TOP ACTIVATIONS
MAX = 0.598

goes " ch oo cho o cho o ".
ch oo cho o cho o ". They both
, when the k idd o got to the university ,
L ila screamed and Nem o hid behind a coral .
wide eyes as Z ipp o waved his wand and said
Pick - a - bo o . He hopped closer and
Oh no !" cried Nem o . " We have to
with a boo - bo o . Later that
him . Le o 's best friend , a
saw a mark on Bob o 's arm and said ,
two best friends , Mom o and L ola . They
got a boo - bo o on her knee . Her
a big boo - bo o on his knee . He
sky . The dove co o ed softly , and the
." The hipp o was confused and asked ,
minutes , then t ipt o ed back to the table
So , the little hipp o went to the river and
Ch ir py . Bob o said , " I found
put the leaves on Bob o 's head . Now ,
a purple bird named Bob o . Bob o loved to

MIN ACTIVATIONS
MIN = -0.573

ever before . Her mum was happy that Daisy
it . Her mom showed her how to
her mom . Her mom smiled when she saw
it back ." Her mom smiled and hugged her
and happy !" Her mom is surprised . She
lovely seal ?" Her mom said , " Sure
touch it ?" Her mom said , " No
go there ?" Her mom replied , " No
sad . Her teacher saw this and asked
asked . Her mom laughed and replied ,
dull ones ." Her mom and dad hugged her
big eyes . Her mom smiled and hugged her
exclaimed . Her dad said , " You
lot . Her mom came outside and saw
glowing red !" Her mother smiled and nodded .
large swing ." Her mom hugged her and said
ground . Her friends gathered around the crack
the cup . Her mom noticed that Lily was
it . Her mom said , " Sure
question . Her mom explained that ge ese

INTERVAL 0.305 - 0.598
CONTAINS 0.877%

excited , but then Mom my said there was going to
you let her hold your bear for a little while ?"
stranger 's car was even faster . The stranger won the
of the cliff and looked down . He saw Tom in
in the sky . Tim my didn 't really understand ,

INTERVAL 0.012 - 0.305
CONTAINS 42.509%

Look , Ben !" Mia says . " The tree has
une was excited . It had never been on an adventure
ily stopped weeping and waited for the gum to come out
record a song together . The man was happy
bar row . John : " What we doing

INTERVAL -0.280 - 0.012
CONTAINS 54.892%

it broke into a million pieces . Lily 's mom was
. From then on , it was much quieter and people
a time , there was a spot . It seemed very
. She was only 3 years old and was very upset
even stronger . So , each day it would go for

INTERVAL -0.573 - -0.280
CONTAINS 1.721%

and slept . Finally , when the sun rose
walking around her garden when she saw an amazing symbol .
saw it . To the little boy 's amaz
house together . He asked her if she wanted to play
very frustrated . Even though she had had a lovely bath
Token goes
Token ID2925
Feature activation+9.99e-02

Pos logit contributions
o+0.104
 alone+0.103
 tank+0.093
 afloat+0.088
 forth+0.087
Neg logit contributions
ves-0.158
 vows-0.156
Her-0.153
 brist-0.148
growth-0.139
Token "
Token ID366
Feature activation-3.48e-02

Pos logit contributions
o+0.164
 alone+0.135
 forth+0.132
 polar+0.132
 tank+0.131
Neg logit contributions
ves-0.203
Her-0.201
 vows-0.199
 brist-0.190
ork-0.182
Tokench
Token ID354
Feature activation+2.02e-01

Pos logit contributions
Her+0.061
ves+0.058
 vows+0.058
 brist+0.058
growth+0.052
Neg logit contributions
o-0.068
 alone-0.065
 tank-0.061
 afloat-0.059
 forth-0.059
Tokenoo
Token ID2238
Feature activation-1.05e-02

Pos logit contributions
o+0.379
 alone+0.354
 forth+0.329
 tank+0.323
 afloat+0.316
Neg logit contributions
ves-0.380
Her-0.368
 vows-0.362
 brist-0.358
growth-0.324
Token cho
Token ID1727
Feature activation+2.12e-01

Pos logit contributions
Her+0.022
 vows+0.021
ves+0.021
 brist+0.021
 blonde+0.020
Neg logit contributions
o-0.018
 alone-0.017
 forth-0.015
 tank-0.015
my-0.014
Tokeno
Token ID78
Feature activation+5.86e-01

Pos logit contributions
 alone+0.410
o+0.407
 forth+0.381
 tank+0.376
 afloat+0.370
Neg logit contributions
ves-0.369
Her-0.356
 vows-0.349
 brist-0.344
ork-0.314
Token cho
Token ID1727
Feature activation+2.09e-01

Pos logit contributions
o+0.972
 alone+0.915
 forth+0.826
 tank+0.817
 afloat+0.796
Neg logit contributions
ves-1.206
 vows-1.183
Her-1.182
 brist-1.159
growth-1.053
Tokeno
Token ID78
Feature activation+5.81e-01

Pos logit contributions
 alone+0.403
o+0.382
 forth+0.375
 tank+0.372
 afloat+0.365
Neg logit contributions
ves-0.362
Her-0.345
 vows-0.336
 brist-0.331
ork-0.309
Token".
Token ID1911
Feature activation+7.20e-02

Pos logit contributions
o+0.948
 alone+0.909
 forth+0.825
 tank+0.819
 afloat+0.795
Neg logit contributions
ves-1.195
 vows-1.154
Her-1.150
 brist-1.124
ork-1.045
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
o+0.114
 alone+0.106
 forth+0.097
 tank+0.093
 afloat+0.092
Neg logit contributions
Her-0.155
ves-0.154
 vows-0.152
 brist-0.150
 blonde-0.139
Token
Token ID198
Feature activation+1.38e-01

Pos logit contributions
o+0.235
 alone+0.233
 forth+0.227
 afloat+0.209
 tank+0.209
Neg logit contributions
Her-0.299
ves-0.295
 vows-0.269
 brist-0.268
ork-0.257
Tokench
Token ID354
Feature activation+2.02e-01

Pos logit contributions
Her+0.061
ves+0.058
 vows+0.058
 brist+0.058
growth+0.052
Neg logit contributions
o-0.068
 alone-0.065
 tank-0.061
 afloat-0.059
 forth-0.059
Tokenoo
Token ID2238
Feature activation-1.05e-02

Pos logit contributions
o+0.379
 alone+0.354
 forth+0.329
 tank+0.323
 afloat+0.316
Neg logit contributions
ves-0.380
Her-0.368
 vows-0.362
 brist-0.358
growth-0.324
Token cho
Token ID1727
Feature activation+2.12e-01

Pos logit contributions
Her+0.022
 vows+0.021
ves+0.021
 brist+0.021
 blonde+0.020
Neg logit contributions
o-0.018
 alone-0.017
 forth-0.015
 tank-0.015
my-0.014
Tokeno
Token ID78
Feature activation+5.86e-01

Pos logit contributions
 alone+0.410
o+0.407
 forth+0.381
 tank+0.376
 afloat+0.370
Neg logit contributions
ves-0.369
Her-0.356
 vows-0.349
 brist-0.344
ork-0.314
Token cho
Token ID1727
Feature activation+2.09e-01

Pos logit contributions
o+0.972
 alone+0.915
 forth+0.826
 tank+0.817
 afloat+0.796
Neg logit contributions
ves-1.206
 vows-1.183
Her-1.182
 brist-1.159
growth-1.053
Tokeno
Token ID78
Feature activation+5.81e-01

Pos logit contributions
 alone+0.403
o+0.382
 forth+0.375
 tank+0.372
 afloat+0.365
Neg logit contributions
ves-0.362
Her-0.345
 vows-0.336
 brist-0.331
ork-0.309
Token".
Token ID1911
Feature activation+7.20e-02

Pos logit contributions
o+0.948
 alone+0.909
 forth+0.825
 tank+0.819
 afloat+0.795
Neg logit contributions
ves-1.195
 vows-1.154
Her-1.150
 brist-1.124
ork-1.045
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
o+0.114
 alone+0.106
 forth+0.097
 tank+0.093
 afloat+0.092
Neg logit contributions
Her-0.155
ves-0.154
 vows-0.152
 brist-0.150
 blonde-0.139
Token
Token ID198
Feature activation+1.38e-01

Pos logit contributions
o+0.235
 alone+0.233
 forth+0.227
 afloat+0.209
 tank+0.209
Neg logit contributions
Her-0.299
ves-0.295
 vows-0.269
 brist-0.268
ork-0.257
TokenThey
Token ID2990
Feature activation-2.22e-02

Pos logit contributions
o+0.265
 alone+0.248
 forth+0.227
 tank+0.224
 afloat+0.219
Neg logit contributions
Her-0.254
ves-0.254
 vows-0.250
 brist-0.246
 blonde-0.223
Token both
Token ID1111
Feature activation+8.77e-02

Pos logit contributions
ves+0.045
Her+0.045
 vows+0.044
 brist+0.044
growth+0.040
Neg logit contributions
o-0.039
 alone-0.036
 forth-0.032
 tank-0.032
my-0.031
Token,
Token ID11
Feature activation+2.15e-02

Pos logit contributions
 vows+0.113
ves+0.110
 brist+0.108
Her+0.108
growth+0.100
Neg logit contributions
 alone-0.085
o-0.084
 forth-0.075
my-0.072
 tank-0.067
Token when
Token ID618
Feature activation+3.68e-02

Pos logit contributions
o+0.038
 alone+0.036
 forth+0.033
my+0.032
 tank+0.031
Neg logit contributions
 vows-0.043
ves-0.043
Her-0.042
 brist-0.041
growth-0.038
Token the
Token ID262
Feature activation+1.41e-01

Pos logit contributions
o+0.065
 alone+0.062
 forth+0.057
 tank+0.054
my+0.054
Neg logit contributions
ves-0.072
 vows-0.072
Her-0.072
 brist-0.071
growth-0.065
Token k
Token ID479
Feature activation+1.63e-04

Pos logit contributions
o+0.253
 alone+0.241
 tank+0.219
 forth+0.219
 polar+0.210
Neg logit contributions
Her-0.277
ves-0.276
 vows-0.270
 brist-0.263
growth-0.245
Tokenidd
Token ID1638
Feature activation+2.59e-01

Pos logit contributions
o+0.000
 alone+0.000
 forth+0.000
 tank+0.000
 afloat+0.000
Neg logit contributions
Her-0.000
ves-0.000
 vows-0.000
 brist-0.000
 blonde-0.000
Tokeno
Token ID78
Feature activation+5.75e-01

Pos logit contributions
o+0.263
 alone+0.222
 forth+0.182
 tank+0.179
my+0.171
Neg logit contributions
ves-0.718
Her-0.714
 vows-0.712
 brist-0.704
 blonde-0.661
Token got
Token ID1392
Feature activation+4.40e-02

Pos logit contributions
o+1.036
 alone+0.945
 tank+0.847
 forth+0.842
my+0.829
Neg logit contributions
Her-1.150
ves-1.141
 vows-1.130
 brist-1.116
growth-1.019
Token to
Token ID284
Feature activation-6.89e-03

Pos logit contributions
o+0.068
 alone+0.062
 forth+0.057
 tank+0.056
 afloat+0.054
Neg logit contributions
Her-0.095
ves-0.093
 vows-0.093
 brist-0.093
 blonde-0.086
Token the
Token ID262
Feature activation+1.40e-01

Pos logit contributions
ves+0.015
Her+0.015
 vows+0.015
 brist+0.014
 blonde+0.013
Neg logit contributions
o-0.011
 alone-0.010
 tank-0.009
 forth-0.009
 afloat-0.009
Token university
Token ID6403
Feature activation-1.15e-01

Pos logit contributions
o+0.259
 alone+0.251
 tank+0.230
 forth+0.225
 wreck+0.220
Neg logit contributions
ves-0.268
Her-0.264
 vows-0.256
 brist-0.253
growth-0.233
Token,
Token ID11
Feature activation+1.94e-02

Pos logit contributions
Her+0.239
 brist+0.238
 vows+0.236
ves+0.235
growth+0.220
Neg logit contributions
o-0.194
 alone-0.188
 forth-0.162
 tank-0.160
my-0.159
TokenL
Token ID43
Feature activation+6.65e-02

Pos logit contributions
o+0.306
 alone+0.292
 forth+0.274
 tank+0.270
 afloat+0.265
Neg logit contributions
Her-0.228
ves-0.219
 vows-0.209
 brist-0.205
 blonde-0.186
Tokenila
Token ID10102
Feature activation+3.53e-02

Pos logit contributions
o+0.151
 alone+0.142
my+0.131
 forth+0.126
 tank+0.125
Neg logit contributions
 vows-0.104
ves-0.101
 brist-0.097
Her-0.096
 blonde-0.090
Token screamed
Token ID25421
Feature activation+7.91e-02

Pos logit contributions
o+0.060
 alone+0.055
my+0.049
 forth+0.048
 tank+0.048
Neg logit contributions
ves-0.075
Her-0.074
 vows-0.073
 brist-0.071
growth-0.067
Token and
Token ID290
Feature activation+6.46e-02

Pos logit contributions
o+0.124
 alone+0.120
 forth+0.103
 tank+0.101
my+0.099
Neg logit contributions
ves-0.178
 vows-0.176
Her-0.168
 brist-0.166
growth-0.163
Token Nem
Token ID22547
Feature activation+4.34e-01

Pos logit contributions
o+0.120
 alone+0.111
 forth+0.102
 tank+0.101
 afloat+0.099
Neg logit contributions
ves-0.122
Her-0.122
 vows-0.121
 brist-0.119
 blonde-0.109
Tokeno
Token ID78
Feature activation+5.72e-01

Pos logit contributions
 alone+0.158
 forth+0.114
 wreck+0.080
 afloat+0.078
igator+0.054
Neg logit contributions
ves-1.395
 vows-1.380
Her-1.362
 brist-1.321
ork-1.280
Token hid
Token ID24519
Feature activation+8.50e-02

Pos logit contributions
o+1.018
 alone+0.935
 tank+0.831
 forth+0.826
my+0.806
Neg logit contributions
Her-1.159
ves-1.145
 vows-1.136
 brist-1.133
 blonde-1.055
Token behind
Token ID2157
Feature activation+2.03e-01

Pos logit contributions
o+0.146
 alone+0.117
|+0.115
my+0.114
 tank+0.114
Neg logit contributions
Her-0.172
ves-0.170
 brist-0.167
 vows-0.165
growth-0.152
Token a
Token ID257
Feature activation-7.57e-02

Pos logit contributions
o+0.289
 alone+0.281
 tank+0.244
 polar+0.239
my+0.224
Neg logit contributions
ves-0.482
 vows-0.472
Her-0.468
 brist-0.458
 blonde-0.417
Token coral
Token ID29537
Feature activation+1.12e-01

Pos logit contributions
ves+0.144
Her+0.141
 vows+0.139
 brist+0.139
ork+0.131
Neg logit contributions
o-0.141
 alone-0.124
 forth-0.123
my-0.112
 afloat-0.111
Token.
Token ID13
Feature activation+2.30e-02

Pos logit contributions
o+0.182
 alone+0.175
 tank+0.159
 forth+0.149
 afloat+0.147
Neg logit contributions
Her-0.237
ves-0.233
 vows-0.233
 brist-0.232
 blonde-0.217
Token wide
Token ID3094
Feature activation+3.73e-02

Pos logit contributions
o+0.194
 alone+0.191
 tank+0.166
 forth+0.166
my+0.161
Neg logit contributions
ves-0.223
Her-0.220
 vows-0.218
 brist-0.215
ork-0.198
Token eyes
Token ID2951
Feature activation-2.39e-01

Pos logit contributions
 alone+0.076
o+0.075
 tank+0.070
 forth+0.069
 polar+0.067
Neg logit contributions
Her-0.064
ves-0.063
 brist-0.058
 vows-0.058
ork-0.054
Token as
Token ID355
Feature activation-2.40e-02

Pos logit contributions
 brist+0.574
 vows+0.569
ves+0.568
Her+0.564
growth+0.552
Neg logit contributions
 alone-0.320
o-0.313
my-0.249
 tank-0.235
 down-0.229
Token Z
Token ID1168
Feature activation+9.48e-02

Pos logit contributions
Her+0.044
ves+0.043
 vows+0.043
 brist+0.043
growth+0.039
Neg logit contributions
o-0.046
 alone-0.044
 forth-0.039
 tank-0.039
my-0.038
Tokenipp
Token ID3974
Feature activation-4.74e-02

Pos logit contributions
o+0.194
 alone+0.181
 forth+0.166
 tank+0.164
my+0.161
Neg logit contributions
ves-0.162
Her-0.161
 vows-0.161
 brist-0.158
 blonde-0.142
Tokeno
Token ID78
Feature activation+5.71e-01

Pos logit contributions
ves+0.092
Her+0.090
 vows+0.090
 brist+0.087
 blonde+0.079
Neg logit contributions
o-0.082
 alone-0.079
 forth-0.075
 tank-0.073
 afloat-0.072
Token waved
Token ID26834
Feature activation+9.69e-02

Pos logit contributions
o+1.040
 alone+0.922
my+0.821
 tank+0.811
 forth+0.796
Neg logit contributions
Her-1.162
ves-1.155
 brist-1.141
 vows-1.119
growth-1.043
Token his
Token ID465
Feature activation+3.24e-01

Pos logit contributions
o+0.174
 alone+0.168
 forth+0.145
 tank+0.144
 polar+0.142
Neg logit contributions
ves-0.192
 brist-0.185
 vows-0.183
Her-0.183
growth-0.173
Token wand
Token ID11569
Feature activation-1.89e-01

Pos logit contributions
o+0.660
 alone+0.625
 forth+0.570
 tank+0.568
 afloat+0.552
Neg logit contributions
ves-0.556
Her-0.554
 vows-0.544
 brist-0.537
growth-0.490
Token and
Token ID290
Feature activation+5.53e-02

Pos logit contributions
 brist+0.425
Her+0.424
ves+0.423
 vows+0.420
growth+0.404
Neg logit contributions
 alone-0.287
o-0.277
 tank-0.231
 forth-0.228
 afloat-0.223
Token said
Token ID531
Feature activation+1.20e-01

Pos logit contributions
o+0.097
 alone+0.090
 forth+0.081
 tank+0.080
 afloat+0.078
Neg logit contributions
ves-0.111
Her-0.110
 vows-0.110
 brist-0.108
 blonde-0.099
Token Pick
Token ID12346
Feature activation+7.49e-02

Pos logit contributions
o+0.297
 alone+0.287
 tank+0.253
my+0.249
 polar+0.244
Neg logit contributions
 vows-0.303
ves-0.296
Her-0.295
 brist-0.289
growth-0.262
Token-
Token ID12
Feature activation+2.41e-02

Pos logit contributions
o+0.113
 alone+0.103
 forth+0.091
 tank+0.090
 afloat+0.087
Neg logit contributions
ves-0.168
Her-0.167
 vows-0.167
 brist-0.164
 blonde-0.152
Tokena
Token ID64
Feature activation-3.29e-02

Pos logit contributions
o+0.047
 alone+0.044
 forth+0.040
my+0.039
 tank+0.039
Neg logit contributions
ves-0.044
 vows-0.044
Her-0.043
 brist-0.042
growth-0.038
Token-
Token ID12
Feature activation+2.39e-02

Pos logit contributions
ves+0.069
Her+0.069
 vows+0.069
 brist+0.068
growth+0.063
Neg logit contributions
o-0.055
 alone-0.051
 tank-0.045
 forth-0.045
my-0.044
Tokenbo
Token ID2127
Feature activation+3.62e-01

Pos logit contributions
o+0.050
 alone+0.045
my+0.042
 forth+0.041
 tank+0.040
Neg logit contributions
ves-0.041
 vows-0.041
 brist-0.040
Her-0.039
growth-0.036
Tokeno
Token ID78
Feature activation+5.71e-01

Pos logit contributions
o+0.175
 alone+0.126
 forth+0.068
 tank+0.062
my+0.049
Neg logit contributions
ves-1.183
 vows-1.179
Her-1.178
 brist-1.166
 blonde-1.105
Token.
Token ID13
Feature activation+3.62e-02

Pos logit contributions
o+0.960
 alone+0.885
 forth+0.792
 tank+0.782
my+0.763
Neg logit contributions
ves-1.186
 vows-1.179
Her-1.179
 brist-1.162
growth-1.069
Token He
Token ID679
Feature activation+3.01e-01

Pos logit contributions
o+0.063
 alone+0.059
 forth+0.055
 afloat+0.053
 tank+0.052
Neg logit contributions
Her-0.072
ves-0.070
 vows-0.070
 brist-0.069
 blonde-0.064
Token hopped
Token ID45230
Feature activation+6.16e-02

Pos logit contributions
o+0.505
 alone+0.454
 tank+0.405
 forth+0.405
my+0.400
Neg logit contributions
ves-0.628
Her-0.623
 vows-0.622
 brist-0.618
growth-0.578
Token closer
Token ID5699
Feature activation+2.00e-01

Pos logit contributions
o+0.087
 alone+0.076
 forth+0.074
 polar+0.070
 wreck+0.070
Neg logit contributions
Her-0.142
 vows-0.137
ves-0.136
 brist-0.134
 ribbon-0.126
Token and
Token ID290
Feature activation+4.81e-02

Pos logit contributions
o+0.313
 alone+0.292
 forth+0.248
my+0.242
 tank+0.240
Neg logit contributions
 vows-0.445
ves-0.445
 brist-0.439
Her-0.438
growth-0.408
TokenOh
Token ID5812
Feature activation+8.33e-02

Pos logit contributions
Her+0.129
 brist+0.121
ves+0.120
 vows+0.118
 blonde+0.108
Neg logit contributions
o-0.145
 alone-0.138
 forth-0.128
 tank-0.128
 afloat-0.127
Token no
Token ID645
Feature activation-7.25e-02

Pos logit contributions
o+0.145
 alone+0.132
my+0.119
 forth+0.119
 tank+0.118
Neg logit contributions
ves-0.173
Her-0.171
 vows-0.168
 brist-0.163
growth-0.158
Token!"
Token ID2474
Feature activation+2.14e-01

Pos logit contributions
 vows+0.154
ves+0.154
Her+0.153
 brist+0.146
growth+0.142
Neg logit contributions
o-0.120
 alone-0.111
 forth-0.103
my-0.099
 tank-0.098
Token cried
Token ID16896
Feature activation+1.60e-01

Pos logit contributions
o+0.342
 alone+0.313
 tank+0.273
 forth+0.270
my+0.264
Neg logit contributions
 vows-0.468
ves-0.467
 brist-0.456
Her-0.454
growth-0.423
Token Nem
Token ID22547
Feature activation+4.35e-01

Pos logit contributions
o+0.260
 alone+0.247
 tank+0.216
 forth+0.213
 afloat+0.207
Neg logit contributions
ves-0.348
 vows-0.345
Her-0.334
 brist-0.328
growth-0.311
Tokeno
Token ID78
Feature activation+5.70e-01

Pos logit contributions
 alone+0.160
 forth+0.142
 wreck+0.133
 tank+0.118
 afloat+0.092
Neg logit contributions
Her-1.376
ves-1.368
 vows-1.324
 brist-1.294
 Her-1.268
Token.
Token ID13
Feature activation+3.25e-02

Pos logit contributions
o+1.035
 alone+0.958
 forth+0.850
 tank+0.844
my+0.835
Neg logit contributions
ves-1.124
 vows-1.120
Her-1.113
 brist-1.099
growth-1.012
Token "
Token ID366
Feature activation-4.26e-02

Pos logit contributions
o+0.066
 alone+0.063
 forth+0.062
 afloat+0.058
 wreck+0.057
Neg logit contributions
Her-0.054
 vows-0.053
ves-0.052
 brist-0.050
 Her-0.048
TokenWe
Token ID1135
Feature activation+9.39e-02

Pos logit contributions
Her+0.073
 brist+0.063
ves+0.062
growth+0.058
 blonde+0.054
Neg logit contributions
o-0.093
 alone-0.085
 tank-0.084
 forth-0.084
 polar-0.080
Token have
Token ID423
Feature activation+1.84e-01

Pos logit contributions
o+0.173
 alone+0.160
 forth+0.149
 afloat+0.144
 tank+0.143
Neg logit contributions
 vows-0.174
ves-0.172
Her-0.172
 brist-0.171
 blonde-0.156
Token to
Token ID284
Feature activation-1.52e-02

Pos logit contributions
o+0.344
 alone+0.322
 tank+0.288
 forth+0.284
my+0.278
Neg logit contributions
ves-0.353
Her-0.352
 vows-0.347
 brist-0.342
growth-0.313
Token with
Token ID351
Feature activation+1.66e-01

Pos logit contributions
o+0.442
 alone+0.403
 forth+0.370
 tank+0.367
 afloat+0.361
Neg logit contributions
ves-0.482
 vows-0.478
Her-0.477
 brist-0.470
 blonde-0.427
Token a
Token ID257
Feature activation-6.46e-02

Pos logit contributions
o+0.290
 alone+0.273
 forth+0.245
 tank+0.241
my+0.234
Neg logit contributions
ves-0.333
 vows-0.330
Her-0.330
 brist-0.324
growth-0.296
Token boo
Token ID22513
Feature activation+2.06e-01

Pos logit contributions
ves+0.122
 vows+0.121
Her+0.121
 brist+0.118
 blonde+0.108
Neg logit contributions
o-0.120
 alone-0.112
 forth-0.102
 tank-0.100
 afloat-0.098
Token-
Token ID12
Feature activation+2.49e-02

Pos logit contributions
o+0.406
 alone+0.382
 tank+0.362
 afloat+0.358
 forth+0.355
Neg logit contributions
ves-0.347
Her-0.342
 brist-0.340
 vows-0.334
ork-0.291
Tokenbo
Token ID2127
Feature activation+3.61e-01

Pos logit contributions
o+0.036
 alone+0.032
 forth+0.029
 tank+0.028
 afloat+0.027
Neg logit contributions
ves-0.058
Her-0.058
 vows-0.058
 brist-0.057
 blonde-0.053
Tokeno
Token ID78
Feature activation+5.70e-01

Pos logit contributions
 alone+0.069
o+0.066
 forth+0.048
 afloat+0.034
 tank+0.020
Neg logit contributions
ves-1.224
Her-1.205
 vows-1.200
 brist-1.177
ork-1.128
Token.
Token ID13
Feature activation+3.13e-02

Pos logit contributions
o+0.969
 alone+0.899
 forth+0.835
 afloat+0.824
 tank+0.823
Neg logit contributions
ves-1.134
 vows-1.119
Her-1.116
 brist-1.095
 blonde-0.993
Token
Token ID198
Feature activation+1.35e-01

Pos logit contributions
o+0.058
 alone+0.055
 forth+0.055
 afloat+0.053
 tank+0.050
Neg logit contributions
Her-0.058
 brist-0.054
ves-0.054
 vows-0.054
 Her-0.052
Token
Token ID198
Feature activation+1.32e-01

Pos logit contributions
 forth+0.235
o+0.231
 alone+0.229
 afloat+0.217
 tank+0.212
Neg logit contributions
Her-0.274
ves-0.263
 brist-0.236
 vows-0.232
ork-0.232
TokenLater
Token ID18602
Feature activation-7.17e-02

Pos logit contributions
o+0.288
 alone+0.273
 forth+0.257
 tank+0.253
 afloat+0.250
Neg logit contributions
Her-0.212
ves-0.205
 vows-0.196
 brist-0.195
 blonde-0.175
Token that
Token ID326
Feature activation-1.02e-01

Pos logit contributions
ves+0.117
 vows+0.116
Her+0.115
 brist+0.113
 blonde+0.102
Neg logit contributions
o-0.153
 alone-0.146
 forth-0.134
 tank-0.132
 polar-0.129
Token him
Token ID683
Feature activation+1.57e-01

Pos logit contributions
Her+0.301
ves+0.278
 brist+0.263
 vows+0.263
growth+0.242
Neg logit contributions
o-0.347
 alone-0.340
 forth-0.319
 tank-0.318
 polar-0.304
Token.
Token ID13
Feature activation+2.34e-02

Pos logit contributions
o+0.283
 alone+0.259
 forth+0.241
 tank+0.235
 afloat+0.234
Neg logit contributions
ves-0.301
 vows-0.300
Her-0.295
 brist-0.288
 blonde-0.266
Token
Token ID198
Feature activation+1.43e-01

Pos logit contributions
o+0.039
 alone+0.037
 forth+0.036
 afloat+0.034
 wreck+0.033
Neg logit contributions
Her-0.048
ves-0.045
 vows-0.045
 brist-0.044
 Her-0.043
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
o+0.239
 alone+0.233
 forth+0.233
 afloat+0.214
 tank+0.212
Neg logit contributions
Her-0.297
ves-0.289
 brist-0.264
 vows-0.263
growth-0.254
TokenLe
Token ID3123
Feature activation-2.81e-02

Pos logit contributions
o+0.307
 alone+0.292
 forth+0.273
 tank+0.268
 afloat+0.264
Neg logit contributions
Her-0.240
ves-0.235
 vows-0.226
 brist-0.223
 blonde-0.201
Tokeno
Token ID78
Feature activation+5.70e-01

Pos logit contributions
ves+0.067
 vows+0.065
Her+0.064
 brist+0.062
growth+0.061
Neg logit contributions
 alone-0.035
 forth-0.032
 afloat-0.031
o-0.030
 tank-0.030
Token's
Token ID338
Feature activation+1.12e-01

Pos logit contributions
o+1.025
 alone+0.940
 tank+0.848
 forth+0.848
my+0.825
Neg logit contributions
Her-1.126
ves-1.123
 vows-1.106
 brist-1.093
 blonde-1.003
Token best
Token ID1266
Feature activation+6.55e-02

Pos logit contributions
o+0.222
 alone+0.208
 forth+0.190
 tank+0.190
 polar+0.183
Neg logit contributions
ves-0.200
Her-0.200
 vows-0.197
 brist-0.193
growth-0.176
Token friend
Token ID1545
Feature activation+1.11e-01

Pos logit contributions
o+0.105
 alone+0.097
 forth+0.087
 tank+0.085
 afloat+0.084
Neg logit contributions
ves-0.141
 vows-0.140
Her-0.140
 brist-0.137
 blonde-0.127
Token,
Token ID11
Feature activation+2.45e-02

Pos logit contributions
o+0.204
 alone+0.191
 forth+0.176
 tank+0.173
 afloat+0.173
Neg logit contributions
ves-0.208
 vows-0.207
Her-0.205
 brist-0.200
 blonde-0.184
Token a
Token ID257
Feature activation-8.02e-02

Pos logit contributions
o+0.038
 alone+0.036
 forth+0.033
 afloat+0.033
 tank+0.032
Neg logit contributions
Her-0.051
ves-0.050
 vows-0.050
 brist-0.048
 blonde-0.046
Token saw
Token ID2497
Feature activation+1.68e-01

Pos logit contributions
Her+0.349
ves+0.338
 brist+0.329
 vows+0.328
growth+0.317
Neg logit contributions
o-0.240
 alone-0.226
 tank-0.196
my-0.195
 forth-0.190
Token a
Token ID257
Feature activation-6.28e-02

Pos logit contributions
o+0.298
 alone+0.289
my+0.256
 polar+0.247
 tank+0.247
Neg logit contributions
 vows-0.353
ves-0.332
Her-0.312
 brist-0.309
ork-0.295
Token mark
Token ID1317
Feature activation+4.27e-02

Pos logit contributions
ves+0.114
Her+0.114
 vows+0.114
 brist+0.113
 blonde+0.103
Neg logit contributions
o-0.121
 alone-0.111
 forth-0.103
 afloat-0.099
 tank-0.099
Token on
Token ID319
Feature activation+1.65e-01

Pos logit contributions
o+0.050
 alone+0.048
 forth+0.038
my+0.038
 tank+0.035
Neg logit contributions
 vows-0.114
Her-0.110
ves-0.109
 brist-0.109
growth-0.106
Token Bob
Token ID5811
Feature activation+2.26e-01

Pos logit contributions
 alone+0.156
o+0.137
 tank+0.118
my+0.117
 his+0.115
Neg logit contributions
 vows-0.475
ves-0.460
Her-0.421
owers-0.417
 brist-0.410
Tokeno
Token ID78
Feature activation+5.69e-01

Pos logit contributions
o+0.384
 alone+0.361
 tank+0.327
 forth+0.326
 afloat+0.324
Neg logit contributions
Her-0.446
ves-0.439
 brist-0.433
 vows-0.426
 blonde-0.400
Token's
Token ID338
Feature activation+1.10e-01

Pos logit contributions
o+0.984
 alone+0.909
 forth+0.812
 tank+0.801
my+0.788
Neg logit contributions
 vows-1.179
ves-1.172
Her-1.166
 brist-1.146
growth-1.055
Token arm
Token ID3211
Feature activation-8.99e-03

Pos logit contributions
o+0.202
 alone+0.194
 tank+0.173
 forth+0.172
my+0.168
Neg logit contributions
ves-0.215
 vows-0.211
Her-0.209
 brist-0.202
 blonde-0.186
Token and
Token ID290
Feature activation+5.28e-02

Pos logit contributions
 vows+0.021
Her+0.020
ves+0.020
 brist+0.019
growth+0.019
Neg logit contributions
o-0.014
 alone-0.014
my-0.012
 forth-0.011
 tank-0.011
Token said
Token ID531
Feature activation+1.20e-01

Pos logit contributions
o+0.084
 alone+0.076
 forth+0.069
my+0.066
 tank+0.066
Neg logit contributions
 vows-0.116
ves-0.115
Her-0.113
 brist-0.111
ork-0.109
Token,
Token ID11
Feature activation+2.11e-02

Pos logit contributions
o+0.179
 alone+0.165
 tank+0.134
 polar+0.127
 Nem+0.126
Neg logit contributions
 brist-0.269
growth-0.268
ves-0.264
 vows-0.263
Her-0.258
Token two
Token ID734
Feature activation-8.78e-02

Pos logit contributions
o+0.533
 alone+0.508
 forth+0.454
 tank+0.446
my+0.439
Neg logit contributions
 vows-0.540
ves-0.540
Her-0.532
 brist-0.521
growth-0.485
Token best
Token ID1266
Feature activation+8.06e-02

Pos logit contributions
Her+0.183
ves+0.181
 brist+0.180
 vows+0.180
growth+0.165
Neg logit contributions
o-0.150
 alone-0.141
 tank-0.126
 forth-0.126
my-0.125
Token friends
Token ID2460
Feature activation+1.49e-01

Pos logit contributions
o+0.133
 alone+0.122
 forth+0.109
 tank+0.108
my+0.105
Neg logit contributions
Her-0.172
ves-0.170
 brist-0.169
 vows-0.168
growth-0.156
Token,
Token ID11
Feature activation+3.09e-02

Pos logit contributions
o+0.259
 alone+0.240
 forth+0.214
 tank+0.211
my+0.208
Neg logit contributions
Her-0.304
ves-0.303
 brist-0.302
 vows-0.298
growth-0.277
Token Mom
Token ID11254
Feature activation+6.93e-02

Pos logit contributions
o+0.051
 alone+0.047
 forth+0.042
 tank+0.042
 afloat+0.041
Neg logit contributions
ves-0.065
Her-0.064
 vows-0.064
 brist-0.063
 blonde-0.058
Tokeno
Token ID78
Feature activation+5.69e-01

Pos logit contributions
o+0.087
 alone+0.081
 forth+0.070
 afloat+0.069
 tank+0.069
Neg logit contributions
Her-0.167
ves-0.167
 vows-0.167
 brist-0.164
 blonde-0.153
Token and
Token ID290
Feature activation+5.60e-02

Pos logit contributions
o+1.007
 alone+0.913
 tank+0.819
 forth+0.817
my+0.799
Neg logit contributions
Her-1.148
ves-1.146
 vows-1.138
 brist-1.128
growth-1.038
Token L
Token ID406
Feature activation+1.31e-01

Pos logit contributions
o+0.086
 alone+0.081
 forth+0.072
 afloat+0.072
 tank+0.071
Neg logit contributions
 vows-0.119
Her-0.119
ves-0.118
 brist-0.116
 blonde-0.108
Tokenola
Token ID5708
Feature activation+2.71e-03

Pos logit contributions
o+0.260
 alone+0.244
 forth+0.225
 tank+0.222
 afloat+0.218
Neg logit contributions
ves-0.232
Her-0.230
 vows-0.229
 brist-0.224
 blonde-0.202
Token.
Token ID13
Feature activation+2.28e-02

Pos logit contributions
o+0.005
 alone+0.004
my+0.004
 tank+0.004
 forth+0.003
Neg logit contributions
 brist-0.006
ves-0.006
Her-0.006
 vows-0.006
growth-0.005
Token They
Token ID1119
Feature activation+3.45e-02

Pos logit contributions
o+0.045
 alone+0.044
 forth+0.041
 afloat+0.039
 tank+0.039
Neg logit contributions
Her-0.040
 vows-0.038
ves-0.038
 brist-0.038
 blonde-0.035
Token got
Token ID1392
Feature activation+5.19e-02

Pos logit contributions
o+0.120
 alone+0.105
 tank+0.098
 forth+0.097
 afloat+0.096
Neg logit contributions
Her-0.157
ves-0.157
 brist-0.154
 vows-0.154
 blonde-0.141
Token a
Token ID257
Feature activation-6.70e-02

Pos logit contributions
o+0.075
 alone+0.063
 tank+0.060
 forth+0.059
 afloat+0.057
Neg logit contributions
Her-0.118
 brist-0.116
ves-0.114
 vows-0.113
 blush-0.106
Token boo
Token ID22513
Feature activation+2.02e-01

Pos logit contributions
ves+0.133
Her+0.132
 vows+0.132
 brist+0.129
 blonde+0.118
Neg logit contributions
o-0.119
 alone-0.110
 forth-0.099
 tank-0.098
 afloat-0.096
Token-
Token ID12
Feature activation+2.25e-02

Pos logit contributions
o+0.411
 alone+0.378
 tank+0.364
 afloat+0.352
 forth+0.352
Neg logit contributions
ves-0.331
Her-0.330
 brist-0.329
 vows-0.312
ork-0.282
Tokenbo
Token ID2127
Feature activation+3.61e-01

Pos logit contributions
o+0.023
 alone+0.021
 forth+0.017
 tank+0.017
 afloat+0.016
Neg logit contributions
ves-0.061
Her-0.061
 vows-0.060
 brist-0.060
growth-0.056
Tokeno
Token ID78
Feature activation+5.69e-01

Pos logit contributions
 alone+0.046
o+0.039
 forth+0.035
 afloat+0.011
 tank+0.004
Neg logit contributions
ves-1.254
Her-1.237
 vows-1.211
 brist-1.201
ork-1.167
Token on
Token ID319
Feature activation+1.60e-01

Pos logit contributions
o+1.001
 alone+0.926
 forth+0.864
 tank+0.855
 afloat+0.847
Neg logit contributions
ves-1.108
Her-1.090
 vows-1.083
 brist-1.070
ork-0.966
Token her
Token ID607
Feature activation-2.14e-01

Pos logit contributions
o+0.307
 alone+0.296
 forth+0.264
 tank+0.263
my+0.257
Neg logit contributions
ves-0.294
 vows-0.291
Her-0.285
 brist-0.280
 blonde-0.256
Token knee
Token ID10329
Feature activation+8.56e-02

Pos logit contributions
ves+0.426
 vows+0.422
Her+0.421
 brist+0.412
growth+0.378
Neg logit contributions
o-0.380
 alone-0.357
 forth-0.321
 tank-0.318
 afloat-0.309
Token.
Token ID13
Feature activation+2.74e-02

Pos logit contributions
o+0.150
 alone+0.142
 forth+0.126
my+0.123
 tank+0.123
Neg logit contributions
 vows-0.174
ves-0.172
Her-0.170
 brist-0.168
growth-0.158
Token Her
Token ID2332
Feature activation-3.99e-01

Pos logit contributions
o+0.058
 alone+0.055
 tank+0.049
 forth+0.049
my+0.048
Neg logit contributions
ves-0.046
 vows-0.045
Her-0.044
 brist-0.044
growth-0.039
Token a
Token ID257
Feature activation-5.82e-02

Pos logit contributions
o+0.280
 alone+0.273
my+0.237
 tank+0.234
 wreck+0.229
Neg logit contributions
ves-0.310
 vows-0.303
Her-0.303
 brist-0.292
growth-0.277
Token big
Token ID1263
Feature activation+4.77e-02

Pos logit contributions
ves+0.110
Her+0.109
 vows+0.109
 brist+0.107
growth+0.098
Neg logit contributions
o-0.108
 alone-0.101
 forth-0.092
 tank-0.091
 afloat-0.089
Token boo
Token ID22513
Feature activation+2.03e-01

Pos logit contributions
o+0.089
 alone+0.079
 forth+0.072
 afloat+0.071
|+0.070
Neg logit contributions
 vows-0.090
 brist-0.090
ves-0.089
Her-0.088
 blonde-0.082
Token-
Token ID12
Feature activation+2.38e-02

Pos logit contributions
o+0.416
 alone+0.387
 forth+0.361
 tank+0.359
 afloat+0.355
Neg logit contributions
ves-0.337
Her-0.333
 brist-0.331
 vows-0.326
 blonde-0.286
Tokenbo
Token ID2127
Feature activation+3.58e-01

Pos logit contributions
o+0.032
 alone+0.029
 forth+0.026
 tank+0.025
 afloat+0.024
Neg logit contributions
ves-0.057
Her-0.057
 vows-0.056
 brist-0.056
growth-0.052
Tokeno
Token ID78
Feature activation+5.68e-01

Pos logit contributions
o+0.153
 alone+0.135
 forth+0.115
 afloat+0.095
 tank+0.084
Neg logit contributions
ves-1.147
Her-1.132
 vows-1.120
 brist-1.106
 blonde-1.056
Token on
Token ID319
Feature activation+1.64e-01

Pos logit contributions
o+1.046
 alone+0.963
 forth+0.896
 tank+0.875
 afloat+0.871
Neg logit contributions
ves-1.075
Her-1.059
 vows-1.056
 brist-1.040
 blonde-0.944
Token his
Token ID465
Feature activation+3.22e-01

Pos logit contributions
o+0.164
 alone+0.149
 tank+0.120
 forth+0.117
my+0.110
Neg logit contributions
ves-0.456
 vows-0.455
Her-0.449
 brist-0.444
 blonde-0.418
Token knee
Token ID10329
Feature activation+8.86e-02

Pos logit contributions
o+0.583
 alone+0.549
 forth+0.495
 tank+0.492
 afloat+0.476
Neg logit contributions
ves-0.627
 vows-0.622
Her-0.620
 brist-0.608
 blonde-0.555
Token.
Token ID13
Feature activation+2.75e-02

Pos logit contributions
o+0.153
 alone+0.144
 forth+0.125
my+0.124
 tank+0.124
Neg logit contributions
 vows-0.184
ves-0.182
Her-0.181
 brist-0.179
growth-0.169
Token He
Token ID679
Feature activation+2.97e-01

Pos logit contributions
o+0.041
 forth+0.040
 alone+0.040
 afloat+0.038
 wreck+0.034
Neg logit contributions
Her-0.060
 Her-0.058
 brist-0.056
 blonde-0.055
ves-0.053
Token sky
Token ID6766
Feature activation-7.77e-02

Pos logit contributions
o+0.348
 alone+0.314
 forth+0.298
 afloat+0.291
 tank+0.290
Neg logit contributions
 brist-0.213
 vows-0.213
Her-0.211
ves-0.210
growth-0.188
Token.
Token ID13
Feature activation+3.28e-02

Pos logit contributions
 vows+0.161
ves+0.160
Her+0.160
 brist+0.157
growth+0.146
Neg logit contributions
o-0.133
 alone-0.127
 forth-0.110
 tank-0.109
my-0.108
Token The
Token ID383
Feature activation+5.50e-02

Pos logit contributions
o+0.061
 alone+0.057
 forth+0.052
 tank+0.051
 afloat+0.050
Neg logit contributions
ves-0.061
Her-0.061
 vows-0.061
 brist-0.060
 blonde-0.055
Token dove
Token ID38862
Feature activation-7.39e-02

Pos logit contributions
o+0.106
 alone+0.099
 forth+0.091
 tank+0.090
 afloat+0.088
Neg logit contributions
ves-0.100
Her-0.099
 vows-0.099
 brist-0.097
 blonde-0.088
Token co
Token ID763
Feature activation+7.09e-02

Pos logit contributions
Her+0.144
 vows+0.143
ves+0.143
 brist+0.142
growth+0.131
Neg logit contributions
o-0.134
 alone-0.128
 forth-0.114
 tank-0.111
my-0.110
Tokeno
Token ID78
Feature activation+5.68e-01

Pos logit contributions
o+0.112
 alone+0.099
 forth+0.088
 tank+0.086
my+0.085
Neg logit contributions
 vows-0.158
ves-0.158
Her-0.156
 brist-0.155
growth-0.144
Tokened
Token ID276
Feature activation-1.22e-01

Pos logit contributions
o+1.056
 alone+0.962
 forth+0.841
 tank+0.834
my+0.834
Neg logit contributions
Her-1.134
 vows-1.102
ves-1.101
 brist-1.093
 blonde-1.009
Token softly
Token ID26625
Feature activation-7.76e-02

Pos logit contributions
ves+0.266
Her+0.264
 vows+0.264
 brist+0.259
growth+0.239
Neg logit contributions
o-0.194
 alone-0.178
 forth-0.159
 tank-0.156
 afloat-0.152
Token,
Token ID11
Feature activation+2.06e-02

Pos logit contributions
ves+0.177
Her+0.170
 vows+0.170
 brist+0.165
growth+0.157
Neg logit contributions
o-0.123
 alone-0.116
 forth-0.102
 tank-0.099
 afloat-0.097
Token and
Token ID290
Feature activation+4.50e-02

Pos logit contributions
o+0.036
 alone+0.032
 tank+0.030
 forth+0.029
 afloat+0.029
Neg logit contributions
Her-0.041
 brist-0.040
ves-0.040
 vows-0.040
 blonde-0.037
Token the
Token ID262
Feature activation+1.30e-01

Pos logit contributions
o+0.080
 alone+0.073
 tank+0.068
 afloat+0.066
 wreck+0.066
Neg logit contributions
ves-0.085
Her-0.085
 vows-0.085
 brist-0.083
 blonde-0.076
Token."
Token ID526
Feature activation+2.10e-01

Pos logit contributions
 vows+0.029
ves+0.028
Her+0.028
 brist+0.027
 blonde+0.025
Neg logit contributions
o-0.024
|-0.020
 forth-0.020
 alone-0.019
 afloat-0.019
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
o+0.351
 alone+0.327
 forth+0.305
 afloat+0.298
 tank+0.294
Neg logit contributions
Her-0.437
ves-0.423
 vows-0.418
 brist-0.411
 blonde-0.384
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
 forth+0.274
o+0.264
 alone+0.264
 afloat+0.258
 tank+0.249
Neg logit contributions
Her-0.306
ves-0.281
 Her-0.247
 brist-0.246
ork-0.238
TokenThe
Token ID464
Feature activation-6.31e-02

Pos logit contributions
o+0.318
 alone+0.304
 forth+0.284
 tank+0.281
 afloat+0.277
Neg logit contributions
Her-0.248
ves-0.239
 vows-0.226
 brist-0.225
 blonde-0.202
Token hipp
Token ID18568
Feature activation+3.00e-01

Pos logit contributions
 vows+0.126
ves+0.126
Her+0.125
 brist+0.124
 blonde+0.113
Neg logit contributions
o-0.110
 alone-0.100
 forth-0.091
 afloat-0.089
 tank-0.088
Tokeno
Token ID78
Feature activation+5.68e-01

Pos logit contributions
 alone+0.110
 afloat+0.094
 forth+0.083
o+0.043
 polar+0.040
Neg logit contributions
ves-0.965
 vows-0.955
Her-0.938
 brist-0.901
owers-0.880
Token was
Token ID373
Feature activation+2.68e-02

Pos logit contributions
o+1.006
 alone+0.936
 forth+0.848
 tank+0.833
 afloat+0.818
Neg logit contributions
ves-1.120
 vows-1.113
Her-1.109
 brist-1.090
growth-0.995
Token confused
Token ID10416
Feature activation+1.96e-01

Pos logit contributions
o+0.042
 forth+0.038
|+0.036
 alone+0.035
 afloat+0.035
Neg logit contributions
Her-0.056
ves-0.056
 brist-0.054
 vows-0.054
 blonde-0.052
Token and
Token ID290
Feature activation+4.82e-02

Pos logit contributions
o+0.370
 alone+0.344
 forth+0.314
 tank+0.310
 afloat+0.304
Neg logit contributions
ves-0.369
Her-0.368
 vows-0.365
 brist-0.360
 blonde-0.327
Token asked
Token ID1965
Feature activation+1.26e-01

Pos logit contributions
o+0.081
 afloat+0.068
|+0.067
 alone+0.067
my+0.066
Neg logit contributions
Her-0.096
 vows-0.095
ves-0.095
 brist-0.091
 blonde-0.087
Token,
Token ID11
Feature activation+1.40e-02

Pos logit contributions
o+0.207
 alone+0.190
 tank+0.165
my+0.163
 forth+0.162
Neg logit contributions
 vows-0.271
ves-0.271
 brist-0.270
Her-0.268
growth-0.250
Token minutes
Token ID2431
Feature activation-5.31e-02

Pos logit contributions
Her+0.241
 vows+0.232
 brist+0.222
ves+0.221
growth+0.204
Neg logit contributions
 alone-0.243
o-0.224
 tank-0.208
 forth-0.206
 wreck-0.199
Token,
Token ID11
Feature activation+2.66e-02

Pos logit contributions
 vows+0.116
Her+0.114
ves+0.113
 brist+0.112
 blonde+0.102
Neg logit contributions
o-0.089
 alone-0.082
 forth-0.073
my-0.072
 tank-0.069
Token then
Token ID788
Feature activation+2.70e-02

Pos logit contributions
o+0.046
 alone+0.043
 forth+0.039
 tank+0.038
my+0.037
Neg logit contributions
ves-0.054
 vows-0.054
Her-0.053
 brist-0.052
growth-0.048
Token t
Token ID256
Feature activation+2.91e-02

Pos logit contributions
o+0.044
 alone+0.041
 forth+0.037
 tank+0.035
my+0.035
Neg logit contributions
ves-0.057
 vows-0.057
Her-0.057
 brist-0.056
growth-0.054
Tokenipt
Token ID10257
Feature activation+9.47e-02

Pos logit contributions
o+0.050
 alone+0.041
my+0.039
 forth+0.038
 polar+0.036
Neg logit contributions
ves-0.064
 vows-0.064
 brist-0.062
Her-0.060
 blonde-0.058
Tokeno
Token ID78
Feature activation+5.67e-01

Pos logit contributions
 alone+0.126
 tank+0.122
o+0.121
 afloat+0.118
 forth+0.114
Neg logit contributions
Her-0.220
ves-0.206
 vows-0.202
 brist-0.200
 Her-0.188
Tokened
Token ID276
Feature activation-1.27e-01

Pos logit contributions
o+1.269
 alone+1.173
 forth+1.070
 tank+1.056
my+1.054
Neg logit contributions
Her-0.890
ves-0.883
 vows-0.877
 brist-0.873
growth-0.787
Token back
Token ID736
Feature activation+2.58e-01

Pos logit contributions
ves+0.308
Her+0.304
 vows+0.303
 brist+0.298
growth+0.277
Neg logit contributions
o-0.174
 alone-0.161
 forth-0.138
 tank-0.136
my-0.131
Token to
Token ID284
Feature activation-1.45e-02

Pos logit contributions
o+0.388
 alone+0.357
 forth+0.314
 tank+0.307
my+0.298
Neg logit contributions
ves-0.585
 vows-0.580
Her-0.579
 brist-0.569
growth-0.528
Token the
Token ID262
Feature activation+1.33e-01

Pos logit contributions
Her+0.032
 vows+0.032
ves+0.032
 brist+0.032
growth+0.029
Neg logit contributions
o-0.022
 alone-0.020
 forth-0.018
 tank-0.018
 afloat-0.017
Token table
Token ID3084
Feature activation-1.13e-01

Pos logit contributions
o+0.258
 alone+0.245
 tank+0.224
 forth+0.223
 polar+0.216
Neg logit contributions
ves-0.242
Her-0.239
 vows-0.235
 brist-0.231
growth-0.209
Token So
Token ID1406
Feature activation-2.58e-02

Pos logit contributions
ves+0.554
 vows+0.550
Her+0.549
 brist+0.540
growth+0.496
Neg logit contributions
o-0.472
 alone-0.436
 forth-0.395
 tank-0.388
my-0.378
Token,
Token ID11
Feature activation+2.19e-02

Pos logit contributions
ves+0.047
 vows+0.047
Her+0.047
 brist+0.046
growth+0.042
Neg logit contributions
o-0.049
 alone-0.046
 forth-0.042
 tank-0.041
my-0.040
Token the
Token ID262
Feature activation+1.36e-01

Pos logit contributions
o+0.039
 alone+0.036
 forth+0.033
 tank+0.032
 afloat+0.032
Neg logit contributions
ves-0.043
Her-0.043
 vows-0.042
 brist-0.041
 blonde-0.038
Token little
Token ID1310
Feature activation-5.93e-03

Pos logit contributions
o+0.238
 alone+0.220
 forth+0.199
 tank+0.196
 afloat+0.192
Neg logit contributions
ves-0.271
Her-0.270
 vows-0.269
 brist-0.265
 blonde-0.242
Token hipp
Token ID18568
Feature activation+3.01e-01

Pos logit contributions
 brist+0.013
 vows+0.013
ves+0.013
Her+0.013
 ribbon+0.012
Neg logit contributions
o-0.009
 alone-0.008
 afloat-0.007
|-0.007
 forth-0.007
Tokeno
Token ID78
Feature activation+5.66e-01

Pos logit contributions
 alone+0.084
 forth+0.061
 afloat+0.045
o+0.024
 polar-0.004
Neg logit contributions
ves-1.000
 vows-0.992
Her-0.982
 brist-0.938
owers-0.928
Token went
Token ID1816
Feature activation+4.89e-02

Pos logit contributions
o+0.995
 alone+0.902
 tank+0.814
 forth+0.804
my+0.786
Neg logit contributions
Her-1.156
ves-1.144
 vows-1.132
 brist-1.128
 blonde-1.038
Token to
Token ID284
Feature activation-5.41e-03

Pos logit contributions
o+0.082
 alone+0.072
 forth+0.072
 afloat+0.067
|+0.066
Neg logit contributions
Her-0.094
ves-0.093
 vows-0.090
 brist-0.086
 ribbon-0.083
Token the
Token ID262
Feature activation+1.40e-01

Pos logit contributions
 vows+0.011
Her+0.011
ves+0.011
 brist+0.010
growth+0.010
Neg logit contributions
o-0.010
 alone-0.008
 forth-0.008
my-0.008
 afloat-0.007
Token river
Token ID7850
Feature activation+1.88e-01

Pos logit contributions
o+0.252
 alone+0.229
 forth+0.214
 afloat+0.206
my+0.200
Neg logit contributions
 vows-0.275
ves-0.262
Her-0.260
 brist-0.258
growth-0.240
Token and
Token ID290
Feature activation+4.74e-02

Pos logit contributions
o+0.351
 alone+0.322
 forth+0.307
 polar+0.292
 afloat+0.289
Neg logit contributions
ves-0.341
Her-0.333
 vows-0.331
 brist-0.324
growth-0.296
Token Ch
Token ID609
Feature activation+1.64e-01

Pos logit contributions
o+0.228
 alone+0.210
 forth+0.187
 tank+0.184
 afloat+0.179
Neg logit contributions
ves-0.325
Her-0.323
 vows-0.322
 brist-0.317
 blonde-0.293
Tokenir
Token ID343
Feature activation-8.29e-02

Pos logit contributions
o+0.366
 alone+0.355
 forth+0.344
 afloat+0.323
 tank+0.321
Neg logit contributions
Her-0.240
ves-0.240
 vows-0.233
 brist-0.228
growth-0.208
Tokenpy
Token ID9078
Feature activation+1.66e-01

Pos logit contributions
ves+0.185
Her+0.184
 vows+0.184
 brist+0.181
 blonde+0.167
Neg logit contributions
o-0.125
 alone-0.115
 forth-0.102
 tank-0.101
 afloat-0.098
Token.
Token ID13
Feature activation+3.83e-02

Pos logit contributions
o+0.301
 alone+0.275
my+0.244
 tank+0.241
 forth+0.240
Neg logit contributions
ves-0.334
 vows-0.334
 brist-0.325
Her-0.325
growth-0.300
Token Bob
Token ID5811
Feature activation+2.27e-01

Pos logit contributions
o+0.062
 alone+0.057
 forth+0.051
 tank+0.050
 afloat+0.049
Neg logit contributions
ves-0.082
 vows-0.081
Her-0.081
 brist-0.080
 blonde-0.073
Tokeno
Token ID78
Feature activation+5.66e-01

Pos logit contributions
o+0.023
 alone+0.023
 forth-0.011
 afloat-0.019
 tank-0.023
Neg logit contributions
Her-0.798
ves-0.797
 vows-0.791
 brist-0.788
 blonde-0.752
Token said
Token ID531
Feature activation+1.23e-01

Pos logit contributions
o+0.975
 alone+0.858
 tank+0.780
my+0.770
 forth+0.760
Neg logit contributions
Her-1.181
ves-1.175
 vows-1.173
 brist-1.158
growth-1.093
Token,
Token ID11
Feature activation+2.49e-02

Pos logit contributions
o+0.191
 alone+0.179
 tank+0.146
my+0.141
 forth+0.136
Neg logit contributions
growth-0.273
 vows-0.273
 brist-0.272
Her-0.264
ves-0.262
Token "
Token ID366
Feature activation-5.01e-02

Pos logit contributions
o+0.051
 alone+0.047
 tank+0.043
 forth+0.042
my+0.042
Neg logit contributions
 vows-0.043
ves-0.043
Her-0.042
 brist-0.042
growth-0.039
TokenI
Token ID40
Feature activation+2.80e-02

Pos logit contributions
Her+0.089
ves+0.087
 vows+0.085
 brist+0.085
 blonde+0.076
Neg logit contributions
o-0.098
 alone-0.095
 tank-0.087
 forth-0.087
 afloat-0.086
Token found
Token ID1043
Feature activation+1.01e-01

Pos logit contributions
o+0.046
 alone+0.043
 forth+0.042
 afloat+0.039
 tank+0.038
Neg logit contributions
ves-0.057
 vows-0.057
Her-0.056
 brist-0.055
 blonde-0.051
Token put
Token ID1234
Feature activation+7.47e-02

Pos logit contributions
o+0.459
 alone+0.420
 forth+0.377
 tank+0.377
my+0.372
Neg logit contributions
Her-0.491
ves-0.481
 vows-0.481
 brist-0.478
 blonde-0.443
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
o+0.111
 alone+0.102
 forth+0.090
 tank+0.089
my+0.086
Neg logit contributions
ves-0.170
Her-0.169
 vows-0.169
 brist-0.165
growth-0.154
Token leaves
Token ID5667
Feature activation-5.63e-02

Pos logit contributions
o+0.304
 alone+0.291
 tank+0.268
 forth+0.265
 polar+0.257
Neg logit contributions
Her-0.274
ves-0.271
 vows-0.265
 brist-0.258
growth-0.239
Token on
Token ID319
Feature activation+1.69e-01

Pos logit contributions
 vows+0.143
ves+0.141
Her+0.139
 brist+0.138
growth+0.131
Neg logit contributions
o-0.072
 alone-0.068
 forth-0.057
 tank-0.055
 afloat-0.055
Token Bob
Token ID5811
Feature activation+2.27e-01

Pos logit contributions
o+0.209
 alone+0.192
 tank+0.176
 polar+0.163
my+0.159
Neg logit contributions
 vows-0.421
ves-0.419
Her-0.402
 brist-0.397
 blush-0.381
Tokeno
Token ID78
Feature activation+5.65e-01

Pos logit contributions
o+0.365
 alone+0.323
 forth+0.290
my+0.287
 tank+0.285
Neg logit contributions
ves-0.508
 vows-0.506
Her-0.499
 brist-0.492
growth-0.457
Token's
Token ID338
Feature activation+1.10e-01

Pos logit contributions
o+0.916
 alone+0.827
 tank+0.721
my+0.715
 forth+0.711
Neg logit contributions
Her-1.255
 vows-1.239
ves-1.226
 brist-1.206
growth-1.148
Token head
Token ID1182
Feature activation+1.53e-01

Pos logit contributions
o+0.210
 alone+0.209
 tank+0.190
 forth+0.185
 polar+0.180
Neg logit contributions
ves-0.204
Her-0.198
 vows-0.195
 brist-0.185
growth-0.175
Token.
Token ID13
Feature activation+2.83e-02

Pos logit contributions
o+0.230
 alone+0.212
my+0.185
 tank+0.179
 forth+0.171
Neg logit contributions
ves-0.353
 vows-0.348
Her-0.346
growth-0.339
 brist-0.336
Token Now
Token ID2735
Feature activation+2.74e-02

Pos logit contributions
o+0.044
 alone+0.043
 forth+0.040
 afloat+0.037
 tank+0.037
Neg logit contributions
Her-0.060
ves-0.059
 vows-0.059
 brist-0.058
 blonde-0.055
Token,
Token ID11
Feature activation+1.86e-02

Pos logit contributions
o+0.046
 alone+0.042
 forth+0.038
 tank+0.038
 afloat+0.037
Neg logit contributions
ves-0.057
 vows-0.057
Her-0.057
 brist-0.055
 blonde-0.051
Token a
Token ID257
Feature activation-7.30e-02

Pos logit contributions
o+0.053
 alone+0.052
 tank+0.045
my+0.045
 polar+0.043
Neg logit contributions
ves-0.051
 vows-0.050
Her-0.048
 brist-0.048
growth-0.044
Token purple
Token ID14032
Feature activation-4.20e-02

Pos logit contributions
 vows+0.127
 brist+0.125
ves+0.124
Her+0.124
 ribbon+0.116
Neg logit contributions
o-0.146
 alone-0.131
 forth-0.121
 afloat-0.120
|-0.120
Token bird
Token ID6512
Feature activation+4.48e-02

Pos logit contributions
ves+0.086
Her+0.085
 vows+0.083
 brist+0.081
growth+0.077
Neg logit contributions
o-0.073
 alone-0.069
 tank-0.065
 forth-0.062
 polar-0.061
Token named
Token ID3706
Feature activation+1.49e-01

Pos logit contributions
o+0.078
 alone+0.072
 forth+0.069
 afloat+0.069
 tank+0.067
Neg logit contributions
ves-0.086
Her-0.085
 vows-0.081
 brist-0.081
 blonde-0.074
Token Bob
Token ID5811
Feature activation+2.28e-01

Pos logit contributions
o+0.214
 alone+0.195
 forth+0.174
 tank+0.169
 afloat+0.165
Neg logit contributions
ves-0.345
Her-0.344
 vows-0.342
 brist-0.338
 blonde-0.314
Tokeno
Token ID78
Feature activation+5.64e-01

Pos logit contributions
 forth+0.431
 alone+0.423
 afloat+0.408
o+0.404
 wreck+0.401
Neg logit contributions
Her-0.378
ves-0.374
 vows-0.357
 brist-0.334
 Her-0.328
Token.
Token ID13
Feature activation+3.20e-02

Pos logit contributions
o+1.061
 alone+1.000
 forth+0.930
 tank+0.900
 afloat+0.897
Neg logit contributions
ves-1.038
Her-1.033
 vows-1.024
 brist-0.997
 blonde-0.907
Token Bob
Token ID5811
Feature activation+2.20e-01

Pos logit contributions
 alone+0.050
o+0.049
 forth+0.049
 afloat+0.045
 wreck+0.043
Neg logit contributions
Her-0.065
 vows-0.063
ves-0.062
 Her-0.062
 blonde-0.061
Tokeno
Token ID78
Feature activation+5.56e-01

Pos logit contributions
 forth+0.083
 afloat+0.081
 alone+0.080
 wreck+0.052
 tank+0.035
Neg logit contributions
Her-0.680
ves-0.667
 brist-0.661
 vows-0.657
 Her-0.646
Token loved
Token ID6151
Feature activation+7.32e-03

Pos logit contributions
o+1.050
 alone+0.986
 forth+0.908
 afloat+0.889
 tank+0.888
Neg logit contributions
ves-1.018
Her-1.010
 vows-1.009
 brist-0.985
 blonde-0.894
Token to
Token ID284
Feature activation-1.59e-02

Pos logit contributions
o+0.015
 alone+0.014
 forth+0.013
 tank+0.012
 afloat+0.012
Neg logit contributions
ves-0.013
 vows-0.013
Her-0.013
 brist-0.012
 blonde-0.011
Token ever
Token ID1683
Feature activation-2.39e-02

Pos logit contributions
o+0.027
 alone+0.027
 forth+0.024
my+0.023
 tank+0.023
Neg logit contributions
ves-0.028
 vows-0.028
Her-0.028
 brist-0.027
growth-0.025
Token before
Token ID878
Feature activation-1.96e-02

Pos logit contributions
ves+0.040
 brist+0.040
Her+0.040
 vows+0.039
 blonde+0.037
Neg logit contributions
o-0.047
 tank-0.042
 alone-0.042
 polar-0.041
 afloat-0.040
Token.
Token ID13
Feature activation-6.00e-02

Pos logit contributions
 vows+0.050
ves+0.047
 brist+0.046
Her+0.045
 blush+0.043
Neg logit contributions
 alone-0.028
o-0.025
 forth-0.021
my-0.020
 afloat-0.019
Token
Token ID198
Feature activation+4.45e-02

Pos logit contributions
ves+0.131
 vows+0.127
 brist+0.121
Her+0.118
 ribbon+0.114
Neg logit contributions
o-0.105
 alone-0.094
my-0.085
 tank-0.081
|-0.079
Token
Token ID198
Feature activation+4.36e-02

Pos logit contributions
o+0.068
 alone+0.061
 tank+0.053
my+0.052
 forth+0.052
Neg logit contributions
 vows-0.101
 brist-0.099
ves-0.099
Her-0.098
 blonde-0.093
TokenHer
Token ID9360
Feature activation-5.72e-01

Pos logit contributions
o+0.081
 alone+0.072
my+0.068
|+0.067
 forth+0.064
Neg logit contributions
 vows-0.086
 brist-0.082
 blonde-0.081
rings-0.076
 blush-0.075
Token mum
Token ID25682
Feature activation-2.40e-01

Pos logit contributions
ves+0.851
Her+0.821
 vows+0.792
 brist+0.782
growth+0.719
Neg logit contributions
o-1.313
 alone-1.267
 forth-1.193
 tank-1.174
 afloat-1.143
Token was
Token ID373
Feature activation-7.11e-02

Pos logit contributions
ves+0.455
 vows+0.451
Her+0.450
 brist+0.442
 blonde+0.401
Neg logit contributions
o-0.433
 alone-0.409
 forth-0.369
 afloat-0.367
 tank-0.366
Token happy
Token ID3772
Feature activation+1.55e-01

Pos logit contributions
Her+0.162
ves+0.157
 vows+0.157
 brist+0.155
 blonde+0.145
Neg logit contributions
o-0.107
 alone-0.093
 forth-0.087
 tank-0.086
 afloat-0.083
Token that
Token ID326
Feature activation-1.89e-01

Pos logit contributions
o+0.277
 alone+0.263
 forth+0.229
my+0.225
 tank+0.218
Neg logit contributions
ves-0.329
 vows-0.320
Her-0.306
 brist-0.305
growth-0.298
Token Daisy
Token ID40355
Feature activation-1.12e-01

Pos logit contributions
 vows+0.343
ves+0.342
 brist+0.331
Her+0.331
growth+0.301
Neg logit contributions
o-0.374
 alone-0.364
 forth-0.330
my-0.322
 tank-0.313
Token it
Token ID340
Feature activation-8.19e-02

Pos logit contributions
 vows+0.054
ves+0.053
Her+0.053
 brist+0.052
growth+0.049
Neg logit contributions
o-0.039
 alone-0.039
 tank-0.034
 forth-0.034
my-0.033
Token.
Token ID13
Feature activation-6.23e-02

Pos logit contributions
 vows+0.197
ves+0.192
 brist+0.190
Her+0.187
growth+0.183
Neg logit contributions
 alone-0.118
o-0.118
my-0.097
 tank-0.095
 forth-0.093
Token
Token ID220
Feature activation+4.68e-02

Pos logit contributions
ves+0.141
 brist+0.139
 vows+0.137
 blonde+0.130
growth+0.127
Neg logit contributions
o-0.104
my-0.079
 alone-0.079
 tank-0.073
 forth-0.067
Token
Token ID198
Feature activation+4.27e-02

Pos logit contributions
o+0.067
 alone+0.059
my+0.050
 tank+0.050
 forth+0.050
Neg logit contributions
 vows-0.111
ves-0.109
 brist-0.108
Her-0.108
growth-0.101
Token
Token ID198
Feature activation+4.19e-02

Pos logit contributions
o+0.056
 alone+0.047
my+0.040
 tank+0.038
|+0.037
Neg logit contributions
 vows-0.107
 brist-0.107
ves-0.104
Her-0.101
 blonde-0.099
TokenHer
Token ID9360
Feature activation-5.72e-01

Pos logit contributions
o+0.081
my+0.068
 forth+0.068
 alone+0.066
ny+0.066
Neg logit contributions
 brist-0.068
 vows-0.067
 icing-0.066
der-0.065
 blonde-0.064
Token mom
Token ID1995
Feature activation-1.24e-01

Pos logit contributions
ves+1.189
Her+1.130
 vows+1.119
growth+1.112
 brist+1.097
Neg logit contributions
o-1.020
 alone-0.936
my-0.882
 forth-0.855
 tank-0.851
Token showed
Token ID3751
Feature activation-7.38e-02

Pos logit contributions
ves+0.276
Her+0.272
 vows+0.272
 brist+0.266
growth+0.258
Neg logit contributions
o-0.205
 alone-0.170
my-0.168
 forth-0.160
 tank-0.156
Token her
Token ID607
Feature activation-3.12e-01

Pos logit contributions
 vows+0.128
ves+0.127
 brist+0.121
 blonde+0.118
Her+0.117
Neg logit contributions
o-0.152
 alone-0.136
my-0.133
 forth-0.121
ny-0.121
Token how
Token ID703
Feature activation-1.48e-01

Pos logit contributions
ves+0.761
 vows+0.746
 brist+0.708
owers+0.701
Her+0.694
Neg logit contributions
 alone-0.439
o-0.418
my-0.372
 tank-0.359
 down-0.317
Token to
Token ID284
Feature activation-1.04e-01

Pos logit contributions
ves+0.326
 vows+0.325
 brist+0.317
growth+0.302
Her+0.301
Neg logit contributions
o-0.244
 alone-0.234
 tank-0.187
my-0.185
 forth-0.179
Token her
Token ID607
Feature activation-3.11e-01

Pos logit contributions
ves+0.189
 vows+0.179
 brist+0.178
Her+0.171
 blonde+0.159
Neg logit contributions
 alone-0.204
o-0.200
 tank-0.177
 forth-0.176
my-0.175
Token mom
Token ID1995
Feature activation-1.24e-01

Pos logit contributions
ves+0.620
Her+0.616
 vows+0.616
 brist+0.604
 blonde+0.553
Neg logit contributions
o-0.552
 alone-0.511
 forth-0.462
 tank-0.456
 afloat-0.445
Token.
Token ID13
Feature activation-6.14e-02

Pos logit contributions
Her+0.214
 brist+0.197
 vows+0.196
ves+0.194
 Her+0.186
Neg logit contributions
o-0.232
 alone-0.218
 afloat-0.210
 wreck-0.208
 polar-0.206
Token
Token ID198
Feature activation+4.23e-02

Pos logit contributions
ves+0.167
 vows+0.161
 brist+0.159
growth+0.154
comb+0.150
Neg logit contributions
o-0.073
my-0.053
 alone-0.053
 Tim-0.046
 tank-0.045
Token
Token ID198
Feature activation+4.26e-02

Pos logit contributions
o+0.059
 alone+0.051
 tank+0.043
my+0.043
 forth+0.041
Neg logit contributions
 vows-0.102
 brist-0.101
ves-0.100
Her-0.098
 blonde-0.095
TokenHer
Token ID9360
Feature activation-5.72e-01

Pos logit contributions
o+0.061
 alone+0.055
my+0.051
 forth+0.047
|+0.045
Neg logit contributions
 vows-0.097
 brist-0.094
 blonde-0.091
growth-0.090
der-0.089
Token mom
Token ID1995
Feature activation-1.25e-01

Pos logit contributions
ves+1.120
Her+1.087
 vows+1.067
 brist+1.042
growth+1.020
Neg logit contributions
o-1.058
 alone-1.011
 tank-0.921
 forth-0.917
my-0.901
Token smiled
Token ID13541
Feature activation-3.37e-02

Pos logit contributions
ves+0.274
 vows+0.272
Her+0.270
 brist+0.266
growth+0.256
Neg logit contributions
o-0.211
 alone-0.176
my-0.174
 forth-0.164
 tank-0.160
Token when
Token ID618
Feature activation-6.11e-02

Pos logit contributions
ves+0.074
 vows+0.071
Her+0.070
 brist+0.070
growth+0.065
Neg logit contributions
o-0.055
 alone-0.052
 forth-0.046
 tank-0.045
my-0.045
Token she
Token ID673
Feature activation-3.50e-01

Pos logit contributions
 vows+0.109
 brist+0.108
growth+0.107
ves+0.107
Her+0.094
Neg logit contributions
 alone-0.123
o-0.115
my-0.110
 forth-0.110
 Tim-0.106
Token saw
Token ID2497
Feature activation+5.95e-02

Pos logit contributions
 vows+0.829
ves+0.819
 brist+0.817
Her+0.815
 blonde+0.754
Neg logit contributions
o-0.514
 alone-0.444
my-0.399
 forth-0.396
 tank-0.386
Token it
Token ID340
Feature activation-8.29e-02

Pos logit contributions
o+0.145
 alone+0.144
 forth+0.123
my+0.121
 tank+0.119
Neg logit contributions
ves-0.198
 vows-0.197
 brist-0.196
Her-0.195
 blonde-0.182
Token back
Token ID736
Feature activation+1.63e-01

Pos logit contributions
ves+0.179
Her+0.179
 vows+0.178
 brist+0.174
 blonde+0.160
Neg logit contributions
o-0.131
 alone-0.120
 forth-0.108
 tank-0.106
 afloat-0.104
Token."
Token ID526
Feature activation+1.09e-01

Pos logit contributions
o+0.266
 alone+0.242
 forth+0.228
 tank+0.224
 afloat+0.224
Neg logit contributions
ves-0.339
Her-0.338
 vows-0.335
 brist-0.325
ork-0.298
Token
Token ID198
Feature activation+4.39e-02

Pos logit contributions
o+0.150
 alone+0.139
my+0.117
 tank+0.106
 forth+0.102
Neg logit contributions
 vows-0.274
ves-0.271
 brist-0.253
growth-0.244
 blonde-0.239
Token
Token ID198
Feature activation+4.32e-02

Pos logit contributions
o+0.072
 alone+0.066
 forth+0.062
 tank+0.060
 afloat+0.059
Neg logit contributions
Her-0.096
ves-0.093
 brist-0.090
 vows-0.089
growth-0.082
TokenHer
Token ID9360
Feature activation-5.72e-01

Pos logit contributions
o+0.133
 alone+0.130
my+0.121
 forth+0.121
 tank+0.116
Neg logit contributions
 vows-0.035
ves-0.029
 brist-0.026
growth-0.024
 blonde-0.022
Token mom
Token ID1995
Feature activation-1.27e-01

Pos logit contributions
ves+1.013
 vows+0.989
Her+0.986
 brist+0.969
growth+0.900
Neg logit contributions
o-1.151
 alone-1.093
 forth-0.991
 tank-0.988
my-0.972
Token smiled
Token ID13541
Feature activation-3.32e-02

Pos logit contributions
ves+0.264
 vows+0.264
Her+0.262
 brist+0.257
growth+0.241
Neg logit contributions
o-0.217
 alone-0.196
 forth-0.176
my-0.175
 tank-0.175
Token and
Token ID290
Feature activation-4.11e-02

Pos logit contributions
Her+0.061
 vows+0.059
 brist+0.059
ves+0.058
 blonde+0.052
Neg logit contributions
o-0.064
 alone-0.058
 forth-0.054
 tank-0.054
 afloat-0.053
Token hugged
Token ID41130
Feature activation-5.93e-02

Pos logit contributions
ves+0.088
 vows+0.087
Her+0.087
 brist+0.085
 blonde+0.079
Neg logit contributions
o-0.067
 alone-0.061
 forth-0.055
 tank-0.054
my-0.053
Token her
Token ID607
Feature activation-3.12e-01

Pos logit contributions
ves+0.107
 vows+0.106
 brist+0.099
Her+0.097
 blonde+0.092
Neg logit contributions
o-0.117
 alone-0.117
my-0.105
 forth-0.103
 tank-0.099
Token and
Token ID290
Feature activation-4.18e-02

Pos logit contributions
ves+0.424
Her+0.422
 vows+0.420
 brist+0.412
growth+0.386
Neg logit contributions
o-0.249
 alone-0.227
 forth-0.197
 tank-0.194
my-0.188
Token happy
Token ID3772
Feature activation+1.50e-01

Pos logit contributions
ves+0.083
Her+0.083
 vows+0.082
 brist+0.081
growth+0.074
Neg logit contributions
o-0.074
 alone-0.069
 forth-0.062
 tank-0.062
 afloat-0.060
Token!"
Token ID2474
Feature activation+1.13e-01

Pos logit contributions
o+0.190
 alone+0.182
 forth+0.151
my+0.142
 tank+0.141
Neg logit contributions
ves-0.379
Her-0.376
 vows-0.374
 brist-0.367
growth-0.354
Token
Token ID198
Feature activation+4.21e-02

Pos logit contributions
o+0.175
 alone+0.168
my+0.142
 forth+0.136
 tank+0.131
Neg logit contributions
 vows-0.261
ves-0.255
 brist-0.239
growth-0.236
 blonde-0.229
Token
Token ID198
Feature activation+4.18e-02

Pos logit contributions
o+0.066
 alone+0.060
 forth+0.055
 tank+0.053
 afloat+0.052
Neg logit contributions
ves-0.092
Her-0.092
 vows-0.091
 brist-0.090
growth-0.083
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.071
 alone+0.070
 forth+0.066
my+0.062
|+0.057
Neg logit contributions
 vows-0.086
growth-0.079
 blonde-0.077
 brist-0.076
ves-0.074
Token mom
Token ID1995
Feature activation-1.29e-01

Pos logit contributions
ves+1.020
Her+1.010
 vows+0.992
 brist+0.981
growth+0.911
Neg logit contributions
o-1.134
 alone-1.078
 tank-0.984
 forth-0.976
 polar-0.945
Token is
Token ID318
Feature activation-1.35e-02

Pos logit contributions
ves+0.264
Her+0.263
 vows+0.259
 brist+0.255
 blonde+0.237
Neg logit contributions
o-0.223
 alone-0.204
 forth-0.186
 tank-0.184
my-0.181
Token surprised
Token ID6655
Feature activation+7.28e-02

Pos logit contributions
Her+0.031
ves+0.029
 vows+0.029
 brist+0.029
 blonde+0.027
Neg logit contributions
o-0.021
 alone-0.017
 tank-0.017
 forth-0.017
 polar-0.016
Token.
Token ID13
Feature activation-6.89e-02

Pos logit contributions
o+0.129
 alone+0.120
 forth+0.108
my+0.106
 tank+0.105
Neg logit contributions
ves-0.148
 vows-0.147
Her-0.144
 brist-0.143
growth-0.133
Token She
Token ID1375
Feature activation-2.71e-01

Pos logit contributions
ves+0.110
 vows+0.107
Her+0.102
 brist+0.100
growth+0.094
Neg logit contributions
o-0.154
 alone-0.147
 tank-0.132
my-0.131
 forth-0.130
Token lovely
Token ID14081
Feature activation-1.17e-01

Pos logit contributions
o+0.111
 alone+0.092
 forth+0.089
my+0.089
|+0.088
Neg logit contributions
 vows-0.103
ves-0.088
 ribbon-0.085
Her-0.081
 brist-0.080
Token seal
Token ID13810
Feature activation+9.05e-02

Pos logit contributions
 vows+0.230
ves+0.212
 ribbon+0.194
Her+0.187
 brist+0.186
Neg logit contributions
o-0.224
 alone-0.191
 forth-0.184
 afloat-0.180
my-0.178
Token?"
Token ID1701
Feature activation+1.72e-01

Pos logit contributions
o+0.129
 afloat+0.117
ior+0.113
|+0.113
 polar+0.112
Neg logit contributions
ves-0.177
 vows-0.177
Her-0.173
ork-0.155
 veil-0.154
Token
Token ID198
Feature activation+4.39e-02

Pos logit contributions
o+0.409
my+0.383
 alone+0.375
 tank+0.347
 forth+0.345
Neg logit contributions
ves-0.265
 vows-0.239
growth-0.228
 brist-0.227
comb-0.211
Token
Token ID198
Feature activation+4.41e-02

Pos logit contributions
o+0.066
 alone+0.061
 forth+0.054
 tank+0.053
 afloat+0.052
Neg logit contributions
ves-0.099
Her-0.098
 vows-0.098
 brist-0.096
 blonde-0.089
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.119
 alone+0.112
my+0.109
 forth+0.105
 tank+0.101
Neg logit contributions
growth-0.045
ves-0.044
 vows-0.043
 brist-0.043
der-0.042
Token mom
Token ID1995
Feature activation-1.24e-01

Pos logit contributions
 vows+0.872
Her+0.865
ves+0.860
 brist+0.837
 blonde+0.741
Neg logit contributions
o-1.288
 alone-1.214
 forth-1.125
 afloat-1.112
 tank-1.096
Token said
Token ID531
Feature activation+2.50e-02

Pos logit contributions
Her+0.232
ves+0.229
 vows+0.228
 brist+0.226
 blonde+0.203
Neg logit contributions
o-0.224
 alone-0.220
 afloat-0.201
 forth-0.195
 tank-0.194
Token,
Token ID11
Feature activation-6.76e-02

Pos logit contributions
o+0.030
 alone+0.028
 tank+0.022
my+0.022
 forth+0.020
Neg logit contributions
growth-0.067
 brist-0.063
 vows-0.062
 meanings-0.060
ves-0.060
Token "
Token ID366
Feature activation-1.35e-01

Pos logit contributions
ves+0.129
 vows+0.128
 brist+0.123
growth+0.121
Her+0.121
Neg logit contributions
o-0.130
 alone-0.118
 tank-0.107
 forth-0.106
my-0.105
TokenSure
Token ID19457
Feature activation-1.21e-01

Pos logit contributions
ves+0.272
 vows+0.271
 brist+0.263
Her+0.261
growth+0.244
Neg logit contributions
o-0.242
 alone-0.220
 forth-0.201
my-0.196
 tank-0.194
Token touch
Token ID3638
Feature activation-1.15e-01

Pos logit contributions
o+0.132
 alone+0.114
 tank+0.106
my+0.103
 polar+0.101
Neg logit contributions
ves-0.173
 vows-0.170
 brist-0.166
Her-0.166
 blonde-0.155
Token it
Token ID340
Feature activation-7.93e-02

Pos logit contributions
ves+0.201
Her+0.200
 vows+0.194
 brist+0.193
growth+0.175
Neg logit contributions
o-0.227
 alone-0.212
 forth-0.196
 afloat-0.194
 tank-0.192
Token?"
Token ID1701
Feature activation+1.75e-01

Pos logit contributions
Her+0.204
ves+0.203
 vows+0.200
 brist+0.197
growth+0.182
Neg logit contributions
o-0.093
 alone-0.080
 forth-0.070
 afloat-0.068
 tank-0.067
Token
Token ID198
Feature activation+4.51e-02

Pos logit contributions
o+0.399
 alone+0.362
my+0.355
 forth+0.329
 tank+0.317
Neg logit contributions
 vows-0.301
ves-0.291
 brist-0.261
growth-0.248
comb-0.237
Token
Token ID198
Feature activation+4.46e-02

Pos logit contributions
o+0.069
 alone+0.064
 forth+0.058
 tank+0.057
 afloat+0.056
Neg logit contributions
Her-0.100
ves-0.100
 vows-0.098
 brist-0.097
growth-0.089
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.137
 alone+0.125
my+0.125
 forth+0.121
 tank+0.115
Neg logit contributions
 vows-0.036
growth-0.032
 brist-0.029
ves-0.029
owers-0.027
Token mom
Token ID1995
Feature activation-1.25e-01

Pos logit contributions
Her+0.858
 vows+0.850
ves+0.844
 brist+0.824
 blonde+0.730
Neg logit contributions
o-1.288
 alone-1.213
 forth-1.128
 afloat-1.126
 tank-1.102
Token said
Token ID531
Feature activation+2.67e-02

Pos logit contributions
 vows+0.290
ves+0.289
Her+0.283
 brist+0.278
growth+0.273
Neg logit contributions
o-0.192
 alone-0.161
my-0.154
 forth-0.150
 tank-0.142
Token,
Token ID11
Feature activation-6.56e-02

Pos logit contributions
o+0.032
 alone+0.029
my+0.023
 tank+0.022
 forth+0.021
Neg logit contributions
growth-0.071
 vows-0.068
 brist-0.067
ves-0.065
 meanings-0.065
Token "
Token ID366
Feature activation-1.35e-01

Pos logit contributions
 vows+0.133
ves+0.132
growth+0.125
 brist+0.125
Her+0.122
Neg logit contributions
o-0.121
 alone-0.109
 tank-0.097
my-0.096
 forth-0.095
TokenNo
Token ID2949
Feature activation-1.91e-01

Pos logit contributions
 vows+0.278
ves+0.274
 brist+0.262
Her+0.255
growth+0.249
Neg logit contributions
o-0.244
 alone-0.220
 forth-0.200
my-0.196
 tank-0.189
Token go
Token ID467
Feature activation-6.51e-02

Pos logit contributions
o+0.156
 alone+0.145
 tank+0.131
 forth+0.130
my+0.127
Neg logit contributions
ves-0.179
 vows-0.175
Her-0.175
 brist-0.174
 blonde-0.158
Token there
Token ID612
Feature activation+1.49e-01

Pos logit contributions
Her+0.104
ves+0.102
 vows+0.102
 brist+0.096
 ribbon+0.095
Neg logit contributions
o-0.122
 alone-0.116
igator-0.111
 afloat-0.106
 forth-0.106
Token?"
Token ID1701
Feature activation+1.74e-01

Pos logit contributions
o+0.211
 alone+0.188
 forth+0.172
 tank+0.167
 afloat+0.165
Neg logit contributions
Her-0.334
 vows-0.333
ves-0.332
 brist-0.324
 blonde-0.303
Token
Token ID198
Feature activation+4.47e-02

Pos logit contributions
o+0.438
 alone+0.410
my+0.408
 Tim+0.396
 forth+0.379
Neg logit contributions
ves-0.246
 vows-0.229
growth-0.200
 brist-0.188
comb-0.182
Token
Token ID198
Feature activation+4.43e-02

Pos logit contributions
o+0.068
 alone+0.063
 forth+0.056
 tank+0.055
 afloat+0.054
Neg logit contributions
Her-0.100
ves-0.100
 vows-0.098
 brist-0.097
 blonde-0.089
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.104
 alone+0.098
my+0.094
 forth+0.090
 tank+0.085
Neg logit contributions
 vows-0.062
growth-0.060
 brist-0.059
ves-0.058
owers-0.054
Token mom
Token ID1995
Feature activation-1.23e-01

Pos logit contributions
ves+0.943
Her+0.936
 vows+0.935
 brist+0.914
 blonde+0.819
Neg logit contributions
o-1.213
 alone-1.138
 forth-1.048
 tank-1.036
 afloat-1.017
Token replied
Token ID8712
Feature activation-8.23e-02

Pos logit contributions
ves+0.258
 vows+0.256
Her+0.256
 brist+0.251
growth+0.232
Neg logit contributions
o-0.207
 alone-0.189
 forth-0.171
 tank-0.168
my-0.165
Token,
Token ID11
Feature activation-6.66e-02

Pos logit contributions
growth+0.235
 vows+0.220
 meanings+0.212
 ribbon+0.209
ves+0.209
Neg logit contributions
 alone-0.089
o-0.088
 down-0.062
my-0.059
 tank-0.059
Token "
Token ID366
Feature activation-1.33e-01

Pos logit contributions
ves+0.135
 vows+0.134
growth+0.130
 brist+0.125
Her+0.123
Neg logit contributions
o-0.120
 alone-0.110
my-0.097
 tank-0.097
 forth-0.095
TokenNo
Token ID2949
Feature activation-1.91e-01

Pos logit contributions
 vows+0.293
ves+0.291
 brist+0.279
growth+0.268
Her+0.265
Neg logit contributions
o-0.224
 alone-0.193
my-0.177
 forth-0.176
 tank-0.163
Token sad
Token ID6507
Feature activation+1.64e-01

Pos logit contributions
o+0.088
 forth+0.077
 afloat+0.077
 alone+0.077
 tank+0.074
Neg logit contributions
Her-0.103
ves-0.100
 vows-0.099
 brist-0.099
 blonde-0.092
Token.
Token ID13
Feature activation-5.79e-02

Pos logit contributions
o+0.235
 alone+0.233
 tank+0.184
my+0.182
 forth+0.178
Neg logit contributions
 vows-0.406
ves-0.398
Her-0.383
 brist-0.377
growth-0.367
Token
Token ID220
Feature activation+4.86e-02

Pos logit contributions
ves+0.092
 vows+0.090
 brist+0.083
Her+0.082
growth+0.075
Neg logit contributions
o-0.132
 alone-0.126
my-0.117
 tank-0.112
 forth-0.111
Token
Token ID198
Feature activation+4.55e-02

Pos logit contributions
o+0.081
 alone+0.075
 forth+0.074
 tank+0.070
 polar+0.070
Neg logit contributions
Her-0.102
ves-0.099
 brist-0.093
 vows-0.093
 Her-0.088
Token
Token ID198
Feature activation+4.51e-02

Pos logit contributions
o+0.072
 alone+0.067
 forth+0.063
 tank+0.061
 afloat+0.060
Neg logit contributions
Her-0.099
ves-0.097
 vows-0.093
 brist-0.093
 blonde-0.087
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.087
 alone+0.082
my+0.076
|+0.068
 forth+0.066
Neg logit contributions
 vows-0.095
 brist-0.084
ves-0.084
growth-0.081
owers-0.076
Token teacher
Token ID4701
Feature activation-2.56e-01

Pos logit contributions
ves+1.057
Her+1.006
 vows+1.004
 brist+0.971
growth+0.920
Neg logit contributions
o-1.124
 alone-1.079
 forth-0.973
 tank-0.969
my-0.951
Token saw
Token ID2497
Feature activation+6.40e-02

Pos logit contributions
ves+0.615
 vows+0.612
 brist+0.603
growth+0.599
Her+0.598
Neg logit contributions
o-0.387
 alone-0.344
my-0.325
 forth-0.289
 tank-0.280
Token this
Token ID428
Feature activation-4.01e-02

Pos logit contributions
o+0.123
 alone+0.122
my+0.116
 forth+0.100
 Tim+0.099
Neg logit contributions
 vows-0.133
ves-0.127
 brist-0.116
comb-0.111
ork-0.109
Token and
Token ID290
Feature activation-3.79e-02

Pos logit contributions
ves+0.084
 vows+0.083
Her+0.083
 brist+0.080
growth+0.076
Neg logit contributions
o-0.067
 alone-0.065
 tank-0.056
 forth-0.056
my-0.056
Token asked
Token ID1965
Feature activation+3.36e-02

Pos logit contributions
growth+0.102
 vows+0.102
ves+0.102
 brist+0.100
ork+0.097
Neg logit contributions
o-0.045
 alone-0.041
my-0.034
 forth-0.031
 tank-0.030
Token asked
Token ID1965
Feature activation+3.48e-02

Pos logit contributions
 vows+0.817
ves+0.812
Her+0.795
 brist+0.793
growth+0.756
Neg logit contributions
o-0.495
 alone-0.453
 forth-0.402
 tank-0.380
my-0.377
Token.
Token ID13
Feature activation-6.04e-02

Pos logit contributions
 alone+0.055
o+0.053
 forth+0.046
my+0.045
 tank+0.042
Neg logit contributions
 vows-0.080
ves-0.078
 brist-0.075
growth-0.074
Her-0.072
Token
Token ID220
Feature activation+4.87e-02

Pos logit contributions
ves+0.107
 vows+0.101
 brist+0.100
 ribbon+0.090
growth+0.090
Neg logit contributions
o-0.131
 alone-0.117
my-0.110
 tank-0.106
 Tim-0.105
Token
Token ID198
Feature activation+4.53e-02

Pos logit contributions
o+0.072
 alone+0.066
 forth+0.058
 tank+0.057
 afloat+0.055
Neg logit contributions
ves-0.111
 vows-0.110
Her-0.110
 brist-0.108
 blonde-0.100
Token
Token ID198
Feature activation+4.47e-02

Pos logit contributions
o+0.057
 alone+0.044
my+0.039
 tank+0.036
|+0.034
Neg logit contributions
 brist-0.119
 vows-0.119
ves-0.115
 blonde-0.112
growth-0.110
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.112
 alone+0.098
my+0.093
 forth+0.089
 tank+0.089
Neg logit contributions
 brist-0.060
 vows-0.056
growth-0.054
 blonde-0.054
der-0.053
Token mom
Token ID1995
Feature activation-1.22e-01

Pos logit contributions
ves+1.040
Her+1.020
 vows+1.006
 brist+0.992
growth+0.933
Neg logit contributions
o-1.132
 alone-1.064
 tank-0.976
 forth-0.969
my-0.947
Token laughed
Token ID13818
Feature activation+2.12e-02

Pos logit contributions
ves+0.275
 vows+0.273
Her+0.266
growth+0.263
 brist+0.261
Neg logit contributions
o-0.202
my-0.167
 alone-0.165
 forth-0.157
 tank-0.149
Token and
Token ID290
Feature activation-3.89e-02

Pos logit contributions
 alone+0.030
o+0.030
 forth+0.025
my+0.025
 tank+0.024
Neg logit contributions
ves-0.052
 vows-0.051
 brist-0.048
growth-0.047
Her-0.047
Token replied
Token ID8712
Feature activation-8.23e-02

Pos logit contributions
ves+0.095
 vows+0.094
Her+0.091
 brist+0.090
growth+0.089
Neg logit contributions
o-0.055
 alone-0.048
 forth-0.045
my-0.041
 tank-0.040
Token,
Token ID11
Feature activation-6.63e-02

Pos logit contributions
growth+0.226
 vows+0.216
ves+0.206
Her+0.203
 meanings+0.199
Neg logit contributions
 alone-0.092
o-0.091
 down-0.068
my-0.063
 forth-0.062
Token dull
Token ID19222
Feature activation-4.08e-02

Pos logit contributions
o+0.095
 alone+0.085
 forth+0.080
 afloat+0.078
|+0.075
Neg logit contributions
 vows-0.100
 brist-0.096
ves-0.096
Her-0.095
 blonde-0.089
Token ones
Token ID3392
Feature activation-1.69e-01

Pos logit contributions
 vows+0.086
ves+0.086
 brist+0.084
Her+0.084
 blonde+0.077
Neg logit contributions
o-0.065
 alone-0.061
 forth-0.055
 afloat-0.054
 tank-0.051
Token."
Token ID526
Feature activation+1.10e-01

Pos logit contributions
ves+0.332
 vows+0.328
Her+0.327
 brist+0.320
 blonde+0.292
Neg logit contributions
o-0.301
 alone-0.276
 forth-0.256
 tank-0.250
 afloat-0.248
Token
Token ID198
Feature activation+4.33e-02

Pos logit contributions
o+0.134
 alone+0.118
my+0.097
 tank+0.091
 forth+0.085
Neg logit contributions
 vows-0.294
ves-0.290
 brist-0.281
Her-0.262
 ribbon-0.261
Token
Token ID198
Feature activation+4.29e-02

Pos logit contributions
o+0.069
 alone+0.065
 forth+0.060
 tank+0.058
 afloat+0.057
Neg logit contributions
Her-0.094
ves-0.093
 vows-0.089
 brist-0.089
growth-0.082
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.130
 alone+0.122
my+0.114
 forth+0.114
 tank+0.112
Neg logit contributions
 vows-0.036
 brist-0.033
ves-0.030
 blonde-0.028
growth-0.025
Token mom
Token ID1995
Feature activation-1.26e-01

Pos logit contributions
ves+1.045
Her+1.036
 brist+1.009
 vows+1.005
growth+0.959
Neg logit contributions
o-1.113
 alone-1.046
 tank-0.962
 polar-0.939
 forth-0.937
Token and
Token ID290
Feature activation-4.03e-02

Pos logit contributions
 vows+0.277
ves+0.277
Her+0.273
 brist+0.267
growth+0.258
Neg logit contributions
o-0.209
 alone-0.177
my-0.173
 tank-0.160
 forth-0.159
Token dad
Token ID9955
Feature activation-6.58e-02

Pos logit contributions
ves+0.082
 vows+0.080
 brist+0.078
Her+0.078
growth+0.072
Neg logit contributions
o-0.072
 alone-0.068
 forth-0.062
my-0.060
 tank-0.060
Token hugged
Token ID41130
Feature activation-5.85e-02

Pos logit contributions
ves+0.146
Her+0.142
 vows+0.140
 brist+0.140
ork+0.132
Neg logit contributions
o-0.108
 alone-0.097
my-0.093
 forth-0.089
 tank-0.087
Token her
Token ID607
Feature activation-3.10e-01

Pos logit contributions
ves+0.092
 vows+0.091
 brist+0.085
Her+0.079
 blonde+0.078
Neg logit contributions
o-0.131
 alone-0.129
my-0.119
 forth-0.117
 tank-0.112
Token big
Token ID1263
Feature activation-6.15e-02

Pos logit contributions
 alone+0.102
o+0.094
 tank+0.085
 polar+0.082
my+0.082
Neg logit contributions
ves-0.126
 vows-0.120
Her-0.112
ork-0.108
owers-0.106
Token eyes
Token ID2951
Feature activation-3.48e-01

Pos logit contributions
ves+0.081
Her+0.076
 vows+0.075
 brist+0.067
growth+0.062
Neg logit contributions
o-0.153
 alone-0.151
 tank-0.139
 forth-0.139
my-0.137
Token.
Token ID13
Feature activation-6.04e-02

Pos logit contributions
ves+0.833
 vows+0.821
Her+0.780
 brist+0.764
growth+0.761
Neg logit contributions
 alone-0.513
o-0.499
my-0.421
 forth-0.394
 tank-0.394
Token
Token ID220
Feature activation+4.97e-02

Pos logit contributions
ves+0.137
 vows+0.133
 brist+0.126
 ribbon+0.120
Her+0.120
Neg logit contributions
o-0.098
 alone-0.090
 tank-0.079
my-0.079
 forth-0.072
Token
Token ID198
Feature activation+4.51e-02

Pos logit contributions
o+0.075
 alone+0.068
 forth+0.061
 tank+0.060
 afloat+0.058
Neg logit contributions
ves-0.111
Her-0.111
 vows-0.110
 brist-0.109
 blonde-0.101
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.059
 alone+0.050
my+0.043
 tank+0.042
 forth+0.039
Neg logit contributions
 vows-0.116
 brist-0.112
ves-0.112
 blonde-0.106
Her-0.104
Token mom
Token ID1995
Feature activation-1.21e-01

Pos logit contributions
Her+0.862
 vows+0.860
ves+0.856
 brist+0.846
 blonde+0.746
Neg logit contributions
o-1.283
 alone-1.195
 forth-1.123
 afloat-1.106
 tank-1.094
Token smiled
Token ID13541
Feature activation-3.09e-02

Pos logit contributions
ves+0.273
 vows+0.272
Her+0.268
 brist+0.264
growth+0.249
Neg logit contributions
o-0.192
 alone-0.170
 forth-0.154
my-0.152
 tank-0.149
Token and
Token ID290
Feature activation-3.78e-02

Pos logit contributions
ves+0.065
 vows+0.064
Her+0.063
 brist+0.062
growth+0.058
Neg logit contributions
o-0.052
 alone-0.049
 forth-0.044
 tank-0.043
my-0.042
Token hugged
Token ID41130
Feature activation-5.79e-02

Pos logit contributions
ves+0.083
 vows+0.083
Her+0.081
 brist+0.080
growth+0.076
Neg logit contributions
o-0.061
 alone-0.054
 forth-0.050
 tank-0.047
my-0.047
Token her
Token ID607
Feature activation-3.10e-01

Pos logit contributions
ves+0.098
 vows+0.097
 brist+0.090
Her+0.089
ork+0.082
Neg logit contributions
o-0.122
 alone-0.119
 forth-0.109
my-0.107
 tank-0.104
Token exclaimed
Token ID33552
Feature activation-1.16e-01

Pos logit contributions
o+0.153
 alone+0.137
 forth+0.120
my+0.117
 tank+0.116
Neg logit contributions
 vows-0.218
ves-0.215
 brist-0.210
Her-0.209
growth-0.200
Token.
Token ID13
Feature activation-6.43e-02

Pos logit contributions
ves+0.226
 vows+0.225
Her+0.223
 brist+0.219
growth+0.201
Neg logit contributions
o-0.213
 alone-0.199
 forth-0.179
 tank-0.177
 afloat-0.173
Token
Token ID220
Feature activation+5.02e-02

Pos logit contributions
ves+0.129
 vows+0.120
 brist+0.116
growth+0.110
Her+0.109
Neg logit contributions
o-0.121
 alone-0.115
 tank-0.104
my-0.102
 forth-0.099
Token
Token ID198
Feature activation+4.61e-02

Pos logit contributions
o+0.083
 alone+0.078
 forth+0.076
 tank+0.073
 polar+0.072
Neg logit contributions
Her-0.106
ves-0.104
 brist-0.097
 vows-0.097
 Her-0.092
Token
Token ID198
Feature activation+4.52e-02

Pos logit contributions
o+0.071
 alone+0.065
 forth+0.058
 tank+0.057
 afloat+0.056
Neg logit contributions
Her-0.103
ves-0.103
 vows-0.101
 brist-0.099
 blonde-0.092
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.091
 alone+0.089
 forth+0.081
my+0.079
 tank+0.079
Neg logit contributions
 vows-0.074
ves-0.073
 brist-0.072
growth-0.070
 blonde-0.065
Token dad
Token ID9955
Feature activation-6.44e-02

Pos logit contributions
ves+1.024
Her+1.009
 vows+0.992
 brist+0.979
growth+0.906
Neg logit contributions
o-1.144
 alone-1.072
 tank-0.981
 forth-0.979
 polar-0.953
Token said
Token ID531
Feature activation+2.52e-02

Pos logit contributions
ves+0.133
 vows+0.133
Her+0.132
 brist+0.130
growth+0.122
Neg logit contributions
o-0.113
 alone-0.100
 forth-0.092
my-0.091
 tank-0.091
Token,
Token ID11
Feature activation-6.62e-02

Pos logit contributions
o+0.041
 alone+0.038
 tank+0.033
 polar+0.031
 forth+0.031
Neg logit contributions
 brist-0.054
 vows-0.054
ves-0.054
Her-0.053
growth-0.053
Token "
Token ID366
Feature activation-1.33e-01

Pos logit contributions
Her+0.102
ves+0.102
 vows+0.101
 brist+0.099
 blonde+0.088
Neg logit contributions
o-0.146
 alone-0.137
 forth-0.128
 tank-0.125
 afloat-0.124
TokenYou
Token ID1639
Feature activation+1.01e-02

Pos logit contributions
Her+0.247
ves+0.240
 brist+0.236
 vows+0.236
 blonde+0.213
Neg logit contributions
o-0.257
 alone-0.244
 tank-0.222
 forth-0.221
 afloat-0.218
Token lot
Token ID1256
Feature activation-2.65e-01

Pos logit contributions
 vows+0.244
ves+0.240
Her+0.233
 brist+0.226
growth+0.205
Neg logit contributions
o-0.376
 alone-0.366
 tank-0.333
 forth-0.332
my-0.327
Token.
Token ID13
Feature activation-6.32e-02

Pos logit contributions
 vows+0.523
ves+0.521
Her+0.515
 brist+0.506
 blonde+0.468
Neg logit contributions
o-0.480
 alone-0.452
 forth-0.399
 tank-0.397
my-0.391
Token
Token ID220
Feature activation+4.93e-02

Pos logit contributions
ves+0.138
 vows+0.137
Her+0.135
 brist+0.134
growth+0.124
Neg logit contributions
o-0.101
 alone-0.093
 forth-0.082
 tank-0.080
my-0.080
Token
Token ID198
Feature activation+4.72e-02

Pos logit contributions
o+0.081
 alone+0.077
 forth+0.075
 polar+0.072
 tank+0.072
Neg logit contributions
Her-0.103
ves-0.101
 brist-0.095
 vows-0.094
 Her-0.089
Token
Token ID198
Feature activation+4.62e-02

Pos logit contributions
o+0.078
 alone+0.074
 forth+0.071
 tank+0.068
 afloat+0.068
Neg logit contributions
Her-0.100
ves-0.097
 vows-0.091
 brist-0.091
 Her-0.086
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
 alone+0.116
o+0.116
my+0.106
 forth+0.102
|+0.098
Neg logit contributions
 vows-0.066
growth-0.052
ves-0.052
 brist-0.051
owers-0.047
Token mom
Token ID1995
Feature activation-1.24e-01

Pos logit contributions
Her+0.916
ves+0.914
 vows+0.907
 brist+0.896
 blonde+0.795
Neg logit contributions
o-1.230
 alone-1.147
 forth-1.060
 tank-1.048
 afloat-1.041
Token came
Token ID1625
Feature activation-6.94e-02

Pos logit contributions
Her+0.368
 brist+0.350
ves+0.347
 vows+0.333
 blush+0.330
Neg logit contributions
o-0.081
 afloat-0.078
 alone-0.075
 tank-0.065
|-0.056
Token outside
Token ID2354
Feature activation+5.44e-02

Pos logit contributions
Her+0.127
 brist+0.112
 Her+0.103
ves+0.102
 vows+0.099
Neg logit contributions
o-0.124
igator-0.118
 afloat-0.116
 tank-0.113
 wreck-0.111
Token and
Token ID290
Feature activation-3.94e-02

Pos logit contributions
o+0.095
 alone+0.089
 forth+0.080
 tank+0.079
my+0.076
Neg logit contributions
ves-0.109
 vows-0.109
Her-0.108
 brist-0.106
 blonde-0.098
Token saw
Token ID2497
Feature activation+6.42e-02

Pos logit contributions
Her+0.081
ves+0.074
 brist+0.073
 vows+0.069
 Her+0.068
Neg logit contributions
o-0.065
 afloat-0.062
 alone-0.061
 tank-0.059
|-0.056
Token glowing
Token ID21377
Feature activation-3.24e-02

Pos logit contributions
o+0.024
 alone+0.022
 forth+0.020
 tank+0.020
 afloat+0.019
Neg logit contributions
ves-0.032
Her-0.031
 vows-0.031
 brist-0.031
 blonde-0.029
Token red
Token ID2266
Feature activation-6.00e-03

Pos logit contributions
Her+0.079
ves+0.078
 vows+0.075
 brist+0.075
growth+0.072
Neg logit contributions
o-0.045
 alone-0.043
 forth-0.036
 tank-0.036
my-0.035
Token!"
Token ID2474
Feature activation+1.16e-01

Pos logit contributions
ves+0.016
Her+0.016
 vows+0.015
 brist+0.015
growth+0.015
Neg logit contributions
o-0.007
 alone-0.006
my-0.006
 forth-0.005
 tank-0.005
Token
Token ID198
Feature activation+4.31e-02

Pos logit contributions
o+0.134
 alone+0.105
my+0.087
 tank+0.084
 polar+0.074
Neg logit contributions
 vows-0.325
ves-0.317
 brist-0.306
 ribbon-0.289
 blonde-0.285
Token
Token ID198
Feature activation+4.34e-02

Pos logit contributions
o+0.062
 alone+0.055
 tank+0.047
 forth+0.047
my+0.046
Neg logit contributions
 vows-0.101
ves-0.100
 brist-0.100
Her-0.099
 blonde-0.093
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.079
 alone+0.065
my+0.060
 forth+0.060
 tank+0.059
Neg logit contributions
 vows-0.089
 brist-0.085
ves-0.084
 blonde-0.082
 blush-0.080
Token mother
Token ID2802
Feature activation-2.56e-01

Pos logit contributions
ves+0.875
 vows+0.821
Her+0.820
 brist+0.773
growth+0.736
Neg logit contributions
o-1.324
 alone-1.217
 forth-1.180
my-1.162
 polar-1.157
Token smiled
Token ID13541
Feature activation-3.21e-02

Pos logit contributions
ves+0.550
 vows+0.549
Her+0.538
 brist+0.525
growth+0.502
Neg logit contributions
o-0.437
 alone-0.382
my-0.359
 forth-0.355
 tank-0.340
Token and
Token ID290
Feature activation-3.93e-02

Pos logit contributions
ves+0.071
 vows+0.069
Her+0.067
 brist+0.067
growth+0.063
Neg logit contributions
o-0.052
 alone-0.049
 forth-0.043
 tank-0.042
my-0.042
Token nodded
Token ID14464
Feature activation-1.59e-01

Pos logit contributions
ves+0.094
 vows+0.093
Her+0.091
 brist+0.091
growth+0.087
Neg logit contributions
o-0.056
 alone-0.048
 forth-0.044
my-0.042
 tank-0.041
Token.
Token ID13
Feature activation-6.35e-02

Pos logit contributions
ves+0.368
 vows+0.348
 brist+0.335
growth+0.332
ork+0.326
Neg logit contributions
 alone-0.243
o-0.240
 forth-0.208
my-0.203
 tank-0.194
Token large
Token ID1588
Feature activation-7.14e-02

Pos logit contributions
 alone+0.105
o+0.105
 forth+0.094
 tank+0.091
my+0.089
Neg logit contributions
Her-0.100
ves-0.100
 vows-0.100
 brist-0.097
growth-0.092
Token swing
Token ID9628
Feature activation-1.33e-01

Pos logit contributions
Her+0.152
ves+0.152
 vows+0.150
 brist+0.146
growth+0.137
Neg logit contributions
o-0.116
 alone-0.113
 forth-0.101
 tank-0.097
my-0.096
Token."
Token ID526
Feature activation+1.10e-01

Pos logit contributions
ves+0.284
Her+0.282
 vows+0.280
 brist+0.271
 ribbon+0.251
Neg logit contributions
o-0.207
 alone-0.186
 afloat-0.174
 forth-0.172
 polar-0.171
Token
Token ID198
Feature activation+4.56e-02

Pos logit contributions
o+0.162
 alone+0.148
my+0.125
 tank+0.125
 forth+0.123
Neg logit contributions
ves-0.258
 vows-0.257
 brist-0.248
Her-0.243
growth-0.233
Token
Token ID198
Feature activation+4.54e-02

Pos logit contributions
o+0.071
 alone+0.065
 forth+0.059
 tank+0.057
 afloat+0.056
Neg logit contributions
Her-0.101
ves-0.101
 vows-0.099
 brist-0.098
growth-0.090
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.122
 alone+0.119
 forth+0.110
my+0.110
 tank+0.105
Neg logit contributions
 vows-0.053
 brist-0.047
ves-0.047
growth-0.044
 blonde-0.041
Token mom
Token ID1995
Feature activation-1.24e-01

Pos logit contributions
ves+1.004
Her+0.991
 vows+0.987
 brist+0.970
growth+0.902
Neg logit contributions
o-1.154
 alone-1.085
 forth-0.992
 tank-0.986
my-0.965
Token hugged
Token ID41130
Feature activation-5.82e-02

Pos logit contributions
 vows+0.271
ves+0.270
Her+0.269
 brist+0.264
growth+0.253
Neg logit contributions
o-0.204
 alone-0.178
my-0.164
 forth-0.161
 tank-0.158
Token her
Token ID607
Feature activation-3.08e-01

Pos logit contributions
ves+0.076
 vows+0.075
Her+0.074
 brist+0.072
 blonde+0.063
Neg logit contributions
o-0.144
 alone-0.138
 forth-0.128
 tank-0.127
my-0.125
Token and
Token ID290
Feature activation-3.92e-02

Pos logit contributions
Her+0.572
 brist+0.564
 vows+0.564
ves+0.559
 ribbon+0.507
Neg logit contributions
o-0.590
 alone-0.526
 forth-0.484
 tank-0.481
 afloat-0.480
Token said
Token ID531
Feature activation+2.66e-02

Pos logit contributions
ves+0.091
 vows+0.091
Her+0.090
 brist+0.089
growth+0.084
Neg logit contributions
o-0.057
 alone-0.052
 forth-0.047
 tank-0.044
my-0.044
Token ground
Token ID2323
Feature activation-1.38e-01

Pos logit contributions
o+0.109
 alone+0.102
 forth+0.093
 tank+0.092
 afloat+0.090
Neg logit contributions
ves-0.093
Her-0.092
 vows-0.092
 brist-0.090
 blonde-0.081
Token.
Token ID13
Feature activation-6.08e-02

Pos logit contributions
 vows+0.289
Her+0.287
ves+0.285
 brist+0.281
growth+0.261
Neg logit contributions
o-0.237
 alone-0.225
 tank-0.196
 forth-0.193
my-0.190
Token
Token ID220
Feature activation+4.89e-02

Pos logit contributions
ves+0.129
 vows+0.123
 brist+0.122
Her+0.122
growth+0.110
Neg logit contributions
o-0.100
 alone-0.098
 tank-0.089
my-0.083
|-0.082
Token
Token ID198
Feature activation+4.45e-02

Pos logit contributions
o+0.078
 alone+0.073
 forth+0.069
 tank+0.065
 polar+0.064
Neg logit contributions
ves-0.105
Her-0.105
 vows-0.101
 brist-0.100
growth-0.093
Token
Token ID198
Feature activation+4.42e-02

Pos logit contributions
o+0.069
 alone+0.063
 forth+0.057
 tank+0.055
 afloat+0.054
Neg logit contributions
ves-0.099
Her-0.099
 vows-0.097
 brist-0.095
 blonde-0.088
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
 alone+0.082
o+0.081
my+0.072
 tank+0.071
 late+0.071
Neg logit contributions
 vows-0.080
 brist-0.077
ves-0.076
growth-0.073
owers-0.070
Token friends
Token ID2460
Feature activation+2.66e-02

Pos logit contributions
Her+1.364
ves+1.358
 vows+1.341
 brist+1.311
growth+1.255
Neg logit contributions
o-0.808
 alone-0.740
 tank-0.651
 forth-0.634
 polar-0.625
Token gathered
Token ID9272
Feature activation-1.38e-01

Pos logit contributions
o+0.047
 alone+0.043
 forth+0.039
my+0.039
 tank+0.038
Neg logit contributions
ves-0.054
Her-0.054
 vows-0.054
 brist-0.053
growth-0.049
Token around
Token ID1088
Feature activation+1.50e-01

Pos logit contributions
ves+0.315
Her+0.310
 vows+0.306
 brist+0.298
growth+0.279
Neg logit contributions
o-0.210
 alone-0.202
 forth-0.176
 tank-0.175
my-0.167
Token the
Token ID262
Feature activation+5.33e-02

Pos logit contributions
 alone+0.178
o+0.167
 tank+0.144
 forth+0.143
my+0.133
Neg logit contributions
ves-0.389
 vows-0.385
Her-0.379
 brist-0.367
growth-0.358
Token crack
Token ID8469
Feature activation-1.11e-01

Pos logit contributions
o+0.110
 alone+0.103
 forth+0.094
 tank+0.093
 afloat+0.092
Neg logit contributions
ves-0.091
Her-0.090
 vows-0.090
 brist-0.088
 blonde-0.079
Token the
Token ID262
Feature activation+5.47e-02

Pos logit contributions
o+0.065
 tank+0.056
 afloat+0.056
 alone+0.055
|+0.055
Neg logit contributions
Her-0.077
 brist-0.075
ves-0.073
 vows-0.073
 blush-0.069
Token cup
Token ID6508
Feature activation-1.56e-01

Pos logit contributions
o+0.100
 alone+0.097
 tank+0.087
my+0.087
 polar+0.082
Neg logit contributions
ves-0.109
Her-0.108
 vows-0.108
growth-0.099
 brist-0.098
Token.
Token ID13
Feature activation-5.87e-02

Pos logit contributions
 vows+0.365
ves+0.365
Her+0.350
 brist+0.347
 blonde+0.333
Neg logit contributions
o-0.241
 alone-0.230
my-0.192
 tank-0.189
 forth-0.188
Token
Token ID198
Feature activation+4.71e-02

Pos logit contributions
ves+0.130
 vows+0.130
 brist+0.124
Her+0.121
growth+0.118
Neg logit contributions
o-0.095
 alone-0.086
my-0.077
 forth-0.076
 tank-0.073
Token
Token ID198
Feature activation+4.62e-02

Pos logit contributions
o+0.079
 alone+0.076
 forth+0.073
 afloat+0.071
 tank+0.071
Neg logit contributions
Her-0.098
ves-0.096
 vows-0.088
 brist-0.088
 Her-0.084
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.103
 alone+0.101
my+0.096
 forth+0.093
ny+0.085
Neg logit contributions
 vows-0.078
growth-0.070
ves-0.064
 brist-0.063
owers-0.062
Token mom
Token ID1995
Feature activation-1.22e-01

Pos logit contributions
ves+1.010
 vows+0.996
Her+0.988
 brist+0.969
growth+0.896
Neg logit contributions
o-1.156
 alone-1.078
 forth-0.986
 tank-0.982
my-0.965
Token noticed
Token ID6810
Feature activation-7.68e-02

Pos logit contributions
Her+0.250
ves+0.249
 vows+0.244
 brist+0.243
 blonde+0.221
Neg logit contributions
o-0.205
 alone-0.193
 afloat-0.174
 tank-0.172
 forth-0.170
Token that
Token ID326
Feature activation-1.87e-01

Pos logit contributions
 vows+0.175
ves+0.159
 brist+0.146
 blonde+0.144
growth+0.142
Neg logit contributions
o-0.138
 alone-0.133
my-0.128
 forth-0.116
 tank-0.107
Token Lily
Token ID20037
Feature activation+9.52e-02

Pos logit contributions
 vows+0.466
ves+0.461
Her+0.450
 brist+0.446
growth+0.428
Neg logit contributions
o-0.247
 alone-0.237
 forth-0.199
my-0.194
 tank-0.190
Token was
Token ID373
Feature activation-6.93e-02

Pos logit contributions
o+0.154
 alone+0.143
my+0.128
 forth+0.123
 tank+0.119
Neg logit contributions
 vows-0.218
Her-0.212
ves-0.210
 brist-0.205
growth-0.202
Token it
Token ID340
Feature activation-7.86e-02

Pos logit contributions
o+0.088
 alone+0.086
 forth+0.076
my+0.072
 tank+0.071
Neg logit contributions
 vows-0.128
ves-0.121
 brist-0.120
Her-0.117
growth-0.114
Token.
Token ID13
Feature activation-6.06e-02

Pos logit contributions
ves+0.157
 vows+0.157
Her+0.156
 brist+0.154
growth+0.142
Neg logit contributions
o-0.139
 alone-0.131
 forth-0.117
 tank-0.115
my-0.113
Token
Token ID220
Feature activation+4.94e-02

Pos logit contributions
ves+0.107
 vows+0.105
 brist+0.102
growth+0.096
Her+0.096
Neg logit contributions
o-0.126
 alone-0.113
my-0.107
 tank-0.105
 forth-0.103
Token
Token ID198
Feature activation+4.63e-02

Pos logit contributions
o+0.080
 alone+0.077
 forth+0.075
 tank+0.071
 afloat+0.071
Neg logit contributions
Her-0.104
ves-0.102
 vows-0.096
 brist-0.094
 Her-0.090
Token
Token ID198
Feature activation+4.55e-02

Pos logit contributions
o+0.074
 alone+0.071
 forth+0.065
 afloat+0.063
 tank+0.063
Neg logit contributions
Her-0.100
ves-0.098
 vows-0.095
 brist-0.092
ork-0.086
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.090
my+0.081
 alone+0.079
 forth+0.074
ny+0.071
Neg logit contributions
growth-0.088
 vows-0.085
ves-0.081
 brist-0.081
der-0.079
Token mom
Token ID1995
Feature activation-1.23e-01

Pos logit contributions
ves+1.013
 vows+0.997
Her+0.989
 brist+0.976
growth+0.909
Neg logit contributions
o-1.150
 alone-1.074
 forth-0.984
 tank-0.979
my-0.966
Token said
Token ID531
Feature activation+2.59e-02

Pos logit contributions
ves+0.273
 vows+0.272
Her+0.270
 brist+0.267
growth+0.251
Neg logit contributions
o-0.193
 alone-0.174
 forth-0.156
 tank-0.152
my-0.152
Token,
Token ID11
Feature activation-6.56e-02

Pos logit contributions
o+0.031
 alone+0.028
 Tim+0.024
 Nem+0.024
my+0.021
Neg logit contributions
growth-0.070
 brist-0.063
 vows-0.063
 meanings-0.062
owers-0.060
Token "
Token ID366
Feature activation-1.34e-01

Pos logit contributions
 vows+0.139
growth+0.136
ves+0.136
 brist+0.129
Her+0.126
Neg logit contributions
o-0.117
 alone-0.102
my-0.093
 tank-0.090
 forth-0.088
TokenSure
Token ID19457
Feature activation-1.19e-01

Pos logit contributions
 vows+0.254
ves+0.253
 brist+0.239
Her+0.236
growth+0.226
Neg logit contributions
o-0.262
 alone-0.241
 forth-0.222
my-0.221
 tank-0.210
Token question
Token ID1808
Feature activation-1.65e-01

Pos logit contributions
o+0.002
 alone+0.002
 forth+0.002
 tank+0.002
 polar+0.002
Neg logit contributions
Her-0.002
ves-0.002
 brist-0.002
 vows-0.002
growth-0.002
Token.
Token ID13
Feature activation-5.79e-02

Pos logit contributions
 brist+0.391
growth+0.381
 vows+0.381
ves+0.373
Her+0.364
Neg logit contributions
o-0.254
 alone-0.239
my-0.213
 tank-0.178
 forth-0.177
Token
Token ID220
Feature activation+4.89e-02

Pos logit contributions
ves+0.105
 vows+0.098
 brist+0.094
growth+0.087
 ribbon+0.085
Neg logit contributions
o-0.128
 alone-0.112
my-0.106
 tank-0.103
 Tim-0.099
Token
Token ID198
Feature activation+4.63e-02

Pos logit contributions
o+0.073
 alone+0.067
 forth+0.060
 tank+0.059
 afloat+0.057
Neg logit contributions
ves-0.110
Her-0.109
 vows-0.109
 brist-0.107
 blonde-0.099
Token
Token ID198
Feature activation+4.49e-02

Pos logit contributions
o+0.064
 alone+0.055
my+0.048
 tank+0.046
 forth+0.045
Neg logit contributions
 vows-0.114
 brist-0.112
ves-0.111
Her-0.107
 blonde-0.104
TokenHer
Token ID9360
Feature activation-5.71e-01

Pos logit contributions
o+0.115
 alone+0.105
my+0.102
 forth+0.096
 late+0.092
Neg logit contributions
 vows-0.061
 brist-0.055
der-0.054
growth-0.053
ves-0.052
Token mom
Token ID1995
Feature activation-1.22e-01

Pos logit contributions
ves+1.174
Her+1.134
 vows+1.110
 brist+1.107
growth+1.101
Neg logit contributions
o-1.027
 alone-0.938
 tank-0.869
my-0.860
 forth-0.847
Token explained
Token ID4893
Feature activation-1.07e-01

Pos logit contributions
 vows+0.272
ves+0.271
Her+0.267
 brist+0.266
growth+0.253
Neg logit contributions
o-0.200
 alone-0.174
my-0.164
 forth-0.160
 tank-0.154
Token that
Token ID326
Feature activation-1.87e-01

Pos logit contributions
 vows+0.258
growth+0.257
ves+0.246
 brist+0.242
 blonde+0.236
Neg logit contributions
 alone-0.149
o-0.143
my-0.125
 by-0.122
 mad-0.115
Token ge
Token ID4903
Feature activation+6.80e-02

Pos logit contributions
 vows+0.434
Her+0.430
 brist+0.422
ves+0.422
growth+0.401
Neg logit contributions
o-0.278
 alone-0.267
my-0.226
 forth-0.220
 tank-0.220
Tokenese
Token ID2771
Feature activation+6.67e-02

Pos logit contributions
o+0.103
 alone+0.095
 forth+0.084
 tank+0.083
 afloat+0.080
Neg logit contributions
ves-0.153
Her-0.152
 vows-0.151
 brist-0.149
 blonde-0.138
Token excited
Token ID6568
Feature activation+4.70e-02

Pos logit contributions
o+0.119
 forth+0.099
 afloat+0.098
 tank+0.098
 alone+0.097
Neg logit contributions
Her-0.156
 vows-0.151
 brist-0.148
ves-0.148
 blonde-0.141
Token,
Token ID11
Feature activation-4.19e-02

Pos logit contributions
o+0.078
 alone+0.074
my+0.065
 forth+0.065
 tank+0.061
Neg logit contributions
 vows-0.102
ves-0.102
Her-0.100
 brist-0.099
growth-0.094
Token but
Token ID475
Feature activation+5.78e-02

Pos logit contributions
 vows+0.106
ves+0.106
Her+0.102
 brist+0.101
growth+0.099
Neg logit contributions
o-0.053
 alone-0.051
 forth-0.043
my-0.042
 tank-0.039
Token then
Token ID788
Feature activation-3.66e-02

Pos logit contributions
o+0.152
 alone+0.145
 forth+0.136
 tank+0.133
my+0.133
Neg logit contributions
ves-0.067
 vows-0.066
Her-0.065
 brist-0.064
growth-0.055
Token Mom
Token ID11254
Feature activation-1.11e-02

Pos logit contributions
ves+0.065
growth+0.062
 vows+0.061
 brist+0.059
ork+0.059
Neg logit contributions
 alone-0.075
 forth-0.074
o-0.073
my-0.070
 Tim-0.065
Tokenmy
Token ID1820
Feature activation+3.84e-01

Pos logit contributions
Her+0.031
 brist+0.030
ves+0.030
 blush+0.029
 vows+0.029
Neg logit contributions
 alone-0.009
 afloat-0.009
 tank-0.007
|-0.007
 wreck-0.007
Token said
Token ID531
Feature activation+4.70e-02

Pos logit contributions
o+0.606
 alone+0.543
 forth+0.487
 tank+0.477
my+0.476
Neg logit contributions
Her-0.849
 vows-0.849
ves-0.847
 brist-0.839
growth-0.787
Token there
Token ID612
Feature activation+1.68e-01

Pos logit contributions
 alone+0.066
o+0.058
 Tim+0.054
 mad+0.052
 tired+0.051
Neg logit contributions
growth-0.116
 brist-0.101
 vows-0.098
owers-0.098
 ribbon-0.096
Token was
Token ID373
Feature activation-4.87e-02

Pos logit contributions
o+0.168
 alone+0.161
my+0.147
 Tim+0.121
 boy+0.121
Neg logit contributions
growth-0.475
 brist-0.453
Her-0.439
 vows-0.427
quet-0.416
Token going
Token ID1016
Feature activation+4.14e-02

Pos logit contributions
ves+0.110
growth+0.108
 brist+0.105
 vows+0.104
Her+0.102
Neg logit contributions
o-0.079
 alone-0.070
my-0.068
 Tim-0.060
 late-0.059
Token to
Token ID284
Feature activation-8.20e-02

Pos logit contributions
o+0.082
 alone+0.075
 tank+0.070
 polar+0.070
 afloat+0.070
Neg logit contributions
Her-0.072
ves-0.072
 vows-0.071
 brist-0.069
 blonde-0.062
Token you
Token ID345
Feature activation+2.32e-01

Pos logit contributions
o+0.283
 alone+0.259
 afloat+0.247
 forth+0.230
 polar+0.229
Neg logit contributions
Her-0.401
ves-0.389
 vows-0.373
 brist-0.360
 Her-0.348
Token let
Token ID1309
Feature activation+1.10e-01

Pos logit contributions
o+0.437
 alone+0.405
 forth+0.369
 tank+0.363
 afloat+0.358
Neg logit contributions
Her-0.436
ves-0.435
 vows-0.432
 brist-0.424
 blonde-0.384
Token her
Token ID607
Feature activation-2.21e-01

Pos logit contributions
o+0.173
 alone+0.160
 afloat+0.152
 tank+0.139
 forth+0.138
Neg logit contributions
Her-0.239
ves-0.237
 vows-0.234
 brist-0.223
 Her-0.211
Token hold
Token ID1745
Feature activation-2.14e-02

Pos logit contributions
 vows+0.418
Her+0.417
ves+0.417
 brist+0.392
 blush+0.375
Neg logit contributions
o-0.385
 alone-0.353
 forth-0.327
 afloat-0.326
|-0.319
Token your
Token ID534
Feature activation+2.42e-01

Pos logit contributions
Her+0.049
ves+0.048
 brist+0.047
 vows+0.047
 ribbon+0.045
Neg logit contributions
o-0.029
 alone-0.027
 afloat-0.026
 forth-0.025
 wreck-0.024
Token bear
Token ID6842
Feature activation+3.20e-01

Pos logit contributions
o+0.398
 alone+0.336
|+0.325
 afloat+0.314
 forth+0.313
Neg logit contributions
 vows-0.507
 brist-0.501
ves-0.495
 ribbon-0.489
Her-0.471
Token for
Token ID329
Feature activation+1.78e-01

Pos logit contributions
o+0.505
 polar+0.454
 alone+0.453
|+0.450
 forth+0.442
Neg logit contributions
Her-0.617
ves-0.609
 vows-0.575
 brist-0.568
 ribbon-0.560
Token a
Token ID257
Feature activation-8.48e-02

Pos logit contributions
o+0.265
 alone+0.248
 forth+0.220
 tank+0.213
 polar+0.207
Neg logit contributions
 vows-0.405
ves-0.402
Her-0.396
 brist-0.392
 blonde-0.366
Token little
Token ID1310
Feature activation-2.50e-02

Pos logit contributions
 vows+0.136
ves+0.135
Her+0.131
 brist+0.130
 ribbon+0.128
Neg logit contributions
o-0.177
 alone-0.165
 forth-0.159
 afloat-0.149
my-0.143
Token while
Token ID981
Feature activation-3.81e-02

Pos logit contributions
 brist+0.038
 ribbon+0.037
 vows+0.036
Her+0.035
ves+0.035
Neg logit contributions
o-0.052
 alone-0.046
|-0.044
 forth-0.043
 afloat-0.043
Token?"
Token ID1701
Feature activation+2.52e-01

Pos logit contributions
ves+0.089
Her+0.089
 vows+0.088
 brist+0.086
 blonde+0.081
Neg logit contributions
o-0.053
 alone-0.047
 forth-0.042
 afloat-0.041
 tank-0.041
Token stranger
Token ID16195
Feature activation-2.82e-02

Pos logit contributions
o+0.166
 alone+0.162
 forth+0.144
 tank+0.143
 afloat+0.137
Neg logit contributions
ves-0.185
Her-0.183
 vows-0.182
 brist-0.180
growth-0.163
Token's
Token ID338
Feature activation+5.33e-02

Pos logit contributions
ves+0.054
 vows+0.054
Her+0.053
 brist+0.052
 blonde+0.048
Neg logit contributions
o-0.051
 alone-0.048
 forth-0.043
 tank-0.043
 afloat-0.043
Token car
Token ID1097
Feature activation+1.14e-01

Pos logit contributions
o+0.093
 alone+0.088
 forth+0.079
 tank+0.079
 afloat+0.075
Neg logit contributions
Her-0.107
ves-0.107
 vows-0.105
 brist-0.104
growth-0.096
Token was
Token ID373
Feature activation-2.91e-02

Pos logit contributions
o+0.201
 alone+0.188
 forth+0.168
 tank+0.167
my+0.162
Neg logit contributions
Her-0.227
 vows-0.225
ves-0.225
 brist-0.223
growth-0.205
Token even
Token ID772
Feature activation-4.27e-02

Pos logit contributions
ves+0.067
Her+0.066
 brist+0.064
 vows+0.064
 blonde+0.062
Neg logit contributions
o-0.040
 forth-0.034
|-0.032
 alone-0.032
 tank-0.032
Token faster
Token ID5443
Feature activation+3.05e-01

Pos logit contributions
ves+0.077
Her+0.076
 brist+0.074
 ribbon+0.070
 blonde+0.070
Neg logit contributions
o-0.078
|-0.071
 tank-0.063
 polar-0.060
 alone-0.060
Token.
Token ID13
Feature activation-2.73e-02

Pos logit contributions
o+0.570
 alone+0.519
 forth+0.479
 tank+0.479
 polar+0.468
Neg logit contributions
ves-0.579
Her-0.568
 vows-0.567
 brist-0.558
 blonde-0.507
Token The
Token ID383
Feature activation-8.94e-03

Pos logit contributions
Her+0.062
ves+0.060
 Her+0.059
 brist+0.059
 vows+0.056
Neg logit contributions
o-0.037
 forth-0.036
 alone-0.036
 afloat-0.033
 polar-0.031
Token stranger
Token ID16195
Feature activation-3.13e-02

Pos logit contributions
ves+0.017
 vows+0.017
Her+0.017
 brist+0.016
 blonde+0.015
Neg logit contributions
o-0.017
 alone-0.016
 forth-0.014
 tank-0.014
 afloat-0.014
Token won
Token ID1839
Feature activation+1.41e-01

Pos logit contributions
ves+0.061
 vows+0.060
Her+0.060
 brist+0.058
 blonde+0.054
Neg logit contributions
o-0.056
 alone-0.052
 forth-0.047
 afloat-0.046
 tank-0.046
Token the
Token ID262
Feature activation+8.64e-02

Pos logit contributions
o+0.242
 alone+0.226
 forth+0.199
 tank+0.197
 afloat+0.193
Neg logit contributions
 vows-0.292
Her-0.288
ves-0.287
 brist-0.284
 blonde-0.265
Token of
Token ID286
Feature activation-6.28e-03

Pos logit contributions
Her+0.120
ves+0.120
 vows+0.117
 brist+0.116
growth+0.105
Neg logit contributions
o-0.135
 alone-0.126
 forth-0.117
 tank-0.116
 afloat-0.115
Token the
Token ID262
Feature activation+1.40e-01

Pos logit contributions
Her+0.011
growth+0.011
 brist+0.011
ves+0.010
 ribbon+0.010
Neg logit contributions
o-0.012
 afloat-0.010
 forth-0.010
 alone-0.010
ny-0.009
Token cliff
Token ID19516
Feature activation+1.75e-02

Pos logit contributions
o+0.257
 forth+0.223
 alone+0.223
 afloat+0.215
|+0.208
Neg logit contributions
 brist-0.243
 vows-0.238
ves-0.236
Her-0.235
ork-0.226
Token and
Token ID290
Feature activation+4.20e-02

Pos logit contributions
o+0.034
 alone+0.030
 polar+0.030
 forth+0.029
 afloat+0.029
Neg logit contributions
ves-0.031
Her-0.030
 vows-0.029
 brist-0.028
ork-0.026
Token looked
Token ID3114
Feature activation+5.07e-03

Pos logit contributions
o+0.080
 alone+0.073
 afloat+0.071
 tank+0.068
 polar+0.067
Neg logit contributions
 vows-0.072
ves-0.072
Her-0.071
 brist-0.069
 blush-0.064
Token down
Token ID866
Feature activation+3.63e-01

Pos logit contributions
o+0.009
|+0.008
 polar+0.007
 forth+0.007
 wreck+0.007
Neg logit contributions
 vows-0.010
Her-0.009
 brist-0.009
ves-0.009
 blush-0.009
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
o+0.588
 alone+0.577
 forth+0.490
 tank+0.489
 afloat+0.475
Neg logit contributions
ves-0.776
 vows-0.769
Her-0.755
 brist-0.754
growth-0.702
Token He
Token ID679
Feature activation+2.82e-01

Pos logit contributions
o+0.012
 alone+0.011
 forth+0.010
 tank+0.009
 afloat+0.009
Neg logit contributions
ves-0.026
Her-0.026
 vows-0.026
 brist-0.025
 blonde-0.024
Token saw
Token ID2497
Feature activation+1.33e-01

Pos logit contributions
o+0.446
 alone+0.420
 forth+0.376
 afloat+0.375
 tank+0.372
Neg logit contributions
ves-0.605
Her-0.595
 vows-0.593
 brist-0.583
 blonde-0.541
Token Tom
Token ID4186
Feature activation+1.71e-01

Pos logit contributions
o+0.258
 alone+0.243
 tank+0.218
 forth+0.218
my+0.212
Neg logit contributions
ves-0.246
 vows-0.245
Her-0.243
 brist-0.238
 blonde-0.216
Token in
Token ID287
Feature activation+1.45e-01

Pos logit contributions
o+0.283
 alone+0.258
 forth+0.239
 tank+0.238
 afloat+0.235
Neg logit contributions
Her-0.340
ves-0.336
 brist-0.324
 vows-0.323
 blonde-0.300
Token in
Token ID287
Feature activation+1.02e-01

Pos logit contributions
Her+0.142
 vows+0.141
ves+0.140
 brist+0.137
growth+0.127
Neg logit contributions
o-0.109
 alone-0.104
 forth-0.092
 tank-0.090
my-0.088
Token the
Token ID262
Feature activation+7.21e-02

Pos logit contributions
o+0.150
 alone+0.137
 forth+0.121
 tank+0.119
 afloat+0.115
Neg logit contributions
ves-0.233
 vows-0.232
Her-0.231
 brist-0.227
 blonde-0.211
Token sky
Token ID6766
Feature activation-1.65e-01

Pos logit contributions
o+0.152
 alone+0.144
 forth+0.132
 tank+0.130
my+0.128
Neg logit contributions
ves-0.120
 vows-0.119
Her-0.119
 brist-0.115
 blonde-0.103
Token.
Token ID13
Feature activation-3.82e-02

Pos logit contributions
ves+0.333
 vows+0.332
Her+0.332
 brist+0.324
growth+0.299
Neg logit contributions
o-0.291
 alone-0.271
 forth-0.240
 tank-0.238
my-0.236
Token Tim
Token ID5045
Feature activation+2.83e-01

Pos logit contributions
Her+0.113
ves+0.113
 vows+0.112
 brist+0.111
 blonde+0.105
Neg logit contributions
o-0.030
 alone-0.026
 forth-0.020
 tank-0.019
 afloat-0.018
Tokenmy
Token ID1820
Feature activation+3.87e-01

Pos logit contributions
 afloat+0.259
 alone+0.225
 polar+0.199
 tank+0.196
 wreck+0.186
Neg logit contributions
Her-0.761
 brist-0.756
 Her-0.708
 vows-0.699
 blush-0.690
Token didn
Token ID1422
Feature activation+2.58e-02

Pos logit contributions
o+0.648
 alone+0.574
my+0.525
 forth+0.522
 tank+0.505
Neg logit contributions
 vows-0.827
ves-0.826
Her-0.804
 brist-0.801
growth-0.778
Token't
Token ID470
Feature activation-1.43e-01

Pos logit contributions
o+0.048
 alone+0.044
 tank+0.040
 wreck+0.040
|+0.039
Neg logit contributions
 vows-0.050
 brist-0.048
 blonde-0.047
ves-0.046
Her-0.046
Token really
Token ID1107
Feature activation+4.56e-02

Pos logit contributions
Her+0.293
ves+0.286
 brist+0.285
 vows+0.284
 blonde+0.260
Neg logit contributions
o-0.242
 alone-0.221
 forth-0.206
 tank-0.203
 afloat-0.198
Token understand
Token ID1833
Feature activation-1.89e-01

Pos logit contributions
o+0.093
 alone+0.084
 forth+0.080
 tank+0.079
 afloat+0.077
Neg logit contributions
ves-0.079
Her-0.078
 vows-0.077
 brist-0.076
 blonde-0.069
Token,
Token ID11
Feature activation-4.18e-02

Pos logit contributions
ves+0.390
 vows+0.390
Her+0.387
 brist+0.380
growth+0.350
Neg logit contributions
o-0.321
 alone-0.299
 forth-0.268
 tank-0.264
my-0.257
TokenLook
Token ID8567
Feature activation-3.57e-02

Pos logit contributions
 vows+0.140
ves+0.140
 brist+0.134
Her+0.131
ork+0.126
Neg logit contributions
o-0.105
 alone-0.092
 forth-0.086
my-0.084
 tank-0.081
Token,
Token ID11
Feature activation-3.95e-02

Pos logit contributions
ves+0.061
 vows+0.061
Her+0.060
 brist+0.058
 blush+0.052
Neg logit contributions
o-0.070
 alone-0.066
 afloat-0.061
 tank-0.061
 polar-0.060
Token Ben
Token ID3932
Feature activation+8.28e-02

Pos logit contributions
ves+0.083
Her+0.083
 vows+0.083
 brist+0.081
 blonde+0.075
Neg logit contributions
o-0.066
 alone-0.061
 forth-0.054
 tank-0.054
 afloat-0.052
Token!"
Token ID2474
Feature activation+1.37e-01

Pos logit contributions
 alone+0.175
|+0.174
o+0.173
 afloat+0.168
 forth+0.166
Neg logit contributions
ves-0.114
 brist-0.109
Her-0.104
 vows-0.102
 ribbon-0.096
Token Mia
Token ID32189
Feature activation+3.76e-02

Pos logit contributions
o+0.161
 alone+0.157
 tank+0.127
 polar+0.120
 boy+0.115
Neg logit contributions
 brist-0.343
 vows-0.342
ves-0.339
Her-0.333
growth-0.317
Token says
Token ID1139
Feature activation+9.37e-02

Pos logit contributions
o+0.061
 alone+0.055
 afloat+0.053
 forth+0.053
 tank+0.051
Neg logit contributions
Her-0.077
ves-0.076
 brist-0.076
 vows-0.075
 Her-0.069
Token.
Token ID13
Feature activation-4.50e-02

Pos logit contributions
o+0.158
 alone+0.150
 forth+0.129
 tank+0.129
 afloat+0.124
Neg logit contributions
 vows-0.196
ves-0.195
 brist-0.191
Her-0.191
growth-0.181
Token "
Token ID366
Feature activation-1.12e-01

Pos logit contributions
 vows+0.091
ves+0.089
 brist+0.080
ork+0.075
 ribbon+0.075
Neg logit contributions
o-0.086
 alone-0.082
 tank-0.072
 down-0.067
 boy-0.066
TokenThe
Token ID464
Feature activation-1.39e-01

Pos logit contributions
 vows+0.211
ves+0.208
 brist+0.201
Her+0.199
 blonde+0.183
Neg logit contributions
o-0.218
 alone-0.203
 tank-0.180
 forth-0.180
my-0.177
Token tree
Token ID5509
Feature activation-4.20e-02

Pos logit contributions
ves+0.276
 vows+0.275
Her+0.270
 brist+0.256
growth+0.250
Neg logit contributions
o-0.250
 alone-0.247
 forth-0.219
my-0.214
 tank-0.213
Token has
Token ID468
Feature activation+1.35e-01

Pos logit contributions
ves+0.088
 vows+0.087
Her+0.086
 brist+0.085
 blonde+0.078
Neg logit contributions
o-0.070
 alone-0.064
 forth-0.058
 tank-0.057
 afloat-0.057
Tokenune
Token ID1726
Feature activation-2.18e-01

Pos logit contributions
ves+0.151
 vows+0.148
Her+0.147
 blonde+0.131
 ribbon+0.123
Neg logit contributions
o-0.195
my-0.157
 alone-0.152
 tank-0.145
 polar-0.143
Token was
Token ID373
Feature activation-2.71e-02

Pos logit contributions
Her+0.442
 vows+0.442
 brist+0.436
ves+0.431
growth+0.401
Neg logit contributions
o-0.386
 alone-0.352
 forth-0.316
 tank-0.314
my-0.309
Token excited
Token ID6568
Feature activation+6.87e-02

Pos logit contributions
Her+0.057
ves+0.056
 vows+0.055
 brist+0.055
 blonde+0.053
Neg logit contributions
o-0.044
 alone-0.038
 forth-0.037
 tank-0.036
|-0.035
Token.
Token ID13
Feature activation-1.99e-02

Pos logit contributions
o+0.117
 alone+0.109
 forth+0.098
my+0.095
 tank+0.094
Neg logit contributions
ves-0.145
 vows-0.144
Her-0.143
 brist-0.141
growth-0.131
Token It
Token ID632
Feature activation-1.59e-01

Pos logit contributions
Her+0.036
ves+0.035
 vows+0.035
 brist+0.035
growth+0.032
Neg logit contributions
o-0.038
 alone-0.036
 forth-0.034
 afloat-0.032
 polar-0.032
Token had
Token ID550
Feature activation+6.98e-02

Pos logit contributions
ves+0.302
 vows+0.300
Her+0.300
 brist+0.294
 blonde+0.268
Neg logit contributions
o-0.292
 alone-0.272
 forth-0.248
 tank-0.244
 afloat-0.240
Token never
Token ID1239
Feature activation-4.18e-02

Pos logit contributions
o+0.112
 alone+0.110
my+0.092
 polar+0.091
 tank+0.090
Neg logit contributions
 brist-0.149
Her-0.148
ves-0.145
 vows-0.141
 blush-0.137
Token been
Token ID587
Feature activation-1.70e-02

Pos logit contributions
ves+0.083
Her+0.083
 vows+0.082
 brist+0.081
 blonde+0.075
Neg logit contributions
o-0.072
 alone-0.066
 tank-0.061
 forth-0.061
 afloat-0.059
Token on
Token ID319
Feature activation+1.03e-01

Pos logit contributions
ves+0.034
 vows+0.034
Her+0.034
 brist+0.033
 blonde+0.031
Neg logit contributions
o-0.029
 alone-0.027
 forth-0.025
 tank-0.024
 afloat-0.024
Token an
Token ID281
Feature activation-1.78e-01

Pos logit contributions
 alone+0.154
o+0.145
 tank+0.126
 polar+0.122
 wreck+0.119
Neg logit contributions
Her-0.238
ves-0.235
 vows-0.231
 brist-0.228
 blush-0.212
Token adventure
Token ID8855
Feature activation+2.11e-02

Pos logit contributions
ves+0.353
Her+0.352
 vows+0.351
 brist+0.346
 blonde+0.316
Neg logit contributions
o-0.314
 alone-0.288
 forth-0.262
 tank-0.259
 afloat-0.253
Tokenily
Token ID813
Feature activation-1.38e-01

Pos logit contributions
o+0.100
 alone+0.094
my+0.087
 forth+0.085
 tank+0.084
Neg logit contributions
 vows-0.064
ves-0.064
Her-0.061
 brist-0.061
 blonde-0.055
Token stopped
Token ID5025
Feature activation-2.40e-02

Pos logit contributions
ves+0.298
Her+0.290
 vows+0.286
 brist+0.279
growth+0.269
Neg logit contributions
o-0.236
 alone-0.209
my-0.199
 forth-0.189
 tank-0.187
Token weeping
Token ID45705
Feature activation+1.50e-01

Pos logit contributions
Her+0.050
 brist+0.048
 vows+0.046
ves+0.045
 Her+0.044
Neg logit contributions
o-0.040
 alone-0.035
 afloat-0.033
 tank-0.033
 forth-0.033
Token and
Token ID290
Feature activation+3.86e-02

Pos logit contributions
 alone+0.235
o+0.231
 forth+0.205
 tank+0.193
my+0.191
Neg logit contributions
ves-0.335
 vows-0.330
Her-0.320
 brist-0.316
growth-0.299
Token waited
Token ID13488
Feature activation-2.32e-02

Pos logit contributions
o+0.065
 alone+0.061
 forth+0.055
 tank+0.053
my+0.052
Neg logit contributions
ves-0.082
 vows-0.080
Her-0.080
 brist-0.079
growth-0.073
Token for
Token ID329
Feature activation+1.72e-01

Pos logit contributions
ves+0.056
 vows+0.055
Her+0.054
 brist+0.053
growth+0.053
Neg logit contributions
 alone-0.032
o-0.029
 tank-0.025
 forth-0.024
 afloat-0.024
Token the
Token ID262
Feature activation+1.24e-01

Pos logit contributions
 alone+0.198
o+0.198
 forth+0.177
 tank+0.173
 polar+0.168
Neg logit contributions
 vows-0.428
ves-0.422
Her-0.409
 brist-0.396
owers-0.382
Token gum
Token ID27142
Feature activation-2.79e-02

Pos logit contributions
o+0.264
 alone+0.246
 forth+0.226
 tank+0.222
 afloat+0.220
Neg logit contributions
ves-0.203
 vows-0.201
Her-0.201
 brist-0.200
 blonde-0.178
Token to
Token ID284
Feature activation-2.66e-02

Pos logit contributions
 brist+0.062
ves+0.062
Her+0.061
 vows+0.061
growth+0.058
Neg logit contributions
o-0.045
 alone-0.044
 tank-0.036
my-0.036
 forth-0.035
Token come
Token ID1282
Feature activation+1.70e-02

Pos logit contributions
ves+0.051
 vows+0.051
Her+0.051
 brist+0.050
 blonde+0.045
Neg logit contributions
o-0.048
 alone-0.046
 forth-0.042
 tank-0.041
 afloat-0.040
Token out
Token ID503
Feature activation+7.46e-02

Pos logit contributions
o+0.025
 alone+0.023
 forth+0.021
 tank+0.020
 wreck+0.020
Neg logit contributions
Her-0.038
 vows-0.037
ves-0.037
 brist-0.037
 blonde-0.034
Token record
Token ID1700
Feature activation+1.84e-02

Pos logit contributions
o+0.065
 alone+0.065
 tank+0.055
 forth+0.054
my+0.053
Neg logit contributions
 vows-0.096
ves-0.094
 brist-0.093
Her-0.092
growth-0.086
Token a
Token ID257
Feature activation-5.57e-02

Pos logit contributions
o+0.030
 alone+0.030
 forth+0.026
 tank+0.025
my+0.025
Neg logit contributions
 vows-0.038
Her-0.037
ves-0.037
 brist-0.037
growth-0.035
Token song
Token ID3496
Feature activation-7.80e-02

Pos logit contributions
ves+0.096
 vows+0.095
Her+0.094
 brist+0.093
 blonde+0.084
Neg logit contributions
o-0.113
 alone-0.105
 forth-0.097
 tank-0.095
 afloat-0.094
Token together
Token ID1978
Feature activation+1.88e-01

Pos logit contributions
 brist+0.172
Her+0.171
 vows+0.171
ves+0.170
growth+0.164
Neg logit contributions
o-0.123
 alone-0.118
 forth-0.098
 tank-0.098
my-0.098
Token.
Token ID13
Feature activation+3.29e-02

Pos logit contributions
 alone+0.283
o+0.280
 forth+0.237
 tank+0.232
my+0.229
Neg logit contributions
Her-0.422
 brist-0.419
ves-0.416
 vows-0.410
growth-0.390
Token
Token ID198
Feature activation+1.37e-01

Pos logit contributions
o+0.061
 alone+0.058
 forth+0.054
 afloat+0.052
 tank+0.052
Neg logit contributions
Her-0.061
ves-0.060
 vows-0.060
 brist-0.059
 blonde-0.054
Token
Token ID198
Feature activation+1.35e-01

Pos logit contributions
o+0.225
 alone+0.217
 forth+0.210
 afloat+0.198
 tank+0.196
Neg logit contributions
Her-0.289
ves-0.284
 vows-0.265
 brist-0.263
growth-0.248
TokenThe
Token ID464
Feature activation-6.67e-02

Pos logit contributions
o+0.295
 alone+0.276
 forth+0.254
 tank+0.251
my+0.248
Neg logit contributions
 vows-0.214
ves-0.213
 brist-0.208
Her-0.208
 blonde-0.185
Token man
Token ID582
Feature activation+1.15e-01

Pos logit contributions
ves+0.127
Her+0.127
 vows+0.126
 brist+0.123
growth+0.113
Neg logit contributions
o-0.122
 alone-0.115
 forth-0.105
 tank-0.104
my-0.100
Token was
Token ID373
Feature activation+1.94e-02

Pos logit contributions
o+0.203
 alone+0.188
 forth+0.169
 tank+0.168
my+0.164
Neg logit contributions
Her-0.231
ves-0.231
 vows-0.229
 brist-0.227
growth-0.208
Token happy
Token ID3772
Feature activation+2.43e-01

Pos logit contributions
o+0.032
 forth+0.027
 alone+0.027
 tank+0.026
|+0.025
Neg logit contributions
Her-0.041
 vows-0.040
ves-0.039
 brist-0.039
 blonde-0.037
Tokenbar
Token ID5657
Feature activation+2.07e-01

Pos logit contributions
o+0.082
 alone+0.075
 forth+0.067
 tank+0.067
my+0.065
Neg logit contributions
 vows-0.097
ves-0.096
Her-0.096
 brist-0.094
 blonde-0.087
Tokenrow
Token ID808
Feature activation+3.84e-02

Pos logit contributions
o+0.378
 alone+0.356
 forth+0.323
 tank+0.318
 afloat+0.311
Neg logit contributions
ves-0.393
Her-0.388
 vows-0.384
 brist-0.379
growth-0.344
Token.
Token ID13
Feature activation+1.73e-03

Pos logit contributions
o+0.065
 alone+0.062
 tank+0.054
 afloat+0.053
 forth+0.052
Neg logit contributions
Her-0.080
 vows-0.080
ves-0.078
 brist-0.078
growth-0.073
Token
Token ID198
Feature activation+1.09e-01

Pos logit contributions
o+0.003
 alone+0.003
 forth+0.003
 afloat+0.002
 tank+0.002
Neg logit contributions
Her-0.003
 vows-0.003
ves-0.003
 brist-0.003
 blonde-0.003
Token
Token ID198
Feature activation+1.08e-01

Pos logit contributions
o+0.176
 alone+0.171
 forth+0.163
 tank+0.151
 afloat+0.150
Neg logit contributions
ves-0.232
Her-0.231
 vows-0.219
 brist-0.215
ork-0.202
TokenJohn
Token ID7554
Feature activation+1.06e-01

Pos logit contributions
o+0.234
 alone+0.219
 forth+0.201
 tank+0.200
my+0.196
Neg logit contributions
ves-0.172
 vows-0.172
Her-0.169
 brist-0.168
 blonde-0.149
Token:
Token ID25
Feature activation-1.96e-01

Pos logit contributions
o+0.192
 alone+0.172
 forth+0.157
my+0.155
 tank+0.154
Neg logit contributions
Her-0.213
ves-0.212
 vows-0.212
 brist-0.207
growth-0.190
Token "
Token ID366
Feature activation-7.34e-02

Pos logit contributions
Her+0.300
 vows+0.298
ves+0.295
 brist+0.291
 blonde+0.266
Neg logit contributions
o-0.429
 alone-0.403
 forth-0.375
 afloat-0.372
 tank-0.368
TokenWhat
Token ID2061
Feature activation+2.97e-02

Pos logit contributions
Her+0.122
 brist+0.119
 vows+0.118
ves+0.118
 blonde+0.107
Neg logit contributions
o-0.154
 alone-0.148
 tank-0.135
 forth-0.134
 afloat-0.131
Token we
Token ID356
Feature activation+1.47e-01

Pos logit contributions
o+0.051
 alone+0.045
 tank+0.041
my+0.041
 wreck+0.038
Neg logit contributions
Her-0.064
 brist-0.062
 vows-0.062
ves-0.061
growth-0.058
Token doing
Token ID1804
Feature activation+1.40e-01

Pos logit contributions
o+0.281
 alone+0.244
 polar+0.233
|+0.227
 afloat+0.223
Neg logit contributions
 brist-0.258
 vows-0.248
Her-0.240
ves-0.239
 ribbon-0.234
Token it
Token ID340
Feature activation+2.12e-02

Pos logit contributions
o+0.122
 alone+0.116
 forth+0.111
my+0.104
 tank+0.102
Neg logit contributions
Her-0.131
ves-0.130
 vows-0.127
 brist-0.123
growth-0.120
Token broke
Token ID6265
Feature activation+4.36e-02

Pos logit contributions
o+0.033
 alone+0.032
my+0.028
 forth+0.028
 tank+0.026
Neg logit contributions
Her-0.048
growth-0.046
ves-0.046
 vows-0.045
 brist-0.044
Token into
Token ID656
Feature activation+1.46e-01

Pos logit contributions
o+0.072
 alone+0.067
 forth+0.060
my+0.059
 tank+0.057
Neg logit contributions
ves-0.094
 vows-0.094
Her-0.092
 brist-0.089
growth-0.085
Token a
Token ID257
Feature activation-7.25e-02

Pos logit contributions
 alone+0.247
o+0.232
 tank+0.204
my+0.201
 wreck+0.198
Neg logit contributions
 vows-0.315
ves-0.305
Her-0.284
owers-0.275
 brist-0.267
Token million
Token ID1510
Feature activation+1.14e-01

Pos logit contributions
ves+0.150
Her+0.149
 vows+0.149
 brist+0.147
 blonde+0.134
Neg logit contributions
o-0.122
 alone-0.112
 forth-0.101
 tank-0.099
 afloat-0.097
Token pieces
Token ID5207
Feature activation-4.71e-02

Pos logit contributions
 alone+0.208
o+0.202
 forth+0.181
 wreck+0.180
 tank+0.178
Neg logit contributions
 vows-0.226
ves-0.224
Her-0.224
 brist-0.202
growth-0.193
Token.
Token ID13
Feature activation+2.27e-02

Pos logit contributions
 vows+0.102
Her+0.101
ves+0.099
 brist+0.099
growth+0.093
Neg logit contributions
o-0.077
 alone-0.076
 tank-0.063
 forth-0.062
my-0.062
Token Lily
Token ID20037
Feature activation+1.84e-01

Pos logit contributions
o+0.041
 alone+0.038
 forth+0.035
 tank+0.034
 afloat+0.034
Neg logit contributions
Her-0.044
ves-0.043
 vows-0.043
 brist-0.042
 blonde-0.039
Token's
Token ID338
Feature activation+9.86e-02

Pos logit contributions
o+0.312
 alone+0.287
my+0.261
 forth+0.255
 tank+0.249
Neg logit contributions
ves-0.396
 vows-0.389
Her-0.385
 brist-0.372
growth-0.361
Token mom
Token ID1995
Feature activation-3.81e-02

Pos logit contributions
o+0.175
 alone+0.173
 tank+0.158
 forth+0.151
 wreck+0.150
Neg logit contributions
Her-0.195
ves-0.193
 vows-0.185
 brist-0.181
growth-0.181
Token was
Token ID373
Feature activation+1.39e-02

Pos logit contributions
ves+0.084
 vows+0.083
Her+0.083
 brist+0.081
growth+0.078
Neg logit contributions
o-0.062
 alone-0.056
my-0.052
 forth-0.051
 tank-0.048
Token.
Token ID13
Feature activation-4.55e-02

Pos logit contributions
 alone+0.319
o+0.317
 tank+0.265
 afloat+0.263
 forth+0.263
Neg logit contributions
 vows-0.434
ves-0.433
Her-0.426
 brist-0.420
growth-0.398
Token From
Token ID3574
Feature activation-6.00e-02

Pos logit contributions
ves+0.084
Her+0.084
 vows+0.083
 brist+0.082
 blonde+0.074
Neg logit contributions
o-0.087
 alone-0.081
 forth-0.074
 tank-0.073
 afloat-0.072
Token then
Token ID788
Feature activation-4.53e-02

Pos logit contributions
ves+0.077
Her+0.077
 brist+0.073
 vows+0.071
 ribbon+0.065
Neg logit contributions
o-0.144
|-0.130
 alone-0.127
 tank-0.124
 polar-0.124
Token on
Token ID319
Feature activation+7.62e-02

Pos logit contributions
ves+0.105
Her+0.104
 vows+0.103
 brist+0.101
 blonde+0.093
Neg logit contributions
o-0.066
 alone-0.060
 tank-0.053
 forth-0.052
 afloat-0.051
Token,
Token ID11
Feature activation-5.24e-02

Pos logit contributions
o+0.125
 alone+0.120
 forth+0.108
 tank+0.105
my+0.099
Neg logit contributions
 vows-0.160
Her-0.158
 brist-0.158
ves-0.156
growth-0.146
Token it
Token ID340
Feature activation-6.74e-02

Pos logit contributions
ves+0.107
Her+0.106
 vows+0.103
 brist+0.102
 blonde+0.095
Neg logit contributions
o-0.090
 alone-0.078
 polar-0.072
 tank-0.072
 afloat-0.071
Token was
Token ID373
Feature activation-5.62e-02

Pos logit contributions
ves+0.119
 vows+0.116
Her+0.115
 brist+0.112
growth+0.101
Neg logit contributions
o-0.131
 alone-0.121
 afloat-0.114
 forth-0.114
 tank-0.112
Token much
Token ID881
Feature activation-9.88e-02

Pos logit contributions
ves+0.109
Her+0.108
 vows+0.107
 brist+0.105
 blonde+0.096
Neg logit contributions
o-0.102
 alone-0.095
 forth-0.087
 tank-0.086
 afloat-0.084
Token quieter
Token ID43880
Feature activation+4.92e-02

Pos logit contributions
Her+0.178
ves+0.178
 brist+0.176
 vows+0.172
 blonde+0.157
Neg logit contributions
o-0.192
 alone-0.170
|-0.159
 tank-0.156
 forth-0.153
Token and
Token ID290
Feature activation-2.58e-02

Pos logit contributions
o+0.084
 alone+0.077
 forth+0.070
 tank+0.069
 afloat+0.067
Neg logit contributions
ves-0.101
Her-0.100
 vows-0.100
 brist-0.098
 blonde-0.090
Token people
Token ID661
Feature activation-7.92e-02

Pos logit contributions
ves+0.048
 vows+0.047
Her+0.046
 brist+0.045
 blonde+0.041
Neg logit contributions
o-0.048
 alone-0.043
 tank-0.041
 afloat-0.040
 polar-0.039
Token a
Token ID257
Feature activation-1.65e-01

Pos logit contributions
o+0.291
 alone+0.273
 tank+0.247
my+0.244
 forth+0.243
Neg logit contributions
 vows-0.228
ves-0.225
 brist-0.221
Her-0.219
 blonde-0.195
Token time
Token ID640
Feature activation-6.96e-02

Pos logit contributions
ves+0.289
Her+0.284
 vows+0.280
 brist+0.276
 blonde+0.253
Neg logit contributions
o-0.329
 alone-0.312
 forth-0.292
 tank-0.284
 afloat-0.281
Token,
Token ID11
Feature activation-6.36e-02

Pos logit contributions
ves+0.096
Her+0.095
 vows+0.083
 brist+0.081
 Her+0.081
Neg logit contributions
o-0.154
 forth-0.152
 alone-0.149
 afloat-0.146
 polar-0.143
Token there
Token ID612
Feature activation+1.49e-01

Pos logit contributions
Her+0.111
ves+0.104
 Her+0.096
 blonde+0.095
 brist+0.092
Neg logit contributions
o-0.113
 forth-0.106
 polar-0.106
ior-0.103
 afloat-0.102
Token was
Token ID373
Feature activation-6.98e-02

Pos logit contributions
o+0.310
 alone+0.298
 forth+0.287
 afloat+0.281
 tank+0.269
Neg logit contributions
ves-0.239
Her-0.235
 vows-0.227
 brist-0.221
growth-0.202
Token a
Token ID257
Feature activation-1.67e-01

Pos logit contributions
ves+0.112
 vows+0.112
Her+0.110
 brist+0.108
 blonde+0.096
Neg logit contributions
o-0.152
 alone-0.143
 tank-0.130
 forth-0.130
my-0.127
Token spot
Token ID4136
Feature activation-3.58e-02

Pos logit contributions
Her+0.229
 brist+0.223
ves+0.221
 vows+0.220
 ribbon+0.205
Neg logit contributions
o-0.384
 alone-0.352
 afloat-0.347
|-0.345
 forth-0.342
Token.
Token ID13
Feature activation-6.25e-02

Pos logit contributions
ves+0.077
Her+0.076
 vows+0.076
 brist+0.074
 blonde+0.068
Neg logit contributions
o-0.056
 alone-0.052
 forth-0.048
 afloat-0.046
 tank-0.046
Token It
Token ID632
Feature activation-2.01e-01

Pos logit contributions
ves+0.119
 vows+0.117
Her+0.114
 brist+0.111
ork+0.099
Neg logit contributions
o-0.122
 alone-0.113
 tank-0.103
my-0.100
 polar-0.098
Token seemed
Token ID3947
Feature activation-1.61e-01

Pos logit contributions
ves+0.352
Her+0.350
 vows+0.344
 brist+0.340
 blonde+0.306
Neg logit contributions
o-0.395
 alone-0.369
 forth-0.355
 afloat-0.346
 tank-0.336
Token very
Token ID845
Feature activation+4.61e-02

Pos logit contributions
ves+0.321
 vows+0.321
Her+0.320
 brist+0.316
 blonde+0.291
Neg logit contributions
o-0.277
 alone-0.249
 forth-0.235
 tank-0.226
my-0.223
Token.
Token ID13
Feature activation-5.09e-02

Pos logit contributions
o+0.189
 alone+0.173
 forth+0.160
 tank+0.156
 afloat+0.156
Neg logit contributions
Her-0.195
ves-0.193
 vows-0.192
 brist-0.190
 blonde-0.173
Token She
Token ID1375
Feature activation-2.59e-01

Pos logit contributions
ves+0.103
 vows+0.091
Her+0.081
 brist+0.081
 ribbon+0.080
Neg logit contributions
o-0.104
 alone-0.102
my-0.090
 tank-0.089
ny-0.081
Token was
Token ID373
Feature activation-6.09e-02

Pos logit contributions
ves+0.557
Her+0.553
 vows+0.553
 brist+0.544
growth+0.501
Neg logit contributions
o-0.421
 alone-0.387
 forth-0.345
 tank-0.341
my-0.330
Token only
Token ID691
Feature activation-1.14e-01

Pos logit contributions
Her+0.130
 brist+0.126
 vows+0.126
ves+0.124
 blonde+0.119
Neg logit contributions
o-0.097
 forth-0.083
 alone-0.083
 afloat-0.081
 tank-0.078
Token 3
Token ID513
Feature activation-7.36e-02

Pos logit contributions
Her+0.166
 vows+0.165
 brist+0.165
ves+0.164
 blonde+0.147
Neg logit contributions
o-0.260
 alone-0.243
 forth-0.228
 tank-0.225
 afloat-0.223
Token years
Token ID812
Feature activation-5.54e-02

Pos logit contributions
 vows+0.141
Her+0.141
ves+0.141
 brist+0.138
growth+0.127
Neg logit contributions
o-0.135
 alone-0.127
 forth-0.114
 tank-0.112
my-0.110
Token old
Token ID1468
Feature activation+1.58e-02

Pos logit contributions
ves+0.115
Her+0.115
 vows+0.115
 brist+0.113
 blonde+0.104
Neg logit contributions
o-0.093
 alone-0.085
 forth-0.077
 tank-0.076
 afloat-0.074
Token and
Token ID290
Feature activation-2.96e-02

Pos logit contributions
o+0.025
 alone+0.024
 tank+0.021
 forth+0.021
my+0.021
Neg logit contributions
ves-0.036
Her-0.035
 vows-0.035
 brist-0.034
growth-0.032
Token was
Token ID373
Feature activation-6.28e-02

Pos logit contributions
ves+0.058
 vows+0.058
Her+0.057
 brist+0.056
growth+0.054
Neg logit contributions
o-0.053
 alone-0.052
 tank-0.045
 forth-0.044
my-0.044
Token very
Token ID845
Feature activation+5.61e-02

Pos logit contributions
Her+0.136
ves+0.135
 vows+0.135
 brist+0.134
 blonde+0.124
Neg logit contributions
o-0.099
 alone-0.089
 forth-0.082
 tank-0.080
 afloat-0.079
Token upset
Token ID9247
Feature activation+2.00e-01

Pos logit contributions
o+0.088
 forth+0.079
 afloat+0.077
|+0.072
 tank+0.071
Neg logit contributions
Her-0.122
 vows-0.119
 brist-0.117
ves-0.116
 blonde-0.113
Token even
Token ID772
Feature activation-7.62e-02

Pos logit contributions
ves+0.027
Her+0.027
 vows+0.026
 brist+0.026
 blonde+0.024
Neg logit contributions
o-0.021
 alone-0.018
 forth-0.018
|-0.017
 tank-0.017
Token stronger
Token ID7387
Feature activation+1.59e-01

Pos logit contributions
Her+0.116
 brist+0.108
ves+0.105
 ribbon+0.098
 words+0.097
Neg logit contributions
o-0.165
|-0.151
 tank-0.139
 polar-0.138
 wreck-0.134
Token.
Token ID13
Feature activation-5.25e-02

Pos logit contributions
o+0.322
 alone+0.287
 polar+0.285
 tank+0.280
|+0.278
Neg logit contributions
ves-0.262
Her-0.253
 vows-0.252
 brist-0.248
 ribbon-0.224
Token So
Token ID1406
Feature activation-9.38e-02

Pos logit contributions
Her+0.098
ves+0.095
 brist+0.093
 vows+0.092
 blonde+0.087
Neg logit contributions
o-0.098
 alone-0.093
 forth-0.088
 afloat-0.086
 polar-0.084
Token,
Token ID11
Feature activation-5.60e-02

Pos logit contributions
ves+0.189
 vows+0.189
Her+0.188
 brist+0.185
growth+0.169
Neg logit contributions
o-0.165
 alone-0.154
 forth-0.141
 tank-0.137
my-0.133
Token each
Token ID1123
Feature activation-1.44e-01

Pos logit contributions
 vows+0.140
ves+0.137
Her+0.136
 brist+0.135
growth+0.125
Neg logit contributions
o-0.073
 alone-0.070
 forth-0.061
 tank-0.058
 afloat-0.054
Token day
Token ID1110
Feature activation+1.33e-01

Pos logit contributions
Her+0.295
ves+0.292
 brist+0.279
 vows+0.277
growth+0.265
Neg logit contributions
o-0.242
 alone-0.208
 afloat-0.201
 forth-0.193
 tank-0.193
Token it
Token ID340
Feature activation-7.53e-02

Pos logit contributions
o+0.185
 alone+0.166
 tank+0.141
 forth+0.130
 afloat+0.130
Neg logit contributions
 vows-0.330
Her-0.322
 brist-0.320
ves-0.308
growth-0.304
Token would
Token ID561
Feature activation-1.32e-01

Pos logit contributions
ves+0.143
Her+0.143
 vows+0.143
 brist+0.140
 blonde+0.128
Neg logit contributions
o-0.140
 alone-0.130
 forth-0.118
 tank-0.117
my-0.113
Token go
Token ID467
Feature activation-6.18e-02

Pos logit contributions
ves+0.282
 vows+0.277
Her+0.275
 brist+0.275
growth+0.254
Neg logit contributions
o-0.211
 alone-0.207
 tank-0.182
 forth-0.178
 wreck-0.172
Token for
Token ID329
Feature activation+9.59e-02

Pos logit contributions
Her+0.102
ves+0.100
 brist+0.093
ork+0.089
 ribbon+0.089
Neg logit contributions
o-0.113
 polar-0.102
 alone-0.099
 forth-0.099
igator-0.098
Token and
Token ID290
Feature activation-3.82e-02

Pos logit contributions
 alone+0.010
o+0.009
 forth+0.008
 afloat+0.007
 tank+0.007
Neg logit contributions
 vows-0.016
ves-0.016
Her-0.016
 brist-0.016
growth-0.015
Token slept
Token ID21256
Feature activation+6.10e-03

Pos logit contributions
ves+0.076
Her+0.075
 vows+0.075
 brist+0.074
 blonde+0.068
Neg logit contributions
o-0.067
 alone-0.063
 forth-0.057
 tank-0.056
my-0.054
Token.
Token ID13
Feature activation-6.12e-02

Pos logit contributions
 alone+0.009
o+0.008
 forth+0.007
 afloat+0.007
 tank+0.007
Neg logit contributions
 vows-0.014
Her-0.014
ves-0.014
 brist-0.014
growth-0.013
Token
Token ID198
Feature activation+4.36e-02

Pos logit contributions
ves+0.132
 vows+0.128
 brist+0.116
Her+0.113
 ribbon+0.112
Neg logit contributions
o-0.108
 alone-0.105
my-0.093
|-0.088
 tank-0.082
Token
Token ID198
Feature activation+4.31e-02

Pos logit contributions
o+0.067
 alone+0.062
 forth+0.057
 tank+0.055
 afloat+0.054
Neg logit contributions
ves-0.096
Her-0.096
 vows-0.094
 brist-0.092
growth-0.086
TokenFinally
Token ID11158
Feature activation-3.58e-01

Pos logit contributions
o+0.079
 alone+0.079
|+0.070
my+0.068
 late+0.065
Neg logit contributions
 vows-0.085
 brist-0.079
 blush-0.073
 blonde-0.073
ves-0.072
Token,
Token ID11
Feature activation-6.68e-02

Pos logit contributions
 vows+0.979
 brist+0.968
ves+0.964
 meanings+0.940
Her+0.930
Neg logit contributions
 alone-0.376
o-0.326
 forth-0.310
my-0.272
 Tim-0.257
Token when
Token ID618
Feature activation-5.88e-02

Pos logit contributions
 vows+0.166
ves+0.165
 brist+0.158
Her+0.153
growth+0.146
Neg logit contributions
 alone-0.091
o-0.083
 forth-0.079
my-0.068
 down-0.066
Token the
Token ID262
Feature activation+4.72e-02

Pos logit contributions
 vows+0.131
ves+0.129
 brist+0.126
Her+0.124
growth+0.115
Neg logit contributions
 alone-0.092
o-0.087
 forth-0.083
my-0.073
 tank-0.071
Token sun
Token ID4252
Feature activation-1.26e-01

Pos logit contributions
 alone+0.085
o+0.083
 forth+0.075
 tank+0.075
 polar+0.073
Neg logit contributions
ves-0.090
Her-0.090
 vows-0.088
 brist-0.088
 blonde-0.080
Token rose
Token ID8278
Feature activation-3.08e-01

Pos logit contributions
Her+0.253
ves+0.252
 brist+0.251
 vows+0.250
 blonde+0.235
Neg logit contributions
o-0.221
 alone-0.202
 forth-0.191
my-0.183
 tank-0.180
Token walking
Token ID6155
Feature activation-9.27e-03

Pos logit contributions
Her+0.140
ves+0.137
 vows+0.137
 brist+0.137
 blonde+0.127
Neg logit contributions
o-0.112
 alone-0.102
 forth-0.094
 tank-0.092
 afloat-0.091
Token around
Token ID1088
Feature activation+1.53e-01

Pos logit contributions
Her+0.021
 brist+0.020
 vows+0.020
ves+0.020
 blonde+0.019
Neg logit contributions
o-0.014
 alone-0.012
 afloat-0.011
 tank-0.011
 polar-0.011
Token her
Token ID607
Feature activation-3.07e-01

Pos logit contributions
o+0.233
 alone+0.222
 forth+0.192
 tank+0.187
my+0.183
Neg logit contributions
ves-0.349
 vows-0.346
Her-0.338
 brist-0.334
 blonde-0.309
Token garden
Token ID11376
Feature activation-1.89e-01

Pos logit contributions
ves+0.674
 vows+0.671
Her+0.655
 brist+0.650
growth+0.607
Neg logit contributions
o-0.500
 alone-0.470
 forth-0.409
 tank-0.407
my-0.394
Token when
Token ID618
Feature activation-5.57e-02

Pos logit contributions
 vows+0.528
ves+0.503
growth+0.477
 brist+0.475
 meanings+0.459
Neg logit contributions
 alone-0.251
o-0.232
my-0.183
 tank-0.176
 forth-0.166
Token she
Token ID673
Feature activation-3.45e-01

Pos logit contributions
 vows+0.083
ves+0.079
 brist+0.078
Her+0.068
 ribbon+0.068
Neg logit contributions
 alone-0.133
o-0.127
 forth-0.119
my-0.114
 tank-0.108
Token saw
Token ID2497
Feature activation+6.59e-02

Pos logit contributions
ves+0.817
 vows+0.816
Her+0.810
 brist+0.803
growth+0.742
Neg logit contributions
o-0.490
 alone-0.441
 forth-0.382
 tank-0.375
my-0.369
Token an
Token ID281
Feature activation-2.18e-01

Pos logit contributions
 alone+0.095
o+0.089
my+0.082
 Tim+0.078
 polar+0.077
Neg logit contributions
 vows-0.165
ves-0.160
ork-0.146
ues-0.142
 brist-0.140
Token amazing
Token ID4998
Feature activation-1.18e-01

Pos logit contributions
Her+0.431
ves+0.429
 vows+0.427
 brist+0.425
 blonde+0.387
Neg logit contributions
o-0.384
 alone-0.346
 forth-0.317
 tank-0.311
 afloat-0.307
Token symbol
Token ID6194
Feature activation-7.45e-02

Pos logit contributions
Her+0.204
ves+0.204
 vows+0.199
 brist+0.192
growth+0.180
Neg logit contributions
o-0.239
 alone-0.229
 forth-0.212
 tank-0.212
 wreck-0.204
Token.
Token ID13
Feature activation-6.20e-02

Pos logit contributions
 vows+0.187
Her+0.183
 brist+0.181
growth+0.175
ves+0.172
Neg logit contributions
o-0.099
 alone-0.098
 tank-0.077
 forth-0.076
my-0.074
Token saw
Token ID2497
Feature activation+6.72e-02

Pos logit contributions
o+0.212
 alone+0.193
 tank+0.167
my+0.167
 forth+0.165
Neg logit contributions
Her-0.284
 brist-0.276
 vows-0.276
ves-0.276
 blonde-0.253
Token it
Token ID340
Feature activation-7.87e-02

Pos logit contributions
o+0.117
 alone+0.115
 tank+0.103
 wreck+0.098
 forth+0.098
Neg logit contributions
Her-0.138
ves-0.134
 vows-0.134
 brist-0.132
 blonde-0.119
Token.
Token ID13
Feature activation-6.28e-02

Pos logit contributions
 vows+0.174
Her+0.173
 brist+0.171
ves+0.170
growth+0.156
Neg logit contributions
o-0.127
 alone-0.124
my-0.106
 tank-0.104
 forth-0.104
Token
Token ID198
Feature activation+4.27e-02

Pos logit contributions
Her+0.116
 brist+0.111
 Her+0.111
ves+0.110
 vows+0.110
Neg logit contributions
 forth-0.113
o-0.109
 alone-0.109
 afloat-0.103
 polar-0.096
Token
Token ID198
Feature activation+4.25e-02

Pos logit contributions
o+0.073
 forth+0.073
 alone+0.072
 afloat+0.065
 tank+0.064
Neg logit contributions
ves-0.087
Her-0.086
 vows-0.078
 brist-0.077
ork-0.075
TokenTo
Token ID2514
Feature activation-2.96e-01

Pos logit contributions
o+0.096
 alone+0.090
 forth+0.083
 tank+0.083
 afloat+0.081
Neg logit contributions
ves-0.064
 vows-0.064
Her-0.064
 brist-0.062
 blonde-0.055
Token the
Token ID262
Feature activation+5.05e-02

Pos logit contributions
ves+0.751
Her+0.747
 vows+0.746
 brist+0.736
 blonde+0.687
Neg logit contributions
o-0.365
 alone-0.328
 forth-0.280
 tank-0.275
 afloat-0.264
Token little
Token ID1310
Feature activation-1.01e-01

Pos logit contributions
 alone+0.092
o+0.091
 forth+0.081
 tank+0.081
my+0.079
Neg logit contributions
ves-0.099
 vows-0.097
Her-0.097
 brist-0.093
growth-0.085
Token boy
Token ID2933
Feature activation+3.01e-01

Pos logit contributions
 brist+0.219
 ribbon+0.213
 blonde+0.207
 words+0.201
growth+0.199
Neg logit contributions
o-0.147
|-0.109
 afloat-0.105
ll-0.105
 polar-0.097
Token's
Token ID338
Feature activation+1.36e-02

Pos logit contributions
o+0.528
 alone+0.489
 forth+0.442
 tank+0.436
 afloat+0.426
Neg logit contributions
ves-0.601
Her-0.598
 vows-0.597
 brist-0.586
 blonde-0.536
Token amaz
Token ID40642
Feature activation-2.41e-01

Pos logit contributions
o+0.028
 alone+0.028
 tank+0.026
 forth+0.025
 wreck+0.025
Neg logit contributions
ves-0.024
Her-0.023
 vows-0.022
 brist-0.022
 blonde-0.019
Token house
Token ID2156
Feature activation+2.00e-02

Pos logit contributions
ves+0.100
 vows+0.099
Her+0.098
 brist+0.095
growth+0.091
Neg logit contributions
o-0.073
 alone-0.072
 forth-0.064
my-0.063
 tank-0.062
Token together
Token ID1978
Feature activation+1.02e-01

Pos logit contributions
o+0.036
 alone+0.033
 forth+0.030
 tank+0.030
my+0.029
Neg logit contributions
ves-0.040
Her-0.039
 vows-0.039
 brist-0.039
growth-0.035
Token.
Token ID13
Feature activation-4.56e-02

Pos logit contributions
 alone+0.149
o+0.146
 tank+0.121
 forth+0.119
my+0.116
Neg logit contributions
 brist-0.235
 vows-0.232
Her-0.231
ves-0.227
growth-0.214
Token He
Token ID679
Feature activation+2.22e-01

Pos logit contributions
Her+0.099
ves+0.095
 Her+0.091
 brist+0.090
 vows+0.090
Neg logit contributions
o-0.070
 forth-0.070
 alone-0.070
 afloat-0.068
 polar-0.063
Token asked
Token ID1965
Feature activation+4.79e-02

Pos logit contributions
o+0.371
 alone+0.330
 tank+0.296
my+0.295
 forth+0.292
Neg logit contributions
Her-0.477
 brist-0.468
ves-0.467
 vows-0.462
growth-0.442
Token her
Token ID607
Feature activation-2.94e-01

Pos logit contributions
o+0.070
 alone+0.067
my+0.058
 forth+0.056
 tank+0.055
Neg logit contributions
 vows-0.110
ves-0.110
 brist-0.110
Her-0.107
growth-0.101
Token if
Token ID611
Feature activation+7.54e-02

Pos logit contributions
 brist+0.721
ves+0.711
 vows+0.706
Her+0.698
growth+0.682
Neg logit contributions
o-0.416
 alone-0.372
my-0.327
 tank-0.320
 forth-0.295
Token she
Token ID673
Feature activation-3.31e-01

Pos logit contributions
o+0.148
 alone+0.140
 forth+0.125
my+0.123
 tank+0.121
Neg logit contributions
 brist-0.136
 vows-0.135
ves-0.134
Her-0.130
growth-0.123
Token wanted
Token ID2227
Feature activation-8.38e-03

Pos logit contributions
ves+0.725
Her+0.722
 vows+0.714
 brist+0.713
growth+0.660
Neg logit contributions
o-0.551
 alone-0.488
my-0.439
 tank-0.425
 forth-0.419
Token to
Token ID284
Feature activation-8.90e-02

Pos logit contributions
ves+0.022
 brist+0.022
 vows+0.021
Her+0.021
owers+0.021
Neg logit contributions
 alone-0.010
o-0.009
 his-0.008
my-0.008
 tank-0.008
Token play
Token ID711
Feature activation+1.05e-01

Pos logit contributions
ves+0.226
 brist+0.218
 vows+0.213
Her+0.202
owers+0.197
Neg logit contributions
 alone-0.113
o-0.112
my-0.098
 wreck-0.097
 forth-0.093
Token very
Token ID845
Feature activation+5.10e-02

Pos logit contributions
Her+0.159
ves+0.153
 vows+0.152
 brist+0.150
 blonde+0.140
Neg logit contributions
o-0.093
 forth-0.079
 alone-0.077
 tank-0.075
 polar-0.071
Token frustrated
Token ID14718
Feature activation+1.06e-01

Pos logit contributions
o+0.073
 forth+0.063
 tank+0.059
my+0.059
 alone+0.058
Neg logit contributions
Her-0.118
 vows-0.111
ves-0.110
 brist-0.108
 Her-0.103
Token.
Token ID13
Feature activation-6.28e-02

Pos logit contributions
 alone+0.156
o+0.152
my+0.125
 forth+0.124
 tank+0.117
Neg logit contributions
 vows-0.260
ves-0.249
Her-0.246
 brist-0.239
growth-0.239
Token Even
Token ID3412
Feature activation-2.43e-01

Pos logit contributions
ves+0.116
 vows+0.103
 brist+0.093
growth+0.093
Her+0.092
Neg logit contributions
o-0.133
 alone-0.130
my-0.119
 tank-0.111
|-0.106
Token though
Token ID996
Feature activation+1.30e-01

Pos logit contributions
Her+0.516
 brist+0.506
ves+0.503
 vows+0.496
 blonde+0.471
Neg logit contributions
o-0.398
 alone-0.342
 tank-0.323
 afloat-0.309
 forth-0.308
Token she
Token ID673
Feature activation-3.47e-01

Pos logit contributions
 alone+0.246
o+0.221
 forth+0.210
my+0.200
 Tim+0.195
Neg logit contributions
 vows-0.248
 brist-0.244
ves-0.234
Her-0.232
growth-0.226
Token had
Token ID550
Feature activation+3.05e-02

Pos logit contributions
ves+0.630
 vows+0.625
Her+0.619
 brist+0.614
 blonde+0.556
Neg logit contributions
o-0.656
 alone-0.619
 forth-0.571
 tank-0.563
 afloat-0.560
Token had
Token ID550
Feature activation+3.03e-02

Pos logit contributions
 alone+0.047
o+0.045
my+0.037
 forth+0.035
 afloat+0.035
Neg logit contributions
ves-0.069
Her-0.069
 vows-0.068
 brist-0.066
owers-0.063
Token a
Token ID257
Feature activation-1.67e-01

Pos logit contributions
 alone+0.046
o+0.044
my+0.036
 wreck+0.034
 tank+0.034
Neg logit contributions
Her-0.068
ves-0.068
 vows-0.066
 brist-0.066
owers-0.064
Token lovely
Token ID14081
Feature activation-1.17e-01

Pos logit contributions
Her+0.340
ves+0.340
 vows+0.330
 brist+0.324
growth+0.309
Neg logit contributions
o-0.288
 alone-0.274
 tank-0.253
 wreck-0.242
 afloat-0.241
Token bath
Token ID7837
Feature activation-3.29e-02

Pos logit contributions
Her+0.269
ves+0.264
 vows+0.255
growth+0.247
 brist+0.247
Neg logit contributions
o-0.175
 alone-0.168
 tank-0.159
 polar-0.150
 wreck-0.145