TOP ACTIVATIONS
MAX = 17.222

by one 1 , 2 ,
perfect bag now I 'm very
it forever things are only available
those in need â even <|endoftext|> One day
When Daisy put the magn ifying glass down , the cater
twenty - eight , twenty - nine , thirty , thirty
loud noise . He sc run ched his eyes tightly and
rare silence that added to the
he got even mad der ! He turned to Bob and
nine , thirty , thirty - one , thirty - two
slowly got back up again . He brushed off his clothes
won 't do it again ." Her mom hugged
softer than the last one . He offered to share his
only joy and content ment . <|endoftext|> The sun was very
always rely on each other ". Tina hugged her back and
a way to get down . He eventually found one and
far away it is distant .
worrying won 't solve anything . It 's best to stay
more spark ly than before . The gray bear smiled ,
let it become old again ! <|endoftext|> Once upon a time

MIN ACTIVATIONS
MIN = -13.712

saw a man selling colorful fireworks . She asked her mom
found a big roll of tape . He was very happy
saw a big bottle of shampoo on the shelf . It
wild - it was a shrink y . She didn 't
's dad took out a microscope . He looked at Katy
, Lily found a magic potion . She drank it and
do not like to eat salad . Salad is green and
day , Max started smoking cigarettes . Lily didn 't know
all of the man 's cakes . The man was very
Fred spotted a jar of glue . He thought it looked
a booth giving out free balloons to kids who played the
and stole the pocket of cookies ! It jumped away with
found a sp ool of thread on the floor . It
that it was full of ink . She was so excited
my accidentally spilled some hot soup on his hand . It
liked to look at the stars at night . He would
it was an old hamb urger wrapper . The car zoom
a big tree with many nuts . They want to eat
to take the knight 's sword . But the knight was
couldn 't find any new planets around her . But then

INTERVAL 9.488 - 17.222
CONTAINS 0.924%

help me pay for it ." Tim was very happy and
bring trouble , he refused . John looked around
belt for when I chew . I have bad teeth ,
to set . When it was time to
a bush . When Sally looked inside the

INTERVAL 1.755 - 9.488
CONTAINS 33.092%

When she opened it , the jelly came out in perfect
threw them on the floor . He took out his toys
set off . When they arrived at the
it home . Anna 's mummy saw what Anna
without permission . <|endoftext|> Once upon a time there was a

INTERVAL -5.978 - 1.755
CONTAINS 58.169%

. " Mom , why are we not moving
let 's go and show everyone my new skirt !" So
were friends . <|endoftext|> Tim and Jen were twins who liked
<|endoftext|> Tom and Lily were playing in the park . They
Mama was so proud of them . She said , "

INTERVAL -13.712 - -5.978
CONTAINS 7.815%

. The bunny was very sad and scared again . The
" I 'm decor ating my door with this pretty
and loved to learn new things . One day , Lily
to see what could be hidden underneath it . He carefully
ither y gl ided across them until he reached the other
Token by
Token ID416
Feature activation+9.11e+00

Pos logit contributions
 Here+0.033
 Watch+0.030
 Majesty+0.029
 First+0.029
 disl+0.029
Neg logit contributions
ier-0.045
 again-0.044
 anymore-0.043
ge-0.041
 than-0.041
Token one
Token ID530
Feature activation+5.45e+00

Pos logit contributions
 Here+0.161
 First+0.154
 Many+0.144
 Watch+0.141
 Everyone+0.137
Neg logit contributions
ier-0.175
 than-0.147
 again-0.146
ge-0.144
 anymore-0.144
Token
Token ID6184
Feature activation+8.89e+00

Pos logit contributions
 Here+0.115
 Watch+0.107
 Everyone+0.105
 Many+0.105
 First+0.104
Neg logit contributions
ier-0.083
ge-0.069
 than-0.050
y-0.049
m-0.049
Token
Token ID95
Feature activation+9.28e+00

Pos logit contributions
 Here+0.114
 First+0.113
 Many+0.106
ossible+0.099
 Watch+0.097
Neg logit contributions
ier-0.196
 than-0.174
 anymore-0.171
 again-0.169
ge-0.166
Token
Token ID26391
Feature activation+1.02e+01

Pos logit contributions
 Here+0.107
 First+0.102
 Many+0.093
 Remy+0.085
 Fin+0.085
Neg logit contributions
ier-0.226
 than-0.200
 again-0.191
 anymore-0.191
ge-0.185
Token
Token ID447
Feature activation+1.36e+01

Pos logit contributions
 First+0.153
 Here+0.149
 Many+0.131
 Watch+0.126
 Fin+0.122
Neg logit contributions
ier-0.193
 than-0.190
 again-0.185
 anymore-0.178
.-0.178
Token
Token ID250
Feature activation+1.06e+01

Pos logit contributions
 First+0.184
 Here+0.177
 Many+0.170
 Watch+0.156
 disl+0.151
Neg logit contributions
ier-0.286
 again-0.263
m-0.245
 anymore-0.244
 than-0.240
Token 1
Token ID352
Feature activation+1.66e+00

Pos logit contributions
 Here+0.153
 First+0.144
 Many+0.133
 Watch+0.130
 Everyone+0.127
Neg logit contributions
ier-0.238
 than-0.203
ge-0.202
 again-0.202
 anymore-0.199
Token,
Token ID11
Feature activation+6.42e+00

Pos logit contributions
 Here+0.033
 First+0.031
 Many+0.030
 Watch+0.029
 Everyone+0.029
Neg logit contributions
ier-0.028
ge-0.023
 again-0.022
 anymore-0.022
 than-0.022
Token 2
Token ID362
Feature activation+2.66e+00

Pos logit contributions
 Here+0.097
 First+0.090
 Many+0.084
 Watch+0.081
 Everyone+0.080
Neg logit contributions
ier-0.138
 again-0.118
 than-0.118
ge-0.116
 anymore-0.115
Token,
Token ID11
Feature activation+5.91e+00

Pos logit contributions
 Here+0.054
 First+0.052
 Many+0.049
 Watch+0.049
 Everyone+0.048
Neg logit contributions
ier-0.044
ge-0.035
 anymore-0.034
 again-0.034
 than-0.034
Token perfect
Token ID2818
Feature activation+5.50e+00

Pos logit contributions
 Here+0.165
 First+0.156
 Many+0.147
 Watch+0.146
 Everyone+0.142
Neg logit contributions
ier-0.174
ge-0.142
 again-0.137
 than-0.137
 anymore-0.136
Token bag
Token ID6131
Feature activation+7.57e-01

Pos logit contributions
 Here+0.104
 First+0.099
 Watch+0.095
 Majesty+0.093
 Everyone+0.091
Neg logit contributions
ier-0.096
ge-0.077
 anymore-0.069
 than-0.068
 again-0.066
Token
Token ID6184
Feature activation+6.99e+00

Pos logit contributions
 Here+0.017
 First+0.016
 Everyone+0.016
 This+0.016
 Watch+0.015
Neg logit contributions
ier-0.009
ge-0.008
 anymore-0.007
 than-0.007
 again-0.007
Token
Token ID95
Feature activation+8.35e+00

Pos logit contributions
 Here+0.096
 First+0.090
 Many+0.088
 disl+0.083
 Watch+0.081
Neg logit contributions
ier-0.155
 again-0.133
 than-0.132
 anymore-0.131
ge-0.129
Token
Token ID26391
Feature activation+9.46e+00

Pos logit contributions
 Here+0.105
 First+0.099
 Many+0.093
 Fin+0.090
 Remy+0.090
Neg logit contributions
ier-0.196
 than-0.169
 again-0.164
 anymore-0.161
ge-0.158
Token
Token ID447
Feature activation+1.36e+01

Pos logit contributions
 Here+0.141
 First+0.141
 Many+0.122
 Fin+0.116
 Watch+0.116
Neg logit contributions
ier-0.182
 than-0.176
 again-0.171
 on-0.164
 anymore-0.163
Token
Token ID250
Feature activation+1.04e+01

Pos logit contributions
 First+0.180
 Here+0.173
 Many+0.169
 disl+0.161
 Remy+0.150
Neg logit contributions
ier-0.280
 again-0.262
m-0.247
 on-0.241
 anymore-0.234
Token now
Token ID783
Feature activation+6.22e+00

Pos logit contributions
 Here+0.143
 First+0.134
 Many+0.124
 Watch+0.121
 Everyone+0.118
Neg logit contributions
ier-0.242
 than-0.206
ge-0.205
 again-0.205
 anymore-0.202
Token I
Token ID314
Feature activation+7.75e+00

Pos logit contributions
 Here+0.089
 First+0.083
 Many+0.079
 Watch+0.073
 Everyone+0.071
Neg logit contributions
ier-0.138
 again-0.122
 than-0.121
 anymore-0.118
ge-0.116
Token'm
Token ID1101
Feature activation+7.46e+00

Pos logit contributions
 Here+0.119
 First+0.114
 Many+0.106
 Watch+0.104
 Everyone+0.102
Neg logit contributions
ier-0.168
ge-0.139
 than-0.138
 anymore-0.136
 again-0.135
Token very
Token ID845
Feature activation+9.11e+00

Pos logit contributions
 Here+0.162
 First+0.155
 Many+0.148
 Watch+0.145
 Everyone+0.141
Neg logit contributions
ier-0.116
 again-0.091
 than-0.088
 anymore-0.088
ge-0.087
Token it
Token ID340
Feature activation+1.51e+00

Pos logit contributions
 Here+0.096
 First+0.090
 Many+0.085
 Watch+0.082
 Everyone+0.079
Neg logit contributions
ier-0.144
 again-0.123
 than-0.122
ge-0.121
 anymore-0.121
Token forever
Token ID8097
Feature activation+4.81e+00

Pos logit contributions
 Here+0.029
 First+0.028
 Watch+0.026
ossible+0.025
 The+0.025
Neg logit contributions
ier-0.024
ge-0.019
y-0.017
 than-0.017
 anymore-0.017
Token
Token ID6184
Feature activation+8.21e+00

Pos logit contributions
 Here+0.088
 First+0.084
 Many+0.078
 Watch+0.078
 The+0.077
Neg logit contributions
ier-0.084
ge-0.066
 anymore-0.063
 than-0.063
y-0.062
Token
Token ID95
Feature activation+9.22e+00

Pos logit contributions
 Here+0.120
 First+0.112
 disl+0.104
 Many+0.104
 Watch+0.100
Neg logit contributions
ier-0.177
 again-0.152
 anymore-0.152
ge-0.142
 than-0.142
Token
Token ID26391
Feature activation+9.78e+00

Pos logit contributions
 Here+0.125
 First+0.116
 Many+0.110
 Fin+0.105
 Remy+0.104
Neg logit contributions
ier-0.211
 than-0.179
 again-0.178
 anymore-0.175
ge-0.165
Token
Token ID447
Feature activation+1.34e+01

Pos logit contributions
 First+0.149
 Here+0.146
 Many+0.127
 Watch+0.120
 Fin+0.119
Neg logit contributions
ier-0.189
 than-0.185
 again-0.180
 anymore-0.174
 on-0.167
Token
Token ID250
Feature activation+1.02e+01

Pos logit contributions
 First+0.173
 Here+0.167
 Many+0.165
 disl+0.150
 Watch+0.146
Neg logit contributions
ier-0.290
 again-0.270
m-0.250
 anymore-0.243
 on-0.239
Token things
Token ID1243
Feature activation+2.31e+00

Pos logit contributions
 Here+0.138
 First+0.127
 Many+0.118
 Watch+0.115
 Everyone+0.110
Neg logit contributions
ier-0.247
 anymore-0.209
ge-0.207
 again-0.206
 than-0.205
Token are
Token ID389
Feature activation+6.05e+00

Pos logit contributions
 Here+0.037
 First+0.035
 Watch+0.033
 Everyone+0.032
 This+0.032
Neg logit contributions
ier-0.046
ge-0.039
 than-0.037
 again-0.037
 anymore-0.037
Token only
Token ID691
Feature activation+4.72e+00

Pos logit contributions
 Here+0.113
 First+0.108
 Watch+0.101
 Everyone+0.099
 This+0.098
Neg logit contributions
ier-0.105
ge-0.091
y-0.083
 again-0.082
 anymore-0.082
Token available
Token ID1695
Feature activation+1.30e+00

Pos logit contributions
 Here+0.091
 First+0.087
 This+0.081
 Watch+0.081
 Many+0.079
Neg logit contributions
ier-0.081
ge-0.067
 anymore-0.064
 again-0.062
 than-0.058
Token those
Token ID883
Feature activation+8.74e+00

Pos logit contributions
 Here+0.050
 First+0.049
 Majesty+0.048
 Watch+0.047
 disl+0.045
Neg logit contributions
ier-0.068
 again-0.066
 anymore-0.064
 than-0.062
 ever-0.057
Token in
Token ID287
Feature activation+8.67e+00

Pos logit contributions
 Here+0.168
 First+0.158
 Everyone+0.151
 Many+0.150
 Watch+0.148
Neg logit contributions
ier-0.152
ge-0.127
 again-0.120
 anymore-0.117
 than-0.115
Token need
Token ID761
Feature activation+5.19e+00

Pos logit contributions
 Here+0.139
 First+0.133
 Many+0.125
 Watch+0.122
 Everyone+0.122
Neg logit contributions
ier-0.183
ge-0.149
 again-0.144
 anymore-0.143
 than-0.143
Tokenâ
Token ID22940
Feature activation+1.03e+01

Pos logit contributions
 Here+0.095
 First+0.094
 Everyone+0.087
 Many+0.086
 Watch+0.084
Neg logit contributions
ier-0.094
ge-0.079
 than-0.074
y-0.072
 anymore-0.072
Token
Token ID26391
Feature activation+9.68e+00

Pos logit contributions
 Here+0.161
 First+0.150
 Many+0.142
 Watch+0.139
 Everyone+0.133
Neg logit contributions
ier-0.226
ge-0.187
 again-0.187
 than-0.186
 anymore-0.185
Token
Token ID447
Feature activation+1.28e+01

Pos logit contributions
 Here+0.173
 First+0.166
 Many+0.152
 Watch+0.152
 Higher+0.140
Neg logit contributions
ier-0.178
 than-0.159
 anymore-0.155
 again-0.155
ge-0.152
Token
Token ID251
Feature activation+1.09e+01

Pos logit contributions
 Here+0.149
 First+0.141
 Many+0.135
 Watch+0.127
 disl+0.116
Neg logit contributions
ier-0.314
 again-0.281
 anymore-0.268
ge-0.265
y-0.261
Tokeneven
Token ID10197
Feature activation+7.57e+00

Pos logit contributions
 Here+0.146
 First+0.136
 Many+0.128
 Watch+0.124
 Majesty+0.119
Neg logit contributions
ier-0.245
 again-0.224
 than-0.213
 anymore-0.210
 on-0.207
Token<|endoftext|>
Token ID50256
Feature activation+7.09e+00

Pos logit contributions
 Here+0.159
 First+0.153
 Many+0.148
 Watch+0.145
 Everyone+0.144
Neg logit contributions
ier-0.116
ge-0.091
 than-0.089
 anymore-0.089
 again-0.087
TokenOne
Token ID3198
Feature activation+5.53e+00

Pos logit contributions
 Here+0.112
 First+0.108
 Many+0.098
 Watch+0.097
 Majesty+0.093
Neg logit contributions
ier-0.146
 again-0.131
 anymore-0.126
 than-0.123
 on-0.121
Token day
Token ID1110
Feature activation+6.73e+00

Pos logit contributions
 Here+0.123
 First+0.118
 Many+0.115
 Everyone+0.112
 Watch+0.111
Neg logit contributions
ier-0.083
ge-0.063
 than-0.061
 again-0.059
 anymore-0.059
Token When
Token ID1649
Feature activation+7.09e+00

Pos logit contributions
 Majesty+0.117
lder+0.115
 disl+0.114
rac+0.112
 majesty+0.109
Neg logit contributions
 again-0.189
.-0.181
 than-0.178
 on-0.176
 anymore-0.172
Token Daisy
Token ID40355
Feature activation+3.79e+00

Pos logit contributions
 Here+0.134
 First+0.126
 Many+0.121
 Watch+0.118
 Everyone+0.115
Neg logit contributions
ier-0.127
 again-0.106
 than-0.103
 anymore-0.103
ge-0.102
Token put
Token ID1234
Feature activation+2.72e+00

Pos logit contributions
 Here+0.073
 First+0.069
 Many+0.066
 Watch+0.065
 Everyone+0.064
Neg logit contributions
ier-0.068
 than-0.055
ge-0.054
 anymore-0.053
 again-0.052
Token the
Token ID262
Feature activation+3.97e+00

Pos logit contributions
 Here+0.058
 First+0.056
 Watch+0.052
 Everyone+0.052
 Many+0.051
Neg logit contributions
ier-0.043
ge-0.035
 than-0.032
 anymore-0.031
 again-0.030
Token magn
Token ID7842
Feature activation+4.33e-01

Pos logit contributions
 Here+0.065
 First+0.059
 Watch+0.058
 Many+0.056
 Everyone+0.054
Neg logit contributions
ier-0.081
ge-0.070
 anymore-0.066
 than-0.066
 again-0.064
Tokenifying
Token ID4035
Feature activation+1.27e+01

Pos logit contributions
 Here+0.008
 First+0.007
 This+0.007
 Watch+0.007
 Everyone+0.007
Neg logit contributions
ier-0.008
 than-0.007
ge-0.007
 anymore-0.007
 again-0.006
Token glass
Token ID5405
Feature activation-2.23e-02

Pos logit contributions
 Here+0.243
 First+0.229
 Many+0.219
 Watch+0.217
 Majesty+0.211
Neg logit contributions
ier-0.208
 again-0.191
 anymore-0.181
 than-0.175
y-0.172
Token down
Token ID866
Feature activation+3.79e+00

Pos logit contributions
ier+0.000
ge+0.000
 than+0.000
 anymore+0.000
 sooner+0.000
Neg logit contributions
 First-0.000
 Here-0.000
 This-0.000
 Everyone-0.000
 Watch-0.000
Token,
Token ID11
Feature activation+7.36e+00

Pos logit contributions
 Here+0.071
 First+0.070
 Everyone+0.064
 The+0.064
 Watch+0.063
Neg logit contributions
ier-0.067
ge-0.058
 than-0.052
 anymore-0.051
 again-0.049
Token the
Token ID262
Feature activation+6.26e+00

Pos logit contributions
 Here+0.159
 First+0.148
 Many+0.143
 Watch+0.141
 Everyone+0.134
Neg logit contributions
ier-0.111
 again-0.095
 anymore-0.091
 than-0.089
 on-0.085
Token cater
Token ID20825
Feature activation+4.42e+00

Pos logit contributions
 Here+0.106
 First+0.097
 Watch+0.095
 Many+0.093
 Everyone+0.093
Neg logit contributions
ier-0.126
ge-0.108
 anymore-0.100
 than-0.100
 again-0.098
Token twenty
Token ID8208
Feature activation+5.08e+00

Pos logit contributions
 Here+0.154
 First+0.146
 Watch+0.137
 Many+0.131
 Dare+0.129
Neg logit contributions
ier-0.143
 again-0.128
 than-0.127
 anymore-0.121
 on-0.116
Token-
Token ID12
Feature activation+1.27e+01

Pos logit contributions
 Here+0.090
 Many+0.088
 Everyone+0.085
 First+0.084
 Watch+0.080
Neg logit contributions
ier-0.089
ge-0.077
 anymore-0.072
 again-0.072
 sooner-0.069
Tokeneight
Token ID26022
Feature activation+3.62e+00

Pos logit contributions
 Here+0.234
 First+0.223
 Many+0.210
 Watch+0.207
 Everyone+0.203
Neg logit contributions
ier-0.237
ge-0.192
 than-0.192
 again-0.191
 anymore-0.189
Token,
Token ID11
Feature activation+8.81e+00

Pos logit contributions
 Here+0.071
 First+0.069
 Many+0.065
 Everyone+0.064
 The+0.064
Neg logit contributions
ier-0.062
ge-0.048
 anymore-0.045
 again-0.045
 than-0.044
Token twenty
Token ID8208
Feature activation+5.73e+00

Pos logit contributions
 Here+0.164
 First+0.153
 Watch+0.147
 Many+0.138
 disl+0.135
Neg logit contributions
ier-0.148
 again-0.132
 than-0.127
 anymore-0.121
ge-0.120
Token-
Token ID12
Feature activation+1.27e+01

Pos logit contributions
 Here+0.121
 Many+0.120
 First+0.117
 Everyone+0.115
 Watch+0.111
Neg logit contributions
ier-0.081
ge-0.065
 anymore-0.063
 again-0.062
 sooner-0.057
Tokennine
Token ID30888
Feature activation+1.32e+00

Pos logit contributions
 Here+0.213
 First+0.202
 Many+0.188
 Watch+0.187
 Everyone+0.181
Neg logit contributions
ier-0.256
ge-0.212
 than-0.212
 again-0.211
 anymore-0.207
Token,
Token ID11
Feature activation+8.28e+00

Pos logit contributions
 Here+0.025
 First+0.024
 This+0.023
 Many+0.022
 The+0.022
Neg logit contributions
ier-0.022
 anymore-0.017
ge-0.017
 again-0.017
 than-0.016
Token thirty
Token ID12277
Feature activation+5.30e+00

Pos logit contributions
 Here+0.160
 First+0.147
 Watch+0.145
 Many+0.135
 disl+0.134
Neg logit contributions
ier-0.135
 again-0.119
 than-0.114
 on-0.109
ge-0.108
Token,
Token ID11
Feature activation+7.97e+00

Pos logit contributions
 Here+0.127
 Many+0.124
 First+0.122
 Everyone+0.120
 Watch+0.116
Neg logit contributions
ier-0.059
 anymore-0.044
 again-0.043
ge-0.043
 anywhere-0.039
Token thirty
Token ID12277
Feature activation+5.05e+00

Pos logit contributions
 Here+0.155
 First+0.144
 Watch+0.140
 Many+0.131
 disl+0.131
Neg logit contributions
ier-0.130
 again-0.113
 than-0.108
 on-0.105
ge-0.103
Token loud
Token ID7812
Feature activation+7.82e+00

Pos logit contributions
 Here+0.026
ossible+0.026
 disl+0.025
 First+0.024
 Deal+0.024
Neg logit contributions
ier-0.052
 again-0.050
 anymore-0.048
 than-0.047
 on-0.045
Token noise
Token ID7838
Feature activation+4.02e+00

Pos logit contributions
 Here+0.165
 First+0.158
 Many+0.152
 Watch+0.150
 Everyone+0.148
Neg logit contributions
ier-0.123
ge-0.096
 than-0.094
 again-0.093
 anymore-0.092
Token.
Token ID13
Feature activation+1.05e+01

Pos logit contributions
 The+0.072
 Everyone+0.072
 This+0.069
 It+0.068
 Watch+0.068
Neg logit contributions
ier-0.050
ge-0.049
 sooner-0.037
ris-0.035
iest-0.035
Token He
Token ID679
Feature activation+5.68e+00

Pos logit contributions
 Here+0.117
 Majesty+0.117
 First+0.116
rac+0.111
lder+0.109
Neg logit contributions
 again-0.209
 anymore-0.198
.-0.196
 than-0.194
ier-0.192
Token sc
Token ID629
Feature activation+7.35e+00

Pos logit contributions
 Here+0.107
 First+0.102
 Many+0.097
 Watch+0.095
 Everyone+0.093
Neg logit contributions
ier-0.102
 again-0.084
 than-0.083
ge-0.083
 anymore-0.082
Tokenrun
Token ID5143
Feature activation+1.25e+01

Pos logit contributions
 Here+0.124
 First+0.116
 Many+0.111
 Watch+0.107
 This+0.105
Neg logit contributions
ier-0.148
ge-0.122
 again-0.120
 than-0.118
 anymore-0.117
Tokenched
Token ID1740
Feature activation+4.24e+00

Pos logit contributions
 Here+0.254
 First+0.235
 Watch+0.228
 Many+0.226
 Majesty+0.221
Neg logit contributions
ier-0.216
ge-0.174
 again-0.174
 than-0.170
y-0.167
Token his
Token ID465
Feature activation+4.89e+00

Pos logit contributions
 Here+0.073
 First+0.069
 Many+0.065
 Watch+0.064
 Everyone+0.062
Neg logit contributions
ier-0.084
 again-0.070
 than-0.070
ge-0.069
 anymore-0.069
Token eyes
Token ID2951
Feature activation-4.33e-01

Pos logit contributions
 Here+0.079
 First+0.074
 Watch+0.070
 Many+0.069
 Everyone+0.067
Neg logit contributions
ier-0.103
ge-0.085
 anymore-0.083
 than-0.083
 again-0.083
Token tightly
Token ID17707
Feature activation+5.57e-01

Pos logit contributions
ier+0.006
ge+0.005
 than+0.005
 anymore+0.004
ies+0.004
Neg logit contributions
 The-0.008
 First-0.008
 This-0.008
 It-0.008
 Every-0.008
Token and
Token ID290
Feature activation+5.15e+00

Pos logit contributions
 The+0.011
 First+0.011
 This+0.011
 Here+0.010
 It+0.010
Neg logit contributions
ier-0.008
ge-0.006
iness-0.005
iest-0.005
m-0.005
Token rare
Token ID4071
Feature activation+2.59e+00

Pos logit contributions
 Here+0.106
 Watch+0.098
 First+0.098
 Many+0.097
 Everyone+0.094
Neg logit contributions
ier-0.111
ge-0.093
 anymore-0.087
 than-0.087
 again-0.086
Token silence
Token ID9550
Feature activation-7.33e-01

Pos logit contributions
 Here+0.047
 Watch+0.043
 First+0.043
 Everyone+0.043
 Many+0.042
Neg logit contributions
ier-0.048
ge-0.041
 anymore-0.036
 than-0.036
 again-0.036
Token
Token ID6184
Feature activation+6.52e+00

Pos logit contributions
ier+0.012
ge+0.010
 anymore+0.009
 again+0.009
 than+0.009
Neg logit contributions
 Here-0.014
 First-0.013
 Everyone-0.013
 Watch-0.013
 This-0.013
Token
Token ID95
Feature activation+9.08e+00

Pos logit contributions
 Here+0.094
 First+0.092
 Many+0.082
ossible+0.077
 Watch+0.076
Neg logit contributions
ier-0.141
 anymore-0.121
 again-0.121
 than-0.119
ge-0.115
Token
Token ID26391
Feature activation+8.76e+00

Pos logit contributions
 Here+0.111
 First+0.109
 Many+0.094
 Remy+0.090
 Fin+0.090
Neg logit contributions
ier-0.211
 than-0.184
 anymore-0.178
 again-0.178
ge-0.169
Token
Token ID447
Feature activation+1.21e+01

Pos logit contributions
 Here+0.141
 First+0.137
 Many+0.118
 Watch+0.114
 Deal+0.112
Neg logit contributions
ier-0.164
 than-0.159
 again-0.149
 anymore-0.147
y-0.145
Token
Token ID250
Feature activation+9.81e+00

Pos logit contributions
 Here+0.166
 First+0.164
 Many+0.150
 disl+0.140
 Watch+0.139
Neg logit contributions
ier-0.252
 again-0.233
 anymore-0.217
m-0.214
 on-0.209
Token that
Token ID326
Feature activation+5.07e+00

Pos logit contributions
 Here+0.136
 First+0.127
 Many+0.119
 Watch+0.116
 Everyone+0.112
Neg logit contributions
ier-0.228
 than-0.192
ge-0.192
 again-0.191
 anymore-0.191
Token added
Token ID2087
Feature activation+1.04e+00

Pos logit contributions
 Here+0.085
 First+0.081
 Many+0.076
 Watch+0.074
 Everyone+0.073
Neg logit contributions
ier-0.102
ge-0.085
 than-0.084
 again-0.084
 anymore-0.083
Token to
Token ID284
Feature activation+5.76e+00

Pos logit contributions
 Here+0.018
 First+0.017
 Watch+0.016
 Many+0.016
 Everyone+0.016
Neg logit contributions
ier-0.020
ge-0.017
 anymore-0.016
 again-0.016
 than-0.016
Token the
Token ID262
Feature activation+5.36e+00

Pos logit contributions
 Here+0.096
 First+0.090
 Many+0.082
 Watch+0.080
 Everyone+0.077
Neg logit contributions
ier-0.113
 again-0.100
 than-0.098
 anymore-0.096
ge-0.095
Token he
Token ID339
Feature activation+6.33e+00

Pos logit contributions
ier+0.053
ge+0.046
 than+0.046
 again+0.046
 anymore+0.046
Neg logit contributions
 Here-0.016
 First-0.015
 Many-0.013
 Watch-0.012
 Everyone-0.012
Token got
Token ID1392
Feature activation+4.73e+00

Pos logit contributions
 Here+0.127
 First+0.121
 Many+0.115
 Watch+0.113
 Everyone+0.111
Neg logit contributions
ier-0.107
 again-0.085
 than-0.085
ge-0.085
 anymore-0.083
Token even
Token ID772
Feature activation+6.74e+00

Pos logit contributions
 Here+0.087
 First+0.083
 The+0.080
 Everyone+0.080
 Many+0.080
Neg logit contributions
ier-0.078
 than-0.064
ge-0.064
 anymore-0.061
y-0.059
Token mad
Token ID8805
Feature activation+2.71e+00

Pos logit contributions
 Here+0.159
 First+0.156
 Many+0.151
 Watch+0.151
 The+0.144
Neg logit contributions
ier-0.079
 than-0.058
ge-0.056
 anymore-0.055
y-0.050
Tokender
Token ID1082
Feature activation+9.58e+00

Pos logit contributions
 Here+0.062
 Everyone+0.061
 Watch+0.059
 First+0.059
 This+0.059
Neg logit contributions
ier-0.028
ge-0.024
 sooner-0.018
bul-0.018
 anymore-0.017
Token!
Token ID0
Feature activation+1.20e+01

Pos logit contributions
 Here+0.245
 First+0.231
 Everyone+0.228
 disl+0.225
 Many+0.225
Neg logit contributions
ier-0.082
ge-0.054
 anymore-0.053
 again-0.052
 sooner-0.046
Token He
Token ID679
Feature activation+5.92e+00

Pos logit contributions
 First+0.138
 Here+0.137
 Majesty+0.128
 disl+0.127
rac+0.123
Neg logit contributions
 again-0.247
ier-0.240
 anymore-0.233
 than-0.222
.-0.219
Token turned
Token ID2900
Feature activation+2.18e+00

Pos logit contributions
 Here+0.110
 First+0.105
 Many+0.099
 Watch+0.098
 Everyone+0.097
Neg logit contributions
ier-0.109
ge-0.088
 than-0.087
 anymore-0.086
 again-0.084
Token to
Token ID284
Feature activation+7.30e+00

Pos logit contributions
 The+0.044
 Everyone+0.044
 First+0.043
 Here+0.042
 Many+0.042
Neg logit contributions
ier-0.031
ge-0.027
 than-0.024
 anymore-0.022
 sooner-0.022
Token Bob
Token ID5811
Feature activation+4.24e-01

Pos logit contributions
 Here+0.150
 First+0.138
 Watch+0.128
 Many+0.126
lder+0.122
Neg logit contributions
ier-0.113
 again-0.111
 anymore-0.103
ge-0.101
 than-0.097
Token and
Token ID290
Feature activation+6.34e+00

Pos logit contributions
 Here+0.010
 First+0.010
 The+0.009
 This+0.009
 Many+0.009
Neg logit contributions
ier-0.006
 than-0.004
 anymore-0.003
ge-0.003
iest-0.003
Tokennine
Token ID30888
Feature activation+1.32e+00

Pos logit contributions
 Here+0.213
 First+0.202
 Many+0.188
 Watch+0.187
 Everyone+0.181
Neg logit contributions
ier-0.256
ge-0.212
 than-0.212
 again-0.211
 anymore-0.207
Token,
Token ID11
Feature activation+8.28e+00

Pos logit contributions
 Here+0.025
 First+0.024
 This+0.023
 Many+0.022
 The+0.022
Neg logit contributions
ier-0.022
 anymore-0.017
ge-0.017
 again-0.017
 than-0.016
Token thirty
Token ID12277
Feature activation+5.30e+00

Pos logit contributions
 Here+0.160
 First+0.147
 Watch+0.145
 Many+0.135
 disl+0.134
Neg logit contributions
ier-0.135
 again-0.119
 than-0.114
 on-0.109
ge-0.108
Token,
Token ID11
Feature activation+7.97e+00

Pos logit contributions
 Here+0.127
 Many+0.124
 First+0.122
 Everyone+0.120
 Watch+0.116
Neg logit contributions
ier-0.059
 anymore-0.044
 again-0.043
ge-0.043
 anywhere-0.039
Token thirty
Token ID12277
Feature activation+5.05e+00

Pos logit contributions
 Here+0.155
 First+0.144
 Watch+0.140
 Many+0.131
 disl+0.131
Neg logit contributions
ier-0.130
 again-0.113
 than-0.108
 on-0.105
ge-0.103
Token-
Token ID12
Feature activation+1.20e+01

Pos logit contributions
 Here+0.120
 Many+0.117
 First+0.115
 Everyone+0.114
 Watch+0.110
Neg logit contributions
ier-0.056
 anymore-0.043
 again-0.042
ge-0.041
 anywhere-0.038
Tokenone
Token ID505
Feature activation+5.10e+00

Pos logit contributions
 Here+0.194
 First+0.183
 Watch+0.171
 Many+0.170
 Everyone+0.164
Neg logit contributions
ier-0.248
ge-0.207
 than-0.207
 again-0.205
 anymore-0.200
Token,
Token ID11
Feature activation+7.75e+00

Pos logit contributions
 Here+0.096
 First+0.092
 Many+0.091
 Everyone+0.088
 This+0.086
Neg logit contributions
ier-0.091
ge-0.074
 anymore-0.072
 again-0.071
 than-0.068
Token thirty
Token ID12277
Feature activation+4.83e+00

Pos logit contributions
 Here+0.150
 First+0.139
 Watch+0.135
 Many+0.127
 disl+0.126
Neg logit contributions
ier-0.130
 again-0.112
 than-0.108
 on-0.103
ge-0.102
Token-
Token ID12
Feature activation+1.15e+01

Pos logit contributions
 Here+0.114
 Many+0.112
 First+0.110
 Everyone+0.109
 Watch+0.105
Neg logit contributions
ier-0.053
 anymore-0.041
 again-0.039
ge-0.038
 anywhere-0.036
Tokentwo
Token ID11545
Feature activation+2.25e+00

Pos logit contributions
 Here+0.186
 First+0.176
 Many+0.164
 Watch+0.163
 Everyone+0.158
Neg logit contributions
ier-0.241
ge-0.200
 than-0.200
 again-0.199
 anymore-0.194
Token slowly
Token ID6364
Feature activation+8.18e+00

Pos logit contributions
 Here+0.029
 Majesty+0.028
 First+0.027
 majesty+0.026
 Deal+0.025
Neg logit contributions
ier-0.028
 than-0.027
 on-0.025
 again-0.025
y-0.025
Token got
Token ID1392
Feature activation+6.78e+00

Pos logit contributions
 Here+0.189
 First+0.186
 Watch+0.175
 Many+0.175
 Everyone+0.173
Neg logit contributions
ier-0.111
ge-0.079
 than-0.077
 anymore-0.075
 again-0.066
Token back
Token ID736
Feature activation+5.13e+00

Pos logit contributions
 Here+0.135
 First+0.131
 The+0.125
 Fin+0.123
 Many+0.123
Neg logit contributions
ier-0.099
 than-0.083
ge-0.081
 anymore-0.074
y-0.071
Token up
Token ID510
Feature activation+5.34e+00

Pos logit contributions
 Here+0.108
 The+0.104
 First+0.103
 This+0.100
 Everyone+0.100
Neg logit contributions
ier-0.076
ge-0.051
 anymore-0.050
iness-0.048
 than-0.047
Token again
Token ID757
Feature activation+4.81e+00

Pos logit contributions
 Here+0.111
 The+0.109
 First+0.109
 Everyone+0.104
 This+0.103
Neg logit contributions
ier-0.079
ge-0.055
iness-0.049
 anymore-0.048
 than-0.046
Token.
Token ID13
Feature activation+1.20e+01

Pos logit contributions
 Here+0.111
 First+0.108
 The+0.106
 Everyone+0.104
 This+0.103
Neg logit contributions
ier-0.060
ge-0.039
 anymore-0.038
iness-0.034
y-0.033
Token He
Token ID679
Feature activation+5.64e+00

Pos logit contributions
rac+0.130
 First+0.128
 Here+0.127
 Majesty+0.124
 disl+0.124
Neg logit contributions
 again-0.245
 anymore-0.232
ier-0.226
 than-0.223
.-0.214
Token brushed
Token ID31782
Feature activation+3.87e+00

Pos logit contributions
 Here+0.110
 First+0.106
 Many+0.100
 Watch+0.099
 Everyone+0.098
Neg logit contributions
ier-0.099
ge-0.078
 than-0.077
 anymore-0.077
 again-0.074
Token off
Token ID572
Feature activation+3.83e+00

Pos logit contributions
 Here+0.068
 First+0.065
 Many+0.061
 Everyone+0.060
 Watch+0.060
Neg logit contributions
ier-0.075
ge-0.061
 than-0.061
 anymore-0.060
 again-0.060
Token his
Token ID465
Feature activation+6.43e+00

Pos logit contributions
 Here+0.051
 First+0.050
 The+0.049
 Everyone+0.048
 This+0.047
Neg logit contributions
ier-0.089
ge-0.073
 than-0.071
 anymore-0.070
y-0.068
Token clothes
Token ID8242
Feature activation-1.74e+00

Pos logit contributions
 Here+0.100
 First+0.094
 Many+0.088
 Watch+0.088
 Everyone+0.084
Neg logit contributions
ier-0.140
ge-0.116
 than-0.114
 anymore-0.113
 again-0.111
Token won
Token ID1839
Feature activation+1.07e+01

Pos logit contributions
 disl+0.017
lder+0.016
 Here+0.016
 Majesty+0.015
 majesty+0.015
Neg logit contributions
 again-0.032
ier-0.031
 anymore-0.031
 than-0.029
 before-0.029
Token't
Token ID470
Feature activation+1.04e+01

Pos logit contributions
 Here+0.247
 First+0.238
 Many+0.227
 Watch+0.224
 Everyone+0.220
Neg logit contributions
ier-0.149
 again-0.112
 than-0.112
ge-0.111
 anymore-0.110
Token do
Token ID466
Feature activation+8.16e+00

Pos logit contributions
 Here+0.156
 First+0.147
 Many+0.140
 Watch+0.136
 Everyone+0.134
Neg logit contributions
ier-0.227
ge-0.190
 than-0.189
 again-0.187
 anymore-0.185
Token it
Token ID340
Feature activation+3.82e+00

Pos logit contributions
 Here+0.152
 First+0.145
 Many+0.137
 Watch+0.135
 Everyone+0.134
Neg logit contributions
ier-0.149
ge-0.121
 than-0.120
 again-0.118
 anymore-0.117
Token again
Token ID757
Feature activation+6.04e+00

Pos logit contributions
 Here+0.093
 First+0.091
 Everyone+0.091
 Watch+0.090
 Many+0.089
Neg logit contributions
ier-0.036
ge-0.026
 than-0.026
y-0.021
 beneath-0.021
Token."
Token ID526
Feature activation+1.20e+01

Pos logit contributions
 Here+0.143
 First+0.137
 Watch+0.133
 Many+0.133
 Everyone+0.132
Neg logit contributions
ier-0.073
ge-0.051
 than-0.045
 anymore-0.044
y-0.043
Token
Token ID198
Feature activation+1.16e+01

Pos logit contributions
 Here+0.157
 First+0.155
 Majesty+0.150
 Watch+0.146
 majesty+0.140
Neg logit contributions
 again-0.236
 anymore-0.216
.-0.216
ier-0.213
 than-0.208
Token
Token ID198
Feature activation+1.11e+01

Pos logit contributions
 Majesty+0.213
 First+0.211
 Here+0.205
cient+0.200
 majesty+0.195
Neg logit contributions
 again-0.169
.-0.165
ge-0.144
 than-0.143
y-0.142
TokenHer
Token ID9360
Feature activation+8.44e+00

Pos logit contributions
 Here+0.181
 First+0.178
 Majesty+0.168
cient+0.164
 majesty+0.158
Neg logit contributions
ge-0.172
ier-0.170
 than-0.169
 again-0.168
y-0.159
Token mom
Token ID1995
Feature activation+3.48e+00

Pos logit contributions
 Here+0.110
 First+0.102
 Many+0.094
 Watch+0.092
 Everyone+0.089
Neg logit contributions
ier-0.203
 again-0.174
 than-0.174
ge-0.173
 anymore-0.172
Token hugged
Token ID41130
Feature activation+6.13e+00

Pos logit contributions
 Here+0.061
 First+0.058
 Many+0.054
 Watch+0.053
 Everyone+0.053
Neg logit contributions
ier-0.068
 than-0.056
ge-0.056
 anymore-0.055
 again-0.053
Token softer
Token ID32359
Feature activation+2.34e+00

Pos logit contributions
 Here+0.176
 First+0.167
 Many+0.159
 Watch+0.157
 Everyone+0.155
Neg logit contributions
ier-0.135
ge-0.111
 anymore-0.105
 than-0.101
 again-0.097
Token than
Token ID621
Feature activation+6.54e+00

Pos logit contributions
 Here+0.051
 First+0.049
 Watch+0.048
 Majesty+0.047
 disl+0.047
Neg logit contributions
ier-0.027
ge-0.021
m-0.015
 emanating-0.015
 anymore-0.015
Token the
Token ID262
Feature activation+7.64e+00

Pos logit contributions
 Here+0.115
 First+0.106
 Many+0.100
 Watch+0.099
 Everyone+0.099
Neg logit contributions
ier-0.120
ge-0.099
 than-0.094
y-0.094
 anymore-0.092
Token last
Token ID938
Feature activation+4.70e+00

Pos logit contributions
 Here+0.134
 First+0.122
 Watch+0.119
 Many+0.118
 Everyone+0.116
Neg logit contributions
ier-0.143
ge-0.122
 than-0.109
 again-0.108
 anymore-0.107
Token one
Token ID530
Feature activation+3.92e+00

Pos logit contributions
 Here+0.085
 First+0.081
 Everyone+0.081
 Watch+0.080
 Many+0.079
Neg logit contributions
ier-0.081
ge-0.062
 anymore-0.055
 than-0.055
 again-0.053
Token.
Token ID13
Feature activation+1.19e+01

Pos logit contributions
 Here+0.082
 The+0.073
 First+0.072
 Everyone+0.072
 Watch+0.072
Neg logit contributions
ier-0.058
ge-0.050
 anymore-0.039
 than-0.036
y-0.035
Token He
Token ID679
Feature activation+6.02e+00

Pos logit contributions
 disl+0.134
rac+0.132
 Here+0.130
lder+0.128
 First+0.128
Neg logit contributions
 again-0.238
 anymore-0.224
ier-0.216
 than-0.214
.-0.212
Token offered
Token ID4438
Feature activation+4.16e+00

Pos logit contributions
 Here+0.119
 First+0.114
 Many+0.108
 Watch+0.107
 Everyone+0.105
Neg logit contributions
ier-0.104
ge-0.082
 than-0.082
 anymore-0.081
 again-0.081
Token to
Token ID284
Feature activation+6.93e+00

Pos logit contributions
 Here+0.072
 First+0.069
 Many+0.065
 Watch+0.063
 Everyone+0.063
Neg logit contributions
ier-0.082
ge-0.068
 than-0.067
 anymore-0.066
 again-0.066
Token share
Token ID2648
Feature activation+1.54e+00

Pos logit contributions
 Here+0.118
 First+0.111
 Many+0.105
 Watch+0.102
 Everyone+0.096
Neg logit contributions
ier-0.130
 again-0.118
 than-0.112
ge-0.112
 anymore-0.111
Token his
Token ID465
Feature activation+6.57e+00

Pos logit contributions
 Here+0.024
 First+0.023
 Many+0.021
 Everyone+0.021
 The+0.021
Neg logit contributions
ier-0.033
ge-0.027
y-0.025
 anymore-0.025
 than-0.025
Token only
Token ID691
Feature activation+8.67e+00

Pos logit contributions
ier+0.077
 than+0.067
ge+0.066
 again+0.066
 anymore+0.066
Neg logit contributions
 Here-0.058
 First-0.054
 Watch-0.050
 Many-0.050
 Higher-0.047
Token joy
Token ID8716
Feature activation+4.71e+00

Pos logit contributions
 Here+0.174
 First+0.165
 Many+0.158
 Watch+0.155
 Everyone+0.153
Neg logit contributions
ier-0.146
ge-0.114
 anymore-0.110
 again-0.109
 than-0.108
Token and
Token ID290
Feature activation+8.15e+00

Pos logit contributions
 Here+0.106
 Everyone+0.099
 This+0.098
 First+0.097
 The+0.094
Neg logit contributions
ier-0.049
ge-0.045
 sooner-0.034
 anymore-0.032
 beneath-0.031
Token content
Token ID2695
Feature activation+5.29e+00

Pos logit contributions
 Here+0.137
 First+0.130
 Many+0.122
 Watch+0.120
 Everyone+0.117
Neg logit contributions
ier-0.164
 than-0.136
 again-0.136
ge-0.136
 anymore-0.134
Tokenment
Token ID434
Feature activation+5.40e+00

Pos logit contributions
 Here+0.122
 Everyone+0.120
 First+0.115
 The+0.114
 This+0.112
Neg logit contributions
ier-0.059
ge-0.050
 anymore-0.039
 again-0.035
 sooner-0.035
Token.
Token ID13
Feature activation+1.19e+01

Pos logit contributions
 Here+0.120
 Everyone+0.117
 First+0.114
 The+0.113
 This+0.111
Neg logit contributions
ge-0.055
ier-0.054
 anymore-0.042
y-0.038
 sooner-0.037
Token<|endoftext|>
Token ID50256
Feature activation+6.47e+00

Pos logit contributions
 Here+0.134
 First+0.133
 Watch+0.133
 disl+0.133
rac+0.130
Neg logit contributions
 again-0.234
ier-0.225
 anymore-0.218
 than-0.217
.-0.209
TokenThe
Token ID464
Feature activation+6.98e+00

Pos logit contributions
 Here+0.095
 First+0.090
 Many+0.082
 Watch+0.082
 disl+0.076
Neg logit contributions
ier-0.142
 again-0.125
 anymore-0.122
 than-0.120
ge-0.118
Token sun
Token ID4252
Feature activation+8.19e-01

Pos logit contributions
 Here+0.134
 First+0.129
 Many+0.120
 Watch+0.118
 Everyone+0.114
Neg logit contributions
ier-0.121
 again-0.104
 than-0.100
 anymore-0.099
ge-0.097
Token was
Token ID373
Feature activation+4.69e+00

Pos logit contributions
 Here+0.019
 First+0.018
 Many+0.017
 Watch+0.017
 Everyone+0.016
Neg logit contributions
ier-0.012
 again-0.009
 than-0.009
 anymore-0.009
y-0.009
Token very
Token ID845
Feature activation+5.55e+00

Pos logit contributions
 Here+0.099
 First+0.095
 Many+0.090
 Watch+0.089
 Everyone+0.087
Neg logit contributions
ier-0.075
 than-0.059
 again-0.059
ge-0.058
 anymore-0.057
Token always
Token ID1464
Feature activation+7.84e+00

Pos logit contributions
 Here+0.162
 First+0.150
 Many+0.140
 Watch+0.138
 Everyone+0.132
Neg logit contributions
ier-0.180
 again-0.172
 anymore-0.167
ge-0.154
 than-0.153
Token rely
Token ID8814
Feature activation+4.87e+00

Pos logit contributions
 Here+0.123
 First+0.115
 Many+0.108
 Watch+0.104
 Everyone+0.103
Neg logit contributions
ier-0.167
 again-0.145
 than-0.143
ge-0.141
 anymore-0.141
Token on
Token ID319
Feature activation+7.49e+00

Pos logit contributions
 Here+0.129
 First+0.125
 Many+0.120
 Watch+0.119
 Everyone+0.118
Neg logit contributions
ier-0.048
ge-0.033
 anymore-0.031
 than-0.031
 again-0.030
Token each
Token ID1123
Feature activation+6.58e+00

Pos logit contributions
 Here+0.108
 First+0.102
 Many+0.096
 Watch+0.093
 Everyone+0.087
Neg logit contributions
ier-0.166
 again-0.145
 than-0.144
 anymore-0.142
ge-0.140
Token other
Token ID584
Feature activation+4.39e+00

Pos logit contributions
 Here+0.117
 First+0.114
 Many+0.112
 Everyone+0.110
 Watch+0.109
Neg logit contributions
ier-0.124
ge-0.107
 anymore-0.096
 than-0.096
 again-0.089
Token".
Token ID1911
Feature activation+1.18e+01

Pos logit contributions
 Here+0.098
 First+0.095
 Watch+0.090
 Many+0.090
 Everyone+0.089
Neg logit contributions
ier-0.063
ge-0.049
 anymore-0.043
 than-0.042
 again-0.040
Token Tina
Token ID35903
Feature activation+5.50e+00

Pos logit contributions
 Here+0.146
 Watch+0.140
 Majesty+0.137
 First+0.135
 disl+0.132
Neg logit contributions
 again-0.238
ier-0.230
 anymore-0.225
 than-0.217
ge-0.213
Token hugged
Token ID41130
Feature activation+5.28e+00

Pos logit contributions
 Here+0.114
 First+0.108
 Many+0.104
 Watch+0.102
 Everyone+0.097
Neg logit contributions
ier-0.089
 again-0.074
 than-0.071
 anymore-0.070
ge-0.069
Token her
Token ID607
Feature activation+6.97e+00

Pos logit contributions
 Here+0.090
 First+0.084
 Many+0.080
 Watch+0.078
 Everyone+0.075
Neg logit contributions
ier-0.106
 again-0.090
 than-0.089
ge-0.088
 anymore-0.088
Token back
Token ID736
Feature activation+4.64e+00

Pos logit contributions
 Here+0.094
 First+0.089
 Many+0.079
 Watch+0.079
 Everyone+0.078
Neg logit contributions
ier-0.167
ge-0.140
 than-0.139
 anymore-0.138
 again-0.136
Token and
Token ID290
Feature activation+6.38e+00

Pos logit contributions
 Here+0.111
 First+0.107
 Everyone+0.102
 The+0.102
 Many+0.099
Neg logit contributions
ier-0.062
ge-0.041
 anymore-0.038
 than-0.035
iness-0.034
Token a
Token ID257
Feature activation+5.61e+00

Pos logit contributions
 Here+0.070
 First+0.067
 Everyone+0.063
 Many+0.062
 Watch+0.061
Neg logit contributions
ier-0.087
ge-0.074
y-0.067
 than-0.067
 anymore-0.067
Token way
Token ID835
Feature activation+4.10e+00

Pos logit contributions
 Here+0.093
 First+0.086
 Watch+0.086
 Majesty+0.083
 Many+0.080
Neg logit contributions
ier-0.113
ge-0.090
iness-0.084
 than-0.083
 anymore-0.082
Token to
Token ID284
Feature activation+7.70e+00

Pos logit contributions
 Here+0.086
 First+0.084
 This+0.082
 Everyone+0.081
 The+0.079
Neg logit contributions
ier-0.060
ge-0.044
 than-0.040
 anymore-0.039
 again-0.038
Token get
Token ID651
Feature activation+5.15e+00

Pos logit contributions
 Here+0.131
 First+0.122
 Many+0.113
 Watch+0.111
 Everyone+0.105
Neg logit contributions
ier-0.154
 again-0.136
 anymore-0.132
ge-0.131
 than-0.130
Token down
Token ID866
Feature activation+2.79e+00

Pos logit contributions
 Here+0.100
 First+0.096
 Everyone+0.091
 Watch+0.089
 Many+0.089
Neg logit contributions
ier-0.086
ge-0.070
 than-0.068
 anymore-0.065
y-0.065
Token.
Token ID13
Feature activation+1.18e+01

Pos logit contributions
 First+0.059
 The+0.059
 Here+0.058
 Everyone+0.057
 This+0.056
Neg logit contributions
ier-0.036
ge-0.028
y-0.024
iness-0.022
le-0.022
Token He
Token ID679
Feature activation+5.16e+00

Pos logit contributions
 disl+0.137
rac+0.133
 Here+0.131
lder+0.130
 Majesty+0.130
Neg logit contributions
 again-0.237
 anymore-0.221
 than-0.214
ier-0.213
.-0.209
Token eventually
Token ID4191
Feature activation+4.87e+00

Pos logit contributions
 Here+0.106
 First+0.101
 Many+0.096
 Watch+0.094
 Everyone+0.093
Neg logit contributions
ier-0.084
 again-0.068
 than-0.067
ge-0.067
 anymore-0.066
Token found
Token ID1043
Feature activation+2.82e+00

Pos logit contributions
 Here+0.092
 First+0.089
 Many+0.084
 Watch+0.083
 Everyone+0.082
Neg logit contributions
ier-0.085
ge-0.069
 than-0.069
 anymore-0.069
 again-0.067
Token one
Token ID530
Feature activation+6.23e-01

Pos logit contributions
 Here+0.046
 First+0.044
 Many+0.040
 Everyone+0.040
 Watch+0.040
Neg logit contributions
ier-0.058
ge-0.049
 than-0.048
 anymore-0.047
 again-0.046
Token and
Token ID290
Feature activation+6.25e+00

Pos logit contributions
 Here+0.011
 First+0.010
 The+0.010
 Fred+0.010
 Watch+0.009
Neg logit contributions
ier-0.011
ge-0.009
iness-0.008
 anymore-0.007
m-0.007
Token far
Token ID1290
Feature activation+4.73e-01

Pos logit contributions
 Here+0.157
 First+0.148
 Many+0.141
 Watch+0.140
 Everyone+0.137
Neg logit contributions
ier-0.138
ge-0.110
 again-0.108
 anymore-0.107
 than-0.107
Token away
Token ID1497
Feature activation+1.99e+00

Pos logit contributions
 The+0.009
 First+0.009
 This+0.008
 Here+0.008
 Every+0.008
Neg logit contributions
ier-0.006
ge-0.005
iness-0.004
m-0.004
bul-0.004
Token
Token ID6184
Feature activation+6.80e+00

Pos logit contributions
 The+0.038
 This+0.037
 First+0.037
 Here+0.037
 Everyone+0.036
Neg logit contributions
ier-0.026
ge-0.019
bul-0.017
iness-0.017
m-0.017
Token
Token ID95
Feature activation+8.49e+00

Pos logit contributions
 Here+0.095
 First+0.091
ossible+0.082
 Many+0.081
 disl+0.078
Neg logit contributions
ier-0.147
 anymore-0.133
 again-0.127
 than-0.126
ge-0.122
Token
Token ID26391
Feature activation+7.88e+00

Pos logit contributions
 Here+0.107
 First+0.105
 Many+0.095
ossible+0.089
 Remy+0.088
Neg logit contributions
ier-0.197
 than-0.172
 anymore-0.166
 again-0.165
ge-0.155
Token
Token ID447
Feature activation+1.18e+01

Pos logit contributions
 First+0.126
 Here+0.125
 Many+0.109
 Watch+0.107
 Deal+0.102
Neg logit contributions
ier-0.149
 than-0.145
 again-0.136
 anymore-0.135
 on-0.130
Token
Token ID250
Feature activation+9.34e+00

Pos logit contributions
 First+0.167
 Here+0.163
 Many+0.149
 disl+0.145
 Watch+0.144
Neg logit contributions
ier-0.242
 again-0.223
m-0.209
 anymore-0.209
 on-0.201
Token it
Token ID340
Feature activation+3.44e+00

Pos logit contributions
 Here+0.127
 First+0.118
 Many+0.111
 Watch+0.108
 Everyone+0.104
Neg logit contributions
ier-0.221
 anymore-0.186
 again-0.186
ge-0.185
 than-0.185
Token is
Token ID318
Feature activation+5.39e+00

Pos logit contributions
 Here+0.056
 First+0.053
 Watch+0.049
 Many+0.049
 Everyone+0.048
Neg logit contributions
ier-0.071
ge-0.060
 than-0.059
 anymore-0.058
 again-0.058
Token distant
Token ID12899
Feature activation-4.33e-01

Pos logit contributions
 Here+0.105
 First+0.101
 Watch+0.095
 Many+0.094
 Everyone+0.092
Neg logit contributions
ier-0.093
ge-0.076
 anymore-0.070
 again-0.069
y-0.069
Token.
Token ID13
Feature activation+9.26e+00

Pos logit contributions
ier+0.007
ge+0.006
 anymore+0.005
 than+0.005
 again+0.005
Neg logit contributions
 Here-0.008
 First-0.008
 Watch-0.008
 Everyone-0.007
 Many-0.007
Token worrying
Token ID18916
Feature activation+7.45e+00

Pos logit contributions
ier+0.083
ge+0.059
 anymore+0.052
 again+0.047
 sooner+0.047
Neg logit contributions
 Here-0.134
 First-0.132
 Everyone-0.128
 This-0.127
 The-0.127
Token won
Token ID1839
Feature activation+8.90e+00

Pos logit contributions
 Here+0.164
 First+0.157
 Everyone+0.154
 Many+0.153
 Watch+0.151
Neg logit contributions
ier-0.104
ge-0.083
 than-0.075
 again-0.074
 anymore-0.071
Token't
Token ID470
Feature activation+9.35e+00

Pos logit contributions
 Here+0.174
 First+0.168
 Many+0.161
 Everyone+0.159
 Watch+0.158
Neg logit contributions
ier-0.149
ge-0.119
 than-0.118
 again-0.114
 anymore-0.114
Token solve
Token ID8494
Feature activation+4.12e+00

Pos logit contributions
 Here+0.126
 First+0.118
 Many+0.114
 Watch+0.112
 Everyone+0.111
Neg logit contributions
ier-0.212
ge-0.176
 than-0.175
 anymore-0.170
 again-0.170
Token anything
Token ID1997
Feature activation+4.82e+00

Pos logit contributions
 Here+0.067
 First+0.064
 Everyone+0.062
 Many+0.060
 The+0.060
Neg logit contributions
ier-0.077
ge-0.060
m-0.060
y-0.059
iness-0.056
Token.
Token ID13
Feature activation+1.18e+01

Pos logit contributions
 Here+0.103
 Everyone+0.101
 Many+0.098
 Watch+0.097
 This+0.097
Neg logit contributions
ier-0.060
ge-0.048
y-0.043
le-0.039
m-0.038
Token It
Token ID632
Feature activation+5.79e+00

Pos logit contributions
rac+0.136
 majesty+0.135
lder+0.134
 First+0.134
 Majesty+0.133
Neg logit contributions
 again-0.235
 anymore-0.218
.-0.208
ier-0.204
 than-0.202
Token's
Token ID338
Feature activation+7.29e+00

Pos logit contributions
 Here+0.111
 First+0.107
 Watch+0.101
 Everyone+0.100
 Many+0.100
Neg logit contributions
ier-0.101
ge-0.084
 than-0.081
 anymore-0.079
 again-0.075
Token best
Token ID1266
Feature activation+3.61e+00

Pos logit contributions
 Here+0.146
 First+0.140
 Many+0.131
 Watch+0.129
 Everyone+0.128
Neg logit contributions
ier-0.125
ge-0.101
 than-0.097
 again-0.096
 anymore-0.096
Token to
Token ID284
Feature activation+8.63e+00

Pos logit contributions
 Here+0.071
 First+0.068
 Watch+0.065
 Everyone+0.064
 Many+0.062
Neg logit contributions
ier-0.063
ge-0.054
y-0.048
 anymore-0.047
le-0.046
Token stay
Token ID2652
Feature activation+1.99e+00

Pos logit contributions
 Here+0.155
 First+0.141
 Many+0.137
 Watch+0.134
 Everyone+0.126
Neg logit contributions
ier-0.163
 again-0.142
 anymore-0.136
ge-0.135
 than-0.135
Token more
Token ID517
Feature activation+7.72e+00

Pos logit contributions
ier+0.018
 than+0.015
 again+0.015
ge+0.014
 anymore+0.014
Neg logit contributions
 Here-0.021
 First-0.020
 Many-0.019
 Watch-0.019
 Everyone-0.018
Token spark
Token ID9009
Feature activation+1.76e+00

Pos logit contributions
 Here+0.158
 disl+0.148
 First+0.148
 Many+0.148
 Watch+0.146
Neg logit contributions
ier-0.118
ge-0.092
 again-0.078
y-0.077
 anymore-0.077
Tokenly
Token ID306
Feature activation+6.13e+00

Pos logit contributions
 Everyone+0.030
 Here+0.030
 Watch+0.029
 The+0.029
 Now+0.027
Neg logit contributions
ge-0.023
ier-0.017
 sooner-0.016
m-0.015
 emanating-0.015
Token than
Token ID621
Feature activation+6.76e+00

Pos logit contributions
 Here+0.130
 Everyone+0.124
 Watch+0.123
 First+0.122
 The+0.120
Neg logit contributions
ier-0.077
ge-0.069
 anymore-0.051
 sooner-0.048
m-0.048
Token before
Token ID878
Feature activation+8.96e+00

Pos logit contributions
 Here+0.120
 First+0.109
 Everyone+0.107
 The+0.106
 Watch+0.103
Neg logit contributions
ier-0.115
ge-0.099
y-0.092
 than-0.086
 anymore-0.086
Token.
Token ID13
Feature activation+1.17e+01

Pos logit contributions
 Here+0.176
 First+0.169
 Many+0.160
 Everyone+0.160
 Watch+0.157
Neg logit contributions
ier-0.153
ge-0.121
 than-0.118
 anymore-0.114
 again-0.112
Token The
Token ID383
Feature activation+7.70e+00

Pos logit contributions
rac+0.133
 disl+0.127
 Here+0.126
lder+0.126
 Majesty+0.122
Neg logit contributions
 again-0.235
 anymore-0.222
.-0.213
ier-0.213
 than-0.211
Token gray
Token ID12768
Feature activation+4.95e+00

Pos logit contributions
 Here+0.132
 First+0.124
 Many+0.120
 Watch+0.118
 Everyone+0.117
Neg logit contributions
ier-0.151
ge-0.125
 than-0.123
 anymore-0.120
 again-0.117
Token bear
Token ID6842
Feature activation+2.03e+00

Pos logit contributions
 Here+0.085
 First+0.079
 Many+0.078
 Everyone+0.077
 Watch+0.075
Neg logit contributions
ier-0.098
ge-0.081
 than-0.077
 anymore-0.076
 again-0.074
Token smiled
Token ID13541
Feature activation+3.78e+00

Pos logit contributions
 Here+0.037
 First+0.035
 Many+0.034
 Watch+0.034
 Everyone+0.033
Neg logit contributions
ier-0.038
ge-0.030
 than-0.029
 anymore-0.029
 again-0.027
Token,
Token ID11
Feature activation+5.25e+00

Pos logit contributions
 The+0.082
 Here+0.078
 Everyone+0.077
 First+0.076
 It+0.075
Neg logit contributions
ier-0.050
ge-0.045
 anymore-0.033
iest-0.033
iness-0.032
Token let
Token ID1309
Feature activation+6.31e+00

Pos logit contributions
 Here+0.162
 Many+0.154
 First+0.150
 Watch+0.150
 The+0.150
Neg logit contributions
ier-0.103
ge-0.075
bul-0.065
 than-0.065
y-0.063
Token it
Token ID340
Feature activation+3.78e+00

Pos logit contributions
 Here+0.115
 First+0.110
 Many+0.104
 Watch+0.101
 Everyone+0.097
Neg logit contributions
ier-0.119
 again-0.100
 anymore-0.098
 than-0.096
ge-0.096
Token become
Token ID1716
Feature activation+6.21e+00

Pos logit contributions
 Here+0.077
 First+0.074
 Watch+0.072
 Everyone+0.071
 Many+0.071
Neg logit contributions
ier-0.059
ge-0.046
 than-0.045
 anymore-0.043
y-0.042
Token old
Token ID1468
Feature activation+1.47e+00

Pos logit contributions
 Here+0.110
 First+0.103
 The+0.101
 Fin+0.099
 Watch+0.098
Neg logit contributions
ier-0.105
ge-0.085
iness-0.081
y-0.080
 than-0.079
Token again
Token ID757
Feature activation+3.31e+00

Pos logit contributions
 Here+0.030
 First+0.029
 The+0.029
 Majesty+0.028
 Watch+0.028
Neg logit contributions
ier-0.018
ge-0.015
iness-0.012
m-0.011
 emanating-0.011
Token!
Token ID0
Feature activation+1.17e+01

Pos logit contributions
 Here+0.075
 The+0.071
 First+0.071
 Everyone+0.070
 This+0.069
Neg logit contributions
ier-0.040
ge-0.028
iness-0.025
 anymore-0.024
y-0.023
Token<|endoftext|>
Token ID50256
Feature activation+6.29e+00

Pos logit contributions
 Majesty+0.168
 First+0.163
 majesty+0.161
 disl+0.160
 Watch+0.158
Neg logit contributions
 again-0.209
 anymore-0.192
ier-0.184
 than-0.181
 ever-0.181
TokenOnce
Token ID7454
Feature activation+6.35e+00

Pos logit contributions
 Here+0.084
 First+0.079
 Many+0.072
 Watch+0.071
 disl+0.066
Neg logit contributions
ier-0.146
 again-0.130
 anymore-0.127
 than-0.125
ge-0.124
Token upon
Token ID2402
Feature activation+7.42e+00

Pos logit contributions
 Here+0.153
 First+0.148
 Watch+0.142
 Many+0.140
 Everyone+0.135
Neg logit contributions
ier-0.083
 again-0.065
 anymore-0.064
ge-0.063
 than-0.060
Token a
Token ID257
Feature activation+6.31e+00

Pos logit contributions
 Here+0.147
 First+0.141
 Watch+0.130
 Many+0.125
 Everyone+0.124
Neg logit contributions
ier-0.125
 again-0.107
 than-0.104
 anymore-0.102
ge-0.099
Token time
Token ID640
Feature activation+4.34e+00

Pos logit contributions
 Here+0.171
 First+0.164
 Watch+0.156
 Everyone+0.155
 Many+0.154
Neg logit contributions
ier-0.060
 than-0.046
 anymore-0.045
 again-0.044
y-0.040
Token saw
Token ID2497
Feature activation-4.80e+00

Pos logit contributions
 on+0.013
 inside+0.013
ier+0.013
 again+0.013
 in+0.012
Neg logit contributions
 Here-0.020
 Many-0.019
 Watch-0.019
 First-0.018
 Everyone-0.018
Token a
Token ID257
Feature activation-4.98e+00

Pos logit contributions
ier+0.066
 again+0.058
 on+0.058
 anymore+0.052
 more+0.051
Neg logit contributions
 Here-0.110
 Deal-0.103
 First-0.103
 Watch-0.101
 Majesty-0.100
Token man
Token ID582
Feature activation-1.09e+01

Pos logit contributions
ier+0.105
ge+0.087
 than+0.085
 anymore+0.084
 again+0.083
Neg logit contributions
 Here-0.080
 First-0.073
 Many-0.072
 Watch-0.072
 Everyone-0.069
Token selling
Token ID6301
Feature activation-8.65e+00

Pos logit contributions
ier+0.214
iness+0.160
iest+0.152
 than+0.151
 anymore+0.140
Neg logit contributions
 Here-0.194
 The-0.179
 This-0.178
 Many-0.175
ossible-0.168
Token colorful
Token ID20239
Feature activation-8.61e+00

Pos logit contributions
ier+0.163
ge+0.134
 than+0.131
 again+0.131
 anymore+0.130
Neg logit contributions
 Here-0.157
 First-0.149
 Many-0.142
 Watch-0.138
 Everyone-0.137
Token fireworks
Token ID26056
Feature activation-1.37e+01

Pos logit contributions
ier+0.178
ge+0.149
 anymore+0.141
 again+0.139
 than+0.136
Neg logit contributions
 Here-0.143
 First-0.136
 Many-0.135
 Everyone-0.128
 Watch-0.123
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
ier+0.225
ge+0.203
iness+0.190
lessness+0.170
 unsolved+0.161
Neg logit contributions
 This-0.239
 Here-0.225
 The-0.223
 Everyone-0.218
 First-0.213
Token She
Token ID1375
Feature activation-3.60e+00

Pos logit contributions
 Majesty+0.029
 majesty+0.026
heit+0.026
rac+0.026
 Here+0.025
Neg logit contributions
 again-0.029
.-0.027
 and-0.026
 anymore-0.025
y-0.025
Token asked
Token ID1965
Feature activation-4.46e+00

Pos logit contributions
ier+0.050
 again+0.045
y+0.044
 than+0.042
ge+0.041
Neg logit contributions
 Here-0.080
 First-0.076
 Watch-0.073
 Deal-0.071
 Many-0.070
Token her
Token ID607
Feature activation-3.19e+00

Pos logit contributions
ier+0.075
 again+0.069
 anymore+0.064
 than+0.060
ge+0.059
Neg logit contributions
 Here-0.090
 First-0.084
 Watch-0.082
 Many-0.077
 disl-0.076
Token mom
Token ID1995
Feature activation-6.80e+00

Pos logit contributions
ier+0.080
ge+0.069
 than+0.069
 anymore+0.068
 again+0.068
Neg logit contributions
 Here-0.039
 First-0.036
 Many-0.033
 Watch-0.031
 Everyone-0.031
Token found
Token ID1043
Feature activation-6.09e+00

Pos logit contributions
ier+0.076
 again+0.060
 than+0.060
ge+0.060
 anymore+0.059
Neg logit contributions
 Here-0.096
 First-0.091
 Many-0.087
 Watch-0.086
 Everyone-0.084
Token a
Token ID257
Feature activation-6.92e+00

Pos logit contributions
ier+0.085
 again+0.073
 on+0.071
 more+0.065
 inside+0.065
Neg logit contributions
 Here-0.140
 disl-0.129
 First-0.128
 Watch-0.128
 Majesty-0.127
Token big
Token ID1263
Feature activation-7.91e+00

Pos logit contributions
ier+0.156
ge+0.127
 than+0.124
 anymore+0.122
 again+0.121
Neg logit contributions
 Here-0.102
 First-0.092
 Watch-0.092
 Many-0.090
 This-0.086
Token roll
Token ID4836
Feature activation-1.14e+01

Pos logit contributions
ier+0.163
ge+0.134
 than+0.126
 anymore+0.123
 again+0.123
Neg logit contributions
 Here-0.129
 First-0.123
 Watch-0.117
 Many-0.117
 This-0.115
Token of
Token ID286
Feature activation-5.45e+00

Pos logit contributions
ier+0.200
ge+0.180
 than+0.163
 again+0.151
 knowing+0.151
Neg logit contributions
 First-0.200
 Here-0.194
 This-0.189
 Watch-0.189
 Everyone-0.188
Token tape
Token ID9154
Feature activation-1.34e+01

Pos logit contributions
ier+0.108
ge+0.089
 than+0.088
 again+0.088
 anymore+0.087
Neg logit contributions
 Here-0.096
 First-0.091
 Many-0.086
 Watch-0.085
 Everyone-0.083
Token.
Token ID13
Feature activation+5.42e-01

Pos logit contributions
ier+0.191
ge+0.146
iness+0.140
sm+0.137
lessness+0.132
Neg logit contributions
 First-0.243
 This-0.240
 Here-0.233
 The-0.230
 Ben-0.218
Token He
Token ID679
Feature activation-4.20e+00

Pos logit contributions
 Majesty+0.009
 majesty+0.008
 disl+0.008
cient+0.007
 Deal+0.007
Neg logit contributions
 again-0.009
.-0.009
 on-0.009
 and-0.009
 anymore-0.009
Token was
Token ID373
Feature activation-6.05e+00

Pos logit contributions
ier+0.061
 again+0.051
 than+0.050
ge+0.049
y+0.048
Neg logit contributions
 Here-0.092
 First-0.086
 Watch-0.083
 Many-0.083
 Everyone-0.081
Token very
Token ID845
Feature activation-3.02e+00

Pos logit contributions
ier+0.087
ge+0.065
 again+0.063
 anymore+0.063
 than+0.061
Neg logit contributions
 Here-0.140
 First-0.135
 Many-0.131
 Watch-0.128
 Everyone-0.125
Token happy
Token ID3772
Feature activation-8.50e+00

Pos logit contributions
ier+0.046
 than+0.039
ge+0.035
 on+0.034
 again+0.033
Neg logit contributions
 Here-0.064
 First-0.064
 Many-0.059
 Everyone-0.058
 Watch-0.058
Token saw
Token ID2497
Feature activation-5.09e+00

Pos logit contributions
ier+0.062
 than+0.049
 anymore+0.049
ge+0.049
 again+0.048
Neg logit contributions
 Here-0.065
 First-0.064
 Many-0.060
 Watch-0.059
 Everyone-0.058
Token a
Token ID257
Feature activation-6.40e+00

Pos logit contributions
ier+0.095
 again+0.079
 anymore+0.076
 than+0.076
ge+0.073
Neg logit contributions
 Here-0.096
 First-0.089
 Many-0.083
 Watch-0.083
 Everyone-0.080
Token big
Token ID1263
Feature activation-7.31e+00

Pos logit contributions
ier+0.148
ge+0.128
 anymore+0.122
 than+0.122
 again+0.117
Neg logit contributions
 Here-0.087
 Watch-0.082
 First-0.078
 Many-0.076
 Everyone-0.075
Token bottle
Token ID9294
Feature activation-1.13e+01

Pos logit contributions
ier+0.155
ge+0.132
 than+0.121
 anymore+0.120
 again+0.116
Neg logit contributions
 Here-0.114
 First-0.108
 Watch-0.107
 Many-0.101
 This-0.099
Token of
Token ID286
Feature activation-6.11e+00

Pos logit contributions
ier+0.156
ge+0.145
 anymore+0.119
 sooner+0.117
 than+0.112
Neg logit contributions
 Here-0.228
 This-0.226
 First-0.225
 Everyone-0.218
 The-0.218
Token shampoo
Token ID47259
Feature activation-1.34e+01

Pos logit contributions
ier+0.118
ge+0.097
 than+0.096
 again+0.096
 anymore+0.095
Neg logit contributions
 Here-0.109
 First-0.104
 Many-0.098
 Watch-0.096
 Everyone-0.094
Token on
Token ID319
Feature activation-5.10e+00

Pos logit contributions
ge+0.190
ier+0.190
 sooner+0.163
 anymore+0.151
 again+0.142
Neg logit contributions
 This-0.231
 First-0.229
 Here-0.222
 Ben-0.220
 Watch-0.217
Token the
Token ID262
Feature activation-3.74e+00

Pos logit contributions
ier+0.107
ge+0.089
 than+0.088
 again+0.088
 anymore+0.087
Neg logit contributions
 Here-0.082
 First-0.078
 Many-0.073
 Watch-0.071
 Everyone-0.070
Token shelf
Token ID18316
Feature activation-9.85e+00

Pos logit contributions
ier+0.080
ge+0.070
 than+0.066
 anymore+0.065
 again+0.065
Neg logit contributions
 Here-0.058
 First-0.056
 Watch-0.052
 Everyone-0.052
 Many-0.050
Token.
Token ID13
Feature activation+1.22e+00

Pos logit contributions
ier+0.134
ge+0.117
iness+0.091
le+0.089
 sooner+0.089
Neg logit contributions
 First-0.198
 The-0.197
 Here-0.196
 This-0.196
 Everyone-0.184
Token It
Token ID632
Feature activation-4.13e+00

Pos logit contributions
 Majesty+0.021
 disl+0.021
 majesty+0.019
cient+0.019
lder+0.019
Neg logit contributions
 again-0.022
 on-0.021
.-0.020
 and-0.020
y-0.020
Token wild
Token ID4295
Feature activation-9.74e+00

Pos logit contributions
ier+0.185
ge+0.165
iness+0.150
 sooner+0.144
 anymore+0.140
Neg logit contributions
 Here-0.094
 This-0.091
 Watch-0.090
 It-0.090
 The-0.086
Token -
Token ID532
Feature activation-5.41e+00

Pos logit contributions
ier+0.161
ge+0.146
 sooner+0.117
iness+0.106
iest+0.106
Neg logit contributions
 It-0.182
 The-0.179
 This-0.179
 Here-0.169
 Fin-0.167
Token it
Token ID340
Feature activation-5.91e+00

Pos logit contributions
ier+0.114
ge+0.095
 than+0.092
 anymore+0.092
 again+0.091
Neg logit contributions
 Here-0.087
 First-0.084
 Many-0.080
 Watch-0.078
 Everyone-0.076
Token was
Token ID373
Feature activation-6.22e+00

Pos logit contributions
ier+0.105
ge+0.085
 than+0.081
 anymore+0.080
 again+0.077
Neg logit contributions
 Here-0.111
 First-0.107
 Watch-0.103
 Many-0.102
 Everyone-0.101
Token a
Token ID257
Feature activation-6.31e+00

Pos logit contributions
ier+0.163
ge+0.148
iness+0.135
 anymore+0.134
le+0.133
Neg logit contributions
 First-0.060
 The-0.059
 Here-0.058
 Watch-0.053
 Many-0.053
Token shrink
Token ID22085
Feature activation-1.34e+01

Pos logit contributions
ier+0.145
ge+0.123
 anymore+0.116
 than+0.115
 again+0.113
Neg logit contributions
 Here-0.092
 Watch-0.085
 Many-0.081
 First-0.079
 Everyone-0.076
Tokeny
Token ID88
Feature activation-9.00e+00

Pos logit contributions
ge+0.241
ier+0.221
m+0.186
 sooner+0.177
ably+0.174
Neg logit contributions
 Watch-0.179
 It-0.170
 This-0.165
 I-0.162
 Ben-0.158
Token.
Token ID13
Feature activation+7.24e-01

Pos logit contributions
ier+0.200
ge+0.175
iness+0.144
 anymore+0.142
m+0.142
Neg logit contributions
 Here-0.129
 Watch-0.125
 This-0.120
 The-0.117
 Everyone-0.113
Token She
Token ID1375
Feature activation-4.15e+00

Pos logit contributions
 Majesty+0.010
 majesty+0.009
 disl+0.009
 Deal+0.009
heit+0.009
Neg logit contributions
 again-0.014
 on-0.014
.-0.014
 and-0.014
 inside-0.013
Token didn
Token ID1422
Feature activation-2.27e+00

Pos logit contributions
ier+0.068
 again+0.055
 than+0.055
ge+0.054
 anymore+0.053
Neg logit contributions
 Here-0.085
 First-0.082
 Many-0.077
 Watch-0.076
 Everyone-0.075
Token't
Token ID470
Feature activation-3.37e+00

Pos logit contributions
ier+0.056
 again+0.049
ge+0.048
 anymore+0.048
 than+0.048
Neg logit contributions
 Here-0.028
 First-0.025
 Many-0.023
 Watch-0.023
 Everyone-0.021
Token's
Token ID338
Feature activation-3.69e+00

Pos logit contributions
ier+0.086
ge+0.067
 anymore+0.066
 than+0.066
 again+0.066
Neg logit contributions
 Here-0.113
 First-0.108
 Many-0.103
 Watch-0.101
 Everyone-0.100
Token dad
Token ID9955
Feature activation-7.74e+00

Pos logit contributions
ier+0.094
 than+0.082
 again+0.082
ge+0.081
 anymore+0.081
Neg logit contributions
 Here-0.042
 First-0.039
 Many-0.035
 Watch-0.034
 Everyone-0.033
Token took
Token ID1718
Feature activation-5.85e+00

Pos logit contributions
ier+0.157
 anymore+0.130
ge+0.124
 than+0.124
 again+0.117
Neg logit contributions
 Here-0.127
 First-0.122
 Many-0.114
 The-0.114
 Everyone-0.112
Token out
Token ID503
Feature activation-5.33e+00

Pos logit contributions
ier+0.119
ge+0.098
 than+0.097
 anymore+0.096
 again+0.096
Neg logit contributions
 Here-0.099
 First-0.095
 Many-0.090
 Everyone-0.087
 Watch-0.087
Token a
Token ID257
Feature activation-5.68e+00

Pos logit contributions
ier+0.134
ge+0.113
 than+0.111
 anymore+0.109
 again+0.103
Neg logit contributions
 First-0.067
 Many-0.061
 Here-0.061
 The-0.060
 Everyone-0.058
Token microscope
Token ID36396
Feature activation-1.32e+01

Pos logit contributions
ier+0.131
 than+0.106
ge+0.102
 anymore+0.101
 again+0.098
Neg logit contributions
 Here-0.087
 First-0.082
 Many-0.078
 Watch-0.076
 This-0.075
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
ier+0.207
ge+0.181
iness+0.153
m+0.149
 anymore+0.138
Neg logit contributions
 First-0.232
 This-0.227
 The-0.215
 Here-0.209
 Every-0.204
Token He
Token ID679
Feature activation-4.99e+00

Pos logit contributions
 Here+0.011
 disl+0.010
 Remy+0.010
 Watch+0.010
 Majesty+0.010
Neg logit contributions
ier-0.024
 again-0.024
 than-0.023
 anymore-0.022
y-0.022
Token looked
Token ID3114
Feature activation-5.94e+00

Pos logit contributions
ier+0.093
 anymore+0.075
ge+0.074
 than+0.073
 again+0.071
Neg logit contributions
 Here-0.093
 First-0.090
 Many-0.084
 Watch-0.083
 Everyone-0.081
Token at
Token ID379
Feature activation-3.84e+00

Pos logit contributions
ier+0.108
ge+0.087
iness+0.077
y+0.071
 anymore+0.071
Neg logit contributions
 Here-0.116
 The-0.113
 First-0.113
 Many-0.107
 Watch-0.105
Token Katy
Token ID36715
Feature activation-9.55e+00

Pos logit contributions
ier+0.080
ge+0.066
 than+0.064
 again+0.063
 anymore+0.063
Neg logit contributions
 Here-0.063
 First-0.061
 Many-0.057
 Everyone-0.055
 Watch-0.054
Token,
Token ID11
Feature activation+3.36e-01

Pos logit contributions
ier+0.046
ge+0.038
 than+0.036
 again+0.034
 anymore+0.033
Neg logit contributions
 Here-0.051
 First-0.049
 Many-0.048
 Everyone-0.046
 This-0.046
Token Lily
Token ID20037
Feature activation-4.50e+00

Pos logit contributions
 Here+0.005
 First+0.005
 Many+0.004
 Watch+0.004
 Everyone+0.004
Neg logit contributions
ier-0.008
ge-0.007
 than-0.006
 anymore-0.006
 again-0.006
Token found
Token ID1043
Feature activation-5.39e+00

Pos logit contributions
ier+0.078
 again+0.063
 than+0.063
ge+0.062
 anymore+0.062
Neg logit contributions
 Here-0.089
 First-0.084
 Many-0.080
 Watch-0.079
 Everyone-0.078
Token a
Token ID257
Feature activation-6.20e+00

Pos logit contributions
ier+0.086
 again+0.073
 on+0.069
 anymore+0.066
 inside+0.064
Neg logit contributions
 Here-0.115
 First-0.105
 Watch-0.105
 disl-0.102
 Majesty-0.101
Token magic
Token ID5536
Feature activation-1.09e+01

Pos logit contributions
ier+0.140
ge+0.115
 than+0.110
 anymore+0.109
iness+0.106
Neg logit contributions
 Here-0.093
 Watch-0.085
 First-0.081
 Many-0.079
 This-0.075
Token potion
Token ID26572
Feature activation-1.32e+01

Pos logit contributions
ier+0.226
ge+0.217
m+0.184
iness+0.179
lling+0.178
Neg logit contributions
 Watch-0.151
 Here-0.147
 This-0.131
 It-0.131
 name-0.124
Token.
Token ID13
Feature activation+1.20e+00

Pos logit contributions
ge+0.218
ier+0.207
 sooner+0.168
 again+0.152
 anymore+0.150
Neg logit contributions
 This-0.225
 Here-0.214
 It-0.202
 The-0.201
 Watch-0.198
Token She
Token ID1375
Feature activation-3.93e+00

Pos logit contributions
 Majesty+0.017
 disl+0.016
 majesty+0.015
ossible+0.015
 Fin+0.015
Neg logit contributions
 again-0.023
 on-0.022
.-0.021
 anymore-0.021
ier-0.021
Token drank
Token ID24070
Feature activation-7.40e+00

Pos logit contributions
ier+0.065
 again+0.053
 than+0.052
ge+0.052
 anymore+0.050
Neg logit contributions
 Here-0.080
 First-0.076
 Many-0.073
 Watch-0.072
 Everyone-0.071
Token it
Token ID340
Feature activation-8.70e+00

Pos logit contributions
ier+0.176
ge+0.165
 than+0.142
iness+0.136
 anymore+0.136
Neg logit contributions
 Here-0.093
 First-0.091
 The-0.091
 Everyone-0.085
 It-0.085
Token and
Token ID290
Feature activation-4.39e+00

Pos logit contributions
ier+0.157
ge+0.149
ruck+0.118
iness+0.116
 outage+0.111
Neg logit contributions
 First-0.152
 The-0.147
 This-0.143
 Every-0.135
 Here-0.135
Token do
Token ID466
Feature activation-3.93e+00

Pos logit contributions
ier+0.049
 than+0.042
 anymore+0.042
 again+0.041
ge+0.040
Neg logit contributions
 Here-0.047
 First-0.045
 Many-0.041
 Watch-0.041
 Everyone-0.040
Token not
Token ID407
Feature activation-3.25e+00

Pos logit contributions
ier+0.096
ge+0.080
 than+0.079
 again+0.078
 anymore+0.077
Neg logit contributions
 Here-0.051
 First-0.048
 Many-0.045
 Watch-0.043
 Everyone-0.043
Token like
Token ID588
Feature activation-5.20e+00

Pos logit contributions
ier+0.069
ge+0.056
 beneath+0.055
 again+0.055
iest+0.053
Neg logit contributions
 Many-0.045
 Here-0.045
 First-0.043
 Everyone-0.043
 The-0.042
Token to
Token ID284
Feature activation-3.82e+00

Pos logit contributions
ier+0.086
ge+0.064
 than+0.061
 again+0.059
 anymore+0.058
Neg logit contributions
 Here-0.108
 First-0.104
 Many-0.103
 Watch-0.099
 Everyone-0.098
Token eat
Token ID4483
Feature activation-8.94e+00

Pos logit contributions
ier+0.090
ge+0.076
 than+0.076
 again+0.076
 anymore+0.075
Neg logit contributions
 Here-0.052
 First-0.049
 Many-0.045
 Watch-0.044
 Everyone-0.043
Token salad
Token ID20698
Feature activation-1.31e+01

Pos logit contributions
ier+0.185
ge+0.153
iness+0.137
 than+0.136
y+0.135
Neg logit contributions
 Here-0.136
 First-0.134
 Many-0.133
 Everyone-0.130
 The-0.129
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
ier+0.176
ge+0.174
bul+0.167
ruck+0.152
 visible+0.150
Neg logit contributions
 Ben-0.230
 First-0.217
 Remy-0.215
 Fin-0.212
 Leo-0.209
Token Salad
Token ID42706
Feature activation-8.75e+00

Pos logit contributions
 Majesty+0.016
 majesty+0.015
cient+0.014
lder+0.014
 Here+0.014
Neg logit contributions
 anymore-0.022
 again-0.021
.-0.019
 than-0.019
ier-0.019
Token is
Token ID318
Feature activation-5.16e+00

Pos logit contributions
ier+0.196
ge+0.174
 again+0.159
 anymore+0.159
 than+0.155
Neg logit contributions
 Here-0.117
 First-0.109
 Watch-0.101
 This-0.101
 The-0.098
Token green
Token ID4077
Feature activation-1.03e+01

Pos logit contributions
ier+0.095
ge+0.081
 again+0.075
 than+0.074
 anymore+0.074
Neg logit contributions
 Here-0.096
 First-0.090
 Many-0.085
 Watch-0.084
 Everyone-0.082
Token and
Token ID290
Feature activation-2.94e+00

Pos logit contributions
ier+0.152
ge+0.146
 visible+0.105
 sooner+0.098
 emanating+0.098
Neg logit contributions
 First-0.194
 Here-0.193
 The-0.190
 This-0.189
 Every-0.180
Token day
Token ID1110
Feature activation-3.39e+00

Pos logit contributions
ier+0.088
ge+0.076
 than+0.063
 anymore+0.063
 again+0.058
Neg logit contributions
 Here-0.078
 Many-0.076
 The-0.071
 First-0.071
ossible-0.070
Token,
Token ID11
Feature activation-1.54e-01

Pos logit contributions
ier+0.057
ge+0.047
 than+0.045
 anymore+0.041
 again+0.041
Neg logit contributions
 Here-0.068
 First-0.067
 Many-0.064
 Everyone-0.062
 Watch-0.062
Token Max
Token ID5436
Feature activation-5.77e+00

Pos logit contributions
ier+0.004
ge+0.004
 than+0.004
 anymore+0.004
 again+0.004
Neg logit contributions
 Here-0.002
 First-0.001
 Many-0.001
 Watch-0.001
 Everyone-0.001
Token started
Token ID2067
Feature activation-5.70e+00

Pos logit contributions
ier+0.103
ge+0.083
 than+0.083
 again+0.082
 anymore+0.081
Neg logit contributions
 Here-0.111
 First-0.106
 Many-0.100
 Watch-0.098
 Everyone-0.096
Token smoking
Token ID9216
Feature activation-1.06e+01

Pos logit contributions
ier+0.122
iest+0.096
iness+0.089
 than+0.086
ge+0.085
Neg logit contributions
 The-0.095
 Many-0.090
 First-0.089
 Mitt-0.089
 This-0.088
Token cigarettes
Token ID17626
Feature activation-1.31e+01

Pos logit contributions
ier+0.205
ge+0.194
iness+0.157
 than+0.150
 ever+0.148
Neg logit contributions
 The-0.167
 First-0.159
 It-0.152
 Everyone-0.151
 Many-0.148
Token.
Token ID13
Feature activation+7.62e-01

Pos logit contributions
ier+0.160
able+0.150
ge+0.146
iest+0.131
 unsolved+0.130
Neg logit contributions
 This-0.233
 First-0.226
 The-0.219
 Here-0.207
 It-0.207
Token Lily
Token ID20037
Feature activation-5.32e+00

Pos logit contributions
 Here+0.011
 First+0.010
ossible+0.010
rac+0.010
 Majesty+0.009
Neg logit contributions
 again-0.015
ier-0.015
 anymore-0.014
 on-0.013
 than-0.013
Token didn
Token ID1422
Feature activation-1.71e+00

Pos logit contributions
ier+0.097
ge+0.078
 than+0.077
 anymore+0.076
 again+0.074
Neg logit contributions
 Here-0.100
 First-0.096
 Many-0.091
 Watch-0.089
 Everyone-0.088
Token't
Token ID470
Feature activation-3.57e+00

Pos logit contributions
ier+0.040
 again+0.035
 anymore+0.035
ge+0.034
 than+0.033
Neg logit contributions
 Here-0.024
 First-0.021
 Majesty-0.020
 Watch-0.020
 Many-0.019
Token know
Token ID760
Feature activation-5.46e+00

Pos logit contributions
ier+0.081
 again+0.071
ge+0.071
 anymore+0.069
 beneath+0.068
Neg logit contributions
 Many-0.045
 Everyone-0.040
 Watch-0.040
 First-0.039
 Here-0.039
Token all
Token ID477
Feature activation-3.95e+00

Pos logit contributions
ier+0.162
ge+0.140
 than+0.132
 anymore+0.127
 again+0.126
Neg logit contributions
 Here-0.106
 First-0.102
 Everyone-0.098
 Many-0.097
 The-0.094
Token of
Token ID286
Feature activation-2.48e+00

Pos logit contributions
ier+0.060
ge+0.048
 again+0.046
 anymore+0.046
 than+0.046
Neg logit contributions
 Here-0.087
 First-0.082
 Many-0.079
 Everyone-0.078
 Watch-0.076
Token the
Token ID262
Feature activation-3.64e+00

Pos logit contributions
ier+0.045
 again+0.038
 than+0.037
 anymore+0.037
ge+0.037
Neg logit contributions
 Here-0.047
 First-0.044
 Watch-0.042
 Many-0.041
 Everyone-0.039
Token man
Token ID582
Feature activation-1.04e+01

Pos logit contributions
ier+0.073
ge+0.066
 again+0.061
 than+0.060
 anymore+0.059
Neg logit contributions
 Here-0.058
 Many-0.057
 First-0.054
 Everyone-0.052
 Watch-0.049
Token's
Token ID338
Feature activation-4.12e+00

Pos logit contributions
ier+0.230
iness+0.177
 than+0.176
 anymore+0.172
ge+0.171
Neg logit contributions
 Here-0.142
 This-0.142
 The-0.136
 Many-0.126
 Everyone-0.123
Token cakes
Token ID30849
Feature activation-1.31e+01

Pos logit contributions
ier+0.081
ge+0.068
 again+0.066
 anymore+0.065
 than+0.065
Neg logit contributions
 Here-0.073
 First-0.068
 Many-0.066
 Everyone-0.063
 Watch-0.062
Token.
Token ID13
Feature activation+1.59e+00

Pos logit contributions
ier+0.171
ge+0.138
iest+0.127
le+0.125
bul+0.122
Neg logit contributions
 This-0.253
 The-0.240
 Here-0.238
 First-0.236
 Jerry-0.234
Token The
Token ID383
Feature activation-1.66e+00

Pos logit contributions
 Majesty+0.021
 Deal+0.021
 majesty+0.020
 Here+0.019
 disl+0.018
Neg logit contributions
 again-0.030
.-0.030
 than-0.028
 anymore-0.028
 and-0.028
Token man
Token ID582
Feature activation-5.73e+00

Pos logit contributions
ier+0.031
ge+0.027
 than+0.025
 again+0.025
 anymore+0.025
Neg logit contributions
 Here-0.030
 First-0.028
 Many-0.028
 Everyone-0.027
 Watch-0.026
Token was
Token ID373
Feature activation-4.25e+00

Pos logit contributions
ier+0.104
ge+0.085
 than+0.084
 anymore+0.082
 again+0.077
Neg logit contributions
 Here-0.105
 First-0.100
 Many-0.099
 Everyone-0.096
 The-0.095
Token very
Token ID845
Feature activation-1.82e+00

Pos logit contributions
ier+0.057
ge+0.043
 than+0.040
 again+0.040
 anymore+0.039
Neg logit contributions
 Here-0.100
 First-0.096
 Many-0.095
 Watch-0.092
 Everyone-0.091
Token Fred
Token ID8559
Feature activation-4.39e+00

Pos logit contributions
ier+0.033
ge+0.025
 than+0.025
 again+0.025
 anymore+0.024
Neg logit contributions
 Here-0.054
 First-0.052
 Many-0.050
 Watch-0.049
 Everyone-0.049
Token spotted
Token ID13489
Feature activation-5.12e+00

Pos logit contributions
ier+0.083
ge+0.067
 than+0.067
 anymore+0.066
 again+0.066
Neg logit contributions
 Here-0.080
 First-0.076
 Many-0.072
 Watch-0.071
 Everyone-0.069
Token a
Token ID257
Feature activation-5.36e+00

Pos logit contributions
ier+0.078
 again+0.072
 anymore+0.065
 on+0.062
 than+0.061
Neg logit contributions
 Here-0.112
 First-0.103
 Watch-0.099
 Deal-0.098
 Many-0.097
Token jar
Token ID17379
Feature activation-1.10e+01

Pos logit contributions
ier+0.119
ge+0.098
 than+0.095
 anymore+0.094
 again+0.092
Neg logit contributions
 Here-0.080
 Watch-0.073
 First-0.073
 Many-0.071
 Everyone-0.067
Token of
Token ID286
Feature activation-5.41e+00

Pos logit contributions
ier+0.145
ge+0.125
 anymore+0.112
 than+0.105
 again+0.098
Neg logit contributions
 Here-0.225
 First-0.217
ossible-0.215
 This-0.215
 Watch-0.213
Token glue
Token ID22749
Feature activation-1.31e+01

Pos logit contributions
ier+0.108
ge+0.091
 anymore+0.087
 again+0.087
 than+0.087
Neg logit contributions
 Here-0.094
 First-0.089
 Many-0.084
 Watch-0.083
 Everyone-0.080
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
ier+0.170
ge+0.127
 sooner+0.122
 than+0.114
 anymore+0.113
Neg logit contributions
 Pip-0.232
 Fin-0.231
 Harry-0.223
 This-0.221
 Remy-0.221
Token He
Token ID679
Feature activation-3.41e+00

Pos logit contributions
 Deal+0.018
 disl+0.017
 Majesty+0.017
ossible+0.017
 majesty+0.016
Neg logit contributions
 again-0.019
 than-0.017
 and-0.017
ier-0.017
.-0.016
Token thought
Token ID1807
Feature activation-4.18e+00

Pos logit contributions
ier+0.052
 again+0.045
 than+0.044
y+0.043
ge+0.043
Neg logit contributions
 Here-0.072
 First-0.068
 Many-0.064
 Everyone-0.064
 Watch-0.063
Token it
Token ID340
Feature activation-4.25e+00

Pos logit contributions
ier+0.074
ge+0.060
 than+0.059
 anymore+0.057
 again+0.057
Neg logit contributions
 Here-0.081
 First-0.077
 Many-0.074
 Watch-0.072
 Everyone-0.070
Token looked
Token ID3114
Feature activation-4.74e+00

Pos logit contributions
ier+0.073
ge+0.059
 than+0.057
 anymore+0.055
 again+0.052
Neg logit contributions
 Here-0.084
 First-0.083
 This-0.076
 Watch-0.076
 Many-0.075
Token a
Token ID257
Feature activation-5.59e+00

Pos logit contributions
ier+0.087
ge+0.073
 than+0.072
 again+0.071
 anymore+0.070
Neg logit contributions
 Here-0.068
 First-0.065
 Many-0.061
 Everyone-0.059
 Watch-0.059
Token booth
Token ID18600
Feature activation-1.01e+01

Pos logit contributions
ier+0.127
ge+0.107
 than+0.102
 anymore+0.100
iness+0.100
Neg logit contributions
 Here-0.076
 Many-0.072
 Watch-0.072
 Everyone-0.068
 First-0.066
Token giving
Token ID3501
Feature activation-6.69e+00

Pos logit contributions
ier+0.185
ge+0.148
iness+0.142
le+0.138
iest+0.133
Neg logit contributions
 Here-0.184
 The-0.179
 This-0.176
 Everyone-0.169
 Many-0.169
Token out
Token ID503
Feature activation-5.04e+00

Pos logit contributions
ier+0.137
ge+0.119
 than+0.111
 anymore+0.107
iness+0.103
Neg logit contributions
 Here-0.110
 First-0.108
 Everyone-0.102
 Many-0.099
 The-0.098
Token free
Token ID1479
Feature activation-8.92e+00

Pos logit contributions
ier+0.114
ge+0.098
 than+0.093
 anymore+0.090
 again+0.090
Neg logit contributions
 Here-0.074
 First-0.070
 Many-0.070
 Everyone-0.068
 The-0.065
Token balloons
Token ID35485
Feature activation-1.31e+01

Pos logit contributions
ier+0.137
ge+0.109
iness+0.085
m+0.084
web+0.079
Neg logit contributions
 Everyone-0.183
 First-0.181
 Here-0.178
 The-0.177
 Many-0.174
Token to
Token ID284
Feature activation-4.36e+00

Pos logit contributions
ier+0.197
ge+0.160
le+0.133
iness+0.133
iest+0.130
Neg logit contributions
 First-0.229
ossible-0.227
 This-0.225
 Here-0.223
 The-0.222
Token kids
Token ID3988
Feature activation-9.76e+00

Pos logit contributions
ier+0.092
ge+0.076
 than+0.076
 again+0.075
 anymore+0.074
Neg logit contributions
 Here-0.070
 First-0.066
 Many-0.063
 Everyone-0.060
 Watch-0.060
Token who
Token ID508
Feature activation-5.06e+00

Pos logit contributions
ier+0.137
iness+0.088
iest+0.085
ge+0.085
 than+0.082
Neg logit contributions
 Here-0.223
 First-0.219
 Everyone-0.210
 This-0.207
 Many-0.205
Token played
Token ID2826
Feature activation-7.63e+00

Pos logit contributions
ier+0.104
ge+0.085
 anymore+0.084
 than+0.082
 again+0.081
Neg logit contributions
 Here-0.080
 Everyone-0.075
 First-0.075
 Many-0.074
 The-0.073
Token the
Token ID262
Feature activation-3.53e+00

Pos logit contributions
ier+0.127
ge+0.100
 than+0.094
 anymore+0.093
 again+0.092
Neg logit contributions
 Here-0.157
 First-0.151
 Many-0.147
 Everyone-0.143
 Watch-0.142
Token and
Token ID290
Feature activation-3.39e+00

Pos logit contributions
ier+0.111
 anymore+0.085
iness+0.079
iest+0.076
 than+0.074
Neg logit contributions
 The-0.117
 First-0.113
 This-0.111
 Here-0.111
 Watch-0.107
Token stole
Token ID18240
Feature activation-7.67e+00

Pos logit contributions
ier+0.063
 anymore+0.050
 than+0.050
ge+0.050
 again+0.049
Neg logit contributions
 Here-0.063
 First-0.060
 Many-0.057
 Watch-0.056
 Everyone-0.055
Token the
Token ID262
Feature activation-4.01e+00

Pos logit contributions
ier+0.172
ge+0.151
 than+0.138
 anymore+0.132
y+0.131
Neg logit contributions
 Here-0.111
 First-0.105
 Everyone-0.103
 The-0.101
 Many-0.100
Token pocket
Token ID10000
Feature activation-1.12e+01

Pos logit contributions
ier+0.089
ge+0.082
 than+0.074
y+0.071
 again+0.071
Neg logit contributions
 Here-0.055
 First-0.053
 Many-0.052
 Watch-0.048
 This-0.046
Token of
Token ID286
Feature activation-3.91e+00

Pos logit contributions
ier+0.145
ge+0.099
iness+0.097
 than+0.094
bul+0.093
Neg logit contributions
 This-0.228
 Here-0.221
 The-0.220
 First-0.216
 Many-0.208
Token cookies
Token ID14746
Feature activation-1.30e+01

Pos logit contributions
ier+0.081
ge+0.067
 than+0.066
 again+0.066
 anymore+0.065
Neg logit contributions
 Here-0.065
 First-0.061
 Many-0.058
 Watch-0.056
 Everyone-0.055
Token!
Token ID0
Feature activation+2.00e+00

Pos logit contributions
ier+0.175
ge+0.140
iest+0.133
bul+0.130
 sooner+0.117
Neg logit contributions
 This-0.252
 The-0.243
 First-0.241
 Here-0.240
 Jerry-0.236
Token It
Token ID632
Feature activation-3.99e+00

Pos logit contributions
 Here+0.017
 Majesty+0.016
 majesty+0.015
 disl+0.014
 First+0.014
Neg logit contributions
ier-0.049
 again-0.048
 anymore-0.047
.-0.045
 than-0.045
Token jumped
Token ID11687
Feature activation-8.89e+00

Pos logit contributions
ier+0.072
ge+0.059
 than+0.056
 anymore+0.056
 again+0.055
Neg logit contributions
 Here-0.073
 First-0.071
 Many-0.068
 Watch-0.067
 Everyone-0.066
Token away
Token ID1497
Feature activation-8.34e+00

Pos logit contributions
ier+0.122
ge+0.100
 than+0.088
iness+0.082
iest+0.080
Neg logit contributions
 First-0.191
 Here-0.187
 The-0.185
 This-0.184
 Watch-0.182
Token with
Token ID351
Feature activation-2.67e+00

Pos logit contributions
ier+0.138
iest+0.119
iness+0.119
le+0.117
ge+0.112
Neg logit contributions
 The-0.142
 This-0.122
 Fred-0.115
 Fin-0.111
 -0.110
Token found
Token ID1043
Feature activation-5.58e+00

Pos logit contributions
ier+0.058
 again+0.047
 than+0.047
ge+0.046
 anymore+0.046
Neg logit contributions
 Here-0.068
 First-0.064
 Many-0.061
 Watch-0.060
 Everyone-0.059
Token a
Token ID257
Feature activation-6.20e+00

Pos logit contributions
ier+0.089
 again+0.075
 on+0.071
 anymore+0.068
 inside+0.065
Neg logit contributions
 Here-0.119
 Watch-0.110
 First-0.109
 disl-0.106
 Majesty-0.104
Token sp
Token ID599
Feature activation-8.01e+00

Pos logit contributions
ier+0.145
ge+0.117
 than+0.114
 anymore+0.113
iness+0.113
Neg logit contributions
 Here-0.086
 Watch-0.078
 Many-0.074
 First-0.074
 This-0.072
Tokenool
Token ID970
Feature activation-1.05e+01

Pos logit contributions
ier+0.139
 again+0.135
ge+0.131
 anymore+0.125
 sooner+0.123
Neg logit contributions
 Here-0.127
 First-0.114
 Watch-0.114
 Everyone-0.112
 Many-0.111
Token of
Token ID286
Feature activation-5.36e+00

Pos logit contributions
ier+0.115
ge+0.115
 than+0.099
 sooner+0.091
 anymore+0.088
Neg logit contributions
 First-0.221
 Here-0.220
 The-0.214
 This-0.210
 Everyone-0.206
Token thread
Token ID4704
Feature activation-1.30e+01

Pos logit contributions
ier+0.110
ge+0.091
 anymore+0.090
 again+0.090
 than+0.089
Neg logit contributions
 Here-0.090
 First-0.086
 Many-0.081
 Watch-0.079
 Everyone-0.076
Token on
Token ID319
Feature activation-5.04e+00

Pos logit contributions
ier+0.177
ge+0.148
 sooner+0.147
iness+0.133
 anymore+0.129
Neg logit contributions
 This-0.212
 The-0.205
 It-0.196
 First-0.191
 Pip-0.189
Token the
Token ID262
Feature activation-3.11e+00

Pos logit contributions
ier+0.114
ge+0.093
 than+0.093
 again+0.091
 anymore+0.091
Neg logit contributions
 Here-0.074
 First-0.072
 Many-0.067
 Everyone-0.064
 The-0.063
Token floor
Token ID4314
Feature activation-9.34e+00

Pos logit contributions
ier+0.065
ge+0.055
 than+0.052
 anymore+0.052
 again+0.052
Neg logit contributions
 Here-0.051
 First-0.048
 Many-0.045
 Watch-0.045
 Everyone-0.043
Token.
Token ID13
Feature activation+1.32e+00

Pos logit contributions
ier+0.137
ge+0.115
bul+0.095
le+0.093
iest+0.093
Neg logit contributions
 The-0.176
 This-0.172
 First-0.166
 Here-0.165
 Every-0.161
Token It
Token ID632
Feature activation-4.07e+00

Pos logit contributions
 Majesty+0.026
 disl+0.024
 majesty+0.024
heit+0.022
 Deal+0.021
Neg logit contributions
 again-0.022
 on-0.020
 and-0.020
.-0.020
 inside-0.019
Token that
Token ID326
Feature activation-3.23e+00

Pos logit contributions
ier+0.057
 again+0.049
 anymore+0.046
 on+0.045
 than+0.044
Neg logit contributions
 Here-0.075
 First-0.071
 Watch-0.068
 Deal-0.066
 Many-0.065
Token it
Token ID340
Feature activation-5.48e+00

Pos logit contributions
ier+0.068
ge+0.057
 than+0.054
 anymore+0.053
 again+0.052
Neg logit contributions
 Here-0.054
 First-0.051
 Many-0.048
 Everyone-0.047
 Watch-0.047
Token was
Token ID373
Feature activation-4.97e+00

Pos logit contributions
ier+0.112
ge+0.097
 than+0.092
 anymore+0.085
iness+0.082
Neg logit contributions
 Here-0.082
 The-0.082
 This-0.079
 First-0.079
 Everyone-0.078
Token full
Token ID1336
Feature activation-7.11e+00

Pos logit contributions
ier+0.104
ge+0.093
iness+0.083
le+0.082
y+0.081
Neg logit contributions
 The-0.070
 Here-0.068
 First-0.067
 Every-0.065
 Mitt-0.063
Token of
Token ID286
Feature activation-5.19e+00

Pos logit contributions
ge+0.136
ier+0.128
lling+0.097
 than+0.093
 anymore+0.093
Neg logit contributions
 The-0.123
 Everyone-0.120
 Here-0.120
 Many-0.118
 Every-0.115
Token ink
Token ID16882
Feature activation-1.30e+01

Pos logit contributions
ier+0.115
ge+0.097
y+0.087
 again+0.086
 anymore+0.084
Neg logit contributions
 Here-0.084
 Many-0.084
 Everyone-0.076
 Watch-0.075
 First-0.075
Token.
Token ID13
Feature activation+1.49e+00

Pos logit contributions
ge+0.194
ier+0.172
 sooner+0.145
away+0.126
iness+0.126
Neg logit contributions
 This-0.235
 Everyone-0.222
 First-0.219
 Watch-0.214
 Here-0.212
Token She
Token ID1375
Feature activation-3.01e+00

Pos logit contributions
ossible+0.020
 Here+0.019
 Majesty+0.018
 disl+0.018
rac+0.017
Neg logit contributions
 again-0.028
 anymore-0.028
ier-0.027
 than-0.027
 inside-0.026
Token was
Token ID373
Feature activation-4.62e+00

Pos logit contributions
ier+0.044
 again+0.039
 than+0.037
y+0.037
ge+0.036
Neg logit contributions
 Here-0.064
 First-0.061
 Many-0.057
 Watch-0.057
 Everyone-0.056
Token so
Token ID523
Feature activation-1.45e+00

Pos logit contributions
ier+0.072
ge+0.056
 than+0.054
 again+0.054
 anymore+0.054
Neg logit contributions
 Here-0.100
 First-0.096
 Many-0.093
 Watch-0.091
 Everyone-0.089
Token excited
Token ID6568
Feature activation-6.26e+00

Pos logit contributions
ier+0.024
 than+0.020
 again+0.018
ge+0.018
 anymore+0.018
Neg logit contributions
 Here-0.030
 First-0.029
 Watch-0.027
 Many-0.027
 Everyone-0.026
Tokenmy
Token ID1820
Feature activation-4.93e+00

Pos logit contributions
ier+0.074
 than+0.062
ge+0.060
 anymore+0.059
 again+0.055
Neg logit contributions
 Here-0.056
 First-0.055
ossible-0.054
 Watch-0.050
 Many-0.050
Token accidentally
Token ID14716
Feature activation-4.04e+00

Pos logit contributions
ier+0.099
ge+0.082
 than+0.081
 anymore+0.079
 again+0.074
Neg logit contributions
 Here-0.078
 First-0.075
 Many-0.073
 Watch-0.072
 The-0.071
Token spilled
Token ID31896
Feature activation-7.77e+00

Pos logit contributions
ier+0.077
 than+0.065
 anymore+0.063
ge+0.062
 again+0.060
Neg logit contributions
 Here-0.068
 First-0.066
 Many-0.062
 Watch-0.062
 Everyone-0.060
Token some
Token ID617
Feature activation-7.38e+00

Pos logit contributions
ier+0.168
ge+0.156
 than+0.143
y+0.137
iness+0.130
Neg logit contributions
 First-0.107
 Here-0.104
 Everyone-0.101
 The-0.101
 Many-0.098
Token hot
Token ID3024
Feature activation-8.11e+00

Pos logit contributions
ge+0.154
ier+0.148
 than+0.126
 again+0.126
 anymore+0.126
Neg logit contributions
 Many-0.100
 Everyone-0.100
 Here-0.099
 First-0.096
 The-0.088
Token soup
Token ID17141
Feature activation-1.30e+01

Pos logit contributions
ge+0.169
ier+0.167
 anymore+0.141
 forever+0.141
 again+0.137
Neg logit contributions
 First-0.115
 Here-0.111
 Many-0.105
 Everyone-0.105
 Now-0.102
Token on
Token ID319
Feature activation-3.56e+00

Pos logit contributions
ge+0.169
ier+0.153
 sooner+0.123
 conflicts+0.117
owing+0.110
Neg logit contributions
 This-0.238
 The-0.228
 First-0.227
 Ben-0.223
 Mitt-0.222
Token his
Token ID465
Feature activation-4.49e+00

Pos logit contributions
ier+0.076
ge+0.063
 than+0.062
 again+0.061
 anymore+0.061
Neg logit contributions
 Here-0.056
 First-0.054
 Many-0.050
 Everyone-0.049
 Watch-0.049
Token hand
Token ID1021
Feature activation-1.01e+01

Pos logit contributions
ier+0.101
ge+0.086
 than+0.082
 anymore+0.081
 again+0.081
Neg logit contributions
 Here-0.066
 First-0.062
 Many-0.058
 Watch-0.057
 Everyone-0.055
Token.
Token ID13
Feature activation+1.56e+00

Pos logit contributions
ier+0.138
ge+0.125
 conflicts+0.098
 anymore+0.091
 sooner+0.091
Neg logit contributions
 This-0.201
 The-0.199
 It-0.192
 First-0.188
 Here-0.187
Token It
Token ID632
Feature activation-3.93e+00

Pos logit contributions
 Here+0.019
 Deal+0.018
ossible+0.018
 First+0.017
 Majesty+0.017
Neg logit contributions
ier-0.031
 again-0.031
 anymore-0.030
.-0.028
 on-0.028
Token liked
Token ID8288
Feature activation-5.03e+00

Pos logit contributions
ier+0.072
ge+0.057
 again+0.056
 anymore+0.056
 than+0.056
Neg logit contributions
 Here-0.082
 First-0.078
 Many-0.074
 Watch-0.072
 Everyone-0.072
Token to
Token ID284
Feature activation-2.39e+00

Pos logit contributions
ier+0.071
ge+0.052
 than+0.050
 anymore+0.049
 again+0.048
Neg logit contributions
 Here-0.118
 First-0.114
 Many-0.110
 Watch-0.108
 Everyone-0.106
Token look
Token ID804
Feature activation-5.27e+00

Pos logit contributions
ier+0.043
 again+0.039
 anymore+0.037
 than+0.037
ge+0.036
Neg logit contributions
 Here-0.042
 First-0.037
 Watch-0.035
 Many-0.034
 Deal-0.034
Token at
Token ID379
Feature activation-4.16e+00

Pos logit contributions
ier+0.074
ge+0.057
 than+0.051
 again+0.048
y+0.048
Neg logit contributions
 Here-0.121
 First-0.117
 Everyone-0.112
 Many-0.111
 Watch-0.110
Token the
Token ID262
Feature activation-3.81e+00

Pos logit contributions
ier+0.087
ge+0.072
 than+0.070
 again+0.069
 anymore+0.069
Neg logit contributions
 Here-0.069
 First-0.066
 Many-0.062
 Everyone-0.060
 Watch-0.059
Token stars
Token ID5788
Feature activation-1.30e+01

Pos logit contributions
ier+0.081
ge+0.072
 than+0.063
 again+0.063
 anymore+0.062
Neg logit contributions
 Here-0.062
 Many-0.057
 Everyone-0.056
 Watch-0.055
 First-0.054
Token at
Token ID379
Feature activation-3.39e+00

Pos logit contributions
ier+0.170
ge+0.162
less+0.140
sm+0.137
 cancelled+0.136
Neg logit contributions
 The-0.231
 This-0.216
 Everyone-0.213
 It-0.208
 Here-0.207
Token night
Token ID1755
Feature activation-8.36e+00

Pos logit contributions
ier+0.055
ge+0.043
 than+0.041
 again+0.040
 anymore+0.040
Neg logit contributions
 Here-0.070
 First-0.068
 Many-0.065
 Everyone-0.064
 The-0.063
Token.
Token ID13
Feature activation+1.82e+00

Pos logit contributions
ier+0.119
ge+0.095
iness+0.077
m+0.066
 sooner+0.065
Neg logit contributions
 Everyone-0.188
 This-0.187
 The-0.186
 Many-0.179
 Here-0.178
Token He
Token ID679
Feature activation-3.84e+00

Pos logit contributions
 Here+0.023
 Majesty+0.023
 majesty+0.021
lder+0.021
cient+0.020
Neg logit contributions
 anymore-0.038
ier-0.038
 again-0.036
 than-0.036
.-0.034
Token would
Token ID561
Feature activation-3.47e+00

Pos logit contributions
ier+0.065
ge+0.051
 anymore+0.050
 than+0.050
 again+0.049
Neg logit contributions
 Here-0.077
 First-0.074
 Many-0.071
 Watch-0.069
 Everyone-0.068
Token it
Token ID340
Feature activation-7.17e+00

Pos logit contributions
ier+0.097
ge+0.087
 than+0.082
 anymore+0.078
y+0.077
Neg logit contributions
 Here-0.070
 First-0.067
 Many-0.065
 Everyone-0.065
 The-0.064
Token was
Token ID373
Feature activation-4.18e+00

Pos logit contributions
ier+0.167
 than+0.138
ge+0.131
iness+0.131
iest+0.129
Neg logit contributions
 The-0.085
 Every-0.072
 It-0.072
 His-0.069
 -0.067
Token an
Token ID281
Feature activation-3.66e+00

Pos logit contributions
ier+0.086
ge+0.074
y+0.070
iness+0.068
 than+0.067
Neg logit contributions
 Here-0.059
 The-0.058
 First-0.057
 Fin-0.054
 Pip-0.053
Token old
Token ID1468
Feature activation-7.45e+00

Pos logit contributions
ier+0.070
 again+0.059
ge+0.059
 anymore+0.058
 than+0.057
Neg logit contributions
 Here-0.060
 First-0.058
 Many-0.057
 Watch-0.054
 Everyone-0.052
Token hamb
Token ID41478
Feature activation-7.88e+00

Pos logit contributions
ier+0.162
ge+0.136
le+0.126
 anymore+0.123
iness+0.122
Neg logit contributions
 Here-0.099
 The-0.095
 Many-0.093
 This-0.091
 Watch-0.091
Tokenurger
Token ID32650
Feature activation-1.30e+01

Pos logit contributions
ier+0.168
 again+0.147
ge+0.147
 than+0.145
 anymore+0.143
Neg logit contributions
 Here-0.115
 First-0.107
 Many-0.100
 Watch-0.098
 Everyone-0.098
Token wrapper
Token ID29908
Feature activation-1.21e+01

Pos logit contributions
ge+0.186
 conflicts+0.179
ier+0.167
able+0.166
away+0.159
Neg logit contributions
 Ben-0.202
 It-0.200
 This-0.199
 The-0.197
 Tom-0.193
Token.
Token ID13
Feature activation+2.38e+00

Pos logit contributions
 conflicts+0.145
ge+0.140
ier+0.140
 sooner+0.126
away+0.124
Neg logit contributions
 This-0.194
 It-0.191
 The-0.188
 Ben-0.187
 Pip-0.185
Token The
Token ID383
Feature activation-1.13e+00

Pos logit contributions
 disl+0.028
 Deal+0.028
 Majesty+0.028
 majesty+0.026
ossible+0.025
Neg logit contributions
 again-0.046
.-0.043
 and-0.043
 too-0.042
ier-0.041
Token car
Token ID1097
Feature activation-6.40e+00

Pos logit contributions
ier+0.023
ge+0.019
 than+0.019
 again+0.018
 anymore+0.018
Neg logit contributions
 Here-0.019
 First-0.018
 Many-0.018
 Watch-0.017
 Everyone-0.017
Token zoom
Token ID19792
Feature activation-7.48e+00

Pos logit contributions
ier+0.128
 anymore+0.103
ge+0.102
 than+0.100
iness+0.092
Neg logit contributions
 Here-0.104
 First-0.102
 The-0.101
 Many-0.101
 Everyone-0.096
Token a
Token ID257
Feature activation-5.57e+00

Pos logit contributions
ier+0.066
 again+0.058
 on+0.055
 than+0.055
 anymore+0.054
Neg logit contributions
 Here-0.093
 First-0.086
 Watch-0.081
 Deal-0.081
 Many-0.079
Token big
Token ID1263
Feature activation-6.80e+00

Pos logit contributions
ier+0.125
ge+0.105
 than+0.102
 anymore+0.098
 again+0.097
Neg logit contributions
 Here-0.081
 Watch-0.074
 Many-0.073
 First-0.071
 Everyone-0.069
Token tree
Token ID5509
Feature activation-1.05e+01

Pos logit contributions
ier+0.149
ge+0.125
 than+0.117
 again+0.115
 anymore+0.115
Neg logit contributions
 Here-0.104
 First-0.096
 Watch-0.093
 Many-0.093
 This-0.089
Token with
Token ID351
Feature activation-4.90e+00

Pos logit contributions
ier+0.168
iness+0.112
ge+0.108
iest+0.103
 anymore+0.097
Neg logit contributions
 Here-0.223
 This-0.218
 The-0.218
 First-0.204
 Every-0.201
Token many
Token ID867
Feature activation-7.32e+00

Pos logit contributions
ier+0.096
ge+0.079
 again+0.078
 than+0.078
 anymore+0.077
Neg logit contributions
 Here-0.086
 First-0.082
 Many-0.078
 Watch-0.076
 Everyone-0.075
Token nuts
Token ID14380
Feature activation-1.30e+01

Pos logit contributions
ier+0.176
ge+0.151
y+0.138
 anymore+0.138
 again+0.138
Neg logit contributions
 Many-0.094
 Here-0.093
 First-0.088
 Everyone-0.082
 Watch-0.079
Token.
Token ID13
Feature activation+1.25e+00

Pos logit contributions
ier+0.180
bul+0.145
 sooner+0.142
iness+0.132
ge+0.129
Neg logit contributions
 Here-0.224
 This-0.222
 Fin-0.218
 The-0.213
ossible-0.213
Token They
Token ID1119
Feature activation-2.98e+00

Pos logit contributions
 Majesty+0.017
 majesty+0.015
 Here+0.015
 disl+0.015
cient+0.015
Neg logit contributions
 again-0.026
 anymore-0.025
ier-0.024
 on-0.024
 than-0.024
Token want
Token ID765
Feature activation-5.26e+00

Pos logit contributions
ier+0.043
 than+0.040
 again+0.038
ge+0.038
y+0.037
Neg logit contributions
 Here-0.060
 First-0.053
 Watch-0.052
 Many-0.051
 Everyone-0.051
Token to
Token ID284
Feature activation-3.38e+00

Pos logit contributions
ier+0.090
ge+0.066
iness+0.066
 than+0.063
y+0.059
Neg logit contributions
 Here-0.106
 First-0.106
 Many-0.104
 The-0.101
 This-0.099
Token eat
Token ID4483
Feature activation-8.13e+00

Pos logit contributions
ge+0.044
 again+0.044
 ever+0.044
 anymore+0.044
 than+0.043
Neg logit contributions
 Here-0.069
 Deal-0.062
 Acc-0.061
 Now-0.061
 First-0.061
Token to
Token ID284
Feature activation-3.13e+00

Pos logit contributions
ier+0.115
iness+0.096
iest+0.095
le+0.089
ge+0.080
Neg logit contributions
 The-0.082
 This-0.077
 Here-0.076
 Remy-0.076
 Fin-0.076
Token take
Token ID1011
Feature activation-5.58e+00

Pos logit contributions
ier+0.053
ge+0.049
 again+0.047
 than+0.045
 anymore+0.045
Neg logit contributions
 Here-0.061
 First-0.056
 Many-0.053
 Everyone-0.052
 Watch-0.051
Token the
Token ID262
Feature activation-4.23e+00

Pos logit contributions
ier+0.112
 again+0.092
 than+0.092
ge+0.092
 anymore+0.092
Neg logit contributions
 Here-0.095
 First-0.090
 Many-0.085
 Watch-0.083
 Everyone-0.081
Token knight
Token ID22062
Feature activation-1.16e+01

Pos logit contributions
ier+0.078
ge+0.066
y+0.065
 than+0.060
 anymore+0.059
Neg logit contributions
 Here-0.077
 Watch-0.071
 First-0.067
 Many-0.067
 Majesty-0.063
Token's
Token ID338
Feature activation-5.49e+00

Pos logit contributions
ier+0.187
 than+0.118
iness+0.118
m+0.115
iest+0.115
Neg logit contributions
 This-0.231
 First-0.221
 The-0.217
 Here-0.217
 Harry-0.214
Token sword
Token ID8429
Feature activation-1.29e+01

Pos logit contributions
ier+0.111
y+0.087
ge+0.086
m+0.081
 anymore+0.081
Neg logit contributions
 Here-0.098
 Watch-0.088
 First-0.086
 Majesty-0.083
 Many-0.083
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
ier+0.183
iest+0.136
m+0.132
bul+0.121
 inches+0.119
Neg logit contributions
 First-0.234
 This-0.233
 The-0.222
 Jerry-0.222
 Harry-0.221
Token But
Token ID887
Feature activation-3.64e+00

Pos logit contributions
 Majesty+0.020
 Deal+0.019
 Here+0.019
 majesty+0.019
 disl+0.018
Neg logit contributions
 again-0.037
.-0.034
ier-0.033
 and-0.033
 anymore-0.033
Token the
Token ID262
Feature activation-2.71e+00

Pos logit contributions
ier+0.083
ge+0.073
 than+0.070
y+0.069
 anymore+0.068
Neg logit contributions
 Here-0.050
 First-0.047
 The-0.045
 Many-0.044
 Everyone-0.043
Token knight
Token ID22062
Feature activation-7.94e+00

Pos logit contributions
ier+0.052
ge+0.046
 than+0.043
y+0.043
 anymore+0.042
Neg logit contributions
 Here-0.045
 Watch-0.043
 First-0.043
 Many-0.043
 Everyone-0.040
Token was
Token ID373
Feature activation-4.73e+00

Pos logit contributions
ier+0.164
ge+0.138
 than+0.137
 anymore+0.131
 sooner+0.122
Neg logit contributions
 Here-0.106
 The-0.102
 Many-0.100
 Fin-0.099
 First-0.099
Token couldn
Token ID3521
Feature activation+7.69e-01

Pos logit contributions
ier+0.055
 anymore+0.045
 than+0.044
ge+0.043
 again+0.041
Neg logit contributions
 First-0.047
 Here-0.046
 Many-0.044
 Watch-0.044
 Everyone-0.043
Token't
Token ID470
Feature activation-3.18e+00

Pos logit contributions
 Here+0.013
 Majesty+0.012
 disl+0.012
 First+0.012
 majesty+0.012
Neg logit contributions
ier-0.015
 again-0.014
 anymore-0.013
 on-0.013
 ever-0.013
Token find
Token ID1064
Feature activation-6.19e+00

Pos logit contributions
ier+0.077
 than+0.065
ge+0.064
y+0.064
 again+0.062
Neg logit contributions
 First-0.036
 Many-0.036
 Here-0.035
 Everyone-0.034
 The-0.033
Token any
Token ID597
Feature activation-6.96e+00

Pos logit contributions
ier+0.127
ge+0.114
y+0.103
 than+0.102
m+0.100
Neg logit contributions
 First-0.095
 Here-0.094
 Many-0.092
 Everyone-0.090
 The-0.089
Token new
Token ID649
Feature activation-6.78e+00

Pos logit contributions
ier+0.139
ge+0.125
y+0.122
m+0.115
ably+0.111
Neg logit contributions
 Many-0.092
 Everyone-0.088
 First-0.087
 Watch-0.087
 Here-0.080
Token planets
Token ID14705
Feature activation-1.29e+01

Pos logit contributions
ier+0.149
ge+0.123
m+0.121
less+0.117
y+0.114
Neg logit contributions
 First-0.094
 Watch-0.088
 Everyone-0.088
 Many-0.087
 Here-0.084
Token around
Token ID1088
Feature activation-5.82e+00

Pos logit contributions
ier+0.196
ge+0.181
ud+0.163
 amount+0.161
m+0.146
Neg logit contributions
 I-0.198
 This-0.187
 The-0.187
 It-0.182
 Fred-0.179
Token her
Token ID607
Feature activation-5.04e+00

Pos logit contributions
ier+0.147
ge+0.124
 than+0.113
m+0.109
less+0.109
Neg logit contributions
 The-0.066
 Everyone-0.061
 It-0.058
 This-0.058
 Many-0.056
Token.
Token ID13
Feature activation+1.78e+00

Pos logit contributions
ier+0.077
ge+0.060
y+0.049
iness+0.048
m+0.047
Neg logit contributions
 The-0.104
 Here-0.102
 Everyone-0.100
 Majesty-0.100
 This-0.098
Token But
Token ID887
Feature activation-2.45e+00

Pos logit contributions
 Here+0.020
 disl+0.020
ossible+0.019
 Deal+0.018
 Fin+0.018
Neg logit contributions
ier-0.037
 again-0.036
 anymore-0.035
 than-0.034
y-0.032
Token then
Token ID788
Feature activation-2.35e+00

Pos logit contributions
ier+0.054
ge+0.043
 than+0.041
 anymore+0.039
y+0.039
Neg logit contributions
 First-0.040
 Here-0.039
 The-0.036
 Many-0.036
 Everyone-0.034
Token help
Token ID1037
Feature activation+2.49e+00

Pos logit contributions
 Here+0.098
 First+0.088
 Many+0.085
 Watch+0.082
 Everyone+0.080
Neg logit contributions
ier-0.112
 again-0.097
ge-0.097
 than-0.095
 anymore-0.094
Token me
Token ID502
Feature activation+9.84e-01

Pos logit contributions
 Here+0.029
 First+0.027
 Many+0.025
 Watch+0.024
 Everyone+0.023
Neg logit contributions
ier-0.063
 again-0.055
 than-0.055
ge-0.055
 anymore-0.055
Token pay
Token ID1414
Feature activation+1.26e+00

Pos logit contributions
 Here+0.019
 First+0.019
 Watch+0.017
 Many+0.017
 Everyone+0.017
Neg logit contributions
ier-0.017
 than-0.013
ge-0.013
 anymore-0.013
y-0.012
Token for
Token ID329
Feature activation+3.93e+00

Pos logit contributions
 Here+0.025
 First+0.024
 Watch+0.022
 Everyone+0.022
 Many+0.022
Neg logit contributions
ier-0.021
ge-0.017
 anymore-0.016
 than-0.016
 again-0.016
Token it
Token ID340
Feature activation-1.04e+00

Pos logit contributions
 Here+0.067
 First+0.064
 Many+0.060
 Watch+0.059
 Everyone+0.057
Neg logit contributions
ier-0.078
 again-0.065
 than-0.065
ge-0.065
 anymore-0.064
Token."
Token ID526
Feature activation+9.74e+00

Pos logit contributions
ier+0.014
ge+0.012
 than+0.010
y+0.010
bul+0.009
Neg logit contributions
 First-0.022
 Here-0.021
 This-0.020
 The-0.020
 Everyone-0.019
Token Tim
Token ID5045
Feature activation+3.99e+00

Pos logit contributions
 Here+0.124
 First+0.121
 Majesty+0.119
 Watch+0.117
 majesty+0.111
Neg logit contributions
 again-0.197
.-0.180
 anymore-0.177
ier-0.175
 than-0.171
Token was
Token ID373
Feature activation+4.95e+00

Pos logit contributions
 Here+0.086
 First+0.082
 Many+0.079
 Watch+0.077
 Everyone+0.076
Neg logit contributions
ier-0.062
 again-0.050
ge-0.048
 than-0.048
 anymore-0.047
Token very
Token ID845
Feature activation+7.41e+00

Pos logit contributions
 Here+0.111
 First+0.106
 Watch+0.100
 Many+0.100
 Everyone+0.096
Neg logit contributions
ier-0.074
 again-0.059
 than-0.057
 anymore-0.057
ge-0.055
Token happy
Token ID3772
Feature activation+1.82e+00

Pos logit contributions
 Here+0.160
 First+0.156
 Many+0.145
 Watch+0.145
 Everyone+0.140
Neg logit contributions
ier-0.115
 than-0.091
 again-0.090
ge-0.086
 anymore-0.084
Token and
Token ID290
Feature activation+5.29e+00

Pos logit contributions
 The+0.033
 Here+0.032
 This+0.032
 Ben+0.031
 Dad+0.030
Neg logit contributions
ier-0.031
ge-0.023
iest-0.022
le-0.020
 visible-0.020
Token bring
Token ID2222
Feature activation+6.39e+00

Pos logit contributions
ier+0.065
ge+0.053
 anymore+0.052
 than+0.052
 again+0.051
Neg logit contributions
 Here-0.062
 First-0.060
 Many-0.056
 Watch-0.055
 Everyone-0.054
Token trouble
Token ID5876
Feature activation+2.53e+00

Pos logit contributions
 Here+0.108
 First+0.102
 Many+0.097
 Watch+0.095
 Everyone+0.091
Neg logit contributions
ier-0.128
 again-0.107
 than-0.106
 anymore-0.105
ge-0.104
Token,
Token ID11
Feature activation+6.78e+00

Pos logit contributions
 Here+0.058
 First+0.055
 Everyone+0.054
 Watch+0.053
 disl+0.053
Neg logit contributions
ier-0.029
ge-0.021
y-0.019
 anymore-0.018
 than-0.017
Token he
Token ID339
Feature activation+4.30e+00

Pos logit contributions
 Here+0.144
 First+0.138
 Watch+0.132
 Many+0.132
 Everyone+0.129
Neg logit contributions
ier-0.108
ge-0.083
 anymore-0.079
 than-0.078
 again-0.077
Token refused
Token ID6520
Feature activation+6.34e+00

Pos logit contributions
 Here+0.085
 First+0.081
 Many+0.076
 Watch+0.076
 Everyone+0.075
Neg logit contributions
ier-0.074
ge-0.059
 than-0.058
 anymore-0.058
 again-0.057
Token.
Token ID13
Feature activation+1.10e+01

Pos logit contributions
 Here+0.132
 First+0.127
 Everyone+0.123
 This+0.121
 The+0.121
Neg logit contributions
ier-0.096
ge-0.074
y-0.068
 than-0.067
 anymore-0.065
Token
Token ID198
Feature activation+1.07e+01

Pos logit contributions
 Here+0.122
 First+0.121
 disl+0.118
rac+0.114
 Majesty+0.113
Neg logit contributions
 again-0.224
ier-0.211
 anymore-0.209
 than-0.202
.-0.198
Token
Token ID198
Feature activation+1.04e+01

Pos logit contributions
cient+0.184
 Sorry+0.183
 Here+0.182
 Majesty+0.182
 First+0.178
Neg logit contributions
 again-0.162
.-0.149
ier-0.146
ge-0.144
 on-0.141
TokenJohn
Token ID7554
Feature activation+3.74e+00

Pos logit contributions
 Here+0.172
 First+0.166
cient+0.162
 Majesty+0.160
sed+0.158
Neg logit contributions
ier-0.164
ge-0.157
 again-0.155
 than-0.152
 ever-0.141
Token looked
Token ID3114
Feature activation+4.35e+00

Pos logit contributions
 Here+0.069
 First+0.067
 Many+0.063
 Everyone+0.063
 Watch+0.062
Neg logit contributions
ier-0.067
 than-0.054
 anymore-0.054
ge-0.053
 again-0.049
Token around
Token ID1088
Feature activation+3.73e+00

Pos logit contributions
 Here+0.091
 First+0.089
 The+0.085
 Watch+0.084
 Everyone+0.083
Neg logit contributions
ier-0.066
ge-0.055
 than-0.048
 anymore-0.045
y-0.044
Token belt
Token ID10999
Feature activation+1.48e-01

Pos logit contributions
 Here+0.072
 First+0.068
 Watch+0.065
 Everyone+0.064
 This+0.063
Neg logit contributions
ier-0.072
ge-0.059
 anymore-0.054
 than-0.053
 again-0.052
Token for
Token ID329
Feature activation+5.58e+00

Pos logit contributions
 Here+0.003
 First+0.003
 Everyone+0.003
 This+0.003
 Watch+0.003
Neg logit contributions
ier-0.002
ge-0.002
 than-0.002
 anymore-0.002
 again-0.002
Token when
Token ID618
Feature activation+5.68e+00

Pos logit contributions
 Here+0.085
 First+0.080
 Many+0.074
 Watch+0.073
 Everyone+0.069
Neg logit contributions
ier-0.120
 again-0.103
 than-0.102
ge-0.101
 anymore-0.101
Token I
Token ID314
Feature activation+6.20e+00

Pos logit contributions
 Here+0.077
 First+0.071
 Many+0.066
 Watch+0.064
 Everyone+0.062
Neg logit contributions
ier-0.133
 again-0.114
 than-0.114
ge-0.113
 anymore-0.113
Token chew
Token ID34722
Feature activation+1.08e+00

Pos logit contributions
 Here+0.105
 First+0.100
 Many+0.094
 Watch+0.093
 Everyone+0.091
Neg logit contributions
ier-0.124
 than-0.102
ge-0.102
 anymore-0.101
 again-0.100
Token.
Token ID13
Feature activation+9.54e+00

Pos logit contributions
 Here+0.022
 First+0.021
 Watch+0.020
 Everyone+0.020
 This+0.020
Neg logit contributions
ier-0.017
ge-0.014
 than-0.013
 anymore-0.013
 again-0.012
Token I
Token ID314
Feature activation+7.34e+00

Pos logit contributions
 Majesty+0.110
lder+0.109
 disl+0.107
cient+0.103
ossible+0.101
Neg logit contributions
 than-0.167
 again-0.164
 too-0.162
 on-0.161
ier-0.159
Token have
Token ID423
Feature activation+4.17e+00

Pos logit contributions
 Here+0.121
 First+0.115
 Many+0.108
 Watch+0.106
 Everyone+0.103
Neg logit contributions
ier-0.151
ge-0.123
 than-0.123
 anymore-0.122
 again-0.121
Token bad
Token ID2089
Feature activation+3.18e+00

Pos logit contributions
 Here+0.078
 First+0.075
 Many+0.071
 Watch+0.070
 Everyone+0.068
Neg logit contributions
ier-0.076
ge-0.061
 than-0.061
 again-0.061
 anymore-0.060
Token teeth
Token ID9941
Feature activation-1.74e+00

Pos logit contributions
 Here+0.059
 First+0.057
 Watch+0.053
 Many+0.053
 Everyone+0.052
Neg logit contributions
ier-0.058
ge-0.049
 anymore-0.047
 again-0.047
 than-0.046
Token,
Token ID11
Feature activation+5.51e+00

Pos logit contributions
ier+0.027
ge+0.024
 beneath+0.021
 anymore+0.020
bul+0.020
Neg logit contributions
 Here-0.032
 First-0.030
 This-0.029
 Everyone-0.029
 The-0.028
Token to
Token ID284
Feature activation+9.33e+00

Pos logit contributions
 First+0.147
 Here+0.145
 Many+0.137
 The+0.137
 Everyone+0.137
Neg logit contributions
ier-0.127
ge-0.094
 than-0.090
 anymore-0.088
iest-0.083
Token set
Token ID900
Feature activation+3.56e+00

Pos logit contributions
 Here+0.159
 First+0.146
 Many+0.140
 Watch+0.136
 Everyone+0.132
Neg logit contributions
ier-0.183
 again-0.159
 anymore-0.156
ge-0.155
 than-0.155
Token.
Token ID13
Feature activation+1.07e+01

Pos logit contributions
 First+0.072
 Here+0.072
 Everyone+0.068
 Watch+0.066
 The+0.065
Neg logit contributions
ier-0.057
ge-0.044
 than-0.043
 anymore-0.042
y-0.041
Token
Token ID220
Feature activation+9.90e+00

Pos logit contributions
 Here+0.112
 Majesty+0.109
 disl+0.105
 majesty+0.104
rac+0.103
Neg logit contributions
 again-0.226
ier-0.217
 anymore-0.213
 than-0.209
.-0.206
Token
Token ID198
Feature activation+1.07e+01

Pos logit contributions
 Here+0.156
 Majesty+0.155
 Watch+0.153
 disl+0.150
lder+0.148
Neg logit contributions
ier-0.180
 again-0.168
.-0.160
 anymore-0.160
y-0.154
Token
Token ID198
Feature activation+1.03e+01

Pos logit contributions
 Majesty+0.177
 Here+0.175
 majesty+0.169
 Sorry+0.165
cient+0.164
Neg logit contributions
 again-0.174
ier-0.166
ge-0.165
y-0.158
.-0.157
TokenWhen
Token ID2215
Feature activation+7.49e+00

Pos logit contributions
 Here+0.169
 Majesty+0.158
 First+0.154
 majesty+0.152
cient+0.151
Neg logit contributions
ier-0.166
ge-0.162
 again-0.157
 than-0.155
y-0.150
Token it
Token ID340
Feature activation+3.04e+00

Pos logit contributions
 Here+0.113
 First+0.110
 Many+0.099
 Everyone+0.099
 Watch+0.098
Neg logit contributions
ier-0.166
ge-0.140
 than-0.139
 anymore-0.135
 again-0.133
Token was
Token ID373
Feature activation+6.58e+00

Pos logit contributions
 First+0.050
 Everyone+0.048
 Many+0.047
 Here+0.047
 The+0.046
Neg logit contributions
ier-0.057
 than-0.053
ge-0.048
 anymore-0.047
 sooner-0.041
Token time
Token ID640
Feature activation+2.39e+00

Pos logit contributions
 Here+0.147
 First+0.145
 Many+0.136
 Watch+0.134
 Everyone+0.133
Neg logit contributions
ier-0.094
ge-0.074
 than-0.072
 anymore-0.069
 again-0.069
Token to
Token ID284
Feature activation+7.36e+00

Pos logit contributions
 First+0.046
 Here+0.045
 This+0.044
 The+0.042
ossible+0.042
Neg logit contributions
ier-0.038
 than-0.031
ge-0.031
 anymore-0.029
bul-0.027
Token a
Token ID257
Feature activation+3.58e+00

Pos logit contributions
 First+0.079
 Here+0.079
 Many+0.077
 Everyone+0.075
 The+0.074
Neg logit contributions
ier-0.142
ge-0.114
 than-0.111
 anymore-0.110
 again-0.108
Token bush
Token ID24484
Feature activation-3.78e-01

Pos logit contributions
 Here+0.053
 Watch+0.050
 Many+0.050
 Everyone+0.048
 First+0.047
Neg logit contributions
ier-0.078
ge-0.064
 than-0.062
 anymore-0.058
iness-0.058
Token.
Token ID13
Feature activation+9.71e+00

Pos logit contributions
ier+0.005
ge+0.004
 than+0.003
iest+0.003
iness+0.003
Neg logit contributions
 This-0.008
 Here-0.008
 The-0.008
 First-0.008
 Everyone-0.008
Token
Token ID220
Feature activation+9.04e+00

Pos logit contributions
 disl+0.119
rac+0.118
 Majesty+0.113
lder+0.111
cient+0.108
Neg logit contributions
 again-0.189
 anymore-0.173
.-0.170
 before-0.166
ier-0.164
Token
Token ID198
Feature activation+1.01e+01

Pos logit contributions
 Majesty+0.150
 Here+0.150
 disl+0.147
 Watch+0.145
lder+0.145
Neg logit contributions
ier-0.150
 again-0.146
 anymore-0.141
.-0.137
 on-0.133
Token
Token ID198
Feature activation+9.69e+00

Pos logit contributions
 Majesty+0.176
cient+0.169
 Here+0.169
 majesty+0.165
 Sorry+0.165
Neg logit contributions
 again-0.156
.-0.139
ge-0.139
ier-0.136
y-0.135
TokenWhen
Token ID2215
Feature activation+6.88e+00

Pos logit contributions
 Here+0.162
 Majesty+0.157
 First+0.156
cient+0.154
 majesty+0.150
Neg logit contributions
 again-0.142
ier-0.140
ge-0.138
 than-0.137
y-0.132
Token Sally
Token ID25737
Feature activation+3.39e+00

Pos logit contributions
 Here+0.109
 First+0.104
 Many+0.096
 Watch+0.095
 Everyone+0.094
Neg logit contributions
ier-0.148
ge-0.124
 than-0.123
 anymore-0.120
 again-0.119
Token looked
Token ID3114
Feature activation+3.22e+00

Pos logit contributions
 Here+0.058
 First+0.056
 The+0.053
 Many+0.053
 Watch+0.051
Neg logit contributions
ier-0.067
 than-0.057
 anymore-0.053
ge-0.052
iness-0.048
Token inside
Token ID2641
Feature activation+2.23e+00

Pos logit contributions
 Here+0.067
 First+0.066
 Watch+0.061
 The+0.061
 Many+0.061
Neg logit contributions
ier-0.049
ge-0.041
 than-0.039
iness-0.033
 anymore-0.033
Token the
Token ID262
Feature activation+5.70e+00

Pos logit contributions
 Here+0.035
 First+0.033
 The+0.032
 Everyone+0.031
 This+0.030
Neg logit contributions
ier-0.047
ge-0.038
 than-0.038
 anymore-0.036
y-0.034
Token When
Token ID1649
Feature activation+4.10e+00

Pos logit contributions
 disl+0.091
 Here+0.084
 Many+0.079
 Watch+0.078
 Fin+0.077
Neg logit contributions
ier-0.153
 again-0.153
 anymore-0.137
.-0.136
 than-0.136
Token she
Token ID673
Feature activation+2.01e+00

Pos logit contributions
 Here+0.068
 First+0.067
 Everyone+0.063
 The+0.061
 Many+0.061
Neg logit contributions
ier-0.084
ge-0.071
 than-0.070
 anymore-0.066
y-0.065
Token opened
Token ID4721
Feature activation+3.78e-01

Pos logit contributions
 Here+0.026
 The+0.026
 First+0.025
 Watch+0.024
 Many+0.024
Neg logit contributions
ier-0.045
 than-0.040
ge-0.037
 anymore-0.036
iness-0.034
Token it
Token ID340
Feature activation-1.80e+00

Pos logit contributions
 Here+0.006
 First+0.006
 Many+0.005
 Everyone+0.005
 The+0.005
Neg logit contributions
ier-0.008
ge-0.007
 than-0.007
 anymore-0.006
 again-0.006
Token,
Token ID11
Feature activation+4.24e+00

Pos logit contributions
ier+0.033
ge+0.028
 than+0.027
iness+0.025
 anymore+0.023
Neg logit contributions
 First-0.033
 Here-0.032
 This-0.031
 The-0.031
 Everyone-0.030
Token the
Token ID262
Feature activation+3.42e+00

Pos logit contributions
 Here+0.079
 First+0.075
 Many+0.070
 Watch+0.070
 Everyone+0.069
Neg logit contributions
ier-0.078
ge-0.063
 than-0.063
 anymore-0.063
 again-0.061
Token jelly
Token ID27644
Feature activation-3.66e+00

Pos logit contributions
 Here+0.053
 Watch+0.049
 First+0.048
 Everyone+0.046
 Many+0.046
Neg logit contributions
ier-0.072
ge-0.064
 anymore-0.059
 than-0.058
y-0.055
Token came
Token ID1625
Feature activation-9.70e-01

Pos logit contributions
ier+0.064
ge+0.061
 anymore+0.056
 than+0.054
 sooner+0.050
Neg logit contributions
 Here-0.061
 Watch-0.058
 First-0.056
 Everyone-0.055
 Remy-0.053
Token out
Token ID503
Feature activation-9.46e-01

Pos logit contributions
ier+0.015
ge+0.012
 than+0.012
 anymore+0.012
iness+0.011
Neg logit contributions
 Here-0.018
 The-0.018
 First-0.018
 Watch-0.017
 This-0.017
Token in
Token ID287
Feature activation+2.20e+00

Pos logit contributions
ier+0.015
iness+0.012
ge+0.012
 conflicts+0.011
 anymore+0.011
Neg logit contributions
 The-0.018
 Every-0.015
 This-0.015
 It-0.015
 Watch-0.014
Token perfect
Token ID2818
Feature activation-2.85e+00

Pos logit contributions
 The+0.033
 First+0.030
 Every+0.029
 +0.029
 This+0.028
Neg logit contributions
ier-0.050
ge-0.038
iness-0.038
owing-0.036
 anymore-0.035
Token threw
Token ID9617
Feature activation-3.52e+00

Pos logit contributions
 Here+0.009
 First+0.009
 Many+0.008
 Watch+0.008
 Everyone+0.008
Neg logit contributions
ier-0.010
ge-0.008
 anymore-0.008
 than-0.008
 again-0.008
Token them
Token ID606
Feature activation-4.88e+00

Pos logit contributions
ier+0.083
ge+0.072
 than+0.067
iness+0.063
 anymore+0.062
Neg logit contributions
 First-0.047
 Here-0.045
 Many-0.043
 Everyone-0.042
 The-0.042
Token on
Token ID319
Feature activation-1.41e+00

Pos logit contributions
ier+0.088
iest+0.068
ge+0.065
iness+0.063
cest+0.061
Neg logit contributions
 First-0.086
 The-0.084
 This-0.081
ossible-0.079
 Here-0.077
Token the
Token ID262
Feature activation+1.02e+00

Pos logit contributions
ier+0.039
iness+0.031
ge+0.031
 than+0.030
iest+0.030
Neg logit contributions
 The-0.015
 First-0.015
 Everyone-0.013
 Many-0.013
 Here-0.013
Token floor
Token ID4314
Feature activation-6.57e+00

Pos logit contributions
 Here+0.012
 First+0.012
 Watch+0.011
 Everyone+0.011
 The+0.011
Neg logit contributions
ier-0.025
ge-0.022
y-0.021
 than-0.020
 anymore-0.020
Token.
Token ID13
Feature activation+4.26e+00

Pos logit contributions
ier+0.099
ge+0.083
iest+0.078
le+0.077
bul+0.076
Neg logit contributions
 The-0.110
 First-0.103
 This-0.102
 Ben-0.097
 Everyone-0.095
Token He
Token ID679
Feature activation-2.86e-01

Pos logit contributions
 Here+0.060
rac+0.055
lder+0.054
ossible+0.054
 disl+0.052
Neg logit contributions
ier-0.088
 again-0.082
 anymore-0.081
 than-0.076
 on-0.074
Token took
Token ID1718
Feature activation-1.24e+00

Pos logit contributions
ier+0.006
 anymore+0.005
ge+0.005
 than+0.004
 again+0.004
Neg logit contributions
 Here-0.005
 First-0.005
 Many-0.005
 Watch-0.004
 Everyone-0.004
Token out
Token ID503
Feature activation-2.26e+00

Pos logit contributions
ier+0.023
ge+0.019
 than+0.019
 anymore+0.018
 again+0.017
Neg logit contributions
 Here-0.023
 First-0.023
 Many-0.021
 Everyone-0.021
 Watch-0.021
Token his
Token ID465
Feature activation-1.06e+00

Pos logit contributions
ier+0.056
ge+0.048
 than+0.048
 anymore+0.046
iness+0.043
Neg logit contributions
 Many-0.026
 First-0.026
 The-0.026
 Everyone-0.024
 Here-0.024
Token toys
Token ID14958
Feature activation-8.82e+00

Pos logit contributions
ier+0.024
ge+0.019
 again+0.018
y+0.018
 anymore+0.018
Neg logit contributions
 Here-0.017
 First-0.016
ossible-0.015
 Many-0.015
 The-0.015
Token set
Token ID900
Feature activation+1.35e-01

Pos logit contributions
 First+0.034
 Here+0.033
 Many+0.030
 Everyone+0.030
 Watch+0.029
Neg logit contributions
ier-0.039
 anymore-0.032
 than-0.032
ge-0.031
 again-0.031
Token off
Token ID572
Feature activation-4.35e-01

Pos logit contributions
 Here+0.003
 First+0.003
 Many+0.003
 Watch+0.003
 Everyone+0.003
Neg logit contributions
ier-0.002
 than-0.001
ge-0.001
 again-0.001
 anymore-0.001
Token.
Token ID13
Feature activation+7.38e+00

Pos logit contributions
ier+0.007
iness+0.006
 than+0.005
iest+0.005
ge+0.005
Neg logit contributions
 The-0.009
 This-0.009
 First-0.009
 Everyone-0.008
 -0.008
Token
Token ID220
Feature activation+6.64e+00

Pos logit contributions
 disl+0.111
lder+0.109
 Majesty+0.107
rac+0.100
 majesty+0.100
Neg logit contributions
 again-0.134
 on-0.127
 anymore-0.124
.-0.121
 before-0.119
Token
Token ID198
Feature activation+7.45e+00

Pos logit contributions
 disl+0.112
 Majesty+0.112
 Watch+0.110
 Here+0.109
lder+0.106
Neg logit contributions
ier-0.110
 again-0.102
.-0.100
 on-0.097
 anymore-0.095
Token
Token ID198
Feature activation+7.16e+00

Pos logit contributions
 Majesty+0.141
 Here+0.136
 disl+0.135
 majesty+0.130
cient+0.127
Neg logit contributions
 again-0.111
ier-0.109
 on-0.105
ge-0.103
m-0.101
TokenWhen
Token ID2215
Feature activation+3.69e+00

Pos logit contributions
 Here+0.137
 Majesty+0.126
 First+0.123
 majesty+0.121
 disl+0.120
Neg logit contributions
ier-0.111
ge-0.100
 again-0.098
 than-0.097
y-0.093
Token they
Token ID484
Feature activation+2.20e+00

Pos logit contributions
 First+0.056
 Here+0.055
 Everyone+0.050
 The+0.049
 Many+0.048
Neg logit contributions
ier-0.083
ge-0.070
 than-0.069
y-0.064
 anymore-0.064
Token arrived
Token ID5284
Feature activation+6.38e-01

Pos logit contributions
 First+0.038
 Here+0.037
 Many+0.035
 Everyone+0.034
 The+0.033
Neg logit contributions
ier-0.043
 than-0.037
ge-0.035
 anymore-0.034
 again-0.034
Token at
Token ID379
Feature activation+3.29e+00

Pos logit contributions
 Here+0.014
 First+0.014
 Everyone+0.013
 The+0.013
 Many+0.013
Neg logit contributions
ier-0.009
ge-0.007
 than-0.007
 anymore-0.006
 again-0.006
Token the
Token ID262
Feature activation+2.38e+00

Pos logit contributions
 Here+0.055
 First+0.052
 Many+0.049
 Watch+0.048
 Everyone+0.047
Neg logit contributions
ier-0.067
 again-0.056
 than-0.055
ge-0.055
 anymore-0.055
Token it
Token ID340
Feature activation-2.24e+00

Pos logit contributions
 First+0.013
 Everyone+0.013
 Here+0.013
 The+0.012
 This+0.012
Neg logit contributions
ier-0.021
ge-0.018
y-0.017
iness-0.017
 than-0.016
Token home
Token ID1363
Feature activation-1.89e+00

Pos logit contributions
ier+0.039
m+0.028
iness+0.027
y+0.026
bul+0.026
Neg logit contributions
 First-0.038
 This-0.035
 Pip-0.033
 Harry-0.033
 Sammy-0.033
Token.
Token ID13
Feature activation+9.49e+00

Pos logit contributions
ier+0.027
iness+0.020
 anymore+0.018
bul+0.018
ge+0.018
Neg logit contributions
 First-0.034
 The-0.034
 This-0.033
 Here-0.032
 Everyone-0.031
Token
Token ID198
Feature activation+8.84e+00

Pos logit contributions
 disl+0.145
rac+0.138
lder+0.136
 Majesty+0.134
 majesty+0.133
Neg logit contributions
 again-0.164
 anymore-0.146
.-0.145
 than-0.136
 before-0.135
Token
Token ID198
Feature activation+8.71e+00

Pos logit contributions
 Here+0.157
 Majesty+0.155
 Sorry+0.151
 disl+0.151
 First+0.146
Neg logit contributions
 again-0.140
ier-0.130
ge-0.128
 on-0.125
.-0.124
TokenAnna
Token ID31160
Feature activation+2.13e+00

Pos logit contributions
 Here+0.154
 First+0.140
 Majesty+0.137
 majesty+0.133
 disl+0.133
Neg logit contributions
ier-0.142
ge-0.134
 again-0.132
 than-0.128
y-0.123
Token's
Token ID338
Feature activation+3.65e+00

Pos logit contributions
 Here+0.041
 First+0.039
 Many+0.037
 Watch+0.037
 Everyone+0.036
Neg logit contributions
ier-0.038
 anymore-0.030
ge-0.030
 than-0.030
 again-0.029
Token mummy
Token ID38567
Feature activation-1.35e+00

Pos logit contributions
 Here+0.049
 First+0.046
 Many+0.042
 Watch+0.042
 Everyone+0.040
Neg logit contributions
ier-0.085
 again-0.074
 than-0.073
 anymore-0.073
ge-0.073
Token saw
Token ID2497
Feature activation+2.84e+00

Pos logit contributions
ier+0.025
 than+0.020
 anymore+0.020
ge+0.020
 again+0.018
Neg logit contributions
 Here-0.024
 First-0.024
 Many-0.022
 Everyone-0.022
 The-0.022
Token what
Token ID644
Feature activation+3.65e+00

Pos logit contributions
 Here+0.046
 First+0.043
 Many+0.041
 Everyone+0.039
 Watch+0.039
Neg logit contributions
ier-0.060
ge-0.050
 than-0.050
 anymore-0.048
 again-0.047
Token Anna
Token ID11735
Feature activation-1.40e+00

Pos logit contributions
 Here+0.061
 Everyone+0.058
 First+0.058
 Many+0.058
 The+0.056
Neg logit contributions
ier-0.074
ge-0.065
 than-0.058
 again-0.056
 anymore-0.056
Token without
Token ID1231
Feature activation+4.89e+00

Pos logit contributions
 Here+0.035
 First+0.034
 Everyone+0.033
 Many+0.032
 The+0.032
Neg logit contributions
ier-0.021
ge-0.015
 than-0.014
 anymore-0.013
 again-0.012
Token permission
Token ID7170
Feature activation+1.00e+00

Pos logit contributions
 Here+0.090
 First+0.086
 Many+0.081
 Watch+0.080
 Everyone+0.080
Neg logit contributions
ier-0.089
ge-0.070
 anymore-0.070
 than-0.070
 again-0.070
Token.
Token ID13
Feature activation+1.03e+01

Pos logit contributions
 Here+0.024
 First+0.024
 Everyone+0.022
 This+0.022
 Many+0.022
Neg logit contributions
ier-0.012
ge-0.009
 than-0.008
 anymore-0.008
 again-0.008
Token<|endoftext|>
Token ID50256
Feature activation+5.03e+00

Pos logit contributions
 Here+0.120
 Majesty+0.119
lder+0.118
rac+0.116
 majesty+0.114
Neg logit contributions
 again-0.199
 anymore-0.197
ier-0.196
 than-0.190
ge-0.183
TokenOnce
Token ID7454
Feature activation+6.06e+00

Pos logit contributions
 Here+0.075
 First+0.071
 Many+0.065
 Watch+0.065
 disl+0.061
Neg logit contributions
ier-0.109
 again-0.096
 anymore-0.094
 than-0.092
ge-0.091
Token upon
Token ID2402
Feature activation+6.92e+00

Pos logit contributions
 Here+0.148
 First+0.142
 Watch+0.138
 Many+0.136
 Everyone+0.130
Neg logit contributions
ier-0.078
 again-0.061
 anymore-0.060
ge-0.058
y-0.055
Token a
Token ID257
Feature activation+5.66e+00

Pos logit contributions
 Here+0.134
 First+0.128
 Watch+0.118
 Many+0.115
 Everyone+0.114
Neg logit contributions
ier-0.119
 again-0.102
 than-0.099
 anymore-0.098
ge-0.095
Token time
Token ID640
Feature activation+3.90e+00

Pos logit contributions
 Here+0.148
 First+0.142
 Watch+0.135
 Many+0.135
 Everyone+0.134
Neg logit contributions
ier-0.060
 than-0.044
 again-0.044
 anymore-0.044
ge-0.041
Token there
Token ID612
Feature activation+3.63e+00

Pos logit contributions
 Here+0.103
 First+0.099
 Watch+0.095
 Many+0.094
 Everyone+0.092
Neg logit contributions
ier-0.041
 again-0.032
 anymore-0.032
 than-0.030
ge-0.028
Token was
Token ID373
Feature activation+4.34e+00

Pos logit contributions
 Here+0.084
 First+0.081
 Many+0.077
 Watch+0.076
 Everyone+0.075
Neg logit contributions
ier-0.050
 again-0.038
 than-0.038
ge-0.038
 anymore-0.038
Token a
Token ID257
Feature activation+2.42e+00

Pos logit contributions
 Here+0.091
 First+0.085
 Watch+0.084
 disl+0.081
 Majesty+0.081
Neg logit contributions
ier-0.064
 on-0.056
 than-0.055
 again-0.053
 anymore-0.052
Token.
Token ID13
Feature activation+5.16e+00

Pos logit contributions
ier+0.105
ge+0.088
 than+0.080
iest+0.079
 sooner+0.077
Neg logit contributions
 The-0.133
 This-0.131
 It-0.131
 Everyone-0.130
 Many-0.119
Token
Token ID198
Feature activation+5.50e+00

Pos logit contributions
 disl+0.079
 Majesty+0.077
 Here+0.077
 Amen+0.073
 majesty+0.073
Neg logit contributions
 again-0.085
.-0.082
 anymore-0.082
ier-0.080
 on-0.079
Token
Token ID198
Feature activation+5.26e+00

Pos logit contributions
 Majesty+0.113
 Here+0.106
 majesty+0.103
 disl+0.102
cient+0.102
Neg logit contributions
 again-0.078
.-0.078
 on-0.071
ier-0.070
ge-0.070
Token"
Token ID1
Feature activation+3.70e+00

Pos logit contributions
 Here+0.094
 First+0.084
 Majesty+0.084
 Many+0.080
 disl+0.080
Neg logit contributions
ier-0.091
ge-0.083
 than-0.082
y-0.077
 on-0.077
TokenMom
Token ID29252
Feature activation-2.62e+00

Pos logit contributions
 Here+0.054
 First+0.049
 Many+0.046
 Everyone+0.044
 Watch+0.044
Neg logit contributions
ier-0.081
 again-0.072
 than-0.070
ge-0.070
y-0.068
Token,
Token ID11
Feature activation-9.68e-02

Pos logit contributions
ier+0.037
ge+0.028
 than+0.028
 again+0.028
 anymore+0.028
Neg logit contributions
 Here-0.060
 First-0.057
 Many-0.055
 Watch-0.054
 Everyone-0.053
Token why
Token ID1521
Feature activation-7.55e-02

Pos logit contributions
ier+0.002
 again+0.002
 anymore+0.001
 than+0.001
 on+0.001
Neg logit contributions
 Here-0.002
 First-0.002
 Many-0.002
 Everyone-0.002
 Watch-0.002
Token are
Token ID389
Feature activation+6.89e-01

Pos logit contributions
ier+0.002
ge+0.001
 again+0.001
 than+0.001
 anymore+0.001
Neg logit contributions
 Here-0.001
 First-0.001
 Many-0.001
 Watch-0.001
 Everyone-0.001
Token we
Token ID356
Feature activation-2.01e+00

Pos logit contributions
 Here+0.012
 First+0.011
 Many+0.011
 Watch+0.011
 Everyone+0.010
Neg logit contributions
ier-0.013
 anymore-0.011
 on-0.011
 again-0.011
 than-0.010
Token not
Token ID407
Feature activation-9.01e-01

Pos logit contributions
ier+0.033
 than+0.028
ge+0.027
 again+0.026
 anymore+0.025
Neg logit contributions
 Here-0.036
 First-0.035
 Many-0.034
 Watch-0.033
ossible-0.033
Token moving
Token ID3867
Feature activation-3.95e+00

Pos logit contributions
ier+0.016
 anymore+0.013
le+0.012
 again+0.012
ge+0.012
Neg logit contributions
 Here-0.015
 Watch-0.015
 The-0.014
 This-0.014
 Many-0.014
Token let
Token ID1309
Feature activation+2.07e+00

Pos logit contributions
 Here+0.047
 First+0.045
 Many+0.042
 Watch+0.040
 Everyone+0.039
Neg logit contributions
ier-0.068
 again-0.058
 than-0.058
 anymore-0.057
ge-0.057
Token's
Token ID338
Feature activation+3.83e+00

Pos logit contributions
 Here+0.052
 disl+0.049
 Many+0.049
 Higher+0.047
 First+0.047
Neg logit contributions
 again-0.021
ier-0.018
--0.018
 on-0.018
 away-0.017
Token go
Token ID467
Feature activation-1.32e+00

Pos logit contributions
 Here+0.069
 Many+0.063
 First+0.062
 Watch+0.059
 disl+0.058
Neg logit contributions
ier-0.067
 again-0.062
 on-0.059
 anymore-0.059
ge-0.057
Token and
Token ID290
Feature activation+4.95e+00

Pos logit contributions
ier+0.020
 than+0.015
 anymore+0.015
ge+0.015
 again+0.015
Neg logit contributions
 Here-0.029
 First-0.028
 Many-0.026
 Watch-0.026
 Everyone-0.026
Token show
Token ID905
Feature activation+1.67e+00

Pos logit contributions
 Here+0.081
 Many+0.077
 First+0.075
 Watch+0.070
 Everyone+0.070
Neg logit contributions
ier-0.088
 again-0.088
 on-0.080
ge-0.079
 anymore-0.078
Token everyone
Token ID2506
Feature activation-1.82e+00

Pos logit contributions
 Here+0.029
 Many+0.027
 First+0.026
 disl+0.025
 Watch+0.025
Neg logit contributions
ier-0.030
 again-0.029
 anymore-0.026
 on-0.026
 than-0.025
Token my
Token ID616
Feature activation+1.94e+00

Pos logit contributions
ier+0.036
ge+0.030
 anymore+0.028
 than+0.027
 again+0.027
Neg logit contributions
 Here-0.032
 First-0.029
 Everyone-0.028
 This-0.027
 Watch-0.027
Token new
Token ID649
Feature activation+3.03e-02

Pos logit contributions
 Here+0.035
 First+0.033
 Many+0.032
 Everyone+0.031
 Watch+0.031
Neg logit contributions
ier-0.038
ge-0.031
 than-0.029
y-0.028
 again-0.028
Token skirt
Token ID23967
Feature activation-4.92e+00

Pos logit contributions
 Here+0.001
 First+0.001
 Watch+0.000
 Many+0.000
 Everyone+0.000
Neg logit contributions
ier-0.001
ge-0.000
 anymore-0.000
 than-0.000
 again-0.000
Token!"
Token ID2474
Feature activation+7.42e+00

Pos logit contributions
ier+0.092
ge+0.085
 anymore+0.075
 than+0.073
 again+0.073
Neg logit contributions
 Here-0.083
 First-0.078
 Everyone-0.073
 Watch-0.073
 This-0.072
Token So
Token ID1406
Feature activation+4.48e+00

Pos logit contributions
 Here+0.069
 First+0.059
 Many+0.054
 Watch+0.053
 Majesty+0.050
Neg logit contributions
ier-0.193
 again-0.180
 anymore-0.176
 than-0.175
y-0.169
Token were
Token ID547
Feature activation-1.63e+00

Pos logit contributions
ier+0.021
ge+0.018
 anymore+0.017
 than+0.017
 again+0.016
Neg logit contributions
 Here-0.014
 First-0.014
 Many-0.014
 The-0.014
 Everyone-0.013
Token friends
Token ID2460
Feature activation-5.79e+00

Pos logit contributions
ier+0.031
ge+0.027
 anymore+0.026
 again+0.025
 than+0.025
Neg logit contributions
 Here-0.028
 First-0.027
 Many-0.025
 Watch-0.025
 Everyone-0.025
Token.
Token ID13
Feature activation+3.49e+00

Pos logit contributions
ge+0.093
ier+0.091
bul+0.076
iful+0.074
ruck+0.073
Neg logit contributions
 The-0.104
 I-0.091
 Everyone-0.091
 It-0.090
 Leave-0.088
Token<|endoftext|>
Token ID50256
Feature activation-1.60e+00

Pos logit contributions
 Majesty+0.053
 Here+0.050
cient+0.050
 First+0.049
lder+0.048
Neg logit contributions
 than-0.063
 anymore-0.061
 again-0.059
ier-0.059
.-0.057
TokenTim
Token ID14967
Feature activation-2.78e+00

Pos logit contributions
ier+0.037
 again+0.032
 than+0.032
ge+0.032
 anymore+0.031
Neg logit contributions
 Here-0.022
 First-0.021
 Many-0.019
 Watch-0.019
 Everyone-0.018
Token and
Token ID290
Feature activation+9.58e-01

Pos logit contributions
ier+0.036
ge+0.026
 anymore+0.024
 than+0.024
 again+0.023
Neg logit contributions
 Here-0.067
 First-0.065
 Many-0.062
 The-0.061
 Everyone-0.061
Token Jen
Token ID13364
Feature activation-2.06e+00

Pos logit contributions
 Majesty+0.022
 Deal+0.021
 Here+0.020
 First+0.020
 majesty+0.020
Neg logit contributions
 on-0.012
 ever-0.011
 in-0.011
 than-0.010
 from-0.010
Token were
Token ID547
Feature activation-2.14e+00

Pos logit contributions
ier+0.038
ge+0.030
 than+0.029
 anymore+0.029
 again+0.029
Neg logit contributions
 Here-0.038
 First-0.036
 Many-0.035
 Everyone-0.034
 The-0.033
Token twins
Token ID20345
Feature activation-5.33e+00

Pos logit contributions
ier+0.029
 again+0.023
 on+0.023
 anymore+0.022
 than+0.022
Neg logit contributions
 Here-0.049
 First-0.047
 Watch-0.046
 disl-0.045
 Many-0.045
Token who
Token ID508
Feature activation-2.09e+00

Pos logit contributions
ier+0.074
ge+0.053
iness+0.049
iest+0.048
 than+0.042
Neg logit contributions
 The-0.123
 Here-0.120
 Everyone-0.115
 Many-0.113
 This-0.112
Token liked
Token ID8288
Feature activation-4.48e+00

Pos logit contributions
ier+0.044
ge+0.037
 again+0.036
 anymore+0.035
 than+0.034
Neg logit contributions
 Here-0.033
 First-0.031
 Many-0.031
 Everyone-0.030
 The-0.030
Token<|endoftext|>
Token ID50256
Feature activation-7.58e-02

Pos logit contributions
cient+0.093
lder+0.088
rac+0.088
 Majesty+0.083
heit+0.083
Neg logit contributions
 than-0.081
.-0.071
 again-0.070
ier-0.068
 anymore-0.065
TokenTom
Token ID13787
Feature activation-8.47e-01

Pos logit contributions
ier+0.002
 again+0.001
 than+0.001
 anymore+0.001
ge+0.001
Neg logit contributions
 Here-0.001
 First-0.001
 Many-0.001
 Watch-0.001
 Everyone-0.001
Token and
Token ID290
Feature activation+2.37e+00

Pos logit contributions
ier+0.014
ge+0.011
 anymore+0.010
 than+0.010
 again+0.010
Neg logit contributions
 Here-0.018
 First-0.017
 Many-0.016
 Watch-0.016
 Everyone-0.015
Token Lily
Token ID20037
Feature activation-5.93e-01

Pos logit contributions
 Majesty+0.052
 Deal+0.050
 Here+0.049
 First+0.048
 majesty+0.047
Neg logit contributions
 on-0.031
 ever-0.028
 in-0.028
 from-0.026
 than-0.026
Token were
Token ID547
Feature activation-8.07e-01

Pos logit contributions
ier+0.011
 than+0.009
 again+0.009
ge+0.009
 anymore+0.009
Neg logit contributions
 Here-0.011
 First-0.011
 Many-0.010
 Watch-0.010
 Everyone-0.010
Token playing
Token ID2712
Feature activation-4.09e+00

Pos logit contributions
ier+0.011
 again+0.009
 on+0.009
 anymore+0.009
 than+0.008
Neg logit contributions
 Here-0.018
 First-0.018
 Watch-0.017
 Many-0.017
 disl-0.017
Token in
Token ID287
Feature activation-2.16e-02

Pos logit contributions
ier+0.042
ge+0.028
 than+0.026
 anymore+0.025
 again+0.024
Neg logit contributions
 Here-0.111
 First-0.108
 Many-0.103
 Watch-0.103
 Everyone-0.101
Token the
Token ID262
Feature activation+1.66e+00

Pos logit contributions
 again+0.000
ier+0.000
 than+0.000
ge+0.000
 on+0.000
Neg logit contributions
 Here-0.000
 First-0.000
 Watch-0.000
 Majesty-0.000
 Many-0.000
Token park
Token ID3952
Feature activation-4.93e+00

Pos logit contributions
 Here+0.034
 Many+0.032
 First+0.031
 Deal+0.030
 Watch+0.030
Neg logit contributions
 again-0.022
 on-0.021
ier-0.021
y-0.020
 inside-0.020
Token.
Token ID13
Feature activation+3.69e+00

Pos logit contributions
ier+0.082
ge+0.059
iness+0.055
bul+0.049
iest+0.048
Neg logit contributions
 First-0.105
 Here-0.104
 The-0.104
 This-0.100
 Everyone-0.099
Token They
Token ID1119
Feature activation-1.47e+00

Pos logit contributions
 Here+0.048
 Majesty+0.046
cient+0.045
rac+0.043
 Watch+0.043
Neg logit contributions
 anymore-0.076
ier-0.074
 again-0.074
 than-0.073
 on-0.069
Token Mama
Token ID40084
Feature activation+1.04e+00

Pos logit contributions
 Here+0.112
 disl+0.103
 Majesty+0.100
lder+0.098
 majesty+0.096
Neg logit contributions
 again-0.191
ier-0.185
 anymore-0.178
 than-0.174
.-0.169
Token was
Token ID373
Feature activation+4.25e+00

Pos logit contributions
 Here+0.021
 First+0.020
 Everyone+0.019
 Many+0.019
 The+0.019
Neg logit contributions
ier-0.016
 than-0.013
ge-0.013
 anymore-0.013
 again-0.011
Token so
Token ID523
Feature activation+6.53e+00

Pos logit contributions
 Here+0.080
 First+0.077
 Many+0.075
 Everyone+0.074
 Watch+0.074
Neg logit contributions
ier-0.073
ge-0.060
 than-0.058
 anymore-0.057
 again-0.056
Token proud
Token ID6613
Feature activation+3.10e+00

Pos logit contributions
 Here+0.114
 First+0.107
 Many+0.103
 Watch+0.100
 Everyone+0.099
Neg logit contributions
ier-0.127
ge-0.105
 anymore-0.104
 again-0.104
 than-0.104
Token of
Token ID286
Feature activation+5.80e+00

Pos logit contributions
 Everyone+0.057
 The+0.054
 Here+0.053
 First+0.053
 Dad+0.053
Neg logit contributions
ier-0.051
ge-0.046
 anywhere-0.038
 anymore-0.036
 sooner-0.036
Token them
Token ID606
Feature activation-9.81e-02

Pos logit contributions
 Here+0.092
 First+0.087
 Many+0.081
 Watch+0.079
 Everyone+0.077
Neg logit contributions
ier-0.124
 again-0.104
 than-0.104
ge-0.104
 anymore-0.103
Token.
Token ID13
Feature activation+9.14e+00

Pos logit contributions
ier+0.002
ge+0.001
bul+0.001
iest+0.001
web+0.001
Neg logit contributions
 The-0.002
 Everyone-0.002
 This-0.002
 First-0.002
 Here-0.002
Token She
Token ID1375
Feature activation+4.06e+00

Pos logit contributions
 Here+0.125
 disl+0.121
Ta+0.120
 Watch+0.117
rac+0.117
Neg logit contributions
 again-0.154
.-0.147
ier-0.146
 than-0.141
 and-0.140
Token said
Token ID531
Feature activation+4.22e+00

Pos logit contributions
 Here+0.074
 First+0.070
 Many+0.066
 Watch+0.065
 Everyone+0.064
Neg logit contributions
ier-0.077
 than-0.062
 again-0.062
ge-0.062
 anymore-0.062
Token,
Token ID11
Feature activation+4.75e+00

Pos logit contributions
 Here+0.093
 First+0.090
 Many+0.084
 Watch+0.084
 Everyone+0.080
Neg logit contributions
ier-0.065
 again-0.052
 anymore-0.049
 than-0.048
ge-0.046
Token "
Token ID366
Feature activation+7.32e+00

Pos logit contributions
 Here+0.061
 First+0.058
 Many+0.053
 Watch+0.051
 Everyone+0.047
Neg logit contributions
ier-0.111
 again-0.100
 than-0.097
ge-0.095
 anymore-0.094
Token.
Token ID13
Feature activation+2.54e+00

Pos logit contributions
ier+0.164
iest+0.114
ge+0.113
m+0.108
 inches+0.098
Neg logit contributions
 First-0.209
ossible-0.207
 The-0.206
 This-0.203
 Here-0.200
Token The
Token ID383
Feature activation+1.05e-02

Pos logit contributions
 disl+0.023
 Here+0.023
 Deal+0.023
ossible+0.022
rac+0.022
Neg logit contributions
 again-0.057
ier-0.053
 anymore-0.053
 than-0.051
 before-0.051
Token bunny
Token ID44915
Feature activation-5.31e+00

Pos logit contributions
 Here+0.000
 First+0.000
 Many+0.000
 Watch+0.000
 Everyone+0.000
Neg logit contributions
ier-0.000
ge-0.000
 than-0.000
 anymore-0.000
 again-0.000
Token was
Token ID373
Feature activation-3.14e+00

Pos logit contributions
ier+0.098
ge+0.079
 than+0.077
 anymore+0.077
 again+0.071
Neg logit contributions
 Here-0.096
 First-0.093
 Many-0.090
 Everyone-0.088
 Watch-0.088
Token very
Token ID845
Feature activation-6.27e-01

Pos logit contributions
ier+0.054
ge+0.044
 than+0.042
 anymore+0.041
y+0.040
Neg logit contributions
 Here-0.059
 Many-0.057
 First-0.057
 The-0.055
 Watch-0.054
Token sad
Token ID6507
Feature activation-6.49e+00

Pos logit contributions
ier+0.011
 than+0.008
ge+0.008
 again+0.008
 anymore+0.008
Neg logit contributions
 Here-0.013
 First-0.012
 Many-0.012
 Watch-0.011
 Everyone-0.011
Token and
Token ID290
Feature activation-9.63e-01

Pos logit contributions
ier+0.119
ge+0.110
iest+0.103
lling+0.101
pr+0.100
Neg logit contributions
 The-0.101
 Remy-0.091
 It-0.091
 Fin-0.090
 Ben-0.089
Token scared
Token ID12008
Feature activation-5.53e+00

Pos logit contributions
ier+0.016
 again+0.013
 than+0.013
ge+0.013
 anymore+0.013
Neg logit contributions
 Here-0.019
 First-0.019
 Many-0.018
 Watch-0.017
 Everyone-0.017
Token again
Token ID757
Feature activation-5.55e+00

Pos logit contributions
ier+0.088
ge+0.086
iest+0.063
bul+0.063
iness+0.061
Neg logit contributions
 The-0.117
 Everyone-0.110
 Fin-0.107
 It-0.105
 Remy-0.103
Token.
Token ID13
Feature activation+3.10e+00

Pos logit contributions
ier+0.090
iest+0.063
iness+0.059
ge+0.055
bul+0.052
Neg logit contributions
 The-0.120
 Remy-0.111
 Fin-0.110
 This-0.110
 Everyone-0.106
Token The
Token ID383
Feature activation+2.95e-01

Pos logit contributions
 disl+0.036
 Here+0.035
 Deal+0.033
 First+0.033
rac+0.033
Neg logit contributions
 again-0.063
 anymore-0.059
 than-0.057
.-0.056
 before-0.055
Token
Token ID198
Feature activation+3.13e+00

Pos logit contributions
 Majesty+0.069
 Here+0.063
 majesty+0.062
 disl+0.061
cient+0.060
Neg logit contributions
 again-0.050
.-0.047
 on-0.045
 and-0.044
 inside-0.041
Token"
Token ID1
Feature activation+9.20e-01

Pos logit contributions
 Here+0.058
 Majesty+0.057
 Fin+0.057
 First+0.057
 Dod+0.054
Neg logit contributions
 again-0.045
y-0.043
ier-0.043
 than-0.042
--0.041
TokenI
Token ID40
Feature activation-3.50e-01

Pos logit contributions
 Majesty+0.016
 Here+0.016
 First+0.016
 majesty+0.015
 Remy+0.014
Neg logit contributions
ier-0.016
 than-0.014
 on-0.013
m-0.013
y-0.013
Token'm
Token ID1101
Feature activation-2.55e+00

Pos logit contributions
ier+0.008
 anymore+0.006
 again+0.006
ge+0.006
 than+0.006
Neg logit contributions
 Here-0.005
 First-0.005
 Many-0.005
 Watch-0.005
 This-0.005
Token decor
Token ID11705
Feature activation-5.64e+00

Pos logit contributions
ier+0.043
 than+0.034
 again+0.034
ge+0.034
 anymore+0.034
Neg logit contributions
 Here-0.051
 First-0.049
 Many-0.047
 Watch-0.046
 Everyone-0.045
Tokenating
Token ID803
Feature activation-6.57e+00

Pos logit contributions
ier+0.109
 again+0.090
 than+0.088
 anymore+0.086
ge+0.085
Neg logit contributions
 Here-0.103
 First-0.098
 Many-0.094
 Watch-0.091
 Everyone-0.087
Token my
Token ID616
Feature activation-3.56e+00

Pos logit contributions
ier+0.140
ge+0.118
 anymore+0.113
 than+0.113
 again+0.111
Neg logit contributions
 Here-0.103
 First-0.098
 Many-0.089
 Watch-0.089
 Everyone-0.089
Token door
Token ID3420
Feature activation-9.50e+00

Pos logit contributions
ier+0.078
ge+0.063
y+0.059
iness+0.059
 anymore+0.057
Neg logit contributions
 Here-0.062
 First-0.056
 The-0.053
 Watch-0.053
 Many-0.052
Token with
Token ID351
Feature activation-4.61e+00

Pos logit contributions
ier+0.180
ge+0.147
 anymore+0.142
iness+0.140
 again+0.135
Neg logit contributions
 Here-0.164
 First-0.162
 This-0.144
 The-0.141
 Watch-0.141
Token this
Token ID428
Feature activation-4.76e+00

Pos logit contributions
ier+0.093
ge+0.078
 than+0.076
 anymore+0.076
 again+0.075
Neg logit contributions
 Here-0.078
 First-0.075
 Many-0.070
 Watch-0.068
 Everyone-0.067
Token pretty
Token ID2495
Feature activation-6.11e+00

Pos logit contributions
ier+0.094
ge+0.083
 anymore+0.075
y+0.075
 than+0.074
Neg logit contributions
 Here-0.078
 First-0.077
 Everyone-0.070
 Watch-0.069
 This-0.069
Token and
Token ID290
Feature activation-2.41e+00

Pos logit contributions
ier+0.120
ge+0.092
iness+0.086
iest+0.076
 anymore+0.071
Neg logit contributions
 This-0.149
 The-0.148
 Here-0.147
 Everyone-0.145
 First-0.145
Token loved
Token ID6151
Feature activation-5.87e+00

Pos logit contributions
ier+0.045
ge+0.037
 than+0.036
 anymore+0.036
 again+0.036
Neg logit contributions
 Here-0.044
 First-0.042
 Many-0.040
 Watch-0.039
 Everyone-0.039
Token to
Token ID284
Feature activation-2.92e+00

Pos logit contributions
ier+0.113
ge+0.089
 than+0.081
iness+0.080
 anymore+0.080
Neg logit contributions
 Here-0.110
 First-0.104
 Many-0.103
 Everyone-0.101
 Watch-0.099
Token learn
Token ID2193
Feature activation-7.98e+00

Pos logit contributions
ier+0.059
 again+0.052
 anymore+0.050
 than+0.050
ge+0.049
Neg logit contributions
 Here-0.048
 First-0.044
 Many-0.039
 Watch-0.039
 Everyone-0.037
Token new
Token ID649
Feature activation-6.83e+00

Pos logit contributions
ier+0.172
ge+0.152
y+0.134
iness+0.133
 ever+0.128
Neg logit contributions
 Everyone-0.120
 Here-0.117
 Many-0.112
 Watch-0.111
 First-0.110
Token things
Token ID1243
Feature activation-8.79e+00

Pos logit contributions
ier+0.127
ge+0.106
y+0.089
 beneath+0.087
 anymore+0.085
Neg logit contributions
 Everyone-0.130
 Here-0.128
 First-0.126
 Many-0.124
 Watch-0.124
Token.
Token ID13
Feature activation+1.85e+00

Pos logit contributions
ier+0.128
ge+0.125
ud+0.102
iness+0.101
ited+0.096
Neg logit contributions
 This-0.162
 Here-0.154
 Everyone-0.151
 The-0.147
 Every-0.144
Token One
Token ID1881
Feature activation-4.32e+00

Pos logit contributions
 Here+0.021
 Majesty+0.021
 disl+0.021
rac+0.021
lder+0.020
Neg logit contributions
 again-0.040
 anymore-0.040
ier-0.037
.-0.036
 than-0.035
Token day
Token ID1110
Feature activation-2.65e+00

Pos logit contributions
ier+0.084
ge+0.069
 anymore+0.063
 again+0.059
 than+0.057
Neg logit contributions
 Here-0.083
 Many-0.080
 First-0.078
 The-0.077
 Watch-0.076
Token,
Token ID11
Feature activation+1.31e-01

Pos logit contributions
ier+0.043
ge+0.034
 than+0.033
 again+0.032
 anymore+0.032
Neg logit contributions
 Here-0.055
 First-0.053
 Many-0.051
 Everyone-0.050
 Watch-0.050
Token Lily
Token ID20037
Feature activation-4.58e+00

Pos logit contributions
 Here+0.002
 First+0.002
 Many+0.002
 Watch+0.002
 Everyone+0.002
Neg logit contributions
ier-0.003
ge-0.002
 than-0.002
 again-0.002
 anymore-0.002
Token to
Token ID284
Feature activation+4.22e-01

Pos logit contributions
ier+0.065
ge+0.053
bul+0.047
iness+0.047
 sooner+0.044
Neg logit contributions
 This-0.066
 Here-0.065
 The-0.064
 Everyone-0.064
 First-0.063
Token see
Token ID766
Feature activation-2.07e+00

Pos logit contributions
 Here+0.006
 First+0.006
 Many+0.005
 Watch+0.005
 Everyone+0.005
Neg logit contributions
ier-0.009
 again-0.008
 than-0.008
ge-0.008
 anymore-0.008
Token what
Token ID644
Feature activation-1.66e+00

Pos logit contributions
ier+0.044
ge+0.036
y+0.036
 than+0.035
 anymore+0.034
Neg logit contributions
 Here-0.032
 First-0.030
 Everyone-0.029
 Many-0.029
 The-0.028
Token could
Token ID714
Feature activation-6.33e-01

Pos logit contributions
ier+0.033
ge+0.029
 anymore+0.026
 than+0.025
y+0.025
Neg logit contributions
 Here-0.028
 Everyone-0.026
 First-0.026
 The-0.026
 Many-0.026
Token be
Token ID307
Feature activation-3.35e+00

Pos logit contributions
ier+0.013
ge+0.010
 than+0.010
 anymore+0.010
 again+0.010
Neg logit contributions
 Here-0.011
 First-0.010
 Many-0.010
 Watch-0.009
 Everyone-0.009
Token hidden
Token ID7104
Feature activation-7.98e+00

Pos logit contributions
ier+0.051
ge+0.044
iness+0.042
y+0.039
m+0.039
Neg logit contributions
 Here-0.059
 disl-0.058
 The-0.057
 Watch-0.056
 This-0.056
Token underneath
Token ID14638
Feature activation-4.41e+00

Pos logit contributions
ier+0.099
m+0.093
ge+0.084
bul+0.082
y+0.079
Neg logit contributions
 The-0.131
 Harry-0.129
 This-0.129
 Fin-0.126
 Here-0.125
Token it
Token ID340
Feature activation-6.39e+00

Pos logit contributions
ier+0.093
ge+0.079
m+0.072
y+0.072
 than+0.070
Neg logit contributions
 The-0.066
 Everyone-0.061
 This-0.061
 It-0.060
 Here-0.059
Token.
Token ID13
Feature activation+4.44e+00

Pos logit contributions
ier+0.095
ge+0.074
iness+0.062
bul+0.059
 than+0.059
Neg logit contributions
 This-0.132
 The-0.131
 First-0.130
 Here-0.128
 Everyone-0.126
Token He
Token ID679
Feature activation-1.38e+00

Pos logit contributions
 disl+0.055
 Majesty+0.054
 majesty+0.051
 Deal+0.049
lder+0.048
Neg logit contributions
 again-0.087
ier-0.080
.-0.078
 anymore-0.078
 than-0.077
Token carefully
Token ID7773
Feature activation-2.63e+00

Pos logit contributions
ier+0.027
 anymore+0.022
ge+0.021
 than+0.021
 again+0.020
Neg logit contributions
 Here-0.025
 First-0.024
 Many-0.022
 Watch-0.022
 Everyone-0.022
Tokenither
Token ID1555
Feature activation-4.21e+00

Pos logit contributions
 Here+0.009
 First+0.009
 Many+0.008
 Watch+0.008
 disl+0.007
Neg logit contributions
ier-0.012
 anymore-0.010
ge-0.010
 than-0.009
 again-0.009
Tokeny
Token ID88
Feature activation-4.16e+00

Pos logit contributions
ier+0.062
ge+0.049
 anymore+0.048
 sooner+0.047
 than+0.047
Neg logit contributions
 Everyone-0.078
 Fin-0.077
 First-0.077
 The-0.077
 Here-0.076
Token gl
Token ID1278
Feature activation-3.04e+00

Pos logit contributions
ier+0.074
ge+0.062
 anymore+0.055
 than+0.052
 sooner+0.052
Neg logit contributions
 Here-0.071
 First-0.071
 Everyone-0.070
 Many-0.069
 Watch-0.069
Tokenided
Token ID1384
Feature activation-3.56e+00

Pos logit contributions
ier+0.051
 again+0.044
 anymore+0.044
 than+0.043
ge+0.042
Neg logit contributions
 Here-0.057
 First-0.054
 Watch-0.051
 Many-0.051
 Everyone-0.050
Token across
Token ID1973
Feature activation-7.13e-01

Pos logit contributions
ier+0.050
ge+0.038
 anymore+0.036
 than+0.034
 again+0.032
Neg logit contributions
 First-0.080
 Here-0.079
 Everyone-0.075
 The-0.075
 Watch-0.074
Token them
Token ID606
Feature activation-6.10e+00

Pos logit contributions
ier+0.018
ge+0.016
 than+0.015
 anymore+0.015
iness+0.015
Neg logit contributions
 The-0.008
 First-0.007
 Here-0.007
 Many-0.007
 Everyone-0.007
Token until
Token ID1566
Feature activation+9.87e-01

Pos logit contributions
ier+0.087
ge+0.065
iest+0.056
iness+0.056
bul+0.055
Neg logit contributions
 The-0.121
 This-0.117
 Here-0.115
 Everyone-0.114
 First-0.114
Token he
Token ID339
Feature activation-1.08e+00

Pos logit contributions
 Here+0.017
 First+0.016
 Many+0.015
 Watch+0.015
 Everyone+0.015
Neg logit contributions
ier-0.020
ge-0.016
 than-0.016
 anymore-0.016
 again-0.016
Token reached
Token ID4251
Feature activation-1.94e+00

Pos logit contributions
ier+0.020
ge+0.016
 than+0.016
 anymore+0.016
 again+0.015
Neg logit contributions
 Here-0.019
 First-0.018
 Many-0.017
 Watch-0.017
 Everyone-0.017
Token the
Token ID262
Feature activation+2.75e-01

Pos logit contributions
ier+0.041
ge+0.034
 than+0.034
 anymore+0.033
y+0.032
Neg logit contributions
 Here-0.030
 First-0.030
 The-0.027
 Watch-0.026
 Everyone-0.026
Token other
Token ID584
Feature activation-2.70e+00

Pos logit contributions
 Here+0.003
 First+0.003
 Everyone+0.003
 Watch+0.003
 Many+0.003
Neg logit contributions
ier-0.007
ge-0.006
 than-0.006
 anymore-0.006
y-0.006