TOP ACTIVATIONS
MAX = 0.615

play with the pe b bles and the water . They
loved to play with mar bles . One day , Tim
Once all the mar bles had been released , the
of the pool . Bub bles tried to help her ,
He takes the screw driver and opens the hole .
B ub bles learned that it 's okay
started to use his mar bles to play some interesting games
liked to play with mar bles . She had many mar
They were racing their mar bles down a big hill .
the story is : L otion is important to protect your
with sand and pe b bles . One day
Their tum m ies rum ble . They look for something
especially liked finding pe b bles on the street and playing
The zo oke eper was angry , but also
my showed Billy his screw driver and they decided to build
liked to collect pe b bles from different places . She
Fin 's friend , Bub bles , said , " I
both started rolling the mar bles around and laughing . Suddenly
am back up to Bub bles and said , " Look
was playing with his mar bles in the garden . He

MIN ACTIVATIONS
MIN = -0.532

." And ever since that day , Sarah has
. He had been worried since the start of the line
then he left . Ever since that day , the stage
he stayed with them ever since ! <|endoftext|> One day ,
way . â Ever since that day , the prince
bother him again , and since that day , Runner had
. The crowd cheered loudly since they now knew who the
felt a bit better , since he knew what the smell
tried to remember it ever since . <|endoftext|> Once upon a
they have been friends ever since ! <|endoftext|> Once upon a
a much better person ever since . The wise owl was
the fa ery . Ever since that day , Buzz y
special piece with him , since he knew that it always
their first big trip together since they met . They paused
par rot hadn 't moved since the loud sound .
. Ever since , the cats continued to
to call home . Ever since then , it never rolled
. Molly was very excited since she had never been to
they have been friends ever since . The
's been a long time since I 've been here ,

INTERVAL 0.328 - 0.615
CONTAINS 0.500%

, Tim my accidentally spilled his juice all over the chair
a single chair to sit on and the children wanted to
playing in his bedroom when he heard a knock on the
," Anna says . " He 's a very nice duck
still feel the sunshine on his face and hear the bub

INTERVAL 0.041 - 0.328
CONTAINS 29.622%

her and praised him for recommending something sensible . Then she
. He grabbed his shoe and ran to his bed .
From then on , Robbie has been telling his friends how
their club . They took some sticks and stones and made
" Okay , we will go to church and pray .

INTERVAL -0.246 - 0.041
CONTAINS 68.237%

" You saved me !" From that day on , Lily
so they went over to the man and helped him .
Grand ma ?" asked a three - year - old girl
We did it ! We put the puzzle together !
in exploring . Everyone was excited and they quickly followed him

INTERVAL -0.532 - -0.246
CONTAINS 1.641%

" Tim , come back !" The truck driver
That was your birthday cake !" " O ops
said . The little girl walked to the tree
they 're good to eat ." Ho pper said , "
was a reliable girl named Jane . One day , Jane
Token play
Token ID711
Feature activation+1.44e-01

Pos logit contributions
 since+0.286
oph+0.249
heart+0.240
eter+0.237
 pleasure+0.237
Neg logit contributions
glass-0.271
bles-0.270
driver-0.263
eper-0.261
ithering-0.260
Token with
Token ID351
Feature activation+1.52e-01

Pos logit contributions
glass+0.222
bles+0.222
driver+0.215
eper+0.212
adders+0.212
Neg logit contributions
 since-0.281
oph-0.248
heart-0.240
eter-0.238
 pleasure-0.238
Token the
Token ID262
Feature activation-2.29e-05

Pos logit contributions
bles+0.232
glass+0.229
driver+0.224
eper+0.224
adders+0.220
Neg logit contributions
 since-0.297
oph-0.267
eter-0.257
 pleasure-0.256
heart-0.255
Token pe
Token ID613
Feature activation+1.23e-01

Pos logit contributions
 since+0.000
oph+0.000
heart+0.000
eter+0.000
 aback+0.000
Neg logit contributions
bles-0.000
glass-0.000
driver-0.000
eper-0.000
adders-0.000
Tokenb
Token ID65
Feature activation+1.96e-01

Pos logit contributions
driver+0.184
ithering+0.182
glass+0.180
otion+0.176
 drill+0.172
Neg logit contributions
 since-0.240
heart-0.216
ya-0.208
!".-0.206
eter-0.201
Tokenbles
Token ID7689
Feature activation+5.40e-01

Pos logit contributions
 elbows+0.108
glass+0.106
otion+0.104
 chores+0.104
ithering+0.102
Neg logit contributions
 since-0.522
!".-0.521
heart-0.512
!",-0.484
 Sus-0.482
Token and
Token ID290
Feature activation+9.17e-02

Pos logit contributions
bles+0.880
glass+0.863
driver+0.842
adders+0.831
eper+0.828
Neg logit contributions
 since-0.995
oph-0.904
heart-0.864
 pleasure-0.861
eter-0.859
Token the
Token ID262
Feature activation-3.31e-02

Pos logit contributions
glass+0.152
bles+0.151
ithering+0.151
adders+0.147
driver+0.147
Neg logit contributions
 since-0.171
oph-0.144
 pleasure-0.140
heart-0.140
eter-0.139
Token water
Token ID1660
Feature activation-4.36e-03

Pos logit contributions
 since+0.064
oph+0.058
eter+0.055
 aback+0.055
heart+0.055
Neg logit contributions
bles-0.052
glass-0.051
eper-0.050
driver-0.049
 drill-0.048
Token.
Token ID13
Feature activation+4.77e-02

Pos logit contributions
 since+0.008
oph+0.007
heart+0.007
 pleasure+0.007
eter+0.007
Neg logit contributions
bles-0.007
glass-0.007
driver-0.007
eper-0.007
adders-0.007
Token They
Token ID1119
Feature activation+7.94e-02

Pos logit contributions
glass+0.069
driver+0.069
adders+0.069
bles+0.069
ithering+0.068
Neg logit contributions
 since-0.091
oph-0.085
heart-0.084
ited-0.082
ya-0.082
Token loved
Token ID6151
Feature activation+1.75e-01

Pos logit contributions
 since+0.172
oph+0.150
eter+0.146
heart+0.145
 pleasure+0.145
Neg logit contributions
glass-0.158
bles-0.157
driver-0.153
eper-0.153
ithering-0.151
Token to
Token ID284
Feature activation+4.43e-02

Pos logit contributions
glass+0.257
 drill+0.249
bles+0.245
driver+0.245
eper+0.241
Neg logit contributions
 since-0.335
oph-0.314
 aback-0.304
eter-0.297
 pleasure-0.284
Token play
Token ID711
Feature activation+8.06e-02

Pos logit contributions
bles+0.074
glass+0.074
eper+0.072
driver+0.072
ithering+0.071
Neg logit contributions
 since-0.081
oph-0.069
heart-0.068
 pleasure-0.068
 Mill-0.068
Token with
Token ID351
Feature activation+1.26e-01

Pos logit contributions
bles+0.133
glass+0.132
eper+0.131
adders+0.130
driver+0.130
Neg logit contributions
 since-0.146
!".-0.124
oph-0.121
heart-0.121
 Daisy-0.119
Token mar
Token ID1667
Feature activation+1.59e-01

Pos logit contributions
glass+0.167
bles+0.166
driver+0.161
eper+0.158
ithering+0.158
Neg logit contributions
 since-0.276
oph-0.246
heart-0.239
eter-0.237
 pleasure-0.237
Tokenbles
Token ID7689
Feature activation+5.36e-01

Pos logit contributions
 drill+0.121
 elbows+0.114
otion+0.112
ithering+0.096
glass+0.092
Neg logit contributions
 since-0.418
oph-0.390
!".-0.382
heart-0.373
fy-0.373
Token.
Token ID13
Feature activation+5.96e-02

Pos logit contributions
glass+0.905
ithering+0.888
bles+0.880
driver+0.879
eper+0.875
Neg logit contributions
 since-0.981
oph-0.829
heart-0.800
!".-0.790
eter-0.787
Token One
Token ID1881
Feature activation-5.88e-02

Pos logit contributions
glass+0.091
adders+0.091
driver+0.090
bles+0.088
 drill+0.087
Neg logit contributions
 since-0.105
oph-0.099
 aback-0.098
ited-0.096
heart-0.095
Token day
Token ID1110
Feature activation-4.22e-02

Pos logit contributions
 since+0.088
oph+0.076
eter+0.072
heart+0.072
 pleasure+0.072
Neg logit contributions
bles-0.117
glass-0.116
driver-0.113
ithering-0.113
eper-0.113
Token,
Token ID11
Feature activation+6.81e-02

Pos logit contributions
 since+0.080
oph+0.071
eter+0.069
heart+0.068
 pleasure+0.068
Neg logit contributions
glass-0.067
bles-0.067
driver-0.066
ithering-0.065
adders-0.064
Token Tim
Token ID5045
Feature activation-6.83e-02

Pos logit contributions
bles+0.100
glass+0.100
driver+0.097
ithering+0.095
 drill+0.095
Neg logit contributions
 since-0.132
oph-0.122
eter-0.118
heart-0.118
 pleasure-0.117
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
 since+0.100
eter+0.094
ited+0.092
oph+0.092
heart+0.091
Neg logit contributions
glass-0.058
bles-0.058
His-0.058
hes-0.056
ves-0.055
TokenOnce
Token ID7454
Feature activation+1.27e-01

Pos logit contributions
glass+0.246
bles+0.244
driver+0.237
ithering+0.237
eper+0.237
Neg logit contributions
 since-0.274
oph-0.240
heart-0.233
eter-0.231
 pleasure-0.230
Token all
Token ID477
Feature activation+1.50e-01

Pos logit contributions
glass+0.174
bles+0.173
driver+0.168
ithering+0.166
eper+0.165
Neg logit contributions
 since-0.271
oph-0.241
heart-0.234
 pleasure-0.231
eter-0.231
Token the
Token ID262
Feature activation-1.36e-02

Pos logit contributions
glass+0.282
bles+0.281
driver+0.275
eper+0.272
adders+0.272
Neg logit contributions
 since-0.243
oph-0.208
heart-0.200
eter-0.198
 pleasure-0.197
Token mar
Token ID1667
Feature activation+1.57e-01

Pos logit contributions
 since+0.028
oph+0.025
eter+0.024
 aback+0.024
heart+0.024
Neg logit contributions
bles-0.020
glass-0.020
eper-0.019
driver-0.019
adders-0.019
Tokenbles
Token ID7689
Feature activation+5.34e-01

Pos logit contributions
 drill+0.103
 elbows+0.095
glass+0.091
ithering+0.088
otion+0.086
Neg logit contributions
 since-0.421
 Sus-0.394
oph-0.391
heart-0.389
 aback-0.389
Token had
Token ID550
Feature activation+1.15e-01

Pos logit contributions
bles+0.777
glass+0.770
eper+0.743
driver+0.733
adders+0.729
Neg logit contributions
 since-1.030
oph-0.947
heart-0.932
eter-0.930
 pleasure-0.912
Token been
Token ID587
Feature activation+8.78e-02

Pos logit contributions
glass+0.181
bles+0.178
adders+0.171
driver+0.170
eper+0.168
Neg logit contributions
 since-0.214
heart-0.195
oph-0.190
eter-0.185
ya-0.182
Token released
Token ID2716
Feature activation-6.84e-02

Pos logit contributions
bles+0.135
glass+0.132
eper+0.131
ithering+0.125
adders+0.125
Neg logit contributions
 since-0.166
oph-0.157
heart-0.150
!".-0.146
eter-0.144
Token,
Token ID11
Feature activation+6.74e-02

Pos logit contributions
 since+0.126
oph+0.118
heart+0.110
ya+0.109
 pleasure+0.108
Neg logit contributions
bles-0.109
glass-0.105
driver-0.103
eper-0.102
ithering-0.102
Token the
Token ID262
Feature activation-4.47e-02

Pos logit contributions
glass+0.113
bles+0.113
driver+0.109
eper+0.108
adders+0.107
Neg logit contributions
 since-0.120
oph-0.106
heart-0.103
eter-0.102
 pleasure-0.101
Token of
Token ID286
Feature activation+2.57e-01

Pos logit contributions
 since+0.227
heart+0.216
oph+0.215
ited+0.209
fy+0.207
Neg logit contributions
 chores-0.146
glass-0.144
 drill-0.144
adders-0.134
 homework-0.127
Token the
Token ID262
Feature activation+1.58e-02

Pos logit contributions
adders+0.389
glass+0.385
eper+0.380
bles+0.380
driver+0.379
Neg logit contributions
 since-0.481
oph-0.460
eter-0.423
 aback-0.411
ya-0.406
Token pool
Token ID5933
Feature activation+1.63e-01

Pos logit contributions
glass+0.023
bles+0.023
eper+0.022
 drill+0.022
driver+0.022
Neg logit contributions
 since-0.031
oph-0.029
 aback-0.028
eter-0.027
heart-0.027
Token.
Token ID13
Feature activation+7.18e-02

Pos logit contributions
glass+0.227
bles+0.224
kin+0.214
adders+0.211
hes+0.211
Neg logit contributions
 since-0.314
oph-0.307
 pleasure-0.296
eter-0.295
 aback-0.294
Token Bub
Token ID19645
Feature activation-7.23e-02

Pos logit contributions
glass+0.105
adders+0.103
driver+0.102
ithering+0.101
bles+0.100
Neg logit contributions
 since-0.138
oph-0.129
heart-0.124
ited-0.123
ya-0.122
Tokenbles
Token ID7689
Feature activation+5.31e-01

Pos logit contributions
 since+0.233
oph+0.216
heart+0.212
eter+0.210
 pleasure+0.210
Neg logit contributions
glass-0.020
bles-0.018
driver-0.017
adders-0.015
ithering-0.015
Token tried
Token ID3088
Feature activation-2.33e-02

Pos logit contributions
bles+0.807
glass+0.795
eper+0.772
driver+0.769
adders+0.762
Neg logit contributions
 since-1.035
oph-0.930
eter-0.900
heart-0.897
 pleasure-0.890
Token to
Token ID284
Feature activation-1.42e-02

Pos logit contributions
 since+0.030
 aback+0.022
 Mill+0.022
 Sus+0.022
eter+0.022
Neg logit contributions
glass-0.053
bles-0.052
eper-0.051
adders-0.051
ithering-0.051
Token help
Token ID1037
Feature activation+1.44e-01

Pos logit contributions
 since+0.029
oph+0.026
heart+0.025
 pleasure+0.025
eter+0.025
Neg logit contributions
glass-0.020
bles-0.020
driver-0.019
eper-0.019
adders-0.019
Token her
Token ID607
Feature activation+1.40e-01

Pos logit contributions
bles+0.208
glass+0.207
driver+0.201
ithering+0.198
eper+0.198
Neg logit contributions
 since-0.296
oph-0.267
heart-0.255
eter-0.255
 pleasure-0.254
Token,
Token ID11
Feature activation+6.76e-02

Pos logit contributions
glass+0.259
adders+0.251
driver+0.250
bles+0.249
otion+0.248
Neg logit contributions
 since-0.235
!".-0.193
heart-0.190
eter-0.190
 pleasure-0.190
Token
Token ID198
Feature activation+1.05e-01

Pos logit contributions
glass+0.246
bles+0.244
driver+0.237
ithering+0.237
eper+0.237
Neg logit contributions
 since-0.274
oph-0.240
heart-0.233
eter-0.231
 pleasure-0.230
TokenHe
Token ID1544
Feature activation+4.38e-01

Pos logit contributions
glass+0.173
bles+0.172
driver+0.167
eper+0.166
ithering+0.166
Neg logit contributions
 since-0.195
oph-0.170
heart-0.165
eter-0.164
 pleasure-0.163
Token takes
Token ID2753
Feature activation+7.99e-02

Pos logit contributions
glass+0.687
eper+0.677
bles+0.669
driver+0.657
 sword+0.640
Neg logit contributions
 since-0.823
oph-0.735
heart-0.727
 pleasure-0.723
eter-0.722
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
driver+0.108
glass+0.108
eper+0.106
bles+0.102
adders+0.102
Neg logit contributions
 since-0.171
oph-0.160
heart-0.151
eter-0.149
ited-0.148
Token screw
Token ID9580
Feature activation+2.73e-01

Pos logit contributions
 since+0.034
oph+0.030
heart+0.029
 pleasure+0.029
eter+0.029
Neg logit contributions
glass-0.023
bles-0.022
driver-0.022
eper-0.021
ithering-0.021
Tokendriver
Token ID26230
Feature activation+5.30e-01

Pos logit contributions
ithering+0.365
glass+0.364
otion+0.350
hes+0.350
adders+0.348
Neg logit contributions
 since-0.595
 aback-0.512
!".-0.496
eter-0.487
 Sus-0.483
Token and
Token ID290
Feature activation+9.05e-02

Pos logit contributions
glass+1.040
bles+1.031
ithering+1.014
eper+1.005
adders+1.002
Neg logit contributions
 since-0.823
oph-0.677
heart-0.651
 aback-0.648
eter-0.642
Token opens
Token ID9808
Feature activation+4.57e-02

Pos logit contributions
glass+0.151
bles+0.150
driver+0.148
eper+0.145
adders+0.144
Neg logit contributions
 since-0.165
oph-0.146
heart-0.141
 pleasure-0.139
eter-0.138
Token the
Token ID262
Feature activation-3.81e-02

Pos logit contributions
bles+0.077
driver+0.076
glass+0.075
eper+0.074
ble+0.072
Neg logit contributions
 since-0.081
oph-0.074
heart-0.072
 pleasure-0.070
eter-0.069
Token hole
Token ID7604
Feature activation+9.67e-02

Pos logit contributions
 since+0.081
oph+0.072
 pleasure+0.070
heart+0.070
eter+0.069
Neg logit contributions
bles-0.051
glass-0.051
adders-0.049
ithering-0.049
driver-0.049
Token.
Token ID13
Feature activation+4.39e-02

Pos logit contributions
glass+0.180
ithering+0.176
bles+0.175
adders+0.173
driver+0.173
Neg logit contributions
 since-0.160
oph-0.130
heart-0.128
eter-0.127
!".-0.126
Token
Token ID220
Feature activation+3.28e-02

Pos logit contributions
 since+0.185
oph+0.168
eter+0.162
heart+0.161
 pleasure+0.161
Neg logit contributions
glass-0.163
bles-0.159
eper-0.158
driver-0.157
ithering-0.153
Token
Token ID198
Feature activation+8.23e-02

Pos logit contributions
glass+0.060
bles+0.060
driver+0.059
eper+0.058
ithering+0.058
Neg logit contributions
 since-0.054
oph-0.046
heart-0.044
 pleasure-0.044
eter-0.044
Token
Token ID198
Feature activation+7.48e-02

Pos logit contributions
glass+0.120
bles+0.120
His+0.118
ithering+0.117
eper+0.116
Neg logit contributions
 since-0.160
eter-0.144
 pleasure-0.143
oph-0.143
heart-0.139
TokenB
Token ID33
Feature activation-6.99e-02

Pos logit contributions
glass+0.119
bles+0.117
ithering+0.115
eper+0.113
driver+0.113
Neg logit contributions
 since-0.140
oph-0.124
 pleasure-0.123
eter-0.122
heart-0.121
Tokenub
Token ID549
Feature activation+1.16e-02

Pos logit contributions
 since+0.122
oph+0.110
 sight+0.108
ya+0.107
 pleasure+0.105
Neg logit contributions
bles-0.121
driver-0.113
ithering-0.113
glass-0.108
eper-0.107
Tokenbles
Token ID7689
Feature activation+5.29e-01

Pos logit contributions
glass+0.011
driver+0.010
bles+0.010
adders+0.010
ithering+0.010
Neg logit contributions
 since-0.030
oph-0.027
heart-0.027
ya-0.026
 aback-0.026
Token learned
Token ID4499
Feature activation+1.80e-02

Pos logit contributions
bles+0.888
glass+0.862
eper+0.860
driver+0.839
adders+0.812
Neg logit contributions
 since-0.931
 pleasure-0.831
eter-0.824
oph-0.821
heart-0.799
Token that
Token ID326
Feature activation+5.79e-02

Pos logit contributions
glass+0.030
bles+0.030
ithering+0.030
driver+0.029
eper+0.029
Neg logit contributions
 since-0.033
oph-0.028
heart-0.028
 aback-0.027
eter-0.027
Token it
Token ID340
Feature activation-3.32e-02

Pos logit contributions
bles+0.110
glass+0.108
ithering+0.106
eper+0.106
driver+0.105
Neg logit contributions
 since-0.097
heart-0.078
 pleasure-0.078
 Mill-0.078
oph-0.078
Token's
Token ID338
Feature activation+3.01e-02

Pos logit contributions
 since+0.062
oph+0.055
heart+0.053
 pleasure+0.053
eter+0.052
Neg logit contributions
bles-0.053
glass-0.053
driver-0.052
eper-0.051
adders-0.051
Token okay
Token ID8788
Feature activation+1.26e-01

Pos logit contributions
glass+0.052
bles+0.051
driver+0.050
adders+0.049
eper+0.049
Neg logit contributions
 since-0.055
oph-0.046
heart-0.045
 pleasure-0.045
eter-0.045
Token started
Token ID2067
Feature activation+2.03e-02

Pos logit contributions
glass+0.382
bles+0.380
eper+0.380
driver+0.374
adders+0.356
Neg logit contributions
 since-0.464
oph-0.436
 pleasure-0.415
eter-0.409
heart-0.406
Token to
Token ID284
Feature activation+1.39e-02

Pos logit contributions
glass+0.037
bles+0.037
driver+0.036
eper+0.036
ithering+0.036
Neg logit contributions
 since-0.034
oph-0.029
heart-0.028
eter-0.027
 pleasure-0.027
Token use
Token ID779
Feature activation+1.43e-01

Pos logit contributions
glass+0.020
bles+0.020
driver+0.019
eper+0.019
ithering+0.019
Neg logit contributions
 since-0.028
oph-0.026
eter-0.024
heart-0.024
 pleasure-0.024
Token his
Token ID465
Feature activation+3.61e-01

Pos logit contributions
glass+0.219
bles+0.219
driver+0.216
adders+0.211
eper+0.211
Neg logit contributions
 since-0.277
oph-0.249
heart-0.238
eter-0.235
 pleasure-0.233
Token mar
Token ID1667
Feature activation+1.51e-01

Pos logit contributions
glass+0.554
bles+0.547
driver+0.538
adders+0.527
eper+0.526
Neg logit contributions
 since-0.711
oph-0.635
heart-0.608
eter-0.599
 aback-0.593
Tokenbles
Token ID7689
Feature activation+5.29e-01

Pos logit contributions
otion+0.071
 drill+0.063
glass+0.061
ithering+0.057
 elbows+0.054
Neg logit contributions
 since-0.443
oph-0.405
!".-0.401
eter-0.400
 aback-0.399
Token to
Token ID284
Feature activation-1.37e-02

Pos logit contributions
glass+0.929
bles+0.926
driver+0.905
eper+0.895
ithering+0.893
Neg logit contributions
 since-0.912
oph-0.790
heart-0.762
eter-0.752
 pleasure-0.751
Token play
Token ID711
Feature activation+3.70e-02

Pos logit contributions
 since+0.026
oph+0.022
heart+0.022
 pleasure+0.022
eter+0.021
Neg logit contributions
glass-0.022
bles-0.022
driver-0.021
eper-0.021
ithering-0.021
Token some
Token ID617
Feature activation+8.11e-02

Pos logit contributions
glass+0.059
bles+0.059
driver+0.058
eper+0.057
ithering+0.057
Neg logit contributions
 since-0.069
oph-0.060
heart-0.058
eter-0.058
 pleasure-0.057
Token interesting
Token ID3499
Feature activation-6.28e-02

Pos logit contributions
bles+0.130
glass+0.128
adders+0.122
driver+0.122
eper+0.120
Neg logit contributions
 since-0.150
oph-0.142
 Mill-0.133
 aback-0.131
 pleasure-0.130
Token games
Token ID1830
Feature activation+4.30e-02

Pos logit contributions
 since+0.127
oph+0.118
 pleasure+0.111
eter+0.110
 aback+0.110
Neg logit contributions
glass-0.092
bles-0.091
driver-0.087
adders-0.085
eper-0.085
Token liked
Token ID8288
Feature activation+1.03e-01

Pos logit contributions
eper+0.454
es+0.451
bles+0.444
hes+0.436
driver+0.424
Neg logit contributions
 since-0.687
 pleasure-0.652
 sight-0.642
oph-0.639
 aback-0.626
Token to
Token ID284
Feature activation+1.26e-02

Pos logit contributions
glass+0.175
bles+0.173
driver+0.170
 drill+0.169
eper+0.168
Neg logit contributions
 since-0.180
oph-0.160
 aback-0.156
eter-0.153
 pleasure-0.151
Token play
Token ID711
Feature activation+6.02e-02

Pos logit contributions
bles+0.021
glass+0.021
eper+0.020
ithering+0.020
driver+0.020
Neg logit contributions
 since-0.023
oph-0.020
 pleasure-0.020
heart-0.020
 Mill-0.019
Token with
Token ID351
Feature activation+1.10e-01

Pos logit contributions
adders+0.114
driver+0.114
eper+0.113
ithering+0.112
bles+0.111
Neg logit contributions
 since-0.082
 Daisy-0.075
!".-0.074
 sight-0.068
 Betsy-0.067
Token mar
Token ID1667
Feature activation+1.48e-01

Pos logit contributions
glass+0.203
ithering+0.195
bles+0.193
otion+0.187
adders+0.187
Neg logit contributions
 since-0.179
 Daisy-0.160
 sight-0.156
 Mill-0.155
 Sus-0.155
Tokenbles
Token ID7689
Feature activation+5.28e-01

Pos logit contributions
 drill+0.122
 elbows+0.111
otion+0.110
glass+0.097
ithering+0.095
Neg logit contributions
 since-0.376
oph-0.357
!".-0.343
heart-0.338
fy-0.334
Token.
Token ID13
Feature activation+4.98e-02

Pos logit contributions
glass+0.925
ithering+0.911
driver+0.894
eper+0.885
bles+0.883
Neg logit contributions
 since-0.948
oph-0.787
heart-0.757
!".-0.753
eter-0.747
Token She
Token ID1375
Feature activation+8.88e-02

Pos logit contributions
glass+0.082
bles+0.082
driver+0.081
adders+0.079
ithering+0.079
Neg logit contributions
 since-0.091
oph-0.080
heart-0.077
eter-0.076
 pleasure-0.076
Token had
Token ID550
Feature activation+9.73e-02

Pos logit contributions
bles+0.146
glass+0.146
driver+0.142
eper+0.141
adders+0.139
Neg logit contributions
 since-0.163
oph-0.143
heart-0.140
 pleasure-0.138
eter-0.138
Token many
Token ID867
Feature activation+1.95e-01

Pos logit contributions
glass+0.133
bles+0.133
driver+0.128
adders+0.128
eper+0.126
Neg logit contributions
 since-0.206
oph-0.185
heart-0.184
eter-0.179
 pleasure-0.178
Token mar
Token ID1667
Feature activation+1.30e-01

Pos logit contributions
bles+0.287
glass+0.278
driver+0.268
eper+0.267
adders+0.261
Neg logit contributions
 since-0.397
oph-0.359
heart-0.347
eter-0.344
 pleasure-0.342
Token They
Token ID1119
Feature activation+1.22e-01

Pos logit contributions
glass+0.133
driver+0.133
bles+0.132
ithering+0.132
eper+0.130
Neg logit contributions
 since-0.163
oph-0.155
ya-0.151
ited-0.148
heart-0.147
Token were
Token ID547
Feature activation+2.54e-01

Pos logit contributions
bles+0.180
glass+0.179
eper+0.178
driver+0.175
adders+0.172
Neg logit contributions
 since-0.233
oph-0.216
eter-0.209
heart-0.209
 pleasure-0.204
Token racing
Token ID11717
Feature activation+3.48e-01

Pos logit contributions
bles+0.366
glass+0.364
eper+0.353
driver+0.351
adders+0.349
Neg logit contributions
 since-0.521
oph-0.465
heart-0.449
eter-0.444
 aback-0.440
Token their
Token ID511
Feature activation+2.76e-01

Pos logit contributions
bles+0.554
eper+0.529
glass+0.528
driver+0.522
hips+0.503
Neg logit contributions
 since-0.632
oph-0.631
heart-0.575
 pleasure-0.570
 Mill-0.564
Token mar
Token ID1667
Feature activation+1.46e-01

Pos logit contributions
bles+0.385
glass+0.375
driver+0.360
eper+0.359
adders+0.352
Neg logit contributions
 since-0.576
oph-0.536
heart-0.518
 aback-0.510
eter-0.496
Tokenbles
Token ID7689
Feature activation+5.27e-01

Pos logit contributions
otion+0.085
 drill+0.082
glass+0.072
hes+0.072
 elbows+0.071
Neg logit contributions
 since-0.405
oph-0.376
!".-0.374
eter-0.374
fy-0.367
Token down
Token ID866
Feature activation+9.34e-03

Pos logit contributions
glass+0.901
bles+0.894
driver+0.874
eper+0.867
ithering+0.865
Neg logit contributions
 since-0.935
oph-0.806
heart-0.780
eter-0.771
 pleasure-0.770
Token a
Token ID257
Feature activation+8.91e-02

Pos logit contributions
bles+0.015
eper+0.015
adders+0.015
ithering+0.015
driver+0.015
Neg logit contributions
 since-0.016
oph-0.016
heart-0.015
ya-0.015
 pleasure-0.014
Token big
Token ID1263
Feature activation+1.09e-01

Pos logit contributions
bles+0.125
 sword+0.123
glass+0.122
 drill+0.119
driver+0.115
Neg logit contributions
 since-0.177
eter-0.168
heart-0.168
oph-0.167
 aback-0.167
Token hill
Token ID12788
Feature activation+1.02e-01

Pos logit contributions
 sword+0.134
 drill+0.120
driver+0.119
 helmet+0.115
glass+0.112
Neg logit contributions
oph-0.236
eter-0.235
 since-0.232
heart-0.224
 aback-0.224
Token.
Token ID13
Feature activation+4.05e-02

Pos logit contributions
bles+0.160
glass+0.156
driver+0.155
hips+0.153
eper+0.151
Neg logit contributions
 since-0.182
oph-0.177
 pleasure-0.168
heart-0.167
ya-0.163
Token the
Token ID262
Feature activation+1.58e-02

Pos logit contributions
adders+0.389
glass+0.385
eper+0.380
bles+0.380
driver+0.379
Neg logit contributions
 since-0.481
oph-0.460
eter-0.423
 aback-0.411
ya-0.406
Token story
Token ID1621
Feature activation+3.84e-01

Pos logit contributions
glass+0.023
bles+0.023
eper+0.022
 drill+0.022
driver+0.022
Neg logit contributions
 since-0.031
oph-0.029
 aback-0.028
eter-0.027
heart-0.027
Token is
Token ID318
Feature activation+2.23e-01

Pos logit contributions
glass+0.554
driver+0.533
bles+0.525
hes+0.518
ves+0.509
Neg logit contributions
 since-0.764
eter-0.711
 aback-0.703
oph-0.697
 pleasure-0.695
Token:
Token ID25
Feature activation+2.45e-01

Pos logit contributions
hes+0.280
eper+0.278
 not+0.269
bles+0.265
glass+0.262
Neg logit contributions
oph-0.474
 since-0.456
heart-0.442
ited-0.430
ksh-0.429
Token L
Token ID406
Feature activation-7.02e-02

Pos logit contributions
 drill+0.391
glass+0.390
eper+0.377
driver+0.374
otion+0.364
Neg logit contributions
oph-0.428
 since-0.414
ited-0.397
 aback-0.385
heart-0.382
Tokenotion
Token ID9650
Feature activation+5.26e-01

Pos logit contributions
 since+0.174
oph+0.161
heart+0.156
!".+0.153
ya+0.153
Neg logit contributions
glass-0.071
driver-0.067
bles-0.067
eper-0.064
adders-0.064
Token is
Token ID318
Feature activation+1.96e-01

Pos logit contributions
bles+0.488
driver+0.476
adders+0.470
glass+0.466
hes+0.459
Neg logit contributions
oph-1.249
 since-1.242
 pleasure-1.192
eter-1.176
ya-1.169
Token important
Token ID1593
Feature activation-3.95e-02

Pos logit contributions
bles+0.261
hes+0.256
 drill+0.243
adders+0.243
 chores+0.242
Neg logit contributions
oph-0.398
 since-0.397
heart-0.373
 aback-0.366
ya-0.361
Token to
Token ID284
Feature activation-1.81e-02

Pos logit contributions
oph+0.069
 since+0.069
ited+0.063
heart+0.061
 aback+0.060
Neg logit contributions
driver-0.065
glass-0.063
bles-0.062
adders-0.061
 drill-0.060
Token protect
Token ID1805
Feature activation+1.64e-01

Pos logit contributions
 since+0.036
oph+0.033
heart+0.031
eter+0.031
 aback+0.031
Neg logit contributions
glass-0.027
bles-0.026
driver-0.026
eper-0.025
ithering-0.025
Token your
Token ID534
Feature activation+8.65e-03

Pos logit contributions
bles+0.257
glass+0.253
eper+0.249
driver+0.246
adders+0.244
Neg logit contributions
 since-0.295
oph-0.291
ited-0.272
 pleasure-0.266
eter-0.262
Token with
Token ID351
Feature activation+1.29e-01

Pos logit contributions
glass+0.564
bles+0.563
driver+0.550
eper+0.543
adders+0.542
Neg logit contributions
 since-0.581
oph-0.508
heart-0.489
 pleasure-0.483
eter-0.483
Token sand
Token ID6450
Feature activation+1.93e-01

Pos logit contributions
glass+0.186
bles+0.185
driver+0.184
adders+0.180
eper+0.180
Neg logit contributions
 since-0.261
oph-0.237
heart-0.226
eter-0.223
ya-0.221
Token and
Token ID290
Feature activation+1.01e-01

Pos logit contributions
glass+0.347
ithering+0.344
eper+0.334
adders+0.334
bles+0.334
Neg logit contributions
 since-0.322
!".-0.268
oph-0.266
heart-0.264
eter-0.261
Token pe
Token ID613
Feature activation+1.05e-01

Pos logit contributions
bles+0.154
glass+0.152
ithering+0.152
driver+0.147
eper+0.146
Neg logit contributions
 since-0.201
oph-0.170
heart-0.168
 pleasure-0.167
eter-0.166
Tokenb
Token ID65
Feature activation+1.77e-01

Pos logit contributions
ithering+0.104
glass+0.103
driver+0.098
otion+0.097
adders+0.093
Neg logit contributions
 since-0.250
heart-0.228
ya-0.227
!".-0.225
eter-0.222
Tokenbles
Token ID7689
Feature activation+5.26e-01

Pos logit contributions
glass+0.082
ithering+0.080
 elbows+0.071
otion+0.070
 drill+0.065
Neg logit contributions
 since-0.494
!".-0.479
heart-0.468
 Sus-0.457
eter-0.453
Token.
Token ID13
Feature activation+4.90e-02

Pos logit contributions
glass+0.909
bles+0.899
ithering+0.882
driver+0.879
eper+0.875
Neg logit contributions
 since-0.920
oph-0.786
heart-0.764
eter-0.755
 pleasure-0.751
Token
Token ID198
Feature activation+3.77e-02

Pos logit contributions
glass+0.075
bles+0.075
driver+0.074
adders+0.073
ithering+0.073
Neg logit contributions
 since-0.094
oph-0.085
heart-0.082
eter-0.080
ya-0.080
Token
Token ID198
Feature activation+3.52e-02

Pos logit contributions
glass+0.072
bles+0.072
driver+0.070
eper+0.069
adders+0.069
Neg logit contributions
 since-0.060
oph-0.051
heart-0.048
 pleasure-0.048
eter-0.047
TokenOne
Token ID3198
Feature activation+9.33e-02

Pos logit contributions
bles+0.060
glass+0.060
driver+0.059
adders+0.058
eper+0.057
Neg logit contributions
 since-0.063
oph-0.054
heart-0.052
ya-0.051
!".-0.051
Token day
Token ID1110
Feature activation-5.56e-02

Pos logit contributions
glass+0.197
bles+0.197
driver+0.194
ithering+0.191
eper+0.191
Neg logit contributions
 since-0.131
oph-0.107
heart-0.104
 pleasure-0.102
eter-0.101
Token Their
Token ID5334
Feature activation+3.94e-01

Pos logit contributions
 since+0.613
eter+0.571
 aback+0.560
oph+0.554
 pleasure+0.538
Neg logit contributions
bles-0.416
eper-0.389
otion-0.388
driver-0.387
adders-0.380
Token tum
Token ID11814
Feature activation+6.37e-02

Pos logit contributions
glass+0.517
bles+0.515
driver+0.498
eper+0.494
adders+0.487
Neg logit contributions
 since-0.853
oph-0.767
heart-0.743
eter-0.734
 pleasure-0.730
Tokenm
Token ID76
Feature activation+2.57e-01

Pos logit contributions
ithering+0.121
glass+0.116
adders+0.115
ither+0.112
bles+0.111
Neg logit contributions
 since-0.109
heart-0.091
oph-0.083
 Sus-0.083
!".-0.082
Tokenies
Token ID444
Feature activation+1.78e-01

Pos logit contributions
glass+0.430
driver+0.417
adders+0.411
ithering+0.399
bles+0.395
Neg logit contributions
 since-0.485
heart-0.435
oph-0.402
eter-0.399
 Sus-0.396
Token rum
Token ID7440
Feature activation+3.73e-02

Pos logit contributions
glass+0.285
bles+0.284
driver+0.277
eper+0.274
ithering+0.273
Neg logit contributions
 since-0.332
oph-0.293
heart-0.282
eter-0.280
 pleasure-0.279
Tokenble
Token ID903
Feature activation+5.26e-01

Pos logit contributions
glass+0.059
driver+0.058
adders+0.058
hips+0.055
bridge+0.053
Neg logit contributions
 since-0.073
heart-0.064
eter-0.062
oph-0.060
!".-0.060
Token.
Token ID13
Feature activation+5.78e-02

Pos logit contributions
bles+0.786
driver+0.768
glass+0.767
ithering+0.742
eper+0.741
Neg logit contributions
 since-1.007
oph-0.940
 pleasure-0.901
ya-0.877
 aback-0.873
Token They
Token ID1119
Feature activation+9.65e-02

Pos logit contributions
glass+0.077
driver+0.075
His+0.075
ithering+0.074
otion+0.073
Neg logit contributions
 since-0.112
oph-0.107
ited-0.107
heart-0.104
ya-0.104
Token look
Token ID804
Feature activation+1.12e-01

Pos logit contributions
glass+0.149
bles+0.149
driver+0.145
eper+0.144
adders+0.143
Neg logit contributions
 since-0.185
oph-0.165
heart-0.159
eter-0.158
 pleasure-0.157
Token for
Token ID329
Feature activation+9.81e-02

Pos logit contributions
bles+0.125
eper+0.120
hes+0.118
glass+0.116
otion+0.114
Neg logit contributions
 since-0.249
oph-0.239
eter-0.233
 pleasure-0.221
heart-0.220
Token something
Token ID1223
Feature activation+1.05e-01

Pos logit contributions
glass+0.139
bles+0.134
adders+0.131
eper+0.131
 drill+0.128
Neg logit contributions
 since-0.202
oph-0.184
heart-0.176
eter-0.174
 aback-0.174
Token especially
Token ID2592
Feature activation+1.08e-01

Pos logit contributions
glass+0.205
bles+0.204
eper+0.200
driver+0.199
adders+0.198
Neg logit contributions
 since-0.277
oph-0.251
heart-0.245
eter-0.244
 pleasure-0.240
Token liked
Token ID8288
Feature activation+8.97e-02

Pos logit contributions
bles+0.160
glass+0.157
hes+0.155
eper+0.153
adders+0.152
Neg logit contributions
 since-0.208
oph-0.199
 pleasure-0.184
eter-0.183
heart-0.181
Token finding
Token ID4917
Feature activation+1.80e-01

Pos logit contributions
glass+0.151
bles+0.145
 drill+0.145
driver+0.145
adders+0.144
Neg logit contributions
 since-0.157
oph-0.147
 aback-0.139
heart-0.134
eter-0.134
Token pe
Token ID613
Feature activation+1.03e-01

Pos logit contributions
bles+0.265
glass+0.265
adders+0.255
eper+0.254
driver+0.252
Neg logit contributions
 since-0.364
oph-0.329
eter-0.313
heart-0.313
 pleasure-0.309
Tokenb
Token ID65
Feature activation+1.76e-01

Pos logit contributions
glass+0.142
driver+0.139
ithering+0.136
adders+0.133
bles+0.132
Neg logit contributions
 since-0.219
heart-0.192
oph-0.191
ya-0.188
eter-0.187
Tokenbles
Token ID7689
Feature activation+5.24e-01

Pos logit contributions
glass+0.095
otion+0.089
ithering+0.088
 drill+0.086
 elbows+0.085
Neg logit contributions
 since-0.499
heart-0.470
!".-0.466
 Mill-0.455
 Sus-0.452
Token on
Token ID319
Feature activation+3.47e-01

Pos logit contributions
glass+0.830
driver+0.809
bles+0.809
ithering+0.806
eper+0.800
Neg logit contributions
 since-1.006
oph-0.856
heart-0.838
eter-0.826
!".-0.825
Token the
Token ID262
Feature activation-3.93e-02

Pos logit contributions
bles+0.578
glass+0.572
eper+0.552
driver+0.550
ithering+0.543
Neg logit contributions
 since-0.622
oph-0.559
heart-0.544
eter-0.536
 aback-0.531
Token street
Token ID4675
Feature activation+9.33e-03

Pos logit contributions
 since+0.073
oph+0.065
heart+0.063
eter+0.062
 pleasure+0.062
Neg logit contributions
glass-0.064
bles-0.064
driver-0.061
eper-0.061
adders-0.061
Token and
Token ID290
Feature activation+7.93e-02

Pos logit contributions
glass+0.015
bles+0.014
driver+0.014
adders+0.014
eper+0.014
Neg logit contributions
 since-0.017
oph-0.016
 aback-0.015
 pleasure-0.015
heart-0.015
Token playing
Token ID2712
Feature activation+2.25e-01

Pos logit contributions
glass+0.126
bles+0.125
driver+0.122
eper+0.121
adders+0.120
Neg logit contributions
 since-0.150
oph-0.133
heart-0.129
eter-0.127
 pleasure-0.127
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
oph+0.199
 since+0.199
 aback+0.195
ited+0.185
eter+0.184
Neg logit contributions
glass-0.174
adders-0.164
eper-0.160
 drill-0.156
bles-0.156
Token
Token ID198
Feature activation+1.05e-01

Pos logit contributions
glass+0.246
bles+0.244
driver+0.237
ithering+0.237
eper+0.237
Neg logit contributions
 since-0.274
oph-0.240
heart-0.233
eter-0.231
 pleasure-0.230
TokenThe
Token ID464
Feature activation+7.24e-02

Pos logit contributions
glass+0.173
bles+0.172
driver+0.167
eper+0.166
ithering+0.166
Neg logit contributions
 since-0.195
oph-0.170
heart-0.165
eter-0.164
 pleasure-0.163
Token zo
Token ID40565
Feature activation+2.37e-01

Pos logit contributions
bles+0.123
glass+0.122
eper+0.119
driver+0.117
ithering+0.115
Neg logit contributions
 since-0.130
oph-0.116
 aback-0.111
eter-0.111
heart-0.110
Tokenoke
Token ID2088
Feature activation+2.20e-01

Pos logit contributions
glass+0.315
bles+0.313
driver+0.305
ithering+0.304
adders+0.297
Neg logit contributions
 since-0.508
oph-0.451
heart-0.441
eter-0.435
 pleasure-0.434
Tokeneper
Token ID5723
Feature activation+5.23e-01

Pos logit contributions
ithering+0.121
adders+0.106
 chores+0.103
hes+0.100
otion+0.097
Neg logit contributions
 since-0.627
heart-0.577
!".-0.575
ya-0.569
 aback-0.543
Token was
Token ID373
Feature activation+8.95e-02

Pos logit contributions
bles+0.884
glass+0.884
driver+0.873
eper+0.872
adders+0.844
Neg logit contributions
 since-0.932
oph-0.819
 pleasure-0.797
eter-0.786
heart-0.785
Token angry
Token ID7954
Feature activation+1.57e-01

Pos logit contributions
glass+0.144
eper+0.143
bles+0.142
ithering+0.138
driver+0.138
Neg logit contributions
 since-0.169
oph-0.152
heart-0.146
eter-0.143
 pleasure-0.141
Token,
Token ID11
Feature activation+7.79e-02

Pos logit contributions
glass+0.271
bles+0.270
driver+0.263
eper+0.261
ithering+0.260
Neg logit contributions
 since-0.277
oph-0.240
heart-0.232
eter-0.229
 pleasure-0.229
Token but
Token ID475
Feature activation-1.62e-02

Pos logit contributions
driver+0.123
glass+0.120
bles+0.120
eper+0.119
 drill+0.118
Neg logit contributions
 since-0.138
oph-0.136
eter-0.130
 pleasure-0.130
heart-0.125
Token also
Token ID635
Feature activation+3.29e-01

Pos logit contributions
 since+0.038
oph+0.035
 pleasure+0.034
eter+0.034
heart+0.034
Neg logit contributions
bles-0.018
glass-0.018
eper-0.018
driver-0.017
adders-0.017
Tokenmy
Token ID1820
Feature activation+1.11e-01

Pos logit contributions
 since+0.058
 pleasure+0.055
oph+0.055
eter+0.054
 sight+0.054
Neg logit contributions
eper-0.042
bles-0.042
driver-0.040
glass-0.039
 drill-0.038
Token showed
Token ID3751
Feature activation+5.56e-02

Pos logit contributions
bles+0.161
eper+0.158
glass+0.157
driver+0.154
 drill+0.149
Neg logit contributions
 since-0.212
 pleasure-0.203
oph-0.198
eter-0.197
 aback-0.193
Token Billy
Token ID15890
Feature activation-6.33e-02

Pos logit contributions
driver+0.060
eper+0.059
bles+0.056
glass+0.055
 sword+0.054
Neg logit contributions
 since-0.135
oph-0.123
ited-0.120
eter-0.119
ya-0.117
Token his
Token ID465
Feature activation+3.59e-01

Pos logit contributions
 since+0.121
oph+0.106
heart+0.103
eter+0.102
 pleasure+0.101
Neg logit contributions
glass-0.100
bles-0.100
driver-0.097
ithering-0.096
eper-0.096
Token screw
Token ID9580
Feature activation+2.63e-01

Pos logit contributions
glass+0.529
bles+0.527
driver+0.513
eper+0.506
ithering+0.505
Neg logit contributions
 since-0.725
oph-0.641
heart-0.622
eter-0.616
 pleasure-0.616
Tokendriver
Token ID26230
Feature activation+5.23e-01

Pos logit contributions
otion+0.326
ithering+0.323
adders+0.300
 narrative+0.297
ither+0.293
Neg logit contributions
 since-0.594
!".-0.508
 aback-0.508
eter-0.500
 Sus-0.497
Token and
Token ID290
Feature activation+8.80e-02

Pos logit contributions
glass+1.022
bles+1.018
ithering+0.995
driver+0.993
eper+0.990
Neg logit contributions
 since-0.806
oph-0.672
heart-0.647
eter-0.640
 pleasure-0.635
Token they
Token ID484
Feature activation+2.02e-01

Pos logit contributions
glass+0.125
bles+0.124
driver+0.122
eper+0.119
adders+0.117
Neg logit contributions
 since-0.181
oph-0.165
heart-0.159
eter-0.158
 pleasure-0.157
Token decided
Token ID3066
Feature activation-7.24e-02

Pos logit contributions
ithering+0.380
otion+0.374
glass+0.370
adders+0.368
bles+0.366
Neg logit contributions
 since-0.339
 Sus-0.263
oph-0.263
 Mill-0.258
eter-0.253
Token to
Token ID284
Feature activation-2.52e-02

Pos logit contributions
 since+0.108
oph+0.092
heart+0.088
eter+0.086
 pleasure+0.086
Neg logit contributions
glass-0.145
bles-0.144
driver-0.141
eper-0.140
adders-0.139
Token build
Token ID1382
Feature activation+2.65e-01

Pos logit contributions
 since+0.049
oph+0.042
 pleasure+0.042
heart+0.041
eter+0.041
Neg logit contributions
bles-0.039
glass-0.039
adders-0.038
ithering-0.038
eper-0.038
Token liked
Token ID8288
Feature activation+9.29e-02

Pos logit contributions
 since+0.383
oph+0.374
 pleasure+0.373
 sight+0.363
eter+0.362
Neg logit contributions
eper-0.241
es-0.235
bles-0.233
glass-0.230
driver-0.225
Token to
Token ID284
Feature activation+3.94e-03

Pos logit contributions
glass+0.159
bles+0.156
driver+0.156
 drill+0.155
adders+0.152
Neg logit contributions
 since-0.159
oph-0.143
 aback-0.136
eter-0.135
heart-0.135
Token collect
Token ID2824
Feature activation+1.11e-01

Pos logit contributions
bles+0.006
glass+0.006
eper+0.006
driver+0.006
ithering+0.006
Neg logit contributions
 since-0.008
oph-0.007
heart-0.006
 pleasure-0.006
eter-0.006
Token pe
Token ID613
Feature activation+1.05e-01

Pos logit contributions
bles+0.161
glass+0.153
adders+0.152
driver+0.152
eper+0.149
Neg logit contributions
 since-0.227
oph-0.210
eter-0.200
 pleasure-0.198
heart-0.197
Tokenb
Token ID65
Feature activation+1.73e-01

Pos logit contributions
glass+0.142
ithering+0.137
driver+0.136
otion+0.133
adders+0.131
Neg logit contributions
 since-0.224
heart-0.197
ya-0.195
oph-0.192
eter-0.190
Tokenbles
Token ID7689
Feature activation+5.23e-01

Pos logit contributions
glass+0.094
otion+0.086
ithering+0.085
 drill+0.082
 laptop+0.075
Neg logit contributions
 since-0.486
heart-0.463
!".-0.453
 Sus-0.439
 Mill-0.436
Token from
Token ID422
Feature activation+8.33e-02

Pos logit contributions
glass+0.844
bles+0.829
driver+0.816
ithering+0.812
eper+0.809
Neg logit contributions
 since-0.987
oph-0.850
heart-0.828
eter-0.816
 pleasure-0.810
Token different
Token ID1180
Feature activation-8.01e-03

Pos logit contributions
bles+0.123
eper+0.122
glass+0.121
adders+0.116
 drill+0.116
Neg logit contributions
 since-0.161
oph-0.151
heart-0.142
 aback-0.142
eter-0.141
Token places
Token ID4113
Feature activation+2.40e-02

Pos logit contributions
 since+0.015
oph+0.014
ksh+0.013
 pleasure+0.013
eter+0.013
Neg logit contributions
bles-0.013
glass-0.012
eper-0.012
 sword-0.011
driver-0.011
Token.
Token ID13
Feature activation+4.69e-02

Pos logit contributions
glass+0.038
bles+0.038
driver+0.037
adders+0.036
eper+0.036
Neg logit contributions
 since-0.044
oph-0.040
heart-0.039
 pleasure-0.038
eter-0.038
Token She
Token ID1375
Feature activation+8.34e-02

Pos logit contributions
adders+0.065
otion+0.064
ithering+0.063
driver+0.062
glass+0.061
Neg logit contributions
 since-0.088
ited-0.081
oph-0.079
 aback-0.079
heart-0.077
TokenFin
Token ID18467
Feature activation+1.16e-01

Pos logit contributions
glass+0.149
bles+0.146
ithering+0.144
eper+0.142
driver+0.140
Neg logit contributions
 since-0.167
oph-0.148
eter-0.146
 pleasure-0.146
heart-0.145
Token's
Token ID338
Feature activation+6.53e-02

Pos logit contributions
bles+0.174
eper+0.169
glass+0.162
 sword+0.154
driver+0.150
Neg logit contributions
 since-0.213
 pleasure-0.209
oph-0.203
 sight-0.200
eter-0.199
Token friend
Token ID1545
Feature activation+6.39e-02

Pos logit contributions
glass+0.097
bles+0.097
driver+0.095
ithering+0.093
adders+0.093
Neg logit contributions
 since-0.130
oph-0.115
 pleasure-0.112
heart-0.111
eter-0.111
Token,
Token ID11
Feature activation+8.67e-02

Pos logit contributions
eper+0.097
bles+0.094
glass+0.094
driver+0.093
ithering+0.090
Neg logit contributions
 since-0.121
oph-0.109
eter-0.109
 pleasure-0.108
ksh-0.104
Token Bub
Token ID19645
Feature activation-8.27e-02

Pos logit contributions
glass+0.151
bles+0.151
eper+0.151
driver+0.149
ithering+0.145
Neg logit contributions
 since-0.145
oph-0.131
eter-0.127
heart-0.124
 pleasure-0.122
Tokenbles
Token ID7689
Feature activation+5.21e-01

Pos logit contributions
 since+0.263
oph+0.242
heart+0.241
ya+0.237
!".+0.236
Neg logit contributions
glass-0.026
adders-0.023
driver-0.022
hes-0.021
 drill-0.018
Token,
Token ID11
Feature activation+7.41e-02

Pos logit contributions
bles+0.788
eper+0.758
glass+0.755
driver+0.737
ithering+0.727
Neg logit contributions
 since-1.006
oph-0.919
eter-0.909
 pleasure-0.902
heart-0.880
Token said
Token ID531
Feature activation-7.44e-02

Pos logit contributions
glass+0.114
bles+0.113
driver+0.112
eper+0.111
ithering+0.108
Neg logit contributions
 since-0.141
oph-0.129
eter-0.125
 pleasure-0.122
heart-0.122
Token,
Token ID11
Feature activation+6.88e-02

Pos logit contributions
 since+0.129
oph+0.109
heart+0.108
 Mill+0.107
 Sus+0.106
Neg logit contributions
glass-0.131
bles-0.130
ithering-0.126
adders-0.126
driver-0.126
Token "
Token ID366
Feature activation+8.57e-02

Pos logit contributions
glass+0.108
bles+0.108
driver+0.107
eper+0.103
ithering+0.103
Neg logit contributions
 since-0.130
oph-0.117
heart-0.113
eter-0.112
 pleasure-0.110
TokenI
Token ID40
Feature activation+2.67e-02

Pos logit contributions
bles+0.141
glass+0.139
eper+0.139
His+0.138
ithering+0.137
Neg logit contributions
 since-0.146
oph-0.136
 pleasure-0.133
eter-0.129
ya-0.129
Token both
Token ID1111
Feature activation+1.46e-01

Pos logit contributions
glass+0.538
bles+0.536
driver+0.522
eper+0.520
adders+0.516
Neg logit contributions
 since-0.629
oph-0.553
heart-0.540
eter-0.535
 pleasure-0.531
Token started
Token ID2067
Feature activation-1.11e-03

Pos logit contributions
eper+0.205
glass+0.202
adders+0.202
bles+0.198
hes+0.191
Neg logit contributions
 since-0.277
oph-0.263
heart-0.256
eter-0.253
 sight-0.250
Token rolling
Token ID10708
Feature activation+2.14e-01

Pos logit contributions
 since+0.002
oph+0.002
heart+0.002
eter+0.002
 pleasure+0.002
Neg logit contributions
glass-0.002
bles-0.002
driver-0.002
eper-0.002
ithering-0.002
Token the
Token ID262
Feature activation-3.19e-02

Pos logit contributions
bles+0.350
driver+0.339
glass+0.327
eper+0.326
adders+0.323
Neg logit contributions
 since-0.391
oph-0.381
heart-0.353
 pleasure-0.347
eter-0.342
Token mar
Token ID1667
Feature activation+1.41e-01

Pos logit contributions
 since+0.069
oph+0.062
heart+0.060
eter+0.060
 pleasure+0.059
Neg logit contributions
bles-0.043
glass-0.042
driver-0.041
eper-0.040
adders-0.040
Tokenbles
Token ID7689
Feature activation+5.21e-01

Pos logit contributions
otion+0.085
 drill+0.083
 elbows+0.077
glass+0.076
adders+0.067
Neg logit contributions
 since-0.389
oph-0.358
!".-0.352
eter-0.349
 aback-0.346
Token around
Token ID1088
Feature activation-2.12e-05

Pos logit contributions
glass+0.919
bles+0.899
eper+0.884
driver+0.881
ithering+0.878
Neg logit contributions
 since-0.910
oph-0.771
heart-0.746
eter-0.741
 pleasure-0.734
Token and
Token ID290
Feature activation+7.76e-02

Pos logit contributions
 since+0.000
oph+0.000
heart+0.000
eter+0.000
 pleasure+0.000
Neg logit contributions
glass-0.000
bles-0.000
driver-0.000
eper-0.000
ithering-0.000
Token laughing
Token ID14376
Feature activation+1.47e-01

Pos logit contributions
bles+0.119
glass+0.118
driver+0.116
eper+0.113
 drill+0.111
Neg logit contributions
 since-0.146
oph-0.139
heart-0.133
eter-0.129
 pleasure-0.129
Token.
Token ID13
Feature activation+3.54e-02

Pos logit contributions
bles+0.218
glass+0.203
balls+0.200
driver+0.195
es+0.187
Neg logit contributions
 since-0.290
oph-0.287
heart-0.268
ya-0.264
ited-0.261
Token Suddenly
Token ID24975
Feature activation-1.17e-01

Pos logit contributions
glass+0.046
balls+0.046
driver+0.046
adders+0.046
bles+0.044
Neg logit contributions
 since-0.071
heart-0.071
ited-0.071
oph-0.067
ya-0.066
Tokenam
Token ID321
Feature activation+2.52e-01

Pos logit contributions
glass+0.115
driver+0.115
otion+0.113
ithering+0.110
adders+0.109
Neg logit contributions
 since-0.205
eter-0.187
oph-0.186
 pleasure-0.182
heart-0.182
Token back
Token ID736
Feature activation+8.98e-02

Pos logit contributions
bles+0.453
glass+0.438
eper+0.433
driver+0.425
ithering+0.424
Neg logit contributions
 since-0.427
oph-0.390
heart-0.368
eter-0.367
 pleasure-0.367
Token up
Token ID510
Feature activation+5.53e-02

Pos logit contributions
bles+0.164
glass+0.161
eper+0.158
driver+0.158
ithering+0.156
Neg logit contributions
 since-0.147
oph-0.138
heart-0.128
eter-0.124
 pleasure-0.122
Token to
Token ID284
Feature activation-9.55e-03

Pos logit contributions
bles+0.087
glass+0.085
eper+0.084
ithering+0.083
driver+0.083
Neg logit contributions
 since-0.098
oph-0.096
heart-0.091
eter-0.088
 pleasure-0.088
Token Bub
Token ID19645
Feature activation-8.80e-02

Pos logit contributions
 since+0.017
oph+0.016
eter+0.015
heart+0.015
fy+0.015
Neg logit contributions
glass-0.016
eper-0.015
bles-0.015
ithering-0.015
 drill-0.015
Tokenbles
Token ID7689
Feature activation+5.21e-01

Pos logit contributions
 since+0.268
oph+0.246
heart+0.244
ya+0.243
!".+0.241
Neg logit contributions
adders-0.039
glass-0.038
driver-0.037
hes-0.035
otion-0.034
Token and
Token ID290
Feature activation+8.07e-02

Pos logit contributions
glass+0.892
bles+0.888
driver+0.868
eper+0.858
adders+0.858
Neg logit contributions
 since-0.925
oph-0.801
heart-0.773
eter-0.762
 pleasure-0.762
Token said
Token ID531
Feature activation-7.73e-02

Pos logit contributions
bles+0.120
glass+0.117
eper+0.114
driver+0.112
 sword+0.108
Neg logit contributions
 since-0.155
oph-0.147
heart-0.144
eter-0.143
 pleasure-0.142
Token,
Token ID11
Feature activation+6.71e-02

Pos logit contributions
 since+0.127
oph+0.106
 pleasure+0.104
 Mill+0.104
 Sus+0.103
Neg logit contributions
glass-0.142
bles-0.139
ithering-0.138
eper-0.136
driver-0.136
Token "
Token ID366
Feature activation+8.09e-02

Pos logit contributions
bles+0.110
glass+0.110
driver+0.107
eper+0.105
ithering+0.105
Neg logit contributions
 since-0.123
oph-0.109
heart-0.105
eter-0.104
 pleasure-0.103
TokenLook
Token ID8567
Feature activation+1.94e-02

Pos logit contributions
glass+0.144
bles+0.143
eper+0.142
His+0.141
ithering+0.139
Neg logit contributions
 since-0.125
oph-0.113
 pleasure-0.112
eter-0.109
ya-0.109
Token was
Token ID373
Feature activation+8.92e-02

Pos logit contributions
glass+0.362
bles+0.357
eper+0.354
driver+0.347
adders+0.338
Neg logit contributions
 since-0.394
oph-0.352
 pleasure-0.343
eter-0.340
heart-0.339
Token playing
Token ID2712
Feature activation+2.53e-01

Pos logit contributions
glass+0.133
bles+0.131
driver+0.130
adders+0.126
ithering+0.126
Neg logit contributions
 since-0.179
oph-0.153
 pleasure-0.152
heart-0.152
eter-0.150
Token with
Token ID351
Feature activation+1.01e-01

Pos logit contributions
driver+0.467
adders+0.463
glass+0.460
hips+0.458
otion+0.455
Neg logit contributions
 since-0.406
!".-0.330
 Daisy-0.330
 sight-0.325
heart-0.320
Token his
Token ID465
Feature activation+3.53e-01

Pos logit contributions
glass+0.130
ithering+0.129
otion+0.128
bles+0.127
adders+0.123
Neg logit contributions
 since-0.220
 Sus-0.203
 sight-0.202
 Daisy-0.198
 Mill-0.195
Token mar
Token ID1667
Feature activation+1.42e-01

Pos logit contributions
glass+0.523
otion+0.520
adders+0.512
driver+0.509
ithering+0.506
Neg logit contributions
 since-0.698
 pleasure-0.604
oph-0.598
 sight-0.595
ya-0.589
Tokenbles
Token ID7689
Feature activation+5.20e-01

Pos logit contributions
otion+0.113
 drill+0.111
 elbows+0.108
adders+0.094
glass+0.093
Neg logit contributions
 since-0.361
oph-0.341
!".-0.330
heart-0.320
fy-0.316
Token in
Token ID287
Feature activation+1.95e-01

Pos logit contributions
glass+0.841
driver+0.812
bles+0.811
eper+0.808
ithering+0.804
Neg logit contributions
 since-1.007
oph-0.839
heart-0.816
!".-0.812
eter-0.805
Token the
Token ID262
Feature activation-4.42e-02

Pos logit contributions
glass+0.326
bles+0.325
driver+0.316
adders+0.313
ithering+0.312
Neg logit contributions
 since-0.359
oph-0.309
heart-0.300
 pleasure-0.297
eter-0.296
Token garden
Token ID11376
Feature activation+5.41e-02

Pos logit contributions
 since+0.084
oph+0.073
 pleasure+0.070
heart+0.070
eter+0.069
Neg logit contributions
bles-0.071
glass-0.071
driver-0.070
adders-0.069
ithering-0.068
Token.
Token ID13
Feature activation+3.45e-02

Pos logit contributions
glass+0.097
bles+0.096
driver+0.094
eper+0.093
ithering+0.093
Neg logit contributions
 since-0.093
oph-0.079
heart-0.077
eter-0.076
 pleasure-0.075
Token He
Token ID679
Feature activation+2.13e-01

Pos logit contributions
glass+0.044
bles+0.043
driver+0.042
eper+0.041
adders+0.041
Neg logit contributions
 since-0.077
oph-0.070
heart-0.068
eter-0.067
 pleasure-0.067
Token."
Token ID526
Feature activation-2.80e-01

Pos logit contributions
oph+0.213
 since+0.189
heart+0.188
 aback+0.184
 Sus+0.180
Neg logit contributions
bles-0.291
glass-0.278
es-0.267
adders-0.267
eper-0.266
Token
Token ID198
Feature activation-4.29e-02

Pos logit contributions
 since+0.534
ya+0.513
ited+0.505
heart+0.502
oph+0.501
Neg logit contributions
glass-0.405
driver-0.395
 drill-0.373
box-0.366
adders-0.362
Token
Token ID198
Feature activation-4.30e-02

Pos logit contributions
 since+0.075
oph+0.065
heart+0.063
eter+0.063
 pleasure+0.062
Neg logit contributions
glass-0.075
bles-0.074
driver-0.073
eper-0.072
ithering-0.072
TokenAnd
Token ID1870
Feature activation+7.08e-02

Pos logit contributions
 since+0.070
oph+0.060
heart+0.058
 pleasure+0.057
eter+0.057
Neg logit contributions
glass-0.081
bles-0.080
driver-0.078
ithering-0.078
eper-0.077
Token ever
Token ID1683
Feature activation-6.39e-02

Pos logit contributions
glass+0.114
bles+0.106
driver+0.106
hips+0.104
eper+0.104
Neg logit contributions
ksh-0.114
oph-0.111
 since-0.110
eter-0.109
ited-0.109
Token since
Token ID1201
Feature activation-5.29e-01

Pos logit contributions
ksh+0.066
 pleasure+0.064
 refreshing+0.061
 aback+0.059
eter+0.058
Neg logit contributions
bles-0.125
 are-0.121
es-0.119
 not-0.119
glass-0.119
Token that
Token ID326
Feature activation-2.71e-02

Pos logit contributions
eter+0.903
 since+0.898
ksh+0.896
oph+0.886
 aback+0.857
Neg logit contributions
glass-0.803
eper-0.774
hips-0.751
otion-0.744
driver-0.733
Token day
Token ID1110
Feature activation-1.31e-01

Pos logit contributions
eter+0.049
 since+0.048
oph+0.048
ksh+0.046
 pleasure+0.045
Neg logit contributions
kin-0.037
otion-0.037
glass-0.036
es-0.036
 chores-0.036
Token,
Token ID11
Feature activation-1.39e-02

Pos logit contributions
 since+0.225
oph+0.197
heart+0.190
eter+0.190
 pleasure+0.189
Neg logit contributions
glass-0.230
bles-0.228
driver-0.225
adders-0.221
eper-0.220
Token Sarah
Token ID10490
Feature activation-2.59e-01

Pos logit contributions
oph+0.017
ksh+0.016
ya+0.016
 since+0.016
 aback+0.016
Neg logit contributions
glass-0.027
bles-0.026
driver-0.026
hips-0.026
 drill-0.026
Token has
Token ID468
Feature activation+1.02e-01

Pos logit contributions
 since+0.505
oph+0.460
heart+0.448
 pleasure+0.443
eter+0.440
Neg logit contributions
bles-0.375
glass-0.375
eper-0.374
driver-0.369
adders-0.355
Token.
Token ID13
Feature activation-3.69e-02

Pos logit contributions
glass+0.094
bles+0.093
driver+0.093
eper+0.089
adders+0.089
Neg logit contributions
oph-0.104
 since-0.102
heart-0.094
eter-0.093
 pleasure-0.093
Token He
Token ID679
Feature activation+1.39e-01

Pos logit contributions
 since+0.090
oph+0.087
ya+0.085
heart+0.084
ited+0.084
Neg logit contributions
driver-0.037
glass-0.035
 drill-0.033
box-0.032
eper-0.032
Token had
Token ID550
Feature activation+1.45e-02

Pos logit contributions
glass+0.229
eper+0.226
driver+0.223
bles+0.218
 sword+0.212
Neg logit contributions
 since-0.248
oph-0.232
 pleasure-0.226
heart-0.220
eter-0.218
Token been
Token ID587
Feature activation-6.66e-03

Pos logit contributions
driver+0.023
glass+0.023
adders+0.022
 drill+0.022
bles+0.022
Neg logit contributions
 since-0.027
heart-0.025
oph-0.025
ya-0.024
eter-0.023
Token worried
Token ID7960
Feature activation-4.97e-03

Pos logit contributions
 since+0.014
oph+0.014
heart+0.013
eter+0.012
 pleasure+0.012
Neg logit contributions
bles-0.009
eper-0.009
glass-0.009
driver-0.009
ithering-0.009
Token since
Token ID1201
Feature activation-5.29e-01

Pos logit contributions
 since+0.009
oph+0.008
heart+0.008
 pleasure+0.007
eter+0.007
Neg logit contributions
bles-0.009
glass-0.009
eper-0.008
ithering-0.008
driver-0.008
Token the
Token ID262
Feature activation-1.24e-01

Pos logit contributions
 since+1.237
oph+1.122
heart+1.091
eter+1.085
 pleasure+1.082
Neg logit contributions
glass-0.602
bles-0.594
driver-0.576
eper-0.568
adders-0.562
Token start
Token ID923
Feature activation+1.03e-01

Pos logit contributions
 since+0.286
oph+0.265
eter+0.255
heart+0.253
 Mill+0.250
Neg logit contributions
glass-0.153
bles-0.145
eper-0.142
adders-0.139
driver-0.138
Token of
Token ID286
Feature activation+5.92e-02

Pos logit contributions
glass+0.180
bles+0.179
driver+0.175
eper+0.173
adders+0.172
Neg logit contributions
 since-0.179
oph-0.156
heart-0.150
eter-0.148
 pleasure-0.148
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
glass+0.099
bles+0.097
driver+0.096
eper+0.094
 drill+0.094
Neg logit contributions
 since-0.106
oph-0.097
heart-0.093
eter-0.091
 aback-0.089
Token line
Token ID1627
Feature activation+1.16e-01

Pos logit contributions
 since+0.277
oph+0.256
eter+0.245
heart+0.244
 Mill+0.240
Neg logit contributions
glass-0.164
bles-0.157
eper-0.151
adders-0.150
driver-0.150
Token then
Token ID788
Feature activation-1.52e-01

Pos logit contributions
 since+0.003
oph+0.002
heart+0.002
 pleasure+0.002
eter+0.002
Neg logit contributions
bles-0.002
glass-0.002
ithering-0.002
driver-0.002
eper-0.002
Token he
Token ID339
Feature activation+2.29e-01

Pos logit contributions
 since+0.295
oph+0.260
heart+0.251
eter+0.249
 pleasure+0.248
Neg logit contributions
glass-0.237
bles-0.236
driver-0.230
eper-0.227
adders-0.227
Token left
Token ID1364
Feature activation-7.32e-02

Pos logit contributions
glass+0.361
bles+0.358
eper+0.354
driver+0.350
hes+0.338
Neg logit contributions
 since-0.426
oph-0.399
heart-0.391
 pleasure-0.378
eter-0.375
Token.
Token ID13
Feature activation-3.68e-02

Pos logit contributions
 since+0.139
oph+0.131
heart+0.123
eter+0.122
ya+0.120
Neg logit contributions
glass-0.116
bles-0.112
eper-0.110
driver-0.110
adders-0.109
Token Ever
Token ID10776
Feature activation-1.92e-01

Pos logit contributions
 since+0.084
ited+0.081
heart+0.080
oph+0.079
ya+0.079
Neg logit contributions
driver-0.041
glass-0.040
His-0.039
adders-0.039
hes-0.038
Token since
Token ID1201
Feature activation-5.28e-01

Pos logit contributions
 pleasure+0.140
 sight+0.126
eter+0.123
ksh+0.120
 Mill+0.104
Neg logit contributions
ino-0.451
bles-0.451
glass-0.446
eper-0.436
His-0.426
Token that
Token ID326
Feature activation-2.72e-02

Pos logit contributions
 since+0.984
eter+0.941
oph+0.922
heart+0.887
 aback+0.874
Neg logit contributions
glass-0.814
eper-0.792
bles-0.748
driver-0.740
otion-0.739
Token day
Token ID1110
Feature activation-1.32e-01

Pos logit contributions
 since+0.044
oph+0.043
eter+0.042
 aback+0.039
heart+0.039
Neg logit contributions
glass-0.047
 drill-0.045
otion-0.044
eper-0.043
 sword-0.043
Token,
Token ID11
Feature activation-1.31e-02

Pos logit contributions
 since+0.231
oph+0.193
heart+0.185
 Mill+0.183
 pleasure+0.183
Neg logit contributions
bles-0.239
glass-0.234
driver-0.231
adders-0.228
ithering-0.228
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
 since+0.024
oph+0.021
heart+0.020
eter+0.020
 pleasure+0.020
Neg logit contributions
glass-0.022
bles-0.022
driver-0.021
eper-0.021
adders-0.021
Token stage
Token ID3800
Feature activation-9.30e-03

Pos logit contributions
 since+0.234
oph+0.205
heart+0.199
eter+0.198
 pleasure+0.195
Neg logit contributions
glass-0.206
bles-0.205
driver-0.199
eper-0.198
ithering-0.196
Token he
Token ID339
Feature activation+2.28e-01

Pos logit contributions
 since+0.002
oph+0.002
heart+0.002
eter+0.002
 pleasure+0.002
Neg logit contributions
bles-0.002
glass-0.002
driver-0.002
ithering-0.002
adders-0.002
Token stayed
Token ID9658
Feature activation+2.70e-02

Pos logit contributions
glass+0.362
bles+0.353
eper+0.351
driver+0.345
adders+0.335
Neg logit contributions
 since-0.426
oph-0.388
heart-0.379
eter-0.365
 pleasure-0.365
Token with
Token ID351
Feature activation+7.00e-03

Pos logit contributions
glass+0.042
bles+0.042
driver+0.042
adders+0.041
ithering+0.040
Neg logit contributions
 since-0.052
oph-0.045
heart-0.044
 pleasure-0.044
eter-0.044
Token them
Token ID606
Feature activation+1.01e-01

Pos logit contributions
bles+0.011
glass+0.011
ithering+0.011
driver+0.011
adders+0.011
Neg logit contributions
 since-0.014
oph-0.012
 pleasure-0.011
heart-0.011
 aback-0.011
Token ever
Token ID1683
Feature activation-6.36e-02

Pos logit contributions
bles+0.168
glass+0.168
driver+0.164
eper+0.161
adders+0.161
Neg logit contributions
 since-0.179
oph-0.161
heart-0.155
eter-0.151
 pleasure-0.150
Token since
Token ID1201
Feature activation-5.28e-01

Pos logit contributions
 Mill+0.095
oph+0.094
 pleasure+0.093
 Sus+0.092
ya+0.088
Neg logit contributions
glass-0.105
bles-0.100
es-0.100
 sticking-0.099
 sword-0.098
Token!
Token ID0
Feature activation-2.48e-01

Pos logit contributions
 since+0.963
oph+0.889
eter+0.857
 pleasure+0.840
 aback+0.835
Neg logit contributions
glass-0.847
eper-0.825
bles-0.820
driver-0.813
adders-0.793
Token<|endoftext|>
Token ID50256
Feature activation+1.08e-01

Pos logit contributions
 since+0.415
oph+0.359
heart+0.346
eter+0.340
 pleasure+0.339
Neg logit contributions
glass-0.452
bles-0.449
driver-0.441
eper-0.435
ithering-0.434
TokenOne
Token ID3198
Feature activation+1.81e-02

Pos logit contributions
glass+0.179
bles+0.178
ithering+0.174
driver+0.173
eper+0.172
Neg logit contributions
 since-0.196
oph-0.172
heart-0.167
eter-0.166
 pleasure-0.164
Token day
Token ID1110
Feature activation-1.31e-01

Pos logit contributions
glass+0.030
adders+0.029
ithering+0.029
bles+0.029
kin+0.029
Neg logit contributions
 since-0.031
oph-0.028
 aback-0.027
eter-0.027
heart-0.026
Token,
Token ID11
Feature activation-1.27e-02

Pos logit contributions
 since+0.213
oph+0.176
 Mill+0.175
 Sus+0.173
heart+0.171
Neg logit contributions
glass-0.250
bles-0.246
eper-0.243
driver-0.242
adders-0.241
Token way
Token ID835
Feature activation-1.91e-01

Pos logit contributions
glass+0.134
bles+0.132
eper+0.131
driver+0.130
 sword+0.127
Neg logit contributions
 since-0.127
oph-0.121
eter-0.111
 aback-0.108
heart-0.105
Token.
Token ID13
Feature activation-3.65e-02

Pos logit contributions
 since+0.314
oph+0.291
eter+0.271
 pleasure+0.266
heart+0.266
Neg logit contributions
bles-0.341
glass-0.334
driver-0.332
adders-0.329
eper-0.325
Tokenâ
Token ID22940
Feature activation-3.21e-03

Pos logit contributions
ited+0.070
ya+0.069
 since+0.068
 sight+0.067
oph+0.067
Neg logit contributions
driver-0.048
adders-0.046
hes-0.045
His-0.045
glass-0.045
Token
Token ID26391
Feature activation-1.53e-01

Pos logit contributions
 since+0.005
eter+0.005
 pleasure+0.005
 Mill+0.005
 sight+0.005
Neg logit contributions
glass-0.006
driver-0.005
kin-0.005
bles-0.005
otion-0.005
Token Ever
Token ID10776
Feature activation-1.92e-01

Pos logit contributions
 since+0.255
heart+0.225
oph+0.224
 aback+0.214
eter+0.214
Neg logit contributions
glass-0.277
bles-0.271
driver-0.266
eper-0.262
adders-0.261
Token since
Token ID1201
Feature activation-5.28e-01

Pos logit contributions
ksh+0.199
eter+0.190
 sight+0.182
 pleasure+0.175
 Mill+0.166
Neg logit contributions
ila-0.397
bles-0.392
eper-0.383
adders-0.382
ibrarian-0.379
Token that
Token ID326
Feature activation-2.45e-02

Pos logit contributions
eter+0.956
 since+0.925
 aback+0.916
ksh+0.902
oph+0.887
Neg logit contributions
eper-0.754
glass-0.752
bles-0.731
otion-0.724
 chores-0.694
Token day
Token ID1110
Feature activation-1.29e-01

Pos logit contributions
 since+0.043
eter+0.042
oph+0.042
 aback+0.040
 Mill+0.039
Neg logit contributions
glass-0.036
 drill-0.034
 chores-0.034
kin-0.034
eper-0.034
Token,
Token ID11
Feature activation-1.22e-02

Pos logit contributions
 since+0.250
eter+0.229
oph+0.223
 pleasure+0.222
heart+0.221
Neg logit contributions
bles-0.187
glass-0.187
driver-0.182
otion-0.180
adders-0.179
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
 since+0.018
 aback+0.017
oph+0.017
eter+0.017
heart+0.016
Neg logit contributions
bles-0.022
glass-0.020
adders-0.020
eper-0.020
driver-0.020
Token prince
Token ID19716
Feature activation-8.02e-02

Pos logit contributions
 since+0.230
eter+0.206
oph+0.204
 aback+0.202
 Mill+0.199
Neg logit contributions
glass-0.196
bles-0.192
eper-0.189
 sword-0.178
bridge-0.177
Token bother
Token ID11393
Feature activation-1.20e-01

Pos logit contributions
bles+0.100
glass+0.100
eper+0.097
driver+0.097
ithering+0.095
Neg logit contributions
 since-0.109
oph-0.099
heart-0.096
eter-0.095
ya-0.095
Token him
Token ID683
Feature activation+2.19e-01

Pos logit contributions
 since+0.270
oph+0.249
heart+0.241
eter+0.237
 pleasure+0.236
Neg logit contributions
bles-0.148
glass-0.148
eper-0.141
ithering-0.138
driver-0.138
Token again
Token ID757
Feature activation-2.05e-01

Pos logit contributions
bles+0.432
glass+0.430
driver+0.414
eper+0.413
ithering+0.412
Neg logit contributions
 since-0.312
oph-0.286
 pleasure-0.266
heart-0.266
 aback-0.264
Token,
Token ID11
Feature activation-9.89e-03

Pos logit contributions
oph+0.390
 since+0.376
 aback+0.362
heart+0.361
ya+0.356
Neg logit contributions
glass-0.294
bles-0.283
eper-0.273
ithering-0.266
ble-0.261
Token and
Token ID290
Feature activation-8.96e-04

Pos logit contributions
 since+0.016
oph+0.016
heart+0.014
ya+0.014
eter+0.014
Neg logit contributions
glass-0.017
bles-0.017
driver-0.017
eper-0.016
 drill-0.016
Token since
Token ID1201
Feature activation-5.27e-01

Pos logit contributions
 since+0.002
oph+0.002
heart+0.002
eter+0.002
 pleasure+0.002
Neg logit contributions
glass-0.001
bles-0.001
driver-0.001
eper-0.001
adders-0.001
Token that
Token ID326
Feature activation-2.41e-02

Pos logit contributions
 since+1.050
oph+1.003
eter+0.973
heart+0.964
 aback+0.955
Neg logit contributions
glass-0.751
bles-0.720
eper-0.718
driver-0.678
ithering-0.674
Token day
Token ID1110
Feature activation-1.29e-01

Pos logit contributions
 since+0.043
oph+0.041
eter+0.039
heart+0.038
 aback+0.038
Neg logit contributions
glass-0.039
bles-0.037
eper-0.037
 drill-0.037
driver-0.036
Token,
Token ID11
Feature activation-1.11e-02

Pos logit contributions
 since+0.253
oph+0.220
heart+0.212
 pleasure+0.211
eter+0.210
Neg logit contributions
bles-0.200
glass-0.199
driver-0.195
eper-0.192
adders-0.192
Token Runner
Token ID21529
Feature activation-7.99e-02

Pos logit contributions
 since+0.022
oph+0.019
heart+0.018
 pleasure+0.018
eter+0.018
Neg logit contributions
glass-0.017
bles-0.017
driver-0.017
eper-0.016
ithering-0.016
Token had
Token ID550
Feature activation+1.42e-02

Pos logit contributions
 since+0.154
oph+0.138
eter+0.135
 pleasure+0.135
heart+0.133
Neg logit contributions
bles-0.123
glass-0.123
eper-0.120
driver-0.118
adders-0.114
Token.
Token ID13
Feature activation-3.61e-02

Pos logit contributions
 since+0.081
oph+0.079
heart+0.076
ya+0.071
 Mill+0.071
Neg logit contributions
glass-0.062
bles-0.061
driver-0.060
eper-0.058
adders-0.058
Token The
Token ID383
Feature activation-2.14e-01

Pos logit contributions
heart+0.083
ited+0.080
 since+0.080
ya+0.078
oph+0.076
Neg logit contributions
driver-0.043
hes-0.043
balls-0.042
His-0.041
glass-0.041
Token crowd
Token ID4315
Feature activation-1.10e-01

Pos logit contributions
 since+0.423
oph+0.370
 pleasure+0.362
heart+0.357
eter+0.356
Neg logit contributions
glass-0.322
bles-0.318
driver-0.313
ithering-0.312
adders-0.311
Token cheered
Token ID34767
Feature activation-1.54e-01

Pos logit contributions
 since+0.192
oph+0.180
heart+0.175
eter+0.175
 pleasure+0.175
Neg logit contributions
glass-0.186
driver-0.179
bles-0.179
eper-0.178
adders-0.171
Token loudly
Token ID23112
Feature activation-5.97e-02

Pos logit contributions
 since+0.294
oph+0.285
eter+0.266
 pleasure+0.266
 aback+0.261
Neg logit contributions
bles-0.230
glass-0.219
driver-0.217
eper-0.212
hips-0.209
Token since
Token ID1201
Feature activation-5.27e-01

Pos logit contributions
 since+0.118
oph+0.115
heart+0.109
 pleasure+0.108
eter+0.107
Neg logit contributions
driver-0.086
glass-0.084
bles-0.083
eper-0.079
balls-0.078
Token they
Token ID484
Feature activation+1.20e-01

Pos logit contributions
 since+0.936
oph+0.881
eter+0.844
heart+0.837
 aback+0.822
Neg logit contributions
glass-0.858
eper-0.848
bles-0.834
driver-0.822
ithering-0.800
Token now
Token ID783
Feature activation-1.14e-01

Pos logit contributions
bles+0.164
glass+0.163
driver+0.159
eper+0.157
adders+0.156
Neg logit contributions
 since-0.252
oph-0.233
heart-0.226
eter-0.222
ya-0.220
Token knew
Token ID2993
Feature activation-8.79e-02

Pos logit contributions
 since+0.217
oph+0.206
heart+0.201
ya+0.195
eter+0.192
Neg logit contributions
glass-0.171
driver-0.170
bles-0.168
eper-0.163
adders-0.162
Token who
Token ID508
Feature activation+7.48e-02

Pos logit contributions
 since+0.169
oph+0.151
heart+0.146
eter+0.143
 pleasure+0.143
Neg logit contributions
bles-0.136
glass-0.136
driver-0.133
adders-0.131
eper-0.131
Token the
Token ID262
Feature activation-1.24e-01

Pos logit contributions
glass+0.118
driver+0.116
bles+0.116
eper+0.114
adders+0.112
Neg logit contributions
 since-0.140
oph-0.130
heart-0.122
eter-0.121
 pleasure-0.120
Token felt
Token ID2936
Feature activation-5.04e-02

Pos logit contributions
eper+0.161
glass+0.160
bles+0.160
driver+0.156
ble+0.151
Neg logit contributions
 since-0.190
 pleasure-0.179
oph-0.176
eter-0.169
 aback-0.166
Token a
Token ID257
Feature activation+4.60e-03

Pos logit contributions
 since+0.096
oph+0.089
eter+0.083
heart+0.083
ya+0.082
Neg logit contributions
glass-0.077
bles-0.076
eper-0.075
ithering-0.075
adders-0.074
Token bit
Token ID1643
Feature activation-3.99e-01

Pos logit contributions
glass+0.011
bles+0.011
ithering+0.011
driver+0.010
ble+0.010
Neg logit contributions
 since-0.005
oph-0.004
eter-0.004
heart-0.004
 Sus-0.004
Token better
Token ID1365
Feature activation-9.78e-02

Pos logit contributions
oph+0.769
 since+0.763
ya+0.691
!".+0.686
eter+0.683
Neg logit contributions
ithering-0.570
bles-0.564
eper-0.552
driver-0.549
hes-0.548
Token,
Token ID11
Feature activation-1.05e-02

Pos logit contributions
 since+0.165
oph+0.129
heart+0.127
 aback+0.127
!".+0.125
Neg logit contributions
bles-0.187
adders-0.186
glass-0.186
driver-0.182
ithering-0.181
Token since
Token ID1201
Feature activation-5.27e-01

Pos logit contributions
 since+0.017
oph+0.017
eter+0.016
heart+0.016
 pleasure+0.015
Neg logit contributions
glass-0.018
bles-0.017
driver-0.017
eper-0.017
 drill-0.016
Token he
Token ID339
Feature activation+2.29e-01

Pos logit contributions
 since+1.231
oph+1.183
eter+1.171
 aback+1.139
 pleasure+1.136
Neg logit contributions
glass-0.544
eper-0.544
bles-0.519
ble-0.496
driver-0.488
Token knew
Token ID2993
Feature activation-9.05e-02

Pos logit contributions
glass+0.362
bles+0.360
eper+0.354
driver+0.349
ithering+0.345
Neg logit contributions
 since-0.429
oph-0.380
heart-0.370
 pleasure-0.365
eter-0.365
Token what
Token ID644
Feature activation+1.28e-01

Pos logit contributions
 since+0.166
 pleasure+0.136
 Mill+0.135
heart+0.135
 Sus+0.134
Neg logit contributions
glass-0.157
bles-0.154
ithering-0.153
driver-0.151
eper-0.147
Token the
Token ID262
Feature activation-1.24e-01

Pos logit contributions
glass+0.238
bles+0.232
driver+0.230
adders+0.227
eper+0.227
Neg logit contributions
 since-0.208
oph-0.185
heart-0.175
eter-0.174
 pleasure-0.172
Token smell
Token ID8508
Feature activation-7.13e-02

Pos logit contributions
 since+0.234
oph+0.207
eter+0.197
heart+0.196
 pleasure+0.193
Neg logit contributions
bles-0.201
glass-0.201
driver-0.196
eper-0.195
ithering-0.194
Token tried
Token ID3088
Feature activation-1.13e-01

Pos logit contributions
glass+0.162
driver+0.155
adders+0.154
hes+0.152
 drill+0.151
Neg logit contributions
 since-0.203
heart-0.183
oph-0.178
ya-0.175
eter-0.175
Token to
Token ID284
Feature activation-1.03e-01

Pos logit contributions
 since+0.186
oph+0.163
heart+0.156
 pleasure+0.152
eter+0.152
Neg logit contributions
bles-0.206
glass-0.205
driver-0.202
ithering-0.198
eper-0.198
Token remember
Token ID3505
Feature activation-5.26e-03

Pos logit contributions
 since+0.193
oph+0.163
 pleasure+0.162
heart+0.161
!".+0.159
Neg logit contributions
glass-0.169
bles-0.168
driver-0.166
adders-0.166
ithering-0.164
Token it
Token ID340
Feature activation-1.13e-01

Pos logit contributions
 since+0.009
oph+0.009
heart+0.008
eter+0.008
ya+0.008
Neg logit contributions
glass-0.009
bles-0.009
driver-0.008
eper-0.008
adders-0.008
Token ever
Token ID1683
Feature activation-6.02e-02

Pos logit contributions
 since+0.203
oph+0.190
heart+0.179
ya+0.178
 pleasure+0.175
Neg logit contributions
bles-0.184
glass-0.181
driver-0.179
adders-0.176
ithering-0.174
Token since
Token ID1201
Feature activation-5.27e-01

Pos logit contributions
oph+0.123
ya+0.120
 pleasure+0.117
 Mill+0.112
eter+0.112
Neg logit contributions
bles-0.076
driver-0.072
es-0.072
 sword-0.070
 sticking-0.068
Token.
Token ID13
Feature activation-3.53e-02

Pos logit contributions
 since+0.990
oph+0.918
eter+0.875
 pleasure+0.862
heart+0.862
Neg logit contributions
glass-0.818
bles-0.801
driver-0.793
eper-0.788
adders-0.766
Token<|endoftext|>
Token ID50256
Feature activation+1.08e-01

Pos logit contributions
 since+0.065
oph+0.058
heart+0.058
ya+0.058
ited+0.056
Neg logit contributions
glass-0.056
driver-0.056
adders-0.055
 drill-0.054
eper-0.053
TokenOnce
Token ID7454
Feature activation-1.04e-02

Pos logit contributions
glass+0.188
bles+0.186
driver+0.182
ithering+0.181
eper+0.180
Neg logit contributions
 since-0.189
oph-0.165
heart-0.161
eter-0.159
 pleasure-0.157
Token upon
Token ID2402
Feature activation+8.89e-02

Pos logit contributions
 since+0.020
 Sus+0.017
oph+0.017
 Mill+0.016
heart+0.016
Neg logit contributions
glass-0.019
ithering-0.017
driver-0.017
bridge-0.017
eper-0.017
Token a
Token ID257
Feature activation+1.60e-03

Pos logit contributions
eper+0.188
bles+0.188
driver+0.185
ithering+0.182
hips+0.181
Neg logit contributions
 since-0.131
oph-0.104
!".-0.103
 pleasure-0.102
 Daisy-0.100
Token they
Token ID484
Feature activation+1.19e-01

Pos logit contributions
glass+0.102
bles+0.102
eper+0.096
es+0.093
hips+0.092
Neg logit contributions
oph-0.132
ited-0.130
heart-0.129
 since-0.129
ksh-0.129
Token have
Token ID423
Feature activation+1.05e-01

Pos logit contributions
bles+0.152
glass+0.150
eper+0.148
adders+0.141
ithering+0.141
Neg logit contributions
 since-0.258
eter-0.233
heart-0.231
oph-0.230
 aback-0.228
Token been
Token ID587
Feature activation-4.00e-03

Pos logit contributions
glass+0.132
hes+0.127
adders+0.122
es+0.121
bles+0.120
Neg logit contributions
 since-0.213
heart-0.205
.''-0.191
 aback-0.189
eter-0.189
Token friends
Token ID2460
Feature activation+7.77e-02

Pos logit contributions
oph+0.008
 since+0.008
heart+0.008
ited+0.007
ksh+0.007
Neg logit contributions
eper-0.006
hes-0.005
bles-0.005
glass-0.005
es-0.005
Token ever
Token ID1683
Feature activation-6.03e-02

Pos logit contributions
glass+0.127
eper+0.122
bles+0.122
driver+0.118
es+0.117
Neg logit contributions
 since-0.128
oph-0.125
heart-0.119
 aback-0.117
 Mill-0.117
Token since
Token ID1201
Feature activation-5.27e-01

Pos logit contributions
 pleasure+0.067
 Mill+0.064
 Sus+0.061
umm+0.061
 Betsy+0.057
Neg logit contributions
bles-0.118
 sitting-0.113
 on-0.112
eper-0.112
 not-0.112
Token!
Token ID0
Feature activation-2.48e-01

Pos logit contributions
eter+1.029
oph+1.013
 aback+1.005
 since+1.004
ksh+0.985
Neg logit contributions
glass-0.693
eper-0.684
ves-0.633
kin-0.619
bles-0.615
Token<|endoftext|>
Token ID50256
Feature activation+1.07e-01

Pos logit contributions
 since+0.449
heart+0.401
oph+0.393
ya+0.385
eter+0.375
Neg logit contributions
glass-0.406
bles-0.401
driver-0.396
eper-0.392
ithering-0.391
TokenOnce
Token ID7454
Feature activation-1.10e-02

Pos logit contributions
glass+0.179
bles+0.178
ithering+0.173
driver+0.173
eper+0.172
Neg logit contributions
 since-0.194
oph-0.169
heart-0.165
eter-0.164
 pleasure-0.163
Token upon
Token ID2402
Feature activation+8.73e-02

Pos logit contributions
 since+0.021
oph+0.018
 Sus+0.018
 Mill+0.018
heart+0.018
Neg logit contributions
glass-0.019
driver-0.017
ithering-0.017
eper-0.017
bles-0.017
Token a
Token ID257
Feature activation+2.12e-03

Pos logit contributions
bles+0.183
driver+0.183
eper+0.183
glass+0.177
ithering+0.177
Neg logit contributions
 since-0.127
!".-0.102
oph-0.100
 pleasure-0.100
 Daisy-0.098
Token a
Token ID257
Feature activation+4.03e-03

Pos logit contributions
oph+0.010
 since+0.010
heart+0.009
umm+0.009
ksh+0.009
Neg logit contributions
eper-0.007
hes-0.007
bles-0.006
glass-0.006
eps-0.006
Token much
Token ID881
Feature activation-6.87e-03

Pos logit contributions
 sword+0.005
 drill+0.005
eper+0.005
glass+0.005
driver+0.005
Neg logit contributions
oph-0.009
heart-0.008
 since-0.008
ksh-0.008
 Mill-0.008
Token better
Token ID1365
Feature activation-9.73e-02

Pos logit contributions
oph+0.015
 Mill+0.014
 Sus+0.014
ya+0.014
 since+0.013
Neg logit contributions
hes-0.008
 chores-0.008
His-0.008
 not-0.007
 sword-0.007
Token person
Token ID1048
Feature activation+1.73e-02

Pos logit contributions
 since+0.162
oph+0.142
heart+0.135
eter+0.133
 pleasure+0.132
Neg logit contributions
glass-0.178
bles-0.177
driver-0.173
eper-0.172
ithering-0.171
Token ever
Token ID1683
Feature activation-6.09e-02

Pos logit contributions
glass+0.028
bles+0.027
driver+0.027
eper+0.027
adders+0.026
Neg logit contributions
 since-0.032
oph-0.029
heart-0.028
eter-0.027
 pleasure-0.027
Token since
Token ID1201
Feature activation-5.27e-01

Pos logit contributions
 pleasure+0.080
oph+0.080
 Mill+0.077
 Sus+0.074
heart+0.072
Neg logit contributions
glass-0.118
bles-0.111
 sticking-0.111
es-0.110
 on-0.109
Token.
Token ID13
Feature activation-3.67e-02

Pos logit contributions
 since+0.961
oph+0.868
eter+0.833
heart+0.827
 pleasure+0.823
Neg logit contributions
glass-0.861
bles-0.839
driver-0.828
eper-0.827
adders-0.810
Token The
Token ID383
Feature activation-2.14e-01

Pos logit contributions
 since+0.068
heart+0.062
oph+0.062
ya+0.060
ited+0.058
Neg logit contributions
glass-0.057
driver-0.056
bles-0.055
eper-0.055
adders-0.055
Token wise
Token ID10787
Feature activation-8.11e-02

Pos logit contributions
 since+0.433
oph+0.376
 pleasure+0.368
heart+0.367
ya+0.361
Neg logit contributions
bles-0.318
glass-0.316
driver-0.310
adders-0.307
ithering-0.306
Token owl
Token ID39610
Feature activation-5.73e-04

Pos logit contributions
 since+0.146
oph+0.131
eter+0.124
heart+0.123
 pleasure+0.122
Neg logit contributions
bles-0.136
glass-0.136
driver-0.135
eper-0.133
adders-0.130
Token was
Token ID373
Feature activation-1.66e-02

Pos logit contributions
 since+0.001
oph+0.001
heart+0.001
 pleasure+0.001
eter+0.001
Neg logit contributions
glass-0.001
eper-0.001
bles-0.001
driver-0.001
adders-0.001
Token the
Token ID262
Feature activation-1.21e-01

Pos logit contributions
 since+0.461
oph+0.409
eter+0.398
heart+0.392
 aback+0.386
Neg logit contributions
bles-0.422
glass-0.418
eper-0.413
ble-0.402
driver-0.397
Token fa
Token ID24685
Feature activation-1.83e-01

Pos logit contributions
 since+0.219
oph+0.197
eter+0.196
ksh+0.190
heart+0.189
Neg logit contributions
bles-0.204
ble-0.196
glass-0.190
eper-0.190
ithering-0.182
Tokenery
Token ID1924
Feature activation+3.30e-01

Pos logit contributions
 since+0.391
 pleasure+0.339
oph+0.335
 Sus+0.327
 aback+0.322
Neg logit contributions
bles-0.292
ble-0.265
eper-0.261
kin-0.249
glass-0.247
Token.
Token ID13
Feature activation-3.29e-02

Pos logit contributions
glass+0.537
bles+0.537
driver+0.516
eper+0.516
adders+0.507
Neg logit contributions
 since-0.604
oph-0.539
heart-0.516
eter-0.515
 pleasure-0.510
Token Ever
Token ID10776
Feature activation-1.90e-01

Pos logit contributions
 since+0.066
oph+0.060
heart+0.057
ited+0.057
ya+0.056
Neg logit contributions
bles-0.047
eper-0.047
driver-0.046
adders-0.046
balls-0.045
Token since
Token ID1201
Feature activation-5.27e-01

Pos logit contributions
eter+0.158
ksh+0.147
 pleasure+0.146
 sight+0.145
 Mill+0.137
Neg logit contributions
bles-0.441
kin-0.424
izards-0.419
es-0.408
hips-0.408
Token that
Token ID326
Feature activation-2.42e-02

Pos logit contributions
 since+0.929
eter+0.924
oph+0.867
 aback+0.861
ksh+0.855
Neg logit contributions
eper-0.822
glass-0.810
ble-0.772
bles-0.763
 sword-0.754
Token day
Token ID1110
Feature activation-1.28e-01

Pos logit contributions
 since+0.039
oph+0.038
eter+0.038
 aback+0.035
 Sus+0.034
Neg logit contributions
glass-0.040
kin-0.038
 drill-0.038
otion-0.038
eper-0.038
Token,
Token ID11
Feature activation-9.96e-03

Pos logit contributions
 since+0.223
oph+0.189
heart+0.185
 pleasure+0.182
 aback+0.181
Neg logit contributions
glass-0.228
bles-0.226
driver-0.222
eper-0.217
adders-0.217
Token Buzz
Token ID15753
Feature activation-2.12e-01

Pos logit contributions
 since+0.014
oph+0.014
eter+0.013
heart+0.012
ya+0.012
Neg logit contributions
bles-0.019
eper-0.018
ble-0.018
glass-0.018
adders-0.018
Tokeny
Token ID88
Feature activation-8.95e-02

Pos logit contributions
 since+0.336
oph+0.289
heart+0.275
 pleasure+0.274
eter+0.273
Neg logit contributions
bles-0.403
glass-0.400
driver-0.390
eper-0.390
ithering-0.387
Token special
Token ID2041
Feature activation-1.76e-01

Pos logit contributions
 since+0.209
oph+0.184
heart+0.181
 Mill+0.176
ya+0.174
Neg logit contributions
glass-0.216
bles-0.214
driver-0.207
ithering-0.205
 drill-0.204
Token piece
Token ID3704
Feature activation-7.92e-02

Pos logit contributions
 since+0.302
oph+0.264
heart+0.256
eter+0.250
ya+0.249
Neg logit contributions
glass-0.311
bles-0.308
driver-0.303
ithering-0.297
eper-0.295
Token with
Token ID351
Feature activation+7.91e-03

Pos logit contributions
 since+0.146
oph+0.123
heart+0.121
 pleasure+0.119
eter+0.119
Neg logit contributions
glass-0.134
bles-0.134
eper-0.130
ithering-0.129
driver-0.128
Token him
Token ID683
Feature activation+2.17e-01

Pos logit contributions
glass+0.010
bles+0.010
eper+0.010
driver+0.009
adders+0.009
Neg logit contributions
 since-0.017
oph-0.016
heart-0.015
eter-0.015
ya-0.015
Token,
Token ID11
Feature activation-1.07e-02

Pos logit contributions
bles+0.332
glass+0.332
driver+0.325
adders+0.313
eper+0.312
Neg logit contributions
 since-0.404
oph-0.391
heart-0.367
ya-0.360
 Mill-0.354
Token since
Token ID1201
Feature activation-5.26e-01

Pos logit contributions
 since+0.019
oph+0.018
heart+0.017
eter+0.017
ya+0.016
Neg logit contributions
glass-0.018
bles-0.017
driver-0.017
eper-0.017
 drill-0.017
Token he
Token ID339
Feature activation+2.29e-01

Pos logit contributions
 since+0.958
oph+0.901
eter+0.887
 aback+0.876
heart+0.858
Neg logit contributions
glass-0.825
eper-0.803
bles-0.783
driver-0.760
ble-0.754
Token knew
Token ID2993
Feature activation-8.95e-02

Pos logit contributions
glass+0.348
bles+0.348
eper+0.344
driver+0.336
adders+0.329
Neg logit contributions
 since-0.435
oph-0.390
heart-0.385
 Mill-0.377
 pleasure-0.377
Token that
Token ID326
Feature activation-2.54e-02

Pos logit contributions
 since+0.177
 pleasure+0.148
oph+0.147
heart+0.146
 Sus+0.145
Neg logit contributions
glass-0.141
bles-0.141
ithering-0.139
driver-0.136
eper-0.134
Token it
Token ID340
Feature activation-1.14e-01

Pos logit contributions
 since+0.056
oph+0.052
heart+0.050
eter+0.049
 aback+0.049
Neg logit contributions
glass-0.032
bles-0.031
driver-0.030
eper-0.030
adders-0.030
Token always
Token ID1464
Feature activation+5.41e-02

Pos logit contributions
 since+0.217
oph+0.198
 pleasure+0.189
heart+0.188
eter+0.188
Neg logit contributions
bles-0.175
glass-0.175
driver-0.172
eper-0.169
adders-0.167
Token their
Token ID511
Feature activation+1.81e-01

Pos logit contributions
 since+0.027
 aback+0.025
oph+0.025
heart+0.024
eter+0.024
Neg logit contributions
hes-0.020
bles-0.019
glass-0.019
eper-0.019
ithering-0.018
Token first
Token ID717
Feature activation+1.37e-02

Pos logit contributions
glass+0.253
bles+0.250
 chores+0.242
eper+0.238
hips+0.237
Neg logit contributions
 since-0.362
oph-0.333
 aback-0.331
heart-0.325
eter-0.307
Token big
Token ID1263
Feature activation+2.64e-02

Pos logit contributions
glass+0.023
bles+0.022
eper+0.022
ithering+0.021
driver+0.021
Neg logit contributions
 since-0.024
oph-0.022
 aback-0.022
eter-0.021
heart-0.021
Token trip
Token ID5296
Feature activation+5.47e-02

Pos logit contributions
 sword+0.036
eper+0.034
bles+0.033
 drill+0.033
glass+0.033
Neg logit contributions
 since-0.051
oph-0.050
 aback-0.048
eter-0.047
heart-0.046
Token together
Token ID1978
Feature activation-7.37e-02

Pos logit contributions
glass+0.086
bles+0.084
driver+0.083
hips+0.080
adders+0.079
Neg logit contributions
 since-0.099
oph-0.094
 pleasure-0.090
heart-0.089
eter-0.089
Token since
Token ID1201
Feature activation-5.26e-01

Pos logit contributions
 since+0.144
oph+0.141
 aback+0.135
heart+0.133
eter+0.131
Neg logit contributions
glass-0.101
bles-0.098
driver-0.093
hips-0.092
eper-0.092
Token they
Token ID484
Feature activation+1.19e-01

Pos logit contributions
 since+1.023
oph+0.958
 aback+0.937
eter+0.930
heart+0.898
Neg logit contributions
glass-0.757
bles-0.727
eper-0.725
driver-0.708
adders-0.697
Token met
Token ID1138
Feature activation-7.23e-02

Pos logit contributions
glass+0.168
bles+0.166
eper+0.162
adders+0.158
driver+0.156
Neg logit contributions
 since-0.238
oph-0.218
eter-0.216
heart-0.216
 aback-0.210
Token.
Token ID13
Feature activation-3.62e-02

Pos logit contributions
 since+0.142
oph+0.124
heart+0.122
 aback+0.121
eter+0.120
Neg logit contributions
glass-0.108
bles-0.107
adders-0.104
eper-0.103
ithering-0.101
Token They
Token ID1119
Feature activation-1.12e-03

Pos logit contributions
 since+0.067
heart+0.066
ited+0.064
eter+0.063
ya+0.062
Neg logit contributions
glass-0.050
otion-0.047
adders-0.047
driver-0.046
His-0.046
Token paused
Token ID24487
Feature activation-2.86e-02

Pos logit contributions
 since+0.002
oph+0.002
eter+0.002
heart+0.002
 aback+0.002
Neg logit contributions
bles-0.001
glass-0.001
eper-0.001
driver-0.001
adders-0.001
Token par
Token ID1582
Feature activation-6.71e-02

Pos logit contributions
 since+0.367
oph+0.319
heart+0.310
eter+0.306
 pleasure+0.303
Neg logit contributions
glass-0.377
bles-0.373
driver-0.362
eper-0.361
ithering-0.356
Tokenrot
Token ID10599
Feature activation+7.63e-02

Pos logit contributions
 since+0.104
oph+0.098
eter+0.089
!".+0.089
heart+0.086
Neg logit contributions
 chores-0.121
adders-0.120
 elbows-0.117
otion-0.114
driver-0.113
Token hadn
Token ID8020
Feature activation-9.63e-02

Pos logit contributions
glass+0.132
bles+0.132
eper+0.130
driver+0.129
 sword+0.124
Neg logit contributions
 since-0.129
 pleasure-0.119
eter-0.117
oph-0.116
 aback-0.111
Token't
Token ID470
Feature activation+1.83e-01

Pos logit contributions
 since+0.218
!".+0.191
oph+0.186
 Mill+0.186
 aback+0.185
Neg logit contributions
bles-0.122
glass-0.121
eper-0.117
adders-0.116
ithering-0.112
Token moved
Token ID3888
Feature activation+4.65e-02

Pos logit contributions
glass+0.313
driver+0.303
bles+0.301
adders+0.296
 drill+0.290
Neg logit contributions
 since-0.325
oph-0.305
heart-0.289
eter-0.285
ya-0.282
Token since
Token ID1201
Feature activation-5.26e-01

Pos logit contributions
bles+0.076
glass+0.074
driver+0.074
ithering+0.073
eper+0.073
Neg logit contributions
 since-0.083
oph-0.078
heart-0.073
 pleasure-0.072
eter-0.072
Token the
Token ID262
Feature activation-1.20e-01

Pos logit contributions
 since+1.022
eter+0.964
oph+0.946
 pleasure+0.936
 aback+0.929
Neg logit contributions
glass-0.714
eper-0.712
bles-0.709
otion-0.680
driver-0.669
Token loud
Token ID7812
Feature activation+4.73e-02

Pos logit contributions
 since+0.232
oph+0.217
heart+0.210
 Mill+0.203
eter+0.202
Neg logit contributions
glass-0.191
bles-0.180
eper-0.176
 drill-0.174
driver-0.173
Token sound
Token ID2128
Feature activation-8.43e-02

Pos logit contributions
glass+0.073
 drill+0.066
driver+0.066
bles+0.065
eper+0.065
Neg logit contributions
 since-0.094
oph-0.089
 pleasure-0.084
eter-0.084
 aback-0.083
Token.
Token ID13
Feature activation-3.82e-02

Pos logit contributions
 since+0.166
oph+0.151
 pleasure+0.146
eter+0.145
heart+0.144
Neg logit contributions
glass-0.125
bles-0.123
driver-0.122
eper-0.119
adders-0.118
Token
Token ID198
Feature activation-4.37e-02

Pos logit contributions
 since+0.070
heart+0.060
ited+0.059
oph+0.059
fy+0.059
Neg logit contributions
ble-0.059
bles-0.059
otion-0.058
adders-0.058
eper-0.058
Token.
Token ID13
Feature activation-3.53e-02

Pos logit contributions
 since+0.138
oph+0.134
 aback+0.126
 pleasure+0.126
ya+0.125
Neg logit contributions
bles-0.104
glass-0.103
eper-0.101
driver-0.099
ble-0.099
Token
Token ID220
Feature activation-1.07e-01

Pos logit contributions
ited+0.082
heart+0.081
 since+0.077
eter+0.074
 matter+0.073
Neg logit contributions
glass-0.038
adders-0.035
hes-0.035
His-0.033
otion-0.032
Token
Token ID198
Feature activation-4.02e-02

Pos logit contributions
 since+0.206
heart+0.183
oph+0.182
ya+0.178
ited+0.171
Neg logit contributions
bles-0.172
adders-0.169
glass-0.167
ithering-0.166
hes-0.165
Token
Token ID198
Feature activation-4.06e-02

Pos logit contributions
 since+0.070
oph+0.061
heart+0.060
eter+0.060
 pleasure+0.059
Neg logit contributions
glass-0.071
bles-0.070
driver-0.068
ithering-0.067
adders-0.067
TokenEver
Token ID23921
Feature activation-5.99e-03

Pos logit contributions
 since+0.071
oph+0.062
 pleasure+0.061
eter+0.061
heart+0.061
Neg logit contributions
glass-0.071
bles-0.070
ithering-0.068
driver-0.068
eper-0.067
Token since
Token ID1201
Feature activation-5.26e-01

Pos logit contributions
eter+0.004
 pleasure+0.004
heart+0.003
ksh+0.003
 ju+0.003
Neg logit contributions
glass-0.015
hips-0.015
ino-0.015
bles-0.015
otion-0.014
Token,
Token ID11
Feature activation-1.21e-02

Pos logit contributions
eter+1.045
 since+1.039
oph+0.997
heart+0.975
ksh+0.963
Neg logit contributions
glass-0.730
eper-0.705
otion-0.662
ble-0.655
hips-0.652
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
oph+0.022
 since+0.021
heart+0.021
ksh+0.021
 aback+0.020
Neg logit contributions
glass-0.018
eper-0.017
adders-0.017
bles-0.017
hes-0.016
Token cats
Token ID11875
Feature activation-1.33e-02

Pos logit contributions
 since+0.292
oph+0.288
heart+0.270
ya+0.267
 aback+0.267
Neg logit contributions
hes-0.144
balls-0.143
bles-0.143
eper-0.140
 chores-0.140
Token continued
Token ID3767
Feature activation-7.99e-02

Pos logit contributions
 since+0.028
oph+0.025
heart+0.024
eter+0.024
 pleasure+0.024
Neg logit contributions
glass-0.019
bles-0.019
driver-0.018
eper-0.018
ithering-0.018
Token to
Token ID284
Feature activation-1.05e-01

Pos logit contributions
 since+0.124
oph+0.106
heart+0.101
eter+0.100
 pleasure+0.100
Neg logit contributions
glass-0.154
bles-0.154
driver-0.151
eper-0.149
ithering-0.149
Token to
Token ID284
Feature activation-9.85e-02

Pos logit contributions
 since+0.286
oph+0.243
heart+0.233
eter+0.229
 pleasure+0.229
Neg logit contributions
glass-0.369
bles-0.368
driver-0.360
eper-0.357
ithering-0.356
Token call
Token ID869
Feature activation+8.34e-02

Pos logit contributions
 since+0.174
 pleasure+0.145
oph+0.145
 Mill+0.142
!".+0.142
Neg logit contributions
bles-0.173
driver-0.170
glass-0.170
eper-0.167
ithering-0.165
Token home
Token ID1363
Feature activation-1.85e-01

Pos logit contributions
glass+0.130
driver+0.125
adders+0.125
bles+0.125
eper+0.124
Neg logit contributions
 since-0.159
oph-0.146
eter-0.137
heart-0.137
ited-0.135
Token.
Token ID13
Feature activation-3.06e-02

Pos logit contributions
 since+0.342
oph+0.322
heart+0.303
 pleasure+0.303
eter+0.299
Neg logit contributions
bles-0.288
glass-0.283
driver-0.278
eper-0.272
adders-0.268
Token Ever
Token ID10776
Feature activation-1.89e-01

Pos logit contributions
 since+0.061
ited+0.060
heart+0.060
ya+0.056
oph+0.056
Neg logit contributions
driver-0.041
hes-0.041
adders-0.040
glass-0.039
bles-0.039
Token since
Token ID1201
Feature activation-5.25e-01

Pos logit contributions
 pleasure+0.120
eter+0.119
ksh+0.116
 sight+0.109
umm+0.092
Neg logit contributions
ino-0.456
bles-0.447
glass-0.447
es-0.435
hips-0.432
Token then
Token ID788
Feature activation-1.49e-01

Pos logit contributions
 since+0.919
eter+0.874
oph+0.845
 aback+0.821
heart+0.819
Neg logit contributions
glass-0.865
eper-0.840
bles-0.800
driver-0.787
otion-0.786
Token,
Token ID11
Feature activation-6.88e-03

Pos logit contributions
 since+0.240
oph+0.190
heart+0.188
 aback+0.186
 Mill+0.186
Neg logit contributions
bles-0.299
glass-0.292
driver-0.286
adders-0.282
bridge-0.280
Token it
Token ID340
Feature activation-1.10e-01

Pos logit contributions
 since+0.011
oph+0.011
 aback+0.010
heart+0.010
ya+0.010
Neg logit contributions
glass-0.012
bles-0.012
eper-0.011
adders-0.011
 drill-0.011
Token never
Token ID1239
Feature activation+6.17e-02

Pos logit contributions
 since+0.207
oph+0.178
heart+0.174
 aback+0.172
 pleasure+0.172
Neg logit contributions
glass-0.180
bles-0.179
driver-0.175
ithering-0.174
adders-0.172
Token rolled
Token ID11686
Feature activation+3.71e-02

Pos logit contributions
glass+0.081
driver+0.080
bles+0.079
 sword+0.079
eper+0.078
Neg logit contributions
 since-0.119
oph-0.119
ya-0.114
heart-0.111
eter-0.109
Token.
Token ID13
Feature activation-3.36e-02

Pos logit contributions
glass+0.087
driver+0.086
bles+0.085
eper+0.083
adders+0.082
Neg logit contributions
 since-0.125
oph-0.117
heart-0.112
eter-0.109
 aback-0.107
Token Molly
Token ID30236
Feature activation-3.14e-01

Pos logit contributions
 since+0.054
heart+0.052
ya+0.050
eter+0.048
bye+0.047
Neg logit contributions
hes-0.053
His-0.053
ither-0.052
balls-0.051
ithering-0.051
Token was
Token ID373
Feature activation-1.25e-02

Pos logit contributions
 since+0.660
 pleasure+0.606
eter+0.601
oph+0.593
heart+0.585
Neg logit contributions
glass-0.400
eper-0.393
driver-0.384
bles-0.379
ves-0.373
Token very
Token ID845
Feature activation+5.04e-02

Pos logit contributions
 since+0.025
oph+0.023
heart+0.022
ya+0.021
eter+0.021
Neg logit contributions
eper-0.019
bles-0.019
hes-0.019
glass-0.018
ithering-0.018
Token excited
Token ID6568
Feature activation-9.41e-02

Pos logit contributions
bles+0.081
ithering+0.080
eper+0.080
glass+0.079
adders+0.079
Neg logit contributions
 since-0.095
oph-0.086
eter-0.079
heart-0.079
 pleasure-0.077
Token since
Token ID1201
Feature activation-5.24e-01

Pos logit contributions
 since+0.170
eter+0.169
 pleasure+0.169
oph+0.166
 aback+0.162
Neg logit contributions
driver-0.123
glass-0.123
box-0.121
bles-0.119
otion-0.116
Token she
Token ID673
Feature activation+6.36e-02

Pos logit contributions
 since+1.112
eter+1.038
 aback+1.026
oph+1.022
 pleasure+1.009
Neg logit contributions
glass-0.661
eper-0.638
bles-0.628
driver-0.614
adders-0.591
Token had
Token ID550
Feature activation+1.86e-02

Pos logit contributions
glass+0.095
bles+0.093
eper+0.093
driver+0.092
adders+0.090
Neg logit contributions
 since-0.124
oph-0.112
heart-0.111
eter-0.107
 Mill-0.107
Token never
Token ID1239
Feature activation+6.30e-02

Pos logit contributions
glass+0.025
adders+0.023
hes+0.023
 chores+0.022
eper+0.022
Neg logit contributions
 since-0.039
heart-0.038
oph-0.038
umm-0.036
eter-0.036
Token been
Token ID587
Feature activation-2.74e-03

Pos logit contributions
glass+0.105
bles+0.100
driver+0.099
adders+0.098
eper+0.097
Neg logit contributions
 since-0.111
oph-0.102
 pleasure-0.099
heart-0.098
eter-0.097
Token to
Token ID284
Feature activation-1.03e-01

Pos logit contributions
 since+0.005
oph+0.005
heart+0.005
 pleasure+0.005
 Mill+0.005
Neg logit contributions
bles-0.004
eper-0.004
hes-0.004
adders-0.004
glass-0.004
Token they
Token ID484
Feature activation+1.23e-01

Pos logit contributions
glass+0.001
eper+0.001
bles+0.001
hes+0.001
driver+0.001
Neg logit contributions
oph-0.002
 since-0.002
heart-0.002
 pleasure-0.002
eter-0.002
Token have
Token ID423
Feature activation+1.07e-01

Pos logit contributions
glass+0.181
bles+0.180
eper+0.176
driver+0.173
adders+0.171
Neg logit contributions
 since-0.244
oph-0.219
heart-0.214
eter-0.212
 pleasure-0.210
Token been
Token ID587
Feature activation-3.01e-03

Pos logit contributions
glass+0.147
adders+0.141
hes+0.139
eper+0.137
bles+0.133
Neg logit contributions
 since-0.217
heart-0.209
oph-0.200
ya-0.195
.''-0.191
Token friends
Token ID2460
Feature activation+7.85e-02

Pos logit contributions
oph+0.006
 since+0.006
heart+0.006
umm+0.006
eter+0.005
Neg logit contributions
eper-0.005
glass-0.004
hes-0.004
ithering-0.004
bles-0.004
Token ever
Token ID1683
Feature activation-5.82e-02

Pos logit contributions
glass+0.138
eper+0.132
bles+0.132
driver+0.131
adders+0.129
Neg logit contributions
 since-0.124
oph-0.120
heart-0.115
 Mill-0.110
eter-0.110
Token since
Token ID1201
Feature activation-5.24e-01

Pos logit contributions
 pleasure+0.079
oph+0.079
 Mill+0.077
 Sus+0.075
eter+0.074
Neg logit contributions
glass-0.101
eper-0.099
 sitting-0.097
 sticking-0.096
eps-0.095
Token.
Token ID13
Feature activation-3.53e-02

Pos logit contributions
 since+0.991
oph+0.967
eter+0.939
 pleasure+0.900
 aback+0.893
Neg logit contributions
glass-0.764
eper-0.749
driver-0.718
bles-0.715
ithering-0.705
Token
Token ID220
Feature activation-1.08e-01

Pos logit contributions
heart+0.072
 since+0.071
ited+0.069
ya+0.067
oph+0.067
Neg logit contributions
glass-0.047
adders-0.047
hes-0.047
ithering-0.046
driver-0.045
Token
Token ID198
Feature activation-4.08e-02

Pos logit contributions
 since+0.185
oph+0.160
heart+0.155
eter+0.152
 pleasure+0.151
Neg logit contributions
bles-0.193
glass-0.192
driver-0.188
adders-0.186
ithering-0.186
Token
Token ID198
Feature activation-4.14e-02

Pos logit contributions
 since+0.069
oph+0.059
heart+0.057
 pleasure+0.057
eter+0.056
Neg logit contributions
glass-0.073
bles-0.073
driver-0.072
eper-0.071
ithering-0.071
TokenThe
Token ID464
Feature activation-5.10e-02

Pos logit contributions
 since+0.066
oph+0.055
heart+0.052
eter+0.052
 pleasure+0.052
Neg logit contributions
bles-0.079
glass-0.079
driver-0.078
adders-0.077
eper-0.077
Token's
Token ID338
Feature activation-4.42e-02

Pos logit contributions
bles+0.018
es+0.018
driver+0.018
eper+0.018
 drill+0.018
Neg logit contributions
 since-0.029
oph-0.029
eter-0.026
 pleasure-0.026
ited-0.025
Token been
Token ID587
Feature activation-2.99e-03

Pos logit contributions
oph+0.093
 since+0.089
ited+0.087
eter+0.085
 aback+0.083
Neg logit contributions
 not-0.056
hes-0.054
ble-0.053
 chores-0.052
bles-0.052
Token a
Token ID257
Feature activation+5.58e-03

Pos logit contributions
oph+0.006
 since+0.006
ited+0.006
eter+0.006
heart+0.006
Neg logit contributions
bles-0.004
adders-0.004
hes-0.004
eper-0.004
 drill-0.003
Token long
Token ID890
Feature activation-5.96e-02

Pos logit contributions
 drill+0.009
 sword+0.009
glass+0.009
driver+0.008
ithering+0.008
Neg logit contributions
oph-0.010
 since-0.010
heart-0.010
eter-0.009
 aback-0.009
Token time
Token ID640
Feature activation-9.12e-02

Pos logit contributions
 since+0.106
oph+0.101
eter+0.094
heart+0.091
 aback+0.091
Neg logit contributions
glass-0.099
driver-0.098
 drill-0.097
bles-0.093
ithering-0.093
Token since
Token ID1201
Feature activation-5.24e-01

Pos logit contributions
oph+0.176
 since+0.170
eter+0.160
 aback+0.155
heart+0.155
Neg logit contributions
adders-0.133
glass-0.132
bles-0.130
driver-0.128
otion-0.125
Token I
Token ID314
Feature activation-1.70e-01

Pos logit contributions
 aback+0.980
oph+0.980
ksh+0.939
eter+0.931
 since+0.928
Neg logit contributions
ble-0.712
otion-0.711
glass-0.698
bles-0.694
adders-0.680
Token've
Token ID1053
Feature activation-7.41e-03

Pos logit contributions
 since+0.316
oph+0.289
eter+0.279
heart+0.275
 pleasure+0.269
Neg logit contributions
glass-0.270
bles-0.268
eper-0.264
driver-0.261
ithering-0.258
Token been
Token ID587
Feature activation-4.26e-03

Pos logit contributions
oph+0.014
 since+0.014
ksh+0.014
eter+0.014
heart+0.014
Neg logit contributions
glass-0.011
adders-0.010
hes-0.010
eper-0.010
bles-0.009
Token here
Token ID994
Feature activation-5.67e-02

Pos logit contributions
oph+0.010
 since+0.010
eter+0.009
ksh+0.009
heart+0.009
Neg logit contributions
eper-0.005
glass-0.005
bles-0.005
hes-0.005
adders-0.005
Token,
Token ID11
Feature activation-9.42e-03

Pos logit contributions
oph+0.110
 since+0.097
ksh+0.097
heart+0.097
ited+0.097
Neg logit contributions
bles-0.081
glass-0.080
adders-0.077
ble-0.077
 not-0.076
Token,
Token ID11
Feature activation+7.81e-02

Pos logit contributions
glass+0.048
bles+0.047
driver+0.046
eper+0.046
adders+0.046
Neg logit contributions
 since-0.052
oph-0.046
heart-0.044
 pleasure-0.044
eter-0.044
Token Tim
Token ID5045
Feature activation-6.57e-02

Pos logit contributions
glass+0.125
bles+0.123
driver+0.120
eper+0.119
adders+0.119
Neg logit contributions
 since-0.142
oph-0.129
heart-0.126
eter-0.125
 aback-0.124
Tokenmy
Token ID1820
Feature activation+8.37e-02

Pos logit contributions
 since+0.127
 pleasure+0.118
oph+0.116
eter+0.113
 aback+0.113
Neg logit contributions
bles-0.096
glass-0.096
eper-0.095
driver-0.093
 drill-0.091
Token accidentally
Token ID14716
Feature activation-3.50e-02

Pos logit contributions
glass+0.134
bles+0.127
eper+0.127
driver+0.124
 drill+0.124
Neg logit contributions
 pleasure-0.148
 since-0.148
 aback-0.139
eter-0.138
oph-0.136
Token spilled
Token ID31896
Feature activation+1.91e-01

Pos logit contributions
 since+0.066
oph+0.056
heart+0.054
!".+0.054
 Mill+0.054
Neg logit contributions
bles-0.056
glass-0.056
ithering-0.054
adders-0.054
eper-0.054
Token his
Token ID465
Feature activation+3.39e-01

Pos logit contributions
glass+0.299
bles+0.298
driver+0.287
ithering+0.286
eper+0.286
Neg logit contributions
 since-0.369
oph-0.322
heart-0.314
 pleasure-0.310
eter-0.310
Token juice
Token ID13135
Feature activation-2.18e-02

Pos logit contributions
glass+0.515
bles+0.513
driver+0.498
eper+0.494
ithering+0.493
Neg logit contributions
 since-0.667
oph-0.585
heart-0.569
 pleasure-0.564
eter-0.564
Token all
Token ID477
Feature activation+1.06e-01

Pos logit contributions
 since+0.041
oph+0.034
!".+0.034
heart+0.032
 aback+0.032
Neg logit contributions
glass-0.037
eper-0.035
adders-0.035
ithering-0.035
bles-0.035
Token over
Token ID625
Feature activation-7.19e-03

Pos logit contributions
driver+0.160
hes+0.159
bles+0.154
eper+0.149
adders+0.148
Neg logit contributions
 since-0.187
oph-0.186
 pleasure-0.180
ya-0.179
eter-0.176
Token the
Token ID262
Feature activation-5.33e-02

Pos logit contributions
 since+0.014
oph+0.013
heart+0.012
 pleasure+0.012
eter+0.012
Neg logit contributions
glass-0.011
bles-0.011
driver-0.010
eper-0.010
ithering-0.010
Token chair
Token ID5118
Feature activation+1.82e-01

Pos logit contributions
 since+0.115
oph+0.114
 pleasure+0.109
eter+0.109
 aback+0.108
Neg logit contributions
 drill-0.064
driver-0.064
glass-0.064
bles-0.059
eper-0.059
Token a
Token ID257
Feature activation+1.47e-01

Pos logit contributions
glass+0.310
adders+0.304
driver+0.296
bles+0.295
eper+0.290
Neg logit contributions
 since-0.422
oph-0.391
heart-0.384
ya-0.372
ksh-0.370
Token single
Token ID2060
Feature activation-7.12e-02

Pos logit contributions
glass+0.252
bles+0.248
 drill+0.245
driver+0.245
ithering+0.242
Neg logit contributions
 since-0.259
oph-0.226
heart-0.220
eter-0.218
 aback-0.214
Token chair
Token ID5118
Feature activation+2.36e-01

Pos logit contributions
 since+0.135
oph+0.120
eter+0.114
heart+0.112
 aback+0.112
Neg logit contributions
glass-0.113
driver-0.111
 drill-0.109
bles-0.108
ithering-0.107
Token to
Token ID284
Feature activation+6.92e-03

Pos logit contributions
glass+0.404
bles+0.402
driver+0.394
eper+0.389
adders+0.387
Neg logit contributions
 since-0.414
oph-0.363
heart-0.349
 pleasure-0.346
eter-0.345
Token sit
Token ID1650
Feature activation+2.07e-01

Pos logit contributions
bles+0.011
glass+0.011
driver+0.010
eper+0.010
ithering+0.010
Neg logit contributions
 since-0.014
oph-0.012
heart-0.011
 pleasure-0.011
eter-0.011
Token on
Token ID319
Feature activation+3.61e-01

Pos logit contributions
glass+0.320
driver+0.312
adders+0.311
bles+0.307
ithering+0.302
Neg logit contributions
 since-0.410
oph-0.346
heart-0.346
!".-0.344
eter-0.344
Token and
Token ID290
Feature activation+8.57e-02

Pos logit contributions
glass+0.501
driver+0.487
ble+0.476
bles+0.474
eper+0.468
Neg logit contributions
 since-0.701
oph-0.683
eter-0.645
 aback-0.642
heart-0.637
Token the
Token ID262
Feature activation-3.64e-02

Pos logit contributions
glass+0.129
driver+0.124
bles+0.124
adders+0.121
eper+0.121
Neg logit contributions
 since-0.165
oph-0.153
eter-0.145
heart-0.145
 aback-0.143
Token children
Token ID1751
Feature activation+5.17e-02

Pos logit contributions
 since+0.079
oph+0.071
eter+0.069
 aback+0.068
heart+0.068
Neg logit contributions
glass-0.048
bles-0.047
driver-0.046
eper-0.045
adders-0.045
Token wanted
Token ID2227
Feature activation-8.30e-02

Pos logit contributions
glass+0.085
bles+0.084
driver+0.082
eper+0.082
adders+0.081
Neg logit contributions
 since-0.094
oph-0.085
 pleasure-0.081
eter-0.081
heart-0.080
Token to
Token ID284
Feature activation-2.18e-02

Pos logit contributions
 since+0.143
oph+0.131
heart+0.125
eter+0.121
 aback+0.121
Neg logit contributions
glass-0.144
driver-0.138
adders-0.138
 drill-0.135
eper-0.134
Token playing
Token ID2712
Feature activation+3.02e-01

Pos logit contributions
bles+0.281
eper+0.279
glass+0.275
adders+0.274
hes+0.273
Neg logit contributions
 since-0.366
oph-0.345
heart-0.318
eter-0.316
ya-0.314
Token in
Token ID287
Feature activation+2.42e-01

Pos logit contributions
glass+0.484
bles+0.481
driver+0.471
adders+0.464
eper+0.464
Neg logit contributions
 since-0.575
oph-0.487
heart-0.483
!".-0.476
 pleasure-0.473
Token his
Token ID465
Feature activation+3.79e-01

Pos logit contributions
glass+0.471
bles+0.469
driver+0.461
eper+0.457
ithering+0.455
Neg logit contributions
 since-0.366
oph-0.317
heart-0.301
eter-0.299
 pleasure-0.295
Token bedroom
Token ID14043
Feature activation+2.12e-01

Pos logit contributions
bles+0.551
glass+0.548
driver+0.543
adders+0.530
ithering+0.529
Neg logit contributions
 since-0.776
oph-0.680
 pleasure-0.666
eter-0.656
heart-0.655
Token when
Token ID618
Feature activation-2.65e-02

Pos logit contributions
glass+0.365
bles+0.364
driver+0.356
eper+0.352
adders+0.350
Neg logit contributions
 since-0.373
oph-0.325
heart-0.313
 pleasure-0.310
eter-0.309
Token he
Token ID339
Feature activation+3.30e-01

Pos logit contributions
 since+0.063
oph+0.055
 Sus+0.055
 Mill+0.055
heart+0.055
Neg logit contributions
bles-0.030
glass-0.030
driver-0.029
adders-0.029
ithering-0.028
Token heard
Token ID2982
Feature activation+1.36e-01

Pos logit contributions
glass+0.531
bles+0.524
eper+0.510
driver+0.502
ithering+0.495
Neg logit contributions
 since-0.608
 pleasure-0.543
oph-0.541
 aback-0.530
eter-0.530
Token a
Token ID257
Feature activation+8.99e-02

Pos logit contributions
glass+0.200
driver+0.188
bles+0.187
adders+0.186
eper+0.185
Neg logit contributions
 since-0.276
oph-0.248
eter-0.241
 pleasure-0.239
heart-0.236
Token knock
Token ID10643
Feature activation+2.37e-01

Pos logit contributions
glass+0.141
bles+0.140
driver+0.136
ithering+0.135
eper+0.135
Neg logit contributions
 since-0.173
oph-0.152
eter-0.147
heart-0.145
 pleasure-0.145
Token on
Token ID319
Feature activation+3.48e-01

Pos logit contributions
bles+0.252
glass+0.244
ithering+0.240
driver+0.235
adders+0.231
Neg logit contributions
 since-0.580
heart-0.513
oph-0.512
!".-0.502
 aback-0.499
Token the
Token ID262
Feature activation-4.31e-02

Pos logit contributions
glass+0.561
driver+0.552
 drill+0.538
eper+0.532
 sword+0.516
Neg logit contributions
 since-0.632
oph-0.582
eter-0.582
 pleasure-0.559
heart-0.548
Token,"
Token ID553
Feature activation-1.21e-01

Pos logit contributions
oph+0.019
 since+0.019
 aback+0.018
ited+0.017
eter+0.017
Neg logit contributions
adders-0.014
bles-0.013
otion-0.013
eper-0.013
driver-0.013
Token Anna
Token ID11735
Feature activation-2.77e-02

Pos logit contributions
 since+0.241
eter+0.220
oph+0.219
 pleasure+0.213
!".+0.209
Neg logit contributions
eper-0.174
glass-0.172
bles-0.166
driver-0.163
 drill-0.163
Token says
Token ID1139
Feature activation-2.45e-03

Pos logit contributions
 since+0.055
 pleasure+0.051
eter+0.049
oph+0.048
 sight+0.048
Neg logit contributions
eper-0.040
bles-0.039
driver-0.039
es-0.038
glass-0.038
Token.
Token ID13
Feature activation+2.38e-02

Pos logit contributions
 since+0.004
oph+0.003
 aback+0.003
eter+0.003
heart+0.003
Neg logit contributions
glass-0.005
bles-0.005
eper-0.005
ithering-0.005
adders-0.005
Token "
Token ID366
Feature activation+6.47e-02

Pos logit contributions
driver+0.036
bles+0.036
glass+0.035
ithering+0.034
adders+0.034
Neg logit contributions
 since-0.047
oph-0.042
heart-0.042
eter-0.040
ya-0.040
TokenHe
Token ID1544
Feature activation+3.62e-01

Pos logit contributions
glass+0.118
bles+0.118
driver+0.116
adders+0.116
eper+0.115
Neg logit contributions
 since-0.107
oph-0.089
eter-0.087
heart-0.085
 aback-0.084
Token's
Token ID338
Feature activation+9.69e-03

Pos logit contributions
eper+0.517
bles+0.517
glass+0.509
driver+0.497
adders+0.489
Neg logit contributions
 since-0.735
oph-0.666
heart-0.630
 pleasure-0.630
eter-0.629
Token a
Token ID257
Feature activation+6.21e-02

Pos logit contributions
eper+0.013
bles+0.013
glass+0.012
 drill+0.012
driver+0.012
Neg logit contributions
oph-0.020
 since-0.020
heart-0.019
eter-0.018
 aback-0.018
Token very
Token ID845
Feature activation+1.05e-01

Pos logit contributions
 drill+0.096
glass+0.096
 sword+0.095
bles+0.094
eper+0.093
Neg logit contributions
 since-0.120
oph-0.110
eter-0.103
heart-0.103
 aback-0.100
Token nice
Token ID3621
Feature activation-1.34e-02

Pos logit contributions
bles+0.160
 sword+0.154
glass+0.153
kin+0.151
 drill+0.150
Neg logit contributions
 since-0.210
oph-0.192
 aback-0.180
eter-0.180
heart-0.176
Token duck
Token ID22045
Feature activation+9.41e-03

Pos logit contributions
 since+0.027
oph+0.024
eter+0.023
ksh+0.022
 aback+0.022
Neg logit contributions
bles-0.019
eper-0.019
ble-0.019
glass-0.019
driver-0.018
Token still
Token ID991
Feature activation+2.19e-01

Pos logit contributions
glass+0.200
bles+0.194
adders+0.194
ithering+0.193
eper+0.190
Neg logit contributions
 since-0.256
!".-0.224
 pleasure-0.217
heart-0.214
 Sus-0.214
Token feel
Token ID1254
Feature activation+1.18e-01

Pos logit contributions
bles+0.356
glass+0.352
adders+0.345
ithering+0.344
driver+0.344
Neg logit contributions
 since-0.413
heart-0.346
 pleasure-0.346
oph-0.343
!".-0.341
Token the
Token ID262
Feature activation-1.57e-02

Pos logit contributions
bles+0.180
eper+0.177
hes+0.176
glass+0.175
adders+0.175
Neg logit contributions
 since-0.215
oph-0.215
ya-0.192
eter-0.191
heart-0.188
Token sunshine
Token ID34488
Feature activation-1.80e-01

Pos logit contributions
 since+0.024
oph+0.021
eter+0.020
heart+0.019
 Mill+0.019
Neg logit contributions
bles-0.030
glass-0.030
driver-0.029
eper-0.029
ithering-0.029
Token on
Token ID319
Feature activation+3.65e-01

Pos logit contributions
 since+0.352
heart+0.297
oph+0.290
 pleasure+0.287
!".+0.285
Neg logit contributions
bles-0.290
glass-0.289
ithering-0.283
adders-0.283
eper-0.279
Token his
Token ID465
Feature activation+3.55e-01

Pos logit contributions
bles+0.396
glass+0.393
driver+0.382
adders+0.381
eper+0.368
Neg logit contributions
 since-0.903
heart-0.803
oph-0.798
!".-0.793
 Mill-0.791
Token face
Token ID1986
Feature activation+1.90e-01

Pos logit contributions
glass+0.547
bles+0.542
driver+0.526
eper+0.520
adders+0.518
Neg logit contributions
 since-0.692
oph-0.613
heart-0.591
eter-0.585
 pleasure-0.581
Token and
Token ID290
Feature activation+8.16e-02

Pos logit contributions
glass+0.315
bles+0.313
driver+0.306
eper+0.299
ithering+0.298
Neg logit contributions
 since-0.340
oph-0.307
heart-0.290
 pleasure-0.290
eter-0.288
Token hear
Token ID3285
Feature activation+3.19e-01

Pos logit contributions
bles+0.129
glass+0.129
driver+0.126
ithering+0.125
adders+0.124
Neg logit contributions
 since-0.157
oph-0.134
heart-0.132
 pleasure-0.132
eter-0.130
Token the
Token ID262
Feature activation-4.17e-02

Pos logit contributions
glass+0.465
bles+0.439
eper+0.432
 drill+0.430
adders+0.429
Neg logit contributions
 since-0.631
oph-0.598
eter-0.556
 aback-0.550
heart-0.539
Token bub
Token ID10015
Feature activation-1.16e-02

Pos logit contributions
 since+0.076
oph+0.068
 aback+0.066
eter+0.064
 Mill+0.062
Neg logit contributions
bles-0.069
glass-0.068
eper-0.067
 drill-0.066
ble-0.065
Token her
Token ID607
Feature activation+1.74e-01

Pos logit contributions
bles+0.119
eper+0.117
glass+0.117
driver+0.117
adders+0.116
Neg logit contributions
 since-0.171
oph-0.161
ited-0.153
eter-0.153
 aback-0.150
Token and
Token ID290
Feature activation+1.04e-01

Pos logit contributions
bles+0.253
glass+0.252
driver+0.248
adders+0.247
eper+0.240
Neg logit contributions
 since-0.338
oph-0.309
 aback-0.294
eter-0.294
heart-0.291
Token praised
Token ID15342
Feature activation+3.17e-02

Pos logit contributions
glass+0.168
bles+0.167
driver+0.164
eper+0.162
adders+0.161
Neg logit contributions
 since-0.194
oph-0.172
heart-0.165
eter-0.164
 pleasure-0.163
Token him
Token ID683
Feature activation+3.11e-01

Pos logit contributions
bles+0.040
glass+0.039
driver+0.039
eper+0.038
adders+0.037
Neg logit contributions
 since-0.069
oph-0.062
eter-0.061
 pleasure-0.060
 aback-0.059
Token for
Token ID329
Feature activation+1.03e-01

Pos logit contributions
bles+0.496
glass+0.493
driver+0.481
eper+0.477
adders+0.471
Neg logit contributions
 since-0.576
oph-0.518
heart-0.493
eter-0.490
 pleasure-0.489
Token recommending
Token ID34639
Feature activation+1.48e-01

Pos logit contributions
bles+0.154
glass+0.152
driver+0.151
adders+0.148
ithering+0.148
Neg logit contributions
 since-0.209
heart-0.177
oph-0.177
 pleasure-0.177
 Mill-0.176
Token something
Token ID1223
Feature activation+1.03e-01

Pos logit contributions
glass+0.212
driver+0.205
bles+0.205
adders+0.203
eper+0.201
Neg logit contributions
 since-0.292
oph-0.269
eter-0.259
heart-0.251
 pleasure-0.249
Token sensible
Token ID20586
Feature activation-3.72e-02

Pos logit contributions
bles+0.168
glass+0.163
adders+0.162
driver+0.160
 chores+0.157
Neg logit contributions
 since-0.176
oph-0.169
eter-0.156
 aback-0.153
heart-0.151
Token.
Token ID13
Feature activation+3.36e-02

Pos logit contributions
 since+0.066
oph+0.059
eter+0.056
heart+0.056
 pleasure+0.056
Neg logit contributions
glass-0.062
bles-0.062
driver-0.061
eper-0.060
adders-0.059
Token Then
Token ID3244
Feature activation-2.47e-02

Pos logit contributions
glass+0.045
driver+0.045
His+0.044
eper+0.044
adders+0.043
Neg logit contributions
 since-0.064
ited-0.061
oph-0.059
heart-0.059
eter-0.059
Token she
Token ID673
Feature activation+1.31e-01

Pos logit contributions
 since+0.056
oph+0.052
eter+0.051
 pleasure+0.050
heart+0.050
Neg logit contributions
glass-0.028
bles-0.027
driver-0.027
eper-0.027
adders-0.025
Token.
Token ID13
Feature activation+1.48e-02

Pos logit contributions
glass+0.217
bles+0.216
driver+0.210
ithering+0.209
eper+0.209
Neg logit contributions
 since-0.220
oph-0.189
heart-0.182
eter-0.181
 pleasure-0.180
Token He
Token ID679
Feature activation+1.88e-01

Pos logit contributions
glass+0.016
driver+0.016
bles+0.015
eper+0.015
adders+0.015
Neg logit contributions
 since-0.035
oph-0.033
heart-0.032
ya-0.032
ited-0.031
Token grabbed
Token ID13176
Feature activation-1.20e-02

Pos logit contributions
glass+0.334
bles+0.331
eper+0.328
driver+0.322
adders+0.312
Neg logit contributions
 since-0.318
 pleasure-0.280
oph-0.275
heart-0.274
eter-0.271
Token his
Token ID465
Feature activation+3.12e-01

Pos logit contributions
 since+0.022
oph+0.020
heart+0.019
eter+0.019
 pleasure+0.019
Neg logit contributions
glass-0.019
bles-0.019
driver-0.019
eper-0.019
ithering-0.019
Token shoe
Token ID17292
Feature activation+1.20e-01

Pos logit contributions
glass+0.472
bles+0.464
adders+0.455
driver+0.453
ithering+0.451
Neg logit contributions
 since-0.616
oph-0.539
 pleasure-0.531
heart-0.523
eter-0.521
Token and
Token ID290
Feature activation+4.59e-02

Pos logit contributions
ithering+0.253
otion+0.252
bles+0.250
adders+0.248
glass+0.248
Neg logit contributions
 since-0.180
 bit-0.125
 aback-0.124
!".-0.121
eter-0.120
Token ran
Token ID4966
Feature activation+7.23e-02

Pos logit contributions
glass+0.075
bles+0.075
driver+0.073
eper+0.072
adders+0.072
Neg logit contributions
 since-0.085
oph-0.075
heart-0.072
 pleasure-0.072
eter-0.071
Token to
Token ID284
Feature activation-5.79e-02

Pos logit contributions
glass+0.139
bles+0.138
driver+0.137
eper+0.135
adders+0.134
Neg logit contributions
 since-0.112
oph-0.099
heart-0.095
 pleasure-0.093
eter-0.093
Token his
Token ID465
Feature activation+3.07e-01

Pos logit contributions
 since+0.116
oph+0.102
heart+0.099
 pleasure+0.098
eter+0.098
Neg logit contributions
glass-0.087
bles-0.087
driver-0.084
ithering-0.083
adders-0.083
Token bed
Token ID3996
Feature activation+9.93e-02

Pos logit contributions
glass+0.430
bles+0.428
driver+0.415
ithering+0.409
eper+0.409
Neg logit contributions
 since-0.648
oph-0.576
heart-0.559
eter-0.555
 pleasure-0.554
Token.
Token ID13
Feature activation+8.29e-03

Pos logit contributions
ithering+0.194
eper+0.192
bles+0.191
glass+0.190
adders+0.189
Neg logit contributions
 since-0.157
oph-0.124
!".-0.118
eter-0.118
 aback-0.116
TokenFrom
Token ID4863
Feature activation-6.38e-02

Pos logit contributions
 since+0.027
oph+0.023
!".+0.023
ya+0.023
heart+0.023
Neg logit contributions
bles-0.022
adders-0.021
driver-0.021
glass-0.021
otion-0.021
Token then
Token ID788
Feature activation-1.25e-01

Pos logit contributions
 since+0.112
eter+0.107
oph+0.105
 pleasure+0.102
heart+0.100
Neg logit contributions
bles-0.103
glass-0.103
eper-0.102
ble-0.100
driver-0.096
Token on
Token ID319
Feature activation+2.88e-01

Pos logit contributions
 since+0.283
 aback+0.235
!".+0.234
 Mill+0.229
 Daisy+0.228
Neg logit contributions
bles-0.168
glass-0.150
bridge-0.149
adders-0.147
ogo-0.145
Token,
Token ID11
Feature activation+1.50e-02

Pos logit contributions
glass+0.495
bles+0.494
driver+0.480
adders+0.477
ithering+0.476
Neg logit contributions
 since-0.515
oph-0.443
heart-0.430
 pleasure-0.424
eter-0.422
Token Robbie
Token ID34855
Feature activation-4.77e-02

Pos logit contributions
glass+0.024
bles+0.023
eper+0.023
driver+0.023
ithering+0.023
Neg logit contributions
 since-0.028
oph-0.025
heart-0.024
eter-0.024
 aback-0.024
Token has
Token ID468
Feature activation+1.30e-01

Pos logit contributions
 since+0.090
oph+0.082
heart+0.079
 pleasure+0.079
eter+0.078
Neg logit contributions
glass-0.074
bles-0.073
eper-0.073
driver-0.071
adders-0.069
Token been
Token ID587
Feature activation+1.89e-02

Pos logit contributions
glass+0.190
driver+0.186
adders+0.182
hes+0.182
 chores+0.179
Neg logit contributions
 since-0.240
heart-0.233
oph-0.223
ya-0.215
eter-0.214
Token telling
Token ID5149
Feature activation-3.00e-02

Pos logit contributions
eper+0.030
hes+0.029
glass+0.028
bles+0.028
driver+0.028
Neg logit contributions
 since-0.036
oph-0.036
heart-0.032
ya-0.031
eter-0.031
Token his
Token ID465
Feature activation+2.87e-01

Pos logit contributions
 since+0.065
oph+0.060
eter+0.057
heart+0.056
ited+0.055
Neg logit contributions
glass-0.039
driver-0.038
eper-0.037
bles-0.037
adders-0.037
Token friends
Token ID2460
Feature activation+9.95e-02

Pos logit contributions
glass+0.353
bles+0.352
driver+0.342
eper+0.337
adders+0.334
Neg logit contributions
 since-0.651
oph-0.590
heart-0.571
 aback-0.565
eter-0.564
Token how
Token ID703
Feature activation-4.39e-02

Pos logit contributions
glass+0.177
bles+0.177
ithering+0.174
eper+0.172
driver+0.170
Neg logit contributions
 since-0.179
heart-0.144
oph-0.144
 pleasure-0.142
!".-0.141
Token their
Token ID511
Feature activation+2.50e-01

Pos logit contributions
glass+0.103
bles+0.102
adders+0.099
eper+0.098
driver+0.097
Neg logit contributions
 since-0.168
oph-0.154
heart-0.149
eter-0.146
 aback-0.145
Token club
Token ID3430
Feature activation+8.28e-02

Pos logit contributions
bles+0.325
glass+0.323
driver+0.309
eper+0.306
adders+0.305
Neg logit contributions
 since-0.554
oph-0.497
heart-0.487
 aback-0.478
eter-0.474
Token.
Token ID13
Feature activation+2.79e-02

Pos logit contributions
glass+0.136
bles+0.136
driver+0.133
adders+0.131
eper+0.131
Neg logit contributions
 since-0.152
oph-0.134
heart-0.129
 pleasure-0.128
eter-0.127
Token They
Token ID1119
Feature activation+6.28e-02

Pos logit contributions
glass+0.031
driver+0.030
adders+0.030
otion+0.027
balls+0.027
Neg logit contributions
ited-0.062
 since-0.060
heart-0.060
oph-0.057
ya-0.057
Token took
Token ID1718
Feature activation+3.10e-02

Pos logit contributions
bles+0.105
glass+0.105
driver+0.103
eper+0.102
adders+0.101
Neg logit contributions
 since-0.113
oph-0.100
heart-0.097
 pleasure-0.096
eter-0.096
Token some
Token ID617
Feature activation+6.12e-02

Pos logit contributions
glass+0.062
bles+0.061
driver+0.061
adders+0.061
eper+0.060
Neg logit contributions
 since-0.047
oph-0.041
heart-0.039
eter-0.037
ya-0.037
Token sticks
Token ID16461
Feature activation+1.55e-01

Pos logit contributions
glass+0.082
bles+0.081
driver+0.080
adders+0.079
ithering+0.077
Neg logit contributions
 since-0.132
oph-0.121
heart-0.117
eter-0.116
 pleasure-0.115
Token and
Token ID290
Feature activation+5.90e-02

Pos logit contributions
glass+0.316
ithering+0.308
eper+0.303
bles+0.302
adders+0.300
Neg logit contributions
 since-0.241
 aback-0.182
 Daisy-0.177
 Mill-0.175
oph-0.173
Token stones
Token ID14966
Feature activation-6.75e-03

Pos logit contributions
glass+0.091
bles+0.091
driver+0.089
adders+0.087
eper+0.087
Neg logit contributions
 since-0.114
oph-0.102
heart-0.099
 pleasure-0.098
eter-0.097
Token and
Token ID290
Feature activation+5.63e-02

Pos logit contributions
 since+0.010
 aback+0.007
 Mill+0.007
!".+0.007
 Daisy+0.007
Neg logit contributions
glass-0.014
ithering-0.014
eper-0.014
otion-0.014
 drill-0.013
Token made
Token ID925
Feature activation-1.97e-03

Pos logit contributions
bles+0.096
glass+0.096
ithering+0.094
driver+0.093
eper+0.093
Neg logit contributions
 since-0.100
oph-0.086
heart-0.083
eter-0.082
 pleasure-0.082
Token"
Token ID1
Feature activation+1.69e-02

Pos logit contributions
 since+0.053
oph+0.044
!".+0.042
ya+0.042
heart+0.041
Neg logit contributions
bles-0.060
glass-0.059
adders-0.058
driver-0.058
eper-0.057
TokenOkay
Token ID16454
Feature activation-2.24e-01

Pos logit contributions
glass+0.033
bles+0.033
driver+0.032
eper+0.032
ithering+0.031
Neg logit contributions
 since-0.026
oph-0.022
heart-0.022
 pleasure-0.022
eter-0.021
Token,
Token ID11
Feature activation+1.02e-03

Pos logit contributions
ited+0.558
oph+0.533
eter+0.532
 aback+0.520
 since+0.518
Neg logit contributions
driver-0.189
bles-0.188
 not-0.177
eper-0.177
balls-0.176
Token we
Token ID356
Feature activation-1.32e-01

Pos logit contributions
glass+0.002
bles+0.002
driver+0.002
eper+0.002
adders+0.002
Neg logit contributions
 since-0.002
oph-0.002
 aback-0.002
heart-0.002
eter-0.002
Token will
Token ID481
Feature activation+1.20e-02

Pos logit contributions
 since+0.256
oph+0.224
 pleasure+0.217
heart+0.216
eter+0.215
Neg logit contributions
glass-0.207
bles-0.206
driver-0.200
ithering-0.198
eper-0.197
Token go
Token ID467
Feature activation+1.41e-01

Pos logit contributions
glass+0.017
bles+0.016
driver+0.016
hips+0.016
 drill+0.016
Neg logit contributions
 since-0.024
oph-0.023
heart-0.022
eter-0.022
 aback-0.021
Token to
Token ID284
Feature activation-9.32e-02

Pos logit contributions
glass+0.253
bles+0.244
driver+0.243
eper+0.240
ithering+0.232
Neg logit contributions
 since-0.239
oph-0.225
heart-0.214
eter-0.206
 pleasure-0.205
Token church
Token ID4928
Feature activation+9.83e-02

Pos logit contributions
 since+0.178
heart+0.166
oph+0.166
eter+0.159
ited+0.155
Neg logit contributions
glass-0.144
 drill-0.139
 chores-0.135
eper-0.134
 sword-0.132
Token and
Token ID290
Feature activation+9.83e-03

Pos logit contributions
glass+0.161
bles+0.159
driver+0.153
eper+0.151
es+0.146
Neg logit contributions
 since-0.168
oph-0.167
heart-0.159
 aback-0.155
 Mill-0.154
Token pray
Token ID12472
Feature activation+8.49e-02

Pos logit contributions
bles+0.016
glass+0.015
driver+0.015
ithering+0.015
eper+0.015
Neg logit contributions
 since-0.019
oph-0.016
 pleasure-0.016
heart-0.016
eter-0.016
Token.
Token ID13
Feature activation-2.57e-02

Pos logit contributions
bles+0.132
glass+0.132
driver+0.131
adders+0.125
ble+0.125
Neg logit contributions
 since-0.150
oph-0.147
 aback-0.135
ited-0.134
heart-0.133
Token "
Token ID366
Feature activation+6.63e-02

Pos logit contributions
driver+0.025
His+0.025
balls+0.024
es+0.024
glass+0.024
Neg logit contributions
ited-0.046
 since-0.045
heart-0.043
 matter-0.042
fy-0.042
TokenYou
Token ID1639
Feature activation+9.65e-02

Pos logit contributions
glass+0.101
bles+0.098
hes+0.095
bridge+0.094
ithering+0.094
Neg logit contributions
 since-0.124
oph-0.113
heart-0.111
 aback-0.110
eter-0.107
Token saved
Token ID7448
Feature activation+3.19e-02

Pos logit contributions
bles+0.100
glass+0.095
adders+0.094
eper+0.093
driver+0.091
Neg logit contributions
 since-0.233
oph-0.218
eter-0.217
heart-0.214
ya-0.212
Token me
Token ID502
Feature activation-2.32e-01

Pos logit contributions
 not+0.050
 chores+0.049
ble+0.048
eper+0.047
aches+0.047
Neg logit contributions
ited-0.057
fy-0.053
 since-0.052
ksh-0.052
oph-0.050
Token!"
Token ID2474
Feature activation-2.75e-01

Pos logit contributions
 since+0.398
oph+0.382
 pleasure+0.356
eter+0.350
heart+0.348
Neg logit contributions
bles-0.392
glass-0.386
ble-0.375
driver-0.374
eper-0.373
Token From
Token ID3574
Feature activation-1.28e-01

Pos logit contributions
 since+0.517
eter+0.481
ited+0.479
oph+0.472
 pleasure+0.468
Neg logit contributions
glass-0.405
hes-0.394
es-0.391
driver-0.385
bles-0.380
Token that
Token ID326
Feature activation+2.49e-02

Pos logit contributions
eter+0.275
 since+0.267
 pleasure+0.262
ksh+0.259
oph+0.259
Neg logit contributions
ble-0.161
eper-0.161
bles-0.156
glass-0.149
hes-0.136
Token day
Token ID1110
Feature activation-7.85e-02

Pos logit contributions
 drill+0.034
eper+0.034
kin+0.033
glass+0.033
 sword+0.033
Neg logit contributions
oph-0.047
eter-0.047
 since-0.046
 aback-0.044
ksh-0.042
Token on
Token ID319
Feature activation+3.10e-01

Pos logit contributions
 since+0.192
!".+0.169
 Daisy+0.166
 Mill+0.165
 aback+0.164
Neg logit contributions
glass-0.083
bles-0.082
 drill-0.076
driver-0.076
hips-0.073
Token,
Token ID11
Feature activation+3.72e-02

Pos logit contributions
bles+0.434
driver+0.434
glass+0.427
eper+0.423
ithering+0.421
Neg logit contributions
 since-0.614
oph-0.568
eter-0.560
 pleasure-0.542
 aback-0.537
Token Lily
Token ID20037
Feature activation-1.81e-01

Pos logit contributions
bles+0.054
es+0.052
adders+0.051
 chores+0.051
driver+0.050
Neg logit contributions
oph-0.064
 aback-0.062
ited-0.062
 since-0.062
ksh-0.061
Token so
Token ID523
Feature activation-2.11e-01

Pos logit contributions
driver+0.022
glass+0.021
hes+0.021
bles+0.021
 drill+0.020
Neg logit contributions
 since-0.026
eter-0.026
oph-0.025
 pleasure-0.024
.''-0.024
Token they
Token ID484
Feature activation+1.43e-01

Pos logit contributions
 since+0.512
oph+0.488
eter+0.478
 pleasure+0.477
 aback+0.473
Neg logit contributions
bles-0.206
driver-0.194
glass-0.191
ithering-0.186
eper-0.186
Token went
Token ID1816
Feature activation-8.83e-03

Pos logit contributions
glass+0.250
bles+0.250
driver+0.244
eper+0.241
ithering+0.241
Neg logit contributions
 since-0.250
oph-0.216
heart-0.209
eter-0.206
 pleasure-0.206
Token over
Token ID625
Feature activation-5.63e-02

Pos logit contributions
 since+0.012
 aback+0.009
!".+0.009
 Mill+0.009
 Sus+0.009
Neg logit contributions
bles-0.019
glass-0.019
eper-0.019
adders-0.019
otion-0.019
Token to
Token ID284
Feature activation-8.07e-02

Pos logit contributions
 since+0.097
oph+0.090
heart+0.089
eter+0.084
 pleasure+0.084
Neg logit contributions
glass-0.097
driver-0.094
bles-0.091
adders-0.091
ithering-0.090
Token the
Token ID262
Feature activation-9.95e-02

Pos logit contributions
 since+0.151
oph+0.136
heart+0.135
eter+0.134
ya+0.125
Neg logit contributions
glass-0.127
driver-0.122
bles-0.122
 drill-0.122
eper-0.121
Token man
Token ID582
Feature activation+8.54e-02

Pos logit contributions
 since+0.183
oph+0.162
 sight+0.156
ya+0.155
 aback+0.152
Neg logit contributions
bles-0.166
ithering-0.160
driver-0.160
adders-0.160
glass-0.159
Token and
Token ID290
Feature activation+1.95e-02

Pos logit contributions
bles+0.168
ithering+0.161
glass+0.161
eper+0.160
adders+0.160
Neg logit contributions
 since-0.139
eter-0.108
 aback-0.107
oph-0.107
 Mill-0.107
Token helped
Token ID4193
Feature activation-9.16e-02

Pos logit contributions
glass+0.031
eper+0.031
driver+0.031
hes+0.030
 drill+0.030
Neg logit contributions
eter-0.034
 since-0.033
heart-0.033
 pleasure-0.032
oph-0.032
Token him
Token ID683
Feature activation+2.40e-01

Pos logit contributions
 since+0.221
oph+0.208
 pleasure+0.204
eter+0.202
heart+0.199
Neg logit contributions
driver-0.091
glass-0.090
bles-0.088
 chores-0.084
eper-0.084
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
glass+0.399
bles+0.394
eper+0.385
driver+0.382
adders+0.379
Neg logit contributions
 since-0.438
oph-0.370
eter-0.368
 aback-0.366
heart-0.366
Token Grand
Token ID5675
Feature activation-1.80e-01

Pos logit contributions
 since+0.008
 aback+0.008
ited+0.008
eter+0.008
oph+0.007
Neg logit contributions
eper-0.008
bles-0.008
 drill-0.007
ble-0.007
otion-0.007
Tokenma
Token ID2611
Feature activation+1.70e-01

Pos logit contributions
 since+0.456
 aback+0.411
 pleasure+0.411
eter+0.406
oph+0.399
Neg logit contributions
glass-0.167
eper-0.162
bles-0.160
driver-0.151
otion-0.150
Token?"
Token ID1701
Feature activation-3.35e-02

Pos logit contributions
eper+0.229
bles+0.223
driver+0.221
glass+0.220
 drill+0.215
Neg logit contributions
 since-0.338
oph-0.321
 pleasure-0.319
 aback-0.311
eter-0.311
Token asked
Token ID1965
Feature activation-2.34e-01

Pos logit contributions
 since+0.058
eter+0.057
 pleasure+0.056
oph+0.055
ksh+0.052
Neg logit contributions
glass-0.056
 drill-0.054
eper-0.053
His-0.052
hes-0.052
Token a
Token ID257
Feature activation+8.08e-03

Pos logit contributions
 since+0.421
 pleasure+0.377
oph+0.376
eter+0.364
ya+0.359
Neg logit contributions
eper-0.389
driver-0.388
glass-0.378
bles-0.376
hes-0.373
Token three
Token ID1115
Feature activation-1.54e-01

Pos logit contributions
 drill+0.014
glass+0.014
 sword+0.013
eper+0.013
bles+0.013
Neg logit contributions
 since-0.014
eter-0.013
oph-0.012
 aback-0.012
heart-0.012
Token-
Token ID12
Feature activation-4.43e-02

Pos logit contributions
 since+0.264
oph+0.230
 pleasure+0.229
eter+0.225
 aback+0.221
Neg logit contributions
glass-0.275
bles-0.272
eper-0.268
driver-0.263
adders-0.258
Tokenyear
Token ID1941
Feature activation+6.15e-02

Pos logit contributions
 since+0.089
oph+0.078
heart+0.076
 aback+0.075
ya+0.075
Neg logit contributions
bles-0.066
glass-0.065
ithering-0.064
driver-0.063
eper-0.062
Token-
Token ID12
Feature activation-4.52e-02

Pos logit contributions
bles+0.117
glass+0.117
ithering+0.116
driver+0.114
adders+0.113
Neg logit contributions
 since-0.096
oph-0.083
heart-0.082
ya-0.080
eter-0.077
Tokenold
Token ID727
Feature activation+3.41e-02

Pos logit contributions
 since+0.084
oph+0.074
heart+0.072
ya+0.071
 aback+0.070
Neg logit contributions
bles-0.074
glass-0.072
ithering-0.072
driver-0.071
eper-0.070
Token girl
Token ID2576
Feature activation-2.55e-01

Pos logit contributions
eper+0.069
glass+0.069
driver+0.067
bles+0.067
 drill+0.064
Neg logit contributions
 since-0.049
oph-0.045
 pleasure-0.042
eter-0.042
 refreshing-0.039
Token
Token ID241
Feature activation-5.30e-02

Pos logit contributions
 since+0.012
heart+0.011
oph+0.010
eter+0.010
 Mill+0.010
Neg logit contributions
glass-0.010
bles-0.009
ves-0.009
hips-0.009
agons-0.009
TokenWe
Token ID1135
Feature activation-1.56e-02

Pos logit contributions
 since+0.090
oph+0.083
 aback+0.079
heart+0.078
eter+0.077
Neg logit contributions
glass-0.088
bles-0.086
ithering-0.084
driver-0.084
hes-0.082
Token did
Token ID750
Feature activation+1.55e-01

Pos logit contributions
 since+0.033
oph+0.029
eter+0.029
heart+0.028
ya+0.028
Neg logit contributions
bles-0.022
glass-0.021
eper-0.021
driver-0.021
adders-0.021
Token it
Token ID340
Feature activation-1.09e-01

Pos logit contributions
glass+0.269
bles+0.265
ves+0.259
driver+0.257
 chores+0.257
Neg logit contributions
 since-0.260
oph-0.249
ited-0.235
heart-0.230
eter-0.226
Token!
Token ID0
Feature activation-2.42e-01

Pos logit contributions
 since+0.135
oph+0.120
eter+0.110
ited+0.110
 aback+0.110
Neg logit contributions
bles-0.240
driver-0.232
glass-0.228
eper-0.227
ble-0.225
Token We
Token ID775
Feature activation-1.98e-01

Pos logit contributions
ited+0.415
 since+0.407
oph+0.389
 sight+0.377
ya+0.376
Neg logit contributions
driver-0.401
glass-0.391
eper-0.377
ithering-0.374
adders-0.374
Token put
Token ID1234
Feature activation-9.05e-02

Pos logit contributions
 since+0.407
oph+0.368
eter+0.360
heart+0.356
 pleasure+0.347
Neg logit contributions
bles-0.284
glass-0.274
eper-0.271
driver-0.270
adders-0.267
Token the
Token ID262
Feature activation-1.21e-01

Pos logit contributions
 since+0.175
oph+0.169
heart+0.161
eter+0.153
ited+0.152
Neg logit contributions
bles-0.144
glass-0.139
eper-0.139
driver-0.135
hips-0.131
Token puzzle
Token ID15027
Feature activation+1.55e-02

Pos logit contributions
 since+0.250
oph+0.236
heart+0.234
ya+0.223
 Mill+0.223
Neg logit contributions
bles-0.174
driver-0.165
adders-0.164
glass-0.162
hips-0.160
Token together
Token ID1978
Feature activation-7.22e-02

Pos logit contributions
bles+0.023
driver+0.023
glass+0.022
adders+0.022
hips+0.021
Neg logit contributions
 since-0.030
oph-0.029
heart-0.028
ya-0.027
eter-0.027
Token!
Token ID0
Feature activation-2.43e-01

Pos logit contributions
 since+0.123
oph+0.123
heart+0.116
 aback+0.115
 Mill+0.115
Neg logit contributions
bles-0.118
glass-0.111
driver-0.109
box-0.108
eper-0.108
Token in
Token ID287
Feature activation+1.45e-01

Pos logit contributions
bles+0.380
glass+0.376
adders+0.364
eper+0.360
driver+0.360
Neg logit contributions
 since-0.484
oph-0.457
heart-0.434
ya-0.420
 pleasure-0.417
Token exploring
Token ID13504
Feature activation+7.07e-02

Pos logit contributions
glass+0.267
bles+0.259
eper+0.257
driver+0.257
ithering+0.257
Neg logit contributions
 since-0.233
oph-0.211
heart-0.202
eter-0.198
ya-0.193
Token.
Token ID13
Feature activation-9.18e-03

Pos logit contributions
glass+0.112
bles+0.111
adders+0.108
eper+0.106
ithering+0.106
Neg logit contributions
 since-0.130
oph-0.122
eter-0.115
heart-0.115
 aback-0.112
Token Everyone
Token ID11075
Feature activation-1.06e-01

Pos logit contributions
 since+0.019
heart+0.018
ited+0.017
oph+0.017
eter+0.017
Neg logit contributions
glass-0.013
bles-0.012
adders-0.012
driver-0.012
balls-0.012
Token was
Token ID373
Feature activation+1.33e-02

Pos logit contributions
 since+0.209
oph+0.191
eter+0.187
 pleasure+0.185
heart+0.182
Neg logit contributions
glass-0.158
bles-0.158
eper-0.154
driver-0.148
adders-0.148
Token excited
Token ID6568
Feature activation-6.68e-02

Pos logit contributions
bles+0.024
glass+0.023
eper+0.023
ithering+0.022
hes+0.022
Neg logit contributions
 since-0.023
oph-0.021
heart-0.020
eter-0.020
 aback-0.019
Token and
Token ID290
Feature activation+2.54e-02

Pos logit contributions
 since+0.117
oph+0.116
eter+0.115
 pleasure+0.115
 aback+0.112
Neg logit contributions
glass-0.096
bles-0.095
driver-0.088
balls-0.088
eper-0.087
Token they
Token ID484
Feature activation+1.49e-01

Pos logit contributions
bles+0.038
glass+0.036
eper+0.035
hes+0.034
balls+0.034
Neg logit contributions
 since-0.048
oph-0.047
 aback-0.045
heart-0.045
eter-0.045
Token quickly
Token ID2952
Feature activation-7.59e-02

Pos logit contributions
bles+0.202
eper+0.190
glass+0.189
adders+0.178
driver+0.175
Neg logit contributions
 since-0.311
eter-0.295
heart-0.285
 aback-0.284
oph-0.284
Token followed
Token ID3940
Feature activation+4.59e-02

Pos logit contributions
 since+0.146
heart+0.135
eter+0.133
 pleasure+0.132
oph+0.130
Neg logit contributions
glass-0.115
bles-0.111
adders-0.107
eper-0.106
driver-0.106
Token him
Token ID683
Feature activation+2.45e-01

Pos logit contributions
glass+0.057
driver+0.053
bles+0.053
eper+0.052
adders+0.051
Neg logit contributions
 since-0.099
oph-0.097
heart-0.092
eter-0.090
 pleasure-0.090
Token "
Token ID366
Feature activation+6.74e-02

Pos logit contributions
bles+0.081
glass+0.081
driver+0.080
ithering+0.078
eper+0.078
Neg logit contributions
 since-0.095
oph-0.085
heart-0.082
eter-0.081
 pleasure-0.080
TokenTim
Token ID14967
Feature activation+2.59e-02

Pos logit contributions
glass+0.111
eper+0.108
driver+0.106
ithering+0.105
bles+0.105
Neg logit contributions
 since-0.123
 pleasure-0.109
oph-0.109
ya-0.106
 Mill-0.105
Token,
Token ID11
Feature activation+4.80e-02

Pos logit contributions
eper+0.042
driver+0.042
bles+0.042
glass+0.040
 drill+0.040
Neg logit contributions
 since-0.047
oph-0.043
 pleasure-0.041
ya-0.041
eter-0.040
Token come
Token ID1282
Feature activation+1.73e-01

Pos logit contributions
bles+0.089
glass+0.088
ithering+0.085
driver+0.084
adders+0.084
Neg logit contributions
 since-0.081
 pleasure-0.067
heart-0.066
 Sus-0.065
oph-0.065
Token back
Token ID736
Feature activation+4.49e-02

Pos logit contributions
bles+0.279
glass+0.276
eper+0.276
ithering+0.273
driver+0.270
Neg logit contributions
 since-0.323
oph-0.302
heart-0.281
ya-0.279
eter-0.273
Token!"
Token ID2474
Feature activation-2.72e-01

Pos logit contributions
eper+0.087
ithering+0.085
driver+0.084
bles+0.084
glass+0.083
Neg logit contributions
oph-0.064
 since-0.059
ited-0.057
ya-0.057
 pleasure-0.055
Token
Token ID198
Feature activation+1.40e-02

Pos logit contributions
 since+0.460
oph+0.405
heart+0.388
eter+0.383
 pleasure+0.382
Neg logit contributions
glass-0.489
bles-0.484
driver-0.478
ithering-0.468
adders-0.468
Token
Token ID198
Feature activation+1.26e-02

Pos logit contributions
bles+0.028
glass+0.027
driver+0.027
eper+0.027
adders+0.027
Neg logit contributions
 since-0.021
oph-0.018
!".-0.017
 Mill-0.017
 Sus-0.017
TokenThe
Token ID464
Feature activation-1.36e-04

Pos logit contributions
bles+0.024
glass+0.023
adders+0.023
driver+0.023
otion+0.023
Neg logit contributions
 since-0.021
!".-0.016
oph-0.016
heart-0.016
 Mill-0.016
Token truck
Token ID7779
Feature activation+2.61e-01

Pos logit contributions
 since+0.000
 sight+0.000
 pleasure+0.000
!".+0.000
ya+0.000
Neg logit contributions
bles-0.000
otion-0.000
ithering-0.000
glass-0.000
driver-0.000
Token driver
Token ID4639
Feature activation+2.13e-01

Pos logit contributions
bles+0.345
ithering+0.334
glass+0.331
adders+0.327
driver+0.326
Neg logit contributions
 since-0.568
oph-0.495
eter-0.482
heart-0.481
 aback-0.480
TokenThat
Token ID2504
Feature activation-3.92e-02

Pos logit contributions
bles+0.123
glass+0.122
driver+0.119
eper+0.118
ithering+0.118
Neg logit contributions
 since-0.137
oph-0.119
heart-0.115
eter-0.114
 pleasure-0.113
Token was
Token ID373
Feature activation+5.10e-02

Pos logit contributions
 since+0.080
oph+0.071
heart+0.069
 pleasure+0.068
eter+0.068
Neg logit contributions
glass-0.057
bles-0.057
driver-0.056
eper-0.055
adders-0.054
Token your
Token ID534
Feature activation-3.70e-03

Pos logit contributions
hes+0.068
 drill+0.067
adders+0.066
bles+0.066
glass+0.065
Neg logit contributions
 since-0.109
oph-0.106
heart-0.103
ited-0.100
eter-0.099
Token birthday
Token ID10955
Feature activation+8.59e-02

Pos logit contributions
 since+0.008
oph+0.007
heart+0.007
 aback+0.007
eter+0.007
Neg logit contributions
glass-0.005
bles-0.005
driver-0.005
eper-0.005
adders-0.005
Token cake
Token ID12187
Feature activation+1.29e-01

Pos logit contributions
glass+0.132
driver+0.124
box+0.124
eper+0.122
bles+0.122
Neg logit contributions
 since-0.162
 aback-0.153
oph-0.151
 Mill-0.145
ya-0.145
Token!"
Token ID2474
Feature activation-2.68e-01

Pos logit contributions
glass+0.225
bles+0.224
driver+0.218
eper+0.215
adders+0.213
Neg logit contributions
 since-0.219
oph-0.195
 aback-0.188
eter-0.186
heart-0.186
Token
Token ID198
Feature activation+1.62e-02

Pos logit contributions
 since+0.523
oph+0.478
eter+0.473
heart+0.464
ited+0.462
Neg logit contributions
bles-0.395
glass-0.391
driver-0.388
adders-0.379
hes-0.379
Token
Token ID198
Feature activation+1.54e-02

Pos logit contributions
glass+0.030
bles+0.030
driver+0.030
eper+0.029
adders+0.029
Neg logit contributions
 since-0.026
oph-0.022
heart-0.022
 pleasure-0.021
eter-0.021
Token"
Token ID1
Feature activation+6.18e-02

Pos logit contributions
glass+0.024
bles+0.024
driver+0.023
eper+0.023
ithering+0.023
Neg logit contributions
 since-0.030
oph-0.027
heart-0.026
 pleasure-0.026
eter-0.026
TokenO
Token ID46
Feature activation-4.90e-02

Pos logit contributions
glass+0.121
bles+0.120
driver+0.117
eper+0.116
ithering+0.116
Neg logit contributions
 since-0.097
oph-0.082
heart-0.080
eter-0.078
 pleasure-0.078
Tokenops
Token ID2840
Feature activation+2.24e-01

Pos logit contributions
 since+0.112
oph+0.101
heart+0.098
eter+0.097
!".+0.096
Neg logit contributions
glass-0.060
bles-0.059
driver-0.057
eper-0.057
ithering-0.057
Token said
Token ID531
Feature activation-1.56e-01

Pos logit contributions
driver+0.092
bles+0.090
glass+0.088
es+0.087
ves+0.085
Neg logit contributions
 pleasure-0.118
 since-0.117
eter-0.111
 sight-0.109
umm-0.106
Token.
Token ID13
Feature activation-3.38e-02

Pos logit contributions
 since+0.284
oph+0.254
heart+0.243
 pleasure+0.241
eter+0.239
Neg logit contributions
glass-0.257
bles-0.256
driver-0.254
adders-0.246
eper-0.245
Token
Token ID198
Feature activation-4.07e-02

Pos logit contributions
 since+0.074
ited+0.073
heart+0.071
oph+0.070
 matter+0.068
Neg logit contributions
driver-0.043
glass-0.039
hes-0.038
bles-0.038
balls-0.037
Token
Token ID198
Feature activation-4.11e-02

Pos logit contributions
 since+0.072
oph+0.062
heart+0.061
eter+0.060
 pleasure+0.060
Neg logit contributions
glass-0.071
bles-0.071
driver-0.069
ithering-0.068
adders-0.068
TokenThe
Token ID464
Feature activation-5.27e-02

Pos logit contributions
 since+0.079
oph+0.071
 pleasure+0.070
heart+0.069
eter+0.069
Neg logit contributions
glass-0.065
bles-0.064
driver-0.062
ithering-0.061
eper-0.061
Token little
Token ID1310
Feature activation-2.48e-01

Pos logit contributions
 since+0.069
oph+0.057
eter+0.056
 Sus+0.056
 aback+0.056
Neg logit contributions
bles-0.114
driver-0.110
eper-0.110
glass-0.109
ithering-0.108
Token girl
Token ID2576
Feature activation-2.60e-01

Pos logit contributions
 since+0.388
oph+0.350
!".+0.347
ya+0.346
ksh+0.343
Neg logit contributions
bles-0.412
eper-0.410
kin-0.407
driver-0.406
kins-0.385
Token walked
Token ID6807
Feature activation+6.41e-02

Pos logit contributions
 since+0.475
heart+0.429
 pleasure+0.424
oph+0.417
 sight+0.410
Neg logit contributions
glass-0.414
bles-0.410
driver-0.407
eper-0.402
es-0.378
Token to
Token ID284
Feature activation-1.04e-01

Pos logit contributions
glass+0.113
bles+0.111
eper+0.110
driver+0.110
adders+0.106
Neg logit contributions
 since-0.109
oph-0.098
 pleasure-0.096
heart-0.094
eter-0.094
Token the
Token ID262
Feature activation-1.20e-01

Pos logit contributions
 since+0.192
eter+0.170
oph+0.169
heart+0.168
fy+0.160
Neg logit contributions
glass-0.165
bles-0.161
eper-0.160
 drill-0.160
driver-0.159
Token tree
Token ID5509
Feature activation-6.00e-02

Pos logit contributions
 since+0.217
oph+0.188
heart+0.188
eter+0.184
 Sus+0.182
Neg logit contributions
glass-0.199
bles-0.198
eper-0.195
driver-0.194
ithering-0.190
Token they
Token ID484
Feature activation+1.38e-01

Pos logit contributions
bles+0.033
balls+0.032
adders+0.032
eper+0.031
driver+0.031
Neg logit contributions
 since-0.037
oph-0.037
 aback-0.034
eter-0.034
ited-0.034
Token're
Token ID821
Feature activation+1.76e-02

Pos logit contributions
bles+0.124
adders+0.116
driver+0.111
glass+0.111
eper+0.110
Neg logit contributions
 since-0.344
oph-0.333
heart-0.325
 sight-0.316
ya-0.315
Token good
Token ID922
Feature activation-2.02e-02

Pos logit contributions
bles+0.028
eper+0.026
adders+0.026
glass+0.026
ithering+0.025
Neg logit contributions
 since-0.034
oph-0.032
heart-0.030
 aback-0.029
eter-0.029
Token to
Token ID284
Feature activation-8.42e-02

Pos logit contributions
 since+0.031
oph+0.031
ya+0.028
 Mill+0.027
 pleasure+0.027
Neg logit contributions
bles-0.038
eper-0.037
driver-0.037
glass-0.036
adders-0.035
Token eat
Token ID4483
Feature activation+2.46e-02

Pos logit contributions
 since+0.164
oph+0.151
 aback+0.144
eter+0.143
heart+0.143
Neg logit contributions
bles-0.127
glass-0.125
eper-0.123
ithering-0.121
driver-0.120
Token."
Token ID526
Feature activation-2.61e-01

Pos logit contributions
bles+0.043
ble+0.040
eper+0.040
glass+0.039
balls+0.039
Neg logit contributions
 since-0.042
oph-0.041
 aback-0.038
 pleasure-0.037
eter-0.037
Token Ho
Token ID9544
Feature activation-5.17e-02

Pos logit contributions
 since+0.462
heart+0.426
oph+0.422
ited+0.405
ya+0.405
Neg logit contributions
bles-0.425
glass-0.425
balls-0.423
eper-0.412
His-0.405
Tokenpper
Token ID2848
Feature activation+1.79e-01

Pos logit contributions
 since+0.118
 pleasure+0.107
 Sus+0.106
oph+0.106
 Mill+0.106
Neg logit contributions
bles-0.067
ithering-0.061
eper-0.060
driver-0.060
glass-0.059
Token said
Token ID531
Feature activation-1.40e-01

Pos logit contributions
bles+0.250
eper+0.241
His+0.240
driver+0.229
 sword+0.227
Neg logit contributions
 pleasure-0.361
 since-0.339
umm-0.328
 sight-0.325
eter-0.319
Token,
Token ID11
Feature activation+7.62e-03

Pos logit contributions
 since+0.258
oph+0.227
heart+0.218
eter+0.216
 pleasure+0.215
Neg logit contributions
glass-0.232
bles-0.231
driver-0.227
eper-0.223
ithering-0.222
Token "
Token ID366
Feature activation+2.40e-02

Pos logit contributions
bles+0.010
glass+0.010
driver+0.010
balls+0.009
hes+0.009
Neg logit contributions
 since-0.016
oph-0.016
eter-0.016
heart-0.015
 pleasure-0.015
Token was
Token ID373
Feature activation-1.80e-02

Pos logit contributions
glass+0.122
bles+0.121
driver+0.118
eper+0.117
ithering+0.117
Neg logit contributions
 since-0.135
oph-0.118
heart-0.114
 pleasure-0.113
eter-0.113
Token a
Token ID257
Feature activation+5.29e-04

Pos logit contributions
 since+0.031
oph+0.027
 pleasure+0.026
 Mill+0.026
heart+0.026
Neg logit contributions
bles-0.032
glass-0.032
driver-0.031
eper-0.031
ithering-0.030
Token reliable
Token ID9314
Feature activation-1.08e-01

Pos logit contributions
bles+0.001
glass+0.001
eper+0.001
ithering+0.001
 drill+0.001
Neg logit contributions
 since-0.001
oph-0.001
 aback-0.001
heart-0.001
eter-0.001
Token girl
Token ID2576
Feature activation-2.62e-01

Pos logit contributions
 since+0.210
oph+0.184
heart+0.178
eter+0.177
 aback+0.177
Neg logit contributions
glass-0.165
bles-0.165
driver-0.160
eper-0.159
ithering-0.157
Token named
Token ID3706
Feature activation+1.48e-02

Pos logit contributions
 since+0.540
oph+0.493
 pleasure+0.475
heart+0.473
eter+0.470
Neg logit contributions
glass-0.370
bles-0.361
eper-0.354
driver-0.353
ithering-0.349
Token Jane
Token ID12091
Feature activation-3.22e-01

Pos logit contributions
otion+0.018
 not+0.018
adders+0.017
hes+0.016
bles+0.016
Neg logit contributions
ited-0.031
eter-0.029
ksh-0.029
heart-0.029
 aback-0.029
Token.
Token ID13
Feature activation-3.89e-02

Pos logit contributions
 since+0.552
oph+0.464
heart+0.452
eter+0.443
!".+0.440
Neg logit contributions
bles-0.583
glass-0.582
driver-0.569
adders-0.564
ithering-0.564
Token One
Token ID1881
Feature activation-1.44e-01

Pos logit contributions
 since+0.076
oph+0.067
eter+0.066
heart+0.066
ya+0.065
Neg logit contributions
adders-0.056
otion-0.056
bles-0.055
glass-0.054
ithering-0.054
Token day
Token ID1110
Feature activation-1.31e-01

Pos logit contributions
 since+0.209
oph+0.176
heart+0.168
eter+0.166
 pleasure+0.165
Neg logit contributions
glass-0.295
bles-0.295
driver-0.289
eper-0.286
ithering-0.286
Token,
Token ID11
Feature activation-1.44e-02

Pos logit contributions
 since+0.211
oph+0.174
 Mill+0.171
 Sus+0.170
heart+0.169
Neg logit contributions
glass-0.259
bles-0.258
eper-0.252
driver-0.251
adders-0.245
Token Jane
Token ID12091
Feature activation-3.23e-01

Pos logit contributions
 since+0.027
oph+0.025
eter+0.024
 pleasure+0.023
heart+0.023
Neg logit contributions
glass-0.022
bles-0.021
adders-0.021
driver-0.021
otion-0.021