TOP ACTIVATIONS
MAX = 0.340

kitchen . They saw their pizz as on the table .
a big TV and a DVD player .
make the waiter drop the pizz as . They said sorry
. They dream of real pizz as . They dream of
They put the pizz as in the oven and
" Mom , are the pizz as ready ?" Lily asked
they put away their fake pizz as and hats . They
the kitchen and saw their pizz as . They smelled good
. Let 's put the pizz as in the oven and
They make and sell many pizz as . They have fun
They wanted to eat their pizz as right away .
a little while until the pizz as were cooked . Lily
They all ate their pizz as and they were very
came back with two big pizz as . She put them
you go , enjoy your pizz as ." "
wall with pictures of different pizz as . Tom and Anna
done , Mom put the pizz as in the oven .
pizza . They cut their pizz as into slices . They
dropped the tray and the pizz as fell on the floor
the door and give the pizz as to the people ."

MIN ACTIVATIONS
MIN = -0.308

little , the little boy inc hed closer . Very soon
from the window . Rel uct antly , he came away
. John inc hed closer and saw it
sea monster insisted . Rel uct antly , it followed him
his climb . He slowly inc hed his way up ,
buy his own . Rel uct antly , his friend gave
. Rel uct antly , Elsa left the
whispers . They smell more inc ense and spices and smoke
and whispers . They smell inc ense and spices and smoke
smiled and said , " Ok !" Then she took the
and then smiled . " Ok , let â € ™
smiled and said , " Ok , that 's fine .
chuckled and said , " Ok , here you go ,"
smiled and said : " Ok mom , I will never
door and said , " Ok Jane , you may enter
smiled and said , " Ok , I will pray like
smiled and said , " Ok !" She walked over to
with his sleeve . " Ok , Mom my . That
� � € � � Ok , I believe in you
led and said , " Ok , then I will hug

INTERVAL 0.178 - 0.340
CONTAINS 0.427%

make the boo - bo o go away . Tim my
He realized that it was much easier to find his toys
it would be a lot of fun . But when her
him up to the top of his house . Every day
. Jack saw a small card near the sand . He

INTERVAL 0.016 - 0.178
CONTAINS 37.662%

he climbed . Wh isk ers me owed and watched Tim
around ". The two friends smiled and thanked the bigger fish
, we are sorry . We were wrong . We should
riding in a me adow with flowers and birds .
of candy ! Dave was so happy . He

INTERVAL -0.146 - 0.016
CONTAINS 60.751%

woods behind their house . One day , they find a
a small hill near his house . He put on his
and bananas and walked back home . He was very happy
before they tried new things . <|endoftext|> L ily was a
on top of the slide . L ily

INTERVAL -0.308 - -0.146
CONTAINS 1.160%

. He looked around and decided to choose an even sun
of it , but he couldn 't . He was sad
it . Later that day , Tim my
for her to eat . Suddenly she started to tick le
some coal . So , Jane went to the
Token kitchen
Token ID9592
Feature activation-8.45e-03

Pos logit contributions
rated+0.092
appointed+0.088
uct+0.086
ulously+0.086
aman+0.084
Neg logit contributions
 mate-0.098
 superheroes-0.098
 heroes-0.092
 soldiers-0.088
 pirates-0.085
Token.
Token ID13
Feature activation+8.92e-03

Pos logit contributions
rated+0.018
appointed+0.018
ulously+0.017
uct+0.017
aman+0.017
Neg logit contributions
 mate-0.012
 superheroes-0.012
 heroes-0.011
 soldiers-0.010
 pirates-0.010
Token They
Token ID1119
Feature activation+3.71e-02

Pos logit contributions
 mate+0.013
 superheroes+0.013
 heroes+0.011
 soldiers+0.011
 pirates+0.011
Neg logit contributions
rated-0.020
ulously-0.018
appointed-0.018
uct-0.018
aman-0.018
Token saw
Token ID2497
Feature activation+3.88e-02

Pos logit contributions
 mate+0.067
 superheroes+0.066
 heroes+0.062
 soldiers+0.059
 pirates+0.057
Neg logit contributions
rated-0.065
appointed-0.062
ulously-0.060
uct-0.060
aman-0.060
Token their
Token ID511
Feature activation+1.33e-01

Pos logit contributions
 mate+0.065
 superheroes+0.056
e+0.053
 heroes+0.053
 loser+0.051
Neg logit contributions
ulously-0.067
ened-0.064
 inc-0.063
aman-0.063
uct-0.062
Token pizz
Token ID38748
Feature activation+3.14e-01

Pos logit contributions
 mate+0.208
 superheroes+0.203
 heroes+0.188
 soldiers+0.174
e+0.168
Neg logit contributions
rated-0.256
appointed-0.246
ulously-0.244
uct-0.241
aman-0.241
Tokenas
Token ID292
Feature activation+1.83e-01

Pos logit contributions
 superheroes+0.536
 villain+0.439
 camping+0.437
 Antarctica+0.431
 Rocky+0.428
Neg logit contributions
ipt-0.490
urious-0.469
anked-0.464
iped-0.462
aut-0.451
Token on
Token ID319
Feature activation+5.77e-02

Pos logit contributions
 mate+0.280
 superheroes+0.276
 heroes+0.258
 soldiers+0.231
 pirates+0.224
Neg logit contributions
rated-0.350
appointed-0.335
aman-0.335
uct-0.335
iously-0.329
Token the
Token ID262
Feature activation-5.54e-02

Pos logit contributions
 mate+0.098
 superheroes+0.097
 heroes+0.090
 soldiers+0.083
 pirates+0.080
Neg logit contributions
rated-0.102
ulously-0.100
aman-0.099
appointed-0.098
uct-0.097
Token table
Token ID3084
Feature activation+2.31e-02

Pos logit contributions
rated+0.069
appointed+0.062
iously+0.061
ulously+0.060
aman+0.060
Neg logit contributions
 superheroes-0.124
 mate-0.121
 heroes-0.116
 spies-0.106
 pirates-0.106
Token.
Token ID13
Feature activation+1.31e-02

Pos logit contributions
 superheroes+0.035
 mate+0.035
 heroes+0.032
 soldiers+0.030
 pirates+0.029
Neg logit contributions
rated-0.046
appointed-0.044
uct-0.043
ulously-0.043
aman-0.043
Token a
Token ID257
Feature activation+1.31e-01

Pos logit contributions
 mate+0.046
 superheroes+0.045
 heroes+0.040
 soldiers+0.036
 pirates+0.033
Neg logit contributions
rated-0.118
appointed-0.115
uct-0.113
ulously-0.113
aman-0.112
Token big
Token ID1263
Feature activation+5.32e-02

Pos logit contributions
 mate+0.210
 superheroes+0.201
 heroes+0.188
e+0.182
 soldiers+0.180
Neg logit contributions
rated-0.235
aman-0.230
appointed-0.224
 inc-0.219
 exp-0.216
Token TV
Token ID3195
Feature activation+1.57e-01

Pos logit contributions
 mate+0.097
 superheroes+0.096
 heroes+0.090
 soldiers+0.085
e+0.082
Neg logit contributions
rated-0.086
aman-0.082
appointed-0.080
ulously-0.079
uct-0.078
Token and
Token ID290
Feature activation+9.96e-03

Pos logit contributions
 mate+0.230
 superheroes+0.228
 heroes+0.212
 soldiers+0.197
 pirates+0.190
Neg logit contributions
rated-0.318
appointed-0.306
uct-0.301
ulously-0.300
aman-0.297
Token a
Token ID257
Feature activation+1.27e-01

Pos logit contributions
 superheroes+0.012
 mate+0.011
 heroes+0.011
 soldiers+0.010
 pirates+0.010
Neg logit contributions
rated-0.024
aman-0.023
appointed-0.023
uct-0.023
ulously-0.022
Token DVD
Token ID12490
Feature activation+3.13e-01

Pos logit contributions
 mate+0.189
 superheroes+0.185
 heroes+0.172
e+0.162
 soldiers+0.159
Neg logit contributions
rated-0.241
aman-0.232
appointed-0.232
 inc-0.226
ulously-0.224
Token player
Token ID2137
Feature activation+1.51e-01

Pos logit contributions
 mate+0.411
 superheroes+0.408
 heroes+0.369
 soldiers+0.331
 queens+0.324
Neg logit contributions
rated-0.641
ulously-0.610
esh-0.606
ened-0.599
appointed-0.599
Token.
Token ID13
Feature activation+5.46e-04

Pos logit contributions
 mate+0.229
 superheroes+0.227
 heroes+0.211
 soldiers+0.199
 pirates+0.191
Neg logit contributions
rated-0.303
appointed-0.293
uct-0.287
ulously-0.286
aman-0.284
Token
Token ID220
Feature activation-2.22e-02

Pos logit contributions
 mate+0.001
 superheroes+0.001
 heroes+0.001
 soldiers+0.001
 pirates+0.001
Neg logit contributions
rated-0.001
appointed-0.001
ulously-0.001
uct-0.001
aman-0.001
Token
Token ID198
Feature activation+5.15e-02

Pos logit contributions
appointed+0.040
rated+0.040
uct+0.039
ulously+0.039
aman+0.038
Neg logit contributions
 mate-0.037
 superheroes-0.037
 heroes-0.034
 soldiers-0.032
 pirates-0.031
Token
Token ID198
Feature activation+5.10e-02

Pos logit contributions
 superheroes+0.073
 mate+0.073
 heroes+0.067
 soldiers+0.063
 pirates+0.059
Neg logit contributions
rated-0.107
appointed-0.105
uct-0.103
ulously-0.102
aman-0.102
Token make
Token ID787
Feature activation-1.67e-02

Pos logit contributions
rated+0.093
appointed+0.090
ulously+0.089
uct+0.087
esh+0.086
Neg logit contributions
 mate-0.093
 superheroes-0.092
 heroes-0.087
 soldiers-0.083
 camping-0.079
Token the
Token ID262
Feature activation-5.68e-02

Pos logit contributions
ulously+0.031
uct+0.030
appointed+0.030
rated+0.030
aman+0.030
Neg logit contributions
 mate-0.027
 superheroes-0.025
 heroes-0.023
 soldiers-0.021
 queens-0.021
Token waiter
Token ID46612
Feature activation+1.44e-01

Pos logit contributions
rated+0.100
aman+0.092
appointed+0.090
uct+0.089
ulously+0.089
Neg logit contributions
 mate-0.096
 superheroes-0.095
 heroes-0.086
e-0.084
izards-0.080
Token drop
Token ID4268
Feature activation+1.61e-02

Pos logit contributions
 mate+0.249
 superheroes+0.241
 heroes+0.219
 soldiers+0.209
 Antarctica+0.202
Neg logit contributions
rated-0.249
uct-0.234
appointed-0.231
iously-0.227
ulously-0.224
Token the
Token ID262
Feature activation-5.75e-02

Pos logit contributions
 mate+0.024
 superheroes+0.024
 heroes+0.022
 camping+0.019
 soldiers+0.019
Neg logit contributions
rated-0.031
ulously-0.031
ened-0.030
appointed-0.030
uct-0.030
Token pizz
Token ID38748
Feature activation+3.12e-01

Pos logit contributions
rated+0.104
aman+0.099
ulously+0.099
inct+0.096
esh+0.096
Neg logit contributions
 superheroes-0.092
 mate-0.088
 heroes-0.083
 much-0.074
izards-0.073
Tokenas
Token ID292
Feature activation+1.83e-01

Pos logit contributions
 superheroes+0.501
 camping+0.413
 mate+0.410
 Antarctica+0.405
 hunting+0.396
Neg logit contributions
inct-0.517
rated-0.513
urious-0.507
uct-0.485
ipt-0.482
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
 mate+0.300
 superheroes+0.298
 heroes+0.277
 soldiers+0.252
 pirates+0.246
Neg logit contributions
rated-0.341
appointed-0.321
uct-0.321
ulously-0.315
aman-0.313
Token They
Token ID1119
Feature activation+3.30e-02

Pos logit contributions
 mate+0.018
 superheroes+0.018
 heroes+0.017
 soldiers+0.016
 pirates+0.016
Neg logit contributions
rated-0.018
appointed-0.017
uct-0.017
ulously-0.017
aman-0.016
Token said
Token ID531
Feature activation+1.15e-02

Pos logit contributions
 superheroes+0.057
 mate+0.057
 heroes+0.054
 soldiers+0.050
 pirates+0.049
Neg logit contributions
rated-0.060
appointed-0.057
esh-0.057
aman-0.056
ulously-0.055
Token sorry
Token ID7926
Feature activation+1.13e-01

Pos logit contributions
 mate+0.015
 superheroes+0.014
 heroes+0.013
e+0.012
 soldiers+0.011
Neg logit contributions
rated-0.024
appointed-0.024
uct-0.024
ulously-0.024
 inc-0.024
Token.
Token ID13
Feature activation+3.25e-04

Pos logit contributions
 mate+0.098
 superheroes+0.089
 heroes+0.082
 soldiers+0.075
prise+0.075
Neg logit contributions
rated-0.125
appointed-0.121
uct-0.119
iously-0.118
aman-0.117
Token They
Token ID1119
Feature activation+2.86e-02

Pos logit contributions
 mate+0.001
 superheroes+0.001
 heroes+0.001
 soldiers+0.001
e+0.001
Neg logit contributions
rated-0.001
appointed-0.000
ulously-0.000
uct-0.000
aman-0.000
Token dream
Token ID4320
Feature activation-4.17e-02

Pos logit contributions
 mate+0.040
 superheroes+0.039
 heroes+0.037
 soldiers+0.035
 spies+0.033
Neg logit contributions
rated-0.059
appointed-0.055
 inc-0.055
uct-0.054
ulously-0.054
Token of
Token ID286
Feature activation+1.86e-01

Pos logit contributions
rated+0.101
appointed+0.098
aman+0.096
ulously+0.095
uct+0.094
Neg logit contributions
 mate-0.044
 superheroes-0.043
 heroes-0.036
 pirates-0.034
 soldiers-0.034
Token real
Token ID1103
Feature activation+8.44e-02

Pos logit contributions
 mate+0.301
 superheroes+0.249
aky+0.246
 loser+0.243
prise+0.241
Neg logit contributions
 inc-0.303
ulously-0.298
aman-0.297
uct-0.291
ened-0.290
Token pizz
Token ID38748
Feature activation+3.11e-01

Pos logit contributions
 mate+0.103
 superheroes+0.090
 heroes+0.078
izards+0.077
aky+0.075
Neg logit contributions
ened-0.169
iously-0.167
rated-0.167
ulously-0.165
 state-0.164
Tokenas
Token ID292
Feature activation+1.79e-01

Pos logit contributions
 superheroes+0.469
 hunting+0.425
 liar+0.415
 tyrann+0.415
 mate+0.412
Neg logit contributions
ipt-0.454
urious-0.408
aut-0.401
uct-0.398
Okay-0.398
Token.
Token ID13
Feature activation+1.29e-03

Pos logit contributions
 mate+0.270
 superheroes+0.263
 heroes+0.245
 soldiers+0.225
 pirates+0.219
Neg logit contributions
rated-0.345
aman-0.328
uct-0.326
appointed-0.324
ulously-0.322
Token They
Token ID1119
Feature activation+2.97e-02

Pos logit contributions
 mate+0.003
 superheroes+0.003
 heroes+0.003
 soldiers+0.002
e+0.002
Neg logit contributions
appointed-0.002
rated-0.002
ulously-0.002
uct-0.002
aman-0.002
Token dream
Token ID4320
Feature activation-4.14e-02

Pos logit contributions
 mate+0.039
 superheroes+0.039
 heroes+0.036
 soldiers+0.034
 spies+0.033
Neg logit contributions
rated-0.062
 inc-0.058
appointed-0.058
uct-0.057
ulously-0.057
Token of
Token ID286
Feature activation+1.86e-01

Pos logit contributions
rated+0.101
appointed+0.098
aman+0.095
ulously+0.095
uct+0.094
Neg logit contributions
 mate-0.043
 superheroes-0.040
 heroes-0.034
 pirates-0.032
 soldiers-0.032
Token
Token ID198
Feature activation+6.17e-02

Pos logit contributions
rated+0.010
ulously+0.009
appointed+0.009
esh+0.009
uct+0.009
Neg logit contributions
 superheroes-0.004
 mate-0.004
 heroes-0.004
 soldiers-0.003
 pirates-0.003
Token
Token ID198
Feature activation+6.29e-02

Pos logit contributions
 mate+0.086
 superheroes+0.085
 heroes+0.078
 soldiers+0.073
 pirates+0.069
Neg logit contributions
rated-0.130
appointed-0.127
uct-0.125
ulously-0.125
aman-0.124
TokenThey
Token ID2990
Feature activation+4.84e-02

Pos logit contributions
 mate+0.086
 superheroes+0.085
 heroes+0.078
 soldiers+0.073
 pirates+0.070
Neg logit contributions
rated-0.138
appointed-0.132
uct-0.130
ulously-0.129
esh-0.127
Token put
Token ID1234
Feature activation-5.48e-02

Pos logit contributions
 mate+0.096
 superheroes+0.095
 heroes+0.089
 soldiers+0.085
 pirates+0.083
Neg logit contributions
rated-0.076
appointed-0.073
uct-0.070
ulously-0.069
aman-0.069
Token the
Token ID262
Feature activation-6.72e-02

Pos logit contributions
rated+0.093
ulously+0.093
uct+0.090
ened+0.089
appointed+0.087
Neg logit contributions
 mate-0.098
 superheroes-0.094
 heroes-0.087
 spies-0.079
 soldiers-0.078
Token pizz
Token ID38748
Feature activation+3.10e-01

Pos logit contributions
rated+0.124
ulously+0.121
inct+0.119
 inc+0.115
aman+0.115
Neg logit contributions
 superheroes-0.095
 mate-0.088
izards-0.087
 heroes-0.081
 spies-0.073
Tokenas
Token ID292
Feature activation+1.83e-01

Pos logit contributions
 superheroes+0.429
 camping+0.349
 hunting+0.341
 mate+0.340
 Antarctica+0.337
Neg logit contributions
ipt-0.592
inct-0.577
ulously-0.571
urious-0.564
iped-0.556
Token in
Token ID287
Feature activation+4.74e-02

Pos logit contributions
 superheroes+0.290
 mate+0.287
 heroes+0.264
 soldiers+0.243
 pirates+0.236
Neg logit contributions
rated-0.347
appointed-0.332
ulously-0.329
uct-0.326
esh-0.325
Token the
Token ID262
Feature activation-6.71e-02

Pos logit contributions
 mate+0.087
 superheroes+0.087
 heroes+0.081
izards+0.079
 soldiers+0.073
Neg logit contributions
ulously-0.077
aman-0.075
rated-0.072
ened-0.071
appointed-0.071
Token oven
Token ID14361
Feature activation+3.09e-02

Pos logit contributions
rated+0.118
appointed+0.113
uct+0.110
esh+0.108
iously+0.107
Neg logit contributions
 mate-0.122
 superheroes-0.120
 heroes-0.116
 soldiers-0.114
 pirates-0.108
Token and
Token ID290
Feature activation-3.03e-03

Pos logit contributions
 mate+0.037
 superheroes+0.037
 heroes+0.034
 soldiers+0.033
 pirates+0.032
Neg logit contributions
rated-0.072
appointed-0.070
uct-0.069
ulously-0.069
esh-0.067
Token"
Token ID1
Feature activation-2.53e-02

Pos logit contributions
 mate+0.108
 superheroes+0.108
 heroes+0.102
 soldiers+0.097
 pirates+0.093
Neg logit contributions
rated-0.098
appointed-0.096
uct-0.094
ulously-0.093
aman-0.092
TokenMom
Token ID29252
Feature activation+9.18e-03

Pos logit contributions
rated+0.041
appointed+0.039
uct+0.038
ulously+0.038
aman+0.037
Neg logit contributions
 mate-0.049
 superheroes-0.048
 heroes-0.046
 soldiers-0.043
 pirates-0.042
Token,
Token ID11
Feature activation+6.83e-02

Pos logit contributions
 mate+0.011
 superheroes+0.010
 heroes+0.010
 soldiers+0.009
 pirates+0.008
Neg logit contributions
rated-0.022
appointed-0.021
uct-0.021
ulously-0.020
esh-0.020
Token are
Token ID389
Feature activation+1.70e-01

Pos logit contributions
 superheroes+0.113
 mate+0.110
 heroes+0.107
 soldiers+0.102
e+0.099
Neg logit contributions
rated-0.113
uct-0.109
ulously-0.108
aman-0.106
 inc-0.105
Token the
Token ID262
Feature activation-6.67e-02

Pos logit contributions
 mate+0.259
 superheroes+0.256
 heroes+0.236
aky+0.224
 soldiers+0.223
Neg logit contributions
uct-0.308
ulously-0.284
appointed-0.281
ths-0.278
arrass-0.274
Token pizz
Token ID38748
Feature activation+3.10e-01

Pos logit contributions
aman+0.114
inct+0.111
rated+0.111
ulously+0.110
 inc+0.108
Neg logit contributions
 superheroes-0.088
izards-0.083
 mate-0.081
e-0.079
 heroes-0.071
Tokenas
Token ID292
Feature activation+1.81e-01

Pos logit contributions
 superheroes+0.466
 hunting+0.400
 camping+0.399
 much+0.387
 Antarctica+0.377
Neg logit contributions
umm-0.432
ipt-0.432
uct-0.427
inct-0.419
Okay-0.416
Token ready
Token ID3492
Feature activation-5.78e-03

Pos logit contributions
 superheroes+0.298
 mate+0.293
 heroes+0.277
 soldiers+0.255
 dinosaurs+0.247
Neg logit contributions
rated-0.333
uct-0.309
appointed-0.306
aman-0.305
ulously-0.296
Token?"
Token ID1701
Feature activation+6.12e-03

Pos logit contributions
rated+0.013
appointed+0.012
ulously+0.012
uct+0.012
esh+0.012
Neg logit contributions
 mate-0.008
 superheroes-0.008
 heroes-0.007
 soldiers-0.007
 pirates-0.006
Token Lily
Token ID20037
Feature activation-1.70e-03

Pos logit contributions
 mate+0.009
 superheroes+0.009
 heroes+0.009
 soldiers+0.008
 pirates+0.008
Neg logit contributions
rated-0.012
appointed-0.012
uct-0.012
ulously-0.012
aman-0.011
Token asked
Token ID1965
Feature activation-9.12e-02

Pos logit contributions
rated+0.003
ulously+0.002
appointed+0.002
aman+0.002
esh+0.002
Neg logit contributions
 superheroes-0.003
 mate-0.003
 heroes-0.003
 soldiers-0.003
 pirates-0.003
Token they
Token ID484
Feature activation+9.31e-02

Pos logit contributions
 mate+0.117
 heroes+0.107
 superheroes+0.106
e+0.104
aky+0.104
Neg logit contributions
appointed-0.119
aman-0.118
uct-0.118
ulously-0.117
rated-0.116
Token put
Token ID1234
Feature activation-5.65e-02

Pos logit contributions
 mate+0.146
 superheroes+0.144
 heroes+0.135
 soldiers+0.126
 pirates+0.121
Neg logit contributions
rated-0.180
appointed-0.173
uct-0.170
ulously-0.169
aman-0.167
Token away
Token ID1497
Feature activation-5.16e-02

Pos logit contributions
rated+0.114
ulously+0.112
uct+0.110
appointed+0.110
ened+0.107
Neg logit contributions
 mate-0.083
 superheroes-0.081
 heroes-0.074
 soldiers-0.067
 pirates-0.064
Token their
Token ID511
Feature activation+1.20e-01

Pos logit contributions
rated+0.104
ulously+0.099
uct+0.099
appointed+0.098
aman+0.098
Neg logit contributions
 mate-0.077
 superheroes-0.073
 heroes-0.066
 soldiers-0.061
e-0.061
Token fake
Token ID8390
Feature activation-6.69e-03

Pos logit contributions
 mate+0.154
 superheroes+0.151
 heroes+0.136
izards+0.129
e+0.123
Neg logit contributions
rated-0.247
ulously-0.234
iously-0.232
appointed-0.231
uct-0.230
Token pizz
Token ID38748
Feature activation+3.10e-01

Pos logit contributions
rated+0.014
iously+0.013
ened+0.013
aman+0.013
ulously+0.013
Neg logit contributions
 mate-0.008
 superheroes-0.008
 heroes-0.007
 much-0.007
e-0.007
Tokenas
Token ID292
Feature activation+1.78e-01

Pos logit contributions
 superheroes+0.477
 Antarctica+0.384
 camping+0.383
 hunting+0.379
 soldiers+0.368
Neg logit contributions
ipt-0.530
urious-0.501
iped-0.491
Okay-0.482
aut-0.478
Token and
Token ID290
Feature activation+2.03e-03

Pos logit contributions
 superheroes+0.288
 mate+0.288
 heroes+0.269
 soldiers+0.246
 pirates+0.242
Neg logit contributions
rated-0.319
aman-0.307
uct-0.303
appointed-0.303
esh-0.298
Token hats
Token ID23910
Feature activation+4.69e-02

Pos logit contributions
 mate+0.003
 superheroes+0.003
 heroes+0.003
 soldiers+0.003
 pirates+0.003
Neg logit contributions
rated-0.004
appointed-0.004
uct-0.004
ulously-0.004
aman-0.004
Token.
Token ID13
Feature activation-4.41e-03

Pos logit contributions
 superheroes+0.072
 mate+0.072
 heroes+0.067
 soldiers+0.062
 pirates+0.060
Neg logit contributions
rated-0.091
appointed-0.087
uct-0.086
aman-0.085
ulously-0.085
Token They
Token ID1119
Feature activation+2.48e-02

Pos logit contributions
rated+0.008
appointed+0.008
uct+0.008
ulously+0.008
aman+0.008
Neg logit contributions
 mate-0.008
 superheroes-0.008
 heroes-0.007
 soldiers-0.007
 pirates-0.006
Token the
Token ID262
Feature activation-6.44e-02

Pos logit contributions
rated+0.098
aman+0.095
appointed+0.095
ulously+0.095
uct+0.095
Neg logit contributions
 mate-0.099
 superheroes-0.097
 heroes-0.093
 soldiers-0.086
 winners-0.082
Token kitchen
Token ID9592
Feature activation-1.84e-02

Pos logit contributions
rated+0.131
appointed+0.126
uct+0.124
ulously+0.123
aman+0.120
Neg logit contributions
 superheroes-0.100
 mate-0.098
 heroes-0.093
 soldiers-0.088
 pirates-0.085
Token and
Token ID290
Feature activation+2.48e-03

Pos logit contributions
rated+0.040
appointed+0.038
uct+0.038
ulously+0.038
aman+0.037
Neg logit contributions
 mate-0.026
 superheroes-0.025
 heroes-0.023
 soldiers-0.022
 pirates-0.021
Token saw
Token ID2497
Feature activation+3.96e-02

Pos logit contributions
 mate+0.005
 superheroes+0.005
 heroes+0.004
 soldiers+0.004
 pirates+0.004
Neg logit contributions
rated-0.004
appointed-0.004
uct-0.004
ulously-0.004
aman-0.004
Token their
Token ID511
Feature activation+1.19e-01

Pos logit contributions
 mate+0.069
 superheroes+0.063
e+0.058
 heroes+0.057
 queens+0.054
Neg logit contributions
ulously-0.067
rated-0.063
aman-0.063
uct-0.063
 inc-0.062
Token pizz
Token ID38748
Feature activation+3.10e-01

Pos logit contributions
 mate+0.188
 superheroes+0.183
 heroes+0.169
 soldiers+0.157
e+0.153
Neg logit contributions
rated-0.228
appointed-0.218
ulously-0.216
uct-0.213
aman-0.212
Tokenas
Token ID292
Feature activation+1.81e-01

Pos logit contributions
 superheroes+0.479
 mate+0.401
 Antarctica+0.395
 camping+0.392
 hunting+0.381
Neg logit contributions
ipt-0.545
urious-0.529
anked-0.509
inct-0.507
aut-0.499
Token.
Token ID13
Feature activation+6.25e-03

Pos logit contributions
 mate+0.270
 superheroes+0.267
 heroes+0.248
 soldiers+0.226
 pirates+0.218
Neg logit contributions
rated-0.361
appointed-0.347
uct-0.343
ulously-0.340
aman-0.339
Token They
Token ID1119
Feature activation+2.80e-02

Pos logit contributions
 mate+0.012
 superheroes+0.012
 heroes+0.012
 soldiers+0.011
e+0.011
Neg logit contributions
rated-0.009
appointed-0.009
uct-0.009
ulously-0.009
aman-0.009
Token smelled
Token ID37609
Feature activation+6.34e-02

Pos logit contributions
 mate+0.055
 superheroes+0.054
 heroes+0.052
 soldiers+0.049
 DVD+0.048
Neg logit contributions
 inc-0.040
rated-0.040
uct-0.038
ulously-0.037
appointed-0.037
Token good
Token ID922
Feature activation+9.56e-03

Pos logit contributions
 mate+0.118
 superheroes+0.110
 heroes+0.101
 queens+0.095
 loser+0.095
Neg logit contributions
rated-0.101
ened-0.100
ulously-0.099
 inc-0.098
uct-0.096
Token.
Token ID13
Feature activation-1.82e-03

Pos logit contributions
rated+0.007
appointed+0.007
uct+0.006
ulously+0.006
aman+0.006
Neg logit contributions
 mate-0.006
 superheroes-0.005
 heroes-0.005
 soldiers-0.005
 pirates-0.005
Token Let
Token ID3914
Feature activation-1.65e-01

Pos logit contributions
rated+0.003
appointed+0.003
uct+0.003
ulously+0.003
aman+0.003
Neg logit contributions
 mate-0.003
 superheroes-0.003
 heroes-0.003
 soldiers-0.003
 pirates-0.003
Token's
Token ID338
Feature activation+6.59e-02

Pos logit contributions
rated+0.392
appointed+0.386
iously+0.384
uct+0.370
esh+0.367
Neg logit contributions
 superheroes-0.181
 mate-0.178
 heroes-0.156
 soldiers-0.154
e-0.150
Token put
Token ID1234
Feature activation-5.48e-02

Pos logit contributions
 mate+0.102
 superheroes+0.101
 heroes+0.094
 soldiers+0.087
 pirates+0.086
Neg logit contributions
rated-0.131
appointed-0.126
uct-0.123
aman-0.123
ulously-0.122
Token the
Token ID262
Feature activation-6.45e-02

Pos logit contributions
ulously+0.094
uct+0.090
ened+0.088
rated+0.086
aman+0.085
Neg logit contributions
 mate-0.095
 superheroes-0.091
 heroes-0.084
 soldiers-0.075
 camping-0.075
Token pizz
Token ID38748
Feature activation+3.09e-01

Pos logit contributions
rated+0.110
ulously+0.107
inct+0.103
ened+0.101
 exp+0.100
Neg logit contributions
 superheroes-0.095
izards-0.092
 mate-0.091
 heroes-0.082
e-0.077
Tokenas
Token ID292
Feature activation+1.81e-01

Pos logit contributions
 superheroes+0.454
 camping+0.374
 villain+0.358
 hunting+0.355
 DVD+0.350
Neg logit contributions
ipt-0.541
urious-0.523
uct-0.523
inct-0.522
rated-0.517
Token in
Token ID287
Feature activation+4.63e-02

Pos logit contributions
 superheroes+0.296
 mate+0.292
 heroes+0.272
 soldiers+0.250
 tyrann+0.244
Neg logit contributions
rated-0.330
appointed-0.313
ulously-0.311
uct-0.309
esh-0.306
Token the
Token ID262
Feature activation-6.48e-02

Pos logit contributions
 mate+0.083
 superheroes+0.082
 heroes+0.078
izards+0.074
 soldiers+0.070
Neg logit contributions
ulously-0.075
aman-0.073
uct-0.070
esh-0.068
rated-0.067
Token oven
Token ID14361
Feature activation+2.94e-02

Pos logit contributions
rated+0.110
appointed+0.106
uct+0.103
ulously+0.102
aman+0.101
Neg logit contributions
 mate-0.119
 superheroes-0.118
 heroes-0.111
 soldiers-0.106
 pirates-0.103
Token and
Token ID290
Feature activation-4.86e-03

Pos logit contributions
 mate+0.040
 superheroes+0.039
 heroes+0.037
 soldiers+0.034
 pirates+0.033
Neg logit contributions
rated-0.064
appointed-0.062
uct-0.061
ulously-0.061
esh-0.060
Token They
Token ID1119
Feature activation+2.53e-02

Pos logit contributions
appointed+0.004
rated+0.004
uct+0.004
ulously+0.004
icol+0.004
Neg logit contributions
 mate-0.007
 superheroes-0.007
 heroes-0.007
prise-0.007
e-0.007
Token make
Token ID787
Feature activation-2.14e-02

Pos logit contributions
 superheroes+0.033
 mate+0.033
 heroes+0.031
 soldiers+0.030
uggets+0.028
Neg logit contributions
rated-0.052
 inc-0.049
uct-0.049
appointed-0.048
 exp-0.048
Token and
Token ID290
Feature activation+4.50e-03

Pos logit contributions
rated+0.046
ulously+0.046
appointed+0.045
uct+0.044
aman+0.044
Neg logit contributions
 mate-0.028
 superheroes-0.026
 heroes-0.024
 soldiers-0.021
e-0.021
Token sell
Token ID3677
Feature activation+9.98e-02

Pos logit contributions
 mate+0.007
 superheroes+0.006
 heroes+0.006
 soldiers+0.006
e+0.005
Neg logit contributions
rated-0.009
appointed-0.008
ulously-0.008
uct-0.008
 inc-0.008
Token many
Token ID867
Feature activation+8.28e-02

Pos logit contributions
 mate+0.185
 superheroes+0.167
 heroes+0.147
izards+0.145
aky+0.145
Neg logit contributions
ulously-0.164
ened-0.153
rated-0.153
uct-0.151
aman-0.147
Token pizz
Token ID38748
Feature activation+3.09e-01

Pos logit contributions
 mate+0.160
 superheroes+0.146
 loser+0.134
e+0.133
ancer+0.129
Neg logit contributions
ened-0.120
rated-0.119
ulously-0.119
urious-0.115
ised-0.109
Tokenas
Token ID292
Feature activation+1.77e-01

Pos logit contributions
 superheroes+0.484
 villain+0.415
 DVD+0.413
 camping+0.409
 mate+0.403
Neg logit contributions
ipt-0.459
urious-0.446
am-0.428
aut-0.428
ups-0.425
Token.
Token ID13
Feature activation-2.85e-03

Pos logit contributions
 superheroes+0.295
 mate+0.294
 heroes+0.267
 soldiers+0.243
 tyrann+0.239
Neg logit contributions
rated-0.300
esh-0.286
iously-0.283
uct-0.282
ened-0.281
Token They
Token ID1119
Feature activation+2.55e-02

Pos logit contributions
appointed+0.003
rated+0.003
uct+0.003
ulously+0.003
 However+0.003
Neg logit contributions
 mate-0.006
 superheroes-0.006
 heroes-0.006
e-0.006
 soldiers-0.006
Token have
Token ID423
Feature activation+1.43e-01

Pos logit contributions
 superheroes+0.035
 mate+0.034
 heroes+0.031
 soldiers+0.030
 spies+0.029
Neg logit contributions
rated-0.052
 inc-0.049
appointed-0.049
uct-0.049
ulously-0.048
Token fun
Token ID1257
Feature activation-2.71e-04

Pos logit contributions
 mate+0.172
 superheroes+0.164
 heroes+0.151
izards+0.140
 soldiers+0.139
Neg logit contributions
ulously-0.294
 inc-0.292
uct-0.290
rated-0.288
appointed-0.286
Token They
Token ID1119
Feature activation+1.90e-02

Pos logit contributions
rated+0.024
esh+0.023
ulously+0.022
appointed+0.022
uct+0.022
Neg logit contributions
 superheroes-0.016
 mate-0.016
 heroes-0.014
 soldiers-0.014
 pirates-0.014
Token wanted
Token ID2227
Feature activation-9.91e-02

Pos logit contributions
 mate+0.035
 superheroes+0.033
 heroes+0.031
 soldiers+0.029
 much+0.029
Neg logit contributions
esh-0.033
rated-0.033
aman-0.032
ulously-0.031
appointed-0.031
Token to
Token ID284
Feature activation-6.02e-02

Pos logit contributions
ulously+0.129
 inc+0.126
ened+0.123
iously+0.119
aman+0.118
Neg logit contributions
 mate-0.200
 superheroes-0.185
 heroes-0.179
aky-0.173
 winners-0.173
Token eat
Token ID4483
Feature activation+8.18e-02

Pos logit contributions
rated+0.111
appointed+0.108
ulously+0.107
uct+0.106
aman+0.104
Neg logit contributions
 superheroes-0.097
 mate-0.097
 heroes-0.092
 soldiers-0.086
 pirates-0.081
Token their
Token ID511
Feature activation+1.18e-01

Pos logit contributions
 mate+0.154
 superheroes+0.140
 heroes+0.135
 winners+0.123
 astronauts+0.122
Neg logit contributions
rated-0.125
ulously-0.124
uct-0.124
aman-0.123
 inc-0.120
Token pizz
Token ID38748
Feature activation+3.09e-01

Pos logit contributions
 mate+0.134
 superheroes+0.131
 heroes+0.116
 soldiers+0.099
 spies+0.097
Neg logit contributions
rated-0.273
ulously-0.266
appointed-0.262
iously-0.260
uct-0.259
Tokenas
Token ID292
Feature activation+1.79e-01

Pos logit contributions
 superheroes+0.490
 mate+0.419
 villain+0.408
 soldiers+0.403
 hunting+0.397
Neg logit contributions
urious-0.492
uct-0.489
aut-0.484
ipt-0.477
angle-0.468
Token right
Token ID826
Feature activation-1.29e-01

Pos logit contributions
 mate+0.295
 superheroes+0.290
 heroes+0.272
 soldiers+0.250
 pirates+0.241
Neg logit contributions
rated-0.324
uct-0.310
aman-0.307
appointed-0.306
ulously-0.301
Token away
Token ID1497
Feature activation-5.12e-02

Pos logit contributions
appointed+0.234
rated+0.229
aman+0.228
 inc+0.228
uct+0.227
Neg logit contributions
 mate-0.210
 superheroes-0.205
 heroes-0.196
 pirates-0.189
 soldiers-0.182
Token.
Token ID13
Feature activation-7.53e-03

Pos logit contributions
rated+0.090
iously+0.085
aman+0.084
appointed+0.084
uct+0.083
Neg logit contributions
 mate-0.087
 superheroes-0.085
 heroes-0.078
 soldiers-0.075
 tyrann-0.071
Token
Token ID198
Feature activation+5.70e-02

Pos logit contributions
rated+0.015
appointed+0.014
esh+0.014
ulously+0.014
uct+0.014
Neg logit contributions
 mate-0.012
 superheroes-0.012
 heroes-0.011
 soldiers-0.010
 pirates-0.010
Token a
Token ID257
Feature activation+1.16e-01

Pos logit contributions
 mate+0.156
 superheroes+0.144
 heroes+0.143
aky+0.135
 winners+0.133
Neg logit contributions
 inc-0.125
iously-0.124
ulously-0.123
uct-0.122
aman-0.122
Token little
Token ID1310
Feature activation-4.41e-02

Pos logit contributions
izards+0.195
 superheroes+0.195
 heroes+0.184
e+0.183
 mate+0.183
Neg logit contributions
rated-0.192
aman-0.182
 inc-0.174
arrass-0.173
 exp-0.170
Token while
Token ID981
Feature activation+4.86e-03

Pos logit contributions
rated+0.086
appointed+0.080
aman+0.078
iously+0.078
ulously+0.077
Neg logit contributions
 mate-0.068
 superheroes-0.067
 heroes-0.062
 soldiers-0.058
e-0.056
Token until
Token ID1566
Feature activation-7.15e-02

Pos logit contributions
 mate+0.008
 superheroes+0.008
 heroes+0.007
 soldiers+0.007
 winners+0.006
Neg logit contributions
rated-0.009
appointed-0.008
iously-0.008
uct-0.008
aman-0.008
Token the
Token ID262
Feature activation-7.17e-02

Pos logit contributions
rated+0.149
appointed+0.144
uct+0.141
ulously+0.141
aman+0.139
Neg logit contributions
 mate-0.103
 superheroes-0.102
 heroes-0.094
 soldiers-0.089
 pirates-0.085
Token pizz
Token ID38748
Feature activation+3.08e-01

Pos logit contributions
rated+0.142
appointed+0.134
ulously+0.132
inct+0.131
uct+0.130
Neg logit contributions
 superheroes-0.104
 mate-0.103
 heroes-0.093
izards-0.086
e-0.085
Tokenas
Token ID292
Feature activation+1.79e-01

Pos logit contributions
 superheroes+0.460
 mate+0.369
 heroes+0.369
 camping+0.364
 hunting+0.359
Neg logit contributions
uct-0.549
rated-0.549
urious-0.540
inct-0.533
aman-0.533
Token were
Token ID547
Feature activation+1.15e-01

Pos logit contributions
 mate+0.299
 superheroes+0.293
 heroes+0.273
 soldiers+0.262
 pirates+0.253
Neg logit contributions
rated-0.328
appointed-0.323
ulously-0.313
uct-0.311
esh-0.307
Token cooked
Token ID15847
Feature activation+4.49e-02

Pos logit contributions
 mate+0.169
 superheroes+0.162
 heroes+0.150
e+0.137
 soldiers+0.135
Neg logit contributions
rated-0.224
uct-0.221
appointed-0.217
 inc-0.204
iously-0.204
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
 mate+0.068
 superheroes+0.067
 heroes+0.062
 soldiers+0.057
 pirates+0.055
Neg logit contributions
rated-0.090
appointed-0.085
uct-0.084
ulously-0.084
aman-0.083
Token Lily
Token ID20037
Feature activation-8.72e-03

Pos logit contributions
rated+0.030
esh+0.028
ulously+0.027
iously+0.027
 inc+0.027
Neg logit contributions
 superheroes-0.014
 mate-0.013
 much-0.012
 soldiers-0.012
 heroes-0.012
Token
Token ID198
Feature activation+6.67e-02

Pos logit contributions
 mate+0.108
 superheroes+0.106
 heroes+0.097
 soldiers+0.091
 pirates+0.087
Neg logit contributions
appointed-0.120
rated-0.119
ulously-0.119
uct-0.117
esh-0.116
TokenThey
Token ID2990
Feature activation+4.47e-02

Pos logit contributions
 mate+0.113
 superheroes+0.113
 heroes+0.104
 soldiers+0.098
 camping+0.097
Neg logit contributions
appointed-0.115
rated-0.113
ulously-0.112
uct-0.111
aman-0.110
Token all
Token ID477
Feature activation-2.12e-02

Pos logit contributions
 mate+0.088
 superheroes+0.087
 heroes+0.083
 soldiers+0.079
 pirates+0.076
Neg logit contributions
rated-0.068
appointed-0.064
uct-0.064
ulously-0.063
aman-0.062
Token ate
Token ID15063
Feature activation+1.82e-02

Pos logit contributions
rated+0.035
appointed+0.034
aman+0.034
ulously+0.032
esh+0.032
Neg logit contributions
 mate-0.039
 superheroes-0.039
 heroes-0.037
 soldiers-0.035
 pirates-0.034
Token their
Token ID511
Feature activation+1.18e-01

Pos logit contributions
 mate+0.029
 superheroes+0.027
 heroes+0.025
 soldiers+0.023
e+0.022
Neg logit contributions
rated-0.034
ulously-0.034
uct-0.033
aman-0.033
appointed-0.033
Token pizz
Token ID38748
Feature activation+3.08e-01

Pos logit contributions
 superheroes+0.148
 mate+0.148
 heroes+0.129
 spies+0.114
 astronauts+0.112
Neg logit contributions
rated-0.261
ulously-0.255
iously-0.246
uct-0.245
appointed-0.243
Tokenas
Token ID292
Feature activation+1.79e-01

Pos logit contributions
 superheroes+0.475
 mate+0.408
 camping+0.396
 hunting+0.387
 Antarctica+0.384
Neg logit contributions
ipt-0.545
urious-0.514
iped-0.501
ulously-0.501
anked-0.494
Token and
Token ID290
Feature activation+3.17e-03

Pos logit contributions
 mate+0.314
 superheroes+0.304
 heroes+0.279
 soldiers+0.256
 spies+0.252
Neg logit contributions
rated-0.311
uct-0.297
ulously-0.296
appointed-0.295
iously-0.291
Token they
Token ID484
Feature activation+8.98e-02

Pos logit contributions
 mate+0.006
 superheroes+0.006
 heroes+0.005
 soldiers+0.005
 camping+0.005
Neg logit contributions
rated-0.005
ulously-0.005
uct-0.005
appointed-0.005
 inc-0.005
Token were
Token ID547
Feature activation+1.17e-01

Pos logit contributions
 mate+0.169
 superheroes+0.167
 heroes+0.157
 soldiers+0.150
 spies+0.145
Neg logit contributions
rated-0.142
uct-0.135
appointed-0.134
ulously-0.134
 inc-0.132
Token very
Token ID845
Feature activation+1.37e-01

Pos logit contributions
 mate+0.166
 superheroes+0.150
 soldiers+0.126
izards+0.126
 rook+0.125
Neg logit contributions
uct-0.236
appointed-0.231
ulously-0.227
rated-0.224
iped-0.212
Token came
Token ID1625
Feature activation+4.14e-02

Pos logit contributions
 mate+0.110
 superheroes+0.108
 heroes+0.102
 soldiers+0.095
 pirates+0.092
Neg logit contributions
rated-0.123
appointed-0.117
uct-0.115
ulously-0.115
aman-0.114
Token back
Token ID736
Feature activation+1.08e-02

Pos logit contributions
 mate+0.087
 superheroes+0.083
prise+0.079
 heroes+0.077
 liar+0.077
Neg logit contributions
urious-0.048
rated-0.047
appointed-0.047
ulously-0.047
ened-0.046
Token with
Token ID351
Feature activation+5.66e-02

Pos logit contributions
 mate+0.018
 superheroes+0.016
 heroes+0.015
 soldiers+0.014
 pirates+0.013
Neg logit contributions
rated-0.020
appointed-0.019
aman-0.019
ulously-0.019
uct-0.019
Token two
Token ID734
Feature activation+4.43e-02

Pos logit contributions
 mate+0.093
 superheroes+0.083
izards+0.079
 heroes+0.079
ancer+0.079
Neg logit contributions
ened-0.095
ulously-0.094
 inc-0.091
uct-0.088
aman-0.088
Token big
Token ID1263
Feature activation+3.04e-02

Pos logit contributions
 mate+0.076
 superheroes+0.071
 Antarctica+0.064
 heroes+0.062
izards+0.062
Neg logit contributions
ened-0.075
rated-0.072
urious-0.071
 inc-0.071
iously-0.071
Token pizz
Token ID38748
Feature activation+3.08e-01

Pos logit contributions
 mate+0.051
 superheroes+0.049
 heroes+0.046
 much+0.042
 queens+0.041
Neg logit contributions
ened-0.052
rated-0.052
ulously-0.050
 inc-0.049
iously-0.049
Tokenas
Token ID292
Feature activation+1.78e-01

Pos logit contributions
 superheroes+0.478
 camping+0.421
 Antarctica+0.410
 DVD+0.381
 hunting+0.379
Neg logit contributions
ipt-0.497
urious-0.481
iped-0.453
aut-0.447
anked-0.437
Token.
Token ID13
Feature activation+6.69e-03

Pos logit contributions
 mate+0.274
 superheroes+0.274
 heroes+0.254
 soldiers+0.232
 pirates+0.226
Neg logit contributions
rated-0.336
appointed-0.321
uct-0.319
aman-0.317
ulously-0.316
Token She
Token ID1375
Feature activation-8.29e-02

Pos logit contributions
 mate+0.015
 superheroes+0.015
 heroes+0.015
e+0.014
 camping+0.014
Neg logit contributions
uct-0.007
appointed-0.007
aman-0.007
rated-0.007
ulously-0.007
Token put
Token ID1234
Feature activation-5.90e-02

Pos logit contributions
rated+0.132
appointed+0.124
uct+0.124
ulously+0.123
aman+0.120
Neg logit contributions
 mate-0.158
 superheroes-0.156
 heroes-0.148
 soldiers-0.140
 pirates-0.134
Token them
Token ID606
Feature activation+1.02e-01

Pos logit contributions
ulously+0.108
ened+0.106
uct+0.103
iped+0.101
aman+0.100
Neg logit contributions
 mate-0.095
 superheroes-0.094
 heroes-0.087
 camping-0.077
 astronauts-0.076
Token you
Token ID345
Feature activation+5.86e-02

Pos logit contributions
rated+0.171
appointed+0.167
uct+0.166
aman+0.165
ulously+0.165
Neg logit contributions
 mate-0.124
 superheroes-0.121
 heroes-0.111
 soldiers-0.103
 pirates-0.098
Token go
Token ID467
Feature activation-1.83e-02

Pos logit contributions
 superheroes+0.107
 mate+0.105
 heroes+0.100
 soldiers+0.093
 camping+0.092
Neg logit contributions
rated-0.095
ulously-0.091
appointed-0.088
uct-0.086
urious-0.086
Token,
Token ID11
Feature activation+6.71e-02

Pos logit contributions
rated+0.036
appointed+0.035
ulously+0.034
uct+0.034
aman+0.034
Neg logit contributions
 superheroes-0.028
 mate-0.028
 heroes-0.025
 soldiers-0.023
 pirates-0.022
Token enjoy
Token ID2883
Feature activation+6.10e-02

Pos logit contributions
 superheroes+0.106
 heroes+0.096
 mate+0.095
 camping+0.090
aky+0.088
Neg logit contributions
uct-0.114
aman-0.112
ulously-0.109
iously-0.108
rated-0.108
Token your
Token ID534
Feature activation+4.27e-02

Pos logit contributions
 mate+0.100
 superheroes+0.096
 heroes+0.091
 soldiers+0.083
 DVD+0.080
Neg logit contributions
aman-0.103
uct-0.102
ulously-0.100
esh-0.097
iously-0.097
Token pizz
Token ID38748
Feature activation+3.07e-01

Pos logit contributions
 mate+0.045
 superheroes+0.044
 heroes+0.038
izards+0.034
 queens+0.033
Neg logit contributions
rated-0.102
appointed-0.095
ulously-0.095
uct-0.094
iously-0.094
Tokenas
Token ID292
Feature activation+1.78e-01

Pos logit contributions
 superheroes+0.499
 camping+0.402
 hunting+0.388
 villain+0.383
 Antarctica+0.379
Neg logit contributions
ipt-0.471
urious-0.467
aut-0.445
iped-0.444
rated-0.438
Token."
Token ID526
Feature activation-7.58e-03

Pos logit contributions
 superheroes+0.305
 mate+0.301
 heroes+0.281
 soldiers+0.259
 astronauts+0.252
Neg logit contributions
rated-0.295
appointed-0.273
uct-0.272
aman-0.272
esh-0.270
Token
Token ID198
Feature activation+6.62e-02

Pos logit contributions
aman+0.012
appointed+0.012
uct+0.012
 inc+0.012
ulously+0.011
Neg logit contributions
 mate-0.014
 superheroes-0.013
 heroes-0.013
 soldiers-0.012
e-0.012
Token
Token ID198
Feature activation+6.75e-02

Pos logit contributions
 mate+0.105
 superheroes+0.102
 heroes+0.095
 soldiers+0.090
 pirates+0.085
Neg logit contributions
appointed-0.124
rated-0.124
ulously-0.122
uct-0.122
aman-0.121
Token"
Token ID1
Feature activation-2.43e-02

Pos logit contributions
 mate+0.121
 superheroes+0.120
 heroes+0.112
 soldiers+0.108
 camping+0.104
Neg logit contributions
appointed-0.112
aman-0.109
uct-0.108
rated-0.107
ulously-0.107
Token wall
Token ID3355
Feature activation-6.26e-02

Pos logit contributions
rated+0.080
appointed+0.075
ulously+0.073
aman+0.072
 exp+0.071
Neg logit contributions
 superheroes-0.140
 mate-0.135
 heroes-0.131
izards-0.125
 winners-0.120
Token with
Token ID351
Feature activation+6.03e-02

Pos logit contributions
rated+0.126
appointed+0.122
uct+0.120
ulously+0.119
aman+0.118
Neg logit contributions
 superheroes-0.092
 mate-0.092
 heroes-0.085
 soldiers-0.079
 pirates-0.075
Token pictures
Token ID5986
Feature activation+2.58e-02

Pos logit contributions
 superheroes+0.081
 mate+0.079
 heroes+0.072
 loser+0.066
ancer+0.065
Neg logit contributions
ulously-0.122
ened-0.117
 inc-0.114
aman-0.112
iped-0.112
Token of
Token ID286
Feature activation+1.84e-01

Pos logit contributions
 superheroes+0.039
 mate+0.039
 heroes+0.036
 soldiers+0.032
e+0.031
Neg logit contributions
rated-0.047
uct-0.046
appointed-0.046
esh-0.045
ulously-0.045
Token different
Token ID1180
Feature activation+3.33e-02

Pos logit contributions
 mate+0.280
 superheroes+0.257
 loser+0.245
aky+0.240
 heroes+0.239
Neg logit contributions
ulously-0.312
aman-0.312
 inc-0.306
ened-0.292
iously-0.288
Token pizz
Token ID38748
Feature activation+3.07e-01

Pos logit contributions
 mate+0.064
 superheroes+0.063
 heroes+0.059
 soldiers+0.054
 spies+0.053
Neg logit contributions
rated-0.053
ulously-0.049
ened-0.049
appointed-0.048
iously-0.047
Tokenas
Token ID292
Feature activation+1.78e-01

Pos logit contributions
 superheroes+0.519
 villain+0.448
 DVD+0.440
 mate+0.416
 camping+0.413
Neg logit contributions
urious-0.456
aut-0.434
ipt-0.425
am-0.419
rated-0.411
Token.
Token ID13
Feature activation-1.03e-03

Pos logit contributions
 mate+0.263
 superheroes+0.261
 heroes+0.243
 soldiers+0.225
 pirates+0.216
Neg logit contributions
rated-0.356
appointed-0.342
uct-0.338
ulously-0.336
aman-0.334
Token Tom
Token ID4186
Feature activation+5.72e-02

Pos logit contributions
rated+0.002
appointed+0.002
uct+0.002
ulously+0.002
aman+0.002
Neg logit contributions
 mate-0.001
 superheroes-0.001
 heroes-0.001
 soldiers-0.001
 pirates-0.001
Token and
Token ID290
Feature activation-7.45e-03

Pos logit contributions
 superheroes+0.095
 mate+0.094
 heroes+0.089
 soldiers+0.084
 pirates+0.083
Neg logit contributions
rated-0.108
appointed-0.104
aman-0.101
ulously-0.101
uct-0.101
Token Anna
Token ID11735
Feature activation+6.16e-02

Pos logit contributions
rated+0.018
appointed+0.018
uct+0.017
ulously+0.017
aman+0.017
Neg logit contributions
 mate-0.008
 superheroes-0.008
 heroes-0.007
 soldiers-0.007
 pirates-0.006
Token done
Token ID1760
Feature activation-1.67e-02

Pos logit contributions
 mate+0.248
 superheroes+0.237
 heroes+0.229
 soldiers+0.212
 tyrann+0.207
Neg logit contributions
uct-0.158
appointed-0.146
rated-0.138
 inc-0.133
aman-0.131
Token,
Token ID11
Feature activation+6.30e-02

Pos logit contributions
aman+0.029
esh+0.029
ened+0.029
iously+0.028
 inc+0.028
Neg logit contributions
 mate-0.028
 superheroes-0.026
 heroes-0.025
aky-0.023
 soldiers-0.021
Token Mom
Token ID11254
Feature activation-4.44e-02

Pos logit contributions
 mate+0.104
 superheroes+0.100
 heroes+0.096
 soldiers+0.088
e+0.086
Neg logit contributions
rated-0.114
appointed-0.112
uct-0.111
ulously-0.110
aman-0.109
Token put
Token ID1234
Feature activation-5.89e-02

Pos logit contributions
rated+0.081
appointed+0.079
ulously+0.075
uct+0.074
aman+0.074
Neg logit contributions
 superheroes-0.076
 mate-0.075
 heroes-0.071
 soldiers-0.068
 pirates-0.066
Token the
Token ID262
Feature activation-6.81e-02

Pos logit contributions
ulously+0.106
ened+0.104
rated+0.103
uct+0.101
iped+0.098
Neg logit contributions
 mate-0.101
 superheroes-0.095
 heroes-0.089
 astronauts-0.078
 spies-0.078
Token pizz
Token ID38748
Feature activation+3.06e-01

Pos logit contributions
rated+0.127
ulously+0.121
 inc+0.116
inct+0.116
appointed+0.115
Neg logit contributions
 mate-0.104
 superheroes-0.103
 heroes-0.095
izards-0.088
 astronauts-0.083
Tokenas
Token ID292
Feature activation+1.77e-01

Pos logit contributions
 superheroes+0.445
 camping+0.368
 mate+0.354
 Antarctica+0.353
 hunting+0.343
Neg logit contributions
ipt-0.531
inct-0.522
urious-0.520
iped-0.518
ulously-0.517
Token in
Token ID287
Feature activation+4.27e-02

Pos logit contributions
 mate+0.235
 superheroes+0.234
 heroes+0.213
 soldiers+0.189
 spies+0.182
Neg logit contributions
rated-0.375
appointed-0.359
ulously-0.359
uct-0.358
esh-0.353
Token the
Token ID262
Feature activation-6.85e-02

Pos logit contributions
 mate+0.073
 superheroes+0.072
 heroes+0.069
izards+0.064
 soldiers+0.060
Neg logit contributions
ulously-0.075
aman-0.072
ened-0.071
uct-0.069
rated-0.069
Token oven
Token ID14361
Feature activation+2.55e-02

Pos logit contributions
rated+0.124
appointed+0.120
uct+0.117
aman+0.115
ulously+0.115
Neg logit contributions
 mate-0.118
 superheroes-0.116
 heroes-0.110
 soldiers-0.108
 pirates-0.103
Token.
Token ID13
Feature activation-6.38e-03

Pos logit contributions
 mate+0.027
 superheroes+0.027
 heroes+0.025
 soldiers+0.025
 pirates+0.023
Neg logit contributions
rated-0.062
appointed-0.061
uct-0.060
ulously-0.059
esh-0.058
Token pizza
Token ID14256
Feature activation+2.45e-01

Pos logit contributions
rated+0.055
uct+0.053
ulously+0.053
appointed+0.053
aman+0.052
Neg logit contributions
 mate-0.036
 superheroes-0.034
 heroes-0.032
 soldiers-0.029
 pirates-0.027
Token.
Token ID13
Feature activation+1.15e-03

Pos logit contributions
 superheroes+0.416
 mate+0.416
 heroes+0.376
 soldiers+0.356
e+0.344
Neg logit contributions
rated-0.428
uct-0.385
appointed-0.384
esh-0.381
ulously-0.380
Token They
Token ID1119
Feature activation+2.35e-02

Pos logit contributions
 mate+0.001
 superheroes+0.001
 heroes+0.001
 pirates+0.001
 soldiers+0.001
Neg logit contributions
rated-0.003
iously-0.003
appointed-0.003
uct-0.003
ulously-0.003
Token cut
Token ID2005
Feature activation-1.03e-02

Pos logit contributions
 mate+0.043
 superheroes+0.042
 heroes+0.040
 soldiers+0.038
 pirates+0.036
Neg logit contributions
rated-0.040
appointed-0.038
uct-0.037
ulously-0.037
aman-0.037
Token their
Token ID511
Feature activation+1.20e-01

Pos logit contributions
ulously+0.020
rated+0.019
ened+0.019
iped+0.019
aman+0.018
Neg logit contributions
 mate-0.016
 superheroes-0.016
 heroes-0.015
 winners-0.013
 camping-0.013
Token pizz
Token ID38748
Feature activation+3.06e-01

Pos logit contributions
 superheroes+0.196
 mate+0.195
 heroes+0.181
 soldiers+0.164
 spies+0.160
Neg logit contributions
rated-0.226
ulously-0.216
appointed-0.214
uct-0.209
iously-0.208
Tokenas
Token ID292
Feature activation+1.77e-01

Pos logit contributions
 superheroes+0.465
 mate+0.373
 camping+0.364
 villain+0.358
 heroes+0.353
Neg logit contributions
urious-0.556
ipt-0.556
ulously-0.555
inct-0.554
iped-0.549
Token into
Token ID656
Feature activation-1.75e-02

Pos logit contributions
 superheroes+0.287
 mate+0.284
 heroes+0.265
 soldiers+0.241
 pirates+0.234
Neg logit contributions
rated-0.331
appointed-0.318
ulously-0.314
uct-0.313
aman-0.311
Token slices
Token ID24314
Feature activation+1.06e-01

Pos logit contributions
ulously+0.028
ened+0.027
 inc+0.026
aman+0.025
rated+0.025
Neg logit contributions
 superheroes-0.030
 mate-0.029
 heroes-0.028
izards-0.028
 camping-0.026
Token.
Token ID13
Feature activation+2.65e-03

Pos logit contributions
 superheroes+0.208
 mate+0.198
 heroes+0.191
 soldiers+0.173
 tyrann+0.169
Neg logit contributions
rated-0.161
uct-0.156
appointed-0.154
aman-0.152
ulously-0.149
Token They
Token ID1119
Feature activation+2.61e-02

Pos logit contributions
 mate+0.005
 superheroes+0.005
 heroes+0.005
 soldiers+0.004
 pirates+0.004
Neg logit contributions
rated-0.004
appointed-0.004
uct-0.004
ulously-0.004
aman-0.004
Token dropped
Token ID5710
Feature activation-1.18e-02

Pos logit contributions
rated+0.029
appointed+0.028
aman+0.028
uct+0.027
esh+0.027
Neg logit contributions
 superheroes-0.030
 mate-0.030
 heroes-0.028
 soldiers-0.027
 pirates-0.026
Token the
Token ID262
Feature activation-6.38e-02

Pos logit contributions
rated+0.021
ulously+0.021
uct+0.020
ened+0.020
appointed+0.020
Neg logit contributions
 mate-0.020
 superheroes-0.019
 heroes-0.018
 soldiers-0.016
 camping-0.016
Token tray
Token ID26473
Feature activation+6.10e-02

Pos logit contributions
rated+0.100
ened+0.094
aman+0.094
inct+0.093
ulously+0.092
Neg logit contributions
 superheroes-0.113
 mate-0.108
 heroes-0.105
 much-0.094
 queens-0.093
Token and
Token ID290
Feature activation+2.07e-03

Pos logit contributions
 mate+0.096
 superheroes+0.096
 heroes+0.089
 soldiers+0.082
 pirates+0.080
Neg logit contributions
rated-0.117
appointed-0.113
uct-0.111
ulously-0.111
aman-0.109
Token the
Token ID262
Feature activation-6.37e-02

Pos logit contributions
 superheroes+0.004
 mate+0.003
 soldiers+0.003
 heroes+0.003
 pirates+0.003
Neg logit contributions
rated-0.004
appointed-0.004
aman-0.004
urious-0.004
uct-0.004
Token pizz
Token ID38748
Feature activation+3.06e-01

Pos logit contributions
rated+0.115
ulously+0.108
appointed+0.106
aman+0.106
 inc+0.106
Neg logit contributions
 mate-0.101
 superheroes-0.101
 heroes-0.094
 camping-0.084
 soldiers-0.083
Tokenas
Token ID292
Feature activation+1.74e-01

Pos logit contributions
 superheroes+0.451
 camping+0.385
 hunting+0.358
 Antarctica+0.353
 dinosaurs+0.352
Neg logit contributions
ipt-0.561
iped-0.559
inct-0.545
anked-0.540
uct-0.536
Token fell
Token ID3214
Feature activation-9.89e-03

Pos logit contributions
 mate+0.241
 superheroes+0.238
 heroes+0.220
 soldiers+0.206
 pirates+0.197
Neg logit contributions
rated-0.371
appointed-0.359
uct-0.352
ulously-0.352
aman-0.348
Token on
Token ID319
Feature activation+5.00e-02

Pos logit contributions
rated+0.020
uct+0.020
appointed+0.019
aman+0.019
ulously+0.019
Neg logit contributions
 mate-0.015
 superheroes-0.015
 heroes-0.014
 soldiers-0.013
 pirates-0.012
Token the
Token ID262
Feature activation-6.40e-02

Pos logit contributions
 mate+0.081
 superheroes+0.080
 heroes+0.075
 soldiers+0.069
 pirates+0.066
Neg logit contributions
rated-0.093
appointed-0.090
ulously-0.090
uct-0.089
aman-0.088
Token floor
Token ID4314
Feature activation-6.10e-02

Pos logit contributions
rated+0.072
appointed+0.066
ulously+0.064
uct+0.064
aman+0.062
Neg logit contributions
 mate-0.153
 superheroes-0.153
 heroes-0.146
 soldiers-0.139
 pirates-0.137
Token the
Token ID262
Feature activation-6.30e-02

Pos logit contributions
 mate+0.079
 superheroes+0.079
 heroes+0.073
 soldiers+0.068
 pirates+0.066
Neg logit contributions
rated-0.105
appointed-0.101
uct-0.099
ulously-0.099
aman-0.098
Token door
Token ID3420
Feature activation-6.55e-02

Pos logit contributions
rated+0.061
inct+0.057
appointed+0.055
 exp+0.055
uct+0.055
Neg logit contributions
 superheroes-0.151
 mate-0.151
 heroes-0.141
e-0.139
izards-0.134
Token and
Token ID290
Feature activation-7.32e-05

Pos logit contributions
rated+0.141
appointed+0.137
uct+0.136
ulously+0.135
aman+0.133
Neg logit contributions
 mate-0.090
 superheroes-0.087
 heroes-0.081
 soldiers-0.075
 pirates-0.072
Token give
Token ID1577
Feature activation+1.87e-02

Pos logit contributions
rated+0.000
appointed+0.000
uct+0.000
ulously+0.000
aman+0.000
Neg logit contributions
 mate-0.000
 superheroes-0.000
 heroes-0.000
 soldiers-0.000
 pirates-0.000
Token the
Token ID262
Feature activation-6.37e-02

Pos logit contributions
 mate+0.029
 superheroes+0.029
 heroes+0.027
 soldiers+0.025
 pirates+0.024
Neg logit contributions
rated-0.037
appointed-0.035
uct-0.035
ulously-0.035
aman-0.034
Token pizz
Token ID38748
Feature activation+3.06e-01

Pos logit contributions
inct+0.101
 inc+0.100
rated+0.098
arrass+0.094
aman+0.093
Neg logit contributions
 superheroes-0.095
e-0.088
izards-0.088
 mate-0.087
aky-0.084
Tokenas
Token ID292
Feature activation+1.76e-01

Pos logit contributions
 superheroes+0.462
 camping+0.363
 DVD+0.351
 hunting+0.350
e+0.349
Neg logit contributions
inct-0.507
rated-0.503
ipt-0.502
urious-0.488
uct-0.468
Token to
Token ID284
Feature activation-6.30e-02

Pos logit contributions
 superheroes+0.288
 mate+0.274
 heroes+0.263
 soldiers+0.242
 pirates+0.236
Neg logit contributions
rated-0.324
appointed-0.304
uct-0.301
ulously-0.300
esh-0.299
Token the
Token ID262
Feature activation-6.38e-02

Pos logit contributions
uct+0.097
rated+0.096
aman+0.095
ulously+0.094
appointed+0.090
Neg logit contributions
 superheroes-0.110
 mate-0.109
 heroes-0.106
 soldiers-0.098
 winners-0.096
Token people
Token ID661
Feature activation+5.07e-02

Pos logit contributions
rated+0.113
inct+0.107
aman+0.107
appointed+0.107
ulously+0.105
Neg logit contributions
 mate-0.095
 superheroes-0.095
e-0.086
 heroes-0.085
izards-0.083
Token."
Token ID526
Feature activation-9.62e-03

Pos logit contributions
 superheroes+0.084
 mate+0.079
 heroes+0.077
 soldiers+0.072
 tyrann+0.071
Neg logit contributions
rated-0.088
uct-0.081
appointed-0.080
aman-0.079
esh-0.077
Token little
Token ID1310
Feature activation-5.45e-02

Pos logit contributions
rated+0.143
appointed+0.140
uct+0.136
ulously+0.134
esh+0.132
Neg logit contributions
 mate-0.102
 superheroes-0.098
 heroes-0.091
 soldiers-0.085
 pirates-0.084
Token,
Token ID11
Feature activation+4.99e-02

Pos logit contributions
rated+0.106
appointed+0.102
uct+0.101
ulously+0.100
esh+0.099
Neg logit contributions
 mate-0.086
 superheroes-0.086
 heroes-0.080
 soldiers-0.076
 pirates-0.073
Token the
Token ID262
Feature activation-7.69e-02

Pos logit contributions
 superheroes+0.080
 mate+0.080
 heroes+0.074
 soldiers+0.069
 pirates+0.067
Neg logit contributions
rated-0.096
appointed-0.092
uct-0.090
ulously-0.090
esh-0.089
Token little
Token ID1310
Feature activation-5.52e-02

Pos logit contributions
rated+0.121
appointed+0.115
aman+0.114
uct+0.113
ulously+0.112
Neg logit contributions
 mate-0.148
 superheroes-0.147
 heroes-0.138
 soldiers-0.130
 pirates-0.127
Token boy
Token ID2933
Feature activation-3.18e-02

Pos logit contributions
rated+0.097
appointed+0.094
uct+0.093
ulously+0.090
esh+0.087
Neg logit contributions
 mate-0.102
 superheroes-0.100
 heroes-0.095
 soldiers-0.090
 pirates-0.090
Token inc
Token ID753
Feature activation-3.08e-01

Pos logit contributions
rated+0.069
appointed+0.066
uct+0.063
aman+0.062
esh+0.062
Neg logit contributions
 superheroes-0.045
 mate-0.045
e-0.043
 heroes-0.042
 pirates-0.040
Tokenhed
Token ID704
Feature activation+1.09e-02

Pos logit contributions
rated+0.591
aman+0.556
appointed+0.556
iously+0.556
arrass+0.551
Neg logit contributions
e-0.450
 superheroes-0.438
 mate-0.435
 heroes-0.411
 soldiers-0.399
Token closer
Token ID5699
Feature activation-3.19e-02

Pos logit contributions
 mate+0.017
 superheroes+0.017
 heroes+0.015
 soldiers+0.014
 dinosaurs+0.014
Neg logit contributions
rated-0.021
appointed-0.020
ulously-0.020
uct-0.020
esh-0.020
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
rated+0.071
appointed+0.068
uct+0.068
ulously+0.068
aman+0.066
Neg logit contributions
 mate-0.042
 superheroes-0.041
 heroes-0.038
 soldiers-0.035
 pirates-0.034
Token Very
Token ID9576
Feature activation-4.00e-02

Pos logit contributions
rated+0.040
esh+0.037
ulously+0.036
uct+0.035
 inc+0.035
Neg logit contributions
 superheroes-0.033
 mate-0.033
 much-0.031
 heroes-0.031
 soldiers-0.029
Token soon
Token ID2582
Feature activation-7.42e-02

Pos logit contributions
rated+0.074
appointed+0.070
esh+0.070
ulously+0.070
iped+0.069
Neg logit contributions
 mate-0.065
 superheroes-0.065
 heroes-0.062
 much-0.059
 pirates-0.056
Token from
Token ID422
Feature activation-5.86e-03

Pos logit contributions
rated+0.125
appointed+0.120
uct+0.117
ulously+0.117
aman+0.117
Neg logit contributions
 mate-0.092
 superheroes-0.092
 heroes-0.085
 soldiers-0.080
 pirates-0.076
Token the
Token ID262
Feature activation-8.35e-02

Pos logit contributions
rated+0.012
appointed+0.012
uct+0.012
ulously+0.012
aman+0.012
Neg logit contributions
 mate-0.008
 superheroes-0.008
 heroes-0.008
 soldiers-0.007
 pirates-0.007
Token window
Token ID4324
Feature activation+2.41e-02

Pos logit contributions
rated+0.136
appointed+0.129
aman+0.125
uct+0.124
ulously+0.124
Neg logit contributions
 mate-0.155
 superheroes-0.154
 heroes-0.143
 soldiers-0.137
 pirates-0.132
Token.
Token ID13
Feature activation-2.49e-02

Pos logit contributions
 mate+0.033
 superheroes+0.032
 heroes+0.030
 soldiers+0.027
 pirates+0.026
Neg logit contributions
rated-0.052
appointed-0.051
uct-0.050
ulously-0.050
aman-0.049
Token Rel
Token ID4718
Feature activation-8.33e-02

Pos logit contributions
rated+0.050
ulously+0.045
esh+0.044
appointed+0.043
uct+0.042
Neg logit contributions
 mate-0.040
 superheroes-0.039
 heroes-0.037
 much-0.035
 soldiers-0.035
Tokenuct
Token ID4782
Feature activation-3.08e-01

Pos logit contributions
rated+0.076
icol+0.073
adoes+0.065
inct+0.063
ened+0.061
Neg logit contributions
e-0.200
 mate-0.195
prise-0.192
 superheroes-0.180
 else-0.179
Tokenantly
Token ID3875
Feature activation-1.35e-01

Pos logit contributions
rated+0.352
uct+0.312
appointed+0.308
arrass+0.298
aman+0.296
Neg logit contributions
 mate-0.729
 superheroes-0.691
 heroes-0.691
e-0.681
 soldiers-0.668
Token,
Token ID11
Feature activation+4.11e-02

Pos logit contributions
rated+0.336
ulously+0.317
uct+0.317
appointed+0.316
urious+0.312
Neg logit contributions
 mate-0.152
 superheroes-0.143
 heroes-0.131
 soldiers-0.119
 pirates-0.114
Token he
Token ID339
Feature activation+1.84e-02

Pos logit contributions
 mate+0.056
 superheroes+0.056
 heroes+0.052
 soldiers+0.048
 pirates+0.047
Neg logit contributions
rated-0.090
appointed-0.084
ulously-0.084
uct-0.082
urious-0.082
Token came
Token ID1625
Feature activation+2.00e-02

Pos logit contributions
 mate+0.035
 superheroes+0.034
 heroes+0.032
 soldiers+0.031
 pirates+0.030
Neg logit contributions
rated-0.031
appointed-0.030
ulously-0.029
uct-0.029
aman-0.028
Token away
Token ID1497
Feature activation-6.25e-02

Pos logit contributions
 superheroes+0.031
 mate+0.031
 heroes+0.029
 soldiers+0.027
 dinosaurs+0.026
Neg logit contributions
rated-0.039
appointed-0.038
esh-0.036
ulously-0.036
uct-0.036
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
rated+0.151
appointed+0.145
uct+0.143
ulously+0.143
aman+0.141
Neg logit contributions
 mate-0.107
 superheroes-0.106
 heroes-0.099
 soldiers-0.092
 pirates-0.088
Token
Token ID220
Feature activation-2.91e-02

Pos logit contributions
rated+0.026
appointed+0.024
ulously+0.024
aman+0.024
uct+0.023
Neg logit contributions
 mate-0.023
 superheroes-0.023
 heroes-0.021
 soldiers-0.020
 pirates-0.020
Token
Token ID198
Feature activation+4.54e-02

Pos logit contributions
rated+0.058
appointed+0.057
uct+0.056
ulously+0.056
aman+0.055
Neg logit contributions
 superheroes-0.043
 mate-0.043
 heroes-0.040
 soldiers-0.037
 pirates-0.035
Token
Token ID198
Feature activation+4.56e-02

Pos logit contributions
 superheroes+0.068
 mate+0.068
 heroes+0.063
 soldiers+0.060
 pirates+0.056
Neg logit contributions
rated-0.089
appointed-0.088
uct-0.087
ulously-0.087
aman-0.085
TokenJohn
Token ID7554
Feature activation+5.33e-02

Pos logit contributions
 mate+0.083
 superheroes+0.082
 heroes+0.077
 soldiers+0.073
 pirates+0.071
Neg logit contributions
rated-0.078
appointed-0.074
uct-0.072
ulously-0.072
aman-0.072
Token inc
Token ID753
Feature activation-3.06e-01

Pos logit contributions
 mate+0.092
e+0.088
 superheroes+0.087
 heroes+0.083
 pirates+0.079
Neg logit contributions
rated-0.094
appointed-0.087
uct-0.085
esh-0.084
aman-0.084
Tokenhed
Token ID704
Feature activation+9.86e-03

Pos logit contributions
rated+0.531
appointed+0.500
uct+0.495
aman+0.494
ulously+0.489
Neg logit contributions
 mate-0.507
 superheroes-0.500
e-0.479
 heroes-0.473
 soldiers-0.450
Token closer
Token ID5699
Feature activation-2.85e-02

Pos logit contributions
 mate+0.014
 superheroes+0.014
 heroes+0.013
 soldiers+0.012
 pirates+0.012
Neg logit contributions
rated-0.020
appointed-0.020
uct-0.020
ulously-0.019
aman-0.019
Token and
Token ID290
Feature activation-2.19e-02

Pos logit contributions
rated+0.066
uct+0.064
appointed+0.064
ulously+0.063
aman+0.061
Neg logit contributions
 mate-0.035
 superheroes-0.033
 heroes-0.031
 much-0.028
 pirates-0.028
Token saw
Token ID2497
Feature activation+2.19e-02

Pos logit contributions
rated+0.043
ulously+0.042
appointed+0.042
aman+0.041
esh+0.041
Neg logit contributions
 mate-0.033
 superheroes-0.033
 heroes-0.030
 pirates-0.028
e-0.027
Token it
Token ID340
Feature activation-6.49e-02

Pos logit contributions
 mate+0.025
 superheroes+0.025
 heroes+0.023
 soldiers+0.021
 pirates+0.019
Neg logit contributions
rated-0.051
appointed-0.050
ulously-0.049
uct-0.049
aman-0.049
Token sea
Token ID5417
Feature activation+2.92e-02

Pos logit contributions
rated+0.151
 inc+0.147
ened+0.145
ulously+0.143
inct+0.143
Neg logit contributions
 mate-0.101
 superheroes-0.091
 heroes-0.083
prise-0.082
e-0.082
Token monster
Token ID9234
Feature activation+6.74e-02

Pos logit contributions
 mate+0.058
 superheroes+0.058
 heroes+0.055
 soldiers+0.052
 pirates+0.051
Neg logit contributions
rated-0.045
appointed-0.043
ulously-0.042
uct-0.042
aman-0.042
Token insisted
Token ID11189
Feature activation-1.84e-01

Pos logit contributions
 mate+0.126
 superheroes+0.124
 heroes+0.118
 soldiers+0.110
 pirates+0.108
Neg logit contributions
rated-0.113
appointed-0.110
ulously-0.106
aman-0.105
uct-0.104
Token.
Token ID13
Feature activation-2.58e-02

Pos logit contributions
rated+0.398
appointed+0.382
aman+0.373
ulously+0.371
esh+0.367
Neg logit contributions
 superheroes-0.252
 mate-0.251
 heroes-0.236
 soldiers-0.222
 pirates-0.212
Token Rel
Token ID4718
Feature activation-7.86e-02

Pos logit contributions
rated+0.048
appointed+0.043
esh+0.043
ulously+0.043
aman+0.043
Neg logit contributions
 mate-0.045
 superheroes-0.045
 heroes-0.042
 soldiers-0.041
 pirates-0.039
Tokenuct
Token ID4782
Feature activation-3.04e-01

Pos logit contributions
rated+0.095
icol+0.088
ened+0.081
 exp+0.081
inct+0.080
Neg logit contributions
e-0.170
 mate-0.167
 superheroes-0.158
 heroes-0.156
prise-0.153
Tokenantly
Token ID3875
Feature activation-1.33e-01

Pos logit contributions
rated+0.313
appointed+0.289
uct+0.287
aman+0.286
arrass+0.262
Neg logit contributions
 mate-0.743
 superheroes-0.723
 heroes-0.712
 soldiers-0.694
e-0.692
Token,
Token ID11
Feature activation+4.47e-02

Pos logit contributions
rated+0.351
urious+0.333
uct+0.330
ulously+0.330
appointed+0.329
Neg logit contributions
 mate-0.136
 superheroes-0.126
 heroes-0.114
 soldiers-0.106
 pirates-0.101
Token it
Token ID340
Feature activation-5.73e-02

Pos logit contributions
 superheroes+0.063
 mate+0.063
 heroes+0.058
 soldiers+0.055
 pirates+0.053
Neg logit contributions
rated-0.096
appointed-0.092
ulously-0.090
uct-0.089
aman-0.089
Token followed
Token ID3940
Feature activation-9.76e-02

Pos logit contributions
aman+0.101
appointed+0.100
rated+0.098
uct+0.097
ulously+0.095
Neg logit contributions
 mate-0.106
 superheroes-0.102
 heroes-0.099
 soldiers-0.092
 pirates-0.089
Token him
Token ID683
Feature activation+8.76e-02

Pos logit contributions
rated+0.201
appointed+0.194
uct+0.190
ulously+0.188
aman+0.187
Neg logit contributions
 mate-0.143
 superheroes-0.143
 heroes-0.133
 soldiers-0.125
 pirates-0.120
Token his
Token ID465
Feature activation+4.60e-02

Pos logit contributions
rated+0.131
uct+0.117
ulously+0.116
appointed+0.116
aman+0.114
Neg logit contributions
 superheroes-0.049
 fishing-0.045
 much-0.044
 heroes-0.044
 mate-0.043
Token climb
Token ID12080
Feature activation-1.09e-01

Pos logit contributions
 superheroes+0.071
 mate+0.069
 heroes+0.067
 soldiers+0.062
 much+0.062
Neg logit contributions
rated-0.091
aman-0.086
esh-0.086
uct-0.085
ulously-0.084
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
rated+0.243
uct+0.234
appointed+0.226
aman+0.226
arrass+0.226
Neg logit contributions
 superheroes-0.146
 heroes-0.136
 mate-0.132
 soldiers-0.129
 much-0.128
Token He
Token ID679
Feature activation-3.35e-02

Pos logit contributions
rated+0.049
uct+0.044
aman+0.044
esh+0.044
urious+0.042
Neg logit contributions
 mate-0.025
 much-0.025
 superheroes-0.024
 heroes-0.024
 dinosaurs-0.022
Token slowly
Token ID6364
Feature activation-1.69e-01

Pos logit contributions
rated+0.066
aman+0.064
esh+0.062
appointed+0.062
icol+0.061
Neg logit contributions
 superheroes-0.051
e-0.049
 much-0.047
 heroes-0.047
 mate-0.047
Token inc
Token ID753
Feature activation-3.02e-01

Pos logit contributions
rated+0.331
appointed+0.300
idents+0.300
esh+0.296
ulously+0.294
Neg logit contributions
 superheroes-0.261
 mate-0.257
e-0.246
 much-0.237
 heroes-0.235
Tokenhed
Token ID704
Feature activation+1.56e-02

Pos logit contributions
rated+0.553
appointed+0.517
aman+0.515
arrass+0.515
esh+0.512
Neg logit contributions
 superheroes-0.464
e-0.458
 mate-0.456
 heroes-0.439
 soldiers-0.424
Token his
Token ID465
Feature activation+4.70e-02

Pos logit contributions
 mate+0.025
 superheroes+0.025
 heroes+0.024
 soldiers+0.022
 pirates+0.022
Neg logit contributions
rated-0.030
appointed-0.029
uct-0.028
ulously-0.028
aman-0.028
Token way
Token ID835
Feature activation-1.39e-01

Pos logit contributions
 mate+0.078
 superheroes+0.076
 heroes+0.075
 soldiers+0.068
 pirates+0.067
Neg logit contributions
rated-0.086
aman-0.083
esh-0.083
uct-0.083
appointed-0.079
Token up
Token ID510
Feature activation-5.03e-02

Pos logit contributions
rated+0.278
uct+0.265
ulously+0.262
appointed+0.262
aman+0.256
Neg logit contributions
 mate-0.211
 superheroes-0.202
 heroes-0.192
 soldiers-0.178
 pirates-0.174
Token,
Token ID11
Feature activation+4.93e-02

Pos logit contributions
rated+0.121
uct+0.115
appointed+0.114
ulously+0.113
urious+0.112
Neg logit contributions
 superheroes-0.057
 mate-0.056
 heroes-0.052
 much-0.048
 soldiers-0.048
Token buy
Token ID2822
Feature activation+7.88e-03

Pos logit contributions
rated+0.128
appointed+0.123
uct+0.121
ulously+0.121
aman+0.119
Neg logit contributions
 mate-0.108
 superheroes-0.107
 heroes-0.100
 soldiers-0.094
 pirates-0.091
Token his
Token ID465
Feature activation+5.02e-02

Pos logit contributions
 mate+0.012
 superheroes+0.011
 heroes+0.010
 soldiers+0.010
 astronauts+0.009
Neg logit contributions
rated-0.015
ulously-0.015
uct-0.015
aman-0.015
appointed-0.015
Token own
Token ID898
Feature activation-2.54e-02

Pos logit contributions
 mate+0.070
 superheroes+0.070
 heroes+0.066
 pirates+0.061
 soldiers+0.060
Neg logit contributions
rated-0.108
appointed-0.104
uct-0.103
esh-0.100
aman-0.099
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
rated+0.054
appointed+0.052
uct+0.051
inct+0.050
esh+0.049
Neg logit contributions
 mate-0.035
 superheroes-0.033
 heroes-0.032
 much-0.030
 pirates-0.030
Token Rel
Token ID4718
Feature activation-7.63e-02

Pos logit contributions
rated+0.031
ulously+0.027
 inc+0.027
esh+0.027
iously+0.027
Neg logit contributions
 superheroes-0.015
 mate-0.014
 soldiers-0.014
 heroes-0.014
 much-0.013
Tokenuct
Token ID4782
Feature activation-3.01e-01

Pos logit contributions
rated+0.120
icol+0.112
inct+0.106
 exp+0.106
ened+0.104
Neg logit contributions
 mate-0.132
e-0.131
 superheroes-0.128
 heroes-0.123
prise-0.119
Tokenantly
Token ID3875
Feature activation-1.31e-01

Pos logit contributions
rated+0.333
uct+0.305
aman+0.301
appointed+0.296
arrass+0.283
Neg logit contributions
 mate-0.708
 superheroes-0.686
 heroes-0.685
 soldiers-0.672
e-0.662
Token,
Token ID11
Feature activation+5.27e-02

Pos logit contributions
rated+0.338
appointed+0.316
uct+0.315
ulously+0.315
urious+0.314
Neg logit contributions
 mate-0.138
 superheroes-0.131
 heroes-0.120
 soldiers-0.111
 pirates-0.105
Token his
Token ID465
Feature activation+4.96e-02

Pos logit contributions
 superheroes+0.079
 mate+0.079
 heroes+0.074
 soldiers+0.070
 pirates+0.067
Neg logit contributions
rated-0.107
appointed-0.101
ulously-0.099
uct-0.099
aman-0.098
Token friend
Token ID1545
Feature activation+8.06e-03

Pos logit contributions
 superheroes+0.070
 mate+0.070
 heroes+0.064
 soldiers+0.060
 pirates+0.057
Neg logit contributions
rated-0.102
appointed-0.099
ulously-0.098
uct-0.096
esh-0.095
Token gave
Token ID2921
Feature activation+3.87e-02

Pos logit contributions
 mate+0.014
 superheroes+0.014
 heroes+0.013
 soldiers+0.013
 pirates+0.012
Neg logit contributions
rated-0.014
appointed-0.014
ulously-0.013
uct-0.013
esh-0.013
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
rated+0.070
appointed+0.068
ulously+0.067
uct+0.067
aman+0.066
Neg logit contributions
 mate-0.044
 superheroes-0.044
 heroes-0.041
 soldiers-0.038
 pirates-0.036
Token
Token ID220
Feature activation-2.53e-02

Pos logit contributions
rated+0.025
ulously+0.022
esh+0.022
uct+0.022
appointed+0.021
Neg logit contributions
 superheroes-0.020
 mate-0.020
 soldiers-0.018
 heroes-0.018
 much-0.018
Token
Token ID198
Feature activation+5.14e-02

Pos logit contributions
rated+0.060
appointed+0.057
ulously+0.056
uct+0.056
aman+0.055
Neg logit contributions
 superheroes-0.029
 mate-0.028
 heroes-0.026
 soldiers-0.024
 much-0.023
Token
Token ID198
Feature activation+5.26e-02

Pos logit contributions
 mate+0.077
 superheroes+0.076
 heroes+0.071
 soldiers+0.066
 pirates+0.064
Neg logit contributions
rated-0.102
appointed-0.102
uct-0.100
aman-0.099
ulously-0.098
TokenRel
Token ID6892
Feature activation-1.48e-01

Pos logit contributions
 mate+0.085
 superheroes+0.085
 heroes+0.079
 soldiers+0.074
 pirates+0.072
Neg logit contributions
rated-0.100
appointed-0.097
uct-0.095
ulously-0.094
aman-0.093
Tokenuct
Token ID4782
Feature activation-3.01e-01

Pos logit contributions
rated+0.131
esh+0.114
 exp+0.111
inct+0.110
ulously+0.109
Neg logit contributions
 mate-0.363
 superheroes-0.358
prise-0.339
 heroes-0.338
izards-0.337
Tokenantly
Token ID3875
Feature activation-1.29e-01

Pos logit contributions
rated+0.361
uct+0.329
arrass+0.324
appointed+0.323
aman+0.319
Neg logit contributions
 mate-0.673
 superheroes-0.656
e-0.651
 heroes-0.648
 soldiers-0.635
Token,
Token ID11
Feature activation+5.30e-02

Pos logit contributions
rated+0.300
appointed+0.288
uct+0.285
ulously+0.285
aman+0.281
Neg logit contributions
 mate-0.158
 superheroes-0.155
 heroes-0.142
 soldiers-0.130
 pirates-0.124
Token Elsa
Token ID19226
Feature activation+9.91e-02

Pos logit contributions
 mate+0.074
 superheroes+0.073
 heroes+0.068
 soldiers+0.063
 pirates+0.060
Neg logit contributions
rated-0.112
appointed-0.109
uct-0.107
ulously-0.106
aman-0.106
Token left
Token ID1364
Feature activation+2.00e-02

Pos logit contributions
 mate+0.167
 superheroes+0.162
 heroes+0.153
e+0.148
 pirates+0.146
Neg logit contributions
rated-0.188
appointed-0.178
ulously-0.175
uct-0.171
aman-0.170
Token the
Token ID262
Feature activation-7.52e-02

Pos logit contributions
 superheroes+0.026
 mate+0.025
 heroes+0.024
 soldiers+0.023
 pirates+0.022
Neg logit contributions
rated-0.045
appointed-0.044
ulously-0.043
uct-0.042
esh-0.042
Token whispers
Token ID37806
Feature activation-9.57e-02

Pos logit contributions
 mate+0.011
 superheroes+0.011
 heroes+0.011
 soldiers+0.010
 pirates+0.010
Neg logit contributions
rated-0.012
appointed-0.011
uct-0.011
ulously-0.011
aman-0.011
Token.
Token ID13
Feature activation-1.15e-03

Pos logit contributions
rated+0.195
appointed+0.188
uct+0.184
ulously+0.184
aman+0.182
Neg logit contributions
 mate-0.139
 superheroes-0.139
 heroes-0.128
 soldiers-0.120
 pirates-0.115
Token They
Token ID1119
Feature activation+3.40e-02

Pos logit contributions
rated+0.002
appointed+0.002
uct+0.002
ulously+0.002
aman+0.002
Neg logit contributions
 mate-0.002
 superheroes-0.002
 heroes-0.002
 soldiers-0.001
 pirates-0.001
Token smell
Token ID8508
Feature activation+4.30e-02

Pos logit contributions
 mate+0.053
 superheroes+0.052
 heroes+0.049
 soldiers+0.046
 pirates+0.044
Neg logit contributions
rated-0.066
appointed-0.064
uct-0.063
ulously-0.063
aman-0.062
Token more
Token ID517
Feature activation+1.12e-01

Pos logit contributions
 mate+0.068
 superheroes+0.063
 heroes+0.058
 queens+0.054
 soldiers+0.054
Neg logit contributions
rated-0.084
ulously-0.079
ened-0.079
appointed-0.078
uct-0.077
Token inc
Token ID753
Feature activation-3.00e-01

Pos logit contributions
 mate+0.171
 superheroes+0.169
 heroes+0.157
 soldiers+0.147
 pirates+0.141
Neg logit contributions
rated-0.223
appointed-0.214
uct-0.211
ulously-0.210
aman-0.208
Tokenense
Token ID1072
Feature activation+5.62e-02

Pos logit contributions
rated+0.555
appointed+0.532
uct+0.527
ulously+0.524
esh+0.521
Neg logit contributions
 mate-0.462
 superheroes-0.461
 heroes-0.435
e-0.434
 soldiers-0.418
Token and
Token ID290
Feature activation-7.72e-03

Pos logit contributions
 mate+0.082
 superheroes+0.081
 heroes+0.076
 soldiers+0.071
 pirates+0.068
Neg logit contributions
rated-0.115
appointed-0.111
uct-0.110
ulously-0.109
aman-0.107
Token spices
Token ID27952
Feature activation+4.74e-02

Pos logit contributions
rated+0.013
appointed+0.013
uct+0.013
ulously+0.013
aman+0.012
Neg logit contributions
 mate-0.014
 superheroes-0.014
 heroes-0.013
 soldiers-0.012
 pirates-0.012
Token and
Token ID290
Feature activation-1.14e-02

Pos logit contributions
 mate+0.059
 superheroes+0.059
 heroes+0.054
 soldiers+0.050
 pirates+0.047
Neg logit contributions
rated-0.106
appointed-0.103
uct-0.102
ulously-0.101
aman-0.100
Token smoke
Token ID7523
Feature activation+5.94e-02

Pos logit contributions
rated+0.020
appointed+0.019
ulously+0.019
uct+0.019
aman+0.019
Neg logit contributions
 mate-0.019
 superheroes-0.019
 heroes-0.018
 soldiers-0.017
 pirates-0.016
Token and
Token ID290
Feature activation+9.96e-03

Pos logit contributions
 mate+0.260
 superheroes+0.258
 heroes+0.241
 soldiers+0.224
 pirates+0.215
Neg logit contributions
rated-0.374
appointed-0.362
uct-0.356
ulously-0.356
aman-0.350
Token whispers
Token ID37806
Feature activation-1.04e-01

Pos logit contributions
 mate+0.019
 superheroes+0.019
 heroes+0.018
 soldiers+0.017
 pirates+0.016
Neg logit contributions
rated-0.015
appointed-0.015
ulously-0.014
 inc-0.014
uct-0.014
Token.
Token ID13
Feature activation+1.42e-03

Pos logit contributions
rated+0.191
appointed+0.180
ened+0.178
 inc+0.176
iously+0.175
Neg logit contributions
 superheroes-0.171
 mate-0.168
 heroes-0.155
 soldiers-0.146
 dinosaurs-0.142
Token They
Token ID1119
Feature activation+2.95e-02

Pos logit contributions
 mate+0.002
 superheroes+0.002
 heroes+0.002
 soldiers+0.002
 pirates+0.002
Neg logit contributions
rated-0.003
appointed-0.002
uct-0.002
ulously-0.002
aman-0.002
Token smell
Token ID8508
Feature activation+3.26e-02

Pos logit contributions
 superheroes+0.042
 mate+0.041
 heroes+0.038
 soldiers+0.037
 pirates+0.035
Neg logit contributions
rated-0.060
appointed-0.057
uct-0.057
 inc-0.056
aman-0.056
Token inc
Token ID753
Feature activation-2.99e-01

Pos logit contributions
 mate+0.060
 superheroes+0.054
 loser+0.051
 heroes+0.050
 rook+0.049
Neg logit contributions
rated-0.053
ened-0.052
uct-0.050
ulously-0.050
 inc-0.049
Tokenense
Token ID1072
Feature activation+5.68e-02

Pos logit contributions
rated+0.538
appointed+0.513
uct+0.506
ulously+0.504
aman+0.500
Neg logit contributions
 superheroes-0.501
 mate-0.501
 heroes-0.472
 soldiers-0.449
e-0.433
Token and
Token ID290
Feature activation+8.26e-03

Pos logit contributions
 mate+0.084
 superheroes+0.083
 heroes+0.078
 soldiers+0.073
 pirates+0.070
Neg logit contributions
rated-0.116
appointed-0.111
uct-0.110
ulously-0.109
aman-0.108
Token spices
Token ID27952
Feature activation+4.87e-02

Pos logit contributions
 mate+0.014
 superheroes+0.014
 heroes+0.013
 soldiers+0.012
e+0.012
Neg logit contributions
rated-0.014
appointed-0.014
ulously-0.013
 inc-0.013
uct-0.013
Token and
Token ID290
Feature activation+8.17e-03

Pos logit contributions
 mate+0.071
 superheroes+0.070
 heroes+0.065
 soldiers+0.060
 pirates+0.058
Neg logit contributions
rated-0.099
appointed-0.095
uct-0.093
ulously-0.093
aman-0.093
Token smoke
Token ID7523
Feature activation+6.60e-02

Pos logit contributions
 mate+0.014
 superheroes+0.013
 heroes+0.013
 soldiers+0.012
 pirates+0.011
Neg logit contributions
rated-0.015
appointed-0.014
ulously-0.014
uct-0.014
aman-0.014
Token smiled
Token ID13541
Feature activation+5.07e-02

Pos logit contributions
rated+0.132
appointed+0.123
aman+0.115
ulously+0.115
esh+0.113
Neg logit contributions
 mate-0.096
 superheroes-0.095
e-0.090
 heroes-0.089
 pirates-0.083
Token and
Token ID290
Feature activation-1.88e-02

Pos logit contributions
 mate+0.064
 superheroes+0.063
 heroes+0.060
 soldiers+0.053
 pirates+0.053
Neg logit contributions
rated-0.117
ulously-0.112
uct-0.112
appointed-0.112
aman-0.109
Token said
Token ID531
Feature activation-1.99e-02

Pos logit contributions
rated+0.042
urious+0.038
ulously+0.037
appointed+0.036
inct+0.035
Neg logit contributions
 superheroes-0.027
 mate-0.026
 heroes-0.025
 a-0.024
 much-0.024
Token,
Token ID11
Feature activation+4.75e-02

Pos logit contributions
rated+0.049
ulously+0.046
appointed+0.046
uct+0.046
aman+0.046
Neg logit contributions
 mate-0.023
 superheroes-0.022
 heroes-0.020
 soldiers-0.018
 much-0.017
Token "
Token ID366
Feature activation-6.80e-02

Pos logit contributions
 mate+0.075
 superheroes+0.071
 heroes+0.068
 much+0.065
 soldiers+0.063
Neg logit contributions
rated-0.097
ulously-0.092
urious-0.089
appointed-0.085
iped-0.084
TokenOk
Token ID18690
Feature activation-2.58e-01

Pos logit contributions
rated+0.127
iously+0.119
ulously+0.116
aman+0.115
iped+0.114
Neg logit contributions
 mate-0.113
 superheroes-0.110
 heroes-0.106
e-0.097
 winners-0.096
Token!"
Token ID2474
Feature activation-4.90e-02

Pos logit contributions
rated+0.633
ulously+0.616
uct+0.609
appointed+0.606
urious+0.603
Neg logit contributions
 mate-0.289
 superheroes-0.270
 heroes-0.254
 soldiers-0.216
 pirates-0.216
Token Then
Token ID3244
Feature activation-1.53e-01

Pos logit contributions
rated+0.116
appointed+0.103
esh+0.103
ulously+0.103
uct+0.100
Neg logit contributions
 superheroes-0.062
 mate-0.060
 heroes-0.057
 much-0.054
 soldiers-0.053
Token she
Token ID673
Feature activation-6.09e-02

Pos logit contributions
rated+0.399
urious+0.375
appointed+0.374
uct+0.372
ulously+0.365
Neg logit contributions
 superheroes-0.160
 mate-0.153
 heroes-0.146
 much-0.127
 soldiers-0.125
Token took
Token ID1718
Feature activation-4.16e-02

Pos logit contributions
rated+0.104
appointed+0.100
ulously+0.098
uct+0.096
aman+0.095
Neg logit contributions
 mate-0.117
 superheroes-0.115
 heroes-0.108
 soldiers-0.102
 pirates-0.100
Token the
Token ID262
Feature activation-8.10e-02

Pos logit contributions
ulously+0.077
rated+0.077
appointed+0.075
uct+0.075
ened+0.074
Neg logit contributions
 mate-0.067
 superheroes-0.064
 heroes-0.060
 soldiers-0.055
 pirates-0.054
Token and
Token ID290
Feature activation-3.96e-03

Pos logit contributions
 mate+0.111
 superheroes+0.108
 heroes+0.105
e+0.102
 pirates+0.095
Neg logit contributions
rated-0.131
appointed-0.122
aman-0.120
esh-0.117
ulously-0.115
Token then
Token ID788
Feature activation-8.19e-02

Pos logit contributions
rated+0.008
appointed+0.007
aman+0.007
uct+0.007
esh+0.007
Neg logit contributions
 superheroes-0.006
 mate-0.006
 heroes-0.006
 soldiers-0.006
 pirates-0.005
Token smiled
Token ID13541
Feature activation+4.57e-02

Pos logit contributions
rated+0.158
appointed+0.152
uct+0.148
ulously+0.148
aman+0.146
Neg logit contributions
 superheroes-0.132
 mate-0.132
 heroes-0.122
 soldiers-0.117
 pirates-0.112
Token.
Token ID13
Feature activation-2.06e-02

Pos logit contributions
 mate+0.055
 superheroes+0.054
 heroes+0.051
 soldiers+0.046
 pirates+0.046
Neg logit contributions
rated-0.109
appointed-0.105
ulously-0.104
uct-0.104
aman-0.101
Token "
Token ID366
Feature activation-6.53e-02

Pos logit contributions
rated+0.046
ulously+0.040
appointed+0.040
esh+0.040
iously+0.039
Neg logit contributions
 mate-0.030
 superheroes-0.029
 heroes-0.026
 soldiers-0.025
 much-0.025
TokenOk
Token ID18690
Feature activation-2.57e-01

Pos logit contributions
rated+0.099
appointed+0.093
ulously+0.090
iously+0.090
uct+0.090
Neg logit contributions
 mate-0.130
 superheroes-0.127
 heroes-0.121
 soldiers-0.113
e-0.112
Token,
Token ID11
Feature activation+4.20e-02

Pos logit contributions
rated+0.574
ulously+0.559
appointed+0.555
uct+0.550
urious+0.547
Neg logit contributions
 mate-0.330
 superheroes-0.314
 heroes-0.293
 soldiers-0.263
 pirates-0.259
Token let
Token ID1309
Feature activation-1.41e-01

Pos logit contributions
 mate+0.066
 superheroes+0.064
 heroes+0.060
 soldiers+0.054
 pirates+0.054
Neg logit contributions
rated-0.084
appointed-0.081
ulously-0.080
uct-0.079
iped-0.078
Tokenâ
Token ID22940
Feature activation-1.65e-01

Pos logit contributions
rated+0.336
appointed+0.326
iously+0.321
uct+0.309
iped+0.308
Neg logit contributions
 mate-0.157
 superheroes-0.152
e-0.137
 heroes-0.136
 soldiers-0.128
Token€
Token ID26391
Feature activation-1.24e-01

Pos logit contributions
ened+0.248
iously+0.246
aman+0.246
icol+0.246
iped+0.240
Neg logit contributions
e-0.312
 mate-0.287
 superheroes-0.249
 winners-0.248
 marry-0.245
Tokenâ„¢
Token ID8151
Feature activation-6.27e-02

Pos logit contributions
rated+0.230
ulously+0.216
appointed+0.214
uct+0.213
aman+0.209
Neg logit contributions
 mate-0.207
 superheroes-0.204
 heroes-0.191
 soldiers-0.179
e-0.177
Token smiled
Token ID13541
Feature activation+5.03e-02

Pos logit contributions
rated+0.010
appointed+0.010
inct+0.010
ulously+0.009
esh+0.009
Neg logit contributions
 mate-0.007
 superheroes-0.006
 heroes-0.006
e-0.006
 soldiers-0.006
Token and
Token ID290
Feature activation-2.22e-02

Pos logit contributions
 mate+0.055
 superheroes+0.054
 heroes+0.052
 soldiers+0.047
 pirates+0.046
Neg logit contributions
rated-0.124
ulously-0.119
appointed-0.118
uct-0.117
aman-0.114
Token said
Token ID531
Feature activation-1.99e-02

Pos logit contributions
rated+0.049
appointed+0.045
urious+0.045
ulously+0.044
inct+0.042
Neg logit contributions
 superheroes-0.032
 mate-0.031
 heroes-0.030
 soldiers-0.027
 much-0.027
Token,
Token ID11
Feature activation+4.86e-02

Pos logit contributions
rated+0.049
ulously+0.047
appointed+0.047
uct+0.046
urious+0.046
Neg logit contributions
 mate-0.022
 superheroes-0.021
 heroes-0.020
 soldiers-0.018
 much-0.017
Token "
Token ID366
Feature activation-6.79e-02

Pos logit contributions
 mate+0.072
 superheroes+0.068
 heroes+0.064
 much+0.062
 soldiers+0.061
Neg logit contributions
rated-0.104
ulously-0.099
urious-0.096
appointed-0.092
uct-0.091
TokenOk
Token ID18690
Feature activation-2.55e-01

Pos logit contributions
rated+0.105
iously+0.096
appointed+0.095
iped+0.093
esh+0.092
Neg logit contributions
 mate-0.135
 superheroes-0.131
 heroes-0.126
 queens-0.117
 pirates-0.116
Token,
Token ID11
Feature activation+4.39e-02

Pos logit contributions
rated+0.640
ulously+0.618
appointed+0.617
uct+0.614
urious+0.609
Neg logit contributions
 mate-0.269
 superheroes-0.243
 heroes-0.228
 pirates-0.197
 soldiers-0.194
Token that
Token ID326
Feature activation-4.79e-02

Pos logit contributions
 mate+0.065
 superheroes+0.062
 heroes+0.058
 pirates+0.053
 soldiers+0.051
Neg logit contributions
rated-0.094
appointed-0.091
ulously-0.088
uct-0.087
iped-0.087
Token's
Token ID338
Feature activation+4.60e-02

Pos logit contributions
rated+0.087
appointed+0.086
uct+0.086
aman+0.084
iously+0.083
Neg logit contributions
 superheroes-0.080
 mate-0.080
 heroes-0.076
 soldiers-0.071
 pirates-0.068
Token fine
Token ID3734
Feature activation+2.60e-03

Pos logit contributions
 mate+0.046
 superheroes+0.046
 heroes+0.041
 soldiers+0.036
 pirates+0.034
Neg logit contributions
rated-0.116
appointed-0.112
uct-0.111
ulously-0.110
aman-0.110
Token.
Token ID13
Feature activation-2.76e-02

Pos logit contributions
 mate+0.004
 superheroes+0.004
 heroes+0.003
 soldiers+0.003
 pirates+0.003
Neg logit contributions
uct-0.006
appointed-0.005
rated-0.005
ulously-0.005
aman-0.005
Token chuckled
Token ID39889
Feature activation+5.80e-02

Pos logit contributions
 mate+0.270
 superheroes+0.264
 heroes+0.250
 soldiers+0.239
 pirates+0.231
Neg logit contributions
rated-0.262
appointed-0.248
ulously-0.241
uct-0.234
aman-0.232
Token and
Token ID290
Feature activation-2.69e-02

Pos logit contributions
 mate+0.074
 superheroes+0.073
 heroes+0.068
 soldiers+0.063
 pirates+0.062
Neg logit contributions
rated-0.131
appointed-0.125
ulously-0.124
uct-0.123
aman-0.121
Token said
Token ID531
Feature activation-2.18e-02

Pos logit contributions
rated+0.052
appointed+0.048
ulously+0.047
urious+0.046
esh+0.045
Neg logit contributions
 mate-0.046
 superheroes-0.045
 heroes-0.042
 soldiers-0.039
 pirates-0.039
Token,
Token ID11
Feature activation+4.34e-02

Pos logit contributions
rated+0.048
appointed+0.047
uct+0.046
ulously+0.046
aman+0.045
Neg logit contributions
 mate-0.028
 superheroes-0.028
 heroes-0.026
 soldiers-0.024
 pirates-0.022
Token "
Token ID366
Feature activation-7.24e-02

Pos logit contributions
 mate+0.068
 superheroes+0.064
 heroes+0.061
 soldiers+0.058
 much+0.057
Neg logit contributions
rated-0.089
ulously-0.085
urious-0.080
appointed-0.079
uct-0.079
TokenOk
Token ID18690
Feature activation-2.55e-01

Pos logit contributions
rated+0.106
appointed+0.098
ulously+0.096
esh+0.094
iously+0.094
Neg logit contributions
 mate-0.149
 superheroes-0.147
 heroes-0.139
 soldiers-0.130
 pirates-0.130
Token,
Token ID11
Feature activation+4.23e-02

Pos logit contributions
rated+0.595
appointed+0.577
ulously+0.574
uct+0.571
aman+0.559
Neg logit contributions
 mate-0.305
 superheroes-0.291
 heroes-0.268
 soldiers-0.245
 pirates-0.238
Token here
Token ID994
Feature activation-8.45e-02

Pos logit contributions
 mate+0.062
 superheroes+0.061
 heroes+0.056
 soldiers+0.052
 pirates+0.051
Neg logit contributions
rated-0.088
appointed-0.085
ulously-0.083
uct-0.082
esh-0.082
Token you
Token ID345
Feature activation+4.51e-02

Pos logit contributions
rated+0.182
appointed+0.176
uct+0.172
ulously+0.172
aman+0.170
Neg logit contributions
 mate-0.116
 superheroes-0.115
 heroes-0.107
 soldiers-0.098
 pirates-0.095
Token go
Token ID467
Feature activation-3.46e-02

Pos logit contributions
 mate+0.072
 superheroes+0.072
 heroes+0.067
 soldiers+0.063
 pirates+0.060
Neg logit contributions
rated-0.086
appointed-0.083
uct-0.081
ulously-0.081
aman-0.080
Token,"
Token ID553
Feature activation+2.61e-02

Pos logit contributions
rated+0.072
appointed+0.070
uct+0.069
ulously+0.069
aman+0.068
Neg logit contributions
 mate-0.050
 superheroes-0.049
 heroes-0.046
 soldiers-0.043
 pirates-0.041
Token smiled
Token ID13541
Feature activation+5.29e-02

Pos logit contributions
e+0.063
 mate+0.062
 superheroes+0.061
 heroes+0.059
 soldiers+0.053
Neg logit contributions
rated-0.085
aman-0.077
esh-0.077
ulously-0.077
appointed-0.077
Token and
Token ID290
Feature activation-2.21e-02

Pos logit contributions
 mate+0.072
 superheroes+0.072
 heroes+0.068
 soldiers+0.062
 pirates+0.060
Neg logit contributions
rated-0.115
appointed-0.110
uct-0.110
ulously-0.109
aman-0.107
Token said
Token ID531
Feature activation-2.07e-02

Pos logit contributions
rated+0.047
urious+0.043
aman+0.042
esh+0.041
ulously+0.041
Neg logit contributions
 superheroes-0.033
 mate-0.032
 heroes-0.031
 much-0.030
 a-0.029
Token:
Token ID25
Feature activation+2.62e-02

Pos logit contributions
rated+0.040
ulously+0.038
appointed+0.038
uct+0.037
aman+0.037
Neg logit contributions
 mate-0.034
 superheroes-0.033
 heroes-0.031
 soldiers-0.029
 much-0.028
Token "
Token ID366
Feature activation-7.07e-02

Pos logit contributions
 mate+0.048
 superheroes+0.047
 heroes+0.044
 soldiers+0.042
 pirates+0.041
Neg logit contributions
rated-0.045
ulously-0.042
appointed-0.042
uct-0.041
aman-0.041
TokenOk
Token ID18690
Feature activation-2.55e-01

Pos logit contributions
rated+0.114
iously+0.107
appointed+0.106
esh+0.103
ulously+0.103
Neg logit contributions
 mate-0.132
 superheroes-0.129
 heroes-0.123
e-0.116
 pirates-0.114
Token mom
Token ID1995
Feature activation-1.27e-02

Pos logit contributions
rated+0.603
uct+0.583
appointed+0.582
ulously+0.581
aman+0.572
Neg logit contributions
 mate-0.301
 superheroes-0.287
 heroes-0.267
 soldiers-0.241
 pirates-0.229
Token,
Token ID11
Feature activation+4.62e-02

Pos logit contributions
rated+0.028
appointed+0.027
uct+0.027
ulously+0.027
aman+0.026
Neg logit contributions
 mate-0.017
 superheroes-0.017
 heroes-0.015
 soldiers-0.014
 pirates-0.013
Token I
Token ID314
Feature activation+2.26e-02

Pos logit contributions
 mate+0.066
 superheroes+0.065
 heroes+0.060
 soldiers+0.056
 pirates+0.054
Neg logit contributions
rated-0.098
appointed-0.094
uct-0.092
ulously-0.092
aman-0.091
Token will
Token ID481
Feature activation-6.95e-02

Pos logit contributions
 mate+0.037
 superheroes+0.036
 heroes+0.034
 soldiers+0.032
 pirates+0.031
Neg logit contributions
rated-0.042
appointed-0.041
uct-0.041
ulously-0.040
aman-0.040
Token never
Token ID1239
Feature activation-7.52e-02

Pos logit contributions
rated+0.148
uct+0.142
ulously+0.142
appointed+0.141
aman+0.139
Neg logit contributions
 mate-0.099
 superheroes-0.095
 heroes-0.088
 soldiers-0.080
e-0.080
Token door
Token ID3420
Feature activation-7.14e-02

Pos logit contributions
rated+0.108
appointed+0.103
ulously+0.102
uct+0.100
esh+0.098
Neg logit contributions
 mate-0.080
 superheroes-0.078
 heroes-0.074
 soldiers-0.072
 pirates-0.069
Token and
Token ID290
Feature activation-2.63e-02

Pos logit contributions
rated+0.179
appointed+0.170
ulously+0.169
uct+0.167
arrass+0.166
Neg logit contributions
 mate-0.068
 superheroes-0.067
 heroes-0.061
 much-0.061
 of-0.059
Token said
Token ID531
Feature activation-2.13e-02

Pos logit contributions
rated+0.052
appointed+0.050
ulously+0.049
uct+0.048
aman+0.048
Neg logit contributions
 superheroes-0.041
 mate-0.041
 heroes-0.038
 soldiers-0.036
 pirates-0.035
Token,
Token ID11
Feature activation+4.42e-02

Pos logit contributions
rated+0.051
appointed+0.049
ulously+0.049
uct+0.049
aman+0.048
Neg logit contributions
 mate-0.025
 superheroes-0.025
 heroes-0.023
 soldiers-0.021
 pirates-0.020
Token "
Token ID366
Feature activation-7.21e-02

Pos logit contributions
 mate+0.067
 superheroes+0.065
 heroes+0.060
 soldiers+0.057
 much+0.057
Neg logit contributions
rated-0.093
ulously-0.090
urious-0.085
appointed-0.084
uct-0.083
TokenOk
Token ID18690
Feature activation-2.55e-01

Pos logit contributions
rated+0.122
appointed+0.115
iously+0.113
ulously+0.110
esh+0.110
Neg logit contributions
 mate-0.132
 superheroes-0.128
 heroes-0.119
 pirates-0.114
e-0.113
Token Jane
Token ID12091
Feature activation-3.83e-02

Pos logit contributions
rated+0.602
appointed+0.584
ulously+0.583
uct+0.577
urious+0.570
Neg logit contributions
 mate-0.299
 superheroes-0.276
 heroes-0.255
 pirates-0.230
 soldiers-0.225
Token,
Token ID11
Feature activation+4.22e-02

Pos logit contributions
rated+0.092
appointed+0.091
uct+0.090
ulously+0.089
esh+0.087
Neg logit contributions
 mate-0.044
 superheroes-0.040
 heroes-0.038
 soldiers-0.034
e-0.033
Token you
Token ID345
Feature activation+4.60e-02

Pos logit contributions
 mate+0.061
 superheroes+0.060
 heroes+0.055
 soldiers+0.050
 pirates+0.050
Neg logit contributions
rated-0.089
appointed-0.086
ulously-0.084
uct-0.084
aman-0.083
Token may
Token ID743
Feature activation-3.86e-02

Pos logit contributions
 superheroes+0.084
 mate+0.083
 heroes+0.079
 soldiers+0.077
 dinosaurs+0.073
Neg logit contributions
rated-0.077
appointed-0.072
uct-0.070
ulously-0.069
aman-0.068
Token enter
Token ID3802
Feature activation-4.45e-02

Pos logit contributions
rated+0.084
appointed+0.080
uct+0.079
ulously+0.079
aman+0.078
Neg logit contributions
 mate-0.053
 superheroes-0.052
 heroes-0.048
 soldiers-0.044
 pirates-0.043
Token smiled
Token ID13541
Feature activation+4.95e-02

Pos logit contributions
 mate+0.054
e+0.053
 superheroes+0.052
 heroes+0.050
 much+0.046
Neg logit contributions
rated-0.058
appointed-0.057
aman-0.055
uct-0.055
esh-0.054
Token and
Token ID290
Feature activation-2.68e-02

Pos logit contributions
 superheroes+0.062
 mate+0.061
 heroes+0.059
 soldiers+0.052
 pirates+0.051
Neg logit contributions
rated-0.114
uct-0.109
ulously-0.109
appointed-0.108
aman-0.107
Token said
Token ID531
Feature activation-2.31e-02

Pos logit contributions
rated+0.055
esh+0.051
urious+0.051
aman+0.050
appointed+0.050
Neg logit contributions
 superheroes-0.039
 much-0.037
 heroes-0.036
 a-0.036
 mate-0.036
Token,
Token ID11
Feature activation+4.39e-02

Pos logit contributions
rated+0.057
ulously+0.054
appointed+0.053
urious+0.053
aman+0.053
Neg logit contributions
 mate-0.026
 superheroes-0.025
 heroes-0.025
 much-0.024
 soldiers-0.021
Token "
Token ID366
Feature activation-7.18e-02

Pos logit contributions
 mate+0.065
 superheroes+0.063
 heroes+0.060
 much+0.059
 soldiers+0.055
Neg logit contributions
rated-0.092
ulously-0.088
urious-0.085
appointed-0.082
iped-0.082
TokenOk
Token ID18690
Feature activation-2.55e-01

Pos logit contributions
rated+0.131
iously+0.123
iped+0.123
appointed+0.120
esh+0.119
Neg logit contributions
 mate-0.116
 superheroes-0.113
 heroes-0.108
e-0.103
 much-0.102
Token,
Token ID11
Feature activation+4.16e-02

Pos logit contributions
rated+0.615
ulously+0.596
uct+0.596
appointed+0.591
urious+0.588
Neg logit contributions
 mate-0.285
 superheroes-0.267
 heroes-0.251
 soldiers-0.211
 much-0.209
Token I
Token ID314
Feature activation+1.83e-02

Pos logit contributions
 mate+0.062
 superheroes+0.061
 heroes+0.057
 soldiers+0.052
 pirates+0.051
Neg logit contributions
rated-0.085
appointed-0.082
ulously-0.080
uct-0.079
esh-0.079
Token will
Token ID481
Feature activation-7.30e-02

Pos logit contributions
 mate+0.031
 superheroes+0.031
 heroes+0.029
 soldiers+0.027
 pirates+0.026
Neg logit contributions
rated-0.033
appointed-0.032
uct-0.032
ulously-0.031
aman-0.031
Token pray
Token ID12472
Feature activation+6.17e-02

Pos logit contributions
rated+0.153
uct+0.148
appointed+0.147
ulously+0.146
aman+0.144
Neg logit contributions
 mate-0.105
 superheroes-0.101
 heroes-0.095
 soldiers-0.086
 pirates-0.084
Token like
Token ID588
Feature activation+6.22e-02

Pos logit contributions
 mate+0.093
 superheroes+0.092
 heroes+0.084
 soldiers+0.081
 pirates+0.077
Neg logit contributions
rated-0.121
appointed-0.117
ulously-0.113
uct-0.112
aman-0.112
Token smiled
Token ID13541
Feature activation+5.15e-02

Pos logit contributions
rated+0.127
appointed+0.113
aman+0.111
inct+0.110
esh+0.108
Neg logit contributions
 mate-0.087
e-0.086
 superheroes-0.084
 heroes-0.076
 much-0.074
Token and
Token ID290
Feature activation-2.65e-02

Pos logit contributions
 superheroes+0.066
 mate+0.066
 heroes+0.063
 soldiers+0.056
 pirates+0.056
Neg logit contributions
rated-0.117
ulously-0.112
uct-0.112
appointed-0.112
aman-0.109
Token said
Token ID531
Feature activation-2.36e-02

Pos logit contributions
rated+0.060
urious+0.056
inct+0.054
ulously+0.053
esh+0.052
Neg logit contributions
 superheroes-0.035
 a-0.033
 much-0.032
 mate-0.032
 heroes-0.030
Token,
Token ID11
Feature activation+4.45e-02

Pos logit contributions
rated+0.059
uct+0.056
ulously+0.056
appointed+0.056
aman+0.055
Neg logit contributions
 mate-0.026
 superheroes-0.025
 heroes-0.023
 soldiers-0.020
 much-0.019
Token "
Token ID366
Feature activation-7.20e-02

Pos logit contributions
 mate+0.063
 superheroes+0.059
 heroes+0.056
 much+0.054
 soldiers+0.053
Neg logit contributions
rated-0.098
ulously-0.095
urious-0.092
uct-0.088
appointed-0.087
TokenOk
Token ID18690
Feature activation-2.54e-01

Pos logit contributions
rated+0.099
iously+0.093
iped+0.089
esh+0.089
appointed+0.089
Neg logit contributions
 mate-0.152
 superheroes-0.146
 heroes-0.140
e-0.135
 much-0.131
Token!"
Token ID2474
Feature activation-5.08e-02

Pos logit contributions
rated+0.633
ulously+0.617
uct+0.613
appointed+0.611
urious+0.610
Neg logit contributions
 mate-0.272
 superheroes-0.251
 heroes-0.233
 pirates-0.199
 soldiers-0.196
Token She
Token ID1375
Feature activation-1.14e-01

Pos logit contributions
rated+0.120
esh+0.106
appointed+0.102
ulously+0.102
urious+0.102
Neg logit contributions
 much-0.061
 superheroes-0.061
 mate-0.058
 heroes-0.056
e-0.053
Token walked
Token ID6807
Feature activation-8.14e-02

Pos logit contributions
rated+0.227
aman+0.214
uct+0.208
ulously+0.205
appointed+0.205
Neg logit contributions
 mate-0.188
 superheroes-0.182
 heroes-0.169
 much-0.161
 camping-0.154
Token over
Token ID625
Feature activation-1.90e-02

Pos logit contributions
rated+0.162
uct+0.155
ulously+0.154
aman+0.154
appointed+0.153
Neg logit contributions
 mate-0.128
 superheroes-0.126
 heroes-0.119
 soldiers-0.113
 pirates-0.109
Token to
Token ID284
Feature activation-7.24e-02

Pos logit contributions
rated+0.042
appointed+0.041
uct+0.039
ulously+0.039
aman+0.038
Neg logit contributions
 superheroes-0.027
 mate-0.026
 heroes-0.024
 soldiers-0.023
 pirates-0.022
Token with
Token ID351
Feature activation+4.36e-02

Pos logit contributions
rated+0.077
appointed+0.073
ened+0.072
uct+0.071
ulously+0.070
Neg logit contributions
 mate-0.068
 superheroes-0.068
 heroes-0.063
 soldiers-0.059
 spies-0.058
Token his
Token ID465
Feature activation+3.87e-02

Pos logit contributions
 mate+0.086
 superheroes+0.083
 heroes+0.077
 queens+0.074
 soldiers+0.073
Neg logit contributions
ulously-0.066
ened-0.064
uct-0.060
rated-0.059
appointed-0.058
Token sleeve
Token ID23179
Feature activation+2.06e-02

Pos logit contributions
 mate+0.075
 superheroes+0.074
 heroes+0.069
 soldiers+0.066
 pirates+0.064
Neg logit contributions
rated-0.062
appointed-0.059
ulously-0.058
uct-0.058
aman-0.057
Token.
Token ID13
Feature activation-2.73e-02

Pos logit contributions
 mate+0.033
 superheroes+0.033
 heroes+0.030
 soldiers+0.028
 pirates+0.028
Neg logit contributions
rated-0.039
appointed-0.038
uct-0.037
ulously-0.037
aman-0.036
Token "
Token ID366
Feature activation-7.44e-02

Pos logit contributions
rated+0.055
aman+0.050
esh+0.049
appointed+0.048
uct+0.048
Neg logit contributions
 mate-0.043
 superheroes-0.042
 heroes-0.040
 much-0.039
 soldiers-0.039
TokenOk
Token ID18690
Feature activation-2.54e-01

Pos logit contributions
rated+0.122
appointed+0.115
ulously+0.111
iously+0.111
aman+0.110
Neg logit contributions
 mate-0.140
 superheroes-0.138
 heroes-0.131
 pirates-0.121
 soldiers-0.121
Token,
Token ID11
Feature activation+4.25e-02

Pos logit contributions
rated+0.593
ulously+0.581
appointed+0.580
uct+0.577
aman+0.572
Neg logit contributions
 mate-0.300
 superheroes-0.285
 heroes-0.264
 soldiers-0.232
 pirates-0.230
Token Mom
Token ID11254
Feature activation-5.69e-02

Pos logit contributions
 mate+0.068
 superheroes+0.067
 heroes+0.063
 soldiers+0.059
 pirates+0.057
Neg logit contributions
rated-0.082
appointed-0.079
uct-0.077
ulously-0.077
aman-0.076
Tokenmy
Token ID1820
Feature activation+1.46e-01

Pos logit contributions
rated+0.131
uct+0.130
appointed+0.130
ulously+0.129
aman+0.128
Neg logit contributions
 mate-0.065
 superheroes-0.062
 heroes-0.058
 pirates-0.049
 soldiers-0.049
Token.
Token ID13
Feature activation-2.63e-02

Pos logit contributions
 mate+0.177
 superheroes+0.164
 heroes+0.159
 much+0.135
 pirates+0.132
Neg logit contributions
uct-0.337
ulously-0.334
appointed-0.329
rated-0.327
aman-0.326
Token That
Token ID1320
Feature activation-1.13e-01

Pos logit contributions
rated+0.052
appointed+0.049
aman+0.048
ulously+0.048
uct+0.048
Neg logit contributions
 mate-0.042
 superheroes-0.040
 heroes-0.038
 soldiers-0.035
 pirates-0.034
Token �
Token ID6184
Feature activation-1.35e-01

Pos logit contributions
 mate+0.059
 superheroes+0.059
 heroes+0.055
 much+0.054
 soldiers+0.053
Neg logit contributions
rated-0.080
ulously-0.077
urious-0.074
esh-0.072
appointed-0.072
Token�
Token ID95
Feature activation-1.32e-01

Pos logit contributions
ulously+0.246
rated+0.244
ened+0.217
urious+0.208
aman+0.205
Neg logit contributions
 mate-0.229
 superheroes-0.225
e-0.216
 heroes-0.209
prise-0.196
Token€
Token ID26391
Feature activation-1.18e-01

Pos logit contributions
rated+0.209
ened+0.206
ulously+0.202
iously+0.196
 inc+0.192
Neg logit contributions
e-0.247
 mate-0.219
 superheroes-0.212
 DVD-0.210
 heroes-0.200
Token�
Token ID129
Feature activation-1.06e-01

Pos logit contributions
rated+0.202
ulously+0.188
appointed+0.181
uct+0.180
iously+0.178
Neg logit contributions
 superheroes-0.217
 mate-0.214
 heroes-0.205
e-0.197
 much-0.190
Token�
Token ID241
Feature activation-8.61e-02

Pos logit contributions
rated+0.148
ened+0.135
ulously+0.134
aman+0.129
heart+0.128
Neg logit contributions
e-0.208
 mate-0.183
 much-0.182
 hunting-0.175
 superheroes-0.173
TokenOk
Token ID18690
Feature activation-2.54e-01

Pos logit contributions
rated+0.150
ulously+0.139
appointed+0.139
uct+0.138
esh+0.137
Neg logit contributions
 mate-0.150
 superheroes-0.150
 heroes-0.140
 much-0.134
 pirates-0.130
Token,
Token ID11
Feature activation+3.89e-02

Pos logit contributions
rated+0.635
urious+0.620
ulously+0.619
appointed+0.603
uct+0.599
Neg logit contributions
 mate-0.253
 superheroes-0.229
 heroes-0.217
 much-0.203
e-0.186
Token I
Token ID314
Feature activation+1.58e-02

Pos logit contributions
 mate+0.052
 superheroes+0.050
 heroes+0.046
 much+0.042
 pirates+0.041
Neg logit contributions
rated-0.090
appointed-0.085
urious-0.085
ulously-0.085
esh-0.083
Token believe
Token ID1975
Feature activation+9.59e-02

Pos logit contributions
 mate+0.026
 superheroes+0.026
 heroes+0.024
 soldiers+0.022
e+0.022
Neg logit contributions
rated-0.029
appointed-0.029
uct-0.028
ulously-0.028
aman-0.027
Token in
Token ID287
Feature activation+3.08e-02

Pos logit contributions
 mate+0.107
 superheroes+0.105
 heroes+0.096
 soldiers+0.086
 pirates+0.084
Neg logit contributions
rated-0.237
appointed-0.230
ulously-0.225
aman-0.222
uct-0.221
Token you
Token ID345
Feature activation+4.32e-02

Pos logit contributions
 mate+0.044
 superheroes+0.044
 heroes+0.040
 soldiers+0.039
 pirates+0.036
Neg logit contributions
uct-0.060
ulously-0.060
rated-0.060
appointed-0.060
aman-0.059
Tokenled
Token ID992
Feature activation+7.33e-03

Pos logit contributions
aman+0.025
icol+0.025
esh+0.024
rated+0.023
appointed+0.023
Neg logit contributions
 superheroes-0.027
 soldiers-0.025
 mate-0.025
 heroes-0.025
aky-0.024
Token and
Token ID290
Feature activation-1.39e-02

Pos logit contributions
 mate+0.009
 superheroes+0.009
 heroes+0.009
 soldiers+0.008
 pirates+0.008
Neg logit contributions
rated-0.017
appointed-0.016
ulously-0.016
uct-0.016
aman-0.016
Token said
Token ID531
Feature activation-1.47e-02

Pos logit contributions
rated+0.032
urious+0.030
inct+0.029
ulously+0.028
esh+0.028
Neg logit contributions
 superheroes-0.018
 much-0.016
 a-0.016
 mate-0.016
 very-0.015
Token,
Token ID11
Feature activation+5.45e-02

Pos logit contributions
rated+0.037
ulously+0.035
appointed+0.034
uct+0.034
aman+0.034
Neg logit contributions
 mate-0.017
 superheroes-0.016
 heroes-0.015
 soldiers-0.013
 much-0.013
Token "
Token ID366
Feature activation-6.43e-02

Pos logit contributions
 mate+0.087
 superheroes+0.083
 heroes+0.077
 much+0.074
 soldiers+0.073
Neg logit contributions
rated-0.111
ulously-0.106
urious-0.102
appointed-0.098
uct-0.098
TokenOk
Token ID18690
Feature activation-2.54e-01

Pos logit contributions
rated+0.117
iously+0.110
esh+0.104
ened+0.103
iped+0.103
Neg logit contributions
 mate-0.102
 superheroes-0.101
e-0.098
 heroes-0.093
 loser-0.092
Token,
Token ID11
Feature activation+4.97e-02

Pos logit contributions
rated+0.634
ulously+0.618
urious+0.612
appointed+0.605
uct+0.605
Neg logit contributions
 mate-0.273
 superheroes-0.247
 heroes-0.226
 pirates-0.197
 soldiers-0.195
Token then
Token ID788
Feature activation-7.69e-02

Pos logit contributions
 mate+0.066
 superheroes+0.062
 heroes+0.057
 pirates+0.050
 soldiers+0.050
Neg logit contributions
rated-0.115
appointed-0.111
ulously-0.109
urious-0.107
esh-0.107
Token I
Token ID314
Feature activation+2.15e-02

Pos logit contributions
rated+0.185
uct+0.181
ulously+0.180
aman+0.180
appointed+0.180
Neg logit contributions
 mate-0.090
 superheroes-0.086
 heroes-0.079
 pirates-0.069
 soldiers-0.067
Token will
Token ID481
Feature activation-7.14e-02

Pos logit contributions
 mate+0.040
 superheroes+0.039
 heroes+0.037
 soldiers+0.034
 pirates+0.034
Neg logit contributions
rated-0.036
appointed-0.035
uct-0.035
ulously-0.034
aman-0.034
Token hug
Token ID16225
Feature activation+9.75e-02

Pos logit contributions
rated+0.157
uct+0.149
aman+0.149
ulously+0.148
appointed+0.147
Neg logit contributions
 mate-0.100
 superheroes-0.094
 heroes-0.086
e-0.085
 soldiers-0.078
Token make
Token ID787
Feature activation-2.99e-02

Pos logit contributions
rated+0.123
appointed+0.118
ulously+0.117
uct+0.117
aman+0.116
Neg logit contributions
 mate-0.109
 superheroes-0.108
 heroes-0.102
 soldiers-0.097
 pirates-0.092
Token the
Token ID262
Feature activation-7.47e-02

Pos logit contributions
rated+0.062
appointed+0.060
ulously+0.060
uct+0.059
aman+0.059
Neg logit contributions
 mate-0.043
 superheroes-0.042
 heroes-0.038
 soldiers-0.036
 pirates-0.034
Token boo
Token ID22513
Feature activation+1.52e-03

Pos logit contributions
rated+0.133
appointed+0.126
ulously+0.124
uct+0.123
aman+0.121
Neg logit contributions
 mate-0.129
 superheroes-0.124
 heroes-0.117
 soldiers-0.110
 pirates-0.106
Token-
Token ID12
Feature activation+8.17e-02

Pos logit contributions
 mate+0.003
 superheroes+0.003
 heroes+0.003
 soldiers+0.003
 pirates+0.002
Neg logit contributions
rated-0.002
appointed-0.002
ulously-0.002
esh-0.002
uct-0.002
Tokenbo
Token ID2127
Feature activation+9.59e-02

Pos logit contributions
 superheroes+0.126
 mate+0.125
 heroes+0.120
e+0.114
 soldiers+0.111
Neg logit contributions
rated-0.152
aman-0.149
appointed-0.148
uct-0.147
esh-0.142
Tokeno
Token ID78
Feature activation+1.84e-01

Pos logit contributions
 superheroes+0.126
 mate+0.124
 heroes+0.113
 soldiers+0.106
 spies+0.103
Neg logit contributions
rated-0.215
ulously-0.200
appointed-0.200
uct-0.194
iously-0.194
Token go
Token ID467
Feature activation-2.80e-02

Pos logit contributions
 mate+0.277
 superheroes+0.275
 heroes+0.256
 soldiers+0.240
 pirates+0.230
Neg logit contributions
rated-0.366
appointed-0.354
uct-0.348
ulously-0.346
aman-0.344
Token away
Token ID1497
Feature activation-5.89e-02

Pos logit contributions
uct+0.054
rated+0.054
aman+0.053
ulously+0.053
appointed+0.053
Neg logit contributions
 superheroes-0.042
 mate-0.041
 heroes-0.039
 soldiers-0.037
 much-0.037
Token.
Token ID13
Feature activation-1.63e-02

Pos logit contributions
rated+0.116
appointed+0.110
ulously+0.107
uct+0.107
esh+0.106
Neg logit contributions
 mate-0.091
 superheroes-0.090
 heroes-0.083
 soldiers-0.079
 pirates-0.075
Token Tim
Token ID5045
Feature activation-3.59e-02

Pos logit contributions
rated+0.043
urious+0.038
esh+0.038
ened+0.037
inct+0.037
Neg logit contributions
 much-0.016
 superheroes-0.014
 mate-0.014
 dinosaurs-0.013
 heroes-0.012
Tokenmy
Token ID1820
Feature activation+1.59e-01

Pos logit contributions
appointed+0.093
inct+0.093
icol+0.093
esh+0.092
 inc+0.091
Neg logit contributions
e-0.027
 superheroes-0.025
 mate-0.023
 heroes-0.023
aky-0.022
Token He
Token ID679
Feature activation-3.78e-02

Pos logit contributions
rated+0.060
iously+0.057
aman+0.055
 inc+0.055
ened+0.054
Neg logit contributions
 much-0.030
 mate-0.028
 superheroes-0.026
 dinosaurs-0.024
 heroes-0.024
Token realized
Token ID6939
Feature activation-1.12e-01

Pos logit contributions
rated+0.074
aman+0.071
appointed+0.071
iously+0.067
uct+0.067
Neg logit contributions
 superheroes-0.065
 mate-0.062
 heroes-0.059
 soldiers-0.057
 pirates-0.056
Token that
Token ID326
Feature activation-4.38e-02

Pos logit contributions
rated+0.268
appointed+0.250
urious+0.240
ulously+0.240
uct+0.235
Neg logit contributions
 superheroes-0.147
 mate-0.141
 heroes-0.134
 soldiers-0.125
 pirates-0.123
Token it
Token ID340
Feature activation-5.65e-02

Pos logit contributions
rated+0.080
ulously+0.079
uct+0.078
esh+0.078
appointed+0.077
Neg logit contributions
 mate-0.071
 superheroes-0.065
 heroes-0.062
e-0.057
 soldiers-0.057
Token was
Token ID373
Feature activation-5.41e-02

Pos logit contributions
rated+0.104
aman+0.103
appointed+0.102
uct+0.099
ulously+0.098
Neg logit contributions
 superheroes-0.094
 mate-0.090
 heroes-0.089
 soldiers-0.085
 pirates-0.080
Token much
Token ID881
Feature activation+1.82e-01

Pos logit contributions
rated+0.104
appointed+0.101
uct+0.098
ulously+0.098
esh+0.095
Neg logit contributions
 mate-0.087
 superheroes-0.084
 heroes-0.078
 soldiers-0.074
e-0.071
Token easier
Token ID4577
Feature activation+7.43e-03

Pos logit contributions
 superheroes+0.208
 mate+0.202
 heroes+0.190
 soldiers+0.170
 pirates+0.163
Neg logit contributions
rated-0.439
appointed-0.423
uct-0.418
ulously-0.417
aman-0.416
Token to
Token ID284
Feature activation-6.90e-02

Pos logit contributions
 mate+0.012
 superheroes+0.012
 heroes+0.011
 soldiers+0.010
 pirates+0.010
Neg logit contributions
rated-0.014
appointed-0.014
uct-0.014
ulously-0.014
aman-0.014
Token find
Token ID1064
Feature activation-3.61e-02

Pos logit contributions
rated+0.131
appointed+0.126
uct+0.124
ulously+0.123
aman+0.122
Neg logit contributions
 mate-0.112
 superheroes-0.111
 heroes-0.104
 soldiers-0.097
 pirates-0.094
Token his
Token ID465
Feature activation+4.62e-02

Pos logit contributions
ulously+0.069
ened+0.067
rated+0.066
esh+0.065
aman+0.064
Neg logit contributions
 mate-0.053
 superheroes-0.048
 heroes-0.043
 loser-0.042
e-0.042
Token toys
Token ID14958
Feature activation+1.36e-01

Pos logit contributions
 mate+0.067
 superheroes+0.066
 heroes+0.062
 soldiers+0.057
 pirates+0.055
Neg logit contributions
rated-0.096
appointed-0.093
uct-0.091
ulously-0.091
aman-0.090
Token it
Token ID340
Feature activation-5.99e-02

Pos logit contributions
rated+0.272
appointed+0.263
uct+0.259
ulously+0.259
aman+0.256
Neg logit contributions
 mate-0.157
 superheroes-0.155
 heroes-0.142
 soldiers-0.131
 pirates-0.125
Token would
Token ID561
Feature activation-4.17e-02

Pos logit contributions
aman+0.115
uct+0.108
iously+0.108
ulously+0.108
icol+0.103
Neg logit contributions
 superheroes-0.094
 much-0.088
 camping-0.086
 heroes-0.086
 mate-0.085
Token be
Token ID307
Feature activation+3.33e-03

Pos logit contributions
rated+0.075
appointed+0.071
uct+0.070
ulously+0.070
aman+0.069
Neg logit contributions
 mate-0.073
 superheroes-0.072
 heroes-0.067
 soldiers-0.063
 pirates-0.061
Token a
Token ID257
Feature activation+1.11e-01

Pos logit contributions
 mate+0.004
 superheroes+0.004
 heroes+0.003
 soldiers+0.003
 pirates+0.003
Neg logit contributions
rated-0.008
appointed-0.008
uct-0.008
ulously-0.008
aman-0.007
Token lot
Token ID1256
Feature activation+6.34e-02

Pos logit contributions
 mate+0.136
 superheroes+0.134
 heroes+0.123
 soldiers+0.115
 pirates+0.109
Neg logit contributions
rated-0.250
appointed-0.241
aman-0.236
uct-0.235
ulously-0.234
Token of
Token ID286
Feature activation+1.78e-01

Pos logit contributions
 mate+0.078
 superheroes+0.075
 heroes+0.068
 soldiers+0.064
 pirates+0.060
Neg logit contributions
rated-0.147
appointed-0.142
uct-0.139
esh-0.137
ulously-0.136
Token fun
Token ID1257
Feature activation-8.82e-03

Pos logit contributions
 mate+0.250
 superheroes+0.236
 heroes+0.220
 soldiers+0.204
 pirates+0.195
Neg logit contributions
rated-0.381
appointed-0.369
uct-0.362
ulously-0.359
aman-0.352
Token.
Token ID13
Feature activation-1.82e-02

Pos logit contributions
rated+0.018
appointed+0.018
uct+0.017
ulously+0.017
aman+0.017
Neg logit contributions
 mate-0.013
 superheroes-0.013
 heroes-0.012
 soldiers-0.011
 pirates-0.010
Token But
Token ID887
Feature activation-1.75e-01

Pos logit contributions
rated+0.057
iously+0.052
ened+0.052
esh+0.051
heit+0.050
Neg logit contributions
 much-0.008
 a-0.006
 mate-0.005
-0.005
 superheroes-0.005
Token when
Token ID618
Feature activation-1.09e-01

Pos logit contributions
rated+0.407
esh+0.370
appointed+0.367
urious+0.366
inct+0.364
Neg logit contributions
 superheroes-0.219
 mate-0.217
 heroes-0.192
 pirates-0.189
 camping-0.188
Token her
Token ID607
Feature activation-3.45e-02

Pos logit contributions
rated+0.226
appointed+0.210
uct+0.210
ulously+0.207
esh+0.207
Neg logit contributions
 superheroes-0.167
 mate-0.158
 heroes-0.153
 soldiers-0.142
 much-0.141
Token him
Token ID683
Feature activation+9.38e-02

Pos logit contributions
rated+0.135
appointed+0.130
ulously+0.127
uct+0.126
esh+0.125
Neg logit contributions
 mate-0.107
 superheroes-0.105
 heroes-0.098
 soldiers-0.091
 pirates-0.088
Token up
Token ID510
Feature activation-4.35e-02

Pos logit contributions
 superheroes+0.113
 mate+0.113
 heroes+0.105
 soldiers+0.095
 camping+0.091
Neg logit contributions
rated-0.214
aman-0.212
uct-0.210
ulously-0.208
appointed-0.208
Token to
Token ID284
Feature activation-6.18e-02

Pos logit contributions
rated+0.099
appointed+0.096
uct+0.095
ulously+0.094
aman+0.094
Neg logit contributions
 mate-0.053
 superheroes-0.053
 heroes-0.049
 soldiers-0.045
 pirates-0.043
Token the
Token ID262
Feature activation-6.46e-02

Pos logit contributions
rated+0.114
ulously+0.108
uct+0.106
appointed+0.105
esh+0.104
Neg logit contributions
 mate-0.100
 superheroes-0.098
 heroes-0.091
 soldiers-0.086
izards-0.081
Token top
Token ID1353
Feature activation-1.10e-01

Pos logit contributions
rated+0.114
appointed+0.109
ulously+0.108
uct+0.107
aman+0.105
Neg logit contributions
 superheroes-0.115
 mate-0.114
 heroes-0.109
 soldiers-0.102
 pirates-0.099
Token of
Token ID286
Feature activation+1.80e-01

Pos logit contributions
rated+0.294
appointed+0.286
uct+0.284
aman+0.282
ulously+0.281
Neg logit contributions
 mate-0.095
 superheroes-0.094
 heroes-0.083
 soldiers-0.075
 much-0.072
Token his
Token ID465
Feature activation+5.57e-02

Pos logit contributions
 mate+0.287
 superheroes+0.282
 heroes+0.264
 soldiers+0.245
 pirates+0.233
Neg logit contributions
rated-0.331
ulously-0.323
appointed-0.320
uct-0.318
aman-0.317
Token house
Token ID2156
Feature activation-4.65e-02

Pos logit contributions
 superheroes+0.088
 heroes+0.084
 mate+0.082
 camping+0.076
 soldiers+0.075
Neg logit contributions
rated-0.122
uct-0.116
ulously-0.116
appointed-0.113
esh-0.111
Token.
Token ID13
Feature activation-4.57e-03

Pos logit contributions
rated+0.110
appointed+0.106
ulously+0.106
uct+0.105
aman+0.105
Neg logit contributions
 mate-0.055
 superheroes-0.055
 heroes-0.050
 soldiers-0.047
 pirates-0.045
Token Every
Token ID3887
Feature activation-1.07e-01

Pos logit contributions
rated+0.009
appointed+0.009
ulously+0.009
uct+0.008
aman+0.008
Neg logit contributions
 mate-0.007
 superheroes-0.007
 heroes-0.006
 soldiers-0.006
 pirates-0.006
Token day
Token ID1110
Feature activation-6.30e-02

Pos logit contributions
rated+0.217
uct+0.216
appointed+0.214
iped+0.207
aman+0.207
Neg logit contributions
 mate-0.162
 superheroes-0.156
 heroes-0.146
 much-0.142
 camping-0.141
Token.
Token ID13
Feature activation-3.93e-03

Pos logit contributions
rated+0.161
appointed+0.155
uct+0.153
ulously+0.153
aman+0.151
Neg logit contributions
 mate-0.105
 superheroes-0.104
 heroes-0.096
 soldiers-0.090
 pirates-0.086
Token Jack
Token ID3619
Feature activation+3.23e-02

Pos logit contributions
rated+0.008
appointed+0.007
uct+0.007
ulously+0.007
aman+0.007
Neg logit contributions
 mate-0.006
 superheroes-0.006
 heroes-0.006
 soldiers-0.005
 pirates-0.005
Token saw
Token ID2497
Feature activation+2.81e-02

Pos logit contributions
 superheroes+0.056
 mate+0.056
 heroes+0.051
 soldiers+0.050
 pirates+0.049
Neg logit contributions
rated-0.058
appointed-0.055
uct-0.055
ulously-0.054
aman-0.054
Token a
Token ID257
Feature activation+1.11e-01

Pos logit contributions
 mate+0.028
 superheroes+0.026
 heroes+0.024
e+0.021
 soldiers+0.020
Neg logit contributions
ulously-0.068
esh-0.066
rated-0.065
aman-0.065
uct-0.065
Token small
Token ID1402
Feature activation+1.87e-03

Pos logit contributions
 mate+0.176
 superheroes+0.169
e+0.162
 heroes+0.158
izards+0.151
Neg logit contributions
rated-0.195
aman-0.195
 exp-0.189
 inc-0.184
icol-0.180
Token card
Token ID2657
Feature activation+1.81e-01

Pos logit contributions
 mate+0.003
 superheroes+0.003
 heroes+0.003
e+0.003
 soldiers+0.003
Neg logit contributions
rated-0.003
aman-0.003
 exp-0.003
 inc-0.003
ened-0.003
Token near
Token ID1474
Feature activation-7.73e-03

Pos logit contributions
 superheroes+0.273
 mate+0.266
 heroes+0.250
 soldiers+0.227
 queens+0.219
Neg logit contributions
esh-0.322
uct-0.322
aman-0.320
appointed-0.318
rated-0.318
Token the
Token ID262
Feature activation-7.40e-02

Pos logit contributions
rated+0.016
ulously+0.015
uct+0.015
appointed+0.015
aman+0.015
Neg logit contributions
 mate-0.011
 superheroes-0.011
 heroes-0.010
 soldiers-0.009
 winners-0.009
Token sand
Token ID6450
Feature activation-3.05e-02

Pos logit contributions
rated+0.098
appointed+0.092
aman+0.090
 exp+0.089
ulously+0.088
Neg logit contributions
 mate-0.156
 superheroes-0.156
 heroes-0.147
 soldiers-0.138
e-0.138
Token.
Token ID13
Feature activation+1.71e-03

Pos logit contributions
rated+0.064
appointed+0.063
ulously+0.061
uct+0.061
aman+0.059
Neg logit contributions
 mate-0.045
 superheroes-0.043
 heroes-0.040
 soldiers-0.038
 pirates-0.038
Token He
Token ID679
Feature activation-2.44e-02

Pos logit contributions
 superheroes+0.002
 mate+0.002
 soldiers+0.002
 much+0.002
 pirates+0.002
Neg logit contributions
rated-0.004
iously-0.004
ulously-0.004
aman-0.004
esh-0.004
Token he
Token ID339
Feature activation+3.61e-02

Pos logit contributions
 mate+0.000
 superheroes+0.000
 heroes+0.000
prise+0.000
e+0.000
Neg logit contributions
 inc-0.000
appointed-0.000
ened-0.000
iously-0.000
esh-0.000
Token climbed
Token ID19952
Feature activation-1.23e-01

Pos logit contributions
 superheroes+0.062
 mate+0.058
 heroes+0.058
e+0.057
 much+0.054
Neg logit contributions
rated-0.066
appointed-0.062
aman-0.062
esh-0.061
uct-0.059
Token.
Token ID13
Feature activation-1.60e-02

Pos logit contributions
rated+0.272
aman+0.259
uct+0.257
urious+0.256
appointed+0.255
Neg logit contributions
 superheroes-0.163
 mate-0.157
 heroes-0.152
 pirates-0.141
 soldiers-0.141
Token Wh
Token ID854
Feature activation-2.10e-02

Pos logit contributions
rated+0.035
urious+0.033
aman+0.031
uct+0.031
ulously+0.031
Neg logit contributions
 mate-0.022
 superheroes-0.022
 much-0.020
 dinosaurs-0.020
 soldiers-0.019
Tokenisk
Token ID1984
Feature activation+3.57e-02

Pos logit contributions
rated+0.034
appointed+0.032
uct+0.032
ulously+0.032
aman+0.031
Neg logit contributions
 mate-0.040
 superheroes-0.040
 heroes-0.038
 soldiers-0.036
 pirates-0.035
Tokeners
Token ID364
Feature activation+1.43e-01

Pos logit contributions
 mate+0.051
 superheroes+0.050
 heroes+0.045
 soldiers+0.043
 pirates+0.041
Neg logit contributions
rated-0.075
ulously-0.072
appointed-0.072
uct-0.071
esh-0.071
Token me
Token ID502
Feature activation-5.72e-02

Pos logit contributions
 mate+0.247
 superheroes+0.237
 heroes+0.227
 soldiers+0.217
e+0.216
Neg logit contributions
rated-0.265
icol-0.245
appointed-0.240
aman-0.236
ulously-0.230
Tokenowed
Token ID6972
Feature activation+4.76e-02

Pos logit contributions
rated+0.078
appointed+0.074
uct+0.072
ulously+0.072
aman+0.071
Neg logit contributions
 mate-0.123
 superheroes-0.122
 heroes-0.116
 soldiers-0.111
 pirates-0.108
Token and
Token ID290
Feature activation-1.22e-02

Pos logit contributions
 mate+0.078
 superheroes+0.076
 heroes+0.070
 soldiers+0.066
 winners+0.063
Neg logit contributions
rated-0.089
appointed-0.085
esh-0.083
ulously-0.083
 inc-0.082
Token watched
Token ID7342
Feature activation-8.51e-02

Pos logit contributions
rated+0.025
ulously+0.024
urious+0.024
aman+0.024
appointed+0.024
Neg logit contributions
 superheroes-0.019
 mate-0.019
 heroes-0.017
 soldiers-0.016
 pirates-0.016
Token Tim
Token ID5045
Feature activation-2.66e-02

Pos logit contributions
rated+0.155
appointed+0.150
uct+0.148
ulously+0.147
esh+0.147
Neg logit contributions
 mate-0.141
 superheroes-0.137
 heroes-0.129
 soldiers-0.119
 pirates-0.115
Token around
Token ID1088
Feature activation-5.35e-02

Pos logit contributions
 mate+0.133
 superheroes+0.132
 heroes+0.122
 soldiers+0.114
 pirates+0.109
Neg logit contributions
rated-0.184
appointed-0.177
uct-0.173
ulously-0.173
aman-0.170
Token".
Token ID1911
Feature activation-6.87e-02

Pos logit contributions
rated+0.107
appointed+0.103
uct+0.101
ulously+0.101
aman+0.100
Neg logit contributions
 mate-0.080
 superheroes-0.080
 heroes-0.074
 soldiers-0.069
 pirates-0.066
Token The
Token ID383
Feature activation-1.01e-01

Pos logit contributions
rated+0.130
appointed+0.120
aman+0.116
esh+0.115
uct+0.115
Neg logit contributions
 superheroes-0.117
 mate-0.116
 heroes-0.110
 soldiers-0.105
 pirates-0.101
Token two
Token ID734
Feature activation+3.19e-02

Pos logit contributions
rated+0.209
ulously+0.202
appointed+0.200
 inc+0.198
uct+0.195
Neg logit contributions
 superheroes-0.132
 mate-0.126
 heroes-0.118
e-0.112
 soldiers-0.107
Token friends
Token ID2460
Feature activation+6.28e-02

Pos logit contributions
 superheroes+0.033
 mate+0.033
 heroes+0.028
 DVD+0.027
uggets+0.026
Neg logit contributions
rated-0.073
ulously-0.072
 inc-0.071
ened-0.071
appointed-0.070
Token smiled
Token ID13541
Feature activation+5.05e-02

Pos logit contributions
 mate+0.111
 superheroes+0.108
 heroes+0.102
 soldiers+0.097
 pirates+0.094
Neg logit contributions
rated-0.111
appointed-0.108
aman-0.105
uct-0.105
ulously-0.103
Token and
Token ID290
Feature activation-2.53e-02

Pos logit contributions
 mate+0.074
 superheroes+0.073
 heroes+0.069
 soldiers+0.064
 pirates+0.062
Neg logit contributions
rated-0.104
appointed-0.100
uct-0.099
ulously-0.098
aman-0.097
Token thanked
Token ID26280
Feature activation-8.71e-02

Pos logit contributions
rated+0.049
aman+0.046
urious+0.046
appointed+0.046
uct+0.045
Neg logit contributions
 mate-0.041
 superheroes-0.041
 heroes-0.039
 soldiers-0.036
 much-0.036
Token the
Token ID262
Feature activation-7.82e-02

Pos logit contributions
rated+0.178
appointed+0.171
uct+0.168
ulously+0.167
aman+0.165
Neg logit contributions
 mate-0.129
 superheroes-0.129
 heroes-0.120
 soldiers-0.112
 pirates-0.108
Token bigger
Token ID5749
Feature activation-2.11e-02

Pos logit contributions
rated+0.165
appointed+0.160
ulously+0.158
esh+0.157
uct+0.156
Neg logit contributions
 superheroes-0.104
 mate-0.101
 heroes-0.093
e-0.087
 soldiers-0.086
Token fish
Token ID5916
Feature activation+1.04e-01

Pos logit contributions
rated+0.048
appointed+0.047
uct+0.046
ulously+0.046
aman+0.045
Neg logit contributions
 mate-0.027
 superheroes-0.026
 heroes-0.024
 soldiers-0.022
 pirates-0.021
Token,
Token ID11
Feature activation+6.50e-02

Pos logit contributions
 mate+0.009
 superheroes+0.009
 heroes+0.008
 soldiers+0.007
 pirates+0.007
Neg logit contributions
rated-0.014
appointed-0.013
ulously-0.013
aman-0.013
uct-0.013
Token we
Token ID356
Feature activation+5.89e-02

Pos logit contributions
 superheroes+0.098
 mate+0.098
e+0.094
aky+0.093
 heroes+0.092
Neg logit contributions
uct-0.101
esh-0.100
aman-0.099
rated-0.099
ulously-0.099
Token are
Token ID389
Feature activation+1.63e-01

Pos logit contributions
 mate+0.079
 superheroes+0.077
 heroes+0.071
 soldiers+0.067
 camping+0.065
Neg logit contributions
rated-0.124
ulously-0.121
appointed-0.120
uct-0.119
 inc-0.114
Token sorry
Token ID7926
Feature activation+1.02e-01

Pos logit contributions
 mate+0.285
 tyrann+0.260
ancer+0.259
 Antarctica+0.252
 pupp+0.249
Neg logit contributions
uct-0.256
appointed-0.214
arrass-0.190
ulously-0.189
ths-0.188
Token.
Token ID13
Feature activation-1.53e-03

Pos logit contributions
 mate+0.160
 superheroes+0.158
 heroes+0.145
 soldiers+0.137
e+0.137
Neg logit contributions
rated-0.192
appointed-0.183
esh-0.180
uct-0.177
ulously-0.177
Token We
Token ID775
Feature activation+3.17e-02

Pos logit contributions
rated+0.003
appointed+0.003
uct+0.003
aman+0.003
ulously+0.003
Neg logit contributions
 mate-0.002
 superheroes-0.002
 heroes-0.002
 soldiers-0.002
 pirates-0.002
Token were
Token ID547
Feature activation+1.13e-01

Pos logit contributions
 mate+0.049
 superheroes+0.049
 heroes+0.045
 soldiers+0.042
 pirates+0.041
Neg logit contributions
rated-0.063
appointed-0.060
uct-0.059
ulously-0.059
aman-0.059
Token wrong
Token ID2642
Feature activation+1.31e-02

Pos logit contributions
 mate+0.189
 Antarctica+0.170
 tyrann+0.160
ancer+0.159
 DVD+0.158
Neg logit contributions
uct-0.191
iped-0.167
appointed-0.166
arrass-0.165
ulously-0.158
Token.
Token ID13
Feature activation-1.66e-03

Pos logit contributions
 mate+0.021
 superheroes+0.020
 heroes+0.019
 soldiers+0.017
 pirates+0.017
Neg logit contributions
rated-0.025
appointed-0.024
uct-0.023
ulously-0.023
esh-0.023
Token We
Token ID775
Feature activation+3.15e-02

Pos logit contributions
rated+0.003
appointed+0.003
ulously+0.003
uct+0.003
aman+0.003
Neg logit contributions
 mate-0.003
 superheroes-0.003
 heroes-0.003
 soldiers-0.003
 pirates-0.002
Token should
Token ID815
Feature activation-6.58e-02

Pos logit contributions
 mate+0.051
 superheroes+0.051
 heroes+0.048
 soldiers+0.045
 pirates+0.043
Neg logit contributions
rated-0.060
appointed-0.057
uct-0.056
ulously-0.056
aman-0.056
Token riding
Token ID10311
Feature activation+5.62e-02

Pos logit contributions
appointed+0.095
rated+0.095
uct+0.093
esh+0.091
ulously+0.091
Neg logit contributions
 mate-0.048
 superheroes-0.040
 heroes-0.037
prise-0.036
 soldiers-0.036
Token in
Token ID287
Feature activation+4.18e-02

Pos logit contributions
 mate+0.080
 superheroes+0.079
 heroes+0.073
 soldiers+0.068
 pirates+0.065
Neg logit contributions
rated-0.118
appointed-0.114
uct-0.112
ulously-0.112
aman-0.110
Token a
Token ID257
Feature activation+1.16e-01

Pos logit contributions
 mate+0.078
 superheroes+0.074
 heroes+0.071
 soldiers+0.067
prise+0.064
Neg logit contributions
ulously-0.065
aman-0.062
uct-0.061
 inc-0.061
ened-0.060
Token me
Token ID502
Feature activation-5.72e-02

Pos logit contributions
 mate+0.184
 superheroes+0.183
 heroes+0.171
 soldiers+0.160
 pirates+0.155
Neg logit contributions
rated-0.216
appointed-0.208
ulously-0.206
uct-0.205
aman-0.204
Tokenadow
Token ID4584
Feature activation+5.61e-03

Pos logit contributions
rated+0.087
appointed+0.081
uct+0.079
urious+0.079
iously+0.078
Neg logit contributions
 superheroes-0.111
 mate-0.108
 heroes-0.105
 soldiers-0.103
 dinosaurs-0.096
Token with
Token ID351
Feature activation+5.62e-02

Pos logit contributions
 mate+0.008
 superheroes+0.008
 heroes+0.008
 soldiers+0.007
 pirates+0.007
Neg logit contributions
rated-0.011
appointed-0.011
uct-0.010
ulously-0.010
aman-0.010
Token flowers
Token ID12734
Feature activation-4.78e-02

Pos logit contributions
 mate+0.093
 superheroes+0.086
 heroes+0.080
prise+0.078
 camping+0.077
Neg logit contributions
ulously-0.095
ened-0.092
 inc-0.090
iped-0.086
appointed-0.085
Token and
Token ID290
Feature activation-2.75e-03

Pos logit contributions
 inc+0.073
rated+0.073
appointed+0.073
uct+0.072
iously+0.072
Neg logit contributions
 mate-0.083
 superheroes-0.081
 heroes-0.076
 soldiers-0.072
prise-0.072
Token birds
Token ID10087
Feature activation-3.07e-02

Pos logit contributions
rated+0.005
 inc+0.005
ulously+0.005
appointed+0.004
ened+0.004
Neg logit contributions
 mate-0.005
 superheroes-0.004
 heroes-0.004
prise-0.004
e-0.004
Token.
Token ID13
Feature activation-5.38e-03

Pos logit contributions
 inc+0.046
ened+0.045
appointed+0.044
rated+0.044
iously+0.043
Neg logit contributions
 mate-0.056
 superheroes-0.053
prise-0.051
 heroes-0.050
 backup-0.048
Token
Token ID198
Feature activation+6.30e-02

Pos logit contributions
rated+0.010
appointed+0.009
uct+0.009
ulously+0.009
aman+0.009
Neg logit contributions
 mate-0.009
 superheroes-0.009
 heroes-0.008
 soldiers-0.008
 pirates-0.008
Token of
Token ID286
Feature activation+1.64e-01

Pos logit contributions
rated+0.109
appointed+0.106
uct+0.105
ulously+0.105
esh+0.104
Neg logit contributions
 superheroes-0.038
 mate-0.037
 heroes-0.033
 soldiers-0.028
 pirates-0.026
Token candy
Token ID18550
Feature activation+1.09e-01

Pos logit contributions
 mate+0.306
 superheroes+0.303
 heroes+0.286
 soldiers+0.271
 pirates+0.263
Neg logit contributions
rated-0.268
appointed-0.256
uct-0.250
ulously-0.250
aman-0.247
Token!
Token ID0
Feature activation-7.87e-02

Pos logit contributions
 mate+0.164
 superheroes+0.162
 heroes+0.150
 soldiers+0.140
 pirates+0.134
Neg logit contributions
rated-0.216
appointed-0.207
uct-0.205
ulously-0.203
aman-0.203
Token
Token ID198
Feature activation+4.39e-02

Pos logit contributions
rated+0.151
appointed+0.142
ulously+0.139
uct+0.139
aman+0.137
Neg logit contributions
 mate-0.129
 superheroes-0.127
 heroes-0.119
 soldiers-0.112
 pirates-0.108
Token
Token ID198
Feature activation+4.58e-02

Pos logit contributions
 mate+0.063
 superheroes+0.063
 heroes+0.058
 soldiers+0.054
 pirates+0.052
Neg logit contributions
rated-0.090
appointed-0.088
uct-0.088
ulously-0.087
aman-0.085
TokenDave
Token ID27984
Feature activation+6.45e-02

Pos logit contributions
 mate+0.077
 superheroes+0.077
 heroes+0.072
 soldiers+0.068
 pirates+0.066
Neg logit contributions
rated-0.084
appointed-0.081
uct-0.079
ulously-0.079
aman-0.078
Token was
Token ID373
Feature activation-6.06e-02

Pos logit contributions
 mate+0.115
 superheroes+0.111
 heroes+0.108
e+0.107
 soldiers+0.101
Neg logit contributions
rated-0.111
appointed-0.106
uct-0.102
aman-0.102
esh-0.101
Token so
Token ID523
Feature activation-7.54e-02

Pos logit contributions
appointed+0.124
rated+0.124
uct+0.123
ulously+0.121
aman+0.117
Neg logit contributions
 mate-0.087
 superheroes-0.086
 heroes-0.078
 soldiers-0.075
 dinosaurs-0.070
Token happy
Token ID3772
Feature activation+2.31e-02

Pos logit contributions
rated+0.155
appointed+0.153
uct+0.151
ulously+0.148
aman+0.144
Neg logit contributions
 mate-0.111
 superheroes-0.109
 heroes-0.098
 soldiers-0.095
 dinosaurs-0.089
Token.
Token ID13
Feature activation-2.48e-02

Pos logit contributions
 superheroes+0.033
 mate+0.033
 heroes+0.030
 soldiers+0.028
 pirates+0.028
Neg logit contributions
rated-0.050
appointed-0.048
ulously-0.047
uct-0.047
aman-0.046
Token He
Token ID679
Feature activation-4.20e-02

Pos logit contributions
rated+0.057
aman+0.052
esh+0.051
ulously+0.051
appointed+0.050
Neg logit contributions
 mate-0.032
 superheroes-0.029
 heroes-0.029
 much-0.029
 soldiers-0.027
Token woods
Token ID16479
Feature activation-9.94e-02

Pos logit contributions
rated+0.110
appointed+0.103
uct+0.102
iously+0.101
ulously+0.099
Neg logit contributions
 superheroes-0.111
 mate-0.110
 heroes-0.104
 soldiers-0.101
 pirates-0.098
Token behind
Token ID2157
Feature activation-2.65e-02

Pos logit contributions
rated+0.168
appointed+0.159
esh+0.154
 inc+0.153
ulously+0.152
Neg logit contributions
 mate-0.172
 superheroes-0.170
 heroes-0.156
 soldiers-0.146
 tyrann-0.144
Token their
Token ID511
Feature activation+1.21e-01

Pos logit contributions
ulously+0.045
esh+0.044
 inc+0.042
 exp+0.041
ened+0.041
Neg logit contributions
 mate-0.047
 superheroes-0.044
 heroes-0.042
 winners-0.040
 loser-0.039
Token house
Token ID2156
Feature activation-5.61e-02

Pos logit contributions
 mate+0.225
 superheroes+0.224
 heroes+0.212
 soldiers+0.202
 pirates+0.195
Neg logit contributions
rated-0.203
appointed-0.193
uct-0.190
ulously-0.188
aman-0.184
Token.
Token ID13
Feature activation+1.10e-03

Pos logit contributions
rated+0.129
appointed+0.125
ulously+0.123
uct+0.123
aman+0.122
Neg logit contributions
 mate-0.071
 superheroes-0.070
 heroes-0.064
 soldiers-0.060
 pirates-0.058
Token One
Token ID1881
Feature activation+2.44e-03

Pos logit contributions
 superheroes+0.002
 mate+0.002
 heroes+0.002
 soldiers+0.002
 pirates+0.002
Neg logit contributions
rated-0.002
appointed-0.002
uct-0.002
ulously-0.002
aman-0.002
Token day
Token ID1110
Feature activation-6.95e-02

Pos logit contributions
 mate+0.004
 superheroes+0.004
 heroes+0.003
 camping+0.003
 much+0.003
Neg logit contributions
uct-0.005
rated-0.005
appointed-0.005
aman-0.005
iously-0.005
Token,
Token ID11
Feature activation+6.85e-02

Pos logit contributions
appointed+0.107
rated+0.106
aman+0.105
ened+0.103
esh+0.102
Neg logit contributions
 superheroes-0.126
 mate-0.120
 heroes-0.118
 soldiers-0.109
aky-0.108
Token they
Token ID484
Feature activation+9.36e-02

Pos logit contributions
 mate+0.103
 superheroes+0.102
 heroes+0.098
e+0.089
 soldiers+0.088
Neg logit contributions
rated-0.128
appointed-0.128
aman-0.126
ulously-0.126
uct-0.123
Token find
Token ID1064
Feature activation-2.68e-02

Pos logit contributions
 superheroes+0.138
 mate+0.138
 heroes+0.131
 soldiers+0.120
 dinosaurs+0.116
Neg logit contributions
rated-0.185
appointed-0.173
 inc-0.170
uct-0.170
ulously-0.170
Token a
Token ID257
Feature activation+1.18e-01

Pos logit contributions
ulously+0.059
esh+0.056
inct+0.055
 inc+0.055
iped+0.054
Neg logit contributions
 superheroes-0.029
 mate-0.028
 queens-0.027
 winners-0.026
 heroes-0.025
Token a
Token ID257
Feature activation+1.15e-01

Pos logit contributions
rated+0.241
appointed+0.235
ulously+0.231
uct+0.230
esh+0.227
Neg logit contributions
 mate-0.135
 superheroes-0.131
 heroes-0.121
 soldiers-0.110
 pirates-0.104
Token small
Token ID1402
Feature activation+6.46e-03

Pos logit contributions
 mate+0.171
 superheroes+0.170
 heroes+0.158
 soldiers+0.147
 pirates+0.141
Neg logit contributions
rated-0.233
appointed-0.223
ulously-0.220
uct-0.220
aman-0.215
Token hill
Token ID12788
Feature activation-1.07e-01

Pos logit contributions
 mate+0.013
 superheroes+0.013
 heroes+0.013
 soldiers+0.012
 pirates+0.012
Neg logit contributions
rated-0.009
uct-0.009
appointed-0.009
ulously-0.009
esh-0.008
Token near
Token ID1474
Feature activation-3.73e-03

Pos logit contributions
rated+0.202
appointed+0.195
uct+0.188
ulously+0.186
esh+0.184
Neg logit contributions
 superheroes-0.176
 mate-0.174
 heroes-0.165
 soldiers-0.152
 pirates-0.146
Token his
Token ID465
Feature activation+5.15e-02

Pos logit contributions
rated+0.008
appointed+0.007
ulously+0.007
uct+0.007
esh+0.007
Neg logit contributions
 mate-0.006
 superheroes-0.005
 heroes-0.005
 soldiers-0.005
 pirates-0.004
Token house
Token ID2156
Feature activation-4.61e-02

Pos logit contributions
 mate+0.093
 superheroes+0.092
 heroes+0.088
 soldiers+0.083
 pirates+0.080
Neg logit contributions
rated-0.092
appointed-0.086
uct-0.086
ulously-0.084
aman-0.082
Token.
Token ID13
Feature activation-2.97e-04

Pos logit contributions
rated+0.114
ulously+0.110
aman+0.109
appointed+0.108
uct+0.108
Neg logit contributions
 mate-0.049
 superheroes-0.047
 heroes-0.042
 soldiers-0.040
 pirates-0.040
Token He
Token ID679
Feature activation-2.66e-02

Pos logit contributions
rated+0.001
aman+0.001
uct+0.001
iously+0.001
ulously+0.001
Neg logit contributions
 mate-0.000
 superheroes-0.000
 much-0.000
 fishing-0.000
 pirates-0.000
Token put
Token ID1234
Feature activation-6.19e-02

Pos logit contributions
aman+0.053
icol+0.053
rated+0.052
umm+0.050
iously+0.050
Neg logit contributions
 mate-0.038
 superheroes-0.038
 much-0.036
 heroes-0.034
 very-0.034
Token on
Token ID319
Feature activation+5.49e-02

Pos logit contributions
rated+0.155
appointed+0.150
ulously+0.148
uct+0.148
aman+0.146
Neg logit contributions
 mate-0.063
 superheroes-0.063
 heroes-0.056
 soldiers-0.050
 pirates-0.047
Token his
Token ID465
Feature activation+5.25e-02

Pos logit contributions
 much+0.034
 a+0.033
 mate+0.031
 camping+0.029
 superheroes+0.028
Neg logit contributions
rated-0.162
uct-0.151
aman-0.147
heart-0.145
umm-0.144
Token and
Token ID290
Feature activation-1.83e-02

Pos logit contributions
rated+0.030
appointed+0.029
uct+0.029
ulously+0.029
aman+0.029
Neg logit contributions
 mate-0.023
 superheroes-0.023
 heroes-0.021
 soldiers-0.020
 pirates-0.019
Token bananas
Token ID35484
Feature activation+5.48e-02

Pos logit contributions
rated+0.035
appointed+0.033
uct+0.032
inct+0.032
esh+0.031
Neg logit contributions
 superheroes-0.031
 mate-0.030
 heroes-0.029
 soldiers-0.028
 pirates-0.027
Token and
Token ID290
Feature activation-1.88e-02

Pos logit contributions
 mate+0.076
 superheroes+0.075
 heroes+0.070
 soldiers+0.065
 pirates+0.062
Neg logit contributions
rated-0.117
appointed-0.112
ulously-0.110
uct-0.110
aman-0.109
Token walked
Token ID6807
Feature activation-7.24e-02

Pos logit contributions
rated+0.034
appointed+0.033
uct+0.032
inct+0.032
esh+0.031
Neg logit contributions
 superheroes-0.033
 mate-0.033
 heroes-0.031
 soldiers-0.030
 pirates-0.029
Token back
Token ID736
Feature activation+5.48e-03

Pos logit contributions
rated+0.133
appointed+0.129
uct+0.125
ulously+0.125
esh+0.123
Neg logit contributions
 superheroes-0.122
 mate-0.120
 heroes-0.113
 soldiers-0.106
 pirates-0.101
Token home
Token ID1363
Feature activation-5.42e-02

Pos logit contributions
 superheroes+0.007
 mate+0.007
 heroes+0.007
 soldiers+0.007
 camping+0.006
Neg logit contributions
rated-0.012
appointed-0.011
uct-0.011
ulously-0.011
aman-0.011
Token.
Token ID13
Feature activation-1.88e-02

Pos logit contributions
rated+0.104
appointed+0.102
uct+0.099
esh+0.097
aman+0.097
Neg logit contributions
 mate-0.085
 superheroes-0.084
 heroes-0.077
 soldiers-0.073
 pirates-0.070
Token He
Token ID679
Feature activation-3.28e-02

Pos logit contributions
rated+0.032
esh+0.029
aman+0.029
appointed+0.029
ulously+0.029
Neg logit contributions
 mate-0.035
 superheroes-0.034
 heroes-0.032
 soldiers-0.030
 much-0.030
Token was
Token ID373
Feature activation-5.31e-02

Pos logit contributions
rated+0.059
appointed+0.056
esh+0.053
inct+0.053
uct+0.052
Neg logit contributions
 superheroes-0.057
 mate-0.055
 heroes-0.053
e-0.051
 much-0.051
Token very
Token ID845
Feature activation+1.31e-01

Pos logit contributions
appointed+0.117
rated+0.116
uct+0.116
ulously+0.114
esh+0.108
Neg logit contributions
 mate-0.068
 superheroes-0.066
 heroes-0.059
 soldiers-0.057
 dinosaurs-0.052
Token happy
Token ID3772
Feature activation+3.16e-02

Pos logit contributions
 mate+0.160
 superheroes+0.159
 heroes+0.141
 soldiers+0.134
 pirates+0.124
Neg logit contributions
rated-0.302
appointed-0.296
uct-0.289
ulously-0.283
aman-0.279
Token before
Token ID878
Feature activation-7.58e-02

Pos logit contributions
rated+0.124
iously+0.116
ulously+0.116
uct+0.116
appointed+0.116
Neg logit contributions
 mate-0.102
 superheroes-0.097
 heroes-0.090
 winners-0.087
 tyrann-0.084
Token they
Token ID484
Feature activation+8.67e-02

Pos logit contributions
rated+0.168
appointed+0.164
uct+0.161
ulously+0.160
aman+0.160
Neg logit contributions
 mate-0.097
 superheroes-0.095
 heroes-0.088
 soldiers-0.081
 pirates-0.076
Token tried
Token ID3088
Feature activation-7.53e-02

Pos logit contributions
 mate+0.150
 superheroes+0.149
 heroes+0.140
 soldiers+0.133
 pirates+0.127
Neg logit contributions
rated-0.154
appointed-0.145
uct-0.144
ulously-0.143
 inc-0.140
Token new
Token ID649
Feature activation+1.87e-02

Pos logit contributions
rated+0.139
ulously+0.136
appointed+0.136
uct+0.133
 inc+0.131
Neg logit contributions
 mate-0.122
 superheroes-0.113
 heroes-0.107
 soldiers-0.097
e-0.095
Token things
Token ID1243
Feature activation-2.84e-02

Pos logit contributions
 superheroes+0.032
 mate+0.031
 heroes+0.030
 soldiers+0.028
 pirates+0.027
Neg logit contributions
rated-0.034
appointed-0.033
uct-0.032
ulously-0.032
aman-0.032
Token.
Token ID13
Feature activation-4.66e-03

Pos logit contributions
rated+0.053
appointed+0.050
uct+0.050
aman+0.049
esh+0.049
Neg logit contributions
 mate-0.045
 superheroes-0.044
 heroes-0.041
 soldiers-0.039
e-0.037
Token<|endoftext|>
Token ID50256
Feature activation+3.24e-03

Pos logit contributions
rated+0.009
appointed+0.009
uct+0.008
ulously+0.008
aman+0.008
Neg logit contributions
 mate-0.008
 superheroes-0.007
 heroes-0.007
 soldiers-0.007
 pirates-0.006
TokenL
Token ID43
Feature activation+3.01e-02

Pos logit contributions
 mate+0.008
 superheroes+0.007
 heroes+0.007
 soldiers+0.007
 winners+0.007
Neg logit contributions
inct-0.003
uct-0.003
rated-0.003
ulously-0.003
esh-0.003
Tokenily
Token ID813
Feature activation+1.07e-02

Pos logit contributions
 superheroes+0.048
 mate+0.045
 heroes+0.045
 winners+0.039
 tyrann+0.038
Neg logit contributions
ulously-0.057
aman-0.056
uct-0.055
rated-0.055
esh-0.054
Token was
Token ID373
Feature activation-4.14e-02

Pos logit contributions
 superheroes+0.016
 mate+0.015
 heroes+0.014
e+0.014
 pirates+0.014
Neg logit contributions
appointed-0.023
rated-0.022
uct-0.022
ulously-0.021
iously-0.021
Token a
Token ID257
Feature activation+1.22e-01

Pos logit contributions
appointed+0.085
uct+0.085
ulously+0.082
rated+0.079
aman+0.078
Neg logit contributions
 mate-0.059
 superheroes-0.052
 heroes-0.050
 queens-0.050
 tyrann-0.046
Token on
Token ID319
Feature activation+4.88e-02

Pos logit contributions
 superheroes+0.110
 mate+0.110
 heroes+0.101
 soldiers+0.095
 pirates+0.091
Neg logit contributions
rated-0.183
appointed-0.176
ulously-0.174
uct-0.173
aman-0.172
Token top
Token ID1353
Feature activation-1.20e-01

Pos logit contributions
 mate+0.076
 superheroes+0.075
 heroes+0.070
 soldiers+0.066
 pirates+0.063
Neg logit contributions
rated-0.094
appointed-0.091
ulously-0.091
uct-0.090
aman-0.090
Token of
Token ID286
Feature activation+1.75e-01

Pos logit contributions
rated+0.342
appointed+0.333
uct+0.329
ulously+0.329
aman+0.326
Neg logit contributions
 mate-0.079
 superheroes-0.077
 heroes-0.065
 soldiers-0.054
 pirates-0.048
Token the
Token ID262
Feature activation-6.70e-02

Pos logit contributions
 mate+0.278
 superheroes+0.270
 heroes+0.256
 soldiers+0.235
 camping+0.223
Neg logit contributions
ulously-0.322
aman-0.320
uct-0.309
esh-0.309
 inc-0.306
Token slide
Token ID10649
Feature activation-2.63e-02

Pos logit contributions
rated+0.120
appointed+0.113
uct+0.112
ulously+0.111
iously+0.110
Neg logit contributions
 superheroes-0.118
 mate-0.118
 heroes-0.112
 soldiers-0.106
 pirates-0.104
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
rated+0.060
appointed+0.057
ulously+0.057
uct+0.056
esh+0.056
Neg logit contributions
 mate-0.032
 superheroes-0.032
 heroes-0.029
 soldiers-0.028
 pirates-0.026
Token
Token ID220
Feature activation-2.72e-02

Pos logit contributions
rated+0.028
esh+0.024
iously+0.023
ulously+0.023
urious+0.023
Neg logit contributions
 superheroes-0.012
 much-0.012
 mate-0.011
 soldiers-0.011
 Robo-0.011
Token
Token ID198
Feature activation+4.71e-02

Pos logit contributions
rated+0.054
appointed+0.053
uct+0.053
ulously+0.052
aman+0.051
Neg logit contributions
 mate-0.041
 superheroes-0.041
 heroes-0.038
 soldiers-0.035
 pirates-0.034
Token
Token ID198
Feature activation+4.81e-02

Pos logit contributions
 mate+0.065
 superheroes+0.064
 heroes+0.060
 soldiers+0.056
 pirates+0.053
Neg logit contributions
rated-0.100
appointed-0.097
uct-0.096
ulously-0.095
aman-0.094
TokenL
Token ID43
Feature activation+1.53e-02

Pos logit contributions
 superheroes+0.071
 mate+0.070
 heroes+0.066
 soldiers+0.061
 much+0.061
Neg logit contributions
rated-0.100
iously-0.093
ulously-0.091
ened-0.091
aman-0.091
Tokenily
Token ID813
Feature activation-5.78e-04

Pos logit contributions
 mate+0.017
 superheroes+0.017
 heroes+0.015
 soldiers+0.014
 pirates+0.013
Neg logit contributions
rated-0.037
appointed-0.036
uct-0.035
ulously-0.035
aman-0.035
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
rated+0.077
appointed+0.072
uct+0.072
iously+0.072
ulously+0.072
Neg logit contributions
 superheroes-0.069
 mate-0.066
 heroes-0.063
 soldiers-0.059
 pirates-0.056
Token He
Token ID679
Feature activation-3.00e-02

Pos logit contributions
rated+0.023
esh+0.020
aman+0.020
appointed+0.019
ulously+0.019
Neg logit contributions
 mate-0.024
 superheroes-0.024
 heroes-0.023
 soldiers-0.022
 pirates-0.022
Token looked
Token ID3114
Feature activation+7.33e-03

Pos logit contributions
rated+0.055
appointed+0.054
aman+0.053
esh+0.051
uct+0.050
Neg logit contributions
 mate-0.052
 superheroes-0.049
 heroes-0.045
 pirates-0.045
e-0.044
Token around
Token ID1088
Feature activation-5.25e-02

Pos logit contributions
 mate+0.011
 superheroes+0.011
 heroes+0.010
 soldiers+0.009
 pirates+0.009
Neg logit contributions
rated-0.015
appointed-0.015
uct-0.014
ulously-0.014
aman-0.014
Token and
Token ID290
Feature activation-1.30e-02

Pos logit contributions
rated+0.105
appointed+0.102
uct+0.100
ulously+0.100
aman+0.099
Neg logit contributions
 mate-0.079
 superheroes-0.078
 heroes-0.072
 soldiers-0.068
 pirates-0.065
Token decided
Token ID3066
Feature activation-1.85e-01

Pos logit contributions
rated+0.026
appointed+0.025
ulously+0.024
aman+0.024
esh+0.024
Neg logit contributions
 mate-0.020
 superheroes-0.020
 heroes-0.018
 pirates-0.017
 soldiers-0.017
Token to
Token ID284
Feature activation-6.88e-02

Pos logit contributions
rated+0.451
ulously+0.425
aman+0.418
appointed+0.417
urious+0.416
Neg logit contributions
 mate-0.231
 superheroes-0.222
 heroes-0.206
 pirates-0.195
 much-0.189
Token choose
Token ID3853
Feature activation+5.48e-02

Pos logit contributions
rated+0.148
appointed+0.139
uct+0.136
aman+0.135
iously+0.135
Neg logit contributions
 mate-0.100
 superheroes-0.093
e-0.084
 heroes-0.083
 pirates-0.081
Token an
Token ID281
Feature activation-2.05e-03

Pos logit contributions
 mate+0.081
 superheroes+0.079
 heroes+0.072
 soldiers+0.069
e+0.066
Neg logit contributions
rated-0.108
uct-0.105
appointed-0.105
ulously-0.104
aman-0.103
Token even
Token ID772
Feature activation+8.04e-04

Pos logit contributions
rated+0.004
appointed+0.003
uct+0.003
ulously+0.003
aman+0.003
Neg logit contributions
 mate-0.004
 superheroes-0.004
 heroes-0.003
 soldiers-0.003
 pirates-0.003
Token sun
Token ID4252
Feature activation-1.05e-01

Pos logit contributions
 superheroes+0.001
 mate+0.001
 heroes+0.001
 soldiers+0.001
 pirates+0.001
Neg logit contributions
rated-0.002
aman-0.002
appointed-0.002
ulously-0.002
esh-0.002
Token of
Token ID286
Feature activation+1.84e-01

Pos logit contributions
 mate+0.009
 superheroes+0.008
 heroes+0.007
 soldiers+0.006
 camping+0.006
Neg logit contributions
rated-0.021
ened-0.021
ulously-0.020
appointed-0.020
iously-0.020
Token it
Token ID340
Feature activation-4.48e-02

Pos logit contributions
 mate+0.307
 superheroes+0.305
 heroes+0.286
 soldiers+0.269
 pirates+0.259
Neg logit contributions
rated-0.338
appointed-0.324
ulously-0.320
uct-0.319
aman-0.315
Token,
Token ID11
Feature activation+6.23e-02

Pos logit contributions
rated+0.099
appointed+0.096
uct+0.095
ulously+0.094
aman+0.093
Neg logit contributions
 mate-0.058
 superheroes-0.058
 heroes-0.053
 soldiers-0.049
 pirates-0.047
Token but
Token ID475
Feature activation-9.30e-02

Pos logit contributions
 mate+0.088
 superheroes+0.088
 heroes+0.081
 soldiers+0.076
 pirates+0.074
Neg logit contributions
rated-0.133
appointed-0.127
ulously-0.125
uct-0.125
aman-0.124
Token he
Token ID339
Feature activation+3.91e-02

Pos logit contributions
rated+0.172
appointed+0.165
ulously+0.162
uct+0.162
aman+0.159
Neg logit contributions
 mate-0.155
 superheroes-0.154
 heroes-0.144
 soldiers-0.136
 pirates-0.130
Token couldn
Token ID3521
Feature activation-1.75e-01

Pos logit contributions
 superheroes+0.089
 mate+0.089
 heroes+0.085
 soldiers+0.081
 pirates+0.080
Neg logit contributions
rated-0.049
appointed-0.046
uct-0.044
aman-0.044
ulously-0.044
Token't
Token ID470
Feature activation+1.29e-01

Pos logit contributions
rated+0.454
appointed+0.440
uct+0.434
ulously+0.433
aman+0.430
Neg logit contributions
 mate-0.160
 superheroes-0.159
 heroes-0.141
 soldiers-0.125
 pirates-0.116
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
 mate+0.210
 superheroes+0.208
 heroes+0.196
 soldiers+0.187
 dinosaurs+0.177
Neg logit contributions
rated-0.242
appointed-0.230
uct-0.227
esh-0.223
ulously-0.223
Token He
Token ID679
Feature activation-2.29e-02

Pos logit contributions
rated+0.022
aman+0.021
esh+0.019
uct+0.019
appointed+0.019
Neg logit contributions
 superheroes-0.015
 mate-0.015
 heroes-0.014
 dinosaurs-0.014
 pirates-0.014
Token was
Token ID373
Feature activation-4.49e-02

Pos logit contributions
aman+0.039
rated+0.038
appointed+0.036
esh+0.036
uct+0.036
Neg logit contributions
 superheroes-0.042
 mate-0.040
 heroes-0.039
e-0.037
 pirates-0.037
Token sad
Token ID6507
Feature activation+6.38e-03

Pos logit contributions
appointed+0.088
uct+0.087
rated+0.083
iously+0.083
 inc+0.082
Neg logit contributions
 mate-0.067
 superheroes-0.061
prise-0.059
 heroes-0.056
 tyrann-0.056
Token it
Token ID340
Feature activation-5.55e-02

Pos logit contributions
esh+0.032
uct+0.032
ulously+0.032
appointed+0.031
rated+0.031
Neg logit contributions
 mate-0.049
 superheroes-0.048
 heroes-0.046
 soldiers-0.044
 dinosaurs-0.042
Token.
Token ID13
Feature activation-9.42e-03

Pos logit contributions
rated+0.110
appointed+0.106
uct+0.105
ulously+0.104
esh+0.103
Neg logit contributions
 mate-0.084
 superheroes-0.083
 heroes-0.078
 soldiers-0.073
 pirates-0.069
Token
Token ID220
Feature activation-2.48e-02

Pos logit contributions
rated+0.028
iously+0.026
ened+0.026
aman+0.025
ths+0.025
Neg logit contributions
 mate-0.005
 much-0.005
 superheroes-0.004
 dinosaurs-0.003
 fishing-0.003
Token
Token ID198
Feature activation+5.79e-02

Pos logit contributions
appointed+0.043
rated+0.043
uct+0.043
ulously+0.043
esh+0.041
Neg logit contributions
 superheroes-0.043
 mate-0.042
 heroes-0.040
 soldiers-0.037
 pirates-0.036
Token
Token ID198
Feature activation+5.83e-02

Pos logit contributions
 superheroes+0.096
 mate+0.095
 heroes+0.091
 soldiers+0.085
 pirates+0.080
Neg logit contributions
rated-0.107
appointed-0.105
uct-0.104
ulously-0.103
aman-0.102
TokenLater
Token ID18602
Feature activation-1.65e-01

Pos logit contributions
 mate+0.079
 superheroes+0.075
 much+0.074
 heroes+0.069
 pirates+0.066
Neg logit contributions
iously-0.121
rated-0.120
ened-0.120
aman-0.116
icol-0.113
Token that
Token ID326
Feature activation-4.02e-02

Pos logit contributions
rated+0.309
appointed+0.300
ulously+0.294
uct+0.294
aman+0.291
Neg logit contributions
 mate-0.270
 superheroes-0.268
 heroes-0.250
 soldiers-0.234
 pirates-0.224
Token day
Token ID1110
Feature activation-7.05e-02

Pos logit contributions
rated+0.069
appointed+0.066
ulously+0.064
uct+0.064
aman+0.064
Neg logit contributions
 mate-0.073
 superheroes-0.073
 heroes-0.069
 soldiers-0.065
 pirates-0.063
Token,
Token ID11
Feature activation+5.64e-02

Pos logit contributions
appointed+0.118
rated+0.117
ulously+0.115
ened+0.115
aman+0.113
Neg logit contributions
 mate-0.125
 superheroes-0.125
 heroes-0.117
 soldiers-0.107
 queens-0.106
Token Tim
Token ID5045
Feature activation-3.57e-02

Pos logit contributions
 mate+0.107
 superheroes+0.105
 heroes+0.100
 soldiers+0.094
 pirates+0.090
Neg logit contributions
rated-0.092
appointed-0.089
ulously-0.087
uct-0.086
aman-0.085
Tokenmy
Token ID1820
Feature activation+1.59e-01

Pos logit contributions
appointed+0.082
rated+0.081
uct+0.080
aman+0.079
iously+0.078
Neg logit contributions
 superheroes-0.043
 mate-0.042
 heroes-0.038
 soldiers-0.036
 pirates-0.035
Token for
Token ID329
Feature activation+8.20e-02

Pos logit contributions
rated+0.025
appointed+0.024
uct+0.024
ulously+0.024
aman+0.023
Neg logit contributions
 superheroes-0.015
 mate-0.015
 heroes-0.014
 soldiers-0.013
 pirates-0.012
Token her
Token ID607
Feature activation-3.67e-02

Pos logit contributions
 mate+0.154
 superheroes+0.147
 heroes+0.141
 soldiers+0.133
 pirates+0.126
Neg logit contributions
rated-0.128
uct-0.128
appointed-0.128
aman-0.128
ulously-0.127
Token to
Token ID284
Feature activation-6.87e-02

Pos logit contributions
rated+0.071
appointed+0.068
ulously+0.067
uct+0.067
aman+0.066
Neg logit contributions
 mate-0.058
 superheroes-0.057
 heroes-0.053
 soldiers-0.050
 pirates-0.048
Token eat
Token ID4483
Feature activation+7.20e-02

Pos logit contributions
rated+0.134
appointed+0.129
ulously+0.128
uct+0.127
esh+0.125
Neg logit contributions
 mate-0.107
 superheroes-0.104
 heroes-0.095
e-0.094
 pirates-0.089
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
 superheroes+0.090
 mate+0.087
 heroes+0.081
 soldiers+0.076
 much+0.074
Neg logit contributions
rated-0.162
appointed-0.158
uct-0.155
ulously-0.154
esh-0.152
Token Suddenly
Token ID24975
Feature activation-1.53e-01

Pos logit contributions
rated+0.027
esh+0.025
ulously+0.023
appointed+0.023
ened+0.023
Neg logit contributions
 superheroes-0.020
 mate-0.019
 much-0.018
 heroes-0.018
 soldiers-0.017
Token she
Token ID673
Feature activation-5.51e-02

Pos logit contributions
rated+0.331
appointed+0.320
ulously+0.315
uct+0.314
aman+0.313
Neg logit contributions
 mate-0.204
 superheroes-0.201
 heroes-0.186
 soldiers-0.172
 pirates-0.164
Token started
Token ID2067
Feature activation-6.47e-02

Pos logit contributions
rated+0.097
appointed+0.093
uct+0.091
ulously+0.091
aman+0.090
Neg logit contributions
 mate-0.097
 superheroes-0.096
 heroes-0.090
 soldiers-0.085
 pirates-0.082
Token to
Token ID284
Feature activation-7.39e-02

Pos logit contributions
rated+0.146
appointed+0.137
uct+0.135
ulously+0.134
aman+0.133
Neg logit contributions
 superheroes-0.087
 mate-0.082
 heroes-0.078
 soldiers-0.076
 pirates-0.072
Token tick
Token ID4378
Feature activation-4.63e-02

Pos logit contributions
rated+0.153
uct+0.151
ulously+0.149
appointed+0.149
aman+0.147
Neg logit contributions
 superheroes-0.103
 mate-0.097
 heroes-0.089
e-0.086
 soldiers-0.085
Tokenle
Token ID293
Feature activation+1.24e-01

Pos logit contributions
aman+0.101
rated+0.100
appointed+0.097
esh+0.095
ulously+0.094
Neg logit contributions
 superheroes-0.061
e-0.057
 soldiers-0.052
 heroes-0.052
izards-0.049
Token some
Token ID617
Feature activation+5.92e-02

Pos logit contributions
 mate+0.081
 superheroes+0.079
 heroes+0.074
 soldiers+0.068
 pirates+0.065
Neg logit contributions
rated-0.104
ulously-0.104
appointed-0.103
aman-0.101
uct-0.101
Token coal
Token ID5655
Feature activation+2.53e-02

Pos logit contributions
 mate+0.106
 superheroes+0.102
 heroes+0.096
e+0.089
 soldiers+0.089
Neg logit contributions
rated-0.096
ulously-0.092
appointed-0.092
 inc-0.091
ened-0.090
Token.
Token ID13
Feature activation-9.45e-03

Pos logit contributions
 mate+0.034
 superheroes+0.034
 heroes+0.031
 soldiers+0.030
 pirates+0.028
Neg logit contributions
rated-0.055
appointed-0.054
uct-0.053
ulously-0.053
aman-0.052
Token
Token ID198
Feature activation+6.21e-02

Pos logit contributions
rated+0.022
esh+0.019
heit+0.019
icol+0.019
inct+0.018
Neg logit contributions
 much-0.012
 a-0.011
 of-0.011
 superheroes-0.010
 many-0.010
Token
Token ID198
Feature activation+6.36e-02

Pos logit contributions
 mate+0.094
 superheroes+0.094
 heroes+0.087
 soldiers+0.082
 pirates+0.078
Neg logit contributions
rated-0.123
appointed-0.121
uct-0.120
ulously-0.119
aman-0.118
TokenSo
Token ID2396
Feature activation-1.51e-01

Pos logit contributions
 much+0.086
 mate+0.081
 superheroes+0.075
e+0.074
 heroes+0.072
Neg logit contributions
rated-0.133
icol-0.133
ened-0.131
iously-0.127
chief-0.125
Token,
Token ID11
Feature activation+5.99e-02

Pos logit contributions
rated+0.407
esh+0.394
icol+0.389
inct+0.386
IT+0.385
Neg logit contributions
 much-0.115
 mate-0.111
 of-0.093
 ever-0.086
 a-0.085
Token Jane
Token ID12091
Feature activation-2.08e-02

Pos logit contributions
 superheroes+0.081
 mate+0.079
 much+0.078
 heroes+0.075
 pirates+0.070
Neg logit contributions
rated-0.125
esh-0.120
icol-0.117
inct-0.116
appointed-0.116
Token went
Token ID1816
Feature activation-9.98e-02

Pos logit contributions
appointed+0.041
aman+0.040
rated+0.040
uct+0.039
icol+0.038
Neg logit contributions
 mate-0.033
 superheroes-0.032
e-0.031
 pirates-0.031
 soldiers-0.031
Token to
Token ID284
Feature activation-6.00e-02

Pos logit contributions
rated+0.172
appointed+0.169
uct+0.164
esh+0.163
aman+0.161
Neg logit contributions
 mate-0.173
 superheroes-0.169
 heroes-0.160
 soldiers-0.147
e-0.144
Token the
Token ID262
Feature activation-6.58e-02

Pos logit contributions
rated+0.134
appointed+0.127
uct+0.121
ulously+0.121
iously+0.120
Neg logit contributions
 superheroes-0.086
 mate-0.082
 heroes-0.076
 soldiers-0.073
 pirates-0.071