TOP ACTIVATIONS
MAX = 3.834

big , bill owing cloud hurd ling through the sky .
. L ily was sad because she loved
. L ily was sad because she loved
. L ily went home feeling very upset
work . L ily 's mom my came in
gone . L ily 's friends tried to help
. L ily 's mom came in and
all . L ily was so happy that she
them . L ily 's mom my said that
. L ily went outside to play and
. L ily said , " Yes ,
. L ily 's mom saw her sad
found . L ily started to feel worried .
. L ily played with the ball for
. L ily 's mom saw her searching
it . L ily frowned as she looked at
. L ily was scared and started to
away . L ily felt bad and wanted to
. L ily felt sad and said ,
. L ily 's grandma loved her very

MIN ACTIVATIONS
MIN = -4.981

smile . S aman tha laughed , happy that
. S aman tha was amazed and she
before dinner . <|endoftext|> S aman tha was a lazy girl
. Exc ited , Lily followed the instructions
sky . Exc ited ly , the two girls
it ?" Exc ited , Sammy eagerly agreed ,
together !" Exc ited ly , Sally and Tim
distance . Exc ited ly , she ran to
on a tree . Exc ited ly , the bird flew
in his raft . Exc ited , Lily jumped in the
inside ." Exc ited , Lucy got some blankets
. Exc ited ly , Ark ie grabbed
it was perfect . Exc ited , she ran to get
in the freezer . Exc ited , she opened the freezer
and unknown things . Exc ited , he kept exploring until
of the mountain . Exc ited ly , she rushed to
saw a chest . Exc ited , he pr icked up
maze . Exc ited ly , she asked her
spaghetti !" Exc ited ly , Lily brought the
." Exc ited for the surprise , John

INTERVAL 1.630 - 3.834
CONTAINS 1.352%

! M ia smiled to herself and said
scary . L ily 's mom saw the picture
're so graceful with your wand ," Max said . "
good twins . <|endoftext|> L ily and Ben are friends .
outside . One day , Julia found an orange telephone in

INTERVAL -0.574 - 1.630
CONTAINS 81.414%

my pig . Let 's go home . â So
He had a playful puppy named Max who would run around
tell him your names and what you like to do .
time , there was a little girl named Lily . She
Ben did not stop crying . He cried louder and louder

INTERVAL -2.778 - -0.574
CONTAINS 17.199%

cat took the little mouse home and decided to keep it
. It had a big road with many cars and trucks
Her mom my came running and saw the pan on
. We should think carefully before we do something to make
loud animal . He looked up and saw a big dog

INTERVAL -4.981 - -2.778
CONTAINS 0.034%

. S aman tha was amazed and she
What do you think you 're doing ?" The baby looked
She said , " You 're welcome , my loves .
Sarah remembered that she was supposed to put on her coat
You â re welcome ! Now , when
Token big
Token ID1263
Feature activation-2.94e-01

Pos logit contributions
 OUT+0.041
 arrest+0.040
 Johnson+0.040
joy+0.039
 Billy+0.038
Neg logit contributions
kin-0.026
ows-0.024
as-0.023
ily-0.022
ute-0.021
Token,
Token ID11
Feature activation-3.47e-01

Pos logit contributions
 OUT+0.030
 arrest+0.030
 Johnson+0.029
istent+0.028
joy+0.028
Neg logit contributions
kin-0.022
ows-0.019
 holes-0.018
as-0.018
ily-0.017
Token bill
Token ID2855
Feature activation+5.98e-01

Pos logit contributions
 OUT+0.036
 Johnson+0.035
 arrest+0.035
joy+0.034
 Billy+0.034
Neg logit contributions
kin-0.026
ows-0.023
as-0.023
ily-0.021
ute-0.021
Tokenowing
Token ID7855
Feature activation-3.15e+00

Pos logit contributions
kin+0.061
ows+0.056
as+0.055
ily+0.053
ute+0.053
Neg logit contributions
 OUT-0.046
 arrest-0.045
 Johnson-0.044
joy-0.042
 Billy-0.041
Token cloud
Token ID6279
Feature activation-9.95e-01

Pos logit contributions
 OUT+0.323
 arrest+0.318
 Johnson+0.312
joy+0.302
 Billy+0.298
Neg logit contributions
kin-0.239
ows-0.216
as-0.209
ily-0.200
a-0.196
Token hurd
Token ID22227
Feature activation+3.75e+00

Pos logit contributions
 OUT+0.104
 arrest+0.102
 Johnson+0.100
 Billy+0.097
joy+0.096
Neg logit contributions
kin-0.074
ows-0.066
as-0.064
ily-0.061
ute-0.060
Tokenling
Token ID1359
Feature activation-2.04e-01

Pos logit contributions
kin+0.390
ily+0.337
works+0.331
ute+0.321
Or+0.318
Neg logit contributions
joy-0.263
ge-0.240
 OUT-0.226
 Billy-0.221
ited-0.220
Token through
Token ID832
Feature activation-4.22e-01

Pos logit contributions
 OUT+0.021
 arrest+0.020
joy+0.020
 Johnson+0.020
 Billy+0.019
Neg logit contributions
kin-0.017
as-0.014
ows-0.014
ute-0.014
ily-0.013
Token the
Token ID262
Feature activation-1.63e-01

Pos logit contributions
 OUT+0.042
 Johnson+0.040
istent+0.040
 arrest+0.039
joy+0.038
Neg logit contributions
kin-0.032
 holes-0.029
ows-0.028
ily-0.028
as-0.027
Token sky
Token ID6766
Feature activation-3.26e-01

Pos logit contributions
 OUT+0.017
 arrest+0.017
 Johnson+0.017
 Billy+0.016
 Frankie+0.016
Neg logit contributions
kin-0.013
ows-0.011
as-0.011
ily-0.010
a-0.010
Token.
Token ID13
Feature activation-1.56e-01

Pos logit contributions
 OUT+0.033
 arrest+0.033
 Johnson+0.032
 Billy+0.031
joy+0.031
Neg logit contributions
kin-0.025
ows-0.022
as-0.021
ily-0.021
ute-0.020
Token.
Token ID13
Feature activation+6.90e-01

Pos logit contributions
 OUT+0.019
 arrest+0.019
 Johnson+0.019
joy+0.018
 Billy+0.018
Neg logit contributions
kin-0.016
ows-0.015
ute-0.015
as-0.014
utes-0.014
Token
Token ID220
Feature activation-1.51e+00

Pos logit contributions
kin+0.076
ows+0.071
ily+0.069
as+0.068
 holes+0.067
Neg logit contributions
 OUT-0.048
 arrest-0.047
 Johnson-0.044
joy-0.042
istent-0.041
Token
Token ID198
Feature activation+7.96e-01

Pos logit contributions
 Johnson+0.127
 OUT+0.126
 arrest+0.124
 Billy+0.121
joy+0.118
Neg logit contributions
kin-0.139
ows-0.123
as-0.121
 holes-0.117
ute-0.117
Token
Token ID198
Feature activation+7.26e-01

Pos logit contributions
kin+0.066
ows+0.060
as+0.058
ily+0.056
a+0.055
Neg logit contributions
 OUT-0.076
 arrest-0.075
 Johnson-0.073
joy-0.071
 Billy-0.070
TokenL
Token ID43
Feature activation+8.75e-01

Pos logit contributions
kin+0.045
ows+0.041
as+0.038
ute+0.035
ily+0.035
Neg logit contributions
 OUT-0.085
 arrest-0.083
 Johnson-0.082
 Billy-0.079
joy-0.079
Tokenily
Token ID813
Feature activation+3.72e+00

Pos logit contributions
kin+0.026
ows+0.023
ute+0.021
utes+0.021
 holes+0.020
Neg logit contributions
 arrest-0.117
 OUT-0.114
 Johnson-0.114
joy-0.113
 Billy-0.111
Token was
Token ID373
Feature activation+8.31e-02

Pos logit contributions
kin+0.277
ows+0.254
as+0.250
a+0.249
ily+0.242
Neg logit contributions
 OUT-0.379
 arrest-0.367
 Johnson-0.363
joy-0.363
 Frankie-0.350
Token sad
Token ID6507
Feature activation+7.97e-01

Pos logit contributions
kin+0.006
ows+0.006
as+0.005
ute+0.005
ily+0.005
Neg logit contributions
 OUT-0.009
 arrest-0.008
 Johnson-0.008
 Billy-0.008
joy-0.008
Token because
Token ID780
Feature activation-3.64e-01

Pos logit contributions
kin+0.065
ows+0.059
as+0.058
ily+0.055
a+0.054
Neg logit contributions
 OUT-0.078
 arrest-0.076
 Johnson-0.075
joy-0.073
 Billy-0.072
Token she
Token ID673
Feature activation-2.45e-01

Pos logit contributions
 OUT+0.038
istent+0.035
 arrest+0.034
arse+0.033
joy+0.033
Neg logit contributions
kin-0.030
ily-0.028
ila-0.025
 holes-0.025
ia-0.023
Token loved
Token ID6151
Feature activation+3.90e-01

Pos logit contributions
 OUT+0.021
 arrest+0.021
 Johnson+0.020
joy+0.020
 Frankie+0.019
Neg logit contributions
kin-0.023
ows-0.021
as-0.021
a-0.020
ily-0.020
Token.
Token ID13
Feature activation+4.15e-01

Pos logit contributions
kin+0.038
ily+0.035
ows+0.035
 holes+0.034
as+0.033
Neg logit contributions
 OUT-0.104
istent-0.099
 arrest-0.098
joy-0.095
 Johnson-0.094
Token
Token ID220
Feature activation-1.82e+00

Pos logit contributions
kin+0.040
ows+0.037
as+0.036
ily+0.035
a+0.034
Neg logit contributions
 OUT-0.034
 arrest-0.033
 Johnson-0.033
joy-0.031
 Billy-0.031
Token
Token ID198
Feature activation+4.33e-01

Pos logit contributions
 Johnson+0.150
 OUT+0.145
 Billy+0.144
 arrest+0.142
 Frankie+0.138
Neg logit contributions
kin-0.173
ows-0.151
as-0.148
 holes-0.146
ute-0.144
Token
Token ID198
Feature activation+4.08e-01

Pos logit contributions
kin+0.036
ows+0.033
as+0.032
ily+0.031
a+0.030
Neg logit contributions
 OUT-0.041
 arrest-0.040
 Johnson-0.040
joy-0.038
 Billy-0.038
TokenL
Token ID43
Feature activation+8.33e-01

Pos logit contributions
kin+0.032
ows+0.029
as+0.028
ily+0.026
ute+0.026
Neg logit contributions
 OUT-0.041
 arrest-0.040
 Johnson-0.040
 Billy-0.038
joy-0.038
Tokenily
Token ID813
Feature activation+3.69e+00

Pos logit contributions
kin+0.025
ows+0.022
utes+0.020
ute+0.020
 holes+0.019
Neg logit contributions
 arrest-0.110
 OUT-0.106
 Johnson-0.106
joy-0.105
 Billy-0.103
Token was
Token ID373
Feature activation-9.10e-02

Pos logit contributions
kin+0.304
ows+0.289
as+0.280
a+0.280
ily+0.279
Neg logit contributions
 OUT-0.342
 arrest-0.330
 Johnson-0.325
joy-0.323
istent-0.309
Token sad
Token ID6507
Feature activation+7.04e-01

Pos logit contributions
 OUT+0.009
 arrest+0.009
 Johnson+0.009
joy+0.008
 Billy+0.008
Neg logit contributions
kin-0.007
ows-0.007
as-0.006
ily-0.006
ute-0.006
Token because
Token ID780
Feature activation-5.26e-01

Pos logit contributions
kin+0.068
ows+0.062
as+0.061
ily+0.058
a+0.057
Neg logit contributions
 OUT-0.058
 Johnson-0.057
 arrest-0.057
joy-0.055
 Billy-0.055
Token she
Token ID673
Feature activation-4.11e-01

Pos logit contributions
 OUT+0.049
 arrest+0.046
istent+0.045
joy+0.043
 Johnson+0.043
Neg logit contributions
kin-0.048
ily-0.044
 holes-0.041
as-0.041
ows-0.040
Token loved
Token ID6151
Feature activation+3.02e-01

Pos logit contributions
 OUT+0.034
 arrest+0.034
 Johnson+0.033
joy+0.032
 Billy+0.031
Neg logit contributions
kin-0.039
ows-0.036
as-0.035
ily-0.034
a-0.034
Token.
Token ID13
Feature activation+6.64e-01

Pos logit contributions
 OUT+0.063
 arrest+0.061
joy+0.058
 Johnson+0.057
istent+0.057
Neg logit contributions
kin-0.032
ows-0.028
ily-0.027
as-0.026
a-0.025
Token
Token ID220
Feature activation-1.67e+00

Pos logit contributions
kin+0.068
as+0.061
ows+0.061
ute+0.058
a+0.058
Neg logit contributions
 Johnson-0.052
 OUT-0.051
 arrest-0.050
 Billy-0.049
joy-0.048
Token
Token ID198
Feature activation+6.96e-01

Pos logit contributions
 Johnson+0.142
 OUT+0.140
 arrest+0.137
 Billy+0.136
joy+0.132
Neg logit contributions
kin-0.153
ows-0.135
as-0.132
 holes-0.129
ute-0.127
Token
Token ID198
Feature activation+6.20e-01

Pos logit contributions
kin+0.060
ows+0.055
as+0.053
ily+0.051
ute+0.050
Neg logit contributions
 OUT-0.063
 arrest-0.062
 Johnson-0.062
 Billy-0.059
joy-0.059
TokenL
Token ID43
Feature activation+8.61e-01

Pos logit contributions
kin+0.050
ows+0.046
as+0.043
ute+0.042
ily+0.040
Neg logit contributions
 OUT-0.059
 arrest-0.058
 Johnson-0.057
 Billy-0.055
 Frankie-0.054
Tokenily
Token ID813
Feature activation+3.68e+00

Pos logit contributions
kin+0.024
ute+0.020
ows+0.020
utes+0.020
 holes+0.019
Neg logit contributions
 arrest-0.115
 OUT-0.112
 Johnson-0.111
joy-0.111
 Billy-0.109
Token went
Token ID1816
Feature activation+1.09e+00

Pos logit contributions
kin+0.337
ows+0.315
as+0.307
ily+0.300
a+0.298
Neg logit contributions
 OUT-0.318
 arrest-0.308
 Johnson-0.302
joy-0.294
 Frankie-0.283
Token home
Token ID1363
Feature activation-1.55e+00

Pos logit contributions
kin+0.078
ows+0.075
as+0.070
ily+0.070
a+0.067
Neg logit contributions
 OUT-0.115
 arrest-0.110
istent-0.108
 Johnson-0.106
 Frankie-0.104
Token feeling
Token ID4203
Feature activation-2.28e+00

Pos logit contributions
 OUT+0.184
 arrest+0.170
istent+0.163
 Frankie+0.163
 Johnson+0.162
Neg logit contributions
kin-0.099
ows-0.095
as-0.087
ily-0.085
a-0.084
Token very
Token ID845
Feature activation+1.60e+00

Pos logit contributions
 Billy+0.178
 arrest+0.178
joy+0.175
 returning+0.171
 Johnson+0.171
Neg logit contributions
kin-0.215
as-0.212
ows-0.207
utes-0.197
ute-0.195
Token upset
Token ID9247
Feature activation+2.53e-01

Pos logit contributions
kin+0.147
ows+0.140
as+0.140
ute+0.128
a+0.127
Neg logit contributions
 arrest-0.132
 OUT-0.130
 Billy-0.127
 Johnson-0.126
 Frankie-0.123
Token work
Token ID670
Feature activation-1.01e+00

Pos logit contributions
 OUT+0.037
 arrest+0.036
 Johnson+0.036
joy+0.036
 Frankie+0.033
Neg logit contributions
kin-0.041
ows-0.037
ily-0.036
as-0.036
 holes-0.035
Token.
Token ID13
Feature activation+5.52e-01

Pos logit contributions
 OUT+0.118
 arrest+0.116
 Johnson+0.112
joy+0.109
 Frankie+0.109
Neg logit contributions
kin-0.066
ows-0.059
as-0.056
ily-0.054
a-0.053
Token
Token ID198
Feature activation+6.54e-01

Pos logit contributions
kin+0.054
ows+0.050
as+0.049
ily+0.048
a+0.047
Neg logit contributions
 OUT-0.045
 arrest-0.044
 Johnson-0.042
joy-0.041
 Billy-0.040
Token
Token ID198
Feature activation+5.93e-01

Pos logit contributions
kin+0.058
ows+0.052
as+0.051
ily+0.048
 holes+0.048
Neg logit contributions
 OUT-0.059
 Johnson-0.058
 arrest-0.057
 Billy-0.055
joy-0.055
TokenL
Token ID43
Feature activation+8.46e-01

Pos logit contributions
kin+0.045
ows+0.041
as+0.039
ute+0.037
ily+0.037
Neg logit contributions
 OUT-0.061
 arrest-0.060
 Johnson-0.059
 Billy-0.057
 Frankie-0.056
Tokenily
Token ID813
Feature activation+3.68e+00

Pos logit contributions
kin+0.026
ows+0.023
utes+0.021
ute+0.021
 holes+0.020
Neg logit contributions
 arrest-0.111
 Johnson-0.107
 OUT-0.107
joy-0.106
 Billy-0.105
Token's
Token ID338
Feature activation+3.41e-01

Pos logit contributions
kin+0.324
ows+0.304
as+0.298
ily+0.292
a+0.291
Neg logit contributions
 OUT-0.326
 arrest-0.316
 Johnson-0.312
joy-0.307
 Frankie-0.295
Token mom
Token ID1995
Feature activation+1.05e+00

Pos logit contributions
kin+0.027
ows+0.026
as+0.024
ily+0.022
a+0.022
Neg logit contributions
 arrest-0.034
 OUT-0.033
 Johnson-0.033
joy-0.032
 Billy-0.032
Tokenmy
Token ID1820
Feature activation-1.35e+00

Pos logit contributions
as+0.084
a+0.084
ily+0.083
ows+0.079
kin+0.078
Neg logit contributions
 OUT-0.097
 arrest-0.094
joy-0.089
 Johnson-0.089
 Frankie-0.089
Token came
Token ID1625
Feature activation+9.08e-01

Pos logit contributions
 OUT+0.144
 arrest+0.141
 Johnson+0.135
joy+0.134
 Frankie+0.133
Neg logit contributions
a-0.089
ily-0.083
as-0.082
ows-0.077
kin-0.075
Token in
Token ID287
Feature activation+1.59e+00

Pos logit contributions
kin+0.054
as+0.052
ows+0.050
a+0.049
ily+0.049
Neg logit contributions
 OUT-0.105
 arrest-0.102
 Johnson-0.098
istent-0.097
 Frankie-0.096
Token gone
Token ID3750
Feature activation+4.51e-01

Pos logit contributions
 OUT+0.008
 arrest+0.008
 Johnson+0.007
joy+0.007
 Billy+0.007
Neg logit contributions
kin-0.010
ows-0.010
as-0.009
ily-0.009
 holes-0.009
Token.
Token ID13
Feature activation+4.10e-01

Pos logit contributions
kin+0.034
ows+0.031
as+0.029
 holes+0.028
ily+0.028
Neg logit contributions
 OUT-0.047
 arrest-0.047
 Johnson-0.044
joy-0.043
istent-0.042
Token
Token ID198
Feature activation+4.30e-01

Pos logit contributions
kin+0.034
ows+0.032
as+0.031
ily+0.030
 holes+0.029
Neg logit contributions
 OUT-0.039
 arrest-0.038
 Johnson-0.036
joy-0.035
istent-0.035
Token
Token ID198
Feature activation+4.01e-01

Pos logit contributions
kin+0.039
ows+0.035
as+0.034
 holes+0.032
ute+0.032
Neg logit contributions
 OUT-0.038
 Johnson-0.037
 arrest-0.037
 Billy-0.036
joy-0.035
TokenL
Token ID43
Feature activation+8.44e-01

Pos logit contributions
kin+0.026
ows+0.023
as+0.022
ily+0.021
a+0.021
Neg logit contributions
 OUT-0.046
 arrest-0.045
 Johnson-0.045
joy-0.044
 Billy-0.043
Tokenily
Token ID813
Feature activation+3.67e+00

Pos logit contributions
kin+0.024
ows+0.018
ute+0.017
utes+0.016
 holes+0.016
Neg logit contributions
 arrest-0.117
 OUT-0.114
 Johnson-0.114
 Billy-0.112
joy-0.111
Token's
Token ID338
Feature activation+3.07e-01

Pos logit contributions
kin+0.323
ows+0.310
as+0.301
ily+0.297
a+0.295
Neg logit contributions
 OUT-0.322
 arrest-0.309
 Johnson-0.306
joy-0.302
 Frankie-0.290
Token friends
Token ID2460
Feature activation+6.57e-01

Pos logit contributions
kin+0.026
ows+0.026
as+0.024
works+0.023
ily+0.022
Neg logit contributions
 arrest-0.028
 Johnson-0.027
 OUT-0.027
joy-0.026
 Billy-0.026
Token tried
Token ID3088
Feature activation+3.12e-01

Pos logit contributions
ily+0.044
as+0.043
ows+0.042
a+0.042
kin+0.040
Neg logit contributions
 arrest-0.068
 OUT-0.066
 Johnson-0.063
joy-0.062
 Frankie-0.062
Token to
Token ID284
Feature activation-3.29e-01

Pos logit contributions
 holes+0.015
ows+0.015
kin+0.014
ily+0.014
as+0.013
Neg logit contributions
 OUT-0.039
istent-0.038
 arrest-0.037
ited-0.035
 Frankie-0.035
Token help
Token ID1037
Feature activation+2.82e-01

Pos logit contributions
 OUT+0.028
 arrest+0.027
 Johnson+0.027
joy+0.027
istent+0.025
Neg logit contributions
kin-0.030
ows-0.028
as-0.027
ily-0.027
a-0.026
Token.
Token ID13
Feature activation+5.51e-01

Pos logit contributions
 OUT+0.055
joy+0.054
 arrest+0.054
 Johnson+0.053
 Frankie+0.051
Neg logit contributions
kin-0.034
ows-0.031
ily-0.030
as-0.029
a-0.028
Token
Token ID220
Feature activation-1.75e+00

Pos logit contributions
kin+0.051
ows+0.047
as+0.046
ily+0.045
a+0.043
Neg logit contributions
 OUT-0.048
 arrest-0.047
 Johnson-0.045
joy-0.044
 Billy-0.043
Token
Token ID198
Feature activation+5.76e-01

Pos logit contributions
 Johnson+0.150
 OUT+0.149
 arrest+0.146
 Billy+0.143
joy+0.139
Neg logit contributions
kin-0.158
ows-0.140
as-0.136
 holes-0.133
ute-0.132
Token
Token ID198
Feature activation+5.32e-01

Pos logit contributions
kin+0.046
ows+0.042
as+0.041
ily+0.040
a+0.039
Neg logit contributions
 OUT-0.057
 arrest-0.055
 Johnson-0.054
joy-0.052
 Billy-0.051
TokenL
Token ID43
Feature activation+8.15e-01

Pos logit contributions
kin+0.038
ows+0.035
as+0.033
ily+0.032
ute+0.031
Neg logit contributions
 OUT-0.057
 arrest-0.056
 Johnson-0.055
joy-0.053
 Billy-0.053
Tokenily
Token ID813
Feature activation+3.67e+00

Pos logit contributions
kin+0.026
ows+0.022
ute+0.021
utes+0.021
 holes+0.020
Neg logit contributions
 arrest-0.106
 Johnson-0.103
 OUT-0.102
joy-0.101
 Emmy-0.099
Token's
Token ID338
Feature activation+2.66e-01

Pos logit contributions
kin+0.324
ows+0.304
as+0.302
a+0.298
ily+0.298
Neg logit contributions
 OUT-0.321
 arrest-0.313
 Johnson-0.307
joy-0.305
 Frankie-0.290
Token mom
Token ID1995
Feature activation+9.56e-01

Pos logit contributions
kin+0.021
ows+0.019
as+0.018
ily+0.017
ute+0.017
Neg logit contributions
 arrest-0.027
 OUT-0.027
 Johnson-0.026
 Billy-0.025
joy-0.025
Token came
Token ID1625
Feature activation+8.85e-01

Pos logit contributions
a+0.070
as+0.068
ily+0.067
kin+0.062
ows+0.061
Neg logit contributions
 arrest-0.097
 OUT-0.096
joy-0.093
 Johnson-0.088
 Frankie-0.088
Token in
Token ID287
Feature activation+1.62e+00

Pos logit contributions
kin+0.050
as+0.049
a+0.047
ows+0.046
ily+0.045
Neg logit contributions
 OUT-0.104
 arrest-0.101
 Johnson-0.097
istent-0.097
 Frankie-0.096
Token and
Token ID290
Feature activation+4.74e-01

Pos logit contributions
kin+0.092
ily+0.080
ows+0.078
as+0.076
 holes+0.075
Neg logit contributions
 OUT-0.193
 arrest-0.180
istent-0.180
 Johnson-0.179
 Frankie-0.176
Token all
Token ID477
Feature activation-7.81e-01

Pos logit contributions
kin+0.092
ows+0.086
as+0.080
ily+0.077
a+0.075
Neg logit contributions
 OUT-0.143
 arrest-0.140
 Johnson-0.135
 Frankie-0.131
joy-0.131
Token.
Token ID13
Feature activation+4.84e-01

Pos logit contributions
 OUT+0.081
 arrest+0.080
 Johnson+0.078
joy+0.076
 Billy+0.075
Neg logit contributions
kin-0.059
ows-0.053
as-0.052
ily-0.049
a-0.048
Token
Token ID198
Feature activation+5.95e-01

Pos logit contributions
kin+0.045
ows+0.041
as+0.040
ily+0.039
a+0.038
Neg logit contributions
 OUT-0.042
 arrest-0.041
 Johnson-0.040
joy-0.039
 Billy-0.038
Token
Token ID198
Feature activation+5.36e-01

Pos logit contributions
kin+0.051
ows+0.046
as+0.045
ily+0.043
ute+0.042
Neg logit contributions
 OUT-0.055
 arrest-0.054
 Johnson-0.054
joy-0.051
 Billy-0.051
TokenL
Token ID43
Feature activation+8.02e-01

Pos logit contributions
kin+0.047
ows+0.044
as+0.042
ute+0.040
ily+0.039
Neg logit contributions
 OUT-0.048
 arrest-0.048
 Johnson-0.046
 Billy-0.044
joy-0.043
Tokenily
Token ID813
Feature activation+3.66e+00

Pos logit contributions
kin+0.022
ows+0.018
ute+0.016
 holes+0.016
utes+0.015
Neg logit contributions
 arrest-0.112
 OUT-0.109
 Johnson-0.108
joy-0.106
 Billy-0.105
Token was
Token ID373
Feature activation+4.32e-03

Pos logit contributions
kin+0.298
ows+0.276
as+0.267
ily+0.258
a+0.255
Neg logit contributions
 OUT-0.355
 arrest-0.345
 Johnson-0.341
joy-0.330
 Frankie-0.324
Token so
Token ID523
Feature activation+1.83e+00

Pos logit contributions
kin+0.000
ows+0.000
as+0.000
ily+0.000
a+0.000
Neg logit contributions
 OUT-0.001
 arrest-0.000
 Johnson-0.000
joy-0.000
 Billy-0.000
Token happy
Token ID3772
Feature activation-1.81e-01

Pos logit contributions
kin+0.165
ows+0.160
ute+0.150
works+0.149
as+0.148
Neg logit contributions
 arrest-0.146
 Johnson-0.144
joy-0.142
 returning-0.142
 Billy-0.140
Token that
Token ID326
Feature activation+1.07e+00

Pos logit contributions
 OUT+0.020
 arrest+0.019
 Johnson+0.019
 Frankie+0.019
istent+0.019
Neg logit contributions
kin-0.012
ows-0.011
as-0.010
ily-0.010
 holes-0.010
Token she
Token ID673
Feature activation-4.26e-01

Pos logit contributions
kin+0.091
ily+0.085
 holes+0.076
ila+0.074
a+0.072
Neg logit contributions
 OUT-0.109
 arrest-0.104
istent-0.102
joy-0.095
 Johnson-0.095
Token them
Token ID606
Feature activation+1.25e+00

Pos logit contributions
kin+0.055
ows+0.050
as+0.049
ily+0.047
 holes+0.046
Neg logit contributions
 OUT-0.066
 arrest-0.065
 Johnson-0.063
joy-0.061
 Billy-0.060
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
kin+0.083
ows+0.076
as+0.073
ily+0.068
a+0.067
Neg logit contributions
 OUT-0.139
 arrest-0.137
 Johnson-0.135
joy-0.131
 Frankie-0.129
Token
Token ID198
Feature activation+5.29e-01

Pos logit contributions
kin+0.047
ows+0.043
as+0.042
ily+0.040
a+0.040
Neg logit contributions
 OUT-0.040
 Johnson-0.039
 arrest-0.039
 Billy-0.038
joy-0.037
Token
Token ID198
Feature activation+4.74e-01

Pos logit contributions
kin+0.049
ows+0.045
as+0.043
 holes+0.041
ute+0.041
Neg logit contributions
 Johnson-0.044
 OUT-0.044
 arrest-0.043
 Billy-0.042
joy-0.041
TokenL
Token ID43
Feature activation+8.27e-01

Pos logit contributions
kin+0.032
ows+0.029
as+0.027
ute+0.025
 holes+0.025
Neg logit contributions
 OUT-0.052
 arrest-0.051
 Johnson-0.051
 Billy-0.049
joy-0.048
Tokenily
Token ID813
Feature activation+3.66e+00

Pos logit contributions
kin+0.023
ows+0.019
 holes+0.016
ute+0.015
as+0.015
Neg logit contributions
 arrest-0.115
 Johnson-0.114
 OUT-0.114
 Billy-0.111
joy-0.110
Token's
Token ID338
Feature activation+2.97e-01

Pos logit contributions
kin+0.274
ows+0.264
as+0.261
a+0.259
ily+0.251
Neg logit contributions
 OUT-0.366
 arrest-0.353
 Johnson-0.349
joy-0.343
 Frankie-0.333
Token mom
Token ID1995
Feature activation+1.17e+00

Pos logit contributions
kin+0.024
ows+0.023
as+0.021
ily+0.021
ila+0.020
Neg logit contributions
 Johnson-0.028
 arrest-0.028
 OUT-0.028
 Billy-0.027
joy-0.027
Tokenmy
Token ID1820
Feature activation-1.35e+00

Pos logit contributions
as+0.120
a+0.117
ows+0.112
kin+0.108
ily+0.108
Neg logit contributions
 arrest-0.093
 OUT-0.091
joy-0.084
 Frankie-0.076
 Johnson-0.074
Token said
Token ID531
Feature activation+9.69e-02

Pos logit contributions
 arrest+0.148
 OUT+0.145
joy+0.137
 Johnson+0.130
 Frankie+0.127
Neg logit contributions
a-0.092
as-0.087
ows-0.085
kin-0.083
ily-0.079
Token that
Token ID326
Feature activation+9.54e-01

Pos logit contributions
kin+0.008
ows+0.007
ily+0.007
as+0.007
a+0.007
Neg logit contributions
 OUT-0.009
 arrest-0.009
 Johnson-0.009
joy-0.009
istent-0.008
Token.
Token ID13
Feature activation+7.44e-01

Pos logit contributions
kin+0.048
ows+0.042
as+0.042
ily+0.040
ute+0.040
Neg logit contributions
 Johnson-0.059
 OUT-0.059
 arrest-0.058
 Billy-0.057
 Frankie-0.055
Token
Token ID220
Feature activation-1.52e+00

Pos logit contributions
kin+0.071
ows+0.065
as+0.064
ily+0.061
a+0.061
Neg logit contributions
 OUT-0.062
 arrest-0.061
 Johnson-0.060
joy-0.057
 Billy-0.057
Token
Token ID198
Feature activation+7.99e-01

Pos logit contributions
 Johnson+0.126
 OUT+0.123
 Billy+0.121
 arrest+0.120
 Frankie+0.117
Neg logit contributions
kin-0.143
ows-0.125
as-0.122
 holes-0.120
ute-0.120
Token
Token ID198
Feature activation+7.26e-01

Pos logit contributions
kin+0.070
ows+0.063
as+0.061
ily+0.059
ute+0.058
Neg logit contributions
 OUT-0.072
 arrest-0.071
 Johnson-0.070
 Billy-0.067
joy-0.067
TokenL
Token ID43
Feature activation+8.08e-01

Pos logit contributions
kin+0.054
ows+0.049
as+0.044
ute+0.043
ily+0.041
Neg logit contributions
 OUT-0.074
 Johnson-0.073
 arrest-0.073
 Billy-0.071
 Frankie-0.068
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.024
ute+0.020
ows+0.019
utes+0.018
 holes+0.018
Neg logit contributions
 arrest-0.107
 OUT-0.106
 Johnson-0.105
joy-0.104
 Billy-0.102
Token went
Token ID1816
Feature activation+9.75e-01

Pos logit contributions
kin+0.320
ows+0.294
as+0.286
ily+0.276
a+0.272
Neg logit contributions
 OUT-0.333
 arrest-0.326
 Johnson-0.320
joy-0.309
 Billy-0.303
Token outside
Token ID2354
Feature activation-1.05e+00

Pos logit contributions
kin+0.070
ows+0.066
as+0.063
ily+0.061
a+0.059
Neg logit contributions
 OUT-0.103
 arrest-0.100
 Johnson-0.097
istent-0.096
 Frankie-0.094
Token to
Token ID284
Feature activation-3.70e-01

Pos logit contributions
 OUT+0.131
 arrest+0.121
istent+0.121
 Johnson+0.119
 Frankie+0.119
Neg logit contributions
kin-0.056
ily-0.050
ows-0.048
as-0.048
a-0.047
Token play
Token ID711
Feature activation-5.71e-01

Pos logit contributions
 OUT+0.034
istent+0.033
joy+0.033
 Johnson+0.032
 arrest+0.032
Neg logit contributions
kin-0.031
ily-0.028
ows-0.028
 holes-0.027
a-0.026
Token and
Token ID290
Feature activation+4.82e-01

Pos logit contributions
 arrest+0.051
 Johnson+0.050
 OUT+0.050
 Billy+0.050
joy+0.049
Neg logit contributions
as-0.046
kin-0.045
ows-0.042
a-0.042
utes-0.041
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 OUT+0.098
 arrest+0.097
 Johnson+0.094
joy+0.092
 Billy+0.090
Neg logit contributions
kin-0.060
ows-0.053
as-0.051
ily-0.049
a-0.048
Token
Token ID220
Feature activation-1.50e+00

Pos logit contributions
kin+0.093
ows+0.087
ily+0.083
as+0.082
 holes+0.079
Neg logit contributions
 OUT-0.103
 arrest-0.102
 Johnson-0.095
joy-0.094
istent-0.093
Token
Token ID198
Feature activation+1.04e+00

Pos logit contributions
 Johnson+0.125
 OUT+0.123
 Billy+0.120
 arrest+0.120
 Frankie+0.116
Neg logit contributions
kin-0.139
ows-0.123
as-0.120
 holes-0.118
ute-0.116
Token
Token ID198
Feature activation+9.70e-01

Pos logit contributions
kin+0.077
ows+0.072
as+0.071
ily+0.068
a+0.067
Neg logit contributions
 OUT-0.108
 arrest-0.106
 Johnson-0.101
joy-0.099
istent-0.097
TokenL
Token ID43
Feature activation+8.50e-01

Pos logit contributions
kin+0.062
ows+0.055
as+0.052
ily+0.049
 holes+0.048
Neg logit contributions
 OUT-0.113
 arrest-0.111
 Johnson-0.109
 Billy-0.106
joy-0.105
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.028
 holes+0.024
ows+0.023
ute+0.022
utes+0.022
Neg logit contributions
 arrest-0.109
 Johnson-0.106
 OUT-0.105
 Billy-0.105
 Emmy-0.104
Token said
Token ID531
Feature activation+1.66e-01

Pos logit contributions
kin+0.289
ows+0.263
as+0.257
ily+0.252
a+0.251
Neg logit contributions
 OUT-0.363
 arrest-0.357
 Johnson-0.344
joy-0.340
 Frankie-0.328
Token,
Token ID11
Feature activation+1.50e-01

Pos logit contributions
kin+0.015
ows+0.014
ily+0.014
as+0.013
a+0.013
Neg logit contributions
 OUT-0.015
 arrest-0.014
 Johnson-0.014
joy-0.013
istent-0.013
Token "
Token ID366
Feature activation+3.73e-01

Pos logit contributions
kin+0.011
ows+0.010
ily+0.010
as+0.010
a+0.009
Neg logit contributions
 arrest-0.016
 OUT-0.015
 Johnson-0.014
joy-0.014
istent-0.014
TokenYes
Token ID5297
Feature activation-2.26e-01

Pos logit contributions
kin+0.030
ows+0.028
as+0.026
 holes+0.025
ily+0.024
Neg logit contributions
 OUT-0.038
 Johnson-0.037
 arrest-0.037
 Billy-0.035
joy-0.035
Token,
Token ID11
Feature activation-6.07e-02

Pos logit contributions
 arrest+0.022
 OUT+0.022
joy+0.021
 Johnson+0.021
 Frankie+0.020
Neg logit contributions
kin-0.019
ows-0.017
ily-0.016
ia-0.016
as-0.016
Token.
Token ID13
Feature activation+5.87e-01

Pos logit contributions
 OUT+0.111
 arrest+0.108
 Johnson+0.105
joy+0.103
 Frankie+0.102
Neg logit contributions
kin-0.064
ows-0.058
as-0.055
ily-0.053
a-0.052
Token
Token ID220
Feature activation-1.80e+00

Pos logit contributions
kin+0.056
ows+0.052
as+0.051
ily+0.050
a+0.049
Neg logit contributions
 OUT-0.049
 arrest-0.047
 Johnson-0.046
joy-0.044
 Billy-0.044
Token
Token ID198
Feature activation+5.72e-01

Pos logit contributions
 Johnson+0.152
 OUT+0.149
 Billy+0.145
 arrest+0.145
joy+0.140
Neg logit contributions
kin-0.167
ows-0.146
as-0.143
 holes-0.141
ute-0.139
Token
Token ID198
Feature activation+5.34e-01

Pos logit contributions
kin+0.046
ows+0.042
as+0.041
ily+0.040
a+0.039
Neg logit contributions
 OUT-0.056
 arrest-0.055
 Johnson-0.053
joy-0.052
 Billy-0.051
TokenL
Token ID43
Feature activation+8.42e-01

Pos logit contributions
kin+0.040
ows+0.036
as+0.035
ily+0.033
ute+0.032
Neg logit contributions
 OUT-0.056
 arrest-0.055
 Johnson-0.054
joy-0.052
 Billy-0.052
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.027
ows+0.023
utes+0.023
ute+0.022
 holes+0.022
Neg logit contributions
 arrest-0.109
 Johnson-0.106
 OUT-0.104
joy-0.104
 Billy-0.102
Token's
Token ID338
Feature activation+3.42e-01

Pos logit contributions
kin+0.318
ows+0.299
as+0.293
a+0.289
ily+0.288
Neg logit contributions
 OUT-0.327
 arrest-0.318
 Johnson-0.311
joy-0.308
 Frankie-0.295
Token mom
Token ID1995
Feature activation+9.53e-01

Pos logit contributions
kin+0.028
ows+0.028
as+0.025
ily+0.024
ute+0.024
Neg logit contributions
 arrest-0.032
 Johnson-0.032
 OUT-0.031
 Billy-0.031
joy-0.031
Token saw
Token ID2497
Feature activation+8.56e-01

Pos logit contributions
a+0.074
as+0.074
ily+0.072
ows+0.069
kin+0.067
Neg logit contributions
 OUT-0.092
 arrest-0.091
joy-0.085
 Frankie-0.083
 Johnson-0.083
Token her
Token ID607
Feature activation+5.20e-01

Pos logit contributions
kin+0.065
ily+0.062
ows+0.060
 holes+0.058
as+0.058
Neg logit contributions
 OUT-0.085
 arrest-0.081
 Johnson-0.081
istent-0.079
joy-0.078
Token sad
Token ID6507
Feature activation+6.49e-01

Pos logit contributions
kin+0.048
ows+0.044
as+0.042
ily+0.042
a+0.041
Neg logit contributions
 OUT-0.046
 arrest-0.044
 Johnson-0.043
 Frankie-0.042
 Billy-0.040
Token found
Token ID1043
Feature activation+1.00e+00

Pos logit contributions
 OUT+0.048
 arrest+0.047
 Johnson+0.046
joy+0.043
 Frankie+0.043
Neg logit contributions
kin-0.056
ows-0.052
as-0.050
ily-0.049
a-0.048
Token.
Token ID13
Feature activation+4.52e-01

Pos logit contributions
kin+0.076
ows+0.068
as+0.066
ute+0.063
ily+0.062
Neg logit contributions
 OUT-0.103
 arrest-0.102
 Johnson-0.101
joy-0.097
 Billy-0.096
Token
Token ID198
Feature activation+5.01e-01

Pos logit contributions
kin+0.042
ows+0.039
as+0.037
ily+0.037
a+0.036
Neg logit contributions
 OUT-0.039
 arrest-0.038
 Johnson-0.037
joy-0.036
 Billy-0.035
Token
Token ID198
Feature activation+4.70e-01

Pos logit contributions
kin+0.045
ows+0.041
as+0.039
ily+0.037
 holes+0.037
Neg logit contributions
 OUT-0.044
 Johnson-0.044
 arrest-0.044
 Billy-0.042
joy-0.041
TokenL
Token ID43
Feature activation+8.46e-01

Pos logit contributions
kin+0.033
ows+0.029
as+0.027
ute+0.026
ily+0.026
Neg logit contributions
 OUT-0.052
 arrest-0.051
 Johnson-0.050
joy-0.048
 Billy-0.048
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.024
ows+0.021
utes+0.019
 holes+0.019
ute+0.018
Neg logit contributions
 arrest-0.115
 OUT-0.112
 Johnson-0.112
joy-0.110
 Billy-0.109
Token started
Token ID2067
Feature activation+5.36e-01

Pos logit contributions
kin+0.310
ows+0.290
as+0.281
ily+0.274
a+0.271
Neg logit contributions
 OUT-0.338
 arrest-0.330
 Johnson-0.324
joy-0.316
 Frankie-0.305
Token to
Token ID284
Feature activation-3.02e-01

Pos logit contributions
kin+0.028
 holes+0.028
ows+0.027
as+0.027
a+0.026
Neg logit contributions
 OUT-0.062
istent-0.060
 arrest-0.059
 Frankie-0.058
 Johnson-0.057
Token feel
Token ID1254
Feature activation-6.89e-01

Pos logit contributions
 OUT+0.025
 arrest+0.024
joy+0.023
 Johnson+0.022
istent+0.022
Neg logit contributions
kin-0.028
ows-0.026
 holes-0.026
ily-0.025
a-0.024
Token worried
Token ID7960
Feature activation+2.01e-01

Pos logit contributions
 arrest+0.053
 Billy+0.053
joy+0.053
 OUT+0.053
 returning+0.051
Neg logit contributions
kin-0.067
as-0.064
ows-0.063
utes-0.061
ute-0.060
Token.
Token ID13
Feature activation+5.75e-01

Pos logit contributions
kin+0.018
as+0.016
ows+0.016
ute+0.015
a+0.015
Neg logit contributions
 OUT-0.018
 Johnson-0.017
 arrest-0.017
 Billy-0.017
joy-0.016
Token.
Token ID13
Feature activation+5.58e-01

Pos logit contributions
 OUT+0.068
 arrest+0.067
 Johnson+0.065
joy+0.063
 Billy+0.062
Neg logit contributions
kin-0.043
ows-0.039
as-0.037
ily-0.035
a-0.034
Token
Token ID220
Feature activation-1.60e+00

Pos logit contributions
ows+0.053
ily+0.052
kin+0.052
 holes+0.049
as+0.049
Neg logit contributions
 OUT-0.045
 arrest-0.044
istent-0.039
 Johnson-0.038
joy-0.038
Token
Token ID198
Feature activation+6.81e-01

Pos logit contributions
 OUT+0.140
 Johnson+0.139
 arrest+0.137
 Billy+0.132
joy+0.130
Neg logit contributions
kin-0.145
ows-0.128
as-0.126
 holes-0.121
ute-0.120
Token
Token ID198
Feature activation+6.18e-01

Pos logit contributions
kin+0.057
ows+0.052
as+0.051
ily+0.049
a+0.048
Neg logit contributions
 OUT-0.064
 arrest-0.063
 Johnson-0.062
joy-0.060
 Billy-0.059
TokenL
Token ID43
Feature activation+8.15e-01

Pos logit contributions
kin+0.058
ows+0.055
as+0.052
ute+0.049
ily+0.049
Neg logit contributions
 OUT-0.052
 arrest-0.051
 Johnson-0.049
 Billy-0.047
joy-0.046
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.022
ows+0.020
ute+0.017
 holes+0.017
utes+0.017
Neg logit contributions
 arrest-0.112
 OUT-0.110
 Johnson-0.108
joy-0.107
 Billy-0.105
Token played
Token ID2826
Feature activation+3.99e-01

Pos logit contributions
kin+0.300
as+0.280
ows+0.277
a+0.273
ily+0.268
Neg logit contributions
 OUT-0.346
 Johnson-0.337
 arrest-0.332
joy-0.321
 Frankie-0.320
Token with
Token ID351
Feature activation-1.96e-01

Pos logit contributions
kin+0.032
as+0.032
ows+0.030
a+0.028
works+0.028
Neg logit contributions
 arrest-0.036
 OUT-0.035
joy-0.035
 Billy-0.034
 Johnson-0.034
Token the
Token ID262
Feature activation+1.65e-01

Pos logit contributions
 OUT+0.018
 arrest+0.017
 Johnson+0.017
joy+0.016
istent+0.016
Neg logit contributions
kin-0.017
ows-0.016
as-0.015
ily-0.015
 holes-0.015
Token ball
Token ID2613
Feature activation+5.08e-01

Pos logit contributions
kin+0.010
ows+0.008
 holes+0.008
as+0.008
ily+0.008
Neg logit contributions
 OUT-0.020
 arrest-0.019
 Johnson-0.019
joy-0.019
 Frankie-0.018
Token for
Token ID329
Feature activation+1.28e-01

Pos logit contributions
kin+0.046
ows+0.042
as+0.041
ily+0.039
ute+0.039
Neg logit contributions
 OUT-0.044
 arrest-0.043
 Johnson-0.042
 Billy-0.040
joy-0.040
Token.
Token ID13
Feature activation+3.18e-01

Pos logit contributions
kin+0.068
ows+0.061
as+0.059
ute+0.056
ily+0.055
Neg logit contributions
 OUT-0.095
 arrest-0.094
 Johnson-0.093
joy-0.090
 Billy-0.089
Token
Token ID220
Feature activation-1.77e+00

Pos logit contributions
kin+0.025
ows+0.025
ily+0.023
as+0.023
 holes+0.023
Neg logit contributions
 arrest-0.031
 OUT-0.031
istent-0.028
 Johnson-0.028
joy-0.027
Token
Token ID198
Feature activation+4.41e-01

Pos logit contributions
 Johnson+0.146
 OUT+0.142
 Billy+0.140
 arrest+0.138
joy+0.134
Neg logit contributions
kin-0.169
ows-0.148
as-0.145
 holes-0.142
ute-0.141
Token
Token ID198
Feature activation+4.11e-01

Pos logit contributions
kin+0.035
ows+0.032
as+0.031
ily+0.030
a+0.030
Neg logit contributions
 OUT-0.044
 arrest-0.043
 Johnson-0.041
joy-0.040
 Billy-0.039
TokenL
Token ID43
Feature activation+8.08e-01

Pos logit contributions
kin+0.026
ows+0.023
as+0.022
ily+0.021
a+0.021
Neg logit contributions
 OUT-0.048
 arrest-0.047
 Johnson-0.046
joy-0.046
 Billy-0.044
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.020
ows+0.014
 holes+0.012
ute+0.012
as+0.012
Neg logit contributions
 arrest-0.116
 OUT-0.116
 Johnson-0.114
 Billy-0.113
joy-0.112
Token's
Token ID338
Feature activation+2.49e-01

Pos logit contributions
kin+0.320
ows+0.301
as+0.292
ily+0.284
a+0.282
Neg logit contributions
 OUT-0.327
 arrest-0.318
 Johnson-0.312
joy-0.304
 Frankie-0.294
Token mom
Token ID1995
Feature activation+1.02e+00

Pos logit contributions
kin+0.020
ows+0.019
as+0.018
ily+0.017
ute+0.017
Neg logit contributions
 arrest-0.024
 Johnson-0.024
 OUT-0.024
joy-0.023
 Billy-0.023
Token saw
Token ID2497
Feature activation+6.94e-01

Pos logit contributions
a+0.069
as+0.068
ily+0.065
ows+0.062
kin+0.058
Neg logit contributions
 OUT-0.107
 arrest-0.106
joy-0.100
istent-0.100
 Johnson-0.096
Token her
Token ID607
Feature activation+4.76e-01

Pos logit contributions
kin+0.049
ily+0.048
ows+0.046
 holes+0.045
as+0.044
Neg logit contributions
 OUT-0.071
istent-0.068
 arrest-0.068
 Johnson-0.067
joy-0.066
Token searching
Token ID10342
Feature activation-9.72e-01

Pos logit contributions
kin+0.043
ows+0.040
as+0.038
ily+0.037
a+0.037
Neg logit contributions
 OUT-0.043
 arrest-0.040
 Johnson-0.039
istent-0.038
 Frankie-0.038
Token it
Token ID340
Feature activation+7.78e-01

Pos logit contributions
 OUT+0.020
 arrest+0.019
 Johnson+0.019
joy+0.018
istent+0.018
Neg logit contributions
kin-0.015
ily-0.013
ows-0.013
 holes-0.013
as-0.013
Token.
Token ID13
Feature activation+1.69e-01

Pos logit contributions
kin+0.055
ows+0.050
as+0.048
ily+0.046
a+0.045
Neg logit contributions
 OUT-0.084
 arrest-0.083
 Johnson-0.081
joy-0.079
 Billy-0.078
Token
Token ID198
Feature activation+2.51e-01

Pos logit contributions
kin+0.013
ows+0.013
ily+0.012
as+0.012
a+0.012
Neg logit contributions
 OUT-0.016
 arrest-0.016
 Johnson-0.015
joy-0.015
istent-0.015
Token
Token ID198
Feature activation+2.44e-01

Pos logit contributions
kin+0.022
ows+0.020
as+0.019
ily+0.019
 holes+0.018
Neg logit contributions
 OUT-0.022
 arrest-0.022
 Johnson-0.022
 Billy-0.021
joy-0.021
TokenL
Token ID43
Feature activation+7.95e-01

Pos logit contributions
kin+0.019
ows+0.017
as+0.016
ute+0.015
 holes+0.015
Neg logit contributions
 OUT-0.025
 arrest-0.025
 Johnson-0.024
 Billy-0.023
 Frankie-0.023
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.025
ows+0.021
 holes+0.020
ute+0.018
utes+0.016
Neg logit contributions
 arrest-0.107
 OUT-0.104
joy-0.103
 Johnson-0.102
 returning-0.100
Token frowned
Token ID32198
Feature activation+8.38e-02

Pos logit contributions
kin+0.325
ows+0.307
as+0.304
a+0.296
ily+0.296
Neg logit contributions
 OUT-0.318
 arrest-0.309
 Johnson-0.305
joy-0.298
 Frankie-0.285
Token as
Token ID355
Feature activation-6.73e-01

Pos logit contributions
kin+0.008
as+0.008
ows+0.008
ily+0.007
utes+0.007
Neg logit contributions
 Johnson-0.007
 OUT-0.007
 Billy-0.006
joy-0.006
 returning-0.006
Token she
Token ID673
Feature activation-5.43e-01

Pos logit contributions
 OUT+0.052
 arrest+0.051
 Johnson+0.049
joy+0.047
 Billy+0.046
Neg logit contributions
kin-0.069
ows-0.063
as-0.062
ily-0.062
a-0.059
Token looked
Token ID3114
Feature activation+6.35e-01

Pos logit contributions
 OUT+0.046
 arrest+0.045
 Johnson+0.045
joy+0.043
 Billy+0.042
Neg logit contributions
kin-0.050
ows-0.047
as-0.045
ily-0.044
a-0.043
Token at
Token ID379
Feature activation+6.29e-01

Pos logit contributions
kin+0.051
ows+0.042
as+0.042
ute+0.040
ia+0.040
Neg logit contributions
 OUT-0.063
joy-0.063
 Billy-0.061
 Johnson-0.060
 arrest-0.060
Token.
Token ID13
Feature activation+3.11e-01

Pos logit contributions
kin+0.038
ows+0.034
as+0.033
ily+0.032
a+0.031
Neg logit contributions
 OUT-0.047
 arrest-0.047
 Johnson-0.046
joy-0.044
 Billy-0.044
Token
Token ID220
Feature activation-1.81e+00

Pos logit contributions
kin+0.033
ows+0.032
as+0.030
ily+0.030
 holes+0.029
Neg logit contributions
 OUT-0.022
 arrest-0.022
 Johnson-0.021
joy-0.020
 Frankie-0.019
Token
Token ID198
Feature activation+5.16e-01

Pos logit contributions
 OUT+0.161
 Johnson+0.159
 arrest+0.157
 Billy+0.151
joy+0.150
Neg logit contributions
kin-0.160
ows-0.143
as-0.140
ily-0.134
 holes-0.133
Token
Token ID198
Feature activation+4.70e-01

Pos logit contributions
kin+0.045
ows+0.041
as+0.040
ily+0.038
ute+0.038
Neg logit contributions
 OUT-0.047
 arrest-0.046
 Johnson-0.046
joy-0.044
 Billy-0.043
TokenL
Token ID43
Feature activation+8.32e-01

Pos logit contributions
kin+0.034
ows+0.030
as+0.028
ute+0.027
 holes+0.026
Neg logit contributions
 OUT-0.050
 arrest-0.050
 Johnson-0.048
 Billy-0.046
joy-0.046
Tokenily
Token ID813
Feature activation+3.65e+00

Pos logit contributions
kin+0.021
ows+0.016
 holes+0.014
ute+0.014
utes+0.013
Neg logit contributions
 arrest-0.119
 OUT-0.118
 Johnson-0.116
joy-0.114
 Billy-0.113
Token was
Token ID373
Feature activation-5.90e-02

Pos logit contributions
kin+0.300
ows+0.284
as+0.276
a+0.275
ily+0.270
Neg logit contributions
 OUT-0.341
 arrest-0.331
 Johnson-0.324
joy-0.321
 Frankie-0.307
Token scared
Token ID12008
Feature activation-2.88e-01

Pos logit contributions
 OUT+0.006
 arrest+0.006
 Johnson+0.006
joy+0.006
 Billy+0.006
Neg logit contributions
kin-0.004
ows-0.004
as-0.004
ily-0.004
a-0.004
Token and
Token ID290
Feature activation+4.65e-01

Pos logit contributions
 OUT+0.031
 arrest+0.030
 Johnson+0.029
joy+0.028
 Frankie+0.028
Neg logit contributions
kin-0.020
ows-0.019
as-0.018
ily-0.018
 holes-0.017
Token started
Token ID2067
Feature activation+5.69e-01

Pos logit contributions
kin+0.046
ows+0.042
as+0.041
ily+0.040
ute+0.039
Neg logit contributions
 OUT-0.037
 arrest-0.037
 Johnson-0.036
joy-0.034
 Billy-0.034
Token to
Token ID284
Feature activation-3.08e-01

Pos logit contributions
 holes+0.025
ows+0.024
a+0.024
as+0.023
kin+0.022
Neg logit contributions
 OUT-0.069
istent-0.067
 arrest-0.066
ited-0.065
 Frankie-0.064
Token away
Token ID1497
Feature activation+1.10e+00

Pos logit contributions
kin+0.075
ows+0.069
as+0.066
ily+0.064
 holes+0.062
Neg logit contributions
 OUT-0.115
 arrest-0.112
 Johnson-0.110
joy-0.107
 Frankie-0.106
Token.
Token ID13
Feature activation+6.07e-01

Pos logit contributions
kin+0.063
ows+0.058
as+0.053
ily+0.052
a+0.051
Neg logit contributions
 OUT-0.132
 arrest-0.129
 Johnson-0.125
joy-0.123
istent-0.122
Token
Token ID198
Feature activation+5.61e-01

Pos logit contributions
kin+0.051
ows+0.047
as+0.045
ily+0.044
 holes+0.043
Neg logit contributions
 OUT-0.057
 arrest-0.056
 Johnson-0.055
joy-0.053
 Billy-0.052
Token
Token ID198
Feature activation+5.37e-01

Pos logit contributions
kin+0.051
ows+0.046
as+0.045
 holes+0.042
ily+0.042
Neg logit contributions
 OUT-0.049
 arrest-0.048
 Johnson-0.048
 Billy-0.046
joy-0.045
TokenL
Token ID43
Feature activation+7.76e-01

Pos logit contributions
kin+0.034
ows+0.031
as+0.029
ute+0.027
ily+0.027
Neg logit contributions
 OUT-0.062
 arrest-0.061
 Johnson-0.060
 Billy-0.058
joy-0.057
Tokenily
Token ID813
Feature activation+3.64e+00

Pos logit contributions
kin+0.024
ows+0.020
ute+0.019
utes+0.019
 holes+0.019
Neg logit contributions
 arrest-0.103
 Johnson-0.099
 OUT-0.099
joy-0.098
 Billy-0.097
Token felt
Token ID2936
Feature activation+7.70e-01

Pos logit contributions
kin+0.262
a+0.252
ows+0.251
ily+0.246
as+0.245
Neg logit contributions
 OUT-0.368
 Johnson-0.350
joy-0.350
 arrest-0.350
 Frankie-0.335
Token bad
Token ID2089
Feature activation+1.50e+00

Pos logit contributions
kin+0.068
as+0.064
ows+0.064
utes+0.058
ute+0.058
Neg logit contributions
 arrest-0.069
 OUT-0.068
 Billy-0.068
 Johnson-0.065
 returning-0.065
Token and
Token ID290
Feature activation+3.22e-01

Pos logit contributions
kin+0.137
as+0.122
ows+0.120
ute+0.114
utes+0.114
Neg logit contributions
 OUT-0.130
 Johnson-0.129
 arrest-0.128
joy-0.125
 Billy-0.125
Token wanted
Token ID2227
Feature activation+3.63e-01

Pos logit contributions
kin+0.032
ows+0.030
as+0.029
ute+0.028
a+0.027
Neg logit contributions
 OUT-0.025
 arrest-0.025
 Billy-0.025
 Johnson-0.024
 Frankie-0.023
Token to
Token ID284
Feature activation-3.66e-01

Pos logit contributions
kin+0.025
ily+0.024
ows+0.023
as+0.023
 holes+0.023
Neg logit contributions
 OUT-0.039
 arrest-0.037
istent-0.036
 Johnson-0.036
joy-0.035
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
kin+0.037
ows+0.034
as+0.033
ily+0.032
a+0.031
Neg logit contributions
 OUT-0.036
 arrest-0.035
 Johnson-0.034
joy-0.033
 Billy-0.033
Token
Token ID220
Feature activation-1.89e+00

Pos logit contributions
kin+0.015
ows+0.014
as+0.014
ily+0.013
a+0.013
Neg logit contributions
 OUT-0.016
 arrest-0.016
 Johnson-0.015
joy-0.015
 Billy-0.015
Token
Token ID198
Feature activation+3.10e-01

Pos logit contributions
 Johnson+0.151
 Billy+0.145
 OUT+0.144
 arrest+0.140
 Frankie+0.138
Neg logit contributions
kin-0.182
ows-0.160
as-0.156
 holes-0.155
ute-0.153
Token
Token ID198
Feature activation+2.96e-01

Pos logit contributions
kin+0.026
ows+0.024
as+0.023
ily+0.022
a+0.022
Neg logit contributions
 OUT-0.029
 arrest-0.029
 Johnson-0.028
joy-0.027
 Billy-0.027
TokenL
Token ID43
Feature activation+7.83e-01

Pos logit contributions
kin+0.021
ows+0.019
as+0.019
ily+0.018
a+0.017
Neg logit contributions
 OUT-0.032
 arrest-0.031
 Johnson-0.031
joy-0.030
 Billy-0.030
Tokenily
Token ID813
Feature activation+3.64e+00

Pos logit contributions
kin+0.024
ute+0.020
ows+0.019
 holes+0.018
utes+0.017
Neg logit contributions
 arrest-0.104
 Billy-0.102
 OUT-0.101
 Johnson-0.100
joy-0.098
Token felt
Token ID2936
Feature activation+6.95e-01

Pos logit contributions
kin+0.319
ows+0.299
as+0.292
a+0.286
ily+0.286
Neg logit contributions
 OUT-0.326
 arrest-0.319
 Johnson-0.309
joy-0.306
 Frankie-0.293
Token sad
Token ID6507
Feature activation+5.65e-01

Pos logit contributions
kin+0.062
ows+0.058
as+0.057
ute+0.054
a+0.053
Neg logit contributions
 OUT-0.061
 arrest-0.061
 Billy-0.059
 Johnson-0.059
joy-0.058
Token and
Token ID290
Feature activation+5.99e-02

Pos logit contributions
kin+0.057
as+0.051
ows+0.050
a+0.048
utes+0.046
Neg logit contributions
 Johnson-0.043
 OUT-0.043
 Billy-0.043
 arrest-0.042
joy-0.041
Token said
Token ID531
Feature activation-4.45e-02

Pos logit contributions
kin+0.005
ows+0.005
as+0.005
ute+0.005
ily+0.005
Neg logit contributions
 OUT-0.005
 arrest-0.005
 Johnson-0.005
 Billy-0.005
joy-0.005
Token,
Token ID11
Feature activation-7.94e-02

Pos logit contributions
 OUT+0.004
 arrest+0.004
 Johnson+0.004
joy+0.003
 Frankie+0.003
Neg logit contributions
kin-0.004
ows-0.004
as-0.004
ily-0.004
a-0.004
Token.
Token ID13
Feature activation+9.14e-01

Pos logit contributions
 OUT+0.118
 arrest+0.114
 Johnson+0.112
joy+0.110
 Frankie+0.108
Neg logit contributions
kin-0.061
ows-0.054
as-0.052
ily-0.051
 holes-0.048
Token
Token ID220
Feature activation-1.55e+00

Pos logit contributions
ows+0.064
kin+0.062
ily+0.061
 holes+0.056
ute+0.055
Neg logit contributions
 OUT-0.097
 arrest-0.095
istent-0.089
joy-0.087
 returning-0.083
Token
Token ID198
Feature activation+9.17e-01

Pos logit contributions
 Johnson+0.131
 OUT+0.130
 arrest+0.128
 Billy+0.126
 Frankie+0.122
Neg logit contributions
kin-0.141
ows-0.125
as-0.122
 holes-0.119
ute-0.118
Token
Token ID198
Feature activation+8.54e-01

Pos logit contributions
kin+0.067
ows+0.062
as+0.061
ily+0.059
a+0.058
Neg logit contributions
 OUT-0.098
 arrest-0.095
 Johnson-0.090
joy-0.089
istent-0.088
TokenL
Token ID43
Feature activation+7.98e-01

Pos logit contributions
kin+0.063
ows+0.057
as+0.056
ily+0.054
a+0.053
Neg logit contributions
 OUT-0.090
 arrest-0.089
 Johnson-0.087
joy-0.086
 Billy-0.084
Tokenily
Token ID813
Feature activation+3.64e+00

Pos logit contributions
kin+0.023
ows+0.019
 holes+0.018
ute+0.017
utes+0.016
Neg logit contributions
 arrest-0.109
 Johnson-0.105
 OUT-0.105
 Billy-0.102
joy-0.102
Token's
Token ID338
Feature activation+2.53e-01

Pos logit contributions
kin+0.256
a+0.243
ows+0.239
as+0.236
ily+0.234
Neg logit contributions
 OUT-0.389
 arrest-0.372
joy-0.368
 Johnson-0.363
istent-0.351
Token grandma
Token ID49890
Feature activation-6.91e-01

Pos logit contributions
kin+0.019
ows+0.018
as+0.017
ily+0.016
a+0.016
Neg logit contributions
 OUT-0.026
 arrest-0.026
 Johnson-0.025
joy-0.024
 Frankie-0.024
Token loved
Token ID6151
Feature activation+2.17e-01

Pos logit contributions
 arrest+0.080
 OUT+0.079
joy+0.074
istent+0.070
 Johnson+0.069
Neg logit contributions
kin-0.046
a-0.045
ily-0.043
ows-0.042
as-0.041
Token her
Token ID607
Feature activation+4.61e-01

Pos logit contributions
kin+0.021
ows+0.019
as+0.019
ily+0.018
a+0.018
Neg logit contributions
 OUT-0.018
 arrest-0.018
 Johnson-0.018
joy-0.017
 Billy-0.017
Token very
Token ID845
Feature activation+1.36e+00

Pos logit contributions
kin+0.028
ows+0.026
as+0.023
ute+0.022
a+0.022
Neg logit contributions
 OUT-0.056
 arrest-0.055
 Johnson-0.051
joy-0.051
 Frankie-0.050
Token smile
Token ID8212
Feature activation-1.02e+00

Pos logit contributions
 OUT+0.040
 arrest+0.039
 Johnson+0.038
joy+0.036
 Billy+0.036
Neg logit contributions
kin-0.034
ows-0.031
as-0.029
ily-0.028
 holes-0.028
Token.
Token ID13
Feature activation-8.18e-02

Pos logit contributions
 OUT+0.111
 arrest+0.109
 Johnson+0.108
joy+0.104
 Frankie+0.103
Neg logit contributions
kin-0.073
ows-0.063
as-0.061
ily-0.059
a-0.059
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
 OUT+0.008
 arrest+0.007
 Johnson+0.007
joy+0.007
istent+0.007
Neg logit contributions
kin-0.007
ows-0.006
as-0.006
ily-0.006
a-0.006
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
 Johnson+0.013
 arrest+0.013
 OUT+0.013
 Billy+0.013
 Frankie+0.013
Neg logit contributions
kin-0.016
ows-0.015
as-0.014
 holes-0.014
ute-0.014
TokenS
Token ID50
Feature activation-1.06e+00

Pos logit contributions
 OUT+0.017
 arrest+0.017
 Johnson+0.016
 Billy+0.016
joy+0.016
Neg logit contributions
kin-0.015
ows-0.015
as-0.013
 holes-0.013
ute-0.013
Tokenaman
Token ID10546
Feature activation-4.98e+00

Pos logit contributions
 OUT+0.091
 arrest+0.090
 Johnson+0.086
 Frankie+0.085
istent+0.084
Neg logit contributions
kin-0.097
ows-0.088
as-0.088
ily-0.087
ia-0.087
Tokentha
Token ID12898
Feature activation-2.27e+00

Pos logit contributions
 OUT+0.373
 arrest+0.352
 Johnson+0.340
istent+0.332
joy+0.331
Neg logit contributions
kin-0.524
ows-0.478
as-0.469
a-0.464
ily-0.460
Token laughed
Token ID13818
Feature activation+6.34e-01

Pos logit contributions
 OUT+0.220
 arrest+0.212
 Johnson+0.211
joy+0.204
 Frankie+0.200
Neg logit contributions
kin-0.180
ows-0.171
as-0.165
a-0.163
ily-0.161
Token,
Token ID11
Feature activation-6.91e-02

Pos logit contributions
kin+0.054
ows+0.048
as+0.048
ily+0.045
ute+0.044
Neg logit contributions
 OUT-0.060
 Johnson-0.058
 arrest-0.057
 Billy-0.057
joy-0.057
Token happy
Token ID3772
Feature activation-5.15e-01

Pos logit contributions
 OUT+0.006
 arrest+0.006
 Johnson+0.006
istent+0.006
joy+0.006
Neg logit contributions
kin-0.006
ows-0.005
as-0.005
a-0.005
ily-0.005
Token that
Token ID326
Feature activation+6.46e-01

Pos logit contributions
 OUT+0.044
 arrest+0.044
 Johnson+0.044
joy+0.043
 Billy+0.043
Neg logit contributions
kin-0.047
ows-0.045
as-0.044
ute-0.041
a-0.040
Token
Token ID26391
Feature activation-8.04e-01

Pos logit contributions
kin+0.016
ows+0.015
as+0.015
ily+0.014
 holes+0.014
Neg logit contributions
 OUT-0.015
 arrest-0.014
 Johnson-0.014
joy-0.014
 Billy-0.013
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
 OUT+0.073
 arrest+0.071
 Johnson+0.069
 Frankie+0.068
 returning+0.066
Neg logit contributions
kin-0.067
ows-0.065
as-0.063
a-0.061
ute-0.058
Token
Token ID198
Feature activation-9.07e-02

Pos logit contributions
 arrest+0.009
 OUT+0.009
 Johnson+0.008
joy+0.008
istent+0.008
Neg logit contributions
kin-0.009
ows-0.008
ily-0.008
as-0.008
a-0.008
Token
Token ID198
Feature activation-1.55e-01

Pos logit contributions
 OUT+0.008
 arrest+0.008
 Johnson+0.008
joy+0.008
 Billy+0.008
Neg logit contributions
kin-0.008
ows-0.007
as-0.007
ily-0.007
ute-0.006
TokenS
Token ID50
Feature activation-1.08e+00

Pos logit contributions
 OUT+0.015
 arrest+0.015
 Johnson+0.015
joy+0.014
 Billy+0.014
Neg logit contributions
kin-0.012
as-0.011
ows-0.011
ily-0.011
a-0.010
Tokenaman
Token ID10546
Feature activation-4.91e+00

Pos logit contributions
 arrest+0.114
 OUT+0.112
 Johnson+0.108
 Frankie+0.107
 Billy+0.105
Neg logit contributions
kin-0.077
as-0.071
ows-0.071
ily-0.069
ia-0.068
Tokentha
Token ID12898
Feature activation-2.32e+00

Pos logit contributions
 OUT+0.343
 arrest+0.332
 Johnson+0.322
joy+0.308
 Billy+0.303
Neg logit contributions
kin-0.533
ows-0.496
as-0.485
ily-0.473
a-0.470
Token was
Token ID373
Feature activation-5.77e-01

Pos logit contributions
 OUT+0.230
 arrest+0.224
 Johnson+0.220
joy+0.214
 Billy+0.208
Neg logit contributions
kin-0.180
ows-0.169
as-0.164
a-0.159
ily-0.158
Token amazed
Token ID24562
Feature activation-1.30e+00

Pos logit contributions
 OUT+0.058
 arrest+0.057
 Johnson+0.056
joy+0.054
 Billy+0.054
Neg logit contributions
kin-0.045
ows-0.041
as-0.039
ily-0.038
a-0.037
Token and
Token ID290
Feature activation+1.96e-01

Pos logit contributions
 OUT+0.120
 Johnson+0.120
joy+0.120
 Billy+0.119
 arrest+0.116
Neg logit contributions
kin-0.116
ows-0.103
as-0.096
ute-0.093
ily-0.093
Token she
Token ID673
Feature activation-9.32e-01

Pos logit contributions
kin+0.017
ows+0.016
as+0.015
ily+0.015
a+0.015
Neg logit contributions
 OUT-0.018
 arrest-0.018
 Johnson-0.017
joy-0.016
 Billy-0.016
Token before
Token ID878
Feature activation-6.89e-01

Pos logit contributions
kin+0.062
ows+0.056
as+0.055
ily+0.053
ute+0.052
Neg logit contributions
 OUT-0.080
 arrest-0.079
 Johnson-0.077
joy-0.075
 Billy-0.074
Token dinner
Token ID8073
Feature activation-4.52e-01

Pos logit contributions
 OUT+0.067
 arrest+0.063
istent+0.063
joy+0.061
 Johnson+0.061
Neg logit contributions
kin-0.054
 holes-0.047
ily-0.045
ows-0.045
a-0.042
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
 OUT+0.039
 arrest+0.038
 Johnson+0.038
 Billy+0.036
joy+0.036
Neg logit contributions
kin-0.040
ows-0.037
as-0.037
ily-0.035
ute-0.035
Token<|endoftext|>
Token ID50256
Feature activation+1.14e+00

Pos logit contributions
kin+0.020
ows+0.019
ily+0.019
as+0.018
a+0.018
Neg logit contributions
 OUT-0.023
 arrest-0.023
 Johnson-0.021
joy-0.021
istent-0.020
TokenS
Token ID50
Feature activation-9.96e-01

Pos logit contributions
kin+0.092
ows+0.084
as+0.081
ily+0.080
a+0.077
Neg logit contributions
 OUT-0.113
 arrest-0.110
 Johnson-0.106
joy-0.103
istent-0.102
Tokenaman
Token ID10546
Feature activation-4.87e+00

Pos logit contributions
 OUT+0.079
 arrest+0.076
istent+0.072
joy+0.067
 Johnson+0.067
Neg logit contributions
kin-0.099
ia-0.096
ily-0.093
a-0.093
as-0.092
Tokentha
Token ID12898
Feature activation-2.33e+00

Pos logit contributions
 OUT+0.399
istent+0.368
 arrest+0.357
joy+0.352
 Johnson+0.334
Neg logit contributions
kin-0.476
a-0.433
ows-0.424
ia-0.423
as-0.419
Token was
Token ID373
Feature activation-3.39e-01

Pos logit contributions
 OUT+0.294
joy+0.276
 arrest+0.273
istent+0.272
 Johnson+0.271
Neg logit contributions
kin-0.114
a-0.113
ows-0.109
as-0.108
ily-0.108
Token a
Token ID257
Feature activation-4.82e-01

Pos logit contributions
 OUT+0.029
 arrest+0.029
 Johnson+0.028
joy+0.027
 Billy+0.027
Neg logit contributions
kin-0.031
ows-0.029
as-0.028
ily-0.026
ute-0.026
Token lazy
Token ID16931
Feature activation+5.42e-01

Pos logit contributions
 OUT+0.046
 arrest+0.045
 Johnson+0.045
joy+0.044
 Billy+0.043
Neg logit contributions
kin-0.039
ows-0.038
as-0.035
ily-0.034
 holes-0.033
Token girl
Token ID2576
Feature activation-3.95e-01

Pos logit contributions
kin+0.042
ows+0.039
as+0.038
ily+0.035
ute+0.035
Neg logit contributions
 OUT-0.054
 Johnson-0.053
 arrest-0.052
 Billy-0.051
joy-0.051
Token.
Token ID13
Feature activation+4.46e-01

Pos logit contributions
kin+0.039
ows+0.035
as+0.034
ily+0.033
a+0.032
Neg logit contributions
 OUT-0.048
 arrest-0.047
 Johnson-0.046
joy-0.045
 Billy-0.044
Token
Token ID220
Feature activation-1.99e+00

Pos logit contributions
kin+0.037
ows+0.035
as+0.034
ily+0.034
a+0.032
Neg logit contributions
 OUT-0.041
 arrest-0.040
 Johnson-0.038
joy-0.038
istent-0.037
Token
Token ID198
Feature activation+2.83e-01

Pos logit contributions
 OUT+0.184
 arrest+0.180
 Johnson+0.178
joy+0.171
 Billy+0.170
Neg logit contributions
kin-0.170
ows-0.154
as-0.150
ily-0.144
ute-0.142
Token
Token ID198
Feature activation+2.12e-01

Pos logit contributions
kin+0.025
ows+0.022
as+0.022
ily+0.021
 holes+0.021
Neg logit contributions
 OUT-0.026
 arrest-0.025
 Johnson-0.025
joy-0.024
 Billy-0.024
TokenExc
Token ID40127
Feature activation+3.63e-01

Pos logit contributions
kin+0.017
ows+0.015
as+0.014
 holes+0.014
ily+0.014
Neg logit contributions
 OUT-0.021
 arrest-0.021
 Johnson-0.021
joy-0.020
 Billy-0.020
Tokenited
Token ID863
Feature activation-4.85e+00

Pos logit contributions
kin+0.047
a+0.045
as+0.044
ily+0.043
ila+0.043
Neg logit contributions
 OUT-0.015
 Johnson-0.015
 arrest-0.015
 Billy-0.014
 Frankie-0.013
Token,
Token ID11
Feature activation-2.12e-02

Pos logit contributions
 OUT+0.480
 arrest+0.471
 Johnson+0.464
joy+0.444
istent+0.435
Neg logit contributions
kin-0.374
ows-0.347
as-0.336
ily-0.333
a-0.321
Token Lily
Token ID20037
Feature activation+4.53e-02

Pos logit contributions
 OUT+0.002
 arrest+0.002
istent+0.002
 Johnson+0.002
joy+0.002
Neg logit contributions
kin-0.002
ows-0.002
ily-0.002
a-0.002
as-0.002
Token followed
Token ID3940
Feature activation+2.40e-01

Pos logit contributions
kin+0.004
ows+0.003
as+0.003
a+0.003
ily+0.003
Neg logit contributions
 OUT-0.004
 arrest-0.004
 Johnson-0.004
joy-0.004
 Frankie-0.004
Token the
Token ID262
Feature activation-1.74e-01

Pos logit contributions
kin+0.017
ily+0.015
 holes+0.015
ows+0.015
ute+0.014
Neg logit contributions
 OUT-0.025
istent-0.023
 Johnson-0.023
 arrest-0.023
joy-0.023
Token instructions
Token ID7729
Feature activation+5.52e-01

Pos logit contributions
 OUT+0.018
 arrest+0.018
 Johnson+0.018
 Billy+0.017
joy+0.017
Neg logit contributions
kin-0.013
ows-0.012
as-0.012
ily-0.011
ute-0.011
Token sky
Token ID6766
Feature activation-2.99e-01

Pos logit contributions
 arrest+0.031
 Johnson+0.030
 OUT+0.030
 Billy+0.029
 Smith+0.028
Neg logit contributions
kin-0.028
ows-0.026
as-0.026
ute-0.023
utes-0.023
Token.
Token ID13
Feature activation+1.66e-01

Pos logit contributions
 OUT+0.031
 arrest+0.030
 Johnson+0.030
joy+0.029
 Billy+0.029
Neg logit contributions
kin-0.022
ows-0.020
as-0.019
ily-0.018
ute-0.018
Token
Token ID198
Feature activation+2.48e-01

Pos logit contributions
kin+0.014
ows+0.013
as+0.013
ily+0.013
a+0.012
Neg logit contributions
 OUT-0.015
 arrest-0.015
 Johnson-0.014
joy-0.014
 Frankie-0.014
Token
Token ID198
Feature activation+1.67e-01

Pos logit contributions
kin+0.022
ows+0.020
as+0.019
 holes+0.019
ute+0.018
Neg logit contributions
 OUT-0.022
 arrest-0.022
 Johnson-0.022
 Billy-0.021
joy-0.021
TokenExc
Token ID40127
Feature activation+4.00e-01

Pos logit contributions
kin+0.013
ows+0.012
as+0.011
ily+0.011
a+0.011
Neg logit contributions
 OUT-0.017
 arrest-0.017
 Johnson-0.016
joy-0.016
 Billy-0.016
Tokenited
Token ID863
Feature activation-4.81e+00

Pos logit contributions
kin+0.046
a+0.045
as+0.044
ila+0.044
OK+0.043
Neg logit contributions
 OUT-0.020
 arrest-0.019
 Frankie-0.019
 Billy-0.018
 Johnson-0.018
Tokenly
Token ID306
Feature activation+1.26e+00

Pos logit contributions
 OUT+0.474
 arrest+0.464
 Johnson+0.458
joy+0.435
istent+0.434
Neg logit contributions
kin-0.369
ows-0.344
as-0.333
ily-0.332
 holes-0.320
Token,
Token ID11
Feature activation+5.47e-02

Pos logit contributions
kin+0.090
a+0.082
ily+0.081
ows+0.078
as+0.076
Neg logit contributions
 OUT-0.125
arse-0.123
 Johnson-0.122
istent-0.121
 arrest-0.119
Token the
Token ID262
Feature activation-1.75e-01

Pos logit contributions
kin+0.005
ily+0.004
ows+0.004
a+0.004
as+0.004
Neg logit contributions
 OUT-0.005
 arrest-0.005
 Johnson-0.005
istent-0.005
joy-0.005
Token two
Token ID734
Feature activation-7.37e-01

Pos logit contributions
 arrest+0.015
 Johnson+0.015
 OUT+0.015
joy+0.015
 Billy+0.015
Neg logit contributions
ows-0.015
kin-0.014
as-0.014
ute-0.013
a-0.013
Token girls
Token ID4813
Feature activation-3.83e-01

Pos logit contributions
 OUT+0.076
 arrest+0.075
 Johnson+0.074
joy+0.071
 Billy+0.071
Neg logit contributions
kin-0.055
ows-0.050
as-0.048
ily-0.046
ute-0.045
Token it
Token ID340
Feature activation+3.56e-01

Pos logit contributions
 OUT+0.064
 Billy+0.063
 arrest+0.062
joy+0.059
 Johnson+0.058
Neg logit contributions
kin-0.066
ows-0.065
as-0.064
a-0.057
auc-0.056
Token?"
Token ID1701
Feature activation+2.91e-01

Pos logit contributions
kin+0.031
ows+0.028
as+0.028
ily+0.026
a+0.026
Neg logit contributions
 OUT-0.031
 Johnson-0.030
 arrest-0.030
 Billy-0.029
 returning-0.028
Token
Token ID198
Feature activation+3.12e-01

Pos logit contributions
kin+0.023
ows+0.022
ily+0.021
as+0.021
a+0.020
Neg logit contributions
 OUT-0.028
 arrest-0.027
 Johnson-0.026
istent-0.025
joy-0.025
Token
Token ID198
Feature activation+2.51e-01

Pos logit contributions
kin+0.028
ows+0.025
as+0.024
 holes+0.023
ily+0.023
Neg logit contributions
 OUT-0.028
 arrest-0.028
 Johnson-0.028
joy-0.026
 Billy-0.026
TokenExc
Token ID40127
Feature activation+4.00e-01

Pos logit contributions
kin+0.020
ows+0.018
as+0.017
ily+0.016
 holes+0.016
Neg logit contributions
 OUT-0.025
 arrest-0.025
 Johnson-0.025
joy-0.024
 Billy-0.024
Tokenited
Token ID863
Feature activation-4.80e+00

Pos logit contributions
kin+0.053
a+0.050
as+0.049
ows+0.049
ily+0.049
Neg logit contributions
 OUT-0.017
 arrest-0.016
 Johnson-0.016
 Billy-0.015
 Frankie-0.015
Token,
Token ID11
Feature activation+2.70e-02

Pos logit contributions
 OUT+0.464
 arrest+0.455
 Johnson+0.447
joy+0.430
 Billy+0.424
Neg logit contributions
kin-0.394
ows-0.361
as-0.350
ily-0.338
a-0.331
Token Sammy
Token ID44067
Feature activation-6.06e-01

Pos logit contributions
kin+0.002
ily+0.002
ows+0.002
a+0.002
as+0.002
Neg logit contributions
 OUT-0.003
 arrest-0.003
istent-0.002
 Johnson-0.002
joy-0.002
Token eagerly
Token ID30130
Feature activation-1.38e-01

Pos logit contributions
 OUT+0.061
 arrest+0.060
 Johnson+0.059
joy+0.058
 Frankie+0.055
Neg logit contributions
kin-0.046
ows-0.043
as-0.041
a-0.040
ily-0.040
Token agreed
Token ID4987
Feature activation+4.68e-01

Pos logit contributions
 OUT+0.013
 arrest+0.012
 Johnson+0.012
joy+0.012
 Frankie+0.011
Neg logit contributions
kin-0.012
ows-0.011
as-0.011
ily-0.010
a-0.010
Token,
Token ID11
Feature activation+7.46e-02

Pos logit contributions
kin+0.033
ows+0.030
as+0.028
ily+0.028
a+0.027
Neg logit contributions
 OUT-0.051
 arrest-0.050
 Johnson-0.049
joy-0.047
 Frankie-0.046
Token together
Token ID1978
Feature activation-1.76e-01

Pos logit contributions
kin+0.076
as+0.067
ows+0.067
ily+0.066
ute+0.065
Neg logit contributions
 arrest-0.073
 Johnson-0.071
 OUT-0.070
 Billy-0.068
 Smith-0.066
Token!"
Token ID2474
Feature activation-5.56e-02

Pos logit contributions
 OUT+0.016
 arrest+0.016
 Johnson+0.016
joy+0.015
 Billy+0.015
Neg logit contributions
kin-0.015
ows-0.013
as-0.013
ily-0.012
ute-0.012
Token
Token ID198
Feature activation+4.51e-01

Pos logit contributions
 OUT+0.005
 arrest+0.005
joy+0.005
 Johnson+0.005
istent+0.004
Neg logit contributions
kin-0.005
ows-0.005
as-0.004
ily-0.004
a-0.004
Token
Token ID198
Feature activation+3.59e-01

Pos logit contributions
kin+0.041
ows+0.037
as+0.036
 holes+0.034
ily+0.034
Neg logit contributions
 OUT-0.040
 Johnson-0.039
 arrest-0.039
 Billy-0.038
 Frankie-0.037
TokenExc
Token ID40127
Feature activation+4.82e-01

Pos logit contributions
kin+0.027
ows+0.025
as+0.023
ily+0.022
 holes+0.022
Neg logit contributions
 OUT-0.037
 arrest-0.037
 Johnson-0.036
 Billy-0.035
 Frankie-0.034
Tokenited
Token ID863
Feature activation-4.78e+00

Pos logit contributions
kin+0.066
as+0.062
ows+0.061
a+0.061
ily+0.061
Neg logit contributions
 OUT-0.019
 arrest-0.018
 Johnson-0.017
 Billy-0.016
 Frankie-0.016
Tokenly
Token ID306
Feature activation+1.27e+00

Pos logit contributions
 OUT+0.482
 arrest+0.472
 Johnson+0.463
joy+0.446
istent+0.437
Neg logit contributions
kin-0.361
ows-0.338
as-0.324
ily-0.319
 holes-0.308
Token,
Token ID11
Feature activation+5.31e-02

Pos logit contributions
kin+0.084
ows+0.078
ily+0.074
a+0.071
 holes+0.068
Neg logit contributions
 OUT-0.131
arse-0.129
 Johnson-0.127
joy-0.127
istent-0.124
Token Sally
Token ID25737
Feature activation-1.66e+00

Pos logit contributions
kin+0.005
ily+0.004
 holes+0.004
 Lia+0.004
ows+0.004
Neg logit contributions
 OUT-0.004
istent-0.004
 arrest-0.004
arse-0.004
joy-0.004
Token and
Token ID290
Feature activation+3.31e-01

Pos logit contributions
 OUT+0.167
 arrest+0.162
 Johnson+0.160
joy+0.159
istent+0.151
Neg logit contributions
kin-0.128
ows-0.123
as-0.118
a-0.113
ily-0.112
Token Tim
Token ID5045
Feature activation-1.06e+00

Pos logit contributions
kin+0.034
ily+0.031
ows+0.031
as+0.030
a+0.030
Neg logit contributions
 OUT-0.025
 arrest-0.023
istent-0.023
joy-0.022
 Johnson-0.022
Token distance
Token ID5253
Feature activation-1.57e+00

Pos logit contributions
 arrest+0.028
 Johnson+0.026
 OUT+0.025
 Billy+0.025
joy+0.025
Neg logit contributions
kin-0.029
ows-0.029
as-0.028
ute-0.025
utes-0.025
Token.
Token ID13
Feature activation+7.23e-02

Pos logit contributions
 OUT+0.176
 arrest+0.173
 Johnson+0.168
joy+0.165
 Billy+0.162
Neg logit contributions
kin-0.104
ows-0.094
as-0.090
ily-0.087
 holes-0.084
Token
Token ID198
Feature activation+4.05e-02

Pos logit contributions
kin+0.006
ows+0.006
ily+0.006
as+0.005
 holes+0.005
Neg logit contributions
 arrest-0.007
 OUT-0.007
 Johnson-0.006
joy-0.006
istent-0.006
Token
Token ID198
Feature activation+9.78e-03

Pos logit contributions
kin+0.004
ows+0.003
as+0.003
 holes+0.003
ute+0.003
Neg logit contributions
 OUT-0.004
 arrest-0.004
 Johnson-0.004
joy-0.003
 Billy-0.003
TokenExc
Token ID40127
Feature activation+4.57e-01

Pos logit contributions
kin+0.001
ows+0.001
as+0.001
ily+0.001
 holes+0.001
Neg logit contributions
 OUT-0.001
 arrest-0.001
 Johnson-0.001
joy-0.001
 Billy-0.001
Tokenited
Token ID863
Feature activation-4.76e+00

Pos logit contributions
kin+0.056
a+0.053
as+0.053
ila+0.053
ily+0.053
Neg logit contributions
 OUT-0.022
 arrest-0.021
 Johnson-0.020
istent-0.019
 Billy-0.019
Tokenly
Token ID306
Feature activation+1.28e+00

Pos logit contributions
 OUT+0.465
 arrest+0.456
 Johnson+0.448
istent+0.430
joy+0.427
Neg logit contributions
kin-0.363
ows-0.341
ily-0.334
as-0.329
 holes-0.321
Token,
Token ID11
Feature activation+5.73e-02

Pos logit contributions
kin+0.087
ily+0.081
a+0.080
ows+0.077
ia+0.074
Neg logit contributions
istent-0.129
 OUT-0.129
arse-0.127
 Johnson-0.124
joy-0.123
Token she
Token ID673
Feature activation-8.23e-01

Pos logit contributions
kin+0.005
ily+0.005
ows+0.005
a+0.004
 holes+0.004
Neg logit contributions
 OUT-0.005
 arrest-0.005
istent-0.005
 Johnson-0.005
joy-0.004
Token ran
Token ID4966
Feature activation+8.41e-01

Pos logit contributions
 OUT+0.062
 arrest+0.061
 Billy+0.059
 Johnson+0.058
 Frankie+0.056
Neg logit contributions
kin-0.087
ows-0.079
as-0.075
ute-0.075
ily-0.074
Token to
Token ID284
Feature activation-5.84e-01

Pos logit contributions
kin+0.070
ows+0.063
as+0.061
ily+0.058
ute+0.057
Neg logit contributions
 OUT-0.081
 arrest-0.080
 Johnson-0.079
joy-0.076
 Billy-0.075
Token on
Token ID319
Feature activation+2.34e-01

Pos logit contributions
 OUT+0.181
 arrest+0.177
 Johnson+0.176
 Billy+0.168
 returning+0.166
Neg logit contributions
kin-0.140
as-0.123
ows-0.122
ily-0.116
a-0.113
Token a
Token ID257
Feature activation-3.56e-01

Pos logit contributions
kin+0.018
ows+0.016
as+0.015
ily+0.015
 holes+0.015
Neg logit contributions
 OUT-0.024
 arrest-0.023
 Johnson-0.023
joy-0.022
 Billy-0.022
Token tree
Token ID5509
Feature activation-1.27e+00

Pos logit contributions
 OUT+0.032
 Johnson+0.031
 arrest+0.031
 Frankie+0.029
 Billy+0.029
Neg logit contributions
kin-0.032
ows-0.030
as-0.029
ily-0.028
ila-0.026
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
 OUT+0.144
 arrest+0.141
 Johnson+0.139
joy+0.136
 Billy+0.134
Neg logit contributions
kin-0.083
ows-0.075
as-0.071
ily-0.067
 holes-0.067
Token Exc
Token ID25268
Feature activation-2.03e-01

Pos logit contributions
 arrest+0.011
 OUT+0.011
 Johnson+0.010
joy+0.010
istent+0.010
Neg logit contributions
kin-0.009
ows-0.009
 holes-0.009
ily-0.009
ute-0.008
Tokenited
Token ID863
Feature activation-4.76e+00

Pos logit contributions
 OUT+0.005
 arrest+0.004
 Johnson+0.004
joy+0.003
 Billy+0.003
Neg logit contributions
kin-0.031
ows-0.030
as-0.029
ily-0.029
ute-0.029
Tokenly
Token ID306
Feature activation+1.24e+00

Pos logit contributions
 OUT+0.461
 arrest+0.456
 Johnson+0.452
istent+0.426
joy+0.425
Neg logit contributions
kin-0.359
ows-0.342
ily-0.328
as-0.326
 holes-0.325
Token,
Token ID11
Feature activation-1.99e-01

Pos logit contributions
kin+0.074
a+0.070
ily+0.070
 holes+0.066
ia+0.062
Neg logit contributions
istent-0.133
 Johnson-0.130
 OUT-0.128
arse-0.128
joy-0.124
Token the
Token ID262
Feature activation-9.05e-02

Pos logit contributions
 OUT+0.022
istent+0.022
 arrest+0.022
 Johnson+0.021
ited+0.021
Neg logit contributions
kin-0.012
 holes-0.011
 Lia-0.010
ily-0.010
a-0.009
Token bird
Token ID6512
Feature activation-2.84e-01

Pos logit contributions
 arrest+0.008
 OUT+0.008
 Johnson+0.008
 Frankie+0.007
 Billy+0.007
Neg logit contributions
kin-0.008
ows-0.008
as-0.008
ily-0.007
ute-0.007
Token flew
Token ID13112
Feature activation+4.91e-01

Pos logit contributions
 OUT+0.030
 Johnson+0.029
 arrest+0.029
joy+0.029
istent+0.027
Neg logit contributions
kin-0.020
ows-0.019
as-0.019
a-0.018
ily-0.018
Token in
Token ID287
Feature activation+1.39e+00

Pos logit contributions
 Johnson+0.217
 OUT+0.217
 arrest+0.213
 Billy+0.209
joy+0.204
Neg logit contributions
kin-0.166
ows-0.151
as-0.148
ily-0.140
 holes-0.139
Token his
Token ID465
Feature activation+1.82e-01

Pos logit contributions
kin+0.109
 holes+0.093
ily+0.093
ows+0.090
as+0.089
Neg logit contributions
 OUT-0.144
istent-0.133
 arrest-0.132
 Johnson-0.130
joy-0.125
Token raft
Token ID31812
Feature activation+1.18e-01

Pos logit contributions
kin+0.015
ows+0.014
as+0.014
ily+0.013
a+0.013
Neg logit contributions
 OUT-0.017
 arrest-0.017
 Johnson-0.017
joy-0.016
 Billy-0.016
Token.
Token ID13
Feature activation+5.70e-01

Pos logit contributions
kin+0.009
ows+0.008
as+0.008
ily+0.007
a+0.007
Neg logit contributions
 OUT-0.012
 arrest-0.012
 Johnson-0.012
 Billy-0.012
joy-0.011
Token Exc
Token ID25268
Feature activation-1.88e-01

Pos logit contributions
kin+0.051
ows+0.046
as+0.046
ily+0.043
a+0.043
Neg logit contributions
 OUT-0.051
 arrest-0.050
 Johnson-0.049
joy-0.047
 Billy-0.047
Tokenited
Token ID863
Feature activation-4.75e+00

Pos logit contributions
 OUT+0.003
 arrest+0.003
 Johnson+0.002
joy+0.002
 Billy+0.002
Neg logit contributions
kin-0.030
ows-0.029
as-0.028
ily-0.027
ute-0.027
Token,
Token ID11
Feature activation-1.10e-02

Pos logit contributions
 OUT+0.500
 arrest+0.490
 Johnson+0.485
istent+0.460
joy+0.459
Neg logit contributions
kin-0.330
ows-0.315
ily-0.300
as-0.296
 holes-0.293
Token Lily
Token ID20037
Feature activation+3.27e-01

Pos logit contributions
 OUT+0.001
istent+0.001
 arrest+0.001
 Johnson+0.001
joy+0.001
Neg logit contributions
kin-0.001
ily-0.001
 holes-0.001
ows-0.001
 Lia-0.001
Token jumped
Token ID11687
Feature activation+1.51e+00

Pos logit contributions
kin+0.025
as+0.023
ows+0.023
a+0.023
ily+0.021
Neg logit contributions
 OUT-0.033
 Johnson-0.032
 arrest-0.031
joy-0.031
 Frankie-0.030
Token in
Token ID287
Feature activation+1.39e+00

Pos logit contributions
kin+0.128
as+0.115
ows+0.114
ily+0.106
a+0.105
Neg logit contributions
 OUT-0.145
 arrest-0.141
 Johnson-0.139
 Billy-0.136
joy-0.136
Token the
Token ID262
Feature activation-8.39e-02

Pos logit contributions
kin+0.098
 holes+0.087
ows+0.085
ily+0.085
as+0.082
Neg logit contributions
 OUT-0.147
 arrest-0.139
 Johnson-0.138
istent-0.137
 Frankie-0.133
Token inside
Token ID2641
Feature activation-1.20e+00

Pos logit contributions
 OUT+0.120
 arrest+0.117
 Johnson+0.117
 Billy+0.113
 Frankie+0.110
Neg logit contributions
kin-0.111
ows-0.101
as-0.100
ute-0.096
ily-0.095
Token."
Token ID526
Feature activation-6.74e-01

Pos logit contributions
 OUT+0.128
 arrest+0.125
 Johnson+0.121
joy+0.119
istent+0.115
Neg logit contributions
kin-0.088
ows-0.079
as-0.076
ily-0.073
 holes-0.072
Token
Token ID198
Feature activation+3.05e-01

Pos logit contributions
 OUT+0.071
 arrest+0.069
joy+0.064
 Johnson+0.063
istent+0.063
Neg logit contributions
kin-0.049
ows-0.046
as-0.043
ily-0.043
a-0.042
Token
Token ID198
Feature activation+2.46e-01

Pos logit contributions
kin+0.025
ows+0.023
as+0.023
ily+0.022
a+0.021
Neg logit contributions
 OUT-0.029
 arrest-0.029
 Johnson-0.028
joy-0.027
 Billy-0.027
TokenExc
Token ID40127
Feature activation+5.51e-01

Pos logit contributions
kin+0.018
ows+0.016
as+0.016
ily+0.015
a+0.015
Neg logit contributions
 OUT-0.026
 arrest-0.025
 Johnson-0.025
joy-0.024
 Billy-0.024
Tokenited
Token ID863
Feature activation-4.75e+00

Pos logit contributions
kin+0.075
a+0.071
ows+0.071
as+0.070
ily+0.070
Neg logit contributions
 OUT-0.021
 arrest-0.021
 Billy-0.018
 Johnson-0.018
joy-0.017
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
 OUT+0.471
 arrest+0.469
 Johnson+0.449
joy+0.437
istent+0.427
Neg logit contributions
kin-0.358
ows-0.343
ily-0.328
as-0.322
ia-0.313
Token Lucy
Token ID22162
Feature activation-1.19e+00

Pos logit contributions
 OUT+0.013
 arrest+0.012
joy+0.011
istent+0.011
 Johnson+0.010
Neg logit contributions
kin-0.016
ows-0.015
a-0.014
ily-0.014
as-0.014
Token got
Token ID1392
Feature activation+6.71e-01

Pos logit contributions
 OUT+0.118
 arrest+0.115
 Johnson+0.113
joy+0.111
 Billy+0.107
Neg logit contributions
kin-0.096
ows-0.089
as-0.087
a-0.084
ily-0.083
Token some
Token ID617
Feature activation-2.24e-01

Pos logit contributions
kin+0.057
ows+0.053
as+0.051
ily+0.049
ute+0.048
Neg logit contributions
 OUT-0.063
 arrest-0.062
 Johnson-0.061
joy-0.058
 Billy-0.058
Token blankets
Token ID34794
Feature activation+3.37e-01

Pos logit contributions
 OUT+0.019
 Johnson+0.019
 arrest+0.019
 Billy+0.018
 Frankie+0.018
Neg logit contributions
kin-0.020
as-0.018
ows-0.017
ute-0.017
ily-0.017
Token.
Token ID13
Feature activation+6.28e-01

Pos logit contributions
 OUT+0.175
 arrest+0.172
 Johnson+0.169
 Billy+0.163
joy+0.162
Neg logit contributions
kin-0.139
ows-0.125
as-0.120
ute-0.115
ily-0.115
Token
Token ID220
Feature activation-1.68e+00

Pos logit contributions
kin+0.057
ows+0.055
 holes+0.053
ily+0.053
ute+0.052
Neg logit contributions
 OUT-0.051
 arrest-0.050
 Johnson-0.046
joy-0.045
istent-0.044
Token
Token ID198
Feature activation+6.73e-01

Pos logit contributions
 OUT+0.167
 arrest+0.164
 Johnson+0.158
joy+0.154
 Billy+0.150
Neg logit contributions
kin-0.131
ows-0.123
as-0.119
ily-0.114
a-0.111
Token
Token ID198
Feature activation+6.10e-01

Pos logit contributions
kin+0.051
ows+0.047
as+0.046
ily+0.045
a+0.044
Neg logit contributions
 OUT-0.068
 arrest-0.066
 Johnson-0.065
joy-0.063
 Billy-0.062
TokenExc
Token ID40127
Feature activation+6.25e-01

Pos logit contributions
kin+0.048
as+0.043
ows+0.042
a+0.041
ily+0.041
Neg logit contributions
 OUT-0.061
 arrest-0.059
 Johnson-0.058
joy-0.057
 Billy-0.056
Tokenited
Token ID863
Feature activation-4.75e+00

Pos logit contributions
kin+0.077
a+0.074
as+0.071
ily+0.071
ila+0.070
Neg logit contributions
 OUT-0.030
 arrest-0.028
 Johnson-0.027
 Billy-0.026
 Frankie-0.024
Tokenly
Token ID306
Feature activation+1.31e+00

Pos logit contributions
 OUT+0.493
 arrest+0.484
 Johnson+0.475
joy+0.453
istent+0.452
Neg logit contributions
kin-0.332
ows-0.312
ily-0.299
as-0.299
 holes-0.293
Token,
Token ID11
Feature activation-1.09e-01

Pos logit contributions
kin+0.097
a+0.086
ows+0.085
ily+0.084
as+0.081
Neg logit contributions
 OUT-0.125
 Johnson-0.123
arse-0.121
joy-0.117
 arrest-0.117
Token Ark
Token ID9128
Feature activation+2.35e-01

Pos logit contributions
 OUT+0.009
 arrest+0.008
istent+0.008
 Johnson+0.008
joy+0.008
Neg logit contributions
kin-0.011
 holes-0.009
a-0.009
ily-0.009
ows-0.009
Tokenie
Token ID494
Feature activation+3.51e-01

Pos logit contributions
kin+0.027
ows+0.026
as+0.025
ute+0.024
 holes+0.024
Neg logit contributions
 OUT-0.014
 arrest-0.014
 Johnson-0.014
 Billy-0.013
 Frankie-0.013
Token grabbed
Token ID13176
Feature activation+5.04e-01

Pos logit contributions
kin+0.030
ows+0.028
as+0.028
a+0.027
ily+0.026
Neg logit contributions
 OUT-0.032
 arrest-0.031
 Johnson-0.031
joy-0.030
 Frankie-0.029
Token it
Token ID340
Feature activation+5.41e-01

Pos logit contributions
 OUT+0.016
 arrest+0.016
 Johnson+0.016
 Billy+0.015
joy+0.015
Neg logit contributions
kin-0.010
ows-0.009
as-0.009
ute-0.008
ily-0.008
Token was
Token ID373
Feature activation-2.98e-01

Pos logit contributions
kin+0.049
ows+0.044
as+0.043
ute+0.043
utes+0.041
Neg logit contributions
 OUT-0.047
 arrest-0.046
 Johnson-0.045
 Billy-0.044
 Frankie-0.043
Token perfect
Token ID2818
Feature activation-4.00e-01

Pos logit contributions
 OUT+0.030
 Johnson+0.029
 arrest+0.029
 Billy+0.028
 Frankie+0.028
Neg logit contributions
kin-0.023
ows-0.021
as-0.020
ute-0.020
ily-0.019
Token.
Token ID13
Feature activation+3.91e-02

Pos logit contributions
 OUT+0.039
 arrest+0.038
 Johnson+0.038
joy+0.037
 Billy+0.036
Neg logit contributions
kin-0.032
ows-0.029
as-0.029
ily-0.027
ute-0.027
Token Exc
Token ID25268
Feature activation-2.14e-01

Pos logit contributions
kin+0.004
ows+0.004
as+0.003
ily+0.003
 holes+0.003
Neg logit contributions
 OUT-0.003
 arrest-0.003
 Johnson-0.003
joy-0.003
 Billy-0.003
Tokenited
Token ID863
Feature activation-4.74e+00

Pos logit contributions
 OUT+0.005
 arrest+0.005
 Johnson+0.005
joy+0.004
 Billy+0.004
Neg logit contributions
kin-0.033
ows-0.031
as-0.031
ily-0.030
a-0.030
Token,
Token ID11
Feature activation-9.63e-02

Pos logit contributions
 OUT+0.474
 arrest+0.469
 Johnson+0.459
istent+0.435
joy+0.432
Neg logit contributions
kin-0.353
ows-0.336
ily-0.323
as-0.321
 holes-0.316
Token she
Token ID673
Feature activation-7.51e-01

Pos logit contributions
 OUT+0.009
 arrest+0.009
 Johnson+0.009
istent+0.009
joy+0.008
Neg logit contributions
kin-0.008
ily-0.007
 holes-0.007
ows-0.007
a-0.007
Token ran
Token ID4966
Feature activation+8.95e-01

Pos logit contributions
 OUT+0.062
 arrest+0.061
 Johnson+0.059
 Billy+0.057
joy+0.057
Neg logit contributions
kin-0.072
ows-0.066
as-0.064
ute-0.062
ily-0.062
Token to
Token ID284
Feature activation-5.32e-01

Pos logit contributions
kin+0.065
ows+0.060
as+0.057
ily+0.056
 holes+0.055
Neg logit contributions
 OUT-0.094
 arrest-0.091
 Johnson-0.090
istent-0.087
joy-0.086
Token get
Token ID651
Feature activation-8.83e-01

Pos logit contributions
 OUT+0.059
istent+0.058
 Johnson+0.055
joy+0.055
ited+0.053
Neg logit contributions
ily-0.032
kin-0.029
 holes-0.029
 shapes-0.028
ows-0.028
Token in
Token ID287
Feature activation+1.48e+00

Pos logit contributions
 Johnson+0.118
 OUT+0.115
 arrest+0.113
 Billy+0.112
 Frankie+0.109
Neg logit contributions
kin-0.094
as-0.086
ows-0.085
ute-0.083
ily-0.082
Token the
Token ID262
Feature activation-2.17e-03

Pos logit contributions
kin+0.134
ows+0.120
as+0.118
ily+0.117
 holes+0.114
Neg logit contributions
 OUT-0.132
 arrest-0.128
 Johnson-0.123
joy-0.121
istent-0.118
Token freezer
Token ID30967
Feature activation-2.32e-01

Pos logit contributions
 OUT+0.000
 Johnson+0.000
 arrest+0.000
joy+0.000
 Billy+0.000
Neg logit contributions
kin-0.000
ows-0.000
as-0.000
ute-0.000
a-0.000
Token.
Token ID13
Feature activation+6.02e-02

Pos logit contributions
 OUT+0.022
 Johnson+0.022
 arrest+0.022
 Billy+0.021
joy+0.021
Neg logit contributions
kin-0.018
ows-0.016
as-0.016
ily-0.016
ute-0.015
Token Exc
Token ID25268
Feature activation-1.10e-01

Pos logit contributions
kin+0.005
ows+0.005
ily+0.005
as+0.005
 holes+0.005
Neg logit contributions
 OUT-0.005
 arrest-0.005
 Johnson-0.005
joy-0.005
 Frankie-0.005
Tokenited
Token ID863
Feature activation-4.74e+00

Pos logit contributions
 OUT+0.004
 arrest+0.004
 Johnson+0.003
 Frankie+0.003
 Billy+0.003
Neg logit contributions
kin-0.016
ows-0.015
as-0.015
ily-0.014
a-0.014
Token,
Token ID11
Feature activation-8.93e-02

Pos logit contributions
 OUT+0.502
 arrest+0.496
 Johnson+0.485
istent+0.464
joy+0.464
Neg logit contributions
kin-0.317
ows-0.306
ily-0.297
as-0.289
 holes-0.283
Token she
Token ID673
Feature activation-6.23e-01

Pos logit contributions
 OUT+0.006
 arrest+0.006
istent+0.005
joy+0.005
 Johnson+0.005
Neg logit contributions
kin-0.010
ily-0.009
ows-0.009
 holes-0.009
 shapes-0.009
Token opened
Token ID4721
Feature activation+7.70e-01

Pos logit contributions
 OUT+0.054
 arrest+0.053
 Johnson+0.052
joy+0.050
 Billy+0.049
Neg logit contributions
kin-0.057
ows-0.053
as-0.051
ily-0.050
a-0.049
Token the
Token ID262
Feature activation-1.43e-02

Pos logit contributions
kin+0.049
 holes+0.047
ily+0.045
ows+0.045
a+0.043
Neg logit contributions
 OUT-0.085
istent-0.082
 arrest-0.080
 Johnson-0.077
joy-0.075
Token freezer
Token ID30967
Feature activation-2.10e-01

Pos logit contributions
 OUT+0.001
 arrest+0.001
 Johnson+0.001
joy+0.001
 Billy+0.001
Neg logit contributions
kin-0.001
ows-0.001
as-0.001
ily-0.001
ute-0.001
Token and
Token ID290
Feature activation+2.55e-01

Pos logit contributions
kin+0.111
ows+0.091
as+0.088
ily+0.087
ute+0.086
Neg logit contributions
 OUT-0.164
 arrest-0.163
joy-0.161
 Johnson-0.156
 Billy-0.154
Token unknown
Token ID6439
Feature activation+7.05e-01

Pos logit contributions
kin+0.019
ows+0.017
as+0.016
ute+0.016
ily+0.015
Neg logit contributions
 OUT-0.027
 arrest-0.026
joy-0.026
 Johnson-0.026
 Billy-0.026
Token things
Token ID1243
Feature activation+7.73e-01

Pos logit contributions
kin+0.056
ows+0.045
ily+0.044
as+0.043
ute+0.043
Neg logit contributions
 arrest-0.073
joy-0.073
 OUT-0.072
 Johnson-0.070
 Billy-0.069
Token.
Token ID13
Feature activation+2.29e-01

Pos logit contributions
kin+0.064
ows+0.055
as+0.055
ute+0.053
ily+0.053
Neg logit contributions
 OUT-0.074
 arrest-0.073
 Johnson-0.072
 Billy-0.070
joy-0.069
Token Exc
Token ID25268
Feature activation-8.87e-02

Pos logit contributions
kin+0.021
ows+0.020
as+0.019
ily+0.019
a+0.018
Neg logit contributions
 OUT-0.020
 arrest-0.019
 Johnson-0.019
joy-0.018
 Billy-0.018
Tokenited
Token ID863
Feature activation-4.74e+00

Pos logit contributions
 OUT+0.003
 arrest+0.002
 Johnson+0.002
joy+0.002
 Billy+0.002
Neg logit contributions
kin-0.013
ows-0.013
as-0.012
ily-0.012
a-0.012
Token,
Token ID11
Feature activation+4.27e-02

Pos logit contributions
 OUT+0.491
 arrest+0.482
 Johnson+0.479
istent+0.453
joy+0.447
Neg logit contributions
kin-0.327
ows-0.315
as-0.301
 holes-0.300
ily-0.298
Token he
Token ID339
Feature activation-5.11e-01

Pos logit contributions
kin+0.004
 holes+0.003
ily+0.003
ows+0.003
 Lia+0.003
Neg logit contributions
 OUT-0.004
istent-0.004
 Johnson-0.004
 arrest-0.004
arse-0.004
Token kept
Token ID4030
Feature activation+1.79e-01

Pos logit contributions
 OUT+0.042
 arrest+0.041
 Johnson+0.039
 Billy+0.038
joy+0.038
Neg logit contributions
kin-0.050
ows-0.046
as-0.044
ily-0.043
ute-0.043
Token exploring
Token ID13504
Feature activation-1.89e+00

Pos logit contributions
kin+0.019
a+0.018
 holes+0.018
as+0.018
ows+0.018
Neg logit contributions
 OUT-0.011
 Johnson-0.011
istent-0.010
 arrest-0.010
 Smith-0.009
Token until
Token ID1566
Feature activation-6.94e-01

Pos logit contributions
 OUT+0.174
 arrest+0.173
 Johnson+0.170
joy+0.169
 Billy+0.165
Neg logit contributions
kin-0.163
ows-0.145
as-0.144
ily-0.138
ute-0.137
Token of
Token ID286
Feature activation+6.77e-01

Pos logit contributions
 OUT+0.120
 arrest+0.117
 Johnson+0.115
joy+0.112
 Billy+0.111
Neg logit contributions
kin-0.084
ows-0.076
as-0.074
ily-0.070
a-0.069
Token the
Token ID262
Feature activation-3.13e-02

Pos logit contributions
kin+0.053
ily+0.046
 holes+0.046
ows+0.045
as+0.044
Neg logit contributions
 OUT-0.069
istent-0.065
 arrest-0.065
 Johnson-0.063
joy-0.062
Token mountain
Token ID8598
Feature activation-7.62e-01

Pos logit contributions
 OUT+0.003
 arrest+0.003
 Johnson+0.003
joy+0.003
 Billy+0.003
Neg logit contributions
kin-0.003
ows-0.002
 holes-0.002
as-0.002
ily-0.002
Token.
Token ID13
Feature activation+3.07e-01

Pos logit contributions
 OUT+0.082
 arrest+0.080
 Johnson+0.078
joy+0.076
 Billy+0.075
Neg logit contributions
kin-0.055
ows-0.050
as-0.047
ily-0.045
a-0.044
Token Exc
Token ID25268
Feature activation-9.52e-02

Pos logit contributions
kin+0.025
ows+0.024
ily+0.023
as+0.022
 holes+0.022
Neg logit contributions
 OUT-0.028
 arrest-0.028
 Johnson-0.027
joy-0.026
istent-0.026
Tokenited
Token ID863
Feature activation-4.73e+00

Pos logit contributions
 OUT+0.002
 arrest+0.002
 Johnson+0.002
joy+0.002
 Billy+0.002
Neg logit contributions
kin-0.015
ows-0.014
as-0.014
ily-0.013
a-0.013
Tokenly
Token ID306
Feature activation+1.29e+00

Pos logit contributions
 OUT+0.488
 arrest+0.479
 Johnson+0.470
istent+0.457
joy+0.440
Neg logit contributions
kin-0.324
ows-0.315
ily-0.309
 holes-0.298
as-0.294
Token,
Token ID11
Feature activation+5.83e-02

Pos logit contributions
kin+0.085
a+0.078
ily+0.078
ows+0.076
ia+0.070
Neg logit contributions
istent-0.133
 OUT-0.133
 Johnson-0.131
arse-0.131
 arrest-0.124
Token she
Token ID673
Feature activation-6.35e-01

Pos logit contributions
kin+0.005
ily+0.004
ows+0.004
 holes+0.004
a+0.004
Neg logit contributions
 OUT-0.005
 arrest-0.005
istent-0.005
 Johnson-0.005
arse-0.005
Token rushed
Token ID13999
Feature activation+7.78e-02

Pos logit contributions
 OUT+0.052
 arrest+0.051
 Johnson+0.049
 Billy+0.047
joy+0.047
Neg logit contributions
kin-0.062
ows-0.057
as-0.055
ute-0.054
ily-0.054
Token to
Token ID284
Feature activation-5.04e-01

Pos logit contributions
ily+0.004
kin+0.004
ows+0.004
 holes+0.004
as+0.004
Neg logit contributions
 OUT-0.009
 arrest-0.009
istent-0.009
 Johnson-0.009
 Frankie-0.008
Token saw
Token ID2497
Feature activation+6.46e-01

Pos logit contributions
 OUT+0.054
 arrest+0.052
 Johnson+0.051
joy+0.049
 Billy+0.048
Neg logit contributions
kin-0.065
ows-0.060
as-0.059
ily-0.057
a-0.056
Token a
Token ID257
Feature activation-3.13e-01

Pos logit contributions
kin+0.053
ows+0.048
as+0.047
ute+0.045
utes+0.042
Neg logit contributions
 OUT-0.063
 arrest-0.062
 Johnson-0.062
 Billy-0.061
joy-0.060
Token chest
Token ID7721
Feature activation+1.29e-01

Pos logit contributions
 OUT+0.034
 arrest+0.034
 Johnson+0.033
joy+0.032
 Billy+0.032
Neg logit contributions
kin-0.022
ows-0.019
as-0.019
ily-0.018
ute-0.017
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
kin+0.010
ows+0.009
as+0.008
a+0.008
ily+0.008
Neg logit contributions
 OUT-0.013
 arrest-0.013
 Johnson-0.013
joy-0.012
 Billy-0.012
Token Exc
Token ID25268
Feature activation-3.55e-01

Pos logit contributions
 OUT+0.001
 arrest+0.001
 Johnson+0.001
joy+0.001
istent+0.001
Neg logit contributions
kin-0.001
ows-0.001
ily-0.001
as-0.001
 holes-0.001
Tokenited
Token ID863
Feature activation-4.73e+00

Pos logit contributions
 OUT+0.010
 Johnson+0.009
 arrest+0.009
 Billy+0.008
 Frankie+0.008
Neg logit contributions
kin-0.053
as-0.051
ows-0.050
a-0.049
ily-0.049
Token,
Token ID11
Feature activation-1.04e-02

Pos logit contributions
 OUT+0.488
 arrest+0.480
 Johnson+0.475
istent+0.450
joy+0.441
Neg logit contributions
kin-0.332
ows-0.315
ily-0.304
 holes-0.300
as-0.300
Token he
Token ID339
Feature activation-6.27e-01

Pos logit contributions
 OUT+0.001
 arrest+0.001
istent+0.001
 Johnson+0.001
arse+0.001
Neg logit contributions
kin-0.001
 holes-0.001
ily-0.001
ows-0.001
a-0.001
Token pr
Token ID778
Feature activation+1.22e-01

Pos logit contributions
 OUT+0.052
 arrest+0.050
 Johnson+0.050
joy+0.047
 Billy+0.047
Neg logit contributions
kin-0.061
ows-0.056
as-0.054
ily-0.052
ute-0.052
Tokenicked
Token ID9484
Feature activation+1.61e+00

Pos logit contributions
kin+0.008
ows+0.008
as+0.008
ily+0.007
a+0.007
Neg logit contributions
 OUT-0.013
 arrest-0.013
 Johnson-0.013
joy-0.013
 Billy-0.012
Token up
Token ID510
Feature activation-7.62e-01

Pos logit contributions
kin+0.146
ows+0.132
as+0.129
ily+0.127
a+0.123
Neg logit contributions
 OUT-0.145
 arrest-0.141
 Johnson-0.137
joy-0.132
istent-0.128
Token maze
Token ID31237
Feature activation+9.33e-01

Pos logit contributions
 OUT+0.023
 arrest+0.023
 Johnson+0.022
istent+0.022
joy+0.022
Neg logit contributions
kin-0.017
ows-0.015
 holes-0.015
as-0.014
ily-0.014
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
kin+0.075
ows+0.068
as+0.067
ute+0.065
utes+0.063
Neg logit contributions
 arrest-0.089
 OUT-0.089
 Johnson-0.086
 Billy-0.082
joy-0.081
Token
Token ID198
Feature activation+2.28e-01

Pos logit contributions
kin+0.015
ows+0.014
as+0.014
ute+0.013
a+0.013
Neg logit contributions
 OUT-0.013
 arrest-0.012
 Johnson-0.012
joy-0.012
 Billy-0.012
Token
Token ID198
Feature activation+1.62e-01

Pos logit contributions
kin+0.022
ows+0.021
as+0.020
 holes+0.019
ute+0.019
Neg logit contributions
 Johnson-0.017
 OUT-0.017
 arrest-0.017
 Billy-0.017
 Frankie-0.017
TokenExc
Token ID40127
Feature activation+5.42e-01

Pos logit contributions
ows+0.014
kin+0.014
as+0.012
 holes+0.012
ute+0.012
Neg logit contributions
 OUT-0.014
 arrest-0.014
 Johnson-0.014
joy-0.014
 Frankie-0.013
Tokenited
Token ID863
Feature activation-4.73e+00

Pos logit contributions
kin+0.069
a+0.068
as+0.065
ila+0.063
ily+0.063
Neg logit contributions
 OUT-0.024
 arrest-0.024
 Billy-0.022
 Johnson-0.022
 Frankie-0.022
Tokenly
Token ID306
Feature activation+1.29e+00

Pos logit contributions
 OUT+0.457
 arrest+0.450
 Johnson+0.440
joy+0.419
istent+0.413
Neg logit contributions
kin-0.380
ows-0.353
as-0.341
ily-0.338
a-0.327
Token,
Token ID11
Feature activation-8.13e-02

Pos logit contributions
kin+0.096
ows+0.087
a+0.086
ily+0.084
as+0.082
Neg logit contributions
 OUT-0.125
 Johnson-0.124
joy-0.120
arse-0.119
 arrest-0.119
Token she
Token ID673
Feature activation-7.52e-01

Pos logit contributions
 OUT+0.006
 arrest+0.006
 Johnson+0.006
joy+0.006
 Billy+0.006
Neg logit contributions
kin-0.008
ows-0.008
as-0.007
ily-0.007
ute-0.007
Token asked
Token ID1965
Feature activation+9.94e-03

Pos logit contributions
 OUT+0.061
 arrest+0.060
 Johnson+0.057
 Billy+0.055
joy+0.055
Neg logit contributions
kin-0.074
ows-0.068
as-0.066
ute-0.064
ily-0.064
Token her
Token ID607
Feature activation+3.75e-01

Pos logit contributions
kin+0.001
ows+0.001
as+0.001
ute+0.001
 holes+0.001
Neg logit contributions
 OUT-0.001
 Johnson-0.001
 arrest-0.001
 Billy-0.001
joy-0.001
Token spaghetti
Token ID48241
Feature activation+9.07e-02

Pos logit contributions
kin+0.048
ows+0.044
as+0.043
ily+0.041
ute+0.040
Neg logit contributions
 OUT-0.055
 arrest-0.055
 Johnson-0.054
joy-0.052
 Billy-0.051
Token!"
Token ID2474
Feature activation+1.32e-01

Pos logit contributions
kin+0.008
as+0.007
ows+0.007
ily+0.007
ute+0.007
Neg logit contributions
 OUT-0.008
 arrest-0.008
 Johnson-0.008
 Billy-0.007
 Frankie-0.007
Token
Token ID198
Feature activation+5.44e-01

Pos logit contributions
kin+0.013
ows+0.012
as+0.012
ute+0.011
a+0.011
Neg logit contributions
 OUT-0.011
 arrest-0.010
 Johnson-0.010
 Billy-0.010
joy-0.010
Token
Token ID198
Feature activation+4.56e-01

Pos logit contributions
kin+0.055
ows+0.049
as+0.047
 holes+0.046
ute+0.045
Neg logit contributions
 Johnson-0.042
 OUT-0.041
 arrest-0.041
 Billy-0.040
joy-0.039
TokenExc
Token ID40127
Feature activation+5.66e-01

Pos logit contributions
kin+0.033
ows+0.031
as+0.027
 holes+0.026
ute+0.026
Neg logit contributions
 OUT-0.048
 arrest-0.047
 Johnson-0.046
 Billy-0.044
joy-0.044
Tokenited
Token ID863
Feature activation-4.73e+00

Pos logit contributions
kin+0.079
a+0.074
as+0.074
ily+0.074
ows+0.073
Neg logit contributions
 OUT-0.020
 arrest-0.019
 Johnson-0.019
 Billy-0.017
 Frankie-0.017
Tokenly
Token ID306
Feature activation+1.29e+00

Pos logit contributions
 OUT+0.502
 arrest+0.493
 Johnson+0.488
joy+0.465
istent+0.462
Neg logit contributions
kin-0.320
ows-0.302
ily-0.292
as-0.286
 holes-0.281
Token,
Token ID11
Feature activation+3.82e-02

Pos logit contributions
kin+0.084
ily+0.074
ows+0.072
a+0.072
 holes+0.067
Neg logit contributions
arse-0.135
 Johnson-0.134
 OUT-0.133
joy-0.130
istent-0.130
Token Lily
Token ID20037
Feature activation+1.54e-01

Pos logit contributions
kin+0.003
ily+0.003
ows+0.003
 holes+0.002
as+0.002
Neg logit contributions
 OUT-0.004
 arrest-0.004
istent-0.004
 Johnson-0.004
joy-0.004
Token brought
Token ID3181
Feature activation-5.63e-01

Pos logit contributions
kin+0.012
ows+0.012
as+0.012
a+0.012
ily+0.011
Neg logit contributions
 OUT-0.015
 Johnson-0.014
 arrest-0.014
joy-0.014
 Frankie-0.013
Token the
Token ID262
Feature activation-7.21e-02

Pos logit contributions
 OUT+0.054
 arrest+0.052
 Johnson+0.051
joy+0.049
istent+0.048
Neg logit contributions
kin-0.048
ows-0.043
as-0.042
ily-0.042
 holes-0.041
Token."
Token ID526
Feature activation-7.49e-01

Pos logit contributions
 OUT+0.186
 arrest+0.183
 Johnson+0.180
 Billy+0.173
 Frankie+0.169
Neg logit contributions
kin-0.169
ows-0.149
as-0.145
ily-0.141
ute-0.140
Token
Token ID220
Feature activation-1.83e+00

Pos logit contributions
 OUT+0.075
 arrest+0.072
joy+0.065
burn+0.064
 returning+0.063
Neg logit contributions
ows-0.054
kin-0.051
ily-0.050
 holes-0.048
as-0.047
Token
Token ID198
Feature activation+3.74e-01

Pos logit contributions
 OUT+0.196
 arrest+0.192
 Johnson+0.181
joy+0.181
istent+0.172
Neg logit contributions
kin-0.130
ows-0.127
as-0.119
ily-0.114
a-0.111
Token
Token ID198
Feature activation+3.32e-01

Pos logit contributions
kin+0.022
ows+0.021
as+0.021
ily+0.020
a+0.020
Neg logit contributions
 OUT-0.044
 arrest-0.042
joy-0.040
 Johnson-0.039
istent-0.039
TokenExc
Token ID40127
Feature activation+6.21e-01

Pos logit contributions
kin+0.036
as+0.036
a+0.034
ows+0.034
ily+0.034
Neg logit contributions
 OUT-0.022
 arrest-0.020
joy-0.020
 Johnson-0.019
 Billy-0.018
Tokenited
Token ID863
Feature activation-4.73e+00

Pos logit contributions
kin+0.081
a+0.078
ily+0.077
as+0.076
ows+0.076
Neg logit contributions
 OUT-0.026
 arrest-0.025
 Johnson-0.022
 Billy-0.022
 Frankie-0.020
Token for
Token ID329
Feature activation-1.28e-01

Pos logit contributions
 OUT+0.479
 arrest+0.476
 Johnson+0.459
joy+0.444
istent+0.437
Neg logit contributions
kin-0.326
ows-0.318
ily-0.308
ia-0.296
as-0.295
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
 OUT+0.014
 arrest+0.013
istent+0.013
 Johnson+0.013
joy+0.012
Neg logit contributions
kin-0.009
ily-0.008
 holes-0.008
ows-0.007
ia-0.007
Token surprise
Token ID5975
Feature activation+3.77e-01

Pos logit contributions
 OUT+0.002
 arrest+0.002
 Johnson+0.002
joy+0.002
 Billy+0.002
Neg logit contributions
kin-0.001
ows-0.001
as-0.001
ily-0.001
a-0.001
Token,
Token ID11
Feature activation-1.79e-01

Pos logit contributions
kin+0.034
ows+0.031
as+0.031
ily+0.030
a+0.029
Neg logit contributions
 OUT-0.033
 arrest-0.032
 Johnson-0.032
joy-0.030
 Billy-0.030
Token John
Token ID1757
Feature activation-1.91e+00

Pos logit contributions
 OUT+0.011
 arrest+0.010
istent+0.009
joy+0.008
arse+0.008
Neg logit contributions
kin-0.021
 holes-0.019
ows-0.019
 shapes-0.019
ily-0.019
Token!
Token ID0
Feature activation-4.52e-01

Pos logit contributions
 OUT+0.137
 arrest+0.135
 Johnson+0.133
joy+0.129
 Billy+0.128
Neg logit contributions
kin-0.128
ows-0.118
as-0.115
ily-0.112
ute-0.109
Token
Token ID220
Feature activation-1.88e+00

Pos logit contributions
 OUT+0.036
 Johnson+0.036
 arrest+0.036
joy+0.035
 Billy+0.035
Neg logit contributions
kin-0.044
ows-0.040
as-0.039
ute-0.038
a-0.037
Token
Token ID198
Feature activation+4.28e-01

Pos logit contributions
 OUT+0.170
 arrest+0.167
 Johnson+0.166
 Billy+0.159
joy+0.159
Neg logit contributions
kin-0.164
ows-0.146
as-0.143
ily-0.137
ute-0.137
Token
Token ID198
Feature activation+3.72e-01

Pos logit contributions
kin+0.044
ows+0.040
ute+0.039
 holes+0.038
as+0.038
Neg logit contributions
 Johnson-0.030
 OUT-0.030
 arrest-0.030
joy-0.029
 Billy-0.028
TokenM
Token ID44
Feature activation+1.04e+00

Pos logit contributions
kin+0.033
ows+0.032
ute+0.030
 holes+0.028
as+0.028
Neg logit contributions
 OUT-0.031
 arrest-0.031
 Johnson-0.030
joy-0.029
 returning-0.028
Tokenia
Token ID544
Feature activation+2.11e+00

Pos logit contributions
kin+0.036
ows+0.034
 holes+0.028
as+0.026
ute+0.025
Neg logit contributions
 OUT-0.139
 arrest-0.137
 Johnson-0.134
joy-0.131
istent-0.131
Token smiled
Token ID13541
Feature activation+6.02e-02

Pos logit contributions
kin+0.187
ows+0.172
as+0.166
ily+0.160
ute+0.159
Neg logit contributions
 OUT-0.189
 arrest-0.186
 Johnson-0.181
joy-0.175
 Billy-0.173
Token to
Token ID284
Feature activation-4.72e-01

Pos logit contributions
kin+0.005
as+0.005
ows+0.005
ily+0.005
ila+0.005
Neg logit contributions
joy-0.005
 OUT-0.005
 Johnson-0.005
 Billy-0.005
 arrest-0.005
Token herself
Token ID5223
Feature activation+2.67e-01

Pos logit contributions
 OUT+0.049
 arrest+0.047
 Johnson+0.047
joy+0.045
istent+0.044
Neg logit contributions
kin-0.035
ily-0.032
ows-0.031
 holes-0.029
ia-0.029
Token and
Token ID290
Feature activation+3.58e-01

Pos logit contributions
kin+0.018
ows+0.017
as+0.016
a+0.016
ute+0.015
Neg logit contributions
 OUT-0.030
 arrest-0.029
 Johnson-0.028
joy-0.027
 Billy-0.026
Token said
Token ID531
Feature activation+1.20e-01

Pos logit contributions
kin+0.032
ows+0.030
as+0.029
ily+0.028
ute+0.028
Neg logit contributions
 OUT-0.031
 arrest-0.031
 Johnson-0.030
 Billy-0.029
joy-0.029
Token scary
Token ID14343
Feature activation+5.03e-01

Pos logit contributions
kin+0.014
ows+0.013
as+0.013
ute+0.012
ily+0.012
Neg logit contributions
 OUT-0.015
 arrest-0.014
 Johnson-0.014
 Billy-0.014
 Frankie-0.013
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
kin+0.039
ows+0.034
as+0.033
ute+0.032
ily+0.031
Neg logit contributions
 OUT-0.052
 arrest-0.051
 Johnson-0.050
joy-0.048
 Billy-0.048
Token
Token ID198
Feature activation+1.04e-01

Pos logit contributions
kin+0.013
ows+0.012
as+0.012
ily+0.011
a+0.011
Neg logit contributions
 OUT-0.013
 arrest-0.013
 Johnson-0.012
joy-0.012
 Billy-0.012
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
kin+0.010
ows+0.009
as+0.008
 holes+0.008
ute+0.008
Neg logit contributions
 OUT-0.009
 Johnson-0.009
 arrest-0.009
 Billy-0.008
joy-0.008
TokenL
Token ID43
Feature activation+6.15e-01

Pos logit contributions
kin+0.008
ows+0.007
as+0.006
ute+0.006
ily+0.006
Neg logit contributions
 OUT-0.013
 arrest-0.013
 Johnson-0.013
 Billy-0.012
joy-0.012
Tokenily
Token ID813
Feature activation+3.47e+00

Pos logit contributions
kin+0.019
ute+0.015
ows+0.015
utes+0.014
 holes+0.013
Neg logit contributions
 arrest-0.083
 OUT-0.081
 Johnson-0.080
joy-0.080
 Billy-0.078
Token's
Token ID338
Feature activation+6.15e-02

Pos logit contributions
kin+0.290
ows+0.271
as+0.263
ily+0.257
a+0.255
Neg logit contributions
 OUT-0.325
 arrest-0.316
 Johnson-0.311
joy-0.305
 Frankie-0.294
Token mom
Token ID1995
Feature activation+8.20e-01

Pos logit contributions
kin+0.005
ows+0.005
as+0.004
ily+0.004
ute+0.004
Neg logit contributions
 arrest-0.006
 Johnson-0.006
 OUT-0.006
joy-0.006
 Billy-0.006
Token saw
Token ID2497
Feature activation+5.33e-01

Pos logit contributions
as+0.062
a+0.062
ily+0.061
ows+0.059
kin+0.058
Neg logit contributions
 OUT-0.081
 arrest-0.077
joy-0.076
 Johnson-0.073
 Frankie-0.073
Token the
Token ID262
Feature activation-9.30e-02

Pos logit contributions
kin+0.040
ily+0.038
ows+0.037
 holes+0.036
as+0.036
Neg logit contributions
 OUT-0.054
 arrest-0.051
 Johnson-0.051
istent-0.050
joy-0.049
Token picture
Token ID4286
Feature activation-7.04e-01

Pos logit contributions
 OUT+0.009
 arrest+0.009
 Johnson+0.009
joy+0.008
 Billy+0.008
Neg logit contributions
kin-0.008
ows-0.007
as-0.007
ily-0.006
a-0.006
Token're
Token ID821
Feature activation-2.76e+00

Pos logit contributions
kin+0.079
ows+0.074
as+0.072
ute+0.069
ily+0.068
Neg logit contributions
 OUT-0.090
 arrest-0.089
 Johnson-0.084
 Billy-0.084
joy-0.082
Token so
Token ID523
Feature activation+1.24e+00

Pos logit contributions
 OUT+0.287
 arrest+0.280
 Johnson+0.279
 Billy+0.272
 Frankie+0.269
Neg logit contributions
kin-0.202
ows-0.185
as-0.183
ute-0.171
ily-0.167
Token graceful
Token ID44363
Feature activation+1.07e-01

Pos logit contributions
kin+0.079
ows+0.071
as+0.068
ily+0.065
ute+0.063
Neg logit contributions
 OUT-0.141
 arrest-0.139
 Johnson-0.135
 Billy-0.133
joy-0.132
Token with
Token ID351
Feature activation-4.98e-01

Pos logit contributions
kin+0.011
ows+0.010
as+0.010
ute+0.009
ily+0.009
Neg logit contributions
 OUT-0.008
 arrest-0.008
 Johnson-0.008
 Billy-0.008
joy-0.008
Token your
Token ID534
Feature activation+5.38e-01

Pos logit contributions
 arrest+0.042
 OUT+0.042
 Billy+0.039
 Johnson+0.039
 Frankie+0.038
Neg logit contributions
kin-0.047
ows-0.045
as-0.042
ute-0.041
ily-0.041
Token wand
Token ID11569
Feature activation+2.88e+00

Pos logit contributions
kin+0.038
ows+0.036
as+0.035
ily+0.034
a+0.032
Neg logit contributions
 arrest-0.057
 OUT-0.056
joy-0.054
 Johnson-0.053
 Billy-0.053
Token,"
Token ID553
Feature activation-1.88e-01

Pos logit contributions
kin+0.267
ows+0.241
as+0.239
ily+0.234
ute+0.228
Neg logit contributions
 OUT-0.240
 arrest-0.237
 Johnson-0.231
 Billy-0.222
 Frankie-0.219
Token Max
Token ID5436
Feature activation-6.47e-01

Pos logit contributions
 OUT+0.013
 Johnson+0.013
 arrest+0.013
 Billy+0.013
 Frankie+0.012
Neg logit contributions
kin-0.020
ows-0.019
as-0.019
ute-0.018
a-0.017
Token said
Token ID531
Feature activation-2.58e-01

Pos logit contributions
 OUT+0.065
 arrest+0.064
 Johnson+0.063
 Billy+0.061
joy+0.060
Neg logit contributions
kin-0.050
ows-0.046
as-0.044
ily-0.042
ute-0.042
Token.
Token ID13
Feature activation+2.85e-01

Pos logit contributions
 OUT+0.028
 arrest+0.028
 Johnson+0.027
joy+0.026
 Billy+0.026
Neg logit contributions
kin-0.018
ows-0.016
as-0.015
ily-0.015
a-0.015
Token "
Token ID366
Feature activation-1.58e-01

Pos logit contributions
kin+0.027
ows+0.025
as+0.024
ute+0.023
a+0.023
Neg logit contributions
 OUT-0.024
 arrest-0.023
 Johnson-0.023
 Billy-0.022
joy-0.022
Token good
Token ID922
Feature activation-2.11e-01

Pos logit contributions
 arrest+0.049
 Johnson+0.048
 OUT+0.048
 Billy+0.048
joy+0.047
Neg logit contributions
kin-0.040
ows-0.038
ute-0.036
as-0.036
auc-0.033
Token twins
Token ID20345
Feature activation-2.56e-01

Pos logit contributions
 OUT+0.022
 arrest+0.022
 Johnson+0.022
joy+0.021
 Billy+0.021
Neg logit contributions
kin-0.016
ows-0.014
as-0.013
ily-0.013
ute-0.013
Token.
Token ID13
Feature activation-5.20e-01

Pos logit contributions
 OUT+0.029
 arrest+0.028
 Johnson+0.027
joy+0.026
 Frankie+0.026
Neg logit contributions
kin-0.018
ows-0.016
as-0.015
ily-0.015
a-0.014
Token<|endoftext|>
Token ID50256
Feature activation+1.15e+00

Pos logit contributions
 Johnson+0.046
 OUT+0.044
 Billy+0.044
 arrest+0.044
joy+0.042
Neg logit contributions
kin-0.049
ows-0.045
as-0.043
a-0.041
ute-0.041
TokenL
Token ID43
Feature activation+4.86e-01

Pos logit contributions
kin+0.115
ows+0.108
as+0.104
ute+0.099
a+0.098
Neg logit contributions
 OUT-0.087
 Johnson-0.086
 arrest-0.086
joy-0.084
 Billy-0.081
Tokenily
Token ID813
Feature activation+3.29e+00

Pos logit contributions
kin+0.026
ows+0.022
as+0.021
ute+0.019
 holes+0.019
Neg logit contributions
 OUT-0.061
 arrest-0.061
 Johnson-0.060
 Billy-0.058
joy-0.058
Token and
Token ID290
Feature activation-3.09e-01

Pos logit contributions
kin+0.223
ows+0.199
as+0.192
ily+0.178
ute+0.178
Neg logit contributions
 OUT-0.362
 arrest-0.361
 Johnson-0.352
joy-0.342
 Billy-0.342
Token Ben
Token ID3932
Feature activation+1.33e+00

Pos logit contributions
 OUT+0.026
 arrest+0.026
 Johnson+0.025
 Billy+0.024
joy+0.024
Neg logit contributions
kin-0.029
ows-0.027
as-0.027
ily-0.025
ute-0.025
Token are
Token ID389
Feature activation-8.03e-01

Pos logit contributions
kin+0.096
ows+0.086
as+0.083
ily+0.080
a+0.078
Neg logit contributions
 OUT-0.142
 arrest-0.139
 Johnson-0.137
joy-0.133
 Billy-0.131
Token friends
Token ID2460
Feature activation+4.24e-01

Pos logit contributions
 OUT+0.070
 arrest+0.069
 Johnson+0.067
joy+0.064
 Billy+0.063
Neg logit contributions
kin-0.074
ows-0.068
as-0.067
ily-0.065
a-0.064
Token.
Token ID13
Feature activation-5.20e-01

Pos logit contributions
kin+0.028
ows+0.025
as+0.024
ily+0.023
a+0.023
Neg logit contributions
 OUT-0.048
 arrest-0.047
 Johnson-0.046
joy-0.044
 Billy-0.044
Token outside
Token ID2354
Feature activation-1.19e+00

Pos logit contributions
 arrest+0.062
 OUT+0.062
 Billy+0.060
 Johnson+0.059
joy+0.059
Neg logit contributions
kin-0.049
as-0.046
ows-0.046
a-0.042
ia-0.040
Token.
Token ID13
Feature activation-1.21e-01

Pos logit contributions
 OUT+0.140
 arrest+0.138
 Johnson+0.136
joy+0.132
 Billy+0.131
Neg logit contributions
kin-0.073
ows-0.065
as-0.062
ily-0.059
a-0.057
Token One
Token ID1881
Feature activation+2.18e-01

Pos logit contributions
 OUT+0.008
 arrest+0.008
 Johnson+0.008
joy+0.007
 Billy+0.007
Neg logit contributions
kin-0.014
ows-0.013
as-0.012
a-0.012
ily-0.012
Token day
Token ID1110
Feature activation-8.89e-01

Pos logit contributions
kin+0.018
ows+0.016
as+0.016
ily+0.015
 holes+0.015
Neg logit contributions
 OUT-0.021
 arrest-0.021
 Johnson-0.021
 Billy-0.020
joy-0.020
Token,
Token ID11
Feature activation-2.43e-01

Pos logit contributions
 OUT+0.063
 arrest+0.062
 Johnson+0.060
joy+0.059
 Billy+0.057
Neg logit contributions
kin-0.093
ows-0.088
as-0.086
ily-0.082
ute-0.082
Token Julia
Token ID22300
Feature activation+1.79e+00

Pos logit contributions
joy+0.015
 arrest+0.015
 OUT+0.015
 John+0.014
 Billy+0.014
Neg logit contributions
kin-0.027
ows-0.026
as-0.025
auc-0.024
an-0.024
Token found
Token ID1043
Feature activation+8.29e-01

Pos logit contributions
kin+0.168
ows+0.155
as+0.151
ily+0.147
a+0.144
Neg logit contributions
 OUT-0.152
 arrest-0.148
 Johnson-0.146
joy-0.140
 Billy-0.138
Token an
Token ID281
Feature activation-1.16e+00

Pos logit contributions
kin+0.077
ows+0.073
as+0.070
ute+0.066
utes+0.063
Neg logit contributions
 Billy-0.073
 Johnson-0.073
 arrest-0.072
 OUT-0.070
 Frankie-0.069
Token orange
Token ID10912
Feature activation-4.62e-01

Pos logit contributions
 OUT+0.117
 Johnson+0.116
 Billy+0.115
 arrest+0.113
 Frankie+0.112
Neg logit contributions
kin-0.088
ows-0.084
as-0.082
a-0.073
ute-0.069
Token telephone
Token ID11426
Feature activation+3.52e-01

Pos logit contributions
 Johnson+0.045
 OUT+0.045
 arrest+0.043
 Billy+0.042
 Frankie+0.041
Neg logit contributions
ows-0.037
as-0.036
kin-0.036
a-0.032
ily-0.032
Token in
Token ID287
Feature activation+1.46e+00

Pos logit contributions
kin+0.023
ows+0.020
as+0.019
ily+0.019
ute+0.018
Neg logit contributions
 OUT-0.040
 arrest-0.039
 Johnson-0.039
joy-0.038
 Billy-0.037
Token my
Token ID616
Feature activation-5.06e-01

Pos logit contributions
kin+0.078
ows+0.071
as+0.069
ute+0.066
ily+0.066
Neg logit contributions
 OUT-0.079
 arrest-0.078
 Johnson-0.076
 Billy-0.074
 Frankie-0.073
Token pig
Token ID12967
Feature activation-7.07e-01

Pos logit contributions
 arrest+0.047
 Johnson+0.047
 OUT+0.046
joy+0.045
 Billy+0.044
Neg logit contributions
kin-0.043
ows-0.041
as-0.038
ily-0.038
a-0.035
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
 OUT+0.068
 arrest+0.066
 Johnson+0.064
joy+0.064
 Billy+0.062
Neg logit contributions
kin-0.058
ows-0.054
as-0.052
a-0.049
ily-0.049
Token Let
Token ID3914
Feature activation-1.31e+00

Pos logit contributions
 OUT+0.017
 arrest+0.017
joy+0.016
 Johnson+0.016
istent+0.015
Neg logit contributions
kin-0.015
ows-0.014
as-0.013
ily-0.013
a-0.013
Token's
Token ID338
Feature activation-7.91e-02

Pos logit contributions
 OUT+0.121
joy+0.119
 arrest+0.118
 Johnson+0.115
istent+0.110
Neg logit contributions
kin-0.106
a-0.105
ily-0.102
ows-0.099
as-0.098
Token go
Token ID467
Feature activation+2.75e-01

Pos logit contributions
 OUT+0.007
 arrest+0.007
 Johnson+0.007
 Billy+0.007
 Frankie+0.006
Neg logit contributions
kin-0.007
ows-0.007
as-0.006
ily-0.006
ute-0.006
Token home
Token ID1363
Feature activation-1.70e+00

Pos logit contributions
kin+0.019
ows+0.019
as+0.018
a+0.018
ute+0.018
Neg logit contributions
 OUT-0.029
 arrest-0.027
 Johnson-0.027
joy-0.027
istent-0.026
Token.
Token ID13
Feature activation+3.99e-02

Pos logit contributions
 OUT+0.181
 arrest+0.176
 Johnson+0.171
joy+0.167
 Billy+0.165
Neg logit contributions
kin-0.125
ows-0.115
as-0.110
a-0.105
ily-0.104
Tokenâ
Token ID22940
Feature activation+3.53e-01

Pos logit contributions
kin+0.003
ows+0.003
as+0.003
ily+0.003
a+0.003
Neg logit contributions
 OUT-0.004
 arrest-0.004
joy-0.004
 Johnson-0.004
istent-0.003
Token
Token ID26391
Feature activation-9.21e-01

Pos logit contributions
kin+0.032
ows+0.030
as+0.029
ily+0.028
a+0.027
Neg logit contributions
 OUT-0.031
 arrest-0.030
 Johnson-0.030
joy-0.028
 Billy-0.028
Token So
Token ID1406
Feature activation+4.10e-01

Pos logit contributions
 OUT+0.086
 Frankie+0.081
 arrest+0.080
ited+0.079
joy+0.078
Neg logit contributions
ows-0.074
kin-0.073
as-0.072
a-0.069
ute-0.064
Token He
Token ID679
Feature activation+4.76e-01

Pos logit contributions
 arrest+0.003
 OUT+0.003
joy+0.002
 returning+0.002
istent+0.002
Neg logit contributions
ows-0.002
kin-0.002
ily-0.002
 holes-0.002
ia-0.002
Token had
Token ID550
Feature activation+1.94e-01

Pos logit contributions
kin+0.040
ows+0.037
as+0.035
ute+0.034
ily+0.033
Neg logit contributions
 OUT-0.044
 arrest-0.044
 Johnson-0.043
 Billy-0.042
joy-0.041
Token a
Token ID257
Feature activation-2.97e-01

Pos logit contributions
kin+0.014
ows+0.013
as+0.012
ily+0.012
ute+0.011
Neg logit contributions
 OUT-0.021
 arrest-0.020
 Johnson-0.020
joy-0.019
 Billy-0.019
Token playful
Token ID34264
Feature activation-4.03e-01

Pos logit contributions
 OUT+0.032
 Johnson+0.032
 arrest+0.032
 Billy+0.031
joy+0.031
Neg logit contributions
kin-0.020
ows-0.019
as-0.018
ily-0.017
a-0.016
Token puppy
Token ID26188
Feature activation-1.67e+00

Pos logit contributions
 OUT+0.042
 arrest+0.041
 Johnson+0.040
istent+0.039
 Frankie+0.038
Neg logit contributions
kin-0.030
ows-0.026
as-0.025
ily-0.025
 holes-0.025
Token named
Token ID3706
Feature activation-2.17e-02

Pos logit contributions
 OUT+0.162
 arrest+0.155
joy+0.154
 Johnson+0.154
istent+0.151
Neg logit contributions
kin-0.136
ows-0.123
as-0.121
ily-0.119
a-0.117
Token Max
Token ID5436
Feature activation-3.70e-01

Pos logit contributions
joy+0.002
 arrest+0.002
 OUT+0.002
ited+0.002
istent+0.002
Neg logit contributions
ows-0.002
kin-0.002
ily-0.002
as-0.002
ia-0.002
Token who
Token ID508
Feature activation+3.32e-01

Pos logit contributions
 OUT+0.045
 arrest+0.045
joy+0.043
 Johnson+0.042
istent+0.042
Neg logit contributions
kin-0.021
ows-0.020
ily-0.019
as-0.018
a-0.018
Token would
Token ID561
Feature activation+2.15e-01

Pos logit contributions
kin+0.021
ows+0.019
as+0.018
a+0.018
ily+0.017
Neg logit contributions
 OUT-0.039
 arrest-0.038
joy-0.037
 Johnson-0.036
istent-0.035
Token run
Token ID1057
Feature activation-5.31e-02

Pos logit contributions
kin+0.020
ows+0.018
as+0.018
ily+0.017
a+0.017
Neg logit contributions
 OUT-0.018
joy-0.018
 Johnson-0.017
 arrest-0.017
istent-0.016
Token around
Token ID1088
Feature activation+4.95e-01

Pos logit contributions
 OUT+0.006
 arrest+0.006
 Johnson+0.005
 Billy+0.005
joy+0.005
Neg logit contributions
kin-0.004
ows-0.003
as-0.003
ily-0.003
ute-0.003
Token tell
Token ID1560
Feature activation+6.95e-02

Pos logit contributions
kin+0.115
ows+0.107
as+0.105
ily+0.102
a+0.102
Neg logit contributions
 OUT-0.109
 arrest-0.104
joy-0.104
 Johnson-0.103
 Billy-0.097
Token him
Token ID683
Feature activation+1.07e+00

Pos logit contributions
kin+0.007
ows+0.007
as+0.006
ute+0.006
ily+0.006
Neg logit contributions
 OUT-0.005
 arrest-0.005
 Billy-0.005
 Johnson-0.005
 Frankie-0.005
Token your
Token ID534
Feature activation+6.03e-01

Pos logit contributions
kin+0.090
ows+0.080
as+0.079
ily+0.076
ute+0.075
Neg logit contributions
 OUT-0.100
 arrest-0.098
 Johnson-0.096
 Billy-0.093
joy-0.092
Token names
Token ID3891
Feature activation+1.33e+00

Pos logit contributions
kin+0.043
ows+0.037
ily+0.037
as+0.036
auc+0.035
Neg logit contributions
 arrest-0.062
 Johnson-0.060
 OUT-0.060
joy-0.060
 dreaming-0.058
Token and
Token ID290
Feature activation-1.66e-01

Pos logit contributions
kin+0.110
ows+0.100
as+0.098
ute+0.094
ily+0.094
Neg logit contributions
 OUT-0.122
 arrest-0.120
 Johnson-0.120
 Billy-0.116
 Frankie-0.114
Token what
Token ID644
Feature activation-4.31e-03

Pos logit contributions
 arrest+0.014
 OUT+0.014
 Johnson+0.013
 Billy+0.013
 Frankie+0.013
Neg logit contributions
kin-0.016
ows-0.015
as-0.014
ily-0.014
ute-0.014
Token you
Token ID345
Feature activation+9.93e-01

Pos logit contributions
 OUT+0.000
 arrest+0.000
 Johnson+0.000
 Billy+0.000
 Frankie+0.000
Neg logit contributions
kin-0.000
ows-0.000
as-0.000
ute-0.000
ily-0.000
Token like
Token ID588
Feature activation+8.74e-01

Pos logit contributions
kin+0.084
ows+0.077
as+0.075
ily+0.072
a+0.071
Neg logit contributions
 OUT-0.093
 arrest-0.091
 Johnson-0.090
joy-0.087
 Billy-0.085
Token to
Token ID284
Feature activation-7.06e-01

Pos logit contributions
kin+0.072
ows+0.065
as+0.062
ute+0.060
ily+0.059
Neg logit contributions
 arrest-0.083
 OUT-0.083
 Johnson-0.081
 Billy-0.079
joy-0.078
Token do
Token ID466
Feature activation+9.76e-01

Pos logit contributions
 OUT+0.063
 arrest+0.061
 Johnson+0.061
joy+0.059
 Billy+0.057
Neg logit contributions
kin-0.063
ows-0.058
as-0.056
ily-0.054
a-0.053
Token.
Token ID13
Feature activation-2.94e-01

Pos logit contributions
kin+0.077
ows+0.069
as+0.068
ute+0.065
ily+0.063
Neg logit contributions
 arrest-0.093
 OUT-0.093
 Johnson-0.089
 Billy-0.088
joy-0.087
Token time
Token ID640
Feature activation+3.56e-01

Pos logit contributions
 OUT+0.033
 arrest+0.032
 Johnson+0.032
joy+0.031
 Billy+0.030
Neg logit contributions
kin-0.025
ows-0.022
as-0.022
ily-0.021
a-0.020
Token,
Token ID11
Feature activation-5.22e-01

Pos logit contributions
kin+0.031
ows+0.027
as+0.027
ily+0.027
a+0.026
Neg logit contributions
 OUT-0.034
 arrest-0.033
 Johnson-0.031
istent-0.031
joy-0.030
Token there
Token ID612
Feature activation+6.59e-02

Pos logit contributions
 Johnson+0.043
 Billy+0.042
 OUT+0.040
 Frankie+0.040
joy+0.039
Neg logit contributions
ows-0.045
kin-0.045
as-0.042
ute-0.040
 holes-0.040
Token was
Token ID373
Feature activation-3.91e-01

Pos logit contributions
kin+0.005
ows+0.005
as+0.004
ily+0.004
ute+0.004
Neg logit contributions
 OUT-0.007
 arrest-0.007
 Johnson-0.007
 Billy-0.006
joy-0.006
Token a
Token ID257
Feature activation-3.61e-01

Pos logit contributions
 arrest+0.038
 OUT+0.038
 Johnson+0.038
 Billy+0.037
joy+0.036
Neg logit contributions
kin-0.031
ows-0.029
as-0.028
ute-0.026
a-0.025
Token little
Token ID1310
Feature activation-9.96e-02

Pos logit contributions
 OUT+0.035
 arrest+0.034
 Johnson+0.034
joy+0.033
 Billy+0.033
Neg logit contributions
kin-0.029
ows-0.027
as-0.026
ily-0.025
 holes-0.024
Token girl
Token ID2576
Feature activation-2.20e-01

Pos logit contributions
 OUT+0.010
 Johnson+0.010
 arrest+0.010
 Billy+0.010
joy+0.010
Neg logit contributions
kin-0.007
ows-0.007
as-0.007
ily-0.006
 holes-0.006
Token named
Token ID3706
Feature activation-2.22e-01

Pos logit contributions
 OUT+0.017
 arrest+0.017
 Johnson+0.016
 Billy+0.016
joy+0.015
Neg logit contributions
kin-0.022
ows-0.021
as-0.020
ily-0.019
 holes-0.019
Token Lily
Token ID20037
Feature activation+2.40e-01

Pos logit contributions
 OUT+0.023
 arrest+0.022
 Johnson+0.021
joy+0.021
istent+0.021
Neg logit contributions
kin-0.017
ows-0.016
ily-0.016
as-0.015
a-0.015
Token.
Token ID13
Feature activation-8.13e-02

Pos logit contributions
kin+0.016
ows+0.014
as+0.014
ily+0.013
a+0.013
Neg logit contributions
 OUT-0.027
 arrest-0.026
 Johnson-0.026
joy-0.025
 Billy-0.025
Token She
Token ID1375
Feature activation-4.12e-01

Pos logit contributions
 arrest+0.008
 OUT+0.008
 Johnson+0.007
joy+0.007
 Frankie+0.007
Neg logit contributions
kin-0.007
ows-0.006
ily-0.006
as-0.006
 holes-0.006
Token Ben
Token ID3932
Feature activation+1.29e+00

Pos logit contributions
 OUT+0.064
 arrest+0.063
 Johnson+0.061
joy+0.059
 Billy+0.059
Neg logit contributions
kin-0.055
ows-0.050
as-0.049
ily-0.047
a-0.046
Token did
Token ID750
Feature activation+1.48e+00

Pos logit contributions
kin+0.090
ows+0.080
as+0.078
ute+0.076
utes+0.073
Neg logit contributions
 OUT-0.139
 arrest-0.138
 Johnson-0.135
 Billy-0.131
joy-0.130
Token not
Token ID407
Feature activation-1.69e-02

Pos logit contributions
kin+0.069
ows+0.057
ily+0.053
a+0.050
as+0.048
Neg logit contributions
 OUT-0.199
 arrest-0.191
 Johnson-0.191
joy-0.191
 Frankie-0.187
Token stop
Token ID2245
Feature activation+1.16e+00

Pos logit contributions
 OUT+0.001
 arrest+0.001
 Johnson+0.001
 Billy+0.001
joy+0.001
Neg logit contributions
kin-0.002
ows-0.002
as-0.002
ute-0.002
 holes-0.002
Token crying
Token ID13774
Feature activation-9.38e-01

Pos logit contributions
kin+0.088
ows+0.080
 holes+0.079
ily+0.079
as+0.078
Neg logit contributions
 OUT-0.113
 arrest-0.110
 Johnson-0.106
istent-0.103
 Frankie-0.102
Token.
Token ID13
Feature activation+2.16e-02

Pos logit contributions
 Johnson+0.080
 OUT+0.080
 arrest+0.078
 Billy+0.077
joy+0.076
Neg logit contributions
kin-0.084
ows-0.074
as-0.074
utes-0.073
ute-0.073
Token He
Token ID679
Feature activation+4.38e-01

Pos logit contributions
kin+0.002
as+0.002
ute+0.002
a+0.002
utes+0.002
Neg logit contributions
 Johnson-0.001
joy-0.001
 OUT-0.001
 Billy-0.001
 arrest-0.001
Token cried
Token ID16896
Feature activation-2.73e-02

Pos logit contributions
kin+0.044
ute+0.042
ows+0.041
utes+0.041
as+0.039
Neg logit contributions
 arrest-0.033
 OUT-0.032
 Johnson-0.031
 Billy-0.031
 John-0.028
Token louder
Token ID27089
Feature activation+9.87e-01

Pos logit contributions
 OUT+0.002
 Johnson+0.002
 Billy+0.002
 arrest+0.002
joy+0.002
Neg logit contributions
kin-0.002
as-0.002
ows-0.002
ute-0.002
utes-0.002
Token and
Token ID290
Feature activation+1.20e-01

Pos logit contributions
kin+0.089
ows+0.079
as+0.076
ute+0.076
a+0.072
Neg logit contributions
 arrest-0.088
 OUT-0.086
joy-0.085
 Johnson-0.082
 Billy-0.079
Token louder
Token ID27089
Feature activation+9.98e-01

Pos logit contributions
kin+0.012
ute+0.011
as+0.011
ows+0.011
utes+0.011
Neg logit contributions
 arrest-0.010
 OUT-0.009
 Billy-0.009
joy-0.009
 Johnson-0.009
Token cat
Token ID3797
Feature activation-5.37e-01

Pos logit contributions
kin+0.022
ows+0.021
as+0.020
ily+0.019
ute+0.019
Neg logit contributions
 OUT-0.021
 Johnson-0.020
 arrest-0.020
 Billy-0.019
joy-0.019
Token took
Token ID1718
Feature activation+1.17e-01

Pos logit contributions
 OUT+0.052
 arrest+0.051
 Johnson+0.050
joy+0.048
 Billy+0.047
Neg logit contributions
kin-0.044
ows-0.040
as-0.039
ily-0.038
a-0.037
Token the
Token ID262
Feature activation-3.13e-01

Pos logit contributions
kin+0.010
ows+0.009
as+0.009
ily+0.009
a+0.009
Neg logit contributions
 OUT-0.011
 arrest-0.010
 Johnson-0.010
joy-0.010
 Billy-0.010
Token little
Token ID1310
Feature activation-2.77e-01

Pos logit contributions
 OUT+0.028
 arrest+0.028
 Johnson+0.027
joy+0.026
 Billy+0.026
Neg logit contributions
kin-0.028
ows-0.025
as-0.024
ily-0.024
a-0.023
Token mouse
Token ID10211
Feature activation-3.85e-02

Pos logit contributions
 OUT+0.027
 arrest+0.026
 Johnson+0.026
joy+0.025
 Billy+0.025
Neg logit contributions
kin-0.023
ows-0.021
as-0.020
ily-0.019
ute-0.019
Token home
Token ID1363
Feature activation-1.82e+00

Pos logit contributions
 OUT+0.004
 Johnson+0.004
 arrest+0.004
joy+0.004
istent+0.004
Neg logit contributions
kin-0.003
ows-0.003
as-0.003
 holes-0.002
a-0.002
Token and
Token ID290
Feature activation+4.18e-01

Pos logit contributions
 OUT+0.206
 arrest+0.199
 Johnson+0.192
joy+0.187
 Frankie+0.185
Neg logit contributions
kin-0.126
ows-0.116
as-0.106
ily-0.101
a-0.100
Token decided
Token ID3066
Feature activation+1.27e+00

Pos logit contributions
kin+0.036
ows+0.032
a+0.030
 holes+0.030
as+0.030
Neg logit contributions
 OUT-0.040
 arrest-0.037
joy-0.037
 Johnson-0.037
istent-0.036
Token to
Token ID284
Feature activation-5.24e-01

Pos logit contributions
kin+0.080
ows+0.076
ily+0.072
a+0.070
as+0.070
Neg logit contributions
 OUT-0.141
 arrest-0.136
 Johnson-0.134
istent-0.132
joy-0.129
Token keep
Token ID1394
Feature activation-4.81e-02

Pos logit contributions
 OUT+0.043
 Johnson+0.041
 arrest+0.041
joy+0.041
 Billy+0.038
Neg logit contributions
kin-0.050
ows-0.046
as-0.045
ily-0.044
a-0.043
Token it
Token ID340
Feature activation+4.99e-01

Pos logit contributions
 OUT+0.005
istent+0.005
 arrest+0.005
ited+0.005
 Johnson+0.005
Neg logit contributions
kin-0.003
 holes-0.003
ily-0.003
a-0.003
ows-0.003
Token.
Token ID13
Feature activation+5.26e-02

Pos logit contributions
kin+0.044
ows+0.041
as+0.039
ily+0.038
 holes+0.037
Neg logit contributions
 OUT-0.059
 arrest-0.058
 Johnson-0.056
joy-0.055
 Frankie-0.054
Token It
Token ID632
Feature activation+3.32e-01

Pos logit contributions
kin+0.005
as+0.005
a+0.005
ute+0.005
ows+0.005
Neg logit contributions
 Johnson-0.004
 OUT-0.004
 arrest-0.004
joy-0.004
 Billy-0.004
Token had
Token ID550
Feature activation+2.43e-01

Pos logit contributions
utes+0.033
ute+0.033
kin+0.033
ows+0.032
as+0.032
Neg logit contributions
 Johnson-0.024
 returned-0.022
 Billy-0.022
 OUT-0.021
 Frankie-0.021
Token a
Token ID257
Feature activation-3.54e-01

Pos logit contributions
kin+0.021
ute+0.019
ows+0.018
as+0.018
utes+0.017
Neg logit contributions
 arrest-0.024
 OUT-0.022
 Billy-0.022
 Johnson-0.022
joy-0.021
Token big
Token ID1263
Feature activation-2.75e-01

Pos logit contributions
 OUT+0.039
 Johnson+0.039
 arrest+0.038
 Billy+0.037
joy+0.037
Neg logit contributions
kin-0.023
ows-0.022
as-0.021
ily-0.021
a-0.019
Token road
Token ID2975
Feature activation-6.87e-01

Pos logit contributions
 OUT+0.034
 arrest+0.033
 Johnson+0.033
joy+0.032
 Billy+0.031
Neg logit contributions
kin-0.016
ows-0.014
as-0.013
ily-0.012
a-0.012
Token with
Token ID351
Feature activation-5.61e-01

Pos logit contributions
 arrest+0.060
 Johnson+0.059
 OUT+0.058
 returning+0.056
 leaving+0.055
Neg logit contributions
kin-0.060
as-0.054
ute-0.054
utes-0.053
ily-0.052
Token many
Token ID867
Feature activation-5.61e-01

Pos logit contributions
 arrest+0.057
 OUT+0.054
 Billy+0.054
 Johnson+0.054
 returning+0.051
Neg logit contributions
kin-0.047
ows-0.040
ute-0.040
as-0.038
a-0.036
Token cars
Token ID5006
Feature activation+7.79e-01

Pos logit contributions
 OUT+0.065
 arrest+0.064
 Johnson+0.063
joy+0.061
 Billy+0.061
Neg logit contributions
kin-0.036
ows-0.031
as-0.030
ily-0.028
ute-0.028
Token and
Token ID290
Feature activation-3.67e-02

Pos logit contributions
kin+0.059
ows+0.053
as+0.051
ily+0.049
ute+0.048
Neg logit contributions
 OUT-0.080
 arrest-0.079
 Johnson-0.077
joy-0.075
 Billy-0.074
Token trucks
Token ID13960
Feature activation-8.45e-03

Pos logit contributions
 arrest+0.004
 OUT+0.004
 Johnson+0.004
 Billy+0.004
joy+0.004
Neg logit contributions
kin-0.003
ows-0.002
as-0.002
ute-0.002
ily-0.002
Token
Token ID198
Feature activation+4.13e-01

Pos logit contributions
kin+0.039
ows+0.036
as+0.035
ily+0.033
a+0.033
Neg logit contributions
 OUT-0.045
 arrest-0.044
 Johnson-0.043
joy-0.041
 Billy-0.041
TokenHer
Token ID9360
Feature activation+1.30e+00

Pos logit contributions
kin+0.029
ows+0.027
as+0.025
ily+0.024
ute+0.023
Neg logit contributions
 OUT-0.045
 arrest-0.044
 Johnson-0.043
 Billy-0.041
joy-0.041
Token mom
Token ID1995
Feature activation+9.32e-01

Pos logit contributions
kin+0.105
ows+0.104
as+0.096
ily+0.092
ute+0.090
Neg logit contributions
 Johnson-0.122
 arrest-0.120
 OUT-0.118
 Billy-0.118
joy-0.113
Tokenmy
Token ID1820
Feature activation-1.46e+00

Pos logit contributions
as+0.102
a+0.100
ows+0.097
ily+0.095
kin+0.094
Neg logit contributions
 arrest-0.065
 OUT-0.063
joy-0.060
 Frankie-0.055
 Johnson-0.054
Token came
Token ID1625
Feature activation+8.35e-01

Pos logit contributions
 arrest+0.151
 OUT+0.150
joy+0.147
 Johnson+0.139
 avail+0.137
Neg logit contributions
a-0.105
as-0.097
ows-0.094
ily-0.093
kin-0.092
Token running
Token ID2491
Feature activation-7.70e-01

Pos logit contributions
kin+0.048
as+0.047
ows+0.045
a+0.045
ily+0.043
Neg logit contributions
 OUT-0.097
 arrest-0.095
 Johnson-0.091
istent-0.090
 Frankie-0.089
Token and
Token ID290
Feature activation+4.95e-01

Pos logit contributions
 OUT+0.077
 arrest+0.075
 Johnson+0.075
joy+0.072
 Billy+0.071
Neg logit contributions
kin-0.062
ows-0.055
as-0.054
ily-0.051
ute-0.051
Token saw
Token ID2497
Feature activation+7.51e-01

Pos logit contributions
a+0.034
as+0.033
ows+0.032
kin+0.031
ily+0.030
Neg logit contributions
 arrest-0.052
 OUT-0.051
istent-0.049
joy-0.047
 Johnson-0.046
Token the
Token ID262
Feature activation-6.74e-02

Pos logit contributions
kin+0.062
ows+0.058
ily+0.056
as+0.056
 holes+0.054
Neg logit contributions
 OUT-0.072
 arrest-0.069
 Johnson-0.068
joy-0.067
istent-0.066
Token pan
Token ID3425
Feature activation-1.18e-01

Pos logit contributions
 arrest+0.006
 Johnson+0.006
 OUT+0.006
joy+0.006
 Frankie+0.006
Neg logit contributions
kin-0.006
ows-0.005
as-0.005
ily-0.005
ute-0.005
Token on
Token ID319
Feature activation+3.39e-01

Pos logit contributions
 OUT+0.012
 arrest+0.012
 Johnson+0.012
joy+0.012
 Billy+0.011
Neg logit contributions
kin-0.009
ows-0.008
as-0.008
ily-0.007
a-0.007
Token.
Token ID13
Feature activation+7.76e-02

Pos logit contributions
 OUT+0.059
 arrest+0.058
 Johnson+0.057
joy+0.055
 Billy+0.055
Neg logit contributions
kin-0.049
ows-0.044
as-0.043
ily-0.042
ute-0.041
Token We
Token ID775
Feature activation-8.41e-01

Pos logit contributions
kin+0.006
ows+0.006
as+0.006
ily+0.006
ute+0.005
Neg logit contributions
 OUT-0.007
 arrest-0.007
 Johnson-0.007
joy-0.007
istent-0.006
Token should
Token ID815
Feature activation+9.09e-01

Pos logit contributions
 OUT+0.092
 arrest+0.091
 Johnson+0.089
 Billy+0.087
 Frankie+0.086
Neg logit contributions
kin-0.058
ows-0.052
as-0.049
ily-0.047
 holes-0.046
Token think
Token ID892
Feature activation+5.37e-01

Pos logit contributions
kin+0.071
ows+0.063
as+0.062
ily+0.061
a+0.060
Neg logit contributions
 OUT-0.091
joy-0.089
 Johnson-0.087
 arrest-0.086
 Frankie-0.080
Token carefully
Token ID7773
Feature activation+3.05e-01

Pos logit contributions
kin+0.043
ows+0.039
as+0.038
ily+0.036
ute+0.036
Neg logit contributions
 OUT-0.053
 arrest-0.052
 Johnson-0.051
 Billy-0.049
joy-0.049
Token before
Token ID878
Feature activation-9.08e-01

Pos logit contributions
kin+0.026
ows+0.024
as+0.023
ily+0.022
a+0.022
Neg logit contributions
 OUT-0.028
 Johnson-0.027
 arrest-0.027
joy-0.026
 Frankie-0.026
Token we
Token ID356
Feature activation-1.22e-01

Pos logit contributions
 OUT+0.092
 Johnson+0.089
ited+0.088
oured+0.085
joy+0.084
Neg logit contributions
kin-0.063
 holes-0.059
 shapes-0.053
ires-0.052
utes-0.052
Token do
Token ID466
Feature activation+1.21e+00

Pos logit contributions
 OUT+0.011
 arrest+0.011
 Johnson+0.011
joy+0.010
 Billy+0.010
Neg logit contributions
kin-0.010
ows-0.009
as-0.009
ily-0.009
ute-0.009
Token something
Token ID1223
Feature activation-1.54e-01

Pos logit contributions
kin+0.093
ows+0.084
as+0.081
ily+0.078
a+0.077
Neg logit contributions
 OUT-0.123
 arrest-0.120
 Johnson-0.119
joy-0.114
 Billy-0.112
Token to
Token ID284
Feature activation-5.64e-01

Pos logit contributions
 OUT+0.015
 arrest+0.014
 Billy+0.014
 Johnson+0.014
 Frankie+0.014
Neg logit contributions
kin-0.012
ows-0.011
as-0.011
ily-0.010
ute-0.010
Token make
Token ID787
Feature activation+1.05e+00

Pos logit contributions
 OUT+0.055
joy+0.053
 Johnson+0.052
 arrest+0.052
 Frankie+0.048
Neg logit contributions
kin-0.047
ows-0.042
as-0.040
ily-0.040
a-0.039
Token loud
Token ID7812
Feature activation+2.33e-01

Pos logit contributions
 OUT+0.025
 Johnson+0.024
 arrest+0.024
 Billy+0.023
 returning+0.023
Neg logit contributions
kin-0.020
ows-0.018
as-0.017
ily-0.017
ires-0.015
Token animal
Token ID5044
Feature activation+3.95e-01

Pos logit contributions
kin+0.015
ows+0.013
as+0.012
ily+0.012
ute+0.012
Neg logit contributions
 OUT-0.026
 arrest-0.026
 Johnson-0.026
joy-0.025
 Billy-0.025
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
kin+0.035
ows+0.032
as+0.031
ily+0.030
a+0.029
Neg logit contributions
 OUT-0.036
 arrest-0.035
 Johnson-0.034
 Billy-0.033
joy-0.033
Token He
Token ID679
Feature activation+2.33e-01

Pos logit contributions
 arrest+0.035
 OUT+0.035
 Johnson+0.032
 Frankie+0.032
istent+0.032
Neg logit contributions
ows-0.024
kin-0.024
ily-0.022
 holes-0.022
as-0.021
Token looked
Token ID3114
Feature activation+3.85e-01

Pos logit contributions
kin+0.021
ows+0.019
as+0.019
ily+0.018
ute+0.018
Neg logit contributions
 OUT-0.021
 arrest-0.020
 Johnson-0.020
 Billy-0.019
joy-0.019
Token up
Token ID510
Feature activation-7.84e-01

Pos logit contributions
kin+0.025
ows+0.023
as+0.022
ily+0.021
a+0.020
Neg logit contributions
 OUT-0.044
 arrest-0.043
 Johnson-0.042
joy-0.041
 Billy-0.041
Token and
Token ID290
Feature activation-6.50e-03

Pos logit contributions
 OUT+0.080
 arrest+0.079
 Johnson+0.077
joy+0.076
 Billy+0.075
Neg logit contributions
kin-0.060
ows-0.055
as-0.053
ily-0.050
a-0.049
Token saw
Token ID2497
Feature activation+5.49e-01

Pos logit contributions
 arrest+0.001
 OUT+0.001
 Johnson+0.001
istent+0.001
 Frankie+0.001
Neg logit contributions
kin-0.001
ows-0.001
as-0.000
 holes-0.000
ily-0.000
Token a
Token ID257
Feature activation-2.82e-01

Pos logit contributions
kin+0.051
ows+0.046
as+0.044
ute+0.044
utes+0.041
Neg logit contributions
 Billy-0.049
 arrest-0.048
 OUT-0.048
 Johnson-0.048
 John-0.047
Token big
Token ID1263
Feature activation-1.13e-01

Pos logit contributions
 OUT+0.030
 Johnson+0.030
 arrest+0.030
joy+0.029
 Billy+0.028
Neg logit contributions
kin-0.020
ows-0.018
as-0.017
ily-0.017
ute-0.016
Token dog
Token ID3290
Feature activation-6.65e-01

Pos logit contributions
 OUT+0.011
 arrest+0.011
 Johnson+0.011
istent+0.011
joy+0.011
Neg logit contributions
kin-0.008
ows-0.007
 holes-0.007
as-0.007
ily-0.007
Token
Token ID26391
Feature activation-8.04e-01

Pos logit contributions
kin+0.016
ows+0.015
as+0.015
ily+0.014
 holes+0.014
Neg logit contributions
 OUT-0.015
 arrest-0.014
 Johnson-0.014
joy-0.014
 Billy-0.013
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
 OUT+0.073
 arrest+0.071
 Johnson+0.069
 Frankie+0.068
 returning+0.066
Neg logit contributions
kin-0.067
ows-0.065
as-0.063
a-0.061
ute-0.058
Token
Token ID198
Feature activation-9.07e-02

Pos logit contributions
 arrest+0.009
 OUT+0.009
 Johnson+0.008
joy+0.008
istent+0.008
Neg logit contributions
kin-0.009
ows-0.008
ily-0.008
as-0.008
a-0.008
Token
Token ID198
Feature activation-1.55e-01

Pos logit contributions
 OUT+0.008
 arrest+0.008
 Johnson+0.008
joy+0.008
 Billy+0.008
Neg logit contributions
kin-0.008
ows-0.007
as-0.007
ily-0.007
ute-0.006
TokenS
Token ID50
Feature activation-1.08e+00

Pos logit contributions
 OUT+0.015
 arrest+0.015
 Johnson+0.015
joy+0.014
 Billy+0.014
Neg logit contributions
kin-0.012
as-0.011
ows-0.011
ily-0.011
a-0.010
Tokenaman
Token ID10546
Feature activation-4.91e+00

Pos logit contributions
 arrest+0.114
 OUT+0.112
 Johnson+0.108
 Frankie+0.107
 Billy+0.105
Neg logit contributions
kin-0.077
as-0.071
ows-0.071
ily-0.069
ia-0.068
Tokentha
Token ID12898
Feature activation-2.32e+00

Pos logit contributions
 OUT+0.343
 arrest+0.332
 Johnson+0.322
joy+0.308
 Billy+0.303
Neg logit contributions
kin-0.533
ows-0.496
as-0.485
ily-0.473
a-0.470
Token was
Token ID373
Feature activation-5.77e-01

Pos logit contributions
 OUT+0.230
 arrest+0.224
 Johnson+0.220
joy+0.214
 Billy+0.208
Neg logit contributions
kin-0.180
ows-0.169
as-0.164
a-0.159
ily-0.158
Token amazed
Token ID24562
Feature activation-1.30e+00

Pos logit contributions
 OUT+0.058
 arrest+0.057
 Johnson+0.056
joy+0.054
 Billy+0.054
Neg logit contributions
kin-0.045
ows-0.041
as-0.039
ily-0.038
a-0.037
Token and
Token ID290
Feature activation+1.96e-01

Pos logit contributions
 OUT+0.120
 Johnson+0.120
joy+0.120
 Billy+0.119
 arrest+0.116
Neg logit contributions
kin-0.116
ows-0.103
as-0.096
ute-0.093
ily-0.093
Token she
Token ID673
Feature activation-9.32e-01

Pos logit contributions
kin+0.017
ows+0.016
as+0.015
ily+0.015
a+0.015
Neg logit contributions
 OUT-0.018
 arrest-0.018
 Johnson-0.017
joy-0.016
 Billy-0.016
TokenWhat
Token ID2061
Feature activation+7.23e-01

Pos logit contributions
kin+0.011
as+0.010
ily+0.010
a+0.010
ows+0.009
Neg logit contributions
 OUT-0.015
 arrest-0.015
 Johnson-0.014
joy-0.014
 Billy-0.014
Token do
Token ID466
Feature activation+1.11e+00

Pos logit contributions
kin+0.048
ows+0.043
as+0.042
ily+0.040
a+0.040
Neg logit contributions
 OUT-0.082
 arrest-0.080
 Johnson-0.079
joy-0.077
 Frankie-0.075
Token you
Token ID345
Feature activation+1.18e+00

Pos logit contributions
kin+0.089
ows+0.082
as+0.079
ily+0.075
ute+0.074
Neg logit contributions
 OUT-0.108
 arrest-0.107
 Johnson-0.104
 Billy-0.101
joy-0.100
Token think
Token ID892
Feature activation+4.49e-01

Pos logit contributions
kin+0.090
ows+0.081
as+0.079
ily+0.076
a+0.074
Neg logit contributions
 OUT-0.120
 arrest-0.119
 Johnson-0.117
joy-0.114
 Billy-0.111
Token you
Token ID345
Feature activation+1.18e+00

Pos logit contributions
kin+0.037
ows+0.034
as+0.033
ily+0.032
a+0.031
Neg logit contributions
 OUT-0.043
 arrest-0.042
 Johnson-0.042
joy-0.040
 Billy-0.040
Token're
Token ID821
Feature activation-2.81e+00

Pos logit contributions
kin+0.084
ows+0.079
as+0.076
a+0.072
ily+0.071
Neg logit contributions
 OUT-0.124
 arrest-0.122
 Johnson-0.122
joy-0.121
 Frankie-0.115
Token doing
Token ID1804
Feature activation-3.68e-01

Pos logit contributions
 arrest+0.194
 OUT+0.186
joy+0.184
 Johnson+0.179
istent+0.164
Neg logit contributions
kin-0.298
ows-0.281
ily-0.271
 holes-0.269
as-0.265
Token?"
Token ID1701
Feature activation+5.47e-01

Pos logit contributions
 OUT+0.036
 arrest+0.036
 Johnson+0.035
joy+0.034
 Frankie+0.033
Neg logit contributions
kin-0.029
ows-0.027
as-0.025
ily-0.025
ute-0.025
Token The
Token ID383
Feature activation-3.61e-01

Pos logit contributions
kin+0.054
ows+0.050
as+0.048
ily+0.048
a+0.047
Neg logit contributions
 OUT-0.043
 arrest-0.042
 Johnson-0.041
joy-0.040
 Billy-0.038
Token baby
Token ID5156
Feature activation-1.75e+00

Pos logit contributions
 OUT+0.028
 arrest+0.027
 Johnson+0.025
joy+0.025
istent+0.025
Neg logit contributions
kin-0.037
ows-0.033
as-0.033
ily-0.033
 holes-0.032
Token looked
Token ID3114
Feature activation+5.02e-01

Pos logit contributions
 arrest+0.187
 OUT+0.182
joy+0.175
istent+0.168
 Johnson+0.167
Neg logit contributions
kin-0.123
a-0.116
ows-0.112
as-0.110
ily-0.108
Token She
Token ID1375
Feature activation-7.38e-01

Pos logit contributions
 OUT+0.009
 arrest+0.009
 Johnson+0.009
joy+0.008
 Billy+0.008
Neg logit contributions
kin-0.010
ows-0.009
as-0.009
ily-0.008
a-0.008
Token said
Token ID531
Feature activation+1.80e-02

Pos logit contributions
 OUT+0.062
 arrest+0.061
 Johnson+0.060
 Billy+0.057
joy+0.057
Neg logit contributions
kin-0.070
ows-0.064
as-0.062
ute-0.060
ily-0.060
Token,
Token ID11
Feature activation-3.71e-01

Pos logit contributions
kin+0.002
ows+0.002
as+0.002
ute+0.002
ily+0.002
Neg logit contributions
 OUT-0.001
 arrest-0.001
 Johnson-0.001
joy-0.001
 Billy-0.001
Token "
Token ID366
Feature activation-3.60e-01

Pos logit contributions
 OUT+0.034
 arrest+0.033
 Johnson+0.032
joy+0.031
 Billy+0.030
Neg logit contributions
kin-0.033
ows-0.030
as-0.029
ily-0.028
a-0.027
TokenYou
Token ID1639
Feature activation+1.20e-01

Pos logit contributions
 OUT+0.038
 arrest+0.037
 Johnson+0.036
joy+0.035
 Billy+0.035
Neg logit contributions
kin-0.027
ows-0.024
as-0.024
ily-0.023
a-0.022
Token're
Token ID821
Feature activation-2.83e+00

Pos logit contributions
kin+0.009
ows+0.009
as+0.008
ily+0.008
a+0.008
Neg logit contributions
 OUT-0.012
 arrest-0.012
 Johnson-0.012
joy-0.011
 Billy-0.011
Token welcome
Token ID7062
Feature activation-1.09e+00

Pos logit contributions
 OUT+0.285
 Johnson+0.283
 arrest+0.279
 Billy+0.276
joy+0.271
Neg logit contributions
kin-0.216
ows-0.200
as-0.195
ute-0.187
a-0.178
Token,
Token ID11
Feature activation-5.70e-01

Pos logit contributions
 OUT+0.095
 arrest+0.093
 Johnson+0.090
joy+0.086
 Billy+0.085
Neg logit contributions
kin-0.100
ows-0.092
as-0.090
ily-0.088
a-0.086
Token my
Token ID616
Feature activation-5.30e-01

Pos logit contributions
 OUT+0.058
 arrest+0.057
 Johnson+0.055
joy+0.054
 Frankie+0.053
Neg logit contributions
kin-0.044
ows-0.039
as-0.039
ily-0.038
a-0.036
Token loves
Token ID10408
Feature activation-1.31e+00

Pos logit contributions
 OUT+0.046
 Johnson+0.046
joy+0.046
 arrest+0.045
 Billy+0.044
Neg logit contributions
kin-0.046
ows-0.044
as-0.042
ily-0.040
ute-0.039
Token.
Token ID13
Feature activation-2.93e-01

Pos logit contributions
 arrest+0.122
 OUT+0.121
 Johnson+0.119
joy+0.116
 Billy+0.114
Neg logit contributions
kin-0.110
ows-0.103
as-0.097
ute-0.095
ily-0.092
TokenSarah
Token ID29284
Feature activation-9.74e-01

Pos logit contributions
kin+0.070
as+0.066
ows+0.065
ily+0.065
a+0.064
Neg logit contributions
 OUT-0.047
 arrest-0.045
 Johnson-0.044
joy-0.042
 Frankie-0.041
Token remembered
Token ID12086
Feature activation+1.38e-01

Pos logit contributions
 OUT+0.096
 arrest+0.094
 Johnson+0.092
joy+0.090
 Frankie+0.087
Neg logit contributions
kin-0.079
ows-0.072
as-0.070
a-0.069
ily-0.067
Token that
Token ID326
Feature activation+8.40e-01

Pos logit contributions
kin+0.010
ily+0.009
ows+0.009
as+0.009
a+0.008
Neg logit contributions
 OUT-0.014
 arrest-0.014
 Johnson-0.014
istent-0.013
 Frankie-0.013
Token she
Token ID673
Feature activation-6.07e-01

Pos logit contributions
kin+0.075
ows+0.067
ily+0.065
as+0.065
 holes+0.064
Neg logit contributions
 OUT-0.077
 arrest-0.075
 Johnson-0.071
joy-0.069
istent-0.068
Token was
Token ID373
Feature activation-1.20e-01

Pos logit contributions
 OUT+0.061
 arrest+0.059
 Johnson+0.059
joy+0.056
 Frankie+0.055
Neg logit contributions
kin-0.048
ows-0.044
as-0.043
a-0.042
ily-0.042
Token supposed
Token ID4385
Feature activation-2.94e+00

Pos logit contributions
 OUT+0.011
 arrest+0.011
 Johnson+0.010
istent+0.010
joy+0.010
Neg logit contributions
kin-0.011
ily-0.010
ows-0.010
a-0.010
as-0.009
Token to
Token ID284
Feature activation-4.72e-01

Pos logit contributions
 OUT+0.317
 Johnson+0.300
 arrest+0.299
istent+0.297
joy+0.283
Neg logit contributions
kin-0.194
as-0.183
ows-0.177
ily-0.176
a-0.174
Token put
Token ID1234
Feature activation+3.58e-01

Pos logit contributions
 OUT+0.045
joy+0.044
 arrest+0.043
 Johnson+0.043
 Frankie+0.039
Neg logit contributions
kin-0.040
ows-0.035
as-0.034
ily-0.034
a-0.033
Token on
Token ID319
Feature activation+3.51e-01

Pos logit contributions
kin+0.030
as+0.028
ows+0.028
ia+0.026
ute+0.026
Neg logit contributions
 OUT-0.032
 Billy-0.031
 Johnson-0.031
 arrest-0.031
 Frankie-0.030
Token her
Token ID607
Feature activation+4.68e-01

Pos logit contributions
kin+0.030
ows+0.027
 holes+0.026
as+0.026
ily+0.026
Neg logit contributions
 OUT-0.033
 arrest-0.031
 Johnson-0.031
istent-0.030
joy-0.030
Token coat
Token ID13209
Feature activation-5.14e-01

Pos logit contributions
kin+0.036
ows+0.033
as+0.031
ily+0.030
ute+0.030
Neg logit contributions
 OUT-0.048
 arrest-0.047
 Johnson-0.046
joy-0.044
 Frankie-0.044
Token
Token ID241
Feature activation-5.28e-01

Pos logit contributions
 OUT+0.065
 Johnson+0.064
 arrest+0.064
joy+0.062
 Billy+0.060
Neg logit contributions
kin-0.071
ows-0.067
as-0.064
ily-0.063
ute-0.062
TokenYou
Token ID1639
Feature activation+1.99e-01

Pos logit contributions
 OUT+0.056
 arrest+0.055
 Johnson+0.053
 Billy+0.051
joy+0.051
Neg logit contributions
kin-0.038
ows-0.034
as-0.034
ily-0.033
a-0.032
Tokenâ
Token ID22940
Feature activation+5.50e-01

Pos logit contributions
kin+0.018
ows+0.016
as+0.016
ily+0.015
a+0.015
Neg logit contributions
 OUT-0.018
 arrest-0.018
 Johnson-0.018
joy-0.017
 Billy-0.016
Token
Token ID26391
Feature activation-6.12e-01

Pos logit contributions
kin+0.049
ows+0.045
as+0.045
ily+0.042
a+0.042
Neg logit contributions
 OUT-0.049
 arrest-0.047
 Johnson-0.047
joy-0.045
 Billy-0.045
Token
Token ID8151
Feature activation-1.72e+00

Pos logit contributions
 OUT+0.049
 Frankie+0.047
 arrest+0.047
 Johnson+0.047
 returning+0.045
Neg logit contributions
kin-0.059
ows-0.056
as-0.055
a-0.052
ily-0.050
Tokenre
Token ID260
Feature activation-2.95e+00

Pos logit contributions
 arrest+0.151
 OUT+0.148
joy+0.136
 Frankie+0.135
 returning+0.130
Neg logit contributions
kin-0.161
as-0.155
ows-0.154
a-0.147
ily-0.145
Token welcome
Token ID7062
Feature activation-9.90e-01

Pos logit contributions
 OUT+0.323
 arrest+0.318
 Johnson+0.313
joy+0.303
 Billy+0.298
Neg logit contributions
kin-0.205
ows-0.183
as-0.177
ily-0.170
a-0.165
Token!
Token ID0
Feature activation-7.69e-01

Pos logit contributions
 OUT+0.092
 arrest+0.092
 Johnson+0.086
istent+0.083
joy+0.082
Neg logit contributions
kin-0.084
ows-0.076
as-0.075
ily-0.074
a-0.073
Token Now
Token ID2735
Feature activation+2.23e-01

Pos logit contributions
 OUT+0.070
 arrest+0.070
 Johnson+0.067
joy+0.065
 Frankie+0.063
Neg logit contributions
kin-0.065
ows-0.060
as-0.059
ily-0.058
a-0.056
Token,
Token ID11
Feature activation-4.30e-01

Pos logit contributions
kin+0.019
ows+0.017
as+0.017
ily+0.017
a+0.016
Neg logit contributions
 OUT-0.021
 arrest-0.021
 Johnson-0.021
joy-0.020
istent-0.019
Token when
Token ID618
Feature activation-2.72e-01

Pos logit contributions
 OUT+0.041
 arrest+0.040
 Johnson+0.039
joy+0.038
 Billy+0.037
Neg logit contributions
kin-0.036
ows-0.033
as-0.032
ily-0.031
a-0.030