TOP ACTIVATIONS
MAX = 0.236

, you can keep the coins . You can buy something
Everyone wanted to share the treasure together . Now , the
They paid him with some coins they had .
hurried away with his borrowed hook . From that day forward
should not have taken your sack . I was curious .
'm sorry I dropped the bag and the gum ."
okay if you keep the treasure . But if you don
okay if you keep the treasure . But if you don
They do not want a haircut . They see
friends and shared the pretty rocks from the mine . They
! You cannot take my corn !" Tom and
He takes his tower of coins and throws it at the
much he loved his funny suit and how much fun he
" Let 's replace the rocks at the bottom of the
fast . I put the rope on the bike to see
bear did not like the broom . It ran to the
the waves crashing against the shore . " Would
would let them keep their patch if they gave him their
couldn 't play with his boat without bubbles .
She even shared her delicious snack with the little boy as

MIN ACTIVATIONS
MIN = -0.493

When Daisy put the magn ifying glass down , the cater
John chose some carrots and cuc umbers to take home .
That â s right , Emma
That â s the gas from
those in need â even <|endoftext|> One day
by one 1 , 2 ,
s ok , â said her mum .
arm chair . THE <|endoftext|> Once upon a time
T IM â . It looked nice and
nos y . <|endoftext|> Once upon a time , a little
Let â s explore and have
Let â s not think about
Let â s play a joke
Let â s have a stretching
please â and
, the little girl â s l imes were
Please don â t eat me ,
very much . <|endoftext|> Once upon a time , there was
Who â s there ? â
Why don â t you come with

INTERVAL 0.054 - 0.236
CONTAINS 34.736%

but you have to be careful with other people 's things
old . Every morning , she would pray . She would
were bright and colorful , and smelled so good ! When
They waited for their mom to come home from work
hungry , but I don 't have anything to eat ."

INTERVAL -0.129 - 0.054
CONTAINS 53.718%

bird . The bird said , " I can 't find
ens . <|endoftext|> Once upon a time , there was a
. They put Lily 's cow in the barn . They
feels bad for pin ching Lily . He sees a red
lucky car and was so thankful for the adventure it was

INTERVAL -0.311 - -0.129
CONTAINS 11.068%

over to the kitten . He was carrying a warm blanket
spaghetti for dinner , which was Lily 's favorite . Lily
crown and make them jealous . He put on his best
That â s why it â
ily was so happy that she made an original cookie all

INTERVAL -0.493 - -0.311
CONTAINS 0.478%

little dog . <|endoftext|> Once upon a time , in a
playful adventure . <|endoftext|> Once upon a time , there was
ever after . <|endoftext|> Once upon a time , there was
flew away . <|endoftext|> Once upon a time , there was
best friends . <|endoftext|> Once upon a time , there was
Token,
Token ID11
Feature activation+9.54e-02

Pos logit contributions
 whispered+0.122
chy+0.116
l+0.109
 woke+0.107
 said+0.106
Neg logit contributions
 unison-0.174
ric-0.166
latable-0.165
 Deal-0.163
 yeah-0.160
Token you
Token ID345
Feature activation+1.10e-01

Pos logit contributions
 said+0.122
 whispered+0.120
 woke+0.112
 fell+0.106
 man+0.105
Neg logit contributions
ric-0.158
latable-0.156
 unison-0.156
igsaw-0.146
 Deal-0.144
Token can
Token ID460
Feature activation+1.13e-01

Pos logit contributions
 whispered+0.123
 said+0.114
 woke+0.110
 fell+0.109
chy+0.108
Neg logit contributions
 unison-0.188
ric-0.183
latable-0.181
 Deal-0.177
igsaw-0.172
Token keep
Token ID1394
Feature activation+1.55e-01

Pos logit contributions
 said+0.139
 whispered+0.138
 fell+0.133
 woke+0.130
chy+0.122
Neg logit contributions
 unison-0.186
ric-0.182
latable-0.175
 Deal-0.172
igsaw-0.169
Token the
Token ID262
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.213
 said+0.204
 fell+0.188
 woke+0.187
l+0.184
Neg logit contributions
 unison-0.229
latable-0.219
ric-0.217
 Deal-0.211
igsaw-0.208
Token coins
Token ID10796
Feature activation+2.29e-01

Pos logit contributions
 whispered+0.154
 said+0.141
 fell+0.140
chy+0.139
 meant+0.137
Neg logit contributions
 unison-0.154
latable-0.150
ric-0.148
 Deal-0.141
 yeah-0.137
Token.
Token ID13
Feature activation+3.31e-02

Pos logit contributions
 whispered+0.211
 said+0.190
 woke+0.187
 fell+0.180
chy+0.179
Neg logit contributions
 unison-0.425
ric-0.419
latable-0.412
 Deal-0.401
igsaw-0.396
Token You
Token ID921
Feature activation+9.19e-02

Pos logit contributions
 whispered+0.036
 said+0.035
 meant+0.033
 woke+0.033
 fell+0.030
Neg logit contributions
ric-0.055
latable-0.054
 unison-0.052
igsaw-0.051
pieces-0.047
Token can
Token ID460
Feature activation+1.16e-01

Pos logit contributions
 whispered+0.109
 said+0.100
l+0.099
chy+0.098
 woke+0.098
Neg logit contributions
 unison-0.147
ric-0.141
latable-0.139
 Deal-0.138
igsaw-0.132
Token buy
Token ID2822
Feature activation+1.61e-01

Pos logit contributions
 whispered+0.152
 said+0.147
 fell+0.140
 woke+0.138
chy+0.136
Neg logit contributions
 unison-0.176
ric-0.170
latable-0.169
igsaw-0.165
 Deal-0.162
Token something
Token ID1223
Feature activation+1.37e-01

Pos logit contributions
 whispered+0.245
chy+0.232
 woke+0.230
 fell+0.229
 said+0.226
Neg logit contributions
 unison-0.204
ric-0.198
latable-0.193
 Deal-0.184
igsaw-0.178
Token Everyone
Token ID11075
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.024
 said+0.024
 woke+0.021
 fell+0.021
 meant+0.020
Neg logit contributions
 unison-0.034
ric-0.034
latable-0.033
 Deal-0.033
igsaw-0.032
Token wanted
Token ID2227
Feature activation+1.24e-01

Pos logit contributions
chy+0.088
 whispered+0.082
l+0.081
 prick+0.080
 low+0.075
Neg logit contributions
 unison-0.203
ric-0.196
latable-0.196
 teammates-0.188
 yeah-0.188
Token to
Token ID284
Feature activation+1.30e-01

Pos logit contributions
 whispered+0.186
chy+0.181
 fell+0.172
l+0.172
 woke+0.169
Neg logit contributions
 unison-0.148
latable-0.144
ric-0.140
igsaw-0.133
 yeah-0.132
Token share
Token ID2648
Feature activation+1.65e-01

Pos logit contributions
 said+0.153
 whispered+0.149
 woke+0.135
 spark+0.133
 fell+0.132
Neg logit contributions
ric-0.248
latable-0.222
 unison-0.217
ifying-0.216
 Deal-0.215
Token the
Token ID262
Feature activation+1.12e-01

Pos logit contributions
 whispered+0.200
chy+0.192
 woke+0.184
 fell+0.183
 said+0.180
Neg logit contributions
 unison-0.262
ric-0.249
latable-0.245
 Deal-0.233
igsaw-0.232
Token treasure
Token ID14068
Feature activation+2.29e-01

Pos logit contributions
 whispered+0.182
 fell+0.172
chy+0.171
 said+0.169
l+0.165
Neg logit contributions
latable-0.120
 unison-0.118
igsaw-0.118
 yeah-0.110
ric-0.110
Token together
Token ID1978
Feature activation+1.37e-01

Pos logit contributions
 whispered+0.228
 woke+0.211
chy+0.203
 said+0.202
 fell+0.200
Neg logit contributions
 unison-0.402
latable-0.390
igsaw-0.384
ric-0.384
 Deal-0.365
Token.
Token ID13
Feature activation+2.88e-02

Pos logit contributions
 whispered+0.151
chy+0.140
 woke+0.140
l+0.137
 fell+0.132
Neg logit contributions
 unison-0.232
ric-0.210
latable-0.209
igsaw-0.208
 teammates-0.207
Token Now
Token ID2735
Feature activation+1.16e-01

Pos logit contributions
 whispered+0.035
 said+0.034
 woke+0.032
 fell+0.031
 meant+0.030
Neg logit contributions
 unison-0.047
ric-0.046
latable-0.045
 Deal-0.044
igsaw-0.043
Token,
Token ID11
Feature activation+1.01e-01

Pos logit contributions
 whispered+0.116
 said+0.103
chy+0.102
 woke+0.100
l+0.099
Neg logit contributions
 unison-0.209
latable-0.203
ric-0.202
 Deal-0.195
igsaw-0.193
Token the
Token ID262
Feature activation+1.01e-01

Pos logit contributions
 whispered+0.127
chy+0.116
 said+0.114
 woke+0.113
l+0.113
Neg logit contributions
 unison-0.154
ric-0.151
latable-0.145
 Deal-0.142
igsaw-0.139
Token They
Token ID1119
Feature activation+8.97e-02

Pos logit contributions
chy+0.019
 whispered+0.019
 woke+0.017
 meant+0.017
 prick+0.017
Neg logit contributions
 unison-0.017
 Deal-0.016
latable-0.016
ric-0.015
 yeah-0.015
Token paid
Token ID3432
Feature activation+1.45e-01

Pos logit contributions
chy+0.080
l+0.073
 prick+0.072
 low+0.068
 whispered+0.067
Neg logit contributions
 unison-0.162
latable-0.145
ric-0.141
 teammates-0.140
 yeah-0.136
Token him
Token ID683
Feature activation+1.55e-01

Pos logit contributions
 whispered+0.202
 woke+0.192
chy+0.190
 fell+0.184
 said+0.181
Neg logit contributions
 unison-0.200
ric-0.189
latable-0.187
 Deal-0.184
igsaw-0.176
Token with
Token ID351
Feature activation+1.20e-01

Pos logit contributions
 whispered+0.200
 woke+0.194
chy+0.182
 fell+0.182
 prick+0.174
Neg logit contributions
ric-0.218
 unison-0.215
latable-0.214
ap-0.201
 Deal-0.195
Token some
Token ID617
Feature activation+1.59e-01

Pos logit contributions
 whispered+0.176
 woke+0.165
chy+0.163
 said+0.162
 fell+0.161
Neg logit contributions
 unison-0.164
ric-0.155
latable-0.155
 Deal-0.146
igsaw-0.141
Token coins
Token ID10796
Feature activation+2.27e-01

Pos logit contributions
 whispered+0.208
chy+0.195
 woke+0.195
 fell+0.185
 said+0.179
Neg logit contributions
 unison-0.234
latable-0.226
ric-0.221
 Deal-0.219
 yeah-0.209
Token they
Token ID484
Feature activation+1.22e-01

Pos logit contributions
 whispered+0.207
 woke+0.195
chy+0.183
 said+0.176
 fell+0.174
Neg logit contributions
 unison-0.408
ric-0.406
latable-0.398
igsaw-0.377
ifying-0.373
Token had
Token ID550
Feature activation+1.01e-01

Pos logit contributions
 aisle+0.115
l+0.109
chy+0.107
 iv+0.106
 prick+0.104
Neg logit contributions
 unison-0.206
latable-0.181
ifying-0.180
 teammates-0.171
ric-0.171
Token.
Token ID13
Feature activation+1.89e-02

Pos logit contributions
chy+0.117
 woke+0.108
 whispered+0.108
 aisle+0.106
l+0.104
Neg logit contributions
 unison-0.155
ric-0.148
latable-0.141
 such-0.134
 gonna-0.132
Token
Token ID198
Feature activation+1.73e-02

Pos logit contributions
chy+0.025
 whispered+0.025
 woke+0.023
 fell+0.023
 prick+0.022
Neg logit contributions
 unison-0.028
latable-0.026
 Deal-0.026
ric-0.026
 yeah-0.024
Token
Token ID198
Feature activation+1.50e-02

Pos logit contributions
chy+0.026
 whispered+0.025
 meant+0.023
 woke+0.023
 prick+0.023
Neg logit contributions
 unison-0.022
ric-0.021
 Deal-0.020
latable-0.020
 teammates-0.018
Token hurried
Token ID31662
Feature activation+1.66e-01

Pos logit contributions
 whispered+0.073
chy+0.070
l+0.066
 woke+0.062
 meant+0.061
Neg logit contributions
 unison-0.186
latable-0.178
ric-0.176
igsaw-0.170
 Deal-0.170
Token away
Token ID1497
Feature activation+1.42e-01

Pos logit contributions
 whispered+0.173
 said+0.166
 woke+0.160
 fell+0.155
l+0.148
Neg logit contributions
 unison-0.308
ric-0.308
latable-0.290
 Deal-0.289
 yeah-0.273
Token with
Token ID351
Feature activation+1.13e-01

Pos logit contributions
chy+0.166
 whispered+0.164
 woke+0.157
 meant+0.151
l+0.148
Neg logit contributions
 unison-0.210
igsaw-0.200
latable-0.191
 teammates-0.190
ric-0.185
Token his
Token ID465
Feature activation+1.25e-01

Pos logit contributions
 whispered+0.109
 said+0.108
 fell+0.095
 woke+0.093
 meant+0.092
Neg logit contributions
ric-0.229
 unison-0.207
latable-0.207
 Deal-0.203
igsaw-0.196
Token borrowed
Token ID22546
Feature activation+1.85e-01

Pos logit contributions
 whispered+0.144
 said+0.135
 fell+0.127
 woke+0.127
chy+0.124
Neg logit contributions
 unison-0.210
ric-0.207
latable-0.203
 Deal-0.197
igsaw-0.193
Token hook
Token ID8011
Feature activation+2.27e-01

Pos logit contributions
 whispered+0.195
 said+0.183
 fell+0.175
 woke+0.172
l+0.170
Neg logit contributions
 unison-0.329
ric-0.328
 Deal-0.320
latable-0.316
igsaw-0.306
Token.
Token ID13
Feature activation+2.33e-02

Pos logit contributions
 whispered+0.215
 woke+0.208
chy+0.187
 meant+0.186
 said+0.183
Neg logit contributions
 unison-0.386
ric-0.368
latable-0.367
igsaw-0.364
 teammates-0.349
Token From
Token ID3574
Feature activation+7.62e-02

Pos logit contributions
 whispered+0.030
 said+0.029
 woke+0.028
 fell+0.028
chy+0.027
Neg logit contributions
 unison-0.036
ric-0.035
latable-0.034
 Deal-0.033
igsaw-0.032
Token that
Token ID326
Feature activation+9.80e-02

Pos logit contributions
 whispered+0.104
 said+0.102
 fell+0.093
 woke+0.091
l+0.090
Neg logit contributions
 unison-0.117
ric-0.115
 Deal-0.113
latable-0.111
igsaw-0.106
Token day
Token ID1110
Feature activation+1.37e-01

Pos logit contributions
 whispered+0.115
l+0.106
 iv+0.093
 meant+0.092
 shouted+0.090
Neg logit contributions
igsaw-0.150
 Deal-0.139
 yeah-0.139
ap-0.139
 Wed-0.138
Token forward
Token ID2651
Feature activation+1.37e-01

Pos logit contributions
 whispered+0.132
l+0.117
chy+0.116
 said+0.113
 prick+0.108
Neg logit contributions
 Deal-0.242
 unison-0.237
ap-0.232
ric-0.227
latable-0.226
Token should
Token ID815
Feature activation+1.08e-01

Pos logit contributions
 whispered+0.078
 aisle+0.068
chy+0.066
 woke+0.065
l+0.065
Neg logit contributions
 unison-0.190
ric-0.185
latable-0.184
 Deal-0.179
 yeah-0.173
Token not
Token ID407
Feature activation+1.05e-01

Pos logit contributions
 said+0.097
 hurt+0.085
 had+0.079
 fell+0.078
 whispered+0.071
Neg logit contributions
ifying-0.257
 unison-0.252
igsaw-0.241
latable-0.239
ric-0.233
Token have
Token ID423
Feature activation+1.24e-01

Pos logit contributions
 whispered+0.135
 said+0.134
 fell+0.126
 woke+0.125
 meant+0.123
Neg logit contributions
 unison-0.170
ric-0.164
latable-0.162
 Deal-0.159
igsaw-0.156
Token taken
Token ID2077
Feature activation+1.71e-01

Pos logit contributions
 whispered+0.129
 said+0.120
 woke+0.114
 fell+0.113
chy+0.111
Neg logit contributions
 unison-0.221
ric-0.216
latable-0.215
 Deal-0.209
igsaw-0.205
Token your
Token ID534
Feature activation+1.46e-01

Pos logit contributions
 whispered+0.239
 said+0.236
l+0.219
 fell+0.218
 woke+0.215
Neg logit contributions
 unison-0.251
latable-0.247
ric-0.243
 Deal-0.229
igsaw-0.219
Token sack
Token ID23704
Feature activation+2.26e-01

Pos logit contributions
 whispered+0.201
 said+0.188
 woke+0.185
 fell+0.181
chy+0.181
Neg logit contributions
 unison-0.209
ric-0.200
latable-0.200
 Deal-0.194
igsaw-0.192
Token.
Token ID13
Feature activation+4.05e-02

Pos logit contributions
 whispered+0.218
 woke+0.189
 said+0.183
 spoke+0.177
 meant+0.172
Neg logit contributions
 unison-0.399
igsaw-0.389
latable-0.386
 teammates-0.376
 Deal-0.375
Token I
Token ID314
Feature activation+1.07e-01

Pos logit contributions
 whispered+0.052
 said+0.052
 woke+0.050
 fell+0.049
 meant+0.049
Neg logit contributions
ric-0.065
 unison-0.064
latable-0.062
pieces-0.056
igsaw-0.055
Token was
Token ID373
Feature activation+1.21e-01

Pos logit contributions
 whispered+0.100
 woke+0.086
chy+0.086
 said+0.086
 aisle+0.085
Neg logit contributions
 unison-0.193
ric-0.189
latable-0.187
 Deal-0.182
 yeah-0.175
Token curious
Token ID11040
Feature activation+1.47e-01

Pos logit contributions
 said+0.090
 whispered+0.085
 hurt+0.078
 sm+0.070
 scared+0.070
Neg logit contributions
 unison-0.295
igsaw-0.283
latable-0.275
ric-0.266
 Deal-0.261
Token.
Token ID13
Feature activation+4.27e-02

Pos logit contributions
 whispered+0.136
chy+0.115
 said+0.112
l+0.110
 fell+0.110
Neg logit contributions
 unison-0.264
latable-0.250
 Deal-0.249
ric-0.248
 yeah-0.237
Token'm
Token ID1101
Feature activation+1.15e-01

Pos logit contributions
 aisle+0.165
 whispered+0.157
 low+0.148
l+0.147
 floor+0.143
Neg logit contributions
 unison-0.109
ric-0.109
 Deal-0.103
latable-0.102
 yeah-0.094
Token sorry
Token ID7926
Feature activation+1.29e-01

Pos logit contributions
 whispered+0.163
 said+0.161
 fell+0.146
chy+0.140
 meant+0.140
Neg logit contributions
 unison-0.181
latable-0.168
igsaw-0.168
ric-0.166
ifying-0.155
Token I
Token ID314
Feature activation+1.10e-01

Pos logit contributions
 said+0.127
 whispered+0.126
 fell+0.119
l+0.116
chy+0.116
Neg logit contributions
 unison-0.245
latable-0.239
ric-0.235
igsaw-0.230
 Deal-0.216
Token dropped
Token ID5710
Feature activation+1.74e-01

Pos logit contributions
 aisle+0.126
 low+0.109
 floor+0.100
 man+0.096
 whispered+0.094
Neg logit contributions
ric-0.168
 unison-0.159
 hey-0.157
latable-0.156
 disl-0.154
Token the
Token ID262
Feature activation+1.21e-01

Pos logit contributions
 whispered+0.235
 said+0.215
 woke+0.214
chy+0.212
 fell+0.210
Neg logit contributions
 unison-0.249
ric-0.246
latable-0.238
 Deal-0.234
igsaw-0.228
Token bag
Token ID6131
Feature activation+2.26e-01

Pos logit contributions
 whispered+0.193
 said+0.176
 woke+0.175
 fell+0.172
chy+0.171
Neg logit contributions
ric-0.143
 unison-0.142
latable-0.141
 Deal-0.136
igsaw-0.131
Token and
Token ID290
Feature activation+1.18e-01

Pos logit contributions
 whispered+0.293
 spoke+0.275
 buzz+0.268
 woke+0.261
 breathed+0.255
Neg logit contributions
ap-0.275
ifying-0.271
 unison-0.259
 such-0.256
 our-0.255
Token the
Token ID262
Feature activation+1.17e-01

Pos logit contributions
 whispered+0.134
 said+0.132
 fell+0.127
 woke+0.124
 needed+0.120
Neg logit contributions
 unison-0.214
latable-0.207
ric-0.201
igsaw-0.197
 Deal-0.196
Token gum
Token ID27142
Feature activation+2.10e-01

Pos logit contributions
 whispered+0.163
 said+0.146
 woke+0.145
 fell+0.141
chy+0.141
Neg logit contributions
ric-0.164
 unison-0.164
latable-0.155
 Deal-0.155
igsaw-0.146
Token."
Token ID526
Feature activation+3.41e-02

Pos logit contributions
 whispered+0.250
 spoke+0.230
 meant+0.211
 woke+0.211
 prick+0.207
Neg logit contributions
 teammates-0.291
 unison-0.277
ap-0.273
 goalie-0.268
 our-0.265
Token
Token ID198
Feature activation+1.83e-02

Pos logit contributions
 whispered+0.029
 said+0.027
 woke+0.025
 fell+0.025
l+0.024
Neg logit contributions
 unison-0.068
ric-0.067
latable-0.066
 Deal-0.064
igsaw-0.063
Token okay
Token ID8788
Feature activation+1.11e-01

Pos logit contributions
 whispered+0.144
 said+0.138
 meant+0.133
chy+0.132
 fell+0.132
Neg logit contributions
 unison-0.150
ric-0.147
latable-0.145
igsaw-0.137
 Deal-0.136
Token if
Token ID611
Feature activation+1.11e-01

Pos logit contributions
 said+0.064
 fell+0.057
 woke+0.057
 whispered+0.055
 needed+0.054
Neg logit contributions
ric-0.260
 unison-0.257
latable-0.253
 Deal-0.240
ifying-0.238
Token you
Token ID345
Feature activation+1.13e-01

Pos logit contributions
 whispered+0.185
 said+0.177
 woke+0.172
 fell+0.172
chy+0.169
Neg logit contributions
 unison-0.129
ric-0.126
latable-0.124
 Deal-0.118
igsaw-0.114
Token keep
Token ID1394
Feature activation+1.53e-01

Pos logit contributions
 whispered+0.165
 said+0.155
 woke+0.152
 fell+0.150
l+0.150
Neg logit contributions
 unison-0.153
ric-0.147
latable-0.145
 Deal-0.140
igsaw-0.136
Token the
Token ID262
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.189
 said+0.184
 fell+0.161
 meant+0.158
 needed+0.156
Neg logit contributions
 unison-0.258
latable-0.252
ric-0.247
 Deal-0.238
igsaw-0.229
Token treasure
Token ID14068
Feature activation+2.26e-01

Pos logit contributions
 whispered+0.183
 said+0.172
 fell+0.170
chy+0.169
l+0.167
Neg logit contributions
 unison-0.116
latable-0.112
ric-0.110
 Deal-0.108
igsaw-0.108
Token.
Token ID13
Feature activation+3.64e-02

Pos logit contributions
 whispered+0.244
 woke+0.222
 said+0.218
 fell+0.209
l+0.209
Neg logit contributions
 unison-0.370
igsaw-0.355
latable-0.352
ric-0.351
 Deal-0.344
Token But
Token ID887
Feature activation+7.78e-02

Pos logit contributions
 said+0.042
 whispered+0.041
 meant+0.039
 needed+0.037
 woke+0.036
Neg logit contributions
latable-0.057
ric-0.056
 unison-0.055
igsaw-0.054
pieces-0.050
Token if
Token ID611
Feature activation+1.15e-01

Pos logit contributions
 whispered+0.105
 said+0.103
 woke+0.096
 fell+0.096
 meant+0.095
Neg logit contributions
 unison-0.116
latable-0.113
ric-0.111
igsaw-0.106
 Deal-0.105
Token you
Token ID345
Feature activation+1.15e-01

Pos logit contributions
 said+0.165
 whispered+0.163
 fell+0.157
 woke+0.154
 needed+0.152
Neg logit contributions
ric-0.170
 unison-0.166
latable-0.164
 Deal-0.153
igsaw-0.148
Token don
Token ID836
Feature activation+1.14e-01

Pos logit contributions
 whispered+0.161
 said+0.152
 woke+0.147
 fell+0.146
chy+0.145
Neg logit contributions
 unison-0.163
ric-0.158
latable-0.156
 Deal-0.151
igsaw-0.147
Token okay
Token ID8788
Feature activation+1.11e-01

Pos logit contributions
 whispered+0.144
 said+0.138
 meant+0.133
chy+0.132
 fell+0.132
Neg logit contributions
 unison-0.150
ric-0.147
latable-0.145
igsaw-0.137
 Deal-0.136
Token if
Token ID611
Feature activation+1.11e-01

Pos logit contributions
 said+0.064
 fell+0.057
 woke+0.057
 whispered+0.055
 needed+0.054
Neg logit contributions
ric-0.260
 unison-0.257
latable-0.253
 Deal-0.240
ifying-0.238
Token you
Token ID345
Feature activation+1.13e-01

Pos logit contributions
 whispered+0.185
 said+0.177
 woke+0.172
 fell+0.172
chy+0.169
Neg logit contributions
 unison-0.129
ric-0.126
latable-0.124
 Deal-0.118
igsaw-0.114
Token keep
Token ID1394
Feature activation+1.53e-01

Pos logit contributions
 whispered+0.165
 said+0.155
 woke+0.152
 fell+0.150
l+0.150
Neg logit contributions
 unison-0.153
ric-0.147
latable-0.145
 Deal-0.140
igsaw-0.136
Token the
Token ID262
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.189
 said+0.184
 fell+0.161
 meant+0.158
 needed+0.156
Neg logit contributions
 unison-0.258
latable-0.252
ric-0.247
 Deal-0.238
igsaw-0.229
Token treasure
Token ID14068
Feature activation+2.26e-01

Pos logit contributions
 whispered+0.183
 said+0.172
 fell+0.170
chy+0.169
l+0.167
Neg logit contributions
 unison-0.116
latable-0.112
ric-0.110
 Deal-0.108
igsaw-0.108
Token.
Token ID13
Feature activation+3.64e-02

Pos logit contributions
 whispered+0.244
 woke+0.222
 said+0.218
 fell+0.209
l+0.209
Neg logit contributions
 unison-0.370
igsaw-0.355
latable-0.352
ric-0.351
 Deal-0.344
Token But
Token ID887
Feature activation+7.78e-02

Pos logit contributions
 said+0.042
 whispered+0.041
 meant+0.039
 needed+0.037
 woke+0.036
Neg logit contributions
latable-0.057
ric-0.056
 unison-0.055
igsaw-0.054
pieces-0.050
Token if
Token ID611
Feature activation+1.15e-01

Pos logit contributions
 whispered+0.105
 said+0.103
 woke+0.096
 fell+0.096
 meant+0.095
Neg logit contributions
 unison-0.116
latable-0.113
ric-0.111
igsaw-0.106
 Deal-0.105
Token you
Token ID345
Feature activation+1.15e-01

Pos logit contributions
 said+0.165
 whispered+0.163
 fell+0.157
 woke+0.154
 needed+0.152
Neg logit contributions
ric-0.170
 unison-0.166
latable-0.164
 Deal-0.153
igsaw-0.148
Token don
Token ID836
Feature activation+1.14e-01

Pos logit contributions
 whispered+0.161
 said+0.152
 woke+0.147
 fell+0.146
chy+0.145
Neg logit contributions
 unison-0.163
ric-0.158
latable-0.156
 Deal-0.151
igsaw-0.147
Token They
Token ID1119
Feature activation+8.83e-02

Pos logit contributions
 whispered+0.015
 said+0.015
 woke+0.014
 fell+0.013
 meant+0.013
Neg logit contributions
 unison-0.020
ric-0.020
latable-0.020
igsaw-0.019
 Deal-0.019
Token do
Token ID466
Feature activation+1.16e-01

Pos logit contributions
 whispered+0.121
l+0.113
 woke+0.112
 said+0.111
chy+0.110
Neg logit contributions
 unison-0.120
 Deal-0.115
latable-0.115
ric-0.114
 hey-0.103
Token not
Token ID407
Feature activation+1.01e-01

Pos logit contributions
 whispered+0.135
 said+0.131
 fell+0.125
chy+0.123
 woke+0.122
Neg logit contributions
 unison-0.200
latable-0.199
ric-0.190
igsaw-0.187
ifying-0.183
Token want
Token ID765
Feature activation+1.26e-01

Pos logit contributions
 whispered+0.159
l+0.158
 aisle+0.158
 woke+0.149
 said+0.149
Neg logit contributions
 unison-0.100
ric-0.099
latable-0.097
 Deal-0.096
ap-0.091
Token a
Token ID257
Feature activation+1.17e-01

Pos logit contributions
 whispered+0.186
 woke+0.171
l+0.171
 said+0.169
chy+0.169
Neg logit contributions
 unison-0.162
latable-0.157
ric-0.156
 Deal-0.145
igsaw-0.144
Token haircut
Token ID45548
Feature activation+2.25e-01

Pos logit contributions
 whispered+0.215
 meant+0.204
 said+0.203
chy+0.203
 woke+0.198
Neg logit contributions
 unison-0.096
ric-0.094
 yeah-0.093
latable-0.092
 Deal-0.092
Token.
Token ID13
Feature activation+2.02e-02

Pos logit contributions
 whispered+0.201
 woke+0.189
chy+0.170
 prick+0.170
l+0.168
Neg logit contributions
 unison-0.407
ric-0.388
latable-0.383
 yeah-0.376
ap-0.370
Token
Token ID198
Feature activation+1.80e-02

Pos logit contributions
 whispered+0.023
 said+0.022
 woke+0.020
 fell+0.020
 meant+0.020
Neg logit contributions
 unison-0.034
ric-0.034
latable-0.033
 Deal-0.032
igsaw-0.032
Token
Token ID198
Feature activation+1.51e-02

Pos logit contributions
chy+0.026
 whispered+0.025
 woke+0.024
 prick+0.023
 meant+0.023
Neg logit contributions
 unison-0.024
 Deal-0.023
ric-0.021
latable-0.021
ap-0.020
TokenThey
Token ID2990
Feature activation+9.33e-02

Pos logit contributions
 whispered+0.017
 said+0.016
 woke+0.016
 fell+0.015
chy+0.015
Neg logit contributions
 unison-0.025
ric-0.024
latable-0.024
 Deal-0.024
igsaw-0.023
Token see
Token ID766
Feature activation+1.38e-01

Pos logit contributions
 whispered+0.135
 said+0.126
l+0.124
 woke+0.124
chy+0.124
Neg logit contributions
 unison-0.124
ric-0.118
latable-0.117
 Deal-0.116
igsaw-0.106
Token friends
Token ID2460
Feature activation+1.41e-01

Pos logit contributions
 whispered+0.132
 said+0.128
 meant+0.121
 fell+0.117
 low+0.114
Neg logit contributions
 unison-0.174
ric-0.173
latable-0.172
igsaw-0.165
 Deal-0.163
Token and
Token ID290
Feature activation+9.98e-02

Pos logit contributions
 whispered+0.121
 said+0.106
chy+0.106
 woke+0.104
l+0.103
Neg logit contributions
 unison-0.279
ric-0.264
latable-0.264
 Deal-0.252
igsaw-0.249
Token shared
Token ID4888
Feature activation+1.50e-01

Pos logit contributions
 whispered+0.112
l+0.105
chy+0.105
 woke+0.099
 said+0.098
Neg logit contributions
 unison-0.160
ric-0.154
latable-0.150
 yeah-0.143
 Deal-0.141
Token the
Token ID262
Feature activation+1.05e-01

Pos logit contributions
 whispered+0.238
chy+0.235
 woke+0.226
 fell+0.226
 meant+0.217
Neg logit contributions
 unison-0.185
ric-0.167
latable-0.167
igsaw-0.151
 Deal-0.149
Token pretty
Token ID2495
Feature activation+1.60e-01

Pos logit contributions
 whispered+0.128
 said+0.116
 fell+0.112
 meant+0.108
 woke+0.107
Neg logit contributions
latable-0.163
igsaw-0.158
ric-0.157
 Deal-0.151
 unison-0.150
Token rocks
Token ID12586
Feature activation+2.25e-01

Pos logit contributions
 whispered+0.171
 said+0.157
 woke+0.151
 fell+0.150
chy+0.148
Neg logit contributions
 unison-0.280
ric-0.275
latable-0.272
 Deal-0.263
igsaw-0.259
Token from
Token ID422
Feature activation+1.23e-01

Pos logit contributions
 whispered+0.191
 said+0.173
 woke+0.163
 fell+0.162
chy+0.160
Neg logit contributions
 unison-0.442
ric-0.433
latable-0.429
 Deal-0.419
igsaw-0.409
Token the
Token ID262
Feature activation+1.07e-01

Pos logit contributions
 whispered+0.171
 woke+0.161
 said+0.157
 fell+0.156
chy+0.155
Neg logit contributions
ric-0.175
 unison-0.172
latable-0.163
 Deal-0.149
 hey-0.144
Token mine
Token ID6164
Feature activation+1.77e-01

Pos logit contributions
 whispered+0.138
 said+0.125
l+0.124
 meant+0.123
 fell+0.120
Neg logit contributions
latable-0.147
 Deal-0.145
ric-0.143
 unison-0.143
 yeah-0.137
Token.
Token ID13
Feature activation+2.12e-02

Pos logit contributions
 whispered+0.155
 woke+0.147
 meant+0.137
chy+0.135
 said+0.133
Neg logit contributions
 unison-0.323
ric-0.314
 teammates-0.305
latable-0.296
igsaw-0.295
Token They
Token ID1119
Feature activation+9.62e-02

Pos logit contributions
 whispered+0.034
chy+0.032
l+0.031
 woke+0.031
 fell+0.031
Neg logit contributions
 unison-0.026
ric-0.025
latable-0.025
 Deal-0.023
igsaw-0.023
Token!
Token ID0
Feature activation+3.59e-02

Pos logit contributions
 whispered+0.240
 said+0.225
 woke+0.216
 fell+0.215
chy+0.213
Neg logit contributions
 unison-0.337
ric-0.327
latable-0.325
 Deal-0.315
igsaw-0.308
Token You
Token ID921
Feature activation+9.44e-02

Pos logit contributions
 whispered+0.056
 said+0.054
 woke+0.053
 fell+0.052
chy+0.051
Neg logit contributions
 unison-0.044
ric-0.043
latable-0.042
igsaw-0.039
 Deal-0.039
Token cannot
Token ID2314
Feature activation+1.34e-01

Pos logit contributions
 whispered+0.115
 said+0.106
 woke+0.103
l+0.102
chy+0.102
Neg logit contributions
 unison-0.148
ric-0.145
latable-0.143
 Deal-0.139
igsaw-0.134
Token take
Token ID1011
Feature activation+1.67e-01

Pos logit contributions
 whispered+0.165
 said+0.152
l+0.147
 meant+0.144
chy+0.144
Neg logit contributions
 unison-0.207
ric-0.203
latable-0.202
 Deal-0.196
igsaw-0.183
Token my
Token ID616
Feature activation+1.44e-01

Pos logit contributions
 whispered+0.262
chy+0.250
 said+0.240
 woke+0.236
 aisle+0.235
Neg logit contributions
ric-0.197
 unison-0.195
 Deal-0.184
latable-0.179
 our-0.175
Token corn
Token ID11676
Feature activation+2.25e-01

Pos logit contributions
 whispered+0.191
 said+0.176
 woke+0.172
 fell+0.170
chy+0.169
Neg logit contributions
 unison-0.209
ric-0.208
latable-0.198
 Deal-0.197
 yeah-0.184
Token!"
Token ID2474
Feature activation+4.48e-02

Pos logit contributions
 whispered+0.218
 said+0.202
 fell+0.192
 woke+0.192
chy+0.190
Neg logit contributions
 unison-0.416
ric-0.404
latable-0.403
 Deal-0.392
igsaw-0.383
Token
Token ID198
Feature activation+2.17e-02

Pos logit contributions
 whispered+0.050
chy+0.048
 woke+0.045
 fell+0.044
 said+0.043
Neg logit contributions
 unison-0.073
 Deal-0.070
latable-0.069
ric-0.069
igsaw-0.068
Token
Token ID198
Feature activation+1.89e-02

Pos logit contributions
 whispered+0.021
 said+0.019
chy+0.018
 woke+0.018
 fell+0.018
Neg logit contributions
 unison-0.040
ric-0.039
latable-0.038
 Deal-0.038
igsaw-0.037
TokenTom
Token ID13787
Feature activation+1.42e-01

Pos logit contributions
 whispered+0.019
 said+0.018
 fell+0.017
l+0.017
 woke+0.017
Neg logit contributions
ric-0.035
 unison-0.035
latable-0.034
 Deal-0.033
igsaw-0.032
Token and
Token ID290
Feature activation+1.03e-01

Pos logit contributions
 whispered+0.122
 said+0.108
 woke+0.105
l+0.104
chy+0.103
Neg logit contributions
 unison-0.271
ric-0.267
latable-0.265
 Deal-0.261
igsaw-0.247
Token He
Token ID679
Feature activation+9.21e-02

Pos logit contributions
 whispered+0.021
chy+0.020
 said+0.019
 fell+0.019
 meant+0.019
Neg logit contributions
 unison-0.018
 Deal-0.017
latable-0.016
ric-0.016
igsaw-0.016
Token takes
Token ID2753
Feature activation+1.50e-01

Pos logit contributions
 whispered+0.092
 said+0.086
 woke+0.082
 fell+0.081
l+0.079
Neg logit contributions
 unison-0.168
latable-0.164
ric-0.163
 Deal-0.159
igsaw-0.158
Token his
Token ID465
Feature activation+1.28e-01

Pos logit contributions
 whispered+0.237
chy+0.224
 woke+0.214
 said+0.214
 needed+0.213
Neg logit contributions
 unison-0.174
 Deal-0.159
latable-0.156
igsaw-0.149
ric-0.147
Token tower
Token ID10580
Feature activation+1.99e-01

Pos logit contributions
 whispered+0.155
 said+0.142
 woke+0.139
chy+0.136
 fell+0.136
Neg logit contributions
 unison-0.206
ric-0.202
latable-0.197
 Deal-0.194
igsaw-0.190
Token of
Token ID286
Feature activation+1.14e-01

Pos logit contributions
 whispered+0.215
 woke+0.197
 said+0.188
 meant+0.184
chy+0.183
Neg logit contributions
ric-0.318
 unison-0.317
igsaw-0.316
latable-0.311
ap-0.294
Token coins
Token ID10796
Feature activation+2.24e-01

Pos logit contributions
 whispered+0.146
 woke+0.138
chy+0.137
 said+0.134
l+0.133
Neg logit contributions
 unison-0.170
ric-0.167
latable-0.160
 Deal-0.155
igsaw-0.152
Token and
Token ID290
Feature activation+1.06e-01

Pos logit contributions
 whispered+0.205
 woke+0.191
chy+0.184
 said+0.179
 meant+0.173
Neg logit contributions
 unison-0.402
ric-0.398
latable-0.390
igsaw-0.376
 Deal-0.368
Token throws
Token ID12542
Feature activation+1.62e-01

Pos logit contributions
 whispered+0.121
 said+0.115
 fell+0.108
 woke+0.106
 meant+0.100
Neg logit contributions
latable-0.187
 unison-0.187
ric-0.184
 Deal-0.181
igsaw-0.179
Token it
Token ID340
Feature activation+1.64e-01

Pos logit contributions
 whispered+0.246
chy+0.230
 said+0.225
 woke+0.225
 fell+0.222
Neg logit contributions
 unison-0.210
ric-0.200
latable-0.194
 Deal-0.185
igsaw-0.183
Token at
Token ID379
Feature activation+1.11e-01

Pos logit contributions
 whispered+0.251
 woke+0.237
 meant+0.234
 aisle+0.225
 said+0.225
Neg logit contributions
ap-0.171
ric-0.167
 teammates-0.163
 unison-0.158
 our-0.157
Token the
Token ID262
Feature activation+1.04e-01

Pos logit contributions
 whispered+0.181
chy+0.170
 meant+0.167
l+0.163
 woke+0.162
Neg logit contributions
 unison-0.135
ric-0.119
latable-0.118
 Deal-0.114
 teammates-0.110
Token much
Token ID881
Feature activation+1.21e-01

Pos logit contributions
 said+0.071
l+0.070
 whispered+0.070
 fell+0.066
 needed+0.063
Neg logit contributions
 unison-0.192
 Deal-0.186
ric-0.185
latable-0.179
igsaw-0.167
Token he
Token ID339
Feature activation+1.14e-01

Pos logit contributions
 whispered+0.118
 said+0.110
 woke+0.103
 fell+0.103
 meant+0.101
Neg logit contributions
 unison-0.225
ric-0.221
latable-0.217
 Deal-0.213
igsaw-0.207
Token loved
Token ID6151
Feature activation+1.18e-01

Pos logit contributions
l+0.098
 aisle+0.096
 whispered+0.089
 prick+0.084
 low+0.082
Neg logit contributions
latable-0.189
 unison-0.189
ric-0.179
 gonna-0.170
 teammates-0.169
Token his
Token ID465
Feature activation+1.35e-01

Pos logit contributions
 whispered+0.177
 woke+0.162
 fell+0.161
chy+0.160
 said+0.160
Neg logit contributions
ric-0.150
 unison-0.149
latable-0.147
igsaw-0.132
 yeah-0.127
Token funny
Token ID8258
Feature activation+1.67e-01

Pos logit contributions
 whispered+0.188
 said+0.173
 woke+0.172
 fell+0.171
chy+0.169
Neg logit contributions
 unison-0.187
latable-0.186
ric-0.183
igsaw-0.175
 Deal-0.170
Token suit
Token ID6050
Feature activation+2.24e-01

Pos logit contributions
 whispered+0.218
 said+0.203
chy+0.196
 woke+0.196
 fell+0.196
Neg logit contributions
 unison-0.249
ric-0.244
latable-0.241
 Deal-0.230
igsaw-0.226
Token and
Token ID290
Feature activation+1.08e-01

Pos logit contributions
 whispered+0.242
 prick+0.216
 woke+0.209
 buzz+0.205
l+0.203
Neg logit contributions
 unison-0.342
latable-0.338
ric-0.336
igsaw-0.333
 yeah-0.313
Token how
Token ID703
Feature activation+9.71e-02

Pos logit contributions
 whispered+0.127
 said+0.122
 woke+0.114
 fell+0.113
 meant+0.111
Neg logit contributions
 unison-0.184
latable-0.179
 Deal-0.179
ric-0.179
igsaw-0.173
Token much
Token ID881
Feature activation+1.27e-01

Pos logit contributions
 said+0.075
 whispered+0.074
l+0.070
 fell+0.070
 needed+0.066
Neg logit contributions
 unison-0.211
 Deal-0.202
ric-0.200
latable-0.200
igsaw-0.190
Token fun
Token ID1257
Feature activation+1.46e-01

Pos logit contributions
 whispered+0.126
 said+0.116
 woke+0.111
 fell+0.110
chy+0.109
Neg logit contributions
 unison-0.229
ric-0.224
latable-0.222
 Deal-0.216
igsaw-0.212
Token he
Token ID339
Feature activation+1.19e-01

Pos logit contributions
 whispered+0.115
 said+0.113
 fell+0.105
 woke+0.103
 meant+0.101
Neg logit contributions
 unison-0.303
ric-0.297
 Deal-0.297
latable-0.290
igsaw-0.276
Token"
Token ID1
Feature activation+7.03e-02

Pos logit contributions
 whispered+0.025
 said+0.024
 woke+0.023
 fell+0.022
l+0.022
Neg logit contributions
ric-0.030
 unison-0.030
latable-0.029
 Deal-0.028
igsaw-0.028
TokenLet
Token ID5756
Feature activation+1.19e-01

Pos logit contributions
 whispered+0.095
chy+0.093
 fell+0.089
l+0.087
 said+0.086
Neg logit contributions
 unison-0.108
ric-0.100
latable-0.099
 Deal-0.095
ifying-0.094
Token's
Token ID338
Feature activation+1.07e-01

Pos logit contributions
 said+0.102
 whispered+0.100
 woke+0.092
 fell+0.086
 meant+0.085
Neg logit contributions
ric-0.250
 unison-0.245
latable-0.237
igsaw-0.233
 Deal-0.233
Token replace
Token ID6330
Feature activation+1.68e-01

Pos logit contributions
 whispered+0.112
 said+0.110
 fell+0.107
 tree+0.101
 woke+0.101
Neg logit contributions
igsaw-0.199
 unison-0.193
 Deal-0.191
latable-0.188
ric-0.181
Token the
Token ID262
Feature activation+1.13e-01

Pos logit contributions
 whispered+0.203
 said+0.197
l+0.177
 meant+0.172
 man+0.170
Neg logit contributions
 unison-0.279
 Deal-0.278
latable-0.266
igsaw-0.263
ric-0.260
Token rocks
Token ID12586
Feature activation+2.24e-01

Pos logit contributions
 whispered+0.157
 said+0.146
 woke+0.145
chy+0.144
 fell+0.138
Neg logit contributions
ric-0.158
 unison-0.153
latable-0.147
 yeah-0.135
igsaw-0.135
Token at
Token ID379
Feature activation+1.17e-01

Pos logit contributions
 whispered+0.194
 said+0.176
 woke+0.166
 fell+0.165
chy+0.162
Neg logit contributions
 unison-0.436
ric-0.426
latable-0.423
 Deal-0.413
igsaw-0.403
Token the
Token ID262
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.183
l+0.177
chy+0.175
 woke+0.173
 spoke+0.166
Neg logit contributions
ric-0.153
 unison-0.130
 our-0.128
latable-0.122
 least-0.116
Token bottom
Token ID4220
Feature activation+1.72e-01

Pos logit contributions
 whispered+0.164
 said+0.152
 woke+0.145
 meant+0.144
chy+0.142
Neg logit contributions
ric-0.145
 unison-0.142
latable-0.135
 hey-0.128
 yeah-0.121
Token of
Token ID286
Feature activation+1.08e-01

Pos logit contributions
 whispered+0.207
 woke+0.190
chy+0.188
 said+0.184
 fell+0.181
Neg logit contributions
 unison-0.270
ric-0.262
latable-0.258
igsaw-0.250
 Deal-0.242
Token the
Token ID262
Feature activation+1.11e-01

Pos logit contributions
 whispered+0.134
 said+0.125
 woke+0.122
 fell+0.121
chy+0.120
Neg logit contributions
 unison-0.170
ric-0.166
latable-0.163
 Deal-0.157
igsaw-0.153
Token fast
Token ID3049
Feature activation+1.60e-01

Pos logit contributions
 whispered+0.239
 woke+0.223
chy+0.219
 fell+0.214
 said+0.210
Neg logit contributions
 unison-0.245
ric-0.242
 our-0.229
ifying-0.224
latable-0.223
Token.
Token ID13
Feature activation+2.91e-02

Pos logit contributions
 whispered+0.160
chy+0.150
 fell+0.139
 said+0.138
 woke+0.138
Neg logit contributions
 unison-0.281
ric-0.268
latable-0.256
 Deal-0.252
ifying-0.248
Token I
Token ID314
Feature activation+9.84e-02

Pos logit contributions
 whispered+0.039
 said+0.037
 meant+0.035
 woke+0.035
 fell+0.034
Neg logit contributions
ric-0.042
latable-0.041
 unison-0.041
igsaw-0.040
 yeah-0.036
Token put
Token ID1234
Feature activation+1.69e-01

Pos logit contributions
 whispered+0.130
 said+0.119
 woke+0.118
l+0.118
chy+0.118
Neg logit contributions
 unison-0.140
ric-0.137
latable-0.133
 Deal-0.130
 yeah-0.122
Token the
Token ID262
Feature activation+1.13e-01

Pos logit contributions
 whispered+0.242
 said+0.227
 woke+0.223
 fell+0.220
chy+0.220
Neg logit contributions
 unison-0.232
ric-0.225
latable-0.222
 Deal-0.215
igsaw-0.208
Token rope
Token ID17182
Feature activation+2.23e-01

Pos logit contributions
 whispered+0.147
 said+0.139
 woke+0.134
 fell+0.134
chy+0.132
Neg logit contributions
 unison-0.172
ric-0.167
latable-0.166
 Deal-0.159
igsaw-0.156
Token on
Token ID319
Feature activation+1.45e-01

Pos logit contributions
 whispered+0.226
 said+0.204
 woke+0.201
 meant+0.193
 fell+0.192
Neg logit contributions
 unison-0.389
ric-0.387
latable-0.379
 Deal-0.364
igsaw-0.363
Token the
Token ID262
Feature activation+1.07e-01

Pos logit contributions
 whispered+0.234
chy+0.216
 said+0.215
 woke+0.215
 fell+0.214
Neg logit contributions
 unison-0.181
ric-0.165
latable-0.161
 Deal-0.158
igsaw-0.155
Token bike
Token ID7161
Feature activation+2.01e-01

Pos logit contributions
 whispered+0.122
 said+0.110
 meant+0.109
 woke+0.106
 fell+0.103
Neg logit contributions
 unison-0.183
ric-0.176
latable-0.172
 Deal-0.169
igsaw-0.160
Token to
Token ID284
Feature activation+1.32e-01

Pos logit contributions
 whispered+0.232
 woke+0.211
 meant+0.209
 spoke+0.208
 prick+0.208
Neg logit contributions
ric-0.311
 unison-0.297
ap-0.286
ifying-0.282
igsaw-0.278
Token see
Token ID766
Feature activation+1.44e-01

Pos logit contributions
 whispered+0.186
chy+0.173
 said+0.173
 woke+0.171
 fell+0.170
Neg logit contributions
 unison-0.185
ric-0.178
latable-0.173
 Deal-0.169
igsaw-0.162
Token bear
Token ID6842
Feature activation+1.74e-01

Pos logit contributions
 whispered+0.107
 meant+0.097
 fell+0.097
 spoke+0.095
 said+0.094
Neg logit contributions
 Deal-0.090
 unison-0.083
ric-0.083
latable-0.080
 hey-0.074
Token did
Token ID750
Feature activation+1.06e-01

Pos logit contributions
 aisle+0.186
chy+0.177
 meant+0.163
l+0.162
 week+0.159
Neg logit contributions
 unison-0.275
latable-0.238
 teammates-0.233
 hey-0.233
 yeah-0.229
Token not
Token ID407
Feature activation+9.90e-02

Pos logit contributions
 fell+0.087
 said+0.083
 whispered+0.081
 low+0.076
 hurt+0.075
Neg logit contributions
igsaw-0.241
ric-0.234
 unison-0.225
latable-0.222
ifying-0.220
Token like
Token ID588
Feature activation+1.17e-01

Pos logit contributions
 whispered+0.159
 aisle+0.152
 said+0.150
chy+0.149
l+0.148
Neg logit contributions
 unison-0.104
latable-0.101
 Deal-0.097
ric-0.095
 hey-0.092
Token the
Token ID262
Feature activation+1.09e-01

Pos logit contributions
 whispered+0.165
 said+0.148
chy+0.147
 fell+0.144
 meant+0.142
Neg logit contributions
ric-0.161
 unison-0.159
latable-0.159
igsaw-0.142
 hey-0.142
Token broom
Token ID47085
Feature activation+2.23e-01

Pos logit contributions
 whispered+0.145
 fell+0.132
 said+0.128
 spoke+0.126
 woke+0.125
Neg logit contributions
ric-0.149
 Deal-0.144
latable-0.143
 unison-0.140
 yeah-0.138
Token.
Token ID13
Feature activation+2.90e-02

Pos logit contributions
 whispered+0.228
 aisle+0.196
mail+0.190
 prick+0.180
l+0.178
Neg logit contributions
 unison-0.373
ric-0.349
latable-0.342
ifying-0.326
ap-0.321
Token It
Token ID632
Feature activation+1.25e-01

Pos logit contributions
 whispered+0.041
 said+0.038
chy+0.038
l+0.037
 woke+0.037
Neg logit contributions
 unison-0.040
ric-0.039
latable-0.039
 Deal-0.039
igsaw-0.036
Token ran
Token ID4966
Feature activation+1.64e-01

Pos logit contributions
 aisle+0.112
 whispered+0.103
l+0.096
books+0.088
 man+0.085
Neg logit contributions
 unison-0.212
latable-0.207
ric-0.196
 Deal-0.181
ifying-0.180
Token to
Token ID284
Feature activation+1.34e-01

Pos logit contributions
 whispered+0.201
 said+0.182
 woke+0.177
chy+0.176
 meant+0.174
Neg logit contributions
 unison-0.247
latable-0.244
ric-0.233
 Deal-0.227
 hey-0.221
Token the
Token ID262
Feature activation+1.03e-01

Pos logit contributions
 whispered+0.140
 said+0.133
 woke+0.126
 fell+0.125
l+0.117
Neg logit contributions
 unison-0.241
ric-0.235
latable-0.234
igsaw-0.229
 Deal-0.224
Token the
Token ID262
Feature activation+1.12e-01

Pos logit contributions
 whispered+0.164
 said+0.155
 woke+0.149
 fell+0.147
l+0.145
Neg logit contributions
 unison-0.209
ric-0.207
latable-0.204
 Deal-0.198
igsaw-0.192
Token waves
Token ID9813
Feature activation+1.92e-01

Pos logit contributions
 whispered+0.165
 said+0.152
 fell+0.150
chy+0.150
 woke+0.149
Neg logit contributions
 unison-0.155
latable-0.147
ric-0.147
 Deal-0.139
igsaw-0.137
Token crashing
Token ID21899
Feature activation+1.78e-01

Pos logit contributions
 whispered+0.235
chy+0.213
 prick+0.211
 meant+0.210
 woke+0.209
Neg logit contributions
 unison-0.305
ric-0.286
latable-0.276
ifying-0.266
ap-0.266
Token against
Token ID1028
Feature activation+1.45e-01

Pos logit contributions
 whispered+0.208
 said+0.185
 woke+0.182
 meant+0.182
chy+0.182
Neg logit contributions
 unison-0.293
ric-0.281
latable-0.274
ifying-0.269
ap-0.253
Token the
Token ID262
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.182
 said+0.173
 woke+0.165
 fell+0.163
l+0.161
Neg logit contributions
ric-0.222
 unison-0.218
latable-0.216
 Deal-0.213
igsaw-0.203
Token shore
Token ID15191
Feature activation+2.23e-01

Pos logit contributions
 whispered+0.158
 said+0.147
 woke+0.143
 meant+0.143
 fell+0.143
Neg logit contributions
 unison-0.154
ric-0.148
latable-0.148
 Deal-0.138
igsaw-0.136
Token.
Token ID13
Feature activation+2.35e-02

Pos logit contributions
 whispered+0.176
chy+0.154
 woke+0.152
 meant+0.146
 said+0.145
Neg logit contributions
 unison-0.453
ric-0.446
latable-0.423
igsaw-0.406
ap-0.402
Token
Token ID198
Feature activation+2.30e-02

Pos logit contributions
 said+0.024
 whispered+0.024
 woke+0.022
 fell+0.021
 meant+0.021
Neg logit contributions
 unison-0.041
ric-0.041
latable-0.041
 Deal-0.039
igsaw-0.038
Token
Token ID198
Feature activation+1.96e-02

Pos logit contributions
 whispered+0.022
 said+0.019
 woke+0.019
chy+0.019
 fell+0.019
Neg logit contributions
 unison-0.043
ric-0.042
latable-0.042
 Deal-0.041
igsaw-0.040
Token"
Token ID1
Feature activation+7.62e-02

Pos logit contributions
 whispered+0.026
 said+0.026
 woke+0.024
l+0.023
 fell+0.023
Neg logit contributions
ric-0.029
latable-0.028
 unison-0.028
 Deal-0.027
igsaw-0.027
TokenWould
Token ID17353
Feature activation+1.13e-01

Pos logit contributions
 whispered+0.096
 said+0.089
 fell+0.087
 woke+0.086
chy+0.086
Neg logit contributions
 unison-0.120
ric-0.115
latable-0.114
 Deal-0.111
igsaw-0.107
Token would
Token ID561
Feature activation+1.04e-01

Pos logit contributions
 aisle+0.087
 low+0.083
 whispered+0.081
 prick+0.077
l+0.077
Neg logit contributions
 unison-0.190
latable-0.187
ric-0.186
 yeah-0.171
 Deal-0.171
Token let
Token ID1309
Feature activation+1.21e-01

Pos logit contributions
 whispered+0.163
l+0.157
 aisle+0.153
 meant+0.152
 woke+0.152
Neg logit contributions
 unison-0.120
ric-0.117
 Deal-0.110
latable-0.108
 yeah-0.102
Token them
Token ID606
Feature activation+1.67e-01

Pos logit contributions
 whispered+0.184
 said+0.174
 woke+0.169
 fell+0.168
chy+0.167
Neg logit contributions
 unison-0.156
ric-0.150
latable-0.149
 Deal-0.143
igsaw-0.139
Token keep
Token ID1394
Feature activation+1.50e-01

Pos logit contributions
 whispered+0.245
 said+0.230
 woke+0.227
chy+0.223
 fell+0.222
Neg logit contributions
 unison-0.217
ric-0.212
latable-0.209
 Deal-0.198
igsaw-0.193
Token their
Token ID511
Feature activation+1.32e-01

Pos logit contributions
 whispered+0.238
 said+0.223
 woke+0.223
chy+0.219
 fell+0.218
Neg logit contributions
 unison-0.183
ric-0.178
latable-0.176
 Deal-0.167
igsaw-0.161
Token patch
Token ID8529
Feature activation+2.23e-01

Pos logit contributions
 whispered+0.174
 said+0.163
 woke+0.160
 meant+0.157
l+0.156
Neg logit contributions
 unison-0.195
ric-0.194
latable-0.186
 Deal-0.180
igsaw-0.172
Token if
Token ID611
Feature activation+1.21e-01

Pos logit contributions
 whispered+0.200
 said+0.172
 woke+0.170
 meant+0.161
 spoke+0.156
Neg logit contributions
 unison-0.406
latable-0.402
ric-0.397
igsaw-0.387
 Deal-0.376
Token they
Token ID484
Feature activation+1.25e-01

Pos logit contributions
 whispered+0.133
 said+0.121
 woke+0.118
chy+0.117
 fell+0.116
Neg logit contributions
 unison-0.206
ric-0.200
latable-0.198
 Deal-0.193
igsaw-0.189
Token gave
Token ID2921
Feature activation+1.48e-01

Pos logit contributions
 aisle+0.158
l+0.145
 floor+0.136
 whispered+0.135
 man+0.133
Neg logit contributions
 unison-0.165
ric-0.155
latable-0.147
 teammates-0.142
 spend-0.141
Token him
Token ID683
Feature activation+1.60e-01

Pos logit contributions
 whispered+0.242
 woke+0.225
chy+0.224
 said+0.224
 fell+0.219
Neg logit contributions
 unison-0.168
ric-0.158
latable-0.154
 Deal-0.149
igsaw-0.141
Token their
Token ID511
Feature activation+1.37e-01

Pos logit contributions
 whispered+0.204
 said+0.189
 woke+0.184
 fell+0.181
chy+0.179
Neg logit contributions
 unison-0.242
ric-0.237
latable-0.234
 Deal-0.222
igsaw-0.220
Token couldn
Token ID3521
Feature activation+9.59e-02

Pos logit contributions
 whispered+0.093
 aisle+0.091
l+0.091
 low+0.082
 man+0.079
Neg logit contributions
 unison-0.198
ric-0.196
latable-0.195
 Deal-0.181
 hey-0.178
Token't
Token ID470
Feature activation+9.91e-02

Pos logit contributions
 fell+0.105
 said+0.100
chy+0.099
 woke+0.099
l+0.098
Neg logit contributions
 unison-0.174
ric-0.162
latable-0.161
 Deal-0.154
 yeah-0.153
Token play
Token ID711
Feature activation+1.56e-01

Pos logit contributions
 whispered+0.136
 said+0.128
 woke+0.125
 fell+0.124
chy+0.123
Neg logit contributions
 unison-0.144
ric-0.140
latable-0.138
 Deal-0.133
igsaw-0.130
Token with
Token ID351
Feature activation+1.20e-01

Pos logit contributions
 whispered+0.174
 said+0.160
 woke+0.153
 fell+0.151
chy+0.149
Neg logit contributions
 unison-0.268
latable-0.262
ric-0.260
 Deal-0.249
igsaw-0.247
Token his
Token ID465
Feature activation+1.31e-01

Pos logit contributions
 whispered+0.151
 said+0.141
 woke+0.137
 fell+0.135
chy+0.134
Neg logit contributions
 unison-0.189
ric-0.184
latable-0.182
 Deal-0.176
igsaw-0.172
Token boat
Token ID8848
Feature activation+2.23e-01

Pos logit contributions
 whispered+0.171
 said+0.160
 woke+0.155
 fell+0.154
chy+0.152
Neg logit contributions
 unison-0.199
ric-0.193
latable-0.191
 Deal-0.186
igsaw-0.181
Token without
Token ID1231
Feature activation+1.30e-01

Pos logit contributions
 whispered+0.336
 woke+0.307
 said+0.298
l+0.290
 meant+0.287
Neg logit contributions
 unison-0.264
latable-0.256
ric-0.243
 teammates-0.237
ap-0.232
Token bubbles
Token ID25037
Feature activation+2.04e-01

Pos logit contributions
 whispered+0.184
l+0.173
 woke+0.172
 said+0.171
chy+0.169
Neg logit contributions
 unison-0.179
ric-0.177
latable-0.170
 Deal-0.167
igsaw-0.157
Token.
Token ID13
Feature activation+2.32e-02

Pos logit contributions
 whispered+0.251
 woke+0.216
 said+0.211
 knew+0.209
 spoke+0.204
Neg logit contributions
 unison-0.282
ifying-0.280
latable-0.278
ric-0.270
igsaw-0.270
Token
Token ID198
Feature activation+1.51e-02

Pos logit contributions
 whispered+0.033
l+0.030
chy+0.030
 said+0.029
 meant+0.029
Neg logit contributions
ric-0.031
latable-0.030
 unison-0.030
 Deal-0.030
igsaw-0.029
Token
Token ID198
Feature activation+1.19e-02

Pos logit contributions
 whispered+0.020
chy+0.018
 meant+0.017
 prick+0.017
 woke+0.017
Neg logit contributions
ric-0.022
 unison-0.021
 Deal-0.021
latable-0.021
igsaw-0.020
Token She
Token ID1375
Feature activation+8.08e-02

Pos logit contributions
 whispered+0.015
 said+0.014
chy+0.014
 woke+0.014
l+0.014
Neg logit contributions
 unison-0.019
ric-0.019
latable-0.019
 Deal-0.018
igsaw-0.018
Token even
Token ID772
Feature activation+1.38e-01

Pos logit contributions
l+0.066
 whispered+0.066
chy+0.065
 aisle+0.064
 low+0.060
Neg logit contributions
 unison-0.147
latable-0.141
ric-0.138
 Deal-0.132
 yeah-0.131
Token shared
Token ID4888
Feature activation+1.50e-01

Pos logit contributions
chy+0.105
 whispered+0.103
l+0.101
 aisle+0.090
 fell+0.089
Neg logit contributions
 unison-0.260
latable-0.245
ric-0.240
 yeah-0.237
 Deal-0.235
Token her
Token ID607
Feature activation+1.17e-01

Pos logit contributions
 whispered+0.180
chy+0.177
 woke+0.169
 fell+0.168
l+0.162
Neg logit contributions
 unison-0.233
ric-0.221
latable-0.219
 Deal-0.210
igsaw-0.210
Token delicious
Token ID12625
Feature activation+1.78e-01

Pos logit contributions
 whispered+0.151
 said+0.141
 woke+0.138
 fell+0.136
chy+0.136
Neg logit contributions
 unison-0.177
ric-0.172
latable-0.170
 Deal-0.165
igsaw-0.161
Token snack
Token ID26906
Feature activation+2.22e-01

Pos logit contributions
 whispered+0.255
chy+0.239
 said+0.236
 fell+0.229
l+0.227
Neg logit contributions
 unison-0.236
latable-0.236
ric-0.231
igsaw-0.222
 Deal-0.217
Token with
Token ID351
Feature activation+1.21e-01

Pos logit contributions
 whispered+0.308
 woke+0.296
 meant+0.282
l+0.277
chy+0.276
Neg logit contributions
igsaw-0.295
 unison-0.280
latable-0.276
 teammates-0.265
ap-0.249
Token the
Token ID262
Feature activation+1.08e-01

Pos logit contributions
 whispered+0.139
 said+0.127
 woke+0.127
chy+0.125
 fell+0.124
Neg logit contributions
 unison-0.202
ric-0.195
latable-0.192
 Deal-0.186
igsaw-0.182
Token little
Token ID1310
Feature activation+1.28e-01

Pos logit contributions
 whispered+0.108
 said+0.096
 woke+0.094
 fell+0.094
chy+0.092
Neg logit contributions
 unison-0.197
latable-0.193
ric-0.191
 Deal-0.186
igsaw-0.185
Token boy
Token ID2933
Feature activation+1.66e-01

Pos logit contributions
 whispered+0.074
 said+0.070
 man+0.058
 fell+0.056
 woke+0.056
Neg logit contributions
ric-0.307
 unison-0.302
 Deal-0.294
latable-0.290
ifying-0.280
Token as
Token ID355
Feature activation+9.11e-02

Pos logit contributions
 whispered+0.133
 woke+0.118
chy+0.115
 said+0.113
l+0.112
Neg logit contributions
 unison-0.328
ric-0.318
latable-0.310
igsaw-0.299
 Deal-0.298
Token When
Token ID1649
Feature activation-2.62e-01

Pos logit contributions
 unison+0.494
ric+0.476
latable+0.467
 Deal+0.465
igsaw+0.446
Neg logit contributions
 whispered-0.382
chy-0.353
 said-0.349
 woke-0.347
 fell-0.344
Token Daisy
Token ID40355
Feature activation-2.12e-01

Pos logit contributions
 unison+0.451
ric+0.439
latable+0.433
 Deal+0.423
igsaw+0.417
Neg logit contributions
 whispered-0.277
 said-0.249
chy-0.244
l-0.241
 woke-0.241
Token put
Token ID1234
Feature activation-1.54e-01

Pos logit contributions
 unison+0.321
latable+0.317
ric+0.307
 yeah+0.298
 gonna+0.298
Neg logit contributions
 prick-0.193
chy-0.182
l-0.178
 low-0.178
 whispered-0.166
Token the
Token ID262
Feature activation-2.10e-01

Pos logit contributions
 unison+0.248
ric+0.242
 Deal+0.238
latable+0.237
igsaw+0.237
Neg logit contributions
 whispered-0.169
 woke-0.159
chy-0.156
l-0.149
 said-0.149
Token magn
Token ID7842
Feature activation-1.79e-01

Pos logit contributions
 unison+0.327
ric+0.317
latable+0.310
igsaw+0.305
 Deal+0.297
Neg logit contributions
 whispered-0.255
 woke-0.233
 said-0.232
 fell-0.231
 meant-0.228
Tokenifying
Token ID4035
Feature activation-3.70e-01

Pos logit contributions
 unison+0.069
ric+0.057
latable+0.055
 Deal+0.048
ifying+0.048
Neg logit contributions
 whispered-0.435
 said-0.420
 woke-0.414
 fell-0.409
chy-0.408
Token glass
Token ID5405
Feature activation-1.32e-01

Pos logit contributions
 unison+0.703
latable+0.692
ric+0.687
 Deal+0.680
 hey+0.665
Neg logit contributions
 said-0.324
 whispered-0.323
 woke-0.310
 fell-0.306
l-0.285
Token down
Token ID866
Feature activation-1.46e-01

Pos logit contributions
igsaw+0.200
 unison+0.190
latable+0.182
ifying+0.180
ric+0.172
Neg logit contributions
 whispered-0.154
 knew-0.139
chy-0.136
 woke-0.136
 meant-0.135
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
 unison+0.198
igsaw+0.194
 yeah+0.186
 Deal+0.182
ifying+0.182
Neg logit contributions
 whispered-0.190
chy-0.175
 woke-0.173
 meant-0.165
 said-0.159
Token the
Token ID262
Feature activation-1.94e-01

Pos logit contributions
 unison+0.403
ric+0.399
latable+0.394
 Deal+0.384
igsaw+0.373
Neg logit contributions
 whispered-0.123
 said-0.111
 fell-0.102
 woke-0.102
l-0.097
Token cater
Token ID20825
Feature activation-1.63e-01

Pos logit contributions
 unison+0.316
ric+0.291
igsaw+0.284
 Deal+0.278
latable+0.277
Neg logit contributions
 whispered-0.223
 meant-0.203
 woke-0.200
 fell-0.195
chy-0.195
Token John
Token ID1757
Feature activation-3.19e-01

Pos logit contributions
chy+0.149
 prick+0.149
l+0.142
 aisle+0.138
 iv+0.132
Neg logit contributions
 unison-0.252
ric-0.216
ap-0.209
 hey-0.207
latable-0.197
Token chose
Token ID7690
Feature activation-2.21e-01

Pos logit contributions
 unison+0.644
ric+0.631
latable+0.616
 Deal+0.601
igsaw+0.580
Neg logit contributions
 whispered-0.243
chy-0.211
l-0.205
 said-0.205
 woke-0.201
Token some
Token ID617
Feature activation-2.10e-01

Pos logit contributions
 unison+0.307
ric+0.299
latable+0.293
igsaw+0.275
 Deal+0.271
Neg logit contributions
 whispered-0.303
 woke-0.283
chy-0.280
 fell-0.278
 said-0.276
Token carrots
Token ID34397
Feature activation-1.70e-01

Pos logit contributions
 unison+0.329
latable+0.315
ric+0.313
igsaw+0.298
 Deal+0.291
Neg logit contributions
 whispered-0.253
 woke-0.237
 fell-0.230
chy-0.224
 said-0.223
Token and
Token ID290
Feature activation-2.25e-01

Pos logit contributions
ric+0.277
 unison+0.274
latable+0.268
ifying+0.254
igsaw+0.248
Neg logit contributions
 whispered-0.180
 woke-0.167
chy-0.157
 fell-0.156
l-0.154
Token cuc
Token ID38421
Feature activation-3.39e-01

Pos logit contributions
 unison+0.385
ric+0.373
latable+0.369
 Deal+0.356
igsaw+0.346
Neg logit contributions
 whispered-0.233
 woke-0.209
 said-0.206
l-0.206
chy-0.205
Tokenumbers
Token ID17024
Feature activation-1.26e-01

Pos logit contributions
 unison+0.538
latable+0.523
ric+0.497
igsaw+0.476
 Deal+0.470
Neg logit contributions
 whispered-0.425
 said-0.414
l-0.406
 meant-0.373
 fell-0.371
Token to
Token ID284
Feature activation-1.91e-01

Pos logit contributions
ric+0.205
 unison+0.195
latable+0.186
 yeah+0.182
ifying+0.182
Neg logit contributions
 whispered-0.133
 woke-0.120
chy-0.115
 aisle-0.111
 prick-0.111
Token take
Token ID1011
Feature activation-1.49e-01

Pos logit contributions
 unison+0.304
ric+0.294
latable+0.293
 Deal+0.286
igsaw+0.279
Neg logit contributions
 whispered-0.234
 said-0.224
 woke-0.212
 fell-0.210
chy-0.208
Token home
Token ID1363
Feature activation-1.18e-01

Pos logit contributions
 unison+0.190
latable+0.179
ric+0.174
igsaw+0.173
 Deal+0.168
Neg logit contributions
 whispered-0.226
 woke-0.207
chy-0.206
 fell-0.205
 said-0.205
Token.
Token ID13
Feature activation-2.47e-01

Pos logit contributions
 unison+0.224
ric+0.219
latable+0.216
igsaw+0.210
 Deal+0.210
Neg logit contributions
 whispered-0.104
 woke-0.093
 said-0.092
 fell-0.089
chy-0.087
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
 whispered+0.190
 said+0.174
l+0.164
chy+0.164
 woke+0.162
Neg logit contributions
 unison-0.228
latable-0.223
ric-0.219
igsaw-0.199
 Deal-0.194
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
TokenThat
Token ID2504
Feature activation-2.63e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.84e-01

Pos logit contributions
 unison+0.461
ric+0.455
latable+0.447
 Deal+0.431
igsaw+0.426
Neg logit contributions
 whispered-0.273
 said-0.247
 woke-0.239
 fell-0.236
chy-0.233
Token
Token ID26391
Feature activation-3.32e-01

Pos logit contributions
ric+0.328
 unison+0.325
latable+0.316
 Deal+0.307
igsaw+0.303
Neg logit contributions
 whispered-0.469
 woke-0.436
 said-0.435
 fell-0.429
l-0.423
Token
Token ID8151
Feature activation-2.99e-01

Pos logit contributions
 unison+0.492
latable+0.476
ric+0.471
 Deal+0.457
igsaw+0.440
Neg logit contributions
 whispered-0.440
 said-0.421
 fell-0.410
 woke-0.406
l-0.396
Tokens
Token ID82
Feature activation-2.37e-01

Pos logit contributions
ric+0.501
 unison+0.450
igsaw+0.444
latable+0.441
 Deal+0.430
Neg logit contributions
 whispered-0.363
 prick-0.323
 woke-0.305
chy-0.295
 said-0.290
Token right
Token ID826
Feature activation-1.91e-01

Pos logit contributions
 unison+0.381
latable+0.367
ric+0.365
 Deal+0.357
igsaw+0.350
Neg logit contributions
 whispered-0.285
 said-0.271
 woke-0.260
 fell-0.258
chy-0.256
Token,
Token ID11
Feature activation-2.28e-01

Pos logit contributions
ric+0.307
 unison+0.304
latable+0.292
 Deal+0.286
igsaw+0.278
Neg logit contributions
 whispered-0.224
 woke-0.201
 said-0.200
chy-0.198
 fell-0.196
Token Emma
Token ID18966
Feature activation-2.03e-01

Pos logit contributions
 unison+0.331
ric+0.321
latable+0.318
 Deal+0.307
igsaw+0.298
Neg logit contributions
 whispered-0.308
 said-0.288
 woke-0.280
 fell-0.278
chy-0.277
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
l+0.113
chy+0.112
 whispered+0.112
 aisle+0.110
 woke+0.106
Neg logit contributions
 unison-0.111
latable-0.104
 yeah-0.102
ric-0.101
 hey-0.098
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
TokenThat
Token ID2504
Feature activation-2.63e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.84e-01

Pos logit contributions
 unison+0.461
ric+0.455
latable+0.447
 Deal+0.431
igsaw+0.426
Neg logit contributions
 whispered-0.273
 said-0.247
 woke-0.239
 fell-0.236
chy-0.233
Token
Token ID26391
Feature activation-3.32e-01

Pos logit contributions
ric+0.328
 unison+0.325
latable+0.316
 Deal+0.307
igsaw+0.303
Neg logit contributions
 whispered-0.469
 woke-0.436
 said-0.435
 fell-0.429
l-0.423
Token
Token ID8151
Feature activation-2.99e-01

Pos logit contributions
 unison+0.492
latable+0.476
ric+0.471
 Deal+0.457
igsaw+0.440
Neg logit contributions
 whispered-0.440
 said-0.421
 fell-0.410
 woke-0.406
l-0.396
Tokens
Token ID82
Feature activation-2.37e-01

Pos logit contributions
ric+0.501
 unison+0.450
igsaw+0.444
latable+0.441
 Deal+0.430
Neg logit contributions
 whispered-0.363
 prick-0.323
 woke-0.305
chy-0.295
 said-0.290
Token the
Token ID262
Feature activation-2.43e-01

Pos logit contributions
 unison+0.381
latable+0.367
ric+0.365
 Deal+0.357
igsaw+0.350
Neg logit contributions
 whispered-0.285
 said-0.271
 woke-0.260
 fell-0.258
chy-0.256
Token gas
Token ID3623
Feature activation-1.48e-01

Pos logit contributions
ric+0.399
 unison+0.396
 Deal+0.378
latable+0.376
igsaw+0.366
Neg logit contributions
 whispered-0.280
 said-0.249
 woke-0.248
 fell-0.247
chy-0.240
Token from
Token ID422
Feature activation-2.12e-01

Pos logit contributions
ric+0.250
 unison+0.245
latable+0.235
 Deal+0.218
ifying+0.216
Neg logit contributions
 whispered-0.165
 woke-0.144
 said-0.143
chy-0.142
 fell-0.141
Token those
Token ID883
Feature activation-3.54e-01

Pos logit contributions
 whispered+0.024
 said+0.022
 woke+0.021
 fell+0.021
l+0.020
Neg logit contributions
 unison-0.056
ric-0.054
latable-0.054
 Deal-0.053
igsaw-0.051
Token in
Token ID287
Feature activation-3.09e-01

Pos logit contributions
 unison+0.578
ric+0.567
latable+0.549
 Deal+0.537
igsaw+0.524
Neg logit contributions
 whispered-0.412
 said-0.375
 woke-0.374
 fell-0.371
chy-0.367
Token need
Token ID761
Feature activation-2.59e-01

Pos logit contributions
 unison+0.468
ric+0.455
latable+0.450
 Deal+0.435
igsaw+0.424
Neg logit contributions
 whispered-0.401
 said-0.375
 woke-0.364
 fell-0.361
chy-0.358
Tokenâ
Token ID22940
Feature activation-2.85e-01

Pos logit contributions
 unison+0.362
ric+0.347
latable+0.336
 Deal+0.333
igsaw+0.320
Neg logit contributions
 whispered-0.359
 woke-0.330
chy-0.330
 said-0.329
 fell-0.326
Token
Token ID26391
Feature activation-3.28e-01

Pos logit contributions
ric+0.358
 unison+0.354
latable+0.345
 Deal+0.339
igsaw+0.329
Neg logit contributions
 whispered-0.438
 said-0.410
 fell-0.410
 woke-0.407
l-0.405
Token
Token ID447
Feature activation-3.31e-01

Pos logit contributions
 unison+0.491
latable+0.475
ric+0.475
 Deal+0.459
igsaw+0.446
Neg logit contributions
 whispered-0.432
 said-0.409
 fell-0.395
 woke-0.395
chy-0.385
Token
Token ID251
Feature activation-2.87e-01

Pos logit contributions
 unison+0.347
ric+0.335
 Deal+0.328
latable+0.303
igsaw+0.300
Neg logit contributions
 whispered-0.580
 woke-0.545
 meant-0.544
 prick-0.539
chy-0.538
Tokeneven
Token ID10197
Feature activation-1.72e-01

Pos logit contributions
 unison+0.454
 Deal+0.430
ric+0.426
 yeah+0.409
latable+0.397
Neg logit contributions
chy-0.329
 whispered-0.304
 prick-0.300
 woke-0.296
l-0.286
Token<|endoftext|>
Token ID50256
Feature activation-2.65e-01

Pos logit contributions
 unison+0.288
ric+0.276
latable+0.274
 Deal+0.269
igsaw+0.265
Neg logit contributions
 whispered-0.188
 said-0.171
 woke-0.171
 fell-0.170
chy-0.167
TokenOne
Token ID3198
Feature activation-2.17e-01

Pos logit contributions
ric+0.388
 unison+0.383
latable+0.362
 Deal+0.358
igsaw+0.357
Neg logit contributions
 whispered-0.343
chy-0.322
 prick-0.307
 said-0.300
 fell-0.300
Token day
Token ID1110
Feature activation-1.70e-01

Pos logit contributions
ric+0.456
 unison+0.455
latable+0.442
igsaw+0.438
 Deal+0.426
Neg logit contributions
 whispered-0.144
 woke-0.112
chy-0.111
 said-0.110
 fell-0.106
Token by
Token ID416
Feature activation-3.25e-01

Pos logit contributions
 whispered+0.026
chy+0.024
 fell+0.023
 meant+0.023
 prick+0.023
Neg logit contributions
 unison-0.032
ric-0.030
latable-0.030
 Deal-0.029
igsaw-0.028
Token one
Token ID530
Feature activation-2.84e-01

Pos logit contributions
 unison+0.474
latable+0.470
ric+0.455
 Deal+0.450
igsaw+0.439
Neg logit contributions
 whispered-0.433
 said-0.413
 woke-0.397
 fell-0.393
chy-0.387
Token
Token ID6184
Feature activation-2.63e-01

Pos logit contributions
 unison+0.463
ric+0.438
latable+0.414
 Deal+0.410
igsaw+0.409
Neg logit contributions
 whispered-0.335
 woke-0.301
chy-0.299
 said-0.298
 fell-0.298
Token
Token ID95
Feature activation-2.42e-01

Pos logit contributions
 unison+0.344
ric+0.337
latable+0.326
 Deal+0.320
igsaw+0.301
Neg logit contributions
 whispered-0.387
 said-0.365
 woke-0.351
l-0.351
chy-0.350
Token
Token ID26391
Feature activation-3.25e-01

Pos logit contributions
 unison+0.305
ric+0.294
latable+0.292
 Deal+0.280
igsaw+0.272
Neg logit contributions
 whispered-0.377
 said-0.357
 woke-0.349
 fell-0.347
chy-0.343
Token
Token ID447
Feature activation-3.31e-01

Pos logit contributions
 unison+0.622
latable+0.609
ric+0.603
 Deal+0.588
igsaw+0.577
Neg logit contributions
 whispered-0.292
 said-0.271
 fell-0.257
 woke-0.257
l-0.246
Token
Token ID250
Feature activation-2.47e-01

Pos logit contributions
 unison+0.292
ric+0.278
 Deal+0.263
latable+0.262
igsaw+0.246
Neg logit contributions
 whispered-0.644
 said-0.608
chy-0.606
 woke-0.604
 meant-0.602
Token 1
Token ID352
Feature activation-1.40e-01

Pos logit contributions
 unison+0.365
ric+0.354
 Deal+0.343
latable+0.342
igsaw+0.330
Neg logit contributions
 whispered-0.332
 said-0.311
 woke-0.305
 fell-0.303
chy-0.300
Token,
Token ID11
Feature activation-2.04e-01

Pos logit contributions
 unison+0.226
ric+0.220
 Deal+0.208
latable+0.207
 yeah+0.204
Neg logit contributions
 whispered-0.159
chy-0.152
 woke-0.146
 prick-0.143
 fell-0.142
Token 2
Token ID362
Feature activation-1.26e-01

Pos logit contributions
 unison+0.281
ric+0.272
latable+0.268
 Deal+0.260
igsaw+0.252
Neg logit contributions
 whispered-0.291
 said-0.273
 woke-0.266
 fell-0.265
chy-0.264
Token,
Token ID11
Feature activation-1.98e-01

Pos logit contributions
 unison+0.205
ric+0.197
latable+0.190
 Deal+0.188
igsaw+0.185
Neg logit contributions
 whispered-0.146
chy-0.139
 woke-0.135
 fell-0.132
 said-0.127
Token
Token ID8151
Feature activation-4.76e-01

Pos logit contributions
 whispered+0.156
 said+0.148
 woke+0.141
 fell+0.139
chy+0.138
Neg logit contributions
 unison-0.204
ric-0.199
latable-0.196
 Deal-0.190
igsaw-0.185
Tokens
Token ID82
Feature activation-3.49e-01

Pos logit contributions
ric+0.889
 unison+0.850
latable+0.831
 Deal+0.808
igsaw+0.802
Neg logit contributions
 whispered-0.445
 prick-0.376
 said-0.374
chy-0.371
 woke-0.369
Token ok
Token ID12876
Feature activation-2.78e-01

Pos logit contributions
 unison+0.557
ric+0.553
latable+0.531
 Deal+0.517
igsaw+0.498
Neg logit contributions
 whispered-0.416
 said-0.377
 woke-0.371
 fell-0.367
l-0.367
Token,
Token ID11
Feature activation-2.83e-01

Pos logit contributions
 unison+0.583
ric+0.571
latable+0.568
 Deal+0.554
igsaw+0.544
Neg logit contributions
 whispered-0.200
 said-0.178
 woke-0.168
 fell-0.165
chy-0.162
Tokenâ
Token ID22940
Feature activation-2.84e-01

Pos logit contributions
 unison+0.428
ric+0.417
latable+0.412
 Deal+0.399
igsaw+0.389
Neg logit contributions
 whispered-0.368
 said-0.345
 woke-0.335
 fell-0.332
chy-0.329
Token
Token ID26391
Feature activation-3.29e-01

Pos logit contributions
 unison+0.331
ric+0.331
 Deal+0.317
latable+0.314
igsaw+0.294
Neg logit contributions
 whispered-0.454
 woke-0.424
 fell-0.417
 said-0.417
 prick-0.415
Token said
Token ID531
Feature activation-2.23e-01

Pos logit contributions
 unison+0.537
latable+0.524
ric+0.513
 Deal+0.506
igsaw+0.495
Neg logit contributions
 whispered-0.391
 said-0.373
 fell-0.363
 woke-0.357
l-0.345
Token her
Token ID607
Feature activation-2.23e-01

Pos logit contributions
 unison+0.386
ric+0.375
latable+0.371
 Deal+0.366
igsaw+0.353
Neg logit contributions
 whispered-0.236
 said-0.213
 woke-0.207
chy-0.205
 fell-0.203
Token mum
Token ID25682
Feature activation-1.70e-01

Pos logit contributions
 unison+0.287
ric+0.283
 Deal+0.273
latable+0.269
igsaw+0.261
Neg logit contributions
 whispered-0.332
 said-0.307
 woke-0.300
chy-0.297
 fell-0.295
Token.
Token ID13
Feature activation-2.67e-01

Pos logit contributions
ric+0.278
 unison+0.265
 yeah+0.248
 hey+0.241
ifying+0.239
Neg logit contributions
 prick-0.167
 whispered-0.155
 aisle-0.152
 low-0.150
mail-0.138
Token
Token ID6184
Feature activation-1.90e-01

Pos logit contributions
 unison+0.420
ric+0.404
 Deal+0.399
latable+0.396
igsaw+0.381
Neg logit contributions
 whispered-0.328
chy-0.310
l-0.299
 fell-0.299
 woke-0.298
Token arm
Token ID3211
Feature activation-1.80e-01

Pos logit contributions
 unison+0.379
ric+0.366
latable+0.350
igsaw+0.338
 Deal+0.332
Neg logit contributions
 whispered-0.279
 said-0.248
 fell-0.247
chy-0.247
 woke-0.247
Tokenchair
Token ID16337
Feature activation-2.41e-01

Pos logit contributions
ric+0.290
 unison+0.266
latable+0.265
ifying+0.257
igsaw+0.251
Neg logit contributions
 whispered-0.188
 prick-0.155
 woke-0.152
 said-0.150
 low-0.148
Token.
Token ID13
Feature activation-2.85e-01

Pos logit contributions
ric+0.380
 unison+0.367
latable+0.347
ifying+0.337
ap+0.333
Neg logit contributions
 whispered-0.256
 prick-0.232
l-0.227
 meant-0.213
 said-0.211
Token
Token ID198
Feature activation-2.78e-01

Pos logit contributions
 unison+0.449
ric+0.434
latable+0.424
 Deal+0.421
igsaw+0.405
Neg logit contributions
 whispered-0.351
 said-0.322
chy-0.321
 fell-0.317
 woke-0.316
Token
Token ID198
Feature activation-2.74e-01

Pos logit contributions
 unison+0.463
ric+0.445
 Deal+0.432
latable+0.427
igsaw+0.414
Neg logit contributions
 whispered-0.317
chy-0.301
 fell-0.287
 woke-0.283
 meant-0.283
TokenTHE
Token ID10970
Feature activation-3.29e-01

Pos logit contributions
 unison+0.437
ric+0.435
latable+0.429
 Deal+0.411
igsaw+0.403
Neg logit contributions
 whispered-0.328
 said-0.308
 woke-0.297
 fell-0.292
l-0.289
Token<|endoftext|>
Token ID50256
Feature activation-2.56e-01

Pos logit contributions
ric+0.531
 unison+0.525
latable+0.495
 Deal+0.487
 yeah+0.483
Neg logit contributions
 whispered-0.369
 meant-0.336
l-0.334
 prick-0.330
chy-0.327
TokenOnce
Token ID7454
Feature activation-2.23e-01

Pos logit contributions
 unison+0.348
ric+0.334
latable+0.308
 Deal+0.303
igsaw+0.301
Neg logit contributions
 whispered-0.363
chy-0.350
 prick-0.340
 said-0.317
l-0.312
Token upon
Token ID2402
Feature activation-2.79e-01

Pos logit contributions
 unison+0.239
ric+0.236
latable+0.225
igsaw+0.221
 Deal+0.218
Neg logit contributions
 whispered-0.376
 said-0.349
 woke-0.346
chy-0.345
 fell-0.341
Token a
Token ID257
Feature activation-1.89e-01

Pos logit contributions
ric+0.520
 unison+0.496
latable+0.495
igsaw+0.488
 Deal+0.488
Neg logit contributions
 said-0.295
 whispered-0.294
 woke-0.284
 fell-0.281
chy-0.257
Token time
Token ID640
Feature activation-1.71e-01

Pos logit contributions
ric+0.398
 unison+0.388
latable+0.376
 Deal+0.371
igsaw+0.365
Neg logit contributions
 whispered-0.135
 woke-0.131
 said-0.129
 fell-0.125
chy-0.121
Token
Token ID129
Feature activation-4.32e-01

Pos logit contributions
 whispered+0.146
 woke+0.135
 fell+0.129
chy+0.129
 said+0.129
Neg logit contributions
 unison-0.239
ric-0.225
latable-0.224
 Deal-0.222
igsaw-0.219
Token
Token ID241
Feature activation-4.07e-01

Pos logit contributions
 unison+0.657
latable+0.613
 Deal+0.603
ric+0.598
igsaw+0.590
Neg logit contributions
 whispered-0.575
 said-0.557
 fell-0.534
 woke-0.531
l-0.526
TokenT
Token ID51
Feature activation-2.60e-01

Pos logit contributions
 unison+0.706
ric+0.686
latable+0.683
 Deal+0.663
igsaw+0.650
Neg logit contributions
 whispered-0.437
 said-0.406
 woke-0.390
 fell-0.386
chy-0.381
TokenIM
Token ID3955
Feature activation-1.86e-01

Pos logit contributions
 unison+0.372
ric+0.361
latable+0.358
 Deal+0.345
igsaw+0.336
Neg logit contributions
 whispered-0.360
 said-0.338
 woke-0.329
 fell-0.326
chy-0.323
Tokenâ
Token ID22940
Feature activation-2.82e-01

Pos logit contributions
 unison+0.253
ric+0.246
latable+0.242
 Deal+0.232
igsaw+0.228
Neg logit contributions
 whispered-0.268
 woke-0.246
 said-0.245
 fell-0.243
chy-0.243
Token
Token ID26391
Feature activation-3.28e-01

Pos logit contributions
ric+0.310
 unison+0.306
 Deal+0.294
latable+0.291
igsaw+0.278
Neg logit contributions
 whispered-0.486
 said-0.451
 woke-0.450
 fell-0.446
l-0.446
Token.
Token ID13
Feature activation-2.83e-01

Pos logit contributions
 unison+0.530
latable+0.519
ric+0.507
 Deal+0.498
igsaw+0.485
Neg logit contributions
 whispered-0.391
 said-0.374
 fell-0.364
 woke-0.359
l-0.347
Token It
Token ID632
Feature activation-2.02e-01

Pos logit contributions
 unison+0.388
ric+0.375
latable+0.374
 Deal+0.356
igsaw+0.350
Neg logit contributions
 whispered-0.404
 said-0.383
 woke-0.370
 fell-0.366
chy-0.361
Token looked
Token ID3114
Feature activation-1.62e-01

Pos logit contributions
ric+0.333
 unison+0.318
latable+0.310
 Deal+0.296
 yeah+0.293
Neg logit contributions
 whispered-0.206
 aisle-0.185
l-0.181
 prick-0.178
 woke-0.174
Token nice
Token ID3621
Feature activation-1.40e-01

Pos logit contributions
 unison+0.230
latable+0.223
ifying+0.211
 Deal+0.211
 gonna+0.209
Neg logit contributions
 whispered-0.212
 aisle-0.196
 woke-0.193
 fell-0.190
 said-0.186
Token and
Token ID290
Feature activation-1.76e-01

Pos logit contributions
 unison+0.225
latable+0.214
ric+0.212
igsaw+0.202
ifying+0.201
Neg logit contributions
 whispered-0.148
chy-0.138
 fell-0.135
l-0.133
 woke-0.132
Token nos
Token ID43630
Feature activation-3.47e-01

Pos logit contributions
 whispered+0.147
 said+0.137
 fell+0.135
 woke+0.133
chy+0.132
Neg logit contributions
 unison-0.139
ric-0.138
latable-0.137
 Deal-0.127
igsaw-0.127
Tokeny
Token ID88
Feature activation-3.10e-01

Pos logit contributions
ric+0.630
 unison+0.611
latable+0.587
igsaw+0.574
 Deal+0.566
Neg logit contributions
 whispered-0.331
chy-0.297
 fell-0.296
 said-0.282
 woke-0.282
Token.
Token ID13
Feature activation-3.33e-01

Pos logit contributions
 unison+0.599
ric+0.589
latable+0.564
 Deal+0.550
igsaw+0.544
Neg logit contributions
 whispered-0.254
 said-0.211
 fell-0.211
chy-0.208
 woke-0.207
Token<|endoftext|>
Token ID50256
Feature activation-3.00e-01

Pos logit contributions
 unison+0.506
ric+0.490
 Deal+0.474
latable+0.473
igsaw+0.455
Neg logit contributions
 whispered-0.426
chy-0.395
 said-0.389
 woke-0.388
 fell-0.387
TokenOnce
Token ID7454
Feature activation-2.70e-01

Pos logit contributions
ric+0.397
 unison+0.370
igsaw+0.354
 Deal+0.351
latable+0.343
Neg logit contributions
 whispered-0.429
chy-0.409
 prick-0.396
 meant-0.368
 said-0.365
Token upon
Token ID2402
Feature activation-3.28e-01

Pos logit contributions
 unison+0.305
ric+0.302
latable+0.289
 Deal+0.282
igsaw+0.275
Neg logit contributions
 whispered-0.447
 said-0.419
 woke-0.412
chy-0.407
 fell-0.407
Token a
Token ID257
Feature activation-2.33e-01

Pos logit contributions
ric+0.628
 unison+0.609
latable+0.605
 Deal+0.599
igsaw+0.596
Neg logit contributions
 whispered-0.333
 said-0.329
 fell-0.320
 woke-0.319
chy-0.285
Token time
Token ID640
Feature activation-2.09e-01

Pos logit contributions
ric+0.459
 unison+0.458
latable+0.442
 Deal+0.433
igsaw+0.428
Neg logit contributions
 whispered-0.191
 said-0.177
 woke-0.173
 fell-0.170
chy-0.167
Token,
Token ID11
Feature activation-2.14e-01

Pos logit contributions
 unison+0.452
ric+0.435
latable+0.433
 Deal+0.420
igsaw+0.408
Neg logit contributions
 whispered-0.146
 said-0.139
 fell-0.132
 woke-0.129
l-0.120
Token a
Token ID257
Feature activation-2.09e-01

Pos logit contributions
 unison+0.341
ric+0.335
latable+0.329
 Deal+0.318
igsaw+0.311
Neg logit contributions
 whispered-0.259
 said-0.237
 woke-0.233
 fell-0.227
chy-0.227
Token little
Token ID1310
Feature activation-1.98e-01

Pos logit contributions
 unison+0.339
latable+0.329
ric+0.321
 Deal+0.311
igsaw+0.308
Neg logit contributions
 whispered-0.248
 said-0.223
 meant-0.220
 woke-0.215
chy-0.214
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
 whispered+0.193
 woke+0.183
 fell+0.168
chy+0.167
 said+0.167
Neg logit contributions
 unison-0.315
latable-0.291
ifying-0.289
ric-0.288
igsaw-0.286
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
TokenLet
Token ID5756
Feature activation-2.55e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.80e-01

Pos logit contributions
 unison+0.468
ric+0.465
latable+0.455
 Deal+0.445
igsaw+0.436
Neg logit contributions
 whispered-0.265
 said-0.260
 woke-0.241
 fell-0.235
 meant-0.232
Token
Token ID26391
Feature activation-3.28e-01

Pos logit contributions
 unison+0.355
ric+0.341
latable+0.338
 Deal+0.324
igsaw+0.314
Neg logit contributions
 whispered-0.434
 said-0.413
 woke-0.401
 fell-0.398
chy-0.395
Token
Token ID8151
Feature activation-2.95e-01

Pos logit contributions
 unison+0.528
latable+0.519
 Deal+0.496
ric+0.489
igsaw+0.478
Neg logit contributions
 whispered-0.396
 said-0.396
 fell-0.393
 woke-0.371
l-0.362
Tokens
Token ID82
Feature activation-2.36e-01

Pos logit contributions
ric+0.522
 unison+0.481
igsaw+0.464
latable+0.464
 Deal+0.463
Neg logit contributions
 whispered-0.318
 prick-0.288
chy-0.271
 woke-0.269
 spark-0.256
Token explore
Token ID7301
Feature activation-1.71e-01

Pos logit contributions
 unison+0.384
latable+0.381
 Deal+0.367
igsaw+0.361
ric+0.360
Neg logit contributions
 said-0.295
 whispered-0.291
 fell-0.279
 woke-0.266
 meant-0.263
Token and
Token ID290
Feature activation-2.02e-01

Pos logit contributions
 unison+0.272
ric+0.264
latable+0.262
 Deal+0.252
igsaw+0.247
Neg logit contributions
 whispered-0.209
 said-0.193
 woke-0.189
 fell-0.187
chy-0.186
Token have
Token ID423
Feature activation-1.93e-01

Pos logit contributions
 unison+0.341
ric+0.332
latable+0.331
 Deal+0.324
igsaw+0.313
Neg logit contributions
 whispered-0.242
 said-0.232
 fell-0.217
 woke-0.214
 meant-0.205
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
 whispered+0.140
chy+0.129
l+0.123
 said+0.121
 prick+0.118
Neg logit contributions
 unison-0.231
latable-0.222
 Deal-0.215
ric-0.214
igsaw-0.209
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
TokenLet
Token ID5756
Feature activation-2.55e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.80e-01

Pos logit contributions
 unison+0.468
ric+0.465
latable+0.455
 Deal+0.445
igsaw+0.436
Neg logit contributions
 whispered-0.265
 said-0.260
 woke-0.241
 fell-0.235
 meant-0.232
Token
Token ID26391
Feature activation-3.28e-01

Pos logit contributions
 unison+0.355
ric+0.341
latable+0.338
 Deal+0.324
igsaw+0.314
Neg logit contributions
 whispered-0.434
 said-0.413
 woke-0.401
 fell-0.398
chy-0.395
Token
Token ID8151
Feature activation-2.95e-01

Pos logit contributions
 unison+0.528
latable+0.519
 Deal+0.496
ric+0.489
igsaw+0.478
Neg logit contributions
 whispered-0.396
 said-0.396
 fell-0.393
 woke-0.371
l-0.362
Tokens
Token ID82
Feature activation-2.36e-01

Pos logit contributions
ric+0.522
 unison+0.481
igsaw+0.464
latable+0.464
 Deal+0.463
Neg logit contributions
 whispered-0.318
 prick-0.288
chy-0.271
 woke-0.269
 spark-0.256
Token not
Token ID407
Feature activation-2.44e-01

Pos logit contributions
 unison+0.384
latable+0.381
 Deal+0.367
igsaw+0.361
ric+0.360
Neg logit contributions
 said-0.295
 whispered-0.291
 fell-0.279
 woke-0.266
 meant-0.263
Token think
Token ID892
Feature activation-2.01e-01

Pos logit contributions
 unison+0.379
latable+0.367
ric+0.365
 Deal+0.355
igsaw+0.345
Neg logit contributions
 whispered-0.312
 said-0.295
 woke-0.283
 fell-0.282
 meant-0.277
Token about
Token ID546
Feature activation-1.94e-01

Pos logit contributions
 unison+0.309
ric+0.301
latable+0.297
 Deal+0.280
igsaw+0.279
Neg logit contributions
 whispered-0.248
 woke-0.223
chy-0.223
 said-0.220
 fell-0.216
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
l+0.114
 whispered+0.111
chy+0.109
 low+0.107
 prick+0.106
Neg logit contributions
latable-0.205
 unison-0.203
ric-0.195
ap-0.185
 hey-0.184
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
TokenLet
Token ID5756
Feature activation-2.55e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.80e-01

Pos logit contributions
 unison+0.468
ric+0.465
latable+0.455
 Deal+0.445
igsaw+0.436
Neg logit contributions
 whispered-0.265
 said-0.260
 woke-0.241
 fell-0.235
 meant-0.232
Token
Token ID26391
Feature activation-3.28e-01

Pos logit contributions
 unison+0.355
ric+0.341
latable+0.338
 Deal+0.324
igsaw+0.314
Neg logit contributions
 whispered-0.434
 said-0.413
 woke-0.401
 fell-0.398
chy-0.395
Token
Token ID8151
Feature activation-2.95e-01

Pos logit contributions
 unison+0.528
latable+0.519
 Deal+0.496
ric+0.489
igsaw+0.478
Neg logit contributions
 whispered-0.396
 said-0.396
 fell-0.393
 woke-0.371
l-0.362
Tokens
Token ID82
Feature activation-2.36e-01

Pos logit contributions
ric+0.522
 unison+0.481
igsaw+0.464
latable+0.464
 Deal+0.463
Neg logit contributions
 whispered-0.318
 prick-0.288
chy-0.271
 woke-0.269
 spark-0.256
Token play
Token ID711
Feature activation-1.90e-01

Pos logit contributions
 unison+0.384
latable+0.381
 Deal+0.367
igsaw+0.361
ric+0.360
Neg logit contributions
 said-0.295
 whispered-0.291
 fell-0.279
 woke-0.266
 meant-0.263
Token a
Token ID257
Feature activation-2.18e-01

Pos logit contributions
 unison+0.316
ric+0.315
latable+0.308
 Deal+0.301
igsaw+0.295
Neg logit contributions
 whispered-0.216
 said-0.206
 woke-0.195
 fell-0.193
l-0.189
Token joke
Token ID9707
Feature activation-1.39e-01

Pos logit contributions
 unison+0.354
latable+0.341
ric+0.341
 Deal+0.327
igsaw+0.323
Neg logit contributions
 whispered-0.260
 said-0.240
 woke-0.232
 fell-0.230
 meant-0.228
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
 prick+0.122
chy+0.110
 iv+0.108
looking+0.106
 whispered+0.105
Neg logit contributions
ric-0.187
 unison-0.179
 teammates-0.164
latable-0.163
ap-0.159
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
TokenLet
Token ID5756
Feature activation-2.55e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.80e-01

Pos logit contributions
 unison+0.468
ric+0.465
latable+0.455
 Deal+0.445
igsaw+0.436
Neg logit contributions
 whispered-0.265
 said-0.260
 woke-0.241
 fell-0.235
 meant-0.232
Token
Token ID26391
Feature activation-3.28e-01

Pos logit contributions
 unison+0.355
ric+0.341
latable+0.338
 Deal+0.324
igsaw+0.314
Neg logit contributions
 whispered-0.434
 said-0.413
 woke-0.401
 fell-0.398
chy-0.395
Token
Token ID8151
Feature activation-2.95e-01

Pos logit contributions
 unison+0.528
latable+0.519
 Deal+0.496
ric+0.489
igsaw+0.478
Neg logit contributions
 whispered-0.396
 said-0.396
 fell-0.393
 woke-0.371
l-0.362
Tokens
Token ID82
Feature activation-2.36e-01

Pos logit contributions
ric+0.522
 unison+0.481
igsaw+0.464
latable+0.464
 Deal+0.463
Neg logit contributions
 whispered-0.318
 prick-0.288
chy-0.271
 woke-0.269
 spark-0.256
Token have
Token ID423
Feature activation-2.22e-01

Pos logit contributions
 unison+0.384
latable+0.381
 Deal+0.367
igsaw+0.361
ric+0.360
Neg logit contributions
 said-0.295
 whispered-0.291
 fell-0.279
 woke-0.266
 meant-0.263
Token a
Token ID257
Feature activation-2.14e-01

Pos logit contributions
ric+0.349
 unison+0.343
latable+0.334
 Deal+0.326
igsaw+0.313
Neg logit contributions
 whispered-0.292
 said-0.285
 woke-0.262
 fell-0.261
 meant-0.254
Token stretching
Token ID20880
Feature activation-1.56e-01

Pos logit contributions
 unison+0.348
ric+0.343
latable+0.336
 Deal+0.327
igsaw+0.317
Neg logit contributions
 whispered-0.252
 said-0.236
 woke-0.228
 fell-0.225
chy-0.223
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
 whispered+0.107
 said+0.100
 woke+0.096
 fell+0.095
chy+0.094
Neg logit contributions
 unison-0.155
ric-0.151
latable-0.150
 Deal-0.145
igsaw-0.142
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
Tokenplease
Token ID29688
Feature activation-2.28e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.79e-01

Pos logit contributions
ric+0.322
 unison+0.299
 Deal+0.286
 yeah+0.284
ap+0.278
Neg logit contributions
 whispered-0.308
chy-0.301
 woke-0.291
 aisle-0.288
 prick-0.283
Token
Token ID26391
Feature activation-3.26e-01

Pos logit contributions
ric+0.330
 unison+0.325
latable+0.314
 Deal+0.310
igsaw+0.296
Neg logit contributions
 whispered-0.456
 woke-0.424
 said-0.422
 fell-0.419
l-0.410
Token and
Token ID290
Feature activation-2.24e-01

Pos logit contributions
 unison+0.508
latable+0.492
ric+0.489
 Deal+0.474
igsaw+0.460
Neg logit contributions
 whispered-0.409
 said-0.389
 fell-0.375
 woke-0.374
l-0.365
Token
Token ID6184
Feature activation-2.20e-01

Pos logit contributions
 unison+0.344
ric+0.335
latable+0.332
 Deal+0.321
igsaw+0.313
Neg logit contributions
 whispered-0.284
 said-0.265
 woke-0.257
 fell-0.255
chy-0.253
Token
Token ID95
Feature activation-2.13e-01

Pos logit contributions
 unison+0.278
ric+0.270
latable+0.262
 Deal+0.255
igsaw+0.245
Neg logit contributions
 whispered-0.331
 said-0.321
l-0.308
 fell-0.307
 woke-0.303
Token
Token ID26391
Feature activation-2.84e-01

Pos logit contributions
 unison+0.271
ric+0.261
latable+0.255
 Deal+0.247
igsaw+0.237
Neg logit contributions
 whispered-0.325
 said-0.311
 woke-0.300
chy-0.297
 fell-0.297
Token
Token ID129
Feature activation-2.36e-01

Pos logit contributions
 unison+0.451
latable+0.439
ric+0.433
 Deal+0.421
igsaw+0.411
Neg logit contributions
 whispered-0.349
 said-0.333
 fell-0.324
 woke-0.321
l-0.313
Token,
Token ID11
Feature activation-3.57e-01

Pos logit contributions
 whispered+0.139
 said+0.130
 woke+0.128
 fell+0.127
chy+0.126
Neg logit contributions
 unison-0.123
ric-0.118
latable-0.117
 Deal-0.112
igsaw-0.109
Token the
Token ID262
Feature activation-3.28e-01

Pos logit contributions
 unison+0.580
ric+0.568
latable+0.552
 Deal+0.542
igsaw+0.520
Neg logit contributions
 whispered-0.408
chy-0.367
 said-0.365
 woke-0.364
l-0.360
Token little
Token ID1310
Feature activation-2.94e-01

Pos logit contributions
 unison+0.556
ric+0.542
latable+0.522
 Deal+0.515
igsaw+0.504
Neg logit contributions
 whispered-0.365
 said-0.328
 woke-0.323
 fell-0.321
 meant-0.317
Token girl
Token ID2576
Feature activation-2.42e-01

Pos logit contributions
 unison+0.565
ric+0.553
latable+0.548
 Deal+0.533
igsaw+0.524
Neg logit contributions
 whispered-0.259
 said-0.234
 woke-0.225
 fell-0.221
chy-0.219
Tokenâ
Token ID22940
Feature activation-2.83e-01

Pos logit contributions
 unison+0.444
ric+0.431
ap+0.398
latable+0.394
 yeah+0.386
Neg logit contributions
 prick-0.182
chy-0.180
l-0.175
 whispered-0.170
 aisle-0.169
Token
Token ID26391
Feature activation-3.24e-01

Pos logit contributions
ric+0.340
 unison+0.337
latable+0.318
 Deal+0.307
igsaw+0.304
Neg logit contributions
 whispered-0.448
l-0.434
 prick-0.427
 fell-0.420
 woke-0.417
Token
Token ID8151
Feature activation-2.85e-01

Pos logit contributions
 unison+0.610
latable+0.606
 Deal+0.593
ric+0.582
igsaw+0.573
Neg logit contributions
 whispered-0.301
 said-0.288
 fell-0.279
 woke-0.269
l-0.254
Tokens
Token ID82
Feature activation-2.37e-01

Pos logit contributions
ric+0.458
 unison+0.411
ifying+0.392
 yeah+0.382
 Deal+0.380
Neg logit contributions
 whispered-0.353
 prick-0.346
chy-0.321
 spark-0.310
 meant-0.306
Token l
Token ID300
Feature activation-2.16e-01

Pos logit contributions
 unison+0.345
ric+0.335
latable+0.326
 Deal+0.316
igsaw+0.307
Neg logit contributions
 whispered-0.323
 said-0.298
 woke-0.292
chy-0.290
 fell-0.289
Tokenimes
Token ID999
Feature activation-1.85e-01

Pos logit contributions
 unison+0.294
 Deal+0.280
ric+0.276
latable+0.274
igsaw+0.266
Neg logit contributions
 whispered-0.317
 said-0.297
 woke-0.297
 meant-0.287
 fell-0.286
Token were
Token ID547
Feature activation-1.99e-01

Pos logit contributions
ifying+0.243
 unison+0.236
ric+0.224
ap+0.223
 such+0.222
Neg logit contributions
 whispered-0.196
 prick-0.188
 low-0.187
 aisle-0.180
 woke-0.179
Token
Token ID129
Feature activation-4.32e-01

Pos logit contributions
 whispered+0.230
 said+0.225
 fell+0.218
chy+0.217
 woke+0.214
Neg logit contributions
ric-0.205
 unison-0.205
 Deal-0.189
latable-0.183
 yeah-0.173
Token
Token ID241
Feature activation-4.07e-01

Pos logit contributions
 unison+0.657
latable+0.613
 Deal+0.603
ric+0.598
igsaw+0.590
Neg logit contributions
 whispered-0.575
 said-0.557
 fell-0.534
 woke-0.531
l-0.526
TokenPlease
Token ID5492
Feature activation-2.93e-01

Pos logit contributions
 unison+0.706
ric+0.686
latable+0.683
 Deal+0.663
igsaw+0.650
Neg logit contributions
 whispered-0.437
 said-0.406
 woke-0.390
 fell-0.386
chy-0.381
Token don
Token ID836
Feature activation-2.70e-01

Pos logit contributions
 unison+0.444
ric+0.433
latable+0.422
 Deal+0.420
 yeah+0.394
Neg logit contributions
 whispered-0.374
 said-0.340
chy-0.337
 woke-0.337
l-0.333
Tokenâ
Token ID22940
Feature activation-2.74e-01

Pos logit contributions
 unison+0.491
ric+0.474
latable+0.467
 yeah+0.438
igsaw+0.437
Neg logit contributions
 said-0.286
 whispered-0.280
 fell-0.276
l-0.273
 meant-0.266
Token
Token ID26391
Feature activation-3.24e-01

Pos logit contributions
 unison+0.346
ric+0.334
latable+0.331
 Deal+0.319
igsaw+0.308
Neg logit contributions
 whispered-0.426
 said-0.402
 woke-0.393
 fell-0.390
chy-0.387
Token
Token ID8151
Feature activation-2.88e-01

Pos logit contributions
 unison+0.505
latable+0.491
ric+0.482
 Deal+0.466
igsaw+0.458
Neg logit contributions
 whispered-0.410
 said-0.397
 fell-0.384
 woke-0.376
l-0.366
Tokent
Token ID83
Feature activation-2.36e-01

Pos logit contributions
ric+0.498
 unison+0.459
 Deal+0.457
ifying+0.449
igsaw+0.448
Neg logit contributions
 whispered-0.318
 prick-0.287
 woke-0.266
 spark-0.265
 buzz-0.259
Token eat
Token ID4483
Feature activation-1.56e-01

Pos logit contributions
ric+0.333
 unison+0.329
latable+0.311
 Deal+0.308
igsaw+0.301
Neg logit contributions
 whispered-0.321
 said-0.290
 woke-0.285
chy-0.285
l-0.283
Token me
Token ID502
Feature activation-1.67e-01

Pos logit contributions
 unison+0.198
ric+0.193
latable+0.191
 Deal+0.183
igsaw+0.177
Neg logit contributions
 whispered-0.238
 said-0.220
 woke-0.219
 fell-0.216
chy-0.216
Token,
Token ID11
Feature activation-2.12e-01

Pos logit contributions
ric+0.261
 unison+0.260
 Deal+0.250
latable+0.250
igsaw+0.240
Neg logit contributions
 whispered-0.191
 woke-0.175
l-0.174
chy-0.169
 said-0.168
Token very
Token ID845
Feature activation-3.60e-01

Pos logit contributions
 whispered+0.077
l+0.064
 said+0.061
 shouted+0.058
 cried+0.057
Neg logit contributions
latable-0.166
 unison-0.160
ric-0.160
igsaw-0.156
ap-0.151
Token much
Token ID881
Feature activation-3.05e-01

Pos logit contributions
 unison+0.539
 Deal+0.536
latable+0.509
 gonna+0.505
ric+0.503
Neg logit contributions
 whispered-0.384
 woke-0.375
chy-0.358
 meant-0.344
 aisle-0.330
Token.
Token ID13
Feature activation-3.18e-01

Pos logit contributions
 unison+0.475
igsaw+0.461
latable+0.457
ric+0.433
 Deal+0.432
Neg logit contributions
 whispered-0.324
 woke-0.309
chy-0.292
 fell-0.281
l-0.274
Token<|endoftext|>
Token ID50256
Feature activation-2.90e-01

Pos logit contributions
 unison+0.498
ric+0.482
latable+0.474
 Deal+0.466
igsaw+0.450
Neg logit contributions
 whispered-0.397
 said-0.367
chy-0.360
 woke-0.360
 fell-0.358
TokenOnce
Token ID7454
Feature activation-2.66e-01

Pos logit contributions
ric+0.377
 unison+0.354
 Deal+0.335
igsaw+0.331
latable+0.331
Neg logit contributions
 whispered-0.420
chy-0.405
 prick-0.391
 meant-0.361
 wil-0.354
Token upon
Token ID2402
Feature activation-3.23e-01

Pos logit contributions
ric+0.282
 unison+0.278
latable+0.261
 Deal+0.259
igsaw+0.254
Neg logit contributions
 whispered-0.454
 said-0.421
 woke-0.417
chy-0.413
 meant-0.411
Token a
Token ID257
Feature activation-2.28e-01

Pos logit contributions
ric+0.642
 unison+0.615
latable+0.609
 Deal+0.607
igsaw+0.607
Neg logit contributions
 said-0.314
 whispered-0.313
 fell-0.300
 woke-0.300
 low-0.265
Token time
Token ID640
Feature activation-2.06e-01

Pos logit contributions
 unison+0.444
ric+0.442
latable+0.428
 Deal+0.419
igsaw+0.414
Neg logit contributions
 whispered-0.192
 said-0.178
 woke-0.173
 fell-0.170
chy-0.167
Token,
Token ID11
Feature activation-2.10e-01

Pos logit contributions
 unison+0.428
ric+0.414
latable+0.412
 Deal+0.399
igsaw+0.390
Neg logit contributions
 whispered-0.159
 said-0.149
 fell-0.142
 woke-0.140
l-0.133
Token there
Token ID612
Feature activation-1.91e-01

Pos logit contributions
 unison+0.333
ric+0.328
latable+0.322
 Deal+0.312
igsaw+0.304
Neg logit contributions
 whispered-0.253
 said-0.231
 woke-0.227
chy-0.221
l-0.220
Token was
Token ID373
Feature activation-1.87e-01

Pos logit contributions
ric+0.340
 unison+0.328
latable+0.326
 yeah+0.302
ap+0.302
Neg logit contributions
 whispered-0.187
chy-0.160
l-0.155
 prick-0.147
 aisle-0.137
Token
Token ID26391
Feature activation-4.93e-01

Pos logit contributions
 whispered+0.028
 said+0.026
 fell+0.025
 woke+0.025
chy+0.025
Neg logit contributions
 unison-0.037
ric-0.037
latable-0.036
 Deal-0.035
igsaw-0.034
Token
Token ID129
Feature activation-3.90e-01

Pos logit contributions
 unison+0.845
latable+0.840
ric+0.800
 Deal+0.792
igsaw+0.790
Neg logit contributions
 whispered-0.540
 said-0.528
 fell-0.510
 woke-0.490
chy-0.470
Token
Token ID241
Feature activation-3.88e-01

Pos logit contributions
 unison+0.521
ric+0.501
latable+0.498
 Deal+0.478
igsaw+0.464
Neg logit contributions
 whispered-0.576
 said-0.546
 woke-0.529
 fell-0.525
chy-0.522
TokenWho
Token ID8241
Feature activation-2.59e-01

Pos logit contributions
 unison+0.635
ric+0.626
latable+0.610
 Deal+0.596
igsaw+0.578
Neg logit contributions
 whispered-0.454
 said-0.418
 woke-0.407
 fell-0.400
chy-0.398
Tokenâ
Token ID22940
Feature activation-2.73e-01

Pos logit contributions
 unison+0.445
ric+0.431
latable+0.425
 Deal+0.411
igsaw+0.402
Neg logit contributions
 whispered-0.272
 said-0.244
chy-0.244
l-0.240
 woke-0.239
Token
Token ID26391
Feature activation-3.22e-01

Pos logit contributions
 unison+0.313
ric+0.312
latable+0.300
 Deal+0.289
igsaw+0.282
Neg logit contributions
 whispered-0.452
 said-0.426
 woke-0.419
 fell-0.417
chy-0.414
Token
Token ID8151
Feature activation-2.92e-01

Pos logit contributions
 unison+0.502
latable+0.488
ric+0.482
 Deal+0.467
igsaw+0.451
Neg logit contributions
 whispered-0.408
 said-0.389
 fell-0.377
 woke-0.376
l-0.363
Tokens
Token ID82
Feature activation-2.33e-01

Pos logit contributions
ric+0.509
 unison+0.444
igsaw+0.437
ifying+0.436
 Deal+0.436
Neg logit contributions
 whispered-0.332
 prick-0.304
chy-0.280
 woke-0.278
 spark-0.271
Token there
Token ID612
Feature activation-2.16e-01

Pos logit contributions
 unison+0.320
latable+0.307
ric+0.304
 Deal+0.297
igsaw+0.285
Neg logit contributions
 whispered-0.339
 said-0.326
 woke-0.314
 fell-0.310
 meant-0.307
Token?
Token ID30
Feature activation-2.67e-01

Pos logit contributions
ric+0.253
 unison+0.231
latable+0.223
 Deal+0.214
 yeah+0.212
Neg logit contributions
 whispered-0.350
chy-0.320
 prick-0.313
l-0.312
 fell-0.309
Tokenâ
Token ID22940
Feature activation-2.17e-01

Pos logit contributions
 unison+0.359
ric+0.348
latable+0.343
 Deal+0.332
igsaw+0.322
Neg logit contributions
 whispered-0.389
 said-0.367
 woke-0.358
 fell-0.355
chy-0.354
Token
Token ID129
Feature activation-4.32e-01

Pos logit contributions
 whispered+0.034
chy+0.033
l+0.032
 woke+0.031
 prick+0.031
Neg logit contributions
 unison-0.017
ric-0.016
latable-0.016
 Deal-0.016
 gonna-0.014
Token
Token ID241
Feature activation-4.07e-01

Pos logit contributions
 unison+0.657
latable+0.613
 Deal+0.603
ric+0.598
igsaw+0.590
Neg logit contributions
 whispered-0.575
 said-0.557
 fell-0.534
 woke-0.531
l-0.526
TokenWhy
Token ID5195
Feature activation-3.13e-01

Pos logit contributions
 unison+0.706
ric+0.686
latable+0.683
 Deal+0.663
igsaw+0.650
Neg logit contributions
 whispered-0.437
 said-0.406
 woke-0.390
 fell-0.386
chy-0.381
Token don
Token ID836
Feature activation-2.67e-01

Pos logit contributions
 unison+0.487
latable+0.470
ric+0.470
 Deal+0.453
igsaw+0.444
Neg logit contributions
 whispered-0.395
 said-0.375
 woke-0.361
 fell-0.357
chy-0.353
Tokenâ
Token ID22940
Feature activation-2.70e-01

Pos logit contributions
 unison+0.573
latable+0.538
ric+0.535
 Deal+0.516
 Majesty+0.509
Neg logit contributions
 said-0.228
 fell-0.222
l-0.216
 meant-0.214
 whispered-0.203
Token
Token ID26391
Feature activation-3.21e-01

Pos logit contributions
 unison+0.337
ric+0.329
latable+0.324
 Deal+0.313
igsaw+0.301
Neg logit contributions
 whispered-0.421
 said-0.395
 woke-0.388
 fell-0.386
l-0.384
Token
Token ID8151
Feature activation-2.83e-01

Pos logit contributions
 unison+0.494
latable+0.478
ric+0.470
 Deal+0.456
igsaw+0.446
Neg logit contributions
 whispered-0.415
 said-0.399
 fell-0.386
 woke-0.384
l-0.369
Tokent
Token ID83
Feature activation-2.33e-01

Pos logit contributions
ric+0.477
ifying+0.426
 unison+0.424
 Deal+0.420
 yeah+0.420
Neg logit contributions
 whispered-0.322
 prick-0.305
 spark-0.272
 buzz-0.268
chy-0.263
Token you
Token ID345
Feature activation-2.12e-01

Pos logit contributions
ric+0.337
 unison+0.334
latable+0.320
igsaw+0.308
 Deal+0.308
Neg logit contributions
 whispered-0.311
 said-0.283
 woke-0.278
chy-0.277
 fell-0.276
Token come
Token ID1282
Feature activation-1.59e-01

Pos logit contributions
ric+0.279
 unison+0.274
 Deal+0.258
 yeah+0.248
latable+0.246
Neg logit contributions
 whispered-0.281
 aisle-0.277
l-0.266
chy-0.258
 prick-0.257
Token with
Token ID351
Feature activation-1.85e-01

Pos logit contributions
 unison+0.280
latable+0.271
ric+0.270
 Deal+0.261
igsaw+0.258
Neg logit contributions
 whispered-0.172
 said-0.160
 woke-0.153
 fell-0.151
chy-0.148
Token but
Token ID475
Feature activation+5.44e-02

Pos logit contributions
 said+0.064
 whispered+0.064
 meant+0.058
 man+0.057
 woke+0.054
Neg logit contributions
ric-0.111
latable-0.107
 unison-0.106
igsaw-0.106
ifying-0.102
Token you
Token ID345
Feature activation+7.83e-02

Pos logit contributions
 said+0.077
 whispered+0.077
 meant+0.071
 fell+0.069
 knew+0.068
Neg logit contributions
 unison-0.082
latable-0.079
ric-0.076
igsaw-0.076
 Deal-0.073
Token have
Token ID423
Feature activation+8.65e-02

Pos logit contributions
 whispered+0.086
 said+0.081
 woke+0.077
 fell+0.076
 meant+0.075
Neg logit contributions
 unison-0.137
latable-0.134
ric-0.133
 Deal-0.129
igsaw-0.128
Token to
Token ID284
Feature activation+9.51e-02

Pos logit contributions
 whispered+0.099
 said+0.095
 fell+0.088
 woke+0.088
 meant+0.086
Neg logit contributions
 unison-0.150
latable-0.146
ric-0.145
 Deal-0.141
igsaw-0.138
Token be
Token ID307
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.135
 said+0.128
 woke+0.122
 fell+0.121
chy+0.120
Neg logit contributions
 unison-0.133
ric-0.132
latable-0.130
igsaw-0.124
 Deal-0.123
Token careful
Token ID8161
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.124
 said+0.116
 fell+0.107
 meant+0.106
 woke+0.105
Neg logit contributions
 unison-0.192
ric-0.190
latable-0.187
igsaw-0.181
 Deal-0.178
Token with
Token ID351
Feature activation+9.90e-02

Pos logit contributions
 whispered+0.065
 said+0.060
 fell+0.056
chy+0.055
 meant+0.052
Neg logit contributions
 unison-0.247
latable-0.240
ric-0.240
 Deal-0.236
igsaw-0.232
Token other
Token ID584
Feature activation+1.22e-01

Pos logit contributions
 whispered+0.154
 woke+0.145
 said+0.144
 fell+0.143
chy+0.141
Neg logit contributions
 unison-0.123
ric-0.121
latable-0.116
 Deal-0.111
igsaw-0.108
Token people
Token ID661
Feature activation+1.51e-01

Pos logit contributions
 whispered+0.165
 said+0.154
 fell+0.153
chy+0.153
 woke+0.153
Neg logit contributions
 unison-0.178
ric-0.167
latable-0.165
 Deal-0.163
igsaw-0.156
Token's
Token ID338
Feature activation+9.53e-02

Pos logit contributions
 whispered+0.135
 woke+0.125
 fell+0.119
chy+0.117
 said+0.116
Neg logit contributions
 unison-0.275
ric-0.270
latable-0.260
 Deal-0.255
igsaw-0.252
Token things
Token ID1243
Feature activation+1.40e-01

Pos logit contributions
 whispered+0.141
 fell+0.138
 woke+0.136
chy+0.136
 said+0.132
Neg logit contributions
 unison-0.119
ric-0.112
latable-0.104
 Deal-0.102
igsaw-0.098
Token old
Token ID1468
Feature activation+1.42e-01

Pos logit contributions
 whispered+0.100
 woke+0.094
 meant+0.091
chy+0.090
 fell+0.089
Neg logit contributions
igsaw-0.136
latable-0.118
 teammates-0.115
 unison-0.112
ocol-0.112
Token.
Token ID13
Feature activation+1.71e-02

Pos logit contributions
 whispered+0.128
chy+0.122
 fell+0.116
 woke+0.116
l+0.116
Neg logit contributions
 unison-0.261
ric-0.247
latable-0.243
 yeah-0.232
 Deal-0.230
Token Every
Token ID3887
Feature activation+7.77e-02

Pos logit contributions
 whispered+0.025
l+0.023
 fell+0.022
chy+0.022
 said+0.022
Neg logit contributions
 unison-0.023
ric-0.023
latable-0.023
 Deal-0.023
igsaw-0.022
Token morning
Token ID3329
Feature activation+1.34e-01

Pos logit contributions
 whispered+0.075
l+0.069
 said+0.062
 shouted+0.060
 spoke+0.055
Neg logit contributions
latable-0.139
 unison-0.138
igsaw-0.134
ric-0.129
ap-0.128
Token,
Token ID11
Feature activation+9.20e-02

Pos logit contributions
 whispered+0.155
chy+0.147
 meant+0.135
l+0.134
 prick+0.129
Neg logit contributions
 unison-0.194
 yeah-0.190
ric-0.188
latable-0.187
ap-0.186
Token she
Token ID673
Feature activation+1.01e-01

Pos logit contributions
 whispered+0.062
 said+0.055
 woke+0.052
 fell+0.050
chy+0.050
Neg logit contributions
 unison-0.197
ric-0.193
latable-0.192
 Deal-0.187
igsaw-0.184
Token would
Token ID561
Feature activation+1.12e-01

Pos logit contributions
l+0.080
 whispered+0.079
 aisle+0.072
 prick+0.071
 meant+0.069
Neg logit contributions
latable-0.172
ric-0.170
 unison-0.169
ap-0.158
 hey-0.156
Token pray
Token ID12472
Feature activation+1.72e-01

Pos logit contributions
 whispered+0.163
 said+0.152
l+0.152
 meant+0.147
chy+0.145
Neg logit contributions
 unison-0.149
ric-0.144
latable-0.144
 Deal-0.137
igsaw-0.127
Token.
Token ID13
Feature activation+2.19e-02

Pos logit contributions
 whispered+0.256
l+0.248
 fell+0.240
 aisle+0.233
 said+0.232
Neg logit contributions
ric-0.205
 unison-0.202
ap-0.192
 Deal-0.187
latable-0.176
Token She
Token ID1375
Feature activation+9.12e-02

Pos logit contributions
 whispered+0.028
l+0.026
 said+0.026
 fell+0.025
chy+0.025
Neg logit contributions
ric-0.034
 unison-0.033
 Deal-0.033
latable-0.032
igsaw-0.031
Token would
Token ID561
Feature activation+1.15e-01

Pos logit contributions
l+0.093
 aisle+0.093
 prick+0.083
 low+0.078
ho+0.078
Neg logit contributions
 unison-0.138
ric-0.137
latable-0.122
ap-0.121
 Deal-0.119
Token were
Token ID547
Feature activation+9.41e-02

Pos logit contributions
l+0.082
chy+0.081
 dies+0.076
 whispered+0.074
 man+0.072
Neg logit contributions
 unison-0.124
latable-0.113
ric-0.107
pieces-0.102
 hey-0.101
Token bright
Token ID6016
Feature activation+1.32e-01

Pos logit contributions
 whispered+0.120
 woke+0.119
l+0.116
chy+0.112
 fell+0.109
Neg logit contributions
 unison-0.138
latable-0.135
ric-0.134
 Deal-0.127
 gonna-0.122
Token and
Token ID290
Feature activation+9.49e-02

Pos logit contributions
 whispered+0.081
 said+0.075
l+0.065
 meant+0.063
 fell+0.063
Neg logit contributions
ric-0.295
 unison-0.291
 Deal-0.290
latable-0.280
igsaw-0.275
Token colorful
Token ID20239
Feature activation+1.47e-01

Pos logit contributions
 whispered+0.098
 woke+0.089
l+0.085
chy+0.085
 said+0.083
Neg logit contributions
 unison-0.166
latable-0.160
ric-0.158
 Deal-0.153
igsaw-0.151
Token,
Token ID11
Feature activation+8.13e-02

Pos logit contributions
 whispered+0.115
 said+0.101
 woke+0.098
 fell+0.095
chy+0.094
Neg logit contributions
 unison-0.299
ric-0.291
latable-0.290
 Deal-0.281
igsaw-0.278
Token and
Token ID290
Feature activation+9.06e-02

Pos logit contributions
 whispered+0.090
 woke+0.083
l+0.082
chy+0.081
 said+0.079
Neg logit contributions
 unison-0.136
latable-0.132
ric-0.127
 Deal-0.121
igsaw-0.121
Token smelled
Token ID37609
Feature activation+1.34e-01

Pos logit contributions
 whispered+0.129
 woke+0.120
chy+0.119
 said+0.118
l+0.118
Neg logit contributions
 unison-0.124
latable-0.118
ric-0.116
 Deal-0.111
igsaw-0.109
Token so
Token ID523
Feature activation+8.61e-02

Pos logit contributions
 whispered+0.166
 said+0.153
 woke+0.149
 fell+0.148
chy+0.146
Neg logit contributions
 unison-0.212
ric-0.205
latable-0.205
 Deal-0.196
igsaw-0.192
Token good
Token ID922
Feature activation+1.45e-01

Pos logit contributions
 whispered+0.101
 woke+0.091
 aisle+0.085
 said+0.084
chy+0.084
Neg logit contributions
 unison-0.139
latable-0.135
igsaw-0.132
 Deal-0.127
 yeah-0.126
Token!
Token ID0
Feature activation+1.68e-02

Pos logit contributions
 whispered+0.097
 said+0.089
 woke+0.079
 fell+0.079
 meant+0.077
Neg logit contributions
 unison-0.315
ric-0.311
latable-0.306
 Deal-0.302
igsaw-0.293
Token When
Token ID1649
Feature activation+6.72e-02

Pos logit contributions
 whispered+0.022
 said+0.021
 woke+0.020
 fell+0.020
 meant+0.019
Neg logit contributions
 unison-0.025
ric-0.025
latable-0.024
 Deal-0.023
igsaw-0.023
Token
Token ID198
Feature activation-5.09e-02

Pos logit contributions
 unison+0.059
ric+0.058
latable+0.054
 Deal+0.053
igsaw+0.047
Neg logit contributions
chy-0.071
 whispered-0.070
 prick-0.065
 meant-0.065
 woke-0.064
TokenThey
Token ID2990
Feature activation+2.65e-02

Pos logit contributions
 unison+0.074
latable+0.070
ric+0.070
 Deal+0.068
igsaw+0.065
Neg logit contributions
 whispered-0.070
 said-0.066
 woke-0.064
chy-0.064
 fell-0.064
Token waited
Token ID13488
Feature activation+8.38e-02

Pos logit contributions
l+0.033
chy+0.031
 prick+0.030
 iv+0.029
 dies+0.028
Neg logit contributions
 unison-0.041
ric-0.034
 hey-0.034
ap-0.032
pieces-0.032
Token for
Token ID329
Feature activation+6.64e-02

Pos logit contributions
 whispered+0.116
 woke+0.107
 meant+0.106
 said+0.106
l+0.106
Neg logit contributions
 unison-0.118
latable-0.111
ric-0.108
 Deal-0.107
igsaw-0.101
Token their
Token ID511
Feature activation+6.54e-02

Pos logit contributions
 whispered+0.084
 said+0.080
 woke+0.075
 fell+0.075
 meant+0.073
Neg logit contributions
ric-0.103
 unison-0.101
latable-0.100
 Deal-0.097
igsaw-0.095
Token mom
Token ID1995
Feature activation+1.07e-01

Pos logit contributions
 whispered+0.101
 woke+0.094
 meant+0.093
l+0.093
chy+0.092
Neg logit contributions
 unison-0.086
latable-0.077
ric-0.075
 Deal-0.075
igsaw-0.074
Token to
Token ID284
Feature activation+7.44e-02

Pos logit contributions
 whispered+0.144
 prick+0.137
 fell+0.136
l+0.135
 woke+0.133
Neg logit contributions
 unison-0.138
ric-0.137
latable-0.130
pieces-0.127
igsaw-0.126
Token come
Token ID1282
Feature activation+1.10e-01

Pos logit contributions
 whispered+0.103
 said+0.097
 woke+0.094
 fell+0.093
chy+0.092
Neg logit contributions
 unison-0.106
ric-0.104
latable-0.103
 Deal-0.099
igsaw-0.097
Token home
Token ID1363
Feature activation+1.25e-01

Pos logit contributions
 whispered+0.096
 said+0.088
 fell+0.082
 woke+0.082
chy+0.077
Neg logit contributions
 unison-0.216
ric-0.214
latable-0.213
 Deal-0.207
igsaw-0.203
Token from
Token ID422
Feature activation+5.83e-02

Pos logit contributions
 whispered+0.139
 woke+0.135
l+0.134
chy+0.132
 meant+0.124
Neg logit contributions
 unison-0.196
ap-0.179
ric-0.178
igsaw-0.177
latable-0.171
Token work
Token ID670
Feature activation+1.24e-01

Pos logit contributions
 whispered+0.094
l+0.090
chy+0.089
 woke+0.089
 said+0.087
Neg logit contributions
 unison-0.070
ric-0.063
latable-0.062
igsaw-0.062
 Deal-0.058
Token hungry
Token ID14720
Feature activation+1.06e-01

Pos logit contributions
 whispered+0.052
 aisle+0.050
 woke+0.048
books+0.048
 meant+0.046
Neg logit contributions
 Deal-0.057
ric-0.056
 hey-0.055
igsaw-0.054
 gonna-0.054
Token,
Token ID11
Feature activation+4.73e-02

Pos logit contributions
 whispered+0.123
 said+0.111
 woke+0.109
 fell+0.107
l+0.107
Neg logit contributions
 unison-0.172
latable-0.169
ric-0.168
 Deal-0.162
igsaw-0.160
Token but
Token ID475
Feature activation+3.86e-02

Pos logit contributions
 whispered+0.058
 said+0.054
 woke+0.053
 fell+0.052
chy+0.051
Neg logit contributions
 unison-0.076
ric-0.074
latable-0.073
 Deal-0.070
igsaw-0.069
Token I
Token ID314
Feature activation+5.58e-02

Pos logit contributions
 whispered+0.063
 said+0.060
 woke+0.059
 fell+0.058
chy+0.058
Neg logit contributions
 unison-0.045
ric-0.044
latable-0.043
 Deal-0.041
igsaw-0.040
Token don
Token ID836
Feature activation+6.08e-02

Pos logit contributions
 whispered+0.068
 said+0.063
 woke+0.061
l+0.060
 fell+0.060
Neg logit contributions
 unison-0.087
ric-0.086
latable-0.085
 Deal-0.082
igsaw-0.080
Token't
Token ID470
Feature activation+5.91e-02

Pos logit contributions
 whispered+0.082
 said+0.078
 fell+0.076
 woke+0.075
l+0.074
Neg logit contributions
 unison-0.090
ric-0.087
latable-0.086
 Deal-0.082
igsaw-0.081
Token have
Token ID423
Feature activation+7.81e-02

Pos logit contributions
 whispered+0.093
l+0.088
 aisle+0.088
 said+0.085
 woke+0.085
Neg logit contributions
ric-0.063
 unison-0.062
 Deal-0.061
latable-0.059
igsaw-0.058
Token anything
Token ID1997
Feature activation+9.03e-02

Pos logit contributions
 whispered+0.133
 said+0.126
l+0.124
chy+0.123
 woke+0.122
Neg logit contributions
 unison-0.082
ric-0.080
latable-0.077
 Deal-0.074
igsaw-0.072
Token to
Token ID284
Feature activation+7.82e-02

Pos logit contributions
 whispered+0.122
 woke+0.113
 aisle+0.113
l+0.109
 said+0.107
Neg logit contributions
 Deal-0.106
 gonna-0.105
latable-0.104
 yeah-0.103
igsaw-0.102
Token eat
Token ID4483
Feature activation+1.33e-01

Pos logit contributions
 whispered+0.109
l+0.100
chy+0.099
 said+0.099
 woke+0.098
Neg logit contributions
 unison-0.107
latable-0.103
ric-0.103
 Deal-0.098
igsaw-0.093
Token."
Token ID526
Feature activation-1.21e-02

Pos logit contributions
 whispered+0.181
 spoke+0.161
 woke+0.160
 said+0.158
 knew+0.155
Neg logit contributions
 unison-0.176
latable-0.176
ric-0.174
 our-0.173
 Deal-0.173
Token bird
Token ID6512
Feature activation+8.40e-02

Pos logit contributions
 whispered+0.028
 said+0.026
 woke+0.025
 fell+0.024
chy+0.024
Neg logit contributions
 unison-0.065
ric-0.063
latable-0.063
 Deal-0.061
igsaw-0.060
Token.
Token ID13
Feature activation-6.16e-02

Pos logit contributions
 whispered+0.061
 said+0.056
 woke+0.052
 fell+0.052
l+0.050
Neg logit contributions
 unison-0.180
latable-0.176
 Deal-0.175
igsaw-0.172
ric-0.171
Token The
Token ID383
Feature activation-5.79e-03

Pos logit contributions
latable+0.072
 unison+0.071
igsaw+0.071
 Deal+0.067
ric+0.067
Neg logit contributions
 whispered-0.091
chy-0.085
l-0.085
 meant-0.082
 fell-0.081
Token bird
Token ID6512
Feature activation+7.76e-02

Pos logit contributions
 unison+0.008
ric+0.008
latable+0.008
 yeah+0.007
 hey+0.007
Neg logit contributions
 whispered-0.007
chy-0.007
 fell-0.006
 aisle-0.006
 meant-0.006
Token said
Token ID531
Feature activation+2.39e-02

Pos logit contributions
 aisle+0.075
books+0.062
book+0.059
chy+0.057
post+0.056
Neg logit contributions
ric-0.133
 unison-0.121
 gonna-0.112
 how-0.112
 yeah-0.112
Token,
Token ID11
Feature activation+7.47e-03

Pos logit contributions
 whispered+0.024
 said+0.022
chy+0.021
 woke+0.021
 meant+0.020
Neg logit contributions
 unison-0.042
ric-0.041
latable-0.041
 Deal-0.040
igsaw-0.039
Token "
Token ID366
Feature activation-1.35e-03

Pos logit contributions
 whispered+0.011
chy+0.011
 aisle+0.011
 prick+0.011
 meant+0.010
Neg logit contributions
ric-0.009
 unison-0.008
 Deal-0.008
 gonna-0.008
latable-0.007
TokenI
Token ID40
Feature activation+9.74e-03

Pos logit contributions
 unison+0.002
ric+0.002
 hey+0.002
 Deal+0.002
 yeah+0.002
Neg logit contributions
chy-0.002
 whispered-0.002
 fell-0.002
 said-0.002
 aisle-0.002
Token can
Token ID460
Feature activation+3.60e-02

Pos logit contributions
 whispered+0.013
l+0.012
 said+0.012
chy+0.012
 aisle+0.012
Neg logit contributions
 unison-0.013
ric-0.013
latable-0.013
 Deal-0.012
igsaw-0.012
Token't
Token ID470
Feature activation+2.55e-02

Pos logit contributions
 whispered+0.054
 said+0.051
 woke+0.050
l+0.049
 fell+0.049
Neg logit contributions
 unison-0.046
ric-0.045
latable-0.044
 Deal-0.043
igsaw-0.040
Token find
Token ID1064
Feature activation+8.26e-02

Pos logit contributions
 whispered+0.038
 said+0.035
chy+0.035
l+0.035
 meant+0.034
Neg logit contributions
 unison-0.031
latable-0.030
ric-0.029
 Deal-0.027
 hey-0.027
Tokenens
Token ID641
Feature activation+8.97e-02

Pos logit contributions
 whispered+0.046
 low+0.041
 woke+0.038
l+0.038
 fell+0.038
Neg logit contributions
latable-0.088
 unison-0.084
 Deal-0.083
igsaw-0.082
ric-0.081
Token.
Token ID13
Feature activation-6.09e-02

Pos logit contributions
 whispered+0.109
l+0.106
 woke+0.103
 prick+0.102
 low+0.099
Neg logit contributions
 unison-0.118
pieces-0.112
latable-0.109
ap-0.107
 teammates-0.107
Token<|endoftext|>
Token ID50256
Feature activation-3.97e-02

Pos logit contributions
 unison+0.096
ric+0.095
latable+0.093
 Deal+0.090
igsaw+0.088
Neg logit contributions
 whispered-0.074
 said-0.068
 woke-0.066
chy-0.066
 fell-0.065
TokenOnce
Token ID7454
Feature activation-1.86e-02

Pos logit contributions
 unison+0.060
ric+0.058
latable+0.058
 Deal+0.056
igsaw+0.054
Neg logit contributions
 whispered-0.049
chy-0.044
 prick-0.042
 said-0.042
 fell-0.041
Token upon
Token ID2402
Feature activation-5.57e-02

Pos logit contributions
 unison+0.023
ric+0.022
latable+0.022
 Deal+0.021
igsaw+0.020
Neg logit contributions
 whispered-0.029
 said-0.027
 woke-0.027
chy-0.026
 fell-0.026
Token a
Token ID257
Feature activation+1.62e-02

Pos logit contributions
ric+0.113
igsaw+0.112
 Deal+0.108
 unison+0.108
latable+0.108
Neg logit contributions
 woke-0.053
 said-0.051
 fell-0.050
 whispered-0.049
 low-0.044
Token time
Token ID640
Feature activation+3.25e-02

Pos logit contributions
 whispered+0.012
 said+0.011
 woke+0.011
 fell+0.011
chy+0.010
Neg logit contributions
ric-0.034
 unison-0.033
latable-0.032
 Deal-0.032
igsaw-0.031
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
 said+0.017
 fell+0.017
 woke+0.016
 whispered+0.016
l+0.013
Neg logit contributions
 unison-0.078
ric-0.075
latable-0.075
 Deal-0.071
ifying-0.070
Token there
Token ID612
Feature activation+3.54e-02

Pos logit contributions
 whispered+0.012
 said+0.011
 woke+0.011
 fell+0.011
chy+0.010
Neg logit contributions
 unison-0.021
ric-0.021
latable-0.021
 Deal-0.020
igsaw-0.020
Token was
Token ID373
Feature activation+2.66e-02

Pos logit contributions
 whispered+0.024
chy+0.018
l+0.018
 said+0.018
 fell+0.016
Neg logit contributions
 unison-0.075
ric-0.075
latable-0.074
 Deal-0.070
 yeah-0.069
Token a
Token ID257
Feature activation+2.29e-02

Pos logit contributions
 said+0.025
 whispered+0.024
 fell+0.022
 woke+0.022
 meant+0.021
Neg logit contributions
ric-0.054
 unison-0.050
 yeah-0.049
 Deal-0.049
latable-0.047
Token.
Token ID13
Feature activation-1.16e-01

Pos logit contributions
 whispered+0.031
 woke+0.028
 fell+0.027
 knew+0.026
chy+0.026
Neg logit contributions
 unison-0.060
ric-0.058
latable-0.056
ap-0.054
ifying-0.054
Token They
Token ID1119
Feature activation-4.86e-02

Pos logit contributions
 unison+0.173
ric+0.165
latable+0.162
 Deal+0.161
igsaw+0.153
Neg logit contributions
 whispered-0.156
chy-0.144
 said-0.144
 woke-0.144
 fell-0.143
Token put
Token ID1234
Feature activation+2.47e-02

Pos logit contributions
 unison+0.085
ric+0.078
latable+0.071
 teammates+0.069
 hey+0.068
Neg logit contributions
l-0.045
 prick-0.043
 aisle-0.042
chy-0.042
 whispered-0.041
Token Lily
Token ID20037
Feature activation+4.89e-03

Pos logit contributions
 whispered+0.036
 woke+0.035
chy+0.034
 fell+0.033
 said+0.033
Neg logit contributions
 unison-0.033
ric-0.031
latable-0.031
 Deal-0.028
ifying-0.028
Token's
Token ID338
Feature activation-1.68e-02

Pos logit contributions
 whispered+0.006
l+0.005
 meant+0.005
 woke+0.005
 said+0.005
Neg logit contributions
ric-0.008
 unison-0.008
latable-0.007
ifying-0.007
igsaw-0.007
Token cow
Token ID9875
Feature activation+4.72e-02

Pos logit contributions
 unison+0.025
ric+0.025
latable+0.024
 Deal+0.023
ifying+0.022
Neg logit contributions
 whispered-0.021
 woke-0.020
 said-0.020
 fell-0.019
 meant-0.019
Token in
Token ID287
Feature activation-2.06e-02

Pos logit contributions
 whispered+0.059
 said+0.055
 woke+0.054
 fell+0.053
chy+0.053
Neg logit contributions
 unison-0.072
ric-0.070
latable-0.069
 Deal-0.065
igsaw-0.065
Token the
Token ID262
Feature activation-3.22e-02

Pos logit contributions
 unison+0.028
ric+0.025
latable+0.025
 Deal+0.024
igsaw+0.024
Neg logit contributions
 whispered-0.031
chy-0.029
 woke-0.029
 fell-0.029
 said-0.029
Token barn
Token ID25203
Feature activation+5.69e-02

Pos logit contributions
 unison+0.049
ric+0.048
latable+0.047
 Deal+0.046
igsaw+0.043
Neg logit contributions
 whispered-0.043
 said-0.040
 fell-0.038
 meant-0.038
l-0.038
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
 whispered+0.064
chy+0.064
 woke+0.062
 meant+0.060
 prick+0.060
Neg logit contributions
ric-0.085
 unison-0.085
ap-0.082
latable-0.075
 teammates-0.071
Token They
Token ID1119
Feature activation-3.21e-02

Pos logit contributions
 unison+0.144
latable+0.134
ric+0.134
 Deal+0.133
igsaw+0.125
Neg logit contributions
 whispered-0.144
chy-0.136
 woke-0.134
 fell-0.132
 said-0.131
Token feels
Token ID5300
Feature activation+2.02e-02

Pos logit contributions
igsaw+0.018
 unison+0.018
ric+0.017
ifying+0.017
pieces+0.017
Neg logit contributions
 said-0.007
 whispered-0.007
 woke-0.006
l-0.006
 fell-0.006
Token bad
Token ID2089
Feature activation+2.53e-02

Pos logit contributions
 whispered+0.021
 said+0.021
 fell+0.019
 meant+0.019
chy+0.019
Neg logit contributions
 unison-0.037
ric-0.037
latable-0.036
igsaw-0.036
 Deal-0.034
Token for
Token ID329
Feature activation+2.65e-02

Pos logit contributions
 whispered+0.023
 aisle+0.020
chy+0.020
l+0.020
 low+0.019
Neg logit contributions
 unison-0.044
ric-0.044
 Deal-0.043
latable-0.042
 yeah-0.041
Token pin
Token ID6757
Feature activation+7.99e-02

Pos logit contributions
 whispered+0.036
 said+0.034
 woke+0.032
 fell+0.032
chy+0.032
Neg logit contributions
 unison-0.039
ric-0.038
latable-0.038
 Deal-0.036
igsaw-0.036
Tokenching
Token ID10813
Feature activation+6.62e-02

Pos logit contributions
 whispered+0.096
 aisle+0.092
 woke+0.089
 said+0.085
 low+0.082
Neg logit contributions
ric-0.114
latable-0.111
 unison-0.109
 Deal-0.107
igsaw-0.106
Token Lily
Token ID20037
Feature activation+4.67e-02

Pos logit contributions
 whispered+0.085
 woke+0.077
chy+0.075
 fell+0.074
 said+0.074
Neg logit contributions
 unison-0.097
ric-0.093
 Deal-0.093
latable-0.091
igsaw-0.088
Token.
Token ID13
Feature activation-6.80e-02

Pos logit contributions
 whispered+0.056
 woke+0.053
 aisle+0.053
 spoke+0.051
 flowed+0.050
Neg logit contributions
ap-0.061
 unison-0.060
ric-0.059
pieces-0.056
latable-0.055
Token He
Token ID679
Feature activation+4.43e-03

Pos logit contributions
 unison+0.100
 Deal+0.100
latable+0.096
ric+0.095
igsaw+0.092
Neg logit contributions
 whispered-0.088
 woke-0.079
chy-0.079
 said-0.077
 fell-0.077
Token sees
Token ID7224
Feature activation+3.63e-02

Pos logit contributions
 whispered+0.004
 said+0.004
 woke+0.004
 fell+0.004
chy+0.004
Neg logit contributions
igsaw-0.009
 unison-0.009
ric-0.009
latable-0.009
ifying-0.008
Token a
Token ID257
Feature activation+1.88e-02

Pos logit contributions
 whispered+0.038
 said+0.037
l+0.034
 woke+0.034
 fell+0.034
Neg logit contributions
 unison-0.066
ric-0.064
latable-0.064
 Deal-0.062
igsaw-0.060
Token red
Token ID2266
Feature activation+6.49e-02

Pos logit contributions
 whispered+0.020
 said+0.018
chy+0.017
 meant+0.017
 fell+0.017
Neg logit contributions
 unison-0.032
ric-0.032
latable-0.030
 Deal-0.030
igsaw-0.029
Token lucky
Token ID9670
Feature activation-8.34e-02

Pos logit contributions
 unison+0.189
ric+0.186
latable+0.183
 Deal+0.179
igsaw+0.174
Neg logit contributions
 whispered-0.109
 said-0.103
 woke-0.096
 fell-0.096
 meant-0.094
Token car
Token ID1097
Feature activation-2.23e-02

Pos logit contributions
 unison+0.133
latable+0.124
ric+0.123
igsaw+0.121
 yeah+0.115
Neg logit contributions
 whispered-0.100
l-0.092
chy-0.090
 said-0.088
 fell-0.087
Token and
Token ID290
Feature activation-1.00e-01

Pos logit contributions
 unison+0.036
ric+0.035
latable+0.034
 yeah+0.033
 hey+0.032
Neg logit contributions
 whispered-0.022
 prick-0.021
 low-0.019
 aisle-0.019
l-0.019
Token was
Token ID373
Feature activation-9.53e-02

Pos logit contributions
 unison+0.175
ric+0.170
latable+0.168
 Deal+0.161
igsaw+0.160
Neg logit contributions
 whispered-0.101
 said-0.090
chy-0.090
l-0.090
 woke-0.089
Token so
Token ID523
Feature activation-1.12e-01

Pos logit contributions
 unison+0.152
ric+0.149
latable+0.145
 Deal+0.140
igsaw+0.136
Neg logit contributions
 whispered-0.114
 said-0.105
 woke-0.104
l-0.102
 fell-0.102
Token thankful
Token ID25535
Feature activation-8.86e-02

Pos logit contributions
 unison+0.171
ric+0.169
latable+0.161
 Deal+0.160
igsaw+0.157
Neg logit contributions
 whispered-0.126
 woke-0.116
chy-0.115
 aisle-0.113
l-0.109
Token for
Token ID329
Feature activation-6.60e-02

Pos logit contributions
 unison+0.135
ric+0.130
latable+0.128
 Deal+0.124
igsaw+0.121
Neg logit contributions
 whispered-0.112
 woke-0.102
 said-0.101
chy-0.101
 fell-0.100
Token the
Token ID262
Feature activation-9.28e-02

Pos logit contributions
 unison+0.093
ric+0.084
 Deal+0.081
latable+0.080
 yeah+0.078
Neg logit contributions
 whispered-0.095
chy-0.092
 woke-0.091
l-0.090
 fell-0.090
Token adventure
Token ID8855
Feature activation-6.67e-03

Pos logit contributions
 unison+0.146
ric+0.136
latable+0.135
 Deal+0.132
igsaw+0.131
Neg logit contributions
 whispered-0.117
 said-0.105
 fell-0.105
 woke-0.104
chy-0.103
Token it
Token ID340
Feature activation-4.12e-02

Pos logit contributions
 unison+0.011
igsaw+0.010
latable+0.010
pieces+0.009
ric+0.009
Neg logit contributions
 whispered-0.007
 prick-0.007
chy-0.007
 woke-0.006
l-0.006
Token was
Token ID373
Feature activation-7.85e-02

Pos logit contributions
 unison+0.063
 such+0.062
 how+0.059
 gonna+0.056
 our+0.056
Neg logit contributions
 prick-0.035
 aisle-0.035
ho-0.033
l-0.033
 whispered-0.031
Token over
Token ID625
Feature activation-1.38e-01

Pos logit contributions
 unison+0.219
ric+0.215
latable+0.211
 Deal+0.205
igsaw+0.200
Neg logit contributions
 whispered-0.144
 said-0.133
 woke-0.130
chy-0.129
 fell-0.129
Token to
Token ID284
Feature activation-1.51e-01

Pos logit contributions
 unison+0.247
ric+0.239
latable+0.237
 Deal+0.232
igsaw+0.227
Neg logit contributions
 whispered-0.142
 said-0.129
chy-0.127
 woke-0.126
 fell-0.125
Token the
Token ID262
Feature activation-1.79e-01

Pos logit contributions
 unison+0.197
ric+0.188
latable+0.183
 Deal+0.180
igsaw+0.174
Neg logit contributions
 whispered-0.223
chy-0.213
 fell-0.208
l-0.206
 said-0.206
Token kitten
Token ID42143
Feature activation-1.10e-01

Pos logit contributions
 unison+0.306
ric+0.289
latable+0.289
igsaw+0.279
 Deal+0.272
Neg logit contributions
 whispered-0.195
 said-0.174
 meant-0.174
 fell-0.173
chy-0.172
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
 unison+0.194
ric+0.191
latable+0.184
igsaw+0.171
ap+0.169
Neg logit contributions
 whispered-0.101
l-0.095
 prick-0.093
 meant-0.093
chy-0.092
Token He
Token ID679
Feature activation-1.59e-01

Pos logit contributions
 unison+0.322
ric+0.309
latable+0.306
igsaw+0.299
 Deal+0.299
Neg logit contributions
 whispered-0.290
chy-0.282
 fell-0.267
l-0.264
 woke-0.264
Token was
Token ID373
Feature activation-1.39e-01

Pos logit contributions
 unison+0.294
ric+0.273
latable+0.272
 yeah+0.255
 gonna+0.254
Neg logit contributions
chy-0.112
 aisle-0.111
l-0.101
 prick-0.101
 low-0.093
Token carrying
Token ID6872
Feature activation-7.77e-02

Pos logit contributions
 unison+0.219
ric+0.212
latable+0.211
 Deal+0.202
igsaw+0.193
Neg logit contributions
 whispered-0.166
 woke-0.156
l-0.154
chy-0.153
 said-0.152
Token a
Token ID257
Feature activation-1.32e-01

Pos logit contributions
 unison+0.090
latable+0.086
igsaw+0.081
ric+0.080
 Deal+0.078
Neg logit contributions
 whispered-0.125
 woke-0.120
chy-0.119
 fell-0.116
 said-0.114
Token warm
Token ID5814
Feature activation-7.70e-02

Pos logit contributions
 unison+0.228
latable+0.219
ric+0.215
igsaw+0.213
 Deal+0.208
Neg logit contributions
 whispered-0.142
 said-0.128
 woke-0.125
 meant-0.125
chy-0.124
Token blanket
Token ID18447
Feature activation-6.04e-02

Pos logit contributions
ric+0.145
 unison+0.145
 Deal+0.143
latable+0.137
 hey+0.133
Neg logit contributions
 whispered-0.073
 woke-0.069
 said-0.069
 fell-0.066
chy-0.062
Token spaghetti
Token ID48241
Feature activation-1.35e-01

Pos logit contributions
 unison+0.256
latable+0.242
ric+0.239
 Deal+0.227
igsaw+0.225
Neg logit contributions
 whispered-0.279
chy-0.262
l-0.259
 woke-0.257
 fell-0.256
Token for
Token ID329
Feature activation-1.54e-01

Pos logit contributions
 unison+0.218
latable+0.210
ric+0.207
igsaw+0.201
 Deal+0.201
Neg logit contributions
 whispered-0.155
 woke-0.139
l-0.138
 said-0.136
chy-0.135
Token dinner
Token ID8073
Feature activation-9.83e-02

Pos logit contributions
 unison+0.200
ric+0.193
latable+0.191
 Deal+0.183
igsaw+0.178
Neg logit contributions
 whispered-0.235
 said-0.223
 woke-0.217
 fell-0.215
chy-0.214
Token,
Token ID11
Feature activation-1.80e-01

Pos logit contributions
 unison+0.182
latable+0.173
igsaw+0.167
 Deal+0.165
ric+0.164
Neg logit contributions
 whispered-0.089
l-0.081
 woke-0.079
chy-0.075
 fell-0.075
Token which
Token ID543
Feature activation-1.39e-01

Pos logit contributions
 unison+0.354
ric+0.350
latable+0.346
 Deal+0.335
igsaw+0.334
Neg logit contributions
 whispered-0.157
 said-0.149
 woke-0.133
 fell-0.132
 meant-0.128
Token was
Token ID373
Feature activation-1.54e-01

Pos logit contributions
 unison+0.232
ric+0.224
latable+0.218
 Deal+0.214
igsaw+0.214
Neg logit contributions
 whispered-0.141
l-0.129
 woke-0.117
chy-0.116
 low-0.116
Token Lily
Token ID20037
Feature activation-1.33e-01

Pos logit contributions
 unison+0.227
latable+0.221
ric+0.220
 Deal+0.215
 gonna+0.202
Neg logit contributions
 whispered-0.191
 woke-0.181
l-0.177
 fell-0.172
 aisle-0.165
Token's
Token ID338
Feature activation-1.51e-01

Pos logit contributions
 unison+0.213
ric+0.205
latable+0.199
 yeah+0.193
ap+0.192
Neg logit contributions
 whispered-0.132
l-0.131
 aisle-0.125
 woke-0.123
 prick-0.120
Token favorite
Token ID4004
Feature activation-1.16e-01

Pos logit contributions
 unison+0.215
latable+0.207
ric+0.206
 Deal+0.204
igsaw+0.194
Neg logit contributions
 whispered-0.210
 woke-0.191
 said-0.191
l-0.190
 fell-0.189
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
 unison+0.213
latable+0.204
ric+0.204
igsaw+0.196
 Deal+0.194
Neg logit contributions
 whispered-0.110
l-0.095
 fell-0.093
 said-0.093
 woke-0.090
Token Lily
Token ID20037
Feature activation-1.27e-01

Pos logit contributions
 unison+0.379
ric+0.369
latable+0.365
 Deal+0.356
igsaw+0.347
Neg logit contributions
 whispered-0.247
 said-0.229
 woke-0.221
 fell-0.219
chy-0.217
Token crown
Token ID12389
Feature activation-8.37e-02

Pos logit contributions
 unison+0.184
ric+0.174
latable+0.169
 Deal+0.165
igsaw+0.164
Neg logit contributions
 whispered-0.236
 said-0.222
 woke-0.219
chy-0.218
 fell-0.218
Token and
Token ID290
Feature activation-1.47e-01

Pos logit contributions
 unison+0.137
ric+0.137
igsaw+0.133
latable+0.131
 yeah+0.127
Neg logit contributions
 whispered-0.086
 woke-0.079
chy-0.076
 said-0.075
 fell-0.075
Token make
Token ID787
Feature activation-1.13e-01

Pos logit contributions
latable+0.243
 unison+0.241
ric+0.241
 Deal+0.232
igsaw+0.228
Neg logit contributions
 whispered-0.183
 said-0.177
 woke-0.163
 fell-0.162
 meant-0.155
Token them
Token ID606
Feature activation-8.42e-02

Pos logit contributions
 unison+0.188
latable+0.184
ric+0.183
 Deal+0.181
igsaw+0.174
Neg logit contributions
 whispered-0.133
 said-0.129
l-0.122
 woke-0.118
 fell-0.117
Token jealous
Token ID19354
Feature activation-1.25e-01

Pos logit contributions
 unison+0.158
latable+0.156
 Deal+0.153
ric+0.151
igsaw+0.145
Neg logit contributions
 whispered-0.085
 said-0.080
l-0.076
 fell-0.075
chy-0.073
Token.
Token ID13
Feature activation-2.12e-01

Pos logit contributions
 unison+0.240
ric+0.229
latable+0.224
 Deal+0.221
igsaw+0.218
Neg logit contributions
 whispered-0.106
chy-0.091
 woke-0.090
 fell-0.089
 said-0.088
Token He
Token ID679
Feature activation-1.42e-01

Pos logit contributions
 unison+0.374
ric+0.365
latable+0.362
 Deal+0.352
igsaw+0.344
Neg logit contributions
 whispered-0.222
 said-0.205
 woke-0.197
 fell-0.195
chy-0.193
Token put
Token ID1234
Feature activation-6.76e-02

Pos logit contributions
 unison+0.266
latable+0.243
ric+0.241
 teammates+0.236
 yeah+0.228
Neg logit contributions
 aisle-0.099
l-0.094
chy-0.092
 prick-0.089
 low-0.088
Token on
Token ID319
Feature activation-8.63e-02

Pos logit contributions
 unison+0.090
ric+0.088
latable+0.084
 Deal+0.083
igsaw+0.081
Neg logit contributions
 whispered-0.094
chy-0.091
 woke-0.088
 fell-0.085
 meant-0.084
Token his
Token ID465
Feature activation-1.09e-01

Pos logit contributions
 unison+0.134
ric+0.130
latable+0.129
 Deal+0.125
igsaw+0.122
Neg logit contributions
 whispered-0.109
 said-0.102
 woke-0.099
 fell-0.098
chy-0.097
Token best
Token ID1266
Feature activation-6.74e-02

Pos logit contributions
 unison+0.173
ric+0.168
latable+0.166
 Deal+0.162
igsaw+0.158
Neg logit contributions
 whispered-0.131
 said-0.122
 woke-0.118
 fell-0.117
chy-0.117
Token
Token ID241
Feature activation-4.61e-01

Pos logit contributions
chy+0.114
 aisle+0.110
 prick+0.104
 whispered+0.103
l+0.101
Neg logit contributions
 unison-0.189
ifying-0.167
ric-0.166
ap-0.165
 teammates-0.161
TokenThat
Token ID2504
Feature activation-2.92e-01

Pos logit contributions
 unison+0.800
latable+0.782
igsaw+0.761
 Deal+0.736
ric+0.717
Neg logit contributions
 said-0.507
 whispered-0.496
 meant-0.470
 fell-0.446
l-0.445
Tokenâ
Token ID22940
Feature activation-3.06e-01

Pos logit contributions
 unison+0.523
ric+0.515
latable+0.507
 Deal+0.491
igsaw+0.483
Neg logit contributions
 whispered-0.293
 said-0.264
 woke-0.258
 fell-0.254
chy-0.252
Token
Token ID26391
Feature activation-3.49e-01

Pos logit contributions
 unison+0.375
ric+0.373
latable+0.361
 Deal+0.350
igsaw+0.343
Neg logit contributions
 whispered-0.484
 woke-0.452
 said-0.447
 fell-0.446
l-0.440
Token
Token ID8151
Feature activation-3.13e-01

Pos logit contributions
 unison+0.525
latable+0.511
ric+0.502
 Deal+0.491
igsaw+0.474
Neg logit contributions
 whispered-0.455
 said-0.438
 fell-0.425
 woke-0.419
l-0.408
Tokens
Token ID82
Feature activation-2.50e-01

Pos logit contributions
ric+0.523
 unison+0.469
igsaw+0.457
 yeah+0.454
latable+0.454
Neg logit contributions
 whispered-0.375
 prick-0.347
 woke-0.320
chy-0.317
 buzz-0.308
Token why
Token ID1521
Feature activation-2.53e-01

Pos logit contributions
 unison+0.413
latable+0.400
ric+0.397
 Deal+0.389
igsaw+0.382
Neg logit contributions
 whispered-0.289
 said-0.280
 woke-0.262
 fell-0.261
 meant-0.261
Token it
Token ID340
Feature activation-1.79e-01

Pos logit contributions
 unison+0.363
ric+0.363
latable+0.347
 Deal+0.338
igsaw+0.329
Neg logit contributions
 whispered-0.338
 said-0.308
 woke-0.307
chy-0.304
 fell-0.301
Tokenâ
Token ID22940
Feature activation-2.42e-01

Pos logit contributions
ric+0.317
latable+0.294
 unison+0.290
 Deal+0.284
igsaw+0.278
Neg logit contributions
 whispered-0.178
 aisle-0.149
 woke-0.147
 said-0.144
l-0.143
Token
Token ID26391
Feature activation-2.87e-01

Pos logit contributions
ric+0.269
 unison+0.265
latable+0.257
 Deal+0.248
igsaw+0.241
Neg logit contributions
 whispered-0.408
 woke-0.380
 said-0.377
 fell-0.377
l-0.375
Token
Token ID8151
Feature activation-2.54e-01

Pos logit contributions
 unison+0.400
latable+0.387
ric+0.382
 Deal+0.372
igsaw+0.359
Neg logit contributions
 whispered-0.408
 said-0.393
 fell-0.383
 woke-0.379
l-0.369
Tokenily
Token ID813
Feature activation-1.78e-01

Pos logit contributions
 unison+0.467
ric+0.458
latable+0.449
 Deal+0.444
igsaw+0.438
Neg logit contributions
 whispered-0.212
 said-0.190
 fell-0.184
 woke-0.182
chy-0.179
Token was
Token ID373
Feature activation-1.88e-01

Pos logit contributions
 unison+0.311
latable+0.294
ric+0.290
ap+0.271
 Deal+0.271
Neg logit contributions
l-0.155
 prick-0.150
 low-0.145
 whispered-0.140
chy-0.138
Token so
Token ID523
Feature activation-1.98e-01

Pos logit contributions
 unison+0.313
ric+0.305
latable+0.302
 Deal+0.293
igsaw+0.286
Neg logit contributions
 whispered-0.218
 said-0.202
 woke-0.196
 fell-0.193
chy-0.191
Token happy
Token ID3772
Feature activation-1.70e-01

Pos logit contributions
 Deal+0.273
 unison+0.260
ap+0.258
latable+0.245
igsaw+0.245
Neg logit contributions
 aisle-0.244
 woke-0.238
 whispered-0.235
 iv-0.234
l-0.233
Token that
Token ID326
Feature activation-1.77e-01

Pos logit contributions
 unison+0.324
ric+0.318
latable+0.316
 Deal+0.312
igsaw+0.298
Neg logit contributions
 whispered-0.163
 said-0.157
 woke-0.144
 fell-0.142
 meant-0.136
Token she
Token ID673
Feature activation-1.70e-01

Pos logit contributions
 unison+0.252
 Wed+0.250
igsaw+0.247
 yeah+0.244
 Deal+0.242
Neg logit contributions
 whispered-0.203
l-0.196
chy-0.180
 woke-0.174
 prick-0.173
Token made
Token ID925
Feature activation-1.35e-01

Pos logit contributions
 unison+0.311
latable+0.299
ric+0.289
 gonna+0.286
 yeah+0.283
Neg logit contributions
l-0.130
 whispered-0.124
 aisle-0.121
chy-0.115
 prick-0.112
Token an
Token ID281
Feature activation-1.60e-01

Pos logit contributions
 unison+0.242
ric+0.236
 Deal+0.232
latable+0.231
ifying+0.224
Neg logit contributions
 whispered-0.149
 said-0.146
 fell-0.130
 meant-0.129
l-0.129
Token original
Token ID2656
Feature activation-1.14e-01

Pos logit contributions
 unison+0.260
ric+0.260
latable+0.247
 Deal+0.245
igsaw+0.237
Neg logit contributions
 whispered-0.191
 said-0.179
chy-0.169
 meant-0.169
 woke-0.167
Token cookie
Token ID19751
Feature activation-7.05e-02

Pos logit contributions
 unison+0.175
latable+0.167
ric+0.167
igsaw+0.160
 Deal+0.158
Neg logit contributions
 whispered-0.146
 said-0.134
 fell-0.131
 woke-0.131
l-0.131
Token all
Token ID477
Feature activation-1.26e-01

Pos logit contributions
 unison+0.121
latable+0.114
ric+0.111
igsaw+0.111
 yeah+0.107
Neg logit contributions
 whispered-0.073
 woke-0.067
l-0.065
 fell-0.062
 said-0.062
Token little
Token ID1310
Feature activation-3.23e-01

Pos logit contributions
 unison+0.550
ric+0.534
latable+0.519
 Deal+0.510
igsaw+0.489
Neg logit contributions
 whispered-0.447
 said-0.410
 woke-0.406
 fell-0.401
l-0.397
Token dog
Token ID3290
Feature activation-2.35e-01

Pos logit contributions
 unison+0.554
ric+0.537
latable+0.529
 Deal+0.518
igsaw+0.506
Neg logit contributions
 whispered-0.350
 said-0.320
 woke-0.312
 fell-0.309
chy-0.309
Token.
Token ID13
Feature activation-3.00e-01

Pos logit contributions
 unison+0.396
ric+0.370
latable+0.355
ap+0.354
 Deal+0.343
Neg logit contributions
 prick-0.228
 whispered-0.214
l-0.214
 aisle-0.208
chy-0.208
Token<|endoftext|>
Token ID50256
Feature activation-2.82e-01

Pos logit contributions
 unison+0.481
ric+0.466
latable+0.460
 Deal+0.450
igsaw+0.436
Neg logit contributions
 whispered-0.360
 said-0.333
 woke-0.325
chy-0.323
 fell-0.323
TokenOnce
Token ID7454
Feature activation-2.55e-01

Pos logit contributions
ric+0.377
 unison+0.371
 Deal+0.345
igsaw+0.339
latable+0.338
Neg logit contributions
 whispered-0.394
chy-0.380
 prick-0.367
 meant-0.338
 said-0.336
Token upon
Token ID2402
Feature activation-3.12e-01

Pos logit contributions
 unison+0.298
ric+0.291
latable+0.283
 Deal+0.274
igsaw+0.266
Neg logit contributions
 whispered-0.415
 said-0.391
 woke-0.383
 fell-0.379
chy-0.378
Token a
Token ID257
Feature activation-2.19e-01

Pos logit contributions
ric+0.600
 unison+0.580
latable+0.577
igsaw+0.577
 Deal+0.573
Neg logit contributions
 whispered-0.311
 said-0.307
 woke-0.299
 fell-0.298
chy-0.269
Token time
Token ID640
Feature activation-1.99e-01

Pos logit contributions
ric+0.441
 unison+0.439
latable+0.423
 Deal+0.413
igsaw+0.411
Neg logit contributions
 whispered-0.170
 said-0.159
 woke-0.156
 fell-0.153
chy-0.151
Token,
Token ID11
Feature activation-2.03e-01

Pos logit contributions
 unison+0.431
ric+0.414
latable+0.414
 Deal+0.400
igsaw+0.389
Neg logit contributions
 whispered-0.137
 said-0.131
 fell-0.125
 woke-0.123
l-0.115
Token in
Token ID287
Feature activation-1.90e-01

Pos logit contributions
 unison+0.331
ric+0.325
latable+0.319
 Deal+0.310
igsaw+0.303
Neg logit contributions
 whispered-0.239
 said-0.220
 woke-0.214
 fell-0.210
chy-0.209
Token a
Token ID257
Feature activation-2.06e-01

Pos logit contributions
ric+0.413
 Deal+0.370
pieces+0.366
 unison+0.357
igsaw+0.351
Neg logit contributions
 whispered-0.148
 prick-0.148
 said-0.146
 woke-0.139
 spark-0.137
Token playful
Token ID34264
Feature activation-3.38e-01

Pos logit contributions
 whispered+0.172
 said+0.152
 woke+0.152
chy+0.151
 meant+0.150
Neg logit contributions
 unison-0.302
latable-0.294
ric-0.293
ap-0.284
igsaw-0.283
Token adventure
Token ID8855
Feature activation-2.15e-01

Pos logit contributions
 unison+0.593
ric+0.587
latable+0.582
 Deal+0.575
igsaw+0.555
Neg logit contributions
 whispered-0.353
 said-0.339
 woke-0.323
 fell-0.312
chy-0.306
Token.
Token ID13
Feature activation-3.00e-01

Pos logit contributions
 unison+0.372
latable+0.355
ric+0.354
igsaw+0.342
 Deal+0.326
Neg logit contributions
 whispered-0.220
 woke-0.192
chy-0.191
 said-0.188
 fell-0.185
Token<|endoftext|>
Token ID50256
Feature activation-2.86e-01

Pos logit contributions
 unison+0.498
ric+0.485
latable+0.480
 Deal+0.466
igsaw+0.455
Neg logit contributions
 whispered-0.345
 said-0.320
 woke-0.309
 fell-0.307
chy-0.305
TokenOnce
Token ID7454
Feature activation-2.59e-01

Pos logit contributions
ric+0.383
 unison+0.364
 Deal+0.342
igsaw+0.342
latable+0.336
Neg logit contributions
 whispered-0.401
chy-0.384
 prick-0.373
 meant-0.349
 said-0.342
Token upon
Token ID2402
Feature activation-3.17e-01

Pos logit contributions
ric+0.277
 unison+0.274
latable+0.257
 Deal+0.254
igsaw+0.250
Neg logit contributions
 whispered-0.441
 said-0.411
 woke-0.407
chy-0.402
 meant-0.401
Token a
Token ID257
Feature activation-2.25e-01

Pos logit contributions
ric+0.617
latable+0.594
 unison+0.593
igsaw+0.592
 Deal+0.592
Neg logit contributions
 whispered-0.312
 said-0.312
 woke-0.296
 fell-0.296
 low-0.264
Token time
Token ID640
Feature activation-2.02e-01

Pos logit contributions
 unison+0.441
ric+0.440
latable+0.426
 Deal+0.416
igsaw+0.412
Neg logit contributions
 whispered-0.185
 said-0.172
 woke-0.168
 fell-0.165
chy-0.163
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
 unison+0.427
latable+0.412
ric+0.411
 Deal+0.398
igsaw+0.389
Neg logit contributions
 whispered-0.148
 said-0.141
 fell-0.134
 woke-0.132
l-0.125
Token there
Token ID612
Feature activation-1.87e-01

Pos logit contributions
 unison+0.326
ric+0.323
latable+0.314
 Deal+0.305
igsaw+0.297
Neg logit contributions
 whispered-0.254
 said-0.232
 woke-0.228
chy-0.222
 fell-0.222
Token was
Token ID373
Feature activation-1.83e-01

Pos logit contributions
ric+0.350
 unison+0.342
latable+0.334
 yeah+0.312
ap+0.307
Neg logit contributions
 whispered-0.169
chy-0.144
l-0.135
 prick-0.132
 aisle-0.126
Token ever
Token ID1683
Feature activation-2.93e-01

Pos logit contributions
 whispered+0.190
 fell+0.165
 said+0.164
 woke+0.162
chy+0.162
Neg logit contributions
 unison-0.303
latable-0.299
ric-0.299
igsaw-0.290
 yeah-0.277
Token after
Token ID706
Feature activation-2.63e-01

Pos logit contributions
 unison+0.514
ric+0.502
latable+0.494
 Deal+0.483
igsaw+0.471
Neg logit contributions
 whispered-0.305
 said-0.280
 woke-0.270
chy-0.267
 fell-0.266
Token.
Token ID13
Feature activation-3.06e-01

Pos logit contributions
 unison+0.421
ric+0.413
latable+0.400
 Deal+0.391
igsaw+0.388
Neg logit contributions
 whispered-0.306
 woke-0.275
 said-0.273
chy-0.273
l-0.266
Token<|endoftext|>
Token ID50256
Feature activation-2.83e-01

Pos logit contributions
 unison+0.503
ric+0.488
latable+0.480
 Deal+0.473
igsaw+0.458
Neg logit contributions
 whispered-0.356
 said-0.326
chy-0.320
 woke-0.319
 fell-0.317
TokenOnce
Token ID7454
Feature activation-2.58e-01

Pos logit contributions
ric+0.379
 unison+0.375
igsaw+0.350
 Deal+0.350
latable+0.347
Neg logit contributions
 whispered-0.395
chy-0.380
 prick-0.367
 meant-0.340
 knew-0.336
Token upon
Token ID2402
Feature activation-3.14e-01

Pos logit contributions
ric+0.280
 unison+0.278
latable+0.262
 Deal+0.258
igsaw+0.253
Neg logit contributions
 whispered-0.436
 said-0.406
 woke-0.403
chy-0.398
 fell-0.396
Token a
Token ID257
Feature activation-2.24e-01

Pos logit contributions
ric+0.622
 unison+0.593
 Deal+0.592
igsaw+0.592
latable+0.592
Neg logit contributions
 said-0.303
 whispered-0.302
 woke-0.288
 fell-0.286
l-0.256
Token time
Token ID640
Feature activation-2.02e-01

Pos logit contributions
ric+0.447
 unison+0.445
latable+0.429
 Deal+0.419
igsaw+0.416
Neg logit contributions
 whispered-0.179
 said-0.166
 woke-0.164
 fell-0.160
chy-0.158
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
 unison+0.428
ric+0.414
latable+0.413
 Deal+0.399
igsaw+0.389
Neg logit contributions
 whispered-0.146
 said-0.139
 fell-0.133
 woke-0.130
l-0.123
Token there
Token ID612
Feature activation-1.86e-01

Pos logit contributions
 unison+0.332
ric+0.327
latable+0.320
 Deal+0.310
igsaw+0.302
Neg logit contributions
 whispered-0.249
 said-0.228
 woke-0.223
chy-0.218
 fell-0.218
Token was
Token ID373
Feature activation-1.82e-01

Pos logit contributions
ric+0.342
 unison+0.335
latable+0.330
 yeah+0.306
ap+0.301
Neg logit contributions
 whispered-0.173
chy-0.148
l-0.140
 prick-0.135
 said-0.124
Token flew
Token ID13112
Feature activation-2.74e-01

Pos logit contributions
 whispered+0.142
l+0.135
 aisle+0.130
 meant+0.126
chy+0.125
Neg logit contributions
 unison-0.254
ric-0.251
latable-0.230
ap-0.219
ifying-0.212
Token away
Token ID1497
Feature activation-2.47e-01

Pos logit contributions
 unison+0.430
ric+0.418
latable+0.408
 Deal+0.390
igsaw+0.382
Neg logit contributions
 whispered-0.311
 woke-0.284
 meant-0.282
chy-0.280
 said-0.279
Token.
Token ID13
Feature activation-3.07e-01

Pos logit contributions
 unison+0.377
ric+0.373
latable+0.343
igsaw+0.341
ap+0.335
Neg logit contributions
 whispered-0.262
 woke-0.244
 aisle-0.242
 meant-0.242
mail-0.229
Token<|endoftext|>
Token ID50256
Feature activation-2.84e-01

Pos logit contributions
 unison+0.459
ric+0.436
 Deal+0.432
latable+0.424
igsaw+0.412
Neg logit contributions
 whispered-0.398
chy-0.373
l-0.363
 woke-0.361
 fell-0.360
TokenOnce
Token ID7454
Feature activation-2.55e-01

Pos logit contributions
ric+0.365
 unison+0.358
igsaw+0.337
 Deal+0.334
latable+0.325
Neg logit contributions
 whispered-0.405
chy-0.395
 prick-0.382
 meant-0.349
 knew-0.348
Token upon
Token ID2402
Feature activation-3.14e-01

Pos logit contributions
ric+0.274
 unison+0.271
latable+0.254
 Deal+0.251
igsaw+0.247
Neg logit contributions
 whispered-0.434
 said-0.403
 woke-0.402
chy-0.397
 fell-0.394
Token a
Token ID257
Feature activation-2.24e-01

Pos logit contributions
ric+0.597
 unison+0.572
latable+0.571
 Deal+0.568
igsaw+0.562
Neg logit contributions
 whispered-0.321
 said-0.316
 woke-0.303
 fell-0.302
 meant-0.275
Token time
Token ID640
Feature activation-2.01e-01

Pos logit contributions
ric+0.447
 unison+0.444
latable+0.430
 Deal+0.419
igsaw+0.416
Neg logit contributions
 whispered-0.177
 said-0.165
 woke-0.162
 fell-0.159
chy-0.157
Token,
Token ID11
Feature activation-2.06e-01

Pos logit contributions
 unison+0.435
latable+0.419
ric+0.418
 Deal+0.404
igsaw+0.393
Neg logit contributions
 whispered-0.138
 said-0.133
 fell-0.126
 woke-0.123
l-0.117
Token there
Token ID612
Feature activation-1.86e-01

Pos logit contributions
 unison+0.324
ric+0.320
latable+0.311
 Deal+0.301
igsaw+0.294
Neg logit contributions
 whispered-0.251
 said-0.229
 woke-0.227
chy-0.220
l-0.219
Token was
Token ID373
Feature activation-1.83e-01

Pos logit contributions
ric+0.346
 unison+0.337
latable+0.329
 yeah+0.306
ap+0.302
Neg logit contributions
 whispered-0.172
chy-0.147
l-0.139
 prick-0.136
 aisle-0.124
Token best
Token ID1266
Feature activation-3.09e-01

Pos logit contributions
 aisle+0.097
l+0.097
 whispered+0.095
 low+0.085
 prick+0.083
Neg logit contributions
latable-0.118
ric-0.114
 unison-0.112
 Wed-0.104
 disl-0.102
Token friends
Token ID2460
Feature activation-2.73e-01

Pos logit contributions
 unison+0.515
latable+0.514
ric+0.512
 Deal+0.492
igsaw+0.486
Neg logit contributions
 whispered-0.356
 said-0.350
 woke-0.322
 fell-0.321
l-0.311
Token.
Token ID13
Feature activation-3.08e-01

Pos logit contributions
 unison+0.479
ric+0.468
latable+0.449
 Deal+0.436
 yeah+0.431
Neg logit contributions
 whispered-0.262
chy-0.238
l-0.234
 prick-0.230
 woke-0.228
Token<|endoftext|>
Token ID50256
Feature activation-2.88e-01

Pos logit contributions
 unison+0.507
ric+0.494
latable+0.490
 Deal+0.475
igsaw+0.464
Neg logit contributions
 whispered-0.356
 said-0.332
 woke-0.320
 fell-0.316
chy-0.313
TokenOnce
Token ID7454
Feature activation-2.62e-01

Pos logit contributions
ric+0.393
 unison+0.385
 Deal+0.359
latable+0.359
igsaw+0.355
Neg logit contributions
 whispered-0.397
chy-0.372
 prick-0.361
 meant-0.341
 said-0.338
Token upon
Token ID2402
Feature activation-3.17e-01

Pos logit contributions
ric+0.281
 unison+0.279
latable+0.262
 Deal+0.259
igsaw+0.255
Neg logit contributions
 whispered-0.445
 said-0.414
 woke-0.409
chy-0.404
 meant-0.403
Token a
Token ID257
Feature activation-2.26e-01

Pos logit contributions
ric+0.612
 unison+0.589
latable+0.587
igsaw+0.585
 Deal+0.581
Neg logit contributions
 whispered-0.318
 said-0.316
 fell-0.303
 woke-0.302
 low-0.273
Token time
Token ID640
Feature activation-2.02e-01

Pos logit contributions
 unison+0.440
ric+0.438
latable+0.425
 Deal+0.415
igsaw+0.411
Neg logit contributions
 whispered-0.190
 said-0.176
 woke-0.171
 fell-0.168
chy-0.165
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
 unison+0.426
ric+0.411
latable+0.411
 Deal+0.397
igsaw+0.387
Neg logit contributions
 whispered-0.150
 said-0.142
 fell-0.135
 woke-0.133
l-0.126
Token there
Token ID612
Feature activation-1.87e-01

Pos logit contributions
 unison+0.333
ric+0.329
latable+0.321
 Deal+0.312
igsaw+0.304
Neg logit contributions
 whispered-0.247
 said-0.226
 woke-0.221
 fell-0.216
chy-0.215
Token was
Token ID373
Feature activation-1.83e-01

Pos logit contributions
ric+0.356
 unison+0.347
latable+0.339
 yeah+0.319
ap+0.313
Neg logit contributions
 whispered-0.163
chy-0.137
l-0.129
 prick-0.125
 aisle-0.118