014
Neg logit contributions
rey-0.011
aleb-0.011
iper-0.011
asha-0.011
aman-0.011
Token.
Token ID13
Feature activation-5.52e-01

Pos logit contributions
 Help+0.036
 Was+0.035
 Do+0.035
 What+0.035
 Where+0.034
Neg logit contributions
rey-0.032
aleb-0.031
asha-0.030
iper-0.030
i-0.029
Token
Token ID198
Feature activation-1.42e-01

Pos logit contributions
 smashing+0.014
 destroying+0.014
free+0.014
 tearing+0.014
 knocking+0.013
Neg logit contributions
rey-0.013
asha-0.013
aleb-0.013
 Stanley-0.013
 Hugo-0.013
Token
Token ID198
Feature activation-4.51e-01

Pos logit contributions
 smashing+0.004
 destroying+0.004
 tearing+0.003
free+0.003
 knocking+0.003
Neg logit contributions
rey-0.004
aleb-0.004
asha-0.004
oto-0.003
iper-0.003
Token"
Token ID1
Feature activation-7.34e-01

Pos logit contributions
 Help+0.010
 tearing+0.010
 smashing+0.010
 What+0.010
 destroying+0.010
Neg logit contributions
rey-0.013
aleb-0.013
asha-0.012
iper-0.012
aman-0.012
TokenLook
Token ID8567
Feature activation-1.06e+00

Pos logit contributions
 Help+0.018
 What+0.017
 Was+0.017
 Do+0.017
 smashing+0.017
Neg logit contributions
rey-0.021
aleb-0.021
asha-0.020
iper-0.020
aman-0.020
Token out
Token ID503
Feature activation-4.11e+00

Pos logit contributions
 Help+0.023
 Was+0.022
 smashing+0.022
 Do+0.022
 What+0.021
Neg logit contributions
rey-0.033
aleb-0.033
iper-0.032
i-0.031
asha-0.031
Token,
Token ID11
Feature activation-9.88e-01

Pos logit contributions
 Whe+0.112
 Was+0.109
 Do+0.105
Are+0.103
 Did+0.103
Neg logit contributions
rey-0.089
i-0.086
aleb-0.083
pa-0.081
iet-0.081
Token dog
Token ID3290
Feature activation-2.53e-01

Pos logit contributions
 Help+0.021
 Was+0.020
 What+0.020
 smashing+0.020
 Do+0.020
Neg logit contributions
rey-0.031
aleb-0.030
iper-0.029
asha-0.029
aman-0.029
Token!"
Token ID2474
Feature activation+6.53e-01

Pos logit contributions
 Help+0.005
 What+0.005
 Was+0.005
 Do+0.005
 Where+0.005
Neg logit contributions
rey-0.008
aleb-0.008
asha-0.008
iper-0.008
aman-0.008
Token Ben
Token ID3932
Feature activation+1.39e+00

Pos logit contributions
rey+0.021
aleb+0.021
iper+0.020
asha+0.020
aman+0.020
Neg logit contributions
 Help-0.014
 What-0.014
 Do-0.013
 Was-0.013
 Where-0.013
Token shouts
Token ID34757
Feature activation-8.88e-01

Pos logit contributions
rey+0.042
aleb+0.041
aman+0.041
asha+0.040
iper+0.040
Neg logit contributions
 Help-0.034
 What-0.033
 Do-0.032
 Was-0.032
 tearing-0.032
Token share
Token ID2648
Feature activation-1.20e+00

Pos logit contributions
 Help+0.024
 What+0.022
 Do+0.022
 Was+0.022
 tearing+0.022
Neg logit contributions
rey-0.035
aleb-0.035
asha-0.034
iper-0.034
aman-0.033
Token and
Token ID290
Feature activation-6.35e-01

Pos logit contributions
 Help+0.028
 What+0.027
 Was+0.026
 Where+0.026
 Do+0.026
Neg logit contributions
rey-0.036
aleb-0.035
asha-0.034
iper-0.034
aman-0.033
Token be
Token ID307
Feature activation-2.48e+00

Pos logit contributions
 Help+0.012
 What+0.011
 Do+0.011
 Was+0.011
 tearing+0.010
Neg logit contributions
rey-0.023
aleb-0.023
asha-0.022
iper-0.022
aman-0.022
Token nice
Token ID3621
Feature activation-2.23e-01

Pos logit contributions
 Help+0.057
 What+0.055
 Was+0.054
 Where+0.053
 smashing+0.053
Neg logit contributions
rey-0.075
aleb-0.073
iper-0.070
asha-0.070
aman-0.068
Token to
Token ID284
Feature activation-8.60e-01

Pos logit contributions
 Help+0.004
 What+0.004
 Do+0.004
 Was+0.004
 Where+0.004
Neg logit contributions
rey-0.008
aleb-0.008
asha-0.008
iper-0.007
aman-0.007
Token each
Token ID1123
Feature activation-4.09e+00

Pos logit contributions
 smashing+0.030
 Was+0.030
 Help+0.029
 bulldo+0.029
 Where+0.029
Neg logit contributions
rey-0.015
aleb-0.013
i-0.013
 Him-0.012
iper-0.012
Token other
Token ID584
Feature activation-1.46e-01

Pos logit contributions
 Was+0.132
 smashing+0.130
 Where+0.130
 Help+0.129
 tearing+0.128
Neg logit contributions
rey-0.079
aleb-0.077
oto-0.072
asha-0.072
i-0.072
Token."
Token ID526
Feature activation-1.80e-01

Pos logit contributions
 Help+0.002
free+0.002
 What+0.002
 Do+0.002
 tearing+0.002
Neg logit contributions
rey-0.006
asha-0.006
aman-0.006
aleb-0.006
iper-0.006
Token Lily
Token ID20037
Feature activation+9.88e-01

Pos logit contributions
 Help+0.003
 smashing+0.003
 Was+0.003
 What+0.003
 tearing+0.003
Neg logit contributions
rey-0.006
aleb-0.006
iper-0.006
asha-0.006
aman-0.006
Token and
Token ID290
Feature activation+4.43e-01

Pos logit contributions
rey+0.029
aleb+0.029
aman+0.028
iper+0.028
asha+0.027
Neg logit contributions
 Help-0.022
 What-0.021
 tearing-0.021
 Was-0.020
 v-0.020
Token Ben
Token ID3932
Feature activation+1.34e+00

Pos logit contributions
rey+0.016
aman+0.015
asha+0.015
onia+0.015
aleb+0.015
Neg logit contributions
 Help-0.008
 What-0.008
 Whe-0.008
 tearing-0.008
 Do-0.008
Token She
Token ID1375
Feature activation-5.51e-02

Pos logit contributions
rey+0.004
asha+0.004
aleb+0.004
iper+0.004
aman+0.004
Neg logit contributions
 smashing-0.006
 destroying-0.006
 tearing-0.006
 biting-0.005
 knocking-0.005
Token said
Token ID531
Feature activation+3.13e-02

Pos logit contributions
 Help+0.001
 Was+0.001
 smashing+0.001
 tearing+0.001
 What+0.001
Neg logit contributions
aleb-0.002
aman-0.002
iper-0.002
asha-0.002
rey-0.002
Token,
Token ID11
Feature activation-9.91e-01

Pos logit contributions
rey+0.001
asha+0.001
iper+0.001
i+0.001
aleb+0.001
Neg logit contributions
 smashing-0.001
 Help-0.001
 Was-0.001
 tearing-0.001
 What-0.001
Token "
Token ID366
Feature activation+1.51e-01

Pos logit contributions
 Help+0.014
 smashing+0.014
smart+0.013
 Was+0.013
matched+0.013
Neg logit contributions
rey-0.032
 Him-0.030
 Hugo-0.030
asha-0.030
aman-0.029
TokenCome
Token ID16773
Feature activation+5.35e-01

Pos logit contributions
rey+0.005
aleb+0.005
iper+0.005
asha+0.005
aman+0.005
Neg logit contributions
 Help-0.003
 What-0.003
 Was-0.003
 Do-0.003
 Where-0.003
Token out
Token ID503
Feature activation-4.08e+00

Pos logit contributions
rey+0.016
aleb+0.016
asha+0.015
i+0.015
iper+0.015
Neg logit contributions
 smashing-0.011
 Was-0.011
 Help-0.011
 tearing-0.011
 Blood-0.010
Token,
Token ID11
Feature activation-4.95e-01

Pos logit contributions
 Whe+0.094
 Was+0.093
 smashing+0.089
 Where+0.088
 What+0.087
Neg logit contributions
rey-0.109
i-0.103
iper-0.099
ita-0.099
aman-0.098
Token crab
Token ID32202
Feature activation+4.17e-01

Pos logit contributions
 Help+0.010
 Do+0.009
 What+0.009
 Where+0.009
 poking+0.008
Neg logit contributions
rey-0.018
iper-0.017
aleb-0.017
onia-0.017
asha-0.017
Token,
Token ID11
Feature activation-3.51e-01

Pos logit contributions
rey+0.015
aleb+0.015
iper+0.015
asha+0.015
aman+0.014
Neg logit contributions
 Help-0.007
 What-0.007
 Do-0.006
 Was-0.006
 smashing-0.006
Token come
Token ID1282
Feature activation-6.67e-01

Pos logit contributions
 Help+0.008
 What+0.008
 Do+0.007
 Was+0.007
 Where+0.007
Neg logit contributions
rey-0.011
aleb-0.011
iper-0.011
asha-0.011
aman-0.010
Token out
Token ID503
Feature activation-2.53e+00

Pos logit contributions
 Help+0.015
 What+0.015
 Was+0.014
 Do+0.014
 smashing+0.014
Neg logit contributions
rey-0.020
aleb-0.020
asha-0.019
iper-0.019
aman-0.019
Token Anna
Token ID11735
Feature activation-8.30e-01

Pos logit contributions
 Help+0.006
 What+0.006
 Do+0.005
 Was+0.005
 tearing+0.005
Neg logit contributions
rey-0.009
aleb-0.009
iper-0.009
asha-0.009
aman-0.009
Token.
Token ID13
Feature activation+2.81e-01

Pos logit contributions
 Help+0.015
 What+0.014
 Do+0.014
 tearing+0.014
 Was+0.013
Neg logit contributions
rey-0.030
aman-0.029
aleb-0.029
asha-0.029
iper-0.028
Token They
Token ID1119
Feature activation-1.25e+00

Pos logit contributions
rey+0.011
aleb+0.011
iper+0.010
asha+0.010
i+0.010
Neg logit contributions
 What-0.005
 Do-0.005
 Help-0.005
 Where-0.005
 Was-0.005
Token also
Token ID635
Feature activation-2.65e+00

Pos logit contributions
 Was+0.022
 Help+0.021
 What+0.021
 tearing+0.020
 Do+0.020
Neg logit contributions
rey-0.044
iper-0.044
aman-0.044
aleb-0.043
asha-0.043
Token liked
Token ID8288
Feature activation-6.04e-01

Pos logit contributions
 Help+0.065
 What+0.063
 Do+0.062
 Was+0.062
 Where+0.061
Neg logit contributions
rey-0.075
aleb-0.072
asha-0.070
iper-0.070
aman-0.068
Token each
Token ID1123
Feature activation-4.03e+00

Pos logit contributions
 Help+0.011
 What+0.010
 Do+0.010
 Was+0.010
 tearing+0.010
Neg logit contributions
rey-0.022
aleb-0.021
iper-0.021
asha-0.021
aman-0.021
Token other
Token ID584
Feature activation-6.92e-01

Pos logit contributions
 Help+0.121
 Was+0.120
 smashing+0.119
 Where+0.118
 Do+0.118
Neg logit contributions
rey-0.084
aleb-0.082
asha-0.076
pa-0.075
i-0.074
Token.
Token ID13
Feature activation+5.99e-01

Pos logit contributions
 What+0.013
 Help+0.013
 Was+0.012
 Do+0.012
 tearing+0.012
Neg logit contributions
rey-0.024
aleb-0.023
asha-0.023
aman-0.023
iper-0.023
Token They
Token ID1119
Feature activation-1.12e+00

Pos logit contributions
rey+0.022
aleb+0.022
iper+0.022
asha+0.022
aman+0.021
Neg logit contributions
 What-0.010
 Do-0.010
 Help-0.010
 Where-0.010
 Was-0.010
Token had
Token ID550
Feature activation-1.31e+00

Pos logit contributions
 Was+0.018
 Help+0.017
 What+0.016
 tearing+0.016
 Do+0.016
Neg logit contributions
aman-0.042
iper-0.041
rey-0.041
aleb-0.040
asha-0.040
Token a
Token ID257
Feature activation-1.67e-01

Pos logit contributions
 Help+0.027
 What+0.026
 Do+0.026
 Was+0.025
 tearing+0.025
Neg logit contributions
rey-0.043
aleb-0.041
iper-0.041
aman-0.040
asha-0.040
Token.
Token ID13
Feature activation-1.68e+00

Pos logit contributions
 Help+0.012
 What+0.012
 Was+0.012
 smashing+0.012
 Do+0.012
Neg logit contributions
rey-0.024
aleb-0.024
iper-0.023
asha-0.023
aman-0.023
Token Now
Token ID2735
Feature activation-8.94e-01

Pos logit contributions
 Help+0.030
 smashing+0.030
 Was+0.029
 tearing+0.029
 destroying+0.029
Neg logit contributions
rey-0.055
aleb-0.055
iper-0.053
asha-0.052
aman-0.051
Token say
Token ID910
Feature activation-1.80e+00

Pos logit contributions
 Help+0.013
 What+0.013
 Do+0.012
 Was+0.012
 Where+0.012
Neg logit contributions
rey-0.035
aleb-0.034
asha-0.034
iper-0.034
aman-0.033
Token sorry
Token ID7926
Feature activation-1.77e+00

Pos logit contributions
 Was+0.041
 smashing+0.039
 bulldo+0.039
 Help+0.038
 Whe+0.038
Neg logit contributions
rey-0.046
iper-0.045
 Him-0.044
icity-0.043
asha-0.043
Token to
Token ID284
Feature activation-1.52e+00

Pos logit contributions
 smashing+0.032
 Help+0.031
 tearing+0.031
 destroying+0.030
 Was+0.030
Neg logit contributions
rey-0.058
iper-0.056
aleb-0.056
asha-0.055
i-0.054
Token each
Token ID1123
Feature activation-4.03e+00

Pos logit contributions
 Help+0.033
 Was+0.032
 smashing+0.032
 What+0.032
 Do+0.031
Neg logit contributions
rey-0.047
aleb-0.045
iper-0.044
asha-0.044
aman-0.043
Token other
Token ID584
Feature activation-1.40e+00

Pos logit contributions
 Was+0.132
 smashing+0.130
onna+0.127
 destroying+0.127
 Help+0.126
Neg logit contributions
rey-0.072
pa-0.070
aleb-0.069
isi-0.067
iper-0.066
Token."
Token ID526
Feature activation-6.73e-02

Pos logit contributions
 Help+0.030
 What+0.029
 Was+0.029
 Do+0.029
 Where+0.029
Neg logit contributions
rey-0.043
aleb-0.042
iper-0.040
asha-0.040
aman-0.040
Token Lily
Token ID20037
Feature activation+1.00e+00

Pos logit contributions
 smashing+0.002
 destroying+0.002
smart+0.002
 Help+0.002
 tearing+0.002
Neg logit contributions
rey-0.002
aleb-0.002
iper-0.002
aman-0.002
asha-0.002
Token and
Token ID290
Feature activation+1.17e+00

Pos logit contributions
rey+0.034
aleb+0.033
iper+0.033
asha+0.033
aman+0.032
Neg logit contributions
 Help-0.019
 What-0.019
 Was-0.018
 tearing-0.018
 smashing-0.018
Token Anna
Token ID11735
Feature activation+1.22e+00

Pos logit contributions
rey+0.038
asha+0.037
aleb+0.037
iper+0.037
aman+0.036
Neg logit contributions
 Help-0.025
 What-0.024
 tearing-0.023
 Do-0.023
 Whe-0.023
Token Daisy
Token ID40355
Feature activation+1.55e-02

Pos logit contributions
aleb+0.020
iper+0.020
rey+0.020
asha+0.019
aman+0.019
Neg logit contributions
 Help-0.010
 What-0.010
 Whe-0.009
 Do-0.009
 Where-0.009
Token accidentally
Token ID14716
Feature activation-8.46e-01

Pos logit contributions
aleb+0.001
rey+0.001
aman+0.001
 Him+0.001
ishment+0.001
Neg logit contributions
 Help-0.000
 Was-0.000
 What-0.000
 tearing-0.000
 Where-0.000
Token broke
Token ID6265
Feature activation-5.54e-01

Pos logit contributions
 Help+0.013
 smashing+0.012
 tearing+0.012
 What+0.012
 Was+0.011
Neg logit contributions
rey-0.033
aleb-0.033
asha-0.032
iper-0.032
aman-0.031
Token Ph
Token ID1380
Feature activation-6.52e-02

Pos logit contributions
 tearing+0.011
 destroying+0.011
 smashing+0.011
 Help+0.011
 What+0.011
Neg logit contributions
iper-0.018
aleb-0.018
rey-0.018
asha-0.018
iri-0.017
Tokenoe
Token ID2577
Feature activation-3.85e+00

Pos logit contributions
 Help+0.001
 What+0.001
 Was+0.001
 Do+0.001
 Where+0.001
Neg logit contributions
rey-0.002
aleb-0.002
iper-0.002
asha-0.002
aman-0.002
Tokenbe
Token ID1350
Feature activation-4.00e+00

Pos logit contributions
 Do+0.087
 What+0.085
 Where+0.084
 Was+0.083
 Help+0.081
Neg logit contributions
rey-0.115
i-0.113
aleb-0.113
iper-0.109
asha-0.108
Token's
Token ID338
Feature activation-9.87e-01

Pos logit contributions
 Do+0.115
 Want+0.111
 Whe+0.108
 Where+0.107
 What+0.107
Neg logit contributions
i-0.097
pa-0.091
rey-0.091
ita-0.091
iper-0.089
Token favourite
Token ID12507
Feature activation-1.88e+00

Pos logit contributions
 Help+0.021
 tearing+0.020
 smashing+0.020
 What+0.019
 destroying+0.019
Neg logit contributions
rey-0.032
asha-0.031
aleb-0.031
iper-0.030
onia-0.030
Token toy
Token ID13373
Feature activation-5.18e-02

Pos logit contributions
 Help+0.042
 What+0.040
 Was+0.040
 Do+0.040
 Where+0.039
Neg logit contributions
rey-0.058
aleb-0.056
asha-0.055
iper-0.055
aman-0.054
Token,
Token ID11
Feature activation-8.17e-01

Pos logit contributions
 Help+0.001
 tearing+0.001
 smashing+0.001
 What+0.001
 destroying+0.001
Neg logit contributions
rey-0.002
asha-0.002
aleb-0.002
iper-0.002
aman-0.002
Token a
Token ID257
Feature activation-1.38e+00

Pos logit contributions
 tearing+0.016
 smashing+0.016
 Help+0.016
 What+0.016
 destroying+0.015
Neg logit contributions
rey-0.029
aleb-0.029
asha-0.028
iper-0.028
onia-0.027
Token very
Token ID845
Feature activation-3.42e-01

Pos logit contributions
rey+0.019
aleb+0.018
asha+0.018
iper+0.018
aman+0.018
Neg logit contributions
 Help-0.010
 What-0.010
 smashing-0.009
 tearing-0.009
 Do-0.009
Token stubborn
Token ID24444
Feature activation+8.13e-02

Pos logit contributions
 Help+0.006
 What+0.006
 Was+0.006
 Do+0.006
 Where+0.006
Neg logit contributions
rey-0.012
aleb-0.011
iper-0.011
asha-0.011
aman-0.011
Token.
Token ID13
Feature activation-4.16e-01

Pos logit contributions
rey+0.003
aleb+0.003
asha+0.003
iper+0.003
aman+0.003
Neg logit contributions
 Help-0.002
 What-0.002
 tearing-0.002
 smashing-0.002
 Was-0.002
Token They
Token ID1119
Feature activation+6.40e-02

Pos logit contributions
 smashing+0.010
 Help+0.010
 tearing+0.010
smart+0.010
 destroying+0.010
Neg logit contributions
rey-0.011
iper-0.011
aleb-0.010
asha-0.010
aman-0.010
Token made
Token ID925
Feature activation+1.44e-01

Pos logit contributions
rey+0.002
asha+0.002
aman+0.002
aleb+0.002
iper+0.002
Neg logit contributions
 Was-0.001
 Help-0.001
 What-0.001
 tearing-0.001
 smashing-0.001
Token each
Token ID1123
Feature activation-4.00e+00

Pos logit contributions
rey+0.005
aleb+0.005
asha+0.005
iper+0.004
aman+0.004
Neg logit contributions
 Help-0.003
 What-0.003
 tearing-0.003
 smashing-0.003
 Was-0.003
Token other
Token ID584
Feature activation-1.22e+00

Pos logit contributions
 Was+0.112
 Help+0.111
 Do+0.111
 Where+0.109
 What+0.109
Neg logit contributions
rey-0.089
aleb-0.086
iper-0.078
ita-0.078
asha-0.075
Token sad
Token ID6507
Feature activation-5.13e-01

Pos logit contributions
 Help+0.028
 What+0.028
 Was+0.028
 Do+0.028
 Where+0.027
Neg logit contributions
rey-0.036
aleb-0.035
iper-0.034
asha-0.033
aman-0.033
Token and
Token ID290
Feature activation+5.01e-01

Pos logit contributions
 Help+0.011
 What+0.010
 Was+0.010
 Do+0.010
 smashing+0.010
Neg logit contributions
rey-0.017
aleb-0.017
asha-0.016
iper-0.016
aman-0.016
Token angry
Token ID7954
Feature activation-5.36e-01

Pos logit contributions
rey+0.018
asha+0.018
aleb+0.018
aman+0.017
iper+0.017
Neg logit contributions
 tearing-0.009
 Help-0.009
 smashing-0.009
 Do-0.009
 destroying-0.009
Token.
Token ID13
Feature activation-7.47e-01

Pos logit contributions
 Help+0.011
 What+0.011
 Was+0.010
 Do+0.010
 Where+0.010
Neg logit contributions
rey-0.018
aleb-0.017
asha-0.017
iper-0.017
aman-0.016
Token.
Token ID13
Feature activation+2.42e-01

Pos logit contributions
i+0.014
iper+0.013
aleb+0.013
hel+0.013
 Him+0.013
Neg logit contributions
 Want-0.021
 Was-0.021
 Where-0.021
 Do-0.021
 Whe-0.021
Token "
Token ID366
Feature activation-1.00e+00

Pos logit contributions
rey+0.006
asha+0.006
aman+0.006
ita+0.006
aleb+0.006
Neg logit contributions
free-0.005
 bulldo-0.005
 smashing-0.005
 destroying-0.005
 Want-0.005
TokenYou
Token ID1639
Feature activation-5.48e-01

Pos logit contributions
 Help+0.028
 Was+0.027
 What+0.026
 Where+0.026
 Do+0.026
Neg logit contributions
rey-0.024
aleb-0.024
asha-0.022
aman-0.021
iper-0.021
Token are
Token ID389
Feature activation-2.71e-01

Pos logit contributions
 Help+0.012
 What+0.012
 Was+0.011
 Do+0.011
 Where+0.011
Neg logit contributions
rey-0.016
aleb-0.016
iper-0.016
asha-0.015
aman-0.015
Token hurting
Token ID21530
Feature activation-1.33e+00

Pos logit contributions
 Was+0.006
 Help+0.006
 Where+0.006
 What+0.006
 Want+0.006
Neg logit contributions
rey-0.008
aleb-0.008
iper-0.007
icity-0.007
onia-0.007
Token each
Token ID1123
Feature activation-3.99e+00

Pos logit contributions
 Help+0.030
 What+0.029
 Do+0.028
 Was+0.028
 smashing+0.028
Neg logit contributions
rey-0.041
aleb-0.040
iper-0.040
asha-0.040
aman-0.039
Token other
Token ID584
Feature activation-1.71e+00

Pos logit contributions
onna+0.138
 Was+0.137
 Help+0.130
 Where+0.130
 Do+0.129
Neg logit contributions
rey-0.062
aleb-0.062
pa-0.057
oto-0.053
isi-0.052
Token and
Token ID290
Feature activation-2.79e-01

Pos logit contributions
 Help+0.036
 What+0.034
 smashing+0.033
 Was+0.033
 Do+0.033
Neg logit contributions
rey-0.056
aleb-0.054
asha-0.053
iper-0.053
aman-0.052
Token the
Token ID262
Feature activation-1.13e+00

Pos logit contributions
 Help+0.006
 What+0.006
 Do+0.006
 Was+0.006
 smashing+0.006
Neg logit contributions
rey-0.009
aleb-0.008
asha-0.008
iper-0.008
aman-0.008
Token car
Token ID1097
Feature activation-1.08e+00

Pos logit contributions
 Help+0.027
 What+0.026
 Was+0.026
 Do+0.025
 Where+0.025
Neg logit contributions
rey-0.033
aleb-0.032
iper-0.030
asha-0.030
aman-0.030
Token.
Token ID13
Feature activation-7.60e-01

Pos logit contributions
 Help+0.020
 What+0.019
 Do+0.018
 Was+0.018
 smashing+0.018
Neg logit contributions
rey-0.038
aleb-0.038
asha-0.037
iper-0.037
aman-0.036
Token and
Token ID290
Feature activation-3.40e-01

Pos logit contributions
 Help+0.034
 What+0.033
 Do+0.032
 Was+0.032
 tearing+0.032
Neg logit contributions
rey-0.043
aleb-0.042
asha-0.041
iper-0.041
aman-0.040
Token daddy
Token ID35822
Feature activation-1.41e+00

Pos logit contributions
 Help+0.008
 What+0.008
 Do+0.008
 tearing+0.008
 Where+0.007
Neg logit contributions
rey-0.011
asha-0.010
aleb-0.010
iper-0.010
aman-0.010
Token who
Token ID508
Feature activation-1.09e+00

Pos logit contributions
 Help+0.033
 What+0.032
 Was+0.031
 Do+0.031
 smashing+0.031
Neg logit contributions
rey-0.042
aleb-0.041
iper-0.039
asha-0.039
aman-0.039
Token both
Token ID1111
Feature activation-2.07e+00

Pos logit contributions
 What+0.023
 Help+0.023
 Was+0.023
 Do+0.022
 Where+0.022
Neg logit contributions
rey-0.035
asha-0.034
iper-0.034
aleb-0.033
aman-0.033
Token loved
Token ID6151
Feature activation-8.50e-02

Pos logit contributions
 Help+0.058
 Do+0.055
 smashing+0.055
 tearing+0.054
 Was+0.054
Neg logit contributions
rey-0.049
aleb-0.049
iper-0.046
i-0.046
asha-0.045
Token each
Token ID1123
Feature activation-3.98e+00

Pos logit contributions
 Help+0.001
 What+0.001
 Do+0.001
 Was+0.001
 smashing+0.001
Neg logit contributions
rey-0.003
aleb-0.003
asha-0.003
iper-0.003
aman-0.003
Token other
Token ID584
Feature activation-1.21e+00

Pos logit contributions
 Help+0.105
 Was+0.104
 Do+0.102
 What+0.101
 smashing+0.099
Neg logit contributions
rey-0.102
aleb-0.101
aman-0.095
asha-0.095
iper-0.095
Token very
Token ID845
Feature activation-8.69e-01

Pos logit contributions
 Help+0.028
 Do+0.026
 What+0.026
 Was+0.026
 Where+0.025
Neg logit contributions
rey-0.037
aleb-0.036
iper-0.034
asha-0.034
aman-0.034
Token much
Token ID881
Feature activation+8.39e-01

Pos logit contributions
 Help+0.014
 What+0.013
 Was+0.012
 Do+0.012
 Where+0.012
Neg logit contributions
rey-0.033
aleb-0.032
asha-0.031
iper-0.031
aman-0.031
Token.
Token ID13
Feature activation-1.63e-01

Pos logit contributions
rey+0.034
asha+0.033
iper+0.033
aleb+0.033
aman+0.032
Neg logit contributions
 What-0.011
 Help-0.011
 Do-0.010
 Was-0.010
free-0.010
Token Every
Token ID3887
Feature activation-1.82e-01

Pos logit contributions
 What+0.003
 Help+0.003
 Do+0.003
 Was+0.003
 Where+0.003
Neg logit contributions
rey-0.006
iper-0.006
aleb-0.006
asha-0.006
i-0.005
Token Mitt
Token ID16627
Feature activation+1.31e+00

Pos logit contributions
 Help+0.023
 What+0.022
 Do+0.021
 tearing+0.021
 smashing+0.021
Neg logit contributions
aleb-0.041
rey-0.041
iper-0.039
asha-0.039
onia-0.037
Tokenens
Token ID641
Feature activation+4.67e-01

Pos logit contributions
rey+0.033
aleb+0.031
aman+0.030
iper+0.029
asha+0.029
Neg logit contributions
 What-0.037
 Do-0.037
 Help-0.036
 Was-0.035
 Where-0.035
Token.
Token ID13
Feature activation-1.55e+00

Pos logit contributions
rey+0.016
aleb+0.016
asha+0.015
iper+0.015
aman+0.015
Neg logit contributions
 Help-0.009
 What-0.008
 Was-0.008
 Do-0.008
 tearing-0.008
Token "
Token ID366
Feature activation-1.08e+00

Pos logit contributions
smart+0.028
 smashing+0.027
 Help+0.026
 destroying+0.026
 tearing+0.026
Neg logit contributions
aman-0.047
iper-0.047
aleb-0.047
asha-0.047
rey-0.046
TokenLook
Token ID8567
Feature activation-1.37e+00

Pos logit contributions
 Help+0.023
 What+0.022
 Was+0.022
 Do+0.022
 smashing+0.021
Neg logit contributions
rey-0.035
aleb-0.034
asha-0.033
iper-0.033
aman-0.032
Token out
Token ID503
Feature activation-3.98e+00

Pos logit contributions
 Help+0.031
 Was+0.030
 Do+0.030
 What+0.030
 smashing+0.029
Neg logit contributions
rey-0.040
aleb-0.040
iper-0.039
i-0.039
asha-0.039
Token,
Token ID11
Feature activation-2.35e+00

Pos logit contributions
 Whe+0.111
 Was+0.108
Are+0.102
 Do+0.101
 Blood+0.100
Neg logit contributions
i-0.081
rey-0.080
 uncle-0.078
pa-0.077
iper-0.077
Token Tim
Token ID5045
Feature activation-3.00e-01

Pos logit contributions
 Help+0.046
 Was+0.044
 What+0.044
 smashing+0.044
 tearing+0.043
Neg logit contributions
rey-0.076
aleb-0.075
iper-0.073
asha-0.073
aman-0.072
Tokenmy
Token ID1820
Feature activation-6.17e-02

Pos logit contributions
 Help+0.010
 What+0.010
 Was+0.010
 Do+0.010
 Where+0.010
Neg logit contributions
rey-0.006
aleb-0.006
iper-0.005
asha-0.005
aman-0.005
Token!"
Token ID2474
Feature activation+2.30e-01

Pos logit contributions
 Help+0.001
 What+0.001
 Was+0.001
 Do+0.001
 Where+0.001
Neg logit contributions
rey-0.002
aleb-0.002
asha-0.002
iper-0.002
aman-0.002
Token yelled
Token ID22760
Feature activation-1.17e+00

Pos logit contributions
rey+0.007
aleb+0.007
asha+0.007
iper+0.007
aman+0.007
Neg logit contributions
 Help-0.005
 What-0.005
 Do-0.005
 Was-0.005
 tearing-0.005
Token.
Token ID13
Feature activation-3.17e-01

Pos logit contributions
 Help+0.023
 What+0.022
 Was+0.022
 Do+0.022
 Where+0.021
Neg logit contributions
rey-0.032
aleb-0.031
asha-0.031
iper-0.030
aman-0.030
Token He
Token ID679
Feature activation-8.25e-01

Pos logit contributions
 Help+0.005
 smashing+0.004
 Was+0.004
 What+0.004
 tearing+0.004
Neg logit contributions
rey-0.012
aleb-0.012
asha-0.011
iper-0.011
aman-0.011
Token was
Token ID373
Feature activation-4.84e-01

Pos logit contributions
 Help+0.020
 What+0.019
 Was+0.019
 Do+0.019
 smashing+0.019
Neg logit contributions
rey-0.024
aleb-0.022
iper-0.022
asha-0.022
i-0.021
Token a
Token ID257
Feature activation-1.08e+00

Pos logit contributions
 Help+0.011
 What+0.011
 Was+0.010
 Do+0.010
 smashing+0.010
Neg logit contributions
rey-0.015
aleb-0.014
iper-0.014
asha-0.014
aman-0.014
Token mis
Token ID2984
Feature activation-1.05e+00

Pos logit contributions
 What+0.026
 Help+0.026
 Was+0.026
 Do+0.026
 smashing+0.025
Neg logit contributions
rey-0.030
aleb-0.029
iper-0.027
asha-0.027
aman-0.026
Tokenchie
Token ID3043
Feature activation-3.98e+00

Pos logit contributions
 What+0.020
 Help+0.020
 Do+0.020
 Was+0.020
 Where+0.019
Neg logit contributions
aleb-0.035
rey-0.035
iper-0.034
asha-0.033
ita-0.032
Tokenvous
Token ID31222
Feature activation-1.08e-01

Pos logit contributions
 Help+0.086
 smashing+0.084
 destroying+0.083
 tearing+0.083
 Was+0.082
Neg logit contributions
rey-0.118
iper-0.114
aleb-0.114
ita-0.114
asha-0.111
Token little
Token ID1310
Feature activation+3.99e-01

Pos logit contributions
 Help+0.003
 What+0.003
 Was+0.003
 Do+0.003
 smashing+0.003
Neg logit contributions
rey-0.003
aleb-0.003
asha-0.003
iper-0.003
aman-0.003
Token baby
Token ID5156
Feature activation-3.75e-01

Pos logit contributions
rey+0.012
aleb+0.012
asha+0.012
iper+0.012
aman+0.011
Neg logit contributions
 Help-0.009
 What-0.009
 Do-0.009
 Was-0.009
 smashing-0.008
Token and
Token ID290
Feature activation-1.26e-01

Pos logit contributions
 Help+0.009
 What+0.008
 Was+0.008
 Do+0.008
 smashing+0.008
Neg logit contributions
rey-0.011
aleb-0.011
asha-0.011
iper-0.010
aman-0.010
Token always
Token ID1464
Feature activation-1.97e+00

Pos logit contributions
 Help+0.003
 What+0.003
 Do+0.003
 Was+0.003
 Where+0.003
Neg logit contributions
rey-0.004
aleb-0.004
asha-0.003
iper-0.003
aman-0.003
Token to
Token ID284
Feature activation+6.53e-01

Pos logit contributions
 Help+0.000
 What+0.000
 Do+0.000
 smashing+0.000
 Was+0.000
Neg logit contributions
rey-0.001
aleb-0.001
asha-0.001
iper-0.001
aman-0.001
Token the
Token ID262
Feature activation+1.50e-01

Pos logit contributions
rey+0.021
aleb+0.021
iper+0.020
asha+0.020
aman+0.020
Neg logit contributions
 Help-0.013
 What-0.013
 Was-0.013
 Do-0.013
 Where-0.012
Token kitchen
Token ID9592
Feature activation+1.10e+00

Pos logit contributions
rey+0.004
aleb+0.004
asha+0.004
aman+0.004
iper+0.004
Neg logit contributions
 Help-0.004
 What-0.004
 Do-0.004
 Was-0.004
 smashing-0.004
Token and
Token ID290
Feature activation-1.18e+00

Pos logit contributions
rey+0.038
aleb+0.037
asha+0.036
iper+0.036
iri+0.035
Neg logit contributions
 Help-0.022
 What-0.020
 Was-0.020
 tearing-0.020
 smashing-0.020
Token mixed
Token ID7668
Feature activation-2.60e-01

Pos logit contributions
 Help+0.026
 What+0.025
 Was+0.025
 Do+0.024
 smashing+0.024
Neg logit contributions
rey-0.037
aleb-0.036
asha-0.035
iper-0.035
aman-0.034
Token a
Token ID257
Feature activation-3.97e+00

Pos logit contributions
 Help+0.006
 What+0.006
 Do+0.006
 Was+0.005
 Where+0.005
Neg logit contributions
rey-0.008
aleb-0.008
asha-0.008
iper-0.008
aman-0.007
Token spicy
Token ID26880
Feature activation-1.52e+00

Pos logit contributions
smart+0.115
 Where+0.111
 Do+0.111
 Help+0.105
 What+0.105
Neg logit contributions
rey-0.085
aman-0.085
aleb-0.081
asha-0.080
onia-0.077
Token and
Token ID290
Feature activation-2.41e+00

Pos logit contributions
smart+0.039
 Do+0.039
 Help+0.038
 Where+0.037
 What+0.036
Neg logit contributions
rey-0.038
aleb-0.037
asha-0.037
aman-0.036
i-0.035
Token a
Token ID257
Feature activation-3.78e+00

Pos logit contributions
 Help+0.056
 What+0.054
 Was+0.053
 Do+0.053
 Where+0.053
Neg logit contributions
rey-0.071
aleb-0.069
iper-0.067
asha-0.067
aman-0.065
Token gray
Token ID12768
Feature activation-2.07e+00

Pos logit contributions
smart+0.094
 Where+0.093
 Do+0.091
 What+0.091
 Help+0.089
Neg logit contributions
rey-0.096
aman-0.092
asha-0.089
aleb-0.088
onia-0.086
Token juice
Token ID13135
Feature activation-3.94e-01

Pos logit contributions
smart+0.044
 Help+0.043
 Do+0.043
 Where+0.043
 What+0.041
Neg logit contributions
rey-0.060
aman-0.058
asha-0.057
aleb-0.057
iper-0.055
Token's
Token ID338
Feature activation-5.47e-01

Pos logit contributions
 Help+0.015
 What+0.014
 Was+0.014
 Do+0.014
 smashing+0.014
Neg logit contributions
rey-0.029
aleb-0.028
asha-0.028
iper-0.028
aman-0.027
Token okay
Token ID8788
Feature activation-1.30e+00

Pos logit contributions
 Help+0.013
 What+0.012
 Do+0.012
 tearing+0.012
 smashing+0.012
Neg logit contributions
rey-0.017
aleb-0.017
asha-0.017
iper-0.016
aman-0.016
Token"
Token ID1
Feature activation-2.15e-01

Pos logit contributions
 Was+0.030
 smashing+0.030
 Help+0.030
 What+0.029
 tearing+0.029
Neg logit contributions
rey-0.036
aleb-0.035
asha-0.034
iper-0.033
i-0.033
Token and
Token ID290
Feature activation-5.76e-01

Pos logit contributions
 What+0.004
 Do+0.004
 Help+0.004
 Was+0.004
 Where+0.004
Neg logit contributions
aleb-0.007
rey-0.007
iper-0.007
aman-0.007
asha-0.007
Token hugged
Token ID41130
Feature activation-1.49e+00

Pos logit contributions
 Help+0.011
 Was+0.010
 What+0.010
 Where+0.010
 Do+0.010
Neg logit contributions
rey-0.019
aleb-0.019
asha-0.018
iper-0.018
i-0.018
Token each
Token ID1123
Feature activation-3.97e+00

Pos logit contributions
 Help+0.024
 What+0.024
 Do+0.023
 Was+0.022
 Where+0.022
Neg logit contributions
rey-0.056
aleb-0.055
aman-0.054
asha-0.054
iper-0.054
Token other
Token ID584
Feature activation-1.98e+00

Pos logit contributions
 Help+0.110
 tearing+0.109
 smashing+0.109
 Was+0.108
 destroying+0.108
Neg logit contributions
rey-0.092
aleb-0.091
asha-0.086
iper-0.086
oto-0.083
Token.
Token ID13
Feature activation-5.90e-01

Pos logit contributions
 Help+0.037
 What+0.036
 Do+0.034
 Was+0.033
 smashing+0.033
Neg logit contributions
rey-0.070
asha-0.067
aman-0.067
aleb-0.067
iper-0.066
Token Then
Token ID3244
Feature activation+2.67e-02

Pos logit contributions
 smashing+0.014
 destroying+0.014
 tearing+0.013
 bulldo+0.013
 knocking+0.013
Neg logit contributions
rey-0.016
aman-0.015
asha-0.014
aleb-0.014
onia-0.014
Token they
Token ID484
Feature activation-1.02e+00

Pos logit contributions
rey+0.001
aleb+0.001
iper+0.001
asha+0.001
aman+0.001
Neg logit contributions
 Help-0.001
 What-0.001
 Do-0.001
 Was-0.001
 Where-0.001
Token decided
Token ID3066
Feature activation-2.16e-01

Pos logit contributions
 Help+0.022
 Was+0.021
 What+0.021
 smashing+0.020
 tearing+0.020
Neg logit contributions
rey-0.032
aleb-0.031
aman-0.031
asha-0.031
iper-0.030
Token to
Token ID284
Feature activation+5.93e-02

Pos logit contributions
 Was+0.002
 Help+0.002
 What+0.002
 Where+0.002
 Do+0.002
Neg logit contributions
aleb-0.005
rey-0.005
iper-0.005
asha-0.005
aman-0.005
Token explore
Token ID7301
Feature activation+3.99e-01

Pos logit contributions
rey+0.002
aleb+0.002
asha+0.002
aman+0.002
iper+0.002
Neg logit contributions
 Help-0.001
 What-0.001
 Do-0.001
 Was-0.001
 tearing-0.001
Token the
Token ID262
Feature activation+1.15e+00

Pos logit contributions
rey+0.013
aleb+0.013
asha+0.012
iper+0.012
aman+0.012
Neg logit contributions
 Help-0.008
 What-0.008
 Was-0.008
 Do-0.008
 smashing-0.008
Token forest
Token ID8222
Feature activation-5.39e-02

Pos logit contributions
rey+0.034
aleb+0.033
iper+0.033
asha+0.033
aman+0.032
Neg logit contributions
 Help-0.027
 What-0.026
 Was-0.025
 Do-0.025
 Where-0.025
Token near
Token ID1474
Feature activation+4.01e-01

Pos logit contributions
 Help+0.001
 What+0.001
 Was+0.001
 Do+0.001
 smashing+0.001
Neg logit contributions
rey-0.002
aleb-0.002
asha-0.002
iper-0.002
aman-0.002
Token his
Token ID465
Feature activation+3.10e+00

Pos logit contributions
rey+0.012
aleb+0.012
iper+0.012
asha+0.012
aman+0.011
Neg logit contributions
 Help-0.009
 What-0.009
 Do-0.009
 Was-0.009
 tearing-0.009
Token house
Token ID2156
Feature activation-2.69e-01

Pos logit contributions
asha+0.106
rey+0.105
iper+0.104
aleb+0.103
onia+0.102
Neg logit contributions
 Help-0.065
 What-0.057
 Was-0.053
 Where-0.053
 tearing-0.050
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
 Help+0.005
 What+0.005
 Was+0.005
 Do+0.005
 Where+0.005
Neg logit contributions
rey-0.009
aleb-0.009
asha-0.009
iper-0.009
aman-0.008
Token One
Token ID1881
Feature activation+1.82e-01

Pos logit contributions
rey+0.000
aleb+0.000
aman+0.000
asha+0.000
iper+0.000
Neg logit contributions
 Help-0.000
 smashing-0.000
 tearing-0.000
 destroying-0.000
 Was-0.000
Token day
Token ID1110
Feature activation-1.60e+00

Pos logit contributions
rey+0.006
aleb+0.005
iper+0.005
asha+0.005
aman+0.005
Neg logit contributions
 Help-0.004
 What-0.004
 Was-0.004
 Do-0.004
 Where-0.004
Token,
Token ID11
Feature activation+3.29e-01

Pos logit contributions
smart+0.049
 Was+0.048
 smashing+0.048
 destroying+0.046
 tearing+0.046
Neg logit contributions
i-0.025
aman-0.024
aleb-0.024
 uncle-0.024
hel-0.024
Token mom
Token ID1995
Feature activation-2.21e-01

Pos logit contributions
rey+0.020
aleb+0.020
asha+0.019
iper+0.019
aman+0.019
Neg logit contributions
 Help-0.023
 What-0.022
 Was-0.022
 Where-0.021
 Do-0.021
Token write
Token ID3551
Feature activation+9.25e-01

Pos logit contributions
 Help+0.005
 What+0.005
 Was+0.005
 tearing+0.005
 knocking+0.004
Neg logit contributions
rey-0.007
aleb-0.007
asha-0.007
aman-0.007
iri-0.006
Token a
Token ID257
Feature activation-7.15e-01

Pos logit contributions
aleb+0.035
aman+0.033
rey+0.032
asha+0.032
iper+0.031
Neg logit contributions
 What-0.015
 Help-0.015
 tearing-0.014
 v-0.014
 Was-0.014
Token letter
Token ID3850
Feature activation+1.00e+00

Pos logit contributions
 Help+0.021
 What+0.021
 Was+0.020
 Do+0.020
 smashing+0.020
Neg logit contributions
rey-0.017
aleb-0.016
asha-0.016
iper-0.016
aman-0.015
Token to
Token ID284
Feature activation+3.25e-01

Pos logit contributions
aleb+0.044
rey+0.043
asha+0.041
aman+0.041
iper+0.040
Neg logit contributions
 Help-0.011
 What-0.011
 Was-0.010
 v-0.010
 tearing-0.009
Token Grand
Token ID5675
Feature activation+3.12e+00

Pos logit contributions
aleb+0.010
rey+0.010
asha+0.010
iper+0.010
aman+0.010
Neg logit contributions
 Help-0.007
 What-0.007
 Do-0.007
 tearing-0.007
 Was-0.007
Tokenma
Token ID2611
Feature activation-1.84e-01

Pos logit contributions
iper+0.054
rey+0.053
aleb+0.050
asha+0.048
ita+0.048
Neg logit contributions
 Help-0.100
 tearing-0.098
 What-0.098
 Do-0.095
 destroying-0.095
Token and
Token ID290
Feature activation+3.68e-01

Pos logit contributions
 What+0.003
 Help+0.003
 drawing+0.003
 Do+0.003
 tearing+0.003
Neg logit contributions
rey-0.007
aleb-0.007
asha-0.007
aman-0.007
oto-0.006
Token put
Token ID1234
Feature activation+1.01e+00

Pos logit contributions
aleb+0.012
asha+0.011
rey+0.011
ust+0.011
iri+0.011
Neg logit contributions
 Help-0.009
 What-0.008
 Was-0.008
 drawing-0.008
 tearing-0.008
Token it
Token ID340
Feature activation+3.83e-01

Pos logit contributions
rey+0.039
aleb+0.038
asha+0.038
aman+0.037
iper+0.037
Neg logit contributions
 What-0.016
 Help-0.015
 Do-0.014
 Was-0.014
 Where-0.014
Token in
Token ID287
Feature activation+2.41e-01

Pos logit contributions
aleb+0.018
asha+0.017
rey+0.017
aman+0.017
iper+0.016
Neg logit contributions
 Help-0.004
free-0.003
 tearing-0.003
 v-0.003
 What-0.003
Token play
Token ID711
Feature activation-6.66e-01

Pos logit contributions
aman+0.004
rey+0.004
aleb+0.004
asha+0.004
iper+0.004
Neg logit contributions
 Help-0.001
 What-0.001
 Do-0.001
 tearing-0.001
 crash-0.001
Token in
Token ID287
Feature activation+4.45e-01

Pos logit contributions
 Help+0.015
 What+0.015
 Was+0.014
 Do+0.014
 smashing+0.014
Neg logit contributions
rey-0.020
aleb-0.020
asha-0.019
iper-0.019
aman-0.019
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
rey+0.014
aleb+0.013
asha+0.012
iper+0.012
aman+0.012
Neg logit contributions
 Help-0.010
 Was-0.010
 What-0.010
 Where-0.009
 Do-0.009
Token field
Token ID2214
Feature activation-5.09e-02

Pos logit contributions
rey+0.033
iper+0.033
aleb+0.032
asha+0.032
i+0.031
Neg logit contributions
 Help-0.027
 What-0.027
 tearing-0.026
 Do-0.026
 v-0.026
Token near
Token ID1474
Feature activation+1.50e-01

Pos logit contributions
 Help+0.001
 What+0.001
 Do+0.001
 Was+0.001
 tearing+0.001
Neg logit contributions
aleb-0.002
rey-0.002
iper-0.002
asha-0.002
aman-0.002
Token their
Token ID511
Feature activation+3.28e+00

Pos logit contributions
rey+0.005
aleb+0.004
asha+0.004
iper+0.004
aman+0.004
Neg logit contributions
 Help-0.003
 What-0.003
 Was-0.003
 Do-0.003
 smashing-0.003
Token house
Token ID2156
Feature activation-5.49e-01

Pos logit contributions
rey+0.103
asha+0.102
iper+0.102
onia+0.101
isi+0.100
Neg logit contributions
 Help-0.067
 What-0.061
 v-0.060
 tearing-0.059
 Whe-0.059
Token.
Token ID13
Feature activation-2.82e-01

Pos logit contributions
 Help+0.009
 What+0.009
 Was+0.008
 tearing+0.008
 Do+0.008
Neg logit contributions
rey-0.021
aleb-0.020
asha-0.020
iper-0.020
onia-0.019
Token They
Token ID1119
Feature activation+6.00e-01

Pos logit contributions
 Help+0.008
 smashing+0.007
 tearing+0.007
 destroying+0.007
 Was+0.007
Neg logit contributions
rey-0.007
aleb-0.007
iper-0.007
asha-0.007
aman-0.007
Token had
Token ID550
Feature activation+5.07e-01

Pos logit contributions
rey+0.021
aman+0.021
aleb+0.021
asha+0.020
iper+0.020
Neg logit contributions
 Help-0.010
 Was-0.010
 What-0.009
 tearing-0.009
 Do-0.009
Token a
Token ID257
Feature activation+8.95e-01

Pos logit contributions
rey+0.015
aleb+0.015
asha+0.015
iper+0.015
aman+0.014
Neg logit contributions
 Help-0.011
 What-0.011
 Was-0.011
 Do-0.011
 smashing-0.011
Token Sally
Token ID25737
Feature activation+5.83e-01

Pos logit contributions
rey+0.011
aleb+0.011
asha+0.010
iper+0.010
aman+0.010
Neg logit contributions
 Help-0.011
 What-0.010
 Was-0.010
 Do-0.010
 smashing-0.010
Token heard
Token ID2982
Feature activation+6.50e-02

Pos logit contributions
rey+0.022
aleb+0.022
iper+0.021
aman+0.021
asha+0.021
Neg logit contributions
 Help-0.009
 Was-0.008
 What-0.008
 tearing-0.008
 Where-0.008
Token strange
Token ID6283
Feature activation+1.43e+00

Pos logit contributions
rey+0.002
aleb+0.002
iper+0.002
asha+0.002
aman+0.002
Neg logit contributions
 Help-0.001
 What-0.001
 Was-0.001
 Where-0.001
 Do-0.001
Token noises
Token ID26782
Feature activation+3.16e-01

Pos logit contributions
rey+0.042
aleb+0.041
asha+0.039
iper+0.039
aman+0.039
Neg logit contributions
 Help-0.034
 What-0.034
 Do-0.033
 Was-0.033
 tearing-0.032
Token coming
Token ID2406
Feature activation+1.69e-01

Pos logit contributions
rey+0.010
aleb+0.010
iper+0.010
asha+0.010
aman+0.010
Neg logit contributions
 Help-0.007
 What-0.006
 Do-0.006
 Was-0.006
 smashing-0.006
Token from
Token ID422
Feature activation+3.18e+00

Pos logit contributions
aleb+0.006
iper+0.005
asha+0.005
rey+0.005
aman+0.005
Neg logit contributions
 Help-0.004
 What-0.004
 Do-0.003
 Where-0.003
 destroying-0.003
Token nearby
Token ID6716
Feature activation-8.50e-04

Pos logit contributions
aleb+0.117
rey+0.114
iper+0.113
asha+0.112
aman+0.111
Neg logit contributions
 Help-0.055
 What-0.053
 Do-0.052
 tearing-0.051
 destroying-0.051
Token.
Token ID13
Feature activation+4.66e-01

Pos logit contributions
 Help+0.000
 What+0.000
 Do+0.000
 Where+0.000
 Was+0.000
Neg logit contributions
rey-0.000
aleb-0.000
iper-0.000
asha-0.000
aman-0.000
Token She
Token ID1375
Feature activation+1.14e+00

Pos logit contributions
rey+0.011
aleb+0.011
asha+0.011
iper+0.010
aman+0.010
Neg logit contributions
 Help-0.013
 smashing-0.013
 tearing-0.013
 Do-0.013
 destroying-0.013
Token followed
Token ID3940
Feature activation+2.09e+00

Pos logit contributions
aleb+0.043
aman+0.042
iper+0.040
ishment+0.040
asha+0.040
Neg logit contributions
 Help-0.020
 What-0.019
 Was-0.019
 Where-0.017
 tearing-0.017
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
rey+0.063
aleb+0.063
aman+0.060
asha+0.060
iper+0.059
Neg logit contributions
 Help-0.049
 What-0.048
 tearing-0.045
 Do-0.045
 Where-0.045
Token go
Token ID467
Feature activation+7.91e-01

Pos logit contributions
aleb+0.045
asha+0.044
aman+0.044
ishment+0.043
onia+0.042
Neg logit contributions
 Help-0.022
 crash-0.019
 tearing-0.018
 knocking-0.017
 What-0.017
Token on
Token ID319
Feature activation+1.89e+00

Pos logit contributions
rey+0.033
aleb+0.032
asha+0.032
aman+0.032
iper+0.031
Neg logit contributions
 Help-0.010
 What-0.010
 Do-0.010
 tearing-0.009
 destroying-0.008
Token an
Token ID281
Feature activation+2.06e+00

Pos logit contributions
aleb+0.070
iper+0.069
asha+0.069
rey+0.067
iri+0.067
Neg logit contributions
 Help-0.032
 tearing-0.029
 destroying-0.029
 What-0.028
 Do-0.028
Token adventure
Token ID8855
Feature activation+8.40e-01

Pos logit contributions
rey+0.052
asha+0.051
onia+0.050
aleb+0.048
hel+0.048
Neg logit contributions
 v-0.051
 tearing-0.050
 knocking-0.050
 Help-0.050
 building-0.049
Token on
Token ID319
Feature activation+1.12e+00

Pos logit contributions
aleb+0.036
rey+0.036
asha+0.035
iri+0.035
aman+0.034
Neg logit contributions
 Help-0.009
 to-0.008
 Do-0.008
 poking-0.008
 building-0.008
Token his
Token ID465
Feature activation+3.31e+00

Pos logit contributions
aleb+0.049
iper+0.048
isi+0.048
asha+0.047
ust+0.046
Neg logit contributions
 Help-0.013
 What-0.011
 The-0.010
 Where-0.010
 building-0.010
Token boat
Token ID8848
Feature activation+1.06e+00

Pos logit contributions
asha+0.102
hel+0.100
aleb+0.100
onia+0.100
aman+0.100
Neg logit contributions
 Help-0.070
 building-0.064
 drawing-0.063
 v-0.061
 to-0.061
Token.
Token ID13
Feature activation+3.68e-01

Pos logit contributions
aleb+0.044
rey+0.042
asha+0.042
iri+0.041
onia+0.041
Neg logit contributions
 Help-0.015
 What-0.013
 v-0.012
 Do-0.012
 Was-0.012
Token He
Token ID679
Feature activation+4.38e-01

Pos logit contributions
rey+0.015
asha+0.014
aleb+0.014
i+0.014
onia+0.014
Neg logit contributions
 What-0.006
 Do-0.006
 Where-0.006
 Help-0.006
 Was-0.005
Token went
Token ID1816
Feature activation+1.10e+00

Pos logit contributions
isi+0.016
aleb+0.016
aman+0.016
asha+0.016
onia+0.015
Neg logit contributions
 Help-0.007
 Was-0.007
 v-0.006
 smashing-0.006
 What-0.006
Token swimming
Token ID14899
Feature activation+5.12e-01

Pos logit contributions
rey+0.044
aleb+0.044
asha+0.043
iper+0.043
aman+0.043
Neg logit contributions
 Help-0.015
 What-0.014
 Do-0.013
 smashing-0.013
 tearing-0.013
TokenThey
Token ID2990
Feature activation+2.01e+00

Pos logit contributions
iper+0.031
rey+0.029
 Him+0.029
i+0.029
aleb+0.028
Neg logit contributions
 Help-0.028
 What-0.026
 Was-0.025
 Do-0.025
 smashing-0.024
Token hold
Token ID1745
Feature activation-2.56e-01

Pos logit contributions
aman+0.076
asha+0.076
rey+0.073
onia+0.073
oto+0.073
Neg logit contributions
 Help-0.033
 crash-0.028
 th-0.026
 knocking-0.025
 Was-0.025
Token hands
Token ID2832
Feature activation+6.98e-01

Pos logit contributions
 Help+0.006
 What+0.005
 Was+0.005
 Do+0.005
 smashing+0.005
Neg logit contributions
rey-0.008
aleb-0.008
iper-0.008
asha-0.008
aman-0.007
Token and
Token ID290
Feature activation+1.99e+00

Pos logit contributions
rey+0.025
asha+0.025
aleb+0.024
iper+0.024
aman+0.024
Neg logit contributions
 Help-0.012
 tearing-0.011
 smashing-0.011
 What-0.011
free-0.010
Token walk
Token ID2513
Feature activation+4.47e-02

Pos logit contributions
aman+0.081
asha+0.079
isi+0.077
onia+0.077
ust+0.077
Neg logit contributions
 Help-0.031
 crash-0.031
 knocking-0.028
 tearing-0.028
 building-0.027
Token into
Token ID656
Feature activation+1.02e+00

Pos logit contributions
rey+0.002
aleb+0.002
asha+0.001
iper+0.001
aman+0.001
Neg logit contributions
 Help-0.001
 What-0.001
 Was-0.001
 Do-0.001
 smashing-0.001
Token the
Token ID262
Feature activation+1.90e+00

Pos logit contributions
rey+0.030
aleb+0.029
iper+0.028
asha+0.027
aman+0.027
Neg logit contributions
 Help-0.023
 Do-0.023
 Was-0.023
 What-0.022
 Want-0.022
Token cave
Token ID11527
Feature activation+8.18e-02

Pos logit contributions
rey+0.052
aleb+0.049
iper+0.047
asha+0.047
aman+0.046
Neg logit contributions
 Help-0.048
 What-0.047
 Do-0.046
 smashing-0.046
 Was-0.046
Token.
Token ID13
Feature activation+2.16e-01

Pos logit contributions
rey+0.003
aleb+0.003
asha+0.003
iper+0.003
aman+0.003
Neg logit contributions
 Help-0.002
 What-0.002
 Was-0.001
 Do-0.001
 smashing-0.001
Token They
Token ID1119
Feature activation+1.86e+00

Pos logit contributions
aleb+0.005
rey+0.005
asha+0.005
aman+0.005
iper+0.005
Neg logit contributions
smart-0.006
 smashing-0.006
 destroying-0.006
 tearing-0.006
 Help-0.006
Token see
Token ID766
Feature activation+1.02e+00

Pos logit contributions
aman+0.083
asha+0.083
oto+0.081
rey+0.080
isi+0.080
Neg logit contributions
 Help-0.020
 Was-0.016
 building-0.016
 crash-0.016
 knocking-0.015
TokenThe
Token ID464
Feature activation-1.30e+00

Pos logit contributions
 Help+0.007
 What+0.007
 Was+0.007
 Do+0.007
 Where+0.007
Neg logit contributions
rey-0.009
aleb-0.009
iper-0.009
asha-0.009
aman-0.008
Token end
Token ID886
Feature activation+5.00e-02

Pos logit contributions
 Help+0.036
 Was+0.034
 Do+0.034
 What+0.034
 smashing+0.034
Neg logit contributions
rey-0.034
aleb-0.033
iper-0.031
asha-0.031
aman-0.030
Token.
Token ID13
Feature activation-1.56e-01

Pos logit contributions
rey+0.002
aleb+0.001
iper+0.001
asha+0.001
aman+0.001
Neg logit contributions
 Help-0.001
 Do-0.001
 What-0.001
 smashing-0.001
 Was-0.001
Token<|endoftext|>
Token ID50256
Feature activation-1.02e+00

Pos logit contributions
 Help+0.003
 What+0.002
 Was+0.002
 Do+0.002
 Where+0.002
Neg logit contributions
rey-0.006
aleb-0.006
iper-0.006
asha-0.006
aman-0.005
TokenOnce
Token ID7454
Feature activation+8.15e-01

Pos logit contributions
 smashing+0.023
 Help+0.022
 tearing+0.022
 destroying+0.022
 Was+0.020
Neg logit contributions
rey-0.031
aleb-0.029
asha-0.028
hel-0.028
onia-0.027
Token upon
Token ID2402
Feature activation+1.37e+00

Pos logit contributions
rey+0.023
aleb+0.022
asha+0.022
iper+0.022
aman+0.021
Neg logit contributions
 Help-0.020
 What-0.020
 Was-0.019
 Do-0.019
 Where-0.019
Token a
Token ID257
Feature activation+1.53e+00

Pos logit contributions
aleb+0.051
rey+0.051
iper+0.051
asha+0.050
aman+0.050
Neg logit contributions
 Help-0.024
 What-0.023
 Do-0.022
 Where-0.021
 Whe-0.020
Token time
Token ID640
Feature activation-1.79e-01

Pos logit contributions
rey+0.047
aleb+0.046
iper+0.045
asha+0.045
i+0.044
Neg logit contributions
 Help-0.033
 What-0.031
 Was-0.030
 Do-0.029
 Whe-0.029
Token there
Token ID612
Feature activation-6.51e-01

Pos logit contributions
 smashing+0.003
 Was+0.003
 Help+0.003
 What+0.003
 tearing+0.003
Neg logit contributions
rey-0.006
aleb-0.005
aman-0.005
iper-0.005
asha-0.005
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
 Help+0.012
 What+0.011
 Was+0.011
 Do+0.011
 Where+0.011
Neg logit contributions
rey-0.023
aleb-0.022
iper-0.022
asha-0.022
aman-0.021
Token a
Token ID257
Feature activation-3.58e-01

Pos logit contributions
rey+0.043
iper+0.043
asha+0.042
aleb+0.042
aman+0.042
Neg logit contributions
 What-0.016
 Help-0.015
 Do-0.015
 Whe-0.014
 tearing-0.014
Token.
Token ID13
Feature activation-3.67e-01

Pos logit contributions
 Help+0.004
 What+0.004
 Was+0.004
 Do+0.004
 tearing+0.004
Neg logit contributions
rey-0.008
aleb-0.008
asha-0.008
iper-0.008
aman-0.008
Token
Token ID220
Feature activation-7.37e-01

Pos logit contributions
 Help+0.007
 What+0.006
 Was+0.006
 Do+0.006
 Where+0.006
Neg logit contributions
rey-0.013
aleb-0.013
asha-0.012
iper-0.012
aman-0.012
Token
Token ID198
Feature activation+1.33e-01

Pos logit contributions
 Help+0.010
 What+0.010
 Was+0.009
 Do+0.009
 Where+0.009
Neg logit contributions
rey-0.030
aleb-0.029
asha-0.029
iper-0.028
aman-0.028
Token
Token ID198
Feature activation-4.24e-03

Pos logit contributions
rey+0.005
aleb+0.005
asha+0.005
iper+0.005
aman+0.005
Neg logit contributions
 Help-0.002
 What-0.002
 Was-0.002
 Do-0.002
 Where-0.002
TokenSuddenly
Token ID38582
Feature activation-3.08e-01

Pos logit contributions
 Help+0.000
 What+0.000
 Was+0.000
 Where+0.000
 Do+0.000
Neg logit contributions
rey-0.000
iper-0.000
asha-0.000
aleb-0.000
i-0.000
Token,
Token ID11
Feature activation+8.81e-01

Pos logit contributions
 Help+0.003
 What+0.003
 Was+0.003
 Where+0.003
 Do+0.002
Neg logit contributions
aleb-0.013
rey-0.013
asha-0.013
iper-0.013
isi-0.013
Token the
Token ID262
Feature activation-1.81e-01

Pos logit contributions
iper+0.030
asha+0.030
ita+0.029
aleb+0.029
rey+0.029
Neg logit contributions
 Help-0.019
 What-0.018
 Where-0.017
 Whe-0.017
 Was-0.017
Token yarn
Token ID21181
Feature activation+2.10e+00

Pos logit contributions
 What+0.004
 Help+0.004
 tearing+0.004
 Was+0.004
 smashing+0.004
Neg logit contributions
rey-0.006
aleb-0.006
asha-0.006
iri-0.006
aman-0.006
Token became
Token ID2627
Feature activation+1.79e+00

Pos logit contributions
aleb+0.078
rey+0.073
aman+0.071
oto+0.071
 Him+0.070
Neg logit contributions
 tearing-0.038
 Help-0.037
 smashing-0.037
 Was-0.037
 poking-0.036
Token slippery
Token ID32911
Feature activation+5.60e-01

Pos logit contributions
aleb+0.063
rey+0.062
iper+0.061
asha+0.060
aman+0.059
Neg logit contributions
 tearing-0.032
 smashing-0.032
 Help-0.031
 destroying-0.031
 Was-0.030
Token and
Token ID290
Feature activation+7.27e-01

Pos logit contributions
rey+0.019
aleb+0.019
iper+0.018
asha+0.018
onia+0.018
Neg logit contributions
 tearing-0.011
 smashing-0.011
 Help-0.011
 destroying-0.011
 What-0.010
Token the
Token ID262
Feature activation+4.76e-01

Pos logit contributions
rey+0.034
aleb+0.034
asha+0.032
iper+0.032
aman+0.032
Neg logit contributions
 What-0.014
 Help-0.014
 Do-0.014
 tearing-0.013
 Where-0.013
Token poem
Token ID21247
Feature activation+1.44e+00

Pos logit contributions
rey+0.010
aleb+0.010
aman+0.010
iper+0.010
asha+0.009
Neg logit contributions
 Help-0.015
 What-0.015
 Do-0.014
 Was-0.014
 Where-0.014
Token by
Token ID416
Feature activation+1.70e-01

Pos logit contributions
aleb+0.056
rey+0.055
iper+0.052
aman+0.052
ishment+0.052
Neg logit contributions
 Help-0.022
 Was-0.022
 What-0.022
 tearing-0.021
 Where-0.021
Token heart
Token ID2612
Feature activation-1.14e+00

Pos logit contributions
rey+0.005
aleb+0.005
asha+0.004
iper+0.004
aman+0.004
Neg logit contributions
 Help-0.004
 What-0.004
 Was-0.004
 Do-0.004
 Where-0.004
Token.
Token ID13
Feature activation+6.08e-02

Pos logit contributions
 Help+0.016
 What+0.015
 tearing+0.015
 Was+0.015
free+0.014
Neg logit contributions
aleb-0.046
rey-0.045
aman-0.042
asha-0.042
onia-0.042
Token
Token ID198
Feature activation+5.85e-01

Pos logit contributions
rey+0.001
iper+0.001
aman+0.001
aleb+0.001
asha+0.001
Neg logit contributions
 smashing-0.002
 destroying-0.002
 Help-0.002
 tearing-0.002
 biting-0.002
Token
Token ID198
Feature activation+3.09e-01

Pos logit contributions
rey+0.018
aleb+0.018
asha+0.017
iper+0.017
aman+0.017
Neg logit contributions
 smashing-0.012
 Help-0.012
 destroying-0.012
 tearing-0.012
 What-0.011
TokenOn
Token ID2202
Feature activation+6.48e-01

Pos logit contributions
rey+0.008
aleb+0.007
iper+0.007
asha+0.007
aman+0.007
Neg logit contributions
 Help-0.009
 What-0.008
 Do-0.008
 Was-0.008
 smashing-0.008
Token a
Token ID257
Feature activation+1.18e+00

Pos logit contributions
aleb+0.023
ust+0.021
asha+0.021
iri+0.021
otton+0.021
Neg logit contributions
 Help-0.012
 tearing-0.011
 destroying-0.010
 What-0.010
 v-0.010
Token bright
Token ID6016
Feature activation+1.60e+00

Pos logit contributions
rey+0.042
aleb+0.041
asha+0.040
iper+0.040
aman+0.040
Neg logit contributions
 Help-0.021
 What-0.020
 Was-0.019
 Do-0.019
 smashing-0.019
Token and
Token ID290
Feature activation-1.10e+00

Pos logit contributions
aleb+0.054
rey+0.050
asha+0.049
iper+0.048
aman+0.048
Neg logit contributions
 tearing-0.029
 What-0.029
 Help-0.029
 Do-0.028
 v-0.028
Token,
Token ID11
Feature activation-6.48e-01

Pos logit contributions
 Help+0.003
 What+0.003
 Was+0.003
 Do+0.003
 smashing+0.003
Neg logit contributions
rey-0.005
aleb-0.005
asha-0.005
iper-0.005
aman-0.005
Token and
Token ID290
Feature activation-4.85e-01

Pos logit contributions
 Help+0.015
 What+0.014
 Do+0.014
 tearing+0.014
 smashing+0.014
Neg logit contributions
aleb-0.020
rey-0.020
iper-0.019
asha-0.019
aman-0.018
Token the
Token ID262
Feature activation-3.16e-01

Pos logit contributions
 Help+0.009
 What+0.008
 Do+0.008
 Was+0.008
 smashing+0.008
Neg logit contributions
aleb-0.017
rey-0.017
asha-0.017
iper-0.017
aman-0.017
Token bird
Token ID6512
Feature activation-9.53e-01

Pos logit contributions
 Help+0.007
 What+0.007
 Was+0.007
 Do+0.007
 smashing+0.007
Neg logit contributions
rey-0.010
aleb-0.009
iper-0.009
asha-0.009
aman-0.009
Token and
Token ID290
Feature activation+2.59e-01

Pos logit contributions
 Help+0.020
 Was+0.019
 What+0.019
 tearing+0.018
 smashing+0.018
Neg logit contributions
aleb-0.031
rey-0.031
iper-0.029
asha-0.029
aman-0.029
Token his
Token ID465
Feature activation+5.91e-01

Pos logit contributions
rey+0.008
aleb+0.008
asha+0.008
iper+0.008
aman+0.008
Neg logit contributions
 Help-0.006
 What-0.006
 Was-0.005
 Do-0.005
 smashing-0.005
Token friends
Token ID2460
Feature activation-4.05e-01

Pos logit contributions
aleb+0.017
rey+0.017
aman+0.016
iper+0.016
asha+0.016
Neg logit contributions
 Help-0.015
 What-0.014
 tearing-0.013
 Was-0.013
 Where-0.013
Token put
Token ID1234
Feature activation+5.79e-01

Pos logit contributions
 Help+0.009
 Was+0.008
 What+0.008
 tearing+0.008
 smashing+0.008
Neg logit contributions
rey-0.013
aleb-0.013
asha-0.012
iper-0.012
aman-0.012
Token their
Token ID511
Feature activation-9.50e-01

Pos logit contributions
asha+0.023
rey+0.023
aleb+0.023
ita+0.023
aman+0.023
Neg logit contributions
 What-0.008
 v-0.008
 Help-0.008
 tearing-0.007
 Do-0.007
Token plan
Token ID1410
Feature activation+1.36e+00

Pos logit contributions
 Help+0.024
 What+0.023
 Was+0.022
 tearing+0.022
 Do+0.022
Neg logit contributions
rey-0.027
aleb-0.026
asha-0.026
iper-0.025
aman-0.025
Token to
Token ID284
Feature activation+6.34e-01

Pos logit contributions
rey+0.050
aleb+0.050
asha+0.049
aman+0.049
iper+0.048
Neg logit contributions
 Help-0.023
 What-0.021
 Was-0.020
 tearing-0.020
 smashing-0.020
Token happy
Token ID3772
Feature activation+1.49e-01

Pos logit contributions
 Help+0.038
 What+0.037
 Do+0.037
 smashing+0.037
 tearing+0.036
Neg logit contributions
aleb-0.057
rey-0.056
asha-0.055
iper-0.055
aman-0.055
Token for
Token ID329
Feature activation-9.59e-02

Pos logit contributions
rey+0.006
aleb+0.006
asha+0.006
iper+0.006
aman+0.006
Neg logit contributions
 Help-0.002
 What-0.002
 Do-0.002
 Was-0.002
 Where-0.002
Token it
Token ID340
Feature activation-3.99e-03

Pos logit contributions
 Help+0.002
 What+0.002
 Do+0.002
 Was+0.002
 smashing+0.002
Neg logit contributions
rey-0.003
aleb-0.003
asha-0.003
iper-0.003
aman-0.003
Token."
Token ID526
Feature activation+1.94e-01

Pos logit contributions
 Help+0.000
 What+0.000
 Do+0.000
 tearing+0.000
 Was+0.000
Neg logit contributions
aleb-0.000
rey-0.000
aman-0.000
asha-0.000
iper-0.000
Token
Token ID198
Feature activation-1.24e-01

Pos logit contributions
rey+0.007
aleb+0.007
asha+0.007
iper+0.007
aman+0.007
Neg logit contributions
 Help-0.003
 What-0.003
 Was-0.003
 Do-0.003
 Where-0.003
Token
Token ID198
Feature activation-3.94e-02

Pos logit contributions
 Help+0.002
 What+0.002
 Was+0.002
 Do+0.002
 smashing+0.002
Neg logit contributions
rey-0.004
aleb-0.004
asha-0.004
iper-0.004
aman-0.004
TokenL
Token ID43
Feature activation-6.05e-01

Pos logit contributions
 Help+0.001
 What+0.001
 Was+0.001
 Do+0.001
 Where+0.001
Neg logit contributions
aleb-0.001
rey-0.001
iper-0.001
ishment-0.001
i-0.001
Tokenily
Token ID813
Feature activation+6.37e-01

Pos logit contributions
 Help+0.012
 What+0.012
 Was+0.011
 Do+0.011
 smashing+0.011
Neg logit contributions
rey-0.020
aleb-0.020
asha-0.019
iper-0.019
aman-0.019
Token nodded
Token ID14464
Feature activation+7.42e-01

Pos logit contributions
 Him+0.022
aman+0.021
 avail+0.021
aleb+0.021
isi+0.021
Neg logit contributions
 Help-0.010
 Was-0.010
 What-0.009
 tearing-0.009
 smashing-0.009
Token and
Token ID290
Feature activation+1.08e+00

Pos logit contributions
aleb+0.025
iper+0.024
rey+0.024
asha+0.023
aman+0.023
Neg logit contributions
 Help-0.016
 What-0.015
 Was-0.014
 Do-0.014
 tearing-0.014
Token they
Token ID484
Feature activation+7.22e-01

Pos logit contributions
aleb+0.037
isi+0.035
aman+0.035
rey+0.035
onia+0.034
Neg logit contributions
 Help-0.020
 throwing-0.018
 tearing-0.018
 smashing-0.017
 What-0.017
Token's
Token ID338
Feature activation+2.46e-01

Pos logit contributions
 Help+0.006
 Was+0.006
 tearing+0.005
 What+0.005
 smashing+0.005
Neg logit contributions
aleb-0.010
rey-0.010
aman-0.010
oto-0.010
 Him-0.010
Token friend
Token ID1545
Feature activation-9.44e-01

Pos logit contributions
rey+0.007
aleb+0.006
asha+0.006
aman+0.006
iper+0.006
Neg logit contributions
 Help-0.007
 What-0.006
 Was-0.006
 tearing-0.006
 smashing-0.006
Token,
Token ID11
Feature activation-8.70e-01

Pos logit contributions
 Help+0.018
 What+0.017
 Was+0.017
 Where+0.016
 Do+0.016
Neg logit contributions
rey-0.033
aleb-0.032
asha-0.031
iper-0.031
aman-0.031
Token Tim
Token ID5045
Feature activation-1.07e-01

Pos logit contributions
 Help+0.018
 What+0.018
 Do+0.017
 Was+0.017
 Where+0.017
Neg logit contributions
rey-0.029
aleb-0.029
iper-0.028
asha-0.028
aman-0.027
Tokenmy
Token ID1820
Feature activation-2.99e-01

Pos logit contributions
 Help+0.003
 What+0.003
 tearing+0.003
 Do+0.003
 smashing+0.003
Neg logit contributions
rey-0.003
aleb-0.003
asha-0.003
iper-0.003
aman-0.003
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
 Help+0.004
 What+0.004
 Was+0.004
 tearing+0.004
 smashing+0.004
Neg logit contributions
rey-0.011
aleb-0.011
iper-0.011
asha-0.011
aman-0.011
Token saw
Token ID2497
Feature activation-7.48e-01

Pos logit contributions
 Help+0.021
 What+0.020
 Was+0.020
 Do+0.019
 smashing+0.019
Neg logit contributions
rey-0.043
aleb-0.043
asha-0.042
iper-0.042
aman-0.040
Token her
Token ID607
Feature activation-7.08e-01

Pos logit contributions
 What+0.017
 Help+0.017
 Was+0.016
 Do+0.016
 tearing+0.016
Neg logit contributions
rey-0.024
aleb-0.023
asha-0.022
iper-0.022
onia-0.021
Token and
Token ID290
Feature activation-1.66e-01

Pos logit contributions
 Help+0.014
 tearing+0.013
 smashing+0.013
 What+0.013
 destroying+0.013
Neg logit contributions
rey-0.024
aleb-0.024
asha-0.023
iper-0.023
aman-0.022
Token asked
Token ID1965
Feature activation-1.01e+00

Pos logit contributions
 Help+0.004
 What+0.004
 tearing+0.004
 smashing+0.004
 Was+0.004
Neg logit contributions
aleb-0.005
rey-0.005
asha-0.005
iper-0.005
aman-0.005
Token,
Token ID11
Feature activation-1.55e+00

Pos logit contributions
 Help+0.023
 What+0.022
 Was+0.022
 smashing+0.022
 Do+0.022
Neg logit contributions
rey-0.029
aleb-0.028
iper-0.028
aman-0.027
asha-0.027
Token!
Token ID0
Feature activation+1.75e-01

Pos logit contributions
aleb+0.034
rey+0.034
iper+0.033
asha+0.033
aman+0.032
Neg logit contributions
 What-0.022
 Help-0.022
 tearing-0.022
 smashing-0.022
 destroying-0.022
Token It
Token ID632
Feature activation+6.19e-01

Pos logit contributions
rey+0.007
aleb+0.007
asha+0.006
iper+0.006
aman+0.006
Neg logit contributions
 Help-0.003
 What-0.002
 Was-0.002
 Do-0.002
 smashing-0.002
Token was
Token ID373
Feature activation+1.20e+00

Pos logit contributions
aleb+0.028
iper+0.027
aman+0.025
oto+0.025
isi+0.025
Neg logit contributions
 Was-0.007
 Help-0.006
 tearing-0.006
 What-0.006
 smashing-0.006
Token a
Token ID257
Feature activation+1.18e-01

Pos logit contributions
aleb+0.047
iper+0.046
asha+0.044
rey+0.044
isi+0.042
Neg logit contributions
 tearing-0.021
 destroying-0.021
 Help-0.020
 smashing-0.020
 What-0.019
Token noise
Token ID7838
Feature activation-1.93e-01

Pos logit contributions
rey+0.003
aleb+0.003
asha+0.003
iper+0.003
aman+0.003
Neg logit contributions
 Help-0.003
 What-0.003
 Do-0.003
 Was-0.003
 Where-0.003
Token,
Token ID11
Feature activation-8.90e-02

Pos logit contributions
 Help+0.003
 destroying+0.003
 tearing+0.003
 smashing+0.003
 What+0.003
Neg logit contributions
aleb-0.007
rey-0.007
iper-0.007
asha-0.007
aman-0.006
Token but
Token ID475
Feature activation+9.55e-01

Pos logit contributions
 tearing+0.002
 What+0.002
 Do+0.002
 smashing+0.002
 destroying+0.002
Neg logit contributions
aleb-0.003
iper-0.003
rey-0.003
asha-0.003
isi-0.003
Token it
Token ID340
Feature activation+8.72e-01

Pos logit contributions
aleb+0.038
rey+0.037
iper+0.037
asha+0.037
aman+0.036
Neg logit contributions
 Help-0.014
 What-0.014
 Do-0.013
 Was-0.013
 tearing-0.013
Token was
Token ID373
Feature activation+1.50e+00

Pos logit contributions
aleb+0.039
iper+0.037
aman+0.036
isi+0.036
 Him+0.035
Neg logit contributions
 Was-0.009
 tearing-0.009
 Help-0.009
 destroying-0.009
 smashing-0.009
Token far
Token ID1290
Feature activation+1.38e+00

Pos logit contributions
aleb+0.056
iper+0.054
asha+0.052
rey+0.052
onia+0.050
Neg logit contributions
 tearing-0.029
 destroying-0.029
 Help-0.028
 smashing-0.028
 knocking-0.026
Token away
Token ID1497
Feature activation-1.42e-01

Pos logit contributions
iper+0.048
aleb+0.048
rey+0.047
asha+0.047
iri+0.045
Neg logit contributions
 What-0.025
 Do-0.025
 destroying-0.024
free-0.024
 smashing-0.024
Token And
Token ID843
Feature activation+6.27e-01

Pos logit contributions
rey+0.021
aleb+0.021
asha+0.021
iper+0.020
aman+0.020
Neg logit contributions
 Help-0.009
 What-0.009
 Do-0.008
 Was-0.008
 Where-0.008
Token I
Token ID314
Feature activation-1.54e-01

Pos logit contributions
rey+0.024
aleb+0.024
asha+0.023
aman+0.023
onia+0.022
Neg logit contributions
 What-0.012
 Do-0.011
 Help-0.011
 Where-0.010
 Was-0.010
Token want
Token ID765
Feature activation-8.09e-01

Pos logit contributions
 Help+0.004
 What+0.004
 Was+0.003
 Do+0.003
 Where+0.003
Neg logit contributions
rey-0.005
aleb-0.004
asha-0.004
iper-0.004
aman-0.004
Token to
Token ID284
Feature activation+5.53e-03

Pos logit contributions
 Help+0.009
 What+0.009
 Was+0.008
 Do+0.008
 smashing+0.008
Neg logit contributions
rey-0.033
aleb-0.033
iper-0.032
asha-0.032
aman-0.032
Token draw
Token ID3197
Feature activation+9.09e-01

Pos logit contributions
aleb+0.000
asha+0.000
aman+0.000
iper+0.000
rey+0.000
Neg logit contributions
 Help-0.000
 Do-0.000
 What-0.000
 Was-0.000
 tearing-0.000
Token a
Token ID257
Feature activation-5.54e-01

Pos logit contributions
aleb+0.037
aman+0.036
rey+0.036
asha+0.036
iper+0.035
Neg logit contributions
 Do-0.015
 What-0.015
 v-0.013
 Help-0.013
 Where-0.012
Token picture
Token ID4286
Feature activation+7.71e-01

Pos logit contributions
 Help+0.013
 What+0.013
 Was+0.013
 Do+0.013
 smashing+0.012
Neg logit contributions
rey-0.016
aleb-0.016
asha-0.015
iper-0.015
aman-0.015
Token of
Token ID286
Feature activation+5.38e-01

Pos logit contributions
rey+0.035
aleb+0.035
aman+0.034
asha+0.034
iper+0.033
Neg logit contributions
 Do-0.008
 Help-0.008
 What-0.007
 v-0.007
smart-0.006
Token us
Token ID514
Feature activation+4.82e-01

Pos logit contributions
aleb+0.019
rey+0.019
asha+0.019
iper+0.018
aman+0.018
Neg logit contributions
 Help-0.011
 Do-0.011
 What-0.011
 tearing-0.010
 v-0.010
Token,"
Token ID553
Feature activation-2.15e-01

Pos logit contributions
asha+0.021
aleb+0.021
aman+0.021
rey+0.021
iper+0.021
Neg logit contributions
 Do-0.005
 Help-0.005
 What-0.005
 v-0.004
free-0.004
Token Lily
Token ID20037
Feature activation+2.46e+00

Pos logit contributions
 Help+0.003
 What+0.003
 Do+0.003
 Was+0.003
 Where+0.002
Neg logit contributions
rey-0.009
aleb-0.009
asha-0.008
iper-0.008
aman-0.008
Token twins
Token ID20345
Feature activation-4.24e-01

Pos logit contributions
rey+0.033
asha+0.032
aleb+0.032
iper+0.031
aman+0.031
Neg logit contributions
 Help-0.018
 What-0.016
 Do-0.016
 tearing-0.016
 smashing-0.016
Token.
Token ID13
Feature activation+8.13e-01

Pos logit contributions
 Help+0.011
 Where+0.011
 Want+0.011
 Whe+0.011
 Do+0.011
Neg logit contributions
rey-0.010
aleb-0.010
i-0.010
pa-0.009
iper-0.009
Token They
Token ID1119
Feature activation+3.38e-01

Pos logit contributions
rey+0.027
iper+0.026
aleb+0.026
asha+0.025
aman+0.025
Neg logit contributions
 Help-0.017
 What-0.017
 Do-0.016
 Was-0.016
 Where-0.016
Token like
Token ID588
Feature activation-5.05e-02

Pos logit contributions
asha+0.013
rey+0.013
aman+0.013
aleb+0.013
iper+0.012
Neg logit contributions
free-0.005
 What-0.005
 Help-0.005
 Was-0.005
 Do-0.005
Token to
Token ID284
Feature activation+1.21e-01

Pos logit contributions
 Help+0.001
 What+0.001
 Was+0.001
 smashing+0.001
 Do+0.001
Neg logit contributions
rey-0.002
aleb-0.002
iper-0.002
asha-0.002
aman-0.002
Token play
Token ID711
Feature activation-6.23e-01

Pos logit contributions
aman+0.005
aleb+0.005
rey+0.005
asha+0.005
iper+0.005
Neg logit contributions
 Help-0.002
 What-0.001
 Do-0.001
 Was-0.001
 Where-0.001
Token in
Token ID287
Feature activation+5.62e-01

Pos logit contributions
 Help+0.013
 What+0.013
 Was+0.012
 Do+0.012
 smashing+0.012
Neg logit contributions
rey-0.020
aleb-0.020
asha-0.019
iper-0.019
aman-0.019
Token the
Token ID262
Feature activation+1.17e+00

Pos logit contributions
rey+0.019
aleb+0.018
asha+0.018
iper+0.018
aman+0.017
Neg logit contributions
 Help-0.011
 What-0.011
 Was-0.011
 Do-0.010
 Where-0.010
Token park
Token ID3952
Feature activation-1.01e+00

Pos logit contributions
rey+0.035
iper+0.035
asha+0.034
aleb+0.033
i+0.033
Neg logit contributions
 Help-0.027
 What-0.026
 Do-0.025
 tearing-0.025
 v-0.025
Token with
Token ID351
Feature activation+7.62e-01

Pos logit contributions
 Help+0.016
 What+0.015
 Do+0.014
 Was+0.014
 Where+0.013
Neg logit contributions
rey-0.039
aleb-0.039
iper-0.038
asha-0.038
aman-0.038
Token their
Token ID511
Feature activation+1.50e+00

Pos logit contributions
aman+0.025
iper+0.024
rey+0.024
asha+0.024
aleb+0.024
Neg logit contributions
 Help-0.016
 What-0.015
 Whe-0.015
 tearing-0.014
 Do-0.014
Token the
Token ID262
Feature activation-1.64e+00

Pos logit contributions
 Help+0.022
 Do+0.022
 smashing+0.022
 Was+0.022
 tearing+0.021
Neg logit contributions
rey-0.021
aleb-0.021
iper-0.021
asha-0.020
onia-0.020
Token apple
Token ID17180
Feature activation+2.46e-01

Pos logit contributions
 Help+0.051
smart+0.051
 Do+0.050
 smashing+0.050
 destroying+0.049
Neg logit contributions
aleb-0.033
asha-0.032
aman-0.031
rey-0.031
onia-0.030
Token and
Token ID290
Feature activation-9.57e-01

Pos logit contributions
rey+0.008
aleb+0.008
iper+0.008
asha+0.008
aman+0.008
Neg logit contributions
 Help-0.005
 What-0.005
 Was-0.005
 tearing-0.005
 smashing-0.005
Token ran
Token ID4966
Feature activation-1.28e+00

Pos logit contributions
 Help+0.019
 What+0.018
 Was+0.018
 smashing+0.018
 Do+0.018
Neg logit contributions
rey-0.032
aleb-0.031
iper-0.031
asha-0.030
aman-0.030
Token back
Token ID736
Feature activation-3.27e-01

Pos logit contributions
 Was+0.035
 Do+0.035
smart+0.034
 Help+0.034
 Are+0.033
Neg logit contributions
aleb-0.029
rey-0.027
iper-0.027
hel-0.026
icity-0.025
Token outside
Token ID2354
Feature activation-2.34e+00

Pos logit contributions
 Do+0.005
 Was+0.005
 Help+0.005
 What+0.005
 smashing+0.005
Neg logit contributions
rey-0.012
aleb-0.012
iper-0.011
asha-0.011
aman-0.011
Token to
Token ID284
Feature activation-8.38e-01

Pos logit contributions
 Was+0.062
 Where+0.058
AAAA+0.058
 What+0.056
 Do+0.056
Neg logit contributions
rey-0.050
i-0.048
pa-0.047
aleb-0.046
 eagerly-0.045
Token play
Token ID711
Feature activation-2.76e+00

Pos logit contributions
free+0.022
 Was+0.022
 Help+0.022
 smashing+0.021
smart+0.021
Neg logit contributions
rey-0.021
aleb-0.020
pa-0.018
aman-0.018
asha-0.018
Token with
Token ID351
Feature activation-7.41e-01

Pos logit contributions
 Help+0.082
 Was+0.081
 Those+0.080
 smashing+0.079
oke+0.079
Neg logit contributions
le-0.050
rey-0.048
hel-0.047
aleb-0.044
 jackets-0.043
Token his
Token ID465
Feature activation-3.59e-04

Pos logit contributions
 Help+0.023
 Was+0.022
 Do+0.022
 What+0.022
 Where+0.022
Neg logit contributions
aleb-0.016
rey-0.016
asha-0.015
iper-0.014
i-0.014
Token friends
Token ID2460
Feature activation-1.02e+00

Pos logit contributions
 Help+0.000
 What+0.000
 Do+0.000
 Was+0.000
 Where+0.000
Neg logit contributions
rey-0.000
aleb-0.000
asha-0.000
iper-0.000
aman-0.000
Token a
Token ID257
Feature activation-2.07e+00

Pos logit contributions
rey+0.001
aleb+0.001
asha+0.001
aman+0.001
iper+0.001
Neg logit contributions
 Help-0.001
 What-0.001
 tearing-0.001
 Was-0.001
 smashing-0.001
Token naughty
Token ID45128
Feature activation-2.09e-01

Pos logit contributions
 What+0.050
 Do+0.049
 Help+0.048
 Where+0.048
 Was+0.047
Neg logit contributions
rey-0.058
aman-0.054
iper-0.054
aleb-0.054
asha-0.054
Token face
Token ID1986
Feature activation-2.97e+00

Pos logit contributions
 Do+0.005
 What+0.005
 Help+0.005
 Was+0.005
 Where+0.005
Neg logit contributions
rey-0.006
i-0.005
aleb-0.005
asha-0.005
iper-0.005
Token every
Token ID790
Feature activation-1.17e+00

Pos logit contributions
 Help+0.072
 Was+0.070
 What+0.070
 Do+0.069
 Where+0.069
Neg logit contributions
rey-0.077
i-0.076
aman-0.075
aleb-0.075
iper-0.075
Token time
Token ID640
Feature activation-1.00e+00

Pos logit contributions
 What+0.031
 Help+0.031
 Do+0.031
 Was+0.031
 smashing+0.031
Neg logit contributions
rey-0.029
aleb-0.028
asha-0.028
iper-0.028
aman-0.027
Token she
Token ID673
Feature activation-2.21e+00

Pos logit contributions
 Help+0.018
 What+0.018
 tearing+0.017
 smashing+0.017
 Do+0.017
Neg logit contributions
rey-0.036
aleb-0.035
iper-0.034
asha-0.034
aman-0.033
Token had
Token ID550
Feature activation-1.21e+00

Pos logit contributions
 Help+0.043
 Was+0.041
 tearing+0.040
 What+0.040
 smashing+0.040
Neg logit contributions
rey-0.075
aleb-0.073
aman-0.072
asha-0.071
iper-0.070
Token to
Token ID284
Feature activation-1.39e+00

Pos logit contributions
 Help+0.022
 What+0.021
 Was+0.021
 Do+0.021
 Where+0.020
Neg logit contributions
rey-0.042
aleb-0.041
asha-0.040
iper-0.040
aman-0.039
Token take
Token ID1011
Feature activation-9.92e-01

Pos logit contributions
 Help+0.021
 th+0.018
 bru+0.018
 tearing+0.017
 crash+0.016
Neg logit contributions
aleb-0.054
rey-0.053
asha-0.051
iper-0.051
aman-0.051
Token it
Token ID340
Feature activation-2.20e-01

Pos logit contributions
 Help+0.022
 What+0.021
 Was+0.021
 Do+0.021
 smashing+0.021
Neg logit contributions
rey-0.030
aleb-0.029
iper-0.029
asha-0.028
aman-0.028
Token.
Token ID13
Feature activation-8.18e-01

Pos logit contributions
 Help+0.005
 What+0.004
 tearing+0.004
 smashing+0.004
 Was+0.004
Neg logit contributions
rey-0.007
aleb-0.007
asha-0.007
iper-0.007
aman-0.007
Token.
Token ID13
Feature activation-9.33e-01

Pos logit contributions
 Help+0.044
 Was+0.044
 smashing+0.043
 Where+0.042
 tearing+0.042
Neg logit contributions
aleb-0.035
rey-0.035
 jackets-0.034
asha-0.033
hel-0.032
Token It
Token ID632
Feature activation-4.23e-01

Pos logit contributions
smart+0.024
 Help+0.022
 smashing+0.022
 destroying+0.022
 tearing+0.021
Neg logit contributions
rey-0.023
iper-0.023
aman-0.023
aleb-0.023
asha-0.022
Token was
Token ID373
Feature activation+3.02e-01

Pos logit contributions
 Help+0.010
 What+0.009
 Do+0.009
 Was+0.009
 Where+0.009
Neg logit contributions
rey-0.013
aleb-0.012
asha-0.012
iper-0.011
aman-0.011
Token a
Token ID257
Feature activation-3.00e-01

Pos logit contributions
rey+0.009
aleb+0.009
asha+0.009
iper+0.009
aman+0.009
Neg logit contributions
 Help-0.007
 What-0.007
 Was-0.007
 Do-0.006
 smashing-0.006
Token messy
Token ID24097
Feature activation+5.28e-02

Pos logit contributions
 Help+0.007
 What+0.007
 Was+0.007
 Where+0.007
 Do+0.007
Neg logit contributions
rey-0.008
aleb-0.008
aman-0.008
asha-0.008
iper-0.008
Token day
Token ID1110
Feature activation-2.02e+00

Pos logit contributions
rey+0.002
aleb+0.002
asha+0.002
iper+0.002
aman+0.001
Neg logit contributions
 Help-0.001
 What-0.001
 Was-0.001
 Do-0.001
 smashing-0.001
Token because
Token ID780
Feature activation-7.19e-01

Pos logit contributions
 Help+0.046
 What+0.044
 Was+0.044
 Do+0.043
 Where+0.043
Neg logit contributions
rey-0.060
aleb-0.059
iper-0.057
asha-0.057
aman-0.057
Token it
Token ID340
Feature activation-4.74e-01

Pos logit contributions
 Help+0.011
 Do+0.011
 What+0.010
 tearing+0.010
 Where+0.010
Neg logit contributions
rey-0.028
aleb-0.028
asha-0.028
iper-0.028
aman-0.027
Token r
Token ID374
Feature activation+1.30e+00

Pos logit contributions
 Help+0.008
 tearing+0.007
 smashing+0.007
 Was+0.007
 What+0.007
Neg logit contributions
aleb-0.017
rey-0.017
iper-0.017
asha-0.017
aman-0.017
Tokenained
Token ID1328
Feature activation-3.53e-01

Pos logit contributions
rey+0.022
aleb+0.021
asha+0.019
aman+0.019
oto+0.019
Neg logit contributions
 Help-0.047
 Was-0.047
 What-0.047
 Do-0.046
 Where-0.046
Token a
Token ID257
Feature activation-1.20e+00

Pos logit contributions
 Help+0.009
 Was+0.009
 What+0.009
 Do+0.009
 Where+0.009
Neg logit contributions
rey-0.009
aman-0.008
hel-0.008
iper-0.008
aleb-0.008
Token didn
Token ID1422
Feature activation-7.32e-01

Pos logit contributions
 Help+0.043
 What+0.043
 Do+0.042
 smashing+0.042
 Where+0.042
Neg logit contributions
rey-0.038
aleb-0.036
iper-0.035
i-0.035
asha-0.034
Token't
Token ID470
Feature activation-2.29e+00

Pos logit contributions
joy+0.017
 Was+0.017
 Do+0.016
 What+0.016
 smashing+0.016
Neg logit contributions
rey-0.020
aleb-0.019
oto-0.018
iper-0.018
hel-0.018
Token mean
Token ID1612
Feature activation-1.86e+00

Pos logit contributions
 Was+0.075
 What+0.071
 Help+0.071
joy+0.070
 Where+0.070
Neg logit contributions
oto-0.040
isi-0.040
ust-0.040
i-0.037
rey-0.036
Token to
Token ID284
Feature activation-2.48e+00

Pos logit contributions
 Was+0.033
 Help+0.032
 tearing+0.032
 smashing+0.032
 hex+0.031
Neg logit contributions
aleb-0.058
i-0.057
rey-0.056
oto-0.056
asha-0.055
Token bite
Token ID13197
Feature activation-1.61e+00

Pos logit contributions
joy+0.066
 Was+0.064
 What+0.062
 Where+0.060
 Did+0.060
Neg logit contributions
i-0.059
rey-0.057
oto-0.054
aleb-0.053
pa-0.052
Token you
Token ID345
Feature activation-2.18e+00

Pos logit contributions
 Help+0.044
 What+0.043
 Do+0.043
 Was+0.042
 smashing+0.042
Neg logit contributions
rey-0.042
aleb-0.040
asha-0.039
iper-0.039
aman-0.038
Token."
Token ID526
Feature activation-9.91e-01

Pos logit contributions
 Help+0.043
 Was+0.042
 What+0.042
 Where+0.041
 smashing+0.041
Neg logit contributions
rey-0.069
aleb-0.067
i-0.065
asha-0.065
aman-0.064
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
 smashing+0.021
 destroying+0.021
 tearing+0.020
 Help+0.020
free+0.020
Neg logit contributions
rey-0.029
iper-0.029
asha-0.029
aleb-0.028
aman-0.027
Token
Token ID198
Feature activation-1.23e+00

Pos logit contributions
 smashing+0.034
 destroying+0.034
 tearing+0.033
 knocking+0.031
 Do+0.031
Neg logit contributions
rey-0.034
iper-0.032
oto-0.032
asha-0.032
aleb-0.031
TokenM
Token ID44
Feature activation+1.84e-01

Pos logit contributions
 Help+0.030
 What+0.030
 Do+0.030
 Was+0.030
 Where+0.030
Neg logit contributions
rey-0.034
aleb-0.033
asha-0.033
iper-0.032
aman-0.031
Tokenittens
Token ID34978
Feature activation+1.78e-01

Pos logit contributions
rey+0.005
aleb+0.005
ishment+0.004
icity+0.004
iper+0.004
Neg logit contributions
 Help-0.005
 Was-0.005
 What-0.004
 Do-0.004
 tearing-0.004
Token.
Token ID13
Feature activation-7.55e-01

Pos logit contributions
 Help+0.013
 What+0.012
 Was+0.012
free+0.012
 smashing+0.012
Neg logit contributions
aleb-0.025
asha-0.024
rey-0.024
aman-0.024
onia-0.023
Token They
Token ID1119
Feature activation+4.45e-01

Pos logit contributions
 What+0.014
 Do+0.014
 Help+0.014
 Where+0.013
 Was+0.013
Neg logit contributions
rey-0.028
aleb-0.027
asha-0.027
iper-0.027
onia-0.026
Token both
Token ID1111
Feature activation-1.13e+00

Pos logit contributions
aman+0.017
aleb+0.017
asha+0.017
rey+0.016
onia+0.016
Neg logit contributions
 th-0.007
 Was-0.006
 Help-0.006
 crash-0.006
 tearing-0.006
Token get
Token ID651
Feature activation-4.36e-01

Pos logit contributions
 What+0.020
 Help+0.020
free+0.020
 Was+0.020
 smashing+0.019
Neg logit contributions
aleb-0.039
rey-0.039
aman-0.039
asha-0.038
iper-0.037
Token wet
Token ID9583
Feature activation-3.77e-01

Pos logit contributions
 Help+0.009
 What+0.009
 smashing+0.008
 tearing+0.008
 Do+0.008
Neg logit contributions
rey-0.015
asha-0.014
aleb-0.014
aman-0.014
iper-0.014
Token,
Token ID11
Feature activation-2.07e+00

Pos logit contributions
 smashing+0.007
 Help+0.007
 tearing+0.007
 destroying+0.007
 What+0.007
Neg logit contributions
rey-0.013
iper-0.013
aleb-0.013
asha-0.012
onia-0.012
Token and
Token ID290
Feature activation-9.95e-01

Pos logit contributions
 smashing+0.037
 tearing+0.037
 Do+0.036
 Help+0.036
 destroying+0.036
Neg logit contributions
rey-0.076
aleb-0.075
iper-0.072
asha-0.072
onia-0.070
Token so
Token ID523
Feature activation-1.21e+00

Pos logit contributions
 Help+0.020
 smashing+0.019
 tearing+0.019
 What+0.019
 Do+0.019
Neg logit contributions
rey-0.034
aleb-0.033
asha-0.032
iper-0.032
aman-0.032
Token do
Token ID466
Feature activation+2.34e-01

Pos logit contributions
 Help+0.023
 What+0.023
 Was+0.022
 tearing+0.022
 Do+0.022
Neg logit contributions
aleb-0.042
rey-0.041
asha-0.040
aman-0.040
iper-0.039
Token their
Token ID511
Feature activation+2.67e-01

Pos logit contributions
aleb+0.008
rey+0.007
iper+0.007
asha+0.007
aman+0.007
Neg logit contributions
 Help-0.005
 What-0.005
 Do-0.005
 Where-0.005
 tearing-0.005
Token toys
Token ID14958
Feature activation-9.96e-02

Pos logit contributions
hel+0.008
aman+0.008
asha+0.008
aleb+0.008
rey+0.008
Neg logit contributions
 Help-0.006
 tearing-0.006
 v-0.005
 destroying-0.005
 smashing-0.005