TOP ACTIVATIONS
MAX = 15.024

first ." N emo asked , " What do
. N emo asked his friend , a
. N emo saw a big jet flying
. N emo said , " Please give
. N emo 's friend , Sammy the
friends . N emo tried to swim away ,
. N emo was scared and didn 't
He said , " N emo , you must keep swimming
far ?" N emo replied , " I want
it . N emo 's friend , D ory
fish . N emo and his friends tried to
ocean ." N emo was curious and wanted to
. N emo finally reached the other side
you ." N emo was grateful for Tim my
anxious . N emo sw am away from the
mouths !" N emo tried his best , but
o . N emo sw am under the blanket
." N emo and D ory dove deep
. N emo sw am up to his
shark . N emo said , " Thanks for

MIN ACTIVATIONS
MIN = -13.215

cl apped her hands in amusement . The other boys had
they went to a big amusement park . Lily was so
took her to a famous amusement park . Lily was so
They learn that qu arre ling is bad and sharing
" Why are you qu arre ling ? You can share
Tom and Mia stop qu arre ling . They see the
They are tired from qu arre ling . They sit in
says , " Stop qu arre ling , Tom and Lily
on , they never qu arre led again over clothes .
sharing is important and qu arre lling is not good .
the mess and the qu arre ling twins . She is
Lily and Jack never qu arre led again . They learned
walking by saw them qu arre ling . She was very
the dog and the black board and the chalk and the
. They opened the cup board and took out some pots
They saw a big cup board with many things inside .
teacher writes on the black board . She writes words and
on , they never qu arre led again and played together
and Ben , stop qu arre ling right now ! Look
they saw a big black board near the fence . It

INTERVAL 7.964 - 15.024
CONTAINS 0.164%

ll ie . O ll ie loved to read . Every
the garden . L izz ie hugged them and thanked them
Quick heard some other animals whist ling . "
confident . It hugged the pig with a big smile and
be alone . Bee decided to leave . He

INTERVAL 0.905 - 7.964
CONTAINS 29.122%

do what they do . He feels happy . He says
a giant feast . They jumped and cl apped
Todd put the coin in his pocket and they walked away
because he was too boss y . At the end of
both have a new shirt ." Ben shakes his

INTERVAL -6.155 - 0.905
CONTAINS 70.209%

. But when they looked at their patch , they saw
. I will use my papers . I will ask and
plays . She sings loud and happy . She makes up
world , and she wanted the mer maid to come too
quickly flew down to see what it could be . As

INTERVAL -13.215 - -6.155
CONTAINS 0.504%

were two best friends , Sarah and Th alia . They
all three went to the party . They had a wonderful
could get to the finish line first . But
had seen a famous carpet today ! <|endoftext|> Paul was a
and started to fight with Sarah . They both got hurt
Token first
Token ID717
Feature activation-1.57e+00

Pos logit contributions
emo+0.096
eer+0.080
 sailor+0.077
ba+0.077
cker+0.077
Neg logit contributions
oph-0.071
cake-0.069
cakes-0.068
board-0.062
 amusement-0.061
Token."
Token ID526
Feature activation+3.79e+00

Pos logit contributions
oph+0.109
cake+0.106
cakes+0.104
board+0.095
 amusement+0.094
Neg logit contributions
emo-0.125
eer-0.103
 sailor-0.102
ba-0.100
cker-0.099
Token
Token ID198
Feature activation+2.43e+00

Pos logit contributions
emo+0.309
eer+0.252
 sailor+0.250
ba+0.246
cker+0.243
Neg logit contributions
oph-0.258
cake-0.250
cakes-0.245
board-0.226
 amusement-0.225
Token
Token ID198
Feature activation+2.42e+00

Pos logit contributions
emo+0.192
eer+0.159
 sailor+0.156
ba+0.154
cker+0.153
Neg logit contributions
oph-0.171
cake-0.166
cakes-0.162
board-0.150
 amusement-0.148
TokenN
Token ID45
Feature activation+3.60e+00

Pos logit contributions
emo+0.232
ba+0.194
 sailor+0.192
eer+0.188
cker+0.186
Neg logit contributions
oph-0.132
cake-0.128
cakes-0.128
board-0.115
 amusement-0.110
Tokenemo
Token ID41903
Feature activation+1.49e+01

Pos logit contributions
emo+0.254
 sailor+0.226
eer+0.224
rito+0.221
 crew+0.218
Neg logit contributions
oph-0.268
cake-0.256
board-0.240
cakes-0.234
aw-0.216
Token asked
Token ID1965
Feature activation+3.65e+00

Pos logit contributions
emo+1.334
eer+1.121
 sailor+1.102
ba+1.090
rito+1.087
Neg logit contributions
oph-0.895
cake-0.861
cakes-0.837
board-0.770
 amusement-0.748
Token,
Token ID11
Feature activation+8.59e-01

Pos logit contributions
emo+0.308
cker+0.261
eer+0.259
rito+0.253
ba+0.251
Neg logit contributions
oph-0.234
cake-0.223
cakes-0.216
board-0.203
 amusement-0.200
Token "
Token ID366
Feature activation-2.05e+00

Pos logit contributions
emo+0.094
eer+0.086
cker+0.081
rito+0.081
fish+0.079
Neg logit contributions
cake-0.033
oph-0.030
cakes-0.027
That-0.024
 Meg-0.023
TokenWhat
Token ID2061
Feature activation-2.56e+00

Pos logit contributions
oph+0.108
cake+0.105
cakes+0.099
board+0.091
 amusement+0.090
Neg logit contributions
emo-0.199
eer-0.172
 sailor-0.165
rito-0.164
cker-0.164
Token do
Token ID466
Feature activation-3.62e+00

Pos logit contributions
oph+0.128
cake+0.124
cakes+0.121
board+0.114
 amusement+0.109
Neg logit contributions
emo-0.249
rito-0.222
ba-0.214
cker-0.212
eer-0.211
Token.
Token ID13
Feature activation+6.28e-03

Pos logit contributions
oph+0.161
cake+0.155
cakes+0.152
 amusement+0.139
board+0.138
Neg logit contributions
emo-0.172
eer-0.143
 sailor-0.139
ba-0.137
cker-0.135
Token
Token ID220
Feature activation-1.68e+00

Pos logit contributions
emo+0.001
eer+0.000
ba+0.000
cker+0.000
rito+0.000
Neg logit contributions
oph-0.000
cake-0.000
cakes-0.000
board-0.000
 amusement-0.000
Token
Token ID198
Feature activation+2.19e+00

Pos logit contributions
cake+0.080
cakes+0.080
oph+0.078
ue+0.069
uct+0.068
Neg logit contributions
emo-0.154
 sailor-0.148
eer-0.146
cker-0.145
fish-0.144
Token
Token ID198
Feature activation+2.20e+00

Pos logit contributions
emo+0.190
eer+0.180
cker+0.175
 sailor+0.171
rito+0.169
Neg logit contributions
oph-0.126
cake-0.119
cakes-0.114
That-0.109
board-0.105
TokenN
Token ID45
Feature activation+3.58e+00

Pos logit contributions
emo+0.184
eer+0.155
 sailor+0.151
ba+0.149
cker+0.149
Neg logit contributions
oph-0.146
cake-0.141
cakes-0.137
board-0.127
 amusement-0.125
Tokenemo
Token ID41903
Feature activation+1.48e+01

Pos logit contributions
Albert+0.037
 Albert+0.032
 exc+0.032
 sailor+0.032
 crew+0.029
Neg logit contributions
oph-0.443
board-0.422
cake-0.410
aw-0.409
ue-0.387
Token asked
Token ID1965
Feature activation+3.31e+00

Pos logit contributions
emo+1.313
eer+1.102
 sailor+1.083
ba+1.069
rito+1.066
Neg logit contributions
oph-0.909
cake-0.875
cakes-0.849
board-0.783
 amusement-0.767
Token his
Token ID465
Feature activation+2.98e+00

Pos logit contributions
emo+0.232
cker+0.207
rito+0.197
fish+0.194
ba+0.190
Neg logit contributions
oph-0.244
cake-0.224
 amusement-0.224
cakes-0.218
board-0.216
Token friend
Token ID1545
Feature activation+2.56e+00

Pos logit contributions
emo+0.258
eer+0.215
ba+0.212
rito+0.211
 sailor+0.209
Neg logit contributions
oph-0.185
cake-0.181
cakes-0.175
 amusement-0.165
board-0.163
Token,
Token ID11
Feature activation+5.66e-01

Pos logit contributions
emo+0.211
eer+0.175
 sailor+0.172
ba+0.170
cker+0.168
Neg logit contributions
oph-0.171
cake-0.167
cakes-0.163
board-0.150
 amusement-0.148
Token a
Token ID257
Feature activation+3.63e-01

Pos logit contributions
emo+0.055
eer+0.049
cker+0.047
rito+0.047
fish+0.045
Neg logit contributions
oph-0.028
cake-0.028
cakes-0.025
 amusement-0.024
 Meg-0.024
Token.
Token ID13
Feature activation-4.43e-02

Pos logit contributions
emo+0.067
eer+0.055
rito+0.055
cker+0.054
ba+0.053
Neg logit contributions
cake-0.047
oph-0.047
cakes-0.046
 amusement-0.044
board-0.043
Token
Token ID220
Feature activation-1.69e+00

Pos logit contributions
oph+0.003
cake+0.002
cakes+0.002
board+0.002
ue+0.002
Neg logit contributions
emo-0.004
eer-0.004
cker-0.004
rito-0.004
ba-0.003
Token
Token ID198
Feature activation+2.18e+00

Pos logit contributions
cake+0.080
oph+0.080
cakes+0.078
ue+0.071
That+0.069
Neg logit contributions
emo-0.154
 sailor-0.147
eer-0.146
cker-0.145
rito-0.142
Token
Token ID198
Feature activation+2.19e+00

Pos logit contributions
emo+0.195
eer+0.177
cker+0.176
 sailor+0.172
rito+0.170
Neg logit contributions
oph-0.124
cake-0.116
cakes-0.113
ue-0.106
board-0.105
TokenN
Token ID45
Feature activation+3.53e+00

Pos logit contributions
emo+0.194
eer+0.163
 sailor+0.160
ba+0.159
cker+0.158
Neg logit contributions
oph-0.137
cake-0.132
cakes-0.129
board-0.118
 amusement-0.116
Tokenemo
Token ID41903
Feature activation+1.48e+01

Pos logit contributions
Albert+0.044
 Albert+0.038
cker+0.028
rito+0.028
 sailor+0.024
Neg logit contributions
oph-0.429
board-0.415
aw-0.402
cake-0.396
ue-0.378
Token saw
Token ID2497
Feature activation-4.63e-01

Pos logit contributions
emo+1.454
rito+1.298
eer+1.278
 sailor+1.241
ba+1.204
Neg logit contributions
oph-0.704
cake-0.612
board-0.588
cakes-0.580
ue-0.554
Token a
Token ID257
Feature activation+3.73e-01

Pos logit contributions
oph+0.027
cake+0.026
cakes+0.026
 amusement+0.025
aw+0.025
Neg logit contributions
emo-0.038
rito-0.035
cker-0.035
eer-0.034
ba-0.033
Token big
Token ID1263
Feature activation-8.26e-01

Pos logit contributions
emo+0.029
eer+0.027
rito+0.026
cker+0.025
eers+0.024
Neg logit contributions
oph-0.023
cake-0.022
 amusement-0.022
board-0.021
cakes-0.021
Token jet
Token ID12644
Feature activation+7.31e-01

Pos logit contributions
oph+0.073
cake+0.071
cakes+0.069
 amusement+0.067
board+0.067
Neg logit contributions
emo-0.051
eer-0.038
ba-0.038
rito-0.037
cker-0.036
Token flying
Token ID7348
Feature activation+5.36e+00

Pos logit contributions
emo+0.050
 sailor+0.041
eer+0.041
fish+0.040
cker+0.040
Neg logit contributions
oph-0.060
cake-0.058
cakes-0.057
board-0.051
 amusement-0.051
Token.
Token ID13
Feature activation+3.49e-02

Pos logit contributions
emo+0.493
eer+0.417
 sailor+0.410
ba+0.407
cker+0.403
Neg logit contributions
oph-0.315
cake-0.305
cakes-0.297
board-0.269
 amusement-0.266
Token
Token ID220
Feature activation-1.72e+00

Pos logit contributions
emo+0.003
eer+0.003
cker+0.003
 sailor+0.003
ba+0.002
Neg logit contributions
oph-0.002
cake-0.002
cakes-0.002
board-0.002
 amusement-0.002
Token
Token ID198
Feature activation+2.18e+00

Pos logit contributions
cake+0.081
oph+0.081
cakes+0.080
That+0.070
ue+0.070
Neg logit contributions
 sailor-0.156
emo-0.155
eer-0.155
cker-0.152
rito-0.147
Token
Token ID198
Feature activation+2.19e+00

Pos logit contributions
emo+0.189
eer+0.185
cker+0.182
 sailor+0.176
rito+0.173
Neg logit contributions
oph-0.121
cake-0.114
cakes-0.112
That-0.105
ue-0.100
TokenN
Token ID45
Feature activation+3.50e+00

Pos logit contributions
emo+0.170
eer+0.135
 sailor+0.134
ba+0.134
cker+0.130
Neg logit contributions
oph-0.160
cake-0.157
cakes-0.154
board-0.142
 amusement-0.141
Tokenemo
Token ID41903
Feature activation+1.47e+01

Pos logit contributions
emo+0.013
rito+0.011
cker+0.011
 sailor+0.009
Albert+0.007
Neg logit contributions
oph-0.470
cake-0.436
board-0.429
cakes-0.419
aw-0.415
Token said
Token ID531
Feature activation-2.36e+00

Pos logit contributions
emo+1.313
eer+1.097
 sailor+1.082
ba+1.080
cker+1.068
Neg logit contributions
oph-0.892
cake-0.874
cakes-0.856
board-0.770
 amusement-0.768
Token,
Token ID11
Feature activation+6.21e-01

Pos logit contributions
cake+0.121
oph+0.118
cakes+0.116
board+0.103
 Meg+0.098
Neg logit contributions
emo-0.225
eer-0.199
rito-0.195
cker-0.195
ba-0.192
Token "
Token ID366
Feature activation-2.20e+00

Pos logit contributions
emo+0.061
eer+0.053
cker+0.052
rito+0.052
 sailor+0.051
Neg logit contributions
cake-0.031
oph-0.031
cakes-0.029
board-0.026
That-0.024
TokenPlease
Token ID5492
Feature activation-9.69e-01

Pos logit contributions
oph+0.108
cake+0.099
cakes+0.093
That+0.087
 amusement+0.084
Neg logit contributions
emo-0.219
eer-0.193
 sailor-0.187
rito-0.187
cker-0.184
Token give
Token ID1577
Feature activation+4.57e-01

Pos logit contributions
cake+0.052
oph+0.051
ue+0.051
board+0.050
cakes+0.048
Neg logit contributions
emo-0.086
eer-0.074
cker-0.073
rito-0.070
eers-0.067
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
cake+0.068
oph+0.066
cakes+0.065
board+0.061
 amusement+0.058
Neg logit contributions
emo-0.096
eer-0.078
 sailor-0.077
cker-0.077
ba-0.076
Token
Token ID220
Feature activation-1.47e+00

Pos logit contributions
oph+0.016
cake+0.015
cakes+0.014
board+0.013
 amusement+0.013
Neg logit contributions
emo-0.022
eer-0.020
rito-0.019
ba-0.019
cker-0.019
Token
Token ID198
Feature activation+2.43e+00

Pos logit contributions
cake+0.068
cakes+0.068
oph+0.066
ue+0.059
board+0.058
Neg logit contributions
emo-0.132
 sailor-0.131
eer-0.126
cker-0.126
rito-0.124
Token
Token ID198
Feature activation+2.39e+00

Pos logit contributions
emo+0.199
eer+0.175
 sailor+0.171
cker+0.168
rito+0.166
Neg logit contributions
oph-0.158
cake-0.152
cakes-0.147
board-0.135
 amusement-0.134
TokenN
Token ID45
Feature activation+3.53e+00

Pos logit contributions
emo+0.218
ba+0.178
 sailor+0.178
eer+0.178
cker+0.174
Neg logit contributions
oph-0.142
cake-0.139
cakes-0.137
board-0.124
 amusement-0.120
Tokenemo
Token ID41903
Feature activation+1.47e+01

Pos logit contributions
 exc+0.037
Albert+0.034
 sword+0.034
 sailor+0.033
rito+0.031
Neg logit contributions
oph-0.433
board-0.411
cake-0.409
aw-0.395
cakes-0.379
Token's
Token ID338
Feature activation-1.89e+00

Pos logit contributions
emo+1.312
eer+1.101
rito+1.084
 sailor+1.076
cker+1.049
Neg logit contributions
oph-0.891
cake-0.828
cakes-0.797
board-0.763
 amusement-0.738
Token friend
Token ID1545
Feature activation+2.69e+00

Pos logit contributions
oph+0.133
cake+0.129
cakes+0.125
 amusement+0.123
board+0.121
Neg logit contributions
emo-0.145
eer-0.118
ba-0.117
rito-0.117
cker-0.115
Token,
Token ID11
Feature activation+6.52e-01

Pos logit contributions
emo+0.234
eer+0.196
 sailor+0.191
rito+0.190
ba+0.190
Neg logit contributions
oph-0.170
cake-0.163
cakes-0.158
board-0.146
 amusement-0.144
Token Sammy
Token ID44067
Feature activation-1.07e+00

Pos logit contributions
emo+0.057
eer+0.049
rito+0.048
cker+0.047
 sailor+0.047
Neg logit contributions
oph-0.040
cake-0.038
cakes-0.036
 amusement-0.034
board-0.033
Token the
Token ID262
Feature activation-2.01e-01

Pos logit contributions
oph+0.054
cake+0.048
board+0.044
cakes+0.044
ue+0.044
Neg logit contributions
emo-0.106
rito-0.090
eer-0.089
 sailor-0.086
ba-0.085
Token friends
Token ID2460
Feature activation+2.07e+00

Pos logit contributions
emo+0.241
rito+0.229
cker+0.226
Albert+0.222
eer+0.221
Neg logit contributions
 amusement-0.158
board-0.156
oph-0.146
ue-0.145
 Meg-0.143
Token.
Token ID13
Feature activation+5.29e-02

Pos logit contributions
emo+0.146
eer+0.122
 sailor+0.122
ba+0.118
fish+0.118
Neg logit contributions
oph-0.162
cakes-0.156
cake-0.156
board-0.137
ue-0.136
Token
Token ID198
Feature activation+2.19e+00

Pos logit contributions
emo+0.004
eer+0.004
 sailor+0.004
ba+0.004
cker+0.004
Neg logit contributions
oph-0.004
cake-0.003
cakes-0.003
board-0.003
 amusement-0.003
Token
Token ID198
Feature activation+2.21e+00

Pos logit contributions
emo+0.194
eer+0.183
cker+0.179
 sailor+0.179
rito+0.176
Neg logit contributions
oph-0.118
cake-0.111
cakes-0.107
ue-0.103
board-0.101
TokenN
Token ID45
Feature activation+3.55e+00

Pos logit contributions
emo+0.207
eer+0.172
 sailor+0.170
ba+0.170
cker+0.167
Neg logit contributions
oph-0.129
cake-0.125
cakes-0.122
board-0.110
 amusement-0.109
Tokenemo
Token ID41903
Feature activation+1.47e+01

Pos logit contributions
Albert+0.037
 Albert+0.036
rito+0.026
cker+0.021
 sailor+0.020
Neg logit contributions
oph-0.439
board-0.422
aw-0.410
cake-0.403
ue-0.386
Token tried
Token ID3088
Feature activation+3.08e+00

Pos logit contributions
emo+1.338
eer+1.117
 sailor+1.109
ba+1.106
cker+1.091
Neg logit contributions
oph-0.872
cake-0.858
cakes-0.840
 amusement-0.746
board-0.746
Token to
Token ID284
Feature activation+6.16e-04

Pos logit contributions
emo+0.253
eer+0.212
 sailor+0.207
ba+0.204
cker+0.204
Neg logit contributions
oph-0.207
cake-0.201
cakes-0.196
board-0.181
 amusement-0.181
Token swim
Token ID9422
Feature activation+6.75e+00

Pos logit contributions
emo+0.000
eer+0.000
rito+0.000
cker+0.000
 sailor+0.000
Neg logit contributions
oph-0.000
cake-0.000
 amusement-0.000
cakes-0.000
ue-0.000
Token away
Token ID1497
Feature activation-1.03e+00

Pos logit contributions
emo+0.558
eer+0.462
 sailor+0.453
ba+0.449
cker+0.445
Neg logit contributions
oph-0.455
cake-0.443
cakes-0.433
board-0.399
 amusement-0.393
Token,
Token ID11
Feature activation+7.04e-01

Pos logit contributions
oph+0.059
cake+0.057
cakes+0.055
board+0.052
 amusement+0.050
Neg logit contributions
emo-0.093
eer-0.080
cker-0.077
 sailor-0.077
rito-0.077
Token.
Token ID13
Feature activation-6.57e-02

Pos logit contributions
emo+0.264
eer+0.216
rito+0.213
 sailor+0.210
ba+0.209
Neg logit contributions
cake-0.151
cakes-0.147
oph-0.140
 amusement-0.140
board-0.135
Token
Token ID220
Feature activation-1.80e+00

Pos logit contributions
oph+0.006
cake+0.006
cakes+0.006
board+0.005
 amusement+0.005
Neg logit contributions
emo-0.004
eer-0.003
ba-0.003
rito-0.003
 sailor-0.003
Token
Token ID198
Feature activation+2.07e+00

Pos logit contributions
cake+0.082
oph+0.081
cakes+0.080
ue+0.072
uct+0.071
Neg logit contributions
emo-0.166
 sailor-0.164
eer-0.161
cker-0.158
fish-0.158
Token
Token ID198
Feature activation+2.08e+00

Pos logit contributions
emo+0.180
eer+0.171
cker+0.165
rito+0.164
 sailor+0.164
Neg logit contributions
oph-0.121
cake-0.114
cakes-0.108
That-0.100
ue-0.099
TokenN
Token ID45
Feature activation+3.50e+00

Pos logit contributions
emo+0.164
eer+0.133
 sailor+0.131
ba+0.130
cker+0.128
Neg logit contributions
oph-0.149
cake-0.146
cakes-0.142
board-0.132
 amusement-0.130
Tokenemo
Token ID41903
Feature activation+1.47e+01

Pos logit contributions
rito+0.027
Albert+0.021
 sailor+0.021
 Albert+0.021
 paddle+0.020
Neg logit contributions
oph-0.460
cake-0.417
board-0.414
aw-0.401
ue-0.384
Token was
Token ID373
Feature activation-6.42e-01

Pos logit contributions
emo+1.293
eer+1.081
 sailor+1.064
ba+1.057
cker+1.046
Neg logit contributions
oph-0.910
cake-0.885
cakes-0.863
board-0.786
 amusement-0.776
Token scared
Token ID12008
Feature activation+1.14e+00

Pos logit contributions
oph+0.037
cake+0.036
 amusement+0.033
cakes+0.033
uct+0.032
Neg logit contributions
emo-0.057
eer-0.049
fish-0.048
 sailor-0.047
rito-0.047
Token and
Token ID290
Feature activation-3.29e-01

Pos logit contributions
emo+0.103
eer+0.087
 sailor+0.085
ba+0.084
cker+0.083
Neg logit contributions
oph-0.069
cake-0.066
cakes-0.065
board-0.059
 amusement-0.058
Token didn
Token ID1422
Feature activation-4.46e-01

Pos logit contributions
oph+0.018
cake+0.017
uct+0.017
cakes+0.017
board+0.016
Neg logit contributions
emo-0.029
rito-0.025
eer-0.025
ba-0.024
 sailor-0.023
Token't
Token ID470
Feature activation+1.69e+00

Pos logit contributions
oph+0.030
cake+0.029
cakes+0.028
board+0.026
 amusement+0.026
Neg logit contributions
emo-0.037
eer-0.030
 sailor-0.030
ba-0.030
cker-0.029
Token He
Token ID679
Feature activation+1.60e+00

Pos logit contributions
emo+0.001
eer+0.000
ba+0.000
 sailor+0.000
cker+0.000
Neg logit contributions
oph-0.000
cake-0.000
cakes-0.000
board-0.000
 amusement-0.000
Token said
Token ID531
Feature activation-2.42e+00

Pos logit contributions
emo+0.141
eer+0.120
rito+0.120
 sailor+0.116
ba+0.115
Neg logit contributions
oph-0.096
cake-0.091
cakes-0.089
board-0.082
 amusement-0.081
Token,
Token ID11
Feature activation+6.35e-01

Pos logit contributions
cake+0.135
oph+0.132
cakes+0.131
board+0.115
aw+0.111
Neg logit contributions
emo-0.224
eer-0.193
rito-0.192
cker-0.189
ba-0.188
Token "
Token ID366
Feature activation-2.16e+00

Pos logit contributions
emo+0.065
eer+0.056
cker+0.054
rito+0.054
ba+0.054
Neg logit contributions
cake-0.030
oph-0.029
cakes-0.028
board-0.025
That-0.023
TokenN
Token ID45
Feature activation+3.51e+00

Pos logit contributions
oph+0.110
cake+0.105
cakes+0.100
board+0.090
 amusement+0.088
Neg logit contributions
emo-0.216
eer-0.186
 sailor-0.183
ba-0.180
rito-0.180
Tokenemo
Token ID41903
Feature activation+1.47e+01

Pos logit contributions
emo+0.155
 sailor+0.141
Albert+0.138
 Albert+0.135
rito+0.133
Neg logit contributions
oph-0.334
cake-0.322
board-0.312
cakes-0.306
aw-0.304
Token,
Token ID11
Feature activation+6.51e-01

Pos logit contributions
emo+1.387
rito+1.178
ba+1.164
 sailor+1.161
eer+1.157
Neg logit contributions
oph-0.772
cake-0.738
cakes-0.692
board-0.691
ue-0.649
Token you
Token ID345
Feature activation+1.63e+00

Pos logit contributions
emo+0.055
eer+0.046
cker+0.045
rito+0.045
ba+0.044
Neg logit contributions
oph-0.042
cake-0.041
cakes-0.040
board-0.037
 amusement-0.037
Token must
Token ID1276
Feature activation-2.45e-01

Pos logit contributions
emo+0.152
rito+0.129
cker+0.127
eer+0.124
ba+0.122
Neg logit contributions
oph-0.081
cake-0.079
cakes-0.077
board-0.076
 amusement-0.074
Token keep
Token ID1394
Feature activation+4.15e+00

Pos logit contributions
oph+0.016
cake+0.015
 amusement+0.014
ue+0.014
cakes+0.014
Neg logit contributions
emo-0.019
eer-0.017
 sailor-0.016
fish-0.016
rito-0.016
Token swimming
Token ID14899
Feature activation+4.12e+00

Pos logit contributions
emo+0.399
rito+0.356
fish+0.348
ba+0.333
oster+0.330
Neg logit contributions
 course-0.177
 amusement-0.166
aw-0.153
 Meg-0.152
uct-0.152
Token far
Token ID1290
Feature activation+2.36e+00

Pos logit contributions
cakes+0.231
cake+0.226
oph+0.223
 amusement+0.221
That+0.216
Neg logit contributions
emo-0.292
rito-0.280
eer-0.272
cker-0.271
ba-0.251
Token?"
Token ID1701
Feature activation+4.06e+00

Pos logit contributions
emo+0.150
eer+0.116
cker+0.114
ba+0.113
rito+0.113
Neg logit contributions
oph-0.196
cake-0.187
 amusement-0.180
board-0.179
cakes-0.179
Token
Token ID198
Feature activation+2.16e+00

Pos logit contributions
emo+0.307
eer+0.297
rito+0.293
cker+0.291
ba+0.271
Neg logit contributions
oph-0.274
cake-0.249
cakes-0.241
board-0.233
That-0.227
Token
Token ID198
Feature activation+2.17e+00

Pos logit contributions
eer+0.205
cker+0.204
emo+0.201
rito+0.198
 sailor+0.191
Neg logit contributions
oph-0.103
cake-0.088
cakes-0.085
ue-0.084
That-0.081
TokenN
Token ID45
Feature activation+3.51e+00

Pos logit contributions
emo+0.153
eer+0.133
cker+0.125
rito+0.125
 sailor+0.124
Neg logit contributions
oph-0.169
cake-0.162
cakes-0.158
board-0.149
 amusement-0.147
Tokenemo
Token ID41903
Feature activation+1.47e+01

Pos logit contributions
rito+0.006
 sailor+0.006
cker+0.005
emo+0.004
Albert+0.004
Neg logit contributions
oph-0.478
cake-0.448
board-0.442
cakes-0.429
aw-0.422
Token replied
Token ID8712
Feature activation-5.41e+00

Pos logit contributions
emo+1.418
eer+1.217
 sailor+1.198
rito+1.188
ba+1.180
Neg logit contributions
oph-0.779
cake-0.735
cakes-0.707
board-0.650
 amusement-0.622
Token,
Token ID11
Feature activation+6.44e-01

Pos logit contributions
cake+0.304
oph+0.304
cakes+0.294
board+0.268
ue+0.249
Neg logit contributions
emo-0.496
eer-0.429
cker-0.418
rito-0.418
ba-0.414
Token "
Token ID366
Feature activation-2.17e+00

Pos logit contributions
emo+0.061
eer+0.052
 sailor+0.051
rito+0.051
ba+0.050
Neg logit contributions
oph-0.035
cake-0.035
cakes-0.033
board-0.030
 amusement-0.029
TokenI
Token ID40
Feature activation-5.60e-01

Pos logit contributions
oph+0.108
cake+0.104
cakes+0.100
board+0.091
 amusement+0.087
Neg logit contributions
emo-0.214
eer-0.187
 sailor-0.183
rito-0.183
cker-0.180
Token want
Token ID765
Feature activation-7.48e-01

Pos logit contributions
oph+0.026
�+0.025
 amusement+0.025
board+0.025
cake+0.024
Neg logit contributions
emo-0.047
Albert-0.040
rito-0.040
eer-0.040
 Albert-0.040
Token it
Token ID340
Feature activation+2.28e+00

Pos logit contributions
emo+0.165
cker+0.152
rito+0.149
oster+0.146
ba+0.144
Neg logit contributions
aw-0.062
 course-0.057
oph-0.053
That-0.051
 amusement-0.050
Token.
Token ID13
Feature activation+4.76e-02

Pos logit contributions
emo+0.196
eer+0.164
 sailor+0.160
cker+0.158
rito+0.157
Neg logit contributions
oph-0.144
cake-0.141
cakes-0.137
board-0.128
 amusement-0.125
Token
Token ID198
Feature activation+2.21e+00

Pos logit contributions
emo+0.004
eer+0.004
cker+0.004
rito+0.004
ba+0.004
Neg logit contributions
oph-0.003
cakes-0.002
cake-0.002
board-0.002
ue-0.002
Token
Token ID198
Feature activation+2.22e+00

Pos logit contributions
emo+0.203
cker+0.190
eer+0.189
rito+0.184
 sailor+0.183
Neg logit contributions
oph-0.116
cake-0.106
cakes-0.104
ue-0.100
board-0.097
TokenN
Token ID45
Feature activation+3.49e+00

Pos logit contributions
emo+0.167
eer+0.135
 sailor+0.133
ba+0.131
cker+0.130
Neg logit contributions
oph-0.169
cake-0.164
cakes-0.161
board-0.150
 amusement-0.148
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
Albert+0.043
 Albert+0.039
cker+0.027
rito+0.025
 sailor+0.023
Neg logit contributions
oph-0.432
board-0.416
cake-0.398
aw-0.392
ue-0.378
Token's
Token ID338
Feature activation-1.93e+00

Pos logit contributions
emo+1.297
rito+1.136
eer+1.131
 sailor+1.100
ba+1.043
Neg logit contributions
oph-0.836
cake-0.754
cakes-0.723
board-0.717
ue-0.690
Token friend
Token ID1545
Feature activation+2.54e+00

Pos logit contributions
oph+0.123
cake+0.117
board+0.116
cakes+0.115
 amusement+0.114
Neg logit contributions
emo-0.141
rito-0.132
cker-0.127
eer-0.126
ba-0.118
Token,
Token ID11
Feature activation+6.86e-01

Pos logit contributions
emo+0.219
eer+0.183
 sailor+0.180
ba+0.178
cker+0.177
Neg logit contributions
oph-0.162
cake-0.157
cakes-0.153
board-0.140
 amusement-0.138
Token D
Token ID360
Feature activation+2.72e+00

Pos logit contributions
emo+0.060
eer+0.050
 sailor+0.050
ba+0.049
cker+0.049
Neg logit contributions
oph-0.043
cake-0.041
cakes-0.040
board-0.037
 amusement-0.036
Tokenory
Token ID652
Feature activation+5.41e+00

Pos logit contributions
emo+0.200
cker+0.192
rito+0.190
eer+0.187
Albert+0.185
Neg logit contributions
oph-0.193
board-0.170
cake-0.169
cakes-0.157
ue-0.151
Token fish
Token ID5916
Feature activation+5.73e+00

Pos logit contributions
cakes+0.019
cake+0.019
oph+0.018
board+0.018
 amusement+0.018
Neg logit contributions
emo-0.026
ba-0.022
cker-0.022
rito-0.021
eer-0.020
Token.
Token ID13
Feature activation-2.00e-01

Pos logit contributions
emo+0.483
eer+0.398
 sailor+0.394
ba+0.391
rito+0.386
Neg logit contributions
oph-0.369
cake-0.365
cakes-0.354
board-0.327
 amusement-0.317
Token
Token ID198
Feature activation+1.97e+00

Pos logit contributions
oph+0.014
cake+0.014
cakes+0.013
 amusement+0.012
board+0.012
Neg logit contributions
emo-0.016
eer-0.013
 sailor-0.013
ba-0.013
cker-0.012
Token
Token ID198
Feature activation+2.02e+00

Pos logit contributions
emo+0.160
eer+0.137
 sailor+0.134
cker+0.132
ba+0.130
Neg logit contributions
oph-0.132
cake-0.129
cakes-0.125
board-0.115
ue-0.113
TokenN
Token ID45
Feature activation+3.36e+00

Pos logit contributions
emo+0.177
ba+0.146
 sailor+0.142
oster+0.139
Albert+0.139
Neg logit contributions
oph-0.130
cakes-0.125
cake-0.125
board-0.111
 amusement-0.108
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
emo+0.104
rito+0.101
cker+0.100
 exc+0.097
 sword+0.092
Neg logit contributions
oph-0.346
board-0.330
cake-0.319
aw-0.317
cakes-0.300
Token and
Token ID290
Feature activation-2.65e-01

Pos logit contributions
emo+1.262
eer+1.053
 sailor+1.035
ba+1.022
rito+1.018
Neg logit contributions
oph-0.924
cake-0.892
cakes-0.867
board-0.803
 amusement-0.784
Token his
Token ID465
Feature activation+2.91e+00

Pos logit contributions
oph+0.018
cake+0.017
 Meg+0.016
 amusement+0.016
cakes+0.016
Neg logit contributions
emo-0.020
rito-0.018
cker-0.017
eer-0.017
fish-0.017
Token friends
Token ID2460
Feature activation+1.85e+00

Pos logit contributions
emo+0.227
rito+0.197
ba+0.190
cker+0.187
eer+0.181
Neg logit contributions
oph-0.184
cake-0.183
cakes-0.181
 amusement-0.179
board-0.176
Token tried
Token ID3088
Feature activation+2.64e+00

Pos logit contributions
emo+0.144
eer+0.123
 sailor+0.123
ba+0.122
cker+0.120
Neg logit contributions
oph-0.128
cake-0.127
cakes-0.125
board-0.109
 amusement-0.109
Token to
Token ID284
Feature activation-3.86e-01

Pos logit contributions
emo+0.220
eer+0.185
 sailor+0.180
ba+0.180
rito+0.178
Neg logit contributions
oph-0.172
cake-0.169
cakes-0.165
 amusement-0.152
board-0.150
Token ocean
Token ID9151
Feature activation+1.12e-01

Pos logit contributions
oph+0.015
cake+0.014
cakes+0.014
board+0.013
 amusement+0.013
Neg logit contributions
emo-0.020
eer-0.016
 sailor-0.016
ba-0.016
cker-0.016
Token."
Token ID526
Feature activation+3.93e+00

Pos logit contributions
emo+0.008
eer+0.007
 sailor+0.007
ba+0.007
fish+0.007
Neg logit contributions
oph-0.008
cake-0.008
cakes-0.008
 amusement-0.007
board-0.007
Token
Token ID198
Feature activation+2.19e+00

Pos logit contributions
emo+0.302
eer+0.242
 sailor+0.240
ba+0.236
cker+0.231
Neg logit contributions
oph-0.286
cake-0.281
cakes-0.276
board-0.255
 amusement-0.252
Token
Token ID198
Feature activation+2.23e+00

Pos logit contributions
emo+0.171
eer+0.140
 sailor+0.138
ba+0.136
cker+0.135
Neg logit contributions
oph-0.157
cake-0.152
cakes-0.149
board-0.138
 amusement-0.136
TokenN
Token ID45
Feature activation+3.40e+00

Pos logit contributions
emo+0.212
ba+0.178
 sailor+0.176
Albert+0.171
cker+0.171
Neg logit contributions
oph-0.121
cakes-0.121
cake-0.120
board-0.108
 amusement-0.101
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
emo+0.221
 sailor+0.204
 crew+0.200
 sail+0.199
 sword+0.198
Neg logit contributions
oph-0.264
cake-0.245
board-0.236
cakes-0.225
aw-0.219
Token was
Token ID373
Feature activation-5.09e-01

Pos logit contributions
emo+1.291
eer+1.078
 sailor+1.061
rito+1.056
ba+1.044
Neg logit contributions
oph-0.892
cake-0.853
cakes-0.828
board-0.774
 amusement-0.747
Token curious
Token ID11040
Feature activation+8.45e-01

Pos logit contributions
oph+0.031
cake+0.031
cakes+0.029
 amusement+0.028
uct+0.028
Neg logit contributions
emo-0.043
eer-0.036
fish-0.035
 sailor-0.035
ba-0.035
Token and
Token ID290
Feature activation-7.65e-02

Pos logit contributions
emo+0.060
eer+0.054
 sailor+0.053
fish+0.050
cker+0.048
Neg logit contributions
oph-0.063
cakes-0.060
cake-0.060
liv-0.056
Tam-0.054
Token wanted
Token ID2227
Feature activation-1.84e-01

Pos logit contributions
oph+0.004
cake+0.004
cakes+0.004
uct+0.004
That+0.004
Neg logit contributions
emo-0.007
rito-0.006
eer-0.006
ba-0.005
 sailor-0.005
Token to
Token ID284
Feature activation-2.60e-01

Pos logit contributions
cake+0.011
oph+0.011
cakes+0.010
 amusement+0.010
board+0.009
Neg logit contributions
emo-0.017
eer-0.014
ba-0.014
rito-0.014
cker-0.014
Token.
Token ID13
Feature activation-1.64e-01

Pos logit contributions
emo+0.143
eer+0.119
 sailor+0.116
ba+0.115
cker+0.114
Neg logit contributions
oph-0.120
cake-0.117
cakes-0.113
board-0.105
 amusement-0.104
Token
Token ID220
Feature activation-1.91e+00

Pos logit contributions
oph+0.011
cake+0.011
cakes+0.010
board+0.010
 amusement+0.009
Neg logit contributions
emo-0.013
eer-0.011
 sailor-0.011
ba-0.011
cker-0.011
Token
Token ID198
Feature activation+2.05e+00

Pos logit contributions
cake+0.094
oph+0.094
cakes+0.093
ue+0.084
uct+0.081
Neg logit contributions
emo-0.172
 sailor-0.167
eer-0.165
cker-0.162
fish-0.159
Token
Token ID198
Feature activation+2.06e+00

Pos logit contributions
emo+0.177
eer+0.168
cker+0.163
 sailor+0.162
rito+0.155
Neg logit contributions
oph-0.116
cake-0.112
cakes-0.107
That-0.102
ue-0.100
TokenN
Token ID45
Feature activation+3.35e+00

Pos logit contributions
emo+0.177
eer+0.146
 sailor+0.144
ba+0.143
cker+0.141
Neg logit contributions
oph-0.134
cake-0.130
cakes-0.127
board-0.117
 amusement-0.115
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
Albert+0.040
 Albert+0.039
 sailor+0.034
 crew+0.031
 exc+0.031
Neg logit contributions
oph-0.400
board-0.388
aw-0.384
cake-0.370
ue-0.355
Token finally
Token ID3443
Feature activation+7.74e-01

Pos logit contributions
emo+1.232
eer+1.024
 sailor+1.006
ba+0.997
cker+0.986
Neg logit contributions
oph-0.955
cake-0.927
cakes-0.903
board-0.831
 amusement-0.818
Token reached
Token ID4251
Feature activation+6.51e-01

Pos logit contributions
emo+0.063
fish+0.051
 sailor+0.050
ba+0.050
eer+0.048
Neg logit contributions
cake-0.052
cakes-0.052
oph-0.051
 amusement-0.048
board-0.046
Token the
Token ID262
Feature activation-4.61e-01

Pos logit contributions
emo+0.065
eer+0.057
cker+0.057
ba+0.057
oster+0.055
Neg logit contributions
 Meg-0.024
 amusement-0.024
oph-0.023
 Tom-0.022
cake-0.022
Token other
Token ID584
Feature activation-9.06e-01

Pos logit contributions
oph+0.033
cake+0.032
cakes+0.032
board+0.029
 amusement+0.029
Neg logit contributions
emo-0.036
eer-0.030
 sailor-0.029
ba-0.029
cker-0.028
Token side
Token ID1735
Feature activation-3.72e+00

Pos logit contributions
oph+0.056
cake+0.054
cakes+0.053
board+0.047
uct+0.046
Neg logit contributions
emo-0.081
eer-0.069
 sailor-0.068
ba-0.067
cker-0.066
Token you
Token ID345
Feature activation+1.67e+00

Pos logit contributions
emo+0.139
ba+0.115
cker+0.115
eer+0.114
rito+0.113
Neg logit contributions
oph-0.099
cakes-0.094
cake-0.093
 amusement-0.088
aw-0.086
Token."
Token ID526
Feature activation+3.77e+00

Pos logit contributions
emo+0.153
eer+0.129
rito+0.127
ba+0.125
cker+0.124
Neg logit contributions
cake-0.080
cakes-0.077
oph-0.076
 amusement-0.074
board-0.071
Token
Token ID198
Feature activation+2.32e+00

Pos logit contributions
emo+0.306
eer+0.247
 sailor+0.246
ba+0.241
cker+0.236
Neg logit contributions
oph-0.257
cake-0.251
cakes-0.246
board-0.227
 amusement-0.226
Token
Token ID198
Feature activation+2.38e+00

Pos logit contributions
emo+0.180
eer+0.146
 sailor+0.144
ba+0.142
cker+0.141
Neg logit contributions
oph-0.168
cake-0.164
cakes-0.160
board-0.148
 amusement-0.146
TokenN
Token ID45
Feature activation+3.37e+00

Pos logit contributions
emo+0.221
ba+0.187
 sailor+0.184
Albert+0.179
cker+0.178
Neg logit contributions
oph-0.136
cake-0.133
cakes-0.132
board-0.120
 amusement-0.110
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
emo+0.237
 sailor+0.212
rito+0.210
 crew+0.205
eer+0.204
Neg logit contributions
oph-0.245
cake-0.234
board-0.225
cakes-0.218
aw-0.205
Token was
Token ID373
Feature activation-3.52e-01

Pos logit contributions
emo+1.304
eer+1.093
 sailor+1.076
rito+1.064
ba+1.064
Neg logit contributions
oph-0.879
cake-0.845
cakes-0.822
board-0.762
 amusement-0.736
Token grateful
Token ID14066
Feature activation+2.54e+00

Pos logit contributions
oph+0.021
cake+0.021
cakes+0.020
 amusement+0.019
uct+0.019
Neg logit contributions
emo-0.030
eer-0.026
 sailor-0.025
fish-0.025
ba-0.025
Token for
Token ID329
Feature activation-2.77e+00

Pos logit contributions
emo+0.210
eer+0.173
 sailor+0.173
fish+0.169
ba+0.167
Neg logit contributions
oph-0.174
cake-0.167
cakes-0.166
 amusement-0.149
board-0.149
Token Tim
Token ID5045
Feature activation-2.36e+00

Pos logit contributions
oph+0.213
cake+0.208
cakes+0.203
 amusement+0.193
board+0.187
Neg logit contributions
emo-0.199
eer-0.162
cker-0.160
rito-0.155
 sailor-0.154
Tokenmy
Token ID1820
Feature activation+4.17e-01

Pos logit contributions
oph+0.138
cake+0.133
cakes+0.131
 amusement+0.116
board+0.116
Neg logit contributions
emo-0.216
eer-0.186
 sailor-0.181
ba-0.179
cker-0.178
Token anxious
Token ID18116
Feature activation+1.53e+00

Pos logit contributions
emo+0.061
ba+0.054
cker+0.054
Albert+0.053
eer+0.052
Neg logit contributions
That-0.028
aw-0.027
 awful-0.026
 amusement-0.026
 so-0.025
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
emo+0.137
 sailor+0.113
eer+0.113
cker+0.113
ba+0.112
Neg logit contributions
cake-0.089
oph-0.088
cakes-0.086
board-0.082
 amusement-0.078
Token
Token ID198
Feature activation+2.01e+00

Pos logit contributions
oph+0.008
cake+0.007
cakes+0.007
board+0.007
uct+0.006
Neg logit contributions
emo-0.012
eer-0.012
cker-0.012
rito-0.011
 sailor-0.011
Token
Token ID198
Feature activation+2.03e+00

Pos logit contributions
emo+0.185
cker+0.176
eer+0.176
rito+0.170
 sailor+0.170
Neg logit contributions
oph-0.103
cake-0.092
cakes-0.089
ue-0.087
board-0.084
TokenN
Token ID45
Feature activation+3.34e+00

Pos logit contributions
emo+0.161
eer+0.136
 sailor+0.132
cker+0.131
rito+0.130
Neg logit contributions
oph-0.142
cake-0.137
cakes-0.134
board-0.126
 amusement-0.123
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
Albert+0.042
 Albert+0.039
cker+0.030
rito+0.027
 sailor+0.022
Neg logit contributions
oph-0.406
board-0.391
aw-0.376
cake-0.369
ue-0.351
Token sw
Token ID1509
Feature activation+6.44e-01

Pos logit contributions
emo+1.305
eer+1.125
rito+1.120
 sailor+1.098
ba+1.061
Neg logit contributions
oph-0.837
cake-0.771
cakes-0.739
board-0.722
ue-0.684
Tokenam
Token ID321
Feature activation+3.68e+00

Pos logit contributions
emo+0.051
 sailor+0.046
eer+0.045
rito+0.045
ba+0.044
Neg logit contributions
oph-0.040
aw-0.036
board-0.036
cakes-0.036
cake-0.035
Token away
Token ID1497
Feature activation-1.28e+00

Pos logit contributions
emo+0.300
eer+0.244
 sailor+0.241
ba+0.240
cker+0.235
Neg logit contributions
oph-0.259
cake-0.251
cakes-0.245
board-0.226
 amusement-0.223
Token from
Token ID422
Feature activation-1.26e+00

Pos logit contributions
cake+0.066
oph+0.065
cakes+0.060
board+0.057
 amusement+0.053
Neg logit contributions
emo-0.118
eer-0.105
rito-0.100
 sailor-0.100
cker-0.099
Token the
Token ID262
Feature activation-3.09e-01

Pos logit contributions
 amusement+0.051
 Tom+0.046
 course+0.042
 Meg+0.040
 Sophia+0.038
Neg logit contributions
emo-0.115
rito-0.111
Albert-0.109
ba-0.109
cker-0.107
Token mouths
Token ID28552
Feature activation+1.22e+00

Pos logit contributions
emo+0.246
ba+0.207
rito+0.199
cker+0.198
eer+0.195
Neg logit contributions
oph-0.210
cake-0.202
cakes-0.201
 amusement-0.201
board-0.200
Token!"
Token ID2474
Feature activation-1.83e+00

Pos logit contributions
emo+0.080
eer+0.063
 sailor+0.062
ba+0.061
cker+0.060
Neg logit contributions
oph-0.103
cake-0.100
cakes-0.098
board-0.092
 amusement-0.091
Token
Token ID198
Feature activation+2.08e+00

Pos logit contributions
oph+0.124
cake+0.122
cakes+0.120
board+0.112
 amusement+0.105
Neg logit contributions
emo-0.148
eer-0.126
cker-0.124
 sailor-0.122
ba-0.122
Token
Token ID198
Feature activation+2.09e+00

Pos logit contributions
emo+0.173
eer+0.154
cker+0.153
 sailor+0.149
rito+0.149
Neg logit contributions
oph-0.131
cake-0.127
cakes-0.125
board-0.117
ue-0.111
TokenN
Token ID45
Feature activation+3.34e+00

Pos logit contributions
emo+0.196
ba+0.163
 sailor+0.161
fish+0.158
eer+0.157
Neg logit contributions
oph-0.123
cake-0.120
cakes-0.117
board-0.105
 amusement-0.103
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
emo+0.047
cker+0.046
 sailor+0.044
 Albert+0.040
Albert+0.036
Neg logit contributions
oph-0.404
board-0.388
cake-0.384
aw-0.375
cakes-0.366
Token tried
Token ID3088
Feature activation+2.79e+00

Pos logit contributions
emo+1.221
eer+1.008
 sailor+0.992
ba+0.989
cker+0.974
Neg logit contributions
oph-0.965
cake-0.939
cakes-0.917
board-0.837
 amusement-0.834
Token his
Token ID465
Feature activation+2.93e+00

Pos logit contributions
emo+0.248
eer+0.211
 sailor+0.205
cker+0.204
ba+0.202
Neg logit contributions
oph-0.169
cake-0.164
cakes-0.159
 amusement-0.146
board-0.145
Token best
Token ID1266
Feature activation+2.23e+00

Pos logit contributions
emo+0.248
cker+0.225
rito+0.224
eer+0.215
 sailor+0.204
Neg logit contributions
oph-0.165
cakes-0.155
cake-0.155
board-0.149
oga-0.149
Token,
Token ID11
Feature activation+5.43e-01

Pos logit contributions
emo+0.207
cker+0.184
rito+0.182
eer+0.181
Albert+0.181
Neg logit contributions
oph-0.104
cake-0.095
board-0.095
 amusement-0.090
ue-0.087
Token but
Token ID475
Feature activation+5.78e-01

Pos logit contributions
emo+0.048
eer+0.041
ba+0.040
 sailor+0.040
cker+0.039
Neg logit contributions
oph-0.033
cake-0.032
cakes-0.031
board-0.029
 amusement-0.028
Tokeno
Token ID78
Feature activation+4.23e+00

Pos logit contributions
emo+0.551
 sailor+0.464
eer+0.445
rito+0.428
fish+0.425
Neg logit contributions
cake-0.510
oph-0.498
cakes-0.478
board-0.457
ue-0.437
Token.
Token ID13
Feature activation-7.98e-02

Pos logit contributions
emo+0.358
eer+0.296
 sailor+0.294
cker+0.282
rito+0.281
Neg logit contributions
cake-0.270
oph-0.269
cakes-0.258
board-0.242
ue-0.227
Token
Token ID198
Feature activation+2.04e+00

Pos logit contributions
cake+0.004
oph+0.004
cakes+0.004
board+0.004
ue+0.003
Neg logit contributions
emo-0.008
eer-0.007
ba-0.007
cker-0.007
 sailor-0.007
Token
Token ID198
Feature activation+2.05e+00

Pos logit contributions
emo+0.177
eer+0.165
cker+0.161
 sailor+0.160
rito+0.158
Neg logit contributions
oph-0.116
cake-0.111
cakes-0.109
board-0.101
ue-0.101
TokenN
Token ID45
Feature activation+3.35e+00

Pos logit contributions
emo+0.188
 sailor+0.155
ba+0.154
eer+0.154
cker+0.151
Neg logit contributions
oph-0.122
cake-0.119
cakes-0.117
board-0.105
 amusement-0.104
Tokenemo
Token ID41903
Feature activation+1.46e+01

Pos logit contributions
Albert+0.029
 Albert+0.028
 sailor+0.025
 crew+0.018
rito+0.015
Neg logit contributions
oph-0.422
board-0.411
cake-0.406
aw-0.393
cakes-0.380
Token sw
Token ID1509
Feature activation+6.62e-01

Pos logit contributions
emo+1.252
eer+1.054
 sailor+1.035
rito+1.021
ba+1.008
Neg logit contributions
oph-0.900
cake-0.872
cakes-0.840
board-0.804
ue-0.753
Tokenam
Token ID321
Feature activation+3.68e+00

Pos logit contributions
emo+0.051
 sailor+0.044
eer+0.043
ba+0.042
rito+0.042
Neg logit contributions
oph-0.046
cake-0.043
cakes-0.043
board-0.041
aw-0.040
Token under
Token ID739
Feature activation+2.91e+00

Pos logit contributions
emo+0.304
eer+0.248
ba+0.245
 sailor+0.245
cker+0.238
Neg logit contributions
oph-0.258
cake-0.248
cakes-0.242
board-0.223
 amusement-0.222
Token the
Token ID262
Feature activation-2.49e-01

Pos logit contributions
emo+0.304
ba+0.288
cker+0.287
eer+0.283
rito+0.279
Neg logit contributions
 amusement-0.099
oph-0.097
cake-0.090
 Tom-0.084
board-0.082
Token blanket
Token ID18447
Feature activation-5.16e-01

Pos logit contributions
oph+0.023
cake+0.022
cakes+0.022
board+0.021
 amusement+0.020
Neg logit contributions
emo-0.015
eer-0.011
 sailor-0.011
ba-0.011
cker-0.011
Token."
Token ID526
Feature activation+3.71e+00

Pos logit contributions
emo+0.165
eer+0.135
 sailor+0.134
cker+0.131
rito+0.129
Neg logit contributions
cake-0.137
cakes-0.135
oph-0.131
board-0.125
ue-0.114
Token
Token ID220
Feature activation-1.89e+00

Pos logit contributions
emo+0.326
eer+0.274
 sailor+0.269
ba+0.267
cker+0.265
Neg logit contributions
oph-0.231
cake-0.224
cakes-0.218
board-0.200
 amusement-0.196
Token
Token ID198
Feature activation+2.06e+00

Pos logit contributions
oph+0.099
cake+0.095
cakes+0.093
ue+0.087
uct+0.083
Neg logit contributions
emo-0.169
 sailor-0.161
eer-0.159
cker-0.158
rito-0.153
Token
Token ID198
Feature activation+2.05e+00

Pos logit contributions
emo+0.178
eer+0.169
cker+0.165
 sailor+0.162
rito+0.161
Neg logit contributions
oph-0.119
cake-0.111
cakes-0.109
ue-0.098
board-0.097
TokenN
Token ID45
Feature activation+3.34e+00

Pos logit contributions
emo+0.166
ba+0.132
 sailor+0.132
eer+0.131
fish+0.128
Neg logit contributions
oph-0.145
cake-0.143
cakes-0.140
board-0.129
 amusement-0.127
Tokenemo
Token ID41903
Feature activation+1.45e+01

Pos logit contributions
Albert+0.013
 sailor+0.013
rito+0.012
 Albert+0.010
cker+0.009
Neg logit contributions
oph-0.445
cake-0.415
board-0.413
cakes-0.396
aw-0.396
Token and
Token ID290
Feature activation-3.03e-01

Pos logit contributions
emo+1.275
eer+1.065
 sailor+1.048
ba+1.043
cker+1.032
Neg logit contributions
oph-0.906
cake-0.882
cakes-0.860
board-0.782
 amusement-0.775
Token D
Token ID360
Feature activation+2.50e+00

Pos logit contributions
oph+0.022
cake+0.019
 amusement+0.019
 Meg+0.018
That+0.018
Neg logit contributions
emo-0.021
rito-0.020
eer-0.020
cker-0.019
ery-0.018
Tokenory
Token ID652
Feature activation+5.25e+00

Pos logit contributions
emo+0.163
eer+0.145
cker+0.143
rito+0.143
 sailor+0.142
Neg logit contributions
oph-0.204
cake-0.189
cakes-0.180
board-0.179
ue-0.166
Token dove
Token ID38862
Feature activation+4.09e+00

Pos logit contributions
emo+0.429
eer+0.356
ba+0.351
 sailor+0.351
cker+0.345
Neg logit contributions
oph-0.359
cake-0.351
cakes-0.340
 amusement-0.311
board-0.309
Token deep
Token ID2769
Feature activation+2.21e+00

Pos logit contributions
emo+0.323
eer+0.260
rito+0.255
 sailor+0.253
cker+0.246
Neg logit contributions
cakes-0.272
oph-0.269
cake-0.266
board-0.254
 amusement-0.245
Token.
Token ID13
Feature activation-1.11e-01

Pos logit contributions
emo+0.144
eer+0.117
 sailor+0.115
ba+0.114
fish+0.112
Neg logit contributions
oph-0.140
cake-0.137
cakes-0.134
board-0.123
 amusement-0.120
Token
Token ID220
Feature activation-1.89e+00

Pos logit contributions
oph+0.007
cakes+0.006
cake+0.006
board+0.006
ue+0.005
Neg logit contributions
emo-0.010
eer-0.009
rito-0.009
cker-0.009
ba-0.008
Token
Token ID198
Feature activation+2.00e+00

Pos logit contributions
oph+0.095
cake+0.093
cakes+0.091
ue+0.084
That+0.082
Neg logit contributions
emo-0.171
 sailor-0.161
eer-0.160
cker-0.158
rito-0.156
Token
Token ID198
Feature activation+2.00e+00

Pos logit contributions
emo+0.181
cker+0.166
eer+0.166
 sailor+0.161
rito+0.161
Neg logit contributions
oph-0.111
cake-0.102
cakes-0.100
ue-0.094
board-0.092
TokenN
Token ID45
Feature activation+3.35e+00

Pos logit contributions
emo+0.144
eer+0.117
 sailor+0.114
cker+0.112
ba+0.112
Neg logit contributions
oph-0.157
cake-0.152
cakes-0.149
board-0.140
 amusement-0.138
Tokenemo
Token ID41903
Feature activation+1.45e+01

Pos logit contributions
Albert+0.047
 Albert+0.043
rito+0.032
 crew+0.030
cker+0.028
Neg logit contributions
oph-0.398
board-0.384
aw-0.376
cake-0.362
ue-0.349
Token sw
Token ID1509
Feature activation+6.73e-01

Pos logit contributions
emo+1.306
eer+1.122
rito+1.113
 sailor+1.097
ba+1.063
Neg logit contributions
oph-0.850
cake-0.790
cakes-0.759
board-0.731
ue-0.692
Tokenam
Token ID321
Feature activation+3.70e+00

Pos logit contributions
emo+0.053
 sailor+0.048
rito+0.048
eer+0.047
ba+0.046
Neg logit contributions
oph-0.042
cakes-0.037
aw-0.037
board-0.037
cake-0.037
Token up
Token ID510
Feature activation+1.88e+00

Pos logit contributions
emo+0.305
eer+0.249
 sailor+0.246
ba+0.245
cker+0.239
Neg logit contributions
oph-0.257
cake-0.249
cakes-0.243
board-0.224
 amusement-0.222
Token to
Token ID284
Feature activation-2.48e-01

Pos logit contributions
emo+0.157
eer+0.132
 sailor+0.129
ba+0.127
rito+0.127
Neg logit contributions
oph-0.123
cake-0.121
cakes-0.118
board-0.109
 amusement-0.107
Token his
Token ID465
Feature activation+2.89e+00

Pos logit contributions
oph+0.009
 Tom+0.009
 amusement+0.009
 Sophia+0.008
 Meg+0.008
Neg logit contributions
rito-0.024
cker-0.024
emo-0.023
eer-0.023
ery-0.022
Token shark
Token ID21027
Feature activation+4.03e+00

Pos logit contributions
oph+0.028
cake+0.028
cakes+0.027
 amusement+0.027
board+0.027
Neg logit contributions
emo-0.013
ba-0.009
eer-0.009
rito-0.009
cker-0.009
Token.
Token ID13
Feature activation-1.79e-01

Pos logit contributions
emo+0.336
eer+0.278
 sailor+0.272
ba+0.270
cker+0.268
Neg logit contributions
oph-0.268
cake-0.261
cakes-0.254
board-0.235
 amusement-0.232
Token
Token ID198
Feature activation+1.94e+00

Pos logit contributions
oph+0.011
cake+0.011
cakes+0.010
board+0.009
That+0.009
Neg logit contributions
emo-0.015
cker-0.014
eer-0.014
ba-0.013
 sailor-0.013
Token
Token ID198
Feature activation+1.96e+00

Pos logit contributions
emo+0.168
eer+0.160
cker+0.158
 sailor+0.156
rito+0.151
Neg logit contributions
oph-0.107
cake-0.103
cakes-0.101
That-0.093
ue-0.089
TokenN
Token ID45
Feature activation+3.33e+00

Pos logit contributions
emo+0.183
eer+0.151
 sailor+0.151
ba+0.151
cker+0.147
Neg logit contributions
oph-0.113
cake-0.109
cakes-0.106
board-0.097
 amusement-0.095
Tokenemo
Token ID41903
Feature activation+1.45e+01

Pos logit contributions
emo+0.014
cker+0.010
 sailor+0.009
rito+0.009
Albert+0.007
Neg logit contributions
oph-0.443
cake-0.411
board-0.408
aw-0.399
cakes-0.395
Token said
Token ID531
Feature activation-2.54e+00

Pos logit contributions
emo+1.257
eer+1.049
 sailor+1.035
ba+1.031
cker+1.012
Neg logit contributions
oph-0.921
cake-0.901
cakes-0.883
board-0.796
 amusement-0.793
Token,
Token ID11
Feature activation+4.54e-01

Pos logit contributions
cake+0.144
oph+0.144
cakes+0.140
board+0.125
 amusement+0.121
Neg logit contributions
emo-0.232
eer-0.198
cker-0.194
rito-0.193
ba-0.192
Token "
Token ID366
Feature activation-2.32e+00

Pos logit contributions
emo+0.044
eer+0.038
cker+0.036
rito+0.036
ba+0.036
Neg logit contributions
cake-0.024
oph-0.024
cakes-0.023
board-0.020
 amusement-0.020
TokenThanks
Token ID9690
Feature activation-3.45e+00

Pos logit contributions
oph+0.109
cake+0.105
cakes+0.101
board+0.089
 amusement+0.087
Neg logit contributions
emo-0.239
eer-0.206
 sailor-0.203
ba-0.202
cker-0.200
Token for
Token ID329
Feature activation-2.94e+00

Pos logit contributions
oph+0.199
cake+0.191
cakes+0.185
board+0.170
 amusement+0.166
Neg logit contributions
emo-0.318
eer-0.271
cker-0.268
rito-0.264
 sailor-0.262
Token cl
Token ID537
Feature activation-2.13e+00

Pos logit contributions
oph+0.399
cake+0.377
cakes+0.370
 amusement+0.341
board+0.337
Neg logit contributions
emo-0.449
eer-0.381
ba-0.379
 sailor-0.378
fish-0.368
Tokenapped
Token ID6320
Feature activation-1.04e+00

Pos logit contributions
oph+0.139
cake+0.136
cakes+0.135
 amusement+0.122
board+0.121
Neg logit contributions
emo-0.183
eer-0.149
ba-0.148
 sailor-0.146
cker-0.144
Token her
Token ID607
Feature activation-6.36e-01

Pos logit contributions
oph+0.084
cake+0.082
cakes+0.081
board+0.075
 amusement+0.072
Neg logit contributions
emo-0.073
 sailor-0.059
eer-0.058
ba-0.057
fish-0.056
Token hands
Token ID2832
Feature activation-1.24e-01

Pos logit contributions
oph+0.044
cake+0.043
cakes+0.042
board+0.038
 amusement+0.038
Neg logit contributions
emo-0.052
eer-0.043
 sailor-0.042
ba-0.042
cker-0.041
Token in
Token ID287
Feature activation+3.70e+00

Pos logit contributions
oph+0.011
cakes+0.010
cake+0.010
board+0.010
ue+0.010
Neg logit contributions
emo-0.007
eer-0.006
 sailor-0.006
ba-0.006
fish-0.006
Token amusement
Token ID30184
Feature activation-1.32e+01

Pos logit contributions
emo+0.263
 sailor+0.229
 sail+0.224
eer+0.213
 crew+0.210
Neg logit contributions
cakes-0.294
cake-0.284
oph-0.282
board-0.263
liv-0.250
Token.
Token ID13
Feature activation-2.38e-01

Pos logit contributions
cake+1.179
cakes+1.175
oph+1.173
uct+1.107
liv+1.087
Neg logit contributions
emo-0.637
 sailor-0.571
eer-0.569
fish-0.509
 sword-0.453
Token The
Token ID383
Feature activation+8.21e-02

Pos logit contributions
oph+0.017
cake+0.016
cakes+0.015
 amusement+0.015
board+0.014
Neg logit contributions
emo-0.019
eer-0.015
 Albert-0.014
cker-0.014
 sailor-0.014
Token other
Token ID584
Feature activation-8.56e-01

Pos logit contributions
emo+0.006
 sailor+0.005
 crew+0.005
eer+0.005
 sailors+0.005
Neg logit contributions
oph-0.007
cake-0.006
uct-0.006
liv-0.006
ue-0.006
Token boys
Token ID6510
Feature activation-4.95e+00

Pos logit contributions
oph+0.070
cake+0.065
uct+0.063
liv+0.060
cakes+0.057
Neg logit contributions
emo-0.057
eer-0.050
 crew-0.049
 sailor-0.048
 sailors-0.047
Token had
Token ID550
Feature activation-1.53e+00

Pos logit contributions
oph+0.328
cake+0.312
cakes+0.306
board+0.274
 amusement+0.274
Neg logit contributions
emo-0.405
 sailor-0.349
eer-0.346
ba-0.345
fish-0.338
Token they
Token ID484
Feature activation+6.82e-01

Pos logit contributions
emo+0.051
eer+0.045
cker+0.043
 sailor+0.043
rito+0.043
Neg logit contributions
oph-0.028
cake-0.027
cakes-0.026
board-0.023
 amusement-0.023
Token went
Token ID1816
Feature activation-1.32e-01

Pos logit contributions
emo+0.063
rito+0.055
eer+0.054
cker+0.053
fish+0.052
Neg logit contributions
oph-0.039
cake-0.035
cakes-0.034
 amusement-0.033
board-0.033
Token to
Token ID284
Feature activation-3.90e-01

Pos logit contributions
cakes+0.007
cake+0.007
oph+0.007
board+0.007
 amusement+0.006
Neg logit contributions
emo-0.012
rito-0.010
eer-0.010
cker-0.010
 sailor-0.010
Token a
Token ID257
Feature activation+6.59e-02

Pos logit contributions
oph+0.019
 amusement+0.019
cake+0.016
 Rebecca+0.016
cakes+0.016
Neg logit contributions
emo-0.039
rito-0.034
fish-0.034
eer-0.034
cker-0.033
Token big
Token ID1263
Feature activation-1.15e+00

Pos logit contributions
emo+0.005
eer+0.004
rito+0.004
ba+0.004
cker+0.004
Neg logit contributions
oph-0.005
cake-0.005
cakes-0.005
 amusement-0.004
board-0.004
Token amusement
Token ID30184
Feature activation-1.32e+01

Pos logit contributions
oph+0.082
cake+0.081
cakes+0.080
uct+0.072
board+0.071
Neg logit contributions
emo-0.088
 sailor-0.075
eer-0.073
cker-0.070
ba-0.070
Token park
Token ID3952
Feature activation-5.48e+00

Pos logit contributions
uct+0.855
oph+0.852
ishly+0.831
cake+0.800
cakes+0.797
Neg logit contributions
emo-1.018
 sailor-0.915
fish-0.879
eer-0.822
 sail-0.784
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
oph+0.531
cake+0.480
cakes+0.466
icious+0.462
uct+0.461
Neg logit contributions
emo-0.295
eer-0.230
cker-0.229
 sail-0.222
fish-0.220
Token Lily
Token ID20037
Feature activation-1.27e+00

Pos logit contributions
oph+0.008
cake+0.008
cakes+0.008
 amusement+0.007
board+0.007
Neg logit contributions
emo-0.010
eer-0.008
 sailor-0.008
ba-0.008
rito-0.008
Token was
Token ID373
Feature activation-8.11e-01

Pos logit contributions
oph+0.079
cake+0.075
cakes+0.073
board+0.069
 amusement+0.067
Neg logit contributions
emo-0.112
eer-0.093
rito-0.092
 sailor-0.091
cker-0.090
Token so
Token ID523
Feature activation-4.15e+00

Pos logit contributions
oph+0.052
cake+0.050
cakes+0.049
board+0.045
 amusement+0.044
Neg logit contributions
emo-0.070
eer-0.058
 sailor-0.057
ba-0.057
cker-0.056
Token took
Token ID1718
Feature activation+1.51e-01

Pos logit contributions
emo+0.140
eer+0.117
 sailor+0.115
ba+0.114
cker+0.114
Neg logit contributions
oph-0.104
cake-0.100
cakes-0.097
board-0.090
 amusement-0.088
Token her
Token ID607
Feature activation-3.79e-01

Pos logit contributions
emo+0.012
eer+0.010
 sailor+0.010
ba+0.010
cker+0.010
Neg logit contributions
oph-0.010
cake-0.010
cakes-0.010
board-0.009
 amusement-0.009
Token to
Token ID284
Feature activation-3.42e-01

Pos logit contributions
oph+0.025
cake+0.025
cakes+0.025
board+0.023
 amusement+0.023
Neg logit contributions
emo-0.031
eer-0.025
ba-0.025
cker-0.025
rito-0.024
Token a
Token ID257
Feature activation+3.29e-01

Pos logit contributions
oph+0.022
cake+0.021
cakes+0.021
board+0.019
 amusement+0.019
Neg logit contributions
emo-0.030
eer-0.025
 sailor-0.024
ba-0.024
cker-0.024
Token famous
Token ID5863
Feature activation+5.79e-01

Pos logit contributions
emo+0.026
eer+0.021
ba+0.020
cker+0.020
 sailor+0.020
Neg logit contributions
oph-0.024
cake-0.024
cakes-0.023
board-0.022
 amusement-0.021
Token amusement
Token ID30184
Feature activation-1.30e+01

Pos logit contributions
emo+0.045
 sailor+0.038
eer+0.037
ba+0.036
cker+0.036
Neg logit contributions
oph-0.041
cake-0.040
cakes-0.039
board-0.036
uct-0.035
Token park
Token ID3952
Feature activation-5.07e+00

Pos logit contributions
oph+0.803
cakes+0.764
cake+0.763
uct+0.762
Those+0.711
Neg logit contributions
emo-0.961
 sailor-0.907
fish-0.867
eer-0.849
 sword-0.775
Token.
Token ID13
Feature activation-4.07e-02

Pos logit contributions
oph+0.424
cake+0.391
cakes+0.380
uct+0.367
ue+0.358
Neg logit contributions
emo-0.315
eer-0.266
 sailor-0.261
fish-0.259
cker-0.253
Token Lily
Token ID20037
Feature activation-1.04e+00

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
 amusement+0.002
board+0.002
Neg logit contributions
emo-0.004
eer-0.003
 sailor-0.003
ba-0.003
rito-0.003
Token was
Token ID373
Feature activation-4.73e-01

Pos logit contributions
oph+0.071
cake+0.069
cakes+0.068
board+0.062
 amusement+0.061
Neg logit contributions
emo-0.084
eer-0.070
 sailor-0.069
ba-0.068
cker-0.067
Token so
Token ID523
Feature activation-4.02e+00

Pos logit contributions
oph+0.029
cake+0.028
cakes+0.027
board+0.025
 amusement+0.024
Neg logit contributions
emo-0.042
eer-0.035
 sailor-0.035
ba-0.035
cker-0.034
Token
Token ID198
Feature activation+2.09e+00

Pos logit contributions
emo+0.182
eer+0.156
 sailor+0.154
ba+0.152
cker+0.151
Neg logit contributions
oph-0.123
cake-0.121
cakes-0.117
 amusement-0.107
board-0.107
TokenThey
Token ID2990
Feature activation-2.78e+00

Pos logit contributions
emo+0.180
ba+0.147
 sailor+0.141
cker+0.140
fish+0.140
Neg logit contributions
oph-0.143
cake-0.135
cakes-0.134
board-0.123
 amusement-0.115
Token learn
Token ID2193
Feature activation-4.97e+00

Pos logit contributions
oph+0.196
cake+0.192
cakes+0.190
board+0.171
 amusement+0.166
Neg logit contributions
emo-0.218
 sailor-0.183
ba-0.180
eer-0.180
fish-0.175
Token that
Token ID326
Feature activation-4.34e+00

Pos logit contributions
oph+0.350
cake+0.320
cakes+0.305
board+0.294
ue+0.288
Neg logit contributions
emo-0.416
 sailor-0.339
eer-0.334
fish-0.331
ba-0.321
Token qu
Token ID627
Feature activation-4.35e-01

Pos logit contributions
oph+0.249
cake+0.248
cakes+0.243
 amusement+0.236
board+0.220
Neg logit contributions
emo-0.379
rito-0.328
eer-0.321
ba-0.320
cker-0.310
Tokenarre
Token ID9624
Feature activation-1.21e+01

Pos logit contributions
oph+0.021
cake+0.020
cakes+0.020
 amusement+0.017
board+0.017
Neg logit contributions
emo-0.045
eer-0.038
ba-0.037
 sailor-0.037
cker-0.037
Tokenling
Token ID1359
Feature activation+3.76e+00

Pos logit contributions
cakes+0.869
cake+0.851
oph+0.847
board+0.815
aw+0.793
Neg logit contributions
emo-0.841
 sailor-0.701
rito-0.678
 Albert-0.671
eer-0.657
Token is
Token ID318
Feature activation+2.32e-01

Pos logit contributions
emo+0.321
eer+0.267
 sailor+0.264
ba+0.262
cker+0.258
Neg logit contributions
oph-0.238
cake-0.234
cakes-0.228
board-0.211
 amusement-0.205
Token bad
Token ID2089
Feature activation-2.46e+00

Pos logit contributions
emo+0.018
eer+0.016
 sailor+0.015
ba+0.015
rito+0.015
Neg logit contributions
cake-0.015
oph-0.015
cakes-0.015
 amusement-0.014
uct-0.014
Token and
Token ID290
Feature activation-2.88e-01

Pos logit contributions
oph+0.151
cake+0.149
cakes+0.146
board+0.137
 amusement+0.131
Neg logit contributions
emo-0.214
eer-0.177
 sailor-0.176
ba-0.176
cker-0.175
Token sharing
Token ID7373
Feature activation-3.77e+00

Pos logit contributions
cake+0.016
cakes+0.016
oph+0.015
 amusement+0.015
That+0.015
Neg logit contributions
emo-0.025
ba-0.021
eer-0.021
rito-0.021
 sailor-0.021
Token "
Token ID366
Feature activation-2.49e+00

Pos logit contributions
cake+0.108
cakes+0.106
oph+0.105
board+0.095
 amusement+0.091
Neg logit contributions
emo-0.169
eer-0.143
rito-0.142
cker-0.142
ba-0.139
TokenWhy
Token ID5195
Feature activation-5.56e+00

Pos logit contributions
oph+0.145
cakes+0.131
cake+0.131
 amusement+0.121
board+0.117
Neg logit contributions
emo-0.231
ba-0.202
eer-0.194
cker-0.191
 sailor-0.191
Token are
Token ID389
Feature activation-2.46e+00

Pos logit contributions
oph+0.328
cake+0.319
cakes+0.311
board+0.284
 amusement+0.278
Neg logit contributions
emo-0.507
eer-0.428
 sailor-0.421
ba-0.417
cker-0.415
Token you
Token ID345
Feature activation+1.06e+00

Pos logit contributions
oph+0.189
cake+0.187
cakes+0.177
board+0.170
 amusement+0.165
Neg logit contributions
emo-0.179
 sailor-0.144
eer-0.142
ba-0.141
fish-0.138
Token qu
Token ID627
Feature activation-3.80e-01

Pos logit contributions
emo+0.086
ba+0.071
 sailor+0.071
eer+0.070
cker+0.069
Neg logit contributions
oph-0.074
cake-0.071
cakes-0.070
board-0.065
 amusement-0.063
Tokenarre
Token ID9624
Feature activation-1.20e+01

Pos logit contributions
oph+0.018
cake+0.018
cakes+0.017
 amusement+0.017
 Rebecca+0.016
Neg logit contributions
emo-0.038
ba-0.032
ery-0.030
eer-0.030
cker-0.030
Tokenling
Token ID1359
Feature activation+3.91e+00

Pos logit contributions
oph+0.984
cakes+0.977
cake+0.976
board+0.922
uct+0.875
Neg logit contributions
emo-0.763
 sailor-0.590
eer-0.582
rito-0.581
cker-0.566
Token?
Token ID30
Feature activation+6.32e-01

Pos logit contributions
emo+0.229
eer+0.180
 sailor+0.179
ba+0.171
fish+0.168
Neg logit contributions
oph-0.360
cake-0.344
cakes-0.344
uct-0.321
 amusement-0.312
Token You
Token ID921
Feature activation-1.81e+00

Pos logit contributions
emo+0.059
eer+0.050
 sailor+0.050
ba+0.049
cker+0.049
Neg logit contributions
oph-0.035
cake-0.034
cakes-0.033
board-0.030
 amusement-0.029
Token can
Token ID460
Feature activation+3.02e+00

Pos logit contributions
cake+0.110
oph+0.109
cakes+0.106
board+0.099
 amusement+0.097
Neg logit contributions
emo-0.159
eer-0.128
 sailor-0.128
rito-0.127
ba-0.125
Token share
Token ID2648
Feature activation+1.15e+00

Pos logit contributions
emo+0.234
eer+0.190
 sailor+0.187
ba+0.187
cker+0.183
Neg logit contributions
oph-0.220
cake-0.212
cakes-0.208
board-0.194
 amusement-0.190
Token Tom
Token ID4186
Feature activation-4.60e+00

Pos logit contributions
emo+0.029
eer+0.023
 sailor+0.022
 exc+0.022
cker+0.022
Neg logit contributions
oph-0.021
cake-0.020
cakes-0.020
board-0.018
 amusement-0.017
Token and
Token ID290
Feature activation-1.09e-01

Pos logit contributions
oph+0.285
cake+0.274
cakes+0.268
 amusement+0.239
board+0.239
Neg logit contributions
emo-0.408
eer-0.346
 sailor-0.339
ba-0.336
cker-0.331
Token Mia
Token ID32189
Feature activation-3.26e+00

Pos logit contributions
oph+0.006
cake+0.006
cakes+0.005
 amusement+0.005
board+0.005
Neg logit contributions
emo-0.011
eer-0.009
 sailor-0.009
ba-0.009
cker-0.009
Token stop
Token ID2245
Feature activation-4.09e+00

Pos logit contributions
oph+0.206
cake+0.203
cakes+0.197
board+0.183
 amusement+0.180
Neg logit contributions
emo-0.282
eer-0.232
 sailor-0.227
ba-0.225
cker-0.224
Token qu
Token ID627
Feature activation-4.54e-01

Pos logit contributions
oph+0.240
cake+0.235
cakes+0.227
 amusement+0.212
board+0.209
Neg logit contributions
emo-0.367
eer-0.308
 sailor-0.301
ba-0.300
rito-0.300
Tokenarre
Token ID9624
Feature activation-1.20e+01

Pos logit contributions
oph+0.033
cake+0.032
cakes+0.031
 amusement+0.029
 Rebecca+0.028
Neg logit contributions
emo-0.038
eer-0.030
ba-0.029
cker-0.028
ery-0.028
Tokenling
Token ID1359
Feature activation+3.98e+00

Pos logit contributions
oph+1.086
cake+1.071
cakes+1.056
board+1.001
 amusement+0.975
Neg logit contributions
emo-0.696
eer-0.515
 sailor-0.512
rito-0.494
cker-0.492
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
emo+0.230
eer+0.190
 sailor+0.183
fish+0.178
ba+0.177
Neg logit contributions
oph-0.382
cake-0.346
cakes-0.346
liv-0.330
uct-0.320
Token They
Token ID1119
Feature activation-4.70e-01

Pos logit contributions
emo+0.015
eer+0.011
 sailor+0.011
cker+0.011
 Albert+0.011
Neg logit contributions
oph-0.017
cake-0.016
cakes-0.016
 amusement-0.015
uct-0.015
Token see
Token ID766
Feature activation+1.47e+00

Pos logit contributions
oph+0.035
cake+0.034
cakes+0.033
board+0.030
 amusement+0.030
Neg logit contributions
emo-0.036
eer-0.029
 sailor-0.029
ba-0.029
cker-0.028
Token the
Token ID262
Feature activation-2.85e-01

Pos logit contributions
emo+0.113
eer+0.093
 sailor+0.092
ba+0.088
cker+0.088
Neg logit contributions
oph-0.113
cake-0.108
cakes-0.104
board-0.098
uct-0.095
TokenThey
Token ID2990
Feature activation-2.94e+00

Pos logit contributions
emo+0.172
ba+0.140
cker+0.139
 sailor+0.137
fish+0.135
Neg logit contributions
oph-0.133
cake-0.124
cakes-0.122
board-0.114
 amusement-0.104
Token are
Token ID389
Feature activation-2.44e+00

Pos logit contributions
oph+0.223
cake+0.223
cakes+0.220
board+0.195
liv+0.189
Neg logit contributions
emo-0.213
 sailor-0.184
eer-0.173
ba-0.171
 sail-0.171
Token tired
Token ID10032
Feature activation+6.00e-01

Pos logit contributions
oph+0.169
cake+0.168
cakes+0.164
 amusement+0.154
uct+0.151
Neg logit contributions
emo-0.185
eer-0.156
rito-0.151
cker-0.151
ba-0.151
Token from
Token ID422
Feature activation-1.50e+00

Pos logit contributions
emo+0.045
 sailor+0.038
eer+0.038
ba+0.037
fish+0.036
Neg logit contributions
oph-0.046
cakes-0.042
cake-0.042
liv-0.041
uct-0.040
Token qu
Token ID627
Feature activation-4.40e-01

Pos logit contributions
oph+0.094
cake+0.091
cakes+0.089
 amusement+0.083
board+0.081
Neg logit contributions
emo-0.130
eer-0.109
ba-0.107
 sailor-0.107
rito-0.107
Tokenarre
Token ID9624
Feature activation-1.20e+01

Pos logit contributions
oph+0.026
cake+0.025
cakes+0.024
 amusement+0.022
 Rebecca+0.021
Neg logit contributions
emo-0.042
eer-0.034
ba-0.034
cker-0.033
fish-0.033
Tokenling
Token ID1359
Feature activation+3.91e+00

Pos logit contributions
cake+0.982
cakes+0.981
oph+0.979
board+0.927
aw+0.889
Neg logit contributions
emo-0.747
rito-0.568
 sailor-0.563
eer-0.557
cker-0.541
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
emo+0.231
eer+0.190
 sailor+0.178
fish+0.171
ba+0.166
Neg logit contributions
oph-0.372
cake-0.341
cakes-0.336
liv-0.320
uct-0.314
Token They
Token ID1119
Feature activation-4.87e-01

Pos logit contributions
emo+0.010
eer+0.007
 sailor+0.007
cker+0.007
 sail+0.007
Neg logit contributions
cake-0.013
oph-0.013
cakes-0.012
board-0.012
uct-0.011
Token sit
Token ID1650
Feature activation+1.65e+00

Pos logit contributions
oph+0.035
cake+0.034
cakes+0.033
board+0.030
 amusement+0.030
Neg logit contributions
emo-0.038
eer-0.032
 sailor-0.031
ba-0.031
cker-0.030
Token in
Token ID287
Feature activation+3.43e+00

Pos logit contributions
emo+0.133
eer+0.110
 sailor+0.107
rito+0.106
ba+0.106
Neg logit contributions
oph-0.112
cake-0.110
cakes-0.108
board-0.100
 amusement-0.099
Token says
Token ID1139
Feature activation-1.78e+00

Pos logit contributions
oph+0.223
cake+0.214
cakes+0.204
board+0.188
 amusement+0.184
Neg logit contributions
emo-0.244
eer-0.207
ba-0.201
 sailor-0.200
cker-0.196
Token,
Token ID11
Feature activation+4.76e-01

Pos logit contributions
oph+0.116
cake+0.113
cakes+0.110
board+0.101
 amusement+0.099
Neg logit contributions
emo-0.152
eer-0.126
 sailor-0.124
ba-0.123
cker-0.122
Token "
Token ID366
Feature activation-2.41e+00

Pos logit contributions
emo+0.043
eer+0.036
 sailor+0.035
ba+0.035
cker+0.034
Neg logit contributions
oph-0.029
cake-0.028
cakes-0.027
board-0.025
 amusement-0.025
TokenStop
Token ID19485
Feature activation-4.69e+00

Pos logit contributions
cake+0.162
cakes+0.162
oph+0.156
board+0.153
oga+0.136
Neg logit contributions
emo-0.187
ba-0.166
 sailor-0.147
Ar-0.147
Albert-0.144
Token qu
Token ID627
Feature activation-4.86e-01

Pos logit contributions
oph+0.306
cake+0.297
cakes+0.290
board+0.266
 amusement+0.261
Neg logit contributions
emo-0.399
eer-0.332
 sailor-0.327
ba-0.324
cker-0.320
Tokenarre
Token ID9624
Feature activation-1.20e+01

Pos logit contributions
cake+0.028
oph+0.027
cakes+0.027
 amusement+0.025
 Rebecca+0.023
Neg logit contributions
emo-0.046
ba-0.038
eer-0.036
cker-0.036
ery-0.035
Tokenling
Token ID1359
Feature activation+3.89e+00

Pos logit contributions
oph+1.047
cake+1.033
cakes+1.022
board+0.973
 amusement+0.937
Neg logit contributions
emo-0.720
 sailor-0.539
eer-0.537
rito-0.528
cker-0.519
Token,
Token ID11
Feature activation+4.48e-01

Pos logit contributions
emo+0.242
eer+0.206
ba+0.201
 sailor+0.194
fish+0.184
Neg logit contributions
oph-0.348
cake-0.325
cakes-0.324
uct-0.305
 amusement-0.296
Token Tom
Token ID4186
Feature activation-4.54e+00

Pos logit contributions
emo+0.029
 sailor+0.027
eer+0.024
ba+0.024
 exc+0.024
Neg logit contributions
oph-0.035
cake-0.034
cakes-0.033
oga-0.031
board-0.031
Token and
Token ID290
Feature activation-2.16e-01

Pos logit contributions
oph+0.318
cakes+0.309
cake+0.308
 amusement+0.282
board+0.272
Neg logit contributions
emo-0.363
eer-0.307
ba-0.297
 sailor-0.293
cker-0.293
Token Lily
Token ID20037
Feature activation-1.18e+00

Pos logit contributions
oph+0.016
cake+0.015
cakes+0.014
board+0.013
 amusement+0.013
Neg logit contributions
emo-0.018
eer-0.015
 sailor-0.015
ba-0.014
cker-0.014
Token on
Token ID319
Feature activation-1.27e+00

Pos logit contributions
oph+0.018
cake+0.018
cakes+0.017
board+0.016
 amusement+0.016
Neg logit contributions
emo-0.020
eer-0.016
 sailor-0.016
ba-0.016
cker-0.015
Token,
Token ID11
Feature activation+2.04e-01

Pos logit contributions
oph+0.076
cake+0.073
cakes+0.072
board+0.066
 amusement+0.064
Neg logit contributions
emo-0.115
eer-0.098
ba-0.096
rito-0.095
 sailor-0.095
Token they
Token ID484
Feature activation+3.53e-01

Pos logit contributions
emo+0.019
eer+0.016
rito+0.016
cker+0.016
ba+0.016
Neg logit contributions
oph-0.012
cake-0.011
cakes-0.011
 amusement-0.010
board-0.010
Token never
Token ID1239
Feature activation-4.74e-01

Pos logit contributions
emo+0.029
eer+0.024
 sailor+0.023
ba+0.023
cker+0.023
Neg logit contributions
oph-0.024
cake-0.024
cakes-0.023
board-0.021
 amusement-0.021
Token qu
Token ID627
Feature activation-4.56e-01

Pos logit contributions
oph+0.033
cake+0.033
cakes+0.032
board+0.029
 amusement+0.029
Neg logit contributions
emo-0.038
eer-0.031
 sailor-0.030
ba-0.030
cker-0.030
Tokenarre
Token ID9624
Feature activation-1.20e+01

Pos logit contributions
oph+0.018
cake+0.018
cakes+0.016
 amusement+0.016
 Rebecca+0.015
Neg logit contributions
emo-0.050
ba-0.042
eer-0.041
rito-0.041
cker-0.041
Tokenled
Token ID992
Feature activation+4.86e+00

Pos logit contributions
oph+0.891
cake+0.873
cakes+0.873
board+0.805
uct+0.784
Neg logit contributions
emo-0.865
 sailor-0.701
eer-0.692
rito-0.688
cker-0.675
Token again
Token ID757
Feature activation-4.76e+00

Pos logit contributions
emo+0.462
eer+0.395
 sailor+0.385
ba+0.384
cker+0.383
Neg logit contributions
oph-0.265
cake-0.256
cakes-0.247
board-0.222
 amusement-0.221
Token over
Token ID625
Feature activation-4.06e+00

Pos logit contributions
oph+0.289
cake+0.279
cakes+0.268
 amusement+0.248
board+0.248
Neg logit contributions
emo-0.424
eer-0.357
 sailor-0.347
rito-0.346
ba-0.345
Token clothes
Token ID8242
Feature activation-8.35e-01

Pos logit contributions
oph+0.242
cake+0.233
cakes+0.227
 amusement+0.213
board+0.209
Neg logit contributions
emo-0.358
eer-0.308
rito-0.304
cker-0.299
ba-0.299
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
oph+0.055
cakes+0.052
cake+0.052
ue+0.048
 amusement+0.048
Neg logit contributions
emo-0.066
 sailor-0.058
fish-0.056
ba-0.056
eer-0.055
Token sharing
Token ID7373
Feature activation-3.86e+00

Pos logit contributions
oph+0.313
cake+0.302
cakes+0.294
board+0.279
 amusement+0.258
Neg logit contributions
emo-0.350
 sailor-0.281
eer-0.280
cker-0.272
ba-0.269
Token is
Token ID318
Feature activation+5.24e-02

Pos logit contributions
oph+0.260
cake+0.252
cakes+0.246
board+0.227
 amusement+0.224
Neg logit contributions
emo-0.319
eer-0.264
 sailor-0.259
ba-0.257
cker-0.254
Token important
Token ID1593
Feature activation+1.65e+00

Pos logit contributions
emo+0.004
eer+0.003
 sailor+0.003
ba+0.003
rito+0.003
Neg logit contributions
oph-0.004
cake-0.004
cakes-0.004
 amusement-0.004
board-0.003
Token and
Token ID290
Feature activation-5.13e-01

Pos logit contributions
emo+0.131
eer+0.108
 sailor+0.105
fish+0.102
ba+0.102
Neg logit contributions
oph-0.119
cake-0.113
cakes-0.110
 amusement-0.101
board-0.100
Token qu
Token ID627
Feature activation-3.24e-01

Pos logit contributions
oph+0.033
cake+0.033
cakes+0.032
 amusement+0.029
board+0.029
Neg logit contributions
emo-0.043
eer-0.036
ba-0.035
rito-0.035
 sailor-0.035
Tokenarre
Token ID9624
Feature activation-1.20e+01

Pos logit contributions
oph+0.013
cake+0.012
cakes+0.011
 amusement+0.010
board+0.010
Neg logit contributions
emo-0.037
eer-0.031
ba-0.031
cker-0.031
rito-0.030
Tokenlling
Token ID2680
Feature activation-2.18e+00

Pos logit contributions
cakes+0.889
cake+0.873
oph+0.866
board+0.818
uct+0.782
Neg logit contributions
emo-0.829
 sailor-0.685
rito-0.661
eer-0.650
 Albert-0.643
Token is
Token ID318
Feature activation+9.07e-02

Pos logit contributions
oph+0.149
cake+0.145
cakes+0.142
board+0.131
 amusement+0.129
Neg logit contributions
emo-0.176
eer-0.145
 sailor-0.143
ba-0.141
cker-0.140
Token not
Token ID407
Feature activation+7.23e-01

Pos logit contributions
emo+0.007
eer+0.006
 sailor+0.006
ba+0.006
rito+0.006
Neg logit contributions
cake-0.006
oph-0.006
cakes-0.006
 amusement-0.005
uct-0.005
Token good
Token ID922
Feature activation+2.22e+00

Pos logit contributions
emo+0.062
eer+0.052
ba+0.052
 sailor+0.052
fish+0.052
Neg logit contributions
oph-0.043
cake-0.042
cakes-0.040
 amusement-0.038
uct-0.037
Token.
Token ID13
Feature activation-8.84e-02

Pos logit contributions
emo+0.179
eer+0.147
 sailor+0.144
ba+0.142
cker+0.141
Neg logit contributions
oph-0.155
cake-0.150
cakes-0.147
board-0.135
 amusement-0.134
Token the
Token ID262
Feature activation-2.55e-01

Pos logit contributions
oph+0.064
cake+0.062
cakes+0.060
board+0.055
 amusement+0.054
Neg logit contributions
emo-0.077
eer-0.064
 sailor-0.063
ba-0.062
fish-0.061
Token mess
Token ID2085
Feature activation-5.86e+00

Pos logit contributions
oph+0.016
cake+0.015
cakes+0.015
board+0.014
 amusement+0.013
Neg logit contributions
emo-0.022
eer-0.019
 sailor-0.019
ba-0.018
cker-0.018
Token and
Token ID290
Feature activation-1.54e-02

Pos logit contributions
oph+0.551
 amusement+0.468
cake+0.450
uct+0.442
liv+0.440
Neg logit contributions
emo-0.346
fish-0.301
ba-0.301
eer-0.281
 sailor-0.274
Token the
Token ID262
Feature activation-2.11e-01

Pos logit contributions
oph+0.001
cake+0.001
cakes+0.001
board+0.001
liv+0.001
Neg logit contributions
emo-0.001
eer-0.001
 sailor-0.001
ba-0.001
 exc-0.001
Token qu
Token ID627
Feature activation-3.18e-01

Pos logit contributions
oph+0.014
cake+0.014
cakes+0.013
board+0.012
 amusement+0.012
Neg logit contributions
emo-0.018
eer-0.015
 sailor-0.015
ba-0.014
cker-0.014
Tokenarre
Token ID9624
Feature activation-1.19e+01

Pos logit contributions
oph+0.022
 amusement+0.020
cake+0.020
cakes+0.018
uct+0.018
Neg logit contributions
emo-0.027
eer-0.022
ba-0.022
rito-0.021
ery-0.021
Tokenling
Token ID1359
Feature activation+4.02e+00

Pos logit contributions
oph+1.117
cake+1.092
cakes+1.073
board+1.013
 amusement+1.006
Neg logit contributions
emo-0.675
eer-0.505
 sailor-0.490
ba-0.484
cker-0.474
Token twins
Token ID20345
Feature activation+8.51e-01

Pos logit contributions
emo+0.286
eer+0.231
 sailor+0.228
fish+0.225
ba+0.215
Neg logit contributions
oph-0.334
cake-0.301
uct-0.296
cakes-0.293
 amusement-0.290
Token.
Token ID13
Feature activation+2.97e-01

Pos logit contributions
emo+0.050
eer+0.042
 sailor+0.041
ba+0.040
fish+0.040
Neg logit contributions
oph-0.078
cake-0.070
cakes-0.070
liv-0.064
 amusement-0.064
Token She
Token ID1375
Feature activation-3.16e+00

Pos logit contributions
emo+0.028
eer+0.024
 sailor+0.023
ba+0.023
 Albert+0.023
Neg logit contributions
oph-0.016
cake-0.015
cakes-0.015
 amusement-0.014
uct-0.014
Token is
Token ID318
Feature activation+4.43e-01

Pos logit contributions
oph+0.263
cake+0.248
cakes+0.237
board+0.220
 amusement+0.219
Neg logit contributions
emo-0.208
ba-0.170
 sailor-0.168
eer-0.166
 exc-0.162
Token Lily
Token ID20037
Feature activation-1.26e+00

Pos logit contributions
emo+0.019
 sailor+0.015
eer+0.015
ba+0.014
fish+0.014
Neg logit contributions
oph-0.013
cake-0.013
cakes-0.013
board-0.012
 amusement-0.012
Token and
Token ID290
Feature activation-6.52e-01

Pos logit contributions
oph+0.080
cake+0.079
cakes+0.078
 amusement+0.070
board+0.069
Neg logit contributions
emo-0.108
eer-0.090
 sailor-0.089
ba-0.088
cker-0.086
Token Jack
Token ID3619
Feature activation-4.88e+00

Pos logit contributions
cake+0.041
cakes+0.040
oph+0.037
board+0.036
aw+0.035
Neg logit contributions
emo-0.059
 sailor-0.049
eer-0.048
 Albert-0.046
cker-0.045
Token never
Token ID1239
Feature activation-4.00e-01

Pos logit contributions
oph+0.355
cake+0.349
cakes+0.343
board+0.314
 amusement+0.311
Neg logit contributions
emo-0.373
eer-0.311
ba-0.304
 sailor-0.303
cker-0.298
Token qu
Token ID627
Feature activation-3.49e-01

Pos logit contributions
oph+0.030
cakes+0.029
cake+0.029
board+0.027
liv+0.026
Neg logit contributions
emo-0.030
eer-0.024
ba-0.024
 sailor-0.024
cker-0.023
Tokenarre
Token ID9624
Feature activation-1.19e+01

Pos logit contributions
oph+0.015
cake+0.015
 amusement+0.014
cakes+0.014
 Rebecca+0.012
Neg logit contributions
emo-0.038
ba-0.031
eer-0.031
cker-0.030
ery-0.030
Tokenled
Token ID992
Feature activation+4.92e+00

Pos logit contributions
oph+0.969
cake+0.951
cakes+0.939
board+0.877
 amusement+0.853
Neg logit contributions
emo-0.804
eer-0.631
 sailor-0.629
rito-0.611
cker-0.609
Token again
Token ID757
Feature activation-4.75e+00

Pos logit contributions
emo+0.452
eer+0.381
 sailor+0.378
ba+0.374
cker+0.367
Neg logit contributions
oph-0.286
cake-0.278
cakes-0.271
board-0.247
 amusement-0.240
Token.
Token ID13
Feature activation-3.15e-01

Pos logit contributions
oph+0.315
cake+0.306
cakes+0.299
board+0.274
 amusement+0.269
Neg logit contributions
emo-0.400
eer-0.331
 sailor-0.326
ba-0.323
cker-0.320
Token They
Token ID1119
Feature activation-6.93e-01

Pos logit contributions
oph+0.021
cake+0.020
cakes+0.020
board+0.019
 amusement+0.019
Neg logit contributions
emo-0.027
eer-0.021
 sailor-0.020
ba-0.020
rito-0.020
Token learned
Token ID4499
Feature activation-3.28e+00

Pos logit contributions
oph+0.047
cake+0.046
cakes+0.045
board+0.041
 amusement+0.040
Neg logit contributions
emo-0.057
eer-0.048
ba-0.047
 sailor-0.047
cker-0.046
Token walking
Token ID6155
Feature activation+2.40e+00

Pos logit contributions
oph+0.050
cake+0.048
cakes+0.047
board+0.044
 amusement+0.042
Neg logit contributions
emo-0.048
eer-0.039
ba-0.039
 sailor-0.039
cker-0.038
Token by
Token ID416
Feature activation-1.23e-01

Pos logit contributions
emo+0.151
eer+0.133
ba+0.129
 sailor+0.124
cker+0.121
Neg logit contributions
oph-0.208
cake-0.192
cakes-0.186
uct-0.174
 amusement-0.174
Token saw
Token ID2497
Feature activation-7.65e-01

Pos logit contributions
oph+0.010
cake+0.010
cakes+0.009
board+0.008
uct+0.008
Neg logit contributions
emo-0.009
ba-0.007
eer-0.007
cker-0.007
fish-0.007
Token them
Token ID606
Feature activation+2.84e+00

Pos logit contributions
oph+0.074
cake+0.073
cakes+0.068
uct+0.066
board+0.066
Neg logit contributions
emo-0.039
eer-0.029
ba-0.027
fish-0.027
 sailor-0.027
Token qu
Token ID627
Feature activation-4.47e-01

Pos logit contributions
emo+0.185
ba+0.159
eer+0.158
 sailor+0.154
cker+0.153
Neg logit contributions
oph-0.237
cake-0.214
cakes-0.212
board-0.191
liv-0.190
Tokenarre
Token ID9624
Feature activation-1.19e+01

Pos logit contributions
oph+0.021
cake+0.021
cakes+0.019
 amusement+0.019
 Rebecca+0.017
Neg logit contributions
emo-0.047
eer-0.039
ba-0.039
cker-0.038
ery-0.037
Tokenling
Token ID1359
Feature activation+3.86e+00

Pos logit contributions
oph+1.064
cake+1.051
cakes+1.038
board+0.983
 amusement+0.957
Neg logit contributions
emo-0.706
eer-0.522
 sailor-0.520
rito-0.503
cker-0.495
Token.
Token ID13
Feature activation+7.15e-02

Pos logit contributions
emo+0.213
eer+0.189
ba+0.176
 sailor+0.173
fish+0.168
Neg logit contributions
oph-0.350
cake-0.316
cakes-0.314
liv-0.302
uct-0.298
Token She
Token ID1375
Feature activation-3.19e+00

Pos logit contributions
emo+0.006
 Albert+0.005
eer+0.005
 exc+0.005
cker+0.005
Neg logit contributions
oph-0.004
cakes-0.004
cake-0.004
 amusement-0.004
icious-0.004
Token was
Token ID373
Feature activation-6.19e-01

Pos logit contributions
oph+0.231
cake+0.224
cakes+0.221
board+0.202
 amusement+0.201
Neg logit contributions
emo-0.242
ba-0.203
eer-0.200
 sailor-0.199
cker-0.195
Token very
Token ID845
Feature activation+1.72e+00

Pos logit contributions
oph+0.049
cake+0.047
cakes+0.046
board+0.044
ue+0.042
Neg logit contributions
emo-0.044
ba-0.035
eer-0.035
 sailor-0.035
rito-0.034
Token the
Token ID262
Feature activation-1.18e-01

Pos logit contributions
oph+0.258
cake+0.250
cakes+0.244
board+0.224
 amusement+0.220
Neg logit contributions
emo-0.348
eer-0.290
 sailor-0.285
ba-0.283
cker-0.280
Token dog
Token ID3290
Feature activation-2.74e+00

Pos logit contributions
oph+0.010
uct+0.009
cake+0.009
cakes+0.009
ue+0.008
Neg logit contributions
emo-0.008
eer-0.007
 sailor-0.007
fish-0.006
cker-0.006
Token and
Token ID290
Feature activation-2.61e-01

Pos logit contributions
oph+0.201
cake+0.187
cakes+0.185
board+0.167
 amusement+0.166
Neg logit contributions
emo-0.210
eer-0.181
ba-0.176
 sailor-0.174
fish-0.173
Token the
Token ID262
Feature activation-1.57e-01

Pos logit contributions
oph+0.017
cake+0.017
cakes+0.016
board+0.015
 amusement+0.015
Neg logit contributions
emo-0.022
eer-0.018
 sailor-0.018
ba-0.018
cker-0.018
Token black
Token ID2042
Feature activation-1.85e+00

Pos logit contributions
oph+0.012
cake+0.011
cakes+0.011
uct+0.010
ue+0.010
Neg logit contributions
emo-0.012
eer-0.010
 sailor-0.010
cker-0.010
ba-0.009
Tokenboard
Token ID3526
Feature activation-1.19e+01

Pos logit contributions
oph+0.147
uct+0.144
cakes+0.137
cake+0.135
liv+0.124
Neg logit contributions
emo-0.129
eer-0.116
 sailor-0.107
cker-0.104
fish-0.103
Token and
Token ID290
Feature activation-2.60e-01

Pos logit contributions
oph+1.088
cake+0.938
cakes+0.934
 amusement+0.921
uct+0.901
Neg logit contributions
emo-0.704
fish-0.612
eer-0.589
cker-0.574
 sailor-0.554
Token the
Token ID262
Feature activation-1.63e-01

Pos logit contributions
oph+0.018
cake+0.018
cakes+0.017
board+0.016
 amusement+0.016
Neg logit contributions
emo-0.021
eer-0.017
 sailor-0.017
cker-0.017
ba-0.017
Token chalk
Token ID30860
Feature activation-5.94e+00

Pos logit contributions
oph+0.012
cake+0.011
cakes+0.011
uct+0.010
ue+0.010
Neg logit contributions
emo-0.012
eer-0.010
 sailor-0.010
cker-0.010
ba-0.010
Token and
Token ID290
Feature activation-2.52e-01

Pos logit contributions
oph+0.510
cake+0.451
cakes+0.449
 amusement+0.439
uct+0.437
Neg logit contributions
emo-0.377
fish-0.328
eer-0.325
 sailor-0.305
ba-0.303
Token the
Token ID262
Feature activation-2.05e-01

Pos logit contributions
oph+0.020
cake+0.019
cakes+0.018
board+0.017
ue+0.017
Neg logit contributions
emo-0.018
eer-0.015
 sailor-0.015
cker-0.015
fish-0.014
Token.
Token ID13
Feature activation-3.94e-01

Pos logit contributions
emo+0.135
eer+0.109
 sailor+0.107
ba+0.106
fish+0.105
Neg logit contributions
oph-0.138
cake-0.134
cakes-0.130
board-0.121
 amusement-0.119
Token They
Token ID1119
Feature activation-6.24e-01

Pos logit contributions
cake+0.027
oph+0.026
cakes+0.026
 amusement+0.024
board+0.023
Neg logit contributions
emo-0.033
 sailor-0.026
eer-0.025
ba-0.024
fish-0.024
Token opened
Token ID4721
Feature activation+3.57e+00

Pos logit contributions
cake+0.052
oph+0.052
cakes+0.050
 amusement+0.047
liv+0.046
Neg logit contributions
emo-0.039
ba-0.032
 sailor-0.032
eer-0.031
cker-0.030
Token the
Token ID262
Feature activation-4.12e-01

Pos logit contributions
emo+0.268
eer+0.216
 sailor+0.215
ba+0.212
cker+0.208
Neg logit contributions
oph-0.267
cake-0.264
cakes-0.255
board-0.239
 amusement-0.230
Token cup
Token ID6508
Feature activation-6.59e+00

Pos logit contributions
oph+0.029
uct+0.025
cake+0.025
 amusement+0.024
cakes+0.024
Neg logit contributions
emo-0.031
rito-0.028
ba-0.027
eer-0.027
fish-0.026
Tokenboard
Token ID3526
Feature activation-1.19e+01

Pos logit contributions
 amusement+0.348
uct+0.345
icious+0.341
oph+0.338
Tam+0.305
Neg logit contributions
fish-0.534
emo-0.502
ware-0.482
eer-0.474
 sword-0.466
Token and
Token ID290
Feature activation-6.54e-01

Pos logit contributions
oph+1.164
icious+1.071
 amusement+1.065
uct+1.050
Tam+1.032
Neg logit contributions
fish-0.456
emo-0.448
 sword-0.389
 sail-0.376
eer-0.355
Token took
Token ID1718
Feature activation+2.87e-01

Pos logit contributions
oph+0.051
cake+0.050
cakes+0.048
 amusement+0.045
ue+0.045
Neg logit contributions
emo-0.046
 sailor-0.038
ba-0.037
eer-0.036
fish-0.035
Token out
Token ID503
Feature activation+2.37e+00

Pos logit contributions
emo+0.024
eer+0.020
 sailor+0.020
cker+0.020
ba+0.020
Neg logit contributions
oph-0.019
cake-0.018
cakes-0.018
board-0.016
 amusement-0.016
Token some
Token ID617
Feature activation-5.30e+00

Pos logit contributions
emo+0.180
eer+0.147
 sailor+0.146
ba+0.143
rito+0.140
Neg logit contributions
oph-0.176
cake-0.172
cakes-0.163
board-0.154
uct-0.150
Token pots
Token ID32195
Feature activation+2.56e+00

Pos logit contributions
oph+0.374
cake+0.357
cakes+0.345
 amusement+0.317
board+0.317
Neg logit contributions
emo-0.423
eer-0.352
 sailor-0.344
ba-0.338
rito-0.338
Token They
Token ID1119
Feature activation-6.36e-01

Pos logit contributions
cake+0.027
cakes+0.026
oph+0.026
 amusement+0.024
uct+0.024
Neg logit contributions
emo-0.028
 sailor-0.022
eer-0.021
rito-0.021
 sail-0.020
Token saw
Token ID2497
Feature activation-9.02e-01

Pos logit contributions
oph+0.043
cake+0.042
cakes+0.041
board+0.038
 amusement+0.037
Neg logit contributions
emo-0.052
eer-0.043
 sailor-0.042
ba-0.042
cker-0.042
Token a
Token ID257
Feature activation-9.77e-02

Pos logit contributions
oph+0.077
cake+0.073
uct+0.070
ue+0.070
cakes+0.067
Neg logit contributions
emo-0.059
 sailor-0.048
eer-0.047
fish-0.044
ba-0.043
Token big
Token ID1263
Feature activation-1.20e+00

Pos logit contributions
oph+0.008
cake+0.008
cakes+0.008
uct+0.007
 amusement+0.007
Neg logit contributions
emo-0.006
 sailor-0.005
eer-0.005
fish-0.005
ba-0.005
Token cup
Token ID6508
Feature activation-6.59e+00

Pos logit contributions
oph+0.096
uct+0.090
cake+0.088
cakes+0.088
liv+0.083
Neg logit contributions
emo-0.077
 sailor-0.073
fish-0.069
 sail-0.066
eer-0.066
Tokenboard
Token ID3526
Feature activation-1.19e+01

Pos logit contributions
oph+0.536
uct+0.499
 amusement+0.479
Tam+0.470
liv+0.449
Neg logit contributions
fish-0.424
emo-0.371
 sailor-0.344
ery-0.333
eer-0.327
Token with
Token ID351
Feature activation-1.08e+00

Pos logit contributions
oph+1.176
uct+0.987
 amusement+0.973
Tam+0.951
icious+0.945
Neg logit contributions
emo-0.582
fish-0.551
 sail-0.475
 exc-0.473
eer-0.470
Token many
Token ID867
Feature activation-2.30e+00

Pos logit contributions
oph+0.087
cake+0.084
cakes+0.079
uct+0.078
ue+0.077
Neg logit contributions
emo-0.074
eer-0.061
 sailor-0.059
ba-0.057
rito-0.057
Token things
Token ID1243
Feature activation+2.70e+00

Pos logit contributions
oph+0.182
cake+0.175
cakes+0.165
uct+0.157
 amusement+0.157
Neg logit contributions
emo-0.161
eer-0.133
 sailor-0.128
fish-0.127
ba-0.127
Token inside
Token ID2641
Feature activation+1.82e+00

Pos logit contributions
emo+0.196
eer+0.159
 sailor+0.155
ba+0.154
fish+0.152
Neg logit contributions
oph-0.210
cake-0.200
cakes-0.195
board-0.182
 amusement-0.181
Token.
Token ID13
Feature activation-3.94e-01

Pos logit contributions
emo+0.135
eer+0.109
 sailor+0.107
ba+0.106
fish+0.105
Neg logit contributions
oph-0.138
cake-0.134
cakes-0.130
board-0.121
 amusement-0.119
Token teacher
Token ID4701
Feature activation-6.05e+00

Pos logit contributions
oph+0.006
cake+0.005
cakes+0.005
uct+0.005
ue+0.005
Neg logit contributions
emo-0.006
 sailor-0.006
eer-0.005
fish-0.005
 exc-0.005
Token writes
Token ID6797
Feature activation+3.81e+00

Pos logit contributions
oph+0.421
cake+0.405
cakes+0.394
board+0.363
 amusement+0.362
Neg logit contributions
emo-0.469
eer-0.399
 sailor-0.392
ba-0.381
cker-0.380
Token on
Token ID319
Feature activation-1.30e+00

Pos logit contributions
emo+0.322
eer+0.274
 sailor+0.269
ba+0.266
fish+0.263
Neg logit contributions
oph-0.246
cake-0.230
cakes-0.221
 amusement-0.207
board-0.205
Token the
Token ID262
Feature activation-3.56e-01

Pos logit contributions
oph+0.101
cake+0.100
cakes+0.096
uct+0.089
board+0.088
Neg logit contributions
emo-0.088
eer-0.076
 sailor-0.072
ba-0.069
rito-0.068
Token black
Token ID2042
Feature activation-1.92e+00

Pos logit contributions
oph+0.025
cake+0.023
cakes+0.023
ue+0.021
uct+0.021
Neg logit contributions
emo-0.028
eer-0.024
 sailor-0.024
cker-0.023
fish-0.023
Tokenboard
Token ID3526
Feature activation-1.19e+01

Pos logit contributions
oph+0.054
uct+0.046
cakes+0.038
cake+0.037
liv+0.033
Neg logit contributions
emo-0.229
eer-0.214
 sailor-0.208
fish-0.204
rito-0.200
Token.
Token ID13
Feature activation-4.02e-01

Pos logit contributions
oph+0.907
cake+0.787
 amusement+0.782
cakes+0.779
uct+0.750
Neg logit contributions
emo-0.845
eer-0.717
fish-0.707
 sailor-0.705
ba-0.682
Token She
Token ID1375
Feature activation-3.31e+00

Pos logit contributions
oph+0.025
cake+0.024
cakes+0.023
board+0.021
 amusement+0.021
Neg logit contributions
emo-0.034
eer-0.029
 sailor-0.029
rito-0.027
 Albert-0.027
Token writes
Token ID6797
Feature activation+3.83e+00

Pos logit contributions
oph+0.209
cake+0.204
cakes+0.199
board+0.183
 amusement+0.180
Neg logit contributions
emo-0.288
eer-0.239
 sailor-0.234
ba-0.233
rito-0.233
Token words
Token ID2456
Feature activation-2.34e+00

Pos logit contributions
emo+0.321
eer+0.272
 sailor+0.267
ba+0.265
fish+0.260
Neg logit contributions
oph-0.249
cake-0.234
cakes-0.225
 amusement-0.211
board-0.209
Token and
Token ID290
Feature activation-6.38e-01

Pos logit contributions
oph+0.143
cake+0.138
cakes+0.134
board+0.123
 amusement+0.121
Neg logit contributions
emo-0.207
eer-0.174
 sailor-0.172
ba-0.170
cker-0.168
Token on
Token ID319
Feature activation-1.17e+00

Pos logit contributions
oph+0.013
cake+0.013
cakes+0.012
 amusement+0.012
board+0.012
Neg logit contributions
emo-0.010
ba-0.008
 sailor-0.007
eer-0.007
fish-0.007
Token,
Token ID11
Feature activation+2.20e-01

Pos logit contributions
oph+0.069
cake+0.066
cakes+0.065
board+0.060
 amusement+0.058
Neg logit contributions
emo-0.107
eer-0.092
ba-0.090
rito-0.090
cker-0.089
Token they
Token ID484
Feature activation+4.24e-01

Pos logit contributions
emo+0.020
 sailor+0.016
eer+0.016
ba+0.016
cker+0.016
Neg logit contributions
oph-0.013
cake-0.013
cakes-0.013
board-0.012
 amusement-0.011
Token never
Token ID1239
Feature activation-3.75e-01

Pos logit contributions
emo+0.035
ba+0.029
 sailor+0.029
eer+0.029
cker+0.028
Neg logit contributions
cake-0.028
oph-0.028
cakes-0.028
board-0.025
 amusement-0.025
Token qu
Token ID627
Feature activation-4.39e-01

Pos logit contributions
oph+0.027
cake+0.027
cakes+0.027
board+0.024
liv+0.024
Neg logit contributions
emo-0.029
eer-0.023
ba-0.023
 sailor-0.023
cker-0.022
Tokenarre
Token ID9624
Feature activation-1.19e+01

Pos logit contributions
oph+0.018
cake+0.018
cakes+0.016
 amusement+0.016
 Rebecca+0.014
Neg logit contributions
emo-0.048
eer-0.040
ba-0.040
rito-0.039
cker-0.039
Tokenled
Token ID992
Feature activation+4.90e+00

Pos logit contributions
oph+0.932
cake+0.917
cakes+0.913
board+0.848
uct+0.823
Neg logit contributions
emo-0.821
 sailor-0.658
eer-0.648
rito-0.639
cker-0.632
Token again
Token ID757
Feature activation-4.72e+00

Pos logit contributions
emo+0.470
eer+0.401
 sailor+0.392
ba+0.391
cker+0.390
Neg logit contributions
oph-0.265
cake-0.255
cakes-0.247
board-0.222
 amusement-0.221
Token and
Token ID290
Feature activation-5.53e-01

Pos logit contributions
oph+0.275
cake+0.265
cakes+0.255
 amusement+0.235
board+0.235
Neg logit contributions
emo-0.430
eer-0.363
 sailor-0.355
rito-0.355
ba-0.352
Token played
Token ID2826
Feature activation-4.98e-01

Pos logit contributions
oph+0.039
cake+0.038
cakes+0.037
board+0.035
 amusement+0.033
Neg logit contributions
emo-0.044
eer-0.036
 sailor-0.035
ba-0.035
cker-0.034
Token together
Token ID1978
Feature activation-1.49e+00

Pos logit contributions
oph+0.036
cake+0.035
cakes+0.034
board+0.031
 amusement+0.031
Neg logit contributions
emo-0.039
 sailor-0.032
eer-0.032
ba-0.031
fish-0.030
Token and
Token ID290
Feature activation-4.07e-02

Pos logit contributions
emo+0.104
eer+0.086
ba+0.083
cker+0.082
 sailor+0.082
Neg logit contributions
oph-0.118
cakes-0.115
cake-0.113
 amusement-0.108
uct-0.105
Token Ben
Token ID3932
Feature activation-7.40e-01

Pos logit contributions
oph+0.003
cake+0.003
cakes+0.002
board+0.002
 amusement+0.002
Neg logit contributions
emo-0.004
 sailor-0.003
eer-0.003
ba-0.003
fish-0.003
Token,
Token ID11
Feature activation+6.15e-01

Pos logit contributions
cakes+0.062
oph+0.062
cake+0.060
 amusement+0.056
uct+0.054
Neg logit contributions
emo-0.046
eer-0.037
ba-0.036
 sailor-0.036
cker-0.035
Token stop
Token ID2245
Feature activation-3.91e+00

Pos logit contributions
emo+0.048
eer+0.039
 sailor+0.039
ba+0.038
fish+0.037
Neg logit contributions
oph-0.045
cake-0.044
cakes-0.043
board-0.039
 amusement-0.039
Token qu
Token ID627
Feature activation-2.56e-01

Pos logit contributions
oph+0.264
cake+0.254
cakes+0.249
board+0.227
 amusement+0.219
Neg logit contributions
emo-0.330
 sailor-0.273
eer-0.271
ba-0.269
fish-0.263
Tokenarre
Token ID9624
Feature activation-1.19e+01

Pos logit contributions
cake+0.015
oph+0.015
cakes+0.014
 amusement+0.013
 Rebecca+0.012
Neg logit contributions
emo-0.024
ba-0.020
ery-0.019
eer-0.019
cker-0.019
Tokenling
Token ID1359
Feature activation+4.05e+00

Pos logit contributions
oph+1.148
cake+1.123
cakes+1.103
board+1.041
 amusement+1.038
Neg logit contributions
emo-0.646
eer-0.479
 sailor-0.462
ba-0.461
cker-0.446
Token right
Token ID826
Feature activation-6.35e+00

Pos logit contributions
emo+0.250
eer+0.217
 sailor+0.208
ba+0.207
fish+0.197
Neg logit contributions
oph-0.349
cakes-0.328
cake-0.326
uct-0.303
liv-0.300
Token now
Token ID783
Feature activation-4.34e+00

Pos logit contributions
oph+0.480
cake+0.460
cakes+0.457
 amusement+0.410
board+0.404
Neg logit contributions
emo-0.479
eer-0.407
ba-0.398
 sailor-0.394
fish-0.386
Token!
Token ID0
Feature activation-5.22e+00

Pos logit contributions
oph+0.377
cakes+0.359
cake+0.359
board+0.331
 amusement+0.330
Neg logit contributions
emo-0.273
eer-0.219
 sailor-0.215
ba-0.207
cker-0.206
Token Look
Token ID6803
Feature activation-2.58e+00

Pos logit contributions
oph+0.254
cake+0.252
cakes+0.240
board+0.220
 amusement+0.208
Neg logit contributions
emo-0.509
eer-0.444
 sailor-0.440
cker-0.440
ba-0.438
Token they
Token ID484
Feature activation+6.59e-01

Pos logit contributions
emo+0.028
eer+0.023
 sailor+0.022
ba+0.022
rito+0.022
Neg logit contributions
oph-0.024
cake-0.023
cakes-0.023
board-0.021
 amusement-0.021
Token saw
Token ID2497
Feature activation-8.64e-01

Pos logit contributions
emo+0.043
 sailor+0.035
ba+0.035
eer+0.031
 sail+0.031
Neg logit contributions
cake-0.056
cakes-0.055
oph-0.053
liv-0.051
uct-0.050
Token a
Token ID257
Feature activation+1.87e-02

Pos logit contributions
oph+0.080
cake+0.079
cakes+0.075
uct+0.073
ue+0.073
Neg logit contributions
emo-0.052
 sailor-0.041
eer-0.038
 sail-0.037
 crew-0.037
Token big
Token ID1263
Feature activation-1.08e+00

Pos logit contributions
emo+0.001
 sailor+0.001
fish+0.001
ba+0.001
eer+0.001
Neg logit contributions
oph-0.002
cake-0.002
cakes-0.002
uct-0.001
board-0.001
Token black
Token ID2042
Feature activation-1.73e+00

Pos logit contributions
oph+0.086
cakes+0.085
cake+0.084
uct+0.083
liv+0.076
Neg logit contributions
 sailor-0.069
emo-0.068
 sword-0.063
fish-0.062
 sail-0.061
Tokenboard
Token ID3526
Feature activation-1.19e+01

Pos logit contributions
uct+0.083
oph+0.079
cakes+0.072
liv+0.070
cake+0.066
Neg logit contributions
emo-0.167
 sailor-0.165
fish-0.158
eer-0.155
 sword-0.155
Token near
Token ID1474
Feature activation+1.92e+00

Pos logit contributions
oph+1.231
cakes+0.996
 Rebecca+0.991
uct+0.990
 amusement+0.989
Neg logit contributions
emo-0.527
fish-0.527
cker-0.464
 sail-0.460
 exc-0.455
Token the
Token ID262
Feature activation-9.29e-02

Pos logit contributions
emo+0.122
eer+0.094
 sailor+0.093
 sail+0.093
cker+0.092
Neg logit contributions
cake-0.171
oph-0.169
cakes-0.166
board-0.153
liv-0.144
Token fence
Token ID13990
Feature activation-4.57e+00

Pos logit contributions
oph+0.008
uct+0.007
cakes+0.007
cake+0.007
liv+0.007
Neg logit contributions
 sailor-0.005
emo-0.005
 mineral-0.005
 sword-0.005
 sail-0.005
Token.
Token ID13
Feature activation-3.29e-01

Pos logit contributions
oph+0.523
liv+0.446
cakes+0.438
cake+0.431
icious+0.431
Neg logit contributions
emo-0.162
fish-0.147
cker-0.141
 sail-0.134
eer-0.132
Token It
Token ID632
Feature activation-1.57e-01

Pos logit contributions
oph+0.024
cake+0.023
cakes+0.021
 amusement+0.021
uct+0.020
Neg logit contributions
emo-0.026
eer-0.020
cker-0.019
 sailor-0.019
 sail-0.019
Tokenll
Token ID297
Feature activation+5.69e+00

Pos logit contributions
emo+0.502
eer+0.456
 sailor+0.453
rito+0.451
 Albert+0.416
Neg logit contributions
oph-0.500
ue-0.474
cake-0.460
cakes-0.450
aw-0.446
Tokenie
Token ID494
Feature activation+8.02e+00

Pos logit contributions
emo+0.402
rito+0.360
 sailor+0.353
Albert+0.345
 Albert+0.341
Neg logit contributions
oph-0.374
ue-0.337
board-0.332
cake-0.321
cakes-0.320
Token.
Token ID13
Feature activation-2.11e-01

Pos logit contributions
emo+0.771
rito+0.647
 sailor+0.640
eer+0.627
Albert+0.622
Neg logit contributions
oph-0.380
cake-0.373
board-0.345
aw-0.342
cakes-0.338
Token O
Token ID440
Feature activation+7.05e+00

Pos logit contributions
cake+0.016
cakes+0.016
oph+0.016
board+0.015
ue+0.014
Neg logit contributions
emo-0.014
cker-0.012
 sailor-0.012
eer-0.012
fish-0.012
Tokenll
Token ID297
Feature activation+5.69e+00

Pos logit contributions
emo+0.488
 sailor+0.459
eer+0.455
rito+0.436
 crew+0.429
Neg logit contributions
oph-0.524
cake-0.484
cakes-0.479
ue-0.479
board-0.462
Tokenie
Token ID494
Feature activation+8.04e+00

Pos logit contributions
emo+0.396
 sailor+0.363
rito+0.361
Albert+0.348
 Albert+0.345
Neg logit contributions
oph-0.352
board-0.321
ue-0.318
cake-0.304
cakes-0.300
Token loved
Token ID6151
Feature activation+3.41e+00

Pos logit contributions
emo+0.726
rito+0.684
ancer+0.644
ba+0.634
 sailor+0.633
Neg logit contributions
board-0.376
aw-0.350
cake-0.343
That-0.337
cakes-0.327
Token to
Token ID284
Feature activation-3.27e-01

Pos logit contributions
emo+0.330
rito+0.300
ba+0.297
cker+0.292
eer+0.287
Neg logit contributions
cakes-0.149
cake-0.139
oph-0.132
 amusement-0.129
board-0.127
Token read
Token ID1100
Feature activation-2.36e+00

Pos logit contributions
 amusement+0.022
cakes+0.022
board+0.021
cake+0.021
 course+0.020
Neg logit contributions
emo-0.023
eer-0.019
rito-0.019
ba-0.019
ancer-0.019
Token.
Token ID13
Feature activation-2.32e-01

Pos logit contributions
oph+0.146
cake+0.144
cakes+0.143
board+0.130
 amusement+0.129
Neg logit contributions
emo-0.207
eer-0.172
ba-0.171
cker-0.170
 sailor-0.169
Token Every
Token ID3887
Feature activation-1.75e+00

Pos logit contributions
cake+0.011
oph+0.010
cakes+0.010
board+0.010
ue+0.009
Neg logit contributions
emo-0.022
cker-0.021
fish-0.020
 sailor-0.020
ba-0.019
Token the
Token ID262
Feature activation-2.40e-01

Pos logit contributions
emo+0.261
 sailor+0.208
rito+0.205
ba+0.203
eer+0.202
Neg logit contributions
cakes-0.287
oph-0.285
cake-0.281
board-0.263
aw-0.249
Token garden
Token ID11376
Feature activation-1.46e+00

Pos logit contributions
oph+0.017
cake+0.017
cakes+0.017
 amusement+0.015
board+0.015
Neg logit contributions
emo-0.019
 sailor-0.016
eer-0.016
cker-0.015
rito-0.015
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
oph+0.120
cake+0.110
cakes+0.110
 amusement+0.105
uct+0.103
Neg logit contributions
emo-0.094
 sailor-0.077
eer-0.077
fish-0.075
cker-0.074
Token L
Token ID406
Feature activation-4.49e-01

Pos logit contributions
oph+0.009
cake+0.009
cakes+0.009
board+0.008
 amusement+0.008
Neg logit contributions
emo-0.013
eer-0.011
 sailor-0.011
ba-0.011
rito-0.010
Tokenizz
Token ID6457
Feature activation+4.78e+00

Pos logit contributions
oph+0.036
cake+0.035
cakes+0.034
 amusement+0.033
board+0.032
Neg logit contributions
emo-0.032
ba-0.025
eer-0.024
rito-0.024
 sailor-0.024
Tokenie
Token ID494
Feature activation+8.09e+00

Pos logit contributions
emo+0.269
eer+0.201
ba+0.195
 sailor+0.193
cker+0.188
Neg logit contributions
oph-0.449
cake-0.441
cakes-0.433
 amusement-0.408
board-0.407
Token hugged
Token ID41130
Feature activation-6.41e-01

Pos logit contributions
emo+0.647
eer+0.527
 sailor+0.525
ba+0.523
cker+0.510
Neg logit contributions
oph-0.567
cake-0.548
cakes-0.534
 amusement-0.496
board-0.488
Token them
Token ID606
Feature activation+2.89e+00

Pos logit contributions
oph+0.037
cake+0.036
cakes+0.035
board+0.032
 amusement+0.031
Neg logit contributions
emo-0.059
eer-0.050
 sailor-0.049
ba-0.049
cker-0.048
Token and
Token ID290
Feature activation-3.53e-01

Pos logit contributions
emo+0.195
 sailor+0.169
ba+0.160
fish+0.156
 sail+0.156
Neg logit contributions
oph-0.219
cake-0.215
cakes-0.215
 amusement-0.201
board-0.199
Token thanked
Token ID26280
Feature activation-2.97e-01

Pos logit contributions
cake+0.025
oph+0.025
cakes+0.024
board+0.023
 amusement+0.022
Neg logit contributions
emo-0.027
 sailor-0.023
ba-0.022
fish-0.021
eer-0.021
Token them
Token ID606
Feature activation+2.88e+00

Pos logit contributions
oph+0.016
cake+0.015
cakes+0.014
board+0.013
 amusement+0.013
Neg logit contributions
emo-0.029
eer-0.025
cker-0.024
 sailor-0.024
rito-0.024
Token Quick
Token ID12029
Feature activation-3.75e+00

Pos logit contributions
emo+0.036
eer+0.029
rito+0.028
ba+0.028
 sailor+0.028
Neg logit contributions
oph-0.038
cake-0.038
cakes-0.037
board-0.035
 amusement-0.035
Token heard
Token ID2982
Feature activation-2.93e+00

Pos logit contributions
oph+0.253
cake+0.247
cakes+0.242
board+0.219
 amusement+0.219
Neg logit contributions
emo-0.308
eer-0.257
 sailor-0.251
ba-0.250
cker-0.247
Token some
Token ID617
Feature activation-5.01e+00

Pos logit contributions
oph+0.276
cake+0.257
cakes+0.248
uct+0.232
liv+0.231
Neg logit contributions
emo-0.164
eer-0.131
 sailor-0.129
ba-0.123
 sword-0.120
Token other
Token ID584
Feature activation-8.50e-01

Pos logit contributions
oph+0.426
cake+0.391
cakes+0.368
uct+0.353
liv+0.347
Neg logit contributions
emo-0.342
 sailor-0.290
eer-0.289
ba-0.277
cker-0.272
Token animals
Token ID4695
Feature activation+4.07e+00

Pos logit contributions
oph+0.068
cake+0.066
cakes+0.063
uct+0.060
liv+0.057
Neg logit contributions
emo-0.062
eer-0.055
 sailor-0.051
ba-0.050
cker-0.047
Token whist
Token ID32262
Feature activation+8.51e+00

Pos logit contributions
emo+0.312
eer+0.260
ba+0.257
 sailor+0.257
fish+0.251
Neg logit contributions
oph-0.303
cake-0.287
cakes-0.280
board-0.255
 amusement-0.251
Tokenling
Token ID1359
Feature activation+4.12e+00

Pos logit contributions
emo+0.479
eer+0.353
 sailor+0.349
rito+0.336
cker+0.333
Neg logit contributions
oph-0.797
cake-0.777
cakes-0.767
board-0.730
 amusement-0.715
Token.
Token ID13
Feature activation-4.81e-02

Pos logit contributions
emo+0.297
eer+0.252
ba+0.241
 sailor+0.240
cker+0.235
Neg logit contributions
oph-0.327
cake-0.309
cakes-0.301
board-0.276
ue-0.272
Token
Token ID198
Feature activation+1.99e+00

Pos logit contributions
oph+0.003
cake+0.003
cakes+0.003
 amusement+0.003
board+0.003
Neg logit contributions
emo-0.004
eer-0.003
 sailor-0.003
cker-0.003
ba-0.003
Token
Token ID198
Feature activation+2.00e+00

Pos logit contributions
emo+0.174
eer+0.152
 sailor+0.149
cker+0.145
rito+0.144
Neg logit contributions
oph-0.116
cake-0.115
cakes-0.112
ue-0.104
board-0.104
Token"
Token ID1
Feature activation-1.81e+00

Pos logit contributions
emo+0.161
cker+0.134
ba+0.132
eer+0.130
 sailor+0.129
Neg logit contributions
oph-0.144
cake-0.135
cakes-0.132
 amusement-0.120
board-0.119
Token confident
Token ID6563
Feature activation+3.27e-01

Pos logit contributions
oph+0.184
cake+0.177
 amusement+0.165
aw+0.163
cakes+0.162
Neg logit contributions
emo-0.206
eer-0.172
ba-0.169
cker-0.167
rito-0.161
Token.
Token ID13
Feature activation+4.16e-02

Pos logit contributions
emo+0.027
eer+0.023
 sailor+0.022
ba+0.022
cker+0.022
Neg logit contributions
oph-0.022
cake-0.021
cakes-0.021
board-0.019
 amusement-0.019
Token It
Token ID632
Feature activation+2.21e-01

Pos logit contributions
emo+0.004
ba+0.003
 sailor+0.003
eer+0.003
cker+0.003
Neg logit contributions
oph-0.002
cake-0.002
cakes-0.002
board-0.002
That-0.002
Token hugged
Token ID41130
Feature activation-3.09e-01

Pos logit contributions
emo+0.018
eer+0.015
 sailor+0.015
ba+0.015
cker+0.014
Neg logit contributions
oph-0.015
cake-0.015
cakes-0.014
board-0.013
 amusement-0.013
Token the
Token ID262
Feature activation-6.90e-02

Pos logit contributions
oph+0.023
cake+0.022
cakes+0.021
board+0.020
 amusement+0.020
Neg logit contributions
emo-0.024
eer-0.019
 sailor-0.019
ba-0.019
cker-0.019
Token pig
Token ID12967
Feature activation+8.11e+00

Pos logit contributions
oph+0.005
cake+0.005
cakes+0.004
board+0.004
 amusement+0.004
Neg logit contributions
emo-0.005
eer-0.004
ba-0.004
fish-0.004
rito-0.004
Token with
Token ID351
Feature activation-6.66e-01

Pos logit contributions
emo+0.716
eer+0.600
 sailor+0.590
ba+0.586
cker+0.579
Neg logit contributions
oph-0.498
cake-0.483
cakes-0.470
board-0.430
 amusement-0.422
Token a
Token ID257
Feature activation+4.15e-01

Pos logit contributions
oph+0.048
cake+0.047
cakes+0.047
board+0.043
 amusement+0.041
Neg logit contributions
emo-0.052
eer-0.042
 sailor-0.042
ba-0.041
cker-0.041
Token big
Token ID1263
Feature activation-8.34e-01

Pos logit contributions
emo+0.030
eer+0.025
ba+0.024
cker+0.023
 sailor+0.023
Neg logit contributions
oph-0.032
cake-0.031
cakes-0.030
board-0.028
 amusement-0.028
Token smile
Token ID8212
Feature activation+6.38e-01

Pos logit contributions
oph+0.066
cakes+0.064
cake+0.064
board+0.059
uct+0.057
Neg logit contributions
emo-0.058
 sailor-0.048
eer-0.047
cker-0.045
rito-0.044
Token and
Token ID290
Feature activation-1.01e-01

Pos logit contributions
emo+0.049
eer+0.041
 sailor+0.040
ba+0.040
cker+0.039
Neg logit contributions
oph-0.047
cakes-0.045
cake-0.044
 amusement-0.041
board-0.040
Token be
Token ID307
Feature activation+2.84e-02

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
 amusement+0.002
ue+0.002
Neg logit contributions
emo-0.002
eer-0.002
 sailor-0.002
ba-0.002
rito-0.002
Token alone
Token ID3436
Feature activation-1.02e-01

Pos logit contributions
emo+0.002
 sailor+0.002
ba+0.002
eer+0.002
ancer+0.002
Neg logit contributions
cake-0.002
cakes-0.002
oph-0.002
aw-0.002
 Meg-0.002
Token.
Token ID13
Feature activation+6.73e-01

Pos logit contributions
cake+0.006
oph+0.006
cakes+0.005
board+0.005
 amusement+0.005
Neg logit contributions
emo-0.009
eer-0.008
cker-0.008
rito-0.008
ba-0.008
Token
Token ID198
Feature activation+2.64e+00

Pos logit contributions
emo+0.064
fish+0.058
rito+0.056
ba+0.056
cker+0.056
Neg logit contributions
cake-0.032
oph-0.031
That-0.030
cakes-0.029
ue-0.029
Token
Token ID198
Feature activation+2.66e+00

Pos logit contributions
emo+0.235
eer+0.204
 sailor+0.202
ba+0.198
rito+0.198
Neg logit contributions
cake-0.148
oph-0.148
cakes-0.143
board-0.131
 amusement-0.130
TokenBee
Token ID49512
Feature activation+9.38e+00

Pos logit contributions
emo+0.256
eer+0.220
 sailor+0.215
ba+0.212
rito+0.212
Neg logit contributions
oph-0.143
cake-0.139
cakes-0.134
board-0.121
 amusement-0.119
Token decided
Token ID3066
Feature activation-3.34e+00

Pos logit contributions
emo+0.779
eer+0.650
 sailor+0.635
ba+0.634
cker+0.628
Neg logit contributions
oph-0.623
cake-0.607
cakes-0.594
board-0.541
 amusement-0.540
Token to
Token ID284
Feature activation+7.92e-03

Pos logit contributions
oph+0.232
cake+0.227
cakes+0.221
board+0.204
 amusement+0.202
Neg logit contributions
emo-0.269
eer-0.221
 sailor-0.216
ba-0.215
cker-0.212
Token leave
Token ID2666
Feature activation-8.92e-01

Pos logit contributions
emo+0.001
eer+0.000
 sailor+0.000
ba+0.000
cker+0.000
Neg logit contributions
oph-0.001
cake-0.001
cakes-0.001
board-0.001
 amusement-0.001
Token.
Token ID13
Feature activation+6.80e-01

Pos logit contributions
cake+0.046
oph+0.045
cakes+0.044
 Meg+0.042
board+0.041
Neg logit contributions
emo-0.083
ba-0.068
 sailor-0.067
eer-0.067
rito-0.067
Token He
Token ID679
Feature activation+2.00e+00

Pos logit contributions
emo+0.082
fish+0.072
ba+0.071
 sailor+0.071
cker+0.070
Neg logit contributions
cake-0.019
oph-0.017
cakes-0.016
board-0.016
 Meg-0.013
Token do
Token ID466
Feature activation-4.05e+00

Pos logit contributions
oph+0.050
cake+0.049
cakes+0.047
 amusement+0.044
board+0.044
Neg logit contributions
emo-0.052
eer-0.043
 sailor-0.042
ba-0.041
cker-0.041
Token what
Token ID644
Feature activation+7.03e-01

Pos logit contributions
oph+0.304
cake+0.296
cakes+0.290
board+0.270
 amusement+0.266
Neg logit contributions
emo-0.304
eer-0.246
 sailor-0.241
ba-0.239
cker-0.236
Token they
Token ID484
Feature activation+6.42e-01

Pos logit contributions
emo+0.069
rito+0.064
eer+0.063
ba+0.062
cker+0.061
Neg logit contributions
cakes-0.030
oph-0.030
cake-0.030
 Meg-0.027
ue-0.027
Token do
Token ID466
Feature activation-4.03e+00

Pos logit contributions
emo+0.055
eer+0.046
 sailor+0.045
rito+0.045
ba+0.044
Neg logit contributions
oph-0.041
cake-0.040
cakes-0.039
board-0.036
 amusement-0.035
Token.
Token ID13
Feature activation-9.76e-02

Pos logit contributions
oph+0.272
cake+0.264
cakes+0.258
board+0.237
 amusement+0.234
Neg logit contributions
emo-0.332
eer-0.274
 sailor-0.269
ba-0.267
cker-0.264
Token He
Token ID679
Feature activation+1.31e+00

Pos logit contributions
oph+0.007
cake+0.007
cakes+0.006
board+0.006
 amusement+0.006
Neg logit contributions
emo-0.008
eer-0.007
 sailor-0.006
ba-0.006
cker-0.006
Token feels
Token ID5300
Feature activation+5.52e-01

Pos logit contributions
emo+0.115
eer+0.097
rito+0.095
 sailor+0.095
ba+0.094
Neg logit contributions
oph-0.080
cake-0.078
cakes-0.076
board-0.071
 amusement-0.069
Token happy
Token ID3772
Feature activation+1.38e+00

Pos logit contributions
emo+0.047
cker+0.042
eer+0.042
ba+0.042
rito+0.040
Neg logit contributions
cake-0.030
oph-0.029
 amusement-0.029
aw-0.029
That-0.029
Token.
Token ID13
Feature activation-3.66e-02

Pos logit contributions
emo+0.118
eer+0.098
 sailor+0.097
ba+0.095
fish+0.095
Neg logit contributions
oph-0.092
cake-0.087
cakes-0.086
 amusement-0.077
board-0.077
Token He
Token ID679
Feature activation+1.34e+00

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
board+0.002
ue+0.002
Neg logit contributions
emo-0.003
eer-0.003
 sailor-0.003
cker-0.003
ba-0.003
Token says
Token ID1139
Feature activation-1.93e+00

Pos logit contributions
emo+0.112
eer+0.094
rito+0.092
ba+0.092
cker+0.091
Neg logit contributions
oph-0.088
cake-0.085
cakes-0.082
board-0.078
 amusement-0.076
Token a
Token ID257
Feature activation+3.14e-01

Pos logit contributions
emo+0.043
eer+0.036
ba+0.035
 sailor+0.035
cker+0.034
Neg logit contributions
oph-0.033
cake-0.032
cakes-0.032
board-0.029
 amusement-0.029
Token giant
Token ID6175
Feature activation-2.87e+00

Pos logit contributions
emo+0.024
eer+0.020
ba+0.019
rito+0.019
cker+0.019
Neg logit contributions
oph-0.023
cake-0.023
cakes-0.022
 amusement-0.020
board-0.020
Token feast
Token ID26951
Feature activation-1.47e+00

Pos logit contributions
oph+0.213
cake+0.203
cakes+0.200
uct+0.183
board+0.182
Neg logit contributions
emo-0.213
 sailor-0.179
eer-0.177
fish-0.172
cker-0.171
Token.
Token ID13
Feature activation+8.34e-02

Pos logit contributions
oph+0.108
cake+0.100
cakes+0.098
uct+0.096
 amusement+0.096
Neg logit contributions
emo-0.104
fish-0.091
 sailor-0.088
eer-0.087
cker-0.083
Token
Token ID198
Feature activation+2.21e+00

Pos logit contributions
emo+0.007
eer+0.006
 sailor+0.006
ba+0.006
rito+0.006
Neg logit contributions
oph-0.005
cake-0.005
cakes-0.005
 amusement-0.005
board-0.005
Token
Token ID198
Feature activation+2.23e+00

Pos logit contributions
emo+0.176
eer+0.145
 sailor+0.142
ba+0.141
cker+0.139
Neg logit contributions
oph-0.156
cake-0.152
cakes-0.148
board-0.137
 amusement-0.135
TokenThey
Token ID2990
Feature activation-2.73e+00

Pos logit contributions
emo+0.182
ba+0.153
 sailor+0.145
Ar+0.145
Albert+0.142
Neg logit contributions
oph-0.150
cake-0.141
cakes-0.138
board-0.133
uct-0.124
Token jumped
Token ID11687
Feature activation-3.60e-01

Pos logit contributions
oph+0.174
cake+0.170
cakes+0.166
board+0.152
 amusement+0.149
Neg logit contributions
emo-0.234
eer-0.196
 sailor-0.194
ba-0.192
cker-0.189
Token and
Token ID290
Feature activation-1.56e-01

Pos logit contributions
oph+0.029
cake+0.027
cakes+0.026
 amusement+0.025
board+0.025
Neg logit contributions
emo-0.026
 sailor-0.021
eer-0.020
ba-0.020
fish-0.020
Token cl
Token ID537
Feature activation-1.83e+00

Pos logit contributions
oph+0.010
cake+0.010
cakes+0.009
board+0.009
 amusement+0.008
Neg logit contributions
emo-0.013
eer-0.011
 sailor-0.011
ba-0.011
cker-0.011
Tokenapped
Token ID6320
Feature activation-6.44e-01

Pos logit contributions
oph+0.113
cake+0.109
cakes+0.106
board+0.097
 amusement+0.096
Neg logit contributions
emo-0.164
eer-0.136
 sailor-0.134
ba-0.132
rito-0.131
Token Todd
Token ID14377
Feature activation+5.33e+00

Pos logit contributions
emo+0.115
eer+0.095
 sailor+0.092
ba+0.092
cker+0.092
Neg logit contributions
oph-0.095
cake-0.092
cakes-0.090
board-0.083
 amusement-0.082
Token put
Token ID1234
Feature activation+3.26e+00

Pos logit contributions
emo+0.482
eer+0.398
rito+0.392
 sailor+0.384
cker+0.382
Neg logit contributions
oph-0.322
cake-0.302
cakes-0.288
board-0.276
aw-0.261
Token the
Token ID262
Feature activation-1.61e-01

Pos logit contributions
emo+0.293
cker+0.245
eer+0.241
ba+0.236
 sailor+0.232
Neg logit contributions
oph-0.191
cake-0.191
cakes-0.190
board-0.174
aw-0.170
Token coin
Token ID10752
Feature activation+7.99e+00

Pos logit contributions
cake+0.011
oph+0.011
cakes+0.011
board+0.010
 amusement+0.010
Neg logit contributions
emo-0.013
eer-0.010
ba-0.010
cker-0.010
rito-0.010
Token in
Token ID287
Feature activation+3.66e+00

Pos logit contributions
emo+0.669
eer+0.545
 sailor+0.524
ba+0.517
rito+0.515
Neg logit contributions
cake-0.523
cakes-0.508
oph-0.499
board-0.477
aw-0.439
Token his
Token ID465
Feature activation+2.98e+00

Pos logit contributions
emo+0.239
eer+0.187
 sailor+0.183
ba+0.180
cker+0.177
Neg logit contributions
oph-0.311
cake-0.304
cakes-0.299
board-0.280
 amusement-0.275
Token pocket
Token ID10000
Feature activation+1.40e+00

Pos logit contributions
emo+0.267
ba+0.228
eer+0.215
rito+0.211
fish+0.209
Neg logit contributions
oph-0.176
cake-0.173
board-0.168
cakes-0.168
 amusement-0.165
Token and
Token ID290
Feature activation-3.39e-01

Pos logit contributions
emo+0.120
eer+0.100
 sailor+0.098
ba+0.097
cker+0.096
Neg logit contributions
oph-0.090
cake-0.087
cakes-0.085
board-0.077
 amusement-0.077
Token they
Token ID484
Feature activation+6.24e-01

Pos logit contributions
oph+0.022
cake+0.021
cakes+0.021
board+0.019
 amusement+0.019
Neg logit contributions
emo-0.029
eer-0.024
rito-0.023
cker-0.023
ba-0.023
Token walked
Token ID6807
Feature activation+1.16e+00

Pos logit contributions
emo+0.054
eer+0.046
 sailor+0.045
ba+0.044
cker+0.044
Neg logit contributions
oph-0.039
cake-0.038
cakes-0.037
board-0.034
 amusement-0.033
Token away
Token ID1497
Feature activation-1.50e+00

Pos logit contributions
emo+0.082
 sailor+0.067
eer+0.065
ba+0.064
 sail+0.062
Neg logit contributions
oph-0.093
cake-0.091
cakes-0.089
board-0.082
uct-0.080
Token because
Token ID780
Feature activation-8.70e-01

Pos logit contributions
emo+0.171
 sailor+0.140
eer+0.138
fish+0.136
ba+0.136
Neg logit contributions
oph-0.183
cake-0.171
cakes-0.170
 amusement-0.157
board-0.156
Token he
Token ID339
Feature activation+2.29e+00

Pos logit contributions
oph+0.080
cake+0.077
cakes+0.075
board+0.071
 amusement+0.070
Neg logit contributions
emo-0.051
eer-0.039
 sailor-0.039
ba-0.036
fish-0.036
Token was
Token ID373
Feature activation-8.67e-01

Pos logit contributions
emo+0.203
 sailor+0.172
rito+0.168
eer+0.168
cker+0.165
Neg logit contributions
oph-0.138
cake-0.134
cakes-0.129
board-0.124
ue-0.113
Token too
Token ID1165
Feature activation-2.36e+00

Pos logit contributions
cake+0.048
oph+0.047
cakes+0.045
 amusement+0.043
uct+0.043
Neg logit contributions
emo-0.077
fish-0.066
eer-0.065
cker-0.065
ba-0.065
Token boss
Token ID6478
Feature activation-1.78e-01

Pos logit contributions
oph+0.154
cake+0.153
cakes+0.143
aw+0.134
 amusement+0.132
Neg logit contributions
emo-0.181
eer-0.156
rito-0.154
ba-0.152
fish-0.150
Tokeny
Token ID88
Feature activation+2.01e+00

Pos logit contributions
oph+0.014
cake+0.014
cakes+0.014
 amusement+0.013
board+0.012
Neg logit contributions
emo-0.013
eer-0.010
ba-0.010
 sailor-0.010
cker-0.010
Token.
Token ID13
Feature activation-2.72e-01

Pos logit contributions
emo+0.149
eer+0.124
 sailor+0.118
ba+0.118
cker+0.115
Neg logit contributions
oph-0.153
cake-0.147
cakes-0.145
 amusement-0.133
board-0.131
Token At
Token ID1629
Feature activation+1.16e+00

Pos logit contributions
oph+0.022
cake+0.021
cakes+0.020
 amusement+0.019
liv+0.018
Neg logit contributions
emo-0.018
eer-0.014
 sailor-0.013
 Albert-0.013
 crew-0.013
Token the
Token ID262
Feature activation-2.74e-01

Pos logit contributions
emo+0.087
 sailor+0.073
ba+0.070
eer+0.069
cker+0.068
Neg logit contributions
cake-0.086
oph-0.086
cakes-0.085
board-0.079
aw-0.074
Token end
Token ID886
Feature activation-5.12e+00

Pos logit contributions
cakes+0.023
cake+0.022
oph+0.022
uct+0.021
aw+0.020
Neg logit contributions
 sailor-0.014
 sail-0.014
emo-0.014
 own-0.014
 sword-0.013
Token of
Token ID286
Feature activation-2.69e+00

Pos logit contributions
oph+0.338
cake+0.308
cakes+0.292
uct+0.287
 amusement+0.276
Neg logit contributions
emo-0.446
 sailor-0.363
eer-0.359
fish-0.351
ba-0.350
Token both
Token ID1111
Feature activation-2.72e+00

Pos logit contributions
emo+0.243
eer+0.204
rito+0.196
cker+0.193
 sailor+0.192
Neg logit contributions
oph-0.207
cake-0.204
cakes-0.198
board-0.184
 amusement-0.184
Token have
Token ID423
Feature activation+1.91e-01

Pos logit contributions
oph+0.202
cake+0.197
cakes+0.192
board+0.180
 amusement+0.178
Neg logit contributions
emo-0.206
eer-0.167
 sailor-0.163
ba-0.162
rito-0.160
Token a
Token ID257
Feature activation+1.82e-02

Pos logit contributions
emo+0.017
eer+0.015
ba+0.014
cker+0.014
 sailor+0.014
Neg logit contributions
oph-0.011
cake-0.011
cakes-0.011
 amusement-0.010
board-0.010
Token new
Token ID649
Feature activation+3.35e+00

Pos logit contributions
emo+0.002
eer+0.001
cker+0.001
ba+0.001
rito+0.001
Neg logit contributions
oph-0.001
cake-0.001
 amusement-0.001
cakes-0.001
board-0.001
Token shirt
Token ID10147
Feature activation-4.32e+00

Pos logit contributions
emo+0.307
eer+0.261
ba+0.254
cker+0.252
rito+0.252
Neg logit contributions
oph-0.197
cake-0.188
cakes-0.181
board-0.170
 amusement-0.169
Token."
Token ID526
Feature activation+3.94e+00

Pos logit contributions
oph+0.362
cake+0.338
cakes+0.333
 amusement+0.321
uct+0.317
Neg logit contributions
emo-0.288
eer-0.231
 sailor-0.226
ba-0.224
fish-0.219
Token
Token ID198
Feature activation+2.03e+00

Pos logit contributions
emo+0.316
eer+0.258
 sailor+0.255
ba+0.251
cker+0.247
Neg logit contributions
oph-0.276
cake-0.269
cakes-0.263
board-0.243
 amusement-0.240
Token
Token ID198
Feature activation+2.04e+00

Pos logit contributions
emo+0.180
eer+0.162
cker+0.158
rito+0.157
 sailor+0.155
Neg logit contributions
oph-0.116
cake-0.109
cakes-0.104
ue-0.101
That-0.098
TokenBen
Token ID11696
Feature activation-2.00e+00

Pos logit contributions
emo+0.182
 sailor+0.152
ba+0.152
fish+0.149
eer+0.146
Neg logit contributions
oph-0.127
cake-0.126
cakes-0.125
board-0.111
 amusement-0.107
Token shakes
Token ID29959
Feature activation+2.01e-01

Pos logit contributions
oph+0.149
cake+0.147
cakes+0.146
liv+0.131
 amusement+0.131
Neg logit contributions
emo-0.141
 sailor-0.119
eer-0.118
fish-0.113
ba-0.108
Token his
Token ID465
Feature activation+2.90e+00

Pos logit contributions
emo+0.009
eer+0.006
 sailor+0.006
ba+0.006
cker+0.005
Neg logit contributions
oph-0.022
cake-0.021
cakes-0.021
board-0.020
 amusement-0.019
Token.
Token ID13
Feature activation+2.55e-01

Pos logit contributions
oph+0.044
cake+0.041
cakes+0.040
uct+0.037
 amusement+0.037
Neg logit contributions
emo-0.038
eer-0.032
 sailor-0.031
ba-0.030
fish-0.030
Token But
Token ID887
Feature activation+2.96e+00

Pos logit contributions
emo+0.018
eer+0.013
 sailor+0.012
 crew+0.012
 Albert+0.012
Neg logit contributions
oph-0.021
cake-0.020
cakes-0.019
board-0.018
 amusement-0.018
Token when
Token ID618
Feature activation+1.37e+00

Pos logit contributions
emo+0.235
 sailor+0.195
eer+0.187
ba+0.187
cker+0.185
Neg logit contributions
oph-0.211
cake-0.203
cakes-0.195
board-0.184
uct-0.170
Token they
Token ID484
Feature activation+1.14e+00

Pos logit contributions
emo+0.097
 sailor+0.078
eer+0.075
ba+0.075
fish+0.073
Neg logit contributions
oph-0.108
cake-0.106
cakes-0.102
board-0.097
 amusement-0.093
Token looked
Token ID3114
Feature activation+1.70e+00

Pos logit contributions
emo+0.081
ba+0.070
fish+0.068
 sailor+0.068
eer+0.064
Neg logit contributions
cakes-0.083
cake-0.083
oph-0.082
 amusement-0.074
oga-0.073
Token at
Token ID379
Feature activation-3.57e+00

Pos logit contributions
emo+0.145
eer+0.120
 sailor+0.120
ba+0.117
fish+0.116
Neg logit contributions
oph-0.110
cake-0.107
cakes-0.104
board-0.095
 amusement-0.093
Token their
Token ID511
Feature activation+7.36e-01

Pos logit contributions
oph+0.220
cake+0.213
cakes+0.208
board+0.190
 amusement+0.188
Neg logit contributions
emo-0.314
eer-0.263
 sailor-0.259
ba-0.258
cker-0.255
Token patch
Token ID8529
Feature activation-2.41e+00

Pos logit contributions
emo+0.054
eer+0.043
 sailor+0.043
cker+0.042
fish+0.042
Neg logit contributions
oph-0.057
cake-0.056
cakes-0.054
board-0.050
uct-0.049
Token,
Token ID11
Feature activation+8.19e-01

Pos logit contributions
oph+0.172
cake+0.162
cakes+0.157
 amusement+0.150
uct+0.146
Neg logit contributions
emo-0.190
eer-0.155
 sailor-0.153
fish-0.153
ba-0.151
Token they
Token ID484
Feature activation+1.17e+00

Pos logit contributions
emo+0.062
eer+0.050
 sailor+0.050
ba+0.049
cker+0.048
Neg logit contributions
oph-0.061
cake-0.059
cakes-0.057
board-0.053
 amusement-0.052
Token saw
Token ID2497
Feature activation-3.35e-01

Pos logit contributions
emo+0.092
 sailor+0.076
ba+0.075
eer+0.075
fish+0.074
Neg logit contributions
oph-0.083
cake-0.081
cakes-0.079
board-0.072
 amusement-0.071
Token.
Token ID13
Feature activation+4.26e-01

Pos logit contributions
oph+0.328
cake+0.320
cakes+0.313
board+0.290
 amusement+0.287
Neg logit contributions
emo-0.337
eer-0.273
 sailor-0.268
ba-0.265
cker-0.262
Token I
Token ID314
Feature activation+1.23e+00

Pos logit contributions
emo+0.036
eer+0.030
ba+0.029
 sailor+0.029
cker+0.029
Neg logit contributions
oph-0.028
cake-0.027
cakes-0.027
board-0.025
 amusement-0.024
Token will
Token ID481
Feature activation+1.98e+00

Pos logit contributions
emo+0.089
eer+0.072
 sailor+0.071
ba+0.069
cker+0.069
Neg logit contributions
oph-0.094
cake-0.094
cakes-0.090
board-0.085
 amusement-0.084
Token use
Token ID779
Feature activation+4.56e+00

Pos logit contributions
emo+0.143
eer+0.113
 sailor+0.113
ba+0.111
cker+0.110
Neg logit contributions
oph-0.155
cake-0.151
cakes-0.149
board-0.138
 amusement-0.135
Token my
Token ID616
Feature activation+2.28e+00

Pos logit contributions
emo+0.336
eer+0.270
 sailor+0.267
ba+0.261
cker+0.257
Neg logit contributions
oph-0.347
cake-0.339
cakes-0.331
board-0.308
 amusement-0.301
Token papers
Token ID9473
Feature activation-1.98e+00

Pos logit contributions
emo+0.207
ba+0.174
eer+0.173
rito+0.168
 sailor+0.168
Neg logit contributions
oph-0.133
cake-0.131
cakes-0.128
board-0.122
 amusement-0.116
Token.
Token ID13
Feature activation+4.65e-01

Pos logit contributions
oph+0.148
cake+0.139
cakes+0.138
 amusement+0.129
board+0.126
Neg logit contributions
emo-0.148
eer-0.121
 sailor-0.119
ba-0.118
rito-0.116
Token I
Token ID314
Feature activation+1.28e+00

Pos logit contributions
emo+0.039
eer+0.032
 sailor+0.032
ba+0.032
cker+0.031
Neg logit contributions
oph-0.031
cake-0.030
cakes-0.029
board-0.027
 amusement-0.026
Token will
Token ID481
Feature activation+2.03e+00

Pos logit contributions
emo+0.095
eer+0.077
 sailor+0.076
cker+0.073
ba+0.073
Neg logit contributions
cake-0.095
oph-0.094
cakes-0.091
board-0.087
 amusement-0.084
Token ask
Token ID1265
Feature activation+5.88e+00

Pos logit contributions
emo+0.146
 sailor+0.115
eer+0.115
ba+0.113
cker+0.112
Neg logit contributions
oph-0.159
cake-0.154
cakes-0.153
board-0.142
 amusement-0.138
Token and
Token ID290
Feature activation+1.42e-01

Pos logit contributions
emo+0.507
eer+0.425
cker+0.414
 sailor+0.413
rito+0.412
Neg logit contributions
oph-0.373
cake-0.364
cakes-0.355
board-0.325
 amusement-0.320
Token plays
Token ID5341
Feature activation+9.70e-01

Pos logit contributions
oph+0.033
cake+0.032
cakes+0.031
board+0.029
 amusement+0.028
Neg logit contributions
emo-0.044
eer-0.037
rito-0.036
 sailor-0.035
cker-0.035
Token.
Token ID13
Feature activation+2.04e-01

Pos logit contributions
emo+0.071
 sailor+0.058
eer+0.058
ba+0.057
fish+0.057
Neg logit contributions
oph-0.074
cake-0.069
cakes-0.068
 amusement-0.063
board-0.063
Token She
Token ID1375
Feature activation-2.92e+00

Pos logit contributions
emo+0.022
eer+0.020
 sailor+0.019
cker+0.019
ba+0.019
Neg logit contributions
oph-0.008
cake-0.008
cakes-0.007
board-0.006
 amusement-0.006
Token sings
Token ID33041
Feature activation+5.44e+00

Pos logit contributions
oph+0.188
cake+0.183
cakes+0.177
board+0.165
 amusement+0.163
Neg logit contributions
emo-0.250
eer-0.205
rito-0.202
ba-0.200
 sailor-0.199
Token loud
Token ID7812
Feature activation-4.05e+00

Pos logit contributions
emo+0.417
 sailor+0.344
eer+0.343
ba+0.341
fish+0.326
Neg logit contributions
oph-0.392
cake-0.372
cakes-0.365
 amusement-0.346
board-0.344
Token and
Token ID290
Feature activation-7.52e-02

Pos logit contributions
oph+0.265
cake+0.256
cakes+0.250
board+0.228
 amusement+0.226
Neg logit contributions
emo-0.339
eer-0.288
 sailor-0.280
ba-0.277
rito-0.271
Token happy
Token ID3772
Feature activation+1.34e+00

Pos logit contributions
oph+0.006
cake+0.006
cakes+0.005
board+0.005
 amusement+0.005
Neg logit contributions
emo-0.006
eer-0.004
 sailor-0.004
ba-0.004
cker-0.004
Token.
Token ID13
Feature activation+1.55e-01

Pos logit contributions
emo+0.103
eer+0.086
 sailor+0.084
ba+0.083
fish+0.081
Neg logit contributions
oph-0.098
cake-0.094
cakes-0.092
 amusement-0.085
board-0.085
Token She
Token ID1375
Feature activation-2.98e+00

Pos logit contributions
emo+0.016
cker+0.014
eer+0.014
fish+0.014
rito+0.014
Neg logit contributions
oph-0.007
cake-0.006
cakes-0.006
board-0.005
 Rebecca-0.005
Token makes
Token ID1838
Feature activation+4.02e-01

Pos logit contributions
oph+0.210
cake+0.204
cakes+0.199
board+0.185
 amusement+0.183
Neg logit contributions
emo-0.238
eer-0.194
 sailor-0.190
ba-0.188
cker-0.187
Token up
Token ID510
Feature activation+1.39e+00

Pos logit contributions
emo+0.035
eer+0.029
 sailor+0.029
ba+0.028
cker+0.028
Neg logit contributions
oph-0.025
cake-0.025
cakes-0.024
board-0.022
 amusement-0.022
Token world
Token ID995
Feature activation-1.63e-01

Pos logit contributions
oph+0.012
cake+0.011
 amusement+0.011
cakes+0.011
board+0.011
Neg logit contributions
emo-0.013
rito-0.011
eer-0.010
cker-0.010
ba-0.010
Token,
Token ID11
Feature activation+7.72e-01

Pos logit contributions
oph+0.012
cake+0.011
cakes+0.011
 amusement+0.010
uct+0.010
Neg logit contributions
emo-0.012
eer-0.010
 sailor-0.010
fish-0.010
ba-0.010
Token and
Token ID290
Feature activation-3.14e-02

Pos logit contributions
emo+0.063
eer+0.052
 sailor+0.052
ba+0.051
cker+0.050
Neg logit contributions
oph-0.053
cake-0.051
cakes-0.050
board-0.046
 amusement-0.045
Token she
Token ID673
Feature activation-4.63e-01

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
board+0.002
 amusement+0.002
Neg logit contributions
emo-0.003
 sailor-0.002
eer-0.002
ba-0.002
fish-0.002
Token wanted
Token ID2227
Feature activation-1.18e-01

Pos logit contributions
oph+0.025
cake+0.024
cakes+0.024
board+0.023
 amusement+0.022
Neg logit contributions
emo-0.041
rito-0.036
eer-0.035
cker-0.034
 sailor-0.032
Token the
Token ID262
Feature activation-1.12e-01

Pos logit contributions
oph+0.008
cake+0.008
cakes+0.008
board+0.007
 amusement+0.007
Neg logit contributions
emo-0.010
eer-0.008
 sailor-0.008
ba-0.008
cker-0.008
Token mer
Token ID4017
Feature activation+2.89e+00

Pos logit contributions
oph+0.008
 amusement+0.008
cake+0.008
board+0.007
cakes+0.007
Neg logit contributions
emo-0.008
cker-0.007
rito-0.007
eer-0.007
ba-0.006
Tokenmaid
Token ID23151
Feature activation+9.62e+00

Pos logit contributions
emo+0.138
eer+0.108
cker+0.107
 exc+0.106
rito+0.104
Neg logit contributions
oph-0.284
cake-0.269
cakes-0.263
board-0.253
ue-0.235
Token to
Token ID284
Feature activation-2.64e-02

Pos logit contributions
emo+0.863
eer+0.709
 sailor+0.696
cker+0.696
rito+0.691
Neg logit contributions
cake-0.577
oph-0.571
cakes-0.562
board-0.497
 amusement-0.481
Token come
Token ID1282
Feature activation+1.23e-01

Pos logit contributions
oph+0.002
cake+0.002
 amusement+0.002
cakes+0.002
board+0.002
Neg logit contributions
emo-0.002
eer-0.002
cker-0.002
rito-0.002
ba-0.002
Token too
Token ID1165
Feature activation-1.80e+00

Pos logit contributions
emo+0.012
eer+0.011
rito+0.010
cker+0.010
eers+0.010
Neg logit contributions
oph-0.005
cake-0.005
 amusement-0.005
cakes-0.005
 Meg-0.004
Token quickly
Token ID2952
Feature activation-2.08e+00

Pos logit contributions
emo+0.131
rito+0.113
eer+0.112
ancer+0.107
 sailor+0.105
Neg logit contributions
oph-0.072
cake-0.064
aw-0.061
cakes-0.061
board-0.060
Token flew
Token ID13112
Feature activation+3.59e+00

Pos logit contributions
oph+0.133
cake+0.125
cakes+0.121
board+0.116
aw+0.112
Neg logit contributions
emo-0.180
eer-0.149
 sailor-0.145
ba-0.145
rito-0.144
Token down
Token ID866
Feature activation-6.17e-02

Pos logit contributions
emo+0.264
ba+0.215
eer+0.210
 sailor+0.210
rito+0.206
Neg logit contributions
oph-0.277
cake-0.266
cakes-0.263
board-0.245
 amusement-0.244
Token to
Token ID284
Feature activation-4.08e-01

Pos logit contributions
oph+0.005
cake+0.004
cakes+0.004
 amusement+0.004
board+0.004
Neg logit contributions
emo-0.005
 sailor-0.004
eer-0.004
ba-0.004
fish-0.004
Token see
Token ID766
Feature activation+1.58e+00

Pos logit contributions
oph+0.024
cake+0.023
 amusement+0.022
cakes+0.022
board+0.020
Neg logit contributions
emo-0.037
eer-0.031
cker-0.030
fish-0.030
ba-0.030
Token what
Token ID644
Feature activation+8.96e-01

Pos logit contributions
emo+0.151
cker+0.127
eer+0.124
rito+0.123
ba+0.121
Neg logit contributions
cake-0.083
cakes-0.081
oph-0.081
 amusement-0.076
aw-0.074
Token it
Token ID340
Feature activation+2.00e+00

Pos logit contributions
emo+0.078
ba+0.065
cker+0.065
eer+0.065
rito+0.065
Neg logit contributions
cake-0.056
oph-0.056
cakes-0.055
board-0.049
 amusement-0.047
Token could
Token ID714
Feature activation+3.78e+00

Pos logit contributions
emo+0.189
 sailor+0.160
eer+0.159
rito+0.154
cker+0.154
Neg logit contributions
oph-0.110
cake-0.109
cakes-0.108
board-0.097
ue-0.089
Token be
Token ID307
Feature activation-3.90e-01

Pos logit contributions
emo+0.303
eer+0.250
 sailor+0.246
ba+0.242
rito+0.238
Neg logit contributions
oph-0.260
cake-0.258
cakes-0.250
board-0.233
 amusement-0.227
Token.
Token ID13
Feature activation-8.52e-02

Pos logit contributions
cake+0.022
cakes+0.021
oph+0.021
aw+0.019
board+0.019
Neg logit contributions
emo-0.035
 sailor-0.030
Albert-0.029
eer-0.029
ba-0.029
Token As
Token ID1081
Feature activation+6.49e-01

Pos logit contributions
cake+0.005
cakes+0.005
oph+0.004
board+0.004
That+0.004
Neg logit contributions
emo-0.008
ba-0.007
fish-0.007
cker-0.007
 sailor-0.007
Token were
Token ID547
Feature activation-2.82e+00

Pos logit contributions
emo+0.123
eer+0.105
 sailor+0.103
rito+0.102
cker+0.102
Neg logit contributions
oph-0.086
cake-0.083
cakes-0.080
board-0.075
 amusement-0.073
Token two
Token ID734
Feature activation-3.88e+00

Pos logit contributions
oph+0.183
cake+0.182
cakes+0.177
board+0.166
 amusement+0.158
Neg logit contributions
emo-0.238
 sailor-0.194
eer-0.193
ba-0.190
cker-0.183
Token best
Token ID1266
Feature activation+2.13e+00

Pos logit contributions
oph+0.348
cake+0.344
cakes+0.334
board+0.316
 amusement+0.310
Neg logit contributions
emo-0.231
eer-0.179
 sailor-0.175
ba-0.170
cker-0.168
Token friends
Token ID2460
Feature activation+1.92e+00

Pos logit contributions
emo+0.142
ba+0.110
eer+0.110
rito+0.109
cker+0.107
Neg logit contributions
oph-0.174
cakes-0.172
cake-0.170
board-0.161
 amusement-0.158
Token,
Token ID11
Feature activation+6.00e-01

Pos logit contributions
emo+0.124
eer+0.102
 sailor+0.098
cker+0.097
ba+0.096
Neg logit contributions
oph-0.165
cake-0.163
cakes-0.160
board-0.145
uct-0.143
Token Sarah
Token ID10490
Feature activation-6.60e+00

Pos logit contributions
emo+0.056
eer+0.047
 sailor+0.047
ba+0.046
cker+0.046
Neg logit contributions
oph-0.034
cake-0.033
cakes-0.032
board-0.029
 amusement-0.029
Token and
Token ID290
Feature activation-2.93e-01

Pos logit contributions
oph+0.441
cake+0.432
cakes+0.430
 amusement+0.388
board+0.384
Neg logit contributions
emo-0.542
eer-0.464
cker-0.448
 sailor-0.447
ba-0.438
Token Th
Token ID536
Feature activation+2.68e+00

Pos logit contributions
oph+0.015
cake+0.014
cakes+0.014
board+0.012
 amusement+0.012
Neg logit contributions
emo-0.029
eer-0.025
 sailor-0.024
rito-0.024
ba-0.024
Tokenalia
Token ID9752
Feature activation+6.38e-01

Pos logit contributions
emo+0.202
eer+0.161
ba+0.160
cker+0.155
 sailor+0.153
Neg logit contributions
cake-0.199
oph-0.198
cakes-0.196
 amusement-0.181
board-0.179
Token.
Token ID13
Feature activation+9.27e-03

Pos logit contributions
emo+0.050
eer+0.041
 sailor+0.040
ba+0.039
cker+0.039
Neg logit contributions
oph-0.046
cake-0.045
cakes-0.044
board-0.040
 amusement-0.040
Token They
Token ID1119
Feature activation-4.92e-01

Pos logit contributions
emo+0.001
eer+0.000
cker+0.000
gy+0.000
 common+0.000
Neg logit contributions
cake-0.001
cakes-0.001
aw-0.001
oph-0.001
board-0.001
Token all
Token ID477
Feature activation-6.16e+00

Pos logit contributions
oph+0.038
cake+0.038
cakes+0.036
board+0.034
ue+0.034
Neg logit contributions
emo-0.042
 sailor-0.036
ba-0.034
eer-0.034
 crew-0.034
Token three
Token ID1115
Feature activation-1.57e-01

Pos logit contributions
oph+0.440
cake+0.427
cakes+0.415
board+0.385
 amusement+0.377
Neg logit contributions
emo-0.479
eer-0.412
 sailor-0.398
cker-0.387
ba-0.384
Token went
Token ID1816
Feature activation-2.41e-02

Pos logit contributions
oph+0.010
cake+0.010
cakes+0.010
board+0.009
 amusement+0.009
Neg logit contributions
emo-0.013
eer-0.011
 sailor-0.011
ba-0.011
cker-0.011
Token to
Token ID284
Feature activation-3.88e-01

Pos logit contributions
oph+0.002
cake+0.002
cakes+0.002
board+0.002
 amusement+0.002
Neg logit contributions
emo-0.002
 sailor-0.001
eer-0.001
ba-0.001
rito-0.001
Token the
Token ID262
Feature activation-9.45e-01

Pos logit contributions
oph+0.028
cake+0.028
cakes+0.027
board+0.025
aw+0.024
Neg logit contributions
emo-0.030
 sailor-0.025
eer-0.024
ba-0.024
cker-0.023
Token party
Token ID2151
Feature activation-7.33e+00

Pos logit contributions
oph+0.061
cake+0.059
liv+0.056
cakes+0.056
uct+0.055
Neg logit contributions
emo-0.071
 sailor-0.067
 crew-0.065
 sail-0.064
fish-0.059
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
oph+0.635
uct+0.601
cake+0.597
liv+0.587
That+0.585
Neg logit contributions
emo-0.356
 sailor-0.315
 crew-0.298
ba-0.287
fish-0.285
Token They
Token ID1119
Feature activation-5.64e-01

Pos logit contributions
oph+0.007
cake+0.007
cakes+0.007
 amusement+0.006
aw+0.006
Neg logit contributions
emo-0.008
 sailor-0.006
 Albert-0.006
eer-0.006
ba-0.006
Token had
Token ID550
Feature activation-1.60e+00

Pos logit contributions
oph+0.039
cake+0.039
cakes+0.037
board+0.035
 amusement+0.034
Neg logit contributions
emo-0.044
 sailor-0.037
ba-0.037
eer-0.036
fish-0.035
Token a
Token ID257
Feature activation+1.32e-01

Pos logit contributions
oph+0.116
cake+0.116
cakes+0.111
board+0.108
ue+0.104
Neg logit contributions
emo-0.117
 sailor-0.096
eer-0.095
ba-0.092
 crew-0.091
Token wonderful
Token ID7932
Feature activation-4.33e-02

Pos logit contributions
emo+0.009
 sailor+0.007
eer+0.007
ba+0.007
fish+0.007
Neg logit contributions
oph-0.010
cake-0.010
cakes-0.010
board-0.009
uct-0.009
Token could
Token ID714
Feature activation+4.11e+00

Pos logit contributions
emo+0.377
eer+0.305
 sailor+0.299
ba+0.295
cker+0.291
Neg logit contributions
oph-0.393
cake-0.383
cakes-0.374
board-0.348
 amusement-0.345
Token get
Token ID651
Feature activation+8.70e-01

Pos logit contributions
emo+0.327
eer+0.268
 sailor+0.260
ba+0.258
rito+0.257
Neg logit contributions
oph-0.287
cake-0.283
cakes-0.276
 amusement-0.254
board-0.254
Token to
Token ID284
Feature activation+7.50e-03

Pos logit contributions
emo+0.071
eer+0.059
 sailor+0.057
rito+0.057
cker+0.057
Neg logit contributions
oph-0.058
cake-0.058
cakes-0.057
 amusement-0.051
board-0.051
Token the
Token ID262
Feature activation-4.97e-02

Pos logit contributions
emo+0.001
eer+0.000
 sailor+0.000
ba+0.000
cker+0.000
Neg logit contributions
oph-0.001
cake-0.001
cakes-0.001
board-0.000
 amusement-0.000
Token finish
Token ID5461
Feature activation-3.93e+00

Pos logit contributions
oph+0.004
cake+0.004
cakes+0.004
board+0.003
uct+0.003
Neg logit contributions
emo-0.004
 sailor-0.003
eer-0.003
cker-0.003
ba-0.003
Token line
Token ID1627
Feature activation-7.15e+00

Pos logit contributions
oph+0.266
cake+0.253
cakes+0.241
uct+0.219
 amusement+0.216
Neg logit contributions
emo-0.321
 sailor-0.274
eer-0.273
fish-0.267
ba-0.264
Token first
Token ID717
Feature activation-2.15e+00

Pos logit contributions
oph+0.564
cake+0.526
cakes+0.512
 amusement+0.487
board+0.473
Neg logit contributions
emo-0.513
eer-0.417
ba-0.411
 sailor-0.411
fish-0.405
Token.
Token ID13
Feature activation+1.69e-01

Pos logit contributions
oph+0.163
cake+0.158
cakes+0.155
board+0.142
 amusement+0.141
Neg logit contributions
emo-0.159
eer-0.130
 sailor-0.126
ba-0.125
cker-0.124
Token
Token ID198
Feature activation+2.28e+00

Pos logit contributions
emo+0.013
eer+0.010
 sailor+0.010
ba+0.009
fish+0.009
Neg logit contributions
cake-0.013
oph-0.013
cakes-0.012
 amusement-0.012
board-0.011
Token
Token ID198
Feature activation+2.30e+00

Pos logit contributions
emo+0.183
eer+0.155
 sailor+0.151
cker+0.151
ba+0.149
Neg logit contributions
oph-0.157
cake-0.151
cakes-0.147
board-0.136
 amusement-0.133
TokenBut
Token ID1537
Feature activation-3.83e-01

Pos logit contributions
emo+0.162
fish+0.126
 sailor+0.122
ba+0.120
Albert+0.117
Neg logit contributions
cake-0.181
cakes-0.179
oph-0.170
board-0.163
 amusement-0.162
Token had
Token ID550
Feature activation-1.46e+00

Pos logit contributions
oph+0.231
cake+0.229
cakes+0.225
board+0.205
 amusement+0.204
Neg logit contributions
emo-0.252
 sailor-0.205
ba-0.205
eer-0.204
cker-0.200
Token seen
Token ID1775
Feature activation+1.22e+00

Pos logit contributions
cake+0.114
cakes+0.113
oph+0.112
board+0.106
ue+0.101
Neg logit contributions
emo-0.098
ba-0.078
 sailor-0.077
rito-0.076
eer-0.075
Token a
Token ID257
Feature activation+1.86e-01

Pos logit contributions
emo+0.100
eer+0.083
 sailor+0.082
ba+0.081
cker+0.079
Neg logit contributions
oph-0.082
cake-0.080
cakes-0.078
board-0.072
 amusement-0.070
Token famous
Token ID5863
Feature activation+3.93e-01

Pos logit contributions
emo+0.014
eer+0.011
ba+0.011
cker+0.011
rito+0.011
Neg logit contributions
oph-0.014
cake-0.014
cakes-0.013
 amusement-0.012
board-0.012
Token carpet
Token ID20710
Feature activation+1.71e+00

Pos logit contributions
emo+0.030
eer+0.024
ba+0.023
 sailor+0.023
cker+0.023
Neg logit contributions
oph-0.029
cake-0.029
cakes-0.028
board-0.026
 amusement-0.026
Token today
Token ID1909
Feature activation-6.18e+00

Pos logit contributions
emo+0.097
fish+0.094
 sailor+0.092
ba+0.087
eer+0.085
Neg logit contributions
oph-0.144
cakes-0.125
liv-0.124
cake-0.124
uct-0.123
Token!
Token ID0
Feature activation-5.54e+00

Pos logit contributions
oph+0.474
cakes+0.454
cake+0.453
 amusement+0.431
uct+0.430
Neg logit contributions
emo-0.407
fish-0.347
 sailor-0.340
eer-0.325
ba-0.325
Token<|endoftext|>
Token ID50256
Feature activation-2.51e+00

Pos logit contributions
oph+0.391
cake+0.387
cakes+0.385
 amusement+0.358
board+0.352
Neg logit contributions
emo-0.430
eer-0.335
 sailor-0.330
ba-0.326
 Albert-0.325
TokenPaul
Token ID12041
Feature activation+1.20e+00

Pos logit contributions
oph+0.174
cake+0.172
cakes+0.167
board+0.158
 amusement+0.150
Neg logit contributions
emo-0.199
eer-0.165
cker-0.165
 sailor-0.163
rito-0.160
Token was
Token ID373
Feature activation-8.49e-01

Pos logit contributions
emo+0.115
rito+0.097
 sailor+0.095
eer+0.094
 crew+0.093
Neg logit contributions
oph-0.065
board-0.058
cake-0.057
aw-0.054
cakes-0.054
Token a
Token ID257
Feature activation+9.27e-02

Pos logit contributions
oph+0.057
cake+0.056
cakes+0.054
 amusement+0.050
board+0.050
Neg logit contributions
emo-0.069
eer-0.058
rito-0.056
fish-0.056
 sailor-0.056
Token and
Token ID290
Feature activation-3.99e-01

Pos logit contributions
oph+0.376
cake+0.343
cakes+0.337
ue+0.313
uct+0.311
Neg logit contributions
emo-0.363
eer-0.305
 sailor-0.291
ba-0.287
fish-0.281
Token started
Token ID2067
Feature activation-1.14e+00

Pos logit contributions
oph+0.029
cake+0.028
cakes+0.027
 amusement+0.025
board+0.025
Neg logit contributions
emo-0.031
eer-0.026
 sailor-0.025
ba-0.025
cker-0.025
Token to
Token ID284
Feature activation-3.26e-01

Pos logit contributions
oph+0.087
cake+0.084
cakes+0.082
board+0.076
 amusement+0.074
Neg logit contributions
emo-0.086
eer-0.069
 sailor-0.068
ba-0.067
cker-0.066
Token fight
Token ID1907
Feature activation-4.11e+00

Pos logit contributions
oph+0.025
cake+0.024
cakes+0.023
board+0.021
aw+0.020
Neg logit contributions
emo-0.025
eer-0.020
 sailor-0.020
ba-0.020
cker-0.019
Token with
Token ID351
Feature activation-7.84e-01

Pos logit contributions
oph+0.347
cake+0.313
cakes+0.305
board+0.283
 amusement+0.281
Neg logit contributions
emo-0.285
eer-0.216
ba-0.214
 exc-0.206
 sailor-0.201
Token Sarah
Token ID10490
Feature activation-6.70e+00

Pos logit contributions
oph+0.047
cake+0.047
cakes+0.044
board+0.041
 amusement+0.038
Neg logit contributions
emo-0.070
eer-0.058
 sailor-0.058
ba-0.056
cker-0.055
Token.
Token ID13
Feature activation-2.89e-01

Pos logit contributions
oph+0.599
cake+0.566
cakes+0.561
 amusement+0.514
board+0.509
Neg logit contributions
emo-0.406
eer-0.340
ba-0.329
cker-0.320
fish-0.309
Token They
Token ID1119
Feature activation-6.15e-01

Pos logit contributions
oph+0.019
cake+0.018
 amusement+0.017
aw+0.017
cakes+0.017
Neg logit contributions
emo-0.024
ba-0.018
 Albert-0.018
 exc-0.018
cker-0.017
Token both
Token ID1111
Feature activation-2.79e+00

Pos logit contributions
oph+0.056
cake+0.054
cakes+0.050
board+0.046
oga+0.045
Neg logit contributions
emo-0.035
ba-0.032
cker-0.031
eer-0.031
 exc-0.031
Token got
Token ID1392
Feature activation-6.02e-01

Pos logit contributions
oph+0.257
cake+0.247
cakes+0.245
board+0.218
 amusement+0.214
Neg logit contributions
emo-0.161
eer-0.143
cker-0.138
ba-0.132
 exc-0.129
Token hurt
Token ID5938
Feature activation+3.05e+00

Pos logit contributions
oph+0.050
cake+0.047
cakes+0.044
board+0.043
ue+0.042
Neg logit contributions
emo-0.043
eer-0.035
ba-0.034
 sailor-0.034
cker-0.033