TOP ACTIVATIONS
MAX = 0.505

on her finger and adm ires it . She feels like
Tom says . He adm ires the puzzle . He thinks
Mia says . She adm ires the puzzle too . She
careful next time . W ires can be dangerous . I
told Fin that he adm ires how brave he is .
, green apple . Y um ! He
. " M um ! Look at this tree
hat . M um asked the priest , "
. " Y um ! This pizza is delicious
asked . M um thought for a minute ,
dog food . " Y um , this is delicious !"
him fly . <|endoftext|> M um and Dad had a new
. " M um , what are these ?"
time to eat . Y um ! It was the best
look ." M um went outside , and found
. " Y um , y um , these
. " Y um !" she exclaimed with delight
her mum , " M um , why do I feel
that day . <|endoftext|> M um woke up early . She
down the street , adm iring the big billboard ahead .

MIN ACTIVATIONS
MIN = -0.561

, the King was over joy ed . He put on
him . Moe was over joy ed to see them again
noises . Lucy was over joy ed and promised to keep
player ! Emily was over joy ed as she recorded the
happy . She was over joy ed that her pet was
. O lly was over joy ed with his prize ,
Jack was over joy ed . He had conquered
happen . Jane was over joy ed , and thanked Pixie
The oct opus was over joy ed , and he thanked
rocket 's friends were over joy ed to have him back
Cl aire was over joy ed - her mug had
. The princess was over joy ed ! She was so
rock . Lily was over joy ed and knew it was
't help but feel over joy ed . He felt so
win . Jane was over joy ed ! <|endoftext|> Once upon
S ally was so over joy ed with her present that
park ! He was over joy ed . He thanked the
L illy was over joy ed and felt so lucky
beach , Maggie was over joy ed . She jumped in
mountain . He was over joy ed . He looked back

INTERVAL 0.239 - 0.505
CONTAINS 1.157%

, she decided to tidy up her room . She put
know . It looks really unusual !" John decided
pour . The milk bub bled and ste amed as it
The old man walked up to the child and asked
leash . Do you understand ?" uncle Ben said .

INTERVAL -0.028 - 0.239
CONTAINS 64.866%

help from others to learn new things . And if we
her special object . She was very proud of herself .
, Jack and Jane decided to play a game . Jane
Lily asked her mom what it was for . " It
your doll . Go away !" Ben said . He was

INTERVAL -0.295 - -0.028
CONTAINS 33.656%

of singing and dancing on the stage . The theater was
milk and poured it over the cereal . They
. They had a fun day at the park with the
They both went back down the hill , happy with their
friends . They had been having so much fun .

INTERVAL -0.561 - -0.295
CONTAINS 0.321%

realized that being fair meant being balanced and that it was
distance . Everyone was over joy ed that the cow had
wind is just singing a lull aby to help you sleep
Mom hugged her back and forg ave her .
" Why are you crying ?" she asks . "
Token on
Token ID319
Feature activation-9.35e-02

Pos logit contributions
joy+0.031
ez+0.030
hered+0.027
 nightmares+0.026
 moment+0.025
Neg logit contributions
ires-0.030
ate-0.028
iring-0.028
um-0.028
ruce-0.026
Token her
Token ID607
Feature activation-3.79e-02

Pos logit contributions
joy+0.202
ez+0.195
hered+0.173
 nightmares+0.166
 moment+0.160
Neg logit contributions
ires-0.141
um-0.138
ate-0.136
iring-0.130
ruce-0.115
Token finger
Token ID7660
Feature activation-6.27e-02

Pos logit contributions
joy+0.081
ez+0.078
hered+0.070
 nightmares+0.066
 moment+0.064
Neg logit contributions
ires-0.058
um-0.055
ate-0.055
iring-0.053
ruce-0.047
Token and
Token ID290
Feature activation-3.95e-02

Pos logit contributions
joy+0.121
ez+0.115
hered+0.104
 nightmares+0.098
 moment+0.096
Neg logit contributions
ires-0.108
ate-0.102
iring-0.102
um-0.101
ruce-0.091
Token adm
Token ID6178
Feature activation-5.60e-02

Pos logit contributions
joy+0.077
ez+0.073
hered+0.067
 nightmares+0.062
 moment+0.062
Neg logit contributions
ires-0.067
ate-0.064
um-0.063
iring-0.062
ruce-0.056
Tokenires
Token ID2387
Feature activation+4.89e-01

Pos logit contributions
joy+0.131
ez+0.123
 nightmares+0.116
ymes+0.113
ching+0.111
Neg logit contributions
 First-0.051
 stack-0.043
 bury-0.041
 Inside-0.038
lly-0.036
Token it
Token ID340
Feature activation-1.72e-02

Pos logit contributions
ires+0.645
ate+0.577
iring+0.557
um+0.553
 Inside+0.486
Neg logit contributions
joy-1.138
ez-1.106
hered-1.084
oing-0.955
 moment-0.940
Token.
Token ID13
Feature activation-7.76e-03

Pos logit contributions
joy+0.035
ez+0.034
hered+0.031
 nightmares+0.029
 moment+0.028
Neg logit contributions
ires-0.028
ate-0.026
iring-0.026
um-0.026
ruce-0.023
Token She
Token ID1375
Feature activation+5.36e-02

Pos logit contributions
joy+0.015
ez+0.014
hered+0.013
 nightmares+0.012
 moment+0.012
Neg logit contributions
ires-0.013
iring-0.013
ate-0.012
um-0.012
ruce-0.011
Token feels
Token ID5300
Feature activation-8.79e-02

Pos logit contributions
iring+0.110
ires+0.107
um+0.105
ate+0.099
ruce+0.097
Neg logit contributions
ez-0.082
joy-0.081
 nightmares-0.070
hered-0.065
 heaven-0.065
Token like
Token ID588
Feature activation+6.83e-02

Pos logit contributions
joy+0.178
ez+0.170
hered+0.159
 moment+0.145
 nightmares+0.145
Neg logit contributions
ires-0.144
ate-0.136
iring-0.134
um-0.132
ruce-0.118
Token Tom
Token ID4186
Feature activation+5.56e-02

Pos logit contributions
iring+0.180
ate+0.176
ires+0.173
um+0.161
ruce+0.161
Neg logit contributions
joy-0.121
ez-0.110
 nightmares-0.103
 moment-0.098
 pain-0.098
Token says
Token ID1139
Feature activation+1.50e-01

Pos logit contributions
ires+0.087
iring+0.082
um+0.080
ate+0.080
ruce+0.072
Neg logit contributions
joy-0.116
ez-0.113
hered-0.102
 nightmares-0.098
 moment-0.095
Token.
Token ID13
Feature activation-6.87e-03

Pos logit contributions
ires+0.212
um+0.204
ate+0.196
iring+0.195
ruce+0.166
Neg logit contributions
joy-0.333
ez-0.329
hered-0.293
Charl-0.285
 nightmares-0.280
Token He
Token ID679
Feature activation+6.38e-02

Pos logit contributions
joy+0.014
ez+0.013
hered+0.012
 nightmares+0.011
 moment+0.011
Neg logit contributions
ires-0.011
ate-0.011
iring-0.011
um-0.011
ruce-0.010
Token adm
Token ID6178
Feature activation-6.44e-02

Pos logit contributions
ires+0.121
iring+0.118
um+0.115
ate+0.113
ruce+0.105
Neg logit contributions
joy-0.111
ez-0.105
hered-0.094
 nightmares-0.088
 moment-0.085
Tokenires
Token ID2387
Feature activation+4.83e-01

Pos logit contributions
joy+0.152
 nightmares+0.135
ymes+0.134
ez+0.133
 asleep+0.130
Neg logit contributions
 First-0.057
lly-0.043
 replied-0.040
 lined-0.039
 Inside-0.038
Token the
Token ID262
Feature activation-3.71e-02

Pos logit contributions
ires+0.710
ate+0.647
iring+0.630
um+0.624
ruce+0.538
Neg logit contributions
ez-1.074
joy-1.071
hered-1.014
 moment-0.899
Charl-0.889
Token puzzle
Token ID15027
Feature activation-1.71e-01

Pos logit contributions
ez+0.071
joy+0.069
hered+0.061
Charl+0.055
smart+0.054
Neg logit contributions
ires-0.068
ate-0.064
um-0.063
iring-0.062
ruce-0.058
Token.
Token ID13
Feature activation-7.04e-03

Pos logit contributions
joy+0.362
ez+0.347
hered+0.315
 nightmares+0.294
Charl+0.284
Neg logit contributions
ires-0.270
ate-0.256
um-0.250
iring-0.249
ruce-0.222
Token He
Token ID679
Feature activation+6.31e-02

Pos logit contributions
joy+0.013
ez+0.012
hered+0.011
 moment+0.010
 nightmares+0.010
Neg logit contributions
ires-0.013
iring-0.012
um-0.012
ate-0.012
ruce-0.011
Token thinks
Token ID6834
Feature activation-8.07e-03

Pos logit contributions
ires+0.122
iring+0.121
um+0.118
ate+0.114
ruce+0.108
Neg logit contributions
joy-0.106
ez-0.099
hered-0.087
 nightmares-0.084
 moment-0.080
Token Mia
Token ID32189
Feature activation+3.82e-02

Pos logit contributions
ires+0.163
iring+0.161
ate+0.155
um+0.150
ruce+0.143
Neg logit contributions
joy-0.150
ez-0.135
 moment-0.125
 nightmares-0.120
hered-0.119
Token says
Token ID1139
Feature activation+1.49e-01

Pos logit contributions
ires+0.050
iring+0.047
ate+0.046
um+0.045
ruce+0.040
Neg logit contributions
joy-0.090
ez-0.086
hered-0.080
 nightmares-0.076
 moment-0.075
Token.
Token ID13
Feature activation-6.97e-03

Pos logit contributions
ires+0.185
um+0.179
iring+0.166
ate+0.162
outed+0.139
Neg logit contributions
ez-0.356
joy-0.348
Charl-0.316
 nightmares-0.308
hered-0.308
Token She
Token ID1375
Feature activation+5.14e-02

Pos logit contributions
joy+0.015
ez+0.015
hered+0.013
 nightmares+0.013
 moment+0.012
Neg logit contributions
ires-0.011
um-0.010
iring-0.010
ate-0.010
ruce-0.009
Token adm
Token ID6178
Feature activation-6.52e-02

Pos logit contributions
ires+0.101
iring+0.098
um+0.096
ate+0.094
ruce+0.088
Neg logit contributions
joy-0.087
ez-0.081
hered-0.072
 nightmares-0.068
 moment-0.066
Tokenires
Token ID2387
Feature activation+4.82e-01

Pos logit contributions
joy+0.154
ymes+0.136
 nightmares+0.136
ez+0.135
 asleep+0.130
Neg logit contributions
 First-0.058
lly-0.046
 bury-0.041
 lined-0.041
 replied-0.040
Token the
Token ID262
Feature activation-3.76e-02

Pos logit contributions
ires+0.727
ate+0.662
iring+0.650
um+0.648
ruce+0.565
Neg logit contributions
joy-1.053
ez-1.046
hered-0.982
 moment-0.876
 nightmares-0.861
Token puzzle
Token ID15027
Feature activation-1.71e-01

Pos logit contributions
ez+0.072
joy+0.070
hered+0.061
Charl+0.056
 nightmares+0.056
Neg logit contributions
ires-0.069
ate-0.065
um-0.064
iring-0.063
ruce-0.058
Token too
Token ID1165
Feature activation-5.23e-02

Pos logit contributions
joy+0.366
ez+0.351
hered+0.319
 nightmares+0.298
Charl+0.288
Neg logit contributions
ires-0.269
ate-0.256
um-0.250
iring-0.248
ruce-0.221
Token.
Token ID13
Feature activation-6.91e-03

Pos logit contributions
joy+0.103
ez+0.099
hered+0.089
 nightmares+0.084
 moment+0.082
Neg logit contributions
ires-0.089
ate-0.084
iring-0.084
um-0.083
ruce-0.074
Token She
Token ID1375
Feature activation+5.09e-02

Pos logit contributions
joy+0.013
ez+0.012
hered+0.011
 nightmares+0.010
 moment+0.010
Neg logit contributions
ires-0.012
iring-0.011
ate-0.011
um-0.011
ruce-0.010
Token careful
Token ID8161
Feature activation-6.09e-03

Pos logit contributions
joy+0.004
ez+0.004
hered+0.004
 nightmares+0.003
 moment+0.003
Neg logit contributions
ires-0.003
ate-0.003
iring-0.003
um-0.003
ruce-0.002
Token next
Token ID1306
Feature activation+8.88e-02

Pos logit contributions
joy+0.013
ez+0.012
hered+0.011
 nightmares+0.010
 moment+0.010
Neg logit contributions
ires-0.010
iring-0.009
ate-0.009
um-0.009
ruce-0.008
Token time
Token ID640
Feature activation-7.40e-02

Pos logit contributions
um+0.128
ires+0.127
ate+0.124
iring+0.117
ruce+0.106
Neg logit contributions
joy-0.187
ez-0.180
hered-0.169
Charl-0.153
 heaven-0.150
Token.
Token ID13
Feature activation-1.86e-02

Pos logit contributions
joy+0.158
ez+0.153
hered+0.136
 nightmares+0.130
 moment+0.127
Neg logit contributions
ires-0.112
ate-0.107
um-0.106
iring-0.104
ruce-0.090
Token W
Token ID370
Feature activation-8.83e-02

Pos logit contributions
joy+0.039
ez+0.037
hered+0.035
 nightmares+0.033
 moment+0.032
Neg logit contributions
ires-0.028
ate-0.027
um-0.027
iring-0.026
 Inside-0.024
Tokenires
Token ID2387
Feature activation+4.78e-01

Pos logit contributions
ez+0.195
joy+0.193
hered+0.165
 nightmares+0.164
 failure+0.160
Neg logit contributions
iring-0.117
ires-0.115
ate-0.112
um-0.109
ruce-0.100
Token can
Token ID460
Feature activation-1.97e-02

Pos logit contributions
ires+0.742
ate+0.716
um+0.691
iring+0.672
ruce+0.618
Neg logit contributions
joy-1.035
ez-0.896
hered-0.856
 moment-0.792
 knowing-0.778
Token be
Token ID307
Feature activation+4.94e-02

Pos logit contributions
ez+0.036
joy+0.034
hered+0.033
 nightmares+0.031
 moment+0.030
Neg logit contributions
ires-0.035
iring-0.032
um-0.031
ate-0.031
outed-0.028
Token dangerous
Token ID4923
Feature activation+3.17e-02

Pos logit contributions
ate+0.069
ires+0.068
iring+0.064
um+0.064
her+0.058
Neg logit contributions
joy-0.107
ez-0.098
hered-0.097
 moment-0.088
 nightmares-0.087
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
ires+0.046
iring+0.044
ate+0.043
um+0.042
ruce+0.036
Neg logit contributions
joy-0.069
ez-0.067
hered-0.062
 moment-0.056
Charl-0.056
Token I
Token ID314
Feature activation+2.60e-02

Pos logit contributions
joy+0.035
ez+0.033
hered+0.030
 moment+0.028
 nightmares+0.028
Neg logit contributions
ires-0.029
ate-0.027
um-0.027
iring-0.026
 Inside-0.024
Token told
Token ID1297
Feature activation+5.01e-02

Pos logit contributions
ires+0.002
ate+0.002
um+0.002
iring+0.002
ruce+0.002
Neg logit contributions
joy-0.004
ez-0.004
hered-0.003
 nightmares-0.003
 heaven-0.003
Token Fin
Token ID4463
Feature activation+3.09e-02

Pos logit contributions
ires+0.089
ate+0.085
iring+0.085
um+0.084
ruce+0.076
Neg logit contributions
joy-0.094
ez-0.090
hered-0.082
 nightmares-0.076
 moment-0.075
Token that
Token ID326
Feature activation+1.58e-01

Pos logit contributions
ires+0.036
ate+0.036
um+0.033
iring+0.033
ered+0.028
Neg logit contributions
joy-0.077
ez-0.073
hered-0.068
Charl-0.064
 nightmares-0.062
Token he
Token ID339
Feature activation-1.06e-02

Pos logit contributions
ires+0.180
iring+0.172
ate+0.172
ruce+0.144
 Inside+0.139
Neg logit contributions
joy-0.384
ez-0.378
hered-0.366
Charl-0.327
 tale-0.321
Token adm
Token ID6178
Feature activation-6.57e-02

Pos logit contributions
joy+0.023
ez+0.021
hered+0.020
 nightmares+0.018
 moment+0.018
Neg logit contributions
ires-0.016
ate-0.015
iring-0.015
um-0.015
ruce-0.013
Tokenires
Token ID2387
Feature activation+4.73e-01

Pos logit contributions
joy+0.162
ez+0.139
 nightmares+0.133
smart+0.131
ching+0.127
Neg logit contributions
 First-0.067
 stack-0.054
 Later-0.052
 brushes-0.047
 elevator-0.044
Token how
Token ID703
Feature activation+9.38e-02

Pos logit contributions
ires+0.647
iring+0.581
ate+0.564
um+0.552
 Inside+0.494
Neg logit contributions
joy-1.102
ez-1.063
hered-0.992
 moment-0.926
ñ-0.918
Token brave
Token ID14802
Feature activation-7.64e-02

Pos logit contributions
ires+0.153
iring+0.144
ate+0.144
um+0.142
ruce+0.127
Neg logit contributions
joy-0.190
ez-0.183
hered-0.167
 nightmares-0.156
 moment-0.154
Token he
Token ID339
Feature activation-1.19e-02

Pos logit contributions
joy+0.154
ez+0.148
hered+0.134
 nightmares+0.127
 moment+0.125
Neg logit contributions
ires-0.125
iring-0.118
ate-0.117
um-0.116
ruce-0.104
Token is
Token ID318
Feature activation-1.98e-02

Pos logit contributions
joy+0.026
ez+0.025
hered+0.023
 nightmares+0.021
 moment+0.021
Neg logit contributions
ires-0.018
ate-0.017
iring-0.017
um-0.016
ruce-0.015
Token.
Token ID13
Feature activation-2.13e-02

Pos logit contributions
joy+0.048
ez+0.046
hered+0.043
Charl+0.041
ñ+0.039
Neg logit contributions
ires-0.024
ate-0.023
iring-0.021
um-0.020
 Inside-0.019
Token,
Token ID11
Feature activation+1.12e-01

Pos logit contributions
joy+0.009
ez+0.009
hered+0.008
 moment+0.007
 nightmares+0.007
Neg logit contributions
ires-0.014
iring-0.013
ate-0.013
um-0.013
ruce-0.012
Token green
Token ID4077
Feature activation+1.93e-01

Pos logit contributions
ires+0.167
um+0.158
iring+0.157
ate+0.156
ruce+0.137
Neg logit contributions
joy-0.232
ez-0.231
hered-0.210
 nightmares-0.193
Charl-0.184
Token apple
Token ID17180
Feature activation+7.40e-02

Pos logit contributions
ires+0.290
ate+0.276
um+0.275
iring+0.270
ruce+0.232
Neg logit contributions
joy-0.410
ez-0.394
hered-0.361
 nightmares-0.332
Charl-0.326
Token.
Token ID13
Feature activation+1.25e-02

Pos logit contributions
ires+0.106
um+0.102
ate+0.101
iring+0.098
ruce+0.086
Neg logit contributions
joy-0.166
ez-0.155
hered-0.140
 nightmares-0.134
 moment-0.130
Token Y
Token ID575
Feature activation-3.65e-02

Pos logit contributions
ires+0.019
ate+0.018
um+0.018
iring+0.018
ruce+0.016
Neg logit contributions
joy-0.026
ez-0.025
hered-0.023
 nightmares-0.022
 moment-0.021
Tokenum
Token ID388
Feature activation+4.72e-01

Pos logit contributions
joy+0.102
ez+0.100
hered+0.099
ñ+0.089
 tale+0.089
Neg logit contributions
ires-0.026
iring-0.021
ate-0.021
ruce-0.019
outed-0.016
Token!
Token ID0
Feature activation-2.44e-02

Pos logit contributions
ires+0.636
um+0.635
ate+0.621
iring+0.600
lly+0.532
Neg logit contributions
joy-1.051
ez-1.003
hered-0.948
 nightmares-0.893
 moment-0.861
Token
Token ID220
Feature activation-6.60e-02

Pos logit contributions
joy+0.047
ez+0.045
hered+0.041
 nightmares+0.039
 moment+0.038
Neg logit contributions
ires-0.041
ate-0.039
um-0.039
iring-0.039
ruce-0.035
Token
Token ID198
Feature activation+2.45e-03

Pos logit contributions
joy+0.117
ez+0.111
hered+0.099
 moment+0.092
 nightmares+0.091
Neg logit contributions
ires-0.120
iring-0.115
ate-0.113
um-0.112
ruce-0.105
Token
Token ID198
Feature activation+2.96e-04

Pos logit contributions
ires+0.005
iring+0.005
ate+0.004
um+0.004
ruce+0.004
Neg logit contributions
joy-0.004
ez-0.004
hered-0.003
 moment-0.003
 heaven-0.003
TokenHe
Token ID1544
Feature activation+2.72e-02

Pos logit contributions
ires+0.001
iring+0.000
ate+0.000
um+0.000
ruce+0.000
Neg logit contributions
joy-0.001
ez-0.001
hered-0.001
 moment-0.000
 nightmares-0.000
Token.
Token ID13
Feature activation+4.73e-02

Pos logit contributions
ires+0.239
ate+0.227
iring+0.223
um+0.223
ruce+0.194
Neg logit contributions
joy-0.346
ez-0.332
hered-0.299
 nightmares-0.286
 moment-0.273
Token
Token ID198
Feature activation+4.87e-02

Pos logit contributions
ires+0.073
ate+0.069
um+0.068
iring+0.068
ruce+0.060
Neg logit contributions
joy-0.099
ez-0.095
hered-0.087
 nightmares-0.082
 moment-0.080
Token
Token ID198
Feature activation+3.56e-02

Pos logit contributions
ires+0.091
iring+0.087
ate+0.085
um+0.084
ruce+0.078
Neg logit contributions
joy-0.086
ez-0.084
hered-0.070
 moment-0.069
 nightmares-0.068
Token"
Token ID1
Feature activation+4.76e-02

Pos logit contributions
ires+0.057
iring+0.054
ate+0.053
um+0.053
ruce+0.048
Neg logit contributions
joy-0.072
ez-0.070
hered-0.063
 moment-0.059
 nightmares-0.059
TokenM
Token ID44
Feature activation-2.15e-02

Pos logit contributions
ires+0.075
ate+0.073
um+0.071
iring+0.069
ruce+0.063
Neg logit contributions
joy-0.099
ez-0.093
 nightmares-0.083
hered-0.082
 breathing-0.079
Tokenum
Token ID388
Feature activation+4.66e-01

Pos logit contributions
joy+0.047
ez+0.044
hered+0.041
 tale+0.040
 nightmares+0.040
Neg logit contributions
ate-0.027
ires-0.027
ruce-0.025
iring-0.025
her-0.021
Token!
Token ID0
Feature activation-1.73e-02

Pos logit contributions
um+0.605
ires+0.599
ate+0.590
iring+0.564
ruce+0.481
Neg logit contributions
joy-1.052
ez-1.017
hered-0.936
 nightmares-0.903
 heaven-0.864
Token Look
Token ID6803
Feature activation-1.52e-02

Pos logit contributions
joy+0.032
ez+0.031
hered+0.028
 nightmares+0.027
 moment+0.026
Neg logit contributions
ires-0.030
um-0.029
ate-0.029
iring-0.028
 Inside-0.026
Token at
Token ID379
Feature activation+1.94e-01

Pos logit contributions
joy+0.028
ez+0.025
hered+0.022
 moment+0.021
 nightmares+0.021
Neg logit contributions
ires-0.029
iring-0.028
ate-0.027
ruce-0.025
um-0.024
Token this
Token ID428
Feature activation+1.70e-02

Pos logit contributions
ires+0.310
iring+0.292
ate+0.290
um+0.287
ruce+0.260
Neg logit contributions
joy-0.391
ez-0.377
hered-0.343
 nightmares-0.328
 moment-0.321
Token tree
Token ID5509
Feature activation+2.49e-02

Pos logit contributions
ires+0.026
ate+0.024
iring+0.024
um+0.024
ruce+0.021
Neg logit contributions
joy-0.036
ez-0.035
hered-0.031
 nightmares-0.030
 moment-0.029
Token hat
Token ID6877
Feature activation+5.81e-02

Pos logit contributions
ires+0.147
ate+0.145
um+0.143
iring+0.135
ruce+0.118
Neg logit contributions
ez-0.224
joy-0.217
hered-0.202
 nightmares-0.182
smart-0.180
Token.
Token ID13
Feature activation+7.36e-03

Pos logit contributions
ires+0.086
ate+0.082
um+0.082
iring+0.081
ruce+0.071
Neg logit contributions
joy-0.125
ez-0.118
hered-0.106
 nightmares-0.103
 moment-0.100
Token
Token ID198
Feature activation+2.60e-02

Pos logit contributions
ires+0.012
ate+0.011
iring+0.011
um+0.011
ruce+0.010
Neg logit contributions
joy-0.015
ez-0.015
hered-0.013
 nightmares-0.013
 moment-0.012
Token
Token ID198
Feature activation+2.05e-02

Pos logit contributions
ires+0.051
iring+0.049
um+0.047
ate+0.047
ruce+0.044
Neg logit contributions
joy-0.044
ez-0.042
 moment-0.035
hered-0.035
 heaven-0.034
TokenM
Token ID44
Feature activation-2.45e-02

Pos logit contributions
ires+0.034
iring+0.032
ate+0.032
um+0.031
ruce+0.028
Neg logit contributions
joy-0.041
ez-0.040
hered-0.036
 moment-0.033
 nightmares-0.033
Tokenum
Token ID388
Feature activation+4.65e-01

Pos logit contributions
joy+0.056
ez+0.052
 nightmares+0.047
hered+0.047
 tale+0.046
Neg logit contributions
ate-0.030
ires-0.028
ruce-0.028
iring-0.026
 Inside-0.024
Token asked
Token ID1965
Feature activation+2.36e-01

Pos logit contributions
ires+0.722
iring+0.676
ate+0.675
um+0.663
ruce+0.595
Neg logit contributions
joy-0.980
ez-0.945
hered-0.860
 nightmares-0.810
 moment-0.800
Token the
Token ID262
Feature activation-2.36e-02

Pos logit contributions
um+0.304
ires+0.286
ate+0.266
iring+0.262
 Inside+0.236
Neg logit contributions
ez-0.546
joy-0.527
hered-0.494
 nightmares-0.489
 tale-0.462
Token priest
Token ID11503
Feature activation-1.11e-02

Pos logit contributions
joy+0.049
ez+0.048
hered+0.044
 nightmares+0.041
 moment+0.039
Neg logit contributions
ires-0.037
ate-0.034
um-0.034
iring-0.034
ruce-0.030
Token,
Token ID11
Feature activation+2.38e-02

Pos logit contributions
joy+0.025
ez+0.024
hered+0.023
 nightmares+0.021
Charl+0.021
Neg logit contributions
ires-0.016
um-0.015
ate-0.015
iring-0.014
ruce-0.012
Token "
Token ID366
Feature activation-6.24e-02

Pos logit contributions
ires+0.036
um+0.034
iring+0.034
ate+0.033
 Inside+0.031
Neg logit contributions
ez-0.049
joy-0.047
 nightmares-0.044
hered-0.044
 heaven-0.040
Token.
Token ID13
Feature activation+6.46e-02

Pos logit contributions
joy+0.729
ez+0.684
hered+0.621
 nightmares+0.597
 moment+0.574
Neg logit contributions
ires-0.533
iring-0.510
um-0.507
ate-0.505
ruce-0.447
Token
Token ID198
Feature activation+6.02e-02

Pos logit contributions
ires+0.102
ate+0.096
um+0.095
iring+0.095
ruce+0.084
Neg logit contributions
joy-0.133
ez-0.128
hered-0.117
 nightmares-0.110
 moment-0.108
Token
Token ID198
Feature activation+4.08e-02

Pos logit contributions
ires+0.107
iring+0.102
ate+0.101
um+0.099
ruce+0.091
Neg logit contributions
joy-0.113
ez-0.109
hered-0.095
 moment-0.090
 nightmares-0.090
Token"
Token ID1
Feature activation+5.24e-02

Pos logit contributions
ires+0.065
iring+0.061
ate+0.061
um+0.060
ruce+0.054
Neg logit contributions
joy-0.084
ez-0.081
hered-0.073
 nightmares-0.069
 moment-0.068
TokenY
Token ID56
Feature activation+2.01e-02

Pos logit contributions
ires+0.087
ate+0.084
um+0.082
iring+0.081
ruce+0.073
Neg logit contributions
joy-0.105
ez-0.099
hered-0.087
 nightmares-0.087
 breathing-0.083
Tokenum
Token ID388
Feature activation+4.64e-01

Pos logit contributions
ires+0.023
ate+0.021
iring+0.021
ruce+0.016
ised+0.016
Neg logit contributions
hered-0.047
joy-0.047
ez-0.046
ñ-0.043
rav-0.041
Token!
Token ID0
Feature activation-2.36e-02

Pos logit contributions
um+0.577
ires+0.548
ate+0.520
iring+0.520
ruce+0.423
Neg logit contributions
joy-1.094
ez-1.064
hered-0.988
 nightmares-0.950
Charl-0.928
Token This
Token ID770
Feature activation-1.92e-02

Pos logit contributions
joy+0.042
ez+0.040
hered+0.036
 nightmares+0.034
 moment+0.033
Neg logit contributions
ires-0.043
ate-0.041
um-0.041
iring-0.041
ruce-0.037
Token pizza
Token ID14256
Feature activation-9.01e-02

Pos logit contributions
joy+0.041
ez+0.039
hered+0.035
 nightmares+0.033
 knowing+0.032
Neg logit contributions
ires-0.029
ate-0.029
um-0.029
iring-0.027
ruce-0.025
Token is
Token ID318
Feature activation-7.86e-03

Pos logit contributions
joy+0.162
ez+0.159
hered+0.143
 moment+0.134
 nightmares+0.132
Neg logit contributions
ires-0.160
iring-0.153
ate-0.150
um-0.149
ruce-0.136
Token delicious
Token ID12625
Feature activation+3.57e-02

Pos logit contributions
joy+0.015
ez+0.015
hered+0.013
 nightmares+0.013
 moment+0.013
Neg logit contributions
ires-0.013
iring-0.012
ate-0.012
um-0.012
ruce-0.011
Token asked
Token ID1965
Feature activation+2.98e-01

Pos logit contributions
ires+0.012
iring+0.011
um+0.011
ate+0.011
ruce+0.010
Neg logit contributions
joy-0.018
ez-0.018
hered-0.016
 nightmares-0.015
Charl-0.015
Token.
Token ID13
Feature activation+2.79e-02

Pos logit contributions
ires+0.435
um+0.419
ate+0.410
iring+0.403
ruce+0.346
Neg logit contributions
joy-0.637
ez-0.620
hered-0.564
 nightmares-0.534
 moment-0.525
Token
Token ID198
Feature activation+3.30e-02

Pos logit contributions
ires+0.043
um+0.042
ate+0.040
iring+0.040
 Inside+0.036
Neg logit contributions
joy-0.056
ez-0.056
hered-0.050
 nightmares-0.049
 moment-0.046
Token
Token ID198
Feature activation+2.38e-02

Pos logit contributions
ires+0.054
ate+0.052
um+0.052
iring+0.051
ruce+0.046
Neg logit contributions
joy-0.066
ez-0.063
hered-0.057
 nightmares-0.054
 moment-0.053
TokenM
Token ID44
Feature activation-2.53e-02

Pos logit contributions
ires+0.037
um+0.036
ate+0.036
iring+0.035
ruce+0.031
Neg logit contributions
joy-0.049
ez-0.047
hered-0.042
 nightmares-0.041
 moment-0.039
Tokenum
Token ID388
Feature activation+4.62e-01

Pos logit contributions
joy+0.063
ez+0.060
hered+0.054
 nightmares+0.053
 tale+0.052
Neg logit contributions
ate-0.027
ires-0.026
ruce-0.024
iring-0.023
 Inside-0.019
Token thought
Token ID1807
Feature activation+5.68e-02

Pos logit contributions
ires+0.604
um+0.569
ate+0.564
iring+0.562
ruce+0.485
Neg logit contributions
joy-1.068
ez-1.025
hered-0.946
 nightmares-0.907
 moment-0.888
Token for
Token ID329
Feature activation+3.91e-02

Pos logit contributions
ires+0.079
um+0.075
iring+0.073
ate+0.071
ruce+0.065
Neg logit contributions
joy-0.128
ez-0.123
hered-0.113
 nightmares-0.105
Charl-0.103
Token a
Token ID257
Feature activation-9.59e-03

Pos logit contributions
ires+0.049
ate+0.047
um+0.045
iring+0.045
 Inside+0.040
Neg logit contributions
ez-0.090
joy-0.090
hered-0.083
oing-0.074
 nightmares-0.074
Token minute
Token ID5664
Feature activation-2.61e-01

Pos logit contributions
ez+0.016
joy+0.013
es+0.012
hered+0.012
tern+0.011
Neg logit contributions
 cool-0.017
um-0.017
 Inside-0.017
 open-0.017
 interesting-0.017
Token,
Token ID11
Feature activation+2.12e-02

Pos logit contributions
joy+0.608
ez+0.599
hered+0.542
Charl+0.512
 nightmares+0.509
Neg logit contributions
um-0.321
ires-0.315
iring-0.296
ate-0.294
 Inside-0.256
Token dog
Token ID3290
Feature activation-2.02e-01

Pos logit contributions
um+0.097
ires+0.090
ate+0.085
iring+0.083
ruce+0.073
Neg logit contributions
joy-0.141
ez-0.134
hered-0.123
Charl-0.120
 nightmares-0.117
Token food
Token ID2057
Feature activation-8.89e-02

Pos logit contributions
joy+0.475
ez+0.431
hered+0.400
 moment+0.388
 nightmares+0.387
Neg logit contributions
ires-0.244
um-0.242
ate-0.229
iring-0.222
lly-0.195
Token.
Token ID13
Feature activation+2.25e-03

Pos logit contributions
joy+0.195
ez+0.186
hered+0.167
 nightmares+0.160
 moment+0.154
Neg logit contributions
ires-0.130
um-0.124
ate-0.122
iring-0.122
ruce-0.106
Token "
Token ID366
Feature activation-4.53e-02

Pos logit contributions
ires+0.003
um+0.003
ate+0.003
iring+0.003
 Inside+0.003
Neg logit contributions
joy-0.005
ez-0.005
hered-0.004
 nightmares-0.004
 moment-0.004
TokenY
Token ID56
Feature activation+1.57e-02

Pos logit contributions
joy+0.099
 nightmares+0.089
ez+0.085
 breathing+0.083
hered+0.081
Neg logit contributions
um-0.060
ate-0.059
ires-0.059
iring-0.052
her-0.051
Tokenum
Token ID388
Feature activation+4.61e-01

Pos logit contributions
ires+0.016
ate+0.015
iring+0.013
ruce+0.011
outed+0.010
Neg logit contributions
ez-0.040
joy-0.040
hered-0.040
ñ-0.035
 moment-0.035
Token,
Token ID11
Feature activation+2.32e-02

Pos logit contributions
um+0.571
ires+0.512
iring+0.506
ate+0.487
lly+0.413
Neg logit contributions
joy-1.101
ez-1.070
hered-0.982
 nightmares-0.971
Charl-0.934
Token this
Token ID428
Feature activation+1.31e-02

Pos logit contributions
ires+0.030
um+0.029
iring+0.028
ate+0.027
 Inside+0.025
Neg logit contributions
joy-0.054
ez-0.052
hered-0.047
 nightmares-0.044
 breathing-0.043
Token is
Token ID318
Feature activation-9.12e-03

Pos logit contributions
um+0.019
ires+0.019
ate+0.019
iring+0.017
lly+0.017
Neg logit contributions
joy-0.029
ez-0.027
hered-0.025
 nightmares-0.023
smart-0.023
Token delicious
Token ID12625
Feature activation+3.73e-02

Pos logit contributions
joy+0.020
ez+0.019
hered+0.017
 nightmares+0.016
 moment+0.016
Neg logit contributions
ires-0.014
ate-0.013
iring-0.013
um-0.013
ruce-0.011
Token!"
Token ID2474
Feature activation+8.26e-02

Pos logit contributions
ires+0.053
um+0.051
ate+0.050
iring+0.049
ruce+0.043
Neg logit contributions
joy-0.083
ez-0.080
hered-0.073
 nightmares-0.070
 moment-0.067
Token him
Token ID683
Feature activation+9.45e-02

Pos logit contributions
joy+0.146
ez+0.135
hered+0.125
 nightmares+0.115
 moment+0.115
Neg logit contributions
ires-0.093
um-0.089
iring-0.087
ate-0.087
ruce-0.076
Token fly
Token ID6129
Feature activation+1.38e-02

Pos logit contributions
ires+0.137
iring+0.127
um+0.126
ate+0.125
ruce+0.111
Neg logit contributions
joy-0.205
ez-0.200
hered-0.184
 nightmares-0.174
 moment-0.173
Token.
Token ID13
Feature activation+1.30e-02

Pos logit contributions
ires+0.020
ate+0.019
iring+0.018
um+0.018
ruce+0.016
Neg logit contributions
joy-0.030
ez-0.029
hered-0.026
 nightmares-0.025
 heaven-0.024
Token<|endoftext|>
Token ID50256
Feature activation+5.50e-02

Pos logit contributions
ires+0.020
ate+0.019
um+0.019
iring+0.019
ruce+0.016
Neg logit contributions
joy-0.027
ez-0.026
hered-0.024
 nightmares-0.023
 moment-0.022
TokenM
Token ID44
Feature activation-3.08e-02

Pos logit contributions
ate+0.072
ires+0.071
um+0.068
iring+0.066
 Inside+0.060
Neg logit contributions
joy-0.122
ez-0.120
hered-0.109
 nightmares-0.109
 knowing-0.105
Tokenum
Token ID388
Feature activation+4.59e-01

Pos logit contributions
joy+0.067
ez+0.063
 moment+0.057
 nightmares+0.055
 tale+0.055
Neg logit contributions
ate-0.043
ires-0.043
iring-0.041
ruce-0.036
ised-0.033
Token and
Token ID290
Feature activation-4.24e-02

Pos logit contributions
ires+0.780
ate+0.735
iring+0.735
um+0.727
ruce+0.657
Neg logit contributions
joy-0.894
ez-0.859
hered-0.776
 nightmares-0.728
 moment-0.718
Token Dad
Token ID17415
Feature activation+2.28e-01

Pos logit contributions
joy+0.091
ez+0.088
hered+0.079
 nightmares+0.077
 moment+0.074
Neg logit contributions
ires-0.062
um-0.060
ate-0.059
iring-0.059
ruce-0.051
Token had
Token ID550
Feature activation-1.38e-01

Pos logit contributions
ires+0.355
um+0.341
ate+0.341
iring+0.331
ruce+0.297
Neg logit contributions
joy-0.469
ez-0.447
hered-0.405
 nightmares-0.396
 moment-0.381
Token a
Token ID257
Feature activation-7.49e-03

Pos logit contributions
joy+0.287
ez+0.278
hered+0.255
 nightmares+0.239
 moment+0.237
Neg logit contributions
ires-0.212
ate-0.202
um-0.200
iring-0.198
ruce-0.177
Token new
Token ID649
Feature activation+4.68e-02

Pos logit contributions
ez+0.019
joy+0.018
hered+0.017
 nightmares+0.016
smart+0.016
Neg logit contributions
ires-0.008
um-0.008
ate-0.007
iring-0.007
ruce-0.006
Token.
Token ID13
Feature activation+1.67e-02

Pos logit contributions
joy+0.269
ez+0.259
hered+0.236
 nightmares+0.223
 heaven+0.214
Neg logit contributions
ires-0.201
ate-0.191
um-0.188
iring-0.186
ruce-0.163
Token
Token ID198
Feature activation+3.36e-02

Pos logit contributions
ires+0.028
ate+0.026
um+0.026
iring+0.026
ruce+0.023
Neg logit contributions
joy-0.033
ez-0.032
hered-0.029
 nightmares-0.027
 moment-0.027
Token
Token ID198
Feature activation+2.51e-02

Pos logit contributions
ires+0.057
iring+0.054
ate+0.053
um+0.053
ruce+0.048
Neg logit contributions
joy-0.066
ez-0.063
hered-0.056
 nightmares-0.053
 moment-0.053
Token"
Token ID1
Feature activation+4.03e-02

Pos logit contributions
ires+0.039
ate+0.037
iring+0.037
um+0.037
ruce+0.033
Neg logit contributions
joy-0.052
ez-0.050
hered-0.046
 nightmares-0.043
 moment-0.042
TokenM
Token ID44
Feature activation-3.05e-02

Pos logit contributions
ires+0.068
ate+0.066
um+0.064
iring+0.064
ruce+0.056
Neg logit contributions
joy-0.080
ez-0.075
hered-0.068
 nightmares-0.066
 breathing-0.063
Tokenum
Token ID388
Feature activation+4.57e-01

Pos logit contributions
joy+0.071
ez+0.066
hered+0.060
 nightmares+0.059
 moment+0.059
Neg logit contributions
ires-0.037
ate-0.036
ruce-0.034
iring-0.033
outed-0.028
Token,
Token ID11
Feature activation+3.20e-02

Pos logit contributions
um+0.590
ires+0.579
ate+0.571
iring+0.545
lly+0.467
Neg logit contributions
joy-1.027
ez-0.997
hered-0.929
 nightmares-0.891
 heaven-0.853
Token what
Token ID644
Feature activation+1.85e-02

Pos logit contributions
ires+0.047
um+0.044
ate+0.044
iring+0.044
ruce+0.039
Neg logit contributions
joy-0.069
ez-0.067
hered-0.061
 nightmares-0.057
 moment-0.055
Token are
Token ID389
Feature activation-8.93e-02

Pos logit contributions
ires+0.028
ate+0.028
um+0.026
iring+0.025
ruce+0.024
Neg logit contributions
joy-0.040
ez-0.038
hered-0.036
 knowing-0.032
 moment-0.031
Token these
Token ID777
Feature activation+5.91e-02

Pos logit contributions
joy+0.101
ez+0.090
 nightmares+0.087
 risking+0.080
 knowing+0.079
Neg logit contributions
ate-0.185
outed-0.179
ires-0.178
um-0.178
iring-0.177
Token?"
Token ID1701
Feature activation+3.27e-01

Pos logit contributions
ires+0.075
ate+0.069
iring+0.068
um+0.066
ruce+0.061
Neg logit contributions
joy-0.134
ez-0.128
hered-0.119
 nightmares-0.117
 moment-0.115
Token time
Token ID640
Feature activation-5.19e-02

Pos logit contributions
ires+0.125
iring+0.118
ate+0.117
um+0.117
ruce+0.105
Neg logit contributions
joy-0.162
ez-0.157
hered-0.139
 nightmares-0.137
 moment-0.134
Token to
Token ID284
Feature activation+1.22e-02

Pos logit contributions
joy+0.106
ez+0.103
hered+0.093
 nightmares+0.088
 moment+0.085
Neg logit contributions
ires-0.083
ate-0.077
um-0.077
iring-0.077
ruce-0.069
Token eat
Token ID4483
Feature activation+4.63e-02

Pos logit contributions
ires+0.019
iring+0.018
ate+0.017
um+0.017
ruce+0.015
Neg logit contributions
joy-0.026
ez-0.025
hered-0.023
 nightmares-0.022
 moment-0.022
Token.
Token ID13
Feature activation-5.25e-03

Pos logit contributions
ires+0.073
ate+0.069
um+0.069
iring+0.068
ruce+0.061
Neg logit contributions
joy-0.095
ez-0.092
hered-0.084
 nightmares-0.078
 moment-0.077
Token Y
Token ID575
Feature activation-5.64e-02

Pos logit contributions
joy+0.011
ez+0.010
hered+0.009
 nightmares+0.009
 moment+0.009
Neg logit contributions
ires-0.008
iring-0.008
ate-0.008
um-0.008
ruce-0.007
Tokenum
Token ID388
Feature activation+4.57e-01

Pos logit contributions
joy+0.154
ez+0.150
hered+0.147
ñ+0.134
 moment+0.133
Neg logit contributions
ires-0.045
iring-0.038
ate-0.035
ruce-0.034
outed-0.026
Token!
Token ID0
Feature activation-3.09e-02

Pos logit contributions
um+0.605
ires+0.603
ate+0.588
iring+0.564
lly+0.504
Neg logit contributions
joy-1.043
ez-0.978
hered-0.928
 nightmares-0.870
 moment-0.845
Token It
Token ID632
Feature activation+3.18e-02

Pos logit contributions
joy+0.062
ez+0.059
hered+0.054
 nightmares+0.051
 moment+0.050
Neg logit contributions
ires-0.051
ate-0.048
um-0.048
iring-0.048
ruce-0.042
Token was
Token ID373
Feature activation+2.26e-02

Pos logit contributions
ires+0.046
ate+0.044
um+0.044
iring+0.044
ruce+0.039
Neg logit contributions
joy-0.071
ez-0.065
hered-0.060
 nightmares-0.056
 moment-0.055
Token the
Token ID262
Feature activation-2.96e-02

Pos logit contributions
ires+0.036
ate+0.034
iring+0.034
um+0.034
ruce+0.030
Neg logit contributions
joy-0.046
ez-0.044
hered-0.041
 nightmares-0.038
 moment-0.038
Token best
Token ID1266
Feature activation-1.24e-02

Pos logit contributions
joy+0.066
ez+0.065
hered+0.059
 nightmares+0.055
 heaven+0.053
Neg logit contributions
ires-0.042
um-0.039
iring-0.039
ate-0.039
ruce-0.033
Token look
Token ID804
Feature activation+1.10e-01

Pos logit contributions
ires+0.152
um+0.144
ate+0.144
iring+0.142
ruce+0.123
Neg logit contributions
joy-0.208
ez-0.203
hered-0.186
 nightmares-0.173
Charl-0.169
Token."
Token ID526
Feature activation+1.24e-02

Pos logit contributions
ires+0.161
ate+0.152
iring+0.151
um+0.150
ruce+0.133
Neg logit contributions
joy-0.239
ez-0.230
hered-0.209
 nightmares-0.200
 moment-0.197
Token
Token ID198
Feature activation+1.99e-02

Pos logit contributions
ires+0.018
um+0.018
ate+0.017
iring+0.017
 Inside+0.015
Neg logit contributions
joy-0.026
ez-0.026
hered-0.024
 nightmares-0.023
 moment-0.022
Token
Token ID198
Feature activation+1.44e-02

Pos logit contributions
ires+0.035
iring+0.033
ate+0.033
um+0.032
ruce+0.029
Neg logit contributions
joy-0.038
ez-0.036
hered-0.032
 nightmares-0.030
 moment-0.030
TokenM
Token ID44
Feature activation-3.01e-02

Pos logit contributions
ires+0.023
ate+0.022
um+0.022
iring+0.022
ruce+0.019
Neg logit contributions
joy-0.029
ez-0.028
hered-0.025
 nightmares-0.024
 moment-0.023
Tokenum
Token ID388
Feature activation+4.57e-01

Pos logit contributions
joy+0.073
ez+0.069
hered+0.063
 nightmares+0.062
 moment+0.060
Neg logit contributions
ate-0.036
ires-0.034
iring-0.032
ruce-0.031
um-0.026
Token went
Token ID1816
Feature activation+8.83e-02

Pos logit contributions
ires+0.650
um+0.617
ate+0.612
iring+0.608
ruce+0.531
Neg logit contributions
joy-1.005
ez-0.960
hered-0.884
 nightmares-0.847
 moment-0.828
Token outside
Token ID2354
Feature activation+1.64e-01

Pos logit contributions
ires+0.133
ate+0.125
iring+0.125
um+0.123
ruce+0.109
Neg logit contributions
joy-0.190
ez-0.182
hered-0.167
 nightmares-0.158
 moment-0.156
Token,
Token ID11
Feature activation+2.68e-02

Pos logit contributions
um+0.165
ires+0.164
iring+0.159
ate+0.159
 Inside+0.154
Neg logit contributions
ez-0.393
joy-0.375
hered-0.352
 nightmares-0.350
 liar-0.349
Token and
Token ID290
Feature activation-4.56e-02

Pos logit contributions
ires+0.043
iring+0.041
um+0.041
ate+0.041
outed+0.036
Neg logit contributions
ez-0.051
joy-0.051
hered-0.046
 nightmares-0.044
 tale-0.041
Token found
Token ID1043
Feature activation+9.77e-02

Pos logit contributions
joy+0.097
ez+0.094
hered+0.086
 nightmares+0.081
 moment+0.080
Neg logit contributions
ires-0.069
ate-0.064
iring-0.064
um-0.064
ruce-0.056
Token.
Token ID13
Feature activation+6.80e-03

Pos logit contributions
ires+0.426
ate+0.401
iring+0.399
um+0.392
ruce+0.361
Neg logit contributions
joy-0.448
ez-0.426
hered-0.390
 moment-0.364
 nightmares-0.359
Token
Token ID198
Feature activation+2.09e-02

Pos logit contributions
ires+0.011
iring+0.011
ate+0.011
um+0.011
ruce+0.010
Neg logit contributions
joy-0.013
ez-0.013
hered-0.011
 nightmares-0.011
 moment-0.011
Token
Token ID198
Feature activation+1.48e-02

Pos logit contributions
ires+0.041
iring+0.040
um+0.039
ate+0.039
ruce+0.036
Neg logit contributions
joy-0.034
ez-0.033
 moment-0.027
hered-0.027
 heaven-0.026
Token"
Token ID1
Feature activation+3.18e-02

Pos logit contributions
ires+0.025
iring+0.024
ate+0.023
um+0.023
ruce+0.021
Neg logit contributions
joy-0.029
ez-0.028
hered-0.025
 moment-0.023
 heaven-0.023
TokenY
Token ID56
Feature activation+1.44e-02

Pos logit contributions
ires+0.055
ate+0.053
um+0.051
iring+0.051
ruce+0.046
Neg logit contributions
joy-0.062
ez-0.059
hered-0.053
 nightmares-0.051
 breathing-0.048
Tokenum
Token ID388
Feature activation+4.57e-01

Pos logit contributions
ires+0.019
iring+0.017
ate+0.016
outed+0.014
ised+0.014
Neg logit contributions
hered-0.032
joy-0.030
ez-0.030
ñ-0.028
rav-0.027
Token,
Token ID11
Feature activation+2.31e-02

Pos logit contributions
ires+0.626
um+0.622
ate+0.595
iring+0.590
ruce+0.504
Neg logit contributions
joy-1.009
ez-0.983
hered-0.900
 nightmares-0.866
 moment-0.838
Token y
Token ID331
Feature activation+7.72e-02

Pos logit contributions
ires+0.038
ate+0.036
iring+0.036
um+0.036
ruce+0.032
Neg logit contributions
joy-0.046
ez-0.044
hered-0.040
 nightmares-0.038
 moment-0.037
Tokenum
Token ID388
Feature activation+4.50e-01

Pos logit contributions
ires+0.066
iring+0.057
ate+0.055
outed+0.048
her+0.046
Neg logit contributions
ez-0.199
joy-0.198
hered-0.196
 moment-0.171
ñ-0.170
Token,
Token ID11
Feature activation+1.73e-02

Pos logit contributions
ires+0.612
um+0.591
ate+0.579
iring+0.572
ruce+0.489
Neg logit contributions
joy-1.022
ez-0.986
hered-0.910
 nightmares-0.867
 moment-0.842
Token these
Token ID777
Feature activation+5.62e-02

Pos logit contributions
ires+0.028
ate+0.027
iring+0.027
um+0.026
ruce+0.024
Neg logit contributions
joy-0.035
ez-0.033
hered-0.030
 moment-0.028
 nightmares-0.028
Token.
Token ID13
Feature activation+2.88e-03

Pos logit contributions
joy+0.207
ez+0.204
hered+0.181
 nightmares+0.172
 heaven+0.164
Neg logit contributions
ires-0.150
ate-0.145
iring-0.141
um-0.138
ruce-0.125
Token
Token ID198
Feature activation+2.14e-02

Pos logit contributions
ires+0.004
ate+0.004
iring+0.004
um+0.004
ruce+0.004
Neg logit contributions
joy-0.006
ez-0.006
hered-0.005
 nightmares-0.005
 moment-0.005
Token
Token ID198
Feature activation+1.65e-02

Pos logit contributions
ires+0.040
iring+0.038
ate+0.037
um+0.037
ruce+0.034
Neg logit contributions
joy-0.038
ez-0.036
hered-0.031
 moment-0.031
 nightmares-0.029
Token"
Token ID1
Feature activation+3.57e-02

Pos logit contributions
ires+0.026
iring+0.025
ate+0.024
um+0.024
ruce+0.022
Neg logit contributions
joy-0.034
ez-0.033
hered-0.029
 moment-0.028
 nightmares-0.027
TokenY
Token ID56
Feature activation+1.15e-02

Pos logit contributions
ires+0.059
ate+0.057
um+0.056
iring+0.056
ruce+0.050
Neg logit contributions
joy-0.071
ez-0.068
hered-0.060
 nightmares-0.059
 breathing-0.056
Tokenum
Token ID388
Feature activation+4.56e-01

Pos logit contributions
ires+0.017
ate+0.015
iring+0.015
outed+0.012
ruce+0.012
Neg logit contributions
hered-0.024
joy-0.023
ez-0.022
ñ-0.022
rav-0.021
Token!"
Token ID2474
Feature activation+7.93e-02

Pos logit contributions
ires+0.651
um+0.628
iring+0.617
ate+0.616
ruce+0.531
Neg logit contributions
joy-0.994
ez-0.965
hered-0.884
 nightmares-0.840
 moment-0.818
Token she
Token ID673
Feature activation-7.35e-02

Pos logit contributions
ires+0.129
iring+0.122
ate+0.121
um+0.116
ruce+0.108
Neg logit contributions
joy-0.162
ez-0.155
hered-0.141
 nightmares-0.132
 moment-0.131
Token exclaimed
Token ID33552
Feature activation+2.25e-01

Pos logit contributions
joy+0.164
ez+0.162
hered+0.148
 nightmares+0.143
 moment+0.138
Neg logit contributions
ires-0.105
iring-0.099
ate-0.093
um-0.091
ruce-0.082
Token with
Token ID351
Feature activation+8.68e-02

Pos logit contributions
um+0.267
ires+0.259
iring+0.246
ate+0.229
outed+0.200
Neg logit contributions
ez-0.532
joy-0.515
hered-0.470
 nightmares-0.468
Charl-0.464
Token delight
Token ID10974
Feature activation-2.13e-02

Pos logit contributions
ires+0.155
ate+0.147
iring+0.147
um+0.145
ruce+0.132
Neg logit contributions
joy-0.163
ez-0.156
hered-0.140
 nightmares-0.132
 moment-0.129
Token her
Token ID607
Feature activation-5.94e-03

Pos logit contributions
ires+0.380
um+0.366
ate+0.350
iring+0.346
ruce+0.295
Neg logit contributions
joy-0.588
ez-0.578
hered-0.534
 moment-0.491
 nightmares-0.488
Token mum
Token ID25682
Feature activation+2.27e-01

Pos logit contributions
joy+0.014
ez+0.013
hered+0.012
 nightmares+0.012
 moment+0.011
Neg logit contributions
ires-0.008
ate-0.007
iring-0.007
um-0.007
ruce-0.006
Token,
Token ID11
Feature activation+4.19e-02

Pos logit contributions
ires+0.321
um+0.306
ate+0.302
iring+0.296
ruce+0.253
Neg logit contributions
joy-0.500
ez-0.496
hered-0.455
 nightmares-0.427
Charl-0.407
Token "
Token ID366
Feature activation-4.41e-02

Pos logit contributions
ires+0.061
um+0.060
iring+0.059
ate+0.057
 Inside+0.053
Neg logit contributions
ez-0.089
joy-0.084
 nightmares-0.079
hered-0.078
 heaven-0.072
TokenM
Token ID44
Feature activation-3.79e-02

Pos logit contributions
joy+0.085
ez+0.083
hered+0.074
 nightmares+0.073
 heaven+0.068
Neg logit contributions
ires-0.073
ate-0.071
um-0.070
iring-0.070
ruce-0.062
Tokenum
Token ID388
Feature activation+4.55e-01

Pos logit contributions
joy+0.081
ez+0.076
 tale+0.069
hered+0.068
 nightmares+0.067
Neg logit contributions
ate-0.047
ires-0.046
ruce-0.044
iring-0.042
 prett-0.038
Token,
Token ID11
Feature activation+2.73e-02

Pos logit contributions
ires+0.587
um+0.585
ate+0.569
iring+0.543
ruce+0.456
Neg logit contributions
joy-1.039
ez-1.011
hered-0.932
 nightmares-0.891
 heaven-0.852
Token why
Token ID1521
Feature activation+9.07e-02

Pos logit contributions
ires+0.039
um+0.037
ate+0.036
iring+0.036
ruce+0.031
Neg logit contributions
joy-0.060
ez-0.059
hered-0.054
 nightmares-0.051
 moment-0.049
Token do
Token ID466
Feature activation+1.68e-01

Pos logit contributions
ires+0.138
ate+0.133
iring+0.127
um+0.125
ruce+0.115
Neg logit contributions
joy-0.199
ez-0.188
hered-0.179
 nightmares-0.153
Charl-0.152
Token I
Token ID314
Feature activation+2.73e-02

Pos logit contributions
ires+0.223
ate+0.211
um+0.208
iring+0.204
lly+0.186
Neg logit contributions
joy-0.403
ez-0.378
hered-0.347
 knowing-0.326
 moment-0.321
Token feel
Token ID1254
Feature activation-8.32e-02

Pos logit contributions
ires+0.046
ate+0.044
iring+0.044
um+0.044
ruce+0.039
Neg logit contributions
joy-0.053
ez-0.051
hered-0.046
 nightmares-0.043
 moment-0.043
Token that
Token ID326
Feature activation+2.20e-01

Pos logit contributions
joy+0.011
ez+0.011
hered+0.010
 nightmares+0.009
 moment+0.009
Neg logit contributions
ires-0.009
ate-0.008
iring-0.008
um-0.008
ruce-0.007
Token day
Token ID1110
Feature activation-4.63e-02

Pos logit contributions
ires+0.307
ate+0.292
um+0.285
iring+0.277
ruce+0.248
Neg logit contributions
joy-0.493
ez-0.458
hered-0.445
Charl-0.400
oing-0.384
Token.
Token ID13
Feature activation+3.15e-03

Pos logit contributions
joy+0.108
ez+0.103
hered+0.092
oing+0.091
 nightmares+0.090
Neg logit contributions
um-0.054
ate-0.047
ires-0.047
iring-0.044
 Inside-0.041
Token<|endoftext|>
Token ID50256
Feature activation+4.94e-02

Pos logit contributions
ires+0.004
um+0.004
ate+0.004
iring+0.004
 Inside+0.004
Neg logit contributions
joy-0.007
ez-0.007
hered-0.006
 nightmares-0.006
 moment-0.006
TokenM
Token ID44
Feature activation-3.74e-02

Pos logit contributions
ate+0.067
ires+0.066
um+0.064
iring+0.062
 Inside+0.056
Neg logit contributions
joy-0.109
ez-0.105
hered-0.096
 nightmares-0.095
 knowing-0.093
Tokenum
Token ID388
Feature activation+4.55e-01

Pos logit contributions
joy+0.082
ez+0.077
 moment+0.069
 nightmares+0.069
hered+0.068
Neg logit contributions
ires-0.053
ate-0.052
iring-0.050
ruce-0.044
ised-0.039
Token woke
Token ID19092
Feature activation-2.38e-01

Pos logit contributions
ires+0.764
ate+0.720
iring+0.719
um+0.712
ruce+0.642
Neg logit contributions
joy-0.894
ez-0.858
hered-0.776
 nightmares-0.730
 moment-0.719
Token up
Token ID510
Feature activation+2.62e-01

Pos logit contributions
joy+0.537
ez+0.493
 heaven+0.464
 knowing+0.456
 asleep+0.454
Neg logit contributions
ires-0.282
ate-0.271
iring-0.254
um-0.229
ruce-0.227
Token early
Token ID1903
Feature activation+1.57e-02

Pos logit contributions
ires+0.351
um+0.334
iring+0.334
ate+0.327
ruce+0.274
Neg logit contributions
ez-0.584
joy-0.568
hered-0.524
 nightmares-0.490
smart-0.487
Token.
Token ID13
Feature activation-3.08e-02

Pos logit contributions
ires+0.025
um+0.023
ate+0.023
iring+0.023
ruce+0.021
Neg logit contributions
joy-0.032
ez-0.031
hered-0.028
 nightmares-0.027
 moment-0.026
Token She
Token ID1375
Feature activation+4.07e-02

Pos logit contributions
joy+0.068
ez+0.067
hered+0.061
 nightmares+0.058
 moment+0.056
Neg logit contributions
ires-0.043
um-0.040
ate-0.040
iring-0.040
ruce-0.035
Token down
Token ID866
Feature activation+1.23e-01

Pos logit contributions
ez+0.055
joy+0.054
hered+0.047
 nightmares+0.046
 heaven+0.044
Neg logit contributions
ires-0.032
um-0.032
iring-0.031
ate-0.030
lly-0.027
Token the
Token ID262
Feature activation+3.65e-02

Pos logit contributions
ires+0.178
ate+0.171
um+0.168
iring+0.166
ruce+0.143
Neg logit contributions
ez-0.260
joy-0.257
hered-0.232
 nightmares-0.220
ñ-0.213
Token street
Token ID4675
Feature activation+8.68e-02

Pos logit contributions
ires+0.047
um+0.044
ate+0.044
iring+0.044
ruce+0.037
Neg logit contributions
joy-0.085
ez-0.083
hered-0.076
 nightmares-0.072
 moment-0.069
Token,
Token ID11
Feature activation+5.60e-02

Pos logit contributions
ires+0.130
um+0.125
ate+0.125
iring+0.124
ruce+0.107
Neg logit contributions
joy-0.178
ez-0.178
hered-0.158
 nightmares-0.153
Charl-0.145
Token adm
Token ID6178
Feature activation-3.07e-02

Pos logit contributions
ires+0.086
iring+0.081
ate+0.080
um+0.079
ruce+0.070
Neg logit contributions
ez-0.112
joy-0.112
hered-0.102
 nightmares-0.095
 tale-0.092
Tokeniring
Token ID3428
Feature activation+4.55e-01

Pos logit contributions
joy+0.080
ez+0.070
 knowing+0.067
 nightmares+0.067
ching+0.066
Neg logit contributions
 First-0.022
 Inside-0.018
ruce-0.016
 Later-0.015
 bury-0.014
Token the
Token ID262
Feature activation-1.18e-02

Pos logit contributions
ires+0.654
iring+0.608
ate+0.605
um+0.593
ruce+0.513
Neg logit contributions
joy-0.996
ez-0.974
hered-0.910
 nightmares-0.823
 moment-0.808
Token big
Token ID1263
Feature activation+2.01e-01

Pos logit contributions
joy+0.027
ez+0.026
hered+0.024
 nightmares+0.022
 heaven+0.022
Neg logit contributions
ires-0.016
iring-0.015
um-0.015
ate-0.015
ruce-0.013
Token billboard
Token ID41448
Feature activation-1.05e-01

Pos logit contributions
um+0.238
ires+0.238
iring+0.218
ate+0.218
 windows+0.191
Neg logit contributions
ez-0.462
joy-0.449
hered-0.417
 nightmares-0.391
Charl-0.391
Token ahead
Token ID4058
Feature activation+8.88e-02

Pos logit contributions
joy+0.225
ez+0.217
hered+0.194
 nightmares+0.185
 moment+0.179
Neg logit contributions
ires-0.159
iring-0.151
um-0.150
ate-0.148
ruce-0.131
Token.
Token ID13
Feature activation-2.59e-02

Pos logit contributions
ires+0.126
um+0.124
iring+0.119
ate+0.118
ruce+0.103
Neg logit contributions
joy-0.196
ez-0.189
hered-0.172
 nightmares-0.166
Charl-0.159
Token,
Token ID11
Feature activation+1.20e-02

Pos logit contributions
joy+0.236
ez+0.209
hered+0.199
 moment+0.187
 nightmares+0.185
Neg logit contributions
ires-0.148
ate-0.139
iring-0.135
um-0.130
ruce-0.127
Token the
Token ID262
Feature activation-3.89e-02

Pos logit contributions
ires+0.017
iring+0.017
um+0.016
ate+0.016
 Inside+0.015
Neg logit contributions
ez-0.028
joy-0.025
hered-0.024
oing-0.022
 nightmares-0.021
Token King
Token ID2677
Feature activation-9.34e-02

Pos logit contributions
joy+0.057
ez+0.056
hered+0.048
 nightmares+0.043
 moment+0.041
Neg logit contributions
ires-0.085
ate-0.082
iring-0.081
um-0.081
ruce-0.074
Token was
Token ID373
Feature activation+1.56e-02

Pos logit contributions
joy+0.195
ez+0.188
hered+0.168
 nightmares+0.165
 heaven+0.158
Neg logit contributions
ires-0.139
ate-0.137
um-0.137
iring-0.136
ruce-0.117
Token over
Token ID625
Feature activation+7.55e-02

Pos logit contributions
ires+0.026
iring+0.024
ate+0.024
um+0.024
ruce+0.021
Neg logit contributions
joy-0.032
ez-0.030
hered-0.028
 nightmares-0.026
 moment-0.025
Tokenjoy
Token ID2633
Feature activation-5.61e-01

Pos logit contributions
um+0.211
ires+0.211
iring+0.208
ate+0.206
 Inside+0.198
Neg logit contributions
ez-0.055
ñ-0.032
hered-0.030
 nightmares-0.029
Charl-0.029
Tokened
Token ID276
Feature activation-8.10e-02

Pos logit contributions
joy+1.223
 nightmares+1.221
 failure+1.196
 attacking+1.195
 foe+1.184
Neg logit contributions
um-0.717
iring-0.641
ires-0.637
ate-0.611
am-0.516
Token.
Token ID13
Feature activation-3.54e-02

Pos logit contributions
ez+0.186
joy+0.173
hered+0.163
 nightmares+0.162
Charl+0.156
Neg logit contributions
ires-0.104
iring-0.104
um-0.104
ate-0.097
 Inside-0.079
Token He
Token ID679
Feature activation+5.35e-02

Pos logit contributions
joy+0.079
ez+0.077
hered+0.071
 nightmares+0.067
 moment+0.066
Neg logit contributions
ires-0.050
ate-0.047
um-0.046
iring-0.046
ruce-0.039
Token put
Token ID1234
Feature activation+2.26e-01

Pos logit contributions
ires+0.100
iring+0.093
ate+0.089
um+0.088
ruce+0.082
Neg logit contributions
joy-0.097
ez-0.095
hered-0.086
 moment-0.079
 knowing-0.079
Token on
Token ID319
Feature activation-1.04e-01

Pos logit contributions
ires+0.366
ate+0.349
um+0.344
iring+0.343
ruce+0.305
Neg logit contributions
joy-0.455
ez-0.439
hered-0.399
 nightmares-0.380
 moment-0.366
Token him
Token ID683
Feature activation+2.48e-02

Pos logit contributions
ires+0.049
um+0.045
ate+0.045
iring+0.043
ruce+0.038
Neg logit contributions
joy-0.096
ez-0.095
hered-0.088
 nightmares-0.084
Charl-0.082
Token.
Token ID13
Feature activation-2.90e-02

Pos logit contributions
ires+0.029
iring+0.028
ate+0.027
um+0.026
 Inside+0.023
Neg logit contributions
joy-0.060
ez-0.058
hered-0.053
Charl-0.051
 nightmares-0.050
Token Moe
Token ID46488
Feature activation+1.69e-01

Pos logit contributions
joy+0.052
ez+0.044
hered+0.040
 moment+0.037
 heaven+0.036
Neg logit contributions
ate-0.054
ires-0.054
iring-0.053
um-0.050
ruce-0.049
Token was
Token ID373
Feature activation+1.85e-02

Pos logit contributions
ires+0.245
ate+0.243
um+0.241
iring+0.235
ruce+0.210
Neg logit contributions
joy-0.359
ez-0.339
hered-0.306
 nightmares-0.299
 moment-0.290
Token over
Token ID625
Feature activation+7.57e-02

Pos logit contributions
ires+0.023
iring+0.023
ate+0.023
um+0.022
ruce+0.019
Neg logit contributions
joy-0.043
ez-0.042
hered-0.038
 nightmares-0.037
 moment-0.036
Tokenjoy
Token ID2633
Feature activation-5.60e-01

Pos logit contributions
ires+0.204
iring+0.202
um+0.200
ate+0.196
 Inside+0.190
Neg logit contributions
ez-0.065
 lull-0.039
ñ-0.038
Charl-0.037
 nightmares-0.036
Tokened
Token ID276
Feature activation-7.90e-02

Pos logit contributions
joy+1.298
 nightmares+1.243
 failure+1.237
 heaven+1.213
Charl+1.198
Neg logit contributions
um-0.646
iring-0.605
ires-0.593
ate-0.583
am-0.532
Token to
Token ID284
Feature activation-2.67e-02

Pos logit contributions
ez+0.196
joy+0.180
hered+0.173
 nightmares+0.169
Charl+0.167
Neg logit contributions
iring-0.093
ires-0.089
um-0.087
ate-0.082
 up-0.067
Token see
Token ID766
Feature activation+1.15e-01

Pos logit contributions
joy+0.056
ez+0.054
hered+0.048
 nightmares+0.047
 heaven+0.045
Neg logit contributions
ires-0.040
ate-0.039
um-0.039
iring-0.037
ruce-0.033
Token them
Token ID606
Feature activation+4.65e-02

Pos logit contributions
ires+0.172
iring+0.160
ate+0.160
um+0.155
ruce+0.135
Neg logit contributions
joy-0.250
ez-0.245
hered-0.227
 nightmares-0.211
 moment-0.205
Token again
Token ID757
Feature activation-2.50e-01

Pos logit contributions
iring+0.065
ires+0.063
ate+0.060
um+0.059
ruce+0.054
Neg logit contributions
ez-0.101
joy-0.100
Charl-0.088
hered-0.085
 nightmares-0.083
Token noises
Token ID26782
Feature activation-7.13e-02

Pos logit contributions
ires+0.170
ate+0.167
iring+0.157
um+0.154
 windows+0.136
Neg logit contributions
joy-0.256
ez-0.244
hered-0.231
Charl-0.217
Patch-0.210
Token.
Token ID13
Feature activation-3.00e-02

Pos logit contributions
joy+0.180
ez+0.165
hered+0.147
 moment+0.143
 nightmares+0.142
Neg logit contributions
ires-0.081
iring-0.078
um-0.075
ate-0.075
her-0.068
Token Lucy
Token ID22162
Feature activation-7.37e-02

Pos logit contributions
joy+0.058
ez+0.056
hered+0.050
 nightmares+0.047
 moment+0.047
Neg logit contributions
ires-0.051
ate-0.049
iring-0.048
um-0.048
ruce-0.043
Token was
Token ID373
Feature activation+1.80e-02

Pos logit contributions
joy+0.161
ez+0.149
hered+0.139
 nightmares+0.134
 moment+0.130
Neg logit contributions
ate-0.103
ires-0.103
um-0.102
iring-0.098
ruce-0.087
Token over
Token ID625
Feature activation+7.80e-02

Pos logit contributions
ires+0.023
ate+0.023
iring+0.022
um+0.022
ruce+0.019
Neg logit contributions
joy-0.041
ez-0.040
hered-0.037
 nightmares-0.035
 moment-0.034
Tokenjoy
Token ID2633
Feature activation-5.59e-01

Pos logit contributions
ires+0.213
um+0.210
iring+0.209
ate+0.206
 Inside+0.192
Neg logit contributions
ez-0.064
ñ-0.038
hered-0.038
ching-0.034
 liar-0.033
Tokened
Token ID276
Feature activation-8.00e-02

Pos logit contributions
joy+1.191
ez+1.102
 failure+1.096
 nightmares+1.090
 attacking+1.079
Neg logit contributions
um-0.798
ires-0.749
ate-0.726
iring-0.724
outed-0.623
Token and
Token ID290
Feature activation-5.78e-02

Pos logit contributions
ez+0.181
joy+0.174
hered+0.160
 nightmares+0.154
ñ+0.150
Neg logit contributions
ires-0.108
um-0.106
iring-0.106
ate-0.102
ruce-0.081
Token promised
Token ID8072
Feature activation-1.37e-01

Pos logit contributions
joy+0.122
ez+0.117
hered+0.107
 nightmares+0.101
 moment+0.100
Neg logit contributions
ires-0.090
iring-0.084
ate-0.083
um-0.083
ruce-0.074
Token to
Token ID284
Feature activation-2.47e-02

Pos logit contributions
ez+0.306
joy+0.305
hered+0.270
 nightmares+0.254
 heaven+0.245
Neg logit contributions
ires-0.194
um-0.191
ate-0.190
iring-0.187
ruce-0.155
Token keep
Token ID1394
Feature activation+1.27e-01

Pos logit contributions
joy+0.046
ez+0.045
hered+0.041
 moment+0.039
 nightmares+0.039
Neg logit contributions
ires-0.043
iring-0.041
um-0.038
ate-0.038
outed-0.036
Token player
Token ID2137
Feature activation-2.12e-01

Pos logit contributions
joy+0.102
ez+0.094
hered+0.081
Charl+0.081
Sleep+0.079
Neg logit contributions
um-0.066
ires-0.066
ate-0.063
iring-0.061
ruce-0.056
Token!
Token ID0
Feature activation-4.19e-02

Pos logit contributions
joy+0.502
ez+0.471
Charl+0.424
hered+0.424
Sleep+0.418
Neg logit contributions
ires-0.246
ate-0.231
um-0.230
iring-0.219
ruce-0.196
Token Emily
Token ID17608
Feature activation-1.96e-01

Pos logit contributions
joy+0.078
ez+0.074
hered+0.067
 nightmares+0.063
 moment+0.061
Neg logit contributions
ires-0.075
ate-0.071
iring-0.071
um-0.071
ruce-0.064
Token was
Token ID373
Feature activation+2.05e-02

Pos logit contributions
joy+0.422
ez+0.395
hered+0.360
 nightmares+0.347
 moment+0.339
Neg logit contributions
ires-0.281
ate-0.279
um-0.274
iring-0.267
ruce-0.244
Token over
Token ID625
Feature activation+7.55e-02

Pos logit contributions
ires+0.025
iring+0.024
ate+0.024
um+0.023
ruce+0.020
Neg logit contributions
joy-0.049
ez-0.047
hered-0.044
 nightmares-0.041
 moment-0.041
Tokenjoy
Token ID2633
Feature activation-5.59e-01

Pos logit contributions
ires+0.213
iring+0.211
um+0.210
ate+0.206
 Inside+0.193
Neg logit contributions
ez-0.056
hered-0.028
ñ-0.028
 liar-0.027
oscope-0.026
Tokened
Token ID276
Feature activation-7.79e-02

Pos logit contributions
joy+1.238
 nightmares+1.170
 failure+1.160
 foe+1.142
 attacking+1.141
Neg logit contributions
um-0.732
iring-0.691
ires-0.677
ate-0.666
outed-0.555
Token as
Token ID355
Feature activation+2.88e-02

Pos logit contributions
ez+0.189
joy+0.177
hered+0.165
 nightmares+0.163
 liar+0.159
Neg logit contributions
iring-0.096
um-0.094
ires-0.093
ate-0.088
 up-0.068
Token she
Token ID673
Feature activation-8.30e-02

Pos logit contributions
ires+0.040
ate+0.037
iring+0.036
um+0.032
 Inside+0.029
Neg logit contributions
ez-0.068
joy-0.065
hered-0.064
ñ-0.056
oscope-0.056
Token recorded
Token ID6264
Feature activation-9.20e-02

Pos logit contributions
joy+0.158
ez+0.153
hered+0.138
 nightmares+0.129
 moment+0.126
Neg logit contributions
ires-0.147
iring-0.138
ate-0.136
um-0.136
ruce-0.122
Token the
Token ID262
Feature activation-3.74e-02

Pos logit contributions
joy+0.220
ez+0.220
hered+0.206
Charl+0.193
Sleep+0.192
Neg logit contributions
ires-0.102
ate-0.097
um-0.093
iring-0.092
 all-0.078
Token happy
Token ID3772
Feature activation-1.30e-01

Pos logit contributions
joy+0.048
ez+0.042
hered+0.037
 knowing+0.036
 moment+0.036
Neg logit contributions
ires-0.061
ate-0.059
um-0.058
iring-0.057
ruce-0.055
Token.
Token ID13
Feature activation-3.31e-02

Pos logit contributions
ez+0.314
joy+0.291
hered+0.291
Charl+0.275
ching+0.259
Neg logit contributions
ires-0.159
iring-0.155
ate-0.145
um-0.143
 Inside-0.111
Token She
Token ID1375
Feature activation+3.89e-02

Pos logit contributions
ez+0.077
joy+0.076
hered+0.072
 nightmares+0.068
 tale+0.066
Neg logit contributions
ires-0.044
um-0.040
ate-0.039
iring-0.038
 Inside-0.036
Token was
Token ID373
Feature activation+1.45e-02

Pos logit contributions
ires+0.069
ate+0.066
iring+0.065
um+0.065
ruce+0.059
Neg logit contributions
joy-0.073
ez-0.069
hered-0.063
 nightmares-0.059
 moment-0.058
Token over
Token ID625
Feature activation+7.32e-02

Pos logit contributions
ate+0.021
ires+0.021
iring+0.021
um+0.021
ruce+0.018
Neg logit contributions
joy-0.029
ez-0.029
hered-0.027
 nightmares-0.025
ñ-0.025
Tokenjoy
Token ID2633
Feature activation-5.59e-01

Pos logit contributions
ires+0.211
iring+0.206
um+0.206
ate+0.202
 Inside+0.188
Neg logit contributions
ez-0.051
ñ-0.035
hered-0.032
 lull-0.028
Charl-0.027
Tokened
Token ID276
Feature activation-7.82e-02

Pos logit contributions
joy+1.209
 nightmares+1.183
 heaven+1.157
ez+1.145
 failure+1.139
Neg logit contributions
um-0.749
ires-0.704
ate-0.697
iring-0.692
am-0.583
Token that
Token ID326
Feature activation+1.51e-01

Pos logit contributions
ez+0.183
joy+0.176
hered+0.165
 nightmares+0.158
ñ+0.156
Neg logit contributions
ires-0.104
iring-0.103
um-0.101
ate-0.096
 Inside-0.074
Token her
Token ID607
Feature activation-4.48e-02

Pos logit contributions
ires+0.153
iring+0.143
um+0.143
 all+0.138
ate+0.136
Neg logit contributions
ez-0.386
joy-0.366
hered-0.356
ñ-0.351
oing-0.339
Token pet
Token ID4273
Feature activation-2.16e-02

Pos logit contributions
ez+0.102
joy+0.102
hered+0.091
 nightmares+0.087
 moment+0.084
Neg logit contributions
ires-0.061
um-0.057
iring-0.057
ate-0.057
ruce-0.047
Token was
Token ID373
Feature activation+1.44e-02

Pos logit contributions
ez+0.042
joy+0.042
 nightmares+0.036
hered+0.035
 breathing+0.034
Neg logit contributions
um-0.034
ires-0.034
iring-0.034
ate-0.033
lly-0.029
Token.
Token ID13
Feature activation-3.74e-02

Pos logit contributions
joy+0.108
ez+0.104
hered+0.093
 nightmares+0.092
Charl+0.090
Neg logit contributions
ate-0.067
ires-0.067
um-0.064
iring-0.063
ered-0.054
Token O
Token ID440
Feature activation+1.58e-01

Pos logit contributions
joy+0.076
ez+0.073
hered+0.066
 nightmares+0.061
 moment+0.061
Neg logit contributions
ires-0.060
ate-0.057
iring-0.056
um-0.056
ruce-0.051
Tokenlly
Token ID12810
Feature activation+3.41e-01

Pos logit contributions
ires+0.124
ate+0.106
iring+0.105
um+0.101
ruce+0.079
Neg logit contributions
joy-0.455
ez-0.442
hered-0.413
 moment-0.395
 nightmares-0.389
Token was
Token ID373
Feature activation+1.23e-02

Pos logit contributions
ires+0.488
ate+0.485
um+0.478
iring+0.463
ruce+0.404
Neg logit contributions
joy-0.732
ez-0.693
hered-0.636
 nightmares-0.618
 heaven-0.595
Token over
Token ID625
Feature activation+7.48e-02

Pos logit contributions
ires+0.015
ate+0.015
um+0.014
iring+0.014
ruce+0.012
Neg logit contributions
joy-0.028
ez-0.028
hered-0.026
 nightmares-0.025
 moment-0.024
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.221
iring+0.219
um+0.216
ate+0.215
 Inside+0.198
Neg logit contributions
ez-0.046
hered-0.023
ñ-0.022
 nightmares-0.019
Charl-0.018
Tokened
Token ID276
Feature activation-7.81e-02

Pos logit contributions
joy+1.202
 nightmares+1.171
 heaven+1.145
 failure+1.123
ez+1.116
Neg logit contributions
um-0.773
ires-0.714
iring-0.711
ate-0.698
am-0.587
Token with
Token ID351
Feature activation+7.55e-02

Pos logit contributions
ez+0.169
joy+0.166
hered+0.152
 nightmares+0.147
 heaven+0.141
Neg logit contributions
ires-0.112
iring-0.109
um-0.109
ate-0.106
ruce-0.086
Token his
Token ID465
Feature activation-2.19e-02

Pos logit contributions
ires+0.113
ate+0.107
iring+0.106
um+0.105
ruce+0.093
Neg logit contributions
joy-0.162
ez-0.156
hered-0.144
 nightmares-0.135
 moment-0.134
Token prize
Token ID11596
Feature activation-3.49e-02

Pos logit contributions
ez+0.050
joy+0.047
hered+0.044
 heaven+0.042
 nightmares+0.041
Neg logit contributions
ires-0.031
um-0.030
ate-0.029
iring-0.028
ruce-0.024
Token,
Token ID11
Feature activation+8.90e-03

Pos logit contributions
ez+0.081
joy+0.080
hered+0.070
 nightmares+0.068
Charl+0.067
Neg logit contributions
ires-0.044
um-0.043
iring-0.043
ate-0.040
lly-0.034
Token
Token ID198
Feature activation-1.04e-02

Pos logit contributions
joy+0.161
ez+0.153
hered+0.138
 nightmares+0.128
 moment+0.127
Neg logit contributions
ires-0.154
iring-0.145
ate-0.144
um-0.143
ruce-0.132
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
joy+0.020
ez+0.019
hered+0.017
 nightmares+0.016
 moment+0.016
Neg logit contributions
ires-0.018
ate-0.017
iring-0.017
um-0.017
ruce-0.015
TokenJack
Token ID14295
Feature activation+1.84e-02

Pos logit contributions
joy+0.021
ez+0.020
hered+0.018
 nightmares+0.018
 moment+0.017
Neg logit contributions
ires-0.016
ate-0.015
iring-0.015
um-0.015
ruce-0.014
Token was
Token ID373
Feature activation+1.24e-02

Pos logit contributions
ires+0.025
um+0.025
ate+0.025
iring+0.024
ruce+0.021
Neg logit contributions
joy-0.041
ez-0.038
hered-0.036
 nightmares-0.034
 heaven-0.033
Token over
Token ID625
Feature activation+7.42e-02

Pos logit contributions
ires+0.017
ate+0.017
um+0.017
iring+0.016
ruce+0.014
Neg logit contributions
joy-0.027
ez-0.026
hered-0.024
 nightmares-0.023
 moment-0.022
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.118
um+0.115
iring+0.114
ate+0.109
 Inside+0.095
Neg logit contributions
ez-0.146
hered-0.130
joy-0.128
 nightmares-0.123
ñ-0.122
Tokened
Token ID276
Feature activation-7.99e-02

Pos logit contributions
joy+1.114
ez+1.057
 nightmares+1.048
 heaven+1.024
 failure+0.991
Neg logit contributions
um-0.858
ires-0.815
ate-0.797
iring-0.778
am-0.665
Token.
Token ID13
Feature activation-3.16e-02

Pos logit contributions
joy+0.170
ez+0.168
hered+0.152
 nightmares+0.146
 heaven+0.140
Neg logit contributions
ires-0.118
um-0.115
iring-0.115
ate-0.112
ruce-0.093
Token He
Token ID679
Feature activation+5.50e-02

Pos logit contributions
joy+0.067
ez+0.064
hered+0.058
 nightmares+0.055
 moment+0.055
Neg logit contributions
ires-0.048
ate-0.045
iring-0.045
um-0.044
ruce-0.040
Token had
Token ID550
Feature activation-1.48e-01

Pos logit contributions
ires+0.090
iring+0.084
ate+0.082
um+0.080
ruce+0.073
Neg logit contributions
joy-0.112
ez-0.110
hered-0.099
 nightmares-0.093
 moment-0.093
Token conquered
Token ID29346
Feature activation-1.63e-01

Pos logit contributions
joy+0.296
ez+0.289
hered+0.269
 nightmares+0.247
 moment+0.244
Neg logit contributions
ate-0.226
ires-0.223
um-0.217
iring-0.210
ruce-0.196
Token happen
Token ID1645
Feature activation-7.80e-02

Pos logit contributions
joy+0.065
ez+0.062
hered+0.056
 nightmares+0.052
Charl+0.050
Neg logit contributions
ires-0.043
ate-0.041
iring-0.040
um-0.039
ruce-0.036
Token.
Token ID13
Feature activation-3.30e-02

Pos logit contributions
joy+0.169
ez+0.169
hered+0.153
 nightmares+0.141
Charl+0.134
Neg logit contributions
ires-0.118
ate-0.113
iring-0.111
um-0.110
ruce-0.092
Token Jane
Token ID12091
Feature activation+6.38e-02

Pos logit contributions
joy+0.069
ez+0.067
hered+0.061
 nightmares+0.058
 moment+0.057
Neg logit contributions
ires-0.051
ate-0.048
um-0.048
iring-0.048
ruce-0.042
Token was
Token ID373
Feature activation+1.40e-02

Pos logit contributions
ate+0.090
ires+0.087
um+0.087
iring+0.083
lly+0.073
Neg logit contributions
joy-0.145
ez-0.128
hered-0.123
 nightmares-0.117
 heaven-0.114
Token over
Token ID625
Feature activation+7.61e-02

Pos logit contributions
ate+0.015
ires+0.015
iring+0.015
um+0.015
ruce+0.012
Neg logit contributions
joy-0.034
ez-0.033
hered-0.032
 nightmares-0.029
 moment-0.029
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.204
um+0.200
iring+0.199
ate+0.196
 Inside+0.181
Neg logit contributions
ez-0.070
hered-0.047
ñ-0.047
oing-0.041
ching-0.037
Tokened
Token ID276
Feature activation-7.78e-02

Pos logit contributions
joy+1.230
 attacking+1.187
 nightmares+1.180
 failure+1.173
ez+1.172
Neg logit contributions
um-0.733
ires-0.692
ate-0.679
iring-0.654
 Inside-0.521
Token,
Token ID11
Feature activation+1.25e-02

Pos logit contributions
ez+0.180
joy+0.172
hered+0.159
 nightmares+0.152
ñ+0.150
Neg logit contributions
ires-0.104
iring-0.103
um-0.102
ate-0.098
ised-0.075
Token and
Token ID290
Feature activation-5.83e-02

Pos logit contributions
ires+0.015
iring+0.014
um+0.014
ate+0.014
 Inside+0.012
Neg logit contributions
ez-0.028
joy-0.027
hered-0.026
ñ-0.024
 liar-0.023
Token thanked
Token ID26280
Feature activation-1.83e-02

Pos logit contributions
joy+0.120
ez+0.115
hered+0.104
 nightmares+0.099
 moment+0.095
Neg logit contributions
ires-0.093
ate-0.089
iring-0.089
um-0.089
ruce-0.077
Token Pixie
Token ID46687
Feature activation-1.10e-01

Pos logit contributions
ez+0.040
joy+0.040
hered+0.036
 nightmares+0.033
 moment+0.033
Neg logit contributions
ires-0.027
um-0.025
ate-0.025
iring-0.024
ruce-0.020
TokenThe
Token ID464
Feature activation-5.26e-04

Pos logit contributions
joy+0.022
ez+0.021
hered+0.019
 nightmares+0.018
 moment+0.018
Neg logit contributions
ires-0.015
ate-0.014
iring-0.014
um-0.014
ruce-0.012
Token oct
Token ID19318
Feature activation+3.24e-02

Pos logit contributions
joy+0.001
ez+0.001
hered+0.001
 nightmares+0.001
 moment+0.001
Neg logit contributions
ires-0.001
ate-0.001
iring-0.001
um-0.001
ruce-0.001
Tokenopus
Token ID25790
Feature activation-1.21e-02

Pos logit contributions
ires+0.058
ate+0.055
um+0.055
iring+0.055
ruce+0.050
Neg logit contributions
joy-0.060
ez-0.057
hered-0.051
 nightmares-0.046
 moment-0.046
Token was
Token ID373
Feature activation+1.38e-02

Pos logit contributions
joy+0.027
ez+0.024
hered+0.023
 nightmares+0.022
 heaven+0.021
Neg logit contributions
um-0.017
ate-0.017
ires-0.017
iring-0.016
lly-0.015
Token over
Token ID625
Feature activation+7.52e-02

Pos logit contributions
ires+0.018
iring+0.017
ate+0.017
um+0.017
ruce+0.015
Neg logit contributions
joy-0.031
ez-0.030
hered-0.028
 nightmares-0.026
 moment-0.026
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
um+0.197
ires+0.196
iring+0.196
ate+0.192
 Inside+0.185
Neg logit contributions
ez-0.057
ñ-0.047
Charl-0.041
hered-0.037
 nightmares-0.034
Tokened
Token ID276
Feature activation-7.88e-02

Pos logit contributions
joy+1.173
 nightmares+1.146
 heaven+1.119
ez+1.091
 forgetting+1.068
Neg logit contributions
um-0.818
ires-0.763
ate-0.752
iring-0.751
am-0.641
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
ez+0.184
joy+0.176
hered+0.165
 nightmares+0.164
Charl+0.162
Neg logit contributions
iring-0.099
um-0.099
ires-0.097
ate-0.091
ised-0.074
Token and
Token ID290
Feature activation-6.10e-02

Pos logit contributions
iring+0.012
ires+0.011
um+0.011
ate+0.011
 Inside+0.010
Neg logit contributions
ez-0.024
joy-0.022
hered-0.022
 nightmares-0.021
ñ-0.021
Token he
Token ID339
Feature activation-1.90e-02

Pos logit contributions
joy+0.134
ez+0.130
hered+0.119
 nightmares+0.115
Charl+0.111
Neg logit contributions
ires-0.084
iring-0.083
ate-0.082
um-0.081
lly-0.068
Token thanked
Token ID26280
Feature activation-1.84e-02

Pos logit contributions
joy+0.040
ez+0.038
hered+0.035
 nightmares+0.034
 heaven+0.033
Neg logit contributions
ires-0.028
ate-0.028
um-0.027
iring-0.027
ruce-0.024
Token rocket
Token ID10701
Feature activation-6.00e-02

Pos logit contributions
joy+0.084
ez+0.082
hered+0.077
smart+0.069
 liar+0.068
Neg logit contributions
ires-0.055
iring-0.053
um-0.051
ate-0.051
ruce-0.046
Token's
Token ID338
Feature activation-1.81e-01

Pos logit contributions
joy+0.133
ez+0.126
hered+0.113
Charl+0.109
 nightmares+0.107
Neg logit contributions
ires-0.082
ate-0.082
iring-0.081
um-0.079
lly-0.070
Token friends
Token ID2460
Feature activation+3.85e-02

Pos logit contributions
joy+0.345
ez+0.336
hered+0.312
Charl+0.275
ñ+0.272
Neg logit contributions
ires-0.310
iring-0.299
um-0.294
ate-0.290
ruce-0.259
Token were
Token ID547
Feature activation-3.49e-02

Pos logit contributions
ate+0.041
um+0.040
lly+0.040
iring+0.039
ires+0.038
Neg logit contributions
joy-0.087
ez-0.084
hered-0.076
 nightmares-0.076
ñ-0.075
Token over
Token ID625
Feature activation+7.68e-02

Pos logit contributions
joy+0.071
ez+0.069
hered+0.063
 nightmares+0.059
 moment+0.058
Neg logit contributions
ires-0.054
iring-0.053
um-0.053
ate-0.053
ruce-0.046
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.149
iring+0.147
um+0.145
ate+0.143
 Inside+0.131
Neg logit contributions
ez-0.121
ñ-0.105
hered-0.102
Charl-0.098
 liar-0.098
Tokened
Token ID276
Feature activation-7.66e-02

Pos logit contributions
joy+1.265
 failure+1.234
 nightmares+1.223
 liar+1.211
 heaven+1.204
Neg logit contributions
um-0.649
iring-0.601
ires-0.597
ate-0.586
am-0.534
Token to
Token ID284
Feature activation-2.51e-02

Pos logit contributions
ez+0.188
joy+0.177
hered+0.166
Charl+0.165
ñ+0.164
Neg logit contributions
iring-0.088
ires-0.086
um-0.083
ate-0.080
 up-0.064
Token have
Token ID423
Feature activation-1.41e-01

Pos logit contributions
joy+0.053
ez+0.051
hered+0.046
 nightmares+0.044
Charl+0.043
Neg logit contributions
ires-0.037
ate-0.036
um-0.035
iring-0.033
ered-0.031
Token him
Token ID683
Feature activation+2.35e-02

Pos logit contributions
joy+0.303
ez+0.291
hered+0.275
oing+0.269
 moment+0.266
Neg logit contributions
ate-0.191
um-0.172
ires-0.161
lly-0.158
iring-0.156
Token back
Token ID736
Feature activation-1.01e-01

Pos logit contributions
ate+0.023
um+0.022
iring+0.022
ires+0.021
 Inside+0.020
Neg logit contributions
ez-0.055
joy-0.055
Charl-0.051
hered-0.051
 liar-0.049
Token
Token ID198
Feature activation-1.03e-02

Pos logit contributions
joy+0.020
ez+0.019
hered+0.017
 nightmares+0.016
 moment+0.016
Neg logit contributions
ires-0.018
iring-0.017
ate-0.017
um-0.017
ruce-0.015
TokenCl
Token ID2601
Feature activation-1.30e-01

Pos logit contributions
joy+0.020
ez+0.019
hered+0.017
 nightmares+0.017
 moment+0.016
Neg logit contributions
ires-0.018
ate-0.017
um-0.017
iring-0.017
ruce-0.015
Tokenaire
Token ID7626
Feature activation-1.42e-01

Pos logit contributions
ez+0.256
joy+0.243
 nightmares+0.224
 breathing+0.217
smart+0.214
Neg logit contributions
um-0.234
ate-0.229
ires-0.228
iring-0.209
outed-0.182
Token was
Token ID373
Feature activation+1.43e-02

Pos logit contributions
joy+0.305
ez+0.282
hered+0.261
 nightmares+0.255
 heaven+0.247
Neg logit contributions
um-0.207
ate-0.206
ires-0.204
iring-0.195
lly-0.175
Token over
Token ID625
Feature activation+7.57e-02

Pos logit contributions
um+0.018
ate+0.017
iring+0.017
ires+0.017
ruce+0.014
Neg logit contributions
joy-0.032
ez-0.032
hered-0.029
 nightmares-0.028
ñ-0.027
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.215
um+0.215
iring+0.214
ate+0.208
 Inside+0.196
Neg logit contributions
ez-0.055
ñ-0.035
hered-0.029
oscope-0.026
 liar-0.026
Tokened
Token ID276
Feature activation-7.71e-02

Pos logit contributions
 nightmares+1.218
joy+1.208
 attacking+1.194
ez+1.187
 breathing+1.162
Neg logit contributions
um-0.756
ires-0.667
ate-0.664
iring-0.652
ised-0.521
Token -
Token ID532
Feature activation+3.74e-02

Pos logit contributions
ez+0.182
joy+0.172
hered+0.160
 nightmares+0.155
ñ+0.152
Neg logit contributions
um-0.101
iring-0.100
ires-0.100
ate-0.093
ised-0.072
Token her
Token ID607
Feature activation-4.40e-02

Pos logit contributions
um+0.052
ires+0.052
ate+0.049
iring+0.049
 Inside+0.044
Neg logit contributions
ez-0.084
joy-0.077
hered-0.073
 nightmares-0.070
ñ-0.068
Token mug
Token ID25152
Feature activation-1.70e-01

Pos logit contributions
ez+0.103
joy+0.095
hered+0.089
smart+0.086
ñ+0.083
Neg logit contributions
ires-0.059
um-0.058
iring-0.054
ate-0.052
ruce-0.048
Token had
Token ID550
Feature activation-1.51e-01

Pos logit contributions
joy+0.402
ez+0.384
hered+0.344
 nightmares+0.338
 heaven+0.328
Neg logit contributions
um-0.211
ate-0.201
ires-0.199
iring-0.196
lly-0.172
Token.
Token ID13
Feature activation-3.56e-02

Pos logit contributions
joy+0.436
ez+0.405
hered+0.365
 nightmares+0.350
Sleep+0.342
Neg logit contributions
ate-0.227
um-0.225
ires-0.223
iring-0.216
lly-0.202
Token The
Token ID383
Feature activation-3.20e-02

Pos logit contributions
joy+0.074
ez+0.072
hered+0.066
 nightmares+0.063
 moment+0.061
Neg logit contributions
ires-0.055
ate-0.052
um-0.052
iring-0.051
ruce-0.045
Token princess
Token ID21752
Feature activation-1.88e-01

Pos logit contributions
ez+0.066
joy+0.065
hered+0.059
 nightmares+0.054
Charl+0.052
Neg logit contributions
ires-0.051
um-0.048
ate-0.048
iring-0.047
ruce-0.041
Token was
Token ID373
Feature activation+1.28e-02

Pos logit contributions
joy+0.411
ez+0.386
hered+0.356
 nightmares+0.342
 heaven+0.328
Neg logit contributions
ires-0.271
ate-0.268
um-0.261
iring-0.259
ruce-0.223
Token over
Token ID625
Feature activation+7.27e-02

Pos logit contributions
ires+0.017
ate+0.016
iring+0.016
um+0.016
ruce+0.014
Neg logit contributions
joy-0.029
ez-0.028
hered-0.026
 nightmares-0.025
 moment-0.024
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.188
iring+0.186
um+0.186
ate+0.180
 Inside+0.167
Neg logit contributions
ez-0.076
ñ-0.053
hered-0.051
 nightmares-0.048
Charl-0.046
Tokened
Token ID276
Feature activation-7.90e-02

Pos logit contributions
joy+1.189
 nightmares+1.186
 heaven+1.131
 failure+1.131
ez+1.127
Neg logit contributions
um-0.780
ires-0.722
ate-0.712
iring-0.695
am-0.559
Token!
Token ID0
Feature activation-4.63e-02

Pos logit contributions
ez+0.180
joy+0.172
hered+0.158
 nightmares+0.157
ñ+0.149
Neg logit contributions
ires-0.107
um-0.106
iring-0.105
ate-0.101
 Inside-0.080
Token She
Token ID1375
Feature activation+3.43e-02

Pos logit contributions
joy+0.096
ez+0.093
hered+0.084
 nightmares+0.081
 moment+0.078
Neg logit contributions
ires-0.073
ate-0.069
um-0.069
iring-0.068
ruce-0.059
Token was
Token ID373
Feature activation+1.33e-02

Pos logit contributions
ires+0.061
iring+0.057
ate+0.056
um+0.055
ruce+0.051
Neg logit contributions
joy-0.064
ez-0.063
hered-0.056
 moment-0.052
 nightmares-0.052
Token so
Token ID523
Feature activation+5.52e-02

Pos logit contributions
ires+0.018
ate+0.017
iring+0.017
um+0.017
ruce+0.014
Neg logit contributions
joy-0.030
ez-0.029
hered-0.027
 nightmares-0.026
 moment-0.025
Token rock
Token ID3881
Feature activation+8.63e-02

Pos logit contributions
ires+0.223
ate+0.221
um+0.219
iring+0.205
ruce+0.182
Neg logit contributions
joy-0.298
ez-0.296
hered-0.264
 nightmares-0.251
Charl-0.245
Token.
Token ID13
Feature activation-3.05e-02

Pos logit contributions
ires+0.128
ate+0.123
iring+0.121
um+0.120
ruce+0.106
Neg logit contributions
joy-0.186
ez-0.176
hered-0.159
 nightmares-0.152
Charl-0.148
Token Lily
Token ID20037
Feature activation+2.35e-03

Pos logit contributions
joy+0.053
ez+0.048
hered+0.043
 moment+0.041
 heaven+0.040
Neg logit contributions
ires-0.059
iring-0.057
ate-0.057
um-0.054
ruce-0.051
Token was
Token ID373
Feature activation+1.66e-02

Pos logit contributions
ires+0.004
iring+0.004
ate+0.004
um+0.004
ruce+0.004
Neg logit contributions
joy-0.004
ez-0.004
hered-0.004
 moment-0.003
 knowing-0.003
Token over
Token ID625
Feature activation+7.54e-02

Pos logit contributions
ires+0.025
ate+0.023
iring+0.023
um+0.023
ruce+0.021
Neg logit contributions
joy-0.036
ez-0.034
hered-0.031
 nightmares-0.029
 moment-0.029
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.225
iring+0.222
um+0.222
ate+0.219
 Inside+0.208
Neg logit contributions
ez-0.050
hered-0.022
ching-0.018
ñ-0.017
 nightmares-0.017
Tokened
Token ID276
Feature activation-7.63e-02

Pos logit contributions
joy+1.198
 failure+1.155
 nightmares+1.154
ez+1.140
 attacking+1.135
Neg logit contributions
um-0.754
ires-0.709
ate-0.704
iring-0.684
 Inside-0.555
Token and
Token ID290
Feature activation-5.91e-02

Pos logit contributions
ez+0.170
joy+0.162
hered+0.150
 nightmares+0.145
 liar+0.138
Neg logit contributions
ires-0.108
iring-0.106
um-0.105
ate-0.103
ruce-0.083
Token knew
Token ID2993
Feature activation-9.81e-02

Pos logit contributions
joy+0.112
ez+0.105
hered+0.097
 knowing+0.093
 moment+0.090
Neg logit contributions
ires-0.105
iring-0.097
ate-0.097
um-0.095
ruce-0.088
Token it
Token ID340
Feature activation-2.29e-02

Pos logit contributions
joy+0.213
ez+0.205
hered+0.187
 nightmares+0.178
 moment+0.175
Neg logit contributions
ires-0.145
ate-0.136
iring-0.136
um-0.135
ruce-0.119
Token was
Token ID373
Feature activation+1.56e-02

Pos logit contributions
joy+0.057
ez+0.055
hered+0.050
 nightmares+0.047
 heaven+0.047
Neg logit contributions
ate-0.027
ires-0.026
iring-0.026
um-0.025
ruce-0.022
Token't
Token ID470
Feature activation+8.69e-03

Pos logit contributions
ires+0.135
ate+0.128
um+0.128
iring+0.127
ruce+0.113
Neg logit contributions
joy-0.182
ez-0.173
hered-0.156
 nightmares-0.149
 moment-0.146
Token help
Token ID1037
Feature activation-8.46e-02

Pos logit contributions
ires+0.013
ate+0.013
um+0.013
iring+0.013
ruce+0.011
Neg logit contributions
joy-0.018
ez-0.017
hered-0.016
 nightmares-0.015
 moment-0.015
Token but
Token ID475
Feature activation-5.75e-02

Pos logit contributions
joy+0.166
ez+0.160
hered+0.143
 nightmares+0.133
 heaven+0.130
Neg logit contributions
ires-0.145
iring-0.140
ate-0.137
um-0.136
ruce-0.122
Token feel
Token ID1254
Feature activation-8.82e-02

Pos logit contributions
joy+0.109
ez+0.105
hered+0.092
 nightmares+0.087
 heaven+0.082
Neg logit contributions
ires-0.101
iring-0.097
ate-0.096
um-0.096
ruce-0.086
Token over
Token ID625
Feature activation+7.75e-02

Pos logit contributions
joy+0.187
ez+0.183
hered+0.174
ñ+0.172
rav+0.160
Neg logit contributions
ires-0.122
iring-0.120
ate-0.116
um-0.109
ised-0.101
Tokenjoy
Token ID2633
Feature activation-5.58e-01

Pos logit contributions
ires+0.150
iring+0.146
ate+0.141
um+0.140
ised+0.123
Neg logit contributions
ez-0.124
ñ-0.111
hered-0.111
Charl-0.104
 tale-0.104
Tokened
Token ID276
Feature activation-7.82e-02

Pos logit contributions
joy+1.231
 nightmares+1.182
 heaven+1.163
 failure+1.149
 foe+1.140
Neg logit contributions
um-0.748
ires-0.699
iring-0.685
ate-0.681
am-0.586
Token.
Token ID13
Feature activation-3.36e-02

Pos logit contributions
ez+0.175
joy+0.170
hered+0.159
 nightmares+0.150
Charl+0.148
Neg logit contributions
ires-0.108
iring-0.107
um-0.104
ate-0.102
ruce-0.079
Token He
Token ID679
Feature activation+5.56e-02

Pos logit contributions
joy+0.071
ez+0.068
hered+0.061
 nightmares+0.058
 moment+0.058
Neg logit contributions
ires-0.052
ate-0.049
iring-0.048
um-0.048
ruce-0.043
Token felt
Token ID2936
Feature activation-6.66e-02

Pos logit contributions
ires+0.091
ate+0.087
um+0.086
iring+0.086
ruce+0.077
Neg logit contributions
joy-0.111
ez-0.106
hered-0.096
 nightmares-0.091
 moment-0.089
Token so
Token ID523
Feature activation+5.86e-02

Pos logit contributions
joy+0.140
ez+0.136
hered+0.124
 nightmares+0.117
ñ+0.115
Neg logit contributions
ires-0.100
ate-0.096
iring-0.095
um-0.094
ruce-0.083
Token win
Token ID1592
Feature activation-4.83e-02

Pos logit contributions
ez+0.090
joy+0.083
hered+0.076
 nightmares+0.072
Charl+0.072
Neg logit contributions
ires-0.045
ate-0.043
um-0.043
iring-0.038
her-0.036
Token.
Token ID13
Feature activation-3.38e-02

Pos logit contributions
joy+0.112
ez+0.105
 nightmares+0.095
hered+0.093
Charl+0.091
Neg logit contributions
um-0.062
ate-0.062
ires-0.060
iring-0.056
ered-0.053
Token Jane
Token ID12091
Feature activation+6.61e-02

Pos logit contributions
joy+0.069
ez+0.068
hered+0.062
 nightmares+0.060
 moment+0.056
Neg logit contributions
ires-0.054
um-0.051
ate-0.050
iring-0.049
 Inside-0.043
Token was
Token ID373
Feature activation+1.60e-02

Pos logit contributions
um+0.091
ate+0.090
ires+0.086
iring+0.083
lly+0.077
Neg logit contributions
joy-0.149
ez-0.134
hered-0.127
 nightmares-0.124
 heaven-0.122
Token over
Token ID625
Feature activation+7.75e-02

Pos logit contributions
um+0.018
ate+0.018
iring+0.018
ires+0.017
her+0.014
Neg logit contributions
joy-0.037
ez-0.037
hered-0.034
 nightmares-0.033
 disturbances-0.032
Tokenjoy
Token ID2633
Feature activation-5.57e-01

Pos logit contributions
um+0.214
ires+0.214
iring+0.213
ate+0.208
 Inside+0.192
Neg logit contributions
ez-0.062
ñ-0.040
hered-0.035
oscope-0.032
 villains-0.032
Tokened
Token ID276
Feature activation-7.72e-02

Pos logit contributions
joy+1.229
 nightmares+1.223
 attacking+1.191
ez+1.171
 failure+1.171
Neg logit contributions
um-0.739
ate-0.651
ires-0.650
iring-0.639
outed-0.503
Token!
Token ID0
Feature activation-4.46e-02

Pos logit contributions
ez+0.182
joy+0.172
hered+0.159
 nightmares+0.157
ñ+0.151
Neg logit contributions
um-0.102
ires-0.101
iring-0.101
ate-0.095
ised-0.074
Token<|endoftext|>
Token ID50256
Feature activation+2.83e-02

Pos logit contributions
ez+0.096
joy+0.095
hered+0.087
 nightmares+0.085
 heaven+0.079
Neg logit contributions
ires-0.066
um-0.063
ate-0.062
iring-0.060
 Inside-0.054
TokenOnce
Token ID7454
Feature activation-1.08e-01

Pos logit contributions
ate+0.035
um+0.033
ires+0.032
iring+0.031
 Inside+0.030
Neg logit contributions
ez-0.065
joy-0.064
 nightmares-0.060
 failure-0.058
 liar-0.058
Token upon
Token ID2402
Feature activation+1.11e-01

Pos logit contributions
joy+0.224
ez+0.197
 moment+0.191
hered+0.181
 nightmares+0.177
Neg logit contributions
ires-0.167
ate-0.166
iring-0.157
um-0.153
ruce-0.142
TokenS
Token ID50
Feature activation-5.22e-02

Pos logit contributions
joy+0.022
ez+0.021
hered+0.019
 moment+0.017
 nightmares+0.017
Neg logit contributions
ires-0.021
iring-0.020
ate-0.020
um-0.019
ruce-0.018
Tokenally
Token ID453
Feature activation+2.02e-01

Pos logit contributions
joy+0.137
ez+0.132
hered+0.124
 moment+0.117
 nightmares+0.116
Neg logit contributions
ires-0.054
ate-0.049
iring-0.049
um-0.046
ruce-0.039
Token was
Token ID373
Feature activation+1.49e-02

Pos logit contributions
um+0.295
ate+0.292
ires+0.286
iring+0.272
lly+0.243
Neg logit contributions
joy-0.436
ez-0.403
hered-0.373
 nightmares-0.366
 heaven-0.353
Token so
Token ID523
Feature activation+5.75e-02

Pos logit contributions
um+0.016
ate+0.016
iring+0.015
ires+0.015
her+0.013
Neg logit contributions
joy-0.036
ez-0.035
hered-0.033
 nightmares-0.032
ñ-0.031
Token over
Token ID625
Feature activation+7.84e-02

Pos logit contributions
ires+0.101
um+0.097
iring+0.097
ate+0.097
ruce+0.085
Neg logit contributions
joy-0.109
ez-0.104
hered-0.094
 nightmares-0.090
 moment-0.085
Tokenjoy
Token ID2633
Feature activation-5.57e-01

Pos logit contributions
um+0.112
ires+0.112
iring+0.109
ate+0.105
 Inside+0.092
Neg logit contributions
ez-0.167
hered-0.144
ñ-0.143
 liar-0.136
 nightmares-0.135
Tokened
Token ID276
Feature activation-7.62e-02

Pos logit contributions
joy+1.165
 nightmares+1.120
ez+1.096
 heaven+1.067
 failure+1.059
Neg logit contributions
um-0.855
ires-0.801
ate-0.770
iring-0.769
ised-0.642
Token with
Token ID351
Feature activation+7.66e-02

Pos logit contributions
ez+0.172
joy+0.171
hered+0.154
 nightmares+0.149
ñ+0.142
Neg logit contributions
ires-0.104
um-0.103
iring-0.101
ate-0.097
ruce-0.079
Token her
Token ID607
Feature activation-4.31e-02

Pos logit contributions
ires+0.120
iring+0.112
ate+0.112
um+0.111
ruce+0.099
Neg logit contributions
joy-0.160
ez-0.155
hered-0.142
 nightmares-0.133
 moment-0.131
Token present
Token ID1944
Feature activation+5.20e-03

Pos logit contributions
ez+0.105
joy+0.099
hered+0.094
 nightmares+0.084
Charl+0.084
Neg logit contributions
ires-0.056
um-0.055
iring-0.051
ate-0.049
ruce-0.042
Token that
Token ID326
Feature activation+1.50e-01

Pos logit contributions
um+0.007
iring+0.006
ires+0.006
ate+0.006
 Inside+0.005
Neg logit contributions
ez-0.013
joy-0.013
 nightmares-0.011
hered-0.010
 heaven-0.010
Token park
Token ID3952
Feature activation+1.10e-01

Pos logit contributions
joy+0.083
ez+0.079
hered+0.073
 nightmares+0.070
 moment+0.069
Neg logit contributions
ires-0.050
iring-0.047
ate-0.046
um-0.046
ruce-0.040
Token!
Token ID0
Feature activation-4.11e-02

Pos logit contributions
ires+0.145
ate+0.144
um+0.143
iring+0.142
ruce+0.119
Neg logit contributions
ez-0.240
joy-0.239
hered-0.213
 nightmares-0.208
Charl-0.202
Token He
Token ID679
Feature activation+5.54e-02

Pos logit contributions
joy+0.085
ez+0.082
hered+0.074
 nightmares+0.070
 moment+0.069
Neg logit contributions
ires-0.065
ate-0.061
iring-0.061
um-0.060
ruce-0.054
Token was
Token ID373
Feature activation+1.57e-02

Pos logit contributions
ires+0.103
iring+0.095
ate+0.093
um+0.092
ruce+0.085
Neg logit contributions
joy-0.103
ez-0.100
hered-0.089
 moment-0.083
 nightmares-0.082
Token over
Token ID625
Feature activation+7.75e-02

Pos logit contributions
ires+0.021
iring+0.020
ate+0.020
um+0.019
ruce+0.017
Neg logit contributions
joy-0.036
ez-0.035
hered-0.032
 nightmares-0.031
 moment-0.030
Tokenjoy
Token ID2633
Feature activation-5.57e-01

Pos logit contributions
ires+0.229
iring+0.227
um+0.226
ate+0.224
 Inside+0.213
Neg logit contributions
ez-0.046
hered-0.023
 nightmares-0.017
ñ-0.017
Charl-0.017
Tokened
Token ID276
Feature activation-7.72e-02

Pos logit contributions
joy+1.164
 nightmares+1.137
ez+1.108
 heaven+1.103
 failure+1.101
Neg logit contributions
um-0.778
ires-0.734
iring-0.709
ate-0.708
am-0.622
Token.
Token ID13
Feature activation-2.89e-02

Pos logit contributions
ez+0.168
joy+0.161
hered+0.148
 nightmares+0.147
 heaven+0.140
Neg logit contributions
ires-0.109
iring-0.108
um-0.107
ate-0.104
ruce-0.084
Token He
Token ID679
Feature activation+5.53e-02

Pos logit contributions
joy+0.059
ez+0.055
hered+0.050
 moment+0.047
 nightmares+0.047
Neg logit contributions
ires-0.047
ate-0.045
iring-0.044
um-0.044
ruce-0.040
Token thanked
Token ID26280
Feature activation-1.68e-02

Pos logit contributions
ires+0.106
iring+0.098
ate+0.096
um+0.093
ruce+0.087
Neg logit contributions
joy-0.100
ez-0.097
hered-0.087
 moment-0.079
 knowing-0.079
Token the
Token ID262
Feature activation-3.78e-02

Pos logit contributions
ez+0.039
joy+0.038
hered+0.035
 nightmares+0.033
ching+0.032
Neg logit contributions
ires-0.022
um-0.022
ate-0.021
iring-0.020
 Inside-0.018
Token
Token ID198
Feature activation-1.08e-02

Pos logit contributions
joy+0.156
ez+0.148
hered+0.135
 nightmares+0.123
 moment+0.122
Neg logit contributions
ires-0.151
iring-0.143
ate-0.142
um-0.141
ruce-0.130
TokenL
Token ID43
Feature activation+1.20e-02

Pos logit contributions
joy+0.024
ez+0.023
hered+0.021
 nightmares+0.021
 breathing+0.020
Neg logit contributions
ires-0.015
um-0.015
ate-0.015
iring-0.014
ruce-0.013
Tokenilly
Token ID6548
Feature activation+1.09e-01

Pos logit contributions
ires+0.015
ate+0.014
um+0.013
iring+0.013
ruce+0.011
Neg logit contributions
joy-0.030
ez-0.028
hered-0.027
 nightmares-0.026
 moment-0.025
Token was
Token ID373
Feature activation+1.79e-02

Pos logit contributions
um+0.165
ate+0.165
ires+0.165
iring+0.157
ruce+0.140
Neg logit contributions
joy-0.224
ez-0.213
hered-0.193
 nightmares-0.185
 moment-0.179
Token over
Token ID625
Feature activation+7.91e-02

Pos logit contributions
ate+0.023
ires+0.023
um+0.023
iring+0.022
her+0.019
Neg logit contributions
joy-0.039
ez-0.039
hered-0.036
 nightmares-0.034
 moment-0.033
Tokenjoy
Token ID2633
Feature activation-5.57e-01

Pos logit contributions
ires+0.207
um+0.204
iring+0.202
ate+0.199
 Inside+0.190
Neg logit contributions
ez-0.072
ñ-0.047
hered-0.047
ching-0.041
oing-0.041
Tokened
Token ID276
Feature activation-7.75e-02

Pos logit contributions
joy+1.196
 nightmares+1.144
ez+1.123
 heaven+1.118
 failure+1.118
Neg logit contributions
um-0.770
ires-0.723
ate-0.710
iring-0.706
outed-0.582
Token and
Token ID290
Feature activation-6.06e-02

Pos logit contributions
ez+0.176
joy+0.170
hered+0.156
 nightmares+0.151
ñ+0.146
Neg logit contributions
ires-0.105
iring-0.104
um-0.103
ate-0.098
ised-0.078
Token felt
Token ID2936
Feature activation-6.55e-02

Pos logit contributions
joy+0.129
ez+0.124
hered+0.113
 nightmares+0.107
 moment+0.105
Neg logit contributions
ires-0.092
ate-0.087
iring-0.087
um-0.086
ruce-0.076
Token so
Token ID523
Feature activation+6.11e-02

Pos logit contributions
joy+0.141
ez+0.139
hered+0.127
 nightmares+0.120
 moment+0.117
Neg logit contributions
ires-0.091
ate-0.090
iring-0.088
um-0.087
ruce-0.076
Token lucky
Token ID9670
Feature activation-6.74e-02

Pos logit contributions
ires+0.116
ate+0.110
iring+0.110
um+0.109
ruce+0.101
Neg logit contributions
joy-0.107
ez-0.101
hered-0.090
 moment-0.084
 nightmares-0.084
Token beach
Token ID10481
Feature activation+2.24e-01

Pos logit contributions
joy+0.077
 moment+0.069
ez+0.062
 payoff+0.062
hered+0.061
Neg logit contributions
ires-0.050
iring-0.045
um-0.042
ate-0.041
outed-0.041
Token,
Token ID11
Feature activation+1.47e-02

Pos logit contributions
ires+0.331
ate+0.317
iring+0.313
um+0.312
ruce+0.271
Neg logit contributions
joy-0.476
ez-0.473
hered-0.426
 nightmares-0.405
 moment-0.387
Token Maggie
Token ID33014
Feature activation+4.95e-03

Pos logit contributions
ires+0.025
ate+0.023
iring+0.023
um+0.023
ruce+0.021
Neg logit contributions
joy-0.029
ez-0.027
hered-0.025
 moment-0.024
 nightmares-0.023
Token was
Token ID373
Feature activation+1.72e-02

Pos logit contributions
ires+0.008
iring+0.007
ate+0.007
um+0.007
ruce+0.006
Neg logit contributions
joy-0.010
ez-0.010
hered-0.009
 nightmares-0.009
 moment-0.008
Token over
Token ID625
Feature activation+7.98e-02

Pos logit contributions
ires+0.029
ate+0.027
iring+0.027
um+0.026
ruce+0.024
Neg logit contributions
joy-0.035
ez-0.033
hered-0.030
 nightmares-0.028
 moment-0.028
Tokenjoy
Token ID2633
Feature activation-5.57e-01

Pos logit contributions
ires+0.243
um+0.239
iring+0.238
ate+0.238
 Inside+0.224
Neg logit contributions
ez-0.047
hered-0.024
ñ-0.018
 nightmares-0.016
ching-0.013
Tokened
Token ID276
Feature activation-7.77e-02

Pos logit contributions
joy+1.202
ez+1.145
 nightmares+1.141
 failure+1.138
 attacking+1.114
Neg logit contributions
um-0.790
ires-0.727
iring-0.716
ate-0.692
am-0.597
Token.
Token ID13
Feature activation-3.17e-02

Pos logit contributions
ez+0.183
joy+0.170
hered+0.162
 nightmares+0.154
ñ+0.152
Neg logit contributions
ires-0.101
iring-0.100
um-0.099
ate-0.095
ruce-0.075
Token She
Token ID1375
Feature activation+3.98e-02

Pos logit contributions
joy+0.062
ez+0.055
hered+0.049
 moment+0.049
 nightmares+0.047
Neg logit contributions
ires-0.054
ate-0.052
iring-0.052
um-0.050
ruce-0.048
Token jumped
Token ID11687
Feature activation-1.06e-02

Pos logit contributions
ires+0.072
iring+0.067
ate+0.062
um+0.060
ruce+0.056
Neg logit contributions
joy-0.076
ez-0.075
hered-0.067
 knowing-0.063
 moment-0.062
Token in
Token ID287
Feature activation+1.03e-01

Pos logit contributions
joy+0.024
ez+0.023
hered+0.022
 moment+0.020
 knowing+0.020
Neg logit contributions
ires-0.015
iring-0.014
ate-0.013
um-0.013
ruce-0.012
Token mountain
Token ID8598
Feature activation+1.46e-02

Pos logit contributions
joy+0.090
ez+0.090
hered+0.083
 nightmares+0.077
 heaven+0.075
Neg logit contributions
ires-0.046
um-0.044
iring-0.043
ate-0.042
ruce-0.036
Token.
Token ID13
Feature activation-3.33e-02

Pos logit contributions
ires+0.021
ate+0.020
iring+0.020
um+0.020
ruce+0.017
Neg logit contributions
joy-0.031
ez-0.031
hered-0.028
 nightmares-0.027
Charl-0.026
Token He
Token ID679
Feature activation+5.47e-02

Pos logit contributions
joy+0.071
ez+0.068
hered+0.062
 nightmares+0.059
 moment+0.058
Neg logit contributions
ires-0.051
iring-0.048
ate-0.047
um-0.047
ruce-0.042
Token was
Token ID373
Feature activation+1.76e-02

Pos logit contributions
ires+0.095
iring+0.089
um+0.087
ate+0.087
ruce+0.079
Neg logit contributions
joy-0.106
ez-0.104
hered-0.092
 nightmares-0.087
 moment-0.087
Token over
Token ID625
Feature activation+7.84e-02

Pos logit contributions
ires+0.023
ate+0.023
iring+0.023
um+0.022
ruce+0.019
Neg logit contributions
joy-0.039
ez-0.038
hered-0.036
 nightmares-0.034
 moment-0.033
Tokenjoy
Token ID2633
Feature activation-5.57e-01

Pos logit contributions
ires+0.188
iring+0.186
um+0.185
ate+0.183
ised+0.169
Neg logit contributions
ez-0.089
hered-0.072
ñ-0.066
Charl-0.065
 tale-0.063
Tokened
Token ID276
Feature activation-7.83e-02

Pos logit contributions
joy+1.182
 nightmares+1.149
 heaven+1.148
ez+1.122
 failure+1.101
Neg logit contributions
um-0.753
ires-0.722
iring-0.709
ate-0.691
am-0.609
Token.
Token ID13
Feature activation-3.17e-02

Pos logit contributions
ez+0.176
joy+0.169
hered+0.158
 nightmares+0.153
 heaven+0.149
Neg logit contributions
iring-0.106
ires-0.106
um-0.102
ate-0.101
ised-0.081
Token He
Token ID679
Feature activation+5.48e-02

Pos logit contributions
joy+0.068
ez+0.065
hered+0.059
 nightmares+0.056
 moment+0.055
Neg logit contributions
ires-0.048
iring-0.045
ate-0.045
um-0.045
ruce-0.040
Token looked
Token ID3114
Feature activation+6.33e-02

Pos logit contributions
ires+0.100
iring+0.094
ate+0.091
um+0.090
ruce+0.083
Neg logit contributions
joy-0.102
ez-0.101
hered-0.088
 moment-0.083
 nightmares-0.082
Token back
Token ID736
Feature activation-9.89e-02

Pos logit contributions
ires+0.091
ate+0.087
um+0.084
iring+0.083
ruce+0.075
Neg logit contributions
joy-0.146
ez-0.130
hered-0.119
 moment-0.118
 knowing-0.117
Token,
Token ID11
Feature activation+1.83e-02

Pos logit contributions
ez+0.192
joy+0.192
hered+0.170
 tale+0.162
oing+0.161
Neg logit contributions
um-0.082
ires-0.074
ate-0.073
iring-0.072
 Inside-0.068
Token she
Token ID673
Feature activation-7.80e-02

Pos logit contributions
ires+0.027
ate+0.026
iring+0.026
um+0.026
ruce+0.023
Neg logit contributions
joy-0.038
ez-0.038
hered-0.034
 nightmares-0.031
 tale-0.030
Token decided
Token ID3066
Feature activation+9.25e-02

Pos logit contributions
ez+0.134
joy+0.132
hered+0.115
 nightmares+0.113
 moment+0.104
Neg logit contributions
ires-0.157
iring-0.146
ate-0.141
um-0.139
ruce-0.129
Token to
Token ID284
Feature activation-2.29e-02

Pos logit contributions
ires+0.123
ate+0.118
um+0.117
iring+0.117
ruce+0.104
Neg logit contributions
ez-0.208
joy-0.203
hered-0.187
 nightmares-0.169
 moment-0.167
Token tidy
Token ID43044
Feature activation+1.86e-01

Pos logit contributions
ez+0.039
 heaven+0.037
hered+0.037
joy+0.036
 nightmares+0.036
Neg logit contributions
ires-0.042
iring-0.040
um-0.036
outed-0.035
ate-0.034
Token up
Token ID510
Feature activation+2.58e-01

Pos logit contributions
ires+0.304
iring+0.288
um+0.286
ate+0.269
ruce+0.247
Neg logit contributions
joy-0.372
ez-0.354
 nightmares-0.314
hered-0.311
 moment-0.308
Token her
Token ID607
Feature activation-4.21e-02

Pos logit contributions
ires+0.386
ate+0.371
iring+0.358
um+0.354
ruce+0.316
Neg logit contributions
joy-0.553
ez-0.538
hered-0.497
 nightmares-0.457
 moment-0.447
Token room
Token ID2119
Feature activation+9.03e-02

Pos logit contributions
joy+0.092
ez+0.087
 nightmares+0.080
hered+0.079
 moment+0.078
Neg logit contributions
ires-0.061
um-0.057
ate-0.057
iring-0.057
ruce-0.050
Token.
Token ID13
Feature activation-2.20e-02

Pos logit contributions
ires+0.148
ate+0.141
iring+0.140
um+0.139
ruce+0.124
Neg logit contributions
joy-0.180
ez-0.174
hered-0.157
 nightmares-0.147
 moment-0.144
Token She
Token ID1375
Feature activation+4.50e-02

Pos logit contributions
joy+0.043
ez+0.039
hered+0.036
 nightmares+0.034
 moment+0.034
Neg logit contributions
ires-0.039
iring-0.037
ate-0.037
um-0.036
ruce-0.033
Token put
Token ID1234
Feature activation+2.25e-01

Pos logit contributions
ires+0.093
iring+0.088
um+0.078
ate+0.073
ruce+0.066
Neg logit contributions
ez-0.079
joy-0.072
 moment-0.066
 nightmares-0.065
hered-0.064
Token know
Token ID760
Feature activation-6.97e-03

Pos logit contributions
ires+0.019
iring+0.018
ate+0.018
um+0.018
ruce+0.016
Neg logit contributions
joy-0.019
ez-0.019
hered-0.017
 nightmares-0.016
 moment-0.015
Token.
Token ID13
Feature activation-2.92e-02

Pos logit contributions
joy+0.015
ez+0.015
hered+0.014
 moment+0.012
 nightmares+0.012
Neg logit contributions
ires-0.011
iring-0.010
ate-0.010
um-0.009
ruce-0.008
Token It
Token ID632
Feature activation+2.18e-02

Pos logit contributions
joy+0.046
ez+0.044
hered+0.038
 nightmares+0.036
 moment+0.035
Neg logit contributions
ires-0.058
um-0.056
iring-0.056
ate-0.056
ruce-0.053
Token looks
Token ID3073
Feature activation+3.27e-02

Pos logit contributions
ires+0.043
ate+0.041
iring+0.040
um+0.040
ruce+0.037
Neg logit contributions
joy-0.038
ez-0.035
hered-0.031
 nightmares-0.028
 moment-0.028
Token really
Token ID1107
Feature activation+1.46e-01

Pos logit contributions
ires+0.050
um+0.048
ate+0.048
iring+0.047
ruce+0.042
Neg logit contributions
joy-0.069
ez-0.066
hered-0.059
 nightmares-0.058
 moment-0.056
Token unusual
Token ID8468
Feature activation+2.47e-01

Pos logit contributions
um+0.235
iring+0.233
ires+0.227
ate+0.218
ruce+0.207
Neg logit contributions
joy-0.270
ez-0.245
 nightmares-0.233
 breathing-0.224
 moment-0.223
Token!"
Token ID2474
Feature activation+7.12e-02

Pos logit contributions
ires+0.394
iring+0.370
ate+0.369
um+0.362
ruce+0.318
Neg logit contributions
joy-0.513
ez-0.495
hered-0.458
 nightmares-0.415
 moment-0.411
Token
Token ID198
Feature activation-7.58e-03

Pos logit contributions
ires+0.102
um+0.096
ate+0.095
iring+0.095
 Inside+0.084
Neg logit contributions
joy-0.157
ez-0.153
hered-0.141
 nightmares-0.135
 tale-0.127
Token
Token ID198
Feature activation-7.92e-03

Pos logit contributions
joy+0.012
ez+0.012
hered+0.010
 moment+0.010
Charl+0.009
Neg logit contributions
ires-0.015
iring-0.014
um-0.014
ate-0.014
outed-0.013
TokenJohn
Token ID7554
Feature activation-6.07e-02

Pos logit contributions
joy+0.012
ez+0.012
hered+0.010
 moment+0.010
Charl+0.010
Neg logit contributions
ires-0.016
iring-0.015
ate-0.015
um-0.015
ruce-0.014
Token decided
Token ID3066
Feature activation+9.02e-02

Pos logit contributions
ez+0.110
joy+0.108
hered+0.096
 moment+0.090
 nightmares+0.087
Neg logit contributions
ires-0.115
iring-0.107
ate-0.101
um-0.098
ruce-0.095
Token pour
Token ID12797
Feature activation+1.09e-01

Pos logit contributions
joy+0.054
ez+0.054
hered+0.048
 moment+0.047
 nightmares+0.047
Neg logit contributions
ires-0.042
iring-0.040
um-0.039
ate-0.037
ruce-0.033
Token.
Token ID13
Feature activation-2.95e-02

Pos logit contributions
ires+0.182
iring+0.171
ate+0.171
um+0.167
ruce+0.151
Neg logit contributions
joy-0.215
ez-0.207
hered-0.187
 nightmares-0.177
 moment-0.176
Token The
Token ID383
Feature activation-2.67e-02

Pos logit contributions
joy+0.052
ez+0.048
hered+0.044
 moment+0.042
 nightmares+0.040
Neg logit contributions
ires-0.056
iring-0.054
ate-0.052
um-0.051
ruce-0.048
Token milk
Token ID7545
Feature activation-6.28e-02

Pos logit contributions
joy+0.057
ez+0.054
hered+0.049
 moment+0.048
 nightmares+0.048
Neg logit contributions
ires-0.040
ate-0.038
iring-0.037
um-0.036
ruce-0.033
Token bub
Token ID10015
Feature activation+7.99e-02

Pos logit contributions
joy+0.126
ez+0.123
hered+0.112
 moment+0.105
 nightmares+0.105
Neg logit contributions
ires-0.101
ate-0.094
iring-0.094
um-0.092
ruce-0.083
Tokenbled
Token ID9342
Feature activation+2.44e-01

Pos logit contributions
ires+0.106
iring+0.094
ate+0.094
um+0.092
ruce+0.084
Neg logit contributions
ez-0.178
joy-0.174
hered-0.165
 moment-0.152
 breathing-0.149
Token and
Token ID290
Feature activation-5.36e-02

Pos logit contributions
ires+0.337
um+0.329
iring+0.325
ate+0.317
ruce+0.276
Neg logit contributions
joy-0.554
ez-0.524
hered-0.484
 nightmares-0.454
 heaven-0.449
Token ste
Token ID2876
Feature activation-5.23e-02

Pos logit contributions
joy+0.117
ez+0.110
hered+0.102
 nightmares+0.095
 heaven+0.092
Neg logit contributions
ires-0.079
ate-0.075
um-0.075
iring-0.074
ruce-0.066
Tokenamed
Token ID2434
Feature activation+1.08e-01

Pos logit contributions
ez+0.102
joy+0.094
hered+0.089
 moment+0.081
 nightmares+0.078
Neg logit contributions
ires-0.089
iring-0.081
ate-0.076
um-0.076
ruce-0.074
Token as
Token ID355
Feature activation+2.92e-02

Pos logit contributions
ires+0.152
iring+0.145
um+0.145
ate+0.144
ruce+0.122
Neg logit contributions
joy-0.242
ez-0.232
hered-0.217
 nightmares-0.205
 moment-0.200
Token it
Token ID340
Feature activation-2.09e-02

Pos logit contributions
ires+0.042
iring+0.040
ate+0.040
um+0.039
ruce+0.032
Neg logit contributions
ez-0.067
joy-0.066
hered-0.061
 tale-0.055
 nightmares-0.054
Token
Token ID198
Feature activation-1.23e-02

Pos logit contributions
joy+0.022
ez+0.022
hered+0.019
 moment+0.018
 nightmares+0.017
Neg logit contributions
ires-0.024
iring-0.023
ate-0.022
um-0.022
ruce-0.020
TokenThe
Token ID464
Feature activation+1.57e-03

Pos logit contributions
joy+0.026
ez+0.024
hered+0.022
 nightmares+0.021
 moment+0.021
Neg logit contributions
ires-0.020
ate-0.018
iring-0.018
um-0.018
ruce-0.016
Token old
Token ID1468
Feature activation+2.43e-01

Pos logit contributions
um+0.002
ires+0.002
ate+0.002
iring+0.002
 old+0.002
Neg logit contributions
ez-0.004
joy-0.004
hered-0.003
 nightmares-0.003
Charl-0.003
Token man
Token ID582
Feature activation-3.35e-02

Pos logit contributions
um+0.282
ate+0.275
ires+0.260
iring+0.227
 elevator+0.211
Neg logit contributions
ez-0.606
hered-0.556
joy-0.544
 nightmares-0.540
 unnecessary-0.517
Token walked
Token ID6807
Feature activation-1.42e-02

Pos logit contributions
joy+0.071
ez+0.067
hered+0.061
 nightmares+0.060
 moment+0.057
Neg logit contributions
ires-0.050
ate-0.049
um-0.048
iring-0.047
ruce-0.041
Token up
Token ID510
Feature activation+2.59e-01

Pos logit contributions
joy+0.031
ez+0.029
hered+0.027
 moment+0.025
 nightmares+0.025
Neg logit contributions
ires-0.022
ate-0.020
iring-0.020
um-0.020
ruce-0.018
Token to
Token ID284
Feature activation-2.42e-02

Pos logit contributions
ires+0.323
ate+0.319
um+0.315
iring+0.304
 Inside+0.289
Neg logit contributions
ez-0.593
joy-0.553
 nightmares-0.518
hered-0.509
 tale-0.493
Token the
Token ID262
Feature activation-3.97e-02

Pos logit contributions
ez+0.054
joy+0.053
hered+0.048
 nightmares+0.048
 tale+0.044
Neg logit contributions
ires-0.033
ate-0.032
um-0.030
iring-0.030
 Inside-0.026
Token child
Token ID1200
Feature activation-2.06e-01

Pos logit contributions
ez+0.085
joy+0.080
hered+0.074
 nightmares+0.071
smart+0.067
Neg logit contributions
ires-0.060
iring-0.059
um-0.058
ate-0.056
 windows-0.048
Token and
Token ID290
Feature activation-6.07e-02

Pos logit contributions
joy+0.431
ez+0.425
hered+0.377
 nightmares+0.377
 liar+0.361
Neg logit contributions
ires-0.293
um-0.289
ate-0.282
iring-0.276
 Inside-0.247
Token asked
Token ID1965
Feature activation+2.24e-01

Pos logit contributions
joy+0.151
ez+0.146
hered+0.135
 nightmares+0.130
 moment+0.127
Neg logit contributions
ires-0.069
ate-0.065
iring-0.064
um-0.063
ruce-0.053
Token leash
Token ID40529
Feature activation-9.08e-02

Pos logit contributions
joy+0.044
ez+0.041
hered+0.037
Charl+0.034
 knowing+0.034
Neg logit contributions
ires-0.033
um-0.031
iring-0.031
ate-0.031
outed-0.027
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
joy+0.158
ez+0.156
hered+0.143
 nightmares+0.134
 moment+0.131
Neg logit contributions
ires-0.164
ate-0.155
iring-0.154
um-0.152
ruce-0.141
Token Do
Token ID2141
Feature activation-2.24e-01

Pos logit contributions
joy+0.038
ez+0.036
hered+0.033
 nightmares+0.030
 moment+0.030
Neg logit contributions
ires-0.042
ate-0.040
iring-0.040
um-0.040
ruce-0.036
Token you
Token ID345
Feature activation+1.64e-02

Pos logit contributions
joy+0.411
ez+0.404
hered+0.365
 nightmares+0.353
 moment+0.337
Neg logit contributions
ires-0.386
iring-0.371
ate-0.370
um-0.362
ruce-0.330
Token understand
Token ID1833
Feature activation-1.48e-01

Pos logit contributions
ires+0.032
iring+0.030
ate+0.030
um+0.030
ruce+0.027
Neg logit contributions
joy-0.028
ez-0.028
hered-0.024
 nightmares-0.023
 moment-0.022
Token?"
Token ID1701
Feature activation+3.22e-01

Pos logit contributions
ez+0.364
joy+0.346
 nightmares+0.331
hered+0.327
 heaven+0.325
Neg logit contributions
ires-0.154
iring-0.152
um-0.135
ate-0.128
outed-0.118
Token uncle
Token ID7711
Feature activation+1.59e-02

Pos logit contributions
ires+0.512
ate+0.482
iring+0.480
um+0.476
ruce+0.425
Neg logit contributions
joy-0.666
ez-0.640
hered-0.582
 nightmares-0.550
 moment-0.541
Token Ben
Token ID3932
Feature activation-3.66e-02

Pos logit contributions
ires+0.025
ate+0.024
iring+0.023
um+0.023
ruce+0.021
Neg logit contributions
joy-0.033
ez-0.032
hered-0.029
 nightmares-0.027
 moment-0.027
Token said
Token ID531
Feature activation+1.83e-01

Pos logit contributions
joy+0.095
ez+0.092
hered+0.085
 nightmares+0.082
 moment+0.081
Neg logit contributions
ires-0.038
ate-0.035
um-0.035
iring-0.034
ruce-0.029
Token.
Token ID13
Feature activation-2.34e-02

Pos logit contributions
um+0.202
ires+0.197
iring+0.189
ate+0.169
outed+0.150
Neg logit contributions
ez-0.451
joy-0.443
 nightmares-0.404
Charl-0.402
hered-0.398
Token
Token ID198
Feature activation-4.29e-04

Pos logit contributions
joy+0.047
ez+0.045
hered+0.041
 nightmares+0.039
 moment+0.038
Neg logit contributions
ires-0.038
ate-0.036
iring-0.036
um-0.036
ruce-0.032
Token help
Token ID1037
Feature activation-8.48e-02

Pos logit contributions
joy+0.350
ez+0.348
hered+0.313
 moment+0.286
ñ+0.282
Neg logit contributions
ires-0.215
ate-0.207
iring-0.197
um-0.192
ruce-0.171
Token from
Token ID422
Feature activation+1.64e-02

Pos logit contributions
joy+0.197
ez+0.190
hered+0.171
 moment+0.156
 nightmares+0.156
Neg logit contributions
ires-0.124
ate-0.118
iring-0.115
um-0.111
ruce-0.095
Token others
Token ID1854
Feature activation-2.62e-02

Pos logit contributions
ires+0.027
ate+0.026
iring+0.025
um+0.024
ruce+0.021
Neg logit contributions
joy-0.034
ez-0.033
hered-0.030
 moment-0.027
ñ-0.026
Token to
Token ID284
Feature activation-2.86e-02

Pos logit contributions
joy+0.067
ez+0.065
hered+0.058
ñ+0.055
 liar+0.052
Neg logit contributions
ires-0.033
ate-0.030
iring-0.029
um-0.026
her-0.023
Token learn
Token ID2193
Feature activation-6.14e-02

Pos logit contributions
joy+0.053
ez+0.051
hered+0.047
 nightmares+0.044
 heaven+0.044
Neg logit contributions
ires-0.050
iring-0.047
um-0.047
ate-0.046
ruce-0.042
Token new
Token ID649
Feature activation+3.40e-02

Pos logit contributions
joy+0.139
ez+0.136
hered+0.124
 moment+0.110
 nightmares+0.109
Neg logit contributions
ires-0.092
ate-0.088
iring-0.085
um-0.081
ruce-0.073
Token things
Token ID1243
Feature activation-2.95e-02

Pos logit contributions
ate+0.039
ires+0.038
iring+0.032
um+0.031
ised+0.026
Neg logit contributions
joy-0.087
ez-0.087
hered-0.084
oled-0.074
Charl-0.073
Token.
Token ID13
Feature activation-3.29e-02

Pos logit contributions
joy+0.068
ez+0.066
hered+0.058
 nightmares+0.054
 heaven+0.052
Neg logit contributions
ires-0.044
ate-0.042
iring-0.041
um-0.038
ruce-0.035
Token And
Token ID843
Feature activation-1.96e-01

Pos logit contributions
joy+0.066
ez+0.062
hered+0.057
 nightmares+0.054
 moment+0.053
Neg logit contributions
ires-0.057
ate-0.054
um-0.052
iring-0.052
 Inside-0.046
Token if
Token ID611
Feature activation-7.86e-03

Pos logit contributions
joy+0.387
ez+0.373
hered+0.336
 nightmares+0.315
 moment+0.308
Neg logit contributions
ires-0.332
ate-0.313
iring-0.313
um-0.308
ruce-0.277
Token we
Token ID356
Feature activation-7.65e-02

Pos logit contributions
ez+0.016
joy+0.016
hered+0.014
 nightmares+0.013
Charl+0.013
Neg logit contributions
ires-0.013
ate-0.012
iring-0.012
um-0.012
ruce-0.010
Token her
Token ID607
Feature activation-4.41e-02

Pos logit contributions
ires+0.035
um+0.034
iring+0.033
ate+0.033
ruce+0.032
Neg logit contributions
joy-0.034
ez-0.031
 nightmares-0.027
 heaven-0.027
hered-0.027
Token special
Token ID2041
Feature activation+1.46e-01

Pos logit contributions
ez+0.091
joy+0.091
hered+0.083
 nightmares+0.076
 moment+0.075
Neg logit contributions
ires-0.070
iring-0.065
ate-0.065
um-0.064
ruce-0.056
Token object
Token ID2134
Feature activation+1.45e-01

Pos logit contributions
ires+0.241
ate+0.230
um+0.228
iring+0.225
ruce+0.200
Neg logit contributions
joy-0.285
ez-0.285
hered-0.255
 nightmares-0.243
 heaven-0.230
Token.
Token ID13
Feature activation-3.15e-02

Pos logit contributions
ires+0.199
iring+0.190
um+0.190
ate+0.180
ruce+0.149
Neg logit contributions
joy-0.327
ez-0.324
hered-0.292
 nightmares-0.273
 moment-0.268
Token She
Token ID1375
Feature activation+4.03e-02

Pos logit contributions
ez+0.075
joy+0.072
hered+0.069
 attacking+0.067
 roaring+0.066
Neg logit contributions
ires-0.041
um-0.039
ate-0.039
 Inside-0.036
iring-0.036
Token was
Token ID373
Feature activation+1.63e-02

Pos logit contributions
ires+0.068
ate+0.065
um+0.064
iring+0.064
ruce+0.057
Neg logit contributions
joy-0.079
ez-0.075
hered-0.069
 nightmares-0.064
 moment-0.063
Token very
Token ID845
Feature activation-2.73e-02

Pos logit contributions
ires+0.022
ate+0.022
iring+0.021
um+0.021
ruce+0.018
Neg logit contributions
joy-0.036
ez-0.036
hered-0.033
 nightmares-0.031
 moment-0.030
Token proud
Token ID6613
Feature activation+2.08e-02

Pos logit contributions
joy+0.044
ez+0.038
 knowing+0.034
 moment+0.034
hered+0.033
Neg logit contributions
ires-0.056
ate-0.053
um-0.053
iring-0.052
ruce-0.050
Token of
Token ID286
Feature activation+9.56e-02

Pos logit contributions
ires+0.025
iring+0.024
um+0.023
ate+0.023
ruce+0.019
Neg logit contributions
joy-0.050
ez-0.050
hered-0.046
 nightmares-0.043
 moment-0.043
Token herself
Token ID5223
Feature activation+5.23e-02

Pos logit contributions
ires+0.130
iring+0.118
ate+0.118
um+0.106
ered+0.090
Neg logit contributions
ez-0.228
joy-0.225
hered-0.220
oing-0.198
tern-0.191
Token.
Token ID13
Feature activation-3.12e-02

Pos logit contributions
um+0.046
iring+0.041
ires+0.039
 all+0.034
ate+0.033
Neg logit contributions
ez-0.146
joy-0.140
hered-0.128
Bad-0.125
 nightmares-0.124
Token,
Token ID11
Feature activation+3.18e-02

Pos logit contributions
ez+0.148
joy+0.147
hered+0.128
 nightmares+0.127
 breathing+0.124
Neg logit contributions
um-0.076
ires-0.071
ate-0.070
iring-0.068
 Inside-0.065
Token Jack
Token ID3619
Feature activation+3.70e-02

Pos logit contributions
ires+0.045
iring+0.044
um+0.043
ate+0.043
 Inside+0.038
Neg logit contributions
ez-0.069
joy-0.067
hered-0.061
 nightmares-0.057
 breathing-0.055
Token and
Token ID290
Feature activation-4.21e-02

Pos logit contributions
ires+0.057
ate+0.054
um+0.054
iring+0.053
ruce+0.047
Neg logit contributions
joy-0.077
ez-0.074
hered-0.068
 nightmares-0.064
 moment-0.063
Token Jane
Token ID12091
Feature activation+7.70e-02

Pos logit contributions
joy+0.089
ez+0.088
hered+0.082
 nightmares+0.074
oing+0.073
Neg logit contributions
ate-0.058
ires-0.058
um-0.057
iring-0.054
 Inside-0.049
Token decided
Token ID3066
Feature activation+9.98e-02

Pos logit contributions
ires+0.130
iring+0.122
ate+0.120
um+0.117
ruce+0.106
Neg logit contributions
joy-0.153
ez-0.150
hered-0.137
 nightmares-0.126
 moment-0.125
Token to
Token ID284
Feature activation-1.53e-02

Pos logit contributions
ires+0.140
ate+0.135
iring+0.133
um+0.133
ruce+0.117
Neg logit contributions
ez-0.221
joy-0.215
hered-0.195
 nightmares-0.183
 heaven-0.178
Token play
Token ID711
Feature activation+7.39e-02

Pos logit contributions
ez+0.029
joy+0.028
hered+0.027
 nightmares+0.025
 heaven+0.025
Neg logit contributions
ires-0.026
iring-0.025
um-0.022
outed-0.022
ate-0.022
Token a
Token ID257
Feature activation-1.31e-02

Pos logit contributions
ires+0.104
ate+0.102
iring+0.096
um+0.095
ruce+0.087
Neg logit contributions
joy-0.164
ez-0.158
hered-0.145
 nightmares-0.136
 moment-0.134
Token game
Token ID983
Feature activation-1.03e-02

Pos logit contributions
joy+0.026
ez+0.025
hered+0.023
 nightmares+0.022
 moment+0.021
Neg logit contributions
ires-0.021
ate-0.020
iring-0.020
um-0.020
ruce-0.018
Token.
Token ID13
Feature activation-1.96e-02

Pos logit contributions
joy+0.021
ez+0.020
hered+0.019
 nightmares+0.018
 moment+0.017
Neg logit contributions
ires-0.016
iring-0.015
ate-0.015
um-0.015
ruce-0.013
Token Jane
Token ID12091
Feature activation+7.15e-02

Pos logit contributions
joy+0.040
ez+0.038
hered+0.035
 nightmares+0.033
 moment+0.033
Neg logit contributions
ires-0.031
iring-0.030
ate-0.030
um-0.029
ruce-0.026
Token Lily
Token ID20037
Feature activation+1.65e-02

Pos logit contributions
joy+0.029
 moment+0.023
hered+0.022
ez+0.022
 heaven+0.020
Neg logit contributions
ires-0.044
iring-0.043
ate-0.042
um-0.040
ered-0.038
Token asked
Token ID1965
Feature activation+2.26e-01

Pos logit contributions
ires+0.035
iring+0.033
ate+0.031
um+0.031
ruce+0.028
Neg logit contributions
joy-0.026
ez-0.026
hered-0.022
 moment-0.021
 knowing-0.021
Token her
Token ID607
Feature activation-3.90e-02

Pos logit contributions
ires+0.321
um+0.317
ate+0.313
iring+0.295
ruce+0.264
Neg logit contributions
joy-0.497
ez-0.489
hered-0.437
 nightmares-0.419
 tale-0.401
Token mom
Token ID1995
Feature activation+1.37e-01

Pos logit contributions
joy+0.085
ez+0.076
hered+0.072
 moment+0.071
 nightmares+0.071
Neg logit contributions
ires-0.060
ate-0.055
iring-0.055
um-0.052
ruce-0.048
Token what
Token ID644
Feature activation+5.88e-03

Pos logit contributions
ires+0.255
ate+0.243
iring+0.241
um+0.233
ruce+0.220
Neg logit contributions
joy-0.245
ez-0.220
hered-0.202
 moment-0.200
 knowing-0.192
Token it
Token ID340
Feature activation-1.94e-02

Pos logit contributions
ate+0.008
ires+0.007
um+0.007
iring+0.007
lly+0.007
Neg logit contributions
joy-0.014
ez-0.013
hered-0.013
 nightmares-0.011
 worrying-0.011
Token was
Token ID373
Feature activation+2.25e-02

Pos logit contributions
ez+0.029
joy+0.029
 moment+0.027
hered+0.026
 nightmares+0.025
Neg logit contributions
ires-0.040
um-0.038
iring-0.037
ate-0.036
ruce-0.032
Token for
Token ID329
Feature activation+2.61e-02

Pos logit contributions
ires+0.046
um+0.044
ate+0.043
iring+0.042
ruce+0.040
Neg logit contributions
joy-0.033
ez-0.030
 knowing-0.030
 breathing-0.029
 moment-0.029
Token.
Token ID13
Feature activation-2.03e-02

Pos logit contributions
ires+0.042
ate+0.039
um+0.039
iring+0.039
ruce+0.034
Neg logit contributions
joy-0.054
ez-0.051
hered-0.047
 nightmares-0.044
 moment-0.044
Token "
Token ID366
Feature activation-6.68e-02

Pos logit contributions
joy+0.032
ez+0.027
hered+0.026
 moment+0.026
 heaven+0.023
Neg logit contributions
ires-0.042
iring-0.041
ate-0.039
um-0.037
ruce-0.036
TokenIt
Token ID1026
Feature activation-4.96e-03

Pos logit contributions
joy+0.127
ez+0.124
hered+0.112
 moment+0.107
Charl+0.103
Neg logit contributions
ires-0.115
iring-0.108
ate-0.105
um-0.103
ruce-0.095
Token your
Token ID534
Feature activation+9.75e-03

Pos logit contributions
joy+0.285
ez+0.274
hered+0.253
 moment+0.234
 nightmares+0.232
Neg logit contributions
ires-0.206
ate-0.197
um-0.191
iring-0.190
ruce-0.170
Token doll
Token ID3654
Feature activation-1.11e-01

Pos logit contributions
ires+0.015
iring+0.015
um+0.015
ate+0.015
ruce+0.013
Neg logit contributions
joy-0.020
ez-0.019
hered-0.017
 nightmares-0.017
 moment-0.017
Token.
Token ID13
Feature activation-2.32e-02

Pos logit contributions
joy+0.217
ez+0.213
hered+0.194
 nightmares+0.184
 moment+0.180
Neg logit contributions
ires-0.184
iring-0.172
ate-0.171
um-0.170
ruce-0.154
Token Go
Token ID1514
Feature activation-6.30e-02

Pos logit contributions
ez+0.035
joy+0.035
hered+0.030
 heaven+0.029
 nightmares+0.028
Neg logit contributions
ires-0.047
iring-0.046
ate-0.045
um-0.045
ruce-0.043
Token away
Token ID1497
Feature activation-8.04e-02

Pos logit contributions
joy+0.101
ez+0.098
hered+0.093
 moment+0.083
 heaven+0.080
Neg logit contributions
ires-0.134
iring-0.129
um-0.119
ate-0.117
ruce-0.111
Token!"
Token ID2474
Feature activation+7.51e-02

Pos logit contributions
joy+0.168
ez+0.158
hered+0.147
 moment+0.142
 nightmares+0.141
Neg logit contributions
ires-0.125
iring-0.115
um-0.115
ate-0.114
ruce-0.106
Token Ben
Token ID3932
Feature activation-3.48e-02

Pos logit contributions
ires+0.145
iring+0.140
ate+0.138
um+0.133
ruce+0.125
Neg logit contributions
joy-0.130
ez-0.125
hered-0.112
 nightmares-0.103
 heaven-0.103
Token said
Token ID531
Feature activation+1.84e-01

Pos logit contributions
joy+0.085
ez+0.083
hered+0.077
 nightmares+0.073
 moment+0.072
Neg logit contributions
ires-0.043
iring-0.039
ate-0.039
um-0.038
ruce-0.033
Token.
Token ID13
Feature activation-2.35e-02

Pos logit contributions
um+0.192
ires+0.173
iring+0.167
ate+0.157
ered+0.146
Neg logit contributions
ez-0.453
joy-0.453
Charl-0.406
 nightmares-0.403
 tale-0.400
Token He
Token ID679
Feature activation+5.99e-02

Pos logit contributions
joy+0.045
ez+0.043
hered+0.039
 nightmares+0.036
 moment+0.036
Neg logit contributions
ires-0.041
ate-0.038
iring-0.038
um-0.038
ruce-0.035
Token was
Token ID373
Feature activation+1.53e-02

Pos logit contributions
ires+0.105
iring+0.098
ate+0.096
um+0.096
ruce+0.087
Neg logit contributions
joy-0.116
ez-0.113
hered-0.103
 nightmares-0.094
 moment-0.093
Token of
Token ID286
Feature activation+9.84e-02

Pos logit contributions
joy+0.602
ez+0.590
hered+0.545
 nightmares+0.509
 moment+0.505
Neg logit contributions
ires-0.274
iring-0.255
um-0.252
ate-0.242
ruce-0.209
Token singing
Token ID13777
Feature activation-2.46e-01

Pos logit contributions
ires+0.150
ate+0.142
iring+0.136
um+0.122
ruce+0.121
Neg logit contributions
ez-0.208
hered-0.196
joy-0.191
oing-0.172
ching-0.167
Token and
Token ID290
Feature activation-5.88e-02

Pos logit contributions
joy+0.578
ez+0.575
hered+0.520
 liar+0.475
Charl+0.469
Neg logit contributions
ires-0.303
ate-0.301
um-0.289
iring-0.285
ruce-0.240
Token dancing
Token ID15360
Feature activation-2.07e-01

Pos logit contributions
joy+0.096
ez+0.095
hered+0.089
 liar+0.074
Charl+0.072
Neg logit contributions
ires-0.112
ate-0.110
iring-0.107
um-0.099
ruce-0.096
Token on
Token ID319
Feature activation-1.01e-01

Pos logit contributions
ez+0.488
joy+0.488
hered+0.439
 nightmares+0.409
 heaven+0.402
Neg logit contributions
ires-0.256
ate-0.253
iring-0.239
um-0.234
ruce-0.202
Token the
Token ID262
Feature activation-3.64e-02

Pos logit contributions
ez+0.225
joy+0.225
hered+0.217
 liar+0.190
oing+0.187
Neg logit contributions
ires-0.136
ate-0.131
iring-0.121
um-0.119
ruce-0.108
Token stage
Token ID3800
Feature activation-5.23e-02

Pos logit contributions
joy+0.079
ez+0.077
hered+0.071
 nightmares+0.065
smart+0.063
Neg logit contributions
ires-0.054
ate-0.051
iring-0.050
um-0.049
ruce-0.045
Token.
Token ID13
Feature activation-3.13e-02

Pos logit contributions
joy+0.116
ez+0.114
hered+0.104
 nightmares+0.094
Charl+0.094
Neg logit contributions
ires-0.074
ate-0.071
iring-0.068
um-0.068
ruce-0.059
Token The
Token ID383
Feature activation-3.05e-02

Pos logit contributions
joy+0.069
ez+0.067
hered+0.063
 nightmares+0.057
 moment+0.056
Neg logit contributions
ires-0.046
um-0.043
ate-0.042
iring-0.042
 Inside-0.037
Token theater
Token ID13766
Feature activation+3.64e-02

Pos logit contributions
joy+0.065
ez+0.064
hered+0.058
 nightmares+0.053
 heaven+0.052
Neg logit contributions
ires-0.047
ate-0.044
um-0.043
iring-0.043
ruce-0.039
Token was
Token ID373
Feature activation+1.53e-02

Pos logit contributions
ires+0.051
ate+0.049
um+0.049
iring+0.048
ruce+0.042
Neg logit contributions
joy-0.082
ez-0.079
hered-0.072
 nightmares-0.067
 heaven-0.066
Token milk
Token ID7545
Feature activation-6.25e-02

Pos logit contributions
ires+0.023
ate+0.022
iring+0.022
um+0.021
ruce+0.019
Neg logit contributions
joy-0.025
ez-0.024
hered-0.022
 nightmares-0.021
 moment-0.021
Token and
Token ID290
Feature activation-5.44e-02

Pos logit contributions
joy+0.125
ez+0.120
hered+0.109
 nightmares+0.103
 moment+0.101
Neg logit contributions
ires-0.103
ate-0.097
iring-0.097
um-0.096
ruce-0.086
Token poured
Token ID19036
Feature activation+1.32e-01

Pos logit contributions
joy+0.110
ez+0.107
hered+0.096
 nightmares+0.092
 moment+0.092
Neg logit contributions
ires-0.088
iring-0.083
ate-0.081
um-0.080
ruce-0.073
Token it
Token ID340
Feature activation-1.98e-02

Pos logit contributions
ires+0.211
ate+0.199
um+0.199
iring+0.198
ruce+0.176
Neg logit contributions
joy-0.272
ez-0.261
hered-0.237
 nightmares-0.225
 moment-0.218
Token over
Token ID625
Feature activation+7.82e-02

Pos logit contributions
ez+0.037
joy+0.037
hered+0.035
 moment+0.033
 nightmares+0.031
Neg logit contributions
ires-0.034
iring-0.032
ate-0.031
um-0.030
ruce-0.027
Token the
Token ID262
Feature activation-3.56e-02

Pos logit contributions
ires+0.114
ate+0.110
um+0.109
iring+0.106
ruce+0.093
Neg logit contributions
ez-0.167
joy-0.166
hered-0.153
 nightmares-0.145
Charl-0.138
Token cereal
Token ID33158
Feature activation+6.88e-03

Pos logit contributions
joy+0.080
ez+0.077
hered+0.071
 nightmares+0.068
 moment+0.067
Neg logit contributions
ires-0.050
ate-0.046
iring-0.046
um-0.045
ruce-0.040
Token.
Token ID13
Feature activation-2.54e-02

Pos logit contributions
ires+0.012
iring+0.011
ate+0.011
um+0.011
ruce+0.010
Neg logit contributions
joy-0.013
ez-0.012
hered-0.011
 moment-0.011
 nightmares-0.011
Token
Token ID198
Feature activation-5.04e-03

Pos logit contributions
joy+0.043
ez+0.040
hered+0.036
 moment+0.034
 nightmares+0.031
Neg logit contributions
ires-0.049
iring-0.048
ate-0.046
um-0.046
ruce-0.043
Token
Token ID198
Feature activation-5.43e-03

Pos logit contributions
joy+0.007
ez+0.007
hered+0.006
 moment+0.006
Charl+0.005
Neg logit contributions
ires-0.011
iring-0.010
ate-0.010
um-0.010
ruce-0.009
TokenThey
Token ID2990
Feature activation+5.38e-02

Pos logit contributions
joy+0.011
ez+0.010
hered+0.010
 moment+0.009
Charl+0.009
Neg logit contributions
ires-0.009
iring-0.008
ate-0.008
um-0.008
ruce-0.007
Token.
Token ID13
Feature activation-2.22e-02

Pos logit contributions
joy+0.018
ez+0.017
hered+0.016
Charl+0.016
Sleep+0.015
Neg logit contributions
ires-0.011
ate-0.011
um-0.010
iring-0.010
ered-0.009
Token They
Token ID1119
Feature activation-6.27e-03

Pos logit contributions
joy+0.036
ez+0.032
 moment+0.029
 nightmares+0.028
hered+0.028
Neg logit contributions
ires-0.042
ate-0.042
iring-0.042
um-0.040
ruce-0.038
Token had
Token ID550
Feature activation-1.44e-01

Pos logit contributions
joy+0.011
ez+0.011
hered+0.010
 nightmares+0.009
 moment+0.009
Neg logit contributions
ires-0.012
iring-0.011
um-0.011
ate-0.011
ruce-0.010
Token a
Token ID257
Feature activation-1.98e-02

Pos logit contributions
joy+0.358
ez+0.355
hered+0.332
 nightmares+0.302
 moment+0.301
Neg logit contributions
ate-0.153
ires-0.151
iring-0.138
um-0.138
ruce-0.129
Token fun
Token ID1257
Feature activation+7.69e-02

Pos logit contributions
ez+0.053
joy+0.047
hered+0.045
smart+0.045
keeping+0.043
Neg logit contributions
um-0.018
 cool-0.017
lly-0.017
ate-0.017
ires-0.016
Token day
Token ID1110
Feature activation-7.81e-02

Pos logit contributions
ires+0.124
ate+0.121
um+0.120
iring+0.113
ruce+0.108
Neg logit contributions
joy-0.154
ez-0.147
hered-0.132
 nightmares-0.126
 heaven-0.123
Token at
Token ID379
Feature activation+1.80e-01

Pos logit contributions
joy+0.184
ez+0.177
hered+0.161
 moment+0.158
 nightmares+0.157
Neg logit contributions
ires-0.097
um-0.088
iring-0.088
ate-0.088
ruce-0.075
Token the
Token ID262
Feature activation-3.84e-02

Pos logit contributions
ires+0.274
ate+0.270
um+0.253
iring+0.253
ruce+0.230
Neg logit contributions
joy-0.377
ez-0.367
hered-0.331
 nightmares-0.315
 heaven-0.300
Token park
Token ID3952
Feature activation+1.13e-01

Pos logit contributions
joy+0.090
ez+0.085
hered+0.080
 moment+0.076
 nightmares+0.076
Neg logit contributions
ires-0.051
iring-0.048
ate-0.046
um-0.046
ruce-0.040
Token with
Token ID351
Feature activation+8.00e-02

Pos logit contributions
ires+0.127
ate+0.125
um+0.119
iring+0.118
her+0.100
Neg logit contributions
ez-0.277
joy-0.263
Charl-0.240
hered-0.239
 nightmares-0.233
Token the
Token ID262
Feature activation-3.75e-02

Pos logit contributions
ires+0.126
ate+0.119
iring+0.119
um+0.118
ruce+0.105
Neg logit contributions
joy-0.167
ez-0.161
hered-0.147
 nightmares-0.138
 moment-0.136
Token They
Token ID1119
Feature activation-1.83e-03

Pos logit contributions
um+0.099
ires+0.091
iring+0.088
 Inside+0.085
ate+0.085
Neg logit contributions
joy-0.196
ez-0.187
 nightmares-0.171
 worrying-0.167
hered-0.166
Token both
Token ID1111
Feature activation+1.90e-01

Pos logit contributions
joy+0.004
ez+0.004
hered+0.003
 moment+0.003
 nightmares+0.003
Neg logit contributions
ires-0.003
iring-0.003
ate-0.003
um-0.003
ruce-0.003
Token went
Token ID1816
Feature activation+7.45e-02

Pos logit contributions
ires+0.281
ate+0.270
um+0.269
iring+0.263
ruce+0.236
Neg logit contributions
joy-0.402
ez-0.380
hered-0.349
 nightmares-0.335
 moment-0.325
Token back
Token ID736
Feature activation-9.67e-02

Pos logit contributions
ires+0.136
ate+0.127
iring+0.127
um+0.127
ruce+0.115
Neg logit contributions
joy-0.139
ez-0.125
hered-0.118
 moment-0.110
 nightmares-0.108
Token down
Token ID866
Feature activation+3.75e-02

Pos logit contributions
joy+0.191
ez+0.177
hered+0.164
 moment+0.154
 nightmares+0.153
Neg logit contributions
ires-0.166
um-0.154
iring-0.154
ate-0.154
ruce-0.139
Token the
Token ID262
Feature activation-3.74e-02

Pos logit contributions
ires+0.051
ate+0.050
iring+0.049
um+0.048
 Inside+0.042
Neg logit contributions
ez-0.086
joy-0.080
 nightmares-0.074
hered-0.074
ñ-0.071
Token hill
Token ID12788
Feature activation+2.79e-02

Pos logit contributions
joy+0.070
ez+0.063
 moment+0.062
hered+0.060
 nightmares+0.056
Neg logit contributions
ires-0.067
ate-0.062
iring-0.062
um-0.061
outed-0.056
Token,
Token ID11
Feature activation+1.79e-02

Pos logit contributions
ires+0.038
um+0.038
ate+0.038
iring+0.037
her+0.031
Neg logit contributions
ez-0.062
joy-0.059
 nightmares-0.054
hered-0.053
Charl-0.051
Token happy
Token ID3772
Feature activation-1.20e-01

Pos logit contributions
ires+0.027
iring+0.026
ate+0.026
um+0.024
 Inside+0.023
Neg logit contributions
ez-0.037
joy-0.033
 nightmares-0.032
hered-0.032
ñ-0.031
Token with
Token ID351
Feature activation+8.30e-02

Pos logit contributions
ez+0.316
joy+0.300
hered+0.284
Charl+0.281
 liar+0.266
Neg logit contributions
iring-0.135
ires-0.134
ate-0.119
um-0.115
 Inside-0.091
Token their
Token ID511
Feature activation-1.01e-01

Pos logit contributions
ires+0.145
iring+0.136
ate+0.135
um+0.132
ruce+0.119
Neg logit contributions
joy-0.162
ez-0.156
hered-0.143
 moment-0.132
 nightmares-0.129
Token friends
Token ID2460
Feature activation+3.98e-02

Pos logit contributions
ires+0.162
ate+0.158
iring+0.150
um+0.146
ruce+0.144
Neg logit contributions
joy-0.184
ez-0.172
hered-0.164
 moment-0.143
oing-0.142
Token.
Token ID13
Feature activation-2.51e-02

Pos logit contributions
ires+0.051
um+0.048
iring+0.048
ate+0.048
ruce+0.041
Neg logit contributions
joy-0.092
ez-0.089
hered-0.081
 nightmares-0.078
 moment-0.076
Token They
Token ID1119
Feature activation-6.66e-03

Pos logit contributions
joy+0.052
ez+0.046
hered+0.043
 moment+0.042
 nightmares+0.040
Neg logit contributions
ires-0.041
iring-0.040
ate-0.038
um-0.037
ruce-0.035
Token had
Token ID550
Feature activation-1.43e-01

Pos logit contributions
joy+0.013
ez+0.013
hered+0.011
 nightmares+0.011
 moment+0.010
Neg logit contributions
ires-0.011
iring-0.011
ate-0.011
um-0.011
ruce-0.009
Token been
Token ID587
Feature activation-1.85e-01

Pos logit contributions
joy+0.334
ez+0.332
hered+0.309
 moment+0.282
 nightmares+0.281
Neg logit contributions
ate-0.164
ires-0.159
um-0.154
iring-0.153
her-0.139
Token having
Token ID1719
Feature activation-1.89e-01

Pos logit contributions
joy+0.351
ez+0.350
hered+0.312
 moment+0.295
 nightmares+0.291
Neg logit contributions
ate-0.297
ires-0.295
iring-0.291
um-0.281
her-0.257
Token so
Token ID523
Feature activation+6.10e-02

Pos logit contributions
ez+0.478
joy+0.466
hered+0.446
oing+0.419
 moment+0.406
Neg logit contributions
ate-0.175
ires-0.173
um-0.169
iring-0.161
ruce-0.152
Token much
Token ID881
Feature activation-1.20e-01

Pos logit contributions
ires+0.118
iring+0.112
um+0.112
ate+0.112
ruce+0.102
Neg logit contributions
joy-0.105
ez-0.100
hered-0.090
 nightmares-0.082
 moment-0.082
Token fun
Token ID1257
Feature activation+7.77e-02

Pos logit contributions
joy+0.300
ez+0.293
hered+0.270
 nightmares+0.253
 moment+0.249
Neg logit contributions
ires-0.137
ate-0.126
um-0.125
iring-0.123
ruce-0.108
Token.
Token ID13
Feature activation-2.51e-02

Pos logit contributions
ires+0.096
iring+0.088
ate+0.085
um+0.079
ruce+0.071
Neg logit contributions
joy-0.183
ez-0.180
hered-0.170
 severe-0.159
Charl-0.158
Token
Token ID198
Feature activation-2.90e-03

Pos logit contributions
joy+0.049
ez+0.043
hered+0.040
 moment+0.039
 nightmares+0.037
Neg logit contributions
ires-0.043
iring-0.042
ate-0.041
um-0.039
ruce-0.038
Token realized
Token ID6939
Feature activation-4.69e-02

Pos logit contributions
ires+0.083
iring+0.079
ate+0.077
um+0.077
ruce+0.071
Neg logit contributions
joy-0.074
ez-0.073
hered-0.064
 nightmares-0.060
 moment-0.058
Token that
Token ID326
Feature activation+1.46e-01

Pos logit contributions
joy+0.116
ez+0.112
hered+0.104
 nightmares+0.099
 moment+0.098
Neg logit contributions
ires-0.055
ate-0.051
iring-0.050
um-0.050
ruce-0.042
Token being
Token ID852
Feature activation-3.02e-01

Pos logit contributions
ires+0.191
ate+0.182
iring+0.182
um+0.159
ruce+0.151
Neg logit contributions
joy-0.325
ez-0.324
hered-0.322
Charl-0.286
oing-0.277
Token fair
Token ID3148
Feature activation+1.11e-01

Pos logit contributions
joy+0.623
ez+0.594
hered+0.550
 moment+0.513
 nightmares+0.504
Neg logit contributions
ires-0.480
ate-0.456
iring-0.455
um-0.438
ruce-0.391
Token meant
Token ID4001
Feature activation-2.54e-02

Pos logit contributions
ires+0.181
iring+0.173
ate+0.172
um+0.166
ruce+0.143
Neg logit contributions
joy-0.231
ez-0.227
hered-0.201
 nightmares-0.189
 heaven-0.188
Token being
Token ID852
Feature activation-3.02e-01

Pos logit contributions
ez+0.056
joy+0.056
hered+0.051
Charl+0.047
oing+0.047
Neg logit contributions
ires-0.036
iring-0.034
ate-0.033
um-0.032
 Inside-0.028
Token balanced
Token ID12974
Feature activation+5.26e-03

Pos logit contributions
joy+0.662
ez+0.637
hered+0.588
 moment+0.550
 nightmares+0.545
Neg logit contributions
ires-0.443
ate-0.428
iring-0.419
um-0.394
ruce-0.346
Token and
Token ID290
Feature activation-6.26e-02

Pos logit contributions
ires+0.008
ate+0.007
iring+0.007
um+0.007
ruce+0.006
Neg logit contributions
joy-0.012
ez-0.011
hered-0.010
 nightmares-0.010
 heaven-0.009
Token that
Token ID326
Feature activation+1.46e-01

Pos logit contributions
joy+0.115
ez+0.111
hered+0.100
 nightmares+0.092
 moment+0.089
Neg logit contributions
ires-0.114
ate-0.109
iring-0.107
um-0.103
ruce-0.095
Token it
Token ID340
Feature activation-2.84e-02

Pos logit contributions
ires+0.215
ate+0.211
iring+0.202
um+0.187
ruce+0.177
Neg logit contributions
joy-0.314
ez-0.306
hered-0.289
Charl-0.262
oing-0.252
Token was
Token ID373
Feature activation+5.37e-03

Pos logit contributions
joy+0.057
ez+0.053
hered+0.048
 nightmares+0.044
 moment+0.044
Neg logit contributions
ires-0.048
ate-0.046
iring-0.045
um-0.044
ruce-0.041
Token distance
Token ID5253
Feature activation-2.22e-01

Pos logit contributions
ires+0.078
um+0.075
ate+0.073
iring+0.073
ruce+0.062
Neg logit contributions
joy-0.110
ez-0.109
hered-0.099
 nightmares-0.091
 heaven-0.087
Token.
Token ID13
Feature activation+3.61e-03

Pos logit contributions
joy+0.464
ez+0.455
hered+0.410
 nightmares+0.386
Charl+0.375
Neg logit contributions
ires-0.339
iring-0.322
um-0.321
ate-0.317
ruce-0.278
Token Everyone
Token ID11075
Feature activation+1.68e-01

Pos logit contributions
ires+0.006
ate+0.005
um+0.005
iring+0.005
ruce+0.005
Neg logit contributions
joy-0.008
ez-0.007
hered-0.007
 nightmares-0.006
 moment-0.006
Token was
Token ID373
Feature activation+5.15e-02

Pos logit contributions
ires+0.248
ate+0.235
iring+0.233
um+0.229
ruce+0.204
Neg logit contributions
joy-0.363
ez-0.343
hered-0.317
 nightmares-0.301
 heaven-0.291
Token over
Token ID625
Feature activation+1.02e-01

Pos logit contributions
ires+0.081
iring+0.079
ate+0.078
um+0.077
ruce+0.068
Neg logit contributions
joy-0.104
ez-0.101
hered-0.091
 nightmares-0.087
 moment-0.084
Tokenjoy
Token ID2633
Feature activation-5.39e-01

Pos logit contributions
ires+0.164
iring+0.159
um+0.158
ate+0.151
ised+0.132
Neg logit contributions
ez-0.211
hered-0.178
ñ-0.174
Charl-0.169
 nightmares-0.168
Tokened
Token ID276
Feature activation-6.54e-02

Pos logit contributions
joy+1.096
ez+1.056
 nightmares+1.017
 heaven+1.003
Charl+0.975
Neg logit contributions
um-0.815
ires-0.799
iring-0.777
ate-0.753
outed-0.656
Token that
Token ID326
Feature activation+1.66e-01

Pos logit contributions
ez+0.151
joy+0.142
hered+0.131
 nightmares+0.129
Charl+0.124
Neg logit contributions
ires-0.087
iring-0.086
um-0.085
ate-0.080
ruce-0.065
Token the
Token ID262
Feature activation-1.87e-02

Pos logit contributions
ires+0.205
um+0.196
iring+0.192
ate+0.189
ered+0.168
Neg logit contributions
ez-0.383
joy-0.367
hered-0.339
Charl-0.324
oing-0.315
Token cow
Token ID9875
Feature activation-1.40e-01

Pos logit contributions
ez+0.039
joy+0.038
hered+0.035
 nightmares+0.031
 heaven+0.031
Neg logit contributions
ires-0.028
um-0.027
iring-0.027
ate-0.027
ruce-0.023
Token had
Token ID550
Feature activation-1.38e-01

Pos logit contributions
joy+0.317
ez+0.298
hered+0.270
 nightmares+0.264
Charl+0.260
Neg logit contributions
ires-0.178
um-0.176
iring-0.175
ate-0.174
lly-0.157
Token wind
Token ID2344
Feature activation+3.64e-02

Pos logit contributions
joy+0.055
ez+0.053
hered+0.048
 nightmares+0.046
 moment+0.045
Neg logit contributions
ires-0.044
ate-0.042
iring-0.041
um-0.041
ruce-0.037
Token is
Token ID318
Feature activation-2.15e-02

Pos logit contributions
ires+0.053
ate+0.052
iring+0.050
um+0.048
ruce+0.043
Neg logit contributions
joy-0.084
ez-0.074
hered-0.067
 nightmares-0.066
Charl-0.065
Token just
Token ID655
Feature activation+1.00e-01

Pos logit contributions
joy+0.045
ez+0.042
hered+0.038
 nightmares+0.035
 moment+0.034
Neg logit contributions
ires-0.034
iring-0.033
ate-0.032
um-0.032
ruce-0.029
Token singing
Token ID13777
Feature activation-2.49e-01

Pos logit contributions
ires+0.148
iring+0.142
ate+0.138
um+0.130
ruce+0.117
Neg logit contributions
joy-0.223
ez-0.206
hered-0.193
Charl-0.176
ñ-0.175
Token a
Token ID257
Feature activation-2.27e-02

Pos logit contributions
joy+0.623
ez+0.552
hered+0.521
 forgetting+0.478
Charl+0.475
Neg logit contributions
ires-0.313
ate-0.300
iring-0.296
um-0.295
her-0.250
Token lull
Token ID42858
Feature activation-4.00e-01

Pos logit contributions
joy+0.054
ez+0.052
hered+0.046
 nightmares+0.042
smart+0.041
Neg logit contributions
um-0.028
iring-0.028
ires-0.027
ate-0.026
ruce-0.024
Tokenaby
Token ID3930
Feature activation-8.17e-02

Pos logit contributions
joy+0.683
ez+0.650
hered+0.580
 nightmares+0.540
 moment+0.530
Neg logit contributions
ires-0.776
ate-0.739
iring-0.736
um-0.731
ruce-0.670
Token to
Token ID284
Feature activation-2.77e-02

Pos logit contributions
joy+0.211
ez+0.185
hered+0.168
Charl+0.163
 nightmares+0.160
Neg logit contributions
ires-0.099
um-0.095
iring-0.095
ate-0.089
?"-0.076
Token help
Token ID1037
Feature activation-8.56e-02

Pos logit contributions
joy+0.061
ez+0.055
hered+0.052
 nightmares+0.047
 moment+0.047
Neg logit contributions
ires-0.042
ate-0.040
iring-0.039
um-0.038
ruce-0.035
Token you
Token ID345
Feature activation+1.20e-02

Pos logit contributions
joy+0.206
ez+0.197
hered+0.182
 nightmares+0.173
 moment+0.171
Neg logit contributions
ires-0.109
ate-0.102
iring-0.101
um-0.100
ruce-0.086
Token sleep
Token ID3993
Feature activation-9.52e-02

Pos logit contributions
ate+0.017
ires+0.017
iring+0.017
um+0.016
ruce+0.014
Neg logit contributions
joy-0.027
ez-0.025
hered-0.022
Charl-0.020
 nightmares-0.020
Token Mom
Token ID11254
Feature activation+2.24e-01

Pos logit contributions
joy+0.068
ez+0.064
hered+0.058
 nightmares+0.055
 moment+0.054
Neg logit contributions
ires-0.057
ate-0.054
iring-0.054
um-0.053
ruce-0.049
Token hugged
Token ID41130
Feature activation-8.96e-02

Pos logit contributions
ires+0.371
um+0.367
ate+0.366
iring+0.359
ruce+0.327
Neg logit contributions
joy-0.431
ez-0.404
hered-0.365
 nightmares-0.355
 heaven-0.340
Token her
Token ID607
Feature activation-5.04e-02

Pos logit contributions
joy+0.189
ez+0.182
hered+0.164
 nightmares+0.154
 moment+0.151
Neg logit contributions
ires-0.141
um-0.133
ate-0.131
iring-0.130
ruce-0.115
Token back
Token ID736
Feature activation-1.01e-01

Pos logit contributions
ez+0.123
joy+0.119
hered+0.109
Charl+0.107
 nightmares+0.105
Neg logit contributions
um-0.060
 up-0.055
ires-0.055
ate-0.053
iring-0.050
Token and
Token ID290
Feature activation-6.28e-02

Pos logit contributions
ez+0.241
joy+0.240
hered+0.228
Charl+0.209
 nightmares+0.205
Neg logit contributions
ires-0.132
um-0.125
iring-0.119
ate-0.117
outed-0.097
Token forg
Token ID5784
Feature activation-3.26e-01

Pos logit contributions
joy+0.149
ez+0.144
hered+0.132
 nightmares+0.126
 moment+0.124
Neg logit contributions
ires-0.080
ate-0.075
iring-0.075
um-0.074
ruce-0.064
Tokenave
Token ID1015
Feature activation-2.29e-02

Pos logit contributions
joy+0.720
ez+0.648
hered+0.604
 nightmares+0.596
 moment+0.591
Neg logit contributions
ires-0.469
ate-0.432
iring-0.431
um-0.429
outed-0.405
Token her
Token ID607
Feature activation-5.03e-02

Pos logit contributions
joy+0.044
ez+0.042
hered+0.038
 nightmares+0.036
 moment+0.035
Neg logit contributions
ires-0.040
ate-0.037
iring-0.037
um-0.037
ruce-0.033
Token.
Token ID13
Feature activation-3.32e-02

Pos logit contributions
ez+0.132
joy+0.129
Charl+0.124
hered+0.122
Patch+0.114
Neg logit contributions
ires-0.051
um-0.047
iring-0.045
ate-0.043
 up-0.040
Token
Token ID198
Feature activation-1.46e-02

Pos logit contributions
joy+0.066
ez+0.061
hered+0.055
 nightmares+0.053
 moment+0.052
Neg logit contributions
ires-0.056
ate-0.054
iring-0.054
um-0.053
ruce-0.049
Token
Token ID198
Feature activation-1.43e-02

Pos logit contributions
joy+0.022
ez+0.021
hered+0.018
 moment+0.018
 breathing+0.017
Neg logit contributions
ires-0.030
iring-0.029
ate-0.028
um-0.028
ruce-0.026
Token
Token ID198
Feature activation+5.99e-04

Pos logit contributions
ires+0.003
iring+0.002
um+0.002
outed+0.002
ate+0.002
Neg logit contributions
joy-0.002
ez-0.002
hered-0.001
 moment-0.001
smart-0.001
Token"
Token ID1
Feature activation+2.15e-02

Pos logit contributions
ires+0.001
iring+0.001
um+0.001
ate+0.001
outed+0.001
Neg logit contributions
joy-0.001
ez-0.001
hered-0.001
smart-0.001
 moment-0.001
TokenWhy
Token ID5195
Feature activation-7.34e-02

Pos logit contributions
ires+0.034
ate+0.034
iring+0.033
um+0.032
ruce+0.029
Neg logit contributions
joy-0.043
ez-0.042
 nightmares-0.036
hered-0.036
 knowing-0.035
Token are
Token ID389
Feature activation-8.97e-02

Pos logit contributions
joy+0.154
ez+0.147
hered+0.132
 nightmares+0.121
 heaven+0.121
Neg logit contributions
ires-0.117
ate-0.114
um-0.109
iring-0.108
ruce-0.097
Token you
Token ID345
Feature activation+1.82e-02

Pos logit contributions
joy+0.129
ez+0.112
 nightmares+0.110
hered+0.106
 forgetting+0.102
Neg logit contributions
ate-0.184
ires-0.178
um-0.177
iring-0.172
ruce-0.159
Token crying
Token ID13774
Feature activation-3.16e-01

Pos logit contributions
ires+0.041
ate+0.039
um+0.039
iring+0.038
ruce+0.036
Neg logit contributions
joy-0.026
ez-0.024
hered-0.021
 nightmares-0.019
 moment-0.019
Token?"
Token ID1701
Feature activation+3.25e-01

Pos logit contributions
joy+0.732
ez+0.698
hered+0.669
 moment+0.631
 nightmares+0.624
Neg logit contributions
ires-0.385
ate-0.343
iring-0.321
ruce-0.315
um-0.310
Token she
Token ID673
Feature activation-7.86e-02

Pos logit contributions
ires+0.679
ate+0.669
iring+0.661
um+0.654
ruce+0.614
Neg logit contributions
joy-0.500
ez-0.436
 nightmares-0.390
hered-0.389
 moment-0.381
Token asks
Token ID7893
Feature activation+1.91e-01

Pos logit contributions
joy+0.169
ez+0.166
hered+0.153
 nightmares+0.151
 moment+0.143
Neg logit contributions
ires-0.112
iring-0.106
um-0.106
ate-0.103
ruce-0.091
Token.
Token ID13
Feature activation-8.67e-03

Pos logit contributions
ires+0.249
um+0.231
iring+0.229
ate+0.218
outed+0.180
Neg logit contributions
ez-0.451
joy-0.438
hered-0.393
Charl-0.388
 nightmares-0.387
Token "
Token ID366
Feature activation-6.97e-02

Pos logit contributions
joy+0.020
ez+0.020
hered+0.018
 nightmares+0.018
ñ+0.017
Neg logit contributions
ires-0.011
ate-0.010
iring-0.010
um-0.010
 Inside-0.010