TOP ACTIVATIONS
MAX = 0.301

the ambulance he saw a paramed ic wearing a big coat
, she noticed a little chip m unk sc ur rying
and wearing gloves . The paramed ic was very polite and
around . Suddenly , the chip m unk stopped and looked
after that . Whenever the chip m unk needed help ,
you ". The chip m unk and Sam were
L ily asked the paramed ic , " Is the
. The driver and the paramed ic jumped out . They
to be okay ?" The paramed ic smiled and said ,
was so clever of the chip m unk to hide from
a big jar of chocolate chip cookies hidden inside . Both
a special treat for the chip m unk . She said
place ! The chip mun ks didn 't know
!" The chip m unk finished the treat
. It was a small chip m unk ! The princess
boy finally understood why the chip m unk had been so
bird . Luckily , the chip m unk said they should
chip m unk ! The chip m unk said to Sally
frog agreed , and the chip m unk agreed too .
animal . It was a chip m unk ! The chip

MIN ACTIVATIONS
MIN = -0.318

is inside . <|endoftext|> One day , a boy named Tim
opl ane . <|endoftext|> One day , a turkey had an
did it !" <|endoftext|> One day , Tim my went to
their faces . <|endoftext|> One day , Mum was looking at
girl named Lily . One day , she went to the
girl named Lily . One day , Lily went outside to
girl named Lily . One day , Lily 's mom asked
good friends . <|endoftext|> One day , a little girl named
big hug . <|endoftext|> One day , there was a slow
are happy . <|endoftext|> One day , Ben and Lily went
cold winter snow . One day , she went outside to
her heart . <|endoftext|> One day , a huge human was
girl named Lily . One day , she was playing outside
girl named Lily . One day , Lily went to the
her face . <|endoftext|> One day , a little boy 's
cars and trucks . One day , Tim my 's mom
the swings . <|endoftext|> One day , Little Billy was feeling
a smile . <|endoftext|> One day , m ama and her
much fun ." <|endoftext|> One day , Ken and his Mom
toys and books . One day , Lily has a new

INTERVAL 0.146 - 0.301
CONTAINS 2.129%

man didn 't like to fight and he tried to get
, I want that glass !" Mom my said
want to play with me ?" asked Lily .
happy that she said , " Thank you for answering our
Jimmy had an idea . " Mom my , I know

INTERVAL -0.009 - 0.146
CONTAINS 54.134%

was about to happen ! When the painting was
!" Dog bark ed , as if to say
. She learned that the clown was not scary . He
and saw lots of tasty cakes . He wanted one of
was a little boy named Tim my . Tim my loved

INTERVAL -0.163 - -0.009
CONTAINS 41.517%

said that the other team couldn 't join . They said
she loved to peek . She would peek in the trees
, Lily started to feel dizz y from lifting Mitt ens
and walked until she was very tired . She was strong
at all the buttons and lights . They are incredible ,"

INTERVAL -0.318 - -0.163
CONTAINS 2.219%

in trouble again . <|endoftext|> Once upon a time there were
together . One day , she and her
strongest . So , every day he would wake up early
her way . <|endoftext|> Once upon a time , there was
played together until it was time to go home .
Token the
Token ID262
Feature activation+4.90e-02

Pos logit contributions
 day+0.061
 night+0.060
 time+0.058
 nights+0.058
 morning+0.057
Neg logit contributions
boys-0.046
 paramed-0.045
 chefs-0.043
 Lee-0.040
 groom-0.039
Token ambulance
Token ID22536
Feature activation+1.29e-01

Pos logit contributions
 paramed+0.063
boys+0.061
 chefs+0.059
 Lee+0.058
 printer+0.056
Neg logit contributions
 day-0.091
 nights-0.091
 night-0.089
fy-0.086
 time-0.085
Token he
Token ID339
Feature activation-9.85e-02

Pos logit contributions
boys+0.214
 paramed+0.214
 chefs+0.210
 Lee+0.200
 groom+0.195
Neg logit contributions
 day-0.194
 night-0.190
 nights-0.186
 morning-0.180
 afternoon-0.176
Token saw
Token ID2497
Feature activation+6.98e-02

Pos logit contributions
 day+0.201
 night+0.199
 nights+0.196
 morning+0.190
 time+0.190
Neg logit contributions
 paramed-0.114
boys-0.112
 chefs-0.108
 Lee-0.105
 reporter-0.096
Token a
Token ID257
Feature activation+3.92e-02

Pos logit contributions
boys+0.102
 paramed+0.101
 chefs+0.095
 Lee+0.093
 groom+0.089
Neg logit contributions
 day-0.123
 night-0.121
 nights-0.119
 time-0.115
 morning-0.114
Token paramed
Token ID34581
Feature activation+3.01e-01

Pos logit contributions
boys+0.072
 chefs+0.067
 Lee+0.065
 wrists+0.065
oa+0.062
Neg logit contributions
 day-0.061
 time-0.057
 night-0.057
 morning-0.053
 evening-0.051
Tokenic
Token ID291
Feature activation+5.17e-02

Pos logit contributions
boys+0.591
 paramed+0.582
 chefs+0.574
 Lee+0.566
 printer+0.539
Neg logit contributions
 day-0.361
 night-0.353
 nights-0.352
 morning-0.327
 afternoon-0.326
Token wearing
Token ID5762
Feature activation-1.00e-01

Pos logit contributions
 paramed+0.107
boys+0.105
 chefs+0.103
 Lee+0.102
 printer+0.099
Neg logit contributions
 nights-0.055
 day-0.055
 night-0.054
fy-0.051
 Along-0.050
Token a
Token ID257
Feature activation+3.77e-02

Pos logit contributions
 day+0.175
 night+0.171
 time+0.169
 nights+0.164
 morning+0.164
Neg logit contributions
boys-0.151
 paramed-0.144
 chefs-0.143
 Lee-0.138
 principal-0.132
Token big
Token ID1263
Feature activation-1.56e-02

Pos logit contributions
boys+0.072
 chefs+0.067
 Lee+0.067
 paramed+0.063
 principal+0.062
Neg logit contributions
 day-0.055
 time-0.054
 night-0.052
 morning-0.050
fy-0.049
Token coat
Token ID13209
Feature activation-3.51e-02

Pos logit contributions
 day+0.026
 time+0.025
 night+0.025
 morning+0.024
 evening+0.023
Neg logit contributions
boys-0.028
 chefs-0.027
 principal-0.024
 Lee-0.023
oa-0.023
Token,
Token ID11
Feature activation+1.14e-01

Pos logit contributions
boys+0.044
 Lee+0.039
 paramed+0.039
 chefs+0.037
 groom+0.037
Neg logit contributions
 nights-0.054
fy-0.052
 day-0.052
 night-0.051
 afternoon-0.051
Token she
Token ID673
Feature activation-9.79e-02

Pos logit contributions
boys+0.188
 paramed+0.184
 chefs+0.180
 Lee+0.172
 principal+0.170
Neg logit contributions
 day-0.180
 night-0.179
 nights-0.172
 morning-0.169
 time-0.163
Token noticed
Token ID6810
Feature activation+1.01e-01

Pos logit contributions
 night+0.173
 day+0.172
 nights+0.170
 time+0.160
 morning+0.160
Neg logit contributions
 paramed-0.144
 chefs-0.139
boys-0.135
 Lee-0.134
 principal-0.123
Token a
Token ID257
Feature activation+5.24e-02

Pos logit contributions
 paramed+0.137
boys+0.136
 chefs+0.133
 Lee+0.130
 principal+0.123
Neg logit contributions
 day-0.186
 night-0.184
 nights-0.180
 morning-0.174
 time-0.173
Token little
Token ID1310
Feature activation-4.54e-02

Pos logit contributions
 chefs+0.102
boys+0.101
 Lee+0.100
 paramed+0.096
 principal+0.093
Neg logit contributions
 day-0.072
 night-0.067
 time-0.066
 morning-0.061
 evening-0.060
Token chip
Token ID11594
Feature activation+2.99e-01

Pos logit contributions
 day+0.077
 night+0.076
 morning+0.071
 nights+0.069
 afternoon+0.068
Neg logit contributions
 paramed-0.069
boys-0.068
 chefs-0.068
 principal-0.066
 Lee-0.066
Tokenm
Token ID76
Feature activation-1.17e-02

Pos logit contributions
 paramed+0.526
boys+0.520
 chefs+0.508
 Lee+0.502
 principal+0.491
Neg logit contributions
 day-0.441
 night-0.420
 nights-0.412
 afternoon-0.395
 morning-0.393
Tokenunk
Token ID2954
Feature activation+1.10e-01

Pos logit contributions
 day+0.019
 night+0.019
 nights+0.019
 morning+0.018
 afternoon+0.018
Neg logit contributions
boys-0.018
 paramed-0.018
 chefs-0.017
 Lee-0.017
 printer-0.016
Token sc
Token ID629
Feature activation-1.09e-02

Pos logit contributions
boys+0.176
 paramed+0.175
 chefs+0.171
 Lee+0.167
 principal+0.159
Neg logit contributions
 day-0.170
 night-0.166
 nights-0.164
 morning-0.157
 time-0.156
Tokenur
Token ID333
Feature activation-1.02e-01

Pos logit contributions
 day+0.012
 night+0.012
 nights+0.012
 morning+0.011
 time+0.011
Neg logit contributions
boys-0.022
 paramed-0.022
 chefs-0.022
 Lee-0.021
 principal-0.020
Tokenrying
Token ID14992
Feature activation-5.25e-02

Pos logit contributions
 nights+0.102
 day+0.102
 night+0.099
 afternoon+0.090
ie+0.090
Neg logit contributions
 paramed-0.217
 Lee-0.209
boys-0.207
 chefs-0.206
 printer-0.203
Token and
Token ID290
Feature activation-1.06e-02

Pos logit contributions
boys+0.205
 paramed+0.203
 Lee+0.196
 chefs+0.195
 printer+0.191
Neg logit contributions
 nights-0.101
 night-0.097
 day-0.097
 afternoon-0.090
 morning-0.090
Token wearing
Token ID5762
Feature activation-1.01e-01

Pos logit contributions
 day+0.019
 night+0.019
 nights+0.018
 morning+0.018
 time+0.017
Neg logit contributions
boys-0.015
 paramed-0.015
 chefs-0.014
 Lee-0.014
 reporter-0.013
Token gloves
Token ID18051
Feature activation+1.69e-02

Pos logit contributions
 day+0.171
 night+0.169
 nights+0.165
 time+0.165
 morning+0.161
Neg logit contributions
boys-0.152
 paramed-0.149
 chefs-0.144
 Lee-0.143
 principal-0.138
Token.
Token ID13
Feature activation-2.14e-03

Pos logit contributions
boys+0.034
 paramed+0.034
 chefs+0.033
 Lee+0.033
 principal+0.031
Neg logit contributions
 day-0.019
 night-0.019
 nights-0.018
 morning-0.017
 time-0.017
Token The
Token ID383
Feature activation+4.51e-02

Pos logit contributions
 day+0.003
 nights+0.003
 night+0.003
 afternoon+0.003
 morning+0.003
Neg logit contributions
boys-0.004
 paramed-0.004
 chefs-0.004
 Lee-0.004
 principal-0.003
Token paramed
Token ID34581
Feature activation+2.98e-01

Pos logit contributions
boys+0.047
 chefs+0.040
 wrists+0.038
 Lee+0.038
 reporter+0.035
Neg logit contributions
 day-0.104
 night-0.100
 morning-0.098
 nights-0.097
 time-0.097
Tokenic
Token ID291
Feature activation+4.89e-02

Pos logit contributions
boys+0.614
 chefs+0.598
 paramed+0.593
 Lee+0.587
 groom+0.564
Neg logit contributions
 day-0.334
 nights-0.328
 night-0.323
 afternoon-0.301
 morning-0.297
Token was
Token ID373
Feature activation+3.58e-02

Pos logit contributions
boys+0.085
 chefs+0.081
 paramed+0.079
 Lee+0.079
 principal+0.075
Neg logit contributions
 day-0.074
 night-0.071
 nights-0.071
 time-0.067
 morning-0.067
Token very
Token ID845
Feature activation-1.93e-02

Pos logit contributions
boys+0.058
 Lee+0.055
 paramed+0.055
 chefs+0.055
 principal+0.052
Neg logit contributions
 day-0.058
 night-0.057
 nights-0.056
 time-0.055
 morning-0.054
Token polite
Token ID23507
Feature activation+6.41e-02

Pos logit contributions
 day+0.030
 night+0.030
 nights+0.030
 morning+0.028
 afternoon+0.028
Neg logit contributions
boys-0.031
 paramed-0.031
 chefs-0.030
 Lee-0.029
 reporter-0.028
Token and
Token ID290
Feature activation-9.60e-03

Pos logit contributions
boys+0.103
 paramed+0.101
 chefs+0.100
 Lee+0.100
 reporter+0.093
Neg logit contributions
 day-0.097
 nights-0.096
 night-0.096
 morning-0.091
 afternoon-0.091
Token around
Token ID1088
Feature activation-3.68e-02

Pos logit contributions
 day+0.062
 nights+0.062
 night+0.061
 morning+0.057
 afternoon+0.056
Neg logit contributions
boys-0.103
 paramed-0.101
 chefs-0.098
 Lee-0.098
 printer-0.093
Token.
Token ID13
Feature activation+7.35e-03

Pos logit contributions
 day+0.055
 night+0.054
 nights+0.053
 morning+0.051
 time+0.051
Neg logit contributions
boys-0.062
 paramed-0.062
 chefs-0.060
 Lee-0.059
 principal-0.056
Token Suddenly
Token ID24975
Feature activation-4.68e-02

Pos logit contributions
boys+0.014
 paramed+0.013
 chefs+0.013
 groom+0.012
 reporter+0.012
Neg logit contributions
 day-0.010
 night-0.010
 nights-0.009
 Along-0.009
 morning-0.009
Token,
Token ID11
Feature activation+1.09e-01

Pos logit contributions
 night+0.063
 day+0.062
 nights+0.061
 time+0.058
 morning+0.058
Neg logit contributions
boys-0.087
 paramed-0.086
 chefs-0.085
 principal-0.083
 reporter-0.081
Token the
Token ID262
Feature activation+5.32e-02

Pos logit contributions
boys+0.203
 paramed+0.194
 chefs+0.192
 Lee+0.185
 principal+0.184
Neg logit contributions
 day-0.149
 night-0.149
 nights-0.142
 morning-0.139
 time-0.135
Token chip
Token ID11594
Feature activation+2.97e-01

Pos logit contributions
boys+0.079
 paramed+0.075
 chefs+0.075
 Lee+0.073
 reporter+0.071
Neg logit contributions
 day-0.094
 night-0.091
 nights-0.089
 morning-0.087
 time-0.086
Tokenm
Token ID76
Feature activation-1.48e-02

Pos logit contributions
boys+0.558
 paramed+0.550
 chefs+0.545
 Lee+0.540
 principal+0.534
Neg logit contributions
 day-0.410
 night-0.371
 nights-0.366
 afternoon-0.365
 morning-0.356
Tokenunk
Token ID2954
Feature activation+1.08e-01

Pos logit contributions
 day+0.028
 night+0.027
 nights+0.027
 morning+0.026
 afternoon+0.026
Neg logit contributions
 paramed-0.019
boys-0.019
 chefs-0.018
 Lee-0.018
 printer-0.016
Token stopped
Token ID5025
Feature activation+6.29e-03

Pos logit contributions
boys+0.148
 paramed+0.146
 chefs+0.141
 Lee+0.138
 printer+0.129
Neg logit contributions
 day-0.194
 night-0.191
 nights-0.190
 morning-0.182
 time-0.181
Token and
Token ID290
Feature activation+2.18e-03

Pos logit contributions
boys+0.010
 paramed+0.010
 chefs+0.010
 Lee+0.010
 principal+0.009
Neg logit contributions
 day-0.009
 night-0.009
 nights-0.009
 morning-0.009
 time-0.009
Token looked
Token ID3114
Feature activation+1.76e-02

Pos logit contributions
 chefs+0.004
boys+0.004
 paramed+0.003
 principal+0.003
 Lee+0.003
Neg logit contributions
 night-0.003
 day-0.003
 morning-0.003
 nights-0.003
 evening-0.003
Token after
Token ID706
Feature activation-3.92e-02

Pos logit contributions
boys+0.054
 paramed+0.053
 chefs+0.052
 Lee+0.052
 reporter+0.049
Neg logit contributions
 day-0.039
 night-0.038
 nights-0.038
 morning-0.036
 afternoon-0.035
Token that
Token ID326
Feature activation+6.83e-02

Pos logit contributions
 day+0.068
 nights+0.067
 night+0.067
fy+0.066
 morning+0.064
Neg logit contributions
boys-0.055
 paramed-0.053
 chefs-0.052
 Lee-0.051
 printer-0.048
Token.
Token ID13
Feature activation-1.87e-03

Pos logit contributions
boys+0.143
 paramed+0.136
 Lee+0.136
 chefs+0.134
 printer+0.132
Neg logit contributions
 nights-0.068
fy-0.066
 night-0.064
 Along-0.064
 day-0.063
Token Whenever
Token ID21326
Feature activation-9.91e-02

Pos logit contributions
 nights+0.003
 day+0.003
 night+0.003
fy+0.003
 afternoon+0.003
Neg logit contributions
boys-0.003
 paramed-0.003
 Lee-0.003
 chefs-0.002
 principal-0.002
Token the
Token ID262
Feature activation+5.85e-02

Pos logit contributions
 day+0.197
 night+0.192
 time+0.185
 nights+0.185
 morning+0.183
Neg logit contributions
 paramed-0.140
boys-0.128
 chefs-0.121
 groom-0.118
 wrists-0.118
Token chip
Token ID11594
Feature activation+2.97e-01

Pos logit contributions
boys+0.072
 Lee+0.065
 reporter+0.065
 paramed+0.064
 chefs+0.062
Neg logit contributions
 day-0.126
 night-0.119
 morning-0.117
 time-0.116
 afternoon-0.115
Tokenm
Token ID76
Feature activation-1.43e-02

Pos logit contributions
boys+0.560
 paramed+0.542
 wrists+0.533
 reporter+0.531
 groom+0.530
Neg logit contributions
 day-0.427
 night-0.377
 afternoon-0.370
 morning-0.370
 nights-0.353
Tokenunk
Token ID2954
Feature activation+1.10e-01

Pos logit contributions
 day+0.026
 night+0.025
 nights+0.025
 time+0.024
 morning+0.024
Neg logit contributions
boys-0.020
 paramed-0.019
 chefs-0.019
 Lee-0.018
 reporter-0.018
Token needed
Token ID2622
Feature activation-1.90e-02

Pos logit contributions
boys+0.152
 paramed+0.150
 chefs+0.145
 Lee+0.143
 reporter+0.133
Neg logit contributions
 day-0.195
 night-0.192
 nights-0.190
 morning-0.182
 time-0.181
Token help
Token ID1037
Feature activation+6.93e-02

Pos logit contributions
 day+0.033
 night+0.032
 nights+0.032
 time+0.032
 morning+0.031
Neg logit contributions
boys-0.029
 paramed-0.028
 Lee-0.027
 chefs-0.027
 principal-0.026
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
 paramed+0.117
boys+0.116
 chefs+0.113
 Lee+0.111
 reporter+0.106
Neg logit contributions
 day-0.104
 night-0.101
 nights-0.100
 time-0.096
 morning-0.095
Token you
Token ID345
Feature activation-5.87e-02

Pos logit contributions
 paramed+0.119
boys+0.107
 chefs+0.107
 reporter+0.103
 Lee+0.103
Neg logit contributions
 day-0.074
 night-0.071
 time-0.069
 nights-0.069
 morning-0.066
Token".
Token ID1911
Feature activation+1.81e-01

Pos logit contributions
 day+0.089
 night+0.087
 nights+0.087
 morning+0.082
 afternoon+0.082
Neg logit contributions
boys-0.097
 paramed-0.095
 chefs-0.093
 Lee-0.091
 groom-0.086
Token
Token ID198
Feature activation+2.38e-02

Pos logit contributions
boys+0.298
 paramed+0.294
 chefs+0.285
 Lee+0.284
 principal+0.267
Neg logit contributions
 day-0.275
 night-0.270
 nights-0.270
 morning-0.255
 time-0.254
Token
Token ID198
Feature activation+2.38e-02

Pos logit contributions
boys+0.041
 paramed+0.041
 chefs+0.039
 Lee+0.039
 principal+0.037
Neg logit contributions
 day-0.034
 nights-0.034
 night-0.033
fy-0.031
 morning-0.031
TokenThe
Token ID464
Feature activation+1.57e-02

Pos logit contributions
boys+0.033
 paramed+0.033
 chefs+0.033
 Lee+0.032
 groom+0.030
Neg logit contributions
 day-0.042
 nights-0.041
 night-0.041
 afternoon-0.040
 time-0.039
Token chip
Token ID11594
Feature activation+2.95e-01

Pos logit contributions
boys+0.024
 Lee+0.022
 chefs+0.022
 reporter+0.022
 paramed+0.021
Neg logit contributions
 day-0.030
 night-0.028
 time-0.027
 morning-0.027
 afternoon-0.027
Tokenm
Token ID76
Feature activation-1.54e-02

Pos logit contributions
boys+0.591
 paramed+0.568
 chefs+0.559
 groom+0.559
 Lee+0.557
Neg logit contributions
 day-0.397
 night-0.345
 afternoon-0.345
 morning-0.337
 nights-0.325
Tokenunk
Token ID2954
Feature activation+1.07e-01

Pos logit contributions
 day+0.027
 night+0.026
 nights+0.026
 time+0.026
 morning+0.025
Neg logit contributions
boys-0.022
 paramed-0.021
 chefs-0.020
 Lee-0.020
 reporter-0.020
Token and
Token ID290
Feature activation-6.85e-03

Pos logit contributions
 paramed+0.147
boys+0.147
 chefs+0.146
 Lee+0.140
 reporter+0.131
Neg logit contributions
 day-0.192
 night-0.188
 nights-0.186
 morning-0.180
 time-0.178
Token Sam
Token ID3409
Feature activation+5.93e-02

Pos logit contributions
 day+0.014
 night+0.013
 afternoon+0.013
 nights+0.012
 morning+0.012
Neg logit contributions
 paramed-0.009
 chefs-0.009
 reporter-0.009
boys-0.009
 principal-0.008
Token were
Token ID547
Feature activation+2.52e-02

Pos logit contributions
boys+0.082
 paramed+0.081
 chefs+0.078
 Lee+0.076
 printer+0.071
Neg logit contributions
 day-0.106
 night-0.104
 nights-0.104
 morning-0.099
 afternoon-0.099
Token
Token ID198
Feature activation-4.52e-03

Pos logit contributions
 day+0.004
 night+0.004
 nights+0.004
 morning+0.003
 time+0.003
Neg logit contributions
boys-0.005
 paramed-0.005
 chefs-0.005
 Lee-0.004
 groom-0.004
TokenL
Token ID43
Feature activation-4.12e-02

Pos logit contributions
 day+0.008
 nights+0.008
 night+0.008
 afternoon+0.007
 time+0.007
Neg logit contributions
boys-0.007
 paramed-0.006
 Lee-0.006
 chefs-0.006
 groom-0.006
Tokenily
Token ID813
Feature activation-2.62e-04

Pos logit contributions
 night+0.077
 nights+0.076
 day+0.075
fy+0.074
 morning+0.073
Neg logit contributions
 chefs-0.055
 paramed-0.050
boys-0.049
 principal-0.047
 Lee-0.047
Token asked
Token ID1965
Feature activation+4.20e-02

Pos logit contributions
 day+0.000
 night+0.000
 nights+0.000
ie+0.000
 time+0.000
Neg logit contributions
 chefs-0.001
 bluff-0.001
 paramed-0.001
 liar-0.001
 Lee-0.001
Token the
Token ID262
Feature activation+3.55e-02

Pos logit contributions
 wrists+0.080
 groom+0.078
 reporter+0.076
 paramed+0.075
boys+0.074
Neg logit contributions
 day-0.060
 night-0.059
ie-0.056
 morning-0.054
 time-0.054
Token paramed
Token ID34581
Feature activation+2.93e-01

Pos logit contributions
boys+0.045
 wrists+0.045
 chefs+0.041
 ah+0.038
 Lee+0.038
Neg logit contributions
 day-0.074
 time-0.071
 night-0.069
 morning-0.069
 nights-0.066
Tokenic
Token ID291
Feature activation+4.09e-02

Pos logit contributions
boys+0.583
 chefs+0.569
 Lee+0.560
 paramed+0.557
 groom+0.543
Neg logit contributions
 day-0.337
 nights-0.329
 night-0.322
 afternoon-0.303
fy-0.295
Token,
Token ID11
Feature activation+8.12e-02

Pos logit contributions
boys+0.082
 chefs+0.078
 paramed+0.077
 wrists+0.076
 Lee+0.076
Neg logit contributions
 day-0.051
 night-0.048
 nights-0.046
 morning-0.045
 time-0.045
Token "
Token ID366
Feature activation+2.19e-01

Pos logit contributions
boys+0.122
 wrists+0.105
 chefs+0.101
 principal+0.098
 reporter+0.095
Neg logit contributions
 day-0.153
 Along-0.144
 morning-0.142
 night-0.141
 time-0.140
TokenIs
Token ID3792
Feature activation+4.73e-02

Pos logit contributions
boys+0.289
 Lee+0.274
 wrists+0.272
 chefs+0.256
 liar+0.255
Neg logit contributions
 day-0.386
 nights-0.378
 night-0.372
 morning-0.360
 afternoon-0.357
Token the
Token ID262
Feature activation+3.55e-02

Pos logit contributions
 paramed+0.071
boys+0.068
 chefs+0.067
 Lee+0.067
 reporter+0.065
Neg logit contributions
 day-0.082
 night-0.081
 nights-0.078
 time-0.077
 morning-0.076
Token.
Token ID13
Feature activation-4.08e-02

Pos logit contributions
 day+0.015
 night+0.015
 nights+0.014
 time+0.014
 morning+0.014
Neg logit contributions
boys-0.027
 paramed-0.027
 chefs-0.026
 Lee-0.026
 principal-0.025
Token The
Token ID383
Feature activation+3.53e-02

Pos logit contributions
 night+0.069
 day+0.069
 time+0.068
 morning+0.067
 nights+0.066
Neg logit contributions
boys-0.064
 paramed-0.059
 chefs-0.056
 groom-0.054
 dads-0.053
Token driver
Token ID4639
Feature activation+9.14e-02

Pos logit contributions
boys+0.048
 chefs+0.045
 Lee+0.044
 paramed+0.044
 wrists+0.041
Neg logit contributions
 day-0.067
 night-0.066
 nights-0.064
 time-0.063
 morning-0.063
Token and
Token ID290
Feature activation-4.16e-02

Pos logit contributions
boys+0.128
 paramed+0.127
 chefs+0.126
 Lee+0.121
 groom+0.115
Neg logit contributions
 day-0.159
 night-0.157
 nights-0.155
 time-0.151
 morning-0.147
Token the
Token ID262
Feature activation+3.26e-02

Pos logit contributions
 night+0.075
 day+0.072
 morning+0.071
 time+0.069
 nights+0.069
Neg logit contributions
boys-0.061
 paramed-0.060
 chefs-0.053
Fighting-0.052
 Lincoln-0.052
Token paramed
Token ID34581
Feature activation+2.91e-01

Pos logit contributions
boys+0.046
 chefs+0.044
 Lee+0.043
 paramed+0.042
 reporter+0.040
Neg logit contributions
 day-0.060
 night-0.058
 nights-0.057
 time-0.056
 morning-0.055
Tokenic
Token ID291
Feature activation+3.80e-02

Pos logit contributions
boys+0.542
 paramed+0.532
 chefs+0.525
 Lee+0.516
 groom+0.494
Neg logit contributions
 day-0.380
 night-0.372
 nights-0.371
 morning-0.346
 afternoon-0.346
Token jumped
Token ID11687
Feature activation-9.98e-02

Pos logit contributions
 paramed+0.060
boys+0.060
 chefs+0.058
 Lee+0.057
 reporter+0.054
Neg logit contributions
 day-0.059
 night-0.058
 nights-0.058
 morning-0.055
 afternoon-0.055
Token out
Token ID503
Feature activation-3.63e-02

Pos logit contributions
 nights+0.142
 day+0.142
 night+0.137
 afternoon+0.132
 morning+0.130
Neg logit contributions
boys-0.174
 paramed-0.170
 chefs-0.166
 Lee-0.165
 printer-0.154
Token.
Token ID13
Feature activation-3.46e-02

Pos logit contributions
fy+0.034
 nights+0.033
 day+0.033
found+0.032
 afternoon+0.032
Neg logit contributions
 paramed-0.076
 chefs-0.076
 Lee-0.076
boys-0.075
 reporter-0.071
Token They
Token ID1119
Feature activation+3.42e-02

Pos logit contributions
 night+0.052
 day+0.051
 nights+0.050
 time+0.049
 morning+0.049
Neg logit contributions
boys-0.060
 paramed-0.058
 chefs-0.055
 groom-0.054
 Lee-0.053
Token to
Token ID284
Feature activation+6.41e-02

Pos logit contributions
 day+0.170
 night+0.167
 nights+0.163
 morning+0.158
 time+0.157
Neg logit contributions
boys-0.190
 paramed-0.189
 chefs-0.183
 Lee-0.181
 reporter-0.174
Token be
Token ID307
Feature activation+7.65e-02

Pos logit contributions
boys+0.091
 Lee+0.089
 chefs+0.088
 paramed+0.087
 reporter+0.085
Neg logit contributions
 day-0.115
 night-0.113
 time-0.108
 nights-0.107
 morning-0.107
Token okay
Token ID8788
Feature activation+4.30e-02

Pos logit contributions
boys+0.118
 Lee+0.117
 paramed+0.115
 reporter+0.111
 principal+0.110
Neg logit contributions
 day-0.126
 night-0.124
 nights-0.123
 time-0.122
 morning-0.118
Token?"
Token ID1701
Feature activation+1.58e-01

Pos logit contributions
 wrists+0.070
boys+0.066
 paramed+0.066
 reporter+0.063
 tripod+0.062
Neg logit contributions
 day-0.073
 time-0.069
 night-0.068
ie-0.066
 of-0.066
Token The
Token ID383
Feature activation+3.21e-02

Pos logit contributions
boys+0.310
 chefs+0.308
 groom+0.295
 liar+0.288
 paramed+0.286
Neg logit contributions
 day-0.210
 morning-0.198
 night-0.197
 Along-0.191
 evening-0.178
Token paramed
Token ID34581
Feature activation+2.90e-01

Pos logit contributions
boys+0.040
 wrists+0.038
 chefs+0.036
 Lee+0.033
 ah+0.031
Neg logit contributions
 day-0.068
 night-0.063
 morning-0.063
 time-0.063
 nights-0.060
Tokenic
Token ID291
Feature activation+3.81e-02

Pos logit contributions
boys+0.614
 chefs+0.595
 Lee+0.586
 paramed+0.577
 groom+0.572
Neg logit contributions
 day-0.306
 nights-0.294
 night-0.290
 afternoon-0.274
 morning-0.264
Token smiled
Token ID13541
Feature activation+2.20e-02

Pos logit contributions
boys+0.064
 chefs+0.061
 Lee+0.059
 wrists+0.056
 paramed+0.056
Neg logit contributions
 day-0.061
 night-0.057
 nights-0.056
ie-0.055
 time-0.055
Token and
Token ID290
Feature activation-3.31e-02

Pos logit contributions
boys+0.037
 paramed+0.037
 chefs+0.036
 Lee+0.035
 printer+0.033
Neg logit contributions
 day-0.033
 night-0.032
 nights-0.032
 morning-0.030
 time-0.030
Token said
Token ID531
Feature activation+1.08e-02

Pos logit contributions
 day+0.050
 night+0.049
 morning+0.047
 nights+0.045
 evening+0.045
Neg logit contributions
 principal-0.058
boys-0.057
 jury-0.055
 chefs-0.054
 liar-0.054
Token,
Token ID11
Feature activation+7.72e-02

Pos logit contributions
boys+0.025
 principal+0.024
 chefs+0.024
 wrists+0.023
 reporter+0.023
Neg logit contributions
 day-0.010
 morning-0.009
 night-0.009
ly-0.009
 time-0.009
Token was
Token ID373
Feature activation+3.77e-02

Pos logit contributions
 paramed+0.105
 Lee+0.100
 chefs+0.099
boys+0.099
 principal+0.097
Neg logit contributions
 day-0.097
 night-0.096
 nights-0.092
 time-0.091
 morning-0.090
Token so
Token ID523
Feature activation+1.72e-02

Pos logit contributions
 paramed+0.060
boys+0.059
 Lee+0.057
 chefs+0.056
 principal+0.055
Neg logit contributions
 day-0.063
 time-0.062
 night-0.062
 nights-0.059
 morning-0.058
Token clever
Token ID14169
Feature activation+4.60e-02

Pos logit contributions
 paramed+0.027
boys+0.027
 chefs+0.026
 Lee+0.025
 printer+0.024
Neg logit contributions
 nights-0.027
 day-0.026
 night-0.026
 morning-0.025
 afternoon-0.025
Token of
Token ID286
Feature activation-9.28e-02

Pos logit contributions
boys+0.067
 chefs+0.064
 paramed+0.064
 Lee+0.062
 printer+0.058
Neg logit contributions
 day-0.077
 nights-0.077
 night-0.076
 afternoon-0.073
 morning-0.073
Token the
Token ID262
Feature activation+4.92e-02

Pos logit contributions
 day+0.138
 night+0.134
 nights+0.132
 time+0.128
 morning+0.126
Neg logit contributions
 paramed-0.165
boys-0.161
 Lee-0.154
 chefs-0.153
 principal-0.148
Token chip
Token ID11594
Feature activation+2.89e-01

Pos logit contributions
boys+0.058
 paramed+0.053
 Lee+0.053
 reporter+0.051
 chefs+0.051
Neg logit contributions
 day-0.107
 night-0.101
 time-0.099
 morning-0.099
 afternoon-0.097
Tokenm
Token ID76
Feature activation-2.21e-02

Pos logit contributions
 paramed+0.495
boys+0.491
 Lee+0.467
 principal+0.462
 wrists+0.462
Neg logit contributions
 day-0.452
 night-0.415
 nights-0.400
 morning-0.399
 afternoon-0.398
Tokenunk
Token ID2954
Feature activation+1.02e-01

Pos logit contributions
 day+0.036
 night+0.035
 time+0.034
 nights+0.034
 morning+0.033
Neg logit contributions
boys-0.035
 paramed-0.033
 chefs-0.032
 Lee-0.032
 reporter-0.031
Token to
Token ID284
Feature activation+7.73e-02

Pos logit contributions
boys+0.164
 paramed+0.162
 chefs+0.157
 Lee+0.155
 printer+0.146
Neg logit contributions
 day-0.159
 night-0.156
 nights-0.156
 morning-0.148
 afternoon-0.147
Token hide
Token ID7808
Feature activation+4.02e-02

Pos logit contributions
 paramed+0.119
boys+0.119
 chefs+0.118
 Lee+0.114
 printer+0.108
Neg logit contributions
 day-0.129
 night-0.127
 time-0.122
 morning-0.120
 nights-0.118
Token from
Token ID422
Feature activation+1.69e-02

Pos logit contributions
 paramed+0.073
boys+0.070
 Lee+0.067
 principal+0.067
 reporter+0.067
Neg logit contributions
 day-0.056
 night-0.055
 nights-0.055
 time-0.052
fy-0.051
Token a
Token ID257
Feature activation+4.69e-02

Pos logit contributions
 paramed+0.062
boys+0.061
 Lee+0.059
 chefs+0.057
 reporter+0.057
Neg logit contributions
 day-0.078
 night-0.078
 nights-0.076
 time-0.073
 morning-0.073
Token big
Token ID1263
Feature activation-4.67e-03

Pos logit contributions
boys+0.092
 Lee+0.087
 paramed+0.086
 chefs+0.084
 wrists+0.083
Neg logit contributions
 day-0.065
 night-0.061
 time-0.060
 morning-0.056
 afternoon-0.056
Token jar
Token ID17379
Feature activation+9.86e-02

Pos logit contributions
 day+0.008
 night+0.008
 time+0.007
 morning+0.007
 afternoon+0.007
Neg logit contributions
boys-0.008
 paramed-0.007
 chefs-0.007
 groom-0.007
Fighting-0.007
Token of
Token ID286
Feature activation-8.94e-02

Pos logit contributions
boys+0.231
 paramed+0.225
 chefs+0.223
 Lee+0.219
 printer+0.217
Neg logit contributions
 nights-0.076
 night-0.075
 day-0.072
 morning-0.067
 evening-0.065
Token chocolate
Token ID11311
Feature activation+5.70e-02

Pos logit contributions
 day+0.154
 night+0.152
 nights+0.147
 time+0.143
 morning+0.143
Neg logit contributions
boys-0.138
 paramed-0.133
 Lee-0.129
 chefs-0.124
 reporter-0.122
Token chip
Token ID11594
Feature activation+2.89e-01

Pos logit contributions
boys+0.090
 paramed+0.089
 chefs+0.085
 Lee+0.084
 principal+0.080
Neg logit contributions
 day-0.091
 night-0.090
 nights-0.088
 morning-0.085
 time-0.084
Token cookies
Token ID14746
Feature activation+1.38e-01

Pos logit contributions
 paramed+0.414
boys+0.411
 Lee+0.383
 chefs+0.375
 reporter+0.371
Neg logit contributions
 day-0.517
 night-0.503
 nights-0.498
 time-0.481
 afternoon-0.479
Token hidden
Token ID7104
Feature activation-5.20e-02

Pos logit contributions
 paramed+0.252
boys+0.251
 chefs+0.242
 Lee+0.239
 principal+0.230
Neg logit contributions
 day-0.186
 night-0.181
 nights-0.177
 time-0.169
 morning-0.168
Token inside
Token ID2641
Feature activation+3.96e-02

Pos logit contributions
 day+0.072
 night+0.071
 nights+0.070
 morning+0.068
 evening+0.067
Neg logit contributions
boys-0.092
 chefs-0.089
 Lee-0.085
 paramed-0.083
 printer-0.079
Token.
Token ID13
Feature activation+6.58e-04

Pos logit contributions
boys+0.071
 paramed+0.070
 chefs+0.070
 Lee+0.068
 printer+0.065
Neg logit contributions
 day-0.052
 nights-0.051
 night-0.051
fy-0.048
 morning-0.048
Token Both
Token ID5747
Feature activation+6.88e-02

Pos logit contributions
boys+0.001
 paramed+0.001
 chefs+0.001
 Lee+0.001
 groom+0.001
Neg logit contributions
 day-0.001
 night-0.001
 nights-0.001
 morning-0.001
 time-0.001
Token a
Token ID257
Feature activation+4.21e-02

Pos logit contributions
 day+0.038
 nights+0.037
 night+0.037
 afternoon+0.036
 morning+0.036
Neg logit contributions
boys-0.025
 paramed-0.024
 chefs-0.023
 Lee-0.023
 groom-0.021
Token special
Token ID2041
Feature activation-6.68e-02

Pos logit contributions
boys+0.077
 Lee+0.072
 chefs+0.072
 paramed+0.071
 principal+0.070
Neg logit contributions
 day-0.063
 night-0.060
 time-0.059
fy-0.057
 morning-0.056
Token treat
Token ID2190
Feature activation+1.38e-01

Pos logit contributions
 day+0.117
 night+0.112
 time+0.109
 morning+0.108
 nights+0.104
Neg logit contributions
boys-0.107
 chefs-0.100
 paramed-0.099
 Lee-0.098
 principal-0.095
Token for
Token ID329
Feature activation+3.75e-02

Pos logit contributions
boys+0.279
 paramed+0.277
 chefs+0.270
 Lee+0.265
 principal+0.256
Neg logit contributions
 day-0.158
 night-0.154
 nights-0.151
 morning-0.143
 time-0.141
Token the
Token ID262
Feature activation+4.86e-02

Pos logit contributions
boys+0.054
 paramed+0.053
 chefs+0.051
 Lee+0.050
 reporter+0.047
Neg logit contributions
 day-0.065
 night-0.064
 nights-0.064
 morning-0.061
 time-0.061
Token chip
Token ID11594
Feature activation+2.88e-01

Pos logit contributions
boys+0.060
 paramed+0.059
 chefs+0.057
 Lee+0.056
 reporter+0.052
Neg logit contributions
 day-0.095
 night-0.093
 nights-0.092
 morning-0.089
 time-0.089
Tokenm
Token ID76
Feature activation-2.04e-02

Pos logit contributions
boys+0.470
 paramed+0.467
 chefs+0.444
 Lee+0.443
 principal+0.432
Neg logit contributions
 day-0.460
 night-0.438
 nights-0.428
 morning-0.417
 afternoon-0.415
Tokenunk
Token ID2954
Feature activation+9.94e-02

Pos logit contributions
 nights+0.035
 night+0.035
 day+0.035
fy+0.033
 afternoon+0.033
Neg logit contributions
 paramed-0.029
boys-0.028
 chefs-0.028
 Lee-0.027
 printer-0.025
Token.
Token ID13
Feature activation-5.96e-04

Pos logit contributions
boys+0.177
 paramed+0.171
 Lee+0.167
 chefs+0.167
 printer+0.159
Neg logit contributions
 nights-0.136
 day-0.133
 night-0.131
 afternoon-0.125
 Along-0.124
Token She
Token ID1375
Feature activation-1.24e-02

Pos logit contributions
 day+0.001
 nights+0.001
 night+0.001
 afternoon+0.001
 time+0.001
Neg logit contributions
 paramed-0.001
boys-0.001
 Lee-0.001
 chefs-0.001
 printer-0.001
Token said
Token ID531
Feature activation+2.74e-02

Pos logit contributions
 day+0.020
 night+0.019
 nights+0.019
 time+0.018
fy+0.018
Neg logit contributions
 paramed-0.020
 Lee-0.019
boys-0.019
 chefs-0.019
 principal-0.018
Token place
Token ID1295
Feature activation-1.11e-02

Pos logit contributions
 day+0.058
 night+0.058
 time+0.058
 nights+0.054
 afternoon+0.053
Neg logit contributions
 paramed-0.048
boys-0.047
 principal-0.043
 Lee-0.043
 chefs-0.042
Token!
Token ID0
Feature activation+2.82e-02

Pos logit contributions
 day+0.016
 night+0.015
 nights+0.015
 time+0.015
 morning+0.014
Neg logit contributions
 paramed-0.020
boys-0.020
 chefs-0.019
 Lee-0.019
 groom-0.019
Token
Token ID198
Feature activation+1.68e-02

Pos logit contributions
boys+0.049
 paramed+0.049
 chefs+0.047
 Lee+0.046
 groom+0.045
Neg logit contributions
 day-0.040
 night-0.039
 nights-0.039
 morning-0.037
 time-0.037
Token
Token ID198
Feature activation+1.63e-02

Pos logit contributions
boys+0.032
 paramed+0.031
 chefs+0.031
 Lee+0.030
 groom+0.029
Neg logit contributions
 day-0.022
 night-0.021
 nights-0.021
 time-0.020
 morning-0.020
TokenThe
Token ID464
Feature activation+1.39e-02

Pos logit contributions
boys+0.030
 Lee+0.029
 chefs+0.028
 paramed+0.028
 wrists+0.027
Neg logit contributions
 day-0.022
 nights-0.022
 time-0.021
 Along-0.021
 afternoon-0.021
Token chip
Token ID11594
Feature activation+2.87e-01

Pos logit contributions
boys+0.020
 paramed+0.019
 Lee+0.019
 chefs+0.019
 reporter+0.018
Neg logit contributions
 day-0.025
 night-0.024
 nights-0.024
 morning-0.023
 time-0.023
Tokenmun
Token ID6199
Feature activation+7.05e-02

Pos logit contributions
boys+0.537
 paramed+0.532
 chefs+0.515
 Lee+0.511
 groom+0.500
Neg logit contributions
 day-0.405
 night-0.371
 nights-0.365
 afternoon-0.361
 morning-0.353
Tokenks
Token ID591
Feature activation+4.33e-02

Pos logit contributions
boys+0.091
 paramed+0.089
 chefs+0.085
 Lee+0.084
 principal+0.079
Neg logit contributions
 day-0.133
 night-0.130
 nights-0.130
 time-0.126
 morning-0.124
Token didn
Token ID1422
Feature activation-2.48e-02

Pos logit contributions
boys+0.073
 paramed+0.072
 chefs+0.071
 Lee+0.070
 principal+0.066
Neg logit contributions
 day-0.064
 night-0.063
 nights-0.062
 time-0.060
 morning-0.059
Token't
Token ID470
Feature activation+1.23e-02

Pos logit contributions
 nights+0.042
 day+0.041
 night+0.040
 afternoon+0.039
fy+0.039
Neg logit contributions
 paramed-0.037
boys-0.037
 Lee-0.035
 chefs-0.034
 printer-0.033
Token know
Token ID760
Feature activation+5.98e-02

Pos logit contributions
boys+0.018
 paramed+0.018
 chefs+0.017
 Lee+0.017
 reporter+0.016
Neg logit contributions
 day-0.021
 night-0.021
 nights-0.021
 morning-0.020
 afternoon-0.020
Token!"
Token ID2474
Feature activation+1.93e-01

Pos logit contributions
 nights+0.102
 day+0.102
 night+0.100
 afternoon+0.096
 morning+0.096
Neg logit contributions
boys-0.095
 paramed-0.091
 chefs-0.090
 Lee-0.089
 groom-0.083
Token
Token ID220
Feature activation-1.17e-02

Pos logit contributions
 paramed+0.283
boys+0.283
 Lee+0.280
 chefs+0.267
 printer+0.254
Neg logit contributions
 nights-0.316
 day-0.315
 night-0.309
fy-0.300
 time-0.298
Token
Token ID198
Feature activation+1.94e-02

Pos logit contributions
 day+0.017
 night+0.017
 nights+0.017
 morning+0.016
 afternoon+0.016
Neg logit contributions
boys-0.020
 paramed-0.020
 chefs-0.019
 Lee-0.019
 principal-0.018
Token
Token ID198
Feature activation+1.84e-02

Pos logit contributions
boys+0.034
 paramed+0.033
 chefs+0.032
 Lee+0.032
 printer+0.030
Neg logit contributions
 day-0.028
 night-0.027
 nights-0.027
 morning-0.025
 afternoon-0.025
TokenThe
Token ID464
Feature activation+5.85e-03

Pos logit contributions
boys+0.032
 chefs+0.032
 Lee+0.032
 paramed+0.031
 printer+0.030
Neg logit contributions
 day-0.026
 nights-0.025
 night-0.024
 afternoon-0.024
 Along-0.024
Token chip
Token ID11594
Feature activation+2.86e-01

Pos logit contributions
boys+0.009
 Lee+0.008
 chefs+0.008
 reporter+0.008
 paramed+0.008
Neg logit contributions
 day-0.011
 night-0.010
 time-0.010
 morning-0.010
 afternoon-0.009
Tokenm
Token ID76
Feature activation-2.29e-02

Pos logit contributions
boys+0.535
 paramed+0.526
 Lee+0.510
 chefs+0.509
 principal+0.498
Neg logit contributions
 day-0.409
 night-0.370
 afternoon-0.365
 nights-0.358
 morning-0.354
Tokenunk
Token ID2954
Feature activation+9.81e-02

Pos logit contributions
 day+0.041
 night+0.040
 nights+0.040
 time+0.039
 morning+0.039
Neg logit contributions
boys-0.032
 paramed-0.030
 chefs-0.030
 Lee-0.029
 reporter-0.028
Token finished
Token ID5201
Feature activation+8.93e-02

Pos logit contributions
boys+0.130
 paramed+0.129
 chefs+0.127
 Lee+0.122
 reporter+0.114
Neg logit contributions
 day-0.181
 night-0.178
 nights-0.176
 morning-0.170
 afternoon-0.169
Token the
Token ID262
Feature activation+4.51e-02

Pos logit contributions
boys+0.144
 paramed+0.142
 chefs+0.137
 reporter+0.132
 Lee+0.131
Neg logit contributions
 day-0.145
 night-0.141
 nights-0.135
 time-0.134
 morning-0.133
Token treat
Token ID2190
Feature activation+1.35e-01

Pos logit contributions
 paramed+0.053
boys+0.053
 chefs+0.050
 Lee+0.049
 printer+0.046
Neg logit contributions
 nights-0.089
 day-0.088
 night-0.088
fy-0.084
 morning-0.084
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
boys+0.039
 paramed+0.038
 Lee+0.036
 chefs+0.036
 printer+0.035
Neg logit contributions
 nights-0.031
 day-0.029
 night-0.029
fy-0.028
 afternoon-0.028
Token It
Token ID632
Feature activation+9.07e-02

Pos logit contributions
 day+0.017
 night+0.017
 nights+0.017
 morning+0.016
 Along+0.016
Neg logit contributions
boys-0.022
 paramed-0.021
 chefs-0.021
 Lee-0.020
 groom-0.020
Token was
Token ID373
Feature activation+3.87e-02

Pos logit contributions
boys+0.143
 paramed+0.142
 chefs+0.139
 Lee+0.137
 principal+0.130
Neg logit contributions
 day-0.146
 night-0.143
 nights-0.141
 time-0.135
 morning-0.135
Token a
Token ID257
Feature activation+3.84e-02

Pos logit contributions
boys+0.055
 paramed+0.054
 chefs+0.052
 Lee+0.051
 principal+0.049
Neg logit contributions
 day-0.070
 night-0.069
 time-0.067
 nights-0.067
 morning-0.065
Token small
Token ID1402
Feature activation-8.47e-03

Pos logit contributions
boys+0.070
 chefs+0.067
 Lee+0.066
 paramed+0.065
 wrists+0.063
Neg logit contributions
 day-0.059
 night-0.056
 time-0.054
 morning-0.052
 evening-0.051
Token chip
Token ID11594
Feature activation+2.86e-01

Pos logit contributions
 day+0.015
 night+0.015
 morning+0.014
 time+0.013
 nights+0.013
Neg logit contributions
boys-0.013
 paramed-0.013
 chefs-0.013
 principal-0.012
 Lee-0.012
Tokenm
Token ID76
Feature activation-2.53e-02

Pos logit contributions
 paramed+0.503
boys+0.502
 chefs+0.481
 Lee+0.478
 principal+0.465
Neg logit contributions
 day-0.418
 night-0.401
 nights-0.392
 morning-0.376
 afternoon-0.375
Tokenunk
Token ID2954
Feature activation+9.41e-02

Pos logit contributions
 day+0.046
 nights+0.046
 night+0.046
 morning+0.044
fy+0.044
Neg logit contributions
 paramed-0.033
boys-0.033
 chefs-0.032
 Lee-0.031
 printer-0.029
Token!
Token ID0
Feature activation+2.34e-02

Pos logit contributions
boys+0.173
 paramed+0.172
 chefs+0.168
 Lee+0.165
 principal+0.158
Neg logit contributions
 day-0.124
 night-0.121
 nights-0.120
 morning-0.113
 time-0.112
Token The
Token ID383
Feature activation+4.93e-02

Pos logit contributions
boys+0.041
 paramed+0.040
 chefs+0.039
 Lee+0.038
 reporter+0.037
Neg logit contributions
 day-0.033
 night-0.033
 nights-0.032
 morning-0.031
 time-0.031
Token princess
Token ID21752
Feature activation+2.95e-02

Pos logit contributions
boys+0.083
 Lee+0.077
 paramed+0.076
 reporter+0.075
 chefs+0.075
Neg logit contributions
 day-0.081
 night-0.077
 time-0.074
 morning-0.074
 nights-0.072
Token boy
Token ID2933
Feature activation+1.38e-01

Pos logit contributions
boys+0.060
 reporter+0.056
 Lee+0.053
 groom+0.052
 paramed+0.050
Neg logit contributions
 day-0.113
 night-0.105
 time-0.102
 morning-0.102
 afternoon-0.102
Token finally
Token ID3443
Feature activation-2.89e-02

Pos logit contributions
 chefs+0.214
 paramed+0.214
boys+0.209
 Lee+0.202
 reporter+0.192
Neg logit contributions
 day-0.225
 night-0.222
 nights-0.218
 time-0.208
 morning-0.208
Token understood
Token ID7247
Feature activation+1.28e-01

Pos logit contributions
 day+0.048
 night+0.048
 time+0.046
 nights+0.045
 morning+0.044
Neg logit contributions
 paramed-0.045
 chefs-0.045
boys-0.045
 Lee-0.043
 printer-0.040
Token why
Token ID1521
Feature activation+9.76e-02

Pos logit contributions
boys+0.212
 paramed+0.208
 chefs+0.198
 Lee+0.190
 reporter+0.188
Neg logit contributions
 day-0.209
 night-0.202
 time-0.199
 nights-0.193
 morning-0.188
Token the
Token ID262
Feature activation+4.93e-02

Pos logit contributions
boys+0.149
 paramed+0.146
 chefs+0.141
 Lee+0.134
 reporter+0.133
Neg logit contributions
 day-0.167
 night-0.162
 nights-0.158
 time-0.156
 morning-0.153
Token chip
Token ID11594
Feature activation+2.85e-01

Pos logit contributions
boys+0.055
 reporter+0.049
 Lee+0.046
 chefs+0.045
 groom+0.044
Neg logit contributions
 day-0.117
 night-0.109
 morning-0.107
 time-0.106
 afternoon-0.105
Tokenm
Token ID76
Feature activation-2.32e-02

Pos logit contributions
boys+0.624
 wrists+0.597
 groom+0.596
 paramed+0.596
 reporter+0.588
Neg logit contributions
 day-0.329
 afternoon-0.271
 night-0.271
 morning-0.264
 time-0.252
Tokenunk
Token ID2954
Feature activation+9.91e-02

Pos logit contributions
 day+0.040
 night+0.038
 time+0.037
 nights+0.037
 morning+0.037
Neg logit contributions
boys-0.035
 paramed-0.033
 chefs-0.032
 reporter-0.032
 Lee-0.031
Token had
Token ID550
Feature activation-1.44e-02

Pos logit contributions
boys+0.155
 paramed+0.155
 chefs+0.151
 Lee+0.147
 principal+0.139
Neg logit contributions
 day-0.160
 night-0.156
 nights-0.152
 time-0.147
 morning-0.147
Token been
Token ID587
Feature activation-4.90e-02

Pos logit contributions
 day+0.023
 night+0.023
 time+0.023
 nights+0.022
 morning+0.021
Neg logit contributions
 paramed-0.024
boys-0.023
 Lee-0.023
 chefs-0.022
 principal-0.021
Token so
Token ID523
Feature activation+2.54e-02

Pos logit contributions
 time+0.078
 day+0.076
 night+0.071
 nights+0.070
 afternoon+0.068
Neg logit contributions
 paramed-0.085
boys-0.080
 Lee-0.079
 chefs-0.074
 wrists-0.073
Token bird
Token ID6512
Feature activation+8.88e-02

Pos logit contributions
 paramed+0.082
boys+0.082
 Lee+0.079
 chefs+0.079
 principal+0.075
Neg logit contributions
 day-0.083
 night-0.081
 nights-0.079
 time-0.077
 morning-0.076
Token.
Token ID13
Feature activation-6.39e-03

Pos logit contributions
boys+0.160
 paramed+0.148
 Lee+0.147
 chefs+0.145
 printer+0.139
Neg logit contributions
 nights-0.124
 night-0.118
 day-0.118
fy-0.114
 afternoon-0.113
Token Luckily
Token ID24262
Feature activation-2.61e-02

Pos logit contributions
 day+0.008
 Along+0.008
 night+0.008
 morning+0.008
 nights+0.008
Neg logit contributions
boys-0.012
 paramed-0.011
 chefs-0.011
 groom-0.011
 reporter-0.011
Token,
Token ID11
Feature activation+9.57e-02

Pos logit contributions
 day+0.038
 night+0.037
 nights+0.037
 morning+0.035
 time+0.035
Neg logit contributions
 paramed-0.045
boys-0.045
 chefs-0.044
 Lee-0.042
 reporter-0.041
Token the
Token ID262
Feature activation+5.01e-02

Pos logit contributions
boys+0.157
 paramed+0.156
 chefs+0.148
 wrists+0.143
 Lee+0.142
Neg logit contributions
 day-0.154
 night-0.150
 nights-0.146
 morning-0.142
 time-0.138
Token chip
Token ID11594
Feature activation+2.85e-01

Pos logit contributions
 paramed+0.080
boys+0.080
 Lee+0.078
 chefs+0.077
 principal+0.074
Neg logit contributions
 day-0.083
 night-0.080
 nights-0.077
 time-0.076
 morning-0.075
Tokenm
Token ID76
Feature activation-2.49e-02

Pos logit contributions
 paramed+0.508
 Lee+0.495
boys+0.493
 principal+0.491
 chefs+0.483
Neg logit contributions
 day-0.430
 night-0.381
ie-0.373
 afternoon-0.373
 nights-0.371
Tokenunk
Token ID2954
Feature activation+9.37e-02

Pos logit contributions
 day+0.042
 nights+0.042
 night+0.042
 morning+0.040
 afternoon+0.040
Neg logit contributions
boys-0.036
 paramed-0.036
 chefs-0.034
 Lee-0.034
 printer-0.032
Token said
Token ID531
Feature activation+2.57e-02

Pos logit contributions
 paramed+0.136
 chefs+0.134
boys+0.133
 Lee+0.128
 principal+0.121
Neg logit contributions
 day-0.163
 night-0.159
 nights-0.155
 time-0.153
 morning-0.151
Token they
Token ID484
Feature activation+4.24e-03

Pos logit contributions
boys+0.045
 chefs+0.043
 paramed+0.043
 principal+0.042
 Lee+0.041
Neg logit contributions
 day-0.037
 night-0.035
 time-0.035
 morning-0.035
 nights-0.034
Token should
Token ID815
Feature activation+1.00e-01

Pos logit contributions
 paramed+0.008
boys+0.007
 chefs+0.007
 Lee+0.007
 principal+0.007
Neg logit contributions
 day-0.006
 night-0.006
 nights-0.006
 time-0.006
 morning-0.005
Token chip
Token ID11594
Feature activation+2.84e-01

Pos logit contributions
boys+0.076
 chefs+0.072
 paramed+0.072
 Lee+0.071
 principal+0.068
Neg logit contributions
 day-0.067
 night-0.064
 time-0.061
 morning-0.059
 afternoon-0.058
Tokenm
Token ID76
Feature activation-2.67e-02

Pos logit contributions
 paramed+0.515
boys+0.513
 chefs+0.491
 Lee+0.487
 groom+0.480
Neg logit contributions
 day-0.398
 night-0.379
 nights-0.370
 time-0.356
 afternoon-0.355
Tokenunk
Token ID2954
Feature activation+9.49e-02

Pos logit contributions
 day+0.051
 nights+0.050
 night+0.050
 morning+0.048
 afternoon+0.048
Neg logit contributions
boys-0.033
 paramed-0.033
 chefs-0.032
 Lee-0.031
 printer-0.029
Token!
Token ID0
Feature activation+2.76e-02

Pos logit contributions
boys+0.174
 paramed+0.172
 chefs+0.168
 Lee+0.166
 reporter+0.158
Neg logit contributions
 day-0.126
 night-0.123
 nights-0.122
 morning-0.115
 time-0.114
Token The
Token ID383
Feature activation+5.02e-02

Pos logit contributions
boys+0.047
 chefs+0.044
 paramed+0.043
 groom+0.041
 Lee+0.041
Neg logit contributions
 day-0.043
 night-0.042
 morning-0.041
 Along-0.040
 time-0.040
Token chip
Token ID11594
Feature activation+2.84e-01

Pos logit contributions
boys+0.061
 chefs+0.055
 reporter+0.055
 wrists+0.052
 principal+0.052
Neg logit contributions
 day-0.106
 night-0.100
 time-0.097
 morning-0.097
 afternoon-0.093
Tokenm
Token ID76
Feature activation-2.70e-02

Pos logit contributions
boys+0.536
 paramed+0.533
 groom+0.525
 wrists+0.518
 principal+0.517
Neg logit contributions
 day-0.390
 night-0.344
 nights-0.338
 afternoon-0.337
 time-0.329
Tokenunk
Token ID2954
Feature activation+9.59e-02

Pos logit contributions
 day+0.050
 night+0.049
 nights+0.049
 time+0.047
 morning+0.047
Neg logit contributions
boys-0.036
 paramed-0.035
 chefs-0.034
 Lee-0.033
 principal-0.031
Token said
Token ID531
Feature activation+2.54e-02

Pos logit contributions
 paramed+0.147
boys+0.146
 chefs+0.146
 Lee+0.140
 principal+0.134
Neg logit contributions
 day-0.157
 night-0.152
 nights-0.150
 time-0.145
 morning-0.144
Token to
Token ID284
Feature activation+7.59e-02

Pos logit contributions
boys+0.054
 chefs+0.053
 principal+0.052
 wrists+0.050
 paramed+0.049
Neg logit contributions
 of-0.028
 day-0.028
 morning-0.026
 night-0.025
 time-0.025
Token Sally
Token ID25737
Feature activation+4.81e-02

Pos logit contributions
boys+0.118
 paramed+0.114
 chefs+0.114
 Lee+0.107
 reporter+0.105
Neg logit contributions
 day-0.131
 night-0.126
 time-0.123
 morning-0.121
 nights-0.119
Token frog
Token ID21264
Feature activation+8.32e-02

Pos logit contributions
boys+0.068
 Lee+0.066
 reporter+0.066
 paramed+0.064
 chefs+0.063
Neg logit contributions
 day-0.101
 night-0.092
 time-0.090
 morning-0.089
 afternoon-0.089
Token agreed
Token ID4987
Feature activation+1.12e-01

Pos logit contributions
 paramed+0.117
 chefs+0.116
boys+0.116
 Lee+0.114
 principal+0.107
Neg logit contributions
 day-0.148
 night-0.144
 nights-0.141
 time-0.138
 morning-0.137
Token,
Token ID11
Feature activation+9.98e-02

Pos logit contributions
boys+0.192
 paramed+0.190
 chefs+0.185
 Lee+0.181
 principal+0.173
Neg logit contributions
 day-0.165
 night-0.161
 nights-0.159
 time-0.152
 morning-0.152
Token and
Token ID290
Feature activation-9.75e-03

Pos logit contributions
boys+0.176
 chefs+0.172
 paramed+0.172
 Lee+0.164
 principal+0.160
Neg logit contributions
 day-0.143
 night-0.138
 nights-0.137
 morning-0.131
 time-0.130
Token the
Token ID262
Feature activation+4.90e-02

Pos logit contributions
 day+0.017
 night+0.016
 nights+0.016
 morning+0.015
 afternoon+0.015
Neg logit contributions
 paramed-0.015
boys-0.014
 chefs-0.014
 principal-0.014
 Lee-0.014
Token chip
Token ID11594
Feature activation+2.84e-01

Pos logit contributions
boys+0.084
 Lee+0.083
 reporter+0.082
 paramed+0.080
 chefs+0.080
Neg logit contributions
 day-0.080
 night-0.073
 time-0.070
 morning-0.070
 afternoon-0.068
Tokenm
Token ID76
Feature activation-2.47e-02

Pos logit contributions
boys+0.551
 paramed+0.541
 Lee+0.537
 principal+0.536
 chefs+0.533
Neg logit contributions
 day-0.385
 night-0.343
 afternoon-0.328
 morning-0.327
 nights-0.320
Tokenunk
Token ID2954
Feature activation+9.49e-02

Pos logit contributions
 day+0.044
 night+0.044
 nights+0.043
 time+0.042
 morning+0.042
Neg logit contributions
boys-0.034
 paramed-0.033
 chefs-0.032
 Lee-0.032
 principal-0.030
Token agreed
Token ID4987
Feature activation+1.14e-01

Pos logit contributions
boys+0.131
 paramed+0.131
 chefs+0.128
 Lee+0.125
 principal+0.117
Neg logit contributions
 day-0.169
 night-0.166
 nights-0.164
 morning-0.158
 time-0.157
Token too
Token ID1165
Feature activation+3.62e-02

Pos logit contributions
boys+0.211
 paramed+0.208
 chefs+0.203
 Lee+0.201
 reporter+0.191
Neg logit contributions
 day-0.147
 night-0.145
 nights-0.145
 morning-0.135
 afternoon-0.135
Token.
Token ID13
Feature activation+2.03e-03

Pos logit contributions
boys+0.067
 Lee+0.063
 paramed+0.063
 chefs+0.063
 reporter+0.059
Neg logit contributions
 nights-0.047
 day-0.047
 night-0.046
 afternoon-0.044
 morning-0.044
Token animal
Token ID5044
Feature activation+1.49e-02

Pos logit contributions
 day+0.003
 night+0.003
 time+0.003
 morning+0.003
 nights+0.003
Neg logit contributions
boys-0.004
 paramed-0.003
 chefs-0.003
 principal-0.003
Fighting-0.003
Token.
Token ID13
Feature activation-7.50e-03

Pos logit contributions
boys+0.025
 paramed+0.024
 chefs+0.024
 Lee+0.023
 printer+0.022
Neg logit contributions
 day-0.022
 nights-0.022
 night-0.022
 morning-0.021
 afternoon-0.021
Token It
Token ID632
Feature activation+9.34e-02

Pos logit contributions
 day+0.011
 night+0.011
 Along+0.011
 morning+0.011
 time+0.010
Neg logit contributions
boys-0.013
 chefs-0.012
 paramed-0.012
 groom-0.012
 Lee-0.011
Token was
Token ID373
Feature activation+4.13e-02

Pos logit contributions
 paramed+0.157
 chefs+0.155
boys+0.154
 Lee+0.149
 principal+0.146
Neg logit contributions
 day-0.143
 night-0.138
 nights-0.134
 time-0.132
 morning-0.129
Token a
Token ID257
Feature activation+4.30e-02

Pos logit contributions
boys+0.062
 paramed+0.062
 chefs+0.060
 Lee+0.059
 principal+0.057
Neg logit contributions
 day-0.069
 night-0.068
 time-0.066
 nights-0.066
 morning-0.064
Token chip
Token ID11594
Feature activation+2.84e-01

Pos logit contributions
boys+0.076
 chefs+0.072
 paramed+0.072
 Lee+0.071
 principal+0.068
Neg logit contributions
 day-0.067
 night-0.064
 time-0.061
 morning-0.059
 afternoon-0.058
Tokenm
Token ID76
Feature activation-2.67e-02

Pos logit contributions
 paramed+0.515
boys+0.513
 chefs+0.491
 Lee+0.487
 groom+0.480
Neg logit contributions
 day-0.398
 night-0.379
 nights-0.370
 time-0.356
 afternoon-0.355
Tokenunk
Token ID2954
Feature activation+9.49e-02

Pos logit contributions
 day+0.051
 nights+0.050
 night+0.050
 morning+0.048
 afternoon+0.048
Neg logit contributions
boys-0.033
 paramed-0.033
 chefs-0.032
 Lee-0.031
 printer-0.029
Token!
Token ID0
Feature activation+2.76e-02

Pos logit contributions
boys+0.174
 paramed+0.172
 chefs+0.168
 Lee+0.166
 reporter+0.158
Neg logit contributions
 day-0.126
 night-0.123
 nights-0.122
 morning-0.115
 time-0.114
Token The
Token ID383
Feature activation+5.02e-02

Pos logit contributions
boys+0.047
 chefs+0.044
 paramed+0.043
 groom+0.041
 Lee+0.041
Neg logit contributions
 day-0.043
 night-0.042
 morning-0.041
 Along-0.040
 time-0.040
Token chip
Token ID11594
Feature activation+2.84e-01

Pos logit contributions
boys+0.061
 chefs+0.055
 reporter+0.055
 wrists+0.052
 principal+0.052
Neg logit contributions
 day-0.106
 night-0.100
 time-0.097
 morning-0.097
 afternoon-0.093
Token is
Token ID318
Feature activation+2.54e-02

Pos logit contributions
 paramed+0.023
boys+0.023
 Lee+0.022
 chefs+0.022
 principal+0.021
Neg logit contributions
 day-0.022
 night-0.021
 nights-0.021
 morning-0.020
 time-0.020
Token inside
Token ID2641
Feature activation-1.87e-02

Pos logit contributions
boys+0.043
 paramed+0.042
 Lee+0.041
 chefs+0.039
 principal+0.039
Neg logit contributions
 day-0.040
 night-0.039
 time-0.038
 nights-0.037
 morning-0.037
Token.
Token ID13
Feature activation-6.36e-02

Pos logit contributions
 day+0.026
 night+0.025
 nights+0.025
 morning+0.024
 time+0.023
Neg logit contributions
boys-0.034
 paramed-0.033
 chefs-0.032
 Lee-0.032
 reporter-0.030
Token<|endoftext|>
Token ID50256
Feature activation-1.82e-01

Pos logit contributions
 day+0.102
 night+0.101
 nights+0.101
 morning+0.095
 afternoon+0.095
Neg logit contributions
boys-0.098
 paramed-0.097
 chefs-0.094
 Lee-0.093
 printer-0.087
TokenOne
Token ID3198
Feature activation-2.16e-01

Pos logit contributions
 nights+0.294
fy+0.286
 day+0.277
 night+0.271
 afternoon+0.265
Neg logit contributions
 Lee-0.275
boys-0.275
 chefs-0.273
 paramed-0.266
 principal-0.250
Token day
Token ID1110
Feature activation-2.94e-01

Pos logit contributions
fy+0.214
 Along+0.199
lessly+0.198
ight+0.197
ly+0.195
Neg logit contributions
 dads-0.409
 mixer-0.409
 dad-0.408
 band-0.398
 paramed-0.398
Token,
Token ID11
Feature activation+3.45e-02

Pos logit contributions
 nights+0.616
fy+0.597
found+0.554
 night+0.548
ingle+0.547
Neg logit contributions
 Lee-0.327
 chefs-0.307
 paramed-0.290
boys-0.286
 printer-0.271
Token a
Token ID257
Feature activation-2.44e-02

Pos logit contributions
boys+0.041
 paramed+0.040
 chefs+0.040
 Lee+0.039
 printer+0.035
Neg logit contributions
 nights-0.068
 day-0.067
 night-0.066
fy-0.065
 morning-0.063
Token boy
Token ID2933
Feature activation+8.34e-02

Pos logit contributions
 day+0.031
 night+0.029
 time+0.028
 morning+0.028
 nights+0.027
Neg logit contributions
boys-0.048
 paramed-0.047
 Lee-0.046
 chefs-0.045
 wrists-0.044
Token named
Token ID3706
Feature activation-7.34e-02

Pos logit contributions
boys+0.081
 paramed+0.080
 chefs+0.077
 Lee+0.074
 printer+0.069
Neg logit contributions
 nights-0.179
 day-0.177
 night-0.176
fy-0.173
 afternoon-0.170
Token Tim
Token ID5045
Feature activation-2.77e-02

Pos logit contributions
 nights+0.175
 day+0.165
fy+0.163
 night+0.163
 afternoon+0.163
Neg logit contributions
boys-0.061
 chefs-0.061
 Lee-0.057
 paramed-0.056
 printer-0.050
Tokenopl
Token ID20106
Feature activation-2.15e-01

Pos logit contributions
fy+0.025
 Along+0.024
ight+0.023
ingle+0.023
dark+0.023
Neg logit contributions
 chefs-0.026
boys-0.023
 spies-0.022
 reporter-0.022
 printer-0.022
Tokenane
Token ID1531
Feature activation-5.54e-02

Pos logit contributions
 nights+0.304
fy+0.295
 night+0.292
 day+0.284
 afternoon+0.275
Neg logit contributions
boys-0.379
 paramed-0.361
 Lee-0.361
 chefs-0.351
 principal-0.347
Token.
Token ID13
Feature activation-6.28e-02

Pos logit contributions
 nights+0.082
 day+0.081
 night+0.081
fy+0.078
 Along+0.078
Neg logit contributions
boys-0.090
 paramed-0.087
 chefs-0.083
 Lee-0.083
 printer-0.081
Token<|endoftext|>
Token ID50256
Feature activation-1.89e-01

Pos logit contributions
 day+0.098
 night+0.097
 nights+0.097
 morning+0.091
 afternoon+0.091
Neg logit contributions
boys-0.099
 paramed-0.098
 chefs-0.095
 Lee-0.095
 printer-0.089
TokenOne
Token ID3198
Feature activation-2.15e-01

Pos logit contributions
fy+0.354
 nights+0.350
 spine+0.318
ly+0.317
rated+0.315
Neg logit contributions
 Lee-0.247
 chefs-0.238
boys-0.231
 paramed-0.222
 principal-0.212
Token day
Token ID1110
Feature activation-2.92e-01

Pos logit contributions
fy+0.237
 Along+0.222
ly+0.215
lessly+0.215
ets+0.211
Neg logit contributions
 dads-0.385
 qu-0.383
 dad-0.383
 band-0.379
 paramed-0.375
Token,
Token ID11
Feature activation+3.35e-02

Pos logit contributions
 nights+0.625
fy+0.612
found+0.565
ingle+0.557
rated+0.555
Neg logit contributions
 Lee-0.306
 chefs-0.284
 paramed-0.281
boys-0.263
 printer-0.252
Token a
Token ID257
Feature activation-2.75e-02

Pos logit contributions
boys+0.038
 paramed+0.037
 chefs+0.037
 Lee+0.036
 printer+0.032
Neg logit contributions
 nights-0.068
 day-0.066
 night-0.065
fy-0.065
 afternoon-0.063
Token turkey
Token ID26876
Feature activation+4.92e-02

Pos logit contributions
 day+0.035
 night+0.034
 nights+0.032
 time+0.032
 morning+0.032
Neg logit contributions
boys-0.053
 paramed-0.052
 chefs-0.051
 Lee-0.051
 principal-0.048
Token had
Token ID550
Feature activation-7.41e-02

Pos logit contributions
boys+0.069
 paramed+0.067
 chefs+0.066
 Lee+0.063
 printer+0.062
Neg logit contributions
 nights-0.086
 day-0.083
fy-0.083
 night-0.082
 afternoon-0.080
Token an
Token ID281
Feature activation-3.51e-02

Pos logit contributions
 nights+0.134
 day+0.132
fy+0.131
 night+0.130
 afternoon+0.126
Neg logit contributions
boys-0.097
 paramed-0.096
 chefs-0.093
 printer-0.088
 Lee-0.087
Token did
Token ID750
Feature activation-5.49e-02

Pos logit contributions
 nights+0.144
fy+0.141
 day+0.139
 night+0.138
 Along+0.134
Neg logit contributions
boys-0.104
 paramed-0.100
 Lee-0.100
 chefs-0.099
 printer-0.090
Token it
Token ID340
Feature activation-3.06e-02

Pos logit contributions
 day+0.115
 nights+0.114
 night+0.113
 morning+0.109
 afternoon+0.109
Neg logit contributions
boys-0.058
 paramed-0.056
 chefs-0.054
 Lee-0.053
 principal-0.049
Token!"
Token ID2474
Feature activation+1.31e-01

Pos logit contributions
 nights+0.045
 day+0.043
 night+0.043
fy+0.041
 Along+0.041
Neg logit contributions
boys-0.052
 chefs-0.049
 Lee-0.049
 paramed-0.049
 principal-0.046
Token<|endoftext|>
Token ID50256
Feature activation-1.81e-01

Pos logit contributions
boys+0.197
 paramed+0.194
 chefs+0.187
 Lee+0.183
 printer+0.173
Neg logit contributions
 day-0.220
 night-0.216
 nights-0.214
 morning-0.206
 time-0.205
TokenOne
Token ID3198
Feature activation-2.10e-01

Pos logit contributions
 nights+0.325
fy+0.319
 spine+0.296
 day+0.293
 night+0.290
Neg logit contributions
 Lee-0.246
 chefs-0.237
boys-0.237
 paramed-0.225
 principal-0.215
Token day
Token ID1110
Feature activation-2.92e-01

Pos logit contributions
fy+0.137
 Along+0.131
 nights+0.130
 spine+0.120
lessly+0.108
Neg logit contributions
 dads-0.462
 qu-0.461
 paramed-0.460
 mixer-0.457
 printer-0.454
Token,
Token ID11
Feature activation+3.76e-02

Pos logit contributions
 nights+0.553
fy+0.533
 night+0.505
 day+0.501
 Along+0.492
Neg logit contributions
 Lee-0.362
 chefs-0.349
boys-0.346
 paramed-0.345
 printer-0.324
Token Tim
Token ID5045
Feature activation-2.90e-02

Pos logit contributions
boys+0.049
 paramed+0.049
 chefs+0.046
 Lee+0.045
 principal+0.043
Neg logit contributions
 day-0.071
 night-0.070
 nights-0.068
 time-0.067
 morning-0.067
Tokenmy
Token ID1820
Feature activation-1.37e-01

Pos logit contributions
fy+0.050
 nights+0.050
 Along+0.047
lessly+0.046
way+0.046
Neg logit contributions
boys-0.040
 chefs-0.040
 Lee-0.038
 paramed-0.036
 printer-0.035
Token went
Token ID1816
Feature activation-1.05e-01

Pos logit contributions
 nights+0.242
fy+0.238
 day+0.235
 Along+0.230
 night+0.229
Neg logit contributions
boys-0.186
 chefs-0.177
 paramed-0.176
 Lee-0.172
 printer-0.165
Token to
Token ID284
Feature activation+3.23e-02

Pos logit contributions
 nights+0.225
ight+0.220
fy+0.217
rated+0.216
ingle+0.207
Neg logit contributions
 Lee-0.107
boys-0.101
 chefs-0.096
 paramed-0.096
 printer-0.091
Token their
Token ID511
Feature activation-4.95e-02

Pos logit contributions
 day+0.257
 night+0.253
 nights+0.252
 morning+0.241
 afternoon+0.240
Neg logit contributions
boys-0.188
 paramed-0.184
 chefs-0.178
 Lee-0.176
 printer-0.164
Token faces
Token ID6698
Feature activation+2.06e-02

Pos logit contributions
 nights+0.083
 Along+0.081
 night+0.081
 day+0.081
fy+0.080
Neg logit contributions
boys-0.072
 Lee-0.065
 paramed-0.065
 chefs-0.065
 printer-0.064
Token.
Token ID13
Feature activation-6.73e-02

Pos logit contributions
boys+0.037
 chefs+0.037
 Lee+0.036
 paramed+0.036
 reporter+0.034
Neg logit contributions
 nights-0.026
 day-0.026
 night-0.026
fy-0.025
 Along-0.024
Token<|endoftext|>
Token ID50256
Feature activation-1.89e-01

Pos logit contributions
 day+0.107
 nights+0.106
 night+0.105
 afternoon+0.099
 morning+0.099
Neg logit contributions
boys-0.105
 paramed-0.104
 Lee-0.101
 chefs-0.101
 principal-0.094
TokenOne
Token ID3198
Feature activation-2.17e-01

Pos logit contributions
 nights+0.343
fy+0.343
 spine+0.312
 day+0.310
ly+0.309
Neg logit contributions
 Lee-0.256
 chefs-0.247
boys-0.244
 paramed-0.235
 principal-0.223
Token day
Token ID1110
Feature activation-2.90e-01

Pos logit contributions
fy+0.214
 Along+0.209
 nights+0.203
ly+0.199
ight+0.198
Neg logit contributions
 dads-0.408
 qu-0.397
 dad-0.395
 band-0.395
 fountain-0.394
Token,
Token ID11
Feature activation+3.14e-02

Pos logit contributions
 nights+0.609
fy+0.583
found+0.543
 night+0.542
 day+0.537
Neg logit contributions
 Lee-0.323
 chefs-0.303
 paramed-0.295
boys-0.281
 printer-0.263
Token Mum
Token ID38367
Feature activation+3.16e-02

Pos logit contributions
boys+0.032
 chefs+0.032
 paramed+0.031
 Lee+0.031
 printer+0.028
Neg logit contributions
 nights-0.067
fy-0.064
 day-0.064
 night-0.063
 afternoon-0.061
Token was
Token ID373
Feature activation-9.50e-03

Pos logit contributions
boys+0.054
 paramed+0.053
 wrists+0.050
 principal+0.050
 chefs+0.050
Neg logit contributions
 day-0.050
 night-0.049
 time-0.046
 morning-0.046
 nights-0.045
Token looking
Token ID2045
Feature activation-8.72e-02

Pos logit contributions
 day+0.016
 nights+0.016
 night+0.016
fy+0.015
 afternoon+0.015
Neg logit contributions
 paramed-0.014
boys-0.014
 chefs-0.014
 Lee-0.013
 printer-0.012
Token at
Token ID379
Feature activation-6.50e-02

Pos logit contributions
 nights+0.137
fy+0.133
 day+0.132
 night+0.129
ight+0.127
Neg logit contributions
 chefs-0.137
 paramed-0.136
 Lee-0.128
boys-0.128
 printer-0.120
Token girl
Token ID2576
Feature activation+1.81e-02

Pos logit contributions
 day+0.244
 night+0.240
 nights+0.239
 morning+0.229
 afternoon+0.228
Neg logit contributions
boys-0.170
 paramed-0.168
 chefs-0.162
 Lee-0.159
 printer-0.148
Token named
Token ID3706
Feature activation-7.85e-02

Pos logit contributions
 paramed+0.027
 chefs+0.026
boys+0.026
 Lee+0.025
 principal+0.024
Neg logit contributions
 day-0.031
 night-0.030
 nights-0.029
 time-0.029
 morning-0.029
Token Lily
Token ID20037
Feature activation-8.76e-03

Pos logit contributions
 day+0.156
 night+0.154
 nights+0.154
 morning+0.148
 afternoon+0.147
Neg logit contributions
boys-0.092
 paramed-0.090
 chefs-0.086
 Lee-0.086
 principal-0.078
Token.
Token ID13
Feature activation-7.02e-02

Pos logit contributions
 nights+0.012
 day+0.012
 night+0.012
fy+0.011
 morning+0.011
Neg logit contributions
boys-0.016
 paramed-0.015
 Lee-0.015
 chefs-0.015
 groom-0.014
Token One
Token ID1881
Feature activation-1.47e-01

Pos logit contributions
 nights+0.112
 day+0.109
 night+0.108
fy+0.105
 afternoon+0.102
Neg logit contributions
boys-0.110
 Lee-0.110
 paramed-0.109
 chefs-0.106
 principal-0.099
Token day
Token ID1110
Feature activation-2.88e-01

Pos logit contributions
ides+0.167
ently+0.165
ight+0.157
ets+0.154
 spine+0.152
Neg logit contributions
 paramed-0.267
 sprayed-0.259
 duck-0.254
 qu-0.251
 printer-0.247
Token,
Token ID11
Feature activation+4.71e-02

Pos logit contributions
 nights+0.553
fy+0.526
 day+0.517
 night+0.515
ight+0.509
Neg logit contributions
 Lee-0.358
 paramed-0.345
 chefs-0.338
boys-0.325
 printer-0.300
Token she
Token ID673
Feature activation-1.61e-01

Pos logit contributions
boys+0.075
 Lee+0.073
 chefs+0.073
 paramed+0.073
 groom+0.068
Neg logit contributions
 nights-0.073
 night-0.071
 day-0.071
fy-0.070
 afternoon-0.068
Token went
Token ID1816
Feature activation-9.67e-02

Pos logit contributions
 day+0.310
 night+0.305
 nights+0.304
 morning+0.292
 afternoon+0.290
Neg logit contributions
boys-0.201
 paramed-0.197
 chefs-0.190
 Lee-0.186
 printer-0.173
Token to
Token ID284
Feature activation+4.00e-02

Pos logit contributions
 nights+0.181
fy+0.173
ight+0.172
 day+0.170
 night+0.169
Neg logit contributions
boys-0.125
 Lee-0.121
 chefs-0.119
 paramed-0.117
 printer-0.111
Token the
Token ID262
Feature activation+1.67e-02

Pos logit contributions
boys+0.050
 paramed+0.050
 chefs+0.047
 Lee+0.046
 reporter+0.043
Neg logit contributions
 day-0.078
 night-0.077
 nights-0.075
 morning-0.073
 time-0.073
Token girl
Token ID2576
Feature activation+1.81e-02

Pos logit contributions
 day+0.244
 night+0.240
 nights+0.239
 morning+0.229
 afternoon+0.228
Neg logit contributions
boys-0.170
 paramed-0.168
 chefs-0.162
 Lee-0.159
 printer-0.148
Token named
Token ID3706
Feature activation-7.85e-02

Pos logit contributions
 paramed+0.027
 chefs+0.026
boys+0.026
 Lee+0.025
 principal+0.024
Neg logit contributions
 day-0.031
 night-0.030
 nights-0.029
 time-0.029
 morning-0.029
Token Lily
Token ID20037
Feature activation-8.76e-03

Pos logit contributions
 day+0.156
 night+0.154
 nights+0.154
 morning+0.148
 afternoon+0.147
Neg logit contributions
boys-0.092
 paramed-0.090
 chefs-0.086
 Lee-0.086
 principal-0.078
Token.
Token ID13
Feature activation-7.02e-02

Pos logit contributions
 nights+0.012
 day+0.012
 night+0.012
fy+0.011
 morning+0.011
Neg logit contributions
boys-0.016
 paramed-0.015
 Lee-0.015
 chefs-0.015
 groom-0.014
Token One
Token ID1881
Feature activation-1.47e-01

Pos logit contributions
 nights+0.112
 day+0.109
 night+0.108
fy+0.105
 afternoon+0.102
Neg logit contributions
boys-0.110
 Lee-0.110
 paramed-0.109
 chefs-0.106
 principal-0.099
Token day
Token ID1110
Feature activation-2.88e-01

Pos logit contributions
ides+0.167
ently+0.165
ight+0.157
ets+0.154
 spine+0.152
Neg logit contributions
 paramed-0.267
 sprayed-0.259
 duck-0.254
 qu-0.251
 printer-0.247
Token,
Token ID11
Feature activation+4.71e-02

Pos logit contributions
 nights+0.553
fy+0.526
 day+0.517
 night+0.515
ight+0.509
Neg logit contributions
 Lee-0.358
 paramed-0.345
 chefs-0.338
boys-0.325
 printer-0.300
Token Lily
Token ID20037
Feature activation+9.22e-03

Pos logit contributions
boys+0.075
 Lee+0.073
 chefs+0.073
 paramed+0.073
 groom+0.068
Neg logit contributions
 nights-0.073
 night-0.071
 day-0.071
fy-0.070
 afternoon-0.068
Token went
Token ID1816
Feature activation-1.01e-01

Pos logit contributions
boys+0.013
 paramed+0.012
 chefs+0.012
 Lee+0.011
 printer+0.011
Neg logit contributions
 nights-0.016
 day-0.016
 night-0.016
fy-0.016
 afternoon-0.015
Token outside
Token ID2354
Feature activation-1.55e-01

Pos logit contributions
 nights+0.196
ight+0.192
fy+0.189
rated+0.184
 time+0.182
Neg logit contributions
boys-0.123
 Lee-0.120
 chefs-0.117
 paramed-0.112
 printer-0.108
Token to
Token ID284
Feature activation+3.81e-02

Pos logit contributions
fy+0.317
 nights+0.307
ight+0.303
rated+0.285
 day+0.282
Neg logit contributions
 Lee-0.170
 chefs-0.166
boys-0.165
 paramed-0.160
 printer-0.144
Token girl
Token ID2576
Feature activation+1.81e-02

Pos logit contributions
 day+0.244
 night+0.240
 nights+0.239
 morning+0.229
 afternoon+0.228
Neg logit contributions
boys-0.170
 paramed-0.168
 chefs-0.162
 Lee-0.159
 printer-0.148
Token named
Token ID3706
Feature activation-7.85e-02

Pos logit contributions
 paramed+0.027
 chefs+0.026
boys+0.026
 Lee+0.025
 principal+0.024
Neg logit contributions
 day-0.031
 night-0.030
 nights-0.029
 time-0.029
 morning-0.029
Token Lily
Token ID20037
Feature activation-8.76e-03

Pos logit contributions
 day+0.156
 night+0.154
 nights+0.154
 morning+0.148
 afternoon+0.147
Neg logit contributions
boys-0.092
 paramed-0.090
 chefs-0.086
 Lee-0.086
 principal-0.078
Token.
Token ID13
Feature activation-7.02e-02

Pos logit contributions
 nights+0.012
 day+0.012
 night+0.012
fy+0.011
 morning+0.011
Neg logit contributions
boys-0.016
 paramed-0.015
 Lee-0.015
 chefs-0.015
 groom-0.014
Token One
Token ID1881
Feature activation-1.47e-01

Pos logit contributions
 nights+0.112
 day+0.109
 night+0.108
fy+0.105
 afternoon+0.102
Neg logit contributions
boys-0.110
 Lee-0.110
 paramed-0.109
 chefs-0.106
 principal-0.099
Token day
Token ID1110
Feature activation-2.88e-01

Pos logit contributions
ides+0.167
ently+0.165
ight+0.157
ets+0.154
 spine+0.152
Neg logit contributions
 paramed-0.267
 sprayed-0.259
 duck-0.254
 qu-0.251
 printer-0.247
Token,
Token ID11
Feature activation+4.71e-02

Pos logit contributions
 nights+0.553
fy+0.526
 day+0.517
 night+0.515
ight+0.509
Neg logit contributions
 Lee-0.358
 paramed-0.345
 chefs-0.338
boys-0.325
 printer-0.300
Token Lily
Token ID20037
Feature activation+9.22e-03

Pos logit contributions
boys+0.075
 Lee+0.073
 chefs+0.073
 paramed+0.073
 groom+0.068
Neg logit contributions
 nights-0.073
 night-0.071
 day-0.071
fy-0.070
 afternoon-0.068
Token's
Token ID338
Feature activation+4.14e-02

Pos logit contributions
boys+0.013
 paramed+0.012
 chefs+0.012
 Lee+0.011
 printer+0.011
Neg logit contributions
 nights-0.016
 day-0.016
 night-0.016
fy-0.016
 afternoon-0.015
Token mom
Token ID1995
Feature activation+8.75e-02

Pos logit contributions
 paramed+0.032
boys+0.032
 chefs+0.030
 Lee+0.029
 printer+0.028
Neg logit contributions
 nights-0.102
fy-0.099
 night-0.096
 day-0.095
 afternoon-0.094
Token asked
Token ID1965
Feature activation+2.32e-02

Pos logit contributions
boys+0.135
 paramed+0.134
 chefs+0.131
 Lee+0.130
 principal+0.124
Neg logit contributions
 day-0.145
 night-0.142
 nights-0.136
 time-0.134
 morning-0.134
Token good
Token ID922
Feature activation+2.98e-02

Pos logit contributions
 day+0.058
 night+0.057
 nights+0.056
 time+0.054
 morning+0.054
Neg logit contributions
boys-0.055
 paramed-0.054
 Lee-0.053
 chefs-0.052
 reporter-0.049
Token friends
Token ID2460
Feature activation-4.68e-03

Pos logit contributions
boys+0.052
 paramed+0.051
 chefs+0.049
 Lee+0.049
 reporter+0.047
Neg logit contributions
 day-0.043
 night-0.042
 nights-0.042
 morning-0.040
 time-0.039
Token.
Token ID13
Feature activation-4.41e-02

Pos logit contributions
 day+0.006
 night+0.005
 nights+0.005
 time+0.005
 morning+0.005
Neg logit contributions
 paramed-0.010
boys-0.009
 chefs-0.009
 Lee-0.009
 printer-0.009
Token<|endoftext|>
Token ID50256
Feature activation-1.82e-01

Pos logit contributions
 nights+0.070
 night+0.068
 day+0.068
fy+0.065
 afternoon+0.064
Neg logit contributions
boys-0.068
 Lee-0.067
 paramed-0.067
 chefs-0.065
 principal-0.061
TokenOne
Token ID3198
Feature activation-2.14e-01

Pos logit contributions
fy+0.337
 nights+0.333
 spine+0.306
ly+0.305
 day+0.303
Neg logit contributions
 Lee-0.235
boys-0.230
 chefs-0.226
 paramed-0.212
 principal-0.205
Token day
Token ID1110
Feature activation-2.88e-01

Pos logit contributions
fy+0.214
lessly+0.206
 spine+0.205
 Along+0.205
ly+0.199
Neg logit contributions
 dads-0.398
 qu-0.385
 dad-0.383
 band-0.379
 mean-0.378
Token,
Token ID11
Feature activation+3.59e-02

Pos logit contributions
 nights+0.633
fy+0.620
found+0.579
des+0.575
ingle+0.573
Neg logit contributions
 Lee-0.280
 chefs-0.254
 paramed-0.244
boys-0.236
 ha-0.231
Token a
Token ID257
Feature activation-2.10e-02

Pos logit contributions
 chefs+0.037
boys+0.037
 Lee+0.036
 paramed+0.035
 printer+0.032
Neg logit contributions
 nights-0.077
fy-0.073
 night-0.071
 day-0.071
 afternoon-0.069
Token little
Token ID1310
Feature activation-1.08e-01

Pos logit contributions
 day+0.027
 night+0.026
 nights+0.025
 time+0.025
 morning+0.025
Neg logit contributions
boys-0.040
 paramed-0.039
 chefs-0.038
 Lee-0.038
 principal-0.036
Token girl
Token ID2576
Feature activation+2.05e-02

Pos logit contributions
 day+0.214
 night+0.208
 morning+0.199
 nights+0.197
 afternoon+0.195
Neg logit contributions
boys-0.141
 paramed-0.136
 chefs-0.131
 Lee-0.128
 principal-0.126
Token named
Token ID3706
Feature activation-7.11e-02

Pos logit contributions
boys+0.020
 paramed+0.019
 chefs+0.019
 Lee+0.018
 printer+0.017
Neg logit contributions
 day-0.044
 nights-0.044
 night-0.044
fy-0.043
 morning-0.042
Token big
Token ID1263
Feature activation-1.06e-01

Pos logit contributions
 day+0.114
 night+0.109
 time+0.106
 morning+0.103
 nights+0.102
Neg logit contributions
boys-0.142
 paramed-0.138
 Lee-0.135
 chefs-0.134
 principal-0.126
Token hug
Token ID16225
Feature activation+2.25e-02

Pos logit contributions
 day+0.186
 night+0.180
 time+0.174
 morning+0.171
 afternoon+0.164
Neg logit contributions
boys-0.174
 paramed-0.166
 chefs-0.160
 Lee-0.154
 principal-0.149
Token.
Token ID13
Feature activation-5.70e-02

Pos logit contributions
boys+0.045
 paramed+0.044
 chefs+0.043
 Lee+0.042
 principal+0.041
Neg logit contributions
 day-0.027
 night-0.026
 nights-0.025
 morning-0.025
 time-0.024
Token<|endoftext|>
Token ID50256
Feature activation-1.84e-01

Pos logit contributions
 day+0.091
 nights+0.090
 night+0.090
 afternoon+0.084
 time+0.084
Neg logit contributions
boys-0.088
 paramed-0.088
 Lee-0.086
 chefs-0.085
 principal-0.079
TokenOne
Token ID3198
Feature activation-2.16e-01

Pos logit contributions
 nights+0.329
fy+0.326
 day+0.300
 spine+0.299
 night+0.295
Neg logit contributions
 Lee-0.254
boys-0.245
 chefs-0.244
 paramed-0.229
 reporter-0.218
Token day
Token ID1110
Feature activation-2.87e-01

Pos logit contributions
fy+0.203
lessly+0.200
 Along+0.198
 spine+0.194
 nights+0.190
Neg logit contributions
 dads-0.404
 qu-0.403
 dad-0.397
 band-0.394
 mixer-0.393
Token,
Token ID11
Feature activation+3.73e-02

Pos logit contributions
 nights+0.609
fy+0.587
found+0.545
ingle+0.542
 night+0.542
Neg logit contributions
 Lee-0.309
 chefs-0.284
 paramed-0.276
boys-0.273
 printer-0.252
Token there
Token ID612
Feature activation-9.70e-02

Pos logit contributions
boys+0.040
 chefs+0.039
 Lee+0.039
 paramed+0.038
 printer+0.034
Neg logit contributions
 nights-0.078
fy-0.075
 day-0.074
 night-0.074
 afternoon-0.071
Token was
Token ID373
Feature activation-7.65e-03

Pos logit contributions
fy+0.189
 nights+0.188
 night+0.176
 day+0.175
 Along+0.174
Neg logit contributions
boys-0.111
 paramed-0.109
 Lee-0.109
 chefs-0.108
 printer-0.095
Token a
Token ID257
Feature activation-1.39e-02

Pos logit contributions
fy+0.019
rated+0.019
 nights+0.019
 spine+0.019
ingle+0.018
Neg logit contributions
 chefs-0.005
 paramed-0.004
boys-0.004
 printer-0.004
 Lee-0.003
Token slow
Token ID3105
Feature activation-1.11e-02

Pos logit contributions
 day+0.017
 night+0.015
 time+0.014
 morning+0.014
 afternoon+0.014
Neg logit contributions
boys-0.030
 Lee-0.028
 paramed-0.028
 wrists-0.028
 chefs-0.027
Token are
Token ID389
Feature activation+3.24e-02

Pos logit contributions
 Lee+0.090
 chefs+0.082
 paramed+0.082
boys+0.081
 principal+0.071
Neg logit contributions
 nights-0.341
fy-0.329
ight-0.324
 day-0.324
way-0.319
Token happy
Token ID3772
Feature activation-6.70e-02

Pos logit contributions
 paramed+0.051
boys+0.050
 Lee+0.050
 chefs+0.046
 reporter+0.045
Neg logit contributions
 day-0.056
 night-0.054
 time-0.052
 morning-0.051
 nights-0.051
Token.
Token ID13
Feature activation-6.42e-02

Pos logit contributions
 day+0.087
 night+0.085
 nights+0.083
 morning+0.079
 time+0.078
Neg logit contributions
boys-0.126
 paramed-0.126
 chefs-0.122
 Lee-0.120
 principal-0.115
Token<|endoftext|>
Token ID50256
Feature activation-1.84e-01

Pos logit contributions
 nights+0.106
 day+0.106
 night+0.105
 afternoon+0.099
 time+0.099
Neg logit contributions
boys-0.094
 paramed-0.094
 Lee-0.092
 chefs-0.090
 reporter-0.084
TokenOne
Token ID3198
Feature activation-2.14e-01

Pos logit contributions
 nights+0.324
fy+0.324
 spine+0.294
 day+0.294
ly+0.291
Neg logit contributions
 Lee-0.252
 chefs-0.248
boys-0.246
 paramed-0.234
 principal-0.223
Token day
Token ID1110
Feature activation-2.87e-01

Pos logit contributions
fy+0.213
 Along+0.204
ight+0.193
lessly+0.192
 spine+0.189
Neg logit contributions
 dads-0.418
 qu-0.403
 dad-0.400
 band-0.400
 fountain-0.394
Token,
Token ID11
Feature activation+3.46e-02

Pos logit contributions
 nights+0.627
fy+0.608
found+0.567
ight+0.560
rated+0.559
Neg logit contributions
 Lee-0.290
 chefs-0.270
 paramed-0.255
boys-0.246
 printer-0.232
Token Ben
Token ID3932
Feature activation+2.79e-02

Pos logit contributions
boys+0.041
 chefs+0.040
 paramed+0.039
 Lee+0.039
 printer+0.035
Neg logit contributions
 nights-0.069
 day-0.066
 night-0.065
fy-0.065
 afternoon-0.063
Token and
Token ID290
Feature activation-6.89e-02

Pos logit contributions
boys+0.040
 chefs+0.038
 paramed+0.038
 Lee+0.037
 printer+0.035
Neg logit contributions
 nights-0.047
 day-0.046
fy-0.046
 night-0.046
 Along-0.044
Token Lily
Token ID20037
Feature activation+1.48e-03

Pos logit contributions
 day+0.102
 night+0.100
 nights+0.094
 morning+0.094
 time+0.092
Neg logit contributions
boys-0.123
 paramed-0.121
 chefs-0.114
 Lee-0.114
 principal-0.113
Token went
Token ID1816
Feature activation-1.05e-01

Pos logit contributions
boys+0.002
 paramed+0.002
 chefs+0.002
 Lee+0.002
 principal+0.002
Neg logit contributions
 day-0.003
 night-0.002
 nights-0.002
 morning-0.002
 time-0.002
Token cold
Token ID4692
Feature activation-2.26e-01

Pos logit contributions
 day+0.224
 night+0.218
 nights+0.212
 time+0.205
 morning+0.204
Neg logit contributions
 paramed-0.171
boys-0.168
 chefs-0.160
 Lee-0.160
 reporter-0.151
Token winter
Token ID7374
Feature activation-2.66e-01

Pos logit contributions
 Along+0.328
fy+0.325
 nights+0.315
found+0.314
 day+0.304
Neg logit contributions
 chefs-0.367
boys-0.364
 paramed-0.360
 Lee-0.352
 printer-0.324
Token snow
Token ID6729
Feature activation-1.51e-01

Pos logit contributions
 Along+0.351
fy+0.350
found+0.349
 nights+0.338
ight+0.331
Neg logit contributions
boys-0.462
 paramed-0.454
 chefs-0.440
 Lee-0.439
 printer-0.412
Token.
Token ID13
Feature activation-6.48e-02

Pos logit contributions
fy+0.233
found+0.230
 nights+0.228
 Along+0.228
 day+0.220
Neg logit contributions
boys-0.239
 paramed-0.229
 Lee-0.221
 chefs-0.220
 printer-0.205
Token One
Token ID1881
Feature activation-1.45e-01

Pos logit contributions
 nights+0.113
 night+0.109
 day+0.108
fy+0.107
 afternoon+0.104
Neg logit contributions
 Lee-0.091
 paramed-0.089
boys-0.086
 chefs-0.083
 printer-0.076
Token day
Token ID1110
Feature activation-2.87e-01

Pos logit contributions
 Along+0.144
ets+0.136
ides+0.135
 spine+0.135
ight+0.130
Neg logit contributions
 paramed-0.294
 duck-0.289
 mixer-0.280
 qu-0.269
 sprayed-0.269
Token,
Token ID11
Feature activation+5.25e-02

Pos logit contributions
 day+0.465
 nights+0.464
 night+0.457
fy+0.440
 afternoon+0.437
Neg logit contributions
 paramed-0.430
boys-0.426
 Lee-0.420
 chefs-0.417
 reporter-0.381
Token she
Token ID673
Feature activation-1.59e-01

Pos logit contributions
boys+0.079
 paramed+0.078
 chefs+0.076
 Lee+0.075
 printer+0.070
Neg logit contributions
 day-0.087
 night-0.086
 nights-0.085
 morning-0.081
 afternoon-0.081
Token went
Token ID1816
Feature activation-9.70e-02

Pos logit contributions
 day+0.310
 nights+0.307
 night+0.305
 afternoon+0.293
fy+0.293
Neg logit contributions
boys-0.191
 paramed-0.186
 chefs-0.180
 Lee-0.173
 groom-0.164
Token outside
Token ID2354
Feature activation-1.46e-01

Pos logit contributions
 nights+0.183
ight+0.177
fy+0.176
 day+0.175
 afternoon+0.172
Neg logit contributions
boys-0.119
 paramed-0.117
 Lee-0.117
 chefs-0.116
 principal-0.105
Token to
Token ID284
Feature activation+4.36e-02

Pos logit contributions
fy+0.294
 nights+0.283
ight+0.279
rated+0.265
 day+0.265
Neg logit contributions
 Lee-0.161
 chefs-0.157
boys-0.157
 paramed-0.155
 printer-0.139
Token her
Token ID607
Feature activation-1.65e-01

Pos logit contributions
boys+0.075
 paramed+0.071
 chefs+0.070
 printer+0.069
 Lee+0.067
Neg logit contributions
 nights-0.076
fy-0.075
 night-0.072
rated-0.070
 morning-0.069
Token heart
Token ID2612
Feature activation+2.63e-03

Pos logit contributions
 nights+0.294
 Along+0.282
fy+0.282
 night+0.280
 day+0.279
Neg logit contributions
boys-0.217
 Lee-0.206
 chefs-0.204
 paramed-0.204
 groom-0.199
Token.
Token ID13
Feature activation-5.02e-02

Pos logit contributions
boys+0.004
 paramed+0.004
 chefs+0.004
 Lee+0.004
 groom+0.004
Neg logit contributions
 day-0.004
 nights-0.004
 night-0.004
 morning-0.003
 afternoon-0.003
Token<|endoftext|>
Token ID50256
Feature activation-1.83e-01

Pos logit contributions
 nights+0.082
 night+0.080
 day+0.080
fy+0.077
 afternoon+0.075
Neg logit contributions
 Lee-0.076
 paramed-0.075
boys-0.073
 chefs-0.070
 principal-0.068
TokenOne
Token ID3198
Feature activation-2.10e-01

Pos logit contributions
fy+0.333
 nights+0.331
 spine+0.302
 day+0.300
ly+0.299
Neg logit contributions
 Lee-0.248
boys-0.237
 chefs-0.234
 paramed-0.225
 principal-0.212
Token day
Token ID1110
Feature activation-2.87e-01

Pos logit contributions
fy+0.190
 Along+0.183
 spine+0.180
 nights+0.178
lessly+0.176
Neg logit contributions
 dads-0.406
 qu-0.402
 mixer-0.394
 paramed-0.393
 band-0.391
Token,
Token ID11
Feature activation+4.02e-02

Pos logit contributions
 nights+0.588
fy+0.568
found+0.531
 night+0.530
ingle+0.526
Neg logit contributions
 Lee-0.322
 paramed-0.302
 chefs-0.298
boys-0.286
 printer-0.267
Token a
Token ID257
Feature activation-2.21e-02

Pos logit contributions
boys+0.045
 paramed+0.044
 chefs+0.044
 Lee+0.043
 printer+0.039
Neg logit contributions
 nights-0.081
 day-0.079
 night-0.079
fy-0.077
 morning-0.075
Token huge
Token ID3236
Feature activation-7.49e-02

Pos logit contributions
 day+0.027
 night+0.026
 nights+0.025
 time+0.024
 morning+0.024
Neg logit contributions
boys-0.044
 paramed-0.043
 chefs-0.042
 Lee-0.042
 principal-0.040
Token human
Token ID1692
Feature activation+1.07e-02

Pos logit contributions
 day+0.149
 night+0.142
 morning+0.137
 time+0.135
 afternoon+0.132
Neg logit contributions
boys-0.105
 paramed-0.098
 chefs-0.097
 Lee-0.093
 wrists-0.092
Token was
Token ID373
Feature activation-3.92e-03

Pos logit contributions
 paramed+0.014
boys+0.014
 chefs+0.013
 Lee+0.013
 wrists+0.013
Neg logit contributions
 day-0.020
 night-0.020
 morning-0.019
 nights-0.019
 time-0.019
Token girl
Token ID2576
Feature activation+1.95e-02

Pos logit contributions
 day+0.246
 night+0.240
 nights+0.232
 morning+0.230
 time+0.226
Neg logit contributions
boys-0.177
 paramed-0.175
 chefs-0.166
 Lee-0.165
 principal-0.158
Token named
Token ID3706
Feature activation-7.38e-02

Pos logit contributions
 paramed+0.025
boys+0.025
 chefs+0.024
 Lee+0.024
 principal+0.023
Neg logit contributions
 day-0.037
 night-0.036
 nights-0.035
 morning-0.034
 time-0.034
Token Lily
Token ID20037
Feature activation-1.91e-03

Pos logit contributions
 day+0.144
 night+0.142
 nights+0.140
 morning+0.136
 time+0.135
Neg logit contributions
boys-0.090
 paramed-0.089
 chefs-0.086
 Lee-0.082
 reporter-0.078
Token.
Token ID13
Feature activation-6.68e-02

Pos logit contributions
 nights+0.003
 day+0.003
 night+0.003
 afternoon+0.003
fy+0.003
Neg logit contributions
boys-0.003
 Lee-0.003
 paramed-0.003
 chefs-0.003
 groom-0.003
Token One
Token ID1881
Feature activation-1.48e-01

Pos logit contributions
 nights+0.104
 day+0.103
 night+0.102
fy+0.096
 afternoon+0.096
Neg logit contributions
boys-0.107
 paramed-0.106
 Lee-0.104
 chefs-0.102
 principal-0.096
Token day
Token ID1110
Feature activation-2.87e-01

Pos logit contributions
ides+0.183
ently+0.179
ets+0.167
ight+0.163
 spine+0.163
Neg logit contributions
 paramed-0.261
 sprayed-0.258
 duck-0.256
 qu-0.248
 printer-0.240
Token,
Token ID11
Feature activation+4.49e-02

Pos logit contributions
 nights+0.551
fy+0.521
 night+0.516
 day+0.515
ight+0.510
Neg logit contributions
 Lee-0.348
 paramed-0.338
 chefs-0.334
boys-0.322
 printer-0.294
Token she
Token ID673
Feature activation-1.60e-01

Pos logit contributions
boys+0.064
 chefs+0.064
 Lee+0.063
 paramed+0.063
 groom+0.059
Neg logit contributions
 nights-0.076
 night-0.074
 day-0.073
fy-0.073
 afternoon-0.070
Token was
Token ID373
Feature activation-2.44e-03

Pos logit contributions
 day+0.303
 nights+0.300
 night+0.298
 morning+0.286
 afternoon+0.285
Neg logit contributions
boys-0.203
 paramed-0.198
 chefs-0.192
 Lee-0.187
 printer-0.176
Token playing
Token ID2712
Feature activation-1.24e-01

Pos logit contributions
 day+0.004
 night+0.004
 nights+0.004
 morning+0.004
 time+0.004
Neg logit contributions
boys-0.004
 paramed-0.004
 chefs-0.004
 Lee-0.004
 reporter-0.003
Token outside
Token ID2354
Feature activation-1.46e-01

Pos logit contributions
 day+0.150
 night+0.139
 time+0.134
 morning+0.133
 nights+0.132
Neg logit contributions
 paramed-0.256
boys-0.250
 Lee-0.247
 reporter-0.237
 wrists-0.236
Token girl
Token ID2576
Feature activation+1.95e-02

Pos logit contributions
 day+0.246
 night+0.240
 nights+0.232
 morning+0.230
 time+0.226
Neg logit contributions
boys-0.177
 paramed-0.175
 chefs-0.166
 Lee-0.165
 principal-0.158
Token named
Token ID3706
Feature activation-7.38e-02

Pos logit contributions
 paramed+0.025
boys+0.025
 chefs+0.024
 Lee+0.024
 principal+0.023
Neg logit contributions
 day-0.037
 night-0.036
 nights-0.035
 morning-0.034
 time-0.034
Token Lily
Token ID20037
Feature activation-1.91e-03

Pos logit contributions
 day+0.144
 night+0.142
 nights+0.140
 morning+0.136
 time+0.135
Neg logit contributions
boys-0.090
 paramed-0.089
 chefs-0.086
 Lee-0.082
 reporter-0.078
Token.
Token ID13
Feature activation-6.68e-02

Pos logit contributions
 nights+0.003
 day+0.003
 night+0.003
 afternoon+0.003
fy+0.003
Neg logit contributions
boys-0.003
 Lee-0.003
 paramed-0.003
 chefs-0.003
 groom-0.003
Token One
Token ID1881
Feature activation-1.48e-01

Pos logit contributions
 nights+0.104
 day+0.103
 night+0.102
fy+0.096
 afternoon+0.096
Neg logit contributions
boys-0.107
 paramed-0.106
 Lee-0.104
 chefs-0.102
 principal-0.096
Token day
Token ID1110
Feature activation-2.87e-01

Pos logit contributions
ides+0.183
ently+0.179
ets+0.167
ight+0.163
 spine+0.163
Neg logit contributions
 paramed-0.261
 sprayed-0.258
 duck-0.256
 qu-0.248
 printer-0.240
Token,
Token ID11
Feature activation+4.49e-02

Pos logit contributions
 nights+0.551
fy+0.521
 night+0.516
 day+0.515
ight+0.510
Neg logit contributions
 Lee-0.348
 paramed-0.338
 chefs-0.334
boys-0.322
 printer-0.294
Token Lily
Token ID20037
Feature activation+1.06e-02

Pos logit contributions
boys+0.064
 chefs+0.064
 Lee+0.063
 paramed+0.063
 groom+0.059
Neg logit contributions
 nights-0.076
 night-0.074
 day-0.073
fy-0.073
 afternoon-0.070
Token went
Token ID1816
Feature activation-9.93e-02

Pos logit contributions
boys+0.014
 chefs+0.013
 paramed+0.013
 Lee+0.013
 printer+0.012
Neg logit contributions
 nights-0.019
 day-0.019
fy-0.019
 night-0.018
 afternoon-0.018
Token to
Token ID284
Feature activation+3.69e-02

Pos logit contributions
 nights+0.199
ight+0.196
fy+0.192
rated+0.188
 time+0.184
Neg logit contributions
boys-0.114
 Lee-0.113
 chefs-0.108
 paramed-0.104
 principal-0.100
Token the
Token ID262
Feature activation+1.38e-02

Pos logit contributions
boys+0.043
 paramed+0.043
 chefs+0.041
 Lee+0.040
 reporter+0.037
Neg logit contributions
 day-0.074
 night-0.073
 nights-0.073
 morning-0.070
 time-0.070
Token her
Token ID607
Feature activation-1.76e-01

Pos logit contributions
 day+0.257
 night+0.253
 nights+0.252
 morning+0.241
 afternoon+0.240
Neg logit contributions
boys-0.188
 paramed-0.184
 chefs-0.178
 Lee-0.176
 printer-0.164
Token face
Token ID1986
Feature activation+3.51e-02

Pos logit contributions
 nights+0.312
 Along+0.308
fy+0.303
ingle+0.303
way+0.299
Neg logit contributions
boys-0.229
 wrists-0.222
 Lee-0.212
 printer-0.208
 principal-0.205
Token.
Token ID13
Feature activation-5.12e-02

Pos logit contributions
boys+0.068
 paramed+0.067
 chefs+0.066
 Lee+0.065
 groom+0.062
Neg logit contributions
 day-0.043
 night-0.042
 nights-0.042
 morning-0.039
 afternoon-0.038
Token<|endoftext|>
Token ID50256
Feature activation-1.86e-01

Pos logit contributions
 nights+0.081
 day+0.080
 night+0.080
fy+0.076
 afternoon+0.075
Neg logit contributions
 Lee-0.079
 paramed-0.079
boys-0.078
 chefs-0.075
 principal-0.071
TokenOne
Token ID3198
Feature activation-2.13e-01

Pos logit contributions
 nights+0.348
fy+0.348
 spine+0.317
ly+0.315
 day+0.312
Neg logit contributions
 Lee-0.243
boys-0.227
 chefs-0.226
 paramed-0.217
 principal-0.205
Token day
Token ID1110
Feature activation-2.86e-01

Pos logit contributions
fy+0.194
 Along+0.194
 nights+0.193
 spine+0.187
lessly+0.187
Neg logit contributions
 dads-0.400
 mixer-0.395
 qu-0.392
 dad-0.388
 band-0.386
Token,
Token ID11
Feature activation+3.40e-02

Pos logit contributions
 nights+0.609
fy+0.584
found+0.546
ingle+0.540
 night+0.540
Neg logit contributions
 Lee-0.308
 paramed-0.283
 chefs-0.282
boys-0.260
 ha-0.250
Token a
Token ID257
Feature activation-2.25e-02

Pos logit contributions
boys+0.033
 chefs+0.033
 Lee+0.033
 paramed+0.032
 printer+0.028
Neg logit contributions
 nights-0.074
fy-0.071
 day-0.070
 night-0.070
 afternoon-0.067
Token little
Token ID1310
Feature activation-1.09e-01

Pos logit contributions
 day+0.028
 night+0.027
 nights+0.025
 time+0.025
 morning+0.025
Neg logit contributions
boys-0.045
 paramed-0.044
 chefs-0.042
 Lee-0.042
 principal-0.040
Token boy
Token ID2933
Feature activation+9.11e-02

Pos logit contributions
 day+0.208
 night+0.202
 morning+0.193
 afternoon+0.188
 nights+0.188
Neg logit contributions
boys-0.150
 paramed-0.144
 chefs-0.139
 Lee-0.136
 principal-0.136
Token's
Token ID338
Feature activation+3.79e-02

Pos logit contributions
boys+0.086
 paramed+0.084
 chefs+0.081
 Lee+0.077
 printer+0.072
Neg logit contributions
 nights-0.199
 day-0.198
 night-0.196
fy-0.192
 afternoon-0.189
Token cars
Token ID5006
Feature activation-8.67e-02

Pos logit contributions
 day+0.097
 night+0.095
 nights+0.093
 morning+0.090
 time+0.089
Neg logit contributions
 paramed-0.093
boys-0.093
 chefs-0.090
 Lee-0.088
 reporter-0.084
Token and
Token ID290
Feature activation-7.66e-02

Pos logit contributions
 day+0.119
 night+0.117
 nights+0.117
 morning+0.110
 afternoon+0.109
Neg logit contributions
boys-0.153
 paramed-0.151
 chefs-0.147
 Lee-0.145
 printer-0.138
Token trucks
Token ID13960
Feature activation-3.70e-02

Pos logit contributions
 day+0.136
 night+0.132
 nights+0.130
 morning+0.124
 time+0.124
Neg logit contributions
 paramed-0.116
boys-0.106
 chefs-0.105
 Lee-0.101
 reporter-0.098
Token.
Token ID13
Feature activation-6.29e-02

Pos logit contributions
 day+0.047
 night+0.046
 nights+0.045
 morning+0.043
 time+0.042
Neg logit contributions
 paramed-0.070
boys-0.070
 chefs-0.068
 Lee-0.067
 groom-0.064
Token One
Token ID1881
Feature activation-1.48e-01

Pos logit contributions
 day+0.099
 nights+0.097
 night+0.097
 morning+0.091
 afternoon+0.091
Neg logit contributions
boys-0.099
 paramed-0.099
 chefs-0.095
 Lee-0.095
 principal-0.089
Token day
Token ID1110
Feature activation-2.86e-01

Pos logit contributions
ight+0.097
fy+0.094
 nights+0.087
 Along+0.085
ingle+0.079
Neg logit contributions
 paramed-0.350
 printer-0.349
 Lee-0.340
 mixer-0.337
 chefs-0.332
Token,
Token ID11
Feature activation+5.19e-02

Pos logit contributions
 day+0.459
 nights+0.459
 night+0.451
fy+0.431
 afternoon+0.430
Neg logit contributions
boys-0.434
 paramed-0.432
 chefs-0.424
 Lee-0.421
 printer-0.389
Token Tim
Token ID5045
Feature activation-1.91e-02

Pos logit contributions
boys+0.076
 paramed+0.075
 chefs+0.070
 Lee+0.069
 principal+0.067
Neg logit contributions
 day-0.091
 night-0.089
 nights-0.087
 morning-0.085
 time-0.084
Tokenmy
Token ID1820
Feature activation-1.39e-01

Pos logit contributions
 nights+0.030
fy+0.029
 day+0.029
 Along+0.028
 night+0.028
Neg logit contributions
boys-0.030
 chefs-0.029
 Lee-0.028
 paramed-0.028
 principal-0.027
Token's
Token ID338
Feature activation+4.12e-02

Pos logit contributions
 day+0.243
 night+0.240
 nights+0.234
 morning+0.227
 time+0.226
Neg logit contributions
 paramed-0.200
boys-0.198
 chefs-0.189
 Lee-0.188
 groom-0.176
Token mom
Token ID1995
Feature activation+9.71e-02

Pos logit contributions
boys+0.041
 paramed+0.040
 chefs+0.039
 Lee+0.038
 printer+0.035
Neg logit contributions
 nights-0.091
 night-0.089
 day-0.088
fy-0.087
 afternoon-0.085
Token the
Token ID262
Feature activation-1.21e-02

Pos logit contributions
 day+0.247
 nights+0.245
 night+0.244
fy+0.236
 morning+0.234
Neg logit contributions
boys-0.127
 paramed-0.120
 chefs-0.117
 Lee-0.115
 printer-0.106
Token swings
Token ID26728
Feature activation-5.75e-03

Pos logit contributions
 day+0.021
 nights+0.021
 night+0.021
fy+0.020
 morning+0.020
Neg logit contributions
boys-0.017
 paramed-0.016
 chefs-0.016
 Lee-0.015
 printer-0.015
Token.
Token ID13
Feature activation-4.90e-02

Pos logit contributions
 nights+0.008
 day+0.008
 night+0.008
fy+0.007
 morning+0.007
Neg logit contributions
boys-0.010
 Lee-0.010
 paramed-0.010
 chefs-0.009
 printer-0.009
Token<|endoftext|>
Token ID50256
Feature activation-1.81e-01

Pos logit contributions
 nights+0.081
 night+0.080
 day+0.079
fy+0.076
 afternoon+0.075
Neg logit contributions
boys-0.073
 Lee-0.072
 paramed-0.072
 chefs-0.069
 principal-0.065
TokenOne
Token ID3198
Feature activation-2.14e-01

Pos logit contributions
 nights+0.326
fy+0.321
 day+0.297
 night+0.296
ly+0.294
Neg logit contributions
 Lee-0.241
boys-0.239
 chefs-0.237
 paramed-0.226
 principal-0.213
Token day
Token ID1110
Feature activation-2.86e-01

Pos logit contributions
fy+0.213
 nights+0.211
lessly+0.202
ly+0.201
 Along+0.200
Neg logit contributions
 dads-0.422
 dad-0.398
 qu-0.389
 band-0.388
 mean-0.385
Token,
Token ID11
Feature activation+3.47e-02

Pos logit contributions
 nights+0.647
fy+0.618
found+0.577
adows+0.571
rated+0.571
Neg logit contributions
 Lee-0.278
 chefs-0.251
 paramed-0.238
boys-0.222
 ha-0.220
Token Little
Token ID7703
Feature activation-9.09e-02

Pos logit contributions
 chefs+0.036
boys+0.035
 paramed+0.034
 Lee+0.034
 printer+0.031
Neg logit contributions
 nights-0.074
fy-0.071
 day-0.070
 night-0.070
 afternoon-0.067
Token Billy
Token ID15890
Feature activation+8.76e-03

Pos logit contributions
 day+0.170
 night+0.167
 nights+0.163
 morning+0.160
 time+0.158
Neg logit contributions
boys-0.122
 paramed-0.121
 chefs-0.116
 Lee-0.111
 principal-0.108
Token was
Token ID373
Feature activation-4.60e-03

Pos logit contributions
boys+0.012
 chefs+0.011
 paramed+0.011
 Lee+0.011
 printer+0.010
Neg logit contributions
 nights-0.015
fy-0.015
 day-0.015
 night-0.015
 Along-0.014
Token feeling
Token ID4203
Feature activation-1.36e-02

Pos logit contributions
fy+0.009
 nights+0.009
 night+0.008
 day+0.008
ight+0.008
Neg logit contributions
 paramed-0.006
 chefs-0.006
boys-0.006
 Lee-0.005
 printer-0.005
Token a
Token ID257
Feature activation-4.55e-02

Pos logit contributions
 day+0.097
 night+0.096
 nights+0.095
 morning+0.091
 time+0.091
Neg logit contributions
boys-0.072
 paramed-0.071
 chefs-0.069
 Lee-0.067
 reporter-0.063
Token smile
Token ID8212
Feature activation+7.42e-02

Pos logit contributions
 day+0.070
 night+0.067
 time+0.065
 morning+0.064
 afternoon+0.062
Neg logit contributions
boys-0.079
 paramed-0.078
 chefs-0.075
 Lee-0.074
 principal-0.070
Token.
Token ID13
Feature activation-5.13e-02

Pos logit contributions
boys+0.131
 paramed+0.129
 Lee+0.128
 chefs+0.126
 groom+0.123
Neg logit contributions
 nights-0.100
 day-0.097
 night-0.095
fy-0.093
 Along-0.092
Token<|endoftext|>
Token ID50256
Feature activation-1.83e-01

Pos logit contributions
 nights+0.081
 day+0.079
 night+0.079
fy+0.075
 afternoon+0.074
Neg logit contributions
 Lee-0.080
boys-0.079
 paramed-0.079
 chefs-0.077
 principal-0.072
TokenOne
Token ID3198
Feature activation-2.13e-01

Pos logit contributions
 nights+0.323
fy+0.319
 day+0.295
 spine+0.293
 night+0.291
Neg logit contributions
 Lee-0.253
boys-0.245
 chefs-0.244
 paramed-0.231
 reporter-0.219
Token day
Token ID1110
Feature activation-2.86e-01

Pos logit contributions
fy+0.192
 Along+0.187
lessly+0.185
 spine+0.185
 nights+0.182
Neg logit contributions
 qu-0.405
 dads-0.404
 band-0.393
 mixer-0.392
 dad-0.391
Token,
Token ID11
Feature activation+3.81e-02

Pos logit contributions
 nights+0.610
fy+0.583
 night+0.543
ingle+0.543
found+0.541
Neg logit contributions
 Lee-0.305
 chefs-0.279
 paramed-0.273
boys-0.266
 printer-0.245
Token m
Token ID285
Feature activation+4.99e-02

Pos logit contributions
boys+0.038
 Lee+0.038
 chefs+0.038
 paramed+0.037
 printer+0.032
Neg logit contributions
 nights-0.083
fy-0.079
 night-0.078
 day-0.077
 afternoon-0.075
Tokenama
Token ID1689
Feature activation-2.59e-02

Pos logit contributions
 paramed+0.074
 Lee+0.069
boys+0.064
 ha+0.059
 principal+0.059
Neg logit contributions
 nights-0.091
 night-0.089
 day-0.087
 time-0.087
 afternoon-0.086
Token and
Token ID290
Feature activation-6.21e-02

Pos logit contributions
 day+0.041
 night+0.040
 nights+0.039
 morning+0.038
 time+0.037
Neg logit contributions
boys-0.042
 paramed-0.042
 chefs-0.040
 Lee-0.040
 principal-0.038
Token her
Token ID607
Feature activation-1.44e-01

Pos logit contributions
 day+0.100
 night+0.100
 morning+0.094
 time+0.090
 evening+0.090
Neg logit contributions
boys-0.104
 principal-0.100
 paramed-0.097
 wrists-0.094
 printer-0.094
Token much
Token ID881
Feature activation-1.45e-01

Pos logit contributions
 nights+0.057
 Along+0.057
 spine+0.055
fy+0.054
ingle+0.052
Neg logit contributions
 groom-0.035
 paramed-0.035
 dads-0.034
 chefs-0.033
 qu-0.033
Token fun
Token ID1257
Feature activation-9.30e-02

Pos logit contributions
 Along+0.220
 nights+0.220
 night+0.211
 day+0.210
fy+0.209
Neg logit contributions
 chefs-0.219
 paramed-0.217
boys-0.215
 Lee-0.199
 reporter-0.197
Token."
Token ID526
Feature activation+1.14e-01

Pos logit contributions
 nights+0.125
 day+0.124
 night+0.124
fy+0.121
 Along+0.118
Neg logit contributions
boys-0.163
 chefs-0.158
 paramed-0.157
 Lee-0.154
 reporter-0.147
Token<|endoftext|>
Token ID50256
Feature activation-1.80e-01

Pos logit contributions
boys+0.187
 paramed+0.185
 chefs+0.179
 Lee+0.178
 principal+0.168
Neg logit contributions
 day-0.173
 night-0.171
 nights-0.170
 morning-0.161
 afternoon-0.160
TokenOne
Token ID3198
Feature activation-2.06e-01

Pos logit contributions
 nights+0.322
fy+0.318
 day+0.295
 night+0.290
 spine+0.288
Neg logit contributions
 Lee-0.245
boys-0.235
 chefs-0.231
 paramed-0.226
 principal-0.213
Token day
Token ID1110
Feature activation-2.86e-01

Pos logit contributions
 Along+0.143
fy+0.137
 nights+0.130
 spine+0.127
lessly+0.122
Neg logit contributions
 paramed-0.444
 qu-0.439
 dads-0.438
 mixer-0.432
 bully-0.431
Token,
Token ID11
Feature activation+4.06e-02

Pos logit contributions
 nights+0.561
fy+0.540
 night+0.510
 day+0.505
found+0.504
Neg logit contributions
 Lee-0.338
 chefs-0.321
 paramed-0.318
boys-0.314
 printer-0.289
Token Ken
Token ID7148
Feature activation-5.81e-02

Pos logit contributions
boys+0.045
 paramed+0.044
 chefs+0.043
 Lee+0.043
 reporter+0.038
Neg logit contributions
 nights-0.082
 day-0.081
 night-0.081
fy-0.079
 morning-0.077
Token and
Token ID290
Feature activation-5.82e-02

Pos logit contributions
 nights+0.102
fy+0.098
 day+0.097
 night+0.095
 afternoon+0.093
Neg logit contributions
boys-0.081
 Lee-0.078
 paramed-0.077
 chefs-0.074
 reporter-0.071
Token his
Token ID465
Feature activation-1.12e-01

Pos logit contributions
 day+0.073
 night+0.069
 morning+0.064
 nights+0.064
 time+0.064
Neg logit contributions
boys-0.119
 paramed-0.117
 chefs-0.112
 printer-0.110
 wrists-0.110
Token Mom
Token ID11254
Feature activation+3.35e-02

Pos logit contributions
 day+0.233
 nights+0.232
 night+0.231
 morning+0.222
 afternoon+0.221
Neg logit contributions
boys-0.122
 paramed-0.118
 chefs-0.114
 Lee-0.111
 printer-0.102
Token toys
Token ID14958
Feature activation-1.01e-01

Pos logit contributions
boys+0.025
 paramed+0.025
 Lee+0.024
 chefs+0.024
 principal+0.022
Neg logit contributions
 day-0.042
 night-0.042
 nights-0.041
 morning-0.040
 time-0.040
Token and
Token ID290
Feature activation-7.35e-02

Pos logit contributions
 day+0.135
 night+0.132
 nights+0.131
 morning+0.124
 time+0.123
Neg logit contributions
boys-0.182
 paramed-0.180
 chefs-0.175
 Lee-0.173
 reporter-0.165
Token books
Token ID3835
Feature activation-6.05e-02

Pos logit contributions
 day+0.128
 night+0.125
 nights+0.122
 morning+0.118
 afternoon+0.117
Neg logit contributions
 paramed-0.111
boys-0.107
 chefs-0.104
 Lee-0.103
 reporter-0.097
Token.
Token ID13
Feature activation-6.29e-02

Pos logit contributions
 day+0.076
 nights+0.074
 night+0.074
 morning+0.069
 afternoon+0.069
Neg logit contributions
boys-0.115
 paramed-0.113
 chefs-0.110
 Lee-0.109
 reporter-0.104
Token One
Token ID1881
Feature activation-1.52e-01

Pos logit contributions
 day+0.097
 nights+0.097
 night+0.096
fy+0.091
 afternoon+0.091
Neg logit contributions
boys-0.100
 paramed-0.099
 Lee-0.097
 chefs-0.096
 principal-0.089
Token day
Token ID1110
Feature activation-2.85e-01

Pos logit contributions
ight+0.086
fy+0.083
 Along+0.083
 nights+0.079
ingle+0.071
Neg logit contributions
 paramed-0.365
 printer-0.360
 mixer-0.355
 Lee-0.354
 chefs-0.351
Token,
Token ID11
Feature activation+5.00e-02

Pos logit contributions
 nights+0.475
 day+0.470
 night+0.463
fy+0.451
 afternoon+0.445
Neg logit contributions
boys-0.414
 paramed-0.413
 Lee-0.410
 chefs-0.408
 printer-0.370
Token Lily
Token ID20037
Feature activation+6.92e-03

Pos logit contributions
boys+0.073
 paramed+0.072
 chefs+0.068
 Lee+0.067
 reporter+0.064
Neg logit contributions
 day-0.087
 night-0.085
 nights-0.084
 morning-0.081
 time-0.081
Token has
Token ID468
Feature activation+1.69e-03

Pos logit contributions
boys+0.010
 paramed+0.010
 chefs+0.010
 Lee+0.009
 reporter+0.009
Neg logit contributions
 day-0.012
 night-0.012
 nights-0.012
 morning-0.011
 time-0.011
Token a
Token ID257
Feature activation-1.33e-02

Pos logit contributions
boys+0.002
 paramed+0.002
 chefs+0.002
 Lee+0.002
 reporter+0.002
Neg logit contributions
 day-0.003
 night-0.003
 nights-0.003
 morning-0.003
 time-0.003
Token new
Token ID649
Feature activation-6.56e-02

Pos logit contributions
 day+0.020
 night+0.019
 time+0.019
 morning+0.018
 evening+0.017
Neg logit contributions
boys-0.025
 chefs-0.024
 paramed-0.023
 Lee-0.023
 principal-0.022
Token man
Token ID582
Feature activation+1.47e-01

Pos logit contributions
boys+0.055
 wrists+0.048
 chefs+0.048
 paramed+0.045
 groom+0.044
Neg logit contributions
 day-0.075
 night-0.069
 time-0.069
 morning-0.067
ly-0.064
Token didn
Token ID1422
Feature activation-4.05e-02

Pos logit contributions
 chefs+0.240
 paramed+0.239
 Lee+0.236
 groom+0.230
boys+0.225
Neg logit contributions
 day-0.235
 night-0.219
 time-0.218
 nights-0.213
way-0.205
Token't
Token ID470
Feature activation-4.84e-03

Pos logit contributions
 nights+0.065
 day+0.065
 night+0.064
 afternoon+0.061
 morning+0.061
Neg logit contributions
boys-0.063
 paramed-0.062
 Lee-0.059
 chefs-0.059
 principal-0.056
Token like
Token ID588
Feature activation-1.08e-02

Pos logit contributions
 day+0.008
 night+0.008
 nights+0.008
 time+0.008
 morning+0.008
Neg logit contributions
boys-0.007
 paramed-0.007
 chefs-0.007
 Lee-0.007
 printer-0.007
Token to
Token ID284
Feature activation+6.55e-02

Pos logit contributions
 day+0.020
 night+0.019
 time+0.019
 nights+0.018
 morning+0.018
Neg logit contributions
 paramed-0.016
boys-0.016
 chefs-0.014
 Lee-0.014
 groom-0.014
Token fight
Token ID1907
Feature activation+1.79e-01

Pos logit contributions
 chefs+0.101
 paramed+0.101
 printer+0.101
 wrists+0.096
 Lee+0.096
Neg logit contributions
 day-0.113
 time-0.110
 night-0.102
ie-0.100
 morning-0.094
Token and
Token ID290
Feature activation-2.88e-02

Pos logit contributions
 paramed+0.325
boys+0.321
 chefs+0.312
 Lee+0.303
 groom+0.300
Neg logit contributions
 day-0.254
 night-0.247
 nights-0.239
 time-0.237
 morning-0.230
Token he
Token ID339
Feature activation-1.19e-01

Pos logit contributions
 day+0.048
 night+0.047
 morning+0.044
 nights+0.044
 time+0.043
Neg logit contributions
 paramed-0.046
 chefs-0.045
boys-0.044
 Lee-0.042
 printer-0.041
Token tried
Token ID3088
Feature activation+2.28e-02

Pos logit contributions
 day+0.175
 time+0.165
 night+0.164
ie+0.153
 morning+0.152
Neg logit contributions
 chefs-0.215
 paramed-0.206
 Lee-0.199
 principal-0.194
 printer-0.193
Token to
Token ID284
Feature activation+6.59e-02

Pos logit contributions
 paramed+0.051
 groom+0.048
boys+0.047
 chefs+0.046
 printer+0.046
Neg logit contributions
 day-0.028
 time-0.027
 night-0.024
way-0.022
 morning-0.022
Token get
Token ID651
Feature activation+4.09e-02

Pos logit contributions
 Lee+0.101
 chefs+0.101
 paramed+0.100
 printer+0.095
 reporter+0.092
Neg logit contributions
 day-0.110
 time-0.110
 night-0.101
 morning-0.095
 afternoon-0.094
Token,
Token ID11
Feature activation+8.82e-02

Pos logit contributions
 day+0.101
 night+0.099
 morning+0.090
 time+0.089
 afternoon+0.085
Neg logit contributions
 paramed-0.192
boys-0.182
 chefs-0.180
 principal-0.178
 groom-0.172
Token I
Token ID314
Feature activation+7.84e-02

Pos logit contributions
boys+0.139
 paramed+0.138
 Lee+0.130
 principal+0.130
 chefs+0.127
Neg logit contributions
 day-0.150
 night-0.147
 morning-0.138
 time-0.138
 evening-0.131
Token want
Token ID765
Feature activation+1.14e-02

Pos logit contributions
boys+0.130
 paramed+0.125
 Lee+0.125
 chefs+0.118
 wrists+0.117
Neg logit contributions
 day-0.128
 night-0.126
 time-0.123
 morning-0.116
fy-0.116
Token that
Token ID326
Feature activation+4.81e-02

Pos logit contributions
 paramed+0.019
boys+0.018
 Lee+0.018
 chefs+0.017
 reporter+0.017
Neg logit contributions
 day-0.019
 night-0.018
 nights-0.017
 morning-0.017
 time-0.017
Token glass
Token ID5405
Feature activation+7.08e-02

Pos logit contributions
 paramed+0.082
boys+0.080
 chefs+0.078
 reporter+0.074
 principal+0.073
Neg logit contributions
 day-0.078
 night-0.076
 morning-0.072
 time-0.069
 afternoon-0.068
Token!"
Token ID2474
Feature activation+1.85e-01

Pos logit contributions
boys+0.115
 paramed+0.115
 chefs+0.110
 Lee+0.109
 principal+0.103
Neg logit contributions
 day-0.109
 night-0.107
 nights-0.106
 morning-0.101
 time-0.101
Token
Token ID198
Feature activation+1.09e-02

Pos logit contributions
 paramed+0.294
boys+0.287
 Lee+0.285
 chefs+0.275
 printer+0.264
Neg logit contributions
 nights-0.288
 day-0.285
 night-0.281
fy-0.274
 afternoon-0.268
Token
Token ID198
Feature activation+1.08e-02

Pos logit contributions
 paramed+0.018
boys+0.018
 Lee+0.017
 chefs+0.017
 printer+0.016
Neg logit contributions
 nights-0.016
 day-0.016
 night-0.016
fy-0.015
 afternoon-0.015
TokenMom
Token ID29252
Feature activation+3.44e-02

Pos logit contributions
boys+0.017
 chefs+0.016
 paramed+0.016
 Lee+0.016
 principal+0.015
Neg logit contributions
 day-0.018
 night-0.017
 nights-0.017
 morning-0.016
 afternoon-0.016
Tokenmy
Token ID1820
Feature activation-9.06e-02

Pos logit contributions
boys+0.072
 paramed+0.071
 chefs+0.071
 Lee+0.068
 principal+0.067
Neg logit contributions
 day-0.038
 night-0.037
 nights-0.035
 morning-0.034
 time-0.033
Token said
Token ID531
Feature activation+1.13e-02

Pos logit contributions
ie+0.124
 day+0.120
ly+0.119
 of+0.115
 night+0.115
Neg logit contributions
 chefs-0.168
 liar-0.164
 wasteful-0.157
 jury-0.154
 principal-0.151
Token want
Token ID765
Feature activation+6.26e-03

Pos logit contributions
 nights+0.136
 day+0.128
 night+0.127
 Along+0.124
 afternoon+0.124
Neg logit contributions
boys-0.100
 chefs-0.097
 paramed-0.097
 groom-0.090
 Lee-0.089
Token to
Token ID284
Feature activation+6.40e-02

Pos logit contributions
 paramed+0.011
boys+0.011
 chefs+0.011
 Lee+0.011
 reporter+0.010
Neg logit contributions
 day-0.010
 night-0.009
 morning-0.009
 nights-0.009
 time-0.009
Token play
Token ID711
Feature activation-8.63e-02

Pos logit contributions
 paramed+0.109
 chefs+0.107
boys+0.106
 Lee+0.105
 reporter+0.100
Neg logit contributions
 day-0.097
 night-0.095
 time-0.090
 morning-0.089
 nights-0.088
Token with
Token ID351
Feature activation+3.64e-03

Pos logit contributions
 day+0.112
 night+0.104
 time+0.103
 morning+0.098
 afternoon+0.092
Neg logit contributions
 paramed-0.184
 Lee-0.169
 dads-0.167
 chefs-0.164
boys-0.162
Token me
Token ID502
Feature activation-5.60e-02

Pos logit contributions
 paramed+0.007
boys+0.006
 chefs+0.006
 Lee+0.006
 reporter+0.006
Neg logit contributions
 day-0.005
 night-0.005
 nights-0.005
 time-0.005
 morning-0.005
Token?"
Token ID1701
Feature activation+1.56e-01

Pos logit contributions
 day+0.111
 night+0.109
 nights+0.105
 morning+0.104
 time+0.103
Neg logit contributions
 paramed-0.072
boys-0.068
 chefs-0.066
 Lee-0.064
 reporter-0.062
Token asked
Token ID1965
Feature activation+4.70e-02

Pos logit contributions
boys+0.238
 chefs+0.235
 paramed+0.226
 Lee+0.205
 reporter+0.205
Neg logit contributions
 day-0.273
 night-0.265
 morning-0.257
 time-0.249
 evening-0.243
Token Lily
Token ID20037
Feature activation+5.09e-02

Pos logit contributions
boys+0.069
 chefs+0.066
 paramed+0.065
 reporter+0.061
 principal+0.060
Neg logit contributions
 day-0.084
 night-0.082
 time-0.079
 morning-0.078
 nights-0.078
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
boys+0.102
 paramed+0.100
 chefs+0.098
 Lee+0.097
 principal+0.093
Neg logit contributions
 day-0.059
 night-0.058
 nights-0.058
 morning-0.054
 afternoon-0.053
Token
Token ID198
Feature activation-1.03e-03

Pos logit contributions
 day+0.014
 Along+0.013
 night+0.013
 morning+0.013
 time+0.013
Neg logit contributions
boys-0.032
 chefs-0.031
 paramed-0.030
 groom-0.029
 wasteful-0.029
Token
Token ID198
Feature activation-7.58e-04

Pos logit contributions
 day+0.001
 night+0.001
 time+0.001
 nights+0.001
 morning+0.001
Neg logit contributions
boys-0.002
 chefs-0.002
 paramed-0.002
 Lee-0.002
 groom-0.002
Token happy
Token ID3772
Feature activation-1.36e-02

Pos logit contributions
boys+0.045
 Lee+0.043
 chefs+0.042
 paramed+0.042
 principal+0.040
Neg logit contributions
 day-0.038
 night-0.037
 nights-0.035
 morning-0.035
 time-0.034
Token that
Token ID326
Feature activation+6.17e-02

Pos logit contributions
 day+0.020
 night+0.020
 nights+0.020
 morning+0.019
 time+0.019
Neg logit contributions
boys-0.023
 paramed-0.023
 chefs-0.022
 Lee-0.022
 groom-0.021
Token she
Token ID673
Feature activation-1.06e-01

Pos logit contributions
boys+0.118
 paramed+0.117
 chefs+0.114
 Lee+0.112
 reporter+0.107
Neg logit contributions
 day-0.078
 night-0.077
 nights-0.076
 morning-0.072
 afternoon-0.071
Token said
Token ID531
Feature activation+3.20e-02

Pos logit contributions
 day+0.151
 night+0.151
fy+0.147
 nights+0.145
 time+0.134
Neg logit contributions
 Lee-0.187
 paramed-0.184
 chefs-0.175
boys-0.173
 wrists-0.169
Token,
Token ID11
Feature activation+9.84e-02

Pos logit contributions
boys+0.062
 chefs+0.059
 paramed+0.057
 principal+0.056
 Lee+0.056
Neg logit contributions
 day-0.045
 night-0.043
 morning-0.042
 of-0.041
 time-0.040
Token "
Token ID366
Feature activation+2.39e-01

Pos logit contributions
boys+0.124
 chefs+0.118
 paramed+0.101
 principal+0.096
 Lee+0.095
Neg logit contributions
 day-0.201
 night-0.192
 Along-0.190
 morning-0.189
 time-0.183
TokenThank
Token ID10449
Feature activation+6.11e-02

Pos logit contributions
 paramed+0.228
boys+0.227
 chefs+0.212
 Lee+0.206
 groom+0.197
Neg logit contributions
 day-0.520
 night-0.514
 nights-0.514
 time-0.496
fy-0.493
Token you
Token ID345
Feature activation-6.60e-02

Pos logit contributions
boys+0.115
 paramed+0.114
 chefs+0.111
 Lee+0.109
 groom+0.105
Neg logit contributions
 day-0.079
 night-0.077
 nights-0.076
 morning-0.073
 time-0.072
Token for
Token ID329
Feature activation+3.26e-02

Pos logit contributions
 day+0.084
 night+0.082
 morning+0.077
 nights+0.076
 time+0.076
Neg logit contributions
boys-0.128
 chefs-0.126
 paramed-0.124
 wrists-0.123
 groom-0.122
Token answering
Token ID18877
Feature activation-5.70e-02

Pos logit contributions
 wrists+0.055
 Lee+0.055
boys+0.054
 paramed+0.051
 groom+0.051
Neg logit contributions
 day-0.052
 night-0.048
 nights-0.047
 time-0.046
 days-0.045
Token our
Token ID674
Feature activation+8.51e-02

Pos logit contributions
 time+0.080
 day+0.080
 night+0.078
 morning+0.074
 nights+0.072
Neg logit contributions
boys-0.105
 paramed-0.104
 chefs-0.101
 reporter-0.099
 liar-0.094
Token Jimmy
Token ID12963
Feature activation+9.14e-02

Pos logit contributions
boys+0.141
 paramed+0.137
 chefs+0.131
 Lee+0.127
 reporter+0.123
Neg logit contributions
 day-0.166
 night-0.165
 nights-0.161
 morning-0.157
 time-0.155
Token had
Token ID550
Feature activation-2.27e-02

Pos logit contributions
 paramed+0.151
 chefs+0.145
boys+0.141
 Lee+0.140
 principal+0.134
Neg logit contributions
 night-0.139
 day-0.138
 time-0.135
 nights-0.135
 morning-0.128
Token an
Token ID281
Feature activation+2.88e-02

Pos logit contributions
 time+0.038
 night+0.035
 day+0.033
 morning+0.032
 nights+0.031
Neg logit contributions
boys-0.039
 Lee-0.037
 reporter-0.035
 paramed-0.034
itor-0.033
Token idea
Token ID2126
Feature activation+5.64e-02

Pos logit contributions
boys+0.063
 Lee+0.060
 paramed+0.060
 chefs+0.059
 groom+0.058
Neg logit contributions
 day-0.031
 night-0.030
 time-0.029
 morning-0.028
 nights-0.028
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
boys+0.100
 paramed+0.098
 Lee+0.097
 chefs+0.096
 reporter+0.091
Neg logit contributions
 nights-0.077
 night-0.075
 day-0.074
 afternoon-0.071
fy-0.071
Token "
Token ID366
Feature activation+2.30e-01

Pos logit contributions
 day+0.013
 night+0.012
 nights+0.012
 morning+0.012
 time+0.011
Neg logit contributions
boys-0.021
 paramed-0.020
 chefs-0.020
 Lee-0.019
 groom-0.019
TokenMom
Token ID29252
Feature activation+4.27e-02

Pos logit contributions
boys+0.253
 paramed+0.247
 chefs+0.236
 Lee+0.232
 printer+0.212
Neg logit contributions
 day-0.477
 night-0.470
 nights-0.468
 morning-0.451
 afternoon-0.450
Tokenmy
Token ID1820
Feature activation-8.29e-02

Pos logit contributions
 paramed+0.093
boys+0.092
 chefs+0.089
 reporter+0.088
 groom+0.087
Neg logit contributions
 day-0.045
 night-0.043
 nights-0.039
 morning-0.039
 time-0.039
Token,
Token ID11
Feature activation+9.21e-02

Pos logit contributions
 day+0.113
 night+0.112
 time+0.104
 morning+0.103
fy+0.096
Neg logit contributions
 paramed-0.155
 principal-0.146
boys-0.145
 wrists-0.144
 chefs-0.143
Token I
Token ID314
Feature activation+8.20e-02

Pos logit contributions
boys+0.136
 paramed+0.132
 wrists+0.123
 Lee+0.121
 reporter+0.118
Neg logit contributions
 day-0.165
 night-0.162
 time-0.155
 morning-0.153
 nights-0.150
Token know
Token ID760
Feature activation+5.80e-02

Pos logit contributions
boys+0.129
 paramed+0.124
 Lee+0.122
 wrists+0.120
 chefs+0.119
Neg logit contributions
 day-0.137
 night-0.134
 time-0.134
 nights-0.125
 morning-0.125
Token was
Token ID373
Feature activation+1.56e-02

Pos logit contributions
 nights+0.111
 day+0.110
 night+0.110
 Along+0.106
fy+0.106
Neg logit contributions
boys-0.126
 chefs-0.123
 paramed-0.122
 Lee-0.120
 printer-0.117
Token about
Token ID546
Feature activation+1.65e-02

Pos logit contributions
boys+0.023
 paramed+0.023
 chefs+0.022
 Lee+0.021
 reporter+0.020
Neg logit contributions
 day-0.027
 night-0.026
 nights-0.026
 morning-0.025
 time-0.025
Token to
Token ID284
Feature activation+5.36e-02

Pos logit contributions
boys+0.022
 paramed+0.022
 chefs+0.021
 Lee+0.021
 reporter+0.019
Neg logit contributions
 day-0.030
 night-0.030
 nights-0.030
 morning-0.028
 time-0.028
Token happen
Token ID1645
Feature activation+1.77e-02

Pos logit contributions
boys+0.074
 paramed+0.074
 chefs+0.071
 Lee+0.070
 reporter+0.065
Neg logit contributions
 day-0.096
 night-0.094
 nights-0.093
 morning-0.090
 time-0.090
Token!
Token ID0
Feature activation+2.48e-02

Pos logit contributions
boys+0.031
 paramed+0.031
 chefs+0.030
 Lee+0.030
 printer+0.028
Neg logit contributions
 day-0.024
 night-0.024
 nights-0.024
 morning-0.022
 afternoon-0.022
Token
Token ID198
Feature activation+9.76e-03

Pos logit contributions
 Lee+0.039
 paramed+0.039
boys+0.039
 chefs+0.037
 principal+0.036
Neg logit contributions
 nights-0.038
 day-0.038
 night-0.038
 afternoon-0.036
fy-0.036
Token
Token ID198
Feature activation+1.43e-02

Pos logit contributions
 paramed+0.015
boys+0.014
 Lee+0.014
 chefs+0.013
 principal+0.013
Neg logit contributions
 nights-0.016
 night-0.015
 day-0.015
fy-0.015
 morning-0.014
TokenWhen
Token ID2215
Feature activation-1.59e-01

Pos logit contributions
 paramed+0.020
boys+0.020
 Lee+0.019
 chefs+0.019
 principal+0.018
Neg logit contributions
 night-0.025
 day-0.025
 nights-0.024
 morning-0.023
fy-0.023
Token the
Token ID262
Feature activation+5.31e-02

Pos logit contributions
 day+0.285
 nights+0.281
 night+0.280
 afternoon+0.267
 morning+0.267
Neg logit contributions
boys-0.215
 paramed-0.211
 chefs-0.204
 Lee-0.202
 printer-0.188
Token painting
Token ID12036
Feature activation+2.24e-02

Pos logit contributions
 paramed+0.084
boys+0.083
 printer+0.083
 chefs+0.080
 reporter+0.079
Neg logit contributions
 nights-0.077
fy-0.077
 Along-0.076
ingle-0.076
adows-0.075
Token was
Token ID373
Feature activation+5.17e-02

Pos logit contributions
boys+0.034
 paramed+0.034
 chefs+0.033
 Lee+0.032
 reporter+0.031
Neg logit contributions
 day-0.036
 night-0.036
 nights-0.035
 morning-0.034
 time-0.034
Token!"
Token ID2474
Feature activation+1.76e-01

Pos logit contributions
 nights+0.251
 day+0.249
 night+0.246
 afternoon+0.235
 morning+0.234
Neg logit contributions
boys-0.249
 paramed-0.234
 chefs-0.233
 Lee-0.233
 printer-0.215
Token
Token ID198
Feature activation-9.05e-04

Pos logit contributions
boys+0.260
 paramed+0.259
 Lee+0.250
 chefs+0.245
 printer+0.228
Neg logit contributions
 day-0.296
 night-0.293
 nights-0.292
fy-0.277
 afternoon-0.277
Token
Token ID198
Feature activation-1.86e-04

Pos logit contributions
 day+0.001
 night+0.001
 nights+0.001
 morning+0.001
 afternoon+0.001
Neg logit contributions
boys-0.002
 paramed-0.002
 chefs-0.001
 Lee-0.001
 principal-0.001
TokenDog
Token ID32942
Feature activation+1.94e-02

Pos logit contributions
 day+0.000
 nights+0.000
 night+0.000
 time+0.000
 afternoon+0.000
Neg logit contributions
boys-0.000
 chefs-0.000
 paramed-0.000
 Lee-0.000
 printer-0.000
Token bark
Token ID21405
Feature activation+5.27e-02

Pos logit contributions
boys+0.028
 paramed+0.027
 Lee+0.026
 chefs+0.026
 printer+0.024
Neg logit contributions
 day-0.034
 night-0.033
 nights-0.033
 morning-0.031
 afternoon-0.031
Tokened
Token ID276
Feature activation+5.16e-02

Pos logit contributions
boys+0.103
 paramed+0.102
 chefs+0.100
 Lee+0.099
 principal+0.095
Neg logit contributions
 day-0.063
 night-0.062
 nights-0.062
 morning-0.058
 time-0.057
Token,
Token ID11
Feature activation+8.43e-02

Pos logit contributions
boys+0.091
 paramed+0.090
 chefs+0.088
 Lee+0.086
 principal+0.082
Neg logit contributions
 day-0.073
 night-0.071
 nights-0.071
 morning-0.067
 time-0.067
Token as
Token ID355
Feature activation-9.18e-02

Pos logit contributions
boys+0.116
 chefs+0.113
 paramed+0.110
 principal+0.107
 liar+0.103
Neg logit contributions
 day-0.154
 night-0.147
 Along-0.146
 morning-0.145
 nights-0.145
Token if
Token ID611
Feature activation+4.14e-02

Pos logit contributions
 nights+0.154
 day+0.153
 night+0.152
fy+0.148
 afternoon+0.147
Neg logit contributions
boys-0.131
 paramed-0.128
 Lee-0.125
 chefs-0.121
 groom-0.115
Token to
Token ID284
Feature activation+6.80e-02

Pos logit contributions
boys+0.055
 paramed+0.055
 chefs+0.054
 Lee+0.050
 principal+0.050
Neg logit contributions
 day-0.078
 night-0.076
 nights-0.075
 morning-0.073
 time-0.072
Token say
Token ID910
Feature activation+3.75e-02

Pos logit contributions
boys+0.095
 paramed+0.092
 Lee+0.091
 chefs+0.089
 groom+0.085
Neg logit contributions
 nights-0.120
 day-0.119
 night-0.118
fy-0.115
 afternoon-0.113
Token.
Token ID13
Feature activation-2.91e-02

Pos logit contributions
 day+0.127
 nights+0.127
 night+0.124
 morning+0.118
 afternoon+0.118
Neg logit contributions
boys-0.146
 paramed-0.142
 chefs-0.138
 Lee-0.138
 groom-0.130
Token She
Token ID1375
Feature activation-2.87e-02

Pos logit contributions
 nights+0.041
 day+0.041
 night+0.040
fy+0.038
 afternoon+0.038
Neg logit contributions
 paramed-0.051
 Lee-0.050
 chefs-0.050
boys-0.050
 principal-0.047
Token learned
Token ID4499
Feature activation+6.03e-02

Pos logit contributions
 day+0.049
 night+0.048
 time+0.046
 nights+0.046
 morning+0.044
Neg logit contributions
 paramed-0.044
 chefs-0.041
 Lee-0.041
boys-0.040
 printer-0.038
Token that
Token ID326
Feature activation+5.18e-02

Pos logit contributions
boys+0.088
 paramed+0.086
 chefs+0.084
 Lee+0.082
 printer+0.078
Neg logit contributions
 day-0.104
 night-0.103
 nights-0.099
 morning-0.097
 time-0.097
Token the
Token ID262
Feature activation+3.87e-02

Pos logit contributions
boys+0.080
 paramed+0.079
 chefs+0.077
 Lee+0.075
 printer+0.071
Neg logit contributions
 day-0.084
 night-0.083
 nights-0.082
 morning-0.078
 time-0.078
Token clown
Token ID25573
Feature activation+6.83e-02

Pos logit contributions
boys+0.052
 paramed+0.051
 chefs+0.049
 Lee+0.049
 groom+0.045
Neg logit contributions
 day-0.074
 night-0.071
 time-0.069
 nights-0.069
 morning-0.068
Token was
Token ID373
Feature activation+2.95e-02

Pos logit contributions
boys+0.099
 paramed+0.095
 chefs+0.092
 Lee+0.091
 reporter+0.086
Neg logit contributions
 day-0.116
 nights-0.116
 night-0.115
 morning-0.110
 afternoon-0.110
Token not
Token ID407
Feature activation+5.53e-02

Pos logit contributions
 paramed+0.041
boys+0.040
 Lee+0.039
 chefs+0.038
 printer+0.036
Neg logit contributions
 day-0.054
 night-0.053
 nights-0.051
 time-0.051
 morning-0.050
Token scary
Token ID14343
Feature activation+8.14e-03

Pos logit contributions
boys+0.085
 paramed+0.085
 chefs+0.081
 Lee+0.081
 principal+0.077
Neg logit contributions
 day-0.091
 night-0.089
 nights-0.087
 time-0.085
 morning-0.084
Token.
Token ID13
Feature activation-2.57e-02

Pos logit contributions
boys+0.013
 chefs+0.013
 Lee+0.013
 paramed+0.012
 reporter+0.012
Neg logit contributions
 nights-0.012
 day-0.012
 night-0.012
 Along-0.012
fy-0.012
Token He
Token ID679
Feature activation-1.48e-02

Pos logit contributions
 nights+0.040
 day+0.040
 night+0.039
fy+0.037
 afternoon+0.037
Neg logit contributions
 paramed-0.041
 Lee-0.041
 chefs-0.041
boys-0.040
 principal-0.038
Token and
Token ID290
Feature activation-3.70e-02

Pos logit contributions
 paramed+0.034
 Lee+0.034
 chefs+0.033
boys+0.033
 principal+0.031
Neg logit contributions
 nights-0.040
 day-0.039
fy-0.039
 night-0.038
 afternoon-0.037
Token saw
Token ID2497
Feature activation+4.63e-02

Pos logit contributions
 day+0.068
 night+0.067
 nights+0.065
 morning+0.063
 afternoon+0.062
Neg logit contributions
 paramed-0.053
boys-0.052
 chefs-0.050
 Lee-0.048
 reporter-0.046
Token lots
Token ID6041
Feature activation-4.52e-02

Pos logit contributions
boys+0.089
 wrists+0.081
 paramed+0.081
 Lee+0.081
 argue+0.079
Neg logit contributions
 day-0.064
 night-0.063
 of-0.058
 morning-0.058
 nights-0.057
Token of
Token ID286
Feature activation-1.08e-01

Pos logit contributions
 Along+0.036
 spine+0.035
 night+0.035
 nights+0.034
rated+0.033
Neg logit contributions
 paramed-0.107
 chefs-0.103
boys-0.100
 Lee-0.099
 principal-0.097
Token tasty
Token ID25103
Feature activation-2.41e-02

Pos logit contributions
 day+0.167
 night+0.158
 nights+0.158
 time+0.156
 morning+0.150
Neg logit contributions
boys-0.187
 Lee-0.176
 paramed-0.169
 chefs-0.168
 reporter-0.166
Token cakes
Token ID30849
Feature activation+1.41e-01

Pos logit contributions
 day+0.043
 night+0.043
 nights+0.042
 morning+0.041
 time+0.040
Neg logit contributions
boys-0.033
 paramed-0.032
 chefs-0.031
 Lee-0.031
 reporter-0.029
Token.
Token ID13
Feature activation-4.15e-02

Pos logit contributions
boys+0.258
 paramed+0.250
 chefs+0.249
 Lee+0.247
 reporter+0.231
Neg logit contributions
 nights-0.189
 day-0.188
 night-0.187
 morning-0.176
 afternoon-0.174
Token He
Token ID679
Feature activation-3.65e-02

Pos logit contributions
 nights+0.063
 day+0.062
 night+0.061
fy+0.059
 afternoon+0.058
Neg logit contributions
 Lee-0.067
boys-0.065
 paramed-0.064
 chefs-0.064
 principal-0.061
Token wanted
Token ID2227
Feature activation-4.87e-02

Pos logit contributions
 day+0.058
 night+0.055
 nights+0.055
 time+0.053
 afternoon+0.051
Neg logit contributions
 Lee-0.061
 paramed-0.061
 chefs-0.059
boys-0.058
 principal-0.056
Token one
Token ID530
Feature activation-4.27e-02

Pos logit contributions
 day+0.063
 time+0.061
 night+0.060
 nights+0.056
 morning+0.055
Neg logit contributions
 paramed-0.097
boys-0.096
 reporter-0.092
 Lee-0.089
 wrists-0.089
Token of
Token ID286
Feature activation-1.08e-01

Pos logit contributions
 nights+0.073
 night+0.069
 Along+0.067
fy+0.067
 day+0.067
Neg logit contributions
boys-0.060
 chefs-0.059
 Lee-0.059
 paramed-0.058
 printer-0.053
Token was
Token ID373
Feature activation+4.03e-03

Pos logit contributions
 nights+0.116
 day+0.113
fy+0.112
 night+0.112
 Along+0.108
Neg logit contributions
boys-0.088
 paramed-0.086
 Lee-0.084
 chefs-0.084
 printer-0.077
Token a
Token ID257
Feature activation+8.90e-04

Pos logit contributions
 chefs+0.003
boys+0.003
 paramed+0.002
 printer+0.002
 Lee+0.002
Neg logit contributions
fy-0.010
 nights-0.010
 spine-0.010
rated-0.009
way-0.009
Token little
Token ID1310
Feature activation-9.05e-02

Pos logit contributions
boys+0.002
 Lee+0.002
 wrists+0.002
 paramed+0.002
 chefs+0.002
Neg logit contributions
 day-0.001
 night-0.001
 time-0.001
 morning-0.001
 afternoon-0.001
Token boy
Token ID2933
Feature activation+1.05e-01

Pos logit contributions
 day+0.164
 night+0.160
 morning+0.150
 afternoon+0.144
 evening+0.142
Neg logit contributions
boys-0.137
 paramed-0.130
 principal-0.128
 wrists-0.127
 Lee-0.124
Token named
Token ID3706
Feature activation-5.43e-02

Pos logit contributions
boys+0.098
 paramed+0.094
 chefs+0.089
 Lee+0.086
 printer+0.079
Neg logit contributions
 nights-0.233
 day-0.232
 night-0.231
fy-0.224
 morning-0.223
Token Tim
Token ID5045
Feature activation+7.18e-03

Pos logit contributions
 nights+0.132
 day+0.125
 afternoon+0.124
 night+0.124
fy+0.123
Neg logit contributions
 chefs-0.043
boys-0.043
 Lee-0.040
 paramed-0.036
 printer-0.032
Tokenmy
Token ID1820
Feature activation-1.13e-01

Pos logit contributions
boys+0.010
 chefs+0.010
 Lee+0.009
 paramed+0.009
 reporter+0.008
Neg logit contributions
 nights-0.013
fy-0.013
 Along-0.012
olly-0.011
andel-0.011
Token.
Token ID13
Feature activation-5.34e-02

Pos logit contributions
 nights+0.154
fy+0.146
 day+0.144
 night+0.143
 morning+0.139
Neg logit contributions
boys-0.204
 paramed-0.199
 chefs-0.194
 Lee-0.190
 printer-0.184
Token Tim
Token ID5045
Feature activation+1.59e-02

Pos logit contributions
 nights+0.115
 night+0.110
 day+0.110
fy+0.109
 afternoon+0.106
Neg logit contributions
boys-0.053
 paramed-0.052
 chefs-0.052
 Lee-0.052
 printer-0.043
Tokenmy
Token ID1820
Feature activation-1.12e-01

Pos logit contributions
boys+0.025
 chefs+0.024
 paramed+0.024
 Lee+0.023
 printer+0.022
Neg logit contributions
 nights-0.024
fy-0.023
 Along-0.023
 day-0.022
 night-0.022
Token loved
Token ID6151
Feature activation-6.40e-02

Pos logit contributions
 nights+0.194
 day+0.189
 night+0.188
fy+0.184
 morning+0.181
Neg logit contributions
boys-0.156
 paramed-0.151
 chefs-0.147
 Lee-0.143
 printer-0.137
Token said
Token ID531
Feature activation+2.39e-02

Pos logit contributions
 day+0.001
 night+0.001
 time+0.001
 nights+0.001
 morning+0.001
Neg logit contributions
 paramed-0.001
 chefs-0.001
 Lee-0.001
boys-0.001
 principal-0.001
Token that
Token ID326
Feature activation+5.78e-02

Pos logit contributions
boys+0.042
 chefs+0.041
 paramed+0.040
 Lee+0.039
 principal+0.039
Neg logit contributions
 day-0.035
 time-0.034
 of-0.033
 morning-0.032
 night-0.032
Token the
Token ID262
Feature activation+4.52e-02

Pos logit contributions
 paramed+0.098
boys+0.088
 chefs+0.085
 Lee+0.084
 wrists+0.084
Neg logit contributions
 day-0.102
 night-0.093
 time-0.089
 nights-0.089
 morning-0.086
Token other
Token ID584
Feature activation-7.03e-02

Pos logit contributions
 paramed+0.074
boys+0.074
 Lee+0.070
 chefs+0.069
 reporter+0.065
Neg logit contributions
 day-0.076
 night-0.072
 time-0.069
 nights-0.069
 morning-0.069
Token team
Token ID1074
Feature activation+9.21e-02

Pos logit contributions
 day+0.128
 night+0.122
 nights+0.121
 time+0.119
 morning+0.116
Neg logit contributions
 paramed-0.102
boys-0.099
 chefs-0.095
 Lee-0.093
 reporter-0.090
Token couldn
Token ID3521
Feature activation-9.00e-02

Pos logit contributions
 paramed+0.151
boys+0.149
 chefs+0.146
 Lee+0.143
 groom+0.137
Neg logit contributions
 day-0.146
 night-0.140
 nights-0.137
 time-0.134
 morning-0.132
Token't
Token ID470
Feature activation+4.84e-03

Pos logit contributions
 day+0.137
 night+0.135
 nights+0.135
 morning+0.127
 afternoon+0.127
Neg logit contributions
boys-0.147
 paramed-0.145
 chefs-0.140
 Lee-0.139
 printer-0.131
Token join
Token ID4654
Feature activation+2.15e-02

Pos logit contributions
boys+0.007
 paramed+0.007
 chefs+0.007
 Lee+0.007
 printer+0.007
Neg logit contributions
 day-0.008
 night-0.008
 nights-0.008
 time-0.007
 morning-0.007
Token.
Token ID13
Feature activation-4.54e-03

Pos logit contributions
 paramed+0.031
boys+0.030
 chefs+0.029
 Lee+0.028
 reporter+0.027
Neg logit contributions
 day-0.038
 night-0.037
 nights-0.037
 time-0.036
 morning-0.036
Token They
Token ID1119
Feature activation+5.25e-02

Pos logit contributions
 day+0.006
 night+0.006
 Along+0.006
 time+0.006
 morning+0.006
Neg logit contributions
boys-0.008
 paramed-0.008
 chefs-0.008
 groom-0.008
 reporter-0.008
Token said
Token ID531
Feature activation+2.65e-02

Pos logit contributions
 chefs+0.096
 paramed+0.094
boys+0.091
 Lee+0.091
 principal+0.087
Neg logit contributions
 day-0.079
 night-0.077
 time-0.073
 nights-0.070
 morning-0.068
Token she
Token ID673
Feature activation-1.39e-01

Pos logit contributions
 day+0.066
 night+0.065
 nights+0.065
 morning+0.061
 time+0.061
Neg logit contributions
boys-0.062
 paramed-0.061
 chefs-0.059
 Lee-0.059
 reporter-0.055
Token loved
Token ID6151
Feature activation-5.99e-02

Pos logit contributions
 day+0.226
 night+0.221
 nights+0.217
 morning+0.208
 time+0.207
Neg logit contributions
boys-0.221
 paramed-0.219
 chefs-0.212
 Lee-0.211
 principal-0.197
Token to
Token ID284
Feature activation+5.85e-02

Pos logit contributions
 day+0.098
 night+0.096
 nights+0.093
 morning+0.090
 time+0.089
Neg logit contributions
boys-0.096
 paramed-0.095
 Lee-0.090
 chefs-0.089
 reporter-0.086
Token peek
Token ID27185
Feature activation-5.09e-02

Pos logit contributions
boys+0.094
 paramed+0.093
 chefs+0.090
 Lee+0.089
 reporter+0.084
Neg logit contributions
 day-0.092
 night-0.090
 nights-0.089
 morning-0.085
 time-0.085
Token.
Token ID13
Feature activation-4.39e-02

Pos logit contributions
 day+0.075
 nights+0.073
 night+0.071
 afternoon+0.071
 evening+0.069
Neg logit contributions
boys-0.085
 chefs-0.083
 paramed-0.081
 Lee-0.078
 groom-0.078
Token She
Token ID1375
Feature activation-5.01e-02

Pos logit contributions
 nights+0.060
fy+0.057
ight+0.054
 day+0.054
 night+0.053
Neg logit contributions
 Lee-0.082
 paramed-0.075
boys-0.073
 wrists-0.072
 principal-0.071
Token would
Token ID561
Feature activation-2.21e-02

Pos logit contributions
 nights+0.092
 day+0.092
 night+0.091
fy+0.089
 morning+0.087
Neg logit contributions
boys-0.063
 paramed-0.060
 chefs-0.057
 Lee-0.057
 groom-0.056
Token peek
Token ID27185
Feature activation-5.14e-02

Pos logit contributions
 day+0.037
 nights+0.037
 night+0.037
 afternoon+0.035
 morning+0.035
Neg logit contributions
boys-0.033
 paramed-0.032
 chefs-0.031
 Lee-0.030
 groom-0.029
Token in
Token ID287
Feature activation-4.90e-02

Pos logit contributions
 day+0.072
 nights+0.068
 night+0.068
 afternoon+0.067
 time+0.066
Neg logit contributions
boys-0.090
 chefs-0.089
 paramed-0.087
 Lee-0.086
 groom-0.083
Token the
Token ID262
Feature activation+1.83e-02

Pos logit contributions
 day+0.095
 nights+0.094
 night+0.094
fy+0.091
 morning+0.090
Neg logit contributions
boys-0.058
 paramed-0.057
 chefs-0.056
 Lee-0.055
 printer-0.051
Token trees
Token ID7150
Feature activation-7.80e-02

Pos logit contributions
 paramed+0.019
 printer+0.018
 principal+0.017
 Lee+0.017
 chefs+0.017
Neg logit contributions
 nights-0.038
fy-0.037
t-0.036
 day-0.036
ight-0.036
Token,
Token ID11
Feature activation+7.32e-02

Pos logit contributions
ight+0.140
fy+0.140
rated+0.138
found+0.138
adow+0.137
Neg logit contributions
 paramed-0.086
 Lee-0.083
boys-0.079
 chefs-0.077
 printer-0.072
Token Lily
Token ID20037
Feature activation+4.19e-02

Pos logit contributions
boys+0.097
 paramed+0.094
 chefs+0.090
 Lee+0.087
 principal+0.085
Neg logit contributions
 day-0.142
 night-0.140
 nights-0.136
 morning-0.134
 time-0.133
Token started
Token ID2067
Feature activation-5.74e-03

Pos logit contributions
 paramed+0.060
 chefs+0.058
 Lee+0.057
boys+0.057
 reporter+0.054
Neg logit contributions
 night-0.073
 day-0.073
 nights-0.071
 time-0.071
 morning-0.068
Token to
Token ID284
Feature activation+6.25e-02

Pos logit contributions
 day+0.008
 night+0.008
 time+0.007
 nights+0.007
 morning+0.007
Neg logit contributions
boys-0.010
 chefs-0.010
 reporter-0.010
 paramed-0.010
 Lee-0.010
Token feel
Token ID1254
Feature activation+1.38e-01

Pos logit contributions
 chefs+0.100
 paramed+0.097
 reporter+0.096
 Lee+0.095
 principal+0.094
Neg logit contributions
 night-0.102
 day-0.101
 time-0.096
 morning-0.093
 evening-0.091
Token dizz
Token ID29527
Feature activation-3.17e-02

Pos logit contributions
boys+0.218
 paramed+0.216
 chefs+0.209
 Lee+0.206
 printer+0.194
Neg logit contributions
 day-0.220
 night-0.217
 nights-0.215
 morning-0.205
 afternoon-0.204
Tokeny
Token ID88
Feature activation-5.74e-02

Pos logit contributions
 Along+0.058
 nights+0.057
 trek+0.056
 journey+0.054
 day+0.052
Neg logit contributions
 chefs-0.040
 paramed-0.040
 Lee-0.039
boys-0.038
 wasteful-0.034
Token from
Token ID422
Feature activation-3.06e-04

Pos logit contributions
 nights+0.091
 Along+0.090
found+0.088
 day+0.085
fy+0.085
Neg logit contributions
boys-0.090
 chefs-0.083
 Lee-0.081
 paramed-0.081
 fighting-0.075
Token lifting
Token ID16842
Feature activation-2.54e-02

Pos logit contributions
 nights+0.001
 day+0.001
fy+0.001
 night+0.001
 Along+0.001
Neg logit contributions
boys-0.000
 Lee-0.000
 paramed-0.000
 chefs-0.000
 groom-0.000
Token Mitt
Token ID16627
Feature activation+8.77e-02

Pos logit contributions
 day+0.041
 night+0.040
 nights+0.039
 time+0.038
 morning+0.038
Neg logit contributions
boys-0.040
 paramed-0.040
 chefs-0.038
 Lee-0.038
 reporter-0.036
Tokenens
Token ID641
Feature activation-8.02e-03

Pos logit contributions
boys+0.153
 paramed+0.150
 Lee+0.146
 chefs+0.146
 reporter+0.136
Neg logit contributions
 day-0.125
 nights-0.123
 night-0.122
 afternoon-0.115
 morning-0.114
Token and
Token ID290
Feature activation-2.80e-02

Pos logit contributions
 nights+0.189
 day+0.183
fy+0.181
 night+0.180
 time+0.176
Neg logit contributions
boys-0.174
 Lee-0.172
 chefs-0.164
 paramed-0.159
 reporter-0.155
Token walked
Token ID6807
Feature activation-1.17e-01

Pos logit contributions
 day+0.051
 nights+0.050
 time+0.049
 night+0.049
fy+0.049
Neg logit contributions
boys-0.036
 Lee-0.035
 paramed-0.034
 chefs-0.034
 groom-0.032
Token until
Token ID1566
Feature activation-1.19e-01

Pos logit contributions
 nights+0.163
fy+0.159
found+0.158
 day+0.158
ight+0.157
Neg logit contributions
boys-0.191
 Lee-0.190
 chefs-0.181
 reporter-0.170
 paramed-0.169
Token she
Token ID673
Feature activation-1.20e-01

Pos logit contributions
fy+0.208
ight+0.203
found+0.202
adow+0.195
 nights+0.193
Neg logit contributions
 Lee-0.157
 paramed-0.148
boys-0.142
 principal-0.132
 chefs-0.131
Token was
Token ID373
Feature activation+2.63e-02

Pos logit contributions
 day+0.244
 nights+0.242
 night+0.238
fy+0.234
 afternoon+0.234
Neg logit contributions
boys-0.130
 paramed-0.126
 chefs-0.121
 Lee-0.120
 groom-0.112
Token very
Token ID845
Feature activation-2.25e-02

Pos logit contributions
boys+0.039
 chefs+0.038
 paramed+0.038
 Lee+0.038
 groom+0.036
Neg logit contributions
 nights-0.042
 day-0.041
fy-0.040
 night-0.040
 afternoon-0.039
Token tired
Token ID10032
Feature activation-3.71e-02

Pos logit contributions
 nights+0.037
 day+0.036
 night+0.034
 Along+0.034
 afternoon+0.034
Neg logit contributions
 chefs-0.032
 paramed-0.032
boys-0.031
 Lee-0.030
 groom-0.030
Token.
Token ID13
Feature activation-2.94e-02

Pos logit contributions
found+0.061
 Along+0.060
 nights+0.060
fy+0.059
 afternoon+0.057
Neg logit contributions
 Lee-0.053
boys-0.052
 chefs-0.051
 paramed-0.050
 reporter-0.045
Token She
Token ID1375
Feature activation-3.28e-02

Pos logit contributions
 nights+0.054
iest+0.052
 night+0.052
fy+0.052
 day+0.052
Neg logit contributions
 Lee-0.040
 paramed-0.037
 principal-0.033
 chefs-0.033
boys-0.033
Token was
Token ID373
Feature activation+2.63e-02

Pos logit contributions
 day+0.060
 nights+0.059
 night+0.059
 morning+0.057
 afternoon+0.057
Neg logit contributions
boys-0.043
 paramed-0.042
 chefs-0.040
 Lee-0.039
 groom-0.038
Token strong
Token ID1913
Feature activation+4.35e-02

Pos logit contributions
boys+0.038
 paramed+0.038
 chefs+0.037
 Lee+0.036
 groom+0.034
Neg logit contributions
 day-0.044
 nights-0.044
 night-0.043
fy-0.041
 morning-0.041
Token at
Token ID379
Feature activation-3.49e-02

Pos logit contributions
 paramed+0.007
boys+0.007
 chefs+0.007
 Lee+0.007
 principal+0.006
Neg logit contributions
 day-0.006
 night-0.005
 nights-0.005
 time-0.005
 morning-0.005
Token all
Token ID477
Feature activation-2.22e-02

Pos logit contributions
 day+0.063
 night+0.062
 nights+0.060
 time+0.059
 morning+0.058
Neg logit contributions
 paramed-0.052
boys-0.050
 chefs-0.048
 Lee-0.047
 reporter-0.046
Token the
Token ID262
Feature activation+4.45e-02

Pos logit contributions
 Along+0.045
fy+0.044
 nights+0.044
 night+0.043
 day+0.043
Neg logit contributions
boys-0.023
 chefs-0.021
 Lee-0.021
 paramed-0.021
 printer-0.020
Token buttons
Token ID12163
Feature activation-1.17e-02

Pos logit contributions
boys+0.069
 chefs+0.068
 paramed+0.065
 Lee+0.063
 printer+0.063
Neg logit contributions
 nights-0.070
fy-0.069
 Along-0.068
 day-0.068
 night-0.067
Token and
Token ID290
Feature activation-2.64e-02

Pos logit contributions
 day+0.018
 nights+0.018
 night+0.018
 afternoon+0.017
 morning+0.017
Neg logit contributions
boys-0.019
 paramed-0.018
 chefs-0.018
 Lee-0.018
 printer-0.017
Token lights
Token ID7588
Feature activation-5.20e-02

Pos logit contributions
 night+0.047
 day+0.047
 nights+0.045
 morning+0.044
 time+0.044
Neg logit contributions
 paramed-0.040
boys-0.036
 chefs-0.034
 reporter-0.034
 Lee-0.033
Token.
Token ID13
Feature activation-2.87e-02

Pos logit contributions
 nights+0.081
 day+0.080
 night+0.078
 afternoon+0.075
 Along+0.075
Neg logit contributions
boys-0.083
 paramed-0.079
 chefs-0.078
 Lee-0.078
 groom-0.073
Token They
Token ID1119
Feature activation+4.13e-02

Pos logit contributions
 day+0.046
 night+0.045
 nights+0.044
 morning+0.043
 Along+0.043
Neg logit contributions
boys-0.044
 paramed-0.044
 chefs-0.042
 groom-0.040
 Lee-0.040
Token are
Token ID389
Feature activation+9.21e-02

Pos logit contributions
 paramed+0.055
boys+0.055
 chefs+0.052
 Lee+0.052
 principal+0.048
Neg logit contributions
 day-0.076
 night-0.075
 nights-0.074
 morning-0.071
 time-0.071
Token incredible
Token ID8082
Feature activation-5.27e-02

Pos logit contributions
 paramed+0.153
boys+0.148
 Lee+0.142
 chefs+0.139
 principal+0.136
Neg logit contributions
 day-0.146
 night-0.143
 nights-0.139
 time-0.137
 morning-0.133
Token,"
Token ID553
Feature activation+1.87e-01

Pos logit contributions
 day+0.079
 night+0.078
 nights+0.077
 morning+0.073
 time+0.073
Neg logit contributions
 paramed-0.089
boys-0.088
 chefs-0.084
 Lee-0.083
 principal-0.080
Token in
Token ID287
Feature activation-2.77e-02

Pos logit contributions
 day+0.161
 nights+0.158
 night+0.158
 morning+0.152
 afternoon+0.150
Neg logit contributions
boys-0.138
 chefs-0.134
 paramed-0.134
 Lee-0.128
 groom-0.122
Token trouble
Token ID5876
Feature activation+1.33e-01

Pos logit contributions
 day+0.050
 nights+0.050
 night+0.049
fy+0.048
 afternoon+0.048
Neg logit contributions
boys-0.036
 paramed-0.035
 chefs-0.034
 Lee-0.034
 printer-0.031
Token again
Token ID757
Feature activation+1.07e-01

Pos logit contributions
boys+0.237
 chefs+0.226
 paramed+0.226
 Lee+0.224
 principal+0.210
Neg logit contributions
 day-0.177
 nights-0.174
 night-0.174
 Along-0.167
fy-0.166
Token.
Token ID13
Feature activation+6.64e-03

Pos logit contributions
boys+0.188
 chefs+0.181
 Lee+0.180
 paramed+0.176
 groom+0.167
Neg logit contributions
 day-0.140
 nights-0.140
 night-0.137
fy-0.136
 Along-0.132
Token<|endoftext|>
Token ID50256
Feature activation-1.42e-01

Pos logit contributions
 paramed+0.010
 Lee+0.010
boys+0.010
 chefs+0.009
 principal+0.009
Neg logit contributions
 nights-0.011
 day-0.011
 night-0.010
fy-0.010
 afternoon-0.010
TokenOnce
Token ID7454
Feature activation-2.14e-01

Pos logit contributions
 nights+0.237
fy+0.234
 day+0.222
 night+0.218
 afternoon+0.214
Neg logit contributions
 Lee-0.206
boys-0.203
 chefs-0.198
 paramed-0.194
 reporter-0.181
Token upon
Token ID2402
Feature activation-2.49e-01

Pos logit contributions
 nights+0.230
fy+0.222
 Along+0.187
des+0.183
abbling+0.179
Neg logit contributions
 Lee-0.432
 dad-0.406
 dads-0.398
 paramed-0.394
 mixer-0.389
Token a
Token ID257
Feature activation-6.00e-03

Pos logit contributions
 nights+0.625
fy+0.617
 spine+0.592
 day+0.583
way+0.577
Neg logit contributions
 chefs-0.158
boys-0.145
 paramed-0.122
 Lee-0.119
 groom-0.102
Token time
Token ID640
Feature activation-2.33e-01

Pos logit contributions
 nights+0.005
lessly+0.004
iest+0.004
ingle+0.004
dark+0.004
Neg logit contributions
boys-0.013
 paramed-0.012
 chefs-0.012
 qu-0.012
 Lee-0.012
Token there
Token ID612
Feature activation-6.85e-02

Pos logit contributions
 nights+0.437
fy+0.423
 night+0.417
 day+0.408
 afternoon+0.402
Neg logit contributions
 Lee-0.302
boys-0.295
 paramed-0.282
 chefs-0.280
 printer-0.249
Token were
Token ID547
Feature activation-2.56e-02

Pos logit contributions
 nights+0.116
 day+0.115
 night+0.114
fy+0.111
 morning+0.109
Neg logit contributions
boys-0.097
 paramed-0.095
 Lee-0.092
 chefs-0.092
 printer-0.085
Token together
Token ID1978
Feature activation+2.84e-03

Pos logit contributions
 day+0.120
 time+0.111
 night+0.107
 afternoon+0.105
 morning+0.104
Neg logit contributions
 paramed-0.186
 Lee-0.169
 principal-0.167
 wasteful-0.163
 groom-0.162
Token.
Token ID13
Feature activation-3.39e-02

Pos logit contributions
boys+0.005
 chefs+0.005
 paramed+0.005
 Lee+0.005
 printer+0.005
Neg logit contributions
 nights-0.003
 day-0.003
 night-0.003
fy-0.003
 morning-0.003
Token
Token ID220
Feature activation-3.75e-02

Pos logit contributions
 nights+0.058
fy+0.057
 night+0.054
 day+0.054
ight+0.052
Neg logit contributions
 Lee-0.049
boys-0.047
 paramed-0.046
 chefs-0.044
 printer-0.043
Token
Token ID198
Feature activation-1.54e-02

Pos logit contributions
 nights+0.064
 night+0.062
 day+0.061
fy+0.061
 afternoon+0.059
Neg logit contributions
boys-0.054
 Lee-0.053
 paramed-0.053
 chefs-0.052
 principal-0.048
Token
Token ID198
Feature activation-1.36e-02

Pos logit contributions
 nights+0.027
fy+0.027
 night+0.026
 day+0.025
 spine+0.025
Neg logit contributions
boys-0.020
 Lee-0.019
 paramed-0.019
 chefs-0.018
 principal-0.018
TokenOne
Token ID3198
Feature activation-1.64e-01

Pos logit contributions
 nights+0.017
 night+0.017
 day+0.016
fy+0.016
 morning+0.015
Neg logit contributions
boys-0.026
 paramed-0.026
 chefs-0.024
 Lee-0.024
 groom-0.024
Token day
Token ID1110
Feature activation-2.44e-01

Pos logit contributions
ently+0.160
ight+0.148
 spine+0.145
ides+0.144
lessly+0.141
Neg logit contributions
 paramed-0.323
 qu-0.319
 dads-0.317
 printer-0.316
 duck-0.314
Token,
Token ID11
Feature activation+7.37e-02

Pos logit contributions
 day+0.345
 night+0.338
 time+0.322
 morning+0.320
 nights+0.320
Neg logit contributions
boys-0.451
 paramed-0.443
 chefs-0.423
 principal-0.419
 Lee-0.410
Token she
Token ID673
Feature activation-1.33e-01

Pos logit contributions
boys+0.121
 paramed+0.119
 principal+0.112
 chefs+0.109
 reporter+0.109
Neg logit contributions
 day-0.126
 night-0.121
 morning-0.117
 time-0.116
 nights-0.112
Token and
Token ID290
Feature activation-3.46e-02

Pos logit contributions
 day+0.241
 night+0.237
 nights+0.228
 time+0.227
 morning+0.222
Neg logit contributions
 paramed-0.190
boys-0.183
 Lee-0.178
 chefs-0.176
 reporter-0.163
Token her
Token ID607
Feature activation-1.18e-01

Pos logit contributions
 day+0.044
 night+0.041
 morning+0.038
 time+0.037
 afternoon+0.036
Neg logit contributions
 chefs-0.074
 paramed-0.073
boys-0.072
 reporter-0.068
 liar-0.068
Token strongest
Token ID12841
Feature activation-1.06e-02

Pos logit contributions
 paramed+0.038
boys+0.036
 Lee+0.035
 chefs+0.033
 wrists+0.032
Neg logit contributions
 day-0.036
 night-0.034
 time-0.032
 morning-0.032
 afternoon-0.032
Token.
Token ID13
Feature activation-3.91e-02

Pos logit contributions
 day+0.017
 night+0.016
 time+0.016
 nights+0.016
 morning+0.015
Neg logit contributions
 paramed-0.018
boys-0.018
 Lee-0.017
 chefs-0.016
 wrists-0.016
Token So
Token ID1406
Feature activation-4.00e-02

Pos logit contributions
 nights+0.049
 night+0.048
 day+0.047
fy+0.046
 afternoon+0.043
Neg logit contributions
 Lee-0.072
boys-0.071
 chefs-0.071
 paramed-0.070
 principal-0.068
Token,
Token ID11
Feature activation+7.30e-02

Pos logit contributions
fy+0.066
 nights+0.063
dark+0.060
ingle+0.060
abbling+0.060
Neg logit contributions
 Lee-0.056
 chefs-0.054
 dads-0.052
boys-0.051
 reporter-0.048
Token every
Token ID790
Feature activation-1.38e-01

Pos logit contributions
 chefs+0.112
 Lee+0.110
 dads+0.105
boys+0.103
 reporter+0.100
Neg logit contributions
fy-0.111
 nights-0.108
 night-0.102
abbling-0.099
 day-0.099
Token day
Token ID1110
Feature activation-2.40e-01

Pos logit contributions
 nights+0.057
fy+0.053
adows+0.044
ight+0.040
 spine+0.040
Neg logit contributions
 printer-0.351
 Lee-0.349
 paramed-0.345
 groom-0.344
 reporter-0.340
Token he
Token ID339
Feature activation-1.23e-01

Pos logit contributions
fy+0.422
 nights+0.420
 night+0.410
 day+0.407
 Along+0.397
Neg logit contributions
 chefs-0.314
 Lee-0.307
boys-0.294
 paramed-0.281
 dads-0.276
Token would
Token ID561
Feature activation-2.00e-02

Pos logit contributions
 day+0.187
 night+0.183
 nights+0.177
 time+0.173
 morning+0.169
Neg logit contributions
 paramed-0.214
 Lee-0.203
boys-0.201
 chefs-0.197
 principal-0.190
Token wake
Token ID7765
Feature activation-2.73e-03

Pos logit contributions
 day+0.033
 night+0.032
 nights+0.031
 time+0.031
 morning+0.030
Neg logit contributions
 paramed-0.031
boys-0.031
 chefs-0.030
 Lee-0.029
 principal-0.028
Token up
Token ID510
Feature activation-3.50e-02

Pos logit contributions
 day+0.003
 night+0.003
 time+0.003
 morning+0.002
 nights+0.002
Neg logit contributions
 paramed-0.006
boys-0.006
 chefs-0.006
 Lee-0.006
 liar-0.006
Token early
Token ID1903
Feature activation-4.71e-02

Pos logit contributions
 day+0.051
 night+0.050
 nights+0.050
 morning+0.047
 time+0.047
Neg logit contributions
boys-0.060
 paramed-0.059
 chefs-0.058
 Lee-0.057
 reporter-0.054
Token her
Token ID607
Feature activation-9.54e-02

Pos logit contributions
boys+0.103
 paramed+0.099
 chefs+0.095
 Lee+0.094
 groom+0.089
Neg logit contributions
 day-0.106
 nights-0.105
 night-0.104
fy-0.100
 morning-0.099
Token way
Token ID835
Feature activation-6.71e-02

Pos logit contributions
 nights+0.140
fy+0.135
 day+0.134
 night+0.133
 Along+0.131
Neg logit contributions
boys-0.161
 Lee-0.150
 chefs-0.150
 paramed-0.146
 principal-0.140
Token.
Token ID13
Feature activation+1.08e-02

Pos logit contributions
 nights+0.110
fy+0.102
 Along+0.101
 afternoon+0.100
 day+0.100
Neg logit contributions
boys-0.099
 Lee-0.087
 paramed-0.087
 printer-0.087
 chefs-0.084
Token<|endoftext|>
Token ID50256
Feature activation-1.38e-01

Pos logit contributions
boys+0.019
 paramed+0.019
 chefs+0.018
 Lee+0.018
 printer+0.017
Neg logit contributions
 day-0.015
 night-0.015
 nights-0.015
 morning-0.014
 afternoon-0.014
TokenOnce
Token ID7454
Feature activation-2.05e-01

Pos logit contributions
 nights+0.219
 day+0.212
fy+0.211
 night+0.209
 afternoon+0.201
Neg logit contributions
boys-0.214
 Lee-0.208
 paramed-0.205
 chefs-0.205
 reporter-0.191
Token upon
Token ID2402
Feature activation-2.39e-01

Pos logit contributions
 nights+0.210
fy+0.205
des+0.170
 Along+0.165
 afternoon+0.162
Neg logit contributions
 Lee-0.427
 dad-0.399
 dads-0.396
boys-0.395
 paramed-0.392
Token a
Token ID257
Feature activation+4.69e-03

Pos logit contributions
 nights+0.581
fy+0.572
 day+0.548
 night+0.542
 spine+0.542
Neg logit contributions
 chefs-0.172
boys-0.169
 paramed-0.142
 Lee-0.139
 groom-0.120
Token time
Token ID640
Feature activation-2.25e-01

Pos logit contributions
boys+0.010
 paramed+0.010
 chefs+0.010
 qu+0.010
 printer+0.010
Neg logit contributions
 nights-0.004
lessly-0.003
iest-0.003
 night-0.003
ingle-0.003
Token,
Token ID11
Feature activation+5.78e-02

Pos logit contributions
 nights+0.437
fy+0.422
 night+0.413
 day+0.401
 afternoon+0.400
Neg logit contributions
 Lee-0.282
boys-0.275
 paramed-0.259
 chefs-0.257
 printer-0.229
Token there
Token ID612
Feature activation-6.10e-02

Pos logit contributions
 chefs+0.053
boys+0.051
 Lee+0.049
 paramed+0.047
 fighting+0.045
Neg logit contributions
 nights-0.128
fy-0.125
ingle-0.116
found-0.114
 night-0.114
Token was
Token ID373
Feature activation+9.36e-03

Pos logit contributions
 day+0.101
 nights+0.100
 night+0.099
 morning+0.094
fy+0.094
Neg logit contributions
boys-0.091
 paramed-0.089
 chefs-0.087
 Lee-0.086
 printer-0.080
Token played
Token ID2826
Feature activation-9.08e-02

Pos logit contributions
 paramed+0.054
 chefs+0.052
 Lee+0.051
boys+0.050
 principal+0.050
Neg logit contributions
 day-0.052
 night-0.051
 nights-0.048
 time-0.047
 morning-0.047
Token together
Token ID1978
Feature activation-4.46e-03

Pos logit contributions
 day+0.128
 time+0.117
 afternoon+0.114
 night+0.113
 morning+0.110
Neg logit contributions
 paramed-0.188
 groom-0.173
 Lee-0.169
 principal-0.166
 reporter-0.164
Token until
Token ID1566
Feature activation-1.32e-01

Pos logit contributions
 nights+0.006
 day+0.006
 night+0.006
fy+0.006
 morning+0.006
Neg logit contributions
boys-0.007
 chefs-0.007
 paramed-0.007
 Lee-0.007
 printer-0.007
Token it
Token ID340
Feature activation+2.05e-02

Pos logit contributions
 day+0.268
 night+0.267
 nights+0.256
 morning+0.254
 time+0.251
Neg logit contributions
boys-0.166
 paramed-0.164
 chefs-0.156
 Lee-0.150
 principal-0.143
Token was
Token ID373
Feature activation+2.08e-02

Pos logit contributions
boys+0.027
 paramed+0.026
 chefs+0.025
 Lee+0.024
 groom+0.023
Neg logit contributions
 nights-0.036
 day-0.036
 night-0.035
fy-0.035
 Along-0.034
Token time
Token ID640
Feature activation-2.17e-01

Pos logit contributions
 chefs+0.051
boys+0.051
 paramed+0.048
 Lee+0.048
 groom+0.047
Neg logit contributions
found-0.012
 nights-0.012
fy-0.011
ingle-0.010
ly-0.010
Token to
Token ID284
Feature activation+6.13e-02

Pos logit contributions
 nights+0.407
fy+0.378
 day+0.377
 night+0.374
 afternoon+0.371
Neg logit contributions
 Lee-0.254
boys-0.252
 chefs-0.247
 paramed-0.237
 printer-0.235
Token go
Token ID467
Feature activation-4.36e-02

Pos logit contributions
boys+0.103
 paramed+0.101
 chefs+0.098
 Lee+0.096
 groom+0.093
Neg logit contributions
 nights-0.091
 day-0.090
 night-0.088
fy-0.084
 afternoon-0.084
Token home
Token ID1363
Feature activation-1.11e-02

Pos logit contributions
 nights+0.066
ight+0.062
fy+0.061
 day+0.059
found+0.059
Neg logit contributions
boys-0.071
 chefs-0.067
 Lee-0.067
 paramed-0.066
 dads-0.063
Token.
Token ID13
Feature activation-2.38e-02

Pos logit contributions
 day+0.012
 night+0.012
 nights+0.012
 morning+0.011
 time+0.011
Neg logit contributions
boys-0.023
 paramed-0.023
 chefs-0.022
 Lee-0.022
 printer-0.021
Token
Token ID198
Feature activation-1.54e-02

Pos logit contributions
 nights+0.053
 day+0.050
adows+0.050
 night+0.050
iest+0.050
Neg logit contributions
 paramed-0.022
 Lee-0.020
boys-0.020
 chefs-0.019
 printer-0.018