TOP ACTIVATIONS
MAX = 0.508

and forth and squ aw ked along . The pirate realized
an idea . It hon ked its horn very loud .
. The chicken squ aw ked and fl apped , but
and kind . She stro ked their hair and kissed their
the dog . He hon ked the horn . He shouted
his bed . She stro ked his hair and kissed his
was coming . It hon ked loudly . "
driver saw Lily and hon ked his horn . Lily was
scared . She gently stro ked its fur and stood up
house ?" The goose hon ked and fl apped its wings
all qu acked and hon ked with joy . The bunny
. Tom and Lily stro ked its fur and gave it
After he finished he stro ked the rabbit 's head and
car hon ked and bra ked , but it was too
goose . The goose hon ked his horn and scared the
coming . The car hon ked and bra ked . Spot
sw am rivers and trek ked through the woods . But
driving by and it hon ked at him . Johnny thought
car hon ked and bra ked . The ambulance s iren
coming . The car hon ked and bra ked , but

MIN ACTIVATIONS
MIN = -0.663

we will go home and you will get no toy at
OK , but only if you let me play with your
itten . It will keep you warm ." Tom
you and I will make you some juice myself ." Lily
best to stay strong and you can always find a way
" Yes , thank you ," Max said .
take care of the things you love ! <|endoftext|> One day
It is a gift for you ." Ben said , "
of you . Anna , you need to share your desk
" Mom , you are so smart . You
hurt your k ite and you . Let 's see if
color you want , but you have to use the yellow
of flour as a thank you present . The princess was
" OK , but you have to be gentle .
is that sm elly thing you are playing with ?" Fl
That is very sweet of you . I will send it
and blue beads , and you sort the yellow and green
. " Thank you , doctor ," Mom said
. " Thank you , Lily and Sam .
can trust me to keep you safe ." Her mom opened

INTERVAL 0.215 - 0.508
CONTAINS 12.079%

Everyone in the village gathered around , eager to take a
, so she sw am over and took it .
shiny in the sand . He picked it up . It
the messy living room . She was not happy . She
that sharing is caring . They learned that welcoming is loving

INTERVAL -0.078 - 0.215
CONTAINS 56.228%

shook his head and kept walking . He wanted to laugh
to cry . mummy said , " it 's OK .
Lily went to bed with her tooth under her pillow .
. He finds a red balloon in his room . He
wh ips were dangerous and he told his friend to put

INTERVAL -0.371 - -0.078
CONTAINS 29.927%

colors together . " What a strange mix ,"
park . L ily said , " Yes
hopped in ! The car drove around town ,
a birthday cake !" They take a big bite
hunter away . The rabbit said , " I

INTERVAL -0.663 - -0.371
CONTAINS 1.764%

asked , " What do you have in your bag ?"
br ac ad ab ra !" He opened his
. It said " Thank you for playing with us !"
for you . I hope you like it ." She gave
. I was worried about you ." L ily
Token and
Token ID290
Feature activation+2.76e-01

Pos logit contributions
elt+0.409
ked+0.400
ashed+0.381
arted+0.380
 shrugged+0.347
Neg logit contributions
 you-0.558
?-0.476
 happen-0.457
uch-0.456
 achieve-0.451
Token forth
Token ID6071
Feature activation+6.15e-02

Pos logit contributions
elt+0.538
ked+0.514
arted+0.512
ashed+0.489
itted+0.480
Neg logit contributions
 you-0.549
 happen-0.483
uch-0.471
prise-0.443
w-0.439
Token and
Token ID290
Feature activation+2.76e-01

Pos logit contributions
elt+0.121
arted+0.120
ked+0.112
ashed+0.107
 eyes+0.107
Neg logit contributions
 you-0.114
 happen-0.105
uch-0.101
gh-0.096
prise-0.095
Token squ
Token ID2809
Feature activation+6.90e-02

Pos logit contributions
elt+0.549
ked+0.523
arted+0.510
ashed+0.484
itted+0.479
Neg logit contributions
 you-0.543
 happen-0.481
uch-0.467
prise-0.444
w-0.433
Tokenaw
Token ID707
Feature activation+6.13e-02

Pos logit contributions
ked+0.094
 asleep+0.092
sed+0.091
elt+0.090
 arms+0.090
Neg logit contributions
 you-0.151
prise-0.149
uch-0.148
w-0.140
irl-0.134
Tokenked
Token ID9091
Feature activation+5.08e-01

Pos logit contributions
elt+0.027
arted+0.026
ked+0.021
 arms+0.021
 eyes+0.021
Neg logit contributions
 you-0.199
uch-0.197
prise-0.191
 happen-0.188
w-0.182
Token along
Token ID1863
Feature activation+1.45e-01

Pos logit contributions
elt+1.030
ashed+0.884
arted+0.873
ked+0.873
oured+0.833
Neg logit contributions
 you-1.012
 happen-0.947
gh-0.828
 ourselves-0.810
ggy-0.806
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
elt+0.310
ked+0.306
arted+0.292
ashed+0.286
ed+0.281
Neg logit contributions
 you-0.250
prise-0.222
uch-0.217
 happen-0.215
 achieve-0.198
Token The
Token ID383
Feature activation+2.53e-01

Pos logit contributions
 you+0.384
n+0.320
uch+0.319
 achieve+0.315
 am+0.311
Neg logit contributions
ked-0.278
elt-0.253
arted-0.238
ashed-0.236
ed-0.230
Token pirate
Token ID25868
Feature activation+7.72e-02

Pos logit contributions
ked+0.373
elt+0.347
 eyes+0.343
 arms+0.335
 confused+0.334
Neg logit contributions
 you-0.568
uch-0.568
prise-0.567
 happen-0.534
 achieve-0.513
Token realized
Token ID6939
Feature activation+1.03e-01

Pos logit contributions
elt+0.150
arted+0.141
ked+0.140
 eyes+0.127
 floppy+0.125
Neg logit contributions
 you-0.152
uch-0.143
 happen-0.132
prise-0.131
n-0.128
Token an
Token ID281
Feature activation+8.47e-02

Pos logit contributions
 you+0.022
uch+0.019
 happen+0.019
prise+0.019
 am+0.018
Neg logit contributions
elt-0.022
ked-0.022
arted-0.021
ed-0.020
ashed-0.020
Token idea
Token ID2126
Feature activation+3.19e-02

Pos logit contributions
ked+0.196
elt+0.193
ed+0.184
 asleep+0.178
ashed+0.177
Neg logit contributions
 happen-0.133
 you-0.131
uch-0.127
prise-0.117
ggy-0.113
Token.
Token ID13
Feature activation-1.76e-01

Pos logit contributions
ked+0.061
ed+0.059
elt+0.058
 arms+0.056
 eyes+0.055
Neg logit contributions
uch-0.061
prise-0.059
 you-0.056
 achieve-0.054
arest-0.051
Token It
Token ID632
Feature activation+2.34e-01

Pos logit contributions
 you+0.424
 am+0.319
".+0.315
?+0.312
"+0.309
Neg logit contributions
ked-0.273
ashed-0.264
arted-0.242
ened-0.237
 shrugged-0.236
Token hon
Token ID3032
Feature activation+7.28e-02

Pos logit contributions
elt+0.399
ked+0.379
arted+0.377
 eyes+0.355
itted+0.340
Neg logit contributions
 you-0.484
prise-0.455
 am-0.448
uch-0.439
 happen-0.437
Tokenked
Token ID9091
Feature activation+5.06e-01

Pos logit contributions
 asleep+0.057
 wooden+0.047
 floppy+0.042
 arms+0.041
 infant+0.040
Neg logit contributions
uch-0.211
w-0.206
 you-0.195
oh-0.183
prise-0.183
Token its
Token ID663
Feature activation+1.02e-01

Pos logit contributions
elt+1.053
ashed+0.896
oured+0.874
ked+0.864
arted+0.860
Neg logit contributions
 you-1.001
 happen-0.898
 ourselves-0.799
ggy-0.781
gh-0.770
Token horn
Token ID12718
Feature activation+2.15e-01

Pos logit contributions
elt+0.145
arted+0.137
ed+0.125
ashed+0.124
ked+0.124
Neg logit contributions
 you-0.249
uch-0.232
 happen-0.231
 ourselves-0.220
 am-0.217
Token very
Token ID845
Feature activation+8.60e-02

Pos logit contributions
elt+0.369
arted+0.339
ashed+0.327
joy+0.311
ked+0.303
Neg logit contributions
 you-0.465
 happen-0.431
uch-0.412
?-0.382
 ourselves-0.379
Token loud
Token ID7812
Feature activation+7.79e-02

Pos logit contributions
ked+0.119
 confused+0.109
arted+0.108
 eyes+0.107
elt+0.107
Neg logit contributions
prise-0.209
uch-0.201
 you-0.198
 happen-0.185
 am-0.182
Token.
Token ID13
Feature activation-1.79e-01

Pos logit contributions
elt+0.177
arted+0.169
ked+0.166
ashed+0.162
 shrugged+0.156
Neg logit contributions
 you-0.124
 happen-0.109
uch-0.097
prise-0.093
 am-0.091
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
ked+0.606
elt+0.591
arted+0.572
ed+0.568
 arms+0.558
Neg logit contributions
 you-0.410
prise-0.408
uch-0.401
 happen-0.358
 achieve-0.338
Token The
Token ID383
Feature activation+2.46e-01

Pos logit contributions
 you+0.414
 am+0.327
?+0.320
 achieve+0.311
't+0.308
Neg logit contributions
ked-0.288
ed-0.257
elt-0.254
arted-0.251
ened-0.243
Token chicken
Token ID9015
Feature activation+1.23e-01

Pos logit contributions
ked+0.348
elt+0.340
arted+0.323
ed+0.311
ashed+0.301
Neg logit contributions
 you-0.590
prise-0.570
uch-0.570
 happen-0.540
 achieve-0.515
Token squ
Token ID2809
Feature activation+6.87e-02

Pos logit contributions
elt+0.224
arted+0.218
ked+0.213
 asleep+0.196
 eyes+0.194
Neg logit contributions
 you-0.245
uch-0.234
prise-0.223
 happen-0.216
 am-0.212
Tokenaw
Token ID707
Feature activation+5.69e-02

Pos logit contributions
 asleep+0.101
 puzzled+0.092
 confused+0.092
 wooden+0.092
 shrugged+0.090
Neg logit contributions
 you-0.146
w-0.144
uch-0.141
prise-0.141
irl-0.123
Tokenked
Token ID9091
Feature activation+5.05e-01

Pos logit contributions
arted+0.031
 arms+0.027
elt+0.027
 eyes+0.025
 floppy+0.023
Neg logit contributions
uch-0.179
 you-0.178
 happen-0.169
w-0.165
prise-0.165
Token and
Token ID290
Feature activation+2.64e-01

Pos logit contributions
elt+0.892
oured+0.782
ashed+0.777
arted+0.775
 shrugged+0.734
Neg logit contributions
 you-1.103
 happen-0.935
gh-0.882
ggy-0.879
w-0.857
Token fl
Token ID781
Feature activation+4.74e-02

Pos logit contributions
elt+0.422
arted+0.409
ked+0.404
ed+0.375
 eyes+0.374
Neg logit contributions
 you-0.587
uch-0.543
prise-0.533
 happen-0.531
w-0.498
Tokenapped
Token ID6320
Feature activation+3.39e-01

Pos logit contributions
ked+0.046
elt+0.046
arted+0.045
 confused+0.045
 asleep+0.045
Neg logit contributions
prise-0.123
uch-0.123
 you-0.123
w-0.115
arest-0.111
Token,
Token ID11
Feature activation-1.43e-02

Pos logit contributions
elt+0.597
ked+0.542
arted+0.535
ashed+0.506
oured+0.496
Neg logit contributions
 you-0.762
 happen-0.644
prise-0.636
 ourselves-0.603
 am-0.592
Token but
Token ID475
Feature activation+1.91e-01

Pos logit contributions
 you+0.031
 happen+0.028
 course+0.026
 achieve+0.026
n+0.026
Neg logit contributions
elt-0.023
arted-0.022
ed-0.021
ked-0.021
ashed-0.020
Token and
Token ID290
Feature activation+2.61e-01

Pos logit contributions
 you+0.141
?+0.109
 happen+0.106
 us+0.105
 ourselves+0.104
Neg logit contributions
ked-0.112
arted-0.108
ashed-0.107
oured-0.106
elt-0.103
Token kind
Token ID1611
Feature activation-7.62e-02

Pos logit contributions
ked+0.451
arted+0.450
elt+0.436
ed+0.417
ashed+0.410
Neg logit contributions
 you-0.557
prise-0.511
uch-0.492
 happen-0.486
 am-0.470
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
 you+0.088
prise+0.063
 happen+0.060
 ourselves+0.053
 am+0.051
Neg logit contributions
arted-0.202
elt-0.199
ked-0.199
ashed-0.194
 shrugged-0.189
Token She
Token ID1375
Feature activation+2.53e-01

Pos logit contributions
 you+0.333
prise+0.281
 am+0.273
uch+0.266
 happen+0.258
Neg logit contributions
ked-0.388
arted-0.364
elt-0.353
ashed-0.352
ened-0.344
Token stro
Token ID9660
Feature activation+2.56e-01

Pos logit contributions
arted+0.500
ked+0.480
elt+0.478
 arms+0.464
 down+0.450
Neg logit contributions
 you-0.446
prise-0.426
 am-0.407
lly-0.406
ggy-0.396
Tokenked
Token ID9091
Feature activation+5.05e-01

Pos logit contributions
 wooden+0.182
 asleep+0.159
 floppy+0.149
 arms+0.145
 shrugged+0.124
Neg logit contributions
 you-0.747
uch-0.738
w-0.703
 ourselves-0.686
prise-0.673
Token their
Token ID511
Feature activation+1.20e-02

Pos logit contributions
elt+1.161
ashed+1.032
oured+0.997
itted+0.997
ked+0.987
Neg logit contributions
 you-0.845
 happen-0.671
ggy-0.631
 us-0.609
 ourselves-0.595
Token hair
Token ID4190
Feature activation+2.44e-01

Pos logit contributions
elt+0.019
arted+0.017
ked+0.015
ed+0.015
ashed+0.015
Neg logit contributions
 you-0.029
 happen-0.027
prise-0.026
uch-0.026
 ourselves-0.025
Token and
Token ID290
Feature activation+2.61e-01

Pos logit contributions
arted+0.379
elt+0.353
ked+0.324
ashed+0.314
joy+0.304
Neg logit contributions
 you-0.559
uch-0.531
 happen-0.524
n-0.486
 am-0.483
Token kissed
Token ID27946
Feature activation+7.21e-02

Pos logit contributions
arted+0.495
elt+0.462
ked+0.450
ashed+0.438
attered+0.417
Neg logit contributions
 you-0.535
 happen-0.483
uch-0.450
prise-0.448
 am-0.445
Token their
Token ID511
Feature activation+1.21e-02

Pos logit contributions
ked+0.156
elt+0.152
arted+0.147
ed+0.145
 eyes+0.142
Neg logit contributions
 you-0.117
prise-0.115
uch-0.115
 happen-0.104
 achieve-0.099
Token the
Token ID262
Feature activation+3.14e-03

Pos logit contributions
arted+0.584
elt+0.560
itted+0.559
ashed+0.542
ked+0.540
Neg logit contributions
 you-0.439
?-0.340
prise-0.325
 happen-0.324
 else-0.313
Token dog
Token ID3290
Feature activation+1.68e-01

Pos logit contributions
ked+0.004
elt+0.004
arted+0.004
ed+0.004
ashed+0.004
Neg logit contributions
 you-0.008
prise-0.007
uch-0.007
 happen-0.007
 am-0.007
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
ked+0.371
elt+0.361
arted+0.350
ed+0.344
 eyes+0.341
Neg logit contributions
 you-0.261
prise-0.256
uch-0.254
 happen-0.229
 achieve-0.215
Token He
Token ID679
Feature activation+3.58e-01

Pos logit contributions
 you+0.488
 am+0.447
?+0.417
prise+0.409
 happen+0.405
Neg logit contributions
ked-0.257
arted-0.245
ashed-0.228
elt-0.210
oured-0.209
Token hon
Token ID3032
Feature activation+7.37e-02

Pos logit contributions
elt+0.768
arted+0.760
ked+0.736
 asleep+0.720
ashed+0.706
Neg logit contributions
 you-0.587
prise-0.515
 am-0.513
uch-0.503
ggy-0.501
Tokenked
Token ID9091
Feature activation+5.05e-01

Pos logit contributions
 asleep+0.043
 floppy+0.036
 wooden+0.034
 arms+0.031
elt+0.031
Neg logit contributions
uch-0.218
w-0.217
 you-0.212
prise-0.212
oh-0.193
Token the
Token ID262
Feature activation+3.29e-03

Pos logit contributions
elt+1.088
ashed+0.983
oured+0.954
ked+0.944
arted+0.933
Neg logit contributions
 you-0.944
 happen-0.806
ggy-0.722
 ourselves-0.701
 am-0.693
Token horn
Token ID12718
Feature activation+2.15e-01

Pos logit contributions
elt+0.005
ked+0.005
arted+0.004
ed+0.004
ashed+0.004
Neg logit contributions
 you-0.008
uch-0.007
prise-0.007
 happen-0.007
 am-0.007
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
elt+0.545
arted+0.523
ked+0.520
ashed+0.510
 shrugged+0.495
Neg logit contributions
 you-0.288
 happen-0.244
uch-0.240
prise-0.225
 am-0.202
Token He
Token ID679
Feature activation+3.58e-01

Pos logit contributions
 you+0.484
 am+0.423
prise+0.401
?+0.400
 happen+0.399
Neg logit contributions
ked-0.257
arted-0.242
elt-0.224
ashed-0.219
ened-0.213
Token shouted
Token ID17293
Feature activation+5.34e-02

Pos logit contributions
elt+0.690
arted+0.663
ked+0.622
 asleep+0.619
itted+0.608
Neg logit contributions
 you-0.685
uch-0.615
 am-0.594
prise-0.592
ggy-0.591
Token his
Token ID465
Feature activation+1.48e-01

Pos logit contributions
elt+0.167
ked+0.167
arted+0.158
ed+0.153
ashed+0.152
Neg logit contributions
 you-0.205
prise-0.189
uch-0.186
 happen-0.182
 am-0.170
Token bed
Token ID3996
Feature activation+3.44e-02

Pos logit contributions
ked+0.289
elt+0.288
arted+0.280
ashed+0.263
ed+0.262
Neg logit contributions
 you-0.292
 happen-0.270
uch-0.263
prise-0.262
 am-0.236
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
elt+0.087
ked+0.087
arted+0.085
ashed+0.081
ed+0.080
Neg logit contributions
 you-0.043
uch-0.039
prise-0.038
 happen-0.037
 achieve-0.032
Token She
Token ID1375
Feature activation+2.51e-01

Pos logit contributions
 you+0.439
 am+0.376
?+0.368
One+0.361
 achieve+0.352
Neg logit contributions
ked-0.297
arted-0.263
ened-0.245
ashed-0.243
ed-0.233
Token stro
Token ID9660
Feature activation+2.53e-01

Pos logit contributions
arted+0.496
ked+0.481
elt+0.471
pered+0.433
itted+0.428
Neg logit contributions
 you-0.473
prise-0.451
uch-0.417
lly-0.416
 am-0.408
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 wooden+0.148
 arms+0.125
 shrugged+0.118
arted+0.118
 floppy+0.116
Neg logit contributions
 you-0.731
uch-0.695
w-0.684
 ourselves-0.663
prise-0.646
Token his
Token ID465
Feature activation+1.49e-01

Pos logit contributions
elt+0.996
arted+0.916
ashed+0.900
ked+0.854
oured+0.842
Neg logit contributions
 you-1.018
 happen-0.881
gh-0.815
ggy-0.808
?-0.762
Token hair
Token ID4190
Feature activation+2.43e-01

Pos logit contributions
arted+0.240
elt+0.217
ashed+0.207
ked+0.198
ed+0.176
Neg logit contributions
 you-0.353
uch-0.330
 happen-0.327
prise-0.309
 am-0.304
Token and
Token ID290
Feature activation+2.63e-01

Pos logit contributions
arted+0.422
elt+0.389
ked+0.366
ashed+0.360
joy+0.335
Neg logit contributions
 you-0.518
uch-0.500
 happen-0.486
n-0.448
 am-0.444
Token kissed
Token ID27946
Feature activation+6.92e-02

Pos logit contributions
arted+0.503
elt+0.462
ked+0.443
ashed+0.428
pered+0.422
Neg logit contributions
 you-0.538
 happen-0.484
uch-0.472
prise-0.465
 am-0.443
Token his
Token ID465
Feature activation+1.50e-01

Pos logit contributions
ked+0.127
elt+0.124
arted+0.118
ed+0.117
 eyes+0.115
Neg logit contributions
 you-0.134
prise-0.132
uch-0.132
 happen-0.122
 achieve-0.116
Token was
Token ID373
Feature activation-4.41e-02

Pos logit contributions
ked+0.197
elt+0.197
arted+0.188
ed+0.177
 eyes+0.177
Neg logit contributions
 you-0.262
uch-0.250
prise-0.247
 happen-0.239
 am-0.226
Token coming
Token ID2406
Feature activation+2.20e-02

Pos logit contributions
 you+0.085
 happen+0.080
uch+0.076
prise+0.073
ggy+0.071
Neg logit contributions
elt-0.086
ked-0.078
ashed-0.078
ed-0.077
arted-0.077
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
ked+0.030
elt+0.030
arted+0.028
ed+0.027
ashed+0.026
Neg logit contributions
 you-0.054
prise-0.051
uch-0.051
 happen-0.049
 achieve-0.046
Token It
Token ID632
Feature activation+2.34e-01

Pos logit contributions
 you+0.380
prise+0.336
uch+0.330
 am+0.316
n+0.306
Neg logit contributions
ked-0.274
elt-0.256
arted-0.255
ened-0.248
ed-0.246
Token hon
Token ID3032
Feature activation+7.11e-02

Pos logit contributions
elt+0.457
ked+0.440
arted+0.430
 eyes+0.411
ed+0.402
Neg logit contributions
 you-0.439
uch-0.419
 happen-0.395
prise-0.395
 am-0.381
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 asleep+0.049
 wooden+0.041
 floppy+0.039
 arms+0.038
elt+0.035
Neg logit contributions
uch-0.209
w-0.199
 you-0.196
prise-0.186
oh-0.186
Token loudly
Token ID23112
Feature activation+2.23e-01

Pos logit contributions
elt+0.994
oured+0.840
ashed+0.840
arted+0.829
ked+0.787
Neg logit contributions
 you-1.024
 happen-0.930
 ourselves-0.842
ggy-0.836
gh-0.828
Token.
Token ID13
Feature activation-1.71e-01

Pos logit contributions
elt+0.486
arted+0.460
ashed+0.450
ked+0.449
 shrugged+0.435
Neg logit contributions
 you-0.378
 happen-0.320
uch-0.280
prise-0.278
!"-0.273
Token
Token ID198
Feature activation-1.27e-01

Pos logit contributions
 you+0.287
prise+0.261
uch+0.260
 happen+0.238
 am+0.231
Neg logit contributions
ked-0.368
elt-0.358
arted-0.348
ed-0.340
ashed-0.334
Token
Token ID198
Feature activation-1.28e-01

Pos logit contributions
uch+0.327
prise+0.309
 happen+0.305
 you+0.288
w+0.287
Neg logit contributions
 He-0.160
elt-0.153
ed-0.146
arted-0.140
 confused-0.137
Token"
Token ID1
Feature activation-3.56e-01

Pos logit contributions
 happen+0.189
uch+0.172
prise+0.167
 you+0.158
vern+0.138
Neg logit contributions
ked-0.299
elt-0.295
ed-0.293
ashed-0.287
arted-0.280
Token driver
Token ID4639
Feature activation+1.74e-01

Pos logit contributions
elt+0.396
ked+0.391
arted+0.368
ed+0.359
ashed+0.343
Neg logit contributions
 you-0.578
prise-0.531
uch-0.525
 happen-0.515
 am-0.485
Token saw
Token ID2497
Feature activation+1.23e-01

Pos logit contributions
elt+0.324
 asleep+0.309
arted+0.309
ked+0.305
 floppy+0.298
Neg logit contributions
 you-0.329
uch-0.301
prise-0.298
 happen-0.274
 am-0.272
Token Lily
Token ID20037
Feature activation+7.78e-02

Pos logit contributions
ked+0.211
elt+0.207
arted+0.197
ed+0.192
ashed+0.188
Neg logit contributions
 you-0.261
prise-0.249
uch-0.245
 happen-0.234
 achieve-0.219
Token and
Token ID290
Feature activation+2.76e-01

Pos logit contributions
elt+0.107
ked+0.101
arted+0.098
ashed+0.095
ed+0.091
Neg logit contributions
 you-0.194
 happen-0.182
uch-0.181
prise-0.172
 achieve-0.171
Token hon
Token ID3032
Feature activation+7.20e-02

Pos logit contributions
arted+0.561
ashed+0.547
elt+0.544
itted+0.543
 asleep+0.536
Neg logit contributions
 you-0.526
 happen-0.392
ggy-0.391
 else-0.387
 am-0.371
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 asleep+0.049
 wooden+0.042
 floppy+0.041
 arms+0.037
elt+0.037
Neg logit contributions
uch-0.199
w-0.196
 you-0.191
prise-0.187
gh-0.180
Token his
Token ID465
Feature activation+1.53e-01

Pos logit contributions
elt+1.133
ashed+1.023
ked+1.001
arted+0.968
oured+0.950
Neg logit contributions
 you-0.892
 happen-0.797
ggy-0.698
 ourselves-0.686
 am-0.665
Token horn
Token ID12718
Feature activation+2.15e-01

Pos logit contributions
elt+0.223
arted+0.215
ashed+0.198
ed+0.186
ked+0.186
Neg logit contributions
 you-0.373
uch-0.349
 happen-0.340
ggy-0.327
 am-0.325
Token.
Token ID13
Feature activation-1.72e-01

Pos logit contributions
elt+0.572
arted+0.537
ashed+0.534
ked+0.521
 shrugged+0.497
Neg logit contributions
 you-0.249
 happen-0.229
uch-0.205
ggy-0.182
?-0.175
Token Lily
Token ID20037
Feature activation+7.76e-02

Pos logit contributions
 you+0.440
 am+0.372
n+0.361
't+0.357
 happen+0.354
Neg logit contributions
ked-0.253
elt-0.211
arted-0.207
ashed-0.196
sed-0.189
Token was
Token ID373
Feature activation-3.86e-02

Pos logit contributions
elt+0.162
arted+0.155
 asleep+0.153
ked+0.151
itted+0.150
Neg logit contributions
 you-0.133
uch-0.119
ggy-0.110
n-0.108
 am-0.108
Token scared
Token ID12008
Feature activation+2.30e-01

Pos logit contributions
elt+0.485
ked+0.484
arted+0.442
ed+0.428
ashed+0.426
Neg logit contributions
 you-0.604
 happen-0.532
uch-0.524
prise-0.514
 am-0.495
Token.
Token ID13
Feature activation-1.65e-01

Pos logit contributions
ked+0.562
elt+0.553
arted+0.527
ashed+0.524
 shrugged+0.514
Neg logit contributions
 you-0.340
 happen-0.269
prise-0.267
uch-0.254
 am-0.236
Token She
Token ID1375
Feature activation+2.63e-01

Pos logit contributions
 you+0.297
n+0.236
One+0.227
prise+0.225
 am+0.225
Neg logit contributions
ked-0.364
elt-0.327
arted-0.315
ashed-0.311
ed-0.307
Token gently
Token ID15165
Feature activation+9.84e-02

Pos logit contributions
elt+0.529
joy+0.467
arted+0.467
ked+0.459
 asleep+0.454
Neg logit contributions
 you-0.500
n-0.432
ggy-0.423
uch-0.423
 happen-0.418
Token stro
Token ID9660
Feature activation+2.51e-01

Pos logit contributions
elt+0.170
arted+0.166
itted+0.158
 asleep+0.157
 eyes+0.155
Neg logit contributions
 you-0.180
n-0.174
prise-0.174
uch-0.167
lly-0.164
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 wooden+0.173
 asleep+0.155
 floppy+0.126
 arms+0.118
 Earlier+0.111
Neg logit contributions
 you-0.705
uch-0.693
w-0.688
 ourselves-0.651
ggy-0.639
Token its
Token ID663
Feature activation+1.04e-01

Pos logit contributions
elt+1.261
ashed+1.136
ked+1.060
oured+1.058
attered+1.049
Neg logit contributions
 you-0.812
 happen-0.707
ggy-0.567
 ourselves-0.567
n-0.556
Token fur
Token ID9230
Feature activation+3.08e-01

Pos logit contributions
elt+0.157
arted+0.152
ashed+0.142
ked+0.134
ed+0.131
Neg logit contributions
 you-0.237
 happen-0.229
uch-0.223
ggy-0.216
gh-0.214
Token and
Token ID290
Feature activation+2.77e-01

Pos logit contributions
elt+0.506
arted+0.493
ashed+0.434
 floppy+0.407
joy+0.403
Neg logit contributions
 you-0.617
 happen-0.574
uch-0.544
n-0.536
 course-0.533
Token stood
Token ID6204
Feature activation+2.46e-01

Pos logit contributions
elt+0.515
arted+0.512
ked+0.478
ashed+0.471
itted+0.466
Neg logit contributions
 you-0.568
 happen-0.500
prise-0.471
uch-0.463
ggy-0.441
Token up
Token ID510
Feature activation+2.42e-01

Pos logit contributions
elt+0.389
ked+0.375
ashed+0.374
arted+0.356
ed+0.336
Neg logit contributions
 you-0.555
prise-0.510
uch-0.477
?-0.471
 ourselves-0.466
Token house
Token ID2156
Feature activation+7.67e-02

Pos logit contributions
ked+0.121
elt+0.115
arted+0.113
ed+0.107
ashed+0.102
Neg logit contributions
 you-0.171
prise-0.161
uch-0.159
 happen-0.155
 am-0.147
Token?"
Token ID1701
Feature activation-4.11e-01

Pos logit contributions
elt+0.214
ked+0.212
 down+0.205
 eyes+0.205
 asleep+0.205
Neg logit contributions
prise-0.066
uch-0.063
 you-0.063
 happen-0.052
arest-0.049
Token The
Token ID383
Feature activation+2.46e-01

Pos logit contributions
 you+0.992
uch+0.898
prise+0.897
 happen+0.861
 achieve+0.843
Neg logit contributions
ked-0.607
elt-0.570
arted-0.559
ashed-0.535
ed-0.531
Token goose
Token ID37246
Feature activation+1.01e-01

Pos logit contributions
ked+0.350
elt+0.341
arted+0.323
ed+0.312
ashed+0.302
Neg logit contributions
 you-0.593
prise-0.571
uch-0.571
 happen-0.543
 achieve-0.517
Token hon
Token ID3032
Feature activation+6.89e-02

Pos logit contributions
elt+0.166
ked+0.162
arted+0.159
 asleep+0.149
ed+0.146
Neg logit contributions
 you-0.216
uch-0.202
prise-0.195
 happen-0.193
 am-0.186
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 asleep+0.043
 arms+0.035
 wooden+0.034
 eyes+0.032
 floppy+0.030
Neg logit contributions
uch-0.209
w-0.202
 you-0.196
prise-0.196
oh-0.187
Token and
Token ID290
Feature activation+2.69e-01

Pos logit contributions
elt+1.083
ashed+0.933
oured+0.918
itted+0.891
attered+0.890
Neg logit contributions
 you-0.905
 happen-0.825
ggy-0.773
gh-0.746
 us-0.700
Token fl
Token ID781
Feature activation+4.24e-02

Pos logit contributions
elt+0.466
arted+0.446
ked+0.444
ashed+0.420
itted+0.417
Neg logit contributions
 you-0.582
 happen-0.516
prise-0.506
uch-0.500
 am-0.481
Tokenapped
Token ID6320
Feature activation+3.38e-01

Pos logit contributions
ked+0.035
elt+0.033
arted+0.032
 arms+0.031
 asleep+0.031
Neg logit contributions
prise-0.119
 you-0.119
uch-0.118
w-0.111
arest-0.108
Token its
Token ID663
Feature activation+9.57e-02

Pos logit contributions
elt+0.607
ked+0.552
arted+0.533
ashed+0.515
ed+0.494
Neg logit contributions
 you-0.755
 happen-0.659
prise-0.644
 ourselves-0.605
 am-0.592
Token wings
Token ID12098
Feature activation+2.70e-01

Pos logit contributions
elt+0.123
arted+0.115
ked+0.105
ashed+0.101
 asleep+0.099
Neg logit contributions
 you-0.242
uch-0.225
prise-0.217
 happen-0.214
w-0.213
Token all
Token ID477
Feature activation+1.28e-01

Pos logit contributions
 you+0.139
prise+0.127
uch+0.123
 happen+0.121
 am+0.117
Neg logit contributions
elt-0.118
ked-0.108
arted-0.104
 eyes-0.104
ed-0.102
Token qu
Token ID627
Feature activation+6.38e-02

Pos logit contributions
elt+0.194
ked+0.191
 eyes+0.179
arted+0.173
 arms+0.169
Neg logit contributions
 you-0.285
prise-0.267
uch-0.264
 happen-0.261
 am-0.253
Tokenacked
Token ID6021
Feature activation+2.27e-01

Pos logit contributions
ked+0.092
elt+0.088
 asleep+0.082
 arms+0.082
 eyes+0.082
Neg logit contributions
uch-0.145
 you-0.145
prise-0.142
w-0.131
 happen-0.129
Token and
Token ID290
Feature activation+2.75e-01

Pos logit contributions
elt+0.451
arted+0.408
 shrugged+0.374
ked+0.369
sed+0.368
Neg logit contributions
 you-0.435
 happen-0.360
 ourselves-0.350
prise-0.344
ggy-0.324
Token hon
Token ID3032
Feature activation+7.14e-02

Pos logit contributions
elt+0.463
ked+0.441
arted+0.425
 eyes+0.401
ed+0.397
Neg logit contributions
 you-0.605
 happen-0.540
prise-0.527
uch-0.527
 am-0.507
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 asleep+0.035
elt+0.030
 eyes+0.029
 arms+0.028
 wooden+0.028
Neg logit contributions
uch-0.216
 you-0.213
prise-0.208
w-0.208
 ourselves-0.198
Token with
Token ID351
Feature activation+1.92e-02

Pos logit contributions
elt+1.025
arted+0.885
ked+0.874
 shrugged+0.865
ashed+0.861
Neg logit contributions
 you-0.971
 happen-0.884
 ourselves-0.817
ggy-0.749
 am-0.746
Token joy
Token ID8716
Feature activation+2.07e-02

Pos logit contributions
ked+0.032
elt+0.031
arted+0.030
ed+0.029
 eyes+0.029
Neg logit contributions
 you-0.041
uch-0.040
prise-0.040
 happen-0.037
 achieve-0.035
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
ked+0.049
elt+0.049
arted+0.048
ed+0.046
 arms+0.046
Neg logit contributions
 you-0.028
prise-0.026
uch-0.026
 happen-0.024
w-0.021
Token The
Token ID383
Feature activation+2.50e-01

Pos logit contributions
 you+0.356
n+0.297
 am+0.289
uch+0.284
 ourselves+0.279
Neg logit contributions
ked-0.273
elt-0.254
 asleep-0.245
 shrugged-0.240
arted-0.237
Token bunny
Token ID44915
Feature activation+1.92e-01

Pos logit contributions
ked+0.387
elt+0.377
arted+0.364
 eyes+0.354
 arms+0.353
Neg logit contributions
 you-0.553
prise-0.550
uch-0.546
 happen-0.511
 achieve-0.496
Token.
Token ID13
Feature activation-1.82e-01

Pos logit contributions
ked+0.731
elt+0.725
arted+0.701
ashed+0.682
ed+0.679
Neg logit contributions
 you-0.486
uch-0.435
prise-0.429
 happen-0.414
 am-0.375
Token Tom
Token ID4186
Feature activation+5.67e-02

Pos logit contributions
 you+0.486
prise+0.467
uch+0.464
 happen+0.443
 achieve+0.428
Neg logit contributions
ked-0.209
elt-0.202
arted-0.191
ed-0.183
ashed-0.176
Token and
Token ID290
Feature activation+2.64e-01

Pos logit contributions
arted+0.089
elt+0.085
ked+0.079
attered+0.077
pered+0.075
Neg logit contributions
 you-0.120
 am-0.107
uch-0.106
ggy-0.104
 else-0.104
Token Lily
Token ID20037
Feature activation+6.71e-02

Pos logit contributions
elt+0.555
ked+0.534
arted+0.522
ed+0.509
itted+0.497
Neg logit contributions
 you-0.496
 happen-0.397
prise-0.388
 am-0.381
uch-0.362
Token stro
Token ID9660
Feature activation+2.54e-01

Pos logit contributions
elt+0.103
arted+0.100
ked+0.095
 asleep+0.092
 arms+0.089
Neg logit contributions
 you-0.144
uch-0.136
prise-0.134
 am-0.132
 happen-0.130
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 wooden+0.114
 asleep+0.110
elt+0.076
 puzzled+0.076
 confused+0.076
Neg logit contributions
 you-0.785
uch-0.772
w-0.748
 ourselves-0.732
prise-0.712
Token its
Token ID663
Feature activation+1.02e-01

Pos logit contributions
elt+1.042
arted+0.957
oured+0.933
ashed+0.914
 asleep+0.881
Neg logit contributions
 you-0.911
 happen-0.815
 ourselves-0.756
ggy-0.737
 am-0.725
Token fur
Token ID9230
Feature activation+3.02e-01

Pos logit contributions
arted+0.138
elt+0.134
ashed+0.117
oured+0.111
 asleep+0.111
Neg logit contributions
 you-0.251
uch-0.237
 happen-0.237
ggy-0.229
 am-0.228
Token and
Token ID290
Feature activation+2.65e-01

Pos logit contributions
arted+0.733
elt+0.730
ashed+0.651
joy+0.649
 Curious+0.640
Neg logit contributions
 you-0.378
 happen-0.340
uch-0.323
ggy-0.289
 am-0.282
Token gave
Token ID2921
Feature activation+1.02e-01

Pos logit contributions
arted+0.497
elt+0.493
itted+0.443
attered+0.434
pered+0.423
Neg logit contributions
 you-0.504
 happen-0.470
 am-0.439
ggy-0.419
uch-0.398
Token it
Token ID340
Feature activation-1.41e-01

Pos logit contributions
ked+0.196
elt+0.191
arted+0.184
ed+0.181
 eyes+0.177
Neg logit contributions
 you-0.190
prise-0.185
uch-0.184
 happen-0.171
 achieve-0.162
Token After
Token ID2293
Feature activation+2.21e-01

Pos logit contributions
 you+0.326
prise+0.275
uch+0.273
n+0.262
 achieve+0.262
Neg logit contributions
ked-0.319
elt-0.294
arted-0.283
ashed-0.283
ed-0.278
Token he
Token ID339
Feature activation+4.64e-02

Pos logit contributions
ked+0.392
elt+0.383
arted+0.370
ed+0.356
ashed+0.353
Neg logit contributions
 you-0.459
prise-0.434
uch-0.426
 happen-0.408
 achieve-0.388
Token finished
Token ID5201
Feature activation-3.79e-02

Pos logit contributions
ked+0.081
elt+0.079
arted+0.076
ed+0.074
 eyes+0.072
Neg logit contributions
 you-0.095
prise-0.092
uch-0.092
 happen-0.086
 achieve-0.081
Token he
Token ID339
Feature activation+4.66e-02

Pos logit contributions
 you+0.069
 happen+0.062
 achieve+0.060
prise+0.058
uch+0.057
Neg logit contributions
ked-0.080
elt-0.077
ashed-0.075
arted-0.075
ed-0.072
Token stro
Token ID9660
Feature activation+2.50e-01

Pos logit contributions
ked+0.076
elt+0.074
arted+0.071
ed+0.068
 eyes+0.067
Neg logit contributions
 you-0.102
uch-0.098
prise-0.098
 happen-0.093
 achieve-0.088
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 wooden+0.109
 asleep+0.106
elt+0.103
 arms+0.101
arted+0.090
Neg logit contributions
 you-0.769
uch-0.760
w-0.713
 ourselves-0.696
ggy-0.695
Token the
Token ID262
Feature activation+1.26e-02

Pos logit contributions
elt+1.061
ashed+0.924
ked+0.915
arted+0.899
itted+0.867
Neg logit contributions
 you-0.958
 happen-0.892
 ourselves-0.773
 achieve-0.737
gh-0.737
Token rabbit
Token ID22746
Feature activation+2.44e-01

Pos logit contributions
elt+0.017
ked+0.017
arted+0.016
ashed+0.015
ed+0.015
Neg logit contributions
 you-0.031
uch-0.029
prise-0.029
 happen-0.028
 am-0.027
Token's
Token ID338
Feature activation+1.52e-02

Pos logit contributions
elt+0.501
ked+0.486
arted+0.485
ashed+0.471
ed+0.438
Neg logit contributions
 you-0.455
 happen-0.391
uch-0.388
prise-0.368
n-0.360
Token head
Token ID1182
Feature activation+2.49e-01

Pos logit contributions
elt+0.021
arted+0.020
ked+0.020
ashed+0.020
ed+0.019
Neg logit contributions
 you-0.037
 happen-0.033
uch-0.033
prise-0.032
 am-0.031
Token and
Token ID290
Feature activation+2.80e-01

Pos logit contributions
arted+0.411
elt+0.403
ked+0.386
ashed+0.381
 eyes+0.361
Neg logit contributions
 you-0.524
uch-0.478
 happen-0.460
prise-0.434
 am-0.424
Token car
Token ID1097
Feature activation+1.22e-01

Pos logit contributions
ked+0.343
elt+0.343
arted+0.323
ed+0.307
ashed+0.294
Neg logit contributions
 you-0.608
prise-0.579
uch-0.576
 happen-0.551
 am-0.530
Token hon
Token ID3032
Feature activation+7.24e-02

Pos logit contributions
elt+0.250
arted+0.230
ked+0.217
 asleep+0.213
joy+0.210
Neg logit contributions
 you-0.225
uch-0.217
 happen-0.201
ggy-0.194
n-0.190
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
 asleep+0.048
 wooden+0.038
 floppy+0.037
 arms+0.035
elt+0.035
Neg logit contributions
uch-0.219
w-0.212
 you-0.206
prise-0.195
oh-0.192
Token and
Token ID290
Feature activation+2.66e-01

Pos logit contributions
elt+0.999
oured+0.872
ashed+0.831
arted+0.803
itted+0.791
Neg logit contributions
 you-1.017
 happen-0.906
ggy-0.871
gh-0.862
 us-0.807
Token bra
Token ID8290
Feature activation+6.50e-02

Pos logit contributions
elt+0.473
arted+0.444
ked+0.434
ashed+0.427
itted+0.420
Neg logit contributions
 you-0.564
 happen-0.510
uch-0.499
prise-0.494
 am-0.469
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
ked+0.058
elt+0.052
arted+0.047
ed+0.047
ashed+0.043
Neg logit contributions
 you-0.194
prise-0.188
uch-0.187
 happen-0.180
 achieve-0.175
Token,
Token ID11
Feature activation-1.39e-02

Pos logit contributions
elt+1.078
ashed+0.957
arted+0.929
oured+0.910
ked+0.908
Neg logit contributions
 you-0.939
 happen-0.829
ggy-0.764
gh-0.742
 ourselves-0.728
Token but
Token ID475
Feature activation+1.91e-01

Pos logit contributions
 you+0.031
 happen+0.028
 achieve+0.025
 am+0.025
uch+0.025
Neg logit contributions
elt-0.024
ashed-0.023
arted-0.022
ked-0.022
ed-0.022
Token it
Token ID340
Feature activation-1.40e-01

Pos logit contributions
elt+0.391
ked+0.383
arted+0.373
ashed+0.361
ed+0.346
Neg logit contributions
 you-0.371
uch-0.320
 happen-0.316
prise-0.315
 am-0.295
Token was
Token ID373
Feature activation-4.60e-02

Pos logit contributions
 you+0.244
uch+0.244
prise+0.221
 happen+0.218
 am+0.210
Neg logit contributions
elt-0.289
ked-0.276
arted-0.274
 eyes-0.259
 asleep-0.258
Token too
Token ID1165
Feature activation+6.95e-02

Pos logit contributions
 you+0.090
uch+0.085
prise+0.084
 happen+0.081
 am+0.075
Neg logit contributions
elt-0.086
ked-0.085
ed-0.080
arted-0.080
ashed-0.077
Token goose
Token ID37246
Feature activation+1.01e-01

Pos logit contributions
 you+0.164
uch+0.151
 happen+0.148
prise+0.148
 am+0.143
Neg logit contributions
ked-0.125
elt-0.121
arted-0.119
ed-0.113
 arms-0.110
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
ked+0.207
elt+0.196
arted+0.189
ed+0.188
 confused+0.184
Neg logit contributions
prise-0.182
uch-0.181
 you-0.173
 happen-0.168
arest-0.161
Token The
Token ID383
Feature activation+2.54e-01

Pos logit contributions
 you+0.381
One+0.320
 am+0.320
uch+0.317
n+0.316
Neg logit contributions
ked-0.263
arted-0.240
ed-0.240
ashed-0.226
elt-0.226
Token goose
Token ID37246
Feature activation+1.02e-01

Pos logit contributions
ked+0.344
elt+0.336
arted+0.315
 eyes+0.309
ed+0.309
Neg logit contributions
 you-0.611
prise-0.609
uch-0.595
 happen-0.564
 achieve-0.553
Token hon
Token ID3032
Feature activation+7.18e-02

Pos logit contributions
elt+0.196
ked+0.194
arted+0.187
 asleep+0.183
 eyes+0.178
Neg logit contributions
 you-0.194
uch-0.185
prise-0.169
 happen-0.162
w-0.161
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
 asleep+0.054
 wooden+0.044
joy+0.038
 arms+0.037
elt+0.036
Neg logit contributions
uch-0.211
w-0.209
 you-0.191
oh-0.179
prise-0.177
Token his
Token ID465
Feature activation+1.60e-01

Pos logit contributions
elt+1.038
oured+0.931
ashed+0.861
uster+0.857
itted+0.854
Neg logit contributions
 you-0.972
 happen-0.833
 us-0.768
w-0.744
ggy-0.736
Token horn
Token ID12718
Feature activation+2.14e-01

Pos logit contributions
arted+0.206
elt+0.204
ashed+0.187
 asleep+0.186
ked+0.175
Neg logit contributions
 you-0.416
uch-0.395
 happen-0.371
ggy-0.365
 ourselves-0.364
Token and
Token ID290
Feature activation+2.77e-01

Pos logit contributions
elt+0.375
joy+0.349
arted+0.344
ashed+0.315
lee+0.313
Neg logit contributions
 you-0.413
uch-0.398
 happen-0.386
w-0.367
ggy-0.351
Token scared
Token ID12008
Feature activation+2.30e-01

Pos logit contributions
elt+0.482
arted+0.458
ked+0.457
ed+0.434
itted+0.432
Neg logit contributions
 you-0.605
uch-0.538
 happen-0.523
prise-0.509
 am-0.486
Token the
Token ID262
Feature activation+1.00e-02

Pos logit contributions
elt+0.449
ked+0.446
ashed+0.422
 puzzled+0.420
arted+0.420
Neg logit contributions
 you-0.455
uch-0.359
 happen-0.358
prise-0.350
w-0.334
Token coming
Token ID2406
Feature activation+2.38e-02

Pos logit contributions
ked+0.208
arted+0.190
elt+0.187
ed+0.185
 down+0.185
Neg logit contributions
prise-0.253
uch-0.243
 you-0.238
arest-0.217
w-0.216
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
ked+0.027
elt+0.026
arted+0.025
ed+0.024
 down+0.023
Neg logit contributions
prise-0.063
uch-0.063
 you-0.062
 happen-0.059
 achieve-0.058
Token The
Token ID383
Feature activation+2.48e-01

Pos logit contributions
 you+0.515
uch+0.480
prise+0.472
 happen+0.456
 am+0.456
Neg logit contributions
ked-0.190
elt-0.173
arted-0.172
ashed-0.163
ed-0.159
Token car
Token ID1097
Feature activation+1.20e-01

Pos logit contributions
ked+0.313
elt+0.304
arted+0.287
ed+0.276
ashed+0.265
Neg logit contributions
 you-0.633
prise-0.614
uch-0.613
 happen-0.582
 achieve-0.557
Token hon
Token ID3032
Feature activation+7.25e-02

Pos logit contributions
elt+0.236
arted+0.213
ked+0.200
 asleep+0.199
itted+0.195
Neg logit contributions
 you-0.231
uch-0.222
 happen-0.207
ggy-0.201
 am-0.196
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
 asleep+0.036
elt+0.031
 wooden+0.026
 floppy+0.026
 arms+0.025
Neg logit contributions
uch-0.232
w-0.225
 you-0.224
prise-0.212
ggy-0.204
Token and
Token ID290
Feature activation+2.65e-01

Pos logit contributions
elt+0.939
oured+0.790
ashed+0.788
arted+0.766
ked+0.751
Neg logit contributions
 you-1.097
 happen-0.961
ggy-0.890
uch-0.873
gh-0.871
Token bra
Token ID8290
Feature activation+6.67e-02

Pos logit contributions
elt+0.475
arted+0.442
ashed+0.429
ked+0.429
itted+0.429
Neg logit contributions
 you-0.564
 happen-0.500
uch-0.491
prise-0.475
 am-0.459
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
ked+0.052
ed+0.039
elt+0.033
ashed+0.031
arted+0.030
Neg logit contributions
 you-0.222
prise-0.215
uch-0.209
 happen-0.207
 achieve-0.203
Token.
Token ID13
Feature activation-1.82e-01

Pos logit contributions
elt+1.085
ked+1.001
arted+0.979
ashed+0.975
 shrugged+0.937
Neg logit contributions
 you-0.899
 happen-0.779
uch-0.760
prise-0.712
 ourselves-0.698
Token Spot
Token ID15899
Feature activation+9.11e-02

Pos logit contributions
 you+0.429
uch+0.390
prise+0.375
 happen+0.368
 am+0.367
Neg logit contributions
ked-0.273
elt-0.263
arted-0.256
ashed-0.248
ed-0.244
Token sw
Token ID1509
Feature activation+1.27e-01

Pos logit contributions
 you+0.012
 achieve+0.010
n+0.009
 happen+0.009
 course+0.009
Neg logit contributions
elt-0.010
 eyes-0.010
itted-0.009
ashed-0.009
ked-0.009
Tokenam
Token ID321
Feature activation+1.53e-01

Pos logit contributions
elt+0.214
 asleep+0.214
ked+0.203
 confused+0.203
 shrugged+0.198
Neg logit contributions
 you-0.248
uch-0.243
 achieve-0.222
 ourselves-0.222
prise-0.219
Token rivers
Token ID18180
Feature activation+2.03e-01

Pos logit contributions
elt+0.255
ked+0.238
ashed+0.220
arted+0.219
 shrugged+0.214
Neg logit contributions
 you-0.348
 happen-0.308
uch-0.296
 achieve-0.296
prise-0.293
Token and
Token ID290
Feature activation+2.74e-01

Pos logit contributions
elt+0.340
ked+0.312
ashed+0.302
arted+0.300
 shrugged+0.299
Neg logit contributions
 you-0.439
 happen-0.404
 achieve-0.379
uch-0.378
n-0.364
Token trek
Token ID30784
Feature activation+9.89e-02

Pos logit contributions
elt+0.427
ked+0.416
arted+0.388
 eyes+0.385
itted+0.382
Neg logit contributions
 you-0.643
 happen-0.555
prise-0.554
uch-0.545
 achieve-0.544
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
elt+0.094
 eyes+0.084
 floppy+0.080
 shrugged+0.079
 confused+0.079
Neg logit contributions
 you-0.269
uch-0.255
 happen-0.247
n-0.242
gh-0.240
Token through
Token ID832
Feature activation+2.79e-01

Pos logit contributions
elt+0.928
ashed+0.809
ked+0.803
arted+0.767
 shrugged+0.767
Neg logit contributions
 you-1.071
 happen-1.018
 ourselves-0.904
 achieve-0.890
 am-0.850
Token the
Token ID262
Feature activation+1.30e-02

Pos logit contributions
elt+0.525
ked+0.524
ashed+0.489
arted+0.483
ed+0.473
Neg logit contributions
 you-0.556
prise-0.499
 happen-0.491
uch-0.475
 achieve-0.460
Token woods
Token ID16479
Feature activation+1.65e-01

Pos logit contributions
ked+0.019
elt+0.019
arted+0.017
ashed+0.017
ed+0.017
Neg logit contributions
 you-0.032
uch-0.029
prise-0.029
 happen-0.028
 achieve-0.028
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
ked+0.402
elt+0.401
arted+0.384
ashed+0.377
ed+0.372
Neg logit contributions
 you-0.224
prise-0.198
uch-0.197
 happen-0.191
 achieve-0.177
Token But
Token ID887
Feature activation+7.93e-02

Pos logit contributions
 you+0.416
 achieve+0.366
n+0.366
 am+0.365
One+0.365
Neg logit contributions
ked-0.227
elt-0.196
ashed-0.187
 shrugged-0.186
arted-0.183
Token driving
Token ID5059
Feature activation+1.74e-01

Pos logit contributions
ked+0.376
elt+0.370
arted+0.357
ed+0.349
 eyes+0.342
Neg logit contributions
 you-0.309
prise-0.297
uch-0.296
 happen-0.273
 achieve-0.256
Token by
Token ID416
Feature activation+2.50e-02

Pos logit contributions
elt+0.242
ked+0.228
ashed+0.221
arted+0.209
 shrugged+0.207
Neg logit contributions
 you-0.433
uch-0.384
 happen-0.378
prise-0.376
w-0.372
Token and
Token ID290
Feature activation+2.73e-01

Pos logit contributions
ked+0.044
elt+0.043
arted+0.041
ed+0.041
 arms+0.040
Neg logit contributions
 you-0.050
prise-0.049
uch-0.049
 happen-0.045
w-0.043
Token it
Token ID340
Feature activation-1.43e-01

Pos logit contributions
ked+0.534
elt+0.524
arted+0.508
ashed+0.501
itted+0.484
Neg logit contributions
 you-0.536
prise-0.457
 happen-0.455
uch-0.448
 am-0.413
Token hon
Token ID3032
Feature activation+7.17e-02

Pos logit contributions
 you+0.273
uch+0.259
 happen+0.250
prise+0.239
ggy+0.230
Neg logit contributions
elt-0.272
ked-0.261
arted-0.252
 eyes-0.237
itted-0.235
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
elt+0.033
 arms+0.031
 asleep+0.030
 floppy+0.028
 eyes+0.028
Neg logit contributions
uch-0.222
 you-0.217
w-0.209
prise-0.208
 happen-0.201
Token at
Token ID379
Feature activation+2.08e-01

Pos logit contributions
elt+1.061
ked+0.953
arted+0.948
ashed+0.941
 shrugged+0.888
Neg logit contributions
 you-0.914
 happen-0.831
uch-0.751
gh-0.745
ggy-0.739
Token him
Token ID683
Feature activation-6.69e-02

Pos logit contributions
ked+0.374
elt+0.366
arted+0.351
ed+0.342
 eyes+0.334
Neg logit contributions
 you-0.416
prise-0.402
uch-0.401
 happen-0.375
 achieve-0.355
Token.
Token ID13
Feature activation-1.71e-01

Pos logit contributions
 you+0.097
prise+0.092
uch+0.092
 happen+0.084
 achieve+0.077
Neg logit contributions
ked-0.156
elt-0.154
arted-0.149
ed-0.146
ashed-0.144
Token Johnny
Token ID15470
Feature activation+1.34e-01

Pos logit contributions
 you+0.427
n+0.347
 achieve+0.344
uch+0.342
prise+0.341
Neg logit contributions
ked-0.248
ashed-0.224
elt-0.210
arted-0.209
ed-0.207
Token thought
Token ID1807
Feature activation+1.14e-01

Pos logit contributions
elt+0.268
ked+0.258
arted+0.252
 asleep+0.242
ashed+0.241
Neg logit contributions
 you-0.239
uch-0.230
n-0.206
 happen-0.202
ggy-0.200
Token car
Token ID1097
Feature activation+1.22e-01

Pos logit contributions
 you+0.634
prise+0.616
uch+0.615
 happen+0.582
 achieve+0.557
Neg logit contributions
ked-0.365
elt-0.356
arted-0.337
ed-0.326
 eyes-0.317
Token hon
Token ID3032
Feature activation+7.22e-02

Pos logit contributions
elt+0.235
arted+0.217
 floppy+0.200
itted+0.196
ked+0.195
Neg logit contributions
 you-0.230
uch-0.223
ggy-0.210
 happen-0.203
n-0.202
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
 asleep+0.044
 floppy+0.037
 wooden+0.035
elt+0.032
 arms+0.031
Neg logit contributions
uch-0.216
w-0.210
 you-0.204
prise-0.199
oh-0.192
Token and
Token ID290
Feature activation+2.65e-01

Pos logit contributions
elt+1.063
oured+0.906
arted+0.893
ked+0.888
ashed+0.887
Neg logit contributions
 you-0.963
 happen-0.853
ggy-0.784
 ourselves-0.760
gh-0.758
Token bra
Token ID8290
Feature activation+6.76e-02

Pos logit contributions
elt+0.470
arted+0.444
ked+0.427
ashed+0.424
itted+0.423
Neg logit contributions
 you-0.564
 happen-0.498
uch-0.493
prise-0.492
 am-0.463
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
ked+0.069
elt+0.058
ed+0.058
arted+0.053
ashed+0.052
Neg logit contributions
 you-0.199
prise-0.192
uch-0.190
 happen-0.184
 achieve-0.180
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
elt+1.178
ked+1.089
arted+1.068
ashed+1.055
 shrugged+1.023
Neg logit contributions
 you-0.811
 happen-0.702
uch-0.652
prise-0.635
 ourselves-0.622
Token The
Token ID383
Feature activation+2.48e-01

Pos logit contributions
 you+0.411
 am+0.348
 happen+0.334
 achieve+0.325
't+0.320
Neg logit contributions
ked-0.304
elt-0.303
arted-0.299
ashed-0.277
oured-0.256
Token ambulance
Token ID22536
Feature activation+1.15e-01

Pos logit contributions
ked+0.346
elt+0.339
arted+0.321
ed+0.309
ashed+0.298
Neg logit contributions
 you-0.598
prise-0.577
uch-0.574
 happen-0.548
 am-0.521
Token s
Token ID264
Feature activation+1.86e-01

Pos logit contributions
elt+0.206
arted+0.198
 floppy+0.181
ked+0.180
itted+0.175
Neg logit contributions
 you-0.228
uch-0.220
 happen-0.207
ggy-0.201
 am-0.200
Tokeniren
Token ID24080
Feature activation+3.75e-02

Pos logit contributions
ked+0.272
elt+0.272
ed+0.261
arted+0.251
ashed+0.232
Neg logit contributions
 you-0.436
prise-0.420
 happen-0.415
uch-0.414
 achieve-0.387
Token coming
Token ID2406
Feature activation+2.27e-02

Pos logit contributions
 you+0.091
uch+0.083
 happen+0.082
prise+0.082
 am+0.074
Neg logit contributions
elt-0.090
ked-0.087
ed-0.084
arted-0.082
ashed-0.081
Token.
Token ID13
Feature activation-1.79e-01

Pos logit contributions
ked+0.030
elt+0.028
arted+0.027
ed+0.026
 eyes+0.025
Neg logit contributions
 you-0.057
prise-0.056
uch-0.056
 happen-0.052
 achieve-0.051
Token The
Token ID383
Feature activation+2.46e-01

Pos logit contributions
 you+0.507
prise+0.473
uch+0.467
 am+0.450
 happen+0.448
Neg logit contributions
ked-0.191
arted-0.171
elt-0.170
ashed-0.162
ed-0.158
Token car
Token ID1097
Feature activation+1.22e-01

Pos logit contributions
ked+0.343
elt+0.343
arted+0.323
ed+0.307
ashed+0.294
Neg logit contributions
 you-0.608
prise-0.579
uch-0.576
 happen-0.551
 am-0.530
Token hon
Token ID3032
Feature activation+7.24e-02

Pos logit contributions
elt+0.250
arted+0.230
ked+0.217
 asleep+0.213
joy+0.210
Neg logit contributions
 you-0.225
uch-0.217
 happen-0.201
ggy-0.194
n-0.190
Tokenked
Token ID9091
Feature activation+5.03e-01

Pos logit contributions
 asleep+0.048
 wooden+0.038
 floppy+0.037
 arms+0.035
elt+0.035
Neg logit contributions
uch-0.219
w-0.212
 you-0.206
prise-0.195
oh-0.192
Token and
Token ID290
Feature activation+2.66e-01

Pos logit contributions
elt+0.999
oured+0.872
ashed+0.831
arted+0.803
itted+0.791
Neg logit contributions
 you-1.017
 happen-0.906
ggy-0.871
gh-0.862
 us-0.807
Token bra
Token ID8290
Feature activation+6.50e-02

Pos logit contributions
elt+0.473
arted+0.444
ked+0.434
ashed+0.427
itted+0.420
Neg logit contributions
 you-0.564
 happen-0.510
uch-0.499
prise-0.494
 am-0.469
Tokenked
Token ID9091
Feature activation+5.04e-01

Pos logit contributions
ked+0.058
elt+0.052
arted+0.047
ed+0.047
ashed+0.043
Neg logit contributions
 you-0.194
prise-0.188
uch-0.187
 happen-0.180
 achieve-0.175
Token,
Token ID11
Feature activation-1.39e-02

Pos logit contributions
elt+1.078
ashed+0.957
arted+0.929
oured+0.910
ked+0.908
Neg logit contributions
 you-0.939
 happen-0.829
ggy-0.764
gh-0.742
 ourselves-0.728
Token but
Token ID475
Feature activation+1.91e-01

Pos logit contributions
 you+0.031
 happen+0.028
 achieve+0.025
 am+0.025
uch+0.025
Neg logit contributions
elt-0.024
ashed-0.023
arted-0.022
ked-0.022
ed-0.022
Token we
Token ID356
Feature activation-4.46e-01

Pos logit contributions
ked+0.012
elt+0.012
arted+0.012
ed+0.011
ashed+0.011
Neg logit contributions
 you-0.016
uch-0.015
prise-0.015
 happen-0.015
 achieve-0.014
Token will
Token ID481
Feature activation-4.19e-01

Pos logit contributions
prise+0.706
uch+0.702
 you+0.635
arest+0.624
vern+0.621
Neg logit contributions
ked-0.891
ed-0.883
elt-0.881
 confused-0.871
ashed-0.868
Token go
Token ID467
Feature activation-2.02e-01

Pos logit contributions
uch+0.783
prise+0.770
w+0.750
arest+0.692
vern+0.627
Neg logit contributions
 eyes-0.750
 asleep-0.740
 confused-0.736
 down-0.709
 arms-0.703
Token home
Token ID1363
Feature activation+6.17e-02

Pos logit contributions
uch+0.486
prise+0.484
 you+0.466
 happen+0.453
w+0.442
Neg logit contributions
ked-0.254
elt-0.250
 down-0.249
 asleep-0.248
ed-0.241
Token and
Token ID290
Feature activation+2.45e-01

Pos logit contributions
 asleep+0.134
elt+0.132
ed+0.132
ked+0.131
 arms+0.129
Neg logit contributions
uch-0.091
prise-0.089
 you-0.084
 happen-0.078
w-0.077
Token you
Token ID345
Feature activation-6.13e-01

Pos logit contributions
ked+0.565
elt+0.558
arted+0.535
 eyes+0.534
ed+0.533
Neg logit contributions
uch-0.336
prise-0.331
 you-0.327
 happen-0.292
w-0.281
Token will
Token ID481
Feature activation-3.87e-01

Pos logit contributions
prise+0.781
uch+0.747
 you+0.747
 happen+0.701
gh+0.654
Neg logit contributions
ked-1.459
ed-1.426
elt-1.415
 confused-1.395
 asleep-1.384
Token get
Token ID651
Feature activation-1.97e-01

Pos logit contributions
prise+0.741
uch+0.732
w+0.719
arest+0.678
 you+0.591
Neg logit contributions
 asleep-0.694
 eyes-0.639
 confused-0.635
 down-0.630
 He-0.615
Token no
Token ID645
Feature activation-1.34e-01

Pos logit contributions
uch+0.381
prise+0.374
 you+0.359
 happen+0.347
 achieve+0.344
Neg logit contributions
ked-0.347
elt-0.346
ed-0.330
 asleep-0.325
 eyes-0.324
Token toy
Token ID13373
Feature activation+1.43e-01

Pos logit contributions
uch+0.251
prise+0.247
 you+0.235
 achieve+0.223
arest+0.218
Neg logit contributions
 asleep-0.242
 eyes-0.241
 arms-0.238
elt-0.233
ked-0.230
Token at
Token ID379
Feature activation+2.00e-01

Pos logit contributions
ked+0.282
elt+0.276
ed+0.271
 asleep+0.265
arted+0.260
Neg logit contributions
uch-0.248
prise-0.245
 you-0.233
 achieve-0.223
 happen-0.220
TokenOK
Token ID11380
Feature activation-3.32e-01

Pos logit contributions
 you+0.442
prise+0.404
uch+0.398
 am+0.393
 happen+0.384
Neg logit contributions
ked-0.225
arted-0.193
elt-0.187
ashed-0.184
ed-0.184
Token,
Token ID11
Feature activation-6.94e-02

Pos logit contributions
uch+0.713
prise+0.698
w+0.612
arest+0.604
 happen+0.593
Neg logit contributions
 down-0.539
ked-0.533
 arms-0.524
 eyes-0.523
ed-0.513
Token but
Token ID475
Feature activation+1.45e-01

Pos logit contributions
uch+0.140
prise+0.135
 you+0.132
 happen+0.124
w+0.123
Neg logit contributions
ked-0.119
elt-0.117
arted-0.111
 eyes-0.111
 arms-0.110
Token only
Token ID691
Feature activation-3.52e-02

Pos logit contributions
 eyes+0.308
 arms+0.304
ked+0.304
 down+0.303
 confused+0.297
Neg logit contributions
prise-0.221
uch-0.209
arest-0.198
vern-0.193
gh-0.174
Token if
Token ID611
Feature activation-1.51e-01

Pos logit contributions
prise+0.071
uch+0.071
 you+0.071
 happen+0.065
 achieve+0.063
Neg logit contributions
ked-0.059
elt-0.058
arted-0.055
 arms-0.054
 eyes-0.054
Token you
Token ID345
Feature activation-6.11e-01

Pos logit contributions
prise+0.206
uch+0.202
arest+0.169
 achieve+0.166
w+0.158
Neg logit contributions
 eyes-0.352
 arms-0.351
ked-0.341
elt-0.340
 asleep-0.332
Token let
Token ID1309
Feature activation-2.18e-01

Pos logit contributions
prise+0.923
 you+0.852
uch+0.839
 happen+0.767
gh+0.738
Neg logit contributions
ked-1.386
elt-1.319
ed-1.297
 confused-1.276
 shrugged-1.272
Token me
Token ID502
Feature activation-1.89e-01

Pos logit contributions
prise+0.415
uch+0.378
arest+0.360
vern+0.342
 achieve+0.339
Neg logit contributions
 down-0.402
 eyes-0.393
ked-0.386
 arms-0.380
elt-0.378
Token play
Token ID711
Feature activation-1.80e-01

Pos logit contributions
prise+0.307
uch+0.298
 you+0.286
 happen+0.272
w+0.267
Neg logit contributions
elt-0.383
ked-0.381
 down-0.365
ed-0.361
 eyes-0.359
Token with
Token ID351
Feature activation+9.27e-03

Pos logit contributions
uch+0.391
prise+0.390
 achieve+0.350
 happen+0.350
arest+0.347
Neg logit contributions
 down-0.265
ed-0.264
ked-0.258
 asleep-0.246
elt-0.244
Token your
Token ID534
Feature activation-2.92e-01

Pos logit contributions
 eyes+0.020
 arms+0.020
ked+0.019
 down+0.019
elt+0.019
Neg logit contributions
prise-0.014
uch-0.014
 achieve-0.012
arest-0.012
 happen-0.012
Tokenitten
Token ID2621
Feature activation-1.16e-01

Pos logit contributions
 you+0.831
prise+0.790
uch+0.782
 happen+0.746
 am+0.709
Neg logit contributions
ked-0.608
elt-0.588
arted-0.566
ed-0.547
ashed-0.533
Token.
Token ID13
Feature activation-2.08e-01

Pos logit contributions
 you+0.237
prise+0.229
uch+0.229
 happen+0.214
 achieve+0.203
Neg logit contributions
ked-0.199
elt-0.195
arted-0.187
ed-0.182
 eyes-0.178
Token It
Token ID632
Feature activation+2.02e-01

Pos logit contributions
 you+0.523
prise+0.491
uch+0.485
 happen+0.459
 am+0.449
Neg logit contributions
ked-0.277
elt-0.259
arted-0.250
ed-0.242
ashed-0.235
Token will
Token ID481
Feature activation-3.90e-01

Pos logit contributions
ked+0.377
elt+0.369
arted+0.357
ed+0.340
 eyes+0.336
Neg logit contributions
 you-0.394
uch-0.375
prise-0.369
 happen-0.352
 am-0.335
Token keep
Token ID1394
Feature activation-2.57e-01

Pos logit contributions
prise+0.675
uch+0.645
 you+0.565
w+0.551
arest+0.545
Neg logit contributions
ked-0.755
 arms-0.744
 eyes-0.740
 confused-0.737
 asleep-0.728
Token you
Token ID345
Feature activation-6.11e-01

Pos logit contributions
prise+0.419
 you+0.414
uch+0.412
 happen+0.377
 achieve+0.363
Neg logit contributions
ked-0.540
elt-0.530
arted-0.513
ed-0.505
 arms-0.501
Token warm
Token ID5814
Feature activation-1.91e-02

Pos logit contributions
 you+1.257
prise+1.249
uch+1.242
 happen+1.156
w+1.106
Neg logit contributions
ked-1.005
elt-0.968
 arms-0.933
ed-0.922
arted-0.917
Token."
Token ID526
Feature activation-3.47e-01

Pos logit contributions
 you+0.045
uch+0.043
prise+0.043
 happen+0.041
 am+0.039
Neg logit contributions
ked-0.028
elt-0.027
arted-0.026
ed-0.025
ashed-0.024
Token
Token ID198
Feature activation-1.57e-01

Pos logit contributions
 you+0.665
prise+0.630
uch+0.623
 happen+0.581
 achieve+0.553
Neg logit contributions
ked-0.659
elt-0.640
arted-0.617
ed-0.603
ashed-0.589
Token
Token ID198
Feature activation-1.56e-01

Pos logit contributions
uch+0.406
 happen+0.379
prise+0.361
 belong+0.335
 you+0.333
Neg logit contributions
 He-0.216
elt-0.191
arted-0.190
 Curious-0.183
 arms-0.182
TokenTom
Token ID13787
Feature activation-3.33e-01

Pos logit contributions
 happen+0.295
uch+0.294
prise+0.240
 you+0.228
 belong+0.221
Neg logit contributions
 He-0.288
elt-0.283
arted-0.278
 Curious-0.274
ked-0.265
Token you
Token ID345
Feature activation-6.63e-01

Pos logit contributions
prise+0.188
 you+0.186
uch+0.185
 happen+0.171
w+0.165
Neg logit contributions
ked-0.134
elt-0.131
arted-0.124
ed-0.123
 arms-0.119
Token and
Token ID290
Feature activation+2.26e-01

Pos logit contributions
uch+1.091
prise+1.091
 you+1.001
 happen+0.941
arest+0.921
Neg logit contributions
ked-1.319
ed-1.306
elt-1.304
 confused-1.283
 eyes-1.273
Token I
Token ID314
Feature activation-2.76e-01

Pos logit contributions
ked+0.512
elt+0.506
 eyes+0.486
arted+0.486
ed+0.485
Neg logit contributions
uch-0.318
prise-0.315
 you-0.306
 happen-0.277
w-0.259
Token will
Token ID481
Feature activation-3.94e-01

Pos logit contributions
prise+0.397
uch+0.395
 you+0.390
 happen+0.355
 ourselves+0.341
Neg logit contributions
ked-0.597
elt-0.595
ed-0.593
 confused-0.592
ashed-0.582
Token make
Token ID787
Feature activation-2.50e-01

Pos logit contributions
prise+0.737
uch+0.713
w+0.654
arest+0.621
 you+0.563
Neg logit contributions
 eyes-0.696
 asleep-0.690
 confused-0.679
 arms-0.670
ked-0.661
Token you
Token ID345
Feature activation-6.11e-01

Pos logit contributions
uch+0.326
prise+0.314
 am+0.264
arest+0.254
w+0.253
Neg logit contributions
 eyes-0.597
ked-0.585
 arms-0.581
elt-0.579
ed-0.571
Token some
Token ID617
Feature activation+8.21e-02

Pos logit contributions
 you+1.369
prise+1.345
uch+1.342
 happen+1.251
w+1.206
Neg logit contributions
ked-0.913
elt-0.889
arted-0.841
ed-0.827
 eyes-0.813
Token juice
Token ID13135
Feature activation-2.56e-02

Pos logit contributions
 eyes+0.140
 arms+0.136
 asleep+0.136
elt+0.134
ked+0.132
Neg logit contributions
uch-0.163
prise-0.156
 you-0.146
w-0.140
n-0.135
Token myself
Token ID3589
Feature activation-3.28e-01

Pos logit contributions
prise+0.043
uch+0.042
 you+0.038
arest+0.036
 achieve+0.036
Neg logit contributions
ed-0.050
elt-0.050
 down-0.050
 asleep-0.050
ked-0.049
Token."
Token ID526
Feature activation-3.41e-01

Pos logit contributions
prise+0.505
uch+0.501
 you+0.479
w+0.429
 happen+0.422
Neg logit contributions
elt-0.690
ked-0.682
 asleep-0.681
ed-0.678
 down-0.677
Token Lily
Token ID20037
Feature activation+6.86e-02

Pos logit contributions
 you+0.648
prise+0.620
uch+0.614
 happen+0.573
 achieve+0.543
Neg logit contributions
ked-0.647
elt-0.632
arted-0.609
ed-0.595
 eyes-0.581
Token best
Token ID1266
Feature activation-1.34e-01

Pos logit contributions
ked+0.426
elt+0.417
arted+0.396
ed+0.387
 eyes+0.378
Neg logit contributions
 you-0.627
prise-0.613
uch-0.612
 happen-0.572
 achieve-0.550
Token to
Token ID284
Feature activation+1.20e-01

Pos logit contributions
uch+0.273
prise+0.265
 you+0.258
 happen+0.245
 achieve+0.241
Neg logit contributions
ked-0.222
elt-0.221
 arms-0.213
ed-0.213
 eyes-0.212
Token stay
Token ID2652
Feature activation-3.11e-01

Pos logit contributions
arted+0.225
 eyes+0.223
 arms+0.223
 down+0.222
ked+0.222
Neg logit contributions
uch-0.206
prise-0.196
arest-0.177
w-0.175
 you-0.164
Token strong
Token ID1913
Feature activation+5.35e-02

Pos logit contributions
 you+0.678
prise+0.670
uch+0.669
 happen+0.627
w+0.594
Neg logit contributions
ked-0.484
elt-0.469
arted-0.450
ed-0.445
 arms-0.435
Token and
Token ID290
Feature activation+2.40e-01

Pos logit contributions
ked+0.081
elt+0.079
arted+0.075
ed+0.072
ashed+0.071
Neg logit contributions
 you-0.123
prise-0.117
uch-0.117
 happen-0.111
 achieve-0.106
Token you
Token ID345
Feature activation-6.11e-01

Pos logit contributions
ked+0.419
elt+0.412
 confused+0.402
 arms+0.398
 down+0.397
Neg logit contributions
prise-0.463
uch-0.445
 you-0.431
 happen-0.402
w-0.394
Token can
Token ID460
Feature activation-1.91e-01

Pos logit contributions
prise+0.896
uch+0.817
 you+0.809
 happen+0.762
gh+0.711
Neg logit contributions
ked-1.381
ed-1.344
elt-1.339
 confused-1.322
 asleep-1.313
Token always
Token ID1464
Feature activation-1.20e-01

Pos logit contributions
prise+0.382
uch+0.326
w+0.325
arest+0.312
gh+0.285
Neg logit contributions
 down-0.326
 asleep-0.321
 He-0.308
 confused-0.307
 eyes-0.301
Token find
Token ID1064
Feature activation-1.38e-01

Pos logit contributions
prise+0.214
uch+0.205
w+0.188
arest+0.176
 you+0.174
Neg logit contributions
 down-0.225
 arms-0.214
 eyes-0.213
 confused-0.212
ked-0.210
Token a
Token ID257
Feature activation+5.22e-02

Pos logit contributions
uch+0.249
prise+0.241
 you+0.234
 happen+0.219
 achieve+0.215
Neg logit contributions
ked-0.262
elt-0.259
 eyes-0.252
arted-0.250
ed-0.249
Token way
Token ID835
Feature activation-2.51e-02

Pos logit contributions
elt+0.082
ked+0.082
 asleep+0.080
 arms+0.080
 eyes+0.079
Neg logit contributions
uch-0.107
 you-0.106
prise-0.105
 happen-0.098
w-0.096
Token
Token ID198
Feature activation-2.13e-01

Pos logit contributions
elt+0.544
arted+0.516
itted+0.468
ked+0.463
pered+0.438
Neg logit contributions
 you-0.594
 happen-0.506
prise-0.490
uch-0.475
ggy-0.458
Token"
Token ID1
Feature activation-4.15e-01

Pos logit contributions
 happen+0.457
uch+0.435
prise+0.371
 you+0.351
arest+0.343
Neg logit contributions
 He-0.365
elt-0.361
arted-0.350
 Curious-0.335
 arms-0.331
TokenYes
Token ID5297
Feature activation-2.12e-01

Pos logit contributions
uch+0.700
 happen+0.686
 you+0.683
prise+0.677
 achieve+0.631
Neg logit contributions
elt-0.858
ked-0.840
ed-0.786
arted-0.763
 shrugged-0.762
Token,
Token ID11
Feature activation-3.50e-02

Pos logit contributions
uch+0.500
prise+0.486
 achieve+0.453
 you+0.442
w+0.441
Neg logit contributions
 eyes-0.310
ked-0.296
 arms-0.275
elt-0.272
ed-0.269
Token thank
Token ID5875
Feature activation-2.03e-01

Pos logit contributions
 you+0.058
uch+0.057
prise+0.056
 happen+0.052
 achieve+0.049
Neg logit contributions
ked-0.074
elt-0.072
arted-0.070
ed-0.068
 eyes-0.068
Token you
Token ID345
Feature activation-6.10e-01

Pos logit contributions
uch+0.160
vern+0.125
arest+0.118
prise+0.109
gh+0.098
Neg logit contributions
 eyes-0.594
 down-0.585
elt-0.573
ked-0.572
 arms-0.567
Token,"
Token ID553
Feature activation-3.19e-01

Pos logit contributions
uch+1.254
 you+1.234
prise+1.225
 happen+1.152
 achieve+1.098
Neg logit contributions
ked-1.040
elt-1.010
arted-0.976
 eyes-0.971
ed-0.967
Token Max
Token ID5436
Feature activation+1.27e-01

Pos logit contributions
 you+0.644
prise+0.518
 happen+0.473
 am+0.462
 course+0.460
Neg logit contributions
ked-0.630
elt-0.623
arted-0.610
ashed-0.592
ed-0.567
Token said
Token ID531
Feature activation+1.38e-02

Pos logit contributions
ked+0.252
elt+0.250
arted+0.238
attered+0.220
itted+0.220
Neg logit contributions
 you-0.240
prise-0.201
?-0.196
n-0.190
 am-0.188
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
elt+0.035
arted+0.034
ked+0.033
 eyes+0.032
 floppy+0.032
Neg logit contributions
 you-0.016
prise-0.013
 happen-0.013
ggy-0.013
uch-0.013
Token
Token ID198
Feature activation-1.44e-01

Pos logit contributions
 you+0.438
One+0.383
"+0.368
 am+0.362
?+0.348
Neg logit contributions
ked-0.300
ened-0.284
arted-0.283
elt-0.280
ashed-0.276
Token take
Token ID1011
Feature activation-2.62e-01

Pos logit contributions
elt+0.145
arted+0.133
ked+0.131
 floppy+0.125
 eyes+0.123
Neg logit contributions
 you-0.148
uch-0.141
 happen-0.131
prise-0.130
n-0.128
Token care
Token ID1337
Feature activation-2.80e-01

Pos logit contributions
prise+0.504
uch+0.504
 you+0.488
 happen+0.462
 achieve+0.452
Neg logit contributions
ked-0.466
elt-0.457
ed-0.447
arted-0.447
 arms-0.436
Token of
Token ID286
Feature activation-8.46e-02

Pos logit contributions
 you+0.590
prise+0.587
uch+0.585
 happen+0.542
 achieve+0.517
Neg logit contributions
ked-0.448
elt-0.445
arted-0.424
ed-0.419
 arms-0.409
Token the
Token ID262
Feature activation-1.44e-02

Pos logit contributions
uch+0.166
prise+0.165
 you+0.149
arest+0.146
w+0.144
Neg logit contributions
 eyes-0.146
 arms-0.145
ked-0.141
elt-0.138
 asleep-0.136
Token things
Token ID1243
Feature activation-1.03e-01

Pos logit contributions
 you+0.032
prise+0.031
uch+0.031
 happen+0.029
 achieve+0.028
Neg logit contributions
ked-0.022
elt-0.022
arted-0.021
ed-0.020
 eyes-0.020
Token you
Token ID345
Feature activation-6.10e-01

Pos logit contributions
prise+0.201
uch+0.200
 you+0.194
 happen+0.180
w+0.175
Neg logit contributions
ked-0.178
elt-0.176
ed-0.170
arted-0.166
 arms-0.165
Token love
Token ID1842
Feature activation-2.82e-01

Pos logit contributions
prise+1.082
uch+1.048
 you+1.020
 happen+0.945
arest+0.909
Neg logit contributions
ked-1.172
elt-1.140
ed-1.134
 arms-1.096
 confused-1.095
Token!
Token ID0
Feature activation-2.35e-01

Pos logit contributions
prise+0.610
uch+0.597
arest+0.537
 you+0.536
 happen+0.523
Neg logit contributions
elt-0.430
ed-0.419
 down-0.418
 eyes-0.416
 arms-0.416
Token<|endoftext|>
Token ID50256
Feature activation-2.11e-01

Pos logit contributions
uch+0.503
 happen+0.484
prise+0.482
 you+0.448
w+0.446
Neg logit contributions
elt-0.394
ked-0.358
 He-0.356
arted-0.352
 arms-0.346
TokenOne
Token ID3198
Feature activation-4.68e-01

Pos logit contributions
prise+0.446
uch+0.432
 happen+0.428
 you+0.418
arest+0.401
Neg logit contributions
elt-0.353
ed-0.348
 asleep-0.332
 down-0.324
ked-0.320
Token day
Token ID1110
Feature activation-2.12e-01

Pos logit contributions
prise+0.775
uch+0.738
 you+0.738
 happen+0.678
 achieve+0.659
Neg logit contributions
elt-0.965
 arms-0.937
arted-0.923
 eyes-0.917
 confused-0.906
Token It
Token ID632
Feature activation+1.45e-01

Pos logit contributions
ked+0.127
elt+0.125
ed+0.119
arted+0.118
 eyes+0.118
Neg logit contributions
 you-0.101
prise-0.100
uch-0.098
 happen-0.086
 achieve-0.083
Token is
Token ID318
Feature activation-2.71e-01

Pos logit contributions
ked+0.273
elt+0.271
ed+0.260
arted+0.255
 arms+0.252
Neg logit contributions
prise-0.264
 you-0.261
uch-0.256
 happen-0.234
 achieve-0.225
Token a
Token ID257
Feature activation+3.74e-02

Pos logit contributions
 you+0.580
prise+0.545
uch+0.540
 happen+0.518
 am+0.485
Neg logit contributions
ked-0.464
elt-0.453
arted-0.434
ed-0.423
ashed-0.411
Token gift
Token ID6979
Feature activation-1.85e-01

Pos logit contributions
ked+0.056
elt+0.056
 eyes+0.054
 arms+0.053
 confused+0.053
Neg logit contributions
uch-0.079
 you-0.079
prise-0.078
 happen-0.073
w-0.070
Token for
Token ID329
Feature activation+1.33e-01

Pos logit contributions
uch+0.398
prise+0.388
 you+0.379
 achieve+0.358
w+0.351
Neg logit contributions
ked-0.284
elt-0.283
ed-0.271
 eyes-0.268
 asleep-0.262
Token you
Token ID345
Feature activation-6.10e-01

Pos logit contributions
 eyes+0.343
 arms+0.329
ked+0.321
elt+0.319
ed+0.314
Neg logit contributions
uch-0.162
prise-0.134
 achieve-0.127
arest-0.120
w-0.119
Token."
Token ID526
Feature activation-3.46e-01

Pos logit contributions
uch+1.269
prise+1.228
 you+1.195
 happen+1.148
w+1.114
Neg logit contributions
ked-0.978
elt-0.957
 eyes-0.956
 arms-0.937
ed-0.926
Token Ben
Token ID3932
Feature activation+5.23e-02

Pos logit contributions
 you+0.655
uch+0.638
prise+0.636
 happen+0.593
 achieve+0.558
Neg logit contributions
ked-0.648
elt-0.638
arted-0.612
ed-0.598
 eyes-0.586
Token said
Token ID531
Feature activation+8.63e-03

Pos logit contributions
ked+0.104
elt+0.102
arted+0.101
itted+0.090
ashed+0.090
Neg logit contributions
 you-0.103
prise-0.088
 happen-0.086
 am-0.086
?-0.086
Token,
Token ID11
Feature activation-2.48e-02

Pos logit contributions
ked+0.018
elt+0.018
ed+0.017
arted+0.017
 eyes+0.017
Neg logit contributions
 you-0.014
uch-0.014
prise-0.014
 happen-0.013
 achieve-0.012
Token "
Token ID366
Feature activation+2.80e-01

Pos logit contributions
 you+0.067
prise+0.059
 happen+0.059
 achieve+0.057
uch+0.057
Neg logit contributions
elt-0.028
arted-0.027
ked-0.026
ashed-0.026
ed-0.026
Token of
Token ID286
Feature activation-1.42e-01

Pos logit contributions
ked+0.135
elt+0.129
 eyes+0.126
 arms+0.126
ed+0.122
Neg logit contributions
prise-0.239
uch-0.237
 you-0.233
 happen-0.217
w-0.213
Token you
Token ID345
Feature activation-6.42e-01

Pos logit contributions
uch+0.298
prise+0.294
 you+0.293
 happen+0.271
 achieve+0.263
Neg logit contributions
elt-0.224
ked-0.223
arted-0.215
 arms-0.214
 eyes-0.213
Token.
Token ID13
Feature activation-2.08e-01

Pos logit contributions
uch+1.063
prise+1.061
 you+1.011
 happen+0.959
arest+0.916
Neg logit contributions
elt-1.264
ked-1.252
ed-1.252
 asleep-1.228
 confused-1.214
Token Anna
Token ID11735
Feature activation-5.96e-03

Pos logit contributions
uch+0.443
prise+0.432
 happen+0.424
 you+0.416
w+0.391
Neg logit contributions
elt-0.341
ked-0.325
arted-0.305
 arms-0.302
 eyes-0.302
Token,
Token ID11
Feature activation-4.96e-02

Pos logit contributions
 you+0.011
prise+0.011
uch+0.011
 happen+0.010
 achieve+0.010
Neg logit contributions
ked-0.011
elt-0.011
arted-0.010
ed-0.010
 eyes-0.010
Token you
Token ID345
Feature activation-6.10e-01

Pos logit contributions
 you+0.074
prise+0.069
uch+0.068
 happen+0.063
 achieve+0.058
Neg logit contributions
ked-0.116
elt-0.113
arted-0.110
ed-0.108
ashed-0.106
Token need
Token ID761
Feature activation-2.30e-01

Pos logit contributions
uch+0.846
prise+0.843
 you+0.832
 happen+0.769
gh+0.754
Neg logit contributions
ked-1.321
 confused-1.316
ed-1.290
 eyes-1.290
 shrugged-1.283
Token to
Token ID284
Feature activation+1.51e-01

Pos logit contributions
uch+0.656
prise+0.643
 you+0.623
 happen+0.610
 achieve+0.608
Neg logit contributions
elt-0.203
 eyes-0.193
 arms-0.189
ked-0.187
 asleep-0.175
Token share
Token ID2648
Feature activation-3.04e-01

Pos logit contributions
 eyes+0.253
 arms+0.235
 confused+0.230
 shoulders+0.227
 shrugged+0.227
Neg logit contributions
uch-0.281
prise-0.273
w-0.265
arest-0.260
 you-0.232
Token your
Token ID534
Feature activation-3.01e-01

Pos logit contributions
uch+0.660
prise+0.645
arest+0.590
 achieve+0.575
 you+0.573
Neg logit contributions
 eyes-0.482
 arms-0.472
ked-0.463
 down-0.458
 asleep-0.447
Token desk
Token ID6915
Feature activation+5.52e-02

Pos logit contributions
 you+0.667
uch+0.652
prise+0.650
 happen+0.611
 achieve+0.587
Neg logit contributions
ked-0.464
elt-0.452
arted-0.427
ed-0.419
 eyes-0.418
Token
Token ID198
Feature activation-2.13e-01

Pos logit contributions
ked+0.106
arted+0.099
elt+0.099
ed+0.092
ashed+0.091
Neg logit contributions
 you-0.150
prise-0.137
uch-0.132
 happen-0.131
 am-0.124
Token
Token ID198
Feature activation-1.78e-01

Pos logit contributions
 happen+0.457
uch+0.435
prise+0.371
 you+0.351
arest+0.343
Neg logit contributions
 He-0.365
elt-0.361
arted-0.350
 Curious-0.335
 arms-0.331
Token"
Token ID1
Feature activation-4.04e-01

Pos logit contributions
 happen+0.349
uch+0.324
prise+0.258
 you+0.256
w+0.245
Neg logit contributions
elt-0.326
 He-0.323
arted-0.320
 Curious-0.314
ked-0.297
TokenMom
Token ID29252
Feature activation-3.20e-01

Pos logit contributions
uch+0.717
 you+0.708
 happen+0.706
prise+0.698
 achieve+0.652
Neg logit contributions
elt-0.804
ked-0.796
ed-0.733
arted-0.722
ashed-0.707
Token,
Token ID11
Feature activation-3.23e-02

Pos logit contributions
 you+0.635
prise+0.610
uch+0.608
 happen+0.564
 am+0.534
Neg logit contributions
ked-0.581
elt-0.564
arted-0.549
ed-0.527
ashed-0.519
Token you
Token ID345
Feature activation-6.10e-01

Pos logit contributions
uch+0.057
 you+0.057
prise+0.056
 happen+0.052
 achieve+0.049
Neg logit contributions
ked-0.062
elt-0.062
 eyes-0.058
arted-0.058
ed-0.058
Token are
Token ID389
Feature activation-3.29e-01

Pos logit contributions
 you+0.906
uch+0.889
prise+0.887
 happen+0.839
 achieve+0.787
Neg logit contributions
ked-1.350
elt-1.327
 eyes-1.292
ed-1.279
 confused-1.264
Token so
Token ID523
Feature activation+2.02e-01

Pos logit contributions
uch+0.716
prise+0.709
 you+0.705
 happen+0.667
w+0.646
Neg logit contributions
ked-0.491
elt-0.487
 confused-0.465
 eyes-0.463
arted-0.462
Token smart
Token ID4451
Feature activation-6.47e-02

Pos logit contributions
elt+0.257
 confused+0.256
ked+0.235
ed+0.234
 puzzled+0.229
Neg logit contributions
uch-0.471
 happen-0.460
prise-0.456
 you-0.454
 achieve-0.437
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
 you+0.101
uch+0.098
prise+0.098
 happen+0.089
 achieve+0.084
Neg logit contributions
ked-0.142
elt-0.140
arted-0.135
ed-0.133
 eyes-0.131
Token You
Token ID921
Feature activation-1.14e-01

Pos logit contributions
 you+0.328
uch+0.318
prise+0.318
 happen+0.297
 achieve+0.278
Neg logit contributions
ked-0.352
elt-0.347
arted-0.332
ed-0.325
 eyes-0.320
Token hurt
Token ID5938
Feature activation-2.02e-01

Pos logit contributions
elt+0.208
ked+0.207
arted+0.204
 eyes+0.193
 arms+0.191
Neg logit contributions
 you-0.156
prise-0.146
uch-0.145
 happen-0.138
 am-0.130
Token your
Token ID534
Feature activation-3.19e-01

Pos logit contributions
prise+0.399
uch+0.390
 you+0.370
 achieve+0.348
arest+0.348
Neg logit contributions
elt-0.361
ked-0.359
 eyes-0.346
ed-0.344
arted-0.344
Token k
Token ID479
Feature activation+7.23e-03

Pos logit contributions
 you+0.807
uch+0.771
prise+0.770
 happen+0.737
 am+0.702
Neg logit contributions
ked-0.408
elt-0.397
arted-0.378
ed-0.360
ashed-0.348
Tokenite
Token ID578
Feature activation-1.60e-01

Pos logit contributions
elt+0.013
ked+0.013
 arms+0.013
ed+0.012
arted+0.012
Neg logit contributions
 happen-0.014
prise-0.014
 you-0.013
uch-0.013
 achieve-0.013
Token and
Token ID290
Feature activation+2.48e-01

Pos logit contributions
prise+0.246
 you+0.221
uch+0.218
 happen+0.198
arest+0.195
Neg logit contributions
ked-0.351
elt-0.349
ed-0.343
 arms-0.341
 asleep-0.340
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
ked+0.599
elt+0.589
arted+0.570
ed+0.564
 eyes+0.561
Neg logit contributions
 you-0.324
prise-0.322
uch-0.318
 happen-0.282
 achieve-0.263
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
prise+1.092
uch+0.991
 happen+0.981
gh+0.974
 you+0.963
Neg logit contributions
ked-1.177
 confused-1.153
ed-1.150
elt-1.118
ashed-1.100
Token Let
Token ID3914
Feature activation+7.29e-02

Pos logit contributions
prise+0.420
uch+0.415
 happen+0.409
 you+0.400
 achieve+0.379
Neg logit contributions
elt-0.315
ked-0.309
 arms-0.286
 eyes-0.286
arted-0.283
Token's
Token ID338
Feature activation-5.45e-03

Pos logit contributions
 down+0.095
ed+0.088
 eyes+0.082
 arms+0.078
ked+0.078
Neg logit contributions
prise-0.188
arest-0.173
vern-0.172
 achieve-0.169
uch-0.163
Token see
Token ID766
Feature activation-1.44e-01

Pos logit contributions
prise+0.011
uch+0.010
arest+0.010
w+0.010
vern+0.010
Neg logit contributions
 down-0.009
 eyes-0.008
 confused-0.008
ked-0.008
 arms-0.008
Token if
Token ID611
Feature activation-1.33e-01

Pos logit contributions
uch+0.257
prise+0.240
gh+0.219
 achieve+0.219
 am+0.211
Neg logit contributions
 down-0.289
ked-0.284
 eyes-0.277
elt-0.274
ed-0.268
Token color
Token ID3124
Feature activation-1.84e-01

Pos logit contributions
 you+0.075
prise+0.067
 happen+0.066
uch+0.065
 am+0.061
Neg logit contributions
ked-0.065
arted-0.063
elt-0.062
ashed-0.058
ed-0.056
Token you
Token ID345
Feature activation-6.42e-01

Pos logit contributions
 you+0.369
prise+0.364
uch+0.361
 happen+0.333
 achieve+0.320
Neg logit contributions
ked-0.316
elt-0.312
arted-0.295
ed-0.293
 eyes-0.288
Token want
Token ID765
Feature activation-8.97e-02

Pos logit contributions
prise+1.162
uch+1.150
 you+1.102
 happen+1.028
ggy+0.996
Neg logit contributions
ked-1.193
elt-1.183
ed-1.159
 confused-1.144
 eyes-1.136
Token,
Token ID11
Feature activation-4.49e-02

Pos logit contributions
uch+0.223
prise+0.220
 achieve+0.201
arest+0.200
 you+0.199
Neg logit contributions
 eyes-0.110
elt-0.110
 arms-0.106
ked-0.103
 asleep-0.103
Token but
Token ID475
Feature activation+1.66e-01

Pos logit contributions
 you+0.099
prise+0.092
uch+0.090
 happen+0.088
 achieve+0.083
Neg logit contributions
ked-0.076
elt-0.074
arted-0.071
ed-0.070
ashed-0.068
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
ked+0.412
elt+0.407
 eyes+0.406
 arms+0.400
 confused+0.396
Neg logit contributions
prise-0.192
uch-0.191
 you-0.160
arest-0.158
vern-0.153
Token have
Token ID423
Feature activation-3.15e-01

Pos logit contributions
prise+0.925
 you+0.870
uch+0.861
 happen+0.801
gh+0.768
Neg logit contributions
ked-1.319
 confused-1.291
 shrugged-1.282
elt-1.266
 eyes-1.247
Token to
Token ID284
Feature activation+1.50e-01

Pos logit contributions
 you+0.798
prise+0.774
uch+0.772
 happen+0.733
 achieve+0.702
Neg logit contributions
ked-0.396
elt-0.384
arted-0.362
ed-0.348
ashed-0.334
Token use
Token ID779
Feature activation-1.89e-01

Pos logit contributions
 eyes+0.245
 shrugged+0.235
 confused+0.230
 arms+0.230
ked+0.218
Neg logit contributions
uch-0.278
prise-0.272
arest-0.256
w-0.250
 you-0.230
Token the
Token ID262
Feature activation-9.16e-03

Pos logit contributions
uch+0.341
prise+0.337
 you+0.320
 happen+0.304
 achieve+0.298
Neg logit contributions
 eyes-0.354
 arms-0.354
ked-0.353
elt-0.348
arted-0.337
Token yellow
Token ID7872
Feature activation+2.28e-01

Pos logit contributions
 you+0.020
prise+0.020
uch+0.019
 happen+0.018
 achieve+0.018
Neg logit contributions
ked-0.014
elt-0.014
 eyes-0.013
 arms-0.013
arted-0.013
Token of
Token ID286
Feature activation-1.42e-01

Pos logit contributions
 you+0.105
prise+0.102
uch+0.101
 happen+0.092
 achieve+0.087
Neg logit contributions
ked-0.140
elt-0.138
arted-0.133
ed-0.131
 eyes-0.128
Token flour
Token ID10601
Feature activation-7.05e-02

Pos logit contributions
uch+0.298
prise+0.294
 you+0.293
 happen+0.271
 achieve+0.263
Neg logit contributions
elt-0.224
ked-0.223
arted-0.215
 arms-0.214
 eyes-0.213
Token as
Token ID355
Feature activation+1.70e-01

Pos logit contributions
 you+0.164
uch+0.158
prise+0.156
 happen+0.150
 am+0.142
Neg logit contributions
ked-0.104
elt-0.100
arted-0.097
ed-0.091
ashed-0.090
Token a
Token ID257
Feature activation+4.01e-02

Pos logit contributions
ked+0.330
elt+0.321
arted+0.312
ed+0.300
 eyes+0.295
Neg logit contributions
 you-0.319
prise-0.300
uch-0.299
 happen-0.280
 am-0.262
Token thank
Token ID5875
Feature activation-2.08e-01

Pos logit contributions
ked+0.064
elt+0.063
 eyes+0.059
 arms+0.059
arted+0.059
Neg logit contributions
 you-0.085
uch-0.084
prise-0.083
 happen-0.078
 achieve-0.075
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
uch+0.246
prise+0.238
 happen+0.194
 you+0.193
 am+0.190
Neg logit contributions
ked-0.529
elt-0.527
ed-0.513
 eyes-0.512
 down-0.505
Token present
Token ID1944
Feature activation-1.06e-01

Pos logit contributions
 you+1.421
uch+1.419
prise+1.413
 happen+1.325
w+1.269
Neg logit contributions
ked-0.843
elt-0.815
arted-0.773
ed-0.769
 eyes-0.745
Token.
Token ID13
Feature activation-1.88e-01

Pos logit contributions
uch+0.171
prise+0.171
 you+0.169
 happen+0.153
 achieve+0.149
Neg logit contributions
ked-0.218
elt-0.216
ed-0.210
arted-0.205
 eyes-0.203
Token The
Token ID383
Feature activation+2.33e-01

Pos logit contributions
uch+0.447
 you+0.440
prise+0.439
 happen+0.425
w+0.401
Neg logit contributions
elt-0.255
ked-0.251
arted-0.234
ed-0.226
 eyes-0.223
Token princess
Token ID21752
Feature activation+2.19e-02

Pos logit contributions
ked+0.356
elt+0.351
 eyes+0.337
 arms+0.330
ed+0.324
Neg logit contributions
 you-0.503
uch-0.499
prise-0.494
 happen-0.467
 achieve-0.453
Token was
Token ID373
Feature activation-5.41e-02

Pos logit contributions
ked+0.040
elt+0.039
arted+0.037
ed+0.036
 eyes+0.036
Neg logit contributions
 you-0.043
prise-0.042
uch-0.041
 happen-0.039
 achieve-0.037
Token
Token ID198
Feature activation-1.78e-01

Pos logit contributions
 happen+0.457
uch+0.435
prise+0.371
 you+0.351
arest+0.343
Neg logit contributions
 He-0.365
elt-0.361
arted-0.350
 Curious-0.335
 arms-0.331
Token"
Token ID1
Feature activation-4.04e-01

Pos logit contributions
 happen+0.349
uch+0.324
prise+0.258
 you+0.256
w+0.245
Neg logit contributions
elt-0.326
 He-0.323
arted-0.320
 Curious-0.314
ked-0.297
TokenOK
Token ID11380
Feature activation-2.78e-01

Pos logit contributions
uch+0.717
 you+0.708
 happen+0.706
prise+0.698
 achieve+0.652
Neg logit contributions
elt-0.804
ked-0.796
ed-0.733
arted-0.722
ashed-0.707
Token,
Token ID11
Feature activation-3.85e-02

Pos logit contributions
uch+0.559
prise+0.537
 you+0.510
w+0.487
 happen+0.484
Neg logit contributions
ked-0.486
 eyes-0.467
elt-0.466
ed-0.457
 arms-0.457
Token but
Token ID475
Feature activation+1.68e-01

Pos logit contributions
 you+0.082
uch+0.081
prise+0.080
 happen+0.075
 achieve+0.072
Neg logit contributions
ked-0.062
elt-0.060
arted-0.058
ed-0.056
 eyes-0.056
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
 eyes+0.374
ked+0.374
elt+0.366
 arms+0.363
 shrugged+0.358
Neg logit contributions
prise-0.238
uch-0.232
arest-0.208
vern-0.206
w-0.191
Token have
Token ID423
Feature activation-3.09e-01

Pos logit contributions
prise+0.843
 you+0.829
uch+0.816
 happen+0.754
w+0.717
Neg logit contributions
ked-1.388
 confused-1.339
 eyes-1.336
 shrugged-1.324
elt-1.317
Token to
Token ID284
Feature activation+1.52e-01

Pos logit contributions
 you+0.802
prise+0.775
uch+0.773
 happen+0.735
 achieve+0.704
Neg logit contributions
ked-0.373
elt-0.360
arted-0.340
ed-0.326
ashed-0.312
Token be
Token ID307
Feature activation-2.25e-01

Pos logit contributions
 eyes+0.248
 confused+0.244
 arms+0.244
 shrugged+0.243
 down+0.239
Neg logit contributions
uch-0.271
prise-0.266
w-0.250
arest-0.249
 you-0.230
Token gentle
Token ID10296
Feature activation+5.84e-04

Pos logit contributions
 you+0.440
prise+0.416
uch+0.406
 happen+0.380
 achieve+0.360
Neg logit contributions
ked-0.425
elt-0.421
arted-0.398
ed-0.388
 eyes-0.380
Token.
Token ID13
Feature activation-1.90e-01

Pos logit contributions
ked+0.001
elt+0.001
arted+0.001
ed+0.001
ashed+0.001
Neg logit contributions
 you-0.001
prise-0.001
uch-0.001
 happen-0.001
 am-0.001
Token is
Token ID318
Feature activation-3.13e-01

Pos logit contributions
ked+0.275
elt+0.265
arted+0.257
ed+0.246
 eyes+0.244
Neg logit contributions
 you-0.369
uch-0.368
prise-0.362
 happen-0.337
w-0.326
Token that
Token ID326
Feature activation-1.73e-01

Pos logit contributions
 you+0.651
prise+0.632
uch+0.630
 happen+0.590
 achieve+0.561
Neg logit contributions
ked-0.529
elt-0.518
arted-0.495
ed-0.482
 eyes-0.472
Token sm
Token ID895
Feature activation+2.11e-02

Pos logit contributions
prise+0.252
uch+0.246
 you+0.223
arest+0.204
 achieve+0.203
Neg logit contributions
elt-0.379
ked-0.376
 eyes-0.374
 arms-0.374
 confused-0.366
Tokenelly
Token ID6148
Feature activation+6.23e-02

Pos logit contributions
ked+0.030
elt+0.030
arted+0.028
ed+0.027
ashed+0.026
Neg logit contributions
 you-0.050
prise-0.049
uch-0.048
 happen-0.046
 achieve-0.044
Token thing
Token ID1517
Feature activation-1.47e-01

Pos logit contributions
ked+0.121
elt+0.120
arted+0.115
ed+0.113
 eyes+0.111
Neg logit contributions
 you-0.112
prise-0.110
uch-0.109
 happen-0.100
 achieve-0.095
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
prise+0.256
uch+0.251
 you+0.247
 happen+0.222
 achieve+0.220
Neg logit contributions
ked-0.290
elt-0.288
ed-0.277
arted-0.274
 eyes-0.269
Token are
Token ID389
Feature activation-3.28e-01

Pos logit contributions
prise+1.016
uch+0.973
 you+0.969
 happen+0.886
gh+0.875
Neg logit contributions
ked-1.233
elt-1.193
ed-1.184
 confused-1.161
 shrugged-1.156
Token playing
Token ID2712
Feature activation+7.70e-02

Pos logit contributions
 you+0.638
prise+0.631
uch+0.629
 happen+0.577
 achieve+0.553
Neg logit contributions
ked-0.586
elt-0.571
arted-0.553
ed-0.539
 eyes-0.533
Token with
Token ID351
Feature activation+1.09e-02

Pos logit contributions
ed+0.134
 down+0.133
ked+0.132
elt+0.130
 asleep+0.129
Neg logit contributions
prise-0.147
uch-0.145
 you-0.132
 happen-0.130
arest-0.128
Token?"
Token ID1701
Feature activation-4.28e-01

Pos logit contributions
 eyes+0.021
 arms+0.021
ked+0.021
elt+0.020
arted+0.020
Neg logit contributions
uch-0.019
prise-0.019
 you-0.017
 achieve-0.017
 happen-0.017
Token Fl
Token ID1610
Feature activation+2.27e-02

Pos logit contributions
 you+0.904
prise+0.877
uch+0.874
 happen+0.821
 achieve+0.779
Neg logit contributions
ked-0.712
elt-0.697
arted-0.666
ed-0.649
 eyes-0.633
TokenThat
Token ID2504
Feature activation-2.41e-01

Pos logit contributions
elt+0.429
ked+0.389
ed+0.370
arted+0.363
 shrugged+0.356
Neg logit contributions
 happen-0.384
uch-0.376
prise-0.374
 you-0.360
vern-0.339
Token is
Token ID318
Feature activation-2.55e-01

Pos logit contributions
prise+0.414
 you+0.413
uch+0.402
 happen+0.367
 achieve+0.350
Neg logit contributions
ked-0.478
elt-0.478
 eyes-0.452
arted-0.451
ed-0.451
Token very
Token ID845
Feature activation+7.79e-02

Pos logit contributions
uch+0.513
prise+0.512
 you+0.505
 happen+0.467
 achieve+0.455
Neg logit contributions
ked-0.429
elt-0.421
 eyes-0.403
arted-0.399
 confused-0.398
Token sweet
Token ID6029
Feature activation-4.46e-02

Pos logit contributions
 confused+0.121
 floppy+0.114
 eyes+0.113
elt+0.111
 arms+0.111
Neg logit contributions
uch-0.158
prise-0.156
 happen-0.147
 you-0.144
w-0.142
Token of
Token ID286
Feature activation-7.22e-02

Pos logit contributions
uch+0.104
 you+0.104
prise+0.104
 happen+0.097
 achieve+0.095
Neg logit contributions
elt-0.062
ked-0.061
ed-0.057
arted-0.057
 eyes-0.055
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
uch+0.075
prise+0.067
arest+0.060
 achieve+0.059
vern+0.055
Neg logit contributions
 eyes-0.196
 arms-0.185
elt-0.180
 down-0.178
 floppy-0.174
Token.
Token ID13
Feature activation-1.77e-01

Pos logit contributions
prise+1.057
uch+1.052
 you+0.999
 happen+0.954
w+0.905
Neg logit contributions
ked-1.192
elt-1.155
 eyes-1.146
 confused-1.135
ed-1.132
Token I
Token ID314
Feature activation-2.57e-01

Pos logit contributions
uch+0.375
prise+0.368
 you+0.365
 happen+0.359
w+0.335
Neg logit contributions
elt-0.288
ked-0.277
arted-0.262
 eyes-0.259
 arms-0.255
Token will
Token ID481
Feature activation-3.71e-01

Pos logit contributions
 you+0.423
uch+0.403
prise+0.398
 happen+0.394
 ourselves+0.385
Neg logit contributions
elt-0.501
ashed-0.496
ed-0.493
 confused-0.493
ked-0.491
Token send
Token ID3758
Feature activation-1.94e-01

Pos logit contributions
uch+0.676
prise+0.673
w+0.627
arest+0.605
vern+0.571
Neg logit contributions
 eyes-0.674
 confused-0.635
 arms-0.625
ked-0.612
 asleep-0.610
Token it
Token ID340
Feature activation-1.56e-01

Pos logit contributions
uch+0.197
prise+0.192
 you+0.167
 achieve+0.167
 happen+0.167
Neg logit contributions
ked-0.517
elt-0.515
 eyes-0.507
ed-0.506
 arms-0.498
Token and
Token ID290
Feature activation+1.93e-01

Pos logit contributions
 you+0.414
 am+0.366
One+0.358
?+0.356
"+0.351
Neg logit contributions
ked-0.242
ened-0.230
arted-0.218
oured-0.209
elt-0.204
Token blue
Token ID4171
Feature activation+1.97e-01

Pos logit contributions
ked+0.330
elt+0.324
arted+0.310
ed+0.293
ashed+0.288
Neg logit contributions
 you-0.421
prise-0.381
uch-0.374
 happen-0.371
 am-0.349
Token beads
Token ID36116
Feature activation-6.15e-03

Pos logit contributions
ked+0.393
elt+0.389
arted+0.369
ed+0.368
 eyes+0.366
Neg logit contributions
 you-0.344
prise-0.341
uch-0.338
 happen-0.308
 achieve-0.297
Token,
Token ID11
Feature activation-4.69e-02

Pos logit contributions
 you+0.013
prise+0.012
uch+0.012
 happen+0.012
 achieve+0.011
Neg logit contributions
ked-0.010
elt-0.010
arted-0.010
ed-0.010
 eyes-0.009
Token and
Token ID290
Feature activation+2.38e-01

Pos logit contributions
 you+0.108
 happen+0.096
uch+0.087
 am+0.087
 achieve+0.086
Neg logit contributions
arted-0.081
elt-0.076
ked-0.069
ashed-0.069
ed-0.065
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
arted+0.411
elt+0.406
ked+0.403
ashed+0.364
ed+0.353
Neg logit contributions
 you-0.530
 happen-0.467
prise-0.462
uch-0.447
 am-0.439
Token sort
Token ID3297
Feature activation-6.10e-02

Pos logit contributions
uch+1.103
prise+1.102
 you+1.072
 happen+1.027
gh+1.021
Neg logit contributions
ked-1.085
ed-1.053
 shrugged-1.031
 confused-1.026
elt-1.019
Token the
Token ID262
Feature activation-1.17e-02

Pos logit contributions
uch+0.119
prise+0.116
 you+0.112
 happen+0.106
 achieve+0.105
Neg logit contributions
ked-0.108
elt-0.107
ed-0.104
 eyes-0.104
arted-0.103
Token yellow
Token ID7872
Feature activation+2.30e-01

Pos logit contributions
 you+0.026
prise+0.026
uch+0.026
 happen+0.024
 achieve+0.023
Neg logit contributions
ked-0.017
elt-0.017
 eyes-0.016
arted-0.016
 arms-0.016
Token and
Token ID290
Feature activation+2.56e-01

Pos logit contributions
ked+0.345
elt+0.339
 eyes+0.325
 arms+0.323
ed+0.318
Neg logit contributions
prise-0.509
uch-0.502
 you-0.500
 happen-0.467
 achieve-0.457
Token green
Token ID4077
Feature activation+2.77e-01

Pos logit contributions
ked+0.401
elt+0.393
arted+0.375
ed+0.360
ashed+0.348
Neg logit contributions
 you-0.584
prise-0.553
uch-0.547
 happen-0.527
 achieve-0.500
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
 you+0.359
prise+0.339
uch+0.329
 happen+0.309
 am+0.299
Neg logit contributions
ked-0.300
arted-0.285
elt-0.284
ed-0.271
ashed-0.267
Token
Token ID198
Feature activation-1.76e-01

Pos logit contributions
 you+0.587
prise+0.561
uch+0.557
 happen+0.528
 achieve+0.510
Neg logit contributions
ked-0.318
elt-0.303
arted-0.290
ed-0.281
ashed-0.271
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
uch+0.410
 happen+0.400
prise+0.368
 you+0.352
arest+0.343
Neg logit contributions
 He-0.263
elt-0.260
arted-0.258
 arms-0.245
 confused-0.235
Token"
Token ID1
Feature activation-3.97e-01

Pos logit contributions
 happen+0.314
uch+0.288
prise+0.239
 you+0.229
 belong+0.220
Neg logit contributions
elt-0.321
 He-0.316
arted-0.315
 Curious-0.304
ked-0.292
TokenThank
Token ID10449
Feature activation-8.27e-02

Pos logit contributions
 you+0.685
uch+0.679
prise+0.674
 happen+0.649
 achieve+0.600
Neg logit contributions
ked-0.816
elt-0.812
arted-0.754
ed-0.750
ashed-0.728
Token you
Token ID345
Feature activation-6.08e-01

Pos logit contributions
uch+0.089
 achieve+0.084
irl+0.072
 happen+0.063
 accomplish+0.061
Neg logit contributions
ed-0.219
elt-0.217
 arms-0.202
 down-0.198
 eyes-0.197
Token,
Token ID11
Feature activation-3.31e-02

Pos logit contributions
 you+1.200
prise+1.149
uch+1.131
 happen+1.066
 achieve+1.002
Neg logit contributions
ked-1.123
elt-1.107
arted-1.055
ed-1.026
ashed-1.004
Token doctor
Token ID6253
Feature activation-7.64e-02

Pos logit contributions
 you+0.073
prise+0.071
uch+0.070
 happen+0.066
 achieve+0.063
Neg logit contributions
ked-0.052
elt-0.051
arted-0.049
ed-0.048
ashed-0.046
Token,"
Token ID553
Feature activation-3.16e-01

Pos logit contributions
uch+0.107
prise+0.105
 you+0.103
 happen+0.094
 achieve+0.091
Neg logit contributions
ked-0.176
elt-0.173
ed-0.170
 eyes-0.164
 arms-0.164
Token Mom
Token ID11254
Feature activation+3.57e-02

Pos logit contributions
 you+0.678
prise+0.595
 happen+0.549
uch+0.549
 am+0.520
Neg logit contributions
ked-0.572
elt-0.570
arted-0.556
ashed-0.536
ed-0.525
Token said
Token ID531
Feature activation+1.44e-02

Pos logit contributions
ked+0.071
elt+0.066
arted+0.065
ashed+0.065
ed+0.062
Neg logit contributions
 you-0.069
prise-0.062
uch-0.058
 happen-0.056
?-0.056
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
 eyes+0.257
 confused+0.241
 down+0.239
 arms+0.237
 shrugged+0.227
Neg logit contributions
w-0.351
uch-0.349
prise-0.348
arest-0.324
reetings-0.307
Token
Token ID198
Feature activation-1.76e-01

Pos logit contributions
 you+0.587
prise+0.561
uch+0.557
 happen+0.528
 achieve+0.510
Neg logit contributions
ked-0.318
elt-0.303
arted-0.290
ed-0.281
ashed-0.271
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
uch+0.410
 happen+0.400
prise+0.368
 you+0.352
arest+0.343
Neg logit contributions
 He-0.263
elt-0.260
arted-0.258
 arms-0.245
 confused-0.235
Token"
Token ID1
Feature activation-3.97e-01

Pos logit contributions
 happen+0.314
uch+0.288
prise+0.239
 you+0.229
 belong+0.220
Neg logit contributions
elt-0.321
 He-0.316
arted-0.315
 Curious-0.304
ked-0.292
TokenThank
Token ID10449
Feature activation-8.27e-02

Pos logit contributions
 you+0.685
uch+0.679
prise+0.674
 happen+0.649
 achieve+0.600
Neg logit contributions
ked-0.816
elt-0.812
arted-0.754
ed-0.750
ashed-0.728
Token you
Token ID345
Feature activation-6.08e-01

Pos logit contributions
uch+0.089
 achieve+0.084
irl+0.072
 happen+0.063
 accomplish+0.061
Neg logit contributions
ed-0.219
elt-0.217
 arms-0.202
 down-0.198
 eyes-0.197
Token,
Token ID11
Feature activation-3.31e-02

Pos logit contributions
 you+1.200
prise+1.149
uch+1.131
 happen+1.066
 achieve+1.002
Neg logit contributions
ked-1.123
elt-1.107
arted-1.055
ed-1.026
ashed-1.004
Token Lily
Token ID20037
Feature activation+6.02e-02

Pos logit contributions
 you+0.073
prise+0.071
uch+0.070
 happen+0.066
 achieve+0.063
Neg logit contributions
ked-0.052
elt-0.051
arted-0.049
ed-0.048
ashed-0.046
Token and
Token ID290
Feature activation+2.48e-01

Pos logit contributions
ked+0.140
elt+0.137
arted+0.133
ed+0.132
 eyes+0.129
Neg logit contributions
 you-0.086
prise-0.084
uch-0.083
 happen-0.076
 achieve-0.070
Token Sam
Token ID3409
Feature activation+1.08e-01

Pos logit contributions
ked+0.387
elt+0.379
arted+0.361
ed+0.350
ashed+0.340
Neg logit contributions
 you-0.567
prise-0.538
uch-0.536
 happen-0.509
 achieve-0.480
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
ked+0.231
ed+0.227
elt+0.227
 eyes+0.220
 arms+0.219
Neg logit contributions
uch-0.167
prise-0.166
 you-0.157
 happen-0.145
arest-0.143
Token can
Token ID460
Feature activation-2.65e-01

Pos logit contributions
 you+0.024
 happen+0.021
uch+0.021
 am+0.021
?+0.020
Neg logit contributions
ked-0.014
 floppy-0.013
elt-0.013
 puzzled-0.013
arted-0.013
Token trust
Token ID3774
Feature activation-2.43e-01

Pos logit contributions
prise+0.453
uch+0.415
w+0.406
arest+0.381
vern+0.356
Neg logit contributions
 confused-0.518
 eyes-0.510
 asleep-0.502
 arms-0.501
 down-0.494
Token me
Token ID502
Feature activation-1.95e-01

Pos logit contributions
prise+0.333
uch+0.327
 you+0.288
 happen+0.277
arest+0.270
Neg logit contributions
ked-0.575
elt-0.569
 eyes-0.563
 arms-0.560
arted-0.553
Token to
Token ID284
Feature activation+1.39e-01

Pos logit contributions
 you+0.351
prise+0.351
uch+0.348
 happen+0.321
 achieve+0.303
Neg logit contributions
ked-0.370
elt-0.364
ed-0.347
arted-0.346
 arms-0.340
Token keep
Token ID1394
Feature activation-2.66e-01

Pos logit contributions
 eyes+0.258
 asleep+0.249
 arms+0.244
 confused+0.242
 down+0.241
Neg logit contributions
uch-0.252
prise-0.249
arest-0.222
w-0.220
vern-0.203
Token you
Token ID345
Feature activation-6.08e-01

Pos logit contributions
prise+0.447
uch+0.444
 you+0.413
 happen+0.397
 achieve+0.393
Neg logit contributions
ked-0.541
elt-0.530
 arms-0.520
arted-0.517
 eyes-0.514
Token safe
Token ID3338
Feature activation-5.00e-02

Pos logit contributions
 you+1.265
prise+1.259
uch+1.250
 happen+1.163
w+1.114
Neg logit contributions
ked-0.990
elt-0.957
 arms-0.917
ed-0.914
arted-0.908
Token."
Token ID526
Feature activation-3.36e-01

Pos logit contributions
prise+0.077
uch+0.077
 you+0.074
 happen+0.067
 achieve+0.064
Neg logit contributions
ked-0.108
elt-0.107
ed-0.104
 asleep-0.103
arted-0.103
Token Her
Token ID2332
Feature activation+1.62e-01

Pos logit contributions
 you+0.636
prise+0.604
uch+0.598
 happen+0.557
 achieve+0.530
Neg logit contributions
ked-0.642
elt-0.625
arted-0.602
ed-0.589
 eyes-0.576
Token mom
Token ID1995
Feature activation-3.05e-04

Pos logit contributions
ked+0.268
elt+0.262
arted+0.251
ed+0.244
ashed+0.237
Neg logit contributions
 you-0.348
prise-0.335
uch-0.333
 happen-0.314
 achieve-0.298
Token opened
Token ID4721
Feature activation+1.68e-01

Pos logit contributions
 you+0.001
prise+0.001
uch+0.001
 happen+0.001
 am+0.001
Neg logit contributions
ked-0.000
elt-0.000
arted-0.000
ed-0.000
ashed-0.000
Token Everyone
Token ID11075
Feature activation-3.56e-02

Pos logit contributions
 you+0.383
mmm+0.298
 achieve+0.292
".+0.292
?+0.290
Neg logit contributions
ked-0.284
ashed-0.260
arted-0.247
ed-0.233
 arms-0.227
Token in
Token ID287
Feature activation+1.04e-01

Pos logit contributions
 you+0.064
prise+0.057
 happen+0.055
uch+0.054
 am+0.053
Neg logit contributions
ked-0.074
elt-0.072
arted-0.071
 floppy-0.068
 asleep-0.067
Token the
Token ID262
Feature activation+1.07e-02

Pos logit contributions
elt+0.195
ked+0.194
arted+0.183
ed+0.179
ashed+0.177
Neg logit contributions
 you-0.206
prise-0.194
uch-0.188
 happen-0.180
 am-0.173
Token village
Token ID7404
Feature activation-5.21e-03

Pos logit contributions
ked+0.019
elt+0.019
arted+0.018
ed+0.018
 eyes+0.017
Neg logit contributions
 you-0.022
prise-0.021
uch-0.021
 happen-0.019
 achieve-0.018
Token gathered
Token ID9272
Feature activation+1.11e-01

Pos logit contributions
 you+0.011
prise+0.010
uch+0.010
 happen+0.009
 achieve+0.009
Neg logit contributions
ked-0.009
elt-0.009
arted-0.009
 floppy-0.008
ashed-0.008
Token around
Token ID1088
Feature activation+2.96e-01

Pos logit contributions
elt+0.214
ked+0.214
arted+0.199
sed+0.195
ashed+0.191
Neg logit contributions
 you-0.228
 happen-0.190
prise-0.190
 ourselves-0.179
 course-0.175
Token,
Token ID11
Feature activation-2.93e-03

Pos logit contributions
elt+0.550
ked+0.550
arted+0.524
ashed+0.513
ed+0.487
Neg logit contributions
 you-0.615
prise-0.540
 happen-0.531
uch-0.502
 achieve-0.489
Token eager
Token ID11069
Feature activation+3.33e-01

Pos logit contributions
 you+0.006
 achieve+0.005
 happen+0.005
prise+0.005
n+0.005
Neg logit contributions
ked-0.005
elt-0.005
arted-0.005
ashed-0.005
ed-0.004
Token to
Token ID284
Feature activation+1.72e-01

Pos logit contributions
ked+0.548
elt+0.507
 puzzled+0.497
arted+0.490
ashed+0.490
Neg logit contributions
 you-0.793
 happen-0.675
prise-0.632
 us-0.595
 ourselves-0.589
Token take
Token ID1011
Feature activation-1.83e-01

Pos logit contributions
ked+0.359
elt+0.348
 eyes+0.347
arted+0.346
 confused+0.338
Neg logit contributions
uch-0.279
 you-0.268
prise-0.267
w-0.244
 happen-0.229
Token a
Token ID257
Feature activation+6.68e-02

Pos logit contributions
 you+0.372
prise+0.347
uch+0.343
 happen+0.326
 am+0.307
Neg logit contributions
ked-0.335
elt-0.330
arted-0.316
ashed-0.300
 shrugged-0.295
Token,
Token ID11
Feature activation-1.38e-02

Pos logit contributions
 you+0.034
prise+0.033
uch+0.033
 happen+0.031
 achieve+0.029
Neg logit contributions
ked-0.032
elt-0.031
arted-0.030
ed-0.029
ashed-0.028
Token so
Token ID523
Feature activation+2.15e-01

Pos logit contributions
 you+0.033
 happen+0.025
 achieve+0.024
n+0.024
 course+0.023
Neg logit contributions
ked-0.026
ed-0.025
ashed-0.025
elt-0.024
arted-0.024
Token she
Token ID673
Feature activation-3.78e-02

Pos logit contributions
ked+0.442
elt+0.437
arted+0.417
ashed+0.402
ed+0.402
Neg logit contributions
 you-0.393
prise-0.356
uch-0.348
 happen-0.331
 achieve-0.308
Token sw
Token ID1509
Feature activation+1.24e-01

Pos logit contributions
 you+0.079
prise+0.071
uch+0.070
n+0.067
lly+0.067
Neg logit contributions
elt-0.064
ked-0.062
arted-0.061
 asleep-0.060
joy-0.058
Tokenam
Token ID321
Feature activation+1.50e-01

Pos logit contributions
 asleep+0.197
elt+0.197
 floppy+0.182
 confused+0.178
ked+0.177
Neg logit contributions
uch-0.263
 you-0.255
prise-0.247
ggy-0.235
w-0.235
Token over
Token ID625
Feature activation+2.25e-01

Pos logit contributions
elt+0.209
 eyes+0.201
ked+0.195
 floppy+0.188
sed+0.184
Neg logit contributions
 you-0.364
 happen-0.318
prise-0.317
n-0.314
uch-0.308
Token and
Token ID290
Feature activation+2.73e-01

Pos logit contributions
ked+0.318
elt+0.300
arted+0.279
ashed+0.275
 eyes+0.264
Neg logit contributions
 you-0.561
prise-0.518
 happen-0.490
uch-0.481
 am-0.478
Token took
Token ID1718
Feature activation+1.08e-01

Pos logit contributions
 eyes+0.465
itted+0.446
elt+0.442
arted+0.423
ked+0.417
Neg logit contributions
 you-0.589
prise-0.482
n-0.472
lly-0.465
 else-0.462
Token it
Token ID340
Feature activation-1.42e-01

Pos logit contributions
ked+0.211
elt+0.207
arted+0.200
ed+0.195
 eyes+0.191
Neg logit contributions
 you-0.198
prise-0.191
uch-0.191
 happen-0.177
 achieve-0.167
Token.
Token ID13
Feature activation-1.76e-01

Pos logit contributions
 you+0.324
prise+0.305
uch+0.300
 happen+0.292
 achieve+0.270
Neg logit contributions
ked-0.222
elt-0.222
arted-0.205
 shrugged-0.196
ed-0.195
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
 you+0.385
prise+0.331
uch+0.318
n+0.318
 am+0.313
Neg logit contributions
ked-0.301
arted-0.261
elt-0.259
ashed-0.257
ened-0.256
Token shiny
Token ID22441
Feature activation+1.14e-01

Pos logit contributions
 you+0.185
prise+0.174
uch+0.172
 happen+0.171
 am+0.157
Neg logit contributions
ked-0.157
elt-0.154
arted-0.150
ed-0.142
ashed-0.142
Token in
Token ID287
Feature activation+1.04e-01

Pos logit contributions
elt+0.182
arted+0.181
ked+0.179
ashed+0.171
 arms+0.160
Neg logit contributions
 you-0.249
 happen-0.234
uch-0.229
prise-0.217
?-0.213
Token the
Token ID262
Feature activation+7.91e-03

Pos logit contributions
ked+0.162
elt+0.157
arted+0.153
 eyes+0.148
 arms+0.147
Neg logit contributions
 you-0.225
uch-0.225
prise-0.223
 happen-0.206
 achieve-0.199
Token sand
Token ID6450
Feature activation+6.02e-02

Pos logit contributions
ked+0.012
elt+0.011
arted+0.011
ed+0.010
ashed+0.010
Neg logit contributions
 you-0.019
uch-0.018
prise-0.018
 happen-0.017
 am-0.016
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
ked+0.130
elt+0.128
arted+0.124
ed+0.121
 eyes+0.119
Neg logit contributions
 you-0.097
prise-0.093
uch-0.093
 happen-0.085
 achieve-0.080
Token He
Token ID679
Feature activation+3.67e-01

Pos logit contributions
 you+0.409
uch+0.356
prise+0.354
 am+0.349
One+0.338
Neg logit contributions
ked-0.251
arted-0.226
ashed-0.226
ened-0.210
 asleep-0.205
Token picked
Token ID6497
Feature activation+1.74e-01

Pos logit contributions
elt+0.654
 asleep+0.642
arted+0.640
ked+0.635
itted+0.593
Neg logit contributions
 you-0.716
prise-0.646
lly-0.642
uch-0.642
 else-0.616
Token it
Token ID340
Feature activation-1.42e-01

Pos logit contributions
elt+0.472
ked+0.464
ashed+0.456
arted+0.454
 asleep+0.435
Neg logit contributions
 you-0.218
 happen-0.172
uch-0.157
prise-0.152
n-0.145
Token up
Token ID510
Feature activation+2.40e-01

Pos logit contributions
 you+0.329
 happen+0.296
uch+0.280
?+0.270
 ourselves+0.266
Neg logit contributions
ked-0.236
elt-0.234
arted-0.219
ashed-0.217
sed-0.206
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
elt+0.322
ked+0.320
arted+0.313
ashed+0.305
 floppy+0.274
Neg logit contributions
 you-0.601
uch-0.529
?-0.522
 happen-0.521
prise-0.519
Token It
Token ID632
Feature activation+2.35e-01

Pos logit contributions
 you+0.379
prise+0.326
uch+0.324
 am+0.320
n+0.312
Neg logit contributions
ked-0.281
arted-0.256
ashed-0.253
elt-0.239
ened-0.237
Token the
Token ID262
Feature activation+6.99e-03

Pos logit contributions
ked+0.225
elt+0.221
arted+0.211
ed+0.207
 eyes+0.204
Neg logit contributions
 you-0.241
uch-0.239
prise-0.237
 happen-0.219
 achieve-0.211
Token messy
Token ID24097
Feature activation+1.15e-01

Pos logit contributions
ked+0.014
elt+0.014
arted+0.014
ed+0.013
ashed+0.013
Neg logit contributions
 you-0.013
prise-0.012
uch-0.012
 happen-0.012
 am-0.011
Token living
Token ID2877
Feature activation+2.01e-02

Pos logit contributions
ked+0.222
arted+0.209
elt+0.207
ashed+0.182
ed+0.180
Neg logit contributions
 you-0.238
 happen-0.218
uch-0.215
prise-0.215
 am-0.206
Token room
Token ID2119
Feature activation+1.16e-01

Pos logit contributions
ked+0.036
elt+0.033
arted+0.033
 floppy+0.030
ashed+0.029
Neg logit contributions
 you-0.044
prise-0.041
uch-0.040
 am-0.038
 happen-0.038
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
ked+0.279
elt+0.274
arted+0.267
ed+0.257
ashed+0.255
Neg logit contributions
 you-0.163
prise-0.152
uch-0.151
 happen-0.142
 am-0.128
Token She
Token ID1375
Feature activation+2.62e-01

Pos logit contributions
 you+0.345
 am+0.298
?+0.285
One+0.266
"+0.265
Neg logit contributions
ked-0.331
arted-0.276
 armour-0.264
ened-0.260
 armor-0.255
Token was
Token ID373
Feature activation-3.97e-02

Pos logit contributions
ked+0.532
elt+0.504
arted+0.496
 asleep+0.495
 arms+0.476
Neg logit contributions
 you-0.480
prise-0.447
uch-0.410
 am-0.403
 happen-0.391
Token not
Token ID407
Feature activation-1.94e-01

Pos logit contributions
 you+0.072
prise+0.068
uch+0.065
 happen+0.061
 am+0.059
Neg logit contributions
ked-0.082
elt-0.080
arted-0.077
ashed-0.076
ed-0.076
Token happy
Token ID3772
Feature activation+6.47e-02

Pos logit contributions
 you+0.416
prise+0.404
uch+0.374
 happen+0.372
 am+0.354
Neg logit contributions
ked-0.334
elt-0.323
arted-0.317
ashed-0.298
ed-0.297
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
ked+0.146
elt+0.143
arted+0.139
ed+0.136
 eyes+0.134
Neg logit contributions
 you-0.100
prise-0.095
uch-0.095
 happen-0.087
 achieve-0.081
Token She
Token ID1375
Feature activation+2.61e-01

Pos logit contributions
 you+0.399
 am+0.338
?+0.324
One+0.311
"+0.303
Neg logit contributions
ked-0.286
arted-0.236
 asleep-0.224
ashed-0.221
ened-0.220
Token that
Token ID326
Feature activation-1.35e-01

Pos logit contributions
ked+0.038
elt+0.038
arted+0.037
ed+0.035
ashed+0.035
Neg logit contributions
 you-0.034
prise-0.032
uch-0.031
 happen-0.030
 achieve-0.028
Token sharing
Token ID7373
Feature activation-7.21e-02

Pos logit contributions
 you+0.253
prise+0.238
uch+0.236
 happen+0.226
 achieve+0.209
Neg logit contributions
ked-0.267
elt-0.262
arted-0.253
ed-0.246
ashed-0.241
Token is
Token ID318
Feature activation-2.12e-01

Pos logit contributions
 you+0.125
uch+0.125
prise+0.125
 happen+0.110
w+0.106
Neg logit contributions
ked-0.142
elt-0.139
ed-0.134
arted-0.133
 eyes-0.133
Token caring
Token ID18088
Feature activation-1.71e-01

Pos logit contributions
uch+0.402
prise+0.385
 you+0.365
w+0.344
arest+0.331
Neg logit contributions
ked-0.399
 confused-0.383
elt-0.377
 eyes-0.373
arted-0.369
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
uch+0.354
prise+0.351
 you+0.332
w+0.306
 achieve+0.304
Neg logit contributions
ked-0.287
 eyes-0.279
elt-0.278
ed-0.278
 arms-0.271
Token They
Token ID1119
Feature activation+2.33e-01

Pos logit contributions
uch+0.462
prise+0.449
 you+0.437
 happen+0.431
w+0.415
Neg logit contributions
elt-0.219
ked-0.212
 eyes-0.198
 arms-0.190
arted-0.190
Token learned
Token ID4499
Feature activation+1.90e-02

Pos logit contributions
ked+0.390
elt+0.371
arted+0.357
ed+0.354
 eyes+0.346
Neg logit contributions
 you-0.489
uch-0.480
prise-0.478
 happen-0.444
w-0.423
Token that
Token ID326
Feature activation-1.35e-01

Pos logit contributions
ked+0.039
elt+0.039
arted+0.038
ed+0.036
ashed+0.036
Neg logit contributions
 you-0.034
prise-0.032
uch-0.031
 happen-0.030
 achieve-0.028
Token welcoming
Token ID22516
Feature activation-4.20e-02

Pos logit contributions
 you+0.252
prise+0.244
uch+0.243
 happen+0.225
 achieve+0.213
Neg logit contributions
ked-0.258
elt-0.253
arted-0.243
ed-0.238
 eyes-0.234
Token is
Token ID318
Feature activation-2.11e-01

Pos logit contributions
 you+0.069
prise+0.067
uch+0.067
 happen+0.061
 achieve+0.058
Neg logit contributions
ked-0.089
elt-0.087
arted-0.084
ed-0.083
 eyes-0.082
Token loving
Token ID14442
Feature activation-4.59e-04

Pos logit contributions
uch+0.437
prise+0.420
 you+0.403
w+0.379
arest+0.369
Neg logit contributions
ked-0.362
 confused-0.341
elt-0.340
 eyes-0.338
arted-0.333
Token shook
Token ID14682
Feature activation+2.76e-01

Pos logit contributions
elt+0.208
ked+0.198
arted+0.196
 asleep+0.194
ashed+0.188
Neg logit contributions
 you-0.222
uch-0.203
prise-0.199
n-0.188
ggy-0.185
Token his
Token ID465
Feature activation+1.62e-01

Pos logit contributions
elt+0.612
ashed+0.592
itted+0.539
ked+0.535
attered+0.507
Neg logit contributions
 you-0.521
 happen-0.425
?-0.415
 us-0.395
 ourselves-0.382
Token head
Token ID1182
Feature activation+2.47e-01

Pos logit contributions
elt+0.314
arted+0.296
ashed+0.294
ked+0.280
ed+0.269
Neg logit contributions
 you-0.294
uch-0.290
ggy-0.284
 happen-0.281
 promise-0.277
Token and
Token ID290
Feature activation+2.81e-01

Pos logit contributions
elt+0.366
arted+0.361
ashed+0.343
ked+0.324
 eyes+0.309
Neg logit contributions
 you-0.549
uch-0.522
 happen-0.495
gh-0.486
?-0.466
Token kept
Token ID4030
Feature activation+1.12e-01

Pos logit contributions
elt+0.568
arted+0.542
itted+0.535
ashed+0.531
ked+0.524
Neg logit contributions
 you-0.539
 happen-0.442
prise-0.438
uch-0.434
n-0.411
Token walking
Token ID6155
Feature activation+1.95e-01

Pos logit contributions
elt+0.175
ked+0.175
ashed+0.166
arted+0.161
ed+0.160
Neg logit contributions
 you-0.256
prise-0.239
uch-0.233
 happen-0.227
 achieve-0.215
Token.
Token ID13
Feature activation-1.58e-01

Pos logit contributions
elt+0.425
ked+0.418
arted+0.392
ashed+0.385
 eyes+0.379
Neg logit contributions
 you-0.331
prise-0.294
uch-0.286
 happen-0.281
 am-0.264
Token He
Token ID679
Feature activation+3.66e-01

Pos logit contributions
 you+0.352
 achieve+0.294
n+0.291
One+0.290
".+0.281
Neg logit contributions
ked-0.244
ashed-0.211
elt-0.201
ed-0.200
ened-0.199
Token wanted
Token ID2227
Feature activation+1.52e-01

Pos logit contributions
elt+0.699
ked+0.659
 asleep+0.639
arted+0.637
 eyes+0.620
Neg logit contributions
 you-0.692
uch-0.647
n-0.611
prise-0.609
lly-0.605
Token to
Token ID284
Feature activation+1.75e-01

Pos logit contributions
ked+0.234
elt+0.223
arted+0.213
ashed+0.212
ed+0.204
Neg logit contributions
 you-0.372
prise-0.330
 happen-0.327
uch-0.326
n-0.305
Token laugh
Token ID6487
Feature activation-4.25e-02

Pos logit contributions
 down+0.298
 eyes+0.296
 confused+0.288
 arms+0.279
 shrugged+0.279
Neg logit contributions
prise-0.324
uch-0.322
w-0.306
arest-0.284
 you-0.273
Token to
Token ID284
Feature activation+1.66e-01

Pos logit contributions
ked+0.297
elt+0.276
arted+0.260
ashed+0.257
ed+0.256
Neg logit contributions
 you-0.450
 happen-0.413
prise-0.407
uch-0.403
 am-0.395
Token cry
Token ID3960
Feature activation-4.67e-02

Pos logit contributions
ked+0.331
elt+0.324
arted+0.310
ed+0.306
ashed+0.299
Neg logit contributions
 you-0.303
prise-0.288
uch-0.287
 happen-0.274
 achieve-0.256
Token.
Token ID13
Feature activation-1.72e-01

Pos logit contributions
 you+0.060
prise+0.051
uch+0.050
 happen+0.049
 am+0.043
Neg logit contributions
ked-0.118
elt-0.118
arted-0.116
ashed-0.111
ed-0.110
Token mummy
Token ID38567
Feature activation-3.17e-02

Pos logit contributions
 you+0.414
uch+0.346
prise+0.343
One+0.343
 am+0.342
Neg logit contributions
ked-0.263
ashed-0.229
arted-0.220
ed-0.219
elt-0.216
Token said
Token ID531
Feature activation+2.28e-02

Pos logit contributions
 you+0.067
prise+0.062
uch+0.060
 happen+0.056
n+0.056
Neg logit contributions
ked-0.054
elt-0.053
ashed-0.049
arted-0.049
itted-0.047
Token,
Token ID11
Feature activation-4.97e-03

Pos logit contributions
ked+0.046
elt+0.046
arted+0.045
ashed+0.043
 arms+0.042
Neg logit contributions
 you-0.042
prise-0.037
uch-0.037
 happen-0.036
 am-0.033
Token "
Token ID366
Feature activation+2.90e-01

Pos logit contributions
 you+0.014
prise+0.012
 happen+0.012
n+0.012
uch+0.012
Neg logit contributions
ked-0.006
arted-0.005
ashed-0.005
elt-0.005
ed-0.005
Tokenit
Token ID270
Feature activation-1.10e-01

Pos logit contributions
elt+0.544
ked+0.510
arted+0.505
ed+0.480
 shrugged+0.457
Neg logit contributions
prise-0.559
uch-0.551
 happen-0.547
 you-0.527
 achieve-0.504
Token's
Token ID338
Feature activation+7.21e-03

Pos logit contributions
 you+0.222
prise+0.219
uch+0.215
 happen+0.203
 achieve+0.194
Neg logit contributions
ked-0.189
elt-0.185
arted-0.177
ed-0.176
 eyes-0.171
Token OK
Token ID7477
Feature activation-1.80e-01

Pos logit contributions
 eyes+0.013
elt+0.013
 confused+0.013
ked+0.013
arted+0.013
Neg logit contributions
prise-0.013
uch-0.013
 you-0.012
 achieve-0.012
arest-0.012
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
uch+0.387
prise+0.384
 you+0.375
 achieve+0.358
 happen+0.358
Neg logit contributions
elt-0.285
ked-0.279
 eyes-0.272
ed-0.267
arted-0.261
Token Lily
Token ID20037
Feature activation+7.96e-02

Pos logit contributions
 you+0.001
prise+0.001
uch+0.001
 happen+0.001
 am+0.001
Neg logit contributions
ked-0.001
elt-0.001
arted-0.001
ashed-0.001
ed-0.001
Token went
Token ID1816
Feature activation+1.42e-01

Pos logit contributions
ked+0.138
elt+0.133
arted+0.129
ashed+0.119
ed+0.118
Neg logit contributions
 you-0.170
uch-0.160
prise-0.156
 happen-0.148
 achieve-0.144
Token to
Token ID284
Feature activation+1.70e-01

Pos logit contributions
ked+0.243
elt+0.223
arted+0.208
 shrugged+0.202
ashed+0.200
Neg logit contributions
 you-0.331
prise-0.299
 happen-0.285
uch-0.275
 achieve-0.274
Token bed
Token ID3996
Feature activation+3.34e-02

Pos logit contributions
ked+0.243
elt+0.241
 asleep+0.237
 eyes+0.237
arted+0.234
Neg logit contributions
uch-0.385
prise-0.371
 you-0.369
w-0.346
 happen-0.338
Token with
Token ID351
Feature activation+1.96e-02

Pos logit contributions
ked+0.054
elt+0.053
arted+0.053
ashed+0.048
 floppy+0.047
Neg logit contributions
 you-0.075
uch-0.069
prise-0.068
 happen-0.068
 achieve-0.065
Token her
Token ID607
Feature activation+4.12e-02

Pos logit contributions
ked+0.026
elt+0.026
 eyes+0.026
 arms+0.025
 asleep+0.025
Neg logit contributions
uch-0.046
 you-0.045
prise-0.045
 happen-0.042
 achieve-0.041
Token tooth
Token ID16162
Feature activation+8.89e-02

Pos logit contributions
ked+0.067
elt+0.066
arted+0.063
ed+0.061
 eyes+0.059
Neg logit contributions
 you-0.089
prise-0.086
uch-0.086
 happen-0.081
 achieve-0.077
Token under
Token ID739
Feature activation+2.35e-01

Pos logit contributions
arted+0.156
ked+0.154
elt+0.152
ashed+0.139
 confused+0.136
Neg logit contributions
 you-0.181
uch-0.174
prise-0.169
 happen-0.162
ggy-0.152
Token her
Token ID607
Feature activation+4.13e-02

Pos logit contributions
ked+0.344
elt+0.337
 eyes+0.330
 arms+0.325
arted+0.321
Neg logit contributions
uch-0.529
prise-0.526
 you-0.523
 happen-0.481
w-0.472
Token pillow
Token ID28774
Feature activation+5.58e-02

Pos logit contributions
ked+0.074
elt+0.072
arted+0.070
ed+0.068
ashed+0.067
Neg logit contributions
 you-0.086
uch-0.081
prise-0.080
 happen-0.077
 achieve-0.072
Token.
Token ID13
Feature activation-1.65e-01

Pos logit contributions
elt+0.128
ked+0.127
arted+0.125
ed+0.118
ashed+0.117
Neg logit contributions
 you-0.083
uch-0.075
prise-0.073
 happen-0.070
 achieve-0.063
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
ked+0.153
elt+0.150
arted+0.143
ed+0.143
 arms+0.140
Neg logit contributions
 you-0.124
prise-0.123
uch-0.123
 happen-0.111
w-0.106
Token He
Token ID679
Feature activation+3.61e-01

Pos logit contributions
 you+0.376
 am+0.351
?+0.325
 happen+0.318
prise+0.315
Neg logit contributions
ked-0.266
arted-0.245
elt-0.220
ashed-0.217
ed-0.215
Token finds
Token ID7228
Feature activation+1.11e-01

Pos logit contributions
ked+0.791
elt+0.765
arted+0.749
ed+0.692
ashed+0.692
Neg logit contributions
 you-0.656
prise-0.579
uch-0.555
 happen-0.545
 am-0.545
Token a
Token ID257
Feature activation+5.92e-02

Pos logit contributions
ked+0.216
elt+0.214
arted+0.211
ashed+0.202
 shrugged+0.191
Neg logit contributions
 you-0.217
prise-0.190
uch-0.175
 happen-0.174
w-0.165
Token red
Token ID2266
Feature activation+2.77e-01

Pos logit contributions
ked+0.097
elt+0.094
arted+0.091
ed+0.088
ashed+0.085
Neg logit contributions
 you-0.128
prise-0.125
uch-0.123
 happen-0.117
 am-0.111
Token balloon
Token ID21190
Feature activation+3.64e-02

Pos logit contributions
ked+0.469
elt+0.458
arted+0.456
ed+0.428
ashed+0.420
Neg logit contributions
 you-0.588
prise-0.559
uch-0.557
 happen-0.527
 am-0.503
Token in
Token ID287
Feature activation+9.61e-02

Pos logit contributions
ked+0.069
elt+0.068
arted+0.068
ashed+0.064
ed+0.062
Neg logit contributions
 you-0.072
uch-0.065
prise-0.064
 happen-0.063
 am-0.058
Token his
Token ID465
Feature activation+1.49e-01

Pos logit contributions
ked+0.112
elt+0.108
arted+0.102
 eyes+0.100
ed+0.099
Neg logit contributions
uch-0.249
 you-0.247
prise-0.244
 happen-0.230
 achieve-0.224
Token room
Token ID2119
Feature activation+1.10e-01

Pos logit contributions
ked+0.224
arted+0.215
elt+0.203
ed+0.195
ashed+0.189
Neg logit contributions
 you-0.366
uch-0.343
prise-0.343
 am-0.314
 happen-0.304
Token.
Token ID13
Feature activation-1.68e-01

Pos logit contributions
ked+0.250
elt+0.247
arted+0.238
ed+0.236
 eyes+0.232
Neg logit contributions
 you-0.164
prise-0.159
uch-0.158
 happen-0.144
 achieve-0.133
Token He
Token ID679
Feature activation+3.61e-01

Pos logit contributions
 you+0.384
 am+0.326
?+0.318
prise+0.298
 happen+0.298
Neg logit contributions
ked-0.278
arted-0.250
elt-0.227
ashed-0.224
 asleep-0.220
Token wh
Token ID348
Feature activation+1.17e-01

Pos logit contributions
 you+0.382
n+0.319
One+0.315
uch+0.312
prise+0.304
Neg logit contributions
ked-0.270
elt-0.239
arted-0.233
ed-0.227
ashed-0.226
Tokenips
Token ID2419
Feature activation-4.32e-02

Pos logit contributions
arted+0.224
ked+0.203
pered+0.199
elt+0.195
 confused+0.194
Neg logit contributions
prise-0.223
 happen-0.215
 you-0.214
uch-0.203
 am-0.193
Token were
Token ID547
Feature activation-6.15e-02

Pos logit contributions
 you+0.094
uch+0.087
prise+0.086
 happen+0.084
 achieve+0.079
Neg logit contributions
ked-0.070
elt-0.070
arted-0.065
 eyes-0.062
ed-0.061
Token dangerous
Token ID4923
Feature activation-1.66e-01

Pos logit contributions
 you+0.148
prise+0.138
uch+0.137
 happen+0.132
 achieve+0.126
Neg logit contributions
ked-0.088
elt-0.087
arted-0.079
ed-0.078
ashed-0.076
Token and
Token ID290
Feature activation+2.47e-01

Pos logit contributions
 you+0.363
 happen+0.331
uch+0.329
prise+0.325
 am+0.306
Neg logit contributions
ked-0.278
elt-0.267
arted-0.255
ashed-0.245
ed-0.242
Token he
Token ID339
Feature activation+2.42e-02

Pos logit contributions
ked+0.445
elt+0.437
arted+0.415
ed+0.401
ashed+0.395
Neg logit contributions
 you-0.514
uch-0.470
prise-0.462
 happen-0.448
 am-0.426
Token told
Token ID1297
Feature activation-2.87e-02

Pos logit contributions
ked+0.042
elt+0.041
arted+0.040
ed+0.038
 eyes+0.037
Neg logit contributions
 you-0.050
uch-0.048
prise-0.047
 happen-0.045
 am-0.043
Token his
Token ID465
Feature activation+1.50e-01

Pos logit contributions
 you+0.064
prise+0.062
uch+0.061
 happen+0.058
 achieve+0.055
Neg logit contributions
ked-0.045
elt-0.044
arted-0.042
ed-0.041
 eyes-0.040
Token friend
Token ID1545
Feature activation+4.63e-03

Pos logit contributions
ked+0.226
elt+0.222
arted+0.211
 eyes+0.211
ed+0.207
Neg logit contributions
 you-0.331
uch-0.329
prise-0.326
 happen-0.304
 achieve-0.293
Token to
Token ID284
Feature activation+1.61e-01

Pos logit contributions
ked+0.008
elt+0.008
arted+0.008
ed+0.007
ashed+0.007
Neg logit contributions
 you-0.010
prise-0.009
uch-0.009
 happen-0.009
 am-0.008
Token put
Token ID1234
Feature activation+3.68e-03

Pos logit contributions
ked+0.318
 eyes+0.316
 shrugged+0.309
 arms+0.300
arted+0.300
Neg logit contributions
prise-0.257
uch-0.254
arest-0.238
w-0.228
 you-0.216
Token colors
Token ID7577
Feature activation+8.19e-02

Pos logit contributions
elt+0.014
ked+0.014
ed+0.013
 arms+0.013
arted+0.013
Neg logit contributions
 you-0.022
uch-0.022
prise-0.022
 happen-0.021
 achieve-0.020
Token together
Token ID1978
Feature activation-9.62e-03

Pos logit contributions
ked+0.157
elt+0.153
arted+0.148
ed+0.143
 eyes+0.140
Neg logit contributions
 you-0.155
prise-0.146
uch-0.146
 happen-0.139
 achieve-0.130
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
 you+0.015
prise+0.014
uch+0.014
 happen+0.013
w+0.012
Neg logit contributions
ked-0.021
elt-0.021
arted-0.020
ed-0.020
 eyes-0.020
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
 you+0.365
One+0.303
 achieve+0.302
uch+0.294
n+0.294
Neg logit contributions
ked-0.294
elt-0.268
arted-0.256
ened-0.251
 asleep-0.251
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
uch+0.306
prise+0.306
 happen+0.290
 you+0.287
w+0.269
Neg logit contributions
 He-0.182
elt-0.181
ed-0.175
arted-0.172
ked-0.164
Token"
Token ID1
Feature activation-3.57e-01

Pos logit contributions
prise+0.202
 you+0.201
uch+0.197
 happen+0.186
 am+0.166
Neg logit contributions
ked-0.296
elt-0.288
arted-0.284
ed-0.277
ashed-0.272
TokenWhat
Token ID2061
Feature activation-1.69e-01

Pos logit contributions
prise+0.716
 you+0.709
uch+0.709
 happen+0.689
vern+0.651
Neg logit contributions
elt-0.647
ked-0.608
arted-0.578
ed-0.561
ashed-0.553
Token a
Token ID257
Feature activation+6.64e-02

Pos logit contributions
uch+0.270
prise+0.262
 you+0.249
arest+0.236
w+0.234
Neg logit contributions
 eyes-0.334
elt-0.330
ed-0.307
 confused-0.305
ked-0.302
Token strange
Token ID6283
Feature activation-3.93e-02

Pos logit contributions
elt+0.117
 wooden+0.113
 confused+0.112
 eyes+0.112
 floppy+0.111
Neg logit contributions
uch-0.122
 you-0.116
prise-0.114
w-0.109
 happen-0.108
Token mix
Token ID5022
Feature activation-6.52e-02

Pos logit contributions
 you+0.075
prise+0.072
uch+0.071
 happen+0.067
 am+0.063
Neg logit contributions
ked-0.075
elt-0.073
arted-0.071
ed-0.068
ashed-0.067
Token,"
Token ID553
Feature activation-2.91e-01

Pos logit contributions
prise+0.090
uch+0.088
 you+0.081
 achieve+0.074
vern+0.074
Neg logit contributions
elt-0.147
ed-0.144
 down-0.142
 arms-0.139
 eyes-0.138
Token park
Token ID3952
Feature activation-8.03e-02

Pos logit contributions
ked+0.027
elt+0.027
arted+0.026
 eyes+0.025
ed+0.025
Neg logit contributions
 you-0.029
uch-0.028
prise-0.028
 happen-0.026
w-0.025
Token.
Token ID13
Feature activation-1.62e-01

Pos logit contributions
 you+0.155
prise+0.149
uch+0.149
 happen+0.139
 achieve+0.131
Neg logit contributions
ked-0.150
elt-0.147
arted-0.141
ed-0.138
 eyes-0.135
Token
Token ID220
Feature activation+3.23e-02

Pos logit contributions
 you+0.325
prise+0.290
uch+0.287
 happen+0.276
 am+0.272
Neg logit contributions
ked-0.300
elt-0.282
arted-0.282
ed-0.266
 eyes-0.260
Token
Token ID198
Feature activation-1.23e-01

Pos logit contributions
elt+0.052
ed+0.049
arted+0.047
ked+0.047
 down+0.046
Neg logit contributions
uch-0.070
prise-0.070
 you-0.066
 happen-0.066
w-0.062
Token
Token ID198
Feature activation-1.23e-01

Pos logit contributions
uch+0.309
prise+0.290
 happen+0.282
 you+0.270
w+0.266
Neg logit contributions
elt-0.160
ed-0.153
 He-0.151
 down-0.148
 arms-0.139
TokenL
Token ID43
Feature activation-2.71e-01

Pos logit contributions
uch+0.201
prise+0.189
 happen+0.188
 you+0.175
 ourselves+0.168
Neg logit contributions
elt-0.259
ashed-0.259
ed-0.250
ked-0.249
 down-0.245
Tokenily
Token ID813
Feature activation-1.16e-01

Pos logit contributions
 you+0.484
uch+0.477
prise+0.464
 happen+0.439
 achieve+0.423
Neg logit contributions
elt-0.529
ked-0.526
ed-0.512
arted-0.511
ashed-0.499
Token said
Token ID531
Feature activation+3.86e-02

Pos logit contributions
 you+0.210
uch+0.192
prise+0.183
n+0.182
ggy+0.176
Neg logit contributions
ked-0.237
elt-0.231
 asleep-0.227
arted-0.223
pered-0.208
Token,
Token ID11
Feature activation+2.16e-03

Pos logit contributions
ked+0.073
elt+0.071
arted+0.071
ed+0.066
 arms+0.066
Neg logit contributions
 you-0.075
uch-0.070
prise-0.070
 happen-0.066
 am-0.062
Token "
Token ID366
Feature activation+3.02e-01

Pos logit contributions
arted+0.003
ked+0.003
ashed+0.003
elt+0.003
ened+0.003
Neg logit contributions
 you-0.005
 happen-0.004
n-0.004
uch-0.004
prise-0.004
TokenYes
Token ID5297
Feature activation-1.70e-01

Pos logit contributions
elt+0.678
ked+0.603
ed+0.575
ashed+0.564
arted+0.561
Neg logit contributions
 happen-0.499
prise-0.489
uch-0.481
 you-0.456
 achieve-0.450
Token hopped
Token ID45230
Feature activation+2.17e-01

Pos logit contributions
ked+0.171
elt+0.170
arted+0.156
 eyes+0.154
 arms+0.147
Neg logit contributions
 you-0.323
prise-0.312
uch-0.311
 happen-0.298
 am-0.285
Token in
Token ID287
Feature activation+1.05e-01

Pos logit contributions
elt+0.334
ked+0.319
arted+0.299
 eyes+0.299
 shrugged+0.296
Neg logit contributions
 you-0.512
prise-0.457
uch-0.446
 happen-0.445
n-0.429
Token!
Token ID0
Feature activation-2.16e-01

Pos logit contributions
ked+0.187
elt+0.183
arted+0.175
ed+0.171
 eyes+0.167
Neg logit contributions
 you-0.211
prise-0.204
uch-0.203
 happen-0.191
 achieve-0.180
Token
Token ID198
Feature activation-1.31e-01

Pos logit contributions
 you+0.382
 am+0.314
prise+0.312
n+0.300
uch+0.298
Neg logit contributions
ked-0.451
elt-0.405
 eyes-0.401
 shrugged-0.399
arted-0.396
Token
Token ID198
Feature activation-1.31e-01

Pos logit contributions
uch+0.310
prise+0.302
 happen+0.292
 you+0.287
w+0.264
Neg logit contributions
ed-0.182
elt-0.181
 He-0.173
arted-0.169
ashed-0.165
TokenThe
Token ID464
Feature activation-2.63e-01

Pos logit contributions
uch+0.207
prise+0.205
 you+0.203
 happen+0.200
 ourselves+0.167
Neg logit contributions
elt-0.277
ked-0.277
arted-0.271
ashed-0.270
ed-0.268
Token car
Token ID1097
Feature activation+1.24e-01

Pos logit contributions
 you+0.633
prise+0.600
uch+0.571
 happen+0.570
 am+0.554
Neg logit contributions
elt-0.366
ked-0.362
arted-0.342
ed-0.323
ashed-0.315
Token drove
Token ID10357
Feature activation+2.19e-01

Pos logit contributions
elt+0.254
arted+0.241
ked+0.234
 eyes+0.227
 asleep+0.223
Neg logit contributions
 you-0.212
uch-0.206
n-0.198
ggy-0.190
 happen-0.180
Token around
Token ID1088
Feature activation+2.96e-01

Pos logit contributions
elt+0.413
ked+0.361
arted+0.337
 shrugged+0.335
sed+0.335
Neg logit contributions
 you-0.477
 happen-0.402
n-0.390
prise-0.388
gh-0.378
Token town
Token ID3240
Feature activation-5.29e-02

Pos logit contributions
elt+0.561
ked+0.559
arted+0.525
ashed+0.508
 eyes+0.501
Neg logit contributions
 you-0.592
prise-0.536
uch-0.515
 happen-0.515
 am-0.492
Token,
Token ID11
Feature activation-2.09e-04

Pos logit contributions
 you+0.093
 happen+0.079
 achieve+0.078
uch+0.076
prise+0.075
Neg logit contributions
elt-0.110
ked-0.106
arted-0.105
 floppy-0.100
ashed-0.100
Token a
Token ID257
Feature activation+5.47e-02

Pos logit contributions
 you+0.441
prise+0.428
uch+0.427
 happen+0.399
 achieve+0.379
Neg logit contributions
ked-0.376
elt-0.368
arted-0.352
ed-0.344
 eyes-0.338
Token birthday
Token ID10955
Feature activation-1.32e-01

Pos logit contributions
elt+0.090
 eyes+0.090
ked+0.090
 confused+0.088
 wooden+0.088
Neg logit contributions
uch-0.106
 you-0.100
prise-0.097
 achieve-0.095
 happen-0.093
Token cake
Token ID12187
Feature activation-1.19e-01

Pos logit contributions
uch+0.238
 you+0.223
prise+0.218
 achieve+0.216
 happen+0.208
Neg logit contributions
elt-0.251
ked-0.241
ed-0.240
 eyes-0.239
 asleep-0.232
Token!"
Token ID2474
Feature activation-3.79e-01

Pos logit contributions
uch+0.154
prise+0.148
 you+0.144
 achieve+0.133
vern+0.130
Neg logit contributions
elt-0.274
ked-0.270
ed-0.270
 down-0.265
 asleep-0.262
Token
Token ID198
Feature activation-1.40e-01

Pos logit contributions
 you+0.606
prise+0.570
uch+0.561
 happen+0.521
 achieve+0.487
Neg logit contributions
ked-0.847
elt-0.830
arted-0.804
ed-0.784
ashed-0.770
Token
Token ID198
Feature activation-1.40e-01

Pos logit contributions
uch+0.366
prise+0.341
 happen+0.317
w+0.307
 you+0.307
Neg logit contributions
 He-0.187
 eyes-0.177
elt-0.168
 arms-0.167
ed-0.166
TokenThey
Token ID2990
Feature activation-2.69e-01

Pos logit contributions
uch+0.295
 happen+0.273
prise+0.260
 you+0.237
 belong+0.235
Neg logit contributions
ed-0.233
 He-0.233
 arms-0.232
ked-0.230
elt-0.226
Token take
Token ID1011
Feature activation-1.87e-01

Pos logit contributions
 you+0.451
prise+0.432
uch+0.422
 happen+0.398
 achieve+0.376
Neg logit contributions
elt-0.568
ked-0.566
arted-0.542
ed-0.530
 arms-0.515
Token a
Token ID257
Feature activation+5.50e-02

Pos logit contributions
 you+0.342
prise+0.289
uch+0.277
 happen+0.269
 ourselves+0.263
Neg logit contributions
elt-0.393
arted-0.384
ked-0.381
 shrugged-0.367
sed-0.354
Token big
Token ID1263
Feature activation+2.23e-02

Pos logit contributions
ked+0.106
elt+0.104
arted+0.100
ed+0.098
 eyes+0.096
Neg logit contributions
 you-0.102
prise-0.098
uch-0.098
 happen-0.091
 achieve-0.086
Token bite
Token ID13197
Feature activation-1.73e-01

Pos logit contributions
ked+0.055
elt+0.055
arted+0.054
ed+0.051
ashed+0.051
Neg logit contributions
 you-0.030
prise-0.029
uch-0.028
 happen-0.026
w-0.023
Token hunter
Token ID19177
Feature activation+1.53e-01

Pos logit contributions
ked+0.003
elt+0.003
arted+0.003
ed+0.003
 eyes+0.003
Neg logit contributions
 you-0.007
prise-0.007
uch-0.007
 happen-0.007
 achieve-0.006
Token away
Token ID1497
Feature activation+1.88e-02

Pos logit contributions
ked+0.279
elt+0.265
arted+0.260
ed+0.258
 arms+0.253
Neg logit contributions
uch-0.293
 you-0.292
prise-0.291
 happen-0.262
w-0.257
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
ked+0.043
elt+0.043
arted+0.041
ed+0.040
ashed+0.040
Neg logit contributions
 you-0.029
prise-0.027
uch-0.026
 happen-0.025
 am-0.023
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
 you+0.279
prise+0.232
uch+0.222
 am+0.217
 achieve+0.216
Neg logit contributions
ked-0.408
elt-0.383
arted-0.370
 asleep-0.370
 floppy-0.367
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
uch+0.337
prise+0.329
 happen+0.317
 you+0.308
w+0.289
Neg logit contributions
 He-0.176
elt-0.170
ed-0.169
arted-0.163
 confused-0.154
TokenThe
Token ID464
Feature activation-2.67e-01

Pos logit contributions
prise+0.203
 happen+0.202
uch+0.199
 you+0.190
 ourselves+0.157
Neg logit contributions
elt-0.299
ked-0.297
arted-0.294
ashed-0.292
ed-0.289
Token rabbit
Token ID22746
Feature activation+2.42e-01

Pos logit contributions
 you+0.687
prise+0.679
uch+0.678
 happen+0.640
 achieve+0.618
Neg logit contributions
ked-0.325
elt-0.308
arted-0.294
ed-0.283
 eyes-0.279
Token said
Token ID531
Feature activation+2.47e-02

Pos logit contributions
elt+0.492
ked+0.455
arted+0.447
itted+0.432
 asleep+0.431
Neg logit contributions
 you-0.447
uch-0.398
n-0.391
ggy-0.388
 course-0.373
Token,
Token ID11
Feature activation-1.03e-02

Pos logit contributions
arted+0.048
elt+0.048
ked+0.046
 arms+0.044
ashed+0.044
Neg logit contributions
 you-0.047
 happen-0.039
gh-0.038
prise-0.038
ggy-0.037
Token "
Token ID366
Feature activation+2.93e-01

Pos logit contributions
 you+0.027
 happen+0.022
One+0.022
n+0.022
prise+0.022
Neg logit contributions
arted-0.013
ashed-0.012
elt-0.012
ked-0.012
ened-0.011
TokenI
Token ID40
Feature activation-2.72e-01

Pos logit contributions
elt+0.627
ked+0.610
arted+0.589
ed+0.585
ashed+0.550
Neg logit contributions
prise-0.503
 happen-0.491
uch-0.477
 you-0.453
vern-0.431
Token asked
Token ID1965
Feature activation+5.86e-02

Pos logit contributions
 you+0.437
uch+0.393
n+0.375
prise+0.366
lly+0.362
Neg logit contributions
elt-0.428
ked-0.425
arted-0.393
 eyes-0.391
 asleep-0.376
Token,
Token ID11
Feature activation-4.25e-03

Pos logit contributions
elt+0.113
ked+0.112
arted+0.103
ashed+0.103
 arms+0.099
Neg logit contributions
 you-0.116
prise-0.104
 happen-0.100
uch-0.095
 am-0.093
Token "
Token ID366
Feature activation+2.92e-01

Pos logit contributions
 you+0.012
prise+0.011
uch+0.010
 happen+0.010
 am+0.010
Neg logit contributions
ked-0.005
arted-0.004
elt-0.004
ashed-0.004
ed-0.004
TokenWhat
Token ID2061
Feature activation-1.68e-01

Pos logit contributions
elt+0.567
ked+0.563
arted+0.523
ed+0.506
 shrugged+0.477
Neg logit contributions
 happen-0.542
uch-0.535
 you-0.520
prise-0.515
vern-0.474
Token do
Token ID466
Feature activation-3.10e-01

Pos logit contributions
prise+0.275
uch+0.267
 you+0.266
 happen+0.244
arest+0.241
Neg logit contributions
elt-0.330
 eyes-0.319
ed-0.318
ked-0.318
 confused-0.306
Token you
Token ID345
Feature activation-5.84e-01

Pos logit contributions
prise+0.243
uch+0.209
 achieve+0.181
vern+0.167
arest+0.152
Neg logit contributions
elt-0.838
 eyes-0.834
 arms-0.822
ed-0.815
 floppy-0.799
Token have
Token ID423
Feature activation-2.93e-01

Pos logit contributions
 you+0.946
prise+0.928
uch+0.905
 happen+0.835
w+0.783
Neg logit contributions
ked-1.228
elt-1.211
arted-1.172
 confused-1.161
ed-1.150
Token in
Token ID287
Feature activation+1.06e-01

Pos logit contributions
prise+0.589
uch+0.580
 you+0.570
 happen+0.551
 achieve+0.531
Neg logit contributions
elt-0.484
ked-0.465
ed-0.458
 eyes-0.437
arted-0.433
Token your
Token ID534
Feature activation-2.82e-01

Pos logit contributions
ked+0.187
elt+0.184
arted+0.179
 arms+0.176
 eyes+0.176
Neg logit contributions
uch-0.200
prise-0.199
 you-0.198
 happen-0.182
 achieve-0.175
Token bag
Token ID6131
Feature activation+2.47e-01

Pos logit contributions
 you+0.655
prise+0.606
uch+0.601
 happen+0.563
 am+0.558
Neg logit contributions
ked-0.466
elt-0.437
arted-0.433
ed-0.415
ashed-0.398
Token?"
Token ID1701
Feature activation-4.10e-01

Pos logit contributions
ked+0.752
elt+0.741
arted+0.725
ed+0.713
 eyes+0.704
Neg logit contributions
 you-0.182
uch-0.163
prise-0.163
 happen-0.132
 achieve-0.109
Tokenbr
Token ID1671
Feature activation-2.08e-01

Pos logit contributions
 ourselves+0.615
uch+0.611
prise+0.608
 you+0.590
 achieve+0.576
Neg logit contributions
 wooden-0.434
 eyes-0.430
elt-0.421
 floppy-0.415
ked-0.411
Tokenac
Token ID330
Feature activation-7.98e-02

Pos logit contributions
 you+0.426
 happen+0.399
uch+0.395
prise+0.375
 achieve+0.363
Neg logit contributions
ked-0.379
elt-0.368
ed-0.352
 eyes-0.345
ashed-0.339
Tokenad
Token ID324
Feature activation-1.70e-01

Pos logit contributions
prise+0.145
 you+0.142
 achieve+0.136
arest+0.129
uch+0.129
Neg logit contributions
ed-0.149
 eyes-0.146
ked-0.144
arted-0.144
elt-0.142
Tokenab
Token ID397
Feature activation+1.30e-02

Pos logit contributions
prise+0.379
uch+0.370
 you+0.370
 ourselves+0.359
 achieve+0.356
Neg logit contributions
ked-0.237
ed-0.232
elt-0.221
 down-0.207
 asleep-0.206
Tokenra
Token ID430
Feature activation-1.63e-01

Pos logit contributions
ked+0.028
ed+0.026
elt+0.026
 eyes+0.025
 arms+0.024
Neg logit contributions
prise-0.022
 you-0.021
uch-0.020
 happen-0.020
 achieve-0.019
Token!"
Token ID2474
Feature activation-3.84e-01

Pos logit contributions
prise+0.289
 you+0.270
 achieve+0.267
uch+0.263
 ourselves+0.257
Neg logit contributions
ed-0.330
ked-0.327
 down-0.283
 eyes-0.281
ened-0.278
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
 you+0.480
prise+0.374
 am+0.355
uch+0.349
 happen+0.336
Neg logit contributions
ked-1.026
arted-0.993
elt-0.968
ashed-0.944
ened-0.935
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
uch+0.332
prise+0.318
 happen+0.298
 you+0.291
w+0.282
Neg logit contributions
 He-0.195
 eyes-0.191
elt-0.189
ed-0.185
 arms-0.179
TokenHe
Token ID1544
Feature activation+9.63e-03

Pos logit contributions
uch+0.208
 happen+0.208
prise+0.195
 you+0.178
 belong+0.163
Neg logit contributions
ed-0.300
ked-0.299
elt-0.296
 He-0.292
 arms-0.283
Token opened
Token ID4721
Feature activation+1.84e-01

Pos logit contributions
elt+0.018
arted+0.018
 asleep+0.017
itted+0.016
joy+0.016
Neg logit contributions
 you-0.017
lly-0.016
ggy-0.016
prise-0.016
uch-0.016
Token his
Token ID465
Feature activation+1.50e-01

Pos logit contributions
elt+0.448
ashed+0.434
ked+0.411
sed+0.393
arted+0.392
Neg logit contributions
 you-0.287
 happen-0.222
?-0.220
 ourselves-0.218
One-0.207
Token.
Token ID13
Feature activation-1.73e-01

Pos logit contributions
ked+0.224
elt+0.219
arted+0.210
ed+0.205
 eyes+0.201
Neg logit contributions
 you-0.262
prise-0.257
uch-0.257
 happen-0.239
 achieve-0.226
Token It
Token ID632
Feature activation+2.33e-01

Pos logit contributions
 you+0.380
prise+0.301
 am+0.293
n+0.292
 achieve+0.287
Neg logit contributions
ked-0.297
ashed-0.274
arted-0.264
elt-0.262
ened-0.259
Token said
Token ID531
Feature activation+2.69e-02

Pos logit contributions
elt+0.486
ked+0.480
arted+0.463
 eyes+0.438
ashed+0.438
Neg logit contributions
 you-0.405
uch-0.358
 happen-0.355
prise-0.354
 am-0.342
Token "
Token ID366
Feature activation+2.94e-01

Pos logit contributions
elt+0.049
ked+0.049
arted+0.049
ashed+0.046
 arms+0.045
Neg logit contributions
 you-0.055
prise-0.049
 happen-0.048
uch-0.047
 am-0.045
TokenThank
Token ID10449
Feature activation-5.89e-02

Pos logit contributions
elt+0.582
ked+0.566
ed+0.538
arted+0.529
ashed+0.491
Neg logit contributions
prise-0.551
uch-0.525
 happen-0.520
 you-0.516
vern-0.507
Token you
Token ID345
Feature activation-5.82e-01

Pos logit contributions
uch+0.054
 achieve+0.050
 happen+0.040
prise+0.040
vern+0.039
Neg logit contributions
ed-0.164
elt-0.163
ked-0.158
arted-0.154
 eyes-0.153
Token for
Token ID329
Feature activation+1.55e-01

Pos logit contributions
 you+1.119
prise+1.072
uch+1.062
 happen+0.991
 achieve+0.934
Neg logit contributions
ked-1.096
elt-1.074
arted-1.031
ed-1.004
ashed-0.981
Token playing
Token ID2712
Feature activation+9.16e-02

Pos logit contributions
ked+0.219
arted+0.212
 eyes+0.212
 arms+0.207
elt+0.202
Neg logit contributions
uch-0.350
prise-0.334
arest-0.317
 you-0.314
w-0.312
Token with
Token ID351
Feature activation+1.80e-02

Pos logit contributions
ked+0.145
ed+0.140
elt+0.137
 down+0.137
arted+0.135
Neg logit contributions
uch-0.192
prise-0.192
 you-0.178
 happen-0.176
arest-0.170
Token us
Token ID514
Feature activation-4.16e-01

Pos logit contributions
 eyes+0.035
 arms+0.034
ked+0.034
arted+0.034
elt+0.033
Neg logit contributions
prise-0.031
uch-0.031
 achieve-0.028
 happen-0.028
arest-0.028
Token!"
Token ID2474
Feature activation-3.79e-01

Pos logit contributions
prise+0.441
uch+0.439
 you+0.425
 happen+0.390
 achieve+0.355
Neg logit contributions
ked-1.091
elt-1.072
ed-1.055
arted-1.053
 eyes-1.045
Token for
Token ID329
Feature activation+1.58e-01

Pos logit contributions
 you+0.387
uch+0.382
prise+0.379
 happen+0.349
 achieve+0.333
Neg logit contributions
ked-0.430
elt-0.420
arted-0.405
 eyes-0.397
ed-0.396
Token you
Token ID345
Feature activation-5.81e-01

Pos logit contributions
 eyes+0.442
 asleep+0.424
 arms+0.422
elt+0.410
ked+0.409
Neg logit contributions
uch-0.152
 am-0.118
prise-0.118
arest-0.114
 achieve-0.113
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
uch+1.268
prise+1.221
 you+1.205
 happen+1.171
w+1.130
Neg logit contributions
ked-0.878
 eyes-0.867
elt-0.867
 arms-0.843
ed-0.820
Token I
Token ID314
Feature activation-2.34e-01

Pos logit contributions
 you+0.345
prise+0.331
uch+0.329
 happen+0.306
 achieve+0.289
Neg logit contributions
ked-0.340
elt-0.332
arted-0.320
ed-0.312
ashed-0.305
Token hope
Token ID2911
Feature activation-1.07e-01

Pos logit contributions
 you+0.347
uch+0.338
 happen+0.317
prise+0.310
 ourselves+0.300
Neg logit contributions
ked-0.507
elt-0.505
ed-0.496
ashed-0.491
 confused-0.486
Token you
Token ID345
Feature activation-5.80e-01

Pos logit contributions
uch+0.090
prise+0.080
w+0.060
 you+0.056
 happen+0.053
Neg logit contributions
 eyes-0.312
 arms-0.308
elt-0.302
ked-0.302
 asleep-0.300
Token like
Token ID588
Feature activation+2.12e-02

Pos logit contributions
 you+0.943
prise+0.932
uch+0.922
 happen+0.847
w+0.813
Neg logit contributions
ked-1.213
elt-1.146
ed-1.130
 asleep-1.107
 confused-1.105
Token it
Token ID340
Feature activation-1.40e-01

Pos logit contributions
 eyes+0.039
ked+0.039
 arms+0.038
elt+0.038
 asleep+0.038
Neg logit contributions
uch-0.041
prise-0.039
 you-0.036
w-0.035
arest-0.035
Token."
Token ID526
Feature activation-3.35e-01

Pos logit contributions
prise+0.250
uch+0.243
 you+0.236
 happen+0.214
w+0.213
Neg logit contributions
ked-0.268
elt-0.260
ed-0.259
 asleep-0.257
 down-0.253
Token She
Token ID1375
Feature activation+2.57e-01

Pos logit contributions
 you+0.770
prise+0.710
uch+0.687
 happen+0.673
 achieve+0.653
Neg logit contributions
ked-0.542
elt-0.509
arted-0.497
ashed-0.475
ed-0.465
Token gave
Token ID2921
Feature activation+9.83e-02

Pos logit contributions
arted+0.547
elt+0.524
ked+0.511
pered+0.477
 floppy+0.476
Neg logit contributions
 you-0.427
prise-0.422
lly-0.389
ggy-0.365
 else-0.363
Token.
Token ID13
Feature activation-1.85e-01

Pos logit contributions
prise+0.394
uch+0.391
 you+0.365
w+0.358
arest+0.350
Neg logit contributions
 eyes-0.279
ked-0.265
 asleep-0.260
 arms-0.260
 confused-0.256
Token I
Token ID314
Feature activation-2.33e-01

Pos logit contributions
 you+0.331
prise+0.313
uch+0.312
 happen+0.288
 achieve+0.271
Neg logit contributions
ked-0.373
elt-0.364
arted-0.354
ed-0.345
ashed-0.339
Token was
Token ID373
Feature activation-4.54e-02

Pos logit contributions
 you+0.426
prise+0.413
uch+0.397
 happen+0.381
 ourselves+0.372
Neg logit contributions
ked-0.440
elt-0.432
ed-0.430
ashed-0.420
 shrugged-0.413
Token worried
Token ID7960
Feature activation+2.37e-01

Pos logit contributions
 you+0.099
prise+0.093
uch+0.093
 happen+0.087
 achieve+0.083
Neg logit contributions
ked-0.076
elt-0.075
arted-0.071
ed-0.069
ashed-0.068
Token about
Token ID546
Feature activation+2.02e-01

Pos logit contributions
 eyes+0.399
 down+0.396
 asleep+0.387
 confused+0.377
 arms+0.375
Neg logit contributions
prise-0.501
uch-0.490
arest-0.431
w-0.423
 achieve-0.420
Token you
Token ID345
Feature activation-5.81e-01

Pos logit contributions
 eyes+0.427
 arms+0.408
 asleep+0.401
 confused+0.397
arted+0.396
Neg logit contributions
prise-0.336
uch-0.328
arest-0.314
w-0.282
 am-0.273
Token."
Token ID526
Feature activation-3.36e-01

Pos logit contributions
prise+1.107
uch+1.012
arest+0.956
 you+0.955
w+0.912
Neg logit contributions
ked-1.106
 confused-1.080
 eyes-1.060
 down-1.046
 asleep-1.044
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
 you+0.600
prise+0.523
uch+0.500
 am+0.481
 happen+0.478
Neg logit contributions
ked-0.730
arted-0.686
elt-0.671
ashed-0.656
ed-0.654
Token
Token ID198
Feature activation-1.37e-01

Pos logit contributions
uch+0.364
prise+0.347
 happen+0.315
w+0.311
arest+0.310
Neg logit contributions
 He-0.179
elt-0.159
 down-0.154
 confused-0.152
 arms-0.151
TokenL
Token ID43
Feature activation-2.80e-01

Pos logit contributions
uch+0.270
 happen+0.257
prise+0.235
n+0.218
gh+0.217
Neg logit contributions
 He-0.250
elt-0.247
 confused-0.229
 arms-0.224
 wooden-0.221
Tokenily
Token ID813
Feature activation-1.22e-01

Pos logit contributions
 you+0.504
uch+0.495
prise+0.491
 happen+0.459
 achieve+0.444
Neg logit contributions
ked-0.548
elt-0.548
ed-0.527
arted-0.525
ashed-0.500