TOP ACTIVATIONS
MAX = 7.217

sand , and deep blue seas . One
cakes and cookies and ch ocol ates and ice cream .
colorful cand ies and ch ocol ates . She said to
and her favourite , ch ocol ates ! She asked mummy
like fish and shells and seaw eed . But they did
them tw irl around each other . Annie 's mother called
added shells and stones and seaw eed to make it look
some shells and rocks and seaw eed . He picked them
of shells , rocks and seaw eed , but Jane was
like fish and shells and seaw eed . One
the different fish and colorful seaw eed below .
shore , collecting shells and seaw eed . Jimmy took time
cast les and collect pretty seas hell s . One day
, cup cakes and ch ocol ates .
sky . Round shapes and other shapes that changed each day
sand cast les and collecting seas hell s .
ling and tick ling each other . Finally ,
his feet and threw a tant rum . "
to sail on the high seas . Lily was happy that
decorated it with shells and seaw eed . They had a

MIN ACTIVATIONS
MIN = -7.600

" Hi , I 'm Bee . Do you want to
. Her name was El isa and she was three years
friendly cat offered to be Honey 's guide . She said
the bird began to tell Pen elope it 's story .
girl . Her name was Cat . Cat had a special
bird began to tell Pen elope it 's story .
YOU ARE MA KING A M ESS ! AND YOU ARE
a bee came flying into Honey 's room . Honey named
. I want to prevent Fl uffy from getting hurt ."
The special menu prevented Laura and Alice from having an
. Lily wanted to prevent Fl uffy from getting hurt .
. The cat waved at Honey and said " Hi !
. They ask Mama if they can bake it
there was a girl called Moon . She was three years
We 're going to see Sun flower ," he said .
was excited and asked the chick , � � € �
I want to prevent Fl uffy from getting hurt ." Her
and out came a little chick ! Pe ep was so
there was a girl called Honey who lived in a small
" Hi Sp ud !" said Lily .

INTERVAL 3.513 - 7.217
CONTAINS 0.135%

is ". The other bees offered the tired bee
just as cheerful in her new uniform . From that day
They hugged each other and said , " We
They smile and admire each other 's drawings . They are
They learned that helping each other is very important . The

INTERVAL -0.192 - 3.513
CONTAINS 59.222%

felt happy and excited . " Thank you ,
at the seas hell and said , " Wow , Lily
to eat . One day , Tony found a whole bunch
Tim my found a sword that he had forgotten about .
need a bath ." Their mom agreed . She

INTERVAL -3.896 - -0.192
CONTAINS 40.614%

is sick ." " Let 's move away ,
." The little bear said , " I will
. The two spent the afternoon bouncing until soon
need to be wealthy to be happy . Their mom smiled
was ok . She said that it was ok to make

INTERVAL -7.600 - -3.896
CONTAINS 0.030%

help , telling her " M ummy , I wanna invite
joy of the new baby chick together . <|endoftext|> Once upon
on special days , like Honey 's birthday , Buzz y
shop . She gave Po ppy some money and said "
stopped . Sad and upset , Sandy and
Token sand
Token ID6450
Feature activation+6.43e+00

Pos logit contributions
 gol+0.177
David+0.150
aden+0.149
ival+0.144
 cheated+0.143
Neg logit contributions
 Sn-0.074
 pap-0.073
elope-0.072
isa-0.072
 sn-0.071
Token,
Token ID11
Feature activation+1.43e+00

Pos logit contributions
 gol+0.348
David+0.295
aden+0.294
ival+0.281
 cheated+0.279
Neg logit contributions
bing-0.112
mary-0.108
 sn-0.107
isa-0.106
elope-0.105
Token and
Token ID290
Feature activation+1.02e+00

Pos logit contributions
 gol+0.079
ival+0.067
aden+0.066
David+0.065
 cheated+0.063
Neg logit contributions
 sn-0.026
 pap-0.025
bing-0.024
 Sn-0.024
 Pr-0.023
Token deep
Token ID2769
Feature activation+1.99e+00

Pos logit contributions
 gol+0.053
aden+0.044
David+0.044
arl+0.043
ival+0.043
Neg logit contributions
 sn-0.022
 pap-0.021
 Sn-0.020
 Pr-0.020
 pur-0.020
Token blue
Token ID4171
Feature activation+1.72e+00

Pos logit contributions
 gol+0.107
David+0.091
aden+0.089
ival+0.088
 cheated+0.085
Neg logit contributions
bing-0.037
isa-0.036
elope-0.035
 sn-0.035
 pap-0.035
Token seas
Token ID21547
Feature activation+6.89e+00

Pos logit contributions
 gol+0.088
David+0.075
aden+0.073
ival+0.072
 cheated+0.070
Neg logit contributions
 sn-0.036
 eyel-0.035
 knees-0.035
 pap-0.034
isa-0.034
Token.
Token ID13
Feature activation+6.61e-01

Pos logit contributions
 gol+0.195
David+0.124
aden+0.122
ival+0.106
 cheated+0.103
Neg logit contributions
elope-0.308
isa-0.306
cel-0.306
mary-0.306
 sn-0.304
Token
Token ID220
Feature activation-5.71e-01

Pos logit contributions
 gol+0.032
aden+0.026
 cheated+0.026
aw+0.026
 tant+0.025
Neg logit contributions
 Sn-0.017
 Pr-0.017
 Moon-0.016
elope-0.016
 Chick-0.015
Token
Token ID198
Feature activation+7.99e-02

Pos logit contributions
elope+0.008
 Pr+0.008
 Sn+0.007
mary+0.007
 Ana+0.007
Neg logit contributions
 gol-0.036
 tant-0.028
 liar-0.028
 cheated-0.028
 trophies-0.028
Token
Token ID198
Feature activation-4.68e-01

Pos logit contributions
 gol+0.004
 cheated+0.003
aw+0.003
aden+0.003
 happened+0.003
Neg logit contributions
elope-0.002
 Sn-0.002
 Pr-0.002
isa-0.002
 Ana-0.001
TokenOne
Token ID3198
Feature activation-1.86e+00

Pos logit contributions
 Sn+0.010
elope+0.010
isa+0.010
 Pr+0.010
 Moon+0.009
Neg logit contributions
 gol-0.023
aden-0.019
 cheated-0.019
aw-0.019
 happened-0.019
Token cakes
Token ID30849
Feature activation-1.50e-01

Pos logit contributions
 gol+0.019
aden+0.015
David+0.015
ival+0.014
arl+0.014
Neg logit contributions
 pap-0.010
 Sn-0.010
 sn-0.010
 Moon-0.010
 Pr-0.009
Token and
Token ID290
Feature activation-1.00e-01

Pos logit contributions
mary+0.002
cel+0.002
 sn+0.002
 Sn+0.002
bing+0.002
Neg logit contributions
 gol-0.009
aden-0.007
David-0.007
 cheated-0.007
 tant-0.007
Token cookies
Token ID14746
Feature activation-1.49e-01

Pos logit contributions
 Sn+0.003
cel+0.003
isa+0.003
 pap+0.003
elope+0.003
Neg logit contributions
 gol-0.004
aw-0.003
aden-0.003
David-0.003
 cheated-0.003
Token and
Token ID290
Feature activation+5.33e-01

Pos logit contributions
mary+0.003
cel+0.003
 Sn+0.003
 sn+0.002
bing+0.002
Neg logit contributions
 gol-0.008
aden-0.007
David-0.007
aw-0.007
ival-0.006
Token ch
Token ID442
Feature activation+1.04e+00

Pos logit contributions
 gol+0.024
aden+0.019
David+0.019
aw+0.018
ival+0.018
Neg logit contributions
 pap-0.015
 sn-0.015
 Sn-0.015
 roast-0.014
cel-0.014
Tokenocol
Token ID4668
Feature activation+6.27e+00

Pos logit contributions
 gol+0.036
David+0.028
aden+0.027
ival+0.027
 cheated+0.026
Neg logit contributions
isa-0.038
mary-0.037
bing-0.037
 Pr-0.037
elope-0.037
Tokenates
Token ID689
Feature activation+2.60e-01

Pos logit contributions
 gol+0.255
aw+0.205
aden+0.199
David+0.199
 cheated+0.191
Neg logit contributions
 Sn-0.186
isa-0.185
cel-0.185
elope-0.184
 pap-0.184
Token and
Token ID290
Feature activation+9.83e-01

Pos logit contributions
 gol+0.015
aden+0.013
David+0.013
ival+0.012
aw+0.012
Neg logit contributions
mary-0.004
bing-0.004
 Sn-0.004
isa-0.004
 sn-0.004
Token ice
Token ID4771
Feature activation+2.51e+00

Pos logit contributions
 gol+0.046
aden+0.037
David+0.037
ival+0.035
ane+0.035
Neg logit contributions
 sn-0.026
 pap-0.026
 roast-0.026
 pur-0.025
 Sn-0.025
Token cream
Token ID8566
Feature activation+2.56e+00

Pos logit contributions
 gol+0.099
David+0.077
aden+0.075
 cheated+0.071
ival+0.069
Neg logit contributions
mary-0.085
isa-0.084
bing-0.083
 Sn-0.082
elope-0.082
Token.
Token ID13
Feature activation-2.16e-02

Pos logit contributions
 gol+0.149
David+0.128
aden+0.126
ival+0.121
 cheated+0.120
Neg logit contributions
 Sn-0.036
mary-0.035
 sn-0.034
bing-0.033
cel-0.033
Token colorful
Token ID20239
Feature activation+1.71e+00

Pos logit contributions
 gol+0.049
aw+0.039
aden+0.038
David+0.038
 cheated+0.036
Neg logit contributions
 Sn-0.035
isa-0.035
elope-0.035
cel-0.035
 pap-0.034
Token cand
Token ID2658
Feature activation+1.55e+00

Pos logit contributions
 gol+0.080
David+0.065
aden+0.065
aw+0.064
 cheated+0.063
Neg logit contributions
isa-0.041
cel-0.041
 Sn-0.040
 pap-0.040
elope-0.040
Tokenies
Token ID444
Feature activation-2.53e-01

Pos logit contributions
 gol+0.080
aden+0.065
David+0.065
aw+0.064
 cheated+0.063
Neg logit contributions
isa-0.032
bing-0.031
cel-0.031
 pap-0.031
elope-0.030
Token and
Token ID290
Feature activation+8.59e-01

Pos logit contributions
isa+0.005
cel+0.005
 Sn+0.005
elope+0.005
 pap+0.005
Neg logit contributions
 gol-0.013
aden-0.010
David-0.010
aw-0.010
 cheated-0.010
Token ch
Token ID442
Feature activation+1.07e+00

Pos logit contributions
 gol+0.040
aw+0.032
aden+0.032
David+0.032
ival+0.031
Neg logit contributions
isa-0.021
 Sn-0.021
 pap-0.021
cel-0.021
elope-0.021
Tokenocol
Token ID4668
Feature activation+5.98e+00

Pos logit contributions
 gol+0.040
David+0.032
 cheated+0.031
ival+0.031
aden+0.029
Neg logit contributions
isa-0.037
mary-0.037
 pap-0.036
bing-0.035
 Pr-0.035
Tokenates
Token ID689
Feature activation+2.98e-01

Pos logit contributions
 gol+0.284
aden+0.226
David+0.223
 cheated+0.220
aw+0.219
Neg logit contributions
isa-0.150
cel-0.146
elope-0.145
bing-0.144
 Sn-0.142
Token.
Token ID13
Feature activation+2.34e-01

Pos logit contributions
 gol+0.017
aden+0.014
David+0.014
aw+0.014
ival+0.014
Neg logit contributions
mary-0.005
bing-0.005
isa-0.005
 Sn-0.004
 pap-0.004
Token She
Token ID1375
Feature activation-7.90e-01

Pos logit contributions
 gol+0.012
aw+0.010
aden+0.010
David+0.010
 cheated+0.010
Neg logit contributions
 Sn-0.005
 Pr-0.005
 Chick-0.005
 pap-0.005
mary-0.005
Token said
Token ID531
Feature activation-2.48e-01

Pos logit contributions
cel+0.023
 Sn+0.023
isa+0.023
bing+0.022
elope+0.022
Neg logit contributions
 gol-0.032
aw-0.026
David-0.026
aden-0.025
 cheated-0.025
Token to
Token ID284
Feature activation+5.67e-01

Pos logit contributions
 pap+0.004
 Sn+0.004
 Pr+0.004
 Flower+0.004
 sn+0.004
Neg logit contributions
 gol-0.014
aden-0.012
David-0.012
aw-0.011
 cheated-0.011
Token and
Token ID290
Feature activation+7.94e-01

Pos logit contributions
 Sn+0.002
isa+0.002
bing+0.002
 pap+0.002
cel+0.002
Neg logit contributions
 gol-0.006
David-0.005
aden-0.005
aw-0.005
 cheated-0.005
Token her
Token ID607
Feature activation+1.50e+00

Pos logit contributions
 gol+0.036
aden+0.029
aw+0.029
David+0.029
ival+0.028
Neg logit contributions
 Sn-0.021
 pap-0.021
cel-0.020
isa-0.020
elope-0.020
Token favourite
Token ID12507
Feature activation+1.28e+00

Pos logit contributions
 gol+0.071
aw+0.058
aden+0.058
David+0.057
 cheated+0.056
Neg logit contributions
isa-0.035
cel-0.035
elope-0.034
 Sn-0.034
 pap-0.034
Token,
Token ID11
Feature activation+1.59e+00

Pos logit contributions
 gol+0.052
aw+0.041
aden+0.040
David+0.040
 cheated+0.039
Neg logit contributions
isa-0.038
cel-0.038
elope-0.037
bing-0.037
 pap-0.037
Token ch
Token ID442
Feature activation+8.40e-01

Pos logit contributions
 gol+0.078
aden+0.063
David+0.062
aw+0.061
 cheated+0.060
Neg logit contributions
 Sn-0.040
 sn-0.039
 pap-0.038
cel-0.038
 Pr-0.037
Tokenocol
Token ID4668
Feature activation+5.89e+00

Pos logit contributions
 gol+0.028
 cheated+0.021
David+0.021
aden+0.019
 happened+0.019
Neg logit contributions
isa-0.033
 pap-0.031
cel-0.030
mary-0.030
 Pr-0.030
Tokenates
Token ID689
Feature activation-2.22e-01

Pos logit contributions
 gol+0.268
aden+0.213
David+0.211
aw+0.210
 cheated+0.206
Neg logit contributions
isa-0.155
cel-0.152
elope-0.152
 Sn-0.150
 pap-0.149
Token!
Token ID0
Feature activation+1.35e+00

Pos logit contributions
isa+0.004
 Sn+0.004
 pap+0.004
elope+0.004
cel+0.004
Neg logit contributions
 gol-0.012
David-0.010
aden-0.010
aw-0.010
 cheated-0.009
Token She
Token ID1375
Feature activation-2.55e-01

Pos logit contributions
 gol+0.052
aw+0.040
David+0.040
aden+0.040
ax+0.038
Neg logit contributions
cel-0.043
bing-0.043
isa-0.042
elope-0.041
cup-0.041
Token asked
Token ID1965
Feature activation+6.08e-02

Pos logit contributions
bing+0.007
cel+0.007
 Sn+0.007
elope+0.007
isa+0.007
Neg logit contributions
 gol-0.011
aw-0.009
aden-0.008
David-0.008
 cheated-0.008
Token mummy
Token ID38567
Feature activation-3.28e+00

Pos logit contributions
 gol+0.002
 trophies+0.002
aden+0.002
 Tommy+0.002
David+0.002
Neg logit contributions
elope-0.002
cel-0.002
bes-0.002
cup-0.002
mary-0.002
Token like
Token ID588
Feature activation+5.74e-01

Pos logit contributions
 gol+0.029
aden+0.023
David+0.023
aw+0.023
ival+0.022
Neg logit contributions
 Sn-0.016
isa-0.016
cel-0.016
 pap-0.016
elope-0.016
Token fish
Token ID5916
Feature activation+3.83e-02

Pos logit contributions
 gol+0.026
David+0.021
aden+0.021
he+0.020
ival+0.020
Neg logit contributions
 sn-0.016
 pap-0.015
 Sn-0.015
 Pr-0.015
 roast-0.015
Token and
Token ID290
Feature activation+9.41e-01

Pos logit contributions
 gol+0.002
David+0.002
aden+0.002
aw+0.002
ival+0.002
Neg logit contributions
 Sn-0.001
elope-0.001
 pap-0.001
cel-0.001
isa-0.001
Token shells
Token ID19679
Feature activation+3.15e+00

Pos logit contributions
 gol+0.039
David+0.031
aden+0.031
aw+0.031
ival+0.030
Neg logit contributions
 pap-0.028
 Sn-0.028
isa-0.027
cel-0.027
elope-0.027
Token and
Token ID290
Feature activation+1.56e+00

Pos logit contributions
 gol+0.190
David+0.164
aden+0.160
ival+0.157
aw+0.153
Neg logit contributions
mary-0.039
 sn-0.038
 Sn-0.037
bing-0.035
 Pr-0.035
Token seaw
Token ID32085
Feature activation+5.87e+00

Pos logit contributions
 gol+0.065
David+0.053
aden+0.052
ival+0.051
aw+0.050
Neg logit contributions
 pap-0.047
 sn-0.046
 roast-0.045
 Sn-0.045
 Pr-0.044
Tokeneed
Token ID2308
Feature activation+1.58e+00

Pos logit contributions
 gol+0.204
aden+0.151
David+0.151
aw+0.150
 cheated+0.143
Neg logit contributions
cel-0.212
isa-0.211
 Sn-0.210
elope-0.209
 pap-0.209
Token.
Token ID13
Feature activation+4.15e-01

Pos logit contributions
 gol+0.090
David+0.076
aden+0.075
aw+0.073
ival+0.072
Neg logit contributions
 Sn-0.023
mary-0.023
isa-0.023
 pap-0.022
cel-0.022
Token But
Token ID887
Feature activation-7.40e-01

Pos logit contributions
 gol+0.019
aden+0.015
aw+0.015
David+0.015
 cheated+0.015
Neg logit contributions
 Sn-0.011
elope-0.010
 pap-0.010
isa-0.010
cel-0.010
Token they
Token ID484
Feature activation-3.87e-01

Pos logit contributions
cel+0.016
isa+0.015
elope+0.015
 Sn+0.014
bing+0.014
Neg logit contributions
 gol-0.037
aw-0.030
David-0.030
aden-0.029
 cheated-0.029
Token did
Token ID750
Feature activation+3.89e-01

Pos logit contributions
 pap+0.010
 sn+0.010
elope+0.010
isa+0.010
mary+0.009
Neg logit contributions
 gol-0.018
aden-0.014
ival-0.014
aw-0.014
David-0.014
Token them
Token ID606
Feature activation+1.08e+00

Pos logit contributions
 Sn+0.013
 pap+0.012
isa+0.012
 Pr+0.012
cel+0.012
Neg logit contributions
 gol-0.022
David-0.018
aden-0.017
aw-0.017
 cheated-0.017
Token tw
Token ID665
Feature activation+5.88e-02

Pos logit contributions
 gol+0.057
David+0.048
aw+0.047
aden+0.047
ival+0.046
Neg logit contributions
 Sn-0.020
bing-0.019
cel-0.019
elope-0.019
isa-0.019
Tokenirl
Token ID1901
Feature activation-1.27e+00

Pos logit contributions
 gol+0.003
aw+0.002
aden+0.002
David+0.002
 cheated+0.002
Neg logit contributions
elope-0.002
isa-0.002
cel-0.002
 pap-0.002
 Sn-0.002
Token around
Token ID1088
Feature activation-2.14e-01

Pos logit contributions
mary+0.015
 Sn+0.015
bing+0.015
 sn+0.013
bed+0.012
Neg logit contributions
 gol-0.077
David-0.069
aden-0.066
ival-0.063
 cheated-0.063
Token each
Token ID1123
Feature activation+1.72e+00

Pos logit contributions
cel+0.004
isa+0.004
 pap+0.004
elope+0.004
 Sn+0.004
Neg logit contributions
 gol-0.011
aw-0.009
aden-0.009
David-0.009
 cheated-0.008
Token other
Token ID584
Feature activation+5.87e+00

Pos logit contributions
 gol+0.072
aw+0.058
aden+0.057
David+0.056
 cheated+0.054
Neg logit contributions
cel-0.051
elope-0.050
 pap-0.050
 Sn-0.050
isa-0.050
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
 gol+0.287
aw+0.241
aden+0.235
David+0.230
 cheated+0.226
Neg logit contributions
cel-0.127
isa-0.124
 pap-0.122
 Sn-0.121
elope-0.121
Token Annie
Token ID25860
Feature activation-1.85e+00

Pos logit contributions
 gol+0.008
aden+0.006
aw+0.006
David+0.006
ival+0.006
Neg logit contributions
bing-0.007
cel-0.007
isa-0.007
 pap-0.007
elope-0.007
Token's
Token ID338
Feature activation-4.95e-02

Pos logit contributions
isa+0.043
elope+0.042
cel+0.042
 Sn+0.042
 pap+0.042
Neg logit contributions
 gol-0.089
aden-0.072
David-0.072
aw-0.072
ival-0.069
Token mother
Token ID2802
Feature activation-8.43e-01

Pos logit contributions
 pap+0.001
 Sn+0.001
 Pr+0.001
cel+0.001
 sn+0.001
Neg logit contributions
 gol-0.002
David-0.002
aw-0.002
aden-0.002
ival-0.002
Token called
Token ID1444
Feature activation+1.43e+00

Pos logit contributions
isa+0.019
cel+0.019
 sn+0.019
 pap+0.019
elope+0.019
Neg logit contributions
 gol-0.042
David-0.033
aden-0.033
aw-0.033
arl-0.032
Token added
Token ID2087
Feature activation-1.90e+00

Pos logit contributions
 sn+0.023
 roast+0.022
isa+0.022
 Sn+0.021
cel+0.021
Neg logit contributions
 gol-0.049
David-0.041
aw-0.041
aden-0.041
arl-0.041
Token shells
Token ID19679
Feature activation+2.01e+00

Pos logit contributions
 sn+0.031
 one+0.029
 making+0.027
 next+0.027
 roast+0.027
Neg logit contributions
 gol-0.113
David-0.098
aden-0.095
ival-0.091
ody-0.089
Token and
Token ID290
Feature activation-5.39e-02

Pos logit contributions
 gol+0.126
David+0.111
aden+0.109
 cheated+0.105
Goal+0.105
Neg logit contributions
mary-0.019
 sn-0.017
 Pr-0.016
 pap-0.016
bing-0.016
Token stones
Token ID14966
Feature activation+2.91e+00

Pos logit contributions
 pap+0.002
 sn+0.002
 roast+0.002
 Pr+0.002
 knees+0.002
Neg logit contributions
 gol-0.002
aden-0.002
ival-0.002
David-0.002
he-0.002
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
 gol+0.179
David+0.160
aden+0.158
ival+0.150
Goal+0.148
Neg logit contributions
mary-0.030
 sn-0.028
bing-0.025
 soon-0.025
 before-0.024
Token seaw
Token ID32085
Feature activation+5.84e+00

Pos logit contributions
 gol+0.046
aden+0.038
arl+0.038
David+0.038
ival+0.038
Neg logit contributions
 sn-0.028
 roast-0.026
 pap-0.026
 knees-0.025
 pur-0.025
Tokeneed
Token ID2308
Feature activation+1.30e+00

Pos logit contributions
 gol+0.227
David+0.176
aden+0.170
 cheated+0.168
 happened+0.161
Neg logit contributions
cel-0.190
 pap-0.182
isa-0.180
bing-0.179
 Sn-0.178
Token to
Token ID284
Feature activation+1.47e+00

Pos logit contributions
 gol+0.077
David+0.067
aden+0.066
ival+0.063
 cheated+0.062
Neg logit contributions
mary-0.017
 sn-0.016
bing-0.015
 Sn-0.015
 pap-0.015
Token make
Token ID787
Feature activation-2.32e+00

Pos logit contributions
 gol+0.086
aden+0.074
ival+0.074
David+0.074
ane+0.072
Neg logit contributions
 roast-0.022
 sn-0.021
 make-0.020
 side-0.019
 search-0.018
Token it
Token ID340
Feature activation-8.61e-01

Pos logit contributions
 sn+0.054
 pur+0.049
 pap+0.049
we+0.048
 Ana+0.048
Neg logit contributions
 gol-0.118
arl-0.098
David-0.097
aden-0.095
ival-0.094
Token look
Token ID804
Feature activation-3.27e-01

Pos logit contributions
 Sn+0.020
elope+0.020
 pap+0.020
cel+0.020
isa+0.020
Neg logit contributions
 gol-0.041
David-0.033
aden-0.033
aw-0.033
ival-0.031
Token some
Token ID617
Feature activation-1.12e+00

Pos logit contributions
 gol+0.127
David+0.105
ival+0.103
aden+0.103
arl+0.102
Neg logit contributions
 Bee-0.038
 pap-0.038
 sn-0.037
 Luna-0.036
 Pr-0.036
Token shells
Token ID19679
Feature activation+2.22e+00

Pos logit contributions
 sn+0.025
 pap+0.025
 buzzing+0.023
 Moon+0.023
 roast+0.022
Neg logit contributions
 gol-0.056
David-0.046
aden-0.045
ival-0.044
ax-0.044
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
 gol+0.128
David+0.109
aden+0.106
ival+0.104
aw+0.103
Neg logit contributions
 sn-0.034
bing-0.033
 following-0.031
mary-0.030
 Sn-0.030
Token rocks
Token ID12586
Feature activation+2.68e+00

Pos logit contributions
 gol+0.044
aden+0.035
David+0.035
aw+0.034
ival+0.034
Neg logit contributions
 pap-0.028
isa-0.028
 Sn-0.028
elope-0.027
cel-0.027
Token and
Token ID290
Feature activation+1.52e+00

Pos logit contributions
 gol+0.159
David+0.141
aden+0.134
ival+0.133
Goal+0.131
Neg logit contributions
 sn-0.036
bing-0.036
 following-0.033
mary-0.033
 making-0.031
Token seaw
Token ID32085
Feature activation+5.83e+00

Pos logit contributions
 gol+0.068
David+0.055
aden+0.055
ival+0.054
aw+0.053
Neg logit contributions
 pap-0.042
 sn-0.041
isa-0.039
 Pr-0.039
 roast-0.039
Tokeneed
Token ID2308
Feature activation+1.35e+00

Pos logit contributions
 gol+0.203
aden+0.149
David+0.149
aw+0.148
 cheated+0.142
Neg logit contributions
cel-0.211
isa-0.210
 Sn-0.209
 pap-0.208
elope-0.208
Token.
Token ID13
Feature activation+3.27e-01

Pos logit contributions
 gol+0.080
David+0.069
aden+0.067
ival+0.065
aw+0.064
Neg logit contributions
 sn-0.018
bing-0.018
mary-0.017
 Sn-0.017
 pap-0.016
Token He
Token ID679
Feature activation+5.81e-01

Pos logit contributions
 gol+0.014
aden+0.012
ival+0.011
David+0.011
 cheated+0.011
Neg logit contributions
 Pr-0.010
 Bee-0.010
 Luna-0.009
 Chick-0.009
 Milo-0.009
Token picked
Token ID6497
Feature activation+5.84e-01

Pos logit contributions
 gol+0.026
aden+0.021
aw+0.021
David+0.021
ival+0.020
Neg logit contributions
isa-0.015
 pap-0.015
 Sn-0.015
elope-0.015
cel-0.015
Token them
Token ID606
Feature activation+1.05e+00

Pos logit contributions
 gol+0.034
David+0.030
aden+0.028
ival+0.028
arl+0.028
Neg logit contributions
 sn-0.008
 Pr-0.008
 Sn-0.008
mary-0.008
 Flower-0.007
Token of
Token ID286
Feature activation+1.46e+00

Pos logit contributions
 gol+0.043
David+0.034
aden+0.033
aw+0.032
 cheated+0.032
Neg logit contributions
bing-0.032
isa-0.031
 Sn-0.031
cel-0.030
 Pr-0.030
Token shells
Token ID19679
Feature activation+2.99e+00

Pos logit contributions
 gol+0.072
arl+0.059
David+0.059
ane+0.058
ival+0.055
Neg logit contributions
 sn-0.034
bing-0.031
isa-0.031
 following-0.030
 Ana-0.030
Token,
Token ID11
Feature activation+1.48e+00

Pos logit contributions
 gol+0.168
David+0.141
aden+0.137
aw+0.134
 cheated+0.133
Neg logit contributions
mary-0.048
bing-0.047
 sn-0.047
cel-0.045
isa-0.044
Token rocks
Token ID12586
Feature activation+2.42e+00

Pos logit contributions
 gol+0.066
David+0.052
aden+0.052
ival+0.051
arl+0.050
Neg logit contributions
 sn-0.040
 pap-0.040
cel-0.039
 Sn-0.039
 Pr-0.039
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
 gol+0.138
David+0.118
aden+0.116
Goal+0.113
aw+0.113
Neg logit contributions
bing-0.037
mary-0.036
 sn-0.033
 Sn-0.033
cel-0.033
Token seaw
Token ID32085
Feature activation+5.83e+00

Pos logit contributions
 gol+0.067
David+0.054
aden+0.053
aw+0.053
arl+0.052
Neg logit contributions
 pap-0.038
 sn-0.037
isa-0.036
 Sn-0.036
 Pr-0.036
Tokeneed
Token ID2308
Feature activation+1.43e+00

Pos logit contributions
 gol+0.219
David+0.165
aden+0.163
 cheated+0.161
aw+0.156
Neg logit contributions
cel-0.196
isa-0.190
 pap-0.189
bing-0.187
mary-0.185
Token,
Token ID11
Feature activation+2.05e+00

Pos logit contributions
 gol+0.081
David+0.068
aden+0.067
aw+0.065
ival+0.065
Neg logit contributions
mary-0.023
bing-0.022
 Sn-0.022
isa-0.021
 pap-0.021
Token but
Token ID475
Feature activation-4.22e-01

Pos logit contributions
 gol+0.112
aden+0.093
David+0.093
aw+0.091
ival+0.091
Neg logit contributions
 pap-0.035
 sn-0.035
 Sn-0.034
cel-0.034
bing-0.033
Token Jane
Token ID12091
Feature activation+3.92e-01

Pos logit contributions
elope+0.009
isa+0.009
 pap+0.009
 Sn+0.009
 Pr+0.009
Neg logit contributions
 gol-0.021
aden-0.018
aw-0.017
David-0.017
ival-0.017
Token was
Token ID373
Feature activation+9.46e-01

Pos logit contributions
 gol+0.019
David+0.015
aden+0.015
aw+0.015
ival+0.015
Neg logit contributions
isa-0.009
elope-0.009
cel-0.009
 pap-0.009
 Sn-0.009
Token like
Token ID588
Feature activation+6.20e-01

Pos logit contributions
 gol+0.032
aden+0.026
David+0.026
aw+0.026
ival+0.025
Neg logit contributions
 Sn-0.015
 pap-0.015
 sn-0.015
cel-0.015
isa-0.015
Token fish
Token ID5916
Feature activation+6.20e-02

Pos logit contributions
 gol+0.029
David+0.024
he+0.023
aden+0.023
ival+0.023
Neg logit contributions
 sn-0.017
 pap-0.016
 Sn-0.016
 Pr-0.015
 roast-0.015
Token and
Token ID290
Feature activation+8.99e-01

Pos logit contributions
 gol+0.003
David+0.003
aden+0.003
aw+0.003
ival+0.003
Neg logit contributions
 Sn-0.001
 pap-0.001
elope-0.001
isa-0.001
cel-0.001
Token shells
Token ID19679
Feature activation+3.20e+00

Pos logit contributions
 gol+0.040
David+0.032
aden+0.032
aw+0.031
ival+0.031
Neg logit contributions
 pap-0.025
 sn-0.024
 roast-0.024
 Sn-0.024
 Pr-0.024
Token and
Token ID290
Feature activation+1.51e+00

Pos logit contributions
 gol+0.195
David+0.169
aden+0.165
ival+0.162
Goal+0.156
Neg logit contributions
mary-0.038
 sn-0.038
 Sn-0.036
bing-0.034
 Pr-0.033
Token seaw
Token ID32085
Feature activation+5.81e+00

Pos logit contributions
 gol+0.066
David+0.054
aden+0.053
ival+0.053
aw+0.052
Neg logit contributions
 pap-0.043
 sn-0.043
 roast-0.042
 Sn-0.040
 Pr-0.040
Tokeneed
Token ID2308
Feature activation+1.62e+00

Pos logit contributions
 gol+0.209
David+0.156
aden+0.155
aw+0.151
 cheated+0.148
Neg logit contributions
cel-0.203
isa-0.202
 pap-0.201
elope-0.199
 Sn-0.199
Token.
Token ID13
Feature activation+3.60e-01

Pos logit contributions
 gol+0.092
David+0.079
aden+0.077
aw+0.075
ival+0.075
Neg logit contributions
mary-0.023
 Sn-0.023
isa-0.023
 pap-0.023
bing-0.022
Token
Token ID198
Feature activation+2.34e-01

Pos logit contributions
 gol+0.017
aw+0.014
aden+0.014
David+0.014
 cheated+0.014
Neg logit contributions
 Sn-0.009
 Pr-0.009
elope-0.009
 Chick-0.008
 pap-0.008
Token
Token ID198
Feature activation-3.14e-01

Pos logit contributions
 gol+0.011
aw+0.009
aden+0.009
 cheated+0.009
David+0.009
Neg logit contributions
 Sn-0.006
elope-0.006
isa-0.005
 Pr-0.005
 Chick-0.005
TokenOne
Token ID3198
Feature activation-2.03e+00

Pos logit contributions
cel+0.007
 pap+0.007
isa+0.007
elope+0.007
 Sn+0.007
Neg logit contributions
 gol-0.015
aw-0.013
David-0.013
aden-0.012
ival-0.012
Token the
Token ID262
Feature activation+3.77e-01

Pos logit contributions
 gol+0.088
David+0.073
aden+0.073
aw+0.071
ival+0.070
Neg logit contributions
 Sn-0.034
elope-0.034
 pap-0.034
bing-0.034
isa-0.033
Token different
Token ID1180
Feature activation+7.96e-01

Pos logit contributions
 gol+0.015
aden+0.012
aw+0.012
David+0.012
 cheated+0.011
Neg logit contributions
isa-0.012
elope-0.011
 Sn-0.011
cel-0.011
 pap-0.011
Token fish
Token ID5916
Feature activation+8.16e-01

Pos logit contributions
 gol+0.036
aw+0.029
aden+0.029
David+0.029
 cheated+0.028
Neg logit contributions
cel-0.020
isa-0.020
 Sn-0.020
elope-0.020
 pap-0.020
Token and
Token ID290
Feature activation+6.57e-01

Pos logit contributions
 gol+0.040
aw+0.033
aden+0.033
David+0.033
 cheated+0.032
Neg logit contributions
cel-0.017
 Sn-0.017
isa-0.017
 pap-0.017
elope-0.017
Token colorful
Token ID20239
Feature activation+2.22e+00

Pos logit contributions
 gol+0.032
aw+0.026
aden+0.026
David+0.026
 cheated+0.025
Neg logit contributions
cel-0.015
 Sn-0.015
isa-0.015
elope-0.014
 pap-0.014
Token seaw
Token ID32085
Feature activation+5.76e+00

Pos logit contributions
 gol+0.097
David+0.078
aden+0.078
aw+0.076
 cheated+0.074
Neg logit contributions
isa-0.061
 pap-0.060
 Sn-0.060
cel-0.059
elope-0.059
Tokeneed
Token ID2308
Feature activation+1.47e+00

Pos logit contributions
 gol+0.190
aw+0.140
aden+0.137
David+0.136
 cheated+0.128
Neg logit contributions
 Sn-0.219
isa-0.218
elope-0.217
cel-0.217
 pap-0.216
Token below
Token ID2174
Feature activation+1.78e+00

Pos logit contributions
 gol+0.076
aw+0.063
aden+0.063
David+0.063
 cheated+0.061
Neg logit contributions
isa-0.027
 Sn-0.027
cel-0.027
elope-0.027
 pap-0.027
Token.
Token ID13
Feature activation+4.56e-01

Pos logit contributions
 gol+0.101
aden+0.084
David+0.084
ival+0.082
 cheated+0.081
Neg logit contributions
elope-0.028
 Pr-0.028
 Sn-0.028
 sn-0.027
isa-0.027
Token
Token ID198
Feature activation+1.66e-01

Pos logit contributions
 gol+0.022
aden+0.018
aw+0.018
David+0.018
 cheated+0.018
Neg logit contributions
elope-0.011
 Pr-0.011
 Sn-0.011
 Flower-0.010
isa-0.010
Token
Token ID198
Feature activation-2.88e-01

Pos logit contributions
 gol+0.008
aw+0.007
aden+0.007
 cheated+0.007
David+0.006
Neg logit contributions
elope-0.004
 Sn-0.004
isa-0.004
 Pr-0.004
 Chick-0.003
Token shore
Token ID15191
Feature activation+8.77e-01

Pos logit contributions
 gol+0.052
aw+0.041
aden+0.041
David+0.041
 cheated+0.039
Neg logit contributions
isa-0.035
 Sn-0.035
cel-0.035
elope-0.035
 pap-0.035
Token,
Token ID11
Feature activation+1.16e+00

Pos logit contributions
 gol+0.047
aden+0.039
David+0.039
aw+0.038
 cheated+0.038
Neg logit contributions
isa-0.016
elope-0.016
bing-0.016
 Sn-0.015
 pap-0.015
Token collecting
Token ID13157
Feature activation+3.55e-01

Pos logit contributions
 gol+0.060
aw+0.050
aden+0.050
David+0.050
 cheated+0.048
Neg logit contributions
isa-0.022
cel-0.021
elope-0.021
 Sn-0.021
 pap-0.021
Token shells
Token ID19679
Feature activation+2.79e+00

Pos logit contributions
 gol+0.016
David+0.013
aden+0.013
 cheated+0.012
ival+0.012
Neg logit contributions
 sn-0.010
 pap-0.009
 Pr-0.009
 Sn-0.009
bing-0.009
Token and
Token ID290
Feature activation+5.43e-01

Pos logit contributions
 gol+0.158
David+0.133
aden+0.130
 cheated+0.129
ival+0.127
Neg logit contributions
bing-0.043
 sn-0.041
mary-0.040
 Sn-0.040
 pap-0.040
Token seaw
Token ID32085
Feature activation+5.73e+00

Pos logit contributions
 gol+0.026
aden+0.021
aw+0.021
David+0.021
ival+0.021
Neg logit contributions
 pap-0.013
 sn-0.013
isa-0.012
 Sn-0.012
bing-0.012
Tokeneed
Token ID2308
Feature activation+1.41e+00

Pos logit contributions
 gol+0.211
David+0.157
aden+0.157
 cheated+0.154
aw+0.151
Neg logit contributions
cel-0.196
isa-0.194
 pap-0.192
bing-0.191
elope-0.190
Token.
Token ID13
Feature activation+3.38e-01

Pos logit contributions
 gol+0.080
David+0.068
aden+0.066
aw+0.064
ival+0.064
Neg logit contributions
bing-0.022
 Sn-0.021
mary-0.021
isa-0.021
 sn-0.020
Token Jimmy
Token ID12963
Feature activation+8.93e-01

Pos logit contributions
 gol+0.016
aw+0.014
David+0.013
aden+0.013
 cheated+0.013
Neg logit contributions
 Sn-0.009
 Pr-0.008
 Ana-0.008
elope-0.008
 Moon-0.007
Token took
Token ID1718
Feature activation-1.60e-01

Pos logit contributions
 gol+0.041
aw+0.034
aden+0.033
David+0.033
 cheated+0.032
Neg logit contributions
cel-0.021
 Sn-0.021
isa-0.021
elope-0.021
 pap-0.021
Token time
Token ID640
Feature activation-1.64e-01

Pos logit contributions
 sn+0.003
 Pr+0.003
 Sn+0.003
 one+0.003
 Moon+0.002
Neg logit contributions
 gol-0.009
arl-0.007
David-0.007
ane-0.007
aden-0.007
Tokencast
Token ID2701
Feature activation+1.49e+00

Pos logit contributions
 gol+0.126
David+0.100
aden+0.097
 cheated+0.095
ival+0.092
Neg logit contributions
bing-0.088
 sn-0.086
 Sn-0.084
mary-0.083
we-0.083
Tokenles
Token ID829
Feature activation+5.96e-01

Pos logit contributions
 gol+0.080
David+0.066
 liar+0.064
 cheated+0.063
 fault+0.063
Neg logit contributions
ches-0.034
isa-0.030
bing-0.028
mary-0.028
 every-0.027
Token and
Token ID290
Feature activation+1.35e-01

Pos logit contributions
 gol+0.034
David+0.029
aden+0.029
 cheated+0.027
ival+0.027
Neg logit contributions
bing-0.009
mary-0.009
isa-0.009
 sn-0.009
 Sn-0.008
Token collect
Token ID2824
Feature activation+9.64e-01

Pos logit contributions
 gol+0.007
aw+0.006
arl+0.006
David+0.005
aden+0.005
Neg logit contributions
 sn-0.003
 roast-0.003
isa-0.003
 pap-0.003
 Sn-0.003
Token pretty
Token ID2495
Feature activation+1.35e+00

Pos logit contributions
 gol+0.046
David+0.038
arl+0.035
ane+0.034
aden+0.034
Neg logit contributions
 sn-0.028
 one-0.025
 n-0.024
 Ana-0.024
 Pr-0.023
Token seas
Token ID21547
Feature activation+5.73e+00

Pos logit contributions
 gol+0.054
David+0.042
 cheated+0.041
aden+0.040
ival+0.039
Neg logit contributions
 sn-0.043
bing-0.042
 pap-0.042
isa-0.042
cel-0.042
Tokenhell
Token ID12758
Feature activation+2.51e+00

Pos logit contributions
 gol+0.149
David+0.093
aden+0.089
 cheated+0.087
aw+0.073
Neg logit contributions
mary-0.265
cel-0.262
isa-0.261
elope-0.256
bing-0.254
Tokens
Token ID82
Feature activation+4.26e-01

Pos logit contributions
 gol+0.139
David+0.121
aden+0.116
 cheated+0.111
aw+0.110
Neg logit contributions
mary-0.042
bing-0.040
 Sn-0.038
isa-0.038
 sn-0.038
Token.
Token ID13
Feature activation+5.41e-01

Pos logit contributions
 gol+0.026
David+0.022
aden+0.022
ival+0.021
 cheated+0.021
Neg logit contributions
bing-0.005
 sn-0.005
mary-0.005
elope-0.005
 pap-0.005
Token One
Token ID1881
Feature activation-1.39e+00

Pos logit contributions
 gol+0.027
 cheated+0.022
aw+0.022
aden+0.022
David+0.022
Neg logit contributions
 Sn-0.012
elope-0.012
 Pr-0.012
 Chick-0.011
 Moon-0.011
Token day
Token ID1110
Feature activation-7.95e-01

Pos logit contributions
isa+0.031
 pap+0.030
 Pr+0.030
 sn+0.029
elope+0.029
Neg logit contributions
 gol-0.069
aden-0.058
David-0.058
 cheated-0.057
ival-0.056
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
 gol+0.013
David+0.011
aden+0.011
aw+0.011
 tant+0.011
Neg logit contributions
bing-0.004
 Sn-0.003
 sn-0.003
 pap-0.003
isa-0.003
Token cup
Token ID6508
Feature activation-3.48e-01

Pos logit contributions
 gol+0.059
aden+0.049
aw+0.048
David+0.048
ival+0.048
Neg logit contributions
 Sn-0.026
 pap-0.024
 sn-0.024
cel-0.024
 Pr-0.023
Tokencakes
Token ID37263
Feature activation-1.08e+00

Pos logit contributions
 Sn+0.008
mary+0.008
 sn+0.008
cel+0.008
 pap+0.008
Neg logit contributions
 gol-0.017
David-0.014
aden-0.014
 cheated-0.013
Kyle-0.013
Token and
Token ID290
Feature activation+5.88e-01

Pos logit contributions
 Sn+0.022
cel+0.022
isa+0.022
elope+0.021
 pap+0.021
Neg logit contributions
 gol-0.055
aden-0.045
David-0.045
aw-0.045
 cheated-0.043
Token ch
Token ID442
Feature activation+1.00e+00

Pos logit contributions
 gol+0.027
aden+0.021
David+0.021
aw+0.021
ival+0.021
Neg logit contributions
 Sn-0.016
 sn-0.016
 pap-0.016
 Pr-0.015
cel-0.015
Tokenocol
Token ID4668
Feature activation+5.66e+00

Pos logit contributions
 gol+0.037
David+0.030
 cheated+0.029
ival+0.028
 happened+0.027
Neg logit contributions
bing-0.033
mary-0.032
isa-0.032
 Pr-0.031
 Sn-0.031
Tokenates
Token ID689
Feature activation+2.07e-01

Pos logit contributions
 gol+0.287
aden+0.231
David+0.228
 cheated+0.227
ival+0.223
Neg logit contributions
isa-0.128
bing-0.124
cup-0.123
we-0.122
cel-0.121
Token.
Token ID13
Feature activation+5.56e-01

Pos logit contributions
 gol+0.012
David+0.010
aden+0.010
aw+0.010
ival+0.010
Neg logit contributions
 Sn-0.003
bing-0.003
isa-0.003
mary-0.003
 sn-0.003
Token
Token ID220
Feature activation-6.90e-01

Pos logit contributions
 gol+0.026
aw+0.021
 happened+0.021
ival+0.021
aden+0.020
Neg logit contributions
 Sn-0.016
 Pr-0.014
 Chick-0.012
 Fl-0.012
elope-0.012
Token
Token ID198
Feature activation+2.55e-01

Pos logit contributions
 Sn+0.011
 Pr+0.009
elope+0.009
 Chick+0.008
mary+0.008
Neg logit contributions
 gol-0.042
aw-0.033
 tant-0.033
 liar-0.033
aden-0.032
Token
Token ID198
Feature activation-2.86e-01

Pos logit contributions
 gol+0.014
 happened+0.012
aw+0.012
 cheated+0.011
aden+0.011
Neg logit contributions
 Sn-0.005
 Pr-0.004
elope-0.004
mary-0.003
 Flower-0.003
Token sky
Token ID6766
Feature activation-3.93e-01

Pos logit contributions
 gol+0.037
David+0.030
aden+0.030
aw+0.029
ival+0.029
Neg logit contributions
 Sn-0.019
elope-0.019
cel-0.019
isa-0.019
 sn-0.019
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
isa+0.008
cel+0.008
 Sn+0.008
elope+0.008
 pap+0.008
Neg logit contributions
 gol-0.020
aw-0.017
aden-0.016
David-0.016
 cheated-0.016
Token Round
Token ID10485
Feature activation-4.97e-01

Pos logit contributions
 gol+0.005
aden+0.004
David+0.004
aw+0.004
 cheated+0.004
Neg logit contributions
 Sn-0.003
isa-0.003
cel-0.003
elope-0.003
 pap-0.003
Token shapes
Token ID15268
Feature activation+2.51e+00

Pos logit contributions
isa+0.007
 Moon+0.007
 Sn+0.007
 sn+0.007
elope+0.007
Neg logit contributions
 gol-0.028
David-0.025
aden-0.025
arl-0.023
 cheated-0.023
Token and
Token ID290
Feature activation+7.41e-01

Pos logit contributions
 gol+0.119
David+0.100
aden+0.099
aw+0.094
ival+0.093
Neg logit contributions
 sn-0.060
bing-0.058
isa-0.058
mary-0.057
 pap-0.057
Token other
Token ID584
Feature activation+5.64e+00

Pos logit contributions
 gol+0.034
aw+0.028
aden+0.027
David+0.027
 cheated+0.026
Neg logit contributions
isa-0.018
cel-0.018
 Sn-0.018
elope-0.018
 pap-0.018
Token shapes
Token ID15268
Feature activation+2.49e+00

Pos logit contributions
 gol+0.284
David+0.235
arl+0.233
aden+0.225
ax+0.221
Neg logit contributions
isa-0.127
 sn-0.123
 Moon-0.120
 pap-0.119
elope-0.118
Token that
Token ID326
Feature activation+1.15e+00

Pos logit contributions
 gol+0.128
David+0.109
aden+0.107
aw+0.103
ival+0.102
Neg logit contributions
 sn-0.050
bing-0.048
mary-0.048
 pap-0.047
 pur-0.047
Token changed
Token ID3421
Feature activation-9.16e-01

Pos logit contributions
 gol+0.057
David+0.049
aden+0.048
aw+0.047
arl+0.047
Neg logit contributions
 sn-0.024
 pap-0.024
 Pr-0.024
 Moon-0.024
elope-0.024
Token each
Token ID1123
Feature activation+1.03e+00

Pos logit contributions
bing+0.017
 pap+0.016
 Pr+0.016
isa+0.016
elope+0.016
Neg logit contributions
 gol-0.050
David-0.042
aden-0.042
ival-0.042
aw-0.040
Token day
Token ID1110
Feature activation+2.04e-01

Pos logit contributions
 gol+0.046
aw+0.037
aden+0.037
David+0.037
 cheated+0.035
Neg logit contributions
isa-0.027
 Sn-0.027
elope-0.027
cel-0.027
 pap-0.027
Token sand
Token ID6450
Feature activation+3.74e+00

Pos logit contributions
 gol+0.015
David+0.012
aden+0.012
aw+0.012
 cheated+0.012
Neg logit contributions
 Sn-0.009
cel-0.009
isa-0.009
bing-0.009
 pap-0.009
Tokencast
Token ID2701
Feature activation+1.77e+00

Pos logit contributions
 gol+0.184
David+0.151
aden+0.148
 cheated+0.143
ival+0.141
Neg logit contributions
bing-0.091
mary-0.086
isa-0.085
 Sn-0.084
cel-0.084
Tokenles
Token ID829
Feature activation+8.04e-01

Pos logit contributions
 gol+0.090
David+0.073
aden+0.069
 liar+0.069
 cheated+0.068
Neg logit contributions
isa-0.042
ches-0.042
mary-0.040
bing-0.040
 sn-0.038
Token and
Token ID290
Feature activation+3.87e-01

Pos logit contributions
 gol+0.044
David+0.037
aden+0.037
ival+0.035
 cheated+0.035
Neg logit contributions
bing-0.014
isa-0.013
 Sn-0.013
mary-0.013
cel-0.013
Token collecting
Token ID13157
Feature activation+6.43e-01

Pos logit contributions
 gol+0.019
aw+0.016
David+0.016
aden+0.016
ival+0.015
Neg logit contributions
isa-0.008
 pap-0.008
 Sn-0.008
 sn-0.008
cel-0.008
Token seas
Token ID21547
Feature activation+5.61e+00

Pos logit contributions
 gol+0.028
David+0.023
aden+0.021
 cheated+0.021
ane+0.020
Neg logit contributions
 sn-0.020
 Ana-0.018
mary-0.018
 Pr-0.018
 knees-0.018
Tokenhell
Token ID12758
Feature activation+2.38e+00

Pos logit contributions
 gol+0.151
David+0.093
aden+0.089
 cheated+0.084
ival+0.074
Neg logit contributions
mary-0.261
cel-0.256
isa-0.256
elope-0.252
we-0.251
Tokens
Token ID82
Feature activation-1.39e-01

Pos logit contributions
 gol+0.133
David+0.114
aden+0.111
 cheated+0.106
aw+0.106
Neg logit contributions
mary-0.039
bing-0.038
 Sn-0.037
isa-0.037
elope-0.035
Token.
Token ID13
Feature activation+4.55e-01

Pos logit contributions
bing+0.002
mary+0.002
 sn+0.002
 Sn+0.002
elope+0.002
Neg logit contributions
 gol-0.008
David-0.007
aden-0.007
ival-0.007
 cheated-0.007
Token
Token ID220
Feature activation-9.80e-01

Pos logit contributions
 gol+0.022
aw+0.018
aden+0.018
 cheated+0.018
David+0.018
Neg logit contributions
 Sn-0.011
 Pr-0.011
elope-0.011
isa-0.010
 Chick-0.010
Token
Token ID198
Feature activation+6.44e-02

Pos logit contributions
 Sn+0.017
 Pr+0.017
elope+0.016
 Chick+0.016
mary+0.015
Neg logit contributions
 gol-0.057
 tant-0.045
 cheated-0.044
aden-0.044
aw-0.044
Tokenling
Token ID1359
Feature activation-1.71e+00

Pos logit contributions
bing+0.024
isa+0.019
mary+0.018
we+0.017
 Sn+0.016
Neg logit contributions
 gol-0.085
David-0.074
aden-0.072
 cheated-0.071
ival-0.071
Token and
Token ID290
Feature activation+3.50e-01

Pos logit contributions
isa+0.040
cel+0.040
 Sn+0.039
elope+0.039
 pap+0.039
Neg logit contributions
 gol-0.081
aw-0.067
aden-0.065
David-0.065
 cheated-0.064
Token tick
Token ID4378
Feature activation-1.50e+00

Pos logit contributions
 gol+0.017
 cheated+0.013
aden+0.013
David+0.013
aw+0.013
Neg logit contributions
isa-0.008
elope-0.008
cel-0.008
 pap-0.007
 Chick-0.007
Tokenling
Token ID1359
Feature activation-1.45e+00

Pos logit contributions
isa+0.045
cel+0.045
 Sn+0.045
elope+0.045
 pap+0.045
Neg logit contributions
 gol-0.062
aw-0.049
aden-0.048
David-0.048
 cheated-0.046
Token each
Token ID1123
Feature activation+1.84e+00

Pos logit contributions
isa+0.033
cel+0.033
 Sn+0.032
elope+0.032
 pap+0.032
Neg logit contributions
 gol-0.069
aw-0.057
aden-0.056
David-0.056
 cheated-0.055
Token other
Token ID584
Feature activation+5.60e+00

Pos logit contributions
 gol+0.085
David+0.068
aden+0.068
aw+0.067
 cheated+0.065
Neg logit contributions
isa-0.047
elope-0.046
 Sn-0.046
 Pr-0.045
cel-0.045
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
 gol+0.251
aw+0.212
aden+0.205
 cheated+0.201
ax+0.196
Neg logit contributions
 pap-0.134
cel-0.133
isa-0.131
 roast-0.126
 Chick-0.125
Token
Token ID198
Feature activation+1.56e-01

Pos logit contributions
 gol+0.007
aden+0.005
aw+0.005
David+0.005
 cheated+0.005
Neg logit contributions
 Sn-0.004
elope-0.004
 Pr-0.003
isa-0.003
cel-0.003
Token
Token ID198
Feature activation-3.33e-01

Pos logit contributions
 gol+0.008
aw+0.006
aden+0.006
 cheated+0.006
David+0.006
Neg logit contributions
elope-0.004
 Sn-0.004
isa-0.004
 Pr-0.003
 Chick-0.003
TokenFinally
Token ID11158
Feature activation+3.07e-01

Pos logit contributions
 Sn+0.008
isa+0.008
elope+0.008
cel+0.008
bing+0.007
Neg logit contributions
 gol-0.016
aden-0.013
aw-0.013
David-0.013
 cheated-0.012
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
 gol+0.015
aw+0.012
David+0.012
aden+0.012
 cheated+0.011
Neg logit contributions
isa-0.007
cel-0.007
elope-0.007
 Sn-0.007
 pap-0.007
Token his
Token ID465
Feature activation+1.19e+00

Pos logit contributions
 gol+0.060
ival+0.046
aden+0.045
David+0.044
aw+0.043
Neg logit contributions
 Pr-0.041
 Sn-0.041
 sn-0.039
isa-0.039
 pap-0.038
Token feet
Token ID3625
Feature activation+8.49e-01

Pos logit contributions
 gol+0.069
aw+0.058
David+0.058
aden+0.058
ival+0.057
Neg logit contributions
 pap-0.016
elope-0.016
isa-0.016
 Sn-0.016
cel-0.015
Token and
Token ID290
Feature activation+4.73e-01

Pos logit contributions
 gol+0.046
David+0.038
aden+0.038
aw+0.037
ival+0.037
Neg logit contributions
 Sn-0.015
bing-0.015
 sn-0.014
isa-0.014
 Pr-0.014
Token threw
Token ID9617
Feature activation+5.11e-01

Pos logit contributions
 gol+0.022
aw+0.018
aden+0.018
David+0.017
 cheated+0.017
Neg logit contributions
isa-0.012
cel-0.012
elope-0.012
 Sn-0.012
 pap-0.011
Token a
Token ID257
Feature activation-3.34e-01

Pos logit contributions
 gol+0.028
David+0.024
ival+0.024
aden+0.023
ane+0.023
Neg logit contributions
 Sn-0.011
 sn-0.010
 one-0.010
 Pr-0.009
 side-0.009
Token tant
Token ID24246
Feature activation+5.56e+00

Pos logit contributions
 bit+0.010
 sn+0.008
 b+0.008
 pur+0.007
 pose+0.007
Neg logit contributions
 gol-0.015
David-0.014
aden-0.014
aw-0.013
ateful-0.013
Tokenrum
Token ID6582
Feature activation-4.76e-01

Pos logit contributions
 gol+0.196
aw+0.150
aden+0.149
David+0.147
 cheated+0.142
Neg logit contributions
 Sn-0.202
cel-0.198
 pap-0.195
elope-0.194
 roast-0.192
Token.
Token ID13
Feature activation+3.70e-01

Pos logit contributions
bing+0.007
 Sn+0.007
elope+0.007
isa+0.007
we+0.007
Neg logit contributions
 gol-0.027
David-0.023
aden-0.023
ival-0.022
aw-0.022
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
 gol+0.019
aden+0.016
ival+0.015
aw+0.015
ane+0.015
Neg logit contributions
 Sn-0.008
 Pr-0.008
 Luna-0.008
 Milo-0.008
 Bee-0.008
Token
Token ID198
Feature activation-3.24e-01

Pos logit contributions
 gol+0.008
aden+0.007
aw+0.007
 trophies+0.006
 cheated+0.006
Neg logit contributions
 Sn-0.003
 Pr-0.003
elope-0.003
 Chick-0.003
 Luna-0.003
Token"
Token ID1
Feature activation-1.61e+00

Pos logit contributions
 Sn+0.007
elope+0.007
isa+0.007
 Pr+0.007
 pap+0.007
Neg logit contributions
 gol-0.016
aden-0.013
aw-0.012
 cheated-0.012
ival-0.012
Token to
Token ID284
Feature activation+1.21e+00

Pos logit contributions
 Sn+0.014
isa+0.013
elope+0.013
cel+0.013
 pap+0.013
Neg logit contributions
 gol-0.034
aden-0.028
David-0.027
aw-0.027
ival-0.026
Token sail
Token ID14936
Feature activation+1.18e+00

Pos logit contributions
 gol+0.064
aw+0.053
aden+0.053
David+0.053
 cheated+0.052
Neg logit contributions
isa-0.022
cel-0.021
bing-0.021
elope-0.020
 pap-0.020
Token on
Token ID319
Feature activation+2.09e-01

Pos logit contributions
 gol+0.067
David+0.059
aden+0.058
 cheated+0.055
ax+0.054
Neg logit contributions
 Sn-0.019
mary-0.019
 sn-0.017
bing-0.016
 Ruby-0.016
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
 gol+0.011
aden+0.009
David+0.009
 cheated+0.009
aw+0.009
Neg logit contributions
 Sn-0.004
isa-0.004
elope-0.004
cel-0.004
mary-0.004
Token high
Token ID1029
Feature activation+1.59e+00

Pos logit contributions
 gol+0.045
aw+0.036
David+0.036
aden+0.036
 cheated+0.034
Neg logit contributions
 Sn-0.028
cel-0.028
isa-0.028
 pap-0.028
elope-0.028
Token seas
Token ID21547
Feature activation+5.53e+00

Pos logit contributions
 gol+0.071
David+0.057
aden+0.057
aw+0.057
 cheated+0.055
Neg logit contributions
isa-0.041
 Sn-0.041
elope-0.041
cel-0.040
 pap-0.040
Token.
Token ID13
Feature activation+1.13e-01

Pos logit contributions
 gol+0.220
David+0.170
aden+0.169
aw+0.167
 cheated+0.163
Neg logit contributions
isa-0.173
cel-0.171
elope-0.171
 Sn-0.171
bing-0.167
Token Lily
Token ID20037
Feature activation+4.63e-01

Pos logit contributions
 gol+0.005
aw+0.004
aden+0.004
David+0.004
 cheated+0.004
Neg logit contributions
 Sn-0.003
cel-0.003
 Pr-0.003
 Chick-0.003
elope-0.003
Token was
Token ID373
Feature activation+7.15e-01

Pos logit contributions
 gol+0.021
aw+0.017
aden+0.017
David+0.017
 cheated+0.017
Neg logit contributions
 Sn-0.011
cel-0.011
isa-0.011
elope-0.011
 pap-0.011
Token happy
Token ID3772
Feature activation-2.18e-01

Pos logit contributions
 gol+0.033
aw+0.026
 cheated+0.026
David+0.026
aden+0.026
Neg logit contributions
isa-0.018
cel-0.018
elope-0.018
mary-0.017
bing-0.017
Token that
Token ID326
Feature activation-3.03e-01

Pos logit contributions
cel+0.007
isa+0.006
elope+0.006
 Sn+0.006
mary+0.006
Neg logit contributions
 gol-0.009
aw-0.007
David-0.007
aden-0.007
 happened-0.007
Token decorated
Token ID24789
Feature activation+5.23e-01

Pos logit contributions
 gol+0.033
aden+0.028
David+0.028
aw+0.027
ival+0.027
Neg logit contributions
 sn-0.014
 roast-0.014
 pap-0.014
elope-0.013
 knees-0.013
Token it
Token ID340
Feature activation+2.30e-01

Pos logit contributions
 gol+0.023
aden+0.018
David+0.018
aw+0.018
 cheated+0.018
Neg logit contributions
 Sn-0.014
isa-0.014
elope-0.014
 pap-0.014
bing-0.014
Token with
Token ID351
Feature activation+9.78e-02

Pos logit contributions
 gol+0.010
aw+0.009
 cheated+0.009
 trophies+0.008
he+0.008
Neg logit contributions
cel-0.006
isa-0.006
 pap-0.006
elope-0.005
 Sn-0.005
Token shells
Token ID19679
Feature activation+2.72e+00

Pos logit contributions
 gol+0.005
ival+0.004
aden+0.004
David+0.004
ane+0.004
Neg logit contributions
 sn-0.002
 pap-0.002
 roast-0.002
 Pr-0.002
 pur-0.002
Token and
Token ID290
Feature activation+1.03e+00

Pos logit contributions
 gol+0.165
David+0.144
aden+0.140
ival+0.137
Goal+0.135
Neg logit contributions
mary-0.032
 sn-0.030
 Sn-0.029
bing-0.028
 Pr-0.028
Token seaw
Token ID32085
Feature activation+5.50e+00

Pos logit contributions
 gol+0.045
David+0.037
aden+0.036
ival+0.036
he+0.035
Neg logit contributions
 pap-0.031
 sn-0.030
 roast-0.029
 knees-0.029
 Moon-0.028
Tokeneed
Token ID2308
Feature activation+1.59e+00

Pos logit contributions
 gol+0.204
David+0.154
aden+0.153
 cheated+0.148
aw+0.146
Neg logit contributions
cel-0.188
isa-0.185
 pap-0.184
elope-0.181
bing-0.180
Token.
Token ID13
Feature activation+2.68e-01

Pos logit contributions
 gol+0.094
David+0.082
aden+0.080
ival+0.077
aw+0.076
Neg logit contributions
mary-0.020
 Sn-0.019
bing-0.019
 pap-0.019
 sn-0.019
Token They
Token ID1119
Feature activation-7.33e-01

Pos logit contributions
 gol+0.014
aden+0.012
aw+0.012
David+0.011
ival+0.011
Neg logit contributions
 Sn-0.006
 Pr-0.005
elope-0.005
 Chick-0.005
 pap-0.005
Token had
Token ID550
Feature activation+1.08e+00

Pos logit contributions
 sn+0.017
isa+0.016
 pap+0.016
 roast+0.016
 Sn+0.016
Neg logit contributions
 gol-0.036
David-0.030
aw-0.030
aden-0.029
arl-0.029
Token a
Token ID257
Feature activation+1.04e-01

Pos logit contributions
 gol+0.041
aden+0.031
aw+0.031
David+0.031
ival+0.029
Neg logit contributions
 Sn-0.036
isa-0.036
elope-0.036
 pap-0.036
cel-0.035
Token "
Token ID366
Feature activation-8.89e-01

Pos logit contributions
 gol+0.005
aw+0.004
David+0.004
 cheated+0.004
 happened+0.004
Neg logit contributions
isa-0.004
elope-0.004
cel-0.004
bing-0.004
 Sn-0.004
TokenHi
Token ID17250
Feature activation+5.68e-02

Pos logit contributions
cel+0.032
isa+0.032
 Sn+0.032
 pap+0.032
elope+0.032
Neg logit contributions
 gol-0.031
aw-0.024
David-0.023
aden-0.022
 cheated-0.021
Token,
Token ID11
Feature activation-1.26e+00

Pos logit contributions
 gol+0.003
aw+0.002
aden+0.002
David+0.002
 cheated+0.002
Neg logit contributions
isa-0.001
cel-0.001
elope-0.001
 Sn-0.001
bing-0.001
Token I
Token ID314
Feature activation+3.78e-01

Pos logit contributions
isa+0.034
cel+0.034
elope+0.034
 Sn+0.034
 pap+0.033
Neg logit contributions
 gol-0.055
aw-0.044
aden-0.044
David-0.044
 cheated-0.042
Token'm
Token ID1101
Feature activation-2.77e+00

Pos logit contributions
 gol+0.017
aden+0.014
David+0.014
aw+0.014
ival+0.013
Neg logit contributions
elope-0.010
cel-0.010
 Sn-0.010
 sn-0.010
isa-0.010
Token Bee
Token ID24719
Feature activation-5.98e+00

Pos logit contributions
isa+0.089
cel+0.089
elope+0.088
 Sn+0.088
 pap+0.087
Neg logit contributions
 gol-0.108
aw-0.084
aden-0.082
David-0.082
 cheated-0.079
Token.
Token ID13
Feature activation-9.12e-01

Pos logit contributions
cel+0.167
bing+0.160
 roast+0.151
isa+0.150
 knees+0.150
Neg logit contributions
 gol-0.249
aw-0.212
ax-0.192
aden-0.188
 cheated-0.187
Token Do
Token ID2141
Feature activation+9.77e-01

Pos logit contributions
bing+0.032
isa+0.031
 pap+0.030
cel+0.030
elope+0.030
Neg logit contributions
 gol-0.033
aw-0.024
aden-0.023
 cheated-0.023
David-0.023
Token you
Token ID345
Feature activation+1.12e+00

Pos logit contributions
 gol+0.042
aw+0.034
David+0.033
aden+0.033
 cheated+0.032
Neg logit contributions
isa-0.028
cel-0.027
 Sn-0.027
elope-0.027
bing-0.027
Token want
Token ID765
Feature activation+1.71e+00

Pos logit contributions
 gol+0.048
David+0.039
aw+0.038
aden+0.038
ival+0.037
Neg logit contributions
 sn-0.031
isa-0.030
elope-0.030
cel-0.030
 pap-0.030
Token to
Token ID284
Feature activation-8.57e-01

Pos logit contributions
 gol+0.061
aw+0.050
 chalk+0.048
 happened+0.047
 cheated+0.046
Neg logit contributions
isa-0.062
elope-0.062
bing-0.062
cel-0.061
 Sn-0.057
Token.
Token ID13
Feature activation+2.93e-01

Pos logit contributions
cel+0.019
 pap+0.019
 Sn+0.019
isa+0.018
elope+0.018
Neg logit contributions
 gol-0.040
aw-0.034
David-0.032
aden-0.032
 cheated-0.032
Token Her
Token ID2332
Feature activation-1.53e+00

Pos logit contributions
 gol+0.012
aw+0.009
David+0.009
aden+0.009
 cheated+0.009
Neg logit contributions
bing-0.009
isa-0.009
 pap-0.009
cel-0.009
 Sn-0.009
Token name
Token ID1438
Feature activation+1.24e+00

Pos logit contributions
isa+0.046
 Sn+0.046
cel+0.045
elope+0.045
 pap+0.045
Neg logit contributions
 gol-0.063
aw-0.049
aden-0.049
David-0.049
 cheated-0.047
Token was
Token ID373
Feature activation+4.77e-01

Pos logit contributions
 gol+0.061
aw+0.051
aden+0.050
David+0.050
 cheated+0.049
Neg logit contributions
isa-0.026
cel-0.026
 Sn-0.026
elope-0.026
 pap-0.026
Token El
Token ID2574
Feature activation-4.63e+00

Pos logit contributions
 gol+0.020
aw+0.016
aden+0.015
David+0.015
 cheated+0.015
Neg logit contributions
isa-0.014
cel-0.014
 Sn-0.014
elope-0.014
 pap-0.014
Tokenisa
Token ID9160
Feature activation-5.86e+00

Pos logit contributions
 Sn+0.109
cel+0.109
 pap+0.107
bing+0.105
elope+0.104
Neg logit contributions
 gol-0.217
aw-0.184
aden-0.177
David-0.171
ax-0.170
Token and
Token ID290
Feature activation+6.15e-01

Pos logit contributions
bing+0.181
 convince+0.167
 Sn+0.166
cel+0.164
 roast+0.163
Neg logit contributions
 gol-0.205
aw-0.200
aden-0.164
 happened-0.164
 Tommy-0.162
Token she
Token ID673
Feature activation+3.58e-01

Pos logit contributions
 gol+0.028
aw+0.022
aden+0.022
David+0.022
 cheated+0.022
Neg logit contributions
cel-0.016
isa-0.016
elope-0.016
 Sn-0.016
bing-0.015
Token was
Token ID373
Feature activation+5.57e-01

Pos logit contributions
 gol+0.012
 cheated+0.009
aw+0.009
 happened+0.009
aden+0.008
Neg logit contributions
bing-0.013
isa-0.013
 pap-0.013
 Pr-0.013
cel-0.013
Token three
Token ID1115
Feature activation-1.48e+00

Pos logit contributions
 gol+0.024
 cheated+0.019
aw+0.018
 Tommy+0.017
aden+0.017
Neg logit contributions
bing-0.016
isa-0.016
cel-0.016
we-0.015
elope-0.015
Token years
Token ID812
Feature activation-1.99e-02

Pos logit contributions
 roast+0.038
 Sn+0.038
 Stacy+0.037
 pap+0.037
cup+0.037
Neg logit contributions
aw-0.063
 gol-0.060
 tant-0.052
aden-0.052
 trophies-0.051
Token friendly
Token ID8030
Feature activation+1.81e+00

Pos logit contributions
isa+0.007
cel+0.007
bing+0.007
elope+0.006
 Sn+0.006
Neg logit contributions
 gol-0.009
aw-0.007
aden-0.007
David-0.007
 cheated-0.007
Token cat
Token ID3797
Feature activation-8.99e-01

Pos logit contributions
 gol+0.074
aw+0.059
aden+0.055
David+0.055
 cheated+0.054
Neg logit contributions
isa-0.055
cel-0.055
bing-0.054
 Sn-0.053
elope-0.053
Token offered
Token ID4438
Feature activation-4.10e-01

Pos logit contributions
cel+0.026
 Sn+0.026
bing+0.026
isa+0.026
 pap+0.025
Neg logit contributions
 gol-0.037
aw-0.030
aden-0.029
 cheated-0.029
David-0.029
Token to
Token ID284
Feature activation-8.11e-01

Pos logit contributions
cel+0.013
bing+0.013
isa+0.013
elope+0.012
 roast+0.012
Neg logit contributions
 gol-0.015
aw-0.013
 happened-0.012
ax-0.012
 cheated-0.012
Token be
Token ID307
Feature activation-9.32e-01

Pos logit contributions
isa+0.020
cel+0.019
bing+0.019
elope+0.018
mary+0.018
Neg logit contributions
 gol-0.036
aden-0.029
David-0.029
 Tommy-0.029
 cheated-0.028
Token Honey
Token ID21788
Feature activation-5.76e+00

Pos logit contributions
cel+0.028
isa+0.027
bing+0.027
 Sn+0.026
mary+0.026
Neg logit contributions
 gol-0.037
aw-0.032
David-0.030
aden-0.029
 cheated-0.029
Token's
Token ID338
Feature activation-2.69e+00

Pos logit contributions
cel+0.166
 eyel+0.150
isa+0.149
we+0.147
bing+0.143
Neg logit contributions
 gol-0.222
aw-0.188
ax-0.181
aden-0.174
he-0.172
Token guide
Token ID5698
Feature activation-3.72e-01

Pos logit contributions
cel+0.081
isa+0.080
bing+0.077
 Chick+0.075
 Sn+0.074
Neg logit contributions
 gol-0.110
aw-0.087
aden-0.086
David-0.084
 cheated-0.082
Token.
Token ID13
Feature activation-1.13e-01

Pos logit contributions
cel+0.009
isa+0.008
 Sn+0.008
bing+0.008
elope+0.008
Neg logit contributions
 gol-0.017
aw-0.015
aden-0.014
David-0.014
ax-0.014
Token She
Token ID1375
Feature activation-8.39e-01

Pos logit contributions
we+0.003
isa+0.003
bing+0.003
cel+0.003
elope+0.003
Neg logit contributions
 gol-0.004
aw-0.004
 Tommy-0.003
ax-0.003
arl-0.003
Token said
Token ID531
Feature activation-7.11e-02

Pos logit contributions
bing+0.025
cel+0.025
isa+0.024
 Sn+0.024
 Pr+0.023
Neg logit contributions
 gol-0.034
aw-0.027
aden-0.026
David-0.026
 cheated-0.026
Token the
Token ID262
Feature activation+1.05e+00

Pos logit contributions
cel+0.012
bing+0.012
we+0.012
 roast+0.011
mary+0.011
Neg logit contributions
 gol-0.012
aw-0.011
 happened-0.011
 cheated-0.011
ival-0.010
Token bird
Token ID6512
Feature activation-1.02e+00

Pos logit contributions
 gol+0.049
aden+0.042
David+0.041
aw+0.040
ax+0.040
Neg logit contributions
 pap-0.025
elope-0.024
 sn-0.024
 Pr-0.024
 Flower-0.024
Token began
Token ID2540
Feature activation-6.18e-01

Pos logit contributions
 Sn+0.030
isa+0.029
cel+0.029
 pap+0.029
elope+0.028
Neg logit contributions
 gol-0.042
aw-0.035
aden-0.033
David-0.033
 cheated-0.033
Token to
Token ID284
Feature activation-9.49e-01

Pos logit contributions
cel+0.019
isa+0.019
 Sn+0.019
elope+0.019
bing+0.018
Neg logit contributions
 gol-0.024
aw-0.019
David-0.019
 happened-0.018
aden-0.018
Token tell
Token ID1560
Feature activation-1.43e+00

Pos logit contributions
isa+0.020
cel+0.020
 Sn+0.019
bing+0.019
we+0.019
Neg logit contributions
 gol-0.046
David-0.037
aden-0.037
 cheated-0.037
aw-0.037
Token Pen
Token ID7507
Feature activation-5.69e+00

Pos logit contributions
cel+0.044
bing+0.042
 roast+0.039
mary+0.039
we+0.039
Neg logit contributions
 gol-0.051
aw-0.050
 cheated-0.043
 happened-0.043
he-0.043
Tokenelope
Token ID47329
Feature activation-5.67e+00

Pos logit contributions
bing+0.088
cel+0.085
 roast+0.083
 Sn+0.078
bed+0.070
Neg logit contributions
aw-0.270
 gol-0.258
ax-0.240
David-0.239
 happened-0.237
Token it
Token ID340
Feature activation-4.16e-01

Pos logit contributions
cel+0.152
isa+0.148
 Sn+0.146
bing+0.146
elope+0.140
Neg logit contributions
 gol-0.238
aw-0.203
aden-0.194
 cheated-0.192
David-0.191
Token's
Token ID338
Feature activation-1.72e+00

Pos logit contributions
cel+0.010
isa+0.010
 Sn+0.010
bing+0.010
 pap+0.010
Neg logit contributions
 gol-0.018
aw-0.016
 happened-0.015
 cheated-0.015
aden-0.015
Token story
Token ID1621
Feature activation-1.57e+00

Pos logit contributions
cel+0.053
isa+0.053
 Sn+0.053
bing+0.052
elope+0.050
Neg logit contributions
 gol-0.070
aw-0.053
aden-0.053
David-0.053
 cheated-0.052
Token.
Token ID13
Feature activation+5.98e-01

Pos logit contributions
elope+0.030
isa+0.030
cel+0.030
 Sn+0.030
 sn+0.029
Neg logit contributions
 gol-0.083
aden-0.068
David-0.067
aw-0.066
 cheated-0.064
Token girl
Token ID2576
Feature activation+4.88e-01

Pos logit contributions
 gol+0.044
ival+0.039
David+0.039
aden+0.038
 cheated+0.037
Neg logit contributions
 pap-0.015
 Pr-0.014
elope-0.013
 sn-0.013
isa-0.013
Token.
Token ID13
Feature activation+1.64e-01

Pos logit contributions
 gol+0.024
aden+0.020
aw+0.020
David+0.020
ival+0.019
Neg logit contributions
isa-0.010
elope-0.010
cel-0.010
 Sn-0.010
 pap-0.010
Token Her
Token ID2332
Feature activation-1.72e+00

Pos logit contributions
 gol+0.008
aw+0.007
aden+0.007
ival+0.007
 cheated+0.007
Neg logit contributions
 Sn-0.004
 Pr-0.004
elope-0.004
 Moon-0.003
 pap-0.003
Token name
Token ID1438
Feature activation+1.11e+00

Pos logit contributions
 pap+0.037
elope+0.034
 Sn+0.033
 Flower+0.032
 Moon+0.032
Neg logit contributions
 gol-0.089
David-0.077
aden-0.077
aw-0.076
ax-0.074
Token was
Token ID373
Feature activation-7.07e-04

Pos logit contributions
 gol+0.061
aden+0.050
David+0.050
aw+0.048
ax+0.048
Neg logit contributions
 Sn-0.020
cel-0.019
elope-0.019
 sn-0.019
 pap-0.019
Token Cat
Token ID5181
Feature activation-5.67e+00

Pos logit contributions
 Sn+0.000
 pap+0.000
 Pr+0.000
 Chick+0.000
elope+0.000
Neg logit contributions
 gol-0.000
ival-0.000
aden-0.000
aw-0.000
 cheated-0.000
Token.
Token ID13
Feature activation-4.45e-02

Pos logit contributions
 roast+0.136
cel+0.135
 pap+0.135
bing+0.134
isa+0.133
Neg logit contributions
 gol-0.238
aw-0.214
aden-0.197
ax-0.191
David-0.191
Token Cat
Token ID5181
Feature activation-3.26e+00

Pos logit contributions
bing+0.001
cel+0.001
isa+0.001
 pap+0.001
we+0.001
Neg logit contributions
 gol-0.002
aw-0.002
David-0.002
aden-0.002
 cheated-0.001
Token had
Token ID550
Feature activation+8.09e-01

Pos logit contributions
 pap+0.081
cel+0.080
 Sn+0.080
bing+0.079
isa+0.079
Neg logit contributions
 gol-0.141
aw-0.121
aden-0.115
 cheated-0.114
David-0.112
Token a
Token ID257
Feature activation-1.93e-01

Pos logit contributions
 gol+0.042
aden+0.034
David+0.033
ival+0.033
aw+0.033
Neg logit contributions
 pap-0.017
 sn-0.017
 Pr-0.017
 Sn-0.017
elope-0.017
Token special
Token ID2041
Feature activation+2.54e-02

Pos logit contributions
 pap+0.005
elope+0.005
isa+0.005
 Sn+0.005
cel+0.005
Neg logit contributions
 gol-0.009
aw-0.007
aden-0.007
David-0.007
 cheated-0.007
Token bird
Token ID6512
Feature activation-1.02e+00

Pos logit contributions
 gol+0.049
aden+0.042
David+0.041
aw+0.040
ax+0.040
Neg logit contributions
 pap-0.025
elope-0.024
 sn-0.024
 Pr-0.024
 Flower-0.024
Token began
Token ID2540
Feature activation-6.18e-01

Pos logit contributions
 Sn+0.030
isa+0.029
cel+0.029
 pap+0.029
elope+0.028
Neg logit contributions
 gol-0.042
aw-0.035
aden-0.033
David-0.033
 cheated-0.033
Token to
Token ID284
Feature activation-9.49e-01

Pos logit contributions
cel+0.019
isa+0.019
 Sn+0.019
elope+0.019
bing+0.018
Neg logit contributions
 gol-0.024
aw-0.019
David-0.019
 happened-0.018
aden-0.018
Token tell
Token ID1560
Feature activation-1.43e+00

Pos logit contributions
isa+0.020
cel+0.020
 Sn+0.019
bing+0.019
we+0.019
Neg logit contributions
 gol-0.046
David-0.037
aden-0.037
 cheated-0.037
aw-0.037
Token Pen
Token ID7507
Feature activation-5.69e+00

Pos logit contributions
cel+0.044
bing+0.042
 roast+0.039
mary+0.039
we+0.039
Neg logit contributions
 gol-0.051
aw-0.050
 cheated-0.043
 happened-0.043
he-0.043
Tokenelope
Token ID47329
Feature activation-5.67e+00

Pos logit contributions
bing+0.088
cel+0.085
 roast+0.083
 Sn+0.078
bed+0.070
Neg logit contributions
aw-0.270
 gol-0.258
ax-0.240
David-0.239
 happened-0.237
Token it
Token ID340
Feature activation-4.16e-01

Pos logit contributions
cel+0.152
isa+0.148
 Sn+0.146
bing+0.146
elope+0.140
Neg logit contributions
 gol-0.238
aw-0.203
aden-0.194
 cheated-0.192
David-0.191
Token's
Token ID338
Feature activation-1.72e+00

Pos logit contributions
cel+0.010
isa+0.010
 Sn+0.010
bing+0.010
 pap+0.010
Neg logit contributions
 gol-0.018
aw-0.016
 happened-0.015
 cheated-0.015
aden-0.015
Token story
Token ID1621
Feature activation-1.57e+00

Pos logit contributions
cel+0.053
isa+0.053
 Sn+0.053
bing+0.052
elope+0.050
Neg logit contributions
 gol-0.070
aw-0.053
aden-0.053
David-0.053
 cheated-0.052
Token.
Token ID13
Feature activation+5.98e-01

Pos logit contributions
elope+0.030
isa+0.030
cel+0.030
 Sn+0.030
 sn+0.029
Neg logit contributions
 gol-0.083
aden-0.068
David-0.067
aw-0.066
 cheated-0.064
Token
Token ID220
Feature activation-1.05e+00

Pos logit contributions
aw+0.013
 gol+0.013
 Tommy+0.012
he+0.012
ival+0.012
Neg logit contributions
bing-0.024
we-0.023
cel-0.023
ci-0.023
isa-0.021
TokenYOU
Token ID36981
Feature activation-1.65e+00

Pos logit contributions
 gol+0.009
aw+0.008
aden+0.008
ival+0.007
David+0.007
Neg logit contributions
 Sn-0.005
isa-0.005
bing-0.005
we-0.005
cel-0.005
Token ARE
Token ID15986
Feature activation-1.94e+00

Pos logit contributions
cel+0.057
isa+0.056
 Sn+0.055
elope+0.055
 sn+0.053
Neg logit contributions
 gol-0.062
aden-0.047
David-0.046
aw-0.045
 cheated-0.043
Token MA
Token ID8779
Feature activation-2.04e+00

Pos logit contributions
 Sn+0.054
isa+0.053
cel+0.053
 pap+0.053
elope+0.052
Neg logit contributions
 gol-0.084
David-0.066
aden-0.066
aw-0.066
 cheated-0.064
TokenKING
Token ID37286
Feature activation-2.30e+00

Pos logit contributions
 pap+0.066
isa+0.066
 Sn+0.066
elope+0.066
cel+0.066
Neg logit contributions
 gol-0.080
aw-0.063
David-0.060
aden-0.060
ival-0.058
Token A
Token ID317
Feature activation-1.73e+00

Pos logit contributions
 Sn+0.058
cel+0.058
elope+0.056
isa+0.056
 pap+0.055
Neg logit contributions
 gol-0.106
aden-0.087
aw-0.086
David-0.086
 cheated-0.083
Token M
Token ID337
Feature activation-5.66e+00

Pos logit contributions
 Sn+0.045
 sn+0.045
cel+0.045
isa+0.044
 Pr+0.044
Neg logit contributions
 gol-0.078
David-0.064
aden-0.064
aw-0.063
ax-0.060
TokenESS
Token ID7597
Feature activation-5.96e-01

Pos logit contributions
isa+0.176
 Sn+0.170
cel+0.170
 pap+0.168
elope+0.168
Neg logit contributions
 gol-0.230
David-0.178
 cheated-0.177
aw-0.176
aden-0.175
Token!
Token ID0
Feature activation-5.24e-02

Pos logit contributions
cel+0.013
isa+0.013
 Sn+0.013
elope+0.013
 pap+0.013
Neg logit contributions
 gol-0.029
David-0.024
aden-0.024
aw-0.024
 cheated-0.023
Token AND
Token ID5357
Feature activation-3.61e-01

Pos logit contributions
isa+0.001
cel+0.001
 Sn+0.001
elope+0.001
 pap+0.001
Neg logit contributions
 gol-0.002
aw-0.002
aden-0.002
David-0.002
 cheated-0.002
Token YOU
Token ID7013
Feature activation+1.90e+00

Pos logit contributions
 Sn+0.010
cel+0.010
isa+0.010
elope+0.010
 pap+0.010
Neg logit contributions
 gol-0.016
aw-0.012
aden-0.012
David-0.012
 cheated-0.012
Token ARE
Token ID15986
Feature activation-2.06e+00

Pos logit contributions
 gol+0.082
aw+0.069
aden+0.066
David+0.065
 cheated+0.065
Neg logit contributions
 pap-0.051
isa-0.050
bing-0.050
 Sn-0.050
elope-0.050
Token a
Token ID257
Feature activation-4.83e-01

Pos logit contributions
 Sn+0.023
 pap+0.022
 sn+0.022
 Pr+0.022
 Moon+0.021
Neg logit contributions
 gol-0.053
aden-0.043
aw-0.043
ival-0.043
 cheated-0.042
Token bee
Token ID20697
Feature activation-3.43e+00

Pos logit contributions
 pap+0.013
 sn+0.012
 Moon+0.012
 Sn+0.012
elope+0.011
Neg logit contributions
 gol-0.022
aden-0.019
aw-0.019
David-0.018
ax-0.018
Token came
Token ID1625
Feature activation+8.24e-03

Pos logit contributions
 Sn+0.101
 pap+0.098
isa+0.097
cel+0.096
 Pr+0.095
Neg logit contributions
 gol-0.141
aw-0.120
aden-0.109
 cheated-0.108
David-0.108
Token flying
Token ID7348
Feature activation-1.18e+00

Pos logit contributions
 gol+0.000
aw+0.000
aden+0.000
David+0.000
ax+0.000
Neg logit contributions
cel-0.000
 Sn-0.000
isa-0.000
elope-0.000
 pap-0.000
Token into
Token ID656
Feature activation-5.75e-01

Pos logit contributions
isa+0.023
 Sn+0.023
elope+0.023
bing+0.023
mary+0.022
Neg logit contributions
 gol-0.061
aden-0.051
David-0.051
aw-0.049
 cheated-0.049
Token Honey
Token ID21788
Feature activation-5.63e+00

Pos logit contributions
 Pr+0.011
 pap+0.011
 Sn+0.010
isa+0.010
 Moon+0.010
Neg logit contributions
 gol-0.031
aden-0.026
ival-0.026
David-0.026
aw-0.026
Token's
Token ID338
Feature activation-2.26e+00

Pos logit contributions
 Sn+0.131
cel+0.130
 eyel+0.117
 pap+0.116
 Ana+0.116
Neg logit contributions
 gol-0.245
aw-0.217
he-0.192
ax-0.189
aden-0.187
Token room
Token ID2119
Feature activation-5.60e-01

Pos logit contributions
cel+0.054
isa+0.054
 Sn+0.054
elope+0.052
 pap+0.052
Neg logit contributions
 gol-0.105
aw-0.086
aden-0.085
David-0.084
 cheated-0.082
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
isa+0.011
 Sn+0.011
cel+0.011
elope+0.011
 pap+0.011
Neg logit contributions
 gol-0.028
aw-0.024
aden-0.023
David-0.023
 cheated-0.023
Token Honey
Token ID21788
Feature activation-3.79e+00

Pos logit contributions
 gol+0.007
aw+0.006
David+0.006
aden+0.006
 Tommy+0.006
Neg logit contributions
bing-0.005
isa-0.005
we-0.004
cel-0.004
elope-0.004
Token named
Token ID3706
Feature activation+1.37e+00

Pos logit contributions
 Sn+0.106
cel+0.104
 Pr+0.100
 pap+0.099
isa+0.099
Neg logit contributions
 gol-0.153
aw-0.131
 cheated-0.121
David-0.121
 happened-0.119
Token.
Token ID13
Feature activation-8.36e-01

Pos logit contributions
 Sn+0.019
cel+0.019
isa+0.018
bing+0.018
elope+0.018
Neg logit contributions
 gol-0.050
David-0.042
aden-0.042
aw-0.041
ival-0.040
Token I
Token ID314
Feature activation+1.30e+00

Pos logit contributions
isa+0.028
bing+0.027
elope+0.027
 pap+0.026
we+0.026
Neg logit contributions
 gol-0.031
aw-0.024
aden-0.024
 cheated-0.023
David-0.023
Token want
Token ID765
Feature activation+2.00e+00

Pos logit contributions
 gol+0.053
David+0.043
aw+0.043
aden+0.042
ival+0.040
Neg logit contributions
cel-0.039
elope-0.039
 Sn-0.038
isa-0.038
 sn-0.038
Token to
Token ID284
Feature activation-7.29e-01

Pos logit contributions
 gol+0.070
aw+0.055
 chalk+0.055
 cheated+0.055
 Tommy+0.055
Neg logit contributions
elope-0.071
isa-0.069
cel-0.068
bing-0.067
mary-0.061
Token prevent
Token ID2948
Feature activation-2.49e+00

Pos logit contributions
isa+0.019
elope+0.018
bing+0.017
cel+0.017
 Sn+0.017
Neg logit contributions
 gol-0.034
aden-0.027
 cheated-0.027
David-0.027
aw-0.027
Token Fl
Token ID1610
Feature activation-5.63e+00

Pos logit contributions
isa+0.071
elope+0.071
cel+0.070
 pap+0.067
mary+0.067
Neg logit contributions
 gol-0.106
aw-0.085
aden-0.083
 cheated-0.083
David-0.080
Tokenuffy
Token ID15352
Feature activation-5.42e+00

Pos logit contributions
 pap+0.225
cel+0.218
isa+0.218
 Moon+0.218
 Pr+0.216
Neg logit contributions
 gol-0.168
aw-0.129
arl-0.126
ane-0.116
he-0.114
Token from
Token ID422
Feature activation-1.54e+00

Pos logit contributions
isa+0.138
elope+0.133
 pap+0.132
cel+0.131
 Moon+0.125
Neg logit contributions
 gol-0.250
aw-0.205
 cheated-0.198
aden-0.196
he-0.193
Token getting
Token ID1972
Feature activation-2.60e+00

Pos logit contributions
isa+0.036
elope+0.036
cel+0.035
mary+0.033
 Sn+0.033
Neg logit contributions
 gol-0.074
aden-0.059
aw-0.059
 cheated-0.059
David-0.059
Token hurt
Token ID5938
Feature activation-1.52e+00

Pos logit contributions
isa+0.069
elope+0.069
cel+0.068
 Sn+0.066
 pap+0.066
Neg logit contributions
 gol-0.117
aw-0.093
aden-0.093
David-0.092
 cheated-0.090
Token."
Token ID526
Feature activation+3.46e-01

Pos logit contributions
isa+0.029
cel+0.029
elope+0.029
 pap+0.029
 Sn+0.028
Neg logit contributions
 gol-0.079
aw-0.066
aden-0.065
David-0.064
 cheated-0.064
Token
Token ID198
Feature activation+9.24e-02

Pos logit contributions
 gol+0.029
aden+0.023
aw+0.022
David+0.022
 cheated+0.022
Neg logit contributions
elope-0.018
isa-0.018
 Sn-0.017
cel-0.017
 pap-0.017
TokenThe
Token ID464
Feature activation-6.02e-01

Pos logit contributions
 gol+0.004
aw+0.003
David+0.003
aden+0.003
ival+0.003
Neg logit contributions
 Sn-0.003
cel-0.003
 pap-0.003
isa-0.003
elope-0.003
Token special
Token ID2041
Feature activation+1.05e+00

Pos logit contributions
elope+0.021
bing+0.021
 Chick+0.020
cel+0.020
isa+0.020
Neg logit contributions
 gol-0.022
David-0.017
aden-0.017
aw-0.017
ival-0.017
Token menu
Token ID6859
Feature activation+9.64e-01

Pos logit contributions
 gol+0.036
David+0.026
aw+0.026
aden+0.026
ival+0.026
Neg logit contributions
elope-0.039
 Chick-0.038
bing-0.038
cel-0.038
isa-0.037
Token prevented
Token ID13351
Feature activation-1.24e+00

Pos logit contributions
 gol+0.051
aden+0.043
arl+0.042
David+0.042
aw+0.041
Neg logit contributions
 sn-0.017
isa-0.017
elope-0.017
 Sn-0.016
 pap-0.016
Token Laura
Token ID16753
Feature activation-5.56e+00

Pos logit contributions
cel+0.033
isa+0.033
 Sn+0.033
 pap+0.033
elope+0.033
Neg logit contributions
 gol-0.054
aw-0.044
aden-0.043
David-0.043
 cheated-0.042
Token and
Token ID290
Feature activation-1.69e+00

Pos logit contributions
cel+0.124
isa+0.124
 Sn+0.120
elope+0.119
 pap+0.119
Neg logit contributions
 gol-0.266
aw-0.219
aden-0.216
David-0.214
 cheated-0.212
Token Alice
Token ID14862
Feature activation-2.31e+00

Pos logit contributions
 pap+0.039
isa+0.039
elope+0.039
 Sn+0.038
 sn+0.037
Neg logit contributions
 gol-0.082
aden-0.067
aw-0.067
David-0.066
ival-0.063
Token from
Token ID422
Feature activation+2.35e-01

Pos logit contributions
cel+0.055
isa+0.055
 Sn+0.054
elope+0.053
 pap+0.053
Neg logit contributions
 gol-0.106
aw-0.088
aden-0.086
David-0.086
 cheated-0.085
Token having
Token ID1719
Feature activation-1.57e+00

Pos logit contributions
 gol+0.012
aden+0.010
aw+0.010
David+0.010
ival+0.010
Neg logit contributions
isa-0.004
 Sn-0.004
elope-0.004
 pap-0.004
bing-0.004
Token an
Token ID281
Feature activation-5.51e-01

Pos logit contributions
 Sn+0.035
 sn+0.035
 pap+0.034
elope+0.034
 Pr+0.033
Neg logit contributions
 gol-0.080
aden-0.064
arl-0.063
aw-0.062
David-0.062
Token.
Token ID13
Feature activation+4.67e-01

Pos logit contributions
 Sn+0.011
cel+0.011
elope+0.010
mary+0.010
bing+0.010
Neg logit contributions
 gol-0.045
David-0.039
aden-0.038
aw-0.037
ival-0.037
Token Lily
Token ID20037
Feature activation+5.18e-01

Pos logit contributions
 gol+0.012
aw+0.010
 Tommy+0.010
 cheated+0.009
Tom+0.009
Neg logit contributions
isa-0.020
we-0.019
bing-0.019
elope-0.018
cel-0.018
Token wanted
Token ID2227
Feature activation+2.51e+00

Pos logit contributions
 gol+0.017
 cheated+0.014
aw+0.014
 happened+0.013
Tom+0.012
Neg logit contributions
bing-0.019
isa-0.019
 Sn-0.019
cel-0.019
 Moon-0.018
Token to
Token ID284
Feature activation-7.50e-01

Pos logit contributions
 gol+0.075
 Tommy+0.066
 cheated+0.060
 chalk+0.060
 happened+0.058
Neg logit contributions
bing-0.098
elope-0.096
isa-0.096
cel-0.093
we-0.089
Token prevent
Token ID2948
Feature activation-2.36e+00

Pos logit contributions
isa+0.020
elope+0.018
bing+0.018
cel+0.018
we+0.017
Neg logit contributions
 gol-0.036
aden-0.028
 cheated-0.028
 chalk-0.028
David-0.028
Token Fl
Token ID1610
Feature activation-5.55e+00

Pos logit contributions
cel+0.064
isa+0.064
elope+0.062
 roast+0.059
 pap+0.059
Neg logit contributions
 gol-0.101
aw-0.085
 cheated-0.082
 Tommy-0.081
aden-0.081
Tokenuffy
Token ID15352
Feature activation-5.34e+00

Pos logit contributions
 pap+0.221
cel+0.218
 Moon+0.216
 Pr+0.214
isa+0.214
Neg logit contributions
 gol-0.161
aw-0.125
arl-0.120
he-0.111
ane-0.111
Token from
Token ID422
Feature activation-1.45e+00

Pos logit contributions
isa+0.127
cel+0.122
elope+0.122
 pap+0.121
 Sn+0.116
Neg logit contributions
 gol-0.255
aw-0.207
aden-0.205
 cheated-0.202
David-0.198
Token getting
Token ID1972
Feature activation-2.52e+00

Pos logit contributions
isa+0.032
elope+0.032
cel+0.032
 Sn+0.030
 pap+0.030
Neg logit contributions
 gol-0.072
aden-0.058
David-0.057
aw-0.057
 cheated-0.057
Token hurt
Token ID5938
Feature activation-1.30e+00

Pos logit contributions
 Sn+0.062
 pap+0.061
 Pr+0.060
cel+0.060
bing+0.059
Neg logit contributions
 gol-0.118
aw-0.096
David-0.096
aden-0.095
ival-0.092
Token.
Token ID13
Feature activation+2.59e-01

Pos logit contributions
 Sn+0.024
isa+0.024
cel+0.024
elope+0.024
 pap+0.024
Neg logit contributions
 gol-0.068
aw-0.057
aden-0.056
David-0.056
 cheated-0.054
Token.
Token ID13
Feature activation-1.52e-01

Pos logit contributions
isa+0.014
cel+0.014
 Sn+0.013
elope+0.013
 pap+0.013
Neg logit contributions
 gol-0.034
aw-0.028
aden-0.028
David-0.028
 cheated-0.027
Token The
Token ID383
Feature activation-8.32e-01

Pos logit contributions
bing+0.005
we+0.005
cel+0.005
isa+0.005
 roast+0.005
Neg logit contributions
 gol-0.005
aw-0.004
 Tommy-0.004
ax-0.004
aden-0.004
Token cat
Token ID3797
Feature activation-1.43e+00

Pos logit contributions
isa+0.024
cel+0.024
bing+0.023
 Sn+0.023
elope+0.023
Neg logit contributions
 gol-0.035
aw-0.028
aden-0.027
David-0.027
 cheated-0.026
Token waved
Token ID26834
Feature activation-4.06e-01

Pos logit contributions
cel+0.039
bing+0.038
 Sn+0.038
isa+0.038
 pap+0.037
Neg logit contributions
 gol-0.060
aw-0.051
 cheated-0.048
aden-0.048
David-0.047
Token at
Token ID379
Feature activation-3.20e-01

Pos logit contributions
 Sn+0.010
 pap+0.010
 Pr+0.010
 sn+0.009
isa+0.009
Neg logit contributions
 gol-0.019
David-0.016
aden-0.016
ival-0.015
aw-0.015
Token Honey
Token ID21788
Feature activation-5.54e+00

Pos logit contributions
cel+0.008
elope+0.007
isa+0.007
 roast+0.007
bing+0.007
Neg logit contributions
 gol-0.014
aw-0.012
 Tommy-0.011
aden-0.011
David-0.011
Token and
Token ID290
Feature activation+1.07e-01

Pos logit contributions
cel+0.166
isa+0.153
 Sn+0.152
 eyel+0.150
elope+0.148
Neg logit contributions
 gol-0.210
aw-0.178
ax-0.162
aden-0.161
 cheated-0.156
Token said
Token ID531
Feature activation-3.61e-01

Pos logit contributions
 gol+0.004
aw+0.004
 cheated+0.003
 happened+0.003
David+0.003
Neg logit contributions
cel-0.003
isa-0.003
bing-0.003
we-0.003
elope-0.003
Token "
Token ID366
Feature activation-7.98e-01

Pos logit contributions
 Sn+0.008
isa+0.008
cel+0.008
 pap+0.008
elope+0.008
Neg logit contributions
 gol-0.018
aden-0.015
aw-0.014
David-0.014
 cheated-0.014
TokenHi
Token ID17250
Feature activation-5.84e-02

Pos logit contributions
isa+0.025
cel+0.025
 Sn+0.025
elope+0.025
 pap+0.025
Neg logit contributions
 gol-0.032
aw-0.025
aden-0.024
David-0.024
 cheated-0.023
Token!
Token ID0
Feature activation-8.73e-01

Pos logit contributions
isa+0.002
elope+0.002
 roast+0.002
cel+0.001
bing+0.001
Neg logit contributions
 gol-0.002
aw-0.002
ax-0.002
 Tommy-0.002
ival-0.002
Token.
Token ID13
Feature activation+5.84e-02

Pos logit contributions
isa+0.034
cel+0.034
 Sn+0.033
elope+0.033
 pap+0.033
Neg logit contributions
 gol-0.091
aw-0.075
aden-0.075
David-0.074
 cheated-0.072
Token
Token ID198
Feature activation-1.78e-01

Pos logit contributions
 gol+0.003
aw+0.002
aden+0.002
 cheated+0.002
ival+0.002
Neg logit contributions
 Sn-0.001
 Pr-0.001
 Chick-0.001
 pap-0.001
 Ana-0.001
Token
Token ID198
Feature activation-5.87e-01

Pos logit contributions
elope+0.004
 Sn+0.003
 Pr+0.003
isa+0.003
 Chick+0.003
Neg logit contributions
 gol-0.010
 cheated-0.008
aden-0.008
aw-0.008
 tant-0.007
TokenThey
Token ID2990
Feature activation-8.55e-01

Pos logit contributions
isa+0.012
 Sn+0.012
elope+0.012
 Pr+0.011
bing+0.011
Neg logit contributions
 gol-0.030
aden-0.025
aw-0.024
 cheated-0.024
 happened-0.024
Token ask
Token ID1265
Feature activation-1.09e+00

Pos logit contributions
isa+0.017
 sn+0.017
 pap+0.017
cel+0.017
 Sn+0.017
Neg logit contributions
 gol-0.044
David-0.037
aden-0.036
aw-0.036
ival-0.035
Token Mama
Token ID40084
Feature activation-5.46e+00

Pos logit contributions
cel+0.030
isa+0.030
elope+0.030
 Sn+0.030
 pap+0.029
Neg logit contributions
 gol-0.047
aw-0.038
aden-0.038
David-0.037
 cheated-0.036
Token if
Token ID611
Feature activation-8.04e-01

Pos logit contributions
isa+0.119
 Sn+0.118
cel+0.117
 pap+0.117
elope+0.117
Neg logit contributions
 gol-0.270
aw-0.221
aden-0.219
David-0.219
 cheated-0.212
Token they
Token ID484
Feature activation-2.29e-01

Pos logit contributions
isa+0.018
cel+0.018
 Sn+0.018
elope+0.018
 pap+0.018
Neg logit contributions
 gol-0.038
aw-0.031
aden-0.031
David-0.031
 cheated-0.030
Token can
Token ID460
Feature activation+1.45e+00

Pos logit contributions
isa+0.007
 pap+0.007
 sn+0.006
 Sn+0.006
 roast+0.006
Neg logit contributions
 gol-0.010
David-0.008
aden-0.008
aw-0.008
ival-0.007
Token bake
Token ID28450
Feature activation-2.74e+00

Pos logit contributions
 gol+0.064
he+0.052
aden+0.051
 cheated+0.051
David+0.051
Neg logit contributions
elope-0.038
isa-0.037
cel-0.037
 pap-0.035
bing-0.035
Token it
Token ID340
Feature activation-8.57e-02

Pos logit contributions
isa+0.063
elope+0.063
cel+0.063
 Sn+0.062
 pap+0.062
Neg logit contributions
 gol-0.130
aw-0.107
aden-0.105
David-0.105
 cheated-0.102
Token there
Token ID612
Feature activation+1.08e+00

Pos logit contributions
 Pr+0.013
 Ana+0.013
elope+0.013
isa+0.013
 Sn+0.013
Neg logit contributions
 gol-0.021
aw-0.018
David-0.016
aden-0.016
ival-0.016
Token was
Token ID373
Feature activation+4.50e-01

Pos logit contributions
 gol+0.068
arl+0.059
aw+0.058
David+0.057
aden+0.057
Neg logit contributions
 Sn-0.012
elope-0.012
 sn-0.010
 Ana-0.009
 M-0.009
Token a
Token ID257
Feature activation-9.56e-01

Pos logit contributions
 gol+0.026
aden+0.022
David+0.022
ival+0.022
arl+0.022
Neg logit contributions
 sn-0.006
elope-0.006
 Chick-0.006
 Sn-0.006
 roast-0.006
Token girl
Token ID2576
Feature activation-1.74e+00

Pos logit contributions
isa+0.028
 Sn+0.028
cel+0.028
elope+0.028
 pap+0.028
Neg logit contributions
 gol-0.040
aw-0.031
aden-0.031
David-0.031
 cheated-0.030
Token called
Token ID1444
Feature activation+6.96e-01

Pos logit contributions
 hips+0.067
bing+0.066
balls+0.065
 Sn+0.065
 forehead+0.064
Neg logit contributions
 gol-0.052
aw-0.046
 chalk-0.038
Tom-0.036
car-0.035
Token Moon
Token ID6869
Feature activation-5.46e+00

Pos logit contributions
 gol+0.026
aw+0.020
David+0.020
aden+0.020
 Tommy+0.019
Neg logit contributions
bing-0.023
isa-0.022
cel-0.022
 pap-0.022
elope-0.021
Token.
Token ID13
Feature activation+4.20e-01

Pos logit contributions
cel+0.157
bing+0.152
 Sn+0.148
 convince+0.145
 eyel+0.143
Neg logit contributions
 gol-0.202
aw-0.186
aden-0.165
ax-0.165
ane-0.162
Token She
Token ID1375
Feature activation-7.56e-01

Pos logit contributions
he+0.009
aw+0.009
 happened+0.009
 See+0.009
ane+0.008
Neg logit contributions
bing-0.017
 convince-0.016
we-0.016
ci-0.015
bes-0.015
Token was
Token ID373
Feature activation+2.54e-01

Pos logit contributions
bing+0.027
 pap+0.026
isa+0.026
 Sn+0.026
 Pr+0.026
Neg logit contributions
 gol-0.026
aw-0.021
 happened-0.020
 cheated-0.020
David-0.019
Token three
Token ID1115
Feature activation-1.56e+00

Pos logit contributions
 gol+0.011
aw+0.008
 cheated+0.008
aden+0.008
David+0.008
Neg logit contributions
cel-0.007
isa-0.007
bing-0.007
elope-0.007
we-0.007
Token years
Token ID812
Feature activation-6.07e-02

Pos logit contributions
 Sn+0.042
 roast+0.041
cup+0.039
 Stacy+0.039
cel+0.039
Neg logit contributions
aw-0.067
 gol-0.060
aden-0.053
 tant-0.053
 trophies-0.051
TokenWe
Token ID1135
Feature activation+3.37e-01

Pos logit contributions
 gol+0.001
aden+0.001
aw+0.001
ival+0.001
David+0.001
Neg logit contributions
 Sn-0.000
isa-0.000
elope-0.000
we-0.000
mary-0.000
Token're
Token ID821
Feature activation-2.14e+00

Pos logit contributions
 gol+0.015
David+0.014
aw+0.013
ival+0.013
aden+0.012
Neg logit contributions
 sn-0.008
 roast-0.008
 Sn-0.008
 bit-0.008
cel-0.008
Token going
Token ID1016
Feature activation-9.67e-01

Pos logit contributions
 Sn+0.050
 pap+0.048
cel+0.048
isa+0.048
elope+0.048
Neg logit contributions
 gol-0.103
aw-0.085
David-0.084
aden-0.084
ival-0.081
Token to
Token ID284
Feature activation-2.44e+00

Pos logit contributions
 Sn+0.020
cel+0.020
 pap+0.019
isa+0.019
bing+0.019
Neg logit contributions
 gol-0.048
aw-0.040
aden-0.040
David-0.040
 cheated-0.038
Token see
Token ID766
Feature activation-6.30e-01

Pos logit contributions
 Sn+0.048
 roast+0.047
 sn+0.045
 pap+0.045
 Moon+0.043
Neg logit contributions
 gol-0.127
aw-0.115
ival-0.108
aden-0.108
David-0.108
Token Sun
Token ID3825
Feature activation-5.46e+00

Pos logit contributions
 Sn+0.014
isa+0.013
 Moon+0.013
 pap+0.013
 Pr+0.013
Neg logit contributions
 gol-0.033
David-0.026
aden-0.026
 cheated-0.025
aw-0.025
Tokenflower
Token ID25547
Feature activation-3.60e+00

Pos logit contributions
cel+0.133
 pap+0.126
 Sn+0.126
 eyel+0.124
isa+0.123
Neg logit contributions
 gol-0.235
aw-0.203
aden-0.190
ane-0.190
he-0.187
Token,"
Token ID553
Feature activation+1.07e+00

Pos logit contributions
isa+0.078
elope+0.077
 Sn+0.077
cel+0.076
 pap+0.076
Neg logit contributions
 gol-0.179
David-0.147
aden-0.146
aw-0.144
 cheated-0.140
Token he
Token ID339
Feature activation+2.89e+00

Pos logit contributions
 gol+0.044
aw+0.035
David+0.034
aden+0.034
 cheated+0.033
Neg logit contributions
cel-0.032
bing-0.031
isa-0.031
 Sn-0.031
elope-0.030
Token said
Token ID531
Feature activation+1.37e+00

Pos logit contributions
 gol+0.098
aw+0.078
David+0.075
aden+0.074
 cheated+0.074
Neg logit contributions
cel-0.103
bing-0.102
 Sn-0.101
isa-0.100
elope-0.098
Token.
Token ID13
Feature activation+3.05e-01

Pos logit contributions
 gol+0.061
 cheated+0.049
aw+0.049
aden+0.048
David+0.048
Neg logit contributions
isa-0.034
cel-0.034
elope-0.033
 Sn-0.032
 pap-0.032
Token was
Token ID373
Feature activation+1.24e-01

Pos logit contributions
cel+0.044
 Sn+0.044
isa+0.044
bing+0.044
 pap+0.042
Neg logit contributions
 gol-0.074
aw-0.061
aden-0.058
David-0.058
 cheated-0.058
Token excited
Token ID6568
Feature activation-1.33e+00

Pos logit contributions
 gol+0.006
aw+0.005
aden+0.005
David+0.005
ival+0.005
Neg logit contributions
 Sn-0.003
isa-0.003
elope-0.003
cel-0.003
 pap-0.003
Token and
Token ID290
Feature activation-2.94e-01

Pos logit contributions
isa+0.028
 Sn+0.028
cel+0.027
elope+0.027
 pap+0.027
Neg logit contributions
 gol-0.067
aw-0.055
aden-0.054
David-0.054
 cheated-0.053
Token asked
Token ID1965
Feature activation-5.12e-01

Pos logit contributions
 pap+0.008
 Sn+0.008
elope+0.007
isa+0.007
 Pr+0.007
Neg logit contributions
 gol-0.013
aden-0.011
aw-0.011
David-0.011
ival-0.010
Token the
Token ID262
Feature activation-5.62e-01

Pos logit contributions
 Sn+0.011
 Pr+0.011
 pap+0.011
 sn+0.010
 Chick+0.010
Neg logit contributions
 gol-0.027
aw-0.022
David-0.022
aden-0.022
 cheated-0.021
Token chick
Token ID17943
Feature activation-5.43e+00

Pos logit contributions
cel+0.018
bing+0.017
isa+0.016
we+0.016
bes+0.016
Neg logit contributions
 gol-0.019
 thief-0.016
Here-0.016
aw-0.015
 trouble-0.015
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
cel+0.129
isa+0.129
 Sn+0.128
elope+0.126
bing+0.124
Neg logit contributions
 gol-0.253
aw-0.207
aden-0.205
David-0.204
 cheated-0.198
Token �
Token ID6184
Feature activation-1.53e+00

Pos logit contributions
 gol+0.009
aw+0.007
aden+0.007
David+0.007
 cheated+0.007
Neg logit contributions
isa-0.004
cel-0.004
 Sn-0.004
elope-0.004
 pap-0.004
Token�
Token ID95
Feature activation-1.81e+00

Pos logit contributions
 knees+0.037
isa+0.037
sey+0.036
we+0.036
fl+0.035
Neg logit contributions
 gol-0.067
aw-0.060
ival-0.050
arl-0.049
David-0.047
Token€
Token ID26391
Feature activation-2.35e+00

Pos logit contributions
 knees+0.059
 Ana+0.051
 pap+0.050
 eyel+0.048
 Sn+0.048
Neg logit contributions
 gol-0.066
aw-0.063
David-0.053
Here-0.052
Tom-0.048
Token�
Token ID129
Feature activation-5.14e-01

Pos logit contributions
 Sn+0.064
isa+0.063
bing+0.061
 eyel+0.061
 pap+0.060
Neg logit contributions
 gol-0.098
aw-0.086
David-0.084
ival-0.078
 cheated-0.078
Token I
Token ID314
Feature activation+1.30e+00

Pos logit contributions
isa+0.028
bing+0.027
elope+0.027
 pap+0.026
we+0.026
Neg logit contributions
 gol-0.031
aw-0.024
aden-0.024
 cheated-0.023
David-0.023
Token want
Token ID765
Feature activation+2.00e+00

Pos logit contributions
 gol+0.053
David+0.043
aw+0.043
aden+0.042
ival+0.040
Neg logit contributions
cel-0.039
elope-0.039
 Sn-0.038
isa-0.038
 sn-0.038
Token to
Token ID284
Feature activation-7.29e-01

Pos logit contributions
 gol+0.070
aw+0.055
 chalk+0.055
 cheated+0.055
 Tommy+0.055
Neg logit contributions
elope-0.071
isa-0.069
cel-0.068
bing-0.067
mary-0.061
Token prevent
Token ID2948
Feature activation-2.49e+00

Pos logit contributions
isa+0.019
elope+0.018
bing+0.017
cel+0.017
 Sn+0.017
Neg logit contributions
 gol-0.034
aden-0.027
 cheated-0.027
David-0.027
aw-0.027
Token Fl
Token ID1610
Feature activation-5.63e+00

Pos logit contributions
isa+0.071
elope+0.071
cel+0.070
 pap+0.067
mary+0.067
Neg logit contributions
 gol-0.106
aw-0.085
aden-0.083
 cheated-0.083
David-0.080
Tokenuffy
Token ID15352
Feature activation-5.42e+00

Pos logit contributions
 pap+0.225
cel+0.218
isa+0.218
 Moon+0.218
 Pr+0.216
Neg logit contributions
 gol-0.168
aw-0.129
arl-0.126
ane-0.116
he-0.114
Token from
Token ID422
Feature activation-1.54e+00

Pos logit contributions
isa+0.138
elope+0.133
 pap+0.132
cel+0.131
 Moon+0.125
Neg logit contributions
 gol-0.250
aw-0.205
 cheated-0.198
aden-0.196
he-0.193
Token getting
Token ID1972
Feature activation-2.60e+00

Pos logit contributions
isa+0.036
elope+0.036
cel+0.035
mary+0.033
 Sn+0.033
Neg logit contributions
 gol-0.074
aden-0.059
aw-0.059
 cheated-0.059
David-0.059
Token hurt
Token ID5938
Feature activation-1.52e+00

Pos logit contributions
isa+0.069
elope+0.069
cel+0.068
 Sn+0.066
 pap+0.066
Neg logit contributions
 gol-0.117
aw-0.093
aden-0.093
David-0.092
 cheated-0.090
Token."
Token ID526
Feature activation+3.46e-01

Pos logit contributions
isa+0.029
cel+0.029
elope+0.029
 pap+0.029
 Sn+0.028
Neg logit contributions
 gol-0.079
aw-0.066
aden-0.065
David-0.064
 cheated-0.064
Token Her
Token ID2332
Feature activation-1.04e+00

Pos logit contributions
 gol+0.010
 Tommy+0.009
aw+0.009
 happened+0.008
Tom+0.008
Neg logit contributions
isa-0.013
cel-0.012
bing-0.012
we-0.012
elope-0.012
Token and
Token ID290
Feature activation-1.67e+00

Pos logit contributions
 Sn+0.038
mary+0.038
 sn+0.038
 pap+0.038
bing+0.038
Neg logit contributions
 gol-0.125
aden-0.104
David-0.102
ival-0.100
 cheated-0.099
Token out
Token ID503
Feature activation+5.49e-01

Pos logit contributions
 pap+0.038
 Sn+0.037
 Pr+0.036
 sn+0.036
 Chick+0.036
Neg logit contributions
 gol-0.086
aden-0.070
aw-0.070
David-0.068
ival-0.066
Token came
Token ID1625
Feature activation+1.61e-01

Pos logit contributions
 gol+0.024
David+0.019
aden+0.019
aw+0.019
ax+0.018
Neg logit contributions
 Sn-0.015
isa-0.015
 sn-0.015
cel-0.015
elope-0.015
Token a
Token ID257
Feature activation-1.15e+00

Pos logit contributions
 gol+0.008
aw+0.006
aden+0.006
David+0.006
ival+0.006
Neg logit contributions
 Sn-0.004
elope-0.004
isa-0.004
 pap-0.004
cel-0.004
Token little
Token ID1310
Feature activation-1.61e+00

Pos logit contributions
 pap+0.030
 Sn+0.029
 sn+0.029
 Moon+0.029
elope+0.029
Neg logit contributions
 gol-0.052
aden-0.045
aw-0.045
David-0.043
ax-0.043
Token chick
Token ID17943
Feature activation-5.42e+00

Pos logit contributions
 pap+0.041
 Sn+0.041
elope+0.041
isa+0.041
cel+0.039
Neg logit contributions
 gol-0.073
David-0.060
aden-0.060
aw-0.059
 cheated-0.057
Token!
Token ID0
Feature activation+9.90e-01

Pos logit contributions
isa+0.123
 Sn+0.120
cel+0.119
 pap+0.118
elope+0.115
Neg logit contributions
 gol-0.259
aw-0.217
aden-0.206
David-0.204
 cheated-0.204
Token Pe
Token ID2631
Feature activation-4.56e-01

Pos logit contributions
 gol+0.046
aw+0.037
aden+0.037
David+0.037
 cheated+0.035
Neg logit contributions
 Sn-0.025
cel-0.024
isa-0.024
elope-0.024
 pap-0.024
Tokenep
Token ID538
Feature activation+1.87e-01

Pos logit contributions
isa+0.015
cel+0.015
elope+0.015
 Sn+0.015
 pap+0.014
Neg logit contributions
 gol-0.018
aw-0.014
aden-0.014
David-0.014
 cheated-0.013
Token was
Token ID373
Feature activation+4.70e-01

Pos logit contributions
 gol+0.009
aden+0.008
David+0.007
aw+0.007
ival+0.007
Neg logit contributions
elope-0.004
isa-0.004
 Sn-0.004
bing-0.004
cel-0.004
Token so
Token ID523
Feature activation-6.78e-02

Pos logit contributions
 gol+0.022
aw+0.018
aden+0.018
David+0.018
 cheated+0.018
Neg logit contributions
isa-0.011
cel-0.011
 Sn-0.011
elope-0.011
bing-0.010
Token there
Token ID612
Feature activation+7.20e-01

Pos logit contributions
 gol+0.043
aw+0.037
aden+0.037
David+0.036
ival+0.035
Neg logit contributions
 Sn-0.010
elope-0.010
 pap-0.009
 Pr-0.009
 Ana-0.009
Token was
Token ID373
Feature activation+2.51e-01

Pos logit contributions
 gol+0.046
arl+0.040
David+0.039
aden+0.039
aw+0.039
Neg logit contributions
elope-0.007
 Sn-0.007
 sn-0.007
 Ana-0.006
isa-0.006
Token a
Token ID257
Feature activation-1.03e+00

Pos logit contributions
 gol+0.014
aden+0.012
ival+0.012
David+0.011
 cheated+0.011
Neg logit contributions
 Sn-0.004
elope-0.004
 Chick-0.004
 sn-0.004
 Pr-0.004
Token girl
Token ID2576
Feature activation-1.71e+00

Pos logit contributions
isa+0.031
cel+0.031
elope+0.031
 Sn+0.031
bing+0.030
Neg logit contributions
 gol-0.042
aw-0.032
David-0.032
aden-0.032
 cheated-0.031
Token called
Token ID1444
Feature activation+6.12e-01

Pos logit contributions
 hips+0.067
iously+0.065
 Sn+0.065
bing+0.065
 Misty+0.065
Neg logit contributions
 gol-0.050
aw-0.043
 chalk-0.037
Tom-0.034
car-0.034
Token Honey
Token ID21788
Feature activation-5.40e+00

Pos logit contributions
 gol+0.025
aw+0.019
David+0.019
aden+0.019
 cheated+0.018
Neg logit contributions
bing-0.019
isa-0.018
cel-0.018
 pap-0.018
elope-0.018
Token who
Token ID508
Feature activation+1.00e+00

Pos logit contributions
cel+0.178
 breaths+0.176
 hips+0.175
 eyel+0.172
 convince+0.171
Neg logit contributions
 gol-0.162
aw-0.138
he-0.124
ax-0.122
 happened-0.121
Token lived
Token ID5615
Feature activation+8.82e-01

Pos logit contributions
 gol+0.036
aw+0.029
 cheated+0.028
 happened+0.027
aden+0.027
Neg logit contributions
bing-0.034
cel-0.033
isa-0.033
 pap-0.033
 Sn-0.032
Token in
Token ID287
Feature activation-6.33e-01

Pos logit contributions
 gol+0.041
aw+0.034
David+0.033
aden+0.032
 cheated+0.032
Neg logit contributions
cel-0.022
isa-0.021
elope-0.021
 pap-0.021
 Sn-0.020
Token a
Token ID257
Feature activation+3.06e-01

Pos logit contributions
bing+0.022
cel+0.021
isa+0.021
mary+0.021
cup+0.020
Neg logit contributions
 gol-0.022
David-0.017
 Tommy-0.017
aw-0.017
 chalk-0.016
Token small
Token ID1402
Feature activation+2.13e-01

Pos logit contributions
 gol+0.014
aden+0.011
David+0.011
aw+0.011
 cheated+0.011
Neg logit contributions
 Sn-0.008
elope-0.008
 pap-0.008
isa-0.008
cel-0.008
Token
Token ID220
Feature activation-1.03e+00

Pos logit contributions
 gol+0.010
 Tommy+0.008
 chalk+0.007
aden+0.007
arl+0.007
Neg logit contributions
bing-0.016
isa-0.016
elope-0.015
we-0.015
 pap-0.014
Token
Token ID198
Feature activation+5.72e-01

Pos logit contributions
 Sn+0.023
elope+0.022
 Pr+0.022
 Chick+0.022
cel+0.021
Neg logit contributions
 gol-0.053
aw-0.042
aden-0.041
David-0.041
ival-0.040
Token
Token ID198
Feature activation+7.68e-02

Pos logit contributions
 gol+0.020
David+0.015
aden+0.015
aw+0.015
he+0.014
Neg logit contributions
 pap-0.020
bing-0.020
isa-0.020
cel-0.020
elope-0.020
Token"
Token ID1
Feature activation-1.64e+00

Pos logit contributions
 gol+0.002
Tom+0.002
he+0.001
David+0.001
aw+0.001
Neg logit contributions
 knees-0.003
 pap-0.003
isa-0.003
elope-0.003
bing-0.003
TokenHi
Token ID17250
Feature activation+4.22e-02

Pos logit contributions
isa+0.059
elope+0.058
cel+0.058
 pap+0.058
 Sn+0.057
Neg logit contributions
 gol-0.059
David-0.043
aw-0.043
aden-0.043
 cheated-0.041
Token Sp
Token ID1338
Feature activation-5.39e+00

Pos logit contributions
 gol+0.002
aw+0.001
aden+0.001
 cheated+0.001
 Tommy+0.001
Neg logit contributions
elope-0.001
isa-0.001
cel-0.001
mary-0.001
bing-0.001
Tokenud
Token ID463
Feature activation-1.11e+00

Pos logit contributions
 pap+0.196
 Pr+0.191
elope+0.189
 Sn+0.187
cel+0.187
Neg logit contributions
 gol-0.188
aw-0.147
aden-0.140
David-0.138
he-0.137
Token!"
Token ID2474
Feature activation+9.08e-01

Pos logit contributions
 pap+0.029
elope+0.029
cel+0.029
isa+0.029
 Sn+0.029
Neg logit contributions
 gol-0.048
aw-0.038
 cheated-0.037
aden-0.036
David-0.036
Token said
Token ID531
Feature activation+1.30e+00

Pos logit contributions
 gol+0.024
aw+0.017
 cheated+0.017
 chalk+0.016
 happened+0.016
Neg logit contributions
bing-0.040
isa-0.038
elope-0.038
cel-0.038
we-0.036
Token Lily
Token ID20037
Feature activation+6.32e-01

Pos logit contributions
 gol+0.041
 Tommy+0.028
 chalk+0.027
 cheated+0.027
 happened+0.026
Neg logit contributions
bing-0.052
cel-0.051
elope-0.051
isa-0.050
we-0.049
Token.
Token ID13
Feature activation+5.29e-01

Pos logit contributions
 gol+0.024
 cheated+0.018
aw+0.018
ax+0.017
 Tommy+0.017
Neg logit contributions
 roast-0.020
isa-0.020
cel-0.019
 carniv-0.019
 pap-0.019
Token is
Token ID318
Feature activation+7.16e-01

Pos logit contributions
 gol+0.034
 cheated+0.028
aw+0.028
aden+0.027
 happened+0.027
Neg logit contributions
isa-0.023
 Sn-0.022
bing-0.022
cel-0.022
elope-0.022
Token".
Token ID1911
Feature activation+4.31e-01

Pos logit contributions
 gol+0.034
aw+0.027
aden+0.027
 cheated+0.027
David+0.027
Neg logit contributions
isa-0.017
cel-0.017
elope-0.016
 Sn-0.016
bing-0.016
Token
Token ID198
Feature activation+8.97e-01

Pos logit contributions
 gol+0.014
aw+0.012
 cheated+0.011
ival+0.011
he+0.010
Neg logit contributions
cel-0.014
bing-0.014
 Sn-0.014
isa-0.014
 knees-0.013
Token
Token ID198
Feature activation+2.99e-01

Pos logit contributions
 gol+0.033
aw+0.026
David+0.026
ival+0.025
aden+0.025
Neg logit contributions
cel-0.030
 Sn-0.030
 pap-0.029
isa-0.029
bing-0.029
TokenThe
Token ID464
Feature activation-6.18e-01

Pos logit contributions
 gol+0.011
aw+0.009
David+0.009
ival+0.009
Tom+0.008
Neg logit contributions
cel-0.010
 Sn-0.010
 knees-0.010
 eyel-0.009
 hips-0.009
Token other
Token ID584
Feature activation+3.64e+00

Pos logit contributions
 Sn+0.018
bing+0.018
cel+0.018
 Chick+0.017
bed+0.017
Neg logit contributions
 gol-0.024
aw-0.020
 cheated-0.019
ival-0.019
 liar-0.019
Token bees
Token ID17002
Feature activation-1.53e+00

Pos logit contributions
aw+0.145
 gol+0.135
 happened+0.119
ival+0.110
ax+0.108
Neg logit contributions
 Sn-0.105
cel-0.104
bing-0.101
 hips-0.096
 Chick-0.094
Token offered
Token ID4438
Feature activation-6.27e-01

Pos logit contributions
elope+0.040
isa+0.039
cel+0.038
 pap+0.038
bing+0.038
Neg logit contributions
 gol-0.069
aden-0.056
David-0.056
aw-0.054
 cheated-0.052
Token the
Token ID262
Feature activation-8.53e-01

Pos logit contributions
cel+0.018
 Sn+0.017
bing+0.016
isa+0.016
elope+0.016
Neg logit contributions
 gol-0.026
aw-0.022
David-0.021
aden-0.021
 cheated-0.020
Token tired
Token ID10032
Feature activation-7.91e-01

Pos logit contributions
bing+0.024
 Sn+0.023
cel+0.023
 Chick+0.022
bed+0.021
Neg logit contributions
 gol-0.036
aw-0.030
 cheated-0.028
ival-0.028
 happened-0.028
Token bee
Token ID20697
Feature activation-3.50e+00

Pos logit contributions
cel+0.024
 Sn+0.023
bing+0.022
elope+0.022
isa+0.021
Neg logit contributions
 gol-0.033
aw-0.028
ax-0.025
aden-0.025
David-0.025
Token just
Token ID655
Feature activation+2.05e-01

Pos logit contributions
 pap+0.023
 Sn+0.023
 sn+0.023
 Pr+0.022
bing+0.022
Neg logit contributions
 gol-0.043
aden-0.036
David-0.036
aw-0.035
ival-0.034
Token as
Token ID355
Feature activation-1.34e-01

Pos logit contributions
 gol+0.010
David+0.009
aden+0.009
ival+0.009
aw+0.008
Neg logit contributions
 sn-0.004
 Pr-0.004
 pap-0.004
 following-0.004
cel-0.004
Token cheerful
Token ID37999
Feature activation+6.79e-01

Pos logit contributions
 pap+0.003
 Pr+0.002
 sn+0.002
 Chick+0.002
 soon+0.002
Neg logit contributions
 gol-0.007
aden-0.006
David-0.006
aw-0.006
ival-0.006
Token in
Token ID287
Feature activation+4.53e-01

Pos logit contributions
 gol+0.039
David+0.033
aden+0.033
aw+0.033
ival+0.032
Neg logit contributions
 Sn-0.009
cel-0.009
bing-0.009
 pap-0.009
isa-0.009
Token her
Token ID607
Feature activation+1.02e+00

Pos logit contributions
 gol+0.022
aw+0.018
aden+0.018
David+0.018
ival+0.018
Neg logit contributions
 Sn-0.010
 pap-0.010
isa-0.010
elope-0.010
bing-0.010
Token new
Token ID649
Feature activation+3.79e+00

Pos logit contributions
 gol+0.048
David+0.041
aden+0.040
aw+0.039
ax+0.039
Neg logit contributions
 pap-0.025
elope-0.025
cel-0.024
 Sn-0.023
isa-0.023
Token uniform
Token ID8187
Feature activation+3.29e+00

Pos logit contributions
 gol+0.175
David+0.145
aden+0.145
aw+0.144
ival+0.140
Neg logit contributions
elope-0.093
 pap-0.092
isa-0.091
 Sn-0.091
cel-0.089
Token.
Token ID13
Feature activation+4.40e-01

Pos logit contributions
 gol+0.195
David+0.168
aden+0.163
aw+0.157
ax+0.156
Neg logit contributions
 Sn-0.045
cel-0.042
cup-0.040
 sn-0.039
elope-0.039
Token From
Token ID3574
Feature activation-3.62e-01

Pos logit contributions
 gol+0.021
aden+0.017
David+0.017
aw+0.017
 cheated+0.017
Neg logit contributions
 Sn-0.011
elope-0.010
 Pr-0.010
 Chick-0.010
cel-0.010
Token that
Token ID326
Feature activation-9.97e-01

Pos logit contributions
bing+0.006
 pap+0.006
isa+0.006
 Sn+0.006
elope+0.006
Neg logit contributions
 gol-0.020
aden-0.017
David-0.016
 cheated-0.016
aw-0.016
Token day
Token ID1110
Feature activation-8.75e-01

Pos logit contributions
cel+0.036
isa+0.035
elope+0.035
mary+0.035
 Sn+0.035
Neg logit contributions
 gol-0.036
David-0.025
he-0.025
aden-0.025
 happened-0.024
Token
Token ID198
Feature activation+1.27e+00

Pos logit contributions
 gol+0.018
aden+0.014
David+0.014
aw+0.014
ival+0.014
Neg logit contributions
 Sn-0.009
 pap-0.009
 Pr-0.009
elope-0.009
mary-0.009
Token
Token ID198
Feature activation+6.71e-01

Pos logit contributions
 gol+0.060
aden+0.048
aw+0.048
David+0.047
 cheated+0.047
Neg logit contributions
 Sn-0.031
elope-0.030
 pap-0.030
 Pr-0.030
isa-0.029
TokenThey
Token ID2990
Feature activation-6.30e-01

Pos logit contributions
 gol+0.028
aw+0.022
David+0.022
aden+0.022
 cheated+0.021
Neg logit contributions
cel-0.020
isa-0.020
elope-0.019
 pap-0.019
 Sn-0.019
Token hugged
Token ID41130
Feature activation+3.89e-01

Pos logit contributions
 Sn+0.016
cel+0.016
isa+0.016
 pap+0.016
elope+0.015
Neg logit contributions
 gol-0.029
aw-0.023
aden-0.023
David-0.023
 cheated-0.022
Token each
Token ID1123
Feature activation+7.03e-01

Pos logit contributions
 gol+0.016
aw+0.014
aden+0.013
David+0.012
 tant+0.012
Neg logit contributions
cel-0.011
isa-0.011
elope-0.011
 pap-0.011
bing-0.011
Token other
Token ID584
Feature activation+3.91e+00

Pos logit contributions
 gol+0.027
aw+0.022
aden+0.022
David+0.021
 cheated+0.020
Neg logit contributions
cel-0.022
elope-0.022
 Sn-0.022
isa-0.022
bing-0.022
Token and
Token ID290
Feature activation-2.05e-01

Pos logit contributions
 gol+0.157
aw+0.133
aden+0.123
 cheated+0.121
ival+0.119
Neg logit contributions
isa-0.117
cel-0.117
elope-0.113
 pap-0.112
 Chick-0.110
Token said
Token ID531
Feature activation-2.21e-01

Pos logit contributions
isa+0.006
cel+0.006
 Sn+0.006
elope+0.006
 pap+0.006
Neg logit contributions
 gol-0.009
aw-0.007
aden-0.007
David-0.007
 cheated-0.006
Token,
Token ID11
Feature activation-2.00e-01

Pos logit contributions
 Sn+0.004
 pap+0.004
cel+0.004
 Pr+0.004
bing+0.004
Neg logit contributions
 gol-0.012
aden-0.010
David-0.010
aw-0.010
ax-0.009
Token "
Token ID366
Feature activation-1.04e+00

Pos logit contributions
isa+0.006
elope+0.006
 pap+0.005
cel+0.005
bing+0.005
Neg logit contributions
 gol-0.008
David-0.006
aw-0.006
 cheated-0.006
arl-0.006
TokenWe
Token ID1135
Feature activation-3.04e-01

Pos logit contributions
cel+0.032
isa+0.032
 pap+0.032
elope+0.032
 Sn+0.031
Neg logit contributions
 gol-0.043
aw-0.034
David-0.033
aden-0.032
 cheated-0.032
TokenThey
Token ID2990
Feature activation-7.09e-01

Pos logit contributions
 gol+0.001
aw+0.001
David+0.001
Tom+0.001
ival+0.001
Neg logit contributions
cel-0.001
 pap-0.001
elope-0.001
 Sn-0.001
 Chick-0.001
Token smile
Token ID8212
Feature activation+6.04e-01

Pos logit contributions
 sn+0.013
 roast+0.012
 pur+0.011
isa+0.011
cel+0.011
Neg logit contributions
 gol-0.038
David-0.033
aw-0.032
ival-0.031
aden-0.031
Token and
Token ID290
Feature activation+6.28e-01

Pos logit contributions
 gol+0.027
aw+0.022
aden+0.021
 cheated+0.021
David+0.021
Neg logit contributions
isa-0.016
elope-0.016
cel-0.016
 Sn-0.016
 pap-0.016
Token admire
Token ID21099
Feature activation-3.89e-01

Pos logit contributions
 gol+0.028
aw+0.022
aden+0.022
David+0.022
 cheated+0.021
Neg logit contributions
isa-0.017
cel-0.017
 Sn-0.017
elope-0.017
 pap-0.016
Token each
Token ID1123
Feature activation+6.61e-01

Pos logit contributions
cel+0.011
isa+0.011
elope+0.011
 Sn+0.011
 pap+0.011
Neg logit contributions
 gol-0.016
aw-0.013
aden-0.013
David-0.013
 cheated-0.012
Token other
Token ID584
Feature activation+4.28e+00

Pos logit contributions
 gol+0.023
aw+0.018
 chalk+0.018
 cheated+0.017
aden+0.017
Neg logit contributions
cel-0.024
 Sn-0.024
 pap-0.024
elope-0.023
 Chick-0.023
Token's
Token ID338
Feature activation-1.19e+00

Pos logit contributions
 gol+0.178
aw+0.157
 cheated+0.146
aden+0.144
 trophies+0.144
Neg logit contributions
cel-0.116
 pap-0.114
elope-0.112
 Chick-0.111
isa-0.110
Token drawings
Token ID23388
Feature activation+8.62e-01

Pos logit contributions
 pap+0.031
elope+0.030
cel+0.030
isa+0.030
bing+0.030
Neg logit contributions
 gol-0.055
David-0.045
aden-0.044
aw-0.044
ax-0.043
Token.
Token ID13
Feature activation-3.83e-01

Pos logit contributions
 gol+0.048
David+0.041
aden+0.040
aw+0.040
ival+0.038
Neg logit contributions
 Sn-0.013
cel-0.013
elope-0.013
isa-0.013
bing-0.013
Token They
Token ID1119
Feature activation-1.09e+00

Pos logit contributions
cel+0.012
isa+0.012
bing+0.012
elope+0.012
 pap+0.011
Neg logit contributions
 gol-0.015
aw-0.012
David-0.011
 cheated-0.011
aden-0.011
Token are
Token ID389
Feature activation-6.33e-01

Pos logit contributions
 sn+0.026
cel+0.024
 roast+0.024
 pap+0.024
 pur+0.024
Neg logit contributions
 gol-0.052
David-0.043
aw-0.043
aden-0.042
ival-0.041
Token They
Token ID1119
Feature activation-1.12e+00

Pos logit contributions
elope+0.003
 Sn+0.003
 Pr+0.003
isa+0.003
 Moon+0.003
Neg logit contributions
 gol-0.007
David-0.006
aden-0.006
 cheated-0.006
aw-0.006
Token learned
Token ID4499
Feature activation+2.02e-01

Pos logit contributions
 sn+0.026
mary+0.024
 Sn+0.024
 pap+0.024
elope+0.024
Neg logit contributions
 gol-0.053
aden-0.046
David-0.046
arl-0.045
aw-0.044
Token that
Token ID326
Feature activation-9.80e-01

Pos logit contributions
 gol+0.011
aden+0.009
David+0.009
ax+0.009
aw+0.009
Neg logit contributions
 pap-0.003
 Sn-0.003
 sn-0.003
 Pr-0.003
mary-0.003
Token helping
Token ID5742
Feature activation-7.15e-01

Pos logit contributions
isa+0.024
cel+0.024
elope+0.024
 Sn+0.024
 pap+0.024
Neg logit contributions
 gol-0.045
aw-0.037
aden-0.036
David-0.036
 cheated-0.035
Token each
Token ID1123
Feature activation+1.15e+00

Pos logit contributions
 pap+0.014
 Sn+0.014
 Pr+0.013
elope+0.013
bing+0.013
Neg logit contributions
 gol-0.037
David-0.031
aw-0.031
aden-0.031
ival-0.030
Token other
Token ID584
Feature activation+4.35e+00

Pos logit contributions
 gol+0.056
David+0.047
aw+0.047
aden+0.046
ival+0.045
Neg logit contributions
isa-0.026
 Pr-0.025
 pap-0.025
 sn-0.025
elope-0.024
Token is
Token ID318
Feature activation-5.14e-01

Pos logit contributions
 gol+0.215
David+0.180
aden+0.175
ax+0.170
aw+0.167
Neg logit contributions
 sn-0.097
elope-0.096
 pap-0.096
 Sn-0.095
 Pr-0.093
Token very
Token ID845
Feature activation+2.69e-02

Pos logit contributions
isa+0.014
cel+0.014
 Sn+0.014
elope+0.014
 pap+0.014
Neg logit contributions
 gol-0.023
aw-0.018
aden-0.018
David-0.018
 cheated-0.017
Token important
Token ID1593
Feature activation+6.75e-01

Pos logit contributions
 gol+0.001
aw+0.001
aden+0.001
David+0.001
ival+0.001
Neg logit contributions
 Sn-0.001
 pap-0.001
elope-0.001
isa-0.001
cel-0.001
Token.
Token ID13
Feature activation-5.33e-01

Pos logit contributions
 gol+0.034
aw+0.028
aden+0.028
David+0.028
 cheated+0.027
Neg logit contributions
isa-0.014
cel-0.014
 Sn-0.014
elope-0.014
 pap-0.014
Token The
Token ID383
Feature activation-7.51e-01

Pos logit contributions
elope+0.013
 Sn+0.013
 Pr+0.013
isa+0.012
 pap+0.012
Neg logit contributions
 gol-0.025
aden-0.021
aw-0.021
David-0.020
 cheated-0.020
Token felt
Token ID2936
Feature activation-8.93e-01

Pos logit contributions
bing+0.031
 Sn+0.031
cel+0.031
isa+0.031
elope+0.030
Neg logit contributions
 gol-0.044
aw-0.035
 cheated-0.034
David-0.034
aden-0.034
Token happy
Token ID3772
Feature activation-1.75e-02

Pos logit contributions
isa+0.027
cel+0.027
elope+0.027
 Sn+0.026
bing+0.026
Neg logit contributions
 gol-0.036
aw-0.029
 cheated-0.028
David-0.028
aden-0.028
Token and
Token ID290
Feature activation-2.77e-01

Pos logit contributions
cel+0.001
isa+0.001
 Sn+0.000
elope+0.000
 Pr+0.000
Neg logit contributions
 gol-0.001
aw-0.001
 cheated-0.001
aden-0.001
 happened-0.001
Token excited
Token ID6568
Feature activation-3.07e-01

Pos logit contributions
isa+0.011
cel+0.011
 Sn+0.010
elope+0.010
 Moon+0.010
Neg logit contributions
 gol-0.008
 cheated-0.006
 happened-0.006
aw-0.006
 chalk-0.005
Token.
Token ID13
Feature activation-4.48e-01

Pos logit contributions
cel+0.008
elope+0.008
isa+0.008
 Sn+0.008
 pap+0.007
Neg logit contributions
 gol-0.014
aw-0.012
aden-0.011
 happened-0.011
 cheated-0.011
Token
Token ID198
Feature activation+5.32e-02

Pos logit contributions
 Sn+0.012
elope+0.012
 pap+0.011
 Pr+0.011
cel+0.011
Neg logit contributions
 gol-0.020
aw-0.017
aden-0.016
David-0.016
 cheated-0.016
Token
Token ID198
Feature activation-3.37e-01

Pos logit contributions
 gol+0.003
aden+0.002
aw+0.002
 cheated+0.002
David+0.002
Neg logit contributions
elope-0.001
 Sn-0.001
 Chick-0.001
 Pr-0.001
 pap-0.001
Token"
Token ID1
Feature activation-1.72e+00

Pos logit contributions
 Sn+0.007
bing+0.007
elope+0.007
isa+0.007
cel+0.007
Neg logit contributions
 gol-0.017
aden-0.014
aw-0.014
 cheated-0.013
David-0.013
TokenThank
Token ID10449
Feature activation-1.53e-01

Pos logit contributions
isa+0.064
elope+0.063
bing+0.063
 pap+0.063
cel+0.063
Neg logit contributions
 gol-0.058
aw-0.044
David-0.044
aden-0.040
 cheated-0.039
Token you
Token ID345
Feature activation+7.47e-02

Pos logit contributions
mary+0.007
cel+0.006
elope+0.006
isa+0.006
 knees+0.006
Neg logit contributions
 gol-0.004
aw-0.004
Tom-0.003
ival-0.003
David-0.003
Token,
Token ID11
Feature activation-9.17e-01

Pos logit contributions
 gol+0.002
aw+0.002
 Tommy+0.002
ax+0.002
aden+0.002
Neg logit contributions
bing-0.003
isa-0.003
we-0.003
cel-0.003
elope-0.003
Token at
Token ID379
Feature activation+7.75e-01

Pos logit contributions
 gol+0.006
David+0.005
aden+0.005
aw+0.004
ival+0.004
Neg logit contributions
 sn-0.003
mary-0.003
cel-0.003
 Sn-0.003
 pap-0.003
Token the
Token ID262
Feature activation-4.70e-01

Pos logit contributions
 gol+0.044
ival+0.039
David+0.037
 cheated+0.037
aw+0.037
Neg logit contributions
 Sn-0.013
 Chick-0.012
 Pr-0.012
 sn-0.011
bing-0.011
Token seas
Token ID21547
Feature activation+3.70e+00

Pos logit contributions
 sn+0.016
 next+0.015
 pap+0.014
 Sn+0.014
cel+0.014
Neg logit contributions
 gol-0.017
David-0.014
arl-0.013
ival-0.013
aden-0.013
Tokenhell
Token ID12758
Feature activation+1.27e+00

Pos logit contributions
 gol+0.132
aw+0.098
aden+0.098
David+0.097
 cheated+0.093
Neg logit contributions
isa-0.131
cel-0.130
elope-0.130
 Sn-0.130
 pap-0.129
Token and
Token ID290
Feature activation+1.31e+00

Pos logit contributions
 gol+0.055
aw+0.046
aden+0.044
 cheated+0.043
ax+0.042
Neg logit contributions
cel-0.034
isa-0.034
 pap-0.033
elope-0.033
 Sn-0.033
Token said
Token ID531
Feature activation+1.57e-01

Pos logit contributions
 gol+0.057
aden+0.045
aw+0.045
David+0.045
ival+0.043
Neg logit contributions
 pap-0.036
isa-0.036
 Sn-0.036
elope-0.036
cel-0.036
Token,
Token ID11
Feature activation+8.75e-01

Pos logit contributions
 gol+0.009
aden+0.008
David+0.008
aw+0.007
ax+0.007
Neg logit contributions
 Sn-0.002
 pap-0.002
cel-0.002
 Pr-0.002
 sn-0.002
Token "
Token ID366
Feature activation-4.34e-01

Pos logit contributions
 gol+0.038
David+0.031
aw+0.030
aden+0.030
 cheated+0.030
Neg logit contributions
isa-0.024
elope-0.023
cel-0.022
 Sn-0.022
 pap-0.021
TokenWow
Token ID22017
Feature activation+9.97e-01

Pos logit contributions
 Sn+0.014
isa+0.014
cel+0.013
elope+0.013
 pap+0.013
Neg logit contributions
 gol-0.017
aw-0.013
aden-0.013
David-0.013
 cheated-0.013
Token,
Token ID11
Feature activation+5.39e-02

Pos logit contributions
 gol+0.045
aw+0.038
aden+0.037
David+0.036
 cheated+0.036
Neg logit contributions
isa-0.025
elope-0.024
 pap-0.024
 Sn-0.024
cel-0.024
Token Lily
Token ID20037
Feature activation-6.71e-01

Pos logit contributions
 gol+0.003
David+0.002
aw+0.002
aden+0.002
ival+0.002
Neg logit contributions
 Sn-0.001
 pap-0.001
cel-0.001
 Pr-0.001
 Chick-0.001
Token to
Token ID284
Feature activation-4.45e-01

Pos logit contributions
 gol+0.041
aden+0.034
aw+0.034
David+0.033
 cheated+0.033
Neg logit contributions
isa-0.015
 Sn-0.015
 pap-0.015
elope-0.015
cel-0.015
Token eat
Token ID4483
Feature activation-1.13e+00

Pos logit contributions
isa+0.012
 Sn+0.012
 pap+0.012
elope+0.012
cel+0.012
Neg logit contributions
 gol-0.019
aw-0.015
aden-0.015
David-0.015
 cheated-0.015
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
 Sn+0.020
 sn+0.019
 Pr+0.019
mary+0.019
bing+0.019
Neg logit contributions
 gol-0.062
aden-0.052
David-0.052
 cheated-0.051
ival-0.050
Token One
Token ID1881
Feature activation-1.59e+00

Pos logit contributions
 gol+0.016
aw+0.013
aden+0.013
David+0.012
 cheated+0.012
Neg logit contributions
isa-0.009
elope-0.009
 Sn-0.009
cel-0.009
 pap-0.009
Token day
Token ID1110
Feature activation-1.30e+00

Pos logit contributions
cel+0.052
 Sn+0.050
bing+0.049
isa+0.048
 pap+0.048
Neg logit contributions
 gol-0.063
aw-0.050
David-0.047
aden-0.047
ax-0.046
Token,
Token ID11
Feature activation+9.87e-02

Pos logit contributions
cel+0.034
elope+0.034
 Sn+0.034
isa+0.033
mary+0.033
Neg logit contributions
 gol-0.059
aw-0.048
David-0.047
aden-0.046
 cheated-0.046
Token Tony
Token ID8832
Feature activation-7.03e-01

Pos logit contributions
 gol+0.004
aw+0.003
David+0.003
aden+0.003
 cheated+0.003
Neg logit contributions
cel-0.003
 Sn-0.003
elope-0.003
isa-0.003
 pap-0.003
Token found
Token ID1043
Feature activation+1.58e+00

Pos logit contributions
isa+0.018
elope+0.017
 pap+0.017
 sn+0.017
mary+0.017
Neg logit contributions
 gol-0.034
aden-0.027
David-0.027
arl-0.026
ival-0.026
Token a
Token ID257
Feature activation-1.80e-01

Pos logit contributions
 gol+0.088
aden+0.074
David+0.073
arl+0.072
ival+0.071
Neg logit contributions
 pap-0.028
 Pr-0.028
 Bee-0.025
 Moon-0.025
 Chick-0.025
Token whole
Token ID2187
Feature activation-9.35e-01

Pos logit contributions
 pap+0.005
 sn+0.004
 bit+0.004
 pur+0.004
elope+0.004
Neg logit contributions
 gol-0.008
aden-0.007
aw-0.007
David-0.007
anes-0.007
Token bunch
Token ID7684
Feature activation+3.52e-01

Pos logit contributions
 sn+0.022
 pap+0.022
elope+0.021
 pur+0.020
 Pr+0.020
Neg logit contributions
 gol-0.044
aden-0.039
 cheated-0.037
David-0.037
aw-0.036
Token Tim
Token ID5045
Feature activation+1.08e+00

Pos logit contributions
 gol+0.045
aw+0.037
aden+0.036
arl+0.036
David+0.036
Neg logit contributions
 Sn-0.031
 Chick-0.029
 Pr-0.029
 pap-0.029
elope-0.029
Tokenmy
Token ID1820
Feature activation+5.57e-02

Pos logit contributions
 gol+0.056
ival+0.046
arl+0.044
 tant+0.043
David+0.043
Neg logit contributions
 sn-0.025
isa-0.024
elope-0.023
cup-0.023
 pap-0.022
Token found
Token ID1043
Feature activation+1.61e+00

Pos logit contributions
 gol+0.003
arl+0.002
aden+0.002
David+0.002
ival+0.002
Neg logit contributions
 pap-0.001
 sn-0.001
cel-0.001
isa-0.001
elope-0.001
Token a
Token ID257
Feature activation-3.53e-01

Pos logit contributions
 gol+0.096
arl+0.080
David+0.079
ane+0.079
ival+0.079
Neg logit contributions
 Sn-0.023
 Chick-0.022
 Pr-0.021
 sn-0.021
 one-0.021
Token sword
Token ID8429
Feature activation+1.60e+00

Pos logit contributions
 pap+0.009
 Sn+0.008
 sn+0.008
 bit+0.008
 pur+0.008
Neg logit contributions
 gol-0.016
aw-0.016
aden-0.015
ax-0.014
David-0.014
Token that
Token ID326
Feature activation+4.13e-01

Pos logit contributions
 gol+0.090
David+0.081
aden+0.078
ival+0.076
aw+0.075
Neg logit contributions
 sn-0.023
cel-0.023
 following-0.022
bing-0.021
 making-0.021
Token he
Token ID339
Feature activation+1.43e+00

Pos logit contributions
 gol+0.021
arl+0.018
aw+0.018
David+0.017
aden+0.017
Neg logit contributions
 Sn-0.009
 sn-0.009
 Chick-0.009
 Pr-0.009
 pap-0.008
Token had
Token ID550
Feature activation+9.96e-01

Pos logit contributions
 gol+0.065
David+0.053
aw+0.053
aden+0.052
ax+0.050
Neg logit contributions
cel-0.037
 Sn-0.036
isa-0.036
elope-0.036
 sn-0.035
Token forgotten
Token ID11564
Feature activation+1.26e+00

Pos logit contributions
 gol+0.053
David+0.043
arl+0.043
aden+0.043
ax+0.042
Neg logit contributions
 sn-0.021
cel-0.019
 Sn-0.018
 eyel-0.018
 Pr-0.017
Token about
Token ID546
Feature activation-1.47e-01

Pos logit contributions
 gol+0.074
David+0.063
ival+0.060
aden+0.060
Kyle+0.060
Neg logit contributions
 because-0.019
 sn-0.019
 before-0.019
 Sn-0.018
 making-0.016
Token.
Token ID13
Feature activation-7.76e-02

Pos logit contributions
 Sn+0.003
 sn+0.003
 making+0.003
 Pr+0.003
cel+0.003
Neg logit contributions
 gol-0.008
aw-0.006
David-0.006
ival-0.006
ax-0.006
Token need
Token ID761
Feature activation+2.86e-01

Pos logit contributions
 gol+0.015
David+0.012
aden+0.012
aw+0.012
ival+0.011
Neg logit contributions
cel-0.012
 Sn-0.011
 sn-0.011
elope-0.011
 roast-0.011
Token a
Token ID257
Feature activation-8.60e-01

Pos logit contributions
 gol+0.014
aw+0.011
aden+0.011
David+0.011
 cheated+0.011
Neg logit contributions
 Sn-0.007
isa-0.007
 pap-0.007
cel-0.007
elope-0.007
Token bath
Token ID7837
Feature activation-1.46e+00

Pos logit contributions
 pap+0.022
 sn+0.021
 Sn+0.021
 roast+0.020
 pur+0.020
Neg logit contributions
 gol-0.039
aw-0.034
aden-0.034
David-0.033
ax-0.032
Token."
Token ID526
Feature activation+3.57e-01

Pos logit contributions
 Sn+0.027
isa+0.026
 pap+0.025
cel+0.025
bing+0.025
Neg logit contributions
 gol-0.076
David-0.065
aden-0.064
aw-0.064
 cheated-0.062
Token
Token ID198
Feature activation+9.50e-01

Pos logit contributions
 gol+0.016
aden+0.013
aw+0.013
David+0.013
 cheated+0.013
Neg logit contributions
 Sn-0.009
elope-0.009
 pap-0.009
 Pr-0.009
 Chick-0.009
Token
Token ID198
Feature activation+3.21e-01

Pos logit contributions
 gol+0.045
aden+0.036
aw+0.035
David+0.035
 cheated+0.035
Neg logit contributions
 Sn-0.024
elope-0.024
cel-0.023
 Chick-0.023
isa-0.023
TokenTheir
Token ID14574
Feature activation-2.62e-02

Pos logit contributions
 gol+0.013
aw+0.010
aden+0.010
David+0.010
 cheated+0.010
Neg logit contributions
isa-0.010
 Sn-0.010
cel-0.010
elope-0.010
 pap-0.010
Token mom
Token ID1995
Feature activation-2.21e-01

Pos logit contributions
 pap+0.000
 Sn+0.000
elope+0.000
 sn+0.000
 pur+0.000
Neg logit contributions
 gol-0.001
aden-0.001
David-0.001
aw-0.001
ax-0.001
Token agreed
Token ID4987
Feature activation-7.25e-01

Pos logit contributions
isa+0.006
 Sn+0.006
cel+0.006
elope+0.006
 pap+0.006
Neg logit contributions
 gol-0.009
aw-0.007
aden-0.007
David-0.007
 cheated-0.007
Token.
Token ID13
Feature activation-4.59e-01

Pos logit contributions
isa+0.019
elope+0.019
cel+0.019
 Sn+0.018
bing+0.018
Neg logit contributions
 gol-0.032
aw-0.027
aden-0.026
David-0.026
ax-0.025
Token She
Token ID1375
Feature activation-1.03e+00

Pos logit contributions
isa+0.014
cel+0.013
elope+0.013
 Sn+0.013
 pap+0.013
Neg logit contributions
 gol-0.019
aw-0.015
aden-0.015
David-0.015
 cheated-0.014
Token is
Token ID318
Feature activation-1.82e-01

Pos logit contributions
bing+0.011
isa+0.011
 pap+0.010
elope+0.010
cel+0.010
Neg logit contributions
 gol-0.011
 cheated-0.010
aw-0.010
 happened-0.009
aden-0.009
Token sick
Token ID6639
Feature activation-1.14e+00

Pos logit contributions
isa+0.005
cel+0.005
elope+0.005
 Sn+0.004
 pap+0.004
Neg logit contributions
 gol-0.008
aw-0.007
aden-0.007
David-0.007
 cheated-0.006
Token."
Token ID526
Feature activation+4.37e-02

Pos logit contributions
 Sn+0.019
isa+0.018
cel+0.018
elope+0.018
 pap+0.018
Neg logit contributions
 gol-0.062
David-0.052
aden-0.052
aw-0.051
ival-0.050
Token
Token ID198
Feature activation+8.62e-01

Pos logit contributions
 gol+0.002
aden+0.001
aw+0.001
David+0.001
 cheated+0.001
Neg logit contributions
 Sn-0.001
isa-0.001
 pap-0.001
elope-0.001
cel-0.001
Token
Token ID198
Feature activation+2.43e-01

Pos logit contributions
 gol+0.039
aden+0.031
aw+0.031
David+0.030
 cheated+0.030
Neg logit contributions
 Sn-0.022
elope-0.022
isa-0.022
 pap-0.022
 Pr-0.022
Token"
Token ID1
Feature activation-1.41e+00

Pos logit contributions
 gol+0.009
aw+0.007
David+0.007
aden+0.007
 cheated+0.006
Neg logit contributions
cel-0.009
 Sn-0.008
isa-0.008
elope-0.008
 pap-0.008
TokenLet
Token ID5756
Feature activation-3.89e-01

Pos logit contributions
isa+0.040
cel+0.040
 Sn+0.040
elope+0.040
 pap+0.039
Neg logit contributions
 gol-0.060
aw-0.048
aden-0.048
David-0.047
 cheated-0.046
Token's
Token ID338
Feature activation-1.88e+00

Pos logit contributions
isa+0.008
cel+0.008
elope+0.008
 Sn+0.008
 pap+0.007
Neg logit contributions
 gol-0.019
aw-0.017
 happened-0.016
aden-0.016
David-0.016
Token move
Token ID1445
Feature activation-1.48e+00

Pos logit contributions
isa+0.044
cel+0.044
 Sn+0.044
elope+0.043
 pap+0.043
Neg logit contributions
 gol-0.089
aw-0.073
aden-0.072
David-0.072
 cheated-0.070
Token away
Token ID1497
Feature activation+1.03e+00

Pos logit contributions
isa+0.036
 Sn+0.036
elope+0.036
cel+0.036
 pap+0.035
Neg logit contributions
 gol-0.069
David-0.055
aden-0.055
aw-0.055
 cheated-0.053
Token,
Token ID11
Feature activation-6.85e-01

Pos logit contributions
 gol+0.050
aw+0.041
aden+0.041
David+0.041
 cheated+0.039
Neg logit contributions
isa-0.023
cel-0.023
 Sn-0.023
elope-0.023
 pap-0.023
Token."
Token ID526
Feature activation+4.38e-01

Pos logit contributions
 gol+0.080
aw+0.067
aden+0.066
David+0.066
 cheated+0.064
Neg logit contributions
isa-0.031
cel-0.031
 Sn-0.030
elope-0.030
 pap-0.030
Token
Token ID198
Feature activation+8.20e-01

Pos logit contributions
 gol+0.020
aden+0.017
David+0.016
aw+0.016
 cheated+0.016
Neg logit contributions
elope-0.011
 Sn-0.011
 Pr-0.011
isa-0.011
 pap-0.011
Token
Token ID198
Feature activation+1.85e-01

Pos logit contributions
 gol+0.042
aden+0.034
 cheated+0.033
aw+0.033
 trophies+0.033
Neg logit contributions
elope-0.018
 Sn-0.018
isa-0.017
 Chick-0.017
 Pr-0.017
TokenThe
Token ID464
Feature activation-5.51e-01

Pos logit contributions
 gol+0.010
aden+0.008
 cheated+0.008
aw+0.008
 happened+0.008
Neg logit contributions
elope-0.004
isa-0.004
 Sn-0.004
bing-0.004
cel-0.003
Token little
Token ID1310
Feature activation+9.30e-01

Pos logit contributions
 Sn+0.013
 pap+0.013
elope+0.013
cel+0.013
 Moon+0.013
Neg logit contributions
 gol-0.027
David-0.022
aw-0.022
aden-0.022
ax-0.021
Token bear
Token ID6842
Feature activation-1.11e+00

Pos logit contributions
 gol+0.043
aw+0.035
aden+0.035
David+0.034
 cheated+0.033
Neg logit contributions
isa-0.023
cel-0.023
 Sn-0.023
elope-0.023
 pap-0.023
Token said
Token ID531
Feature activation+1.70e-01

Pos logit contributions
cel+0.030
 Sn+0.030
isa+0.030
 pap+0.029
bing+0.029
Neg logit contributions
 gol-0.049
aw-0.040
aden-0.038
David-0.038
 cheated-0.037
Token,
Token ID11
Feature activation+6.70e-01

Pos logit contributions
 gol+0.008
aw+0.006
aden+0.006
David+0.006
 cheated+0.006
Neg logit contributions
isa-0.004
cel-0.004
elope-0.004
 Sn-0.004
 pap-0.004
Token "
Token ID366
Feature activation-5.83e-01

Pos logit contributions
 gol+0.025
aw+0.020
David+0.019
 cheated+0.018
 Tommy+0.018
Neg logit contributions
isa-0.022
elope-0.021
cel-0.020
bing-0.020
mary-0.019
TokenI
Token ID40
Feature activation+1.30e+00

Pos logit contributions
cel+0.019
isa+0.019
 pap+0.019
 Sn+0.019
elope+0.019
Neg logit contributions
 gol-0.022
aw-0.018
David-0.017
aden-0.017
 cheated-0.016
Token will
Token ID481
Feature activation-1.16e+00

Pos logit contributions
 gol+0.057
aw+0.046
David+0.046
aden+0.045
ival+0.043
Neg logit contributions
elope-0.036
isa-0.035
 Sn-0.035
 pap-0.035
 sn-0.035
Token.
Token ID13
Feature activation+5.36e-01

Pos logit contributions
 gol+0.144
aw+0.118
aden+0.117
David+0.117
 cheated+0.114
Neg logit contributions
isa-0.059
cel-0.059
elope-0.058
 Sn-0.058
 pap-0.057
Token
Token ID198
Feature activation+7.07e-01

Pos logit contributions
 gol+0.025
aw+0.021
aden+0.021
ival+0.020
 cheated+0.020
Neg logit contributions
 Sn-0.013
 Pr-0.013
 pap-0.013
elope-0.012
 Chick-0.012
Token
Token ID198
Feature activation+1.99e-01

Pos logit contributions
 gol+0.034
aw+0.028
aden+0.028
 cheated+0.027
 tant+0.026
Neg logit contributions
 Sn-0.017
elope-0.016
 Pr-0.016
 Chick-0.016
 pap-0.015
TokenThe
Token ID464
Feature activation-6.09e-01

Pos logit contributions
 gol+0.008
aw+0.007
aden+0.007
David+0.006
 cheated+0.006
Neg logit contributions
 Sn-0.006
isa-0.006
elope-0.006
 pap-0.006
cel-0.006
Token two
Token ID734
Feature activation+9.99e-01

Pos logit contributions
 Sn+0.014
 sn+0.014
 pap+0.013
 following+0.013
 Moon+0.013
Neg logit contributions
 gol-0.029
aw-0.025
David-0.025
aden-0.024
ax-0.024
Token spent
Token ID3377
Feature activation-1.56e+00

Pos logit contributions
 gol+0.047
David+0.039
arl+0.038
aden+0.036
 fault+0.036
Neg logit contributions
 sn-0.024
 pap-0.023
 Sn-0.022
 Pr-0.022
 pur-0.022
Token the
Token ID262
Feature activation+7.01e-01

Pos logit contributions
elope+0.032
isa+0.032
 Sn+0.032
cel+0.031
bing+0.031
Neg logit contributions
 gol-0.078
aden-0.065
David-0.065
 cheated-0.062
aw-0.062
Token afternoon
Token ID6672
Feature activation-7.25e-01

Pos logit contributions
 gol+0.033
aw+0.027
aden+0.027
David+0.027
 cheated+0.026
Neg logit contributions
isa-0.016
 Sn-0.016
cel-0.016
elope-0.016
 pap-0.016
Token bouncing
Token ID30713
Feature activation-1.79e-01

Pos logit contributions
cel+0.014
isa+0.014
bing+0.014
 Sn+0.014
elope+0.014
Neg logit contributions
 gol-0.036
David-0.031
aden-0.030
aw-0.030
arl-0.029
Token until
Token ID1566
Feature activation-3.76e-01

Pos logit contributions
bing+0.003
 sn+0.003
 Sn+0.003
bed+0.003
elope+0.003
Neg logit contributions
 gol-0.009
David-0.009
aden-0.008
arl-0.008
ax-0.008
Token soon
Token ID2582
Feature activation-6.56e-01

Pos logit contributions
 Sn+0.008
 Pr+0.008
 sn+0.007
 roast+0.007
 Chick+0.007
Neg logit contributions
 gol-0.019
aden-0.016
arl-0.016
aw-0.016
ival-0.016
Token need
Token ID761
Feature activation+1.48e-01

Pos logit contributions
isa+0.009
elope+0.009
 Sn+0.009
cel+0.009
 pap+0.009
Neg logit contributions
 gol-0.014
David-0.011
aw-0.011
aden-0.011
ival-0.011
Token to
Token ID284
Feature activation-1.03e+00

Pos logit contributions
 gol+0.007
aden+0.006
aw+0.006
David+0.006
ival+0.006
Neg logit contributions
 pap-0.003
 Pr-0.003
isa-0.003
 Sn-0.003
 Chick-0.003
Token be
Token ID307
Feature activation-1.18e+00

Pos logit contributions
isa+0.023
cel+0.023
elope+0.022
 Sn+0.022
 pap+0.022
Neg logit contributions
 gol-0.051
aw-0.041
aden-0.041
David-0.041
 cheated-0.040
Token wealthy
Token ID11574
Feature activation-7.42e-01

Pos logit contributions
 sn+0.034
 pap+0.034
 Sn+0.033
mary+0.033
 Pr+0.032
Neg logit contributions
 gol-0.050
aden-0.041
David-0.040
ival-0.040
ane-0.038
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
 Sn+0.014
 pap+0.014
bing+0.013
elope+0.013
cel+0.013
Neg logit contributions
 gol-0.038
David-0.033
aden-0.032
aw-0.032
ival-0.031
Token be
Token ID307
Feature activation-1.26e+00

Pos logit contributions
 pap+0.019
 Sn+0.019
 sn+0.019
elope+0.019
 Chick+0.019
Neg logit contributions
 gol-0.053
aw-0.044
ival-0.044
aden-0.044
David-0.043
Token happy
Token ID3772
Feature activation-1.07e+00

Pos logit contributions
 sn+0.032
 pap+0.032
mary+0.031
elope+0.031
bing+0.031
Neg logit contributions
 gol-0.059
aden-0.049
David-0.047
ival-0.047
ane-0.046
Token.
Token ID13
Feature activation-7.25e-01

Pos logit contributions
 Sn+0.018
 pap+0.017
bing+0.017
elope+0.017
cel+0.017
Neg logit contributions
 gol-0.058
David-0.050
aden-0.049
aw-0.049
ival-0.048
Token Their
Token ID5334
Feature activation-1.01e+00

Pos logit contributions
 Sn+0.015
 Pr+0.015
 Chick+0.014
elope+0.014
 pap+0.014
Neg logit contributions
 gol-0.038
ival-0.032
aden-0.032
aw-0.031
ax-0.031
Token mom
Token ID1995
Feature activation-8.95e-01

Pos logit contributions
 pap+0.016
 Sn+0.015
elope+0.015
 sn+0.014
 pur+0.014
Neg logit contributions
 gol-0.057
aw-0.049
aden-0.049
David-0.048
ival-0.047
Token smiled
Token ID13541
Feature activation-7.29e-01

Pos logit contributions
isa+0.025
 Sn+0.025
elope+0.025
cel+0.025
 pap+0.024
Neg logit contributions
 gol-0.039
aw-0.031
aden-0.031
David-0.030
 cheated-0.029
Token was
Token ID373
Feature activation-1.92e-01

Pos logit contributions
isa+0.008
cel+0.008
 Sn+0.008
elope+0.008
 pap+0.008
Neg logit contributions
 gol-0.018
aw-0.015
aden-0.015
David-0.015
 cheated-0.014
Token ok
Token ID12876
Feature activation-2.62e+00

Pos logit contributions
isa+0.005
 Sn+0.005
cel+0.005
elope+0.005
 pap+0.005
Neg logit contributions
 gol-0.008
aw-0.007
aden-0.006
David-0.006
 cheated-0.006
Token.
Token ID13
Feature activation-3.58e-01

Pos logit contributions
cel+0.065
bing+0.063
isa+0.062
 Sn+0.062
 pap+0.062
Neg logit contributions
 gol-0.118
aw-0.098
aden-0.096
David-0.096
 cheated-0.095
Token She
Token ID1375
Feature activation-1.03e+00

Pos logit contributions
isa+0.009
 Sn+0.009
cel+0.009
elope+0.009
 pap+0.009
Neg logit contributions
 gol-0.016
aw-0.013
aden-0.013
David-0.013
 cheated-0.012
Token said
Token ID531
Feature activation-1.34e-01

Pos logit contributions
isa+0.029
cel+0.029
 Sn+0.029
elope+0.028
bing+0.028
Neg logit contributions
 gol-0.044
aw-0.035
aden-0.035
David-0.034
 cheated-0.034
Token that
Token ID326
Feature activation-3.28e-01

Pos logit contributions
 Sn+0.002
 pap+0.002
 sn+0.002
 Pr+0.002
 Chick+0.002
Neg logit contributions
 gol-0.007
aden-0.006
David-0.006
aw-0.006
ax-0.006
Token it
Token ID340
Feature activation+1.61e-01

Pos logit contributions
 Sn+0.007
 pap+0.007
 Pr+0.007
isa+0.007
elope+0.007
Neg logit contributions
 gol-0.017
aw-0.014
aden-0.014
David-0.013
ax-0.013
Token was
Token ID373
Feature activation+1.05e-01

Pos logit contributions
 gol+0.008
aw+0.006
 cheated+0.006
aden+0.006
David+0.006
Neg logit contributions
isa-0.004
cel-0.004
 Sn-0.004
 pap-0.004
elope-0.004
Token ok
Token ID12876
Feature activation-2.27e+00

Pos logit contributions
 gol+0.005
aw+0.004
aden+0.004
David+0.004
 cheated+0.004
Neg logit contributions
isa-0.003
 Sn-0.003
cel-0.003
elope-0.003
 pap-0.003
Token to
Token ID284
Feature activation-7.23e-01

Pos logit contributions
cel+0.063
bing+0.061
 Sn+0.061
isa+0.060
 roast+0.059
Neg logit contributions
 gol-0.095
aw-0.079
David-0.077
aden-0.077
 cheated-0.075
Token make
Token ID787
Feature activation-2.50e+00

Pos logit contributions
 Sn+0.012
elope+0.012
isa+0.012
cel+0.012
 pap+0.012
Neg logit contributions
 gol-0.039
aw-0.033
aden-0.032
David-0.032
ival-0.031
Token help
Token ID1037
Feature activation-1.01e+00

Pos logit contributions
 gol+0.024
aw+0.020
aden+0.020
David+0.019
 cheated+0.019
Neg logit contributions
 Sn-0.011
isa-0.011
cel-0.011
 pap-0.011
elope-0.011
Token,
Token ID11
Feature activation+2.15e-01

Pos logit contributions
elope+0.027
isa+0.027
cel+0.027
 pap+0.026
 Moon+0.026
Neg logit contributions
 gol-0.042
David-0.034
aden-0.034
he-0.033
aw-0.033
Token telling
Token ID5149
Feature activation-1.10e+00

Pos logit contributions
 gol+0.011
aw+0.009
aden+0.009
David+0.009
ax+0.009
Neg logit contributions
isa-0.004
elope-0.004
cel-0.004
bing-0.004
 Sn-0.004
Token her
Token ID607
Feature activation-1.17e+00

Pos logit contributions
elope+0.037
cel+0.037
bing+0.036
isa+0.036
mary+0.035
Neg logit contributions
 gol-0.039
aw-0.032
aden-0.032
David-0.031
ax-0.029
Token "
Token ID366
Feature activation-8.87e-01

Pos logit contributions
isa+0.027
 Sn+0.027
 pap+0.027
elope+0.027
cel+0.027
Neg logit contributions
 gol-0.056
aw-0.046
aden-0.046
David-0.045
 cheated-0.044
TokenM
Token ID44
Feature activation-4.72e+00

Pos logit contributions
 Sn+0.022
isa+0.022
cel+0.021
elope+0.021
bing+0.021
Neg logit contributions
 gol-0.041
aden-0.033
aw-0.033
David-0.033
 cheated-0.032
Tokenummy
Token ID13513
Feature activation-1.82e+00

Pos logit contributions
cel+0.137
elope+0.135
 Sn+0.133
isa+0.133
bing+0.133
Neg logit contributions
 gol-0.197
aw-0.162
aden-0.157
David-0.154
ival-0.149
Token,
Token ID11
Feature activation-1.19e-01

Pos logit contributions
 pap+0.039
 Sn+0.039
isa+0.039
elope+0.038
 Pr+0.038
Neg logit contributions
 gol-0.091
aden-0.075
aw-0.074
David-0.074
 cheated-0.072
Token I
Token ID314
Feature activation+1.05e+00

Pos logit contributions
elope+0.004
isa+0.004
bing+0.004
cel+0.004
 eyel+0.004
Neg logit contributions
 gol-0.005
aden-0.004
aw-0.004
ax-0.003
ival-0.003
Token wanna
Token ID18869
Feature activation+1.36e+00

Pos logit contributions
 gol+0.046
aw+0.038
aden+0.037
David+0.036
ival+0.035
Neg logit contributions
 pap-0.028
 Sn-0.028
elope-0.028
cel-0.028
isa-0.028
Token invite
Token ID14037
Feature activation-1.54e+00

Pos logit contributions
 gol+0.062
aden+0.050
David+0.050
aw+0.049
 cheated+0.048
Neg logit contributions
isa-0.035
elope-0.035
cel-0.034
 pap-0.034
bing-0.034
Token joy
Token ID8716
Feature activation+3.54e-01

Pos logit contributions
cel+0.006
 Sn+0.006
isa+0.006
bing+0.005
elope+0.005
Neg logit contributions
 gol-0.009
aw-0.007
aden-0.007
David-0.007
 cheated-0.007
Token of
Token ID286
Feature activation+1.03e-01

Pos logit contributions
 gol+0.013
aw+0.010
aden+0.010
David+0.010
 cheated+0.010
Neg logit contributions
isa-0.012
cel-0.012
 Sn-0.012
elope-0.012
 pap-0.011
Token the
Token ID262
Feature activation+4.65e-01

Pos logit contributions
 gol+0.004
aw+0.003
David+0.003
aden+0.003
 cheated+0.003
Neg logit contributions
cel-0.003
isa-0.003
 Sn-0.003
elope-0.003
bing-0.003
Token new
Token ID649
Feature activation+2.27e+00

Pos logit contributions
 gol+0.020
aw+0.017
aden+0.016
David+0.016
 happened+0.016
Neg logit contributions
 Sn-0.012
cel-0.012
isa-0.012
elope-0.011
bing-0.011
Token baby
Token ID5156
Feature activation-8.85e-01

Pos logit contributions
 gol+0.079
 happened+0.066
aw+0.064
 fault+0.060
 chalk+0.060
Neg logit contributions
cel-0.076
 Stacy-0.073
 Sn-0.072
 Luna-0.069
isa-0.069
Token chick
Token ID17943
Feature activation-4.08e+00

Pos logit contributions
cel+0.022
 eyel+0.022
 Sn+0.021
 Stacy+0.021
 hips+0.020
Neg logit contributions
 gol-0.034
aw-0.033
 happened-0.029
he-0.029
ane-0.028
Token together
Token ID1978
Feature activation-5.98e-01

Pos logit contributions
cel+0.106
isa+0.103
 Sn+0.102
 pap+0.099
bing+0.096
Neg logit contributions
 gol-0.176
aw-0.149
 cheated-0.139
aden-0.137
ax-0.135
Token.
Token ID13
Feature activation+2.48e-01

Pos logit contributions
isa+0.010
 Sn+0.010
elope+0.010
cel+0.010
 pap+0.010
Neg logit contributions
 gol-0.032
aden-0.027
David-0.027
aw-0.027
 cheated-0.026
Token<|endoftext|>
Token ID50256
Feature activation+3.09e-01

Pos logit contributions
 gol+0.011
aw+0.009
aden+0.009
David+0.009
 cheated+0.009
Neg logit contributions
 Sn-0.006
elope-0.006
cel-0.006
 Pr-0.006
isa-0.006
TokenOnce
Token ID7454
Feature activation-4.16e-01

Pos logit contributions
 gol+0.017
aden+0.014
 tant+0.014
David+0.014
aw+0.014
Neg logit contributions
 Sn-0.006
elope-0.006
 Pr-0.005
 Flower-0.005
 Moon-0.005
Token upon
Token ID2402
Feature activation+3.04e-01

Pos logit contributions
 Pr+0.012
elope+0.012
 pap+0.012
 Ana+0.011
isa+0.011
Neg logit contributions
 gol-0.018
aw-0.015
David-0.014
ival-0.014
aden-0.014
Token on
Token ID319
Feature activation+6.18e-01

Pos logit contributions
cel+0.014
we+0.014
bing+0.013
isa+0.013
bes+0.013
Neg logit contributions
 gol-0.012
 happened-0.011
aw-0.010
 Tommy-0.010
 cheated-0.010
Token special
Token ID2041
Feature activation+8.66e-01

Pos logit contributions
 gol+0.018
 Tommy+0.016
 happened+0.016
aw+0.016
 av+0.015
Neg logit contributions
we-0.022
cel-0.020
 roast-0.018
isa-0.018
 convince-0.018
Token days
Token ID1528
Feature activation+7.90e-01

Pos logit contributions
 gol+0.029
 happened+0.027
 chalk+0.023
aw+0.023
 trophies+0.022
Neg logit contributions
 Sn-0.030
cel-0.030
 Chick-0.029
mary-0.029
 Pr-0.028
Token,
Token ID11
Feature activation+1.01e+00

Pos logit contributions
 gol+0.041
aden+0.035
David+0.035
aw+0.034
 cheated+0.033
Neg logit contributions
isa-0.015
 Sn-0.015
elope-0.015
 pap-0.015
 Pr-0.014
Token like
Token ID588
Feature activation+7.22e-01

Pos logit contributions
 gol+0.041
aw+0.035
 Tommy+0.033
 happened+0.033
 cheated+0.032
Neg logit contributions
cel-0.027
bing-0.024
isa-0.024
 hips-0.024
we-0.023
Token Honey
Token ID21788
Feature activation-4.06e+00

Pos logit contributions
 gol+0.038
aw+0.032
David+0.031
aden+0.031
ival+0.030
Neg logit contributions
 pap-0.015
 Sn-0.015
 Moon-0.014
 Pr-0.014
 Flower-0.014
Token's
Token ID338
Feature activation-1.09e+00

Pos logit contributions
 Sn+0.087
cel+0.087
isa+0.085
elope+0.084
bing+0.082
Neg logit contributions
 gol-0.195
aw-0.164
aden-0.158
David-0.158
 cheated-0.155
Token birthday
Token ID10955
Feature activation-5.63e-01

Pos logit contributions
 pap+0.026
 Sn+0.026
elope+0.026
isa+0.026
cel+0.026
Neg logit contributions
 gol-0.051
aw-0.041
aden-0.041
David-0.041
 cheated-0.040
Token,
Token ID11
Feature activation+1.08e+00

Pos logit contributions
 Sn+0.011
isa+0.011
elope+0.011
 pap+0.011
cel+0.011
Neg logit contributions
 gol-0.029
David-0.024
aden-0.024
aw-0.023
 cheated-0.023
Token Buzz
Token ID15753
Feature activation-2.01e+00

Pos logit contributions
 gol+0.055
aden+0.046
David+0.045
aw+0.045
 cheated+0.044
Neg logit contributions
 Sn-0.022
 pap-0.022
elope-0.021
isa-0.021
cel-0.021
Tokeny
Token ID88
Feature activation-1.51e-01

Pos logit contributions
isa+0.055
elope+0.054
 pap+0.053
 Sn+0.052
mary+0.052
Neg logit contributions
 gol-0.092
aden-0.073
David-0.073
aw-0.072
ival-0.071
Token shop
Token ID6128
Feature activation-3.79e-01

Pos logit contributions
 pap+0.020
 Sn+0.019
 Moon+0.019
 Pr+0.018
 sn+0.018
Neg logit contributions
 gol-0.027
aden-0.023
David-0.023
 cheated-0.022
aw-0.022
Token.
Token ID13
Feature activation+2.35e-01

Pos logit contributions
cel+0.009
isa+0.009
elope+0.009
bing+0.008
 Sn+0.008
Neg logit contributions
 gol-0.018
aw-0.015
aden-0.015
David-0.014
ival-0.014
Token She
Token ID1375
Feature activation-6.72e-01

Pos logit contributions
 gol+0.009
aw+0.007
David+0.006
 chalk+0.006
aden+0.006
Neg logit contributions
isa-0.008
bing-0.008
we-0.008
elope-0.008
cel-0.008
Token gave
Token ID2921
Feature activation-8.81e-01

Pos logit contributions
cel+0.019
bing+0.019
isa+0.019
 Sn+0.019
elope+0.019
Neg logit contributions
 gol-0.028
aw-0.022
David-0.022
aden-0.022
 cheated-0.021
Token Po
Token ID7695
Feature activation-2.78e+00

Pos logit contributions
elope+0.023
isa+0.023
cel+0.022
bing+0.021
 Sn+0.021
Neg logit contributions
 gol-0.039
aw-0.032
aden-0.031
 chalk-0.030
ax-0.030
Tokenppy
Token ID14097
Feature activation-4.30e+00

Pos logit contributions
 Sn+0.062
elope+0.062
isa+0.061
bing+0.061
cel+0.061
Neg logit contributions
 gol-0.130
aw-0.108
aden-0.108
David-0.105
ax-0.103
Token some
Token ID617
Feature activation-1.92e+00

Pos logit contributions
cel+0.111
isa+0.108
elope+0.107
 Sn+0.106
bing+0.106
Neg logit contributions
 gol-0.190
aw-0.157
David-0.154
aden-0.154
ival-0.149
Token money
Token ID1637
Feature activation+2.13e+00

Pos logit contributions
 sn+0.053
 pap+0.053
 Pr+0.052
 roast+0.052
 Sn+0.052
Neg logit contributions
 gol-0.083
David-0.070
aden-0.069
ax-0.065
 cheated-0.064
Token and
Token ID290
Feature activation+3.62e-01

Pos logit contributions
 gol+0.115
David+0.095
aden+0.095
aw+0.094
 cheated+0.092
Neg logit contributions
 Sn-0.038
 pap-0.037
 Pr-0.036
isa-0.035
mary-0.035
Token said
Token ID531
Feature activation-1.84e-01

Pos logit contributions
 gol+0.016
aw+0.013
David+0.013
aden+0.013
 cheated+0.012
Neg logit contributions
cel-0.009
isa-0.009
elope-0.009
bing-0.009
 Sn-0.009
Token "
Token ID366
Feature activation-6.06e-01

Pos logit contributions
 Sn+0.003
 pap+0.003
 Pr+0.003
cel+0.003
 Chick+0.003
Neg logit contributions
 gol-0.010
aden-0.008
David-0.008
aw-0.008
 cheated-0.008
Token stopped
Token ID5025
Feature activation+1.31e+00

Pos logit contributions
 gol+0.036
aden+0.029
David+0.028
arl+0.028
aw+0.028
Neg logit contributions
 sn-0.023
 pur-0.022
 pap-0.021
cel-0.021
elope-0.021
Token.
Token ID13
Feature activation-7.83e-02

Pos logit contributions
 gol+0.065
aw+0.054
aden+0.054
David+0.053
ival+0.053
Neg logit contributions
 pap-0.028
bing-0.028
 Sn-0.028
cel-0.028
isa-0.028
Token
Token ID220
Feature activation-1.47e+00

Pos logit contributions
 Pr+0.002
 Sn+0.002
elope+0.002
 pap+0.002
cel+0.002
Neg logit contributions
 gol-0.004
aden-0.003
 cheated-0.003
aw-0.003
ival-0.003
Token
Token ID198
Feature activation+1.27e-01

Pos logit contributions
 Pr+0.025
 Sn+0.025
elope+0.024
 Chick+0.024
 Luna+0.023
Neg logit contributions
 gol-0.083
 tant-0.069
 trophies-0.068
aw-0.067
aden-0.066
Token
Token ID198
Feature activation-2.87e-01

Pos logit contributions
 gol+0.006
 cheated+0.005
aden+0.005
 trophies+0.005
 tant+0.005
Neg logit contributions
elope-0.003
 Pr-0.003
 Sn-0.003
mary-0.003
 Chick-0.003
TokenSad
Token ID26699
Feature activation-4.35e+00

Pos logit contributions
elope+0.008
isa+0.007
 Sn+0.007
cel+0.007
bing+0.007
Neg logit contributions
 gol-0.013
aden-0.010
 cheated-0.010
aw-0.010
David-0.010
Token and
Token ID290
Feature activation+8.60e-01

Pos logit contributions
isa+0.090
elope+0.090
 pap+0.089
 Pr+0.086
 Sn+0.085
Neg logit contributions
 gol-0.220
David-0.179
aden-0.179
ival-0.179
 cheated-0.177
Token upset
Token ID9247
Feature activation+2.05e+00

Pos logit contributions
 gol+0.034
aden+0.027
aw+0.027
David+0.026
ival+0.026
Neg logit contributions
isa-0.027
elope-0.027
 Sn-0.027
 pap-0.027
bing-0.026
Token,
Token ID11
Feature activation+9.01e-01

Pos logit contributions
 gol+0.101
aden+0.082
David+0.082
aw+0.082
 cheated+0.079
Neg logit contributions
isa-0.045
 Sn-0.045
elope-0.045
cel-0.045
 pap-0.044
Token Sandy
Token ID17581
Feature activation-2.80e-01

Pos logit contributions
 gol+0.038
aden+0.030
David+0.030
aw+0.030
 cheated+0.029
Neg logit contributions
 Sn-0.025
elope-0.025
isa-0.025
 pap-0.025
cel-0.025
Token and
Token ID290
Feature activation+1.63e+00

Pos logit contributions
elope+0.006
isa+0.006
 Sn+0.006
cel+0.006
 pap+0.006
Neg logit contributions
 gol-0.013
aden-0.011
David-0.011
aw-0.011
ival-0.010