TOP ACTIVATIONS
MAX = 15.579

and makes them cry . War is not fun . You
and scary and sad . War hurts people and makes them
is not a game . War is bad and scary and
oys , stop it . War is not a game .
I teach about war . War is when people fight .
, " Me too . War is bad . It makes
missile was for war . War is bad . I don
It is for war . War is bad ," Lily said
birds ," said the scare crow . " Oh
people and their feelings . Learn to appreciate and enjoy different
? Share ? Play ? Learn ?" the wolf says .
Join the Little League ! Learn to play baseball with other
Join the Jazz Club ! Learn to play instruments and sing
Have fun , Lily . Learn a lot . We are
any situation too seriously . Learn to laugh at yourself and
ockey Camp for Kids . Learn from the Best . Sign
for help . The scare crow said " Come with me
. They thanked the scare crow and hugged him . They
. Suddenly , the scare crow moved and waved its arms
stop it !" the scare crow said . " You are

MIN ACTIVATIONS
MIN = -16.703

a cup of warm , freshly made soup and a cozy
saw her mother holding a freshly - b aked muff in
went home and enjoyed his freshly caught fish . <|endoftext|> Once
Tim my a warm , freshly baked cookie .
the church and noticed a freshly dug hole in the ground
sky . The grass was freshly cut , and a gentle
to play and explore the freshly organized lawn . <|endoftext|> Once
. The sweet smell of freshly baked port filled the house
so happy to see a freshly baked bean . After that
mom my surprised him with freshly baked cookies . Tim my
it when the snow was freshly fallen . Today , he
the sweet aroma of a freshly baked cake .
he saw a basket of freshly baked bread . It smelled
crown and playing in the freshly cut grass . It looked
tidy , with his clothes freshly cleaned . Suddenly , he
Andy looked at the freshly printed picture and smiled .
mom put on her a pron and said , " Let
Dad put on his a pron and seemed really happy .
and put on an a pron . His siblings watched him
put on his special a pron and decided to travel .

INTERVAL 7.509 - 15.579
CONTAINS 1.083%

, the baby wasn 't scared anymore . She now knew
, he saw two other mice there . " These are
's mom asked , " Did you let Bob go ?"
be mail men and deliver letters to their mom and dad
he did not recognize the danger . There was a big

INTERVAL -0.562 - 7.509
CONTAINS 62.876%

of hot pepper to his food , and it became very
jump and slide . They saw a big hill with a
and cl apped . " You 're awesome . I 'm
away . They were so happy and proud of themselves for
boy was very surprised . He had never seen a fake

INTERVAL -8.633 - -0.562
CONTAINS 35.749%

kne eled down and told L ola to be careful .
find Lily , so he went to get help . He
so happy and excited ! The bee cut
sand . They make a big pile of sand and say
box opened up with candy inside ! Sarah was

INTERVAL -16.703 - -8.633
CONTAINS 0.291%

Mom said , " Your favorite color is blue , right
a trail ! Em ma got ready to go
many games , but their favorite was pretend . They pretended
. S ally couldn 't wait to give
than having a l oll ipop . He learned that he
Token and
Token ID290
Feature activation+5.48e-02

Pos logit contributions
crow+0.908
Hey+0.893
Leave+0.875
Stop+0.870
Bad+0.845
Neg logit contributions
pron-0.547
 favourite-0.492
 favorite-0.475
 collection-0.459
 masterpiece-0.453
Token makes
Token ID1838
Feature activation+2.09e-01

Pos logit contributions
crow+0.004
vious+0.004
Leave+0.004
eper+0.004
Hey+0.004
Neg logit contributions
pron-0.004
 favourite-0.004
 masterpiece-0.004
 usual-0.004
 favorite-0.004
Token them
Token ID606
Feature activation+2.61e+00

Pos logit contributions
crow+0.014
Leave+0.014
Bad+0.013
eper+0.013
vious+0.012
Neg logit contributions
pron-0.017
 favourite-0.017
 masterpiece-0.017
 favorite-0.016
 brand-0.016
Token cry
Token ID3960
Feature activation+2.90e+00

Pos logit contributions
crow+0.222
Leave+0.205
Bad+0.201
Stop+0.201
Hey+0.199
Neg logit contributions
pron-0.189
 favourite-0.182
 masterpiece-0.175
 favorite-0.168
 collection-0.162
Token.
Token ID13
Feature activation+1.89e-01

Pos logit contributions
crow+0.287
Leave+0.279
Bad+0.271
Hey+0.268
Stop+0.264
Neg logit contributions
pron-0.144
 favourite-0.143
 favorite-0.140
 masterpiece-0.129
 daddy-0.121
Token War
Token ID1810
Feature activation+1.56e+01

Pos logit contributions
crow+0.013
vious+0.012
eper+0.012
Leave+0.012
Stop+0.011
Neg logit contributions
 favourite-0.014
 favorite-0.013
pron-0.013
 Daddy-0.013
 Grand-0.012
Token is
Token ID318
Feature activation+1.30e+00

Pos logit contributions
crow+1.312
Leave+1.272
Bad+1.227
eper+1.198
 hunters+1.166
Neg logit contributions
pron-0.964
 favourite-0.922
 favorite-0.913
 masterpiece-0.846
 couldn-0.833
Token not
Token ID407
Feature activation-2.90e+00

Pos logit contributions
crow+0.115
Leave+0.108
vious+0.103
Stop+0.103
Bad+0.102
Neg logit contributions
pron-0.090
 favourite-0.084
 masterpiece-0.082
 favorite-0.077
 brand-0.076
Token fun
Token ID1257
Feature activation-6.78e-01

Pos logit contributions
pron+0.194
 favourite+0.176
 masterpiece+0.170
 favorite+0.162
 brand+0.159
Neg logit contributions
crow-0.265
Leave-0.253
Bad-0.240
vious-0.239
Stop-0.238
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
pron+0.045
 favourite+0.042
 masterpiece+0.041
 favorite+0.039
 collection+0.038
Neg logit contributions
crow-0.059
Leave-0.058
Bad-0.057
Stop-0.054
vious-0.054
Token You
Token ID921
Feature activation+5.37e+00

Pos logit contributions
crow+0.011
eper+0.010
Leave+0.010
vious+0.010
 hunters+0.009
Neg logit contributions
 favourite-0.018
 favorite-0.017
pron-0.017
 masterpiece-0.016
 Daddy-0.016
Token and
Token ID290
Feature activation+4.42e-02

Pos logit contributions
crow+0.201
Bad+0.199
Leave+0.199
eper+0.185
Hey+0.185
Neg logit contributions
 favourite-0.113
pron-0.107
 favorite-0.105
 masterpiece-0.102
 collection-0.098
Token scary
Token ID14343
Feature activation+2.70e+00

Pos logit contributions
crow+0.003
Leave+0.003
eper+0.003
Hey+0.003
vious+0.003
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 favorite-0.003
 brand-0.003
Token and
Token ID290
Feature activation+4.22e-02

Pos logit contributions
crow+0.261
Leave+0.259
Bad+0.254
Hey+0.245
vious+0.243
Neg logit contributions
 favourite-0.124
 favorite-0.117
pron-0.114
 masterpiece-0.113
 collection-0.110
Token sad
Token ID6507
Feature activation+3.73e+00

Pos logit contributions
crow+0.003
Leave+0.003
eper+0.003
Bad+0.003
vious+0.003
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 favorite-0.003
 usual-0.003
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
crow+0.350
Leave+0.346
Bad+0.336
vious+0.328
eper+0.327
Neg logit contributions
 favourite-0.187
 favorite-0.179
pron-0.178
 masterpiece-0.172
 collection-0.166
Token War
Token ID1810
Feature activation+1.56e+01

Pos logit contributions
crow+0.011
vious+0.010
Leave+0.010
eper+0.010
Stop+0.009
Neg logit contributions
 favourite-0.013
 favorite-0.012
 Daddy-0.011
 Grand-0.011
 Mam-0.011
Token hurts
Token ID20406
Feature activation+8.91e-01

Pos logit contributions
crow+1.297
Leave+1.270
Bad+1.222
eper+1.181
vious+1.157
Neg logit contributions
pron-0.981
 favourite-0.944
 favorite-0.923
 masterpiece-0.862
 couldn-0.842
Token people
Token ID661
Feature activation+9.69e+00

Pos logit contributions
Leave+0.074
vious+0.071
crow+0.071
eper+0.068
Bad+0.067
Neg logit contributions
 favourite-0.048
pron-0.048
 favorite-0.047
 usual-0.044
 couldn-0.043
Token and
Token ID290
Feature activation+5.48e-02

Pos logit contributions
crow+0.908
Hey+0.893
Leave+0.875
Stop+0.870
Bad+0.845
Neg logit contributions
pron-0.547
 favourite-0.492
 favorite-0.475
 collection-0.459
 masterpiece-0.453
Token makes
Token ID1838
Feature activation+2.09e-01

Pos logit contributions
crow+0.004
vious+0.004
Leave+0.004
eper+0.004
Hey+0.004
Neg logit contributions
pron-0.004
 favourite-0.004
 masterpiece-0.004
 usual-0.004
 favorite-0.004
Token them
Token ID606
Feature activation+2.61e+00

Pos logit contributions
crow+0.014
Leave+0.014
Bad+0.013
eper+0.013
vious+0.012
Neg logit contributions
pron-0.017
 favourite-0.017
 masterpiece-0.017
 favorite-0.016
 brand-0.016
Token is
Token ID318
Feature activation+1.23e+00

Pos logit contributions
crow+1.326
Leave+1.284
Bad+1.246
eper+1.207
vious+1.178
Neg logit contributions
pron-0.962
 favourite-0.913
 favorite-0.889
 masterpiece-0.832
 couldn-0.811
Token not
Token ID407
Feature activation-2.96e+00

Pos logit contributions
crow+0.113
Leave+0.107
vious+0.102
Bad+0.102
Stop+0.102
Neg logit contributions
pron-0.081
 favourite-0.075
 masterpiece-0.073
 favorite-0.067
 brand-0.067
Token a
Token ID257
Feature activation+2.10e-01

Pos logit contributions
pron+0.201
 favourite+0.182
 masterpiece+0.178
 favorite+0.165
 usual+0.165
Neg logit contributions
crow-0.267
Leave-0.256
Bad-0.246
vious-0.242
Stop-0.242
Token game
Token ID983
Feature activation+2.34e+00

Pos logit contributions
crow+0.017
Leave+0.016
Bad+0.016
vious+0.015
Stop+0.015
Neg logit contributions
pron-0.016
 masterpiece-0.015
 favourite-0.015
 collection-0.014
 brand-0.013
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
crow+0.203
Leave+0.200
Bad+0.198
vious+0.188
Stop+0.187
Neg logit contributions
pron-0.153
 favourite-0.144
 masterpiece-0.140
 collection-0.132
 usual-0.131
Token War
Token ID1810
Feature activation+1.55e+01

Pos logit contributions
crow+0.010
Leave+0.009
eper+0.009
vious+0.009
Stop+0.009
Neg logit contributions
 favourite-0.012
 favorite-0.011
pron-0.011
 masterpiece-0.010
 Daddy-0.010
Token is
Token ID318
Feature activation+1.26e+00

Pos logit contributions
crow+1.280
Leave+1.250
Bad+1.210
eper+1.164
vious+1.148
Neg logit contributions
pron-1.026
 favourite-0.978
 favorite-0.941
 masterpiece-0.905
 usual-0.874
Token bad
Token ID2089
Feature activation+2.18e+00

Pos logit contributions
crow+0.116
Leave+0.110
Bad+0.106
vious+0.105
Stop+0.105
Neg logit contributions
pron-0.084
 favourite-0.077
 masterpiece-0.076
 favorite-0.070
 usual-0.069
Token and
Token ID290
Feature activation+4.42e-02

Pos logit contributions
crow+0.201
Bad+0.199
Leave+0.199
eper+0.185
Hey+0.185
Neg logit contributions
 favourite-0.113
pron-0.107
 favorite-0.105
 masterpiece-0.102
 collection-0.098
Token scary
Token ID14343
Feature activation+2.70e+00

Pos logit contributions
crow+0.003
Leave+0.003
eper+0.003
Hey+0.003
vious+0.003
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 favorite-0.003
 brand-0.003
Token and
Token ID290
Feature activation+4.22e-02

Pos logit contributions
crow+0.261
Leave+0.259
Bad+0.254
Hey+0.245
vious+0.243
Neg logit contributions
 favourite-0.124
 favorite-0.117
pron-0.114
 masterpiece-0.113
 collection-0.110
Tokenoys
Token ID19417
Feature activation+1.88e+00

Pos logit contributions
Leave+0.531
crow+0.527
Bad+0.522
Stop+0.493
vious+0.488
Neg logit contributions
pron-0.450
 favourite-0.416
 masterpiece-0.403
ail-0.394
 collection-0.380
Token,
Token ID11
Feature activation+1.20e+00

Pos logit contributions
crow+0.168
Leave+0.164
Bad+0.162
Stop+0.155
vious+0.154
Neg logit contributions
pron-0.127
 favourite-0.114
 masterpiece-0.112
 collection-0.103
ail-0.101
Token stop
Token ID2245
Feature activation+3.86e+00

Pos logit contributions
crow+0.083
Leave+0.079
Bad+0.078
vious+0.076
Stop+0.075
Neg logit contributions
pron-0.107
 favourite-0.098
 masterpiece-0.097
 collection-0.090
 usual-0.089
Token it
Token ID340
Feature activation+7.12e-02

Pos logit contributions
crow+0.331
Leave+0.313
Bad+0.308
vious+0.305
Stop+0.296
Neg logit contributions
pron-0.274
 masterpiece-0.249
 favourite-0.246
 collection-0.221
 brand-0.219
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
crow+0.006
Leave+0.006
Bad+0.006
Stop+0.006
vious+0.006
Neg logit contributions
pron-0.005
 masterpiece-0.004
 favourite-0.004
 collection-0.004
 usual-0.004
Token War
Token ID1810
Feature activation+1.55e+01

Pos logit contributions
Leave+0.008
crow+0.008
Bad+0.008
vious+0.008
Stop+0.008
Neg logit contributions
pron-0.012
 favourite-0.012
 masterpiece-0.011
 favorite-0.011
 bedroom-0.011
Token is
Token ID318
Feature activation+1.23e+00

Pos logit contributions
crow+1.326
Leave+1.284
Bad+1.246
eper+1.207
vious+1.178
Neg logit contributions
pron-0.962
 favourite-0.913
 favorite-0.889
 masterpiece-0.832
 couldn-0.811
Token not
Token ID407
Feature activation-2.96e+00

Pos logit contributions
crow+0.113
Leave+0.107
vious+0.102
Bad+0.102
Stop+0.102
Neg logit contributions
pron-0.081
 favourite-0.075
 masterpiece-0.073
 favorite-0.067
 brand-0.067
Token a
Token ID257
Feature activation+2.10e-01

Pos logit contributions
pron+0.201
 favourite+0.182
 masterpiece+0.178
 favorite+0.165
 usual+0.165
Neg logit contributions
crow-0.267
Leave-0.256
Bad-0.246
vious-0.242
Stop-0.242
Token game
Token ID983
Feature activation+2.34e+00

Pos logit contributions
crow+0.017
Leave+0.016
Bad+0.016
vious+0.015
Stop+0.015
Neg logit contributions
pron-0.016
 masterpiece-0.015
 favourite-0.015
 collection-0.014
 brand-0.013
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
crow+0.203
Leave+0.200
Bad+0.198
vious+0.188
Stop+0.187
Neg logit contributions
pron-0.153
 favourite-0.144
 masterpiece-0.140
 collection-0.132
 usual-0.131
Token I
Token ID314
Feature activation-2.43e+00

Pos logit contributions
Bad+0.008
Leave+0.008
crow+0.008
vious+0.008
Stop+0.008
Neg logit contributions
pron-0.010
 favourite-0.010
 masterpiece-0.009
 favorite-0.009
 bedroom-0.009
Token teach
Token ID4545
Feature activation+3.89e+00

Pos logit contributions
pron+0.206
 favourite+0.190
 masterpiece+0.187
 collection+0.174
 favorite+0.170
Neg logit contributions
crow-0.175
Leave-0.169
Bad-0.167
Stop-0.159
vious-0.157
Token about
Token ID546
Feature activation-2.11e+00

Pos logit contributions
crow+0.225
Leave+0.216
Bad+0.213
vious+0.200
Stop+0.199
Neg logit contributions
pron-0.382
 favourite-0.360
 masterpiece-0.356
 collection-0.331
 usual-0.330
Token war
Token ID1175
Feature activation+6.84e+00

Pos logit contributions
pron+0.194
 masterpiece+0.177
 favourite+0.177
 collection+0.163
ail+0.160
Neg logit contributions
crow-0.138
Bad-0.133
Leave-0.131
Stop-0.126
vious-0.122
Token.
Token ID13
Feature activation+1.07e-01

Pos logit contributions
Leave+0.594
crow+0.585
Bad+0.579
Stop+0.546
vious+0.541
Neg logit contributions
pron-0.467
 favourite-0.450
 masterpiece-0.430
 favorite-0.404
 collection-0.402
Token War
Token ID1810
Feature activation+1.55e+01

Pos logit contributions
crow+0.007
Leave+0.007
Bad+0.007
vious+0.007
Stop+0.007
Neg logit contributions
 favourite-0.008
pron-0.008
 masterpiece-0.008
 favorite-0.007
 bedroom-0.007
Token is
Token ID318
Feature activation+1.20e+00

Pos logit contributions
crow+1.209
Leave+1.208
Bad+1.163
vious+1.091
eper+1.074
Neg logit contributions
pron-1.141
 favourite-1.088
 masterpiece-1.044
 favorite-1.017
 collection-0.965
Token when
Token ID618
Feature activation+6.78e+00

Pos logit contributions
crow+0.106
Leave+0.101
Bad+0.097
vious+0.096
Stop+0.096
Neg logit contributions
pron-0.083
 favourite-0.077
 masterpiece-0.076
 brand-0.068
 favorite-0.068
Token people
Token ID661
Feature activation+9.60e+00

Pos logit contributions
crow+0.502
Leave+0.481
Bad+0.477
Stop+0.458
vious+0.456
Neg logit contributions
pron-0.562
 favourite-0.518
 masterpiece-0.515
 collection-0.473
 usual-0.467
Token fight
Token ID1907
Feature activation+4.75e+00

Pos logit contributions
crow+0.744
Leave+0.717
Bad+0.704
vious+0.654
eper+0.649
Neg logit contributions
pron-0.725
 favourite-0.657
 masterpiece-0.650
 collection-0.631
 usual-0.617
Token.
Token ID13
Feature activation+8.82e-02

Pos logit contributions
crow+0.410
Leave+0.408
Bad+0.386
vious+0.376
eper+0.361
Neg logit contributions
pron-0.308
 favourite-0.290
 masterpiece-0.287
 favorite-0.270
 collection-0.266
Token,
Token ID11
Feature activation+1.13e+00

Pos logit contributions
pron+0.100
 masterpiece+0.093
 favourite+0.090
 usual+0.081
 collection+0.081
Neg logit contributions
crow-0.095
Leave-0.091
Bad-0.090
Stop-0.086
vious-0.085
Token "
Token ID366
Feature activation-1.87e-01

Pos logit contributions
Leave+0.086
crow+0.085
Bad+0.084
Stop+0.080
ting+0.077
Neg logit contributions
pron-0.086
 masterpiece-0.083
 favourite-0.082
 collection-0.075
 usual-0.073
TokenMe
Token ID5308
Feature activation+1.56e+00

Pos logit contributions
pron+0.018
 favourite+0.016
 masterpiece+0.016
 usual+0.015
 brand+0.014
Neg logit contributions
crow-0.012
ases-0.011
Leave-0.011
vious-0.011
Bad-0.011
Token too
Token ID1165
Feature activation+5.19e+00

Pos logit contributions
crow+0.094
Leave+0.090
Bad+0.089
Stop+0.085
vious+0.083
Neg logit contributions
pron-0.155
 favourite-0.144
 masterpiece-0.143
 collection-0.133
 brand-0.131
Token.
Token ID13
Feature activation+4.93e-02

Pos logit contributions
crow+0.400
Leave+0.384
Bad+0.383
Stop+0.367
vious+0.364
Neg logit contributions
pron-0.421
 favourite-0.384
 masterpiece-0.383
 collection-0.349
 usual-0.342
Token War
Token ID1810
Feature activation+1.54e+01

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.003
Neg logit contributions
pron-0.004
 favourite-0.004
 masterpiece-0.004
 collection-0.004
 brand-0.004
Token is
Token ID318
Feature activation+1.14e+00

Pos logit contributions
crow+1.226
Leave+1.195
Bad+1.160
vious+1.102
eper+1.098
Neg logit contributions
pron-1.133
 favourite-1.079
 masterpiece-1.023
 favorite-0.994
 collection-0.960
Token bad
Token ID2089
Feature activation+2.07e+00

Pos logit contributions
crow+0.093
Leave+0.090
Bad+0.089
Stop+0.086
vious+0.085
Neg logit contributions
pron-0.088
 favourite-0.079
 masterpiece-0.079
 collection-0.072
 usual-0.070
Token.
Token ID13
Feature activation+4.12e-02

Pos logit contributions
crow+0.177
Leave+0.175
Bad+0.174
Stop+0.164
vious+0.161
Neg logit contributions
pron-0.137
 favourite-0.134
 masterpiece-0.126
 favorite-0.120
 collection-0.119
Token It
Token ID632
Feature activation+7.48e-01

Pos logit contributions
crow+0.003
Leave+0.003
vious+0.003
Bad+0.003
Stop+0.003
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 favorite-0.003
 brand-0.003
Token makes
Token ID1838
Feature activation+6.67e-02

Pos logit contributions
crow+0.060
Leave+0.058
Bad+0.056
ases+0.054
Stop+0.054
Neg logit contributions
pron-0.055
 favourite-0.052
 masterpiece-0.052
 favorite-0.048
 collection-0.048
Token missile
Token ID10105
Feature activation+2.54e+00

Pos logit contributions
crow+0.105
Leave+0.104
ases+0.099
vious+0.099
Bad+0.097
Neg logit contributions
pron-0.093
 masterpiece-0.089
 favourite-0.089
 favorite-0.083
 collection-0.082
Token was
Token ID373
Feature activation-1.57e+00

Pos logit contributions
crow+0.218
Leave+0.217
Bad+0.210
Stop+0.205
vious+0.199
Neg logit contributions
pron-0.168
 favourite-0.158
 masterpiece-0.154
 collection-0.147
 favorite-0.145
Token for
Token ID329
Feature activation-5.41e+00

Pos logit contributions
pron+0.118
 favourite+0.110
 masterpiece+0.108
 favorite+0.100
 usual+0.100
Neg logit contributions
crow-0.129
Leave-0.123
Stop-0.119
Bad-0.117
vious-0.117
Token war
Token ID1175
Feature activation+6.78e+00

Pos logit contributions
pron+0.427
 favourite+0.402
 masterpiece+0.402
 usual+0.376
 brand+0.366
Neg logit contributions
crow-0.416
Leave-0.386
vious-0.378
Bad-0.374
Stop-0.365
Token.
Token ID13
Feature activation+5.42e-02

Pos logit contributions
crow+0.597
Leave+0.594
Bad+0.586
Stop+0.556
vious+0.542
Neg logit contributions
pron-0.436
 favourite-0.417
 masterpiece-0.395
 favorite-0.379
 collection-0.376
Token War
Token ID1810
Feature activation+1.54e+01

Pos logit contributions
crow+0.004
Leave+0.004
eper+0.004
vious+0.004
Stop+0.004
Neg logit contributions
 favourite-0.004
pron-0.003
 favorite-0.003
 brand-0.003
 masterpiece-0.003
Token is
Token ID318
Feature activation+1.15e+00

Pos logit contributions
crow+1.231
Leave+1.216
Bad+1.169
eper+1.117
vious+1.108
Neg logit contributions
pron-1.088
 favourite-1.038
 favorite-0.982
 masterpiece-0.976
 usual-0.927
Token bad
Token ID2089
Feature activation+2.06e+00

Pos logit contributions
crow+0.100
Leave+0.095
vious+0.091
Stop+0.091
Bad+0.090
Neg logit contributions
pron-0.081
 favourite-0.076
 masterpiece-0.075
 brand-0.069
 favorite-0.069
Token.
Token ID13
Feature activation+4.82e-02

Pos logit contributions
crow+0.186
Leave+0.184
Bad+0.183
Stop+0.171
eper+0.169
Neg logit contributions
pron-0.118
 favourite-0.116
 masterpiece-0.108
 favorite-0.106
 collection-0.101
Token I
Token ID314
Feature activation-2.52e+00

Pos logit contributions
crow+0.004
eper+0.004
Leave+0.004
vious+0.004
ting+0.003
Neg logit contributions
 favourite-0.003
 favorite-0.003
pron-0.003
 Grand-0.003
 Daddy-0.003
Token don
Token ID836
Feature activation+5.04e+00

Pos logit contributions
pron+0.182
 favourite+0.181
 masterpiece+0.168
 favorite+0.167
 collection+0.158
Neg logit contributions
crow-0.193
Leave-0.190
Bad-0.181
ting-0.177
Stop-0.176
Token It
Token ID632
Feature activation+7.37e-01

Pos logit contributions
Leave+0.003
crow+0.003
Stop+0.003
Bad+0.003
vious+0.003
Neg logit contributions
 favourite-0.002
pron-0.002
 favorite-0.002
 Grand-0.002
 Daddy-0.002
Token is
Token ID318
Feature activation+1.14e+00

Pos logit contributions
crow+0.059
Leave+0.059
Bad+0.056
Stop+0.055
ases+0.054
Neg logit contributions
pron-0.053
 favourite-0.050
 masterpiece-0.048
 favorite-0.046
 collection-0.045
Token for
Token ID329
Feature activation-5.42e+00

Pos logit contributions
crow+0.091
Bad+0.090
Leave+0.088
Stop+0.084
vious+0.084
Neg logit contributions
pron-0.088
 masterpiece-0.079
 favourite-0.078
 collection-0.072
ail-0.071
Token war
Token ID1175
Feature activation+6.78e+00

Pos logit contributions
pron+0.449
 favourite+0.416
 masterpiece+0.413
 usual+0.380
 collection+0.378
Neg logit contributions
crow-0.400
Leave-0.381
Bad-0.375
vious-0.365
Stop-0.362
Token.
Token ID13
Feature activation+2.88e-02

Pos logit contributions
crow+0.564
Leave+0.558
Bad+0.546
Stop+0.522
vious+0.517
Neg logit contributions
pron-0.483
 favourite-0.459
 masterpiece-0.437
 favorite-0.417
 collection-0.413
Token War
Token ID1810
Feature activation+1.54e+01

Pos logit contributions
crow+0.002
Leave+0.002
vious+0.002
eper+0.002
Stop+0.002
Neg logit contributions
 favourite-0.002
pron-0.002
 Grand-0.002
 favorite-0.002
 Daddy-0.002
Token is
Token ID318
Feature activation+1.14e+00

Pos logit contributions
Leave+1.238
crow+1.237
Bad+1.187
vious+1.130
eper+1.120
Neg logit contributions
pron-1.030
 favourite-1.003
 favorite-0.966
 masterpiece-0.914
 usual-0.899
Token bad
Token ID2089
Feature activation+2.06e+00

Pos logit contributions
crow+0.103
Leave+0.098
vious+0.094
Stop+0.094
Bad+0.093
Neg logit contributions
pron-0.074
 favourite-0.070
 masterpiece-0.068
 favorite-0.064
 usual-0.063
Token,"
Token ID553
Feature activation-4.70e+00

Pos logit contributions
Leave+0.178
crow+0.178
Bad+0.176
Stop+0.164
vious+0.163
Neg logit contributions
pron-0.124
 favourite-0.122
 favorite-0.114
 masterpiece-0.113
 collection-0.108
Token Lily
Token ID20037
Feature activation-1.93e+00

Pos logit contributions
pron+0.353
 favourite+0.319
 masterpiece+0.318
 collection+0.287
 usual+0.283
Neg logit contributions
crow-0.391
Leave-0.377
Bad-0.374
Stop-0.361
vious-0.359
Token said
Token ID531
Feature activation-1.25e+00

Pos logit contributions
pron+0.098
 favourite+0.085
 masterpiece+0.079
 favorite+0.073
ail+0.070
Neg logit contributions
crow-0.199
Leave-0.196
Bad-0.194
ases-0.188
Stop-0.187
Token birds
Token ID10087
Feature activation+9.41e+00

Pos logit contributions
crow+0.179
Bad+0.171
Leave+0.171
Stop+0.165
vious+0.162
Neg logit contributions
pron-0.158
 favourite-0.143
 masterpiece-0.142
 collection-0.128
 brand-0.126
Token,"
Token ID553
Feature activation-3.61e+00

Pos logit contributions
crow+0.734
Leave+0.705
Bad+0.701
Stop+0.674
vious+0.668
Neg logit contributions
pron-0.747
 favourite-0.681
 masterpiece-0.678
 collection-0.617
 usual-0.605
Token said
Token ID531
Feature activation-3.02e-01

Pos logit contributions
pron+0.254
 favourite+0.229
 masterpiece+0.228
 collection+0.205
 usual+0.200
Neg logit contributions
crow-0.315
Leave-0.304
Bad-0.303
Stop-0.292
vious-0.290
Token the
Token ID262
Feature activation+2.08e+00

Pos logit contributions
pron+0.023
 masterpiece+0.021
 favourite+0.021
 collection+0.019
 brand+0.019
Neg logit contributions
crow-0.025
Bad-0.023
Leave-0.023
Stop-0.022
eper-0.022
Token scare
Token ID19437
Feature activation+4.88e+00

Pos logit contributions
crow+0.148
Leave+0.142
Bad+0.141
Stop+0.136
vious+0.134
Neg logit contributions
pron-0.178
 favourite-0.164
 masterpiece-0.163
 collection-0.150
 usual-0.147
Tokencrow
Token ID47114
Feature activation+1.51e+01

Pos logit contributions
Leave+0.099
Bad+0.096
Stop+0.075
ases+0.069
vious+0.067
Neg logit contributions
pron-0.638
 favourite-0.606
 masterpiece-0.597
ail-0.592
 usual-0.579
Token.
Token ID13
Feature activation+5.33e-01

Pos logit contributions
crow+1.032
Bad+0.936
Leave+0.934
vious+0.906
eper+0.904
Neg logit contributions
pron-1.347
 masterpiece-1.239
 favourite-1.204
 collection-1.114
 brand-1.110
Token
Token ID198
Feature activation-3.26e-02

Pos logit contributions
crow+0.042
Leave+0.041
Bad+0.041
Stop+0.039
vious+0.039
Neg logit contributions
pron-0.041
 favourite-0.038
 masterpiece-0.037
 collection-0.034
 brand-0.033
Token
Token ID198
Feature activation-7.88e-02

Pos logit contributions
pron+0.002
 favourite+0.002
 masterpiece+0.002
ail+0.002
 usual+0.002
Neg logit contributions
crow-0.003
Leave-0.003
Bad-0.003
vious-0.003
Stop-0.002
Token"
Token ID1
Feature activation+5.74e+00

Pos logit contributions
pron+0.006
 masterpiece+0.005
 favourite+0.005
ail+0.005
addy+0.005
Neg logit contributions
vious-0.006
crow-0.006
ases-0.005
ting-0.005
 hunters-0.005
TokenOh
Token ID5812
Feature activation+2.32e+00

Pos logit contributions
crow+0.352
ases+0.338
vious+0.333
 hunters+0.318
eper+0.315
Neg logit contributions
pron-0.535
 favourite-0.484
 masterpiece-0.453
 usual-0.431
 favorite-0.425
Token people
Token ID661
Feature activation+9.71e+00

Pos logit contributions
Bad+0.324
Leave+0.319
crow+0.314
eper+0.291
Hey+0.288
Neg logit contributions
 favourite-0.463
 masterpiece-0.448
pron-0.442
 favorite-0.435
 usual-0.431
Token and
Token ID290
Feature activation+6.92e-02

Pos logit contributions
Leave+0.789
crow+0.785
Bad+0.761
Stop+0.760
Hey+0.744
Neg logit contributions
pron-0.728
 favourite-0.675
 masterpiece-0.631
 collection-0.617
 favorite-0.613
Token their
Token ID511
Feature activation-7.23e-01

Pos logit contributions
crow+0.005
Leave+0.004
Bad+0.004
vious+0.004
Stop+0.004
Neg logit contributions
pron-0.006
 favourite-0.006
 masterpiece-0.006
 collection-0.005
 usual-0.005
Token feelings
Token ID7666
Feature activation+3.41e+00

Pos logit contributions
pron+0.060
 favourite+0.058
 masterpiece+0.057
 collection+0.053
 favorite+0.052
Neg logit contributions
crow-0.052
Leave-0.051
Bad-0.050
Stop-0.048
vious-0.047
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
crow+0.279
Leave+0.271
Bad+0.269
Stop+0.260
vious+0.255
Neg logit contributions
pron-0.254
 favourite-0.234
 masterpiece-0.230
 collection-0.213
 usual-0.208
Token Learn
Token ID14365
Feature activation+1.51e+01

Pos logit contributions
crow+0.016
Leave+0.016
vious+0.015
Stop+0.015
Bad+0.015
Neg logit contributions
pron-0.015
 favourite-0.015
 masterpiece-0.014
onna-0.013
 favorite-0.013
Token to
Token ID284
Feature activation-1.47e+00

Pos logit contributions
crow+1.118
Bad+1.061
Leave+1.049
Stop+1.025
vious+1.000
Neg logit contributions
pron-1.283
 masterpiece-1.159
 favourite-1.152
 collection-1.057
 brand-1.037
Token appreciate
Token ID9144
Feature activation+9.93e-02

Pos logit contributions
pron+0.123
 favourite+0.113
 masterpiece+0.113
 collection+0.104
 usual+0.103
Neg logit contributions
crow-0.107
Leave-0.102
Bad-0.101
vious-0.097
Stop-0.097
Token and
Token ID290
Feature activation+9.73e-02

Pos logit contributions
crow+0.007
Leave+0.007
Bad+0.007
vious+0.006
Stop+0.006
Neg logit contributions
pron-0.009
 favourite-0.008
 masterpiece-0.008
 collection-0.007
 usual-0.007
Token enjoy
Token ID2883
Feature activation-2.58e+00

Pos logit contributions
crow+0.007
Leave+0.007
Bad+0.007
vious+0.006
Stop+0.006
Neg logit contributions
pron-0.008
 favourite-0.008
 masterpiece-0.008
 collection-0.007
 usual-0.007
Token different
Token ID1180
Feature activation+6.05e-01

Pos logit contributions
pron+0.223
 favourite+0.210
 masterpiece+0.207
 collection+0.191
 usual+0.191
Neg logit contributions
crow-0.180
Leave-0.173
Bad-0.168
vious-0.167
Stop-0.162
Token?
Token ID30
Feature activation-3.44e+00

Pos logit contributions
Leave+0.226
Bad+0.219
crow+0.209
Stop+0.202
vious+0.194
Neg logit contributions
pron-0.157
 favourite-0.147
 collection-0.141
 masterpiece-0.139
 usual-0.132
Token Share
Token ID8734
Feature activation+8.35e+00

Pos logit contributions
pron+0.301
 favourite+0.295
 masterpiece+0.276
 favorite+0.265
 collection+0.264
Neg logit contributions
crow-0.224
Leave-0.216
vious-0.211
Bad-0.207
Stop-0.202
Token?
Token ID30
Feature activation-3.44e+00

Pos logit contributions
crow+0.660
Leave+0.656
Bad+0.625
vious+0.620
Stop+0.603
Neg logit contributions
pron-0.645
 favourite-0.603
 masterpiece-0.583
 collection-0.546
 favorite-0.541
Token Play
Token ID3811
Feature activation+1.13e+01

Pos logit contributions
 favourite+0.280
pron+0.279
 masterpiece+0.249
 favorite+0.247
 collection+0.238
Neg logit contributions
crow-0.231
Leave-0.223
Bad-0.220
vious-0.219
Stop-0.212
Token?
Token ID30
Feature activation-3.44e+00

Pos logit contributions
Leave+0.900
crow+0.891
Bad+0.864
vious+0.860
Stop+0.844
Neg logit contributions
pron-0.880
 favourite-0.808
 masterpiece-0.774
ail-0.709
 favorite-0.709
Token Learn
Token ID14365
Feature activation+1.50e+01

Pos logit contributions
pron+0.284
 favourite+0.282
 masterpiece+0.252
 favorite+0.249
 brand+0.241
Neg logit contributions
crow-0.230
Leave-0.218
Bad-0.217
vious-0.216
Stop-0.210
Token?"
Token ID1701
Feature activation-6.20e+00

Pos logit contributions
crow+1.119
Leave+1.099
Bad+1.076
vious+1.033
Stop+1.030
Neg logit contributions
pron-1.230
 favourite-1.152
 masterpiece-1.134
 collection-1.045
 favorite-1.031
Token the
Token ID262
Feature activation+1.46e+00

Pos logit contributions
pron+0.366
 favourite+0.365
 masterpiece+0.357
 usual+0.330
 daddy+0.319
Neg logit contributions
crow-0.531
Leave-0.523
Bad-0.520
vious-0.516
ases-0.503
Token wolf
Token ID17481
Feature activation+3.02e+00

Pos logit contributions
crow+0.089
Leave+0.085
Bad+0.084
Stop+0.080
vious+0.079
Neg logit contributions
pron-0.142
 favourite-0.132
 masterpiece-0.130
 collection-0.121
 brand-0.120
Token says
Token ID1139
Feature activation+2.23e+00

Pos logit contributions
Bad+0.253
Leave+0.249
crow+0.242
Stop+0.242
ases+0.226
Neg logit contributions
pron-0.194
 favourite-0.185
 masterpiece-0.184
 collection-0.170
 favorite-0.169
Token.
Token ID13
Feature activation+2.26e-01

Pos logit contributions
crow+0.192
Bad+0.188
Leave+0.187
Stop+0.185
vious+0.177
Neg logit contributions
pron-0.159
 favourite-0.145
 masterpiece-0.142
 collection-0.128
ail-0.127
TokenJoin
Token ID18234
Feature activation+6.38e+00

Pos logit contributions
crow+0.002
Bad+0.002
eper+0.002
vious+0.002
 hunters+0.002
Neg logit contributions
pron-0.003
 favourite-0.002
 masterpiece-0.002
 usual-0.002
 favorite-0.002
Token the
Token ID262
Feature activation+1.46e+00

Pos logit contributions
Leave+0.482
crow+0.471
Bad+0.457
vious+0.449
eper+0.428
Neg logit contributions
 favourite-0.496
pron-0.491
 masterpiece-0.468
 favorite-0.445
 collection-0.434
Token Little
Token ID7703
Feature activation-2.68e+00

Pos logit contributions
crow+0.122
Leave+0.120
Bad+0.118
vious+0.114
Stop+0.113
Neg logit contributions
pron-0.106
 favourite-0.098
 masterpiece-0.096
 collection-0.088
 usual-0.086
Token League
Token ID4041
Feature activation+2.27e+00

Pos logit contributions
pron+0.218
 favourite+0.204
 masterpiece+0.199
 collection+0.185
 usual+0.183
Neg logit contributions
crow-0.193
Leave-0.191
Bad-0.187
vious-0.184
ases-0.180
Token!
Token ID0
Feature activation-3.01e+00

Pos logit contributions
Leave+0.175
crow+0.174
Bad+0.172
Stop+0.164
vious+0.163
Neg logit contributions
pron-0.176
 favourite-0.163
 masterpiece-0.158
 collection-0.150
 usual-0.144
Token Learn
Token ID14365
Feature activation+1.50e+01

Pos logit contributions
pron+0.225
 favourite+0.225
 Sus+0.208
 masterpiece+0.203
 Daddy+0.203
Neg logit contributions
Bad-0.197
Leave-0.195
crow-0.192
vious-0.186
Stop-0.180
Token to
Token ID284
Feature activation-1.52e+00

Pos logit contributions
crow+1.154
Leave+1.105
Bad+1.101
Stop+1.060
vious+1.046
Neg logit contributions
pron-1.217
 favourite-1.105
 masterpiece-1.103
 collection-1.005
 brand-0.986
Token play
Token ID711
Feature activation+1.38e+00

Pos logit contributions
pron+0.120
 favourite+0.110
 masterpiece+0.110
 collection+0.101
 usual+0.099
Neg logit contributions
crow-0.117
Leave-0.113
Bad-0.113
vious-0.108
Stop-0.108
Token baseball
Token ID9283
Feature activation-3.27e-02

Pos logit contributions
Leave+0.115
crow+0.114
vious+0.110
Bad+0.110
Stop+0.106
Neg logit contributions
pron-0.096
 favourite-0.093
 masterpiece-0.087
 collection-0.083
 favorite-0.083
Token with
Token ID351
Feature activation+1.48e+00

Pos logit contributions
pron+0.002
 favourite+0.002
 masterpiece+0.002
 collection+0.002
 favorite+0.002
Neg logit contributions
Leave-0.003
crow-0.003
Bad-0.003
Stop-0.003
vious-0.002
Token other
Token ID584
Feature activation+5.41e+00

Pos logit contributions
crow+0.104
Leave+0.102
Bad+0.098
vious+0.096
Stop+0.094
Neg logit contributions
pron-0.127
 favourite-0.120
 masterpiece-0.117
 collection-0.109
 usual-0.108
TokenJoin
Token ID18234
Feature activation+6.36e+00

Pos logit contributions
crow+0.000
 hunters+0.000
Bad+0.000
eper+0.000
Leave+0.000
Neg logit contributions
pron-0.000
 favourite-0.000
 masterpiece-0.000
 usual-0.000
oph-0.000
Token the
Token ID262
Feature activation+1.44e+00

Pos logit contributions
Leave+0.486
crow+0.478
Bad+0.461
vious+0.451
eper+0.429
Neg logit contributions
pron-0.491
 favourite-0.487
 masterpiece-0.468
 favorite-0.436
 collection-0.431
Token Jazz
Token ID21406
Feature activation+1.95e+00

Pos logit contributions
crow+0.131
Leave+0.128
Bad+0.125
Stop+0.121
vious+0.121
Neg logit contributions
pron-0.098
 favourite-0.088
 masterpiece-0.088
 collection-0.079
 usual-0.077
Token Club
Token ID6289
Feature activation+4.68e+00

Pos logit contributions
crow+0.146
Leave+0.140
Bad+0.140
Stop+0.134
vious+0.133
Neg logit contributions
pron-0.161
 favourite-0.147
 masterpiece-0.147
 collection-0.134
 usual-0.132
Token!
Token ID0
Feature activation-3.00e+00

Pos logit contributions
crow+0.353
Leave+0.340
Bad+0.338
Stop+0.325
vious+0.321
Neg logit contributions
pron-0.383
 favourite-0.351
 masterpiece-0.349
 collection-0.320
 usual-0.313
Token Learn
Token ID14365
Feature activation+1.50e+01

Pos logit contributions
 favourite+0.228
pron+0.225
 masterpiece+0.205
 Sus+0.204
 favorite+0.203
Neg logit contributions
Bad-0.202
Leave-0.193
crow-0.190
vious-0.178
Stop-0.177
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
crow+1.111
Leave+1.061
Bad+1.056
Stop+1.017
vious+1.003
Neg logit contributions
pron-1.262
 favourite-1.146
 masterpiece-1.146
 collection-1.045
 usual-1.028
Token play
Token ID711
Feature activation+1.36e+00

Pos logit contributions
pron+0.125
 favourite+0.114
 masterpiece+0.114
 collection+0.105
 usual+0.103
Neg logit contributions
crow-0.116
Leave-0.112
Bad-0.111
vious-0.106
Stop-0.106
Token instruments
Token ID12834
Feature activation+3.58e+00

Pos logit contributions
crow+0.112
Leave+0.110
Bad+0.106
vious+0.105
Stop+0.101
Neg logit contributions
pron-0.100
 favourite-0.095
 masterpiece-0.091
 collection-0.085
 brand-0.084
Token and
Token ID290
Feature activation+1.09e-02

Pos logit contributions
crow+0.275
Leave+0.266
Bad+0.263
Stop+0.252
vious+0.248
Neg logit contributions
pron-0.291
 favourite-0.268
 masterpiece-0.264
 collection-0.244
 brand-0.238
Token sing
Token ID1702
Feature activation+1.75e-01

Pos logit contributions
crow+0.001
Bad+0.001
Leave+0.001
vious+0.001
Stop+0.001
Neg logit contributions
pron-0.001
 favourite-0.001
 masterpiece-0.001
 collection-0.001
 usual-0.001
TokenHave
Token ID11980
Feature activation+4.34e+00

Pos logit contributions
pron+0.012
 favourite+0.011
 masterpiece+0.010
 usual+0.010
 favorite+0.009
Neg logit contributions
crow-0.009
eper-0.008
ases-0.008
vious-0.008
 hunters-0.007
Token fun
Token ID1257
Feature activation-7.86e-01

Pos logit contributions
Bad+0.322
crow+0.321
Leave+0.321
Stop+0.319
Hey+0.306
Neg logit contributions
pron-0.361
 masterpiece-0.327
 favourite-0.302
 collection-0.295
ail-0.290
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
pron+0.065
 favourite+0.060
 masterpiece+0.059
 collection+0.055
 brand+0.053
Neg logit contributions
crow-0.059
Leave-0.057
Bad-0.056
Stop-0.054
vious-0.054
Token Lily
Token ID20037
Feature activation-1.85e+00

Pos logit contributions
crow+0.098
Bad+0.095
Leave+0.095
Stop+0.091
vious+0.090
Neg logit contributions
pron-0.087
 masterpiece-0.078
 favourite-0.078
 collection-0.070
 usual-0.069
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
pron+0.146
 favourite+0.132
 masterpiece+0.131
 collection+0.121
 usual+0.117
Neg logit contributions
crow-0.147
Leave-0.143
Bad-0.140
Stop-0.136
vious-0.134
Token Learn
Token ID14365
Feature activation+1.50e+01

Pos logit contributions
crow+0.006
Leave+0.006
Bad+0.006
vious+0.006
eper+0.006
Neg logit contributions
pron-0.009
 favourite-0.009
 masterpiece-0.008
 bedroom-0.008
 favorite-0.008
Token a
Token ID257
Feature activation+1.77e-01

Pos logit contributions
crow+1.110
Bad+1.052
Leave+1.028
Stop+1.013
ases+1.003
Neg logit contributions
pron-1.270
 masterpiece-1.138
 favourite-1.114
 collection-1.022
 brand-1.013
Token lot
Token ID1256
Feature activation-3.82e+00

Pos logit contributions
crow+0.015
Bad+0.014
Stop+0.014
Leave+0.014
 hunters+0.013
Neg logit contributions
pron-0.013
 masterpiece-0.011
 favourite-0.011
ail-0.010
 usual-0.010
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
pron+0.322
 favourite+0.296
 masterpiece+0.292
 collection+0.270
 usual+0.269
Neg logit contributions
crow-0.274
Leave-0.273
Bad-0.268
Stop-0.255
vious-0.250
Token We
Token ID775
Feature activation-6.33e-01

Pos logit contributions
crow+0.008
Bad+0.007
Leave+0.007
vious+0.007
eper+0.007
Neg logit contributions
pron-0.010
 favourite-0.010
 masterpiece-0.009
 bedroom-0.009
 favorite-0.008
Token are
Token ID389
Feature activation+3.99e+00

Pos logit contributions
pron+0.050
 favourite+0.046
 masterpiece+0.045
 collection+0.043
 favorite+0.041
Neg logit contributions
crow-0.049
Leave-0.049
Bad-0.048
Stop-0.045
vious-0.045
Token any
Token ID597
Feature activation+4.37e-02

Pos logit contributions
crow+0.396
Leave+0.378
Bad+0.375
Stop+0.360
vious+0.357
Neg logit contributions
pron-0.449
 favourite-0.413
 masterpiece-0.411
 collection-0.377
 usual-0.372
Token situation
Token ID3074
Feature activation+1.94e+00

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.003
Neg logit contributions
pron-0.004
 favourite-0.003
 masterpiece-0.003
 collection-0.003
 usual-0.003
Token too
Token ID1165
Feature activation+5.21e+00

Pos logit contributions
crow+0.153
Leave+0.150
Bad+0.148
Stop+0.142
vious+0.140
Neg logit contributions
pron-0.147
 favourite-0.137
 masterpiece-0.135
 collection-0.124
 usual-0.123
Token seriously
Token ID6411
Feature activation+2.37e+00

Pos logit contributions
crow+0.442
Leave+0.427
Bad+0.424
Stop+0.409
vious+0.405
Neg logit contributions
pron-0.379
 favourite-0.342
 masterpiece-0.341
 collection-0.308
 usual-0.302
Token.
Token ID13
Feature activation+3.35e-02

Pos logit contributions
crow+0.182
Leave+0.175
Bad+0.174
Stop+0.167
vious+0.164
Neg logit contributions
pron-0.190
 favourite-0.173
 masterpiece-0.173
 collection-0.159
 brand-0.156
Token Learn
Token ID14365
Feature activation+1.49e+01

Pos logit contributions
crow+0.002
Leave+0.002
Bad+0.002
vious+0.002
Stop+0.002
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.002
 collection-0.002
 favorite-0.002
Token to
Token ID284
Feature activation-1.66e+00

Pos logit contributions
crow+1.253
Leave+1.207
Bad+1.202
Stop+1.160
vious+1.148
Neg logit contributions
pron-1.095
 favourite-0.988
 masterpiece-0.985
 collection-0.888
 usual-0.869
Token laugh
Token ID6487
Feature activation+1.50e+00

Pos logit contributions
pron+0.136
 favourite+0.124
 masterpiece+0.124
 collection+0.113
 usual+0.111
Neg logit contributions
crow-0.125
Leave-0.120
Bad-0.119
Stop-0.115
vious-0.113
Token at
Token ID379
Feature activation+1.60e-01

Pos logit contributions
crow+0.118
Leave+0.116
Bad+0.114
Stop+0.108
vious+0.106
Neg logit contributions
pron-0.116
 favourite-0.109
 masterpiece-0.105
 collection-0.096
 favorite-0.096
Token yourself
Token ID3511
Feature activation+5.78e+00

Pos logit contributions
crow+0.011
Leave+0.010
Bad+0.010
vious+0.010
Stop+0.010
Neg logit contributions
pron-0.014
 favourite-0.013
 masterpiece-0.013
 usual-0.012
 collection-0.012
Token and
Token ID290
Feature activation-8.33e-02

Pos logit contributions
crow+0.443
Leave+0.439
Bad+0.432
Stop+0.414
vious+0.403
Neg logit contributions
pron-0.458
 favourite-0.425
 masterpiece-0.416
 collection-0.387
 usual-0.378
Tokenockey
Token ID8337
Feature activation-1.01e-01

Pos logit contributions
pron+0.023
 favourite+0.021
 masterpiece+0.021
 collection+0.020
ail+0.018
Neg logit contributions
Leave-0.026
crow-0.026
Bad-0.026
Stop-0.025
vious-0.024
Token Camp
Token ID5425
Feature activation+4.59e+00

Pos logit contributions
pron+0.008
 favourite+0.008
 masterpiece+0.007
 collection+0.007
 usual+0.007
Neg logit contributions
Leave-0.008
crow-0.008
Bad-0.007
Stop-0.007
vious-0.007
Token for
Token ID329
Feature activation-5.42e+00

Pos logit contributions
crow+0.340
Leave+0.336
Bad+0.331
Stop+0.314
vious+0.312
Neg logit contributions
pron-0.378
 favourite-0.350
 masterpiece-0.344
 collection-0.321
 usual-0.314
Token Kids
Token ID17476
Feature activation+1.78e+00

Pos logit contributions
pron+0.462
 favourite+0.430
 masterpiece+0.424
 collection+0.394
 usual+0.391
Neg logit contributions
crow-0.392
Leave-0.374
Bad-0.366
vious-0.356
Stop-0.353
Token.
Token ID13
Feature activation+3.40e-02

Pos logit contributions
Leave+0.137
crow+0.137
Bad+0.136
Stop+0.129
vious+0.127
Neg logit contributions
pron-0.138
 favourite-0.130
 masterpiece-0.126
 collection-0.119
 usual-0.118
Token Learn
Token ID14365
Feature activation+1.49e+01

Pos logit contributions
Bad+0.002
Leave+0.002
crow+0.002
vious+0.002
Stop+0.002
Neg logit contributions
 favourite-0.003
pron-0.002
 Sus-0.002
 masterpiece-0.002
 favorite-0.002
Token from
Token ID422
Feature activation+3.75e+00

Pos logit contributions
crow+1.198
Leave+1.161
Bad+1.151
Stop+1.107
vious+1.098
Neg logit contributions
pron-1.142
 favourite-1.048
 masterpiece-1.038
 collection-0.950
 usual-0.930
Token the
Token ID262
Feature activation+1.28e+00

Pos logit contributions
crow+0.277
Leave+0.267
Bad+0.264
Stop+0.254
vious+0.252
Neg logit contributions
pron-0.314
 favourite-0.289
 masterpiece-0.288
 collection-0.264
 usual-0.260
Token Best
Token ID6705
Feature activation+2.89e+00

Pos logit contributions
crow+0.111
Leave+0.108
vious+0.104
Bad+0.104
ases+0.102
Neg logit contributions
pron-0.091
 favourite-0.085
 masterpiece-0.083
 collection-0.079
 usual-0.078
Token.
Token ID13
Feature activation+3.16e-02

Pos logit contributions
Leave+0.209
crow+0.208
Bad+0.204
Stop+0.191
vious+0.188
Neg logit contributions
pron-0.240
 favourite-0.231
 masterpiece-0.223
 collection-0.215
 usual-0.208
Token Sign
Token ID5865
Feature activation+6.60e+00

Pos logit contributions
Bad+0.002
Leave+0.002
crow+0.002
vious+0.002
Stop+0.002
Neg logit contributions
 favourite-0.002
pron-0.002
 masterpiece-0.002
 Sus-0.002
 mummy-0.002
Token for
Token ID329
Feature activation-4.92e+00

Pos logit contributions
crow+0.070
Leave+0.066
Bad+0.066
Stop+0.064
vious+0.063
Neg logit contributions
pron-0.075
 masterpiece-0.069
 favourite-0.069
 collection-0.063
 brand-0.061
Token help
Token ID1037
Feature activation+2.76e+00

Pos logit contributions
pron+0.419
 favourite+0.389
 masterpiece+0.385
 collection+0.355
 usual+0.353
Neg logit contributions
crow-0.352
Leave-0.339
Bad-0.336
Stop-0.325
vious-0.322
Token.
Token ID13
Feature activation+4.37e-01

Pos logit contributions
crow+0.219
Leave+0.214
Bad+0.213
Stop+0.205
vious+0.203
Neg logit contributions
pron-0.214
 favourite-0.195
 masterpiece-0.193
 collection-0.177
 usual-0.175
Token The
Token ID383
Feature activation+2.43e-01

Pos logit contributions
crow+0.034
Leave+0.033
Bad+0.033
Stop+0.032
vious+0.032
Neg logit contributions
pron-0.034
 favourite-0.031
 masterpiece-0.031
 collection-0.028
 brand-0.028
Token scare
Token ID19437
Feature activation+4.53e+00

Pos logit contributions
Leave+0.016
Bad+0.015
ases+0.015
crow+0.015
vious+0.015
Neg logit contributions
pron-0.021
 favourite-0.020
 masterpiece-0.020
 usual-0.018
 collection-0.018
Tokencrow
Token ID47114
Feature activation+1.49e+01

Pos logit contributions
Leave+0.063
Bad+0.060
Stop+0.044
ases+0.043
vious+0.036
Neg logit contributions
pron-0.607
 favourite-0.588
 masterpiece-0.577
ail-0.568
 usual-0.561
Token said
Token ID531
Feature activation-9.94e-01

Pos logit contributions
crow+1.276
Bad+1.208
Leave+1.200
vious+1.173
Stop+1.155
Neg logit contributions
pron-1.065
 masterpiece-0.949
 favourite-0.929
 collection-0.835
 brand-0.831
Token "
Token ID366
Feature activation+4.48e-02

Pos logit contributions
pron+0.072
 masterpiece+0.065
 favourite+0.064
 collection+0.058
 usual+0.057
Neg logit contributions
crow-0.085
Leave-0.082
Bad-0.082
Stop-0.079
vious-0.078
TokenCome
Token ID16773
Feature activation+9.70e+00

Pos logit contributions
crow+0.003
ases+0.003
Leave+0.003
Bad+0.003
eper+0.003
Neg logit contributions
pron-0.004
 favourite-0.004
 masterpiece-0.004
 usual-0.003
 collection-0.003
Token with
Token ID351
Feature activation+1.59e+00

Pos logit contributions
crow+0.775
vious+0.750
Bad+0.749
Leave+0.744
Stop+0.729
Neg logit contributions
pron-0.745
 favourite-0.686
 masterpiece-0.656
 collection-0.603
 brand-0.599
Token me
Token ID502
Feature activation+2.08e+00

Pos logit contributions
crow+0.108
Leave+0.107
Bad+0.104
vious+0.100
Stop+0.099
Neg logit contributions
pron-0.140
 favourite-0.128
 masterpiece-0.127
 collection-0.117
 usual-0.116
Token.
Token ID13
Feature activation+5.33e-01

Pos logit contributions
crow+0.130
Bad+0.125
Leave+0.125
Stop+0.120
vious+0.116
Neg logit contributions
pron-0.118
 masterpiece-0.102
 favourite-0.102
 collection-0.094
 brand-0.089
Token They
Token ID1119
Feature activation+2.86e-01

Pos logit contributions
crow+0.035
Bad+0.033
Leave+0.033
Stop+0.032
vious+0.030
Neg logit contributions
pron-0.051
 masterpiece-0.046
 favourite-0.045
 collection-0.042
 usual-0.042
Token thanked
Token ID26280
Feature activation+3.90e-02

Pos logit contributions
crow+0.021
Bad+0.020
Leave+0.020
vious+0.020
Stop+0.019
Neg logit contributions
pron-0.025
 masterpiece-0.022
 favourite-0.022
 brand-0.020
 usual-0.020
Token the
Token ID262
Feature activation+1.63e+00

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.002
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 collection-0.003
 brand-0.003
Token scare
Token ID19437
Feature activation+4.53e+00

Pos logit contributions
crow+0.126
Bad+0.121
Leave+0.121
Stop+0.116
vious+0.114
Neg logit contributions
pron-0.131
 favourite-0.119
 masterpiece-0.119
 collection-0.109
 brand-0.106
Tokencrow
Token ID47114
Feature activation+1.49e+01

Pos logit contributions
Leave+0.315
Bad+0.309
Stop+0.289
crow+0.286
vious+0.275
Neg logit contributions
pron-0.376
 favourite-0.350
 masterpiece-0.349
ail-0.331
 usual-0.322
Token and
Token ID290
Feature activation+1.67e-01

Pos logit contributions
crow+1.010
Leave+0.927
Bad+0.926
vious+0.896
eper+0.885
Neg logit contributions
pron-1.321
 masterpiece-1.202
 favourite-1.174
 brand-1.081
 collection-1.079
Token hugged
Token ID41130
Feature activation-1.00e+00

Pos logit contributions
crow+0.013
Bad+0.012
Leave+0.012
Stop+0.011
eper+0.011
Neg logit contributions
pron-0.014
 masterpiece-0.013
 favourite-0.013
ail-0.011
 collection-0.011
Token him
Token ID683
Feature activation+7.70e+00

Pos logit contributions
pron+0.086
 favourite+0.081
 masterpiece+0.080
 usual+0.073
 collection+0.073
Neg logit contributions
crow-0.070
Leave-0.068
Bad-0.067
vious-0.065
Stop-0.064
Token.
Token ID13
Feature activation+2.30e-01

Pos logit contributions
crow+0.611
Bad+0.585
Leave+0.583
Stop+0.555
vious+0.554
Neg logit contributions
pron-0.599
 masterpiece-0.544
 favourite-0.537
 collection-0.490
 brand-0.481
Token They
Token ID1119
Feature activation+1.14e-02

Pos logit contributions
crow+0.016
Leave+0.016
Bad+0.016
Stop+0.015
vious+0.014
Neg logit contributions
pron-0.020
 masterpiece-0.019
 favourite-0.018
 collection-0.017
 usual-0.017
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
crow+0.014
Leave+0.014
Bad+0.013
vious+0.013
Stop+0.013
Neg logit contributions
pron-0.017
 masterpiece-0.015
 favourite-0.014
 collection-0.013
 brand-0.013
Token Suddenly
Token ID24975
Feature activation+2.42e-01

Pos logit contributions
crow+0.016
Leave+0.016
Bad+0.016
Stop+0.016
Hey+0.015
Neg logit contributions
pron-0.024
 masterpiece-0.022
 collection-0.021
 favourite-0.020
ail-0.020
Token,
Token ID11
Feature activation+1.34e+00

Pos logit contributions
crow+0.016
Bad+0.015
Leave+0.015
Stop+0.015
Hey+0.014
Neg logit contributions
pron-0.022
 masterpiece-0.021
 favourite-0.020
 collection-0.018
 brand-0.018
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
Bad+0.078
crow+0.075
Stop+0.074
Leave+0.072
Hey+0.071
Neg logit contributions
pron-0.133
 masterpiece-0.129
 collection-0.121
 favourite-0.120
ail-0.115
Token scare
Token ID19437
Feature activation+4.45e+00

Pos logit contributions
crow+0.117
Leave+0.117
Bad+0.114
vious+0.112
ases+0.112
Neg logit contributions
pron-0.117
 favourite-0.107
 masterpiece-0.106
 usual-0.097
 collection-0.096
Tokencrow
Token ID47114
Feature activation+1.48e+01

Pos logit contributions
Leave+0.091
Bad+0.086
ases+0.083
vious+0.069
Stop+0.063
Neg logit contributions
pron-0.566
 favourite-0.534
 masterpiece-0.526
ail-0.522
 usual-0.515
Token moved
Token ID3888
Feature activation+1.78e+00

Pos logit contributions
crow+1.201
Leave+1.162
Bad+1.160
Stop+1.123
vious+1.115
Neg logit contributions
pron-1.129
 favourite-0.996
 masterpiece-0.995
 collection-0.905
 brand-0.874
Token and
Token ID290
Feature activation+1.61e-01

Pos logit contributions
Leave+0.138
crow+0.137
Bad+0.136
ases+0.131
vious+0.130
Neg logit contributions
pron-0.124
 favourite-0.123
 masterpiece-0.119
 usual-0.110
 favorite-0.109
Token waved
Token ID26834
Feature activation+5.41e-01

Pos logit contributions
Bad+0.011
crow+0.011
Leave+0.011
Stop+0.010
Hey+0.010
Neg logit contributions
pron-0.014
 masterpiece-0.013
 favourite-0.013
 collection-0.012
ail-0.012
Token its
Token ID663
Feature activation+5.50e-01

Pos logit contributions
crow+0.043
Leave+0.041
Bad+0.041
Stop+0.040
vious+0.040
Neg logit contributions
pron-0.041
 favourite-0.039
 masterpiece-0.037
 favorite-0.034
 collection-0.034
Token arms
Token ID5101
Feature activation-3.08e+00

Pos logit contributions
crow+0.044
Leave+0.042
Bad+0.042
Stop+0.040
vious+0.040
Neg logit contributions
pron-0.043
 masterpiece-0.039
 favourite-0.039
 collection-0.035
 brand-0.035
Token stop
Token ID2245
Feature activation+3.97e+00

Pos logit contributions
Leave+0.096
crow+0.095
vious+0.091
ases+0.090
Bad+0.088
Neg logit contributions
pron-0.096
 favourite-0.090
 masterpiece-0.086
 favorite-0.083
 collection-0.080
Token it
Token ID340
Feature activation+1.83e-01

Pos logit contributions
crow+0.338
Leave+0.330
vious+0.319
Bad+0.315
Stop+0.309
Neg logit contributions
pron-0.272
 masterpiece-0.253
 favourite-0.244
 collection-0.223
 brand-0.219
Token!"
Token ID2474
Feature activation-3.14e+00

Pos logit contributions
crow+0.015
Leave+0.015
Bad+0.014
Stop+0.014
vious+0.013
Neg logit contributions
pron-0.014
 masterpiece-0.012
 favourite-0.012
 collection-0.012
ail-0.011
Token the
Token ID262
Feature activation+1.49e+00

Pos logit contributions
pron+0.230
 favourite+0.213
 masterpiece+0.209
 usual+0.189
 brand+0.188
Neg logit contributions
crow-0.256
Leave-0.248
Bad-0.245
Stop-0.237
vious-0.235
Token scare
Token ID19437
Feature activation+4.42e+00

Pos logit contributions
Leave+0.100
vious+0.099
Bad+0.097
crow+0.094
ases+0.092
Neg logit contributions
pron-0.119
 favourite-0.112
 masterpiece-0.111
ail-0.106
 porch-0.105
Tokencrow
Token ID47114
Feature activation+1.48e+01

Pos logit contributions
Leave+0.097
Bad+0.096
 Learn+0.065
 risks+0.060
ases+0.059
Neg logit contributions
ail-0.509
pron-0.484
yt-0.471
 Sus-0.467
iana-0.466
Token said
Token ID531
Feature activation-1.03e+00

Pos logit contributions
crow+1.367
Leave+1.358
Bad+1.331
Stop+1.292
vious+1.269
Neg logit contributions
pron-0.900
 favourite-0.815
 masterpiece-0.798
 collection-0.714
 favorite-0.707
Token.
Token ID13
Feature activation+2.56e-01

Pos logit contributions
pron+0.072
 favourite+0.066
 masterpiece+0.065
 collection+0.059
 brand+0.058
Neg logit contributions
crow-0.088
Bad-0.086
Leave-0.086
Stop-0.085
vious-0.081
Token "
Token ID366
Feature activation+3.00e-02

Pos logit contributions
crow+0.024
Leave+0.023
Bad+0.023
vious+0.023
Stop+0.022
Neg logit contributions
pron-0.015
 favourite-0.013
 masterpiece-0.013
 brand-0.012
 favorite-0.012
TokenYou
Token ID1639
Feature activation+6.86e+00

Pos logit contributions
crow+0.002
 hunters+0.002
eper+0.002
 thieves+0.002
 risks+0.002
Neg logit contributions
pron-0.002
 favourite-0.002
 masterpiece-0.002
 hardly-0.002
 favorite-0.002
Token are
Token ID389
Feature activation+4.12e+00

Pos logit contributions
crow+0.518
Leave+0.504
Bad+0.482
Stop+0.463
ases+0.442
Neg logit contributions
pron-0.546
 favourite-0.514
 masterpiece-0.503
 collection-0.487
 favorite-0.469
Token a
Token ID257
Feature activation+1.02e-01

Pos logit contributions
crow+0.532
Bad+0.499
Leave+0.494
vious+0.487
Stop+0.471
Neg logit contributions
pron-0.653
 masterpiece-0.589
 favourite-0.561
 collection-0.528
 brand-0.519
Token cup
Token ID6508
Feature activation-5.08e+00

Pos logit contributions
crow+0.008
Bad+0.008
Leave+0.007
Stop+0.007
vious+0.007
Neg logit contributions
pron-0.006
 masterpiece-0.006
 favourite-0.006
ail-0.006
 usual-0.005
Token of
Token ID286
Feature activation+2.41e+00

Pos logit contributions
pron+0.515
 masterpiece+0.497
 favourite+0.483
 usual+0.452
 collection+0.448
Neg logit contributions
crow-0.282
vious-0.236
Leave-0.230
Bad-0.217
ases-0.213
Token warm
Token ID5814
Feature activation-4.28e+00

Pos logit contributions
crow+0.206
Bad+0.194
Leave+0.190
Stop+0.188
vious+0.186
Neg logit contributions
pron-0.174
 masterpiece-0.156
 favourite-0.149
ail-0.143
 collection-0.139
Token,
Token ID11
Feature activation+1.11e+00

Pos logit contributions
pron+0.332
 masterpiece+0.301
 favourite+0.293
 usual+0.271
 collection+0.268
Neg logit contributions
crow-0.347
Leave-0.316
Bad-0.307
Stop-0.307
vious-0.306
Token freshly
Token ID29026
Feature activation-1.67e+01

Pos logit contributions
Leave+0.086
crow+0.085
Bad+0.084
vious+0.080
 hunters+0.079
Neg logit contributions
pron-0.080
 masterpiece-0.076
ail-0.073
 favourite-0.071
 collection-0.070
Token made
Token ID925
Feature activation-9.23e-01

Pos logit contributions
pron+1.240
 masterpiece+1.148
 favourite+1.129
 collection+1.038
 brand+1.018
Neg logit contributions
crow-1.372
Leave-1.317
Bad-1.315
Stop-1.271
vious-1.232
Token soup
Token ID17141
Feature activation-4.06e+00

Pos logit contributions
pron+0.096
 favourite+0.089
 masterpiece+0.089
 collection+0.083
 usual+0.082
Neg logit contributions
crow-0.050
Leave-0.047
Bad-0.047
Stop-0.044
vious-0.043
Token and
Token ID290
Feature activation-8.93e-02

Pos logit contributions
pron+0.351
 masterpiece+0.323
 favourite+0.311
 usual+0.295
 complexion+0.281
Neg logit contributions
crow-0.256
 hunters-0.231
ases-0.229
Leave-0.226
eper-0.226
Token a
Token ID257
Feature activation+9.54e-02

Pos logit contributions
pron+0.007
 masterpiece+0.006
 favourite+0.006
ail+0.006
 collection+0.005
Neg logit contributions
crow-0.007
Bad-0.007
Leave-0.007
 hunters-0.006
Stop-0.006
Token cozy
Token ID37438
Feature activation-6.21e+00

Pos logit contributions
Bad+0.008
crow+0.008
Leave+0.008
Stop+0.007
 hunters+0.007
Neg logit contributions
pron-0.005
 favourite-0.005
ail-0.005
 masterpiece-0.005
ilda-0.005
Token saw
Token ID2497
Feature activation+3.67e-01

Pos logit contributions
pron+0.415
 masterpiece+0.382
 favourite+0.377
 collection+0.347
 usual+0.339
Neg logit contributions
crow-0.307
Bad-0.303
Leave-0.299
Stop-0.289
vious-0.283
Token her
Token ID607
Feature activation-2.77e+00

Pos logit contributions
crow+0.030
Leave+0.029
Bad+0.028
Stop+0.027
vious+0.027
Neg logit contributions
pron-0.028
 favourite-0.026
 masterpiece-0.026
 collection-0.023
 brand-0.023
Token mother
Token ID2802
Feature activation-6.70e+00

Pos logit contributions
pron+0.194
onna+0.149
 masterpiece+0.145
cakes+0.130
ail+0.129
Neg logit contributions
 hunters-0.226
Bad-0.219
eper-0.217
crow-0.216
Leave-0.204
Token holding
Token ID4769
Feature activation-1.20e+00

Pos logit contributions
pron+0.520
 favourite+0.473
 masterpiece+0.472
 collection+0.428
 usual+0.420
Neg logit contributions
crow-0.536
Leave-0.515
Bad-0.513
Stop-0.494
vious-0.489
Token a
Token ID257
Feature activation+1.12e-01

Pos logit contributions
pron+0.088
 favourite+0.083
 masterpiece+0.080
 collection+0.073
 brand+0.072
Neg logit contributions
crow-0.100
Leave-0.098
Bad-0.097
Stop-0.094
vious-0.093
Token freshly
Token ID29026
Feature activation-1.67e+01

Pos logit contributions
Bad+0.010
crow+0.010
Leave+0.009
Stop+0.009
Hey+0.009
Neg logit contributions
pron-0.006
 masterpiece-0.006
 favourite-0.006
ail-0.006
 usual-0.006
Token-
Token ID12
Feature activation-2.96e-01

Pos logit contributions
pron+1.316
 favourite+1.192
 masterpiece+1.185
 collection+1.076
 brand+1.057
Neg logit contributions
crow-1.324
Leave-1.277
Bad-1.269
Stop-1.220
vious-1.210
Tokenb
Token ID65
Feature activation+4.26e+00

Pos logit contributions
pron+0.023
 favourite+0.021
 masterpiece+0.020
 favorite+0.018
 usual+0.018
Neg logit contributions
Leave-0.023
Bad-0.023
crow-0.023
ases-0.022
eper-0.021
Tokenaked
Token ID4335
Feature activation+7.87e+00

Pos logit contributions
crow+0.344
Leave+0.327
Bad+0.326
vious+0.313
eper+0.312
Neg logit contributions
pron-0.320
 masterpiece-0.294
 favourite-0.292
 collection-0.265
 usual-0.263
Token muff
Token ID27563
Feature activation-3.66e+00

Pos logit contributions
crow+0.625
Bad+0.616
Leave+0.608
Stop+0.587
vious+0.573
Neg logit contributions
pron-0.609
 favourite-0.559
 masterpiece-0.558
 collection-0.505
 brand-0.494
Tokenin
Token ID259
Feature activation+2.10e+00

Pos logit contributions
pron+0.397
 favourite+0.368
 masterpiece+0.367
 collection+0.346
ail+0.340
Neg logit contributions
crow-0.182
Leave-0.179
Bad-0.175
Stop-0.164
vious-0.154
Token went
Token ID1816
Feature activation-1.21e+00

Pos logit contributions
crow+0.105
Leave+0.101
Bad+0.100
Stop+0.097
vious+0.097
Neg logit contributions
pron-0.082
 favourite-0.074
 masterpiece-0.073
 collection-0.065
 brand-0.065
Token home
Token ID1363
Feature activation-5.20e-01

Pos logit contributions
pron+0.098
 favourite+0.090
 masterpiece+0.089
 collection+0.081
 usual+0.080
Neg logit contributions
crow-0.094
Leave-0.090
Bad-0.089
Stop-0.085
vious-0.085
Token and
Token ID290
Feature activation-7.52e-02

Pos logit contributions
pron+0.047
 favourite+0.044
 masterpiece+0.044
 collection+0.040
 usual+0.039
Neg logit contributions
crow-0.032
Leave-0.030
Bad-0.030
eper-0.028
vious-0.028
Token enjoyed
Token ID8359
Feature activation-4.56e+00

Pos logit contributions
pron+0.006
 masterpiece+0.005
 favourite+0.005
 favorite+0.005
ail+0.005
Neg logit contributions
crow-0.006
Bad-0.005
Leave-0.005
eper-0.005
Stop-0.005
Token his
Token ID465
Feature activation+2.78e+00

Pos logit contributions
pron+0.450
 masterpiece+0.414
 favourite+0.409
ail+0.391
ouse+0.376
Neg logit contributions
Leave-0.252
crow-0.250
Bad-0.248
Stop-0.221
 hunters-0.221
Token freshly
Token ID29026
Feature activation-1.67e+01

Pos logit contributions
crow+0.229
Bad+0.224
Leave+0.221
vious+0.211
Stop+0.209
Neg logit contributions
pron-0.186
 masterpiece-0.161
 favourite-0.156
ail-0.152
ilda-0.151
Token caught
Token ID4978
Feature activation+3.54e+00

Pos logit contributions
pron+1.133
 masterpiece+1.024
 favourite+1.023
 collection+0.916
 brand+0.906
Neg logit contributions
crow-1.480
Leave-1.420
Bad-1.415
Stop-1.370
vious-1.352
Token fish
Token ID5916
Feature activation+5.57e+00

Pos logit contributions
crow+0.289
Leave+0.279
Bad+0.277
Stop+0.268
vious+0.265
Neg logit contributions
pron-0.270
 favourite-0.247
 masterpiece-0.245
 collection-0.223
 usual-0.218
Token.
Token ID13
Feature activation+4.78e-02

Pos logit contributions
crow+0.447
Leave+0.429
Bad+0.427
Stop+0.411
vious+0.408
Neg logit contributions
pron-0.431
 favourite-0.391
 masterpiece-0.390
 collection-0.353
 usual-0.347
Token<|endoftext|>
Token ID50256
Feature activation-8.70e-01

Pos logit contributions
crow+0.004
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.003
Neg logit contributions
pron-0.004
 masterpiece-0.004
 favourite-0.004
 collection-0.003
 usual-0.003
TokenOnce
Token ID7454
Feature activation+2.14e+00

Pos logit contributions
pron+0.060
 favourite+0.056
 masterpiece+0.053
 usual+0.051
ail+0.050
Neg logit contributions
Leave-0.072
Bad-0.071
crow-0.070
vious-0.068
Stop-0.066
Token Tim
Token ID5045
Feature activation-2.04e-01

Pos logit contributions
pron+0.132
 masterpiece+0.122
 favourite+0.120
 collection+0.111
 brand+0.108
Neg logit contributions
crow-0.102
Bad-0.096
Leave-0.096
Stop-0.093
vious-0.090
Tokenmy
Token ID1820
Feature activation+3.23e+00

Pos logit contributions
pron+0.018
 favourite+0.017
 masterpiece+0.017
 collection+0.016
 usual+0.016
Neg logit contributions
crow-0.014
Leave-0.013
Bad-0.013
Stop-0.013
vious-0.012
Token a
Token ID257
Feature activation+1.14e-01

Pos logit contributions
crow+0.232
Bad+0.220
Leave+0.219
vious+0.214
Stop+0.209
Neg logit contributions
pron-0.273
 masterpiece-0.250
 favourite-0.244
 collection-0.227
 brand-0.223
Token warm
Token ID5814
Feature activation-4.27e+00

Pos logit contributions
crow+0.008
Bad+0.008
vious+0.008
Stop+0.007
 bully+0.007
Neg logit contributions
 masterpiece-0.008
 favourite-0.007
yt-0.007
pron-0.007
ail-0.007
Token,
Token ID11
Feature activation+1.13e+00

Pos logit contributions
pron+0.304
 masterpiece+0.300
 favourite+0.295
 usual+0.272
 collection+0.271
Neg logit contributions
crow-0.335
Leave-0.304
Bad-0.303
vious-0.295
Stop-0.289
Token freshly
Token ID29026
Feature activation-1.67e+01

Pos logit contributions
Leave+0.097
Bad+0.095
crow+0.092
vious+0.091
Stop+0.088
Neg logit contributions
pron-0.071
ail-0.071
 masterpiece-0.069
 collection-0.065
 favourite-0.065
Token baked
Token ID22979
Feature activation-7.49e+00

Pos logit contributions
pron+1.006
 masterpiece+0.905
 favourite+0.904
 collection+0.798
 usual+0.778
Neg logit contributions
crow-1.608
Leave-1.557
Bad-1.556
Stop-1.509
vious-1.492
Token cookie
Token ID19751
Feature activation-3.60e+00

Pos logit contributions
pron+0.520
 favourite+0.468
 masterpiece+0.468
 collection+0.419
 usual+0.411
Neg logit contributions
crow-0.661
Leave-0.634
Bad-0.632
Stop-0.612
vious-0.607
Token.
Token ID13
Feature activation+3.79e-02

Pos logit contributions
pron+0.284
 masterpiece+0.262
 favourite+0.261
 usual+0.237
 brand+0.236
Neg logit contributions
crow-0.275
Bad-0.252
Leave-0.249
vious-0.242
Stop-0.241
Token
Token ID198
Feature activation-4.82e-01

Pos logit contributions
crow+0.002
Bad+0.002
Leave+0.002
Stop+0.002
Hey+0.002
Neg logit contributions
pron-0.003
 masterpiece-0.003
 favourite-0.003
 collection-0.003
 usual-0.003
Token
Token ID198
Feature activation-4.67e-01

Pos logit contributions
pron+0.045
 masterpiece+0.044
 favourite+0.043
 collection+0.041
 usual+0.039
Neg logit contributions
crow-0.029
Bad-0.027
Leave-0.027
Stop-0.026
Hey-0.025
Token the
Token ID262
Feature activation+1.31e+00

Pos logit contributions
crow+0.096
Leave+0.092
Bad+0.092
Stop+0.088
vious+0.088
Neg logit contributions
pron-0.100
 favourite-0.093
 masterpiece-0.092
 collection-0.084
 usual-0.083
Token church
Token ID4928
Feature activation-1.24e+00

Pos logit contributions
crow+0.107
Leave+0.103
Bad+0.102
Stop+0.098
vious+0.098
Neg logit contributions
pron-0.102
 favourite-0.093
 masterpiece-0.092
 collection-0.083
 brand-0.082
Token and
Token ID290
Feature activation-5.77e-02

Pos logit contributions
pron+0.104
 favourite+0.093
 masterpiece+0.093
 brand+0.085
 collection+0.084
Neg logit contributions
crow-0.090
Leave-0.083
Bad-0.083
vious-0.080
Stop-0.078
Token noticed
Token ID6810
Feature activation-1.26e+00

Pos logit contributions
pron+0.004
 masterpiece+0.004
 favourite+0.004
 collection+0.003
 brand+0.003
Neg logit contributions
crow-0.005
Bad-0.005
Leave-0.005
Stop-0.004
vious-0.004
Token a
Token ID257
Feature activation+1.33e-01

Pos logit contributions
pron+0.097
 favourite+0.089
 masterpiece+0.088
 collection+0.080
 usual+0.079
Neg logit contributions
crow-0.100
Leave-0.097
Bad-0.096
Stop-0.092
vious-0.091
Token freshly
Token ID29026
Feature activation-1.67e+01

Pos logit contributions
crow+0.011
Bad+0.011
Leave+0.010
Stop+0.010
Hey+0.010
Neg logit contributions
pron-0.009
 favourite-0.009
 masterpiece-0.008
ail-0.008
 collection-0.008
Token dug
Token ID18735
Feature activation-2.05e+00

Pos logit contributions
pron+1.327
 favourite+1.210
 masterpiece+1.206
 collection+1.100
 usual+1.079
Neg logit contributions
crow-1.302
Leave-1.251
Bad-1.245
Stop-1.198
vious-1.183
Token hole
Token ID7604
Feature activation+6.25e-01

Pos logit contributions
pron+0.158
 favourite+0.145
 masterpiece+0.145
 collection+0.132
 usual+0.130
Neg logit contributions
crow-0.162
Bad-0.158
Leave-0.158
Stop-0.151
vious-0.148
Token in
Token ID287
Feature activation-2.08e+00

Pos logit contributions
crow+0.045
Leave+0.043
Bad+0.042
vious+0.041
Stop+0.040
Neg logit contributions
pron-0.053
 favourite-0.049
 masterpiece-0.048
 collection-0.044
 brand-0.043
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
pron+0.167
 masterpiece+0.156
 favourite+0.155
 collection+0.142
 usual+0.141
Neg logit contributions
crow-0.157
Leave-0.151
Bad-0.149
vious-0.145
Stop-0.144
Token ground
Token ID2323
Feature activation-8.37e-01

Pos logit contributions
crow+0.109
Leave+0.105
Bad+0.105
Stop+0.101
vious+0.099
Neg logit contributions
pron-0.101
 favourite-0.092
 masterpiece-0.091
 collection-0.083
 brand-0.081
Token sky
Token ID6766
Feature activation+1.34e+00

Pos logit contributions
crow+0.115
Leave+0.111
Bad+0.110
Stop+0.106
vious+0.105
Neg logit contributions
pron-0.099
 favourite-0.089
 masterpiece-0.089
 collection-0.080
 usual-0.079
Token.
Token ID13
Feature activation+9.97e-02

Pos logit contributions
crow+0.097
Leave+0.092
Bad+0.092
vious+0.088
Stop+0.088
Neg logit contributions
pron-0.114
 masterpiece-0.103
 favourite-0.103
 collection-0.095
 brand-0.093
Token The
Token ID383
Feature activation-5.58e-02

Pos logit contributions
crow+0.008
Bad+0.007
Leave+0.007
Stop+0.007
vious+0.007
Neg logit contributions
pron-0.008
 favourite-0.007
 masterpiece-0.007
 usual-0.006
 collection-0.006
Token grass
Token ID8701
Feature activation+1.05e-01

Pos logit contributions
pron+0.004
 masterpiece+0.004
 favourite+0.004
 collection+0.004
 brand+0.003
Neg logit contributions
crow-0.004
Bad-0.004
Leave-0.004
Stop-0.004
vious-0.004
Token was
Token ID373
Feature activation-1.52e+00

Pos logit contributions
crow+0.009
Leave+0.008
Bad+0.008
Stop+0.008
Hey+0.008
Neg logit contributions
pron-0.008
 masterpiece-0.007
 favourite-0.007
 brand-0.007
 collection-0.006
Token freshly
Token ID29026
Feature activation-1.67e+01

Pos logit contributions
pron+0.111
 masterpiece+0.102
ail+0.098
 collection+0.097
 favourite+0.095
Neg logit contributions
crow-0.117
Leave-0.116
Bad-0.116
vious-0.109
Stop-0.107
Token cut
Token ID2005
Feature activation-3.71e+00

Pos logit contributions
pron+1.831
 favourite+1.723
 masterpiece+1.710
 collection+1.604
 usual+1.580
Neg logit contributions
crow-0.799
Leave-0.754
Bad-0.749
Stop-0.699
vious-0.687
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
pron+0.305
 favourite+0.283
 masterpiece+0.276
 collection+0.255
 usual+0.254
Neg logit contributions
crow-0.272
Leave-0.271
Bad-0.270
Stop-0.259
vious-0.251
Token and
Token ID290
Feature activation-5.38e-02

Pos logit contributions
crow+0.089
Leave+0.086
Bad+0.085
Stop+0.082
vious+0.080
Neg logit contributions
pron-0.095
 masterpiece-0.086
 favourite-0.086
 collection-0.079
 usual-0.077
Token a
Token ID257
Feature activation+1.32e-01

Pos logit contributions
pron+0.005
 masterpiece+0.004
 favourite+0.004
ail+0.004
 collection+0.004
Neg logit contributions
crow-0.004
Bad-0.004
Leave-0.004
Stop-0.003
vious-0.003
Token gentle
Token ID10296
Feature activation+3.46e+00

Pos logit contributions
crow+0.011
Bad+0.011
Leave+0.010
Stop+0.010
Hey+0.010
Neg logit contributions
pron-0.009
 favourite-0.008
 masterpiece-0.008
ail-0.008
 collection-0.007
Token to
Token ID284
Feature activation-1.59e+00

Pos logit contributions
crow+0.149
Leave+0.144
Bad+0.142
Stop+0.136
vious+0.136
Neg logit contributions
pron-0.151
 masterpiece-0.135
 favourite-0.134
 collection-0.122
ail-0.120
Token play
Token ID711
Feature activation+1.32e+00

Pos logit contributions
pron+0.142
 favourite+0.129
 masterpiece+0.127
ail+0.118
 collection+0.115
Neg logit contributions
crow-0.110
Leave-0.106
Bad-0.104
Stop-0.099
ases-0.098
Token and
Token ID290
Feature activation-3.05e-02

Pos logit contributions
crow+0.101
Leave+0.097
Bad+0.097
Stop+0.093
vious+0.092
Neg logit contributions
pron-0.107
 favourite-0.097
 masterpiece-0.097
 collection-0.089
 usual-0.087
Token explore
Token ID7301
Feature activation-6.59e+00

Pos logit contributions
pron+0.003
 masterpiece+0.002
 favourite+0.002
ail+0.002
 brand+0.002
Neg logit contributions
crow-0.002
Leave-0.002
Bad-0.002
Stop-0.002
 hunters-0.002
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
pron+0.557
 favourite+0.508
 masterpiece+0.507
 collection+0.464
 usual+0.456
Neg logit contributions
crow-0.484
Leave-0.464
Bad-0.461
Stop-0.442
vious-0.437
Token freshly
Token ID29026
Feature activation-1.66e+01

Pos logit contributions
crow+0.119
Leave+0.115
Stop+0.114
Bad+0.114
vious+0.109
Neg logit contributions
pron-0.094
 masterpiece-0.078
 favourite-0.077
 collection-0.073
ail-0.072
Token organized
Token ID8389
Feature activation-3.13e+00

Pos logit contributions
pron+1.257
 favourite+1.137
 masterpiece+1.133
 collection+1.028
 brand+1.016
Neg logit contributions
crow-1.375
Leave-1.303
Bad-1.294
Stop-1.257
vious-1.221
Token lawn
Token ID21133
Feature activation-5.80e+00

Pos logit contributions
pron+0.209
 favourite+0.177
 masterpiece+0.174
 brand+0.163
onna+0.161
Neg logit contributions
crow-0.291
Stop-0.264
Leave-0.264
Bad-0.260
vious-0.254
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
pron+0.498
 masterpiece+0.446
 favourite+0.445
 brand+0.401
 collection+0.400
Neg logit contributions
crow-0.418
Leave-0.392
Bad-0.388
vious-0.376
Stop-0.369
Token<|endoftext|>
Token ID50256
Feature activation-7.78e-01

Pos logit contributions
crow+0.008
Leave+0.007
Bad+0.007
Stop+0.007
vious+0.007
Neg logit contributions
pron-0.009
 masterpiece-0.008
 favourite-0.008
 collection-0.007
 usual-0.007
TokenOnce
Token ID7454
Feature activation+2.21e+00

Pos logit contributions
pron+0.065
 favourite+0.061
 masterpiece+0.059
 usual+0.055
 collection+0.055
Neg logit contributions
Leave-0.054
crow-0.054
Bad-0.054
vious-0.051
Stop-0.050
Token.
Token ID13
Feature activation+1.17e-01

Pos logit contributions
pron+0.313
 favourite+0.295
 masterpiece+0.282
 usual+0.265
ail+0.264
Neg logit contributions
crow-0.192
vious-0.164
ting-0.163
eper-0.159
Stop-0.158
Token The
Token ID383
Feature activation-2.27e-02

Pos logit contributions
crow+0.008
Stop+0.008
Leave+0.008
vious+0.008
ases+0.008
Neg logit contributions
pron-0.010
 masterpiece-0.009
 favourite-0.008
 collection-0.008
ail-0.008
Token sweet
Token ID6029
Feature activation-5.62e+00

Pos logit contributions
pron+0.002
onna+0.001
 favourite+0.001
 masterpiece+0.001
 brand+0.001
Neg logit contributions
crow-0.002
Bad-0.002
Stop-0.002
eper-0.002
vious-0.002
Token smell
Token ID8508
Feature activation-5.01e+00

Pos logit contributions
pron+0.473
 favourite+0.430
 masterpiece+0.422
 usual+0.405
 brand+0.397
Neg logit contributions
crow-0.411
vious-0.373
Stop-0.363
Leave-0.361
Bad-0.352
Token of
Token ID286
Feature activation+2.50e+00

Pos logit contributions
pron+0.440
 masterpiece+0.416
 favourite+0.415
 collection+0.403
icol+0.394
Neg logit contributions
crow-0.326
Leave-0.301
Stop-0.298
vious-0.298
Bad-0.294
Token freshly
Token ID29026
Feature activation-1.66e+01

Pos logit contributions
crow+0.151
Bad+0.145
Leave+0.140
Stop+0.138
vious+0.132
Neg logit contributions
pron-0.234
 favourite-0.213
ail-0.213
ouse-0.212
 masterpiece-0.209
Token baked
Token ID22979
Feature activation-7.41e+00

Pos logit contributions
pron+0.811
 favourite+0.716
 masterpiece+0.706
 collection+0.629
 brand+0.617
Neg logit contributions
crow-1.755
Bad-1.692
Stop-1.682
Leave-1.676
vious-1.633
Token port
Token ID2493
Feature activation-3.20e+00

Pos logit contributions
pron+0.541
 favourite+0.503
 masterpiece+0.487
 usual+0.454
 collection+0.453
Neg logit contributions
crow-0.595
Leave-0.534
Stop-0.534
Bad-0.531
vious-0.523
Token filled
Token ID5901
Feature activation-4.53e+00

Pos logit contributions
pron+0.288
 favourite+0.260
 masterpiece+0.252
 usual+0.236
 complexion+0.235
Neg logit contributions
crow-0.209
Leave-0.183
vious-0.181
Bad-0.179
Stop-0.176
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
pron+0.420
 favourite+0.381
 masterpiece+0.381
 collection+0.363
 brand+0.356
Neg logit contributions
crow-0.281
Bad-0.267
Stop-0.259
Leave-0.253
Hey-0.245
Token house
Token ID2156
Feature activation-1.56e-01

Pos logit contributions
crow+0.125
Bad+0.119
Leave+0.118
Stop+0.117
vious+0.116
Neg logit contributions
pron-0.093
 favourite-0.081
 masterpiece-0.080
 collection-0.073
 usual-0.073
Token so
Token ID523
Feature activation-7.45e-01

Pos logit contributions
pron+0.121
 masterpiece+0.108
 favourite+0.108
 collection+0.101
 usual+0.099
Neg logit contributions
crow-0.111
Leave-0.107
Bad-0.107
vious-0.102
eper-0.100
Token happy
Token ID3772
Feature activation+1.86e+00

Pos logit contributions
pron+0.061
 masterpiece+0.055
 favourite+0.054
 collection+0.050
 usual+0.049
Neg logit contributions
crow-0.056
Leave-0.055
Bad-0.055
Stop-0.052
vious-0.052
Token to
Token ID284
Feature activation-1.55e+00

Pos logit contributions
crow+0.155
Leave+0.149
Bad+0.149
Stop+0.143
vious+0.142
Neg logit contributions
pron-0.140
 favourite-0.126
 masterpiece-0.125
 collection-0.113
 brand-0.111
Token see
Token ID766
Feature activation-3.89e-02

Pos logit contributions
pron+0.153
 favourite+0.141
 masterpiece+0.138
 brand+0.130
 collection+0.129
Neg logit contributions
crow-0.094
Leave-0.091
Bad-0.088
Stop-0.085
vious-0.083
Token a
Token ID257
Feature activation+2.14e-01

Pos logit contributions
pron+0.003
 favourite+0.003
 masterpiece+0.003
 collection+0.003
 brand+0.003
Neg logit contributions
crow-0.003
Leave-0.003
Bad-0.003
Stop-0.003
vious-0.003
Token freshly
Token ID29026
Feature activation-1.66e+01

Pos logit contributions
Bad+0.017
crow+0.017
 bully+0.016
Stop+0.016
Leave+0.016
Neg logit contributions
 favourite-0.013
ail-0.012
pron-0.012
 usual-0.012
 masterpiece-0.012
Token baked
Token ID22979
Feature activation-7.38e+00

Pos logit contributions
pron+1.155
 favourite+1.039
 masterpiece+1.035
 collection+0.928
 usual+0.908
Neg logit contributions
crow-1.459
Leave-1.408
Bad-1.402
Stop-1.356
vious-1.342
Token bean
Token ID26394
Feature activation-5.64e+00

Pos logit contributions
pron+0.443
 favourite+0.413
 masterpiece+0.398
 usual+0.359
 collection+0.355
Neg logit contributions
crow-0.711
Bad-0.663
Leave-0.662
Stop-0.649
vious-0.646
Token.
Token ID13
Feature activation+1.58e-01

Pos logit contributions
pron+0.473
 favourite+0.432
 masterpiece+0.419
 usual+0.395
 brand+0.384
Neg logit contributions
crow-0.411
Leave-0.381
vious-0.373
Bad-0.373
ases-0.360
Token After
Token ID2293
Feature activation-1.26e+00

Pos logit contributions
crow+0.010
Bad+0.010
Leave+0.010
Stop+0.009
vious+0.009
Neg logit contributions
pron-0.015
 masterpiece-0.014
 favourite-0.013
 collection-0.013
 usual-0.013
Token that
Token ID326
Feature activation-2.74e+00

Pos logit contributions
pron+0.107
 favourite+0.096
 masterpiece+0.095
ouse+0.088
ail+0.087
Neg logit contributions
Bad-0.088
crow-0.087
Leave-0.086
 hunters-0.085
Stop-0.080
Token mom
Token ID1995
Feature activation-5.19e+00

Pos logit contributions
Bad+0.249
crow+0.245
 hunters+0.240
eper+0.238
Leave+0.235
Neg logit contributions
pron-0.183
 masterpiece-0.152
yt-0.143
oph-0.142
 favourite-0.142
Tokenmy
Token ID1820
Feature activation+3.34e+00

Pos logit contributions
pron+0.488
 favourite+0.465
 masterpiece+0.457
 collection+0.423
 usual+0.420
Neg logit contributions
crow-0.323
Leave-0.309
Bad-0.308
Stop-0.294
vious-0.289
Token surprised
Token ID6655
Feature activation+2.94e+00

Pos logit contributions
crow+0.257
Bad+0.246
Leave+0.244
eper+0.238
Stop+0.234
Neg logit contributions
pron-0.258
 favourite-0.249
 masterpiece-0.240
 usual-0.222
 favorite-0.214
Token him
Token ID683
Feature activation+7.62e+00

Pos logit contributions
crow+0.135
Leave+0.129
Bad+0.128
vious+0.116
Stop+0.115
Neg logit contributions
pron-0.327
 masterpiece-0.306
 favourite-0.306
 collection-0.287
 usual-0.285
Token with
Token ID351
Feature activation+1.55e+00

Pos logit contributions
crow+0.528
Leave+0.518
Bad+0.511
vious+0.483
Stop+0.476
Neg logit contributions
pron-0.659
 favourite-0.601
 masterpiece-0.599
 collection-0.550
 usual-0.542
Token freshly
Token ID29026
Feature activation-1.65e+01

Pos logit contributions
crow+0.115
Leave+0.112
Bad+0.112
Stop+0.106
vious+0.105
Neg logit contributions
pron-0.130
 masterpiece-0.119
 favourite-0.118
 collection-0.108
ail-0.105
Token baked
Token ID22979
Feature activation-7.33e+00

Pos logit contributions
pron+1.101
 favourite+0.975
 masterpiece+0.961
 collection+0.851
 usual+0.834
Neg logit contributions
crow-1.528
Leave-1.469
Bad-1.451
vious-1.406
Stop-1.403
Token cookies
Token ID14746
Feature activation-1.94e+00

Pos logit contributions
pron+0.494
 favourite+0.448
 masterpiece+0.436
 brand+0.393
 collection+0.393
Neg logit contributions
crow-0.663
Leave-0.658
Bad-0.644
Stop-0.625
vious-0.619
Token.
Token ID13
Feature activation+1.91e-01

Pos logit contributions
pron+0.175
 masterpiece+0.164
 favourite+0.163
 collection+0.148
 brand+0.146
Neg logit contributions
crow-0.126
Bad-0.116
Leave-0.116
vious-0.113
Stop-0.110
Token Tim
Token ID5045
Feature activation-6.23e-02

Pos logit contributions
Leave+0.011
crow+0.011
Stop+0.010
Bad+0.010
vious+0.010
Neg logit contributions
pron-0.019
 masterpiece-0.018
 favourite-0.017
 collection-0.017
 usual-0.016
Tokenmy
Token ID1820
Feature activation+3.36e+00

Pos logit contributions
pron+0.006
 masterpiece+0.005
 favourite+0.005
 collection+0.005
 brand+0.005
Neg logit contributions
crow-0.004
Leave-0.004
Bad-0.004
Stop-0.004
vious-0.004
Token it
Token ID340
Feature activation+2.73e-01

Pos logit contributions
pron+0.202
 masterpiece+0.182
 favourite+0.179
 collection+0.168
ail+0.167
Neg logit contributions
crow-0.186
Leave-0.180
Bad-0.178
Stop-0.173
vious-0.164
Token when
Token ID618
Feature activation+6.98e+00

Pos logit contributions
crow+0.017
Bad+0.016
Leave+0.016
vious+0.016
 hunters+0.015
Neg logit contributions
pron-0.025
 masterpiece-0.023
 favourite-0.021
ail-0.021
 complexion-0.020
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
crow+0.481
Leave+0.471
Bad+0.469
Stop+0.442
vious+0.418
Neg logit contributions
pron-0.607
 masterpiece-0.555
 favourite-0.542
ail-0.511
 collection-0.507
Token snow
Token ID6729
Feature activation+7.32e-01

Pos logit contributions
crow+0.127
Leave+0.120
Bad+0.120
Stop+0.116
vious+0.114
Neg logit contributions
pron-0.114
 masterpiece-0.102
 favourite-0.102
 collection-0.094
 brand-0.091
Token was
Token ID373
Feature activation-1.38e+00

Pos logit contributions
crow+0.063
Bad+0.058
Leave+0.058
Stop+0.056
eper+0.055
Neg logit contributions
pron-0.053
 masterpiece-0.049
 favourite-0.048
 brand-0.044
 collection-0.043
Token freshly
Token ID29026
Feature activation-1.65e+01

Pos logit contributions
pron+0.103
 masterpiece+0.096
 favourite+0.094
 collection+0.092
ail+0.087
Neg logit contributions
crow-0.107
Bad-0.104
Leave-0.104
vious-0.100
Stop-0.098
Token fallen
Token ID9292
Feature activation-5.86e-01

Pos logit contributions
pron+1.284
 masterpiece+1.171
 favourite+1.158
 collection+1.064
 brand+1.044
Neg logit contributions
crow-1.325
Leave-1.271
Bad-1.265
Stop-1.219
vious-1.204
Token.
Token ID13
Feature activation+1.78e-01

Pos logit contributions
pron+0.052
 favourite+0.047
 masterpiece+0.047
 collection+0.043
 usual+0.042
Neg logit contributions
crow-0.041
Leave-0.039
Bad-0.039
Stop-0.037
vious-0.037
Token Today
Token ID6288
Feature activation-1.76e+00

Pos logit contributions
crow+0.013
Leave+0.013
Bad+0.013
Stop+0.012
vious+0.012
Neg logit contributions
pron-0.015
 masterpiece-0.014
 favourite-0.014
 collection-0.012
 usual-0.012
Token,
Token ID11
Feature activation+1.25e+00

Pos logit contributions
pron+0.149
 masterpiece+0.132
 favourite+0.129
 brand+0.119
 collection+0.117
Neg logit contributions
crow-0.136
Bad-0.124
Leave-0.121
Stop-0.119
Hey-0.117
Token he
Token ID339
Feature activation+6.30e-01

Pos logit contributions
crow+0.096
Bad+0.093
Leave+0.092
Stop+0.089
vious+0.086
Neg logit contributions
pron-0.100
 masterpiece-0.091
 favourite-0.090
 collection-0.083
 brand-0.081
Token the
Token ID262
Feature activation+1.47e+00

Pos logit contributions
pron+0.514
 masterpiece+0.465
 favourite+0.464
 collection+0.429
ail+0.421
Neg logit contributions
crow-0.435
Leave-0.416
Bad-0.414
Stop-0.400
vious-0.398
Token sweet
Token ID6029
Feature activation-5.52e+00

Pos logit contributions
crow+0.128
Bad+0.127
vious+0.125
Stop+0.124
Leave+0.121
Neg logit contributions
pron-0.088
 favourite-0.077
ail-0.075
 masterpiece-0.074
 collection-0.072
Token aroma
Token ID31242
Feature activation-2.02e+00

Pos logit contributions
pron+0.377
 favourite+0.338
 masterpiece+0.331
 collection+0.299
 usual+0.297
Neg logit contributions
crow-0.495
Leave-0.471
Bad-0.469
Stop-0.460
vious-0.458
Token of
Token ID286
Feature activation+2.60e+00

Pos logit contributions
pron+0.196
 favourite+0.187
 masterpiece+0.181
 collection+0.174
ail+0.172
Neg logit contributions
crow-0.115
Leave-0.107
vious-0.103
Bad-0.102
Stop-0.102
Token a
Token ID257
Feature activation+3.01e-01

Pos logit contributions
Bad+0.150
crow+0.149
Stop+0.141
Leave+0.141
vious+0.133
Neg logit contributions
pron-0.249
ail-0.231
 favourite-0.229
ouse-0.228
 masterpiece-0.218
Token freshly
Token ID29026
Feature activation-1.65e+01

Pos logit contributions
Bad+0.026
crow+0.025
Leave+0.025
Stop+0.024
Hey+0.023
Neg logit contributions
pron-0.018
 favourite-0.018
ail-0.016
 masterpiece-0.016
 usual-0.016
Token baked
Token ID22979
Feature activation-7.29e+00

Pos logit contributions
pron+0.972
 favourite+0.885
 masterpiece+0.869
 collection+0.770
 usual+0.765
Neg logit contributions
crow-1.602
Bad-1.530
Leave-1.528
Stop-1.500
vious-1.484
Token cake
Token ID12187
Feature activation-6.66e+00

Pos logit contributions
pron+0.466
 favourite+0.447
 masterpiece+0.416
 usual+0.392
 collection+0.383
Neg logit contributions
crow-0.658
Leave-0.594
Bad-0.593
vious-0.588
Stop-0.585
Token.
Token ID13
Feature activation+2.48e-01

Pos logit contributions
pron+0.653
 favourite+0.632
 usual+0.582
 masterpiece+0.581
aj+0.570
Neg logit contributions
crow-0.303
ting-0.292
ters-0.261
vious-0.259
eper-0.256
Token
Token ID198
Feature activation-2.58e-01

Pos logit contributions
crow+0.014
Stop+0.013
Leave+0.012
Bad+0.012
Hey+0.012
Neg logit contributions
pron-0.025
 masterpiece-0.024
 favourite-0.023
 collection-0.023
 usual-0.022
Token
Token ID198
Feature activation-2.60e-01

Pos logit contributions
pron+0.023
 masterpiece+0.021
 favourite+0.021
 collection+0.020
 usual+0.019
Neg logit contributions
crow-0.018
Leave-0.017
Bad-0.017
Stop-0.016
Hey-0.015
Token he
Token ID339
Feature activation+6.89e-01

Pos logit contributions
crow+0.103
Leave+0.099
Bad+0.097
vious+0.095
Stop+0.095
Neg logit contributions
pron-0.102
 favourite-0.094
 masterpiece-0.091
 usual-0.084
 collection-0.084
Token saw
Token ID2497
Feature activation+5.50e-01

Pos logit contributions
crow+0.048
Leave+0.047
Bad+0.047
Stop+0.046
Hey+0.046
Neg logit contributions
pron-0.058
 favourite-0.054
 masterpiece-0.053
 usual-0.048
 brand-0.048
Token a
Token ID257
Feature activation+2.88e-01

Pos logit contributions
crow+0.043
Leave+0.041
Bad+0.041
Stop+0.039
vious+0.039
Neg logit contributions
pron-0.045
 favourite-0.041
 masterpiece-0.041
 collection-0.037
 usual-0.036
Token basket
Token ID7988
Feature activation-7.03e+00

Pos logit contributions
Bad+0.023
crow+0.023
Leave+0.022
Stop+0.022
Hey+0.021
Neg logit contributions
pron-0.020
 favourite-0.019
 masterpiece-0.019
ail-0.018
 usual-0.017
Token of
Token ID286
Feature activation+2.60e+00

Pos logit contributions
pron+0.576
 favourite+0.530
 masterpiece+0.527
 collection+0.479
 usual+0.471
Neg logit contributions
crow-0.531
Leave-0.510
Bad-0.504
vious-0.483
Stop-0.483
Token freshly
Token ID29026
Feature activation-1.65e+01

Pos logit contributions
crow+0.245
Leave+0.237
Bad+0.236
Stop+0.231
vious+0.230
Neg logit contributions
pron-0.163
 masterpiece-0.144
 favourite-0.142
 collection-0.127
ail-0.126
Token baked
Token ID22979
Feature activation-7.29e+00

Pos logit contributions
pron+1.021
 masterpiece+0.922
 favourite+0.917
 brand+0.813
 collection+0.807
Neg logit contributions
crow-1.565
Leave-1.500
Bad-1.497
Stop-1.470
vious-1.441
Token bread
Token ID8509
Feature activation+1.03e+00

Pos logit contributions
pron+0.562
 masterpiece+0.514
 favourite+0.514
 brand+0.464
 usual+0.460
Neg logit contributions
crow-0.587
Leave-0.536
Bad-0.535
vious-0.528
Stop-0.525
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
crow+0.069
Bad+0.061
Leave+0.061
vious+0.061
 hunters+0.060
Neg logit contributions
pron-0.092
 masterpiece-0.083
 favourite-0.083
 brand-0.076
 usual-0.076
Token It
Token ID632
Feature activation+9.42e-01

Pos logit contributions
crow+0.013
Leave+0.013
Bad+0.012
Stop+0.012
vious+0.012
Neg logit contributions
pron-0.026
 masterpiece-0.024
 favourite-0.024
 collection-0.022
 usual-0.022
Token smelled
Token ID37609
Feature activation-5.96e+00

Pos logit contributions
Hey+0.058
crow+0.057
Bad+0.054
Stop+0.053
Leave+0.052
Neg logit contributions
pron-0.086
 masterpiece-0.077
 favourite-0.075
aj-0.074
 complexion-0.074
Token crown
Token ID12389
Feature activation-4.77e+00

Pos logit contributions
pron+0.129
 favourite+0.101
addy+0.100
icol+0.100
 usual+0.099
Neg logit contributions
crow-0.120
 hunters-0.114
vious-0.112
Leave-0.112
eper-0.110
Token and
Token ID290
Feature activation+1.04e-01

Pos logit contributions
pron+0.420
 favourite+0.365
 masterpiece+0.365
 bedroom+0.351
icol+0.345
Neg logit contributions
vious-0.277
crow-0.275
Leave-0.261
ases-0.252
eper-0.252
Token playing
Token ID2712
Feature activation+9.73e-01

Pos logit contributions
Bad+0.008
crow+0.008
Leave+0.008
Stop+0.007
 hunters+0.007
Neg logit contributions
pron-0.008
 favourite-0.007
 masterpiece-0.007
ail-0.007
 brand-0.006
Token in
Token ID287
Feature activation-1.93e+00

Pos logit contributions
crow+0.070
Leave+0.067
Bad+0.066
Stop+0.064
vious+0.063
Neg logit contributions
pron-0.084
 favourite-0.077
 masterpiece-0.077
 collection-0.070
 usual-0.069
Token the
Token ID262
Feature activation+1.49e+00

Pos logit contributions
pron+0.187
 favourite+0.172
 masterpiece+0.167
ail+0.159
 collection+0.157
Neg logit contributions
crow-0.116
Bad-0.113
Leave-0.112
Stop-0.108
ases-0.102
Token freshly
Token ID29026
Feature activation-1.65e+01

Pos logit contributions
crow+0.126
Leave+0.121
Bad+0.121
Stop+0.119
vious+0.114
Neg logit contributions
pron-0.108
 masterpiece-0.096
 favourite-0.096
 collection-0.088
ail-0.087
Token cut
Token ID2005
Feature activation-3.54e+00

Pos logit contributions
pron+1.090
 favourite+0.998
 masterpiece+0.984
 collection+0.886
 usual+0.876
Neg logit contributions
crow-1.471
Bad-1.414
Leave-1.410
Stop-1.384
vious-1.344
Token grass
Token ID8701
Feature activation+2.80e-01

Pos logit contributions
pron+0.329
 favourite+0.303
 masterpiece+0.303
 collection+0.280
 usual+0.275
Neg logit contributions
crow-0.229
Leave-0.220
Bad-0.218
Stop-0.208
vious-0.205
Token.
Token ID13
Feature activation+2.56e-01

Pos logit contributions
crow+0.020
Leave+0.019
Bad+0.019
vious+0.018
Stop+0.018
Neg logit contributions
pron-0.024
 favourite-0.022
 masterpiece-0.022
 brand-0.020
 collection-0.019
Token It
Token ID632
Feature activation+9.58e-01

Pos logit contributions
Stop+0.011
 Fighting+0.010
 If+0.010
crow+0.010
Leave+0.010
Neg logit contributions
pron-0.027
 masterpiece-0.025
 collection-0.024
 usual-0.024
 complexion-0.023
Token looked
Token ID3114
Feature activation-4.59e+00

Pos logit contributions
crow+0.067
Bad+0.065
Stop+0.064
vious+0.064
Leave+0.064
Neg logit contributions
pron-0.083
 favourite-0.071
 masterpiece-0.070
 usual-0.067
 complexion-0.066
Token tidy
Token ID43044
Feature activation-3.38e+00

Pos logit contributions
pron+0.096
 favourite+0.087
 masterpiece+0.086
 collection+0.076
 usual+0.076
Neg logit contributions
crow-0.121
Leave-0.116
Bad-0.116
Stop-0.112
vious-0.111
Token,
Token ID11
Feature activation+1.33e+00

Pos logit contributions
pron+0.298
 masterpiece+0.276
 favourite+0.270
 collection+0.247
ail+0.246
Neg logit contributions
crow-0.225
Bad-0.215
Leave-0.214
Stop-0.202
vious-0.201
Token with
Token ID351
Feature activation+1.61e+00

Pos logit contributions
crow+0.107
Leave+0.106
Bad+0.105
Stop+0.100
vious+0.098
Neg logit contributions
pron-0.101
 masterpiece-0.092
 favourite-0.090
 collection-0.084
ail-0.083
Token his
Token ID465
Feature activation+2.99e+00

Pos logit contributions
crow+0.114
Leave+0.112
Bad+0.110
Stop+0.106
vious+0.105
Neg logit contributions
pron-0.135
 masterpiece-0.123
 favourite-0.117
ail-0.115
 collection-0.111
Token clothes
Token ID8242
Feature activation-2.37e+00

Pos logit contributions
crow+0.238
Bad+0.237
Leave+0.231
Stop+0.219
 hunters+0.219
Neg logit contributions
pron-0.204
 masterpiece-0.180
onna-0.179
oph-0.172
yt-0.163
Token freshly
Token ID29026
Feature activation-1.65e+01

Pos logit contributions
pron+0.220
 masterpiece+0.206
 favourite+0.197
onna+0.181
oph+0.178
Neg logit contributions
crow-0.137
Leave-0.134
vious-0.129
Bad-0.125
ting-0.124
Token cleaned
Token ID20750
Feature activation-2.83e+00

Pos logit contributions
pron+1.185
 masterpiece+1.165
onna+1.071
 favourite+1.056
yt+1.041
Neg logit contributions
crow-1.272
Leave-1.218
Stop-1.207
Bad-1.206
Hey-1.177
Token.
Token ID13
Feature activation+2.68e-01

Pos logit contributions
pron+0.245
 masterpiece+0.221
 favourite+0.217
 collection+0.199
 usual+0.196
Neg logit contributions
crow-0.202
Leave-0.189
Bad-0.189
Stop-0.182
vious-0.179
Token Suddenly
Token ID24975
Feature activation+2.71e-01

Pos logit contributions
crow+0.018
Leave+0.017
Bad+0.017
Stop+0.016
vious+0.016
Neg logit contributions
pron-0.025
 favourite-0.023
 masterpiece-0.023
 collection-0.021
 usual-0.021
Token,
Token ID11
Feature activation+1.35e+00

Pos logit contributions
crow+0.024
Leave+0.023
Bad+0.023
vious+0.022
Stop+0.022
Neg logit contributions
pron-0.019
 favourite-0.017
 masterpiece-0.017
 collection-0.015
 usual-0.015
Token he
Token ID339
Feature activation+7.47e-01

Pos logit contributions
crow+0.104
Leave+0.100
Bad+0.099
Stop+0.096
vious+0.094
Neg logit contributions
pron-0.109
 favourite-0.099
 masterpiece-0.099
 collection-0.090
 brand-0.088
Token
Token ID198
Feature activation-2.60e-01

Pos logit contributions
pron+0.274
 masterpiece+0.253
 favourite+0.253
 collection+0.235
 usual+0.230
Neg logit contributions
crow-0.188
Leave-0.177
Bad-0.175
Stop-0.168
vious-0.163
TokenAndy
Token ID35314
Feature activation+2.53e+00

Pos logit contributions
pron+0.025
 masterpiece+0.023
 favourite+0.022
ail+0.021
 brand+0.021
Neg logit contributions
crow-0.015
Bad-0.015
vious-0.015
Leave-0.015
ases-0.014
Token looked
Token ID3114
Feature activation-4.59e+00

Pos logit contributions
crow+0.202
Bad+0.196
Leave+0.194
Stop+0.188
vious+0.188
Neg logit contributions
pron-0.191
 favourite-0.170
 masterpiece-0.163
 usual-0.158
 collection-0.152
Token at
Token ID379
Feature activation+3.84e-01

Pos logit contributions
pron+0.426
 masterpiece+0.374
 favourite+0.366
 usual+0.359
ail+0.354
Neg logit contributions
crow-0.290
vious-0.285
Leave-0.282
Bad-0.282
Stop-0.270
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
crow+0.028
Leave+0.027
Bad+0.027
Stop+0.026
vious+0.025
Neg logit contributions
pron-0.033
 favourite-0.030
 masterpiece-0.030
 collection-0.028
 usual-0.027
Token freshly
Token ID29026
Feature activation-1.65e+01

Pos logit contributions
crow+0.139
Bad+0.137
Stop+0.134
Leave+0.133
vious+0.131
Neg logit contributions
pron-0.091
 favourite-0.084
 masterpiece-0.079
 collection-0.077
ail-0.074
Token printed
Token ID10398
Feature activation-3.71e+00

Pos logit contributions
pron+0.901
 favourite+0.790
 masterpiece+0.773
 collection+0.678
 usual+0.667
Neg logit contributions
crow-1.685
Bad-1.636
Leave-1.633
Stop-1.595
vious-1.571
Token picture
Token ID4286
Feature activation-5.48e+00

Pos logit contributions
pron+0.250
 favourite+0.232
 masterpiece+0.220
 usual+0.205
 collection+0.202
Neg logit contributions
crow-0.327
Bad-0.304
Leave-0.304
Stop-0.296
vious-0.294
Token and
Token ID290
Feature activation+1.61e-01

Pos logit contributions
pron+0.496
 favourite+0.456
 masterpiece+0.446
 collection+0.413
 usual+0.413
Neg logit contributions
crow-0.359
Leave-0.327
vious-0.321
Bad-0.321
Stop-0.313
Token smiled
Token ID13541
Feature activation-9.51e-01

Pos logit contributions
crow+0.012
Bad+0.012
Leave+0.012
Stop+0.012
Hey+0.011
Neg logit contributions
pron-0.013
 favourite-0.011
 masterpiece-0.011
 collection-0.010
 usual-0.010
Token.
Token ID13
Feature activation+2.80e-01

Pos logit contributions
pron+0.085
 masterpiece+0.076
 favourite+0.075
 collection+0.070
 usual+0.069
Neg logit contributions
crow-0.065
Leave-0.062
Bad-0.062
vious-0.059
Stop-0.058
Token mom
Token ID1995
Feature activation-5.35e+00

Pos logit contributions
crow+0.264
eper+0.257
Bad+0.255
 bully+0.250
Stop+0.249
Neg logit contributions
pron-0.243
onna-0.234
 masterpiece-0.233
icol-0.216
yt-0.215
Token put
Token ID1234
Feature activation-5.58e+00

Pos logit contributions
 favourite+0.431
 masterpiece+0.429
pron+0.428
 usual+0.398
 brand+0.389
Neg logit contributions
crow-0.359
Stop-0.346
vious-0.346
Bad-0.345
Hey-0.340
Token on
Token ID319
Feature activation-1.49e+00

Pos logit contributions
pron+0.463
 masterpiece+0.433
 favourite+0.426
 collection+0.394
 brand+0.385
Neg logit contributions
crow-0.416
Bad-0.395
Leave-0.391
Stop-0.380
vious-0.372
Token her
Token ID607
Feature activation-2.79e+00

Pos logit contributions
pron+0.131
 masterpiece+0.121
 favourite+0.120
 collection+0.116
ail+0.116
Neg logit contributions
crow-0.093
Bad-0.092
Stop-0.090
Leave-0.087
Hey-0.083
Token a
Token ID257
Feature activation+9.40e-02

Pos logit contributions
yt+0.161
 masterpiece+0.161
onna+0.160
pron+0.160
oph+0.154
Neg logit contributions
crow-0.220
vious-0.215
Bad-0.212
Leave-0.208
Stop-0.198
Tokenpron
Token ID31186
Feature activation-1.45e+01

Pos logit contributions
crow+0.008
Hey+0.007
Stop+0.007
Bad+0.007
 mean+0.007
Neg logit contributions
ert-0.004
icol-0.004
ail-0.004
yt-0.004
onna-0.004
Token and
Token ID290
Feature activation-8.30e-02

Pos logit contributions
 masterpiece+1.311
pron+1.248
 favourite+1.241
 brand+1.160
 usual+1.152
Neg logit contributions
crow-0.911
vious-0.753
Bad-0.748
ting-0.737
eper-0.737
Token said
Token ID531
Feature activation-1.24e+00

Pos logit contributions
 masterpiece+0.007
pron+0.006
ail+0.006
onna+0.006
 favourite+0.006
Neg logit contributions
Bad-0.005
Stop-0.005
Hey-0.005
crow-0.005
Leave-0.005
Token,
Token ID11
Feature activation+1.11e+00

Pos logit contributions
pron+0.112
 masterpiece+0.111
 favourite+0.105
 usual+0.098
 collection+0.098
Neg logit contributions
crow-0.077
Bad-0.071
Leave-0.071
Stop-0.070
 Stop-0.066
Token "
Token ID366
Feature activation-1.89e-01

Pos logit contributions
Leave+0.068
Bad+0.067
crow+0.067
Stop+0.065
ting+0.064
Neg logit contributions
 masterpiece-0.095
pron-0.095
 favourite-0.091
 collection-0.089
ail-0.084
TokenLet
Token ID5756
Feature activation+1.48e+00

Pos logit contributions
pron+0.018
 favourite+0.015
 masterpiece+0.015
 usual+0.014
 favorite+0.014
Neg logit contributions
crow-0.013
Bad-0.012
ases-0.012
Leave-0.012
eper-0.012
Token Dad
Token ID17415
Feature activation-5.66e+00

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.003
Neg logit contributions
pron-0.003
 masterpiece-0.003
 favourite-0.003
 collection-0.003
ail-0.003
Token put
Token ID1234
Feature activation-5.57e+00

Pos logit contributions
pron+0.426
 masterpiece+0.416
 favourite+0.407
 usual+0.389
 collection+0.366
Neg logit contributions
eper-0.374
crow-0.374
vious-0.362
Bad-0.357
Hey-0.356
Token on
Token ID319
Feature activation-1.48e+00

Pos logit contributions
pron+0.490
 masterpiece+0.459
 favourite+0.445
 collection+0.419
ail+0.412
Neg logit contributions
crow-0.380
Bad-0.358
Leave-0.350
Stop-0.345
vious-0.337
Token his
Token ID465
Feature activation+2.77e+00

Pos logit contributions
pron+0.141
 masterpiece+0.128
 favourite+0.123
ail+0.123
 collection+0.120
Neg logit contributions
crow-0.083
Bad-0.082
Leave-0.079
Stop-0.078
Hey-0.075
Token a
Token ID257
Feature activation+9.76e-02

Pos logit contributions
Leave+0.225
Bad+0.222
crow+0.221
vious+0.216
Stop+0.209
Neg logit contributions
pron-0.161
 masterpiece-0.154
onna-0.150
yt-0.146
ail-0.146
Tokenpron
Token ID31186
Feature activation-1.45e+01

Pos logit contributions
Bad+0.007
Leave+0.007
Hey+0.007
crow+0.007
Stop+0.007
Neg logit contributions
ail-0.004
oph-0.004
icol-0.004
onna-0.004
yt-0.004
Token and
Token ID290
Feature activation-8.94e-02

Pos logit contributions
pron+1.266
 masterpiece+1.223
 favourite+1.192
 usual+1.106
 brand+1.095
Neg logit contributions
crow-0.916
vious-0.784
eper-0.761
ases-0.759
Leave-0.753
Token seemed
Token ID3947
Feature activation-1.29e+00

Pos logit contributions
pron+0.007
 masterpiece+0.007
ail+0.006
 collection+0.006
 favourite+0.006
Neg logit contributions
Bad-0.006
crow-0.006
Hey-0.006
Stop-0.006
Leave-0.005
Token really
Token ID1107
Feature activation-2.76e+00

Pos logit contributions
pron+0.099
 masterpiece+0.090
ail+0.087
 favourite+0.084
 collection+0.083
Neg logit contributions
crow-0.092
vious-0.091
Leave-0.090
Bad-0.089
Stop-0.085
Token happy
Token ID3772
Feature activation+1.76e+00

Pos logit contributions
pron+0.195
 masterpiece+0.190
 favourite+0.182
 porch+0.176
ail+0.175
Neg logit contributions
vious-0.200
crow-0.199
Bad-0.199
Leave-0.194
Stop-0.188
Token.
Token ID13
Feature activation+4.38e-02

Pos logit contributions
crow+0.113
Leave+0.107
Bad+0.106
Stop+0.104
vious+0.102
Neg logit contributions
pron-0.160
 masterpiece-0.143
 favourite-0.142
ail-0.134
 collection-0.130
Token and
Token ID290
Feature activation-8.40e-02

Pos logit contributions
pron+0.151
 masterpiece+0.140
 favourite+0.138
ail+0.129
 usual+0.128
Neg logit contributions
crow-0.092
vious-0.081
Stop-0.080
eper-0.079
Bad-0.079
Token put
Token ID1234
Feature activation-5.56e+00

Pos logit contributions
pron+0.006
 masterpiece+0.005
 favourite+0.005
ail+0.005
 brand+0.005
Neg logit contributions
crow-0.006
Bad-0.006
Stop-0.006
Leave-0.006
eper-0.006
Token on
Token ID319
Feature activation-1.48e+00

Pos logit contributions
pron+0.512
 masterpiece+0.474
 favourite+0.469
 collection+0.437
 usual+0.430
Neg logit contributions
crow-0.359
Bad-0.333
Leave-0.327
Stop-0.324
vious-0.313
Token an
Token ID281
Feature activation-2.69e+00

Pos logit contributions
pron+0.136
 masterpiece+0.122
 favourite+0.120
yt+0.116
ail+0.115
Neg logit contributions
crow-0.085
Bad-0.084
Leave-0.080
Stop-0.080
ases-0.077
Token a
Token ID257
Feature activation+1.10e-01

Pos logit contributions
pron+0.185
 masterpiece+0.162
ail+0.162
 favourite+0.157
yt+0.156
Neg logit contributions
crow-0.218
vious-0.213
Leave-0.203
eper-0.202
Bad-0.202
Tokenpron
Token ID31186
Feature activation-1.45e+01

Pos logit contributions
crow+0.010
Bad+0.010
Stop+0.010
Hey+0.010
Leave+0.009
Neg logit contributions
ail-0.004
 masterpiece-0.004
 usual-0.004
ilda-0.004
liv-0.004
Token.
Token ID13
Feature activation+4.12e-02

Pos logit contributions
pron+1.194
 masterpiece+1.147
 favourite+1.126
 brand+1.065
 usual+1.031
Neg logit contributions
crow-1.029
vious-0.875
eper-0.861
ases-0.854
Leave-0.840
Token His
Token ID2399
Feature activation-4.70e-02

Pos logit contributions
crow+0.003
Leave+0.002
Bad+0.002
Stop+0.002
vious+0.002
Neg logit contributions
pron-0.004
 favourite-0.004
 masterpiece-0.004
 collection-0.003
 usual-0.003
Token siblings
Token ID20569
Feature activation+1.96e+00

Pos logit contributions
pron+0.003
yt+0.002
onna+0.002
 masterpiece+0.002
oph+0.002
Neg logit contributions
Bad-0.004
crow-0.004
eper-0.004
 hunters-0.004
Leave-0.004
Token watched
Token ID7342
Feature activation+3.65e-01

Pos logit contributions
crow+0.151
Leave+0.148
vious+0.144
Stop+0.142
Bad+0.141
Neg logit contributions
pron-0.141
 favourite-0.129
 masterpiece-0.128
 brand-0.116
 usual-0.115
Token him
Token ID683
Feature activation+7.48e+00

Pos logit contributions
crow+0.025
Leave+0.024
Bad+0.024
Stop+0.023
vious+0.023
Neg logit contributions
pron-0.033
 favourite-0.030
 masterpiece-0.030
 collection-0.028
 brand-0.027
Token put
Token ID1234
Feature activation-5.57e+00

Pos logit contributions
crow+0.278
Bad+0.275
Leave+0.267
Stop+0.260
Hey+0.257
Neg logit contributions
pron-0.210
 masterpiece-0.200
 favourite-0.192
 collection-0.172
ail-0.171
Token on
Token ID319
Feature activation-1.47e+00

Pos logit contributions
pron+0.491
 favourite+0.452
 masterpiece+0.445
 collection+0.413
 brand+0.406
Neg logit contributions
crow-0.393
Leave-0.380
Bad-0.375
Stop-0.359
vious-0.356
Token his
Token ID465
Feature activation+2.77e+00

Pos logit contributions
pron+0.157
 masterpiece+0.146
 favourite+0.145
ail+0.136
 collection+0.135
Neg logit contributions
crow-0.072
Leave-0.068
Bad-0.067
Stop-0.064
vious-0.063
Token special
Token ID2041
Feature activation-6.23e+00

Pos logit contributions
crow+0.201
Leave+0.200
Bad+0.195
 hunters+0.194
 brake+0.191
Neg logit contributions
pron-0.183
oph-0.181
onna-0.177
 masterpiece-0.167
yt-0.161
Token a
Token ID257
Feature activation+1.06e-01

Pos logit contributions
pron+0.423
 masterpiece+0.380
oph+0.379
onna+0.373
 favourite+0.371
Neg logit contributions
crow-0.492
Leave-0.455
Bad-0.448
 hunters-0.429
Stop-0.427
Tokenpron
Token ID31186
Feature activation-1.45e+01

Pos logit contributions
crow+0.008
Bad+0.008
 bully+0.007
Leave+0.007
 brake+0.007
Neg logit contributions
 masterpiece-0.006
 favourite-0.006
ail-0.006
oph-0.006
liv-0.006
Token and
Token ID290
Feature activation-7.80e-02

Pos logit contributions
 masterpiece+1.222
pron+1.209
 favourite+1.123
 brand+1.073
ail+1.045
Neg logit contributions
crow-0.997
eper-0.840
Bad-0.839
 hunters-0.838
Leave-0.833
Token decided
Token ID3066
Feature activation+3.93e+00

Pos logit contributions
 masterpiece+0.006
pron+0.006
ail+0.006
onna+0.006
 favourite+0.006
Neg logit contributions
Bad-0.005
Leave-0.005
crow-0.005
Stop-0.005
Hey-0.005
Token to
Token ID284
Feature activation-1.64e+00

Pos logit contributions
Leave+0.305
crow+0.302
Bad+0.298
Stop+0.293
 hunters+0.278
Neg logit contributions
pron-0.302
 masterpiece-0.277
 favourite-0.262
ail-0.247
 collection-0.243
Token travel
Token ID3067
Feature activation-2.11e+00

Pos logit contributions
pron+0.123
 favourite+0.116
 masterpiece+0.114
 brand+0.104
ail+0.103
Neg logit contributions
crow-0.131
Leave-0.126
Bad-0.123
Stop-0.121
vious-0.118
Token.
Token ID13
Feature activation+4.05e-02

Pos logit contributions
pron+0.131
 favourite+0.116
 masterpiece+0.115
 collection+0.102
 usual+0.100
Neg logit contributions
crow-0.203
Leave-0.197
Bad-0.196
Stop-0.190
vious-0.188
Token,
Token ID11
Feature activation+1.11e+00

Pos logit contributions
pron+0.130
 favourite+0.114
 masterpiece+0.113
 brand+0.104
 favorite+0.101
Neg logit contributions
crow-0.130
Leave-0.118
Bad-0.115
Stop-0.114
vious-0.113
Token the
Token ID262
Feature activation+1.28e+00

Pos logit contributions
crow+0.082
Bad+0.078
Leave+0.077
Stop+0.074
vious+0.071
Neg logit contributions
pron-0.095
 masterpiece-0.086
 favourite-0.083
 brand-0.077
 collection-0.077
Token baby
Token ID5156
Feature activation-8.00e-01

Pos logit contributions
crow+0.098
Bad+0.095
Leave+0.092
vious+0.089
Stop+0.088
Neg logit contributions
pron-0.103
 masterpiece-0.089
 favourite-0.088
 brand-0.084
ail-0.083
Token wasn
Token ID2492
Feature activation-6.67e-01

Pos logit contributions
pron+0.063
 favourite+0.057
 masterpiece+0.057
 collection+0.052
 brand+0.051
Neg logit contributions
crow-0.064
Leave-0.061
Bad-0.061
Stop-0.058
vious-0.058
Token't
Token ID470
Feature activation+8.58e-01

Pos logit contributions
pron+0.054
 favourite+0.049
 masterpiece+0.049
 collection+0.045
 brand+0.044
Neg logit contributions
crow-0.051
Leave-0.050
Bad-0.049
Stop-0.047
vious-0.047
Token scared
Token ID12008
Feature activation+8.22e+00

Pos logit contributions
crow+0.061
Leave+0.058
Bad+0.058
Stop+0.056
vious+0.054
Neg logit contributions
pron-0.075
 favourite-0.069
 masterpiece-0.068
 collection-0.063
 usual-0.062
Token anymore
Token ID7471
Feature activation+3.11e+00

Pos logit contributions
Bad+0.626
crow+0.614
Leave+0.602
Stop+0.569
eper+0.564
Neg logit contributions
pron-0.610
 favourite-0.603
 masterpiece-0.592
 usual-0.553
 favorite-0.543
Token.
Token ID13
Feature activation+4.38e-02

Pos logit contributions
crow+0.233
Leave+0.223
Bad+0.222
Stop+0.212
vious+0.211
Neg logit contributions
pron-0.259
 favourite-0.233
 masterpiece-0.233
 collection-0.212
 brand-0.209
Token She
Token ID1375
Feature activation-1.17e+00

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.003
Neg logit contributions
pron-0.004
 masterpiece-0.004
 favourite-0.003
 collection-0.003
 usual-0.003
Token now
Token ID783
Feature activation-1.97e+00

Pos logit contributions
pron+0.095
 masterpiece+0.082
 favourite+0.082
 usual+0.076
 brand+0.076
Neg logit contributions
crow-0.092
Bad-0.087
Leave-0.086
vious-0.085
Stop-0.084
Token knew
Token ID2993
Feature activation+2.03e-02

Pos logit contributions
pron+0.154
 favourite+0.139
 masterpiece+0.136
 brand+0.124
 usual+0.123
Neg logit contributions
crow-0.163
Leave-0.154
Bad-0.152
vious-0.150
Stop-0.147
Token,
Token ID11
Feature activation+1.11e+00

Pos logit contributions
pron+0.242
 masterpiece+0.216
 favourite+0.214
 collection+0.192
 brand+0.191
Neg logit contributions
crow-0.213
Bad-0.197
Leave-0.196
Stop-0.191
eper-0.188
Token he
Token ID339
Feature activation+4.96e-01

Pos logit contributions
crow+0.084
Bad+0.081
Leave+0.080
Stop+0.077
vious+0.075
Neg logit contributions
pron-0.092
 masterpiece-0.084
 favourite-0.083
 collection-0.076
ail-0.074
Token saw
Token ID2497
Feature activation+3.70e-01

Pos logit contributions
crow+0.039
Bad+0.038
Leave+0.038
Stop+0.036
eper+0.036
Neg logit contributions
pron-0.039
 masterpiece-0.034
 favourite-0.034
 usual-0.030
 collection-0.030
Token two
Token ID734
Feature activation+1.50e+00

Pos logit contributions
crow+0.031
Leave+0.030
Bad+0.029
Stop+0.028
vious+0.028
Neg logit contributions
pron-0.027
 favourite-0.025
 masterpiece-0.025
 brand-0.023
 collection-0.023
Token other
Token ID584
Feature activation+5.31e+00

Pos logit contributions
crow+0.116
Leave+0.111
Bad+0.111
Stop+0.107
vious+0.105
Neg logit contributions
pron-0.120
 favourite-0.111
 masterpiece-0.110
 collection-0.101
 usual-0.099
Token mice
Token ID10693
Feature activation+9.24e+00

Pos logit contributions
crow+0.275
Leave+0.261
Bad+0.258
Stop+0.243
vious+0.237
Neg logit contributions
pron-0.559
 favourite-0.530
 masterpiece-0.525
 collection-0.493
 usual-0.486
Token there
Token ID612
Feature activation+2.00e+00

Pos logit contributions
crow+0.802
Bad+0.774
Leave+0.773
Stop+0.750
vious+0.737
Neg logit contributions
pron-0.639
 favourite-0.589
 masterpiece-0.588
 collection-0.538
 brand-0.518
Token.
Token ID13
Feature activation+2.76e-02

Pos logit contributions
crow+0.154
Leave+0.147
Bad+0.147
Stop+0.141
vious+0.139
Neg logit contributions
pron-0.162
 favourite-0.147
 masterpiece-0.147
 collection-0.133
 brand-0.130
Token "
Token ID366
Feature activation-1.96e-01

Pos logit contributions
crow+0.002
Leave+0.002
Bad+0.002
Stop+0.002
vious+0.002
Neg logit contributions
pron-0.002
 favourite-0.002
 masterpiece-0.002
 collection-0.002
 brand-0.002
TokenThese
Token ID4711
Feature activation+2.76e+00

Pos logit contributions
pron+0.016
 favourite+0.014
 masterpiece+0.014
oph+0.013
 Sus+0.013
Neg logit contributions
crow-0.013
ases-0.012
vious-0.012
 risks-0.012
 hunters-0.012
Token are
Token ID389
Feature activation+3.89e+00

Pos logit contributions
crow+0.179
Leave+0.175
Bad+0.169
Stop+0.159
vious+0.156
Neg logit contributions
 favourite-0.238
pron-0.231
 masterpiece-0.224
 collection-0.220
 favorite-0.217
Token's
Token ID338
Feature activation+3.72e+00

Pos logit contributions
pron+0.015
 masterpiece+0.014
 favourite+0.014
 brand+0.012
 collection+0.012
Neg logit contributions
crow-0.015
Leave-0.015
Bad-0.015
vious-0.014
Stop-0.014
Token mom
Token ID1995
Feature activation-5.31e+00

Pos logit contributions
crow+0.334
Bad+0.330
Leave+0.325
 hunters+0.319
eper+0.313
Neg logit contributions
pron-0.221
 masterpiece-0.183
onna-0.178
yt-0.163
 favourite-0.160
Token asked
Token ID1965
Feature activation+3.72e-01

Pos logit contributions
pron+0.408
 masterpiece+0.393
 favourite+0.388
 brand+0.346
 usual+0.343
Neg logit contributions
crow-0.401
eper-0.376
Bad-0.376
Leave-0.375
vious-0.371
Token,
Token ID11
Feature activation+1.14e+00

Pos logit contributions
crow+0.017
Leave+0.017
Bad+0.017
vious+0.016
Stop+0.015
Neg logit contributions
pron-0.041
 favourite-0.039
 masterpiece-0.038
 usual-0.036
 collection-0.036
Token "
Token ID366
Feature activation-1.83e-01

Pos logit contributions
crow+0.097
Bad+0.094
Leave+0.094
Stop+0.090
vious+0.088
Neg logit contributions
pron-0.081
 masterpiece-0.075
 favourite-0.074
 collection-0.067
 usual-0.065
TokenDid
Token ID11633
Feature activation+8.42e+00

Pos logit contributions
pron+0.019
 favourite+0.017
 masterpiece+0.016
 usual+0.015
 brand+0.015
Neg logit contributions
crow-0.011
ases-0.010
vious-0.010
Leave-0.009
Bad-0.009
Token you
Token ID345
Feature activation+3.31e+00

Pos logit contributions
crow+0.469
Leave+0.443
Bad+0.438
Stop+0.414
vious+0.411
Neg logit contributions
pron-0.857
 favourite-0.804
 masterpiece-0.796
 collection-0.747
 usual-0.738
Token let
Token ID1309
Feature activation+3.65e-01

Pos logit contributions
crow+0.244
Leave+0.235
Bad+0.233
vious+0.225
Stop+0.223
Neg logit contributions
pron-0.276
 masterpiece-0.254
 favourite-0.253
 collection-0.230
 brand-0.227
Token Bob
Token ID5811
Feature activation+1.04e+00

Pos logit contributions
crow+0.025
Leave+0.025
Bad+0.024
vious+0.023
Stop+0.023
Neg logit contributions
pron-0.032
 favourite-0.030
 masterpiece-0.029
 collection-0.027
 usual-0.027
Token go
Token ID467
Feature activation-2.19e-01

Pos logit contributions
crow+0.083
Leave+0.080
Bad+0.079
Stop+0.076
vious+0.076
Neg logit contributions
pron-0.080
 masterpiece-0.073
 favourite-0.073
 collection-0.066
 brand-0.065
Token?"
Token ID1701
Feature activation-6.35e+00

Pos logit contributions
pron+0.019
 masterpiece+0.017
 favourite+0.016
 collection+0.015
 brand+0.014
Neg logit contributions
crow-0.016
Leave-0.015
vious-0.015
Bad-0.015
ases-0.014
Token be
Token ID307
Feature activation-1.68e+00

Pos logit contributions
pron+0.122
 favourite+0.111
 masterpiece+0.111
 collection+0.101
 usual+0.099
Neg logit contributions
crow-0.128
Leave-0.123
Bad-0.122
Stop-0.118
vious-0.117
Token mail
Token ID6920
Feature activation+4.21e+00

Pos logit contributions
pron+0.130
 favourite+0.129
 masterpiece+0.123
 favorite+0.121
 collection+0.116
Neg logit contributions
crow-0.125
Leave-0.124
Stop-0.119
Bad-0.118
vious-0.114
Tokenmen
Token ID3653
Feature activation+6.54e+00

Pos logit contributions
Leave+0.338
crow+0.335
Bad+0.330
vious+0.320
Stop+0.319
Neg logit contributions
pron-0.320
 favourite-0.303
 masterpiece-0.293
 favorite-0.274
 collection-0.271
Token and
Token ID290
Feature activation-3.51e-02

Pos logit contributions
crow+0.515
Leave+0.500
Bad+0.496
Stop+0.478
vious+0.469
Neg logit contributions
pron-0.515
 favourite-0.472
 masterpiece-0.464
 collection-0.431
 usual-0.427
Token deliver
Token ID5203
Feature activation+3.02e+00

Pos logit contributions
pron+0.003
 favourite+0.003
 masterpiece+0.003
 collection+0.002
ail+0.002
Neg logit contributions
crow-0.003
Leave-0.003
Bad-0.003
Stop-0.002
vious-0.002
Token letters
Token ID7475
Feature activation+7.74e+00

Pos logit contributions
crow+0.227
Leave+0.218
Bad+0.217
Stop+0.209
vious+0.206
Neg logit contributions
pron-0.248
 favourite-0.227
 masterpiece-0.226
 collection-0.207
 usual-0.203
Token to
Token ID284
Feature activation-1.61e+00

Pos logit contributions
crow+0.649
Bad+0.609
Leave+0.609
vious+0.588
Stop+0.586
Neg logit contributions
pron-0.572
 masterpiece-0.514
 favourite-0.504
 collection-0.454
 brand-0.449
Token their
Token ID511
Feature activation-8.65e-01

Pos logit contributions
pron+0.131
 favourite+0.119
 masterpiece+0.119
 collection+0.108
 brand+0.106
Neg logit contributions
crow-0.124
Leave-0.118
Bad-0.118
Stop-0.114
vious-0.112
Token mom
Token ID1995
Feature activation-5.31e+00

Pos logit contributions
pron+0.059
 masterpiece+0.050
 favourite+0.049
 brand+0.044
ail+0.044
Neg logit contributions
crow-0.078
Bad-0.075
Leave-0.073
Stop-0.072
eper-0.071
Token and
Token ID290
Feature activation-5.15e-02

Pos logit contributions
pron+0.446
 masterpiece+0.408
 favourite+0.408
 collection+0.371
 brand+0.366
Neg logit contributions
crow-0.392
Leave-0.372
Bad-0.371
Stop-0.356
vious-0.355
Token dad
Token ID9955
Feature activation-5.57e+00

Pos logit contributions
pron+0.003
 masterpiece+0.002
 favourite+0.002
ail+0.002
 brand+0.002
Neg logit contributions
crow-0.005
Bad-0.005
Leave-0.005
Stop-0.005
eper-0.005
Token he
Token ID339
Feature activation+5.33e-01

Pos logit contributions
pron+0.130
 favourite+0.119
 masterpiece+0.111
 usual+0.110
 favorite+0.105
Neg logit contributions
crow-0.144
Leave-0.139
vious-0.136
ases-0.135
Bad-0.134
Token did
Token ID750
Feature activation+2.44e+00

Pos logit contributions
crow+0.043
Bad+0.043
Leave+0.041
Stop+0.040
eper+0.040
Neg logit contributions
pron-0.040
 masterpiece-0.038
 favourite-0.037
 brand-0.034
 collection-0.033
Token not
Token ID407
Feature activation-3.02e+00

Pos logit contributions
crow+0.272
Leave+0.258
Bad+0.256
Stop+0.252
vious+0.252
Neg logit contributions
pron-0.119
 favourite-0.103
 masterpiece-0.101
 collection-0.086
 usual-0.086
Token recognize
Token ID7564
Feature activation-2.48e-01

Pos logit contributions
pron+0.210
 masterpiece+0.192
 favourite+0.186
 collection+0.184
 usual+0.178
Neg logit contributions
crow-0.254
Bad-0.254
Leave-0.248
Stop-0.236
Hey-0.227
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
pron+0.017
 favourite+0.017
 masterpiece+0.016
 usual+0.016
 favorite+0.015
Neg logit contributions
crow-0.020
Leave-0.020
vious-0.019
Bad-0.019
Stop-0.019
Token danger
Token ID3514
Feature activation+9.00e+00

Pos logit contributions
crow+0.100
Leave+0.098
Bad+0.094
Stop+0.092
vious+0.091
Neg logit contributions
pron-0.109
 favourite-0.102
 masterpiece-0.100
 favorite-0.093
 collection-0.093
Token.
Token ID13
Feature activation+8.90e-02

Pos logit contributions
Bad+0.805
Leave+0.799
crow+0.772
Stop+0.769
vious+0.767
Neg logit contributions
pron-0.534
 favourite-0.491
 usual-0.479
 masterpiece-0.474
 collection-0.452
Token There
Token ID1318
Feature activation+1.10e+00

Pos logit contributions
crow+0.007
vious+0.007
Leave+0.007
Bad+0.007
Stop+0.006
Neg logit contributions
pron-0.007
 favourite-0.006
 favorite-0.006
 masterpiece-0.006
 brand-0.006
Token was
Token ID373
Feature activation-1.52e+00

Pos logit contributions
crow+0.101
Leave+0.099
Bad+0.098
Stop+0.095
vious+0.095
Neg logit contributions
pron-0.070
 favourite-0.064
 masterpiece-0.063
 collection-0.057
 usual-0.056
Token a
Token ID257
Feature activation+1.49e-01

Pos logit contributions
pron+0.117
 favourite+0.108
 masterpiece+0.106
 usual+0.097
 collection+0.096
Neg logit contributions
crow-0.123
Leave-0.118
Bad-0.116
Stop-0.113
vious-0.112
Token big
Token ID1263
Feature activation-5.86e+00

Pos logit contributions
crow+0.013
Bad+0.012
Leave+0.012
Stop+0.012
vious+0.011
Neg logit contributions
pron-0.011
 favourite-0.010
 masterpiece-0.010
 collection-0.009
ail-0.009
Token of
Token ID286
Feature activation+2.53e+00

Pos logit contributions
pron+0.357
 favourite+0.330
 masterpiece+0.324
 brand+0.297
 collection+0.297
Neg logit contributions
crow-0.300
Bad-0.296
Leave-0.294
Stop-0.276
eper-0.269
Token hot
Token ID3024
Feature activation-2.41e+00

Pos logit contributions
crow+0.228
Leave+0.220
Bad+0.220
Stop+0.213
vious+0.211
Neg logit contributions
pron-0.172
 favourite-0.153
 masterpiece-0.153
 collection-0.137
 usual-0.134
Token pepper
Token ID13385
Feature activation-1.06e+00

Pos logit contributions
pron+0.162
 favourite+0.146
 masterpiece+0.144
 collection+0.128
 brand+0.125
Neg logit contributions
crow-0.218
Bad-0.213
Leave-0.212
Stop-0.201
vious-0.201
Token to
Token ID284
Feature activation-1.50e+00

Pos logit contributions
pron+0.080
 masterpiece+0.072
 favourite+0.072
 brand+0.064
 collection+0.064
Neg logit contributions
crow-0.087
Bad-0.082
Leave-0.082
Stop-0.080
vious-0.079
Token his
Token ID465
Feature activation+2.91e+00

Pos logit contributions
pron+0.124
 favourite+0.115
 masterpiece+0.114
 collection+0.105
ail+0.103
Neg logit contributions
crow-0.110
Bad-0.105
Leave-0.105
Stop-0.101
vious-0.098
Token food
Token ID2057
Feature activation+5.17e+00

Pos logit contributions
crow+0.232
Bad+0.229
Leave+0.223
Stop+0.213
ases+0.211
Neg logit contributions
pron-0.213
 masterpiece-0.190
 favourite-0.183
ail-0.174
 brand-0.169
Token,
Token ID11
Feature activation+1.26e+00

Pos logit contributions
crow+0.352
Bad+0.317
Leave+0.309
ases+0.306
vious+0.304
Neg logit contributions
pron-0.445
 masterpiece-0.414
 favourite-0.409
 brand-0.370
ail-0.366
Token and
Token ID290
Feature activation+7.44e-02

Pos logit contributions
crow+0.091
Leave+0.090
Bad+0.090
Stop+0.085
vious+0.084
Neg logit contributions
pron-0.102
 masterpiece-0.095
 favourite-0.095
ail-0.088
 collection-0.087
Token it
Token ID340
Feature activation+1.38e-01

Pos logit contributions
crow+0.006
Bad+0.006
Leave+0.005
Stop+0.005
vious+0.005
Neg logit contributions
pron-0.006
 favourite-0.005
 masterpiece-0.005
ail-0.005
 brand-0.005
Token became
Token ID2627
Feature activation-2.61e-01

Pos logit contributions
crow+0.010
Bad+0.010
Stop+0.010
vious+0.010
Leave+0.009
Neg logit contributions
pron-0.011
 favourite-0.010
 masterpiece-0.010
 complexion-0.009
 brand-0.009
Token very
Token ID845
Feature activation+8.88e-01

Pos logit contributions
pron+0.019
 masterpiece+0.018
 favourite+0.017
ail+0.016
 collection+0.016
Neg logit contributions
crow-0.021
Bad-0.021
Leave-0.020
Stop-0.020
vious-0.019
Token jump
Token ID4391
Feature activation+7.04e-01

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.002
Neg logit contributions
pron-0.003
 masterpiece-0.003
 favourite-0.003
 brand-0.002
 collection-0.002
Token and
Token ID290
Feature activation+5.77e-02

Pos logit contributions
crow+0.056
Leave+0.054
Bad+0.054
Stop+0.051
vious+0.051
Neg logit contributions
pron-0.055
 favourite-0.051
 masterpiece-0.050
 collection-0.046
 usual-0.045
Token slide
Token ID10649
Feature activation-3.23e+00

Pos logit contributions
crow+0.005
Leave+0.005
Bad+0.005
Stop+0.004
vious+0.004
Neg logit contributions
pron-0.004
 favourite-0.004
 masterpiece-0.004
 collection-0.003
 brand-0.003
Token.
Token ID13
Feature activation+1.89e-01

Pos logit contributions
pron+0.265
 favourite+0.241
 masterpiece+0.241
 collection+0.219
 brand+0.215
Neg logit contributions
crow-0.247
Leave-0.237
Bad-0.235
Stop-0.226
vious-0.223
Token They
Token ID1119
Feature activation-2.22e-02

Pos logit contributions
crow+0.013
Leave+0.012
Bad+0.012
Stop+0.012
Hey+0.011
Neg logit contributions
pron-0.018
 masterpiece-0.016
 favourite-0.015
 collection-0.015
 brand-0.015
Token saw
Token ID2497
Feature activation+5.13e-01

Pos logit contributions
pron+0.002
 masterpiece+0.002
 favourite+0.002
 brand+0.002
 collection+0.001
Neg logit contributions
crow-0.002
Leave-0.002
Bad-0.002
Stop-0.002
Hey-0.002
Token a
Token ID257
Feature activation+2.41e-01

Pos logit contributions
crow+0.044
Leave+0.043
Bad+0.042
Stop+0.041
vious+0.040
Neg logit contributions
pron-0.034
 favourite-0.034
 masterpiece-0.031
 favorite-0.030
 usual-0.029
Token big
Token ID1263
Feature activation-5.75e+00

Pos logit contributions
Bad+0.021
crow+0.021
Stop+0.020
Leave+0.020
Hey+0.019
Neg logit contributions
pron-0.015
 favourite-0.014
 masterpiece-0.014
ail-0.013
 collection-0.012
Token hill
Token ID12788
Feature activation-1.12e+00

Pos logit contributions
pron+0.426
 favourite+0.387
 masterpiece+0.384
 collection+0.345
 usual+0.342
Neg logit contributions
crow-0.480
Leave-0.461
Bad-0.461
Stop-0.444
vious-0.437
Token with
Token ID351
Feature activation+1.55e+00

Pos logit contributions
pron+0.093
 favourite+0.085
 masterpiece+0.085
 collection+0.078
 usual+0.076
Neg logit contributions
crow-0.084
Leave-0.081
Bad-0.080
Stop-0.077
vious-0.076
Token a
Token ID257
Feature activation+2.52e-01

Pos logit contributions
crow+0.151
Leave+0.146
Bad+0.145
Stop+0.141
vious+0.140
Neg logit contributions
pron-0.091
 favourite-0.085
 masterpiece-0.082
 collection-0.073
 usual-0.072
Token and
Token ID290
Feature activation-8.56e-02

Pos logit contributions
crow+0.669
Bad+0.628
Leave+0.628
vious+0.609
Stop+0.604
Neg logit contributions
pron-0.452
 favourite-0.425
 masterpiece-0.404
 favorite-0.389
 brand-0.370
Token cl
Token ID537
Feature activation+1.28e+00

Pos logit contributions
pron+0.007
 masterpiece+0.007
 favourite+0.007
 collection+0.006
 usual+0.006
Neg logit contributions
Leave-0.006
Bad-0.006
crow-0.006
Stop-0.006
vious-0.006
Tokenapped
Token ID6320
Feature activation+5.85e-01

Pos logit contributions
crow+0.122
Leave+0.121
Bad+0.120
Stop+0.118
 hunters+0.115
Neg logit contributions
pron-0.074
 favourite-0.069
 masterpiece-0.065
 collection-0.060
ouse-0.058
Token.
Token ID13
Feature activation+3.40e-02

Pos logit contributions
crow+0.052
Bad+0.050
Leave+0.050
Stop+0.048
vious+0.047
Neg logit contributions
pron-0.041
 favourite-0.038
 masterpiece-0.036
 favorite-0.034
 collection-0.033
Token "
Token ID366
Feature activation-1.95e-01

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.002
Stop+0.002
vious+0.002
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 collection-0.002
 usual-0.002
TokenYou
Token ID1639
Feature activation+6.63e+00

Pos logit contributions
pron+0.018
 favourite+0.017
 masterpiece+0.016
 favorite+0.015
 usual+0.015
Neg logit contributions
crow-0.012
eper-0.011
 thieves-0.010
vious-0.010
 hunters-0.010
Token're
Token ID821
Feature activation+7.59e-02

Pos logit contributions
crow+0.483
Leave+0.463
Bad+0.459
Stop+0.440
vious+0.434
Neg logit contributions
pron-0.566
 favourite-0.521
 masterpiece-0.518
 collection-0.476
 brand-0.467
Token awesome
Token ID7427
Feature activation-2.91e+00

Pos logit contributions
crow+0.006
Leave+0.006
Bad+0.005
Stop+0.005
vious+0.005
Neg logit contributions
pron-0.006
 favourite-0.006
 masterpiece-0.006
 brand-0.005
 favorite-0.005
Token.
Token ID13
Feature activation+3.16e-02

Pos logit contributions
pron+0.202
 favourite+0.185
 masterpiece+0.182
 collection+0.168
 favorite+0.162
Neg logit contributions
crow-0.255
Leave-0.250
Bad-0.243
Stop-0.235
vious-0.234
Token I
Token ID314
Feature activation-2.52e+00

Pos logit contributions
crow+0.002
Leave+0.002
Bad+0.002
vious+0.002
Stop+0.002
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.002
 favorite-0.002
 bedroom-0.002
Token'm
Token ID1101
Feature activation-4.81e-01

Pos logit contributions
pron+0.204
 favourite+0.186
 masterpiece+0.186
 collection+0.169
 brand+0.166
Neg logit contributions
crow-0.194
Leave-0.186
Bad-0.186
Stop-0.179
vious-0.178
Token away
Token ID1497
Feature activation+7.52e+00

Pos logit contributions
pron+0.058
 favourite+0.058
 masterpiece+0.055
 favorite+0.051
 usual+0.051
Neg logit contributions
crow-0.062
Bad-0.062
Leave-0.061
vious-0.059
Stop-0.058
Token.
Token ID13
Feature activation+1.96e-01

Pos logit contributions
crow+0.540
Leave+0.511
Bad+0.509
Stop+0.479
vious+0.475
Neg logit contributions
pron-0.674
 masterpiece-0.598
 favourite-0.595
 collection-0.542
 brand-0.537
Token They
Token ID1119
Feature activation-7.24e-03

Pos logit contributions
crow+0.011
Leave+0.010
Stop+0.010
Bad+0.010
vious+0.010
Neg logit contributions
pron-0.021
 masterpiece-0.019
 favourite-0.018
 collection-0.017
 usual-0.017
Token were
Token ID547
Feature activation+2.71e-02

Pos logit contributions
pron+0.001
 masterpiece+0.001
 favourite+0.001
 brand+0.000
 collection+0.000
Neg logit contributions
crow-0.001
Bad-0.001
Leave-0.001
Stop-0.001
vious-0.001
Token so
Token ID523
Feature activation-6.90e-01

Pos logit contributions
crow+0.002
Leave+0.002
Bad+0.002
Stop+0.002
vious+0.002
Neg logit contributions
pron-0.002
 favourite-0.002
 masterpiece-0.002
 collection-0.002
 brand-0.002
Token happy
Token ID3772
Feature activation+1.92e+00

Pos logit contributions
pron+0.049
 favourite+0.045
 masterpiece+0.044
 collection+0.040
 brand+0.040
Neg logit contributions
crow-0.060
Leave-0.058
Bad-0.057
Stop-0.056
vious-0.055
Token and
Token ID290
Feature activation+8.74e-02

Pos logit contributions
crow+0.152
Leave+0.147
Bad+0.147
Stop+0.141
vious+0.138
Neg logit contributions
pron-0.157
 masterpiece-0.137
 favourite-0.135
 collection-0.123
 brand-0.121
Token proud
Token ID6613
Feature activation-1.60e+00

Pos logit contributions
crow+0.006
Bad+0.006
Leave+0.006
vious+0.006
Stop+0.006
Neg logit contributions
pron-0.008
 masterpiece-0.007
 favourite-0.007
 collection-0.006
ail-0.006
Token of
Token ID286
Feature activation+2.58e+00

Pos logit contributions
pron+0.148
 masterpiece+0.136
 favourite+0.136
 collection+0.125
 usual+0.123
Neg logit contributions
crow-0.107
Leave-0.102
Bad-0.101
Stop-0.096
vious-0.096
Token themselves
Token ID2405
Feature activation+3.37e+00

Pos logit contributions
crow+0.206
Leave+0.198
Bad+0.196
vious+0.190
Stop+0.190
Neg logit contributions
pron-0.201
 favourite-0.186
 masterpiece-0.185
 collection-0.168
 usual-0.166
Token for
Token ID329
Feature activation-5.24e+00

Pos logit contributions
crow+0.262
Leave+0.252
Bad+0.251
Stop+0.240
vious+0.239
Neg logit contributions
pron-0.270
 favourite-0.244
 masterpiece-0.244
 collection-0.221
 usual-0.218
Token boy
Token ID2933
Feature activation+4.85e+00

Pos logit contributions
pron+0.214
 favourite+0.207
 masterpiece+0.198
 collection+0.194
 favorite+0.193
Neg logit contributions
crow-0.179
Leave-0.178
Bad-0.171
ases-0.167
Stop-0.164
Token was
Token ID373
Feature activation-1.57e+00

Pos logit contributions
crow+0.406
Leave+0.390
Bad+0.388
Stop+0.376
vious+0.374
Neg logit contributions
pron-0.363
 masterpiece-0.323
 favourite-0.322
 collection-0.289
 brand-0.288
Token very
Token ID845
Feature activation+7.48e-01

Pos logit contributions
pron+0.135
 masterpiece+0.123
 favourite+0.123
 collection+0.113
 usual+0.111
Neg logit contributions
crow-0.114
Leave-0.109
Bad-0.108
Stop-0.103
vious-0.103
Token surprised
Token ID6655
Feature activation+2.80e+00

Pos logit contributions
crow+0.053
Leave+0.051
Bad+0.050
Stop+0.048
vious+0.047
Neg logit contributions
pron-0.066
 favourite-0.061
 masterpiece-0.060
 collection-0.055
 usual-0.055
Token.
Token ID13
Feature activation+4.78e-02

Pos logit contributions
crow+0.246
Leave+0.243
Bad+0.242
Stop+0.228
vious+0.224
Neg logit contributions
pron-0.188
 favourite-0.180
 masterpiece-0.173
 favorite-0.160
 usual-0.160
Token He
Token ID679
Feature activation+3.19e+00

Pos logit contributions
crow+0.003
Leave+0.002
Bad+0.002
Stop+0.002
vious+0.002
Neg logit contributions
pron-0.005
 favourite-0.005
 masterpiece-0.005
 collection-0.004
 brand-0.004
Token had
Token ID550
Feature activation-5.24e+00

Pos logit contributions
crow+0.235
Bad+0.232
Leave+0.230
Stop+0.230
vious+0.220
Neg logit contributions
pron-0.262
 masterpiece-0.235
 favourite-0.232
 collection-0.216
ail-0.212
Token never
Token ID1239
Feature activation-7.07e-01

Pos logit contributions
pron+0.447
 favourite+0.392
 masterpiece+0.390
ail+0.362
 collection+0.358
Neg logit contributions
crow-0.382
Bad-0.378
Leave-0.377
Stop-0.366
vious-0.365
Token seen
Token ID1775
Feature activation+3.14e+00

Pos logit contributions
pron+0.068
 favourite+0.063
 masterpiece+0.062
 collection+0.058
ail+0.057
Neg logit contributions
crow-0.044
Leave-0.042
Bad-0.041
vious-0.041
Stop-0.040
Token a
Token ID257
Feature activation+1.30e-01

Pos logit contributions
crow+0.229
Leave+0.221
Bad+0.219
Stop+0.210
vious+0.207
Neg logit contributions
pron-0.265
 favourite-0.245
 masterpiece-0.243
 collection-0.222
 usual-0.220
Token fake
Token ID8390
Feature activation-1.48e+00

Pos logit contributions
crow+0.010
Bad+0.010
Stop+0.010
Leave+0.010
eper+0.009
Neg logit contributions
pron-0.009
 favourite-0.008
 masterpiece-0.008
ail-0.008
 collection-0.007
Token kne
Token ID24813
Feature activation+7.42e-01

Pos logit contributions
pron+0.397
 favourite+0.370
 masterpiece+0.361
 collection+0.327
 usual+0.327
Neg logit contributions
crow-0.446
Leave-0.426
Bad-0.424
Stop-0.411
vious-0.409
Tokeneled
Token ID18449
Feature activation+2.08e-01

Pos logit contributions
Bad+0.058
crow+0.057
Leave+0.056
 hunters+0.055
Stop+0.055
Neg logit contributions
pron-0.052
 masterpiece-0.045
ail-0.043
 favourite-0.042
 complexion-0.040
Token down
Token ID866
Feature activation+3.73e-01

Pos logit contributions
crow+0.014
Leave+0.014
Bad+0.014
Stop+0.013
vious+0.013
Neg logit contributions
pron-0.019
 favourite-0.017
 masterpiece-0.017
 collection-0.016
 usual-0.015
Token and
Token ID290
Feature activation-8.90e-02

Pos logit contributions
crow+0.025
Leave+0.024
Bad+0.024
Stop+0.023
vious+0.023
Neg logit contributions
pron-0.033
 favourite-0.031
 masterpiece-0.031
 collection-0.029
 usual-0.028
Token told
Token ID1297
Feature activation-2.63e+00

Pos logit contributions
pron+0.007
 favourite+0.006
 masterpiece+0.006
 collection+0.006
 usual+0.006
Neg logit contributions
Bad-0.007
crow-0.007
Leave-0.007
Stop-0.007
Hey-0.007
Token L
Token ID406
Feature activation-7.99e-01

Pos logit contributions
pron+0.201
 favourite+0.177
 masterpiece+0.176
 collection+0.162
 brand+0.156
Neg logit contributions
crow-0.221
Leave-0.210
Bad-0.208
Stop-0.207
vious-0.202
Tokenola
Token ID5708
Feature activation-5.23e+00

Pos logit contributions
pron+0.051
 favourite+0.046
 masterpiece+0.045
 collection+0.041
 brand+0.040
Neg logit contributions
crow-0.076
Leave-0.072
vious-0.071
Bad-0.071
Stop-0.071
Token to
Token ID284
Feature activation-1.66e+00

Pos logit contributions
pron+0.414
 masterpiece+0.372
 favourite+0.366
 collection+0.330
 brand+0.328
Neg logit contributions
crow-0.421
Bad-0.389
Leave-0.388
vious-0.382
Stop-0.375
Token be
Token ID307
Feature activation-1.73e+00

Pos logit contributions
pron+0.135
 favourite+0.125
 masterpiece+0.124
 collection+0.112
 brand+0.112
Neg logit contributions
crow-0.125
Leave-0.120
Bad-0.119
Stop-0.116
vious-0.112
Token careful
Token ID8161
Feature activation+6.74e+00

Pos logit contributions
pron+0.142
 favourite+0.133
 masterpiece+0.129
 brand+0.119
 favorite+0.118
Neg logit contributions
crow-0.128
Bad-0.122
Leave-0.121
Stop-0.119
vious-0.114
Token.
Token ID13
Feature activation+3.63e-02

Pos logit contributions
crow+0.515
Leave+0.495
Bad+0.492
Stop+0.473
vious+0.468
Neg logit contributions
pron-0.548
 favourite-0.501
 masterpiece-0.499
 collection-0.455
 usual-0.447
Token find
Token ID1064
Feature activation-2.54e+00

Pos logit contributions
pron+0.210
 favourite+0.190
 masterpiece+0.189
 collection+0.171
 usual+0.168
Neg logit contributions
crow-0.255
Bad-0.247
Leave-0.246
Stop-0.238
vious-0.234
Token Lily
Token ID20037
Feature activation-1.81e+00

Pos logit contributions
pron+0.175
 favourite+0.170
 masterpiece+0.159
 favorite+0.152
 usual+0.151
Neg logit contributions
crow-0.212
Leave-0.208
Bad-0.204
Stop-0.199
vious-0.199
Token,
Token ID11
Feature activation+1.23e+00

Pos logit contributions
pron+0.150
 masterpiece+0.135
 favourite+0.133
 collection+0.120
 brand+0.119
Neg logit contributions
crow-0.138
Leave-0.132
Bad-0.131
vious-0.126
Stop-0.124
Token so
Token ID523
Feature activation-7.39e-01

Pos logit contributions
crow+0.097
Leave+0.094
Bad+0.093
Stop+0.089
vious+0.088
Neg logit contributions
pron-0.097
 masterpiece-0.089
 favourite-0.088
 collection-0.081
 brand-0.078
Token he
Token ID339
Feature activation+6.28e-01

Pos logit contributions
pron+0.064
 masterpiece+0.061
 favourite+0.058
 collection+0.054
ail+0.054
Neg logit contributions
Bad-0.050
crow-0.050
Leave-0.050
Stop-0.046
vious-0.044
Token went
Token ID1816
Feature activation-1.10e+00

Pos logit contributions
crow+0.050
Leave+0.047
Bad+0.047
Stop+0.045
eper+0.045
Neg logit contributions
pron-0.050
 masterpiece-0.047
 favourite-0.045
 brand-0.041
 collection-0.041
Token to
Token ID284
Feature activation-1.52e+00

Pos logit contributions
pron+0.076
 masterpiece+0.067
 favourite+0.067
 collection+0.059
 brand+0.058
Neg logit contributions
crow-0.100
Leave-0.096
Bad-0.095
Stop-0.092
vious-0.091
Token get
Token ID651
Feature activation+4.14e-01

Pos logit contributions
pron+0.127
 masterpiece+0.114
 favourite+0.114
 collection+0.104
 brand+0.102
Neg logit contributions
crow-0.115
Leave-0.111
Bad-0.110
Stop-0.106
vious-0.102
Token help
Token ID1037
Feature activation+2.44e+00

Pos logit contributions
crow+0.031
Leave+0.029
Bad+0.029
Stop+0.028
vious+0.027
Neg logit contributions
pron-0.035
 masterpiece-0.032
 favourite-0.032
 collection-0.029
 brand-0.029
Token.
Token ID13
Feature activation+1.81e-01

Pos logit contributions
Bad+0.207
crow+0.205
Leave+0.204
Stop+0.200
vious+0.197
Neg logit contributions
pron-0.170
 favourite-0.156
 masterpiece-0.155
 collection-0.143
 usual-0.142
Token He
Token ID679
Feature activation+3.30e+00

Pos logit contributions
crow+0.012
Leave+0.011
Bad+0.011
Stop+0.010
Hey+0.010
Neg logit contributions
pron-0.017
 masterpiece-0.016
 favourite-0.015
 collection-0.015
 usual-0.014
Token so
Token ID523
Feature activation-7.42e-01

Pos logit contributions
pron+0.144
 masterpiece+0.127
ail+0.125
 favourite+0.124
 collection+0.124
Neg logit contributions
vious-0.080
crow-0.079
Leave-0.077
Bad-0.077
eper-0.075
Token happy
Token ID3772
Feature activation+1.88e+00

Pos logit contributions
pron+0.070
 masterpiece+0.066
ail+0.062
icol+0.061
 favourite+0.061
Neg logit contributions
vious-0.038
Bad-0.037
Leave-0.037
crow-0.036
ases-0.035
Token and
Token ID290
Feature activation+2.73e-02

Pos logit contributions
crow+0.130
Leave+0.124
Bad+0.122
Stop+0.120
vious+0.118
Neg logit contributions
pron-0.168
 masterpiece-0.150
 favourite-0.148
 collection-0.136
 brand-0.134
Token excited
Token ID6568
Feature activation+2.81e+00

Pos logit contributions
Leave+0.002
Bad+0.002
crow+0.002
ting+0.002
vious+0.001
Neg logit contributions
pron-0.002
 masterpiece-0.002
 favourite-0.002
ool-0.002
ail-0.002
Token!
Token ID0
Feature activation-3.00e+00

Pos logit contributions
crow+0.196
Stop+0.184
vious+0.183
Leave+0.180
Bad+0.177
Neg logit contributions
pron-0.255
 masterpiece-0.224
 favourite-0.218
 collection-0.205
 brand-0.200
Token
Token ID220
Feature activation-1.20e+00

Pos logit contributions
pron+0.308
 masterpiece+0.284
 favourite+0.259
 collection+0.251
 brand+0.250
Neg logit contributions
crow-0.192
Leave-0.164
Stop-0.163
Bad-0.157
vious-0.156
Token
Token ID198
Feature activation-3.48e-01

Pos logit contributions
pron+0.111
 masterpiece+0.103
 favourite+0.100
 collection+0.095
 brand+0.092
Neg logit contributions
crow-0.079
Leave-0.073
Bad-0.073
Stop-0.071
ases-0.069
Token
Token ID198
Feature activation-3.55e-01

Pos logit contributions
pron+0.032
 masterpiece+0.030
 favourite+0.029
 collection+0.028
 brand+0.027
Neg logit contributions
crow-0.023
Leave-0.022
Bad-0.022
Stop-0.021
Hey-0.020
TokenThe
Token ID464
Feature activation+1.28e+00

Pos logit contributions
pron+0.030
 favourite+0.027
 masterpiece+0.027
 usual+0.024
 collection+0.024
Neg logit contributions
crow-0.026
Bad-0.025
Leave-0.024
vious-0.024
ases-0.024
Token bee
Token ID20697
Feature activation+8.90e-01

Pos logit contributions
crow+0.090
Bad+0.087
Leave+0.086
Stop+0.083
vious+0.083
Neg logit contributions
pron-0.107
 masterpiece-0.100
 favourite-0.100
 brand-0.094
 collection-0.093
Token cut
Token ID2005
Feature activation-3.62e+00

Pos logit contributions
crow+0.070
Bad+0.065
Leave+0.065
vious+0.064
eper+0.063
Neg logit contributions
pron-0.069
 favourite-0.063
 masterpiece-0.060
 usual-0.058
 brand-0.057
Token sand
Token ID6450
Feature activation-3.05e+00

Pos logit contributions
crow+0.101
Leave+0.096
Bad+0.096
Stop+0.094
vious+0.091
Neg logit contributions
pron-0.105
 masterpiece-0.093
 favourite-0.093
 collection-0.085
ail-0.084
Token.
Token ID13
Feature activation+7.44e-02

Pos logit contributions
pron+0.261
 masterpiece+0.236
 favourite+0.233
 brand+0.215
 usual+0.209
Neg logit contributions
crow-0.222
Leave-0.206
Bad-0.206
vious-0.201
ases-0.201
Token They
Token ID1119
Feature activation-1.35e-01

Pos logit contributions
crow+0.006
Leave+0.005
Bad+0.005
Stop+0.005
vious+0.005
Neg logit contributions
pron-0.006
 masterpiece-0.006
 favourite-0.006
 collection-0.005
ail-0.005
Token make
Token ID787
Feature activation-1.70e+00

Pos logit contributions
pron+0.012
 masterpiece+0.011
 favourite+0.011
 brand+0.010
ail+0.010
Neg logit contributions
crow-0.009
Leave-0.009
Bad-0.009
Stop-0.009
vious-0.008
Token a
Token ID257
Feature activation+1.28e-01

Pos logit contributions
pron+0.107
 favourite+0.099
 masterpiece+0.097
 collection+0.086
 favorite+0.085
Neg logit contributions
crow-0.161
Leave-0.155
Bad-0.154
Stop-0.149
vious-0.147
Token big
Token ID1263
Feature activation-5.87e+00

Pos logit contributions
Bad+0.011
crow+0.010
Leave+0.010
Stop+0.010
 hunters+0.010
Neg logit contributions
pron-0.008
 favourite-0.007
 masterpiece-0.007
ail-0.007
ilda-0.007
Token pile
Token ID14540
Feature activation-4.39e+00

Pos logit contributions
pron+0.392
 favourite+0.338
 masterpiece+0.328
 usual+0.305
ail+0.302
Neg logit contributions
crow-0.525
Bad-0.509
Leave-0.503
Stop-0.488
vious-0.485
Token of
Token ID286
Feature activation+2.45e+00

Pos logit contributions
pron+0.422
 favourite+0.387
 masterpiece+0.386
 collection+0.354
 brand+0.354
Neg logit contributions
crow-0.274
Leave-0.256
Bad-0.251
vious-0.243
ases-0.239
Token sand
Token ID6450
Feature activation-3.04e+00

Pos logit contributions
crow+0.221
Leave+0.215
Bad+0.213
Stop+0.206
vious+0.204
Neg logit contributions
pron-0.164
 favourite-0.149
 masterpiece-0.148
 collection-0.133
 brand-0.130
Token and
Token ID290
Feature activation-3.76e-02

Pos logit contributions
pron+0.248
 favourite+0.214
 masterpiece+0.213
 brand+0.196
 usual+0.193
Neg logit contributions
crow-0.231
ases-0.222
eper-0.218
 hunters-0.212
Leave-0.211
Token say
Token ID910
Feature activation+2.19e+00

Pos logit contributions
pron+0.003
 masterpiece+0.003
 favourite+0.002
ail+0.002
 brand+0.002
Neg logit contributions
Leave-0.003
Bad-0.003
crow-0.003
Stop-0.003
vious-0.003
Token box
Token ID3091
Feature activation-7.75e-01

Pos logit contributions
pron+0.135
 favourite+0.123
 masterpiece+0.123
 collection+0.111
 brand+0.109
Neg logit contributions
crow-0.141
Leave-0.136
Bad-0.135
Stop-0.130
vious-0.129
Token opened
Token ID4721
Feature activation-1.92e+00

Pos logit contributions
pron+0.062
 favourite+0.055
 masterpiece+0.053
 usual+0.049
 favorite+0.049
Neg logit contributions
crow-0.062
Leave-0.059
Bad-0.055
vious-0.055
Stop-0.054
Token up
Token ID510
Feature activation-8.90e-01

Pos logit contributions
pron+0.176
 favourite+0.157
 masterpiece+0.155
 usual+0.144
 collection+0.144
Neg logit contributions
crow-0.128
Leave-0.121
Bad-0.119
Stop-0.116
vious-0.115
Token with
Token ID351
Feature activation+1.52e+00

Pos logit contributions
pron+0.088
 favourite+0.076
 masterpiece+0.076
 collection+0.071
ail+0.069
Neg logit contributions
crow-0.057
Leave-0.053
Bad-0.051
Stop-0.051
vious-0.051
Token candy
Token ID18550
Feature activation-2.07e-01

Pos logit contributions
crow+0.107
Leave+0.103
Bad+0.103
Stop+0.100
vious+0.099
Neg logit contributions
pron-0.136
 masterpiece-0.118
 favourite-0.117
ail-0.111
 collection-0.110
Token inside
Token ID2641
Feature activation-1.10e+00

Pos logit contributions
pron+0.018
 favourite+0.017
 masterpiece+0.017
 usual+0.015
 favorite+0.015
Neg logit contributions
crow-0.014
Leave-0.013
Bad-0.013
Stop-0.013
vious-0.013
Token!
Token ID0
Feature activation-2.98e+00

Pos logit contributions
pron+0.102
 favourite+0.095
 masterpiece+0.091
 favorite+0.086
 collection+0.084
Neg logit contributions
crow-0.071
Leave-0.066
Bad-0.065
Stop-0.064
vious-0.063
Token
Token ID198
Feature activation-3.41e-01

Pos logit contributions
pron+0.292
 favourite+0.265
 masterpiece+0.261
 collection+0.251
 usual+0.247
Neg logit contributions
crow-0.181
Stop-0.172
Leave-0.166
Bad-0.160
Hey-0.158
Token
Token ID198
Feature activation-3.35e-01

Pos logit contributions
pron+0.032
 favourite+0.029
 masterpiece+0.029
 collection+0.028
 usual+0.027
Neg logit contributions
crow-0.022
Leave-0.021
Stop-0.020
Bad-0.020
Hey-0.019
TokenSarah
Token ID29284
Feature activation-2.42e+00

Pos logit contributions
pron+0.026
 favourite+0.024
 masterpiece+0.024
 collection+0.022
 brand+0.021
Neg logit contributions
crow-0.027
Leave-0.026
Bad-0.025
Stop-0.024
vious-0.024
Token was
Token ID373
Feature activation-1.42e+00

Pos logit contributions
pron+0.193
 favourite+0.165
 masterpiece+0.162
 usual+0.159
 favorite+0.148
Neg logit contributions
crow-0.181
Leave-0.177
Bad-0.177
Stop-0.171
eper-0.170
Token Mom
Token ID11254
Feature activation-5.52e+00

Pos logit contributions
pron+0.367
 masterpiece+0.344
 favourite+0.321
 usual+0.304
 collection+0.303
Neg logit contributions
crow-0.381
Bad-0.366
Leave-0.357
Stop-0.354
Hey-0.347
Token said
Token ID531
Feature activation-1.23e+00

Pos logit contributions
pron+0.396
 favourite+0.376
 masterpiece+0.367
 usual+0.345
 brand+0.336
Neg logit contributions
crow-0.466
vious-0.426
Bad-0.422
eper-0.417
Stop-0.412
Token,
Token ID11
Feature activation+1.13e+00

Pos logit contributions
pron+0.113
 masterpiece+0.106
 favourite+0.103
 collection+0.096
 brand+0.095
Neg logit contributions
crow-0.080
Bad-0.073
Leave-0.073
vious-0.070
ases-0.069
Token "
Token ID366
Feature activation-1.75e-01

Pos logit contributions
Leave+0.081
crow+0.081
Bad+0.080
Stop+0.074
vious+0.073
Neg logit contributions
 masterpiece-0.087
pron-0.087
 favourite-0.087
 collection-0.082
 usual-0.080
TokenYour
Token ID7120
Feature activation+4.08e+00

Pos logit contributions
pron+0.016
 favourite+0.014
 masterpiece+0.014
 usual+0.013
 favorite+0.013
Neg logit contributions
crow-0.012
Bad-0.011
Leave-0.011
vious-0.011
ases-0.011
Token favorite
Token ID4004
Feature activation-1.10e+01

Pos logit contributions
crow+0.380
Leave+0.379
Bad+0.373
vious+0.368
Stop+0.363
Neg logit contributions
pron-0.227
 masterpiece-0.211
onna-0.187
 collection-0.175
 favourite-0.171
Token color
Token ID3124
Feature activation-2.24e+00

Pos logit contributions
pron+0.869
 masterpiece+0.826
 favourite+0.788
 usual+0.720
 brand+0.716
Neg logit contributions
crow-0.863
Leave-0.798
Bad-0.797
Stop-0.775
vious-0.765
Token is
Token ID318
Feature activation+1.16e+00

Pos logit contributions
pron+0.227
 masterpiece+0.217
 favourite+0.206
icol+0.201
 usual+0.194
Neg logit contributions
crow-0.115
vious-0.098
ases-0.095
Bad-0.092
Leave-0.091
Token blue
Token ID4171
Feature activation-5.03e+00

Pos logit contributions
crow+0.068
Bad+0.067
 hunters+0.064
vious+0.064
Leave+0.063
Neg logit contributions
pron-0.098
 masterpiece-0.096
ail-0.092
 favourite-0.089
 complexion-0.088
Token,
Token ID11
Feature activation+1.14e+00

Pos logit contributions
pron+0.449
 masterpiece+0.417
 favourite+0.412
 collection+0.379
 usual+0.376
Neg logit contributions
crow-0.345
Leave-0.325
Bad-0.322
vious-0.313
Stop-0.311
Token right
Token ID826
Feature activation+2.27e+00

Pos logit contributions
crow+0.088
Bad+0.087
Leave+0.087
Stop+0.084
vious+0.082
Neg logit contributions
pron-0.083
 masterpiece-0.080
 favourite-0.076
ail-0.074
 collection-0.074
Token a
Token ID257
Feature activation+1.95e-01

Pos logit contributions
pron+0.142
 masterpiece+0.124
ouse+0.121
ail+0.121
 collection+0.118
Neg logit contributions
Bad-0.068
Leave-0.066
Stop-0.064
 hunters-0.063
Hey-0.062
Token trail
Token ID8025
Feature activation-2.82e+00

Pos logit contributions
Leave+0.014
crow+0.014
Bad+0.014
 hunters+0.013
 bully+0.013
Neg logit contributions
pron-0.012
 masterpiece-0.011
ail-0.010
 favourite-0.010
ouse-0.010
Token!
Token ID0
Feature activation-3.02e+00

Pos logit contributions
pron+0.239
 masterpiece+0.224
 favourite+0.219
 brand+0.198
 collection+0.196
Neg logit contributions
crow-0.202
Leave-0.187
vious-0.185
Bad-0.176
Stop-0.174
Token
Token ID198
Feature activation-3.63e-01

Pos logit contributions
pron+0.299
 masterpiece+0.289
 collection+0.270
 favourite+0.264
 usual+0.258
Neg logit contributions
crow-0.162
Stop-0.161
Leave-0.160
Hey-0.149
Bad-0.147
Token
Token ID198
Feature activation-3.65e-01

Pos logit contributions
pron+0.037
 masterpiece+0.035
 favourite+0.033
 collection+0.033
 brand+0.031
Neg logit contributions
crow-0.020
Stop-0.019
Leave-0.019
Bad-0.018
Hey-0.017
TokenEm
Token ID10161
Feature activation-9.22e+00

Pos logit contributions
pron+0.029
 masterpiece+0.028
 favourite+0.027
 collection+0.026
 usual+0.025
Neg logit contributions
Leave-0.027
crow-0.026
Bad-0.026
Stop-0.026
Hey-0.025
Tokenma
Token ID2611
Feature activation-6.66e-01

Pos logit contributions
pron+0.748
 favourite+0.714
 masterpiece+0.690
 usual+0.639
 brand+0.638
Neg logit contributions
crow-0.679
Bad-0.658
Leave-0.655
Stop-0.644
vious-0.623
Token got
Token ID1392
Feature activation-2.12e-01

Pos logit contributions
pron+0.059
 masterpiece+0.053
 brand+0.050
 favourite+0.050
 usual+0.048
Neg logit contributions
crow-0.048
eper-0.044
vious-0.042
Leave-0.041
Hey-0.041
Token ready
Token ID3492
Feature activation-6.77e-01

Pos logit contributions
pron+0.017
 masterpiece+0.016
 favourite+0.015
 collection+0.014
 brand+0.014
Neg logit contributions
crow-0.016
Leave-0.016
Bad-0.015
vious-0.015
Stop-0.015
Token to
Token ID284
Feature activation-1.52e+00

Pos logit contributions
pron+0.063
 masterpiece+0.060
 favourite+0.058
 collection+0.056
oph+0.054
Neg logit contributions
ting-0.034
crow-0.031
Leave-0.031
vious-0.030
smart-0.029
Token go
Token ID467
Feature activation-1.14e-01

Pos logit contributions
pron+0.138
 favourite+0.125
 masterpiece+0.124
 brand+0.113
 favorite+0.111
Neg logit contributions
crow-0.100
Leave-0.098
Stop-0.092
Bad-0.091
ases-0.090
Token many
Token ID867
Feature activation-2.09e+00

Pos logit contributions
pron+0.481
 masterpiece+0.440
ail+0.410
 collection+0.395
 favourite+0.391
Neg logit contributions
crow-0.321
Leave-0.320
Bad-0.317
Stop-0.308
 hunters-0.304
Token games
Token ID1830
Feature activation+1.96e+00

Pos logit contributions
pron+0.153
 favourite+0.142
 masterpiece+0.139
 collection+0.127
 favorite+0.124
Neg logit contributions
crow-0.178
Leave-0.172
Bad-0.171
Stop-0.165
vious-0.162
Token,
Token ID11
Feature activation+1.27e+00

Pos logit contributions
crow+0.131
Leave+0.120
ases+0.120
Bad+0.118
 hunters+0.115
Neg logit contributions
pron-0.179
 masterpiece-0.164
 favourite-0.157
 brand-0.146
ail-0.144
Token but
Token ID475
Feature activation-1.64e+00

Pos logit contributions
crow+0.096
Leave+0.095
Bad+0.093
Stop+0.090
vious+0.089
Neg logit contributions
pron-0.102
 masterpiece-0.094
 favourite-0.090
 collection-0.085
ail-0.084
Token their
Token ID511
Feature activation-7.33e-01

Pos logit contributions
pron+0.118
 masterpiece+0.109
 favourite+0.097
ail+0.097
 brand+0.095
Neg logit contributions
crow-0.139
Bad-0.138
Leave-0.135
Stop-0.130
vious-0.127
Token favorite
Token ID4004
Feature activation-1.09e+01

Pos logit contributions
pron+0.034
 masterpiece+0.025
ail+0.021
 brand+0.020
onna+0.020
Neg logit contributions
crow-0.080
Bad-0.080
Leave-0.078
Stop-0.077
vious-0.076
Token was
Token ID373
Feature activation-1.40e+00

Pos logit contributions
pron+0.793
 masterpiece+0.711
 favourite+0.697
 brand+0.632
 collection+0.621
Neg logit contributions
crow-0.938
Bad-0.888
Leave-0.875
Stop-0.859
vious-0.840
Token pretend
Token ID16614
Feature activation+1.01e+00

Pos logit contributions
pron+0.123
 masterpiece+0.115
 favourite+0.110
ail+0.105
 collection+0.104
Neg logit contributions
crow-0.094
Bad-0.090
Leave-0.088
vious-0.086
 hunters-0.084
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
crow+0.081
Bad+0.076
Leave+0.075
Stop+0.074
ases+0.074
Neg logit contributions
pron-0.075
 masterpiece-0.066
 favourite-0.065
ail-0.060
 brand-0.059
Token They
Token ID1119
Feature activation+2.94e-02

Pos logit contributions
crow+0.017
Leave+0.016
Bad+0.016
Stop+0.015
vious+0.015
Neg logit contributions
pron-0.017
 masterpiece-0.016
 favourite-0.015
 collection-0.014
 brand-0.014
Token pretended
Token ID36766
Feature activation+1.36e+00

Pos logit contributions
crow+0.002
Leave+0.002
vious+0.002
Bad+0.002
Stop+0.002
Neg logit contributions
pron-0.002
 masterpiece-0.002
 favourite-0.002
 brand-0.002
ail-0.002
Token.
Token ID13
Feature activation+2.30e-01

Pos logit contributions
pron+0.572
 favourite+0.525
 masterpiece+0.514
ail+0.480
 brand+0.474
Neg logit contributions
crow-0.453
Bad-0.403
vious-0.403
Leave-0.402
Stop-0.398
Token
Token ID220
Feature activation-1.15e+00

Pos logit contributions
crow+0.017
Leave+0.016
Bad+0.016
Stop+0.015
vious+0.015
Neg logit contributions
pron-0.020
 masterpiece-0.018
 favourite-0.018
 collection-0.016
 usual-0.016
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
pron+0.102
 masterpiece+0.094
 favourite+0.093
 collection+0.087
 usual+0.085
Neg logit contributions
crow-0.079
Leave-0.074
Bad-0.074
Stop-0.071
vious-0.070
Token
Token ID198
Feature activation-3.37e-01

Pos logit contributions
pron+0.027
 masterpiece+0.025
 favourite+0.025
 collection+0.023
 brand+0.022
Neg logit contributions
crow-0.023
Leave-0.022
Bad-0.022
Stop-0.021
vious-0.021
TokenS
Token ID50
Feature activation+2.08e+00

Pos logit contributions
pron+0.031
 favourite+0.028
 masterpiece+0.028
 collection+0.026
 usual+0.025
Neg logit contributions
crow-0.023
Leave-0.022
Bad-0.022
vious-0.021
Stop-0.021
Tokenally
Token ID453
Feature activation-8.74e+00

Pos logit contributions
crow+0.223
Bad+0.213
Leave+0.211
vious+0.211
Stop+0.210
Neg logit contributions
pron-0.105
 favourite-0.093
 masterpiece-0.089
 brand-0.078
 collection-0.076
Token couldn
Token ID3521
Feature activation-6.77e+00

Pos logit contributions
pron+0.686
 favourite+0.614
 masterpiece+0.603
 brand+0.575
 usual+0.571
Neg logit contributions
crow-0.678
vious-0.639
Bad-0.635
Leave-0.634
Stop-0.619
Token't
Token ID470
Feature activation+9.58e-01

Pos logit contributions
pron+0.588
 favourite+0.539
 masterpiece+0.534
 collection+0.495
 brand+0.485
Neg logit contributions
crow-0.489
Leave-0.467
Bad-0.458
Stop-0.447
vious-0.442
Token wait
Token ID4043
Feature activation-5.13e-01

Pos logit contributions
crow+0.072
Leave+0.069
Bad+0.067
vious+0.066
Stop+0.066
Neg logit contributions
pron-0.079
 favourite-0.072
 masterpiece-0.071
 brand-0.066
 collection-0.065
Token to
Token ID284
Feature activation-1.56e+00

Pos logit contributions
pron+0.044
 masterpiece+0.038
 favourite+0.037
ail+0.036
ouse+0.036
Neg logit contributions
Leave-0.033
vious-0.031
ases-0.031
crow-0.030
Stop-0.030
Token give
Token ID1577
Feature activation+2.03e+00

Pos logit contributions
pron+0.133
 favourite+0.123
 masterpiece+0.117
ail+0.110
 favorite+0.109
Neg logit contributions
crow-0.109
Leave-0.106
Bad-0.104
Stop-0.102
ases-0.099
Token than
Token ID621
Feature activation+1.72e+00

Pos logit contributions
Leave+0.430
crow+0.424
Bad+0.409
vious+0.406
Stop+0.404
Neg logit contributions
 favourite-0.449
pron-0.446
 favorite-0.418
 masterpiece-0.413
 collection-0.412
Token having
Token ID1719
Feature activation-1.35e+00

Pos logit contributions
crow+0.127
Leave+0.121
Bad+0.118
Stop+0.114
vious+0.114
Neg logit contributions
pron-0.145
 favourite-0.134
 masterpiece-0.133
 usual-0.125
 collection-0.123
Token a
Token ID257
Feature activation+1.04e-01

Pos logit contributions
pron+0.093
 favourite+0.091
 masterpiece+0.087
 collection+0.081
 favorite+0.080
Neg logit contributions
crow-0.115
Leave-0.110
Bad-0.108
Stop-0.105
vious-0.104
Token l
Token ID300
Feature activation-2.68e+00

Pos logit contributions
crow+0.009
Leave+0.009
Bad+0.009
Stop+0.008
vious+0.008
Neg logit contributions
pron-0.008
 favourite-0.007
 masterpiece-0.007
 collection-0.006
 usual-0.006
Tokenoll
Token ID692
Feature activation-9.71e+00

Pos logit contributions
pron+0.112
 favourite+0.094
 masterpiece+0.080
 collection+0.078
ail+0.073
Neg logit contributions
Bad-0.312
Leave-0.310
Stop-0.305
crow-0.301
Hey-0.290
Tokenipop
Token ID42800
Feature activation-8.91e+00

Pos logit contributions
pron+0.384
 favourite+0.314
 masterpiece+0.310
 collection+0.250
 usual+0.237
Neg logit contributions
crow-1.151
Leave-1.123
Bad-1.118
Stop-1.092
vious-1.083
Token.
Token ID13
Feature activation+3.52e-02

Pos logit contributions
pron+0.712
 favourite+0.651
 masterpiece+0.646
 collection+0.592
 usual+0.580
Neg logit contributions
crow-0.691
Leave-0.667
Bad-0.662
Stop-0.639
vious-0.628
Token He
Token ID679
Feature activation+3.16e+00

Pos logit contributions
crow+0.003
Leave+0.003
Bad+0.003
Stop+0.003
vious+0.003
Neg logit contributions
pron-0.003
 favourite-0.002
 masterpiece-0.002
 favorite-0.002
onna-0.002
Token learned
Token ID4499
Feature activation+4.83e+00

Pos logit contributions
crow+0.230
Bad+0.223
Leave+0.222
vious+0.212
Stop+0.212
Neg logit contributions
pron-0.269
 masterpiece-0.245
 favourite-0.244
 collection-0.222
 usual-0.221
Token that
Token ID326
Feature activation-2.85e+00

Pos logit contributions
crow+0.407
Bad+0.393
Leave+0.390
Stop+0.377
vious+0.373
Neg logit contributions
pron-0.361
 masterpiece-0.324
 favourite-0.318
 collection-0.291
 usual-0.281
Token he
Token ID339
Feature activation+4.99e-01

Pos logit contributions
pron+0.227
 favourite+0.211
 masterpiece+0.208
 collection+0.193
 usual+0.190
Neg logit contributions
crow-0.221
Leave-0.213
Bad-0.210
Stop-0.204
vious-0.203