TOP ACTIVATIONS
MAX = 0.212

some things that cannot be wished for and he had learned
wait too long so it wished to grow quickly .
all he could do was wish that something would lift him
about what he wanted to wish for . He had so
you have to do is wish for it ."
too . Maybe we can wish to play in the water
big surprises if it was wished on with a pure heart
about what she wanted to wish for . Then , she
girl . What do you wish to gain ?" Jane
must be careful what you wish for ." Tim
She wondered what she could wish for . She thought of
't let yourself become too dependent on one thing . It
't tell me what you wish for . It is a
She wondered what she would wish for with her wand .
one wish . Whatever you wish for , it will come
to be careful what you wish for . Sometimes , wishes
is coming to town ! Won 't that be fun ?"
was thinking about how she wished her life would be different
gle eful , " I Won !" Bob felt
fish 's shiny scales and wished he had some too .

MIN ACTIVATIONS
MIN = -0.201

him and they cl apped their hands . They thanked Tom
! <|endoftext|> John looked out his window and saw a bright
she marched and cl apped their hands .
The little boy cl apped his hands and said , "
. Tim my cl apped his hands and cheered .
dad smiled and cl apped their hands . They said ,
The baby cl apped his hands and smiled . They
bigger . He cl apped his hands and watched them tw
. John cl apped his hands and smiled , proud
He cl apped his hands and wh irled around
Sam cl apped his hands . " Great job
Jen and Ben cl apped their hands and sang along .
They laugh and cl ap their hands . They are very
The little boy cl apped his hands and ran to the
applaud . They cl apped their hands and paws , and
Tom my cl apped his hands happily and began to
Jo jo cl apped his hands and danced along as
They cl apped their hands and said , "
. Tim my cl apped his hands too and smiled .
prints . Lucky cl apped his paws in excitement and cheered

INTERVAL 0.108 - 0.212
CONTAINS 3.718%

They kissed and smiled and played for a while . They
see the world and have adventures . She waved goodbye to
realized that they could only succeed if they worked together -
her purple crown and remembered how the knight saved her .
were twins who liked to play outside . They had many

INTERVAL 0.005 - 0.108
CONTAINS 51.927%

The little girl was safe . She was
, she was not happy . She saw toys scattered everywhere
the world . From that day on , Lily would always
. What do you want to do while we wait ?"
take a better look . " What could this be ?"

INTERVAL -0.098 - 0.005
CONTAINS 32.013%

a time Bob was walking in a me adow when he
. " Are you ready to go , Lily
They have fun with the wheat . But they do not
. He is mine ." They started to argue .
her rubber duck ie . One day , Lily 's mom

INTERVAL -0.201 - -0.098
CONTAINS 12.342%

man was happy and let the bear in . The bear
The moral of the story : don 't eat
your mistake ." Sam and Mia said sorry to
. Her mom explained that the trap was made to catch
Buddy . One day , Buddy hurt his paw while they
Token some
Token ID617
Feature activation-3.14e-02

Pos logit contributions
ig+0.036
iper+0.036
 fort+0.034
ches+0.034
 web+0.033
Neg logit contributions
all-0.020
 him-0.019
 Mike-0.018
 Joey-0.017
no-0.017
Token things
Token ID1243
Feature activation+3.87e-02

Pos logit contributions
ig+0.055
iper+0.055
ches+0.052
 fort+0.050
aj+0.050
Neg logit contributions
all-0.045
 him-0.043
uts-0.042
no-0.042
Welcome-0.041
Token that
Token ID326
Feature activation+2.60e-03

Pos logit contributions
all+0.049
uts+0.046
 Mike+0.042
 Crab+0.039
Welcome+0.039
Neg logit contributions
 fort-0.078
ig-0.077
iper-0.076
ches-0.075
 web-0.075
Token cannot
Token ID2314
Feature activation+7.63e-02

Pos logit contributions
all+0.004
uts+0.004
 Mike+0.004
 Crab+0.004
 Joey+0.004
Neg logit contributions
 fort-0.004
ig-0.004
iper-0.004
ches-0.004
 web-0.004
Token be
Token ID307
Feature activation-7.98e-03

Pos logit contributions
all+0.144
uts+0.138
 Mike+0.131
 Crab+0.126
Welcome+0.126
Neg logit contributions
 fort-0.107
ches-0.101
 web-0.100
ig-0.100
iper-0.096
Token wished
Token ID16555
Feature activation+2.12e-01

Pos logit contributions
ig+0.014
 fort+0.014
iper+0.014
 closet+0.013
ches+0.013
Neg logit contributions
all-0.012
uts-0.012
 Mike-0.011
 Joey-0.010
 Crab-0.010
Token for
Token ID329
Feature activation+3.56e-02

Pos logit contributions
all+0.256
uts+0.235
 Mike+0.217
 Joey+0.202
no+0.198
Neg logit contributions
 fort-0.440
ig-0.435
iper-0.429
 web-0.427
ches-0.424
Token and
Token ID290
Feature activation-1.65e-02

Pos logit contributions
all+0.029
uts+0.027
 Mike+0.022
Welcome+0.021
 Crab+0.020
Neg logit contributions
 fort-0.088
ig-0.086
iper-0.085
ches-0.085
 web-0.085
Token he
Token ID339
Feature activation-7.33e-02

Pos logit contributions
 fort+0.032
ig+0.031
ches+0.031
iper+0.031
 web+0.031
Neg logit contributions
all-0.022
uts-0.020
 Mike-0.019
 Crab-0.018
Welcome-0.018
Token had
Token ID550
Feature activation+1.15e-02

Pos logit contributions
 fort+0.147
eh+0.143
 closet+0.141
aj+0.138
iper+0.137
Neg logit contributions
all-0.097
uts-0.088
't-0.082
 him-0.082
 Mike-0.080
Token learned
Token ID4499
Feature activation+9.45e-02

Pos logit contributions
all+0.013
uts+0.011
 Mike+0.010
no+0.010
 Crab+0.010
Neg logit contributions
 fort-0.026
ig-0.026
ches-0.025
iper-0.025
 web-0.024
Token wait
Token ID4043
Feature activation+1.35e-01

Pos logit contributions
all+0.033
uts+0.033
 Mike+0.031
Welcome+0.030
anes+0.030
Neg logit contributions
 fort-0.028
 web-0.027
ig-0.027
ches-0.027
iper-0.026
Token too
Token ID1165
Feature activation+3.83e-02

Pos logit contributions
all+0.168
uts+0.159
 Mike+0.144
 Crab+0.139
Welcome+0.139
Neg logit contributions
 fort-0.276
ig-0.268
ches-0.265
iper-0.263
 web-0.262
Token long
Token ID890
Feature activation+2.18e-02

Pos logit contributions
all+0.067
uts+0.065
 Mike+0.062
anes+0.062
 Cr+0.061
Neg logit contributions
 fort-0.058
ig-0.056
 web-0.056
ches-0.054
iper-0.054
Token so
Token ID523
Feature activation+3.33e-02

Pos logit contributions
all+0.032
Welcome+0.032
anes+0.030
 Crab+0.030
Joe+0.030
Neg logit contributions
ches-0.037
ets-0.035
 fort-0.035
ig-0.034
iper-0.034
Token it
Token ID340
Feature activation-4.94e-02

Pos logit contributions
all+0.040
uts+0.038
anes+0.034
Welcome+0.032
unch+0.031
Neg logit contributions
 fort-0.069
 web-0.067
ig-0.067
iper-0.065
ches-0.065
Token wished
Token ID16555
Feature activation+2.09e-01

Pos logit contributions
iper+0.080
 fort+0.079
ig+0.079
 closet+0.077
aj+0.072
Neg logit contributions
all-0.079
uts-0.074
Welcome-0.067
 Hipp-0.067
 him-0.067
Token to
Token ID284
Feature activation+2.94e-02

Pos logit contributions
all+0.302
uts+0.282
 Mike+0.263
 Crab+0.249
 Joey+0.248
Neg logit contributions
 fort-0.386
ig-0.380
iper-0.375
ches-0.373
 web-0.366
Token grow
Token ID1663
Feature activation+1.13e-01

Pos logit contributions
all+0.052
uts+0.049
 Mike+0.046
 Crab+0.045
Welcome+0.045
Neg logit contributions
 fort-0.045
ig-0.044
ches-0.043
iper-0.043
 web-0.042
Token quickly
Token ID2952
Feature activation+4.53e-02

Pos logit contributions
all+0.160
uts+0.148
 Mike+0.136
Welcome+0.132
 Joey+0.132
Neg logit contributions
 fort-0.209
ig-0.206
iper-0.205
ches-0.202
 web-0.199
Token.
Token ID13
Feature activation+7.38e-02

Pos logit contributions
all+0.061
uts+0.056
 Mike+0.054
 Cr+0.052
 Crab+0.052
Neg logit contributions
 fort-0.090
 web-0.086
ches-0.086
ig-0.085
 closet-0.085
Token
Token ID198
Feature activation+3.29e-02

Pos logit contributions
all+0.099
uts+0.092
 Mike+0.088
 Joey+0.083
 Crab+0.082
Neg logit contributions
ig-0.147
 fort-0.146
ches-0.142
iper-0.140
 web-0.138
Token all
Token ID477
Feature activation-1.51e-02

Pos logit contributions
 fort+0.054
iper+0.054
ig+0.054
ches+0.051
 closet+0.050
Neg logit contributions
all-0.042
 Mike-0.039
 him-0.038
 Joey-0.038
uts-0.037
Token he
Token ID339
Feature activation-9.11e-02

Pos logit contributions
 fort+0.034
iper+0.034
ig+0.033
ches+0.033
 web+0.033
Neg logit contributions
all-0.016
 Mike-0.014
uts-0.013
 Joey-0.013
no-0.012
Token could
Token ID714
Feature activation+8.03e-02

Pos logit contributions
 fort+0.186
iper+0.181
 closet+0.178
 clinic+0.176
aj+0.174
Neg logit contributions
all-0.105
 him-0.103
no-0.102
 it-0.102
 Mike-0.101
Token do
Token ID466
Feature activation+8.75e-02

Pos logit contributions
all+0.146
Welcome+0.137
uts+0.135
 Mike+0.132
 Cr+0.131
Neg logit contributions
 fort-0.115
 web-0.111
ches-0.110
ig-0.110
iper-0.106
Token was
Token ID373
Feature activation-8.37e-03

Pos logit contributions
all+0.089
uts+0.079
 Mike+0.073
no+0.068
 Crab+0.066
Neg logit contributions
 fort-0.200
iper-0.200
ig-0.196
ches-0.195
 closet-0.192
Token wish
Token ID4601
Feature activation+2.08e-01

Pos logit contributions
 fort+0.014
ig+0.014
iper+0.014
ches+0.013
 web+0.013
Neg logit contributions
all-0.013
uts-0.013
 Mike-0.012
 Crab-0.011
Welcome-0.011
Token that
Token ID326
Feature activation+2.14e-02

Pos logit contributions
all+0.245
uts+0.229
 Mike+0.205
no+0.190
 Joey+0.188
Neg logit contributions
 fort-0.435
ig-0.434
iper-0.432
 web-0.421
ches-0.420
Token something
Token ID1223
Feature activation+1.76e-02

Pos logit contributions
all+0.024
uts+0.023
 Mike+0.020
Welcome+0.019
 Crab+0.019
Neg logit contributions
 fort-0.046
ig-0.045
ches-0.044
iper-0.044
 web-0.044
Token would
Token ID561
Feature activation+6.86e-02

Pos logit contributions
all+0.027
uts+0.026
 Mike+0.025
 Joey+0.025
no+0.025
Neg logit contributions
iper-0.031
ig-0.030
 fort-0.029
 closet-0.029
 necks-0.028
Token lift
Token ID10303
Feature activation+1.28e-01

Pos logit contributions
all+0.107
uts+0.102
 Mike+0.095
Welcome+0.090
anes+0.090
Neg logit contributions
 fort-0.119
 web-0.113
ches-0.113
ig-0.111
iper-0.110
Token him
Token ID683
Feature activation-8.80e-02

Pos logit contributions
all+0.055
uts+0.037
 Mike+0.034
 Joey+0.027
 him+0.026
Neg logit contributions
 fort-0.365
ig-0.361
iper-0.358
 web-0.358
 closet-0.353
Token about
Token ID546
Feature activation+5.24e-02

Pos logit contributions
all+0.106
uts+0.097
 Mike+0.087
 Crab+0.082
Welcome+0.081
Neg logit contributions
 fort-0.231
ig-0.228
ches-0.225
iper-0.224
 web-0.222
Token what
Token ID644
Feature activation+4.02e-02

Pos logit contributions
uts+0.075
all+0.072
anes+0.065
amb+0.064
Welcome+0.064
Neg logit contributions
 closet-0.091
 fort-0.091
 room-0.091
 web-0.090
ig-0.090
Token he
Token ID339
Feature activation-5.64e-02

Pos logit contributions
all+0.050
uts+0.046
Welcome+0.039
anes+0.039
unch+0.038
Neg logit contributions
 fort-0.081
 closet-0.079
ig-0.077
iper-0.077
 room-0.077
Token wanted
Token ID2227
Feature activation+1.42e-01

Pos logit contributions
 fort+0.077
ig+0.074
iper+0.072
 web+0.071
ches+0.068
Neg logit contributions
all-0.112
uts-0.103
 Mike-0.100
Welcome-0.099
 Crab-0.097
Token to
Token ID284
Feature activation+2.58e-02

Pos logit contributions
all+0.182
uts+0.176
 Mike+0.157
 Cr+0.155
 Crab+0.154
Neg logit contributions
 fort-0.276
ches-0.271
ig-0.269
iper-0.265
 closet-0.262
Token wish
Token ID4601
Feature activation+2.08e-01

Pos logit contributions
all+0.048
uts+0.047
Welcome+0.047
 Cr+0.045
 Hipp+0.045
Neg logit contributions
 web-0.034
 fort-0.033
ig-0.033
ches-0.032
iper-0.032
Token for
Token ID329
Feature activation+3.55e-02

Pos logit contributions
all+0.291
uts+0.272
 Mike+0.253
Welcome+0.252
 Crab+0.251
Neg logit contributions
 fort-0.387
ig-0.376
ches-0.374
iper-0.364
 web-0.363
Token.
Token ID13
Feature activation+6.07e-02

Pos logit contributions
uts+0.047
all+0.047
anes+0.042
Welcome+0.041
ous+0.040
Neg logit contributions
 fort-0.068
 closet-0.066
ig-0.065
ches-0.064
 web-0.064
Token He
Token ID679
Feature activation-9.67e-02

Pos logit contributions
all+0.088
uts+0.082
no+0.078
ous+0.078
ful+0.076
Neg logit contributions
 fort-0.104
 closet-0.103
iper-0.100
 room-0.097
ig-0.097
Token had
Token ID550
Feature activation+3.86e-04

Pos logit contributions
 fort+0.181
ig+0.175
iper+0.169
 web+0.164
ches+0.162
Neg logit contributions
all-0.145
 Mike-0.127
uts-0.127
 Crab-0.120
 rep-0.118
Token so
Token ID523
Feature activation+9.86e-03

Pos logit contributions
all+0.001
uts+0.001
 Mike+0.001
 Crab+0.001
no+0.001
Neg logit contributions
 fort-0.001
ig-0.001
ches-0.001
iper-0.001
 web-0.001
Token you
Token ID345
Feature activation-7.76e-02

Pos logit contributions
all+0.043
 Joey+0.037
 Mike+0.037
uts+0.037
 him+0.036
Neg logit contributions
 fort-0.077
iper-0.074
ig-0.073
 closet-0.073
aj-0.072
Token have
Token ID423
Feature activation+4.62e-03

Pos logit contributions
 fort+0.142
ig+0.135
eh+0.133
iper+0.132
 closet+0.130
Neg logit contributions
all-0.114
uts-0.106
't-0.098
 Mike-0.097
 Joey-0.096
Token to
Token ID284
Feature activation+1.39e-04

Pos logit contributions
all+0.005
uts+0.005
 Mike+0.004
 Crab+0.004
 Joey+0.004
Neg logit contributions
 fort-0.010
ig-0.010
iper-0.010
ches-0.010
eh-0.009
Token do
Token ID466
Feature activation+8.57e-02

Pos logit contributions
all+0.000
uts+0.000
 Mike+0.000
 Crab+0.000
 Joey+0.000
Neg logit contributions
 fort-0.000
ig-0.000
ches-0.000
iper-0.000
 web-0.000
Token is
Token ID318
Feature activation-1.25e-02

Pos logit contributions
all+0.115
uts+0.110
 Mike+0.102
 him+0.095
 Joey+0.094
Neg logit contributions
 fort-0.165
iper-0.161
ig-0.160
eh-0.156
 web-0.154
Token wish
Token ID4601
Feature activation+2.07e-01

Pos logit contributions
 fort+0.022
ig+0.021
iper+0.021
ches+0.021
 web+0.020
Neg logit contributions
all-0.020
uts-0.019
 Mike-0.017
 Crab-0.017
 Joey-0.017
Token for
Token ID329
Feature activation+3.06e-02

Pos logit contributions
all+0.315
uts+0.296
 Mike+0.283
 Crab+0.278
Welcome+0.276
Neg logit contributions
 fort-0.362
ig-0.353
ches-0.350
iper-0.343
 web-0.341
Token it
Token ID340
Feature activation-4.36e-02

Pos logit contributions
all+0.039
uts+0.038
 Mike+0.032
anes+0.032
Welcome+0.032
Neg logit contributions
 fort-0.061
 web-0.060
ig-0.059
iper-0.058
 closet-0.058
Token."
Token ID526
Feature activation+7.07e-02

Pos logit contributions
 fort+0.093
ches+0.091
ig+0.090
iper+0.089
 web+0.088
Neg logit contributions
all-0.049
uts-0.045
 Mike-0.042
 Crab-0.040
no-0.040
Token
Token ID198
Feature activation+1.78e-02

Pos logit contributions
all+0.076
uts+0.067
ous+0.063
Welcome+0.059
 returning+0.058
Neg logit contributions
 fort-0.155
 closet-0.150
ig-0.148
 web-0.146
ches-0.146
Token
Token ID198
Feature activation+1.71e-02

Pos logit contributions
all+0.018
uts+0.016
 Crab+0.014
 Mike+0.014
 Cr+0.013
Neg logit contributions
 fort-0.041
ches-0.040
ig-0.040
 web-0.040
iper-0.039
Token too
Token ID1165
Feature activation+3.46e-02

Pos logit contributions
all+0.249
uts+0.226
 Cr+0.226
no+0.225
 Crab+0.224
Neg logit contributions
 fort-0.331
ig-0.310
 closet-0.305
ches-0.300
 web-0.298
Token.
Token ID13
Feature activation+6.82e-02

Pos logit contributions
all+0.057
 Cr+0.056
that+0.054
anes+0.054
uts+0.053
Neg logit contributions
 fort-0.058
 room-0.050
 closet-0.050
 tent-0.048
 web-0.048
Token Maybe
Token ID6674
Feature activation+8.85e-02

Pos logit contributions
all+0.105
uts+0.100
 Mike+0.090
no+0.090
 Crab+0.087
Neg logit contributions
 fort-0.120
ig-0.114
 web-0.113
iper-0.113
 closet-0.113
Token we
Token ID356
Feature activation-2.17e-02

Pos logit contributions
uts+0.125
all+0.125
anes+0.112
unch+0.106
ous+0.103
Neg logit contributions
 fort-0.170
 closet-0.163
 room-0.157
ig-0.156
 web-0.151
Token can
Token ID460
Feature activation+1.03e-01

Pos logit contributions
 fort+0.030
ig+0.029
iper+0.029
ches+0.028
 web+0.028
Neg logit contributions
all-0.041
uts-0.040
 Mike-0.037
 Crab-0.036
Welcome-0.036
Token wish
Token ID4601
Feature activation+2.06e-01

Pos logit contributions
all+0.203
uts+0.200
Welcome+0.190
no+0.186
 Mike+0.186
Neg logit contributions
 fort-0.138
ig-0.129
 web-0.128
 closet-0.128
ches-0.127
Token to
Token ID284
Feature activation+2.13e-02

Pos logit contributions
all+0.348
uts+0.333
Welcome+0.311
 Crab+0.310
no+0.307
Neg logit contributions
 fort-0.330
ches-0.313
ig-0.308
 web-0.301
 closet-0.297
Token play
Token ID711
Feature activation+1.18e-01

Pos logit contributions
all+0.041
uts+0.040
 Mike+0.037
 Joey+0.036
 Crab+0.035
Neg logit contributions
 fort-0.029
ig-0.028
 web-0.028
 closet-0.027
ches-0.027
Token in
Token ID287
Feature activation-2.49e-02

Pos logit contributions
all+0.161
uts+0.154
 Mike+0.140
 Joey+0.135
no+0.131
Neg logit contributions
 fort-0.230
ig-0.222
 web-0.218
ches-0.218
 closet-0.214
Token the
Token ID262
Feature activation-1.42e-01

Pos logit contributions
 fort+0.047
ig+0.045
ches+0.045
 web+0.044
iper+0.044
Neg logit contributions
all-0.036
uts-0.034
 Mike-0.031
 Crab-0.030
Welcome-0.029
Token water
Token ID1660
Feature activation+5.04e-02

Pos logit contributions
iper+0.222
ches+0.218
ig+0.206
 fort+0.201
 web+0.194
Neg logit contributions
all-0.245
 Mike-0.229
uts-0.228
Welcome-0.226
 Crab-0.226
Token big
Token ID1263
Feature activation-2.27e-02

Pos logit contributions
all+0.131
uts+0.120
 Mike+0.114
 Joey+0.108
 Crab+0.107
Neg logit contributions
 fort-0.205
ig-0.202
ches-0.196
iper-0.195
 web-0.193
Token surprises
Token ID24072
Feature activation+1.00e-01

Pos logit contributions
 fort+0.036
ig+0.035
ches+0.035
iper+0.035
 web+0.034
Neg logit contributions
all-0.038
uts-0.035
 Mike-0.034
 Crab-0.033
 Joey-0.032
Token if
Token ID611
Feature activation+7.30e-02

Pos logit contributions
all+0.125
uts+0.118
 Mike+0.108
 Crab+0.105
 Cr+0.104
Neg logit contributions
 fort-0.202
ig-0.195
ches-0.195
iper-0.192
 web-0.190
Token it
Token ID340
Feature activation-3.80e-02

Pos logit contributions
all+0.081
uts+0.075
 Mike+0.067
 Crab+0.063
Welcome+0.062
Neg logit contributions
 fort-0.158
ig-0.155
iper-0.153
ches-0.153
 web-0.151
Token was
Token ID373
Feature activation+4.99e-03

Pos logit contributions
 fort+0.055
ig+0.054
iper+0.053
 closet+0.051
 web+0.051
Neg logit contributions
all-0.071
uts-0.067
 Mike-0.062
Welcome-0.061
 Joey-0.060
Token wished
Token ID16555
Feature activation+2.06e-01

Pos logit contributions
all+0.008
uts+0.008
 Mike+0.007
 Crab+0.007
Welcome+0.007
Neg logit contributions
 fort-0.008
ig-0.008
ches-0.008
iper-0.008
 web-0.008
Token on
Token ID319
Feature activation+3.29e-02

Pos logit contributions
all+0.295
uts+0.278
 Mike+0.258
 Crab+0.249
Welcome+0.246
Neg logit contributions
 fort-0.378
ig-0.370
ches-0.365
iper-0.364
 web-0.359
Token with
Token ID351
Feature activation+5.42e-02

Pos logit contributions
all+0.042
uts+0.039
 Mike+0.036
 Crab+0.034
Welcome+0.034
Neg logit contributions
 fort-0.066
ig-0.065
ches-0.064
iper-0.064
 web-0.063
Token a
Token ID257
Feature activation-6.87e-02

Pos logit contributions
all+0.067
uts+0.064
 Mike+0.056
 Crab+0.055
Welcome+0.054
Neg logit contributions
 fort-0.109
ig-0.107
iper-0.107
ches-0.106
 web-0.105
Token pure
Token ID5899
Feature activation-3.84e-04

Pos logit contributions
 fort+0.098
ig+0.095
ches+0.093
iper+0.092
 web+0.091
Neg logit contributions
all-0.128
uts-0.122
 Mike-0.116
 Crab-0.112
Welcome-0.111
Token heart
Token ID2612
Feature activation+6.24e-02

Pos logit contributions
 fort+0.001
ig+0.001
ches+0.001
iper+0.001
 web+0.001
Neg logit contributions
all-0.001
uts-0.001
 Mike-0.001
 Crab-0.001
Welcome-0.001
Token about
Token ID546
Feature activation+5.23e-02

Pos logit contributions
all+0.045
uts+0.042
 Mike+0.040
 Crab+0.038
no+0.038
Neg logit contributions
 fort-0.051
ig-0.049
ches-0.048
 web-0.048
iper-0.048
Token what
Token ID644
Feature activation+4.16e-02

Pos logit contributions
all+0.059
uts+0.058
Welcome+0.048
anes+0.048
 Mike+0.047
Neg logit contributions
 fort-0.110
ig-0.110
 web-0.109
 closet-0.107
iper-0.107
Token she
Token ID673
Feature activation-6.59e-02

Pos logit contributions
all+0.045
uts+0.041
 Mike+0.037
 Crab+0.035
 Joey+0.035
Neg logit contributions
 fort-0.093
ig-0.091
ches-0.090
iper-0.089
 web-0.088
Token wanted
Token ID2227
Feature activation+1.43e-01

Pos logit contributions
 fort+0.102
ig+0.097
 web+0.094
iper+0.094
ches+0.091
Neg logit contributions
all-0.120
uts-0.108
 Mike-0.105
Welcome-0.103
no-0.102
Token to
Token ID284
Feature activation+2.84e-02

Pos logit contributions
all+0.201
uts+0.194
 Mike+0.177
 Crab+0.172
 Cr+0.170
Neg logit contributions
 fort-0.262
ig-0.259
ches-0.256
iper-0.254
 web-0.250
Token wish
Token ID4601
Feature activation+2.05e-01

Pos logit contributions
uts+0.053
all+0.052
Welcome+0.052
 Hipp+0.050
anes+0.050
Neg logit contributions
 web-0.038
ig-0.037
 fort-0.035
iper-0.035
ches-0.035
Token for
Token ID329
Feature activation+3.33e-02

Pos logit contributions
all+0.284
uts+0.267
 Mike+0.248
 Crab+0.241
Welcome+0.239
Neg logit contributions
 fort-0.386
ig-0.378
ches-0.374
iper-0.371
 web-0.366
Token.
Token ID13
Feature activation+5.96e-02

Pos logit contributions
all+0.033
uts+0.032
anes+0.026
Welcome+0.026
 Mike+0.026
Neg logit contributions
 fort-0.076
ig-0.075
 web-0.074
iper-0.073
 closet-0.073
Token Then
Token ID3244
Feature activation+3.79e-02

Pos logit contributions
all+0.080
uts+0.077
no+0.068
ous+0.067
Welcome+0.067
Neg logit contributions
iper-0.112
 fort-0.109
ig-0.108
 closet-0.108
ches-0.104
Token,
Token ID11
Feature activation+1.97e-02

Pos logit contributions
all+0.045
uts+0.042
 Mike+0.037
 Crab+0.036
Welcome+0.035
Neg logit contributions
 fort-0.080
ig-0.079
iper-0.077
ches-0.077
 web-0.076
Token she
Token ID673
Feature activation-9.81e-02

Pos logit contributions
uts+0.025
all+0.024
anes+0.021
Welcome+0.020
 Mike+0.020
Neg logit contributions
 fort-0.039
ig-0.038
 closet-0.037
iper-0.037
 web-0.036
Token girl
Token ID2576
Feature activation-6.75e-02

Pos logit contributions
all+0.065
uts+0.059
 Mike+0.059
 Joey+0.057
Welcome+0.056
Neg logit contributions
ches-0.057
 fort-0.057
ig-0.057
iper-0.055
ns-0.054
Token.
Token ID13
Feature activation+8.56e-02

Pos logit contributions
 fort+0.141
ig+0.139
ches+0.137
iper+0.136
 web+0.135
Neg logit contributions
all-0.080
uts-0.074
 Mike-0.068
 Crab-0.064
Welcome-0.063
Token What
Token ID1867
Feature activation+4.77e-02

Pos logit contributions
uts+0.102
all+0.099
no+0.089
 Mike+0.082
 Crab+0.082
Neg logit contributions
iper-0.169
 fort-0.167
ig-0.166
ches-0.165
 web-0.164
Token do
Token ID466
Feature activation+1.01e-01

Pos logit contributions
all+0.086
uts+0.082
 Mike+0.078
 Crab+0.075
Welcome+0.075
Neg logit contributions
 fort-0.071
ig-0.069
ches-0.068
iper-0.067
 web-0.066
Token you
Token ID345
Feature activation-3.22e-02

Pos logit contributions
all+0.112
uts+0.102
 Mike+0.092
 Crab+0.088
Welcome+0.087
Neg logit contributions
 fort-0.223
ig-0.218
ches-0.215
iper-0.214
 web-0.213
Token wish
Token ID4601
Feature activation+2.05e-01

Pos logit contributions
 fort+0.056
ig+0.055
ches+0.054
iper+0.054
 web+0.053
Neg logit contributions
all-0.049
uts-0.047
 Mike-0.044
 Crab-0.042
Welcome-0.042
Token to
Token ID284
Feature activation+3.61e-02

Pos logit contributions
all+0.252
uts+0.235
 Mike+0.215
 Crab+0.204
Welcome+0.201
Neg logit contributions
 fort-0.419
ig-0.411
ches-0.405
iper-0.405
 web-0.399
Token gain
Token ID4461
Feature activation+8.28e-02

Pos logit contributions
uts+0.067
all+0.064
 Mike+0.062
Welcome+0.061
 Lib+0.060
Neg logit contributions
 fort-0.051
 web-0.050
iper-0.048
ches-0.048
ig-0.047
Token?"
Token ID1701
Feature activation+9.02e-02

Pos logit contributions
all+0.110
uts+0.103
 Mike+0.095
 Crab+0.091
Welcome+0.090
Neg logit contributions
 fort-0.162
ig-0.159
iper-0.156
ches-0.156
 web-0.153
Token
Token ID198
Feature activation+3.66e-02

Pos logit contributions
uts+0.093
all+0.093
 Crab+0.075
Welcome+0.073
ous+0.072
Neg logit contributions
 fort-0.193
 web-0.188
iper-0.186
ches-0.185
ig-0.185
TokenJane
Token ID41083
Feature activation-1.32e-01

Pos logit contributions
uts+0.044
all+0.041
ous+0.039
 Crab+0.038
 Hipp+0.037
Neg logit contributions
 fort-0.070
ches-0.069
eh-0.069
 web-0.069
iper-0.067
Token must
Token ID1276
Feature activation+6.49e-02

Pos logit contributions
 fort+0.104
eh+0.104
ig+0.101
 closet+0.099
iper+0.099
Neg logit contributions
all-0.074
't-0.068
uts-0.068
 Mike-0.061
 Joey-0.058
Token be
Token ID307
Feature activation-1.26e-02

Pos logit contributions
all+0.111
uts+0.101
 Mike+0.097
 Joey+0.092
 Crab+0.092
Neg logit contributions
 fort-0.104
ig-0.100
ches-0.100
iper-0.099
ns-0.097
Token careful
Token ID8161
Feature activation+1.09e-01

Pos logit contributions
 fort+0.022
iper+0.021
ig+0.021
ches+0.021
 closet+0.020
Neg logit contributions
all-0.020
 going-0.018
 returning-0.018
 pointing-0.018
uts-0.018
Token what
Token ID644
Feature activation+5.05e-02

Pos logit contributions
 Cr+0.166
 Crab+0.164
Welcome+0.163
all+0.161
 Mike+0.160
Neg logit contributions
ches-0.179
 fort-0.175
ig-0.172
 web-0.172
iper-0.169
Token you
Token ID345
Feature activation-3.36e-02

Pos logit contributions
all+0.083
uts+0.081
 Mike+0.072
Welcome+0.072
no+0.072
Neg logit contributions
 fort-0.082
iper-0.080
ig-0.080
ches-0.078
eh-0.076
Token wish
Token ID4601
Feature activation+2.05e-01

Pos logit contributions
 fort+0.064
ig+0.062
iper+0.060
eh+0.060
 web+0.059
Neg logit contributions
all-0.048
uts-0.043
 Mike-0.041
't-0.039
 him-0.038
Token for
Token ID329
Feature activation+3.30e-02

Pos logit contributions
all+0.279
uts+0.261
 Mike+0.243
 Crab+0.236
Welcome+0.232
Neg logit contributions
 fort-0.390
ig-0.382
ches-0.379
iper-0.375
 web-0.370
Token."
Token ID526
Feature activation+8.43e-02

Pos logit contributions
all+0.043
uts+0.040
 Mike+0.038
 Crab+0.038
 Cr+0.037
Neg logit contributions
 fort-0.065
ches-0.064
 web-0.063
ig-0.063
iper-0.063
Token
Token ID198
Feature activation+2.73e-02

Pos logit contributions
all+0.089
uts+0.086
Welcome+0.071
ous+0.070
 Crab+0.069
Neg logit contributions
 fort-0.182
ig-0.176
iper-0.176
ches-0.174
house-0.172
Token
Token ID198
Feature activation+2.60e-02

Pos logit contributions
all+0.027
uts+0.026
 Crab+0.022
 Mike+0.022
 Cr+0.022
Neg logit contributions
 fort-0.061
ches-0.060
ig-0.059
iper-0.058
 web-0.058
TokenTim
Token ID14967
Feature activation-1.23e-01

Pos logit contributions
all+0.040
uts+0.038
 Mike+0.036
 Crab+0.034
Welcome+0.034
Neg logit contributions
 fort-0.045
ig-0.044
ches-0.044
iper-0.044
 web-0.043
Token She
Token ID1375
Feature activation-1.05e-01

Pos logit contributions
all+0.079
uts+0.072
no+0.071
ous+0.069
 returning+0.068
Neg logit contributions
 closet-0.078
 web-0.070
 fort-0.069
 room-0.068
 backyard-0.068
Token wondered
Token ID14028
Feature activation+1.17e-01

Pos logit contributions
 fort+0.217
ig+0.211
iper+0.197
 web+0.196
ringe+0.195
Neg logit contributions
all-0.134
 Mike-0.125
 pointing-0.120
 rep-0.115
uts-0.114
Token what
Token ID644
Feature activation+3.72e-02

Pos logit contributions
all+0.155
uts+0.151
Welcome+0.137
anes+0.131
 Crab+0.131
Neg logit contributions
 fort-0.225
ig-0.224
 closet-0.220
ches-0.216
iper-0.216
Token she
Token ID673
Feature activation-6.33e-02

Pos logit contributions
all+0.044
uts+0.041
 Mike+0.037
 Crab+0.036
Welcome+0.035
Neg logit contributions
 fort-0.078
ig-0.077
ches-0.076
iper-0.076
 web-0.075
Token could
Token ID714
Feature activation+9.74e-02

Pos logit contributions
 fort+0.097
ig+0.094
iper+0.092
 web+0.092
ches+0.088
Neg logit contributions
all-0.113
uts-0.103
 Mike-0.103
Welcome-0.098
 Crab-0.097
Token wish
Token ID4601
Feature activation+2.04e-01

Pos logit contributions
Welcome+0.215
 Hipp+0.213
 Cr+0.209
all+0.209
 Mike+0.209
Neg logit contributions
 web-0.098
 head-0.094
 pile-0.093
 fort-0.091
 finds-0.089
Token for
Token ID329
Feature activation+3.48e-02

Pos logit contributions
all+0.291
uts+0.272
 Crab+0.255
 Mike+0.255
Welcome+0.253
Neg logit contributions
 fort-0.377
ig-0.367
ches-0.364
iper-0.358
 web-0.357
Token.
Token ID13
Feature activation+5.04e-02

Pos logit contributions
all+0.049
uts+0.047
anes+0.044
 Cr+0.044
ous+0.044
Neg logit contributions
 fort-0.063
ches-0.062
 closet-0.061
 web-0.061
ig-0.061
Token She
Token ID1375
Feature activation-1.06e-01

Pos logit contributions
all+0.072
uts+0.066
ous+0.063
no+0.060
anes+0.060
Neg logit contributions
 closet-0.095
 fort-0.089
 web-0.087
 backyard-0.086
iper-0.086
Token thought
Token ID1807
Feature activation+1.05e-01

Pos logit contributions
 fort+0.224
ig+0.216
 web+0.208
iper+0.205
 spine+0.205
Neg logit contributions
all-0.124
 Mike-0.111
 rep-0.102
 pointing-0.101
uts-0.096
Token of
Token ID286
Feature activation+5.12e-03

Pos logit contributions
all+0.118
uts+0.109
 Mike+0.098
 Crab+0.094
Welcome+0.093
Neg logit contributions
 fort-0.226
ig-0.222
ches-0.220
iper-0.219
 web-0.217
Token't
Token ID470
Feature activation+4.17e-03

Pos logit contributions
 Crab+0.095
 Mike+0.091
 Lib+0.089
 Hello+0.086
 Gig+0.085
Neg logit contributions
ches-0.217
ig-0.191
iper-0.185
house-0.183
 web-0.181
Token let
Token ID1309
Feature activation+1.15e-01

Pos logit contributions
all+0.007
uts+0.007
 Mike+0.007
 Crab+0.007
 Lib+0.007
Neg logit contributions
ches-0.006
 web-0.006
ig-0.006
 forgot-0.006
 fort-0.006
Token yourself
Token ID3511
Feature activation-1.45e-02

Pos logit contributions
all+0.184
uts+0.179
 Mike+0.163
 Crab+0.161
Welcome+0.159
Neg logit contributions
 fort-0.187
ches-0.187
ig-0.185
iper-0.183
 web-0.178
Token become
Token ID1716
Feature activation+2.79e-02

Pos logit contributions
ches+0.025
ig+0.025
 fort+0.024
 web+0.024
 closet+0.023
Neg logit contributions
all-0.021
uts-0.020
 Mike-0.019
Welcome-0.019
 Crab-0.019
Token too
Token ID1165
Feature activation+5.22e-02

Pos logit contributions
all+0.045
uts+0.043
 Mike+0.040
 Crab+0.039
 Joey+0.038
Neg logit contributions
 fort-0.046
ig-0.045
iper-0.045
ches-0.044
 web-0.044
Token dependent
Token ID10795
Feature activation+2.04e-01

Pos logit contributions
all+0.101
 Cr+0.097
 Mike+0.096
 Crab+0.096
 Wow+0.096
Neg logit contributions
 forgot-0.062
ches-0.061
 fort-0.059
 web-0.058
 room-0.058
Token on
Token ID319
Feature activation+2.73e-02

Pos logit contributions
all+0.266
uts+0.245
 Crab+0.238
 Mike+0.237
 Cr+0.233
Neg logit contributions
ches-0.399
ig-0.378
iper-0.374
 fort-0.363
ets-0.357
Token one
Token ID530
Feature activation-2.73e-02

Pos logit contributions
all+0.042
uts+0.039
 Mike+0.036
 Crab+0.036
Welcome+0.035
Neg logit contributions
 fort-0.047
ig-0.047
ches-0.046
iper-0.046
 web-0.045
Token thing
Token ID1517
Feature activation+7.67e-02

Pos logit contributions
 fort+0.052
ig+0.051
 web+0.050
ches+0.049
 closet+0.048
Neg logit contributions
all-0.039
uts-0.037
 Mike-0.034
 Cr-0.033
 Crab-0.033
Token.
Token ID13
Feature activation+5.29e-02

Pos logit contributions
all+0.091
uts+0.081
 Mike+0.077
Welcome+0.077
 Crab+0.077
Neg logit contributions
 fort-0.156
ches-0.155
ig-0.153
 web-0.150
iper-0.149
Token It
Token ID632
Feature activation-5.65e-02

Pos logit contributions
all+0.065
uts+0.065
no+0.059
ous+0.057
piring+0.055
Neg logit contributions
iper-0.097
house-0.097
 fort-0.095
ig-0.095
ches-0.095
Token't
Token ID470
Feature activation+4.61e-03

Pos logit contributions
all+0.087
 Crab+0.084
 Mike+0.083
 Joey+0.081
 Cr+0.080
Neg logit contributions
ches-0.226
 fort-0.220
house-0.208
ig-0.208
 web-0.204
Token tell
Token ID1560
Feature activation+1.23e-01

Pos logit contributions
all+0.009
uts+0.009
 Mike+0.008
anes+0.008
Welcome+0.008
Neg logit contributions
 fort-0.006
 web-0.006
ig-0.006
 closet-0.006
ches-0.005
Token me
Token ID502
Feature activation-5.01e-02

Pos logit contributions
all+0.192
uts+0.177
 Mike+0.172
 Crab+0.162
no+0.162
Neg logit contributions
 fort-0.214
ig-0.210
iper-0.204
ches-0.203
 web-0.201
Token what
Token ID644
Feature activation+4.83e-02

Pos logit contributions
 fort+0.105
ig+0.103
iper+0.102
ches+0.102
 web+0.101
Neg logit contributions
all-0.059
uts-0.055
 Mike-0.050
 Crab-0.048
Welcome-0.047
Token you
Token ID345
Feature activation-3.74e-02

Pos logit contributions
all+0.066
uts+0.062
 Mike+0.057
 Crab+0.054
Welcome+0.054
Neg logit contributions
 fort-0.093
ig-0.091
ches-0.090
iper-0.089
 web-0.089
Token wish
Token ID4601
Feature activation+2.04e-01

Pos logit contributions
 fort+0.072
ig+0.070
iper+0.069
 web+0.068
ches+0.068
Neg logit contributions
all-0.051
uts-0.048
 Mike-0.044
 Crab-0.042
Welcome-0.042
Token for
Token ID329
Feature activation+3.40e-02

Pos logit contributions
all+0.273
uts+0.252
 Crab+0.242
 Mike+0.239
 Cr+0.237
Neg logit contributions
 fort-0.392
ches-0.385
ig-0.382
 web-0.368
iper-0.368
Token.
Token ID13
Feature activation+6.56e-02

Pos logit contributions
all+0.051
uts+0.051
unch+0.046
anes+0.045
 Cr+0.045
Neg logit contributions
 fort-0.059
 room-0.057
 closet-0.057
ches-0.057
 web-0.056
Token It
Token ID632
Feature activation-4.65e-02

Pos logit contributions
all+0.094
uts+0.089
no+0.086
 Mike+0.080
 Crab+0.079
Neg logit contributions
 fort-0.118
 closet-0.115
iper-0.114
 web-0.114
ig-0.112
Token is
Token ID318
Feature activation-1.76e-02

Pos logit contributions
iper+0.072
eh+0.070
ig+0.066
 closet+0.066
 fort+0.064
Neg logit contributions
all-0.080
't-0.074
uts-0.074
 Hipp-0.071
Welcome-0.071
Token a
Token ID257
Feature activation-7.80e-02

Pos logit contributions
ig+0.035
iper+0.034
 fort+0.034
ches+0.033
eh+0.032
Neg logit contributions
all-0.023
uts-0.020
 Mike-0.020
 Crab-0.019
 Joey-0.019
Token She
Token ID1375
Feature activation-1.14e-01

Pos logit contributions
all+0.063
uts+0.057
no+0.053
anes+0.052
 Crab+0.052
Neg logit contributions
 fort-0.096
 web-0.095
 closet-0.094
iper-0.092
ig-0.090
Token wondered
Token ID14028
Feature activation+1.15e-01

Pos logit contributions
ig+0.215
 fort+0.201
iper+0.196
 ramp+0.194
ringe+0.194
Neg logit contributions
all-0.155
 going-0.136
uts-0.136
 Mike-0.134
 him-0.131
Token what
Token ID644
Feature activation+3.73e-02

Pos logit contributions
all+0.133
uts+0.128
 Mike+0.110
Welcome+0.110
 Crab+0.109
Neg logit contributions
 fort-0.243
ig-0.238
ches-0.234
iper-0.234
 closet-0.232
Token she
Token ID673
Feature activation-6.83e-02

Pos logit contributions
all+0.048
uts+0.044
 Mike+0.043
Welcome+0.042
no+0.042
Neg logit contributions
 fort-0.074
ig-0.074
iper-0.072
ches-0.071
eh-0.069
Token would
Token ID561
Feature activation+6.71e-02

Pos logit contributions
ig+0.112
 fort+0.112
iper+0.110
 web+0.110
eh+0.108
Neg logit contributions
all-0.112
uts-0.099
 him-0.098
Welcome-0.098
 Mike-0.098
Token wish
Token ID4601
Feature activation+2.04e-01

Pos logit contributions
all+0.117
uts+0.115
 Mike+0.107
 Crab+0.105
 Cr+0.104
Neg logit contributions
 fort-0.102
 web-0.098
ches-0.096
ig-0.096
 closet-0.095
Token for
Token ID329
Feature activation+3.62e-02

Pos logit contributions
all+0.294
uts+0.276
 Mike+0.254
no+0.239
 Crab+0.238
Neg logit contributions
 fort-0.377
ig-0.369
iper-0.365
ches-0.361
 web-0.358
Token with
Token ID351
Feature activation+4.92e-02

Pos logit contributions
all+0.042
uts+0.039
 Mike+0.036
 Crab+0.034
 Cr+0.034
Neg logit contributions
 fort-0.077
ig-0.076
ches-0.075
iper-0.074
 web-0.074
Token her
Token ID607
Feature activation-1.37e-01

Pos logit contributions
all+0.058
uts+0.053
 Mike+0.050
 Crab+0.047
 Joey+0.046
Neg logit contributions
 fort-0.104
ig-0.102
iper-0.100
ches-0.100
 web-0.099
Token wand
Token ID11569
Feature activation+8.10e-02

Pos logit contributions
ches+0.226
iper+0.225
eh+0.223
 fort+0.220
ig+0.219
Neg logit contributions
all-0.212
uts-0.201
 Mike-0.184
no-0.177
 rep-0.176
Token.
Token ID13
Feature activation+5.01e-02

Pos logit contributions
all+0.084
uts+0.078
 Mike+0.067
 Crab+0.063
 Joey+0.061
Neg logit contributions
 fort-0.180
ig-0.178
iper-0.176
ches-0.173
 web-0.172
Token one
Token ID530
Feature activation-4.25e-02

Pos logit contributions
 fort+0.112
ig+0.111
iper+0.110
ches+0.108
 closet+0.107
Neg logit contributions
uts-0.089
all-0.089
 Mike-0.078
no-0.076
Welcome-0.076
Token wish
Token ID4601
Feature activation+1.74e-01

Pos logit contributions
 fort+0.062
ches+0.061
iper+0.061
ig+0.061
 web+0.058
Neg logit contributions
all-0.075
uts-0.070
 Mike-0.067
 Crab-0.065
no-0.065
Token.
Token ID13
Feature activation+6.94e-02

Pos logit contributions
all+0.236
uts+0.221
 Crab+0.215
Welcome+0.212
 Cr+0.212
Neg logit contributions
 fort-0.325
ig-0.324
ches-0.320
iper-0.314
 closet-0.309
Token Whatever
Token ID15935
Feature activation+5.84e-02

Pos logit contributions
uts+0.089
all+0.087
no+0.081
ous+0.075
anes+0.072
Neg logit contributions
iper-0.130
 closet-0.128
 fort-0.128
ig-0.127
ches-0.126
Token you
Token ID345
Feature activation-3.39e-02

Pos logit contributions
all+0.061
uts+0.056
 Mike+0.053
Welcome+0.048
 Joey+0.047
Neg logit contributions
 fort-0.132
ig-0.128
ches-0.127
iper-0.127
 web-0.127
Token wish
Token ID4601
Feature activation+2.04e-01

Pos logit contributions
 fort+0.056
ig+0.054
iper+0.053
ches+0.053
 web+0.052
Neg logit contributions
all-0.056
uts-0.053
 Mike-0.050
 Crab-0.048
Welcome-0.047
Token for
Token ID329
Feature activation+3.02e-02

Pos logit contributions
all+0.294
uts+0.277
 Mike+0.256
 Crab+0.252
Welcome+0.249
Neg logit contributions
 fort-0.370
ig-0.364
ches-0.359
iper-0.356
 web-0.351
Token,
Token ID11
Feature activation+2.94e-02

Pos logit contributions
uts+0.043
all+0.042
anes+0.038
Welcome+0.037
 Mike+0.037
Neg logit contributions
 fort-0.054
ig-0.053
ches-0.053
iper-0.052
 closet-0.052
Token it
Token ID340
Feature activation-4.90e-02

Pos logit contributions
all+0.034
uts+0.032
 Mike+0.028
 Crab+0.027
no+0.027
Neg logit contributions
 fort-0.062
ig-0.061
iper-0.060
ches-0.060
 web-0.059
Token will
Token ID481
Feature activation+7.12e-02

Pos logit contributions
 necks+0.070
 fort+0.070
iper+0.068
ig+0.068
eh+0.067
Neg logit contributions
all-0.089
uts-0.080
't-0.078
 Mike-0.075
 Joey-0.075
Token come
Token ID1282
Feature activation+8.26e-02

Pos logit contributions
all+0.119
uts+0.112
 Mike+0.105
 Crab+0.102
 Joey+0.101
Neg logit contributions
 fort-0.115
ig-0.113
iper-0.111
ches-0.110
 web-0.108
Token to
Token ID284
Feature activation+5.45e-03

Pos logit contributions
all+0.007
uts+0.006
 Mike+0.005
 Crab+0.005
no+0.004
Neg logit contributions
 fort-0.028
ig-0.027
ches-0.027
iper-0.026
eh-0.026
Token be
Token ID307
Feature activation-1.91e-02

Pos logit contributions
all+0.009
uts+0.008
 Mike+0.008
 Crab+0.008
 Joey+0.008
Neg logit contributions
 fort-0.009
ig-0.009
ches-0.009
iper-0.008
eh-0.008
Token careful
Token ID8161
Feature activation+1.06e-01

Pos logit contributions
 fort+0.034
ig+0.033
iper+0.032
ches+0.031
 ramp+0.030
Neg logit contributions
all-0.030
 pointing-0.026
 returning-0.025
ful-0.025
uts-0.025
Token what
Token ID644
Feature activation+4.93e-02

Pos logit contributions
all+0.151
Welcome+0.142
 Mike+0.141
 Cr+0.141
uts+0.141
Neg logit contributions
 fort-0.184
ches-0.184
ig-0.182
 web-0.179
iper-0.178
Token you
Token ID345
Feature activation-3.49e-02

Pos logit contributions
all+0.072
uts+0.069
 Mike+0.062
Welcome+0.061
 Crab+0.060
Neg logit contributions
 fort-0.091
ig-0.088
iper-0.088
ches-0.086
 closet-0.084
Token wish
Token ID4601
Feature activation+2.04e-01

Pos logit contributions
 fort+0.069
ig+0.067
iper+0.065
 web+0.064
eh+0.063
Neg logit contributions
all-0.048
uts-0.043
 Mike-0.041
 Crab-0.039
Welcome-0.038
Token for
Token ID329
Feature activation+3.20e-02

Pos logit contributions
all+0.277
uts+0.260
 Mike+0.240
 Crab+0.230
Welcome+0.227
Neg logit contributions
 fort-0.390
ig-0.382
ches-0.376
iper-0.376
 web-0.370
Token.
Token ID13
Feature activation+6.86e-02

Pos logit contributions
all+0.042
uts+0.039
 Mike+0.037
 Crab+0.035
 Cr+0.035
Neg logit contributions
 fort-0.063
ches-0.062
 web-0.062
ig-0.062
iper-0.061
Token Sometimes
Token ID8975
Feature activation+5.47e-02

Pos logit contributions
all+0.090
uts+0.088
no+0.084
 Mike+0.078
ous+0.076
Neg logit contributions
iper-0.123
 web-0.122
ig-0.121
 closet-0.121
 fort-0.121
Token,
Token ID11
Feature activation+3.31e-02

Pos logit contributions
all+0.062
uts+0.058
 Mike+0.053
 Crab+0.050
Welcome+0.050
Neg logit contributions
 fort-0.115
iper-0.113
ig-0.113
ches-0.113
eh-0.111
Token wishes
Token ID12802
Feature activation+1.85e-01

Pos logit contributions
all+0.039
uts+0.036
 Mike+0.033
 Crab+0.032
Welcome+0.031
Neg logit contributions
 fort-0.069
ig-0.068
ches-0.067
iper-0.067
 web-0.066
Token is
Token ID318
Feature activation-1.74e-02

Pos logit contributions
all+0.150
uts+0.144
 Mike+0.135
 Crab+0.132
Welcome+0.131
Neg logit contributions
 fort-0.109
ig-0.105
ches-0.103
iper-0.103
 web-0.101
Token coming
Token ID2406
Feature activation+1.17e-01

Pos logit contributions
 fort+0.032
 closet+0.030
ches+0.030
 web+0.030
 room+0.029
Neg logit contributions
uts-0.025
all-0.024
 Cr-0.021
 Crab-0.021
unch-0.021
Token to
Token ID284
Feature activation-1.25e-03

Pos logit contributions
uts+0.143
unch+0.134
all+0.126
 Crab+0.121
 Cr+0.119
Neg logit contributions
 fort-0.232
ches-0.227
 room-0.218
 closet-0.218
iper-0.209
Token town
Token ID3240
Feature activation+5.01e-02

Pos logit contributions
 fort+0.002
 closet+0.002
 web+0.002
iper+0.002
 room+0.002
Neg logit contributions
uts-0.002
all-0.002
 Mike-0.002
anes-0.002
 Crab-0.002
Token!
Token ID0
Feature activation+6.09e-02

Pos logit contributions
uts+0.064
all+0.062
 Crab+0.059
 Cr+0.059
 Joey+0.057
Neg logit contributions
 fort-0.095
ches-0.091
 room-0.089
 closet-0.088
ig-0.088
Token Won
Token ID23306
Feature activation+2.04e-01

Pos logit contributions
all+0.081
uts+0.078
no+0.077
ful+0.068
 Crab+0.068
Neg logit contributions
 fort-0.105
house-0.104
 closet-0.104
iper-0.104
ches-0.103
Token't
Token ID470
Feature activation+3.72e-02

Pos logit contributions
 Joey+0.120
all+0.119
 Crab+0.119
uts+0.115
 Mike+0.111
Neg logit contributions
ches-0.508
 fort-0.477
ns-0.472
house-0.471
ig-0.465
Token that
Token ID326
Feature activation+4.20e-02

Pos logit contributions
uts+0.055
all+0.053
ges+0.052
unch+0.048
 Cr+0.047
Neg logit contributions
 fort-0.062
 room-0.059
 belt-0.056
ches-0.055
ns-0.055
Token be
Token ID307
Feature activation+9.42e-03

Pos logit contributions
uts+0.071
all+0.071
 Mike+0.064
ges+0.064
 Crab+0.063
Neg logit contributions
 fort-0.064
ches-0.060
 web-0.059
ig-0.057
 room-0.057
Token fun
Token ID1257
Feature activation+1.29e-01

Pos logit contributions
all+0.014
uts+0.012
 Mike+0.012
 Joey+0.011
Welcome+0.011
Neg logit contributions
ig-0.018
 fort-0.017
iper-0.017
 web-0.017
ches-0.017
Token?"
Token ID1701
Feature activation+8.93e-02

Pos logit contributions
uts+0.191
all+0.186
 Cr+0.183
 Crab+0.182
Welcome+0.180
Neg logit contributions
 fort-0.213
ches-0.208
ig-0.204
 room-0.200
ets-0.197
Token was
Token ID373
Feature activation-3.34e-02

Pos logit contributions
 fort+0.200
ig+0.190
iper+0.184
 ramp+0.180
eh+0.180
Neg logit contributions
all-0.142
 him-0.137
 Mike-0.131
 going-0.128
't-0.126
Token thinking
Token ID3612
Feature activation+1.28e-01

Pos logit contributions
 fort+0.058
ig+0.057
iper+0.056
ches+0.056
 web+0.054
Neg logit contributions
all-0.053
uts-0.049
 Mike-0.046
 Crab-0.044
no-0.044
Token about
Token ID546
Feature activation+5.53e-02

Pos logit contributions
all+0.123
uts+0.108
 Mike+0.094
 him+0.089
ous+0.087
Neg logit contributions
 fort-0.308
ig-0.300
ns-0.292
iper-0.291
 web-0.290
Token how
Token ID703
Feature activation+1.21e-01

Pos logit contributions
uts+0.084
all+0.080
anes+0.072
 Crab+0.071
 Mike+0.070
Neg logit contributions
 closet-0.096
 web-0.096
 fort-0.095
ig-0.092
 room-0.092
Token she
Token ID673
Feature activation-5.96e-02

Pos logit contributions
all+0.167
uts+0.157
 Mike+0.145
 Crab+0.140
Welcome+0.137
Neg logit contributions
 fort-0.230
ig-0.225
ches-0.221
iper-0.221
 web-0.219
Token wished
Token ID16555
Feature activation+2.03e-01

Pos logit contributions
 fort+0.104
eh+0.101
iper+0.099
ig+0.096
aj+0.095
Neg logit contributions
all-0.091
 him-0.085
 Mike-0.081
uts-0.078
Welcome-0.078
Token her
Token ID607
Feature activation-1.20e-01

Pos logit contributions
all+0.245
uts+0.223
 Mike+0.205
no+0.190
 Joey+0.188
Neg logit contributions
 fort-0.432
ig-0.421
iper-0.417
ches-0.415
 web-0.411
Token life
Token ID1204
Feature activation+4.48e-02

Pos logit contributions
ches+0.184
ig+0.182
iper+0.181
 fort+0.181
eh+0.175
Neg logit contributions
all-0.204
uts-0.198
 Mike-0.183
no-0.176
 Crab-0.175
Token would
Token ID561
Feature activation+7.53e-02

Pos logit contributions
all+0.078
uts+0.075
 Mike+0.069
Welcome+0.066
no+0.066
Neg logit contributions
 fort-0.070
eh-0.068
ig-0.067
iper-0.066
 web-0.065
Token be
Token ID307
Feature activation+6.42e-03

Pos logit contributions
all+0.137
uts+0.133
 Mike+0.129
 Crab+0.127
 Joey+0.123
Neg logit contributions
 fort-0.106
ches-0.103
 web-0.101
ig-0.099
 closet-0.098
Token different
Token ID1180
Feature activation+1.43e-02

Pos logit contributions
all+0.008
uts+0.008
 Mike+0.007
 Crab+0.007
Welcome+0.007
Neg logit contributions
 fort-0.013
ig-0.012
ches-0.012
iper-0.012
 web-0.012
Token gle
Token ID26852
Feature activation-1.75e-02

Pos logit contributions
 fort+0.138
ig+0.136
iper+0.135
ches+0.134
 web+0.129
Neg logit contributions
all-0.170
uts-0.163
 Mike-0.155
 Crab-0.151
Welcome-0.150
Tokeneful
Token ID13839
Feature activation-1.43e-02

Pos logit contributions
 fort+0.030
ches+0.029
iper+0.028
 web+0.027
 closet+0.027
Neg logit contributions
all-0.030
uts-0.026
 Mike-0.025
 Crab-0.024
no-0.024
Token,
Token ID11
Feature activation+9.50e-03

Pos logit contributions
 fort+0.021
ig+0.021
ches+0.021
iper+0.021
 web+0.020
Neg logit contributions
all-0.025
uts-0.024
 Mike-0.023
 Crab-0.022
 Joey-0.022
Token "
Token ID366
Feature activation+3.05e-02

Pos logit contributions
all+0.014
uts+0.013
 Mike+0.012
 Crab+0.012
anes+0.011
Neg logit contributions
 fort-0.017
 web-0.017
ches-0.017
ig-0.016
iper-0.016
TokenI
Token ID40
Feature activation-5.16e-03

Pos logit contributions
uts+0.042
all+0.038
 Crab+0.037
 Joey+0.037
 Mike+0.036
Neg logit contributions
ches-0.054
ns-0.053
eh-0.053
ig-0.052
house-0.052
Token Won
Token ID23306
Feature activation+2.03e-01

Pos logit contributions
 fort+0.009
ig+0.009
ches+0.009
iper+0.009
 web+0.009
Neg logit contributions
all-0.008
uts-0.007
 Mike-0.007
 Crab-0.006
Welcome-0.006
Token!"
Token ID2474
Feature activation+1.01e-01

Pos logit contributions
 Joey+0.134
 Mike+0.132
all+0.128
 Crab+0.122
 Whale+0.119
Neg logit contributions
ches-0.502
house-0.462
 web-0.459
ig-0.457
ns-0.455
Token
Token ID198
Feature activation+3.45e-02

Pos logit contributions
all+0.120
uts+0.110
ful+0.104
 Cr+0.102
Welcome+0.101
Neg logit contributions
 fort-0.196
iper-0.192
ches-0.190
 necks-0.190
ig-0.188
Token
Token ID198
Feature activation+3.29e-02

Pos logit contributions
all+0.040
uts+0.037
 Cr+0.036
 Crab+0.035
Welcome+0.034
Neg logit contributions
ches-0.070
 fort-0.068
ig-0.068
iper-0.068
 web-0.065
TokenBob
Token ID18861
Feature activation-1.17e-01

Pos logit contributions
all+0.048
uts+0.045
 Mike+0.042
 Crab+0.041
 Cr+0.041
Neg logit contributions
 fort-0.060
ches-0.058
ig-0.058
iper-0.057
 web-0.056
Token felt
Token ID2936
Feature activation+9.85e-03

Pos logit contributions
 fort+0.224
 closet+0.211
 web+0.211
ig+0.204
iper+0.204
Neg logit contributions
all-0.185
 Mike-0.164
uts-0.157
 Joey-0.150
 Crab-0.145
Token fish
Token ID5916
Feature activation-8.27e-03

Pos logit contributions
 fort+0.090
ig+0.088
ches+0.086
iper+0.086
 web+0.085
Neg logit contributions
all-0.070
uts-0.066
 Mike-0.061
Welcome-0.058
 Crab-0.057
Token's
Token ID338
Feature activation-9.59e-02

Pos logit contributions
 fort+0.012
ig+0.012
ches+0.012
 web+0.012
house+0.011
Neg logit contributions
all-0.014
uts-0.013
Welcome-0.013
no-0.013
 Mike-0.013
Token shiny
Token ID22441
Feature activation+5.29e-03

Pos logit contributions
 fort+0.135
ig+0.132
ches+0.129
iper+0.129
 web+0.126
Neg logit contributions
all-0.180
uts-0.172
 Mike-0.162
 Crab-0.158
Welcome-0.156
Token scales
Token ID16252
Feature activation+2.61e-02

Pos logit contributions
all+0.009
uts+0.009
 Mike+0.008
 Crab+0.008
 Joey+0.008
Neg logit contributions
 fort-0.008
iper-0.008
ig-0.008
ches-0.008
 web-0.007
Token and
Token ID290
Feature activation-2.61e-02

Pos logit contributions
all+0.042
Welcome+0.041
no+0.038
 Cr+0.038
Joe+0.037
Neg logit contributions
ig-0.041
ches-0.041
 fort-0.041
 web-0.040
ets-0.040
Token wished
Token ID16555
Feature activation+2.03e-01

Pos logit contributions
 fort+0.048
ig+0.048
iper+0.047
ches+0.047
 web+0.045
Neg logit contributions
all-0.038
uts-0.035
 Mike-0.033
 Crab-0.032
 Joey-0.032
Token he
Token ID339
Feature activation-5.41e-02

Pos logit contributions
all+0.228
uts+0.216
Welcome+0.184
 Mike+0.183
anes+0.175
Neg logit contributions
 fort-0.431
ches-0.420
ig-0.418
 web-0.407
iper-0.406
Token had
Token ID550
Feature activation+2.11e-02

Pos logit contributions
 fort+0.078
ig+0.076
iper+0.075
ches+0.074
 web+0.073
Neg logit contributions
all-0.101
uts-0.096
 Mike-0.091
 Crab-0.089
Welcome-0.088
Token some
Token ID617
Feature activation-1.85e-02

Pos logit contributions
all+0.031
uts+0.030
anes+0.027
 Mike+0.027
ous+0.026
Neg logit contributions
 fort-0.036
ig-0.036
ches-0.036
 web-0.035
 closet-0.035
Token too
Token ID1165
Feature activation+3.62e-02

Pos logit contributions
 fort+0.028
ig+0.027
 web+0.026
ches+0.026
 closet+0.026
Neg logit contributions
all-0.033
uts-0.032
 Mike-0.030
Welcome-0.029
 Lib-0.029
Token.
Token ID13
Feature activation+6.74e-02

Pos logit contributions
anes+0.070
 Whale+0.064
all+0.064
Welcome+0.063
 Wow+0.063
Neg logit contributions
 web-0.044
ig-0.043
ets-0.043
 fort-0.042
ches-0.042
Token him
Token ID683
Feature activation-1.13e-01

Pos logit contributions
 fort+0.029
ig+0.028
iper+0.028
 web+0.028
ches+0.028
Neg logit contributions
all-0.020
uts-0.020
Welcome-0.016
 Crab-0.016
anes-0.016
Token and
Token ID290
Feature activation-4.17e-02

Pos logit contributions
 fort+0.240
ig+0.235
iper+0.231
 web+0.229
ches+0.228
Neg logit contributions
all-0.133
uts-0.120
 Mike-0.111
 Joey-0.103
 Crab-0.103
Token they
Token ID484
Feature activation-8.93e-02

Pos logit contributions
 fort+0.072
ig+0.071
ches+0.070
iper+0.069
 web+0.068
Neg logit contributions
all-0.065
uts-0.061
 Mike-0.057
 Crab-0.055
Welcome-0.054
Token cl
Token ID537
Feature activation+1.10e-01

Pos logit contributions
 fort+0.157
ig+0.153
 web+0.148
ches+0.148
iper+0.147
Neg logit contributions
all-0.136
uts-0.125
 Mike-0.122
 Joey-0.116
 Crab-0.114
Tokenapped
Token ID6320
Feature activation+8.92e-02

Pos logit contributions
all+0.186
uts+0.180
no+0.176
Welcome+0.171
 Lib+0.169
Neg logit contributions
ig-0.176
iper-0.157
house-0.154
 fort-0.151
ets-0.147
Token their
Token ID511
Feature activation-1.95e-01

Pos logit contributions
all+0.121
uts+0.114
 Mike+0.104
 Crab+0.101
Welcome+0.099
Neg logit contributions
 fort-0.172
ig-0.168
ches-0.166
iper-0.165
 web-0.163
Token hands
Token ID2832
Feature activation+3.01e-02

Pos logit contributions
eh+0.323
 fort+0.320
auldron+0.314
ches+0.310
 closet+0.302
Neg logit contributions
 Mike-0.267
all-0.265
 Joey-0.260
uts-0.256
 cheering-0.248
Token.
Token ID13
Feature activation+3.29e-02

Pos logit contributions
all+0.043
uts+0.041
 Mike+0.038
Welcome+0.037
 Crab+0.037
Neg logit contributions
 fort-0.055
ig-0.054
ches-0.054
iper-0.052
 web-0.052
Token They
Token ID1119
Feature activation-9.17e-02

Pos logit contributions
all+0.049
no+0.047
uts+0.045
piring+0.043
ous+0.043
Neg logit contributions
 closet-0.054
iper-0.052
 fort-0.051
aj-0.050
uel-0.050
Token thanked
Token ID26280
Feature activation+7.57e-02

Pos logit contributions
 fort+0.160
ig+0.155
iper+0.150
ches+0.147
 web+0.146
Neg logit contributions
all-0.143
 Mike-0.137
uts-0.136
 Crab-0.125
 rep-0.124
Token Tom
Token ID4186
Feature activation-1.36e-01

Pos logit contributions
uts+0.101
all+0.100
Welcome+0.085
anes+0.082
no+0.080
Neg logit contributions
 fort-0.144
iper-0.142
ig-0.139
ches-0.137
 closet-0.135
Token!
Token ID0
Feature activation+3.19e-02

Pos logit contributions
all+0.080
uts+0.075
 Mike+0.068
 Crab+0.066
Welcome+0.065
Neg logit contributions
 fort-0.139
ig-0.136
ches-0.135
iper-0.134
 web-0.133
Token<|endoftext|>
Token ID50256
Feature activation+2.85e-02

Pos logit contributions
all+0.037
uts+0.036
no+0.032
ous+0.031
piring+0.031
Neg logit contributions
iper-0.062
 fort-0.061
 closet-0.061
ches-0.060
 web-0.060
TokenJohn
Token ID7554
Feature activation-1.49e-01

Pos logit contributions
all+0.037
uts+0.036
ous+0.031
 Cr+0.031
no+0.031
Neg logit contributions
 fort-0.055
ig-0.054
ches-0.053
 closet-0.053
 web-0.052
Token looked
Token ID3114
Feature activation+2.77e-02

Pos logit contributions
 fort+0.255
 web+0.243
ig+0.238
iper+0.236
ches+0.230
Neg logit contributions
all-0.243
 Mike-0.219
uts-0.213
 Joey-0.207
 him-0.204
Token out
Token ID503
Feature activation-3.54e-02

Pos logit contributions
all+0.029
uts+0.025
 Mike+0.024
 Joey+0.023
 Crab+0.021
Neg logit contributions
 fort-0.062
ig-0.061
ches-0.061
iper-0.061
 web-0.060
Token his
Token ID465
Feature activation-1.94e-01

Pos logit contributions
 fort+0.061
 web+0.058
ig+0.057
 closet+0.057
iper+0.056
Neg logit contributions
uts-0.055
all-0.054
 Crab-0.049
 Cr-0.048
Welcome-0.047
Token window
Token ID4324
Feature activation+3.43e-02

Pos logit contributions
ches+0.267
ns+0.253
ets+0.241
iper+0.240
 fort+0.234
Neg logit contributions
all-0.362
 Mike-0.345
uts-0.338
 Joey-0.334
 pointing-0.328
Token and
Token ID290
Feature activation-3.88e-02

Pos logit contributions
all+0.050
uts+0.047
 Mike+0.044
 Crab+0.041
 Joey+0.041
Neg logit contributions
 fort-0.062
ig-0.061
iper-0.061
ches-0.061
 web-0.059
Token saw
Token ID2497
Feature activation+4.41e-02

Pos logit contributions
 fort+0.049
ig+0.048
ches+0.047
iper+0.047
 web+0.046
Neg logit contributions
all-0.078
uts-0.075
 Mike-0.071
 Crab-0.069
Welcome-0.068
Token a
Token ID257
Feature activation-1.01e-01

Pos logit contributions
all+0.071
uts+0.069
Welcome+0.060
unch+0.058
no+0.057
Neg logit contributions
 fort-0.075
 closet-0.073
 web-0.070
 room-0.069
ig-0.068
Token bright
Token ID6016
Feature activation-4.01e-02

Pos logit contributions
 fort+0.151
ig+0.150
iper+0.148
ches+0.148
 web+0.142
Neg logit contributions
all-0.175
uts-0.166
 Mike-0.159
 Crab-0.154
Welcome-0.153
Token she
Token ID673
Feature activation-8.24e-02

Pos logit contributions
all+0.093
uts+0.088
 Mike+0.077
 Crab+0.074
Welcome+0.074
Neg logit contributions
 fort-0.158
ig-0.153
ches-0.152
iper-0.152
 web-0.150
Token marched
Token ID23558
Feature activation+1.05e-01

Pos logit contributions
 fort+0.131
iper+0.122
ig+0.121
 web+0.119
eh+0.115
Neg logit contributions
all-0.139
 Mike-0.132
uts-0.129
 him-0.123
 Crab-0.122
Token and
Token ID290
Feature activation-3.97e-02

Pos logit contributions
all+0.141
uts+0.132
 Mike+0.122
 Crab+0.116
Welcome+0.115
Neg logit contributions
 fort-0.205
ig-0.201
iper-0.198
ches-0.198
 web-0.195
Token cl
Token ID537
Feature activation+1.24e-01

Pos logit contributions
 fort+0.067
ig+0.065
iper+0.064
ches+0.063
 web+0.062
Neg logit contributions
all-0.064
 Mike-0.060
uts-0.059
Welcome-0.055
no-0.055
Tokenapped
Token ID6320
Feature activation+9.24e-02

Pos logit contributions
all+0.190
 Crab+0.183
no+0.181
uts+0.180
Welcome+0.179
Neg logit contributions
ig-0.216
iper-0.189
ets-0.186
house-0.179
aj-0.178
Token their
Token ID511
Feature activation-1.93e-01

Pos logit contributions
all+0.116
uts+0.110
 Mike+0.099
 Crab+0.098
Welcome+0.095
Neg logit contributions
 fort-0.185
ig-0.182
ches-0.180
iper-0.179
 web-0.178
Token hands
Token ID2832
Feature activation+3.29e-02

Pos logit contributions
 fort+0.340
eh+0.338
auldron+0.325
ches+0.322
ig+0.315
Neg logit contributions
 Mike-0.259
all-0.242
 cheering-0.240
Welcome-0.240
uts-0.237
Token.
Token ID13
Feature activation+3.36e-02

Pos logit contributions
all+0.044
uts+0.042
 Crab+0.040
 Cr+0.040
Welcome+0.039
Neg logit contributions
ches-0.061
 fort-0.061
ig-0.061
 web-0.058
iper-0.058
Token
Token ID220
Feature activation+2.37e-02

Pos logit contributions
all+0.046
uts+0.043
no+0.042
ous+0.040
piring+0.039
Neg logit contributions
 closet-0.059
iper-0.058
 fort-0.057
ig-0.056
ches-0.056
Token
Token ID198
Feature activation+1.07e-02

Pos logit contributions
all+0.028
 Crab+0.025
no+0.024
 Cr+0.024
 Hipp+0.023
Neg logit contributions
ches-0.047
iper-0.046
 fort-0.045
ig-0.045
 closet-0.044
Token
Token ID198
Feature activation+1.26e-02

Pos logit contributions
uts+0.013
all+0.012
ous+0.012
 Crab+0.011
piring+0.011
Neg logit contributions
eh-0.020
ches-0.020
iper-0.020
uel-0.019
ig-0.019
TokenThe
Token ID464
Feature activation-1.49e-01

Pos logit contributions
all+0.052
uts+0.050
 Mike+0.050
 Joey+0.048
 Crab+0.048
Neg logit contributions
 fort-0.043
iper-0.040
ches-0.040
ig-0.040
 web-0.040
Token little
Token ID1310
Feature activation-6.94e-02

Pos logit contributions
ig+0.187
ches+0.186
 fort+0.185
iper+0.183
 web+0.177
Neg logit contributions
all-0.302
uts-0.285
 Mike-0.275
 Crab-0.269
Welcome-0.267
Token boy
Token ID2933
Feature activation-8.94e-02

Pos logit contributions
ches+0.107
iper+0.101
 web+0.096
ig+0.095
ns+0.094
Neg logit contributions
all-0.126
 Mike-0.121
 Crab-0.119
 Joey-0.116
 Cr-0.115
Token cl
Token ID537
Feature activation+9.93e-02

Pos logit contributions
 closet+0.165
 fort+0.162
iper+0.158
 web+0.155
 spine+0.152
Neg logit contributions
all-0.137
 Mike-0.117
no-0.112
uts-0.111
 Joey-0.108
Tokenapped
Token ID6320
Feature activation+8.18e-02

Pos logit contributions
all+0.151
uts+0.144
Welcome+0.135
no+0.134
 Hipp+0.129
Neg logit contributions
ig-0.180
iper-0.164
 fort-0.164
house-0.161
ches-0.156
Token his
Token ID465
Feature activation-1.92e-01

Pos logit contributions
all+0.100
uts+0.091
 Mike+0.084
 Crab+0.080
 Joey+0.079
Neg logit contributions
 fort-0.170
ig-0.168
ches-0.165
iper-0.165
 web-0.163
Token hands
Token ID2832
Feature activation+2.61e-02

Pos logit contributions
 closet+0.328
ches+0.309
 clinic+0.304
 fort+0.303
ital+0.302
Neg logit contributions
all-0.262
uts-0.255
 Joey-0.254
 Crab-0.240
 pointing-0.238
Token and
Token ID290
Feature activation-3.61e-02

Pos logit contributions
all+0.044
uts+0.043
Welcome+0.041
 Mike+0.040
anes+0.039
Neg logit contributions
 fort-0.040
ches-0.039
ig-0.038
iper-0.037
 web-0.037
Token said
Token ID531
Feature activation+4.52e-02

Pos logit contributions
ig+0.065
 fort+0.065
ches+0.064
iper+0.064
 closet+0.062
Neg logit contributions
all-0.053
uts-0.049
 Mike-0.049
 Joey-0.046
 Crab-0.046
Token,
Token ID11
Feature activation+2.00e-02

Pos logit contributions
all+0.095
Welcome+0.090
uts+0.089
anes+0.087
Ice+0.086
Neg logit contributions
ig-0.052
 fort-0.049
ches-0.043
iper-0.043
 web-0.042
Token "
Token ID366
Feature activation+3.20e-02

Pos logit contributions
uts+0.036
all+0.035
reating+0.034
anes+0.034
Welcome+0.034
Neg logit contributions
 head-0.025
 fort-0.023
 pile-0.022
 room-0.022
ches-0.022
Token.
Token ID13
Feature activation+4.44e-02

Pos logit contributions
all+0.030
uts+0.028
 Crab+0.028
 Cr+0.027
Welcome+0.027
Neg logit contributions
ches-0.036
 fort-0.035
 web-0.035
ets-0.034
 forgot-0.034
Token Tim
Token ID5045
Feature activation-1.40e-01

Pos logit contributions
all+0.059
uts+0.056
no+0.053
 returning+0.049
ful+0.048
Neg logit contributions
 closet-0.078
 fort-0.078
iper-0.078
ches-0.077
house-0.076
Tokenmy
Token ID1820
Feature activation-1.04e-01

Pos logit contributions
 fort+0.244
eh+0.223
 web+0.223
ns+0.212
ig+0.210
Neg logit contributions
all-0.246
 Mike-0.223
 him-0.201
 Joey-0.197
uts-0.192
Token cl
Token ID537
Feature activation+1.04e-01

Pos logit contributions
 fort+0.190
eh+0.174
ig+0.169
iper+0.169
 web+0.168
Neg logit contributions
all-0.171
 Mike-0.158
uts-0.149
 him-0.138
 Joey-0.137
Tokenapped
Token ID6320
Feature activation+8.41e-02

Pos logit contributions
all+0.156
uts+0.148
no+0.145
Welcome+0.144
 Crab+0.136
Neg logit contributions
ig-0.181
iper-0.168
 fort-0.163
house-0.160
ches-0.160
Token his
Token ID465
Feature activation-1.91e-01

Pos logit contributions
all+0.108
uts+0.103
 Mike+0.093
 Crab+0.090
Welcome+0.089
Neg logit contributions
 fort-0.167
ig-0.163
ches-0.161
iper-0.161
 web-0.159
Token hands
Token ID2832
Feature activation+2.66e-02

Pos logit contributions
 fort+0.301
eh+0.285
ches+0.283
auldron+0.283
 closet+0.282
Neg logit contributions
all-0.286
 Mike-0.281
 Joey-0.270
uts-0.269
 pointing-0.267
Token and
Token ID290
Feature activation-4.32e-02

Pos logit contributions
all+0.044
uts+0.042
Welcome+0.040
 Crab+0.040
 Mike+0.040
Neg logit contributions
ches-0.041
ig-0.041
 fort-0.041
 web-0.038
iper-0.038
Token cheered
Token ID34767
Feature activation+1.17e-01

Pos logit contributions
 fort+0.072
ig+0.070
iper+0.069
ches+0.068
 web+0.066
Neg logit contributions
all-0.071
uts-0.067
 Mike-0.065
 Crab-0.062
 Joey-0.061
Token.
Token ID13
Feature activation+4.58e-02

Pos logit contributions
uts+0.178
anes+0.176
Welcome+0.176
Ice+0.173
unch+0.172
Neg logit contributions
 fort-0.183
ches-0.173
 head-0.168
iper-0.166
 room-0.164
Token
Token ID220
Feature activation+2.95e-02

Pos logit contributions
all+0.068
uts+0.066
no+0.064
ful+0.063
piring+0.063
Neg logit contributions
 fort-0.070
 closet-0.070
uel-0.069
house-0.068
 room-0.068
Token dad
Token ID9955
Feature activation-3.19e-02

Pos logit contributions
 fort+0.096
iper+0.094
ig+0.092
 closet+0.091
ches+0.091
Neg logit contributions
all-0.083
uts-0.079
 Mike-0.071
Welcome-0.070
no-0.069
Token smiled
Token ID13541
Feature activation+2.00e-02

Pos logit contributions
 fort+0.051
 web+0.049
ig+0.048
eh+0.047
ches+0.046
Neg logit contributions
all-0.056
 Mike-0.052
uts-0.051
 Joey-0.048
Welcome-0.047
Token and
Token ID290
Feature activation-5.32e-02

Pos logit contributions
all+0.040
uts+0.040
no+0.037
anes+0.037
 Cr+0.037
Neg logit contributions
 fort-0.025
 closet-0.022
ig-0.022
iper-0.022
ches-0.021
Token cl
Token ID537
Feature activation+1.07e-01

Pos logit contributions
 fort+0.078
ig+0.076
iper+0.075
ches+0.075
 web+0.073
Neg logit contributions
all-0.096
uts-0.092
 Mike-0.084
 Crab-0.083
no-0.083
Tokenapped
Token ID6320
Feature activation+8.66e-02

Pos logit contributions
all+0.180
uts+0.178
no+0.177
 Crab+0.171
 Gig+0.166
Neg logit contributions
ig-0.164
house-0.148
iper-0.147
ets-0.145
aj-0.138
Token their
Token ID511
Feature activation-1.91e-01

Pos logit contributions
all+0.116
uts+0.111
 Crab+0.100
 Mike+0.099
 Cr+0.096
Neg logit contributions
 fort-0.170
ig-0.163
ches-0.162
iper-0.162
 web-0.160
Token hands
Token ID2832
Feature activation+2.68e-02

Pos logit contributions
eh+0.306
 fort+0.304
ig+0.293
ches+0.283
 closet+0.282
Neg logit contributions
all-0.297
uts-0.288
 Mike-0.280
 pointing-0.269
Welcome-0.266
Token.
Token ID13
Feature activation+5.35e-02

Pos logit contributions
all+0.038
uts+0.036
 Crab+0.036
 Cr+0.036
Welcome+0.035
Neg logit contributions
 fort-0.047
ches-0.047
ig-0.044
 closet-0.044
ets-0.044
Token They
Token ID1119
Feature activation-7.97e-02

Pos logit contributions
all+0.080
uts+0.073
no+0.070
unch+0.063
 Crab+0.063
Neg logit contributions
 fort-0.098
 closet-0.096
iper-0.093
 web-0.089
ches-0.088
Token said
Token ID531
Feature activation+3.40e-02

Pos logit contributions
 fort+0.136
ig+0.133
 web+0.128
ches+0.127
iper+0.127
Neg logit contributions
all-0.128
uts-0.119
 Mike-0.117
 Joey-0.108
Welcome-0.108
Token,
Token ID11
Feature activation+2.94e-03

Pos logit contributions
all+0.065
uts+0.063
anes+0.060
Welcome+0.059
no+0.058
Neg logit contributions
ig-0.044
 fort-0.042
iper-0.041
ches-0.040
 web-0.038
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
all+0.035
uts+0.033
 Crab+0.031
ous+0.030
 Cr+0.030
Neg logit contributions
ches-0.058
 fort-0.056
ig-0.056
iper-0.056
 web-0.055
TokenThe
Token ID464
Feature activation-1.54e-01

Pos logit contributions
all+0.047
uts+0.045
 Mike+0.042
 Crab+0.041
 Joey+0.040
Neg logit contributions
 fort-0.043
ig-0.042
iper-0.042
ches-0.042
 web-0.041
Token baby
Token ID5156
Feature activation-7.54e-02

Pos logit contributions
 fort+0.267
 closet+0.259
 web+0.254
ig+0.249
iper+0.248
Neg logit contributions
uts-0.254
all-0.239
anes-0.220
 Cr-0.210
 Mike-0.206
Token cl
Token ID537
Feature activation+9.93e-02

Pos logit contributions
 fort+0.125
ets+0.121
ches+0.118
 closet+0.117
 web+0.116
Neg logit contributions
all-0.127
 Joey-0.115
 Mike-0.115
 Crab-0.107
 Hipp-0.105
Tokenapped
Token ID6320
Feature activation+8.39e-02

Pos logit contributions
all+0.136
uts+0.127
Welcome+0.120
no+0.118
 Mike+0.117
Neg logit contributions
ig-0.193
 fort-0.183
iper-0.183
 web-0.178
ches-0.177
Token his
Token ID465
Feature activation-1.91e-01

Pos logit contributions
all+0.105
uts+0.094
 Mike+0.089
 Joey+0.084
 Crab+0.083
Neg logit contributions
 fort-0.172
ig-0.170
ches-0.167
iper-0.167
 web-0.164
Token hands
Token ID2832
Feature activation+2.57e-02

Pos logit contributions
 fort+0.294
 closet+0.292
 slammed+0.282
eh+0.281
ns+0.279
Neg logit contributions
 Joey-0.280
uts-0.278
all-0.275
 pointing-0.257
 Hipp-0.250
Token and
Token ID290
Feature activation-3.41e-02

Pos logit contributions
all+0.043
uts+0.041
Welcome+0.040
 Mike+0.039
 Crab+0.038
Neg logit contributions
 fort-0.039
ig-0.039
ches-0.039
 web-0.037
iper-0.037
Token smiled
Token ID13541
Feature activation+2.50e-02

Pos logit contributions
 fort+0.059
ig+0.058
ches+0.057
iper+0.056
 closet+0.055
Neg logit contributions
all-0.053
 Mike-0.050
uts-0.049
 Joey-0.048
 Crab-0.046
Token.
Token ID13
Feature activation+6.19e-02

Pos logit contributions
anes+0.044
uts+0.041
Welcome+0.041
all+0.041
otion+0.041
Neg logit contributions
 fort-0.036
 head-0.034
 room-0.033
ig-0.032
 closet-0.032
Token They
Token ID1119
Feature activation-7.27e-02

Pos logit contributions
all+0.085
uts+0.081
no+0.075
Welcome+0.072
 Mike+0.071
Neg logit contributions
 fort-0.112
iper-0.111
 web-0.108
ig-0.107
 closet-0.106
Token bigger
Token ID5749
Feature activation+4.28e-02

Pos logit contributions
iper+0.072
 fort+0.071
ig+0.070
 closet+0.068
 web+0.068
Neg logit contributions
all-0.064
 Joey-0.056
Welcome-0.056
 Mike-0.055
no-0.055
Token.
Token ID13
Feature activation+4.14e-02

Pos logit contributions
all+0.054
uts+0.050
 Mike+0.046
 Crab+0.045
Welcome+0.044
Neg logit contributions
 fort-0.087
ig-0.085
ches-0.083
 web-0.083
iper-0.082
Token He
Token ID679
Feature activation-1.13e-01

Pos logit contributions
all+0.057
uts+0.056
no+0.051
ous+0.049
 returning+0.049
Neg logit contributions
 fort-0.072
house-0.070
iper-0.070
ches-0.070
 closet-0.069
Token cl
Token ID537
Feature activation+1.09e-01

Pos logit contributions
 fort+0.184
iper+0.183
ig+0.177
 closet+0.173
 spine+0.167
Neg logit contributions
all-0.181
 Mike-0.168
uts-0.163
 Joey-0.154
no-0.153
Tokenapped
Token ID6320
Feature activation+8.82e-02

Pos logit contributions
all+0.172
uts+0.169
no+0.168
Welcome+0.165
 Lib+0.162
Neg logit contributions
ig-0.186
house-0.166
 web-0.160
iper-0.159
 fort-0.157
Token his
Token ID465
Feature activation-1.91e-01

Pos logit contributions
all+0.109
uts+0.104
 Mike+0.094
 Crab+0.090
Welcome+0.090
Neg logit contributions
 fort-0.180
ig-0.175
ches-0.174
iper-0.173
 web-0.171
Token hands
Token ID2832
Feature activation+2.79e-02

Pos logit contributions
 closet+0.287
 fort+0.286
auldron+0.281
ches+0.277
 clinic+0.275
Neg logit contributions
all-0.268
 Joey-0.263
uts-0.255
 Mike-0.253
 Bang-0.252
Token and
Token ID290
Feature activation-5.10e-02

Pos logit contributions
all+0.049
uts+0.048
Welcome+0.047
 Mike+0.046
 Crab+0.045
Neg logit contributions
ches-0.039
ig-0.039
 fort-0.039
 web-0.037
iper-0.036
Token watched
Token ID7342
Feature activation+1.23e-01

Pos logit contributions
 fort+0.084
iper+0.083
ig+0.083
ches+0.082
 closet+0.078
Neg logit contributions
all-0.082
 Mike-0.078
uts-0.078
 Joey-0.074
 Crab-0.073
Token them
Token ID606
Feature activation-9.91e-02

Pos logit contributions
uts+0.205
Welcome+0.195
all+0.191
 Lib+0.178
Ice+0.178
Neg logit contributions
 fort-0.187
 web-0.180
ches-0.179
ig-0.175
iper-0.163
Token tw
Token ID665
Feature activation+8.09e-02

Pos logit contributions
 fort+0.165
 web+0.157
ig+0.152
ches+0.150
house+0.149
Neg logit contributions
all-0.160
uts-0.154
 Crab-0.154
Welcome-0.153
 Lib-0.147
Token.
Token ID13
Feature activation+4.65e-02

Pos logit contributions
all+0.055
uts+0.053
Welcome+0.048
anes+0.047
no+0.047
Neg logit contributions
 fort-0.064
ig-0.064
ches-0.063
iper-0.063
 web-0.061
Token
Token ID198
Feature activation+8.23e-03

Pos logit contributions
all+0.063
no+0.056
uts+0.056
piring+0.051
Welcome+0.051
Neg logit contributions
 closet-0.083
 fort-0.082
house-0.080
iper-0.080
ches-0.080
TokenJohn
Token ID7554
Feature activation-1.40e-01

Pos logit contributions
all+0.009
uts+0.008
ous+0.008
 Crab+0.007
 Mike+0.007
Neg logit contributions
ches-0.017
iper-0.017
 fort-0.017
ig-0.017
 web-0.017
Token cl
Token ID537
Feature activation+1.04e-01

Pos logit contributions
 fort+0.282
 web+0.261
ig+0.249
 closet+0.248
eh+0.242
Neg logit contributions
all-0.208
 Mike-0.194
 him-0.174
 Joey-0.166
 Dave-0.166
Tokenapped
Token ID6320
Feature activation+8.35e-02

Pos logit contributions
all+0.163
uts+0.157
no+0.151
Welcome+0.151
 Hipp+0.148
Neg logit contributions
ig-0.176
iper-0.163
ets-0.153
ches-0.152
house-0.152
Token his
Token ID465
Feature activation-1.91e-01

Pos logit contributions
all+0.105
uts+0.101
 Mike+0.090
 Crab+0.088
Welcome+0.087
Neg logit contributions
 fort-0.168
ig-0.163
ches-0.162
iper-0.162
 web-0.160
Token hands
Token ID2832
Feature activation+2.94e-02

Pos logit contributions
 fort+0.283
auldron+0.274
ches+0.272
house+0.269
iper+0.265
Neg logit contributions
all-0.281
 Mike-0.280
 pointing-0.276
 Joey-0.275
uts-0.275
Token and
Token ID290
Feature activation-4.26e-02

Pos logit contributions
all+0.052
uts+0.051
Welcome+0.049
 Crab+0.048
 Mike+0.048
Neg logit contributions
ches-0.041
ig-0.041
 fort-0.040
 web-0.038
ets-0.038
Token smiled
Token ID13541
Feature activation+1.83e-02

Pos logit contributions
 fort+0.070
ig+0.069
iper+0.068
ches+0.067
 web+0.065
Neg logit contributions
all-0.070
uts-0.066
 Mike-0.066
 Crab-0.061
 Joey-0.061
Token,
Token ID11
Feature activation-1.05e-04

Pos logit contributions
anes+0.030
all+0.030
uts+0.030
otion+0.029
unch+0.028
Neg logit contributions
 fort-0.027
 head-0.026
ig-0.024
 room-0.024
 closet-0.024
Token proud
Token ID6613
Feature activation+5.41e-02

Pos logit contributions
 fort+0.000
ig+0.000
ches+0.000
 web+0.000
iper+0.000
Neg logit contributions
all-0.000
uts-0.000
anes-0.000
Welcome-0.000
 Mike-0.000
Token
Token ID220
Feature activation+2.50e-02

Pos logit contributions
all+0.059
uts+0.056
no+0.052
ous+0.050
 returning+0.047
Neg logit contributions
 closet-0.078
 fort-0.077
house-0.075
iper-0.075
 web-0.074
Token
Token ID198
Feature activation+1.70e-02

Pos logit contributions
all+0.027
uts+0.024
 Crab+0.023
no+0.023
Welcome+0.022
Neg logit contributions
ches-0.053
 fort-0.052
iper-0.052
ig-0.051
 closet-0.050
TokenHe
Token ID1544
Feature activation-9.71e-02

Pos logit contributions
uts+0.019
all+0.018
ous+0.017
 Crab+0.016
 Mike+0.015
Neg logit contributions
eh-0.035
 fort-0.034
ches-0.034
iper-0.034
ig-0.034
Token cl
Token ID537
Feature activation+1.05e-01

Pos logit contributions
 fort+0.173
ig+0.170
iper+0.162
 web+0.160
ringe+0.156
Neg logit contributions
all-0.144
 Mike-0.138
 him-0.122
uts-0.122
 pointing-0.121
Tokenapped
Token ID6320
Feature activation+8.80e-02

Pos logit contributions
all+0.158
uts+0.155
no+0.147
 Hipp+0.143
Welcome+0.143
Neg logit contributions
ig-0.186
iper-0.175
 fort-0.170
 closet-0.168
house-0.168
Token his
Token ID465
Feature activation-1.91e-01

Pos logit contributions
all+0.107
uts+0.101
 Mike+0.091
 Crab+0.087
Welcome+0.086
Neg logit contributions
 fort-0.182
ig-0.178
ches-0.176
iper-0.175
 web-0.173
Token hands
Token ID2832
Feature activation+2.97e-02

Pos logit contributions
isk+0.313
auldron+0.312
 fort+0.310
house+0.307
eh+0.306
Neg logit contributions
 Mike-0.235
 pointing-0.232
all-0.230
 Bang-0.228
 Wow-0.226
Token and
Token ID290
Feature activation-3.94e-02

Pos logit contributions
all+0.053
uts+0.053
Welcome+0.051
 Crab+0.050
 Cr+0.049
Neg logit contributions
ches-0.041
ig-0.040
 fort-0.040
iper-0.037
 web-0.037
Token wh
Token ID348
Feature activation+1.15e-01

Pos logit contributions
 fort+0.064
ig+0.063
iper+0.062
ches+0.061
 web+0.059
Neg logit contributions
all-0.065
 Mike-0.062
uts-0.062
 Joey-0.058
 Crab-0.057
Tokenirled
Token ID49376
Feature activation+8.71e-02

Pos logit contributions
uts+0.209
all+0.204
Welcome+0.199
 Crab+0.197
 Mike+0.195
Neg logit contributions
ig-0.175
ches-0.156
iper-0.151
eh-0.151
 fort-0.145
Token around
Token ID1088
Feature activation+1.46e-02

Pos logit contributions
all+0.134
uts+0.130
 Crab+0.117
 Mike+0.116
Welcome+0.115
Neg logit contributions
 fort-0.149
ig-0.146
ches-0.146
 web-0.141
iper-0.141
Token
Token ID198
Feature activation+1.99e-02

Pos logit contributions
all+0.073
uts+0.069
no+0.062
ous+0.059
Welcome+0.059
Neg logit contributions
 fort-0.104
iper-0.103
ches-0.103
 closet-0.100
 web-0.100
Token
Token ID198
Feature activation+2.04e-02

Pos logit contributions
all+0.025
uts+0.024
ous+0.023
 Crab+0.022
 Cr+0.021
Neg logit contributions
ches-0.038
eh-0.036
 fort-0.036
iper-0.036
 web-0.036
TokenSam
Token ID16305
Feature activation-1.09e-01

Pos logit contributions
all+0.034
uts+0.033
 Crab+0.032
 Mike+0.032
ous+0.032
Neg logit contributions
eh-0.030
ches-0.029
 fort-0.029
iper-0.029
 web-0.028
Token cl
Token ID537
Feature activation+9.92e-02

Pos logit contributions
 fort+0.194
 web+0.178
 closet+0.176
ig+0.175
iper+0.173
Neg logit contributions
all-0.182
 Mike-0.156
uts-0.150
 Joey-0.145
Joe-0.144
Tokenapped
Token ID6320
Feature activation+8.14e-02

Pos logit contributions
all+0.140
uts+0.131
Welcome+0.125
no+0.123
 Mike+0.118
Neg logit contributions
ig-0.188
 fort-0.178
iper-0.178
ches-0.170
 web-0.170
Token his
Token ID465
Feature activation-1.91e-01

Pos logit contributions
all+0.100
uts+0.091
 Mike+0.085
 Joey+0.080
 Crab+0.080
Neg logit contributions
 fort-0.168
ig-0.166
ches-0.163
iper-0.163
 web-0.161
Token hands
Token ID2832
Feature activation+2.38e-02

Pos logit contributions
ches+0.323
 closet+0.314
 clinic+0.308
auldron+0.308
ns+0.306
Neg logit contributions
 Joey-0.244
all-0.233
 pointing-0.226
 Mike-0.225
uts-0.222
Token.
Token ID13
Feature activation+5.88e-02

Pos logit contributions
all+0.040
uts+0.039
Welcome+0.038
 Crab+0.037
 Cr+0.037
Neg logit contributions
 fort-0.036
ig-0.035
ches-0.034
 web-0.033
iper-0.033
Token "
Token ID366
Feature activation+2.24e-02

Pos logit contributions
all+0.087
no+0.083
uts+0.083
piring+0.079
ful+0.078
Neg logit contributions
 fort-0.089
 closet-0.089
iper-0.088
uel-0.086
ches-0.086
TokenGreat
Token ID13681
Feature activation-3.53e-02

Pos logit contributions
uts+0.033
ous+0.028
all+0.028
 Mike+0.026
 Joey+0.026
Neg logit contributions
eh-0.040
ig-0.039
ns-0.038
 web-0.038
house-0.037
Token job
Token ID1693
Feature activation+9.56e-02

Pos logit contributions
 fort+0.054
ig+0.053
iper+0.050
ches+0.050
 web+0.050
Neg logit contributions
all-0.063
uts-0.061
 Mike-0.056
Welcome-0.056
 Crab-0.055
Token Jen
Token ID13364
Feature activation-1.46e-01

Pos logit contributions
all+0.066
no+0.058
piring+0.057
uts+0.057
ous+0.056
Neg logit contributions
 closet-0.073
 fort-0.067
 web-0.066
 backyard-0.066
iper-0.066
Token and
Token ID290
Feature activation-6.10e-02

Pos logit contributions
 fort+0.335
eh+0.306
iper+0.304
 web+0.304
ig+0.297
Neg logit contributions
all-0.181
uts-0.155
 Mike-0.151
 him-0.123
 Dave-0.121
Token Ben
Token ID3932
Feature activation-1.19e-01

Pos logit contributions
 fort+0.125
ig+0.125
ches+0.122
 web+0.120
iper+0.119
Neg logit contributions
all-0.076
uts-0.071
 Mike-0.069
 Crab-0.065
 Joey-0.064
Token cl
Token ID537
Feature activation+9.81e-02

Pos logit contributions
 fort+0.211
ig+0.199
eh+0.196
 web+0.194
iper+0.193
Neg logit contributions
all-0.187
uts-0.177
 Mike-0.174
 rep-0.160
Welcome-0.159
Tokenapped
Token ID6320
Feature activation+8.78e-02

Pos logit contributions
all+0.149
uts+0.137
no+0.131
 Crab+0.129
Welcome+0.129
Neg logit contributions
ig-0.178
 fort-0.167
iper-0.166
house-0.160
 closet-0.159
Token their
Token ID511
Feature activation-1.91e-01

Pos logit contributions
all+0.129
uts+0.120
 Mike+0.112
Welcome+0.107
 Crab+0.107
Neg logit contributions
 fort-0.159
ig-0.158
iper-0.155
ches-0.155
 web-0.152
Token hands
Token ID2832
Feature activation+2.77e-02

Pos logit contributions
eh+0.363
ches+0.347
 fort+0.346
auldron+0.341
ns+0.333
Neg logit contributions
uts-0.223
all-0.211
 Mike-0.200
 pointing-0.196
 along-0.196
Token and
Token ID290
Feature activation-5.06e-02

Pos logit contributions
all+0.045
uts+0.043
 Mike+0.041
 Crab+0.040
Welcome+0.039
Neg logit contributions
 fort-0.045
ches-0.044
ig-0.043
 web-0.042
 closet-0.042
Token sang
Token ID25889
Feature activation+1.10e-01

Pos logit contributions
 fort+0.093
ig+0.093
ches+0.091
iper+0.090
eh+0.088
Neg logit contributions
 Mike-0.071
all-0.071
uts-0.069
 Cr-0.064
 pointing-0.064
Token along
Token ID1863
Feature activation+2.24e-02

Pos logit contributions
all+0.159
uts+0.152
 Crab+0.147
 Mike+0.141
anes+0.139
Neg logit contributions
 fort-0.200
ches-0.194
 web-0.187
iper-0.187
ig-0.185
Token.
Token ID13
Feature activation+4.26e-02

Pos logit contributions
all+0.029
uts+0.027
 Crab+0.024
 Mike+0.024
anes+0.024
Neg logit contributions
 fort-0.044
ches-0.043
 web-0.043
ig-0.043
iper-0.042
TokenThey
Token ID2990
Feature activation-5.28e-02

Pos logit contributions
all+0.017
uts+0.016
 Mike+0.014
Welcome+0.014
Joe+0.014
Neg logit contributions
 fort-0.032
iper-0.031
ig-0.031
ches-0.031
 closet-0.030
Token laugh
Token ID6487
Feature activation+5.18e-02

Pos logit contributions
 fort+0.098
ig+0.096
iper+0.093
eh+0.093
ches+0.091
Neg logit contributions
all-0.072
 Mike-0.069
uts-0.063
 him-0.063
 Joey-0.063
Token and
Token ID290
Feature activation-4.83e-02

Pos logit contributions
all+0.105
uts+0.101
 Crab+0.099
no+0.098
 Mike+0.098
Neg logit contributions
 fort-0.068
ches-0.062
ets-0.060
 web-0.059
 closet-0.058
Token cl
Token ID537
Feature activation+1.16e-01

Pos logit contributions
 fort+0.082
ig+0.080
ches+0.079
iper+0.079
 web+0.078
Neg logit contributions
all-0.077
uts-0.072
 Mike-0.068
 Crab-0.065
Welcome-0.065
Tokenap
Token ID499
Feature activation+5.76e-02

Pos logit contributions
all+0.270
uts+0.256
no+0.256
Welcome+0.253
 Lib+0.252
Neg logit contributions
ig-0.115
 fort-0.108
 web-0.100
ets-0.100
house-0.098
Token their
Token ID511
Feature activation-1.91e-01

Pos logit contributions
all+0.086
uts+0.081
 Crab+0.076
 Mike+0.075
anes+0.074
Neg logit contributions
 fort-0.104
ig-0.100
ches-0.100
 web-0.099
iper-0.097
Token hands
Token ID2832
Feature activation+3.07e-02

Pos logit contributions
ches+0.353
eh+0.350
iper+0.344
auldron+0.328
issy+0.325
Neg logit contributions
uts-0.228
 Mike-0.216
 pointing-0.212
all-0.206
 cheering-0.206
Token.
Token ID13
Feature activation+4.79e-02

Pos logit contributions
all+0.048
Welcome+0.046
uts+0.046
 Crab+0.046
 Cr+0.045
Neg logit contributions
 fort-0.051
ches-0.048
 web-0.048
ig-0.046
ets-0.046
Token They
Token ID1119
Feature activation-7.89e-02

Pos logit contributions
all+0.080
uts+0.075
no+0.070
ous+0.069
anes+0.068
Neg logit contributions
 fort-0.075
 closet-0.074
 web-0.072
 necks-0.072
 backyard-0.071
Token are
Token ID389
Feature activation-3.89e-02

Pos logit contributions
 fort+0.150
ig+0.148
iper+0.145
eh+0.142
ches+0.141
Neg logit contributions
all-0.107
 Mike-0.098
uts-0.098
 rep-0.089
 Joey-0.089
Token very
Token ID845
Feature activation-9.93e-03

Pos logit contributions
 fort+0.065
ig+0.062
ches+0.061
 web+0.061
iper+0.061
Neg logit contributions
all-0.063
uts-0.060
 Mike-0.056
Welcome-0.054
 Crab-0.054
Token The
Token ID383
Feature activation-1.46e-01

Pos logit contributions
all+0.096
uts+0.089
 Mike+0.079
 Crab+0.077
Welcome+0.077
Neg logit contributions
 fort-0.176
ig-0.173
iper-0.172
ches-0.171
 web-0.169
Token little
Token ID1310
Feature activation-7.22e-02

Pos logit contributions
ches+0.237
ig+0.231
 fort+0.224
iper+0.221
ets+0.220
Neg logit contributions
all-0.236
 Mike-0.220
uts-0.214
 Joey-0.210
 Hipp-0.208
Token boy
Token ID2933
Feature activation-8.81e-02

Pos logit contributions
ches+0.119
ets+0.111
iper+0.105
ns+0.105
 fort+0.104
Neg logit contributions
 Mike-0.119
all-0.116
 Joey-0.114
 Crab-0.110
 Hipp-0.109
Token cl
Token ID537
Feature activation+1.09e-01

Pos logit contributions
 fort+0.166
 closet+0.153
 web+0.152
iper+0.150
eh+0.147
Neg logit contributions
all-0.137
 Mike-0.134
uts-0.123
 pointing-0.114
 Joey-0.112
Tokenapped
Token ID6320
Feature activation+8.34e-02

Pos logit contributions
all+0.174
Welcome+0.165
uts+0.165
no+0.163
 Hipp+0.155
Neg logit contributions
ig-0.187
house-0.165
iper-0.163
 fort-0.159
 web-0.154
Token his
Token ID465
Feature activation-1.90e-01

Pos logit contributions
all+0.122
uts+0.117
 Mike+0.107
 Crab+0.104
Welcome+0.103
Neg logit contributions
 fort-0.152
ig-0.148
ches-0.146
iper-0.146
 web-0.143
Token hands
Token ID2832
Feature activation+2.80e-02

Pos logit contributions
 fort+0.332
auldron+0.328
 closet+0.325
ital+0.308
 clinic+0.307
Neg logit contributions
uts-0.257
all-0.244
 pointing-0.241
 Joey-0.237
 Mike-0.236
Token and
Token ID290
Feature activation-3.94e-02

Pos logit contributions
all+0.053
uts+0.052
Welcome+0.051
 Crab+0.049
 Cr+0.049
Neg logit contributions
 fort-0.035
ig-0.035
ches-0.035
iper-0.033
 web-0.032
Token ran
Token ID4966
Feature activation+6.89e-02

Pos logit contributions
 fort+0.070
ig+0.068
iper+0.067
ches+0.067
 web+0.066
Neg logit contributions
all-0.060
 Mike-0.057
uts-0.056
 Joey-0.053
 Crab-0.052
Token to
Token ID284
Feature activation-1.12e-02

Pos logit contributions
uts+0.105
all+0.104
anes+0.100
unch+0.097
 Crab+0.097
Neg logit contributions
ches-0.114
 fort-0.114
ig-0.109
ets-0.107
iper-0.104
Token the
Token ID262
Feature activation-1.62e-01

Pos logit contributions
 fort+0.017
 closet+0.016
ig+0.016
 web+0.016
 room+0.016
Neg logit contributions
uts-0.021
all-0.019
anes-0.018
Welcome-0.017
ous-0.017
Token applaud
Token ID22517
Feature activation+1.54e-01

Pos logit contributions
 fort+0.007
ig+0.007
ches+0.007
iper+0.007
 web+0.007
Neg logit contributions
all-0.008
uts-0.008
 Mike-0.007
 Crab-0.007
Welcome-0.007
Token.
Token ID13
Feature activation+4.75e-02

Pos logit contributions
all+0.207
uts+0.198
 Crab+0.183
 Cr+0.176
 Mike+0.175
Neg logit contributions
ches-0.287
 fort-0.282
iper-0.277
ig-0.276
ets-0.267
Token They
Token ID1119
Feature activation-8.30e-02

Pos logit contributions
all+0.062
uts+0.060
no+0.052
ous+0.051
 returning+0.050
Neg logit contributions
iper-0.086
 fort-0.086
ches-0.086
 closet-0.084
house-0.083
Token cl
Token ID537
Feature activation+1.11e-01

Pos logit contributions
 fort+0.126
ig+0.123
ches+0.121
iper+0.120
 web+0.118
Neg logit contributions
all-0.146
uts-0.139
 Mike-0.130
 Crab-0.126
Welcome-0.125
Tokenapped
Token ID6320
Feature activation+8.68e-02

Pos logit contributions
all+0.173
uts+0.166
no+0.162
 Crab+0.161
Welcome+0.159
Neg logit contributions
ig-0.189
iper-0.179
ets-0.170
 fort-0.170
house-0.169
Token their
Token ID511
Feature activation-1.90e-01

Pos logit contributions
all+0.132
uts+0.127
 Mike+0.117
 Crab+0.115
Welcome+0.113
Neg logit contributions
 fort-0.151
ig-0.147
ches-0.146
iper-0.145
 web-0.143
Token hands
Token ID2832
Feature activation+2.90e-02

Pos logit contributions
 fort+0.310
eh+0.307
ig+0.295
 closet+0.293
auldron+0.289
Neg logit contributions
all-0.279
 Mike-0.277
uts-0.271
 Joey-0.263
 cheering-0.259
Token and
Token ID290
Feature activation-5.13e-02

Pos logit contributions
all+0.052
uts+0.050
 Crab+0.048
Welcome+0.048
 Cr+0.048
Neg logit contributions
ches-0.041
ig-0.040
 fort-0.040
iper-0.038
 web-0.037
Token paws
Token ID49193
Feature activation+4.65e-02

Pos logit contributions
 fort+0.089
ig+0.087
iper+0.085
ches+0.084
 closet+0.082
Neg logit contributions
all-0.080
uts-0.075
 Mike-0.075
 Joey-0.070
 Crab-0.069
Token,
Token ID11
Feature activation+3.53e-03

Pos logit contributions
all+0.067
uts+0.063
 Crab+0.061
Welcome+0.061
 Cr+0.059
Neg logit contributions
ches-0.083
 fort-0.080
ig-0.080
 web-0.077
iper-0.076
Token and
Token ID290
Feature activation-4.46e-02

Pos logit contributions
all+0.005
uts+0.005
 Mike+0.005
 Joey+0.004
 Crab+0.004
Neg logit contributions
 fort-0.006
ig-0.006
iper-0.006
ches-0.006
 closet-0.006
Token
Token ID198
Feature activation+2.47e-02

Pos logit contributions
all+0.036
uts+0.033
ous+0.032
 Crab+0.031
 Cr+0.031
Neg logit contributions
 fort-0.049
ches-0.048
ig-0.048
iper-0.047
eh-0.046
TokenTom
Token ID13787
Feature activation-9.96e-02

Pos logit contributions
all+0.041
uts+0.039
 Mike+0.037
 Crab+0.037
ous+0.037
Neg logit contributions
 fort-0.038
ig-0.037
iper-0.037
ches-0.037
eh-0.036
Tokenmy
Token ID1820
Feature activation-1.06e-01

Pos logit contributions
 fort+0.169
 web+0.169
ns+0.162
 clinic+0.156
eh+0.156
Neg logit contributions
all-0.174
 Mike-0.149
 Joey-0.138
 him-0.133
Joe-0.133
Token cl
Token ID537
Feature activation+1.00e-01

Pos logit contributions
 fort+0.201
 closet+0.191
 web+0.178
ns+0.178
eh+0.178
Neg logit contributions
all-0.169
 Mike-0.145
uts-0.144
 Joey-0.128
Joe-0.127
Tokenapped
Token ID6320
Feature activation+8.46e-02

Pos logit contributions
all+0.147
uts+0.139
Welcome+0.134
no+0.133
 Hipp+0.129
Neg logit contributions
ig-0.183
iper-0.171
 fort-0.170
house-0.165
 closet-0.162
Token his
Token ID465
Feature activation-1.90e-01

Pos logit contributions
all+0.106
uts+0.097
 Mike+0.090
 Joey+0.085
 Crab+0.085
Neg logit contributions
 fort-0.173
ig-0.171
ches-0.168
iper-0.167
 web-0.166
Token hands
Token ID2832
Feature activation+2.42e-02

Pos logit contributions
 fort+0.318
 closet+0.307
ches+0.298
house+0.294
auldron+0.293
Neg logit contributions
all-0.264
uts-0.260
 Mike-0.255
 Joey-0.254
 pointing-0.244
Token happily
Token ID18177
Feature activation-1.36e-03

Pos logit contributions
all+0.041
uts+0.040
Welcome+0.038
 Mike+0.037
 Crab+0.037
Neg logit contributions
 fort-0.036
ig-0.036
ches-0.036
iper-0.035
 web-0.034
Token and
Token ID290
Feature activation-3.55e-02

Pos logit contributions
ig+0.002
 fort+0.002
ches+0.002
 web+0.002
iper+0.002
Neg logit contributions
all-0.002
uts-0.002
 Mike-0.002
Welcome-0.002
anes-0.002
Token began
Token ID2540
Feature activation+7.92e-02

Pos logit contributions
 fort+0.059
ig+0.057
ches+0.056
iper+0.056
 web+0.055
Neg logit contributions
all-0.059
 Mike-0.056
uts-0.055
 Joey-0.052
 Crab-0.052
Token to
Token ID284
Feature activation-5.79e-03

Pos logit contributions
all+0.112
uts+0.109
Welcome+0.105
anes+0.105
mmmm+0.102
Neg logit contributions
ig-0.136
 fort-0.134
 closet-0.133
 room-0.132
 web-0.130
Token
Token ID198
Feature activation+2.46e-02

Pos logit contributions
 Crab+0.031
all+0.030
uts+0.030
 Cr+0.029
Welcome+0.026
Neg logit contributions
 fort-0.052
ig-0.052
ches-0.051
 web-0.050
 closet-0.049
TokenJo
Token ID9908
Feature activation-9.26e-02

Pos logit contributions
uts+0.038
all+0.038
 Crab+0.038
 Cr+0.036
 Joey+0.034
Neg logit contributions
 fort-0.040
ig-0.040
ches-0.038
 web-0.038
iper-0.038
Tokenjo
Token ID7639
Feature activation-1.38e-01

Pos logit contributions
 fort+0.145
 web+0.131
 closet+0.130
eh+0.128
ns+0.124
Neg logit contributions
all-0.183
 Mike-0.162
ous-0.157
uts-0.156
ful-0.149
Token cl
Token ID537
Feature activation+1.02e-01

Pos logit contributions
 fort+0.253
 closet+0.232
iper+0.223
 web+0.220
eh+0.219
Neg logit contributions
all-0.230
 Mike-0.211
uts-0.200
 Joey-0.185
 pointing-0.182
Tokenapped
Token ID6320
Feature activation+8.42e-02

Pos logit contributions
all+0.164
Welcome+0.160
no+0.157
uts+0.156
 Lib+0.150
Neg logit contributions
ig-0.174
iper-0.155
house-0.147
 fort-0.142
aj-0.141
Token his
Token ID465
Feature activation-1.90e-01

Pos logit contributions
all+0.121
uts+0.117
 Mike+0.106
 Crab+0.104
Welcome+0.104
Neg logit contributions
 fort-0.155
ig-0.151
ches-0.148
iper-0.148
 web-0.147
Token hands
Token ID2832
Feature activation+2.51e-02

Pos logit contributions
 fort+0.299
 closet+0.283
 clinic+0.274
auldron+0.273
ns+0.272
Neg logit contributions
all-0.303
uts-0.303
 Mike-0.288
 Joey-0.288
 pointing-0.284
Token and
Token ID290
Feature activation-3.61e-02

Pos logit contributions
all+0.044
Welcome+0.043
uts+0.043
anes+0.042
 Crab+0.042
Neg logit contributions
ig-0.034
ches-0.033
 fort-0.033
 web-0.031
house-0.031
Token danced
Token ID39480
Feature activation+1.07e-01

Pos logit contributions
 fort+0.059
ig+0.056
iper+0.056
ches+0.055
 web+0.054
Neg logit contributions
all-0.061
uts-0.058
 Mike-0.056
 Joey-0.053
 Crab-0.052
Token along
Token ID1863
Feature activation+2.18e-02

Pos logit contributions
all+0.161
uts+0.155
 Crab+0.142
Welcome+0.140
 Mike+0.140
Neg logit contributions
 fort-0.190
ches-0.184
ig-0.182
 web-0.179
iper-0.178
Token as
Token ID355
Feature activation+3.98e-02

Pos logit contributions
all+0.033
uts+0.033
anes+0.029
Welcome+0.029
unch+0.028
Neg logit contributions
 fort-0.038
 web-0.037
ig-0.036
ches-0.036
 closet-0.035
Token
Token ID198
Feature activation+1.08e-02

Pos logit contributions
all+0.074
uts+0.066
Welcome+0.058
ous+0.057
no+0.057
Neg logit contributions
 fort-0.135
iper-0.131
 closet-0.131
 web-0.130
ches-0.129
Token
Token ID198
Feature activation+1.14e-02

Pos logit contributions
all+0.011
uts+0.010
 Crab+0.009
 Cr+0.009
 Mike+0.009
Neg logit contributions
 fort-0.024
ches-0.023
 web-0.023
iper-0.023
ig-0.023
TokenThey
Token ID2990
Feature activation-5.97e-02

Pos logit contributions
all+0.019
uts+0.018
 Mike+0.017
 Crab+0.016
Welcome+0.016
Neg logit contributions
 fort-0.019
ig-0.018
ches-0.018
iper-0.018
 web-0.018
Token cl
Token ID537
Feature activation+1.09e-01

Pos logit contributions
ig+0.104
 fort+0.104
 web+0.102
ches+0.101
iper+0.098
Neg logit contributions
 Mike-0.090
all-0.085
 him-0.081
ful-0.080
 rep-0.078
Tokenapped
Token ID6320
Feature activation+8.58e-02

Pos logit contributions
all+0.153
uts+0.143
no+0.133
 Crab+0.131
Welcome+0.131
Neg logit contributions
ig-0.205
 fort-0.203
iper-0.197
 web-0.192
 closet-0.191
Token their
Token ID511
Feature activation-1.90e-01

Pos logit contributions
all+0.123
uts+0.113
 Mike+0.107
 Joey+0.100
 him+0.099
Neg logit contributions
ig-0.159
ches-0.156
iper-0.155
 fort-0.153
eh-0.152
Token hands
Token ID2832
Feature activation+2.98e-02

Pos logit contributions
eh+0.368
ches+0.363
auldron+0.363
isk+0.351
ital+0.350
Neg logit contributions
 pointing-0.181
 Mike-0.171
uts-0.170
ges-0.164
 Bang-0.162
Token and
Token ID290
Feature activation-4.80e-02

Pos logit contributions
all+0.053
uts+0.050
 Crab+0.049
 Mike+0.048
 Cr+0.048
Neg logit contributions
 fort-0.045
ig-0.042
ches-0.042
 web-0.041
 closet-0.040
Token said
Token ID531
Feature activation+3.70e-02

Pos logit contributions
ig+0.093
ches+0.091
iper+0.088
eh+0.085
 fort+0.084
Neg logit contributions
 Mike-0.068
 pointing-0.063
 cheering-0.061
 rep-0.061
all-0.060
Token,
Token ID11
Feature activation+2.51e-03

Pos logit contributions
all+0.075
Welcome+0.069
uts+0.068
no+0.067
Ice+0.067
Neg logit contributions
ig-0.045
 fort-0.044
 web-0.040
ches-0.039
ows-0.038
Token "
Token ID366
Feature activation+1.82e-02

Pos logit contributions
all+0.004
reating+0.004
no+0.004
uts+0.004
anes+0.004
Neg logit contributions
 fort-0.003
 head-0.003
 web-0.003
 closet-0.003
 room-0.003
Token.
Token ID13
Feature activation+5.64e-02

Pos logit contributions
 fort+0.287
ig+0.279
ches+0.272
iper+0.271
 web+0.271
Neg logit contributions
all-0.228
uts-0.215
 Mike-0.201
Welcome-0.198
 Crab-0.196
Token Tim
Token ID5045
Feature activation-1.25e-01

Pos logit contributions
ful+0.087
all+0.087
uts+0.086
piring+0.081
no+0.079
Neg logit contributions
house-0.091
 fort-0.087
 backyard-0.087
 room-0.086
 closet-0.085
Tokenmy
Token ID1820
Feature activation-1.04e-01

Pos logit contributions
 fort+0.243
ns+0.241
 web+0.237
eh+0.231
 clinic+0.229
Neg logit contributions
all-0.191
 Mike-0.153
 him-0.148
that-0.139
 Joey-0.136
Token cl
Token ID537
Feature activation+9.63e-02

Pos logit contributions
 fort+0.187
eh+0.172
iper+0.171
ns+0.166
 closet+0.164
Neg logit contributions
all-0.175
uts-0.156
 Mike-0.153
 pointing-0.143
't-0.139
Tokenapped
Token ID6320
Feature activation+8.69e-02

Pos logit contributions
all+0.139
uts+0.131
no+0.124
Welcome+0.122
 Joey+0.120
Neg logit contributions
ig-0.178
 fort-0.166
iper-0.164
house-0.160
 web-0.160
Token his
Token ID465
Feature activation-1.90e-01

Pos logit contributions
all+0.113
uts+0.101
 Mike+0.095
 Joey+0.089
 Crab+0.089
Neg logit contributions
 fort-0.176
ig-0.174
iper-0.171
ches-0.170
 web-0.168
Token hands
Token ID2832
Feature activation+2.54e-02

Pos logit contributions
 fort+0.339
eh+0.330
ns+0.327
 closet+0.319
isk+0.318
Neg logit contributions
all-0.245
uts-0.244
 pointing-0.243
 Bang-0.219
 along-0.217
Token too
Token ID1165
Feature activation+7.87e-03

Pos logit contributions
all+0.044
uts+0.044
 Mike+0.041
 Crab+0.041
Welcome+0.041
Neg logit contributions
 fort-0.036
ig-0.036
ches-0.036
 web-0.034
 closet-0.033
Token and
Token ID290
Feature activation-3.00e-02

Pos logit contributions
all+0.013
uts+0.012
 Crab+0.012
Welcome+0.011
anes+0.011
Neg logit contributions
 fort-0.012
ches-0.012
ig-0.012
 web-0.012
ets-0.012
Token smiled
Token ID13541
Feature activation+3.05e-02

Pos logit contributions
 fort+0.052
ig+0.051
iper+0.050
ches+0.050
 web+0.049
Neg logit contributions
all-0.047
uts-0.044
 Mike-0.041
 Crab-0.040
Welcome-0.039
Token.
Token ID13
Feature activation+5.69e-02

Pos logit contributions
anes+0.050
uts+0.049
unch+0.048
all+0.048
otion+0.048
Neg logit contributions
 fort-0.046
 head-0.042
 room-0.041
 closet-0.040
house-0.040
Token prints
Token ID20842
Feature activation+1.07e-01

Pos logit contributions
all+0.079
uts+0.073
 Mike+0.067
 Crab+0.065
Welcome+0.064
Neg logit contributions
 fort-0.130
ig-0.126
ches-0.125
 web-0.123
iper-0.123
Token.
Token ID13
Feature activation+6.03e-02

Pos logit contributions
all+0.142
uts+0.126
 Mike+0.124
 Crab+0.121
 Cr+0.118
Neg logit contributions
 fort-0.212
ches-0.204
 web-0.200
ig-0.199
ets-0.197
Token Lucky
Token ID27963
Feature activation-9.36e-02

Pos logit contributions
all+0.077
uts+0.072
 Mike+0.064
no+0.063
Welcome+0.062
Neg logit contributions
 fort-0.120
ches-0.117
iper-0.117
ig-0.116
 web-0.115
Token cl
Token ID537
Feature activation+1.05e-01

Pos logit contributions
 fort+0.165
ig+0.162
iper+0.153
eh+0.151
 closet+0.148
Neg logit contributions
all-0.146
uts-0.139
 Mike-0.132
 Joey-0.123
 Crab-0.117
Tokenapped
Token ID6320
Feature activation+8.96e-02

Pos logit contributions
all+0.152
uts+0.141
Welcome+0.136
no+0.135
 Lib+0.131
Neg logit contributions
ig-0.196
 fort-0.186
iper-0.184
 web-0.179
ches-0.177
Token his
Token ID465
Feature activation-1.90e-01

Pos logit contributions
all+0.120
uts+0.112
 Mike+0.104
 Crab+0.099
 Joey+0.097
Neg logit contributions
 fort-0.175
ig-0.172
ches-0.169
iper-0.169
 web-0.166
Token paws
Token ID49193
Feature activation+2.48e-02

Pos logit contributions
 closet+0.338
auldron+0.337
eh+0.336
 clinic+0.335
ital+0.331
Neg logit contributions
uts-0.212
 pointing-0.203
 Bang-0.200
 Joey-0.200
all-0.195
Token in
Token ID287
Feature activation-4.45e-02

Pos logit contributions
all+0.043
uts+0.040
Welcome+0.040
 Mike+0.039
 Crab+0.038
Neg logit contributions
 fort-0.037
ig-0.037
ches-0.036
 web-0.036
iper-0.035
Token excitement
Token ID14067
Feature activation+8.54e-02

Pos logit contributions
 web+0.069
 fort+0.068
 pile+0.067
 room+0.066
 closet+0.065
Neg logit contributions
uts-0.085
anes-0.078
all-0.077
ous-0.072
unch-0.070
Token and
Token ID290
Feature activation-3.91e-02

Pos logit contributions
all+0.137
Welcome+0.130
uts+0.127
 Cr+0.126
 Crab+0.125
Neg logit contributions
 fort-0.139
ches-0.132
ig-0.131
 web-0.129
iper-0.129
Token cheered
Token ID34767
Feature activation+1.19e-01

Pos logit contributions
 fort+0.064
ig+0.062
ches+0.061
iper+0.061
 web+0.060
Neg logit contributions
all-0.065
uts-0.061
 Mike-0.058
 Crab-0.056
 Joey-0.055
TokenThey
Token ID2990
Feature activation-4.97e-02

Pos logit contributions
all+0.028
uts+0.026
 Mike+0.024
Welcome+0.023
 Crab+0.023
Neg logit contributions
 fort-0.037
ig-0.036
ches-0.036
iper-0.036
 web-0.035
Token kissed
Token ID27946
Feature activation+1.21e-01

Pos logit contributions
 fort+0.092
ig+0.085
 web+0.085
iper+0.084
eh+0.083
Neg logit contributions
 Mike-0.069
all-0.069
 him-0.065
ful-0.061
uts-0.061
Token and
Token ID290
Feature activation-4.53e-02

Pos logit contributions
all+0.140
 Mike+0.126
uts+0.126
 him+0.119
no+0.118
Neg logit contributions
 fort-0.257
eh-0.251
ig-0.250
iper-0.248
ches-0.245
Token smiled
Token ID13541
Feature activation+3.29e-02

Pos logit contributions
 fort+0.076
ig+0.075
iper+0.071
ches+0.070
eh+0.069
Neg logit contributions
all-0.070
 Mike-0.070
no-0.066
 rep-0.065
uts-0.065
Token and
Token ID290
Feature activation-4.56e-02

Pos logit contributions
all+0.049
uts+0.046
 Mike+0.045
 Crab+0.045
anes+0.045
Neg logit contributions
 fort-0.060
ig-0.055
 web-0.054
 closet-0.053
ches-0.052
Token played
Token ID2826
Feature activation+1.10e-01

Pos logit contributions
 fort+0.071
ig+0.068
ches+0.066
iper+0.066
eh+0.064
Neg logit contributions
all-0.079
uts-0.077
 Mike-0.075
 Crab-0.071
no-0.071
Token for
Token ID329
Feature activation+5.37e-03

Pos logit contributions
all+0.106
uts+0.098
 Mike+0.088
 Crab+0.081
no+0.081
Neg logit contributions
iper-0.251
 fort-0.249
ig-0.248
ches-0.247
 closet-0.241
Token a
Token ID257
Feature activation-8.36e-02

Pos logit contributions
all+0.006
 Mike+0.005
uts+0.005
no+0.005
Welcome+0.005
Neg logit contributions
ig-0.012
 fort-0.012
iper-0.011
ches-0.011
 closet-0.011
Token while
Token ID981
Feature activation+8.40e-02

Pos logit contributions
 fort+0.155
iper+0.154
ig+0.154
 closet+0.150
ches+0.150
Neg logit contributions
all-0.116
uts-0.108
 Mike-0.099
no-0.098
Welcome-0.098
Token.
Token ID13
Feature activation+6.11e-02

Pos logit contributions
all+0.112
uts+0.107
 Crab+0.097
 Mike+0.094
 Cr+0.093
Neg logit contributions
 fort-0.165
ig-0.164
 web-0.160
ches-0.157
 closet-0.156
Token They
Token ID1119
Feature activation-7.10e-02

Pos logit contributions
all+0.077
uts+0.072
 Mike+0.066
 Crab+0.063
Welcome+0.062
Neg logit contributions
 fort-0.125
ig-0.122
ches-0.120
iper-0.120
 web-0.119
Token see
Token ID766
Feature activation+6.99e-02

Pos logit contributions
all+0.034
uts+0.033
 Mike+0.030
Welcome+0.030
 Crab+0.029
Neg logit contributions
 fort-0.028
 web-0.027
ig-0.027
iper-0.026
 closet-0.026
Token the
Token ID262
Feature activation-1.41e-01

Pos logit contributions
all+0.099
uts+0.098
 Crab+0.084
 Mike+0.084
 Cr+0.083
Neg logit contributions
 fort-0.129
ig-0.126
ches-0.124
 web-0.124
 closet-0.123
Token world
Token ID995
Feature activation+3.23e-02

Pos logit contributions
 fort+0.236
ig+0.223
 web+0.221
iper+0.217
 closet+0.217
Neg logit contributions
all-0.231
uts-0.228
 Mike-0.208
 Crab-0.200
 Cr-0.198
Token and
Token ID290
Feature activation-1.27e-02

Pos logit contributions
all+0.045
uts+0.043
 Mike+0.040
 Crab+0.038
Welcome+0.037
Neg logit contributions
 fort-0.061
ig-0.059
ches-0.059
iper-0.058
 web-0.058
Token have
Token ID423
Feature activation+1.87e-02

Pos logit contributions
 fort+0.023
ig+0.023
ches+0.023
iper+0.023
 web+0.022
Neg logit contributions
all-0.019
uts-0.017
 Mike-0.016
 Crab-0.016
Welcome-0.015
Token adventures
Token ID17545
Feature activation+1.14e-01

Pos logit contributions
all+0.023
uts+0.021
 Mike+0.020
Welcome+0.019
no+0.019
Neg logit contributions
ig-0.039
ches-0.038
 fort-0.037
iper-0.037
eh-0.035
Token.
Token ID13
Feature activation+6.78e-02

Pos logit contributions
all+0.144
uts+0.133
 Crab+0.122
 Mike+0.122
 Cr+0.120
Neg logit contributions
 fort-0.231
ig-0.223
ches-0.222
 web-0.219
iper-0.217
Token She
Token ID1375
Feature activation-1.05e-01

Pos logit contributions
all+0.060
 Mike+0.053
uts+0.052
 Lib+0.047
 Joey+0.046
Neg logit contributions
ig-0.167
 fort-0.165
ches-0.161
eh-0.158
iper-0.157
Token waved
Token ID26834
Feature activation+8.08e-02

Pos logit contributions
 web+0.201
 fort+0.201
iper+0.193
 spine+0.190
ets+0.187
Neg logit contributions
all-0.145
 Mike-0.130
 Hipp-0.118
 pointing-0.117
Joe-0.116
Token goodbye
Token ID24829
Feature activation+5.91e-02

Pos logit contributions
all+0.092
uts+0.082
 Mike+0.079
 Joey+0.072
Welcome+0.071
Neg logit contributions
 fort-0.177
ig-0.174
ches-0.172
iper-0.169
 web-0.169
Token to
Token ID284
Feature activation-6.35e-03

Pos logit contributions
all+0.051
uts+0.046
 Mike+0.037
no+0.034
 Joey+0.034
Neg logit contributions
 fort-0.146
ig-0.145
ches-0.143
iper-0.142
 closet-0.141
Token realized
Token ID6939
Feature activation+4.44e-02

Pos logit contributions
 fort+0.013
ig+0.012
 web+0.012
iper+0.012
 closet+0.011
Neg logit contributions
all-0.017
uts-0.016
 Mike-0.016
 Crab-0.015
 Joey-0.015
Token that
Token ID326
Feature activation-9.97e-03

Pos logit contributions
uts+0.062
all+0.061
Welcome+0.060
anes+0.060
unch+0.059
Neg logit contributions
ig-0.073
 closet-0.069
 fort-0.068
ches-0.068
 belt-0.068
Token they
Token ID484
Feature activation-6.79e-02

Pos logit contributions
 fort+0.018
 closet+0.018
 room+0.018
ig+0.018
 web+0.017
Neg logit contributions
uts-0.013
all-0.013
anes-0.012
ous-0.011
unch-0.011
Token could
Token ID714
Feature activation+7.66e-02

Pos logit contributions
 fort+0.115
ig+0.112
iper+0.108
 web+0.108
eh+0.108
Neg logit contributions
all-0.112
uts-0.105
 Mike-0.100
 Joey-0.096
Welcome-0.094
Token only
Token ID691
Feature activation-6.58e-03

Pos logit contributions
all+0.132
uts+0.127
 Mike+0.119
Welcome+0.115
 Crab+0.115
Neg logit contributions
 fort-0.119
ig-0.116
ches-0.114
iper-0.113
 web-0.113
Token succeed
Token ID6758
Feature activation+1.49e-01

Pos logit contributions
 fort+0.011
ig+0.011
iper+0.011
ches+0.011
 web+0.010
Neg logit contributions
all-0.011
uts-0.010
 Mike-0.009
 Crab-0.009
no-0.009
Token if
Token ID611
Feature activation+6.91e-02

Pos logit contributions
all+0.186
uts+0.177
 Mike+0.161
Welcome+0.159
 Crab+0.158
Neg logit contributions
 fort-0.295
ig-0.294
ches-0.290
 web-0.284
iper-0.284
Token they
Token ID484
Feature activation-4.51e-02

Pos logit contributions
all+0.079
uts+0.076
anes+0.066
Welcome+0.063
 Crab+0.062
Neg logit contributions
ig-0.141
 fort-0.140
iper-0.137
ches-0.136
 closet-0.135
Token worked
Token ID3111
Feature activation+1.17e-01

Pos logit contributions
 fort+0.068
ig+0.065
iper+0.064
ches+0.064
 web+0.063
Neg logit contributions
all-0.081
uts-0.077
 Mike-0.073
 Crab-0.071
 Joey-0.070
Token together
Token ID1978
Feature activation+5.05e-02

Pos logit contributions
all+0.163
uts+0.154
 Mike+0.142
 Crab+0.137
Welcome+0.136
Neg logit contributions
 fort-0.219
ig-0.216
ches-0.213
iper-0.211
 web-0.208
Token -
Token ID532
Feature activation+3.54e-02

Pos logit contributions
all+0.067
uts+0.065
Welcome+0.061
 Cr+0.060
 Crab+0.060
Neg logit contributions
ig-0.094
 fort-0.094
ches-0.093
 web-0.091
iper-0.089
Token her
Token ID607
Feature activation-1.43e-01

Pos logit contributions
all+0.066
uts+0.059
 him+0.059
 Mike+0.050
 Crab+0.049
Neg logit contributions
ig-0.193
 fort-0.189
ches-0.187
iper-0.183
 closet-0.182
Token purple
Token ID14032
Feature activation-2.26e-02

Pos logit contributions
iper+0.226
ches+0.224
 fort+0.207
house+0.203
eh+0.198
Neg logit contributions
all-0.233
 Crab-0.210
 him-0.205
 pointing-0.204
uts-0.204
Token crown
Token ID12389
Feature activation+4.15e-02

Pos logit contributions
iper+0.030
ches+0.029
ns+0.027
 forgot+0.027
 fort+0.026
Neg logit contributions
all-0.043
uts-0.040
 Crab-0.039
 him-0.038
 Mike-0.038
Token and
Token ID290
Feature activation-3.25e-02

Pos logit contributions
all+0.047
uts+0.046
ful+0.033
no+0.032
't+0.031
Neg logit contributions
 fort-0.089
 closet-0.088
 web-0.087
iper-0.087
ns-0.085
Token remembered
Token ID12086
Feature activation+5.15e-02

Pos logit contributions
ig+0.052
ches+0.051
 fort+0.051
iper+0.050
eh+0.048
Neg logit contributions
all-0.054
uts-0.053
 returning-0.049
 him-0.048
 Mike-0.048
Token how
Token ID703
Feature activation+1.10e-01

Pos logit contributions
all+0.058
uts+0.056
 Mike+0.049
Welcome+0.048
anes+0.047
Neg logit contributions
 fort-0.109
ig-0.106
 web-0.105
iper-0.105
ches-0.105
Token the
Token ID262
Feature activation-1.24e-01

Pos logit contributions
all+0.145
uts+0.136
 Mike+0.127
 Crab+0.122
Welcome+0.119
Neg logit contributions
 fort-0.213
ig-0.208
ches-0.206
iper-0.206
 web-0.203
Token knight
Token ID22062
Feature activation+2.70e-02

Pos logit contributions
ig+0.195
iper+0.193
ches+0.191
aj+0.175
 fort+0.171
Neg logit contributions
all-0.211
Welcome-0.202
 Crab-0.198
 rep-0.188
uts-0.188
Token saved
Token ID7448
Feature activation+9.88e-02

Pos logit contributions
all+0.047
uts+0.045
 him+0.041
 Mike+0.040
 Crab+0.040
Neg logit contributions
 fort-0.042
ig-0.041
iper-0.040
 web-0.040
eh-0.039
Token her
Token ID607
Feature activation-1.33e-01

Pos logit contributions
all+0.115
uts+0.107
 Mike+0.096
 Crab+0.091
Welcome+0.091
Neg logit contributions
 fort-0.210
ig-0.205
ches-0.203
iper-0.202
 web-0.200
Token.
Token ID13
Feature activation+5.25e-02

Pos logit contributions
 fort+0.213
ig+0.209
iper+0.206
ches+0.206
 web+0.201
Neg logit contributions
all-0.223
uts-0.211
 Mike-0.197
 Crab-0.192
Welcome-0.189
Token were
Token ID547
Feature activation-3.61e-02

Pos logit contributions
ig+0.216
 web+0.205
 fort+0.205
iper+0.204
ches+0.203
Neg logit contributions
all-0.182
 Mike-0.175
 him-0.173
uts-0.172
Welcome-0.169
Token twins
Token ID20345
Feature activation-3.32e-02

Pos logit contributions
ches+0.077
 fort+0.075
ig+0.075
 web+0.075
iper+0.074
Neg logit contributions
all-0.040
uts-0.034
 going-0.034
 Mike-0.033
't-0.031
Token who
Token ID508
Feature activation-3.60e-02

Pos logit contributions
 fort+0.077
iper+0.076
ig+0.075
ches+0.075
 web+0.073
Neg logit contributions
all-0.032
uts-0.029
 Mike-0.027
 Crab-0.025
no-0.025
Token liked
Token ID8288
Feature activation+6.29e-02

Pos logit contributions
ig+0.053
 fort+0.052
iper+0.050
 web+0.050
ches+0.049
Neg logit contributions
all-0.067
uts-0.064
 Mike-0.063
Welcome-0.060
 Joey-0.059
Token to
Token ID284
Feature activation-4.76e-04

Pos logit contributions
all+0.090
uts+0.088
unch+0.076
anes+0.076
 Mike+0.075
Neg logit contributions
 fort-0.120
 room-0.111
 closet-0.111
 backyard-0.105
 web-0.104
Token play
Token ID711
Feature activation+1.09e-01

Pos logit contributions
 fort+0.001
 closet+0.001
 web+0.001
ig+0.001
house+0.001
Neg logit contributions
all-0.001
uts-0.001
Welcome-0.001
no-0.001
 Mike-0.001
Token outside
Token ID2354
Feature activation+5.80e-02

Pos logit contributions
all+0.134
uts+0.125
 Mike+0.114
 Crab+0.109
Welcome+0.107
Neg logit contributions
 fort-0.225
ig-0.221
iper-0.219
ches-0.218
 web-0.215
Token.
Token ID13
Feature activation+6.19e-02

Pos logit contributions
all+0.075
uts+0.072
 Mike+0.064
Welcome+0.062
 Crab+0.061
Neg logit contributions
 fort-0.117
ig-0.112
ches-0.111
 web-0.111
 closet-0.109
Token They
Token ID1119
Feature activation-7.06e-02

Pos logit contributions
all+0.102
uts+0.099
ous+0.089
anes+0.089
no+0.088
Neg logit contributions
 fort-0.102
 closet-0.099
ches-0.095
iper-0.094
ig-0.093
Token had
Token ID550
Feature activation-6.29e-03

Pos logit contributions
ig+0.129
 fort+0.126
 web+0.123
aj+0.118
ches+0.118
Neg logit contributions
 Mike-0.103
all-0.100
 Joey-0.095
 him-0.094
uts-0.091
Token many
Token ID867
Feature activation-1.14e-02

Pos logit contributions
ig+0.017
ches+0.016
iper+0.016
 fort+0.015
ets+0.015
Neg logit contributions
 Mike-0.004
all-0.004
no-0.004
uts-0.004
 going-0.004
Token The
Token ID383
Feature activation-1.39e-01

Pos logit contributions
all+0.082
uts+0.076
 Mike+0.070
 Crab+0.067
Welcome+0.066
Neg logit contributions
 fort-0.126
ig-0.123
iper-0.121
ches-0.121
 web-0.120
Token little
Token ID1310
Feature activation-6.35e-02

Pos logit contributions
iper+0.236
ches+0.235
ig+0.233
ox+0.218
 necks+0.218
Neg logit contributions
all-0.207
 Joey-0.202
 Hipp-0.198
Welcome-0.197
 Mike-0.189
Token girl
Token ID2576
Feature activation-9.39e-02

Pos logit contributions
ches+0.109
ns+0.104
iper+0.100
aj+0.099
eh+0.098
Neg logit contributions
 Joey-0.099
all-0.099
 Mike-0.097
 Abby-0.096
Welcome-0.096
Token was
Token ID373
Feature activation-4.15e-02

Pos logit contributions
 fort+0.187
iper+0.179
ets+0.177
ringe+0.173
 closet+0.170
Neg logit contributions
all-0.127
 Mike-0.123
uts-0.107
 Joey-0.106
 pointing-0.106
Token safe
Token ID3338
Feature activation+5.41e-02

Pos logit contributions
 fort+0.072
ig+0.071
iper+0.070
ches+0.070
 web+0.067
Neg logit contributions
all-0.066
uts-0.061
 Mike-0.058
 Joey-0.055
 Crab-0.054
Token.
Token ID13
Feature activation+5.79e-02

Pos logit contributions
all+0.084
uts+0.080
 Mike+0.073
 Cr+0.072
Welcome+0.072
Neg logit contributions
 fort-0.094
ig-0.091
 web-0.088
 closet-0.087
ches-0.087
Token
Token ID220
Feature activation+3.52e-02

Pos logit contributions
all+0.069
uts+0.064
 Crab+0.056
 Mike+0.056
no+0.055
Neg logit contributions
 fort-0.118
iper-0.117
ig-0.117
 web-0.116
 closet-0.115
Token
Token ID198
Feature activation+2.69e-02

Pos logit contributions
all+0.036
 Crab+0.030
uts+0.030
Welcome+0.029
 Cr+0.029
Neg logit contributions
 fort-0.076
ches-0.076
ig-0.075
iper-0.075
 web-0.074
Token
Token ID198
Feature activation+2.63e-02

Pos logit contributions
all+0.033
 Crab+0.031
uts+0.031
 Cr+0.030
 Mike+0.030
Neg logit contributions
 web-0.050
ches-0.050
eh-0.049
iper-0.049
ig-0.048
TokenShe
Token ID3347
Feature activation-9.35e-02

Pos logit contributions
all+0.046
uts+0.045
 Mike+0.043
 Crab+0.042
 Joey+0.041
Neg logit contributions
 fort-0.038
ig-0.038
 web-0.038
iper-0.037
ches-0.037
Token was
Token ID373
Feature activation-4.30e-02

Pos logit contributions
 fort+0.179
iper+0.169
ringe+0.168
ets+0.167
 spine+0.163
Neg logit contributions
all-0.130
 Mike-0.125
 Joey-0.113
 ever-0.109
 returning-0.107
Token,
Token ID11
Feature activation+2.24e-02

Pos logit contributions
all+0.037
uts+0.034
 Mike+0.034
 Joey+0.030
no+0.030
Neg logit contributions
iper-0.061
 fort-0.060
ches-0.059
ig-0.059
 web-0.059
Token she
Token ID673
Feature activation-9.81e-02

Pos logit contributions
all+0.021
uts+0.020
 Mike+0.018
 Crab+0.016
 Joey+0.016
Neg logit contributions
 fort-0.052
ig-0.051
ches-0.051
iper-0.051
 web-0.050
Token was
Token ID373
Feature activation-3.13e-02

Pos logit contributions
 fort+0.176
iper+0.176
ig+0.169
 web+0.167
ets+0.165
Neg logit contributions
all-0.141
 him-0.131
 Mike-0.130
 pointing-0.126
't-0.125
Token not
Token ID407
Feature activation-8.50e-04

Pos logit contributions
 fort+0.055
ig+0.055
iper+0.054
ches+0.052
 web+0.051
Neg logit contributions
all-0.049
uts-0.045
 Mike-0.043
no-0.041
 pointing-0.041
Token happy
Token ID3772
Feature activation+5.49e-02

Pos logit contributions
 fort+0.001
ig+0.001
ches+0.001
iper+0.001
 web+0.001
Neg logit contributions
all-0.001
uts-0.001
 Mike-0.001
 Crab-0.001
Welcome-0.001
Token.
Token ID13
Feature activation+5.51e-02

Pos logit contributions
all+0.080
 Cr+0.078
 Hipp+0.077
anes+0.077
Welcome+0.075
Neg logit contributions
 fort-0.098
 closet-0.093
 room-0.092
 web-0.088
ets-0.086
Token She
Token ID1375
Feature activation-1.09e-01

Pos logit contributions
all+0.084
no+0.072
uts+0.071
ous+0.068
 returning+0.068
Neg logit contributions
 closet-0.098
 fort-0.094
 web-0.092
 room-0.090
house-0.089
Token saw
Token ID2497
Feature activation+4.80e-02

Pos logit contributions
 fort+0.226
ig+0.220
 spine+0.209
iper+0.208
 web+0.205
Neg logit contributions
 Mike-0.137
all-0.134
 him-0.125
 ever-0.121
 Rob-0.113
Token toys
Token ID14958
Feature activation+4.07e-02

Pos logit contributions
all+0.069
uts+0.064
Welcome+0.057
 Mike+0.056
 Crab+0.056
Neg logit contributions
 fort-0.088
 closet-0.086
 web-0.084
ches-0.084
iper-0.084
Token scattered
Token ID16830
Feature activation+1.03e-01

Pos logit contributions
all+0.054
uts+0.052
 Mike+0.047
 Crab+0.044
Welcome+0.044
Neg logit contributions
iper-0.079
 fort-0.077
ig-0.077
ches-0.076
 web-0.075
Token everywhere
Token ID8347
Feature activation+1.02e-01

Pos logit contributions
all+0.140
uts+0.130
 Mike+0.129
 Joey+0.121
 him+0.121
Neg logit contributions
iper-0.193
ig-0.193
 fort-0.190
ches-0.186
 web-0.184
Token the
Token ID262
Feature activation-1.48e-01

Pos logit contributions
 web+0.048
 closet+0.047
 room+0.047
 fort+0.046
iper+0.045
Neg logit contributions
uts-0.058
all-0.054
unch-0.052
anes-0.050
 Cr-0.048
Token world
Token ID995
Feature activation+3.10e-02

Pos logit contributions
ches+0.279
iper+0.277
ig+0.273
 fort+0.267
aj+0.265
Neg logit contributions
Welcome-0.198
all-0.180
 sunset-0.178
no-0.171
 sunrise-0.171
Token.
Token ID13
Feature activation+5.64e-02

Pos logit contributions
all+0.036
uts+0.033
 Crab+0.031
 Mike+0.030
 Cr+0.030
Neg logit contributions
 fort-0.065
ches-0.065
ig-0.063
 web-0.063
iper-0.062
Token From
Token ID3574
Feature activation-2.04e-02

Pos logit contributions
all+0.069
uts+0.065
 Mike+0.058
 Crab+0.057
no+0.056
Neg logit contributions
 fort-0.115
ig-0.113
ches-0.112
iper-0.112
 web-0.111
Token that
Token ID326
Feature activation-2.35e-02

Pos logit contributions
 fort+0.049
ig+0.047
ches+0.046
iper+0.046
 web+0.046
Neg logit contributions
all-0.020
uts-0.017
 Mike-0.016
 Joey-0.015
 Crab-0.015
Token day
Token ID1110
Feature activation+4.60e-02

Pos logit contributions
 fort+0.050
ns+0.049
iper+0.049
ches+0.048
 necks+0.048
Neg logit contributions
all-0.027
no-0.022
Welcome-0.022
 Mike-0.021
't-0.021
Token on
Token ID319
Feature activation+3.15e-03

Pos logit contributions
all+0.061
uts+0.058
 Crab+0.053
 Mike+0.053
 Joey+0.051
Neg logit contributions
ig-0.092
 fort-0.087
ches-0.087
iper-0.085
 web-0.084
Token,
Token ID11
Feature activation+1.31e-02

Pos logit contributions
all+0.003
 Mike+0.003
uts+0.003
 Joey+0.003
't+0.003
Neg logit contributions
ns-0.007
eh-0.007
oscope-0.007
 fort-0.007
ches-0.007
Token Lily
Token ID20037
Feature activation-1.38e-01

Pos logit contributions
all+0.019
uts+0.017
 Mike+0.017
 Cr+0.016
Welcome+0.016
Neg logit contributions
 fort-0.024
ig-0.024
iper-0.024
ches-0.024
 web-0.023
Token would
Token ID561
Feature activation+3.76e-02

Pos logit contributions
 fort+0.242
eh+0.221
 closet+0.218
iper+0.216
ig+0.214
Neg logit contributions
all-0.235
uts-0.213
 Mike-0.193
ous-0.188
't-0.186
Token always
Token ID1464
Feature activation-9.56e-03

Pos logit contributions
all+0.066
uts+0.064
 Mike+0.060
 Crab+0.058
Welcome+0.058
Neg logit contributions
 fort-0.056
ig-0.055
ches-0.054
iper-0.054
 web-0.053
Token.
Token ID13
Feature activation+5.12e-02

Pos logit contributions
 Cr+0.112
all+0.110
 Crab+0.110
uts+0.110
 Hipp+0.104
Neg logit contributions
 fort-0.162
ig-0.161
ets-0.158
ches-0.157
 room-0.155
Token What
Token ID1867
Feature activation+3.34e-02

Pos logit contributions
all+0.070
uts+0.069
no+0.064
ous+0.060
 Crab+0.059
Neg logit contributions
 fort-0.092
house-0.090
 closet-0.090
iper-0.089
 web-0.089
Token do
Token ID466
Feature activation+9.29e-02

Pos logit contributions
all+0.060
uts+0.057
 Mike+0.054
 Crab+0.052
Welcome+0.052
Neg logit contributions
 fort-0.050
ig-0.049
ches-0.048
iper-0.048
 web-0.047
Token you
Token ID345
Feature activation-4.54e-02

Pos logit contributions
all+0.105
uts+0.097
 Mike+0.088
 Crab+0.083
Welcome+0.082
Neg logit contributions
 fort-0.200
ig-0.197
ches-0.194
iper-0.194
 web-0.192
Token want
Token ID765
Feature activation+1.39e-01

Pos logit contributions
 fort+0.083
ig+0.081
ches+0.080
iper+0.080
 web+0.079
Neg logit contributions
all-0.066
uts-0.063
 Mike-0.058
 Crab-0.056
Welcome-0.055
Token to
Token ID284
Feature activation+1.73e-02

Pos logit contributions
uts+0.172
all+0.172
 Mike+0.153
Welcome+0.149
 Crab+0.147
Neg logit contributions
 fort-0.277
ches-0.272
ig-0.267
iper-0.266
 closet-0.263
Token do
Token ID466
Feature activation+9.97e-02

Pos logit contributions
uts+0.033
Welcome+0.031
all+0.029
 Cr+0.029
 Crab+0.029
Neg logit contributions
 fort-0.024
 pile-0.023
 room-0.023
house-0.022
 closet-0.022
Token while
Token ID981
Feature activation+1.13e-01

Pos logit contributions
uts+0.147
all+0.145
Welcome+0.144
 Mike+0.140
 Hipp+0.136
Neg logit contributions
 fort-0.167
ches-0.161
ig-0.160
 room-0.159
house-0.156
Token we
Token ID356
Feature activation-2.27e-02

Pos logit contributions
all+0.156
uts+0.154
Welcome+0.140
 Cr+0.136
 Mike+0.135
Neg logit contributions
 fort-0.206
ig-0.200
 closet-0.196
 room-0.196
 web-0.194
Token wait
Token ID4043
Feature activation+1.31e-01

Pos logit contributions
 fort+0.038
ig+0.037
ches+0.037
iper+0.036
 web+0.036
Neg logit contributions
all-0.036
uts-0.035
 Mike-0.032
 Crab-0.031
Welcome-0.031
Token?"
Token ID1701
Feature activation+6.54e-02

Pos logit contributions
uts+0.191
all+0.188
 Crab+0.171
Welcome+0.170
 Cr+0.169
Neg logit contributions
 fort-0.238
ig-0.231
 closet-0.225
ches-0.224
iper-0.221
Token take
Token ID1011
Feature activation+7.60e-02

Pos logit contributions
 finds+0.000
 web+0.000
 pile+0.000
 closet+0.000
 room+0.000
Neg logit contributions
uts-0.000
all-0.000
unch-0.000
anes-0.000
Ice-0.000
Token a
Token ID257
Feature activation-8.28e-02

Pos logit contributions
uts+0.084
all+0.083
anes+0.068
 Crab+0.067
ous+0.067
Neg logit contributions
ig-0.163
 fort-0.161
iper-0.159
ches-0.159
 web-0.159
Token better
Token ID1365
Feature activation+2.54e-02

Pos logit contributions
 fort+0.164
ig+0.162
ches+0.161
 web+0.158
iper+0.156
Neg logit contributions
all-0.109
uts-0.104
 Mike-0.093
 Crab-0.089
 Cr-0.088
Token look
Token ID804
Feature activation+4.41e-02

Pos logit contributions
all+0.034
uts+0.032
 Mike+0.031
 Crab+0.029
no+0.029
Neg logit contributions
iper-0.048
ches-0.047
 fort-0.046
ig-0.046
ns-0.045
Token.
Token ID13
Feature activation+6.60e-02

Pos logit contributions
all+0.059
uts+0.055
 Cr+0.053
 Crab+0.053
 Mike+0.052
Neg logit contributions
ig-0.085
ches-0.084
 fort-0.084
 web-0.080
 closet-0.079
Token "
Token ID366
Feature activation+2.89e-02

Pos logit contributions
all+0.070
uts+0.064
 Mike+0.059
 Crab+0.054
 Joey+0.054
Neg logit contributions
 fort-0.148
ig-0.146
ches-0.144
iper-0.143
 web-0.141
TokenWhat
Token ID2061
Feature activation+4.36e-02

Pos logit contributions
uts+0.043
ous+0.038
all+0.038
 Mike+0.036
 Joey+0.035
Neg logit contributions
ns-0.050
eh-0.050
house-0.048
c-0.048
oscope-0.048
Token could
Token ID714
Feature activation+1.03e-01

Pos logit contributions
all+0.090
uts+0.086
 Mike+0.082
 Crab+0.080
Welcome+0.079
Neg logit contributions
 fort-0.053
ig-0.051
ches-0.050
iper-0.050
 web-0.049
Token this
Token ID428
Feature activation-5.52e-02

Pos logit contributions
all+0.125
uts+0.115
 Mike+0.105
Welcome+0.101
 Crab+0.100
Neg logit contributions
 fort-0.211
ig-0.206
iper-0.204
 web-0.204
ches-0.204
Token be
Token ID307
Feature activation-2.00e-03

Pos logit contributions
 fort+0.086
ig+0.084
 web+0.082
house+0.078
ches+0.078
Neg logit contributions
uts-0.093
all-0.093
 Mike-0.085
Welcome-0.084
 Joey-0.082
Token?"
Token ID1701
Feature activation+9.23e-02

Pos logit contributions
 fort+0.004
iper+0.004
ig+0.004
 closet+0.004
ches+0.004
Neg logit contributions
all-0.002
uts-0.002
 Mike-0.002
 Crab-0.002
 Joey-0.002
Token a
Token ID257
Feature activation-7.80e-02

Pos logit contributions
 fort+0.174
ches+0.166
 web+0.165
ig+0.164
iper+0.164
Neg logit contributions
all-0.136
uts-0.131
 Mike-0.120
 Crab-0.116
 Cr-0.114
Token time
Token ID640
Feature activation+2.95e-02

Pos logit contributions
ringe+0.128
 closet+0.125
ig+0.124
 fort+0.124
iper+0.121
Neg logit contributions
all-0.128
no-0.109
 Mike-0.105
unch-0.104
uts-0.104
Token Bob
Token ID5811
Feature activation-1.35e-01

Pos logit contributions
all+0.051
uts+0.050
Welcome+0.046
no+0.046
anes+0.045
Neg logit contributions
ig-0.044
 fort-0.043
 web-0.040
ches-0.040
iper-0.040
Token was
Token ID373
Feature activation-4.30e-02

Pos logit contributions
 fort+0.219
iper+0.210
 web+0.209
ig+0.204
ches+0.202
Neg logit contributions
all-0.232
 Mike-0.208
 Joey-0.207
 him-0.201
 Crab-0.201
Token walking
Token ID6155
Feature activation+7.09e-02

Pos logit contributions
 fort+0.087
ig+0.085
ches+0.084
iper+0.083
 web+0.082
Neg logit contributions
all-0.055
uts-0.052
 Mike-0.047
 Crab-0.045
Welcome-0.045
Token in
Token ID287
Feature activation-4.00e-02

Pos logit contributions
all+0.093
uts+0.087
 Mike+0.080
 Crab+0.076
Welcome+0.075
Neg logit contributions
 fort-0.141
ig-0.138
ches-0.136
iper-0.136
 web-0.134
Token a
Token ID257
Feature activation-8.72e-02

Pos logit contributions
 fort+0.075
ig+0.073
iper+0.072
ches+0.072
 web+0.071
Neg logit contributions
all-0.057
uts-0.054
 Mike-0.049
 Crab-0.047
Welcome-0.047
Token me
Token ID502
Feature activation-8.41e-02

Pos logit contributions
ches+0.160
iper+0.159
ets+0.159
oscope+0.154
ig+0.151
Neg logit contributions
Welcome-0.119
all-0.115
 Joey-0.108
 Crab-0.108
 Mike-0.108
Tokenadow
Token ID4584
Feature activation+3.00e-02

Pos logit contributions
 fort+0.110
iper+0.109
ches+0.108
 web+0.096
 scar+0.095
Neg logit contributions
all-0.166
uts-0.149
 Mike-0.145
ful-0.141
no-0.141
Token when
Token ID618
Feature activation+4.00e-02

Pos logit contributions
all+0.035
uts+0.033
 Mike+0.030
 Crab+0.028
Welcome+0.028
Neg logit contributions
 fort-0.063
ig-0.062
ches-0.061
iper-0.061
 web-0.060
Token he
Token ID339
Feature activation-8.83e-02

Pos logit contributions
uts+0.048
all+0.048
anes+0.040
ous+0.038
Welcome+0.037
Neg logit contributions
 fort-0.082
ig-0.078
eh-0.077
 closet-0.077
 web-0.077
Token.
Token ID13
Feature activation+4.74e-02

Pos logit contributions
all+0.030
Welcome+0.027
 Cr+0.027
uts+0.026
anes+0.026
Neg logit contributions
 fort-0.036
ig-0.034
 closet-0.034
ches-0.034
 web-0.034
Token
Token ID198
Feature activation+1.10e-02

Pos logit contributions
all+0.070
uts+0.061
no+0.059
ous+0.059
piring+0.056
Neg logit contributions
 closet-0.087
 fort-0.082
 web-0.081
iper-0.081
 backyard-0.080
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
all+0.016
ous+0.015
uts+0.015
 Crab+0.014
 Cr+0.014
Neg logit contributions
 fort-0.019
ches-0.019
 web-0.018
 closet-0.018
iper-0.018
Token"
Token ID1
Feature activation+2.48e-02

Pos logit contributions
all+0.020
uts+0.019
 Mike+0.018
 Crab+0.018
ous+0.018
Neg logit contributions
 fort-0.021
ig-0.021
eh-0.021
 web-0.021
iper-0.021
TokenAre
Token ID8491
Feature activation+1.12e-01

Pos logit contributions
uts+0.037
all+0.037
ous+0.034
 Joey+0.033
 Mike+0.033
Neg logit contributions
 necks-0.040
iper-0.040
 closet-0.040
 fort-0.039
ns-0.039
Token you
Token ID345
Feature activation-6.71e-02

Pos logit contributions
all+0.154
uts+0.152
anes+0.133
Welcome+0.133
no+0.132
Neg logit contributions
ig-0.202
 fort-0.198
iper-0.197
ches-0.196
 web-0.188
Token ready
Token ID3492
Feature activation+9.53e-02

Pos logit contributions
ig+0.125
 fort+0.124
iper+0.122
ches+0.121
 closet+0.120
Neg logit contributions
uts-0.093
all-0.089
anes-0.081
no-0.081
 Mike-0.080
Token to
Token ID284
Feature activation+1.18e-03

Pos logit contributions
all+0.127
uts+0.125
Welcome+0.108
 Mike+0.108
 Crab+0.106
Neg logit contributions
 fort-0.185
ig-0.181
ches-0.177
iper-0.176
 closet-0.175
Token go
Token ID467
Feature activation+8.29e-02

Pos logit contributions
uts+0.002
all+0.002
Welcome+0.002
no+0.002
ous+0.002
Neg logit contributions
 fort-0.002
ig-0.002
 closet-0.002
ches-0.002
iper-0.002
Token,
Token ID11
Feature activation+1.53e-02

Pos logit contributions
uts+0.118
all+0.117
 Mike+0.102
no+0.102
Welcome+0.102
Neg logit contributions
 fort-0.156
ig-0.154
ches-0.149
 closet-0.147
iper-0.143
Token Lily
Token ID20037
Feature activation-1.32e-01

Pos logit contributions
all+0.025
uts+0.024
no+0.022
Welcome+0.021
 Mike+0.021
Neg logit contributions
 fort-0.026
iper-0.025
ig-0.024
 closet-0.024
 web-0.024
TokenThey
Token ID2990
Feature activation-5.25e-02

Pos logit contributions
all+0.025
uts+0.022
Welcome+0.020
no+0.020
Joe+0.019
Neg logit contributions
 fort-0.037
ig-0.037
iper-0.037
 web-0.036
 closet-0.036
Token have
Token ID423
Feature activation-8.64e-03

Pos logit contributions
 fort+0.096
ig+0.094
eh+0.092
iper+0.092
aj+0.091
Neg logit contributions
all-0.072
 Mike-0.068
uts-0.063
 him-0.063
 Joey-0.062
Token fun
Token ID1257
Feature activation+8.01e-02

Pos logit contributions
ig+0.016
 fort+0.016
iper+0.016
ches+0.016
 web+0.015
Neg logit contributions
all-0.012
uts-0.012
 Mike-0.011
no-0.010
 Crab-0.010
Token with
Token ID351
Feature activation+2.99e-02

Pos logit contributions
all+0.123
uts+0.118
Welcome+0.113
 Crab+0.112
 Lib+0.111
Neg logit contributions
 fort-0.146
ig-0.142
 web-0.141
house-0.132
eh-0.129
Token the
Token ID262
Feature activation-1.50e-01

Pos logit contributions
all+0.029
 Mike+0.028
uts+0.026
 Joey+0.025
 him+0.025
Neg logit contributions
ig-0.067
ches-0.066
 fort-0.065
iper-0.065
eh-0.064
Token wheat
Token ID17135
Feature activation-2.27e-02

Pos logit contributions
ig+0.252
ches+0.252
 fort+0.246
iper+0.243
 web+0.240
Neg logit contributions
all-0.230
uts-0.214
no-0.203
 Joey-0.201
 Mike-0.200
Token.
Token ID13
Feature activation+5.68e-02

Pos logit contributions
 fort+0.040
ig+0.040
iper+0.039
ches+0.039
 web+0.038
Neg logit contributions
all-0.033
uts-0.032
 Mike-0.029
 Crab-0.028
 Joey-0.028
Token But
Token ID887
Feature activation+1.16e-02

Pos logit contributions
all+0.074
uts+0.069
 Mike+0.062
 Crab+0.060
no+0.060
Neg logit contributions
 fort-0.114
ches-0.109
ig-0.108
 web-0.108
iper-0.108
Token they
Token ID484
Feature activation-6.73e-02

Pos logit contributions
all+0.016
 Mike+0.015
uts+0.014
 Crab+0.014
no+0.014
Neg logit contributions
 fort-0.022
iper-0.022
ches-0.022
ig-0.022
 web-0.021
Token do
Token ID466
Feature activation+6.82e-02

Pos logit contributions
 fort+0.138
iper+0.136
ig+0.135
eh+0.135
aj+0.131
Neg logit contributions
all-0.081
uts-0.077
't-0.076
 Mike-0.075
 him-0.072
Token not
Token ID407
Feature activation+5.49e-05

Pos logit contributions
all+0.106
uts+0.097
 Mike+0.092
no+0.088
 Crab+0.087
Neg logit contributions
 fort-0.122
iper-0.120
ig-0.119
ches-0.117
 web-0.115
Token.
Token ID13
Feature activation+7.66e-02

Pos logit contributions
 fort+0.180
ig+0.176
ches+0.175
iper+0.173
 web+0.171
Neg logit contributions
all-0.102
uts-0.094
 Mike-0.087
 Crab-0.082
Welcome-0.082
Token He
Token ID679
Feature activation-8.24e-02

Pos logit contributions
all+0.109
uts+0.098
no+0.093
anes+0.085
 returning+0.084
Neg logit contributions
 fort-0.144
 closet-0.139
ches-0.139
iper-0.136
 web-0.134
Token is
Token ID318
Feature activation-1.81e-02

Pos logit contributions
 fort+0.116
eh+0.115
 web+0.112
ig+0.112
iper+0.111
Neg logit contributions
uts-0.144
all-0.144
 Mike-0.137
 him-0.137
't-0.133
Token mine
Token ID6164
Feature activation+2.80e-02

Pos logit contributions
ig+0.034
 fort+0.032
iper+0.032
ches+0.030
 web+0.030
Neg logit contributions
all-0.027
uts-0.024
 Mike-0.024
 Crab-0.024
 Joey-0.023
Token."
Token ID526
Feature activation+7.98e-02

Pos logit contributions
all+0.036
Welcome+0.034
 Cr+0.034
uts+0.033
 Crab+0.033
Neg logit contributions
 fort-0.054
ig-0.052
ches-0.051
 closet-0.051
 web-0.050
Token They
Token ID1119
Feature activation-6.66e-02

Pos logit contributions
all+0.065
uts+0.060
 Mike+0.054
 Crab+0.049
 Joey+0.047
Neg logit contributions
 fort-0.197
ig-0.196
iper-0.193
ches-0.192
 web-0.190
Token started
Token ID2067
Feature activation+7.75e-02

Pos logit contributions
 fort+0.148
ig+0.144
eh+0.137
 web+0.137
aj+0.133
Neg logit contributions
 Mike-0.082
 him-0.074
 pointing-0.066
 Dave-0.065
 Rob-0.065
Token to
Token ID284
Feature activation-5.44e-03

Pos logit contributions
all+0.091
uts+0.084
anes+0.075
Welcome+0.074
 Mike+0.072
Neg logit contributions
 fort-0.166
 closet-0.158
 web-0.158
ches-0.158
ig-0.156
Token argue
Token ID7267
Feature activation+1.54e-01

Pos logit contributions
ig+0.009
 fort+0.009
iper+0.009
ches+0.009
 web+0.009
Neg logit contributions
all-0.008
uts-0.008
 Mike-0.008
 Joey-0.007
 Crab-0.007
Token.
Token ID13
Feature activation+5.50e-02

Pos logit contributions
all+0.210
 Crab+0.195
uts+0.192
 Cr+0.191
 Joey+0.187
Neg logit contributions
 fort-0.293
ches-0.286
ig-0.278
 web-0.275
 closet-0.274
Token
Token ID198
Feature activation+1.86e-02

Pos logit contributions
all+0.063
uts+0.058
 Mike+0.052
 Crab+0.050
Welcome+0.049
Neg logit contributions
 fort-0.118
ig-0.115
ches-0.114
iper-0.114
 web-0.113
Token her
Token ID607
Feature activation-1.41e-01

Pos logit contributions
all+0.059
uts+0.056
 Mike+0.051
ous+0.050
 Crab+0.050
Neg logit contributions
 fort-0.072
 closet-0.071
 web-0.069
ig-0.068
iper-0.068
Token rubber
Token ID14239
Feature activation+2.82e-02

Pos logit contributions
ches+0.260
iper+0.254
ets+0.250
ns+0.249
eh+0.245
Neg logit contributions
uts-0.199
all-0.188
 Mike-0.180
 Joey-0.171
 Hipp-0.169
Token duck
Token ID22045
Feature activation-3.07e-02

Pos logit contributions
all+0.045
uts+0.044
 Mike+0.041
 Crab+0.041
 Cr+0.040
Neg logit contributions
iper-0.046
ches-0.044
 fort-0.043
ns-0.042
ig-0.042
Tokenie
Token ID494
Feature activation-1.04e-01

Pos logit contributions
 fort+0.069
iper+0.068
ig+0.067
ches+0.067
 web+0.067
Neg logit contributions
all-0.030
uts-0.028
 Crab-0.024
 Mike-0.024
 Joey-0.023
Token.
Token ID13
Feature activation+6.25e-02

Pos logit contributions
 fort+0.246
ig+0.241
iper+0.239
ches+0.236
 web+0.236
Neg logit contributions
all-0.090
uts-0.084
 Mike-0.071
 Crab-0.069
no-0.066
Token One
Token ID1881
Feature activation-7.03e-03

Pos logit contributions
all+0.086
uts+0.081
 Mike+0.074
 Crab+0.071
no+0.071
Neg logit contributions
 fort-0.121
ig-0.118
ches-0.116
iper-0.116
 closet-0.114
Token day
Token ID1110
Feature activation+4.66e-02

Pos logit contributions
 fort+0.013
iper+0.013
ig+0.013
ches+0.013
 web+0.013
Neg logit contributions
all-0.010
uts-0.009
 Mike-0.008
 Joey-0.008
Welcome-0.008
Token,
Token ID11
Feature activation+2.07e-02

Pos logit contributions
all+0.082
uts+0.078
 Mike+0.072
anes+0.071
 Crab+0.071
Neg logit contributions
ig-0.071
 fort-0.070
ches-0.067
iper-0.066
 web-0.066
Token Lily
Token ID20037
Feature activation-1.31e-01

Pos logit contributions
all+0.025
uts+0.023
 Mike+0.021
 Crab+0.020
Welcome+0.020
Neg logit contributions
 fort-0.043
ig-0.043
ches-0.042
iper-0.042
 web-0.042
Token's
Token ID338
Feature activation-9.63e-02

Pos logit contributions
iper+0.224
 web+0.219
ig+0.218
 fort+0.212
 spine+0.210
Neg logit contributions
all-0.183
 Joey-0.176
uts-0.170
 Mike-0.166
 him-0.166
Token mom
Token ID1995
Feature activation-5.09e-02

Pos logit contributions
 fort+0.145
ig+0.142
ches+0.141
iper+0.141
 web+0.137
Neg logit contributions
all-0.169
uts-0.161
 Mike-0.153
 Crab-0.148
 Joey-0.146
Token man
Token ID582
Feature activation-4.19e-02

Pos logit contributions
ig+0.098
iper+0.098
ches+0.097
 fort+0.097
ets+0.096
Neg logit contributions
all-0.112
 Mike-0.104
uts-0.103
 Crab-0.102
 Hipp-0.099
Token was
Token ID373
Feature activation-3.65e-02

Pos logit contributions
 fort+0.079
 web+0.075
 closet+0.075
ig+0.074
iper+0.074
Neg logit contributions
all-0.063
 Mike-0.056
uts-0.053
 Joey-0.051
 Crab-0.051
Token happy
Token ID3772
Feature activation+4.71e-02

Pos logit contributions
 fort+0.062
ig+0.061
ches+0.060
iper+0.060
 web+0.059
Neg logit contributions
all-0.057
uts-0.054
 Mike-0.051
 Crab-0.049
Welcome-0.049
Token and
Token ID290
Feature activation-2.99e-02

Pos logit contributions
uts+0.068
anes+0.067
all+0.067
Welcome+0.066
 Cr+0.061
Neg logit contributions
 fort-0.081
ig-0.076
 web-0.076
 room-0.076
 closet-0.075
Token let
Token ID1309
Feature activation+1.09e-01

Pos logit contributions
 fort+0.054
ig+0.053
ches+0.051
iper+0.051
 web+0.051
Neg logit contributions
all-0.046
uts-0.043
 Mike-0.041
 Crab-0.039
 Joey-0.039
Token the
Token ID262
Feature activation-1.33e-01

Pos logit contributions
all+0.112
uts+0.099
 Mike+0.093
 Crab+0.087
 Joey+0.087
Neg logit contributions
 fort-0.248
ig-0.244
iper-0.240
 web-0.239
ches-0.238
Token bear
Token ID6842
Feature activation-1.81e-02

Pos logit contributions
 fort+0.164
ig+0.159
ches+0.155
iper+0.155
 web+0.151
Neg logit contributions
all-0.276
uts-0.265
 Mike-0.252
 Crab-0.245
Welcome-0.244
Token in
Token ID287
Feature activation-2.20e-02

Pos logit contributions
 fort+0.031
ches+0.029
ig+0.029
iper+0.029
 closet+0.028
Neg logit contributions
all-0.029
uts-0.028
 Mike-0.026
 Crab-0.025
Welcome-0.025
Token.
Token ID13
Feature activation+6.70e-02

Pos logit contributions
 fort+0.038
 closet+0.037
 web+0.036
ig+0.035
iper+0.035
Neg logit contributions
all-0.035
uts-0.035
anes-0.030
Welcome-0.029
ous-0.029
Token The
Token ID383
Feature activation-1.34e-01

Pos logit contributions
all+0.092
uts+0.087
Welcome+0.076
no+0.076
 Mike+0.075
Neg logit contributions
 fort-0.126
ches-0.124
ig-0.124
iper-0.123
 web-0.120
Token bear
Token ID6842
Feature activation-3.81e-02

Pos logit contributions
iper+0.192
ches+0.192
ets+0.188
ig+0.187
 fort+0.174
Neg logit contributions
all-0.243
 Hipp-0.231
 Crab-0.228
 Mike-0.226
 Joey-0.222
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
all+0.036
Welcome+0.033
uts+0.032
 Crab+0.031
no+0.030
Neg logit contributions
 fort-0.069
ches-0.069
ig-0.068
iper-0.067
 web-0.066
Token
Token ID198
Feature activation+2.77e-02

Pos logit contributions
all+0.035
uts+0.034
 Mike+0.031
 Crab+0.030
ous+0.030
Neg logit contributions
 fort-0.054
ches-0.054
ig-0.052
 web-0.052
eh-0.052
TokenThe
Token ID464
Feature activation-1.47e-01

Pos logit contributions
all+0.045
uts+0.042
 Mike+0.039
 Crab+0.038
Welcome+0.038
Neg logit contributions
 fort-0.047
ig-0.046
iper-0.045
ches-0.045
 web-0.044
Token moral
Token ID6573
Feature activation+6.81e-02

Pos logit contributions
 fort+0.215
ig+0.210
ches+0.207
iper+0.205
 web+0.203
Neg logit contributions
all-0.270
uts-0.255
 Mike-0.241
 Crab-0.237
no-0.236
Token of
Token ID286
Feature activation+2.13e-02

Pos logit contributions
all+0.049
uts+0.040
 Mike+0.036
no+0.034
Welcome+0.033
Neg logit contributions
 fort-0.180
ig-0.175
iper-0.174
ches-0.173
 closet-0.172
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
all+0.027
uts+0.022
 Mike+0.022
 Crab+0.022
 Joey+0.022
Neg logit contributions
 fort-0.045
ig-0.044
ches-0.043
iper-0.042
 closet-0.042
Token story
Token ID1621
Feature activation+5.64e-02

Pos logit contributions
 fort+0.164
iper+0.158
ig+0.158
ches+0.155
 web+0.151
Neg logit contributions
all-0.242
uts-0.239
 Mike-0.225
 Joey-0.214
 Cr-0.213
Token:
Token ID25
Feature activation+3.00e-02

Pos logit contributions
all+0.119
uts+0.114
 Mike+0.107
't+0.103
no+0.103
Neg logit contributions
iper-0.067
 fort-0.066
eh-0.065
ig-0.065
ns-0.063
Token don
Token ID836
Feature activation+9.88e-02

Pos logit contributions
uts+0.040
all+0.038
 Lib+0.036
 Mike+0.035
no+0.034
Neg logit contributions
ig-0.055
 fort-0.055
 web-0.055
ches-0.054
iper-0.053
Token't
Token ID470
Feature activation+9.47e-03

Pos logit contributions
all+0.067
Welcome+0.064
 Mike+0.063
 Crab+0.062
 Joey+0.058
Neg logit contributions
ches-0.244
 fort-0.233
ig-0.232
 web-0.229
iper-0.226
Token eat
Token ID4483
Feature activation+1.27e-01

Pos logit contributions
all+0.019
uts+0.019
anes+0.017
 Lib+0.017
 Mike+0.017
Neg logit contributions
 web-0.012
 fort-0.011
ig-0.011
ches-0.011
 forgot-0.010
Token your
Token ID534
Feature activation-1.36e-01

Pos logit contributions
all+0.009
uts+0.009
 Mike+0.008
 Crab+0.008
Welcome+0.008
Neg logit contributions
 fort-0.011
ig-0.011
ches-0.011
iper-0.011
 web-0.011
Token mistake
Token ID7457
Feature activation+8.01e-02

Pos logit contributions
ches+0.209
iper+0.202
eh+0.201
ig+0.197
ns+0.196
Neg logit contributions
all-0.231
uts-0.221
 Mike-0.209
no-0.205
 Crab-0.197
Token."
Token ID526
Feature activation+5.20e-02

Pos logit contributions
all+0.104
 Mike+0.095
 Crab+0.094
uts+0.094
 Cr+0.093
Neg logit contributions
ches-0.152
 fort-0.151
ig-0.149
iper-0.147
ets-0.145
Token
Token ID198
Feature activation+7.92e-03

Pos logit contributions
all+0.063
uts+0.059
ous+0.054
anes+0.051
Welcome+0.050
Neg logit contributions
 fort-0.102
 closet-0.101
iper-0.101
ig-0.098
 web-0.098
Token
Token ID198
Feature activation+8.83e-03

Pos logit contributions
all+0.009
uts+0.008
ous+0.007
 Crab+0.007
 Mike+0.007
Neg logit contributions
 fort-0.017
ches-0.017
iper-0.017
 web-0.017
ig-0.017
TokenSam
Token ID16305
Feature activation-1.08e-01

Pos logit contributions
all+0.016
uts+0.015
 Mike+0.014
 Crab+0.014
 Joey+0.014
Neg logit contributions
 fort-0.013
ig-0.013
iper-0.012
ches-0.012
 web-0.012
Token and
Token ID290
Feature activation-5.80e-02

Pos logit contributions
ig+0.190
 fort+0.187
 web+0.180
 spine+0.179
eh+0.179
Neg logit contributions
all-0.159
 him-0.145
 Mike-0.137
 rep-0.129
 Share-0.125
Token Mia
Token ID32189
Feature activation-1.45e-01

Pos logit contributions
ig+0.118
ches+0.116
 fort+0.115
iper+0.114
ets+0.111
Neg logit contributions
 Mike-0.072
all-0.072
 Crab-0.066
 Joey-0.066
 Cr-0.066
Token said
Token ID531
Feature activation+3.40e-02

Pos logit contributions
 fort+0.256
ig+0.248
eh+0.243
 web+0.242
iper+0.241
Neg logit contributions
all-0.218
 Mike-0.208
uts-0.201
 rep-0.197
 him-0.195
Token sorry
Token ID7926
Feature activation+6.37e-02

Pos logit contributions
all+0.067
Welcome+0.062
 Crab+0.059
Joe+0.059
anes+0.059
Neg logit contributions
ig-0.044
 fort-0.043
 forgot-0.039
 web-0.039
ches-0.038
Token to
Token ID284
Feature activation-3.82e-03

Pos logit contributions
all+0.087
 Crab+0.083
 Mike+0.081
 Lib+0.080
anes+0.080
Neg logit contributions
 fort-0.125
ches-0.115
ets-0.113
ig-0.112
 closet-0.111
Token.
Token ID13
Feature activation+6.80e-02

Pos logit contributions
all+0.077
uts+0.071
 Mike+0.065
 Crab+0.062
 Joey+0.061
Neg logit contributions
 fort-0.127
ig-0.125
iper-0.124
ches-0.123
 web-0.122
Token Her
Token ID2332
Feature activation-1.31e-01

Pos logit contributions
all+0.081
uts+0.074
 Mike+0.069
 Crab+0.065
 Joey+0.065
Neg logit contributions
 fort-0.144
ig-0.143
ches-0.141
iper-0.139
 web-0.138
Token mom
Token ID1995
Feature activation-5.58e-02

Pos logit contributions
ches+0.328
ets+0.322
ns+0.311
eh+0.309
 Street+0.308
Neg logit contributions
uts-0.109
all-0.093
 Dad-0.090
 Crab-0.087
 Mike-0.082
Token explained
Token ID4893
Feature activation+6.27e-02

Pos logit contributions
 fort+0.108
 web+0.104
ig+0.102
 closet+0.098
eh+0.097
Neg logit contributions
all-0.082
 Mike-0.070
uts-0.068
 Joey-0.066
 pointing-0.065
Token that
Token ID326
Feature activation-8.76e-03

Pos logit contributions
all+0.069
uts+0.066
 Mike+0.057
Welcome+0.057
 Crab+0.056
Neg logit contributions
 fort-0.136
ches-0.133
iper-0.132
ig-0.132
 web-0.130
Token the
Token ID262
Feature activation-1.40e-01

Pos logit contributions
 fort+0.019
ig+0.019
ches+0.018
iper+0.018
 web+0.018
Neg logit contributions
all-0.010
uts-0.009
 Mike-0.008
 Crab-0.008
Welcome-0.008
Token trap
Token ID12840
Feature activation+7.03e-02

Pos logit contributions
ig+0.174
ches+0.156
iper+0.150
aj+0.149
uel+0.146
Neg logit contributions
Welcome-0.277
all-0.271
uts-0.267
 returning-0.263
't-0.260
Token was
Token ID373
Feature activation-1.89e-02

Pos logit contributions
all+0.109
uts+0.108
 Mike+0.096
 Joey+0.095
't+0.095
Neg logit contributions
ig-0.116
eh-0.116
 fort-0.113
iper-0.113
aj-0.111
Token made
Token ID925
Feature activation+7.46e-02

Pos logit contributions
ig+0.035
 fort+0.034
iper+0.033
ches+0.033
 web+0.032
Neg logit contributions
all-0.028
uts-0.025
 Mike-0.023
 Joey-0.023
 returning-0.023
Token to
Token ID284
Feature activation+4.07e-03

Pos logit contributions
all+0.064
uts+0.053
 Mike+0.046
 Joey+0.045
Welcome+0.042
Neg logit contributions
 fort-0.183
ig-0.183
 necks-0.177
iper-0.177
 web-0.177
Token catch
Token ID4929
Feature activation+1.07e-01

Pos logit contributions
all+0.006
uts+0.006
 Mike+0.006
 Joey+0.005
 Crab+0.005
Neg logit contributions
ig-0.007
 fort-0.007
ches-0.007
iper-0.007
 closet-0.006
Token Buddy
Token ID36896
Feature activation-1.24e-01

Pos logit contributions
all+0.091
uts+0.087
 Mike+0.082
 Crab+0.079
 Joey+0.079
Neg logit contributions
 fort-0.097
ig-0.096
iper-0.091
ches-0.091
 web-0.090
Token.
Token ID13
Feature activation+5.88e-02

Pos logit contributions
 fort+0.292
ig+0.289
iper+0.283
 web+0.281
ches+0.279
Neg logit contributions
all-0.112
uts-0.101
 Mike-0.094
 Joey-0.087
 Crab-0.087
Token One
Token ID1881
Feature activation-8.52e-03

Pos logit contributions
all+0.089
uts+0.084
 Mike+0.077
no+0.075
 Crab+0.075
Neg logit contributions
 fort-0.105
ches-0.101
ig-0.100
iper-0.099
 web-0.099
Token day
Token ID1110
Feature activation+4.59e-02

Pos logit contributions
ig+0.017
 fort+0.017
iper+0.017
 necks+0.017
 closet+0.017
Neg logit contributions
all-0.011
uts-0.009
Welcome-0.009
 Joey-0.009
 Mike-0.008
Token,
Token ID11
Feature activation+2.03e-02

Pos logit contributions
all+0.081
uts+0.077
 Mike+0.071
 Crab+0.071
anes+0.070
Neg logit contributions
 fort-0.070
ig-0.068
ches-0.067
 web-0.065
iper-0.065
Token Buddy
Token ID36896
Feature activation-1.18e-01

Pos logit contributions
all+0.030
uts+0.028
 Mike+0.026
 Crab+0.025
Welcome+0.025
Neg logit contributions
 fort-0.037
ig-0.036
ches-0.035
iper-0.035
 web-0.035
Token hurt
Token ID5938
Feature activation+5.03e-02

Pos logit contributions
ig+0.223
 fort+0.213
 web+0.204
iper+0.201
 ramp+0.196
Neg logit contributions
all-0.173
 Joey-0.163
uts-0.160
 Crab-0.155
 Mike-0.155
Token his
Token ID465
Feature activation-1.54e-01

Pos logit contributions
all+0.049
 Mike+0.044
 Joey+0.044
uts+0.043
 him+0.042
Neg logit contributions
ig-0.115
 fort-0.115
iper-0.113
ets-0.112
ns-0.111
Token paw
Token ID41827
Feature activation+4.97e-02

Pos logit contributions
iper+0.198
ets+0.195
ns+0.194
ches+0.192
ig+0.184
Neg logit contributions
uts-0.286
all-0.285
no-0.262
ful-0.258
 Crab-0.256
Token while
Token ID981
Feature activation+1.02e-01

Pos logit contributions
all+0.045
uts+0.045
ful+0.040
no+0.037
't+0.036
Neg logit contributions
iper-0.112
 fort-0.110
ig-0.109
ns-0.105
aj-0.104
Token they
Token ID484
Feature activation-6.65e-02

Pos logit contributions
all+0.143
uts+0.135
 Mike+0.121
Welcome+0.121
anes+0.121
Neg logit contributions
 fort-0.190
ig-0.186
 web-0.185
eh-0.180
ches-0.180