TOP ACTIVATIONS
MAX = 16.621

sky . The grass was freshly cut , and a gentle
went home and enjoyed his freshly caught fish . <|endoftext|> Once
a cup of warm , freshly made soup and a cozy
saw her mother holding a freshly - b aked muff in
it when the snow was freshly fallen . Today , he
the church and noticed a freshly dug hole in the ground
Tim my a warm , freshly baked cookie .
so happy to see a freshly baked bean . After that
to play and explore the freshly organized lawn . <|endoftext|> Once
. The sweet smell of freshly baked port filled the house
he saw a basket of freshly baked bread . It smelled
crown and playing in the freshly cut grass . It looked
the sweet aroma of a freshly baked cake .
tidy , with his clothes freshly cleaned . Suddenly , he
mom my surprised him with freshly baked cookies . Tim my
Andy looked at the freshly printed picture and smiled .
them over for a fair yt ale tea party . They
was walking through a fair yt ale . She fell asleep
so attractive in the a pron that everyone wanted to see
and saw a magical fair yt ale creature called a n

MIN ACTIVATIONS
MIN = -16.511

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

INTERVAL 8.338 - 16.621
CONTAINS 0.346%

enough money for an adventurous holiday !" Da isy
thoughtful . Su zy knew that she could trust
who wanted to have a picnic . They packed a basket
They had ruined the cool skirt . Their mom
. The animals and the long snake protected the gum tree

INTERVAL 0.055 - 8.338
CONTAINS 50.565%

Whenever they did , they were always happy because they were
bird ie ! The bird ie felt very scared and didn
jump into the nest . The bunny was so
friends there . From then on , Benny didn 't mind
watch the film tomorrow . Sara cal ms down and says

INTERVAL -8.228 - 0.055
CONTAINS 48.589%

saw some children playing on the swings . They looked so
his head and it flew away . Tim my started to
! He noticed a crowd at the park and
lift this rock ?" she asked . Her
for food . Mom my will be mad if you make

INTERVAL -16.511 - -8.228
CONTAINS 0.500%

was just a joke . Come on , let 's play
fan in the forest . If you find it , it
It was so small and scared , so the girl decided
Lily like to see the animals and learn their names .
saw a big T - Rex and said , " Mom
Token sky
Token ID6766
Feature activation-1.99e+00

Pos logit contributions
crow+0.101
Bad+0.099
Leave+0.098
eper+0.092
vious+0.092
Neg logit contributions
pron-0.086
 favourite-0.081
 masterpiece-0.080
 brand-0.072
 favorite-0.071
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
crow+0.148
Bad+0.142
Leave+0.140
vious+0.133
eper+0.131
Neg logit contributions
pron-0.159
 favourite-0.149
 masterpiece-0.149
 brand-0.136
 favorite-0.133
Token The
Token ID383
Feature activation+2.50e-01

Pos logit contributions
pron+0.011
 favourite+0.010
 masterpiece+0.010
 favorite+0.009
 brand+0.009
Neg logit contributions
crow-0.011
Bad-0.011
Leave-0.011
eper-0.010
vious-0.010
Token grass
Token ID8701
Feature activation-2.64e-01

Pos logit contributions
pron+0.019
 favourite+0.018
 masterpiece+0.017
 brand+0.016
 favorite+0.016
Neg logit contributions
crow-0.020
Bad-0.019
Leave-0.019
vious-0.018
eper-0.018
Token was
Token ID373
Feature activation+1.74e+00

Pos logit contributions
crow+0.023
Bad+0.021
Leave+0.021
eper+0.020
Hey+0.019
Neg logit contributions
pron-0.019
 masterpiece-0.018
 favourite-0.017
 brand-0.016
 favorite-0.015
Token freshly
Token ID29026
Feature activation+1.66e+01

Pos logit contributions
pron+0.121
 masterpiece+0.114
 favourite+0.108
ail+0.105
 collection+0.103
Neg logit contributions
Bad-0.136
crow-0.135
Leave-0.133
eper-0.124
vious-0.124
Token cut
Token ID2005
Feature activation+3.41e+00

Pos logit contributions
pron+1.819
 favourite+1.762
 masterpiece+1.740
 brand+1.625
 favorite+1.624
Neg logit contributions
crow-0.749
Bad-0.724
Leave-0.700
vious-0.627
Stop-0.614
Token,
Token ID11
Feature activation-1.07e+00

Pos logit contributions
pron+0.267
 favourite+0.257
 masterpiece+0.249
 brand+0.231
 favorite+0.230
Neg logit contributions
Bad-0.256
crow-0.252
Leave-0.251
Stop-0.233
ases-0.232
Token and
Token ID290
Feature activation+4.35e-01

Pos logit contributions
crow+0.082
Bad+0.081
Leave+0.080
vious+0.074
Stop+0.074
Neg logit contributions
pron-0.082
 favourite-0.078
 masterpiece-0.077
 brand-0.070
 favorite-0.069
Token a
Token ID257
Feature activation+1.33e-01

Pos logit contributions
pron+0.036
 masterpiece+0.034
 favourite+0.034
 brand+0.031
 favorite+0.030
Neg logit contributions
crow-0.031
Bad-0.030
Leave-0.029
Stop-0.028
eper-0.027
Token gentle
Token ID10296
Feature activation-3.38e+00

Pos logit contributions
pron+0.008
 favourite+0.008
 masterpiece+0.008
 favorite+0.007
 brand+0.007
Neg logit contributions
Bad-0.011
crow-0.011
Leave-0.011
Stop-0.010
eper-0.010
Token went
Token ID1816
Feature activation+1.64e+00

Pos logit contributions
crow+0.111
Bad+0.109
Leave+0.107
vious+0.102
eper+0.101
Neg logit contributions
pron-0.081
 favourite-0.076
 masterpiece-0.075
 brand-0.067
 favorite-0.066
Token home
Token ID1363
Feature activation+8.13e-01

Pos logit contributions
pron+0.126
 favourite+0.119
 masterpiece+0.118
 brand+0.107
 favorite+0.106
Neg logit contributions
crow-0.129
Bad-0.125
Leave-0.123
vious-0.116
eper-0.116
Token and
Token ID290
Feature activation+3.80e-01

Pos logit contributions
pron+0.070
 favourite+0.067
 masterpiece+0.066
 favorite+0.060
 brand+0.059
Neg logit contributions
crow-0.051
Bad-0.049
Leave-0.049
eper-0.047
vious-0.045
Token enjoyed
Token ID8359
Feature activation+4.43e+00

Pos logit contributions
pron+0.028
 favourite+0.027
 masterpiece+0.027
 favorite+0.024
 brand+0.023
Neg logit contributions
crow-0.029
Bad-0.029
Leave-0.027
eper-0.026
vious-0.025
Token his
Token ID465
Feature activation-3.09e+00

Pos logit contributions
pron+0.420
 masterpiece+0.396
 favourite+0.394
ail+0.363
 favorite+0.361
Neg logit contributions
Bad-0.248
Leave-0.245
crow-0.243
eper-0.220
ases-0.216
Token freshly
Token ID29026
Feature activation+1.66e+01

Pos logit contributions
crow+0.254
Bad+0.253
Leave+0.245
vious+0.233
ases+0.230
Neg logit contributions
pron-0.198
 masterpiece-0.178
 favourite-0.174
ilda-0.168
yt-0.163
Token caught
Token ID4978
Feature activation-3.39e+00

Pos logit contributions
pron+1.079
 favourite+1.020
 masterpiece+1.013
 brand+0.920
 favorite+0.887
Neg logit contributions
crow-1.460
Bad-1.420
Leave-1.396
eper-1.324
vious-1.321
Token fish
Token ID5916
Feature activation-5.77e+00

Pos logit contributions
crow+0.278
Bad+0.272
Leave+0.268
vious+0.253
Stop+0.251
Neg logit contributions
pron-0.245
 favourite-0.233
 masterpiece-0.230
 brand-0.208
 favorite-0.206
Token.
Token ID13
Feature activation-1.86e-02

Pos logit contributions
crow+0.469
Bad+0.459
Leave+0.452
vious+0.425
Stop+0.425
Neg logit contributions
pron-0.422
 favourite-0.401
 masterpiece-0.395
 brand-0.358
 favorite-0.354
Token<|endoftext|>
Token ID50256
Feature activation+1.06e+00

Pos logit contributions
crow+0.001
Bad+0.001
Leave+0.001
vious+0.001
eper+0.001
Neg logit contributions
pron-0.001
 masterpiece-0.001
 favourite-0.001
 brand-0.001
 favorite-0.001
TokenOnce
Token ID7454
Feature activation-2.61e+00

Pos logit contributions
pron+0.068
 favourite+0.066
 masterpiece+0.062
 usual+0.058
 favorite+0.058
Neg logit contributions
Bad-0.090
Leave-0.089
crow-0.086
vious-0.084
eper-0.081
Token a
Token ID257
Feature activation+5.69e-02

Pos logit contributions
crow+0.486
Bad+0.466
Leave+0.449
vious+0.444
eper+0.438
Neg logit contributions
pron-0.554
 masterpiece-0.512
 favourite-0.486
 brand-0.457
yt-0.441
Token cup
Token ID6508
Feature activation+4.95e+00

Pos logit contributions
 masterpiece+0.003
pron+0.003
 favourite+0.003
oph+0.003
ilda+0.003
Neg logit contributions
crow-0.004
Bad-0.004
 bully-0.004
Leave-0.004
 brake-0.004
Token of
Token ID286
Feature activation-2.69e+00

Pos logit contributions
pron+0.486
 masterpiece+0.480
 favourite+0.469
 usual+0.428
 favorite+0.426
Neg logit contributions
crow-0.274
vious-0.227
Leave-0.223
Bad-0.219
eper-0.216
Token warm
Token ID5814
Feature activation+4.35e+00

Pos logit contributions
crow+0.230
Bad+0.221
Leave+0.211
vious+0.206
Stop+0.205
Neg logit contributions
pron-0.185
 masterpiece-0.171
 favourite-0.165
ail-0.149
 brand-0.147
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
pron+0.324
 masterpiece+0.304
 favourite+0.298
 usual+0.266
 brand+0.266
Neg logit contributions
crow-0.352
Leave-0.319
Bad-0.317
vious-0.307
Stop-0.302
Token freshly
Token ID29026
Feature activation+1.66e+01

Pos logit contributions
Leave+0.080
Bad+0.080
crow+0.079
vious+0.074
 hunters+0.073
Neg logit contributions
pron-0.070
 masterpiece-0.069
 favourite-0.065
ail-0.064
 collection-0.060
Token made
Token ID925
Feature activation+6.00e-01

Pos logit contributions
pron+1.173
 masterpiece+1.130
 favourite+1.116
 brand+1.024
 favorite+0.982
Neg logit contributions
crow-1.358
Bad-1.327
Leave-1.299
eper-1.238
Stop-1.223
Token soup
Token ID17141
Feature activation+3.46e+00

Pos logit contributions
pron+0.059
 favourite+0.057
 masterpiece+0.056
 brand+0.052
 favorite+0.052
Neg logit contributions
crow-0.033
Bad-0.032
Leave-0.031
vious-0.029
eper-0.028
Token and
Token ID290
Feature activation+3.87e-01

Pos logit contributions
pron+0.283
 masterpiece+0.268
 favourite+0.260
 usual+0.239
 brand+0.236
Neg logit contributions
crow-0.221
eper-0.203
ases-0.200
 hunters-0.198
Bad-0.196
Token a
Token ID257
Feature activation+7.45e-02

Pos logit contributions
pron+0.028
 masterpiece+0.025
 favourite+0.025
ail+0.023
 favorite+0.022
Neg logit contributions
crow-0.030
Bad-0.029
Leave-0.029
 hunters-0.027
vious-0.027
Token cozy
Token ID37438
Feature activation+6.18e+00

Pos logit contributions
pron+0.004
 favourite+0.004
 masterpiece+0.004
ilda+0.004
ail+0.003
Neg logit contributions
Bad-0.006
crow-0.006
Leave-0.006
 bully-0.006
eper-0.006
Token saw
Token ID2497
Feature activation-3.68e-01

Pos logit contributions
pron+0.419
 masterpiece+0.396
 favourite+0.394
 favorite+0.356
 brand+0.354
Neg logit contributions
Bad-0.340
crow-0.338
Leave-0.328
eper-0.319
vious-0.308
Token her
Token ID607
Feature activation+3.19e+00

Pos logit contributions
crow+0.030
Bad+0.029
Leave+0.029
vious+0.027
eper+0.027
Neg logit contributions
pron-0.028
 favourite-0.026
 masterpiece-0.026
 brand-0.023
 favorite-0.023
Token mother
Token ID2802
Feature activation+6.35e+00

Pos logit contributions
pron+0.212
 masterpiece+0.165
onna+0.162
cakes+0.149
 favourite+0.147
Neg logit contributions
Bad-0.257
 hunters-0.256
eper-0.255
crow-0.249
 bully-0.237
Token holding
Token ID4769
Feature activation+1.09e+00

Pos logit contributions
pron+0.470
 favourite+0.445
 masterpiece+0.441
 brand+0.401
 favorite+0.392
Neg logit contributions
crow-0.509
Bad-0.498
Leave-0.488
vious-0.461
Stop-0.457
Token a
Token ID257
Feature activation+7.68e-02

Pos logit contributions
pron+0.075
 favourite+0.073
 masterpiece+0.071
 brand+0.064
 favorite+0.064
Neg logit contributions
crow-0.092
Bad-0.091
Leave-0.090
vious-0.085
Stop-0.084
Token freshly
Token ID29026
Feature activation+1.66e+01

Pos logit contributions
 masterpiece+0.004
 favourite+0.004
pron+0.004
ail+0.004
ilda+0.004
Neg logit contributions
Bad-0.007
crow-0.007
Leave-0.006
 bully-0.006
Stop-0.006
Token-
Token ID12
Feature activation+1.72e+00

Pos logit contributions
pron+1.250
 favourite+1.179
 masterpiece+1.164
 brand+1.060
 favorite+1.045
Neg logit contributions
crow-1.308
Bad-1.278
Leave-1.257
vious-1.184
eper-1.174
Tokenb
Token ID65
Feature activation-3.60e+00

Pos logit contributions
pron+0.126
 favourite+0.119
 masterpiece+0.113
 favorite+0.105
 brand+0.103
Neg logit contributions
Bad-0.138
Leave-0.136
crow-0.136
eper-0.128
ases-0.127
Tokenaked
Token ID4335
Feature activation-7.33e+00

Pos logit contributions
crow+0.282
Bad+0.272
Leave+0.267
eper+0.263
ases+0.254
Neg logit contributions
pron-0.266
 favourite-0.253
 masterpiece-0.253
 brand-0.231
 favorite-0.224
Token muff
Token ID27563
Feature activation+3.54e+00

Pos logit contributions
crow+0.580
Bad+0.575
Leave+0.560
vious+0.526
Stop+0.525
Neg logit contributions
pron-0.546
 favourite-0.520
 masterpiece-0.515
 brand-0.467
 favorite-0.459
Tokenin
Token ID259
Feature activation-1.44e+00

Pos logit contributions
pron+0.367
 favourite+0.348
 masterpiece+0.346
 brand+0.320
 favorite+0.319
Neg logit contributions
Bad-0.182
crow-0.182
Leave-0.181
Stop-0.159
vious-0.152
Token it
Token ID340
Feature activation+3.74e-01

Pos logit contributions
pron+0.230
 masterpiece+0.214
 favourite+0.211
 brand+0.189
ail+0.188
Neg logit contributions
crow-0.227
Bad-0.222
Leave-0.219
Stop-0.205
eper-0.199
Token when
Token ID618
Feature activation-6.78e+00

Pos logit contributions
pron+0.032
 masterpiece+0.030
 favourite+0.029
icol+0.027
 complexion+0.027
Neg logit contributions
crow-0.023
Bad-0.023
Leave-0.022
vious-0.021
 hunters-0.021
Token the
Token ID262
Feature activation-1.49e+00

Pos logit contributions
crow+0.480
Bad+0.478
Leave+0.468
eper+0.429
Stop+0.428
Neg logit contributions
pron-0.555
 masterpiece-0.522
 favourite-0.515
 brand-0.473
 favorite-0.464
Token snow
Token ID6729
Feature activation-8.63e-02

Pos logit contributions
crow+0.123
Bad+0.119
Leave+0.117
vious+0.110
Stop+0.110
Neg logit contributions
pron-0.106
 favourite-0.100
 masterpiece-0.099
 brand-0.090
 favorite-0.088
Token was
Token ID373
Feature activation+1.61e+00

Pos logit contributions
crow+0.007
Bad+0.007
Leave+0.007
eper+0.007
Stop+0.007
Neg logit contributions
pron-0.006
 favourite-0.006
 masterpiece-0.006
 brand-0.005
 favorite-0.005
Token freshly
Token ID29026
Feature activation+1.65e+01

Pos logit contributions
pron+0.114
 masterpiece+0.110
 favourite+0.109
 collection+0.099
 complexion+0.097
Neg logit contributions
crow-0.126
Bad-0.125
Leave-0.122
vious-0.116
eper-0.115
Token fallen
Token ID9292
Feature activation+6.24e-01

Pos logit contributions
pron+1.218
 masterpiece+1.145
 favourite+1.145
 brand+1.041
 favorite+1.012
Neg logit contributions
crow-1.334
Bad-1.301
Leave-1.278
eper-1.208
vious-1.205
Token.
Token ID13
Feature activation+2.59e-02

Pos logit contributions
pron+0.052
 favourite+0.049
 masterpiece+0.049
 favorite+0.044
 brand+0.044
Neg logit contributions
crow-0.044
Bad-0.043
Leave-0.042
vious-0.040
eper-0.039
Token Today
Token ID6288
Feature activation+2.23e+00

Pos logit contributions
pron+0.002
 favourite+0.002
 masterpiece+0.002
 brand+0.002
 favorite+0.002
Neg logit contributions
crow-0.002
Bad-0.002
Leave-0.002
vious-0.002
eper-0.002
Token,
Token ID11
Feature activation-1.23e+00

Pos logit contributions
pron+0.177
 masterpiece+0.163
 favourite+0.160
 brand+0.148
 favorite+0.142
Neg logit contributions
crow-0.175
Bad-0.164
Leave-0.157
vious-0.151
Hey-0.151
Token he
Token ID339
Feature activation-7.79e-01

Pos logit contributions
crow+0.096
Bad+0.094
Leave+0.092
eper+0.086
Stop+0.086
Neg logit contributions
pron-0.094
 masterpiece-0.088
 favourite-0.088
 brand-0.079
 favorite-0.078
Token the
Token ID262
Feature activation-1.19e+00

Pos logit contributions
crow+0.090
Bad+0.088
Leave+0.086
vious+0.082
eper+0.081
Neg logit contributions
pron-0.089
 favourite-0.085
 masterpiece-0.084
 brand-0.076
 favorite-0.076
Token church
Token ID4928
Feature activation+1.40e+00

Pos logit contributions
crow+0.096
Bad+0.093
Leave+0.092
ases+0.087
vious+0.087
Neg logit contributions
pron-0.090
 favourite-0.085
 masterpiece-0.084
 brand-0.077
 favorite-0.076
Token and
Token ID290
Feature activation+3.59e-01

Pos logit contributions
pron+0.111
 favourite+0.103
 masterpiece+0.102
 brand+0.094
 favorite+0.092
Neg logit contributions
crow-0.104
Bad-0.098
Leave-0.096
eper-0.092
vious-0.092
Token noticed
Token ID6810
Feature activation+1.38e+00

Pos logit contributions
pron+0.026
 masterpiece+0.024
 favourite+0.023
 brand+0.021
 favorite+0.021
Neg logit contributions
crow-0.030
Bad-0.029
Leave-0.028
eper-0.027
vious-0.027
Token a
Token ID257
Feature activation+1.16e-02

Pos logit contributions
pron+0.102
 favourite+0.096
 masterpiece+0.095
 brand+0.086
 favorite+0.085
Neg logit contributions
crow-0.111
Bad-0.108
Leave-0.106
vious-0.100
eper-0.100
Token freshly
Token ID29026
Feature activation+1.65e+01

Pos logit contributions
pron+0.001
 favourite+0.001
 masterpiece+0.001
 favorite+0.001
 usual+0.001
Neg logit contributions
crow-0.001
Bad-0.001
Leave-0.001
Stop-0.001
eper-0.001
Token dug
Token ID18735
Feature activation+1.64e+00

Pos logit contributions
pron+1.261
 favourite+1.198
 masterpiece+1.185
 brand+1.081
 favorite+1.065
Neg logit contributions
crow-1.287
Bad-1.256
Leave-1.233
vious-1.156
eper-1.154
Token hole
Token ID7604
Feature activation-1.81e+00

Pos logit contributions
pron+0.122
 favourite+0.116
 masterpiece+0.115
 brand+0.105
 favorite+0.103
Neg logit contributions
crow-0.129
Bad-0.128
Leave-0.125
eper-0.118
vious-0.117
Token in
Token ID287
Feature activation+1.54e+00

Pos logit contributions
crow+0.131
Bad+0.125
Leave+0.124
eper+0.117
vious+0.117
Neg logit contributions
pron-0.149
 favourite-0.140
 masterpiece-0.138
 brand-0.126
 favorite-0.125
Token the
Token ID262
Feature activation-1.41e+00

Pos logit contributions
pron+0.118
 favourite+0.114
 masterpiece+0.113
 brand+0.104
 favorite+0.101
Neg logit contributions
crow-0.117
Bad-0.113
Leave-0.112
vious-0.107
eper-0.105
Token ground
Token ID2323
Feature activation+1.99e-03

Pos logit contributions
crow+0.113
Bad+0.111
Leave+0.109
vious+0.103
eper+0.102
Neg logit contributions
pron-0.105
 favourite-0.099
 masterpiece-0.098
 brand-0.089
 favorite-0.088
Token Tim
Token ID5045
Feature activation+4.32e-01

Pos logit contributions
pron+0.110
 masterpiece+0.103
 favourite+0.102
 brand+0.093
 favorite+0.091
Neg logit contributions
crow-0.091
Bad-0.088
Leave-0.085
eper-0.081
Stop-0.080
Tokenmy
Token ID1820
Feature activation-3.02e+00

Pos logit contributions
pron+0.038
 favourite+0.037
 masterpiece+0.036
 brand+0.034
 favorite+0.034
Neg logit contributions
crow-0.028
Bad-0.028
Leave-0.027
Stop-0.025
eper-0.025
Token a
Token ID257
Feature activation-1.59e-02

Pos logit contributions
crow+0.219
Bad+0.213
Leave+0.205
vious+0.202
eper+0.197
Neg logit contributions
pron-0.241
 masterpiece-0.227
 favourite-0.222
 brand-0.205
 collection-0.196
Token warm
Token ID5814
Feature activation+4.26e+00

Pos logit contributions
Bad+0.001
crow+0.001
 bully+0.001
vious+0.001
Leave+0.001
Neg logit contributions
 masterpiece-0.001
 favourite-0.001
yt-0.001
icol-0.001
ilda-0.001
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
 masterpiece+0.298
 favourite+0.295
pron+0.290
 usual+0.264
yt+0.264
Neg logit contributions
crow-0.330
Bad-0.304
Leave-0.298
vious-0.288
Hey-0.278
Token freshly
Token ID29026
Feature activation+1.65e+01

Pos logit contributions
Bad+0.094
Leave+0.094
crow+0.089
vious+0.088
Stop+0.083
Neg logit contributions
 masterpiece-0.066
ail-0.065
pron-0.065
 favourite-0.062
 collection-0.059
Token baked
Token ID22979
Feature activation+7.82e+00

Pos logit contributions
pron+0.942
 favourite+0.897
 masterpiece+0.892
 brand+0.788
 favorite+0.759
Neg logit contributions
crow-1.578
Bad-1.554
Leave-1.525
vious-1.454
eper-1.448
Token cookie
Token ID19751
Feature activation+3.27e+00

Pos logit contributions
pron+0.516
 favourite+0.487
 masterpiece+0.483
 brand+0.431
 favorite+0.423
Neg logit contributions
crow-0.688
Bad-0.668
Leave-0.656
vious-0.626
eper-0.625
Token.
Token ID13
Feature activation+3.49e-02

Pos logit contributions
pron+0.245
 favourite+0.235
 masterpiece+0.233
 brand+0.215
 favorite+0.207
Neg logit contributions
crow-0.250
Bad-0.234
Leave-0.226
eper-0.225
ases-0.220
Token
Token ID198
Feature activation+6.90e-01

Pos logit contributions
pron+0.003
 masterpiece+0.003
 favourite+0.003
 usual+0.003
 collection+0.003
Neg logit contributions
crow-0.002
Bad-0.002
Leave-0.002
Hey-0.002
Stop-0.002
Token
Token ID198
Feature activation+6.20e-01

Pos logit contributions
pron+0.062
 masterpiece+0.062
 favourite+0.061
 collection+0.056
 brand+0.056
Neg logit contributions
crow-0.042
Bad-0.040
Leave-0.039
Rex-0.036
Hey-0.036
Token so
Token ID523
Feature activation+1.81e-01

Pos logit contributions
pron+0.126
 favourite+0.117
 masterpiece+0.116
 brand+0.103
 usual+0.103
Neg logit contributions
crow-0.123
Bad-0.121
Leave-0.118
eper-0.114
vious-0.112
Token happy
Token ID3772
Feature activation-1.24e+00

Pos logit contributions
pron+0.014
 favourite+0.013
 masterpiece+0.013
 brand+0.011
 favorite+0.011
Neg logit contributions
crow-0.014
Bad-0.014
Leave-0.014
vious-0.013
eper-0.013
Token to
Token ID284
Feature activation+1.69e+00

Pos logit contributions
crow+0.103
Bad+0.101
Leave+0.099
vious+0.094
eper+0.093
Neg logit contributions
pron-0.089
 favourite-0.082
 masterpiece-0.082
 brand-0.074
 favorite-0.072
Token see
Token ID766
Feature activation+2.64e-01

Pos logit contributions
pron+0.158
 favourite+0.151
 masterpiece+0.146
 brand+0.139
 favorite+0.136
Neg logit contributions
crow-0.105
Leave-0.101
Bad-0.101
vious-0.092
ases-0.092
Token a
Token ID257
Feature activation+1.51e-02

Pos logit contributions
pron+0.020
 favourite+0.019
 masterpiece+0.019
 brand+0.017
 favorite+0.017
Neg logit contributions
crow-0.021
Bad-0.020
Leave-0.020
vious-0.019
eper-0.019
Token freshly
Token ID29026
Feature activation+1.64e+01

Pos logit contributions
 favourite+0.001
ail+0.001
 masterpiece+0.001
pron+0.001
 usual+0.001
Neg logit contributions
Bad-0.001
 bully-0.001
crow-0.001
Leave-0.001
Stop-0.001
Token baked
Token ID22979
Feature activation+7.71e+00

Pos logit contributions
pron+1.077
 favourite+1.017
 masterpiece+1.003
 brand+0.900
 favorite+0.882
Neg logit contributions
crow-1.449
Bad-1.417
Leave-1.394
vious-1.322
eper-1.318
Token bean
Token ID26394
Feature activation+5.37e+00

Pos logit contributions
pron+0.445
 favourite+0.440
 masterpiece+0.419
 brand+0.378
 favorite+0.377
Neg logit contributions
crow-0.733
Bad-0.693
Leave-0.678
vious-0.660
eper-0.659
Token.
Token ID13
Feature activation-8.88e-02

Pos logit contributions
pron+0.431
 favourite+0.408
 masterpiece+0.391
 brand+0.367
 favorite+0.365
Neg logit contributions
crow-0.392
Bad-0.362
Leave-0.361
vious-0.353
eper-0.350
Token After
Token ID2293
Feature activation+9.56e-01

Pos logit contributions
crow+0.006
Bad+0.006
Leave+0.005
vious+0.005
Stop+0.005
Neg logit contributions
pron-0.008
 masterpiece-0.008
 favourite-0.007
 brand-0.007
 usual-0.007
Token that
Token ID326
Feature activation+2.82e+00

Pos logit contributions
pron+0.077
 favourite+0.072
 masterpiece+0.070
 favorite+0.064
yt+0.063
Neg logit contributions
Bad-0.069
crow-0.067
Leave-0.066
 hunters-0.064
eper-0.062
Token to
Token ID284
Feature activation+1.60e+00

Pos logit contributions
crow+0.161
Bad+0.157
Leave+0.155
vious+0.146
eper+0.146
Neg logit contributions
pron-0.148
 favourite-0.137
 masterpiece-0.136
 brand-0.123
 favorite-0.121
Token play
Token ID711
Feature activation-1.10e+00

Pos logit contributions
pron+0.135
 favourite+0.127
 masterpiece+0.124
 brand+0.114
 favorite+0.114
Neg logit contributions
crow-0.113
Bad-0.108
Leave-0.108
ases-0.100
eper-0.099
Token and
Token ID290
Feature activation+1.75e-01

Pos logit contributions
crow+0.085
Bad+0.083
Leave+0.081
vious+0.076
eper+0.076
Neg logit contributions
pron-0.085
 favourite-0.081
 masterpiece-0.080
 brand-0.073
 favorite-0.072
Token explore
Token ID7301
Feature activation+6.73e+00

Pos logit contributions
pron+0.014
 masterpiece+0.012
 favourite+0.012
 brand+0.011
ail+0.011
Neg logit contributions
crow-0.012
Leave-0.012
Bad-0.012
 bully-0.011
Stop-0.011
Token the
Token ID262
Feature activation-1.83e+00

Pos logit contributions
pron+0.546
 favourite+0.515
 masterpiece+0.511
 brand+0.465
 favorite+0.461
Neg logit contributions
crow-0.494
Bad-0.481
Leave-0.472
vious-0.441
eper-0.439
Token freshly
Token ID29026
Feature activation+1.64e+01

Pos logit contributions
crow+0.159
Bad+0.156
Leave+0.153
Stop+0.149
Hey+0.144
Neg logit contributions
pron-0.122
 masterpiece-0.105
 favourite-0.105
 brand-0.099
 complexion-0.095
Token organized
Token ID8389
Feature activation+3.22e+00

Pos logit contributions
pron+1.183
 favourite+1.115
 masterpiece+1.103
 brand+1.011
 favorite+0.982
Neg logit contributions
crow-1.353
Bad-1.297
Leave-1.278
eper-1.205
Stop-1.203
Token lawn
Token ID21133
Feature activation+5.71e+00

Pos logit contributions
pron+0.207
 favourite+0.184
 masterpiece+0.180
 brand+0.173
onna+0.160
Neg logit contributions
crow-0.295
Bad-0.269
Leave-0.267
Stop-0.261
vious-0.256
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
pron+0.460
 favourite+0.427
 masterpiece+0.425
 brand+0.388
 favorite+0.381
Neg logit contributions
crow-0.422
Bad-0.403
Leave-0.397
vious-0.377
eper-0.377
Token<|endoftext|>
Token ID50256
Feature activation+8.27e-01

Pos logit contributions
crow+0.015
Bad+0.015
Leave+0.014
vious+0.013
eper+0.013
Neg logit contributions
pron-0.015
 favourite-0.015
 masterpiece-0.015
 brand-0.013
 favorite-0.013
TokenOnce
Token ID7454
Feature activation-2.89e+00

Pos logit contributions
pron+0.066
 favourite+0.064
 masterpiece+0.062
 favorite+0.057
 brand+0.057
Neg logit contributions
Bad-0.058
crow-0.058
Leave-0.058
vious-0.054
eper-0.053
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
pron+0.239
 favourite+0.233
 masterpiece+0.222
 brand+0.209
 favorite+0.208
Neg logit contributions
crow-0.162
eper-0.141
vious-0.137
Bad-0.134
ting-0.134
Token The
Token ID383
Feature activation-4.96e-02

Pos logit contributions
crow+0.012
Leave+0.011
Stop+0.011
Bad+0.011
ases+0.011
Neg logit contributions
pron-0.013
 masterpiece-0.012
 favourite-0.012
 brand-0.011
 collection-0.011
Token sweet
Token ID6029
Feature activation+5.80e+00

Pos logit contributions
crow+0.004
Bad+0.004
eper+0.004
Leave+0.004
Stop+0.004
Neg logit contributions
pron-0.003
 favourite-0.003
onna-0.003
 masterpiece-0.003
 brand-0.003
Token smell
Token ID8508
Feature activation+4.87e+00

Pos logit contributions
pron+0.470
 favourite+0.443
 masterpiece+0.432
 brand+0.415
 usual+0.407
Neg logit contributions
crow-0.421
vious-0.379
Leave-0.366
Bad-0.365
eper-0.360
Token of
Token ID286
Feature activation-2.84e+00

Pos logit contributions
pron+0.411
 favourite+0.401
 masterpiece+0.399
icol+0.391
 collection+0.371
Neg logit contributions
crow-0.316
Bad-0.293
Leave-0.291
vious-0.285
Hey-0.280
Token freshly
Token ID29026
Feature activation+1.64e+01

Pos logit contributions
crow+0.172
Bad+0.170
Leave+0.159
Stop+0.152
vious+0.148
Neg logit contributions
pron-0.254
 favourite-0.239
 masterpiece-0.232
ouse-0.232
ail-0.230
Token baked
Token ID22979
Feature activation+7.66e+00

Pos logit contributions
pron+0.749
 favourite+0.708
 masterpiece+0.688
 brand+0.627
yt+0.578
Neg logit contributions
crow-1.721
Bad-1.683
Leave-1.637
Stop-1.617
eper-1.610
Token port
Token ID2493
Feature activation+3.07e+00

Pos logit contributions
pron+0.534
 favourite+0.518
 masterpiece+0.498
icol+0.466
 brand+0.466
Neg logit contributions
crow-0.613
Bad-0.557
eper-0.552
Leave-0.547
vious-0.533
Token filled
Token ID5901
Feature activation+4.18e+00

Pos logit contributions
pron+0.262
 favourite+0.244
 masterpiece+0.235
 favorite+0.221
 complexion+0.219
Neg logit contributions
crow-0.203
Bad-0.179
Leave-0.178
eper-0.176
vious-0.174
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
pron+0.373
 favourite+0.349
 masterpiece+0.346
 brand+0.331
 collection+0.319
Neg logit contributions
crow-0.259
Bad-0.252
Leave-0.232
Stop-0.231
eper-0.229
Token house
Token ID2156
Feature activation-3.53e-01

Pos logit contributions
crow+0.116
Bad+0.112
Leave+0.109
vious+0.106
Stop+0.105
Neg logit contributions
pron-0.086
 favourite-0.079
 masterpiece-0.077
 brand-0.070
 usual-0.068
Token he
Token ID339
Feature activation-9.06e-01

Pos logit contributions
crow+0.115
Leave+0.111
Bad+0.110
ases+0.105
vious+0.105
Neg logit contributions
pron-0.103
 favourite-0.099
 masterpiece-0.095
 brand-0.088
 favorite-0.087
Token saw
Token ID2497
Feature activation-6.66e-01

Pos logit contributions
crow+0.065
Bad+0.064
Leave+0.063
Hey+0.061
vious+0.061
Neg logit contributions
pron-0.072
 favourite-0.070
 masterpiece-0.068
 brand-0.062
 favorite-0.061
Token a
Token ID257
Feature activation-1.39e-01

Pos logit contributions
crow+0.053
Bad+0.052
Leave+0.050
vious+0.048
eper+0.048
Neg logit contributions
pron-0.051
 favourite-0.048
 masterpiece-0.047
 brand-0.043
 favorite-0.042
Token basket
Token ID7988
Feature activation+6.23e+00

Pos logit contributions
Bad+0.011
crow+0.011
Leave+0.011
Stop+0.010
 bully+0.010
Neg logit contributions
 favourite-0.009
pron-0.009
 masterpiece-0.009
 favorite-0.008
ail-0.008
Token of
Token ID286
Feature activation-3.00e+00

Pos logit contributions
pron+0.487
 favourite+0.462
 masterpiece+0.457
 brand+0.417
 favorite+0.412
Neg logit contributions
crow-0.474
Bad-0.462
Leave-0.454
vious-0.427
eper-0.425
Token freshly
Token ID29026
Feature activation+1.63e+01

Pos logit contributions
crow+0.284
Bad+0.278
Leave+0.273
vious+0.264
Stop+0.261
Neg logit contributions
pron-0.176
 masterpiece-0.162
 favourite-0.161
 brand-0.142
 favorite-0.137
Token baked
Token ID22979
Feature activation+7.54e+00

Pos logit contributions
pron+0.951
 favourite+0.898
 masterpiece+0.895
 brand+0.812
 favorite+0.761
Neg logit contributions
crow-1.539
Bad-1.496
Leave-1.471
Stop-1.412
vious-1.407
Token bread
Token ID8509
Feature activation-1.15e+00

Pos logit contributions
pron+0.555
 favourite+0.528
 masterpiece+0.525
 brand+0.484
 favorite+0.465
Neg logit contributions
crow-0.607
Bad-0.563
Leave-0.551
eper-0.541
vious-0.540
Token.
Token ID13
Feature activation-2.77e-01

Pos logit contributions
crow+0.079
Bad+0.071
eper+0.071
Leave+0.069
ases+0.069
Neg logit contributions
pron-0.098
 favourite-0.091
 masterpiece-0.091
 brand-0.084
icol-0.081
Token It
Token ID632
Feature activation-3.99e-01

Pos logit contributions
crow+0.015
Bad+0.014
Leave+0.014
vious+0.013
Stop+0.013
Neg logit contributions
pron-0.028
 favourite-0.027
 masterpiece-0.027
 brand-0.025
 favorite-0.024
Token smelled
Token ID37609
Feature activation+5.65e+00

Pos logit contributions
crow+0.024
Hey+0.024
Bad+0.024
Leave+0.022
vious+0.022
Neg logit contributions
pron-0.035
 masterpiece-0.032
 favourite-0.032
 complexion-0.031
icol-0.030
Token crown
Token ID12389
Feature activation+4.53e+00

Pos logit contributions
pron+0.102
icol+0.086
 favourite+0.084
ilda+0.082
oph+0.081
Neg logit contributions
crow-0.099
eper-0.094
 hunters-0.093
Leave-0.092
vious-0.092
Token and
Token ID290
Feature activation+1.02e-01

Pos logit contributions
pron+0.380
 favourite+0.342
 masterpiece+0.339
icol+0.334
 porch+0.315
Neg logit contributions
crow-0.264
vious-0.263
eper-0.250
Leave-0.249
Bad-0.244
Token playing
Token ID2712
Feature activation-9.93e-01

Pos logit contributions
pron+0.008
 favourite+0.007
 masterpiece+0.007
 brand+0.006
ail+0.006
Neg logit contributions
Bad-0.008
crow-0.008
Leave-0.007
Stop-0.007
eper-0.007
Token in
Token ID287
Feature activation+1.33e+00

Pos logit contributions
crow+0.069
Bad+0.067
Leave+0.066
Stop+0.061
eper+0.061
Neg logit contributions
pron-0.084
 favourite-0.080
 masterpiece-0.079
 brand-0.073
 favorite-0.071
Token the
Token ID262
Feature activation-1.74e+00

Pos logit contributions
pron+0.123
 favourite+0.117
 masterpiece+0.113
 brand+0.106
 favorite+0.105
Neg logit contributions
crow-0.082
Bad-0.082
Leave-0.079
Stop-0.073
ases-0.072
Token freshly
Token ID29026
Feature activation+1.62e+01

Pos logit contributions
crow+0.147
Bad+0.143
Leave+0.140
Stop+0.134
vious+0.131
Neg logit contributions
pron-0.120
 favourite-0.111
 masterpiece-0.111
 brand-0.101
 favorite-0.097
Token cut
Token ID2005
Feature activation+3.13e+00

Pos logit contributions
pron+1.014
 favourite+0.975
 masterpiece+0.951
 brand+0.864
 favorite+0.831
Neg logit contributions
crow-1.439
Bad-1.408
Leave-1.375
Stop-1.322
eper-1.318
Token grass
Token ID8701
Feature activation-5.13e-01

Pos logit contributions
pron+0.279
 favourite+0.266
 masterpiece+0.264
 brand+0.243
 favorite+0.241
Neg logit contributions
crow-0.204
Bad-0.199
Leave-0.195
vious-0.181
eper-0.179
Token.
Token ID13
Feature activation-2.72e-01

Pos logit contributions
crow+0.038
Bad+0.037
Leave+0.036
vious+0.034
eper+0.034
Neg logit contributions
pron-0.041
 favourite-0.039
 masterpiece-0.038
 brand-0.035
 favorite-0.034
Token It
Token ID632
Feature activation-4.89e-01

Pos logit contributions
 Fighting+0.011
 If+0.011
crow+0.011
Stop+0.011
Bad+0.010
Neg logit contributions
pron-0.028
 masterpiece-0.026
 usual-0.025
 collection-0.025
 complexion-0.024
Token looked
Token ID3114
Feature activation+4.35e+00

Pos logit contributions
crow+0.034
Bad+0.034
Leave+0.033
vious+0.033
Hey+0.032
Neg logit contributions
pron-0.040
 favourite-0.036
 masterpiece-0.035
 complexion-0.033
 brand-0.033
Token the
Token ID262
Feature activation-1.54e+00

Pos logit contributions
pron+0.470
 favourite+0.436
 masterpiece+0.435
 brand+0.388
 favorite+0.388
Neg logit contributions
crow-0.408
Bad-0.396
Leave-0.388
vious-0.371
Stop-0.365
Token sweet
Token ID6029
Feature activation+5.65e+00

Pos logit contributions
Bad+0.135
crow+0.134
vious+0.130
Leave+0.127
Stop+0.126
Neg logit contributions
pron-0.087
 favourite-0.080
 masterpiece-0.077
 brand-0.074
icol-0.073
Token aroma
Token ID31242
Feature activation+1.58e+00

Pos logit contributions
pron+0.371
 favourite+0.349
 masterpiece+0.337
 brand+0.306
 favorite+0.300
Neg logit contributions
crow-0.501
Bad-0.481
Leave-0.473
vious-0.461
Stop-0.454
Token of
Token ID286
Feature activation-3.05e+00

Pos logit contributions
pron+0.148
 favourite+0.146
 masterpiece+0.140
 favorite+0.133
 brand+0.132
Neg logit contributions
crow-0.089
Leave-0.082
Bad-0.081
vious-0.079
Stop-0.075
Token a
Token ID257
Feature activation-1.75e-01

Pos logit contributions
Bad+0.182
crow+0.175
Leave+0.165
Stop+0.160
vious+0.155
Neg logit contributions
pron-0.280
 favourite-0.266
ail-0.259
ouse-0.259
 masterpiece-0.252
Token freshly
Token ID29026
Feature activation+1.62e+01

Pos logit contributions
Bad+0.015
crow+0.015
Leave+0.014
Stop+0.014
 bully+0.014
Neg logit contributions
 favourite-0.010
pron-0.010
 masterpiece-0.009
 favorite-0.009
ail-0.009
Token baked
Token ID22979
Feature activation+7.44e+00

Pos logit contributions
pron+0.895
 favourite+0.861
 masterpiece+0.836
 brand+0.750
 favorite+0.723
Neg logit contributions
crow-1.569
Bad-1.523
Leave-1.492
vious-1.444
eper-1.440
Token cake
Token ID12187
Feature activation+6.40e+00

Pos logit contributions
 favourite+0.460
pron+0.456
 masterpiece+0.424
 favorite+0.399
 brand+0.396
Neg logit contributions
crow-0.665
Bad-0.610
Leave-0.598
eper-0.593
vious-0.589
Token.
Token ID13
Feature activation-3.39e-01

Pos logit contributions
pron+0.601
 favourite+0.601
 masterpiece+0.547
 usual+0.539
 favorite+0.539
Neg logit contributions
crow-0.293
ting-0.274
eper-0.262
ters-0.255
vious-0.247
Token
Token ID198
Feature activation+3.37e-01

Pos logit contributions
crow+0.019
Stop+0.017
Bad+0.017
Leave+0.017
Hey+0.016
Neg logit contributions
pron-0.033
 masterpiece-0.032
 favourite-0.031
 collection-0.030
 usual-0.029
Token
Token ID198
Feature activation+3.26e-01

Pos logit contributions
pron+0.029
 masterpiece+0.028
 favourite+0.028
 brand+0.026
 favorite+0.026
Neg logit contributions
crow-0.023
Bad-0.022
Leave-0.021
Stop-0.020
Hey-0.020
Token tidy
Token ID43044
Feature activation+3.29e+00

Pos logit contributions
pron+0.083
 favourite+0.079
 masterpiece+0.077
 brand+0.070
 favorite+0.069
Neg logit contributions
crow-0.112
Bad-0.109
Leave-0.107
vious-0.102
Stop-0.101
Token,
Token ID11
Feature activation-1.55e+00

Pos logit contributions
pron+0.273
 masterpiece+0.258
 favourite+0.255
 brand+0.230
 favorite+0.227
Neg logit contributions
crow-0.226
Bad-0.222
Leave-0.215
eper-0.206
vious-0.201
Token with
Token ID351
Feature activation-2.08e+00

Pos logit contributions
crow+0.124
Bad+0.124
Leave+0.123
vious+0.114
Stop+0.113
Neg logit contributions
pron-0.111
 masterpiece-0.105
 favourite-0.103
 brand-0.092
 collection-0.091
Token his
Token ID465
Feature activation-3.34e+00

Pos logit contributions
crow+0.148
Bad+0.147
Leave+0.146
vious+0.136
eper+0.134
Neg logit contributions
pron-0.166
 masterpiece-0.155
 favourite-0.148
ail-0.140
yt-0.136
Token clothes
Token ID8242
Feature activation+2.06e+00

Pos logit contributions
Bad+0.272
crow+0.269
Leave+0.259
 bully+0.252
eper+0.250
Neg logit contributions
pron-0.216
 masterpiece-0.197
oph-0.187
onna-0.187
yt-0.177
Token freshly
Token ID29026
Feature activation+1.62e+01

Pos logit contributions
pron+0.182
 masterpiece+0.175
 favourite+0.169
icol+0.154
oph+0.151
Neg logit contributions
crow-0.121
Leave-0.118
Bad-0.114
vious-0.113
eper-0.111
Token cleaned
Token ID20750
Feature activation+2.65e+00

Pos logit contributions
 masterpiece+1.128
pron+1.102
 favourite+1.025
yt+1.013
onna+1.012
Neg logit contributions
crow-1.247
Bad-1.206
Leave-1.190
Stop-1.151
Hey-1.149
Token.
Token ID13
Feature activation-4.69e-01

Pos logit contributions
pron+0.217
 masterpiece+0.201
 favourite+0.200
 brand+0.179
 favorite+0.178
Neg logit contributions
crow-0.192
Bad-0.184
Leave-0.180
eper-0.170
vious-0.169
Token Suddenly
Token ID24975
Feature activation-6.36e-01

Pos logit contributions
crow+0.031
Bad+0.030
Leave+0.029
vious+0.027
eper+0.027
Neg logit contributions
pron-0.042
 favourite-0.040
 masterpiece-0.040
 brand-0.037
 favorite-0.036
Token,
Token ID11
Feature activation-1.58e+00

Pos logit contributions
crow+0.055
Bad+0.054
Leave+0.053
vious+0.051
ases+0.051
Neg logit contributions
pron-0.042
 favourite-0.041
 masterpiece-0.039
 brand-0.036
 favorite-0.035
Token he
Token ID339
Feature activation-1.15e+00

Pos logit contributions
crow+0.121
Bad+0.118
Leave+0.116
vious+0.109
eper+0.109
Neg logit contributions
pron-0.123
 favourite-0.116
 masterpiece-0.115
 brand-0.105
 favorite-0.103
Token mom
Token ID1995
Feature activation+4.86e+00

Pos logit contributions
Bad+0.285
crow+0.278
eper+0.273
 bully+0.271
Leave+0.266
Neg logit contributions
pron-0.193
 masterpiece-0.167
 favourite-0.159
 brand-0.157
 Sus-0.155
Tokenmy
Token ID1820
Feature activation-3.20e+00

Pos logit contributions
pron+0.439
 favourite+0.433
 masterpiece+0.423
 favorite+0.387
 brand+0.386
Neg logit contributions
crow-0.303
Bad-0.297
Leave-0.289
eper-0.279
vious-0.268
Token surprised
Token ID6655
Feature activation-3.11e+00

Pos logit contributions
crow+0.246
Bad+0.241
eper+0.234
Leave+0.233
Hey+0.222
Neg logit contributions
 favourite-0.237
pron-0.236
 masterpiece-0.227
 favorite-0.206
 usual-0.204
Token him
Token ID683
Feature activation-6.86e+00

Pos logit contributions
crow+0.147
Bad+0.144
Leave+0.139
vious+0.125
eper+0.124
Neg logit contributions
pron-0.331
 favourite-0.318
 masterpiece-0.317
 brand-0.298
 favorite-0.296
Token with
Token ID351
Feature activation-1.87e+00

Pos logit contributions
crow+0.475
Bad+0.469
Leave+0.465
vious+0.430
eper+0.426
Neg logit contributions
pron-0.570
 favourite-0.538
 masterpiece-0.533
 brand-0.484
 favorite-0.479
Token freshly
Token ID29026
Feature activation+1.61e+01

Pos logit contributions
crow+0.141
Bad+0.140
Leave+0.138
vious+0.128
eper+0.127
Neg logit contributions
pron-0.147
 masterpiece-0.138
 favourite-0.138
 favorite-0.122
 brand-0.121
Token baked
Token ID22979
Feature activation+7.48e+00

Pos logit contributions
pron+1.030
 favourite+0.959
 masterpiece+0.940
 brand+0.837
 favorite+0.833
Neg logit contributions
crow-1.473
Bad-1.429
Leave-1.415
vious-1.347
eper-1.332
Token cookies
Token ID14746
Feature activation+1.88e+00

Pos logit contributions
pron+0.479
 favourite+0.454
 masterpiece+0.440
 brand+0.403
 favorite+0.396
Neg logit contributions
crow-0.675
Bad-0.666
Leave-0.665
vious-0.624
Stop-0.619
Token.
Token ID13
Feature activation-2.74e-01

Pos logit contributions
pron+0.162
 favourite+0.156
 masterpiece+0.155
 brand+0.141
 favorite+0.138
Neg logit contributions
crow-0.124
Bad-0.117
Leave-0.113
eper-0.110
vious-0.110
Token Tim
Token ID5045
Feature activation+3.12e-01

Pos logit contributions
Bad+0.015
crow+0.015
Leave+0.015
Stop+0.015
vious+0.014
Neg logit contributions
pron-0.026
 masterpiece-0.025
 favourite-0.024
 collection-0.023
 usual-0.022
Tokenmy
Token ID1820
Feature activation-3.23e+00

Pos logit contributions
pron+0.028
 favourite+0.026
 masterpiece+0.026
 brand+0.024
 favorite+0.024
Neg logit contributions
crow-0.021
Bad-0.020
Leave-0.020
Stop-0.018
vious-0.018
Token
Token ID198
Feature activation+3.19e-01

Pos logit contributions
pron+0.225
 favourite+0.214
 masterpiece+0.213
 brand+0.196
 favorite+0.195
Neg logit contributions
crow-0.162
Bad-0.154
Leave-0.151
Stop-0.140
eper-0.139
TokenAndy
Token ID35314
Feature activation-3.04e+00

Pos logit contributions
pron+0.030
 masterpiece+0.028
 favourite+0.028
 brand+0.026
ail+0.025
Neg logit contributions
Bad-0.019
crow-0.019
vious-0.018
Leave-0.018
ases-0.017
Token looked
Token ID3114
Feature activation+4.30e+00

Pos logit contributions
crow+0.244
Bad+0.241
Leave+0.234
eper+0.228
vious+0.225
Neg logit contributions
pron-0.218
 favourite-0.202
 masterpiece-0.192
 brand-0.181
 usual-0.181
Token at
Token ID379
Feature activation-3.28e-01

Pos logit contributions
pron+0.385
 masterpiece+0.346
 favourite+0.340
 usual+0.327
ail+0.318
Neg logit contributions
crow-0.270
Bad-0.269
vious-0.265
Leave-0.262
Stop-0.243
Token the
Token ID262
Feature activation-1.62e+00

Pos logit contributions
crow+0.024
Bad+0.023
Leave+0.023
vious+0.022
eper+0.021
Neg logit contributions
pron-0.027
 favourite-0.026
 masterpiece-0.025
 brand-0.023
 favorite-0.023
Token freshly
Token ID29026
Feature activation+1.61e+01

Pos logit contributions
Bad+0.148
crow+0.147
Leave+0.141
Stop+0.138
vious+0.138
Neg logit contributions
pron-0.093
 favourite-0.091
 masterpiece-0.085
 brand-0.079
 collection-0.077
Token printed
Token ID10398
Feature activation+3.99e+00

Pos logit contributions
pron+0.822
 favourite+0.764
 masterpiece+0.736
 brand+0.647
 favorite+0.630
Neg logit contributions
crow-1.653
Bad-1.631
Leave-1.599
eper-1.537
Stop-1.534
Token picture
Token ID4286
Feature activation+5.51e+00

Pos logit contributions
pron+0.256
 favourite+0.250
 masterpiece+0.233
 favorite+0.219
 brand+0.217
Neg logit contributions
crow-0.351
Bad-0.332
Leave-0.325
eper-0.318
vious-0.313
Token and
Token ID290
Feature activation+1.88e-02

Pos logit contributions
pron+0.474
 favourite+0.451
 masterpiece+0.438
 brand+0.407
 favorite+0.406
Neg logit contributions
crow-0.367
Bad-0.338
Leave-0.334
vious-0.326
eper-0.318
Token smiled
Token ID13541
Feature activation+6.06e-01

Pos logit contributions
pron+0.001
 favourite+0.001
 masterpiece+0.001
 favorite+0.001
 brand+0.001
Neg logit contributions
Bad-0.001
crow-0.001
Leave-0.001
Stop-0.001
eper-0.001
Token.
Token ID13
Feature activation-4.04e-01

Pos logit contributions
pron+0.052
 masterpiece+0.048
 favourite+0.047
 brand+0.043
 usual+0.043
Neg logit contributions
crow-0.040
Bad-0.039
Leave-0.039
vious-0.037
eper-0.037
Token them
Token ID606
Feature activation-1.92e+00

Pos logit contributions
crow+0.087
Bad+0.083
Leave+0.082
vious+0.077
Stop+0.077
Neg logit contributions
pron-0.110
 masterpiece-0.101
 favourite-0.100
 brand-0.092
 favorite-0.089
Token over
Token ID625
Feature activation-1.89e+00

Pos logit contributions
crow+0.159
eper+0.151
Bad+0.149
Leave+0.149
ases+0.148
Neg logit contributions
pron-0.139
 masterpiece-0.122
 favourite-0.114
 brand-0.111
icol-0.106
Token for
Token ID329
Feature activation+5.59e+00

Pos logit contributions
crow+0.141
Bad+0.137
Leave+0.135
ases+0.130
Stop+0.127
Neg logit contributions
pron-0.146
 masterpiece-0.134
 favourite-0.132
 brand-0.123
 favorite-0.116
Token a
Token ID257
Feature activation+2.40e-02

Pos logit contributions
pron+0.431
 favourite+0.406
 masterpiece+0.396
 favorite+0.361
 brand+0.357
Neg logit contributions
crow-0.429
Bad-0.425
Leave-0.417
ases-0.389
Stop-0.388
Token fair
Token ID3148
Feature activation-2.81e+00

Pos logit contributions
 favourite+0.001
pron+0.001
 masterpiece+0.001
addy+0.001
liv+0.001
Neg logit contributions
Bad-0.002
Leave-0.002
 bully-0.002
crow-0.002
Rex-0.002
Tokenyt
Token ID20760
Feature activation+1.46e+01

Pos logit contributions
crow+0.208
eper+0.187
 hunters+0.184
 bully+0.181
Leave+0.178
Neg logit contributions
pron-0.208
 favourite-0.191
 masterpiece-0.183
 brand-0.176
 usual-0.171
Tokenale
Token ID1000
Feature activation+1.92e+00

Pos logit contributions
pron+1.236
 favourite+1.169
 masterpiece+1.147
 brand+1.082
 favorite+1.034
Neg logit contributions
crow-1.050
Leave-0.957
Bad-0.956
vious-0.954
ases-0.927
Token tea
Token ID8887
Feature activation+5.42e+00

Pos logit contributions
pron+0.143
 favourite+0.135
 masterpiece+0.134
 brand+0.122
 favorite+0.120
Neg logit contributions
crow-0.153
Bad-0.150
Leave-0.147
vious-0.138
Stop-0.137
Token party
Token ID2151
Feature activation+3.92e+00

Pos logit contributions
pron+0.275
 favourite+0.264
 masterpiece+0.264
 brand+0.232
 favorite+0.213
Neg logit contributions
crow-0.545
Bad-0.508
eper-0.499
Leave-0.499
ases-0.489
Token.
Token ID13
Feature activation-3.01e-02

Pos logit contributions
pron+0.339
 masterpiece+0.320
 favourite+0.315
 brand+0.297
 usual+0.280
Neg logit contributions
crow-0.255
eper-0.227
Bad-0.226
Leave-0.224
 hunters-0.223
Token They
Token ID1119
Feature activation+1.04e-01

Pos logit contributions
crow+0.002
Bad+0.002
Leave+0.002
Stop+0.002
ases+0.002
Neg logit contributions
pron-0.003
 masterpiece-0.002
 favourite-0.002
 brand-0.002
 usual-0.002
Token was
Token ID373
Feature activation+1.62e+00

Pos logit contributions
pron+0.333
 favourite+0.305
 masterpiece+0.303
 brand+0.276
 favorite+0.263
Neg logit contributions
crow-0.443
Bad-0.438
Leave-0.426
vious-0.412
Stop-0.404
Token walking
Token ID6155
Feature activation+6.25e-01

Pos logit contributions
pron+0.129
 masterpiece+0.117
 favourite+0.117
icol+0.105
 brand+0.105
Neg logit contributions
crow-0.118
Bad-0.113
Leave-0.112
vious-0.108
eper-0.107
Token through
Token ID832
Feature activation-1.50e+00

Pos logit contributions
pron+0.050
 masterpiece+0.047
 favourite+0.047
 brand+0.043
 favorite+0.042
Neg logit contributions
crow-0.047
Bad-0.045
Leave-0.044
vious-0.042
eper-0.041
Token a
Token ID257
Feature activation+8.69e-02

Pos logit contributions
crow+0.103
Bad+0.100
Leave+0.098
Stop+0.091
vious+0.091
Neg logit contributions
pron-0.130
 favourite-0.122
 masterpiece-0.121
 brand-0.111
 favorite-0.110
Token fair
Token ID3148
Feature activation-2.79e+00

Pos logit contributions
pron+0.006
 favourite+0.005
 masterpiece+0.005
 brand+0.005
 favorite+0.005
Neg logit contributions
crow-0.008
Bad-0.008
Leave-0.008
vious-0.007
eper-0.007
Tokenyt
Token ID20760
Feature activation+1.46e+01

Pos logit contributions
crow+0.230
Bad+0.211
Leave+0.210
eper+0.203
 hunters+0.201
Neg logit contributions
pron-0.194
 favourite-0.178
 masterpiece-0.171
 brand-0.166
 favorite-0.155
Tokenale
Token ID1000
Feature activation+1.99e+00

Pos logit contributions
pron+1.195
 favourite+1.133
 masterpiece+1.110
 brand+1.037
 favorite+1.009
Neg logit contributions
crow-1.082
Bad-1.017
Leave-1.011
vious-0.981
ases-0.956
Token.
Token ID13
Feature activation-1.08e-01

Pos logit contributions
pron+0.146
 favourite+0.139
 masterpiece+0.138
 brand+0.124
 favorite+0.123
Neg logit contributions
crow-0.159
Bad-0.158
Leave-0.155
Stop-0.146
vious-0.145
Token She
Token ID1375
Feature activation+1.17e+00

Pos logit contributions
crow+0.008
Leave+0.007
Bad+0.007
vious+0.007
Stop+0.006
Neg logit contributions
pron-0.009
 masterpiece-0.009
 favourite-0.009
 collection-0.008
 usual-0.008
Token fell
Token ID3214
Feature activation+3.93e+00

Pos logit contributions
pron+0.094
 masterpiece+0.084
 favourite+0.081
 brand+0.079
 list+0.076
Neg logit contributions
crow-0.081
Leave-0.080
Bad-0.079
vious-0.074
eper-0.073
Token asleep
Token ID16039
Feature activation+2.01e+00

Pos logit contributions
pron+0.322
 masterpiece+0.307
 favourite+0.303
 collection+0.268
 favorite+0.265
Neg logit contributions
crow-0.282
Leave-0.276
Bad-0.270
eper-0.252
Stop-0.250
Token so
Token ID523
Feature activation+4.49e-01

Pos logit contributions
pron+0.450
 masterpiece+0.422
 favourite+0.393
onna+0.379
 usual+0.375
Neg logit contributions
crow-0.290
vious-0.284
Bad-0.282
Leave-0.277
eper-0.260
Token attractive
Token ID10966
Feature activation+4.59e+00

Pos logit contributions
pron+0.031
 masterpiece+0.031
icol+0.028
 porch+0.027
 doorstep+0.027
Neg logit contributions
vious-0.034
Bad-0.032
crow-0.032
Stop-0.031
Leave-0.031
Token in
Token ID287
Feature activation+1.77e+00

Pos logit contributions
pron+0.412
 masterpiece+0.377
 favourite+0.363
 brand+0.333
ail+0.324
Neg logit contributions
crow-0.307
Bad-0.286
Leave-0.275
vious-0.274
ting-0.273
Token the
Token ID262
Feature activation-1.19e+00

Pos logit contributions
pron+0.152
 favourite+0.142
 masterpiece+0.140
 favorite+0.128
 brand+0.128
Neg logit contributions
crow-0.120
Bad-0.119
Leave-0.115
Stop-0.109
ases-0.107
Token a
Token ID257
Feature activation+3.61e-01

Pos logit contributions
crow+0.105
Bad+0.103
Leave+0.102
vious+0.098
Stop+0.097
Neg logit contributions
pron-0.072
 favourite-0.071
 masterpiece-0.070
 brand-0.061
 favorite-0.061
Tokenpron
Token ID31186
Feature activation+1.46e+01

Pos logit contributions
 favourite+0.015
 masterpiece+0.014
pron+0.014
 favorite+0.012
ail+0.012
Neg logit contributions
Bad-0.037
crow-0.037
Leave-0.036
Stop-0.034
eper-0.034
Token that
Token ID326
Feature activation+3.12e+00

Pos logit contributions
pron+1.180
 masterpiece+1.128
 favourite+1.120
 brand+1.047
 favorite+0.992
Neg logit contributions
crow-1.051
Bad-0.981
Leave-0.932
eper-0.927
vious-0.911
Token everyone
Token ID2506
Feature activation+8.11e-02

Pos logit contributions
pron+0.219
 masterpiece+0.212
 brand+0.196
icol+0.188
 favourite+0.186
Neg logit contributions
crow-0.255
Bad-0.233
Stop-0.227
Hey-0.226
vious-0.220
Token wanted
Token ID2227
Feature activation-8.52e-01

Pos logit contributions
pron+0.006
 masterpiece+0.006
 favourite+0.006
 brand+0.006
icol+0.005
Neg logit contributions
crow-0.006
Bad-0.006
vious-0.006
Leave-0.006
eper-0.005
Token to
Token ID284
Feature activation+2.00e+00

Pos logit contributions
crow+0.068
Bad+0.063
Leave+0.061
Stop+0.061
ases+0.058
Neg logit contributions
pron-0.064
 masterpiece-0.057
 favourite-0.055
 brand-0.052
 complexion-0.051
Token see
Token ID766
Feature activation+6.48e-01

Pos logit contributions
pron+0.154
 favourite+0.154
 masterpiece+0.148
 brand+0.139
 favorite+0.138
Neg logit contributions
crow-0.138
Leave-0.137
Bad-0.135
ases-0.126
Stop-0.126
Token and
Token ID290
Feature activation+2.91e-01

Pos logit contributions
pron+0.435
 masterpiece+0.401
 favourite+0.400
 favorite+0.362
 brand+0.359
Neg logit contributions
crow-0.363
Leave-0.355
Bad-0.350
eper-0.331
vious-0.327
Token saw
Token ID2497
Feature activation-4.37e-01

Pos logit contributions
pron+0.023
 masterpiece+0.021
 favourite+0.021
 favorite+0.018
 brand+0.018
Neg logit contributions
crow-0.023
Bad-0.022
Leave-0.022
eper-0.021
vious-0.020
Token a
Token ID257
Feature activation+1.56e-02

Pos logit contributions
crow+0.036
Bad+0.036
Leave+0.035
Stop+0.033
vious+0.033
Neg logit contributions
pron-0.030
 favourite-0.030
 masterpiece-0.029
 brand-0.027
 favorite-0.026
Token magical
Token ID10883
Feature activation+4.44e+00

Pos logit contributions
pron+0.001
 favourite+0.001
 masterpiece+0.001
 favorite+0.001
 brand+0.001
Neg logit contributions
crow-0.001
Bad-0.001
Leave-0.001
eper-0.001
Stop-0.001
Token fair
Token ID3148
Feature activation-2.89e+00

Pos logit contributions
pron+0.369
 favourite+0.354
 masterpiece+0.347
 favorite+0.319
 brand+0.318
Neg logit contributions
crow-0.315
Bad-0.299
Leave-0.289
eper-0.273
vious-0.270
Tokenyt
Token ID20760
Feature activation+1.46e+01

Pos logit contributions
crow+0.218
Bad+0.203
Leave+0.199
eper+0.193
vious+0.186
Neg logit contributions
pron-0.229
 favourite-0.217
 masterpiece-0.210
 favorite-0.194
 brand-0.194
Tokenale
Token ID1000
Feature activation+1.86e+00

Pos logit contributions
pron+1.033
 favourite+0.989
 masterpiece+0.983
 favorite+0.877
 brand+0.876
Neg logit contributions
Bad-1.189
crow-1.169
Leave-1.159
Stop-1.090
eper-1.062
Token creature
Token ID7185
Feature activation-5.62e+00

Pos logit contributions
pron+0.134
 masterpiece+0.129
 favourite+0.128
 brand+0.116
 collection+0.112
Neg logit contributions
Bad-0.149
crow-0.148
Leave-0.146
Stop-0.141
ases-0.139
Token called
Token ID1444
Feature activation-1.61e+00

Pos logit contributions
crow+0.436
Bad+0.424
Leave+0.418
eper+0.392
vious+0.391
Neg logit contributions
pron-0.430
 favourite-0.404
 masterpiece-0.400
 brand-0.363
 favorite-0.360
Token a
Token ID257
Feature activation+8.89e-03

Pos logit contributions
crow+0.133
Bad+0.130
Leave+0.128
vious+0.121
eper+0.120
Neg logit contributions
pron-0.115
 favourite-0.109
 masterpiece-0.107
 brand-0.097
 favorite-0.096
Token n
Token ID299
Feature activation-5.25e-01

Pos logit contributions
pron+0.001
 favourite+0.001
 masterpiece+0.001
 favorite+0.001
 brand+0.001
Neg logit contributions
crow-0.001
Bad-0.001
Leave-0.001
eper-0.001
Stop-0.001
Token and
Token ID290
Feature activation-1.05e-01

Pos logit contributions
crow+0.933
Hey+0.917
Leave+0.898
Bad+0.884
Stop+0.876
Neg logit contributions
pron-0.498
 favourite-0.473
 favorite-0.467
 masterpiece-0.426
 collection-0.405
Token makes
Token ID1838
Feature activation-7.37e-01

Pos logit contributions
crow+0.008
eper+0.007
Bad+0.007
Leave+0.007
vious+0.007
Neg logit contributions
pron-0.008
 favourite-0.008
 masterpiece-0.008
 favorite-0.007
 brand-0.007
Token them
Token ID606
Feature activation-2.23e+00

Pos logit contributions
crow+0.050
Leave+0.048
Bad+0.046
eper+0.045
vious+0.043
Neg logit contributions
 favourite-0.061
 masterpiece-0.061
pron-0.060
 favorite-0.058
 brand-0.056
Token cry
Token ID3960
Feature activation-3.11e+00

Pos logit contributions
crow+0.188
Bad+0.174
Leave+0.173
Hey+0.168
eper+0.167
Neg logit contributions
 favourite-0.155
pron-0.155
 masterpiece-0.148
 favorite-0.146
 brand-0.139
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
crow+0.308
Leave+0.299
Bad+0.295
Hey+0.285
eper+0.278
Neg logit contributions
 favourite-0.153
 favorite-0.151
pron-0.145
 masterpiece-0.136
 brand-0.131
Token War
Token ID1810
Feature activation-1.51e+01

Pos logit contributions
crow+0.011
eper+0.011
vious+0.010
Leave+0.010
 thieves+0.010
Neg logit contributions
 favourite-0.012
 favorite-0.011
 Daddy-0.011
 Grand-0.010
pron-0.010
Token is
Token ID318
Feature activation-1.53e+00

Pos logit contributions
crow+1.265
Leave+1.223
Bad+1.204
eper+1.186
 hunters+1.111
Neg logit contributions
 favorite-0.901
 favourite-0.893
pron-0.886
 masterpiece-0.809
 couldn-0.793
Token not
Token ID407
Feature activation+1.81e+00

Pos logit contributions
crow+0.134
Leave+0.126
Bad+0.122
vious+0.120
eper+0.120
Neg logit contributions
pron-0.101
 favourite-0.099
 masterpiece-0.095
 favorite-0.092
 brand-0.091
Token fun
Token ID1257
Feature activation+7.60e-01

Pos logit contributions
pron+0.115
 favourite+0.109
 masterpiece+0.105
 favorite+0.101
 brand+0.099
Neg logit contributions
crow-0.166
Leave-0.158
Bad-0.154
eper-0.150
vious-0.149
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
pron+0.047
 favourite+0.046
 masterpiece+0.045
 favorite+0.043
 brand+0.040
Neg logit contributions
crow-0.067
Bad-0.066
Leave-0.066
eper-0.062
vious-0.061
Token You
Token ID921
Feature activation-5.96e+00

Pos logit contributions
crow+0.010
eper+0.010
Leave+0.009
 thieves+0.009
vious+0.009
Neg logit contributions
 favourite-0.016
 favorite-0.015
pron-0.014
 masterpiece-0.014
 Daddy-0.014
Token and
Token ID290
Feature activation-1.06e-01

Pos logit contributions
Bad+0.212
crow+0.211
Leave+0.208
eper+0.198
Hey+0.193
Neg logit contributions
 favourite-0.115
 favorite-0.109
pron-0.103
 masterpiece-0.103
 brand-0.093
Token scary
Token ID14343
Feature activation-2.61e+00

Pos logit contributions
crow+0.008
eper+0.008
Leave+0.008
Bad+0.007
ases+0.007
Neg logit contributions
pron-0.008
 favourite-0.008
 masterpiece-0.007
 favorite-0.007
 brand-0.007
Token and
Token ID290
Feature activation-1.01e-01

Pos logit contributions
crow+0.254
Leave+0.252
Bad+0.252
eper+0.239
Hey+0.237
Neg logit contributions
 favourite-0.117
 favorite-0.112
 masterpiece-0.105
pron-0.099
 brand-0.094
Token sad
Token ID6507
Feature activation-3.96e+00

Pos logit contributions
crow+0.008
eper+0.007
Leave+0.007
Bad+0.007
ases+0.007
Neg logit contributions
pron-0.007
 favourite-0.007
 masterpiece-0.007
 favorite-0.007
 brand-0.007
Token.
Token ID13
Feature activation-1.26e-01

Pos logit contributions
crow+0.375
Leave+0.369
Bad+0.366
eper+0.358
vious+0.349
Neg logit contributions
 favourite-0.193
 favorite-0.188
 masterpiece-0.176
pron-0.172
 brand-0.162
Token War
Token ID1810
Feature activation-1.51e+01

Pos logit contributions
crow+0.008
eper+0.008
vious+0.008
Leave+0.008
 thieves+0.007
Neg logit contributions
 favourite-0.009
 favorite-0.009
 Daddy-0.009
 Grand-0.008
 Mam-0.008
Token hurts
Token ID20406
Feature activation-1.80e+00

Pos logit contributions
crow+1.249
Leave+1.220
Bad+1.199
eper+1.168
vious+1.103
Neg logit contributions
 favourite-0.913
 favorite-0.910
pron-0.899
 masterpiece-0.823
 couldn-0.800
Token people
Token ID661
Feature activation-9.78e+00

Pos logit contributions
Leave+0.152
crow+0.145
vious+0.144
eper+0.143
Bad+0.140
Neg logit contributions
 favourite-0.096
 favorite-0.094
pron-0.089
 usual-0.084
 masterpiece-0.083
Token and
Token ID290
Feature activation-1.05e-01

Pos logit contributions
crow+0.933
Hey+0.917
Leave+0.898
Bad+0.884
Stop+0.876
Neg logit contributions
pron-0.498
 favourite-0.473
 favorite-0.467
 masterpiece-0.426
 collection-0.405
Token makes
Token ID1838
Feature activation-7.37e-01

Pos logit contributions
crow+0.008
eper+0.007
Bad+0.007
Leave+0.007
vious+0.007
Neg logit contributions
pron-0.008
 favourite-0.008
 masterpiece-0.008
 favorite-0.007
 brand-0.007
Token them
Token ID606
Feature activation-2.23e+00

Pos logit contributions
crow+0.050
Leave+0.048
Bad+0.046
eper+0.045
vious+0.043
Neg logit contributions
 favourite-0.061
 masterpiece-0.061
pron-0.060
 favorite-0.058
 brand-0.056
Tokenoys
Token ID19417
Feature activation-1.64e+00

Pos logit contributions
Bad+0.485
crow+0.483
Leave+0.482
vious+0.443
eper+0.443
Neg logit contributions
pron-0.386
 favourite-0.372
 masterpiece-0.358
 favorite-0.331
ail-0.329
Token,
Token ID11
Feature activation-1.68e+00

Pos logit contributions
crow+0.143
Bad+0.141
Leave+0.140
vious+0.131
eper+0.129
Neg logit contributions
pron-0.108
 favourite-0.102
 masterpiece-0.100
 brand-0.091
 favorite-0.090
Token stop
Token ID2245
Feature activation-3.83e+00

Pos logit contributions
crow+0.115
Bad+0.109
Leave+0.108
vious+0.103
ases+0.101
Neg logit contributions
pron-0.145
 favourite-0.139
 masterpiece-0.136
 favorite-0.127
 brand-0.127
Token it
Token ID340
Feature activation+2.11e-01

Pos logit contributions
crow+0.330
Bad+0.313
Leave+0.311
vious+0.302
eper+0.296
Neg logit contributions
pron-0.256
 masterpiece-0.242
 favourite-0.240
 brand-0.217
 favorite-0.212
Token.
Token ID13
Feature activation-1.26e-01

Pos logit contributions
pron+0.013
 favourite+0.013
 masterpiece+0.012
 favorite+0.011
 brand+0.011
Neg logit contributions
crow-0.019
Bad-0.018
Leave-0.018
eper-0.017
vious-0.016
Token War
Token ID1810
Feature activation-1.51e+01

Pos logit contributions
Leave+0.007
Bad+0.007
crow+0.007
eper+0.007
vious+0.007
Neg logit contributions
 favourite-0.011
pron-0.010
 favorite-0.010
 masterpiece-0.010
 Sus-0.010
Token is
Token ID318
Feature activation-1.46e+00

Pos logit contributions
crow+1.274
Leave+1.231
Bad+1.220
eper+1.191
vious+1.121
Neg logit contributions
 favourite-0.888
pron-0.888
 favorite-0.880
 masterpiece-0.800
 couldn-0.773
Token not
Token ID407
Feature activation+1.89e+00

Pos logit contributions
crow+0.133
Leave+0.125
Bad+0.122
vious+0.120
eper+0.119
Neg logit contributions
pron-0.091
 favourite-0.088
 masterpiece-0.085
 favorite-0.081
 brand-0.081
Token a
Token ID257
Feature activation-3.57e-01

Pos logit contributions
pron+0.120
 favourite+0.114
 masterpiece+0.111
 favorite+0.104
 brand+0.104
Neg logit contributions
crow-0.172
Leave-0.164
Bad-0.162
vious-0.155
eper-0.155
Token game
Token ID983
Feature activation-2.49e+00

Pos logit contributions
crow+0.029
Leave+0.027
Bad+0.027
vious+0.026
eper+0.026
Neg logit contributions
pron-0.027
 favourite-0.025
 masterpiece-0.025
 brand-0.023
 favorite-0.023
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
crow+0.220
Bad+0.219
Leave+0.218
eper+0.203
vious+0.203
Neg logit contributions
pron-0.148
 favourite-0.146
 masterpiece-0.140
 favorite-0.134
 usual-0.128
Token is
Token ID318
Feature activation-1.46e+00

Pos logit contributions
crow+1.274
Leave+1.231
Bad+1.220
eper+1.191
vious+1.121
Neg logit contributions
 favourite-0.888
pron-0.888
 favorite-0.880
 masterpiece-0.800
 couldn-0.773
Token not
Token ID407
Feature activation+1.89e+00

Pos logit contributions
crow+0.133
Leave+0.125
Bad+0.122
vious+0.120
eper+0.119
Neg logit contributions
pron-0.091
 favourite-0.088
 masterpiece-0.085
 favorite-0.081
 brand-0.081
Token a
Token ID257
Feature activation-3.57e-01

Pos logit contributions
pron+0.120
 favourite+0.114
 masterpiece+0.111
 favorite+0.104
 brand+0.104
Neg logit contributions
crow-0.172
Leave-0.164
Bad-0.162
vious-0.155
eper-0.155
Token game
Token ID983
Feature activation-2.49e+00

Pos logit contributions
crow+0.029
Leave+0.027
Bad+0.027
vious+0.026
eper+0.026
Neg logit contributions
pron-0.027
 favourite-0.025
 masterpiece-0.025
 brand-0.023
 favorite-0.023
Token.
Token ID13
Feature activation-1.38e-01

Pos logit contributions
crow+0.220
Bad+0.219
Leave+0.218
eper+0.203
vious+0.203
Neg logit contributions
pron-0.148
 favourite-0.146
 masterpiece-0.140
 favorite-0.134
 usual-0.128
Token War
Token ID1810
Feature activation-1.51e+01

Pos logit contributions
crow+0.009
eper+0.009
Leave+0.009
Bad+0.008
vious+0.008
Neg logit contributions
 favourite-0.011
 favorite-0.010
 Daddy-0.009
 masterpiece-0.009
pron-0.009
Token is
Token ID318
Feature activation-1.49e+00

Pos logit contributions
crow+1.231
Leave+1.201
Bad+1.187
eper+1.152
vious+1.094
Neg logit contributions
 favourite-0.948
pron-0.946
 favorite-0.928
 masterpiece-0.867
 couldn-0.822
Token bad
Token ID2089
Feature activation-2.27e+00

Pos logit contributions
crow+0.136
Leave+0.129
Bad+0.126
vious+0.123
eper+0.122
Neg logit contributions
pron-0.094
 favourite-0.091
 masterpiece-0.088
 favorite-0.083
 brand-0.082
Token and
Token ID290
Feature activation-1.06e-01

Pos logit contributions
Bad+0.212
crow+0.211
Leave+0.208
eper+0.198
Hey+0.193
Neg logit contributions
 favourite-0.115
 favorite-0.109
pron-0.103
 masterpiece-0.103
 brand-0.093
Token scary
Token ID14343
Feature activation-2.61e+00

Pos logit contributions
crow+0.008
eper+0.008
Leave+0.008
Bad+0.007
ases+0.007
Neg logit contributions
pron-0.008
 favourite-0.008
 masterpiece-0.007
 favorite-0.007
 brand-0.007
Token and
Token ID290
Feature activation-1.01e-01

Pos logit contributions
crow+0.254
Leave+0.252
Bad+0.252
eper+0.239
Hey+0.237
Neg logit contributions
 favourite-0.117
 favorite-0.112
 masterpiece-0.105
pron-0.099
 brand-0.094
Token I
Token ID314
Feature activation+1.29e+00

Pos logit contributions
Bad+0.014
Leave+0.013
crow+0.013
eper+0.013
vious+0.012
Neg logit contributions
 favourite-0.017
pron-0.017
 masterpiece-0.016
 favorite-0.016
 Sus-0.015
Token teach
Token ID4545
Feature activation-4.20e+00

Pos logit contributions
pron+0.105
 favourite+0.101
 masterpiece+0.099
 favorite+0.091
 brand+0.090
Neg logit contributions
crow-0.092
Bad-0.090
Leave-0.089
vious-0.082
eper-0.082
Token about
Token ID546
Feature activation+2.25e+00

Pos logit contributions
crow+0.233
Bad+0.226
Leave+0.223
vious+0.203
eper+0.202
Neg logit contributions
pron-0.407
 favourite-0.398
 masterpiece-0.391
 brand-0.365
 favorite-0.365
Token war
Token ID1175
Feature activation-7.00e+00

Pos logit contributions
pron+0.199
 favourite+0.187
 masterpiece+0.186
 brand+0.171
 favorite+0.167
Neg logit contributions
crow-0.147
Bad-0.145
Leave-0.139
eper-0.130
Stop-0.130
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
Leave+0.607
Bad+0.604
crow+0.600
vious+0.551
Stop+0.546
Neg logit contributions
 favourite-0.456
pron-0.453
 masterpiece-0.432
 favorite-0.414
 brand-0.387
Token War
Token ID1810
Feature activation-1.50e+01

Pos logit contributions
crow+0.009
Bad+0.009
Leave+0.008
eper+0.008
vious+0.008
Neg logit contributions
 favourite-0.010
pron-0.010
 masterpiece-0.009
 favorite-0.009
 Sus-0.009
Token is
Token ID318
Feature activation-1.30e+00

Pos logit contributions
crow+1.163
Leave+1.159
Bad+1.141
eper+1.062
vious+1.038
Neg logit contributions
pron-1.066
 favourite-1.062
 masterpiece-1.010
 favorite-1.006
 brand-0.915
Token when
Token ID618
Feature activation-7.18e+00

Pos logit contributions
crow+0.114
Leave+0.110
Bad+0.107
vious+0.104
eper+0.102
Neg logit contributions
pron-0.085
 favourite-0.082
 masterpiece-0.081
 brand-0.075
 favorite-0.075
Token people
Token ID661
Feature activation-9.62e+00

Pos logit contributions
crow+0.529
Bad+0.513
Leave+0.506
vious+0.478
eper+0.474
Neg logit contributions
pron-0.571
 favourite-0.550
 masterpiece-0.541
 brand-0.496
 favorite-0.494
Token fight
Token ID1907
Feature activation-4.96e+00

Pos logit contributions
crow+0.751
Bad+0.725
Leave+0.723
eper+0.676
vious+0.654
Neg logit contributions
pron-0.685
 favourite-0.646
 masterpiece-0.634
 favorite-0.600
 collection-0.588
Token.
Token ID13
Feature activation-2.56e-02

Pos logit contributions
crow+0.430
Leave+0.428
Bad+0.413
vious+0.392
eper+0.389
Neg logit contributions
pron-0.302
 favourite-0.298
 masterpiece-0.293
 favorite-0.282
 brand-0.266
Token?
Token ID30
Feature activation+2.82e+00

Pos logit contributions
Leave+0.252
Bad+0.250
crow+0.235
Stop+0.220
eper+0.216
Neg logit contributions
pron-0.172
 favourite-0.169
 masterpiece-0.158
 favorite-0.151
 collection-0.151
Token Share
Token ID8734
Feature activation-8.30e+00

Pos logit contributions
 favourite+0.240
pron+0.237
 masterpiece+0.224
 favorite+0.218
 brand+0.211
Neg logit contributions
crow-0.186
Leave-0.179
Bad-0.176
vious-0.173
ases-0.162
Token?
Token ID30
Feature activation+2.82e+00

Pos logit contributions
crow+0.663
Leave+0.657
Bad+0.641
vious+0.618
eper+0.602
Neg logit contributions
pron-0.605
 favourite-0.589
 masterpiece-0.565
 favorite-0.534
 brand-0.520
Token Play
Token ID3811
Feature activation-1.13e+01

Pos logit contributions
 favourite+0.230
pron+0.222
 favorite+0.206
 masterpiece+0.204
 brand+0.198
Neg logit contributions
crow-0.188
Bad-0.183
Leave-0.181
vious-0.176
eper-0.169
Token?
Token ID30
Feature activation+2.82e+00

Pos logit contributions
Leave+0.896
crow+0.888
Bad+0.879
vious+0.851
Stop+0.818
Neg logit contributions
pron-0.843
 favourite-0.805
 masterpiece-0.765
 favorite-0.716
 brand-0.711
Token Learn
Token ID14365
Feature activation-1.50e+01

Pos logit contributions
 favourite+0.231
pron+0.225
 favorite+0.206
 masterpiece+0.206
 brand+0.200
Neg logit contributions
crow-0.188
Bad-0.182
Leave-0.177
vious-0.174
eper-0.168
Token?"
Token ID1701
Feature activation+5.58e+00

Pos logit contributions
crow+1.131
Bad+1.112
Leave+1.109
vious+1.037
Stop+1.011
Neg logit contributions
pron-1.164
 favourite-1.133
 masterpiece-1.107
 favorite-1.027
 brand-1.018
Token the
Token ID262
Feature activation-1.74e+00

Pos logit contributions
 favourite+0.323
 masterpiece+0.313
pron+0.307
 Sus+0.289
 Mill+0.283
Neg logit contributions
crow-0.481
Bad-0.479
Leave-0.472
vious-0.464
ases-0.457
Token wolf
Token ID17481
Feature activation-3.04e+00

Pos logit contributions
crow+0.109
Bad+0.105
Leave+0.104
ases+0.097
vious+0.097
Neg logit contributions
pron-0.161
 favourite-0.154
 masterpiece-0.151
 brand-0.142
 favorite-0.140
Token says
Token ID1139
Feature activation-2.08e+00

Pos logit contributions
Bad+0.260
Leave+0.251
crow+0.245
Stop+0.238
ases+0.229
Neg logit contributions
pron-0.185
 favourite-0.184
 masterpiece-0.182
 favorite-0.171
onna-0.161
Token.
Token ID13
Feature activation-8.39e-02

Pos logit contributions
crow+0.178
Bad+0.178
Leave+0.173
Stop+0.167
vious+0.163
Neg logit contributions
pron-0.142
 favourite-0.135
 masterpiece-0.132
 favorite-0.120
 brand-0.119
TokenJoin
Token ID18234
Feature activation-5.91e+00

Pos logit contributions
pron+0.034
 favourite+0.033
 masterpiece+0.033
 favorite+0.030
 usual+0.030
Neg logit contributions
crow-0.026
Bad-0.025
eper-0.025
Leave-0.024
 hunters-0.024
Token the
Token ID262
Feature activation-1.90e+00

Pos logit contributions
Leave+0.443
crow+0.438
Bad+0.431
vious+0.409
eper+0.404
Neg logit contributions
 favourite-0.456
pron-0.443
 masterpiece-0.435
 favorite-0.412
 brand-0.399
Token Jazz
Token ID21406
Feature activation-1.74e+00

Pos logit contributions
crow+0.170
Bad+0.166
Leave+0.166
vious+0.156
eper+0.156
Neg logit contributions
pron-0.123
 favourite-0.117
 masterpiece-0.116
 favorite-0.102
 brand-0.102
Token Club
Token ID6289
Feature activation-4.06e+00

Pos logit contributions
crow+0.131
Bad+0.128
Leave+0.126
vious+0.118
eper+0.117
Neg logit contributions
pron-0.137
 favourite-0.130
 masterpiece-0.129
 brand-0.118
 favorite-0.116
Token!
Token ID0
Feature activation+3.01e+00

Pos logit contributions
crow+0.308
Bad+0.303
Leave+0.298
vious+0.278
Stop+0.277
Neg logit contributions
pron-0.315
 favourite-0.300
 masterpiece-0.296
 brand-0.270
 favorite-0.268
Token Learn
Token ID14365
Feature activation-1.50e+01

Pos logit contributions
 favourite+0.232
pron+0.221
 Sus+0.214
 favorite+0.209
 masterpiece+0.208
Neg logit contributions
Bad-0.204
Leave-0.190
crow-0.188
eper-0.179
vious-0.174
Token to
Token ID284
Feature activation+1.38e+00

Pos logit contributions
crow+1.125
Bad+1.095
Leave+1.074
vious+1.009
eper+1.005
Neg logit contributions
pron-1.194
 favourite-1.128
 masterpiece-1.118
 brand-1.021
 favorite-1.004
Token play
Token ID711
Feature activation-1.16e+00

Pos logit contributions
pron+0.106
 favourite+0.102
 masterpiece+0.101
 brand+0.091
 favorite+0.091
Neg logit contributions
crow-0.104
Bad-0.102
Leave-0.100
vious-0.095
eper-0.094
Token instruments
Token ID12834
Feature activation-3.38e+00

Pos logit contributions
crow+0.095
Leave+0.094
Bad+0.093
vious+0.089
eper+0.087
Neg logit contributions
pron-0.082
 favourite-0.081
 masterpiece-0.077
 brand-0.073
 favorite-0.072
Token and
Token ID290
Feature activation+2.42e-01

Pos logit contributions
crow+0.263
Bad+0.257
Leave+0.254
vious+0.236
Stop+0.235
Neg logit contributions
pron-0.260
 favourite-0.250
 masterpiece-0.244
 favorite-0.223
 brand-0.223
Token sing
Token ID1702
Feature activation-1.71e-01

Pos logit contributions
pron+0.018
 favourite+0.017
 masterpiece+0.017
 brand+0.015
 favorite+0.015
Neg logit contributions
crow-0.019
Bad-0.019
Leave-0.018
eper-0.018
vious-0.018
Token people
Token ID661
Feature activation-9.76e+00

Pos logit contributions
Bad+0.363
Leave+0.348
crow+0.343
eper+0.330
Hey+0.312
Neg logit contributions
 favourite-0.508
 masterpiece-0.489
 favorite-0.482
pron-0.468
 usual-0.460
Token and
Token ID290
Feature activation-1.45e-01

Pos logit contributions
Leave+0.796
crow+0.792
Bad+0.783
Hey+0.749
Stop+0.749
Neg logit contributions
pron-0.693
 favourite-0.672
 masterpiece-0.620
 favorite-0.619
 collection-0.578
Token their
Token ID511
Feature activation+7.25e-01

Pos logit contributions
crow+0.010
Bad+0.009
Leave+0.009
vious+0.009
eper+0.009
Neg logit contributions
pron-0.012
 favourite-0.012
 masterpiece-0.012
 favorite-0.011
 brand-0.011
Token feelings
Token ID7666
Feature activation-3.54e+00

Pos logit contributions
pron+0.058
 favourite+0.057
 masterpiece+0.056
 favorite+0.052
 brand+0.051
Neg logit contributions
crow-0.052
Bad-0.051
Leave-0.051
vious-0.047
eper-0.047
Token.
Token ID13
Feature activation-5.99e-01

Pos logit contributions
crow+0.296
Bad+0.291
Leave+0.288
vious+0.269
eper+0.269
Neg logit contributions
pron-0.244
 favourite-0.235
 masterpiece-0.228
 favorite-0.210
 brand-0.208
Token Learn
Token ID14365
Feature activation-1.49e+01

Pos logit contributions
crow+0.044
Leave+0.044
vious+0.044
Bad+0.042
eper+0.041
Neg logit contributions
 favourite-0.040
pron-0.040
 Sus-0.037
 masterpiece-0.037
 favorite-0.036
Token to
Token ID284
Feature activation+1.29e+00

Pos logit contributions
crow+1.140
Bad+1.107
Leave+1.072
ases+1.021
eper+1.018
Neg logit contributions
pron-1.185
 favourite-1.102
 masterpiece-1.100
 brand-1.001
 favorite-0.961
Token appreciate
Token ID9144
Feature activation+1.91e-01

Pos logit contributions
pron+0.102
 favourite+0.097
 masterpiece+0.096
 brand+0.088
 favorite+0.087
Neg logit contributions
crow-0.095
Bad-0.092
Leave-0.090
vious-0.086
eper-0.085
Token and
Token ID290
Feature activation-1.94e-01

Pos logit contributions
pron+0.016
 favourite+0.015
 masterpiece+0.015
 brand+0.014
 favorite+0.014
Neg logit contributions
crow-0.014
Bad-0.013
Leave-0.013
vious-0.012
eper-0.012
Token enjoy
Token ID2883
Feature activation+2.52e+00

Pos logit contributions
crow+0.014
Bad+0.014
Leave+0.013
vious+0.013
eper+0.013
Neg logit contributions
pron-0.015
 favourite-0.015
 masterpiece-0.015
 brand-0.013
 favorite-0.013
Token different
Token ID1180
Feature activation-5.65e-01

Pos logit contributions
pron+0.209
 favourite+0.203
 masterpiece+0.199
 brand+0.185
 favorite+0.184
Neg logit contributions
crow-0.175
Leave-0.167
Bad-0.167
vious-0.160
eper-0.155
Token It
Token ID632
Feature activation-2.96e-01

Pos logit contributions
Leave+0.015
crow+0.015
Bad+0.015
eper+0.015
Stop+0.015
Neg logit contributions
 favourite-0.009
 favorite-0.008
 Grand-0.008
pron-0.008
 Sus-0.008
Token is
Token ID318
Feature activation-1.36e+00

Pos logit contributions
crow+0.024
Leave+0.024
Bad+0.023
ases+0.022
eper+0.022
Neg logit contributions
 favourite-0.020
pron-0.020
 masterpiece-0.019
 favorite-0.018
 brand-0.017
Token for
Token ID329
Feature activation+5.47e+00

Pos logit contributions
crow+0.111
Bad+0.110
Leave+0.106
eper+0.101
vious+0.100
Neg logit contributions
pron-0.099
 masterpiece-0.092
 favourite-0.092
 brand-0.082
 favorite-0.079
Token war
Token ID1175
Feature activation-6.76e+00

Pos logit contributions
pron+0.429
 favourite+0.414
 masterpiece+0.407
 brand+0.376
 favorite+0.372
Neg logit contributions
crow-0.409
Bad-0.391
Leave-0.389
vious-0.371
eper-0.362
Token.
Token ID13
Feature activation-7.98e-02

Pos logit contributions
crow+0.566
Leave+0.559
Bad+0.559
vious+0.516
eper+0.512
Neg logit contributions
pron-0.454
 favourite-0.451
 masterpiece-0.426
 favorite-0.415
 brand-0.389
Token War
Token ID1810
Feature activation-1.48e+01

Pos logit contributions
crow+0.006
eper+0.006
Leave+0.006
Bad+0.006
vious+0.005
Neg logit contributions
 favourite-0.005
 Grand-0.005
 favorite-0.005
pron-0.005
 Sus-0.005
Token is
Token ID318
Feature activation-1.32e+00

Pos logit contributions
crow+1.182
Leave+1.182
Bad+1.156
eper+1.101
vious+1.070
Neg logit contributions
 favourite-0.962
 favorite-0.943
pron-0.940
 masterpiece-0.865
 couldn-0.845
Token bad
Token ID2089
Feature activation-2.00e+00

Pos logit contributions
crow+0.119
Leave+0.113
Bad+0.109
vious+0.108
eper+0.106
Neg logit contributions
pron-0.081
 favourite-0.081
 masterpiece-0.078
 favorite-0.075
 brand-0.074
Token,"
Token ID553
Feature activation+4.74e+00

Pos logit contributions
Bad+0.175
crow+0.173
Leave+0.173
eper+0.160
Hey+0.158
Neg logit contributions
 favourite-0.118
pron-0.114
 favorite-0.111
 masterpiece-0.108
 brand-0.099
Token Lily
Token ID20037
Feature activation+1.90e+00

Pos logit contributions
pron+0.333
 favourite+0.314
 masterpiece+0.310
 brand+0.280
 favorite+0.278
Neg logit contributions
crow-0.400
Bad-0.389
Leave-0.384
vious-0.366
eper-0.363
Token said
Token ID531
Feature activation+9.63e-01

Pos logit contributions
pron+0.090
 favourite+0.083
 masterpiece+0.076
 favorite+0.073
 brand+0.069
Neg logit contributions
crow-0.195
Bad-0.193
Leave-0.192
ases-0.184
eper-0.180
Token missile
Token ID10105
Feature activation-2.52e+00

Pos logit contributions
crow+0.121
Leave+0.120
ases+0.115
Bad+0.114
vious+0.113
Neg logit contributions
 favourite-0.105
pron-0.105
 masterpiece-0.104
 favorite-0.099
 brand-0.095
Token was
Token ID373
Feature activation+1.22e+00

Pos logit contributions
crow+0.216
Leave+0.215
Bad+0.212
Stop+0.198
vious+0.196
Neg logit contributions
pron-0.157
 favourite-0.155
 masterpiece-0.149
 favorite-0.144
 collection-0.135
Token for
Token ID329
Feature activation+5.50e+00

Pos logit contributions
pron+0.087
 favourite+0.084
 masterpiece+0.082
 favorite+0.078
 brand+0.076
Neg logit contributions
crow-0.100
Leave-0.095
Bad-0.093
vious-0.090
Stop-0.090
Token war
Token ID1175
Feature activation-6.73e+00

Pos logit contributions
pron+0.412
 favourite+0.404
 masterpiece+0.401
 brand+0.374
 usual+0.368
Neg logit contributions
crow-0.425
Leave-0.392
Bad-0.388
vious-0.382
eper-0.372
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
crow+0.597
Bad+0.596
Leave+0.592
eper+0.547
Stop+0.542
Neg logit contributions
 favourite-0.407
pron-0.406
 masterpiece-0.382
 favorite-0.375
 usual-0.346
Token War
Token ID1810
Feature activation-1.48e+01

Pos logit contributions
crow+0.013
eper+0.012
Leave+0.012
vious+0.012
Bad+0.012
Neg logit contributions
 favourite-0.010
 favorite-0.009
pron-0.009
 brand-0.009
 Grand-0.009
Token is
Token ID318
Feature activation-1.38e+00

Pos logit contributions
crow+1.173
Leave+1.156
Bad+1.135
eper+1.095
vious+1.045
Neg logit contributions
pron-0.997
 favourite-0.996
 favorite-0.957
 masterpiece-0.926
 couldn-0.862
Token bad
Token ID2089
Feature activation-1.99e+00

Pos logit contributions
crow+0.120
Leave+0.113
Bad+0.109
vious+0.107
eper+0.106
Neg logit contributions
pron-0.092
 favourite-0.090
 masterpiece-0.088
 brand-0.084
 favorite-0.084
Token.
Token ID13
Feature activation-1.08e-01

Pos logit contributions
Bad+0.181
crow+0.180
Leave+0.178
eper+0.167
vious+0.162
Neg logit contributions
 favourite-0.111
pron-0.107
 favorite-0.103
 masterpiece-0.102
 brand-0.094
Token I
Token ID314
Feature activation+1.60e+00

Pos logit contributions
crow+0.009
eper+0.008
Leave+0.008
vious+0.008
 thieves+0.008
Neg logit contributions
 favourite-0.007
 favorite-0.007
 Grand-0.006
 Daddy-0.006
pron-0.006
Token don
Token ID836
Feature activation-4.25e+00

Pos logit contributions
 favourite+0.114
pron+0.111
 favorite+0.107
 masterpiece+0.106
 couldn+0.095
Neg logit contributions
crow-0.123
Leave-0.121
Bad-0.118
eper-0.115
ases-0.111
TokenHave
Token ID11980
Feature activation-4.31e+00

Pos logit contributions
pron+0.049
 favourite+0.045
 masterpiece+0.043
 favorite+0.040
 usual+0.039
Neg logit contributions
crow-0.036
eper-0.033
ases-0.032
Bad-0.032
vious-0.032
Token fun
Token ID1257
Feature activation+1.02e+00

Pos logit contributions
Bad+0.330
crow+0.323
Leave+0.322
Stop+0.312
Hey+0.306
Neg logit contributions
pron-0.339
 masterpiece-0.317
 favourite-0.293
 porch-0.273
 collection-0.272
Token,
Token ID11
Feature activation-1.29e+00

Pos logit contributions
pron+0.082
 favourite+0.078
 masterpiece+0.077
 brand+0.070
 favorite+0.070
Neg logit contributions
crow-0.076
Bad-0.074
Leave-0.072
vious-0.068
eper-0.067
Token Lily
Token ID20037
Feature activation+1.95e+00

Pos logit contributions
crow+0.110
Bad+0.108
Leave+0.106
vious+0.100
eper+0.099
Neg logit contributions
pron-0.089
 favourite-0.084
 masterpiece-0.083
 brand-0.075
 favorite-0.073
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
pron+0.147
 favourite+0.137
 masterpiece+0.136
 favorite+0.123
 brand+0.123
Neg logit contributions
crow-0.155
Bad-0.150
Leave-0.150
vious-0.140
Stop-0.139
Token Learn
Token ID14365
Feature activation-1.48e+01

Pos logit contributions
crow+0.009
Bad+0.009
Leave+0.009
eper+0.008
vious+0.008
Neg logit contributions
pron-0.013
 favourite-0.013
 masterpiece-0.012
 favorite-0.012
 Sus-0.012
Token a
Token ID257
Feature activation-1.02e-01

Pos logit contributions
crow+1.125
Bad+1.090
Leave+1.043
ases+1.021
eper+1.013
Neg logit contributions
pron-1.179
 masterpiece-1.087
 favourite-1.072
 brand-0.984
 collection-0.928
Token lot
Token ID1256
Feature activation+3.29e+00

Pos logit contributions
Bad+0.008
crow+0.008
Leave+0.008
Stop+0.008
 bully+0.008
Neg logit contributions
pron-0.007
 masterpiece-0.006
 favourite-0.006
 brand-0.005
 usual-0.005
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
pron+0.266
 favourite+0.254
 masterpiece+0.249
 favorite+0.229
 brand+0.229
Neg logit contributions
crow-0.237
Bad-0.236
Leave-0.235
vious-0.214
Stop-0.214
Token We
Token ID775
Feature activation+7.59e-02

Pos logit contributions
crow+0.011
Bad+0.011
eper+0.010
Leave+0.010
vious+0.010
Neg logit contributions
pron-0.014
 favourite-0.014
 masterpiece-0.013
 favorite-0.012
 Sus-0.012
Token are
Token ID389
Feature activation-4.09e+00

Pos logit contributions
pron+0.006
 favourite+0.005
 masterpiece+0.005
 favorite+0.005
 collection+0.005
Neg logit contributions
crow-0.006
Leave-0.006
Bad-0.006
vious-0.005
Stop-0.005
Token,
Token ID11
Feature activation-1.28e+00

Pos logit contributions
pron+0.085
 masterpiece+0.081
 favourite+0.079
 brand+0.072
 favorite+0.070
Neg logit contributions
crow-0.079
Bad-0.076
Leave-0.075
eper-0.071
vious-0.070
Token "
Token ID366
Feature activation+7.18e-01

Pos logit contributions
Bad+0.098
Leave+0.098
crow+0.097
eper+0.089
Stop+0.089
Neg logit contributions
 masterpiece-0.091
pron-0.091
 favourite-0.090
 favorite-0.079
 brand-0.079
TokenMe
Token ID5308
Feature activation-1.20e+00

Pos logit contributions
pron+0.066
 favourite+0.062
 masterpiece+0.060
 brand+0.056
 favorite+0.055
Neg logit contributions
crow-0.047
Bad-0.043
Leave-0.042
eper-0.042
ases-0.042
Token too
Token ID1165
Feature activation-5.70e+00

Pos logit contributions
crow+0.074
Bad+0.071
Leave+0.071
Stop+0.064
vious+0.063
Neg logit contributions
pron-0.113
 favourite-0.110
 masterpiece-0.107
 brand-0.101
 favorite-0.101
Token.
Token ID13
Feature activation+1.04e-01

Pos logit contributions
crow+0.446
Bad+0.434
Leave+0.427
vious+0.401
eper+0.399
Neg logit contributions
pron-0.437
 favourite-0.415
 masterpiece-0.409
 brand-0.375
 favorite-0.369
Token War
Token ID1810
Feature activation-1.48e+01

Pos logit contributions
pron+0.009
 favourite+0.008
 masterpiece+0.008
 brand+0.008
 favorite+0.008
Neg logit contributions
crow-0.007
Bad-0.007
Leave-0.007
vious-0.006
eper-0.006
Token is
Token ID318
Feature activation-1.21e+00

Pos logit contributions
crow+1.172
Leave+1.140
Bad+1.131
eper+1.081
ases+1.049
Neg logit contributions
pron-1.033
 favourite-1.030
 masterpiece-0.965
 favorite-0.964
 brand-0.905
Token bad
Token ID2089
Feature activation-2.05e+00

Pos logit contributions
crow+0.099
Bad+0.096
Leave+0.095
vious+0.090
eper+0.089
Neg logit contributions
pron-0.088
 favourite-0.083
 masterpiece-0.082
 brand-0.075
 favorite-0.074
Token.
Token ID13
Feature activation+1.04e-01

Pos logit contributions
crow+0.176
Bad+0.175
Leave+0.173
eper+0.160
vious+0.158
Neg logit contributions
 favourite-0.131
pron-0.129
 masterpiece-0.122
 favorite-0.119
 brand-0.112
Token It
Token ID632
Feature activation-2.31e-01

Pos logit contributions
 favourite+0.008
pron+0.008
 masterpiece+0.007
 favorite+0.007
 brand+0.007
Neg logit contributions
crow-0.008
Leave-0.007
Bad-0.007
eper-0.007
vious-0.007
Token makes
Token ID1838
Feature activation-4.88e-01

Pos logit contributions
crow+0.019
Leave+0.018
Bad+0.018
ases+0.017
eper+0.017
Neg logit contributions
 favourite-0.016
pron-0.016
 masterpiece-0.016
 favorite-0.015
 brand-0.014
Token birds
Token ID10087
Feature activation-9.19e+00

Pos logit contributions
crow+0.138
Bad+0.134
Leave+0.132
vious+0.124
eper+0.124
Neg logit contributions
pron-0.119
 favourite-0.112
 masterpiece-0.111
 brand-0.100
 favorite-0.098
Token,"
Token ID553
Feature activation+3.95e+00

Pos logit contributions
crow+0.727
Bad+0.711
Leave+0.698
vious+0.657
eper+0.655
Neg logit contributions
pron-0.684
 favourite-0.648
 masterpiece-0.640
 brand-0.582
 favorite-0.573
Token said
Token ID531
Feature activation+3.74e-01

Pos logit contributions
pron+0.259
 favourite+0.244
 masterpiece+0.239
 brand+0.214
 favorite+0.212
Neg logit contributions
crow-0.348
Bad-0.341
Leave-0.337
vious-0.320
eper-0.318
Token the
Token ID262
Feature activation-1.89e+00

Pos logit contributions
pron+0.027
 masterpiece+0.026
 favourite+0.025
 brand+0.023
 favorite+0.022
Neg logit contributions
crow-0.031
Bad-0.030
Leave-0.028
eper-0.028
vious-0.026
Token scare
Token ID19437
Feature activation-4.75e+00

Pos logit contributions
crow+0.135
Bad+0.132
Leave+0.129
vious+0.121
eper+0.120
Neg logit contributions
pron-0.156
 favourite-0.148
 masterpiece-0.147
 brand-0.135
 favorite-0.133
Tokencrow
Token ID47114
Feature activation-1.48e+01

Pos logit contributions
Bad+0.099
Leave+0.095
ases+0.067
Stop+0.063
vious+0.062
Neg logit contributions
pron-0.605
 favourite-0.588
 masterpiece-0.577
ail-0.559
 favorite-0.553
Token.
Token ID13
Feature activation-4.99e-01

Pos logit contributions
crow+1.020
Bad+0.950
eper+0.923
Leave+0.922
vious+0.889
Neg logit contributions
pron-1.249
 masterpiece-1.180
 favourite-1.154
 brand-1.075
 favorite-1.029
Token
Token ID198
Feature activation+3.21e-02

Pos logit contributions
crow+0.040
Bad+0.039
Leave+0.038
vious+0.036
eper+0.036
Neg logit contributions
pron-0.037
 favourite-0.035
 masterpiece-0.034
 brand-0.031
 favorite-0.031
Token
Token ID198
Feature activation-3.38e-02

Pos logit contributions
pron+0.002
 favourite+0.002
 masterpiece+0.002
 brand+0.002
 favorite+0.002
Neg logit contributions
crow-0.003
Bad-0.003
Leave-0.003
vious-0.002
eper-0.002
Token"
Token ID1
Feature activation-5.26e+00

Pos logit contributions
vious+0.002
crow+0.002
ases+0.002
eper+0.002
ting+0.002
Neg logit contributions
pron-0.003
 favourite-0.002
 masterpiece-0.002
ail-0.002
 brand-0.002
TokenOh
Token ID5812
Feature activation-2.88e+00

Pos logit contributions
crow+0.328
ases+0.315
vious+0.306
eper+0.304
Bad+0.295
Neg logit contributions
pron-0.467
 favourite-0.437
 masterpiece-0.408
 favorite-0.388
 usual-0.378
TokenJoin
Token ID18234
Feature activation-5.73e+00

Pos logit contributions
pron+0.047
 favourite+0.045
 masterpiece+0.044
 usual+0.041
 favorite+0.041
Neg logit contributions
crow-0.035
Bad-0.034
eper-0.034
Leave-0.032
vious-0.032
Token the
Token ID262
Feature activation-1.59e+00

Pos logit contributions
Leave+0.426
crow+0.418
Bad+0.414
vious+0.394
eper+0.390
Neg logit contributions
 favourite-0.447
pron-0.427
 masterpiece-0.420
 favorite-0.406
 brand-0.387
Token Little
Token ID7703
Feature activation+2.92e+00

Pos logit contributions
crow+0.132
Bad+0.130
Leave+0.129
vious+0.122
eper+0.121
Neg logit contributions
pron-0.111
 favourite-0.108
 masterpiece-0.105
 favorite-0.095
 brand-0.094
Token League
Token ID4041
Feature activation-1.87e+00

Pos logit contributions
pron+0.231
 favourite+0.223
 masterpiece+0.217
 favorite+0.201
 usual+0.195
Neg logit contributions
crow-0.208
Bad-0.206
Leave-0.205
vious-0.196
ases-0.194
Token!
Token ID0
Feature activation+3.27e+00

Pos logit contributions
Bad+0.143
Leave+0.143
crow+0.143
vious+0.132
Stop+0.130
Neg logit contributions
pron-0.139
 favourite-0.135
 masterpiece-0.130
 favorite-0.121
 collection-0.117
Token Learn
Token ID14365
Feature activation-1.47e+01

Pos logit contributions
 favourite+0.244
pron+0.235
 Sus+0.234
 Grand+0.220
 masterpiece+0.219
Neg logit contributions
Bad-0.218
Leave-0.211
crow-0.208
eper-0.201
vious-0.200
Token to
Token ID284
Feature activation+1.56e+00

Pos logit contributions
crow+1.149
Bad+1.120
Leave+1.100
vious+1.035
eper+1.031
Neg logit contributions
pron-1.124
 favourite-1.063
 masterpiece-1.052
 brand-0.958
 favorite-0.943
Token play
Token ID711
Feature activation-1.17e+00

Pos logit contributions
pron+0.117
 favourite+0.112
 masterpiece+0.111
 brand+0.100
 favorite+0.100
Neg logit contributions
crow-0.121
Bad-0.119
Leave-0.117
vious-0.111
eper-0.110
Token baseball
Token ID9283
Feature activation+4.47e-01

Pos logit contributions
Leave+0.098
crow+0.097
Bad+0.095
vious+0.093
eper+0.090
Neg logit contributions
 favourite-0.078
pron-0.077
 masterpiece-0.072
 favorite-0.071
 brand-0.068
Token with
Token ID351
Feature activation-1.84e+00

Pos logit contributions
pron+0.031
 favourite+0.030
 masterpiece+0.029
 favorite+0.028
 collection+0.027
Neg logit contributions
Leave-0.037
crow-0.037
Bad-0.037
vious-0.034
eper-0.033
Token other
Token ID584
Feature activation-5.73e+00

Pos logit contributions
crow+0.128
Leave+0.126
Bad+0.124
vious+0.117
eper+0.115
Neg logit contributions
pron-0.153
 favourite-0.150
 masterpiece-0.145
 favorite-0.136
 brand-0.135
Token any
Token ID597
Feature activation+1.25e-01

Pos logit contributions
crow+0.368
Bad+0.355
Leave+0.349
eper+0.328
vious+0.327
Neg logit contributions
pron-0.396
 favourite-0.380
 masterpiece-0.375
 brand-0.345
 favorite-0.341
Token situation
Token ID3074
Feature activation-2.03e+00

Pos logit contributions
pron+0.010
 favourite+0.010
 masterpiece+0.010
 brand+0.009
 favorite+0.009
Neg logit contributions
crow-0.009
Bad-0.009
Leave-0.009
eper-0.008
ases-0.008
Token too
Token ID1165
Feature activation-5.69e+00

Pos logit contributions
crow+0.162
Bad+0.160
Leave+0.158
eper+0.148
vious+0.147
Neg logit contributions
pron-0.146
 favourite-0.141
 masterpiece-0.138
 brand-0.127
 favorite-0.126
Token seriously
Token ID6411
Feature activation-1.97e+00

Pos logit contributions
crow+0.487
Bad+0.476
Leave+0.470
eper+0.444
vious+0.442
Neg logit contributions
pron-0.390
 favourite-0.368
 masterpiece-0.362
 brand-0.327
 favorite-0.322
Token.
Token ID13
Feature activation-1.26e-01

Pos logit contributions
crow+0.152
Bad+0.148
Leave+0.145
eper+0.137
ases+0.136
Neg logit contributions
pron-0.150
 favourite-0.142
 masterpiece-0.140
 brand-0.130
 favorite-0.127
Token Learn
Token ID14365
Feature activation-1.47e+01

Pos logit contributions
Bad+0.009
crow+0.009
Leave+0.009
vious+0.008
eper+0.008
Neg logit contributions
 favourite-0.010
pron-0.010
 masterpiece-0.009
 favorite-0.009
 Sus-0.009
Token to
Token ID284
Feature activation+1.70e+00

Pos logit contributions
crow+1.276
Bad+1.250
Leave+1.233
vious+1.166
eper+1.159
Neg logit contributions
pron-0.984
 favourite-0.931
 masterpiece-0.916
 brand-0.824
 favorite-0.814
Token laugh
Token ID6487
Feature activation-1.78e+00

Pos logit contributions
pron+0.133
 favourite+0.126
 masterpiece+0.125
 brand+0.114
 favorite+0.112
Neg logit contributions
crow-0.129
Bad-0.125
Leave-0.123
vious-0.116
eper-0.115
Token at
Token ID379
Feature activation+1.76e-03

Pos logit contributions
crow+0.142
Bad+0.140
Leave+0.139
eper+0.130
ases+0.128
Neg logit contributions
pron-0.129
 favourite-0.127
 masterpiece-0.121
 favorite-0.113
 brand-0.112
Token yourself
Token ID3511
Feature activation-6.38e+00

Pos logit contributions
pron+0.000
 favourite+0.000
 masterpiece+0.000
 brand+0.000
 favorite+0.000
Neg logit contributions
crow-0.000
Leave-0.000
Bad-0.000
vious-0.000
eper-0.000
Token and
Token ID290
Feature activation+2.36e-01

Pos logit contributions
crow+0.495
Bad+0.493
Leave+0.490
ases+0.451
Stop+0.450
Neg logit contributions
pron-0.477
 favourite-0.460
 masterpiece-0.446
 brand-0.411
 favorite-0.408
Tokenockey
Token ID8337
Feature activation+3.92e-01

Pos logit contributions
pron+0.056
 favourite+0.053
 masterpiece+0.052
 collection+0.048
 brand+0.046
Neg logit contributions
Bad-0.066
Leave-0.066
crow-0.066
Stop-0.061
eper-0.061
Token Camp
Token ID5425
Feature activation-4.12e+00

Pos logit contributions
pron+0.030
 favourite+0.029
 masterpiece+0.028
 brand+0.026
 favorite+0.026
Neg logit contributions
Leave-0.030
Bad-0.029
crow-0.029
eper-0.027
vious-0.027
Token for
Token ID329
Feature activation+5.62e+00

Pos logit contributions
crow+0.304
Bad+0.302
Leave+0.300
vious+0.276
eper+0.273
Neg logit contributions
pron-0.327
 favourite-0.314
 masterpiece-0.307
 brand-0.282
 favorite-0.281
Token Kids
Token ID17476
Feature activation-1.86e+00

Pos logit contributions
pron+0.456
 favourite+0.442
 masterpiece+0.432
 brand+0.404
 favorite+0.397
Neg logit contributions
crow-0.409
Leave-0.388
Bad-0.388
vious-0.368
eper-0.361
Token.
Token ID13
Feature activation+8.59e-02

Pos logit contributions
Bad+0.145
crow+0.142
Leave+0.142
vious+0.130
Stop+0.130
Neg logit contributions
pron-0.137
 favourite-0.136
 masterpiece-0.130
 favorite-0.121
 usual-0.119
Token Learn
Token ID14365
Feature activation-1.46e+01

Pos logit contributions
 favourite+0.006
 Sus+0.006
pron+0.006
 favorite+0.006
 masterpiece+0.006
Neg logit contributions
Bad-0.006
Leave-0.006
crow-0.006
vious-0.005
eper-0.005
Token from
Token ID422
Feature activation-3.66e+00

Pos logit contributions
crow+1.208
Bad+1.187
Leave+1.175
vious+1.105
Stop+1.090
Neg logit contributions
pron-1.038
 favourite-0.999
 masterpiece-0.976
 brand-0.890
 favorite-0.888
Token the
Token ID262
Feature activation-1.27e+00

Pos logit contributions
crow+0.273
Bad+0.264
Leave+0.262
vious+0.246
Stop+0.242
Neg logit contributions
pron-0.292
 favourite-0.279
 masterpiece-0.275
 brand-0.253
 favorite-0.250
Token Best
Token ID6705
Feature activation-2.82e+00

Pos logit contributions
crow+0.110
Leave+0.107
Bad+0.104
vious+0.102
ases+0.102
Neg logit contributions
pron-0.086
 favourite-0.084
 masterpiece-0.082
 usual-0.075
 favorite-0.075
Token.
Token ID13
Feature activation+4.66e-02

Pos logit contributions
Bad+0.203
Leave+0.202
crow+0.201
vious+0.180
eper+0.179
Neg logit contributions
 favourite-0.226
pron-0.225
 masterpiece-0.216
 favorite-0.205
 collection-0.201
Token Sign
Token ID5865
Feature activation-5.95e+00

Pos logit contributions
 favourite+0.004
pron+0.003
 Sus+0.003
 masterpiece+0.003
 Mill+0.003
Neg logit contributions
Bad-0.003
Leave-0.003
crow-0.003
eper-0.003
vious-0.003
TokenStop
Token ID19485
Feature activation-1.16e+01

Pos logit contributions
pron+0.023
 masterpiece+0.021
 brushes+0.021
 favourite+0.021
 Sus+0.021
Neg logit contributions
crow-0.021
vious-0.020
 hunters-0.020
ases-0.020
eper-0.019
Token it
Token ID340
Feature activation+1.83e-01

Pos logit contributions
crow+0.990
Leave+0.917
Bad+0.897
vious+0.896
ases+0.875
Neg logit contributions
pron-0.807
 masterpiece-0.768
 favourite-0.758
 brand-0.709
 favorite-0.682
Token,
Token ID11
Feature activation-1.56e+00

Pos logit contributions
pron+0.010
 favourite+0.009
 masterpiece+0.009
 favorite+0.008
 brand+0.008
Neg logit contributions
crow-0.018
Leave-0.017
Bad-0.017
vious-0.016
eper-0.016
Token girls
Token ID4813
Feature activation-5.39e+00

Pos logit contributions
crow+0.116
Leave+0.112
Bad+0.110
vious+0.104
ases+0.102
Neg logit contributions
pron-0.119
 favourite-0.117
 masterpiece-0.114
 favorite-0.107
 brand-0.104
Token!
Token ID0
Feature activation+2.76e+00

Pos logit contributions
crow+0.480
Bad+0.467
Leave+0.464
vious+0.437
eper+0.431
Neg logit contributions
pron-0.338
 masterpiece-0.314
 favourite-0.314
 collection-0.281
 favorite-0.278
Token Fighting
Token ID19098
Feature activation-1.46e+01

Pos logit contributions
pron+0.235
 favourite+0.234
 Sus+0.228
 masterpiece+0.224
 Daddy+0.216
Neg logit contributions
crow-0.144
vious-0.140
Leave-0.139
Bad-0.137
 hunters-0.137
Token is
Token ID318
Feature activation-1.43e+00

Pos logit contributions
crow+1.081
Leave+1.027
Bad+1.024
vious+0.957
eper+0.946
Neg logit contributions
pron-1.167
 favourite-1.116
 masterpiece-1.100
 favorite-1.035
 brand-1.025
Token not
Token ID407
Feature activation+1.92e+00

Pos logit contributions
crow+0.130
Leave+0.123
Bad+0.118
vious+0.117
eper+0.115
Neg logit contributions
pron-0.092
 favourite-0.086
 masterpiece-0.085
 brand-0.080
 favorite-0.080
Token nice
Token ID3621
Feature activation-4.04e-01

Pos logit contributions
pron+0.123
 favourite+0.114
 masterpiece+0.111
 favorite+0.104
 brand+0.104
Neg logit contributions
crow-0.177
Leave-0.169
Bad-0.165
eper-0.160
vious-0.159
Token.
Token ID13
Feature activation+2.49e-02

Pos logit contributions
crow+0.036
Leave+0.036
Bad+0.036
eper+0.033
vious+0.032
Neg logit contributions
pron-0.024
 favourite-0.024
 masterpiece-0.024
 favorite-0.022
 brand-0.021
Token You
Token ID921
Feature activation-5.89e+00

Pos logit contributions
 favourite+0.002
pron+0.002
 masterpiece+0.002
 favorite+0.002
 Sus+0.002
Neg logit contributions
crow-0.002
Leave-0.002
Bad-0.002
eper-0.002
 hunters-0.001
Token for
Token ID329
Feature activation+5.21e+00

Pos logit contributions
crow+0.087
Bad+0.084
Leave+0.082
eper+0.077
vious+0.077
Neg logit contributions
pron-0.088
 masterpiece-0.082
 favourite-0.082
 brand-0.075
 favorite-0.073
Token help
Token ID1037
Feature activation-2.70e+00

Pos logit contributions
pron+0.419
 favourite+0.403
 masterpiece+0.395
 brand+0.365
 favorite+0.360
Neg logit contributions
crow-0.379
Bad-0.370
Leave-0.364
vious-0.344
Stop-0.339
Token.
Token ID13
Feature activation-4.03e-01

Pos logit contributions
crow+0.218
Bad+0.216
Leave+0.212
vious+0.201
Stop+0.199
Neg logit contributions
pron-0.197
 favourite-0.187
 masterpiece-0.184
 brand-0.167
 favorite-0.164
Token The
Token ID383
Feature activation-2.06e-01

Pos logit contributions
crow+0.032
Bad+0.031
Leave+0.031
vious+0.029
eper+0.029
Neg logit contributions
pron-0.030
 favourite-0.028
 masterpiece-0.028
 brand-0.025
 favorite-0.025
Token scare
Token ID19437
Feature activation-4.52e+00

Pos logit contributions
Leave+0.013
Bad+0.013
ases+0.013
crow+0.013
vious+0.012
Neg logit contributions
pron-0.017
 favourite-0.017
 masterpiece-0.017
 favorite-0.015
 brand-0.015
Tokencrow
Token ID47114
Feature activation-1.45e+01

Pos logit contributions
Bad+0.068
Leave+0.063
ases+0.045
eper+0.035
Stop+0.035
Neg logit contributions
pron-0.587
 favourite-0.583
 masterpiece-0.569
ail-0.549
 usual-0.546
Token said
Token ID531
Feature activation+9.58e-01

Pos logit contributions
crow+1.255
Bad+1.211
Leave+1.179
vious+1.145
eper+1.144
Neg logit contributions
pron-0.989
 masterpiece-0.912
 favourite-0.902
 brand-0.816
 favorite-0.781
Token "
Token ID366
Feature activation+6.93e-01

Pos logit contributions
pron+0.066
 favourite+0.062
 masterpiece+0.062
 brand+0.055
 favorite+0.054
Neg logit contributions
crow-0.082
Bad-0.080
Leave-0.079
vious-0.074
eper-0.074
TokenCome
Token ID16773
Feature activation-8.37e+00

Pos logit contributions
pron+0.061
 favourite+0.055
 masterpiece+0.055
 usual+0.051
 favorite+0.049
Neg logit contributions
crow-0.044
Bad-0.042
eper-0.041
ases-0.041
Leave-0.041
Token with
Token ID351
Feature activation-1.90e+00

Pos logit contributions
crow+0.673
Bad+0.663
vious+0.648
Leave+0.644
ases+0.618
Neg logit contributions
pron-0.609
 favourite-0.583
 masterpiece-0.553
 brand-0.516
 favorite-0.509
Token me
Token ID502
Feature activation-2.71e+00

Pos logit contributions
crow+0.126
Leave+0.126
Bad+0.124
vious+0.117
ases+0.114
Neg logit contributions
pron-0.163
 favourite-0.155
 masterpiece-0.152
 brand-0.141
 favorite-0.140
Token share
Token ID2648
Feature activation-3.17e+00

Pos logit contributions
pron+0.094
 masterpiece+0.088
 favourite+0.087
 favorite+0.079
 brand+0.079
Neg logit contributions
crow-0.100
Leave-0.095
Bad-0.095
vious-0.093
eper-0.090
Token and
Token ID290
Feature activation+9.59e-02

Pos logit contributions
crow+0.279
Leave+0.274
Bad+0.264
vious+0.261
eper+0.252
Neg logit contributions
pron-0.206
 favourite-0.199
 masterpiece-0.190
 favorite-0.185
 brand-0.178
Token be
Token ID307
Feature activation+8.15e-01

Pos logit contributions
pron+0.008
 favourite+0.007
 masterpiece+0.007
 brand+0.007
 favorite+0.007
Neg logit contributions
crow-0.007
Bad-0.007
Leave-0.007
vious-0.006
Stop-0.006
Token nice
Token ID3621
Feature activation-3.97e-01

Pos logit contributions
pron+0.049
 favourite+0.048
 favorite+0.045
 masterpiece+0.044
 brand+0.043
Neg logit contributions
crow-0.077
Leave-0.071
Bad-0.070
vious-0.068
Hey-0.068
Token.
Token ID13
Feature activation-2.34e-02

Pos logit contributions
crow+0.036
Bad+0.035
Leave+0.035
Hey+0.033
Stop+0.032
Neg logit contributions
 favourite-0.024
pron-0.024
 masterpiece-0.023
 favorite-0.023
 brand-0.021
Token Fighting
Token ID19098
Feature activation-1.45e+01

Pos logit contributions
crow+0.001
Leave+0.001
Bad+0.001
vious+0.001
eper+0.001
Neg logit contributions
 favourite-0.002
pron-0.002
 Grand-0.002
 favorite-0.002
 masterpiece-0.002
Token is
Token ID318
Feature activation-1.53e+00

Pos logit contributions
crow+1.020
Bad+0.989
Leave+0.979
vious+0.913
eper+0.902
Neg logit contributions
pron-1.224
 favourite-1.168
 masterpiece-1.147
 favorite-1.070
 brand-1.063
Token bad
Token ID2089
Feature activation-2.20e+00

Pos logit contributions
crow+0.137
Leave+0.131
Bad+0.128
vious+0.124
eper+0.123
Neg logit contributions
pron-0.100
 favourite-0.095
 masterpiece-0.093
 favorite-0.087
 brand-0.086
Token.
Token ID13
Feature activation-5.12e-02

Pos logit contributions
Leave+0.199
Bad+0.197
crow+0.196
eper+0.182
vious+0.180
Neg logit contributions
 favourite-0.120
pron-0.120
 favorite-0.115
 masterpiece-0.111
 collection-0.100
Token It
Token ID632
Feature activation-4.50e-01

Pos logit contributions
crow+0.003
Leave+0.003
eper+0.003
Bad+0.003
vious+0.003
Neg logit contributions
 favourite-0.004
pron-0.004
 favorite-0.004
 masterpiece-0.004
 Grand-0.004
Token hurts
Token ID20406
Feature activation-1.80e+00

Pos logit contributions
crow+0.036
Leave+0.035
Bad+0.033
eper+0.032
ases+0.031
Neg logit contributions
pron-0.031
 favourite-0.030
 favorite-0.029
 masterpiece-0.029
 brand-0.027
Token talk
Token ID1561
Feature activation-5.14e+00

Pos logit contributions
pron+0.094
 favourite+0.088
 masterpiece+0.088
 brand+0.079
 favorite+0.079
Neg logit contributions
crow-0.095
Bad-0.092
Leave-0.091
vious-0.087
eper-0.086
Token calm
Token ID9480
Feature activation-3.31e+00

Pos logit contributions
crow+0.508
Bad+0.498
Leave+0.494
vious+0.468
eper+0.467
Neg logit contributions
pron-0.284
 favourite-0.265
 masterpiece-0.257
 brand-0.227
 favorite-0.226
Token and
Token ID290
Feature activation+3.97e-02

Pos logit contributions
Bad+0.272
Leave+0.272
crow+0.265
eper+0.248
vious+0.247
Neg logit contributions
 favourite-0.217
pron-0.212
 favorite-0.204
 masterpiece-0.203
 collection-0.180
Token polite
Token ID23507
Feature activation-4.04e+00

Pos logit contributions
pron+0.003
 favourite+0.003
 masterpiece+0.003
 brand+0.003
 favorite+0.003
Neg logit contributions
crow-0.003
Bad-0.003
Leave-0.003
vious-0.003
eper-0.003
Token.
Token ID13
Feature activation-2.53e-02

Pos logit contributions
Leave+0.364
Bad+0.357
crow+0.354
eper+0.328
vious+0.324
Neg logit contributions
 favourite-0.239
pron-0.237
 favorite-0.225
 masterpiece-0.222
 usual-0.199
Token Fighting
Token ID19098
Feature activation-1.45e+01

Pos logit contributions
crow+0.002
Bad+0.002
Leave+0.001
eper+0.001
vious+0.001
Neg logit contributions
 favourite-0.002
pron-0.002
 favorite-0.002
 masterpiece-0.002
 brand-0.002
Token over
Token ID625
Feature activation-2.15e+00

Pos logit contributions
crow+1.023
Bad+0.993
Leave+0.984
vious+0.912
eper+0.905
Neg logit contributions
pron-1.219
 favourite-1.164
 masterpiece-1.143
 favorite-1.068
 brand-1.057
Token shapes
Token ID15268
Feature activation-2.06e+00

Pos logit contributions
crow+0.154
Leave+0.153
Bad+0.150
vious+0.140
eper+0.138
Neg logit contributions
pron-0.168
 favourite-0.162
 masterpiece-0.160
 favorite-0.151
 brand-0.145
Token is
Token ID318
Feature activation-1.46e+00

Pos logit contributions
crow+0.157
Bad+0.155
Leave+0.153
eper+0.142
vious+0.140
Neg logit contributions
pron-0.157
 favourite-0.149
 masterpiece-0.147
 favorite-0.136
 brand-0.133
Token not
Token ID407
Feature activation+1.93e+00

Pos logit contributions
crow+0.126
Bad+0.123
Leave+0.122
vious+0.115
eper+0.115
Neg logit contributions
pron-0.099
 favourite-0.093
 masterpiece-0.092
 brand-0.082
 favorite-0.081
Token fun
Token ID1257
Feature activation+8.89e-01

Pos logit contributions
pron+0.134
 favourite+0.127
 masterpiece+0.125
 brand+0.113
 favorite+0.113
Neg logit contributions
crow-0.164
Bad-0.159
Leave-0.158
vious-0.148
eper-0.148
Token enough
Token ID1576
Feature activation-3.32e-01

Pos logit contributions
crow+0.319
Bad+0.311
Leave+0.301
vious+0.290
eper+0.283
Neg logit contributions
pron-0.326
 masterpiece-0.306
 favourite-0.299
 brand-0.273
 favorite-0.262
Token money
Token ID1637
Feature activation-6.51e-01

Pos logit contributions
crow+0.028
Bad+0.027
Leave+0.026
eper+0.025
ases+0.025
Neg logit contributions
pron-0.024
 masterpiece-0.022
 favourite-0.021
 brand-0.019
 favorite-0.018
Token for
Token ID329
Feature activation+5.34e+00

Pos logit contributions
crow+0.050
Bad+0.049
Leave+0.047
eper+0.046
vious+0.045
Neg logit contributions
pron-0.049
 masterpiece-0.047
 favourite-0.046
 brand-0.041
 favorite-0.040
Token an
Token ID281
Feature activation+2.54e+00

Pos logit contributions
pron+0.449
 favourite+0.426
 masterpiece+0.424
 brand+0.385
 favorite+0.382
Neg logit contributions
crow-0.370
Bad-0.369
Leave-0.358
eper-0.332
Stop-0.329
Token adventurous
Token ID39770
Feature activation+2.85e-01

Pos logit contributions
pron+0.189
 favourite+0.174
 masterpiece+0.174
 brand+0.158
 favorite+0.153
Neg logit contributions
crow-0.203
Bad-0.195
Leave-0.193
vious-0.185
eper-0.184
Token holiday
Token ID9912
Feature activation+8.87e+00

Pos logit contributions
pron+0.018
 favourite+0.017
 masterpiece+0.017
 brand+0.015
 favorite+0.015
Neg logit contributions
crow-0.026
Bad-0.024
Leave-0.024
vious-0.023
eper-0.023
Token!"
Token ID2474
Feature activation+2.98e+00

Pos logit contributions
pron+0.763
 masterpiece+0.721
 favourite+0.707
 brand+0.661
 favorite+0.622
Neg logit contributions
crow-0.607
Bad-0.546
Leave-0.529
eper-0.523
vious-0.521
Token
Token ID198
Feature activation+4.94e-01

Pos logit contributions
pron+0.219
 favourite+0.206
 masterpiece+0.205
 brand+0.186
 favorite+0.182
Neg logit contributions
crow-0.241
Bad-0.235
Leave-0.231
vious-0.218
eper-0.217
Token
Token ID198
Feature activation+4.08e-01

Pos logit contributions
pron+0.038
 favourite+0.035
 masterpiece+0.035
 brand+0.032
 favorite+0.031
Neg logit contributions
crow-0.039
Bad-0.038
Leave-0.037
vious-0.036
eper-0.035
TokenDa
Token ID26531
Feature activation+7.15e-01

Pos logit contributions
pron+0.034
 favourite+0.031
 masterpiece+0.031
 brand+0.027
 usual+0.027
Neg logit contributions
crow-0.029
vious-0.028
Bad-0.028
Leave-0.027
ases-0.027
Tokenisy
Token ID13560
Feature activation+7.65e+00

Pos logit contributions
pron+0.039
 favourite+0.035
 masterpiece+0.034
 brand+0.031
 favorite+0.029
Neg logit contributions
crow-0.072
Bad-0.070
Leave-0.069
vious-0.067
eper-0.066
Token thoughtful
Token ID22677
Feature activation+1.08e+00

Pos logit contributions
 masterpiece+0.033
pron+0.032
 favourite+0.031
icol+0.030
 brand+0.029
Neg logit contributions
Bad-0.027
crow-0.027
Leave-0.026
vious-0.025
eper-0.024
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
pron+0.083
 favourite+0.078
 masterpiece+0.078
 brand+0.071
 favorite+0.069
Neg logit contributions
crow-0.084
Bad-0.082
Leave-0.080
vious-0.076
eper-0.075
Token
Token ID198
Feature activation+7.69e-01

Pos logit contributions
pron+0.012
 masterpiece+0.011
 favourite+0.011
 brand+0.010
 collection+0.010
Neg logit contributions
crow-0.007
Leave-0.006
Bad-0.006
Stop-0.006
Hey-0.005
Token
Token ID198
Feature activation+7.30e-01

Pos logit contributions
pron+0.071
 masterpiece+0.069
 favourite+0.067
 brand+0.063
 collection+0.062
Neg logit contributions
crow-0.048
Bad-0.044
Leave-0.044
Stop-0.041
Rex-0.040
TokenSu
Token ID5606
Feature activation+6.34e+00

Pos logit contributions
pron+0.066
 masterpiece+0.063
 favourite+0.063
 brand+0.058
 favorite+0.057
Neg logit contributions
crow-0.047
Bad-0.046
Leave-0.045
Stop-0.042
vious-0.041
Tokenzy
Token ID7357
Feature activation+8.97e+00

Pos logit contributions
pron+0.401
 favourite+0.389
 masterpiece+0.361
 brand+0.354
 favorite+0.333
Neg logit contributions
crow-0.592
vious-0.552
Leave-0.550
Bad-0.545
Stop-0.527
Token knew
Token ID2993
Feature activation+6.47e-01

Pos logit contributions
pron+0.744
 favourite+0.691
 masterpiece+0.691
 brand+0.657
 favorite+0.610
Neg logit contributions
crow-0.645
Bad-0.617
Leave-0.611
vious-0.593
eper-0.580
Token that
Token ID326
Feature activation+2.98e+00

Pos logit contributions
pron+0.056
 masterpiece+0.054
 favourite+0.050
icol+0.050
ouse+0.047
Neg logit contributions
crow-0.043
Bad-0.041
eper-0.040
Leave-0.039
 hunters-0.038
Token she
Token ID673
Feature activation+5.18e+00

Pos logit contributions
pron+0.215
 masterpiece+0.208
 favourite+0.201
 brand+0.190
ail+0.189
Neg logit contributions
crow-0.236
Bad-0.229
Leave-0.219
Stop-0.211
eper-0.206
Token could
Token ID714
Feature activation-6.81e-01

Pos logit contributions
pron+0.372
 masterpiece+0.345
 favourite+0.336
 brand+0.316
 porch+0.298
Neg logit contributions
crow-0.422
Bad-0.411
vious-0.401
Leave-0.395
eper-0.387
Token trust
Token ID3774
Feature activation-2.31e+00

Pos logit contributions
crow+0.046
Leave+0.045
Bad+0.045
ases+0.043
eper+0.042
Neg logit contributions
pron-0.056
 masterpiece-0.052
 favourite-0.051
 brand-0.050
yt-0.048
Token who
Token ID508
Feature activation-1.92e+00

Pos logit contributions
pron+0.248
 favourite+0.237
 masterpiece+0.236
 brand+0.217
 favorite+0.213
Neg logit contributions
crow-0.195
Bad-0.189
Leave-0.185
eper-0.172
vious-0.172
Token wanted
Token ID2227
Feature activation-9.32e-01

Pos logit contributions
crow+0.180
Bad+0.177
Leave+0.173
vious+0.164
Stop+0.164
Neg logit contributions
pron-0.117
 masterpiece-0.110
 favourite-0.107
 brand-0.095
 favorite-0.090
Token to
Token ID284
Feature activation+1.88e+00

Pos logit contributions
crow+0.074
Bad+0.072
Leave+0.069
 hunters+0.068
Stop+0.067
Neg logit contributions
pron-0.069
 masterpiece-0.063
 favourite-0.059
ail-0.056
yt-0.055
Token have
Token ID423
Feature activation+1.55e+00

Pos logit contributions
pron+0.149
 favourite+0.139
 masterpiece+0.138
 brand+0.129
 favorite+0.123
Neg logit contributions
crow-0.136
Leave-0.130
Bad-0.128
ases-0.123
Stop-0.120
Token a
Token ID257
Feature activation+2.73e-01

Pos logit contributions
pron+0.128
 masterpiece+0.119
 favourite+0.114
ail+0.112
yt+0.105
Neg logit contributions
Bad-0.106
crow-0.104
Leave-0.104
vious-0.099
 hunters-0.098
Token picnic
Token ID35715
Feature activation+8.39e+00

Pos logit contributions
pron+0.015
 masterpiece+0.014
ilda+0.013
ail+0.013
onna+0.013
Neg logit contributions
 bully-0.022
Bad-0.022
crow-0.022
Leave-0.020
eper-0.020
Token.
Token ID13
Feature activation+3.00e-01

Pos logit contributions
pron+0.720
 masterpiece+0.715
 favourite+0.674
 brand+0.658
icol+0.629
Neg logit contributions
crow-0.530
Bad-0.475
eper-0.474
 hunters-0.469
ases-0.460
Token They
Token ID1119
Feature activation+2.14e-01

Pos logit contributions
pron+0.026
 masterpiece+0.025
 favourite+0.024
 brand+0.023
ail+0.021
Neg logit contributions
crow-0.021
Bad-0.020
Leave-0.019
Stop-0.018
vious-0.018
Token packed
Token ID11856
Feature activation+3.66e+00

Pos logit contributions
 masterpiece+0.017
pron+0.017
 brand+0.015
icol+0.015
 favourite+0.015
Neg logit contributions
crow-0.015
eper-0.015
Bad-0.015
Leave-0.014
Hey-0.014
Token a
Token ID257
Feature activation+2.89e-01

Pos logit contributions
pron+0.349
 masterpiece+0.332
ail+0.307
onna+0.305
ilda+0.305
Neg logit contributions
Bad-0.173
crow-0.166
Hey-0.158
ases-0.156
 hunters-0.155
Token basket
Token ID7988
Feature activation+6.54e+00

Pos logit contributions
 masterpiece+0.017
ilda+0.017
pron+0.017
 couldn+0.016
ail+0.015
Neg logit contributions
Bad-0.022
crow-0.022
 hunters-0.020
Rex-0.020
eper-0.020
Token They
Token ID1119
Feature activation-7.95e-02

Pos logit contributions
crow+0.017
Bad+0.017
Leave+0.016
Stop+0.015
ases+0.015
Neg logit contributions
pron-0.021
 masterpiece-0.019
 favourite-0.019
 brand-0.018
 collection-0.017
Token had
Token ID550
Feature activation+4.52e+00

Pos logit contributions
crow+0.006
Bad+0.006
Leave+0.006
vious+0.006
eper+0.006
Neg logit contributions
pron-0.006
 favourite-0.005
 masterpiece-0.005
 brand-0.005
 favorite-0.005
Token ruined
Token ID20484
Feature activation+9.30e-01

Pos logit contributions
pron+0.374
 masterpiece+0.336
 favourite+0.333
 brand+0.303
ail+0.296
Neg logit contributions
Bad-0.344
Leave-0.331
crow-0.327
vious-0.314
ases-0.312
Token the
Token ID262
Feature activation-1.63e+00

Pos logit contributions
pron+0.081
 favourite+0.075
 masterpiece+0.073
 brand+0.067
 favorite+0.065
Neg logit contributions
Bad-0.065
crow-0.064
Leave-0.060
Stop-0.058
ases-0.058
Token cool
Token ID3608
Feature activation+3.77e+00

Pos logit contributions
Bad+0.155
crow+0.152
Leave+0.151
Stop+0.150
vious+0.149
Neg logit contributions
pron-0.081
 masterpiece-0.073
onna-0.072
 favourite-0.071
 brand-0.065
Token skirt
Token ID23967
Feature activation+8.76e+00

Pos logit contributions
pron+0.195
 favourite+0.182
 masterpiece+0.172
 brand+0.161
 usual+0.158
Neg logit contributions
crow-0.370
vious-0.344
Stop-0.340
Leave-0.340
Bad-0.334
Token.
Token ID13
Feature activation-2.46e-01

Pos logit contributions
pron+0.762
 favourite+0.722
 masterpiece+0.704
 brand+0.652
 favorite+0.635
Neg logit contributions
crow-0.586
Bad-0.558
Leave-0.545
vious-0.528
eper-0.519
Token
Token ID198
Feature activation+1.74e-01

Pos logit contributions
crow+0.018
Bad+0.018
Leave+0.017
Stop+0.016
vious+0.016
Neg logit contributions
pron-0.020
 masterpiece-0.019
 favourite-0.019
 brand-0.017
 favorite-0.017
Token
Token ID198
Feature activation+1.59e-01

Pos logit contributions
pron+0.015
 favourite+0.014
 masterpiece+0.014
 brand+0.013
 favorite+0.012
Neg logit contributions
crow-0.012
Bad-0.012
Leave-0.012
Stop-0.011
ases-0.011
TokenTheir
Token ID14574
Feature activation-1.72e+00

Pos logit contributions
pron+0.013
 favourite+0.012
 masterpiece+0.012
 brand+0.011
 favorite+0.011
Neg logit contributions
crow-0.011
vious-0.011
Leave-0.010
Bad-0.010
ases-0.010
Token mom
Token ID1995
Feature activation+4.92e+00

Pos logit contributions
Bad+0.146
Leave+0.143
 bully+0.142
crow+0.139
ases+0.139
Neg logit contributions
pron-0.115
 masterpiece-0.089
 favourite-0.089
onna-0.086
 brand-0.086
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
Leave+0.704
Bad+0.698
crow+0.694
Stop+0.660
vious+0.659
Neg logit contributions
pron-0.500
 favourite-0.493
 masterpiece-0.490
 usual-0.445
 favorite-0.444
Token The
Token ID383
Feature activation-2.06e-01

Pos logit contributions
Leave+0.012
Bad+0.012
crow+0.012
eper+0.012
Stop+0.011
Neg logit contributions
 favourite-0.009
pron-0.009
 masterpiece-0.008
 favorite-0.008
 brand-0.008
Token animals
Token ID4695
Feature activation-1.01e+01

Pos logit contributions
crow+0.018
ases+0.017
Leave+0.017
vious+0.016
Bad+0.016
Neg logit contributions
pron-0.015
 favourite-0.013
 masterpiece-0.013
 favorite-0.013
 porch-0.012
Token and
Token ID290
Feature activation+2.51e-01

Pos logit contributions
crow+0.936
Bad+0.927
Leave+0.921
ases+0.891
vious+0.879
Neg logit contributions
pron-0.554
 favourite-0.521
 masterpiece-0.502
 couldn-0.457
 favorite-0.453
Token the
Token ID262
Feature activation-1.68e+00

Pos logit contributions
 favourite+0.017
pron+0.017
 favorite+0.016
 usual+0.016
 masterpiece+0.016
Neg logit contributions
Leave-0.019
crow-0.019
Bad-0.018
vious-0.018
ases-0.018
Token long
Token ID890
Feature activation+8.40e+00

Pos logit contributions
crow+0.150
ases+0.139
Leave+0.138
vious+0.137
Bad+0.135
Neg logit contributions
pron-0.118
 favourite-0.109
 masterpiece-0.104
 favorite-0.102
 brand-0.097
Token snake
Token ID17522
Feature activation-5.76e+00

Pos logit contributions
pron+0.694
 favourite+0.634
 masterpiece+0.615
 favorite+0.580
 collection+0.563
Neg logit contributions
crow-0.613
Bad-0.602
Leave-0.601
ases-0.575
vious-0.574
Token protected
Token ID6861
Feature activation-4.29e+00

Pos logit contributions
crow+0.505
Bad+0.494
Leave+0.487
vious+0.461
eper+0.459
Neg logit contributions
pron-0.381
 favourite-0.359
 masterpiece-0.354
 brand-0.318
 favorite-0.313
Token the
Token ID262
Feature activation-1.69e+00

Pos logit contributions
Leave+0.354
vious+0.341
Bad+0.340
crow+0.339
eper+0.316
Neg logit contributions
 favourite-0.288
 masterpiece-0.276
 usual-0.273
 favorite-0.266
pron-0.264
Token gum
Token ID27142
Feature activation+1.18e+00

Pos logit contributions
crow+0.145
Leave+0.135
ases+0.135
Bad+0.132
eper+0.131
Neg logit contributions
pron-0.125
 favourite-0.114
 masterpiece-0.111
 favorite-0.105
 brand-0.103
Token tree
Token ID5509
Feature activation-8.70e-01

Pos logit contributions
pron+0.082
 favourite+0.079
 masterpiece+0.078
 favorite+0.070
 brand+0.070
Neg logit contributions
crow-0.098
Bad-0.097
Leave-0.096
Stop-0.090
vious-0.089
Token Whenever
Token ID21326
Feature activation-3.30e+00

Pos logit contributions
crow+0.018
Bad+0.017
Leave+0.017
vious+0.016
Stop+0.016
Neg logit contributions
pron-0.021
 masterpiece-0.019
 favourite-0.019
 brand-0.018
 favorite-0.017
Token they
Token ID484
Feature activation+5.02e+00

Pos logit contributions
crow+0.344
Bad+0.340
Leave+0.338
vious+0.328
ases+0.325
Neg logit contributions
 favourite-0.151
pron-0.149
 masterpiece-0.142
 favorite-0.125
 usual-0.122
Token did
Token ID750
Feature activation-2.56e+00

Pos logit contributions
pron+0.309
 favourite+0.295
 masterpiece+0.287
 favorite+0.257
 brand+0.256
Neg logit contributions
crow-0.458
Bad-0.452
Leave-0.444
Stop-0.417
eper-0.416
Token,
Token ID11
Feature activation-1.35e+00

Pos logit contributions
crow+0.213
Bad+0.208
Leave+0.205
vious+0.193
eper+0.192
Neg logit contributions
pron-0.181
 favourite-0.171
 masterpiece-0.169
 brand-0.153
 favorite-0.150
Token they
Token ID484
Feature activation+4.98e+00

Pos logit contributions
crow+0.136
Bad+0.134
Leave+0.132
vious+0.126
eper+0.126
Neg logit contributions
pron-0.072
 favourite-0.067
 masterpiece-0.066
 brand-0.057
 favorite-0.057
Token were
Token ID547
Feature activation+1.10e-01

Pos logit contributions
pron+0.270
 masterpiece+0.243
 favourite+0.243
 brand+0.213
 favorite+0.201
Neg logit contributions
crow-0.504
Bad-0.489
Leave-0.483
eper-0.470
vious-0.468
Token always
Token ID1464
Feature activation+3.10e+00

Pos logit contributions
pron+0.008
 favourite+0.008
 masterpiece+0.007
 brand+0.007
 favorite+0.007
Neg logit contributions
crow-0.009
Bad-0.009
Leave-0.009
Stop-0.008
vious-0.008
Token happy
Token ID3772
Feature activation-1.33e+00

Pos logit contributions
pron+0.212
 favourite+0.204
 masterpiece+0.199
 brand+0.182
 favorite+0.180
Neg logit contributions
crow-0.271
Bad-0.258
Leave-0.256
Stop-0.245
vious-0.243
Token because
Token ID780
Feature activation+1.96e+00

Pos logit contributions
crow+0.114
Bad+0.112
Leave+0.110
vious+0.104
eper+0.103
Neg logit contributions
pron-0.091
 favourite-0.086
 masterpiece-0.085
 brand-0.077
 favorite-0.076
Token they
Token ID484
Feature activation+4.97e+00

Pos logit contributions
pron+0.106
 masterpiece+0.092
 favourite+0.091
 brand+0.080
 favorite+0.074
Neg logit contributions
crow-0.202
Bad-0.198
Leave-0.194
eper-0.186
vious-0.184
Token were
Token ID547
Feature activation+9.33e-02

Pos logit contributions
pron+0.319
 favourite+0.295
 masterpiece+0.293
 brand+0.261
 favorite+0.254
Neg logit contributions
crow-0.450
Bad-0.443
Leave-0.434
vious-0.417
eper-0.415
Token bird
Token ID6512
Feature activation-4.76e+00

Pos logit contributions
crow+0.104
Bad+0.100
Leave+0.099
eper+0.093
ases+0.092
Neg logit contributions
pron-0.117
 favourite-0.112
 masterpiece-0.111
 favorite-0.102
 brand-0.101
Tokenie
Token ID494
Feature activation+4.22e+00

Pos logit contributions
Bad+0.459
Leave+0.456
crow+0.450
Stop+0.439
Hey+0.424
Neg logit contributions
pron-0.270
 favourite-0.257
 masterpiece-0.249
 favorite-0.226
 brand-0.222
Token!
Token ID0
Feature activation+2.87e+00

Pos logit contributions
pron+0.303
 favourite+0.290
 masterpiece+0.284
 favorite+0.259
 brand+0.259
Neg logit contributions
Bad-0.340
crow-0.340
Leave-0.335
Stop-0.317
eper-0.312
Token The
Token ID383
Feature activation-3.06e-03

Pos logit contributions
pron+0.237
 favourite+0.226
 masterpiece+0.223
 brand+0.205
 favorite+0.203
Neg logit contributions
crow-0.207
Bad-0.202
Leave-0.198
vious-0.185
eper-0.185
Token bird
Token ID6512
Feature activation-4.79e+00

Pos logit contributions
crow+0.000
Bad+0.000
Leave+0.000
vious+0.000
eper+0.000
Neg logit contributions
pron-0.000
 favourite-0.000
 masterpiece-0.000
 brand-0.000
 favorite-0.000
Tokenie
Token ID494
Feature activation+4.21e+00

Pos logit contributions
crow+0.451
Bad+0.448
Leave+0.443
Stop+0.420
ases+0.419
Neg logit contributions
pron-0.283
 favourite-0.258
 masterpiece-0.258
 brand-0.225
 favorite-0.224
Token felt
Token ID2936
Feature activation+4.72e+00

Pos logit contributions
pron+0.252
 favourite+0.237
 masterpiece+0.231
 favorite+0.206
 brand+0.201
Neg logit contributions
crow-0.387
Bad-0.383
Leave-0.380
ases-0.363
vious-0.359
Token very
Token ID845
Feature activation-9.94e-01

Pos logit contributions
 favourite+0.298
 brand+0.287
 favorite+0.268
pron+0.252
 masterpiece+0.237
Neg logit contributions
ases-0.396
crow-0.394
eper-0.387
Bad-0.377
Stop-0.372
Token scared
Token ID12008
Feature activation-8.70e+00

Pos logit contributions
crow+0.072
Bad+0.071
Leave+0.069
eper+0.066
Stop+0.065
Neg logit contributions
 favourite-0.078
pron-0.078
 masterpiece-0.074
 favorite-0.071
 brand-0.070
Token and
Token ID290
Feature activation+3.45e-01

Pos logit contributions
Bad+0.791
crow+0.787
Leave+0.759
eper+0.743
ases+0.729
Neg logit contributions
 favourite-0.504
pron-0.494
 masterpiece-0.464
 favorite-0.456
 brand-0.453
Token didn
Token ID1422
Feature activation-7.32e-01

Pos logit contributions
pron+0.021
 favourite+0.020
 masterpiece+0.019
 favorite+0.018
 brand+0.018
Neg logit contributions
crow-0.030
Bad-0.030
Leave-0.029
ases-0.029
Stop-0.028
Token jump
Token ID4391
Feature activation-9.00e-01

Pos logit contributions
pron+0.145
 favourite+0.137
 masterpiece+0.135
 brand+0.123
 favorite+0.123
Neg logit contributions
crow-0.134
Leave-0.131
Bad-0.130
vious-0.120
eper-0.120
Token into
Token ID656
Feature activation+7.72e-01

Pos logit contributions
crow+0.065
Bad+0.063
Leave+0.062
vious+0.058
Stop+0.058
Neg logit contributions
pron-0.074
 favourite-0.069
 masterpiece-0.069
 brand-0.063
 favorite-0.062
Token the
Token ID262
Feature activation-1.63e+00

Pos logit contributions
pron+0.065
 favourite+0.061
 masterpiece+0.061
 brand+0.055
 favorite+0.055
Neg logit contributions
crow-0.055
Bad-0.054
Leave-0.052
vious-0.049
eper-0.049
Token nest
Token ID16343
Feature activation+4.43e+00

Pos logit contributions
crow+0.133
Bad+0.129
Leave+0.126
vious+0.120
Stop+0.118
Neg logit contributions
pron-0.123
 favourite-0.114
 masterpiece-0.112
 brand-0.102
 favorite-0.100
Token.
Token ID13
Feature activation+7.68e-02

Pos logit contributions
pron+0.366
 favourite+0.345
 masterpiece+0.342
 brand+0.313
 favorite+0.307
Neg logit contributions
crow-0.316
Bad-0.297
Leave-0.291
vious-0.283
eper-0.280
Token
Token ID198
Feature activation+7.39e-01

Pos logit contributions
pron+0.006
 masterpiece+0.006
 favourite+0.006
 brand+0.005
 favorite+0.005
Neg logit contributions
crow-0.006
Bad-0.005
Leave-0.005
vious-0.005
Stop-0.005
Token
Token ID198
Feature activation+7.12e-01

Pos logit contributions
pron+0.062
 masterpiece+0.059
 favourite+0.059
 brand+0.054
 favorite+0.053
Neg logit contributions
crow-0.052
Bad-0.050
Leave-0.049
Stop-0.046
eper-0.045
TokenThe
Token ID464
Feature activation-1.16e+00

Pos logit contributions
pron+0.053
 favourite+0.046
 masterpiece+0.044
 brand+0.041
 usual+0.039
Neg logit contributions
crow-0.060
ases-0.057
vious-0.056
eper-0.055
Bad-0.054
Token bunny
Token ID44915
Feature activation-1.40e+00

Pos logit contributions
crow+0.089
Bad+0.087
Leave+0.085
vious+0.080
eper+0.080
Neg logit contributions
pron-0.092
 favourite-0.087
 masterpiece-0.086
 brand-0.079
 favorite-0.078
Token was
Token ID373
Feature activation+1.64e+00

Pos logit contributions
crow+0.116
Bad+0.112
Leave+0.110
vious+0.105
eper+0.105
Neg logit contributions
pron-0.100
 favourite-0.092
 masterpiece-0.092
 brand-0.085
 usual-0.082
Token so
Token ID523
Feature activation+2.85e-01

Pos logit contributions
pron+0.126
 masterpiece+0.118
 favourite+0.117
 brand+0.105
 favorite+0.104
Neg logit contributions
crow-0.126
Bad-0.124
Leave-0.122
vious-0.115
eper-0.115
Token friends
Token ID2460
Feature activation-3.85e+00

Pos logit contributions
crow+0.108
Bad+0.103
Leave+0.102
vious+0.097
eper+0.096
Neg logit contributions
pron-0.116
 masterpiece-0.106
 favourite-0.106
 brand-0.097
 favorite-0.094
Token there
Token ID612
Feature activation-2.15e+00

Pos logit contributions
crow+0.276
Bad+0.269
Leave+0.264
vious+0.248
eper+0.247
Neg logit contributions
pron-0.313
 masterpiece-0.294
 favourite-0.290
 brand-0.263
 favorite-0.260
Token.
Token ID13
Feature activation-1.05e-01

Pos logit contributions
crow+0.169
Bad+0.165
Leave+0.160
eper+0.152
vious+0.152
Neg logit contributions
pron-0.161
 masterpiece-0.150
 favourite-0.148
 brand-0.135
 favorite-0.131
Token From
Token ID3574
Feature activation+2.84e+00

Pos logit contributions
crow+0.008
Bad+0.008
Leave+0.008
vious+0.008
eper+0.007
Neg logit contributions
pron-0.008
 masterpiece-0.007
 favourite-0.007
 brand-0.007
 favorite-0.007
Token then
Token ID788
Feature activation+3.08e+00

Pos logit contributions
pron+0.208
 masterpiece+0.194
 favourite+0.192
 brand+0.171
 favorite+0.168
Neg logit contributions
crow-0.235
Bad-0.232
Leave-0.223
eper-0.214
Stop-0.210
Token on
Token ID319
Feature activation+1.30e+00

Pos logit contributions
pron+0.220
 favourite+0.210
 masterpiece+0.200
 favorite+0.184
 brand+0.182
Neg logit contributions
crow-0.247
Bad-0.246
Leave-0.237
vious-0.231
eper-0.225
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
pron+0.101
 masterpiece+0.095
 favourite+0.094
 brand+0.086
 favorite+0.084
Neg logit contributions
crow-0.101
Bad-0.098
Leave-0.096
eper-0.090
Stop-0.089
Token Benny
Token ID44275
Feature activation+2.97e+00

Pos logit contributions
crow+0.099
Bad+0.097
Leave+0.095
vious+0.091
eper+0.091
Neg logit contributions
pron-0.069
 favourite-0.065
 masterpiece-0.064
 brand-0.057
 favorite-0.056
Token didn
Token ID1422
Feature activation-6.48e-01

Pos logit contributions
pron+0.186
 favourite+0.175
 masterpiece+0.172
 favorite+0.152
 brand+0.152
Neg logit contributions
crow-0.270
Bad-0.265
Leave-0.261
vious-0.247
ases-0.246
Token't
Token ID470
Feature activation-1.30e+00

Pos logit contributions
crow+0.046
Bad+0.045
Leave+0.044
vious+0.041
Stop+0.041
Neg logit contributions
pron-0.054
 favourite-0.051
 masterpiece-0.051
 brand-0.047
 favorite-0.046
Token mind
Token ID2000
Feature activation-1.87e+00

Pos logit contributions
Bad+0.093
crow+0.092
Leave+0.089
eper+0.086
ases+0.085
Neg logit contributions
pron-0.102
 favourite-0.099
 masterpiece-0.097
 favorite-0.090
 usual-0.088
Token watch
Token ID2342
Feature activation+9.93e-01

Pos logit contributions
crow+0.300
Bad+0.293
Leave+0.289
eper+0.272
Stop+0.269
Neg logit contributions
pron-0.307
 favourite-0.291
 masterpiece-0.287
 brand-0.262
 favorite-0.258
Token the
Token ID262
Feature activation-1.59e+00

Pos logit contributions
pron+0.078
 favourite+0.074
 masterpiece+0.073
 brand+0.067
 favorite+0.066
Neg logit contributions
crow-0.075
Bad-0.073
Leave-0.072
vious-0.068
eper-0.067
Token film
Token ID2646
Feature activation-1.56e+00

Pos logit contributions
crow+0.142
Leave+0.135
Bad+0.131
vious+0.128
eper+0.127
Neg logit contributions
pron-0.110
 favourite-0.106
 masterpiece-0.103
 favorite-0.095
 brand-0.091
Token tomorrow
Token ID9439
Feature activation+3.34e-01

Pos logit contributions
crow+0.124
Bad+0.121
Leave+0.119
vious+0.112
Stop+0.111
Neg logit contributions
pron-0.117
 favourite-0.111
 masterpiece-0.110
 brand-0.100
 favorite-0.099
Token.
Token ID13
Feature activation-2.17e-02

Pos logit contributions
pron+0.026
 favourite+0.025
 masterpiece+0.025
 brand+0.023
 favorite+0.022
Neg logit contributions
crow-0.025
Bad-0.024
Leave-0.024
vious-0.022
eper-0.022
Token Sara
Token ID24799
Feature activation+2.09e+00

Pos logit contributions
crow+0.001
Bad+0.001
Leave+0.001
vious+0.001
eper+0.001
Neg logit contributions
pron-0.002
 favourite-0.002
 masterpiece-0.002
 brand-0.002
 favorite-0.002
Token cal
Token ID2386
Feature activation-7.26e+00

Pos logit contributions
pron+0.141
 favourite+0.137
 masterpiece+0.134
 favorite+0.128
 brand+0.118
Neg logit contributions
crow-0.177
Bad-0.168
Leave-0.167
Stop-0.151
eper-0.150
Tokenms
Token ID907
Feature activation-9.11e+00

Pos logit contributions
Bad+0.350
Leave+0.341
 hunters+0.324
crow+0.322
Stop+0.307
Neg logit contributions
pron-0.652
 favourite-0.637
 complexion-0.620
 masterpiece-0.614
 favorite-0.612
Token down
Token ID866
Feature activation-2.09e-01

Pos logit contributions
crow+0.748
Bad+0.743
Leave+0.729
vious+0.693
Stop+0.670
Neg logit contributions
pron-0.633
 favourite-0.599
 masterpiece-0.583
 favorite-0.545
 usual-0.536
Token and
Token ID290
Feature activation+2.07e-01

Pos logit contributions
crow+0.018
Bad+0.018
Leave+0.018
Stop+0.017
vious+0.017
Neg logit contributions
pron-0.013
 favourite-0.012
 masterpiece-0.012
 favorite-0.011
 brand-0.011
Token says
Token ID1139
Feature activation-1.89e+00

Pos logit contributions
pron+0.016
 favourite+0.015
 masterpiece+0.015
 brand+0.014
 favorite+0.014
Neg logit contributions
crow-0.016
Bad-0.015
Leave-0.015
vious-0.014
eper-0.014
Token saw
Token ID2497
Feature activation-4.06e-01

Pos logit contributions
pron+0.012
 favourite+0.011
 masterpiece+0.011
 favorite+0.010
 brand+0.010
Neg logit contributions
crow-0.012
Bad-0.012
Leave-0.012
Stop-0.011
vious-0.011
Token some
Token ID617
Feature activation+9.63e-01

Pos logit contributions
crow+0.032
Bad+0.031
Leave+0.030
vious+0.029
eper+0.029
Neg logit contributions
pron-0.032
 masterpiece-0.029
 favourite-0.029
 brand-0.026
 favorite-0.026
Token children
Token ID1751
Feature activation-7.55e+00

Pos logit contributions
pron+0.083
 favourite+0.080
 masterpiece+0.079
 brand+0.074
 favorite+0.072
Neg logit contributions
crow-0.064
Bad-0.063
Leave-0.061
eper-0.057
ases-0.057
Token playing
Token ID2712
Feature activation-6.89e-01

Pos logit contributions
crow+0.638
Bad+0.624
Leave+0.614
vious+0.580
eper+0.577
Neg logit contributions
pron-0.525
 favourite-0.495
 masterpiece-0.489
 brand-0.441
 favorite-0.434
Token on
Token ID319
Feature activation+1.29e+00

Pos logit contributions
crow+0.056
Bad+0.055
Leave+0.054
vious+0.052
eper+0.052
Neg logit contributions
pron-0.048
 favourite-0.048
 masterpiece-0.045
 favorite-0.042
 brand-0.042
Token the
Token ID262
Feature activation-1.42e+00

Pos logit contributions
pron+0.108
 favourite+0.103
 masterpiece+0.102
 brand+0.094
 favorite+0.092
Neg logit contributions
crow-0.092
Bad-0.089
Leave-0.088
vious-0.082
Stop-0.081
Token swings
Token ID26728
Feature activation+2.44e+00

Pos logit contributions
crow+0.112
Bad+0.110
Leave+0.108
Stop+0.102
vious+0.100
Neg logit contributions
pron-0.107
 masterpiece-0.098
 favourite-0.097
 brand-0.090
 collection-0.087
Token.
Token ID13
Feature activation-7.41e-02

Pos logit contributions
pron+0.175
 favourite+0.167
 masterpiece+0.164
 brand+0.148
 favorite+0.148
Neg logit contributions
crow-0.196
Bad-0.194
Leave-0.191
Stop-0.179
vious-0.179
Token They
Token ID1119
Feature activation+1.14e-01

Pos logit contributions
crow+0.006
Bad+0.005
Leave+0.005
vious+0.005
Stop+0.005
Neg logit contributions
pron-0.006
 masterpiece-0.006
 favourite-0.006
 brand-0.005
 favorite-0.005
Token looked
Token ID3114
Feature activation+4.69e+00

Pos logit contributions
pron+0.008
 masterpiece+0.008
 favourite+0.008
 brand+0.007
 favorite+0.007
Neg logit contributions
crow-0.009
Bad-0.009
Leave-0.009
eper-0.009
vious-0.008
Token so
Token ID523
Feature activation+2.68e-01

Pos logit contributions
pron+0.367
 favourite+0.343
 masterpiece+0.342
 brand+0.310
 favorite+0.305
Neg logit contributions
crow-0.358
Bad-0.350
Leave-0.344
vious-0.324
eper-0.320
Token his
Token ID465
Feature activation-2.96e+00

Pos logit contributions
crow+0.024
Bad+0.023
Leave+0.023
vious+0.021
eper+0.021
Neg logit contributions
pron-0.029
 favourite-0.027
 masterpiece-0.027
 brand-0.025
 favorite-0.024
Token head
Token ID1182
Feature activation+1.96e+00

Pos logit contributions
crow+0.219
Bad+0.219
Leave+0.213
eper+0.199
ases+0.196
Neg logit contributions
pron-0.228
 masterpiece-0.210
 favourite-0.205
 brand-0.192
 usual-0.184
Token and
Token ID290
Feature activation+3.54e-01

Pos logit contributions
pron+0.154
 favourite+0.146
 masterpiece+0.144
 brand+0.131
 favorite+0.129
Neg logit contributions
crow-0.149
Bad-0.144
Leave-0.142
vious-0.134
eper-0.133
Token it
Token ID340
Feature activation+5.13e-01

Pos logit contributions
pron+0.028
 favourite+0.026
 masterpiece+0.026
 favorite+0.023
 usual+0.022
Neg logit contributions
Bad-0.027
crow-0.027
Leave-0.026
Stop-0.025
eper-0.024
Token flew
Token ID13112
Feature activation+4.55e-01

Pos logit contributions
pron+0.041
 favourite+0.038
 masterpiece+0.037
 brand+0.034
 favorite+0.033
Neg logit contributions
crow-0.039
Bad-0.039
Leave-0.038
vious-0.036
Stop-0.035
Token away
Token ID1497
Feature activation-7.94e+00

Pos logit contributions
pron+0.036
 favourite+0.036
 masterpiece+0.035
 brand+0.034
 favorite+0.033
Neg logit contributions
crow-0.031
Bad-0.030
Leave-0.030
eper-0.029
ases-0.028
Token.
Token ID13
Feature activation-2.97e-02

Pos logit contributions
crow+0.536
Bad+0.529
Leave+0.512
vious+0.484
ases+0.474
Neg logit contributions
pron-0.701
 favourite-0.645
 masterpiece-0.639
 brand-0.581
 favorite-0.570
Token Tim
Token ID5045
Feature activation+5.77e-01

Pos logit contributions
Bad+0.002
crow+0.002
Leave+0.002
Stop+0.002
vious+0.002
Neg logit contributions
pron-0.003
 masterpiece-0.002
 favourite-0.002
 usual-0.002
 collection-0.002
Tokenmy
Token ID1820
Feature activation-2.99e+00

Pos logit contributions
pron+0.049
 masterpiece+0.046
 favourite+0.046
 brand+0.042
 favorite+0.042
Neg logit contributions
crow-0.041
Bad-0.039
Leave-0.039
ases-0.036
Stop-0.036
Token started
Token ID2067
Feature activation-1.46e+00

Pos logit contributions
crow+0.253
Bad+0.250
Leave+0.245
vious+0.232
eper+0.231
Neg logit contributions
pron-0.209
 favourite-0.196
 masterpiece-0.194
 brand-0.174
 favorite-0.170
Token to
Token ID284
Feature activation+1.68e+00

Pos logit contributions
crow+0.137
Leave+0.134
Bad+0.134
vious+0.126
Stop+0.125
Neg logit contributions
pron-0.091
 favourite-0.081
 masterpiece-0.081
 brand-0.070
 favorite-0.068
Token!
Token ID0
Feature activation+2.85e+00

Pos logit contributions
crow+0.331
Bad+0.322
Leave+0.317
vious+0.299
eper+0.297
Neg logit contributions
pron-0.326
 favourite-0.307
 masterpiece-0.304
 brand-0.276
 favorite-0.273
Token
Token ID198
Feature activation+4.58e-01

Pos logit contributions
pron+0.217
 favourite+0.210
 masterpiece+0.205
 brand+0.189
 favorite+0.186
Neg logit contributions
crow-0.218
Bad-0.217
Leave-0.213
vious-0.199
eper-0.199
Token
Token ID198
Feature activation+4.16e-01

Pos logit contributions
pron+0.034
 favourite+0.032
 masterpiece+0.032
 brand+0.029
 favorite+0.029
Neg logit contributions
crow-0.036
Bad-0.036
Leave-0.035
vious-0.033
eper-0.033
TokenHe
Token ID1544
Feature activation-5.32e+00

Pos logit contributions
pron+0.033
 favourite+0.031
 masterpiece+0.031
 brand+0.028
 favorite+0.027
Neg logit contributions
crow-0.031
Bad-0.030
ases-0.029
vious-0.028
Leave-0.028
Token noticed
Token ID6810
Feature activation+1.29e+00

Pos logit contributions
crow+0.427
Leave+0.410
Bad+0.409
eper+0.390
vious+0.383
Neg logit contributions
pron-0.398
 masterpiece-0.356
 favourite-0.349
 brand-0.323
 favorite-0.313
Token a
Token ID257
Feature activation-4.40e-02

Pos logit contributions
pron+0.097
 favourite+0.091
 masterpiece+0.090
 brand+0.081
 favorite+0.080
Neg logit contributions
crow-0.103
Bad-0.100
Leave-0.098
vious-0.093
eper-0.092
Token crowd
Token ID4315
Feature activation-5.63e+00

Pos logit contributions
Bad+0.004
crow+0.004
Leave+0.004
Stop+0.003
eper+0.003
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 favorite-0.002
 brand-0.002
Token at
Token ID379
Feature activation-3.79e-02

Pos logit contributions
crow+0.399
Bad+0.398
Leave+0.382
eper+0.359
Stop+0.359
Neg logit contributions
pron-0.461
 favourite-0.443
 masterpiece-0.441
 brand-0.405
 favorite-0.393
Token the
Token ID262
Feature activation-1.35e+00

Pos logit contributions
crow+0.003
Bad+0.003
Leave+0.003
vious+0.003
eper+0.003
Neg logit contributions
pron-0.003
 favourite-0.003
 masterpiece-0.003
 brand-0.003
 favorite-0.003
Token park
Token ID3952
Feature activation-1.69e+00

Pos logit contributions
crow+0.100
Bad+0.097
Leave+0.097
ases+0.092
eper+0.090
Neg logit contributions
pron-0.106
 favourite-0.105
 masterpiece-0.103
 favorite-0.094
 usual-0.094
Token and
Token ID290
Feature activation+2.53e-01

Pos logit contributions
crow+0.134
Bad+0.132
Leave+0.130
vious+0.122
eper+0.121
Neg logit contributions
pron-0.125
 favourite-0.119
 masterpiece-0.118
 brand-0.107
 favorite-0.105
Token lift
Token ID10303
Feature activation+5.10e-01

Pos logit contributions
crow+0.177
Bad+0.168
Leave+0.167
eper+0.162
vious+0.161
Neg logit contributions
pron-0.185
 favourite-0.177
 masterpiece-0.173
 brand-0.157
 favorite-0.155
Token this
Token ID428
Feature activation+9.76e-01

Pos logit contributions
pron+0.041
 favourite+0.039
 masterpiece+0.039
 brand+0.036
 favorite+0.035
Neg logit contributions
crow-0.037
Bad-0.036
Leave-0.036
vious-0.034
eper-0.033
Token rock
Token ID3881
Feature activation-7.39e-02

Pos logit contributions
pron+0.093
 favourite+0.088
 masterpiece+0.088
 brand+0.080
ail+0.078
Neg logit contributions
crow-0.054
Bad-0.052
Leave-0.050
vious-0.049
eper-0.048
Token?"
Token ID1701
Feature activation+6.22e+00

Pos logit contributions
crow+0.006
Bad+0.006
Leave+0.005
vious+0.005
eper+0.005
Neg logit contributions
pron-0.006
 favourite-0.005
 masterpiece-0.005
 brand-0.005
 favorite-0.005
Token she
Token ID673
Feature activation+5.04e+00

Pos logit contributions
pron+0.451
 masterpiece+0.445
 favourite+0.426
 brand+0.401
 usual+0.382
Neg logit contributions
crow-0.519
Leave-0.487
Bad-0.487
Stop-0.458
Hey-0.453
Token asked
Token ID1965
Feature activation-5.99e-01

Pos logit contributions
pron+0.353
 favourite+0.332
 masterpiece+0.327
 brand+0.295
 favorite+0.292
Neg logit contributions
crow-0.426
Bad-0.416
Leave-0.410
vious-0.388
eper-0.385
Token.
Token ID13
Feature activation+2.26e-01

Pos logit contributions
crow+0.050
Bad+0.049
Leave+0.049
vious+0.046
eper+0.046
Neg logit contributions
pron-0.042
 favourite-0.040
 masterpiece-0.039
 brand-0.036
 favorite-0.035
Token
Token ID220
Feature activation+1.15e+00

Pos logit contributions
 masterpiece+0.021
pron+0.020
 favourite+0.020
 brand+0.019
 collection+0.018
Neg logit contributions
crow-0.013
Bad-0.013
Leave-0.013
Stop-0.012
Hey-0.012
Token
Token ID198
Feature activation+7.69e-01

Pos logit contributions
pron+0.099
 masterpiece+0.094
 favourite+0.093
 brand+0.086
 collection+0.083
Neg logit contributions
crow-0.078
Bad-0.074
Leave-0.073
eper-0.069
ases-0.069
Token
Token ID198
Feature activation+7.56e-01

Pos logit contributions
pron+0.067
 masterpiece+0.065
 favourite+0.064
 brand+0.059
 collection+0.057
Neg logit contributions
crow-0.051
Bad-0.049
Leave-0.047
Stop-0.045
eper-0.044
TokenHer
Token ID9360
Feature activation+2.27e+00

Pos logit contributions
pron+0.064
 masterpiece+0.062
 favourite+0.062
 brand+0.058
 favorite+0.056
Neg logit contributions
crow-0.051
Bad-0.050
Leave-0.050
Stop-0.046
eper-0.045
Token for
Token ID329
Feature activation+5.45e+00

Pos logit contributions
Bad+0.094
crow+0.091
eper+0.086
Leave+0.086
 hunters+0.083
Neg logit contributions
pron-0.086
 masterpiece-0.082
 favourite-0.080
 complexion-0.074
ail-0.073
Token food
Token ID2057
Feature activation-4.99e+00

Pos logit contributions
pron+0.404
 favourite+0.378
 masterpiece+0.375
 brand+0.339
 favorite+0.330
Neg logit contributions
crow-0.432
Bad-0.430
Leave-0.413
ases-0.398
eper-0.398
Token.
Token ID13
Feature activation+2.19e-01

Pos logit contributions
crow+0.374
Bad+0.358
Leave+0.348
eper+0.335
vious+0.333
Neg logit contributions
pron-0.398
 masterpiece-0.377
 favourite-0.374
 brand-0.344
 favorite-0.327
Token Mom
Token ID11254
Feature activation+5.38e+00

Pos logit contributions
pron+0.016
 favourite+0.016
 favorite+0.015
 masterpiece+0.014
 Mam+0.014
Neg logit contributions
crow-0.016
Leave-0.015
Bad-0.015
vious-0.015
eper-0.015
Tokenmy
Token ID1820
Feature activation-3.06e+00

Pos logit contributions
pron+0.417
 masterpiece+0.381
 favourite+0.376
 favorite+0.342
 brand+0.342
Neg logit contributions
crow-0.413
Leave-0.407
Bad-0.406
vious-0.368
Stop-0.365
Token will
Token ID481
Feature activation-2.65e+00

Pos logit contributions
crow+0.249
Leave+0.244
Bad+0.242
vious+0.224
Stop+0.221
Neg logit contributions
pron-0.222
 masterpiece-0.202
 favourite-0.201
 favorite-0.182
 brand-0.181
Token be
Token ID307
Feature activation+1.02e+00

Pos logit contributions
Bad+0.205
crow+0.205
Leave+0.199
Stop+0.188
eper+0.185
Neg logit contributions
pron-0.198
 favourite-0.193
 masterpiece-0.190
 brand-0.174
 favorite-0.168
Token mad
Token ID8805
Feature activation-7.77e+00

Pos logit contributions
pron+0.097
 favourite+0.091
 masterpiece+0.089
 favorite+0.085
 brand+0.085
Neg logit contributions
crow-0.064
Bad-0.058
Leave-0.057
Hey-0.054
Stop-0.054
Token if
Token ID611
Feature activation-2.75e+00

Pos logit contributions
crow+0.644
Bad+0.637
Leave+0.627
eper+0.571
Stop+0.571
Neg logit contributions
pron-0.537
 favourite-0.533
 masterpiece-0.501
 favorite-0.487
 brand-0.458
Token you
Token ID345
Feature activation-3.81e+00

Pos logit contributions
crow+0.187
Bad+0.181
Leave+0.170
Stop+0.165
eper+0.162
Neg logit contributions
pron-0.239
 masterpiece-0.232
 favourite-0.221
 brand-0.215
icol-0.201
Token make
Token ID787
Feature activation+1.20e+00

Pos logit contributions
crow+0.289
Bad+0.282
Leave+0.277
vious+0.259
eper+0.259
Neg logit contributions
pron-0.299
 favourite-0.284
 masterpiece-0.281
 brand-0.256
 favorite-0.253
Token was
Token ID373
Feature activation+1.01e+00

Pos logit contributions
crow+0.040
Leave+0.040
Bad+0.038
ases+0.036
Stop+0.036
Neg logit contributions
 favourite-0.033
pron-0.032
 masterpiece-0.032
 favorite-0.031
 collection-0.028
Token just
Token ID655
Feature activation+9.43e-01

Pos logit contributions
pron+0.076
 favourite+0.071
 masterpiece+0.071
 brand+0.063
 favorite+0.062
Neg logit contributions
crow-0.080
Bad-0.079
Leave-0.077
eper-0.072
vious-0.072
Token a
Token ID257
Feature activation-3.72e-01

Pos logit contributions
pron+0.071
 favourite+0.067
 masterpiece+0.066
 brand+0.060
 favorite+0.059
Neg logit contributions
crow-0.075
Bad-0.073
Leave-0.071
vious-0.068
eper-0.067
Token joke
Token ID9707
Feature activation-1.85e+00

Pos logit contributions
crow+0.028
Bad+0.028
Leave+0.027
Stop+0.025
vious+0.025
Neg logit contributions
pron-0.029
 favourite-0.027
 masterpiece-0.027
 brand-0.025
 favorite-0.024
Token.
Token ID13
Feature activation-5.88e-01

Pos logit contributions
crow+0.150
Bad+0.149
Leave+0.149
eper+0.137
vious+0.136
Neg logit contributions
pron-0.132
 favourite-0.124
 masterpiece-0.119
 favorite-0.112
 brand-0.108
Token Come
Token ID7911
Feature activation-8.38e+00

Pos logit contributions
crow+0.044
Leave+0.043
eper+0.042
Bad+0.042
vious+0.040
Neg logit contributions
 favourite-0.041
pron-0.040
 favorite-0.037
 masterpiece-0.035
onna-0.035
Token on
Token ID319
Feature activation+9.18e-01

Pos logit contributions
crow+0.708
Bad+0.680
Leave+0.672
vious+0.668
Stop+0.631
Neg logit contributions
pron-0.587
 favourite-0.571
 masterpiece-0.545
 favorite-0.512
 brand-0.505
Token,
Token ID11
Feature activation-1.72e+00

Pos logit contributions
pron+0.064
 favourite+0.060
 masterpiece+0.059
 brand+0.054
 favorite+0.053
Neg logit contributions
crow-0.078
Bad-0.076
Leave-0.076
vious-0.072
Stop-0.071
Token let
Token ID1309
Feature activation-6.69e-01

Pos logit contributions
crow+0.144
Bad+0.138
Leave+0.137
ases+0.136
vious+0.134
Neg logit contributions
pron-0.114
 favourite-0.107
 masterpiece-0.102
 favorite-0.097
 brand-0.093
Token's
Token ID338
Feature activation-4.34e+00

Pos logit contributions
Leave+0.050
crow+0.050
Bad+0.050
vious+0.045
ases+0.045
Neg logit contributions
pron-0.051
 favourite-0.050
 masterpiece-0.048
 favorite-0.045
 brand-0.043
Token play
Token ID711
Feature activation-1.37e+00

Pos logit contributions
crow+0.365
Bad+0.356
Leave+0.351
vious+0.333
Stop+0.326
Neg logit contributions
pron-0.304
 favourite-0.291
 masterpiece-0.288
 favorite-0.257
 brand-0.256
Token fan
Token ID4336
Feature activation+4.78e+00

Pos logit contributions
pron+0.036
 favourite+0.035
 masterpiece+0.034
 brand+0.031
 favorite+0.030
Neg logit contributions
crow-0.038
Bad-0.036
Leave-0.035
eper-0.033
vious-0.033
Token in
Token ID287
Feature activation+1.58e+00

Pos logit contributions
pron+0.351
 favourite+0.329
 masterpiece+0.327
 brand+0.295
 favorite+0.293
Neg logit contributions
crow-0.381
Bad-0.377
Leave-0.372
Stop-0.349
vious-0.346
Token the
Token ID262
Feature activation-1.43e+00

Pos logit contributions
pron+0.123
 masterpiece+0.117
 favourite+0.117
 brand+0.107
 favorite+0.104
Neg logit contributions
crow-0.118
Leave-0.116
Bad-0.115
vious-0.108
Stop-0.106
Token forest
Token ID8222
Feature activation-3.98e+00

Pos logit contributions
crow+0.118
Bad+0.117
Leave+0.116
ases+0.110
eper+0.109
Neg logit contributions
pron-0.102
 favourite-0.096
 masterpiece-0.096
 brand-0.087
 favorite-0.085
Token.
Token ID13
Feature activation+1.28e-01

Pos logit contributions
Bad+0.322
Leave+0.321
crow+0.320
Stop+0.300
Hey+0.294
Neg logit contributions
pron-0.281
 favourite-0.269
 masterpiece-0.266
 favorite-0.240
 brand-0.240
Token If
Token ID1002
Feature activation-1.10e+01

Pos logit contributions
pron+0.010
 favourite+0.010
 masterpiece+0.009
 favorite+0.009
 brand+0.009
Neg logit contributions
crow-0.009
Bad-0.009
Leave-0.009
eper-0.008
vious-0.008
Token you
Token ID345
Feature activation-3.75e+00

Pos logit contributions
crow+0.507
Bad+0.499
Leave+0.473
Stop+0.430
eper+0.416
Neg logit contributions
pron-1.195
 masterpiece-1.133
 favourite-1.129
 brand-1.058
 favorite-1.036
Token find
Token ID1064
Feature activation+2.85e+00

Pos logit contributions
crow+0.285
Bad+0.280
Leave+0.275
eper+0.256
vious+0.255
Neg logit contributions
pron-0.291
 favourite-0.278
 masterpiece-0.274
 brand-0.248
 favorite-0.248
Token it
Token ID340
Feature activation+5.38e-01

Pos logit contributions
pron+0.228
 favourite+0.215
 masterpiece+0.214
 brand+0.195
 favorite+0.192
Neg logit contributions
crow-0.212
Bad-0.207
Leave-0.202
vious-0.190
eper-0.190
Token,
Token ID11
Feature activation-1.27e+00

Pos logit contributions
pron+0.042
 masterpiece+0.039
 favourite+0.039
 brand+0.035
 favorite+0.034
Neg logit contributions
crow-0.041
Bad-0.040
Leave-0.039
vious-0.037
eper-0.037
Token it
Token ID340
Feature activation+5.28e-01

Pos logit contributions
crow+0.089
Bad+0.086
Leave+0.085
vious+0.079
eper+0.079
Neg logit contributions
pron-0.107
 favourite-0.102
 masterpiece-0.101
 brand-0.093
 favorite-0.092
Token It
Token ID632
Feature activation-2.94e-01

Pos logit contributions
pron+0.025
 favourite+0.024
 masterpiece+0.024
 brand+0.022
 favorite+0.021
Neg logit contributions
crow-0.021
Bad-0.020
Leave-0.020
vious-0.018
Stop-0.018
Token was
Token ID373
Feature activation+1.56e+00

Pos logit contributions
crow+0.027
Bad+0.027
Leave+0.026
vious+0.025
eper+0.025
Neg logit contributions
pron-0.018
 favourite-0.017
 masterpiece-0.017
 brand-0.015
 favorite-0.015
Token so
Token ID523
Feature activation+1.18e-01

Pos logit contributions
pron+0.113
 masterpiece+0.107
 favourite+0.104
 collection+0.092
 brand+0.092
Neg logit contributions
crow-0.126
Bad-0.126
Leave-0.122
eper-0.114
vious-0.114
Token small
Token ID1402
Feature activation+1.35e+00

Pos logit contributions
pron+0.007
 favourite+0.006
 masterpiece+0.006
 brand+0.006
 favorite+0.005
Neg logit contributions
crow-0.011
Bad-0.011
Leave-0.011
vious-0.010
Stop-0.010
Token and
Token ID290
Feature activation+3.39e-01

Pos logit contributions
pron+0.091
 favourite+0.089
 masterpiece+0.086
 brand+0.079
 favorite+0.079
Neg logit contributions
crow-0.113
Bad-0.113
Leave-0.111
Stop-0.104
eper-0.103
Token scared
Token ID12008
Feature activation-8.65e+00

Pos logit contributions
pron+0.022
 favourite+0.021
 masterpiece+0.021
 brand+0.018
 favorite+0.018
Neg logit contributions
crow-0.030
Bad-0.029
Leave-0.029
vious-0.027
Stop-0.027
Token,
Token ID11
Feature activation-1.24e+00

Pos logit contributions
Bad+0.787
crow+0.771
Leave+0.768
eper+0.746
ases+0.739
Neg logit contributions
 favourite-0.490
pron-0.482
 masterpiece-0.460
 favorite-0.427
 brand-0.427
Token so
Token ID523
Feature activation+1.05e-01

Pos logit contributions
crow+0.111
Bad+0.109
Leave+0.108
Stop+0.101
vious+0.100
Neg logit contributions
pron-0.083
 masterpiece-0.076
 favourite-0.076
 brand-0.067
 favorite-0.066
Token the
Token ID262
Feature activation-1.58e+00

Pos logit contributions
pron+0.006
 masterpiece+0.006
 favourite+0.006
 brand+0.005
 favorite+0.005
Neg logit contributions
crow-0.010
Bad-0.010
Leave-0.010
Stop-0.009
eper-0.009
Token girl
Token ID2576
Feature activation-2.37e+00

Pos logit contributions
crow+0.137
Bad+0.134
Leave+0.131
vious+0.125
eper+0.124
Neg logit contributions
pron-0.109
 masterpiece-0.101
 favourite-0.101
 brand-0.091
 favorite-0.087
Token decided
Token ID3066
Feature activation-3.43e+00

Pos logit contributions
crow+0.197
Bad+0.190
Leave+0.187
eper+0.179
vious+0.178
Neg logit contributions
pron-0.171
 masterpiece-0.160
 favourite-0.160
 brand-0.146
 favorite-0.140
Token Lily
Token ID20037
Feature activation+2.20e+00

Pos logit contributions
 masterpiece+0.053
pron+0.052
 favourite+0.051
 brand+0.049
icol+0.047
Neg logit contributions
crow-0.043
Bad-0.040
Leave-0.039
vious-0.038
Hey-0.037
Token like
Token ID588
Feature activation-3.47e+00

Pos logit contributions
pron+0.185
 favourite+0.183
 masterpiece+0.178
 favorite+0.167
 brand+0.161
Neg logit contributions
crow-0.150
Bad-0.147
Leave-0.143
eper-0.132
ases-0.130
Token to
Token ID284
Feature activation+1.60e+00

Pos logit contributions
crow+0.289
Bad+0.281
Leave+0.277
vious+0.261
eper+0.260
Neg logit contributions
pron-0.250
 favourite-0.234
 masterpiece-0.232
 brand-0.210
 favorite-0.204
Token see
Token ID766
Feature activation+4.87e-01

Pos logit contributions
pron+0.125
 favourite+0.117
 masterpiece+0.116
 brand+0.108
 favorite+0.104
Neg logit contributions
crow-0.124
Bad-0.119
Leave-0.119
vious-0.111
ases-0.110
Token the
Token ID262
Feature activation-1.34e+00

Pos logit contributions
pron+0.038
 favourite+0.037
 masterpiece+0.036
 favorite+0.034
 brand+0.034
Neg logit contributions
crow-0.036
Bad-0.035
Leave-0.035
vious-0.033
Stop-0.032
Token animals
Token ID4695
Feature activation-9.77e+00

Pos logit contributions
crow+0.092
Leave+0.090
Bad+0.089
ases+0.083
vious+0.083
Neg logit contributions
 favourite-0.112
pron-0.111
 masterpiece-0.108
 favorite-0.103
 usual-0.100
Token and
Token ID290
Feature activation+6.47e-01

Pos logit contributions
Bad+0.824
crow+0.823
Leave+0.799
Stop+0.759
vious+0.752
Neg logit contributions
pron-0.654
 favourite-0.641
 masterpiece-0.624
 favorite-0.569
 brand-0.560
Token learn
Token ID2193
Feature activation-4.88e+00

Pos logit contributions
pron+0.050
 favourite+0.048
 masterpiece+0.047
 brand+0.043
 favorite+0.043
Neg logit contributions
crow-0.049
Bad-0.048
Leave-0.047
vious-0.044
eper-0.044
Token their
Token ID511
Feature activation+1.03e+00

Pos logit contributions
crow+0.424
Bad+0.415
Leave+0.409
vious+0.388
eper+0.386
Neg logit contributions
pron-0.328
 favourite-0.310
 masterpiece-0.305
 brand-0.275
 favorite-0.271
Token names
Token ID3891
Feature activation-2.28e+00

Pos logit contributions
pron+0.073
 masterpiece+0.067
 favourite+0.066
 brand+0.061
 favorite+0.057
Neg logit contributions
crow-0.087
Bad-0.085
Leave-0.084
vious-0.079
eper-0.079
Token.
Token ID13
Feature activation+5.71e-01

Pos logit contributions
crow+0.184
Bad+0.183
Leave+0.179
vious+0.168
Stop+0.167
Neg logit contributions
pron-0.165
 favourite-0.157
 masterpiece-0.155
 brand-0.140
 favorite-0.140
Token saw
Token ID2497
Feature activation-1.86e-01

Pos logit contributions
crow+0.201
Bad+0.197
Leave+0.192
eper+0.186
vious+0.184
Neg logit contributions
pron-0.217
 masterpiece-0.200
 favourite-0.197
 brand-0.182
 usual-0.173
Token a
Token ID257
Feature activation+2.71e-01

Pos logit contributions
crow+0.015
Bad+0.015
Leave+0.015
vious+0.014
eper+0.014
Neg logit contributions
pron-0.014
 favourite-0.013
 masterpiece-0.013
 brand-0.012
 favorite-0.011
Token big
Token ID1263
Feature activation+5.97e+00

Pos logit contributions
pron+0.017
 favourite+0.016
 masterpiece+0.016
 favorite+0.014
 brand+0.014
Neg logit contributions
Bad-0.024
crow-0.024
Leave-0.023
eper-0.022
Stop-0.022
Token T
Token ID309
Feature activation+2.73e+00

Pos logit contributions
pron+0.451
 favourite+0.423
 masterpiece+0.422
 brand+0.391
 favorite+0.380
Neg logit contributions
crow-0.473
Leave-0.464
Bad-0.460
vious-0.433
ases-0.430
Token-
Token ID12
Feature activation+1.83e+00

Pos logit contributions
pron+0.208
 favourite+0.197
 masterpiece+0.195
 brand+0.177
 favorite+0.175
Neg logit contributions
crow-0.214
Bad-0.209
Leave-0.205
vious-0.193
eper-0.192
TokenRex
Token ID47389
Feature activation-1.28e+01

Pos logit contributions
pron+0.162
 favourite+0.152
 masterpiece+0.146
 favorite+0.141
 brand+0.138
Neg logit contributions
Leave-0.122
Bad-0.119
crow-0.119
ases-0.110
Stop-0.110
Token and
Token ID290
Feature activation+6.09e-01

Pos logit contributions
crow+1.014
Bad+0.990
Leave+0.973
vious+0.917
eper+0.911
Neg logit contributions
pron-0.965
 favourite-0.913
 masterpiece-0.903
 brand-0.821
 favorite-0.809
Token said
Token ID531
Feature activation+1.42e+00

Pos logit contributions
pron+0.051
 masterpiece+0.051
 favourite+0.048
ail+0.046
 collection+0.044
Neg logit contributions
Bad-0.042
Leave-0.039
crow-0.038
Stop-0.036
Hey-0.035
Token,
Token ID11
Feature activation-7.63e-01

Pos logit contributions
pron+0.107
 masterpiece+0.101
 favourite+0.100
 brand+0.090
 favorite+0.088
Neg logit contributions
crow-0.113
Bad-0.110
Leave-0.108
vious-0.102
eper-0.101
Token "
Token ID366
Feature activation+9.04e-01

Pos logit contributions
Bad+0.056
crow+0.055
Leave+0.054
Stop+0.050
eper+0.049
Neg logit contributions
pron-0.058
 masterpiece-0.058
 favourite-0.057
 collection-0.051
 favorite-0.050
TokenMom
Token ID29252
Feature activation-7.20e-01

Pos logit contributions
pron+0.067
 favourite+0.064
 masterpiece+0.060
 favorite+0.057
 usual+0.056
Neg logit contributions
crow-0.065
ases-0.064
 risks-0.060
vious-0.060
eper-0.059