TOP ACTIVATIONS
MAX = 9.343

" WHAT ARE YOU DO ING ?" Mom yells .
something new - there were tad p oles swimming around in
deep breath and shouted " ST OP !"
were four seasons in a year : winter , spring ,
and it was going on pic n ics !
, you little worm !" Terr ified , John ran away
in the castle for a year . Jimmy was delighted and
been replaced by a big ol ' bowl of rolling stones
. The sign said " ST OP ". "
there was a loud " P OP !" Rob stopped and
until he had a delicious batch of brown ies . When
'm never going to try ol ives only once again !"
go to the land of Imp ressive Things .
his socks away in a timely manner . And each time
sandwiches and mini packets of cris ps . The children had
she saw a tree with ol ives growing on it .
came by and ate a french fry from his hands .
ICK ! AND YOU WILL GET IN TR OU BLE !"
time until she achieved a lot of great things .
could see lots of av oc ados that the supplier had

MIN ACTIVATIONS
MIN = -6.938

man . They loved their snow man . They cried .
. And we love our snow man . He was a
Lily was sad because her snow man was disappearing . She
happy . She likes her snow man . The
. They still love their snow man . <|endoftext|> L ily
kind . You love your snow men and each other .
Ben smiled and hugged their snow man . They were happy
nodded . He liked their snow baby . He wanted to
back . They missed their snow man very much . They
They hugged their snow man and ran inside to
They laughed and hugged their snow man . They thought he
smiled and played with their snow man until it was time
know you loved your blue snow man . But you know
are very happy with their snow man . But
They were happy with their snow man . But
They hugged their snow man and said goodbye .
were very happy with their snow man . But
smiles . She thinks the snow man is happy now .
were very happy with their snow man . "
were very happy with their snow man . But

INTERVAL 5.273 - 9.343
CONTAINS 0.018%

new friends and had a lot of fun . He pretended
tricks . They have a lot of fun . They laugh
, please ask me before you add anything . And be
what was around the river â € ™ s bend .
the me adow as the Pers istent Lamb - the one

INTERVAL 1.202 - 5.273
CONTAINS 17.386%

looking at him with curious eyes . The man
with the children for a while , but then it saw
upon a time , there was a big bear . The
. She liked to watch them swim and qu ack and
Gab ri ella , would you like to come visit me

INTERVAL -2.868 - 1.202
CONTAINS 80.724%

. They take the train off the track . They put
toy . It is a yellow brain . It can make
pretty necklace was ruined , but her friends told her it
at all the pretty flowers . One day , she saw
Can I grab it too ?" J ill said

INTERVAL -6.938 - -2.868
CONTAINS 1.872%

home , and Emma knew that it would bring them a
. Max loved to play outside in the sunshine . One
at small bear and said : " We can share the
. The bear and rabbit loved each other very much ,
back to her shadow and started to play with it .
Token
Token ID198
Feature activation+6.46e-01

Pos logit contributions
burn+0.004
 blowing+0.004
 shining+0.003
 daddy+0.003
 waving+0.003
Neg logit contributions
 ounces-0.007
hell-0.007
izards-0.007
ets-0.007
ocol-0.007
Token"
Token ID1
Feature activation+2.94e+00

Pos logit contributions
 ounces+0.021
ets+0.020
hell+0.019
izards+0.019
ocol+0.019
Neg logit contributions
 blowing-0.016
burn-0.016
 daddy-0.014
 waving-0.013
 shining-0.013
TokenWHAT
Token ID32971
Feature activation+4.90e+00

Pos logit contributions
 ounces+0.099
ets+0.092
ocol+0.090
hell+0.089
 pounds+0.089
Neg logit contributions
 blowing-0.071
burn-0.065
 daddy-0.062
 waving-0.060
 neighborhood-0.059
Token ARE
Token ID15986
Feature activation+5.91e+00

Pos logit contributions
 ounces+0.181
ocol+0.165
ets+0.163
 pounds+0.162
 dollars+0.154
Neg logit contributions
burn-0.104
 blowing-0.098
 daddy-0.092
 grandma-0.088
 neighborhood-0.087
Token YOU
Token ID7013
Feature activation+5.60e+00

Pos logit contributions
 ounces+0.177
ets+0.171
 pounds+0.157
 dollars+0.151
bridge+0.148
Neg logit contributions
 blowing-0.158
burn-0.152
 daddy-0.151
 mom-0.148
 grandma-0.143
Token DO
Token ID8410
Feature activation+9.34e+00

Pos logit contributions
 ounces+0.192
ets+0.177
 pounds+0.176
ocol+0.174
 dollars+0.171
Neg logit contributions
 blowing-0.138
burn-0.132
 waving-0.117
 daddy-0.114
 blew-0.114
TokenING
Token ID2751
Feature activation+2.60e+00

Pos logit contributions
 ounces+0.307
 pounds+0.277
ocol+0.270
 dollars+0.258
ets+0.246
Neg logit contributions
 blowing-0.228
burn-0.220
 daddy-0.208
 mom-0.206
 grandma-0.205
Token?"
Token ID1701
Feature activation+2.11e+00

Pos logit contributions
 ounces+0.088
ets+0.087
 pounds+0.080
izards+0.078
 dollars+0.078
Neg logit contributions
burn-0.068
 blowing-0.065
 daddy-0.060
 mom-0.060
 grandma-0.056
Token Mom
Token ID11254
Feature activation-2.13e+00

Pos logit contributions
 ounces+0.084
ets+0.081
 pounds+0.078
hell+0.078
ocol+0.077
Neg logit contributions
 blowing-0.039
burn-0.036
 daddy-0.032
 waving-0.030
 neighborhood-0.030
Token yells
Token ID42675
Feature activation+4.44e+00

Pos logit contributions
 blowing+0.060
burn+0.059
 daddy+0.053
 neighborhood+0.051
 shining+0.050
Neg logit contributions
 ounces-0.063
ets-0.060
izards-0.057
ocol-0.056
 pounds-0.056
Token.
Token ID13
Feature activation+4.85e-01

Pos logit contributions
 ounces+0.171
ets+0.154
 pounds+0.153
ocol+0.152
hell+0.148
Neg logit contributions
 blowing-0.094
 crying-0.088
burn-0.088
 daddy-0.087
 mom-0.084
Token something
Token ID1223
Feature activation+2.20e+00

Pos logit contributions
 ounces+0.050
ets+0.048
ocol+0.046
 pounds+0.045
hell+0.045
Neg logit contributions
 blowing-0.031
burn-0.028
 daddy-0.026
 waving-0.025
 neighborhood-0.025
Token new
Token ID649
Feature activation-5.24e-01

Pos logit contributions
 ounces+0.078
ets+0.074
ocol+0.071
 pounds+0.070
izards+0.070
Neg logit contributions
 blowing-0.051
burn-0.046
 daddy-0.043
 waving-0.042
 shining-0.041
Token-
Token ID12
Feature activation+2.00e+00

Pos logit contributions
 blowing+0.010
burn+0.008
 waving+0.008
 daddy+0.008
 neighborhood+0.008
Neg logit contributions
 ounces-0.021
ocol-0.020
ets-0.020
 dollars-0.019
 pounds-0.019
Token there
Token ID612
Feature activation+7.28e-04

Pos logit contributions
 ounces+0.053
ets+0.050
 pounds+0.048
ocol+0.048
 dollars+0.047
Neg logit contributions
 blowing-0.064
burn-0.059
 shining-0.054
 daddy-0.054
 leaning-0.054
Token were
Token ID547
Feature activation+1.77e+00

Pos logit contributions
 ounces+0.000
ets+0.000
ocol+0.000
 pounds+0.000
 dollars+0.000
Neg logit contributions
 blowing-0.000
burn-0.000
 daddy-0.000
 waving-0.000
 neighborhood-0.000
Token tad
Token ID36264
Feature activation+7.74e+00

Pos logit contributions
 ounces+0.063
ets+0.060
 pounds+0.058
ocol+0.057
hell+0.057
Neg logit contributions
 blowing-0.040
burn-0.038
 daddy-0.034
 neighborhood-0.033
 waving-0.033
Tokenp
Token ID79
Feature activation+1.78e+00

Pos logit contributions
 ounces+0.184
 pounds+0.170
ocol+0.169
 dollars+0.167
ocket+0.155
Neg logit contributions
 blowing-0.251
 spinning-0.205
 leaning-0.205
 singing-0.204
 shining-0.204
Tokenoles
Token ID4316
Feature activation+2.54e+00

Pos logit contributions
 ounces+0.054
ets+0.048
 dollars+0.047
 pounds+0.047
ocol+0.047
Neg logit contributions
 blowing-0.053
burn-0.048
 waving-0.044
 shining-0.043
 daddy-0.043
Token swimming
Token ID14899
Feature activation+6.93e-01

Pos logit contributions
 ounces+0.092
ets+0.085
ocol+0.083
 pounds+0.082
hell+0.082
Neg logit contributions
 blowing-0.060
burn-0.054
 waving-0.050
 leaning-0.048
 daddy-0.048
Token around
Token ID1088
Feature activation-1.10e+00

Pos logit contributions
 ounces+0.029
ocol+0.027
 dollars+0.026
 pounds+0.026
ets+0.025
Neg logit contributions
 blowing-0.014
 shining-0.011
 next-0.011
 waving-0.010
burn-0.010
Token in
Token ID287
Feature activation-1.95e-01

Pos logit contributions
 blowing+0.024
 waving+0.019
 shining+0.019
 daddy+0.019
 spinning+0.019
Neg logit contributions
 ounces-0.043
ets-0.041
 dollars-0.040
hell-0.039
 pounds-0.039
Token deep
Token ID2769
Feature activation+7.14e-01

Pos logit contributions
 blowing+0.004
burn+0.004
 neighborhood+0.003
 daddy+0.003
 leaning+0.003
Neg logit contributions
 ounces-0.007
ets-0.007
hell-0.007
 pounds-0.007
ocol-0.007
Token breath
Token ID8033
Feature activation+1.44e+00

Pos logit contributions
 ounces+0.025
ets+0.024
 pounds+0.023
izards+0.023
hell+0.023
Neg logit contributions
 blowing-0.017
burn-0.016
 daddy-0.014
 waving-0.014
 shining-0.013
Token and
Token ID290
Feature activation+2.04e+00

Pos logit contributions
 ounces+0.060
ets+0.056
ocol+0.056
 pounds+0.055
izards+0.055
Neg logit contributions
 blowing-0.025
burn-0.023
 daddy-0.020
 waving-0.019
 shining-0.018
Token shouted
Token ID17293
Feature activation+3.62e+00

Pos logit contributions
 ounces+0.072
ets+0.069
 pounds+0.066
ocol+0.065
hell+0.065
Neg logit contributions
 blowing-0.045
burn-0.044
 daddy-0.039
 neighborhood-0.038
 waving-0.037
Token "
Token ID366
Feature activation+2.06e+00

Pos logit contributions
 ounces+0.148
ets+0.139
 pounds+0.135
 dollars+0.134
ocol+0.132
Neg logit contributions
 blowing-0.067
burn-0.059
 daddy-0.059
 waving-0.055
 spinning-0.054
TokenST
Token ID2257
Feature activation+7.28e+00

Pos logit contributions
 ounces+0.069
ets+0.065
 pounds+0.062
hell+0.062
ocol+0.062
Neg logit contributions
 blowing-0.050
burn-0.048
 daddy-0.044
 waving-0.042
 neighborhood-0.042
TokenOP
Token ID3185
Feature activation+4.18e+00

Pos logit contributions
 ounces+0.204
izards+0.187
 pounds+0.185
ets+0.184
 dollars+0.180
Neg logit contributions
burn-0.200
 blowing-0.193
tr-0.175
 leaning-0.173
 neighborhood-0.169
Token!"
Token ID2474
Feature activation+2.13e+00

Pos logit contributions
 ounces+0.087
ets+0.084
izards+0.082
ocol+0.080
hell+0.076
Neg logit contributions
 blowing-0.153
burn-0.151
 spinning-0.134
 waving-0.133
 daddy-0.133
Token
Token ID220
Feature activation+3.33e-01

Pos logit contributions
 ounces+0.084
ets+0.081
 pounds+0.079
ocol+0.078
hell+0.077
Neg logit contributions
 blowing-0.040
burn-0.037
 daddy-0.034
 waving-0.031
 neighborhood-0.031
Token
Token ID198
Feature activation+1.32e+00

Pos logit contributions
 ounces+0.015
ets+0.014
hell+0.014
ocol+0.014
 pounds+0.014
Neg logit contributions
 blowing-0.004
burn-0.004
 daddy-0.003
 waving-0.003
 neighborhood-0.003
Token
Token ID198
Feature activation+1.63e+00

Pos logit contributions
 ounces+0.055
ets+0.052
hell+0.051
ocol+0.050
izards+0.050
Neg logit contributions
 blowing-0.022
burn-0.021
 daddy-0.017
 waving-0.016
 neighborhood-0.016
Token were
Token ID547
Feature activation+1.36e+00

Pos logit contributions
 blowing+0.037
burn+0.034
 daddy+0.031
 waving+0.029
 neighborhood+0.029
Neg logit contributions
 ounces-0.087
ets-0.084
ocol-0.081
 pounds-0.081
hell-0.080
Token four
Token ID1440
Feature activation+8.92e-01

Pos logit contributions
 ounces+0.049
ets+0.047
hell+0.046
ocol+0.045
 pounds+0.045
Neg logit contributions
 blowing-0.030
burn-0.028
 daddy-0.026
 waving-0.024
 neighborhood-0.024
Token seasons
Token ID7028
Feature activation+9.09e-01

Pos logit contributions
 ounces+0.030
ets+0.029
hell+0.028
izards+0.028
ocol+0.027
Neg logit contributions
 blowing-0.021
 daddy-0.018
 neighborhood-0.018
burn-0.018
 spinning-0.018
Token in
Token ID287
Feature activation-5.02e-01

Pos logit contributions
 ounces+0.032
ets+0.031
ocol+0.029
 pounds+0.029
hell+0.029
Neg logit contributions
 blowing-0.020
burn-0.019
 daddy-0.018
 neighborhood-0.017
 waving-0.016
Token a
Token ID257
Feature activation+2.37e+00

Pos logit contributions
 blowing+0.009
burn+0.008
 daddy+0.008
 waving+0.007
 neighborhood+0.007
Neg logit contributions
 ounces-0.020
ets-0.020
hell-0.019
 pounds-0.019
izards-0.019
Token year
Token ID614
Feature activation+7.21e+00

Pos logit contributions
 ounces+0.098
ets+0.095
izards+0.093
 pounds+0.092
ocol+0.091
Neg logit contributions
 blowing-0.038
burn-0.036
 neighborhood-0.034
 daddy-0.034
 waving-0.031
Token:
Token ID25
Feature activation-6.81e-01

Pos logit contributions
 ounces+0.283
ocol+0.257
izards+0.256
 pounds+0.255
ets+0.254
Neg logit contributions
 blowing-0.138
 daddy-0.119
 neighborhood-0.115
 waving-0.114
 leaning-0.113
Token winter
Token ID7374
Feature activation-9.41e-01

Pos logit contributions
 blowing+0.014
burn+0.013
 daddy+0.012
 waving+0.011
 neighborhood+0.011
Neg logit contributions
 ounces-0.026
ets-0.025
hell-0.024
ocol-0.024
 pounds-0.024
Token,
Token ID11
Feature activation+3.49e-01

Pos logit contributions
 blowing+0.019
burn+0.018
 daddy+0.016
 waving+0.015
 neighborhood+0.015
Neg logit contributions
 ounces-0.035
ets-0.034
 pounds-0.032
ocol-0.032
hell-0.032
Token spring
Token ID6076
Feature activation+5.77e-01

Pos logit contributions
 ounces+0.013
ets+0.012
ocol+0.012
 pounds+0.012
hell+0.012
Neg logit contributions
 blowing-0.007
burn-0.007
 daddy-0.006
 waving-0.006
 neighborhood-0.006
Token,
Token ID11
Feature activation-5.27e-02

Pos logit contributions
 ounces+0.021
ets+0.020
ocol+0.019
 pounds+0.019
hell+0.019
Neg logit contributions
 blowing-0.013
burn-0.012
 daddy-0.011
 waving-0.010
 neighborhood-0.010
Token and
Token ID290
Feature activation-6.02e-01

Pos logit contributions
 ounces+0.023
ets+0.022
ocol+0.022
 pounds+0.021
hell+0.021
Neg logit contributions
 blowing-0.014
burn-0.013
 daddy-0.012
 waving-0.012
 neighborhood-0.011
Token it
Token ID340
Feature activation-4.95e-01

Pos logit contributions
 blowing+0.013
burn+0.013
 daddy+0.011
 neighborhood+0.011
 waving+0.010
Neg logit contributions
 ounces-0.021
ets-0.021
izards-0.020
hell-0.019
 pounds-0.019
Token was
Token ID373
Feature activation+1.01e-01

Pos logit contributions
burn+0.010
 blowing+0.009
 daddy+0.008
 neighborhood+0.008
 waving+0.008
Neg logit contributions
 ounces-0.018
ets-0.018
hell-0.017
izards-0.017
ils-0.017
Token going
Token ID1016
Feature activation-2.81e-01

Pos logit contributions
 ounces+0.004
ets+0.004
 pounds+0.003
hell+0.003
izards+0.003
Neg logit contributions
burn-0.002
 blowing-0.002
 neighborhood-0.002
 daddy-0.002
 waving-0.002
Token on
Token ID319
Feature activation+7.70e-01

Pos logit contributions
 blowing+0.005
burn+0.005
 daddy+0.004
 neighborhood+0.004
 waving+0.004
Neg logit contributions
 ounces-0.011
ets-0.011
hell-0.010
 pounds-0.010
izards-0.010
Token pic
Token ID8301
Feature activation+7.12e+00

Pos logit contributions
 ounces+0.027
ets+0.026
hell+0.025
 pounds+0.025
izards+0.025
Neg logit contributions
burn-0.016
 blowing-0.016
 daddy-0.014
 neighborhood-0.013
 waving-0.013
Tokenn
Token ID77
Feature activation+2.19e+00

Pos logit contributions
 ounces+0.126
ets+0.119
hell+0.109
 pounds+0.101
izards+0.100
Neg logit contributions
 blowing-0.280
burn-0.280
 daddy-0.267
 neighborhood-0.257
 waving-0.254
Tokenics
Token ID873
Feature activation+5.41e-01

Pos logit contributions
ets+0.072
 ounces+0.070
hell+0.069
izards+0.067
 pounds+0.065
Neg logit contributions
burn-0.050
 blowing-0.049
 daddy-0.046
 neighborhood-0.044
 shining-0.043
Token!
Token ID0
Feature activation+4.18e-01

Pos logit contributions
 ounces+0.020
ocol+0.019
ets+0.018
 pounds+0.018
 dollars+0.018
Neg logit contributions
 blowing-0.012
burn-0.011
 daddy-0.010
 waving-0.010
 neighborhood-0.010
Token
Token ID198
Feature activation-4.17e-01

Pos logit contributions
 ounces+0.018
ets+0.017
 pounds+0.017
ocol+0.017
hell+0.017
Neg logit contributions
 blowing-0.006
burn-0.006
 daddy-0.005
 waving-0.005
 neighborhood-0.005
Token
Token ID198
Feature activation+6.25e-01

Pos logit contributions
burn+0.007
 blowing+0.007
 daddy+0.006
 waving+0.006
 leaning+0.005
Neg logit contributions
 ounces-0.016
ets-0.016
hell-0.016
izards-0.016
 pounds-0.015
Token,
Token ID11
Feature activation-3.26e-01

Pos logit contributions
 blowing+0.034
 daddy+0.032
 mom+0.031
 next+0.030
 waving+0.029
Neg logit contributions
 ounces-0.062
ets-0.059
hell-0.059
izards-0.059
 pounds-0.059
Token you
Token ID345
Feature activation+2.91e+00

Pos logit contributions
 blowing+0.008
 daddy+0.007
burn+0.007
 waving+0.007
 mom+0.007
Neg logit contributions
 ounces-0.011
ets-0.011
hell-0.010
izards-0.010
 pounds-0.010
Token little
Token ID1310
Feature activation-1.43e+00

Pos logit contributions
 ounces+0.101
ocol+0.098
 pounds+0.096
ets+0.092
izards+0.092
Neg logit contributions
 blowing-0.067
burn-0.063
 daddy-0.061
 waving-0.057
 blew-0.056
Token worm
Token ID23849
Feature activation+2.63e-01

Pos logit contributions
 blowing+0.031
 daddy+0.029
burn+0.029
 waving+0.026
 neighborhood+0.026
Neg logit contributions
 ounces-0.051
ets-0.051
hell-0.050
izards-0.049
ocol-0.047
Token!"
Token ID2474
Feature activation+1.15e+00

Pos logit contributions
 ounces+0.008
ocol+0.008
 pounds+0.007
ets+0.007
izards+0.007
Neg logit contributions
 blowing-0.007
burn-0.007
 daddy-0.007
 waving-0.007
 crying-0.006
Token Terr
Token ID38859
Feature activation+6.97e+00

Pos logit contributions
 ounces+0.051
ets+0.050
 pounds+0.050
ocol+0.049
izards+0.048
Neg logit contributions
 blowing-0.015
 daddy-0.014
burn-0.013
 waving-0.012
 mom-0.011
Tokenified
Token ID1431
Feature activation+6.32e-01

Pos logit contributions
 ounces+0.158
ets+0.153
 pounds+0.148
hell+0.143
 dollars+0.140
Neg logit contributions
 blowing-0.234
burn-0.224
 leaning-0.206
 waving-0.206
 crying-0.203
Token,
Token ID11
Feature activation+4.16e-01

Pos logit contributions
 ounces+0.030
ets+0.029
hell+0.028
 pounds+0.028
izards+0.027
Neg logit contributions
 blowing-0.007
 daddy-0.007
 crying-0.006
 waving-0.006
 mom-0.005
Token John
Token ID1757
Feature activation-1.47e+00

Pos logit contributions
 ounces+0.018
ets+0.017
 pounds+0.016
izards+0.016
ocol+0.016
Neg logit contributions
 blowing-0.007
 daddy-0.006
burn-0.006
 waving-0.005
 leaning-0.005
Token ran
Token ID4966
Feature activation+2.25e+00

Pos logit contributions
 blowing+0.029
burn+0.026
 daddy+0.023
 waving+0.023
 leaning+0.022
Neg logit contributions
 ounces-0.057
ocol-0.055
ets-0.054
 pounds-0.053
izards-0.053
Token away
Token ID1497
Feature activation+7.55e-01

Pos logit contributions
 ounces+0.076
 pounds+0.071
ocol+0.071
ets+0.069
izards+0.069
Neg logit contributions
 blowing-0.059
burn-0.054
 waving-0.050
 daddy-0.050
 spinning-0.049
Token in
Token ID287
Feature activation-6.87e-01

Pos logit contributions
 blowing+0.013
burn+0.011
 next+0.011
 daddy+0.010
 waving+0.010
Neg logit contributions
 ounces-0.030
ets-0.028
 pounds-0.027
ocol-0.027
hell-0.027
Token the
Token ID262
Feature activation+1.67e+00

Pos logit contributions
 blowing+0.012
burn+0.011
 daddy+0.011
 waving+0.010
 neighborhood+0.010
Neg logit contributions
 ounces-0.028
ets-0.027
hell-0.026
 pounds-0.026
izards-0.026
Token castle
Token ID16669
Feature activation+1.33e+00

Pos logit contributions
 ounces+0.068
ets+0.065
 pounds+0.063
ocol+0.063
hell+0.062
Neg logit contributions
 blowing-0.029
burn-0.027
 daddy-0.024
 neighborhood-0.023
 waving-0.023
Token for
Token ID329
Feature activation+3.26e+00

Pos logit contributions
 ounces+0.048
ocol+0.046
 pounds+0.044
ets+0.044
izards+0.044
Neg logit contributions
 blowing-0.029
 daddy-0.026
burn-0.026
 neighborhood-0.026
 waving-0.025
Token a
Token ID257
Feature activation+9.37e-01

Pos logit contributions
ets+0.146
 ounces+0.146
 dollars+0.139
hell+0.139
 pounds+0.137
Neg logit contributions
 blowing-0.042
 daddy-0.035
 waving-0.032
 grandma-0.032
 mom-0.032
Token year
Token ID614
Feature activation+6.96e+00

Pos logit contributions
 ounces+0.035
ets+0.033
ocol+0.032
izards+0.032
 pounds+0.032
Neg logit contributions
 blowing-0.020
burn-0.019
 daddy-0.017
 waving-0.016
 neighborhood-0.016
Token.
Token ID13
Feature activation+6.78e-01

Pos logit contributions
 ounces+0.255
izards+0.242
ocol+0.241
ets+0.234
hell+0.228
Neg logit contributions
 blowing-0.147
 daddy-0.134
 waving-0.126
 neighborhood-0.125
 next-0.124
Token Jimmy
Token ID12963
Feature activation-1.99e+00

Pos logit contributions
 ounces+0.026
ets+0.025
ocol+0.025
izards+0.024
hell+0.024
Neg logit contributions
 daddy-0.012
 blowing-0.012
 neighborhood-0.012
burn-0.011
 grandma-0.011
Token was
Token ID373
Feature activation-7.35e-01

Pos logit contributions
 blowing+0.032
burn+0.030
 daddy+0.025
 neighborhood+0.024
 waving+0.024
Neg logit contributions
 ounces-0.084
ets-0.081
 pounds-0.077
hell-0.077
ocol-0.077
Token delighted
Token ID20707
Feature activation+3.23e-01

Pos logit contributions
burn+0.021
 blowing+0.020
 daddy+0.018
 neighborhood+0.018
 shining+0.017
Neg logit contributions
 ounces-0.021
ets-0.020
izards-0.019
 dollars-0.019
hell-0.019
Token and
Token ID290
Feature activation-1.72e+00

Pos logit contributions
 ounces+0.013
ets+0.012
ocol+0.012
 pounds+0.012
izards+0.012
Neg logit contributions
 blowing-0.006
burn-0.005
 daddy-0.005
 waving-0.005
 neighborhood-0.005
Token been
Token ID587
Feature activation+8.10e-01

Pos logit contributions
 ounces+0.048
ets+0.046
ocol+0.045
izards+0.045
 pounds+0.044
Neg logit contributions
 blowing-0.025
burn-0.023
 daddy-0.022
 shining-0.020
 waving-0.020
Token replaced
Token ID6928
Feature activation-1.69e-01

Pos logit contributions
 ounces+0.031
ets+0.030
hell+0.028
ocol+0.028
izards+0.028
Neg logit contributions
 blowing-0.016
burn-0.015
 daddy-0.014
 waving-0.013
 neighborhood-0.013
Token by
Token ID416
Feature activation+4.94e-01

Pos logit contributions
 blowing+0.003
burn+0.003
 daddy+0.003
 waving+0.003
 neighborhood+0.003
Neg logit contributions
 ounces-0.006
ets-0.006
ocol-0.006
 pounds-0.006
hell-0.006
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
 ounces+0.018
ets+0.018
 dollars+0.017
hell+0.017
ocol+0.017
Neg logit contributions
 blowing-0.011
burn-0.009
 daddy-0.009
 waving-0.008
 shining-0.008
Token big
Token ID1263
Feature activation+1.44e+00

Pos logit contributions
 ounces+0.045
ets+0.042
 pounds+0.041
hell+0.041
ocol+0.041
Neg logit contributions
 blowing-0.026
burn-0.025
 daddy-0.021
 waving-0.021
 neighborhood-0.021
Token ol
Token ID25776
Feature activation+6.84e+00

Pos logit contributions
 ounces+0.053
ets+0.050
izards+0.049
ocol+0.048
 pounds+0.048
Neg logit contributions
 blowing-0.031
burn-0.029
 daddy-0.028
 waving-0.026
 neighborhood-0.026
Token'
Token ID6
Feature activation+3.62e+00

Pos logit contributions
 ounces+0.147
bors+0.127
 risks+0.124
ocol+0.121
 pounds+0.118
Neg logit contributions
 blowing-0.235
burn-0.226
 leaning-0.216
 shining-0.215
 folding-0.214
Token bowl
Token ID9396
Feature activation+1.10e+00

Pos logit contributions
 ounces+0.115
izards+0.109
ocol+0.107
ets+0.106
hell+0.105
Neg logit contributions
 blowing-0.091
 daddy-0.087
 neighborhood-0.084
burn-0.082
 shining-0.079
Token of
Token ID286
Feature activation+1.66e+00

Pos logit contributions
 ounces+0.040
ocol+0.036
ets+0.036
izards+0.035
 risks+0.035
Neg logit contributions
 blowing-0.027
burn-0.023
 daddy-0.022
 shining-0.022
 leaning-0.022
Token rolling
Token ID10708
Feature activation+3.40e-01

Pos logit contributions
 ounces+0.052
ets+0.050
 dollars+0.047
izards+0.047
hell+0.045
Neg logit contributions
 blowing-0.045
 daddy-0.042
 shining-0.040
 waving-0.038
burn-0.038
Token stones
Token ID14966
Feature activation+8.07e-01

Pos logit contributions
 ounces+0.014
ocol+0.013
 dollars+0.013
ets+0.013
izards+0.012
Neg logit contributions
 blowing-0.006
burn-0.005
 shining-0.005
 daddy-0.005
 spinning-0.005
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
 ounces+0.085
ocol+0.079
ets+0.078
 pounds+0.076
hell+0.074
Neg logit contributions
 blowing-0.061
burn-0.053
 waving-0.051
 leaning-0.050
 daddy-0.049
Token The
Token ID383
Feature activation-1.15e+00

Pos logit contributions
 blowing+0.002
burn+0.002
 daddy+0.002
 neighborhood+0.002
 waving+0.002
Neg logit contributions
 ounces-0.004
ets-0.004
 pounds-0.004
ocol-0.004
hell-0.004
Token sign
Token ID1051
Feature activation+1.71e+00

Pos logit contributions
 blowing+0.030
burn+0.030
 daddy+0.027
 neighborhood+0.025
 waving+0.025
Neg logit contributions
 ounces-0.037
ets-0.035
 pounds-0.034
hell-0.033
 dollars-0.033
Token said
Token ID531
Feature activation+2.53e+00

Pos logit contributions
 ounces+0.053
ets+0.051
hell+0.051
 dollars+0.049
izards+0.049
Neg logit contributions
burn-0.044
 blowing-0.041
 daddy-0.037
 neighborhood-0.036
 waving-0.033
Token "
Token ID366
Feature activation+1.25e+00

Pos logit contributions
 ounces+0.109
ets+0.107
ocol+0.101
 pounds+0.101
izards+0.098
Neg logit contributions
 blowing-0.040
 daddy-0.034
burn-0.033
 waving-0.033
 shining-0.031
TokenST
Token ID2257
Feature activation+6.83e+00

Pos logit contributions
 ounces+0.041
ets+0.039
ocol+0.037
 pounds+0.037
hell+0.037
Neg logit contributions
 blowing-0.032
burn-0.030
 daddy-0.027
 neighborhood-0.026
 waving-0.026
TokenOP
Token ID3185
Feature activation+4.98e+00

Pos logit contributions
 ounces+0.189
 pounds+0.171
izards+0.167
hell+0.160
ly+0.160
Neg logit contributions
burn-0.194
 blowing-0.191
 neighborhood-0.174
tr-0.173
 leaning-0.171
Token".
Token ID1911
Feature activation+2.13e+00

Pos logit contributions
 ounces+0.100
ets+0.091
izards+0.091
ocol+0.088
hell+0.085
Neg logit contributions
 blowing-0.186
burn-0.182
 daddy-0.165
 waving-0.162
 leaning-0.162
Token
Token ID198
Feature activation+4.60e-02

Pos logit contributions
 ounces+0.090
 pounds+0.087
ets+0.085
 dollars+0.084
ocol+0.083
Neg logit contributions
 blowing-0.034
 mom-0.033
 neighborhood-0.031
 Mom-0.030
 daddy-0.030
Token
Token ID198
Feature activation+8.63e-01

Pos logit contributions
 ounces+0.002
ets+0.002
hell+0.002
izards+0.002
 pounds+0.002
Neg logit contributions
 blowing-0.001
burn-0.001
 daddy-0.000
 waving-0.000
 neighborhood-0.000
Token"
Token ID1
Feature activation+2.48e+00

Pos logit contributions
 ounces+0.029
ets+0.028
ocol+0.027
izards+0.027
 pounds+0.026
Neg logit contributions
 blowing-0.022
burn-0.020
 neighborhood-0.019
 daddy-0.018
 waving-0.018
Token there
Token ID612
Feature activation-1.31e+00

Pos logit contributions
 ounces+0.008
 pounds+0.007
ets+0.007
izards+0.007
ocol+0.007
Neg logit contributions
 blowing-0.006
burn-0.006
 neighborhood-0.005
 daddy-0.005
 waving-0.005
Token was
Token ID373
Feature activation+1.83e+00

Pos logit contributions
burn+0.023
 blowing+0.023
 daddy+0.019
 neighborhood+0.018
 waving+0.017
Neg logit contributions
 ounces-0.051
hell-0.048
ets-0.047
 pounds-0.046
ly-0.046
Token a
Token ID257
Feature activation+7.17e-01

Pos logit contributions
 ounces+0.059
 pounds+0.053
ets+0.053
hell+0.053
bridge+0.052
Neg logit contributions
burn-0.043
 blowing-0.043
 neighborhood-0.038
 daddy-0.037
 waving-0.035
Token loud
Token ID7812
Feature activation+1.20e+00

Pos logit contributions
 ounces+0.026
hell+0.024
 pounds+0.024
ets+0.024
ocol+0.023
Neg logit contributions
burn-0.015
 blowing-0.015
 daddy-0.012
 neighborhood-0.012
 waving-0.011
Token "
Token ID366
Feature activation+2.96e+00

Pos logit contributions
 ounces+0.038
ets+0.036
 pounds+0.035
izards+0.035
ocol+0.034
Neg logit contributions
 blowing-0.032
burn-0.030
 daddy-0.028
 waving-0.027
 spinning-0.027
TokenP
Token ID47
Feature activation+6.79e+00

Pos logit contributions
 ounces+0.092
ets+0.088
ocol+0.083
 pounds+0.083
hell+0.083
Neg logit contributions
 blowing-0.080
burn-0.077
 daddy-0.069
 waving-0.067
 neighborhood-0.067
TokenOP
Token ID3185
Feature activation+4.98e+00

Pos logit contributions
 ounces+0.164
ets+0.157
ocol+0.150
hell+0.146
izards+0.145
Neg logit contributions
burn-0.197
 blowing-0.193
 neighborhood-0.182
 daddy-0.182
 leaning-0.180
Token!"
Token ID2474
Feature activation+2.00e+00

Pos logit contributions
 ounces+0.100
izards+0.094
ets+0.093
ocol+0.088
hell+0.085
Neg logit contributions
 blowing-0.189
burn-0.185
 spinning-0.164
 waving-0.163
 daddy-0.163
Token Rob
Token ID3851
Feature activation-7.87e-01

Pos logit contributions
 ounces+0.071
ets+0.068
ocol+0.065
 pounds+0.064
hell+0.064
Neg logit contributions
 blowing-0.046
burn-0.043
 daddy-0.039
 waving-0.038
 neighborhood-0.037
Token stopped
Token ID5025
Feature activation-4.74e+00

Pos logit contributions
 blowing+0.015
burn+0.014
 daddy+0.013
 waving+0.012
 neighborhood+0.012
Neg logit contributions
 ounces-0.030
ets-0.029
ocol-0.028
 pounds-0.028
hell-0.028
Token and
Token ID290
Feature activation+1.12e-01

Pos logit contributions
burn+0.124
tr+0.114
 neighborhood+0.105
uffy+0.101
 daddy+0.097
Neg logit contributions
ocol-0.118
izards-0.115
 ounces-0.112
 risks-0.112
ly-0.112
Token until
Token ID1566
Feature activation+2.19e+00

Pos logit contributions
 blowing+0.011
burn+0.010
 daddy+0.010
 shining+0.009
 neighborhood+0.009
Neg logit contributions
 ounces-0.020
ets-0.019
izards-0.019
ocol-0.018
hell-0.018
Token he
Token ID339
Feature activation+3.18e+00

Pos logit contributions
 ounces+0.071
ets+0.069
izards+0.065
hell+0.065
ocol+0.065
Neg logit contributions
 blowing-0.056
burn-0.053
 daddy-0.050
 waving-0.047
 neighborhood-0.047
Token had
Token ID550
Feature activation+1.15e+00

Pos logit contributions
 ounces+0.123
ets+0.119
 pounds+0.113
hell+0.113
izards+0.112
Neg logit contributions
 blowing-0.061
burn-0.059
 daddy-0.050
 waving-0.050
 neighborhood-0.049
Token a
Token ID257
Feature activation+7.65e-01

Pos logit contributions
 ounces+0.047
ets+0.044
izards+0.044
ocol+0.044
hell+0.043
Neg logit contributions
 blowing-0.021
burn-0.018
 daddy-0.018
 shining-0.016
 blew-0.015
Token delicious
Token ID12625
Feature activation+2.27e+00

Pos logit contributions
 ounces+0.026
 pounds+0.024
 dollars+0.024
hell+0.024
ets+0.024
Neg logit contributions
 blowing-0.018
burn-0.017
 neighborhood-0.015
 waving-0.014
 leaning-0.014
Token batch
Token ID15458
Feature activation+6.77e+00

Pos logit contributions
 ounces+0.072
ets+0.068
ocol+0.066
 pounds+0.065
hell+0.065
Neg logit contributions
 blowing-0.059
burn-0.057
 daddy-0.051
 neighborhood-0.050
 waving-0.050
Token of
Token ID286
Feature activation+1.07e+00

Pos logit contributions
 ounces+0.245
 risks+0.243
ocol+0.234
bors+0.230
ets+0.229
Neg logit contributions
 blowing-0.135
 next-0.113
 holding-0.111
 mom-0.109
 daddy-0.104
Token brown
Token ID7586
Feature activation+1.32e+00

Pos logit contributions
ets+0.037
 ounces+0.037
izards+0.035
hell+0.034
 pounds+0.033
Neg logit contributions
 blowing-0.025
burn-0.023
 daddy-0.022
 shining-0.022
 waving-0.021
Tokenies
Token ID444
Feature activation+1.80e+00

Pos logit contributions
ets+0.044
izards+0.043
 ounces+0.043
hell+0.041
cher+0.039
Neg logit contributions
 blowing-0.032
burn-0.030
 shining-0.028
 daddy-0.027
 spinning-0.026
Token.
Token ID13
Feature activation+3.73e-01

Pos logit contributions
 ounces+0.067
ocol+0.064
ets+0.061
hell+0.060
izards+0.060
Neg logit contributions
 blowing-0.041
burn-0.035
 waving-0.033
 daddy-0.033
 shining-0.033
Token When
Token ID1649
Feature activation-5.00e-01

Pos logit contributions
 ounces+0.014
ets+0.014
hell+0.013
 pounds+0.013
izards+0.013
Neg logit contributions
 blowing-0.007
burn-0.007
 daddy-0.006
 neighborhood-0.006
 waving-0.006
Token'm
Token ID1101
Feature activation+1.20e+00

Pos logit contributions
 blowing+0.002
burn+0.002
 daddy+0.002
 neighborhood+0.002
 waving+0.002
Neg logit contributions
 ounces-0.004
ets-0.003
 pounds-0.003
ocol-0.003
izards-0.003
Token never
Token ID1239
Feature activation-1.06e+00

Pos logit contributions
 ounces+0.041
ets+0.039
hell+0.037
 pounds+0.037
ocol+0.037
Neg logit contributions
 blowing-0.029
burn-0.027
 daddy-0.025
 waving-0.024
 leaning-0.024
Token going
Token ID1016
Feature activation-2.03e+00

Pos logit contributions
 blowing+0.028
burn+0.024
 daddy+0.024
 waving+0.023
 crying+0.023
Neg logit contributions
 ounces-0.035
ets-0.033
hell-0.032
ocol-0.032
 pounds-0.032
Token to
Token ID284
Feature activation-5.77e-01

Pos logit contributions
 blowing+0.032
burn+0.029
 daddy+0.025
 waving+0.024
 neighborhood+0.023
Neg logit contributions
 ounces-0.087
ets-0.083
ocol-0.081
hell-0.080
 pounds-0.080
Token try
Token ID1949
Feature activation-8.03e-01

Pos logit contributions
 blowing+0.014
burn+0.013
 daddy+0.012
 neighborhood+0.012
 waving+0.011
Neg logit contributions
 ounces-0.019
ets-0.018
hell-0.018
ocol-0.017
 pounds-0.017
Token ol
Token ID25776
Feature activation+6.75e+00

Pos logit contributions
 blowing+0.021
burn+0.020
 daddy+0.018
 waving+0.018
 spinning+0.018
Neg logit contributions
 ounces-0.026
ets-0.025
ocol-0.023
izards-0.023
 pounds-0.023
Tokenives
Token ID1083
Feature activation+2.39e+00

Pos logit contributions
 ounces+0.130
ocol+0.113
 pounds+0.104
bors+0.102
 dollars+0.100
Neg logit contributions
 blowing-0.248
burn-0.246
 leaning-0.219
 waving-0.218
tr-0.218
Token only
Token ID691
Feature activation+1.38e+00

Pos logit contributions
 ounces+0.083
ets+0.076
ocol+0.076
 pounds+0.074
izards+0.074
Neg logit contributions
 blowing-0.057
burn-0.053
 daddy-0.052
 mom-0.047
 next-0.047
Token once
Token ID1752
Feature activation+4.66e-02

Pos logit contributions
 ounces+0.044
ocol+0.041
ets+0.041
izards+0.041
hell+0.040
Neg logit contributions
 blowing-0.036
burn-0.032
 daddy-0.031
 waving-0.030
 shining-0.029
Token again
Token ID757
Feature activation-3.48e-01

Pos logit contributions
 ounces+0.001
ets+0.001
ocol+0.001
bridge+0.001
izards+0.001
Neg logit contributions
 blowing-0.001
 next-0.001
burn-0.001
 daddy-0.001
 spinning-0.001
Token!"
Token ID2474
Feature activation+1.73e+00

Pos logit contributions
 blowing+0.011
burn+0.010
 daddy+0.010
 neighborhood+0.010
 waving+0.010
Neg logit contributions
 ounces-0.009
ets-0.009
hell-0.009
ocol-0.009
izards-0.008
Token go
Token ID467
Feature activation-1.06e+00

Pos logit contributions
 blowing+0.026
burn+0.025
 daddy+0.023
 neighborhood+0.022
 waving+0.022
Neg logit contributions
 ounces-0.035
ets-0.033
hell-0.032
ocol-0.032
 pounds-0.032
Token to
Token ID284
Feature activation+1.21e+00

Pos logit contributions
 blowing+0.024
burn+0.023
 daddy+0.020
 neighborhood+0.019
 leaning+0.019
Neg logit contributions
 ounces-0.037
ets-0.036
izards-0.034
hell-0.034
ocol-0.034
Token the
Token ID262
Feature activation+1.80e+00

Pos logit contributions
 ounces+0.046
ets+0.044
ocol+0.042
izards+0.042
 pounds+0.042
Neg logit contributions
 blowing-0.024
burn-0.023
 daddy-0.020
 neighborhood-0.019
 waving-0.019
Token land
Token ID1956
Feature activation+5.61e-01

Pos logit contributions
 ounces+0.065
ets+0.061
izards+0.060
 pounds+0.059
hell+0.059
Neg logit contributions
 blowing-0.038
burn-0.035
 daddy-0.028
 blew-0.027
 leaning-0.027
Token of
Token ID286
Feature activation+8.95e-01

Pos logit contributions
 ounces+0.022
ets+0.021
ocol+0.021
 pounds+0.020
hell+0.020
Neg logit contributions
 blowing-0.010
burn-0.009
 daddy-0.009
 waving-0.008
 neighborhood-0.008
Token Imp
Token ID9855
Feature activation+6.75e+00

Pos logit contributions
 ounces+0.034
ets+0.033
hell+0.031
 pounds+0.031
ocol+0.031
Neg logit contributions
 blowing-0.018
burn-0.017
 daddy-0.016
 waving-0.015
 neighborhood-0.015
Tokenressive
Token ID3314
Feature activation+4.61e-01

Pos logit contributions
 ounces+0.177
ets+0.165
 pounds+0.155
ocol+0.155
hell+0.154
Neg logit contributions
 blowing-0.216
burn-0.209
 daddy-0.195
 waving-0.188
 neighborhood-0.188
Token Things
Token ID11597
Feature activation+1.80e-01

Pos logit contributions
 ounces+0.017
hell+0.016
ocol+0.016
ets+0.016
 dollars+0.015
Neg logit contributions
 blowing-0.009
 neighborhood-0.009
 waving-0.008
 daddy-0.008
 leaning-0.008
Token.
Token ID13
Feature activation-9.12e-02

Pos logit contributions
 ounces+0.007
ets+0.006
ocol+0.006
 pounds+0.006
izards+0.006
Neg logit contributions
 blowing-0.004
burn-0.004
 daddy-0.003
 waving-0.003
 neighborhood-0.003
Token
Token ID198
Feature activation-1.79e-01

Pos logit contributions
 blowing+0.001
burn+0.001
 daddy+0.001
 neighborhood+0.001
 waving+0.001
Neg logit contributions
 ounces-0.004
ets-0.004
ocol-0.004
hell-0.004
 pounds-0.004
Token
Token ID198
Feature activation+7.11e-01

Pos logit contributions
 blowing+0.003
burn+0.003
 daddy+0.002
 waving+0.002
 leaning+0.002
Neg logit contributions
 ounces-0.007
ets-0.007
hell-0.007
izards-0.007
 pounds-0.007
Token his
Token ID465
Feature activation-1.18e+00

Pos logit contributions
 blowing+0.035
burn+0.033
 daddy+0.031
 shining+0.029
 waving+0.029
Neg logit contributions
 ounces-0.052
ets-0.049
hell-0.047
 pounds-0.047
izards-0.047
Token socks
Token ID24359
Feature activation+3.35e-01

Pos logit contributions
 blowing+0.030
burn+0.028
 daddy+0.028
 neighborhood+0.026
 spinning+0.026
Neg logit contributions
 ounces-0.038
ets-0.036
hell-0.035
ocol-0.034
izards-0.034
Token away
Token ID1497
Feature activation+8.32e-01

Pos logit contributions
 ounces+0.012
ets+0.011
ocol+0.011
 pounds+0.011
izards+0.011
Neg logit contributions
 blowing-0.007
burn-0.007
 daddy-0.006
 shining-0.006
 waving-0.006
Token in
Token ID287
Feature activation-1.73e-01

Pos logit contributions
 ounces+0.031
ets+0.029
ocol+0.028
izards+0.028
 pounds+0.028
Neg logit contributions
 blowing-0.018
burn-0.016
 daddy-0.015
 waving-0.014
 shining-0.014
Token a
Token ID257
Feature activation+2.39e+00

Pos logit contributions
 blowing+0.004
burn+0.004
 daddy+0.003
 neighborhood+0.003
 waving+0.003
Neg logit contributions
 ounces-0.006
ets-0.006
ocol-0.006
 pounds-0.006
hell-0.006
Token timely
Token ID19376
Feature activation+6.74e+00

Pos logit contributions
 ounces+0.095
izards+0.093
ets+0.093
ocol+0.090
 pounds+0.088
Neg logit contributions
 blowing-0.042
burn-0.038
 neighborhood-0.037
 daddy-0.037
 spinning-0.035
Token manner
Token ID5642
Feature activation+2.25e+00

Pos logit contributions
izards+0.187
 ounces+0.186
 pounds+0.178
ocol+0.170
 dollars+0.167
Neg logit contributions
 neighborhood-0.195
 blowing-0.192
burn-0.189
 daddy-0.184
 mom-0.178
Token.
Token ID13
Feature activation+2.62e-02

Pos logit contributions
 ounces+0.083
ocol+0.078
ets+0.078
izards+0.077
hell+0.075
Neg logit contributions
 blowing-0.049
burn-0.043
 daddy-0.042
 waving-0.040
 leaning-0.039
Token And
Token ID843
Feature activation+1.49e+00

Pos logit contributions
 ounces+0.001
ets+0.001
 pounds+0.001
hell+0.001
ocol+0.001
Neg logit contributions
 blowing-0.001
burn-0.001
 daddy-0.001
 waving-0.001
 shining-0.001
Token each
Token ID1123
Feature activation-1.75e+00

Pos logit contributions
 ounces+0.047
ets+0.044
 pounds+0.042
 dollars+0.042
izards+0.042
Neg logit contributions
burn-0.039
 blowing-0.039
 neighborhood-0.034
 daddy-0.033
 waving-0.033
Token time
Token ID640
Feature activation-2.21e+00

Pos logit contributions
 blowing+0.030
burn+0.028
 daddy+0.025
 waving+0.023
 neighborhood+0.023
Neg logit contributions
 ounces-0.072
ets-0.069
ocol-0.067
 pounds-0.067
izards-0.066
Token sandwiches
Token ID29777
Feature activation+2.63e+00

Pos logit contributions
 ounces+0.029
ets+0.027
izards+0.026
ocol+0.025
 pounds+0.025
Neg logit contributions
 blowing-0.028
burn-0.027
 shining-0.026
 daddy-0.025
 waving-0.025
Token and
Token ID290
Feature activation+8.36e-01

Pos logit contributions
 ounces+0.112
ocol+0.106
ets+0.103
 pounds+0.102
izards+0.100
Neg logit contributions
 blowing-0.045
burn-0.039
 waving-0.036
 daddy-0.035
 shining-0.034
Token mini
Token ID9927
Feature activation+2.36e+00

Pos logit contributions
 ounces+0.028
ets+0.027
ocol+0.026
izards+0.025
 pounds+0.025
Neg logit contributions
 blowing-0.021
burn-0.020
 daddy-0.019
 shining-0.018
 waving-0.018
Token packets
Token ID24624
Feature activation+1.89e+00

Pos logit contributions
 ounces+0.067
ets+0.061
izards+0.059
 pounds+0.059
ocol+0.058
Neg logit contributions
 blowing-0.069
burn-0.065
 neighborhood-0.062
 waving-0.061
 daddy-0.061
Token of
Token ID286
Feature activation+1.02e+00

Pos logit contributions
 ounces+0.072
 risks+0.064
ocol+0.064
ets+0.063
 pounds+0.063
Neg logit contributions
 blowing-0.042
burn-0.036
 shining-0.034
 waving-0.034
 daddy-0.033
Token cris
Token ID4442
Feature activation+6.73e+00

Pos logit contributions
 ounces+0.033
ets+0.032
 pounds+0.029
izards+0.029
 dollars+0.029
Neg logit contributions
 blowing-0.027
 daddy-0.024
burn-0.024
 waving-0.024
 shining-0.024
Tokenps
Token ID862
Feature activation+1.62e+00

Pos logit contributions
 ounces+0.189
hell+0.169
 risks+0.163
izards+0.163
 dollars+0.162
Neg logit contributions
 blowing-0.194
burn-0.173
 waving-0.167
 leaning-0.163
 holding-0.159
Token.
Token ID13
Feature activation-2.75e-02

Pos logit contributions
 ounces+0.057
ocol+0.053
ets+0.052
izards+0.052
 pounds+0.051
Neg logit contributions
 blowing-0.038
burn-0.035
 waving-0.032
 shining-0.032
 daddy-0.030
Token The
Token ID383
Feature activation-1.31e+00

Pos logit contributions
 blowing+0.000
 daddy+0.000
burn+0.000
 neighborhood+0.000
 mom+0.000
Neg logit contributions
 ounces-0.001
ets-0.001
 pounds-0.001
ocol-0.001
hell-0.001
Token children
Token ID1751
Feature activation-4.19e-02

Pos logit contributions
 blowing+0.029
burn+0.028
 daddy+0.027
 neighborhood+0.025
 waving+0.025
Neg logit contributions
 ounces-0.047
ets-0.045
ocol-0.043
izards-0.043
 pounds-0.042
Token had
Token ID550
Feature activation-4.23e-01

Pos logit contributions
 blowing+0.001
burn+0.001
 daddy+0.001
 waving+0.001
 neighborhood+0.001
Neg logit contributions
 ounces-0.002
ets-0.001
ocol-0.001
 pounds-0.001
hell-0.001
Token she
Token ID673
Feature activation+1.78e+00

Pos logit contributions
 blowing+0.003
burn+0.003
 daddy+0.002
 waving+0.002
 neighborhood+0.002
Neg logit contributions
 ounces-0.006
ets-0.005
 pounds-0.005
ocol-0.005
hell-0.005
Token saw
Token ID2497
Feature activation+4.16e-01

Pos logit contributions
ets+0.053
 ounces+0.052
izards+0.049
ly+0.047
 pounds+0.047
Neg logit contributions
burn-0.048
 blowing-0.046
 daddy-0.038
 waving-0.037
 leaning-0.036
Token a
Token ID257
Feature activation+7.44e-01

Pos logit contributions
 ounces+0.014
izards+0.013
ets+0.013
hell+0.013
 pounds+0.013
Neg logit contributions
 blowing-0.010
burn-0.010
 daddy-0.008
 neighborhood-0.008
 waving-0.008
Token tree
Token ID5509
Feature activation+8.46e-01

Pos logit contributions
 ounces+0.025
hell+0.024
 pounds+0.023
 dollars+0.022
ocol+0.022
Neg logit contributions
burn-0.017
 blowing-0.017
 daddy-0.013
 neighborhood-0.013
 leaning-0.013
Token with
Token ID351
Feature activation+2.28e+00

Pos logit contributions
 ounces+0.027
ets+0.027
hell+0.026
 pounds+0.025
 dollars+0.025
Neg logit contributions
burn-0.020
 daddy-0.019
 blowing-0.019
 neighborhood-0.016
 grandma-0.015
Token ol
Token ID25776
Feature activation+6.71e+00

Pos logit contributions
 ounces+0.083
ets+0.078
 pounds+0.076
hell+0.076
ocol+0.075
Neg logit contributions
 blowing-0.050
burn-0.048
 daddy-0.042
 neighborhood-0.041
 waving-0.040
Tokenives
Token ID1083
Feature activation+2.28e+00

Pos logit contributions
 ounces+0.132
 pounds+0.105
bors+0.103
 dollars+0.100
ocol+0.098
Neg logit contributions
 blowing-0.246
burn-0.238
 shining-0.227
 leaning-0.226
 waving-0.223
Token growing
Token ID3957
Feature activation+7.78e-01

Pos logit contributions
 ounces+0.095
ets+0.087
ocol+0.086
 pounds+0.085
hell+0.083
Neg logit contributions
 blowing-0.045
burn-0.038
 waving-0.036
 leaning-0.035
 shining-0.035
Token on
Token ID319
Feature activation+1.87e+00

Pos logit contributions
 ounces+0.031
ets+0.027
 pounds+0.027
ocol+0.027
izards+0.027
Neg logit contributions
 blowing-0.015
 shining-0.013
burn-0.012
 leaning-0.012
 next-0.011
Token it
Token ID340
Feature activation+2.35e+00

Pos logit contributions
 ounces+0.067
ets+0.066
izards+0.062
 dollars+0.062
ocol+0.062
Neg logit contributions
 blowing-0.042
burn-0.038
 waving-0.035
 daddy-0.035
 shining-0.035
Token.
Token ID13
Feature activation+2.74e-01

Pos logit contributions
 ounces+0.088
ocol+0.084
 pounds+0.079
ets+0.079
izards+0.077
Neg logit contributions
 blowing-0.054
burn-0.045
 waving-0.044
 shining-0.043
 leaning-0.043
Token came
Token ID1625
Feature activation+1.44e-01

Pos logit contributions
 ounces+0.032
ets+0.031
ocol+0.029
 pounds+0.029
hell+0.029
Neg logit contributions
 blowing-0.022
burn-0.021
 daddy-0.019
 neighborhood-0.018
 waving-0.018
Token by
Token ID416
Feature activation+8.36e-01

Pos logit contributions
 ounces+0.004
ets+0.004
izards+0.004
ly+0.004
 risks+0.004
Neg logit contributions
burn-0.003
 daddy-0.003
 blowing-0.003
 neighborhood-0.003
 grandma-0.003
Token and
Token ID290
Feature activation-2.11e-01

Pos logit contributions
 ounces+0.027
ets+0.026
ocol+0.025
 pounds+0.024
hell+0.024
Neg logit contributions
 blowing-0.022
burn-0.020
 daddy-0.019
 waving-0.018
 neighborhood-0.018
Token ate
Token ID15063
Feature activation+9.92e-01

Pos logit contributions
burn+0.005
 blowing+0.005
 neighborhood+0.004
 daddy+0.004
 waving+0.004
Neg logit contributions
 ounces-0.007
ets-0.007
izards-0.006
ocol-0.006
 pounds-0.006
Token a
Token ID257
Feature activation+1.82e-01

Pos logit contributions
 ounces+0.036
ets+0.036
izards+0.033
 pounds+0.032
 dollars+0.032
Neg logit contributions
 blowing-0.022
burn-0.019
 daddy-0.019
 shining-0.019
 waving-0.018
Token french
Token ID48718
Feature activation+6.68e+00

Pos logit contributions
 ounces+0.007
ets+0.006
hell+0.006
 pounds+0.006
ocol+0.006
Neg logit contributions
 blowing-0.004
burn-0.004
 daddy-0.003
 neighborhood-0.003
 waving-0.003
Token fry
Token ID32959
Feature activation+1.28e+00

Pos logit contributions
 ounces+0.174
ets+0.173
izards+0.169
hell+0.155
 pounds+0.153
Neg logit contributions
burn-0.196
 blowing-0.191
 daddy-0.181
 mom-0.170
 waving-0.169
Token from
Token ID422
Feature activation+2.03e+00

Pos logit contributions
 ounces+0.050
ets+0.047
ocol+0.045
izards+0.045
 risks+0.044
Neg logit contributions
 blowing-0.027
burn-0.022
 shining-0.020
 leaning-0.019
 daddy-0.019
Token his
Token ID465
Feature activation+1.49e+00

Pos logit contributions
 ounces+0.076
ets+0.073
hell+0.070
 pounds+0.069
izards+0.069
Neg logit contributions
 blowing-0.043
burn-0.040
 daddy-0.036
 waving-0.035
 neighborhood-0.034
Token hands
Token ID2832
Feature activation-1.32e-01

Pos logit contributions
 ounces+0.054
ets+0.052
 pounds+0.050
ocol+0.050
hell+0.049
Neg logit contributions
 blowing-0.032
burn-0.031
 daddy-0.027
 waving-0.026
 neighborhood-0.025
Token.
Token ID13
Feature activation+3.83e-03

Pos logit contributions
 blowing+0.004
burn+0.003
 daddy+0.003
 waving+0.003
 shining+0.003
Neg logit contributions
 ounces-0.004
ets-0.004
ocol-0.004
izards-0.004
 pounds-0.004
TokenICK
Token ID11860
Feature activation+3.69e+00

Pos logit contributions
 ounces+0.092
ocol+0.079
 pounds+0.078
ets+0.075
 dollars+0.075
Neg logit contributions
burn-0.091
 blowing-0.090
 leaning-0.079
 neighborhood-0.078
 daddy-0.077
Token!
Token ID0
Feature activation+4.99e-01

Pos logit contributions
 ounces+0.097
ocol+0.086
ets+0.085
izards+0.085
hell+0.083
Neg logit contributions
 blowing-0.120
burn-0.120
 waving-0.104
 spinning-0.102
 daddy-0.101
Token AND
Token ID5357
Feature activation+3.75e+00

Pos logit contributions
 ounces+0.017
ets+0.017
 pounds+0.016
hell+0.016
ils+0.016
Neg logit contributions
burn-0.012
 blowing-0.011
 daddy-0.010
 waving-0.010
 mom-0.010
Token YOU
Token ID7013
Feature activation+4.89e+00

Pos logit contributions
 ounces+0.127
ocol+0.119
 pounds+0.115
ets+0.115
izards+0.110
Neg logit contributions
 blowing-0.096
burn-0.089
 spinning-0.080
 waving-0.079
 daddy-0.079
Token WILL
Token ID17682
Feature activation+3.44e+00

Pos logit contributions
 ounces+0.150
ocol+0.141
 pounds+0.139
 dollars+0.136
izards+0.132
Neg logit contributions
 blowing-0.136
burn-0.123
 blew-0.118
 waving-0.114
zag-0.111
Token GET
Token ID17151
Feature activation+6.68e+00

Pos logit contributions
 ounces+0.119
ets+0.114
 pounds+0.110
hell+0.108
izards+0.108
Neg logit contributions
 blowing-0.082
burn-0.080
 daddy-0.070
 waving-0.068
 neighborhood-0.065
Token IN
Token ID3268
Feature activation+4.15e+00

Pos logit contributions
 ounces+0.229
ets+0.214
bridge+0.212
 pounds+0.208
 dollars+0.208
Neg logit contributions
 blowing-0.159
burn-0.158
 spinning-0.134
 daddy-0.133
 waving-0.132
Token TR
Token ID7579
Feature activation+5.01e+00

Pos logit contributions
 ounces+0.127
ets+0.118
 pounds+0.112
hell+0.111
izards+0.110
Neg logit contributions
 blowing-0.116
burn-0.111
 waving-0.099
 leaning-0.098
 daddy-0.098
TokenOU
Token ID2606
Feature activation+5.41e+00

Pos logit contributions
 ounces+0.151
ets+0.137
 pounds+0.134
 dollars+0.134
izards+0.132
Neg logit contributions
burn-0.141
 blowing-0.133
 neighborhood-0.120
 daddy-0.117
 waving-0.115
TokenBLE
Token ID19146
Feature activation+3.14e+00

Pos logit contributions
 ounces+0.166
ets+0.155
ocol+0.151
izards+0.150
 pounds+0.149
Neg logit contributions
burn-0.152
 blowing-0.148
 daddy-0.129
 waving-0.126
 neighborhood-0.124
Token!"
Token ID2474
Feature activation+1.81e+00

Pos logit contributions
 ounces+0.084
ocol+0.078
izards+0.073
ets+0.073
 pounds+0.071
Neg logit contributions
burn-0.102
 blowing-0.101
 daddy-0.090
 waving-0.088
zag-0.087
Token time
Token ID640
Feature activation-1.30e+00

Pos logit contributions
 blowing+0.005
burn+0.004
 daddy+0.004
 neighborhood+0.004
 waving+0.004
Neg logit contributions
 ounces-0.008
ets-0.007
ocol-0.007
izards-0.007
hell-0.007
Token until
Token ID1566
Feature activation+1.18e+00

Pos logit contributions
burn+0.029
 blowing+0.029
 daddy+0.025
 neighborhood+0.024
 waving+0.024
Neg logit contributions
 ounces-0.046
ets-0.045
 pounds-0.042
hell-0.042
 dollars-0.041
Token she
Token ID673
Feature activation+3.67e+00

Pos logit contributions
 ounces+0.037
ets+0.034
ocol+0.034
 pounds+0.032
hell+0.032
Neg logit contributions
burn-0.030
 blowing-0.030
 neighborhood-0.026
 daddy-0.025
 waving-0.025
Token achieved
Token ID8793
Feature activation+1.20e+00

Pos logit contributions
 ounces+0.145
ets+0.140
hell+0.133
izards+0.132
 pounds+0.132
Neg logit contributions
 blowing-0.069
burn-0.068
 daddy-0.057
 waving-0.054
 shining-0.053
Token a
Token ID257
Feature activation+2.31e+00

Pos logit contributions
 ounces+0.048
ets+0.046
ocol+0.044
izards+0.044
 pounds+0.044
Neg logit contributions
 blowing-0.022
burn-0.020
 daddy-0.018
 waving-0.017
 neighborhood-0.017
Token lot
Token ID1256
Feature activation+6.65e+00

Pos logit contributions
 ounces+0.083
ets+0.080
ocol+0.076
 pounds+0.076
hell+0.076
Neg logit contributions
 blowing-0.051
burn-0.048
 daddy-0.044
 neighborhood-0.041
 waving-0.041
Token of
Token ID286
Feature activation+1.90e+00

Pos logit contributions
 ounces+0.194
ets+0.179
ocol+0.178
 pounds+0.173
izards+0.172
Neg logit contributions
 blowing-0.192
burn-0.168
 leaning-0.164
 waving-0.164
 neighborhood-0.163
Token great
Token ID1049
Feature activation+2.60e+00

Pos logit contributions
 ounces+0.066
ets+0.063
ocol+0.060
izards+0.060
hell+0.060
Neg logit contributions
 blowing-0.044
burn-0.041
 daddy-0.038
 neighborhood-0.037
 waving-0.037
Token things
Token ID1243
Feature activation+6.28e-01

Pos logit contributions
 ounces+0.081
ets+0.076
ocol+0.074
hell+0.073
izards+0.073
Neg logit contributions
 blowing-0.069
burn-0.065
 daddy-0.061
 neighborhood-0.060
 waving-0.059
Token.
Token ID13
Feature activation+2.59e-01

Pos logit contributions
 ounces+0.021
ets+0.019
ocol+0.019
 pounds+0.019
 dollars+0.019
Neg logit contributions
 blowing-0.016
burn-0.015
 daddy-0.014
 waving-0.014
 shining-0.013
Token
Token ID198
Feature activation+4.40e-01

Pos logit contributions
 ounces+0.011
ets+0.010
hell+0.010
izards+0.010
ocol+0.010
Neg logit contributions
 blowing-0.005
burn-0.004
 daddy-0.003
 waving-0.003
 shining-0.003
Token could
Token ID714
Feature activation-1.16e+00

Pos logit contributions
 blowing+0.037
burn+0.032
 daddy+0.029
 waving+0.029
 shining+0.028
Neg logit contributions
 ounces-0.079
ets-0.075
ocol-0.074
izards-0.073
 pounds-0.073
Token see
Token ID766
Feature activation+6.85e-01

Pos logit contributions
 blowing+0.026
burn+0.024
 daddy+0.022
 waving+0.021
 neighborhood+0.021
Neg logit contributions
 ounces-0.042
ets-0.040
 pounds-0.038
ocol-0.038
izards-0.038
Token lots
Token ID6041
Feature activation+2.85e+00

Pos logit contributions
 ounces+0.025
ets+0.024
ocol+0.023
izards+0.022
 dollars+0.022
Neg logit contributions
 blowing-0.015
burn-0.013
 daddy-0.013
 shining-0.012
 waving-0.012
Token of
Token ID286
Feature activation+6.19e-01

Pos logit contributions
 ounces+0.091
ets+0.084
izards+0.083
ocol+0.082
 dollars+0.080
Neg logit contributions
 blowing-0.073
 shining-0.063
 waving-0.060
 leaning-0.058
 spinning-0.058
Token av
Token ID1196
Feature activation+3.57e+00

Pos logit contributions
 ounces+0.022
ets+0.021
izards+0.020
 dollars+0.020
ocol+0.020
Neg logit contributions
 blowing-0.014
 daddy-0.012
 shining-0.012
 neighborhood-0.012
burn-0.011
Tokenoc
Token ID420
Feature activation+6.62e+00

Pos logit contributions
 ounces+0.059
ets+0.053
izards+0.051
ocol+0.048
 pounds+0.047
Neg logit contributions
 blowing-0.144
burn-0.139
 neighborhood-0.132
 leaning-0.129
 daddy-0.129
Tokenados
Token ID22484
Feature activation+2.63e+00

Pos logit contributions
ets+0.121
 ounces+0.115
izards+0.106
hell+0.105
bridge+0.098
Neg logit contributions
 blowing-0.248
burn-0.237
 leaning-0.227
 daddy-0.225
 neighborhood-0.224
Token that
Token ID326
Feature activation-1.15e-01

Pos logit contributions
 ounces+0.094
ocol+0.087
ets+0.086
 pounds+0.083
 dollars+0.082
Neg logit contributions
 blowing-0.063
burn-0.053
 waving-0.052
 shining-0.052
 leaning-0.050
Token the
Token ID262
Feature activation-1.99e-01

Pos logit contributions
 blowing+0.003
burn+0.002
 daddy+0.002
 waving+0.002
 neighborhood+0.002
Neg logit contributions
 ounces-0.004
ets-0.004
ocol-0.004
 pounds-0.004
izards-0.004
Token supplier
Token ID22693
Feature activation+1.01e+00

Pos logit contributions
 blowing+0.005
burn+0.004
 daddy+0.004
 waving+0.004
 neighborhood+0.004
Neg logit contributions
 ounces-0.007
ets-0.007
 pounds-0.006
ocol-0.006
hell-0.006
Token had
Token ID550
Feature activation+9.69e-01

Pos logit contributions
 ounces+0.037
ets+0.035
ocol+0.035
 pounds+0.035
 risks+0.034
Neg logit contributions
 blowing-0.022
 daddy-0.019
burn-0.019
 waving-0.018
 shining-0.018
Tokenman
Token ID805
Feature activation-4.41e-01

Pos logit contributions
 blowing+0.100
burn+0.089
 daddy+0.088
 waving+0.085
 neighborhood+0.082
Neg logit contributions
ets-0.195
 ounces-0.194
hell-0.187
ly-0.180
 pounds-0.180
Token.
Token ID13
Feature activation+5.75e-03

Pos logit contributions
 blowing+0.010
burn+0.009
 daddy+0.009
 waving+0.008
 neighborhood+0.008
Neg logit contributions
 ounces-0.016
ocol-0.015
ets-0.015
izards-0.014
 pounds-0.014
Token They
Token ID1119
Feature activation+1.30e+00

Pos logit contributions
 ounces+0.000
ets+0.000
hell+0.000
izards+0.000
ocol+0.000
Neg logit contributions
burn-0.000
 blowing-0.000
 daddy-0.000
 shining-0.000
 waving-0.000
Token loved
Token ID6151
Feature activation-2.08e+00

Pos logit contributions
 ounces+0.046
ets+0.043
ocol+0.042
 pounds+0.042
hell+0.041
Neg logit contributions
 blowing-0.030
burn-0.028
 daddy-0.026
 waving-0.025
 neighborhood-0.025
Token their
Token ID511
Feature activation-9.85e-01

Pos logit contributions
burn+0.051
 blowing+0.049
 neighborhood+0.044
zag+0.041
rolling+0.041
Neg logit contributions
 ounces-0.067
ets-0.062
 pounds-0.062
ocol-0.061
izards-0.061
Token snow
Token ID6729
Feature activation-6.94e+00

Pos logit contributions
 blowing+0.027
burn+0.026
 Smith+0.023
ina+0.022
rolling+0.022
Neg logit contributions
 ounces-0.025
 pounds-0.023
 dollars-0.023
ets-0.023
 risks-0.022
Tokenman
Token ID805
Feature activation-2.54e+00

Pos logit contributions
 blowing+0.119
burn+0.106
 daddy+0.097
 neighborhood+0.094
 waving+0.094
Neg logit contributions
 ounces-0.271
ets-0.265
hell-0.262
 pounds-0.253
 dollars-0.246
Token.
Token ID13
Feature activation-6.52e-01

Pos logit contributions
 blowing+0.056
burn+0.054
 daddy+0.050
 waving+0.047
 mom+0.046
Neg logit contributions
 ounces-0.092
ocol-0.091
ets-0.085
izards-0.084
 pounds-0.082
Token They
Token ID1119
Feature activation+5.99e-01

Pos logit contributions
 blowing+0.017
burn+0.017
 daddy+0.014
 waving+0.014
 leaning+0.014
Neg logit contributions
 ounces-0.021
ets-0.020
hell-0.019
izards-0.019
ocol-0.019
Token cried
Token ID16896
Feature activation+2.56e+00

Pos logit contributions
 ounces+0.022
ets+0.021
ocol+0.021
 pounds+0.020
izards+0.020
Neg logit contributions
 blowing-0.013
burn-0.012
 daddy-0.011
 waving-0.011
 neighborhood-0.010
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
 ounces+0.100
ets+0.094
ocol+0.092
 pounds+0.091
izards+0.091
Neg logit contributions
 blowing-0.050
burn-0.047
 daddy-0.043
 waving-0.040
 neighborhood-0.039
Token.
Token ID13
Feature activation-1.90e+00

Pos logit contributions
 blowing+0.112
burn+0.110
 daddy+0.102
 waving+0.096
 leaning+0.094
Neg logit contributions
 ounces-0.133
ets-0.123
ocol-0.123
izards-0.122
hell-0.117
Token And
Token ID843
Feature activation+1.09e+00

Pos logit contributions
 blowing+0.056
burn+0.055
 daddy+0.052
 waving+0.049
 neighborhood+0.049
Neg logit contributions
 ounces-0.054
ets-0.051
hell-0.048
 pounds-0.048
izards-0.048
Token we
Token ID356
Feature activation+6.09e-01

Pos logit contributions
 ounces+0.037
ets+0.036
hell+0.034
ocol+0.034
izards+0.034
Neg logit contributions
 blowing-0.027
burn-0.025
 daddy-0.024
 waving-0.022
 shining-0.022
Token love
Token ID1842
Feature activation-2.97e+00

Pos logit contributions
 ounces+0.025
ocol+0.023
 pounds+0.023
ets+0.023
izards+0.022
Neg logit contributions
 blowing-0.011
burn-0.011
 daddy-0.010
 neighborhood-0.009
 blew-0.009
Token our
Token ID674
Feature activation-9.26e-01

Pos logit contributions
 blowing+0.093
burn+0.093
 neighborhood+0.089
zag+0.084
 waving+0.084
Neg logit contributions
 ounces-0.073
ocol-0.067
 pounds-0.065
ets-0.064
 dollars-0.063
Token snow
Token ID6729
Feature activation-6.82e+00

Pos logit contributions
 blowing+0.021
burn+0.020
 leaning+0.018
 waving+0.017
 daddy+0.017
Neg logit contributions
 ounces-0.031
ets-0.030
 dollars-0.029
 pounds-0.029
ocol-0.028
Tokenman
Token ID805
Feature activation-2.15e+00

Pos logit contributions
 blowing+0.104
burn+0.096
 daddy+0.082
 waving+0.076
 neighborhood+0.076
Neg logit contributions
 ounces-0.292
ets-0.281
ocol-0.271
 pounds-0.271
hell-0.270
Token.
Token ID13
Feature activation-1.92e+00

Pos logit contributions
burn+0.051
 blowing+0.049
 daddy+0.048
 mom+0.047
 next+0.045
Neg logit contributions
ocol-0.075
 ounces-0.074
izards-0.068
ets-0.067
 risks-0.064
Token He
Token ID679
Feature activation-6.92e-01

Pos logit contributions
 blowing+0.051
burn+0.050
 daddy+0.048
 waving+0.044
 mom+0.043
Neg logit contributions
 ounces-0.058
ets-0.056
izards-0.053
hell-0.053
 pounds-0.053
Token was
Token ID373
Feature activation-1.68e+00

Pos logit contributions
 blowing+0.013
burn+0.012
 daddy+0.011
 waving+0.010
 neighborhood+0.010
Neg logit contributions
 ounces-0.027
ets-0.026
ocol-0.025
 pounds-0.025
izards-0.025
Token a
Token ID257
Feature activation-1.79e+00

Pos logit contributions
 blowing+0.032
burn+0.029
 daddy+0.027
 waving+0.025
 shining+0.025
Neg logit contributions
 ounces-0.068
ets-0.065
hell-0.062
ocol-0.062
 pounds-0.062
Token Lily
Token ID20037
Feature activation-8.77e-01

Pos logit contributions
 pounds+0.059
 ounces+0.059
ocol+0.058
izards+0.058
 dollars+0.057
Neg logit contributions
 daddy-0.020
 mom-0.019
 crying-0.018
 blowing-0.018
 feeling-0.018
Token was
Token ID373
Feature activation-1.28e+00

Pos logit contributions
 blowing+0.015
burn+0.014
 daddy+0.012
 neighborhood+0.011
 waving+0.011
Neg logit contributions
 ounces-0.036
ets-0.034
hell-0.033
 pounds-0.033
izards-0.032
Token sad
Token ID6507
Feature activation-4.76e-01

Pos logit contributions
burn+0.033
 blowing+0.030
 neighborhood+0.029
 daddy+0.028
flower+0.026
Neg logit contributions
 ounces-0.039
ets-0.036
izards-0.035
hell-0.035
 pounds-0.035
Token because
Token ID780
Feature activation-1.40e+00

Pos logit contributions
burn+0.013
 blowing+0.013
 neighborhood+0.011
 daddy+0.011
 waving+0.011
Neg logit contributions
ets-0.014
 ounces-0.014
ly-0.013
 pounds-0.013
hell-0.013
Token her
Token ID607
Feature activation-2.71e+00

Pos logit contributions
burn+0.034
 blowing+0.034
 neighborhood+0.029
 waving+0.027
 daddy+0.027
Neg logit contributions
 ounces-0.046
izards-0.043
ets-0.042
ocol-0.042
hell-0.042
Token snow
Token ID6729
Feature activation-6.76e+00

Pos logit contributions
 blowing+0.066
burn+0.065
 leaning+0.054
 Smith+0.054
 neighborhood+0.054
Neg logit contributions
 ounces-0.080
ets-0.075
 pounds-0.074
hell-0.072
ocol-0.070
Tokenman
Token ID805
Feature activation-2.41e+00

Pos logit contributions
 blowing+0.116
burn+0.108
 neighborhood+0.100
 waving+0.100
 daddy+0.098
Neg logit contributions
 ounces-0.253
hell-0.245
ets-0.245
ly-0.236
 pounds-0.234
Token was
Token ID373
Feature activation-1.41e+00

Pos logit contributions
 blowing+0.040
burn+0.038
 daddy+0.032
 neighborhood+0.030
 waving+0.030
Neg logit contributions
 ounces-0.099
ets-0.095
hell-0.092
 pounds-0.091
 dollars-0.090
Token disappearing
Token ID28867
Feature activation+3.55e-01

Pos logit contributions
burn+0.028
 blowing+0.027
 neighborhood+0.027
 daddy+0.024
 waving+0.023
Neg logit contributions
 ounces-0.049
ets-0.047
 pounds-0.045
ocol-0.045
hell-0.045
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
 ounces+0.011
ets+0.011
ocol+0.010
hell+0.010
 pounds+0.010
Neg logit contributions
 blowing-0.009
burn-0.009
 daddy-0.008
 waving-0.008
 neighborhood-0.008
Token She
Token ID1375
Feature activation+3.55e-01

Pos logit contributions
 ounces+0.004
ets+0.004
ocol+0.004
 pounds+0.004
hell+0.004
Neg logit contributions
 blowing-0.002
burn-0.002
 daddy-0.002
 waving-0.002
 neighborhood-0.002
Token happy
Token ID3772
Feature activation-8.06e-02

Pos logit contributions
 blowing+0.040
 crying+0.034
 waving+0.033
burn+0.033
 daddy+0.031
Neg logit contributions
 ounces-0.101
ets-0.096
ocol-0.095
 pounds-0.092
 dollars-0.091
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
 blowing+0.002
burn+0.002
 daddy+0.002
 waving+0.002
 crying+0.002
Neg logit contributions
 ounces-0.003
ets-0.003
ocol-0.003
 pounds-0.003
hell-0.003
Token She
Token ID1375
Feature activation+4.16e-01

Pos logit contributions
 blowing+0.024
burn+0.024
 daddy+0.020
 shining+0.019
 waving+0.019
Neg logit contributions
 ounces-0.034
ets-0.032
izards-0.032
hell-0.031
ocol-0.031
Token likes
Token ID7832
Feature activation-2.60e+00

Pos logit contributions
 ounces+0.014
ets+0.013
 pounds+0.013
ocol+0.013
hell+0.013
Neg logit contributions
 blowing-0.010
burn-0.010
 daddy-0.009
 neighborhood-0.009
 waving-0.008
Token her
Token ID607
Feature activation-1.76e+00

Pos logit contributions
 blowing+0.064
burn+0.062
 daddy+0.056
 neighborhood+0.054
 waving+0.054
Neg logit contributions
 ounces-0.086
ets-0.081
ocol-0.078
 pounds-0.078
izards-0.077
Token snow
Token ID6729
Feature activation-6.70e+00

Pos logit contributions
 blowing+0.038
burn+0.037
 daddy+0.032
 neighborhood+0.031
 waving+0.031
Neg logit contributions
 ounces-0.063
ets-0.060
hell-0.058
ocol-0.057
 pounds-0.057
Tokenman
Token ID805
Feature activation-2.19e+00

Pos logit contributions
 blowing+0.098
burn+0.089
 daddy+0.077
 neighborhood+0.072
 waving+0.071
Neg logit contributions
 ounces-0.289
ets-0.279
hell-0.270
 pounds-0.269
izards-0.267
Token.
Token ID13
Feature activation-1.31e+00

Pos logit contributions
 blowing+0.047
burn+0.046
 daddy+0.041
 waving+0.041
 crying+0.040
Neg logit contributions
 ounces-0.080
ocol-0.079
ets-0.075
izards-0.073
 pounds-0.070
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
 blowing+0.026
burn+0.025
 daddy+0.021
 waving+0.020
 neighborhood+0.020
Neg logit contributions
 ounces-0.050
ets-0.048
izards-0.046
hell-0.046
ocol-0.046
Token
Token ID198
Feature activation-1.55e-01

Pos logit contributions
burn+0.020
 blowing+0.019
 daddy+0.015
 shining+0.014
 waving+0.014
Neg logit contributions
 ounces-0.041
hell-0.039
ets-0.039
izards-0.039
ocol-0.038
TokenThe
Token ID464
Feature activation-1.58e+00

Pos logit contributions
 blowing+0.004
burn+0.004
 daddy+0.003
 neighborhood+0.003
 waving+0.003
Neg logit contributions
 ounces-0.005
ets-0.005
ocol-0.005
 pounds-0.005
hell-0.005
Token.
Token ID13
Feature activation-8.72e-01

Pos logit contributions
 blowing+0.053
burn+0.050
 daddy+0.047
 neighborhood+0.045
 waving+0.045
Neg logit contributions
 ounces-0.053
ets-0.051
hell-0.048
 pounds-0.048
ocol-0.047
Token They
Token ID1119
Feature activation+9.43e-01

Pos logit contributions
 blowing+0.021
burn+0.020
 waving+0.017
 daddy+0.017
 leaning+0.017
Neg logit contributions
 ounces-0.030
ets-0.029
izards-0.028
ocol-0.027
hell-0.027
Token still
Token ID991
Feature activation-3.47e+00

Pos logit contributions
 ounces+0.032
ets+0.030
 pounds+0.029
ocol+0.029
hell+0.029
Neg logit contributions
 blowing-0.023
burn-0.022
 daddy-0.020
 waving-0.019
 neighborhood-0.019
Token love
Token ID1842
Feature activation-2.69e+00

Pos logit contributions
 blowing+0.083
burn+0.079
 daddy+0.072
 waving+0.070
 neighborhood+0.069
Neg logit contributions
 ounces-0.119
ets-0.112
 pounds-0.108
ocol-0.108
izards-0.108
Token their
Token ID511
Feature activation-1.10e+00

Pos logit contributions
 blowing+0.066
burn+0.065
 neighborhood+0.059
 waving+0.056
rolling+0.056
Neg logit contributions
 ounces-0.087
 pounds-0.080
ets-0.079
ocol-0.079
 dollars-0.078
Token snow
Token ID6729
Feature activation-6.67e+00

Pos logit contributions
 blowing+0.025
burn+0.024
 leaning+0.020
 waving+0.020
 neighborhood+0.020
Neg logit contributions
 ounces-0.037
 dollars-0.035
 pounds-0.035
ets-0.034
ocol-0.034
Tokenman
Token ID805
Feature activation-2.09e+00

Pos logit contributions
 blowing+0.107
burn+0.096
 daddy+0.085
 neighborhood+0.082
 waving+0.081
Neg logit contributions
 ounces-0.275
ets-0.267
hell-0.259
 pounds-0.256
izards-0.252
Token.
Token ID13
Feature activation-1.36e+00

Pos logit contributions
 blowing+0.042
burn+0.040
 daddy+0.038
 mom+0.036
 waving+0.035
Neg logit contributions
 ounces-0.079
ocol-0.079
ets-0.073
izards-0.073
 pounds-0.070
Token<|endoftext|>
Token ID50256
Feature activation-7.09e-01

Pos logit contributions
 blowing+0.030
burn+0.029
 daddy+0.024
 waving+0.024
 leaning+0.023
Neg logit contributions
 ounces-0.049
ets-0.047
izards-0.045
hell-0.045
ocol-0.044
TokenL
Token ID43
Feature activation+3.60e+00

Pos logit contributions
 blowing+0.013
burn+0.013
 daddy+0.011
 waving+0.011
 neighborhood+0.011
Neg logit contributions
 ounces-0.028
ets-0.026
ocol-0.025
 pounds-0.025
hell-0.025
Tokenily
Token ID813
Feature activation-5.99e-01

Pos logit contributions
 ounces+0.115
 risks+0.100
 pounds+0.100
ocol+0.100
ets+0.099
Neg logit contributions
 daddy-0.095
 blowing-0.089
 mom-0.089
burn-0.088
 grandma-0.087
Token kind
Token ID1611
Feature activation-1.39e-01

Pos logit contributions
 blowing+0.042
burn+0.037
 daddy+0.037
 waving+0.035
 leaning+0.034
Neg logit contributions
 ounces-0.078
ets-0.075
hell-0.074
ocol-0.073
 pounds-0.073
Token.
Token ID13
Feature activation-2.07e+00

Pos logit contributions
 daddy+0.003
 blowing+0.003
 mom+0.003
burn+0.003
 next+0.003
Neg logit contributions
 ounces-0.005
ocol-0.005
hell-0.005
bridge-0.005
 pounds-0.005
Token You
Token ID921
Feature activation+3.04e+00

Pos logit contributions
 blowing+0.053
 daddy+0.052
burn+0.052
 neighborhood+0.048
 leaning+0.048
Neg logit contributions
 ounces-0.063
hell-0.062
ets-0.061
 pounds-0.059
 dollars-0.056
Token love
Token ID1842
Feature activation-3.21e+00

Pos logit contributions
 ounces+0.106
ocol+0.100
 pounds+0.100
hell+0.094
ets+0.093
Neg logit contributions
 blowing-0.071
burn-0.065
 daddy-0.063
 also-0.063
 blew-0.062
Token your
Token ID534
Feature activation-1.35e+00

Pos logit contributions
burn+0.094
 blowing+0.093
 daddy+0.083
 neighborhood+0.082
 waving+0.080
Neg logit contributions
 ounces-0.090
ets-0.084
ocol-0.081
izards-0.081
 pounds-0.080
Token snow
Token ID6729
Feature activation-6.64e+00

Pos logit contributions
 blowing+0.028
burn+0.027
 daddy+0.023
 waving+0.022
 neighborhood+0.022
Neg logit contributions
 ounces-0.050
ets-0.047
 pounds-0.046
ocol-0.046
hell-0.046
Tokenmen
Token ID3653
Feature activation-2.05e+00

Pos logit contributions
 blowing+0.115
burn+0.112
 daddy+0.097
 neighborhood+0.088
 waving+0.088
Neg logit contributions
 ounces-0.273
ets-0.259
ocol-0.259
 pounds-0.250
izards-0.249
Token and
Token ID290
Feature activation-2.22e+00

Pos logit contributions
 blowing+0.054
burn+0.052
 daddy+0.050
 neighborhood+0.046
 waving+0.046
Neg logit contributions
 ounces-0.066
ocol-0.063
izards-0.059
ets-0.058
 pounds-0.058
Token each
Token ID1123
Feature activation-1.46e+00

Pos logit contributions
 blowing+0.060
burn+0.058
 daddy+0.052
 neighborhood+0.051
 waving+0.051
Neg logit contributions
 ounces-0.069
ets-0.065
ocol-0.062
 pounds-0.062
izards-0.061
Token other
Token ID584
Feature activation-1.30e+00

Pos logit contributions
 blowing+0.025
burn+0.023
 daddy+0.020
 neighborhood+0.019
 waving+0.019
Neg logit contributions
 ounces-0.060
ocol-0.059
izards-0.058
 pounds-0.057
ets-0.056
Token.
Token ID13
Feature activation-1.88e+00

Pos logit contributions
 blowing+0.037
burn+0.034
 daddy+0.033
 neighborhood+0.032
 waving+0.032
Neg logit contributions
 ounces-0.038
ocol-0.038
izards-0.035
 pounds-0.033
ets-0.033
Token Ben
Token ID3932
Feature activation-3.45e-01

Pos logit contributions
 blowing+0.027
burn+0.026
 neighborhood+0.023
 shining+0.023
 waving+0.022
Neg logit contributions
 ounces-0.029
ets-0.028
izards-0.028
ocol-0.028
 pounds-0.026
Token smiled
Token ID13541
Feature activation-2.63e+00

Pos logit contributions
 blowing+0.008
burn+0.007
 daddy+0.007
 waving+0.006
 neighborhood+0.006
Neg logit contributions
 ounces-0.012
ets-0.012
ocol-0.011
 pounds-0.011
hell-0.011
Token and
Token ID290
Feature activation-9.45e-01

Pos logit contributions
 blowing+0.066
burn+0.064
 daddy+0.056
 neighborhood+0.055
 waving+0.055
Neg logit contributions
ets-0.084
 ounces-0.081
hell-0.078
izards-0.077
 dollars-0.076
Token hugged
Token ID41130
Feature activation+6.02e-02

Pos logit contributions
 blowing+0.024
burn+0.023
 daddy+0.021
 neighborhood+0.020
 leaning+0.019
Neg logit contributions
ets-0.029
 ounces-0.029
hell-0.027
izards-0.027
 dollars-0.027
Token their
Token ID511
Feature activation+2.15e-02

Pos logit contributions
 ounces+0.002
ets+0.002
 pounds+0.002
ocol+0.002
hell+0.002
Neg logit contributions
 blowing-0.001
burn-0.001
 daddy-0.001
 neighborhood-0.001
 waving-0.001
Token snow
Token ID6729
Feature activation-6.63e+00

Pos logit contributions
 ounces+0.001
 pounds+0.001
ocol+0.001
 dollars+0.001
ets+0.001
Neg logit contributions
 blowing-0.000
burn-0.000
rolling-0.000
 waving-0.000
 neighborhood-0.000
Tokenman
Token ID805
Feature activation-1.84e+00

Pos logit contributions
 blowing+0.109
burn+0.097
 neighborhood+0.086
 daddy+0.085
 waving+0.082
Neg logit contributions
 ounces-0.267
ets-0.259
hell-0.255
 pounds-0.248
izards-0.246
Token.
Token ID13
Feature activation-7.36e-01

Pos logit contributions
 blowing+0.041
burn+0.040
 daddy+0.037
 waving+0.036
 mom+0.035
Neg logit contributions
 ounces-0.066
ocol-0.063
ets-0.060
 pounds-0.059
izards-0.059
Token They
Token ID1119
Feature activation+1.28e+00

Pos logit contributions
 blowing+0.021
burn+0.020
 daddy+0.017
 waving+0.017
 leaning+0.017
Neg logit contributions
 ounces-0.022
ets-0.021
izards-0.020
hell-0.020
ocol-0.019
Token were
Token ID547
Feature activation-9.88e-01

Pos logit contributions
 ounces+0.043
ets+0.042
hell+0.040
izards+0.039
 pounds+0.039
Neg logit contributions
 blowing-0.030
burn-0.029
 daddy-0.026
 waving-0.025
 neighborhood-0.025
Token happy
Token ID3772
Feature activation-8.25e-01

Pos logit contributions
 blowing+0.022
burn+0.021
 neighborhood+0.018
 daddy+0.017
zag+0.017
Neg logit contributions
 ounces-0.032
ets-0.031
izards-0.031
hell-0.031
 dollars-0.030
Token nodded
Token ID14464
Feature activation-3.06e+00

Pos logit contributions
burn+0.032
 blowing+0.031
 daddy+0.027
 shining+0.026
 neighborhood+0.025
Neg logit contributions
ets-0.042
 ounces-0.042
ly-0.040
hell-0.039
izards-0.038
Token.
Token ID13
Feature activation+3.04e-01

Pos logit contributions
 blowing+0.072
burn+0.069
 daddy+0.062
 neighborhood+0.060
 waving+0.059
Neg logit contributions
 ounces-0.106
ets-0.101
ocol-0.097
 pounds-0.097
hell-0.096
Token He
Token ID679
Feature activation+1.66e-01

Pos logit contributions
 ounces+0.011
ets+0.011
ocol+0.011
izards+0.011
 pounds+0.010
Neg logit contributions
 blowing-0.006
 daddy-0.006
burn-0.006
 mom-0.005
 neighborhood-0.005
Token liked
Token ID8288
Feature activation-2.08e+00

Pos logit contributions
 ounces+0.006
ets+0.006
hell+0.005
 pounds+0.005
izards+0.005
Neg logit contributions
 blowing-0.004
burn-0.004
 daddy-0.003
 neighborhood-0.003
 waving-0.003
Token their
Token ID511
Feature activation-1.27e+00

Pos logit contributions
 blowing+0.041
burn+0.039
 daddy+0.034
 neighborhood+0.033
 waving+0.033
Neg logit contributions
 ounces-0.079
ets-0.075
 pounds-0.072
ocol-0.072
hell-0.072
Token snow
Token ID6729
Feature activation-6.60e+00

Pos logit contributions
 blowing+0.032
burn+0.031
 neighborhood+0.027
 leaning+0.027
 waving+0.026
Neg logit contributions
 ounces-0.038
 pounds-0.034
ets-0.034
 dollars-0.033
ocol-0.033
Token baby
Token ID5156
Feature activation-1.40e+00

Pos logit contributions
 blowing+0.106
burn+0.097
 daddy+0.086
 neighborhood+0.083
 waving+0.081
Neg logit contributions
 ounces-0.272
ets-0.263
hell-0.255
 pounds-0.252
izards-0.249
Token.
Token ID13
Feature activation+1.35e-01

Pos logit contributions
 blowing+0.030
burn+0.029
 daddy+0.026
 waving+0.025
 shining+0.024
Neg logit contributions
 ounces-0.052
ocol-0.050
ets-0.050
izards-0.048
hell-0.047
Token He
Token ID679
Feature activation-2.84e-01

Pos logit contributions
 ounces+0.005
ils+0.005
ets+0.005
izards+0.005
 pounds+0.005
Neg logit contributions
 mom-0.002
 Mom-0.002
 daddy-0.002
 blowing-0.002
-0.002
Token wanted
Token ID2227
Feature activation-6.72e-01

Pos logit contributions
 blowing+0.006
burn+0.006
 daddy+0.005
 neighborhood+0.005
 waving+0.005
Neg logit contributions
 ounces-0.010
ets-0.010
 pounds-0.009
hell-0.009
izards-0.009
Token to
Token ID284
Feature activation-1.61e+00

Pos logit contributions
 blowing+0.010
burn+0.010
 daddy+0.008
 waving+0.008
 neighborhood+0.008
Neg logit contributions
 ounces-0.029
ets-0.028
ocol-0.027
 pounds-0.027
hell-0.027
Token back
Token ID736
Feature activation-2.98e+00

Pos logit contributions
 blowing+0.031
burn+0.030
 daddy+0.027
 waving+0.026
 mom+0.025
Neg logit contributions
 ounces-0.051
ocol-0.049
ets-0.046
izards-0.046
 pounds-0.045
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
 blowing+0.083
burn+0.080
 daddy+0.074
 neighborhood+0.071
 waving+0.071
Neg logit contributions
 ounces-0.090
ets-0.085
 pounds-0.080
ocol-0.080
hell-0.080
Token They
Token ID1119
Feature activation+1.04e+00

Pos logit contributions
 blowing+0.022
burn+0.020
 waving+0.017
 shining+0.016
 leaning+0.016
Neg logit contributions
 ounces-0.042
ets-0.039
izards-0.039
hell-0.039
ocol-0.038
Token missed
Token ID6825
Feature activation-2.26e+00

Pos logit contributions
 ounces+0.039
ets+0.037
ocol+0.036
 pounds+0.036
hell+0.035
Neg logit contributions
 blowing-0.021
burn-0.020
 daddy-0.018
 waving-0.017
 neighborhood-0.017
Token their
Token ID511
Feature activation-8.59e-01

Pos logit contributions
burn+0.046
 blowing+0.045
 neighborhood+0.040
 waving+0.037
zag+0.036
Neg logit contributions
 ounces-0.081
ets-0.077
ocol-0.076
 pounds-0.076
izards-0.075
Token snow
Token ID6729
Feature activation-6.55e+00

Pos logit contributions
 blowing+0.016
burn+0.015
 leaning+0.013
rolling+0.012
 waving+0.012
Neg logit contributions
 ounces-0.031
 dollars-0.030
ets-0.029
 pounds-0.029
hell-0.029
Tokenman
Token ID805
Feature activation-2.19e+00

Pos logit contributions
 blowing+0.110
burn+0.095
 neighborhood+0.088
 daddy+0.088
 waving+0.087
Neg logit contributions
 ounces-0.258
ets-0.253
hell-0.248
 pounds-0.241
 dollars-0.236
Token very
Token ID845
Feature activation+1.28e+00

Pos logit contributions
 blowing+0.043
burn+0.042
 daddy+0.037
 waving+0.035
 mom+0.035
Neg logit contributions
 ounces-0.084
ocol-0.083
izards-0.078
ets-0.078
 pounds-0.076
Token much
Token ID881
Feature activation-6.31e-01

Pos logit contributions
 ounces+0.043
ocol+0.040
ets+0.040
izards+0.039
 pounds+0.038
Neg logit contributions
 blowing-0.031
burn-0.029
 daddy-0.028
 neighborhood-0.026
 waving-0.026
Token.
Token ID13
Feature activation-1.21e+00

Pos logit contributions
 next+0.009
 blowing+0.009
 mom+0.009
 still+0.008
 daddy+0.008
Neg logit contributions
ocol-0.028
 ounces-0.027
izards-0.026
bors-0.025
bridge-0.024
Token They
Token ID1119
Feature activation+9.61e-01

Pos logit contributions
 blowing+0.026
burn+0.024
 waving+0.020
 daddy+0.019
 shining+0.019
Neg logit contributions
 ounces-0.045
ets-0.042
izards-0.041
ocol-0.041
hell-0.041
Token
Token ID198
Feature activation-4.34e-02

Pos logit contributions
 ounces+0.026
ets+0.025
ocol+0.024
 pounds+0.024
hell+0.024
Neg logit contributions
 blowing-0.011
burn-0.010
 daddy-0.009
 waving-0.008
 neighborhood-0.008
Token
Token ID198
Feature activation+5.97e-01

Pos logit contributions
 blowing+0.001
burn+0.001
 daddy+0.001
 waving+0.001
 leaning+0.001
Neg logit contributions
 ounces-0.002
ets-0.002
hell-0.002
izards-0.002
 pounds-0.002
TokenThey
Token ID2990
Feature activation+1.50e+00

Pos logit contributions
 ounces+0.023
ets+0.022
ocol+0.022
izards+0.021
hell+0.021
Neg logit contributions
 blowing-0.012
burn-0.011
 daddy-0.009
 neighborhood-0.009
 blew-0.009
Token hugged
Token ID41130
Feature activation+5.96e-02

Pos logit contributions
 ounces+0.056
ets+0.053
ocol+0.051
 pounds+0.051
hell+0.051
Neg logit contributions
 blowing-0.031
burn-0.030
 daddy-0.027
 waving-0.025
 neighborhood-0.025
Token their
Token ID511
Feature activation-2.52e-01

Pos logit contributions
 ounces+0.003
ets+0.002
ocol+0.002
 pounds+0.002
hell+0.002
Neg logit contributions
 blowing-0.001
burn-0.001
 daddy-0.001
 mom-0.001
 waving-0.001
Token snow
Token ID6729
Feature activation-6.50e+00

Pos logit contributions
 blowing+0.006
burn+0.006
 leaning+0.005
 neighborhood+0.005
 waving+0.005
Neg logit contributions
 ounces-0.008
 pounds-0.008
 dollars-0.008
ocol-0.007
ets-0.007
Tokenman
Token ID805
Feature activation-1.60e+00

Pos logit contributions
 blowing+0.118
burn+0.106
 neighborhood+0.100
 leaning+0.096
 daddy+0.094
Neg logit contributions
 ounces-0.240
ets-0.235
hell-0.232
 pounds-0.224
ly-0.224
Token and
Token ID290
Feature activation-3.27e-01

Pos logit contributions
 blowing+0.028
burn+0.026
 daddy+0.023
 waving+0.021
 neighborhood+0.021
Neg logit contributions
 ounces-0.065
ets-0.062
ocol-0.060
 pounds-0.060
izards-0.060
Token ran
Token ID4966
Feature activation+1.69e+00

Pos logit contributions
 blowing+0.007
burn+0.007
 neighborhood+0.006
 daddy+0.006
 leaning+0.006
Neg logit contributions
 ounces-0.011
ets-0.011
 dollars-0.010
 pounds-0.010
hell-0.010
Token inside
Token ID2641
Feature activation-2.28e+00

Pos logit contributions
 ounces+0.077
ocol+0.074
 pounds+0.073
izards+0.071
 dollars+0.070
Neg logit contributions
 blowing-0.024
burn-0.022
 daddy-0.019
 waving-0.018
 spinning-0.017
Token to
Token ID284
Feature activation+9.41e-01

Pos logit contributions
burn+0.063
 blowing+0.061
 neighborhood+0.054
 daddy+0.054
 leaning+0.052
Neg logit contributions
 ounces-0.066
ets-0.063
ocol-0.060
 pounds-0.060
hell-0.059
TokenThey
Token ID2990
Feature activation+1.78e+00

Pos logit contributions
 ounces+0.011
ets+0.011
hell+0.010
 pounds+0.010
izards+0.010
Neg logit contributions
 blowing-0.009
burn-0.009
 daddy-0.008
 waving-0.008
 shining-0.008
Token laughed
Token ID13818
Feature activation-6.44e-01

Pos logit contributions
 ounces+0.065
ets+0.062
hell+0.059
ocol+0.059
 pounds+0.059
Neg logit contributions
 blowing-0.039
burn-0.037
 daddy-0.032
 neighborhood-0.031
 waving-0.031
Token and
Token ID290
Feature activation-1.08e-01

Pos logit contributions
 blowing+0.011
burn+0.011
 daddy+0.009
 waving+0.009
 neighborhood+0.009
Neg logit contributions
 ounces-0.026
ets-0.025
ocol-0.024
 pounds-0.024
hell-0.024
Token hugged
Token ID41130
Feature activation+3.95e-01

Pos logit contributions
 blowing+0.002
burn+0.002
 daddy+0.002
 neighborhood+0.002
 waving+0.002
Neg logit contributions
 ounces-0.004
ets-0.004
hell-0.003
izards-0.003
 pounds-0.003
Token their
Token ID511
Feature activation-5.29e-02

Pos logit contributions
 ounces+0.015
ets+0.014
ocol+0.014
izards+0.014
 pounds+0.014
Neg logit contributions
 blowing-0.008
burn-0.007
 daddy-0.007
 mom-0.006
 waving-0.006
Token snow
Token ID6729
Feature activation-6.49e+00

Pos logit contributions
 blowing+0.001
burn+0.001
 leaning+0.001
 neighborhood+0.001
zag+0.001
Neg logit contributions
 ounces-0.002
 pounds-0.002
 dollars-0.002
ocol-0.002
ets-0.002
Tokenman
Token ID805
Feature activation-1.76e+00

Pos logit contributions
 blowing+0.105
burn+0.095
 neighborhood+0.084
 daddy+0.084
 waving+0.079
Neg logit contributions
 ounces-0.264
ets-0.256
hell-0.249
 pounds-0.246
 dollars-0.242
Token.
Token ID13
Feature activation-3.36e-01

Pos logit contributions
 blowing+0.040
burn+0.038
 daddy+0.036
 waving+0.034
 mom+0.033
Neg logit contributions
 ounces-0.063
ocol-0.059
ets-0.058
izards-0.057
 pounds-0.056
Token They
Token ID1119
Feature activation+1.49e+00

Pos logit contributions
 blowing+0.010
burn+0.010
 daddy+0.008
 neighborhood+0.008
 leaning+0.008
Neg logit contributions
 ounces-0.009
ets-0.009
hell-0.008
ocol-0.008
izards-0.008
Token thought
Token ID1807
Feature activation+1.56e+00

Pos logit contributions
 ounces+0.051
ets+0.049
hell+0.047
izards+0.046
 pounds+0.046
Neg logit contributions
 blowing-0.035
burn-0.033
 daddy-0.029
 neighborhood-0.029
 waving-0.028
Token he
Token ID339
Feature activation+1.03e+00

Pos logit contributions
 ounces+0.047
ets+0.044
ocol+0.042
hell+0.041
 pounds+0.041
Neg logit contributions
 blowing-0.044
burn-0.041
 daddy-0.040
 waving-0.038
 leaning-0.037
Token smiled
Token ID13541
Feature activation-2.41e+00

Pos logit contributions
 ounces+0.046
ets+0.045
hell+0.043
izards+0.042
 pounds+0.042
Neg logit contributions
 blowing-0.030
burn-0.028
 daddy-0.025
 neighborhood-0.025
 waving-0.024
Token and
Token ID290
Feature activation-5.62e-01

Pos logit contributions
 blowing+0.063
burn+0.063
 leaning+0.053
 neighborhood+0.053
 blew+0.052
Neg logit contributions
ets-0.071
ly-0.069
 dollars-0.064
hell-0.063
 ounces-0.063
Token played
Token ID2826
Feature activation-2.06e+00

Pos logit contributions
 blowing+0.014
burn+0.013
 neighborhood+0.012
 daddy+0.012
 leaning+0.011
Neg logit contributions
ets-0.017
 ounces-0.017
ly-0.015
hell-0.015
 dollars-0.015
Token with
Token ID351
Feature activation+1.61e+00

Pos logit contributions
 blowing+0.028
burn+0.023
 daddy+0.023
 waving+0.022
 neighborhood+0.022
Neg logit contributions
 ounces-0.095
ocol-0.087
 pounds-0.087
ets-0.087
hell-0.085
Token their
Token ID511
Feature activation-9.87e-02

Pos logit contributions
 ounces+0.067
ets+0.064
 pounds+0.062
ocol+0.061
hell+0.061
Neg logit contributions
 blowing-0.027
burn-0.026
 daddy-0.023
 neighborhood-0.021
 waving-0.021
Token snow
Token ID6729
Feature activation-6.41e+00

Pos logit contributions
burn+0.002
 blowing+0.002
zag+0.002
rolling+0.002
ina+0.002
Neg logit contributions
 ounces-0.003
ocol-0.003
 dollars-0.003
 pounds-0.003
ets-0.003
Tokenman
Token ID805
Feature activation-1.90e+00

Pos logit contributions
 blowing+0.115
burn+0.106
 daddy+0.094
 neighborhood+0.094
 waving+0.091
Neg logit contributions
 ounces-0.243
ets-0.239
hell-0.233
 pounds-0.226
bridge-0.224
Token until
Token ID1566
Feature activation+8.43e-01

Pos logit contributions
 blowing+0.041
burn+0.038
 daddy+0.035
 waving+0.034
 neighborhood+0.033
Neg logit contributions
 ounces-0.070
ets-0.066
ocol-0.066
izards-0.063
hell-0.063
Token it
Token ID340
Feature activation+1.72e+00

Pos logit contributions
 ounces+0.025
ets+0.023
ocol+0.023
hell+0.022
 pounds+0.022
Neg logit contributions
 blowing-0.023
burn-0.022
 neighborhood-0.021
 daddy-0.020
 waving-0.020
Token was
Token ID373
Feature activation-3.01e-01

Pos logit contributions
 ounces+0.067
ets+0.066
hell+0.064
bridge+0.063
ly+0.061
Neg logit contributions
 blowing-0.029
burn-0.028
 daddy-0.027
 neighborhood-0.024
 waving-0.023
Token time
Token ID640
Feature activation-7.88e-01

Pos logit contributions
 blowing+0.007
burn+0.007
 neighborhood+0.007
 daddy+0.006
 waving+0.006
Neg logit contributions
ets-0.009
 ounces-0.008
ocol-0.008
hell-0.008
bridge-0.008
Token know
Token ID760
Feature activation+1.37e-01

Pos logit contributions
 blowing+0.007
burn+0.007
 daddy+0.006
 waving+0.006
 leaning+0.006
Neg logit contributions
 ounces-0.011
ets-0.011
hell-0.011
izards-0.010
 dollars-0.010
Token you
Token ID345
Feature activation+3.32e+00

Pos logit contributions
ets+0.004
 ounces+0.004
hell+0.004
ocol+0.004
 dollars+0.004
Neg logit contributions
 daddy-0.004
 blowing-0.004
 mom-0.004
 waving-0.003
 grandma-0.003
Token loved
Token ID6151
Feature activation-2.38e+00

Pos logit contributions
 ounces+0.128
ocol+0.121
ets+0.117
 pounds+0.116
 dollars+0.114
Neg logit contributions
 blowing-0.068
burn-0.063
 daddy-0.060
 waving-0.054
 neighborhood-0.054
Token your
Token ID534
Feature activation-1.19e+00

Pos logit contributions
 blowing+0.062
 daddy+0.058
burn+0.056
 mom+0.052
 waving+0.052
Neg logit contributions
 ounces-0.076
ets-0.076
hell-0.072
 dollars-0.069
izards-0.069
Token blue
Token ID4171
Feature activation-5.47e+00

Pos logit contributions
 blowing+0.029
burn+0.027
 leaning+0.024
 neighborhood+0.023
 waving+0.023
Neg logit contributions
 ounces-0.038
ets-0.035
 pounds-0.035
 dollars-0.035
ocol-0.034
Token snow
Token ID6729
Feature activation-6.41e+00

Pos logit contributions
 blowing+0.128
burn+0.117
 waving+0.105
 leaning+0.105
 daddy+0.104
Neg logit contributions
 ounces-0.181
ets-0.172
ocol-0.168
 pounds-0.167
hell-0.167
Tokenman
Token ID805
Feature activation-1.86e+00

Pos logit contributions
 blowing+0.091
burn+0.085
 daddy+0.071
 waving+0.065
 neighborhood+0.065
Neg logit contributions
 ounces-0.281
ets-0.270
ocol-0.261
 pounds-0.260
hell-0.260
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
 blowing+0.042
burn+0.040
 daddy+0.038
 crying+0.035
 mom+0.035
Neg logit contributions
 ounces-0.066
ocol-0.065
ets-0.062
izards-0.061
 pounds-0.059
Token But
Token ID887
Feature activation-2.59e-01

Pos logit contributions
 blowing+0.037
burn+0.036
 daddy+0.035
 waving+0.033
 neighborhood+0.032
Neg logit contributions
 ounces-0.041
ets-0.039
hell-0.037
 pounds-0.037
izards-0.037
Token you
Token ID345
Feature activation+3.30e+00

Pos logit contributions
 blowing+0.009
burn+0.009
 neighborhood+0.008
 daddy+0.008
 waving+0.008
Neg logit contributions
 ounces-0.006
ets-0.006
ocol-0.006
 pounds-0.005
izards-0.005
Token know
Token ID760
Feature activation-2.44e-02

Pos logit contributions
 ounces+0.119
 pounds+0.109
ocol+0.109
ets+0.108
 dollars+0.104
Neg logit contributions
 blowing-0.075
burn-0.069
 daddy-0.068
 also-0.063
 neighborhood-0.062
Token are
Token ID389
Feature activation-5.37e-01

Pos logit contributions
 ounces+0.028
 pounds+0.026
ets+0.025
ocol+0.025
hell+0.025
Neg logit contributions
 blowing-0.014
 daddy-0.013
burn-0.013
 also-0.011
 waving-0.011
Token very
Token ID845
Feature activation+4.55e-01

Pos logit contributions
 blowing+0.010
burn+0.010
 daddy+0.008
 neighborhood+0.008
 waving+0.008
Neg logit contributions
 ounces-0.021
ets-0.020
 pounds-0.019
izards-0.019
ocol-0.019
Token happy
Token ID3772
Feature activation-1.19e-01

Pos logit contributions
 ounces+0.018
ets+0.017
ocol+0.017
 pounds+0.017
hell+0.017
Neg logit contributions
 blowing-0.009
burn-0.008
 daddy-0.007
 neighborhood-0.007
 waving-0.007
Token with
Token ID351
Feature activation-4.12e-01

Pos logit contributions
 blowing+0.003
burn+0.003
 daddy+0.003
 waving+0.003
 neighborhood+0.003
Neg logit contributions
 ounces-0.004
ets-0.004
ocol-0.004
hell-0.004
 pounds-0.004
Token their
Token ID511
Feature activation-2.95e-01

Pos logit contributions
 blowing+0.006
 daddy+0.005
burn+0.005
 mom+0.005
 waving+0.005
Neg logit contributions
 ounces-0.018
ets-0.018
hell-0.017
izards-0.017
 pounds-0.016
Token snow
Token ID6729
Feature activation-6.37e+00

Pos logit contributions
 blowing+0.007
burn+0.007
 leaning+0.006
 waving+0.006
 neighborhood+0.006
Neg logit contributions
 ounces-0.010
 pounds-0.009
ets-0.009
ocol-0.009
 dollars-0.009
Tokenman
Token ID805
Feature activation-1.50e+00

Pos logit contributions
 blowing+0.108
burn+0.098
 neighborhood+0.087
 daddy+0.086
 waving+0.084
Neg logit contributions
 ounces-0.254
ets-0.248
hell-0.240
 pounds-0.237
izards-0.233
Token.
Token ID13
Feature activation-6.74e-01

Pos logit contributions
 blowing+0.036
burn+0.034
 daddy+0.031
 waving+0.031
 leaning+0.029
Neg logit contributions
 ounces-0.054
ocol-0.050
ets-0.049
izards-0.047
 pounds-0.047
Token
Token ID198
Feature activation-1.01e+00

Pos logit contributions
 blowing+0.013
burn+0.012
 daddy+0.010
 shining+0.010
 waving+0.010
Neg logit contributions
 ounces-0.026
ets-0.025
hell-0.024
 dollars-0.024
 pounds-0.024
Token
Token ID198
Feature activation+2.42e-01

Pos logit contributions
burn+0.021
 blowing+0.020
 daddy+0.018
flower+0.017
 shining+0.016
Neg logit contributions
 ounces-0.036
hell-0.036
ets-0.035
izards-0.034
 pounds-0.033
TokenBut
Token ID1537
Feature activation+1.25e+00

Pos logit contributions
 ounces+0.009
ets+0.009
ocol+0.008
 pounds+0.008
hell+0.008
Neg logit contributions
 blowing-0.005
burn-0.005
 daddy-0.004
 waving-0.004
 neighborhood-0.004
Token They
Token ID1119
Feature activation+1.09e+00

Pos logit contributions
 blowing+0.017
burn+0.017
 daddy+0.015
 waving+0.014
 leaning+0.014
Neg logit contributions
 ounces-0.017
ets-0.017
hell-0.016
izards-0.016
 dollars-0.016
Token were
Token ID547
Feature activation-9.67e-01

Pos logit contributions
 ounces+0.041
ets+0.039
ocol+0.038
 pounds+0.038
izards+0.037
Neg logit contributions
 blowing-0.023
burn-0.021
 daddy-0.019
 waving-0.018
 neighborhood-0.018
Token happy
Token ID3772
Feature activation-8.22e-01

Pos logit contributions
burn+0.020
 blowing+0.019
 neighborhood+0.017
 daddy+0.016
 waving+0.014
Neg logit contributions
 ounces-0.035
ets-0.034
izards-0.033
 pounds-0.032
hell-0.032
Token with
Token ID351
Feature activation-5.86e-01

Pos logit contributions
 blowing+0.018
burn+0.017
 daddy+0.015
 waving+0.015
 neighborhood+0.015
Neg logit contributions
 ounces-0.030
ets-0.029
ocol-0.028
 pounds-0.028
hell-0.027
Token their
Token ID511
Feature activation-3.61e-01

Pos logit contributions
 blowing+0.010
burn+0.010
 daddy+0.008
 neighborhood+0.008
 waving+0.008
Neg logit contributions
 ounces-0.024
ets-0.023
ocol-0.022
 pounds-0.022
hell-0.022
Token snow
Token ID6729
Feature activation-6.32e+00

Pos logit contributions
burn+0.009
 blowing+0.009
zag+0.008
 daddy+0.007
 neighborhood+0.007
Neg logit contributions
 ounces-0.011
ocol-0.010
 pounds-0.010
ets-0.010
 dollars-0.010
Tokenman
Token ID805
Feature activation-1.68e+00

Pos logit contributions
 blowing+0.106
burn+0.096
 neighborhood+0.087
 daddy+0.087
 waving+0.083
Neg logit contributions
 ounces-0.248
ets-0.244
hell-0.238
 pounds-0.232
izards-0.229
Token.
Token ID13
Feature activation-9.07e-01

Pos logit contributions
 blowing+0.037
burn+0.034
 daddy+0.031
 waving+0.031
 mom+0.029
Neg logit contributions
 ounces-0.062
ocol-0.060
ets-0.057
izards-0.056
 pounds-0.056
Token
Token ID198
Feature activation-6.05e-01

Pos logit contributions
 blowing+0.024
burn+0.023
 daddy+0.020
 waving+0.019
 leaning+0.019
Neg logit contributions
ets-0.028
 ounces-0.027
hell-0.026
izards-0.025
ocol-0.025
Token
Token ID198
Feature activation+2.37e-01

Pos logit contributions
burn+0.012
 blowing+0.011
 daddy+0.009
 shining+0.009
 waving+0.009
Neg logit contributions
 ounces-0.023
ets-0.022
hell-0.022
izards-0.022
 pounds-0.021
TokenBut
Token ID1537
Feature activation+1.33e+00

Pos logit contributions
 ounces+0.008
ets+0.008
ocol+0.008
 pounds+0.008
izards+0.008
Neg logit contributions
 blowing-0.006
burn-0.005
 daddy-0.005
 neighborhood-0.005
 waving-0.005
Token
Token ID198
Feature activation-4.11e-01

Pos logit contributions
 blowing+0.011
burn+0.010
 daddy+0.010
 neighborhood+0.009
 waving+0.009
Neg logit contributions
 ounces-0.017
ets-0.016
 pounds-0.015
ocol-0.015
izards-0.015
Token
Token ID198
Feature activation+4.75e-01

Pos logit contributions
burn+0.008
 blowing+0.007
 daddy+0.006
 shining+0.006
 waving+0.006
Neg logit contributions
 ounces-0.016
hell-0.015
ets-0.015
izards-0.015
 pounds-0.015
TokenThey
Token ID2990
Feature activation+1.57e+00

Pos logit contributions
 ounces+0.017
ets+0.017
ocol+0.016
 pounds+0.016
izards+0.016
Neg logit contributions
 blowing-0.010
burn-0.009
 daddy-0.009
 neighborhood-0.008
 waving-0.008
Token hugged
Token ID41130
Feature activation+4.45e-01

Pos logit contributions
 ounces+0.061
ets+0.058
ocol+0.056
 pounds+0.056
hell+0.055
Neg logit contributions
 blowing-0.031
burn-0.029
 daddy-0.027
 waving-0.025
 neighborhood-0.024
Token their
Token ID511
Feature activation+3.96e-01

Pos logit contributions
 ounces+0.019
ets+0.018
ocol+0.018
 pounds+0.018
izards+0.017
Neg logit contributions
 blowing-0.007
burn-0.007
 daddy-0.006
 mom-0.006
 waving-0.006
Token snow
Token ID6729
Feature activation-6.28e+00

Pos logit contributions
 ounces+0.013
ets+0.012
 pounds+0.012
ocol+0.012
 dollars+0.012
Neg logit contributions
 blowing-0.009
burn-0.009
 neighborhood-0.008
 leaning-0.007
 waving-0.007
Tokenman
Token ID805
Feature activation-1.37e+00

Pos logit contributions
 blowing+0.118
burn+0.103
 neighborhood+0.101
 leaning+0.096
 spinning+0.094
Neg logit contributions
 ounces-0.228
ets-0.225
hell-0.223
ly-0.213
 pounds-0.212
Token and
Token ID290
Feature activation-1.54e-01

Pos logit contributions
 blowing+0.023
burn+0.021
 daddy+0.019
 waving+0.017
 neighborhood+0.017
Neg logit contributions
 ounces-0.057
ets-0.054
ocol-0.053
 pounds-0.052
izards-0.052
Token said
Token ID531
Feature activation+1.84e+00

Pos logit contributions
 blowing+0.003
burn+0.003
 daddy+0.003
 neighborhood+0.003
 waving+0.003
Neg logit contributions
 ounces-0.005
ets-0.005
 pounds-0.005
hell-0.005
ocol-0.005
Token goodbye
Token ID24829
Feature activation+7.97e-01

Pos logit contributions
 ounces+0.075
ets+0.074
 pounds+0.069
ocol+0.069
izards+0.068
Neg logit contributions
 blowing-0.032
 daddy-0.030
burn-0.029
 waving-0.026
 mom-0.026
Token.
Token ID13
Feature activation-4.14e-01

Pos logit contributions
 ounces+0.033
ocol+0.031
ets+0.030
izards+0.030
 pounds+0.030
Neg logit contributions
 blowing-0.015
burn-0.014
 daddy-0.012
 waving-0.012
 crying-0.011
Token were
Token ID547
Feature activation-9.59e-01

Pos logit contributions
 ounces+0.033
ets+0.032
ocol+0.031
 pounds+0.031
hell+0.030
Neg logit contributions
 blowing-0.018
burn-0.017
 daddy-0.016
 waving-0.015
 neighborhood-0.014
Token very
Token ID845
Feature activation+6.82e-01

Pos logit contributions
burn+0.019
 blowing+0.018
 neighborhood+0.015
 daddy+0.015
 waving+0.014
Neg logit contributions
 ounces-0.036
ets-0.034
 pounds-0.033
izards-0.033
ocol-0.033
Token happy
Token ID3772
Feature activation+1.15e-01

Pos logit contributions
 ounces+0.027
ets+0.025
 pounds+0.025
ocol+0.025
hell+0.024
Neg logit contributions
 blowing-0.013
burn-0.013
 daddy-0.011
 neighborhood-0.010
 waving-0.010
Token with
Token ID351
Feature activation-1.69e-01

Pos logit contributions
 ounces+0.004
ets+0.004
ocol+0.004
 pounds+0.003
hell+0.003
Neg logit contributions
 blowing-0.003
burn-0.003
 daddy-0.003
 waving-0.002
 neighborhood-0.002
Token their
Token ID511
Feature activation-1.88e-01

Pos logit contributions
 blowing+0.003
 daddy+0.002
burn+0.002
 waving+0.002
 mom+0.002
Neg logit contributions
 ounces-0.007
ets-0.007
hell-0.007
izards-0.007
 pounds-0.007
Token snow
Token ID6729
Feature activation-6.28e+00

Pos logit contributions
 blowing+0.005
burn+0.005
 leaning+0.004
 waving+0.004
 neighborhood+0.004
Neg logit contributions
 ounces-0.006
 pounds-0.006
ets-0.005
 dollars-0.005
ocol-0.005
Tokenman
Token ID805
Feature activation-1.48e+00

Pos logit contributions
 blowing+0.107
burn+0.098
 neighborhood+0.088
 daddy+0.087
 waving+0.084
Neg logit contributions
 ounces-0.247
ets-0.241
hell-0.233
 pounds-0.231
izards-0.225
Token.
Token ID13
Feature activation-3.28e-01

Pos logit contributions
 blowing+0.036
burn+0.034
 daddy+0.031
 waving+0.031
 leaning+0.029
Neg logit contributions
 ounces-0.052
ocol-0.049
ets-0.049
izards-0.046
 pounds-0.046
Token
Token ID198
Feature activation-7.39e-01

Pos logit contributions
 blowing+0.005
burn+0.005
 daddy+0.004
 waving+0.004
 neighborhood+0.004
Neg logit contributions
 ounces-0.014
ets-0.013
hell-0.013
ocol-0.013
izards-0.013
Token
Token ID198
Feature activation+4.73e-01

Pos logit contributions
burn+0.015
 blowing+0.014
 daddy+0.012
 waving+0.012
 leaning+0.012
Neg logit contributions
 ounces-0.026
hell-0.026
ets-0.026
izards-0.025
 pounds-0.024
TokenBut
Token ID1537
Feature activation+1.34e+00

Pos logit contributions
 ounces+0.016
ets+0.015
 pounds+0.014
ocol+0.014
izards+0.014
Neg logit contributions
 blowing-0.012
burn-0.011
 daddy-0.010
 neighborhood-0.010
 waving-0.010
Token smiles
Token ID21845
Feature activation-3.14e+00

Pos logit contributions
 ounces+0.039
ets+0.038
izards+0.036
 dollars+0.035
 pounds+0.035
Neg logit contributions
 blowing-0.038
burn-0.038
 daddy-0.032
 neighborhood-0.032
 shining-0.031
Token.
Token ID13
Feature activation-8.18e-01

Pos logit contributions
 blowing+0.097
burn+0.096
 daddy+0.087
 neighborhood+0.086
 leaning+0.081
Neg logit contributions
ets-0.077
 ounces-0.074
izards-0.070
hell-0.070
ly-0.069
Token She
Token ID1375
Feature activation+9.88e-01

Pos logit contributions
 blowing+0.021
burn+0.021
 daddy+0.017
 waving+0.016
 shining+0.016
Neg logit contributions
 ounces-0.026
ets-0.025
izards-0.025
hell-0.024
ocol-0.023
Token thinks
Token ID6834
Feature activation+1.55e+00

Pos logit contributions
ets+0.028
 ounces+0.028
izards+0.026
 dollars+0.026
hell+0.025
Neg logit contributions
 blowing-0.029
burn-0.028
 daddy-0.025
 shining-0.024
 neighborhood-0.024
Token the
Token ID262
Feature activation-2.70e+00

Pos logit contributions
 ounces+0.053
ets+0.051
hell+0.047
 pounds+0.047
ocol+0.047
Neg logit contributions
 blowing-0.039
 daddy-0.035
burn-0.034
 waving-0.033
 leaning-0.032
Token snow
Token ID6729
Feature activation-6.28e+00

Pos logit contributions
 blowing+0.066
burn+0.064
 daddy+0.057
 neighborhood+0.055
 waving+0.055
Neg logit contributions
 ounces-0.088
ets-0.083
 pounds-0.082
 dollars-0.080
hell-0.079
Tokenman
Token ID805
Feature activation-1.48e+00

Pos logit contributions
 blowing+0.104
burn+0.095
 daddy+0.084
 neighborhood+0.081
 waving+0.079
Neg logit contributions
 ounces-0.259
ets-0.249
hell-0.241
 pounds-0.240
izards-0.236
Token is
Token ID318
Feature activation-1.28e+00

Pos logit contributions
 blowing+0.022
burn+0.019
 daddy+0.017
 waving+0.017
 also+0.017
Neg logit contributions
 ounces-0.062
ocol-0.060
ets-0.058
izards-0.057
 pounds-0.057
Token happy
Token ID3772
Feature activation-1.47e+00

Pos logit contributions
 blowing+0.025
burn+0.023
 daddy+0.021
 waving+0.020
 shining+0.019
Neg logit contributions
 ounces-0.050
ets-0.048
ocol-0.046
 pounds-0.046
hell-0.046
Token now
Token ID783
Feature activation-2.58e+00

Pos logit contributions
 blowing+0.037
burn+0.033
 daddy+0.033
 waving+0.032
 leaning+0.031
Neg logit contributions
 ounces-0.051
ets-0.047
ocol-0.047
 pounds-0.045
hell-0.045
Token.
Token ID13
Feature activation-9.10e-01

Pos logit contributions
 blowing+0.053
burn+0.044
 waving+0.044
 next+0.043
 leaning+0.043
Neg logit contributions
 ounces-0.103
ocol-0.100
izards-0.095
ets-0.094
 pounds-0.092
Token were
Token ID547
Feature activation-9.07e-01

Pos logit contributions
 ounces+0.035
ets+0.033
ocol+0.032
 pounds+0.032
hell+0.031
Neg logit contributions
 blowing-0.019
burn-0.018
 daddy-0.016
 waving-0.015
 neighborhood-0.015
Token very
Token ID845
Feature activation+6.67e-01

Pos logit contributions
burn+0.018
 blowing+0.018
 neighborhood+0.015
 daddy+0.015
 waving+0.014
Neg logit contributions
 ounces-0.033
ets-0.032
 pounds-0.031
ocol-0.031
izards-0.030
Token happy
Token ID3772
Feature activation+1.30e-01

Pos logit contributions
 ounces+0.025
ets+0.024
 pounds+0.023
ocol+0.023
 dollars+0.023
Neg logit contributions
burn-0.014
 blowing-0.013
 neighborhood-0.011
 daddy-0.011
 waving-0.011
Token with
Token ID351
Feature activation-3.55e-01

Pos logit contributions
 ounces+0.004
ets+0.004
ocol+0.004
 pounds+0.004
hell+0.004
Neg logit contributions
 blowing-0.003
burn-0.003
 daddy-0.003
 waving-0.003
 neighborhood-0.003
Token their
Token ID511
Feature activation-3.22e-01

Pos logit contributions
 blowing+0.006
burn+0.006
 daddy+0.006
 waving+0.005
 shining+0.005
Neg logit contributions
 ounces-0.014
ets-0.014
hell-0.013
ocol-0.013
izards-0.013
Token snow
Token ID6729
Feature activation-6.27e+00

Pos logit contributions
burn+0.008
 blowing+0.008
 leaning+0.007
 waving+0.006
 neighborhood+0.006
Neg logit contributions
 ounces-0.010
 pounds-0.010
ets-0.009
 dollars-0.009
ocol-0.009
Tokenman
Token ID805
Feature activation-1.53e+00

Pos logit contributions
 blowing+0.105
burn+0.096
 neighborhood+0.086
 daddy+0.085
 waving+0.081
Neg logit contributions
 ounces-0.249
ets-0.243
hell-0.235
 pounds-0.233
izards-0.228
Token.
Token ID13
Feature activation-4.19e-01

Pos logit contributions
 blowing+0.038
burn+0.035
 daddy+0.033
 waving+0.032
 leaning+0.031
Neg logit contributions
 ounces-0.052
ets-0.049
ocol-0.049
izards-0.047
 pounds-0.046
Token
Token ID198
Feature activation-6.98e-01

Pos logit contributions
 blowing+0.007
burn+0.007
 daddy+0.006
 waving+0.005
 leaning+0.005
Neg logit contributions
 ounces-0.017
ets-0.017
izards-0.016
hell-0.016
 pounds-0.016
Token
Token ID198
Feature activation+4.91e-01

Pos logit contributions
burn+0.014
 blowing+0.013
 daddy+0.011
 leaning+0.010
 waving+0.010
Neg logit contributions
 ounces-0.026
ets-0.026
hell-0.025
izards-0.025
 pounds-0.024
Token"
Token ID1
Feature activation+2.38e+00

Pos logit contributions
 ounces+0.018
ets+0.017
ocol+0.017
izards+0.016
hell+0.016
Neg logit contributions
 blowing-0.011
burn-0.010
 daddy-0.009
 neighborhood-0.009
 waving-0.009
Token were
Token ID547
Feature activation-8.91e-01

Pos logit contributions
 ounces+0.039
ets+0.037
ocol+0.037
 pounds+0.036
izards+0.036
Neg logit contributions
 blowing-0.019
burn-0.018
 daddy-0.017
 waving-0.015
 blew-0.015
Token very
Token ID845
Feature activation+6.89e-01

Pos logit contributions
 blowing+0.017
burn+0.016
 daddy+0.014
 neighborhood+0.014
 waving+0.013
Neg logit contributions
 ounces-0.034
ets-0.033
 pounds-0.032
ocol-0.032
izards-0.031
Token happy
Token ID3772
Feature activation+1.75e-02

Pos logit contributions
 ounces+0.026
ets+0.025
 pounds+0.024
ocol+0.024
hell+0.024
Neg logit contributions
 blowing-0.014
burn-0.013
 daddy-0.011
 neighborhood-0.011
 waving-0.011
Token with
Token ID351
Feature activation-3.46e-01

Pos logit contributions
 ounces+0.001
ets+0.001
ocol+0.001
hell+0.001
 pounds+0.001
Neg logit contributions
 blowing-0.000
burn-0.000
 daddy-0.000
 waving-0.000
 neighborhood-0.000
Token their
Token ID511
Feature activation-2.84e-01

Pos logit contributions
 blowing+0.006
burn+0.005
 daddy+0.005
 waving+0.005
 shining+0.004
Neg logit contributions
 ounces-0.014
ets-0.014
hell-0.013
 pounds-0.013
izards-0.013
Token snow
Token ID6729
Feature activation-6.26e+00

Pos logit contributions
burn+0.007
 blowing+0.007
 leaning+0.006
 neighborhood+0.006
 waving+0.006
Neg logit contributions
 ounces-0.009
 pounds-0.008
ocol-0.008
ets-0.008
 dollars-0.008
Tokenman
Token ID805
Feature activation-1.50e+00

Pos logit contributions
 blowing+0.106
burn+0.096
 neighborhood+0.087
 daddy+0.086
 waving+0.082
Neg logit contributions
 ounces-0.247
ets-0.241
hell-0.234
 pounds-0.232
izards-0.226
Token.
Token ID13
Feature activation-3.74e-01

Pos logit contributions
 blowing+0.037
burn+0.035
 daddy+0.032
 waving+0.032
 leaning+0.030
Neg logit contributions
 ounces-0.052
ocol-0.048
ets-0.048
izards-0.046
 pounds-0.046
Token
Token ID198
Feature activation-6.59e-01

Pos logit contributions
 blowing+0.007
burn+0.007
 daddy+0.006
 waving+0.005
 shining+0.005
Neg logit contributions
 ounces-0.015
ets-0.014
 dollars-0.013
ocol-0.013
izards-0.013
Token
Token ID198
Feature activation+5.26e-01

Pos logit contributions
burn+0.013
 blowing+0.013
 daddy+0.011
 shining+0.010
 waving+0.010
Neg logit contributions
 ounces-0.024
hell-0.023
ets-0.023
izards-0.022
 pounds-0.022
TokenBut
Token ID1537
Feature activation+1.35e+00

Pos logit contributions
 ounces+0.018
ets+0.018
ocol+0.017
izards+0.017
 pounds+0.017
Neg logit contributions
 blowing-0.012
burn-0.012
 daddy-0.010
 neighborhood-0.010
 waving-0.010
Token new
Token ID649
Feature activation-2.30e+00

Pos logit contributions
 blowing+0.005
burn+0.005
 daddy+0.004
 neighborhood+0.004
 leaning+0.004
Neg logit contributions
 ounces-0.008
ets-0.007
 pounds-0.007
ocol-0.007
 dollars-0.007
Token friends
Token ID2460
Feature activation-3.89e-01

Pos logit contributions
 blowing+0.047
burn+0.045
 daddy+0.039
 neighborhood+0.037
 waving+0.037
Neg logit contributions
 ounces-0.087
ets-0.083
ocol-0.079
 pounds-0.079
hell-0.079
Token and
Token ID290
Feature activation+3.17e-02

Pos logit contributions
 blowing+0.007
burn+0.006
 daddy+0.006
 waving+0.005
 neighborhood+0.005
Neg logit contributions
 ounces-0.016
ets-0.015
ocol-0.015
 pounds-0.015
hell-0.015
Token had
Token ID550
Feature activation-4.58e-01

Pos logit contributions
 ounces+0.001
ets+0.001
izards+0.001
hell+0.001
 pounds+0.001
Neg logit contributions
burn-0.001
 blowing-0.001
 neighborhood-0.001
 daddy-0.001
 leaning-0.001
Token a
Token ID257
Feature activation+1.48e-01

Pos logit contributions
 blowing+0.007
 daddy+0.006
burn+0.006
 waving+0.006
 neighborhood+0.006
Neg logit contributions
ocol-0.020
 ounces-0.020
ets-0.018
 pounds-0.018
 dollars-0.018
Token lot
Token ID1256
Feature activation+5.29e+00

Pos logit contributions
 ounces+0.004
hell+0.004
ets+0.004
 dollars+0.004
 pounds+0.004
Neg logit contributions
 blowing-0.004
burn-0.004
 leaning-0.003
 waving-0.003
 daddy-0.003
Token of
Token ID286
Feature activation+2.27e-01

Pos logit contributions
 ounces+0.170
 pounds+0.159
ocol+0.156
 dollars+0.151
izards+0.146
Neg logit contributions
 blowing-0.132
 waving-0.116
burn-0.115
 neighborhood-0.114
 spinning-0.111
Token fun
Token ID1257
Feature activation-6.10e-01

Pos logit contributions
 ounces+0.009
 pounds+0.009
ets+0.009
ocol+0.008
 dollars+0.008
Neg logit contributions
 blowing-0.004
 neighborhood-0.003
 waving-0.003
 daddy-0.003
 spinning-0.003
Token.
Token ID13
Feature activation-3.56e-02

Pos logit contributions
 blowing+0.014
 waving+0.012
 spinning+0.012
burn+0.012
 shining+0.011
Neg logit contributions
 ounces-0.023
ets-0.021
 pounds-0.021
 dollars-0.021
hell-0.020
Token He
Token ID679
Feature activation+3.03e-01

Pos logit contributions
 blowing+0.001
burn+0.001
 daddy+0.001
 neighborhood+0.001
 waving+0.001
Neg logit contributions
 ounces-0.001
ets-0.001
ocol-0.001
 pounds-0.001
hell-0.001
Token pretended
Token ID36766
Feature activation-9.14e-01

Pos logit contributions
 ounces+0.010
ets+0.010
izards+0.010
hell+0.009
 pounds+0.009
Neg logit contributions
burn-0.007
 blowing-0.007
 daddy-0.006
 leaning-0.006
 shining-0.006
Token tricks
Token ID15910
Feature activation+2.64e-01

Pos logit contributions
 blowing+0.014
 daddy+0.012
burn+0.012
 waving+0.012
 spinning+0.011
Neg logit contributions
 ounces-0.022
ets-0.021
ocol-0.021
 pounds-0.020
 dollars-0.020
Token.
Token ID13
Feature activation-5.07e-01

Pos logit contributions
 ounces+0.010
ets+0.009
ocol+0.009
 pounds+0.009
 dollars+0.009
Neg logit contributions
 blowing-0.006
 daddy-0.005
 waving-0.005
burn-0.005
 shining-0.005
Token They
Token ID1119
Feature activation+1.07e+00

Pos logit contributions
 blowing+0.012
burn+0.011
 daddy+0.010
 neighborhood+0.010
 waving+0.010
Neg logit contributions
 ounces-0.018
ets-0.017
 pounds-0.016
ocol-0.016
hell-0.016
Token have
Token ID423
Feature activation-1.55e-01

Pos logit contributions
 ounces+0.038
ets+0.035
 pounds+0.034
ocol+0.034
hell+0.034
Neg logit contributions
 blowing-0.025
burn-0.024
 daddy-0.022
 waving-0.021
 neighborhood-0.021
Token a
Token ID257
Feature activation-3.90e-01

Pos logit contributions
 blowing+0.003
burn+0.003
 daddy+0.002
 neighborhood+0.002
 waving+0.002
Neg logit contributions
 ounces-0.006
ocol-0.006
 pounds-0.006
ets-0.006
 dollars-0.006
Token lot
Token ID1256
Feature activation+5.30e+00

Pos logit contributions
 blowing+0.011
burn+0.010
 leaning+0.010
flower+0.009
hat+0.009
Neg logit contributions
hell-0.010
ets-0.010
 ounces-0.010
 dollars-0.010
 risks-0.009
Token of
Token ID286
Feature activation+5.95e-01

Pos logit contributions
 ounces+0.153
 pounds+0.137
ocol+0.136
ets+0.132
 dollars+0.130
Neg logit contributions
 blowing-0.159
burn-0.147
 waving-0.137
 neighborhood-0.137
 daddy-0.137
Token fun
Token ID1257
Feature activation-6.65e-01

Pos logit contributions
 ounces+0.023
 pounds+0.022
ets+0.021
ocol+0.021
 dollars+0.021
Neg logit contributions
 blowing-0.012
burn-0.010
 daddy-0.010
 neighborhood-0.010
 waving-0.009
Token.
Token ID13
Feature activation-7.31e-01

Pos logit contributions
 blowing+0.015
burn+0.013
 daddy+0.013
 waving+0.013
 neighborhood+0.012
Neg logit contributions
 ounces-0.025
ets-0.023
 pounds-0.022
ocol-0.022
hell-0.022
Token They
Token ID1119
Feature activation+8.10e-01

Pos logit contributions
 blowing+0.015
burn+0.014
 daddy+0.012
 waving+0.012
 leaning+0.012
Neg logit contributions
 ounces-0.027
ets-0.026
ocol-0.025
izards-0.025
hell-0.025
Token laugh
Token ID6487
Feature activation-2.31e-01

Pos logit contributions
 ounces+0.025
ets+0.024
ocol+0.023
hell+0.023
 pounds+0.023
Neg logit contributions
 blowing-0.022
burn-0.021
 daddy-0.019
 neighborhood-0.018
 waving-0.018
Token,
Token ID11
Feature activation-1.05e+00

Pos logit contributions
 blowing+0.038
burn+0.034
 daddy+0.033
 waving+0.030
 leaning+0.029
Neg logit contributions
 ounces-0.095
ets-0.091
hell-0.088
 pounds-0.087
ocol-0.087
Token please
Token ID3387
Feature activation+6.83e-01

Pos logit contributions
 blowing+0.030
burn+0.029
 daddy+0.027
 waving+0.026
 neighborhood+0.026
Neg logit contributions
 ounces-0.031
ets-0.029
 pounds-0.027
hell-0.027
ocol-0.027
Token ask
Token ID1265
Feature activation+1.58e+00

Pos logit contributions
 ounces+0.023
ets+0.022
ocol+0.021
 pounds+0.021
hell+0.020
Neg logit contributions
 blowing-0.017
burn-0.016
 daddy-0.014
 neighborhood-0.014
 waving-0.014
Token me
Token ID502
Feature activation+2.02e+00

Pos logit contributions
 ounces+0.054
ets+0.052
hell+0.050
 pounds+0.049
izards+0.049
Neg logit contributions
 blowing-0.038
burn-0.036
 daddy-0.034
 waving-0.032
 neighborhood-0.031
Token before
Token ID878
Feature activation-3.41e-01

Pos logit contributions
 ounces+0.075
ets+0.072
hell+0.070
ocol+0.069
 pounds+0.068
Neg logit contributions
 blowing-0.043
burn-0.040
 daddy-0.039
 waving-0.035
 neighborhood-0.034
Token you
Token ID345
Feature activation+5.33e+00

Pos logit contributions
 blowing+0.011
burn+0.011
 daddy+0.010
 neighborhood+0.010
 waving+0.010
Neg logit contributions
 ounces-0.008
ets-0.007
ocol-0.007
 pounds-0.007
izards-0.007
Token add
Token ID751
Feature activation+1.45e+00

Pos logit contributions
 ounces+0.196
ets+0.181
 pounds+0.179
hell+0.178
ocol+0.177
Neg logit contributions
 blowing-0.116
burn-0.109
 daddy-0.100
 waving-0.093
 neighborhood-0.092
Token anything
Token ID1997
Feature activation+1.22e+00

Pos logit contributions
 ounces+0.052
ets+0.048
izards+0.048
hell+0.047
bridge+0.046
Neg logit contributions
 blowing-0.032
burn-0.029
 daddy-0.029
 shining-0.027
 mom-0.027
Token.
Token ID13
Feature activation-5.13e-01

Pos logit contributions
 ounces+0.039
ets+0.037
ocol+0.035
hell+0.035
izards+0.035
Neg logit contributions
 blowing-0.032
burn-0.029
 daddy-0.028
 waving-0.027
 leaning-0.026
Token And
Token ID843
Feature activation+1.92e+00

Pos logit contributions
 blowing+0.013
burn+0.013
 daddy+0.012
 neighborhood+0.011
 waving+0.011
Neg logit contributions
 ounces-0.016
ets-0.016
hell-0.015
 pounds-0.015
izards-0.015
Token be
Token ID307
Feature activation-3.68e-01

Pos logit contributions
 ounces+0.057
ets+0.054
hell+0.051
ocol+0.051
 pounds+0.051
Neg logit contributions
 blowing-0.055
burn-0.052
 daddy-0.049
 waving-0.047
 neighborhood-0.047
Token what
Token ID644
Feature activation-1.82e+00

Pos logit contributions
 ounces+0.003
ets+0.003
ocol+0.003
 pounds+0.003
hell+0.003
Neg logit contributions
 blowing-0.002
burn-0.001
 daddy-0.001
 waving-0.001
 neighborhood-0.001
Token was
Token ID373
Feature activation+9.24e-01

Pos logit contributions
 blowing+0.046
burn+0.045
 daddy+0.039
 waving+0.038
 neighborhood+0.037
Neg logit contributions
 ounces-0.060
ets-0.056
 pounds-0.054
hell-0.054
izards-0.053
Token around
Token ID1088
Feature activation-2.69e+00

Pos logit contributions
 ounces+0.038
ets+0.036
ocol+0.035
hell+0.035
 pounds+0.035
Neg logit contributions
 blowing-0.017
burn-0.015
 waving-0.013
 daddy-0.013
 shining-0.013
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
 blowing+0.075
burn+0.073
 daddy+0.066
 neighborhood+0.064
 waving+0.064
Neg logit contributions
 ounces-0.081
ets-0.077
 pounds-0.073
ocol-0.072
hell-0.072
Token river
Token ID7850
Feature activation-5.44e-01

Pos logit contributions
 ounces+0.046
ets+0.044
izards+0.043
ocol+0.043
hell+0.043
Neg logit contributions
 blowing-0.026
burn-0.024
 neighborhood-0.022
 daddy-0.022
 waving-0.021
Tokenâ
Token ID22940
Feature activation+5.38e+00

Pos logit contributions
 blowing+0.014
burn+0.012
 waving+0.012
 daddy+0.012
 neighborhood+0.012
Neg logit contributions
 ounces-0.018
ets-0.017
ocol-0.017
izards-0.016
 pounds-0.016
Token€
Token ID26391
Feature activation+2.32e+00

Pos logit contributions
 ounces+0.160
izards+0.149
 pounds+0.148
 dollars+0.145
ocol+0.144
Neg logit contributions
 blowing-0.154
burn-0.146
 neighborhood-0.136
 leaning-0.131
 waving-0.130
Tokenâ„¢
Token ID8151
Feature activation+3.68e-01

Pos logit contributions
 ounces+0.074
ocol+0.068
ets+0.068
 pounds+0.066
 dollars+0.066
Neg logit contributions
 blowing-0.061
burn-0.058
 neighborhood-0.054
 daddy-0.054
 waving-0.052
Tokens
Token ID82
Feature activation+4.43e-01

Pos logit contributions
 ounces+0.012
ets+0.011
ocol+0.011
 pounds+0.011
hell+0.011
Neg logit contributions
 blowing-0.010
burn-0.009
 daddy-0.008
 waving-0.008
 neighborhood-0.008
Token bend
Token ID19396
Feature activation-1.80e+00

Pos logit contributions
 ounces+0.013
ets+0.013
 pounds+0.012
hell+0.012
 dollars+0.012
Neg logit contributions
burn-0.012
 blowing-0.011
 daddy-0.011
 waving-0.010
 neighborhood-0.010
Token.
Token ID13
Feature activation-2.07e-02

Pos logit contributions
 blowing+0.037
burn+0.035
 daddy+0.031
 waving+0.029
 neighborhood+0.029
Neg logit contributions
 ounces-0.068
ets-0.065
ocol-0.063
 pounds-0.062
hell-0.062
Token the
Token ID262
Feature activation+4.31e-01

Pos logit contributions
 blowing+0.055
burn+0.052
 daddy+0.046
 neighborhood+0.044
 waving+0.044
Neg logit contributions
 ounces-0.101
ets-0.097
ocol-0.093
 pounds-0.092
hell-0.092
Token me
Token ID502
Feature activation+7.26e-01

Pos logit contributions
 ounces+0.014
ets+0.014
 risks+0.013
 dollars+0.013
ocol+0.013
Neg logit contributions
 blowing-0.010
burn-0.010
 daddy-0.008
 waving-0.008
 leaning-0.008
Tokenadow
Token ID4584
Feature activation+4.77e-01

Pos logit contributions
 ounces+0.021
ets+0.019
ocol+0.018
 pounds+0.018
hell+0.018
Neg logit contributions
 blowing-0.022
burn-0.021
 daddy-0.019
 waving-0.019
 neighborhood-0.019
Token as
Token ID355
Feature activation-2.72e-01

Pos logit contributions
 ounces+0.018
ets+0.017
ocol+0.017
 pounds+0.016
hell+0.016
Neg logit contributions
 blowing-0.010
burn-0.009
 daddy-0.008
 waving-0.008
 neighborhood-0.008
Token the
Token ID262
Feature activation-4.11e-01

Pos logit contributions
 blowing+0.006
burn+0.005
 daddy+0.005
 waving+0.004
 neighborhood+0.004
Neg logit contributions
 ounces-0.010
ets-0.010
ocol-0.009
 pounds-0.009
hell-0.009
Token Pers
Token ID9467
Feature activation+5.86e+00

Pos logit contributions
 blowing+0.010
burn+0.009
 daddy+0.008
 waving+0.008
 neighborhood+0.008
Neg logit contributions
 ounces-0.014
ets-0.013
ocol-0.012
 pounds-0.012
 dollars-0.012
Tokenistent
Token ID7609
Feature activation+4.88e-01

Pos logit contributions
 ounces+0.153
izards+0.139
 pounds+0.136
hell+0.135
 dollars+0.135
Neg logit contributions
 blowing-0.190
burn-0.182
 leaning-0.161
 neighborhood-0.159
 waving-0.159
Token Lamb
Token ID21114
Feature activation+7.48e-01

Pos logit contributions
 ounces+0.015
ets+0.014
ocol+0.014
izards+0.014
 pounds+0.014
Neg logit contributions
 blowing-0.013
burn-0.013
 daddy-0.011
 waving-0.011
 neighborhood-0.011
Token -
Token ID532
Feature activation-1.47e+00

Pos logit contributions
 ounces+0.027
ets+0.025
ocol+0.025
 pounds+0.024
hell+0.024
Neg logit contributions
 blowing-0.018
burn-0.016
 daddy-0.015
 waving-0.014
 leaning-0.014
Token the
Token ID262
Feature activation-1.02e+00

Pos logit contributions
 blowing+0.032
burn+0.032
 daddy+0.028
 neighborhood+0.028
 waving+0.026
Neg logit contributions
 ounces-0.051
ets-0.048
ocol-0.046
 pounds-0.046
 dollars-0.046
Token one
Token ID530
Feature activation-1.76e+00

Pos logit contributions
 blowing+0.026
burn+0.025
 daddy+0.022
 waving+0.022
 neighborhood+0.021
Neg logit contributions
 ounces-0.033
ets-0.031
 pounds-0.030
 dollars-0.030
ocol-0.029
Token looking
Token ID2045
Feature activation+4.26e-01

Pos logit contributions
 ounces+0.074
ets+0.070
izards+0.067
ocol+0.067
 pounds+0.067
Neg logit contributions
 blowing-0.045
 waving-0.040
 daddy-0.038
burn-0.037
 leaning-0.037
Token at
Token ID379
Feature activation-4.71e-01

Pos logit contributions
 ounces+0.016
ets+0.015
 pounds+0.014
ocol+0.014
hell+0.014
Neg logit contributions
 blowing-0.009
burn-0.009
 daddy-0.008
 waving-0.008
 neighborhood-0.008
Token him
Token ID683
Feature activation+8.68e-01

Pos logit contributions
 blowing+0.012
burn+0.011
 daddy+0.011
 waving+0.010
 shining+0.010
Neg logit contributions
 ounces-0.016
ets-0.015
 dollars-0.014
hell-0.014
 pounds-0.014
Token with
Token ID351
Feature activation+1.35e+00

Pos logit contributions
 ounces+0.030
ets+0.029
ocol+0.028
 pounds+0.027
izards+0.027
Neg logit contributions
 blowing-0.021
burn-0.019
 daddy-0.018
 waving-0.018
 shining-0.017
Token curious
Token ID11040
Feature activation+1.37e+00

Pos logit contributions
 ounces+0.051
ets+0.049
ocol+0.047
 pounds+0.047
hell+0.047
Neg logit contributions
 blowing-0.028
burn-0.026
 daddy-0.023
 neighborhood-0.022
 waving-0.022
Token eyes
Token ID2951
Feature activation+1.97e+00

Pos logit contributions
 ounces+0.049
ets+0.047
izards+0.046
hell+0.044
 pounds+0.044
Neg logit contributions
 blowing-0.029
 daddy-0.028
 waving-0.026
 crying-0.025
 neighborhood-0.025
Token.
Token ID13
Feature activation-7.56e-01

Pos logit contributions
 ounces+0.064
ets+0.061
ocol+0.058
izards+0.058
 pounds+0.057
Neg logit contributions
 blowing-0.052
burn-0.049
 daddy-0.045
 waving-0.044
 shining-0.043
Token
Token ID198
Feature activation-1.58e-01

Pos logit contributions
 blowing+0.012
burn+0.011
 daddy+0.010
 neighborhood+0.009
 waving+0.009
Neg logit contributions
 ounces-0.032
ets-0.031
ocol-0.030
 pounds-0.029
hell-0.029
Token
Token ID198
Feature activation+6.41e-01

Pos logit contributions
 blowing+0.002
burn+0.002
 daddy+0.001
 neighborhood+0.001
 waving+0.001
Neg logit contributions
 ounces-0.007
ets-0.007
ocol-0.007
 pounds-0.007
hell-0.007
TokenThe
Token ID464
Feature activation-1.98e+00

Pos logit contributions
ets+0.026
 ounces+0.026
ocol+0.025
izards+0.025
 pounds+0.024
Neg logit contributions
 blowing-0.011
burn-0.009
 neighborhood-0.009
 daddy-0.009
 waving-0.008
Token man
Token ID582
Feature activation-4.80e-01

Pos logit contributions
burn+0.050
 blowing+0.049
 daddy+0.038
 spinning+0.037
 neighborhood+0.037
Neg logit contributions
 ounces-0.067
 pounds-0.061
ly-0.061
 dollars-0.061
ets-0.060
Token with
Token ID351
Feature activation+2.07e+00

Pos logit contributions
 blowing+0.029
 spinning+0.023
 shining+0.021
 waving+0.021
 feeling+0.021
Neg logit contributions
 ounces-0.101
ocol-0.094
 dollars-0.093
 pounds-0.093
 cents-0.088
Token the
Token ID262
Feature activation-6.74e-01

Pos logit contributions
 ounces+0.086
ets+0.081
 dollars+0.080
ocol+0.080
 pounds+0.080
Neg logit contributions
 blowing-0.036
 daddy-0.033
burn-0.030
 mom-0.030
 waving-0.028
Token children
Token ID1751
Feature activation+3.36e-01

Pos logit contributions
 blowing+0.018
burn+0.018
 daddy+0.016
 waving+0.016
 neighborhood+0.016
Neg logit contributions
 ounces-0.021
ets-0.020
ocol-0.019
 pounds-0.019
hell-0.019
Token for
Token ID329
Feature activation+2.35e+00

Pos logit contributions
 ounces+0.013
ets+0.012
ocol+0.012
 pounds+0.012
hell+0.012
Neg logit contributions
 blowing-0.007
burn-0.006
 daddy-0.005
 waving-0.005
 neighborhood-0.005
Token a
Token ID257
Feature activation+3.60e-01

Pos logit contributions
 ounces+0.089
ets+0.087
ocol+0.085
 dollars+0.084
izards+0.083
Neg logit contributions
 blowing-0.050
 spinning-0.039
 waving-0.039
 daddy-0.037
 shining-0.037
Token while
Token ID981
Feature activation+3.26e+00

Pos logit contributions
 ounces+0.012
ets+0.012
ocol+0.011
 pounds+0.011
hell+0.011
Neg logit contributions
 blowing-0.009
burn-0.008
 daddy-0.008
 waving-0.007
 neighborhood-0.007
Token,
Token ID11
Feature activation+5.31e-01

Pos logit contributions
 ounces+0.126
ets+0.120
hell+0.117
ocol+0.115
izards+0.115
Neg logit contributions
 blowing-0.068
burn-0.058
 daddy-0.056
 waving-0.054
 spinning-0.052
Token but
Token ID475
Feature activation+1.09e+00

Pos logit contributions
 ounces+0.018
ets+0.017
 pounds+0.016
hell+0.016
izards+0.016
Neg logit contributions
 blowing-0.012
burn-0.012
 daddy-0.011
 neighborhood-0.010
 waving-0.010
Token then
Token ID788
Feature activation-7.48e-01

Pos logit contributions
 ounces+0.037
ets+0.035
ocol+0.033
 pounds+0.033
izards+0.033
Neg logit contributions
 blowing-0.026
burn-0.025
 daddy-0.022
 neighborhood-0.022
 waving-0.021
Token it
Token ID340
Feature activation+1.03e+00

Pos logit contributions
 blowing+0.014
 daddy+0.013
burn+0.013
 waving+0.012
 mom+0.011
Neg logit contributions
 ounces-0.030
ets-0.029
hell-0.028
ocol-0.028
 pounds-0.027
Token saw
Token ID2497
Feature activation+6.79e-01

Pos logit contributions
 ounces+0.036
ets+0.035
hell+0.033
izards+0.033
 pounds+0.033
Neg logit contributions
 blowing-0.022
burn-0.021
 daddy-0.019
 neighborhood-0.018
 waving-0.018
Token upon
Token ID2402
Feature activation+8.85e-01

Pos logit contributions
burn+0.026
 blowing+0.025
 waving+0.020
 neighborhood+0.020
 ticking+0.020
Neg logit contributions
hell-0.035
ets-0.034
izards-0.034
 ounces-0.033
ocol-0.033
Token a
Token ID257
Feature activation-4.98e-01

Pos logit contributions
 ounces+0.036
ets+0.034
ocol+0.033
 pounds+0.033
 dollars+0.033
Neg logit contributions
 blowing-0.016
burn-0.015
 daddy-0.013
 waving-0.012
 neighborhood-0.012
Token time
Token ID640
Feature activation-2.85e-01

Pos logit contributions
 blowing+0.014
burn+0.013
 daddy+0.012
 waving+0.012
 shining+0.012
Neg logit contributions
ets-0.015
hell-0.015
 ounces-0.014
 pounds-0.013
 dollars-0.013
Token,
Token ID11
Feature activation-3.10e-01

Pos logit contributions
burn+0.008
 blowing+0.008
 neighborhood+0.006
 daddy+0.006
 blew+0.006
Neg logit contributions
 ounces-0.008
hell-0.008
izards-0.008
ets-0.008
ocol-0.008
Token there
Token ID612
Feature activation-2.43e+00

Pos logit contributions
 blowing+0.009
burn+0.009
 neighborhood+0.008
 daddy+0.008
 waving+0.008
Neg logit contributions
 ounces-0.009
ets-0.008
hell-0.008
izards-0.008
 pounds-0.008
Token was
Token ID373
Feature activation+1.53e+00

Pos logit contributions
burn+0.066
 blowing+0.059
 ticking+0.049
 daddy+0.048
rolling+0.047
Neg logit contributions
hell-0.073
 ounces-0.072
izards-0.067
 pounds-0.067
ets-0.064
Token a
Token ID257
Feature activation-1.41e-01

Pos logit contributions
 ounces+0.054
ets+0.052
hell+0.050
izards+0.050
ocol+0.050
Neg logit contributions
 blowing-0.033
burn-0.032
 daddy-0.028
 waving-0.027
 neighborhood-0.027
Token big
Token ID1263
Feature activation+5.95e-02

Pos logit contributions
 blowing+0.004
burn+0.003
 waving+0.003
 leaning+0.003
zag+0.003
Neg logit contributions
 ounces-0.004
hell-0.004
 pounds-0.004
 dollars-0.004
ets-0.004
Token bear
Token ID6842
Feature activation+2.82e-01

Pos logit contributions
 ounces+0.002
ets+0.002
ocol+0.002
 dollars+0.002
 pounds+0.002
Neg logit contributions
 blowing-0.001
burn-0.001
 neighborhood-0.001
 waving-0.001
 daddy-0.001
Token.
Token ID13
Feature activation+3.01e-01

Pos logit contributions
 ounces+0.008
ets+0.008
hell+0.008
izards+0.008
 pounds+0.007
Neg logit contributions
 blowing-0.008
burn-0.007
 daddy-0.007
 neighborhood-0.007
 waving-0.007
Token The
Token ID383
Feature activation-1.86e+00

Pos logit contributions
 ounces+0.010
ets+0.010
 pounds+0.009
ocol+0.009
hell+0.009
Neg logit contributions
 blowing-0.007
burn-0.007
 daddy-0.006
 waving-0.006
 neighborhood-0.006
Token.
Token ID13
Feature activation+1.97e-01

Pos logit contributions
 ounces+0.045
ocol+0.042
ets+0.041
 pounds+0.041
izards+0.040
Neg logit contributions
 blowing-0.021
burn-0.019
 daddy-0.017
 waving-0.016
 shining-0.015
Token She
Token ID1375
Feature activation+8.25e-01

Pos logit contributions
 ounces+0.006
ets+0.006
ocol+0.005
hell+0.005
 pounds+0.005
Neg logit contributions
 blowing-0.005
burn-0.005
 daddy-0.005
 waving-0.005
 neighborhood-0.005
Token liked
Token ID8288
Feature activation-1.75e+00

Pos logit contributions
 ounces+0.028
ets+0.028
izards+0.026
hell+0.026
ils+0.026
Neg logit contributions
burn-0.018
 blowing-0.018
 waving-0.015
 shining-0.015
 leaning-0.015
Token to
Token ID284
Feature activation-1.68e+00

Pos logit contributions
burn+0.035
 blowing+0.034
 neighborhood+0.030
 daddy+0.029
 waving+0.027
Neg logit contributions
 ounces-0.064
ets-0.061
izards-0.059
ocol-0.059
 pounds-0.059
Token watch
Token ID2342
Feature activation+2.46e-01

Pos logit contributions
 blowing+0.035
burn+0.033
 daddy+0.030
 waving+0.029
 shining+0.027
Neg logit contributions
 ounces-0.064
ets-0.060
 pounds-0.060
izards-0.058
 dollars-0.058
Token them
Token ID606
Feature activation+1.53e+00

Pos logit contributions
 ounces+0.009
ets+0.009
 pounds+0.009
hell+0.009
ocol+0.009
Neg logit contributions
 blowing-0.005
burn-0.005
 daddy-0.004
 waving-0.004
 shining-0.004
Token swim
Token ID9422
Feature activation-3.64e-01

Pos logit contributions
 ounces+0.051
ets+0.050
hell+0.047
izards+0.047
ocol+0.047
Neg logit contributions
 blowing-0.035
burn-0.035
 daddy-0.032
 neighborhood-0.031
 waving-0.029
Token and
Token ID290
Feature activation+6.54e-02

Pos logit contributions
 blowing+0.006
burn+0.005
 daddy+0.005
 shining+0.005
 neighborhood+0.005
Neg logit contributions
 ounces-0.016
ocol-0.015
 pounds-0.014
ets-0.014
izards-0.014
Token qu
Token ID627
Feature activation+1.04e+00

Pos logit contributions
 ounces+0.002
ets+0.002
ocol+0.002
hell+0.002
izards+0.002
Neg logit contributions
 blowing-0.001
burn-0.001
 daddy-0.001
 neighborhood-0.001
 waving-0.001
Tokenack
Token ID441
Feature activation+9.49e-01

Pos logit contributions
 ounces+0.036
ets+0.033
 pounds+0.033
ocol+0.033
 dollars+0.032
Neg logit contributions
 blowing-0.025
burn-0.024
 neighborhood-0.021
 daddy-0.021
 waving-0.020
Token and
Token ID290
Feature activation-2.20e-01

Pos logit contributions
 ounces+0.037
ets+0.033
ocol+0.033
 pounds+0.033
 dollars+0.032
Neg logit contributions
 blowing-0.021
burn-0.019
 daddy-0.017
 singing-0.017
 waving-0.016
Token Gab
Token ID12300
Feature activation+3.00e+00

Pos logit contributions
 daddy+0.009
 blowing+0.009
 mom+0.009
 waving+0.008
burn+0.008
Neg logit contributions
 ounces-0.025
ets-0.025
ocol-0.023
hell-0.023
aces-0.023
Tokenri
Token ID380
Feature activation+2.09e+00

Pos logit contributions
 ounces+0.139
ets+0.133
izards+0.130
hell+0.128
 pounds+0.127
Neg logit contributions
burn-0.035
 blowing-0.035
 daddy-0.031
 neighborhood-0.025
 waving-0.024
Tokenella
Token ID12627
Feature activation+1.59e+00

Pos logit contributions
 ounces+0.059
ets+0.056
izards+0.055
ocol+0.054
 risks+0.054
Neg logit contributions
 blowing-0.062
burn-0.054
zag-0.053
 waving-0.053
 daddy-0.053
Token,
Token ID11
Feature activation-4.89e-01

Pos logit contributions
 ounces+0.057
ets+0.052
ocol+0.051
izards+0.051
hell+0.051
Neg logit contributions
 blowing-0.038
burn-0.036
 daddy-0.035
 waving-0.033
 spinning-0.031
Token would
Token ID561
Feature activation-8.59e-01

Pos logit contributions
 blowing+0.014
 daddy+0.012
burn+0.012
 waving+0.012
 spinning+0.011
Neg logit contributions
 ounces-0.015
ets-0.014
 pounds-0.014
ocol-0.014
hell-0.014
Token you
Token ID345
Feature activation+3.28e+00

Pos logit contributions
 blowing+0.021
 daddy+0.020
 waving+0.019
burn+0.018
 spinning+0.018
Neg logit contributions
 ounces-0.030
 pounds-0.029
ets-0.028
 dollars-0.028
izards-0.027
Token like
Token ID588
Feature activation-2.20e+00

Pos logit contributions
 ounces+0.125
 pounds+0.118
ocol+0.115
 dollars+0.112
hell+0.111
Neg logit contributions
 blowing-0.070
burn-0.065
 daddy-0.062
 waving-0.061
 spinning-0.059
Token to
Token ID284
Feature activation-1.69e+00

Pos logit contributions
 blowing+0.044
burn+0.039
 daddy+0.037
 waving+0.035
 spinning+0.033
Neg logit contributions
 ounces-0.086
ets-0.083
hell-0.079
ocol-0.079
 pounds-0.079
Token come
Token ID1282
Feature activation-4.24e-01

Pos logit contributions
 blowing+0.029
burn+0.026
 daddy+0.025
 waving+0.024
 spinning+0.022
Neg logit contributions
 ounces-0.071
 pounds-0.067
ets-0.067
 dollars-0.067
izards-0.065
Token visit
Token ID3187
Feature activation+2.08e-01

Pos logit contributions
 blowing+0.009
burn+0.008
 daddy+0.007
 neighborhood+0.007
 leaning+0.007
Neg logit contributions
 ounces-0.015
ets-0.015
izards-0.014
ocol-0.014
hell-0.014
Token me
Token ID502
Feature activation+1.26e+00

Pos logit contributions
 ounces+0.008
hell+0.007
ocol+0.007
ets+0.007
 pounds+0.007
Neg logit contributions
 daddy-0.004
 blowing-0.004
 grandma-0.004
 mom-0.004
 next-0.004
Token.
Token ID13
Feature activation-6.09e-01

Pos logit contributions
 ounces+0.100
ocol+0.092
ets+0.089
 pounds+0.087
bridge+0.086
Neg logit contributions
 blowing-0.035
 waving-0.028
 next-0.028
 leaning-0.028
 holding-0.027
Token They
Token ID1119
Feature activation+1.42e+00

Pos logit contributions
 blowing+0.013
burn+0.013
 daddy+0.011
 waving+0.011
 neighborhood+0.011
Neg logit contributions
 ounces-0.022
ets-0.021
 pounds-0.020
ocol-0.020
hell-0.020
Token take
Token ID1011
Feature activation+2.12e+00

Pos logit contributions
 ounces+0.055
 pounds+0.051
ocol+0.050
hell+0.049
ets+0.048
Neg logit contributions
 blowing-0.028
 daddy-0.026
burn-0.025
 also-0.024
 waving-0.024
Token the
Token ID262
Feature activation-7.91e-01

Pos logit contributions
 ounces+0.077
ets+0.073
ocol+0.070
 pounds+0.070
hell+0.070
Neg logit contributions
 blowing-0.047
burn-0.045
 daddy-0.040
 waving-0.038
 neighborhood-0.038
Token train
Token ID4512
Feature activation+8.45e-01

Pos logit contributions
 blowing+0.016
burn+0.015
 daddy+0.013
 waving+0.012
 neighborhood+0.012
Neg logit contributions
 ounces-0.030
ets-0.029
ocol-0.028
 pounds-0.028
hell-0.028
Token off
Token ID572
Feature activation+1.19e+00

Pos logit contributions
ets+0.030
 ounces+0.029
hell+0.027
izards+0.027
 dollars+0.027
Neg logit contributions
 blowing-0.018
burn-0.018
 daddy-0.016
 neighborhood-0.016
 waving-0.015
Token the
Token ID262
Feature activation+4.04e-01

Pos logit contributions
 ounces+0.046
ets+0.044
 pounds+0.043
ocol+0.043
hell+0.042
Neg logit contributions
 blowing-0.023
burn-0.021
 daddy-0.019
 neighborhood-0.018
 waving-0.018
Token track
Token ID2610
Feature activation+1.07e+00

Pos logit contributions
 ounces+0.016
ets+0.015
ocol+0.015
izards+0.015
 pounds+0.015
Neg logit contributions
 blowing-0.007
burn-0.007
 daddy-0.006
 waving-0.006
 neighborhood-0.006
Token.
Token ID13
Feature activation-6.21e-01

Pos logit contributions
 ounces+0.042
ets+0.040
ocol+0.039
 pounds+0.039
izards+0.038
Neg logit contributions
 blowing-0.021
burn-0.019
 daddy-0.017
 waving-0.017
 neighborhood-0.016
Token They
Token ID1119
Feature activation+1.30e+00

Pos logit contributions
 blowing+0.014
burn+0.014
 daddy+0.012
 neighborhood+0.012
 waving+0.012
Neg logit contributions
 ounces-0.022
ets-0.021
ocol-0.020
 pounds-0.020
hell-0.020
Token put
Token ID1234
Feature activation-1.23e+00

Pos logit contributions
 ounces+0.052
 pounds+0.048
ocol+0.048
hell+0.047
ets+0.047
Neg logit contributions
 blowing-0.024
burn-0.022
 daddy-0.022
 waving-0.020
 spinning-0.020
Token toy
Token ID13373
Feature activation+6.08e-02

Pos logit contributions
 blowing+0.032
burn+0.030
 leaning+0.026
rolling+0.025
 waving+0.024
Neg logit contributions
hell-0.038
 ounces-0.037
ets-0.036
 dollars-0.036
ly-0.036
Token.
Token ID13
Feature activation-1.92e-01

Pos logit contributions
 ounces+0.002
ets+0.002
ocol+0.002
 pounds+0.002
hell+0.002
Neg logit contributions
 blowing-0.001
burn-0.001
 daddy-0.001
 waving-0.001
 neighborhood-0.001
Token It
Token ID632
Feature activation-8.33e-01

Pos logit contributions
 blowing+0.006
burn+0.006
 daddy+0.005
 waving+0.005
 neighborhood+0.005
Neg logit contributions
 ounces-0.005
ets-0.005
hell-0.004
ocol-0.004
izards-0.004
Token is
Token ID318
Feature activation+2.04e-02

Pos logit contributions
 blowing+0.020
burn+0.020
 daddy+0.017
 neighborhood+0.017
 waving+0.016
Neg logit contributions
 ounces-0.028
ets-0.027
hell-0.026
izards-0.026
ocol-0.025
Token a
Token ID257
Feature activation-9.51e-01

Pos logit contributions
ets+0.001
 ounces+0.001
hell+0.001
izards+0.001
 dollars+0.001
Neg logit contributions
burn-0.000
 blowing-0.000
 neighborhood-0.000
 daddy-0.000
rolling-0.000
Token yellow
Token ID7872
Feature activation-1.49e+00

Pos logit contributions
burn+0.022
 blowing+0.021
 neighborhood+0.017
rolling+0.017
hat+0.017
Neg logit contributions
 ounces-0.030
hell-0.030
 dollars-0.027
 pounds-0.027
ets-0.027
Token brain
Token ID3632
Feature activation+8.38e-01

Pos logit contributions
 blowing+0.030
burn+0.028
 daddy+0.025
 neighborhood+0.025
 waving+0.024
Neg logit contributions
 ounces-0.055
ets-0.053
hell-0.051
ocol-0.051
 pounds-0.051
Token.
Token ID13
Feature activation-7.57e-01

Pos logit contributions
 ounces+0.028
ets+0.026
ocol+0.025
 pounds+0.025
izards+0.025
Neg logit contributions
 blowing-0.021
burn-0.020
 daddy-0.018
 waving-0.018
 neighborhood-0.017
Token It
Token ID632
Feature activation-1.11e+00

Pos logit contributions
 blowing+0.020
burn+0.019
 daddy+0.017
 waving+0.017
 neighborhood+0.017
Neg logit contributions
 ounces-0.024
ets-0.023
hell-0.022
ocol-0.022
izards-0.022
Token can
Token ID460
Feature activation-1.43e+00

Pos logit contributions
 blowing+0.025
burn+0.025
 daddy+0.021
 neighborhood+0.021
 waving+0.020
Neg logit contributions
 ounces-0.039
ets-0.038
izards-0.036
hell-0.036
ocol-0.035
Token make
Token ID787
Feature activation+3.34e-01

Pos logit contributions
burn+0.033
 blowing+0.032
 neighborhood+0.028
 daddy+0.027
 waving+0.026
Neg logit contributions
 ounces-0.049
ets-0.047
izards-0.045
hell-0.045
ocol-0.045
Token pretty
Token ID2495
Feature activation-2.89e+00

Pos logit contributions
 blowing+0.041
burn+0.039
 daddy+0.034
 neighborhood+0.033
 waving+0.033
Neg logit contributions
 ounces-0.058
ets-0.056
hell-0.054
 pounds-0.053
izards-0.053
Token necklace
Token ID38987
Feature activation-1.74e+00

Pos logit contributions
 blowing+0.079
burn+0.076
 daddy+0.070
 waving+0.068
 neighborhood+0.067
Neg logit contributions
 ounces-0.090
ets-0.084
 pounds-0.081
izards-0.081
ocol-0.080
Token was
Token ID373
Feature activation-8.14e-01

Pos logit contributions
 blowing+0.028
burn+0.026
 daddy+0.022
 neighborhood+0.021
 waving+0.021
Neg logit contributions
 ounces-0.073
ets-0.070
hell-0.068
 pounds-0.067
izards-0.067
Token ruined
Token ID20484
Feature activation-4.66e-01

Pos logit contributions
 blowing+0.015
burn+0.015
 neighborhood+0.013
 daddy+0.013
 waving+0.012
Neg logit contributions
 ounces-0.031
ets-0.030
hell-0.029
ocol-0.028
 pounds-0.028
Token,
Token ID11
Feature activation-5.52e-01

Pos logit contributions
 blowing+0.011
burn+0.011
 daddy+0.010
 waving+0.009
 shining+0.009
Neg logit contributions
 ounces-0.016
ets-0.015
ocol-0.015
izards-0.014
 pounds-0.014
Token but
Token ID475
Feature activation+5.00e-01

Pos logit contributions
 blowing+0.015
burn+0.015
 daddy+0.013
 neighborhood+0.013
 waving+0.013
Neg logit contributions
 ounces-0.017
ets-0.016
hell-0.015
 pounds-0.015
ocol-0.015
Token her
Token ID607
Feature activation-1.35e+00

Pos logit contributions
 ounces+0.018
ets+0.017
ocol+0.016
 pounds+0.016
hell+0.016
Neg logit contributions
 blowing-0.012
burn-0.011
 daddy-0.010
 neighborhood-0.010
 waving-0.010
Token friends
Token ID2460
Feature activation-7.42e-01

Pos logit contributions
 blowing+0.033
burn+0.032
 daddy+0.026
 waving+0.025
 leaning+0.025
Neg logit contributions
 ounces-0.046
ets-0.043
hell-0.042
 dollars-0.042
 pounds-0.041
Token told
Token ID1297
Feature activation+3.14e+00

Pos logit contributions
 blowing+0.016
burn+0.014
 daddy+0.013
 waving+0.013
 neighborhood+0.013
Neg logit contributions
 ounces-0.028
ets-0.026
ocol-0.026
 pounds-0.026
izards-0.025
Token her
Token ID607
Feature activation+4.99e-01

Pos logit contributions
 ounces+0.136
ets+0.129
 pounds+0.127
 dollars+0.127
ocol+0.124
Neg logit contributions
 blowing-0.050
 daddy-0.045
burn-0.043
 mom-0.039
 waving-0.038
Token it
Token ID340
Feature activation-1.50e-01

Pos logit contributions
 ounces+0.019
ocol+0.018
ets+0.018
 pounds+0.017
izards+0.016
Neg logit contributions
 blowing-0.010
 daddy-0.010
burn-0.009
 mom-0.009
 crying-0.009
Token at
Token ID379
Feature activation-1.15e+00

Pos logit contributions
 blowing+0.014
 daddy+0.013
burn+0.013
 shining+0.012
 waving+0.012
Neg logit contributions
 ounces-0.028
ets-0.025
 pounds-0.025
hell-0.025
izards-0.025
Token all
Token ID477
Feature activation-1.99e+00

Pos logit contributions
 blowing+0.026
burn+0.025
 daddy+0.021
 neighborhood+0.021
 waving+0.021
Neg logit contributions
 ounces-0.039
ets-0.038
izards-0.036
ocol-0.036
hell-0.036
Token the
Token ID262
Feature activation-6.82e-01

Pos logit contributions
 blowing+0.042
burn+0.041
 daddy+0.036
 neighborhood+0.034
 waving+0.034
Neg logit contributions
 ounces-0.072
ets-0.070
ocol-0.067
hell-0.067
izards-0.066
Token pretty
Token ID2495
Feature activation-8.34e-01

Pos logit contributions
 blowing+0.016
burn+0.016
 daddy+0.014
 waving+0.013
 neighborhood+0.013
Neg logit contributions
 ounces-0.023
ets-0.023
hell-0.022
 pounds-0.021
izards-0.021
Token flowers
Token ID12734
Feature activation-1.69e+00

Pos logit contributions
 blowing+0.018
burn+0.016
 neighborhood+0.016
 shining+0.015
 daddy+0.015
Neg logit contributions
 ounces-0.031
ets-0.028
 dollars-0.028
 pounds-0.028
ocol-0.027
Token.
Token ID13
Feature activation-4.68e-02

Pos logit contributions
 blowing+0.042
burn+0.040
 daddy+0.037
 waving+0.036
 neighborhood+0.035
Neg logit contributions
 ounces-0.057
ets-0.053
ocol-0.051
 pounds-0.051
hell-0.051
Token One
Token ID1881
Feature activation-1.17e+00

Pos logit contributions
 blowing+0.001
burn+0.001
 waving+0.001
 daddy+0.001
 leaning+0.001
Neg logit contributions
ets-0.001
 ounces-0.001
hell-0.001
ocol-0.001
izards-0.001
Token day
Token ID1110
Feature activation+3.00e-01

Pos logit contributions
burn+0.024
 blowing+0.024
rolling+0.023
 waving+0.022
 neighborhood+0.022
Neg logit contributions
ly-0.036
hell-0.036
ets-0.036
le-0.033
 ounces-0.033
Token,
Token ID11
Feature activation-7.14e-01

Pos logit contributions
 ounces+0.009
ets+0.009
hell+0.008
ocol+0.008
ly+0.008
Neg logit contributions
 blowing-0.008
burn-0.008
 neighborhood-0.007
 waving-0.007
 daddy-0.007
Token she
Token ID673
Feature activation+1.88e+00

Pos logit contributions
 blowing+0.019
burn+0.018
 neighborhood+0.017
 waving+0.016
 leaning+0.016
Neg logit contributions
 ounces-0.020
ets-0.020
ly-0.020
hell-0.019
ocol-0.019
Token saw
Token ID2497
Feature activation-2.48e-02

Pos logit contributions
ets+0.048
ly+0.043
 ounces+0.042
ils+0.042
izards+0.042
Neg logit contributions
 blowing-0.058
burn-0.055
 waving-0.049
 leaning-0.048
 ticking-0.048
TokenCan
Token ID6090
Feature activation+5.51e-01

Pos logit contributions
 ounces+0.034
ets+0.033
 pounds+0.031
hell+0.031
ocol+0.031
Neg logit contributions
 blowing-0.018
burn-0.017
 daddy-0.016
 waving-0.015
 neighborhood-0.015
Token I
Token ID314
Feature activation+7.85e-01

Pos logit contributions
 ounces+0.013
ets+0.012
ocol+0.011
 pounds+0.011
hell+0.011
Neg logit contributions
 blowing-0.019
burn-0.018
 daddy-0.017
 neighborhood-0.017
 waving-0.017
Token grab
Token ID5552
Feature activation+7.03e-01

Pos logit contributions
 ounces+0.030
ets+0.028
 pounds+0.028
ocol+0.028
hell+0.027
Neg logit contributions
 blowing-0.016
burn-0.015
 daddy-0.014
 waving-0.013
 neighborhood-0.013
Token it
Token ID340
Feature activation+1.58e+00

Pos logit contributions
 ounces+0.028
ets+0.027
bridge+0.026
hell+0.026
izards+0.025
Neg logit contributions
 blowing-0.012
 daddy-0.012
 mom-0.011
 spinning-0.011
 grandma-0.010
Token too
Token ID1165
Feature activation+1.91e+00

Pos logit contributions
 ounces+0.054
ets+0.052
 pounds+0.049
ocol+0.049
hell+0.049
Neg logit contributions
 blowing-0.037
burn-0.036
 daddy-0.032
 neighborhood-0.031
 waving-0.031
Token?"
Token ID1701
Feature activation+7.11e-01

Pos logit contributions
 ounces+0.050
ets+0.048
 pounds+0.046
hell+0.045
 dollars+0.045
Neg logit contributions
 blowing-0.057
burn-0.056
 daddy-0.051
 waving-0.050
 neighborhood-0.050
Token
Token ID198
Feature activation+7.42e-01

Pos logit contributions
 ounces+0.026
ets+0.025
 pounds+0.024
ocol+0.024
 dollars+0.024
Neg logit contributions
 blowing-0.015
burn-0.014
 daddy-0.014
 neighborhood-0.013
 waving-0.013
Token
Token ID198
Feature activation+1.18e+00

Pos logit contributions
 ounces+0.032
ets+0.031
hell+0.030
izards+0.029
ocol+0.029
Neg logit contributions
 blowing-0.011
burn-0.011
 daddy-0.009
 waving-0.008
 neighborhood-0.008
TokenJ
Token ID41
Feature activation+2.23e+00

Pos logit contributions
 ounces+0.040
ets+0.038
ocol+0.037
 pounds+0.036
izards+0.036
Neg logit contributions
 blowing-0.029
burn-0.027
 daddy-0.025
 neighborhood-0.024
 waving-0.024
Tokenill
Token ID359
Feature activation-6.77e-01

Pos logit contributions
 ounces+0.073
 dollars+0.066
 pounds+0.066
ocol+0.066
 risks+0.064
Neg logit contributions
 blowing-0.055
burn-0.051
 daddy-0.050
 neighborhood-0.048
my-0.046
Token said
Token ID531
Feature activation+1.52e+00

Pos logit contributions
 blowing+0.015
burn+0.015
 daddy+0.013
 neighborhood+0.012
 waving+0.012
Neg logit contributions
 ounces-0.024
ets-0.023
hell-0.022
 pounds-0.022
izards-0.022
Token home
Token ID1363
Feature activation-2.27e-01

Pos logit contributions
 ounces+0.084
ets+0.080
 dollars+0.077
ocol+0.077
 pounds+0.076
Neg logit contributions
 blowing-0.050
burn-0.050
 blew-0.038
 leaning-0.037
 waving-0.037
Token,
Token ID11
Feature activation-1.89e-01

Pos logit contributions
 blowing+0.005
burn+0.005
 daddy+0.005
 waving+0.004
 neighborhood+0.004
Neg logit contributions
 ounces-0.008
ets-0.007
ocol-0.007
 pounds-0.007
hell-0.007
Token and
Token ID290
Feature activation-9.04e-01

Pos logit contributions
burn+0.004
 blowing+0.004
 daddy+0.003
 neighborhood+0.003
 leaning+0.003
Neg logit contributions
 ounces-0.007
ets-0.007
 dollars-0.006
hell-0.006
 pounds-0.006
Token Emma
Token ID18966
Feature activation-8.63e-01

Pos logit contributions
 blowing+0.020
burn+0.019
 daddy+0.017
 waving+0.016
 neighborhood+0.016
Neg logit contributions
 ounces-0.033
ets-0.031
ocol-0.030
 pounds-0.030
hell-0.030
Token knew
Token ID2993
Feature activation+2.05e+00

Pos logit contributions
 blowing+0.016
burn+0.016
 daddy+0.013
 neighborhood+0.013
 waving+0.013
Neg logit contributions
 ounces-0.033
ets-0.032
hell-0.031
 pounds-0.031
izards-0.030
Token that
Token ID326
Feature activation-3.60e+00

Pos logit contributions
 ounces+0.071
ets+0.068
ocol+0.065
hell+0.064
 pounds+0.064
Neg logit contributions
 blowing-0.050
burn-0.046
 daddy-0.044
 waving-0.041
 neighborhood-0.040
Token it
Token ID340
Feature activation-4.83e-01

Pos logit contributions
burn+0.090
 blowing+0.089
 neighborhood+0.077
 daddy+0.075
 waving+0.075
Neg logit contributions
 ounces-0.115
ets-0.106
 pounds-0.104
izards-0.102
 dollars-0.102
Token would
Token ID561
Feature activation-4.43e-01

Pos logit contributions
burn+0.008
 blowing+0.008
 daddy+0.007
 waving+0.007
 neighborhood+0.007
Neg logit contributions
 ounces-0.019
ets-0.019
hell-0.018
 pounds-0.018
izards-0.018
Token bring
Token ID2222
Feature activation+9.10e-01

Pos logit contributions
 blowing+0.008
burn+0.008
 daddy+0.007
 neighborhood+0.007
 waving+0.007
Neg logit contributions
 ounces-0.017
ets-0.016
hell-0.016
ocol-0.016
 pounds-0.016
Token them
Token ID606
Feature activation+1.00e+00

Pos logit contributions
 ounces+0.033
ets+0.031
 pounds+0.031
ocol+0.031
izards+0.030
Neg logit contributions
 blowing-0.019
burn-0.018
 daddy-0.018
 neighborhood-0.016
 shining-0.016
Token a
Token ID257
Feature activation-2.28e-01

Pos logit contributions
 ounces+0.040
ocol+0.037
ets+0.037
 pounds+0.036
izards+0.036
Neg logit contributions
 blowing-0.019
burn-0.018
 daddy-0.017
 waving-0.016
 shining-0.016
Token.
Token ID13
Feature activation+1.04e-02

Pos logit contributions
 ounces+0.000
ocol+0.000
ets+0.000
 pounds+0.000
 dollars+0.000
Neg logit contributions
 blowing-0.000
burn-0.000
 daddy-0.000
 waving-0.000
 neighborhood-0.000
Token Max
Token ID5436
Feature activation-1.51e+00

Pos logit contributions
 ounces+0.000
ets+0.000
izards+0.000
ocol+0.000
hell+0.000
Neg logit contributions
 blowing-0.000
burn-0.000
 daddy-0.000
 neighborhood-0.000
 shining-0.000
Token loved
Token ID6151
Feature activation-3.04e+00

Pos logit contributions
burn+0.030
 blowing+0.028
 daddy+0.024
 shining+0.022
 leaning+0.022
Neg logit contributions
ets-0.056
 ounces-0.055
hell-0.053
izards-0.052
ly-0.051
Token to
Token ID284
Feature activation-2.67e+00

Pos logit contributions
burn+0.062
 blowing+0.060
 neighborhood+0.053
 daddy+0.051
flower+0.051
Neg logit contributions
 ounces-0.103
ets-0.100
izards-0.096
 pounds-0.094
ocol-0.093
Token play
Token ID711
Feature activation-2.68e+00

Pos logit contributions
 blowing+0.048
burn+0.045
 daddy+0.039
 neighborhood+0.038
 waving+0.037
Neg logit contributions
 ounces-0.104
ets-0.102
hell-0.098
ocol-0.097
izards-0.097
Token outside
Token ID2354
Feature activation-3.29e+00

Pos logit contributions
 blowing+0.041
burn+0.033
 spinning+0.031
 neighborhood+0.030
 shining+0.030
Neg logit contributions
 ounces-0.122
 pounds-0.112
 dollars-0.112
ocol-0.111
ets-0.111
Token in
Token ID287
Feature activation-3.38e-01

Pos logit contributions
 blowing+0.063
burn+0.059
 daddy+0.052
 waving+0.050
 neighborhood+0.049
Neg logit contributions
 ounces-0.129
ets-0.123
ocol-0.119
 pounds-0.118
hell-0.118
Token the
Token ID262
Feature activation+1.50e+00

Pos logit contributions
 blowing+0.008
burn+0.007
 daddy+0.006
 neighborhood+0.006
 waving+0.006
Neg logit contributions
 ounces-0.012
ets-0.011
ocol-0.011
izards-0.011
hell-0.011
Token sunshine
Token ID34488
Feature activation-1.79e+00

Pos logit contributions
ets+0.053
 ounces+0.052
hell+0.050
ocol+0.048
izards+0.048
Neg logit contributions
 blowing-0.034
burn-0.031
 daddy-0.028
 waving-0.026
 leaning-0.025
Token.
Token ID13
Feature activation-3.46e-01

Pos logit contributions
 blowing+0.048
burn+0.046
 daddy+0.042
 waving+0.041
 neighborhood+0.041
Neg logit contributions
 ounces-0.056
ets-0.053
 pounds-0.050
hell-0.050
ocol-0.050
Token One
Token ID1881
Feature activation-8.29e-01

Pos logit contributions
 blowing+0.010
burn+0.010
 daddy+0.009
 waving+0.009
 shining+0.009
Neg logit contributions
 ounces-0.010
ets-0.009
hell-0.009
izards-0.009
 pounds-0.009
Token at
Token ID379
Feature activation+1.05e-01

Pos logit contributions
burn+0.069
 blowing+0.066
 daddy+0.058
 neighborhood+0.057
 waving+0.054
Neg logit contributions
 ounces-0.089
ets-0.087
ly-0.084
 dollars-0.083
 pounds-0.082
Token small
Token ID1402
Feature activation-3.69e-01

Pos logit contributions
 ounces+0.004
ets+0.003
ocol+0.003
 pounds+0.003
izards+0.003
Neg logit contributions
 blowing-0.002
burn-0.002
 neighborhood-0.002
 daddy-0.002
 waving-0.002
Token bear
Token ID6842
Feature activation-5.78e-02

Pos logit contributions
 blowing+0.008
burn+0.007
 daddy+0.006
 waving+0.006
 neighborhood+0.006
Neg logit contributions
 ounces-0.014
ets-0.013
hell-0.013
ocol-0.013
izards-0.013
Token and
Token ID290
Feature activation-1.06e-02

Pos logit contributions
 blowing+0.001
burn+0.001
 daddy+0.001
 waving+0.001
 neighborhood+0.001
Neg logit contributions
 ounces-0.002
ets-0.002
ocol-0.002
 pounds-0.002
izards-0.002
Token said
Token ID531
Feature activation+1.97e+00

Pos logit contributions
 blowing+0.000
burn+0.000
 daddy+0.000
 neighborhood+0.000
 waving+0.000
Neg logit contributions
 ounces-0.000
ets-0.000
 pounds-0.000
ocol-0.000
hell-0.000
Token:
Token ID25
Feature activation-3.75e+00

Pos logit contributions
 ounces+0.080
ets+0.078
 pounds+0.074
ocol+0.074
izards+0.073
Neg logit contributions
 blowing-0.034
 daddy-0.029
burn-0.029
 waving-0.028
 leaning-0.026
Token "
Token ID366
Feature activation+6.84e-01

Pos logit contributions
burn+0.104
 blowing+0.095
 neighborhood+0.089
 daddy+0.083
flower+0.077
Neg logit contributions
 ounces-0.106
hell-0.096
 pounds-0.096
ocol-0.094
ets-0.092
TokenWe
Token ID1135
Feature activation+6.62e-01

Pos logit contributions
 ounces+0.025
ets+0.024
 pounds+0.022
ocol+0.022
hell+0.022
Neg logit contributions
 blowing-0.015
burn-0.014
 daddy-0.013
 neighborhood-0.012
 waving-0.012
Token can
Token ID460
Feature activation-1.99e+00

Pos logit contributions
 ounces+0.024
 pounds+0.023
ly+0.022
ocol+0.022
ets+0.021
Neg logit contributions
 also-0.013
 only-0.013
 blowing-0.013
 still-0.012
 daddy-0.012
Token share
Token ID2648
Feature activation-1.19e+00

Pos logit contributions
 blowing+0.045
burn+0.043
 daddy+0.039
 neighborhood+0.037
 waving+0.037
Neg logit contributions
 ounces-0.070
ets-0.067
ocol-0.064
hell-0.064
 pounds-0.064
Token the
Token ID262
Feature activation-6.75e-01

Pos logit contributions
 blowing+0.024
 daddy+0.021
burn+0.021
 waving+0.021
 mom+0.020
Neg logit contributions
 ounces-0.044
ets-0.044
bridge-0.041
ocol-0.040
izards-0.040
Token.
Token ID13
Feature activation+3.42e-01

Pos logit contributions
 ounces+0.050
ets+0.046
 pounds+0.045
ocol+0.045
izards+0.043
Neg logit contributions
 blowing-0.035
burn-0.033
 daddy-0.030
 waving-0.030
 neighborhood-0.029
Token The
Token ID383
Feature activation-2.07e+00

Pos logit contributions
 ounces+0.010
ets+0.010
izards+0.009
ocol+0.009
hell+0.009
Neg logit contributions
 blowing-0.009
burn-0.009
 daddy-0.008
 waving-0.008
 shining-0.008
Token bear
Token ID6842
Feature activation-2.08e+00

Pos logit contributions
 blowing+0.064
burn+0.060
 leaning+0.057
 waving+0.053
 ticking+0.053
Neg logit contributions
 ounces-0.050
hell-0.048
ets-0.047
izards-0.046
ly-0.046
Token and
Token ID290
Feature activation-1.38e+00

Pos logit contributions
burn+0.041
 blowing+0.040
 daddy+0.033
 waving+0.031
 leaning+0.030
Neg logit contributions
 ounces-0.079
ets-0.078
hell-0.074
izards-0.074
 dollars-0.072
Token rabbit
Token ID22746
Feature activation+2.19e-01

Pos logit contributions
 blowing+0.032
burn+0.031
 neighborhood+0.027
 daddy+0.027
 waving+0.026
Neg logit contributions
 ounces-0.047
ets-0.045
izards-0.043
ocol-0.043
hell-0.043
Token loved
Token ID6151
Feature activation-2.98e+00

Pos logit contributions
 ounces+0.009
ocol+0.008
ets+0.008
 pounds+0.008
hell+0.008
Neg logit contributions
 blowing-0.004
burn-0.004
 daddy-0.003
 neighborhood-0.003
 waving-0.003
Token each
Token ID1123
Feature activation-2.32e+00

Pos logit contributions
 blowing+0.051
burn+0.050
 daddy+0.042
 neighborhood+0.040
 waving+0.039
Neg logit contributions
 ounces-0.119
ets-0.115
izards-0.111
 pounds-0.110
ocol-0.110
Token other
Token ID584
Feature activation-2.02e+00

Pos logit contributions
 blowing+0.052
burn+0.048
 daddy+0.043
 neighborhood+0.042
 waving+0.042
Neg logit contributions
 ounces-0.084
ets-0.079
ocol-0.078
 pounds-0.077
izards-0.076
Token very
Token ID845
Feature activation+4.06e-01

Pos logit contributions
 blowing+0.027
burn+0.021
 neighborhood+0.019
 waving+0.019
 daddy+0.018
Neg logit contributions
ocol-0.094
 ounces-0.092
izards-0.085
ets-0.084
 pounds-0.084
Token much
Token ID881
Feature activation-1.49e+00

Pos logit contributions
 ounces+0.014
ocol+0.013
ets+0.013
 pounds+0.013
 dollars+0.012
Neg logit contributions
 blowing-0.010
burn-0.009
 daddy-0.009
 waving-0.008
 neighborhood-0.008
Token,
Token ID11
Feature activation-1.34e+00

Pos logit contributions
 blowing+0.019
 mom+0.017
 next+0.017
 still+0.017
 daddy+0.016
Neg logit contributions
ocol-0.068
 ounces-0.065
bridge-0.062
pieces-0.060
bors-0.059
Token back
Token ID736
Feature activation-2.42e+00

Pos logit contributions
 blowing+0.011
burn+0.011
 daddy+0.010
 neighborhood+0.009
 leaning+0.009
Neg logit contributions
 ounces-0.017
ets-0.017
izards-0.016
hell-0.016
 dollars-0.016
Token to
Token ID284
Feature activation+9.09e-01

Pos logit contributions
burn+0.063
 blowing+0.062
 daddy+0.053
 blew+0.052
omo+0.052
Neg logit contributions
ets-0.067
izards-0.062
ly-0.061
 risks-0.061
 ounces-0.059
Token her
Token ID607
Feature activation+1.19e+00

Pos logit contributions
 ounces+0.026
ocol+0.025
izards+0.025
ets+0.025
 risks+0.024
Neg logit contributions
burn-0.022
 blowing-0.020
flower-0.018
tr-0.018
icycle-0.018
Token shadow
Token ID9082
Feature activation-3.38e-01

Pos logit contributions
 ounces+0.041
ets+0.039
 dollars+0.039
ly+0.038
 pounds+0.038
Neg logit contributions
burn-0.024
 blowing-0.022
 blew-0.018
 shining-0.016
 leaning-0.016
Token and
Token ID290
Feature activation-8.68e-03

Pos logit contributions
 blowing+0.007
burn+0.007
 daddy+0.006
 neighborhood+0.006
 waving+0.006
Neg logit contributions
 ounces-0.012
ets-0.012
hell-0.011
 pounds-0.011
izards-0.011
Token started
Token ID2067
Feature activation-3.50e+00

Pos logit contributions
 blowing+0.000
burn+0.000
 neighborhood+0.000
 daddy+0.000
 leaning+0.000
Neg logit contributions
 ounces-0.000
ets-0.000
izards-0.000
hell-0.000
ly-0.000
Token to
Token ID284
Feature activation-9.66e-02

Pos logit contributions
burn+0.072
ama+0.065
 neighborhood+0.064
 daddy+0.064
 blowing+0.062
Neg logit contributions
 ounces-0.104
 risks-0.101
ets-0.100
izards-0.098
ocol-0.095
Token play
Token ID711
Feature activation-1.93e+00

Pos logit contributions
burn+0.002
 blowing+0.002
 daddy+0.002
 neighborhood+0.002
ama+0.002
Neg logit contributions
 ounces-0.003
ets-0.003
 risks-0.003
hell-0.003
izards-0.003
Token with
Token ID351
Feature activation+1.99e+00

Pos logit contributions
 spinning+0.025
 blowing+0.025
 crying+0.022
 feeling+0.022
 next+0.021
Neg logit contributions
 ounces-0.093
 pounds-0.088
 dollars-0.087
ocol-0.086
 cents-0.085
Token it
Token ID340
Feature activation+3.87e-01

Pos logit contributions
 ounces+0.076
ets+0.073
 dollars+0.071
 pounds+0.070
ocol+0.069
Neg logit contributions
 blowing-0.040
burn-0.037
 daddy-0.036
 waving-0.033
 spinning-0.033
Token.
Token ID13
Feature activation+3.07e-01

Pos logit contributions
 ounces+0.012
ets+0.012
ocol+0.011
 pounds+0.011
hell+0.011
Neg logit contributions
 blowing-0.010
burn-0.010
 daddy-0.009
 waving-0.009
 neighborhood-0.009