TOP ACTIVATIONS
MAX = 10.648

. He t ipt oes to her bed and
naughty idea . She t ipt o ed to his bed
the baby . They t ipt o ed inside and put
aked out . They t ipt o ed to the living
he was . She t ipt o ed to the big
of her bed and t ipt o ed to the wardrobe
She stood on her t ipt oes and reached up high
her chance . She t ipt o ed to the oven
time . She quietly t ipt o ed down the street
M olly t ipt o ed around the corner
with it . She t ipt o ed closer and reached
the table . They t ipt o ed to the pot
to stand on their t ipt oes to see some of
the wind . He t ipt o ed closer and took
room . Then they t ipt o ed out of their
sword too . They t ipt o ed to the shed
brave , so she t ipt o ed around and didn
, and then they t ipt o ed to the table
and stood on her t ipt oes to make sure they
cream . He carefully t ipt o ed out of the

MIN ACTIVATIONS
MIN = -12.140

giving him too many ch ocol ates ." The king learned
as he opened the ch ocol ates and started eating them
not eat too many ch ocol ates and his friend learned
reward . It was ch ocol ates and sweets !
because of his big bus hy mustache . One
colorful cand ies and ch ocol ates . She said to
, cup cakes and ch ocol ates .
oll ip ops , ch ocol ates , g ummies ,
he ate all the ch ocol ates and sweets . Then
was a box of ch ocol ates . " For me
a big box of ch ocol ates . It was so
enjoyed her cool , ch ocol at y treat !
a large selection of ch ocol ates . Ell a picked
was a box of ch ocol ates . Lily loved ch
was filled with delicious ch ocol ates . He was happy
and started eating the ch ocol ates . The shop keeper
ates . Lily loved ch ocol ates . She thanked Ben
't have all these ch ocol ates ! Now , go
had a big , bus hy tail and sharp teeth .
son is eating our ch ocol ates !"

INTERVAL 4.951 - 10.648
CONTAINS 1.944%

and jumped in . Anna followed him . She did not
in and meet the other boats . The yacht quickly gathered
the beach . He was excited to explore the deep blue
€ The older girl smiled and said ,
. " Can we play with you , bird

INTERVAL -0.746 - 4.951
CONTAINS 67.889%

, Lily , we did it ! We are the best
started playing with the toy . He loved watching it print
so she asked if she could borrow it .
big brown truck outside her window . Em
runners in the world ! Even though he was nervous ,

INTERVAL -6.443 - -0.746
CONTAINS 29.868%

He was wearing a warm coat and looked very wise .
ran away . He had a big smile on his
, they went to the park with their k ites .
cast her eyes on the wreck and wondered what it could
and dry . After the rain stopped , Benny

INTERVAL -12.140 - -6.443
CONTAINS 0.299%

Comfort ably eating his l oll ipop , John happily went
hole . But Spot remembered what the family said and stayed
. She wanted to know what was inside the brain .
a good thing you know what you want ! Let 's
Jack said to Jill " What shall we do today ?"
Token.
Token ID13
Feature activation-3.86e-01

Pos logit contributions
 nodded+0.087
 youngest+0.085
ver+0.085
 led+0.082
 So+0.082
Neg logit contributions
 poisonous-0.118
ocol-0.114
ocket-0.112
arter-0.110
 bamboo-0.103
Token
Token ID198
Feature activation+5.97e-01

Pos logit contributions
 poisonous+0.020
ocol+0.018
ocket+0.018
aster+0.018
arter+0.018
Neg logit contributions
 nodded-0.012
ver-0.012
 youngest-0.012
 acts-0.012
Let-0.012
Token
Token ID198
Feature activation+6.00e-01

Pos logit contributions
Let+0.013
 So+0.013
ver+0.013
 led+0.012
 nodded+0.011
Neg logit contributions
 poisonous-0.039
ocol-0.038
ocket-0.037
arter-0.037
 injuries-0.034
TokenHe
Token ID1544
Feature activation-2.15e+00

Pos logit contributions
 nodded+0.024
Let+0.023
ver+0.023
 youngest+0.023
bars+0.022
Neg logit contributions
 poisonous-0.027
ocket-0.025
ocol-0.025
arter-0.024
aster-0.023
Token t
Token ID256
Feature activation-8.20e-01

Pos logit contributions
 poisonous+0.112
aster+0.103
ocket+0.102
ocol+0.100
 bamboo+0.100
Neg logit contributions
ver-0.067
folk-0.067
 youngest-0.064
Let-0.061
 oldest-0.060
Tokenipt
Token ID10257
Feature activation+1.03e+01

Pos logit contributions
 poisonous+0.054
ocol+0.050
ocket+0.050
aster+0.049
arter+0.048
Neg logit contributions
bars-0.015
ver-0.015
 nodded-0.015
 youngest-0.015
Let-0.014
Tokenoes
Token ID3028
Feature activation+4.48e+00

Pos logit contributions
 nodded+0.424
ver+0.424
Let+0.421
bars+0.419
 youngest+0.404
Neg logit contributions
 poisonous-0.443
ocol-0.407
ocket-0.403
arter-0.385
aster-0.377
Token to
Token ID284
Feature activation-2.23e-01

Pos logit contributions
 youngest+0.197
 acts+0.193
folk+0.192
 oldest+0.191
ver+0.189
Neg logit contributions
 poisonous-0.169
aster-0.149
ocket-0.149
ocol-0.144
 bamboo-0.143
Token her
Token ID607
Feature activation-2.32e+00

Pos logit contributions
ocket+0.012
 poisonous+0.012
ocol+0.012
arter+0.012
endant+0.011
Neg logit contributions
 led-0.007
Let-0.007
 youngest-0.007
 oldest-0.006
 younger-0.006
Token bed
Token ID3996
Feature activation-5.10e+00

Pos logit contributions
 poisonous+0.120
ocol+0.118
arter+0.108
aster+0.108
ocket+0.106
Neg logit contributions
 youngest-0.078
 nodded-0.077
 acts-0.076
 led-0.075
 So-0.075
Token and
Token ID290
Feature activation-1.03e-01

Pos logit contributions
 poisonous+0.228
ocol+0.211
ocket+0.207
aster+0.202
arter+0.200
Neg logit contributions
 nodded-0.192
ver-0.192
 youngest-0.190
 acts-0.189
Let-0.186
Token naughty
Token ID45128
Feature activation-2.61e-01

Pos logit contributions
ocol+0.021
 poisonous+0.020
ocket+0.020
aster+0.020
arter+0.019
Neg logit contributions
 nodded-0.016
 youngest-0.016
 led-0.016
Let-0.016
 nic-0.015
Token idea
Token ID2126
Feature activation+4.15e+00

Pos logit contributions
 poisonous+0.014
ocol+0.013
ocket+0.013
aster+0.012
arter+0.012
Neg logit contributions
 acts-0.008
 nodded-0.008
 youngest-0.007
 led-0.007
 nods-0.007
Token.
Token ID13
Feature activation-3.26e-01

Pos logit contributions
 led+0.138
ver+0.131
 nodded+0.131
Let+0.129
's+0.129
Neg logit contributions
 poisonous-0.209
ocol-0.206
ocket-0.194
arter-0.194
aster-0.188
Token She
Token ID1375
Feature activation-3.23e+00

Pos logit contributions
 poisonous+0.014
aster+0.012
ocket+0.012
ocol+0.012
 bamboo+0.012
Neg logit contributions
 acts-0.013
 youngest-0.012
ver-0.012
folk-0.012
 oldest-0.012
Token t
Token ID256
Feature activation-8.71e-01

Pos logit contributions
 poisonous+0.182
ocket+0.163
aster+0.158
 bamboo+0.156
ocol+0.153
Neg logit contributions
folk-0.091
ver-0.089
bars-0.086
 acts-0.083
 youngest-0.083
Tokenipt
Token ID10257
Feature activation+1.03e+01

Pos logit contributions
 poisonous+0.036
ocol+0.032
ocket+0.032
aster+0.031
arter+0.030
Neg logit contributions
ver-0.037
 nodded-0.037
 youngest-0.037
bars-0.036
Let-0.036
Tokeno
Token ID78
Feature activation-3.66e+00

Pos logit contributions
 nodded+0.439
ver+0.439
Let+0.436
bars+0.432
 youngest+0.423
Neg logit contributions
 poisonous-0.419
ocol-0.384
ocket-0.380
arter-0.363
aster-0.359
Tokened
Token ID276
Feature activation+2.55e+00

Pos logit contributions
 poisonous+0.156
ocket+0.138
 bamboo+0.129
aster+0.128
eds+0.128
Neg logit contributions
 acts-0.144
folk-0.143
 youngest-0.143
mun-0.139
 oldest-0.138
Token to
Token ID284
Feature activation-2.18e-01

Pos logit contributions
 led+0.084
Let+0.084
 nodded+0.084
ver+0.081
 youngest+0.079
Neg logit contributions
 poisonous-0.126
ocol-0.125
arter-0.123
ocket-0.122
aster-0.118
Token his
Token ID465
Feature activation-3.96e-01

Pos logit contributions
 poisonous+0.012
ocket+0.011
ocol+0.011
arter+0.011
endant+0.011
Neg logit contributions
 led-0.007
Let-0.007
 youngest-0.007
 asked-0.006
 asks-0.006
Token bed
Token ID3996
Feature activation-5.06e+00

Pos logit contributions
ocol+0.020
 poisonous+0.020
aster+0.018
ocket+0.018
arter+0.017
Neg logit contributions
 youngest-0.015
 oldest-0.014
 acts-0.013
 led-0.013
 eldest-0.013
Token the
Token ID262
Feature activation+1.28e+00

Pos logit contributions
 nodded+0.083
 acts+0.081
 led+0.081
 youngest+0.080
ver+0.079
Neg logit contributions
 poisonous-0.123
ocket-0.118
ocol-0.117
aster-0.114
arter-0.112
Token baby
Token ID5156
Feature activation-1.07e+00

Pos logit contributions
 youngest+0.056
 acts+0.055
Let+0.054
 oldest+0.054
 nodded+0.054
Neg logit contributions
 poisonous-0.048
aster-0.047
ocol-0.047
arter-0.045
ocket-0.043
Token.
Token ID13
Feature activation-5.11e-01

Pos logit contributions
 poisonous+0.046
ocol+0.042
ocket+0.042
aster+0.041
arter+0.040
Neg logit contributions
 acts-0.042
 youngest-0.042
 nodded-0.042
ver-0.041
Let-0.041
Token They
Token ID1119
Feature activation+6.86e-01

Pos logit contributions
 poisonous+0.025
 bamboo+0.023
arter+0.023
 heaven+0.023
ocol+0.023
Neg logit contributions
ver-0.015
mun-0.015
 acts-0.015
bars-0.015
folk-0.014
Token t
Token ID256
Feature activation-8.21e-01

Pos logit contributions
sets+0.021
bars+0.020
folk+0.019
ver+0.019
 acts+0.018
Neg logit contributions
 poisonous-0.037
ocket-0.034
 bamboo-0.032
aster-0.031
 injuries-0.031
Tokenipt
Token ID10257
Feature activation+1.03e+01

Pos logit contributions
 poisonous+0.052
ocol+0.048
ocket+0.048
aster+0.047
arter+0.047
Neg logit contributions
ver-0.016
 nodded-0.016
 youngest-0.016
 acts-0.016
Let-0.015
Tokeno
Token ID78
Feature activation-3.63e+00

Pos logit contributions
ver+0.450
 nodded+0.450
 youngest+0.446
 acts+0.446
Let+0.443
Neg logit contributions
 poisonous-0.398
ocol-0.358
ocket-0.356
aster-0.344
arter-0.339
Tokened
Token ID276
Feature activation+2.56e+00

Pos logit contributions
 poisonous+0.155
ocket+0.140
eds+0.131
 bamboo+0.130
sm+0.127
Neg logit contributions
 acts-0.141
folk-0.137
 basics-0.136
 youngest-0.136
mun-0.136
Token inside
Token ID2641
Feature activation-1.88e+00

Pos logit contributions
 nodded+0.097
Let+0.096
 led+0.096
ver+0.096
 youngest+0.095
Neg logit contributions
 poisonous-0.114
ocol-0.107
ocket-0.106
arter-0.104
aster-0.104
Token and
Token ID290
Feature activation-1.54e-01

Pos logit contributions
 poisonous+0.081
ocol+0.074
ocket+0.074
aster+0.072
arter+0.071
Neg logit contributions
ver-0.073
 nodded-0.073
 acts-0.073
 youngest-0.073
Let-0.072
Token put
Token ID1234
Feature activation-1.91e+00

Pos logit contributions
 poisonous+0.008
ocket+0.007
aster+0.007
ocol+0.007
 bamboo+0.007
Neg logit contributions
 acts-0.005
ver-0.005
folk-0.005
bars-0.005
 youngest-0.005
Tokenaked
Token ID4335
Feature activation+2.45e+00

Pos logit contributions
 poisonous+0.001
arter+0.001
ocol+0.001
ocket+0.001
 brand+0.001
Neg logit contributions
 nodded-0.000
 acts-0.000
Let-0.000
ver-0.000
 led-0.000
Token out
Token ID503
Feature activation+6.47e-01

Pos logit contributions
 youngest+0.094
Let+0.093
 nodded+0.092
 led+0.092
ver+0.091
Neg logit contributions
 poisonous-0.109
ocket-0.102
ocol-0.101
arter-0.099
aster-0.096
Token.
Token ID13
Feature activation-1.20e+00

Pos logit contributions
 youngest+0.023
 led+0.023
ver+0.023
 acts+0.023
Let+0.022
Neg logit contributions
 poisonous-0.030
ocket-0.029
ocol-0.028
aster-0.027
arter-0.027
Token They
Token ID1119
Feature activation+4.34e-01

Pos logit contributions
 poisonous+0.070
ocol+0.065
ocket+0.065
aster+0.064
arter+0.063
Neg logit contributions
 acts-0.028
ver-0.028
 nodded-0.028
 youngest-0.028
folk-0.027
Token t
Token ID256
Feature activation-9.02e-01

Pos logit contributions
 acts+0.013
 youngest+0.013
folk+0.013
bars+0.013
ver+0.012
Neg logit contributions
 poisonous-0.023
ocket-0.021
aster-0.021
ocol-0.020
 bamboo-0.020
Tokenipt
Token ID10257
Feature activation+1.03e+01

Pos logit contributions
 poisonous+0.057
ocol+0.053
ocket+0.053
aster+0.053
arter+0.052
Neg logit contributions
ver-0.017
 youngest-0.017
 nodded-0.017
 acts-0.017
Let-0.017
Tokeno
Token ID78
Feature activation-3.66e+00

Pos logit contributions
ver+0.439
 nodded+0.437
Let+0.434
bars+0.429
 youngest+0.427
Neg logit contributions
 poisonous-0.415
ocol-0.377
ocket-0.375
aster-0.358
arter-0.357
Tokened
Token ID276
Feature activation+2.52e+00

Pos logit contributions
 poisonous+0.157
ocket+0.142
eds+0.133
aster+0.133
 injuries+0.130
Neg logit contributions
 acts-0.144
 youngest-0.137
folk-0.135
mun-0.134
 oldest-0.134
Token to
Token ID284
Feature activation-3.15e-01

Pos logit contributions
 led+0.089
Let+0.089
 nodded+0.088
ver+0.087
 youngest+0.087
Neg logit contributions
 poisonous-0.119
ocol-0.114
ocket-0.113
arter-0.111
aster-0.109
Token the
Token ID262
Feature activation+9.74e-01

Pos logit contributions
 poisonous+0.018
ocket+0.018
ocol+0.017
affle+0.017
arter+0.017
Neg logit contributions
 youngest-0.009
Let-0.009
 led-0.009
 oldest-0.008
 younger-0.008
Token living
Token ID2877
Feature activation-2.76e+00

Pos logit contributions
 youngest+0.032
 oldest+0.031
Let+0.029
 eldest+0.029
 way+0.029
Neg logit contributions
ocol-0.053
ocket-0.050
 poisonous-0.050
ez-0.049
arter-0.048
Token he
Token ID339
Feature activation+1.92e+00

Pos logit contributions
 poisonous+0.126
ocol+0.116
ocket+0.115
aster+0.111
arter+0.111
Neg logit contributions
 nodded-0.097
 acts-0.097
ver-0.096
 youngest-0.095
Let-0.095
Token was
Token ID373
Feature activation+5.46e-02

Pos logit contributions
 youngest+0.043
ver+0.043
 acts+0.042
 nodded+0.042
Let+0.041
Neg logit contributions
 poisonous-0.115
ocket-0.107
ocol-0.107
aster-0.105
arter-0.104
Token.
Token ID13
Feature activation-9.75e-01

Pos logit contributions
 led+0.002
ver+0.002
 acts+0.002
 nodded+0.002
 youngest+0.002
Neg logit contributions
 poisonous-0.002
ocol-0.002
ocket-0.002
aster-0.002
arter-0.002
Token She
Token ID1375
Feature activation-3.21e+00

Pos logit contributions
 poisonous+0.047
ocket+0.044
ocol+0.043
aster+0.043
arter+0.042
Neg logit contributions
 youngest-0.032
 acts-0.032
ver-0.032
folk-0.031
 nodded-0.031
Token t
Token ID256
Feature activation-8.93e-01

Pos logit contributions
 poisonous+0.173
ocket+0.162
aster+0.152
 bamboo+0.152
ocol+0.150
Neg logit contributions
folk-0.092
ver-0.090
bars-0.089
 youngest-0.088
 acts-0.088
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.059
ocol+0.054
aster+0.054
ocket+0.054
arter+0.053
Neg logit contributions
ver-0.016
 nodded-0.016
bars-0.016
 youngest-0.016
Let-0.015
Tokeno
Token ID78
Feature activation-3.60e+00

Pos logit contributions
ver+0.440
 nodded+0.440
Let+0.434
bars+0.428
 youngest+0.420
Neg logit contributions
 poisonous-0.416
ocol-0.383
ocket-0.375
arter-0.360
aster-0.359
Tokened
Token ID276
Feature activation+2.54e+00

Pos logit contributions
 poisonous+0.156
ocket+0.144
 bamboo+0.135
eds+0.130
aster+0.129
Neg logit contributions
 acts-0.135
 youngest-0.135
folk-0.134
mun-0.132
 basics-0.130
Token to
Token ID284
Feature activation-1.73e-01

Pos logit contributions
 nodded+0.091
 led+0.091
Let+0.090
ver+0.086
 acts+0.086
Neg logit contributions
 poisonous-0.121
ocol-0.116
arter-0.115
ocket-0.114
aster-0.111
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
 poisonous+0.010
ocket+0.010
ocol+0.010
arter+0.009
affle+0.009
Neg logit contributions
 led-0.005
Let-0.004
 youngest-0.004
 asks-0.004
 asked-0.004
Token big
Token ID1263
Feature activation-3.24e+00

Pos logit contributions
 youngest+0.042
 oldest+0.041
Let+0.041
 led+0.040
 smallest+0.040
Neg logit contributions
ocol-0.071
aster-0.066
ocket-0.066
arter-0.065
 poisonous-0.064
Token of
Token ID286
Feature activation-8.86e-01

Pos logit contributions
 led+0.022
 acts+0.021
 nodded+0.020
 leads+0.020
 youngest+0.020
Neg logit contributions
 poisonous-0.031
ocket-0.030
ocol-0.030
arter-0.030
affle-0.028
Token her
Token ID607
Feature activation-2.50e+00

Pos logit contributions
 poisonous+0.044
ocket+0.043
affle+0.043
arter+0.043
aker+0.042
Neg logit contributions
 led-0.030
 way-0.028
 acts-0.027
 leads-0.026
 youngest-0.026
Token bed
Token ID3996
Feature activation-5.08e+00

Pos logit contributions
 poisonous+0.110
ocol+0.102
aster+0.101
arter+0.100
ocket+0.098
Neg logit contributions
 youngest-0.099
 led-0.099
 acts-0.097
 oldest-0.095
 nodded-0.095
Token and
Token ID290
Feature activation-1.64e-01

Pos logit contributions
 poisonous+0.229
ocol+0.213
ocket+0.207
aster+0.203
arter+0.201
Neg logit contributions
 nodded-0.190
ver-0.189
 youngest-0.188
 acts-0.187
 led-0.184
Token t
Token ID256
Feature activation-8.80e-01

Pos logit contributions
 poisonous+0.008
aster+0.008
ocket+0.008
 bamboo+0.007
 heaven+0.007
Neg logit contributions
folk-0.005
ver-0.005
 acts-0.005
 youngest-0.005
 basics-0.005
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.059
ocol+0.054
ocket+0.054
aster+0.053
arter+0.053
Neg logit contributions
bars-0.015
 youngest-0.015
 nodded-0.015
ver-0.015
Let-0.014
Tokeno
Token ID78
Feature activation-3.68e+00

Pos logit contributions
Let+0.406
 nodded+0.406
bars+0.405
ver+0.404
 led+0.379
Neg logit contributions
 poisonous-0.460
ocol-0.426
ocket-0.419
arter-0.403
aster-0.387
Tokened
Token ID276
Feature activation+2.50e+00

Pos logit contributions
 poisonous+0.164
ocket+0.152
aster+0.144
 bamboo+0.141
 injuries+0.139
Neg logit contributions
 acts-0.134
folk-0.133
 youngest-0.130
mun-0.129
ver-0.129
Token to
Token ID284
Feature activation-2.95e-01

Pos logit contributions
 led+0.087
Let+0.083
 nodded+0.083
 youngest+0.078
 leads+0.077
Neg logit contributions
arter-0.126
 poisonous-0.125
ocol-0.124
ocket-0.121
aster-0.116
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
 poisonous+0.017
affle+0.016
arter+0.016
ocol+0.016
ocket+0.016
Neg logit contributions
 led-0.009
Let-0.008
 youngest-0.008
 asked-0.008
 acts-0.008
Token wardrobe
Token ID35593
Feature activation-2.73e+00

Pos logit contributions
 youngest+0.040
 oldest+0.040
 way+0.038
 nic+0.037
 led+0.036
Neg logit contributions
ocol-0.070
arter-0.067
aster-0.064
ez-0.064
 poisonous-0.064
Token She
Token ID1375
Feature activation-3.00e+00

Pos logit contributions
 poisonous+0.015
 bamboo+0.013
aster+0.013
ocol+0.013
arter+0.013
Neg logit contributions
 acts-0.012
folk-0.012
ver-0.012
 youngest-0.012
mun-0.012
Token stood
Token ID6204
Feature activation+9.81e-01

Pos logit contributions
 poisonous+0.142
ocket+0.126
aster+0.124
 bamboo+0.120
isk+0.116
Neg logit contributions
folk-0.110
sets-0.104
 acts-0.104
bars-0.102
 youngest-0.098
Token on
Token ID319
Feature activation-1.03e+00

Pos logit contributions
 nodded+0.031
 nic+0.028
 youngest+0.027
 best+0.027
Let+0.027
Neg logit contributions
 poisonous-0.053
ocol-0.052
arter-0.051
ocket-0.051
aster-0.050
Token her
Token ID607
Feature activation-2.24e+00

Pos logit contributions
 poisonous+0.051
ocket+0.050
arter+0.049
ocol+0.048
affle+0.045
Neg logit contributions
Let-0.034
 led-0.033
 youngest-0.033
 acts-0.032
 nodded-0.032
Token t
Token ID256
Feature activation-8.76e-01

Pos logit contributions
 poisonous+0.098
ocol+0.093
ocket+0.089
aster+0.087
arter+0.087
Neg logit contributions
 youngest-0.089
 nodded-0.087
 acts-0.086
 oldest-0.086
 led-0.085
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.046
ocol+0.041
ocket+0.039
 bamboo+0.038
arter+0.038
Neg logit contributions
bars-0.032
 youngest-0.030
 So-0.029
 eldest-0.028
 oldest-0.028
Tokenoes
Token ID3028
Feature activation+4.60e+00

Pos logit contributions
ver+0.282
bars+0.280
 nodded+0.270
Let+0.267
 youngest+0.253
Neg logit contributions
 poisonous-0.587
ocol-0.550
ocket-0.543
arter-0.523
aster-0.513
Token and
Token ID290
Feature activation-1.39e-01

Pos logit contributions
 acts+0.188
 youngest+0.187
 nodded+0.183
folk+0.183
Let+0.183
Neg logit contributions
 poisonous-0.188
ocket-0.169
ocol-0.165
aster-0.164
arter-0.158
Token reached
Token ID4251
Feature activation+2.98e+00

Pos logit contributions
 poisonous+0.006
aster+0.006
ocket+0.006
 bamboo+0.006
 jam+0.006
Neg logit contributions
 acts-0.005
folk-0.005
 youngest-0.005
 basics-0.005
 smallest-0.005
Token up
Token ID510
Feature activation+2.49e+00

Pos logit contributions
bars+0.139
 led+0.137
 youngest+0.137
ver+0.136
 oldest+0.133
Neg logit contributions
 poisonous-0.112
ocket-0.104
arter-0.099
ocol-0.098
aster-0.091
Token high
Token ID1029
Feature activation-2.56e-01

Pos logit contributions
 led+0.083
 nodded+0.082
Let+0.081
ver+0.080
 youngest+0.079
Neg logit contributions
 poisonous-0.123
ocket-0.121
ocol-0.118
arter-0.117
aster-0.109
Token her
Token ID607
Feature activation-2.51e+00

Pos logit contributions
ocol+0.159
arter+0.153
 poisonous+0.151
ocket+0.150
eds+0.145
Neg logit contributions
 led-0.119
 youngest-0.112
 neither-0.110
Let-0.109
 oldest-0.108
Token chance
Token ID2863
Feature activation+7.06e-01

Pos logit contributions
 poisonous+0.127
ocol+0.125
ocket+0.119
aster+0.119
arter+0.117
Neg logit contributions
 youngest-0.082
 nodded-0.078
 oldest-0.078
 acts-0.077
 led-0.074
Token.
Token ID13
Feature activation-5.51e-01

Pos logit contributions
 nodded+0.027
 acts+0.027
 youngest+0.027
ver+0.027
Let+0.026
Neg logit contributions
 poisonous-0.031
ocol-0.029
ocket-0.028
aster-0.028
arter-0.027
Token She
Token ID1375
Feature activation-3.27e+00

Pos logit contributions
 poisonous+0.027
ocket+0.025
ocol+0.025
aster+0.024
arter+0.024
Neg logit contributions
 acts-0.018
ver-0.018
folk-0.018
 youngest-0.018
 nodded-0.018
Token t
Token ID256
Feature activation-8.77e-01

Pos logit contributions
 poisonous+0.164
ocket+0.154
aster+0.146
 bamboo+0.141
ocol+0.139
Neg logit contributions
folk-0.105
ver-0.102
sets-0.099
 acts-0.099
 youngest-0.096
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.053
ocol+0.049
ocket+0.048
aster+0.048
arter+0.048
Neg logit contributions
 youngest-0.020
ver-0.020
 nodded-0.020
bars-0.020
Let-0.020
Tokeno
Token ID78
Feature activation-3.60e+00

Pos logit contributions
ver+0.409
Let+0.407
 nodded+0.407
bars+0.403
 youngest+0.374
Neg logit contributions
 poisonous-0.461
ocol-0.434
ocket-0.420
arter-0.405
aster-0.392
Tokened
Token ID276
Feature activation+2.54e+00

Pos logit contributions
 poisonous+0.166
ocket+0.154
 bamboo+0.143
aster+0.142
 injuries+0.139
Neg logit contributions
 acts-0.126
 youngest-0.124
folk-0.124
ver-0.121
mun-0.121
Token to
Token ID284
Feature activation-3.50e-01

Pos logit contributions
 led+0.088
Let+0.086
 nodded+0.085
 youngest+0.081
ver+0.080
Neg logit contributions
 poisonous-0.125
ocol-0.123
arter-0.122
ocket-0.119
aster-0.118
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
 poisonous+0.020
ocol+0.019
affle+0.018
arter+0.018
ocket+0.018
Neg logit contributions
 led-0.011
Let-0.010
 youngest-0.010
 oldest-0.010
 way-0.009
Token oven
Token ID14361
Feature activation-8.04e-01

Pos logit contributions
 youngest+0.035
 oldest+0.035
Let+0.034
 nic+0.032
 way+0.032
Neg logit contributions
ocol-0.061
ocket-0.057
 poisonous-0.057
arter-0.057
ez-0.056
Token time
Token ID640
Feature activation+1.78e+00

Pos logit contributions
 led+0.013
 youngest+0.013
 nodded+0.012
Let+0.012
ver+0.012
Neg logit contributions
ocket-0.021
ocol-0.021
 poisonous-0.021
arter-0.020
aster-0.019
Token.
Token ID13
Feature activation-8.87e-04

Pos logit contributions
ver+0.068
 nodded+0.066
 led+0.066
Let+0.066
 youngest+0.065
Neg logit contributions
 poisonous-0.079
ocol-0.077
ocket-0.072
arter-0.072
 bamboo-0.071
Token She
Token ID1375
Feature activation-2.82e+00

Pos logit contributions
 poisonous+0.000
aster+0.000
 heaven+0.000
 bamboo+0.000
 what+0.000
Neg logit contributions
 acts-0.000
 youngest-0.000
 oldest-0.000
bars-0.000
spe-0.000
Token quietly
Token ID12703
Feature activation+4.39e+00

Pos logit contributions
 poisonous+0.152
ocket+0.135
aster+0.134
 bamboo+0.131
ocol+0.124
Neg logit contributions
folk-0.086
ver-0.083
sets-0.083
bars-0.079
 acts-0.079
Token t
Token ID256
Feature activation-7.48e-01

Pos logit contributions
ver+0.136
folk+0.134
 youngest+0.128
 acts+0.126
 oldest+0.126
Neg logit contributions
 poisonous-0.227
aster-0.210
ocket-0.205
ocol-0.201
 bamboo-0.192
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.048
ocol+0.045
ocket+0.045
aster+0.045
arter+0.044
Neg logit contributions
ver-0.013
 nodded-0.013
 youngest-0.013
 acts-0.013
Let-0.013
Tokeno
Token ID78
Feature activation-3.35e+00

Pos logit contributions
ver+0.416
 nodded+0.414
bars+0.412
Let+0.408
 youngest+0.396
Neg logit contributions
 poisonous-0.443
ocol-0.404
ocket-0.401
arter-0.387
aster-0.377
Tokened
Token ID276
Feature activation+2.55e+00

Pos logit contributions
 poisonous+0.153
ocket+0.140
aster+0.132
 bamboo+0.127
 injuries+0.126
Neg logit contributions
 acts-0.119
 youngest-0.115
folk-0.114
ver-0.114
 oldest-0.113
Token down
Token ID866
Feature activation-2.54e-01

Pos logit contributions
 nodded+0.087
 led+0.087
Let+0.086
 youngest+0.084
ver+0.083
Neg logit contributions
 poisonous-0.123
arter-0.118
ocol-0.117
ocket-0.116
aster-0.113
Token the
Token ID262
Feature activation+1.57e+00

Pos logit contributions
 poisonous+0.013
ocol+0.012
arter+0.012
ocket+0.012
aster+0.011
Neg logit contributions
 led-0.009
 nodded-0.008
Let-0.008
ver-0.008
 youngest-0.008
Token street
Token ID4675
Feature activation+9.00e-02

Pos logit contributions
 youngest+0.049
bars+0.048
 oldest+0.047
Let+0.047
 led+0.045
Neg logit contributions
ocol-0.082
 poisonous-0.081
ocket-0.079
arter-0.077
aster-0.073
Token
Token ID198
Feature activation+8.64e-01

Pos logit contributions
 acts+0.005
folk+0.005
ver+0.005
bars+0.005
 nodded+0.005
Neg logit contributions
 poisonous-0.005
ocol-0.005
ocket-0.005
 bamboo-0.005
aster-0.005
Token
Token ID198
Feature activation+8.64e-01

Pos logit contributions
 acts+0.036
 youngest+0.034
folk+0.034
 nodded+0.034
bars+0.034
Neg logit contributions
 poisonous-0.035
aster-0.031
ocket-0.031
ocol-0.031
 bamboo-0.030
TokenM
Token ID44
Feature activation+9.44e-01

Pos logit contributions
 acts+0.037
folk+0.035
bars+0.034
ver+0.034
 youngest+0.034
Neg logit contributions
 poisonous-0.036
aster-0.032
ocol-0.031
ocket-0.031
 bamboo-0.030
Tokenolly
Token ID5098
Feature activation+7.65e-01

Pos logit contributions
ver+0.035
 acts+0.035
 nodded+0.035
 youngest+0.035
Let+0.034
Neg logit contributions
 poisonous-0.043
ocol-0.039
ocket-0.039
aster-0.038
arter-0.037
Token t
Token ID256
Feature activation-7.40e-01

Pos logit contributions
ver+0.022
bars+0.021
sets+0.021
folk+0.021
mun+0.020
Neg logit contributions
 poisonous-0.039
ocket-0.036
aster-0.036
 bamboo-0.034
ez-0.033
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.041
ocol+0.039
ocket+0.038
aster+0.038
arter+0.037
Neg logit contributions
 acts-0.020
ver-0.019
 nodded-0.019
 youngest-0.019
Let-0.019
Tokeno
Token ID78
Feature activation-3.25e+00

Pos logit contributions
 acts+0.452
 youngest+0.451
ver+0.450
 nodded+0.450
Let+0.443
Neg logit contributions
 poisonous-0.386
ocol-0.344
ocket-0.343
aster-0.334
arter-0.327
Tokened
Token ID276
Feature activation+2.52e+00

Pos logit contributions
 poisonous+0.146
ocket+0.132
 bamboo+0.124
aster+0.124
eds+0.122
Neg logit contributions
 acts-0.115
ver-0.111
 basics-0.110
folk-0.110
 youngest-0.110
Token around
Token ID1088
Feature activation+1.92e+00

Pos logit contributions
 nodded+0.094
 youngest+0.093
ver+0.092
Let+0.092
 acts+0.092
Neg logit contributions
 poisonous-0.114
ocol-0.106
ocket-0.105
arter-0.104
aster-0.103
Token the
Token ID262
Feature activation+1.67e+00

Pos logit contributions
 nodded+0.067
 led+0.067
Let+0.065
 acts+0.064
 youngest+0.062
Neg logit contributions
 poisonous-0.096
arter-0.091
ocket-0.090
ocol-0.088
aster-0.084
Token corner
Token ID5228
Feature activation-1.01e+00

Pos logit contributions
 youngest+0.057
 oldest+0.055
Let+0.054
 nodded+0.052
 eldest+0.052
Neg logit contributions
 poisonous-0.084
ocol-0.083
ocket-0.081
arter-0.079
aster-0.074
Token with
Token ID351
Feature activation-1.16e-01

Pos logit contributions
 nodded+0.155
's+0.148
 acts+0.144
mun+0.137
 So+0.137
Neg logit contributions
 poisonous-0.221
ocol-0.209
 injuries-0.203
ocket-0.203
arter-0.202
Token it
Token ID340
Feature activation-5.98e-01

Pos logit contributions
 poisonous+0.006
arter+0.005
ocket+0.005
ocol+0.005
prise+0.005
Neg logit contributions
 acts-0.004
 led-0.004
 nodded-0.004
 youngest-0.004
Let-0.003
Token.
Token ID13
Feature activation-4.95e-01

Pos logit contributions
 poisonous+0.025
ocol+0.024
aster+0.023
ocket+0.023
arter+0.022
Neg logit contributions
 youngest-0.024
 led-0.024
 nodded-0.024
ver-0.024
 acts-0.024
Token She
Token ID1375
Feature activation-3.22e+00

Pos logit contributions
 poisonous+0.022
aster+0.020
 bamboo+0.020
ocol+0.019
ocket+0.019
Neg logit contributions
 acts-0.018
folk-0.018
ver-0.017
 youngest-0.017
 oldest-0.017
Token t
Token ID256
Feature activation-9.04e-01

Pos logit contributions
 poisonous+0.167
ocket+0.152
 bamboo+0.149
aster+0.147
 injuries+0.139
Neg logit contributions
folk-0.103
bars-0.098
ver-0.097
sets-0.095
 acts-0.095
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.060
ocket+0.056
ocol+0.056
aster+0.055
arter+0.055
Neg logit contributions
ver-0.015
 nodded-0.015
 youngest-0.015
 acts-0.014
Let-0.014
Tokeno
Token ID78
Feature activation-3.57e+00

Pos logit contributions
Let+0.418
ver+0.417
 nodded+0.415
bars+0.408
 led+0.386
Neg logit contributions
 poisonous-0.447
ocol-0.416
ocket-0.408
arter-0.392
aster-0.381
Tokened
Token ID276
Feature activation+2.51e+00

Pos logit contributions
 poisonous+0.161
ocket+0.144
 bamboo+0.138
eds+0.136
aster+0.135
Neg logit contributions
 acts-0.135
folk-0.130
 youngest-0.127
bars-0.127
 basics-0.126
Token closer
Token ID5699
Feature activation+2.81e+00

Pos logit contributions
 led+0.087
Let+0.086
 nodded+0.085
 youngest+0.081
ver+0.080
Neg logit contributions
 poisonous-0.122
ocol-0.120
arter-0.119
ocket-0.118
aster-0.115
Token and
Token ID290
Feature activation-1.44e-01

Pos logit contributions
 nodded+0.108
ver+0.108
 acts+0.107
 youngest+0.107
Let+0.106
Neg logit contributions
 poisonous-0.123
ocol-0.112
ocket-0.111
aster-0.108
arter-0.107
Token reached
Token ID4251
Feature activation+3.01e+00

Pos logit contributions
 poisonous+0.007
ocket+0.006
aster+0.006
ocol+0.006
 bamboo+0.006
Neg logit contributions
 acts-0.005
 youngest-0.005
folk-0.005
ver-0.005
bars-0.005
Token the
Token ID262
Feature activation+1.27e+00

Pos logit contributions
 acts+0.098
 youngest+0.094
 led+0.093
Let+0.093
 oldest+0.090
Neg logit contributions
 poisonous-0.136
ocket-0.126
ocol-0.124
arter-0.122
aster-0.118
Token table
Token ID3084
Feature activation-2.01e+00

Pos logit contributions
 oldest+0.036
 way+0.036
Let+0.036
's+0.036
 youngest+0.035
Neg logit contributions
ocol-0.070
ez-0.066
 poisonous-0.065
ocket-0.064
arter-0.064
Token.
Token ID13
Feature activation-5.22e-01

Pos logit contributions
 poisonous+0.084
ocol+0.077
ocket+0.074
aster+0.072
arter+0.072
Neg logit contributions
 nodded-0.082
 acts-0.082
 youngest-0.081
 led-0.081
ver-0.081
Token They
Token ID1119
Feature activation+7.72e-01

Pos logit contributions
 poisonous+0.022
aster+0.020
 bamboo+0.020
ores+0.020
ocket+0.020
Neg logit contributions
bars-0.020
sets-0.020
folk-0.020
mun-0.019
lest-0.019
Token t
Token ID256
Feature activation-9.66e-01

Pos logit contributions
sets+0.027
bars+0.027
 basics+0.026
 acts+0.026
 hardest+0.025
Neg logit contributions
 poisonous-0.036
ocket-0.034
aster-0.032
 injuries-0.031
 what-0.031
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.061
ocol+0.057
ocket+0.057
aster+0.056
arter+0.056
Neg logit contributions
 acts-0.018
 youngest-0.018
ver-0.018
 nodded-0.018
Let-0.017
Tokeno
Token ID78
Feature activation-3.74e+00

Pos logit contributions
 acts+0.462
 youngest+0.461
ver+0.460
 nodded+0.460
Let+0.453
Neg logit contributions
 poisonous-0.376
ocol-0.334
ocket-0.333
aster-0.324
arter-0.317
Tokened
Token ID276
Feature activation+2.49e+00

Pos logit contributions
 poisonous+0.159
ocket+0.147
eds+0.133
aster+0.131
 bamboo+0.131
Neg logit contributions
 acts-0.144
 youngest-0.142
 basics-0.139
folk-0.138
 oldest-0.138
Token to
Token ID284
Feature activation-2.65e-01

Pos logit contributions
 nodded+0.094
ver+0.094
 acts+0.093
Let+0.093
 youngest+0.093
Neg logit contributions
 poisonous-0.111
ocol-0.102
ocket-0.102
aster-0.099
arter-0.099
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
 poisonous+0.014
ocket+0.013
ocol+0.013
arter+0.012
affle+0.012
Neg logit contributions
Let-0.009
 led-0.009
 youngest-0.009
 acts-0.008
 nodded-0.008
Token pot
Token ID1787
Feature activation+8.19e-01

Pos logit contributions
 youngest+0.042
 oldest+0.041
Let+0.040
 led+0.039
 eldest+0.039
Neg logit contributions
ocol-0.064
 poisonous-0.061
ocket-0.059
arter-0.059
aster-0.057
Token to
Token ID284
Feature activation-1.44e-01

Pos logit contributions
 poisonous+0.059
 bamboo+0.049
ocket+0.045
aster+0.043
 what+0.043
Neg logit contributions
bars-0.096
folk-0.093
 acts-0.093
ver-0.093
lest-0.090
Token stand
Token ID1302
Feature activation-1.07e+00

Pos logit contributions
 poisonous+0.007
ocol+0.006
aster+0.006
ocket+0.006
arter+0.006
Neg logit contributions
ver-0.005
 nodded-0.005
 acts-0.005
 youngest-0.005
bars-0.005
Token on
Token ID319
Feature activation-1.06e+00

Pos logit contributions
 poisonous+0.047
ocol+0.045
aster+0.044
ocket+0.044
arter+0.042
Neg logit contributions
 nodded-0.041
ver-0.041
 led-0.040
Let-0.039
 youngest-0.039
Token their
Token ID511
Feature activation-1.06e-01

Pos logit contributions
 poisonous+0.044
ocol+0.040
ocket+0.040
aster+0.039
arter+0.039
Neg logit contributions
 acts-0.043
 youngest-0.042
 nodded-0.042
ver-0.042
Let-0.042
Token t
Token ID256
Feature activation-8.71e-01

Pos logit contributions
 poisonous+0.006
ocket+0.005
ocol+0.005
aster+0.005
arter+0.005
Neg logit contributions
ver-0.003
 nodded-0.003
 acts-0.003
 youngest-0.003
folk-0.003
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.037
ocol+0.033
ocket+0.032
aster+0.032
arter+0.030
Neg logit contributions
bars-0.037
 youngest-0.036
 So-0.035
 oldest-0.035
ver-0.035
Tokenoes
Token ID3028
Feature activation+4.59e+00

Pos logit contributions
ver+0.214
 nodded+0.209
 youngest+0.209
 acts+0.205
Let+0.204
Neg logit contributions
 poisonous-0.628
ocol-0.588
ocket-0.586
aster-0.572
arter-0.568
Token to
Token ID284
Feature activation-1.55e-01

Pos logit contributions
 acts+0.195
 youngest+0.194
 nodded+0.192
Let+0.191
folk+0.190
Neg logit contributions
 poisonous-0.178
ocket-0.159
aster-0.153
ocol-0.151
 bamboo-0.150
Token see
Token ID766
Feature activation-3.83e+00

Pos logit contributions
 poisonous+0.007
ocol+0.007
ocket+0.007
arter+0.006
aster+0.006
Neg logit contributions
 acts-0.006
 youngest-0.006
Let-0.005
 led-0.005
 nodded-0.005
Token some
Token ID617
Feature activation+3.27e+00

Pos logit contributions
 poisonous+0.144
ocol+0.129
ocket+0.126
aster+0.122
 bamboo+0.120
Neg logit contributions
 nodded-0.171
ver-0.170
 youngest-0.169
 acts-0.168
folk-0.167
Token of
Token ID286
Feature activation-6.46e-01

Pos logit contributions
 acts+0.099
 youngest+0.098
 nodded+0.097
Let+0.095
 oldest+0.094
Neg logit contributions
 poisonous-0.169
ocket-0.159
ocol-0.157
aster-0.156
arter-0.154
Token the
Token ID262
Feature activation+1.61e+00

Pos logit contributions
Let+0.062
 youngest+0.058
 acts+0.058
 nodded+0.057
 led+0.056
Neg logit contributions
ocket-0.106
 poisonous-0.105
arter-0.103
affle-0.099
ocol-0.096
Token wind
Token ID2344
Feature activation+3.32e+00

Pos logit contributions
Let+0.040
 nodded+0.038
 youngest+0.037
 oldest+0.036
 way+0.034
Neg logit contributions
ocol-0.095
arter-0.094
 poisonous-0.094
ocket-0.091
affle-0.086
Token.
Token ID13
Feature activation-1.54e-02

Pos logit contributions
 nodded+0.137
 youngest+0.135
ver+0.135
 acts+0.135
bars+0.133
Neg logit contributions
 poisonous-0.137
ocol-0.125
ocket-0.125
aster-0.121
arter-0.119
Token He
Token ID679
Feature activation-1.12e+00

Pos logit contributions
 poisonous+0.001
aster+0.001
 bamboo+0.001
ocol+0.000
ocket+0.000
Neg logit contributions
 acts-0.001
mun-0.001
 youngest-0.001
ver-0.001
folk-0.001
Token t
Token ID256
Feature activation-8.39e-01

Pos logit contributions
 poisonous+0.060
ocket+0.054
aster+0.053
 bamboo+0.052
ocol+0.050
Neg logit contributions
folk-0.033
ver-0.032
 acts-0.031
sets-0.031
 youngest-0.030
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.057
ocol+0.053
ocket+0.053
aster+0.053
arter+0.052
Neg logit contributions
 nodded-0.013
ver-0.013
 youngest-0.012
bars-0.012
Let-0.012
Tokeno
Token ID78
Feature activation-3.34e+00

Pos logit contributions
 nodded+0.429
ver+0.429
Let+0.426
bars+0.420
 youngest+0.409
Neg logit contributions
 poisonous-0.425
ocol-0.391
ocket-0.386
arter-0.367
aster-0.366
Tokened
Token ID276
Feature activation+2.49e+00

Pos logit contributions
 poisonous+0.150
ocket+0.137
 bamboo+0.129
sm+0.125
aster+0.125
Neg logit contributions
 acts-0.120
folk-0.119
 youngest-0.119
mun-0.117
ver-0.117
Token closer
Token ID5699
Feature activation+2.82e+00

Pos logit contributions
 nodded+0.087
Let+0.086
 led+0.085
ver+0.085
 acts+0.085
Neg logit contributions
 poisonous-0.119
ocol-0.111
ocket-0.110
arter-0.109
aster-0.109
Token and
Token ID290
Feature activation+8.42e-02

Pos logit contributions
 youngest+0.113
 acts+0.112
ver+0.112
folk+0.111
 nodded+0.110
Neg logit contributions
 poisonous-0.119
ocket-0.106
ocol-0.106
aster-0.103
arter-0.101
Token took
Token ID1718
Feature activation-4.23e-01

Pos logit contributions
 acts+0.003
 youngest+0.003
folk+0.003
ver+0.003
bars+0.003
Neg logit contributions
 poisonous-0.004
ocket-0.004
aster-0.004
ocol-0.003
 bamboo-0.003
Token room
Token ID2119
Feature activation-2.49e+00

Pos logit contributions
ocol+0.133
 poisonous+0.128
ocket+0.120
arter+0.118
aster+0.117
Neg logit contributions
 youngest-0.090
 led-0.089
's-0.088
 So-0.087
 oldest-0.086
Token.
Token ID13
Feature activation-9.18e-01

Pos logit contributions
 poisonous+0.106
ocol+0.100
ocket+0.096
arter+0.094
aster+0.093
Neg logit contributions
 nodded-0.101
ver-0.098
 youngest-0.098
 led-0.098
 acts-0.097
Token Then
Token ID3244
Feature activation+2.60e-01

Pos logit contributions
 poisonous+0.054
ocol+0.052
ocket+0.052
aster+0.049
arter+0.049
Neg logit contributions
Let-0.024
 So-0.023
 nodded-0.023
 led-0.022
 youngest-0.022
Token they
Token ID484
Feature activation+4.43e+00

Pos logit contributions
 youngest+0.007
 acts+0.007
ver+0.007
 nodded+0.007
Let+0.007
Neg logit contributions
 poisonous-0.014
ocol-0.013
ocket-0.013
aster-0.013
arter-0.012
Token t
Token ID256
Feature activation-8.75e-01

Pos logit contributions
 nodded+0.115
ver+0.114
 youngest+0.114
 acts+0.113
Let+0.111
Neg logit contributions
 poisonous-0.250
ocol-0.234
ocket-0.231
aster-0.227
arter-0.226
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.054
ocol+0.050
ocket+0.050
aster+0.049
arter+0.048
Neg logit contributions
ver-0.019
 nodded-0.019
bars-0.019
 youngest-0.019
Let-0.019
Tokeno
Token ID78
Feature activation-3.64e+00

Pos logit contributions
ver+0.418
 nodded+0.417
Let+0.413
bars+0.411
 youngest+0.404
Neg logit contributions
 poisonous-0.432
ocol-0.395
ocket-0.391
arter-0.375
aster-0.371
Tokened
Token ID276
Feature activation+2.47e+00

Pos logit contributions
 poisonous+0.160
ocket+0.146
aster+0.139
 bamboo+0.135
sm+0.134
Neg logit contributions
 acts-0.139
folk-0.135
 youngest-0.132
mun-0.130
 basics-0.129
Token out
Token ID503
Feature activation+6.98e-01

Pos logit contributions
 led+0.090
Let+0.090
 nodded+0.090
ver+0.088
 youngest+0.088
Neg logit contributions
 poisonous-0.114
ocol-0.110
ocket-0.107
arter-0.106
aster-0.104
Token of
Token ID286
Feature activation-8.91e-01

Pos logit contributions
 nodded+0.026
 led+0.026
ver+0.026
 youngest+0.026
 acts+0.026
Neg logit contributions
 poisonous-0.032
ocket-0.029
ocol-0.029
aster-0.028
arter-0.028
Token their
Token ID511
Feature activation-6.57e-01

Pos logit contributions
ocket+0.051
 poisonous+0.050
ocol+0.048
arter+0.048
affle+0.047
Neg logit contributions
 led-0.024
 way-0.022
 youngest-0.021
Let-0.021
 leads-0.020
Token sword
Token ID8429
Feature activation+9.07e-01

Pos logit contributions
 poisonous+0.022
ocol+0.020
arter+0.020
aster+0.020
ores+0.020
Neg logit contributions
 acts-0.022
 youngest-0.021
 led-0.020
 oldest-0.020
 leads-0.020
Token too
Token ID1165
Feature activation+2.43e-01

Pos logit contributions
Let+0.045
 youngest+0.044
 acts+0.044
 oldest+0.043
mun+0.043
Neg logit contributions
 poisonous-0.030
ocket-0.027
 bamboo-0.024
aster-0.024
ocol-0.024
Token.
Token ID13
Feature activation-7.97e-01

Pos logit contributions
Let+0.013
 acts+0.013
 youngest+0.013
folk+0.013
 oldest+0.013
Neg logit contributions
 poisonous-0.008
aster-0.006
 injuries-0.006
ocket-0.006
 bamboo-0.006
Token They
Token ID1119
Feature activation+6.60e-01

Pos logit contributions
 poisonous+0.037
arter+0.034
 bamboo+0.034
aster+0.033
ocol+0.032
Neg logit contributions
 acts-0.028
 youngest-0.028
folk-0.027
bars-0.027
 oldest-0.027
Token t
Token ID256
Feature activation-8.30e-01

Pos logit contributions
 acts+0.022
sets+0.022
folk+0.021
 basics+0.021
bars+0.021
Neg logit contributions
 poisonous-0.032
ocket-0.030
 bamboo-0.029
aster-0.028
 injuries-0.027
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.053
ocket+0.049
ocol+0.049
aster+0.048
arter+0.048
Neg logit contributions
ver-0.016
 nodded-0.016
 youngest-0.016
 acts-0.016
Let-0.016
Tokeno
Token ID78
Feature activation-3.57e+00

Pos logit contributions
ver+0.455
 nodded+0.454
 acts+0.451
 youngest+0.451
Let+0.448
Neg logit contributions
 poisonous-0.384
ocol-0.344
ocket-0.342
aster-0.331
arter-0.326
Tokened
Token ID276
Feature activation+2.45e+00

Pos logit contributions
 poisonous+0.124
ocket+0.108
 bamboo+0.106
eds+0.106
sm+0.104
Neg logit contributions
 acts-0.164
mun-0.156
 youngest-0.156
folk-0.155
 oldest-0.155
Token to
Token ID284
Feature activation-1.73e-01

Pos logit contributions
ver+0.096
 nodded+0.096
 acts+0.096
 youngest+0.096
Let+0.095
Neg logit contributions
 poisonous-0.105
ocol-0.095
ocket-0.095
aster-0.092
arter-0.091
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
 poisonous+0.009
ocket+0.009
ocol+0.009
arter+0.008
affle+0.008
Neg logit contributions
 youngest-0.005
Let-0.005
 led-0.005
 oldest-0.005
 acts-0.005
Token shed
Token ID14999
Feature activation+2.07e+00

Pos logit contributions
 youngest+0.046
 oldest+0.045
 way+0.044
 smallest+0.043
 leader+0.042
Neg logit contributions
ocol-0.074
ez-0.070
oof-0.068
ake-0.067
 poisonous-0.067
Token brave
Token ID14802
Feature activation+4.18e+00

Pos logit contributions
 acts+0.014
ver+0.014
 nodded+0.014
 youngest+0.014
Let+0.014
Neg logit contributions
 poisonous-0.018
ocol-0.017
ocket-0.017
aster-0.016
arter-0.016
Token,
Token ID11
Feature activation+3.12e-01

Pos logit contributions
ver+0.170
 youngest+0.169
 acts+0.167
 nodded+0.167
Let+0.166
Neg logit contributions
 poisonous-0.174
ocket-0.156
ocol-0.155
aster-0.150
arter-0.148
Token so
Token ID523
Feature activation+4.87e-01

Pos logit contributions
ver+0.012
 youngest+0.012
 acts+0.012
 nodded+0.012
folk+0.012
Neg logit contributions
 poisonous-0.013
ocket-0.012
ocol-0.012
aster-0.012
 bamboo-0.011
Token she
Token ID673
Feature activation+4.99e-01

Pos logit contributions
 acts+0.017
 youngest+0.017
ver+0.017
bars+0.017
folk+0.017
Neg logit contributions
 poisonous-0.023
ocket-0.021
aster-0.021
ocol-0.020
arter-0.019
Token t
Token ID256
Feature activation-7.87e-01

Pos logit contributions
bars+0.017
 acts+0.017
folk+0.017
mun+0.016
sets+0.016
Neg logit contributions
 poisonous-0.025
ocket-0.023
aster-0.021
 bamboo-0.021
 buried-0.019
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.046
ocket+0.043
ocol+0.043
aster+0.042
arter+0.042
Neg logit contributions
 acts-0.018
 nodded-0.018
 youngest-0.018
ver-0.018
Let-0.018
Tokeno
Token ID78
Feature activation-3.26e+00

Pos logit contributions
ver+0.437
 nodded+0.437
 youngest+0.432
 acts+0.431
Let+0.430
Neg logit contributions
 poisonous-0.402
ocol-0.363
ocket-0.360
aster-0.348
arter-0.345
Tokened
Token ID276
Feature activation+2.47e+00

Pos logit contributions
 poisonous+0.133
ocket+0.121
eds+0.116
aster+0.113
 bamboo+0.112
Neg logit contributions
 acts-0.133
mun-0.125
folk-0.124
 youngest-0.123
 basics-0.121
Token around
Token ID1088
Feature activation+1.79e+00

Pos logit contributions
 led+0.086
Let+0.085
 nodded+0.085
 youngest+0.082
ver+0.081
Neg logit contributions
 poisonous-0.119
arter-0.115
ocol-0.115
ocket-0.113
aster-0.109
Token and
Token ID290
Feature activation+3.26e-02

Pos logit contributions
 led+0.062
 nodded+0.061
Let+0.060
 acts+0.059
 youngest+0.057
Neg logit contributions
 poisonous-0.091
arter-0.085
ocol-0.084
ocket-0.083
affle-0.080
Token didn
Token ID1422
Feature activation-1.22e+00

Pos logit contributions
 acts+0.001
 youngest+0.001
folk+0.001
ver+0.001
bars+0.001
Neg logit contributions
 poisonous-0.002
ocket-0.002
aster-0.002
ocol-0.002
 bamboo-0.001
Token,
Token ID11
Feature activation+1.24e-01

Pos logit contributions
 poisonous+0.030
ocket+0.027
aster+0.026
ocol+0.025
arter+0.025
Neg logit contributions
mun-0.037
ver-0.037
 youngest-0.037
 acts-0.037
Let-0.037
Token and
Token ID290
Feature activation-1.71e-01

Pos logit contributions
ver+0.004
 youngest+0.004
 acts+0.004
 nodded+0.004
folk+0.004
Neg logit contributions
 poisonous-0.006
ocket-0.005
ocol-0.005
aster-0.005
arter-0.005
Token then
Token ID788
Feature activation-1.20e-01

Pos logit contributions
 poisonous+0.008
ocket+0.007
ocol+0.007
aster+0.007
arter+0.006
Neg logit contributions
 acts-0.007
ver-0.007
 youngest-0.007
 nodded-0.006
folk-0.006
Token they
Token ID484
Feature activation+4.46e+00

Pos logit contributions
 poisonous+0.006
aster+0.006
ocket+0.006
ocol+0.005
 injuries+0.005
Neg logit contributions
 acts-0.004
 youngest-0.004
folk-0.004
mun-0.004
ver-0.004
Token t
Token ID256
Feature activation-8.59e-01

Pos logit contributions
 acts+0.134
ver+0.131
 youngest+0.131
 nodded+0.128
Let+0.128
Neg logit contributions
 poisonous-0.234
ocket-0.217
ocol-0.213
aster-0.212
arter-0.205
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.053
ocol+0.050
ocket+0.050
aster+0.049
arter+0.049
Neg logit contributions
 acts-0.017
 nodded-0.017
ver-0.017
 youngest-0.017
Let-0.016
Tokeno
Token ID78
Feature activation-3.61e+00

Pos logit contributions
ver+0.424
 nodded+0.423
 youngest+0.420
 acts+0.419
Let+0.417
Neg logit contributions
 poisonous-0.414
ocol-0.374
ocket-0.373
aster-0.360
arter-0.357
Tokened
Token ID276
Feature activation+2.53e+00

Pos logit contributions
 poisonous+0.156
ocket+0.144
aster+0.135
eds+0.131
 injuries+0.130
Neg logit contributions
 acts-0.140
mun-0.134
folk-0.132
 youngest-0.132
 oldest-0.130
Token to
Token ID284
Feature activation-2.82e-01

Pos logit contributions
 nodded+0.096
Let+0.095
ver+0.095
 youngest+0.095
 led+0.094
Neg logit contributions
 poisonous-0.113
ocol-0.105
ocket-0.105
arter-0.103
aster-0.101
Token the
Token ID262
Feature activation+1.17e+00

Pos logit contributions
 poisonous+0.016
ocket+0.015
ocol+0.015
arter+0.014
affle+0.014
Neg logit contributions
Let-0.008
 youngest-0.008
 led-0.008
 oldest-0.008
 acts-0.008
Token table
Token ID3084
Feature activation-1.96e+00

Pos logit contributions
 youngest+0.035
Let+0.034
 oldest+0.033
 way+0.032
 eldest+0.031
Neg logit contributions
ocol-0.066
arter-0.063
ez-0.061
 poisonous-0.061
ocket-0.061
Token and
Token ID290
Feature activation-4.57e-03

Pos logit contributions
 poisonous+0.065
ocol+0.062
ocket+0.061
arter+0.060
aster+0.059
Neg logit contributions
ver-0.045
 led-0.044
 acts-0.043
 nodded-0.043
bars-0.043
Token stood
Token ID6204
Feature activation+1.01e+00

Pos logit contributions
 poisonous+0.000
ocket+0.000
aster+0.000
ocol+0.000
arter+0.000
Neg logit contributions
 youngest-0.000
 acts-0.000
ver-0.000
folk-0.000
 nodded-0.000
Token on
Token ID319
Feature activation-1.05e+00

Pos logit contributions
 nodded+0.029
 nic+0.029
 best+0.028
 hardest+0.028
Let+0.027
Neg logit contributions
arter-0.057
 poisonous-0.056
ocket-0.054
aster-0.054
ocol-0.053
Token her
Token ID607
Feature activation-2.18e+00

Pos logit contributions
 poisonous+0.052
arter+0.050
ocket+0.049
ocol+0.049
aster+0.046
Neg logit contributions
 led-0.034
 acts-0.034
Let-0.034
 youngest-0.033
 nodded-0.032
Token t
Token ID256
Feature activation-8.70e-01

Pos logit contributions
 poisonous+0.096
ocol+0.093
aster+0.087
arter+0.087
ocket+0.086
Neg logit contributions
 youngest-0.088
 oldest-0.085
 led-0.084
 acts-0.084
 way-0.084
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.038
ocol+0.032
ocket+0.031
aster+0.030
arter+0.030
Neg logit contributions
bars-0.040
 youngest-0.037
ver-0.037
 So-0.036
 eldest-0.035
Tokenoes
Token ID3028
Feature activation+4.55e+00

Pos logit contributions
bars+0.250
ver+0.249
 nodded+0.231
Let+0.228
 youngest+0.219
Neg logit contributions
 poisonous-0.619
ocol-0.581
ocket-0.576
arter-0.554
aster-0.546
Token to
Token ID284
Feature activation-1.55e-01

Pos logit contributions
ver+0.165
 nodded+0.162
 youngest+0.159
 led+0.159
 acts+0.159
Neg logit contributions
 poisonous-0.215
ocol-0.199
ocket-0.194
arter-0.192
aster-0.192
Token make
Token ID787
Feature activation+8.84e-01

Pos logit contributions
 poisonous+0.008
ocket+0.008
arter+0.008
ocol+0.008
affle+0.007
Neg logit contributions
 youngest-0.005
 led-0.005
Let-0.005
 oldest-0.005
 acts-0.005
Token sure
Token ID1654
Feature activation+2.32e+00

Pos logit contributions
 youngest+0.032
 led+0.032
 acts+0.032
 nodded+0.031
 basics+0.031
Neg logit contributions
 poisonous-0.040
ocket-0.038
arter-0.038
ocol-0.037
aster-0.035
Token they
Token ID484
Feature activation+4.89e+00

Pos logit contributions
 youngest+0.098
 acts+0.097
 nodded+0.096
ver+0.096
Let+0.095
Neg logit contributions
 poisonous-0.093
ocket-0.083
ocol-0.082
aster-0.081
arter-0.078
Tokencream
Token ID36277
Feature activation-4.58e+00

Pos logit contributions
 poisonous+0.092
ocket+0.083
ocol+0.081
arter+0.080
aster+0.077
Neg logit contributions
ver-0.126
 youngest-0.126
 nodded-0.126
 acts-0.126
Let-0.125
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
 poisonous+0.155
ocol+0.135
ocket+0.135
aster+0.133
 bamboo+0.127
Neg logit contributions
 acts-0.220
 youngest-0.218
 nodded-0.217
Let-0.216
ver-0.213
Token He
Token ID679
Feature activation-1.14e+00

Pos logit contributions
aster+0.004
ocket+0.004
 poisonous+0.004
 heaven+0.004
ocol+0.004
Neg logit contributions
mun-0.004
sets-0.004
lest-0.004
folk-0.004
ver-0.004
Token carefully
Token ID7773
Feature activation+1.90e+00

Pos logit contributions
 poisonous+0.060
aster+0.055
ocket+0.055
 bamboo+0.053
ocol+0.053
Neg logit contributions
ver-0.032
folk-0.032
 acts-0.031
sets-0.031
mun-0.030
Token t
Token ID256
Feature activation-7.50e-01

Pos logit contributions
ver+0.061
 acts+0.060
 youngest+0.060
folk+0.060
 oldest+0.058
Neg logit contributions
 poisonous-0.093
aster-0.088
ocol-0.085
ocket-0.085
 bamboo-0.080
Tokenipt
Token ID10257
Feature activation+1.02e+01

Pos logit contributions
 poisonous+0.052
ocket+0.048
arter+0.047
ocol+0.047
aster+0.047
Neg logit contributions
bars-0.011
 nodded-0.011
ver-0.011
 youngest-0.011
Let-0.011
Tokeno
Token ID78
Feature activation-3.38e+00

Pos logit contributions
ver+0.362
bars+0.359
 nodded+0.355
Let+0.350
 youngest+0.339
Neg logit contributions
 poisonous-0.502
ocol-0.457
ocket-0.454
arter-0.440
aster-0.429
Tokened
Token ID276
Feature activation+2.47e+00

Pos logit contributions
 poisonous+0.151
ocket+0.142
aster+0.137
ocol+0.132
 bamboo+0.131
Neg logit contributions
 acts-0.118
 youngest-0.114
 oldest-0.111
mun-0.110
ver-0.110
Token out
Token ID503
Feature activation+8.08e-01

Pos logit contributions
 led+0.081
 nodded+0.081
Let+0.080
 youngest+0.078
ver+0.076
Neg logit contributions
 poisonous-0.124
arter-0.121
ocket-0.117
ocol-0.117
aster-0.114
Token of
Token ID286
Feature activation-5.95e-01

Pos logit contributions
 nodded+0.033
ver+0.033
 acts+0.033
 youngest+0.033
Let+0.032
Neg logit contributions
 poisonous-0.034
ocol-0.030
ocket-0.030
aster-0.029
arter-0.029
Token the
Token ID262
Feature activation+1.61e+00

Pos logit contributions
arter+0.033
ocket+0.033
 poisonous+0.032
ocol+0.029
alo+0.029
Neg logit contributions
 led-0.017
 way-0.016
Let-0.016
 youngest-0.016
bars-0.015
Token giving
Token ID3501
Feature activation+8.19e-01

Pos logit contributions
 acts+0.106
 youngest+0.105
 way+0.101
 means+0.101
 led+0.100
Neg logit contributions
ocket-0.103
 poisonous-0.102
arter-0.094
ocol-0.092
sm-0.086
Token him
Token ID683
Feature activation-1.50e+00

Pos logit contributions
 acts+0.034
Let+0.034
 nodded+0.033
 youngest+0.033
 means+0.032
Neg logit contributions
 poisonous-0.033
arter-0.032
ocket-0.030
ocol-0.030
aster-0.029
Token too
Token ID1165
Feature activation+4.69e-01

Pos logit contributions
arter+0.064
ocket+0.063
ocol+0.063
 poisonous+0.062
aster+0.059
Neg logit contributions
 acts-0.055
 youngest-0.055
 nodded-0.055
 nic-0.054
's-0.053
Token many
Token ID867
Feature activation-6.57e-01

Pos logit contributions
 nodded+0.023
ver+0.023
 acts+0.023
 youngest+0.023
Let+0.022
Neg logit contributions
 poisonous-0.015
ocket-0.014
ocol-0.014
arter-0.013
aster-0.013
Token ch
Token ID442
Feature activation+1.83e+00

Pos logit contributions
 poisonous+0.028
arter+0.027
ocket+0.027
aster+0.026
ocol+0.026
Neg logit contributions
 acts-0.026
 nodded-0.024
 youngest-0.024
 led-0.023
Let-0.023
Tokenocol
Token ID4668
Feature activation-1.20e+01

Pos logit contributions
 acts+0.093
folk+0.088
 nodded+0.087
bars+0.087
 youngest+0.086
Neg logit contributions
 poisonous-0.059
ocket-0.050
aster-0.049
 brand-0.047
 bamboo-0.047
Tokenates
Token ID689
Feature activation+2.20e-01

Pos logit contributions
 poisonous+0.412
ocket+0.354
ocol+0.353
aster+0.346
arter+0.342
Neg logit contributions
ver-0.577
 acts-0.572
 nodded-0.571
 youngest-0.569
folk-0.562
Token."
Token ID526
Feature activation+1.13e+00

Pos logit contributions
ver+0.009
bars+0.008
 acts+0.008
 nodded+0.008
 youngest+0.008
Neg logit contributions
 poisonous-0.009
ocol-0.009
arter-0.008
ocket-0.008
aster-0.008
Token The
Token ID383
Feature activation+4.18e-02

Pos logit contributions
 acts+0.038
ver+0.038
 youngest+0.038
bars+0.037
 nodded+0.037
Neg logit contributions
 poisonous-0.055
ocol-0.050
aster-0.050
ocket-0.050
arter-0.048
Token king
Token ID5822
Feature activation-1.77e+00

Pos logit contributions
 youngest+0.001
 oldest+0.001
 nodded+0.001
 acts+0.001
 eldest+0.001
Neg logit contributions
 poisonous-0.002
ocol-0.002
arter-0.002
ocket-0.002
aster-0.002
Token learned
Token ID4499
Feature activation-3.73e-01

Pos logit contributions
 poisonous+0.099
ocket+0.092
aster+0.089
ocol+0.086
 bamboo+0.086
Neg logit contributions
Let-0.046
 youngest-0.046
folk-0.045
ver-0.044
 oldest-0.044
Token as
Token ID355
Feature activation+8.52e-01

Pos logit contributions
ver+0.002
Let+0.002
 nodded+0.002
 youngest+0.002
 acts+0.002
Neg logit contributions
 poisonous-0.002
ocket-0.002
ocol-0.002
aster-0.002
arter-0.002
Token he
Token ID339
Feature activation+2.06e+00

Pos logit contributions
 acts+0.027
 youngest+0.027
 nodded+0.027
ver+0.027
Let+0.026
Neg logit contributions
 poisonous-0.043
ocol-0.039
ocket-0.039
aster-0.039
arter-0.038
Token opened
Token ID4721
Feature activation+1.93e+00

Pos logit contributions
 youngest+0.052
bars+0.051
ver+0.051
folk+0.051
 oldest+0.050
Neg logit contributions
 poisonous-0.115
ocket-0.107
aster-0.104
ocol-0.104
 bamboo-0.099
Token the
Token ID262
Feature activation+1.76e+00

Pos logit contributions
 youngest+0.071
 nodded+0.070
 acts+0.069
 led+0.069
bars+0.068
Neg logit contributions
 poisonous-0.088
ocket-0.084
arter-0.081
ocol-0.078
aster-0.078
Token ch
Token ID442
Feature activation+2.06e+00

Pos logit contributions
 youngest+0.061
 oldest+0.059
 acts+0.058
bars+0.058
 nic+0.057
Neg logit contributions
 poisonous-0.084
ocol-0.080
aster-0.080
ocket-0.079
arter-0.079
Tokenocol
Token ID4668
Feature activation-1.20e+01

Pos logit contributions
 acts+0.123
 nodded+0.122
 youngest+0.121
folk+0.121
bars+0.119
Neg logit contributions
 poisonous-0.049
ocket-0.040
aster-0.036
arter-0.035
ocol-0.035
Tokenates
Token ID689
Feature activation+2.02e-01

Pos logit contributions
 poisonous+0.410
ocket+0.353
ocol+0.350
aster+0.343
arter+0.340
Neg logit contributions
ver-0.578
 acts-0.574
 nodded-0.573
 youngest-0.573
folk-0.565
Token and
Token ID290
Feature activation-2.31e-01

Pos logit contributions
 acts+0.009
 youngest+0.009
 nodded+0.009
Let+0.009
ver+0.009
Neg logit contributions
 poisonous-0.007
ocket-0.007
ocol-0.006
aster-0.006
arter-0.006
Token started
Token ID2067
Feature activation+3.59e+00

Pos logit contributions
 poisonous+0.011
ocket+0.010
ocol+0.010
aster+0.010
arter+0.010
Neg logit contributions
ver-0.008
 acts-0.008
 youngest-0.008
 nodded-0.007
folk-0.007
Token eating
Token ID6600
Feature activation-5.25e+00

Pos logit contributions
 nodded+0.141
 youngest+0.140
 acts+0.140
Let+0.138
ver+0.138
Neg logit contributions
 poisonous-0.154
ocket-0.141
ocol-0.140
arter-0.135
aster-0.135
Token them
Token ID606
Feature activation+3.54e-02

Pos logit contributions
 poisonous+0.227
ocket+0.217
arter+0.215
aster+0.203
ocol+0.202
Neg logit contributions
 nodded-0.199
 acts-0.197
Let-0.195
 led-0.193
 youngest-0.190
Token not
Token ID407
Feature activation+7.59e-01

Pos logit contributions
 poisonous+0.140
ocol+0.126
aster+0.126
ocket+0.126
arter+0.123
Neg logit contributions
ver-0.106
 youngest-0.106
 acts-0.104
folk-0.104
 nodded-0.103
Token eat
Token ID4483
Feature activation-5.57e+00

Pos logit contributions
 acts+0.026
 nodded+0.026
 youngest+0.026
Let+0.026
ver+0.025
Neg logit contributions
 poisonous-0.036
ocket-0.034
ocol-0.034
arter-0.032
aster-0.032
Token too
Token ID1165
Feature activation+2.43e-01

Pos logit contributions
 poisonous+0.232
ocket+0.227
aster+0.225
arter+0.218
ocol+0.212
Neg logit contributions
 acts-0.213
 led-0.204
 nodded-0.202
 hardest-0.199
ver-0.198
Token many
Token ID867
Feature activation-7.95e-01

Pos logit contributions
ver+0.011
 acts+0.011
bars+0.011
 nodded+0.011
 So+0.011
Neg logit contributions
ocket-0.008
 poisonous-0.008
ocol-0.008
arter-0.007
aster-0.007
Token ch
Token ID442
Feature activation+1.65e+00

Pos logit contributions
 poisonous+0.038
arter+0.035
ocket+0.035
aster+0.035
ocol+0.034
Neg logit contributions
 acts-0.028
 nodded-0.027
 led-0.026
 youngest-0.026
folk-0.026
Tokenocol
Token ID4668
Feature activation-1.20e+01

Pos logit contributions
 acts+0.109
folk+0.105
ver+0.104
bars+0.104
 nodded+0.103
Neg logit contributions
 poisonous-0.028
ocket-0.020
aster-0.018
 bamboo-0.016
 brand-0.015
Tokenates
Token ID689
Feature activation+2.07e-01

Pos logit contributions
 poisonous+0.427
ocket+0.362
ocol+0.361
aster+0.359
arter+0.355
Neg logit contributions
ver-0.569
 acts-0.557
 nodded-0.555
 youngest-0.553
folk-0.550
Token and
Token ID290
Feature activation-7.09e-01

Pos logit contributions
ver+0.008
 nodded+0.008
 acts+0.008
bars+0.008
folk+0.008
Neg logit contributions
 poisonous-0.009
ocol-0.008
aster-0.008
arter-0.008
ocket-0.008
Token his
Token ID465
Feature activation-6.76e-01

Pos logit contributions
 poisonous+0.033
ocol+0.030
ocket+0.030
aster+0.029
arter+0.029
Neg logit contributions
ver-0.026
 youngest-0.025
 nodded-0.025
 acts-0.025
Let-0.025
Token friend
Token ID1545
Feature activation+2.32e+00

Pos logit contributions
 poisonous+0.033
aster+0.031
ocket+0.030
ocol+0.030
arter+0.030
Neg logit contributions
 acts-0.023
 youngest-0.023
 nodded-0.022
 oldest-0.022
 eldest-0.021
Token learned
Token ID4499
Feature activation-4.63e-01

Pos logit contributions
 youngest+0.063
bars+0.062
folk+0.061
ver+0.061
 oldest+0.060
Neg logit contributions
 poisonous-0.128
ocket-0.116
ocol-0.113
aster-0.113
 bamboo-0.110
Token reward
Token ID6721
Feature activation+2.28e-01

Pos logit contributions
ver+0.067
 nodded+0.066
 youngest+0.066
 acts+0.065
Let+0.064
Neg logit contributions
 poisonous-0.094
ocol-0.086
ocket-0.086
aster-0.084
arter-0.083
Token.
Token ID13
Feature activation+1.19e+00

Pos logit contributions
 nodded+0.010
ver+0.010
 acts+0.010
 youngest+0.010
Let+0.010
Neg logit contributions
 poisonous-0.009
ocol-0.008
ocket-0.008
aster-0.008
arter-0.008
Token It
Token ID632
Feature activation-1.72e+00

Pos logit contributions
 acts+0.039
ver+0.038
 youngest+0.037
 nodded+0.037
 oldest+0.036
Neg logit contributions
 poisonous-0.056
ocol-0.053
ocket-0.053
aster-0.053
 bamboo-0.051
Token was
Token ID373
Feature activation+7.13e-01

Pos logit contributions
 poisonous+0.089
ocket+0.079
 bamboo+0.077
aster+0.074
sm+0.072
Neg logit contributions
folk-0.053
 youngest-0.052
bars-0.051
ver-0.051
 eldest-0.050
Token ch
Token ID442
Feature activation+2.24e+00

Pos logit contributions
 youngest+0.026
 led+0.026
 oldest+0.025
 nodded+0.025
ver+0.025
Neg logit contributions
 poisonous-0.031
ocket-0.030
ocol-0.030
arter-0.030
aster-0.030
Tokenocol
Token ID4668
Feature activation-1.19e+01

Pos logit contributions
 acts+0.080
ver+0.079
folk+0.077
 youngest+0.077
 nodded+0.077
Neg logit contributions
 poisonous-0.103
aster-0.100
ocket-0.095
 injuries-0.090
 bamboo-0.090
Tokenates
Token ID689
Feature activation+3.75e-01

Pos logit contributions
 poisonous+0.440
ocket+0.371
arter+0.369
aster+0.367
ocol+0.360
Neg logit contributions
ver-0.555
 acts-0.541
 nodded-0.541
 youngest-0.539
folk-0.538
Token and
Token ID290
Feature activation-5.95e-01

Pos logit contributions
ver+0.018
 nodded+0.017
 youngest+0.017
 acts+0.017
bars+0.017
Neg logit contributions
 poisonous-0.013
ocol-0.012
ocket-0.012
aster-0.012
arter-0.011
Token sweets
Token ID42402
Feature activation-3.39e+00

Pos logit contributions
 poisonous+0.027
ocol+0.025
ocket+0.025
aster+0.024
arter+0.024
Neg logit contributions
 nodded-0.022
 acts-0.022
 youngest-0.021
ver-0.021
Let-0.021
Token!
Token ID0
Feature activation-3.00e-01

Pos logit contributions
 poisonous+0.131
ocol+0.122
ocket+0.117
aster+0.117
arter+0.115
Neg logit contributions
ver-0.148
 nodded-0.148
 acts-0.146
 youngest-0.145
 led-0.145
Token
Token ID198
Feature activation+2.17e-01

Pos logit contributions
 poisonous+0.014
ocol+0.013
aster+0.013
ocket+0.013
 bamboo+0.012
Neg logit contributions
 acts-0.011
 youngest-0.010
ver-0.010
 nodded-0.010
 oldest-0.010
Token because
Token ID780
Feature activation-1.37e+00

Pos logit contributions
ver+0.215
 acts+0.214
bars+0.205
 nodded+0.203
 led+0.202
Neg logit contributions
 poisonous-0.248
aster-0.239
ocol-0.224
ocket-0.217
 what-0.207
Token of
Token ID286
Feature activation+2.61e-02

Pos logit contributions
 poisonous+0.059
ocol+0.054
aster+0.053
ocket+0.052
arter+0.051
Neg logit contributions
ver-0.054
 nodded-0.054
 acts-0.053
 youngest-0.053
folk-0.052
Token his
Token ID465
Feature activation+4.04e-01

Pos logit contributions
 acts+0.001
 nodded+0.001
 youngest+0.001
ver+0.001
Let+0.001
Neg logit contributions
 poisonous-0.001
ocket-0.001
ocol-0.001
aster-0.001
arter-0.001
Token big
Token ID1263
Feature activation-2.76e+00

Pos logit contributions
 youngest+0.014
 acts+0.014
 oldest+0.014
 nodded+0.014
 eldest+0.013
Neg logit contributions
 poisonous-0.019
ocket-0.018
ocol-0.017
aster-0.017
arter-0.017
Token bus
Token ID1323
Feature activation-2.17e+00

Pos logit contributions
 poisonous+0.134
ocket+0.123
ocol+0.122
aster+0.120
arter+0.118
Neg logit contributions
 acts-0.094
 youngest-0.093
 nodded-0.092
ver-0.090
Let-0.089
Tokenhy
Token ID12114
Feature activation-1.19e+01

Pos logit contributions
 poisonous+0.086
ocket+0.077
ocol+0.077
aster+0.075
arter+0.074
Neg logit contributions
 youngest-0.091
 acts-0.091
 nodded-0.091
ver-0.091
Let-0.090
Token mustache
Token ID49303
Feature activation-2.40e+00

Pos logit contributions
 poisonous+0.508
ocol+0.460
ocket+0.455
aster+0.443
arter+0.443
Neg logit contributions
 nodded-0.480
 youngest-0.470
 acts-0.467
folk-0.467
ver-0.466
Token.
Token ID13
Feature activation-6.01e-01

Pos logit contributions
 poisonous+0.094
ocol+0.085
ocket+0.084
aster+0.082
arter+0.080
Neg logit contributions
ver-0.102
 acts-0.102
 nodded-0.102
 youngest-0.102
Let-0.101
Token
Token ID198
Feature activation+4.18e-01

Pos logit contributions
 poisonous+0.029
ocol+0.027
aster+0.027
ocket+0.027
arter+0.026
Neg logit contributions
 acts-0.020
 nodded-0.020
 youngest-0.019
ver-0.019
 led-0.019
Token
Token ID198
Feature activation+4.20e-01

Pos logit contributions
Let+0.010
 So+0.010
ver+0.009
First+0.009
 basics+0.009
Neg logit contributions
 poisonous-0.026
ocket-0.025
ocol-0.024
arter-0.024
 injuries-0.023
TokenOne
Token ID3198
Feature activation+1.77e+00

Pos logit contributions
Let+0.015
ver+0.014
 nodded+0.014
 youngest+0.014
 So+0.014
Neg logit contributions
 poisonous-0.021
ocket-0.019
ocol-0.019
arter-0.019
 injuries-0.017
Token colorful
Token ID20239
Feature activation-1.07e+00

Pos logit contributions
 poisonous+0.030
ocol+0.028
ocket+0.027
 bamboo+0.026
aster+0.025
Neg logit contributions
ver-0.028
bars-0.026
 nodded-0.026
Let-0.026
 youngest-0.026
Token cand
Token ID2658
Feature activation-3.46e+00

Pos logit contributions
 poisonous+0.053
ocol+0.049
ocket+0.048
aster+0.047
arter+0.046
Neg logit contributions
ver-0.035
 nodded-0.034
 youngest-0.034
 acts-0.034
Let-0.034
Tokenies
Token ID444
Feature activation+7.81e-01

Pos logit contributions
 poisonous+0.188
aster+0.175
ocol+0.174
ocket+0.173
arter+0.171
Neg logit contributions
 nodded-0.095
ver-0.094
 youngest-0.094
 acts-0.093
 led-0.091
Token and
Token ID290
Feature activation-1.63e-01

Pos logit contributions
 nodded+0.033
 acts+0.032
ver+0.032
 youngest+0.032
Let+0.032
Neg logit contributions
 poisonous-0.032
ocol-0.029
ocket-0.028
aster-0.028
arter-0.028
Token ch
Token ID442
Feature activation+1.63e+00

Pos logit contributions
 poisonous+0.008
ocol+0.008
ocket+0.008
aster+0.008
arter+0.008
Neg logit contributions
 nodded-0.005
 youngest-0.005
 acts-0.005
ver-0.005
Let-0.005
Tokenocol
Token ID4668
Feature activation-1.17e+01

Pos logit contributions
 acts+0.100
 nodded+0.099
folk+0.099
 youngest+0.099
ver+0.097
Neg logit contributions
 poisonous-0.035
aster-0.027
ocket-0.027
arter-0.024
 bamboo-0.023
Tokenates
Token ID689
Feature activation+3.87e-01

Pos logit contributions
 poisonous+0.420
aster+0.360
ocket+0.358
ocol+0.355
arter+0.351
Neg logit contributions
ver-0.551
 nodded-0.543
 acts-0.542
 youngest-0.541
folk-0.536
Token.
Token ID13
Feature activation-4.39e-01

Pos logit contributions
 nodded+0.016
ver+0.015
 acts+0.015
 youngest+0.015
 led+0.015
Neg logit contributions
 poisonous-0.016
ocol-0.015
aster-0.015
ocket-0.015
arter-0.015
Token She
Token ID1375
Feature activation-3.07e+00

Pos logit contributions
 poisonous+0.018
ocol+0.017
ocket+0.016
aster+0.016
 bamboo+0.016
Neg logit contributions
ver-0.017
 acts-0.017
folk-0.016
 nodded-0.016
mun-0.016
Token said
Token ID531
Feature activation+9.62e-01

Pos logit contributions
 poisonous+0.180
ocket+0.166
aster+0.163
ocol+0.162
 bamboo+0.158
Neg logit contributions
ver-0.074
 acts-0.072
folk-0.072
bars-0.070
 youngest-0.068
Token to
Token ID284
Feature activation-3.60e-01

Pos logit contributions
 youngest+0.040
 acts+0.040
bars+0.040
 oldest+0.039
folk+0.039
Neg logit contributions
 poisonous-0.039
ocket-0.035
ocol-0.035
 bamboo-0.034
aster-0.033
Token,
Token ID11
Feature activation+1.31e-01

Pos logit contributions
 poisonous+0.009
ocket+0.008
ocol+0.008
aster+0.007
arter+0.007
Neg logit contributions
 acts-0.011
 youngest-0.011
Let-0.011
 nodded-0.011
ver-0.011
Token cup
Token ID6508
Feature activation-4.83e+00

Pos logit contributions
 nodded+0.005
Let+0.005
 youngest+0.005
 acts+0.005
ver+0.005
Neg logit contributions
 poisonous-0.006
ocket-0.005
ocol-0.005
arter-0.005
aster-0.005
Tokencakes
Token ID37263
Feature activation-9.75e-01

Pos logit contributions
 poisonous+0.221
ocol+0.202
ocket+0.201
aster+0.196
arter+0.194
Neg logit contributions
 nodded-0.176
ver-0.176
 acts-0.175
 youngest-0.175
Let-0.172
Token and
Token ID290
Feature activation-3.60e-01

Pos logit contributions
 poisonous+0.042
ocol+0.038
ocket+0.038
aster+0.038
arter+0.036
Neg logit contributions
 acts-0.038
 youngest-0.038
ver-0.037
 nodded-0.037
Let-0.037
Token ch
Token ID442
Feature activation+1.83e+00

Pos logit contributions
 poisonous+0.015
ocol+0.013
aster+0.013
ocket+0.013
 bamboo+0.012
Neg logit contributions
ver-0.015
 acts-0.015
 youngest-0.015
 nodded-0.014
folk-0.014
Tokenocol
Token ID4668
Feature activation-1.17e+01

Pos logit contributions
 nodded+0.116
folk+0.116
 acts+0.116
bars+0.113
 youngest+0.113
Neg logit contributions
 poisonous-0.037
ocket-0.030
arter-0.025
aster-0.023
 injuries-0.022
Tokenates
Token ID689
Feature activation+4.60e-01

Pos logit contributions
 poisonous+0.462
arter+0.390
aster+0.388
ocket+0.388
ocol+0.368
Neg logit contributions
ver-0.519
folk-0.504
 nodded-0.502
 youngest-0.499
 acts-0.499
Token.
Token ID13
Feature activation-7.39e-01

Pos logit contributions
 nodded+0.019
ver+0.019
 youngest+0.018
 acts+0.018
bars+0.018
Neg logit contributions
 poisonous-0.019
ocol-0.017
ocket-0.017
arter-0.017
aster-0.017
Token
Token ID220
Feature activation+3.52e+00

Pos logit contributions
 poisonous+0.036
ocol+0.033
aster+0.033
ocket+0.032
arter+0.031
Neg logit contributions
 acts-0.025
ver-0.024
 youngest-0.024
 nodded-0.024
 oldest-0.024
Token
Token ID198
Feature activation+6.68e-01

Pos logit contributions
 acts+0.120
 youngest+0.119
 nodded+0.119
ver+0.116
folk+0.115
Neg logit contributions
 poisonous-0.168
ocol-0.155
ocket-0.154
aster-0.151
arter-0.149
Token
Token ID198
Feature activation+6.62e-01

Pos logit contributions
ver+0.021
 nodded+0.020
Let+0.020
 youngest+0.020
 acts+0.020
Neg logit contributions
 poisonous-0.035
ocket-0.032
ocol-0.032
arter-0.031
aster-0.031
Tokenoll
Token ID692
Feature activation-8.83e+00

Pos logit contributions
 poisonous+0.196
aster+0.171
arter+0.162
 injuries+0.160
eds+0.159
Neg logit contributions
ver-0.269
 nodded-0.253
bars-0.246
 youngest-0.246
folk-0.245
Tokenip
Token ID541
Feature activation-4.58e+00

Pos logit contributions
 poisonous+0.364
arter+0.335
aster+0.329
ocol+0.322
ocket+0.320
Neg logit contributions
ver-0.365
 nodded-0.360
bars-0.352
 acts-0.351
mun-0.337
Tokenops
Token ID2840
Feature activation-3.38e-01

Pos logit contributions
 poisonous+0.210
ocol+0.195
ocket+0.193
arter+0.191
aster+0.189
Neg logit contributions
 acts-0.165
 nodded-0.165
ver-0.164
 youngest-0.161
bars-0.159
Token,
Token ID11
Feature activation+1.22e-01

Pos logit contributions
 poisonous+0.015
ocol+0.014
ocket+0.013
arter+0.013
aster+0.013
Neg logit contributions
ver-0.013
 nodded-0.013
 led-0.013
bars-0.013
folk-0.012
Token ch
Token ID442
Feature activation+1.87e+00

Pos logit contributions
 nodded+0.005
Let+0.005
 led+0.004
 acts+0.004
 youngest+0.004
Neg logit contributions
 poisonous-0.006
ocket-0.005
ocol-0.005
arter-0.005
aster-0.005
Tokenocol
Token ID4668
Feature activation-1.17e+01

Pos logit contributions
 acts+0.101
 nodded+0.100
bars+0.097
folk+0.095
 nods+0.094
Neg logit contributions
 poisonous-0.052
 heaven-0.044
ocket-0.044
prise-0.042
 brand-0.042
Tokenates
Token ID689
Feature activation+3.97e-01

Pos logit contributions
 poisonous+0.503
arter+0.429
aster+0.420
ocket+0.410
 brand+0.405
Neg logit contributions
ver-0.485
 nodded-0.461
 acts-0.457
 youngest-0.457
folk-0.456
Token,
Token ID11
Feature activation-1.63e-02

Pos logit contributions
 nodded+0.014
ver+0.014
 acts+0.014
 led+0.013
bars+0.013
Neg logit contributions
 poisonous-0.019
ocol-0.017
aster-0.017
ocket-0.017
arter-0.017
Token g
Token ID308
Feature activation+8.69e-01

Pos logit contributions
 poisonous+0.001
arter+0.001
ocket+0.001
ocol+0.001
aster+0.001
Neg logit contributions
 nodded-0.001
Let-0.001
 acts-0.001
 led-0.001
bars-0.001
Tokenummies
Token ID39578
Feature activation-1.89e+00

Pos logit contributions
 youngest+0.031
 nodded+0.030
bars+0.029
 oldest+0.029
 eldest+0.029
Neg logit contributions
 poisonous-0.041
aster-0.036
ocket-0.036
 injuries-0.036
 handcuffs-0.035
Token,
Token ID11
Feature activation+5.85e-02

Pos logit contributions
 poisonous+0.091
ocol+0.085
aster+0.084
ocket+0.084
arter+0.081
Neg logit contributions
 nodded-0.064
 acts-0.062
 led-0.060
ver-0.060
 youngest-0.060
Token he
Token ID339
Feature activation+1.97e+00

Pos logit contributions
 poisonous+0.148
aster+0.134
ocket+0.134
ocol+0.133
arter+0.128
Neg logit contributions
ver-0.124
 acts-0.123
 youngest-0.122
 nodded-0.121
folk-0.121
Token ate
Token ID15063
Feature activation-3.10e+00

Pos logit contributions
 acts+0.052
ver+0.051
folk+0.050
 youngest+0.049
bars+0.049
Neg logit contributions
 poisonous-0.111
ocket-0.103
ocol-0.099
aster-0.099
 bamboo-0.097
Token all
Token ID477
Feature activation+5.34e+00

Pos logit contributions
arter+0.154
ocket+0.152
 poisonous+0.149
ocol+0.140
eds+0.136
Neg logit contributions
 nodded-0.099
Let-0.095
 led-0.095
 nic-0.093
 however-0.090
Token the
Token ID262
Feature activation+1.15e+00

Pos logit contributions
 nodded+0.207
 acts+0.206
Let+0.206
 youngest+0.204
ver+0.203
Neg logit contributions
 poisonous-0.231
ocket-0.216
ocol-0.211
arter-0.207
 injuries-0.199
Token ch
Token ID442
Feature activation+1.86e+00

Pos logit contributions
 acts+0.048
 nodded+0.047
mun+0.047
 youngest+0.047
 nic+0.046
Neg logit contributions
arter-0.046
 poisonous-0.045
ocket-0.043
aster-0.042
ocol-0.041
Tokenocol
Token ID4668
Feature activation-1.16e+01

Pos logit contributions
 acts+0.130
folk+0.128
 nodded+0.127
bars+0.126
 youngest+0.125
Neg logit contributions
 poisonous-0.025
ocket-0.016
arter-0.012
 injuries-0.012
 brand-0.011
Tokenates
Token ID689
Feature activation+5.62e-01

Pos logit contributions
 poisonous+0.428
ocket+0.361
arter+0.359
aster+0.354
ocol+0.353
Neg logit contributions
ver-0.539
 nodded-0.527
 acts-0.524
folk-0.523
 youngest-0.522
Token and
Token ID290
Feature activation-4.29e-01

Pos logit contributions
ver+0.023
 nodded+0.023
 acts+0.023
 youngest+0.023
Let+0.023
Neg logit contributions
 poisonous-0.023
ocol-0.021
ocket-0.021
aster-0.020
arter-0.020
Token sweets
Token ID42402
Feature activation-3.52e+00

Pos logit contributions
 poisonous+0.023
ocol+0.022
ocket+0.022
arter+0.022
aster+0.021
Neg logit contributions
 nodded-0.012
 youngest-0.012
Let-0.012
 acts-0.012
 led-0.012
Token.
Token ID13
Feature activation-5.63e-01

Pos logit contributions
 poisonous+0.145
ocol+0.134
ocket+0.131
arter+0.129
aster+0.128
Neg logit contributions
 nodded-0.145
ver-0.144
 youngest-0.143
 acts-0.141
 led-0.141
Token Then
Token ID3244
Feature activation+3.55e-01

Pos logit contributions
 poisonous+0.025
ocol+0.023
aster+0.023
ocket+0.023
arter+0.023
Neg logit contributions
 acts-0.020
ver-0.020
folk-0.019
 nodded-0.019
 youngest-0.019
Token was
Token ID373
Feature activation+5.93e-01

Pos logit contributions
 poisonous+0.018
aster+0.016
ocol+0.016
ocket+0.016
 bamboo+0.015
Neg logit contributions
 youngest-0.022
 eldest-0.021
 oldest-0.021
 acts-0.021
 basics-0.020
Token a
Token ID257
Feature activation-1.48e-01

Pos logit contributions
 youngest+0.025
 nodded+0.025
ver+0.024
Let+0.024
 acts+0.024
Neg logit contributions
 poisonous-0.024
ocol-0.022
ocket-0.022
arter-0.021
aster-0.021
Token box
Token ID3091
Feature activation+1.35e+00

Pos logit contributions
ocol+0.007
 poisonous+0.007
ocket+0.007
arter+0.007
aster+0.006
Neg logit contributions
 nodded-0.005
 youngest-0.005
Let-0.005
 oldest-0.005
 led-0.005
Token of
Token ID286
Feature activation-4.61e-01

Pos logit contributions
 nodded+0.052
bars+0.052
 led+0.052
ver+0.051
 youngest+0.051
Neg logit contributions
 poisonous-0.060
ocol-0.056
ocket-0.054
aster-0.053
arter-0.053
Token ch
Token ID442
Feature activation+1.79e+00

Pos logit contributions
 poisonous+0.022
arter+0.021
ocket+0.021
aster+0.020
ocol+0.019
Neg logit contributions
 acts-0.016
 youngest-0.016
Let-0.016
 oldest-0.016
 nodded-0.015
Tokenocol
Token ID4668
Feature activation-1.16e+01

Pos logit contributions
 acts+0.112
bars+0.109
folk+0.109
 youngest+0.107
 nodded+0.106
Neg logit contributions
 poisonous-0.039
ocket-0.030
 bamboo-0.028
arter-0.026
aster-0.026
Tokenates
Token ID689
Feature activation+6.62e-01

Pos logit contributions
 poisonous+0.430
ocket+0.363
ocol+0.360
arter+0.359
aster+0.359
Neg logit contributions
ver-0.533
 acts-0.523
 nodded-0.522
 youngest-0.522
folk-0.519
Token.
Token ID13
Feature activation-5.14e-02

Pos logit contributions
ver+0.028
 nodded+0.028
bars+0.027
 youngest+0.027
 acts+0.027
Neg logit contributions
 poisonous-0.027
ocol-0.024
aster-0.024
ocket-0.023
arter-0.023
Token "
Token ID366
Feature activation+2.69e+00

Pos logit contributions
 poisonous+0.002
ocol+0.002
aster+0.002
ocket+0.002
 bamboo+0.002
Neg logit contributions
 acts-0.002
 youngest-0.002
 nodded-0.002
ver-0.002
 oldest-0.002
TokenFor
Token ID1890
Feature activation-2.32e+00

Pos logit contributions
 nodded+0.085
 youngest+0.085
ver+0.085
 acts+0.085
Let+0.084
Neg logit contributions
 poisonous-0.136
ocol-0.125
ocket-0.124
aster-0.121
arter-0.121
Token me
Token ID502
Feature activation-2.36e+00

Pos logit contributions
 poisonous+0.099
ocket+0.090
arter+0.088
ocol+0.087
aster+0.083
Neg logit contributions
 youngest-0.094
 acts-0.093
 oldest-0.091
 led-0.090
 nodded-0.090
Token a
Token ID257
Feature activation-3.30e-01

Pos logit contributions
 poisonous+0.129
ocol+0.124
arter+0.121
ocket+0.119
aster+0.115
Neg logit contributions
 nodded-0.131
 youngest-0.131
 led-0.130
Let-0.129
 acts-0.127
Token big
Token ID1263
Feature activation-3.06e+00

Pos logit contributions
ocol+0.017
 poisonous+0.016
ocket+0.016
arter+0.016
aster+0.016
Neg logit contributions
 nodded-0.010
 youngest-0.010
Let-0.010
 oldest-0.010
 led-0.010
Token box
Token ID3091
Feature activation+1.31e+00

Pos logit contributions
 poisonous+0.157
ocket+0.151
ocol+0.144
arter+0.143
aster+0.141
Neg logit contributions
 acts-0.094
 nodded-0.092
 led-0.086
folk-0.085
 youngest-0.085
Token of
Token ID286
Feature activation-5.57e-01

Pos logit contributions
 nodded+0.053
bars+0.052
 led+0.052
ver+0.052
 youngest+0.052
Neg logit contributions
 poisonous-0.056
ocol-0.052
ocket-0.050
arter-0.049
aster-0.049
Token ch
Token ID442
Feature activation+1.73e+00

Pos logit contributions
arter+0.027
 poisonous+0.027
ocket+0.026
aster+0.026
isk+0.025
Neg logit contributions
Let-0.018
 acts-0.018
 youngest-0.018
 oldest-0.017
 led-0.017
Tokenocol
Token ID4668
Feature activation-1.16e+01

Pos logit contributions
 acts+0.097
folk+0.096
bars+0.094
 youngest+0.092
 towns+0.090
Neg logit contributions
 poisonous-0.048
ocket-0.036
 bamboo-0.036
 brand-0.036
aster-0.034
Tokenates
Token ID689
Feature activation+5.46e-01

Pos logit contributions
 poisonous+0.420
ocket+0.355
ocol+0.353
aster+0.351
arter+0.349
Neg logit contributions
ver-0.539
 youngest-0.530
 acts-0.529
 nodded-0.529
folk-0.526
Token.
Token ID13
Feature activation-5.20e-01

Pos logit contributions
ver+0.023
 nodded+0.023
 youngest+0.023
 acts+0.023
bars+0.023
Neg logit contributions
 poisonous-0.022
ocol-0.020
ocket-0.019
aster-0.019
arter-0.019
Token It
Token ID632
Feature activation-2.47e+00

Pos logit contributions
 poisonous+0.024
ocol+0.023
ocket+0.022
aster+0.022
arter+0.022
Neg logit contributions
 acts-0.018
ver-0.018
 nodded-0.018
 youngest-0.018
folk-0.017
Token was
Token ID373
Feature activation+1.80e-01

Pos logit contributions
 poisonous+0.128
 bamboo+0.114
ocket+0.114
ocol+0.109
aster+0.108
Neg logit contributions
ver-0.076
folk-0.076
 acts-0.074
 youngest-0.074
bars-0.072
Token so
Token ID523
Feature activation+3.60e-01

Pos logit contributions
 led+0.006
 youngest+0.006
 oldest+0.005
 younger+0.005
 best+0.005
Neg logit contributions
eds-0.009
ocket-0.009
arter-0.009
 poisonous-0.009
aster-0.009
Token enjoyed
Token ID8359
Feature activation-3.19e+00

Pos logit contributions
ver+0.002
 acts+0.002
bars+0.002
 basics+0.002
 youngest+0.002
Neg logit contributions
 poisonous-0.004
aster-0.004
ocket-0.004
ocol-0.004
 bamboo-0.004
Token her
Token ID607
Feature activation-2.44e+00

Pos logit contributions
 poisonous+0.156
ocket+0.149
arter+0.149
ocol+0.139
aster+0.133
Neg logit contributions
 nodded-0.112
Let-0.108
 led-0.104
 youngest-0.102
 acts-0.100
Token cool
Token ID3608
Feature activation-6.64e-02

Pos logit contributions
 poisonous+0.091
ocol+0.082
ocket+0.082
arter+0.081
aster+0.077
Neg logit contributions
 acts-0.110
 nodded-0.110
 youngest-0.109
Let-0.107
ver-0.106
Token,
Token ID11
Feature activation+3.25e-01

Pos logit contributions
 poisonous+0.003
ocket+0.003
arter+0.003
ocol+0.002
aster+0.002
Neg logit contributions
 acts-0.003
 nodded-0.003
Let-0.003
 youngest-0.003
 nods-0.003
Token ch
Token ID442
Feature activation+1.90e+00

Pos logit contributions
 nodded+0.013
Let+0.013
 youngest+0.013
 acts+0.013
 led+0.012
Neg logit contributions
 poisonous-0.014
ocol-0.013
ocket-0.013
arter-0.012
aster-0.012
Tokenocol
Token ID4668
Feature activation-1.16e+01

Pos logit contributions
 acts+0.089
 nodded+0.089
folk+0.087
 youngest+0.085
bars+0.085
Neg logit contributions
 poisonous-0.071
ocket-0.060
 bamboo-0.059
aster-0.057
 injuries-0.055
Tokenat
Token ID265
Feature activation-3.33e+00

Pos logit contributions
 poisonous+0.431
ocket+0.361
aster+0.361
ocol+0.357
arter+0.357
Neg logit contributions
ver-0.538
 nodded-0.528
 acts-0.524
 youngest-0.523
folk-0.519
Tokeny
Token ID88
Feature activation-1.90e+00

Pos logit contributions
 poisonous+0.141
ocol+0.127
ocket+0.127
aster+0.124
arter+0.121
Neg logit contributions
 acts-0.132
ver-0.131
 youngest-0.131
 nodded-0.131
Let-0.129
Token treat
Token ID2190
Feature activation-2.26e+00

Pos logit contributions
 poisonous+0.084
ocol+0.077
ocket+0.077
arter+0.075
aster+0.075
Neg logit contributions
 nodded-0.073
 youngest-0.073
 acts-0.073
Let-0.071
ver-0.070
Token!
Token ID0
Feature activation-4.83e-01

Pos logit contributions
 poisonous+0.093
arter+0.085
ocket+0.085
ocol+0.084
aster+0.082
Neg logit contributions
 nodded-0.094
 acts-0.091
Let-0.091
ver-0.091
 led-0.090
Token
Token ID198
Feature activation+7.93e-01

Pos logit contributions
 poisonous+0.024
ocol+0.022
ocket+0.022
aster+0.022
arter+0.021
Neg logit contributions
 acts-0.016
 youngest-0.015
ver-0.015
 nodded-0.015
 oldest-0.015
Token a
Token ID257
Feature activation-4.62e-01

Pos logit contributions
 poisonous+0.078
ocol+0.071
ocket+0.071
aster+0.069
arter+0.068
Neg logit contributions
 youngest-0.072
 nodded-0.072
 acts-0.072
ver-0.072
Let-0.071
Token large
Token ID1588
Feature activation-1.20e+00

Pos logit contributions
ocol+0.022
ocket+0.022
aster+0.022
 poisonous+0.022
arter+0.022
Neg logit contributions
 nic-0.015
 way-0.015
 youngest-0.015
Let-0.014
 oldest-0.014
Token selection
Token ID6356
Feature activation-2.28e+00

Pos logit contributions
 poisonous+0.057
ocket+0.054
arter+0.052
aster+0.052
ocol+0.051
Neg logit contributions
 acts-0.041
 nodded-0.040
 youngest-0.039
 led-0.039
Let-0.038
Token of
Token ID286
Feature activation-3.70e-01

Pos logit contributions
 poisonous+0.095
ocol+0.085
ocket+0.085
aster+0.083
arter+0.082
Neg logit contributions
ver-0.093
 acts-0.092
 nodded-0.092
 youngest-0.092
Let-0.091
Token ch
Token ID442
Feature activation+1.88e+00

Pos logit contributions
 poisonous+0.017
arter+0.017
ocket+0.016
aster+0.016
 injuries+0.015
Neg logit contributions
 acts-0.014
 youngest-0.013
Let-0.013
 led-0.013
 nodded-0.013
Tokenocol
Token ID4668
Feature activation-1.16e+01

Pos logit contributions
 acts+0.133
folk+0.131
bars+0.129
 youngest+0.129
 oldest+0.126
Neg logit contributions
 poisonous-0.027
ocket-0.016
arter-0.013
aster-0.012
 bamboo-0.012
Tokenates
Token ID689
Feature activation+6.53e-01

Pos logit contributions
 poisonous+0.447
arter+0.375
ocket+0.368
aster+0.364
ocol+0.355
Neg logit contributions
ver-0.521
 acts-0.510
folk-0.508
 youngest-0.506
 nodded-0.502
Token.
Token ID13
Feature activation-1.79e-01

Pos logit contributions
ver+0.027
 nodded+0.026
 acts+0.026
 youngest+0.026
bars+0.026
Neg logit contributions
 poisonous-0.027
ocol-0.025
ocket-0.024
aster-0.024
arter-0.024
Token Ell
Token ID7122
Feature activation-1.67e+00

Pos logit contributions
 poisonous+0.009
ocol+0.008
ocket+0.008
aster+0.008
arter+0.008
Neg logit contributions
 acts-0.006
 nodded-0.006
ver-0.006
 youngest-0.006
folk-0.005
Tokena
Token ID64
Feature activation-4.00e-01

Pos logit contributions
 poisonous+0.072
ocket+0.067
ocol+0.064
aster+0.064
sm+0.060
Neg logit contributions
 acts-0.064
folk-0.062
 led-0.062
Let-0.062
 youngest-0.062
Token picked
Token ID6497
Feature activation-1.44e+00

Pos logit contributions
 poisonous+0.018
ocket+0.017
aster+0.016
ocol+0.015
sm+0.015
Neg logit contributions
bars-0.013
sets-0.013
folk-0.013
ver-0.013
 acts-0.013
Token was
Token ID373
Feature activation-2.80e-02

Pos logit contributions
 poisonous+0.138
ocket+0.126
 bamboo+0.124
aster+0.118
ocol+0.115
Neg logit contributions
folk-0.082
 youngest-0.078
ver-0.077
 acts-0.076
mun-0.074
Token a
Token ID257
Feature activation-6.03e-01

Pos logit contributions
eds+0.001
aster+0.001
ez+0.001
arter+0.001
 poisonous+0.001
Neg logit contributions
 led-0.001
 best-0.001
 younger-0.001
 nic-0.001
 way-0.001
Token box
Token ID3091
Feature activation+1.29e+00

Pos logit contributions
ocol+0.031
ez+0.030
aster+0.030
isk+0.029
eds+0.029
Neg logit contributions
 way-0.020
 best-0.019
 boy-0.018
 leader-0.017
 led-0.017
Token of
Token ID286
Feature activation-7.44e-01

Pos logit contributions
bars+0.046
ver+0.046
 led+0.046
's+0.045
 youngest+0.045
Neg logit contributions
 poisonous-0.060
ocol-0.058
ocket-0.054
aster-0.053
arter-0.052
Token ch
Token ID442
Feature activation+1.70e+00

Pos logit contributions
 poisonous+0.036
arter+0.036
aster+0.035
ocket+0.035
isk+0.034
Neg logit contributions
 acts-0.024
Let-0.024
 youngest-0.024
 led-0.023
 oldest-0.023
Tokenocol
Token ID4668
Feature activation-1.15e+01

Pos logit contributions
 acts+0.098
folk+0.094
bars+0.093
 teams+0.091
 towns+0.091
Neg logit contributions
 poisonous-0.045
 brand-0.034
 prank-0.033
ocket-0.032
 liking-0.031
Tokenates
Token ID689
Feature activation+6.97e-01

Pos logit contributions
 poisonous+0.444
arter+0.370
ocket+0.368
aster+0.364
ocol+0.357
Neg logit contributions
ver-0.516
folk-0.506
 acts-0.504
 youngest-0.502
 nodded-0.501
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
ver+0.029
bars+0.028
 youngest+0.028
 nodded+0.028
 acts+0.028
Neg logit contributions
 poisonous-0.029
ocol-0.026
aster-0.025
arter-0.025
ocket-0.025
Token Lily
Token ID20037
Feature activation-4.37e+00

Pos logit contributions
 poisonous+0.055
ocol+0.051
ocket+0.051
aster+0.050
arter+0.049
Neg logit contributions
 nodded-0.035
ver-0.035
 acts-0.035
 youngest-0.034
Let-0.034
Token loved
Token ID6151
Feature activation-1.74e+00

Pos logit contributions
 poisonous+0.201
ocket+0.191
aster+0.177
 bamboo+0.176
isk+0.168
Neg logit contributions
folk-0.153
bars-0.144
 hardest-0.143
ver-0.141
 youngest-0.140
Token ch
Token ID442
Feature activation+1.70e+00

Pos logit contributions
 poisonous+0.082
ocket+0.080
arter+0.080
ocol+0.074
aster+0.073
Neg logit contributions
 acts-0.059
 oldest-0.058
 youngest-0.058
 led-0.058
 asks-0.058
Token was
Token ID373
Feature activation+3.89e-01

Pos logit contributions
 poisonous+0.028
ocol+0.026
ocket+0.025
aster+0.025
arter+0.024
Neg logit contributions
 nodded-0.029
ver-0.029
 acts-0.029
 led-0.029
 youngest-0.029
Token filled
Token ID5901
Feature activation+8.57e-01

Pos logit contributions
 led+0.015
 nodded+0.015
 youngest+0.015
ver+0.014
 nic+0.014
Neg logit contributions
ocol-0.016
 poisonous-0.016
arter-0.015
ocket-0.015
aster-0.015
Token with
Token ID351
Feature activation+8.46e-02

Pos logit contributions
Let+0.032
ver+0.032
 nodded+0.031
 youngest+0.031
 acts+0.031
Neg logit contributions
 poisonous-0.038
ocol-0.036
arter-0.035
ocket-0.035
aster-0.033
Token delicious
Token ID12625
Feature activation-3.32e+00

Pos logit contributions
 acts+0.003
 youngest+0.003
 nodded+0.003
Let+0.003
 led+0.003
Neg logit contributions
 poisonous-0.004
arter-0.003
ocket-0.003
aster-0.003
ocol-0.003
Token ch
Token ID442
Feature activation+1.65e+00

Pos logit contributions
 poisonous+0.141
ocket+0.132
aster+0.130
arter+0.127
ocol+0.122
Neg logit contributions
 acts-0.135
 nodded-0.131
 youngest-0.127
Let-0.125
 led-0.124
Tokenocol
Token ID4668
Feature activation-1.15e+01

Pos logit contributions
 acts+0.101
folk+0.100
 youngest+0.099
 nodded+0.096
 oldest+0.096
Neg logit contributions
 poisonous-0.035
ocket-0.028
aster-0.027
 bamboo-0.024
 injuries-0.023
Tokenates
Token ID689
Feature activation+6.42e-01

Pos logit contributions
 poisonous+0.402
ocket+0.344
ocol+0.344
aster+0.342
arter+0.335
Neg logit contributions
ver-0.546
 acts-0.540
 nodded-0.540
 youngest-0.538
folk-0.532
Token.
Token ID13
Feature activation-3.51e-02

Pos logit contributions
ver+0.027
 nodded+0.027
 youngest+0.027
 acts+0.026
bars+0.026
Neg logit contributions
 poisonous-0.026
ocol-0.023
aster-0.023
arter-0.023
ocket-0.022
Token He
Token ID679
Feature activation-1.18e+00

Pos logit contributions
 poisonous+0.001
aster+0.001
ocol+0.001
ocket+0.001
 bamboo+0.001
Neg logit contributions
 acts-0.001
 youngest-0.001
ver-0.001
 oldest-0.001
 nodded-0.001
Token was
Token ID373
Feature activation+3.63e-01

Pos logit contributions
 poisonous+0.064
ocket+0.059
ocol+0.058
aster+0.058
 bamboo+0.056
Neg logit contributions
ver-0.033
 acts-0.032
 youngest-0.032
folk-0.032
bars-0.032
Token happy
Token ID3772
Feature activation-1.76e+00

Pos logit contributions
 nodded+0.013
 youngest+0.013
ver+0.012
 oldest+0.012
Let+0.012
Neg logit contributions
 poisonous-0.018
ocol-0.017
ocket-0.016
arter-0.016
aster-0.016
Token and
Token ID290
Feature activation+2.12e-01

Pos logit contributions
 acts+0.064
ver+0.063
 youngest+0.062
folk+0.062
mun+0.062
Neg logit contributions
 poisonous-0.056
ocket-0.051
aster-0.049
ocol-0.049
arter-0.047
Token started
Token ID2067
Feature activation+3.37e+00

Pos logit contributions
 nodded+0.006
 youngest+0.006
ver+0.006
 acts+0.006
Let+0.006
Neg logit contributions
 poisonous-0.011
ocol-0.010
ocket-0.010
aster-0.010
arter-0.010
Token eating
Token ID6600
Feature activation-5.13e+00

Pos logit contributions
 led+0.116
Let+0.115
 nodded+0.114
 youngest+0.113
 acts+0.109
Neg logit contributions
 poisonous-0.165
ocket-0.156
arter-0.154
ocol-0.152
 bamboo-0.141
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
arter+0.252
ocket+0.251
 poisonous+0.250
ocol+0.230
eds+0.227
Neg logit contributions
 nodded-0.171
Let-0.164
 led-0.163
 acts-0.159
 So-0.159
Token ch
Token ID442
Feature activation+1.87e+00

Pos logit contributions
 nic+0.055
 youngest+0.055
 acts+0.055
Let+0.054
 led+0.054
Neg logit contributions
 poisonous-0.061
arter-0.060
aster-0.059
ocol-0.059
ocket-0.058
Tokenocol
Token ID4668
Feature activation-1.15e+01

Pos logit contributions
 acts+0.123
folk+0.117
bars+0.114
 youngest+0.114
lest+0.110
Neg logit contributions
 poisonous-0.037
 bamboo-0.024
ocket-0.021
 brand-0.021
 injuries-0.021
Tokenates
Token ID689
Feature activation+7.71e-01

Pos logit contributions
 poisonous+0.450
arter+0.372
ocket+0.370
ocol+0.361
aster+0.360
Neg logit contributions
ver-0.512
folk-0.493
 acts-0.492
 nodded-0.491
 youngest-0.490
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
ver+0.032
 nodded+0.032
 youngest+0.031
 acts+0.031
bars+0.031
Neg logit contributions
 poisonous-0.032
ocol-0.029
ocket-0.028
arter-0.028
aster-0.028
Token The
Token ID383
Feature activation+3.45e-01

Pos logit contributions
 acts+0.007
ver+0.007
 nodded+0.007
 youngest+0.006
folk+0.006
Neg logit contributions
 poisonous-0.010
ocol-0.010
ocket-0.010
aster-0.009
arter-0.009
Token shop
Token ID6128
Feature activation+2.41e+00

Pos logit contributions
 youngest+0.013
 oldest+0.012
 nic+0.012
 nodded+0.012
 eldest+0.012
Neg logit contributions
arter-0.017
 poisonous-0.016
ocket-0.015
ocol-0.015
aster-0.015
Tokenkeeper
Token ID13884
Feature activation+8.54e-01

Pos logit contributions
 acts+0.078
ver+0.076
 youngest+0.072
folk+0.072
 basics+0.071
Neg logit contributions
 poisonous-0.117
ocket-0.108
aster-0.104
ocol-0.102
 bamboo-0.099
Tokenates
Token ID689
Feature activation+6.97e-01

Pos logit contributions
 poisonous+0.444
arter+0.370
ocket+0.368
aster+0.364
ocol+0.357
Neg logit contributions
ver-0.516
folk-0.506
 acts-0.504
 youngest-0.502
 nodded-0.501
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
ver+0.029
bars+0.028
 youngest+0.028
 nodded+0.028
 acts+0.028
Neg logit contributions
 poisonous-0.029
ocol-0.026
aster-0.025
arter-0.025
ocket-0.025
Token Lily
Token ID20037
Feature activation-4.37e+00

Pos logit contributions
 poisonous+0.055
ocol+0.051
ocket+0.051
aster+0.050
arter+0.049
Neg logit contributions
 nodded-0.035
ver-0.035
 acts-0.035
 youngest-0.034
Let-0.034
Token loved
Token ID6151
Feature activation-1.74e+00

Pos logit contributions
 poisonous+0.201
ocket+0.191
aster+0.177
 bamboo+0.176
isk+0.168
Neg logit contributions
folk-0.153
bars-0.144
 hardest-0.143
ver-0.141
 youngest-0.140
Token ch
Token ID442
Feature activation+1.70e+00

Pos logit contributions
 poisonous+0.082
ocket+0.080
arter+0.080
ocol+0.074
aster+0.073
Neg logit contributions
 acts-0.059
 oldest-0.058
 youngest-0.058
 led-0.058
 asks-0.058
Tokenocol
Token ID4668
Feature activation-1.14e+01

Pos logit contributions
 acts+0.106
folk+0.103
ver+0.101
bars+0.099
 nodded+0.098
Neg logit contributions
 poisonous-0.036
ocket-0.026
 brand-0.026
 injuries-0.024
aster-0.023
Tokenates
Token ID689
Feature activation+7.68e-01

Pos logit contributions
 poisonous+0.459
arter+0.381
aster+0.377
ocket+0.376
ocol+0.366
Neg logit contributions
ver-0.501
folk-0.485
 acts-0.485
 nodded-0.482
 youngest-0.480
Token.
Token ID13
Feature activation-1.10e+00

Pos logit contributions
 nodded+0.027
ver+0.027
 acts+0.026
's+0.026
 led+0.026
Neg logit contributions
 poisonous-0.036
ocol-0.035
aster-0.033
arter-0.033
ocket-0.032
Token She
Token ID1375
Feature activation-3.33e+00

Pos logit contributions
 poisonous+0.050
ocol+0.047
ocket+0.046
aster+0.046
arter+0.046
Neg logit contributions
 youngest-0.039
ver-0.039
folk-0.038
 acts-0.038
 nodded-0.037
Token thanked
Token ID26280
Feature activation+1.46e+00

Pos logit contributions
 poisonous+0.175
ocket+0.164
aster+0.157
 bamboo+0.156
ocol+0.151
Neg logit contributions
folk-0.101
ver-0.096
bars-0.095
 youngest-0.093
sets-0.093
Token Ben
Token ID3932
Feature activation-4.05e-02

Pos logit contributions
 youngest+0.056
 acts+0.056
 nodded+0.056
 oldest+0.054
Let+0.054
Neg logit contributions
 poisonous-0.067
ocket-0.059
ocol-0.057
arter-0.057
aster-0.053
Token't
Token ID470
Feature activation+2.67e+00

Pos logit contributions
 poisonous+0.025
ocol+0.024
ocket+0.023
arter+0.022
aster+0.022
Neg logit contributions
ver-0.017
 nodded-0.017
 youngest-0.017
Let-0.016
 acts-0.016
Token have
Token ID423
Feature activation-3.37e+00

Pos logit contributions
 nodded+0.089
Let+0.088
 youngest+0.088
 acts+0.087
ver+0.086
Neg logit contributions
 poisonous-0.131
ocol-0.122
ocket-0.121
arter-0.117
 bamboo-0.113
Token all
Token ID477
Feature activation+5.30e+00

Pos logit contributions
 poisonous+0.137
ocol+0.125
ocket+0.124
aster+0.120
arter+0.119
Neg logit contributions
 nodded-0.139
 acts-0.139
 youngest-0.139
ver-0.139
Let-0.137
Token these
Token ID777
Feature activation+2.79e-01

Pos logit contributions
ver+0.246
 youngest+0.241
 nodded+0.240
 acts+0.236
folk+0.235
Neg logit contributions
 poisonous-0.200
ocol-0.175
aster-0.173
ocket-0.167
arter-0.162
Token ch
Token ID442
Feature activation+1.70e+00

Pos logit contributions
ver+0.011
 nodded+0.011
 youngest+0.011
 acts+0.011
Let+0.011
Neg logit contributions
 poisonous-0.012
ocol-0.011
ocket-0.011
aster-0.010
arter-0.010
Tokenocol
Token ID4668
Feature activation-1.13e+01

Pos logit contributions
 acts+0.119
folk+0.115
 youngest+0.115
bars+0.114
 nodded+0.114
Neg logit contributions
 poisonous-0.023
ocket-0.015
 bamboo-0.012
aster-0.012
arter-0.010
Tokenates
Token ID689
Feature activation+7.38e-01

Pos logit contributions
 poisonous+0.416
ocket+0.352
aster+0.349
arter+0.347
ocol+0.345
Neg logit contributions
ver-0.527
 acts-0.517
 nodded-0.513
 youngest-0.513
folk-0.512
Token!
Token ID0
Feature activation-7.48e-01

Pos logit contributions
ver+0.031
 nodded+0.030
 acts+0.030
 youngest+0.030
Let+0.030
Neg logit contributions
 poisonous-0.029
ocol-0.027
ocket-0.026
aster-0.026
arter-0.026
Token Now
Token ID2735
Feature activation-1.50e+00

Pos logit contributions
 poisonous+0.030
ocol+0.029
aster+0.028
ocket+0.027
 heaven+0.027
Neg logit contributions
 nodded-0.029
 youngest-0.029
 led-0.029
 acts-0.028
ver-0.028
Token,
Token ID11
Feature activation+2.74e-01

Pos logit contributions
 poisonous+0.062
ocket+0.055
aster+0.055
ocol+0.055
 bamboo+0.051
Neg logit contributions
 youngest-0.061
ver-0.060
bars-0.059
folk-0.059
 acts-0.059
Token go
Token ID467
Feature activation-6.47e-01

Pos logit contributions
 youngest+0.011
 acts+0.011
folk+0.011
ver+0.011
 nodded+0.011
Neg logit contributions
 poisonous-0.012
aster-0.010
ocket-0.010
ocol-0.010
arter-0.010
Token had
Token ID550
Feature activation-1.83e+00

Pos logit contributions
ocol+0.065
 poisonous+0.063
arter+0.062
ocket+0.061
aster+0.061
Neg logit contributions
 led-0.019
Let-0.019
 nodded-0.019
 acts-0.017
 youngest-0.017
Token a
Token ID257
Feature activation-2.99e-01

Pos logit contributions
 poisonous+0.076
ocol+0.073
ocket+0.070
arter+0.069
aster+0.068
Neg logit contributions
Let-0.076
 youngest-0.075
 nodded-0.074
 led-0.074
 oldest-0.073
Token big
Token ID1263
Feature activation-3.02e+00

Pos logit contributions
ocol+0.014
 poisonous+0.014
ocket+0.013
aster+0.013
arter+0.012
Neg logit contributions
 youngest-0.011
 nodded-0.011
 oldest-0.010
Let-0.010
 led-0.010
Token,
Token ID11
Feature activation+3.95e-02

Pos logit contributions
 poisonous+0.142
ocol+0.131
ocket+0.131
aster+0.128
arter+0.124
Neg logit contributions
 nodded-0.107
 acts-0.106
 youngest-0.105
ver-0.103
Let-0.102
Token bus
Token ID1323
Feature activation-2.05e+00

Pos logit contributions
 nodded+0.001
Let+0.001
 youngest+0.001
 led+0.001
 nic+0.001
Neg logit contributions
 poisonous-0.002
ocol-0.002
ocket-0.002
aster-0.002
arter-0.002
Tokenhy
Token ID12114
Feature activation-1.13e+01

Pos logit contributions
 poisonous+0.082
ocol+0.079
ocket+0.072
arter+0.070
aster+0.069
Neg logit contributions
 nodded-0.092
ver-0.091
 led-0.091
bars-0.090
Let-0.089
Token tail
Token ID7894
Feature activation-5.65e-02

Pos logit contributions
 poisonous+0.499
ocol+0.460
ocket+0.455
aster+0.443
arter+0.426
Neg logit contributions
 nodded-0.449
 youngest-0.429
 acts-0.421
folk-0.419
ver-0.417
Token and
Token ID290
Feature activation-2.62e-01

Pos logit contributions
 poisonous+0.002
ocket+0.002
ocol+0.002
aster+0.002
arter+0.002
Neg logit contributions
 acts-0.003
ver-0.003
 youngest-0.002
 nodded-0.002
folk-0.002
Token sharp
Token ID7786
Feature activation-1.01e+00

Pos logit contributions
 poisonous+0.012
ocket+0.010
ocol+0.010
aster+0.010
 bamboo+0.010
Neg logit contributions
ver-0.010
 acts-0.010
 youngest-0.010
folk-0.010
 nodded-0.010
Token teeth
Token ID9941
Feature activation-1.81e+00

Pos logit contributions
 poisonous+0.046
ocol+0.041
ocket+0.041
aster+0.041
arter+0.040
Neg logit contributions
 acts-0.038
 nodded-0.038
 youngest-0.037
ver-0.037
Let-0.037
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
ocol+0.088
 poisonous+0.087
arter+0.082
ocket+0.082
aster+0.081
Neg logit contributions
 nodded-0.062
ver-0.062
 led-0.061
bars-0.058
Let-0.058
Token son
Token ID3367
Feature activation+2.78e+00

Pos logit contributions
 poisonous+0.119
aster+0.110
ocket+0.110
arter+0.110
ocol+0.109
Neg logit contributions
 youngest-0.087
 acts-0.086
 nodded-0.085
 oldest-0.083
 nic-0.080
Token is
Token ID318
Feature activation+1.05e-01

Pos logit contributions
 youngest+0.103
ver+0.102
 acts+0.101
folk+0.101
 nodded+0.101
Neg logit contributions
 poisonous-0.125
ocket-0.112
ocol-0.111
aster-0.110
arter-0.107
Token eating
Token ID6600
Feature activation-5.22e+00

Pos logit contributions
 youngest+0.004
 nodded+0.004
 oldest+0.004
 led+0.004
ver+0.004
Neg logit contributions
 poisonous-0.004
ocket-0.004
ocol-0.004
arter-0.004
aster-0.004
Token our
Token ID674
Feature activation-9.41e-01

Pos logit contributions
 poisonous+0.225
arter+0.221
ocket+0.221
ocol+0.203
aster+0.196
Neg logit contributions
Let-0.189
 nodded-0.186
 acts-0.185
 youngest-0.185
 nic-0.183
Token ch
Token ID442
Feature activation+1.78e+00

Pos logit contributions
 poisonous+0.038
ocket+0.036
arter+0.035
aster+0.035
ocol+0.034
Neg logit contributions
 acts-0.040
 youngest-0.039
 oldest-0.038
 nodded-0.038
 nic-0.038
Tokenocol
Token ID4668
Feature activation-1.13e+01

Pos logit contributions
 acts+0.120
 youngest+0.114
folk+0.113
bars+0.112
 oldest+0.111
Neg logit contributions
 poisonous-0.032
ocket-0.020
 bamboo-0.020
aster-0.017
 brand-0.016
Tokenates
Token ID689
Feature activation+7.75e-01

Pos logit contributions
 poisonous+0.443
arter+0.368
ocket+0.364
aster+0.363
ocol+0.359
Neg logit contributions
ver-0.507
 acts-0.490
 nodded-0.487
 youngest-0.486
folk-0.484
Token!"
Token ID2474
Feature activation+5.88e-01

Pos logit contributions
ver+0.034
 nodded+0.033
 youngest+0.033
 acts+0.033
Let+0.033
Neg logit contributions
 poisonous-0.030
ocol-0.027
ocket-0.027
aster-0.026
arter-0.026
Token
Token ID220
Feature activation+3.78e+00

Pos logit contributions
 acts+0.020
 youngest+0.020
ver+0.020
 oldest+0.019
folk+0.019
Neg logit contributions
 poisonous-0.028
aster-0.026
ocol-0.026
ocket-0.026
arter-0.025
Token
Token ID198
Feature activation+9.59e-01

Pos logit contributions
 acts+0.156
 youngest+0.151
folk+0.149
 nodded+0.149
 oldest+0.148
Neg logit contributions
 poisonous-0.154
aster-0.142
ocol-0.140
ocket-0.137
arter-0.134
Token
Token ID198
Feature activation+9.53e-01

Pos logit contributions
 nodded+0.032
ver+0.032
Let+0.031
 youngest+0.031
 acts+0.030
Neg logit contributions
 poisonous-0.048
ocol-0.044
ocket-0.044
arter-0.043
aster-0.042
Token and
Token ID290
Feature activation-7.32e-01

Pos logit contributions
 youngest+0.124
 acts+0.124
ver+0.124
 nodded+0.123
Let+0.121
Neg logit contributions
 poisonous-0.127
ocket-0.113
ocol-0.112
aster-0.111
arter-0.109
Token jumped
Token ID11687
Feature activation+1.45e+00

Pos logit contributions
 poisonous+0.038
aster+0.034
 bamboo+0.033
ocket+0.033
ocol+0.032
Neg logit contributions
ver-0.024
folk-0.024
 youngest-0.023
bars-0.023
 acts-0.022
Token in
Token ID287
Feature activation+1.91e+00

Pos logit contributions
Let+0.049
 led+0.049
 nodded+0.047
 neither+0.045
ver+0.045
Neg logit contributions
ocol-0.070
ocket-0.070
 poisonous-0.069
aster-0.068
arter-0.067
Token.
Token ID13
Feature activation-1.27e+00

Pos logit contributions
Let+0.063
 led+0.062
 acts+0.060
 nodded+0.060
 So+0.058
Neg logit contributions
ocket-0.098
 poisonous-0.097
arter-0.094
ocol-0.093
affle-0.088
Token Anna
Token ID11735
Feature activation-1.87e+00

Pos logit contributions
 poisonous+0.072
ocket+0.068
ocol+0.068
arter+0.064
aster+0.064
Neg logit contributions
 nodded-0.034
Let-0.034
 youngest-0.033
ver-0.033
 acts-0.032
Token followed
Token ID3940
Feature activation+5.48e+00

Pos logit contributions
 poisonous+0.084
ocket+0.072
 bamboo+0.072
 injuries+0.071
aster+0.071
Neg logit contributions
sets-0.074
 youngest-0.070
folk-0.070
bars-0.070
 oldest-0.069
Token him
Token ID683
Feature activation-1.73e+00

Pos logit contributions
 youngest+0.223
Let+0.219
 nodded+0.217
 acts+0.217
 neither+0.212
Neg logit contributions
 poisonous-0.239
arter-0.208
ocol-0.206
ocket-0.206
 brand-0.190
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
 poisonous+0.071
ocket+0.063
ocol+0.062
aster+0.061
arter+0.060
Neg logit contributions
 youngest-0.072
 nodded-0.072
 acts-0.072
ver-0.072
folk-0.071
Token She
Token ID1375
Feature activation-3.55e+00

Pos logit contributions
 poisonous+0.069
ocol+0.064
ocket+0.064
aster+0.063
arter+0.062
Neg logit contributions
ver-0.037
 acts-0.036
 nodded-0.036
 youngest-0.036
Let-0.036
Token did
Token ID750
Feature activation-1.43e+00

Pos logit contributions
 poisonous+0.179
 bamboo+0.158
ocket+0.157
aster+0.153
 injuries+0.152
Neg logit contributions
folk-0.121
sets-0.118
bars-0.116
ver-0.115
 youngest-0.115
Token not
Token ID407
Feature activation+9.77e-01

Pos logit contributions
ocol+0.084
ocket+0.083
 poisonous+0.077
arter+0.076
affle+0.073
Neg logit contributions
 neither-0.039
 nodded-0.038
ver-0.038
 led-0.037
 hardest-0.034
Token in
Token ID287
Feature activation+1.87e+00

Pos logit contributions
 acts+0.041
 led+0.040
 hardest+0.039
 youngest+0.038
 means+0.038
Neg logit contributions
 poisonous-0.063
aster-0.059
arter-0.058
ocket-0.056
isk-0.055
Token and
Token ID290
Feature activation-6.20e-01

Pos logit contributions
 led+0.061
 acts+0.060
Let+0.059
 youngest+0.058
 way+0.057
Neg logit contributions
 poisonous-0.096
arter-0.089
ocket-0.088
affle-0.086
aster-0.084
Token meet
Token ID1826
Feature activation-1.69e+00

Pos logit contributions
 poisonous+0.027
ocol+0.025
ocket+0.025
aster+0.024
arter+0.024
Neg logit contributions
ver-0.024
 acts-0.024
 youngest-0.024
 nodded-0.023
folk-0.023
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
 poisonous+0.075
ocol+0.068
ocket+0.067
aster+0.066
arter+0.065
Neg logit contributions
ver-0.065
 acts-0.065
 nodded-0.065
 youngest-0.065
Let-0.064
Token other
Token ID584
Feature activation+4.14e+00

Pos logit contributions
ver+0.051
 nodded+0.049
 acts+0.048
bars+0.048
Let+0.048
Neg logit contributions
 poisonous-0.055
ocket-0.049
ocol-0.049
 bamboo-0.047
aster-0.046
Token boats
Token ID16659
Feature activation+5.91e+00

Pos logit contributions
ver+0.173
 nodded+0.163
bars+0.163
Let+0.155
folk+0.151
Neg logit contributions
 poisonous-0.177
ocol-0.164
 bamboo-0.163
ocket-0.160
arter-0.150
Token.
Token ID13
Feature activation-8.12e-01

Pos logit contributions
 youngest+0.260
 acts+0.260
ver+0.259
 nodded+0.259
Let+0.258
Neg logit contributions
 poisonous-0.222
ocket-0.198
ocol-0.195
aster-0.190
arter-0.187
Token The
Token ID383
Feature activation-8.31e-02

Pos logit contributions
aster+0.029
 poisonous+0.028
 bamboo+0.027
ocol+0.026
 heaven+0.026
Neg logit contributions
 acts-0.033
 oldest-0.032
 youngest-0.032
ver-0.032
bars-0.032
Token yacht
Token ID43207
Feature activation+2.21e+00

Pos logit contributions
 poisonous+0.004
ocket+0.004
 bamboo+0.004
ocol+0.004
aster+0.003
Neg logit contributions
ver-0.003
bars-0.003
 nodded-0.003
 So-0.003
 acts-0.003
Token quickly
Token ID2952
Feature activation+2.35e-01

Pos logit contributions
First+0.080
 First+0.076
 Und+0.075
 acts+0.074
mun+0.074
Neg logit contributions
 poisonous-0.095
ocket-0.084
 buried-0.082
 bamboo-0.080
 brand-0.079
Token gathered
Token ID9272
Feature activation+1.07e+00

Pos logit contributions
mun+0.008
ver+0.008
sets+0.008
 oldest+0.008
folk+0.008
Neg logit contributions
 poisonous-0.011
ocket-0.010
aster-0.010
 bamboo-0.010
ocol-0.010
Token the
Token ID262
Feature activation+1.74e+00

Pos logit contributions
 youngest+0.004
Let+0.004
 acts+0.004
 led+0.004
 oldest+0.004
Neg logit contributions
 poisonous-0.005
ocket-0.005
ocol-0.005
arter-0.005
 injuries-0.004
Token beach
Token ID10481
Feature activation+9.21e-01

Pos logit contributions
 youngest+0.054
 oldest+0.052
Let+0.051
 eldest+0.048
 nic+0.047
Neg logit contributions
ocol-0.097
 poisonous-0.096
ocket-0.092
arter-0.088
 injuries-0.085
Token.
Token ID13
Feature activation+1.61e-02

Pos logit contributions
ver+0.045
 acts+0.045
 youngest+0.045
folk+0.044
 nodded+0.044
Neg logit contributions
 poisonous-0.030
aster-0.027
ocket-0.026
ocol-0.025
 bamboo-0.025
Token He
Token ID679
Feature activation-9.44e-01

Pos logit contributions
 acts+0.001
ver+0.001
mun+0.001
folk+0.001
 youngest+0.001
Neg logit contributions
 poisonous-0.001
aster-0.001
ocol-0.001
arter-0.001
ocket-0.001
Token was
Token ID373
Feature activation+5.20e-01

Pos logit contributions
 poisonous+0.038
aster+0.034
 bamboo+0.033
ocket+0.033
sm+0.031
Neg logit contributions
folk-0.039
sets-0.038
 acts-0.038
 youngest-0.037
ver-0.037
Token excited
Token ID6568
Feature activation+5.09e+00

Pos logit contributions
 youngest+0.021
 nodded+0.021
ver+0.021
Let+0.021
 oldest+0.021
Neg logit contributions
 poisonous-0.021
ocol-0.020
ocket-0.020
aster-0.019
arter-0.019
Token to
Token ID284
Feature activation+4.92e-02

Pos logit contributions
ver+0.222
 acts+0.220
 nodded+0.218
 youngest+0.218
folk+0.216
Neg logit contributions
 poisonous-0.199
ocket-0.175
aster-0.174
ocol-0.174
arter-0.169
Token explore
Token ID7301
Feature activation-4.90e-01

Pos logit contributions
ver+0.002
 acts+0.002
folk+0.002
 nodded+0.002
bars+0.002
Neg logit contributions
 poisonous-0.002
aster-0.002
ocol-0.002
ocket-0.002
arter-0.002
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
 poisonous+0.023
ocket+0.021
ocol+0.021
arter+0.020
aster+0.020
Neg logit contributions
 nodded-0.018
 acts-0.018
 led-0.018
Let-0.017
bars-0.017
Token deep
Token ID2769
Feature activation+3.67e-01

Pos logit contributions
ver+0.062
 nodded+0.059
 acts+0.059
folk+0.058
 youngest+0.057
Neg logit contributions
 poisonous-0.063
ocol-0.056
ocket-0.056
aster-0.054
 bamboo-0.054
Token blue
Token ID4171
Feature activation+2.19e+00

Pos logit contributions
ver+0.013
 nodded+0.013
 acts+0.013
 youngest+0.013
Let+0.013
Neg logit contributions
 poisonous-0.017
ocol-0.016
ocket-0.016
aster-0.015
arter-0.015
Token€
Token ID26391
Feature activation-7.44e-01

Pos logit contributions
 youngest+0.130
ver+0.129
 acts+0.128
 oldest+0.125
 nodded+0.125
Neg logit contributions
 poisonous-0.179
ocket-0.164
aster-0.164
ocol-0.164
arter-0.156
Token
Token ID220
Feature activation+3.82e+00

Pos logit contributions
 poisonous+0.035
ocket+0.033
ocol+0.032
aster+0.032
arter+0.031
Neg logit contributions
 youngest-0.026
 acts-0.025
 nodded-0.025
 oldest-0.025
ver-0.025
Token
Token ID198
Feature activation+8.68e-01

Pos logit contributions
 acts+0.125
 nodded+0.125
 youngest+0.124
ver+0.124
Let+0.121
Neg logit contributions
 poisonous-0.188
ocol-0.173
ocket-0.172
aster-0.169
arter-0.166
Token
Token ID198
Feature activation+8.85e-01

Pos logit contributions
Let+0.025
ver+0.025
 nodded+0.024
 youngest+0.023
 led+0.023
Neg logit contributions
 poisonous-0.048
ocol-0.044
ocket-0.044
arter-0.044
aster-0.042
TokenThe
Token ID464
Feature activation+6.87e-01

Pos logit contributions
Let+0.032
 nodded+0.030
ver+0.030
 youngest+0.030
folk+0.029
Neg logit contributions
 poisonous-0.043
ocket-0.040
arter-0.039
ocol-0.039
aster-0.037
Token older
Token ID4697
Feature activation+5.85e+00

Pos logit contributions
ver+0.021
 nodded+0.020
 acts+0.020
folk+0.020
bars+0.019
Neg logit contributions
 poisonous-0.037
ocol-0.034
ocket-0.033
aster-0.033
arter-0.032
Token girl
Token ID2576
Feature activation+6.08e-01

Pos logit contributions
ver+0.173
First+0.153
 led+0.149
bars+0.149
Let+0.146
Neg logit contributions
 poisonous-0.297
aster-0.290
ocol-0.289
ocket-0.275
 bamboo-0.265
Token smiled
Token ID13541
Feature activation+4.13e+00

Pos logit contributions
ver+0.017
 youngest+0.017
bars+0.017
folk+0.017
 acts+0.017
Neg logit contributions
 poisonous-0.032
ocket-0.030
aster-0.029
ocol-0.028
 bamboo-0.027
Token and
Token ID290
Feature activation+2.94e-02

Pos logit contributions
ver+0.166
 acts+0.166
 youngest+0.165
 nodded+0.164
Let+0.163
Neg logit contributions
 poisonous-0.173
ocol-0.156
ocket-0.155
aster-0.151
arter-0.149
Token said
Token ID531
Feature activation+1.25e+00

Pos logit contributions
folk+0.001
ver+0.001
 acts+0.001
bars+0.001
 youngest+0.001
Neg logit contributions
 poisonous-0.002
ocket-0.001
aster-0.001
 bamboo-0.001
ocol-0.001
Token,
Token ID11
Feature activation+3.62e-01

Pos logit contributions
 youngest+0.053
 acts+0.052
 oldest+0.051
bars+0.051
folk+0.051
Neg logit contributions
 poisonous-0.050
ocol-0.045
ocket-0.045
aster-0.043
 bamboo-0.042
Token.
Token ID13
Feature activation-1.24e+00

Pos logit contributions
ver+0.067
bars+0.065
 led+0.064
 acts+0.062
 nodded+0.062
Neg logit contributions
 poisonous-0.073
ocol-0.071
aster-0.067
arter-0.066
ocket-0.065
Token
Token ID198
Feature activation-8.33e-02

Pos logit contributions
 poisonous+0.058
ocket+0.054
ocol+0.053
aster+0.052
arter+0.051
Neg logit contributions
 youngest-0.043
 acts-0.043
folk-0.042
 nodded-0.042
bars-0.042
Token
Token ID198
Feature activation-7.38e-02

Pos logit contributions
 poisonous+0.005
ocol+0.005
ocket+0.005
arter+0.005
affle+0.005
Neg logit contributions
Let-0.002
 So-0.002
ver-0.002
 nodded-0.002
 led-0.002
Token"
Token ID1
Feature activation+1.01e+00

Pos logit contributions
 poisonous+0.003
aster+0.003
ocket+0.003
ocol+0.003
 bamboo+0.003
Neg logit contributions
 acts-0.003
 youngest-0.003
ver-0.003
 oldest-0.003
bars-0.003
TokenCan
Token ID6090
Feature activation-3.33e+00

Pos logit contributions
ver+0.038
bars+0.038
 youngest+0.037
 acts+0.037
folk+0.036
Neg logit contributions
 poisonous-0.046
ocket-0.041
aster-0.041
ocol-0.040
 bamboo-0.038
Token we
Token ID356
Feature activation+5.67e+00

Pos logit contributions
 poisonous+0.179
aster+0.164
ocket+0.163
ocol+0.160
 bamboo+0.156
Neg logit contributions
 youngest-0.098
 acts-0.095
 nodded-0.093
ver-0.092
folk-0.092
Token play
Token ID711
Feature activation-4.02e+00

Pos logit contributions
ver+0.194
 youngest+0.193
 nodded+0.191
 led+0.188
 acts+0.186
Neg logit contributions
 poisonous-0.277
ocol-0.257
ocket-0.251
arter-0.245
aster-0.241
Token with
Token ID351
Feature activation+3.05e-02

Pos logit contributions
 poisonous+0.226
ocol+0.223
arter+0.222
ocket+0.204
eds+0.201
Neg logit contributions
's-0.115
 nodded-0.111
 nic-0.110
 led-0.107
Let-0.103
Token you
Token ID345
Feature activation+2.05e+00

Pos logit contributions
 acts+0.001
's+0.001
Let+0.001
 led+0.001
folk+0.001
Neg logit contributions
 poisonous-0.001
arter-0.001
ocket-0.001
affle-0.001
ocol-0.001
Token,
Token ID11
Feature activation-4.91e-02

Pos logit contributions
ver+0.067
 nodded+0.066
 led+0.061
's+0.061
 means+0.060
Neg logit contributions
 poisonous-0.106
ocol-0.105
ocket-0.099
arter-0.099
bones-0.096
Token bird
Token ID6512
Feature activation+1.68e+00

Pos logit contributions
 poisonous+0.003
ocol+0.002
ocket+0.002
aster+0.002
arter+0.002
Neg logit contributions
ver-0.001
 acts-0.001
 nodded-0.001
 youngest-0.001
Let-0.001
Token,
Token ID11
Feature activation+7.51e-02

Pos logit contributions
 nodded+0.071
ver+0.070
 youngest+0.069
 acts+0.068
 led+0.066
Neg logit contributions
 poisonous-0.117
ocket-0.109
ocol-0.107
aster-0.105
arter-0.103
Token Lily
Token ID20037
Feature activation-4.20e+00

Pos logit contributions
 nodded+0.002
 acts+0.002
ver+0.002
Let+0.002
 youngest+0.002
Neg logit contributions
 poisonous-0.004
ocol-0.004
ocket-0.004
aster-0.003
arter-0.003
Token,
Token ID11
Feature activation+8.47e-02

Pos logit contributions
 poisonous+0.163
ocket+0.142
ocol+0.138
aster+0.135
arter+0.135
Neg logit contributions
 youngest-0.187
bars-0.184
folk-0.183
 oldest-0.182
ver-0.181
Token we
Token ID356
Feature activation+5.65e+00

Pos logit contributions
 youngest+0.003
 acts+0.003
 nodded+0.003
ver+0.003
folk+0.003
Neg logit contributions
 poisonous-0.004
ocket-0.004
ocol-0.004
aster-0.004
arter-0.003
Token did
Token ID750
Feature activation-1.41e+00

Pos logit contributions
 acts+0.154
 youngest+0.153
ver+0.153
 nodded+0.152
folk+0.150
Neg logit contributions
 poisonous-0.311
ocket-0.288
ocol-0.288
aster-0.283
arter-0.278
Token it
Token ID340
Feature activation-7.17e-01

Pos logit contributions
 poisonous+0.065
ocket+0.063
ocol+0.061
arter+0.060
isk+0.059
Neg logit contributions
 So-0.052
 nodded-0.051
 neither-0.051
's-0.050
ver-0.050
Token!
Token ID0
Feature activation-1.08e+00

Pos logit contributions
 poisonous+0.022
ocol+0.019
ocket+0.019
aster+0.018
arter+0.017
Neg logit contributions
ver-0.037
 nodded-0.037
 acts-0.037
 youngest-0.037
Let-0.037
Token We
Token ID775
Feature activation+3.77e+00

Pos logit contributions
arter+0.041
ocol+0.040
 poisonous+0.039
aster+0.039
oof+0.038
Neg logit contributions
mun-0.044
 youngest-0.042
folk-0.042
 led-0.041
 nodded-0.041
Token are
Token ID389
Feature activation-5.37e-01

Pos logit contributions
bars+0.118
folk+0.116
 youngest+0.115
 acts+0.114
ver+0.112
Neg logit contributions
 poisonous-0.192
ocket-0.178
ocol-0.175
aster-0.174
arter-0.166
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
 poisonous+0.025
ocol+0.023
ocket+0.023
aster+0.022
arter+0.022
Neg logit contributions
 youngest-0.020
 oldest-0.020
 nodded-0.019
ver-0.019
 nic-0.019
Token best
Token ID1266
Feature activation+5.88e+00

Pos logit contributions
 acts+0.023
 nodded+0.022
ver+0.021
folk+0.021
 led+0.021
Neg logit contributions
 poisonous-0.069
aster-0.064
ocket-0.062
ocol-0.062
 bamboo-0.062
Token started
Token ID2067
Feature activation+3.20e+00

Pos logit contributions
 poisonous+0.118
ocket+0.108
aster+0.106
ez+0.099
eds+0.098
Neg logit contributions
folk-0.108
ver-0.105
 Und-0.104
bars-0.104
 quickest-0.103
Token playing
Token ID2712
Feature activation-2.55e+00

Pos logit contributions
 youngest+0.126
 acts+0.126
 nodded+0.125
Let+0.125
 led+0.123
Neg logit contributions
 poisonous-0.138
ocket-0.127
ocol-0.126
arter-0.120
aster-0.119
Token with
Token ID351
Feature activation+1.22e-01

Pos logit contributions
 poisonous+0.137
ocket+0.132
arter+0.131
ocol+0.130
 injuries+0.121
Neg logit contributions
Let-0.080
 led-0.079
 nodded-0.078
's-0.074
 acts-0.072
Token the
Token ID262
Feature activation+1.59e+00

Pos logit contributions
 youngest+0.004
 led+0.004
 acts+0.004
Let+0.004
 oldest+0.004
Neg logit contributions
 poisonous-0.006
ocket-0.006
arter-0.006
prise-0.006
alo-0.006
Token toy
Token ID13373
Feature activation-2.40e+00

Pos logit contributions
 youngest+0.060
 acts+0.059
Let+0.059
 nodded+0.058
 oldest+0.058
Neg logit contributions
 poisonous-0.071
ocol-0.066
ocket-0.066
aster-0.065
arter-0.063
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
 poisonous+0.111
ocol+0.103
ocket+0.101
aster+0.098
arter+0.097
Neg logit contributions
 youngest-0.087
 acts-0.087
ver-0.086
Let-0.086
 nodded-0.085
Token He
Token ID679
Feature activation-1.09e+00

Pos logit contributions
 youngest+0.008
Let+0.007
 nodded+0.007
 acts+0.007
ver+0.007
Neg logit contributions
 poisonous-0.015
ocket-0.014
ocol-0.014
aster-0.013
arter-0.013
Token loved
Token ID6151
Feature activation-1.77e+00

Pos logit contributions
 poisonous+0.048
ocket+0.044
aster+0.043
 bamboo+0.040
 brand+0.040
Neg logit contributions
folk-0.040
ver-0.038
bars-0.038
 acts-0.038
 Und-0.037
Token watching
Token ID4964
Feature activation+7.33e-01

Pos logit contributions
 poisonous+0.088
ocket+0.086
ocol+0.083
arter+0.082
prise+0.078
Neg logit contributions
Let-0.061
 led-0.058
 acts-0.056
 basics-0.055
 would-0.055
Token it
Token ID340
Feature activation-3.84e-01

Pos logit contributions
's+0.022
 acts+0.021
 youngest+0.021
 led+0.021
 means+0.020
Neg logit contributions
 poisonous-0.040
ocket-0.037
prise-0.036
arter-0.036
 injuries-0.035
Token print
Token ID3601
Feature activation+3.33e-01

Pos logit contributions
 poisonous+0.019
ocket+0.018
ocol+0.018
aster+0.017
 injuries+0.017
Neg logit contributions
 led-0.013
 acts-0.013
 youngest-0.013
 means-0.012
 nodded-0.012
Token so
Token ID523
Feature activation+3.56e-01

Pos logit contributions
 nodded+0.009
 acts+0.009
Let+0.009
 youngest+0.009
ver+0.009
Neg logit contributions
 poisonous-0.010
ocol-0.009
ocket-0.009
arter-0.009
aster-0.009
Token she
Token ID673
Feature activation+4.78e-01

Pos logit contributions
 nodded+0.011
Let+0.010
 led+0.010
ver+0.010
 youngest+0.010
Neg logit contributions
 poisonous-0.019
ocol-0.018
ocket-0.018
arter-0.018
aster-0.017
Token asked
Token ID1965
Feature activation+4.53e+00

Pos logit contributions
 acts+0.012
folk+0.012
ver+0.012
bars+0.011
sets+0.011
Neg logit contributions
 poisonous-0.028
ocket-0.025
aster-0.024
 bamboo-0.024
ocol-0.023
Token if
Token ID611
Feature activation+1.03e+00

Pos logit contributions
 nodded+0.197
ver+0.197
 acts+0.194
 led+0.193
Let+0.190
Neg logit contributions
 poisonous-0.184
ocol-0.168
arter-0.167
ocket-0.162
aster-0.156
Token she
Token ID673
Feature activation+4.78e-01

Pos logit contributions
 youngest+0.042
bars+0.040
 acts+0.040
folk+0.040
 eldest+0.040
Neg logit contributions
 poisonous-0.043
ocket-0.039
aster-0.039
ocol-0.037
 bamboo-0.036
Token could
Token ID714
Feature activation+7.06e-01

Pos logit contributions
folk+0.010
 youngest+0.010
 acts+0.010
mun+0.010
bars+0.010
Neg logit contributions
 poisonous-0.029
ocket-0.027
ocol-0.026
aster-0.026
arter-0.025
Token borrow
Token ID8804
Feature activation-3.93e+00

Pos logit contributions
ver+0.029
 nodded+0.027
 acts+0.027
 led+0.027
Let+0.027
Neg logit contributions
 poisonous-0.032
ocol-0.030
arter-0.028
ocket-0.028
 bamboo-0.027
Token it
Token ID340
Feature activation-4.56e-01

Pos logit contributions
arter+0.237
 poisonous+0.227
ocket+0.207
affle+0.206
ocol+0.206
Neg logit contributions
's-0.110
 means-0.108
 acts-0.105
 led-0.102
 So-0.099
Token.
Token ID13
Feature activation-1.91e-01

Pos logit contributions
 poisonous+0.024
ocol+0.024
arter+0.023
aster+0.023
ocket+0.022
Neg logit contributions
ver-0.014
 So-0.014
's-0.014
 led-0.014
 means-0.014
Token
Token ID220
Feature activation+3.58e+00

Pos logit contributions
aster+0.006
 poisonous+0.006
 heaven+0.005
 bamboo+0.005
ocket+0.005
Neg logit contributions
 acts-0.009
ver-0.009
 youngest-0.009
folk-0.008
 hardest-0.008
Token
Token ID198
Feature activation+6.48e-01

Pos logit contributions
 acts+0.137
 youngest+0.136
 nodded+0.133
 oldest+0.132
folk+0.131
Neg logit contributions
 poisonous-0.154
ocket-0.141
ocol-0.139
aster-0.138
arter-0.134
Token big
Token ID1263
Feature activation-3.10e+00

Pos logit contributions
ocol+0.019
aster+0.018
ocket+0.018
 poisonous+0.018
ez+0.018
Neg logit contributions
 youngest-0.011
 oldest-0.010
Let-0.010
 nodded-0.010
 led-0.010
Token brown
Token ID7586
Feature activation-1.28e+00

Pos logit contributions
 poisonous+0.163
ocket+0.159
ocol+0.153
aster+0.148
 injuries+0.148
Neg logit contributions
 acts-0.088
 nodded-0.085
 way-0.082
 led-0.081
 oldest-0.081
Token truck
Token ID7779
Feature activation+1.55e+00

Pos logit contributions
 poisonous+0.068
ocket+0.065
ocol+0.064
 injuries+0.062
bones+0.062
Neg logit contributions
 acts-0.035
 youngest-0.034
 boy-0.034
Let-0.034
 nodded-0.034
Token outside
Token ID2354
Feature activation-2.17e-01

Pos logit contributions
Let+0.062
 led+0.061
bars+0.060
 youngest+0.060
 nodded+0.060
Neg logit contributions
 poisonous-0.068
ocol-0.064
ocket-0.062
arter-0.058
aster-0.057
Token her
Token ID607
Feature activation-2.38e+00

Pos logit contributions
 poisonous+0.010
ocket+0.010
ocol+0.009
affle+0.009
arter+0.009
Neg logit contributions
Let-0.009
 led-0.008
 nodded-0.008
 acts-0.008
's-0.008
Token window
Token ID4324
Feature activation+2.22e-01

Pos logit contributions
 poisonous+0.127
ocol+0.124
ocket+0.116
aster+0.114
 bamboo+0.109
Neg logit contributions
 youngest-0.081
 oldest-0.075
 So-0.073
 eldest-0.073
bars-0.070
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
 nodded+0.009
 youngest+0.009
 acts+0.009
Let+0.009
ver+0.009
Neg logit contributions
 poisonous-0.009
ocol-0.008
ocket-0.008
aster-0.008
arter-0.008
Token
Token ID220
Feature activation+3.54e+00

Pos logit contributions
 poisonous+0.010
aster+0.009
ocket+0.009
 heaven+0.009
ocol+0.009
Neg logit contributions
 acts-0.011
ver-0.010
 youngest-0.010
folk-0.010
mun-0.010
Token
Token ID198
Feature activation+5.85e-01

Pos logit contributions
ver+0.110
 nodded+0.107
Let+0.106
 youngest+0.106
 acts+0.106
Neg logit contributions
 poisonous-0.184
ocol-0.170
ocket-0.169
aster-0.165
arter-0.163
Token
Token ID198
Feature activation+6.13e-01

Pos logit contributions
 acts+0.019
 youngest+0.019
 nodded+0.019
ver+0.019
folk+0.019
Neg logit contributions
 poisonous-0.029
ocket-0.026
ocol-0.026
aster-0.026
arter-0.025
TokenEm
Token ID10161
Feature activation-1.07e+00

Pos logit contributions
 nodded+0.022
ver+0.022
 youngest+0.022
 acts+0.022
Let+0.022
Neg logit contributions
 poisonous-0.028
ocol-0.026
ocket-0.026
aster-0.025
arter-0.025
Token runners
Token ID19323
Feature activation+6.43e+00

Pos logit contributions
 nodded+0.316
ver+0.312
 youngest+0.311
 eldest+0.307
 oldest+0.307
Neg logit contributions
 poisonous-0.175
aster-0.167
ocol-0.160
 bamboo-0.147
ocket-0.145
Token in
Token ID287
Feature activation+2.08e+00

Pos logit contributions
 youngest+0.305
 acts+0.304
 oldest+0.300
 nodded+0.298
Let+0.295
Neg logit contributions
 poisonous-0.207
ocket-0.188
aster-0.187
ocol-0.184
 bamboo-0.167
Token the
Token ID262
Feature activation+1.32e+00

Pos logit contributions
 acts+0.076
 youngest+0.075
ver+0.075
Let+0.074
folk+0.074
Neg logit contributions
 poisonous-0.098
ocket-0.090
ocol-0.088
arter-0.086
aster-0.083
Token world
Token ID995
Feature activation+2.47e-01

Pos logit contributions
ver+0.055
 nodded+0.050
 acts+0.049
bars+0.048
Let+0.048
Neg logit contributions
 poisonous-0.055
aster-0.051
 bamboo-0.047
ocol-0.047
 brand-0.045
Token!
Token ID0
Feature activation-5.03e-01

Pos logit contributions
 youngest+0.013
 acts+0.012
 oldest+0.012
 nodded+0.012
 eldest+0.012
Neg logit contributions
 poisonous-0.007
aster-0.006
ocket-0.006
ocol-0.006
 bamboo-0.006
Token Even
Token ID3412
Feature activation+1.36e+00

Pos logit contributions
 poisonous+0.025
ocol+0.024
ocket+0.023
aster+0.023
arter+0.023
Neg logit contributions
 acts-0.016
 nodded-0.016
 youngest-0.016
ver-0.015
Let-0.015
Token though
Token ID996
Feature activation+1.55e+00

Pos logit contributions
 acts+0.058
ver+0.058
 youngest+0.058
 nodded+0.058
Let+0.057
Neg logit contributions
 poisonous-0.053
ocol-0.047
aster-0.045
 bamboo-0.044
ocket-0.043
Token he
Token ID339
Feature activation+1.95e+00

Pos logit contributions
 youngest+0.059
 acts+0.059
 nodded+0.059
ver+0.059
Let+0.058
Neg logit contributions
 poisonous-0.068
ocol-0.062
aster-0.060
ocket-0.059
 bamboo-0.059
Token was
Token ID373
Feature activation+3.64e-01

Pos logit contributions
bars+0.058
 youngest+0.058
folk+0.057
 oldest+0.056
 eldest+0.055
Neg logit contributions
 poisonous-0.099
ocket-0.090
aster-0.088
ocol-0.087
ez-0.084
Token nervous
Token ID10927
Feature activation+3.69e+00

Pos logit contributions
 acts+0.016
bars+0.015
Let+0.015
 nodded+0.015
mun+0.015
Neg logit contributions
 poisonous-0.014
aster-0.012
ocol-0.012
ocket-0.011
 bamboo-0.011
Token,
Token ID11
Feature activation+1.25e-01

Pos logit contributions
Let+0.160
 youngest+0.157
 nic+0.155
 nodded+0.154
ver+0.154
Neg logit contributions
 poisonous-0.142
ocol-0.127
arter-0.123
aster-0.116
ocket-0.116
Token He
Token ID679
Feature activation-2.02e-01

Pos logit contributions
 acts+0.065
 youngest+0.064
ver+0.064
 nodded+0.062
 oldest+0.061
Neg logit contributions
 poisonous-0.095
ocol-0.089
aster-0.089
ocket-0.088
arter-0.086
Token was
Token ID373
Feature activation+1.24e+00

Pos logit contributions
 poisonous+0.011
ocket+0.010
aster+0.010
ocol+0.010
 bamboo+0.010
Neg logit contributions
ver-0.005
 youngest-0.005
folk-0.005
bars-0.005
 oldest-0.005
Token wearing
Token ID5762
Feature activation-2.66e+00

Pos logit contributions
 youngest+0.046
 nodded+0.045
 oldest+0.045
ver+0.043
Let+0.043
Neg logit contributions
 poisonous-0.056
ocol-0.054
ocket-0.053
arter-0.052
aster-0.051
Token a
Token ID257
Feature activation+1.85e-01

Pos logit contributions
 poisonous+0.119
arter+0.114
ocol+0.112
ocket+0.111
aster+0.107
Neg logit contributions
 nodded-0.102
 youngest-0.100
Let-0.098
 nic-0.097
 led-0.097
Token warm
Token ID5814
Feature activation-8.29e-01

Pos logit contributions
 nic+0.006
 nodded+0.006
 best+0.005
 way+0.005
 youngest+0.005
Neg logit contributions
ocol-0.010
isk-0.009
 poisonous-0.009
arter-0.009
ocket-0.009
Token coat
Token ID13209
Feature activation-3.06e+00

Pos logit contributions
 poisonous+0.040
ocol+0.038
ocket+0.037
arter+0.037
bones+0.035
Neg logit contributions
 nodded-0.031
 way-0.029
 led-0.028
 youngest-0.027
 nods-0.027
Token and
Token ID290
Feature activation-3.49e-01

Pos logit contributions
 poisonous+0.134
ocol+0.125
ocket+0.120
aster+0.118
arter+0.118
Neg logit contributions
ver-0.120
 nodded-0.119
 youngest-0.118
bars-0.117
Let-0.115
Token looked
Token ID3114
Feature activation+1.79e+00

Pos logit contributions
 poisonous+0.016
ocol+0.015
ocket+0.014
arter+0.014
aster+0.014
Neg logit contributions
 nodded-0.013
 led-0.013
Let-0.013
 youngest-0.013
 acts-0.013
Token very
Token ID845
Feature activation-3.64e+00

Pos logit contributions
 nodded+0.061
 youngest+0.060
 nic+0.058
 oldest+0.057
Let+0.056
Neg logit contributions
 poisonous-0.086
ocket-0.084
aster-0.084
arter-0.082
ocol-0.081
Token wise
Token ID10787
Feature activation+3.82e+00

Pos logit contributions
 poisonous+0.151
ocket+0.138
ocol+0.138
aster+0.135
arter+0.131
Neg logit contributions
 nodded-0.148
 youngest-0.147
 acts-0.146
ver-0.146
Let-0.143
Token.
Token ID13
Feature activation-5.02e-01

Pos logit contributions
ver+0.187
Let+0.184
 youngest+0.183
 nodded+0.183
mun+0.182
Neg logit contributions
 poisonous-0.125
ocket-0.110
ocol-0.106
 bamboo-0.101
arter-0.098
Token ran
Token ID4966
Feature activation+2.34e+00

Pos logit contributions
 poisonous+0.003
ocket+0.003
aster+0.003
 bamboo+0.003
ocol+0.003
Neg logit contributions
 youngest-0.002
ver-0.002
 acts-0.002
folk-0.002
mun-0.002
Token away
Token ID1497
Feature activation-2.65e+00

Pos logit contributions
 nodded+0.075
Let+0.073
 So+0.073
 youngest+0.073
 led+0.072
Neg logit contributions
 poisonous-0.123
ocol-0.123
arter-0.117
ocket-0.113
aster-0.110
Token.
Token ID13
Feature activation-5.29e-01

Pos logit contributions
 poisonous+0.108
ocol+0.100
ocket+0.099
aster+0.097
arter+0.094
Neg logit contributions
 nodded-0.110
 youngest-0.109
ver-0.109
 acts-0.108
 led-0.107
Token
Token ID220
Feature activation+3.70e+00

Pos logit contributions
 poisonous+0.022
aster+0.021
ocket+0.020
arter+0.020
ocol+0.020
Neg logit contributions
 acts-0.020
mun-0.020
 youngest-0.020
ver-0.019
folk-0.019
Token He
Token ID679
Feature activation-1.05e+00

Pos logit contributions
 acts+0.136
 youngest+0.134
 nodded+0.133
 oldest+0.130
folk+0.130
Neg logit contributions
 poisonous-0.166
ocol-0.152
ocket-0.151
aster-0.151
arter-0.147
Token had
Token ID550
Feature activation-1.68e+00

Pos logit contributions
 poisonous+0.055
ocket+0.051
 bamboo+0.048
aster+0.047
 injuries+0.045
Neg logit contributions
folk-0.031
ver-0.030
bars-0.030
 youngest-0.030
 acts-0.029
Token a
Token ID257
Feature activation-3.43e-01

Pos logit contributions
 poisonous+0.069
ocket+0.059
aster+0.057
 bamboo+0.055
ocol+0.055
Neg logit contributions
 acts-0.071
ver-0.071
folk-0.070
bars-0.070
mun-0.069
Token big
Token ID1263
Feature activation-3.04e+00

Pos logit contributions
 poisonous+0.014
ocol+0.014
ocket+0.013
arter+0.013
aster+0.013
Neg logit contributions
 nodded-0.014
 youngest-0.013
ver-0.013
 acts-0.013
Let-0.013
Token smile
Token ID8212
Feature activation-6.06e-01

Pos logit contributions
 poisonous+0.146
ocol+0.136
ocket+0.135
aster+0.130
arter+0.129
Neg logit contributions
 nodded-0.106
 acts-0.106
 youngest-0.103
ver-0.101
Let-0.100
Token on
Token ID319
Feature activation-1.04e+00

Pos logit contributions
 poisonous+0.027
ocol+0.026
ocket+0.024
arter+0.024
aster+0.023
Neg logit contributions
 nodded-0.024
ver-0.023
 led-0.023
 youngest-0.023
Let-0.023
Token his
Token ID465
Feature activation-5.03e-01

Pos logit contributions
 poisonous+0.054
prise+0.051
ocket+0.051
ocol+0.048
arter+0.048
Neg logit contributions
 nodded-0.033
 So-0.031
 acts-0.031
 youngest-0.030
Let-0.030
Token,
Token ID11
Feature activation-5.44e-02

Pos logit contributions
 poisonous+0.032
ocol+0.030
aster+0.030
 what+0.030
 bamboo+0.029
Neg logit contributions
folk-0.052
 youngest-0.052
bars-0.052
 nic-0.052
 oldest-0.052
Token they
Token ID484
Feature activation+4.43e+00

Pos logit contributions
 poisonous+0.003
aster+0.003
 bamboo+0.003
ocket+0.003
ocol+0.003
Neg logit contributions
 acts-0.002
folk-0.002
bars-0.001
 basics-0.001
 youngest-0.001
Token went
Token ID1816
Feature activation+2.30e-02

Pos logit contributions
bars+0.201
 acts+0.195
 hardest+0.192
 basics+0.191
sets+0.185
Neg logit contributions
 poisonous-0.169
ocket-0.152
aster-0.144
sm-0.135
 what-0.131
Token to
Token ID284
Feature activation-2.20e-01

Pos logit contributions
 led+0.001
Let+0.001
 nodded+0.001
ver+0.001
 youngest+0.001
Neg logit contributions
ocol-0.001
 poisonous-0.001
ocket-0.001
aster-0.001
arter-0.001
Token the
Token ID262
Feature activation+1.37e+00

Pos logit contributions
 poisonous+0.010
ocket+0.009
ocol+0.009
arter+0.009
aster+0.009
Neg logit contributions
 youngest-0.008
Let-0.008
 acts-0.008
 led-0.008
 nodded-0.008
Token park
Token ID3952
Feature activation-1.22e+00

Pos logit contributions
 youngest+0.044
Let+0.043
 oldest+0.043
 led+0.042
 nodded+0.041
Neg logit contributions
 poisonous-0.069
ocol-0.068
ocket-0.066
arter-0.064
aster-0.063
Token with
Token ID351
Feature activation-1.75e-01

Pos logit contributions
 poisonous+0.037
aster+0.033
ocket+0.031
 bamboo+0.031
 heaven+0.029
Neg logit contributions
folk-0.062
 acts-0.062
bars-0.061
 youngest-0.061
ver-0.060
Token their
Token ID511
Feature activation-5.98e-01

Pos logit contributions
 poisonous+0.008
ocol+0.008
ocket+0.008
aster+0.007
arter+0.007
Neg logit contributions
 youngest-0.006
 nodded-0.006
 acts-0.006
Let-0.006
ver-0.006
Token k
Token ID479
Feature activation+4.17e-01

Pos logit contributions
 poisonous+0.026
 bamboo+0.024
 injuries+0.023
ocol+0.021
ocket+0.021
Neg logit contributions
ver-0.024
 acts-0.022
folk-0.022
mun-0.022
bars-0.022
Tokenites
Token ID2737
Feature activation+5.96e+00

Pos logit contributions
 youngest+0.011
 nodded+0.011
 acts+0.011
ver+0.011
Let+0.010
Neg logit contributions
 poisonous-0.023
ocol-0.022
ocket-0.022
aster-0.021
arter-0.021
Token.
Token ID13
Feature activation-6.81e-01

Pos logit contributions
 acts+0.324
ver+0.316
Let+0.313
folk+0.313
 youngest+0.313
Neg logit contributions
 poisonous-0.150
 bamboo-0.128
ocket-0.127
aster-0.113
arter-0.112
Token cast
Token ID3350
Feature activation+5.92e-02

Pos logit contributions
bars+0.020
ver+0.019
folk+0.019
mun+0.019
sets+0.018
Neg logit contributions
 poisonous-0.032
ocket-0.031
aster-0.028
 bamboo-0.028
sm-0.027
Token her
Token ID607
Feature activation-2.31e+00

Pos logit contributions
ver+0.002
 nodded+0.002
 youngest+0.002
 acts+0.002
Let+0.002
Neg logit contributions
 poisonous-0.003
ocol-0.003
ocket-0.003
aster-0.003
arter-0.003
Token eyes
Token ID2951
Feature activation+4.14e-01

Pos logit contributions
 poisonous+0.118
ocol+0.108
ocket+0.108
aster+0.106
arter+0.104
Neg logit contributions
 acts-0.073
 youngest-0.073
 nodded-0.073
ver-0.073
Let-0.071
Token on
Token ID319
Feature activation-1.09e+00

Pos logit contributions
 acts+0.017
 youngest+0.016
ver+0.016
 nodded+0.016
folk+0.016
Neg logit contributions
 poisonous-0.018
ocket-0.016
ocol-0.016
aster-0.015
arter-0.015
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
 poisonous+0.053
ocol+0.051
arter+0.050
ocket+0.049
prise+0.048
Neg logit contributions
 led-0.038
Let-0.037
 youngest-0.037
 acts-0.037
 nodded-0.036
Token wreck
Token ID15228
Feature activation-2.23e+00

Pos logit contributions
 youngest+0.053
 acts+0.052
 nodded+0.052
ver+0.051
Let+0.051
Neg logit contributions
 poisonous-0.066
ocol-0.061
ocket-0.060
aster-0.059
arter-0.058
Token and
Token ID290
Feature activation-6.34e-02

Pos logit contributions
 poisonous+0.090
ocket+0.080
aster+0.079
ocol+0.078
arter+0.076
Neg logit contributions
 youngest-0.093
 acts-0.093
Let-0.092
ver-0.092
 nodded-0.091
Token wondered
Token ID14028
Feature activation+2.84e+00

Pos logit contributions
 poisonous+0.003
ocket+0.003
aster+0.003
ocol+0.003
 bamboo+0.003
Neg logit contributions
 acts-0.002
ver-0.002
 youngest-0.002
folk-0.002
bars-0.002
Token what
Token ID644
Feature activation-7.14e+00

Pos logit contributions
ver+0.176
 nodded+0.173
 acts+0.170
 youngest+0.170
 led+0.170
Neg logit contributions
 poisonous-0.062
ocol-0.053
aster-0.049
ocket-0.048
arter-0.047
Token it
Token ID340
Feature activation-5.12e-01

Pos logit contributions
 poisonous+0.240
ocket+0.203
aster+0.197
 what+0.191
sm+0.190
Neg logit contributions
 youngest-0.358
 eldest-0.351
ver-0.347
folk-0.346
bars-0.346
Token could
Token ID714
Feature activation+8.77e-01

Pos logit contributions
 poisonous+0.025
ocket+0.023
 what+0.022
 bamboo+0.021
sm+0.021
Neg logit contributions
folk-0.017
 youngest-0.017
bars-0.017
 eldest-0.016
mun-0.016
Token and
Token ID290
Feature activation-2.40e-01

Pos logit contributions
 poisonous+0.107
ocol+0.097
ocket+0.096
aster+0.094
arter+0.092
Neg logit contributions
 acts-0.114
ver-0.114
 nodded-0.114
 youngest-0.114
Let-0.112
Token dry
Token ID5894
Feature activation-1.37e+00

Pos logit contributions
 poisonous+0.009
aster+0.008
 injuries+0.007
 bamboo+0.007
ocket+0.007
Neg logit contributions
ver-0.011
folk-0.011
 youngest-0.011
 acts-0.011
bars-0.011
Token.
Token ID13
Feature activation-4.43e-01

Pos logit contributions
 poisonous+0.057
ocket+0.054
ocol+0.052
aster+0.051
arter+0.050
Neg logit contributions
 acts-0.055
 nodded-0.055
 youngest-0.055
Let-0.055
bars-0.054
Token
Token ID198
Feature activation+3.11e-01

Pos logit contributions
 poisonous+0.015
 bamboo+0.013
 brand+0.012
 what+0.012
arter+0.012
Neg logit contributions
bars-0.023
folk-0.022
 acts-0.021
 youngest-0.021
ver-0.021
Token
Token ID198
Feature activation+3.36e-01

Pos logit contributions
ver+0.009
Let+0.009
 nodded+0.009
 led+0.009
 youngest+0.009
Neg logit contributions
 poisonous-0.017
ocol-0.016
ocket-0.016
arter-0.015
aster-0.015
TokenAfter
Token ID3260
Feature activation-3.20e+00

Pos logit contributions
 acts+0.015
ver+0.015
 youngest+0.015
 nodded+0.015
bars+0.015
Neg logit contributions
 poisonous-0.013
ocol-0.011
ocket-0.011
aster-0.011
arter-0.011
Token the
Token ID262
Feature activation+1.19e+00

Pos logit contributions
ocket+0.172
 poisonous+0.164
ocol+0.163
arter+0.159
eds+0.152
Neg logit contributions
 led-0.104
Let-0.098
 neither-0.093
 nodded-0.092
 they-0.090
Token rain
Token ID6290
Feature activation+1.08e+00

Pos logit contributions
ver+0.068
bars+0.066
folk+0.064
 acts+0.062
 nodded+0.061
Neg logit contributions
 poisonous-0.039
 bamboo-0.032
 injuries-0.030
arter-0.028
aster-0.026
Token stopped
Token ID5025
Feature activation-5.72e-01

Pos logit contributions
bars+0.050
 acts+0.048
 nic+0.047
 youngest+0.047
 oldest+0.046
Neg logit contributions
 poisonous-0.042
 bamboo-0.034
isk-0.034
 injuries-0.033
aster-0.032
Token,
Token ID11
Feature activation+1.44e-01

Pos logit contributions
 poisonous+0.025
ocol+0.022
aster+0.021
arter+0.021
ocket+0.021
Neg logit contributions
 youngest-0.023
ver-0.023
 acts-0.023
 nodded-0.023
folk-0.023
Token Benny
Token ID44275
Feature activation-1.65e+00

Pos logit contributions
bars+0.008
 acts+0.008
folk+0.008
ver+0.007
 nodded+0.007
Neg logit contributions
 poisonous-0.005
aster-0.004
 bamboo-0.004
arter-0.003
ocol-0.003
Token Comfort
Token ID45769
Feature activation+4.55e-01

Pos logit contributions
 acts+0.005
 youngest+0.005
 oldest+0.005
mun+0.005
ver+0.005
Neg logit contributions
 poisonous-0.005
aster-0.005
ocket-0.005
ocol-0.005
arter-0.005
Tokenably
Token ID1346
Feature activation+5.98e-01

Pos logit contributions
 acts+0.013
 youngest+0.013
ver+0.013
 nodded+0.013
Let+0.013
Neg logit contributions
 poisonous-0.024
ocket-0.022
ocol-0.022
aster-0.022
arter-0.021
Token eating
Token ID6600
Feature activation-5.26e+00

Pos logit contributions
 acts+0.018
 youngest+0.018
ver+0.018
bars+0.018
Let+0.018
Neg logit contributions
 poisonous-0.031
ocket-0.028
ocol-0.028
aster-0.028
arter-0.027
Token his
Token ID465
Feature activation-5.03e-01

Pos logit contributions
 poisonous+0.243
arter+0.238
ocket+0.230
ocol+0.224
eds+0.215
Neg logit contributions
 nodded-0.191
 led-0.184
 acts-0.180
Let-0.179
ver-0.178
Token l
Token ID300
Feature activation-5.51e+00

Pos logit contributions
arter+0.022
 poisonous+0.021
ocol+0.020
aster+0.019
ores+0.019
Neg logit contributions
 nic-0.021
 acts-0.020
 youngest-0.020
 nodded-0.020
 oldest-0.020
Tokenoll
Token ID692
Feature activation-8.20e+00

Pos logit contributions
 poisonous+0.219
arter+0.204
 prank+0.187
aster+0.186
 heaven+0.186
Neg logit contributions
ver-0.262
bars-0.241
 nodded-0.240
 acts-0.212
 nic-0.211
Tokenipop
Token ID42800
Feature activation-4.85e+00

Pos logit contributions
 poisonous+0.357
arter+0.342
 heaven+0.329
aster+0.324
ocol+0.306
Neg logit contributions
ver-0.333
 nodded-0.322
bars-0.313
 acts-0.298
 led-0.284
Token,
Token ID11
Feature activation+4.19e-01

Pos logit contributions
 poisonous+0.225
ocol+0.216
arter+0.206
ocket+0.204
aster+0.202
Neg logit contributions
 nodded-0.177
ver-0.176
 youngest-0.170
 led-0.170
 acts-0.167
Token John
Token ID1757
Feature activation+1.61e+00

Pos logit contributions
 nodded+0.016
Let+0.015
 led+0.015
ver+0.015
 youngest+0.015
Neg logit contributions
 poisonous-0.019
ocol-0.018
ocket-0.018
arter-0.018
aster-0.017
Token happily
Token ID18177
Feature activation+1.18e+00

Pos logit contributions
 acts+0.043
 youngest+0.043
ver+0.043
 nodded+0.043
Let+0.042
Neg logit contributions
 poisonous-0.088
ocket-0.082
ocol-0.081
aster-0.080
arter-0.078
Token went
Token ID1816
Feature activation+2.87e-01

Pos logit contributions
 nodded+0.034
ver+0.034
 acts+0.034
 youngest+0.033
Let+0.033
Neg logit contributions
 poisonous-0.063
ocol-0.059
ocket-0.058
aster-0.057
arter-0.057
Token hole
Token ID7604
Feature activation-8.04e-01

Pos logit contributions
Let+0.051
 youngest+0.051
 acts+0.050
 led+0.050
 nodded+0.049
Neg logit contributions
 poisonous-0.061
ocol-0.060
ocket-0.059
aster-0.058
arter-0.056
Token.
Token ID13
Feature activation-1.31e-01

Pos logit contributions
 poisonous+0.029
ocket+0.025
ocol+0.025
aster+0.024
arter+0.024
Neg logit contributions
 acts-0.037
 youngest-0.037
 nodded-0.037
ver-0.037
Let-0.036
Token But
Token ID887
Feature activation+2.84e+00

Pos logit contributions
 poisonous+0.006
 bamboo+0.005
aster+0.005
ocol+0.005
ocket+0.005
Neg logit contributions
 acts-0.005
 youngest-0.004
ver-0.004
 oldest-0.004
 nodded-0.004
Token Spot
Token ID15899
Feature activation-2.28e+00

Pos logit contributions
 acts+0.114
 youngest+0.113
ver+0.112
 nodded+0.112
Let+0.110
Neg logit contributions
 poisonous-0.121
ocket-0.107
ocol-0.107
aster-0.106
arter-0.102
Token remembered
Token ID12086
Feature activation-5.69e-01

Pos logit contributions
 poisonous+0.122
ocket+0.107
aster+0.103
 bamboo+0.102
 injuries+0.101
Neg logit contributions
bars-0.072
folk-0.069
 acts-0.067
 youngest-0.067
 oldest-0.065
Token what
Token ID644
Feature activation-7.24e+00

Pos logit contributions
 poisonous+0.019
ocol+0.018
ocket+0.017
arter+0.017
aster+0.017
Neg logit contributions
 nodded-0.027
 acts-0.027
ver-0.027
 youngest-0.027
 led-0.027
Token the
Token ID262
Feature activation+1.39e+00

Pos logit contributions
 poisonous+0.237
ocket+0.190
aster+0.189
ocol+0.180
 bamboo+0.178
Neg logit contributions
folk-0.374
 youngest-0.371
bars-0.370
 acts-0.361
 eldest-0.361
Token family
Token ID1641
Feature activation+9.85e-01

Pos logit contributions
ver+0.066
folk+0.063
bars+0.062
mun+0.062
 nodded+0.060
Neg logit contributions
 poisonous-0.057
ocket-0.048
 bamboo-0.046
 injuries-0.046
arter-0.044
Token said
Token ID531
Feature activation+1.05e+00

Pos logit contributions
 youngest+0.034
 eldest+0.033
 Und+0.033
 oldest+0.032
bars+0.032
Neg logit contributions
 poisonous-0.047
ocket-0.044
aster-0.041
ocol-0.040
 what-0.039
Token and
Token ID290
Feature activation-1.42e-02

Pos logit contributions
 youngest+0.046
 oldest+0.045
 acts+0.045
ver+0.045
Let+0.044
Neg logit contributions
 poisonous-0.040
ocket-0.036
ocol-0.035
aster-0.034
arter-0.034
Token stayed
Token ID9658
Feature activation+1.54e+00

Pos logit contributions
 poisonous+0.001
ocket+0.001
aster+0.001
 what+0.001
 bamboo+0.001
Neg logit contributions
bars-0.000
ver-0.000
 youngest-0.000
folk-0.000
 oldest-0.000
Token.
Token ID13
Feature activation-3.18e-01

Pos logit contributions
 acts+0.041
 nodded+0.041
 So+0.041
ver+0.040
 means+0.040
Neg logit contributions
 poisonous-0.062
ocket-0.061
ocol-0.061
aster-0.058
arter-0.057
Token She
Token ID1375
Feature activation-2.96e+00

Pos logit contributions
 poisonous+0.014
ocket+0.013
ocol+0.013
aster+0.013
arter+0.012
Neg logit contributions
ver-0.012
mun-0.011
 acts-0.011
folk-0.011
 youngest-0.011
Token wanted
Token ID2227
Feature activation+5.53e-01

Pos logit contributions
 poisonous+0.181
ocket+0.167
ocol+0.165
aster+0.164
arter+0.160
Neg logit contributions
ver-0.064
folk-0.063
 acts-0.063
 youngest-0.063
bars-0.061
Token to
Token ID284
Feature activation-2.06e-01

Pos logit contributions
Let+0.018
 led+0.018
 acts+0.018
 youngest+0.017
 oldest+0.017
Neg logit contributions
 poisonous-0.027
ocol-0.027
ocket-0.026
arter-0.026
aster-0.024
Token know
Token ID760
Feature activation-3.41e+00

Pos logit contributions
 poisonous+0.010
ocol+0.010
ocket+0.009
arter+0.009
 bamboo+0.009
Neg logit contributions
 youngest-0.007
 nodded-0.007
 acts-0.007
 oldest-0.007
ver-0.007
Token what
Token ID644
Feature activation-7.25e+00

Pos logit contributions
 poisonous+0.090
ocol+0.078
ocket+0.077
arter+0.074
aster+0.073
Neg logit contributions
ver-0.191
 nodded-0.190
 acts-0.189
 led-0.187
 youngest-0.187
Token was
Token ID373
Feature activation+2.42e-01

Pos logit contributions
 poisonous+0.335
aster+0.299
ocket+0.293
sm+0.276
 bamboo+0.276
Neg logit contributions
folk-0.277
 youngest-0.276
bars-0.268
 eldest-0.265
ver-0.259
Token inside
Token ID2641
Feature activation-1.99e+00

Pos logit contributions
ver+0.010
 youngest+0.010
 led+0.010
 acts+0.010
 nodded+0.010
Neg logit contributions
 poisonous-0.009
ocol-0.009
aster-0.009
ocket-0.009
arter-0.008
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
 poisonous+0.096
ocket+0.089
ocol+0.088
arter+0.086
aster+0.085
Neg logit contributions
 acts-0.067
ver-0.066
 led-0.066
bars-0.065
 nodded-0.064
Token brain
Token ID3632
Feature activation+8.53e-01

Pos logit contributions
 nodded+0.061
ver+0.060
folk+0.057
mun+0.057
 acts+0.057
Neg logit contributions
 poisonous-0.063
ocket-0.057
ocol-0.055
aster-0.055
arter-0.054
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
 youngest+0.035
 nodded+0.034
 acts+0.034
Let+0.034
ver+0.034
Neg logit contributions
 poisonous-0.035
ocket-0.032
ocol-0.031
aster-0.031
arter-0.030
Token a
Token ID257
Feature activation-3.54e-01

Pos logit contributions
 youngest+0.195
ver+0.190
 nodded+0.189
 nic+0.187
 oldest+0.187
Neg logit contributions
 poisonous-0.355
ocket-0.355
ocol-0.346
arter-0.339
aster-0.332
Token good
Token ID922
Feature activation-1.68e+00

Pos logit contributions
ocol+0.016
ocket+0.016
 poisonous+0.015
arter+0.015
aster+0.015
Neg logit contributions
 youngest-0.013
Let-0.013
 oldest-0.013
 basics-0.013
 nodded-0.013
Token thing
Token ID1517
Feature activation-1.14e+00

Pos logit contributions
 poisonous+0.091
ocol+0.083
ocket+0.083
aster+0.082
arter+0.081
Neg logit contributions
ver-0.049
folk-0.048
 youngest-0.047
 nodded-0.047
bars-0.047
Token you
Token ID345
Feature activation+2.07e+00

Pos logit contributions
 poisonous+0.044
ocket+0.039
ocol+0.038
aster+0.037
arter+0.037
Neg logit contributions
 youngest-0.050
 acts-0.049
 nodded-0.049
ver-0.049
Let-0.049
Token know
Token ID760
Feature activation-3.39e+00

Pos logit contributions
ver+0.065
 acts+0.064
 youngest+0.064
 nodded+0.064
Let+0.063
Neg logit contributions
 poisonous-0.106
ocol-0.098
ocket-0.097
aster-0.095
arter-0.094
Token what
Token ID644
Feature activation-7.22e+00

Pos logit contributions
 poisonous+0.130
ocket+0.117
ocol+0.117
aster+0.113
arter+0.113
Neg logit contributions
ver-0.148
 nodded-0.147
 acts-0.147
 youngest-0.145
Let-0.144
Token you
Token ID345
Feature activation+2.08e+00

Pos logit contributions
 poisonous+0.286
aster+0.258
ocket+0.249
ocol+0.241
 heaven+0.229
Neg logit contributions
bars-0.317
 youngest-0.317
folk-0.315
ver-0.308
 eldest-0.306
Token want
Token ID765
Feature activation-1.80e+00

Pos logit contributions
bars+0.076
folk+0.074
 youngest+0.073
ver+0.073
 acts+0.072
Neg logit contributions
 poisonous-0.096
ocket-0.089
ocol-0.087
aster-0.086
arter-0.084
Token!
Token ID0
Feature activation-8.05e-01

Pos logit contributions
 poisonous+0.076
ocol+0.069
ocket+0.068
aster+0.067
arter+0.066
Neg logit contributions
 acts-0.072
ver-0.072
 nodded-0.072
 youngest-0.072
Let-0.071
Token Let
Token ID3914
Feature activation+4.51e+00

Pos logit contributions
ocol+0.027
aster+0.027
 poisonous+0.026
arter+0.025
ocket+0.025
Neg logit contributions
 youngest-0.035
 led-0.035
mun-0.035
folk-0.035
 nodded-0.034
Token's
Token ID338
Feature activation+6.88e+00

Pos logit contributions
bars+0.142
ver+0.137
folk+0.133
spe+0.119
 acts+0.115
Neg logit contributions
 poisonous-0.248
aster-0.230
 what-0.216
 heaven-0.211
 jam-0.210
Token Jack
Token ID3619
Feature activation+1.81e+00

Pos logit contributions
bars+0.009
 acts+0.008
folk+0.008
mun+0.008
 oldest+0.008
Neg logit contributions
 poisonous-0.007
 what-0.007
aster-0.006
ocket-0.006
 brand-0.006
Token said
Token ID531
Feature activation+1.16e+00

Pos logit contributions
bars+0.084
ver+0.082
folk+0.081
 hardest+0.081
 youngest+0.079
Neg logit contributions
 poisonous-0.066
ocket-0.057
aster-0.055
arter-0.051
 heaven-0.051
Token to
Token ID284
Feature activation-5.75e-02

Pos logit contributions
bars+0.055
 youngest+0.054
 acts+0.054
 oldest+0.053
mun+0.053
Neg logit contributions
 poisonous-0.041
ocket-0.036
aster-0.035
ocol-0.034
arter-0.033
Token Jill
Token ID22772
Feature activation+4.23e-01

Pos logit contributions
 poisonous+0.003
ocol+0.003
ocket+0.003
 bamboo+0.002
 injuries+0.002
Neg logit contributions
 youngest-0.002
Let-0.002
 nodded-0.002
 led-0.002
 oldest-0.002
Token "
Token ID366
Feature activation+2.58e+00

Pos logit contributions
 youngest+0.017
Let+0.017
 acts+0.016
 nodded+0.016
 oldest+0.016
Neg logit contributions
 poisonous-0.018
ocket-0.016
ocol-0.016
aster-0.016
arter-0.016
TokenWhat
Token ID2061
Feature activation-7.56e+00

Pos logit contributions
 acts+0.056
ver+0.055
 nodded+0.053
 youngest+0.053
bars+0.052
Neg logit contributions
 poisonous-0.155
ocket-0.145
aster-0.145
ocol-0.144
arter-0.139
Token shall
Token ID2236
Feature activation+1.76e+00

Pos logit contributions
 what+0.271
ocket+0.264
 poisonous+0.261
aster+0.248
sm+0.237
Neg logit contributions
folk-0.350
 youngest-0.332
bars-0.330
 eldest-0.330
lest-0.310
Token we
Token ID356
Feature activation+5.84e+00

Pos logit contributions
ver+0.064
mun+0.063
 nodded+0.062
 youngest+0.062
 acts+0.060
Neg logit contributions
 poisonous-0.077
aster-0.073
 what-0.072
ocol-0.071
arter-0.070
Token do
Token ID466
Feature activation-4.56e+00

Pos logit contributions
mun+0.273
bars+0.267
 nodded+0.265
folk+0.262
 acts+0.259
Neg logit contributions
 poisonous-0.195
aster-0.191
ocket-0.187
ocol-0.183
arter-0.179
Token today
Token ID1909
Feature activation-6.15e-01

Pos logit contributions
 poisonous+0.169
ocket+0.152
ocol+0.151
aster+0.150
arter+0.144
Neg logit contributions
 nodded-0.202
 youngest-0.201
 acts-0.200
bars-0.198
folk-0.197
Token?"
Token ID1701
Feature activation-8.99e-01

Pos logit contributions
 poisonous+0.021
aster+0.020
ocket+0.019
ocol+0.019
arter+0.019
Neg logit contributions
 acts-0.028
 nodded-0.028
ver-0.028
 youngest-0.028
folk-0.028