TOP ACTIVATIONS
MAX = 8.562

Tim wanted to help the sun flower . He had an
Y ay ! I love sun fl owers !" From that
us !" The sun flower laughed , and told
sun flower that followed the sun everywhere it went . The
are you sad ?" The sun flower said , " I
hugged it tightly . The sun flower felt safe and loved
it every day . The sun flower started to grow bigger
are very pretty !" The sun flower smiled and said ,
. The boy and the sun flower spent every day together
like the bunny . The sun flower was so happy and
Let 's plant some more sun fl owers , and we
seen !" The sun flower smiled and nodded her
Listen ! I think the sun flower is talking to us
ily insisted on keeping the sun flower in her room .
That 's the most attractive sun flower I 've ever seen
She had never tasted a sun flower before but she knew
sad . Tim asked the sun flower , " Why are
big field and followed the sun together , every day .
. He saw that the sun flower was sad . Tim
said , " Hello , sun flower ! You are very

MIN ACTIVATIONS
MIN = -9.378

his lion the name " ZE B RA K ILL ER
Stay away from my or chard , young Fox ! รข
ummy cotton candy and play carn ival games .
go the other way . How does that sound ?"
for taking her to the carn ival . They hugged her
had been disturbing his or chard and he wanted to get
ride to the apple or chard . The neighbor said yes
a fun ride at the carn ival . Twe ety thought
you to be safe . How about we finish our m
, Lily went to a carn ival with her family .
people who are hungry . How does that sound ?"
and a pet family . How does that sound ?"
, Lily went to a carn ival with her mom my
, Max , to the carn ival . Everywhere they looked
and have some breakfast . How does that sound ?"
the park and play . How does that sound ?" mom
and they walked through the carn ival gates , while Max
your favorite book together . How does that sound ?"
Max loved being at the carn ival so much that he
about we have our own carn ival at home ? We

INTERVAL 4.077 - 8.562
CONTAINS 2.808%

hear the thunder and the rain . They did not notice
her delicious dinner . She never felt so warm and happy
to play with his toys all day long . One day
naughty and rude to his mom . He does not listen
Now , Tim and Sue both felt sad . They could

INTERVAL -0.408 - 4.077
CONTAINS 61.564%

were invited . The rabbit was very excited to go to
. <|endoftext|> C ory and his best friend Amber were playing
singers and dancers when they grow up . They know they
Suddenly , the light became brighter and brighter . Steve
help the rabbit and find his family .

INTERVAL -4.893 - -0.408
CONTAINS 34.514%

to support her no matter what . The girl smiled happily
his scrap es . He felt sorry for him .
Annie , my name is Fred . It 's nice to
. The little girl was happy to help her mom my
subway stopped at a big station . Mom my and Billy

INTERVAL -9.378 - -4.893
CONTAINS 1.114%

that the gold was not worth it . He had lost
, can I touch one ?" Sara begged .
. Now it is gone ," Tom said .
. She couldn 't grow anything else because the fake plant
. Suddenly , he felt something wet on his foot .
Token Tim
Token ID5045
Feature activation+9.16e-01

Pos logit contributions
chard+0.131
nam+0.126
rily+0.125
 appet+0.122
 angrily+0.122
Neg logit contributions
 night-0.121
 day-0.120
ama-0.114
 end-0.113
 eye-0.113
Token wanted
Token ID2227
Feature activation+5.97e-01

Pos logit contributions
 night+0.050
 day+0.049
ama+0.049
 eye+0.048
 end+0.048
Neg logit contributions
chard-0.049
 angrily-0.048
 appet-0.047
nam-0.046
rily-0.046
Token to
Token ID284
Feature activation-2.40e-01

Pos logit contributions
ama+0.036
 eye+0.034
opl+0.033
 end+0.032
 night+0.032
Neg logit contributions
chard-0.030
 oh-0.028
 angrily-0.028
nam-0.027
 Edward-0.027
Token help
Token ID1037
Feature activation+5.22e+00

Pos logit contributions
chard+0.012
 angrily+0.012
nam+0.012
 oh+0.012
 Freddie+0.012
Neg logit contributions
ama-0.013
opl-0.013
ummy-0.012
 night-0.011
oes-0.011
Token the
Token ID262
Feature activation+6.96e-01

Pos logit contributions
 night+0.310
ama+0.302
 eye+0.302
 day+0.301
 end+0.293
Neg logit contributions
chard-0.260
 angrily-0.246
nam-0.242
rily-0.238
 oh-0.237
Token sun
Token ID4252
Feature activation+8.33e+00

Pos logit contributions
ama+0.031
bars+0.029
issy+0.029
opl+0.028
iff+0.028
Neg logit contributions
chard-0.039
 oh-0.036
 Claw-0.035
 hello-0.035
 handful-0.035
Tokenflower
Token ID25547
Feature activation+4.00e-01

Pos logit contributions
ama+0.384
 night+0.372
 eye+0.363
opl+0.355
 end+0.352
Neg logit contributions
chard-0.485
rily-0.458
 handful-0.453
ked-0.438
 angrily-0.433
Token.
Token ID13
Feature activation+5.75e-01

Pos logit contributions
ama+0.020
opl+0.018
 night+0.018
 eye+0.017
ummy+0.017
Neg logit contributions
chard-0.024
 angrily-0.023
 handful-0.022
nam-0.021
 appet-0.021
Token He
Token ID679
Feature activation-7.29e-01

Pos logit contributions
 night+0.028
 end+0.028
 eye+0.028
 day+0.027
ama+0.027
Neg logit contributions
chard-0.034
 angrily-0.033
 appet-0.033
rily-0.032
 Percy-0.032
Token had
Token ID550
Feature activation+1.18e+00

Pos logit contributions
chard+0.046
nam+0.045
rily+0.045
 appet+0.044
 angrily+0.044
Neg logit contributions
 night-0.035
 day-0.034
 end-0.033
 eye-0.033
ama-0.031
Token an
Token ID281
Feature activation-1.13e+00

Pos logit contributions
ama+0.083
 night+0.081
 eye+0.081
 day+0.080
 end+0.080
Neg logit contributions
chard-0.046
nam-0.044
 angrily-0.044
 handful-0.042
 appet-0.042
TokenY
Token ID56
Feature activation-3.07e-01

Pos logit contributions
chard+0.203
 appet+0.193
nam+0.190
 angrily+0.186
rily+0.185
Neg logit contributions
 night-0.290
 eye-0.286
ama-0.281
 end-0.280
 day-0.280
Tokenay
Token ID323
Feature activation+4.62e+00

Pos logit contributions
 appet+0.022
 handful+0.022
ked+0.022
 angrily+0.022
rily+0.022
Neg logit contributions
 night-0.010
 day-0.009
 eye-0.009
 end-0.008
opl-0.008
Token!
Token ID0
Feature activation-8.27e-01

Pos logit contributions
 night+0.227
 day+0.221
 end+0.218
 eye+0.217
ama+0.214
Neg logit contributions
chard-0.284
nam-0.271
 angrily-0.270
 appet-0.268
rily-0.267
Token I
Token ID314
Feature activation-4.82e-01

Pos logit contributions
chard+0.035
 appet+0.034
rily+0.033
 angrily+0.033
 oh+0.033
Neg logit contributions
 night-0.054
 end-0.054
 eye-0.053
 day-0.053
ama-0.050
Token love
Token ID1842
Feature activation+3.26e+00

Pos logit contributions
 appet+0.029
 angrily+0.026
 handful+0.026
chard+0.026
ked+0.025
Neg logit contributions
ama-0.024
ummy-0.022
 night-0.022
opl-0.022
oes-0.022
Token sun
Token ID4252
Feature activation+8.31e+00

Pos logit contributions
 eye+0.191
ama+0.183
 end+0.182
 night+0.171
opl+0.164
Neg logit contributions
chard-0.161
 handful-0.154
 oh-0.154
 appet-0.149
nam-0.148
Tokenfl
Token ID2704
Feature activation-7.10e-01

Pos logit contributions
 night+0.344
 eye+0.337
 end+0.333
 day+0.329
ama+0.312
Neg logit contributions
chard-0.545
rily-0.533
 handful-0.530
 appet-0.526
ked-0.517
Tokenowers
Token ID3618
Feature activation+8.84e-01

Pos logit contributions
 handful+0.035
 appet+0.035
chard+0.035
rily+0.034
ked+0.034
Neg logit contributions
 end-0.041
 night-0.040
 eye-0.040
 day-0.039
ama-0.036
Token!"
Token ID2474
Feature activation-4.27e+00

Pos logit contributions
 night+0.045
 eye+0.044
 end+0.044
 day+0.044
ama+0.044
Neg logit contributions
chard-0.051
 appet-0.049
rily-0.048
 handful-0.048
 angrily-0.047
Token From
Token ID3574
Feature activation-2.74e-01

Pos logit contributions
 angrily+0.208
 handful+0.198
rily+0.198
 appet+0.195
chard+0.194
Neg logit contributions
 end-0.245
 eye-0.237
 night-0.234
ama-0.229
opl-0.228
Token that
Token ID326
Feature activation+2.62e+00

Pos logit contributions
chard+0.015
 oh+0.014
 angrily+0.014
 Percy+0.013
rily+0.013
Neg logit contributions
 eye-0.014
 night-0.014
oes-0.014
opl-0.014
 day-0.014
Token us
Token ID514
Feature activation+1.48e+00

Pos logit contributions
chard+0.019
 angrily+0.018
nam+0.018
 appet+0.018
rily+0.018
Neg logit contributions
 night-0.014
 eye-0.014
ama-0.013
 day-0.013
 end-0.013
Token!"
Token ID2474
Feature activation-4.14e+00

Pos logit contributions
 night+0.073
 day+0.071
 end+0.070
 eye+0.068
ama+0.067
Neg logit contributions
chard-0.092
nam-0.089
 angrily-0.087
 appet-0.086
rily-0.086
Token
Token ID198
Feature activation+5.78e-01

Pos logit contributions
chard+0.286
rily+0.278
nam+0.277
 appet+0.274
 handful+0.266
Neg logit contributions
 night-0.176
 day-0.173
 of-0.164
 eye-0.164
 end-0.160
Token
Token ID198
Feature activation+5.84e-01

Pos logit contributions
 night+0.024
 day+0.023
 eye+0.023
 end+0.022
ama+0.022
Neg logit contributions
chard-0.040
 angrily-0.038
nam-0.038
 appet-0.038
rily-0.038
TokenThe
Token ID464
Feature activation+1.43e+00

Pos logit contributions
 end+0.024
 day+0.023
 night+0.023
ama+0.023
 of+0.022
Neg logit contributions
chard-0.040
rily-0.039
nam-0.039
 appet-0.038
 handful-0.038
Token sun
Token ID4252
Feature activation+8.29e+00

Pos logit contributions
opl+0.058
ama+0.056
oes+0.053
 night+0.053
 eye+0.051
Neg logit contributions
chard-0.092
 handful-0.085
 oh-0.084
 appet-0.084
nam-0.084
Tokenflower
Token ID25547
Feature activation+2.78e-01

Pos logit contributions
 night+0.377
 end+0.351
 eye+0.351
 day+0.347
opl+0.340
Neg logit contributions
chard-0.493
 angrily-0.490
rily-0.488
ked-0.487
 handful-0.484
Token laughed
Token ID13818
Feature activation-1.50e+00

Pos logit contributions
 night+0.017
ama+0.016
 eye+0.016
 day+0.016
 end+0.016
Neg logit contributions
 angrily-0.013
chard-0.013
ked-0.012
 handful-0.012
rily-0.012
Token,
Token ID11
Feature activation-1.70e-01

Pos logit contributions
chard+0.135
nam+0.131
ports+0.125
cher+0.123
 appet+0.122
Neg logit contributions
 night-0.041
 of-0.040
 end-0.039
 day-0.037
 eye-0.036
Token and
Token ID290
Feature activation+1.30e-01

Pos logit contributions
chard+0.010
nam+0.010
rily+0.010
ports+0.010
 appet+0.010
Neg logit contributions
 night-0.008
 day-0.008
 end-0.008
 eye-0.008
 of-0.008
Token told
Token ID1297
Feature activation+4.93e-01

Pos logit contributions
 night+0.006
 day+0.006
 end+0.006
 of+0.005
 eye+0.005
Neg logit contributions
 appet-0.008
rily-0.008
chard-0.008
nam-0.008
ports-0.008
Token sun
Token ID4252
Feature activation+7.64e+00

Pos logit contributions
rily+0.080
chard+0.080
 angrily+0.080
ked+0.079
nam+0.078
Neg logit contributions
 day-0.043
 night-0.043
 end-0.041
 eye-0.039
ama-0.038
Tokenflower
Token ID25547
Feature activation+3.38e-01

Pos logit contributions
 eye+0.360
opl+0.359
ama+0.356
 end+0.347
 night+0.340
Neg logit contributions
chard-0.408
rily-0.401
 handful-0.390
ked-0.375
 appet-0.355
Token that
Token ID326
Feature activation+2.70e+00

Pos logit contributions
ama+0.018
 end+0.018
 eye+0.017
oes+0.016
 night+0.016
Neg logit contributions
chard-0.017
 handful-0.015
rily-0.015
 appet-0.014
 donkey-0.014
Token followed
Token ID3940
Feature activation+1.12e+00

Pos logit contributions
 eye+0.147
ama+0.142
 end+0.137
opl+0.131
oes+0.130
Neg logit contributions
chard-0.151
nam-0.141
 appet-0.136
 handful-0.136
 oh-0.134
Token the
Token ID262
Feature activation+8.53e-01

Pos logit contributions
 night+0.047
 day+0.045
 of+0.041
 end+0.041
 eye+0.036
Neg logit contributions
chard-0.085
cher-0.084
 appet-0.081
nam-0.080
ked-0.080
Token sun
Token ID4252
Feature activation+8.29e+00

Pos logit contributions
ama+0.032
 eye+0.032
opl+0.030
 night+0.029
 end+0.029
Neg logit contributions
chard-0.059
nam-0.056
 donkey-0.053
 appet-0.053
 oh-0.053
Token everywhere
Token ID8347
Feature activation-4.29e-01

Pos logit contributions
 end+0.450
ama+0.447
opl+0.434
 eye+0.433
 night+0.411
Neg logit contributions
ked-0.410
rily-0.388
chard-0.388
 handful-0.363
ged-0.350
Token it
Token ID340
Feature activation-6.49e-01

Pos logit contributions
chard+0.028
 angrily+0.027
nam+0.027
rily+0.027
 appet+0.027
Neg logit contributions
 night-0.019
 day-0.018
 eye-0.018
 end-0.018
ama-0.018
Token went
Token ID1816
Feature activation+1.34e+00

Pos logit contributions
chard+0.037
 appet+0.035
 angrily+0.034
rily+0.034
 handful+0.034
Neg logit contributions
ama-0.034
 eye-0.030
opl-0.029
ummy-0.028
 end-0.028
Token.
Token ID13
Feature activation+3.88e-01

Pos logit contributions
 night+0.056
 eye+0.055
ama+0.055
 end+0.055
 day+0.054
Neg logit contributions
chard-0.090
 angrily-0.086
nam-0.086
rily-0.085
 appet-0.085
Token The
Token ID383
Feature activation+1.53e+00

Pos logit contributions
 night+0.021
 day+0.021
 eye+0.021
 end+0.021
ama+0.020
Neg logit contributions
chard-0.021
 angrily-0.020
nam-0.020
 appet-0.020
rily-0.020
Token are
Token ID389
Feature activation+5.93e-01

Pos logit contributions
chard+0.211
nam+0.203
 appet+0.202
 angrily+0.202
 oh+0.198
Neg logit contributions
 night-0.162
 day-0.158
 eye-0.157
ama-0.155
 end-0.155
Token you
Token ID345
Feature activation+7.88e-01

Pos logit contributions
 night+0.025
 day+0.025
 end+0.024
 eye+0.024
ama+0.024
Neg logit contributions
chard-0.040
 angrily-0.038
 appet-0.038
rily-0.038
nam-0.038
Token sad
Token ID6507
Feature activation-1.22e+00

Pos logit contributions
 night+0.045
 day+0.044
 eye+0.043
 end+0.043
ama+0.043
Neg logit contributions
chard-0.042
nam-0.040
 angrily-0.039
rily-0.039
 handful-0.038
Token?"
Token ID1701
Feature activation-3.88e+00

Pos logit contributions
chard+0.068
nam+0.064
 appet+0.063
 angrily+0.063
 handful+0.062
Neg logit contributions
 night-0.064
 eye-0.063
ama-0.062
 day-0.062
 end-0.061
Token The
Token ID383
Feature activation+1.43e+00

Pos logit contributions
chard+0.230
rily+0.223
nam+0.221
 appet+0.220
 angrily+0.220
Neg logit contributions
 night-0.201
 day-0.197
 end-0.190
 eye-0.188
ama-0.187
Token sun
Token ID4252
Feature activation+8.29e+00

Pos logit contributions
ama+0.055
issy+0.053
opl+0.051
iff+0.049
bars+0.049
Neg logit contributions
chard-0.090
 handful-0.084
 oh-0.082
 appet-0.081
 hello-0.080
Tokenflower
Token ID25547
Feature activation+4.08e-01

Pos logit contributions
 night+0.350
 eye+0.340
 end+0.338
 day+0.324
ama+0.323
Neg logit contributions
chard-0.526
 angrily-0.506
rily-0.502
 handful-0.499
 appet-0.494
Token said
Token ID531
Feature activation+1.03e+00

Pos logit contributions
 night+0.024
ama+0.024
 eye+0.024
opl+0.023
 day+0.023
Neg logit contributions
 angrily-0.019
chard-0.019
 oh-0.018
 handful-0.018
ked-0.017
Token,
Token ID11
Feature activation-1.80e-01

Pos logit contributions
 end+0.025
 of+0.024
 night+0.023
 day+0.023
ama+0.021
Neg logit contributions
chard-0.091
nam-0.090
 appet-0.088
rily-0.088
ports-0.087
Token "
Token ID366
Feature activation-4.50e+00

Pos logit contributions
nam+0.009
chard+0.009
 handful+0.009
 appet+0.009
 Edward+0.009
Neg logit contributions
 day-0.010
 night-0.010
 end-0.010
 of-0.009
ama-0.009
TokenI
Token ID40
Feature activation+2.13e-01

Pos logit contributions
chard+0.230
nam+0.209
 angrily+0.207
 oh+0.203
 appet+0.196
Neg logit contributions
 eye-0.284
 night-0.270
 end-0.269
ama-0.269
 day-0.255
Token hugged
Token ID41130
Feature activation+5.21e-01

Pos logit contributions
 night+0.000
 day+0.000
 end+0.000
 of+0.000
 eye+0.000
Neg logit contributions
rily-0.000
 appet-0.000
 Edward-0.000
chard-0.000
 handful-0.000
Token it
Token ID340
Feature activation-6.95e-01

Pos logit contributions
 night+0.029
 day+0.028
 end+0.027
 of+0.026
 eye+0.023
Neg logit contributions
chard-0.033
 appet-0.032
cher-0.032
chers-0.031
 Edward-0.030
Token tightly
Token ID17707
Feature activation+3.07e+00

Pos logit contributions
chard+0.037
 angrily+0.036
rily+0.036
 handful+0.035
nam+0.035
Neg logit contributions
ama-0.038
 night-0.037
 end-0.037
 eye-0.037
 day-0.036
Token.
Token ID13
Feature activation+7.64e-01

Pos logit contributions
 night+0.079
 day+0.074
 end+0.066
 eye+0.064
 of+0.064
Neg logit contributions
chard-0.266
nam-0.261
 appet-0.258
 oh-0.253
 Edward-0.252
Token The
Token ID383
Feature activation+1.61e+00

Pos logit contributions
 night+0.036
 day+0.036
ama+0.034
 eye+0.034
 end+0.033
Neg logit contributions
chard-0.049
nam-0.047
rily-0.047
 appet-0.046
 angrily-0.046
Token sun
Token ID4252
Feature activation+8.29e+00

Pos logit contributions
ama+0.062
opl+0.057
 night+0.056
 eye+0.053
el+0.053
Neg logit contributions
chard-0.113
 oh-0.106
 appet-0.105
 angrily-0.104
nam-0.104
Tokenflower
Token ID25547
Feature activation+4.21e-01

Pos logit contributions
opl+0.380
 night+0.373
 end+0.371
 eye+0.371
ama+0.366
Neg logit contributions
chard-0.496
ked-0.489
 angrily-0.466
rily-0.464
 handful-0.464
Token felt
Token ID2936
Feature activation-1.91e+00

Pos logit contributions
ama+0.025
oes+0.024
opl+0.024
ummy+0.023
 eye+0.023
Neg logit contributions
 angrily-0.021
chard-0.020
ked-0.019
 oh-0.019
 handful-0.019
Token safe
Token ID3338
Feature activation+9.30e-01

Pos logit contributions
chard+0.097
 angrily+0.093
nam+0.092
 appet+0.091
rily+0.090
Neg logit contributions
ama-0.111
 night-0.110
 day-0.108
 eye-0.108
 end-0.105
Token and
Token ID290
Feature activation+1.39e-02

Pos logit contributions
 night+0.038
 day+0.037
 end+0.036
 eye+0.036
ama+0.034
Neg logit contributions
chard-0.065
nam-0.062
 angrily-0.062
 appet-0.062
rily-0.061
Token loved
Token ID6151
Feature activation+7.79e-01

Pos logit contributions
ama+0.001
 eye+0.001
 night+0.001
 end+0.001
 day+0.001
Neg logit contributions
chard-0.001
nam-0.001
 angrily-0.001
 oh-0.001
 appet-0.001
Token it
Token ID340
Feature activation-7.20e-01

Pos logit contributions
chard+0.041
 angrily+0.038
nam+0.038
 appet+0.038
rily+0.037
Neg logit contributions
 night-0.072
 day-0.071
 end-0.070
 eye-0.070
ama-0.069
Token every
Token ID790
Feature activation+3.13e+00

Pos logit contributions
chard+0.046
 angrily+0.044
nam+0.044
rily+0.044
 appet+0.044
Neg logit contributions
 night-0.033
 day-0.032
 eye-0.032
 end-0.032
ama-0.031
Token day
Token ID1110
Feature activation+3.09e+00

Pos logit contributions
ama+0.094
opl+0.086
father+0.057
oes+0.055
ummy+0.054
Neg logit contributions
chard-0.252
 handful-0.249
 oh-0.232
rily-0.228
nam-0.222
Token.
Token ID13
Feature activation+5.69e-01

Pos logit contributions
 night+0.123
 end+0.122
 eye+0.121
ama+0.120
 day+0.117
Neg logit contributions
chard-0.213
 angrily-0.203
nam-0.203
rily-0.202
 appet-0.199
Token The
Token ID383
Feature activation+1.46e+00

Pos logit contributions
 night+0.028
 day+0.027
 eye+0.027
 end+0.027
ama+0.026
Neg logit contributions
chard-0.035
nam-0.033
 angrily-0.033
 appet-0.033
rily-0.033
Token sun
Token ID4252
Feature activation+8.29e+00

Pos logit contributions
opl+0.060
ama+0.056
umbles+0.055
bars+0.054
issy+0.053
Neg logit contributions
 appet-0.084
 oh-0.080
 handful-0.077
chard-0.077
 Hi-0.073
Tokenflower
Token ID25547
Feature activation+4.41e-01

Pos logit contributions
opl+0.377
 eye+0.372
 end+0.372
 night+0.367
ama+0.362
Neg logit contributions
chard-0.465
ked-0.457
 handful-0.454
rily-0.452
 appet-0.447
Token started
Token ID2067
Feature activation+2.90e+00

Pos logit contributions
ama+0.024
 eye+0.024
opl+0.023
oes+0.023
 end+0.023
Neg logit contributions
 angrily-0.021
chard-0.021
 handful-0.021
 appet-0.020
rily-0.020
Token to
Token ID284
Feature activation-2.44e-01

Pos logit contributions
 end+0.167
ama+0.163
 eye+0.158
 night+0.154
 day+0.153
Neg logit contributions
 handful-0.146
 angrily-0.146
chard-0.144
rily-0.140
ked-0.138
Token grow
Token ID1663
Feature activation+2.02e+00

Pos logit contributions
chard+0.014
nam+0.013
 appet+0.013
 handful+0.013
 angrily+0.013
Neg logit contributions
ama-0.013
 day-0.012
 night-0.012
 eye-0.012
 of-0.011
Token bigger
Token ID5749
Feature activation-1.91e+00

Pos logit contributions
 night+0.084
 day+0.081
 end+0.080
 eye+0.079
ama+0.077
Neg logit contributions
chard-0.140
nam-0.135
 angrily-0.133
 appet-0.132
rily-0.131
Token are
Token ID389
Feature activation+6.04e-01

Pos logit contributions
chard+0.244
 appet+0.237
 handful+0.235
nam+0.235
 angrily+0.232
Neg logit contributions
ama-0.190
 day-0.181
 night-0.181
 eye-0.174
 end-0.173
Token very
Token ID845
Feature activation-3.11e+00

Pos logit contributions
 night+0.034
 day+0.033
 end+0.032
 eye+0.031
 of+0.031
Neg logit contributions
chard-0.033
rily-0.033
 angrily-0.033
 appet-0.032
ked-0.032
Token pretty
Token ID2495
Feature activation+1.26e+00

Pos logit contributions
chard+0.169
nam+0.160
 appet+0.157
 angrily+0.155
 handful+0.154
Neg logit contributions
 night-0.175
 end-0.172
 eye-0.172
 day-0.168
ama-0.165
Token!"
Token ID2474
Feature activation-4.21e+00

Pos logit contributions
 night+0.057
 day+0.054
 of+0.053
 eye+0.052
 end+0.052
Neg logit contributions
chard-0.086
nam-0.082
 angrily-0.082
ked-0.080
 Edward-0.079
Token The
Token ID383
Feature activation+1.49e+00

Pos logit contributions
chard+0.271
rily+0.267
 appet+0.262
nam+0.261
 handful+0.258
Neg logit contributions
 night-0.198
 day-0.194
 eye-0.184
 of-0.180
 end-0.180
Token sun
Token ID4252
Feature activation+8.29e+00

Pos logit contributions
opl+0.069
ama+0.067
 night+0.064
oes+0.060
el+0.060
Neg logit contributions
chard-0.091
 handful-0.084
 appet-0.083
nam-0.082
 oh-0.082
Tokenflower
Token ID25547
Feature activation+3.65e-01

Pos logit contributions
 night+0.338
 end+0.325
 eye+0.324
ama+0.317
 day+0.315
Neg logit contributions
chard-0.543
 angrily-0.521
 handful-0.521
rily-0.520
 appet-0.519
Token smiled
Token ID13541
Feature activation-5.99e-01

Pos logit contributions
 night+0.021
ama+0.021
 eye+0.021
 day+0.020
 end+0.020
Neg logit contributions
 angrily-0.018
chard-0.017
 appet-0.017
 handful-0.017
rily-0.016
Token and
Token ID290
Feature activation+2.54e-01

Pos logit contributions
chard+0.042
 angrily+0.040
nam+0.040
 appet+0.040
rily+0.040
Neg logit contributions
 night-0.024
 day-0.023
 eye-0.023
 end-0.023
ama-0.023
Token said
Token ID531
Feature activation+9.99e-01

Pos logit contributions
 night+0.010
 day+0.010
 eye+0.009
 end+0.008
 of+0.008
Neg logit contributions
rily-0.018
chard-0.018
 angrily-0.018
nam-0.018
 appet-0.018
Token,
Token ID11
Feature activation-1.59e-01

Pos logit contributions
 of+0.013
 end+0.010
 day+0.010
 night+0.009
ama+0.006
Neg logit contributions
chard-0.100
Roger-0.099
nam-0.098
ports-0.098
rily-0.097
Token.
Token ID13
Feature activation+5.65e-01

Pos logit contributions
 night+0.042
 day+0.041
 end+0.039
 eye+0.038
ama+0.038
Neg logit contributions
chard-0.045
rily-0.043
 appet-0.043
nam-0.043
 angrily-0.042
Token The
Token ID383
Feature activation+1.52e+00

Pos logit contributions
 night+0.028
 day+0.027
 eye+0.026
 end+0.026
ama+0.026
Neg logit contributions
chard-0.035
 angrily-0.033
nam-0.033
 appet-0.033
rily-0.033
Token boy
Token ID2933
Feature activation-2.95e+00

Pos logit contributions
ama+0.076
 night+0.071
opl+0.070
 eye+0.068
el+0.068
Neg logit contributions
chard-0.090
 appet-0.085
nam-0.083
 oh-0.083
 handful-0.082
Token and
Token ID290
Feature activation+3.28e-02

Pos logit contributions
chard+0.162
 angrily+0.156
 appet+0.152
nam+0.150
ked+0.149
Neg logit contributions
ama-0.157
 night-0.157
 day-0.153
 end-0.153
 eye-0.152
Token the
Token ID262
Feature activation+7.82e-01

Pos logit contributions
 night+0.002
 day+0.002
 end+0.002
 eye+0.002
 of+0.002
Neg logit contributions
chard-0.002
rily-0.002
 appet-0.002
 angrily-0.002
 Edward-0.002
Token sun
Token ID4252
Feature activation+8.28e+00

Pos logit contributions
ama+0.036
 night+0.035
 eye+0.034
 day+0.033
 end+0.033
Neg logit contributions
chard-0.050
nam-0.046
 angrily-0.046
 oh-0.046
 appet-0.046
Tokenflower
Token ID25547
Feature activation+4.05e-01

Pos logit contributions
opl+0.428
 end+0.393
ama+0.386
 eye+0.385
 night+0.380
Neg logit contributions
ked-0.484
 handful-0.446
rily-0.440
chard-0.437
ged-0.436
Token spent
Token ID3377
Feature activation-1.43e+00

Pos logit contributions
ama+0.024
ummy+0.023
opl+0.023
oes+0.023
 eye+0.022
Neg logit contributions
ked-0.019
 angrily-0.018
chard-0.018
 handful-0.018
 aimed-0.017
Token every
Token ID790
Feature activation+2.93e+00

Pos logit contributions
chard+0.098
cher+0.098
rily+0.096
 angrily+0.092
 appet+0.092
Neg logit contributions
 day-0.074
 night-0.074
 end-0.068
 of-0.060
 eye-0.059
Token day
Token ID1110
Feature activation+3.04e+00

Pos logit contributions
ama+0.032
 eye+0.027
 night+0.023
 end+0.021
 day+0.016
Neg logit contributions
chard-0.290
 handful-0.279
 angrily-0.278
 appet-0.277
nam-0.277
Token together
Token ID1978
Feature activation-2.31e+00

Pos logit contributions
 night+0.167
 day+0.164
 end+0.160
 eye+0.159
ama+0.156
Neg logit contributions
chard-0.167
 angrily-0.158
rily-0.158
nam-0.157
 appet-0.157
Token like
Token ID588
Feature activation-1.83e+00

Pos logit contributions
 night+0.227
 day+0.221
ama+0.220
 end+0.220
 eye+0.219
Neg logit contributions
chard-0.176
 angrily-0.167
nam-0.166
 appet-0.165
rily-0.163
Token the
Token ID262
Feature activation+6.60e-01

Pos logit contributions
chard+0.091
 appet+0.086
 angrily+0.086
rily+0.086
nam+0.085
Neg logit contributions
 night-0.111
 day-0.109
 end-0.107
 eye-0.105
ama-0.104
Token bunny
Token ID44915
Feature activation-2.68e+00

Pos logit contributions
ama+0.019
opl+0.016
 eye+0.016
 night+0.015
oes+0.015
Neg logit contributions
chard-0.053
 handful-0.050
nam-0.050
 Edward-0.049
 Percy-0.049
Token.
Token ID13
Feature activation+5.44e-01

Pos logit contributions
chard+0.181
 angrily+0.174
nam+0.173
 appet+0.173
rily+0.172
Neg logit contributions
 night-0.112
 day-0.108
 eye-0.107
 end-0.107
ama-0.105
Token The
Token ID383
Feature activation+1.41e+00

Pos logit contributions
 night+0.033
 end+0.032
 eye+0.032
 day+0.032
ama+0.031
Neg logit contributions
chard-0.027
 angrily-0.026
 appet-0.025
rily-0.025
nam-0.025
Token sun
Token ID4252
Feature activation+8.28e+00

Pos logit contributions
ama+0.044
opl+0.042
oes+0.039
 of+0.037
 eye+0.037
Neg logit contributions
chard-0.109
 handful-0.102
nam-0.100
 appet-0.100
 donkey-0.099
Tokenflower
Token ID25547
Feature activation+4.00e-01

Pos logit contributions
 night+0.367
 end+0.365
 eye+0.359
opl+0.353
ama+0.353
Neg logit contributions
chard-0.505
ked-0.502
 handful-0.484
rily-0.479
 angrily-0.465
Token was
Token ID373
Feature activation+7.43e-01

Pos logit contributions
ama+0.023
ummy+0.023
oes+0.022
 eye+0.022
 end+0.021
Neg logit contributions
 angrily-0.018
 aimed-0.018
 handful-0.018
ked-0.018
 dodged-0.018
Token so
Token ID523
Feature activation-2.49e+00

Pos logit contributions
 night+0.044
ama+0.044
 eye+0.043
 end+0.043
 day+0.043
Neg logit contributions
chard-0.037
 angrily-0.035
nam-0.034
 handful-0.034
rily-0.034
Token happy
Token ID3772
Feature activation-1.73e+00

Pos logit contributions
chard+0.091
nam+0.089
 handful+0.087
 Percy+0.084
 appet+0.084
Neg logit contributions
 eye-0.180
ama-0.175
 end-0.171
 night-0.169
oes-0.166
Token and
Token ID290
Feature activation-1.15e-03

Pos logit contributions
chard+0.125
nam+0.120
rily+0.118
 angrily+0.118
 appet+0.118
Neg logit contributions
 night-0.069
 day-0.066
 end-0.064
 eye-0.063
ama-0.061
TokenLet
Token ID5756
Feature activation-1.66e+00

Pos logit contributions
chard+0.188
 oh+0.176
 appet+0.175
 angrily+0.175
nam+0.174
Neg logit contributions
 eye-0.312
 night-0.309
ama-0.305
 end-0.304
 day-0.299
Token's
Token ID338
Feature activation+3.60e+00

Pos logit contributions
 oh+0.092
 angrily+0.092
 handful+0.085
 Freddie+0.084
 Edward+0.084
Neg logit contributions
 eye-0.081
oes-0.080
opl-0.079
ama-0.078
 night-0.076
Token plant
Token ID4618
Feature activation+1.31e+00

Pos logit contributions
ama+0.167
opl+0.162
oes+0.158
 night+0.155
ummy+0.152
Neg logit contributions
chard-0.211
nam-0.200
 angrily-0.198
 oh-0.197
 handful-0.194
Token some
Token ID617
Feature activation+5.92e-01

Pos logit contributions
 night+0.082
 day+0.080
 end+0.080
 eye+0.079
ama+0.077
Neg logit contributions
chard-0.063
nam-0.061
 angrily-0.059
 appet-0.059
rily-0.059
Token more
Token ID517
Feature activation+1.52e+00

Pos logit contributions
ama+0.033
 night+0.031
opl+0.030
 eye+0.030
oes+0.030
Neg logit contributions
chard-0.030
 handful-0.030
 appet-0.030
nam-0.029
 oh-0.029
Token sun
Token ID4252
Feature activation+8.28e+00

Pos logit contributions
ama+0.080
 end+0.078
 eye+0.074
 night+0.072
opl+0.071
Neg logit contributions
chard-0.082
 appet-0.082
 handful-0.079
rily-0.079
 angrily-0.077
Tokenfl
Token ID2704
Feature activation-7.43e-01

Pos logit contributions
 end+0.443
 night+0.429
ama+0.417
 eye+0.415
 day+0.401
Neg logit contributions
ked-0.414
 appet-0.405
chard-0.396
 handful-0.391
rily-0.386
Tokenowers
Token ID3618
Feature activation+8.54e-01

Pos logit contributions
 handful+0.030
ked+0.030
 appet+0.029
rily+0.029
ged+0.027
Neg logit contributions
 end-0.052
 night-0.048
 eye-0.046
 day-0.046
 parent-0.045
Token,
Token ID11
Feature activation-3.72e-02

Pos logit contributions
ama+0.051
 end+0.050
 eye+0.049
 night+0.049
 day+0.048
Neg logit contributions
chard-0.041
 appet-0.041
 handful-0.038
rily-0.038
nam-0.037
Token and
Token ID290
Feature activation+1.10e-01

Pos logit contributions
chard+0.002
 angrily+0.002
nam+0.002
rily+0.002
 appet+0.002
Neg logit contributions
 night-0.002
 day-0.002
 end-0.002
 eye-0.002
ama-0.002
Token we
Token ID356
Feature activation+8.36e-01

Pos logit contributions
 night+0.006
 day+0.006
 eye+0.006
 end+0.006
ama+0.006
Neg logit contributions
chard-0.006
nam-0.006
 angrily-0.006
 appet-0.006
rily-0.006
Token seen
Token ID1775
Feature activation+9.80e-01

Pos logit contributions
ama+0.129
 eye+0.118
 end+0.118
 night+0.118
 day+0.116
Neg logit contributions
chard-0.107
 appet-0.103
nam-0.099
 angrily-0.098
 handful-0.096
Token!"
Token ID2474
Feature activation-4.96e+00

Pos logit contributions
 night+0.049
 day+0.047
 end+0.045
 of+0.045
 eye+0.044
Neg logit contributions
chard-0.061
nam-0.059
 angrily-0.059
 appet-0.058
rily-0.057
Token
Token ID198
Feature activation+4.75e-01

Pos logit contributions
chard+0.336
rily+0.336
 appet+0.332
nam+0.326
 handful+0.325
Neg logit contributions
 night-0.214
 day-0.209
 end-0.197
 eye-0.192
 of-0.188
Token
Token ID198
Feature activation+4.78e-01

Pos logit contributions
 night+0.020
 eye+0.020
 day+0.019
 end+0.019
ama+0.019
Neg logit contributions
chard-0.032
 angrily-0.031
nam-0.030
rily-0.030
 appet-0.030
TokenThe
Token ID464
Feature activation+1.49e+00

Pos logit contributions
 end+0.020
 day+0.020
 night+0.020
ama+0.019
 eye+0.018
Neg logit contributions
chard-0.032
rily-0.031
nam-0.031
 appet-0.031
 handful-0.031
Token sun
Token ID4252
Feature activation+8.27e+00

Pos logit contributions
ama+0.054
oes+0.052
opl+0.051
 night+0.051
 eye+0.050
Neg logit contributions
chard-0.100
 appet-0.093
 donkey-0.091
 handful-0.090
 oh-0.090
Tokenflower
Token ID25547
Feature activation+2.67e-01

Pos logit contributions
 night+0.366
 eye+0.348
 end+0.347
 day+0.337
ama+0.332
Neg logit contributions
chard-0.496
rily-0.487
 angrily-0.485
 handful-0.483
ked-0.477
Token smiled
Token ID13541
Feature activation-5.73e-01

Pos logit contributions
 night+0.015
ama+0.015
 eye+0.014
 end+0.014
oes+0.014
Neg logit contributions
 angrily-0.014
chard-0.013
rily-0.013
 handful-0.012
 appet-0.012
Token and
Token ID290
Feature activation+2.27e-01

Pos logit contributions
chard+0.040
nam+0.039
 angrily+0.038
 appet+0.038
rily+0.038
Neg logit contributions
 night-0.023
 day-0.022
 eye-0.022
 end-0.022
ama-0.021
Token nodded
Token ID14464
Feature activation-6.56e-01

Pos logit contributions
 night+0.010
 day+0.009
 eye+0.009
 end+0.008
 of+0.008
Neg logit contributions
chard-0.016
rily-0.015
nam-0.015
 appet-0.015
 angrily-0.015
Token her
Token ID607
Feature activation+6.15e-01

Pos logit contributions
chard+0.053
nam+0.052
ports+0.051
 appet+0.050
 bluff+0.050
Neg logit contributions
 night-0.021
 end-0.020
 day-0.020
 of-0.019
 eye-0.018
TokenListen
Token ID23061
Feature activation-2.37e+00

Pos logit contributions
chard+0.171
 angrily+0.156
nam+0.156
 appet+0.155
 oh+0.153
Neg logit contributions
 night-0.322
 eye-0.320
ama-0.316
 day-0.315
 end-0.312
Token!
Token ID0
Feature activation-9.05e-01

Pos logit contributions
nam+0.186
chard+0.184
rob+0.177
ged+0.177
ked+0.175
Neg logit contributions
 night-0.087
 day-0.083
ama-0.074
 end-0.072
 of-0.072
Token I
Token ID314
Feature activation-5.57e-01

Pos logit contributions
chard+0.044
 angrily+0.041
nam+0.041
 appet+0.041
rily+0.041
Neg logit contributions
 night-0.056
 day-0.054
 end-0.054
 eye-0.054
ama-0.053
Token think
Token ID892
Feature activation+2.78e-01

Pos logit contributions
 angrily+0.031
 appet+0.031
chard+0.030
 handful+0.029
 Percy+0.029
Neg logit contributions
 night-0.028
ama-0.028
 day-0.027
 end-0.027
 eye-0.027
Token the
Token ID262
Feature activation+6.45e-01

Pos logit contributions
 night+0.016
 day+0.016
 eye+0.016
 end+0.016
ama+0.016
Neg logit contributions
chard-0.014
 angrily-0.013
nam-0.013
 appet-0.013
rily-0.013
Token sun
Token ID4252
Feature activation+8.27e+00

Pos logit contributions
ama+0.019
 night+0.017
 of+0.016
opl+0.016
oes+0.016
Neg logit contributions
chard-0.048
 appet-0.046
 handful-0.046
 angrily-0.045
 oh-0.045
Tokenflower
Token ID25547
Feature activation+2.94e-01

Pos logit contributions
 night+0.386
 end+0.383
 eye+0.381
ama+0.366
 day+0.360
Neg logit contributions
chard-0.461
 appet-0.452
rily-0.446
 handful-0.444
ked-0.436
Token is
Token ID318
Feature activation+1.14e+00

Pos logit contributions
 night+0.014
ama+0.014
 end+0.014
 eye+0.014
 day+0.013
Neg logit contributions
chard-0.017
 appet-0.017
 angrily-0.017
rily-0.016
 handful-0.016
Token talking
Token ID3375
Feature activation-1.64e+00

Pos logit contributions
 night+0.061
 day+0.060
 eye+0.059
 end+0.059
ama+0.059
Neg logit contributions
chard-0.063
 angrily-0.060
nam-0.060
 appet-0.060
rily-0.060
Token to
Token ID284
Feature activation-3.05e-01

Pos logit contributions
chard+0.108
nam+0.105
 angrily+0.101
rily+0.101
 appet+0.100
Neg logit contributions
 night-0.077
 day-0.075
 of-0.071
 end-0.071
 eye-0.069
Token us
Token ID514
Feature activation+1.48e+00

Pos logit contributions
chard+0.019
 angrily+0.018
nam+0.018
 appet+0.018
rily+0.018
Neg logit contributions
 night-0.014
 eye-0.014
ama-0.013
 day-0.013
 end-0.013
Tokenily
Token ID813
Feature activation+4.22e-01

Pos logit contributions
 night+0.007
 day+0.007
 end+0.007
 eye+0.007
ama+0.007
Neg logit contributions
chard-0.008
nam-0.007
 angrily-0.007
 appet-0.007
rily-0.007
Token insisted
Token ID11189
Feature activation-8.95e-01

Pos logit contributions
 night+0.023
ama+0.022
 day+0.022
opl+0.022
 end+0.022
Neg logit contributions
 angrily-0.022
 appet-0.022
chard-0.021
ked-0.021
 aimed-0.020
Token on
Token ID319
Feature activation-3.51e+00

Pos logit contributions
chard+0.054
 angrily+0.053
nam+0.052
rily+0.051
 appet+0.051
Neg logit contributions
 night-0.043
 eye-0.042
 day-0.041
 end-0.041
ama-0.040
Token keeping
Token ID5291
Feature activation-3.09e-01

Pos logit contributions
chard+0.171
nam+0.166
 angrily+0.165
 oh+0.162
 handful+0.159
Neg logit contributions
 night-0.205
ama-0.203
 eye-0.203
 day-0.201
 end-0.200
Token the
Token ID262
Feature activation+8.39e-01

Pos logit contributions
chard+0.018
 appet+0.017
 angrily+0.017
rily+0.017
ked+0.017
Neg logit contributions
 night-0.017
 day-0.016
 eye-0.016
 end-0.016
ama-0.015
Token sun
Token ID4252
Feature activation+8.26e+00

Pos logit contributions
bars+0.032
ama+0.031
opl+0.030
iff+0.029
umbles+0.027
Neg logit contributions
chard-0.051
 handful-0.050
 appet-0.048
 oh-0.047
 hi-0.045
Tokenflower
Token ID25547
Feature activation+4.28e-01

Pos logit contributions
opl+0.377
 end+0.372
 night+0.369
ama+0.366
 eye+0.365
Neg logit contributions
chard-0.478
 handful-0.458
rily-0.453
ked-0.439
nam-0.436
Token in
Token ID287
Feature activation-1.39e+00

Pos logit contributions
ama+0.025
opl+0.024
 end+0.023
 night+0.023
oes+0.023
Neg logit contributions
chard-0.022
 handful-0.020
nam-0.020
 appet-0.019
rily-0.019
Token her
Token ID607
Feature activation+7.19e-01

Pos logit contributions
nam+0.056
chard+0.053
 handful+0.051
 oh+0.050
 angrily+0.046
Neg logit contributions
ama-0.098
oes-0.094
 eye-0.088
opl-0.087
 night-0.086
Token room
Token ID2119
Feature activation+1.89e+00

Pos logit contributions
oes+0.032
ama+0.031
opl+0.031
 of+0.031
 end+0.029
Neg logit contributions
chard-0.044
nam-0.043
 oh-0.043
 handful-0.042
 appet-0.041
Token.
Token ID13
Feature activation+4.66e-01

Pos logit contributions
ama+0.081
 night+0.079
 eye+0.076
 day+0.075
 end+0.074
Neg logit contributions
chard-0.122
 angrily-0.119
nam-0.117
 appet-0.116
rily-0.115
TokenThat
Token ID2504
Feature activation-1.56e+00

Pos logit contributions
chard+0.209
nam+0.195
 angrily+0.195
rily+0.193
 appet+0.193
Neg logit contributions
 night-0.295
 day-0.288
 eye-0.288
 end-0.285
ama-0.284
Token's
Token ID338
Feature activation+3.50e+00

Pos logit contributions
chard+0.100
 appet+0.097
 angrily+0.097
 oh+0.096
 handful+0.095
Neg logit contributions
ama-0.063
 eye-0.063
 night-0.062
 day-0.059
 end-0.059
Token the
Token ID262
Feature activation+7.15e-01

Pos logit contributions
 night+0.187
 day+0.184
 end+0.183
 eye+0.171
ama+0.162
Neg logit contributions
chard-0.210
rily-0.209
ked-0.206
 angrily-0.206
ged-0.205
Token most
Token ID749
Feature activation-1.65e+00

Pos logit contributions
ama+0.024
 of+0.022
bars+0.021
 eye+0.020
el+0.020
Neg logit contributions
chard-0.047
 Claw-0.046
 Edward-0.045
 donkey-0.045
 Percy-0.045
Token attractive
Token ID10966
Feature activation-4.08e-01

Pos logit contributions
chard+0.086
 appet+0.084
 angrily+0.083
rily+0.082
 handful+0.081
Neg logit contributions
 end-0.090
 night-0.090
 eye-0.090
ama-0.089
 day-0.085
Token sun
Token ID4252
Feature activation+8.26e+00

Pos logit contributions
chard+0.024
 handful+0.024
 oh+0.023
rily+0.023
 appet+0.023
Neg logit contributions
ama-0.018
 night-0.018
 end-0.017
 eye-0.017
 day-0.016
Tokenflower
Token ID25547
Feature activation+2.99e-01

Pos logit contributions
 eye+0.346
 end+0.345
 night+0.345
ama+0.324
 day+0.316
Neg logit contributions
chard-0.530
rily-0.510
 appet-0.506
 oh-0.500
 handful-0.499
Token I
Token ID314
Feature activation-6.02e-01

Pos logit contributions
 end+0.015
 eye+0.015
 night+0.015
ama+0.015
 day+0.014
Neg logit contributions
chard-0.017
 appet-0.016
rily-0.016
 angrily-0.016
 handful-0.016
Token've
Token ID1053
Feature activation-1.84e+00

Pos logit contributions
chard+0.030
 appet+0.029
 angrily+0.028
 handful+0.028
 Edward+0.027
Neg logit contributions
ama-0.035
 night-0.034
 day-0.033
 end-0.033
 eye-0.033
Token ever
Token ID1683
Feature activation+2.11e+00

Pos logit contributions
chard+0.125
 appet+0.120
 angrily+0.119
nam+0.117
 oh+0.117
Neg logit contributions
ama-0.075
 eye-0.072
 night-0.071
 end-0.071
 day-0.069
Token seen
Token ID1775
Feature activation+9.80e-01

Pos logit contributions
ama+0.129
 eye+0.118
 end+0.118
 night+0.118
 day+0.116
Neg logit contributions
chard-0.107
 appet-0.103
nam-0.099
 angrily-0.098
 handful-0.096
Token She
Token ID1375
Feature activation-1.05e-01

Pos logit contributions
chard+0.081
nam+0.078
 appet+0.077
rily+0.077
 angrily+0.077
Neg logit contributions
 night-0.054
 day-0.052
 eye-0.051
 end-0.051
ama-0.050
Token had
Token ID550
Feature activation+1.09e+00

Pos logit contributions
chard+0.006
nam+0.006
 appet+0.006
rily+0.006
 angrily+0.006
Neg logit contributions
 night-0.005
 day-0.005
 end-0.005
 eye-0.005
ama-0.005
Token never
Token ID1239
Feature activation+4.67e+00

Pos logit contributions
ama+0.056
 night+0.056
 day+0.055
 eye+0.054
 end+0.054
Neg logit contributions
chard-0.063
 angrily-0.061
 handful-0.060
nam-0.060
 Edward-0.058
Token tasted
Token ID29187
Feature activation-2.55e+00

Pos logit contributions
ama+0.291
 night+0.273
 end+0.267
 day+0.267
 eye+0.265
Neg logit contributions
chard-0.237
nam-0.220
 angrily-0.213
 appet-0.212
 handful-0.209
Token a
Token ID257
Feature activation-1.44e+00

Pos logit contributions
chard+0.127
 appet+0.123
cher+0.123
nam+0.122
 angrily+0.122
Neg logit contributions
 night-0.156
 day-0.151
 end-0.149
 eye-0.148
 of-0.144
Token sun
Token ID4252
Feature activation+8.26e+00

Pos logit contributions
chard+0.080
 angrily+0.076
nam+0.076
 appet+0.076
rily+0.075
Neg logit contributions
 night-0.077
 day-0.075
 eye-0.074
 end-0.074
ama-0.074
Tokenflower
Token ID25547
Feature activation+3.49e-01

Pos logit contributions
 night+0.346
 day+0.329
ama+0.325
 end+0.322
 eye+0.315
Neg logit contributions
chard-0.538
rily-0.530
 handful-0.521
ked-0.509
 angrily-0.497
Token before
Token ID878
Feature activation-3.56e-01

Pos logit contributions
 night+0.018
ama+0.017
 day+0.017
 eye+0.017
 end+0.017
Neg logit contributions
chard-0.020
 angrily-0.019
rily-0.019
 appet-0.019
 handful-0.019
Token but
Token ID475
Feature activation-1.52e+00

Pos logit contributions
chard+0.022
 angrily+0.022
rily+0.021
 Edward+0.021
 handful+0.021
Neg logit contributions
 eye-0.016
 night-0.015
 end-0.015
ama-0.015
 day-0.015
Token she
Token ID673
Feature activation+6.77e-01

Pos logit contributions
chard+0.081
nam+0.077
 angrily+0.076
 oh+0.073
 appet+0.073
Neg logit contributions
 night-0.085
ama-0.085
 eye-0.084
 day-0.083
 end-0.081
Token knew
Token ID2993
Feature activation+4.80e-01

Pos logit contributions
 night+0.032
 day+0.031
ama+0.031
 eye+0.031
 end+0.030
Neg logit contributions
chard-0.042
 angrily-0.041
 appet-0.039
rily-0.039
nam-0.039
Token sad
Token ID6507
Feature activation-1.25e+00

Pos logit contributions
ama+0.043
 night+0.042
 eye+0.042
 end+0.042
oes+0.041
Neg logit contributions
chard-0.041
nam-0.037
 angrily-0.037
rily-0.037
 handful-0.036
Token.
Token ID13
Feature activation+5.11e-01

Pos logit contributions
 angrily+0.063
chard+0.061
 appet+0.060
 oh+0.059
 handful+0.059
Neg logit contributions
ama-0.071
opl-0.070
 eye-0.062
 end-0.060
 night-0.060
Token Tim
Token ID5045
Feature activation+9.57e-01

Pos logit contributions
 day+0.025
 night+0.025
 of+0.024
ama+0.024
 eye+0.023
Neg logit contributions
rily-0.031
chard-0.031
nam-0.030
 handful-0.030
 appet-0.030
Token asked
Token ID1965
Feature activation+3.03e+00

Pos logit contributions
 night+0.051
 day+0.050
ama+0.050
 eye+0.050
 end+0.049
Neg logit contributions
chard-0.053
 angrily-0.051
 appet-0.050
nam-0.050
rily-0.049
Token the
Token ID262
Feature activation+6.63e-01

Pos logit contributions
 end+0.147
 day+0.146
 night+0.143
 of+0.139
 last+0.120
Neg logit contributions
rily-0.224
 appet-0.213
chard-0.211
ked-0.207
nam-0.206
Token sun
Token ID4252
Feature activation+8.25e+00

Pos logit contributions
ama+0.032
opl+0.032
 eye+0.031
el+0.031
 night+0.030
Neg logit contributions
chard-0.039
 Claw-0.034
 bluff-0.034
 oh-0.033
 donkey-0.033
Tokenflower
Token ID25547
Feature activation+3.76e-01

Pos logit contributions
 night+0.379
opl+0.352
 eye+0.351
 day+0.342
 end+0.333
Neg logit contributions
chard-0.510
 handful-0.482
ked-0.470
rily-0.466
 oh-0.461
Token,
Token ID11
Feature activation-2.35e-01

Pos logit contributions
 night+0.018
 eye+0.017
 day+0.017
ama+0.017
 end+0.016
Neg logit contributions
chard-0.024
 angrily-0.022
nam-0.022
 handful-0.022
 appet-0.022
Token "
Token ID366
Feature activation-4.48e+00

Pos logit contributions
rily+0.013
heit+0.013
 appet+0.013
chard+0.013
 Edward+0.012
Neg logit contributions
 day-0.013
 of-0.013
 night-0.013
 end-0.013
 last-0.011
TokenWhy
Token ID5195
Feature activation-3.47e+00

Pos logit contributions
chard+0.186
 angrily+0.181
rily+0.181
nam+0.179
 appet+0.179
Neg logit contributions
 night-0.303
 end-0.299
 day-0.297
 eye-0.288
ama-0.284
Token are
Token ID389
Feature activation+5.93e-01

Pos logit contributions
chard+0.211
nam+0.203
 appet+0.202
 angrily+0.202
 oh+0.198
Neg logit contributions
 night-0.162
 day-0.158
 eye-0.157
ama-0.155
 end-0.155
Token big
Token ID1263
Feature activation+1.52e+00

Pos logit contributions
ama+0.019
 eye+0.018
 of+0.017
 night+0.017
oes+0.017
Neg logit contributions
chard-0.038
 appet-0.036
 handful-0.036
 Edward-0.035
 angrily-0.035
Token field
Token ID2214
Feature activation-3.71e-01

Pos logit contributions
ama+0.073
oes+0.065
 eye+0.063
 night+0.061
 end+0.060
Neg logit contributions
 handful-0.091
chard-0.090
 appet-0.087
 Percy-0.083
 donkey-0.083
Token and
Token ID290
Feature activation-1.54e-01

Pos logit contributions
chard+0.023
 angrily+0.022
rily+0.022
 handful+0.022
 appet+0.021
Neg logit contributions
ama-0.017
 night-0.016
 eye-0.016
 end-0.016
 day-0.015
Token followed
Token ID3940
Feature activation+9.23e-01

Pos logit contributions
chard+0.009
 angrily+0.008
nam+0.008
 appet+0.008
rily+0.008
Neg logit contributions
 night-0.008
 day-0.008
 eye-0.008
 end-0.008
ama-0.008
Token the
Token ID262
Feature activation+5.26e-01

Pos logit contributions
 night+0.057
 day+0.055
 end+0.053
 of+0.052
 eye+0.051
Neg logit contributions
chard-0.049
 appet-0.048
nam-0.047
 bluff-0.046
cher-0.046
Token sun
Token ID4252
Feature activation+8.25e+00

Pos logit contributions
ama+0.020
 eye+0.019
 night+0.018
opl+0.018
 of+0.017
Neg logit contributions
chard-0.036
 appet-0.035
 angrily-0.034
 handful-0.034
nam-0.034
Token together
Token ID1978
Feature activation-2.41e+00

Pos logit contributions
 end+0.426
ama+0.416
 eye+0.416
 night+0.416
opl+0.403
Neg logit contributions
rily-0.441
ked-0.427
chard-0.426
 handful-0.413
 angrily-0.389
Token,
Token ID11
Feature activation-3.53e-01

Pos logit contributions
chard+0.168
 angrily+0.162
rily+0.161
nam+0.161
 appet+0.160
Neg logit contributions
 night-0.094
 day-0.091
 eye-0.091
ama-0.090
 end-0.090
Token every
Token ID790
Feature activation+2.83e+00

Pos logit contributions
chard+0.020
 angrily+0.019
nam+0.019
 appet+0.018
rily+0.018
Neg logit contributions
 night-0.019
 day-0.019
 eye-0.018
 end-0.018
ama-0.018
Token day
Token ID1110
Feature activation+2.95e+00

Pos logit contributions
ama+0.083
opl+0.072
oes+0.070
ummy+0.061
 eye+0.058
Neg logit contributions
 handful-0.225
chard-0.212
 angrily-0.210
rily-0.208
 gru-0.206
Token.
Token ID13
Feature activation+4.06e-01

Pos logit contributions
 night+0.129
 eye+0.127
 end+0.125
 day+0.125
ama+0.125
Neg logit contributions
chard-0.192
 angrily-0.185
rily-0.183
 appet-0.182
nam-0.182
Token.
Token ID13
Feature activation+5.41e-01

Pos logit contributions
ama+0.019
 eye+0.017
 end+0.016
 night+0.016
opl+0.016
Neg logit contributions
chard-0.023
 angrily-0.021
rily-0.021
 handful-0.020
nam-0.020
Token He
Token ID679
Feature activation-6.77e-01

Pos logit contributions
 night+0.028
 day+0.028
 eye+0.027
 end+0.026
 of+0.026
Neg logit contributions
chard-0.032
rily-0.031
nam-0.031
 appet-0.030
 handful-0.030
Token saw
Token ID2497
Feature activation-1.58e+00

Pos logit contributions
rily+0.043
chard+0.041
 appet+0.041
nam+0.041
 angrily+0.040
Neg logit contributions
 night-0.033
 day-0.033
 end-0.031
 eye-0.030
ama-0.029
Token that
Token ID326
Feature activation+2.61e+00

Pos logit contributions
chard+0.086
 appet+0.085
rily+0.084
 angrily+0.083
nam+0.082
Neg logit contributions
 night-0.090
 day-0.087
 end-0.085
 eye-0.083
 of-0.082
Token the
Token ID262
Feature activation+6.96e-01

Pos logit contributions
 night+0.152
 day+0.150
 end+0.142
 of+0.137
 eye+0.136
Neg logit contributions
rily-0.138
 appet-0.138
chard-0.138
 angrily-0.137
ked-0.134
Token sun
Token ID4252
Feature activation+8.24e+00

Pos logit contributions
ama+0.026
opl+0.022
issy+0.020
iff+0.020
 of+0.020
Neg logit contributions
chard-0.048
 handful-0.044
nam-0.043
 appet-0.042
 oh-0.042
Tokenflower
Token ID25547
Feature activation+3.92e-01

Pos logit contributions
 eye+0.391
 end+0.379
ama+0.377
 night+0.376
opl+0.367
Neg logit contributions
chard-0.467
rily-0.440
ked-0.439
 handful-0.426
 angrily-0.417
Token was
Token ID373
Feature activation+7.62e-01

Pos logit contributions
ama+0.022
 eye+0.021
opl+0.020
oes+0.020
 end+0.020
Neg logit contributions
chard-0.020
 angrily-0.019
 appet-0.017
 oh-0.017
 handful-0.017
Token sad
Token ID6507
Feature activation-1.25e+00

Pos logit contributions
ama+0.043
 night+0.042
 eye+0.042
 end+0.042
oes+0.041
Neg logit contributions
chard-0.041
nam-0.037
 angrily-0.037
rily-0.037
 handful-0.036
Token.
Token ID13
Feature activation+5.11e-01

Pos logit contributions
 angrily+0.063
chard+0.061
 appet+0.060
 oh+0.059
 handful+0.059
Neg logit contributions
ama-0.071
opl-0.070
 eye-0.062
 end-0.060
 night-0.060
Token Tim
Token ID5045
Feature activation+9.57e-01

Pos logit contributions
 day+0.025
 night+0.025
 of+0.024
ama+0.024
 eye+0.023
Neg logit contributions
rily-0.031
chard-0.031
nam-0.030
 handful-0.030
 appet-0.030
Token said
Token ID531
Feature activation+9.02e-01

Pos logit contributions
 night+0.002
 day+0.002
 end+0.002
 of+0.002
 eye+0.002
Neg logit contributions
rily-0.004
 appet-0.004
chard-0.004
 Edward-0.004
cher-0.004
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
 of+0.015
 day+0.013
 night+0.012
 end+0.011
ama+0.010
Neg logit contributions
rily-0.088
Roger-0.084
cca-0.084
chard-0.084
rob-0.084
Token "
Token ID366
Feature activation-4.52e+00

Pos logit contributions
nam+0.008
chard+0.008
rily+0.008
ts+0.008
 appet+0.008
Neg logit contributions
 day-0.008
 night-0.007
ama-0.007
 end-0.007
 of-0.007
TokenHello
Token ID15496
Feature activation-2.39e+00

Pos logit contributions
chard+0.177
nam+0.163
 angrily+0.162
 appet+0.161
rily+0.159
Neg logit contributions
 night-0.322
 eye-0.316
 day-0.315
ama-0.312
 end-0.312
Token,
Token ID11
Feature activation-2.75e-01

Pos logit contributions
chard+0.174
nam+0.169
 angrily+0.168
rily+0.167
 appet+0.166
Neg logit contributions
 night-0.091
 day-0.087
 end-0.086
 eye-0.085
ama-0.084
Token sun
Token ID4252
Feature activation+8.24e+00

Pos logit contributions
chard+0.016
 angrily+0.016
nam+0.016
 appet+0.015
rily+0.015
Neg logit contributions
 night-0.014
 day-0.013
 eye-0.013
 end-0.013
ama-0.013
Tokenflower
Token ID25547
Feature activation+3.26e-01

Pos logit contributions
 night+0.369
 eye+0.353
 day+0.337
 end+0.334
opl+0.305
Neg logit contributions
 handful-0.487
chard-0.486
 oh-0.483
rily-0.472
 appet-0.458
Token!
Token ID0
Feature activation-8.96e-01

Pos logit contributions
 night+0.016
 eye+0.015
 day+0.015
 end+0.015
ama+0.015
Neg logit contributions
chard-0.020
 angrily-0.019
 appet-0.019
nam-0.019
rily-0.019
Token You
Token ID921
Feature activation-4.02e+00

Pos logit contributions
rily+0.039
chard+0.039
 angrily+0.038
nam+0.037
 handful+0.037
Neg logit contributions
 night-0.059
 day-0.058
 of-0.056
ama-0.056
 eye-0.056
Token are
Token ID389
Feature activation+6.04e-01

Pos logit contributions
chard+0.244
 appet+0.237
 handful+0.235
nam+0.235
 angrily+0.232
Neg logit contributions
ama-0.190
 day-0.181
 night-0.181
 eye-0.174
 end-0.173
Token very
Token ID845
Feature activation-3.11e+00

Pos logit contributions
 night+0.034
 day+0.033
 end+0.032
 eye+0.031
 of+0.031
Neg logit contributions
chard-0.033
rily-0.033
 angrily-0.033
 appet-0.032
ked-0.032
Token his
Token ID465
Feature activation+1.89e-01

Pos logit contributions
 appet+0.046
chard+0.045
 angrily+0.042
rily+0.041
nam+0.041
Neg logit contributions
 night-0.051
 day-0.049
 end-0.047
 eye-0.046
 of-0.045
Token lion
Token ID18744
Feature activation-2.61e+00

Pos logit contributions
 night+0.007
 day+0.007
 eye+0.007
 end+0.007
ama+0.006
Neg logit contributions
chard-0.014
 appet-0.014
 angrily-0.013
rily-0.013
ked-0.013
Token the
Token ID262
Feature activation+9.26e-01

Pos logit contributions
chard+0.152
nam+0.145
rily+0.144
 appet+0.139
 angrily+0.137
Neg logit contributions
 night-0.142
 end-0.140
 eye-0.139
 day-0.138
 of-0.136
Token name
Token ID1438
Feature activation-2.41e-01

Pos logit contributions
 night+0.051
 day+0.049
 eye+0.049
 end+0.049
ama+0.046
Neg logit contributions
chard-0.052
rily-0.049
nam-0.049
 angrily-0.049
 appet-0.049
Token "
Token ID366
Feature activation-4.71e+00

Pos logit contributions
chard+0.017
nam+0.016
 appet+0.016
rily+0.016
 angrily+0.016
Neg logit contributions
 night-0.010
 day-0.010
 end-0.010
 of-0.010
 eye-0.009
TokenZE
Token ID21211
Feature activation-9.38e+00

Pos logit contributions
chard+0.234
 angrily+0.220
nam+0.220
 appet+0.218
rily+0.217
Neg logit contributions
 night-0.282
 day-0.275
 eye-0.273
 end-0.273
ama-0.270
TokenB
Token ID33
Feature activation+2.79e+00

Pos logit contributions
nam+0.630
chard+0.598
rily+0.556
ked+0.554
 angrily+0.529
Neg logit contributions
 day-0.507
 night-0.485
 of-0.469
 end-0.452
opl-0.407
TokenRA
Token ID3861
Feature activation-8.83e-01

Pos logit contributions
 night+0.145
 day+0.140
 end+0.139
 eye+0.139
ama+0.134
Neg logit contributions
chard-0.160
 appet-0.155
 angrily-0.155
rily-0.151
nam-0.151
TokenK
Token ID42
Feature activation-7.14e-01

Pos logit contributions
chard+0.038
rily+0.037
nam+0.037
 angrily+0.036
 handful+0.035
Neg logit contributions
 night-0.059
 day-0.058
 end-0.057
ama-0.056
 eye-0.056
TokenILL
Token ID8267
Feature activation-9.66e-02

Pos logit contributions
 appet+0.036
chard+0.036
 Percy+0.035
ked+0.035
 Edward+0.034
Neg logit contributions
 end-0.039
 eye-0.038
 night-0.038
 day-0.037
ama-0.035
TokenER
Token ID1137
Feature activation-7.32e+00

Pos logit contributions
chard+0.006
nam+0.005
 appet+0.005
rily+0.005
 angrily+0.005
Neg logit contributions
 night-0.005
 day-0.005
 end-0.005
 eye-0.005
ama-0.005
TokenStay
Token ID25681
Feature activation-2.56e+00

Pos logit contributions
chard+0.010
nam+0.010
rily+0.010
 angrily+0.010
 appet+0.010
Neg logit contributions
 night-0.011
 day-0.011
 end-0.010
 eye-0.010
 of-0.010
Token away
Token ID1497
Feature activation-2.43e+00

Pos logit contributions
chard+0.157
nam+0.156
 appet+0.143
ked+0.143
rily+0.142
Neg logit contributions
 night-0.129
 eye-0.126
 end-0.126
 day-0.125
ama-0.121
Token from
Token ID422
Feature activation-3.21e+00

Pos logit contributions
chard+0.156
 angrily+0.150
nam+0.149
 appet+0.148
rily+0.148
Neg logit contributions
 night-0.110
 day-0.107
 eye-0.105
 end-0.105
ama-0.103
Token my
Token ID616
Feature activation-2.04e+00

Pos logit contributions
 appet+0.187
chard+0.186
rily+0.183
 angrily+0.182
nam+0.179
Neg logit contributions
 night-0.174
 day-0.169
 end-0.165
 eye-0.157
 of-0.150
Token or
Token ID393
Feature activation-3.35e+00

Pos logit contributions
chard+0.130
 angrily+0.129
 handful+0.126
 appet+0.124
 Percy+0.124
Neg logit contributions
ama-0.082
 night-0.082
 day-0.079
 end-0.079
oes-0.078
Tokenchard
Token ID30215
Feature activation-9.29e+00

Pos logit contributions
rily+0.218
 appet+0.208
 angrily+0.205
 handful+0.203
ked+0.203
Neg logit contributions
 night-0.162
 day-0.156
 end-0.149
 eye-0.143
 of-0.136
Token,
Token ID11
Feature activation-7.67e-01

Pos logit contributions
chard+0.619
 angrily+0.596
 appet+0.585
nam+0.579
 handful+0.578
Neg logit contributions
 night-0.385
ama-0.364
 day-0.363
 eye-0.359
 end-0.353
Token young
Token ID1862
Feature activation+1.97e-01

Pos logit contributions
chard+0.042
rily+0.040
nam+0.040
 appet+0.039
 angrily+0.039
Neg logit contributions
 night-0.043
 day-0.043
 end-0.041
 of-0.041
 eye-0.041
Token Fox
Token ID5426
Feature activation-1.44e+00

Pos logit contributions
 night+0.010
 day+0.010
 end+0.010
 eye+0.010
 of+0.009
Neg logit contributions
chard-0.012
nam-0.012
 appet-0.011
 angrily-0.011
rily-0.011
Token!
Token ID0
Feature activation-1.46e+00

Pos logit contributions
chard+0.100
nam+0.096
 angrily+0.095
rily+0.095
 appet+0.095
Neg logit contributions
 night-0.059
 day-0.057
 end-0.056
 eye-0.056
ama-0.054
Tokenรข
Token ID22940
Feature activation+1.39e+00

Pos logit contributions
chard+0.095
nam+0.093
rily+0.091
 appet+0.091
ts+0.091
Neg logit contributions
 night-0.063
 day-0.063
ama-0.063
 of-0.061
 eye-0.058
Tokenummy
Token ID13513
Feature activation+3.94e+00

Pos logit contributions
rily+0.204
 handful+0.200
 appet+0.199
 angrily+0.196
 Edward+0.194
Neg logit contributions
 end-0.064
 night-0.061
 day-0.060
 eye-0.056
ama-0.049
Token cotton
Token ID15985
Feature activation-4.05e+00

Pos logit contributions
 night+0.251
 day+0.248
 of+0.234
 end+0.232
 eye+0.232
Neg logit contributions
chard-0.212
 angrily-0.194
nam-0.190
rily-0.188
ked-0.183
Token candy
Token ID18550
Feature activation-5.29e+00

Pos logit contributions
chard+0.175
nam+0.163
 angrily+0.163
rily+0.160
 appet+0.156
Neg logit contributions
 night-0.277
 day-0.272
 end-0.267
 eye-0.265
ama-0.259
Token and
Token ID290
Feature activation-4.63e-01

Pos logit contributions
chard+0.384
nam+0.375
 angrily+0.368
 appet+0.365
rily+0.362
Neg logit contributions
 night-0.205
 day-0.200
 end-0.188
 eye-0.186
 of-0.182
Token play
Token ID711
Feature activation+1.81e+00

Pos logit contributions
chard+0.026
rily+0.025
 angrily+0.025
 appet+0.025
ked+0.024
Neg logit contributions
 night-0.026
 day-0.026
 end-0.024
 eye-0.024
 of-0.023
Token carn
Token ID18466
Feature activation-9.14e+00

Pos logit contributions
 day+0.079
 of+0.077
 night+0.068
 end+0.067
 morning+0.055
Neg logit contributions
chard-0.142
ked-0.142
nam-0.139
heit-0.139
 appet-0.129
Tokenival
Token ID2473
Feature activation-6.99e+00

Pos logit contributions
chard+0.407
nam+0.384
rily+0.383
 oh+0.378
ked+0.373
Neg logit contributions
 of-0.616
 day-0.602
 night-0.579
 end-0.577
ama-0.542
Token games
Token ID1830
Feature activation-4.69e+00

Pos logit contributions
chard+0.519
ked+0.502
nam+0.496
rily+0.488
 appet+0.483
Neg logit contributions
 day-0.289
 night-0.272
 of-0.266
 end-0.252
 eye-0.221
Token.
Token ID13
Feature activation+2.53e-01

Pos logit contributions
chard+0.350
nam+0.339
 angrily+0.337
 appet+0.336
rily+0.336
Neg logit contributions
 night-0.169
 day-0.166
 end-0.157
 eye-0.155
 of-0.149
Token
Token ID198
Feature activation+4.50e-01

Pos logit contributions
 night+0.013
 eye+0.013
 end+0.013
 day+0.013
ama+0.012
Neg logit contributions
chard-0.014
nam-0.014
 angrily-0.014
rily-0.013
 appet-0.013
Token
Token ID198
Feature activation+4.57e-01

Pos logit contributions
 night+0.019
 eye+0.018
 day+0.018
 end+0.018
ama+0.018
Neg logit contributions
chard-0.030
 angrily-0.029
nam-0.029
rily-0.029
 appet-0.029
Token go
Token ID467
Feature activation+1.19e+00

Pos logit contributions
ama+0.058
 night+0.056
 eye+0.056
 day+0.055
oes+0.052
Neg logit contributions
chard-0.085
 angrily-0.082
 Edward-0.082
 Percy-0.082
 appet-0.080
Token the
Token ID262
Feature activation+3.12e-01

Pos logit contributions
 night+0.056
 day+0.054
 end+0.053
 eye+0.053
ama+0.052
Neg logit contributions
chard-0.075
nam-0.072
 angrily-0.072
 appet-0.071
rily-0.071
Token other
Token ID584
Feature activation+2.89e+00

Pos logit contributions
 night+0.012
 eye+0.012
ama+0.012
 day+0.011
 end+0.011
Neg logit contributions
chard-0.022
nam-0.021
 appet-0.021
 angrily-0.021
 handful-0.021
Token way
Token ID835
Feature activation+3.33e+00

Pos logit contributions
ama+0.109
 eye+0.098
 night+0.097
 day+0.089
oes+0.088
Neg logit contributions
chard-0.202
 appet-0.196
 oh-0.194
nam-0.194
 Edward-0.192
Token.
Token ID13
Feature activation+3.22e-01

Pos logit contributions
 eye+0.186
ama+0.179
 night+0.179
 end+0.175
 day+0.174
Neg logit contributions
chard-0.172
rily-0.162
nam-0.157
 angrily-0.157
 Percy-0.154
Token How
Token ID1374
Feature activation-9.09e+00

Pos logit contributions
 night+0.018
 day+0.017
 eye+0.017
 end+0.017
ama+0.017
Neg logit contributions
chard-0.017
 angrily-0.017
nam-0.017
 appet-0.016
rily-0.016
Token does
Token ID857
Feature activation-1.90e+00

Pos logit contributions
chard+0.569
 angrily+0.545
nam+0.544
 appet+0.541
rily+0.537
Neg logit contributions
 night-0.424
 day-0.410
 eye-0.408
 end-0.406
ama-0.402
Token that
Token ID326
Feature activation+2.19e+00

Pos logit contributions
chard+0.104
 angrily+0.099
nam+0.099
 appet+0.098
rily+0.098
Neg logit contributions
 night-0.105
 day-0.103
 end-0.101
 eye-0.101
ama-0.100
Token sound
Token ID2128
Feature activation+2.03e-01

Pos logit contributions
ama+0.097
 eye+0.097
 night+0.093
 day+0.087
oes+0.087
Neg logit contributions
 oh-0.133
 angrily-0.128
 appet-0.128
chard-0.127
 Edward-0.123
Token?"
Token ID1701
Feature activation-4.21e+00

Pos logit contributions
 night+0.009
 day+0.009
 end+0.009
 eye+0.009
ama+0.009
Neg logit contributions
chard-0.013
nam-0.012
rily-0.012
 angrily-0.012
 appet-0.012
Token
Token ID198
Feature activation+3.58e-01

Pos logit contributions
chard+0.287
 appet+0.280
rily+0.277
nam+0.274
 handful+0.272
Neg logit contributions
 night-0.182
 day-0.178
ama-0.169
 end-0.167
 eye-0.163
Token for
Token ID329
Feature activation-3.00e+00

Pos logit contributions
ama+0.128
 eye+0.126
opl+0.125
 night+0.124
 day+0.121
Neg logit contributions
chard-0.095
 angrily-0.093
 handful-0.092
 Edward-0.091
 Percy-0.090
Token taking
Token ID2263
Feature activation-1.85e+00

Pos logit contributions
 appet+0.178
chard+0.176
rily+0.175
 angrily+0.172
 handful+0.163
Neg logit contributions
 night-0.157
 day-0.155
 end-0.154
 of-0.141
 eye-0.139
Token her
Token ID607
Feature activation+4.60e-01

Pos logit contributions
chard+0.128
 appet+0.118
nam+0.118
rily+0.116
ked+0.113
Neg logit contributions
 night-0.093
 day-0.088
 end-0.083
 eye-0.081
 of-0.080
Token to
Token ID284
Feature activation-3.57e-01

Pos logit contributions
 night+0.025
 day+0.024
 eye+0.024
 end+0.024
ama+0.024
Neg logit contributions
chard-0.026
 angrily-0.024
nam-0.024
 appet-0.024
rily-0.024
Token the
Token ID262
Feature activation+5.69e-01

Pos logit contributions
chard+0.019
nam+0.018
 angrily+0.018
 appet+0.018
rily+0.018
Neg logit contributions
 night-0.020
 day-0.020
 eye-0.019
ama-0.019
 end-0.019
Token carn
Token ID18466
Feature activation-9.03e+00

Pos logit contributions
 night+0.023
 eye+0.023
ama+0.023
 day+0.022
 end+0.021
Neg logit contributions
chard-0.039
nam-0.037
 angrily-0.037
 appet-0.037
 Edward-0.036
Tokenival
Token ID2473
Feature activation-6.92e+00

Pos logit contributions
chard+0.320
rily+0.311
nam+0.306
 angrily+0.299
ked+0.294
Neg logit contributions
 day-0.664
 night-0.660
 end-0.655
 of-0.645
ama-0.636
Token.
Token ID13
Feature activation+3.72e-01

Pos logit contributions
chard+0.483
 angrily+0.465
nam+0.463
 appet+0.461
rily+0.460
Neg logit contributions
 night-0.273
 day-0.262
 eye-0.260
 end-0.259
ama-0.256
Token They
Token ID1119
Feature activation-7.01e-01

Pos logit contributions
 night+0.022
 end+0.022
 eye+0.021
 day+0.021
ama+0.021
Neg logit contributions
chard-0.018
 angrily-0.018
rily-0.018
nam-0.017
 Edward-0.017
Token hugged
Token ID41130
Feature activation+4.18e-01

Pos logit contributions
chard+0.042
nam+0.040
 angrily+0.039
 handful+0.039
 appet+0.039
Neg logit contributions
 night-0.034
 eye-0.034
ama-0.034
 day-0.033
 end-0.033
Token her
Token ID607
Feature activation+4.97e-01

Pos logit contributions
 night+0.014
 day+0.014
 end+0.014
 of+0.013
 eye+0.012
Neg logit contributions
chard-0.036
cher-0.033
nam-0.033
 appet-0.033
 bluff-0.033
Token had
Token ID550
Feature activation+9.85e-01

Pos logit contributions
chard+0.217
 angrily+0.209
nam+0.207
rily+0.205
 appet+0.205
Neg logit contributions
 night-0.152
 day-0.147
 eye-0.146
 end-0.144
ama-0.144
Token been
Token ID587
Feature activation+3.13e+00

Pos logit contributions
 night+0.047
 day+0.046
 end+0.045
 eye+0.045
ama+0.043
Neg logit contributions
chard-0.061
 appet-0.059
rily-0.059
nam-0.059
 angrily-0.058
Token disturbing
Token ID14851
Feature activation-1.31e+00

Pos logit contributions
 day+0.158
 night+0.156
 of+0.155
 end+0.148
 eye+0.146
Neg logit contributions
rily-0.179
chard-0.178
 appet-0.177
nam-0.175
ked-0.173
Token his
Token ID465
Feature activation-7.90e-02

Pos logit contributions
chard+0.074
 appet+0.072
nam+0.070
rily+0.070
ked+0.069
Neg logit contributions
 night-0.072
 day-0.071
 end-0.069
 of-0.068
 eye-0.065
Token or
Token ID393
Feature activation-3.20e+00

Pos logit contributions
chard+0.005
 angrily+0.005
nam+0.005
 appet+0.005
 handful+0.005
Neg logit contributions
 night-0.003
ama-0.003
 eye-0.003
 end-0.003
 day-0.003
Tokenchard
Token ID30215
Feature activation-9.03e+00

Pos logit contributions
rily+0.171
 appet+0.170
ked+0.164
chard+0.164
 angrily+0.163
Neg logit contributions
 night-0.180
 day-0.178
 end-0.171
 eye-0.162
 of-0.161
Token and
Token ID290
Feature activation-5.64e-01

Pos logit contributions
chard+0.593
 angrily+0.568
nam+0.563
 appet+0.557
rily+0.554
Neg logit contributions
 night-0.397
 day-0.378
ama-0.377
 eye-0.376
 end-0.370
Token he
Token ID339
Feature activation+3.35e-01

Pos logit contributions
chard+0.032
 appet+0.031
rily+0.031
nam+0.030
 handful+0.030
Neg logit contributions
 night-0.030
 day-0.029
 end-0.029
 eye-0.028
 of-0.027
Token wanted
Token ID2227
Feature activation+2.01e-01

Pos logit contributions
 night+0.015
 day+0.014
 end+0.014
 eye+0.014
ama+0.014
Neg logit contributions
chard-0.022
nam-0.021
rily-0.021
 appet-0.021
 handful-0.021
Token to
Token ID284
Feature activation-3.11e-01

Pos logit contributions
 night+0.009
 day+0.009
 end+0.009
 eye+0.008
ama+0.008
Neg logit contributions
chard-0.013
nam-0.013
rily-0.013
 appet-0.013
 angrily-0.012
Token get
Token ID651
Feature activation-1.21e+00

Pos logit contributions
chard+0.019
 angrily+0.019
 Percy+0.018
 Clive+0.018
 Edward+0.018
Neg logit contributions
 night-0.015
ama-0.014
 day-0.014
 eye-0.014
opl-0.013
Token ride
Token ID6594
Feature activation+6.91e-01

Pos logit contributions
chard+0.091
rily+0.088
 angrily+0.088
nam+0.087
 appet+0.087
Neg logit contributions
 night-0.066
 day-0.064
 eye-0.063
 end-0.062
ama-0.060
Token to
Token ID284
Feature activation-3.01e-01

Pos logit contributions
 night+0.027
 day+0.027
 end+0.025
 eye+0.025
ama+0.024
Neg logit contributions
chard-0.050
 appet-0.048
nam-0.048
 angrily-0.048
rily-0.048
Token the
Token ID262
Feature activation+5.94e-01

Pos logit contributions
chard+0.018
 appet+0.018
rily+0.017
 angrily+0.017
 handful+0.017
Neg logit contributions
 night-0.015
 day-0.015
 end-0.015
 eye-0.015
 of-0.014
Token apple
Token ID17180
Feature activation-2.68e+00

Pos logit contributions
 night+0.023
ama+0.023
 eye+0.022
 day+0.022
 end+0.021
Neg logit contributions
chard-0.042
 angrily-0.040
nam-0.040
 appet-0.039
 oh-0.039
Token or
Token ID393
Feature activation-3.11e+00

Pos logit contributions
chard+0.183
 angrily+0.175
nam+0.174
rily+0.173
 appet+0.173
Neg logit contributions
 night-0.111
 day-0.106
 eye-0.106
 end-0.105
ama-0.104
Tokenchard
Token ID30215
Feature activation-9.02e+00

Pos logit contributions
rily+0.195
 appet+0.194
 handful+0.182
 angrily+0.181
ked+0.178
Neg logit contributions
 night-0.157
 day-0.154
 end-0.148
 of-0.142
 eye-0.141
Token.
Token ID13
Feature activation-2.51e-02

Pos logit contributions
chard+0.665
 angrily+0.641
nam+0.640
 appet+0.638
rily+0.637
Neg logit contributions
 night-0.326
 day-0.315
 end-0.309
 eye-0.308
ama-0.299
Token The
Token ID383
Feature activation+1.24e+00

Pos logit contributions
chard+0.002
nam+0.002
 appet+0.002
cher+0.002
 handful+0.002
Neg logit contributions
 night-0.001
 day-0.001
ama-0.001
 of-0.001
 end-0.001
Token neighbor
Token ID4780
Feature activation-6.80e-01

Pos logit contributions
 night+0.056
ama+0.052
 eye+0.052
 day+0.051
 end+0.049
Neg logit contributions
chard-0.082
 angrily-0.077
nam-0.076
 oh-0.075
 appet-0.074
Token said
Token ID531
Feature activation+5.33e-01

Pos logit contributions
chard+0.041
nam+0.040
rily+0.040
 appet+0.040
 angrily+0.039
Neg logit contributions
 night-0.033
 day-0.033
 end-0.032
 eye-0.032
ama-0.031
Token yes
Token ID3763
Feature activation-3.94e+00

Pos logit contributions
 of+0.028
 end+0.026
 day+0.025
 night+0.024
ama+0.023
Neg logit contributions
 appet-0.033
rily-0.032
ports-0.032
RR-0.032
chard-0.032
Token a
Token ID257
Feature activation-1.33e+00

Pos logit contributions
chard+0.120
 angrily+0.112
nam+0.112
 appet+0.111
rily+0.110
Neg logit contributions
 night-0.202
 day-0.198
 eye-0.196
 end-0.195
ama-0.194
Token fun
Token ID1257
Feature activation+1.26e+00

Pos logit contributions
rily+0.087
chard+0.086
 angrily+0.084
nam+0.084
ports+0.083
Neg logit contributions
 day-0.063
 night-0.062
 end-0.058
 eye-0.057
 of-0.052
Token ride
Token ID6594
Feature activation+9.48e-01

Pos logit contributions
ama+0.036
 night+0.035
 end+0.034
 eye+0.034
 day+0.031
Neg logit contributions
chard-0.098
 angrily-0.097
 handful-0.097
 appet-0.096
 oh-0.095
Token at
Token ID379
Feature activation-7.65e-01

Pos logit contributions
 day+0.043
 night+0.043
 of+0.039
 end+0.037
 eye+0.036
Neg logit contributions
 appet-0.065
rily-0.064
chard-0.064
nam-0.063
 handful-0.063
Token the
Token ID262
Feature activation+7.46e-01

Pos logit contributions
chard+0.040
nam+0.038
 angrily+0.037
rily+0.037
 Edward+0.037
Neg logit contributions
 eye-0.043
 night-0.042
ama-0.042
 end-0.042
 day-0.042
Token carn
Token ID18466
Feature activation-9.01e+00

Pos logit contributions
ama+0.030
 eye+0.027
 night+0.026
oes+0.026
opl+0.025
Neg logit contributions
chard-0.051
 oh-0.048
 appet-0.048
 Edward-0.047
 handful-0.047
Tokenival
Token ID2473
Feature activation-7.00e+00

Pos logit contributions
chard+0.330
rily+0.324
nam+0.318
 angrily+0.314
 appet+0.305
Neg logit contributions
 day-0.654
 night-0.654
 end-0.640
 of-0.628
ama-0.622
Token.
Token ID13
Feature activation+3.44e-01

Pos logit contributions
chard+0.562
nam+0.550
rily+0.548
 appet+0.546
 handful+0.539
Neg logit contributions
 night-0.220
 day-0.218
 end-0.200
 eye-0.190
 of-0.186
Token Twe
Token ID24205
Feature activation-1.47e+00

Pos logit contributions
 night+0.014
 day+0.014
 eye+0.013
 end+0.013
ama+0.013
Neg logit contributions
chard-0.023
rily-0.023
 angrily-0.023
nam-0.023
 Edward-0.022
Tokenety
Token ID2963
Feature activation+1.11e+00

Pos logit contributions
chard+0.076
ked+0.074
 appet+0.073
 angrily+0.073
rily+0.072
Neg logit contributions
 night-0.087
 end-0.083
 day-0.083
 eye-0.078
ama-0.078
Token thought
Token ID1807
Feature activation+2.60e-01

Pos logit contributions
 night+0.056
 eye+0.055
ama+0.055
 end+0.055
 day+0.055
Neg logit contributions
chard-0.065
 angrily-0.062
 appet-0.061
nam-0.061
rily-0.060
Token you
Token ID345
Feature activation+6.52e-01

Pos logit contributions
chard+0.074
 angrily+0.071
nam+0.071
 appet+0.070
 Edward+0.069
Neg logit contributions
 eye-0.060
 night-0.059
ama-0.058
 end-0.057
 day-0.057
Token to
Token ID284
Feature activation-2.32e-01

Pos logit contributions
 night+0.030
 day+0.029
 eye+0.029
 end+0.028
ama+0.028
Neg logit contributions
chard-0.042
 angrily-0.040
nam-0.040
 appet-0.040
rily-0.039
Token be
Token ID307
Feature activation+2.80e+00

Pos logit contributions
chard+0.014
 Edward+0.013
 Percy+0.013
 angrily+0.013
 Clive+0.013
Neg logit contributions
ama-0.011
 eye-0.010
 night-0.010
 day-0.010
ummy-0.009
Token safe
Token ID3338
Feature activation+7.03e-01

Pos logit contributions
 night+0.125
 day+0.124
 of+0.118
 end+0.117
 eye+0.110
Neg logit contributions
rily-0.189
chard-0.186
 Percy-0.179
ked-0.179
nam-0.178
Token.
Token ID13
Feature activation+8.79e-01

Pos logit contributions
 night+0.027
 day+0.026
 end+0.026
 of+0.024
 eye+0.024
Neg logit contributions
chard-0.052
nam-0.050
 handful-0.049
ked-0.049
rily-0.048
Token How
Token ID1374
Feature activation-8.99e+00

Pos logit contributions
 night+0.057
 day+0.056
 end+0.055
 eye+0.055
ama+0.054
Neg logit contributions
chard-0.040
nam-0.037
 angrily-0.037
 appet-0.037
rily-0.036
Token about
Token ID546
Feature activation-2.77e+00

Pos logit contributions
chard+0.501
nam+0.482
 angrily+0.478
 appet+0.477
 Edward+0.466
Neg logit contributions
 night-0.469
 eye-0.461
ama-0.455
 day-0.454
 end-0.450
Token we
Token ID356
Feature activation+7.38e-01

Pos logit contributions
chard+0.164
 angrily+0.158
rily+0.158
 appet+0.157
nam+0.155
Neg logit contributions
 night-0.142
 day-0.138
 end-0.135
ama-0.134
 eye-0.134
Token finish
Token ID5461
Feature activation+1.77e+00

Pos logit contributions
ama+0.038
opl+0.037
 night+0.036
 day+0.036
 eye+0.035
Neg logit contributions
chard-0.040
 appet-0.037
nam-0.036
 angrily-0.035
 Edward-0.035
Token our
Token ID674
Feature activation-3.11e+00

Pos logit contributions
 night+0.100
 day+0.097
 end+0.095
 eye+0.090
ama+0.089
Neg logit contributions
chard-0.097
ked-0.096
 angrily-0.095
rily-0.094
 appet-0.092
Token m
Token ID285
Feature activation+1.78e+00

Pos logit contributions
chard+0.173
 appet+0.172
nam+0.171
 handful+0.170
 angrily+0.167
Neg logit contributions
ama-0.150
 eye-0.146
 of-0.142
oes-0.138
 night-0.137
Token,
Token ID11
Feature activation-4.63e-01

Pos logit contributions
 night+0.104
 day+0.100
 of+0.094
 end+0.076
ama+0.070
Neg logit contributions
chard-0.352
rily-0.351
nam-0.348
 appet-0.341
 bluff-0.335
Token Lily
Token ID20037
Feature activation-1.45e+00

Pos logit contributions
 appet+0.032
rily+0.031
 bluff+0.029
heit+0.029
 angrily+0.029
Neg logit contributions
 day-0.023
 night-0.022
 of-0.019
 end-0.019
 family-0.018
Token went
Token ID1816
Feature activation+1.32e+00

Pos logit contributions
 angrily+0.079
 appet+0.079
chard+0.079
 Edward+0.075
 handful+0.074
Neg logit contributions
ama-0.075
 end-0.070
oes-0.068
 eye-0.068
opl-0.067
Token to
Token ID284
Feature activation+1.03e-01

Pos logit contributions
 night+0.066
ama+0.064
 end+0.064
 day+0.064
 eye+0.063
Neg logit contributions
chard-0.077
 angrily-0.073
 handful-0.073
nam-0.073
 Edward-0.072
Token a
Token ID257
Feature activation-9.82e-01

Pos logit contributions
 night+0.006
 day+0.006
 end+0.006
 eye+0.006
ama+0.005
Neg logit contributions
chard-0.006
 angrily-0.005
nam-0.005
 appet-0.005
rily-0.005
Token carn
Token ID18466
Feature activation-8.98e+00

Pos logit contributions
chard+0.065
 angrily+0.063
rily+0.063
nam+0.063
 appet+0.063
Neg logit contributions
 night-0.043
 day-0.042
 end-0.041
 eye-0.040
ama-0.039
Tokenival
Token ID2473
Feature activation-6.66e+00

Pos logit contributions
rily+0.344
chard+0.340
 angrily+0.326
 appet+0.325
nam+0.321
Neg logit contributions
 day-0.634
 of-0.630
 night-0.623
 end-0.619
ama-0.601
Token with
Token ID351
Feature activation-2.98e+00

Pos logit contributions
chard+0.399
rily+0.388
 angrily+0.387
nam+0.384
 appet+0.383
Neg logit contributions
 night-0.337
 day-0.337
 end-0.321
 eye-0.318
 of-0.311
Token her
Token ID607
Feature activation+5.27e-01

Pos logit contributions
 appet+0.173
chard+0.172
 angrily+0.168
rily+0.166
 handful+0.159
Neg logit contributions
 night-0.161
 day-0.157
 end-0.150
 of-0.148
 eye-0.147
Token family
Token ID1641
Feature activation+2.50e+00

Pos logit contributions
 night+0.017
 end+0.016
 eye+0.016
 day+0.016
ama+0.015
Neg logit contributions
chard-0.041
nam-0.040
 angrily-0.039
 Percy-0.039
 handful-0.039
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
 night+0.108
ama+0.107
 eye+0.104
 end+0.104
opl+0.101
Neg logit contributions
chard-0.160
nam-0.151
 handful-0.151
rily-0.149
 Edward-0.149
Token people
Token ID661
Feature activation-4.73e-01

Pos logit contributions
 night+0.029
 day+0.028
 end+0.028
 eye+0.027
ama+0.027
Neg logit contributions
chard-0.031
 angrily-0.029
nam-0.029
rily-0.029
 appet-0.029
Token who
Token ID508
Feature activation-2.79e+00

Pos logit contributions
chard+0.030
nam+0.028
 angrily+0.028
 appet+0.028
rily+0.028
Neg logit contributions
 night-0.022
 day-0.021
 eye-0.021
 end-0.021
ama-0.021
Token are
Token ID389
Feature activation+1.60e-01

Pos logit contributions
chard+0.175
 appet+0.166
 angrily+0.164
nam+0.164
 handful+0.161
Neg logit contributions
ama-0.128
 eye-0.127
 night-0.125
 end-0.123
 day-0.123
Token hungry
Token ID14720
Feature activation-3.82e+00

Pos logit contributions
 night+0.008
 day+0.008
 end+0.008
 eye+0.008
ama+0.008
Neg logit contributions
chard-0.009
 angrily-0.009
nam-0.009
 appet-0.009
rily-0.009
Token.
Token ID13
Feature activation+7.30e-01

Pos logit contributions
chard+0.240
 appet+0.236
 angrily+0.234
rily+0.232
 handful+0.231
Neg logit contributions
ama-0.171
 night-0.165
 eye-0.164
 day-0.159
 end-0.156
Token How
Token ID1374
Feature activation-8.96e+00

Pos logit contributions
 night+0.036
 day+0.035
ama+0.034
 end+0.034
 eye+0.034
Neg logit contributions
chard-0.044
rily-0.042
nam-0.042
 angrily-0.042
ked-0.042
Token does
Token ID857
Feature activation-1.75e+00

Pos logit contributions
chard+0.579
nam+0.555
 angrily+0.552
rily+0.551
 appet+0.544
Neg logit contributions
 night-0.421
 day-0.411
 end-0.401
 eye-0.397
ama-0.386
Token that
Token ID326
Feature activation+2.33e+00

Pos logit contributions
chard+0.106
ked+0.104
 angrily+0.103
nam+0.102
rily+0.102
Neg logit contributions
 night-0.089
 day-0.088
 end-0.085
ama-0.084
 of-0.083
Token sound
Token ID2128
Feature activation+2.76e-01

Pos logit contributions
 night+0.105
 eye+0.105
ama+0.103
 day+0.100
 end+0.099
Neg logit contributions
chard-0.143
 appet-0.139
 angrily-0.139
 oh-0.137
rily-0.136
Token?"
Token ID1701
Feature activation-4.12e+00

Pos logit contributions
 night+0.012
 end+0.012
 day+0.012
 of+0.012
 eye+0.010
Neg logit contributions
chard-0.019
nam-0.019
rily-0.018
ked-0.018
 Percy-0.018
Token
Token ID198
Feature activation+6.27e-01

Pos logit contributions
 appet+0.317
chard+0.313
ked+0.309
rily+0.309
 handful+0.308
Neg logit contributions
 night-0.140
 day-0.139
ama-0.128
 end-0.126
 of-0.123
Token and
Token ID290
Feature activation-3.35e-01

Pos logit contributions
 night+0.105
ama+0.105
 eye+0.103
 end+0.101
 day+0.101
Neg logit contributions
chard-0.148
 appet-0.143
nam-0.140
 angrily-0.139
 handful-0.139
Token a
Token ID257
Feature activation-1.56e+00

Pos logit contributions
chard+0.020
nam+0.019
 angrily+0.019
 appet+0.019
rily+0.019
Neg logit contributions
 night-0.016
 day-0.016
ama-0.016
 eye-0.016
 end-0.016
Token pet
Token ID4273
Feature activation-5.68e-01

Pos logit contributions
chard+0.101
 angrily+0.097
rily+0.097
nam+0.097
 appet+0.096
Neg logit contributions
 night-0.071
 day-0.069
 end-0.068
 eye-0.067
ama-0.065
Token family
Token ID1641
Feature activation+2.26e+00

Pos logit contributions
chard+0.040
nam+0.038
 angrily+0.038
rily+0.038
 appet+0.038
Neg logit contributions
 night-0.023
 day-0.022
 end-0.022
 eye-0.022
ama-0.021
Token.
Token ID13
Feature activation+6.72e-01

Pos logit contributions
 night+0.093
 eye+0.091
ama+0.091
 day+0.089
 end+0.089
Neg logit contributions
chard-0.151
 appet-0.145
nam-0.143
 angrily-0.143
rily-0.143
Token How
Token ID1374
Feature activation-8.96e+00

Pos logit contributions
 night+0.039
 day+0.038
 eye+0.038
 end+0.038
ama+0.038
Neg logit contributions
chard-0.035
 angrily-0.033
nam-0.033
rily-0.033
 handful-0.032
Token does
Token ID857
Feature activation-1.82e+00

Pos logit contributions
chard+0.535
 angrily+0.513
 appet+0.510
nam+0.510
rily+0.505
Neg logit contributions
 night-0.445
 day-0.432
 eye-0.429
 end-0.426
ama-0.423
Token that
Token ID326
Feature activation+2.37e+00

Pos logit contributions
chard+0.123
ked+0.122
 angrily+0.121
rily+0.120
 appet+0.120
Neg logit contributions
 night-0.079
 day-0.077
 end-0.075
 of-0.073
ama-0.072
Token sound
Token ID2128
Feature activation+2.18e-01

Pos logit contributions
 night+0.105
 eye+0.105
ama+0.105
 day+0.101
 end+0.099
Neg logit contributions
chard-0.148
 angrily-0.143
 appet-0.142
 oh-0.140
rily-0.139
Token?"
Token ID1701
Feature activation-4.07e+00

Pos logit contributions
 night+0.010
 day+0.009
 end+0.009
 of+0.009
 eye+0.008
Neg logit contributions
chard-0.015
nam-0.015
rily-0.015
ked-0.014
 handful-0.014
Token
Token ID198
Feature activation+5.90e-01

Pos logit contributions
 appet+0.308
chard+0.302
 handful+0.301
rily+0.300
ked+0.299
Neg logit contributions
 night-0.144
 day-0.140
ama-0.131
 end-0.129
 of-0.123
Token,
Token ID11
Feature activation-3.31e-01

Pos logit contributions
 night+0.108
 day+0.104
 end+0.101
 eye+0.097
ama+0.097
Neg logit contributions
chard-0.233
rily-0.225
 angrily-0.224
nam-0.223
 appet-0.222
Token Lily
Token ID20037
Feature activation-1.39e+00

Pos logit contributions
rily+0.024
 appet+0.023
cher+0.023
 angrily+0.023
 gru+0.023
Neg logit contributions
 day-0.016
 night-0.016
 end-0.015
 of-0.014
 morning-0.013
Token went
Token ID1816
Feature activation+1.23e+00

Pos logit contributions
chard+0.071
 appet+0.070
 angrily+0.070
 aimed+0.066
 oh+0.066
Neg logit contributions
ama-0.075
opl-0.075
oes-0.072
 end-0.072
 night-0.066
Token to
Token ID284
Feature activation-2.91e-01

Pos logit contributions
 night+0.056
 day+0.055
 eye+0.053
 end+0.053
ama+0.052
Neg logit contributions
chard-0.080
 angrily-0.077
nam-0.077
rily-0.077
 appet-0.076
Token a
Token ID257
Feature activation-1.32e+00

Pos logit contributions
chard+0.016
nam+0.015
 angrily+0.015
 appet+0.015
rily+0.015
Neg logit contributions
 night-0.016
 day-0.016
 eye-0.016
 end-0.016
ama-0.016
Token carn
Token ID18466
Feature activation-8.96e+00

Pos logit contributions
chard+0.090
rily+0.089
 angrily+0.089
nam+0.088
 appet+0.087
Neg logit contributions
 night-0.056
 day-0.054
 end-0.053
 eye-0.051
ama-0.049
Tokenival
Token ID2473
Feature activation-6.91e+00

Pos logit contributions
chard+0.351
rily+0.351
 angrily+0.340
 appet+0.331
nam+0.331
Neg logit contributions
 day-0.622
 night-0.620
 end-0.612
 of-0.600
 eye-0.596
Token with
Token ID351
Feature activation-3.03e+00

Pos logit contributions
chard+0.378
rily+0.364
 angrily+0.364
nam+0.363
 appet+0.359
Neg logit contributions
 night-0.388
 day-0.385
 end-0.371
 eye-0.368
 of-0.357
Token her
Token ID607
Feature activation+6.23e-01

Pos logit contributions
chard+0.180
 appet+0.178
 angrily+0.174
rily+0.173
 handful+0.167
Neg logit contributions
 night-0.156
 day-0.152
 end-0.148
 eye-0.146
ama-0.143
Token mom
Token ID1995
Feature activation+5.04e+00

Pos logit contributions
 night+0.021
 end+0.021
 eye+0.020
ama+0.020
 day+0.020
Neg logit contributions
chard-0.046
nam-0.045
 Percy-0.044
 Edward-0.044
 handful-0.044
Tokenmy
Token ID1820
Feature activation+4.95e+00

Pos logit contributions
ama+0.195
 eye+0.179
 end+0.178
 night+0.176
opl+0.175
Neg logit contributions
chard-0.338
 handful-0.323
nam-0.318
 appet-0.314
 Edward-0.306
Token,
Token ID11
Feature activation-1.47e-01

Pos logit contributions
 night+0.065
 day+0.063
 eye+0.060
 end+0.060
 of+0.057
Neg logit contributions
chard-0.088
rily-0.084
 appet-0.083
 angrily-0.082
 Edward-0.081
Token Max
Token ID5436
Feature activation-1.26e+00

Pos logit contributions
rily+0.009
ked+0.008
chard+0.008
 angrily+0.008
cher+0.008
Neg logit contributions
 day-0.008
 night-0.008
 of-0.007
 eye-0.007
 end-0.007
Token,
Token ID11
Feature activation-1.11e-01

Pos logit contributions
chard+0.087
nam+0.084
 angrily+0.084
 appet+0.083
rily+0.083
Neg logit contributions
 night-0.051
 day-0.049
 eye-0.048
 end-0.048
ama-0.047
Token to
Token ID284
Feature activation-2.17e-01

Pos logit contributions
chard+0.007
rily+0.007
 angrily+0.007
 appet+0.007
nam+0.006
Neg logit contributions
 night-0.006
 day-0.005
 eye-0.005
 end-0.005
 of-0.005
Token the
Token ID262
Feature activation+7.83e-01

Pos logit contributions
rily+0.014
 angrily+0.014
chard+0.014
 appet+0.014
ked+0.013
Neg logit contributions
 night-0.011
 day-0.010
 end-0.010
 eye-0.010
 of-0.009
Token carn
Token ID18466
Feature activation-8.95e+00

Pos logit contributions
 night+0.027
 day+0.026
 end+0.026
 eye+0.025
ama+0.024
Neg logit contributions
chard-0.059
rily-0.058
 angrily-0.058
 appet-0.058
nam-0.057
Tokenival
Token ID2473
Feature activation-6.81e+00

Pos logit contributions
rily+0.349
chard+0.339
nam+0.327
 angrily+0.326
ked+0.323
Neg logit contributions
 day-0.636
 night-0.623
 of-0.620
 end-0.619
ama-0.598
Token.
Token ID13
Feature activation+6.91e-01

Pos logit contributions
chard+0.542
nam+0.533
rily+0.529
 appet+0.527
ked+0.521
Neg logit contributions
 day-0.233
 night-0.221
 end-0.204
 of-0.203
 eye-0.187
Token Everywhere
Token ID48201
Feature activation-3.73e-01

Pos logit contributions
 night+0.043
 day+0.042
 end+0.041
 eye+0.041
ama+0.040
Neg logit contributions
chard-0.034
rily-0.032
 angrily-0.032
 appet-0.032
nam-0.032
Token they
Token ID484
Feature activation-1.24e-01

Pos logit contributions
chard+0.021
rily+0.020
 angrily+0.020
nam+0.019
 appet+0.019
Neg logit contributions
 night-0.022
 day-0.021
 end-0.020
 of-0.020
ama-0.019
Token looked
Token ID3114
Feature activation-6.37e-01

Pos logit contributions
chard+0.009
 angrily+0.009
rily+0.009
 appet+0.009
nam+0.008
Neg logit contributions
 night-0.005
 day-0.005
 end-0.004
 eye-0.004
ama-0.004
Token and
Token ID290
Feature activation-1.63e-01

Pos logit contributions
 night+0.070
 day+0.067
 eye+0.067
 end+0.067
ama+0.066
Neg logit contributions
chard-0.106
 angrily-0.102
nam-0.101
 appet-0.101
rily-0.101
Token have
Token ID423
Feature activation+7.23e-01

Pos logit contributions
chard+0.011
nam+0.011
 angrily+0.011
 appet+0.011
rily+0.010
Neg logit contributions
 night-0.007
 day-0.007
 eye-0.007
ama-0.006
 end-0.006
Token some
Token ID617
Feature activation+5.56e-01

Pos logit contributions
 night+0.041
 day+0.040
 end+0.039
 eye+0.038
ama+0.037
Neg logit contributions
chard-0.040
rily-0.038
 angrily-0.038
nam-0.037
 appet-0.037
Token breakfast
Token ID12607
Feature activation-2.10e+00

Pos logit contributions
ama+0.031
 eye+0.029
 night+0.029
 end+0.029
oes+0.028
Neg logit contributions
chard-0.028
 appet-0.028
 handful-0.028
nam-0.028
 oh-0.027
Token.
Token ID13
Feature activation+6.76e-01

Pos logit contributions
chard+0.133
 appet+0.128
nam+0.127
 angrily+0.127
rily+0.126
Neg logit contributions
 night-0.095
 eye-0.093
 end-0.092
ama-0.091
 day-0.091
Token How
Token ID1374
Feature activation-8.95e+00

Pos logit contributions
 night+0.041
 day+0.040
 eye+0.039
 end+0.039
ama+0.039
Neg logit contributions
chard-0.034
nam-0.032
 angrily-0.032
rily-0.031
 handful-0.031
Token does
Token ID857
Feature activation-1.74e+00

Pos logit contributions
chard+0.541
 angrily+0.521
 appet+0.519
nam+0.516
rily+0.511
Neg logit contributions
 night-0.429
 eye-0.416
 day-0.416
 end-0.413
ama-0.412
Token that
Token ID326
Feature activation+2.31e+00

Pos logit contributions
chard+0.105
 angrily+0.101
nam+0.100
 appet+0.100
rily+0.099
Neg logit contributions
 night-0.090
 day-0.087
 end-0.085
ama-0.083
 eye-0.082
Token sound
Token ID2128
Feature activation+3.36e-01

Pos logit contributions
ama+0.110
 eye+0.109
 night+0.104
 day+0.101
 end+0.100
Neg logit contributions
 oh-0.132
chard-0.131
 angrily-0.129
 appet-0.128
rily-0.126
Token?"
Token ID1701
Feature activation-4.97e+00

Pos logit contributions
 night+0.016
 day+0.015
 end+0.015
 of+0.015
 eye+0.014
Neg logit contributions
chard-0.023
nam-0.022
rily-0.021
ked-0.021
 angrily-0.021
Token
Token ID198
Feature activation+5.81e-01

Pos logit contributions
 appet+0.339
chard+0.338
rily+0.329
ked+0.327
 handful+0.325
Neg logit contributions
 night-0.211
 day-0.207
 end-0.195
ama-0.192
 of-0.191
Token the
Token ID262
Feature activation+5.36e-01

Pos logit contributions
chard+0.018
 angrily+0.017
 appet+0.017
rily+0.017
nam+0.017
Neg logit contributions
 night-0.018
 day-0.017
 end-0.017
 eye-0.017
ama-0.016
Token park
Token ID3952
Feature activation+8.13e-01

Pos logit contributions
 night+0.020
 end+0.019
 day+0.019
 eye+0.018
ama+0.016
Neg logit contributions
chard-0.039
rily-0.039
 angrily-0.039
ked-0.039
nam-0.038
Token and
Token ID290
Feature activation-2.30e-01

Pos logit contributions
 night+0.035
 day+0.034
 end+0.033
 eye+0.032
 of+0.031
Neg logit contributions
chard-0.055
nam-0.054
 angrily-0.053
rily-0.053
ked-0.053
Token play
Token ID711
Feature activation+1.86e+00

Pos logit contributions
chard+0.016
 angrily+0.015
rily+0.015
nam+0.015
 appet+0.015
Neg logit contributions
 night-0.009
 day-0.009
 end-0.009
 eye-0.009
ama-0.009
Token.
Token ID13
Feature activation+6.49e-01

Pos logit contributions
 end+0.089
 day+0.086
 of+0.086
 night+0.085
 house+0.068
Neg logit contributions
chard-0.134
ked-0.133
nam-0.133
 Percy-0.128
heit-0.124
Token How
Token ID1374
Feature activation-8.95e+00

Pos logit contributions
 night+0.037
 day+0.036
 eye+0.036
ama+0.035
 end+0.035
Neg logit contributions
chard-0.035
 angrily-0.033
rily-0.033
nam-0.033
 handful-0.032
Token does
Token ID857
Feature activation-1.70e+00

Pos logit contributions
chard+0.548
 angrily+0.523
nam+0.522
rily+0.520
 appet+0.515
Neg logit contributions
 night-0.447
 day-0.435
 end-0.427
 eye-0.424
ama-0.414
Token that
Token ID326
Feature activation+2.36e+00

Pos logit contributions
chard+0.112
 angrily+0.109
ked+0.109
nam+0.107
rily+0.107
Neg logit contributions
 night-0.081
 day-0.078
 end-0.076
ama-0.073
 of-0.073
Token sound
Token ID2128
Feature activation+3.02e-01

Pos logit contributions
 eye+0.107
ama+0.106
 night+0.105
 day+0.100
 end+0.098
Neg logit contributions
chard-0.144
 oh-0.141
 appet-0.141
 angrily-0.141
rily-0.137
Token?"
Token ID1701
Feature activation-4.82e+00

Pos logit contributions
 night+0.013
 day+0.013
 end+0.013
 of+0.013
 eye+0.011
Neg logit contributions
chard-0.022
nam-0.021
ked-0.021
rily-0.021
 angrily-0.020
Token mom
Token ID1995
Feature activation+4.66e+00

Pos logit contributions
 appet+0.358
ked+0.345
rily+0.343
 handful+0.342
chard+0.340
Neg logit contributions
 day-0.182
 night-0.182
 end-0.167
ama-0.167
 of-0.166
Token and
Token ID290
Feature activation+5.93e-02

Pos logit contributions
 night+0.077
 day+0.075
 eye+0.074
 end+0.074
ama+0.073
Neg logit contributions
chard-0.115
 angrily-0.111
nam-0.110
rily-0.109
 appet-0.109
Token they
Token ID484
Feature activation-2.62e-01

Pos logit contributions
 night+0.003
 day+0.002
 end+0.002
 eye+0.002
ama+0.002
Neg logit contributions
chard-0.004
rily-0.004
 angrily-0.004
 appet-0.004
nam-0.004
Token walked
Token ID6807
Feature activation+2.44e-01

Pos logit contributions
chard+0.016
nam+0.016
 angrily+0.016
rily+0.015
 handful+0.015
Neg logit contributions
 night-0.012
 eye-0.012
ama-0.012
 day-0.012
 end-0.012
Token through
Token ID832
Feature activation-1.59e+00

Pos logit contributions
 night+0.009
 day+0.009
 of+0.008
 end+0.008
 last+0.008
Neg logit contributions
chard-0.019
 appet-0.019
nam-0.019
RR-0.019
 bluff-0.018
Token the
Token ID262
Feature activation+6.28e-01

Pos logit contributions
 appet+0.106
chard+0.105
rily+0.101
ked+0.100
cher+0.098
Neg logit contributions
 night-0.079
 day-0.075
 end-0.074
 of-0.071
 last-0.066
Token carn
Token ID18466
Feature activation-8.95e+00

Pos logit contributions
ama+0.041
 eye+0.039
 night+0.039
oes+0.037
 day+0.037
Neg logit contributions
chard-0.026
 handful-0.026
 Percy-0.025
 appet-0.025
 Edward-0.025
Tokenival
Token ID2473
Feature activation-6.91e+00

Pos logit contributions
chard+0.315
rily+0.305
nam+0.296
 angrily+0.290
 appet+0.289
Neg logit contributions
 night-0.659
 day-0.657
 end-0.652
 of-0.639
ama-0.634
Token gates
Token ID17435
Feature activation-7.59e-01

Pos logit contributions
chard+0.503
nam+0.484
 angrily+0.483
 appet+0.481
rily+0.481
Neg logit contributions
 night-0.259
 day-0.250
 end-0.243
 eye-0.242
ama-0.234
Token,
Token ID11
Feature activation-2.55e-01

Pos logit contributions
chard+0.047
 angrily+0.046
rily+0.044
nam+0.044
 handful+0.043
Neg logit contributions
ama-0.035
 night-0.033
 eye-0.032
 end-0.031
 day-0.031
Token while
Token ID981
Feature activation-2.40e+00

Pos logit contributions
chard+0.015
rily+0.015
 appet+0.015
 angrily+0.015
nam+0.015
Neg logit contributions
 night-0.013
 day-0.013
 eye-0.012
 end-0.012
 of-0.012
Token Max
Token ID5436
Feature activation-1.50e+00

Pos logit contributions
 appet+0.124
chard+0.122
rily+0.121
 handful+0.117
 angrily+0.115
Neg logit contributions
 night-0.147
 day-0.143
 end-0.139
 of-0.134
ama-0.133
Token your
Token ID534
Feature activation-2.03e+00

Pos logit contributions
chard+0.113
ked+0.110
rily+0.110
 angrily+0.109
 gru+0.106
Neg logit contributions
 night-0.114
 end-0.109
 day-0.109
 of-0.104
 last-0.097
Token favorite
Token ID4004
Feature activation+1.21e+00

Pos logit contributions
chard+0.126
 angrily+0.118
rily+0.117
nam+0.117
 Edward+0.114
Neg logit contributions
 night-0.107
 day-0.105
 end-0.102
 eye-0.102
ama-0.095
Token book
Token ID1492
Feature activation-4.34e+00

Pos logit contributions
 night+0.066
 day+0.065
 end+0.064
 eye+0.062
ama+0.059
Neg logit contributions
chard-0.070
 angrily-0.067
nam-0.066
rily-0.065
ked-0.065
Token together
Token ID1978
Feature activation-2.33e+00

Pos logit contributions
chard+0.260
 angrily+0.249
nam+0.247
 appet+0.247
rily+0.246
Neg logit contributions
 night-0.214
 day-0.208
 eye-0.206
 end-0.205
ama-0.203
Token.
Token ID13
Feature activation+8.36e-01

Pos logit contributions
chard+0.154
 angrily+0.148
 appet+0.148
nam+0.147
rily+0.147
Neg logit contributions
 night-0.099
 eye-0.095
 day-0.095
 end-0.094
ama-0.094
Token How
Token ID1374
Feature activation-8.93e+00

Pos logit contributions
 night+0.048
 day+0.047
 eye+0.046
 end+0.046
ama+0.046
Neg logit contributions
chard-0.044
 angrily-0.042
nam-0.042
rily-0.042
 handful-0.041
Token does
Token ID857
Feature activation-1.66e+00

Pos logit contributions
chard+0.563
nam+0.537
 angrily+0.537
rily+0.533
 appet+0.531
Neg logit contributions
 night-0.426
 day-0.413
 end-0.406
 eye-0.404
ama-0.396
Token that
Token ID326
Feature activation+2.39e+00

Pos logit contributions
chard+0.105
ked+0.103
 angrily+0.102
nam+0.100
 appet+0.100
Neg logit contributions
 night-0.083
 day-0.080
 end-0.079
 of-0.076
ama-0.075
Token sound
Token ID2128
Feature activation+2.36e-01

Pos logit contributions
 eye+0.107
ama+0.107
 night+0.106
 day+0.103
 end+0.100
Neg logit contributions
chard-0.146
 angrily-0.144
 appet-0.142
 oh-0.141
rily-0.139
Token?"
Token ID1701
Feature activation-4.10e+00

Pos logit contributions
 night+0.010
 day+0.010
 end+0.010
 of+0.010
 eye+0.009
Neg logit contributions
chard-0.017
nam-0.016
ked-0.016
rily-0.016
 Percy-0.016
Token
Token ID198
Feature activation+6.21e-01

Pos logit contributions
 appet+0.305
chard+0.304
rily+0.300
 handful+0.299
ked+0.298
Neg logit contributions
 night-0.148
 day-0.144
ama-0.135
 end-0.132
 of-0.128
Token Max
Token ID5436
Feature activation-1.34e+00

Pos logit contributions
 night+0.026
 day+0.026
ama+0.025
 end+0.025
 eye+0.024
Neg logit contributions
chard-0.034
 appet-0.033
nam-0.033
rily-0.033
 angrily-0.032
Token loved
Token ID6151
Feature activation+7.70e-01

Pos logit contributions
chard+0.092
nam+0.089
rily+0.088
 handful+0.086
 angrily+0.086
Neg logit contributions
 night-0.057
 day-0.055
 eye-0.053
 end-0.052
ama-0.051
Token being
Token ID852
Feature activation-1.36e+00

Pos logit contributions
 night+0.039
 day+0.039
 of+0.034
 end+0.033
 eye+0.031
Neg logit contributions
 appet-0.048
rily-0.048
chard-0.048
 angrily-0.047
ked-0.046
Token at
Token ID379
Feature activation-8.12e-01

Pos logit contributions
 appet+0.080
 angrily+0.080
rily+0.079
heit+0.079
chard+0.079
Neg logit contributions
 night-0.070
 day-0.070
 of-0.069
 eye-0.061
 family-0.055
Token the
Token ID262
Feature activation+6.92e-01

Pos logit contributions
chard+0.048
 appet+0.046
 angrily+0.046
rily+0.046
ked+0.045
Neg logit contributions
 night-0.045
 day-0.044
 end-0.041
 eye-0.039
 of-0.038
Token carn
Token ID18466
Feature activation-8.93e+00

Pos logit contributions
 night+0.041
 day+0.040
 end+0.040
 eye+0.039
ama+0.038
Neg logit contributions
chard-0.036
 angrily-0.034
nam-0.034
rily-0.034
 appet-0.033
Tokenival
Token ID2473
Feature activation-6.85e+00

Pos logit contributions
chard+0.320
rily+0.312
nam+0.307
 angrily+0.302
ked+0.296
Neg logit contributions
 day-0.657
 night-0.653
 end-0.640
 of-0.635
ama-0.627
Token so
Token ID523
Feature activation-2.55e+00

Pos logit contributions
chard+0.484
nam+0.466
rily+0.463
 appet+0.461
 angrily+0.461
Neg logit contributions
 night-0.276
 day-0.271
 end-0.260
 eye-0.256
ama-0.244
Token much
Token ID881
Feature activation-5.25e-01

Pos logit contributions
chard+0.147
 angrily+0.143
nam+0.141
rily+0.138
 Edward+0.137
Neg logit contributions
 night-0.131
 eye-0.129
 day-0.127
 end-0.127
ama-0.125
Token that
Token ID326
Feature activation+2.60e+00

Pos logit contributions
chard+0.035
 angrily+0.035
 appet+0.034
nam+0.034
rily+0.034
Neg logit contributions
 night-0.021
 eye-0.021
ama-0.021
 end-0.021
 day-0.021
Token he
Token ID339
Feature activation+6.68e-01

Pos logit contributions
 night+0.146
 eye+0.145
ama+0.143
 end+0.143
 day+0.142
Neg logit contributions
chard-0.136
nam-0.130
 angrily-0.128
 appet-0.127
rily-0.126
Token about
Token ID546
Feature activation-2.65e+00

Pos logit contributions
chard+0.392
 appet+0.381
 angrily+0.378
nam+0.377
 oh+0.370
Neg logit contributions
 night-0.339
ama-0.335
 eye-0.334
 end-0.327
 day-0.326
Token we
Token ID356
Feature activation+8.52e-01

Pos logit contributions
chard+0.152
 angrily+0.150
rily+0.150
 appet+0.146
ked+0.144
Neg logit contributions
 night-0.141
 day-0.138
 end-0.132
 of-0.130
ama-0.127
Token have
Token ID423
Feature activation+9.25e-01

Pos logit contributions
ama+0.035
 night+0.035
 eye+0.034
 day+0.034
opl+0.032
Neg logit contributions
chard-0.057
nam-0.054
 angrily-0.053
 appet-0.053
 Percy-0.053
Token our
Token ID674
Feature activation-3.10e+00

Pos logit contributions
 night+0.052
 day+0.050
 end+0.048
 of+0.047
 eye+0.046
Neg logit contributions
chard-0.052
rily-0.052
 angrily-0.051
nam-0.049
 appet-0.049
Token own
Token ID898
Feature activation+4.97e+00

Pos logit contributions
 appet+0.189
chard+0.186
nam+0.185
 handful+0.184
 Percy+0.181
Neg logit contributions
ama-0.140
 eye-0.130
 end-0.128
 night-0.127
 of-0.125
Token carn
Token ID18466
Feature activation-8.92e+00

Pos logit contributions
 night+0.252
 day+0.245
 eye+0.242
 end+0.242
ama+0.238
Neg logit contributions
chard-0.294
 angrily-0.280
nam-0.280
 appet-0.278
rily-0.277
Tokenival
Token ID2473
Feature activation-6.91e+00

Pos logit contributions
chard+0.300
rily+0.285
 angrily+0.282
nam+0.279
ked+0.265
Neg logit contributions
 day-0.679
 night-0.677
 end-0.666
 of-0.654
ama-0.653
Token at
Token ID379
Feature activation-8.44e-01

Pos logit contributions
chard+0.467
 angrily+0.459
rily+0.458
nam+0.452
ked+0.449
Neg logit contributions
 day-0.307
 night-0.306
 end-0.291
 eye-0.282
 of-0.277
Token home
Token ID1363
Feature activation+1.73e+00

Pos logit contributions
chard+0.049
nam+0.046
 Edward+0.046
 Percy+0.045
 handful+0.045
Neg logit contributions
ama-0.043
 eye-0.042
 night-0.042
 day-0.041
 end-0.040
Token?
Token ID30
Feature activation-9.97e-01

Pos logit contributions
 night+0.076
 day+0.074
 end+0.072
 eye+0.071
ama+0.070
Neg logit contributions
chard-0.116
nam-0.112
 angrily-0.112
rily-0.111
ked-0.110
Token We
Token ID775
Feature activation-1.80e+00

Pos logit contributions
chard+0.056
rily+0.053
nam+0.053
 handful+0.053
 angrily+0.052
Neg logit contributions
 night-0.053
 of-0.052
ama-0.052
 day-0.052
 eye-0.051
Token hear
Token ID3285
Feature activation-6.46e-01

Pos logit contributions
 night+0.141
 day+0.137
ama+0.136
 eye+0.134
 end+0.133
Neg logit contributions
chard-0.178
 angrily-0.170
nam-0.169
 appet-0.168
 handful-0.165
Token the
Token ID262
Feature activation+5.84e-01

Pos logit contributions
chard+0.026
 angrily+0.026
nam+0.025
rily+0.024
 Edward+0.024
Neg logit contributions
ama-0.043
 night-0.043
 day-0.042
 eye-0.042
 end-0.041
Token thunder
Token ID18355
Feature activation+1.29e+00

Pos logit contributions
ama+0.022
 night+0.022
 eye+0.022
 day+0.021
 end+0.021
Neg logit contributions
chard-0.040
 angrily-0.039
nam-0.038
rily-0.038
 appet-0.038
Token and
Token ID290
Feature activation-6.95e-03

Pos logit contributions
ama+0.066
 eye+0.063
 night+0.060
 day+0.058
 end+0.057
Neg logit contributions
 angrily-0.076
ked-0.071
rily-0.071
chard-0.071
 appet-0.070
Token the
Token ID262
Feature activation+5.85e-01

Pos logit contributions
chard+0.000
rily+0.000
 appet+0.000
 angrily+0.000
nam+0.000
Neg logit contributions
 night-0.000
 day-0.000
 end-0.000
 eye-0.000
ama-0.000
Token rain
Token ID6290
Feature activation+4.80e+00

Pos logit contributions
 night+0.020
ama+0.020
 eye+0.020
 day+0.020
 end+0.019
Neg logit contributions
chard-0.043
 angrily-0.041
nam-0.041
 appet-0.041
 handful-0.041
Token.
Token ID13
Feature activation+7.02e-01

Pos logit contributions
ama+0.275
 eye+0.247
ummy+0.237
 night+0.237
 day+0.228
Neg logit contributions
 angrily-0.265
ked-0.256
 dodging-0.242
ged-0.235
 appet-0.232
Token They
Token ID1119
Feature activation-5.54e-01

Pos logit contributions
 night+0.034
 day+0.033
 eye+0.032
 end+0.032
ama+0.032
Neg logit contributions
chard-0.045
nam-0.043
rily-0.042
 handful-0.042
 angrily-0.041
Token did
Token ID750
Feature activation-6.76e-01

Pos logit contributions
chard+0.031
 angrily+0.030
nam+0.030
 appet+0.029
rily+0.029
Neg logit contributions
 night-0.030
 day-0.029
ama-0.029
 eye-0.028
 end-0.028
Token not
Token ID407
Feature activation+2.92e+00

Pos logit contributions
chard+0.052
rily+0.050
nam+0.050
cher+0.049
 handful+0.048
Neg logit contributions
 end-0.026
 night-0.025
 day-0.024
 eye-0.022
 last-0.022
Token notice
Token ID4003
Feature activation-1.72e+00

Pos logit contributions
ama+0.151
 night+0.147
 day+0.144
 eye+0.140
 end+0.138
Neg logit contributions
chard-0.169
 angrily-0.161
nam-0.160
 appet-0.160
 handful-0.157
Token her
Token ID607
Feature activation+4.79e-01

Pos logit contributions
chard+0.072
ked+0.069
 appet+0.068
cher+0.068
nam+0.068
Neg logit contributions
 night-0.073
 day-0.070
 end-0.067
 of-0.067
 eye-0.063
Token delicious
Token ID12625
Feature activation-3.76e+00

Pos logit contributions
 night+0.023
 day+0.022
 end+0.022
 eye+0.022
ama+0.022
Neg logit contributions
chard-0.030
 appet-0.028
nam-0.028
 angrily-0.028
rily-0.028
Token dinner
Token ID8073
Feature activation-1.47e+00

Pos logit contributions
chard+0.180
 appet+0.178
 handful+0.177
rily+0.174
 angrily+0.173
Neg logit contributions
 night-0.218
ama-0.218
 end-0.214
 eye-0.214
 day-0.213
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
chard+0.102
rily+0.098
 angrily+0.098
 appet+0.098
nam+0.097
Neg logit contributions
 night-0.058
 eye-0.057
 end-0.056
ama-0.056
 day-0.055
Token She
Token ID1375
Feature activation-1.77e-01

Pos logit contributions
 end+0.021
 eye+0.021
 night+0.020
 day+0.019
ama+0.019
Neg logit contributions
chard-0.016
 angrily-0.016
nam-0.016
 Edward-0.016
 Percy-0.015
Token never
Token ID1239
Feature activation+4.54e+00

Pos logit contributions
 angrily+0.009
chard+0.009
 appet+0.009
rily+0.009
 handful+0.009
Neg logit contributions
oes-0.009
ama-0.009
 end-0.009
 eye-0.009
 day-0.009
Token felt
Token ID2936
Feature activation-2.08e+00

Pos logit contributions
ama+0.299
opl+0.273
 end+0.266
ummy+0.262
 eye+0.261
Neg logit contributions
chard-0.212
 appet-0.203
 angrily-0.200
nam-0.191
 Edward-0.191
Token so
Token ID523
Feature activation-2.63e+00

Pos logit contributions
chard+0.113
nam+0.108
 angrily+0.107
 appet+0.106
rily+0.106
Neg logit contributions
 night-0.116
 day-0.113
 end-0.111
 eye-0.111
ama-0.107
Token warm
Token ID5814
Feature activation+4.52e+00

Pos logit contributions
chard+0.122
 angrily+0.119
 appet+0.116
rily+0.114
nam+0.113
Neg logit contributions
oes-0.165
ama-0.161
 eye-0.155
 end-0.153
 day-0.152
Token and
Token ID290
Feature activation-2.41e-01

Pos logit contributions
 night+0.216
 day+0.209
 end+0.204
 eye+0.203
ama+0.196
Neg logit contributions
chard-0.285
nam-0.275
 angrily-0.271
 appet-0.268
rily-0.267
Token happy
Token ID3772
Feature activation-1.84e+00

Pos logit contributions
chard+0.013
nam+0.013
 appet+0.012
 oh+0.012
 handful+0.012
Neg logit contributions
ama-0.014
 eye-0.013
oes-0.013
 end-0.013
opl-0.012
Token to
Token ID284
Feature activation-2.25e-01

Pos logit contributions
chard+0.062
nam+0.060
 angrily+0.058
 handful+0.057
 appet+0.057
Neg logit contributions
 eye-0.049
 end-0.049
ama-0.049
 night-0.049
 day-0.047
Token play
Token ID711
Feature activation+2.06e+00

Pos logit contributions
chard+0.013
nam+0.012
 handful+0.012
 oh+0.012
 pret+0.012
Neg logit contributions
ama-0.011
 night-0.010
 eye-0.010
opl-0.010
 end-0.010
Token with
Token ID351
Feature activation-3.00e+00

Pos logit contributions
 day+0.093
 night+0.087
 of+0.086
 end+0.084
 house+0.078
Neg logit contributions
chard-0.150
nam-0.146
rily-0.143
 appet-0.141
 angrily-0.137
Token his
Token ID465
Feature activation-4.26e-02

Pos logit contributions
chard+0.133
 angrily+0.124
 appet+0.124
nam+0.123
rily+0.123
Neg logit contributions
 night-0.200
 day-0.196
 end-0.194
 eye-0.193
ama-0.190
Token toys
Token ID14958
Feature activation-9.99e-02

Pos logit contributions
chard+0.002
nam+0.002
 handful+0.002
 oh+0.002
 angrily+0.002
Neg logit contributions
 end-0.002
 night-0.002
 eye-0.002
ama-0.002
 of-0.002
Token all
Token ID477
Feature activation+4.57e+00

Pos logit contributions
chard+0.005
nam+0.005
 angrily+0.005
 handful+0.005
ked+0.005
Neg logit contributions
ama-0.006
 eye-0.005
opl-0.005
 night-0.005
oes-0.005
Token day
Token ID1110
Feature activation+3.11e+00

Pos logit contributions
ama+0.131
 eye+0.098
ummy+0.073
 parent+0.068
 end+0.061
Neg logit contributions
chard-0.383
nam-0.371
 handful-0.363
 appet-0.351
ged-0.351
Token long
Token ID890
Feature activation+3.01e+00

Pos logit contributions
 end+0.189
 eye+0.188
ama+0.185
 night+0.180
oes+0.176
Neg logit contributions
chard-0.148
nam-0.146
 handful-0.141
 angrily-0.140
rily-0.140
Token.
Token ID13
Feature activation+3.47e-01

Pos logit contributions
ama+0.125
 eye+0.122
 night+0.119
 end+0.116
 day+0.112
Neg logit contributions
chard-0.199
 angrily-0.197
nam-0.194
 appet-0.191
rily-0.190
Token One
Token ID1881
Feature activation+3.91e+00

Pos logit contributions
 night+0.018
 eye+0.018
ama+0.018
 end+0.018
 day+0.017
Neg logit contributions
chard-0.019
 handful-0.018
 appet-0.018
 Percy-0.017
 Edward-0.017
Token day
Token ID1110
Feature activation+3.12e+00

Pos logit contributions
opl+0.121
ama+0.119
el+0.095
bars+0.092
 least+0.091
Neg logit contributions
 oh-0.288
chard-0.265
 football-0.260
 appet-0.259
 handful-0.253
Token naughty
Token ID45128
Feature activation-1.23e+00

Pos logit contributions
chard+0.145
 angrily+0.141
nam+0.136
 appet+0.132
rily+0.131
Neg logit contributions
 night-0.207
 day-0.201
 end-0.200
 eye-0.199
ama-0.198
Token and
Token ID290
Feature activation+1.57e-01

Pos logit contributions
 angrily+0.075
 appet+0.070
 oh+0.069
ked+0.069
rily+0.068
Neg logit contributions
ama-0.060
 night-0.057
 eye-0.056
 day-0.054
 end-0.054
Token rude
Token ID22066
Feature activation-2.32e+00

Pos logit contributions
 night+0.009
 day+0.009
 end+0.009
 eye+0.008
 of+0.008
Neg logit contributions
chard-0.008
rily-0.008
 handful-0.008
 appet-0.008
nam-0.008
Token to
Token ID284
Feature activation-3.52e-01

Pos logit contributions
 angrily+0.158
chard+0.151
 appet+0.150
ked+0.150
rily+0.148
Neg logit contributions
 night-0.094
ama-0.093
 day-0.090
 eye-0.089
 end-0.088
Token his
Token ID465
Feature activation-1.04e-01

Pos logit contributions
chard+0.016
 appet+0.015
 angrily+0.015
nam+0.015
rily+0.015
Neg logit contributions
 night-0.023
 day-0.022
 end-0.022
 eye-0.022
ama-0.022
Token mom
Token ID1995
Feature activation+4.97e+00

Pos logit contributions
 angrily+0.008
chard+0.008
nam+0.008
 appet+0.008
rily+0.008
Neg logit contributions
 night-0.003
ama-0.003
 day-0.003
 eye-0.003
 end-0.003
Token.
Token ID13
Feature activation+9.85e-01

Pos logit contributions
 night+0.215
ama+0.211
 day+0.198
 eye+0.196
 end+0.190
Neg logit contributions
 angrily-0.330
chard-0.312
 oh-0.304
 appet-0.302
nam-0.302
Token He
Token ID679
Feature activation-5.92e-01

Pos logit contributions
 night+0.054
 day+0.053
 end+0.053
 eye+0.052
ama+0.052
Neg logit contributions
chard-0.054
 angrily-0.052
nam-0.052
rily-0.051
 appet-0.051
Token does
Token ID857
Feature activation-1.55e+00

Pos logit contributions
chard+0.034
nam+0.032
 angrily+0.032
 appet+0.032
rily+0.032
Neg logit contributions
 night-0.031
 day-0.031
 eye-0.030
 end-0.030
ama-0.030
Token not
Token ID407
Feature activation+2.91e+00

Pos logit contributions
chard+0.106
rily+0.102
 appet+0.101
nam+0.101
 angrily+0.099
Neg logit contributions
 end-0.066
 night-0.066
 day-0.065
 eye-0.062
ama-0.061
Token listen
Token ID6004
Feature activation-2.71e-01

Pos logit contributions
 night+0.155
ama+0.154
 day+0.151
 eye+0.149
 end+0.146
Neg logit contributions
chard-0.160
 angrily-0.155
 appet-0.153
nam-0.152
 handful-0.149
TokenNow
Token ID3844
Feature activation+6.41e-01

Pos logit contributions
 day+0.015
 end+0.015
 night+0.015
ama+0.015
 of+0.015
Neg logit contributions
chard-0.019
rily-0.018
nam-0.018
 appet-0.018
 Edward-0.018
Token,
Token ID11
Feature activation-3.37e-01

Pos logit contributions
 night+0.025
 day+0.025
 end+0.024
 of+0.023
 eye+0.023
Neg logit contributions
chard-0.048
nam-0.046
rily-0.046
 appet-0.045
cher-0.044
Token Tim
Token ID5045
Feature activation+8.22e-01

Pos logit contributions
rily+0.018
 appet+0.018
chard+0.018
 angrily+0.017
 Edward+0.017
Neg logit contributions
 day-0.020
 night-0.020
 end-0.019
 of-0.019
 eye-0.018
Token and
Token ID290
Feature activation-1.11e-01

Pos logit contributions
ama+0.039
 end+0.038
 night+0.038
 eye+0.038
 day+0.038
Neg logit contributions
 angrily-0.048
chard-0.047
 appet-0.046
 Edward-0.045
 Percy-0.045
Token Sue
Token ID26089
Feature activation-2.32e+00

Pos logit contributions
 appet+0.006
rily+0.006
chard+0.006
cher+0.006
 angrily+0.006
Neg logit contributions
 day-0.007
 night-0.007
 end-0.006
 of-0.006
 eye-0.006
Token both
Token ID1111
Feature activation+4.93e+00

Pos logit contributions
 angrily+0.125
chard+0.123
ked+0.117
nam+0.116
 appet+0.116
Neg logit contributions
ama-0.133
ummy-0.118
 eye-0.113
 day-0.113
 night-0.111
Token felt
Token ID2936
Feature activation-2.17e+00

Pos logit contributions
ama+0.300
 end+0.271
 night+0.269
 eye+0.268
 day+0.266
Neg logit contributions
chard-0.249
 angrily-0.243
nam-0.237
 appet-0.236
ked-0.229
Token sad
Token ID6507
Feature activation-1.45e+00

Pos logit contributions
chard+0.130
rily+0.128
 appet+0.124
 angrily+0.123
 Edward+0.123
Neg logit contributions
 night-0.111
 end-0.109
 day-0.108
 eye-0.104
 of-0.101
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
 angrily+0.088
chard+0.087
 appet+0.085
rily+0.085
 oh+0.084
Neg logit contributions
ama-0.066
 night-0.066
 eye-0.066
 day-0.064
 end-0.063
Token They
Token ID1119
Feature activation-8.95e-01

Pos logit contributions
 night+0.015
 day+0.015
 eye+0.015
 end+0.015
ama+0.015
Neg logit contributions
chard-0.014
nam-0.013
rily-0.013
 appet-0.013
 angrily-0.013
Token could
Token ID714
Feature activation+2.49e+00

Pos logit contributions
chard+0.048
 angrily+0.047
nam+0.047
ked+0.044
 Percy+0.044
Neg logit contributions
ama-0.052
ummy-0.046
 day-0.046
opl-0.046
 eye-0.046
Token were
Token ID547
Feature activation+5.08e-01

Pos logit contributions
 night+0.089
ama+0.088
 eye+0.087
 end+0.086
 day+0.084
Neg logit contributions
chard-0.098
nam-0.092
 angrily-0.092
 appet-0.091
 handful-0.089
Token invited
Token ID9392
Feature activation-1.28e+00

Pos logit contributions
 day+0.026
 night+0.026
 of+0.023
 end+0.023
ama+0.022
Neg logit contributions
 angrily-0.031
 appet-0.031
chard-0.031
rily-0.031
ked-0.030
Token.
Token ID13
Feature activation+5.17e-01

Pos logit contributions
chard+0.102
nam+0.097
rily+0.096
 appet+0.095
 bluff+0.095
Neg logit contributions
 of-0.045
 day-0.045
 night-0.045
 end-0.038
ama-0.037
Token The
Token ID383
Feature activation+1.45e+00

Pos logit contributions
 day+0.024
 night+0.023
 of+0.022
 sky+0.021
 end+0.020
Neg logit contributions
 angrily-0.036
rily-0.035
cher-0.034
 oh-0.034
ked-0.034
Token rabbit
Token ID22746
Feature activation-1.92e+00

Pos logit contributions
 night+0.063
 day+0.061
 end+0.060
 eye+0.059
ama+0.058
Neg logit contributions
chard-0.097
 angrily-0.094
nam-0.093
rily-0.093
 appet-0.093
Token was
Token ID373
Feature activation+7.50e-01

Pos logit contributions
chard+0.135
nam+0.133
rily+0.132
 angrily+0.131
 appet+0.128
Neg logit contributions
 night-0.078
 day-0.078
 end-0.072
 eye-0.071
 of-0.069
Token very
Token ID845
Feature activation-3.09e+00

Pos logit contributions
 day+0.037
 night+0.037
 of+0.034
 end+0.033
 eye+0.032
Neg logit contributions
rily-0.047
 appet-0.047
 angrily-0.047
ked-0.046
chard-0.046
Token excited
Token ID6568
Feature activation-5.66e-01

Pos logit contributions
chard+0.171
 angrily+0.163
nam+0.162
rily+0.161
 appet+0.161
Neg logit contributions
 night-0.170
 day-0.166
 eye-0.163
 end-0.163
ama-0.161
Token to
Token ID284
Feature activation-3.21e-01

Pos logit contributions
chard+0.035
 angrily+0.034
 appet+0.034
 oh+0.033
 Edward+0.033
Neg logit contributions
ama-0.025
 end-0.025
 eye-0.025
 night-0.025
 day-0.024
Token go
Token ID467
Feature activation+1.68e+00

Pos logit contributions
chard+0.022
nam+0.021
 angrily+0.020
 Edward+0.020
rily+0.020
Neg logit contributions
 night-0.013
ama-0.013
 eye-0.013
 day-0.013
 end-0.012
Token to
Token ID284
Feature activation-3.26e-01

Pos logit contributions
 day+0.074
 night+0.074
 of+0.067
 end+0.064
 eye+0.063
Neg logit contributions
 angrily-0.118
chard-0.118
nam-0.117
rily-0.117
ked-0.113
Token.
Token ID13
Feature activation+3.87e-01

Pos logit contributions
chard+0.126
 angrily+0.125
 appet+0.123
rily+0.122
nam+0.121
Neg logit contributions
 night-0.072
ama-0.070
 eye-0.069
 day-0.068
 end-0.067
Token<|endoftext|>
Token ID50256
Feature activation+1.70e+00

Pos logit contributions
 eye+0.024
 end+0.024
 night+0.022
 day+0.022
ama+0.022
Neg logit contributions
 Percy-0.017
 Skip-0.017
 Edward-0.017
 Lewis-0.016
 Clive-0.016
TokenC
Token ID34
Feature activation-5.21e+00

Pos logit contributions
 night+0.068
 day+0.065
 end+0.062
 eye+0.060
ama+0.059
Neg logit contributions
chard-0.124
nam-0.122
 angrily-0.119
rily-0.119
 appet-0.118
Tokenory
Token ID652
Feature activation-4.74e+00

Pos logit contributions
 Edward+0.283
chard+0.278
 Percy+0.272
ports+0.271
Roger+0.271
Neg logit contributions
 eye-0.260
ama-0.242
 of-0.240
 day-0.236
oes-0.233
Token and
Token ID290
Feature activation+1.25e-01

Pos logit contributions
chard+0.269
 appet+0.262
 angrily+0.258
 Edward+0.251
 handful+0.251
Neg logit contributions
ama-0.235
 end-0.233
 eye-0.231
 night-0.229
 day-0.224
Token his
Token ID465
Feature activation-9.70e-02

Pos logit contributions
 night+0.007
 day+0.007
 of+0.007
 end+0.007
 eye+0.007
Neg logit contributions
 appet-0.007
rily-0.007
chard-0.007
 angrily-0.007
ked-0.006
Token best
Token ID1266
Feature activation-8.26e-01

Pos logit contributions
chard+0.007
nam+0.007
 Edward+0.007
 Percy+0.007
 angrily+0.007
Neg logit contributions
 night-0.004
 end-0.003
 eye-0.003
 day-0.003
ama-0.003
Token friend
Token ID1545
Feature activation+1.32e+00

Pos logit contributions
 handful+0.046
 oh+0.043
 donkey+0.042
 football+0.041
ked+0.041
Neg logit contributions
opl-0.043
oes-0.035
ama-0.033
 horizon-0.032
 night-0.032
Token Amber
Token ID21896
Feature activation-5.92e+00

Pos logit contributions
 night+0.060
 day+0.058
 end+0.057
 eye+0.055
ama+0.054
Neg logit contributions
chard-0.088
nam-0.086
rily-0.084
 appet-0.083
 angrily-0.083
Token were
Token ID547
Feature activation+5.04e-01

Pos logit contributions
chard+0.407
nam+0.393
 angrily+0.389
rily+0.387
 appet+0.381
Neg logit contributions
 night-0.252
 day-0.245
 end-0.236
 eye-0.235
ama-0.228
Token playing
Token ID2712
Feature activation-1.11e+00

Pos logit contributions
 night+0.027
 eye+0.027
 end+0.027
 day+0.026
ama+0.026
Neg logit contributions
chard-0.028
nam-0.026
 angrily-0.026
rily-0.026
 Edward-0.025
Token singers
Token ID39113
Feature activation-3.39e+00

Pos logit contributions
 night+0.121
 day+0.117
 of+0.105
 end+0.104
 eye+0.101
Neg logit contributions
 angrily-0.221
rily-0.220
chard-0.220
nam-0.212
 appet-0.211
Token and
Token ID290
Feature activation+1.75e-01

Pos logit contributions
chard+0.254
nam+0.248
 angrily+0.243
rily+0.241
 handful+0.241
Neg logit contributions
 night-0.125
 day-0.121
 end-0.120
 of-0.113
 eye-0.111
Token dancers
Token ID35837
Feature activation-3.87e+00

Pos logit contributions
 night+0.010
 day+0.010
 eye+0.010
 end+0.010
ama+0.010
Neg logit contributions
chard-0.009
nam-0.008
 angrily-0.008
 appet-0.008
rily-0.008
Token when
Token ID618
Feature activation+8.88e-01

Pos logit contributions
chard+0.301
nam+0.294
 angrily+0.292
rily+0.289
 appet+0.289
Neg logit contributions
 night-0.130
 day-0.125
 end-0.121
 eye-0.114
 of-0.113
Token they
Token ID484
Feature activation-5.39e-02

Pos logit contributions
 night+0.055
 day+0.054
 end+0.052
ama+0.050
 of+0.049
Neg logit contributions
chard-0.045
 appet-0.044
rily-0.043
 angrily-0.043
 handful-0.042
Token grow
Token ID1663
Feature activation+1.75e+00

Pos logit contributions
chard+0.003
 Edward+0.003
 appet+0.003
 angrily+0.003
 Percy+0.003
Neg logit contributions
ama-0.003
ummy-0.002
 day-0.002
 eye-0.002
 night-0.002
Token up
Token ID510
Feature activation-4.34e+00

Pos logit contributions
 night+0.098
 day+0.095
 end+0.093
 eye+0.092
ama+0.090
Neg logit contributions
chard-0.098
nam-0.093
 angrily-0.092
 oh-0.091
 appet-0.091
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
chard+0.345
nam+0.333
 appet+0.328
 angrily+0.327
rily+0.326
Neg logit contributions
 night-0.143
 day-0.136
 end-0.132
 eye-0.126
ama-0.123
Token They
Token ID1119
Feature activation-3.22e-01

Pos logit contributions
 night+0.052
 day+0.051
 end+0.048
 eye+0.048
ama+0.047
Neg logit contributions
chard-0.065
nam-0.062
rily-0.061
 angrily-0.061
 handful-0.060
Token know
Token ID760
Feature activation+2.07e+00

Pos logit contributions
chard+0.019
nam+0.018
 Edward+0.018
 appet+0.018
 Percy+0.018
Neg logit contributions
ama-0.016
ummy-0.015
 day-0.014
 night-0.014
 eye-0.014
Token they
Token ID484
Feature activation-3.46e-02

Pos logit contributions
 night+0.116
 day+0.113
 end+0.113
 of+0.108
 eye+0.107
Neg logit contributions
chard-0.115
rily-0.111
 appet-0.109
 angrily-0.108
 handful-0.107
Token
Token ID198
Feature activation+4.81e-01

Pos logit contributions
 night+0.021
 eye+0.021
 end+0.020
 day+0.020
ama+0.019
Neg logit contributions
chard-0.030
 angrily-0.030
 Percy-0.029
 Edward-0.029
 handful-0.029
TokenSuddenly
Token ID38582
Feature activation-3.77e-01

Pos logit contributions
 night+0.025
 day+0.025
 end+0.025
ama+0.024
 eye+0.024
Neg logit contributions
chard-0.028
nam-0.027
rily-0.027
 appet-0.026
 angrily-0.026
Token,
Token ID11
Feature activation-2.91e-01

Pos logit contributions
rily+0.032
chard+0.031
nam+0.031
 appet+0.031
 handful+0.029
Neg logit contributions
 night-0.012
 day-0.011
 end-0.011
 of-0.011
ama-0.010
Token the
Token ID262
Feature activation+5.96e-01

Pos logit contributions
rily+0.018
 appet+0.018
chard+0.016
 handful+0.016
 Ivy+0.016
Neg logit contributions
 night-0.016
 day-0.016
 end-0.016
 of-0.015
 last-0.014
Token light
Token ID1657
Feature activation+5.26e+00

Pos logit contributions
ama+0.022
imi+0.019
oes+0.019
opl+0.018
 eye+0.018
Neg logit contributions
chard-0.043
nam-0.039
 gru-0.039
 appet-0.039
 Percy-0.039
Token became
Token ID2627
Feature activation+1.25e+00

Pos logit contributions
opl+0.317
ama+0.298
oes+0.278
ummy+0.274
 night+0.270
Neg logit contributions
ked-0.249
 angrily-0.249
rily-0.240
chard-0.235
 handful-0.227
Token brighter
Token ID26083
Feature activation-2.29e+00

Pos logit contributions
 night+0.067
 day+0.065
 eye+0.064
 end+0.064
ama+0.063
Neg logit contributions
chard-0.071
 angrily-0.068
nam-0.067
 appet-0.067
rily-0.067
Token and
Token ID290
Feature activation-4.05e-02

Pos logit contributions
rily+0.130
 appet+0.130
 angrily+0.130
chard+0.130
 handful+0.124
Neg logit contributions
ama-0.114
 end-0.109
 night-0.107
 day-0.107
oes-0.105
Token brighter
Token ID26083
Feature activation-2.31e+00

Pos logit contributions
chard+0.002
 angrily+0.002
rily+0.002
nam+0.002
 appet+0.002
Neg logit contributions
 night-0.002
 day-0.002
 end-0.002
 eye-0.002
ama-0.002
Token.
Token ID13
Feature activation+5.20e-01

Pos logit contributions
chard+0.161
 angrily+0.156
 appet+0.155
rily+0.155
nam+0.154
Neg logit contributions
 night-0.091
 day-0.088
 end-0.087
 eye-0.087
ama-0.087
Token Steve
Token ID6542
Feature activation-3.65e+00

Pos logit contributions
 night+0.031
 day+0.030
 eye+0.030
 end+0.030
ama+0.030
Neg logit contributions
chard-0.027
rily-0.026
nam-0.026
 appet-0.025
 handful-0.025
Token help
Token ID1037
Feature activation+5.09e+00

Pos logit contributions
chard+0.026
 Percy+0.025
 Edward+0.025
 Claw+0.025
 angrily+0.025
Neg logit contributions
ama-0.020
opl-0.019
 night-0.018
 day-0.018
 eye-0.018
Token the
Token ID262
Feature activation+5.75e-01

Pos logit contributions
 night+0.294
 day+0.286
 end+0.286
 eye+0.278
ama+0.272
Neg logit contributions
chard-0.274
nam-0.264
 appet-0.260
rily-0.255
 handful-0.254
Token rabbit
Token ID22746
Feature activation-1.97e+00

Pos logit contributions
 night+0.029
ama+0.028
 day+0.028
 eye+0.028
 end+0.028
Neg logit contributions
chard-0.034
 angrily-0.032
 appet-0.032
nam-0.032
rily-0.032
Token and
Token ID290
Feature activation-2.19e-01

Pos logit contributions
chard+0.122
 angrily+0.119
rily+0.117
 handful+0.115
 appet+0.114
Neg logit contributions
 night-0.092
ama-0.091
 day-0.088
 eye-0.087
 end-0.086
Token find
Token ID1064
Feature activation+1.45e+00

Pos logit contributions
chard+0.013
nam+0.012
 angrily+0.012
 appet+0.012
rily+0.012
Neg logit contributions
 night-0.011
 day-0.011
 end-0.011
 eye-0.011
ama-0.011
Token his
Token ID465
Feature activation-1.80e-01

Pos logit contributions
 night+0.090
 day+0.085
 end+0.084
 eye+0.084
 of+0.083
Neg logit contributions
chard-0.077
nam-0.075
 appet-0.074
rily-0.070
 angrily-0.069
Token family
Token ID1641
Feature activation+2.41e+00

Pos logit contributions
chard+0.014
 handful+0.013
 appet+0.013
 angrily+0.013
 donkey+0.013
Neg logit contributions
ama-0.005
oes-0.005
opl-0.005
 of-0.005
 end-0.005
Token.
Token ID13
Feature activation+2.72e-01

Pos logit contributions
 night+0.107
 day+0.104
 end+0.102
 eye+0.100
 of+0.095
Neg logit contributions
chard-0.159
nam-0.153
 angrily-0.153
 appet-0.153
rily-0.152
Token
Token ID220
Feature activation+2.84e-01

Pos logit contributions
 night+0.014
 day+0.014
 eye+0.014
 end+0.014
ama+0.014
Neg logit contributions
chard-0.016
nam-0.015
 appet-0.015
 angrily-0.015
rily-0.015
Token
Token ID198
Feature activation+3.58e-01

Pos logit contributions
 night+0.012
 day+0.012
 eye+0.012
 end+0.012
ama+0.011
Neg logit contributions
chard-0.019
 angrily-0.018
rily-0.018
nam-0.018
 appet-0.018
Token
Token ID198
Feature activation+3.96e-01

Pos logit contributions
 night+0.013
 day+0.013
 end+0.013
ama+0.012
 eye+0.012
Neg logit contributions
chard-0.026
nam-0.025
 appet-0.025
 angrily-0.025
rily-0.025
Token to
Token ID284
Feature activation-4.47e-01

Pos logit contributions
chard+0.032
 angrily+0.030
nam+0.030
 appet+0.030
rily+0.030
Neg logit contributions
 night-0.025
 day-0.024
 eye-0.024
 end-0.024
ama-0.024
Token support
Token ID1104
Feature activation+2.26e+00

Pos logit contributions
chard+0.030
nam+0.029
 angrily+0.029
 Percy+0.028
 handful+0.028
Neg logit contributions
ama-0.018
 night-0.018
 eye-0.018
 day-0.017
 end-0.016
Token her
Token ID607
Feature activation+4.25e-01

Pos logit contributions
 night+0.116
 day+0.113
 end+0.111
 eye+0.106
 of+0.105
Neg logit contributions
chard-0.139
 appet-0.132
rily-0.131
nam-0.129
 handful-0.129
Token no
Token ID645
Feature activation+1.95e+00

Pos logit contributions
 night+0.017
 day+0.017
 eye+0.016
 end+0.016
ama+0.016
Neg logit contributions
chard-0.029
 angrily-0.028
nam-0.028
rily-0.028
 appet-0.028
Token matter
Token ID2300
Feature activation+1.53e+00

Pos logit contributions
ama+0.102
opl+0.089
 eye+0.086
oes+0.084
ummy+0.082
Neg logit contributions
chard-0.111
 handful-0.109
 oh-0.109
 angrily-0.109
rily-0.107
Token what
Token ID644
Feature activation-4.68e+00

Pos logit contributions
 night+0.098
 eye+0.098
ama+0.096
 day+0.095
 end+0.093
Neg logit contributions
chard-0.067
nam-0.065
 angrily-0.064
 oh-0.062
rily-0.062
Token.
Token ID13
Feature activation+2.20e-01

Pos logit contributions
chard+0.301
 angrily+0.294
nam+0.290
 appet+0.287
 Edward+0.286
Neg logit contributions
 eye-0.201
ama-0.196
 night-0.195
 end-0.193
 day-0.188
Token The
Token ID383
Feature activation+1.28e+00

Pos logit contributions
 night+0.012
 end+0.012
 eye+0.012
 day+0.012
ama+0.011
Neg logit contributions
chard-0.012
 angrily-0.011
nam-0.011
 Percy-0.011
 Edward-0.011
Token girl
Token ID2576
Feature activation-2.99e+00

Pos logit contributions
oes+0.047
ama+0.046
opl+0.044
 night+0.043
 eye+0.043
Neg logit contributions
chard-0.088
nam-0.085
 handful-0.085
 angrily-0.084
 appet-0.084
Token smiled
Token ID13541
Feature activation-7.30e-01

Pos logit contributions
 angrily+0.166
chard+0.162
 appet+0.160
 Percy+0.158
rily+0.158
Neg logit contributions
 night-0.152
 end-0.150
 day-0.146
ama-0.146
 eye-0.145
Token happily
Token ID18177
Feature activation-2.35e+00

Pos logit contributions
chard+0.050
nam+0.048
 appet+0.048
 angrily+0.048
rily+0.047
Neg logit contributions
 night-0.031
 day-0.029
 eye-0.029
 end-0.029
ama-0.028
Token his
Token ID465
Feature activation-1.10e-01

Pos logit contributions
rily+0.038
chard+0.038
 appet+0.038
 Edward+0.036
 Percy+0.036
Neg logit contributions
 night-0.031
 eye-0.030
 day-0.030
 end-0.029
 of-0.028
Token scrap
Token ID15881
Feature activation-1.53e+00

Pos logit contributions
nam+0.006
chard+0.006
 angrily+0.006
 handful+0.006
rily+0.005
Neg logit contributions
ama-0.006
 night-0.006
 day-0.006
 end-0.006
 eye-0.006
Tokenes
Token ID274
Feature activation-4.78e+00

Pos logit contributions
chard+0.037
 angrily+0.035
rily+0.033
nam+0.032
 appet+0.032
Neg logit contributions
 night-0.129
 day-0.127
 eye-0.126
 end-0.126
ama-0.125
Token.
Token ID13
Feature activation+3.11e-01

Pos logit contributions
chard+0.393
 appet+0.381
nam+0.379
ports+0.369
 Edward+0.368
Neg logit contributions
 night-0.143
 end-0.142
 day-0.137
 of-0.130
 eye-0.129
Token He
Token ID679
Feature activation-8.74e-01

Pos logit contributions
 day+0.013
 night+0.013
ama+0.013
 eye+0.012
 of+0.012
Neg logit contributions
chard-0.021
 appet-0.021
cher-0.020
rily-0.020
ts-0.020
Token felt
Token ID2936
Feature activation-2.33e+00

Pos logit contributions
chard+0.059
 appet+0.058
rily+0.058
nam+0.056
 handful+0.056
Neg logit contributions
 night-0.037
 eye-0.036
 end-0.036
 day-0.035
 of-0.034
Token sorry
Token ID7926
Feature activation-2.30e+00

Pos logit contributions
chard+0.118
 appet+0.111
rily+0.111
nam+0.110
 handful+0.108
Neg logit contributions
 night-0.140
 end-0.138
 day-0.136
 eye-0.136
 of-0.130
Token for
Token ID329
Feature activation-2.99e+00

Pos logit contributions
 angrily+0.119
 appet+0.111
 oh+0.111
rily+0.108
 handful+0.107
Neg logit contributions
ama-0.128
 night-0.127
 eye-0.123
 day-0.122
opl-0.119
Token him
Token ID683
Feature activation+1.11e+00

Pos logit contributions
 appet+0.160
chard+0.154
rily+0.151
 handful+0.150
 angrily+0.148
Neg logit contributions
 end-0.173
 night-0.170
 day-0.169
 eye-0.158
ama-0.157
Token.
Token ID13
Feature activation+3.63e-01

Pos logit contributions
ama+0.048
 night+0.047
 day+0.045
 eye+0.044
 end+0.043
Neg logit contributions
 angrily-0.073
chard-0.072
nam-0.069
rily-0.069
 handful-0.068
Token
Token ID198
Feature activation+5.69e-01

Pos logit contributions
 day+0.014
 night+0.014
ama+0.013
 end+0.013
 eye+0.013
Neg logit contributions
chard-0.026
rily-0.025
 appet-0.025
nam-0.025
 handful-0.025
Token Annie
Token ID25860
Feature activation-2.89e+00

Pos logit contributions
chard+0.230
nam+0.225
ked+0.218
rily+0.214
 angrily+0.211
Neg logit contributions
 night-0.080
 day-0.077
 of-0.071
ama-0.071
 end-0.070
Token,
Token ID11
Feature activation-6.70e-01

Pos logit contributions
chard+0.221
nam+0.215
 angrily+0.211
 appet+0.209
rily+0.209
Neg logit contributions
 night-0.100
 day-0.096
 eye-0.092
 end-0.092
ama-0.091
Token my
Token ID616
Feature activation-1.89e+00

Pos logit contributions
chard+0.038
rily+0.037
ked+0.037
 appet+0.036
 angrily+0.036
Neg logit contributions
 night-0.037
 day-0.036
 end-0.035
 of-0.034
 eye-0.034
Token name
Token ID1438
Feature activation-2.12e-01

Pos logit contributions
chard+0.118
 angrily+0.114
 appet+0.114
nam+0.113
rily+0.113
Neg logit contributions
 night-0.088
 day-0.085
 end-0.084
 eye-0.084
ama-0.082
Token is
Token ID318
Feature activation+9.27e-01

Pos logit contributions
chard+0.017
nam+0.016
rily+0.016
 appet+0.016
 angrily+0.016
Neg logit contributions
 night-0.008
 day-0.007
 end-0.007
 of-0.007
 eye-0.006
Token Fred
Token ID8559
Feature activation-3.48e+00

Pos logit contributions
 night+0.061
 day+0.059
ama+0.055
 of+0.055
 end+0.053
Neg logit contributions
chard-0.045
ked-0.045
 appet-0.044
nam-0.044
rily-0.043
Token.
Token ID13
Feature activation+4.02e-01

Pos logit contributions
chard+0.293
nam+0.291
rily+0.280
ked+0.279
 angrily+0.278
Neg logit contributions
 night-0.100
 day-0.097
 end-0.091
 of-0.084
 eye-0.082
Token It
Token ID632
Feature activation-1.13e+00

Pos logit contributions
 day+0.020
 of+0.020
 night+0.020
ama+0.020
 end+0.019
Neg logit contributions
chard-0.023
rily-0.023
nam-0.023
ked-0.023
ts-0.022
Token's
Token ID338
Feature activation+3.35e+00

Pos logit contributions
chard+0.083
nam+0.080
rily+0.079
 angrily+0.079
 appet+0.079
Neg logit contributions
 night-0.043
 day-0.041
 end-0.040
 eye-0.039
ama-0.038
Token nice
Token ID3621
Feature activation-8.45e-01

Pos logit contributions
 night+0.179
ama+0.175
 eye+0.174
 day+0.174
 end+0.173
Neg logit contributions
chard-0.183
 angrily-0.175
 appet-0.173
nam-0.172
 Edward-0.171
Token to
Token ID284
Feature activation-3.31e-01

Pos logit contributions
chard+0.051
 angrily+0.050
 appet+0.050
rily+0.049
 handful+0.049
Neg logit contributions
ama-0.038
 night-0.038
 end-0.037
 eye-0.036
 day-0.036
Token.
Token ID13
Feature activation+2.90e-01

Pos logit contributions
ama+0.098
 night+0.097
 eye+0.095
 day+0.092
 end+0.092
Neg logit contributions
chard-0.155
 angrily-0.152
rily-0.150
nam-0.149
 handful-0.144
Token The
Token ID383
Feature activation+1.44e+00

Pos logit contributions
 eye+0.015
 end+0.015
 night+0.015
 day+0.015
ama+0.014
Neg logit contributions
chard-0.016
 angrily-0.015
nam-0.015
 appet-0.015
rily-0.015
Token little
Token ID1310
Feature activation+2.89e+00

Pos logit contributions
opl+0.084
oes+0.079
el+0.078
ama+0.076
 night+0.074
Neg logit contributions
 oh-0.074
nam-0.072
chard-0.069
 angrily-0.064
 handful-0.064
Token girl
Token ID2576
Feature activation-2.90e+00

Pos logit contributions
 night+0.164
ama+0.162
 day+0.158
 eye+0.156
opl+0.156
Neg logit contributions
chard-0.149
nam-0.144
 handful-0.140
 angrily-0.140
 oh-0.138
Token was
Token ID373
Feature activation+7.86e-01

Pos logit contributions
chard+0.172
 angrily+0.168
 appet+0.164
nam+0.164
rily+0.162
Neg logit contributions
 night-0.144
 day-0.138
 end-0.138
 eye-0.138
ama-0.135
Token happy
Token ID3772
Feature activation-1.66e+00

Pos logit contributions
 night+0.042
 day+0.041
 end+0.040
 eye+0.040
ama+0.039
Neg logit contributions
chard-0.044
 appet-0.043
rily-0.043
 angrily-0.042
 Edward-0.042
Token to
Token ID284
Feature activation-2.55e-01

Pos logit contributions
chard+0.098
 angrily+0.097
 oh+0.095
 appet+0.094
nam+0.093
Neg logit contributions
ama-0.080
 eye-0.079
 night-0.079
 end-0.078
 day-0.075
Token help
Token ID1037
Feature activation+5.26e+00

Pos logit contributions
chard+0.012
 oh+0.012
 angrily+0.012
nam+0.012
 tag+0.011
Neg logit contributions
ama-0.013
 night-0.012
opl-0.012
oes-0.012
ummy-0.012
Token her
Token ID607
Feature activation+6.74e-01

Pos logit contributions
 night+0.303
ama+0.289
 day+0.287
opl+0.286
 eye+0.282
Neg logit contributions
 angrily-0.257
 oh-0.255
chard-0.246
nam-0.245
rily-0.239
Token mom
Token ID1995
Feature activation+5.23e+00

Pos logit contributions
 night+0.026
opl+0.024
 day+0.023
oes+0.022
 eye+0.022
Neg logit contributions
 oh-0.047
nam-0.047
chard-0.046
 angrily-0.046
 handful-0.045
Tokenmy
Token ID1820
Feature activation+5.06e+00

Pos logit contributions
ama+0.186
opl+0.183
 night+0.174
 storm+0.161
 eye+0.143
Neg logit contributions
nam-0.374
chard-0.374
 handful-0.354
 angrily-0.349
 oh-0.344
Token subway
Token ID19612
Feature activation-2.17e+00

Pos logit contributions
oes+0.069
ama+0.068
 eye+0.066
 night+0.065
el+0.062
Neg logit contributions
 oh-0.072
ports-0.071
 handful-0.070
nam-0.070
chard-0.069
Token stopped
Token ID5025
Feature activation-4.69e-02

Pos logit contributions
chard+0.129
 angrily+0.126
 appet+0.122
 Percy+0.121
rily+0.121
Neg logit contributions
 night-0.103
ama-0.101
 eye-0.100
 end-0.098
 day-0.097
Token at
Token ID379
Feature activation-8.48e-01

Pos logit contributions
 angrily+0.003
chard+0.003
ked+0.002
 oh+0.002
 dodging+0.002
Neg logit contributions
ama-0.002
 night-0.002
 eye-0.002
 day-0.002
 end-0.002
Token a
Token ID257
Feature activation-1.34e+00

Pos logit contributions
chard+0.046
 angrily+0.044
nam+0.044
 appet+0.044
rily+0.044
Neg logit contributions
 night-0.048
 day-0.046
 end-0.046
 eye-0.045
ama-0.045
Token big
Token ID1263
Feature activation+1.63e+00

Pos logit contributions
chard+0.086
 angrily+0.082
 appet+0.081
nam+0.081
 handful+0.080
Neg logit contributions
 night-0.061
 eye-0.059
 day-0.059
ama-0.059
 end-0.058
Token station
Token ID4429
Feature activation-1.16e+00

Pos logit contributions
 night+0.067
ama+0.066
 eye+0.065
 day+0.065
 end+0.064
Neg logit contributions
chard-0.109
 angrily-0.105
 appet-0.104
nam-0.104
 handful-0.104
Token.
Token ID13
Feature activation+5.75e-01

Pos logit contributions
chard+0.076
 angrily+0.074
 appet+0.072
rily+0.072
nam+0.071
Neg logit contributions
ama-0.049
 night-0.049
 eye-0.047
 day-0.047
 end-0.046
Token Mom
Token ID11254
Feature activation+5.33e+00

Pos logit contributions
 night+0.035
 day+0.034
 end+0.034
 eye+0.034
ama+0.033
Neg logit contributions
chard-0.028
 angrily-0.026
nam-0.026
 appet-0.026
rily-0.026
Tokenmy
Token ID1820
Feature activation+5.02e+00

Pos logit contributions
 end+0.175
 night+0.162
 eye+0.157
 day+0.153
opl+0.150
Neg logit contributions
 angrily-0.387
 handful-0.383
ked-0.383
ged-0.372
cher-0.371
Token and
Token ID290
Feature activation-1.26e-01

Pos logit contributions
 night+0.255
 end+0.248
 day+0.247
 eye+0.245
ama+0.239
Neg logit contributions
chard-0.287
 angrily-0.283
 appet-0.276
 handful-0.274
rily-0.274
Token Billy
Token ID15890
Feature activation-1.49e-01

Pos logit contributions
chard+0.007
 appet+0.007
 angrily+0.007
rily+0.007
 Edward+0.007
Neg logit contributions
 night-0.007
 day-0.007
 end-0.006
 eye-0.006
ama-0.006
Token that
Token ID326
Feature activation+2.30e+00

Pos logit contributions
chard+0.093
 appet+0.092
rily+0.089
nam+0.088
 handful+0.087
Neg logit contributions
 night-0.057
 day-0.056
 end-0.056
 of-0.055
ama-0.052
Token the
Token ID262
Feature activation+5.37e-01

Pos logit contributions
 night+0.140
 eye+0.139
ama+0.138
 day+0.136
 end+0.136
Neg logit contributions
chard-0.111
nam-0.106
 angrily-0.105
 appet-0.102
 Edward-0.101
Token gold
Token ID3869
Feature activation+3.02e-01

Pos logit contributions
 night+0.031
ama+0.031
 day+0.030
 eye+0.029
 end+0.029
Neg logit contributions
chard-0.027
 appet-0.026
 angrily-0.026
nam-0.025
 handful-0.025
Token was
Token ID373
Feature activation+5.21e-01

Pos logit contributions
ama+0.015
 night+0.015
 day+0.014
 end+0.014
 eye+0.014
Neg logit contributions
chard-0.016
 angrily-0.016
rily-0.016
ked-0.016
 appet-0.016
Token not
Token ID407
Feature activation+2.84e+00

Pos logit contributions
 night+0.025
 end+0.024
 day+0.024
 eye+0.023
 of+0.022
Neg logit contributions
chard-0.033
rily-0.032
 appet-0.032
 angrily-0.032
nam-0.031
Token worth
Token ID2861
Feature activation-5.50e+00

Pos logit contributions
 night+0.150
 day+0.149
 eye+0.139
 end+0.138
 of+0.138
Neg logit contributions
chard-0.169
rily-0.165
 angrily-0.164
 Edward-0.164
 Percy-0.161
Token it
Token ID340
Feature activation-8.91e-01

Pos logit contributions
rily+0.289
 appet+0.288
chard+0.287
 handful+0.272
 angrily+0.267
Neg logit contributions
 night-0.313
 day-0.307
 end-0.303
 of-0.282
 eye-0.282
Token.
Token ID13
Feature activation+3.34e-01

Pos logit contributions
 angrily+0.058
chard+0.058
 appet+0.056
 oh+0.056
nam+0.056
Neg logit contributions
 night-0.037
ama-0.036
 eye-0.036
 end-0.034
 day-0.034
Token He
Token ID679
Feature activation-9.21e-01

Pos logit contributions
 night+0.018
 day+0.017
 eye+0.017
 end+0.017
ama+0.017
Neg logit contributions
chard-0.019
nam-0.018
 appet-0.018
rily-0.018
 handful-0.018
Token had
Token ID550
Feature activation+9.38e-01

Pos logit contributions
chard+0.054
 angrily+0.053
nam+0.051
 appet+0.051
rily+0.050
Neg logit contributions
 night-0.047
 day-0.046
ama-0.045
 eye-0.045
 end-0.045
Token lost
Token ID2626
Feature activation+1.38e+00

Pos logit contributions
ama+0.055
 night+0.053
 day+0.052
 eye+0.052
 end+0.052
Neg logit contributions
chard-0.048
 angrily-0.047
nam-0.046
 handful-0.045
 oh-0.045
Token,
Token ID11
Feature activation+7.33e-02

Pos logit contributions
 appet+0.177
chard+0.174
 angrily+0.168
 handful+0.167
 oh+0.162
Neg logit contributions
 night-0.178
 day-0.177
opl-0.171
 eye-0.162
ama-0.161
Token can
Token ID460
Feature activation+2.09e+00

Pos logit contributions
 night+0.003
 day+0.003
 end+0.003
 eye+0.003
ama+0.003
Neg logit contributions
chard-0.005
 angrily-0.004
nam-0.004
rily-0.004
 appet-0.004
Token I
Token ID314
Feature activation-4.63e-01

Pos logit contributions
 night+0.111
 eye+0.108
 day+0.108
 end+0.106
ama+0.105
Neg logit contributions
chard-0.119
nam-0.114
 angrily-0.113
rily-0.111
 appet-0.111
Token touch
Token ID3638
Feature activation+3.55e+00

Pos logit contributions
chard+0.024
 angrily+0.023
 handful+0.023
 appet+0.022
 Ivy+0.021
Neg logit contributions
 night-0.025
 day-0.024
ama-0.024
opl-0.024
ummy-0.022
Token one
Token ID530
Feature activation+2.50e+00

Pos logit contributions
 night+0.207
 day+0.202
 end+0.201
 of+0.197
 eye+0.189
Neg logit contributions
chard-0.189
 angrily-0.188
 appet-0.188
rily-0.183
nam-0.178
Token?"
Token ID1701
Feature activation-4.99e+00

Pos logit contributions
ama+0.133
 night+0.133
 eye+0.127
opl+0.126
 day+0.123
Neg logit contributions
chard-0.138
 handful-0.125
rily-0.123
 oh-0.122
 appet-0.120
Token Sara
Token ID24799
Feature activation-2.06e+00

Pos logit contributions
chard+0.185
 angrily+0.171
nam+0.170
 appet+0.168
rily+0.168
Neg logit contributions
 night-0.366
 day-0.359
 eye-0.356
 end-0.355
ama-0.351
Token begged
Token ID32946
Feature activation+2.16e+00

Pos logit contributions
chard+0.121
 angrily+0.118
nam+0.115
rily+0.115
 appet+0.113
Neg logit contributions
 night-0.106
 day-0.102
 end-0.102
 eye-0.100
ama-0.099
Token.
Token ID13
Feature activation+6.04e-01

Pos logit contributions
 night+0.091
 eye+0.088
 day+0.088
opl+0.087
ama+0.085
Neg logit contributions
chard-0.142
 angrily-0.140
nam-0.137
rily-0.132
 oh-0.132
Token
Token ID198
Feature activation+4.69e-01

Pos logit contributions
 night+0.029
 eye+0.028
 end+0.028
 day+0.027
ama+0.025
Neg logit contributions
chard-0.038
 angrily-0.037
nam-0.036
 Edward-0.035
 oh-0.035
Token
Token ID198
Feature activation+5.07e-01

Pos logit contributions
 eye+0.029
 night+0.027
 end+0.026
 day+0.026
opl+0.025
Neg logit contributions
 angrily-0.022
chard-0.021
 Clive-0.021
 Edward-0.021
 oh-0.020
Token.
Token ID13
Feature activation+7.90e-01

Pos logit contributions
chard+0.066
 angrily+0.063
nam+0.063
rily+0.063
 appet+0.062
Neg logit contributions
 night-0.037
 day-0.035
 end-0.034
 eye-0.034
ama-0.032
Token Now
Token ID2735
Feature activation+5.11e-01

Pos logit contributions
 night+0.048
 eye+0.048
 day+0.047
ama+0.047
 end+0.047
Neg logit contributions
chard-0.039
 angrily-0.036
 handful-0.036
nam-0.036
rily-0.036
Token it
Token ID340
Feature activation-9.28e-01

Pos logit contributions
 night+0.024
 end+0.023
 day+0.023
 eye+0.022
 of+0.021
Neg logit contributions
chard-0.034
 angrily-0.032
rily-0.032
nam-0.032
 appet-0.032
Token is
Token ID318
Feature activation+1.14e+00

Pos logit contributions
 angrily+0.055
 appet+0.054
chard+0.054
 handful+0.053
rily+0.052
Neg logit contributions
ama-0.044
 eye-0.043
 night-0.042
 day-0.041
 end-0.041
Token gone
Token ID3750
Feature activation+2.34e+00

Pos logit contributions
 night+0.060
 day+0.058
 eye+0.057
 end+0.057
ama+0.056
Neg logit contributions
chard-0.066
 angrily-0.063
nam-0.062
 appet-0.062
rily-0.062
Token,"
Token ID553
Feature activation-5.39e+00

Pos logit contributions
 night+0.102
 day+0.098
 eye+0.097
 end+0.097
ama+0.095
Neg logit contributions
chard-0.156
 angrily-0.149
nam-0.149
 appet-0.148
rily-0.148
Token Tom
Token ID4186
Feature activation-1.20e+00

Pos logit contributions
chard+0.303
rily+0.291
 appet+0.290
 angrily+0.284
 handful+0.283
Neg logit contributions
 night-0.293
 day-0.287
 end-0.284
 eye-0.281
ama-0.277
Token said
Token ID531
Feature activation+8.19e-01

Pos logit contributions
chard+0.073
 angrily+0.071
nam+0.070
 appet+0.069
rily+0.069
Neg logit contributions
 night-0.059
 day-0.058
 end-0.057
 eye-0.056
ama-0.056
Token.
Token ID13
Feature activation+6.97e-01

Pos logit contributions
 night+0.025
 day+0.024
 eye+0.024
 end+0.024
ama+0.023
Neg logit contributions
chard-0.065
nam-0.063
 appet-0.063
rily-0.062
 Edward-0.061
Token
Token ID198
Feature activation+4.44e-01

Pos logit contributions
 day+0.022
 night+0.022
 of+0.021
 end+0.020
 eye+0.020
Neg logit contributions
chard-0.056
nam-0.055
rily-0.054
 appet-0.054
 angrily-0.052
Token
Token ID198
Feature activation+4.73e-01

Pos logit contributions
 night+0.022
 eye+0.022
 day+0.021
ama+0.021
 end+0.021
Neg logit contributions
 angrily-0.026
chard-0.025
 handful-0.025
 appet-0.024
rily-0.024
Token.
Token ID13
Feature activation+3.84e-01

Pos logit contributions
 night+0.080
ama+0.080
 day+0.077
 end+0.077
 eye+0.074
Neg logit contributions
chard-0.136
 angrily-0.133
rily-0.130
nam-0.130
 handful-0.129
Token She
Token ID1375
Feature activation-1.32e-01

Pos logit contributions
 night+0.021
 day+0.020
 eye+0.019
 end+0.019
 of+0.019
Neg logit contributions
chard-0.022
nam-0.021
cher-0.021
 handful-0.021
 appet-0.021
Token couldn
Token ID3521
Feature activation+9.96e-01

Pos logit contributions
chard+0.008
 angrily+0.008
nam+0.008
 appet+0.008
rily+0.008
Neg logit contributions
 night-0.007
 day-0.006
 eye-0.006
 end-0.006
ama-0.006
Token't
Token ID470
Feature activation+3.52e+00

Pos logit contributions
 eye+0.057
 night+0.052
 day+0.051
 end+0.049
ama+0.049
Neg logit contributions
 angrily-0.052
 Percy-0.051
 Edward-0.050
chard-0.050
rily-0.050
Token grow
Token ID1663
Feature activation+1.86e+00

Pos logit contributions
ama+0.193
 night+0.182
 day+0.181
opl+0.173
 eye+0.170
Neg logit contributions
chard-0.197
 angrily-0.190
 appet-0.182
rily-0.181
nam-0.181
Token anything
Token ID1997
Feature activation-5.20e+00

Pos logit contributions
 night+0.089
 end+0.085
 day+0.085
 eye+0.083
 of+0.082
Neg logit contributions
chard-0.119
nam-0.116
 appet-0.112
 oh-0.112
 angrily-0.111
Token else
Token ID2073
Feature activation-2.77e+00

Pos logit contributions
chard+0.320
nam+0.305
 angrily+0.302
rily+0.302
 appet+0.301
Neg logit contributions
 night-0.256
 day-0.250
 end-0.244
 eye-0.242
ama-0.233
Token because
Token ID780
Feature activation+1.13e+00

Pos logit contributions
chard+0.184
 angrily+0.178
 appet+0.176
nam+0.175
rily+0.173
Neg logit contributions
 night-0.118
ama-0.117
 eye-0.114
 end-0.113
 day-0.113
Token the
Token ID262
Feature activation+6.97e-01

Pos logit contributions
 eye+0.075
 night+0.074
ama+0.073
 end+0.073
 day+0.072
Neg logit contributions
chard-0.049
nam-0.046
 angrily-0.045
rily-0.044
 handful-0.043
Token fake
Token ID8390
Feature activation-2.42e+00

Pos logit contributions
 night+0.030
 day+0.030
 end+0.029
 eye+0.029
ama+0.028
Neg logit contributions
chard-0.047
 angrily-0.045
nam-0.045
rily-0.045
 appet-0.045
Token plant
Token ID4618
Feature activation+1.22e+00

Pos logit contributions
chard+0.160
 angrily+0.153
 appet+0.152
rily+0.151
nam+0.151
Neg logit contributions
 night-0.105
 day-0.101
ama-0.100
 end-0.100
 eye-0.100
Token.
Token ID13
Feature activation+2.10e-01

Pos logit contributions
ama+0.174
 eye+0.166
 night+0.165
 day+0.164
 end+0.162
Neg logit contributions
chard-0.244
 angrily-0.243
rily-0.240
 appet-0.236
 handful-0.236
Token Suddenly
Token ID24975
Feature activation-8.71e-01

Pos logit contributions
 night+0.011
 day+0.011
ama+0.010
 end+0.010
 eye+0.010
Neg logit contributions
chard-0.013
nam-0.012
 appet-0.012
rily-0.012
 handful-0.012
Token,
Token ID11
Feature activation-4.93e-01

Pos logit contributions
chard+0.072
nam+0.070
rily+0.070
 appet+0.070
 angrily+0.067
Neg logit contributions
 night-0.028
 day-0.026
 end-0.026
 of-0.024
 eye-0.023
Token he
Token ID339
Feature activation+4.67e-01

Pos logit contributions
 appet+0.030
rily+0.029
chard+0.028
ked+0.028
 angrily+0.028
Neg logit contributions
 night-0.028
 day-0.026
 end-0.025
 of-0.024
 last-0.023
Token felt
Token ID2936
Feature activation-2.21e+00

Pos logit contributions
 night+0.027
 day+0.027
 eye+0.026
 end+0.026
ama+0.026
Neg logit contributions
chard-0.024
 angrily-0.023
nam-0.023
 appet-0.022
rily-0.022
Token something
Token ID1223
Feature activation-4.97e+00

Pos logit contributions
chard+0.095
 angrily+0.090
nam+0.088
 appet+0.087
rily+0.087
Neg logit contributions
 night-0.147
 day-0.144
ama-0.143
 eye-0.142
 end-0.141
Token wet
Token ID9583
Feature activation+3.10e+00

Pos logit contributions
chard+0.269
 angrily+0.263
rily+0.256
 handful+0.255
 appet+0.254
Neg logit contributions
 night-0.269
ama-0.263
 day-0.262
 eye-0.259
 end-0.256
Token on
Token ID319
Feature activation-3.80e+00

Pos logit contributions
 night+0.177
 day+0.173
 eye+0.170
 end+0.170
ama+0.167
Neg logit contributions
chard-0.165
nam-0.156
 angrily-0.156
 appet-0.155
rily-0.154
Token his
Token ID465
Feature activation-2.37e-01

Pos logit contributions
chard+0.162
 angrily+0.152
nam+0.151
rily+0.150
 appet+0.150
Neg logit contributions
 night-0.257
 day-0.252
 eye-0.249
 end-0.248
ama-0.246
Token foot
Token ID2366
Feature activation+2.88e+00

Pos logit contributions
rily+0.013
 angrily+0.012
 handful+0.012
 donkey+0.012
 oh+0.012
Neg logit contributions
 night-0.012
ama-0.012
 day-0.012
oes-0.012
opl-0.012
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
ama+0.148
 night+0.147
 day+0.138
 end+0.138
 eye+0.131
Neg logit contributions
 angrily-0.165
chard-0.155
 handful-0.151
rily-0.151
ged-0.149