TOP ACTIVATIONS
MAX = 8.880

with glasses and a pony tail . She is reading a
, Emma decided a pony tail wasn 't so important after
her hair in a pony tail so she could look pretty
" You are a good seeker , Mia ! That was
seek . Ben was the seeker and Lily was the h
house . Lily was the seeker and Max was the h
seek . Tom was the seeker and Lily was the h
park . Lily was the seeker and Max was the h
park . Sara is the seeker and Ben is the h
. You are a fair seeker . You did not cheat
" You are a good seeker and a good sister .
park . Lily was the seeker and Tom was the h
seek . Tom is the seeker . He counts to ten
park . Anna was the seeker and Ben was the h
park . Lily is the seeker and Ben is the h
seek . Tom is the seeker and Mia is the h
park . Lily was the seeker and Tom was the h
the dog is the best seeker !" Ben smiled
garden . Ben was the seeker and Lily was the h
park . Lily is the seeker and Tom is the h

MIN ACTIVATIONS
MIN = -12.299

, but only with our supervision . And maybe you can
to use it with adult supervision ," Mr . Lee said
cried . " The ost ric hes are mean ! They
with a man on a stret cher . The man 's
They put Lily on a stret cher and carried her to
They lifted him onto a stret cher and put him in
When Daisy put the magn ifying glass down , the cater
the elderly man on a stret cher . She thanked Tim
flashlight , and a magn ifying glass . As
but be careful . Ost ric hes can be gr umpy
ie . Unlike other ost ric hes , his feathers gl
They all went to the living room , where the cake
Lily was painting in the living room . She had a
was a spoiled rabbit , living in a nice little home
Rose were playing in the living room when they heard a
ostr ich pen . Ost ric hes are big birds with
and zoom ed around the living room . It felt so
bear was running around the living room when suddenly it stepped
raise the curtains in the living room . Lily tried her
there was an intelligent fox living in a big green valley

INTERVAL 3.585 - 8.880
CONTAINS 2.141%

She kept asking the cloud questions , and the cloud kept
they hoped that they could do better next time . <|endoftext|>
." " Good idea !" Mia says . "
so happy . One day , the bells started
trip . They woke up early the next day and went

INTERVAL -1.710 - 3.585
CONTAINS 83.745%

worried . They cry for help . A man
dad . When they came home , Tim my revealed the
girl smiled and hopped around the room . Suddenly , the
who became very curious . She wanted to know what was
they looked at the race and saw that it was fair

INTERVAL -7.004 - -1.710
CONTAINS 13.941%

they are my shoes and I love them . They are
eddy bear that she loved very much . One day ,
to taste them . <|endoftext|> Once upon a time , there
kind to others . <|endoftext|> Once upon a time , there
keeps laughing and watching his car . He does not see

INTERVAL -12.299 - -7.004
CONTAINS 0.173%

was a boy named Max who loved to go on adventures
mom my coming from the living room . She quickly got
sp oons inside the dish washer . She was careful not
't worry , we can repair it !" Lily was happy
sat down and talked about who would be the leader of
Token with
Token ID351
Feature activation-5.73e-02

Pos logit contributions
 moments+0.167
 inspection+0.149
ment+0.147
ed+0.141
abouts+0.139
Neg logit contributions
 Claus-0.141
 daddy-0.137
ingu-0.132
ric-0.125
washer-0.125
Token glasses
Token ID15232
Feature activation+2.14e+00

Pos logit contributions
 Claus+0.003
 daddy+0.003
ingu+0.003
 boo+0.003
ric+0.003
Neg logit contributions
 moments-0.003
 inspection-0.002
ment-0.002
abouts-0.002
ed-0.002
Token and
Token ID290
Feature activation+4.91e-01

Pos logit contributions
 moments+0.076
ed+0.064
ment+0.061
 inspection+0.058
edly+0.058
Neg logit contributions
 Claus-0.137
ric-0.137
 daddy-0.135
ingu-0.135
oun-0.131
Token a
Token ID257
Feature activation+5.26e-02

Pos logit contributions
 moments+0.024
 inspection+0.022
ment+0.021
abouts+0.020
ed+0.020
Neg logit contributions
 Claus-0.025
 daddy-0.025
 boo-0.023
ingu-0.023
ric-0.022
Token pony
Token ID26902
Feature activation-9.20e-01

Pos logit contributions
 moments+0.003
 inspection+0.002
ment+0.002
 Alicia+0.002
ed+0.002
Neg logit contributions
ll-0.002
 Claus-0.002
ingu-0.002
ric-0.002
washer-0.002
Tokentail
Token ID13199
Feature activation+8.88e+00

Pos logit contributions
 daddy+0.051
 Claus+0.051
ingu+0.051
ric+0.048
washer+0.048
Neg logit contributions
 moments-0.040
ment-0.034
 inspection-0.034
ed-0.033
abouts-0.032
Token.
Token ID13
Feature activation-1.48e-01

Pos logit contributions
 moments+0.434
 inspection+0.386
ment+0.379
abouts+0.361
ed+0.355
Neg logit contributions
 Claus-0.463
 daddy-0.447
ingu-0.422
 boo-0.412
washer-0.410
Token She
Token ID1375
Feature activation+1.27e+00

Pos logit contributions
 daddy+0.008
 Claus+0.008
ingu+0.008
 boo+0.008
oun+0.007
Neg logit contributions
 moments-0.007
 inspection-0.006
ment-0.006
abouts-0.005
ed-0.005
Token is
Token ID318
Feature activation+4.48e-01

Pos logit contributions
 moments+0.058
 inspection+0.050
ment+0.048
ed+0.048
 Alicia+0.046
Neg logit contributions
 Claus-0.069
 daddy-0.067
ingu-0.066
washer-0.064
ric-0.063
Token reading
Token ID3555
Feature activation+1.66e+00

Pos logit contributions
 moments+0.020
 Alicia+0.020
 Meg+0.019
ed+0.018
 after+0.017
Neg logit contributions
oun-0.023
ingu-0.022
ll-0.022
washer-0.022
 Claus-0.022
Token a
Token ID257
Feature activation+6.46e-02

Pos logit contributions
 moments+0.081
 inspection+0.074
ment+0.072
abouts+0.067
ed+0.067
Neg logit contributions
 daddy-0.084
 Claus-0.084
ingu-0.077
 boo-0.074
washer-0.073
Token,
Token ID11
Feature activation-3.65e-03

Pos logit contributions
 Claus+0.245
 daddy+0.241
ingu+0.229
washer+0.222
 boo+0.222
Neg logit contributions
 moments-0.186
 inspection-0.163
ment-0.159
ed-0.150
abouts-0.150
Token Emma
Token ID18966
Feature activation-5.25e+00

Pos logit contributions
 Claus+0.000
 daddy+0.000
ingu+0.000
ric+0.000
ll+0.000
Neg logit contributions
 moments-0.000
 inspection-0.000
ment-0.000
ed-0.000
abouts-0.000
Token decided
Token ID3066
Feature activation+1.25e+00

Pos logit contributions
 Claus+0.292
 daddy+0.286
ingu+0.277
ric+0.272
washer+0.266
Neg logit contributions
 moments-0.234
 inspection-0.202
ment-0.198
ed-0.193
abouts-0.185
Token a
Token ID257
Feature activation-2.73e-01

Pos logit contributions
 moments+0.062
 inspection+0.055
ment+0.054
abouts+0.052
ed+0.051
Neg logit contributions
 Claus-0.064
 daddy-0.063
ingu-0.059
 boo-0.058
washer-0.057
Token pony
Token ID26902
Feature activation-1.15e+00

Pos logit contributions
ric+0.014
ingu+0.013
ll+0.013
 Claus+0.013
ppa+0.013
Neg logit contributions
 moments-0.014
 inspection-0.012
 Alicia-0.011
 Meg-0.011
Exc-0.011
Tokentail
Token ID13199
Feature activation+8.71e+00

Pos logit contributions
 Claus+0.062
 daddy+0.061
ingu+0.059
ric+0.057
 boo+0.056
Neg logit contributions
 moments-0.054
 inspection-0.047
ment-0.046
ed-0.045
abouts-0.043
Token wasn
Token ID2492
Feature activation-1.08e+00

Pos logit contributions
 moments+0.369
 inspection+0.321
ment+0.314
ed+0.294
abouts+0.294
Neg logit contributions
 Claus-0.506
 daddy-0.496
ingu-0.476
washer-0.461
 boo-0.460
Token't
Token ID470
Feature activation-3.38e+00

Pos logit contributions
 Claus+0.059
ingu+0.057
 daddy+0.057
ric+0.055
washer+0.053
Neg logit contributions
 Alicia-0.042
When-0.041
 after-0.041
Exc-0.041
 Meg-0.040
Token so
Token ID523
Feature activation-2.91e+00

Pos logit contributions
 Claus+0.173
ingu+0.172
ric+0.170
washer+0.163
oun+0.163
Neg logit contributions
 moments-0.158
 inspection-0.145
 after-0.139
ed-0.138
ment-0.137
Token important
Token ID1593
Feature activation-1.96e-01

Pos logit contributions
 Claus+0.132
ric+0.126
ingu+0.125
 daddy+0.122
ll+0.117
Neg logit contributions
 moments-0.166
 inspection-0.148
ment-0.148
ed-0.145
 Alicia-0.138
Token after
Token ID706
Feature activation+4.98e+00

Pos logit contributions
 daddy+0.009
 Claus+0.009
ll+0.008
washer+0.008
ingu+0.008
Neg logit contributions
 moments-0.010
 inspection-0.009
abouts-0.009
ment-0.009
ed-0.008
Token her
Token ID607
Feature activation+1.48e+00

Pos logit contributions
 Claus+0.110
ingu+0.103
ll+0.103
 daddy+0.103
ric+0.102
Neg logit contributions
 moments-0.063
ment-0.052
ed-0.050
 inspection-0.050
abouts-0.045
Token hair
Token ID4190
Feature activation-6.49e-01

Pos logit contributions
 moments+0.073
ed+0.062
ment+0.062
 inspection+0.058
edly+0.054
Neg logit contributions
 Claus-0.082
ingu-0.078
ll-0.076
ric-0.073
oun-0.073
Token in
Token ID287
Feature activation-2.18e+00

Pos logit contributions
 Claus+0.034
 daddy+0.033
ingu+0.032
ric+0.031
 boo+0.030
Neg logit contributions
 moments-0.031
 inspection-0.028
ment-0.027
ed-0.026
abouts-0.026
Token a
Token ID257
Feature activation-2.01e-01

Pos logit contributions
 Claus+0.142
 daddy+0.136
ingu+0.135
washer+0.131
ll+0.131
Neg logit contributions
 moments-0.080
 inspection-0.066
ment-0.065
abouts-0.059
ed-0.059
Token pony
Token ID26902
Feature activation-1.23e+00

Pos logit contributions
 Claus+0.011
ll+0.010
ric+0.010
ingu+0.010
oun+0.009
Neg logit contributions
 moments-0.011
 inspection-0.009
Exc-0.008
abouts-0.008
 after-0.008
Tokentail
Token ID13199
Feature activation+8.65e+00

Pos logit contributions
ingu+0.076
 Claus+0.075
oun+0.074
ric+0.073
 daddy+0.073
Neg logit contributions
 moments-0.045
ment-0.038
 after-0.037
ed-0.036
edly-0.035
Token so
Token ID523
Feature activation-2.84e+00

Pos logit contributions
 moments+0.330
 inspection+0.279
ment+0.271
ed+0.260
edly+0.250
Neg logit contributions
 Claus-0.540
 daddy-0.520
ingu-0.515
ric-0.507
oun-0.500
Token she
Token ID673
Feature activation+2.30e+00

Pos logit contributions
 Claus+0.214
ric+0.205
ingu+0.202
 daddy+0.195
 boo+0.195
Neg logit contributions
 moments-0.080
ment-0.065
 inspection-0.063
ed-0.058
edly-0.050
Token could
Token ID714
Feature activation-2.23e+00

Pos logit contributions
 moments+0.098
ed+0.091
ment+0.083
 inspection+0.081
edly+0.078
Neg logit contributions
ric-0.132
 Claus-0.125
ingu-0.119
 fault-0.119
oun-0.118
Token look
Token ID804
Feature activation+2.17e+00

Pos logit contributions
 Claus+0.121
ingu+0.116
washer+0.109
 daddy+0.108
ric+0.108
Neg logit contributions
 moments-0.096
 inspection-0.088
ment-0.086
 behold-0.082
 after-0.082
Token pretty
Token ID2495
Feature activation+2.04e+00

Pos logit contributions
 moments+0.087
 inspection+0.074
ment+0.073
ed+0.069
abouts+0.066
Neg logit contributions
 Claus-0.134
 daddy-0.128
ingu-0.125
ric-0.124
ll-0.122
Token "
Token ID366
Feature activation+2.78e-01

Pos logit contributions
 moments+0.010
 inspection+0.009
ment+0.009
ed+0.008
edly+0.008
Neg logit contributions
 Claus-0.016
 daddy-0.015
ingu-0.015
ric-0.015
washer-0.015
TokenYou
Token ID1639
Feature activation+4.98e-01

Pos logit contributions
 inspection+0.014
 moments+0.013
ment+0.013
 passages+0.013
oos+0.012
Neg logit contributions
 Claus-0.012
ll-0.012
 daddy-0.012
oun-0.012
 cube-0.011
Token are
Token ID389
Feature activation+6.15e-01

Pos logit contributions
 moments+0.023
ed+0.022
 inspection+0.020
 Alicia+0.020
 Meg+0.019
Neg logit contributions
 Claus-0.024
ric-0.024
oun-0.023
 daddy-0.023
ppa-0.023
Token a
Token ID257
Feature activation-1.25e-02

Pos logit contributions
 moments+0.026
 Alicia+0.024
 Meg+0.023
 after+0.021
 circles+0.020
Neg logit contributions
 Claus-0.036
oun-0.034
washer-0.034
ingu-0.034
ppa-0.033
Token good
Token ID922
Feature activation+1.15e+00

Pos logit contributions
 Claus+0.001
ric+0.001
ingu+0.001
ppa+0.001
 daddy+0.001
Neg logit contributions
 moments-0.001
 Alicia-0.001
 inspection-0.001
 after-0.001
abouts-0.000
Token seeker
Token ID45993
Feature activation+8.62e+00

Pos logit contributions
 moments+0.078
 inspection+0.072
ment+0.071
ed+0.068
abouts+0.068
Neg logit contributions
 Claus-0.038
 daddy-0.037
ingu-0.034
 boo-0.032
washer-0.032
Token,
Token ID11
Feature activation+3.10e-01

Pos logit contributions
 moments+0.350
 inspection+0.303
ment+0.296
ed+0.280
abouts+0.273
Neg logit contributions
 Claus-0.518
 daddy-0.506
ingu-0.490
ric-0.477
 boo-0.473
Token Mia
Token ID32189
Feature activation+3.73e+00

Pos logit contributions
 moments+0.011
 inspection+0.009
ment+0.009
ed+0.009
abouts+0.008
Neg logit contributions
 Claus-0.020
 daddy-0.020
ingu-0.019
 boo-0.019
washer-0.019
Token!
Token ID0
Feature activation+2.22e-01

Pos logit contributions
 moments+0.138
ment+0.113
 inspection+0.110
ed+0.105
 Alicia+0.098
Neg logit contributions
 Claus-0.241
 daddy-0.234
ingu-0.232
ric-0.230
 boo-0.224
Token That
Token ID1320
Feature activation-1.70e+00

Pos logit contributions
 moments+0.013
 inspection+0.012
ment+0.012
ed+0.012
abouts+0.011
Neg logit contributions
 Claus-0.009
 daddy-0.009
ingu-0.008
washer-0.008
ric-0.008
Token was
Token ID373
Feature activation+5.17e-01

Pos logit contributions
 Claus+0.086
 daddy+0.084
ingu+0.080
ric+0.077
washer+0.077
Neg logit contributions
 moments-0.086
 inspection-0.076
ment-0.075
ed-0.071
abouts-0.071
Token seek
Token ID5380
Feature activation+4.81e+00

Pos logit contributions
 moments+0.019
 inspection+0.016
ment+0.016
ed+0.015
abouts+0.015
Neg logit contributions
 Claus-0.036
 daddy-0.036
ingu-0.034
 boo-0.034
washer-0.034
Token.
Token ID13
Feature activation-9.25e-02

Pos logit contributions
 moments+0.271
 inspection+0.263
ment+0.248
abouts+0.232
 Alicia+0.231
Neg logit contributions
 daddy-0.197
 Claus-0.189
 living-0.180
washer-0.177
ingu-0.171
Token Ben
Token ID3932
Feature activation-6.07e-01

Pos logit contributions
 daddy+0.004
 Claus+0.004
ingu+0.003
 tank+0.003
 boo+0.003
Neg logit contributions
 moments-0.006
 inspection-0.005
ment-0.005
abouts-0.005
Found-0.005
Token was
Token ID373
Feature activation+5.78e-01

Pos logit contributions
 Claus+0.032
 daddy+0.030
ll+0.028
washer+0.028
ingu+0.028
Neg logit contributions
 moments-0.031
ment-0.030
 inspection-0.027
abouts-0.026
iece-0.025
Token the
Token ID262
Feature activation-5.40e-01

Pos logit contributions
 moments+0.037
 inspection+0.034
ment+0.034
abouts+0.032
ed+0.031
Neg logit contributions
 Claus-0.022
 daddy-0.021
ingu-0.019
 boo-0.019
washer-0.018
Token seeker
Token ID45993
Feature activation+8.55e+00

Pos logit contributions
ric+0.024
ingu+0.024
 Claus+0.023
ll+0.023
ppa+0.022
Neg logit contributions
 moments-0.028
 Alicia-0.025
 after-0.024
 insects-0.024
ger-0.024
Token and
Token ID290
Feature activation+5.64e-01

Pos logit contributions
 moments+0.319
 inspection+0.274
ment+0.265
abouts+0.246
ed+0.241
Neg logit contributions
 Claus-0.538
 daddy-0.533
ingu-0.507
washer-0.495
 boo-0.492
Token Lily
Token ID20037
Feature activation+9.66e-01

Pos logit contributions
 moments+0.027
 inspection+0.024
ment+0.023
abouts+0.023
ed+0.022
Neg logit contributions
 daddy-0.030
 Claus-0.030
ingu-0.028
washer-0.027
 boo-0.027
Token was
Token ID373
Feature activation+5.55e-01

Pos logit contributions
 moments+0.048
ment+0.044
 inspection+0.043
abouts+0.040
eways+0.037
Neg logit contributions
 Claus-0.051
 daddy-0.049
washer-0.047
ll-0.046
ingu-0.046
Token the
Token ID262
Feature activation-5.40e-01

Pos logit contributions
 moments+0.031
 inspection+0.028
ment+0.028
ed+0.026
abouts+0.026
Neg logit contributions
 Claus-0.025
 daddy-0.025
ingu-0.023
ric-0.022
washer-0.022
Token h
Token ID289
Feature activation+2.34e+00

Pos logit contributions
 daddy+0.023
 Claus+0.023
 boo+0.021
ingu+0.020
washer+0.020
Neg logit contributions
 moments-0.031
ment-0.029
 inspection-0.029
abouts-0.027
ed-0.027
Token house
Token ID2156
Feature activation-6.32e-01

Pos logit contributions
 moments+0.065
ment+0.062
 inspection+0.061
ed+0.059
edly+0.059
Neg logit contributions
 daddy-0.042
 Claus-0.040
ingu-0.037
washer-0.037
 cube-0.036
Token.
Token ID13
Feature activation-4.90e-02

Pos logit contributions
 Claus+0.032
 daddy+0.032
ingu+0.030
washer+0.029
ric+0.028
Neg logit contributions
 moments-0.031
 inspection-0.028
ment-0.027
abouts-0.026
ed-0.026
Token Lily
Token ID20037
Feature activation+9.36e-01

Pos logit contributions
 Claus+0.003
 daddy+0.003
ingu+0.003
ric+0.002
 boo+0.002
Neg logit contributions
 moments-0.002
ment-0.002
 inspection-0.002
ed-0.002
abouts-0.002
Token was
Token ID373
Feature activation+7.19e-01

Pos logit contributions
 moments+0.051
ment+0.050
 inspection+0.046
abouts+0.043
edly+0.043
Neg logit contributions
 Claus-0.044
 daddy-0.043
washer-0.039
ingu-0.039
ll-0.039
Token the
Token ID262
Feature activation-4.60e-01

Pos logit contributions
 moments+0.047
ment+0.045
 inspection+0.045
abouts+0.042
edly+0.041
Neg logit contributions
 daddy-0.025
 Claus-0.025
 boo-0.022
ingu-0.021
 living-0.021
Token seeker
Token ID45993
Feature activation+8.50e+00

Pos logit contributions
 Claus+0.021
ric+0.020
ingu+0.020
ppa+0.019
oun+0.019
Neg logit contributions
 moments-0.024
 Alicia-0.022
 Meg-0.020
 insects-0.020
 after-0.020
Token and
Token ID290
Feature activation+6.02e-01

Pos logit contributions
 moments+0.321
 inspection+0.278
ment+0.272
abouts+0.252
ed+0.242
Neg logit contributions
 Claus-0.526
 daddy-0.525
ingu-0.495
washer-0.483
 boo-0.480
Token Max
Token ID5436
Feature activation-3.49e+00

Pos logit contributions
 moments+0.033
 inspection+0.031
ment+0.030
abouts+0.029
ed+0.028
Neg logit contributions
 daddy-0.027
 Claus-0.027
ingu-0.025
washer-0.024
 boo-0.024
Token was
Token ID373
Feature activation+7.08e-01

Pos logit contributions
 Claus+0.164
 daddy+0.151
washer+0.145
ingu+0.141
ll+0.141
Neg logit contributions
 moments-0.187
ment-0.183
 inspection-0.173
abouts-0.163
iece-0.162
Token the
Token ID262
Feature activation-4.53e-01

Pos logit contributions
 moments+0.040
 inspection+0.037
ment+0.036
abouts+0.034
edly+0.033
Neg logit contributions
 Claus-0.031
 daddy-0.031
ingu-0.028
 boo-0.028
washer-0.028
Token h
Token ID289
Feature activation+2.36e+00

Pos logit contributions
 daddy+0.019
 Claus+0.018
ingu+0.017
 boo+0.016
washer+0.016
Neg logit contributions
 moments-0.027
ment-0.026
 inspection-0.025
ed-0.024
abouts-0.024
Token seek
Token ID5380
Feature activation+4.81e+00

Pos logit contributions
 moments+0.024
ment+0.022
 inspection+0.022
ed+0.020
abouts+0.019
Neg logit contributions
 daddy-0.037
 Claus-0.037
ingu-0.034
 boo-0.034
 cube-0.034
Token.
Token ID13
Feature activation-5.18e-02

Pos logit contributions
 inspection+0.297
 moments+0.296
ment+0.286
Run+0.269
 Alicia+0.268
Neg logit contributions
 living-0.159
 daddy-0.155
 sewing-0.139
 tank-0.137
 Claus-0.136
Token Tom
Token ID4186
Feature activation-3.72e-01

Pos logit contributions
 daddy+0.003
 Claus+0.003
ingu+0.002
ric+0.002
oun+0.002
Neg logit contributions
 moments-0.003
ment-0.002
 inspection-0.002
ed-0.002
edly-0.002
Token was
Token ID373
Feature activation+6.62e-01

Pos logit contributions
 Claus+0.018
 daddy+0.017
ingu+0.016
washer+0.016
ll+0.016
Neg logit contributions
 moments-0.020
ment-0.019
 inspection-0.018
abouts-0.017
edly-0.017
Token the
Token ID262
Feature activation-5.68e-01

Pos logit contributions
 moments+0.042
 inspection+0.039
ment+0.039
abouts+0.037
edly+0.036
Neg logit contributions
 Claus-0.025
 daddy-0.024
ingu-0.022
 boo-0.022
washer-0.021
Token seeker
Token ID45993
Feature activation+8.49e+00

Pos logit contributions
 Claus+0.026
ingu+0.024
ric+0.024
 daddy+0.024
ppa+0.024
Neg logit contributions
 moments-0.030
 Alicia-0.027
 Meg-0.025
 insects-0.025
 inspection-0.025
Token and
Token ID290
Feature activation+6.25e-01

Pos logit contributions
 moments+0.298
 inspection+0.253
ment+0.246
abouts+0.225
ed+0.224
Neg logit contributions
 Claus-0.554
 daddy-0.547
ingu-0.524
washer-0.510
 boo-0.508
Token Lily
Token ID20037
Feature activation+9.81e-01

Pos logit contributions
 moments+0.029
 inspection+0.026
ment+0.025
abouts+0.024
ed+0.024
Neg logit contributions
 Claus-0.034
 daddy-0.034
ingu-0.032
washer-0.031
 boo-0.031
Token was
Token ID373
Feature activation+6.39e-01

Pos logit contributions
 moments+0.049
ment+0.046
 inspection+0.045
abouts+0.041
edly+0.040
Neg logit contributions
 Claus-0.050
 daddy-0.048
washer-0.046
ingu-0.046
ll-0.045
Token the
Token ID262
Feature activation-5.64e-01

Pos logit contributions
 moments+0.035
 inspection+0.031
ment+0.031
abouts+0.029
ed+0.029
Neg logit contributions
 Claus-0.030
 daddy-0.029
ingu-0.028
ric-0.027
washer-0.027
Token h
Token ID289
Feature activation+2.36e+00

Pos logit contributions
 daddy+0.023
 Claus+0.022
 boo+0.020
washer+0.020
ingu+0.020
Neg logit contributions
 moments-0.034
ment-0.033
 inspection-0.032
ed-0.030
abouts-0.030
Token park
Token ID3952
Feature activation-6.78e-01

Pos logit contributions
 Claus+0.027
 daddy+0.025
ingu+0.024
ric+0.023
ll+0.023
Neg logit contributions
 moments-0.033
 inspection-0.029
ment-0.028
abouts-0.027
ed-0.027
Token.
Token ID13
Feature activation-7.87e-02

Pos logit contributions
 Claus+0.034
 daddy+0.033
ingu+0.031
washer+0.030
ll+0.029
Neg logit contributions
 moments-0.035
 inspection-0.032
ment-0.030
abouts-0.029
ed-0.029
Token Lily
Token ID20037
Feature activation+8.93e-01

Pos logit contributions
 Claus+0.004
 daddy+0.004
ingu+0.004
ric+0.004
 boo+0.004
Neg logit contributions
 moments-0.004
ment-0.003
 inspection-0.003
ed-0.003
edly-0.003
Token was
Token ID373
Feature activation+5.67e-01

Pos logit contributions
 moments+0.049
ment+0.048
 inspection+0.045
abouts+0.042
edly+0.042
Neg logit contributions
 Claus-0.042
 daddy-0.040
washer-0.037
ll-0.037
ingu-0.037
Token the
Token ID262
Feature activation-5.61e-01

Pos logit contributions
 moments+0.038
ment+0.036
 inspection+0.036
abouts+0.034
edly+0.033
Neg logit contributions
 daddy-0.020
 Claus-0.019
 boo-0.017
 living-0.017
ingu-0.016
Token seeker
Token ID45993
Feature activation+8.47e+00

Pos logit contributions
 Claus+0.025
ingu+0.024
 daddy+0.024
ric+0.023
washer+0.023
Neg logit contributions
 moments-0.030
 Alicia-0.027
 inspection-0.026
abouts-0.026
 Meg-0.026
Token and
Token ID290
Feature activation+5.43e-01

Pos logit contributions
 moments+0.295
 inspection+0.250
ment+0.242
abouts+0.222
ed+0.219
Neg logit contributions
 Claus-0.556
 daddy-0.549
ingu-0.526
washer-0.512
 boo-0.510
Token Max
Token ID5436
Feature activation-3.50e+00

Pos logit contributions
 moments+0.030
 inspection+0.027
ment+0.027
abouts+0.025
ed+0.025
Neg logit contributions
 Claus-0.025
 daddy-0.024
ingu-0.023
washer-0.022
 boo-0.022
Token was
Token ID373
Feature activation+5.67e-01

Pos logit contributions
 Claus+0.167
 daddy+0.155
washer+0.147
ll+0.144
ingu+0.144
Neg logit contributions
 moments-0.187
ment-0.180
 inspection-0.172
abouts-0.162
iece-0.159
Token the
Token ID262
Feature activation-5.67e-01

Pos logit contributions
 moments+0.029
 inspection+0.027
ment+0.027
abouts+0.025
edly+0.025
Neg logit contributions
 Claus-0.027
 daddy-0.027
ingu-0.025
 boo-0.025
washer-0.024
Token h
Token ID289
Feature activation+2.30e+00

Pos logit contributions
 daddy+0.023
 Claus+0.022
 boo+0.020
ingu+0.020
washer+0.020
Neg logit contributions
 moments-0.034
ment-0.033
 inspection-0.032
ed-0.030
abouts-0.030
Token park
Token ID3952
Feature activation-6.43e-01

Pos logit contributions
 Claus+0.025
 daddy+0.023
ingu+0.023
ll+0.022
ric+0.022
Neg logit contributions
 moments-0.029
 inspection-0.026
ment-0.025
abouts-0.025
ed-0.024
Token.
Token ID13
Feature activation-5.18e-02

Pos logit contributions
 Claus+0.030
 daddy+0.029
ingu+0.027
washer+0.026
 cube+0.026
Neg logit contributions
 moments-0.035
 inspection-0.032
ment-0.031
abouts-0.029
ed-0.028
Token Sara
Token ID24799
Feature activation+7.91e-01

Pos logit contributions
 Claus+0.003
 daddy+0.003
ingu+0.003
ric+0.002
 boo+0.002
Neg logit contributions
 moments-0.002
 inspection-0.002
ment-0.002
ed-0.002
abouts-0.002
Token is
Token ID318
Feature activation+5.81e-01

Pos logit contributions
 moments+0.045
ment+0.042
 inspection+0.041
abouts+0.038
edly+0.038
Neg logit contributions
 Claus-0.035
 daddy-0.034
ingu-0.031
ll-0.031
washer-0.031
Token the
Token ID262
Feature activation-5.30e-01

Pos logit contributions
 moments+0.038
ment+0.037
 inspection+0.036
abouts+0.035
oos+0.034
Neg logit contributions
 daddy-0.021
 Claus-0.020
 living-0.018
 boo-0.018
 supposed-0.017
Token seeker
Token ID45993
Feature activation+8.47e+00

Pos logit contributions
 Claus+0.024
ingu+0.022
 daddy+0.022
ric+0.022
ppa+0.021
Neg logit contributions
 moments-0.029
 Alicia-0.026
 inspection-0.025
 Meg-0.024
abouts-0.024
Token and
Token ID290
Feature activation+5.98e-01

Pos logit contributions
 moments+0.308
 inspection+0.264
ment+0.256
abouts+0.237
ed+0.231
Neg logit contributions
 Claus-0.538
 daddy-0.534
ingu-0.509
washer-0.495
 boo-0.492
Token Ben
Token ID3932
Feature activation-6.54e-01

Pos logit contributions
 moments+0.030
 inspection+0.027
ment+0.027
ed+0.025
abouts+0.025
Neg logit contributions
 Claus-0.030
 daddy-0.029
ingu-0.028
ric-0.027
 boo-0.027
Token is
Token ID318
Feature activation+5.78e-01

Pos logit contributions
 Claus+0.030
 daddy+0.029
ingu+0.027
washer+0.026
ll+0.026
Neg logit contributions
 moments-0.036
 inspection-0.033
ment-0.032
abouts-0.031
ed-0.030
Token the
Token ID262
Feature activation-5.38e-01

Pos logit contributions
 moments+0.031
 inspection+0.030
ment+0.030
edly+0.028
abouts+0.028
Neg logit contributions
 daddy-0.026
 Claus-0.026
 living-0.023
washer-0.023
 boo-0.022
Token h
Token ID289
Feature activation+2.32e+00

Pos logit contributions
 daddy+0.023
 Claus+0.023
ingu+0.021
 boo+0.020
washer+0.020
Neg logit contributions
 moments-0.031
ment-0.029
 inspection-0.029
ed-0.027
abouts-0.027
Token.
Token ID13
Feature activation-3.29e-01

Pos logit contributions
ric+0.061
ingu+0.059
 Claus+0.056
 daddy+0.056
oun+0.055
Neg logit contributions
 moments-0.022
ed-0.019
 after-0.017
ger-0.016
ment-0.016
Token You
Token ID921
Feature activation+1.53e-03

Pos logit contributions
 Claus+0.013
 daddy+0.012
ingu+0.012
ric+0.012
ll+0.012
Neg logit contributions
 moments-0.020
ment-0.018
 inspection-0.018
ed-0.018
edly-0.017
Token are
Token ID389
Feature activation+5.69e-01

Pos logit contributions
 moments+0.000
ed+0.000
 inspection+0.000
 after+0.000
 widened+0.000
Neg logit contributions
ric-0.000
 Claus-0.000
 daddy-0.000
ingu-0.000
ich-0.000
Token a
Token ID257
Feature activation-3.69e-02

Pos logit contributions
 Meg+0.022
 Alicia+0.021
 moments+0.021
 after+0.020
 insects+0.020
Neg logit contributions
oun-0.034
ric-0.032
ll-0.032
ingu-0.031
 Claus-0.031
Token fair
Token ID3148
Feature activation+2.86e+00

Pos logit contributions
ric+0.002
 Claus+0.002
ingu+0.002
ll+0.002
ppa+0.002
Neg logit contributions
 moments-0.002
 after-0.001
 insects-0.001
 minutes-0.001
ger-0.001
Token seeker
Token ID45993
Feature activation+8.45e+00

Pos logit contributions
 moments+0.152
ment+0.137
 inspection+0.134
ed+0.130
abouts+0.124
Neg logit contributions
 Claus-0.135
ingu-0.128
ric-0.127
 daddy-0.125
ll-0.121
Token.
Token ID13
Feature activation-2.95e-01

Pos logit contributions
 moments+0.370
 inspection+0.316
ment+0.313
ed+0.305
abouts+0.290
Neg logit contributions
 Claus-0.485
 daddy-0.468
ingu-0.459
ric-0.452
 boo-0.439
Token You
Token ID921
Feature activation+2.03e-02

Pos logit contributions
 Claus+0.011
 daddy+0.011
ingu+0.010
 boo+0.009
washer+0.009
Neg logit contributions
 moments-0.019
 inspection-0.017
ment-0.017
abouts-0.016
ed-0.016
Token did
Token ID750
Feature activation+1.14e+00

Pos logit contributions
 moments+0.001
ed+0.001
 inspection+0.001
 widened+0.001
 after+0.001
Neg logit contributions
 daddy-0.001
ric-0.001
 Claus-0.001
ingu-0.001
oun-0.001
Token not
Token ID407
Feature activation-2.96e+00

Pos logit contributions
 moments+0.081
 inspection+0.075
ment+0.073
ed+0.071
abouts+0.071
Neg logit contributions
 Claus-0.034
 daddy-0.032
ingu-0.030
washer-0.028
ric-0.028
Token cheat
Token ID22705
Feature activation+2.68e-01

Pos logit contributions
 Claus+0.138
 daddy+0.134
ingu+0.130
washer+0.124
ll+0.123
Neg logit contributions
 moments-0.162
 inspection-0.145
ment-0.140
ed-0.135
abouts-0.134
Token "
Token ID366
Feature activation+1.28e-01

Pos logit contributions
 Claus+0.016
 daddy+0.016
ingu+0.015
washer+0.014
 boo+0.014
Neg logit contributions
 moments-0.015
 inspection-0.013
ment-0.013
abouts-0.012
oos-0.012
TokenYou
Token ID1639
Feature activation+3.34e-01

Pos logit contributions
 moments+0.006
 inspection+0.006
ment+0.005
 passages+0.005
oos+0.005
Neg logit contributions
 Claus-0.007
 daddy-0.006
ingu-0.006
 boo-0.006
oun-0.006
Token are
Token ID389
Feature activation+4.79e-01

Pos logit contributions
 moments+0.014
ed+0.013
 inspection+0.012
 after+0.012
 reached+0.012
Neg logit contributions
ric-0.017
oun-0.017
ich-0.017
 daddy-0.016
 Claus-0.016
Token a
Token ID257
Feature activation-1.87e-01

Pos logit contributions
 moments+0.021
 Alicia+0.018
 Meg+0.018
 after+0.017
ed+0.016
Neg logit contributions
oun-0.026
 Claus-0.025
ll-0.025
ric-0.025
ingu-0.025
Token good
Token ID922
Feature activation+9.84e-01

Pos logit contributions
ric+0.009
 Claus+0.009
ingu+0.008
ll+0.008
ppa+0.008
Neg logit contributions
 moments-0.010
 inspection-0.008
 Alicia-0.008
 after-0.008
Exc-0.008
Token seeker
Token ID45993
Feature activation+8.44e+00

Pos logit contributions
 moments+0.062
 inspection+0.057
ment+0.056
ed+0.054
abouts+0.054
Neg logit contributions
 Claus-0.037
 daddy-0.036
ingu-0.034
 boo-0.032
washer-0.032
Token and
Token ID290
Feature activation+3.79e-01

Pos logit contributions
 moments+0.345
 inspection+0.298
ment+0.291
ed+0.276
abouts+0.268
Neg logit contributions
 Claus-0.505
 daddy-0.492
ingu-0.479
ric-0.470
 boo-0.462
Token a
Token ID257
Feature activation-1.75e-01

Pos logit contributions
 moments+0.023
ment+0.020
ed+0.020
 inspection+0.019
 Alicia+0.019
Neg logit contributions
 Claus-0.016
ric-0.016
 daddy-0.015
ingu-0.015
ll-0.014
Token good
Token ID922
Feature activation+9.95e-01

Pos logit contributions
 Claus+0.008
ric+0.008
ingu+0.007
ppa+0.007
 daddy+0.007
Neg logit contributions
 moments-0.010
 inspection-0.008
 Alicia-0.008
abouts-0.008
ment-0.008
Token sister
Token ID6621
Feature activation+9.54e-01

Pos logit contributions
 moments+0.061
 inspection+0.055
ment+0.055
ed+0.053
abouts+0.052
Neg logit contributions
 Claus-0.040
 daddy-0.038
ingu-0.036
ric-0.035
washer-0.034
Token.
Token ID13
Feature activation-2.56e-01

Pos logit contributions
 moments+0.049
ment+0.042
 inspection+0.042
ed+0.041
edly+0.038
Neg logit contributions
 Claus-0.047
 daddy-0.047
ingu-0.046
ric-0.046
 boo-0.044
Token park
Token ID3952
Feature activation-6.63e-01

Pos logit contributions
 Claus+0.026
 daddy+0.025
ingu+0.024
ric+0.023
washer+0.023
Neg logit contributions
 moments-0.033
 inspection-0.029
ment-0.029
ed-0.028
abouts-0.027
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
 Claus+0.029
 daddy+0.029
ingu+0.026
washer+0.026
 cube+0.025
Neg logit contributions
 moments-0.037
 inspection-0.034
ment-0.033
abouts-0.031
ed-0.030
Token Lily
Token ID20037
Feature activation+8.70e-01

Pos logit contributions
 Claus+0.007
 daddy+0.007
ingu+0.007
oun+0.006
ric+0.006
Neg logit contributions
 moments-0.007
ment-0.006
 inspection-0.006
ed-0.005
edly-0.005
Token was
Token ID373
Feature activation+5.08e-01

Pos logit contributions
 moments+0.047
ment+0.045
 inspection+0.043
abouts+0.040
edly+0.040
Neg logit contributions
 Claus-0.041
 daddy-0.040
ingu-0.037
washer-0.036
ll-0.036
Token the
Token ID262
Feature activation-5.82e-01

Pos logit contributions
 moments+0.032
ment+0.030
 inspection+0.030
abouts+0.029
edly+0.028
Neg logit contributions
 daddy-0.019
 Claus-0.019
ingu-0.017
 boo-0.017
washer-0.016
Token seeker
Token ID45993
Feature activation+8.43e+00

Pos logit contributions
 Claus+0.024
ingu+0.023
ric+0.022
 daddy+0.022
washer+0.022
Neg logit contributions
 moments-0.033
 Alicia-0.031
 Meg-0.029
 inspection-0.028
abouts-0.028
Token and
Token ID290
Feature activation+5.06e-01

Pos logit contributions
 moments+0.311
 inspection+0.267
ment+0.260
abouts+0.240
ed+0.236
Neg logit contributions
 Claus-0.532
 daddy-0.528
ingu-0.502
washer-0.488
 boo-0.486
Token Tom
Token ID4186
Feature activation-4.30e-01

Pos logit contributions
 moments+0.025
 inspection+0.022
ment+0.021
abouts+0.020
ed+0.020
Neg logit contributions
 Claus-0.027
 daddy-0.026
ingu-0.025
washer-0.024
 boo-0.024
Token was
Token ID373
Feature activation+5.26e-01

Pos logit contributions
 Claus+0.021
 daddy+0.020
ingu+0.019
washer+0.019
ll+0.019
Neg logit contributions
 moments-0.022
ment-0.020
 inspection-0.020
abouts-0.019
edly-0.018
Token the
Token ID262
Feature activation-5.81e-01

Pos logit contributions
 moments+0.025
 inspection+0.022
ment+0.022
ed+0.021
abouts+0.021
Neg logit contributions
 Claus-0.028
 daddy-0.027
ingu-0.026
ric-0.025
washer-0.025
Token h
Token ID289
Feature activation+2.36e+00

Pos logit contributions
 daddy+0.023
 Claus+0.022
 boo+0.020
ingu+0.019
washer+0.019
Neg logit contributions
ment-0.036
 moments-0.036
 inspection-0.035
ed-0.032
abouts-0.032
Token seek
Token ID5380
Feature activation+4.62e+00

Pos logit contributions
 moments+0.020
ment+0.018
 inspection+0.018
ed+0.017
oos+0.016
Neg logit contributions
 daddy-0.028
 Claus-0.027
ingu-0.025
 boo-0.025
 cube-0.025
Token.
Token ID13
Feature activation-1.22e-01

Pos logit contributions
 moments+0.291
 inspection+0.285
ment+0.273
growth+0.252
 Alicia+0.251
Neg logit contributions
 living-0.151
 daddy-0.146
 Claus-0.136
washer-0.128
 sewing-0.126
Token Tom
Token ID4186
Feature activation-4.67e-01

Pos logit contributions
 Claus+0.007
 daddy+0.007
ingu+0.007
washer+0.006
 boo+0.006
Neg logit contributions
 moments-0.005
 inspection-0.005
ment-0.005
abouts-0.004
ed-0.004
Token is
Token ID318
Feature activation+4.35e-01

Pos logit contributions
 Claus+0.023
 daddy+0.022
ingu+0.021
ll+0.020
 boo+0.020
Neg logit contributions
 moments-0.025
ment-0.022
 inspection-0.022
abouts-0.020
ed-0.020
Token the
Token ID262
Feature activation-6.56e-01

Pos logit contributions
 moments+0.027
ment+0.025
 inspection+0.025
abouts+0.024
edly+0.023
Neg logit contributions
 Claus-0.018
 daddy-0.017
ingu-0.016
 boo-0.015
washer-0.015
Token seeker
Token ID45993
Feature activation+8.40e+00

Pos logit contributions
 Claus+0.028
 daddy+0.026
ingu+0.026
ric+0.026
ppa+0.025
Neg logit contributions
 moments-0.038
 Alicia-0.033
 inspection-0.033
abouts-0.032
 Meg-0.031
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
 moments+0.318
 inspection+0.273
ment+0.265
ed+0.246
abouts+0.245
Neg logit contributions
 Claus-0.527
 daddy-0.518
ingu-0.498
washer-0.483
ric-0.483
Token He
Token ID679
Feature activation-1.24e-01

Pos logit contributions
 Claus+0.007
 daddy+0.006
ingu+0.006
oun+0.006
washer+0.006
Neg logit contributions
 moments-0.006
ment-0.005
 inspection-0.005
abouts-0.005
oos-0.005
Token counts
Token ID9853
Feature activation+5.71e+00

Pos logit contributions
 Claus+0.006
 daddy+0.006
ingu+0.006
ll+0.006
 boo+0.006
Neg logit contributions
 moments-0.006
ment-0.006
 inspection-0.006
abouts-0.005
edly-0.005
Token to
Token ID284
Feature activation+6.11e-01

Pos logit contributions
 moments+0.295
ment+0.257
 inspection+0.253
ed+0.246
abouts+0.245
Neg logit contributions
 daddy-0.280
 Claus-0.275
ingu-0.259
ric-0.255
washer-0.250
Token ten
Token ID3478
Feature activation+3.80e+00

Pos logit contributions
ment+0.034
 moments+0.033
ed+0.032
edly+0.031
overed+0.031
Neg logit contributions
 daddy-0.026
 living-0.024
 Claus-0.024
ingu-0.022
 boo-0.022
Token park
Token ID3952
Feature activation-7.87e-01

Pos logit contributions
 Claus+0.030
 daddy+0.029
ingu+0.028
ric+0.026
washer+0.026
Neg logit contributions
 moments-0.039
 inspection-0.036
ment-0.035
ed-0.034
abouts-0.033
Token.
Token ID13
Feature activation-7.03e-02

Pos logit contributions
 Claus+0.034
 daddy+0.034
ingu+0.030
washer+0.030
 cube+0.030
Neg logit contributions
 moments-0.045
 inspection-0.041
ment-0.039
abouts-0.038
ed-0.037
Token Anna
Token ID11735
Feature activation-3.33e-01

Pos logit contributions
 daddy+0.004
 Claus+0.004
ingu+0.004
oun+0.004
 boo+0.003
Neg logit contributions
 moments-0.003
ment-0.003
 inspection-0.003
ed-0.003
abouts-0.003
Token was
Token ID373
Feature activation+4.90e-01

Pos logit contributions
 Claus+0.016
 daddy+0.015
washer+0.014
ingu+0.014
ll+0.014
Neg logit contributions
 moments-0.018
ment-0.017
 inspection-0.016
abouts-0.015
edly-0.015
Token the
Token ID262
Feature activation-6.86e-01

Pos logit contributions
 moments+0.032
ment+0.031
 inspection+0.030
abouts+0.029
edly+0.028
Neg logit contributions
 daddy-0.018
 Claus-0.017
 boo-0.015
 living-0.015
ingu-0.015
Token seeker
Token ID45993
Feature activation+8.40e+00

Pos logit contributions
 Claus+0.031
ingu+0.028
 daddy+0.028
ric+0.028
washer+0.027
Neg logit contributions
 moments-0.038
 Alicia-0.034
 inspection-0.033
 Meg-0.032
abouts-0.032
Token and
Token ID290
Feature activation+5.05e-01

Pos logit contributions
 moments+0.297
 inspection+0.254
ment+0.247
abouts+0.227
ed+0.221
Neg logit contributions
 Claus-0.542
 daddy-0.539
ingu-0.513
washer-0.499
 boo-0.497
Token Ben
Token ID3932
Feature activation-7.47e-01

Pos logit contributions
 moments+0.024
 inspection+0.021
ment+0.021
ed+0.020
abouts+0.019
Neg logit contributions
 Claus-0.027
 daddy-0.026
ingu-0.025
ric-0.025
 boo-0.025
Token was
Token ID373
Feature activation+4.81e-01

Pos logit contributions
 Claus+0.037
 daddy+0.036
ingu+0.033
washer+0.033
ll+0.033
Neg logit contributions
 moments-0.038
ment-0.035
 inspection-0.035
abouts-0.033
edly-0.031
Token the
Token ID262
Feature activation-6.96e-01

Pos logit contributions
 moments+0.025
 inspection+0.023
ment+0.023
abouts+0.021
edly+0.021
Neg logit contributions
 Claus-0.023
 daddy-0.023
ingu-0.021
 boo-0.021
ric-0.021
Token h
Token ID289
Feature activation+2.27e+00

Pos logit contributions
 daddy+0.029
 Claus+0.028
ingu+0.025
 boo+0.025
washer+0.025
Neg logit contributions
 moments-0.041
ment-0.040
 inspection-0.039
ed-0.037
abouts-0.036
Token park
Token ID3952
Feature activation-7.47e-01

Pos logit contributions
 Claus+0.028
 daddy+0.027
ingu+0.026
ll+0.025
ric+0.025
Neg logit contributions
 moments-0.034
 inspection-0.030
ment-0.029
abouts-0.028
ed-0.028
Token.
Token ID13
Feature activation-9.01e-02

Pos logit contributions
 Claus+0.036
 daddy+0.035
ingu+0.032
washer+0.032
ll+0.031
Neg logit contributions
 moments-0.039
 inspection-0.036
ment-0.035
abouts-0.033
ed-0.032
Token Lily
Token ID20037
Feature activation+7.80e-01

Pos logit contributions
 daddy+0.005
 Claus+0.005
ingu+0.005
 boo+0.004
 tank+0.004
Neg logit contributions
 moments-0.004
ment-0.004
 inspection-0.004
ed-0.004
edly-0.004
Token is
Token ID318
Feature activation+5.00e-01

Pos logit contributions
 moments+0.045
ment+0.043
 inspection+0.041
edly+0.039
abouts+0.039
Neg logit contributions
 Claus-0.034
 daddy-0.033
ingu-0.030
ll-0.030
washer-0.030
Token the
Token ID262
Feature activation-6.30e-01

Pos logit contributions
 moments+0.031
ment+0.030
 inspection+0.030
abouts+0.029
oos+0.028
Neg logit contributions
 daddy-0.020
 Claus-0.019
 living-0.018
 boo-0.017
 supposed-0.017
Token seeker
Token ID45993
Feature activation+8.36e+00

Pos logit contributions
 Claus+0.028
ingu+0.027
 daddy+0.027
ric+0.026
washer+0.026
Neg logit contributions
 moments-0.034
 Alicia-0.030
 inspection-0.030
 Meg-0.029
abouts-0.028
Token and
Token ID290
Feature activation+4.57e-01

Pos logit contributions
 moments+0.300
 inspection+0.257
ment+0.250
abouts+0.229
ed+0.222
Neg logit contributions
 Claus-0.537
 daddy-0.532
ingu-0.507
washer-0.494
 boo-0.491
Token Ben
Token ID3932
Feature activation-7.50e-01

Pos logit contributions
 moments+0.022
 inspection+0.020
ment+0.019
ed+0.018
abouts+0.018
Neg logit contributions
 Claus-0.024
 daddy-0.023
ingu-0.022
washer-0.021
ric-0.021
Token is
Token ID318
Feature activation+4.96e-01

Pos logit contributions
 Claus+0.035
 daddy+0.034
ingu+0.032
washer+0.031
ll+0.031
Neg logit contributions
 moments-0.040
ment-0.037
 inspection-0.036
abouts-0.034
edly-0.034
Token the
Token ID262
Feature activation-6.39e-01

Pos logit contributions
 moments+0.027
 inspection+0.026
ment+0.025
abouts+0.024
edly+0.024
Neg logit contributions
 daddy-0.023
 Claus-0.022
 living-0.020
washer-0.020
 boo-0.020
Token h
Token ID289
Feature activation+2.25e+00

Pos logit contributions
 daddy+0.028
 Claus+0.027
ingu+0.025
 boo+0.025
washer+0.024
Neg logit contributions
 moments-0.037
ment-0.035
 inspection-0.034
ed-0.032
abouts-0.032
Token seek
Token ID5380
Feature activation+4.62e+00

Pos logit contributions
 moments+0.020
 inspection+0.017
ment+0.017
ed+0.016
abouts+0.016
Neg logit contributions
 daddy-0.033
 Claus-0.033
ingu-0.031
 boo-0.031
washer-0.030
Token.
Token ID13
Feature activation-3.84e-02

Pos logit contributions
 moments+0.261
 inspection+0.249
ment+0.235
abouts+0.223
 Alicia+0.220
Neg logit contributions
 daddy-0.193
 Claus-0.187
washer-0.179
 living-0.173
ingu-0.170
Token Tom
Token ID4186
Feature activation-4.04e-01

Pos logit contributions
 daddy+0.002
 Claus+0.002
ingu+0.002
washer+0.002
 boo+0.002
Neg logit contributions
 moments-0.002
ment-0.002
 inspection-0.002
ed-0.002
abouts-0.001
Token is
Token ID318
Feature activation+5.06e-01

Pos logit contributions
 Claus+0.022
 daddy+0.021
ingu+0.020
washer+0.020
 boo+0.020
Neg logit contributions
 moments-0.019
ment-0.017
 inspection-0.017
abouts-0.016
ed-0.015
Token the
Token ID262
Feature activation-5.65e-01

Pos logit contributions
 moments+0.029
 inspection+0.026
ment+0.025
ed+0.025
 Alicia+0.024
Neg logit contributions
 Claus-0.022
 daddy-0.021
ingu-0.021
ric-0.020
ll-0.020
Token seeker
Token ID45993
Feature activation+8.36e+00

Pos logit contributions
 Claus+0.026
ric+0.026
ppa+0.026
oun+0.025
ingu+0.025
Neg logit contributions
 moments-0.028
 Alicia-0.025
 after-0.023
 insects-0.023
 Meg-0.023
Token and
Token ID290
Feature activation+5.38e-01

Pos logit contributions
 moments+0.308
 inspection+0.264
ment+0.255
abouts+0.236
ed+0.233
Neg logit contributions
 Claus-0.531
 daddy-0.524
ingu-0.501
washer-0.490
 boo-0.485
Token Mia
Token ID32189
Feature activation+3.77e+00

Pos logit contributions
 moments+0.020
 inspection+0.017
ment+0.016
abouts+0.016
ed+0.015
Neg logit contributions
 daddy-0.035
 Claus-0.034
ingu-0.033
washer-0.032
 boo-0.031
Token is
Token ID318
Feature activation+5.02e-01

Pos logit contributions
 moments+0.173
 inspection+0.153
ment+0.150
abouts+0.140
ed+0.140
Neg logit contributions
 Claus-0.207
 daddy-0.202
ingu-0.194
washer-0.188
 boo-0.187
Token the
Token ID262
Feature activation-5.75e-01

Pos logit contributions
 moments+0.026
 inspection+0.023
ment+0.023
abouts+0.022
ed+0.022
Neg logit contributions
 Claus-0.025
 daddy-0.024
ingu-0.023
 boo-0.022
washer-0.022
Token h
Token ID289
Feature activation+2.29e+00

Pos logit contributions
 Claus+0.026
 daddy+0.025
ingu+0.024
 boo+0.023
washer+0.023
Neg logit contributions
 moments-0.032
 inspection-0.029
ment-0.029
ed-0.028
abouts-0.027
Token park
Token ID3952
Feature activation-7.70e-01

Pos logit contributions
 Claus+0.027
 daddy+0.026
ingu+0.025
ric+0.024
ll+0.024
Neg logit contributions
 moments-0.032
 inspection-0.028
ment-0.028
abouts-0.027
ed-0.027
Token.
Token ID13
Feature activation-8.73e-02

Pos logit contributions
 Claus+0.034
 daddy+0.033
ingu+0.029
 cube+0.029
washer+0.029
Neg logit contributions
 moments-0.044
 inspection-0.040
ment-0.039
abouts-0.037
ed-0.036
Token Lily
Token ID20037
Feature activation+7.99e-01

Pos logit contributions
 Claus+0.004
 daddy+0.004
ingu+0.004
oun+0.004
 tank+0.004
Neg logit contributions
 moments-0.005
ment-0.004
 inspection-0.004
ed-0.004
edly-0.004
Token was
Token ID373
Feature activation+5.14e-01

Pos logit contributions
 moments+0.045
ment+0.043
 inspection+0.041
abouts+0.038
edly+0.038
Neg logit contributions
 Claus-0.037
 daddy-0.036
washer-0.033
ll-0.033
ingu-0.032
Token the
Token ID262
Feature activation-5.89e-01

Pos logit contributions
 moments+0.034
ment+0.032
 inspection+0.032
abouts+0.031
edly+0.029
Neg logit contributions
 daddy-0.018
 Claus-0.018
 boo-0.016
ingu-0.015
 living-0.015
Token seeker
Token ID45993
Feature activation+8.33e+00

Pos logit contributions
 Claus+0.025
ingu+0.024
 daddy+0.024
ric+0.023
washer+0.023
Neg logit contributions
 moments-0.033
 Alicia-0.030
 inspection-0.028
 Meg-0.028
abouts-0.028
Token and
Token ID290
Feature activation+5.17e-01

Pos logit contributions
 moments+0.286
 inspection+0.243
ment+0.235
abouts+0.215
ed+0.212
Neg logit contributions
 Claus-0.550
 daddy-0.544
ingu-0.521
washer-0.507
 boo-0.505
Token Tom
Token ID4186
Feature activation-4.63e-01

Pos logit contributions
 moments+0.024
 inspection+0.022
ment+0.021
abouts+0.020
ed+0.020
Neg logit contributions
 Claus-0.028
 daddy-0.028
ingu-0.026
washer-0.025
 boo-0.025
Token was
Token ID373
Feature activation+5.07e-01

Pos logit contributions
 Claus+0.023
 daddy+0.022
ingu+0.021
washer+0.021
ll+0.021
Neg logit contributions
 moments-0.024
ment-0.022
 inspection-0.021
abouts-0.020
edly-0.020
Token the
Token ID262
Feature activation-6.04e-01

Pos logit contributions
 moments+0.027
 inspection+0.024
ment+0.024
abouts+0.023
ed+0.022
Neg logit contributions
 Claus-0.025
 daddy-0.024
ingu-0.022
 boo-0.022
ric-0.022
Token h
Token ID289
Feature activation+2.23e+00

Pos logit contributions
 daddy+0.024
 Claus+0.024
ingu+0.021
 boo+0.021
washer+0.021
Neg logit contributions
 moments-0.037
ment-0.035
 inspection-0.035
ed-0.032
abouts-0.032
Token the
Token ID262
Feature activation-7.88e-01

Pos logit contributions
 moments+0.116
 inspection+0.101
ment+0.099
 Meg+0.098
 Alicia+0.098
Neg logit contributions
 Claus-0.084
oun-0.080
ingu-0.078
ric-0.077
ppa-0.074
Token dog
Token ID3290
Feature activation+8.93e-01

Pos logit contributions
 Claus+0.042
ingu+0.041
 daddy+0.039
ppa+0.038
ll+0.038
Neg logit contributions
 moments-0.041
 inspection-0.032
abouts-0.032
ment-0.031
 Alicia-0.031
Token is
Token ID318
Feature activation+4.72e-01

Pos logit contributions
 moments+0.037
ed+0.033
 inspection+0.032
ger+0.029
 after+0.029
Neg logit contributions
 daddy-0.052
ingu-0.051
 Claus-0.049
ric-0.049
ppa-0.048
Token the
Token ID262
Feature activation-8.22e-01

Pos logit contributions
 moments+0.021
 Alicia+0.019
 after+0.018
 Meg+0.018
 minutes+0.017
Neg logit contributions
washer-0.025
ingu-0.025
oun-0.025
 Claus-0.025
ll-0.024
Token best
Token ID1266
Feature activation-2.53e-02

Pos logit contributions
ingu+0.035
 Claus+0.035
washer+0.034
ric+0.034
ppa+0.032
Neg logit contributions
 moments-0.047
 after-0.040
 insects-0.040
 Alicia-0.039
ger-0.039
Token seeker
Token ID45993
Feature activation+8.30e+00

Pos logit contributions
 Claus+0.001
ingu+0.001
ric+0.001
 daddy+0.001
ppa+0.001
Neg logit contributions
 moments-0.001
 inspection-0.001
ment-0.001
ed-0.001
 after-0.001
Token!"
Token ID2474
Feature activation+3.23e-01

Pos logit contributions
 moments+0.351
 inspection+0.303
ment+0.296
ed+0.287
abouts+0.276
Neg logit contributions
 Claus-0.489
 daddy-0.476
ingu-0.463
ric-0.451
 boo-0.445
Token
Token ID198
Feature activation-1.81e-02

Pos logit contributions
 moments+0.016
 inspection+0.014
ment+0.014
ed+0.013
abouts+0.013
Neg logit contributions
 Claus-0.017
 daddy-0.016
ingu-0.016
washer-0.015
ric-0.015
Token
Token ID198
Feature activation-4.41e-02

Pos logit contributions
 Claus+0.001
 daddy+0.001
washer+0.001
ingu+0.001
 boo+0.001
Neg logit contributions
 moments-0.001
ment-0.001
 inspection-0.001
ed-0.001
abouts-0.001
TokenBen
Token ID11696
Feature activation+1.55e+00

Pos logit contributions
 Claus+0.003
 daddy+0.003
ingu+0.002
ll+0.002
ric+0.002
Neg logit contributions
 moments-0.002
 inspection-0.002
ment-0.002
ed-0.001
abouts-0.001
Token smiled
Token ID13541
Feature activation-3.38e-01

Pos logit contributions
 moments+0.076
 inspection+0.071
ment+0.070
eways+0.065
abouts+0.065
Neg logit contributions
 Claus-0.081
 daddy-0.077
 boo-0.074
ingu-0.073
washer-0.072
Token garden
Token ID11376
Feature activation-6.40e-01

Pos logit contributions
 Claus+0.027
 daddy+0.026
ingu+0.025
ric+0.024
ll+0.024
Neg logit contributions
 moments-0.033
 inspection-0.029
ment-0.029
abouts-0.028
ed-0.027
Token.
Token ID13
Feature activation-8.31e-02

Pos logit contributions
 Claus+0.036
 daddy+0.035
ingu+0.034
 boo+0.033
ric+0.032
Neg logit contributions
 moments-0.029
 inspection-0.025
ment-0.025
ed-0.024
abouts-0.023
Token Ben
Token ID3932
Feature activation-7.64e-01

Pos logit contributions
 daddy+0.004
ingu+0.004
 Claus+0.003
acey+0.003
 twin+0.003
Neg logit contributions
 moments-0.005
ment-0.004
 inspection-0.004
edly-0.004
ed-0.004
Token was
Token ID373
Feature activation+4.52e-01

Pos logit contributions
 Claus+0.037
 daddy+0.035
ingu+0.033
washer+0.033
ll+0.032
Neg logit contributions
 moments-0.041
ment-0.038
 inspection-0.037
abouts-0.035
edly-0.034
Token the
Token ID262
Feature activation-6.49e-01

Pos logit contributions
 moments+0.027
 inspection+0.025
ment+0.025
abouts+0.024
edly+0.023
Neg logit contributions
 Claus-0.019
 daddy-0.019
ingu-0.017
 boo-0.017
washer-0.016
Token seeker
Token ID45993
Feature activation+8.29e+00

Pos logit contributions
 Claus+0.030
ric+0.029
ingu+0.028
 daddy+0.028
ppa+0.028
Neg logit contributions
 moments-0.034
 Alicia-0.030
 Meg-0.028
 inspection-0.028
 insects-0.028
Token and
Token ID290
Feature activation+4.68e-01

Pos logit contributions
 moments+0.292
 inspection+0.250
ment+0.242
abouts+0.223
ed+0.216
Neg logit contributions
 Claus-0.538
 daddy-0.534
ingu-0.510
washer-0.497
 boo-0.493
Token Lily
Token ID20037
Feature activation+8.06e-01

Pos logit contributions
 moments+0.023
 inspection+0.021
ment+0.020
abouts+0.019
ed+0.019
Neg logit contributions
 daddy-0.024
 Claus-0.024
ingu-0.023
washer-0.022
 boo-0.022
Token was
Token ID373
Feature activation+4.29e-01

Pos logit contributions
 moments+0.041
ment+0.037
 inspection+0.037
abouts+0.034
edly+0.033
Neg logit contributions
 Claus-0.041
 daddy-0.040
washer-0.038
ingu-0.037
ll-0.037
Token the
Token ID262
Feature activation-6.54e-01

Pos logit contributions
 moments+0.022
 inspection+0.019
ment+0.019
ed+0.018
abouts+0.018
Neg logit contributions
 Claus-0.022
 daddy-0.021
ingu-0.020
ric-0.020
washer-0.020
Token h
Token ID289
Feature activation+2.18e+00

Pos logit contributions
 daddy+0.028
 Claus+0.028
ingu+0.025
 boo+0.025
washer+0.025
Neg logit contributions
 moments-0.038
ment-0.036
 inspection-0.036
ed-0.033
abouts-0.033
Token park
Token ID3952
Feature activation-7.84e-01

Pos logit contributions
 Claus+0.029
 daddy+0.027
ingu+0.027
ll+0.026
ric+0.026
Neg logit contributions
 moments-0.034
 inspection-0.029
ment-0.029
abouts-0.028
ed-0.028
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
 Claus+0.036
 daddy+0.036
ingu+0.032
washer+0.032
 cube+0.031
Neg logit contributions
 moments-0.043
 inspection-0.039
ment-0.037
abouts-0.036
ed-0.035
Token Lily
Token ID20037
Feature activation+8.79e-01

Pos logit contributions
 Claus+0.006
 daddy+0.006
ingu+0.006
 boo+0.005
ric+0.005
Neg logit contributions
 moments-0.005
ment-0.005
 inspection-0.005
ed-0.005
edly-0.004
Token is
Token ID318
Feature activation+5.28e-01

Pos logit contributions
 moments+0.052
ment+0.049
 inspection+0.048
edly+0.045
abouts+0.045
Neg logit contributions
 Claus-0.037
 daddy-0.035
ingu-0.033
washer-0.032
ll-0.032
Token the
Token ID262
Feature activation-6.33e-01

Pos logit contributions
 moments+0.032
ment+0.031
 inspection+0.030
abouts+0.029
edly+0.028
Neg logit contributions
 daddy-0.022
 Claus-0.021
 boo-0.019
 living-0.018
ingu-0.018
Token seeker
Token ID45993
Feature activation+8.28e+00

Pos logit contributions
 Claus+0.029
ingu+0.027
 daddy+0.027
ric+0.027
ppa+0.026
Neg logit contributions
 moments-0.034
 Alicia-0.030
 inspection-0.029
 Meg-0.029
abouts-0.028
Token and
Token ID290
Feature activation+4.58e-01

Pos logit contributions
 moments+0.307
 inspection+0.265
ment+0.257
abouts+0.238
ed+0.229
Neg logit contributions
 Claus-0.519
 daddy-0.518
ingu-0.489
washer-0.480
 boo-0.474
Token Tom
Token ID4186
Feature activation-4.01e-01

Pos logit contributions
 moments+0.022
 inspection+0.020
ment+0.019
abouts+0.018
ed+0.018
Neg logit contributions
 Claus-0.024
 daddy-0.024
ingu-0.023
washer-0.022
 boo-0.022
Token is
Token ID318
Feature activation+5.17e-01

Pos logit contributions
 Claus+0.019
 daddy+0.018
ingu+0.018
ric+0.017
washer+0.017
Neg logit contributions
 moments-0.021
 inspection-0.019
ment-0.019
ed-0.018
abouts-0.018
Token the
Token ID262
Feature activation-6.39e-01

Pos logit contributions
 moments+0.027
 inspection+0.025
ment+0.025
abouts+0.023
edly+0.023
Neg logit contributions
 daddy-0.025
 Claus-0.025
 boo-0.022
washer-0.022
ingu-0.022
Token h
Token ID289
Feature activation+2.20e+00

Pos logit contributions
 daddy+0.027
 Claus+0.027
ingu+0.024
 boo+0.024
washer+0.024
Neg logit contributions
 moments-0.037
ment-0.035
 inspection-0.035
ed-0.032
abouts-0.032
Token,
Token ID11
Feature activation+1.38e-01

Pos logit contributions
 moments+0.102
 inspection+0.087
ment+0.084
ed+0.076
abouts+0.074
Neg logit contributions
 Claus-0.165
ingu-0.158
 daddy-0.156
ric-0.152
washer-0.151
Token but
Token ID475
Feature activation+2.04e+00

Pos logit contributions
 moments+0.008
 inspection+0.007
ment+0.007
 Meg+0.007
 Alicia+0.007
Neg logit contributions
 Claus-0.006
ric-0.006
ingu-0.006
oun-0.005
washer-0.005
Token only
Token ID691
Feature activation-1.08e+00

Pos logit contributions
 moments+0.110
 inspection+0.095
 after+0.089
ment+0.086
 behold+0.082
Neg logit contributions
ingu-0.105
 Claus-0.104
oun-0.096
washer-0.096
acey-0.092
Token with
Token ID351
Feature activation-1.85e-01

Pos logit contributions
ingu+0.070
oun+0.069
 Claus+0.068
ppa+0.065
ric+0.064
Neg logit contributions
 moments-0.042
 after-0.035
 inspection-0.033
ment-0.032
ed-0.029
Token our
Token ID674
Feature activation-2.92e+00

Pos logit contributions
 Claus+0.011
ingu+0.010
oun+0.010
ll+0.010
washer+0.010
Neg logit contributions
 moments-0.009
ment-0.007
 inspection-0.007
 insects-0.007
 hours-0.006
Token supervision
Token ID20865
Feature activation-1.23e+01

Pos logit contributions
 Claus+0.175
ingu+0.167
oun+0.158
ll+0.154
ppa+0.152
Neg logit contributions
 moments-0.152
 inspection-0.112
ment-0.112
 insects-0.104
oos-0.103
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
 Claus+0.807
ingu+0.780
ric+0.761
 daddy+0.757
 boo+0.751
Neg logit contributions
 moments-0.445
ed-0.363
ment-0.347
 inspection-0.331
edly-0.318
Token And
Token ID843
Feature activation-1.79e+00

Pos logit contributions
 Claus+0.011
ingu+0.011
 daddy+0.011
ll+0.011
washer+0.011
Neg logit contributions
 moments-0.007
ment-0.006
 Alicia-0.005
edly-0.005
 inspection-0.005
Token maybe
Token ID3863
Feature activation+2.82e+00

Pos logit contributions
ingu+0.091
 Claus+0.087
oun+0.084
washer+0.081
 cube+0.078
Neg logit contributions
 moments-0.098
ment-0.083
 after-0.080
 inspection-0.080
edly-0.073
Token you
Token ID345
Feature activation-9.62e-01

Pos logit contributions
 moments+0.156
ment+0.138
 inspection+0.135
 after+0.127
ed+0.119
Neg logit contributions
ingu-0.133
 Claus-0.133
oun-0.127
washer-0.125
ric-0.122
Token can
Token ID460
Feature activation-1.33e+00

Pos logit contributions
 daddy+0.051
ingu+0.051
ich+0.050
oun+0.050
pron+0.049
Neg logit contributions
 after-0.036
 moments-0.034
 inspection-0.032
ed-0.032
 reached-0.031
Token to
Token ID284
Feature activation+5.89e-01

Pos logit contributions
 Claus+0.052
oun+0.050
ingu+0.049
washer+0.047
 daddy+0.045
Neg logit contributions
 moments-0.025
 inspection-0.019
ment-0.017
 after-0.017
ed-0.017
Token use
Token ID779
Feature activation+2.39e-01

Pos logit contributions
 moments+0.025
 behold+0.022
 after+0.022
 inspection+0.021
 Meg+0.021
Neg logit contributions
washer-0.033
 Claus-0.031
ingu-0.031
ll-0.030
 daddy-0.030
Token it
Token ID340
Feature activation+1.21e+00

Pos logit contributions
 moments+0.008
 inspection+0.006
ment+0.006
 after+0.006
ed+0.005
Neg logit contributions
 Claus-0.018
ingu-0.016
ll-0.016
oun-0.016
washer-0.016
Token with
Token ID351
Feature activation-1.94e-01

Pos logit contributions
 moments+0.049
 inspection+0.043
ment+0.042
ed+0.042
edly+0.039
Neg logit contributions
 Claus-0.072
 daddy-0.069
ingu-0.068
ric-0.068
 boo-0.066
Token adult
Token ID4044
Feature activation-3.46e+00

Pos logit contributions
 Claus+0.011
washer+0.010
ingu+0.010
ll+0.010
oun+0.010
Neg logit contributions
 moments-0.009
ment-0.008
 inspection-0.008
ed-0.007
 after-0.007
Token supervision
Token ID20865
Feature activation-1.19e+01

Pos logit contributions
ingu+0.201
 Claus+0.198
oun+0.192
 daddy+0.192
ll+0.185
Neg logit contributions
 moments-0.147
ment-0.129
ed-0.126
 after-0.117
 inspection-0.117
Token,"
Token ID553
Feature activation-1.16e+00

Pos logit contributions
 Claus+0.793
ric+0.788
 daddy+0.775
ingu+0.773
 boo+0.756
Neg logit contributions
 moments-0.388
ed-0.337
ment-0.303
edly-0.298
 inspection-0.286
Token Mr
Token ID1770
Feature activation-3.22e+00

Pos logit contributions
 Claus+0.067
ingu+0.064
washer+0.064
ric+0.063
ll+0.063
Neg logit contributions
 moments-0.048
 inspection-0.043
ment-0.042
 Alicia-0.039
 Meg-0.038
Token.
Token ID13
Feature activation-2.64e-01

Pos logit contributions
 Claus+0.168
 daddy+0.161
ingu+0.153
ric+0.150
ll+0.149
Neg logit contributions
 moments-0.162
 inspection-0.140
ment-0.136
ed-0.131
abouts-0.131
Token Lee
Token ID5741
Feature activation+3.75e-01

Pos logit contributions
 Claus+0.012
 daddy+0.011
ingu+0.010
ric+0.010
 boo+0.010
Neg logit contributions
 moments-0.016
 inspection-0.014
ment-0.014
ed-0.013
abouts-0.013
Token said
Token ID531
Feature activation-8.58e-01

Pos logit contributions
 moments+0.020
 inspection+0.018
ment+0.017
ed+0.017
abouts+0.016
Neg logit contributions
 Claus-0.018
 daddy-0.018
ingu-0.017
ric-0.016
 boo-0.016
Token cried
Token ID16896
Feature activation+4.82e-03

Pos logit contributions
 moments+0.046
 inspection+0.041
ment+0.040
abouts+0.038
ed+0.037
Neg logit contributions
 Claus-0.041
 daddy-0.040
ingu-0.038
 boo-0.037
washer-0.037
Token.
Token ID13
Feature activation-9.34e-05

Pos logit contributions
 moments+0.000
 inspection+0.000
abouts+0.000
ment+0.000
 behold+0.000
Neg logit contributions
 daddy-0.000
 Claus-0.000
 boo-0.000
ingu-0.000
washer-0.000
Token "
Token ID366
Feature activation+4.07e-01

Pos logit contributions
 daddy+0.000
 Claus+0.000
 boo+0.000
 tank+0.000
 cube+0.000
Neg logit contributions
 moments-0.000
ment-0.000
 inspection-0.000
abouts-0.000
 passages-0.000
TokenThe
Token ID464
Feature activation-7.76e-01

Pos logit contributions
 moments+0.020
 inspection+0.018
ment+0.017
abouts+0.016
 passages+0.016
Neg logit contributions
 Claus-0.021
 daddy-0.021
 boo-0.020
ingu-0.019
ric-0.019
Token ost
Token ID23619
Feature activation+1.09e+00

Pos logit contributions
 Claus+0.040
ingu+0.040
ll+0.038
ppa+0.037
oun+0.037
Neg logit contributions
 moments-0.040
 insects-0.032
ment-0.031
ger-0.031
abouts-0.031
Tokenric
Token ID1173
Feature activation-1.10e+01

Pos logit contributions
oos+0.072
ment+0.072
ed+0.071
 inspection+0.070
 moments+0.070
Neg logit contributions
 daddy-0.036
ingu-0.030
 Claus-0.030
oun-0.028
 Rudolph-0.028
Tokenhes
Token ID956
Feature activation-1.44e+00

Pos logit contributions
 Claus+0.415
 daddy+0.407
ingu+0.375
 boo+0.358
ric+0.344
Neg logit contributions
 moments-0.687
ment-0.630
 inspection-0.628
ed-0.616
abouts-0.596
Token are
Token ID389
Feature activation+5.59e-01

Pos logit contributions
 Claus+0.073
 daddy+0.070
ingu+0.068
ppa+0.064
ll+0.063
Neg logit contributions
 moments-0.073
 inspection-0.065
ment-0.065
ed-0.064
abouts-0.060
Token mean
Token ID1612
Feature activation+1.60e+00

Pos logit contributions
 moments+0.027
 after+0.024
 insects+0.023
 inspection+0.023
ment+0.022
Neg logit contributions
 Claus-0.030
ingu-0.029
washer-0.028
oun-0.028
 daddy-0.027
Token!
Token ID0
Feature activation+4.01e-01

Pos logit contributions
 moments+0.083
 inspection+0.075
ment+0.073
abouts+0.070
edly+0.068
Neg logit contributions
 Claus-0.077
 daddy-0.075
ingu-0.070
washer-0.069
 boo-0.069
Token They
Token ID1119
Feature activation+9.16e-01

Pos logit contributions
 moments+0.012
ment+0.011
ed+0.010
 inspection+0.009
abouts+0.008
Neg logit contributions
 Claus-0.028
ingu-0.027
ll-0.027
 daddy-0.027
ppa-0.026
Token with
Token ID351
Feature activation-1.88e-01

Pos logit contributions
 moments+0.004
abouts+0.004
 inspection+0.004
ment+0.003
ed+0.003
Neg logit contributions
 daddy-0.005
 Claus-0.005
washer-0.005
 boo-0.004
ll-0.004
Token a
Token ID257
Feature activation-1.82e-01

Pos logit contributions
 Claus+0.013
ll+0.013
ingu+0.012
ric+0.012
oun+0.012
Neg logit contributions
 moments-0.007
ment-0.005
 inspection-0.005
ed-0.005
abouts-0.005
Token man
Token ID582
Feature activation+1.93e+00

Pos logit contributions
ll+0.009
ingu+0.009
ric+0.009
 Claus+0.009
ppa+0.009
Neg logit contributions
 moments-0.009
 inspection-0.008
 widened-0.007
Exc-0.007
ment-0.007
Token on
Token ID319
Feature activation+4.86e-01

Pos logit contributions
 moments+0.081
ment+0.074
ed+0.073
 inspection+0.070
 after+0.068
Neg logit contributions
ingu-0.112
ric-0.104
 daddy-0.103
oun-0.102
 Claus-0.102
Token a
Token ID257
Feature activation-1.66e-01

Pos logit contributions
 moments+0.019
 inspection+0.016
ment+0.016
abouts+0.014
ed+0.014
Neg logit contributions
 Claus-0.031
ll-0.030
ingu-0.029
washer-0.029
 daddy-0.029
Token stret
Token ID5759
Feature activation-1.09e+01

Pos logit contributions
ll+0.008
ingu+0.008
ric+0.008
 Claus+0.008
ppa+0.007
Neg logit contributions
 moments-0.009
 inspection-0.008
Exc-0.007
abouts-0.007
 widened-0.007
Tokencher
Token ID2044
Feature activation-3.54e+00

Pos logit contributions
 daddy+0.303
 Claus+0.302
ingu+0.289
ric+0.271
 boo+0.265
Neg logit contributions
 moments-0.783
 inspection-0.718
ed-0.717
ment-0.715
abouts-0.681
Token.
Token ID13
Feature activation-2.03e-01

Pos logit contributions
ingu+0.218
 Claus+0.216
 daddy+0.215
ric+0.210
ll+0.207
Neg logit contributions
 moments-0.132
ed-0.117
ment-0.111
 inspection-0.107
edly-0.103
Token The
Token ID383
Feature activation-9.47e-01

Pos logit contributions
 Claus+0.013
ric+0.013
uch+0.013
ll+0.013
ingu+0.013
Neg logit contributions
 moments-0.007
 inspection-0.006
ed-0.005
ment-0.005
Exc-0.005
Token man
Token ID582
Feature activation+1.95e+00

Pos logit contributions
ingu+0.045
 Claus+0.044
ric+0.044
ll+0.043
 daddy+0.040
Neg logit contributions
 moments-0.052
ment-0.043
ed-0.042
 inspection-0.042
abouts-0.041
Token's
Token ID338
Feature activation-2.31e+00

Pos logit contributions
 moments+0.079
ed+0.075
 inspection+0.068
Exc+0.065
ment+0.065
Neg logit contributions
ric-0.113
 fault-0.111
ingu-0.108
 daddy-0.103
oun-0.103
Token They
Token ID1119
Feature activation+7.65e-01

Pos logit contributions
 daddy+0.065
 Claus+0.064
ingu+0.059
washer+0.056
 boo+0.056
Neg logit contributions
 moments-0.082
 inspection-0.072
ment-0.072
ed-0.069
abouts-0.069
Token put
Token ID1234
Feature activation-1.65e+00

Pos logit contributions
 moments+0.037
 inspection+0.033
ment+0.032
ed+0.032
edly+0.030
Neg logit contributions
 Claus-0.038
ric-0.037
 daddy-0.037
ingu-0.036
ll-0.035
Token Lily
Token ID20037
Feature activation+8.08e-01

Pos logit contributions
 Claus+0.103
 daddy+0.102
ingu+0.098
 boo+0.095
ric+0.094
Neg logit contributions
 moments-0.063
 inspection-0.055
ment-0.053
abouts-0.049
ed-0.049
Token on
Token ID319
Feature activation+5.18e-01

Pos logit contributions
 moments+0.035
ed+0.034
ment+0.031
 after+0.029
 inspection+0.028
Neg logit contributions
ingu-0.045
 Claus-0.043
ric-0.043
 daddy-0.042
ll-0.042
Token a
Token ID257
Feature activation-9.76e-02

Pos logit contributions
 moments+0.023
 inspection+0.020
ment+0.020
ed+0.019
abouts+0.019
Neg logit contributions
 daddy-0.029
 Claus-0.029
ingu-0.027
 boo-0.027
ric-0.026
Token stret
Token ID5759
Feature activation-1.09e+01

Pos logit contributions
ll+0.004
ric+0.004
ingu+0.004
 Claus+0.004
uch+0.004
Neg logit contributions
 moments-0.005
 inspection-0.005
Exc-0.005
abouts-0.004
 minutes-0.004
Tokencher
Token ID2044
Feature activation-3.55e+00

Pos logit contributions
 Claus+0.266
 daddy+0.245
ingu+0.214
washer+0.207
ll+0.199
Neg logit contributions
 moments-0.839
 inspection-0.785
ment-0.766
abouts-0.752
ed-0.734
Token and
Token ID290
Feature activation+4.48e-01

Pos logit contributions
 Claus+0.228
 daddy+0.223
washer+0.209
ingu+0.208
 boo+0.208
Neg logit contributions
 moments-0.132
 inspection-0.117
ment-0.110
abouts-0.105
 Alicia-0.098
Token carried
Token ID5281
Feature activation+3.84e-01

Pos logit contributions
 moments+0.023
 inspection+0.021
ment+0.020
ed+0.020
abouts+0.019
Neg logit contributions
 Claus-0.022
 daddy-0.021
ingu-0.021
ric-0.020
ll-0.020
Token her
Token ID607
Feature activation+1.66e+00

Pos logit contributions
 moments+0.014
 inspection+0.012
ment+0.011
abouts+0.011
edly+0.010
Neg logit contributions
 daddy-0.025
 Claus-0.024
ingu-0.023
 boo-0.022
washer-0.022
Token to
Token ID284
Feature activation+6.90e-01

Pos logit contributions
 moments+0.052
 after+0.046
 towards+0.043
ed+0.039
ment+0.038
Neg logit contributions
ingu-0.123
str-0.112
oun-0.112
 Claus-0.111
ric-0.110
Token They
Token ID1119
Feature activation+7.98e-01

Pos logit contributions
 Claus+0.009
 daddy+0.009
ingu+0.008
washer+0.008
 boo+0.008
Neg logit contributions
 moments-0.007
 inspection-0.006
ment-0.006
abouts-0.006
ed-0.006
Token lifted
Token ID13663
Feature activation-1.33e+00

Pos logit contributions
 moments+0.035
ed+0.030
 inspection+0.030
ment+0.030
 widened+0.029
Neg logit contributions
ric-0.042
 Claus-0.042
oun-0.041
ingu-0.041
 daddy-0.040
Token him
Token ID683
Feature activation-1.61e+00

Pos logit contributions
 daddy+0.065
 Claus+0.062
ingu+0.060
 boo+0.058
 tank+0.055
Neg logit contributions
 moments-0.069
 inspection-0.062
ment-0.062
edly-0.058
abouts-0.058
Token onto
Token ID4291
Feature activation+5.09e-01

Pos logit contributions
 Claus+0.093
 daddy+0.092
ingu+0.091
ric+0.086
washer+0.086
Neg logit contributions
 moments-0.067
 inspection-0.059
ment-0.058
ed-0.057
abouts-0.052
Token a
Token ID257
Feature activation-3.50e-02

Pos logit contributions
 moments+0.023
 inspection+0.020
ment+0.019
ed+0.018
abouts+0.018
Neg logit contributions
 Claus-0.029
 daddy-0.028
ingu-0.027
ric-0.026
washer-0.026
Token stret
Token ID5759
Feature activation-1.09e+01

Pos logit contributions
ll+0.002
ingu+0.002
 Claus+0.002
ric+0.002
 fault+0.002
Neg logit contributions
 moments-0.002
 inspection-0.002
abouts-0.001
Exc-0.001
 after-0.001
Tokencher
Token ID2044
Feature activation-3.53e+00

Pos logit contributions
 Claus+0.277
 daddy+0.264
ingu+0.240
ric+0.221
washer+0.220
Neg logit contributions
 moments-0.820
 inspection-0.760
ment-0.751
ed-0.728
abouts-0.725
Token and
Token ID290
Feature activation+5.20e-01

Pos logit contributions
 Claus+0.219
 daddy+0.214
ingu+0.206
washer+0.200
ric+0.200
Neg logit contributions
 moments-0.138
 inspection-0.119
ment-0.115
ed-0.107
abouts-0.107
Token put
Token ID1234
Feature activation-1.58e+00

Pos logit contributions
 moments+0.026
ment+0.023
ed+0.022
 inspection+0.022
edly+0.021
Neg logit contributions
 Claus-0.026
ric-0.026
ingu-0.026
ll-0.025
 daddy-0.025
Token him
Token ID683
Feature activation-1.58e+00

Pos logit contributions
 Claus+0.104
ll+0.101
ric+0.099
 daddy+0.098
ingu+0.098
Neg logit contributions
 moments-0.057
ed-0.050
ment-0.047
 inspection-0.044
abouts-0.040
Token in
Token ID287
Feature activation-2.08e+00

Pos logit contributions
ingu+0.096
 Claus+0.093
 daddy+0.093
ric+0.091
oun+0.089
Neg logit contributions
 moments-0.062
ed-0.058
ment-0.056
edly-0.049
 after-0.048
Token When
Token ID1649
Feature activation-6.05e-01

Pos logit contributions
 moments+0.021
 inspection+0.018
ment+0.017
ed+0.016
 Alicia+0.016
Neg logit contributions
 Claus-0.042
 daddy-0.040
ingu-0.040
ll-0.039
ric-0.039
Token Daisy
Token ID40355
Feature activation-1.48e+00

Pos logit contributions
 Claus+0.037
ingu+0.036
ric+0.035
 daddy+0.035
ll+0.035
Neg logit contributions
 moments-0.024
 inspection-0.021
ment-0.020
ed-0.018
 Alicia-0.018
Token put
Token ID1234
Feature activation-1.45e+00

Pos logit contributions
 Claus+0.087
 daddy+0.086
ingu+0.083
ric+0.083
washer+0.080
Neg logit contributions
 moments-0.060
 inspection-0.053
ed-0.051
ment-0.050
abouts-0.047
Token the
Token ID262
Feature activation+5.92e-02

Pos logit contributions
 daddy+0.078
 Claus+0.077
ingu+0.073
 boo+0.071
ric+0.070
Neg logit contributions
 moments-0.066
 inspection-0.059
ment-0.058
abouts-0.055
edly-0.054
Token magn
Token ID7842
Feature activation+1.94e+00

Pos logit contributions
 moments+0.003
ment+0.003
abouts+0.003
 insects+0.003
ed+0.003
Neg logit contributions
 Claus-0.003
ll-0.003
ingu-0.003
oun-0.003
ric-0.003
Tokenifying
Token ID4035
Feature activation-1.08e+01

Pos logit contributions
 moments+0.128
 inspection+0.117
ment+0.115
abouts+0.111
ed+0.109
Neg logit contributions
 Claus-0.068
 daddy-0.065
ingu-0.061
washer-0.058
ric-0.057
Token glass
Token ID5405
Feature activation-2.86e+00

Pos logit contributions
 Claus+0.401
 daddy+0.389
ingu+0.365
ric+0.347
washer+0.345
Neg logit contributions
 moments-0.685
 inspection-0.626
ment-0.615
ed-0.593
abouts-0.591
Token down
Token ID866
Feature activation+1.55e+00

Pos logit contributions
 Claus+0.163
 daddy+0.159
ingu+0.153
ric+0.148
 boo+0.147
Neg logit contributions
 moments-0.126
 inspection-0.110
ment-0.108
ed-0.102
abouts-0.101
Token,
Token ID11
Feature activation+4.85e-01

Pos logit contributions
 moments+0.070
 inspection+0.062
abouts+0.061
ment+0.061
edly+0.058
Neg logit contributions
 daddy-0.082
 Claus-0.076
washer-0.072
 cube-0.072
ingu-0.071
Token the
Token ID262
Feature activation-2.87e-01

Pos logit contributions
 moments+0.020
abouts+0.018
ment+0.018
edly+0.017
 inspection+0.017
Neg logit contributions
 daddy-0.029
 Claus-0.026
ingu-0.024
washer-0.024
 boo-0.024
Token cater
Token ID20825
Feature activation+1.18e+00

Pos logit contributions
 Claus+0.015
ingu+0.014
ll+0.014
oun+0.014
ric+0.014
Neg logit contributions
 moments-0.015
ment-0.012
abouts-0.012
ed-0.012
 inspection-0.012
Token the
Token ID262
Feature activation-6.42e-01

Pos logit contributions
 Claus+0.099
 daddy+0.095
ingu+0.095
ll+0.093
ric+0.092
Neg logit contributions
 moments-0.064
ed-0.054
ment-0.054
 inspection-0.053
abouts-0.048
Token elderly
Token ID13830
Feature activation-4.25e-01

Pos logit contributions
ric+0.033
ll+0.033
ingu+0.032
oun+0.029
 Claus+0.029
Neg logit contributions
 moments-0.033
ment-0.027
 after-0.026
ed-0.026
 paths-0.026
Token man
Token ID582
Feature activation+1.90e+00

Pos logit contributions
ingu+0.024
 Claus+0.024
ric+0.024
 daddy+0.023
ll+0.023
Neg logit contributions
 moments-0.019
ment-0.016
 inspection-0.016
ed-0.015
abouts-0.014
Token on
Token ID319
Feature activation+5.28e-01

Pos logit contributions
 moments+0.074
ed+0.071
ment+0.070
 after+0.061
 inspection+0.059
Neg logit contributions
ingu-0.114
 daddy-0.111
 Claus-0.109
ll-0.107
ric-0.107
Token a
Token ID257
Feature activation-6.84e-02

Pos logit contributions
 moments+0.023
 inspection+0.020
ment+0.019
ed+0.018
abouts+0.018
Neg logit contributions
 Claus-0.030
 daddy-0.030
ingu-0.029
ric-0.028
 boo-0.028
Token stret
Token ID5759
Feature activation-1.08e+01

Pos logit contributions
ll+0.003
ingu+0.003
ric+0.003
 Claus+0.003
uch+0.003
Neg logit contributions
 moments-0.004
 inspection-0.003
Exc-0.003
ment-0.003
 minutes-0.003
Tokencher
Token ID2044
Feature activation-3.44e+00

Pos logit contributions
 daddy+0.293
 Claus+0.284
ingu+0.278
ric+0.260
 boo+0.258
Neg logit contributions
 moments-0.779
ment-0.719
ed-0.718
 inspection-0.711
edly-0.679
Token.
Token ID13
Feature activation-1.36e-01

Pos logit contributions
 Claus+0.196
 daddy+0.193
ingu+0.188
ric+0.182
ll+0.180
Neg logit contributions
 moments-0.149
ment-0.128
 inspection-0.127
ed-0.124
edly-0.117
Token She
Token ID1375
Feature activation+1.22e+00

Pos logit contributions
 daddy+0.009
 Claus+0.009
 boo+0.008
ingu+0.008
ric+0.008
Neg logit contributions
 moments-0.005
 inspection-0.004
ment-0.004
abouts-0.004
ed-0.004
Token thanked
Token ID26280
Feature activation-3.54e+00

Pos logit contributions
 moments+0.058
ed+0.051
ment+0.050
 inspection+0.050
Exc+0.047
Neg logit contributions
ric-0.062
ingu-0.061
 Claus-0.059
 daddy-0.059
oun-0.058
Token Tim
Token ID5045
Feature activation-1.72e+00

Pos logit contributions
 Claus+0.202
 daddy+0.192
ingu+0.189
washer+0.185
ric+0.183
Neg logit contributions
 moments-0.156
 inspection-0.139
ment-0.133
abouts-0.125
ed-0.124
Token flashlight
Token ID38371
Feature activation-1.59e+00

Pos logit contributions
 moments+0.021
 inspection+0.017
abouts+0.017
 Alicia+0.016
ment+0.016
Neg logit contributions
ll-0.019
 Claus-0.019
ingu-0.018
ric-0.018
ppa-0.018
Token,
Token ID11
Feature activation+4.52e-01

Pos logit contributions
ingu+0.098
 Claus+0.096
 daddy+0.095
ric+0.092
ppa+0.091
Neg logit contributions
 moments-0.061
 inspection-0.054
ed-0.052
ment-0.051
edly-0.047
Token and
Token ID290
Feature activation+6.82e-01

Pos logit contributions
 moments+0.018
 inspection+0.016
ment+0.016
abouts+0.015
ed+0.015
Neg logit contributions
 daddy-0.027
 Claus-0.027
 boo-0.024
ingu-0.024
washer-0.024
Token a
Token ID257
Feature activation+2.75e-01

Pos logit contributions
 moments+0.030
 inspection+0.027
ment+0.026
abouts+0.025
ed+0.024
Neg logit contributions
 Claus-0.038
 daddy-0.038
ingu-0.036
washer-0.035
 boo-0.035
Token magn
Token ID7842
Feature activation+2.16e+00

Pos logit contributions
 moments+0.015
 inspection+0.012
abouts+0.012
ment+0.012
 Alicia+0.011
Neg logit contributions
ll-0.013
 Claus-0.013
ingu-0.013
ppa-0.012
ric-0.012
Tokenifying
Token ID4035
Feature activation-1.07e+01

Pos logit contributions
 moments+0.127
ed+0.122
 inspection+0.122
ment+0.117
abouts+0.111
Neg logit contributions
 daddy-0.084
 Claus-0.084
 boo-0.079
ingu-0.078
ric-0.075
Token glass
Token ID5405
Feature activation-3.06e+00

Pos logit contributions
 Claus+0.407
 daddy+0.390
ingu+0.369
ll+0.349
ric+0.348
Neg logit contributions
 moments-0.673
 inspection-0.614
ment-0.607
ed-0.584
abouts-0.580
Token.
Token ID13
Feature activation+3.14e-01

Pos logit contributions
 Claus+0.172
 daddy+0.166
ingu+0.163
ric+0.159
 boo+0.157
Neg logit contributions
 moments-0.139
 inspection-0.121
ment-0.121
ed-0.116
abouts-0.111
Token
Token ID198
Feature activation+2.55e-01

Pos logit contributions
 moments+0.011
 inspection+0.009
ment+0.009
ed+0.008
abouts+0.008
Neg logit contributions
 Claus-0.021
 daddy-0.020
ingu-0.020
ric-0.019
washer-0.019
Token
Token ID198
Feature activation+1.77e-01

Pos logit contributions
 moments+0.012
 inspection+0.011
ment+0.010
abouts+0.010
ed+0.010
Neg logit contributions
 Claus-0.014
 daddy-0.013
ingu-0.013
 boo-0.012
ric-0.012
TokenAs
Token ID1722
Feature activation+3.50e-01

Pos logit contributions
 moments+0.007
 inspection+0.006
ment+0.006
ed+0.006
abouts+0.006
Neg logit contributions
 daddy-0.010
 Claus-0.010
ingu-0.010
washer-0.010
ll-0.009
Token but
Token ID475
Feature activation+1.96e+00

Pos logit contributions
 moments+0.001
 inspection+0.001
ment+0.001
ed+0.001
 Alicia+0.001
Neg logit contributions
 Claus-0.001
 daddy-0.001
ric-0.001
ingu-0.001
washer-0.001
Token be
Token ID307
Feature activation+2.28e-01

Pos logit contributions
 moments+0.100
 inspection+0.095
ment+0.084
 after+0.084
 insects+0.081
Neg logit contributions
ingu-0.097
 Claus-0.096
washer-0.095
acey-0.092
oun-0.092
Token careful
Token ID8161
Feature activation-1.28e+00

Pos logit contributions
 moments+0.013
ment+0.011
 inspection+0.011
ed+0.011
 Alicia+0.011
Neg logit contributions
 Claus-0.010
 daddy-0.010
ingu-0.010
oun-0.010
washer-0.009
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
ingu+0.085
 Claus+0.083
 boo+0.079
 daddy+0.079
acey+0.078
Neg logit contributions
 moments-0.044
ment-0.039
ed-0.036
 inspection-0.034
eways-0.034
Token Ost
Token ID38919
Feature activation+1.30e+00

Pos logit contributions
 Claus+0.008
 daddy+0.008
washer+0.008
ingu+0.008
ll+0.007
Neg logit contributions
 moments-0.005
ment-0.005
 inspection-0.004
 Alicia-0.004
edly-0.004
Tokenric
Token ID1173
Feature activation-1.07e+01

Pos logit contributions
 moments+0.100
ment+0.095
iece+0.093
 inspection+0.092
ed+0.091
Neg logit contributions
 daddy-0.027
 Claus-0.023
 boo-0.022
ingu-0.022
washer-0.021
Tokenhes
Token ID956
Feature activation-1.40e+00

Pos logit contributions
 Claus+0.421
 daddy+0.420
ingu+0.385
 boo+0.377
oun+0.356
Neg logit contributions
 moments-0.645
ment-0.596
 inspection-0.593
ed-0.581
abouts-0.558
Token can
Token ID460
Feature activation-1.39e+00

Pos logit contributions
 Claus+0.076
 daddy+0.074
ingu+0.072
ll+0.067
ppa+0.067
Neg logit contributions
 moments-0.065
ment-0.060
 inspection-0.057
ed-0.057
 after-0.051
Token be
Token ID307
Feature activation+2.99e-01

Pos logit contributions
washer+0.071
 daddy+0.071
ingu+0.071
 Claus+0.068
acey+0.063
Neg logit contributions
 inspection-0.056
 moments-0.056
 behold-0.053
 after-0.053
ment-0.052
Token gr
Token ID1036
Feature activation+9.36e-01

Pos logit contributions
 moments+0.014
ed+0.012
ment+0.012
 inspection+0.012
 after+0.012
Neg logit contributions
ingu-0.016
 daddy-0.016
 Claus-0.015
washer-0.015
oun-0.015
Tokenumpy
Token ID32152
Feature activation+4.20e-01

Pos logit contributions
 moments+0.041
ment+0.038
ed+0.036
 inspection+0.035
abouts+0.035
Neg logit contributions
 daddy-0.053
 Claus-0.051
ingu-0.048
 boo-0.047
washer-0.046
Tokenie
Token ID494
Feature activation+1.15e+00

Pos logit contributions
ed+0.112
 inspection+0.107
ment+0.103
 moments+0.099
oos+0.097
Neg logit contributions
 Claus-0.145
 daddy-0.145
washer-0.141
ingu-0.141
 Love-0.140
Token.
Token ID13
Feature activation+1.10e-01

Pos logit contributions
 and+0.015
 moments+0.014
 after+0.014
 until+0.010
ger+0.010
Neg logit contributions
 fault-0.089
uch-0.088
 Claus-0.087
emic-0.086
 remote-0.085
Token Unlike
Token ID12101
Feature activation-2.28e+00

Pos logit contributions
 moments+0.005
 inspection+0.005
ment+0.005
ed+0.004
abouts+0.004
Neg logit contributions
 Claus-0.006
 daddy-0.006
ingu-0.005
washer-0.005
 boo-0.005
Token other
Token ID584
Feature activation+8.99e-01

Pos logit contributions
 Claus+0.131
 daddy+0.123
ingu+0.119
washer+0.119
 boo+0.116
Neg logit contributions
 moments-0.100
 inspection-0.094
ment-0.090
ed-0.083
abouts-0.078
Token ost
Token ID23619
Feature activation+1.32e+00

Pos logit contributions
 moments+0.050
ment+0.046
 inspection+0.046
edly+0.045
abouts+0.045
Neg logit contributions
 daddy-0.037
 Claus-0.036
ric-0.035
 je-0.034
 boo-0.034
Tokenric
Token ID1173
Feature activation-1.06e+01

Pos logit contributions
 inspection+0.091
oos+0.088
eways+0.087
 moments+0.086
ways+0.085
Neg logit contributions
 boo-0.036
 daddy-0.036
 Claus-0.033
washer-0.032
oun-0.030
Tokenhes
Token ID956
Feature activation-1.25e+00

Pos logit contributions
 daddy+0.451
 Claus+0.450
 boo+0.422
ingu+0.409
oun+0.394
Neg logit contributions
 moments-0.607
ed-0.571
ment-0.563
 inspection-0.557
eways-0.528
Token,
Token ID11
Feature activation+3.05e-01

Pos logit contributions
 Claus+0.075
 daddy+0.073
ingu+0.071
ppa+0.069
 boo+0.069
Neg logit contributions
 moments-0.050
ed-0.045
ment-0.045
 inspection-0.041
ger-0.039
Token his
Token ID465
Feature activation-3.76e-01

Pos logit contributions
 moments+0.013
 inspection+0.012
ment+0.011
ed+0.011
abouts+0.010
Neg logit contributions
 Claus-0.018
ingu-0.017
 daddy-0.016
ll-0.016
 boo-0.016
Token feathers
Token ID27400
Feature activation+1.36e+00

Pos logit contributions
ingu+0.019
 Claus+0.019
washer+0.019
acey+0.018
ppa+0.017
Neg logit contributions
 moments-0.020
ment-0.017
 inspection-0.016
ed-0.015
edly-0.015
Token gl
Token ID1278
Feature activation+1.17e+00

Pos logit contributions
ed+0.041
 moments+0.041
ment+0.039
 inspection+0.039
abouts+0.031
Neg logit contributions
 Claus-0.089
 daddy-0.089
ingu-0.087
acey-0.085
 boo-0.084
TokenThey
Token ID2990
Feature activation-7.65e-01

Pos logit contributions
 Claus+0.001
 daddy+0.001
ingu+0.001
ric+0.001
 boo+0.001
Neg logit contributions
 moments-0.001
 inspection-0.001
ment-0.001
abouts-0.000
ed-0.000
Token all
Token ID477
Feature activation-8.39e-01

Pos logit contributions
ric+0.041
 Claus+0.040
 fault+0.039
 daddy+0.039
oun+0.039
Neg logit contributions
 moments-0.033
ed-0.030
 inspection-0.028
ment-0.027
 widened-0.027
Token went
Token ID1816
Feature activation+7.82e-01

Pos logit contributions
 Claus+0.047
 daddy+0.046
ric+0.044
ingu+0.044
ich+0.043
Neg logit contributions
 moments-0.037
ed-0.032
 inspection-0.031
ment-0.031
abouts-0.029
Token to
Token ID284
Feature activation+9.10e-01

Pos logit contributions
 moments+0.037
 inspection+0.033
ed+0.032
ment+0.031
 Alicia+0.030
Neg logit contributions
 Claus-0.041
 daddy-0.040
ric-0.039
ingu-0.039
 boo-0.039
Token the
Token ID262
Feature activation-4.59e-01

Pos logit contributions
 moments+0.036
 inspection+0.033
 Alicia+0.029
 Meg+0.028
ment+0.028
Neg logit contributions
 Claus-0.053
washer-0.052
uch-0.052
ingu-0.052
ppa-0.051
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
ric+0.023
ppa+0.023
ll+0.023
oun+0.022
ingu+0.022
Neg logit contributions
 moments-0.021
 pathways-0.018
 passages-0.018
 insects-0.017
 after-0.017
Token room
Token ID2119
Feature activation-3.29e+00

Pos logit contributions
 Claus+0.282
 daddy+0.278
ingu+0.244
washer+0.232
ric+0.223
Neg logit contributions
 moments-0.779
 inspection-0.734
ment-0.719
abouts-0.697
ed-0.691
Token,
Token ID11
Feature activation+1.69e-01

Pos logit contributions
 Claus+0.195
 daddy+0.193
ingu+0.182
washer+0.179
ll+0.176
Neg logit contributions
 moments-0.136
 inspection-0.119
ment-0.116
abouts-0.110
ed-0.107
Token where
Token ID810
Feature activation-3.08e+00

Pos logit contributions
 moments+0.008
 inspection+0.007
ment+0.006
ed+0.006
 Alicia+0.006
Neg logit contributions
 Claus-0.009
ingu-0.009
ric-0.009
oun-0.008
 daddy-0.008
Token the
Token ID262
Feature activation-5.26e-01

Pos logit contributions
 Claus+0.172
ric+0.163
ingu+0.160
 daddy+0.159
 boo+0.158
Neg logit contributions
 moments-0.139
 inspection-0.121
ment-0.119
ed-0.114
abouts-0.108
Token cake
Token ID12187
Feature activation-7.99e-01

Pos logit contributions
ppa+0.027
ric+0.027
ll+0.026
 Claus+0.026
ingu+0.025
Neg logit contributions
 moments-0.030
 hours-0.022
abouts-0.021
 insects-0.021
 pathways-0.021
Token Lily
Token ID20037
Feature activation+9.72e-01

Pos logit contributions
 moments+0.008
 inspection+0.007
ment+0.007
ed+0.006
abouts+0.006
Neg logit contributions
 Claus-0.009
 daddy-0.009
ingu-0.008
ric-0.008
washer-0.008
Token was
Token ID373
Feature activation+4.72e-01

Pos logit contributions
 moments+0.050
 inspection+0.044
ment+0.044
abouts+0.041
ed+0.040
Neg logit contributions
 Claus-0.049
 daddy-0.048
ingu-0.045
 boo-0.044
washer-0.044
Token painting
Token ID12036
Feature activation-6.35e-01

Pos logit contributions
 moments+0.022
ed+0.020
 after+0.020
 hours+0.019
 Alicia+0.019
Neg logit contributions
 Claus-0.025
oun-0.025
ll-0.023
ingu-0.022
washer-0.022
Token in
Token ID287
Feature activation-1.72e+00

Pos logit contributions
 daddy+0.031
 cube+0.026
washer+0.026
 living+0.026
 Claus+0.026
Neg logit contributions
 inspection-0.034
 moments-0.033
ment-0.029
abouts-0.029
edly-0.029
Token the
Token ID262
Feature activation-5.28e-01

Pos logit contributions
 daddy+0.106
 living+0.091
 sewing+0.090
 boo+0.090
 iron+0.088
Neg logit contributions
 moments-0.068
 inspection-0.066
ment-0.066
ed-0.065
edly-0.063
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
 Claus+0.030
ingu+0.028
ll+0.027
oun+0.027
ppa+0.026
Neg logit contributions
 moments-0.026
abouts-0.021
ment-0.020
 inspection-0.020
oos-0.020
Token room
Token ID2119
Feature activation-3.36e+00

Pos logit contributions
 daddy+0.280
 Claus+0.277
ingu+0.247
washer+0.237
ric+0.234
Neg logit contributions
 moments-0.780
 inspection-0.734
ment-0.713
abouts-0.694
ed-0.688
Token.
Token ID13
Feature activation+4.27e-01

Pos logit contributions
 Claus+0.184
 daddy+0.183
ingu+0.173
washer+0.169
ric+0.167
Neg logit contributions
 moments-0.152
 inspection-0.135
ment-0.131
abouts-0.124
ed-0.123
Token She
Token ID1375
Feature activation+1.61e+00

Pos logit contributions
 moments+0.015
ment+0.013
 inspection+0.013
ed+0.011
abouts+0.011
Neg logit contributions
 daddy-0.029
 Claus-0.027
 boo-0.027
ingu-0.027
ric-0.026
Token had
Token ID550
Feature activation-2.22e+00

Pos logit contributions
 moments+0.074
 inspection+0.064
ed+0.062
ment+0.061
abouts+0.059
Neg logit contributions
 Claus-0.089
ingu-0.085
 daddy-0.085
ric-0.081
oun-0.081
Token a
Token ID257
Feature activation+1.10e-02

Pos logit contributions
 Claus+0.117
 daddy+0.114
ingu+0.109
ric+0.105
washer+0.105
Neg logit contributions
 moments-0.107
 inspection-0.095
ment-0.093
ed-0.089
abouts-0.088
Token was
Token ID373
Feature activation+6.60e-01

Pos logit contributions
 Claus+0.001
 daddy+0.001
ingu+0.001
washer+0.001
ric+0.001
Neg logit contributions
 moments-0.001
 inspection-0.001
ed-0.001
ment-0.001
abouts-0.001
Token a
Token ID257
Feature activation-2.06e-04

Pos logit contributions
 moments+0.021
 Alicia+0.020
ed+0.019
 Meg+0.018
Pat+0.018
Neg logit contributions
ll-0.040
 Claus-0.040
washer-0.040
ingu-0.037
 supervision-0.037
Token spoiled
Token ID34781
Feature activation-1.39e+00

Pos logit contributions
ric+0.000
 supervision+0.000
 fault+0.000
ingu+0.000
ll+0.000
Neg logit contributions
 moments-0.000
 after-0.000
Da-0.000
ger-0.000
Exc-0.000
Token rabbit
Token ID22746
Feature activation+7.44e-01

Pos logit contributions
 Claus+0.076
ric+0.072
 daddy+0.070
ingu+0.070
ll+0.070
Neg logit contributions
 moments-0.063
 inspection-0.054
ment-0.053
ed-0.051
abouts-0.051
Token,
Token ID11
Feature activation+2.47e-01

Pos logit contributions
 moments+0.023
 after+0.022
ger+0.019
 towards+0.017
 and+0.017
Neg logit contributions
 Claus-0.048
ingu-0.048
 daddy-0.047
ric-0.047
oun-0.045
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
 moments+0.010
 inspection+0.010
 Meg+0.009
ment+0.009
 after+0.008
Neg logit contributions
 Claus-0.014
ingu-0.013
ll-0.013
washer-0.013
acey-0.013
Token in
Token ID287
Feature activation-2.05e+00

Pos logit contributions
 Claus+0.533
 daddy+0.498
ingu+0.489
ric+0.477
oun+0.472
Neg logit contributions
 moments-0.544
 inspection-0.473
ed-0.473
ment-0.472
abouts-0.439
Token a
Token ID257
Feature activation-5.51e-03

Pos logit contributions
 Claus+0.129
ll+0.125
ingu+0.123
 daddy+0.121
washer+0.119
Neg logit contributions
 moments-0.081
 inspection-0.066
ment-0.064
 Alicia-0.059
ed-0.059
Token nice
Token ID3621
Feature activation+1.76e+00

Pos logit contributions
 Claus+0.000
ric+0.000
ingu+0.000
ll+0.000
 fault+0.000
Neg logit contributions
 moments-0.000
 inspection-0.000
Exc-0.000
Da-0.000
 Alicia-0.000
Token little
Token ID1310
Feature activation-2.09e+00

Pos logit contributions
 moments+0.080
 inspection+0.072
ment+0.067
 Alicia+0.064
abouts+0.064
Neg logit contributions
 Claus-0.095
ric-0.089
washer-0.089
ingu-0.088
ll-0.088
Token home
Token ID1363
Feature activation-5.48e-01

Pos logit contributions
 Claus+0.107
ingu+0.102
 daddy+0.100
ll+0.099
ric+0.098
Neg logit contributions
 moments-0.107
 inspection-0.091
ment-0.089
abouts-0.087
ed-0.086
Token Rose
Token ID8049
Feature activation-6.93e-01

Pos logit contributions
 moments+0.016
 inspection+0.015
ment+0.014
abouts+0.014
ed+0.014
Neg logit contributions
 Claus-0.015
 daddy-0.015
ingu-0.014
washer-0.013
 boo-0.013
Token were
Token ID547
Feature activation-8.90e-01

Pos logit contributions
 Claus+0.040
 daddy+0.039
ingu+0.038
ric+0.038
 boo+0.037
Neg logit contributions
 moments-0.029
 inspection-0.026
ed-0.024
ment-0.024
abouts-0.023
Token playing
Token ID2712
Feature activation-3.16e+00

Pos logit contributions
 Claus+0.045
oun+0.041
washer+0.041
ric+0.040
ingu+0.039
Neg logit contributions
 moments-0.045
ed-0.043
 Alicia-0.039
 Meg-0.039
 after-0.038
Token in
Token ID287
Feature activation-1.91e+00

Pos logit contributions
 daddy+0.123
 living+0.115
 cube+0.113
 tank+0.113
 boo+0.109
Neg logit contributions
 inspection-0.185
 moments-0.185
ment-0.179
ways-0.162
edly-0.161
Token the
Token ID262
Feature activation-3.66e-01

Pos logit contributions
 daddy+0.093
 Claus+0.086
ric+0.082
 living+0.080
 boo+0.080
Neg logit contributions
 moments-0.099
ment-0.094
 inspection-0.090
ed-0.090
edly-0.088
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
 Claus+0.020
 daddy+0.018
ingu+0.018
ll+0.018
ppa+0.017
Neg logit contributions
 moments-0.018
 inspection-0.015
abouts-0.015
ment-0.014
 Alicia-0.014
Token room
Token ID2119
Feature activation-3.43e+00

Pos logit contributions
 Claus+0.295
 daddy+0.288
ingu+0.262
washer+0.245
ric+0.244
Neg logit contributions
 moments-0.771
 inspection-0.718
ment-0.705
ed-0.681
abouts-0.680
Token when
Token ID618
Feature activation-4.76e-01

Pos logit contributions
 daddy+0.185
 Claus+0.183
ingu+0.171
washer+0.171
ll+0.167
Neg logit contributions
 moments-0.156
 inspection-0.142
ment-0.136
abouts-0.129
ed-0.125
Token they
Token ID484
Feature activation-8.54e-02

Pos logit contributions
 Claus+0.025
 daddy+0.025
ingu+0.023
ric+0.022
washer+0.022
Neg logit contributions
 moments-0.023
 inspection-0.020
ment-0.020
ed-0.019
abouts-0.019
Token heard
Token ID2982
Feature activation+4.26e+00

Pos logit contributions
 Claus+0.006
 daddy+0.005
ingu+0.005
washer+0.005
ric+0.005
Neg logit contributions
 moments-0.003
 inspection-0.003
ment-0.003
ed-0.002
abouts-0.002
Token a
Token ID257
Feature activation+1.17e-01

Pos logit contributions
 moments+0.205
 inspection+0.184
ment+0.176
abouts+0.172
ed+0.169
Neg logit contributions
 daddy-0.221
 Claus-0.219
ingu-0.204
 boo-0.198
washer-0.197
Token ostr
Token ID42387
Feature activation-4.09e+00

Pos logit contributions
ingu+0.021
 Claus+0.021
 daddy+0.020
oun+0.020
ppa+0.020
Neg logit contributions
 moments-0.021
 inspection-0.017
abouts-0.017
 Alicia-0.017
 insects-0.016
Tokenich
Token ID488
Feature activation-1.86e+00

Pos logit contributions
 daddy+0.080
ingu+0.073
 Claus+0.068
 boo+0.068
acey+0.065
Neg logit contributions
 moments-0.312
 inspection-0.303
ment-0.302
ed-0.296
abouts-0.287
Token pen
Token ID3112
Feature activation-1.06e+00

Pos logit contributions
 daddy+0.109
 Claus+0.109
ingu+0.108
oun+0.106
acey+0.104
Neg logit contributions
 moments-0.070
 inspection-0.062
ment-0.059
 after-0.056
 Alicia-0.055
Token.
Token ID13
Feature activation+7.25e-02

Pos logit contributions
 Claus+0.070
 daddy+0.069
ric+0.067
ingu+0.067
 boo+0.066
Neg logit contributions
 moments-0.035
 inspection-0.029
ment-0.029
ed-0.028
edly-0.027
Token Ost
Token ID38919
Feature activation+1.43e+00

Pos logit contributions
 moments+0.003
 inspection+0.002
ment+0.002
ed+0.002
abouts+0.002
Neg logit contributions
 Claus-0.005
 daddy-0.004
ingu-0.004
ric-0.004
 boo-0.004
Tokenric
Token ID1173
Feature activation-1.06e+01

Pos logit contributions
 moments+0.118
 inspection+0.112
ment+0.111
abouts+0.108
ed+0.108
Neg logit contributions
 daddy-0.023
 Claus-0.021
 boo-0.018
ingu-0.017
washer-0.017
Tokenhes
Token ID956
Feature activation-1.15e+00

Pos logit contributions
 Claus+0.383
 daddy+0.372
ingu+0.347
 boo+0.329
washer+0.325
Neg logit contributions
 moments-0.682
 inspection-0.625
ment-0.618
ed-0.598
abouts-0.591
Token are
Token ID389
Feature activation+5.76e-01

Pos logit contributions
 Claus+0.061
 daddy+0.060
ingu+0.058
ll+0.055
ppa+0.054
Neg logit contributions
 moments-0.055
ment-0.050
 inspection-0.049
ed-0.047
abouts-0.044
Token big
Token ID1263
Feature activation+9.63e-01

Pos logit contributions
 moments+0.026
 inspection+0.024
 vines+0.023
 insects+0.023
ment+0.022
Neg logit contributions
ingu-0.030
oun-0.029
 Claus-0.028
washer-0.028
 daddy-0.028
Token birds
Token ID10087
Feature activation+4.26e+00

Pos logit contributions
 moments+0.040
 inspection+0.036
ment+0.035
abouts+0.032
edly+0.032
Neg logit contributions
 Claus-0.056
 daddy-0.055
ingu-0.052
 boo-0.051
ric-0.051
Token with
Token ID351
Feature activation+2.43e-02

Pos logit contributions
 moments+0.090
 after+0.085
ment+0.080
ed+0.075
 inspection+0.065
Neg logit contributions
ingu-0.329
 daddy-0.317
acey-0.303
 Claus-0.300
oun-0.293
Token and
Token ID290
Feature activation+3.70e-01

Pos logit contributions
 Claus+0.035
 daddy+0.035
washer+0.033
ingu+0.033
ll+0.032
Neg logit contributions
 moments-0.025
 inspection-0.022
ment-0.021
abouts-0.020
ed-0.019
Token zoom
Token ID19792
Feature activation+6.78e-01

Pos logit contributions
 moments+0.016
 inspection+0.014
ment+0.014
abouts+0.013
ed+0.013
Neg logit contributions
 Claus-0.021
 daddy-0.021
ingu-0.019
washer-0.019
 boo-0.019
Tokened
Token ID276
Feature activation+3.23e+00

Pos logit contributions
 amaz+0.025
 moments+0.025
Rachel+0.022
growth+0.022
Meg+0.021
Neg logit contributions
 daddy-0.036
 cube-0.034
oun-0.034
 Claus-0.034
washer-0.034
Token around
Token ID1088
Feature activation+1.30e+00

Pos logit contributions
 moments+0.158
ment+0.153
edly+0.140
 Alicia+0.137
 inspection+0.136
Neg logit contributions
 daddy-0.150
 Claus-0.137
 cube-0.134
 living-0.134
 tank-0.131
Token the
Token ID262
Feature activation-4.88e-01

Pos logit contributions
 moments+0.067
ment+0.062
 inspection+0.061
abouts+0.058
ed+0.058
Neg logit contributions
 daddy-0.062
 Claus-0.059
 cube-0.054
 living-0.054
ric-0.054
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
 Claus+0.023
 daddy+0.021
ingu+0.021
ll+0.020
ric+0.020
Neg logit contributions
 moments-0.027
 inspection-0.024
ment-0.023
abouts-0.023
ed-0.023
Token room
Token ID2119
Feature activation-3.24e+00

Pos logit contributions
 daddy+0.194
 Claus+0.173
washer+0.165
 living+0.164
 cube+0.160
Neg logit contributions
 moments-0.837
 inspection-0.805
ment-0.780
Run-0.764
Exc-0.755
Token.
Token ID13
Feature activation+1.48e-01

Pos logit contributions
 Claus+0.161
 daddy+0.160
ingu+0.149
washer+0.148
ric+0.143
Neg logit contributions
 moments-0.163
 inspection-0.146
ment-0.142
abouts-0.135
ed-0.133
Token It
Token ID632
Feature activation+1.06e+00

Pos logit contributions
 moments+0.005
 inspection+0.004
ment+0.004
ed+0.003
abouts+0.003
Neg logit contributions
 Claus-0.010
 daddy-0.010
ingu-0.010
ll-0.010
ric-0.010
Token felt
Token ID2936
Feature activation+1.69e+00

Pos logit contributions
 moments+0.054
ment+0.050
 inspection+0.049
edly+0.045
abouts+0.045
Neg logit contributions
 Claus-0.052
 daddy-0.052
washer-0.050
 boo-0.048
 cube-0.047
Token so
Token ID523
Feature activation-2.71e+00

Pos logit contributions
 moments+0.085
ment+0.073
 inspection+0.072
ed+0.070
 after+0.067
Neg logit contributions
 Claus-0.090
 daddy-0.083
ingu-0.081
ll-0.080
ric-0.080
Token bear
Token ID6842
Feature activation-1.97e+00

Pos logit contributions
 Claus+0.026
ric+0.026
ingu+0.025
ll+0.025
oun+0.024
Neg logit contributions
 moments-0.026
 insects-0.020
 Alicia-0.020
ment-0.020
ed-0.020
Token was
Token ID373
Feature activation+3.08e-01

Pos logit contributions
 Claus+0.118
 daddy+0.116
ingu+0.112
ric+0.109
 boo+0.108
Neg logit contributions
 moments-0.080
 inspection-0.069
ment-0.067
ed-0.064
abouts-0.062
Token running
Token ID2491
Feature activation-2.19e-01

Pos logit contributions
 moments+0.015
ed+0.013
 Alicia+0.013
 after+0.012
 inspection+0.012
Neg logit contributions
 Claus-0.016
oun-0.015
ingu-0.015
ll-0.015
 daddy-0.014
Token around
Token ID1088
Feature activation+1.34e+00

Pos logit contributions
 daddy+0.010
 Claus+0.009
 tank+0.009
 cube+0.009
 boo+0.009
Neg logit contributions
 moments-0.012
ment-0.012
 inspection-0.010
growth-0.010
abouts-0.010
Token the
Token ID262
Feature activation-4.38e-01

Pos logit contributions
 moments+0.062
ment+0.056
 inspection+0.055
ed+0.052
abouts+0.052
Neg logit contributions
 daddy-0.072
 Claus-0.070
 boo-0.065
ingu-0.064
ric-0.064
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
 Claus+0.027
ll+0.025
oun+0.025
ingu+0.025
 daddy+0.025
Neg logit contributions
 moments-0.016
 pathways-0.014
 streams-0.014
 valleys-0.014
abouts-0.013
Token room
Token ID2119
Feature activation-3.42e+00

Pos logit contributions
 daddy+0.284
 Claus+0.283
ingu+0.255
washer+0.242
ric+0.238
Neg logit contributions
 moments-0.774
 inspection-0.726
ment-0.710
abouts-0.685
ed-0.681
Token when
Token ID618
Feature activation-3.29e-01

Pos logit contributions
 Claus+0.199
 daddy+0.199
ingu+0.187
washer+0.186
ll+0.181
Neg logit contributions
 moments-0.142
 inspection-0.124
ment-0.121
abouts-0.113
ed-0.111
Token suddenly
Token ID6451
Feature activation+1.43e+00

Pos logit contributions
 Claus+0.020
 daddy+0.019
ingu+0.019
ric+0.018
washer+0.018
Neg logit contributions
 moments-0.013
 inspection-0.011
ment-0.011
ed-0.010
abouts-0.010
Token it
Token ID340
Feature activation+1.84e+00

Pos logit contributions
 moments+0.064
 inspection+0.056
ment+0.054
abouts+0.052
edly+0.051
Neg logit contributions
 Claus-0.079
 daddy-0.079
ingu-0.073
 boo-0.072
washer-0.071
Token stepped
Token ID10764
Feature activation-8.83e-01

Pos logit contributions
 moments+0.088
 inspection+0.080
ment+0.079
abouts+0.073
edly+0.069
Neg logit contributions
 Claus-0.097
 daddy-0.095
washer-0.090
 boo-0.089
ingu-0.088
Token raise
Token ID5298
Feature activation+2.07e-01

Pos logit contributions
 Claus+0.083
 daddy+0.081
ingu+0.079
ric+0.076
washer+0.076
Neg logit contributions
 moments-0.055
 inspection-0.047
ment-0.046
ed-0.044
abouts-0.043
Token the
Token ID262
Feature activation-4.73e-01

Pos logit contributions
 moments+0.008
 inspection+0.007
ment+0.007
ed+0.007
abouts+0.007
Neg logit contributions
 Claus-0.012
 daddy-0.012
ingu-0.012
 boo-0.011
ric-0.011
Token curtains
Token ID41160
Feature activation-5.44e-01

Pos logit contributions
ingu+0.025
 Claus+0.024
ll+0.024
ppa+0.024
ric+0.023
Neg logit contributions
 moments-0.025
 insects-0.020
 vines-0.020
 paths-0.019
abouts-0.019
Token in
Token ID287
Feature activation-1.92e+00

Pos logit contributions
 Claus+0.032
ingu+0.031
 daddy+0.031
 boo+0.029
ric+0.029
Neg logit contributions
 moments-0.023
ment-0.020
 inspection-0.020
ed-0.018
abouts-0.018
Token the
Token ID262
Feature activation-5.89e-01

Pos logit contributions
 daddy+0.104
 Claus+0.104
ingu+0.097
 boo+0.095
ric+0.095
Neg logit contributions
 moments-0.087
 inspection-0.078
ment-0.076
ed-0.073
abouts-0.072
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
 Claus+0.026
ll+0.025
ingu+0.025
oun+0.024
ppa+0.023
Neg logit contributions
 moments-0.038
 valleys-0.029
oos-0.029
abouts-0.029
 inspection-0.029
Token room
Token ID2119
Feature activation-3.22e+00

Pos logit contributions
 Claus+0.287
 daddy+0.282
ingu+0.251
washer+0.239
ric+0.235
Neg logit contributions
 moments-0.776
 inspection-0.725
ment-0.710
abouts-0.690
ed-0.687
Token.
Token ID13
Feature activation+2.68e-01

Pos logit contributions
 Claus+0.181
 daddy+0.175
ingu+0.172
ric+0.166
 boo+0.165
Neg logit contributions
 moments-0.144
 inspection-0.125
ment-0.124
ed-0.118
abouts-0.114
Token Lily
Token ID20037
Feature activation+7.85e-01

Pos logit contributions
 moments+0.014
ment+0.013
 inspection+0.012
ed+0.012
abouts+0.011
Neg logit contributions
 daddy-0.013
 Claus-0.013
ingu-0.012
 boo-0.012
washer-0.012
Token tried
Token ID3088
Feature activation-1.80e+00

Pos logit contributions
 moments+0.036
 inspection+0.032
ment+0.031
ed+0.030
abouts+0.029
Neg logit contributions
 Claus-0.043
 daddy-0.042
ingu-0.040
ric-0.039
 boo-0.038
Token her
Token ID607
Feature activation+1.54e+00

Pos logit contributions
 Claus+0.098
 daddy+0.096
ingu+0.092
ric+0.089
washer+0.089
Neg logit contributions
 moments-0.085
 inspection-0.075
ment-0.073
ed-0.069
abouts-0.069
Token there
Token ID612
Feature activation-2.29e-01

Pos logit contributions
 moments+0.009
 inspection+0.008
ment+0.008
ed+0.007
abouts+0.007
Neg logit contributions
 Claus-0.010
 daddy-0.009
ingu-0.009
ric-0.009
washer-0.009
Token was
Token ID373
Feature activation+6.44e-01

Pos logit contributions
 daddy+0.012
 Claus+0.012
ingu+0.012
ric+0.011
washer+0.011
Neg logit contributions
 moments-0.011
ment-0.009
 inspection-0.009
edly-0.009
abouts-0.009
Token an
Token ID281
Feature activation+9.62e-01

Pos logit contributions
 moments+0.032
 inspection+0.029
ment+0.028
ed+0.026
abouts+0.026
Neg logit contributions
 daddy-0.033
 Claus-0.033
ingu-0.031
 boo-0.030
ric-0.029
Token intelligent
Token ID12661
Feature activation+3.48e+00

Pos logit contributions
 moments+0.055
ment+0.048
 inspection+0.048
abouts+0.046
edly+0.045
Neg logit contributions
 Claus-0.042
ll-0.038
ric-0.038
 daddy-0.038
ingu-0.037
Token fox
Token ID21831
Feature activation+2.22e+00

Pos logit contributions
 moments+0.158
 Alicia+0.130
 inspection+0.130
ment+0.128
ger+0.128
Neg logit contributions
ric-0.189
ll-0.187
 Claus-0.182
ingu-0.176
uch-0.176
Token living
Token ID2877
Feature activation-1.06e+01

Pos logit contributions
 moments+0.111
ment+0.103
ed+0.099
 inspection+0.098
 after+0.093
Neg logit contributions
ingu-0.107
 Claus-0.106
 daddy-0.102
 boo-0.101
oun-0.099
Token in
Token ID287
Feature activation-2.16e+00

Pos logit contributions
 Claus+0.538
ingu+0.502
 daddy+0.494
ric+0.482
oun+0.481
Neg logit contributions
 moments-0.550
ed-0.478
ment-0.471
 inspection-0.467
edly-0.433
Token a
Token ID257
Feature activation-4.62e-02

Pos logit contributions
 Claus+0.113
 daddy+0.113
ingu+0.104
 boo+0.103
ric+0.103
Neg logit contributions
 moments-0.102
 inspection-0.092
ment-0.090
abouts-0.088
ed-0.087
Token big
Token ID1263
Feature activation+9.30e-01

Pos logit contributions
 Claus+0.002
ingu+0.002
ric+0.002
 fault+0.002
ll+0.002
Neg logit contributions
 moments-0.002
 inspection-0.002
Exc-0.002
 Alicia-0.002
 valleys-0.002
Token green
Token ID4077
Feature activation+2.77e+00

Pos logit contributions
 moments+0.043
 inspection+0.037
ment+0.035
abouts+0.033
 Alicia+0.033
Neg logit contributions
 Claus-0.052
ingu-0.049
 daddy-0.049
washer-0.048
ll-0.047
Token valley
Token ID19272
Feature activation+1.45e+00

Pos logit contributions
 moments+0.125
 inspection+0.107
ment+0.105
abouts+0.102
ed+0.096
Neg logit contributions
 Claus-0.157
 daddy-0.146
ingu-0.145
ll-0.144
washer-0.143
Token She
Token ID1375
Feature activation+1.94e+00

Pos logit contributions
 moments+0.021
 inspection+0.018
ment+0.017
ed+0.016
abouts+0.016
Neg logit contributions
 Claus-0.038
 daddy-0.037
ingu-0.036
 boo-0.035
ll-0.035
Token kept
Token ID4030
Feature activation-4.94e-01

Pos logit contributions
 moments+0.089
 inspection+0.079
ment+0.078
abouts+0.073
ed+0.072
Neg logit contributions
 Claus-0.105
 daddy-0.104
ingu-0.098
washer-0.095
 boo-0.095
Token asking
Token ID4737
Feature activation+8.23e-01

Pos logit contributions
 Claus+0.021
 daddy+0.020
ingu+0.020
washer+0.019
ric+0.019
Neg logit contributions
 moments-0.029
 inspection-0.026
ment-0.026
ed-0.024
abouts-0.024
Token the
Token ID262
Feature activation-4.74e-02

Pos logit contributions
 moments+0.035
 inspection+0.031
ment+0.030
abouts+0.028
ed+0.028
Neg logit contributions
 Claus-0.047
 daddy-0.047
ingu-0.045
washer-0.043
ric-0.043
Token cloud
Token ID6279
Feature activation+9.82e-01

Pos logit contributions
ingu+0.002
 Claus+0.002
ll+0.002
ppa+0.002
oun+0.002
Neg logit contributions
 moments-0.002
 insects-0.002
ment-0.002
 inspection-0.002
abouts-0.002
Token questions
Token ID2683
Feature activation+5.80e+00

Pos logit contributions
 moments+0.041
 inspection+0.036
ment+0.035
ed+0.033
abouts+0.031
Neg logit contributions
 Claus-0.058
 daddy-0.056
ingu-0.056
 boo-0.053
ric-0.053
Token,
Token ID11
Feature activation+5.66e-01

Pos logit contributions
 moments+0.226
 inspection+0.196
ment+0.192
ed+0.180
abouts+0.170
Neg logit contributions
 Claus-0.358
ingu-0.348
 daddy-0.348
 boo-0.335
ric-0.330
Token and
Token ID290
Feature activation+6.97e-01

Pos logit contributions
 moments+0.026
 inspection+0.022
ment+0.022
abouts+0.021
ed+0.021
Neg logit contributions
 Claus-0.031
 daddy-0.031
ingu-0.029
ric-0.028
 boo-0.028
Token the
Token ID262
Feature activation-2.64e-01

Pos logit contributions
 moments+0.032
 inspection+0.028
ment+0.028
abouts+0.027
ed+0.026
Neg logit contributions
 daddy-0.038
 Claus-0.038
ric-0.034
washer-0.034
ingu-0.034
Token cloud
Token ID6279
Feature activation+9.16e-01

Pos logit contributions
ingu+0.015
 Claus+0.015
ll+0.014
oun+0.014
ppa+0.014
Neg logit contributions
 moments-0.013
ment-0.010
 inspection-0.010
abouts-0.009
 insects-0.009
Token kept
Token ID4030
Feature activation-6.30e-01

Pos logit contributions
 moments+0.040
 inspection+0.035
ment+0.034
ed+0.033
abouts+0.031
Neg logit contributions
 Claus-0.052
 daddy-0.051
ingu-0.050
ric-0.048
 boo-0.047
Token they
Token ID484
Feature activation-1.38e-02

Pos logit contributions
 moments+0.023
 inspection+0.021
ment+0.020
ed+0.020
edly+0.019
Neg logit contributions
 Claus-0.022
 daddy-0.021
ingu-0.021
ric-0.020
ll-0.019
Token hoped
Token ID10719
Feature activation+3.68e-01

Pos logit contributions
 Claus+0.001
 daddy+0.001
ingu+0.001
ric+0.001
oun+0.001
Neg logit contributions
 moments-0.001
ed-0.001
 inspection-0.001
ment-0.001
edly-0.001
Token that
Token ID326
Feature activation-4.25e+00

Pos logit contributions
 moments+0.017
ment+0.014
 inspection+0.014
ed+0.013
 after+0.012
Neg logit contributions
 Claus-0.022
ingu-0.021
ric-0.020
ppa-0.020
oun-0.020
Token they
Token ID484
Feature activation-1.10e-02

Pos logit contributions
 Claus+0.260
ingu+0.256
ric+0.245
ppa+0.245
inky+0.241
Neg logit contributions
 moments-0.185
 inspection-0.143
ment-0.143
ed-0.134
 after-0.132
Token could
Token ID714
Feature activation-2.28e+00

Pos logit contributions
ingu+0.001
 daddy+0.001
 Claus+0.001
oun+0.001
ich+0.001
Neg logit contributions
 moments-0.000
ed-0.000
 inspection-0.000
 after-0.000
 widened-0.000
Token do
Token ID466
Feature activation+3.75e+00

Pos logit contributions
 Claus+0.120
ingu+0.117
oun+0.116
washer+0.115
cient+0.112
Neg logit contributions
 moments-0.089
 after-0.084
 inspection-0.081
 behold-0.081
 Alicia-0.077
Token better
Token ID1365
Feature activation-2.46e+00

Pos logit contributions
 moments+0.170
 inspection+0.148
ment+0.145
ed+0.136
abouts+0.135
Neg logit contributions
 Claus-0.212
 daddy-0.204
ingu-0.198
ric-0.191
washer-0.190
Token next
Token ID1306
Feature activation+2.56e+00

Pos logit contributions
 daddy+0.124
 Claus+0.119
ll+0.109
 boo+0.109
ingu+0.106
Neg logit contributions
 inspection-0.113
 moments-0.113
abouts-0.107
eways-0.105
 Alicia-0.104
Token time
Token ID640
Feature activation-3.44e-01

Pos logit contributions
 moments+0.135
 inspection+0.119
ment+0.116
abouts+0.111
ed+0.111
Neg logit contributions
 Claus-0.127
 daddy-0.123
ingu-0.118
ric-0.115
 boo-0.113
Token.
Token ID13
Feature activation-1.57e-01

Pos logit contributions
ingu+0.023
ric+0.023
 Claus+0.023
oun+0.022
 boo+0.022
Neg logit contributions
 moments-0.012
 after-0.010
ed-0.009
ment-0.009
 inspection-0.008
Token<|endoftext|>
Token ID50256
Feature activation-6.35e-02

Pos logit contributions
 Claus+0.010
 daddy+0.010
ingu+0.010
washer+0.010
ll+0.009
Neg logit contributions
 moments-0.006
 inspection-0.005
ment-0.005
ed-0.004
edly-0.004
Token."
Token ID526
Feature activation-1.41e+00

Pos logit contributions
 moments+0.064
ed+0.060
 after+0.060
 inspection+0.058
 towards+0.056
Neg logit contributions
ric-0.066
ingu-0.064
 boo-0.063
 Claus-0.063
 daddy-0.063
Token
Token ID198
Feature activation+5.86e-02

Pos logit contributions
 daddy+0.050
 tank+0.044
 twin+0.043
 cube+0.042
washer+0.040
Neg logit contributions
 moments-0.083
iece-0.081
edly-0.077
ment-0.076
ed-0.076
Token
Token ID198
Feature activation+3.82e-02

Pos logit contributions
 moments+0.004
ment+0.003
edly+0.003
 inspection+0.003
abouts+0.003
Neg logit contributions
 daddy-0.002
ll-0.002
 Claus-0.002
washer-0.002
ingu-0.002
Token"
Token ID1
Feature activation+1.55e+00

Pos logit contributions
 moments+0.002
ened+0.002
overed+0.002
ment+0.002
 inspection+0.002
Neg logit contributions
ll-0.001
washer-0.001
o-0.001
 cube-0.001
 tank-0.001
TokenGood
Token ID10248
Feature activation+9.79e-01

Pos logit contributions
ment+0.069
 moments+0.067
 inspection+0.065
ed+0.061
oos+0.059
Neg logit contributions
 Claus-0.079
 daddy-0.077
 cube-0.075
oun-0.074
washer-0.073
Token idea
Token ID2126
Feature activation+4.78e+00

Pos logit contributions
 moments+0.057
 inspection+0.054
ment+0.052
abouts+0.049
Exc+0.049
Neg logit contributions
 Claus-0.042
 daddy-0.041
 boo-0.037
ingu-0.036
washer-0.036
Token!"
Token ID2474
Feature activation+4.44e-01

Pos logit contributions
 moments+0.249
 inspection+0.223
ment+0.219
ed+0.210
abouts+0.205
Neg logit contributions
 Claus-0.234
 daddy-0.227
ingu-0.220
ric-0.213
 boo-0.210
Token Mia
Token ID32189
Feature activation+3.73e+00

Pos logit contributions
iece+0.022
 moments+0.021
ment+0.020
edly+0.020
abouts+0.020
Neg logit contributions
 daddy-0.020
 twin-0.018
 tank-0.017
 sister-0.017
washer-0.017
Token says
Token ID1139
Feature activation-1.95e-01

Pos logit contributions
 moments+0.174
 inspection+0.154
ment+0.152
abouts+0.141
ed+0.140
Neg logit contributions
 Claus-0.203
 daddy-0.200
ingu-0.189
washer-0.184
 boo-0.184
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
 Claus+0.010
 daddy+0.010
ingu+0.009
washer+0.009
 boo+0.009
Neg logit contributions
 moments-0.009
 inspection-0.008
ment-0.008
abouts-0.008
ed-0.008
Token "
Token ID366
Feature activation+2.55e-01

Pos logit contributions
 daddy+0.010
 Claus+0.010
oun+0.009
ll+0.009
washer+0.009
Neg logit contributions
 moments-0.012
ment-0.011
 inspection-0.010
abouts-0.010
iece-0.010
Token so
Token ID523
Feature activation-2.46e+00

Pos logit contributions
 moments+0.119
ment+0.101
 inspection+0.096
 after+0.095
ed+0.095
Neg logit contributions
 Claus-0.124
ingu-0.115
ll-0.114
 daddy-0.111
ric-0.109
Token happy
Token ID3772
Feature activation+5.89e-01

Pos logit contributions
 Claus+0.123
ingu+0.116
 daddy+0.113
ric+0.110
ppa+0.107
Neg logit contributions
 moments-0.132
ment-0.118
 inspection-0.115
ed-0.109
 after-0.103
Token.
Token ID13
Feature activation+3.75e-01

Pos logit contributions
 moments+0.027
 inspection+0.024
ment+0.023
abouts+0.023
ed+0.022
Neg logit contributions
 Claus-0.032
 daddy-0.031
ingu-0.030
washer-0.029
ric-0.029
Token
Token ID198
Feature activation+4.56e-01

Pos logit contributions
 moments+0.013
 inspection+0.011
ment+0.010
abouts+0.010
 Alicia+0.009
Neg logit contributions
 Claus-0.026
 boo-0.024
ppa-0.024
uch-0.024
 daddy-0.023
Token
Token ID198
Feature activation+3.96e-01

Pos logit contributions
 moments+0.018
 inspection+0.016
ment+0.015
abouts+0.014
eways+0.014
Neg logit contributions
 Claus-0.029
 daddy-0.027
 boo-0.027
ingu-0.026
washer-0.025
TokenOne
Token ID3198
Feature activation+3.66e+00

Pos logit contributions
 moments+0.015
 inspection+0.013
ment+0.012
abouts+0.011
ed+0.011
Neg logit contributions
 Claus-0.025
 daddy-0.025
ingu-0.024
 boo-0.023
ric-0.023
Token day
Token ID1110
Feature activation+4.33e-01

Pos logit contributions
 moments+0.193
ment+0.167
 inspection+0.158
ed+0.150
 Alicia+0.149
Neg logit contributions
 Claus-0.192
ingu-0.183
ric-0.173
 daddy-0.170
ppa-0.168
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
 moments+0.020
 inspection+0.018
ment+0.017
abouts+0.017
edly+0.016
Neg logit contributions
 daddy-0.024
 Claus-0.023
ingu-0.022
washer-0.021
 boo-0.021
Token the
Token ID262
Feature activation-4.46e-01

Pos logit contributions
 moments+0.011
 inspection+0.009
ment+0.009
ed+0.008
abouts+0.008
Neg logit contributions
 Claus-0.014
 daddy-0.013
ingu-0.013
ric-0.012
washer-0.012
Token bells
Token ID30987
Feature activation+5.32e-01

Pos logit contributions
ingu+0.027
ppa+0.026
ll+0.026
 Claus+0.026
inky+0.026
Neg logit contributions
 moments-0.021
abouts-0.015
 hours-0.015
 scenery-0.015
ed-0.014
Token started
Token ID2067
Feature activation-8.32e-02

Pos logit contributions
 moments+0.021
ed+0.019
 inspection+0.019
ment+0.018
abouts+0.017
Neg logit contributions
 Claus-0.031
ingu-0.031
 daddy-0.031
 boo-0.029
ric-0.029
Token trip
Token ID5296
Feature activation-5.79e-01

Pos logit contributions
ppa+0.027
ric+0.027
ll+0.026
 Claus+0.026
ingu+0.026
Neg logit contributions
 moments-0.028
 hours-0.022
 insects-0.022
 paths-0.022
 after-0.022
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
ric+0.036
 boo+0.036
 Claus+0.035
 daddy+0.035
ingu+0.035
Neg logit contributions
 moments-0.020
ed-0.019
ment-0.018
 inspection-0.017
ways-0.016
Token They
Token ID1119
Feature activation+9.21e-01

Pos logit contributions
 moments+0.006
 inspection+0.005
ment+0.005
ed+0.005
abouts+0.005
Neg logit contributions
 Claus-0.014
 daddy-0.013
ingu-0.013
ll-0.013
ric-0.013
Token woke
Token ID19092
Feature activation+1.25e-01

Pos logit contributions
 moments+0.042
ed+0.037
 inspection+0.037
 widened+0.036
Exc+0.035
Neg logit contributions
ric-0.047
 fault-0.046
ich-0.046
 boo-0.045
 Claus-0.044
Token up
Token ID510
Feature activation+1.24e+00

Pos logit contributions
 moments+0.005
 inspection+0.005
ment+0.005
ed+0.005
abouts+0.004
Neg logit contributions
 Claus-0.007
 daddy-0.007
ingu-0.007
washer-0.007
ric-0.007
Token early
Token ID1903
Feature activation+3.59e+00

Pos logit contributions
 moments+0.041
 inspection+0.035
ment+0.035
ed+0.032
edly+0.030
Neg logit contributions
 Claus-0.081
 daddy-0.079
ingu-0.079
ric-0.078
washer-0.077
Token the
Token ID262
Feature activation-4.73e-01

Pos logit contributions
 moments+0.103
 inspection+0.086
ment+0.079
ed+0.078
edly+0.072
Neg logit contributions
 Claus-0.250
 daddy-0.249
ingu-0.248
ric-0.247
 boo-0.240
Token next
Token ID1306
Feature activation+2.86e+00

Pos logit contributions
ppa+0.025
ingu+0.024
ric+0.024
ll+0.023
acey+0.023
Neg logit contributions
 moments-0.023
 scenery-0.019
 after-0.018
 paths-0.018
 view-0.018
Token day
Token ID1110
Feature activation+4.86e-01

Pos logit contributions
 moments+0.144
 after+0.107
 inspection+0.103
 towards+0.101
ment+0.101
Neg logit contributions
ppa-0.168
ingu-0.166
ric-0.163
 Claus-0.161
 boo-0.154
Token and
Token ID290
Feature activation+6.77e-01

Pos logit contributions
 moments+0.017
ment+0.014
 inspection+0.013
ed+0.013
 after+0.012
Neg logit contributions
 Claus-0.032
ingu-0.031
 daddy-0.031
ric-0.031
 boo-0.031
Token went
Token ID1816
Feature activation+9.28e-01

Pos logit contributions
 moments+0.030
 inspection+0.026
ment+0.025
ed+0.024
abouts+0.023
Neg logit contributions
 Claus-0.038
 daddy-0.037
ingu-0.036
ric-0.036
 boo-0.035
Token worried
Token ID7960
Feature activation-7.72e-01

Pos logit contributions
ingu+0.161
 Claus+0.150
ric+0.149
ppa+0.139
oun+0.139
Neg logit contributions
 moments-0.172
ed-0.162
ment-0.159
 inspection-0.153
 after-0.145
Token.
Token ID13
Feature activation-1.96e-01

Pos logit contributions
 Claus+0.040
 daddy+0.040
ingu+0.038
washer+0.037
ric+0.037
Neg logit contributions
 moments-0.037
 inspection-0.033
ment-0.032
ed-0.031
abouts-0.031
Token They
Token ID1119
Feature activation+6.14e-01

Pos logit contributions
 Claus+0.011
 daddy+0.011
ingu+0.011
ric+0.011
washer+0.010
Neg logit contributions
 moments-0.009
 inspection-0.007
ment-0.007
ed-0.007
abouts-0.007
Token cry
Token ID3960
Feature activation-1.89e+00

Pos logit contributions
 moments+0.032
 inspection+0.029
ment+0.028
ed+0.027
abouts+0.027
Neg logit contributions
 Claus-0.030
 daddy-0.029
ingu-0.028
washer-0.027
ric-0.027
Token for
Token ID329
Feature activation+3.51e+00

Pos logit contributions
 Claus+0.096
 daddy+0.095
 boo+0.089
ingu+0.087
washer+0.086
Neg logit contributions
 moments-0.096
 inspection-0.087
ment-0.083
abouts-0.081
 Alicia-0.079
Token help
Token ID1037
Feature activation-1.39e+00

Pos logit contributions
 moments+0.198
 inspection+0.168
ment+0.167
 Alicia+0.152
 Meg+0.152
Neg logit contributions
 Claus-0.169
ingu-0.164
oun-0.162
washer-0.159
ric-0.156
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
 Claus+0.089
ingu+0.088
ric+0.084
 daddy+0.083
washer+0.083
Neg logit contributions
 moments-0.053
 inspection-0.043
ment-0.041
 after-0.041
ed-0.041
Token
Token ID198
Feature activation+1.13e-02

Pos logit contributions
 Claus+0.010
 daddy+0.010
ingu+0.010
ric+0.010
washer+0.010
Neg logit contributions
 moments-0.009
 inspection-0.008
ment-0.007
ed-0.007
edly-0.007
Token
Token ID198
Feature activation-1.18e-02

Pos logit contributions
 moments+0.000
 inspection+0.000
ment+0.000
ed+0.000
 Alicia+0.000
Neg logit contributions
 Claus-0.001
 daddy-0.001
ingu-0.001
 boo-0.001
ric-0.001
TokenA
Token ID32
Feature activation+1.24e+00

Pos logit contributions
 Claus+0.001
 daddy+0.001
ingu+0.001
ric+0.001
 boo+0.001
Neg logit contributions
 moments-0.000
ment-0.000
 inspection-0.000
ed-0.000
edly-0.000
Token man
Token ID582
Feature activation+1.92e+00

Pos logit contributions
 moments+0.067
 inspection+0.059
ment+0.058
ed+0.054
abouts+0.054
Neg logit contributions
 Claus-0.058
ingu-0.056
 daddy-0.056
ric-0.055
ll-0.052
Token dad
Token ID9955
Feature activation-2.01e+00

Pos logit contributions
 moments+0.035
 inspection+0.032
ment+0.032
ed+0.031
 Meg+0.030
Neg logit contributions
 Claus-0.014
ric-0.014
uch-0.013
oun-0.012
ingu-0.012
Token.
Token ID13
Feature activation-7.00e-02

Pos logit contributions
uch+0.135
 Claus+0.132
 boo+0.128
ich+0.127
ric+0.126
Neg logit contributions
 moments-0.063
 inspection-0.058
ment-0.057
 after-0.056
ed-0.053
Token When
Token ID1649
Feature activation-8.52e-01

Pos logit contributions
 Claus+0.004
 daddy+0.004
ingu+0.004
washer+0.004
ric+0.004
Neg logit contributions
 moments-0.003
 inspection-0.002
ment-0.002
abouts-0.002
ed-0.002
Token they
Token ID484
Feature activation+6.75e-02

Pos logit contributions
 daddy+0.043
 Claus+0.042
ingu+0.039
washer+0.037
 cube+0.037
Neg logit contributions
 moments-0.044
ment-0.040
 inspection-0.039
abouts-0.038
edly-0.038
Token came
Token ID1625
Feature activation+2.09e+00

Pos logit contributions
 moments+0.003
ment+0.003
edly+0.003
abouts+0.003
 inspection+0.003
Neg logit contributions
 Claus-0.004
 daddy-0.003
ingu-0.003
washer-0.003
ll-0.003
Token home
Token ID1363
Feature activation-4.04e-01

Pos logit contributions
 moments+0.132
 inspection+0.118
ment+0.117
abouts+0.116
edly+0.112
Neg logit contributions
 daddy-0.082
 Claus-0.080
ingu-0.073
ll-0.070
washer-0.069
Token,
Token ID11
Feature activation+2.91e-01

Pos logit contributions
 Claus+0.024
 daddy+0.023
ingu+0.022
washer+0.022
 boo+0.022
Neg logit contributions
 moments-0.017
 inspection-0.015
ment-0.014
abouts-0.014
ed-0.014
Token Tim
Token ID5045
Feature activation-1.65e+00

Pos logit contributions
 moments+0.015
 inspection+0.013
ment+0.013
ed+0.012
abouts+0.012
Neg logit contributions
 Claus-0.015
 daddy-0.014
ingu-0.014
ric-0.013
 boo-0.013
Tokenmy
Token ID1820
Feature activation-3.25e+00

Pos logit contributions
oun+0.070
 Claus+0.068
 remote+0.065
ric+0.065
 daddy+0.064
Neg logit contributions
 moments-0.085
ed-0.079
 inspection-0.078
abouts-0.073
 Alicia-0.073
Token revealed
Token ID4602
Feature activation+9.54e-01

Pos logit contributions
ric+0.183
 Claus+0.180
oun+0.178
 daddy+0.174
ingu+0.172
Neg logit contributions
 moments-0.130
 inspection-0.115
ed-0.114
ment-0.106
 Alicia-0.101
Token the
Token ID262
Feature activation-6.29e-01

Pos logit contributions
 moments+0.043
 inspection+0.039
ment+0.038
ed+0.037
 Alicia+0.034
Neg logit contributions
 Claus-0.053
ll-0.050
ric-0.049
ingu-0.049
 boo-0.049
Token girl
Token ID2576
Feature activation+2.71e+00

Pos logit contributions
 daddy+0.109
 Claus+0.106
 boo+0.099
ingu+0.095
washer+0.095
Neg logit contributions
 moments-0.097
 inspection-0.091
ment-0.087
abouts-0.083
ed-0.081
Token smiled
Token ID13541
Feature activation-1.08e-01

Pos logit contributions
 moments+0.120
 inspection+0.104
ment+0.102
ed+0.097
abouts+0.095
Neg logit contributions
 Claus-0.154
 daddy-0.150
ingu-0.145
ric-0.140
washer-0.139
Token and
Token ID290
Feature activation+3.73e-01

Pos logit contributions
 daddy+0.006
 Claus+0.005
 boo+0.005
 living+0.004
ingu+0.004
Neg logit contributions
 moments-0.006
abouts-0.006
 inspection-0.005
oos-0.005
Run-0.005
Token hopped
Token ID45230
Feature activation+2.88e+00

Pos logit contributions
 moments+0.020
 inspection+0.018
ment+0.018
abouts+0.018
eways+0.016
Neg logit contributions
 Claus-0.017
 daddy-0.017
ingu-0.016
 boo-0.015
washer-0.015
Token around
Token ID1088
Feature activation+1.36e+00

Pos logit contributions
 moments+0.167
 inspection+0.160
abouts+0.157
ment+0.156
growth+0.144
Neg logit contributions
 Claus-0.109
 daddy-0.108
washer-0.097
 tank-0.096
oun-0.093
Token the
Token ID262
Feature activation-6.36e-01

Pos logit contributions
 moments+0.070
ment+0.068
abouts+0.067
 inspection+0.066
eways+0.062
Neg logit contributions
 daddy-0.063
 Claus-0.057
 living-0.056
 sewing-0.053
 boo-0.052
Token room
Token ID2119
Feature activation-3.01e+00

Pos logit contributions
 Claus+0.027
ric+0.026
ingu+0.025
ll+0.025
ppa+0.024
Neg logit contributions
 moments-0.038
ed-0.032
 passages-0.032
abouts-0.032
 pathways-0.031
Token.
Token ID13
Feature activation+5.86e-02

Pos logit contributions
 Claus+0.161
 daddy+0.161
ingu+0.150
washer+0.148
 boo+0.145
Neg logit contributions
 moments-0.139
 inspection-0.123
ment-0.121
abouts-0.115
ed-0.112
Token Suddenly
Token ID24975
Feature activation+1.08e+00

Pos logit contributions
 moments+0.002
 inspection+0.002
ment+0.002
abouts+0.002
ed+0.002
Neg logit contributions
 Claus-0.004
 daddy-0.004
ingu-0.003
ric-0.003
washer-0.003
Token,
Token ID11
Feature activation+6.09e-02

Pos logit contributions
 moments+0.053
abouts+0.051
edly+0.049
 inspection+0.048
ment+0.047
Neg logit contributions
 daddy-0.055
 Claus-0.049
 boo-0.043
 living-0.042
washer-0.042
Token the
Token ID262
Feature activation-6.45e-01

Pos logit contributions
 moments+0.003
abouts+0.003
 inspection+0.002
ment+0.002
edly+0.002
Neg logit contributions
 daddy-0.003
 Claus-0.003
 boo-0.003
washer-0.003
ingu-0.003
Token who
Token ID508
Feature activation-7.79e+00

Pos logit contributions
 moments+0.179
ment+0.158
 inspection+0.156
ed+0.152
abouts+0.147
Neg logit contributions
 Claus-0.115
ingu-0.109
 daddy-0.105
ric-0.102
ll-0.100
Token became
Token ID2627
Feature activation-2.02e-01

Pos logit contributions
 Claus+0.308
 daddy+0.298
ingu+0.277
 boo+0.268
washer+0.266
Neg logit contributions
 moments-0.481
 inspection-0.444
ment-0.437
abouts-0.419
ed-0.413
Token very
Token ID845
Feature activation-3.34e+00

Pos logit contributions
 Claus+0.010
ingu+0.009
ric+0.009
ll+0.009
washer+0.009
Neg logit contributions
 moments-0.010
ed-0.009
 after-0.009
ment-0.009
 Alicia-0.009
Token curious
Token ID11040
Feature activation+2.68e+00

Pos logit contributions
 Claus+0.166
ric+0.163
ingu+0.151
 fault+0.144
ppa+0.140
Neg logit contributions
 moments-0.170
ment-0.149
ed-0.145
 after-0.142
 inspection-0.141
Token.
Token ID13
Feature activation-1.11e-01

Pos logit contributions
 moments+0.116
 inspection+0.099
ment+0.098
ed+0.091
abouts+0.091
Neg logit contributions
 Claus-0.158
 daddy-0.150
ingu-0.148
ll-0.145
ric-0.145
Token She
Token ID1375
Feature activation+1.13e+00

Pos logit contributions
 daddy+0.007
 Claus+0.007
ingu+0.007
 living+0.007
 boo+0.006
Neg logit contributions
 moments-0.004
ment-0.003
 inspection-0.003
ed-0.003
abouts-0.003
Token wanted
Token ID2227
Feature activation-1.96e-01

Pos logit contributions
 moments+0.065
 inspection+0.059
ment+0.059
abouts+0.056
ed+0.056
Neg logit contributions
 Claus-0.049
 daddy-0.047
ingu-0.045
washer-0.043
 boo-0.043
Token to
Token ID284
Feature activation+6.90e-01

Pos logit contributions
 Claus+0.011
 daddy+0.010
ingu+0.010
ric+0.010
 boo+0.009
Neg logit contributions
 moments-0.009
 inspection-0.008
ment-0.008
ed-0.008
abouts-0.008
Token know
Token ID760
Feature activation+1.37e+00

Pos logit contributions
 moments+0.034
 inspection+0.030
ment+0.029
ed+0.027
abouts+0.027
Neg logit contributions
 Claus-0.036
 daddy-0.034
ingu-0.034
ll-0.032
ric-0.032
Token what
Token ID644
Feature activation-1.77e+00

Pos logit contributions
 moments+0.062
 inspection+0.054
ment+0.053
abouts+0.047
 passages+0.047
Neg logit contributions
 Claus-0.080
ingu-0.074
oun-0.072
ric-0.072
ll-0.071
Token was
Token ID373
Feature activation+6.24e-01

Pos logit contributions
 Claus+0.102
ingu+0.097
ric+0.095
 daddy+0.094
ll+0.092
Neg logit contributions
 moments-0.083
 inspection-0.070
ment-0.069
ed-0.064
 Alicia-0.062
Token they
Token ID484
Feature activation-6.13e-02

Pos logit contributions
 moments+0.061
 inspection+0.052
ment+0.051
ed+0.048
 Alicia+0.045
Neg logit contributions
 Claus-0.094
ingu-0.090
 daddy-0.089
ric-0.088
ll-0.086
Token looked
Token ID3114
Feature activation+5.25e-01

Pos logit contributions
 Claus+0.004
oun+0.003
 daddy+0.003
ingu+0.003
ric+0.003
Neg logit contributions
 moments-0.002
ed-0.002
 inspection-0.002
ment-0.002
 Alicia-0.002
Token at
Token ID379
Feature activation+2.14e+00

Pos logit contributions
 moments+0.026
ment+0.023
 inspection+0.023
abouts+0.021
edly+0.021
Neg logit contributions
 daddy-0.027
 Claus-0.026
ingu-0.025
washer-0.024
 boo-0.024
Token the
Token ID262
Feature activation+1.73e-01

Pos logit contributions
 moments+0.090
 inspection+0.078
ment+0.075
ed+0.070
abouts+0.069
Neg logit contributions
 Claus-0.131
ingu-0.124
 daddy-0.121
ll-0.120
washer-0.118
Token race
Token ID3234
Feature activation+2.17e-01

Pos logit contributions
 moments+0.009
abouts+0.007
 insects+0.007
 inspection+0.007
ment+0.007
Neg logit contributions
 Claus-0.009
ll-0.009
ingu-0.009
ppa-0.008
oun-0.008
Token and
Token ID290
Feature activation+7.04e-01

Pos logit contributions
 moments+0.011
 inspection+0.010
ment+0.009
abouts+0.009
ed+0.009
Neg logit contributions
 Claus-0.011
 daddy-0.011
ingu-0.011
ric-0.010
 boo-0.010
Token saw
Token ID2497
Feature activation+1.98e+00

Pos logit contributions
 moments+0.032
ment+0.028
 inspection+0.028
abouts+0.026
edly+0.025
Neg logit contributions
 Claus-0.039
 daddy-0.039
ingu-0.036
washer-0.035
 boo-0.035
Token that
Token ID326
Feature activation-3.89e+00

Pos logit contributions
 moments+0.088
 inspection+0.077
ment+0.075
ed+0.073
abouts+0.070
Neg logit contributions
 Claus-0.115
 daddy-0.108
ingu-0.108
ll-0.104
ric-0.103
Token it
Token ID340
Feature activation+1.86e+00

Pos logit contributions
 Claus+0.235
ingu+0.224
 daddy+0.222
ric+0.215
ll+0.215
Neg logit contributions
 moments-0.163
 inspection-0.139
ment-0.136
ed-0.127
abouts-0.125
Token was
Token ID373
Feature activation+7.07e-01

Pos logit contributions
 moments+0.068
 inspection+0.056
ed+0.056
abouts+0.051
ment+0.050
Neg logit contributions
 Claus-0.117
 daddy-0.116
ingu-0.116
ppa-0.110
ric-0.110
Token fair
Token ID3148
Feature activation+2.85e+00

Pos logit contributions
 moments+0.034
 inspection+0.029
 Meg+0.027
 after+0.027
abouts+0.027
Neg logit contributions
 Claus-0.038
ingu-0.036
ll-0.035
ppa-0.034
washer-0.034
Token they
Token ID484
Feature activation-6.73e-02

Pos logit contributions
 moments+0.131
 inspection+0.112
ment+0.110
 after+0.108
ed+0.104
Neg logit contributions
 Claus-0.114
ric-0.105
oun-0.105
ingu-0.104
ppa-0.101
Token are
Token ID389
Feature activation+5.36e-01

Pos logit contributions
ich+0.004
 daddy+0.004
 Claus+0.004
pron+0.004
ppa+0.004
Neg logit contributions
 after-0.002
 moments-0.002
 inspection-0.002
ed-0.002
 reached-0.002
Token my
Token ID616
Feature activation-2.22e+00

Pos logit contributions
 moments+0.018
 after+0.017
 minutes+0.017
 as+0.017
 her+0.017
Neg logit contributions
cient-0.032
str-0.031
 Claus-0.031
ric-0.031
oun-0.031
Token shoes
Token ID10012
Feature activation+3.05e+00

Pos logit contributions
 Claus+0.122
ric+0.109
ingu+0.105
uch+0.104
str+0.104
Neg logit contributions
 moments-0.116
 inspection-0.095
ment-0.090
 after-0.089
 insects-0.089
Token and
Token ID290
Feature activation+4.06e-01

Pos logit contributions
ed+0.080
 after+0.075
 moments+0.073
ment+0.066
 inspection+0.061
Neg logit contributions
ric-0.205
ingu-0.203
 daddy-0.200
 Claus-0.198
ich-0.194
Token I
Token ID314
Feature activation-2.87e+00

Pos logit contributions
 moments+0.020
 inspection+0.017
ment+0.017
ed+0.015
 insects+0.015
Neg logit contributions
 Claus-0.021
ll-0.020
ingu-0.020
ric-0.019
str-0.019
Token love
Token ID1842
Feature activation-1.34e+00

Pos logit contributions
 daddy+0.150
 Claus+0.149
ingu+0.143
ric+0.140
ich+0.140
Neg logit contributions
 moments-0.128
ed-0.118
 inspection-0.117
ment-0.111
 after-0.107
Token them
Token ID606
Feature activation-1.14e+00

Pos logit contributions
 Claus+0.076
str+0.069
ingu+0.067
washer+0.066
emic+0.066
Neg logit contributions
 moments-0.064
ment-0.055
 after-0.054
 inspection-0.052
ed-0.051
Token.
Token ID13
Feature activation-2.49e-01

Pos logit contributions
ric+0.073
str+0.070
 Claus+0.068
 boo+0.067
 daddy+0.065
Neg logit contributions
 after-0.040
 moments-0.038
ed-0.036
edly-0.033
ment-0.032
Token They
Token ID1119
Feature activation+7.20e-01

Pos logit contributions
 Claus+0.015
 daddy+0.015
ll+0.015
ingu+0.015
ric+0.014
Neg logit contributions
 moments-0.010
ment-0.008
ed-0.007
edly-0.007
 inspection-0.007
Token are
Token ID389
Feature activation+5.52e-01

Pos logit contributions
 moments+0.023
 after+0.022
ed+0.021
 inspection+0.019
 widened+0.019
Neg logit contributions
ich-0.044
 daddy-0.042
ingu-0.041
 Claus-0.041
ric-0.041
Tokeneddy
Token ID21874
Feature activation-3.66e+00

Pos logit contributions
 Claus+0.056
 daddy+0.052
ingu+0.046
ric+0.042
 boo+0.042
Neg logit contributions
 moments-0.231
 inspection-0.216
ment-0.214
ed-0.209
abouts-0.206
Token bear
Token ID6842
Feature activation-1.40e+00

Pos logit contributions
 Claus+0.130
ingu+0.122
ric+0.118
ll+0.118
 daddy+0.118
Neg logit contributions
 moments-0.237
ment-0.208
ed-0.207
 inspection-0.206
abouts-0.200
Token that
Token ID326
Feature activation-4.16e+00

Pos logit contributions
ingu+0.070
 daddy+0.069
 Claus+0.067
 boo+0.066
oun+0.065
Neg logit contributions
ed-0.066
 moments-0.065
ment-0.060
 after-0.057
edly-0.057
Token she
Token ID673
Feature activation+2.37e+00

Pos logit contributions
 Claus+0.286
ric+0.274
ingu+0.274
 daddy+0.272
ll+0.266
Neg logit contributions
 moments-0.132
 inspection-0.104
ment-0.103
ed-0.101
 Alicia-0.087
Token loved
Token ID6151
Feature activation-2.50e+00

Pos logit contributions
 moments+0.091
ed+0.090
 imagined+0.077
 hours+0.074
edly+0.073
Neg logit contributions
 fault-0.135
 Claus-0.131
 daddy-0.131
ric-0.130
 supervision-0.130
Token very
Token ID845
Feature activation-3.23e+00

Pos logit contributions
 Claus+0.121
 daddy+0.116
ingu+0.112
ric+0.107
washer+0.107
Neg logit contributions
 moments-0.133
 inspection-0.119
ment-0.116
ed-0.111
abouts-0.110
Token much
Token ID881
Feature activation-7.63e-01

Pos logit contributions
 Claus+0.145
 daddy+0.141
ingu+0.134
ric+0.128
washer+0.128
Neg logit contributions
 moments-0.181
 inspection-0.164
ment-0.161
ed-0.154
abouts-0.153
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
 Claus+0.039
 daddy+0.038
ingu+0.036
washer+0.035
 boo+0.035
Neg logit contributions
 moments-0.038
 inspection-0.034
ment-0.033
abouts-0.031
ed-0.031
Token One
Token ID1881
Feature activation+2.87e+00

Pos logit contributions
 moments+0.007
 inspection+0.006
ment+0.005
abouts+0.005
ed+0.005
Neg logit contributions
 Claus-0.013
 daddy-0.012
ingu-0.012
washer-0.012
ric-0.012
Token day
Token ID1110
Feature activation+4.59e-01

Pos logit contributions
 moments+0.157
 inspection+0.137
ment+0.137
ed+0.130
abouts+0.127
Neg logit contributions
 Claus-0.136
ingu-0.126
 daddy-0.125
ric-0.122
ll-0.119
Token,
Token ID11
Feature activation+3.39e-01

Pos logit contributions
 moments+0.023
 inspection+0.020
ment+0.020
edly+0.019
abouts+0.019
Neg logit contributions
 daddy-0.024
 Claus-0.023
ingu-0.022
 boo-0.021
 cube-0.021
Token to
Token ID284
Feature activation+7.48e-01

Pos logit contributions
 daddy+0.044
 Claus+0.043
ingu+0.041
washer+0.040
ll+0.039
Neg logit contributions
 moments-0.040
 inspection-0.036
ment-0.035
abouts-0.034
ed-0.033
Token taste
Token ID6938
Feature activation+2.62e+00

Pos logit contributions
 moments+0.038
 inspection+0.033
ment+0.033
ed+0.031
abouts+0.030
Neg logit contributions
 Claus-0.039
 daddy-0.036
ingu-0.036
ll-0.035
ric-0.034
Token them
Token ID606
Feature activation-8.68e-01

Pos logit contributions
 moments+0.120
 inspection+0.105
ment+0.104
ed+0.097
abouts+0.096
Neg logit contributions
 Claus-0.147
 daddy-0.141
ingu-0.136
ric-0.133
ll-0.132
Token.
Token ID13
Feature activation-9.37e-02

Pos logit contributions
 Claus+0.050
 daddy+0.048
ingu+0.048
ric+0.047
 boo+0.047
Neg logit contributions
 moments-0.036
ment-0.032
 inspection-0.031
ed-0.030
edly-0.028
Token<|endoftext|>
Token ID50256
Feature activation-8.48e-03

Pos logit contributions
 Claus+0.005
 daddy+0.005
ingu+0.005
 boo+0.005
ric+0.005
Neg logit contributions
 moments-0.004
 inspection-0.004
ment-0.004
ed-0.004
abouts-0.004
TokenOnce
Token ID7454
Feature activation-2.84e+00

Pos logit contributions
 Claus+0.000
 daddy+0.000
ingu+0.000
 boo+0.000
ric+0.000
Neg logit contributions
 moments-0.000
 inspection-0.000
ment-0.000
ed-0.000
abouts-0.000
Token upon
Token ID2402
Feature activation+1.04e+00

Pos logit contributions
 Claus+0.192
 boo+0.179
ppa+0.173
ric+0.172
ingu+0.170
Neg logit contributions
 inspection-0.097
 moments-0.090
ment-0.079
ed-0.075
 Alicia-0.072
Token a
Token ID257
Feature activation+5.65e-02

Pos logit contributions
 moments+0.054
 inspection+0.048
ment+0.047
ed+0.044
abouts+0.044
Neg logit contributions
 daddy-0.052
 Claus-0.052
ingu-0.048
 boo-0.047
washer-0.046
Token time
Token ID640
Feature activation-2.26e-01

Pos logit contributions
 moments+0.003
 inspection+0.003
ment+0.002
abouts+0.002
ed+0.002
Neg logit contributions
 Claus-0.003
 daddy-0.003
ingu-0.003
washer-0.003
ric-0.003
Token,
Token ID11
Feature activation+3.40e-01

Pos logit contributions
 Claus+0.013
 daddy+0.013
ingu+0.012
ric+0.012
washer+0.012
Neg logit contributions
 moments-0.010
 inspection-0.008
ment-0.008
ed-0.008
abouts-0.008
Token there
Token ID612
Feature activation-1.73e-01

Pos logit contributions
 moments+0.018
 inspection+0.016
ment+0.015
ed+0.015
abouts+0.015
Neg logit contributions
 Claus-0.017
 daddy-0.016
ingu-0.016
ric-0.015
washer-0.015
Token kind
Token ID1611
Feature activation+2.81e+00

Pos logit contributions
 moments+0.030
ment+0.026
ed+0.026
 inspection+0.026
 Meg+0.024
Neg logit contributions
 Claus-0.022
ingu-0.021
 daddy-0.020
ric-0.020
oun-0.020
Token to
Token ID284
Feature activation+8.19e-01

Pos logit contributions
 moments+0.112
 inspection+0.096
ment+0.094
ed+0.088
abouts+0.087
Neg logit contributions
 Claus-0.171
 daddy-0.168
ingu-0.161
ric-0.157
washer-0.156
Token others
Token ID1854
Feature activation-1.47e+00

Pos logit contributions
 moments+0.047
 inspection+0.039
ment+0.039
 insects+0.038
 after+0.037
Neg logit contributions
 Claus-0.041
ingu-0.037
oun-0.037
washer-0.037
ll-0.034
Token.
Token ID13
Feature activation-7.78e-02

Pos logit contributions
ingu+0.097
 Claus+0.097
ric+0.093
oun+0.092
 boo+0.092
Neg logit contributions
 moments-0.051
ment-0.041
 after-0.039
ed-0.038
edly-0.035
Token<|endoftext|>
Token ID50256
Feature activation+5.94e-02

Pos logit contributions
 Claus+0.004
 daddy+0.004
ingu+0.004
washer+0.004
 boo+0.004
Neg logit contributions
 moments-0.004
 inspection-0.003
ment-0.003
ed-0.003
abouts-0.003
TokenOnce
Token ID7454
Feature activation-2.75e+00

Pos logit contributions
 moments+0.003
 inspection+0.002
ed+0.002
ment+0.002
abouts+0.002
Neg logit contributions
 Claus-0.003
 daddy-0.003
 boo-0.003
ingu-0.003
ric-0.003
Token upon
Token ID2402
Feature activation+9.83e-01

Pos logit contributions
 Claus+0.185
 boo+0.169
ric+0.166
ppa+0.164
ingu+0.163
Neg logit contributions
 inspection-0.095
 moments-0.091
ment-0.079
ed-0.076
 Alicia-0.071
Token a
Token ID257
Feature activation+1.14e-02

Pos logit contributions
 moments+0.051
 inspection+0.045
ment+0.044
ed+0.042
abouts+0.042
Neg logit contributions
 daddy-0.048
 Claus-0.048
ingu-0.045
 boo-0.044
ric-0.042
Token time
Token ID640
Feature activation-2.96e-01

Pos logit contributions
 moments+0.001
 inspection+0.001
ment+0.000
abouts+0.000
ed+0.000
Neg logit contributions
 Claus-0.001
 daddy-0.001
ingu-0.001
washer-0.001
ric-0.001
Token,
Token ID11
Feature activation+3.01e-01

Pos logit contributions
 Claus+0.018
 daddy+0.017
ingu+0.017
ric+0.016
washer+0.016
Neg logit contributions
 moments-0.012
 inspection-0.011
ment-0.010
ed-0.010
abouts-0.010
Token there
Token ID612
Feature activation-2.09e-01

Pos logit contributions
 moments+0.016
 inspection+0.014
ment+0.014
ed+0.013
abouts+0.013
Neg logit contributions
 Claus-0.015
 daddy-0.014
ingu-0.014
ric-0.013
washer-0.013
Token keeps
Token ID7622
Feature activation-2.35e-01

Pos logit contributions
 moments+0.000
 inspection+0.000
ment+0.000
ed+0.000
abouts+0.000
Neg logit contributions
 Claus-0.000
 daddy-0.000
ingu-0.000
washer-0.000
ric-0.000
Token laughing
Token ID14376
Feature activation-8.82e-01

Pos logit contributions
 Claus+0.012
ingu+0.012
ll+0.012
washer+0.012
oun+0.012
Neg logit contributions
 moments-0.011
 inspection-0.010
 Alicia-0.010
ed-0.009
 Meg-0.009
Token and
Token ID290
Feature activation+4.85e-01

Pos logit contributions
 daddy+0.041
 boo+0.039
 Claus+0.039
washer+0.037
 living+0.036
Neg logit contributions
 moments-0.045
 inspection-0.045
ment-0.040
growth-0.040
eways-0.039
Token watching
Token ID4964
Feature activation-1.46e+00

Pos logit contributions
 moments+0.029
 inspection+0.025
ment+0.025
ed+0.024
edly+0.023
Neg logit contributions
ingu-0.021
 Claus-0.021
 daddy-0.020
washer-0.019
oun-0.019
Token his
Token ID465
Feature activation-4.49e-01

Pos logit contributions
 daddy+0.078
 Claus+0.074
 boo+0.072
ingu+0.070
ric+0.068
Neg logit contributions
 moments-0.071
 inspection-0.064
ment-0.061
ed-0.059
abouts-0.058
Token car
Token ID1097
Feature activation-3.79e+00

Pos logit contributions
ppa+0.021
 Claus+0.020
ll+0.020
str+0.019
ingu+0.019
Neg logit contributions
 moments-0.025
abouts-0.021
ment-0.021
ed-0.021
 after-0.020
Token.
Token ID13
Feature activation-5.49e-02

Pos logit contributions
 Claus+0.178
 daddy+0.173
ingu+0.162
 boo+0.160
washer+0.159
Neg logit contributions
 moments-0.205
 inspection-0.185
ment-0.181
ed-0.172
abouts-0.170
Token He
Token ID679
Feature activation+7.80e-03

Pos logit contributions
 daddy+0.003
 Claus+0.003
ingu+0.003
ric+0.003
 boo+0.003
Neg logit contributions
 moments-0.002
 inspection-0.002
ment-0.002
ed-0.002
abouts-0.002
Token does
Token ID857
Feature activation+2.72e+00

Pos logit contributions
 moments+0.000
 inspection+0.000
ment+0.000
ed+0.000
abouts+0.000
Neg logit contributions
 Claus-0.000
 daddy-0.000
ingu-0.000
washer-0.000
ric-0.000
Token not
Token ID407
Feature activation-2.94e+00

Pos logit contributions
 moments+0.201
 inspection+0.187
ment+0.184
ed+0.177
abouts+0.177
Neg logit contributions
 Claus-0.074
 daddy-0.070
ingu-0.065
washer-0.060
ric-0.059
Token see
Token ID766
Feature activation+2.58e+00

Pos logit contributions
ingu+0.185
 Claus+0.185
 daddy+0.183
washer+0.179
ric+0.179
Neg logit contributions
 moments-0.100
 inspection-0.087
 after-0.080
ment-0.079
 Alicia-0.076
Token was
Token ID373
Feature activation+6.49e-01

Pos logit contributions
 Claus+0.016
 daddy+0.015
ingu+0.015
ric+0.014
washer+0.014
Neg logit contributions
 moments-0.010
 inspection-0.009
ment-0.008
ed-0.008
abouts-0.008
Token a
Token ID257
Feature activation-4.83e-02

Pos logit contributions
 moments+0.033
 inspection+0.030
ment+0.029
ed+0.027
abouts+0.027
Neg logit contributions
 daddy-0.033
 Claus-0.032
ingu-0.031
 boo-0.030
washer-0.029
Token boy
Token ID2933
Feature activation+7.52e-01

Pos logit contributions
ric+0.003
 fault+0.003
ll+0.002
 supervision+0.002
ingu+0.002
Neg logit contributions
 moments-0.002
Exc-0.002
 Alicia-0.002
 after-0.002
 insects-0.002
Token named
Token ID3706
Feature activation-2.66e+00

Pos logit contributions
 moments+0.039
ment+0.034
 inspection+0.033
 after+0.033
ed+0.032
Neg logit contributions
 Claus-0.036
ingu-0.035
 fault-0.033
oun-0.033
ric-0.032
Token Max
Token ID5436
Feature activation-3.55e+00

Pos logit contributions
ric+0.209
ppa+0.198
ich+0.197
 fault+0.195
onda+0.189
Neg logit contributions
 after-0.051
 Mia-0.042
 Meg-0.041
 inspection-0.041
 moments-0.040
Token who
Token ID508
Feature activation-7.63e+00

Pos logit contributions
 Claus+0.222
ingu+0.216
 daddy+0.213
ric+0.211
washer+0.209
Neg logit contributions
 moments-0.124
 inspection-0.108
ment-0.103
ed-0.098
 after-0.092
Token loved
Token ID6151
Feature activation-2.44e+00

Pos logit contributions
 Claus+0.359
 daddy+0.353
ric+0.350
ingu+0.344
ll+0.327
Neg logit contributions
 moments-0.399
ed-0.341
 inspection-0.340
ment-0.335
abouts-0.315
Token to
Token ID284
Feature activation+7.36e-01

Pos logit contributions
 Claus+0.166
uch+0.158
acey+0.158
ppa+0.157
inky+0.155
Neg logit contributions
 moments-0.081
 inspection-0.064
 after-0.061
 insects-0.060
ment-0.059
Token go
Token ID467
Feature activation+8.15e-01

Pos logit contributions
 moments+0.032
 inspection+0.028
ment+0.028
abouts+0.026
 Meg+0.025
Neg logit contributions
 Claus-0.041
ll-0.039
ppa-0.038
ingu-0.038
ric-0.038
Token on
Token ID319
Feature activation+5.74e-01

Pos logit contributions
 moments+0.038
 inspection+0.034
ment+0.033
ed+0.032
abouts+0.031
Neg logit contributions
 Claus-0.044
 daddy-0.042
ingu-0.041
ric-0.040
 boo-0.040
Token adventures
Token ID17545
Feature activation+2.87e+00

Pos logit contributions
 moments+0.025
ment+0.022
 inspection+0.022
ed+0.021
edly+0.020
Neg logit contributions
 Claus-0.033
 daddy-0.033
ingu-0.031
 boo-0.030
ric-0.030
Token mom
Token ID1995
Feature activation-3.07e-01

Pos logit contributions
 moments+0.104
 inspection+0.094
ment+0.094
ed+0.090
abouts+0.089
Neg logit contributions
 Claus-0.049
ingu-0.045
 daddy-0.043
ric-0.042
ll-0.041
Tokenmy
Token ID1820
Feature activation-3.40e+00

Pos logit contributions
 Claus+0.010
 daddy+0.010
ingu+0.009
 boo+0.009
ric+0.009
Neg logit contributions
 moments-0.021
 inspection-0.019
ment-0.019
ed-0.018
abouts-0.018
Token coming
Token ID2406
Feature activation-2.97e+00

Pos logit contributions
 Claus+0.188
 daddy+0.185
ingu+0.178
ric+0.171
washer+0.171
Neg logit contributions
 moments-0.154
 inspection-0.136
ment-0.132
ed-0.126
abouts-0.124
Token from
Token ID422
Feature activation-1.01e+00

Pos logit contributions
 daddy+0.148
 Claus+0.140
 boo+0.128
washer+0.123
ll+0.123
Neg logit contributions
 moments-0.159
ment-0.140
abouts-0.139
 inspection-0.137
edly-0.129
Token the
Token ID262
Feature activation-6.52e-01

Pos logit contributions
 daddy+0.045
 Claus+0.041
 boo+0.039
 living+0.038
 iron+0.037
Neg logit contributions
 moments-0.055
ment-0.052
ed-0.051
abouts-0.050
 inspection-0.049
Token living
Token ID2877
Feature activation-1.05e+01

Pos logit contributions
 Claus+0.029
oun+0.028
ll+0.028
ingu+0.028
ric+0.027
Neg logit contributions
 moments-0.037
 inspection-0.031
ment-0.030
 insects-0.029
abouts-0.029
Token room
Token ID2119
Feature activation-2.98e+00

Pos logit contributions
 Claus+0.276
 daddy+0.276
ingu+0.242
washer+0.231
 boo+0.226
Neg logit contributions
 moments-0.771
 inspection-0.719
ment-0.707
abouts-0.686
ed-0.684
Token.
Token ID13
Feature activation-2.23e-01

Pos logit contributions
 Claus+0.154
 daddy+0.153
washer+0.142
ingu+0.140
 boo+0.137
Neg logit contributions
 moments-0.143
 inspection-0.128
ment-0.125
abouts-0.120
ed-0.118
Token She
Token ID1375
Feature activation+1.37e+00

Pos logit contributions
 daddy+0.015
 Claus+0.014
 boo+0.014
 living+0.013
washer+0.013
Neg logit contributions
 moments-0.008
ment-0.007
abouts-0.007
 inspection-0.006
ed-0.006
Token quickly
Token ID2952
Feature activation+3.40e-01

Pos logit contributions
 moments+0.065
ment+0.059
 inspection+0.057
abouts+0.056
iece+0.054
Neg logit contributions
 daddy-0.073
 Claus-0.073
 boo-0.068
washer-0.066
ingu-0.065
Token got
Token ID1392
Feature activation-7.96e-01

Pos logit contributions
 moments+0.019
ment+0.017
 inspection+0.017
abouts+0.017
edly+0.016
Neg logit contributions
 Claus-0.015
 daddy-0.015
 boo-0.014
washer-0.014
 iron-0.013
Token sp
Token ID599
Feature activation-8.88e-01

Pos logit contributions
 moments+0.023
ment+0.020
 inspection+0.019
ed+0.019
abouts+0.018
Neg logit contributions
 Claus-0.021
ric-0.021
ingu-0.020
ll-0.020
oun-0.020
Tokenoons
Token ID13022
Feature activation-5.88e-01

Pos logit contributions
 Claus+0.048
 daddy+0.046
 boo+0.043
ric+0.043
ingu+0.043
Neg logit contributions
 moments-0.042
 inspection-0.038
ment-0.038
ed-0.036
abouts-0.036
Token inside
Token ID2641
Feature activation-1.73e+00

Pos logit contributions
 Claus+0.035
 daddy+0.034
ingu+0.034
ric+0.033
 boo+0.033
Neg logit contributions
 moments-0.024
 inspection-0.021
ment-0.020
ed-0.020
abouts-0.018
Token the
Token ID262
Feature activation-7.40e-01

Pos logit contributions
 Claus+0.096
 daddy+0.093
ingu+0.090
ric+0.087
 boo+0.087
Neg logit contributions
 moments-0.079
 inspection-0.069
ment-0.068
ed-0.064
abouts-0.063
Token dish
Token ID9433
Feature activation-3.15e+00

Pos logit contributions
ric+0.028
ppa+0.027
 Claus+0.026
ich+0.025
str+0.025
Neg logit contributions
 moments-0.049
ed-0.040
 after-0.040
 passages-0.039
 inspection-0.039
Tokenwasher
Token ID45146
Feature activation-8.42e+00

Pos logit contributions
 boo+0.051
 Claus+0.049
ric+0.046
ppa+0.040
 daddy+0.040
Neg logit contributions
 moments-0.254
ed-0.247
ment-0.244
 inspection-0.234
edly-0.229
Token.
Token ID13
Feature activation-2.26e-01

Pos logit contributions
 Claus+0.524
ingu+0.505
ric+0.503
 daddy+0.495
oun+0.492
Neg logit contributions
 moments-0.324
ed-0.275
ment-0.271
 inspection-0.265
edly-0.241
Token She
Token ID1375
Feature activation+1.22e+00

Pos logit contributions
 daddy+0.015
 Claus+0.014
ingu+0.013
 boo+0.013
 sewing+0.013
Neg logit contributions
 moments-0.009
 inspection-0.007
ment-0.007
abouts-0.007
ed-0.006
Token was
Token ID373
Feature activation+3.72e-01

Pos logit contributions
 moments+0.064
 inspection+0.056
ment+0.055
ed+0.054
abouts+0.053
Neg logit contributions
 Claus-0.060
 daddy-0.058
ingu-0.055
ric-0.054
 boo-0.053
Token careful
Token ID8161
Feature activation-8.20e-01

Pos logit contributions
 moments+0.021
ment+0.018
ed+0.018
 inspection+0.018
 Alicia+0.017
Neg logit contributions
 Claus-0.017
ingu-0.016
oun-0.016
ll-0.015
 daddy-0.015
Token not
Token ID407
Feature activation-2.96e+00

Pos logit contributions
 Claus+0.032
 daddy+0.030
ingu+0.030
 boo+0.028
ric+0.028
Neg logit contributions
 moments-0.051
 inspection-0.047
ment-0.046
ed-0.044
abouts-0.043
Token't
Token ID470
Feature activation-2.81e+00

Pos logit contributions
 moments+0.102
 inspection+0.093
ed+0.091
ment+0.090
 Alicia+0.088
Neg logit contributions
 Claus-0.063
ingu-0.060
 daddy-0.060
ric-0.057
 boo-0.057
Token worry
Token ID5490
Feature activation-8.91e-01

Pos logit contributions
 Claus+0.149
ingu+0.146
washer+0.139
acey+0.136
ophone+0.129
Neg logit contributions
 moments-0.135
 after-0.121
 inspection-0.118
 tones-0.114
ment-0.113
Token,
Token ID11
Feature activation+5.00e-01

Pos logit contributions
 Claus+0.059
ric+0.056
ingu+0.055
 daddy+0.054
ll+0.054
Neg logit contributions
 moments-0.032
 inspection-0.027
ment-0.026
ed-0.024
abouts-0.023
Token we
Token ID356
Feature activation-1.13e+00

Pos logit contributions
 moments+0.028
 inspection+0.024
ment+0.024
 Meg+0.022
 after+0.022
Neg logit contributions
 Claus-0.024
ingu-0.022
ric-0.022
ll-0.021
washer-0.020
Token can
Token ID460
Feature activation-9.16e-01

Pos logit contributions
 Claus+0.058
ingu+0.056
oun+0.055
 daddy+0.055
ich+0.055
Neg logit contributions
 moments-0.050
ed-0.047
 after-0.047
 inspection-0.041
 tones-0.039
Token repair
Token ID9185
Feature activation-8.15e+00

Pos logit contributions
 Claus+0.050
ingu+0.049
nam+0.048
ppa+0.047
str+0.047
Neg logit contributions
 after-0.031
 moments-0.031
 behold-0.029
 tones-0.028
oos-0.028
Token it
Token ID340
Feature activation+1.61e+00

Pos logit contributions
 Claus+0.497
ingu+0.472
ll+0.467
 daddy+0.461
washer+0.452
Neg logit contributions
 moments-0.340
ment-0.279
 inspection-0.275
ed-0.265
abouts-0.258
Token!"
Token ID2474
Feature activation+7.84e-01

Pos logit contributions
 moments+0.072
ed+0.064
 inspection+0.063
ment+0.062
abouts+0.059
Neg logit contributions
 Claus-0.086
 daddy-0.084
ric-0.083
ingu-0.083
 boo-0.079
Token Lily
Token ID20037
Feature activation+7.76e-01

Pos logit contributions
 moments+0.035
 inspection+0.031
ment+0.030
ed+0.029
abouts+0.028
Neg logit contributions
 Claus-0.044
 daddy-0.042
ingu-0.042
ric-0.041
 boo-0.040
Token was
Token ID373
Feature activation+5.20e-01

Pos logit contributions
 moments+0.036
 inspection+0.032
ment+0.031
abouts+0.029
ed+0.029
Neg logit contributions
 Claus-0.042
 daddy-0.042
ingu-0.040
washer-0.039
 boo-0.038
Token happy
Token ID3772
Feature activation+3.09e-01

Pos logit contributions
 moments+0.023
ed+0.019
ment+0.019
 widened+0.018
edly+0.018
Neg logit contributions
 Claus-0.029
ingu-0.028
oun-0.028
ll-0.027
ric-0.027
Token sat
Token ID3332
Feature activation-1.76e+00

Pos logit contributions
 Claus+0.063
 daddy+0.061
ingu+0.059
ric+0.057
 boo+0.057
Neg logit contributions
 moments-0.049
 inspection-0.043
ment-0.041
ed-0.040
abouts-0.039
Token down
Token ID866
Feature activation+1.04e+00

Pos logit contributions
 daddy+0.077
 Claus+0.076
ll+0.071
washer+0.068
ich+0.067
Neg logit contributions
 moments-0.101
 inspection-0.096
growth-0.090
abouts-0.088
Exc-0.085
Token and
Token ID290
Feature activation+4.03e-01

Pos logit contributions
 moments+0.057
 inspection+0.051
ment+0.049
abouts+0.048
 Alicia+0.046
Neg logit contributions
 Claus-0.048
 daddy-0.048
washer-0.045
ll-0.044
 cube-0.043
Token talked
Token ID6619
Feature activation+1.79e-01

Pos logit contributions
 moments+0.019
 inspection+0.017
ment+0.017
ed+0.016
abouts+0.016
Neg logit contributions
 Claus-0.021
 daddy-0.021
ingu-0.020
washer-0.019
 boo-0.019
Token about
Token ID546
Feature activation-5.81e-01

Pos logit contributions
 moments+0.009
 inspection+0.009
ment+0.008
abouts+0.008
 Alicia+0.008
Neg logit contributions
 daddy-0.008
 Claus-0.008
washer-0.007
ingu-0.007
ll-0.007
Token who
Token ID508
Feature activation-7.83e+00

Pos logit contributions
 Claus+0.036
ingu+0.034
ppa+0.033
ll+0.033
uch+0.033
Neg logit contributions
 moments-0.025
 inspection-0.021
ment-0.020
 insects-0.019
abouts-0.018
Token would
Token ID561
Feature activation-2.26e-01

Pos logit contributions
 Claus+0.439
ingu+0.431
ric+0.431
 daddy+0.420
oun+0.418
Neg logit contributions
 moments-0.342
 inspection-0.288
ed-0.288
ment-0.285
 Alicia-0.260
Token be
Token ID307
Feature activation+3.24e-01

Pos logit contributions
ingu+0.012
 Claus+0.012
oun+0.011
washer+0.011
 daddy+0.011
Neg logit contributions
 moments-0.010
 inspection-0.009
 after-0.008
ment-0.008
 behold-0.008
Token the
Token ID262
Feature activation-6.54e-01

Pos logit contributions
 moments+0.018
ment+0.016
 inspection+0.015
ed+0.015
 Alicia+0.015
Neg logit contributions
 Claus-0.014
ingu-0.014
 daddy-0.014
oun-0.014
ric-0.013
Token leader
Token ID3554
Feature activation+9.55e-01

Pos logit contributions
 Claus+0.029
ric+0.029
oun+0.028
ingu+0.027
ppa+0.027
Neg logit contributions
 moments-0.037
 insects-0.032
 after-0.030
 vines-0.029
 Alicia-0.028
Token of
Token ID286
Feature activation-1.30e+00

Pos logit contributions
 moments+0.032
ment+0.025
 after+0.025
ed+0.025
 inspection+0.023
Neg logit contributions
 Claus-0.064
ingu-0.064
oun-0.062
ppa-0.061
 daddy-0.061