TOP ACTIVATIONS
MAX = 0.242

. Lily had a magn ifying glass that she found in
When Daisy put the magn ifying glass down , the cater
the necklace and the magn ifying glass and told him that
examine it with the magn ifying glass ?" "
cried , dropping the magn ifying glass . "
flashlight , and a magn ifying glass . As
She took out a magn ifying glass and looked very carefully
and handed him the magn ifying glass . He
. They had a magn ifying glass and a small box
borrowed her mom 's magn ifying glass to take a closer
She takes out a magn ifying glass . She looks at
He pointed his magn ifying glass at different classmates and
said , holding the magn ifying glass over a black ant
the watch with the magn ifying glass . He saw the
, handing him the magn ifying glass . She looked around
She had a big magn ifying glass that made things look
a flashlight and a magn ifying glass to examine their finds
it she had a magn ifying glass , a tiny torch
hat and grabbed her magn ifying glass . She was ready
He took out a magn ifying glass and a notebook and

MIN ACTIVATIONS
MIN = -0.251

idea . She suggested that Cro c should go for a
and Tom named his frog Cro aky . One
you sad , Mr . Cro cod ile ?" The crocod
is a silly story . Cro cod iles are not poor
" Hello , Mr . Cro cod ile ," said Lily
's wrong , Mr . Cro cod ile ?"
, we can 't . Cro cod iles are bad .
, we can 't . Cro cod iles are dangerous .
enjoy the cool water . Cro c thought it was a
in the cool water . Cro c enjoyed his swim so
That is not true . Cro cod iles can be poor
ing , and stretching . Cro cod iles do that sometimes
stood up for yourself and Cro co . You know what
and hugged her mom and Cro co . She felt happy
She had her mom and Cro co , and that was
it started to rain . Cle o got scared , so
sunshine . One day when Cle o was playing , it
monkey named Cle o . Cle o liked to play outside
and they both said " che ese !" at the same
she recognized the word " che ap " and said ,

INTERVAL 0.118 - 0.242
CONTAINS 4.281%

. It had a shiny thing in its be ak .
You can 't sell these things !" she says . "
The fog was very sp ooky , and it
S ally was very scared . She backed away
the children enjoyed them very much . After they

INTERVAL -0.005 - 0.118
CONTAINS 49.609%

but then she got a stern look on her face .
No , Max ! Don 't chase the bird . Ask
can make life more enjoyable . <|endoftext|> Once upon a time
thought about it . They realized that the lady was right
M ama got out the jar of jam and spread

INTERVAL -0.128 - -0.005
CONTAINS 43.014%

wished he could go in , but he knew that he
Molly was so excited ! She went over and
" Yes , please !" Jane showed Tim her jar ,
told her , " Thanks for flying the k ite with
. From that day on , everyone knew that the small

INTERVAL -0.251 - -0.128
CONTAINS 3.096%

gathering in her garden . Ab i smiled and said ,
" Maybe we can come back tomorrow and play again
with joy as the plane flew sharp in the sky .
eating his plants . He took a mighty can and sprayed
to draw pictures . She stepped outside and saw some beautiful
Token.
Token ID13
Feature activation+1.63e-03

Pos logit contributions
 ped+0.054
ena+0.053
ila+0.048
ases+0.047
okes+0.046
Neg logit contributions
 valuable-0.093
 may-0.084
 virtue-0.083
 must-0.080
 brightly-0.080
Token Lily
Token ID20037
Feature activation-9.46e-02

Pos logit contributions
 valuable+0.003
 virtue+0.003
 may+0.003
 must+0.002
 brightly+0.002
Neg logit contributions
ena-0.003
 ped-0.003
ila-0.003
okes-0.003
ases-0.003
Token had
Token ID550
Feature activation+3.23e-02

Pos logit contributions
ases+0.190
ila+0.187
 ped+0.187
ena+0.186
aster+0.183
Neg logit contributions
 valuable-0.152
 may-0.136
 must-0.135
 might-0.134
 brightly-0.116
Token a
Token ID257
Feature activation+3.09e-02

Pos logit contributions
 valuable+0.059
 may+0.053
 virtue+0.051
 must+0.049
 brightly+0.049
Neg logit contributions
 ped-0.061
ena-0.060
ila-0.056
ases-0.054
okes-0.053
Token magn
Token ID7842
Feature activation-1.06e-01

Pos logit contributions
 valuable+0.052
 virtue+0.050
umm+0.047
 may+0.046
idents+0.045
Neg logit contributions
 ped-0.054
ena-0.054
ila-0.052
 swinging-0.050
okes-0.045
Tokenifying
Token ID4035
Feature activation+2.42e-01

Pos logit contributions
 ped+0.298
ena+0.296
ila+0.284
ases+0.282
okes+0.280
Neg logit contributions
 valuable-0.096
 virtue-0.065
 may-0.065
 must-0.056
 might-0.056
Token glass
Token ID5405
Feature activation+5.95e-02

Pos logit contributions
 valuable+0.402
 may+0.339
 virtue+0.333
 must+0.319
 might+0.315
Neg logit contributions
 ped-0.470
ena-0.467
ila-0.454
ases-0.443
aster-0.432
Token that
Token ID326
Feature activation+1.17e-01

Pos logit contributions
 valuable+0.126
 may+0.112
 virtue+0.110
 brightly+0.106
 must+0.106
Neg logit contributions
ena-0.090
 ped-0.090
ila-0.086
ases-0.082
okes-0.080
Token she
Token ID673
Feature activation+2.58e-02

Pos logit contributions
 valuable+0.213
 virtue+0.184
 may+0.184
 must+0.176
 brightly+0.174
Neg logit contributions
 ped-0.214
ena-0.213
ila-0.204
ases-0.192
okes-0.191
Token found
Token ID1043
Feature activation-6.62e-02

Pos logit contributions
 valuable+0.046
 may+0.040
 must+0.039
 might+0.039
 virtue+0.038
Neg logit contributions
 ped-0.049
ena-0.048
ila-0.046
ases-0.045
okes-0.045
Token in
Token ID287
Feature activation-5.31e-02

Pos logit contributions
 ped+0.108
ena+0.105
ila+0.099
okes+0.097
ases+0.097
Neg logit contributions
 valuable-0.136
 may-0.122
 must-0.119
 might-0.117
 brightly-0.115
Token When
Token ID1649
Feature activation+1.22e-01

Pos logit contributions
 valuable+0.036
 may+0.031
 must+0.029
 might+0.029
 brightly+0.028
Neg logit contributions
 ped-0.060
ena-0.059
ila-0.056
ases-0.056
okes-0.055
Token Daisy
Token ID40355
Feature activation-5.47e-02

Pos logit contributions
 valuable+0.194
 may+0.171
 must+0.162
 might+0.158
 virtue+0.157
Neg logit contributions
 ped-0.251
ena-0.250
ila-0.237
ases-0.234
okes-0.231
Token put
Token ID1234
Feature activation-9.05e-02

Pos logit contributions
ena+0.104
 ped+0.101
ases+0.100
ila+0.095
okes+0.095
Neg logit contributions
 may-0.094
 must-0.091
 valuable-0.088
 might-0.088
 should-0.074
Token the
Token ID262
Feature activation+5.51e-03

Pos logit contributions
 ped+0.146
ena+0.144
ila+0.132
ases+0.132
okes+0.131
Neg logit contributions
 valuable-0.185
 may-0.169
 must-0.164
 might-0.162
 brightly-0.161
Token magn
Token ID7842
Feature activation-9.80e-02

Pos logit contributions
 valuable+0.010
 may+0.009
 virtue+0.009
 must+0.009
 might+0.008
Neg logit contributions
 ped-0.010
ena-0.010
ila-0.009
ases-0.009
 swinging-0.009
Tokenifying
Token ID4035
Feature activation+2.42e-01

Pos logit contributions
 ped+0.265
ena+0.262
ila+0.253
ases+0.251
okes+0.248
Neg logit contributions
 valuable-0.097
 may-0.070
 virtue-0.069
 might-0.062
 must-0.061
Token glass
Token ID5405
Feature activation+6.29e-02

Pos logit contributions
 valuable+0.441
 may+0.380
 virtue+0.370
 must+0.356
 might+0.354
Neg logit contributions
ena-0.433
 ped-0.432
ila-0.422
ases-0.410
aster-0.407
Token down
Token ID866
Feature activation-1.54e-02

Pos logit contributions
 valuable+0.137
 may+0.120
 virtue+0.120
 must+0.114
 fantastic+0.112
Neg logit contributions
 ped-0.092
ena-0.091
ila-0.089
ases-0.084
okes-0.083
Token,
Token ID11
Feature activation-2.79e-02

Pos logit contributions
 ped+0.024
ena+0.024
ila+0.023
ases+0.022
okes+0.021
Neg logit contributions
 valuable-0.032
 may-0.028
 virtue-0.028
 must-0.027
 might-0.027
Token the
Token ID262
Feature activation+2.64e-03

Pos logit contributions
 ped+0.048
ena+0.046
ila+0.045
 swinging+0.043
ases+0.041
Neg logit contributions
 valuable-0.054
 virtue-0.048
 may-0.047
 must-0.044
 brightly-0.044
Token cater
Token ID20825
Feature activation-8.16e-02

Pos logit contributions
 valuable+0.005
 may+0.004
 virtue+0.004
 must+0.004
 might+0.004
Neg logit contributions
ena-0.005
 ped-0.005
ila-0.005
ases-0.004
 swinging-0.004
Token the
Token ID262
Feature activation+2.09e-03

Pos logit contributions
 ped+0.129
ena+0.126
ila+0.118
ases+0.114
okes+0.114
Neg logit contributions
 valuable-0.154
 may-0.138
 must-0.133
 might-0.132
 brightly-0.127
Token necklace
Token ID38987
Feature activation-4.42e-03

Pos logit contributions
 valuable+0.004
 may+0.004
 virtue+0.004
 must+0.003
 brightly+0.003
Neg logit contributions
 ped-0.004
ena-0.003
ila-0.003
ases-0.003
okes-0.003
Token and
Token ID290
Feature activation-2.53e-02

Pos logit contributions
 ped+0.006
ena+0.006
ila+0.006
ases+0.006
okes+0.006
Neg logit contributions
 valuable-0.010
 may-0.009
 must-0.009
 might-0.009
 brightly-0.008
Token the
Token ID262
Feature activation+1.85e-03

Pos logit contributions
 ped+0.042
ases+0.042
ena+0.042
ogged+0.041
ila+0.040
Neg logit contributions
 valuable-0.046
 must-0.042
 may-0.042
 might-0.040
 brightly-0.038
Token magn
Token ID7842
Feature activation-1.03e-01

Pos logit contributions
 valuable+0.004
 may+0.003
 must+0.003
 virtue+0.003
 might+0.003
Neg logit contributions
 ped-0.003
ena-0.003
ila-0.003
ases-0.003
okes-0.003
Tokenifying
Token ID4035
Feature activation+2.42e-01

Pos logit contributions
 ped+0.285
ena+0.282
ila+0.272
ases+0.266
okes+0.264
Neg logit contributions
 valuable-0.093
 may-0.074
 must-0.067
 brightly-0.063
 might-0.063
Token glass
Token ID5405
Feature activation+6.17e-02

Pos logit contributions
 valuable+0.394
 may+0.344
 virtue+0.328
 must+0.320
 might+0.319
Neg logit contributions
 ped-0.475
ena-0.472
ila-0.459
ases-0.449
okes-0.437
Token and
Token ID290
Feature activation-2.57e-02

Pos logit contributions
 valuable+0.124
 may+0.111
 must+0.107
 virtue+0.105
 might+0.105
Neg logit contributions
 ped-0.103
ena-0.101
ila-0.095
ases-0.092
okes-0.091
Token told
Token ID1297
Feature activation-6.96e-02

Pos logit contributions
 ped+0.042
ena+0.041
ila+0.040
ases+0.040
ogged+0.039
Neg logit contributions
 valuable-0.050
 may-0.045
 must-0.044
 might-0.043
 brightly-0.042
Token him
Token ID683
Feature activation-7.71e-02

Pos logit contributions
 ped+0.108
ena+0.102
ases+0.094
ila+0.094
okes+0.093
Neg logit contributions
 valuable-0.151
 may-0.139
 must-0.131
 might-0.131
 brightly-0.129
Token that
Token ID326
Feature activation+1.22e-01

Pos logit contributions
 ped+0.142
ena+0.141
ila+0.134
ases+0.127
okes+0.127
Neg logit contributions
 valuable-0.138
 virtue-0.122
 may-0.121
 brightly-0.118
 must-0.115
Token examine
Token ID10716
Feature activation-8.07e-02

Pos logit contributions
 valuable+0.064
 may+0.057
 must+0.055
 virtue+0.055
 might+0.054
Neg logit contributions
 ped-0.046
ena-0.046
ila-0.043
ases-0.042
okes-0.041
Token it
Token ID340
Feature activation+8.58e-02

Pos logit contributions
 ped+0.158
ena+0.158
ila+0.153
ases+0.148
okes+0.147
Neg logit contributions
 valuable-0.135
 virtue-0.119
 may-0.113
 must-0.107
 daunting-0.106
Token with
Token ID351
Feature activation-2.69e-02

Pos logit contributions
 valuable+0.200
 may+0.179
 virtue+0.176
 must+0.172
 might+0.170
Neg logit contributions
 ped-0.115
ena-0.114
ila-0.106
ases-0.100
okes-0.099
Token the
Token ID262
Feature activation-9.15e-04

Pos logit contributions
 ped+0.046
ena+0.046
ila+0.044
ases+0.042
okes+0.041
Neg logit contributions
 valuable-0.052
 may-0.045
 virtue-0.045
 must-0.043
 might-0.042
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
ena+0.002
 ped+0.002
ila+0.002
 swinging+0.001
ases+0.001
Neg logit contributions
 valuable-0.002
 virtue-0.001
 may-0.001
 must-0.001
 brightly-0.001
Tokenifying
Token ID4035
Feature activation+2.41e-01

Pos logit contributions
 ped+0.286
ena+0.285
ila+0.276
ases+0.273
okes+0.271
Neg logit contributions
 valuable-0.099
 virtue-0.068
 may-0.068
 might-0.060
 must-0.059
Token glass
Token ID5405
Feature activation+6.01e-02

Pos logit contributions
 valuable+0.398
 may+0.339
 virtue+0.330
 must+0.317
 might+0.313
Neg logit contributions
ena-0.468
 ped-0.468
ila-0.462
ases-0.453
okes-0.440
Token?"
Token ID1701
Feature activation-3.60e-02

Pos logit contributions
 valuable+0.141
 may+0.126
 virtue+0.125
 fantastic+0.120
 brightly+0.120
Neg logit contributions
ena-0.077
ila-0.076
 ped-0.074
ases-0.071
okes-0.069
Token
Token ID198
Feature activation-3.42e-02

Pos logit contributions
ena+0.077
 ped+0.075
ases+0.073
ila+0.069
okes+0.068
Neg logit contributions
 valuable-0.056
 may-0.048
 must-0.047
 might-0.047
 brightly-0.045
Token
Token ID198
Feature activation-3.32e-02

Pos logit contributions
 ped+0.080
ena+0.078
ases+0.074
ila+0.072
okes+0.071
Neg logit contributions
 valuable-0.048
 may-0.040
 might-0.038
 must-0.038
 brightly-0.037
Token"
Token ID1
Feature activation+1.06e-02

Pos logit contributions
 ped+0.051
ena+0.050
ila+0.047
ases+0.046
okes+0.045
Neg logit contributions
 valuable-0.072
 may-0.064
 must-0.062
 virtue-0.062
 brightly-0.061
Token cried
Token ID16896
Feature activation-8.59e-02

Pos logit contributions
ases+0.167
ila+0.156
aster+0.154
ips+0.153
ogged+0.152
Neg logit contributions
 must-0.140
 valuable-0.138
 might-0.137
 may-0.127
 brightly-0.122
Token,
Token ID11
Feature activation-3.50e-02

Pos logit contributions
 ped+0.180
ena+0.179
ila+0.174
ases+0.171
okes+0.169
Neg logit contributions
 valuable-0.119
 brightly-0.116
 might-0.100
 must-0.098
 may-0.096
Token dropping
Token ID12047
Feature activation-2.97e-02

Pos logit contributions
ases+0.060
ila+0.059
ena+0.057
okes+0.056
ogged+0.055
Neg logit contributions
 valuable-0.063
 brightly-0.059
 must-0.058
 might-0.058
 may-0.057
Token the
Token ID262
Feature activation+2.62e-03

Pos logit contributions
 ped+0.046
ena+0.045
ila+0.042
okes+0.042
ases+0.040
Neg logit contributions
 valuable-0.063
 may-0.056
 brightly-0.055
 must-0.055
 might-0.055
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
 valuable+0.005
 virtue+0.004
 may+0.004
 brightly+0.004
 brand+0.004
Neg logit contributions
ila-0.004
ena-0.004
 ped-0.004
 swinging-0.004
ases-0.004
Tokenifying
Token ID4035
Feature activation+2.41e-01

Pos logit contributions
 ped+0.314
ena+0.311
ila+0.302
ases+0.296
okes+0.294
Neg logit contributions
 valuable-0.073
 may-0.051
 must-0.043
 virtue-0.042
 might-0.040
Token glass
Token ID5405
Feature activation+6.05e-02

Pos logit contributions
 valuable+0.393
 may+0.341
 virtue+0.323
 might+0.312
 must+0.311
Neg logit contributions
ena-0.487
 ped-0.483
ila-0.472
ases-0.461
okes-0.447
Token.
Token ID13
Feature activation+1.04e-02

Pos logit contributions
 valuable+0.127
 may+0.112
 virtue+0.109
 must+0.107
 brightly+0.106
Neg logit contributions
 ped-0.094
ena-0.093
ila-0.089
ases-0.086
okes-0.084
Token
Token ID198
Feature activation-2.77e-02

Pos logit contributions
 valuable+0.016
 may+0.013
 must+0.013
 virtue+0.013
 might+0.013
Neg logit contributions
 ped-0.022
ena-0.022
ila-0.021
ases-0.021
okes-0.020
Token
Token ID198
Feature activation-2.69e-02

Pos logit contributions
 ped+0.070
ena+0.067
ases+0.067
eks+0.063
ila+0.063
Neg logit contributions
 valuable-0.030
 may-0.024
 might-0.024
 must-0.022
 brightly-0.021
Token"
Token ID1
Feature activation+1.18e-02

Pos logit contributions
 ped+0.048
ena+0.046
ases+0.046
okes+0.044
ila+0.044
Neg logit contributions
 valuable-0.049
 may-0.042
 brightly-0.041
 virtue-0.041
 might-0.041
Token flashlight
Token ID38371
Feature activation+5.25e-02

Pos logit contributions
 valuable+0.062
 may+0.055
 virtue+0.054
 must+0.052
 might+0.052
Neg logit contributions
 ped-0.062
ena-0.061
ila-0.058
 swinging-0.056
okes-0.053
Token,
Token ID11
Feature activation-3.16e-02

Pos logit contributions
 valuable+0.107
 may+0.095
 virtue+0.093
 must+0.090
 brightly+0.090
Neg logit contributions
 ped-0.086
ena-0.084
ila-0.079
ases-0.076
okes-0.075
Token and
Token ID290
Feature activation-2.07e-02

Pos logit contributions
 ped+0.051
ena+0.050
ila+0.048
ases+0.046
okes+0.046
Neg logit contributions
 valuable-0.065
 may-0.058
 must-0.056
 might-0.055
 brightly-0.055
Token a
Token ID257
Feature activation+3.48e-02

Pos logit contributions
 ped+0.038
ena+0.037
ila+0.035
ases+0.034
okes+0.034
Neg logit contributions
 valuable-0.038
 may-0.034
 virtue-0.032
 must-0.032
 might-0.031
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
 valuable+0.063
 may+0.056
 virtue+0.055
 must+0.054
 might+0.053
Neg logit contributions
 ped-0.061
ena-0.058
ila-0.055
 swinging-0.055
ases-0.050
Tokenifying
Token ID4035
Feature activation+2.41e-01

Pos logit contributions
 ped+0.283
ena+0.281
ila+0.271
ases+0.266
okes+0.263
Neg logit contributions
 valuable-0.102
 may-0.080
 must-0.072
 virtue-0.071
 might-0.069
Token glass
Token ID5405
Feature activation+5.81e-02

Pos logit contributions
 valuable+0.436
 may+0.368
 virtue+0.364
 might+0.344
 must+0.341
Neg logit contributions
 ped-0.442
ena-0.429
ila-0.418
aster-0.413
ases-0.409
Token.
Token ID13
Feature activation+1.16e-02

Pos logit contributions
 valuable+0.123
 may+0.109
 virtue+0.107
 must+0.104
 might+0.102
Neg logit contributions
 ped-0.089
ena-0.088
ila-0.084
ases-0.081
okes-0.079
Token
Token ID198
Feature activation-2.28e-02

Pos logit contributions
 valuable+0.020
 may+0.017
 must+0.017
 brightly+0.016
 virtue+0.016
Neg logit contributions
 ped-0.023
ena-0.022
ila-0.021
ases-0.021
okes-0.021
Token
Token ID198
Feature activation-2.23e-02

Pos logit contributions
 ped+0.054
ena+0.051
ases+0.050
okes+0.049
 swinging+0.048
Neg logit contributions
 valuable-0.031
 may-0.025
 must-0.025
 might-0.024
 virtue-0.023
TokenAs
Token ID1722
Feature activation+1.04e-01

Pos logit contributions
 ped+0.042
ena+0.040
ases+0.040
okes+0.040
ila+0.038
Neg logit contributions
 valuable-0.040
 virtue-0.033
 may-0.033
 brightly-0.033
 must-0.032
Token She
Token ID1375
Feature activation+5.66e-02

Pos logit contributions
 valuable+0.025
 may+0.023
 virtue+0.022
 brightly+0.022
 fantastic+0.022
Neg logit contributions
 ped-0.021
ena-0.020
ila-0.019
okes-0.019
ases-0.019
Token took
Token ID1718
Feature activation-1.36e-01

Pos logit contributions
 valuable+0.109
 must+0.099
 may+0.098
 might+0.095
 brightly+0.088
Neg logit contributions
ena-0.096
ila-0.095
ases-0.093
 ped-0.093
okes-0.091
Token out
Token ID503
Feature activation-4.17e-02

Pos logit contributions
 ped+0.219
ena+0.215
ila+0.203
ases+0.197
okes+0.191
Neg logit contributions
 valuable-0.284
 may-0.254
 virtue-0.246
 must-0.242
 might-0.239
Token a
Token ID257
Feature activation+3.61e-02

Pos logit contributions
 ped+0.074
ena+0.073
ila+0.070
okes+0.070
ases+0.068
Neg logit contributions
 valuable-0.079
 brightly-0.067
 may-0.067
 must-0.066
 might-0.064
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
umm+0.055
 valuable+0.054
 virtue+0.053
idents+0.051
 may+0.048
Neg logit contributions
 ped-0.067
 swinging-0.062
ena-0.060
ila-0.059
aster-0.059
Tokenifying
Token ID4035
Feature activation+2.41e-01

Pos logit contributions
 ped+0.293
ena+0.290
ila+0.277
ases+0.275
okes+0.272
Neg logit contributions
 valuable-0.096
 may-0.068
 virtue-0.065
 might-0.059
 must-0.059
Token glass
Token ID5405
Feature activation+5.97e-02

Pos logit contributions
 valuable+0.399
 may+0.346
 virtue+0.332
 might+0.321
 must+0.314
Neg logit contributions
ena-0.469
 ped-0.467
ila-0.453
ases-0.441
aster-0.427
Token and
Token ID290
Feature activation-2.48e-02

Pos logit contributions
 valuable+0.138
 may+0.124
 virtue+0.122
 fantastic+0.118
 might+0.117
Neg logit contributions
 ped-0.078
ena-0.077
ila-0.074
ases-0.070
okes-0.067
Token looked
Token ID3114
Feature activation+9.11e-03

Pos logit contributions
 ped+0.039
ena+0.039
ila+0.037
ases+0.036
okes+0.035
Neg logit contributions
 valuable-0.052
 may-0.046
 must-0.045
 virtue-0.044
 might-0.044
Token very
Token ID845
Feature activation+1.39e-01

Pos logit contributions
 valuable+0.020
 virtue+0.019
 may+0.018
 might+0.017
 must+0.017
Neg logit contributions
 ped-0.013
ena-0.012
ila-0.011
 swinging-0.011
okes-0.011
Token carefully
Token ID7773
Feature activation-1.82e-02

Pos logit contributions
 valuable+0.222
 virtue+0.211
 may+0.206
 must+0.199
 might+0.190
Neg logit contributions
 ped-0.252
ila-0.248
ena-0.245
okes-0.238
 swinging-0.232
Token and
Token ID290
Feature activation-2.75e-02

Pos logit contributions
 valuable+0.060
 may+0.054
 virtue+0.053
 brightly+0.052
 must+0.051
Neg logit contributions
 ped-0.033
ena-0.033
ila-0.030
ases-0.028
okes-0.028
Token handed
Token ID10158
Feature activation-6.24e-02

Pos logit contributions
 ped+0.046
ena+0.045
ases+0.044
okes+0.043
ila+0.042
Neg logit contributions
 valuable-0.053
 may-0.047
 must-0.047
 might-0.044
 brightly-0.044
Token him
Token ID683
Feature activation-7.68e-02

Pos logit contributions
 ped+0.118
ena+0.108
okes+0.103
ases+0.102
 swinging+0.100
Neg logit contributions
 valuable-0.109
 may-0.107
 might-0.102
 must-0.100
 brightly-0.092
Token the
Token ID262
Feature activation+4.73e-03

Pos logit contributions
 ped+0.137
ena+0.135
ila+0.128
okes+0.123
ases+0.123
Neg logit contributions
 valuable-0.146
 may-0.128
 must-0.123
 might-0.123
 brightly-0.119
Token magn
Token ID7842
Feature activation-1.03e-01

Pos logit contributions
 valuable+0.009
 may+0.008
 virtue+0.008
 must+0.008
 brightly+0.008
Neg logit contributions
 ped-0.008
ena-0.008
ila-0.007
ases-0.007
okes-0.007
Tokenifying
Token ID4035
Feature activation+2.41e-01

Pos logit contributions
 ped+0.268
ena+0.266
ila+0.257
ases+0.253
okes+0.250
Neg logit contributions
 valuable-0.111
 may-0.084
 virtue-0.083
 must-0.076
 might-0.076
Token glass
Token ID5405
Feature activation+6.17e-02

Pos logit contributions
 valuable+0.389
 may+0.339
 virtue+0.325
 must+0.316
 might+0.315
Neg logit contributions
ena-0.473
 ped-0.471
ila-0.462
ases-0.451
okes-0.440
Token.
Token ID13
Feature activation+1.30e-02

Pos logit contributions
 valuable+0.130
 may+0.116
 virtue+0.113
 must+0.111
 might+0.110
Neg logit contributions
 ped-0.096
ena-0.094
ila-0.090
ases-0.087
okes-0.084
Token
Token ID198
Feature activation-2.34e-02

Pos logit contributions
 valuable+0.027
 may+0.024
 must+0.023
 might+0.023
 brightly+0.022
Neg logit contributions
 ped-0.021
ena-0.021
ila-0.019
ases-0.019
okes-0.018
Token
Token ID198
Feature activation-2.26e-02

Pos logit contributions
 ped+0.061
ena+0.058
ases+0.057
okes+0.055
 swinging+0.055
Neg logit contributions
 valuable-0.025
 may-0.021
 might-0.020
 must-0.018
 brightly-0.016
TokenHe
Token ID1544
Feature activation+4.10e-02

Pos logit contributions
 ped+0.032
ena+0.030
ases+0.028
okes+0.028
 swinging+0.027
Neg logit contributions
 valuable-0.051
 may-0.045
 brightly-0.044
 might-0.043
 virtue-0.043
Token.
Token ID13
Feature activation+1.32e-03

Pos logit contributions
 ped+0.019
ena+0.019
ila+0.018
ases+0.017
okes+0.017
Neg logit contributions
 valuable-0.022
 may-0.020
 must-0.019
 might-0.019
 brightly-0.019
Token They
Token ID1119
Feature activation+6.81e-02

Pos logit contributions
 valuable+0.002
 virtue+0.002
 may+0.002
 must+0.002
 brightly+0.002
Neg logit contributions
 ped-0.003
ena-0.003
ila-0.002
okes-0.002
ases-0.002
Token had
Token ID550
Feature activation+3.17e-02

Pos logit contributions
 valuable+0.092
 might+0.092
 may+0.090
 must+0.088
 brightly+0.079
Neg logit contributions
ases-0.146
okes-0.143
ena-0.141
 ped-0.140
ips-0.139
Token a
Token ID257
Feature activation+3.10e-02

Pos logit contributions
 valuable+0.060
 may+0.057
 virtue+0.056
umm+0.052
 must+0.051
Neg logit contributions
 ped-0.056
ena-0.055
ila-0.050
 swinging-0.050
ases-0.047
Token magn
Token ID7842
Feature activation-1.06e-01

Pos logit contributions
 valuable+0.039
 may+0.033
 virtue+0.033
 must+0.031
umm+0.030
Neg logit contributions
 ped-0.070
ena-0.069
ila-0.068
 swinging-0.067
okes-0.061
Tokenifying
Token ID4035
Feature activation+2.40e-01

Pos logit contributions
 ped+0.303
ena+0.301
ila+0.291
ases+0.287
okes+0.284
Neg logit contributions
 valuable-0.089
 may-0.061
 virtue-0.058
 must-0.052
 might-0.051
Token glass
Token ID5405
Feature activation+5.84e-02

Pos logit contributions
 valuable+0.418
 may+0.355
 virtue+0.345
 must+0.333
 might+0.326
Neg logit contributions
 ped-0.448
ena-0.446
ila-0.439
ases-0.429
 swinging-0.418
Token and
Token ID290
Feature activation-3.10e-02

Pos logit contributions
 valuable+0.118
 may+0.105
 virtue+0.102
 must+0.099
 brightly+0.098
Neg logit contributions
ena-0.094
 ped-0.094
ila-0.091
ases-0.087
okes-0.084
Token a
Token ID257
Feature activation+3.15e-02

Pos logit contributions
 ped+0.055
ena+0.055
ila+0.051
ases+0.049
okes+0.048
Neg logit contributions
 valuable-0.059
 may-0.052
 virtue-0.052
 must-0.049
 might-0.048
Token small
Token ID1402
Feature activation+6.60e-02

Pos logit contributions
 valuable+0.056
 virtue+0.051
 may+0.050
 must+0.049
 daunting+0.047
Neg logit contributions
 ped-0.052
ena-0.051
ila-0.050
 swinging-0.050
okes-0.044
Token box
Token ID3091
Feature activation+6.92e-02

Pos logit contributions
 valuable+0.125
 may+0.108
 virtue+0.107
 must+0.104
 daunting+0.101
Neg logit contributions
 ped-0.111
ena-0.107
 swinging-0.103
ila-0.103
ases-0.098
Token borrowed
Token ID22546
Feature activation-9.20e-02

Pos logit contributions
 valuable+0.089
 may+0.077
 must+0.074
 might+0.073
 brightly+0.072
Neg logit contributions
ena-0.106
 ped-0.106
ila-0.102
ases-0.102
okes-0.099
Token her
Token ID607
Feature activation-8.17e-02

Pos logit contributions
 ped+0.132
ena+0.129
ila+0.123
ases+0.119
 swinging+0.118
Neg logit contributions
 valuable-0.196
 virtue-0.181
 may-0.179
 must-0.169
 might-0.168
Token mom
Token ID1995
Feature activation-1.06e-01

Pos logit contributions
 ped+0.138
ena+0.133
 swinging+0.132
ila+0.125
okes+0.122
Neg logit contributions
 valuable-0.143
 virtue-0.131
 may-0.127
 brightly-0.126
 daunting-0.126
Token's
Token ID338
Feature activation-9.84e-04

Pos logit contributions
 ped+0.137
ena+0.132
ila+0.124
ases+0.120
okes+0.117
Neg logit contributions
 valuable-0.253
 may-0.230
 must-0.224
 might-0.221
 virtue-0.220
Token magn
Token ID7842
Feature activation-1.04e-01

Pos logit contributions
 ped+0.002
ena+0.002
 swinging+0.001
ases+0.001
ila+0.001
Neg logit contributions
 valuable-0.002
 may-0.002
 virtue-0.002
 daunting-0.002
 brightly-0.002
Tokenifying
Token ID4035
Feature activation+2.40e-01

Pos logit contributions
 ped+0.290
ena+0.286
ila+0.275
ases+0.273
okes+0.271
Neg logit contributions
 valuable-0.093
 may-0.066
 virtue-0.063
 must-0.057
 might-0.056
Token glass
Token ID5405
Feature activation+6.09e-02

Pos logit contributions
 valuable+0.388
 may+0.336
 virtue+0.323
 might+0.311
 must+0.311
Neg logit contributions
 ped-0.474
ena-0.469
ila-0.457
ases-0.449
okes-0.442
Token to
Token ID284
Feature activation-5.93e-02

Pos logit contributions
 valuable+0.134
 may+0.119
 virtue+0.118
 fantastic+0.114
 brightly+0.113
Neg logit contributions
 ped-0.086
ena-0.085
ila-0.082
ases-0.079
okes-0.077
Token take
Token ID1011
Feature activation-1.24e-01

Pos logit contributions
 ped+0.102
ena+0.100
ila+0.093
okes+0.092
ases+0.091
Neg logit contributions
 valuable-0.118
 may-0.108
 must-0.104
 might-0.103
 brightly-0.100
Token a
Token ID257
Feature activation+3.55e-02

Pos logit contributions
 ped+0.168
ena+0.165
ila+0.153
ases+0.149
okes+0.143
Neg logit contributions
 valuable-0.288
 may-0.261
 virtue-0.253
 must-0.250
 might-0.248
Token closer
Token ID5699
Feature activation+3.37e-02

Pos logit contributions
 valuable+0.070
 virtue+0.068
umm+0.065
 brightly+0.063
 may+0.062
Neg logit contributions
 ped-0.049
 swinging-0.046
ila-0.044
aster-0.043
ena-0.043
Token She
Token ID1375
Feature activation+5.06e-02

Pos logit contributions
 ped+0.001
ena+0.001
ila+0.001
ases+0.001
okes+0.001
Neg logit contributions
 valuable-0.000
 may-0.000
 must-0.000
 might-0.000
 brightly-0.000
Token takes
Token ID2753
Feature activation-1.18e-01

Pos logit contributions
 valuable+0.094
 may+0.092
 must+0.088
 might+0.086
 virtue+0.076
Neg logit contributions
ena-0.086
 ped-0.085
ila-0.083
aster-0.081
ases-0.079
Token out
Token ID503
Feature activation-4.36e-02

Pos logit contributions
 ped+0.233
ena+0.223
okes+0.220
ila+0.218
 swinging+0.211
Neg logit contributions
 valuable-0.188
 must-0.165
 brightly-0.161
 may-0.160
 biggest-0.159
Token a
Token ID257
Feature activation+3.38e-02

Pos logit contributions
 ped+0.086
okes+0.084
ena+0.083
ases+0.082
ila+0.080
Neg logit contributions
 valuable-0.071
 brightly-0.060
 must-0.058
 may-0.057
 might-0.056
Token magn
Token ID7842
Feature activation-1.07e-01

Pos logit contributions
 valuable+0.057
 virtue+0.053
 may+0.050
umm+0.049
idents+0.049
Neg logit contributions
 ped-0.060
ena-0.057
ila-0.056
 swinging-0.055
aster-0.054
Tokenifying
Token ID4035
Feature activation+2.40e-01

Pos logit contributions
 ped+0.302
ena+0.299
ila+0.289
ases+0.284
okes+0.281
Neg logit contributions
 valuable-0.093
 may-0.069
 virtue-0.061
 must-0.061
 might-0.058
Token glass
Token ID5405
Feature activation+6.10e-02

Pos logit contributions
 valuable+0.411
 may+0.359
 virtue+0.340
 might+0.333
 must+0.329
Neg logit contributions
ena-0.456
 ped-0.455
ila-0.439
ases-0.429
aster-0.421
Token.
Token ID13
Feature activation-2.22e-03

Pos logit contributions
 valuable+0.130
 may+0.116
 virtue+0.113
 must+0.110
 might+0.109
Neg logit contributions
 ped-0.094
ena-0.093
ila-0.089
ases-0.085
okes-0.083
Token She
Token ID1375
Feature activation+4.64e-02

Pos logit contributions
 ped+0.005
ena+0.005
ila+0.005
ases+0.005
okes+0.005
Neg logit contributions
 valuable-0.003
 may-0.003
 must-0.002
 might-0.002
 brightly-0.002
Token looks
Token ID3073
Feature activation+4.08e-02

Pos logit contributions
 valuable+0.089
 may+0.084
 must+0.081
 might+0.080
 brightly+0.072
Neg logit contributions
 ped-0.078
ena-0.077
ila-0.075
ases-0.072
ogged-0.071
Token at
Token ID379
Feature activation-7.05e-02

Pos logit contributions
 valuable+0.094
 may+0.086
 virtue+0.086
 must+0.082
 might+0.082
Neg logit contributions
 ped-0.054
ena-0.052
ila-0.049
okes-0.046
ases-0.046
Token
Token ID198
Feature activation-2.78e-02

Pos logit contributions
 ped+0.066
ena+0.063
ases+0.061
okes+0.061
ila+0.061
Neg logit contributions
 valuable-0.041
 may-0.034
 must-0.033
 might-0.033
 virtue-0.031
TokenHe
Token ID1544
Feature activation+3.30e-02

Pos logit contributions
 ped+0.044
ena+0.042
ila+0.040
ases+0.039
okes+0.039
Neg logit contributions
 valuable-0.059
 may-0.052
 must-0.051
 virtue-0.050
 might-0.050
Token pointed
Token ID6235
Feature activation-7.31e-02

Pos logit contributions
 valuable+0.055
 must+0.054
 may+0.050
 might+0.049
 brightly+0.049
Neg logit contributions
ases-0.065
ips-0.061
ags-0.059
okes-0.059
packs-0.059
Token his
Token ID465
Feature activation-6.75e-02

Pos logit contributions
 ped+0.122
ena+0.121
ila+0.115
ases+0.110
okes+0.108
Neg logit contributions
 valuable-0.147
 may-0.132
 must-0.127
 brightly-0.126
 might-0.125
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
ena+0.113
 ped+0.111
ila+0.106
okes+0.100
ases+0.100
Neg logit contributions
 valuable-0.133
 virtue-0.118
 may-0.115
 brightly-0.113
 must-0.111
Tokenifying
Token ID4035
Feature activation+2.40e-01

Pos logit contributions
 ped+0.306
ena+0.303
ila+0.292
ases+0.289
okes+0.286
Neg logit contributions
 valuable-0.083
 may-0.057
 virtue-0.052
 must-0.049
 might-0.047
Token glass
Token ID5405
Feature activation+5.95e-02

Pos logit contributions
 valuable+0.378
 may+0.326
 virtue+0.310
 must+0.305
 might+0.302
Neg logit contributions
 ped-0.497
ena-0.494
ila-0.476
ases-0.465
okes-0.458
Token at
Token ID379
Feature activation-6.12e-02

Pos logit contributions
 valuable+0.128
 may+0.114
 virtue+0.111
 must+0.109
 might+0.108
Neg logit contributions
 ped-0.091
ena-0.089
ila-0.084
ases-0.081
okes-0.080
Token different
Token ID1180
Feature activation+1.44e-01

Pos logit contributions
 ped+0.092
ena+0.089
ila+0.084
okes+0.081
ases+0.081
Neg logit contributions
 valuable-0.133
 may-0.121
 must-0.117
 might-0.116
 brightly-0.115
Token classmates
Token ID28999
Feature activation-4.14e-02

Pos logit contributions
 valuable+0.240
 may+0.207
 virtue+0.207
 must+0.190
 brightly+0.188
Neg logit contributions
ena-0.286
 ped-0.279
ila-0.263
ases-0.262
okes-0.255
Token and
Token ID290
Feature activation-2.36e-02

Pos logit contributions
 ped+0.064
ena+0.062
ila+0.060
ases+0.057
okes+0.056
Neg logit contributions
 valuable-0.088
 may-0.080
 must-0.077
 might-0.076
 virtue-0.075
Token said
Token ID531
Feature activation-1.18e-01

Pos logit contributions
 ped+0.165
ases+0.164
ila+0.161
ena+0.160
aster+0.154
Neg logit contributions
 valuable-0.163
 must-0.145
 might-0.143
 may-0.143
 brightly-0.132
Token,
Token ID11
Feature activation-3.67e-02

Pos logit contributions
 ped+0.235
ena+0.234
ila+0.234
ases+0.229
okes+0.220
Neg logit contributions
 valuable-0.184
 may-0.159
 brightly-0.156
 might-0.155
 must-0.155
Token holding
Token ID4769
Feature activation-1.17e-01

Pos logit contributions
ases+0.066
ila+0.066
okes+0.062
ena+0.061
ogged+0.060
Neg logit contributions
 valuable-0.064
 brightly-0.060
 must-0.056
 may-0.055
 brand-0.055
Token the
Token ID262
Feature activation-4.36e-03

Pos logit contributions
 ped+0.234
ena+0.230
ila+0.228
okes+0.221
ases+0.220
Neg logit contributions
 valuable-0.182
 brightly-0.159
 must-0.159
 may-0.158
 might-0.156
Token magn
Token ID7842
Feature activation-1.07e-01

Pos logit contributions
ena+0.007
ila+0.007
 ped+0.006
 swinging+0.006
ases+0.006
Neg logit contributions
 valuable-0.009
 virtue-0.008
 may-0.008
 brightly-0.007
 daunting-0.007
Tokenifying
Token ID4035
Feature activation+2.40e-01

Pos logit contributions
 ped+0.316
ena+0.313
ila+0.304
ases+0.298
okes+0.296
Neg logit contributions
 valuable-0.077
 may-0.054
 must-0.047
 virtue-0.046
 might-0.044
Token glass
Token ID5405
Feature activation+5.83e-02

Pos logit contributions
 valuable+0.386
 may+0.335
 virtue+0.319
 must+0.310
 might+0.309
Neg logit contributions
ena-0.481
 ped-0.479
ila-0.468
ases-0.458
okes-0.446
Token over
Token ID625
Feature activation-7.13e-02

Pos logit contributions
 valuable+0.124
 may+0.112
 virtue+0.108
 must+0.106
 might+0.105
Neg logit contributions
 ped-0.089
ena-0.088
ila-0.083
ases-0.080
okes-0.078
Token a
Token ID257
Feature activation+3.26e-02

Pos logit contributions
 ped+0.117
okes+0.116
ena+0.114
ases+0.107
ila+0.105
Neg logit contributions
 valuable-0.131
 brightly-0.130
 might-0.122
 may-0.119
 must-0.118
Token black
Token ID2042
Feature activation+5.10e-03

Pos logit contributions
 valuable+0.060
 virtue+0.056
idents+0.056
umm+0.054
 may+0.054
Neg logit contributions
 ped-0.048
ena-0.047
 swinging-0.046
ila-0.046
aster-0.044
Token ant
Token ID1885
Feature activation-2.78e-02

Pos logit contributions
 valuable+0.008
 may+0.007
 must+0.007
 virtue+0.007
 might+0.007
Neg logit contributions
 ped-0.011
ena-0.010
ila-0.010
ases-0.010
okes-0.010
Token the
Token ID262
Feature activation-5.60e-04

Pos logit contributions
 ped+0.101
ena+0.098
ila+0.090
okes+0.090
ases+0.088
Neg logit contributions
 valuable-0.141
 may-0.128
 might-0.124
 must-0.124
 brightly-0.122
Token watch
Token ID2342
Feature activation-2.22e-02

Pos logit contributions
ena+0.001
 ped+0.001
ila+0.001
 swinging+0.001
ases+0.001
Neg logit contributions
 valuable-0.001
 may-0.001
 virtue-0.001
 must-0.001
 might-0.001
Token with
Token ID351
Feature activation-2.71e-02

Pos logit contributions
 ped+0.038
ena+0.036
ila+0.035
ases+0.035
okes+0.034
Neg logit contributions
 valuable-0.043
 may-0.039
 must-0.038
 might-0.037
 brightly-0.037
Token the
Token ID262
Feature activation-9.10e-04

Pos logit contributions
 ped+0.045
ena+0.045
ila+0.042
ases+0.041
okes+0.040
Neg logit contributions
 valuable-0.055
 may-0.049
 virtue-0.047
 must-0.047
 might-0.046
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
ena+0.002
 ped+0.002
ila+0.002
ases+0.001
 swinging+0.001
Neg logit contributions
 valuable-0.002
 may-0.001
 virtue-0.001
 must-0.001
 brightly-0.001
Tokenifying
Token ID4035
Feature activation+2.40e-01

Pos logit contributions
 ped+0.308
ena+0.305
ila+0.296
ases+0.290
okes+0.288
Neg logit contributions
 valuable-0.078
 may-0.055
 must-0.048
 virtue-0.047
 might-0.045
Token glass
Token ID5405
Feature activation+5.95e-02

Pos logit contributions
 valuable+0.395
 may+0.339
 virtue+0.327
 must+0.314
 might+0.313
Neg logit contributions
ena-0.474
 ped-0.472
ila-0.462
ases-0.452
okes-0.441
Token.
Token ID13
Feature activation+2.02e-03

Pos logit contributions
 valuable+0.124
 may+0.110
 virtue+0.107
 must+0.105
 brightly+0.104
Neg logit contributions
 ped-0.094
ena-0.093
ila-0.089
ases-0.085
okes-0.083
Token He
Token ID679
Feature activation+4.75e-02

Pos logit contributions
 valuable+0.003
 may+0.002
 virtue+0.002
 must+0.002
 might+0.002
Neg logit contributions
 ped-0.005
ena-0.004
ila-0.004
okes-0.004
ases-0.004
Token saw
Token ID2497
Feature activation-5.89e-02

Pos logit contributions
 valuable+0.083
 may+0.077
 might+0.075
 must+0.075
 brightly+0.071
Neg logit contributions
ases-0.088
 ped-0.086
ena-0.086
ila-0.083
okes-0.081
Token the
Token ID262
Feature activation-5.72e-04

Pos logit contributions
 ped+0.099
ena+0.099
ila+0.094
ases+0.090
 swinging+0.089
Neg logit contributions
 valuable-0.118
 may-0.107
 virtue-0.106
 must-0.101
 might-0.098
Token,
Token ID11
Feature activation-3.81e-02

Pos logit contributions
 ped+0.216
ena+0.213
ila+0.202
ases+0.197
okes+0.193
Neg logit contributions
 valuable-0.250
 may-0.224
 must-0.213
 might-0.212
 virtue-0.211
Token handing
Token ID22786
Feature activation-6.97e-02

Pos logit contributions
ena+0.091
 ped+0.090
ases+0.090
ila+0.089
okes+0.087
Neg logit contributions
 valuable-0.046
 may-0.040
 must-0.037
 might-0.036
 brightly-0.036
Token him
Token ID683
Feature activation-8.17e-02

Pos logit contributions
 ped+0.108
ena+0.104
ila+0.098
okes+0.097
ases+0.094
Neg logit contributions
 valuable-0.142
 may-0.134
 might-0.131
 must-0.131
 brightly-0.127
Token the
Token ID262
Feature activation-3.54e-03

Pos logit contributions
 ped+0.140
ena+0.135
ila+0.129
okes+0.125
ases+0.124
Neg logit contributions
 valuable-0.160
 may-0.144
 might-0.139
 must-0.138
 brightly-0.133
Token magn
Token ID7842
Feature activation-1.04e-01

Pos logit contributions
 ped+0.006
ena+0.006
ila+0.006
ases+0.006
okes+0.006
Neg logit contributions
 valuable-0.007
 may-0.006
 virtue-0.006
 must-0.006
 might-0.006
Tokenifying
Token ID4035
Feature activation+2.40e-01

Pos logit contributions
 ped+0.296
ena+0.295
ila+0.284
ases+0.281
okes+0.278
Neg logit contributions
 valuable-0.089
 may-0.060
 virtue-0.058
 must-0.052
 might-0.051
Token glass
Token ID5405
Feature activation+5.84e-02

Pos logit contributions
 valuable+0.397
 may+0.344
 virtue+0.330
 must+0.321
 might+0.319
Neg logit contributions
ena-0.467
 ped-0.464
ila-0.454
ases-0.445
okes-0.437
Token.
Token ID13
Feature activation-4.69e-04

Pos logit contributions
 valuable+0.119
 may+0.107
 must+0.102
 virtue+0.102
 might+0.101
Neg logit contributions
 ped-0.095
ena-0.094
ila-0.088
ases-0.085
okes-0.084
Token She
Token ID1375
Feature activation+5.36e-02

Pos logit contributions
 ped+0.001
ena+0.001
ila+0.001
ases+0.001
okes+0.001
Neg logit contributions
 valuable-0.001
 may-0.001
 might-0.001
 must-0.001
 brightly-0.001
Token looked
Token ID3114
Feature activation+3.61e-03

Pos logit contributions
 valuable+0.088
 must+0.083
 may+0.082
 might+0.081
 should+0.072
Neg logit contributions
ases-0.106
ips-0.100
aster-0.099
ags-0.097
ila-0.096
Token around
Token ID1088
Feature activation+1.52e-02

Pos logit contributions
 valuable+0.009
 may+0.009
 virtue+0.008
 must+0.008
 might+0.008
Neg logit contributions
 ped-0.004
ena-0.004
ila-0.003
okes-0.003
ases-0.003
Token She
Token ID1375
Feature activation+4.55e-02

Pos logit contributions
 valuable+0.002
 may+0.002
 might+0.002
 must+0.001
 brightly+0.001
Neg logit contributions
 ped-0.003
ena-0.003
ila-0.003
ases-0.003
okes-0.003
Token had
Token ID550
Feature activation+3.29e-02

Pos logit contributions
 valuable+0.058
 might+0.055
 may+0.053
 must+0.052
 brightly+0.047
Neg logit contributions
ases-0.105
ips-0.100
okes-0.100
 ped-0.098
ags-0.098
Token a
Token ID257
Feature activation+3.23e-02

Pos logit contributions
 valuable+0.061
 may+0.056
 virtue+0.055
 must+0.051
 brightly+0.050
Neg logit contributions
 ped-0.060
ena-0.060
ila-0.055
 swinging-0.054
ases-0.051
Token big
Token ID1263
Feature activation+4.43e-03

Pos logit contributions
 valuable+0.046
 may+0.042
 virtue+0.042
umm+0.041
 must+0.039
Neg logit contributions
 ped-0.063
ena-0.063
 swinging-0.062
ila-0.061
 Tom-0.054
Token magn
Token ID7842
Feature activation-1.07e-01

Pos logit contributions
 valuable+0.008
 may+0.008
 must+0.007
 virtue+0.007
 might+0.007
Neg logit contributions
 ped-0.008
ena-0.008
ila-0.007
ases-0.007
okes-0.007
Tokenifying
Token ID4035
Feature activation+2.39e-01

Pos logit contributions
 ped+0.295
ena+0.293
ila+0.283
ases+0.279
okes+0.277
Neg logit contributions
 valuable-0.103
 may-0.072
 virtue-0.072
 must-0.063
 might-0.062
Token glass
Token ID5405
Feature activation+5.93e-02

Pos logit contributions
 valuable+0.416
 may+0.355
 virtue+0.347
 must+0.327
 might+0.326
Neg logit contributions
ena-0.442
 ped-0.439
ila-0.430
ases-0.424
aster-0.417
Token that
Token ID326
Feature activation+1.16e-01

Pos logit contributions
 valuable+0.124
 may+0.110
 virtue+0.108
 must+0.104
 fantastic+0.103
Neg logit contributions
ena-0.092
 ped-0.091
ila-0.089
ases-0.084
okes-0.082
Token made
Token ID925
Feature activation+2.62e-02

Pos logit contributions
 valuable+0.196
 may+0.169
 virtue+0.163
 must+0.161
 brightly+0.157
Neg logit contributions
 ped-0.231
ena-0.229
ila-0.218
ases-0.211
okes-0.209
Token things
Token ID1243
Feature activation+1.32e-01

Pos logit contributions
 valuable+0.061
 may+0.055
 must+0.053
 brightly+0.053
 might+0.053
Neg logit contributions
 ped-0.036
ena-0.035
ila-0.032
ases-0.031
okes-0.031
Token look
Token ID804
Feature activation+4.35e-02

Pos logit contributions
 virtue+0.269
 valuable+0.265
 may+0.233
umm+0.233
 lifetime+0.232
Neg logit contributions
 ped-0.194
 swinging-0.185
ena-0.179
ila-0.170
ases-0.167
Token a
Token ID257
Feature activation+2.88e-02

Pos logit contributions
 valuable+0.054
 may+0.049
 virtue+0.048
 brightly+0.045
 must+0.045
Neg logit contributions
 ped-0.053
ena-0.052
ila-0.048
 swinging-0.046
ases-0.046
Token flashlight
Token ID38371
Feature activation+5.24e-02

Pos logit contributions
 valuable+0.043
 virtue+0.038
 may+0.038
 must+0.036
 brightly+0.035
Neg logit contributions
 ped-0.058
ena-0.057
ila-0.056
 swinging-0.054
okes-0.051
Token and
Token ID290
Feature activation-3.18e-02

Pos logit contributions
 valuable+0.107
 may+0.094
 virtue+0.093
 must+0.089
 brightly+0.088
Neg logit contributions
 ped-0.087
ena-0.085
ila-0.079
ases-0.077
 swinging-0.076
Token a
Token ID257
Feature activation+2.92e-02

Pos logit contributions
 ped+0.058
ena+0.058
ila+0.054
ases+0.053
okes+0.052
Neg logit contributions
 valuable-0.059
 may-0.052
 virtue-0.050
 must-0.049
 might-0.049
Token magn
Token ID7842
Feature activation-1.07e-01

Pos logit contributions
 valuable+0.055
 virtue+0.050
 may+0.049
 must+0.047
umm+0.046
Neg logit contributions
 ped-0.049
ena-0.047
ila-0.045
 swinging-0.044
okes-0.040
Tokenifying
Token ID4035
Feature activation+2.39e-01

Pos logit contributions
 ped+0.303
ena+0.300
ila+0.290
ases+0.285
okes+0.282
Neg logit contributions
 valuable-0.092
 may-0.068
 virtue-0.061
 must-0.060
 might-0.058
Token glass
Token ID5405
Feature activation+5.76e-02

Pos logit contributions
 valuable+0.438
 may+0.369
 virtue+0.365
 must+0.345
 might+0.339
Neg logit contributions
 ped-0.414
ena-0.408
aster-0.403
ila-0.403
ases-0.393
Token to
Token ID284
Feature activation-6.81e-02

Pos logit contributions
 valuable+0.120
 may+0.107
 virtue+0.104
 must+0.101
 brightly+0.100
Neg logit contributions
 ped-0.090
ena-0.090
ila-0.085
ases-0.082
okes-0.080
Token examine
Token ID10716
Feature activation-8.65e-02

Pos logit contributions
 ped+0.125
ena+0.121
okes+0.119
ila+0.114
ases+0.113
Neg logit contributions
 valuable-0.123
 may-0.114
 might-0.113
 must-0.111
 brightly-0.106
Token their
Token ID511
Feature activation-4.19e-02

Pos logit contributions
ena+0.121
 ped+0.117
ila+0.115
ases+0.109
els+0.106
Neg logit contributions
 valuable-0.190
 virtue-0.177
 may-0.169
 daunting-0.161
 must-0.160
Token finds
Token ID7228
Feature activation-7.04e-02

Pos logit contributions
ena+0.072
 ped+0.069
ases+0.067
ila+0.065
okes+0.063
Neg logit contributions
 valuable-0.081
 virtue-0.070
 may-0.069
 daunting-0.067
 must-0.067
Token it
Token ID340
Feature activation+8.62e-02

Pos logit contributions
 ped+0.011
ena+0.011
ila+0.010
okes+0.010
ases+0.010
Neg logit contributions
 valuable-0.020
 may-0.018
 must-0.018
 might-0.018
 virtue-0.017
Token she
Token ID673
Feature activation+2.82e-02

Pos logit contributions
 valuable+0.157
 may+0.145
 must+0.138
 might+0.138
 brightly+0.130
Neg logit contributions
 ped-0.159
ena-0.159
ases-0.150
ila-0.148
okes-0.146
Token had
Token ID550
Feature activation+3.01e-02

Pos logit contributions
 valuable+0.044
 may+0.041
 must+0.040
 might+0.039
 most+0.035
Neg logit contributions
ena-0.057
ases-0.056
 ped-0.055
ila-0.055
okes-0.055
Token a
Token ID257
Feature activation+3.08e-02

Pos logit contributions
 valuable+0.053
 may+0.047
 must+0.045
 virtue+0.044
 might+0.044
Neg logit contributions
 ped-0.058
ena-0.057
ila-0.054
ases-0.053
okes-0.052
Token magn
Token ID7842
Feature activation-1.04e-01

Pos logit contributions
 valuable+0.042
 virtue+0.040
umm+0.039
 may+0.038
idents+0.038
Neg logit contributions
 ped-0.061
 swinging-0.057
ena-0.054
ila-0.052
 swing-0.048
Tokenifying
Token ID4035
Feature activation+2.39e-01

Pos logit contributions
 ped+0.290
ena+0.286
ila+0.275
ases+0.271
okes+0.268
Neg logit contributions
 valuable-0.096
 may-0.069
 virtue-0.066
 must-0.060
 might-0.059
Token glass
Token ID5405
Feature activation+5.83e-02

Pos logit contributions
 valuable+0.405
 may+0.348
 virtue+0.337
 might+0.324
 must+0.321
Neg logit contributions
 ped-0.451
ena-0.440
ila-0.424
aster-0.419
ases-0.417
Token,
Token ID11
Feature activation-3.59e-02

Pos logit contributions
 valuable+0.117
 may+0.105
 virtue+0.102
 must+0.098
 fantastic+0.098
Neg logit contributions
 ped-0.094
ena-0.092
ila-0.089
ases-0.084
 swinging-0.083
Token a
Token ID257
Feature activation+3.11e-02

Pos logit contributions
 ped+0.066
ena+0.065
ila+0.061
ases+0.059
okes+0.058
Neg logit contributions
 valuable-0.067
 may-0.059
 virtue-0.056
 must-0.056
 might-0.055
Token tiny
Token ID7009
Feature activation+8.47e-02

Pos logit contributions
 valuable+0.048
 virtue+0.044
 may+0.043
idents+0.042
 must+0.041
Neg logit contributions
 ped-0.058
ena-0.055
 swinging-0.054
ila-0.053
aster-0.047
Token torch
Token ID28034
Feature activation+4.37e-02

Pos logit contributions
 valuable+0.147
 virtue+0.130
 may+0.129
 might+0.121
 must+0.120
Neg logit contributions
 ped-0.154
ena-0.147
ila-0.142
 swinging-0.140
okes-0.133
Token hat
Token ID6877
Feature activation-1.86e-02

Pos logit contributions
 ped+0.168
ena+0.166
ila+0.159
ases+0.156
okes+0.153
Neg logit contributions
 valuable-0.117
 may-0.099
 must-0.093
 might-0.092
 brightly-0.091
Token and
Token ID290
Feature activation-2.86e-02

Pos logit contributions
ila+0.033
 ped+0.032
ases+0.032
ena+0.032
okes+0.031
Neg logit contributions
 valuable-0.034
 may-0.031
 must-0.031
 might-0.030
 brightly-0.030
Token grabbed
Token ID13176
Feature activation-1.21e-01

Pos logit contributions
ases+0.048
okes+0.047
ips+0.045
ila+0.045
ena+0.045
Neg logit contributions
 valuable-0.052
 may-0.049
 might-0.049
 brightly-0.047
 must-0.046
Token her
Token ID607
Feature activation-7.67e-02

Pos logit contributions
 ped+0.200
ena+0.194
ila+0.181
okes+0.177
ases+0.176
Neg logit contributions
 valuable-0.248
 may-0.221
 brightly-0.218
 must-0.213
 might-0.211
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
 ped+0.139
ena+0.138
ila+0.131
ases+0.126
okes+0.125
Neg logit contributions
 valuable-0.142
 may-0.125
 virtue-0.121
 must-0.119
 brightly-0.117
Tokenifying
Token ID4035
Feature activation+2.39e-01

Pos logit contributions
 ped+0.320
ena+0.316
ila+0.310
ases+0.301
okes+0.298
Neg logit contributions
 valuable-0.064
 may-0.046
 must-0.039
 brightly-0.037
 might-0.035
Token glass
Token ID5405
Feature activation+6.07e-02

Pos logit contributions
 valuable+0.366
 may+0.315
 virtue+0.297
 must+0.295
 might+0.291
Neg logit contributions
 ped-0.505
ena-0.501
ila-0.482
ases-0.471
okes-0.465
Token.
Token ID13
Feature activation+4.19e-03

Pos logit contributions
 valuable+0.120
 may+0.107
 must+0.103
 might+0.102
 brightly+0.101
Neg logit contributions
 ped-0.105
ena-0.102
ila-0.096
ases-0.092
okes-0.092
Token She
Token ID1375
Feature activation+5.60e-02

Pos logit contributions
 valuable+0.007
 may+0.006
 must+0.005
 might+0.005
 virtue+0.005
Neg logit contributions
 ped-0.009
ena-0.009
ila-0.008
ases-0.008
okes-0.008
Token was
Token ID373
Feature activation-1.08e-02

Pos logit contributions
 valuable+0.097
 might+0.092
 must+0.090
 may+0.090
 brightly+0.082
Neg logit contributions
ases-0.101
okes-0.097
ips-0.097
ogged-0.096
 ped-0.095
Token ready
Token ID3492
Feature activation+5.12e-02

Pos logit contributions
 ped+0.027
ases+0.027
ena+0.026
ogged+0.026
okes+0.026
Neg logit contributions
 valuable-0.013
 must-0.009
 biggest-0.009
 brightly-0.009
 most-0.009
Token He
Token ID679
Feature activation+5.02e-02

Pos logit contributions
 ped+0.016
ena+0.015
ila+0.014
ases+0.014
okes+0.014
Neg logit contributions
 valuable-0.015
 may-0.013
 virtue-0.013
 brightly-0.013
 must-0.013
Token took
Token ID1718
Feature activation-1.42e-01

Pos logit contributions
 valuable+0.083
 must+0.075
 may+0.071
 might+0.069
 brightly+0.067
Neg logit contributions
ases-0.099
ila-0.098
okes-0.096
aster-0.094
ips-0.093
Token out
Token ID503
Feature activation-4.25e-02

Pos logit contributions
 ped+0.230
ena+0.226
ila+0.214
ases+0.206
okes+0.205
Neg logit contributions
 valuable-0.293
 may-0.261
 must-0.253
 virtue-0.249
 might-0.248
Token a
Token ID257
Feature activation+3.36e-02

Pos logit contributions
 ped+0.073
ena+0.073
ila+0.072
okes+0.070
ases+0.069
Neg logit contributions
 valuable-0.081
 may-0.069
 brightly-0.069
 must-0.069
 might-0.067
Token magn
Token ID7842
Feature activation-1.05e-01

Pos logit contributions
 valuable+0.057
 virtue+0.051
 may+0.050
 brightly+0.048
umm+0.048
Neg logit contributions
 ped-0.062
ena-0.059
ila-0.057
 swinging-0.056
aster-0.054
Tokenifying
Token ID4035
Feature activation+2.38e-01

Pos logit contributions
 ped+0.308
ena+0.305
ila+0.295
ases+0.290
okes+0.288
Neg logit contributions
 valuable-0.081
 may-0.057
 virtue-0.050
 must-0.049
 might-0.047
Token glass
Token ID5405
Feature activation+5.82e-02

Pos logit contributions
 valuable+0.402
 may+0.347
 virtue+0.330
 might+0.323
 must+0.317
Neg logit contributions
ena-0.462
 ped-0.460
ila-0.445
ases-0.432
aster-0.422
Token and
Token ID290
Feature activation-2.71e-02

Pos logit contributions
 valuable+0.130
 may+0.116
 virtue+0.114
 must+0.111
 might+0.110
Neg logit contributions
 ped-0.084
ena-0.082
ila-0.078
ases-0.074
okes-0.072
Token a
Token ID257
Feature activation+3.40e-02

Pos logit contributions
 ped+0.043
ena+0.043
ila+0.042
ases+0.041
okes+0.040
Neg logit contributions
 valuable-0.055
 may-0.050
 must-0.048
 might-0.047
 brightly-0.047
Token notebook
Token ID20922
Feature activation+2.47e-02

Pos logit contributions
 valuable+0.057
 may+0.052
 virtue+0.051
idents+0.049
 must+0.049
Neg logit contributions
 ped-0.060
ena-0.058
ila-0.056
 swinging-0.055
aster-0.051
Token and
Token ID290
Feature activation-2.73e-02

Pos logit contributions
 valuable+0.048
 may+0.043
 must+0.042
 might+0.041
 virtue+0.041
Neg logit contributions
 ped-0.042
ena-0.041
ila-0.040
ases-0.039
okes-0.038
Token idea
Token ID2126
Feature activation+1.22e-01

Pos logit contributions
 valuable+0.220
 may+0.190
 virtue+0.180
 must+0.176
 might+0.175
Neg logit contributions
 ped-0.291
ena-0.285
ila-0.272
ases-0.262
 swinging-0.262
Token.
Token ID13
Feature activation+2.50e-02

Pos logit contributions
 valuable+0.227
 may+0.203
 must+0.199
 might+0.193
 virtue+0.189
Neg logit contributions
 ped-0.221
ena-0.215
ila-0.205
okes-0.203
ases-0.203
Token She
Token ID1375
Feature activation+5.78e-02

Pos logit contributions
 valuable+0.036
 may+0.030
 must+0.029
 virtue+0.028
 might+0.028
Neg logit contributions
 ped-0.056
ena-0.055
ila-0.053
ases-0.052
okes-0.051
Token suggested
Token ID5220
Feature activation-4.56e-02

Pos logit contributions
 valuable+0.110
 may+0.102
 must+0.102
 might+0.097
 virtue+0.089
Neg logit contributions
ena-0.098
 ped-0.095
ases-0.095
ila-0.094
okes-0.092
Token that
Token ID326
Feature activation+1.18e-01

Pos logit contributions
 ped+0.098
ena+0.097
ila+0.093
ases+0.091
okes+0.090
Neg logit contributions
 valuable-0.070
 may-0.060
 must-0.056
 virtue-0.056
 might-0.055
Token Cro
Token ID9325
Feature activation-2.51e-01

Pos logit contributions
 valuable+0.217
 may+0.192
 must+0.185
 might+0.181
 virtue+0.179
Neg logit contributions
 ped-0.219
ena-0.215
ila-0.204
ases-0.202
okes-0.201
Tokenc
Token ID66
Feature activation+1.10e-02

Pos logit contributions
 ped+0.381
ena+0.355
ila+0.335
ogged+0.326
 swinging+0.321
Neg logit contributions
 valuable-0.537
 might-0.472
 virtue-0.470
 may-0.468
 must-0.464
Token should
Token ID815
Feature activation+7.44e-02

Pos logit contributions
 valuable+0.021
 may+0.018
 virtue+0.017
 must+0.017
 might+0.017
Neg logit contributions
 ped-0.020
ena-0.020
ila-0.019
ases-0.018
okes-0.018
Token go
Token ID467
Feature activation-1.50e-01

Pos logit contributions
 valuable+0.145
 may+0.132
 must+0.126
 might+0.124
 virtue+0.123
Neg logit contributions
 ped-0.128
ena-0.126
ila-0.119
okes-0.116
ases-0.116
Token for
Token ID329
Feature activation-1.91e-02

Pos logit contributions
ena+0.269
 ped+0.267
ila+0.253
ases+0.246
okes+0.246
Neg logit contributions
 valuable-0.284
 may-0.250
 must-0.243
 might-0.238
 virtue-0.236
Token a
Token ID257
Feature activation+3.30e-02

Pos logit contributions
 ped+0.036
ena+0.036
ila+0.034
ases+0.033
okes+0.033
Neg logit contributions
 valuable-0.034
 may-0.030
 must-0.029
 virtue-0.028
 might-0.028
Token and
Token ID290
Feature activation-1.54e-02

Pos logit contributions
 ped+0.089
ena+0.087
ila+0.082
ases+0.080
okes+0.079
Neg logit contributions
 valuable-0.099
 may-0.086
 virtue-0.084
 brightly-0.083
 must-0.083
Token Tom
Token ID4186
Feature activation-1.53e-01

Pos logit contributions
ena+0.026
 ped+0.025
ila+0.024
ases+0.024
okes+0.024
Neg logit contributions
 valuable-0.030
 may-0.028
 must-0.027
 might-0.026
 brightly-0.026
Token named
Token ID3706
Feature activation-1.04e-01

Pos logit contributions
 ped+0.285
ena+0.282
ila+0.269
ases+0.261
okes+0.260
Neg logit contributions
 valuable-0.269
 may-0.246
 must-0.236
 might-0.233
 virtue-0.224
Token his
Token ID465
Feature activation-7.80e-02

Pos logit contributions
 ped+0.162
ena+0.159
ila+0.148
ases+0.144
okes+0.143
Neg logit contributions
 valuable-0.221
 may-0.201
 must-0.194
 might-0.193
 brightly-0.189
Token frog
Token ID21264
Feature activation-3.37e-02

Pos logit contributions
ena+0.127
 ped+0.125
ila+0.119
ases+0.115
okes+0.111
Neg logit contributions
 valuable-0.157
 may-0.141
 virtue-0.135
 must-0.134
 brightly-0.133
Token Cro
Token ID9325
Feature activation-2.50e-01

Pos logit contributions
 ped+0.056
ena+0.055
ila+0.052
ases+0.050
okes+0.050
Neg logit contributions
 valuable-0.067
 may-0.061
 must-0.058
 might-0.058
 virtue-0.057
Tokenaky
Token ID15492
Feature activation+5.81e-02

Pos logit contributions
 ped+0.384
ena+0.344
 swinging+0.324
ogged+0.321
okes+0.320
Neg logit contributions
 valuable-0.521
 might-0.472
 may-0.463
 virtue-0.456
 must-0.452
Token.
Token ID13
Feature activation+3.55e-03

Pos logit contributions
 valuable+0.115
 may+0.102
 must+0.098
 virtue+0.098
 might+0.097
Neg logit contributions
 ped-0.099
ena-0.097
ila-0.092
ases-0.089
okes-0.088
Token
Token ID198
Feature activation-3.02e-02

Pos logit contributions
 valuable+0.005
 may+0.005
 must+0.005
 might+0.004
 virtue+0.004
Neg logit contributions
 ped-0.008
ena-0.007
ila-0.007
ases-0.007
okes-0.007
Token
Token ID198
Feature activation-2.87e-02

Pos logit contributions
 ped+0.071
ena+0.068
ases+0.066
okes+0.066
 swinging+0.064
Neg logit contributions
 valuable-0.041
 may-0.032
 must-0.032
 might-0.031
 virtue-0.030
TokenOne
Token ID3198
Feature activation+4.23e-02

Pos logit contributions
 ped+0.056
ena+0.055
okes+0.053
ases+0.052
ila+0.051
Neg logit contributions
 valuable-0.048
 may-0.040
 virtue-0.040
 must-0.039
 might-0.038
Token you
Token ID345
Feature activation-8.87e-03

Pos logit contributions
 valuable+0.071
 virtue+0.065
 may+0.063
 must+0.059
 daunting+0.058
Neg logit contributions
 ped-0.070
ena-0.068
ila-0.067
 swinging-0.064
ases-0.063
Token sad
Token ID6507
Feature activation+1.26e-01

Pos logit contributions
 ped+0.016
ena+0.016
ila+0.015
ases+0.014
okes+0.014
Neg logit contributions
 valuable-0.017
 may-0.015
 must-0.014
 virtue-0.014
 might-0.014
Token,
Token ID11
Feature activation-3.79e-02

Pos logit contributions
 valuable+0.273
 may+0.247
 must+0.240
 brightly+0.235
 might+0.235
Neg logit contributions
 ped-0.192
ena-0.187
ila-0.176
ases-0.167
okes-0.162
Token Mr
Token ID1770
Feature activation-1.79e-01

Pos logit contributions
 ped+0.067
ena+0.067
ila+0.063
ases+0.061
okes+0.060
Neg logit contributions
 valuable-0.072
 may-0.064
 virtue-0.061
 must-0.061
 might-0.060
Token.
Token ID13
Feature activation+7.16e-03

Pos logit contributions
 ped+0.345
ena+0.321
ila+0.304
ases+0.298
okes+0.295
Neg logit contributions
 valuable-0.328
 may-0.286
 must-0.277
 might-0.277
 virtue-0.277
Token Cro
Token ID9325
Feature activation-2.48e-01

Pos logit contributions
 valuable+0.012
 may+0.010
 must+0.010
 might+0.010
 virtue+0.010
Neg logit contributions
 ped-0.015
ena-0.014
ila-0.013
ases-0.013
okes-0.013
Tokencod
Token ID19815
Feature activation-6.83e-02

Pos logit contributions
 ped+0.391
ena+0.355
ogged+0.330
 swinging+0.327
ases+0.323
Neg logit contributions
 valuable-0.524
 might-0.456
 virtue-0.454
 may-0.445
 must-0.444
Tokenile
Token ID576
Feature activation+3.78e-03

Pos logit contributions
 ped+0.116
ena+0.110
ila+0.102
okes+0.098
 swinging+0.098
Neg logit contributions
 valuable-0.136
 may-0.121
 must-0.118
 virtue-0.117
 might-0.117
Token?"
Token ID1701
Feature activation-3.46e-02

Pos logit contributions
 valuable+0.009
 may+0.008
 virtue+0.008
 brightly+0.008
 must+0.008
Neg logit contributions
 ped-0.005
ena-0.005
ila-0.005
ases-0.004
okes-0.004
Token The
Token ID383
Feature activation+3.82e-02

Pos logit contributions
ena+0.079
 ped+0.078
ases+0.078
ila+0.074
okes+0.074
Neg logit contributions
 valuable-0.046
 may-0.039
 must-0.037
 might-0.036
 brightly-0.035
Token crocod
Token ID37565
Feature activation-8.00e-02

Pos logit contributions
 valuable+0.068
 may+0.062
 virtue+0.059
 must+0.058
 might+0.057
Neg logit contributions
ena-0.070
 ped-0.070
ila-0.068
ases-0.065
 swinging-0.063
Token is
Token ID318
Feature activation+3.05e-02

Pos logit contributions
 valuable+0.271
 virtue+0.244
 brightly+0.240
 daunting+0.239
 fantastic+0.232
Neg logit contributions
ena-0.218
 ped-0.218
ila-0.199
 swinging-0.191
okes-0.185
Token a
Token ID257
Feature activation+3.57e-02

Pos logit contributions
 valuable+0.057
 may+0.054
 virtue+0.052
 brightly+0.051
 must+0.050
Neg logit contributions
ena-0.052
 ped-0.050
ila-0.048
 Tom-0.046
 swinging-0.045
Token silly
Token ID14397
Feature activation+1.14e-01

Pos logit contributions
 may+0.050
 valuable+0.050
 might+0.046
 must+0.045
idents+0.045
Neg logit contributions
 ped-0.063
ila-0.063
ena-0.063
 swinging-0.062
aster-0.058
Token story
Token ID1621
Feature activation+5.98e-02

Pos logit contributions
 valuable+0.180
 may+0.155
 virtue+0.147
 must+0.144
 brightly+0.143
Neg logit contributions
 ped-0.238
ena-0.237
ila-0.229
ases-0.220
okes-0.217
Token.
Token ID13
Feature activation+3.14e-03

Pos logit contributions
 valuable+0.118
 may+0.105
 must+0.101
 virtue+0.099
 might+0.099
Neg logit contributions
 ped-0.104
ena-0.098
ila-0.095
ases-0.093
okes-0.093
Token Cro
Token ID9325
Feature activation-2.48e-01

Pos logit contributions
 valuable+0.004
 may+0.004
 must+0.004
 virtue+0.003
 might+0.003
Neg logit contributions
 ped-0.007
ena-0.007
ila-0.007
ases-0.007
okes-0.007
Tokencod
Token ID19815
Feature activation-7.04e-02

Pos logit contributions
 ped+0.385
ena+0.361
ila+0.334
ases+0.322
ogged+0.321
Neg logit contributions
 valuable-0.532
 may-0.474
 might-0.467
 must-0.459
 virtue-0.454
Tokeniles
Token ID2915
Feature activation-3.32e-02

Pos logit contributions
 ped+0.108
ena+0.105
ila+0.098
ases+0.094
okes+0.093
Neg logit contributions
 valuable-0.152
 may-0.137
 must-0.132
 virtue-0.131
 might-0.130
Token are
Token ID389
Feature activation+3.75e-02

Pos logit contributions
 ped+0.063
ena+0.063
ila+0.060
ases+0.059
okes+0.057
Neg logit contributions
 valuable-0.059
 may-0.050
 virtue-0.049
 brightly-0.048
 must-0.048
Token not
Token ID407
Feature activation+2.39e-02

Pos logit contributions
 valuable+0.061
 may+0.054
 virtue+0.052
 must+0.051
 brightly+0.050
Neg logit contributions
 ped-0.076
ena-0.075
ila-0.071
ases-0.069
okes-0.068
Token poor
Token ID3595
Feature activation+1.48e-01

Pos logit contributions
 valuable+0.038
 may+0.034
 virtue+0.032
 must+0.031
 might+0.031
Neg logit contributions
 ped-0.049
ena-0.049
ila-0.047
ases-0.045
okes-0.045
Token"
Token ID1
Feature activation+1.02e-02

Pos logit contributions
 ped+0.050
ena+0.049
ases+0.046
ila+0.045
okes+0.044
Neg logit contributions
 valuable-0.082
 may-0.074
 must-0.071
 might-0.071
 brightly-0.070
TokenHello
Token ID15496
Feature activation-2.37e-02

Pos logit contributions
 valuable+0.017
 may+0.015
 brightly+0.015
 might+0.015
 must+0.015
Neg logit contributions
 ped-0.020
ena-0.019
ases-0.019
okes-0.019
ila-0.019
Token,
Token ID11
Feature activation-2.96e-02

Pos logit contributions
 ped+0.039
ena+0.039
ila+0.037
ases+0.035
okes+0.035
Neg logit contributions
 valuable-0.048
 may-0.043
 must-0.041
 virtue-0.041
 might-0.041
Token Mr
Token ID1770
Feature activation-1.80e-01

Pos logit contributions
ila+0.053
ena+0.053
 ped+0.052
 Tom+0.049
 swinging+0.048
Neg logit contributions
 valuable-0.054
 virtue-0.049
 may-0.045
 daunting-0.044
 brightly-0.043
Token.
Token ID13
Feature activation+8.09e-03

Pos logit contributions
ena+0.267
 ped+0.259
ila+0.252
ases+0.239
okes+0.235
Neg logit contributions
 valuable-0.395
 may-0.352
 virtue-0.344
 must-0.340
 brightly-0.334
Token Cro
Token ID9325
Feature activation-2.48e-01

Pos logit contributions
 valuable+0.016
 may+0.014
 virtue+0.014
 must+0.014
 might+0.014
Neg logit contributions
 ped-0.013
ena-0.013
ila-0.013
ases-0.012
okes-0.012
Tokencod
Token ID19815
Feature activation-6.49e-02

Pos logit contributions
 ped+0.382
ena+0.363
ases+0.331
ila+0.329
 swinging+0.322
Neg logit contributions
 valuable-0.537
 may-0.475
 might-0.469
 must-0.462
 virtue-0.454
Tokenile
Token ID576
Feature activation+4.15e-03

Pos logit contributions
 ped+0.111
ena+0.106
ila+0.096
okes+0.095
 swinging+0.094
Neg logit contributions
 valuable-0.128
 may-0.115
 must-0.111
 might-0.110
 virtue-0.109
Token,"
Token ID553
Feature activation-3.94e-02

Pos logit contributions
 valuable+0.008
 may+0.007
 virtue+0.007
 brightly+0.007
 must+0.006
Neg logit contributions
 ped-0.007
ena-0.007
ila-0.007
ases-0.007
okes-0.007
Token said
Token ID531
Feature activation-1.14e-01

Pos logit contributions
 ped+0.054
ena+0.053
ases+0.049
ila+0.048
okes+0.047
Neg logit contributions
 valuable-0.092
 may-0.083
 must-0.081
 might-0.080
 brightly-0.080
Token Lily
Token ID20037
Feature activation-9.12e-02

Pos logit contributions
 ped+0.186
ena+0.183
ases+0.175
okes+0.172
ila+0.166
Neg logit contributions
 valuable-0.231
 must-0.203
 may-0.203
 brightly-0.202
 might-0.199
Token's
Token ID338
Feature activation-2.50e-03

Pos logit contributions
 valuable+0.252
 virtue+0.220
 brightly+0.214
 may+0.212
 daunting+0.207
Neg logit contributions
 ped-0.267
ena-0.266
ila-0.249
ases-0.242
okes-0.241
Token wrong
Token ID2642
Feature activation+1.37e-01

Pos logit contributions
 ped+0.006
ena+0.006
ila+0.006
ases+0.005
okes+0.005
Neg logit contributions
 valuable-0.003
 may-0.003
 virtue-0.003
 must-0.003
 brightly-0.003
Token,
Token ID11
Feature activation-3.65e-02

Pos logit contributions
 valuable+0.274
 may+0.242
 must+0.237
 virtue+0.231
 brightly+0.231
Neg logit contributions
 ped-0.237
ena-0.230
ila-0.219
ases-0.213
okes-0.207
Token Mr
Token ID1770
Feature activation-1.80e-01

Pos logit contributions
ena+0.059
 ped+0.057
ila+0.056
 Tom+0.052
 swinging+0.052
Neg logit contributions
 valuable-0.073
 virtue-0.065
 may-0.063
 might-0.061
 daunting-0.060
Token.
Token ID13
Feature activation+1.52e-02

Pos logit contributions
 ped+0.305
ena+0.292
ila+0.275
ases+0.270
okes+0.264
Neg logit contributions
 valuable-0.365
 may-0.328
 must-0.314
 might-0.313
 virtue-0.311
Token Cro
Token ID9325
Feature activation-2.47e-01

Pos logit contributions
 valuable+0.027
 may+0.024
 must+0.023
 virtue+0.023
 might+0.022
Neg logit contributions
 ped-0.029
ena-0.029
ila-0.027
ases-0.026
okes-0.026
Tokencod
Token ID19815
Feature activation-6.39e-02

Pos logit contributions
 ped+0.396
ena+0.374
ases+0.346
ogged+0.339
ila+0.339
Neg logit contributions
 valuable-0.521
 might-0.452
 may-0.450
 must-0.442
 virtue-0.436
Tokenile
Token ID576
Feature activation+5.29e-03

Pos logit contributions
 ped+0.113
ena+0.107
ila+0.097
okes+0.096
 swinging+0.096
Neg logit contributions
 valuable-0.123
 may-0.109
 must-0.106
 might-0.105
 virtue-0.104
Token?"
Token ID1701
Feature activation-3.20e-02

Pos logit contributions
 valuable+0.013
 may+0.011
 virtue+0.011
 must+0.011
 brightly+0.011
Neg logit contributions
 ped-0.007
ena-0.007
ila-0.006
ases-0.006
okes-0.006
Token
Token ID220
Feature activation+8.78e-02

Pos logit contributions
ena+0.084
ases+0.084
 ped+0.082
ila+0.080
okes+0.079
Neg logit contributions
 valuable-0.034
 may-0.029
 might-0.027
 must-0.026
 brightly-0.024
Token
Token ID198
Feature activation-2.63e-02

Pos logit contributions
 valuable+0.101
 may+0.078
 must+0.075
 might+0.074
 biggest+0.067
Neg logit contributions
 ped-0.228
ena-0.218
ases-0.208
ila-0.201
 swinging-0.200
Token,
Token ID11
Feature activation-3.75e-02

Pos logit contributions
 ped+0.160
ena+0.156
ila+0.147
ases+0.144
okes+0.141
Neg logit contributions
 valuable-0.181
 may-0.164
 must-0.157
 might-0.156
 virtue-0.153
Token we
Token ID356
Feature activation+4.57e-03

Pos logit contributions
 ped+0.081
ena+0.080
ila+0.076
ases+0.075
okes+0.074
Neg logit contributions
 valuable-0.057
 may-0.050
 must-0.047
 might-0.046
 virtue-0.046
Token can
Token ID460
Feature activation+1.09e-01

Pos logit contributions
 valuable+0.007
 brightly+0.005
 virtue+0.005
 may+0.005
 daunting+0.005
Neg logit contributions
 ped-0.010
ena-0.010
ila-0.010
ases-0.009
okes-0.009
Token't
Token ID470
Feature activation+3.03e-02

Pos logit contributions
 valuable+0.148
 may+0.137
 might+0.130
 must+0.128
 virtue+0.116
Neg logit contributions
ena-0.246
 ped-0.244
ila-0.235
ases-0.227
okes-0.226
Token.
Token ID13
Feature activation+2.88e-03

Pos logit contributions
 valuable+0.048
 might+0.047
 may+0.047
 must+0.047
 brightly+0.042
Neg logit contributions
ena-0.059
 ped-0.057
ips-0.053
okes-0.052
ila-0.052
Token Cro
Token ID9325
Feature activation-2.47e-01

Pos logit contributions
 valuable+0.005
 virtue+0.004
 may+0.004
 fantastic+0.004
 must+0.003
Neg logit contributions
ena-0.006
 ped-0.006
ila-0.006
ases-0.006
okes-0.006
Tokencod
Token ID19815
Feature activation-6.92e-02

Pos logit contributions
 ped+0.383
ena+0.362
ila+0.332
ogged+0.321
 swinging+0.315
Neg logit contributions
 valuable-0.525
 may-0.471
 might-0.468
 must-0.458
 virtue-0.450
Tokeniles
Token ID2915
Feature activation-3.06e-02

Pos logit contributions
 ped+0.116
ena+0.109
ila+0.099
 swinging+0.097
okes+0.095
Neg logit contributions
 valuable-0.137
 may-0.126
 might-0.122
 must-0.121
 virtue-0.118
Token are
Token ID389
Feature activation+3.34e-02

Pos logit contributions
 ped+0.063
ena+0.063
ila+0.058
ases+0.057
okes+0.057
Neg logit contributions
 valuable-0.048
 may-0.044
 might-0.042
 must-0.042
 virtue-0.039
Token bad
Token ID2089
Feature activation+9.10e-02

Pos logit contributions
 valuable+0.049
 may+0.042
 virtue+0.040
 must+0.039
 might+0.039
Neg logit contributions
 ped-0.074
ena-0.073
ila-0.070
ases-0.068
okes-0.067
Token.
Token ID13
Feature activation+4.99e-04

Pos logit contributions
 valuable+0.173
 may+0.153
 must+0.148
 might+0.146
 virtue+0.145
Neg logit contributions
 ped-0.162
ena-0.160
ila-0.151
ases-0.145
okes-0.143
Token,
Token ID11
Feature activation-3.46e-02

Pos logit contributions
 valuable+0.072
 may+0.063
 virtue+0.062
 brightly+0.061
 must+0.061
Neg logit contributions
 ped-0.048
ena-0.048
ila-0.045
okes-0.042
ases-0.042
Token we
Token ID356
Feature activation+7.97e-03

Pos logit contributions
ena+0.068
 ped+0.068
ila+0.066
ases+0.061
 swinging+0.061
Neg logit contributions
 valuable-0.058
 virtue-0.050
 may-0.049
 must-0.047
 brightly-0.046
Token can
Token ID460
Feature activation+1.14e-01

Pos logit contributions
 valuable+0.012
 brightly+0.010
 virtue+0.010
 biggest+0.009
 daunting+0.009
Neg logit contributions
 ped-0.017
ena-0.016
ila-0.016
ases-0.015
okes-0.015
Token't
Token ID470
Feature activation+3.22e-02

Pos logit contributions
 valuable+0.196
 may+0.167
 virtue+0.163
 must+0.158
 brightly+0.158
Neg logit contributions
 ped-0.224
ena-0.220
ila-0.211
ases-0.206
okes-0.203
Token.
Token ID13
Feature activation+5.28e-03

Pos logit contributions
 valuable+0.065
 may+0.059
 must+0.056
 virtue+0.056
 might+0.055
Neg logit contributions
 ped-0.053
ena-0.053
ila-0.050
ases-0.048
okes-0.047
Token Cro
Token ID9325
Feature activation-2.46e-01

Pos logit contributions
 valuable+0.008
 virtue+0.006
 may+0.006
 fantastic+0.006
 must+0.006
Neg logit contributions
ena-0.012
ila-0.011
 ped-0.011
ases-0.011
okes-0.011
Tokencod
Token ID19815
Feature activation-6.66e-02

Pos logit contributions
 ped+0.357
ena+0.328
ila+0.303
ogged+0.298
 swinging+0.298
Neg logit contributions
 valuable-0.547
 might-0.494
 may-0.488
 must-0.479
 virtue-0.476
Tokeniles
Token ID2915
Feature activation-2.88e-02

Pos logit contributions
 ped+0.111
ena+0.103
ila+0.094
 swinging+0.093
okes+0.092
Neg logit contributions
 valuable-0.134
 may-0.123
 might-0.119
 must-0.118
 virtue-0.116
Token are
Token ID389
Feature activation+3.68e-02

Pos logit contributions
 ped+0.060
ena+0.059
ila+0.055
ases+0.054
okes+0.054
Neg logit contributions
 valuable-0.046
 may-0.041
 might-0.039
 must-0.039
 virtue-0.037
Token dangerous
Token ID4923
Feature activation+1.02e-01

Pos logit contributions
 valuable+0.057
 may+0.051
 virtue+0.048
 must+0.047
 brightly+0.046
Neg logit contributions
 ped-0.076
ena-0.076
ila-0.073
ases-0.070
okes-0.070
Token.
Token ID13
Feature activation+2.69e-03

Pos logit contributions
 valuable+0.212
 may+0.190
 virtue+0.184
 must+0.180
 brightly+0.177
Neg logit contributions
 ped-0.165
ena-0.161
ila-0.152
ases-0.149
okes-0.146
Token enjoy
Token ID2883
Feature activation+5.04e-02

Pos logit contributions
 ped+0.035
ena+0.034
ila+0.032
ases+0.031
okes+0.031
Neg logit contributions
 valuable-0.045
 may-0.040
 must-0.038
 virtue-0.038
 might-0.038
Token the
Token ID262
Feature activation-2.03e-03

Pos logit contributions
 valuable+0.105
 may+0.094
 must+0.090
 virtue+0.089
 might+0.089
Neg logit contributions
 ped-0.081
ena-0.080
ila-0.075
ases-0.073
okes-0.072
Token cool
Token ID3608
Feature activation+6.48e-02

Pos logit contributions
 ped+0.004
ila+0.004
 swinging+0.004
ases+0.004
ena+0.004
Neg logit contributions
 valuable-0.003
 may-0.003
 virtue-0.003
 must-0.002
idents-0.002
Token water
Token ID1660
Feature activation+5.84e-02

Pos logit contributions
 valuable+0.116
 virtue+0.103
 may+0.096
 must+0.095
 fantastic+0.090
Neg logit contributions
 ped-0.117
 swinging-0.110
ila-0.109
ases-0.108
ogged-0.103
Token.
Token ID13
Feature activation+1.03e-02

Pos logit contributions
 valuable+0.126
 may+0.113
 virtue+0.111
 must+0.109
 might+0.107
Neg logit contributions
 ped-0.086
ena-0.083
ila-0.079
ases-0.076
 swinging-0.075
Token Cro
Token ID9325
Feature activation-2.46e-01

Pos logit contributions
 valuable+0.015
 may+0.013
 must+0.013
 might+0.012
 virtue+0.012
Neg logit contributions
 ped-0.022
ena-0.022
ila-0.021
ases-0.021
okes-0.020
Tokenc
Token ID66
Feature activation+1.46e-02

Pos logit contributions
 ped+0.372
ena+0.355
ases+0.323
ila+0.322
 swinging+0.318
Neg logit contributions
 valuable-0.525
 might-0.463
 may-0.461
 must-0.456
 virtue-0.454
Token thought
Token ID1807
Feature activation+1.76e-02

Pos logit contributions
 valuable+0.032
 may+0.029
 virtue+0.028
 must+0.028
 brightly+0.027
Neg logit contributions
 ped-0.021
ena-0.021
ila-0.020
ases-0.019
okes-0.019
Token it
Token ID340
Feature activation+8.83e-02

Pos logit contributions
 valuable+0.029
 may+0.025
 must+0.024
 might+0.024
 brightly+0.023
Neg logit contributions
ena-0.037
 ped-0.036
ases-0.035
okes-0.034
ila-0.033
Token was
Token ID373
Feature activation-1.35e-02

Pos logit contributions
 virtue+0.159
 valuable+0.159
umm+0.156
ifying+0.148
 pleasure+0.138
Neg logit contributions
 ped-0.136
ena-0.127
 climbed-0.111
 ran-0.110
 swinging-0.107
Token a
Token ID257
Feature activation+3.48e-02

Pos logit contributions
ena+0.022
 Tom+0.022
 swinging+0.021
 ped+0.021
ila+0.021
Neg logit contributions
umm-0.023
 virtue-0.022
 valuable-0.021
 may-0.021
idents-0.021
Token in
Token ID287
Feature activation-5.66e-02

Pos logit contributions
 ped+0.013
ena+0.012
ila+0.011
 swinging+0.011
ases+0.011
Neg logit contributions
 valuable-0.019
 may-0.017
 virtue-0.017
 must-0.017
 might-0.016
Token the
Token ID262
Feature activation-3.41e-05

Pos logit contributions
 ped+0.087
ena+0.086
ila+0.080
okes+0.078
ases+0.078
Neg logit contributions
 valuable-0.121
 may-0.109
 must-0.105
 might-0.104
 brightly-0.104
Token cool
Token ID3608
Feature activation+6.56e-02

Pos logit contributions
 ped+0.000
ila+0.000
 swinging+0.000
ena+0.000
aster+0.000
Neg logit contributions
 valuable-0.000
 may-0.000
 virtue-0.000
 must-0.000
idents-0.000
Token water
Token ID1660
Feature activation+5.73e-02

Pos logit contributions
 valuable+0.118
 virtue+0.105
 may+0.097
 must+0.096
 fantastic+0.091
Neg logit contributions
 ped-0.118
 swinging-0.110
ogged-0.110
ases-0.109
ila-0.107
Token.
Token ID13
Feature activation+6.82e-03

Pos logit contributions
 valuable+0.124
 may+0.111
 virtue+0.108
 must+0.106
 might+0.104
Neg logit contributions
 ped-0.086
ena-0.084
ila-0.079
ases-0.077
okes-0.074
Token Cro
Token ID9325
Feature activation-2.46e-01

Pos logit contributions
 valuable+0.011
 may+0.009
 must+0.009
 virtue+0.009
 might+0.009
Neg logit contributions
 ped-0.014
ena-0.014
ila-0.013
ases-0.013
okes-0.013
Tokenc
Token ID66
Feature activation+1.46e-02

Pos logit contributions
 ped+0.369
ena+0.358
ases+0.333
ila+0.329
okes+0.326
Neg logit contributions
 valuable-0.520
 might-0.458
 may-0.456
 must-0.452
 virtue-0.448
Token enjoyed
Token ID8359
Feature activation+3.20e-02

Pos logit contributions
 valuable+0.028
 may+0.025
 virtue+0.024
 must+0.024
 brightly+0.023
Neg logit contributions
 ped-0.025
ena-0.025
ila-0.024
ases-0.023
okes-0.022
Token his
Token ID465
Feature activation-6.76e-02

Pos logit contributions
 valuable+0.063
 may+0.055
 brightly+0.054
 must+0.052
 might+0.052
Neg logit contributions
ena-0.055
okes-0.052
 ped-0.050
ases-0.050
ila-0.050
Token swim
Token ID9422
Feature activation-8.93e-02

Pos logit contributions
 ped+0.142
ena+0.136
ila+0.134
 swinging+0.129
ases+0.128
Neg logit contributions
 valuable-0.103
 may-0.088
 virtue-0.088
 must-0.086
 brightly-0.081
Token so
Token ID523
Feature activation+1.75e-01

Pos logit contributions
 ped+0.134
ena+0.128
ila+0.121
ases+0.118
 swinging+0.113
Neg logit contributions
 valuable-0.193
 may-0.173
 virtue-0.169
 must-0.167
 might-0.163
Token That
Token ID1320
Feature activation+1.63e-01

Pos logit contributions
 valuable+0.005
 virtue+0.004
 may+0.004
 brightly+0.004
 must+0.004
Neg logit contributions
ena-0.007
 ped-0.006
ila-0.006
ases-0.006
okes-0.006
Token is
Token ID318
Feature activation+3.11e-02

Pos logit contributions
 valuable+0.324
 virtue+0.296
 brightly+0.293
 daunting+0.288
 brand+0.284
Neg logit contributions
ena-0.257
 ped-0.257
ila-0.244
ases-0.229
 swinging-0.226
Token not
Token ID407
Feature activation+2.42e-02

Pos logit contributions
 valuable+0.058
 may+0.054
 virtue+0.051
 brightly+0.050
 must+0.050
Neg logit contributions
ena-0.054
 ped-0.052
ila-0.050
 swinging-0.047
ases-0.047
Token true
Token ID2081
Feature activation+2.40e-03

Pos logit contributions
 valuable+0.037
 may+0.036
 virtue+0.034
 must+0.032
 brightly+0.031
Neg logit contributions
ena-0.048
 ped-0.047
ila-0.044
 Tom-0.043
 swinging-0.043
Token.
Token ID13
Feature activation+2.43e-03

Pos logit contributions
 valuable+0.005
 may+0.005
 virtue+0.005
 brightly+0.005
 must+0.005
Neg logit contributions
ena-0.003
 ped-0.003
ases-0.003
ila-0.003
okes-0.003
Token Cro
Token ID9325
Feature activation-2.46e-01

Pos logit contributions
 valuable+0.004
 may+0.003
 virtue+0.003
 must+0.003
 brightly+0.003
Neg logit contributions
ena-0.005
 ped-0.005
ila-0.005
ases-0.005
okes-0.005
Tokencod
Token ID19815
Feature activation-6.90e-02

Pos logit contributions
 ped+0.360
ena+0.345
ila+0.318
ases+0.305
okes+0.301
Neg logit contributions
 valuable-0.551
 may-0.495
 might-0.480
 must-0.478
 virtue-0.474
Tokeniles
Token ID2915
Feature activation-3.01e-02

Pos logit contributions
 ped+0.102
ena+0.100
ila+0.093
ases+0.090
okes+0.088
Neg logit contributions
 valuable-0.153
 may-0.138
 must-0.132
 virtue-0.132
 might-0.131
Token can
Token ID460
Feature activation+1.11e-01

Pos logit contributions
 ped+0.059
ena+0.059
ila+0.056
ases+0.055
okes+0.054
Neg logit contributions
 valuable-0.051
 may-0.044
 virtue-0.042
 must-0.042
 brightly-0.041
Token be
Token ID307
Feature activation-6.33e-02

Pos logit contributions
 valuable+0.211
 may+0.189
 must+0.181
 might+0.180
 virtue+0.177
Neg logit contributions
 ped-0.199
ena-0.196
ila-0.184
okes-0.178
ases-0.177
Token poor
Token ID3595
Feature activation+1.51e-01

Pos logit contributions
 ped+0.135
ena+0.133
ila+0.127
ases+0.123
okes+0.122
Neg logit contributions
 valuable-0.099
 may-0.085
 must-0.080
 virtue-0.080
 might-0.079
Tokening
Token ID278
Feature activation+3.36e-03

Pos logit contributions
ena+0.140
 ped+0.140
ila+0.133
ases+0.128
okes+0.127
Neg logit contributions
 valuable-0.157
 may-0.139
 virtue-0.133
 must-0.131
 might-0.131
Token,
Token ID11
Feature activation-3.27e-02

Pos logit contributions
 valuable+0.007
 may+0.007
 virtue+0.006
 must+0.006
 might+0.006
Neg logit contributions
 ped-0.005
ena-0.005
ila-0.005
ases-0.004
okes-0.004
Token and
Token ID290
Feature activation-2.89e-02

Pos logit contributions
 ped+0.062
ena+0.061
ila+0.059
ases+0.056
okes+0.055
Neg logit contributions
 valuable-0.059
 may-0.051
 virtue-0.050
 must-0.048
 might-0.048
Token stretching
Token ID20880
Feature activation-5.74e-03

Pos logit contributions
 ped+0.058
ena+0.057
ila+0.055
 swinging+0.053
ases+0.052
Neg logit contributions
 valuable-0.048
 virtue-0.041
 may-0.041
 must-0.039
 brightly-0.038
Token.
Token ID13
Feature activation+9.55e-03

Pos logit contributions
 ped+0.009
ena+0.009
ila+0.009
ases+0.009
okes+0.008
Neg logit contributions
 valuable-0.012
 may-0.010
 virtue-0.010
 must-0.010
 brightly-0.010
Token Cro
Token ID9325
Feature activation-2.45e-01

Pos logit contributions
 valuable+0.013
 virtue+0.010
 may+0.010
 must+0.010
 might+0.010
Neg logit contributions
ena-0.023
 ped-0.022
ila-0.022
ases-0.021
okes-0.021
Tokencod
Token ID19815
Feature activation-6.65e-02

Pos logit contributions
 ped+0.334
ena+0.321
ila+0.296
ases+0.285
okes+0.278
Neg logit contributions
 valuable-0.566
 may-0.512
 might-0.501
 must-0.498
 virtue-0.491
Tokeniles
Token ID2915
Feature activation-2.99e-02

Pos logit contributions
 ped+0.092
ena+0.091
ila+0.086
ases+0.083
okes+0.080
Neg logit contributions
 valuable-0.154
 may-0.139
 virtue-0.134
 must-0.133
 brightly-0.132
Token do
Token ID466
Feature activation+5.15e-02

Pos logit contributions
 ped+0.058
ena+0.057
ila+0.055
ases+0.054
okes+0.053
Neg logit contributions
 valuable-0.052
 may-0.043
 virtue-0.043
 brightly-0.042
 must-0.041
Token that
Token ID326
Feature activation+1.23e-01

Pos logit contributions
 valuable+0.108
umm+0.104
 virtue+0.099
 may+0.098
 brightly+0.098
Neg logit contributions
 ped-0.075
ena-0.073
ila-0.070
aster-0.065
ases-0.065
Token sometimes
Token ID3360
Feature activation+1.37e-01

Pos logit contributions
 valuable+0.233
 virtue+0.205
 may+0.197
 brightly+0.190
 daunting+0.189
Neg logit contributions
 ped-0.213
ena-0.205
ila-0.202
ases-0.193
okes-0.191
Token stood
Token ID6204
Feature activation-1.29e-01

Pos logit contributions
 valuable+0.150
 brightly+0.131
umm+0.131
 virtue+0.130
 daunting+0.126
Neg logit contributions
 ped-0.118
ena-0.116
ila-0.111
ases-0.108
eks-0.102
Token up
Token ID510
Feature activation-4.92e-02

Pos logit contributions
 ped+0.223
ena+0.220
ila+0.208
ases+0.201
okes+0.198
Neg logit contributions
 valuable-0.255
 may-0.226
 must-0.216
 virtue-0.216
 might-0.213
Token for
Token ID329
Feature activation-1.43e-02

Pos logit contributions
 ped+0.079
ena+0.078
ila+0.073
ases+0.071
okes+0.070
Neg logit contributions
 valuable-0.103
 may-0.091
 must-0.088
 virtue-0.088
 brightly-0.087
Token yourself
Token ID3511
Feature activation+5.59e-02

Pos logit contributions
 ped+0.027
ena+0.026
ila+0.025
okes+0.025
ases+0.024
Neg logit contributions
 valuable-0.026
 may-0.022
 brightly-0.022
 might-0.021
 must-0.021
Token and
Token ID290
Feature activation-2.51e-02

Pos logit contributions
 valuable+0.118
 may+0.105
 virtue+0.101
 must+0.100
 brightly+0.099
Neg logit contributions
 ped-0.087
ena-0.086
ila-0.080
ases-0.077
okes-0.076
Token Cro
Token ID9325
Feature activation-2.42e-01

Pos logit contributions
 ped+0.048
ena+0.047
ila+0.045
ases+0.043
okes+0.043
Neg logit contributions
 valuable-0.045
 may-0.039
 virtue-0.037
 must-0.037
 brightly-0.036
Tokenco
Token ID1073
Feature activation-1.57e-01

Pos logit contributions
 ped+0.357
ena+0.325
ila+0.312
 swinging+0.310
ogged+0.309
Neg logit contributions
 valuable-0.497
 might-0.460
 virtue-0.446
 must-0.435
 may-0.434
Token.
Token ID13
Feature activation+5.33e-03

Pos logit contributions
 ped+0.177
ena+0.167
ila+0.157
okes+0.155
ases+0.153
Neg logit contributions
 valuable-0.381
 may-0.351
 might-0.351
 virtue-0.342
 must-0.340
Token You
Token ID921
Feature activation+6.73e-02

Pos logit contributions
 valuable+0.007
 may+0.006
 must+0.006
 virtue+0.005
 might+0.005
Neg logit contributions
 ped-0.012
ena-0.012
ila-0.012
ases-0.011
okes-0.011
Token know
Token ID760
Feature activation+1.77e-02

Pos logit contributions
 valuable+0.127
 virtue+0.108
 brightly+0.107
 daunting+0.103
umm+0.103
Neg logit contributions
 ped-0.122
ena-0.119
ila-0.113
ases-0.110
eks-0.103
Token what
Token ID644
Feature activation+1.47e-01

Pos logit contributions
 valuable+0.033
 may+0.029
 virtue+0.027
 must+0.027
 might+0.027
Neg logit contributions
 ped-0.032
ena-0.032
ila-0.030
ases-0.029
okes-0.029
Token and
Token ID290
Feature activation-3.41e-02

Pos logit contributions
 ped+0.117
ena+0.115
ila+0.112
ases+0.107
okes+0.104
Neg logit contributions
 valuable-0.171
 brightly-0.149
 may-0.148
 must-0.144
 might-0.141
Token hugged
Token ID41130
Feature activation-1.24e-01

Pos logit contributions
ena+0.045
 ped+0.043
ases+0.042
ila+0.042
okes+0.039
Neg logit contributions
 valuable-0.079
 may-0.073
 must-0.070
 might-0.069
 brightly-0.067
Token her
Token ID607
Feature activation-8.03e-02

Pos logit contributions
 ped+0.200
ena+0.199
okes+0.183
eks+0.182
ila+0.182
Neg logit contributions
 valuable-0.226
 may-0.212
 might-0.212
 brightly-0.208
 lot-0.202
Token mom
Token ID1995
Feature activation-9.94e-02

Pos logit contributions
 ped+0.139
ena+0.139
ila+0.133
okes+0.132
ases+0.132
Neg logit contributions
 valuable-0.156
 may-0.139
 might-0.134
 brightly-0.132
 biggest-0.130
Token and
Token ID290
Feature activation-3.18e-02

Pos logit contributions
 ped+0.173
ena+0.166
ila+0.164
ases+0.160
okes+0.159
Neg logit contributions
 valuable-0.195
 may-0.171
 must-0.164
 might-0.164
 brightly-0.161
Token Cro
Token ID9325
Feature activation-2.42e-01

Pos logit contributions
ena+0.051
ila+0.050
 ped+0.049
ases+0.049
okes+0.047
Neg logit contributions
 valuable-0.063
 may-0.056
 might-0.054
 must-0.054
 brightly-0.052
Tokenco
Token ID1073
Feature activation-1.56e-01

Pos logit contributions
 ped+0.341
ena+0.325
ila+0.300
 swinging+0.300
okes+0.290
Neg logit contributions
 valuable-0.535
 might-0.478
 may-0.475
 virtue-0.466
 must-0.465
Token.
Token ID13
Feature activation-4.43e-03

Pos logit contributions
 ped+0.220
ena+0.205
ila+0.204
ases+0.202
okes+0.201
Neg logit contributions
 valuable-0.342
 may-0.298
 might-0.296
 virtue-0.290
 must-0.281
Token She
Token ID1375
Feature activation+5.14e-02

Pos logit contributions
 ped+0.010
ena+0.010
ila+0.009
ases+0.009
aster+0.009
Neg logit contributions
 valuable-0.006
 may-0.005
 brightly-0.005
 might-0.005
 must-0.005
Token felt
Token ID2936
Feature activation+1.50e-02

Pos logit contributions
 valuable+0.085
 may+0.074
 must+0.071
 might+0.070
 brightly+0.067
Neg logit contributions
 ped-0.102
ena-0.101
ases-0.100
ila-0.099
okes-0.097
Token happy
Token ID3772
Feature activation+1.18e-01

Pos logit contributions
 valuable+0.024
 may+0.024
 virtue+0.023
 might+0.022
 must+0.022
Neg logit contributions
 ped-0.027
ena-0.026
ila-0.026
ases-0.025
 swinging-0.025
Token She
Token ID1375
Feature activation+5.25e-02

Pos logit contributions
ena+0.009
 ped+0.009
ila+0.008
ases+0.008
okes+0.008
Neg logit contributions
 valuable-0.008
 may-0.007
 virtue-0.007
 must-0.007
 might-0.007
Token had
Token ID550
Feature activation+3.56e-02

Pos logit contributions
 valuable+0.085
 may+0.075
 must+0.071
 might+0.070
 virtue+0.069
Neg logit contributions
 ped-0.107
ena-0.106
ila-0.102
ases-0.100
okes-0.099
Token her
Token ID607
Feature activation-7.70e-02

Pos logit contributions
 valuable+0.063
 may+0.055
 must+0.052
 might+0.052
 virtue+0.052
Neg logit contributions
 ped-0.069
ena-0.068
ila-0.065
ases-0.063
okes-0.063
Token mom
Token ID1995
Feature activation-9.61e-02

Pos logit contributions
 ped+0.138
ena+0.136
ila+0.128
ases+0.126
 swinging+0.126
Neg logit contributions
 valuable-0.138
 may-0.121
 virtue-0.119
 brightly-0.117
 must-0.117
Token and
Token ID290
Feature activation-3.26e-02

Pos logit contributions
 ped+0.164
ena+0.161
ila+0.154
ases+0.149
okes+0.147
Neg logit contributions
 valuable-0.189
 may-0.169
 must-0.163
 might-0.161
 virtue-0.160
Token Cro
Token ID9325
Feature activation-2.41e-01

Pos logit contributions
ases+0.044
ena+0.044
okes+0.044
 ped+0.043
ogged+0.042
Neg logit contributions
 valuable-0.070
 may-0.065
 might-0.064
 must-0.063
 most-0.059
Tokenco
Token ID1073
Feature activation-1.55e-01

Pos logit contributions
 ped+0.290
ena+0.276
ila+0.254
 swinging+0.246
okes+0.243
Neg logit contributions
 valuable-0.582
 might-0.527
 may-0.521
 must-0.517
 virtue-0.511
Token,
Token ID11
Feature activation-3.83e-02

Pos logit contributions
 ped+0.201
ena+0.186
ila+0.182
okes+0.180
ases+0.176
Neg logit contributions
 valuable-0.363
 may-0.322
 might-0.319
 must-0.312
 virtue-0.312
Token and
Token ID290
Feature activation-3.23e-02

Pos logit contributions
ena+0.064
 ped+0.064
okes+0.063
ases+0.063
ogged+0.060
Neg logit contributions
 valuable-0.072
 may-0.066
 might-0.065
 must-0.064
 brightly-0.061
Token that
Token ID326
Feature activation+1.18e-01

Pos logit contributions
ena+0.049
 ped+0.047
okes+0.046
ases+0.045
ila+0.045
Neg logit contributions
 valuable-0.068
 may-0.062
 must-0.060
 might-0.060
 brightly-0.056
Token was
Token ID373
Feature activation-1.16e-02

Pos logit contributions
 valuable+0.203
 may+0.178
 must+0.169
 might+0.167
 virtue+0.163
Neg logit contributions
 ped-0.230
ena-0.229
ila-0.216
ases-0.214
okes-0.213
Token it
Token ID340
Feature activation+8.70e-02

Pos logit contributions
ena+0.080
 ped+0.079
ases+0.077
ila+0.076
okes+0.075
Neg logit contributions
 valuable-0.054
 may-0.046
 must-0.043
 might-0.043
 brightly-0.043
Token started
Token ID2067
Feature activation-2.38e-02

Pos logit contributions
 valuable+0.166
 may+0.146
 virtue+0.141
 must+0.139
 brightly+0.137
Neg logit contributions
 ped-0.156
ena-0.152
ila-0.145
ases-0.139
okes-0.138
Token to
Token ID284
Feature activation-6.08e-02

Pos logit contributions
ena+0.050
 ped+0.049
ila+0.048
ases+0.046
okes+0.045
Neg logit contributions
 valuable-0.038
 may-0.032
 must-0.031
 might-0.031
 virtue-0.031
Token rain
Token ID6290
Feature activation+1.42e-02

Pos logit contributions
ena+0.119
 ped+0.117
ila+0.112
okes+0.111
ases+0.111
Neg logit contributions
 valuable-0.103
 may-0.091
 must-0.087
 might-0.087
 brightly-0.085
Token.
Token ID13
Feature activation+4.44e-03

Pos logit contributions
 valuable+0.031
 may+0.027
 virtue+0.026
 must+0.026
 brightly+0.025
Neg logit contributions
 ped-0.023
ena-0.022
ila-0.020
ases-0.020
 swinging-0.019
Token Cle
Token ID3779
Feature activation-2.35e-01

Pos logit contributions
 valuable+0.007
 may+0.006
 must+0.005
 might+0.005
 virtue+0.005
Neg logit contributions
ena-0.010
 ped-0.010
ila-0.009
ases-0.009
okes-0.009
Tokeno
Token ID78
Feature activation-1.10e-01

Pos logit contributions
 ped+0.337
ases+0.334
ena+0.331
ila+0.321
aster+0.304
Neg logit contributions
 valuable-0.486
 may-0.462
 might-0.451
 must-0.448
 virtue-0.413
Token got
Token ID1392
Feature activation-4.55e-02

Pos logit contributions
ena+0.224
 ped+0.224
ila+0.214
ases+0.213
okes+0.206
Neg logit contributions
 valuable-0.175
 may-0.154
 must-0.149
 might-0.147
 virtue-0.140
Token scared
Token ID12008
Feature activation+8.17e-02

Pos logit contributions
 ped+0.090
ena+0.082
ila+0.081
ases+0.079
 swinging+0.079
Neg logit contributions
 valuable-0.080
 may-0.072
 virtue-0.070
 must-0.065
 might-0.064
Token,
Token ID11
Feature activation-3.59e-02

Pos logit contributions
 valuable+0.202
 may+0.184
 virtue+0.181
 must+0.176
 might+0.174
Neg logit contributions
 ped-0.103
ena-0.098
ila-0.091
ases-0.086
okes-0.085
Token so
Token ID523
Feature activation+1.76e-01

Pos logit contributions
 ped+0.076
ena+0.071
ila+0.069
 swinging+0.066
okes+0.065
Neg logit contributions
 valuable-0.059
 virtue-0.051
 may-0.050
 must-0.046
 brightly-0.046
Token sunshine
Token ID34488
Feature activation+8.74e-02

Pos logit contributions
ena+0.010
 ped+0.010
ila+0.010
ases+0.009
okes+0.009
Neg logit contributions
 valuable-0.007
 may-0.006
 brightly-0.005
 must-0.005
 might-0.005
Token.
Token ID13
Feature activation-1.25e-03

Pos logit contributions
 valuable+0.203
 may+0.180
 virtue+0.178
 must+0.173
 fantastic+0.168
Neg logit contributions
 ped-0.124
ena-0.120
ila-0.109
 swinging-0.107
ases-0.107
Token One
Token ID1881
Feature activation+5.24e-02

Pos logit contributions
ena+0.003
 ped+0.003
ila+0.003
ases+0.003
okes+0.003
Neg logit contributions
 valuable-0.002
 may-0.001
 might-0.001
 must-0.001
 brightly-0.001
Token day
Token ID1110
Feature activation+1.06e-01

Pos logit contributions
 valuable+0.057
 may+0.045
 must+0.041
 virtue+0.041
 might+0.040
Neg logit contributions
 ped-0.137
ena-0.136
ila-0.130
ases-0.128
okes-0.127
Token when
Token ID618
Feature activation+8.99e-02

Pos logit contributions
 valuable+0.193
 may+0.178
 might+0.165
 must+0.163
 brightly+0.163
Neg logit contributions
ena-0.200
ases-0.187
 ped-0.187
ila-0.183
okes-0.176
Token Cle
Token ID3779
Feature activation-2.34e-01

Pos logit contributions
 valuable+0.171
 may+0.152
 must+0.144
 might+0.143
 brightly+0.142
Neg logit contributions
ena-0.160
 ped-0.158
ila-0.150
ases-0.148
okes-0.145
Tokeno
Token ID78
Feature activation-1.10e-01

Pos logit contributions
ases+0.363
ena+0.362
 ped+0.360
ila+0.343
aster+0.326
Neg logit contributions
 may-0.446
 might-0.430
 valuable-0.419
 must-0.419
'll-0.381
Token was
Token ID373
Feature activation-1.53e-02

Pos logit contributions
ena+0.272
ases+0.268
 ped+0.262
ila+0.257
ags+0.256
Neg logit contributions
 may-0.117
 must-0.117
 might-0.115
 valuable-0.109
 should-0.086
Token playing
Token ID2712
Feature activation-3.35e-02

Pos logit contributions
ases+0.026
ena+0.026
els+0.025
ila+0.024
packs+0.024
Neg logit contributions
 valuable-0.025
 most-0.025
 biggest-0.024
 very-0.024
 wonderful-0.023
Token,
Token ID11
Feature activation-3.66e-02

Pos logit contributions
ena+0.058
 ped+0.056
ila+0.053
okes+0.052
ases+0.051
Neg logit contributions
 valuable-0.065
 may-0.059
 must-0.057
 brightly-0.057
 might-0.056
Token it
Token ID340
Feature activation+8.70e-02

Pos logit contributions
ena+0.080
 ped+0.079
ases+0.077
ila+0.076
okes+0.075
Neg logit contributions
 valuable-0.054
 may-0.046
 must-0.043
 might-0.043
 brightly-0.043
Token monkey
Token ID21657
Feature activation-8.38e-02

Pos logit contributions
 valuable+0.113
 may+0.094
 must+0.088
 brightly+0.088
 might+0.085
Neg logit contributions
 ped-0.200
ena-0.197
ila-0.190
ases-0.189
okes-0.186
Token named
Token ID3706
Feature activation-1.08e-01

Pos logit contributions
 ped+0.106
ena+0.105
ila+0.101
ases+0.098
okes+0.096
Neg logit contributions
 valuable-0.195
 may-0.176
 might-0.174
 must-0.173
 brightly-0.169
Token Cle
Token ID3779
Feature activation-2.28e-01

Pos logit contributions
 ped+0.198
ases+0.193
ena+0.191
okes+0.181
ogged+0.181
Neg logit contributions
 valuable-0.198
 may-0.176
 might-0.171
 must-0.170
 brightly-0.161
Tokeno
Token ID78
Feature activation-1.08e-01

Pos logit contributions
ases+0.380
 ped+0.364
okes+0.342
ena+0.338
ogged+0.337
Neg logit contributions
 valuable-0.442
 may-0.416
 might-0.413
 must-0.393
 truly-0.353
Token.
Token ID13
Feature activation-1.72e-03

Pos logit contributions
 ped+0.185
ena+0.184
ila+0.177
ases+0.173
okes+0.171
Neg logit contributions
 valuable-0.207
 may-0.184
 might-0.177
 must-0.177
 virtue-0.174
Token Cle
Token ID3779
Feature activation-2.33e-01

Pos logit contributions
ena+0.003
ila+0.003
ases+0.003
 ped+0.003
okes+0.003
Neg logit contributions
 valuable-0.003
 may-0.003
 might-0.003
 must-0.003
 brightly-0.002
Tokeno
Token ID78
Feature activation-1.10e-01

Pos logit contributions
 ped+0.342
ases+0.337
ena+0.333
ila+0.315
okes+0.311
Neg logit contributions
 valuable-0.485
 may-0.460
 might-0.445
 must-0.441
 virtue-0.402
Token liked
Token ID8288
Feature activation+5.58e-02

Pos logit contributions
 ped+0.232
ena+0.229
ila+0.218
ases+0.212
okes+0.209
Neg logit contributions
 valuable-0.172
 may-0.148
 virtue-0.141
 must-0.139
 brightly-0.137
Token to
Token ID284
Feature activation-6.18e-02

Pos logit contributions
 valuable+0.089
 may+0.076
 must+0.073
 might+0.072
 virtue+0.071
Neg logit contributions
ena-0.116
 ped-0.116
ila-0.111
ases-0.108
okes-0.106
Token play
Token ID711
Feature activation-5.80e-02

Pos logit contributions
ena+0.131
okes+0.124
ila+0.122
ips+0.122
 ped+0.117
Neg logit contributions
 valuable-0.090
 may-0.089
 might-0.085
 must-0.082
 biggest-0.078
Token outside
Token ID2354
Feature activation-1.95e-02

Pos logit contributions
ena+0.106
ila+0.100
 ped+0.099
okes+0.096
ases+0.092
Neg logit contributions
 valuable-0.108
 brightly-0.097
 may-0.096
 must-0.096
 might-0.094
Token and
Token ID290
Feature activation-2.70e-02

Pos logit contributions
 valuable+0.023
 may+0.021
 virtue+0.020
 must+0.020
 might+0.019
Neg logit contributions
 ped-0.017
ena-0.017
ila-0.016
ases-0.016
okes-0.015
Token they
Token ID484
Feature activation+4.59e-02

Pos logit contributions
ena+0.052
 ped+0.051
ila+0.050
ases+0.050
okes+0.048
Neg logit contributions
 valuable-0.046
 may-0.041
 must-0.039
 brightly-0.039
 might-0.039
Token both
Token ID1111
Feature activation+7.75e-02

Pos logit contributions
 valuable+0.083
 may+0.078
 might+0.076
 must+0.076
 brightly+0.074
Neg logit contributions
ena-0.081
ila-0.080
ases-0.078
 ped-0.078
okes-0.077
Token said
Token ID531
Feature activation-1.18e-01

Pos logit contributions
 valuable+0.162
 may+0.151
 might+0.147
 must+0.146
 brightly+0.143
Neg logit contributions
ena-0.116
ila-0.113
 ped-0.111
ases-0.110
okes-0.107
Token "
Token ID366
Feature activation+7.11e-02

Pos logit contributions
 ped+0.226
ena+0.219
ila+0.210
 swinging+0.202
okes+0.201
Neg logit contributions
 valuable-0.202
 virtue-0.177
 may-0.174
 must-0.166
 might-0.166
Tokenche
Token ID2395
Feature activation-2.31e-01

Pos logit contributions
 valuable+0.118
 may+0.103
 must+0.097
 virtue+0.097
 might+0.095
Neg logit contributions
 ped-0.144
ena-0.143
ila-0.135
ases-0.132
okes-0.130
Tokenese
Token ID2771
Feature activation-9.11e-02

Pos logit contributions
 ped+0.303
ena+0.285
ila+0.271
okes+0.254
 swinging+0.247
Neg logit contributions
 valuable-0.543
 may-0.503
 must-0.490
 virtue-0.487
 might-0.481
Token!"
Token ID2474
Feature activation-1.25e-02

Pos logit contributions
ena+0.170
 ped+0.168
ases+0.159
ila+0.159
okes+0.154
Neg logit contributions
 valuable-0.164
 virtue-0.135
 brightly-0.133
 may-0.132
 daunting-0.131
Token at
Token ID379
Feature activation-6.37e-02

Pos logit contributions
 ped+0.025
ena+0.025
ila+0.024
ases+0.023
okes+0.023
Neg logit contributions
 valuable-0.021
 may-0.018
 virtue-0.017
 must-0.017
 might-0.017
Token the
Token ID262
Feature activation-5.53e-04

Pos logit contributions
 ped+0.116
okes+0.110
ases+0.104
ena+0.104
ogged+0.101
Neg logit contributions
 valuable-0.114
 may-0.099
 brightly-0.098
 must-0.098
 most-0.097
Token same
Token ID976
Feature activation+1.00e-01

Pos logit contributions
ena+0.001
 ped+0.001
 swinging+0.001
 Tom+0.001
ila+0.001
Neg logit contributions
 valuable-0.001
 virtue-0.001
 may-0.001
 daunting-0.001
 brightly-0.001
Token she
Token ID673
Feature activation+3.02e-02

Pos logit contributions
 valuable+0.152
 may+0.137
 must+0.132
 might+0.130
 brightly+0.128
Neg logit contributions
ases-0.147
 ped-0.141
ena-0.140
okes-0.138
ila-0.134
Token recognized
Token ID8018
Feature activation-5.21e-02

Pos logit contributions
 valuable+0.056
 may+0.049
 must+0.048
 might+0.047
 virtue+0.046
Neg logit contributions
 ped-0.055
ena-0.054
ila-0.052
ases-0.052
okes-0.051
Token the
Token ID262
Feature activation-1.09e-04

Pos logit contributions
ena+0.092
 ped+0.092
ila+0.087
ases+0.083
okes+0.082
Neg logit contributions
 valuable-0.099
 may-0.088
 virtue-0.086
 must-0.083
 might-0.082
Token word
Token ID1573
Feature activation+3.77e-02

Pos logit contributions
ena+0.000
 ped+0.000
ila+0.000
 swinging+0.000
 Tom+0.000
Neg logit contributions
 valuable-0.000
 may-0.000
 brightly-0.000
 virtue-0.000
 daunting-0.000
Token "
Token ID366
Feature activation+7.07e-02

Pos logit contributions
 valuable+0.077
 may+0.069
 virtue+0.068
 must+0.065
 might+0.065
Neg logit contributions
ena-0.060
 ped-0.059
ila-0.055
ases-0.052
okes-0.052
Tokenche
Token ID2395
Feature activation-2.31e-01

Pos logit contributions
 valuable+0.129
 may+0.114
 must+0.109
 virtue+0.108
 might+0.107
Neg logit contributions
 ped-0.130
ena-0.128
ila-0.121
ases-0.118
okes-0.117
Tokenap
Token ID499
Feature activation-3.01e-02

Pos logit contributions
 ped+0.378
ena+0.346
ila+0.335
 swinging+0.326
okes+0.319
Neg logit contributions
 valuable-0.462
 may-0.425
 virtue-0.418
 must-0.416
 might-0.406
Token"
Token ID1
Feature activation+1.14e-02

Pos logit contributions
ena+0.050
 ped+0.050
ila+0.047
ases+0.046
okes+0.045
Neg logit contributions
 valuable-0.060
 may-0.053
 virtue-0.051
 must-0.050
 might-0.050
Token and
Token ID290
Feature activation-2.77e-02

Pos logit contributions
 valuable+0.024
 may+0.021
 must+0.021
 virtue+0.020
 might+0.020
Neg logit contributions
 ped-0.018
ena-0.018
ila-0.017
ases-0.016
okes-0.016
Token said
Token ID531
Feature activation-1.11e-01

Pos logit contributions
 ped+0.044
ena+0.044
ila+0.042
ases+0.041
okes+0.040
Neg logit contributions
 valuable-0.057
 may-0.052
 must-0.050
 virtue-0.049
 might-0.049
Token,
Token ID11
Feature activation-3.36e-02

Pos logit contributions
 ped+0.177
ena+0.177
ila+0.168
ases+0.159
 swinging+0.158
Neg logit contributions
 valuable-0.225
 may-0.196
 virtue-0.192
 must-0.188
 might-0.188
Token.
Token ID13
Feature activation+5.84e-03

Pos logit contributions
 valuable+0.036
 may+0.034
 might+0.033
 must+0.032
 brightly+0.032
Neg logit contributions
 ped-0.037
ena-0.037
ila-0.035
okes-0.034
ases-0.034
Token It
Token ID632
Feature activation+1.66e-01

Pos logit contributions
 valuable+0.006
 may+0.005
 must+0.004
 might+0.004
 brightly+0.004
Neg logit contributions
 ped-0.015
ena-0.015
ila-0.015
ases-0.014
okes-0.014
Token had
Token ID550
Feature activation+3.64e-02

Pos logit contributions
 valuable+0.241
 may+0.209
 must+0.197
 might+0.196
 brightly+0.190
Neg logit contributions
ena-0.366
 ped-0.366
ila-0.348
ases-0.348
okes-0.341
Token a
Token ID257
Feature activation+3.67e-02

Pos logit contributions
 valuable+0.063
 may+0.053
 must+0.052
 might+0.051
 brightly+0.051
Neg logit contributions
ena-0.071
 ped-0.071
ila-0.067
ases-0.066
okes-0.066
Token shiny
Token ID22441
Feature activation+3.24e-02

Pos logit contributions
 valuable+0.064
 virtue+0.059
 may+0.057
umm+0.056
 must+0.054
Neg logit contributions
 ped-0.068
ena-0.062
ila-0.062
 swinging-0.061
okes-0.057
Token thing
Token ID1517
Feature activation+1.35e-01

Pos logit contributions
 valuable+0.060
 may+0.053
 must+0.051
 virtue+0.050
 brightly+0.050
Neg logit contributions
 ped-0.059
ena-0.059
ila-0.055
ases-0.054
okes-0.053
Token in
Token ID287
Feature activation-5.07e-02

Pos logit contributions
 valuable+0.289
 may+0.260
 must+0.251
 virtue+0.248
 might+0.247
Neg logit contributions
 ped-0.207
ena-0.204
ila-0.191
ases-0.185
okes-0.181
Token its
Token ID663
Feature activation+2.09e-02

Pos logit contributions
 ped+0.092
ena+0.091
ila+0.086
okes+0.085
ases+0.085
Neg logit contributions
 valuable-0.094
 may-0.083
 must-0.080
 might-0.079
 brightly-0.078
Token be
Token ID307
Feature activation-6.06e-02

Pos logit contributions
 valuable+0.044
 may+0.039
 virtue+0.038
 must+0.038
 brightly+0.037
Neg logit contributions
 ped-0.033
ena-0.032
ila-0.030
ases-0.029
okes-0.028
Tokenak
Token ID461
Feature activation+5.05e-03

Pos logit contributions
 ped+0.099
ases+0.089
 elbow+0.089
 Lee+0.086
ena+0.086
Neg logit contributions
 valuable-0.123
 might-0.103
 may-0.098
 must-0.097
 brightly-0.096
Token.
Token ID13
Feature activation+5.27e-03

Pos logit contributions
 valuable+0.009
 may+0.008
 must+0.008
 might+0.008
 brightly+0.008
Neg logit contributions
ena-0.009
 ped-0.009
ila-0.009
ases-0.008
okes-0.008
Token You
Token ID921
Feature activation+6.17e-02

Pos logit contributions
 valuable+0.013
 may+0.012
 must+0.011
 might+0.011
 virtue+0.011
Neg logit contributions
 ped-0.023
ena-0.023
ila-0.022
ases-0.021
okes-0.021
Token can
Token ID460
Feature activation+1.09e-01

Pos logit contributions
 valuable+0.109
 may+0.094
 virtue+0.090
 must+0.089
 brightly+0.089
Neg logit contributions
 ped-0.119
ena-0.117
ila-0.112
ases-0.109
okes-0.107
Token't
Token ID470
Feature activation+3.20e-02

Pos logit contributions
 valuable+0.104
 may+0.104
 must+0.097
 might+0.096
 virtue+0.081
Neg logit contributions
ena-0.278
 ped-0.274
ila-0.265
okes-0.264
ases-0.255
Token sell
Token ID3677
Feature activation-2.96e-02

Pos logit contributions
 must+0.048
 might+0.047
 may+0.046
 valuable+0.045
 should+0.042
Neg logit contributions
ena-0.064
okes-0.063
 ped-0.063
ila-0.059
aj-0.059
Token these
Token ID777
Feature activation+4.06e-02

Pos logit contributions
 ped+0.053
ena+0.052
ila+0.049
ogged+0.047
ases+0.046
Neg logit contributions
 valuable-0.056
 may-0.050
 might-0.049
 must-0.048
 brightly-0.048
Token things
Token ID1243
Feature activation+1.31e-01

Pos logit contributions
 valuable+0.075
 may+0.066
 must+0.063
 virtue+0.062
 might+0.062
Neg logit contributions
 ped-0.075
ena-0.074
ila-0.070
ases-0.068
okes-0.067
Token!"
Token ID2474
Feature activation-1.93e-02

Pos logit contributions
 valuable+0.238
 may+0.209
 must+0.200
 virtue+0.199
 might+0.197
Neg logit contributions
 ped-0.246
ena-0.242
ila-0.229
ases-0.222
okes-0.220
Token she
Token ID673
Feature activation+2.89e-02

Pos logit contributions
 ped+0.034
ena+0.033
ila+0.031
ases+0.031
okes+0.030
Neg logit contributions
 valuable-0.037
 may-0.033
 must-0.032
 might-0.031
 virtue-0.031
Token says
Token ID1139
Feature activation-1.19e-01

Pos logit contributions
 valuable+0.057
 may+0.055
 might+0.055
 must+0.054
 brightly+0.048
Neg logit contributions
 ped-0.045
ena-0.044
ogged-0.042
ases-0.041
aster-0.041
Token.
Token ID13
Feature activation+1.78e-04

Pos logit contributions
 ped+0.246
ena+0.243
ila+0.241
ases+0.235
okes+0.225
Neg logit contributions
 valuable-0.182
 may-0.155
 might-0.151
 brightly-0.150
 must-0.146
Token "
Token ID366
Feature activation+6.62e-02

Pos logit contributions
 valuable+0.000
 may+0.000
 must+0.000
 might+0.000
 brightly+0.000
Neg logit contributions
 ped-0.000
ena-0.000
ases-0.000
ila-0.000
okes-0.000
Token
Token ID198
Feature activation-2.63e-02

Pos logit contributions
 valuable+0.117
 may+0.097
 might+0.093
 must+0.093
 virtue+0.088
Neg logit contributions
 ped-0.206
ena-0.199
ases-0.191
ila-0.189
aster-0.183
Token
Token ID198
Feature activation-2.47e-02

Pos logit contributions
 ped+0.057
ena+0.056
ases+0.054
ila+0.053
okes+0.053
Neg logit contributions
 valuable-0.040
 may-0.033
 must-0.032
 might-0.031
 virtue-0.031
TokenThe
Token ID464
Feature activation+6.04e-02

Pos logit contributions
 ped+0.051
ena+0.050
ila+0.048
ases+0.047
okes+0.046
Neg logit contributions
 valuable-0.040
 may-0.035
 must-0.033
 virtue-0.033
 might-0.032
Token fog
Token ID19558
Feature activation+2.19e-02

Pos logit contributions
 valuable+0.109
 virtue+0.097
 may+0.095
 must+0.090
 daunting+0.089
Neg logit contributions
 ped-0.106
ena-0.102
ila-0.095
 swinging-0.095
ases-0.087
Token was
Token ID373
Feature activation-9.20e-03

Pos logit contributions
 valuable+0.041
 may+0.035
 virtue+0.034
 must+0.033
 brightly+0.032
Neg logit contributions
 ped-0.041
ena-0.040
ila-0.037
ases-0.035
okes-0.035
Token very
Token ID845
Feature activation+1.39e-01

Pos logit contributions
 ped+0.019
ena+0.018
 swinging+0.017
ila+0.017
ases+0.016
Neg logit contributions
 valuable-0.015
 may-0.013
 virtue-0.013
 might-0.012
 must-0.012
Token sp
Token ID599
Feature activation+3.13e-02

Pos logit contributions
 may+0.204
 valuable+0.198
 virtue+0.184
 must+0.181
 might+0.177
Neg logit contributions
 ped-0.278
ena-0.260
ila-0.259
 swinging-0.244
ck-0.232
Tokenooky
Token ID29655
Feature activation+6.92e-02

Pos logit contributions
 valuable+0.046
 may+0.039
 must+0.037
 virtue+0.037
 might+0.036
Neg logit contributions
 ped-0.069
ena-0.069
ila-0.066
ases-0.064
okes-0.064
Token,
Token ID11
Feature activation-3.00e-02

Pos logit contributions
 valuable+0.162
 may+0.148
 virtue+0.147
 might+0.138
 must+0.137
Neg logit contributions
 ped-0.090
ena-0.085
 swinging-0.078
ila-0.072
ases-0.070
Token and
Token ID290
Feature activation-2.31e-02

Pos logit contributions
 ped+0.044
ena+0.041
 swinging+0.039
ila+0.037
 Tom+0.036
Neg logit contributions
 valuable-0.064
 virtue-0.059
 may-0.058
 biggest-0.055
 might-0.053
Token it
Token ID340
Feature activation+8.90e-02

Pos logit contributions
 ped+0.032
ena+0.031
 Tom+0.029
 swinging+0.028
ila+0.028
Neg logit contributions
 valuable-0.050
 virtue-0.046
 may-0.045
 biggest-0.042
idents-0.042
Token
Token ID198
Feature activation-3.32e-02

Pos logit contributions
 valuable+0.122
 may+0.104
 must+0.099
 might+0.098
 virtue+0.094
Neg logit contributions
 ped-0.187
ena-0.182
ases-0.172
ila-0.172
okes-0.167
Token
Token ID198
Feature activation-3.24e-02

Pos logit contributions
 ped+0.074
ena+0.074
ases+0.069
ila+0.068
okes+0.068
Neg logit contributions
 valuable-0.049
 may-0.041
 must-0.039
 might-0.039
 brightly-0.038
TokenS
Token ID50
Feature activation-1.59e-01

Pos logit contributions
ena+0.043
 ped+0.042
ases+0.038
ila+0.037
okes+0.037
Neg logit contributions
 valuable-0.079
 may-0.069
 brightly-0.068
 must-0.067
 virtue-0.067
Tokenally
Token ID453
Feature activation-1.19e-01

Pos logit contributions
 ped+0.306
ena+0.299
ases+0.275
 elbow+0.256
ila+0.256
Neg logit contributions
 valuable-0.297
 may-0.266
 must-0.250
 might-0.246
 brightly-0.245
Token was
Token ID373
Feature activation-1.16e-02

Pos logit contributions
ena+0.242
 ped+0.239
ila+0.235
ases+0.234
okes+0.227
Neg logit contributions
 valuable-0.190
 may-0.170
 must-0.167
 might-0.162
 brightly-0.150
Token very
Token ID845
Feature activation+1.39e-01

Pos logit contributions
 ped+0.027
ena+0.027
ila+0.026
ases+0.025
okes+0.025
Neg logit contributions
 valuable-0.016
 must-0.013
 may-0.012
 might-0.012
 brightly-0.012
Token scared
Token ID12008
Feature activation+8.38e-02

Pos logit contributions
 valuable+0.223
 may+0.185
 must+0.178
 brightly+0.175
 might+0.175
Neg logit contributions
 ped-0.296
ena-0.294
ila-0.277
ases-0.276
okes-0.271
Token.
Token ID13
Feature activation+1.01e-02

Pos logit contributions
 valuable+0.176
 may+0.157
 must+0.151
 virtue+0.151
 might+0.149
Neg logit contributions
 ped-0.134
ena-0.132
ila-0.124
ases-0.120
okes-0.118
Token She
Token ID1375
Feature activation+5.37e-02

Pos logit contributions
 valuable+0.019
 may+0.017
 virtue+0.016
 must+0.016
 might+0.016
Neg logit contributions
 ped-0.018
ena-0.018
ila-0.017
okes-0.016
 swinging-0.016
Token backed
Token ID9763
Feature activation-1.19e-01

Pos logit contributions
 valuable+0.104
 may+0.092
 virtue+0.088
 must+0.088
 might+0.086
Neg logit contributions
 ped-0.094
ena-0.093
ila-0.088
ases-0.085
okes-0.084
Token away
Token ID1497
Feature activation+6.87e-02

Pos logit contributions
ena+0.245
 ped+0.245
ila+0.233
okes+0.230
ases+0.230
Neg logit contributions
 valuable-0.188
 may-0.160
 must-0.159
 might-0.155
 brightly-0.152
Token the
Token ID262
Feature activation+8.74e-04

Pos logit contributions
 ped+0.039
ena+0.038
ila+0.035
 swinging+0.034
ases+0.032
Neg logit contributions
 valuable-0.053
 may-0.048
 virtue-0.048
 must-0.046
 might-0.045
Token children
Token ID1751
Feature activation-1.41e-02

Pos logit contributions
 valuable+0.002
 may+0.002
 virtue+0.002
 must+0.002
 might+0.002
Neg logit contributions
 ped-0.001
ena-0.001
ila-0.001
 swinging-0.001
ases-0.001
Token enjoyed
Token ID8359
Feature activation+3.45e-02

Pos logit contributions
ena+0.027
 ped+0.027
ila+0.026
ases+0.025
okes+0.025
Neg logit contributions
 valuable-0.024
 may-0.022
 must-0.021
 might-0.021
 brightly-0.020
Token them
Token ID606
Feature activation-2.84e-02

Pos logit contributions
 valuable+0.070
 may+0.063
 must+0.060
 virtue+0.060
 might+0.059
Neg logit contributions
 ped-0.057
ena-0.056
ila-0.053
ases-0.051
okes-0.050
Token very
Token ID845
Feature activation+1.40e-01

Pos logit contributions
 ped+0.053
ena+0.052
ila+0.049
ases+0.048
okes+0.047
Neg logit contributions
 valuable-0.051
 may-0.045
 virtue-0.043
 must-0.043
 might-0.043
Token much
Token ID881
Feature activation+1.82e-01

Pos logit contributions
 valuable+0.136
 may+0.115
 must+0.108
 virtue+0.103
 might+0.100
Neg logit contributions
 ped-0.367
ena-0.362
ila-0.355
ases-0.343
okes-0.340
Token.
Token ID13
Feature activation+7.84e-03

Pos logit contributions
 valuable+0.437
 may+0.423
 virtue+0.416
 must+0.416
 might+0.402
Neg logit contributions
 ped-0.181
ena-0.169
ila-0.166
 swinging-0.159
 Tom-0.154
Token
Token ID198
Feature activation-2.73e-02

Pos logit contributions
 valuable+0.014
 may+0.012
 virtue+0.011
 must+0.011
 brightly+0.011
Neg logit contributions
 ped-0.015
ena-0.015
ila-0.014
ases-0.014
okes-0.014
Token
Token ID198
Feature activation-2.57e-02

Pos logit contributions
 ped+0.050
ena+0.049
ases+0.046
ila+0.045
okes+0.045
Neg logit contributions
 valuable-0.051
 may-0.044
 must-0.043
 might-0.042
 virtue-0.041
TokenAfter
Token ID3260
Feature activation+1.07e-01

Pos logit contributions
 ped+0.059
ena+0.058
ila+0.056
ases+0.055
okes+0.055
Neg logit contributions
 valuable-0.036
 may-0.029
 virtue-0.028
 must-0.028
 brightly-0.027
Token they
Token ID484
Feature activation+4.72e-02

Pos logit contributions
 valuable+0.192
 may+0.169
 must+0.161
 virtue+0.160
 might+0.158
Neg logit contributions
 ped-0.201
ena-0.199
ila-0.189
ases-0.183
okes-0.181
Token but
Token ID475
Feature activation+8.23e-02

Pos logit contributions
ena+0.063
 ped+0.062
ases+0.061
ila+0.060
okes+0.058
Neg logit contributions
 valuable-0.064
 may-0.055
 must-0.053
 brightly-0.053
 might-0.052
Token then
Token ID788
Feature activation+4.67e-02

Pos logit contributions
 valuable+0.180
 may+0.161
 virtue+0.157
 must+0.155
 might+0.153
Neg logit contributions
 ped-0.123
ena-0.121
ila-0.114
ases-0.106
okes-0.105
Token she
Token ID673
Feature activation+3.21e-02

Pos logit contributions
 valuable+0.078
 may+0.073
 must+0.068
 brightly+0.067
 might+0.067
Neg logit contributions
ases-0.094
ena-0.092
 ped-0.091
ila-0.087
okes-0.086
Token got
Token ID1392
Feature activation-4.56e-02

Pos logit contributions
 valuable+0.048
 may+0.046
 might+0.046
 must+0.045
 brightly+0.042
Neg logit contributions
ases-0.072
ips-0.064
ags-0.064
ena-0.064
 ped-0.062
Token a
Token ID257
Feature activation+3.55e-02

Pos logit contributions
ena+0.102
 ped+0.096
ila+0.096
ases+0.094
okes+0.092
Neg logit contributions
 valuable-0.071
 must-0.057
 might-0.056
 brightly-0.056
 may-0.055
Token stern
Token ID26370
Feature activation+3.90e-02

Pos logit contributions
 valuable+0.057
 may+0.053
 virtue+0.050
 must+0.049
umm+0.049
Neg logit contributions
 ped-0.067
ena-0.063
ila-0.061
 swinging-0.060
aster-0.057
Token look
Token ID804
Feature activation+4.38e-02

Pos logit contributions
 valuable+0.066
 may+0.057
 must+0.056
 brightly+0.054
 virtue+0.054
Neg logit contributions
 ped-0.077
ena-0.076
ila-0.073
ases-0.073
okes-0.072
Token on
Token ID319
Feature activation-3.68e-02

Pos logit contributions
 valuable+0.088
 may+0.078
 must+0.077
 might+0.074
 brightly+0.073
Neg logit contributions
ena-0.073
 ped-0.071
ases-0.070
okes-0.068
ila-0.068
Token her
Token ID607
Feature activation-8.27e-02

Pos logit contributions
 ped+0.040
ena+0.039
ila+0.036
ases+0.035
okes+0.035
Neg logit contributions
 valuable-0.097
 may-0.088
 must-0.087
 might-0.085
 brightly-0.085
Token face
Token ID1986
Feature activation+1.66e-02

Pos logit contributions
ases+0.136
 ped+0.136
ila+0.133
okes+0.132
ena+0.132
Neg logit contributions
 valuable-0.168
 may-0.147
 brightly-0.141
 might-0.139
 biggest-0.139
Token.
Token ID13
Feature activation+4.71e-03

Pos logit contributions
 valuable+0.034
 may+0.030
 must+0.029
 might+0.029
 brightly+0.029
Neg logit contributions
 ped-0.027
ena-0.027
ila-0.026
ases-0.025
okes-0.024
TokenNo
Token ID2949
Feature activation+2.97e-02

Pos logit contributions
 valuable+0.123
 may+0.106
 virtue+0.100
 must+0.099
 might+0.095
Neg logit contributions
 ped-0.159
ena-0.154
ila-0.149
ases-0.144
okes-0.139
Token,
Token ID11
Feature activation-3.18e-02

Pos logit contributions
 valuable+0.066
 brightly+0.059
 daunting+0.056
 virtue+0.056
 biggest+0.056
Neg logit contributions
 ped-0.043
ena-0.042
ila-0.040
 Tom-0.038
 swinging-0.037
Token Max
Token ID5436
Feature activation-9.78e-02

Pos logit contributions
 ped+0.054
ena+0.054
ila+0.051
 Tom+0.048
 swinging+0.048
Neg logit contributions
 valuable-0.062
 virtue-0.053
 may-0.052
 brightly-0.051
 daunting-0.050
Token!
Token ID0
Feature activation+2.23e-02

Pos logit contributions
 ped+0.154
ena+0.154
ila+0.145
ases+0.138
okes+0.135
Neg logit contributions
 valuable-0.205
 may-0.177
 brightly-0.177
 virtue-0.173
 daunting-0.168
Token Don
Token ID2094
Feature activation+1.21e-02

Pos logit contributions
 valuable+0.032
 may+0.027
 virtue+0.025
 must+0.025
 might+0.025
Neg logit contributions
 ped-0.050
ena-0.050
ila-0.048
ases-0.046
okes-0.046
Token't
Token ID470
Feature activation+3.03e-02

Pos logit contributions
 valuable+0.020
 may+0.016
 virtue+0.016
 brightly+0.016
 must+0.015
Neg logit contributions
 ped-0.025
ena-0.025
ila-0.024
ases-0.023
okes-0.023
Token chase
Token ID15505
Feature activation-1.18e-01

Pos logit contributions
 valuable+0.065
 may+0.057
 virtue+0.056
 brightly+0.055
 must+0.055
Neg logit contributions
 ped-0.047
ena-0.044
ila-0.043
ases-0.042
 swinging-0.042
Token the
Token ID262
Feature activation-4.75e-03

Pos logit contributions
 ped+0.211
ena+0.207
ila+0.198
ases+0.193
okes+0.190
Neg logit contributions
 valuable-0.223
 may-0.197
 virtue-0.189
 must-0.187
 brightly-0.184
Token bird
Token ID6512
Feature activation-3.82e-02

Pos logit contributions
 ped+0.009
ena+0.009
ila+0.009
ases+0.009
okes+0.008
Neg logit contributions
 valuable-0.008
 may-0.007
 virtue-0.007
 must-0.007
 might-0.006
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
 ped+0.067
ena+0.066
ila+0.063
ases+0.062
okes+0.060
Neg logit contributions
 valuable-0.073
 may-0.064
 virtue-0.062
 must-0.061
 brightly-0.061
Token Ask
Token ID16981
Feature activation-1.02e-01

Pos logit contributions
 valuable+0.015
 virtue+0.012
 may+0.012
 brightly+0.012
 fantastic+0.011
Neg logit contributions
ena-0.024
 ped-0.024
ila-0.023
ases-0.022
okes-0.022
Token can
Token ID460
Feature activation+1.18e-01

Pos logit contributions
 valuable+0.209
 brightly+0.182
 virtue+0.181
 may+0.177
 daunting+0.175
Neg logit contributions
 ped-0.241
ena-0.238
ila-0.233
 swinging-0.230
ases-0.225
Token make
Token ID787
Feature activation+2.46e-02

Pos logit contributions
 valuable+0.220
 may+0.193
 virtue+0.187
 must+0.184
 brightly+0.182
Neg logit contributions
 ped-0.212
ena-0.208
ila-0.199
ases-0.193
okes-0.189
Token life
Token ID1204
Feature activation+3.21e-02

Pos logit contributions
 valuable+0.039
 may+0.034
 must+0.032
 virtue+0.032
 might+0.031
Neg logit contributions
 ped-0.052
ena-0.051
ila-0.048
ases-0.047
okes-0.047
Token more
Token ID517
Feature activation+1.31e-01

Pos logit contributions
 valuable+0.048
 virtue+0.045
 may+0.044
 must+0.041
 might+0.041
Neg logit contributions
 ped-0.061
ena-0.060
ases-0.057
ila-0.056
 swinging-0.056
Token enjoyable
Token ID20050
Feature activation+1.20e-01

Pos logit contributions
 valuable+0.200
 may+0.191
 virtue+0.184
 must+0.182
 might+0.180
Neg logit contributions
 ped-0.246
ena-0.238
ila-0.230
 swinging-0.229
ases-0.227
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
 valuable+0.263
 may+0.239
 virtue+0.233
 must+0.229
 might+0.227
Neg logit contributions
 ped-0.169
ena-0.166
ila-0.154
ases-0.152
 swinging-0.146
Token<|endoftext|>
Token ID50256
Feature activation-6.71e-02

Pos logit contributions
 valuable+0.023
 may+0.021
 virtue+0.020
 brightly+0.020
 might+0.020
Neg logit contributions
ena-0.020
 ped-0.020
ila-0.019
ases-0.017
 swinging-0.017
TokenOnce
Token ID7454
Feature activation+1.34e-02

Pos logit contributions
 ped+0.142
ena+0.141
ila+0.132
ases+0.132
okes+0.130
Neg logit contributions
 valuable-0.103
 may-0.092
 must-0.087
 might-0.086
 brightly-0.083
Token upon
Token ID2402
Feature activation+3.36e-02

Pos logit contributions
 valuable+0.026
 may+0.024
 might+0.022
 must+0.022
 brightly+0.022
Neg logit contributions
 ped-0.023
ena-0.023
ases-0.021
ila-0.021
okes-0.020
Token a
Token ID257
Feature activation+2.88e-02

Pos logit contributions
 valuable+0.062
 may+0.055
 virtue+0.053
 must+0.052
 might+0.051
Neg logit contributions
 ped-0.062
ena-0.061
ila-0.058
ases-0.055
okes-0.054
Token time
Token ID640
Feature activation+7.86e-02

Pos logit contributions
 valuable+0.045
 may+0.038
 might+0.036
 must+0.036
 virtue+0.036
Neg logit contributions
 ped-0.062
ena-0.060
ila-0.058
ases-0.058
okes-0.056
Token thought
Token ID1807
Feature activation+2.58e-02

Pos logit contributions
 ped+0.036
ena+0.035
ila+0.032
ases+0.031
okes+0.030
Neg logit contributions
 valuable-0.058
 may-0.052
 virtue-0.050
 must-0.050
 might-0.049
Token about
Token ID546
Feature activation+4.45e-02

Pos logit contributions
 valuable+0.046
 may+0.041
 must+0.039
 virtue+0.039
 might+0.038
Neg logit contributions
 ped-0.049
ena-0.048
ila-0.045
ases-0.044
okes-0.044
Token it
Token ID340
Feature activation+8.78e-02

Pos logit contributions
 valuable+0.087
 may+0.077
 virtue+0.077
 must+0.074
 brightly+0.073
Neg logit contributions
 ped-0.074
ena-0.073
ila-0.069
 swinging-0.065
ases-0.065
Token.
Token ID13
Feature activation+8.42e-03

Pos logit contributions
 valuable+0.200
 virtue+0.182
 may+0.181
 brightly+0.176
 daunting+0.174
Neg logit contributions
ena-0.115
 ped-0.112
ila-0.103
ases-0.098
 swinging-0.096
Token They
Token ID1119
Feature activation+7.76e-02

Pos logit contributions
 valuable+0.012
 may+0.011
 virtue+0.010
 must+0.010
 might+0.010
Neg logit contributions
ena-0.018
 ped-0.018
ila-0.017
ases-0.017
okes-0.017
Token realized
Token ID6939
Feature activation+8.98e-03

Pos logit contributions
 valuable+0.142
 may+0.126
 must+0.121
 might+0.119
 virtue+0.118
Neg logit contributions
 ped-0.142
ena-0.141
ila-0.134
ases-0.132
okes-0.130
Token that
Token ID326
Feature activation+1.21e-01

Pos logit contributions
 valuable+0.011
 may+0.009
 virtue+0.009
 must+0.009
 might+0.009
Neg logit contributions
 ped-0.022
ena-0.021
ila-0.021
ases-0.020
okes-0.020
Token the
Token ID262
Feature activation+3.75e-03

Pos logit contributions
 valuable+0.208
 may+0.181
 must+0.172
 virtue+0.169
 might+0.169
Neg logit contributions
 ped-0.238
ena-0.236
ila-0.225
ases-0.220
okes-0.218
Token lady
Token ID10846
Feature activation-1.21e-01

Pos logit contributions
 valuable+0.007
 may+0.006
 must+0.006
 virtue+0.006
 might+0.006
Neg logit contributions
 ped-0.007
ena-0.007
ila-0.006
ases-0.006
okes-0.006
Token was
Token ID373
Feature activation-1.03e-02

Pos logit contributions
 ped+0.245
ena+0.245
ila+0.231
ases+0.222
okes+0.221
Neg logit contributions
 valuable-0.196
 may-0.166
 virtue-0.166
 brightly-0.160
 must-0.155
Token right
Token ID826
Feature activation-3.20e-02

Pos logit contributions
 ped+0.021
ena+0.020
ila+0.019
ases+0.019
okes+0.019
Neg logit contributions
 valuable-0.018
 may-0.015
 must-0.015
 virtue-0.014
 brightly-0.014
Token
Token ID198
Feature activation-3.05e-02

Pos logit contributions
 ped+0.067
ena+0.065
ases+0.063
okes+0.063
ila+0.062
Neg logit contributions
 valuable-0.047
 may-0.040
 must-0.038
 brightly-0.038
 might-0.038
TokenM
Token ID44
Feature activation-8.56e-02

Pos logit contributions
 ped+0.053
ena+0.052
ila+0.049
ases+0.047
okes+0.046
Neg logit contributions
 valuable-0.060
 may-0.053
 must-0.051
 virtue-0.051
 might-0.050
Tokenama
Token ID1689
Feature activation-8.64e-02

Pos logit contributions
 ped+0.159
ena+0.150
ases+0.144
ila+0.142
okes+0.140
Neg logit contributions
 valuable-0.161
 may-0.140
 brightly-0.137
 virtue-0.135
 must-0.135
Token got
Token ID1392
Feature activation-4.70e-02

Pos logit contributions
ases+0.155
 ped+0.153
ena+0.145
okes+0.144
ila+0.143
Neg logit contributions
 valuable-0.150
 must-0.146
 may-0.141
 might-0.136
 brightly-0.131
Token out
Token ID503
Feature activation-4.40e-02

Pos logit contributions
ena+0.090
 ped+0.090
ila+0.086
ases+0.083
okes+0.083
Neg logit contributions
 valuable-0.083
 must-0.071
 brightly-0.069
 may-0.068
 might-0.068
Token the
Token ID262
Feature activation-2.22e-03

Pos logit contributions
 ped+0.075
ena+0.074
okes+0.072
ila+0.070
ases+0.070
Neg logit contributions
 valuable-0.086
 brightly-0.074
 must-0.073
 may-0.071
 might-0.069
Token jar
Token ID17379
Feature activation+5.02e-02

Pos logit contributions
 ped+0.004
ena+0.004
ila+0.004
ases+0.004
okes+0.004
Neg logit contributions
 valuable-0.004
 may-0.004
 virtue-0.004
 must-0.004
 might-0.004
Token of
Token ID286
Feature activation+4.88e-03

Pos logit contributions
 valuable+0.105
 may+0.093
 must+0.092
 might+0.089
 brightly+0.089
Neg logit contributions
 ped-0.081
ena-0.080
ila-0.075
ases-0.075
okes-0.073
Token jam
Token ID16853
Feature activation+1.37e-03

Pos logit contributions
 valuable+0.011
 may+0.009
 must+0.009
 might+0.009
 brightly+0.009
Neg logit contributions
 ped-0.008
ena-0.007
ila-0.007
ases-0.007
okes-0.007
Token and
Token ID290
Feature activation-2.93e-02

Pos logit contributions
 valuable+0.003
 may+0.003
 must+0.003
 might+0.003
 brightly+0.003
Neg logit contributions
 ped-0.002
ena-0.002
ila-0.002
ases-0.002
okes-0.002
Token spread
Token ID4104
Feature activation-2.49e-02

Pos logit contributions
 ped+0.047
ena+0.047
ases+0.044
ila+0.044
okes+0.042
Neg logit contributions
 valuable-0.060
 may-0.054
 must-0.053
 might-0.052
 brightly-0.052
Token wished
Token ID16555
Feature activation+1.54e-02

Pos logit contributions
 valuable+0.087
 must+0.077
 may+0.076
 might+0.075
 brightly+0.074
Neg logit contributions
ases-0.088
ena-0.087
ila-0.085
 ped-0.085
okes-0.083
Token he
Token ID339
Feature activation+2.40e-02

Pos logit contributions
 valuable+0.022
 may+0.018
 brightly+0.017
 must+0.017
 might+0.017
Neg logit contributions
ena-0.035
 ped-0.035
ases-0.033
ila-0.033
okes-0.033
Token could
Token ID714
Feature activation+8.01e-02

Pos logit contributions
 valuable+0.038
 virtue+0.033
 may+0.030
 brightly+0.030
 biggest+0.030
Neg logit contributions
 ped-0.051
ena-0.048
ila-0.045
 Tom-0.043
 swinging-0.042
Token go
Token ID467
Feature activation-1.51e-01

Pos logit contributions
 valuable+0.171
 may+0.154
 must+0.148
 virtue+0.147
 might+0.146
Neg logit contributions
 ped-0.124
ena-0.123
ila-0.115
ases-0.111
okes-0.110
Token in
Token ID287
Feature activation-5.45e-02

Pos logit contributions
ena+0.272
 ped+0.259
ila+0.250
ases+0.247
okes+0.245
Neg logit contributions
 valuable-0.296
 may-0.256
 must-0.254
 might-0.246
 brightly-0.241
Token,
Token ID11
Feature activation-3.68e-02

Pos logit contributions
ena+0.088
 ped+0.088
ila+0.083
okes+0.081
ases+0.081
Neg logit contributions
 valuable-0.112
 may-0.100
 must-0.098
 might-0.096
 brightly-0.094
Token but
Token ID475
Feature activation+8.03e-02

Pos logit contributions
 ped+0.079
ena+0.077
ila+0.074
ases+0.072
okes+0.071
Neg logit contributions
 valuable-0.057
 may-0.049
 virtue-0.046
 must-0.046
 might-0.045
Token he
Token ID339
Feature activation+2.40e-02

Pos logit contributions
 valuable+0.137
 may+0.117
 virtue+0.115
 must+0.111
 might+0.109
Neg logit contributions
 ped-0.162
ena-0.157
ila-0.148
 swinging-0.142
ases-0.140
Token knew
Token ID2993
Feature activation-1.24e-02

Pos logit contributions
 valuable+0.036
 may+0.031
 must+0.029
 virtue+0.029
 might+0.029
Neg logit contributions
 ped-0.052
ena-0.051
ila-0.049
ases-0.048
okes-0.048
Token that
Token ID326
Feature activation+1.16e-01

Pos logit contributions
 ped+0.028
ena+0.028
ila+0.026
ases+0.026
okes+0.026
Neg logit contributions
 valuable-0.018
 may-0.015
 must-0.014
 might-0.014
 virtue-0.014
Token he
Token ID339
Feature activation+2.38e-02

Pos logit contributions
 valuable+0.201
 may+0.176
 virtue+0.170
 must+0.167
 brightly+0.164
Neg logit contributions
 ped-0.226
ena-0.221
ila-0.210
ases-0.202
okes-0.199
Token Molly
Token ID30236
Feature activation-6.10e-02

Pos logit contributions
 valuable+0.023
 virtue+0.021
 may+0.020
 must+0.019
 brightly+0.019
Neg logit contributions
ena-0.018
ila-0.018
 ped-0.017
okes-0.017
ogged-0.017
Token was
Token ID373
Feature activation-1.32e-02

Pos logit contributions
 ped+0.127
ena+0.125
ila+0.120
ases+0.119
okes+0.117
Neg logit contributions
 valuable-0.096
 may-0.084
 must-0.080
 might-0.078
 virtue-0.078
Token so
Token ID523
Feature activation+1.74e-01

Pos logit contributions
 ped+0.032
ena+0.032
ila+0.030
ases+0.030
okes+0.029
Neg logit contributions
 valuable-0.017
 may-0.014
 virtue-0.013
 must-0.013
 might-0.012
Token excited
Token ID6568
Feature activation+5.56e-02

Pos logit contributions
 valuable+0.348
 may+0.323
 virtue+0.307
 must+0.302
 might+0.301
Neg logit contributions
 ped-0.292
ena-0.287
ila-0.272
 swinging-0.255
ases-0.253
Token!
Token ID0
Feature activation+1.49e-02

Pos logit contributions
 valuable+0.115
 virtue+0.103
 may+0.103
 must+0.096
 brightly+0.095
Neg logit contributions
 ped-0.089
ena-0.088
ila-0.082
 swinging-0.079
okes-0.078
Token
Token ID198
Feature activation-2.95e-02

Pos logit contributions
 valuable+0.028
 may+0.024
 virtue+0.024
 must+0.024
 brightly+0.023
Neg logit contributions
 ped-0.026
ena-0.026
ila-0.025
okes-0.024
ases-0.024
Token
Token ID198
Feature activation-2.90e-02

Pos logit contributions
 ped+0.058
ena+0.057
ila+0.055
ases+0.053
okes+0.052
Neg logit contributions
 valuable-0.050
 may-0.044
 virtue-0.042
 must-0.042
 might-0.041
TokenShe
Token ID3347
Feature activation+4.51e-02

Pos logit contributions
ena+0.049
 ped+0.049
ila+0.048
ases+0.044
 swinging+0.043
Neg logit contributions
 valuable-0.055
 may-0.051
 must-0.048
 virtue-0.048
 might-0.047
Token went
Token ID1816
Feature activation-1.83e-01

Pos logit contributions
 valuable+0.083
 must+0.078
 may+0.076
 might+0.075
 brightly+0.070
Neg logit contributions
ases-0.081
ila-0.077
ena-0.076
okes-0.075
ips-0.074
Token over
Token ID625
Feature activation-6.97e-02

Pos logit contributions
ena+0.381
ila+0.370
 ped+0.369
ases+0.367
okes+0.360
Neg logit contributions
 valuable-0.283
 must-0.239
 may-0.239
 might-0.230
 brightly-0.227
Token and
Token ID290
Feature activation-2.80e-02

Pos logit contributions
 ped+0.148
ena+0.146
ila+0.141
ases+0.139
okes+0.139
Neg logit contributions
 valuable-0.106
 may-0.092
 must-0.090
 brightly-0.089
 might-0.088
Token "
Token ID366
Feature activation+7.15e-02

Pos logit contributions
 ped+0.074
ena+0.074
ila+0.070
ases+0.069
okes+0.068
Neg logit contributions
 valuable-0.052
 may-0.044
 must-0.042
 virtue-0.042
 might-0.041
TokenYes
Token ID5297
Feature activation+2.62e-02

Pos logit contributions
 valuable+0.123
 may+0.109
 must+0.102
 virtue+0.101
 fantastic+0.097
Neg logit contributions
 ped-0.143
ena-0.138
ila-0.134
ases-0.125
aster-0.123
Token,
Token ID11
Feature activation-3.37e-02

Pos logit contributions
 valuable+0.055
 may+0.049
 virtue+0.047
 must+0.047
 brightly+0.046
Neg logit contributions
 ped-0.042
ena-0.041
ila-0.039
ases-0.037
okes-0.037
Token please
Token ID3387
Feature activation+2.22e-02

Pos logit contributions
 ped+0.068
ena+0.068
ila+0.065
ases+0.062
okes+0.062
Neg logit contributions
 valuable-0.055
 may-0.047
 virtue-0.046
 must-0.044
 might-0.043
Token!"
Token ID2474
Feature activation-1.17e-02

Pos logit contributions
 valuable+0.043
 may+0.037
 brightly+0.036
 virtue+0.036
 must+0.035
Neg logit contributions
ena-0.039
 ped-0.038
ila-0.036
ases-0.035
okes-0.034
Token Jane
Token ID12091
Feature activation-6.99e-02

Pos logit contributions
 ped+0.019
ena+0.019
ila+0.017
ases+0.017
okes+0.016
Neg logit contributions
 valuable-0.025
 may-0.022
 virtue-0.022
 must-0.021
 brightly-0.021
Token showed
Token ID3751
Feature activation-7.30e-02

Pos logit contributions
ases+0.129
 ped+0.128
ila+0.127
ena+0.126
okes+0.123
Neg logit contributions
 valuable-0.117
 must-0.112
 may-0.111
 might-0.110
 brightly-0.095
Token Tim
Token ID5045
Feature activation-1.21e-01

Pos logit contributions
 ped+0.115
ena+0.112
ila+0.104
ases+0.098
okes+0.097
Neg logit contributions
 valuable-0.150
 may-0.138
 must-0.135
 might-0.135
 brightly-0.133
Token her
Token ID607
Feature activation-8.28e-02

Pos logit contributions
 ped+0.190
ena+0.190
ila+0.188
ases+0.177
okes+0.176
Neg logit contributions
 valuable-0.251
 may-0.215
 might-0.211
 must-0.210
 brightly-0.202
Token jar
Token ID17379
Feature activation+5.20e-02

Pos logit contributions
 ped+0.162
ena+0.159
ila+0.151
ases+0.148
okes+0.145
Neg logit contributions
 valuable-0.145
 may-0.127
 must-0.121
 virtue-0.120
 might-0.119
Token,
Token ID11
Feature activation-3.28e-02

Pos logit contributions
 valuable+0.101
 may+0.085
 must+0.084
 might+0.083
 brightly+0.081
Neg logit contributions
 ped-0.094
ena-0.092
ila-0.088
ases-0.087
okes-0.086
Token told
Token ID1297
Feature activation-8.07e-02

Pos logit contributions
ases+0.050
okes+0.050
ena+0.048
ips+0.047
els+0.047
Neg logit contributions
 valuable-0.045
 may-0.041
 must-0.041
 might-0.039
 brightly-0.037
Token her
Token ID607
Feature activation-8.24e-02

Pos logit contributions
 ped+0.110
ena+0.110
okes+0.105
ila+0.102
ases+0.099
Neg logit contributions
 valuable-0.190
 brightly-0.168
 may-0.165
 must-0.164
 wonderful-0.158
Token,
Token ID11
Feature activation-3.21e-02

Pos logit contributions
 ped+0.162
ena+0.157
ila+0.149
 swinging+0.142
ases+0.140
Neg logit contributions
 valuable-0.138
 may-0.123
 virtue-0.122
 brightly-0.117
 might-0.116
Token "
Token ID366
Feature activation+7.44e-02

Pos logit contributions
ena+0.078
ases+0.077
 ped+0.075
ila+0.075
okes+0.075
Neg logit contributions
 valuable-0.042
 may-0.034
 must-0.032
 brightly-0.031
 might-0.030
TokenThanks
Token ID9690
Feature activation+5.40e-03

Pos logit contributions
 valuable+0.101
 may+0.083
 virtue+0.079
 brightly+0.079
 must+0.079
Neg logit contributions
 ped-0.171
ena-0.170
ila-0.164
ases-0.162
okes-0.162
Token for
Token ID329
Feature activation-1.58e-02

Pos logit contributions
 valuable+0.012
 may+0.010
 virtue+0.010
 must+0.010
 might+0.010
Neg logit contributions
 ped-0.008
ena-0.008
ila-0.008
ases-0.007
okes-0.007
Token flying
Token ID7348
Feature activation-3.50e-02

Pos logit contributions
ena+0.025
ila+0.024
okes+0.024
 ped+0.024
ases+0.023
Neg logit contributions
 valuable-0.033
 must-0.029
 may-0.029
 virtue-0.028
 might-0.028
Token the
Token ID262
Feature activation+6.98e-04

Pos logit contributions
 ped+0.061
ena+0.060
ila+0.056
ases+0.055
okes+0.054
Neg logit contributions
 valuable-0.068
 may-0.060
 virtue-0.058
 must-0.057
 might-0.057
Token k
Token ID479
Feature activation-1.14e-01

Pos logit contributions
 valuable+0.001
 may+0.001
 virtue+0.001
 must+0.001
 brightly+0.001
Neg logit contributions
 ped-0.001
ena-0.001
ila-0.001
ases-0.001
 swinging-0.001
Tokenite
Token ID578
Feature activation+1.26e-02

Pos logit contributions
ena+0.230
 ped+0.222
ila+0.213
ases+0.204
okes+0.202
Neg logit contributions
 valuable-0.188
 may-0.166
 might-0.159
 must-0.158
 brightly-0.157
Token with
Token ID351
Feature activation-2.67e-02

Pos logit contributions
 valuable+0.024
 may+0.022
 virtue+0.021
 must+0.021
 might+0.020
Neg logit contributions
 ped-0.022
ena-0.021
ila-0.020
ases-0.020
okes-0.019
Token.
Token ID13
Feature activation+1.12e-02

Pos logit contributions
 valuable+0.047
 may+0.043
 must+0.041
 might+0.040
 brightly+0.040
Neg logit contributions
 ped-0.040
ena-0.040
ila-0.038
ases-0.037
okes-0.037
Token From
Token ID3574
Feature activation-3.26e-02

Pos logit contributions
 valuable+0.017
 may+0.015
 must+0.014
 virtue+0.014
 might+0.014
Neg logit contributions
 ped-0.024
ena-0.024
ila-0.023
ases-0.022
okes-0.022
Token that
Token ID326
Feature activation+1.23e-01

Pos logit contributions
 ped+0.070
ena+0.069
ila+0.066
ases+0.062
 swinging+0.062
Neg logit contributions
 valuable-0.051
 may-0.044
 virtue-0.043
 must-0.041
 might-0.041
Token day
Token ID1110
Feature activation+1.11e-01

Pos logit contributions
 valuable+0.161
 may+0.135
 virtue+0.132
 brightly+0.132
 must+0.127
Neg logit contributions
 ped-0.280
ena-0.270
ila-0.260
 swinging-0.258
aster-0.246
Token on
Token ID319
Feature activation-3.23e-02

Pos logit contributions
 valuable+0.210
 may+0.198
 must+0.189
 might+0.183
 brightly+0.176
Neg logit contributions
ena-0.190
 ped-0.180
okes-0.177
ases-0.175
ila-0.174
Token,
Token ID11
Feature activation-2.50e-02

Pos logit contributions
 ped+0.051
ena+0.049
ila+0.047
ases+0.045
okes+0.044
Neg logit contributions
 valuable-0.069
 may-0.061
 virtue-0.060
 must-0.059
 brightly-0.058
Token everyone
Token ID2506
Feature activation+6.61e-03

Pos logit contributions
 ped+0.049
ena+0.049
ila+0.046
ases+0.045
okes+0.044
Neg logit contributions
 valuable-0.043
 may-0.038
 virtue-0.036
 must-0.036
 might-0.035
Token knew
Token ID2993
Feature activation-7.14e-03

Pos logit contributions
 valuable+0.012
 virtue+0.010
 may+0.010
 brightly+0.010
 daunting+0.010
Neg logit contributions
 ped-0.013
ena-0.012
ila-0.012
ases-0.011
 swinging-0.011
Token that
Token ID326
Feature activation+1.22e-01

Pos logit contributions
 ped+0.015
ena+0.014
ila+0.014
 swinging+0.013
ases+0.013
Neg logit contributions
 valuable-0.011
 may-0.010
 virtue-0.010
 must-0.009
 brightly-0.009
Token the
Token ID262
Feature activation+6.44e-03

Pos logit contributions
 valuable+0.222
 may+0.195
 virtue+0.188
 must+0.187
 might+0.183
Neg logit contributions
 ped-0.225
ena-0.220
ila-0.209
ases-0.203
okes-0.199
Token small
Token ID1402
Feature activation+7.03e-02

Pos logit contributions
 valuable+0.009
 may+0.008
 virtue+0.008
 must+0.008
 brightly+0.007
Neg logit contributions
 ped-0.014
ena-0.013
ila-0.013
 swinging-0.013
ases-0.012
Token gathering
Token ID11228
Feature activation-1.96e-03

Pos logit contributions
 ped+0.053
ena+0.052
ila+0.048
ases+0.047
okes+0.046
Neg logit contributions
 valuable-0.071
 may-0.063
 virtue-0.062
 must-0.061
 might-0.060
Token in
Token ID287
Feature activation-5.48e-02

Pos logit contributions
 ped+0.003
ena+0.003
ila+0.003
ases+0.003
 swinging+0.003
Neg logit contributions
 valuable-0.004
 may-0.003
 virtue-0.003
 must-0.003
 might-0.003
Token her
Token ID607
Feature activation-8.31e-02

Pos logit contributions
 ped+0.078
ena+0.077
ila+0.071
ases+0.069
 swinging+0.066
Neg logit contributions
 valuable-0.123
 may-0.112
 virtue-0.109
 must-0.106
 might-0.105
Token garden
Token ID11376
Feature activation+6.00e-02

Pos logit contributions
 ped+0.137
ena+0.134
ila+0.120
 swinging+0.119
ases+0.118
Neg logit contributions
 valuable-0.165
 virtue-0.150
 may-0.145
 must-0.139
 daunting-0.138
Token.
Token ID13
Feature activation+6.06e-03

Pos logit contributions
 valuable+0.121
 may+0.107
 must+0.104
 might+0.103
 virtue+0.102
Neg logit contributions
 ped-0.099
ena-0.098
ila-0.093
ases-0.090
okes-0.089
Token Ab
Token ID2275
Feature activation-2.02e-01

Pos logit contributions
 valuable+0.010
 may+0.009
 virtue+0.008
 must+0.008
 might+0.008
Neg logit contributions
 ped-0.012
ena-0.012
ila-0.012
okes-0.011
ases-0.011
Tokeni
Token ID72
Feature activation-1.18e-01

Pos logit contributions
ena+0.326
 ped+0.318
ases+0.318
aster+0.300
 Tom+0.286
Neg logit contributions
 valuable-0.369
 may-0.366
 might-0.362
 must-0.343
 brightly-0.319
Token smiled
Token ID13541
Feature activation-8.15e-02

Pos logit contributions
ases+0.220
ena+0.216
 ped+0.214
ila+0.212
aster+0.203
Neg logit contributions
 valuable-0.200
 may-0.191
 must-0.188
 might-0.185
 brightly-0.170
Token and
Token ID290
Feature activation-2.81e-02

Pos logit contributions
 ped+0.091
ena+0.085
ila+0.071
 swinging+0.071
okes+0.068
Neg logit contributions
 valuable-0.210
 may-0.196
 virtue-0.195
 must-0.187
 might-0.187
Token said
Token ID531
Feature activation-1.18e-01

Pos logit contributions
ena+0.047
ases+0.045
 ped+0.045
ila+0.044
okes+0.043
Neg logit contributions
 valuable-0.056
 may-0.051
 must-0.049
 might-0.048
 brightly-0.048
Token,
Token ID11
Feature activation-3.19e-02

Pos logit contributions
 ped+0.169
ena+0.161
ila+0.154
 swinging+0.145
okes+0.145
Neg logit contributions
 valuable-0.260
 virtue-0.233
 may-0.232
 must-0.224
 might-0.223
Token
Token ID198
Feature activation-4.32e-02

Pos logit contributions
 ped+0.110
ena+0.106
ases+0.103
okes+0.100
ila+0.099
Neg logit contributions
 valuable-0.056
 may-0.042
 might-0.040
 must-0.039
 virtue-0.037
Token"
Token ID1
Feature activation+2.19e-03

Pos logit contributions
 ped+0.089
ena+0.087
ases+0.085
okes+0.085
ila+0.081
Neg logit contributions
 valuable-0.069
 virtue-0.055
 may-0.055
 brightly-0.054
 might-0.053
TokenMaybe
Token ID13300
Feature activation+6.73e-02

Pos logit contributions
 valuable+0.003
 may+0.003
 must+0.003
 virtue+0.003
 might+0.003
Neg logit contributions
 ped-0.005
ena-0.005
ila-0.004
ases-0.004
okes-0.004
Token we
Token ID356
Feature activation+4.29e-03

Pos logit contributions
 valuable+0.078
 may+0.068
 might+0.063
 brightly+0.062
 must+0.060
Neg logit contributions
 ped-0.171
ena-0.164
ases-0.159
ogged-0.155
okes-0.154
Token can
Token ID460
Feature activation+1.07e-01

Pos logit contributions
 valuable+0.005
 brightly+0.004
 virtue+0.003
 daunting+0.003
 biggest+0.003
Neg logit contributions
 ped-0.011
ena-0.011
ila-0.010
ases-0.010
okes-0.010
Token come
Token ID1282
Feature activation-1.49e-01

Pos logit contributions
 valuable+0.224
 may+0.199
 virtue+0.192
 must+0.191
 brightly+0.188
Neg logit contributions
 ped-0.173
ena-0.170
ila-0.160
ases-0.156
okes-0.153
Token back
Token ID736
Feature activation-6.69e-02

Pos logit contributions
 ped+0.283
ena+0.277
ila+0.267
okes+0.254
ases+0.253
Neg logit contributions
 valuable-0.262
 may-0.232
 brightly-0.228
 must-0.226
 might-0.221
Token tomorrow
Token ID9439
Feature activation+3.93e-02

Pos logit contributions
 ped+0.128
ena+0.119
ila+0.114
ases+0.113
okes+0.112
Neg logit contributions
 valuable-0.119
 may-0.104
 must-0.104
 brightly-0.103
 might-0.102
Token and
Token ID290
Feature activation-3.70e-02

Pos logit contributions
 valuable+0.074
 may+0.065
 must+0.064
 might+0.063
 brightly+0.063
Neg logit contributions
 ped-0.070
ena-0.068
ila-0.065
ases-0.064
okes-0.063
Token play
Token ID711
Feature activation-5.96e-02

Pos logit contributions
 ped+0.056
ena+0.055
ila+0.051
ases+0.050
okes+0.049
Neg logit contributions
 valuable-0.080
 may-0.072
 virtue-0.069
 must-0.069
 might-0.068
Token again
Token ID757
Feature activation-1.94e-03

Pos logit contributions
 ped+0.103
ena+0.101
ila+0.094
okes+0.091
ases+0.090
Neg logit contributions
 valuable-0.117
 may-0.104
 brightly-0.102
 must-0.101
 might-0.099
Token with
Token ID351
Feature activation-2.56e-02

Pos logit contributions
 ped+0.281
ena+0.278
ila+0.265
ases+0.257
okes+0.252
Neg logit contributions
 valuable-0.313
 may-0.277
 must-0.265
 brightly-0.264
 virtue-0.261
Token joy
Token ID8716
Feature activation+5.10e-02

Pos logit contributions
 ped+0.052
ena+0.051
ases+0.048
ila+0.048
 swinging+0.047
Neg logit contributions
 valuable-0.042
 may-0.037
 virtue-0.037
 might-0.034
 must-0.034
Token as
Token ID355
Feature activation+1.05e-01

Pos logit contributions
 valuable+0.108
 may+0.096
 virtue+0.093
 must+0.092
 might+0.090
Neg logit contributions
 ped-0.081
ena-0.080
ila-0.074
ases-0.072
okes-0.071
Token the
Token ID262
Feature activation+1.41e-03

Pos logit contributions
 valuable+0.191
 may+0.168
 virtue+0.160
 must+0.160
 might+0.157
Neg logit contributions
 ped-0.195
ena-0.192
ila-0.183
ases-0.177
okes-0.174
Token plane
Token ID6614
Feature activation+1.37e-02

Pos logit contributions
 valuable+0.003
 virtue+0.002
 may+0.002
 must+0.002
 might+0.002
Neg logit contributions
 ped-0.003
ena-0.003
ila-0.002
 swinging-0.002
ases-0.002
Token flew
Token ID13112
Feature activation-1.44e-01

Pos logit contributions
 valuable+0.029
 may+0.027
 must+0.026
 might+0.026
 brightly+0.025
Neg logit contributions
ena-0.021
 ped-0.020
ila-0.019
ases-0.019
okes-0.019
Token sharp
Token ID7786
Feature activation+8.83e-03

Pos logit contributions
 ped+0.245
ena+0.230
ila+0.220
ases+0.214
 swinging+0.213
Neg logit contributions
 valuable-0.287
 may-0.254
 virtue-0.252
 must-0.236
 might-0.232
Token in
Token ID287
Feature activation-5.33e-02

Pos logit contributions
 valuable+0.018
 may+0.016
 virtue+0.016
 must+0.016
 might+0.015
Neg logit contributions
 ped-0.014
ena-0.014
ila-0.013
ases-0.013
okes-0.013
Token the
Token ID262
Feature activation+1.17e-03

Pos logit contributions
 ped+0.078
ena+0.077
ila+0.072
ases+0.069
okes+0.068
Neg logit contributions
 valuable-0.119
 may-0.107
 must-0.103
 virtue-0.103
 might-0.102
Token sky
Token ID6766
Feature activation+9.85e-02

Pos logit contributions
 valuable+0.002
 virtue+0.002
 may+0.002
idents+0.002
 must+0.002
Neg logit contributions
 ped-0.002
ena-0.002
ila-0.002
 swinging-0.002
ogged-0.002
Token.
Token ID13
Feature activation+1.18e-02

Pos logit contributions
 valuable+0.211
 may+0.189
 virtue+0.183
 must+0.180
 might+0.177
Neg logit contributions
 ped-0.152
ena-0.149
ila-0.139
ases-0.134
okes-0.131
Token eating
Token ID6600
Feature activation-2.79e-02

Pos logit contributions
 ped+0.016
ena+0.016
ila+0.015
ases+0.014
okes+0.014
Neg logit contributions
 valuable-0.026
 may-0.024
 must-0.023
 might-0.023
 virtue-0.023
Token his
Token ID465
Feature activation-7.17e-02

Pos logit contributions
 ped+0.047
ena+0.046
ila+0.045
ases+0.044
okes+0.042
Neg logit contributions
 valuable-0.054
 may-0.048
 virtue-0.047
 must-0.046
 might-0.045
Token plants
Token ID6134
Feature activation+1.96e-02

Pos logit contributions
 ped+0.139
ena+0.138
ila+0.132
ases+0.129
okes+0.127
Neg logit contributions
 valuable-0.121
 may-0.105
 virtue-0.103
 must-0.100
 brightly-0.098
Token.
Token ID13
Feature activation+7.78e-03

Pos logit contributions
 valuable+0.044
 may+0.040
 virtue+0.039
 must+0.038
 brightly+0.038
Neg logit contributions
 ped-0.027
ena-0.026
ila-0.025
 swinging-0.024
ases-0.024
Token He
Token ID679
Feature activation+4.54e-02

Pos logit contributions
 valuable+0.013
 may+0.011
 virtue+0.011
 must+0.010
 brightly+0.010
Neg logit contributions
 ped-0.016
ena-0.016
ila-0.015
okes-0.015
ases-0.014
Token took
Token ID1718
Feature activation-1.41e-01

Pos logit contributions
 valuable+0.074
 might+0.064
 must+0.063
 may+0.063
 brightly+0.059
Neg logit contributions
ases-0.092
ena-0.091
 ped-0.090
okes-0.087
ips-0.087
Token a
Token ID257
Feature activation+3.19e-02

Pos logit contributions
 ped+0.229
ena+0.226
ila+0.213
ases+0.206
okes+0.203
Neg logit contributions
 valuable-0.288
 may-0.257
 virtue-0.247
 must-0.247
 might-0.243
Token mighty
Token ID18680
Feature activation+7.00e-02

Pos logit contributions
 valuable+0.057
 virtue+0.052
 may+0.051
 brightly+0.049
 must+0.048
Neg logit contributions
 ped-0.056
ena-0.054
ila-0.053
 swinging-0.051
okes-0.050
Token can
Token ID460
Feature activation+1.18e-01

Pos logit contributions
 valuable+0.126
 may+0.111
 virtue+0.106
 must+0.106
 might+0.104
Neg logit contributions
 ped-0.130
ena-0.128
ila-0.122
ases-0.118
okes-0.117
Token and
Token ID290
Feature activation-2.78e-02

Pos logit contributions
 valuable+0.228
 must+0.204
 may+0.204
 might+0.200
 brightly+0.188
Neg logit contributions
 ped-0.203
ena-0.193
ila-0.181
okes-0.179
ases-0.173
Token sprayed
Token ID35729
Feature activation-5.69e-03

Pos logit contributions
 ped+0.044
ena+0.043
ila+0.040
ases+0.038
okes+0.038
Neg logit contributions
 valuable-0.059
 may-0.053
 virtue-0.051
 must-0.050
 brightly-0.050
Token to
Token ID284
Feature activation-6.25e-02

Pos logit contributions
ila+0.043
ena+0.043
ases+0.040
 ped+0.040
okes+0.039
Neg logit contributions
 valuable-0.042
 must-0.035
 may-0.035
 might-0.034
 brightly-0.034
Token draw
Token ID3197
Feature activation-6.75e-02

Pos logit contributions
ena+0.102
 ped+0.100
ila+0.100
okes+0.095
ases+0.095
Neg logit contributions
 valuable-0.125
 may-0.116
 must-0.112
 might-0.110
 brightly-0.108
Token pictures
Token ID5986
Feature activation+4.20e-02

Pos logit contributions
 ped+0.121
ena+0.119
ila+0.113
ases+0.110
okes+0.109
Neg logit contributions
 valuable-0.128
 may-0.113
 must-0.108
 brightly-0.107
 might-0.106
Token.
Token ID13
Feature activation+7.71e-03

Pos logit contributions
 valuable+0.087
 may+0.077
 must+0.075
 virtue+0.074
 might+0.073
Neg logit contributions
 ped-0.068
ena-0.067
ila-0.063
ases-0.061
okes-0.060
Token She
Token ID1375
Feature activation+5.32e-02

Pos logit contributions
 valuable+0.013
 may+0.011
 virtue+0.011
 must+0.011
 might+0.010
Neg logit contributions
 ped-0.016
ena-0.015
ila-0.015
ases-0.014
okes-0.014
Token stepped
Token ID10764
Feature activation-1.75e-01

Pos logit contributions
 valuable+0.092
 must+0.084
 might+0.083
 may+0.083
 brightly+0.078
Neg logit contributions
ases-0.097
ila-0.096
 ped-0.094
ena-0.094
okes-0.093
Token outside
Token ID2354
Feature activation-1.84e-02

Pos logit contributions
ena+0.281
 ped+0.280
ila+0.266
ases+0.257
okes+0.253
Neg logit contributions
 valuable-0.365
 may-0.325
 must-0.317
 brightly-0.317
 might-0.308
Token and
Token ID290
Feature activation-2.56e-02

Pos logit contributions
 ped+0.027
ena+0.027
ila+0.027
okes+0.026
ases+0.026
Neg logit contributions
 valuable-0.039
 may-0.035
 brightly-0.035
 must-0.035
 might-0.034
Token saw
Token ID2497
Feature activation-5.55e-02

Pos logit contributions
ena+0.044
 ped+0.044
ila+0.043
ases+0.043
okes+0.041
Neg logit contributions
 valuable-0.048
 may-0.044
 must-0.043
 might-0.042
 brightly-0.042
Token some
Token ID617
Feature activation+6.30e-02

Pos logit contributions
ena+0.099
 ped+0.098
ila+0.093
ases+0.090
 swinging+0.089
Neg logit contributions
 valuable-0.105
 may-0.095
 virtue-0.093
 must-0.088
 might-0.087
Token beautiful
Token ID4950
Feature activation+1.18e-01

Pos logit contributions
 valuable+0.102
 virtue+0.090
 may+0.090
 must+0.084
 might+0.082
Neg logit contributions
 ped-0.126
ena-0.125
ila-0.119
ases-0.115
 swinging-0.114