TOP ACTIVATIONS
MAX = 0.077

asked Max , " Which leash do you want ?" Max
. He escaped from his leash . He is usually friendly
went into the woods collecting berries and nuts . One day
Lily . She loved picking berries in the forest . One
when they bought Sunshine the leash . Sunshine was happy too
home . She put the leash back on Daisy and they
home . She put the leash back on Daisy and they
forest where she would pick berries . One day , she
up a basket full of berries and carried them back to
outside and look at the cher ries on the tree .
of juicy , tasty looking berries . Suddenly he
walk and they noticed the leash was broken . The owner
was able to restore the leash and it was as good
Jimmy grabbed his dog 's leash and started marching with the
that Max understood what the leash was for and enjoyed it
helped someone find their lost pet . She knew that being
" What are peanuts ?" Lily asked .
to get his pet 's leash . It was purple ,
<|endoftext|> L ily loved pe aches . She liked to eat
was relieved and she filled Fl uffy 's bowl with medicine

MIN ACTIVATIONS
MIN = -0.107

watched as her mom carefully se wed Ted 's arm back
Joe , a 3 - year - old boy . He
twenty - eight , twenty - nine , thirty , thirty
nine , thirty , thirty - one , thirty - two
!" shouted her three - year - old son , happy
watched as his mom carefully se wed the stitch in the
place for a 3 - year - old to be ."
the t eddy bear and se wed up the hole in
out a young three - year - old girl in excitement
, a tiny three - year - old girl came across
needle and thread and carefully se wed the hole shut .
Billy , a three - year - old boy .
, a little 3 - year - old boy named Tim
of waves and wind and se ag ull s .
and like all three - year - olds , he was
izzy was a three - year - old girl . She
a needle and thread and se wed the t eddy bear
day , a three - year - old boy decided to
took Sara the 3 - year - old to the park
thirty - one , thirty - two , thirty - three

INTERVAL 0.031 - 0.077
CONTAINS 1.331%

over to the cookie to pick it up , but then
day on , they became friends and played together every time
hands and picked the creamy fruit . She tasted it and
excited to have a new pet . They tried to grab
he was done he went back home , much richer for

INTERVAL -0.015 - 0.031
CONTAINS 86.567%

of her blocks and goes to Tim . She says ,
over to it and said in a happy voice , "
<|endoftext|> Anna and Ben are twins . They like to play
ran outside and he was so wet ! He yelled from
, giving him a big hug . Jack smiled

INTERVAL -0.061 - -0.015
CONTAINS 12.078%

are secrets or treasures or magic in there ," Ben said
. His mom told him to stay inside until he felt
Maybe it was just a big dog ." "
flowers . M imi carried the honey from one flower to
the sand castle . Mama and Mia stayed at the beach

INTERVAL -0.107 - -0.061
CONTAINS 0.024%

this crib is just as wide as my old one ,"
Jimmy was a 3 - year - old who loved to
, Tim took the monster - ch aser to bed with
. Every day two 3 - year - old children enjoyed
but the words were too complicated for him .
Token asked
Token ID1965
Feature activation-1.02e-02

Pos logit contributions
 tant+0.002
sc+0.002
 baths+0.002
 tests+0.002
 videos+0.002
Neg logit contributions
ich-0.002
opsy-0.002
field-0.002
ster-0.002
flower-0.002
Token Max
Token ID5436
Feature activation-1.19e-02

Pos logit contributions
sc+0.014
 tant+0.013
igators+0.012
 baths+0.012
igator+0.011
Neg logit contributions
ich-0.020
ster-0.019
opsy-0.019
-0.018
illa-0.017
Token,
Token ID11
Feature activation+2.93e-03

Pos logit contributions
 tant+0.018
sc+0.017
 baths+0.016
 videos+0.015
 tests+0.015
Neg logit contributions
ich-0.025
opsy-0.022
ster-0.021
field-0.021
sters-0.020
Token "
Token ID366
Feature activation+5.81e-04

Pos logit contributions
ich+0.007
opsy+0.006
field+0.006
ster+0.006
flower+0.005
Neg logit contributions
 tant-0.004
sc-0.004
 baths-0.004
 videos-0.003
 tests-0.003
TokenWhich
Token ID13828
Feature activation+1.54e-02

Pos logit contributions
ich+0.001
opsy+0.001
field+0.001
ster+0.001
sters+0.001
Neg logit contributions
sc-0.001
 tant-0.001
 baths-0.001
 videos-0.001
 tests-0.001
Token leash
Token ID40529
Feature activation+7.35e-02

Pos logit contributions
ich+0.033
opsy+0.030
field+0.029
ster+0.027
flower+0.025
Neg logit contributions
 tant-0.022
sc-0.021
 baths-0.021
 videos-0.020
 tests-0.020
Token do
Token ID466
Feature activation+8.03e-03

Pos logit contributions
ich+0.152
opsy+0.131
field+0.130
ster+0.125
sters+0.117
Neg logit contributions
 tant-0.110
 baths-0.105
sc-0.105
 videos-0.100
 tests-0.098
Token you
Token ID345
Feature activation-9.47e-03

Pos logit contributions
ich+0.016
opsy+0.014
field+0.013
ster+0.013
sters+0.012
Neg logit contributions
 tant-0.014
sc-0.013
 baths-0.012
 videos-0.012
 bang-0.012
Token want
Token ID765
Feature activation+7.41e-03

Pos logit contributions
sc+0.008
 baths+0.008
 tant+0.008
 tests+0.008
 around+0.008
Neg logit contributions
ich-0.026
opsy-0.023
field-0.022
ster-0.022
sters-0.021
Token?"
Token ID1701
Feature activation-7.30e-03

Pos logit contributions
ich+0.015
opsy+0.014
field+0.013
ster+0.012
flower+0.011
Neg logit contributions
 tant-0.011
sc-0.011
 baths-0.011
 videos-0.010
 tests-0.010
Token Max
Token ID5436
Feature activation-5.03e-03

Pos logit contributions
 tant+0.007
sc+0.007
igators+0.007
 baths+0.006
igator+0.006
Neg logit contributions
ich-0.018
opsy-0.017
field-0.016
-0.016
ster-0.016
Token.
Token ID13
Feature activation+2.68e-03

Pos logit contributions
ich+0.060
ster+0.051
opsy+0.050
field+0.049
+0.047
Neg logit contributions
 baths-0.050
 videos-0.048
 tests-0.048
 tant-0.047
 bang-0.047
Token He
Token ID679
Feature activation+1.83e-02

Pos logit contributions
ich+0.005
ster+0.004
opsy+0.004
+0.004
field+0.004
Neg logit contributions
 tant-0.005
sc-0.005
 err-0.004
bench-0.004
 baths-0.004
Token escaped
Token ID13537
Feature activation+3.19e-02

Pos logit contributions
ich+0.037
opsy+0.032
field+0.031
ster+0.030
sters+0.028
Neg logit contributions
 tant-0.029
sc-0.028
 baths-0.027
 videos-0.027
 tests-0.026
Token from
Token ID422
Feature activation+5.68e-03

Pos logit contributions
ich+0.063
opsy+0.053
field+0.052
ster+0.050
ese+0.046
Neg logit contributions
 baths-0.047
 tant-0.046
 tests-0.046
sc-0.046
 videos-0.045
Token his
Token ID465
Feature activation+9.66e-03

Pos logit contributions
ich+0.013
opsy+0.011
field+0.011
ster+0.010
ese+0.010
Neg logit contributions
sc-0.008
 tant-0.007
 baths-0.007
taker-0.007
 aids-0.007
Token leash
Token ID40529
Feature activation+7.24e-02

Pos logit contributions
ich+0.018
opsy+0.016
field+0.015
ster+0.015
flower+0.014
Neg logit contributions
 tant-0.016
 baths-0.016
sc-0.016
 videos-0.015
 tests-0.015
Token.
Token ID13
Feature activation+1.64e-03

Pos logit contributions
ich+0.152
opsy+0.132
field+0.129
ster+0.124
sters+0.114
Neg logit contributions
 tant-0.106
 baths-0.104
sc-0.103
 videos-0.100
 tests-0.099
Token He
Token ID679
Feature activation+1.70e-02

Pos logit contributions
ich+0.004
ster+0.003
opsy+0.003
+0.003
field+0.003
Neg logit contributions
 tant-0.002
sc-0.002
 err-0.002
 baths-0.002
igsaw-0.002
Token is
Token ID318
Feature activation+2.44e-03

Pos logit contributions
ich+0.034
opsy+0.030
field+0.029
ster+0.028
sters+0.026
Neg logit contributions
 tant-0.027
sc-0.026
 baths-0.026
 videos-0.025
 tests-0.024
Token usually
Token ID3221
Feature activation+1.90e-02

Pos logit contributions
ich+0.005
opsy+0.004
ster+0.004
anut+0.004
pper+0.004
Neg logit contributions
sc-0.004
 tant-0.004
igsaw-0.004
head-0.004
 baths-0.003
Token friendly
Token ID8030
Feature activation-1.49e-03

Pos logit contributions
ich+0.039
opsy+0.034
field+0.033
ster+0.032
ese+0.031
Neg logit contributions
 tant-0.028
sc-0.026
igsaw-0.025
 aids-0.024
 baths-0.024
Token went
Token ID1816
Feature activation-9.90e-03

Pos logit contributions
sc+0.011
 tant+0.011
 baths+0.011
 videos+0.011
 tests+0.011
Neg logit contributions
ich-0.018
opsy-0.016
field-0.015
ster-0.015
flower-0.014
Token into
Token ID656
Feature activation-4.86e-03

Pos logit contributions
 tant+0.012
sc+0.011
 aids+0.010
igators+0.010
taker+0.010
Neg logit contributions
ich-0.024
field-0.021
opsy-0.021
ster-0.020
 wife-0.018
Token the
Token ID262
Feature activation+1.73e-02

Pos logit contributions
sc+0.006
 tant+0.006
 baths+0.005
igators+0.005
taker+0.005
Neg logit contributions
ich-0.011
opsy-0.010
field-0.010
ster-0.009
sters-0.009
Token woods
Token ID16479
Feature activation+7.38e-03

Pos logit contributions
ich+0.026
opsy+0.021
field+0.020
ster+0.018
flower+0.017
Neg logit contributions
sc-0.039
 tant-0.037
taker-0.036
 baths-0.035
 bang-0.035
Token collecting
Token ID13157
Feature activation+1.33e-02

Pos logit contributions
ich+0.016
field+0.014
opsy+0.014
ster+0.013
flower+0.012
Neg logit contributions
 tant-0.011
 baths-0.010
sc-0.010
 videos-0.010
 bang-0.010
Token berries
Token ID36322
Feature activation+7.24e-02

Pos logit contributions
ich+0.019
opsy+0.018
ster+0.017
sters+0.017
field+0.016
Neg logit contributions
 James-0.024
 aids-0.024
 bang-0.024
 videos-0.023
 crash-0.023
Token and
Token ID290
Feature activation+1.23e-02

Pos logit contributions
ich+0.164
opsy+0.148
field+0.141
ster+0.136
sters+0.127
Neg logit contributions
 tant-0.094
sc-0.093
 baths-0.091
 videos-0.087
 tests-0.087
Token nuts
Token ID14380
Feature activation+4.99e-02

Pos logit contributions
ich+0.022
opsy+0.020
field+0.020
ster+0.018
sters+0.017
Neg logit contributions
 tant-0.022
sc-0.021
 baths-0.020
 videos-0.020
taker-0.020
Token.
Token ID13
Feature activation-1.29e-03

Pos logit contributions
ich+0.117
opsy+0.105
field+0.100
ster+0.096
sters+0.090
Neg logit contributions
sc-0.062
 tant-0.061
 baths-0.060
 tests-0.056
 videos-0.056
Token One
Token ID1881
Feature activation+1.42e-02

Pos logit contributions
 tests+0.001
 baths+0.001
sc+0.001
 videos+0.001
 Everywhere+0.001
Neg logit contributions
ich-0.004
opsy-0.003
ster-0.003
field-0.003
sters-0.003
Token day
Token ID1110
Feature activation-3.21e-02

Pos logit contributions
ich+0.035
opsy+0.032
field+0.030
ster+0.029
sters+0.028
Neg logit contributions
 tant-0.016
sc-0.016
 baths-0.015
 videos-0.015
 tests-0.014
Token Lily
Token ID20037
Feature activation+1.30e-02

Pos logit contributions
ich+0.004
opsy+0.004
field+0.004
ster+0.003
+0.003
Neg logit contributions
 tant-0.001
sc-0.001
 tests-0.001
 baths-0.001
 videos-0.001
Token.
Token ID13
Feature activation+4.15e-04

Pos logit contributions
ich+0.032
opsy+0.030
field+0.029
ster+0.027
sters+0.027
Neg logit contributions
sc-0.013
 tant-0.013
 baths-0.013
 videos-0.013
 around-0.012
Token She
Token ID1375
Feature activation+1.34e-02

Pos logit contributions
opsy+0.001
ich+0.001
flower+0.001
field+0.001
+0.001
Neg logit contributions
 tant-0.001
sc-0.001
 tests-0.001
 baths-0.000
 bang-0.000
Token loved
Token ID6151
Feature activation+3.99e-04

Pos logit contributions
ich+0.028
opsy+0.025
field+0.024
ster+0.023
sters+0.021
Neg logit contributions
sc-0.019
 baths-0.019
 tant-0.019
 videos-0.019
 tests-0.018
Token picking
Token ID10868
Feature activation+2.62e-02

Pos logit contributions
ich+0.001
opsy+0.001
field+0.001
ster+0.001
sters+0.001
Neg logit contributions
sc-0.000
 tant-0.000
taker-0.000
 aids-0.000
igators-0.000
Token berries
Token ID36322
Feature activation+7.12e-02

Pos logit contributions
ich+0.045
opsy+0.040
ster+0.036
field+0.035
sters+0.034
Neg logit contributions
 tant-0.047
sc-0.047
 tests-0.044
 aids-0.044
 bang-0.044
Token in
Token ID287
Feature activation+1.96e-02

Pos logit contributions
ich+0.171
opsy+0.154
field+0.148
ster+0.143
flower+0.134
Neg logit contributions
 tant-0.083
sc-0.082
 baths-0.080
 videos-0.077
 tests-0.076
Token the
Token ID262
Feature activation+3.53e-02

Pos logit contributions
ich+0.049
opsy+0.045
field+0.043
ster+0.041
flower+0.039
Neg logit contributions
sc-0.021
 tant-0.021
 baths-0.019
 tests-0.019
 videos-0.018
Token forest
Token ID8222
Feature activation+3.43e-03

Pos logit contributions
ich+0.067
opsy+0.059
field+0.056
ster+0.053
flower+0.049
Neg logit contributions
 tant-0.060
sc-0.059
 baths-0.058
 videos-0.056
 tests-0.056
Token.
Token ID13
Feature activation+9.38e-04

Pos logit contributions
ich+0.007
opsy+0.007
field+0.007
ster+0.006
flower+0.006
Neg logit contributions
 tant-0.005
 baths-0.005
sc-0.005
 bang-0.005
 videos-0.005
Token One
Token ID1881
Feature activation+1.65e-02

Pos logit contributions
ich+0.003
opsy+0.003
field+0.003
ster+0.002
sters+0.002
Neg logit contributions
 tant-0.001
sc-0.001
 baths-0.001
 videos-0.000
 tests-0.000
Token when
Token ID618
Feature activation+8.75e-03

Pos logit contributions
ich+0.030
field+0.026
opsy+0.026
ster+0.025
flower+0.023
Neg logit contributions
 tant-0.021
 videos-0.019
 baths-0.019
sc-0.019
 tests-0.018
Token they
Token ID484
Feature activation+6.33e-03

Pos logit contributions
ich+0.020
opsy+0.018
field+0.017
ster+0.017
flower+0.016
Neg logit contributions
 tant-0.011
sc-0.011
 baths-0.011
 tests-0.010
 videos-0.010
Token bought
Token ID5839
Feature activation-1.92e-03

Pos logit contributions
ich+0.013
opsy+0.011
field+0.011
ster+0.010
flower+0.009
Neg logit contributions
 tant-0.010
sc-0.010
 baths-0.010
 videos-0.009
 tests-0.009
Token Sunshine
Token ID32210
Feature activation+6.97e-03

Pos logit contributions
sc+0.002
 tant+0.002
 videos+0.002
 bang+0.002
 baths+0.002
Neg logit contributions
ich-0.004
opsy-0.004
field-0.004
ster-0.003
 wife-0.003
Token the
Token ID262
Feature activation-5.60e-03

Pos logit contributions
ich+0.016
opsy+0.014
field+0.014
ster+0.013
sters+0.012
Neg logit contributions
 tant-0.009
sc-0.009
 baths-0.009
 videos-0.008
 tests-0.008
Token leash
Token ID40529
Feature activation+7.08e-02

Pos logit contributions
sc+0.008
 baths+0.008
 tant+0.008
 loud+0.007
 tests+0.007
Neg logit contributions
ich-0.012
opsy-0.011
field-0.010
ster-0.010
sters-0.010
Token.
Token ID13
Feature activation+3.80e-03

Pos logit contributions
ich+0.145
opsy+0.126
field+0.125
ster+0.119
flower+0.110
Neg logit contributions
 tant-0.108
 baths-0.104
sc-0.101
 videos-0.101
 tests-0.100
Token Sunshine
Token ID32210
Feature activation+9.61e-03

Pos logit contributions
ich+0.009
opsy+0.008
field+0.008
ster+0.008
sters+0.007
Neg logit contributions
sc-0.004
 baths-0.004
 tant-0.004
 videos-0.004
 tests-0.004
Token was
Token ID373
Feature activation-2.59e-03

Pos logit contributions
ich+0.022
opsy+0.019
field+0.018
ster+0.017
sters+0.016
Neg logit contributions
sc-0.013
 baths-0.012
 tant-0.012
 tests-0.011
 around-0.011
Token happy
Token ID3772
Feature activation+1.55e-02

Pos logit contributions
sc+0.003
 tant+0.003
 baths+0.003
 videos+0.003
 tests+0.003
Neg logit contributions
ich-0.006
opsy-0.005
field-0.005
ster-0.005
flower-0.005
Token too
Token ID1165
Feature activation+2.55e-02

Pos logit contributions
ich+0.040
opsy+0.036
field+0.035
ster+0.034
sters+0.032
Neg logit contributions
 baths-0.015
 tant-0.015
sc-0.015
 videos-0.014
 tests-0.014
Token home
Token ID1363
Feature activation+3.90e-03

Pos logit contributions
ich+0.019
opsy+0.016
field+0.016
ster+0.015
flower+0.014
Neg logit contributions
 tant-0.013
sc-0.013
 tests-0.012
 bang-0.012
 aids-0.012
Token.
Token ID13
Feature activation-1.87e-04

Pos logit contributions
ich+0.007
field+0.006
opsy+0.006
ster+0.006
flower+0.005
Neg logit contributions
 tant-0.007
sc-0.006
 baths-0.006
 videos-0.006
 bang-0.006
Token She
Token ID1375
Feature activation+8.56e-03

Pos logit contributions
 tant+0.000
sc+0.000
 baths+0.000
 tests+0.000
 bang+0.000
Neg logit contributions
ich-0.000
field-0.000
opsy-0.000
-0.000
ster-0.000
Token put
Token ID1234
Feature activation-3.33e-03

Pos logit contributions
ich+0.016
opsy+0.014
field+0.013
ster+0.013
flower+0.011
Neg logit contributions
 tant-0.015
sc-0.015
 baths-0.014
 videos-0.014
 tests-0.014
Token the
Token ID262
Feature activation-4.36e-03

Pos logit contributions
 villains+0.005
 tant+0.005
sc+0.005
 tests+0.005
 baths+0.004
Neg logit contributions
ich-0.006
opsy-0.005
flower-0.005
field-0.005
ster-0.005
Token leash
Token ID40529
Feature activation+6.97e-02

Pos logit contributions
 tant+0.007
 baths+0.007
sc+0.007
 tests+0.006
 videos+0.006
Neg logit contributions
ich-0.009
opsy-0.008
field-0.008
ster-0.007
sters-0.007
Token back
Token ID736
Feature activation+4.33e-02

Pos logit contributions
ich+0.136
field+0.115
ster+0.113
opsy+0.111
+0.110
Neg logit contributions
 tant-0.105
 baths-0.105
 videos-0.104
 tests-0.101
 bang-0.100
Token on
Token ID319
Feature activation+7.26e-03

Pos logit contributions
ich+0.095
field+0.083
opsy+0.083
ster+0.078
flower+0.074
Neg logit contributions
 tant-0.060
 baths-0.059
 videos-0.057
sc-0.057
 bang-0.057
Token Daisy
Token ID40355
Feature activation+2.51e-02

Pos logit contributions
ich+0.016
opsy+0.015
field+0.015
ster+0.013
flower+0.013
Neg logit contributions
sc-0.009
 tant-0.009
 baths-0.009
 tests-0.008
 bang-0.008
Token and
Token ID290
Feature activation-9.01e-03

Pos logit contributions
ich+0.048
opsy+0.042
field+0.042
ster+0.039
flower+0.036
Neg logit contributions
 tant-0.042
sc-0.040
 tests-0.039
 baths-0.039
 videos-0.039
Token they
Token ID484
Feature activation+1.80e-02

Pos logit contributions
 tant+0.016
sc+0.016
 baths+0.015
 videos+0.015
 tests+0.015
Neg logit contributions
ich-0.016
opsy-0.015
field-0.014
ster-0.013
flower-0.012
Token home
Token ID1363
Feature activation+3.90e-03

Pos logit contributions
ich+0.019
opsy+0.016
field+0.016
ster+0.015
flower+0.014
Neg logit contributions
 tant-0.013
sc-0.013
 tests-0.012
 bang-0.012
 aids-0.012
Token.
Token ID13
Feature activation-1.87e-04

Pos logit contributions
ich+0.007
field+0.006
opsy+0.006
ster+0.006
flower+0.005
Neg logit contributions
 tant-0.007
sc-0.006
 baths-0.006
 videos-0.006
 bang-0.006
Token She
Token ID1375
Feature activation+8.56e-03

Pos logit contributions
 tant+0.000
sc+0.000
 baths+0.000
 tests+0.000
 bang+0.000
Neg logit contributions
ich-0.000
field-0.000
opsy-0.000
-0.000
ster-0.000
Token put
Token ID1234
Feature activation-3.33e-03

Pos logit contributions
ich+0.016
opsy+0.014
field+0.013
ster+0.013
flower+0.011
Neg logit contributions
 tant-0.015
sc-0.015
 baths-0.014
 videos-0.014
 tests-0.014
Token the
Token ID262
Feature activation-4.36e-03

Pos logit contributions
 villains+0.005
 tant+0.005
sc+0.005
 tests+0.005
 baths+0.004
Neg logit contributions
ich-0.006
opsy-0.005
flower-0.005
field-0.005
ster-0.005
Token leash
Token ID40529
Feature activation+6.97e-02

Pos logit contributions
 tant+0.007
 baths+0.007
sc+0.007
 tests+0.006
 videos+0.006
Neg logit contributions
ich-0.009
opsy-0.008
field-0.008
ster-0.007
sters-0.007
Token back
Token ID736
Feature activation+4.33e-02

Pos logit contributions
ich+0.136
field+0.115
ster+0.113
opsy+0.111
+0.110
Neg logit contributions
 tant-0.105
 baths-0.105
 videos-0.104
 tests-0.101
 bang-0.100
Token on
Token ID319
Feature activation+7.26e-03

Pos logit contributions
ich+0.095
field+0.083
opsy+0.083
ster+0.078
flower+0.074
Neg logit contributions
 tant-0.060
 baths-0.059
 videos-0.057
sc-0.057
 bang-0.057
Token Daisy
Token ID40355
Feature activation+2.51e-02

Pos logit contributions
ich+0.016
opsy+0.015
field+0.015
ster+0.013
flower+0.013
Neg logit contributions
sc-0.009
 tant-0.009
 baths-0.009
 tests-0.008
 bang-0.008
Token and
Token ID290
Feature activation-9.01e-03

Pos logit contributions
ich+0.048
opsy+0.042
field+0.042
ster+0.039
flower+0.036
Neg logit contributions
 tant-0.042
sc-0.040
 tests-0.039
 baths-0.039
 videos-0.039
Token they
Token ID484
Feature activation+1.80e-02

Pos logit contributions
 tant+0.016
sc+0.016
 baths+0.015
 videos+0.015
 tests+0.015
Neg logit contributions
ich-0.016
opsy-0.015
field-0.014
ster-0.013
flower-0.012
Token forest
Token ID8222
Feature activation-1.65e-03

Pos logit contributions
ich+0.039
opsy+0.033
field+0.030
ster+0.028
flower+0.026
Neg logit contributions
 tant-0.050
sc-0.050
 tests-0.046
taker-0.046
 baths-0.046
Token where
Token ID810
Feature activation+2.15e-02

Pos logit contributions
 tant+0.002
 baths+0.002
 bang+0.002
sc+0.002
 videos+0.002
Neg logit contributions
ich-0.003
field-0.003
opsy-0.003
ster-0.003
flower-0.003
Token she
Token ID673
Feature activation+9.39e-03

Pos logit contributions
ich+0.037
opsy+0.032
field+0.031
flower+0.028
ster+0.027
Neg logit contributions
sc-0.041
 tant-0.040
 channel-0.036
 bang-0.035
riend-0.035
Token would
Token ID561
Feature activation+1.80e-02

Pos logit contributions
ich+0.019
opsy+0.017
field+0.016
ster+0.016
flower+0.014
Neg logit contributions
 tant-0.014
sc-0.014
 baths-0.014
 videos-0.013
 tests-0.013
Token pick
Token ID2298
Feature activation+4.79e-02

Pos logit contributions
ich+0.037
opsy+0.033
field+0.032
ster+0.030
flower+0.028
Neg logit contributions
 tant-0.027
sc-0.027
 baths-0.026
 videos-0.025
 tests-0.024
Token berries
Token ID36322
Feature activation+6.88e-02

Pos logit contributions
ich+0.075
opsy+0.065
ster+0.058
field+0.058
sters+0.054
Neg logit contributions
 tant-0.095
sc-0.090
 tests-0.089
 videos-0.088
 bang-0.088
Token.
Token ID13
Feature activation+1.10e-03

Pos logit contributions
ich+0.164
opsy+0.148
field+0.141
ster+0.137
flower+0.127
Neg logit contributions
sc-0.082
 tant-0.081
 baths-0.079
 videos-0.075
 tests-0.075
Token One
Token ID1881
Feature activation+1.60e-02

Pos logit contributions
ich+0.003
opsy+0.003
field+0.003
ster+0.003
sters+0.003
Neg logit contributions
sc-0.001
 tant-0.001
 baths-0.001
 videos-0.001
 tests-0.001
Token day
Token ID1110
Feature activation-3.39e-02

Pos logit contributions
ich+0.042
opsy+0.037
field+0.037
ster+0.036
sters+0.035
Neg logit contributions
 baths-0.015
sc-0.015
 tant-0.015
 videos-0.014
 around-0.013
Token,
Token ID11
Feature activation-1.96e-03

Pos logit contributions
 tant+0.041
sc+0.041
 baths+0.040
 videos+0.038
 tests+0.038
Neg logit contributions
ich-0.080
opsy-0.072
field-0.070
ster-0.067
flower-0.062
Token she
Token ID673
Feature activation+9.07e-03

Pos logit contributions
sc+0.002
 tant+0.002
 baths+0.002
 tests+0.002
igators+0.002
Neg logit contributions
ich-0.005
opsy-0.004
field-0.004
ster-0.004
-0.004
Token up
Token ID510
Feature activation+2.31e-02

Pos logit contributions
opsy+0.019
ich+0.018
field+0.017
ige+0.016
ster+0.016
Neg logit contributions
 villains-0.016
sc-0.014
 bang-0.014
 crashes-0.014
 crash-0.014
Token a
Token ID257
Feature activation-1.01e-02

Pos logit contributions
ich+0.049
opsy+0.046
field+0.044
ster+0.041
sters+0.038
Neg logit contributions
sc-0.030
 tant-0.030
 bang-0.029
igators-0.029
 videos-0.028
Token basket
Token ID7988
Feature activation+3.69e-02

Pos logit contributions
 tant+0.013
sc+0.012
 baths+0.012
 tests+0.011
 videos+0.011
Neg logit contributions
ich-0.024
opsy-0.021
field-0.020
ster-0.019
sters-0.018
Token full
Token ID1336
Feature activation-1.79e-02

Pos logit contributions
ich+0.093
opsy+0.085
field+0.082
ster+0.079
flower+0.075
Neg logit contributions
 tant-0.039
sc-0.037
 baths-0.037
 videos-0.035
 tests-0.035
Token of
Token ID286
Feature activation-2.70e-03

Pos logit contributions
 tant+0.013
sc+0.012
 baths+0.012
 videos+0.012
 tests+0.011
Neg logit contributions
ich-0.049
opsy-0.047
field-0.045
ster-0.044
flower-0.042
Token berries
Token ID36322
Feature activation+6.84e-02

Pos logit contributions
sc+0.005
 tant+0.004
 videos+0.004
 baths+0.004
 bang+0.004
Neg logit contributions
ich-0.005
opsy-0.004
field-0.004
ster-0.004
sters-0.004
Token and
Token ID290
Feature activation+2.66e-03

Pos logit contributions
ich+0.154
opsy+0.139
field+0.133
ster+0.128
sters+0.119
Neg logit contributions
 tant-0.090
sc-0.088
 baths-0.087
 videos-0.083
 tests-0.083
Token carried
Token ID5281
Feature activation-3.86e-03

Pos logit contributions
ich+0.005
opsy+0.005
field+0.004
ster+0.004
sters+0.004
Neg logit contributions
 tant-0.004
sc-0.004
 videos-0.004
 tests-0.004
 baths-0.004
Token them
Token ID606
Feature activation-2.89e-03

Pos logit contributions
 tant+0.005
sc+0.005
 videos+0.005
 tests+0.005
igators+0.005
Neg logit contributions
ich-0.008
opsy-0.008
field-0.007
ster-0.007
pper-0.007
Token back
Token ID736
Feature activation+3.43e-02

Pos logit contributions
 tant+0.004
 videos+0.004
sc+0.004
 bang+0.004
 tests+0.004
Neg logit contributions
ich-0.006
opsy-0.006
field-0.005
ster-0.005
flower-0.005
Token to
Token ID284
Feature activation+8.34e-03

Pos logit contributions
ich+0.077
opsy+0.069
field+0.066
ster+0.063
flower+0.059
Neg logit contributions
 tant-0.046
sc-0.045
 baths-0.045
 videos-0.043
 tests-0.043
Token outside
Token ID2354
Feature activation+6.69e-03

Pos logit contributions
 tant+0.008
sc+0.007
 baths+0.007
 videos+0.007
 tests+0.007
Neg logit contributions
ich-0.020
opsy-0.018
field-0.017
ster-0.017
flower-0.016
Token and
Token ID290
Feature activation+1.07e-02

Pos logit contributions
ich+0.013
field+0.012
opsy+0.011
ster+0.011
flower+0.010
Neg logit contributions
 tant-0.010
sc-0.010
 baths-0.010
 videos-0.010
 aids-0.010
Token look
Token ID804
Feature activation+3.54e-03

Pos logit contributions
ich+0.022
field+0.020
opsy+0.020
ster+0.018
flower+0.017
Neg logit contributions
 tant-0.016
sc-0.016
 baths-0.015
 videos-0.015
taker-0.014
Token at
Token ID379
Feature activation+1.17e-02

Pos logit contributions
ich+0.008
opsy+0.007
field+0.007
ster+0.007
flower+0.006
Neg logit contributions
 tant-0.005
sc-0.005
 baths-0.005
 videos-0.004
 tests-0.004
Token the
Token ID262
Feature activation+1.79e-02

Pos logit contributions
ich+0.029
opsy+0.026
field+0.025
ster+0.024
flower+0.022
Neg logit contributions
sc-0.014
 tant-0.013
 baths-0.013
 videos-0.012
 tests-0.012
Token cher
Token ID21382
Feature activation+6.81e-02

Pos logit contributions
ich+0.044
opsy+0.043
field+0.042
ster+0.041
pper+0.040
Neg logit contributions
 loud-0.018
 tant-0.017
 traffic-0.016
 around-0.016
 noise-0.016
Tokenries
Token ID1678
Feature activation+5.98e-02

Pos logit contributions
 wife+0.133
opsy+0.132
ich+0.131
iya+0.125
field+0.122
Neg logit contributions
 around-0.071
 tant-0.070
iren-0.067
chairs-0.066
head-0.065
Token on
Token ID319
Feature activation+8.97e-03

Pos logit contributions
ich+0.149
opsy+0.137
field+0.125
ster+0.123
iya+0.117
Neg logit contributions
sc-0.064
 tant-0.062
 baths-0.061
 tests-0.059
 around-0.058
Token the
Token ID262
Feature activation+6.05e-03

Pos logit contributions
ich+0.022
opsy+0.019
field+0.019
ster+0.018
flower+0.017
Neg logit contributions
sc-0.011
 tant-0.010
 baths-0.010
 videos-0.009
 tests-0.009
Token tree
Token ID5509
Feature activation+5.67e-03

Pos logit contributions
ich+0.014
opsy+0.013
field+0.012
ster+0.012
ipper+0.012
Neg logit contributions
 loud-0.007
 around-0.007
 tant-0.007
sc-0.006
 baths-0.006
Token.
Token ID13
Feature activation-5.40e-04

Pos logit contributions
ich+0.012
field+0.010
opsy+0.010
ster+0.009
flower+0.009
Neg logit contributions
 tant-0.009
 baths-0.009
sc-0.008
 videos-0.008
 tests-0.008
Token of
Token ID286
Feature activation-8.46e-03

Pos logit contributions
 tant+0.019
sc+0.017
 baths+0.016
 tests+0.016
 videos+0.016
Neg logit contributions
ich-0.075
opsy-0.071
field-0.068
ster-0.067
flower-0.063
Token juicy
Token ID35075
Feature activation+4.13e-02

Pos logit contributions
sc+0.016
 tant+0.015
 videos+0.015
 aids+0.015
 bang+0.015
Neg logit contributions
ich-0.013
opsy-0.013
field-0.011
ster-0.010
sters-0.010
Token,
Token ID11
Feature activation+2.05e-02

Pos logit contributions
ich+0.081
opsy+0.070
field+0.067
ster+0.064
flower+0.058
Neg logit contributions
 tant-0.067
sc-0.067
 baths-0.066
 videos-0.063
 tests-0.063
Token tasty
Token ID25103
Feature activation+3.23e-02

Pos logit contributions
ich+0.041
opsy+0.037
field+0.035
ster+0.035
sters+0.032
Neg logit contributions
 tant-0.032
sc-0.030
 tests-0.030
 baths-0.029
 videos-0.029
Token looking
Token ID2045
Feature activation+8.34e-03

Pos logit contributions
ich+0.062
opsy+0.055
field+0.051
ster+0.049
sters+0.045
Neg logit contributions
 tant-0.053
sc-0.053
 baths-0.052
 videos-0.050
 tests-0.050
Token berries
Token ID36322
Feature activation+6.81e-02

Pos logit contributions
ich+0.016
opsy+0.015
ster+0.014
field+0.014
sters+0.013
Neg logit contributions
 tests-0.013
 tant-0.013
 baths-0.012
 videos-0.012
sc-0.012
Token.
Token ID13
Feature activation+4.94e-04

Pos logit contributions
ich+0.157
opsy+0.140
field+0.133
ster+0.128
flower+0.119
Neg logit contributions
sc-0.088
 baths-0.084
 tant-0.084
 videos-0.078
 tests-0.077
Token
Token ID198
Feature activation+1.51e-03

Pos logit contributions
ich+0.001
opsy+0.001
field+0.001
ster+0.001
+0.001
Neg logit contributions
 tant-0.001
sc-0.001
 baths-0.001
 videos-0.001
 tests-0.001
Token
Token ID198
Feature activation+9.95e-03

Pos logit contributions
ich+0.003
opsy+0.003
field+0.003
ster+0.003
flower+0.003
Neg logit contributions
sc-0.002
 tant-0.002
 baths-0.002
 tests-0.002
 videos-0.002
TokenSuddenly
Token ID38582
Feature activation-1.11e-02

Pos logit contributions
ich+0.018
opsy+0.016
field+0.015
ster+0.014
sters+0.013
Neg logit contributions
 tant-0.017
sc-0.017
 baths-0.017
 videos-0.016
 tests-0.016
Token he
Token ID339
Feature activation+8.12e-03

Pos logit contributions
 tant+0.016
sc+0.016
 baths+0.015
 videos+0.015
 tests+0.014
Neg logit contributions
ich-0.024
opsy-0.021
field-0.020
ster-0.020
sters-0.018
Token walk
Token ID2513
Feature activation+1.46e-02

Pos logit contributions
 tant+0.024
sc+0.024
 baths+0.023
 tests+0.022
taker+0.022
Neg logit contributions
ich-0.024
opsy-0.021
field-0.020
ster-0.019
-0.017
Token and
Token ID290
Feature activation+3.34e-03

Pos logit contributions
ich+0.028
field+0.025
opsy+0.023
ster+0.022
flower+0.021
Neg logit contributions
 tant-0.025
 baths-0.024
 bang-0.023
 tests-0.023
 aids-0.022
Token they
Token ID484
Feature activation+1.28e-02

Pos logit contributions
ich+0.006
opsy+0.005
field+0.005
ster+0.005
+0.004
Neg logit contributions
 tant-0.006
sc-0.006
 baths-0.006
 videos-0.006
igsaw-0.006
Token noticed
Token ID6810
Feature activation-2.26e-03

Pos logit contributions
ich+0.031
opsy+0.027
field+0.026
ster+0.026
sters+0.024
Neg logit contributions
sc-0.015
 tant-0.015
 baths-0.015
 around-0.014
 bang-0.014
Token the
Token ID262
Feature activation+1.05e-02

Pos logit contributions
sc+0.003
 tant+0.003
 baths+0.003
 channel+0.003
igsaw+0.003
Neg logit contributions
ich-0.005
opsy-0.004
field-0.004
ster-0.004
sters-0.004
Token leash
Token ID40529
Feature activation+6.78e-02

Pos logit contributions
ich+0.021
opsy+0.019
field+0.018
ster+0.017
flower+0.016
Neg logit contributions
sc-0.017
 tant-0.016
 baths-0.016
 tests-0.015
 videos-0.015
Token was
Token ID373
Feature activation-8.27e-03

Pos logit contributions
ich+0.145
opsy+0.129
field+0.123
ster+0.118
flower+0.109
Neg logit contributions
 tant-0.097
sc-0.096
 baths-0.095
 videos-0.091
 tests-0.090
Token broken
Token ID5445
Feature activation-2.42e-02

Pos logit contributions
 tant+0.013
sc+0.013
igsaw+0.012
 baths+0.012
 tests+0.012
Neg logit contributions
ich-0.017
field-0.014
opsy-0.014
ster-0.012
flower-0.012
Token.
Token ID13
Feature activation-3.60e-03

Pos logit contributions
 tant+0.045
 baths+0.043
sc+0.042
 tests+0.042
 aids+0.042
Neg logit contributions
ich-0.041
field-0.034
opsy-0.033
ster-0.032
flower-0.030
Token The
Token ID383
Feature activation-1.97e-03

Pos logit contributions
 tant+0.005
sc+0.005
 tests+0.004
 baths+0.004
 videos+0.004
Neg logit contributions
ich-0.008
opsy-0.007
field-0.007
-0.007
ster-0.006
Token owner
Token ID4870
Feature activation+2.53e-02

Pos logit contributions
 tant+0.003
 loud+0.003
 baths+0.003
 videos+0.003
sc+0.003
Neg logit contributions
ich-0.004
opsy-0.003
field-0.003
ster-0.003
sters-0.003
Token was
Token ID373
Feature activation-9.58e-03

Pos logit contributions
ich+0.059
opsy+0.052
field+0.050
ster+0.050
flower+0.046
Neg logit contributions
 tant-0.035
 baths-0.034
sc-0.034
 videos-0.033
 tests-0.032
Token able
Token ID1498
Feature activation+3.20e-02

Pos logit contributions
sc+0.015
 tant+0.015
 baths+0.014
 videos+0.014
 tests+0.014
Neg logit contributions
ich-0.020
opsy-0.017
field-0.016
ster-0.016
flower-0.015
Token to
Token ID284
Feature activation+6.03e-03

Pos logit contributions
ich+0.088
opsy+0.080
field+0.077
ster+0.075
sters+0.071
Neg logit contributions
 tant-0.027
sc-0.027
 baths-0.025
 videos-0.024
 tests-0.023
Token restore
Token ID11169
Feature activation-1.66e-02

Pos logit contributions
ich+0.013
opsy+0.012
field+0.011
ster+0.011
pper+0.010
Neg logit contributions
 tant-0.009
sc-0.008
 baths-0.008
igators-0.008
 videos-0.008
Token the
Token ID262
Feature activation+8.92e-03

Pos logit contributions
sc+0.025
 tant+0.024
riend+0.023
igators+0.023
 bang+0.023
Neg logit contributions
ich-0.031
opsy-0.028
field-0.026
ster-0.025
illa-0.023
Token leash
Token ID40529
Feature activation+6.76e-02

Pos logit contributions
ich+0.018
opsy+0.016
field+0.016
ster+0.015
sters+0.014
Neg logit contributions
 tant-0.014
sc-0.014
 baths-0.014
 tests-0.013
 videos-0.013
Token and
Token ID290
Feature activation+4.25e-03

Pos logit contributions
ich+0.131
field+0.115
ster+0.109
opsy+0.107
flower+0.099
Neg logit contributions
 tant-0.108
 baths-0.106
igators-0.099
 tests-0.099
 showers-0.099
Token it
Token ID340
Feature activation-1.27e-02

Pos logit contributions
ich+0.008
field+0.007
opsy+0.007
ster+0.007
 wife+0.007
Neg logit contributions
 tant-0.007
sc-0.007
igsaw-0.006
 aids-0.006
 baths-0.006
Token was
Token ID373
Feature activation-2.25e-03

Pos logit contributions
 tant+0.023
 videos+0.021
igsaw+0.021
sc+0.021
igators+0.021
Neg logit contributions
ich-0.021
field-0.019
opsy-0.019
ster-0.018
flower-0.017
Token as
Token ID355
Feature activation+2.08e-02

Pos logit contributions
sc+0.003
 tant+0.003
 baths+0.003
 tests+0.003
 videos+0.003
Neg logit contributions
ich-0.005
opsy-0.005
field-0.004
ster-0.004
flower-0.004
Token good
Token ID922
Feature activation-1.92e-02

Pos logit contributions
ich+0.041
opsy+0.035
ster+0.035
field+0.033
 husband+0.032
Neg logit contributions
sc-0.030
 tant-0.029
 aids-0.029
aled-0.028
 bang-0.028
Token Jimmy
Token ID12963
Feature activation+9.34e-03

Pos logit contributions
 tant+0.005
sc+0.005
 baths+0.004
 tests+0.004
 videos+0.004
Neg logit contributions
ich-0.008
opsy-0.007
field-0.007
ster-0.007
-0.006
Token grabbed
Token ID13176
Feature activation+1.65e-02

Pos logit contributions
ich+0.021
opsy+0.019
field+0.018
ster+0.017
flower+0.016
Neg logit contributions
sc-0.012
 baths-0.012
 tant-0.012
 videos-0.011
 tests-0.011
Token his
Token ID465
Feature activation-1.48e-02

Pos logit contributions
 wife+0.025
opsy+0.025
 husband+0.024
ich+0.024
ster+0.023
Neg logit contributions
sc-0.026
 villains-0.024
 outage-0.024
|-0.023
storms-0.023
Token dog
Token ID3290
Feature activation+1.74e-02

Pos logit contributions
sc+0.023
 tant+0.023
 baths+0.022
 tests+0.021
 videos+0.021
Neg logit contributions
ich-0.030
opsy-0.026
field-0.025
ster-0.024
sters-0.022
Token's
Token ID338
Feature activation-2.80e-02

Pos logit contributions
ich+0.031
opsy+0.027
ster+0.025
field+0.024
flower+0.022
Neg logit contributions
 tant-0.030
 aids-0.028
igators-0.028
 tests-0.028
taker-0.028
Token leash
Token ID40529
Feature activation+6.76e-02

Pos logit contributions
igators+0.050
 tests+0.049
 tant+0.049
head+0.049
sc+0.049
Neg logit contributions
ich-0.047
opsy-0.039
ster-0.038
field-0.037
-0.033
Token and
Token ID290
Feature activation-1.76e-03

Pos logit contributions
ich+0.124
field+0.105
opsy+0.104
ster+0.102
+0.091
Neg logit contributions
 tant-0.117
 baths-0.114
 tests-0.110
igators-0.109
 videos-0.109
Token started
Token ID2067
Feature activation+5.38e-03

Pos logit contributions
 tant+0.003
 aids+0.003
sc+0.003
igsaw+0.003
 tests+0.003
Neg logit contributions
ich-0.003
opsy-0.003
field-0.003
ster-0.003
sters-0.002
Token marching
Token ID26409
Feature activation-3.41e-02

Pos logit contributions
ich+0.010
opsy+0.008
field+0.008
ster+0.007
+0.007
Neg logit contributions
 tant-0.009
igator-0.009
igators-0.009
sc-0.009
igsaw-0.008
Token with
Token ID351
Feature activation-7.30e-03

Pos logit contributions
 aids+0.058
igators+0.056
igsaw+0.054
 x+0.054
 tant+0.053
Neg logit contributions
ich-0.052
-0.045
ster-0.043
field-0.043
opsy-0.040
Token the
Token ID262
Feature activation-6.90e-03

Pos logit contributions
sc+0.014
auc+0.013
riend+0.012
ro+0.012
|+0.012
Neg logit contributions
ich-0.009
opsy-0.009
 mum-0.009
 husband-0.009
 pearl-0.009
Token that
Token ID326
Feature activation+6.54e-03

Pos logit contributions
 tant+0.002
sc+0.002
 baths+0.001
 bang+0.001
 aids+0.001
Neg logit contributions
ich-0.004
opsy-0.004
field-0.004
ster-0.003
sters-0.003
Token Max
Token ID5436
Feature activation+1.25e-02

Pos logit contributions
ich+0.010
field+0.009
ster+0.008
opsy+0.008
+0.008
Neg logit contributions
 tant-0.012
sc-0.011
igsaw-0.011
riend-0.011
igators-0.010
Token understood
Token ID7247
Feature activation+1.77e-02

Pos logit contributions
ich+0.026
opsy+0.023
field+0.022
ster+0.021
sters+0.019
Neg logit contributions
 tant-0.019
sc-0.019
 baths-0.018
 videos-0.018
 tests-0.018
Token what
Token ID644
Feature activation+2.49e-02

Pos logit contributions
ich+0.038
opsy+0.034
field+0.033
ster+0.032
sters+0.029
Neg logit contributions
sc-0.025
 tant-0.024
 baths-0.023
 videos-0.022
igators-0.022
Token the
Token ID262
Feature activation+7.97e-03

Pos logit contributions
ich+0.053
opsy+0.046
ster+0.045
field+0.045
 wife+0.042
Neg logit contributions
 tant-0.036
sc-0.034
aled-0.029
head-0.029
 bang-0.029
Token leash
Token ID40529
Feature activation+6.76e-02

Pos logit contributions
ich+0.014
opsy+0.012
field+0.012
ster+0.011
sters+0.010
Neg logit contributions
 tant-0.014
sc-0.014
 baths-0.014
 videos-0.014
 tests-0.013
Token was
Token ID373
Feature activation+1.28e-02

Pos logit contributions
ich+0.133
opsy+0.115
field+0.113
ster+0.108
flower+0.100
Neg logit contributions
 tant-0.109
 baths-0.104
sc-0.104
 videos-0.102
 tests-0.099
Token for
Token ID329
Feature activation-1.38e-02

Pos logit contributions
ich+0.029
opsy+0.026
field+0.025
ster+0.024
sters+0.023
Neg logit contributions
 tant-0.016
sc-0.016
 baths-0.016
 videos-0.015
 tests-0.015
Token and
Token ID290
Feature activation-1.51e-02

Pos logit contributions
 tant+0.019
sc+0.019
 baths+0.017
igators+0.016
 tests+0.016
Neg logit contributions
ich-0.031
opsy-0.027
field-0.026
ster-0.026
sters-0.024
Token enjoyed
Token ID8359
Feature activation+1.01e-02

Pos logit contributions
sc+0.025
 tant+0.024
igsaw+0.022
 x+0.022
 channel+0.021
Neg logit contributions
ich-0.028
field-0.024
opsy-0.024
ster-0.024
 wife-0.022
Token it
Token ID340
Feature activation-2.06e-02

Pos logit contributions
ich+0.024
opsy+0.021
field+0.021
ster+0.020
sters+0.018
Neg logit contributions
 tant-0.013
sc-0.013
 baths-0.011
igators-0.011
 videos-0.011
Token helped
Token ID4193
Feature activation-6.80e-03

Pos logit contributions
ich+0.075
opsy+0.069
field+0.066
ster+0.064
ese+0.060
Neg logit contributions
 tant-0.033
sc-0.032
 baths-0.030
 videos-0.030
 tests-0.029
Token someone
Token ID2130
Feature activation-3.04e-02

Pos logit contributions
 tant+0.010
sc+0.010
igators+0.009
igsaw+0.009
taker+0.009
Neg logit contributions
ich-0.014
opsy-0.013
field-0.012
ster-0.012
 wife-0.011
Token find
Token ID1064
Feature activation+6.46e-03

Pos logit contributions
 tant+0.039
sc+0.038
 baths+0.037
 videos+0.036
 tests+0.035
Neg logit contributions
ich-0.070
opsy-0.063
field-0.061
ster-0.059
sters-0.055
Token their
Token ID511
Feature activation+3.06e-03

Pos logit contributions
ich+0.014
opsy+0.013
ster+0.012
field+0.012
ese+0.011
Neg logit contributions
 tant-0.008
sc-0.008
 bang-0.008
 baths-0.008
 videos-0.008
Token lost
Token ID2626
Feature activation+7.73e-03

Pos logit contributions
ich+0.006
opsy+0.006
field+0.005
ster+0.005
sters+0.005
Neg logit contributions
 tant-0.005
 baths-0.005
sc-0.004
 tests-0.004
 videos-0.004
Token pet
Token ID4273
Feature activation+6.73e-02

Pos logit contributions
ich+0.015
opsy+0.013
field+0.012
ster+0.012
flower+0.011
Neg logit contributions
sc-0.013
 tant-0.013
 baths-0.012
 tests-0.012
 videos-0.012
Token.
Token ID13
Feature activation+1.28e-03

Pos logit contributions
ich+0.150
opsy+0.135
field+0.128
ster+0.123
sters+0.115
Neg logit contributions
sc-0.090
 tant-0.089
 baths-0.087
 videos-0.084
 tests-0.083
Token She
Token ID1375
Feature activation+1.27e-02

Pos logit contributions
ich+0.003
opsy+0.003
field+0.003
ster+0.003
sters+0.003
Neg logit contributions
sc-0.001
 tant-0.001
 baths-0.001
 videos-0.001
 tests-0.001
Token knew
Token ID2993
Feature activation+1.01e-02

Pos logit contributions
ich+0.030
opsy+0.025
field+0.024
sters+0.023
ese+0.023
Neg logit contributions
 baths-0.015
 Lily-0.015
 around-0.014
sc-0.014
 bang-0.014
Token that
Token ID326
Feature activation+3.22e-03

Pos logit contributions
ich+0.024
opsy+0.021
field+0.020
ster+0.020
sters+0.018
Neg logit contributions
sc-0.014
 tant-0.014
 bang-0.012
 videos-0.012
 baths-0.012
Token being
Token ID852
Feature activation-6.82e-04

Pos logit contributions
ich+0.006
opsy+0.006
field+0.005
ster+0.005
flower+0.005
Neg logit contributions
 tant-0.005
sc-0.005
igsaw-0.005
aled-0.005
 bang-0.004
Token
Token ID198
Feature activation-8.11e-03

Pos logit contributions
sc+0.003
 baths+0.003
 tant+0.003
 tests+0.003
igators+0.003
Neg logit contributions
ich-0.004
opsy-0.004
field-0.004
ster-0.003
-0.003
Token
Token ID198
Feature activation-7.07e-04

Pos logit contributions
sc+0.010
 tant+0.010
 baths+0.009
 videos+0.009
 tests+0.009
Neg logit contributions
ich-0.019
opsy-0.017
field-0.017
ster-0.016
flower-0.015
Token"
Token ID1
Feature activation+1.88e-02

Pos logit contributions
sc+0.001
 tant+0.001
 baths+0.001
 videos+0.001
 tests+0.001
Neg logit contributions
ich-0.001
opsy-0.001
field-0.001
ster-0.001
flower-0.001
TokenWhat
Token ID2061
Feature activation+3.24e-02

Pos logit contributions
ich+0.038
opsy+0.034
field+0.032
ster+0.031
sters+0.028
Neg logit contributions
sc-0.029
 tant-0.029
 baths-0.028
 videos-0.027
 tests-0.027
Token are
Token ID389
Feature activation+2.49e-02

Pos logit contributions
ich+0.078
opsy+0.071
field+0.069
ster+0.064
flower+0.061
Neg logit contributions
 videos-0.038
 baths-0.037
sc-0.037
 tests-0.037
 tant-0.036
Token peanuts
Token ID45612
Feature activation+6.73e-02

Pos logit contributions
ich+0.059
opsy+0.054
field+0.051
ster+0.049
flower+0.048
Neg logit contributions
 baths-0.030
sc-0.030
 videos-0.028
 tests-0.028
 tant-0.027
Token?"
Token ID1701
Feature activation-3.86e-03

Pos logit contributions
ich+0.117
opsy+0.102
field+0.095
ster+0.090
flower+0.082
Neg logit contributions
sc-0.122
 tant-0.121
 baths-0.120
 videos-0.116
 tests-0.116
Token Lily
Token ID20037
Feature activation-3.20e-03

Pos logit contributions
sc+0.006
 baths+0.006
 tant+0.006
igators+0.005
nob+0.005
Neg logit contributions
ich-0.007
opsy-0.007
field-0.006
 wife-0.006
-0.006
Token asked
Token ID1965
Feature activation-1.03e-02

Pos logit contributions
 tant+0.003
 baths+0.003
sc+0.003
 videos+0.003
 tests+0.003
Neg logit contributions
ich-0.008
opsy-0.007
field-0.007
ster-0.007
flower-0.006
Token.
Token ID13
Feature activation-1.18e-02

Pos logit contributions
sc+0.015
 tant+0.015
 baths+0.014
 videos+0.013
 tests+0.013
Neg logit contributions
ich-0.022
opsy-0.020
field-0.019
ster-0.018
sters-0.017
Token
Token ID198
Feature activation-7.86e-03

Pos logit contributions
sc+0.019
 tant+0.018
 baths+0.018
igators+0.018
 videos+0.017
Neg logit contributions
ich-0.024
opsy-0.020
field-0.019
-0.019
ster-0.018
Token to
Token ID284
Feature activation-4.26e-03

Pos logit contributions
ich+0.026
opsy+0.023
field+0.022
ster+0.021
sters+0.020
Neg logit contributions
 tant-0.014
sc-0.014
 baths-0.013
 videos-0.013
 tests-0.013
Token get
Token ID651
Feature activation+1.73e-02

Pos logit contributions
 tant+0.006
sc+0.006
 videos+0.006
 baths+0.006
 tests+0.006
Neg logit contributions
ich-0.009
opsy-0.008
field-0.008
ster-0.007
pper-0.007
Token his
Token ID465
Feature activation+2.14e-03

Pos logit contributions
ich+0.035
opsy+0.032
field+0.029
 wife+0.029
ster+0.028
Neg logit contributions
sc-0.026
 tant-0.025
igsaw-0.025
 aids-0.023
 bang-0.023
Token pet
Token ID4273
Feature activation+5.68e-02

Pos logit contributions
ich+0.004
opsy+0.003
field+0.003
ster+0.003
sters+0.003
Neg logit contributions
 tant-0.004
 baths-0.004
sc-0.004
 tests-0.003
 videos-0.003
Token's
Token ID338
Feature activation-1.77e-02

Pos logit contributions
ich+0.121
opsy+0.108
field+0.103
ster+0.099
sters+0.092
Neg logit contributions
 tant-0.081
sc-0.081
 baths-0.079
 videos-0.076
 tests-0.075
Token leash
Token ID40529
Feature activation+6.73e-02

Pos logit contributions
 tant+0.031
sc+0.031
 baths+0.030
 videos+0.029
 tests+0.029
Neg logit contributions
ich-0.032
opsy-0.028
field-0.027
ster-0.025
flower-0.023
Token.
Token ID13
Feature activation-2.91e-03

Pos logit contributions
ich+0.141
opsy+0.123
field+0.121
ster+0.116
flower+0.106
Neg logit contributions
 tant-0.100
 baths-0.097
sc-0.095
 tests-0.093
 videos-0.093
Token It
Token ID632
Feature activation-1.85e-02

Pos logit contributions
 tant+0.003
sc+0.003
 baths+0.003
 videos+0.002
 tests+0.002
Neg logit contributions
ich-0.007
opsy-0.007
field-0.007
ster-0.006
-0.006
Token was
Token ID373
Feature activation-8.07e-03

Pos logit contributions
igsaw+0.038
 videos+0.037
 tant+0.037
 baths+0.036
 tests+0.035
Neg logit contributions
ich-0.026
field-0.023
opsy-0.023
flower-0.021
ster-0.020
Token purple
Token ID14032
Feature activation-1.36e-02

Pos logit contributions
sc+0.012
 tant+0.012
igsaw+0.012
and+0.011
head+0.011
Neg logit contributions
ich-0.015
opsy-0.013
field-0.013
pper-0.011
 remembered-0.011
Token,
Token ID11
Feature activation+1.12e-02

Pos logit contributions
 tant+0.025
sc+0.024
 aids+0.023
 videos+0.023
 tests+0.023
Neg logit contributions
ich-0.024
opsy-0.020
ster-0.019
field-0.019
flower-0.018
Token<|endoftext|>
Token ID50256
Feature activation+1.17e-03

Pos logit contributions
ich+0.003
opsy+0.002
field+0.002
ster+0.002
flower+0.002
Neg logit contributions
 tant-0.001
sc-0.001
 baths-0.001
 videos-0.001
 tests-0.001
TokenL
Token ID43
Feature activation-5.16e-02

Pos logit contributions
ich+0.002
opsy+0.002
field+0.001
ster+0.001
sters+0.001
Neg logit contributions
sc-0.002
 tant-0.002
 baths-0.002
 videos-0.002
 tests-0.002
Tokenily
Token ID813
Feature activation+7.52e-03

Pos logit contributions
 tant+0.058
sc+0.058
 baths+0.057
 videos+0.056
 tests+0.055
Neg logit contributions
ich-0.127
opsy-0.112
field-0.112
ster-0.103
flower-0.100
Token loved
Token ID6151
Feature activation+2.34e-03

Pos logit contributions
ich+0.016
opsy+0.015
field+0.014
ster+0.013
sters+0.012
Neg logit contributions
 tant-0.010
sc-0.010
 baths-0.010
 videos-0.010
 tests-0.010
Token pe
Token ID613
Feature activation+2.27e-02

Pos logit contributions
ich+0.005
opsy+0.005
field+0.005
ster+0.004
sters+0.004
Neg logit contributions
sc-0.003
 tant-0.003
taker-0.003
 aids-0.003
 tests-0.003
Tokenaches
Token ID3694
Feature activation+6.72e-02

Pos logit contributions
ich+0.036
opsy+0.031
field+0.030
ster+0.027
flower+0.025
Neg logit contributions
 tant-0.044
 baths-0.043
sc-0.043
 tests-0.042
 videos-0.041
Token.
Token ID13
Feature activation+6.84e-03

Pos logit contributions
ich+0.163
opsy+0.146
field+0.139
ster+0.134
sters+0.126
Neg logit contributions
 tant-0.075
sc-0.075
 baths-0.074
 videos-0.070
 around-0.068
Token She
Token ID1375
Feature activation+1.44e-02

Pos logit contributions
opsy+0.012
ich+0.012
flower+0.012
+0.012
field+0.011
Neg logit contributions
 tant-0.010
sc-0.009
 tests-0.009
 crashes-0.009
 bang-0.009
Token liked
Token ID8288
Feature activation-2.19e-03

Pos logit contributions
ich+0.033
opsy+0.028
field+0.027
ster+0.026
sters+0.025
Neg logit contributions
sc-0.019
 baths-0.019
 tant-0.018
 tests-0.018
 bang-0.017
Token to
Token ID284
Feature activation+1.69e-02

Pos logit contributions
sc+0.003
 tant+0.003
 baths+0.002
 videos+0.002
 tests+0.002
Neg logit contributions
ich-0.005
opsy-0.005
field-0.005
ster-0.004
sters-0.004
Token eat
Token ID4483
Feature activation+3.06e-02

Pos logit contributions
ich+0.033
opsy+0.031
field+0.030
ster+0.028
flower+0.027
Neg logit contributions
sc-0.026
 tant-0.026
 baths-0.024
 videos-0.023
 tests-0.023
Token was
Token ID373
Feature activation-9.43e-03

Pos logit contributions
ich+0.008
opsy+0.007
field+0.007
ster+0.007
flower+0.006
Neg logit contributions
 tant-0.007
sc-0.007
 baths-0.007
 videos-0.007
 tests-0.007
Token relieved
Token ID22598
Feature activation+1.29e-02

Pos logit contributions
sc+0.015
 tant+0.014
 baths+0.013
 videos+0.013
igsaw+0.013
Neg logit contributions
ich-0.020
opsy-0.018
field-0.017
ster-0.016
 husband-0.015
Token and
Token ID290
Feature activation-5.38e-03

Pos logit contributions
ich+0.025
opsy+0.022
field+0.021
ster+0.021
+0.018
Neg logit contributions
 tant-0.021
sc-0.021
igators-0.020
 baths-0.020
 videos-0.020
Token she
Token ID673
Feature activation+1.46e-02

Pos logit contributions
 tant+0.010
sc+0.010
 baths+0.009
 videos+0.009
 tests+0.009
Neg logit contributions
ich-0.009
opsy-0.008
field-0.008
ster-0.007
-0.007
Token filled
Token ID5901
Feature activation-2.66e-02

Pos logit contributions
ich+0.032
opsy+0.028
field+0.026
ster+0.025
sters+0.024
Neg logit contributions
sc-0.020
 tant-0.020
 baths-0.020
 bang-0.019
 tests-0.019
Token Fl
Token ID1610
Feature activation+6.71e-02

Pos logit contributions
 tant+0.037
sc+0.037
igators+0.035
igsaw+0.035
riend+0.034
Neg logit contributions
ich-0.055
opsy-0.052
field-0.048
ster-0.046
illa-0.046
Tokenuffy
Token ID15352
Feature activation+2.78e-02

Pos logit contributions
ich+0.097
field+0.084
opsy+0.080
ster+0.077
sters+0.069
Neg logit contributions
 tant-0.131
 baths-0.129
sc-0.129
 tests-0.125
 videos-0.121
Token's
Token ID338
Feature activation-4.42e-03

Pos logit contributions
ich+0.054
opsy+0.050
field+0.047
ster+0.047
sters+0.042
Neg logit contributions
 tant-0.043
sc-0.042
igators-0.041
 videos-0.040
 tests-0.039
Token bowl
Token ID9396
Feature activation+1.62e-02

Pos logit contributions
sc+0.008
 tant+0.007
igators+0.007
 tests+0.007
 videos+0.007
Neg logit contributions
ich-0.008
opsy-0.007
field-0.007
ster-0.007
-0.006
Token with
Token ID351
Feature activation-1.06e-03

Pos logit contributions
ich+0.035
opsy+0.033
ster+0.031
field+0.031
flower+0.029
Neg logit contributions
 videos-0.021
 tant-0.021
 tests-0.021
 bang-0.021
sc-0.021
Token medicine
Token ID9007
Feature activation+1.57e-02

Pos logit contributions
sc+0.001
igsaw+0.001
igators+0.001
 videos+0.001
 tant+0.001
Neg logit contributions
opsy-0.002
ich-0.002
field-0.002
ster-0.002
 wife-0.002
Token watched
Token ID7342
Feature activation-8.93e-03

Pos logit contributions
sc+0.005
 tant+0.005
 baths+0.005
 tests+0.005
 videos+0.005
Neg logit contributions
ich-0.009
opsy-0.008
field-0.008
ster-0.007
sters-0.007
Token as
Token ID355
Feature activation+1.92e-02

Pos logit contributions
sc+0.015
 tant+0.014
igators+0.013
riend+0.013
bench+0.013
Neg logit contributions
ich-0.015
opsy-0.014
ble-0.013
ster-0.012
field-0.012
Token her
Token ID607
Feature activation-1.80e-02

Pos logit contributions
ich+0.046
opsy+0.042
field+0.038
ster+0.037
flower+0.035
Neg logit contributions
sc-0.025
 tant-0.022
 baths-0.020
 aids-0.019
 tests-0.019
Token mom
Token ID1995
Feature activation-9.56e-03

Pos logit contributions
sc+0.036
 tant+0.035
 baths+0.034
 videos+0.033
 tests+0.033
Neg logit contributions
ich-0.029
opsy-0.025
field-0.022
ster-0.022
flower-0.020
Token carefully
Token ID7773
Feature activation-2.59e-02

Pos logit contributions
 tant+0.012
sc+0.012
 baths+0.011
 videos+0.011
 tests+0.011
Neg logit contributions
ich-0.022
opsy-0.020
field-0.019
ster-0.018
sters-0.017
Token se
Token ID384
Feature activation-1.07e-01

Pos logit contributions
 tant+0.039
igators+0.038
sc+0.038
 baths+0.038
 videos+0.038
Neg logit contributions
ich-0.050
opsy-0.046
field-0.043
ster-0.043
flower-0.039
Tokenwed
Token ID19103
Feature activation+1.96e-02

Pos logit contributions
 baths+0.196
 videos+0.189
 tests+0.188
sc+0.188
 TV+0.183
Neg logit contributions
ich-0.162
opsy-0.154
ese-0.135
pper-0.135
ster-0.132
Token Ted
Token ID11396
Feature activation-1.87e-02

Pos logit contributions
ich+0.031
opsy+0.031
ster+0.027
flower+0.026
ble+0.026
Neg logit contributions
 aids-0.033
 villains-0.032
igators-0.030
riend-0.030
 Lots-0.029
Token's
Token ID338
Feature activation-2.07e-02

Pos logit contributions
 videos+0.034
igators+0.034
 tant+0.034
iren+0.032
 showers+0.032
Neg logit contributions
ich-0.027
ster-0.025
opsy-0.025
field-0.023
flower-0.023
Token arm
Token ID3211
Feature activation-9.74e-03

Pos logit contributions
igators+0.029
sc+0.029
 videos+0.028
 tant+0.028
 baths+0.028
Neg logit contributions
ich-0.044
opsy-0.040
ster-0.037
field-0.037
flower-0.034
Token back
Token ID736
Feature activation+4.20e-02

Pos logit contributions
igators+0.022
 aids+0.020
igator+0.020
 videos+0.019
 villains+0.019
Neg logit contributions
ich-0.009
ster-0.008
field-0.007
flower-0.007
opsy-0.007
Token Joe
Token ID5689
Feature activation-1.34e-02

Pos logit contributions
sc+0.014
 tant+0.014
 tests+0.014
igators+0.013
 baths+0.013
Neg logit contributions
ich-0.021
opsy-0.020
ster-0.018
field-0.018
-0.017
Token,
Token ID11
Feature activation-5.22e-03

Pos logit contributions
 tant+0.020
sc+0.020
 baths+0.019
 videos+0.019
 tests+0.019
Neg logit contributions
ich-0.027
opsy-0.024
field-0.023
ster-0.023
flower-0.021
Token a
Token ID257
Feature activation-1.54e-02

Pos logit contributions
 tant+0.007
sc+0.007
 baths+0.007
 tests+0.007
 videos+0.007
Neg logit contributions
ich-0.011
opsy-0.010
field-0.010
ster-0.009
flower-0.009
Token 3
Token ID513
Feature activation-6.74e-02

Pos logit contributions
sc+0.020
 baths+0.020
 tant+0.019
 videos+0.019
 tests+0.019
Neg logit contributions
ich-0.035
opsy-0.031
field-0.030
ster-0.029
-0.027
Token-
Token ID12
Feature activation-8.55e-02

Pos logit contributions
 baths+0.097
sc+0.095
 videos+0.094
 tests+0.090
igsaw+0.088
Neg logit contributions
ich-0.135
opsy-0.120
ster-0.113
field-0.113
ese-0.107
Tokenyear
Token ID1941
Feature activation-1.06e-01

Pos logit contributions
 baths+0.117
 videos+0.112
 TV+0.101
 tant+0.100
 tests+0.099
Neg logit contributions
ich-0.191
opsy-0.167
illa-0.159
ster-0.158
pper-0.154
Token-
Token ID12
Feature activation-7.41e-02

Pos logit contributions
sc+0.193
 videos+0.188
 baths+0.181
 Math+0.178
 Emma+0.176
Neg logit contributions
ich-0.186
ster-0.159
opsy-0.158
field-0.143
 wife-0.141
Tokenold
Token ID727
Feature activation-9.08e-03

Pos logit contributions
 baths+0.117
 videos+0.113
 tant+0.113
 bang+0.106
 TV+0.105
Neg logit contributions
ich-0.151
opsy-0.128
ster-0.122
illa-0.120
field-0.118
Token boy
Token ID2933
Feature activation-9.77e-03

Pos logit contributions
 tant+0.017
sc+0.017
 baths+0.017
 videos+0.016
 tests+0.016
Neg logit contributions
ich-0.015
opsy-0.013
ster-0.012
field-0.012
flower-0.011
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
 tant+0.016
sc+0.015
 baths+0.015
 videos+0.015
 tests+0.014
Neg logit contributions
ich-0.020
opsy-0.017
field-0.017
ster-0.016
flower-0.015
Token He
Token ID679
Feature activation+4.86e-03

Pos logit contributions
 tant+0.013
sc+0.013
 baths+0.013
 videos+0.012
 tests+0.012
Neg logit contributions
ich-0.025
opsy-0.022
field-0.021
ster-0.020
flower-0.019
Token twenty
Token ID8208
Feature activation-5.54e-02

Pos logit contributions
sc+0.025
 tant+0.023
 baths+0.022
 videos+0.021
 tests+0.020
Neg logit contributions
ich-0.040
opsy-0.037
field-0.035
ster-0.033
-0.033
Token-
Token ID12
Feature activation-1.03e-01

Pos logit contributions
 tant+0.082
sc+0.081
 baths+0.079
 tests+0.077
 videos+0.076
Neg logit contributions
ich-0.117
opsy-0.103
field-0.099
ster-0.094
flower-0.087
Tokeneight
Token ID26022
Feature activation-2.25e-02

Pos logit contributions
 baths+0.155
 videos+0.146
sc+0.145
 tant+0.143
 showers+0.136
Neg logit contributions
ich-0.207
opsy-0.182
illa-0.171
field-0.165
ster-0.164
Token,
Token ID11
Feature activation-2.77e-02

Pos logit contributions
 tant+0.030
sc+0.030
 baths+0.029
 videos+0.028
 tests+0.027
Neg logit contributions
ich-0.050
opsy-0.045
field-0.043
ster-0.041
sters-0.039
Token twenty
Token ID8208
Feature activation-5.87e-02

Pos logit contributions
sc+0.039
 tant+0.036
 baths+0.035
 videos+0.032
igators+0.032
Neg logit contributions
ich-0.061
opsy-0.056
field-0.053
ster-0.051
-0.050
Token-
Token ID12
Feature activation-1.06e-01

Pos logit contributions
sc+0.084
 baths+0.083
 tant+0.083
 videos+0.080
 tests+0.075
Neg logit contributions
ich-0.123
opsy-0.111
field-0.104
ster-0.101
sters-0.094
Tokennine
Token ID30888
Feature activation-3.95e-02

Pos logit contributions
 baths+0.175
 videos+0.167
 tant+0.163
sc+0.163
 showers+0.155
Neg logit contributions
ich-0.194
opsy-0.169
illa-0.161
field-0.153
ster-0.148
Token,
Token ID11
Feature activation-3.16e-02

Pos logit contributions
 tant+0.053
sc+0.052
 baths+0.051
 videos+0.049
 tests+0.049
Neg logit contributions
ich-0.087
opsy-0.079
field-0.075
ster-0.072
sters-0.067
Token thirty
Token ID12277
Feature activation-4.99e-02

Pos logit contributions
sc+0.045
 tant+0.042
 baths+0.041
 videos+0.037
igators+0.037
Neg logit contributions
ich-0.070
opsy-0.063
field-0.060
ster-0.058
-0.057
Token,
Token ID11
Feature activation-3.38e-02

Pos logit contributions
sc+0.069
 baths+0.067
 tant+0.067
 videos+0.065
 tests+0.061
Neg logit contributions
ich-0.108
opsy-0.098
field-0.092
ster-0.090
sters-0.085
Token thirty
Token ID12277
Feature activation-4.92e-02

Pos logit contributions
sc+0.048
 tant+0.045
 baths+0.044
igators+0.040
 videos+0.040
Neg logit contributions
ich-0.075
opsy-0.067
field-0.064
ster-0.062
-0.061
Tokennine
Token ID30888
Feature activation-3.95e-02

Pos logit contributions
 baths+0.175
 videos+0.167
 tant+0.163
sc+0.163
 showers+0.155
Neg logit contributions
ich-0.194
opsy-0.169
illa-0.161
field-0.153
ster-0.148
Token,
Token ID11
Feature activation-3.16e-02

Pos logit contributions
 tant+0.053
sc+0.052
 baths+0.051
 videos+0.049
 tests+0.049
Neg logit contributions
ich-0.087
opsy-0.079
field-0.075
ster-0.072
sters-0.067
Token thirty
Token ID12277
Feature activation-4.99e-02

Pos logit contributions
sc+0.045
 tant+0.042
 baths+0.041
 videos+0.037
igators+0.037
Neg logit contributions
ich-0.070
opsy-0.063
field-0.060
ster-0.058
-0.057
Token,
Token ID11
Feature activation-3.38e-02

Pos logit contributions
sc+0.069
 baths+0.067
 tant+0.067
 videos+0.065
 tests+0.061
Neg logit contributions
ich-0.108
opsy-0.098
field-0.092
ster-0.090
sters-0.085
Token thirty
Token ID12277
Feature activation-4.92e-02

Pos logit contributions
sc+0.048
 tant+0.045
 baths+0.044
igators+0.040
 videos+0.040
Neg logit contributions
ich-0.075
opsy-0.067
field-0.064
ster-0.062
-0.061
Token-
Token ID12
Feature activation-1.05e-01

Pos logit contributions
sc+0.067
 baths+0.066
 tant+0.066
 videos+0.063
 tests+0.059
Neg logit contributions
ich-0.107
opsy-0.097
field-0.091
ster-0.089
sters-0.084
Tokenone
Token ID505
Feature activation-3.18e-02

Pos logit contributions
 baths+0.181
 videos+0.173
 tant+0.170
sc+0.168
 showers+0.161
Neg logit contributions
ich-0.182
opsy-0.156
illa-0.149
field-0.144
pper-0.139
Token,
Token ID11
Feature activation-3.49e-02

Pos logit contributions
sc+0.053
 baths+0.052
 tant+0.051
 videos+0.050
 showers+0.047
Neg logit contributions
ich-0.059
opsy-0.052
field-0.050
ster-0.048
flower-0.044
Token thirty
Token ID12277
Feature activation-4.80e-02

Pos logit contributions
sc+0.050
 tant+0.047
 baths+0.045
igators+0.041
 videos+0.041
Neg logit contributions
ich-0.077
opsy-0.069
field-0.065
ster-0.064
-0.063
Token-
Token ID12
Feature activation-1.01e-01

Pos logit contributions
sc+0.064
 baths+0.063
 tant+0.063
 videos+0.060
 tests+0.057
Neg logit contributions
ich-0.106
opsy-0.096
field-0.091
ster-0.089
sters-0.083
Tokentwo
Token ID11545
Feature activation-3.71e-02

Pos logit contributions
 baths+0.173
 videos+0.167
 tant+0.165
sc+0.162
 showers+0.155
Neg logit contributions
ich-0.180
opsy-0.153
illa-0.146
field-0.142
pper-0.136
Token!"
Token ID2474
Feature activation+3.82e-03

Pos logit contributions
 baths+0.033
sc+0.033
 tant+0.032
 videos+0.032
 tests+0.031
Neg logit contributions
ich-0.060
opsy-0.054
field-0.051
ster-0.048
iri-0.046
Token shouted
Token ID17293
Feature activation-8.49e-03

Pos logit contributions
ich+0.007
opsy+0.006
field+0.006
ster+0.006
sters+0.005
Neg logit contributions
sc-0.007
 tant-0.007
 baths-0.006
 tests-0.006
 videos-0.006
Token her
Token ID607
Feature activation-1.42e-02

Pos logit contributions
sc+0.014
 tant+0.013
igators+0.012
 videos+0.012
 tests+0.012
Neg logit contributions
ich-0.017
opsy-0.016
field-0.014
ster-0.014
flower-0.013
Token three
Token ID1115
Feature activation-6.23e-02

Pos logit contributions
 tant+0.025
sc+0.025
 baths+0.025
 videos+0.024
 tests+0.024
Neg logit contributions
ich-0.025
opsy-0.022
field-0.021
ster-0.020
sters-0.018
Token-
Token ID12
Feature activation-8.18e-02

Pos logit contributions
sc+0.094
 baths+0.085
 videos+0.082
 tant+0.082
 tests+0.082
Neg logit contributions
ich-0.126
opsy-0.118
ster-0.108
field-0.104
sters-0.101
Tokenyear
Token ID1941
Feature activation-1.04e-01

Pos logit contributions
 baths+0.098
 videos+0.098
 tant+0.093
 TV+0.087
 bang+0.087
Neg logit contributions
ich-0.190
opsy-0.176
illa-0.165
ster-0.165
field-0.157
Token-
Token ID12
Feature activation-7.14e-02

Pos logit contributions
sc+0.186
 videos+0.166
 bang+0.166
 baths+0.164
 tests+0.160
Neg logit contributions
ich-0.193
opsy-0.175
ster-0.171
ama-0.154
field-0.153
Tokenold
Token ID727
Feature activation-8.90e-03

Pos logit contributions
 tant+0.104
 videos+0.102
 baths+0.102
sc+0.101
 bang+0.100
Neg logit contributions
ich-0.148
opsy-0.136
ster-0.128
illa-0.123
field-0.120
Token son
Token ID3367
Feature activation-8.31e-03

Pos logit contributions
sc+0.020
 tant+0.020
 baths+0.019
 tests+0.019
 videos+0.019
Neg logit contributions
ich-0.011
opsy-0.009
ster-0.009
field-0.008
flower-0.007
Token,
Token ID11
Feature activation-2.57e-03

Pos logit contributions
 tant+0.014
sc+0.014
 baths+0.013
 tests+0.013
 videos+0.012
Neg logit contributions
ich-0.016
opsy-0.014
ster-0.013
field-0.013
flower-0.012
Token happy
Token ID3772
Feature activation+9.74e-03

Pos logit contributions
sc+0.004
 tant+0.004
 baths+0.004
 videos+0.003
 tests+0.003
Neg logit contributions
ich-0.006
opsy-0.005
field-0.005
ster-0.004
flower-0.004
Token watched
Token ID7342
Feature activation-8.52e-03

Pos logit contributions
 tant+0.021
sc+0.021
 baths+0.021
 tests+0.020
 videos+0.020
Neg logit contributions
ich-0.031
opsy-0.028
field-0.026
ster-0.025
sters-0.023
Token as
Token ID355
Feature activation+1.86e-02

Pos logit contributions
sc+0.018
igators+0.017
 tant+0.015
bench+0.015
|+0.015
Neg logit contributions
ich-0.012
ble-0.011
opsy-0.010
ster-0.009
icking-0.008
Token his
Token ID465
Feature activation-1.25e-02

Pos logit contributions
ich+0.044
opsy+0.041
field+0.037
ster+0.036
ble+0.036
Neg logit contributions
sc-0.025
 tant-0.021
 baths-0.020
 channel-0.019
igators-0.019
Token mom
Token ID1995
Feature activation-1.22e-02

Pos logit contributions
sc+0.027
 tant+0.025
igators+0.025
 baths+0.024
 videos+0.024
Neg logit contributions
ich-0.020
opsy-0.017
ster-0.015
field-0.015
flower-0.013
Token carefully
Token ID7773
Feature activation-2.51e-02

Pos logit contributions
 tant+0.019
sc+0.018
 baths+0.018
 videos+0.017
 tests+0.017
Neg logit contributions
ich-0.025
opsy-0.022
field-0.021
ster-0.020
flower-0.019
Token se
Token ID384
Feature activation-1.04e-01

Pos logit contributions
igators+0.043
 videos+0.041
 tant+0.041
sc+0.040
igsaw+0.039
Neg logit contributions
ich-0.042
opsy-0.040
field-0.039
ster-0.037
flower-0.034
Tokenwed
Token ID19103
Feature activation+1.70e-02

Pos logit contributions
 baths+0.189
 videos+0.182
 TV+0.179
 tests+0.179
sc+0.177
Neg logit contributions
ich-0.153
opsy-0.148
ese-0.137
pper-0.133
ige-0.127
Token the
Token ID262
Feature activation-3.19e-03

Pos logit contributions
ich+0.027
opsy+0.026
ble+0.024
ster+0.024
flower+0.023
Neg logit contributions
 aids-0.028
 villains-0.028
igators-0.027
 Lots-0.026
 videos-0.025
Token stitch
Token ID24695
Feature activation-1.30e-02

Pos logit contributions
sc+0.005
 videos+0.005
 aids+0.005
igators+0.005
 tant+0.005
Neg logit contributions
ich-0.006
ster-0.005
opsy-0.005
field-0.005
sters-0.005
Token in
Token ID287
Feature activation+9.87e-04

Pos logit contributions
 Many+0.022
 tant+0.022
 aids+0.022
 videos+0.022
 tests+0.021
Neg logit contributions
ich-0.021
field-0.019
ster-0.019
opsy-0.018
flower-0.018
Token the
Token ID262
Feature activation+1.68e-02

Pos logit contributions
ich+0.002
field+0.002
opsy+0.002
flower+0.002
ster+0.002
Neg logit contributions
sc-0.001
igators-0.001
 baths-0.001
 tests-0.001
 videos-0.001
Token place
Token ID1295
Feature activation-6.93e-03

Pos logit contributions
ich+0.045
opsy+0.039
ster+0.038
field+0.036
flower+0.034
Neg logit contributions
sc-0.033
 tant-0.032
aled-0.030
 baths-0.029
 Everywhere-0.029
Token for
Token ID329
Feature activation-1.67e-02

Pos logit contributions
 tant+0.012
 baths+0.011
sc+0.011
 videos+0.011
 tests+0.010
Neg logit contributions
ich-0.013
field-0.011
opsy-0.011
ster-0.010
flower-0.010
Token a
Token ID257
Feature activation-3.17e-02

Pos logit contributions
sc+0.027
 tant+0.026
taker+0.021
riend+0.021
bench+0.021
Neg logit contributions
ich-0.035
opsy-0.032
field-0.030
ster-0.028
sters-0.027
Token 3
Token ID513
Feature activation-7.26e-02

Pos logit contributions
aled+0.040
sc+0.038
 videos+0.038
 tant+0.037
igators+0.036
Neg logit contributions
ich-0.071
opsy-0.064
field-0.061
ster-0.059
 wife-0.054
Token-
Token ID12
Feature activation-8.25e-02

Pos logit contributions
sc+0.118
aled+0.117
 Everywhere+0.116
 backward+0.115
 videos+0.115
Neg logit contributions
ich-0.118
opsy-0.104
ster-0.098
ese-0.095
field-0.091
Tokenyear
Token ID1941
Feature activation-1.03e-01

Pos logit contributions
 baths+0.119
 videos+0.118
 channel+0.111
 TV+0.110
 cartoons+0.109
Neg logit contributions
ich-0.168
opsy-0.142
ster-0.139
illa-0.135
pper-0.128
Token-
Token ID12
Feature activation-7.09e-02

Pos logit contributions
sc+0.200
 videos+0.192
 Emma+0.186
 Math+0.184
|+0.183
Neg logit contributions
ich-0.169
ster-0.145
opsy-0.136
field-0.124
ama-0.123
Tokenold
Token ID727
Feature activation-9.94e-03

Pos logit contributions
 videos+0.116
 baths+0.113
 bang+0.110
 channel+0.110
 tant+0.109
Neg logit contributions
ich-0.134
opsy-0.111
ster-0.108
illa-0.104
ese-0.100
Token to
Token ID284
Feature activation+3.63e-03

Pos logit contributions
 tant+0.017
sc+0.016
 baths+0.016
 videos+0.015
 tests+0.015
Neg logit contributions
ich-0.018
opsy-0.015
ster-0.015
field-0.015
flower-0.013
Token be
Token ID307
Feature activation+2.25e-02

Pos logit contributions
ich+0.007
opsy+0.007
field+0.007
ster+0.006
pper+0.005
Neg logit contributions
sc-0.006
 tant-0.006
 videos-0.005
 baths-0.005
taker-0.005
Token."
Token ID526
Feature activation+1.03e-02

Pos logit contributions
ich+0.046
opsy+0.040
field+0.038
ster+0.037
ese+0.036
Neg logit contributions
sc-0.034
 tant-0.033
 videos-0.031
 baths-0.031
igsaw-0.031
Token the
Token ID262
Feature activation-1.72e-02

Pos logit contributions
 outage+0.023
bench+0.022
riend+0.022
 villains+0.022
 gru+0.022
Neg logit contributions
opsy-0.016
 husband-0.014
ich-0.013
 daughter-0.013
ige-0.013
Token t
Token ID256
Feature activation-8.77e-03

Pos logit contributions
sc+0.024
 videos+0.024
 aids+0.023
 tests+0.023
igators+0.023
Neg logit contributions
ich-0.037
opsy-0.032
ster-0.031
field-0.030
flower-0.029
Tokeneddy
Token ID21874
Feature activation-2.01e-02

Pos logit contributions
 tant+0.014
sc+0.014
 baths+0.013
 videos+0.013
 tests+0.013
Neg logit contributions
ich-0.017
opsy-0.015
field-0.015
ster-0.014
sters-0.013
Token bear
Token ID6842
Feature activation-4.69e-03

Pos logit contributions
 tant+0.026
sc+0.025
 baths+0.025
 videos+0.024
 tests+0.024
Neg logit contributions
ich-0.046
opsy-0.042
field-0.040
ster-0.038
sters-0.036
Token and
Token ID290
Feature activation-7.97e-03

Pos logit contributions
 tant+0.007
sc+0.006
 baths+0.006
 tests+0.006
 videos+0.006
Neg logit contributions
ich-0.010
opsy-0.009
ster-0.009
field-0.009
flower-0.008
Token se
Token ID384
Feature activation-1.03e-01

Pos logit contributions
 tant+0.012
sc+0.012
 baths+0.011
 aids+0.011
 tests+0.011
Neg logit contributions
ich-0.016
opsy-0.015
field-0.014
ster-0.014
sters-0.012
Tokenwed
Token ID19103
Feature activation+1.63e-02

Pos logit contributions
 baths+0.196
 tests+0.192
 videos+0.189
sc+0.189
 TV+0.183
Neg logit contributions
ich-0.146
opsy-0.138
ese-0.119
ster-0.117
pper-0.115
Token up
Token ID510
Feature activation+1.75e-02

Pos logit contributions
ich+0.024
opsy+0.022
ster+0.019
ble+0.018
field+0.018
Neg logit contributions
 aids-0.030
igators-0.030
riend-0.028
 villains-0.028
 videos-0.028
Token the
Token ID262
Feature activation-3.81e-03

Pos logit contributions
ich+0.026
opsy+0.026
field+0.022
ster+0.022
 husband+0.021
Neg logit contributions
sc-0.029
igators-0.027
bench-0.027
riend-0.026
igator-0.026
Token hole
Token ID7604
Feature activation-3.68e-03

Pos logit contributions
sc+0.005
 videos+0.005
 tant+0.005
 tests+0.004
 baths+0.004
Neg logit contributions
ich-0.009
opsy-0.008
field-0.007
ster-0.007
flower-0.007
Token in
Token ID287
Feature activation+8.76e-03

Pos logit contributions
 baths+0.007
 tant+0.007
 tests+0.007
 bang+0.007
 showers+0.007
Neg logit contributions
ich-0.005
ster-0.005
field-0.005
opsy-0.005
flower-0.005
Token out
Token ID503
Feature activation-1.95e-02

Pos logit contributions
sc+0.047
 tant+0.043
 channels+0.037
 videos+0.036
igators+0.035
Neg logit contributions
ich-0.086
opsy-0.082
field-0.077
ster-0.073
illa-0.073
Token a
Token ID257
Feature activation-7.52e-03

Pos logit contributions
sc+0.033
 tant+0.029
 tests+0.027
igators+0.027
 baths+0.026
Neg logit contributions
ich-0.035
-0.031
opsy-0.031
ster-0.030
flower-0.029
Token young
Token ID1862
Feature activation-1.67e-02

Pos logit contributions
sc+0.012
aled+0.012
igators+0.011
 baths+0.011
 tant+0.011
Neg logit contributions
ich-0.015
opsy-0.013
ster-0.013
field-0.013
-0.012
Token three
Token ID1115
Feature activation-5.34e-02

Pos logit contributions
sc+0.034
 tant+0.033
 baths+0.032
 tests+0.032
aled+0.032
Neg logit contributions
ich-0.027
opsy-0.023
ster-0.022
field-0.021
flower-0.019
Token-
Token ID12
Feature activation-7.61e-02

Pos logit contributions
sc+0.083
 baths+0.077
aled+0.074
 tests+0.073
 videos+0.073
Neg logit contributions
ich-0.107
opsy-0.096
ster-0.091
field-0.086
-0.083
Tokenyear
Token ID1941
Feature activation-1.03e-01

Pos logit contributions
 baths+0.107
 videos+0.095
 showers+0.092
 tant+0.091
 TV+0.089
Neg logit contributions
ich-0.172
illa-0.147
opsy-0.146
ster-0.144
flower-0.134
Token-
Token ID12
Feature activation-6.84e-02

Pos logit contributions
sc+0.186
 baths+0.167
 videos+0.166
 bang+0.164
 Chloe+0.159
Neg logit contributions
ich-0.192
ster-0.165
opsy-0.165
 wife-0.146
field-0.145
Tokenold
Token ID727
Feature activation-5.29e-03

Pos logit contributions
 baths+0.113
 tant+0.107
 videos+0.105
 bang+0.104
 showers+0.102
Neg logit contributions
ich-0.137
opsy-0.114
ster-0.111
illa-0.111
field-0.104
Token girl
Token ID2576
Feature activation-1.77e-02

Pos logit contributions
sc+0.010
 tant+0.010
 baths+0.010
 tests+0.010
 videos+0.010
Neg logit contributions
ich-0.008
opsy-0.007
ster-0.007
field-0.007
flower-0.006
Token in
Token ID287
Feature activation-8.16e-03

Pos logit contributions
 tant+0.029
sc+0.028
 baths+0.027
 tests+0.026
 videos+0.026
Neg logit contributions
ich-0.036
opsy-0.032
field-0.030
ster-0.029
flower-0.028
Token excitement
Token ID14067
Feature activation-1.79e-02

Pos logit contributions
sc+0.017
auc+0.016
taker+0.015
igators+0.015
riend+0.014
Neg logit contributions
ich-0.010
opsy-0.010
field-0.009
 wife-0.009
iya-0.009
Token,
Token ID11
Feature activation-1.46e-03

Pos logit contributions
 tant+0.050
sc+0.048
 videos+0.045
 baths+0.044
 tests+0.044
Neg logit contributions
ich-0.057
opsy-0.052
field-0.048
ster-0.048
-0.045
Token a
Token ID257
Feature activation-8.28e-03

Pos logit contributions
 tant+0.002
sc+0.002
 baths+0.001
 tests+0.001
 videos+0.001
Neg logit contributions
ich-0.004
opsy-0.003
field-0.003
ster-0.003
flower-0.003
Token tiny
Token ID7009
Feature activation-2.48e-02

Pos logit contributions
sc+0.011
 tant+0.011
 baths+0.011
igators+0.010
 tests+0.010
Neg logit contributions
ich-0.019
opsy-0.017
field-0.016
ster-0.016
-0.015
Token three
Token ID1115
Feature activation-5.42e-02

Pos logit contributions
sc+0.050
aled+0.048
 baths+0.046
 tant+0.046
 tests+0.045
Neg logit contributions
ich-0.040
opsy-0.037
ster-0.034
field-0.032
flower-0.030
Token-
Token ID12
Feature activation-8.54e-02

Pos logit contributions
sc+0.087
aled+0.079
 backward+0.079
 baths+0.078
 videos+0.076
Neg logit contributions
ich-0.101
opsy-0.097
ster-0.088
sters-0.082
field-0.082
Tokenyear
Token ID1941
Feature activation-1.02e-01

Pos logit contributions
 baths+0.117
 tant+0.106
 videos+0.105
 showers+0.100
sc+0.099
Neg logit contributions
ich-0.194
opsy-0.169
illa-0.165
ster-0.163
flower-0.156
Token-
Token ID12
Feature activation-7.22e-02

Pos logit contributions
sc+0.184
 videos+0.166
 baths+0.166
 bang+0.164
 tant+0.163
Neg logit contributions
ich-0.194
opsy-0.166
ster-0.165
field-0.152
ama-0.147
Tokenold
Token ID727
Feature activation-6.41e-03

Pos logit contributions
 tant+0.113
 baths+0.112
sc+0.108
 videos+0.106
 bang+0.105
Neg logit contributions
ich-0.150
opsy-0.128
ster-0.122
illa-0.120
field-0.119
Token girl
Token ID2576
Feature activation-1.62e-02

Pos logit contributions
 tant+0.011
sc+0.011
 baths+0.011
 videos+0.011
 tests+0.011
Neg logit contributions
ich-0.012
opsy-0.010
field-0.009
ster-0.009
flower-0.008
Token came
Token ID1625
Feature activation-1.15e-02

Pos logit contributions
 tant+0.027
sc+0.025
 baths+0.025
 videos+0.024
 tests+0.024
Neg logit contributions
ich-0.032
opsy-0.029
field-0.027
ster-0.026
flower-0.024
Token across
Token ID1973
Feature activation+2.74e-03

Pos logit contributions
 tant+0.012
sc+0.011
 baths+0.011
 videos+0.010
 tests+0.010
Neg logit contributions
ich-0.030
opsy-0.027
field-0.026
ster-0.025
flower-0.025
Token needle
Token ID17598
Feature activation-2.93e-02

Pos logit contributions
 aids+0.010
 tant+0.010
sc+0.010
|+0.010
igators+0.010
Neg logit contributions
opsy-0.015
ich-0.014
field-0.013
ster-0.013
flower-0.012
Token and
Token ID290
Feature activation+4.41e-05

Pos logit contributions
 tant+0.054
 videos+0.052
 tests+0.052
 aids+0.051
igators+0.050
Neg logit contributions
ich-0.049
ster-0.044
opsy-0.041
field-0.040
flower-0.040
Token thread
Token ID4704
Feature activation-2.25e-02

Pos logit contributions
ich+0.000
opsy+0.000
field+0.000
ster+0.000
flower+0.000
Neg logit contributions
 tant-0.000
sc-0.000
 aids-0.000
 channel-0.000
igators-0.000
Token and
Token ID290
Feature activation-6.63e-03

Pos logit contributions
 videos+0.035
 tant+0.034
 tests+0.034
 aids+0.033
igators+0.032
Neg logit contributions
ich-0.043
opsy-0.038
ster-0.037
field-0.036
flower-0.035
Token carefully
Token ID7773
Feature activation-1.56e-02

Pos logit contributions
 tant+0.011
sc+0.011
igsaw+0.010
 aids+0.010
 channel+0.010
Neg logit contributions
ich-0.011
opsy-0.011
field-0.010
ster-0.010
 wife-0.009
Token se
Token ID384
Feature activation-1.02e-01

Pos logit contributions
 tant+0.028
igators+0.026
 videos+0.026
sc+0.026
 baths+0.025
Neg logit contributions
ich-0.026
opsy-0.024
field-0.024
ster-0.023
sters-0.021
Tokenwed
Token ID19103
Feature activation+2.03e-02

Pos logit contributions
 baths+0.192
 videos+0.188
sc+0.186
 tests+0.184
 TV+0.183
Neg logit contributions
ich-0.145
opsy-0.137
ese-0.122
pper-0.118
ster-0.116
Token the
Token ID262
Feature activation-3.43e-03

Pos logit contributions
ich+0.038
opsy+0.036
ster+0.033
field+0.032
ble+0.031
Neg logit contributions
 aids-0.030
igators-0.029
 videos-0.028
 tant-0.028
 villains-0.028
Token hole
Token ID7604
Feature activation-4.43e-04

Pos logit contributions
 tant+0.005
sc+0.005
igators+0.005
 videos+0.005
 baths+0.004
Neg logit contributions
ich-0.007
opsy-0.007
field-0.006
ster-0.006
flower-0.006
Token shut
Token ID4423
Feature activation+1.48e-03

Pos logit contributions
 baths+0.001
 tests+0.001
 videos+0.001
 tant+0.001
 bang+0.001
Neg logit contributions
ich-0.001
ster-0.001
field-0.001
opsy-0.001
flower-0.001
Token.
Token ID13
Feature activation+6.45e-04

Pos logit contributions
ich+0.003
opsy+0.002
field+0.002
ster+0.002
+0.002
Neg logit contributions
sc-0.002
igators-0.002
 bang-0.002
 videos-0.002
 tests-0.002
Token Billy
Token ID15890
Feature activation-5.96e-03

Pos logit contributions
 tant+0.012
sc+0.012
 baths+0.012
 tests+0.011
 videos+0.011
Neg logit contributions
ich-0.024
opsy-0.022
field-0.021
ster-0.020
flower-0.019
Token,
Token ID11
Feature activation-1.60e-03

Pos logit contributions
 tant+0.009
sc+0.009
 baths+0.008
 tests+0.008
 videos+0.008
Neg logit contributions
ich-0.013
opsy-0.011
field-0.011
ster-0.011
flower-0.010
Token a
Token ID257
Feature activation-1.36e-02

Pos logit contributions
sc+0.002
 tant+0.002
 baths+0.002
 tests+0.002
 videos+0.002
Neg logit contributions
ich-0.003
opsy-0.003
field-0.003
ster-0.003
flower-0.003
Token three
Token ID1115
Feature activation-5.72e-02

Pos logit contributions
sc+0.018
 baths+0.017
 tant+0.017
 tests+0.017
 videos+0.017
Neg logit contributions
ich-0.031
opsy-0.028
field-0.027
ster-0.026
-0.024
Token-
Token ID12
Feature activation-8.53e-02

Pos logit contributions
sc+0.088
 baths+0.082
aled+0.080
 videos+0.080
 tests+0.079
Neg logit contributions
ich-0.113
opsy-0.106
ster-0.097
field-0.094
flower-0.089
Tokenyear
Token ID1941
Feature activation-1.02e-01

Pos logit contributions
 baths+0.132
 videos+0.121
 TV+0.114
 showers+0.114
 tests+0.112
Neg logit contributions
ich-0.169
opsy-0.148
illa-0.147
ster-0.141
flower-0.135
Token-
Token ID12
Feature activation-7.41e-02

Pos logit contributions
sc+0.186
 videos+0.166
 baths+0.164
 Chloe+0.162
 tests+0.162
Neg logit contributions
ich-0.185
opsy-0.168
ster-0.165
 wife-0.149
ama-0.146
Tokenold
Token ID727
Feature activation-6.01e-03

Pos logit contributions
 baths+0.121
 videos+0.115
 bang+0.114
 tant+0.113
sc+0.110
Neg logit contributions
ich-0.143
opsy-0.124
illa-0.119
ster-0.118
 wife-0.111
Token boy
Token ID2933
Feature activation-1.08e-02

Pos logit contributions
sc+0.012
 tant+0.012
 baths+0.012
 tests+0.011
 videos+0.011
Neg logit contributions
ich-0.010
opsy-0.008
ster-0.008
field-0.007
flower-0.007
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
 tant+0.018
sc+0.017
 baths+0.017
 tests+0.016
 videos+0.016
Neg logit contributions
ich-0.022
opsy-0.019
field-0.018
ster-0.018
flower-0.017
Token
Token ID198
Feature activation-1.59e-02

Pos logit contributions
 tant+0.019
sc+0.018
 baths+0.018
 tests+0.017
 videos+0.016
Neg logit contributions
ich-0.035
opsy-0.031
field-0.030
ster-0.029
-0.028
Token,
Token ID11
Feature activation-5.31e-03

Pos logit contributions
 tant+0.054
sc+0.053
 videos+0.049
 baths+0.049
 tests+0.049
Neg logit contributions
ich-0.060
opsy-0.054
field-0.051
ster-0.050
-0.047
Token a
Token ID257
Feature activation-1.34e-02

Pos logit contributions
sc+0.006
 tant+0.006
 baths+0.006
 tests+0.005
 aids+0.005
Neg logit contributions
ich-0.013
opsy-0.011
field-0.011
ster-0.011
-0.010
Token little
Token ID1310
Feature activation-3.99e-03

Pos logit contributions
sc+0.019
 tant+0.018
 baths+0.018
aled+0.017
igators+0.017
Neg logit contributions
ich-0.030
opsy-0.026
ster-0.025
field-0.024
-0.023
Token 3
Token ID513
Feature activation-5.98e-02

Pos logit contributions
aled+0.009
sc+0.009
 tant+0.009
 baths+0.008
nob+0.008
Neg logit contributions
ich-0.006
opsy-0.004
ster-0.004
flower-0.004
field-0.004
Token-
Token ID12
Feature activation-8.44e-02

Pos logit contributions
sc+0.090
 baths+0.085
 videos+0.082
igsaw+0.081
 backward+0.081
Neg logit contributions
ich-0.121
opsy-0.105
ster-0.101
field-0.096
ese-0.093
Tokenyear
Token ID1941
Feature activation-1.02e-01

Pos logit contributions
 baths+0.121
 videos+0.108
 tant+0.108
 showers+0.104
sc+0.103
Neg logit contributions
ich-0.185
illa-0.160
ster-0.158
opsy-0.158
pper-0.144
Token-
Token ID12
Feature activation-7.43e-02

Pos logit contributions
sc+0.183
 baths+0.161
 videos+0.161
 bang+0.159
 tant+0.158
Neg logit contributions
ich-0.196
ster-0.166
opsy-0.166
 wife-0.150
ama-0.147
Tokenold
Token ID727
Feature activation-5.75e-03

Pos logit contributions
 baths+0.121
 tant+0.119
sc+0.116
 videos+0.114
 bang+0.113
Neg logit contributions
ich-0.147
opsy-0.124
ster-0.122
illa-0.120
field-0.113
Token boy
Token ID2933
Feature activation-7.99e-03

Pos logit contributions
 tant+0.010
sc+0.010
 baths+0.009
 videos+0.009
 tests+0.009
Neg logit contributions
ich-0.011
opsy-0.009
field-0.009
ster-0.009
flower-0.008
Token named
Token ID3706
Feature activation-8.94e-03

Pos logit contributions
 tant+0.012
sc+0.011
 baths+0.011
 videos+0.011
 tests+0.010
Neg logit contributions
ich-0.017
opsy-0.015
field-0.015
ster-0.014
flower-0.013
Token Tim
Token ID5045
Feature activation+1.22e-02

Pos logit contributions
 tant+0.013
sc+0.013
 baths+0.011
 videos+0.011
 aids+0.011
Neg logit contributions
ich-0.019
opsy-0.016
ster-0.016
illa-0.016
field-0.015
Token of
Token ID286
Feature activation-3.12e-02

Pos logit contributions
 tant+0.014
sc+0.013
igsaw+0.013
 tests+0.013
 baths+0.013
Neg logit contributions
ich-0.017
opsy-0.014
ster-0.014
field-0.013
flower-0.012
Token waves
Token ID9813
Feature activation-4.15e-03

Pos logit contributions
sc+0.043
chair+0.040
 aids+0.038
 tant+0.038
nob+0.038
Neg logit contributions
ich-0.063
opsy-0.056
field-0.055
ster-0.052
 wife-0.051
Token and
Token ID290
Feature activation-2.70e-03

Pos logit contributions
 tant+0.007
 tests+0.007
sc+0.007
 baths+0.007
igators+0.007
Neg logit contributions
ich-0.007
ster-0.006
opsy-0.006
field-0.006
flower-0.006
Token wind
Token ID2344
Feature activation-2.38e-02

Pos logit contributions
 tant+0.005
sc+0.004
igsaw+0.004
 x+0.004
 If+0.004
Neg logit contributions
ich-0.004
field-0.004
ster-0.004
sters-0.004
 wife-0.004
Token and
Token ID290
Feature activation+7.66e-04

Pos logit contributions
 tant+0.037
sc+0.037
 baths+0.036
 tests+0.035
 videos+0.034
Neg logit contributions
ich-0.049
opsy-0.042
field-0.041
ster-0.040
flower-0.037
Token se
Token ID384
Feature activation-1.02e-01

Pos logit contributions
ich+0.001
field+0.001
ster+0.001
 wife+0.001
sters+0.001
Neg logit contributions
sc-0.001
igsaw-0.001
 tant-0.001
 Everywhere-0.001
 aback-0.001
Tokenag
Token ID363
Feature activation-3.09e-03

Pos logit contributions
 baths+0.171
 tests+0.166
sc+0.166
 videos+0.164
igsaw+0.163
Neg logit contributions
ich-0.165
opsy-0.151
ese-0.146
pper-0.135
ster-0.132
Tokenull
Token ID724
Feature activation-3.17e-02

Pos logit contributions
 tant+0.005
sc+0.005
 baths+0.005
 videos+0.004
 tests+0.004
Neg logit contributions
ich-0.006
opsy-0.006
field-0.005
ster-0.005
sters-0.005
Tokens
Token ID82
Feature activation-5.47e-03

Pos logit contributions
 tant+0.061
sc+0.060
 tests+0.059
 baths+0.059
 videos+0.058
Neg logit contributions
ich-0.052
opsy-0.044
field-0.041
ster-0.040
sters-0.036
Token.
Token ID13
Feature activation-8.21e-03

Pos logit contributions
 tant+0.008
sc+0.008
 baths+0.008
 tests+0.008
 videos+0.007
Neg logit contributions
ich-0.011
opsy-0.010
field-0.010
ster-0.009
flower-0.009
Token
Token ID198
Feature activation-1.49e-02

Pos logit contributions
 tant+0.010
sc+0.010
 baths+0.010
 videos+0.010
 tests+0.009
Neg logit contributions
ich-0.019
opsy-0.017
field-0.016
ster-0.016
flower-0.015
Token and
Token ID290
Feature activation-3.03e-02

Pos logit contributions
sc+0.117
 tant+0.107
 baths+0.107
 tests+0.104
 bang+0.103
Neg logit contributions
ich-0.119
opsy-0.103
ster-0.094
field-0.091
sters-0.090
Token like
Token ID588
Feature activation-6.50e-03

Pos logit contributions
 tant+0.056
sc+0.056
 baths+0.050
 tests+0.049
 bang+0.048
Neg logit contributions
ich-0.056
opsy-0.049
field-0.047
ster-0.045
-0.041
Token all
Token ID477
Feature activation-2.72e-03

Pos logit contributions
sc+0.010
 tant+0.009
 aids+0.008
igators+0.008
aled+0.008
Neg logit contributions
ich-0.015
opsy-0.013
field-0.012
ster-0.012
 wife-0.011
Token three
Token ID1115
Feature activation-6.35e-02

Pos logit contributions
sc+0.004
 tant+0.004
 bang+0.004
driver+0.004
ro+0.004
Neg logit contributions
ich-0.005
field-0.004
flower-0.004
opsy-0.004
ster-0.004
Token-
Token ID12
Feature activation-7.63e-02

Pos logit contributions
sc+0.109
 tant+0.100
 baths+0.096
 tests+0.096
 bang+0.095
Neg logit contributions
ich-0.115
opsy-0.101
sters-0.092
ster-0.091
field-0.090
Tokenyear
Token ID1941
Feature activation-1.02e-01

Pos logit contributions
 tant+0.121
sc+0.120
 baths+0.115
 bang+0.113
 TV+0.113
Neg logit contributions
ich-0.148
opsy-0.124
anut-0.118
illa-0.117
ll-0.113
Token-
Token ID12
Feature activation-6.91e-02

Pos logit contributions
sc+0.173
 bang+0.157
 tant+0.148
 James+0.148
 Emma+0.147
Neg logit contributions
ich-0.202
opsy-0.173
ster-0.164
sters-0.162
 wife-0.155
Tokenolds
Token ID10119
Feature activation+1.87e-02

Pos logit contributions
sc+0.109
 tant+0.109
 bang+0.106
 TV+0.100
 baths+0.100
Neg logit contributions
ich-0.135
opsy-0.112
anut-0.106
ese-0.106
ll-0.105
Token,
Token ID11
Feature activation+4.39e-03

Pos logit contributions
ich+0.034
opsy+0.029
sters+0.028
ster+0.028
field+0.027
Neg logit contributions
sc-0.032
 tant-0.031
igsaw-0.029
 bang-0.028
 baths-0.028
Token he
Token ID339
Feature activation+2.58e-03

Pos logit contributions
ich+0.008
opsy+0.007
field+0.007
ster+0.006
 wife+0.006
Neg logit contributions
sc-0.008
 tant-0.008
aled-0.007
igsaw-0.007
 baths-0.007
Token was
Token ID373
Feature activation-1.74e-02

Pos logit contributions
ich+0.005
opsy+0.005
field+0.004
ster+0.004
flower+0.004
Neg logit contributions
 tant-0.004
sc-0.004
 baths-0.004
 videos-0.004
 tests-0.004
Tokenizzy
Token ID40593
Feature activation-1.86e-02

Pos logit contributions
 tant+0.027
 baths+0.026
sc+0.026
 videos+0.026
 tests+0.026
Neg logit contributions
ich-0.034
opsy-0.030
field-0.028
ster-0.027
flower-0.025
Token was
Token ID373
Feature activation-1.28e-02

Pos logit contributions
sc+0.030
 tant+0.030
 baths+0.029
 videos+0.028
 tests+0.027
Neg logit contributions
ich-0.036
opsy-0.032
field-0.031
ster-0.029
sters-0.027
Token a
Token ID257
Feature activation-8.10e-03

Pos logit contributions
sc+0.022
 tant+0.020
head+0.019
igsaw+0.019
 videos+0.018
Neg logit contributions
ich-0.026
opsy-0.024
field-0.021
ster-0.020
ble-0.019
Token three
Token ID1115
Feature activation-5.50e-02

Pos logit contributions
sc+0.012
igators+0.011
aled+0.011
 videos+0.011
 baths+0.011
Neg logit contributions
ich-0.017
opsy-0.016
ster-0.015
field-0.015
-0.014
Token-
Token ID12
Feature activation-7.90e-02

Pos logit contributions
sc+0.083
 videos+0.078
 baths+0.078
aled+0.076
igators+0.075
Neg logit contributions
ich-0.107
opsy-0.099
ster-0.092
field-0.087
-0.085
Tokenyear
Token ID1941
Feature activation-1.02e-01

Pos logit contributions
 baths+0.118
 videos+0.113
 TV+0.106
 showers+0.104
 cartoons+0.101
Neg logit contributions
ich-0.172
opsy-0.151
illa-0.141
ster-0.141
pper-0.139
Token-
Token ID12
Feature activation-6.76e-02

Pos logit contributions
sc+0.188
 videos+0.177
 bang+0.170
 baths+0.169
|+0.169
Neg logit contributions
ich-0.182
opsy-0.158
ster-0.157
ama-0.140
field-0.139
Tokenold
Token ID727
Feature activation-4.70e-03

Pos logit contributions
 baths+0.115
 videos+0.114
 tant+0.110
 bang+0.110
 TV+0.109
Neg logit contributions
ich-0.130
opsy-0.112
ster-0.104
illa-0.104
ll-0.099
Token girl
Token ID2576
Feature activation-1.50e-02

Pos logit contributions
sc+0.009
 tant+0.009
 baths+0.009
 videos+0.009
igators+0.009
Neg logit contributions
ich-0.007
opsy-0.006
ster-0.006
field-0.005
flower-0.005
Token.
Token ID13
Feature activation-4.50e-03

Pos logit contributions
 tant+0.024
sc+0.023
 baths+0.023
 videos+0.022
igators+0.022
Neg logit contributions
ich-0.030
opsy-0.027
field-0.025
ster-0.025
flower-0.023
Token She
Token ID1375
Feature activation+5.01e-03

Pos logit contributions
 tant+0.007
sc+0.006
 tests+0.006
igators+0.006
 bang+0.006
Neg logit contributions
ich-0.009
opsy-0.009
-0.008
field-0.008
ama-0.008
Token a
Token ID257
Feature activation-1.58e-02

Pos logit contributions
sc+0.031
igators+0.027
 baths+0.025
 aids+0.025
 villains+0.025
Neg logit contributions
ich-0.036
opsy-0.035
ster-0.031
 wife-0.030
ige-0.029
Token needle
Token ID17598
Feature activation-2.41e-02

Pos logit contributions
igators+0.021
 baths+0.021
 videos+0.020
aled+0.020
sc+0.020
Neg logit contributions
ich-0.033
opsy-0.030
field-0.029
ster-0.029
-0.027
Token and
Token ID290
Feature activation-6.44e-04

Pos logit contributions
 baths+0.049
igators+0.048
 videos+0.048
 tests+0.047
 aids+0.047
Neg logit contributions
ich-0.038
ster-0.031
flower-0.029
field-0.028
opsy-0.028
Token thread
Token ID4704
Feature activation-2.17e-02

Pos logit contributions
 tant+0.001
sc+0.001
 aids+0.001
 baths+0.001
igators+0.001
Neg logit contributions
ich-0.001
opsy-0.001
ster-0.001
field-0.001
sters-0.001
Token and
Token ID290
Feature activation-8.36e-03

Pos logit contributions
 videos+0.034
 tant+0.033
 aids+0.032
igators+0.032
 baths+0.032
Neg logit contributions
ich-0.042
opsy-0.036
ster-0.035
field-0.034
flower-0.033
Token se
Token ID384
Feature activation-1.02e-01

Pos logit contributions
 tant+0.013
 aids+0.013
sc+0.013
igators+0.013
 baths+0.012
Neg logit contributions
ich-0.016
opsy-0.014
ster-0.014
field-0.013
sters-0.012
Tokenwed
Token ID19103
Feature activation+1.54e-02

Pos logit contributions
 baths+0.196
 videos+0.188
 tests+0.188
sc+0.187
 TV+0.184
Neg logit contributions
ich-0.143
opsy-0.132
ese-0.118
ster-0.115
pper-0.115
Token the
Token ID262
Feature activation-3.22e-03

Pos logit contributions
ich+0.027
opsy+0.025
ster+0.023
field+0.022
+0.022
Neg logit contributions
igators-0.024
 aids-0.024
 videos-0.023
 tant-0.023
 baths-0.023
Token t
Token ID256
Feature activation+1.90e-03

Pos logit contributions
sc+0.004
 videos+0.004
 tant+0.004
igators+0.004
 baths+0.004
Neg logit contributions
ich-0.007
opsy-0.007
ster-0.006
field-0.006
flower-0.006
Tokeneddy
Token ID21874
Feature activation-1.11e-02

Pos logit contributions
ich+0.004
opsy+0.003
field+0.003
ster+0.003
flower+0.003
Neg logit contributions
 tant-0.003
sc-0.003
 baths-0.003
 videos-0.003
 tests-0.003
Token bear
Token ID6842
Feature activation-2.17e-03

Pos logit contributions
 tant+0.016
sc+0.015
 baths+0.015
 videos+0.015
 tests+0.015
Neg logit contributions
ich-0.024
opsy-0.021
field-0.020
ster-0.020
flower-0.018
Token day
Token ID1110
Feature activation-3.15e-02

Pos logit contributions
ich+0.026
opsy+0.024
field+0.024
ster+0.021
flower+0.020
Neg logit contributions
 tant-0.024
sc-0.024
 videos-0.022
 baths-0.022
 bang-0.022
Token,
Token ID11
Feature activation-1.47e-03

Pos logit contributions
 tant+0.053
sc+0.051
 videos+0.048
 tests+0.047
 baths+0.047
Neg logit contributions
ich-0.058
opsy-0.054
field-0.050
ster-0.049
-0.046
Token a
Token ID257
Feature activation-8.55e-03

Pos logit contributions
 tant+0.002
sc+0.002
 baths+0.002
 videos+0.001
 tests+0.001
Neg logit contributions
ich-0.004
opsy-0.003
field-0.003
ster-0.003
flower-0.003
Token three
Token ID1115
Feature activation-5.30e-02

Pos logit contributions
sc+0.012
 tant+0.011
 baths+0.011
 videos+0.010
 tests+0.010
Neg logit contributions
ich-0.019
opsy-0.018
field-0.016
ster-0.016
-0.015
Token-
Token ID12
Feature activation-8.59e-02

Pos logit contributions
sc+0.081
 baths+0.075
 videos+0.073
 backward+0.072
aled+0.071
Neg logit contributions
ich-0.104
opsy-0.097
ster-0.090
field-0.085
sters-0.083
Tokenyear
Token ID1941
Feature activation-1.02e-01

Pos logit contributions
 baths+0.112
 videos+0.103
 tant+0.102
 showers+0.095
 bang+0.094
Neg logit contributions
ich-0.203
opsy-0.175
ster-0.170
illa-0.168
field-0.162
Token-
Token ID12
Feature activation-7.33e-02

Pos logit contributions
sc+0.176
 videos+0.162
 baths+0.161
 tant+0.159
 bang+0.156
Neg logit contributions
ich-0.200
opsy-0.169
ster-0.169
field-0.159
 wife-0.151
Tokenold
Token ID727
Feature activation-9.82e-03

Pos logit contributions
 baths+0.107
 tant+0.106
 videos+0.102
sc+0.101
 bang+0.099
Neg logit contributions
ich-0.160
opsy-0.137
ster-0.132
field-0.129
illa-0.126
Token boy
Token ID2933
Feature activation-1.01e-02

Pos logit contributions
 tant+0.017
sc+0.017
 baths+0.017
 videos+0.016
 tests+0.016
Neg logit contributions
ich-0.018
opsy-0.016
field-0.015
ster-0.014
flower-0.013
Token decided
Token ID3066
Feature activation+6.17e-03

Pos logit contributions
 tant+0.016
sc+0.015
 baths+0.015
 videos+0.014
 tests+0.014
Neg logit contributions
ich-0.021
opsy-0.018
field-0.017
ster-0.017
flower-0.016
Token to
Token ID284
Feature activation-4.85e-03

Pos logit contributions
ich+0.016
opsy+0.014
field+0.014
ster+0.014
sters+0.013
Neg logit contributions
 tant-0.007
sc-0.006
 baths-0.006
 videos-0.005
 tests-0.005
Token took
Token ID1718
Feature activation-1.41e-02

Pos logit contributions
 bang+0.022
sc+0.022
 baths+0.022
 Lily+0.021
 around+0.021
Neg logit contributions
ich-0.061
opsy-0.054
field-0.052
ster-0.051
sters-0.049
Token Sara
Token ID24799
Feature activation+6.42e-03

Pos logit contributions
sc+0.021
igator+0.020
bench+0.020
taker+0.020
riend+0.020
Neg logit contributions
ich-0.025
opsy-0.024
iya-0.022
ese-0.021
 wife-0.021
Token the
Token ID262
Feature activation-1.78e-02

Pos logit contributions
ich+0.017
opsy+0.015
field+0.015
ster+0.014
flower+0.013
Neg logit contributions
 tant-0.006
sc-0.006
 baths-0.006
 videos-0.006
 tests-0.005
Token 3
Token ID513
Feature activation-6.90e-02

Pos logit contributions
 aids+0.028
smart+0.027
sc+0.027
 tant+0.027
aled+0.027
Neg logit contributions
ich-0.035
opsy-0.028
field-0.028
ster-0.027
 wife-0.025
Token-
Token ID12
Feature activation-7.70e-02

Pos logit contributions
 backward+0.108
 Everywhere+0.105
sc+0.103
 If+0.102
 baths+0.102
Neg logit contributions
ich-0.122
opsy-0.104
ster-0.104
ese-0.096
iya-0.096
Tokenyear
Token ID1941
Feature activation-1.02e-01

Pos logit contributions
 baths+0.092
 tant+0.091
 bang+0.086
 videos+0.086
sc+0.083
Neg logit contributions
ich-0.173
opsy-0.153
illa-0.150
ster-0.147
ese-0.141
Token-
Token ID12
Feature activation-7.00e-02

Pos logit contributions
sc+0.173
 bang+0.165
 baths+0.159
 videos+0.158
 tant+0.158
Neg logit contributions
ich-0.187
ster-0.159
opsy-0.159
ama-0.144
field-0.142
Tokenold
Token ID727
Feature activation-7.77e-04

Pos logit contributions
 tant+0.107
 baths+0.103
 bang+0.103
sc+0.101
 videos+0.100
Neg logit contributions
ich-0.138
opsy-0.117
illa-0.114
ster-0.114
ese-0.108
Token to
Token ID284
Feature activation+1.73e-03

Pos logit contributions
 tant+0.002
sc+0.002
 baths+0.002
 tests+0.002
 bang+0.002
Neg logit contributions
ich-0.001
opsy-0.001
ster-0.001
field-0.001
sters-0.001
Token the
Token ID262
Feature activation+1.37e-02

Pos logit contributions
ich+0.003
opsy+0.003
field+0.003
 wife+0.003
iya+0.003
Neg logit contributions
sc-0.003
 tant-0.003
taker-0.002
igators-0.002
 aids-0.002
Token park
Token ID3952
Feature activation+9.77e-03

Pos logit contributions
ich+0.027
opsy+0.023
field+0.022
ster+0.021
+0.019
Neg logit contributions
sc-0.023
 tant-0.022
 baths-0.022
igators-0.021
 videos-0.020
Token thirty
Token ID12277
Feature activation-4.92e-02

Pos logit contributions
sc+0.048
 tant+0.045
 baths+0.044
igators+0.040
 videos+0.040
Neg logit contributions
ich-0.075
opsy-0.067
field-0.064
ster-0.062
-0.061
Token-
Token ID12
Feature activation-1.05e-01

Pos logit contributions
sc+0.067
 baths+0.066
 tant+0.066
 videos+0.063
 tests+0.059
Neg logit contributions
ich-0.107
opsy-0.097
field-0.091
ster-0.089
sters-0.084
Tokenone
Token ID505
Feature activation-3.18e-02

Pos logit contributions
 baths+0.181
 videos+0.173
 tant+0.170
sc+0.168
 showers+0.161
Neg logit contributions
ich-0.182
opsy-0.156
illa-0.149
field-0.144
pper-0.139
Token,
Token ID11
Feature activation-3.49e-02

Pos logit contributions
sc+0.053
 baths+0.052
 tant+0.051
 videos+0.050
 showers+0.047
Neg logit contributions
ich-0.059
opsy-0.052
field-0.050
ster-0.048
flower-0.044
Token thirty
Token ID12277
Feature activation-4.80e-02

Pos logit contributions
sc+0.050
 tant+0.047
 baths+0.045
igators+0.041
 videos+0.041
Neg logit contributions
ich-0.077
opsy-0.069
field-0.065
ster-0.064
-0.063
Token-
Token ID12
Feature activation-1.01e-01

Pos logit contributions
sc+0.064
 baths+0.063
 tant+0.063
 videos+0.060
 tests+0.057
Neg logit contributions
ich-0.106
opsy-0.096
field-0.091
ster-0.089
sters-0.083
Tokentwo
Token ID11545
Feature activation-3.71e-02

Pos logit contributions
 baths+0.173
 videos+0.167
 tant+0.165
sc+0.162
 showers+0.155
Neg logit contributions
ich-0.180
opsy-0.153
illa-0.146
field-0.142
pper-0.136
Token,
Token ID11
Feature activation-3.03e-02

Pos logit contributions
sc+0.055
 tant+0.053
 baths+0.053
 videos+0.051
 tests+0.048
Neg logit contributions
ich-0.077
opsy-0.069
field-0.065
ster-0.063
sters-0.059
Token thirty
Token ID12277
Feature activation-4.40e-02

Pos logit contributions
sc+0.044
 tant+0.042
 baths+0.040
igators+0.037
 videos+0.036
Neg logit contributions
ich-0.066
opsy-0.059
field-0.056
ster-0.055
-0.053
Token-
Token ID12
Feature activation-9.06e-02

Pos logit contributions
sc+0.056
 tant+0.055
 baths+0.055
 videos+0.052
 tests+0.050
Neg logit contributions
ich-0.100
opsy-0.090
field-0.086
ster-0.084
sters-0.079
Tokenthree
Token ID15542
Feature activation-4.62e-02

Pos logit contributions
 baths+0.151
 tant+0.147
 videos+0.146
sc+0.143
 showers+0.136
Neg logit contributions
ich-0.169
opsy-0.144
field-0.135
illa-0.134
ster-0.133
Token over
Token ID625
Feature activation+4.85e-04

Pos logit contributions
 tant+0.007
 aids+0.006
igators+0.006
 videos+0.006
 tests+0.006
Neg logit contributions
ich-0.011
opsy-0.010
field-0.009
ster-0.009
-0.009
Token to
Token ID284
Feature activation-1.23e-03

Pos logit contributions
ich+0.001
field+0.001
opsy+0.001
ster+0.001
flower+0.001
Neg logit contributions
 tant-0.001
 videos-0.001
 aids-0.001
 baths-0.001
taker-0.001
Token the
Token ID262
Feature activation+1.50e-03

Pos logit contributions
 baths+0.001
sc+0.001
 tant+0.001
 bang+0.001
 tests+0.001
Neg logit contributions
ich-0.003
opsy-0.003
field-0.003
ster-0.003
sters-0.003
Token cookie
Token ID19751
Feature activation+2.55e-02

Pos logit contributions
ich+0.003
opsy+0.003
field+0.003
ster+0.003
flower+0.002
Neg logit contributions
 tant-0.002
sc-0.002
 baths-0.002
 videos-0.002
 tests-0.002
Token to
Token ID284
Feature activation+8.26e-03

Pos logit contributions
ich+0.049
opsy+0.043
field+0.043
ster+0.040
flower+0.037
Neg logit contributions
 tant-0.043
 baths-0.041
sc-0.041
 videos-0.040
 tests-0.040
Token pick
Token ID2298
Feature activation+3.80e-02

Pos logit contributions
ich+0.018
opsy+0.016
field+0.015
ster+0.015
flower+0.014
Neg logit contributions
 tant-0.012
sc-0.012
 baths-0.011
 videos-0.011
 tests-0.011
Token it
Token ID340
Feature activation-1.50e-02

Pos logit contributions
ich+0.083
opsy+0.076
field+0.071
ster+0.071
sters+0.066
Neg logit contributions
 tant-0.050
sc-0.048
 baths-0.047
 videos-0.047
 tests-0.046
Token up
Token ID510
Feature activation+1.25e-02

Pos logit contributions
 tant+0.019
 baths+0.018
sc+0.018
 tests+0.018
 videos+0.017
Neg logit contributions
ich-0.034
opsy-0.032
field-0.030
ster-0.029
sters-0.027
Token,
Token ID11
Feature activation+1.51e-02

Pos logit contributions
ich+0.028
opsy+0.025
field+0.024
ster+0.023
flower+0.022
Neg logit contributions
 tant-0.016
sc-0.016
 baths-0.016
 videos-0.015
 tests-0.015
Token but
Token ID475
Feature activation+1.28e-03

Pos logit contributions
ich+0.032
opsy+0.028
field+0.027
ster+0.026
flower+0.024
Neg logit contributions
 tant-0.022
sc-0.022
 baths-0.021
 videos-0.020
 tests-0.020
Token then
Token ID788
Feature activation-2.62e-02

Pos logit contributions
ich+0.003
opsy+0.003
field+0.003
ster+0.003
sters+0.002
Neg logit contributions
 tant-0.001
sc-0.001
 baths-0.001
 tests-0.001
 videos-0.001
Token day
Token ID1110
Feature activation-9.13e-03

Pos logit contributions
ich+0.044
opsy+0.040
field+0.038
ster+0.037
sters+0.037
Neg logit contributions
sc-0.017
 tant-0.017
 baths-0.017
 videos-0.016
 tests-0.015
Token on
Token ID319
Feature activation+5.27e-03

Pos logit contributions
sc+0.007
 baths+0.007
 around+0.007
 tant+0.006
 loud+0.006
Neg logit contributions
ich-0.025
opsy-0.023
field-0.023
ster-0.021
sters-0.021
Token,
Token ID11
Feature activation+1.45e-02

Pos logit contributions
ich+0.011
opsy+0.010
field+0.010
ster+0.009
+0.009
Neg logit contributions
 tant-0.008
sc-0.008
 baths-0.007
 videos-0.007
 tests-0.007
Token they
Token ID484
Feature activation+2.49e-02

Pos logit contributions
ich+0.035
opsy+0.033
field+0.031
+0.030
ster+0.030
Neg logit contributions
 tant-0.015
sc-0.015
 aids-0.013
igators-0.013
 tests-0.013
Token became
Token ID2627
Feature activation+1.57e-02

Pos logit contributions
ich+0.063
opsy+0.054
ster+0.052
field+0.052
sters+0.050
Neg logit contributions
 baths-0.027
 bang-0.025
 tant-0.025
sc-0.025
 around-0.025
Token friends
Token ID2460
Feature activation+3.36e-02

Pos logit contributions
ich+0.037
opsy+0.033
field+0.032
ster+0.031
sters+0.029
Neg logit contributions
 baths-0.019
sc-0.019
 tant-0.019
 videos-0.018
 tests-0.018
Token and
Token ID290
Feature activation-8.94e-03

Pos logit contributions
ich+0.083
opsy+0.077
field+0.073
ster+0.070
sters+0.067
Neg logit contributions
 baths-0.037
sc-0.036
 tant-0.035
 around-0.035
 videos-0.034
Token played
Token ID2826
Feature activation+9.71e-03

Pos logit contributions
 baths+0.012
sc+0.011
 tant+0.011
 videos+0.011
 tests+0.011
Neg logit contributions
ich-0.020
opsy-0.018
field-0.017
ster-0.017
sters-0.016
Token together
Token ID1978
Feature activation-6.93e-03

Pos logit contributions
ich+0.025
opsy+0.023
field+0.022
ster+0.021
flower+0.020
Neg logit contributions
sc-0.010
 baths-0.010
 tant-0.009
 videos-0.009
 tests-0.009
Token every
Token ID790
Feature activation+8.04e-03

Pos logit contributions
 tant+0.010
sc+0.010
 baths+0.009
 videos+0.009
 tests+0.009
Neg logit contributions
ich-0.015
opsy-0.013
field-0.013
ster-0.012
flower-0.011
Token time
Token ID640
Feature activation-1.06e-02

Pos logit contributions
ich+0.018
opsy+0.017
field+0.016
ster+0.015
flower+0.014
Neg logit contributions
 tant-0.010
sc-0.010
 baths-0.010
 tests-0.009
 videos-0.009
Token hands
Token ID2832
Feature activation+1.48e-02

Pos logit contributions
 tant+0.031
sc+0.029
 baths+0.029
 videos+0.028
 tests+0.028
Neg logit contributions
ich-0.046
opsy-0.040
field-0.039
ster-0.037
sters-0.034
Token and
Token ID290
Feature activation-7.27e-03

Pos logit contributions
ich+0.031
opsy+0.028
field+0.027
ster+0.026
flower+0.024
Neg logit contributions
 tant-0.022
sc-0.021
 baths-0.021
 tests-0.020
 videos-0.020
Token picked
Token ID6497
Feature activation+2.96e-02

Pos logit contributions
 tant+0.010
sc+0.010
 baths+0.010
 videos+0.009
 tests+0.009
Neg logit contributions
ich-0.016
opsy-0.014
field-0.013
ster-0.013
flower-0.012
Token the
Token ID262
Feature activation-3.67e-03

Pos logit contributions
ich+0.077
opsy+0.070
field+0.067
ster+0.065
flower+0.061
Neg logit contributions
 tant-0.029
sc-0.029
 baths-0.028
 videos-0.027
 tests-0.026
Token creamy
Token ID27892
Feature activation+2.27e-02

Pos logit contributions
 loud+0.004
 tant+0.004
 Lily+0.004
 around+0.004
 hard+0.004
Neg logit contributions
ich-0.009
opsy-0.008
field-0.008
iya-0.008
ipper-0.007
Token fruit
Token ID8234
Feature activation+4.31e-02

Pos logit contributions
ich+0.051
opsy+0.043
field+0.042
ster+0.039
iya+0.037
Neg logit contributions
 tant-0.033
 baths-0.032
sc-0.031
 around-0.029
 videos-0.029
Token.
Token ID13
Feature activation-2.77e-03

Pos logit contributions
ich+0.099
opsy+0.089
field+0.085
ster+0.082
flower+0.077
Neg logit contributions
 tant-0.055
sc-0.054
 baths-0.053
 videos-0.051
 tests-0.050
Token She
Token ID1375
Feature activation+5.78e-03

Pos logit contributions
 tant+0.004
sc+0.003
 tests+0.003
igators+0.003
 baths+0.003
Neg logit contributions
ich-0.006
opsy-0.006
field-0.006
-0.006
ster-0.005
Token tasted
Token ID29187
Feature activation+3.42e-02

Pos logit contributions
ich+0.014
opsy+0.012
field+0.012
ster+0.011
ese+0.010
Neg logit contributions
 tant-0.007
sc-0.007
 baths-0.007
 tests-0.007
 bang-0.006
Token it
Token ID340
Feature activation-1.93e-03

Pos logit contributions
ich+0.086
opsy+0.078
field+0.075
ster+0.072
flower+0.068
Neg logit contributions
 tant-0.036
sc-0.036
 baths-0.035
 videos-0.033
 tests-0.033
Token and
Token ID290
Feature activation-3.44e-03

Pos logit contributions
 tant+0.003
sc+0.003
 baths+0.003
 videos+0.002
 tests+0.002
Neg logit contributions
ich-0.004
opsy-0.004
field-0.004
ster-0.004
sters-0.003
Token excited
Token ID6568
Feature activation+3.71e-03

Pos logit contributions
sc+0.011
 tant+0.011
igsaw+0.010
 baths+0.010
 tests+0.010
Neg logit contributions
ich-0.016
opsy-0.014
ster-0.013
field-0.013
sters-0.012
Token to
Token ID284
Feature activation+1.43e-02

Pos logit contributions
ich+0.007
opsy+0.006
field+0.005
ster+0.005
flower+0.005
Neg logit contributions
 tant-0.007
sc-0.006
 tests-0.006
 bang-0.006
 baths-0.006
Token have
Token ID423
Feature activation+1.40e-02

Pos logit contributions
ich+0.028
opsy+0.025
field+0.024
ster+0.023
flower+0.021
Neg logit contributions
 tant-0.023
sc-0.023
 baths-0.022
 tests-0.021
 videos-0.021
Token a
Token ID257
Feature activation-6.85e-03

Pos logit contributions
ich+0.032
opsy+0.030
field+0.028
ster+0.027
sters+0.026
Neg logit contributions
 tant-0.018
sc-0.017
 videos-0.016
 baths-0.016
 tests-0.016
Token new
Token ID649
Feature activation-9.10e-03

Pos logit contributions
 tant+0.010
sc+0.010
 baths+0.009
 videos+0.009
 tests+0.009
Neg logit contributions
ich-0.015
opsy-0.013
field-0.013
ster-0.012
sters-0.011
Token pet
Token ID4273
Feature activation+5.01e-02

Pos logit contributions
 tant+0.015
sc+0.014
 baths+0.014
 videos+0.014
 tests+0.013
Neg logit contributions
ich-0.018
opsy-0.016
field-0.015
ster-0.014
sters-0.013
Token.
Token ID13
Feature activation-3.08e-03

Pos logit contributions
ich+0.114
opsy+0.102
field+0.098
ster+0.093
sters+0.087
Neg logit contributions
sc-0.065
 tant-0.064
 baths-0.063
 videos-0.060
 tests-0.059
Token They
Token ID1119
Feature activation+1.35e-02

Pos logit contributions
sc+0.003
 baths+0.003
 tant+0.003
 videos+0.003
 tests+0.002
Neg logit contributions
ich-0.008
opsy-0.007
field-0.007
ster-0.007
pper-0.007
Token tried
Token ID3088
Feature activation+1.14e-02

Pos logit contributions
ich+0.028
opsy+0.025
field+0.024
ster+0.023
flower+0.021
Neg logit contributions
sc-0.020
 tant-0.020
 baths-0.020
 videos-0.019
 bang-0.019
Token to
Token ID284
Feature activation-1.34e-02

Pos logit contributions
ich+0.028
opsy+0.025
field+0.024
ster+0.023
flower+0.022
Neg logit contributions
sc-0.013
 tant-0.013
taker-0.012
 baths-0.011
igators-0.011
Token grab
Token ID5552
Feature activation+2.50e-02

Pos logit contributions
 tant+0.021
sc+0.021
 baths+0.020
 videos+0.019
 tests+0.019
Neg logit contributions
ich-0.027
opsy-0.024
field-0.023
ster-0.022
flower-0.021
Token he
Token ID339
Feature activation+7.78e-03

Pos logit contributions
 baths+0.010
 tant+0.010
sc+0.010
 tests+0.009
 videos+0.009
Neg logit contributions
ich-0.029
opsy-0.026
field-0.024
ster-0.024
flower-0.023
Token was
Token ID373
Feature activation-1.14e-03

Pos logit contributions
ich+0.019
opsy+0.017
field+0.016
ster+0.015
sters+0.015
Neg logit contributions
sc-0.009
 tant-0.009
 baths-0.009
 tests-0.008
 bang-0.008
Token done
Token ID1760
Feature activation-5.91e-03

Pos logit contributions
 tant+0.002
sc+0.002
 videos+0.002
 baths+0.002
 tests+0.002
Neg logit contributions
ich-0.002
opsy-0.002
field-0.002
ster-0.002
iya-0.002
Token he
Token ID339
Feature activation+1.51e-02

Pos logit contributions
 tant+0.011
sc+0.010
igators+0.009
 videos+0.009
 tests+0.009
Neg logit contributions
ich-0.011
opsy-0.010
field-0.009
ster-0.009
-0.008
Token went
Token ID1816
Feature activation-4.96e-03

Pos logit contributions
ich+0.036
opsy+0.031
field+0.029
ster+0.029
flower+0.028
Neg logit contributions
sc-0.019
 baths-0.018
 tests-0.017
 around-0.017
 tant-0.017
Token back
Token ID736
Feature activation+3.28e-02

Pos logit contributions
 tant+0.008
sc+0.007
 baths+0.007
 videos+0.007
 tests+0.007
Neg logit contributions
ich-0.011
opsy-0.009
field-0.009
ster-0.009
sters-0.008
Token home
Token ID1363
Feature activation+2.31e-03

Pos logit contributions
ich+0.071
opsy+0.063
field+0.061
ster+0.058
flower+0.054
Neg logit contributions
 tant-0.047
sc-0.047
 baths-0.045
 videos-0.044
 tests-0.043
Token,
Token ID11
Feature activation+1.97e-02

Pos logit contributions
ich+0.005
opsy+0.005
field+0.004
ster+0.004
sters+0.004
Neg logit contributions
sc-0.003
 tant-0.003
 baths-0.003
 videos-0.003
 tests-0.003
Token much
Token ID881
Feature activation+1.32e-02

Pos logit contributions
ich+0.051
opsy+0.047
field+0.045
ster+0.043
sters+0.041
Neg logit contributions
 tant-0.019
 baths-0.019
sc-0.019
 videos-0.017
 tests-0.017
Token richer
Token ID26192
Feature activation-3.89e-03

Pos logit contributions
ich+0.027
field+0.024
opsy+0.024
ster+0.023
sters+0.020
Neg logit contributions
sc-0.020
 tant-0.020
igators-0.018
aled-0.018
 aids-0.018
Token for
Token ID329
Feature activation+6.29e-03

Pos logit contributions
 tant+0.005
sc+0.005
 baths+0.005
 tests+0.005
 videos+0.005
Neg logit contributions
ich-0.009
opsy-0.008
field-0.007
ster-0.007
flower-0.007
Token of
Token ID286
Feature activation-4.74e-02

Pos logit contributions
|+0.022
sc+0.022
 baths+0.021
 Everywhere+0.021
aled+0.021
Neg logit contributions
ich-0.025
ster-0.022
opsy-0.021
field-0.021
 wife-0.020
Token her
Token ID607
Feature activation-1.37e-02

Pos logit contributions
sc+0.063
 tant+0.057
 baths+0.054
 tests+0.053
 aids+0.050
Neg logit contributions
ich-0.107
opsy-0.101
field-0.093
flower-0.089
ster-0.086
Token blocks
Token ID7021
Feature activation+1.18e-02

Pos logit contributions
sc+0.020
 baths+0.019
 tant+0.019
 videos+0.019
 tests+0.018
Neg logit contributions
ich-0.029
opsy-0.026
field-0.025
ster-0.024
flower-0.022
Token and
Token ID290
Feature activation+7.63e-04

Pos logit contributions
ich+0.024
opsy+0.021
field+0.020
ster+0.020
flower+0.019
Neg logit contributions
 baths-0.018
sc-0.017
 tant-0.017
 videos-0.017
 tests-0.017
Token goes
Token ID2925
Feature activation-1.59e-02

Pos logit contributions
ich+0.002
opsy+0.001
field+0.001
ster+0.001
sters+0.001
Neg logit contributions
 tant-0.001
sc-0.001
 baths-0.001
taker-0.001
igsaw-0.001
Token to
Token ID284
Feature activation-1.54e-03

Pos logit contributions
 tant+0.020
 aids+0.018
 baths+0.018
sc+0.018
 videos+0.017
Neg logit contributions
ich-0.037
field-0.032
opsy-0.032
ster-0.031
flower-0.029
Token Tim
Token ID5045
Feature activation+1.71e-02

Pos logit contributions
sc+0.002
 tant+0.002
 baths+0.002
igators+0.002
taker+0.002
Neg logit contributions
ich-0.004
opsy-0.003
field-0.003
ster-0.003
 wife-0.003
Token.
Token ID13
Feature activation-3.43e-03

Pos logit contributions
ich+0.031
opsy+0.027
field+0.026
ster+0.025
flower+0.023
Neg logit contributions
 tant-0.030
sc-0.029
 baths-0.028
taker-0.027
 videos-0.027
Token She
Token ID1375
Feature activation+9.35e-03

Pos logit contributions
 tant+0.005
sc+0.005
igators+0.005
 baths+0.005
igator+0.004
Neg logit contributions
ich-0.007
opsy-0.006
-0.006
field-0.006
ster-0.005
Token says
Token ID1139
Feature activation+1.84e-02

Pos logit contributions
ich+0.019
opsy+0.017
field+0.016
ster+0.015
sters+0.014
Neg logit contributions
 tant-0.014
sc-0.014
 baths-0.014
 videos-0.013
taker-0.013
Token,
Token ID11
Feature activation-4.17e-03

Pos logit contributions
ich+0.032
ster+0.028
opsy+0.027
sters+0.026
+0.025
Neg logit contributions
sc-0.035
 tant-0.032
|-0.031
 channel-0.030
igators-0.030
Token over
Token ID625
Feature activation+4.41e-03

Pos logit contributions
 tant+0.005
sc+0.004
 aids+0.004
 tests+0.004
 baths+0.004
Neg logit contributions
ich-0.010
opsy-0.009
field-0.009
ster-0.009
-0.008
Token to
Token ID284
Feature activation+3.47e-03

Pos logit contributions
ich+0.011
opsy+0.010
field+0.009
ster+0.009
flower+0.008
Neg logit contributions
 tant-0.005
sc-0.005
 baths-0.005
 videos-0.005
 aids-0.005
Token it
Token ID340
Feature activation-1.26e-02

Pos logit contributions
ich+0.010
opsy+0.009
field+0.009
ster+0.009
sters+0.008
Neg logit contributions
 baths-0.003
 bang-0.003
 Lily-0.002
 videos-0.002
 around-0.002
Token and
Token ID290
Feature activation-1.66e-03

Pos logit contributions
sc+0.016
 baths+0.016
 tant+0.016
 videos+0.015
 tests+0.015
Neg logit contributions
ich-0.029
opsy-0.026
field-0.024
ster-0.024
sters-0.022
Token said
Token ID531
Feature activation+1.55e-02

Pos logit contributions
 baths+0.002
sc+0.002
 tant+0.002
 videos+0.002
 tests+0.002
Neg logit contributions
ich-0.004
opsy-0.003
field-0.003
ster-0.003
flower-0.003
Token in
Token ID287
Feature activation-4.62e-03

Pos logit contributions
ich+0.032
opsy+0.029
ster+0.027
field+0.027
sters+0.025
Neg logit contributions
 tant-0.023
sc-0.023
 videos-0.022
 baths-0.022
 tests-0.021
Token a
Token ID257
Feature activation+6.18e-04

Pos logit contributions
sc+0.006
 tant+0.005
igators+0.005
taker+0.005
 tests+0.005
Neg logit contributions
ich-0.011
opsy-0.010
field-0.009
ster-0.009
 wife-0.009
Token happy
Token ID3772
Feature activation+1.20e-02

Pos logit contributions
ich+0.001
opsy+0.001
field+0.001
ster+0.001
+0.001
Neg logit contributions
 baths-0.001
sc-0.001
 videos-0.001
 tant-0.001
 tests-0.001
Token voice
Token ID3809
Feature activation-3.66e-02

Pos logit contributions
ich+0.026
opsy+0.024
field+0.022
ster+0.022
 wife+0.021
Neg logit contributions
sc-0.018
 tests-0.017
 tant-0.016
igators-0.016
aled-0.015
Token,
Token ID11
Feature activation-1.87e-03

Pos logit contributions
 tant+0.067
sc+0.064
 baths+0.061
 tests+0.059
igators+0.058
Neg logit contributions
ich-0.066
ster-0.054
opsy-0.054
field-0.051
flower-0.049
Token "
Token ID366
Feature activation-1.94e-03

Pos logit contributions
 tant+0.002
sc+0.002
 baths+0.002
 videos+0.002
 tests+0.002
Neg logit contributions
ich-0.004
opsy-0.004
field-0.004
ster-0.004
flower-0.003
Token<|endoftext|>
Token ID50256
Feature activation+7.05e-03

Pos logit contributions
ich+0.021
opsy+0.019
field+0.018
ster+0.017
flower+0.016
Neg logit contributions
 tant-0.012
sc-0.012
 baths-0.012
 tests-0.011
 videos-0.011
TokenAnna
Token ID31160
Feature activation-1.43e-02

Pos logit contributions
ich+0.015
opsy+0.013
field+0.012
ster+0.012
sters+0.011
Neg logit contributions
sc-0.011
 tant-0.011
 baths-0.010
 videos-0.010
 tests-0.010
Token and
Token ID290
Feature activation-1.30e-03

Pos logit contributions
sc+0.016
 baths+0.016
 tant+0.015
 around+0.015
 tests+0.015
Neg logit contributions
ich-0.035
opsy-0.031
field-0.030
ster-0.028
sters-0.028
Token Ben
Token ID3932
Feature activation+4.88e-03

Pos logit contributions
 baths+0.001
 tant+0.001
 videos+0.001
sc+0.001
 Lily+0.001
Neg logit contributions
ich-0.004
opsy-0.003
field-0.003
ster-0.003
sters-0.003
Token are
Token ID389
Feature activation-1.59e-02

Pos logit contributions
ich+0.012
opsy+0.011
field+0.010
ster+0.010
sters+0.009
Neg logit contributions
 baths-0.005
 Lily-0.005
 around-0.005
 bang-0.005
sc-0.005
Token twins
Token ID20345
Feature activation+6.91e-03

Pos logit contributions
sc+0.025
 tant+0.025
 baths+0.024
 tests+0.023
 videos+0.023
Neg logit contributions
ich-0.033
opsy-0.029
field-0.027
ster-0.026
flower-0.024
Token.
Token ID13
Feature activation-2.33e-04

Pos logit contributions
ich+0.018
opsy+0.017
field+0.016
ster+0.016
sters+0.015
Neg logit contributions
 around-0.006
 baths-0.006
 videos-0.006
 tant-0.006
 tests-0.006
Token They
Token ID1119
Feature activation+1.39e-02

Pos logit contributions
 tant+0.000
sc+0.000
 tests+0.000
taker+0.000
 baths+0.000
Neg logit contributions
opsy-0.001
ich-0.001
field-0.000
-0.000
flower-0.000
Token like
Token ID588
Feature activation+6.65e-03

Pos logit contributions
ich+0.031
opsy+0.029
field+0.027
ster+0.026
flower+0.025
Neg logit contributions
 tant-0.018
sc-0.017
 baths-0.016
 tests-0.016
 videos-0.016
Token to
Token ID284
Feature activation+1.15e-02

Pos logit contributions
ich+0.016
opsy+0.014
field+0.014
ster+0.013
 wife+0.013
Neg logit contributions
sc-0.007
 tant-0.007
taker-0.006
igsaw-0.006
 baths-0.006
Token play
Token ID711
Feature activation+5.21e-03

Pos logit contributions
ich+0.020
opsy+0.019
field+0.018
 wife+0.017
flower+0.017
Neg logit contributions
sc-0.021
 tant-0.020
taker-0.018
 aback-0.017
 baths-0.017
Token ran
Token ID4966
Feature activation-7.89e-03

Pos logit contributions
 tant+0.021
sc+0.020
 baths+0.020
 videos+0.019
 tests+0.019
Neg logit contributions
ich-0.023
opsy-0.020
field-0.019
ster-0.019
flower-0.017
Token outside
Token ID2354
Feature activation-6.21e-04

Pos logit contributions
 tant+0.013
 aids+0.013
igators+0.012
igsaw+0.011
igator+0.011
Neg logit contributions
ich-0.012
field-0.010
-0.010
opsy-0.009
 wife-0.009
Token and
Token ID290
Feature activation-6.69e-04

Pos logit contributions
 tant+0.001
sc+0.001
igators+0.001
 baths+0.001
 tests+0.001
Neg logit contributions
ich-0.001
field-0.001
opsy-0.001
ster-0.001
flower-0.001
Token he
Token ID339
Feature activation+8.77e-03

Pos logit contributions
 tant+0.001
 aids+0.001
sc+0.001
igsaw+0.001
 videos+0.001
Neg logit contributions
ich-0.001
field-0.001
opsy-0.001
ster-0.001
-0.001
Token was
Token ID373
Feature activation-8.26e-03

Pos logit contributions
ich+0.014
opsy+0.013
field+0.012
ster+0.011
+0.010
Neg logit contributions
 tant-0.017
 videos-0.016
sc-0.016
 baths-0.016
igsaw-0.016
Token so
Token ID523
Feature activation+7.65e-03

Pos logit contributions
sc+0.013
 tant+0.012
igsaw+0.011
 videos+0.011
 baths+0.010
Neg logit contributions
ich-0.018
opsy-0.015
field-0.015
ster-0.014
ese-0.013
Token wet
Token ID9583
Feature activation+1.13e-03

Pos logit contributions
ich+0.013
opsy+0.011
field+0.010
ster+0.010
+0.010
Neg logit contributions
sc-0.015
 tant-0.014
 videos-0.014
 baths-0.013
 tests-0.013
Token!
Token ID0
Feature activation-7.25e-03

Pos logit contributions
ich+0.002
field+0.002
opsy+0.002
ster+0.002
flower+0.002
Neg logit contributions
 tant-0.002
sc-0.002
 aids-0.002
 tests-0.002
 videos-0.002
Token He
Token ID679
Feature activation+4.31e-03

Pos logit contributions
sc+0.008
 tant+0.008
 baths+0.007
igators+0.007
 bang+0.007
Neg logit contributions
ich-0.016
field-0.015
opsy-0.015
-0.014
ama-0.014
Token yelled
Token ID22760
Feature activation+5.71e-03

Pos logit contributions
ich+0.007
opsy+0.006
field+0.006
ster+0.006
 remembered+0.005
Neg logit contributions
igsaw-0.008
 tant-0.008
sc-0.008
 videos-0.008
 baths-0.007
Token from
Token ID422
Feature activation-1.75e-02

Pos logit contributions
ich+0.010
ster+0.009
opsy+0.008
+0.008
sters+0.007
Neg logit contributions
igators-0.010
sc-0.010
 tant-0.009
bench-0.009
igator-0.009
Token,
Token ID11
Feature activation-4.68e-03

Pos logit contributions
ich+0.018
opsy+0.016
ster+0.016
field+0.015
+0.014
Neg logit contributions
sc-0.017
 tant-0.017
igators-0.017
 tests-0.016
 baths-0.016
Token giving
Token ID3501
Feature activation-4.82e-03

Pos logit contributions
sc+0.007
 tant+0.007
 baths+0.007
 tests+0.007
 videos+0.006
Neg logit contributions
ich-0.010
opsy-0.009
field-0.008
ster-0.008
flower-0.007
Token him
Token ID683
Feature activation-4.24e-03

Pos logit contributions
sc+0.007
 tant+0.007
 bang+0.006
 tests+0.006
igators+0.006
Neg logit contributions
ich-0.010
opsy-0.009
ster-0.009
field-0.008
ese-0.008
Token a
Token ID257
Feature activation-2.12e-02

Pos logit contributions
sc+0.004
 tant+0.004
 videos+0.004
 baths+0.004
 bang+0.004
Neg logit contributions
ich-0.011
opsy-0.010
field-0.009
ster-0.009
ese-0.009
Token big
Token ID1263
Feature activation-1.29e-02

Pos logit contributions
sc+0.021
 tant+0.020
 baths+0.020
 videos+0.019
 tests+0.019
Neg logit contributions
ich-0.053
opsy-0.049
field-0.047
ster-0.046
flower-0.043
Token hug
Token ID16225
Feature activation+2.51e-02

Pos logit contributions
sc+0.017
 baths+0.017
 tant+0.016
 videos+0.016
igators+0.016
Neg logit contributions
ich-0.027
opsy-0.025
field-0.024
ster-0.023
flower-0.022
Token.
Token ID13
Feature activation-3.91e-03

Pos logit contributions
ich+0.050
opsy+0.042
field+0.042
ster+0.042
flower+0.038
Neg logit contributions
 tant-0.039
 baths-0.039
sc-0.039
 tests-0.037
 videos-0.037
Token
Token ID220
Feature activation+9.85e-03

Pos logit contributions
sc+0.003
 baths+0.003
 tant+0.003
 videos+0.003
 tests+0.002
Neg logit contributions
ich-0.011
opsy-0.010
field-0.010
ster-0.010
flower-0.009
Token
Token ID198
Feature activation+1.06e-03

Pos logit contributions
ich+0.022
opsy+0.020
field+0.019
ster+0.018
flower+0.017
Neg logit contributions
 tant-0.013
sc-0.013
 baths-0.013
 videos-0.012
 tests-0.012
TokenJack
Token ID14295
Feature activation-1.86e-03

Pos logit contributions
ich+0.003
opsy+0.002
field+0.002
ster+0.002
flower+0.002
Neg logit contributions
sc-0.001
 baths-0.001
 videos-0.001
 tant-0.001
 tests-0.001
Token smiled
Token ID13541
Feature activation+2.44e-02

Pos logit contributions
 tant+0.003
 baths+0.002
sc+0.002
 bang+0.002
 tests+0.002
Neg logit contributions
ich-0.004
opsy-0.004
field-0.003
ster-0.003
sters-0.003
Token are
Token ID389
Feature activation+8.05e-03

Pos logit contributions
 tant+0.039
sc+0.038
 baths+0.037
 videos+0.036
 tests+0.035
Neg logit contributions
ich-0.050
opsy-0.044
field-0.043
ster-0.041
sters-0.038
Token secrets
Token ID13141
Feature activation-2.94e-03

Pos logit contributions
ich+0.017
opsy+0.014
field+0.014
ster+0.014
sters+0.013
Neg logit contributions
 tant-0.012
sc-0.012
igsaw-0.011
bench-0.011
 baths-0.011
Token or
Token ID393
Feature activation+2.36e-02

Pos logit contributions
 tant+0.005
 baths+0.005
sc+0.004
 videos+0.004
 bang+0.004
Neg logit contributions
ich-0.006
field-0.005
opsy-0.005
ster-0.005
sters-0.004
Token treasures
Token ID29561
Feature activation+3.59e-03

Pos logit contributions
ich+0.048
field+0.041
ster+0.041
opsy+0.040
sters+0.039
Neg logit contributions
sc-0.037
 tant-0.034
igsaw-0.033
bench-0.032
iren-0.032
Token or
Token ID393
Feature activation+2.41e-02

Pos logit contributions
ich+0.007
field+0.006
opsy+0.006
ster+0.006
sters+0.005
Neg logit contributions
 tant-0.006
sc-0.006
 baths-0.006
 videos-0.005
 tests-0.005
Token magic
Token ID5536
Feature activation-2.00e-02

Pos logit contributions
ich+0.047
ster+0.041
field+0.041
opsy+0.040
sters+0.040
Neg logit contributions
sc-0.038
 tant-0.034
igsaw-0.034
bench-0.034
iren-0.033
Token in
Token ID287
Feature activation+1.80e-02

Pos logit contributions
 tant+0.033
 baths+0.032
sc+0.032
igsaw+0.030
 showers+0.030
Neg logit contributions
ich-0.036
ster-0.032
field-0.031
opsy-0.030
sters-0.030
Token there
Token ID612
Feature activation-2.04e-02

Pos logit contributions
ich+0.034
field+0.030
opsy+0.029
ster+0.028
 pearl+0.026
Neg logit contributions
sc-0.030
 tant-0.027
taker-0.026
 baths-0.026
lic-0.025
Token,"
Token ID553
Feature activation+1.48e-02

Pos logit contributions
 tant+0.031
sc+0.030
 baths+0.030
 videos+0.028
 tests+0.028
Neg logit contributions
ich-0.042
opsy-0.037
field-0.036
ster-0.034
flower-0.032
Token Ben
Token ID3932
Feature activation-1.43e-02

Pos logit contributions
ich+0.033
opsy+0.030
field+0.028
ster+0.027
+0.025
Neg logit contributions
sc-0.021
 tant-0.020
 baths-0.019
 tests-0.018
 videos-0.018
Token said
Token ID531
Feature activation+9.75e-03

Pos logit contributions
 tant+0.028
 baths+0.028
sc+0.028
 showers+0.027
 tests+0.027
Neg logit contributions
ich-0.021
opsy-0.019
field-0.018
ster-0.018
sters-0.016
Token.
Token ID13
Feature activation-7.23e-03

Pos logit contributions
ich+0.009
opsy+0.007
ster+0.007
field+0.007
sters+0.007
Neg logit contributions
 tant-0.013
sc-0.012
igsaw-0.012
 aids-0.012
igators-0.012
Token His
Token ID2399
Feature activation-6.86e-04

Pos logit contributions
sc+0.008
 tant+0.008
 baths+0.008
 tests+0.008
 videos+0.008
Neg logit contributions
ich-0.017
opsy-0.016
field-0.015
ster-0.014
-0.014
Token mom
Token ID1995
Feature activation-2.75e-03

Pos logit contributions
 tant+0.001
 baths+0.001
sc+0.001
 tests+0.001
 videos+0.001
Neg logit contributions
ich-0.001
opsy-0.001
field-0.001
ster-0.001
sters-0.001
Token told
Token ID1297
Feature activation-1.43e-02

Pos logit contributions
 tant+0.004
sc+0.004
 baths+0.004
 videos+0.004
 tests+0.004
Neg logit contributions
ich-0.006
opsy-0.005
field-0.005
ster-0.005
flower-0.004
Token him
Token ID683
Feature activation-1.90e-02

Pos logit contributions
sc+0.029
 tant+0.026
 channel+0.024
riend+0.024
igsaw+0.023
Neg logit contributions
ich-0.021
opsy-0.020
ese-0.018
iri-0.017
ama-0.017
Token to
Token ID284
Feature activation-2.26e-02

Pos logit contributions
sc+0.030
 tant+0.030
 channel+0.025
aled+0.024
igators+0.024
Neg logit contributions
ich-0.039
opsy-0.035
ster-0.033
field-0.032
ama-0.031
Token stay
Token ID2652
Feature activation+1.18e-02

Pos logit contributions
 tant+0.036
sc+0.036
 videos+0.033
 baths+0.033
 tests+0.032
Neg logit contributions
ich-0.045
opsy-0.042
field-0.039
ster-0.036
flower-0.034
Token inside
Token ID2641
Feature activation-5.91e-03

Pos logit contributions
ich+0.029
opsy+0.027
field+0.025
ster+0.025
flower+0.023
Neg logit contributions
 tant-0.013
sc-0.013
 baths-0.012
 videos-0.012
 tests-0.012
Token until
Token ID1566
Feature activation-1.89e-02

Pos logit contributions
sc+0.009
 tant+0.009
 baths+0.008
 videos+0.008
 bang+0.008
Neg logit contributions
ich-0.012
opsy-0.011
field-0.011
ster-0.010
flower-0.009
Token he
Token ID339
Feature activation-2.27e-04

Pos logit contributions
 tant+0.021
sc+0.021
 baths+0.020
 videos+0.019
 tests+0.019
Neg logit contributions
ich-0.047
opsy-0.043
field-0.041
ster-0.040
flower-0.037
Token felt
Token ID2936
Feature activation-6.21e-03

Pos logit contributions
sc+0.000
 baths+0.000
 tant+0.000
 tests+0.000
 Lily+0.000
Neg logit contributions
ich-0.001
opsy-0.000
field-0.000
ster-0.000
sters-0.000
TokenMaybe
Token ID13300
Feature activation-1.42e-02

Pos logit contributions
 baths+0.012
 tant+0.012
sc+0.012
 videos+0.012
 tests+0.012
Neg logit contributions
ich-0.013
opsy-0.011
field-0.011
ster-0.010
flower-0.009
Token it
Token ID340
Feature activation-1.23e-02

Pos logit contributions
 baths+0.014
sc+0.014
 tant+0.014
 tests+0.013
 videos+0.013
Neg logit contributions
ich-0.036
opsy-0.033
field-0.031
ster-0.030
flower-0.029
Token was
Token ID373
Feature activation-3.34e-03

Pos logit contributions
 tant+0.021
 baths+0.020
 videos+0.020
igsaw+0.020
sc+0.020
Neg logit contributions
ich-0.023
opsy-0.020
field-0.019
ster-0.018
flower-0.018
Token just
Token ID655
Feature activation+2.21e-02

Pos logit contributions
 tant+0.005
sc+0.004
igsaw+0.004
 baths+0.004
taker+0.004
Neg logit contributions
ich-0.008
opsy-0.007
field-0.006
ster-0.006
ese-0.006
Token a
Token ID257
Feature activation-1.01e-02

Pos logit contributions
ich+0.048
opsy+0.042
field+0.041
ster+0.039
flower+0.037
Neg logit contributions
sc-0.032
 tant-0.032
igsaw-0.027
bench-0.026
 baths-0.026
Token big
Token ID1263
Feature activation-2.11e-02

Pos logit contributions
sc+0.015
 tant+0.014
 baths+0.014
 videos+0.014
 tests+0.013
Neg logit contributions
ich-0.022
opsy-0.019
field-0.018
ster-0.018
flower-0.016
Token dog
Token ID3290
Feature activation+1.07e-02

Pos logit contributions
sc+0.036
 tant+0.034
 baths+0.034
 tests+0.032
 videos+0.032
Neg logit contributions
ich-0.039
opsy-0.034
field-0.033
ster-0.032
flower-0.030
Token."
Token ID526
Feature activation-6.65e-03

Pos logit contributions
ich+0.021
opsy+0.018
ster+0.018
field+0.018
pper+0.016
Neg logit contributions
 tant-0.018
 baths-0.016
sc-0.016
 tests-0.015
 videos-0.015
Token
Token ID198
Feature activation-6.14e-03

Pos logit contributions
sc+0.007
 tant+0.007
 baths+0.007
 tests+0.007
 videos+0.007
Neg logit contributions
ich-0.016
opsy-0.015
field-0.014
ster-0.014
flower-0.013
Token
Token ID198
Feature activation-1.03e-04

Pos logit contributions
 loud+0.005
sc+0.005
 baths+0.005
 tant+0.005
 Lily+0.005
Neg logit contributions
ich-0.016
opsy-0.015
field-0.014
ster-0.014
flower-0.014
Token"
Token ID1
Feature activation+1.63e-02

Pos logit contributions
 loud+0.000
 Lily+0.000
 If+0.000
sc+0.000
 traffic+0.000
Neg logit contributions
ich-0.000
opsy-0.000
field-0.000
flower-0.000
ster-0.000
Token flowers
Token ID12734
Feature activation+3.44e-02

Pos logit contributions
ich+0.001
opsy+0.001
field+0.001
ster+0.001
sters+0.001
Neg logit contributions
sc-0.001
 tant-0.001
 baths-0.001
 videos-0.001
 bang-0.001
Token.
Token ID13
Feature activation-1.31e-03

Pos logit contributions
ich+0.079
opsy+0.071
field+0.068
ster+0.065
sters+0.061
Neg logit contributions
sc-0.043
 tant-0.043
 baths-0.042
 videos-0.040
 tests-0.040
Token M
Token ID337
Feature activation-1.26e-03

Pos logit contributions
 baths+0.001
sc+0.001
 tant+0.001
 videos+0.001
 tests+0.001
Neg logit contributions
ich-0.003
opsy-0.003
field-0.003
ster-0.003
sters-0.003
Tokenimi
Token ID25236
Feature activation-2.69e-04

Pos logit contributions
 baths+0.002
 tant+0.002
 videos+0.002
 tests+0.002
sc+0.002
Neg logit contributions
ich-0.002
field-0.002
ster-0.002
opsy-0.002
-0.002
Token carried
Token ID5281
Feature activation-1.74e-02

Pos logit contributions
 baths+0.000
sc+0.000
 tests+0.000
 around+0.000
 videos+0.000
Neg logit contributions
ich-0.001
opsy-0.001
field-0.001
ster-0.000
iri-0.000
Token the
Token ID262
Feature activation-1.80e-02

Pos logit contributions
 tant+0.027
bench+0.026
 aids+0.025
riend+0.025
 crashes+0.024
Neg logit contributions
opsy-0.031
ich-0.030
field-0.027
ster-0.026
flower-0.025
Token honey
Token ID12498
Feature activation+5.99e-03

Pos logit contributions
sc+0.026
 baths+0.026
 tests+0.025
 around+0.024
 loud+0.024
Neg logit contributions
ich-0.037
opsy-0.033
field-0.031
ster-0.030
ipper-0.029
Token from
Token ID422
Feature activation-8.16e-03

Pos logit contributions
ich+0.014
opsy+0.013
field+0.012
ster+0.012
flower+0.011
Neg logit contributions
 tant-0.008
 baths-0.007
sc-0.007
 videos-0.007
 tests-0.007
Token one
Token ID530
Feature activation+3.14e-03

Pos logit contributions
sc+0.013
 tant+0.012
taker+0.011
 baths+0.011
head+0.010
Neg logit contributions
ich-0.017
field-0.016
opsy-0.016
ster-0.013
flower-0.013
Token flower
Token ID15061
Feature activation+3.66e-03

Pos logit contributions
ich+0.006
opsy+0.005
field+0.005
ster+0.005
flower+0.004
Neg logit contributions
 tant-0.005
sc-0.005
 baths-0.005
 videos-0.005
 tests-0.005
Token to
Token ID284
Feature activation+6.17e-03

Pos logit contributions
ich+0.009
opsy+0.008
field+0.008
ster+0.008
flower+0.007
Neg logit contributions
 tant-0.004
sc-0.004
 baths-0.004
 videos-0.004
 tests-0.004
Token the
Token ID262
Feature activation-3.48e-03

Pos logit contributions
sc+0.018
 tant+0.017
taker+0.015
igators+0.015
 videos+0.014
Neg logit contributions
ich-0.027
opsy-0.024
field-0.024
ster-0.022
flower-0.021
Token sand
Token ID6450
Feature activation+1.69e-02

Pos logit contributions
sc+0.005
 tant+0.005
 baths+0.005
 videos+0.004
 tests+0.004
Neg logit contributions
ich-0.008
opsy-0.007
field-0.007
ster-0.006
flower-0.006
Token castle
Token ID16669
Feature activation-2.02e-02

Pos logit contributions
ich+0.036
opsy+0.032
field+0.031
ster+0.030
flower+0.028
Neg logit contributions
 tant-0.025
sc-0.024
 baths-0.024
 videos-0.023
 tests-0.023
Token.
Token ID13
Feature activation-1.21e-03

Pos logit contributions
 tant+0.035
sc+0.032
 baths+0.032
 videos+0.032
 bang+0.031
Neg logit contributions
ich-0.039
field-0.034
opsy-0.032
ster-0.031
flower-0.029
Token Mama
Token ID40084
Feature activation+6.43e-03

Pos logit contributions
 tant+0.001
sc+0.001
 baths+0.001
 videos+0.001
 tests+0.001
Neg logit contributions
ich-0.003
opsy-0.003
field-0.003
ster-0.002
flower-0.002
Token and
Token ID290
Feature activation-3.93e-02

Pos logit contributions
ich+0.013
opsy+0.012
field+0.011
ster+0.011
flower+0.010
Neg logit contributions
 tant-0.010
sc-0.010
 baths-0.010
 videos-0.009
 tests-0.009
Token Mia
Token ID32189
Feature activation+5.29e-03

Pos logit contributions
sc+0.055
 tant+0.052
 baths+0.049
 tests+0.049
 videos+0.048
Neg logit contributions
ich-0.087
opsy-0.082
field-0.077
ster-0.073
flower-0.070
Token stayed
Token ID9658
Feature activation+1.34e-02

Pos logit contributions
ich+0.012
opsy+0.010
field+0.010
ster+0.010
sters+0.009
Neg logit contributions
sc-0.007
 baths-0.007
 tant-0.007
 bang-0.007
 around-0.007
Token at
Token ID379
Feature activation+2.88e-04

Pos logit contributions
ich+0.034
opsy+0.031
field+0.029
ster+0.028
sters+0.027
Neg logit contributions
 tant-0.014
 baths-0.014
sc-0.014
 videos-0.013
 tests-0.013
Token the
Token ID262
Feature activation-2.05e-03

Pos logit contributions
ich+0.001
opsy+0.001
field+0.001
ster+0.001
flower+0.001
Neg logit contributions
sc-0.000
 tant-0.000
 baths-0.000
 videos-0.000
 tests-0.000
Token beach
Token ID10481
Feature activation+7.83e-03

Pos logit contributions
 tant+0.004
sc+0.004
 baths+0.004
 videos+0.004
 tests+0.004
Neg logit contributions
ich-0.003
opsy-0.003
field-0.003
ster-0.002
flower-0.002
Token this
Token ID428
Feature activation-1.04e-02

Pos logit contributions
 tant+0.005
sc+0.005
bench+0.004
 tests+0.004
 aids+0.004
Neg logit contributions
ich-0.005
opsy-0.004
field-0.004
ster-0.004
 wife-0.004
Token crib
Token ID48083
Feature activation-9.39e-03

Pos logit contributions
 tant+0.017
sc+0.016
 videos+0.015
 baths+0.015
 tests+0.015
Neg logit contributions
ich-0.020
field-0.018
opsy-0.017
ster-0.016
-0.016
Token is
Token ID318
Feature activation-3.20e-03

Pos logit contributions
 tant+0.017
 baths+0.017
sc+0.016
 videos+0.016
 tests+0.016
Neg logit contributions
ich-0.016
field-0.014
opsy-0.014
ster-0.013
flower-0.012
Token just
Token ID655
Feature activation+2.47e-02

Pos logit contributions
 tant+0.005
sc+0.004
 baths+0.004
 tests+0.004
 videos+0.004
Neg logit contributions
ich-0.007
opsy-0.006
field-0.006
ster-0.006
flower-0.005
Token as
Token ID355
Feature activation+2.15e-02

Pos logit contributions
ich+0.050
field+0.044
opsy+0.043
ster+0.040
flower+0.040
Neg logit contributions
 tant-0.039
sc-0.037
 tests-0.032
 baths-0.032
iren-0.032
Token wide
Token ID3094
Feature activation-6.24e-02

Pos logit contributions
ich+0.047
opsy+0.042
field+0.042
ster+0.039
 wife+0.037
Neg logit contributions
 tant-0.030
sc-0.027
 aids-0.026
aled-0.025
 bang-0.025
Token as
Token ID355
Feature activation+1.32e-02

Pos logit contributions
 tant+0.116
sc+0.109
 aids+0.107
 rage+0.104
 tests+0.100
Neg logit contributions
ich-0.100
ster-0.082
opsy-0.082
field-0.081
sters-0.079
Token my
Token ID616
Feature activation-6.85e-03

Pos logit contributions
ich+0.029
opsy+0.025
field+0.025
ster+0.023
sters+0.021
Neg logit contributions
 tant-0.020
sc-0.018
 aids-0.017
 baths-0.017
 bang-0.016
Token old
Token ID1468
Feature activation-4.61e-02

Pos logit contributions
sc+0.010
 tant+0.010
 videos+0.009
igators+0.009
 bang+0.009
Neg logit contributions
ich-0.014
opsy-0.013
field-0.012
ster-0.011
 wife-0.011
Token one
Token ID530
Feature activation-6.38e-03

Pos logit contributions
sc+0.065
 tant+0.063
 videos+0.058
 baths+0.058
 bang+0.057
Neg logit contributions
ich-0.095
field-0.086
opsy-0.085
ster-0.080
flower-0.076
Token,"
Token ID553
Feature activation+1.72e-02

Pos logit contributions
 tant+0.010
 baths+0.010
sc+0.010
 videos+0.010
 tests+0.009
Neg logit contributions
ich-0.012
field-0.011
opsy-0.011
ster-0.010
flower-0.009
TokenJimmy
Token ID40335
Feature activation+1.22e-02

Pos logit contributions
ich+0.021
opsy+0.018
field+0.017
ster+0.016
sters+0.015
Neg logit contributions
sc-0.021
 baths-0.020
 tant-0.020
 videos-0.019
 tests-0.019
Token was
Token ID373
Feature activation-8.21e-03

Pos logit contributions
ich+0.026
opsy+0.023
field+0.022
ster+0.021
sters+0.020
Neg logit contributions
 tant-0.017
sc-0.017
 baths-0.017
 videos-0.016
 tests-0.016
Token a
Token ID257
Feature activation+5.09e-03

Pos logit contributions
sc+0.014
 tant+0.014
 baths+0.013
igators+0.012
 tests+0.012
Neg logit contributions
ich-0.016
opsy-0.014
field-0.014
flower-0.012
ster-0.012
Token 3
Token ID513
Feature activation-4.93e-02

Pos logit contributions
ich+0.013
opsy+0.012
field+0.011
ster+0.011
sters+0.010
Neg logit contributions
 tant-0.005
sc-0.005
 baths-0.005
 videos-0.005
 tests-0.005
Token-
Token ID12
Feature activation-6.26e-02

Pos logit contributions
sc+0.068
 tant+0.064
 baths+0.063
 tests+0.062
 videos+0.059
Neg logit contributions
ich-0.106
opsy-0.096
field-0.089
ster-0.088
flower-0.084
Tokenyear
Token ID1941
Feature activation-8.56e-02

Pos logit contributions
 baths+0.077
 tant+0.074
 videos+0.074
 bang+0.073
sc+0.072
Neg logit contributions
ich-0.144
opsy-0.131
ster-0.122
illa-0.119
field-0.115
Token-
Token ID12
Feature activation-5.75e-02

Pos logit contributions
sc+0.138
 bang+0.125
 tant+0.125
 videos+0.125
 baths+0.122
Neg logit contributions
ich-0.169
opsy-0.152
ster-0.147
field-0.139
 wife-0.132
Tokenold
Token ID727
Feature activation+1.46e-02

Pos logit contributions
 tant+0.085
 bang+0.084
 baths+0.084
sc+0.083
 videos+0.081
Neg logit contributions
ich-0.118
opsy-0.106
ster-0.098
field-0.094
illa-0.094
Token who
Token ID508
Feature activation+1.19e-02

Pos logit contributions
ich+0.030
opsy+0.026
field+0.025
ster+0.024
sters+0.022
Neg logit contributions
 tant-0.022
sc-0.022
 baths-0.022
 videos-0.021
 tests-0.021
Token loved
Token ID6151
Feature activation+4.84e-03

Pos logit contributions
ich+0.019
opsy+0.017
field+0.017
ster+0.015
+0.014
Neg logit contributions
 tant-0.023
sc-0.022
 videos-0.021
 baths-0.021
igators-0.020
Token to
Token ID284
Feature activation+2.00e-02

Pos logit contributions
ich+0.011
field+0.009
opsy+0.009
ster+0.008
flower+0.008
Neg logit contributions
sc-0.007
 tant-0.006
taker-0.006
aled-0.006
igators-0.006
Token,
Token ID11
Feature activation+2.63e-03

Pos logit contributions
 tant+0.045
sc+0.042
 baths+0.041
aled+0.040
igators+0.040
Neg logit contributions
ich-0.041
field-0.035
opsy-0.035
ster-0.033
ama-0.032
Token Tim
Token ID5045
Feature activation+2.47e-02

Pos logit contributions
ich+0.007
opsy+0.006
field+0.006
ster+0.005
flower+0.005
Neg logit contributions
 tant-0.003
sc-0.003
 baths-0.003
 tests-0.003
 videos-0.002
Token took
Token ID1718
Feature activation-5.49e-03

Pos logit contributions
ich+0.059
opsy+0.053
field+0.051
ster+0.048
sters+0.046
Neg logit contributions
sc-0.030
 baths-0.029
 tant-0.028
 bang-0.027
 videos-0.027
Token the
Token ID262
Feature activation-1.93e-02

Pos logit contributions
sc+0.010
 tant+0.010
riend+0.010
bench+0.009
 ult+0.009
Neg logit contributions
ich-0.008
opsy-0.008
ster-0.007
 wife-0.006
ese-0.006
Token monster
Token ID9234
Feature activation-2.29e-02

Pos logit contributions
sc+0.029
 tant+0.029
 baths+0.028
igators+0.027
 videos+0.027
Neg logit contributions
ich-0.040
ster-0.034
opsy-0.033
field-0.032
flower-0.029
Token-
Token ID12
Feature activation-6.82e-02

Pos logit contributions
 tant+0.030
sc+0.029
 baths+0.029
 tests+0.028
 videos+0.028
Neg logit contributions
ich-0.050
opsy-0.043
ster-0.043
field-0.043
flower-0.040
Tokench
Token ID354
Feature activation-3.43e-02

Pos logit contributions
 tant+0.113
 videos+0.112
 baths+0.110
sc+0.106
 bang+0.106
Neg logit contributions
ich-0.129
opsy-0.110
ster-0.105
field-0.102
flower-0.098
Tokenaser
Token ID6005
Feature activation-1.61e-02

Pos logit contributions
 tant+0.048
 tests+0.046
sc+0.046
 videos+0.045
 baths+0.044
Neg logit contributions
ich-0.073
opsy-0.064
field-0.060
ster-0.059
pper-0.057
Token to
Token ID284
Feature activation+3.21e-03

Pos logit contributions
 tant+0.027
 baths+0.026
 tests+0.026
 videos+0.026
sc+0.025
Neg logit contributions
ich-0.029
field-0.025
ster-0.025
opsy-0.024
flower-0.022
Token bed
Token ID3996
Feature activation-2.48e-02

Pos logit contributions
ich+0.007
opsy+0.006
field+0.006
ster+0.006
pper+0.005
Neg logit contributions
sc-0.005
 tant-0.005
 baths-0.004
igators-0.004
taker-0.004
Token with
Token ID351
Feature activation-3.64e-03

Pos logit contributions
igators+0.042
sc+0.042
 tant+0.041
 baths+0.041
 tests+0.040
Neg logit contributions
ich-0.046
field-0.039
ster-0.038
opsy-0.037
sters-0.033
Token.
Token ID13
Feature activation+4.38e-04

Pos logit contributions
sc+0.026
 tant+0.025
 baths+0.025
 videos+0.024
 tests+0.023
Neg logit contributions
ich-0.052
opsy-0.048
field-0.045
ster-0.044
sters-0.041
Token Every
Token ID3887
Feature activation+1.79e-02

Pos logit contributions
ich+0.001
field+0.001
opsy+0.001
+0.001
ster+0.001
Neg logit contributions
 tant-0.001
sc-0.001
 baths-0.000
 tests-0.000
taker-0.000
Token day
Token ID1110
Feature activation-2.03e-02

Pos logit contributions
ich+0.036
opsy+0.034
field+0.033
ster+0.030
flower+0.028
Neg logit contributions
 tant-0.028
 videos-0.026
sc-0.026
 tests-0.026
 baths-0.026
Token two
Token ID734
Feature activation-5.33e-03

Pos logit contributions
 tant+0.030
sc+0.029
 baths+0.027
 videos+0.027
 tests+0.027
Neg logit contributions
ich-0.042
opsy-0.038
field-0.036
ster-0.035
-0.033
Token 3
Token ID513
Feature activation-5.00e-02

Pos logit contributions
 tant+0.008
sc+0.008
 baths+0.008
 videos+0.007
 tests+0.007
Neg logit contributions
ich-0.011
opsy-0.010
field-0.010
ster-0.009
flower-0.009
Token-
Token ID12
Feature activation-6.63e-02

Pos logit contributions
sc+0.061
 tant+0.060
 baths+0.058
 tests+0.056
 videos+0.056
Neg logit contributions
ich-0.116
opsy-0.105
field-0.099
ster-0.098
sters-0.092
Tokenyear
Token ID1941
Feature activation-9.19e-02

Pos logit contributions
 tant+0.063
 baths+0.061
sc+0.059
 tests+0.056
 videos+0.056
Neg logit contributions
ich-0.172
opsy-0.158
field-0.149
ster-0.148
illa-0.142
Token-
Token ID12
Feature activation-6.15e-02

Pos logit contributions
sc+0.148
 tant+0.133
 bang+0.132
 tests+0.131
 videos+0.131
Neg logit contributions
ich-0.186
opsy-0.165
ster-0.158
field-0.146
sters-0.146
Tokenold
Token ID727
Feature activation+6.50e-03

Pos logit contributions
 tant+0.082
sc+0.078
 baths+0.078
 bang+0.075
 videos+0.074
Neg logit contributions
ich-0.137
opsy-0.124
field-0.116
ster-0.115
illa-0.109
Token children
Token ID1751
Feature activation+7.72e-03

Pos logit contributions
ich+0.014
opsy+0.013
field+0.012
ster+0.011
flower+0.011
Neg logit contributions
sc-0.009
 tant-0.009
 baths-0.009
 videos-0.009
 tests-0.008
Token enjoyed
Token ID8359
Feature activation+3.33e-03

Pos logit contributions
ich+0.015
opsy+0.014
field+0.013
ster+0.012
flower+0.012
Neg logit contributions
 tant-0.012
sc-0.012
 baths-0.012
 videos-0.011
 tests-0.011
Token but
Token ID475
Feature activation+1.72e-04

Pos logit contributions
 tant+0.051
igators+0.050
 baths+0.047
igator+0.046
 aids+0.046
Neg logit contributions
ich-0.039
ster-0.034
field-0.034
opsy-0.032
ble-0.030
Token the
Token ID262
Feature activation-3.81e-03

Pos logit contributions
ich+0.000
opsy+0.000
field+0.000
ster+0.000
+0.000
Neg logit contributions
sc-0.000
 tant-0.000
 videos-0.000
 baths-0.000
 tests-0.000
Token words
Token ID2456
Feature activation-1.04e-02

Pos logit contributions
 tant+0.006
sc+0.006
 baths+0.006
 videos+0.006
 tests+0.006
Neg logit contributions
ich-0.007
opsy-0.006
field-0.006
ster-0.006
flower-0.005
Token were
Token ID547
Feature activation-1.10e-02

Pos logit contributions
 baths+0.018
 tant+0.018
sc+0.018
 videos+0.017
igsaw+0.017
Neg logit contributions
ich-0.017
field-0.015
opsy-0.015
ster-0.014
flower-0.013
Token too
Token ID1165
Feature activation+5.30e-03

Pos logit contributions
sc+0.017
 tant+0.016
 baths+0.015
head+0.014
|+0.014
Neg logit contributions
ich-0.023
field-0.020
opsy-0.019
ster-0.018
flower-0.018
Token complicated
Token ID8253
Feature activation-6.40e-02

Pos logit contributions
ich+0.013
opsy+0.012
field+0.011
ster+0.011
+0.011
Neg logit contributions
sc-0.006
 baths-0.005
 tant-0.005
aled-0.005
igators-0.005
Token for
Token ID329
Feature activation-2.66e-02

Pos logit contributions
 tant+0.130
igators+0.118
 baths+0.117
igator+0.116
sc+0.116
Neg logit contributions
ich-0.095
ster-0.080
field-0.077
sters-0.072
opsy-0.069
Token him
Token ID683
Feature activation-1.99e-02

Pos logit contributions
sc+0.036
 tant+0.035
 baths+0.030
igators+0.029
 tests+0.029
Neg logit contributions
ich-0.059
opsy-0.054
field-0.053
ster-0.050
sters-0.047
Token.
Token ID13
Feature activation-5.10e-03

Pos logit contributions
 tant+0.030
sc+0.030
 baths+0.028
 videos+0.028
igators+0.027
Neg logit contributions
ich-0.041
opsy-0.035
field-0.035
ster-0.034
sters-0.031
Token
Token ID198
Feature activation-1.85e-03

Pos logit contributions
 tant+0.006
sc+0.006
 baths+0.006
 tests+0.005
 bang+0.005
Neg logit contributions
ich-0.012
opsy-0.011
field-0.011
ster-0.010
-0.010
Token
Token ID198
Feature activation+6.95e-03

Pos logit contributions
 tant+0.003
sc+0.003
 baths+0.003
 videos+0.002
 tests+0.002
Neg logit contributions
ich-0.004
opsy-0.004
field-0.003
ster-0.003
sters-0.003