TOP ACTIVATIONS
MAX = 0.102

accidentally broke it and the things inside the box got ruined
But the shiny things were not stars . They
was covered in flames and everything was gone .
was gone , and suddenly everything felt good . Joe and
the dots . But the dots were hard to see and
are too full . Their things do not fit . Sara
. Then , something bad happened . Z ee
When they got there , everything was safe and Lucy felt
But then , something bad happened . Tim hit
his carrot . But then something strange happened .
After a few minutes , something incredible happened . John saw
shoes . But then , something happened . Tom
Suddenly , something loud happened . It was
the hole . Suddenly , something popped out of the hole
big garden . Suddenly , everything started to shake . The
when he was gone , something magical happened . A great
to join them , but something was different . Her friends
she worked , but then something bad happened . The apple
they reached the stand , things weren 't as expected .
they reached the bottom , something bad happened . Tim 's

MIN ACTIVATIONS
MIN = -0.172

give to the rh in oc eros . Lily walked to
stick the mustache on her upper lip with some tape .
't know the rh in oc eros was wild . Can
he would take the av oc ados and scatter them around
She loved to eat av oc ados . One day ,
am taking the rh in oc eros to a new home
't cry , boys . Acc idents happen . I have
She loved to eat av oc ados because they were y
it to the rh in oc eros . When he tasted
," said the rh in oc eros . The
" The rh in oc eros is in there ,
't touch the rh in oc eros ! It might bite
. And put on your swe aters , or you will
Did you know that av oc ados are very healthy for
s wrong , rh in oc eros ? â € said
that the bad rh in oc eros was now nice .
to see the rh in oc eros . Tim my was
come in ," said his grand pa . They all turned
Unicorn !" The rh in oc eros said , feeling much
there was a rh in oc eros who was always naughty

INTERVAL 0.033 - 0.102
CONTAINS 11.204%

going on a trip . " Let 's load
needed it very much . After that , the bunny sat
of the window ?" " We had a plan
why his friend the frog was so encouraging . Joe had
. They knew that Max was still very little , and

INTERVAL -0.035 - 0.033
CONTAINS 80.984%

very happy . She said , " Look , Spot ,
cloud , Lily . It 's fog . It makes it
Finally , he went to the doctor even though his wife
sun . When he woke up , all his candy was
them when they were the right temperature . <|endoftext|> Once upon

INTERVAL -0.104 - -0.035
CONTAINS 7.784%

away and ran back to his castle where he was safe
. <|endoftext|> L ily and Ben were playing in the park
want a hug after playing in the rain ." Lily smiled
the rabbit home to her Mum . But , before she
, there was a little boy named Tim my . Tim

INTERVAL -0.172 - -0.104
CONTAINS 0.028%

turned out that the av oc ados were bad and made
there was a rh in oc eros who was always naughty
big , beautiful rainbow - col oured butterfly ! The little
't cry , boys . Acc idents happen . I have
K itty wanted to introduce Dog gy to her ball .
Token accidentally
Token ID14716
Feature activation-1.16e-02

Pos logit contributions
 much+0.063
lessly+0.054
 wonderful+0.053
br+0.052
On+0.051
Neg logit contributions
 Cr-0.065
ados-0.065
 Majesty-0.063
ishment-0.062
 Fro-0.060
Token broke
Token ID6265
Feature activation+9.88e-03

Pos logit contributions
ados+0.025
 Cr+0.024
 Majesty+0.024
ishment+0.023
lee+0.022
Neg logit contributions
 much-0.018
lessly-0.015
 wonderful-0.015
On-0.014
br-0.014
Token it
Token ID340
Feature activation+4.37e-02

Pos logit contributions
 much+0.019
lessly+0.016
 wonderful+0.016
On+0.015
 hard+0.015
Neg logit contributions
 Majesty-0.017
 Cr-0.017
ados-0.017
ishment-0.017
icans-0.016
Token and
Token ID290
Feature activation+3.06e-03

Pos logit contributions
 wonderful+0.078
br+0.078
 much+0.077
In+0.075
arest+0.072
Neg logit contributions
ados-0.071
gy-0.067
stick-0.063
 Cr-0.062
ishment-0.062
Token the
Token ID262
Feature activation+4.28e-02

Pos logit contributions
 much+0.005
 wonderful+0.004
lessly+0.004
On+0.004
br+0.004
Neg logit contributions
ados-0.006
 Cr-0.006
 Majesty-0.006
ishment-0.006
lee-0.005
Token things
Token ID1243
Feature activation+1.02e-01

Pos logit contributions
 much+0.070
lic+0.065
br+0.063
lessly+0.062
On+0.061
Neg logit contributions
ados-0.081
 Majesty-0.077
 knees-0.075
keeping-0.071
 heads-0.071
Token inside
Token ID2641
Feature activation+3.57e-02

Pos logit contributions
 much+0.153
On+0.149
 wonderful+0.144
br+0.143
One+0.141
Neg logit contributions
ados-0.186
 Cr-0.171
 knees-0.166
lee-0.164
stick-0.163
Token the
Token ID262
Feature activation+1.96e-02

Pos logit contributions
 much+0.046
lessly+0.039
 wonderful+0.039
br+0.039
On+0.038
Neg logit contributions
ados-0.080
 Cr-0.080
ishment-0.077
lee-0.075
gy-0.073
Token box
Token ID3091
Feature activation+6.12e-02

Pos logit contributions
 much+0.041
lessly+0.039
ching+0.038
lic+0.037
br+0.036
Neg logit contributions
ados-0.030
 Majesty-0.027
ishment-0.026
ASH-0.025
keeping-0.025
Token got
Token ID1392
Feature activation+4.57e-02

Pos logit contributions
 much+0.087
 wonderful+0.075
lessly+0.072
On+0.071
br+0.070
Neg logit contributions
ados-0.130
 Cr-0.129
gy-0.126
ishment-0.124
lee-0.123
Token ruined
Token ID20484
Feature activation+2.71e-02

Pos logit contributions
 much+0.058
lessly+0.056
br+0.056
In+0.055
On+0.055
Neg logit contributions
 Cr-0.097
ados-0.096
ishment-0.089
gy-0.089
lee-0.087
Token
Token ID198
Feature activation+5.67e-02

Pos logit contributions
ados+0.017
 Majesty+0.016
ishment+0.016
 Cr+0.016
gy+0.015
Neg logit contributions
 much-0.009
On-0.007
lessly-0.007
 wonderful-0.007
In-0.007
Token
Token ID198
Feature activation+4.76e-02

Pos logit contributions
 much+0.091
lessly+0.083
br+0.083
 wonderful+0.081
ching+0.073
Neg logit contributions
 Cr-0.106
 Fro-0.101
ados-0.097
lee-0.096
 Rib-0.096
TokenBut
Token ID1537
Feature activation+3.52e-02

Pos logit contributions
 much+0.065
lessly+0.057
 wonderful+0.055
br+0.054
 hard+0.051
Neg logit contributions
 Cr-0.097
 Fro-0.090
ishment-0.090
 Rib-0.090
ados-0.089
Token the
Token ID262
Feature activation+4.71e-02

Pos logit contributions
 much+0.059
 wonderful+0.048
On+0.047
lessly+0.046
 hard+0.046
Neg logit contributions
ados-0.072
 Majesty-0.070
 Cr-0.068
ishment-0.068
lee-0.066
Token shiny
Token ID22441
Feature activation+1.07e-02

Pos logit contributions
 much+0.101
lessly+0.096
ching+0.090
br+0.089
On+0.086
Neg logit contributions
ados-0.064
 Majesty-0.060
ishment-0.058
 Cr-0.057
 knees-0.057
Token things
Token ID1243
Feature activation+9.76e-02

Pos logit contributions
 much+0.019
lessly+0.016
 wonderful+0.016
On+0.016
In+0.016
Neg logit contributions
ados-0.020
 Cr-0.019
ishment-0.019
 Majesty-0.019
gy-0.018
Token were
Token ID547
Feature activation+5.93e-02

Pos logit contributions
 much+0.149
On+0.134
br+0.131
Finally+0.129
 wonderful+0.128
Neg logit contributions
ados-0.182
 Cr-0.178
lee-0.165
 knees-0.165
ishment-0.164
Token not
Token ID407
Feature activation+5.80e-02

Pos logit contributions
arest+0.082
lessly+0.080
 much+0.077
Finally+0.077
br+0.077
Neg logit contributions
 Cr-0.118
 Fro-0.111
ados-0.108
ishment-0.105
 Rib-0.103
Token stars
Token ID5788
Feature activation+6.79e-02

Pos logit contributions
 much+0.088
In+0.088
Finally+0.087
On+0.087
Over+0.085
Neg logit contributions
ados-0.099
 Cr-0.099
ishment-0.094
 Harry-0.092
gy-0.088
Token.
Token ID13
Feature activation-4.91e-03

Pos logit contributions
 much+0.119
On+0.109
In+0.108
lessly+0.105
 wonderful+0.104
Neg logit contributions
ados-0.118
 Cr-0.113
ishment-0.113
gy-0.112
lee-0.107
Token They
Token ID1119
Feature activation+3.50e-02

Pos logit contributions
 Majesty+0.008
ados+0.008
ci+0.008
keeping+0.007
gy+0.007
Neg logit contributions
 much-0.011
On-0.008
In-0.008
lessly-0.008
 lot-0.008
Token was
Token ID373
Feature activation+5.47e-02

Pos logit contributions
 much+0.096
lessly+0.081
 wonderful+0.081
br+0.079
On+0.079
Neg logit contributions
ados-0.146
gy-0.142
 Cr-0.140
ishment-0.138
lee-0.137
Token covered
Token ID5017
Feature activation+2.75e-02

Pos logit contributions
br+0.080
arest+0.078
lessly+0.073
ching+0.069
hest+0.069
Neg logit contributions
gy-0.097
ishment-0.091
stick-0.090
lee-0.090
 Cr-0.088
Token in
Token ID287
Feature activation+1.73e-02

Pos logit contributions
 much+0.042
br+0.036
 wonderful+0.036
lessly+0.035
On+0.035
Neg logit contributions
ados-0.056
 Cr-0.054
ishment-0.054
gy-0.051
 Majesty-0.050
Token flames
Token ID16209
Feature activation+4.48e-02

Pos logit contributions
br+0.030
lessly+0.030
 much+0.029
In+0.028
ching+0.028
Neg logit contributions
ados-0.028
ishment-0.027
 Cr-0.026
 Majesty-0.025
keeping-0.025
Token and
Token ID290
Feature activation+4.76e-03

Pos logit contributions
 much+0.077
In+0.070
 wonderful+0.068
br+0.067
On+0.067
Neg logit contributions
ados-0.078
ishment-0.076
gy-0.073
 Cr-0.073
 Majesty-0.072
Token everything
Token ID2279
Feature activation+9.68e-02

Pos logit contributions
 much+0.008
br+0.007
lessly+0.007
On+0.007
 wonderful+0.007
Neg logit contributions
ados-0.009
 Cr-0.008
 Majesty-0.008
ishment-0.008
lee-0.008
Token was
Token ID373
Feature activation+5.66e-02

Pos logit contributions
On+0.142
 much+0.142
br+0.135
Finally+0.134
In+0.133
Neg logit contributions
ishment-0.152
lee-0.152
ados-0.151
ci-0.150
 Cr-0.150
Token gone
Token ID3750
Feature activation+3.02e-02

Pos logit contributions
br+0.087
arest+0.081
Over+0.080
cro+0.075
lessly+0.073
Neg logit contributions
gy-0.099
ishment-0.098
lee-0.096
 Harry-0.092
urg-0.091
Token.
Token ID13
Feature activation+7.30e-03

Pos logit contributions
 much+0.053
br+0.052
In+0.052
On+0.049
Over+0.049
Neg logit contributions
ishment-0.049
gy-0.048
ados-0.046
 Majesty-0.043
keeping-0.043
Token
Token ID220
Feature activation+2.74e-02

Pos logit contributions
 much+0.015
lessly+0.012
 wonderful+0.012
On+0.012
In+0.012
Neg logit contributions
ados-0.013
 Majesty-0.012
ishment-0.012
 Cr-0.012
icans-0.011
Token
Token ID198
Feature activation+6.43e-02

Pos logit contributions
 much+0.037
 wonderful+0.029
lessly+0.029
On+0.028
br+0.028
Neg logit contributions
ados-0.063
 Cr-0.062
 Majesty-0.061
ishment-0.061
lee-0.058
Token was
Token ID373
Feature activation+4.67e-02

Pos logit contributions
 much+0.056
lessly+0.044
 wonderful+0.044
On+0.042
br+0.042
Neg logit contributions
ados-0.082
 Cr-0.082
ishment-0.081
 Majesty-0.081
gy-0.080
Token gone
Token ID3750
Feature activation+2.74e-02

Pos logit contributions
arest+0.072
br+0.071
cro+0.068
lessly+0.065
hest+0.061
Neg logit contributions
gy-0.080
 Harry-0.079
ishment-0.078
 Cr-0.078
 Fro-0.076
Token,
Token ID11
Feature activation+1.78e-02

Pos logit contributions
br+0.055
 much+0.054
In+0.053
arest+0.053
lic+0.051
Neg logit contributions
gy-0.037
ishment-0.036
 Harry-0.033
ados-0.031
 Sammy-0.031
Token and
Token ID290
Feature activation+1.38e-02

Pos logit contributions
 much+0.031
br+0.028
lessly+0.027
 wonderful+0.026
In+0.026
Neg logit contributions
 Cr-0.032
ishment-0.031
ados-0.031
 Majesty-0.030
 Fro-0.029
Token suddenly
Token ID6451
Feature activation+3.38e-02

Pos logit contributions
 much+0.027
br+0.023
lessly+0.023
 wonderful+0.023
On+0.023
Neg logit contributions
 Cr-0.023
ados-0.023
ishment-0.022
 Majesty-0.022
lee-0.021
Token everything
Token ID2279
Feature activation+9.67e-02

Pos logit contributions
 much+0.059
 wonderful+0.049
lessly+0.048
br+0.047
On+0.047
Neg logit contributions
ados-0.066
 Cr-0.065
ishment-0.063
 Majesty-0.063
lee-0.059
Token felt
Token ID2936
Feature activation+5.97e-02

Pos logit contributions
 much+0.157
br+0.145
On+0.139
lessly+0.134
Finally+0.133
Neg logit contributions
 Cr-0.159
lee-0.159
 knees-0.157
ishment-0.155
ados-0.149
Token good
Token ID922
Feature activation+1.40e-02

Pos logit contributions
br+0.085
arest+0.084
cro+0.079
ris+0.076
Finally+0.076
Neg logit contributions
 Nem-0.108
 Cr-0.108
 D-0.103
 Fro-0.100
 Sammy-0.098
Token.
Token ID13
Feature activation+8.93e-03

Pos logit contributions
 much+0.023
On+0.021
In+0.020
 wonderful+0.020
Finally+0.020
Neg logit contributions
ados-0.027
 Cr-0.026
lee-0.025
ishment-0.025
 Fro-0.023
Token Joe
Token ID5689
Feature activation+1.23e-02

Pos logit contributions
 much+0.019
 wonderful+0.016
lessly+0.016
In+0.016
On+0.015
Neg logit contributions
ados-0.015
 Majesty-0.014
ishment-0.014
 Cr-0.014
 Rib-0.013
Token and
Token ID290
Feature activation-2.55e-02

Pos logit contributions
 much+0.019
 wonderful+0.016
lessly+0.016
On+0.015
In+0.015
Neg logit contributions
ados-0.026
 Cr-0.025
 Majesty-0.025
ishment-0.025
icans-0.023
Token the
Token ID262
Feature activation+3.02e-02

Pos logit contributions
 much+0.039
lessly+0.034
br+0.033
On+0.033
In+0.033
Neg logit contributions
ados-0.044
 Cr-0.043
ishment-0.042
 Majesty-0.042
lee-0.039
Token dots
Token ID22969
Feature activation+7.82e-02

Pos logit contributions
 much+0.055
lessly+0.050
br+0.049
On+0.048
lic+0.047
Neg logit contributions
 Majesty-0.053
 Cr-0.052
ishment-0.051
ados-0.051
 Harry-0.046
Token.
Token ID13
Feature activation-9.73e-03

Pos logit contributions
 much+0.124
 wonderful+0.111
In+0.110
On+0.108
br+0.105
Neg logit contributions
ados-0.149
 Cr-0.141
ishment-0.139
 Majesty-0.137
lee-0.136
Token But
Token ID887
Feature activation+4.44e-02

Pos logit contributions
ados+0.016
 Cr+0.016
 Majesty+0.015
ishment+0.015
lee+0.014
Neg logit contributions
 much-0.021
On-0.018
In-0.017
 wonderful-0.017
lessly-0.017
Token the
Token ID262
Feature activation+3.92e-02

Pos logit contributions
 much+0.076
lessly+0.066
 wonderful+0.065
br+0.064
On+0.062
Neg logit contributions
 Cr-0.084
ados-0.084
ishment-0.081
 Majesty-0.080
 Fro-0.076
Token dots
Token ID22969
Feature activation+9.66e-02

Pos logit contributions
 much+0.076
lessly+0.067
On+0.064
br+0.064
In+0.064
Neg logit contributions
 Majesty-0.067
ados-0.067
 Cr-0.066
ishment-0.065
 Fro-0.058
Token were
Token ID547
Feature activation+5.55e-02

Pos logit contributions
 much+0.141
 wonderful+0.123
On+0.116
br+0.112
lessly+0.112
Neg logit contributions
ados-0.192
 Cr-0.185
lee-0.182
 Fro-0.180
 knees-0.179
Token hard
Token ID1327
Feature activation+1.12e-02

Pos logit contributions
arest+0.081
br+0.080
 much+0.076
ching+0.075
lessly+0.075
Neg logit contributions
ishment-0.101
 Cr-0.099
ados-0.098
 Fro-0.097
lee-0.093
Token to
Token ID284
Feature activation-2.39e-04

Pos logit contributions
 much+0.023
In+0.022
 wonderful+0.022
Over+0.021
arest+0.021
Neg logit contributions
ados-0.015
ishment-0.014
gy-0.013
 Cr-0.013
keeping-0.013
Token see
Token ID766
Feature activation+2.72e-02

Pos logit contributions
 Cr+0.000
ados+0.000
ishment+0.000
gy+0.000
 Majesty+0.000
Neg logit contributions
 much-0.000
lessly-0.000
 wonderful-0.000
br-0.000
In-0.000
Token and
Token ID290
Feature activation-4.65e-04

Pos logit contributions
 much+0.047
lessly+0.042
On+0.041
In+0.040
 wonderful+0.040
Neg logit contributions
ados-0.050
 Cr-0.048
ishment-0.048
 Majesty-0.048
lee-0.045
Token are
Token ID389
Feature activation+7.05e-02

Pos logit contributions
 much+0.105
 wonderful+0.101
br+0.094
On+0.091
lessly+0.090
Neg logit contributions
ados-0.129
ishment-0.117
 heads-0.117
 Cr-0.116
 knees-0.116
Token too
Token ID1165
Feature activation+8.38e-02

Pos logit contributions
arest+0.115
ching+0.108
br+0.104
hest+0.099
lessly+0.099
Neg logit contributions
gy-0.112
 Cr-0.107
ados-0.107
 heads-0.103
ishment-0.102
Token full
Token ID1336
Feature activation+2.68e-02

Pos logit contributions
lessly+0.096
br+0.095
arest+0.092
hest+0.091
ching+0.090
Neg logit contributions
gy-0.157
ados-0.150
 knees-0.147
ishment-0.144
lee-0.144
Token.
Token ID13
Feature activation-6.08e-03

Pos logit contributions
 much+0.041
 wonderful+0.038
lessly+0.036
In+0.036
arest+0.035
Neg logit contributions
ados-0.051
 Cr-0.048
ishment-0.046
lee-0.046
 Fro-0.045
Token Their
Token ID5334
Feature activation+1.11e-02

Pos logit contributions
 Majesty+0.010
ados+0.009
 Cr+0.009
ishment+0.009
ci+0.008
Neg logit contributions
 much-0.013
On-0.011
lessly-0.011
In-0.011
 lot-0.011
Token things
Token ID1243
Feature activation+9.62e-02

Pos logit contributions
 much+0.023
 wonderful+0.020
 hard+0.019
lessly+0.019
On+0.019
Neg logit contributions
 Cr-0.019
ados-0.018
ishment-0.018
 Majesty-0.017
 Fro-0.016
Token do
Token ID466
Feature activation+3.45e-02

Pos logit contributions
 much+0.152
br+0.146
lic+0.145
On+0.144
Finally+0.142
Neg logit contributions
ados-0.154
 heads-0.153
 knees-0.152
ishment-0.139
lee-0.138
Token not
Token ID407
Feature activation+4.05e-02

Pos logit contributions
lessly+0.056
 much+0.054
 wonderful+0.049
br+0.049
 importantly+0.048
Neg logit contributions
gy-0.059
 Cr-0.055
ishment-0.052
 Av-0.050
ci-0.050
Token fit
Token ID4197
Feature activation+1.75e-03

Pos logit contributions
 much+0.072
ching+0.071
br+0.070
 million+0.068
In+0.068
Neg logit contributions
 Cr-0.051
ados-0.048
ishment-0.047
 Harry-0.046
gy-0.046
Token.
Token ID13
Feature activation-2.12e-03

Pos logit contributions
 much+0.003
On+0.002
 wonderful+0.002
lessly+0.002
In+0.002
Neg logit contributions
ados-0.003
 Cr-0.003
ishment-0.003
 Majesty-0.003
lee-0.003
Token Sara
Token ID24799
Feature activation+2.42e-03

Pos logit contributions
 Majesty+0.003
ados+0.003
 Cr+0.003
ishment+0.003
lee+0.003
Neg logit contributions
 much-0.005
lessly-0.004
On-0.004
 wonderful-0.004
In-0.004
Token.
Token ID13
Feature activation+1.56e-03

Pos logit contributions
 much+0.021
 wonderful+0.019
In+0.019
On+0.018
br+0.018
Neg logit contributions
ados-0.019
 Cr-0.018
ishment-0.018
 Majesty-0.017
lee-0.017
Token
Token ID198
Feature activation+6.07e-02

Pos logit contributions
 much+0.004
 wonderful+0.003
lessly+0.003
br+0.003
On+0.003
Neg logit contributions
 Cr-0.002
ados-0.002
ishment-0.002
 Majesty-0.002
 Fro-0.002
Token
Token ID198
Feature activation+5.60e-02

Pos logit contributions
 much+0.099
lessly+0.099
 wonderful+0.098
br+0.097
ching+0.089
Neg logit contributions
 Cr-0.106
 Fro-0.097
 Rib-0.093
gy-0.091
lee-0.090
TokenThen
Token ID6423
Feature activation+4.68e-02

Pos logit contributions
lessly+0.073
 much+0.073
 wonderful+0.073
iest+0.061
br+0.061
Neg logit contributions
 Cr-0.116
 Rib-0.105
 Fro-0.103
gy-0.101
 Majesty-0.097
Token,
Token ID11
Feature activation+4.60e-02

Pos logit contributions
 much+0.087
lessly+0.077
 wonderful+0.075
On+0.074
In+0.072
Neg logit contributions
 Cr-0.082
ados-0.082
 Majesty-0.079
ishment-0.078
 Fro-0.074
Token something
Token ID1223
Feature activation+9.52e-02

Pos logit contributions
 much+0.086
lessly+0.079
ching+0.076
 wonderful+0.076
br+0.075
Neg logit contributions
 Cr-0.080
ados-0.072
 Majesty-0.072
ishment-0.071
 Fro-0.071
Token bad
Token ID2089
Feature activation+2.29e-02

Pos logit contributions
ifying+0.124
lessly+0.121
On+0.110
 much+0.110
arest+0.108
Neg logit contributions
 Cr-0.170
 Fro-0.168
 Nem-0.158
 slur-0.155
 Freddy-0.154
Token happened
Token ID3022
Feature activation+7.14e-03

Pos logit contributions
 much+0.035
 wonderful+0.029
lessly+0.029
On+0.029
In+0.027
Neg logit contributions
 Cr-0.047
ados-0.046
ishment-0.043
 Fro-0.043
lee-0.043
Token.
Token ID13
Feature activation+8.82e-03

Pos logit contributions
 much+0.012
 wonderful+0.011
lessly+0.011
br+0.011
In+0.011
Neg logit contributions
 Cr-0.012
ados-0.012
gy-0.012
 Majesty-0.012
ishment-0.012
Token Z
Token ID1168
Feature activation-1.11e-02

Pos logit contributions
 much+0.020
lessly+0.017
 wonderful+0.017
On+0.017
br+0.017
Neg logit contributions
ados-0.012
 Majesty-0.012
ishment-0.012
 Cr-0.012
lee-0.011
Tokenee
Token ID1453
Feature activation+1.52e-02

Pos logit contributions
ados+0.020
 Cr+0.020
 Majesty+0.019
ishment+0.019
lee+0.018
Neg logit contributions
 much-0.020
 wonderful-0.017
lessly-0.017
On-0.017
br-0.017
Token When
Token ID1649
Feature activation+5.89e-02

Pos logit contributions
 much+0.007
 wonderful+0.006
lessly+0.006
br+0.006
On+0.006
Neg logit contributions
ados-0.005
 Cr-0.005
 Majesty-0.005
ishment-0.005
lee-0.005
Token they
Token ID484
Feature activation+3.30e-02

Pos logit contributions
 much+0.108
lessly+0.102
br+0.102
ching+0.099
On+0.098
Neg logit contributions
 Cr-0.093
ados-0.092
 Majesty-0.084
lee-0.084
ishment-0.082
Token got
Token ID1392
Feature activation+3.57e-02

Pos logit contributions
 much+0.057
lessly+0.055
br+0.054
ching+0.050
 valuable+0.050
Neg logit contributions
 Cr-0.057
 Fro-0.055
lee-0.052
 Av-0.049
 D-0.048
Token there
Token ID612
Feature activation+4.43e-02

Pos logit contributions
 much+0.076
 wonderful+0.065
lessly+0.064
On+0.063
In+0.062
Neg logit contributions
ados-0.057
 Majesty-0.056
 Cr-0.056
ishment-0.055
lee-0.049
Token,
Token ID11
Feature activation+3.52e-02

Pos logit contributions
 much+0.082
lessly+0.070
 wonderful+0.070
br+0.068
On+0.068
Neg logit contributions
ados-0.079
 Cr-0.079
 Majesty-0.076
ishment-0.076
lee-0.071
Token everything
Token ID2279
Feature activation+9.48e-02

Pos logit contributions
 much+0.076
br+0.074
lessly+0.071
ching+0.070
On+0.068
Neg logit contributions
ados-0.046
 Cr-0.045
ishment-0.044
 Majesty-0.041
gy-0.039
Token was
Token ID373
Feature activation+5.89e-02

Pos logit contributions
 much+0.143
br+0.127
On+0.126
lessly+0.122
He+0.118
Neg logit contributions
lee-0.168
 Cr-0.166
ci-0.164
ishment-0.164
 knees-0.158
Token safe
Token ID3338
Feature activation+2.45e-02

Pos logit contributions
cro+0.100
br+0.099
arest+0.095
lessly+0.086
vere+0.083
Neg logit contributions
 Twe-0.095
gy-0.093
 Harry-0.091
ishment-0.091
 Sammy-0.088
Token and
Token ID290
Feature activation+2.75e-02

Pos logit contributions
 much+0.047
br+0.043
On+0.042
In+0.041
 wonderful+0.040
Neg logit contributions
ados-0.038
ishment-0.037
 Cr-0.036
gy-0.036
lee-0.035
Token Lucy
Token ID22162
Feature activation+1.39e-02

Pos logit contributions
br+0.040
ching+0.038
 much+0.037
lessly+0.036
arest+0.035
Neg logit contributions
ishment-0.053
 Cr-0.051
ados-0.048
ci-0.048
lee-0.047
Token felt
Token ID2936
Feature activation+6.92e-02

Pos logit contributions
 much+0.019
 wonderful+0.016
lessly+0.015
On+0.015
br+0.015
Neg logit contributions
ados-0.032
 Cr-0.031
 Majesty-0.031
ishment-0.031
lee-0.029
Token
Token ID198
Feature activation+6.03e-02

Pos logit contributions
 Cr+0.010
ados+0.009
 Majesty+0.009
ishment+0.009
 Fro+0.008
Neg logit contributions
 much-0.011
 wonderful-0.010
lessly-0.010
br-0.010
On-0.010
Token
Token ID198
Feature activation+5.39e-02

Pos logit contributions
 much+0.090
lessly+0.084
br+0.083
 wonderful+0.079
On+0.073
Neg logit contributions
 Cr-0.120
 Fro-0.114
ados-0.110
lee-0.109
 Majesty-0.107
TokenBut
Token ID1537
Feature activation+4.28e-02

Pos logit contributions
 much+0.085
lessly+0.085
 wonderful+0.082
br+0.079
ier+0.078
Neg logit contributions
 Cr-0.096
 Fro-0.088
roc-0.082
 Harry-0.082
ados-0.081
Token then
Token ID788
Feature activation+3.21e-02

Pos logit contributions
 much+0.088
lessly+0.082
br+0.081
 wonderful+0.080
ching+0.078
Neg logit contributions
 Cr-0.067
ados-0.061
 Fro-0.059
ishment-0.058
 Majesty-0.056
Token,
Token ID11
Feature activation+4.76e-02

Pos logit contributions
 much+0.054
 wonderful+0.044
 hard+0.042
br+0.042
On+0.041
Neg logit contributions
ados-0.066
ishment-0.066
 Majesty-0.064
 Cr-0.064
lee-0.061
Token something
Token ID1223
Feature activation+9.42e-02

Pos logit contributions
 much+0.093
lessly+0.084
 wonderful+0.081
br+0.081
On+0.079
Neg logit contributions
 Cr-0.080
ados-0.078
ishment-0.073
 Majesty-0.073
 Fro-0.071
Token bad
Token ID2089
Feature activation+1.68e-02

Pos logit contributions
ifying+0.111
lessly+0.104
 million+0.103
arest+0.100
On+0.096
Neg logit contributions
 Cr-0.182
 Fro-0.174
 Nem-0.164
 Freddy-0.163
lee-0.162
Token happened
Token ID3022
Feature activation+7.53e-04

Pos logit contributions
 much+0.025
 wonderful+0.021
lessly+0.021
On+0.021
In+0.020
Neg logit contributions
 Cr-0.035
ados-0.034
 Fro-0.031
ishment-0.031
lee-0.031
Token.
Token ID13
Feature activation+7.18e-03

Pos logit contributions
 much+0.001
 wonderful+0.001
lessly+0.001
br+0.001
In+0.001
Neg logit contributions
 Cr-0.001
ados-0.001
ishment-0.001
 Majesty-0.001
gy-0.001
Token Tim
Token ID5045
Feature activation+1.99e-02

Pos logit contributions
 much+0.017
On+0.014
In+0.014
lessly+0.014
br+0.013
Neg logit contributions
 Majesty-0.011
ishment-0.010
ados-0.010
ishes-0.009
ans-0.009
Token hit
Token ID2277
Feature activation+1.99e-02

Pos logit contributions
 much+0.034
lessly+0.030
 wonderful+0.030
br+0.028
On+0.027
Neg logit contributions
ados-0.036
lee-0.035
 Cr-0.035
ishment-0.035
gy-0.035
Token his
Token ID465
Feature activation+8.06e-03

Pos logit contributions
ados+0.020
 Majesty+0.020
 Cr+0.020
ishment+0.020
lee+0.018
Neg logit contributions
 much-0.023
 wonderful-0.020
lessly-0.019
On-0.019
 hard-0.019
Token carrot
Token ID40562
Feature activation+6.12e-03

Pos logit contributions
 much+0.016
 wonderful+0.014
lessly+0.014
On+0.013
br+0.013
Neg logit contributions
ados-0.013
 Cr-0.013
 Majesty-0.013
ishment-0.013
lee-0.012
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
 much+0.009
 wonderful+0.007
lessly+0.007
 hard+0.007
On+0.007
Neg logit contributions
 Cr-0.013
 Majesty-0.013
ados-0.013
ishment-0.013
lee-0.012
Token But
Token ID887
Feature activation+3.95e-02

Pos logit contributions
ishment+0.022
ados+0.022
 Majesty+0.021
 Cr+0.021
ican+0.021
Neg logit contributions
 much-0.020
lessly-0.016
In-0.016
 hard-0.015
On-0.015
Token then
Token ID788
Feature activation+2.52e-02

Pos logit contributions
 much+0.071
lessly+0.062
 wonderful+0.062
br+0.061
On+0.059
Neg logit contributions
 Cr-0.072
ados-0.071
ishment-0.068
 Majesty-0.068
 Fro-0.065
Token something
Token ID1223
Feature activation+9.38e-02

Pos logit contributions
 much+0.039
 wonderful+0.031
lessly+0.030
 hard+0.029
br+0.029
Neg logit contributions
ados-0.055
ishment-0.054
 Cr-0.054
 Majesty-0.053
lee-0.050
Token strange
Token ID6283
Feature activation+3.77e-02

Pos logit contributions
lessly+0.094
 much+0.092
On+0.088
ifying+0.088
arest+0.087
Neg logit contributions
 Cr-0.204
 Fro-0.200
 Nem-0.190
 Freddy-0.186
lee-0.184
Token happened
Token ID3022
Feature activation+1.46e-03

Pos logit contributions
 much+0.065
lessly+0.054
 wonderful+0.052
On+0.052
Finally+0.052
Neg logit contributions
 Cr-0.069
ados-0.066
lee-0.065
ishment-0.065
 Harry-0.064
Token.
Token ID13
Feature activation+6.28e-03

Pos logit contributions
 much+0.002
br+0.002
 wonderful+0.002
lessly+0.002
In+0.002
Neg logit contributions
 Cr-0.003
ados-0.003
ishment-0.003
 Majesty-0.003
 Fro-0.003
Token
Token ID198
Feature activation+6.09e-02

Pos logit contributions
 much+0.014
In+0.011
On+0.011
lessly+0.011
 wonderful+0.011
Neg logit contributions
 Majesty-0.010
ishment-0.010
ados-0.010
 Cr-0.009
ci-0.009
Token
Token ID198
Feature activation+5.30e-02

Pos logit contributions
 much+0.098
lessly+0.094
 wonderful+0.093
br+0.089
 terrible+0.083
Neg logit contributions
 Cr-0.108
 Fro-0.102
ados-0.098
 Rib-0.096
lee-0.096
Token After
Token ID2293
Feature activation+4.53e-02

Pos logit contributions
ados+0.001
 Cr+0.000
 Majesty+0.000
ishment+0.000
lee+0.000
Neg logit contributions
 much-0.001
 wonderful-0.001
lessly-0.001
On-0.001
br-0.001
Token a
Token ID257
Feature activation+5.59e-02

Pos logit contributions
 much+0.067
lessly+0.061
br+0.059
 wonderful+0.058
On+0.058
Neg logit contributions
 Cr-0.093
ados-0.092
 Majesty-0.087
ishment-0.084
lee-0.084
Token few
Token ID1178
Feature activation+4.89e-02

Pos logit contributions
hes+0.091
lessly+0.088
ier+0.084
eps+0.081
ooky+0.076
Neg logit contributions
 Cr-0.086
 Harry-0.084
 Po-0.083
 Av-0.082
 fro-0.082
Token minutes
Token ID2431
Feature activation+4.52e-02

Pos logit contributions
lessly+0.083
 much+0.083
On+0.082
In+0.081
lic+0.078
Neg logit contributions
ados-0.076
 breaths-0.075
 Majesty-0.073
lee-0.072
 knees-0.069
Token,
Token ID11
Feature activation+4.43e-02

Pos logit contributions
 much+0.078
 wonderful+0.068
lessly+0.067
On+0.065
br+0.064
Neg logit contributions
ados-0.085
 Cr-0.085
ishment-0.080
 Majesty-0.079
lee-0.077
Token something
Token ID1223
Feature activation+9.36e-02

Pos logit contributions
br+0.091
ching+0.088
 much+0.087
lessly+0.084
lic+0.083
Neg logit contributions
ados-0.063
 Cr-0.061
 Harry-0.058
ishment-0.057
 Majesty-0.052
Token incredible
Token ID8082
Feature activation+2.64e-02

Pos logit contributions
On+0.109
lessly+0.107
ifying+0.106
Finally+0.103
 much+0.101
Neg logit contributions
 Cr-0.174
 Harry-0.170
 Nem-0.168
lee-0.166
 Sammy-0.161
Token happened
Token ID3022
Feature activation+1.64e-03

Pos logit contributions
 much+0.041
On+0.033
lessly+0.033
In+0.032
 lot+0.031
Neg logit contributions
 Cr-0.054
ados-0.053
ishment-0.052
 Harry-0.051
lee-0.051
Token.
Token ID13
Feature activation+1.51e-02

Pos logit contributions
 much+0.003
 wonderful+0.002
br+0.002
lessly+0.002
In+0.002
Neg logit contributions
 Cr-0.003
ados-0.003
ishment-0.003
 Majesty-0.003
lee-0.003
Token John
Token ID1757
Feature activation+1.29e-02

Pos logit contributions
 much+0.035
br+0.033
 wonderful+0.033
lessly+0.033
ching+0.032
Neg logit contributions
 Cr-0.018
ados-0.018
ishment-0.016
 Majesty-0.016
lee-0.015
Token saw
Token ID2497
Feature activation+2.91e-02

Pos logit contributions
 much+0.018
lessly+0.015
 wonderful+0.015
br+0.014
On+0.014
Neg logit contributions
ados-0.028
 Cr-0.028
 Majesty-0.028
ishment-0.027
lee-0.026
Token shoes
Token ID10012
Feature activation+3.10e-02

Pos logit contributions
ados+0.018
 Cr+0.018
ishment+0.017
 Majesty+0.017
lee+0.016
Neg logit contributions
 much-0.022
 wonderful-0.019
lessly-0.019
On-0.019
br-0.018
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
 much+0.053
 wonderful+0.049
br+0.047
In+0.045
lessly+0.045
Neg logit contributions
ados-0.056
 Cr-0.056
ishment-0.055
gy-0.052
 Fro-0.051
Token But
Token ID887
Feature activation+4.05e-02

Pos logit contributions
ados+0.022
 Cr+0.022
 Majesty+0.021
ishment+0.021
lee+0.019
Neg logit contributions
 much-0.030
lessly-0.026
 wonderful-0.026
On-0.026
br-0.025
Token then
Token ID788
Feature activation+2.65e-02

Pos logit contributions
 much+0.086
lessly+0.080
 wonderful+0.080
br+0.079
ching+0.078
Neg logit contributions
 Cr-0.058
ados-0.056
 Fro-0.052
ishment-0.050
 Majesty-0.048
Token,
Token ID11
Feature activation+4.09e-02

Pos logit contributions
 much+0.048
lessly+0.041
 wonderful+0.041
On+0.039
br+0.039
Neg logit contributions
ados-0.049
 Cr-0.049
 Majesty-0.047
ishment-0.047
lee-0.044
Token something
Token ID1223
Feature activation+9.34e-02

Pos logit contributions
 much+0.080
lessly+0.073
 wonderful+0.071
br+0.070
ching+0.069
Neg logit contributions
 Cr-0.065
ados-0.065
 Majesty-0.060
 Fro-0.058
ishment-0.058
Token happened
Token ID3022
Feature activation+1.40e-03

Pos logit contributions
ifying+0.112
lessly+0.107
 much+0.102
arest+0.102
On+0.101
Neg logit contributions
 Fro-0.170
 Cr-0.165
lee-0.164
 Freddy-0.160
 slur-0.158
Token.
Token ID13
Feature activation+4.57e-03

Pos logit contributions
 much+0.002
 wonderful+0.002
lessly+0.002
br+0.002
On+0.002
Neg logit contributions
ados-0.003
 Cr-0.003
 Majesty-0.003
ishment-0.003
lee-0.003
Token
Token ID198
Feature activation+6.27e-02

Pos logit contributions
 much+0.010
 wonderful+0.009
lessly+0.009
On+0.009
br+0.009
Neg logit contributions
ados-0.006
 Cr-0.006
 Majesty-0.006
ishment-0.006
lee-0.005
Token
Token ID198
Feature activation+5.94e-02

Pos logit contributions
 much+0.096
lessly+0.090
 wonderful+0.088
br+0.086
On+0.080
Neg logit contributions
 Cr-0.119
ados-0.114
 Fro-0.112
lee-0.108
 Majesty-0.107
TokenTom
Token ID13787
Feature activation+1.54e-02

Pos logit contributions
 wonderful+0.085
 much+0.084
lessly+0.083
 hard+0.073
 valuable+0.073
Neg logit contributions
ados-0.108
 Cr-0.106
 Fro-0.097
 Rib-0.096
ree-0.095
Token
Token ID220
Feature activation+9.09e-03

Pos logit contributions
ados+0.018
ican+0.018
ishment+0.017
 Majesty+0.017
ans+0.017
Neg logit contributions
 much-0.015
On-0.013
In-0.012
lessly-0.012
 wonderful-0.011
Token
Token ID198
Feature activation+5.30e-02

Pos logit contributions
 much+0.013
 wonderful+0.011
lessly+0.011
br+0.011
On+0.010
Neg logit contributions
 Cr-0.019
ados-0.019
 Majesty-0.018
ishment-0.018
 Fro-0.018
Token
Token ID198
Feature activation+4.54e-02

Pos logit contributions
 much+0.084
 wonderful+0.075
br+0.073
lessly+0.073
 terrible+0.069
Neg logit contributions
 Cr-0.099
 Fro-0.096
ados-0.094
 Rib-0.092
lee-0.092
TokenSuddenly
Token ID38582
Feature activation+4.82e-02

Pos logit contributions
 much+0.058
 wonderful+0.049
lessly+0.048
br+0.048
 hard+0.046
Neg logit contributions
 Cr-0.096
ados-0.095
 Majesty-0.093
 Fro-0.093
ishment-0.092
Token,
Token ID11
Feature activation+4.54e-02

Pos logit contributions
 much+0.081
 wonderful+0.066
lessly+0.064
br+0.063
 hard+0.063
Neg logit contributions
ados-0.099
 Cr-0.098
ishment-0.097
 Majesty-0.096
keeping-0.090
Token something
Token ID1223
Feature activation+9.34e-02

Pos logit contributions
 much+0.113
 wonderful+0.100
lessly+0.099
On+0.097
br+0.097
Neg logit contributions
ados-0.054
 Cr-0.053
 Majesty-0.051
ishment-0.051
lee-0.045
Token loud
Token ID7812
Feature activation+9.80e-03

Pos logit contributions
ris+0.109
ifying+0.107
 much+0.104
 million+0.104
arest+0.098
Neg logit contributions
lee-0.159
 Fro-0.158
 Harry-0.154
 Sammy-0.153
 Freddy-0.150
Token happened
Token ID3022
Feature activation-8.97e-04

Pos logit contributions
 much+0.017
 wonderful+0.014
In+0.014
lessly+0.014
On+0.014
Neg logit contributions
ados-0.018
 Cr-0.018
ishment-0.017
lee-0.017
icans-0.016
Token.
Token ID13
Feature activation+8.41e-03

Pos logit contributions
 Cr+0.002
ados+0.002
gy+0.001
ishment+0.001
lee+0.001
Neg logit contributions
 much-0.002
br-0.001
 wonderful-0.001
lessly-0.001
In-0.001
Token It
Token ID632
Feature activation+5.82e-02

Pos logit contributions
 much+0.019
lessly+0.016
On+0.016
In+0.015
 hard+0.015
Neg logit contributions
ados-0.013
ishment-0.013
 Majesty-0.013
ans-0.013
ci-0.013
Token was
Token ID373
Feature activation+4.51e-02

Pos logit contributions
 much+0.099
arest+0.087
lessly+0.085
 wonderful+0.081
vere+0.080
Neg logit contributions
gy-0.100
 Harry-0.091
stick-0.091
 Cr-0.091
lee-0.091
Token the
Token ID262
Feature activation+1.96e-02

Pos logit contributions
 Cr+0.013
ados+0.013
 Majesty+0.013
ishment+0.012
amb+0.012
Neg logit contributions
 much-0.012
 wonderful-0.010
 hard-0.010
lessly-0.010
On-0.009
Token hole
Token ID7604
Feature activation+4.31e-02

Pos logit contributions
 much+0.036
br+0.035
lessly+0.034
On+0.034
lic+0.033
Neg logit contributions
ados-0.031
 Cr-0.029
ishment-0.028
 Majesty-0.027
 Harry-0.026
Token.
Token ID13
Feature activation-9.95e-03

Pos logit contributions
 much+0.068
 wonderful+0.062
br+0.061
In+0.060
On+0.058
Neg logit contributions
ados-0.081
 Cr-0.079
ishment-0.078
lee-0.076
 Majesty-0.075
Token Suddenly
Token ID24975
Feature activation+4.19e-02

Pos logit contributions
 Cr+0.017
ados+0.017
ishment+0.016
 Majesty+0.016
ans+0.015
Neg logit contributions
 much-0.021
On-0.017
In-0.017
lessly-0.017
 wonderful-0.017
Token,
Token ID11
Feature activation+4.34e-02

Pos logit contributions
 much+0.076
 wonderful+0.065
lessly+0.064
On+0.062
br+0.062
Neg logit contributions
ados-0.077
 Cr-0.076
 Majesty-0.074
ishment-0.074
lee-0.069
Token something
Token ID1223
Feature activation+9.29e-02

Pos logit contributions
 much+0.081
br+0.075
lessly+0.074
 wonderful+0.072
ching+0.071
Neg logit contributions
ados-0.071
 Cr-0.067
ishment-0.063
 Harry-0.061
 Majesty-0.061
Token popped
Token ID22928
Feature activation+1.89e-02

Pos logit contributions
 much+0.113
ris+0.112
ifying+0.108
Today+0.106
 million+0.106
Neg logit contributions
 Harry-0.161
 Fro-0.159
 Freddy-0.157
 Sammy-0.154
 Cr-0.154
Token out
Token ID503
Feature activation+3.03e-02

Pos logit contributions
 much+0.032
 wonderful+0.028
lessly+0.027
On+0.026
br+0.026
Neg logit contributions
ados-0.036
 Cr-0.035
ishment-0.034
gy-0.033
lee-0.033
Token of
Token ID286
Feature activation+1.13e-02

Pos logit contributions
 much+0.045
 wonderful+0.040
arest+0.040
br+0.039
In+0.039
Neg logit contributions
ados-0.057
lee-0.056
 Cr-0.055
 Harry-0.054
ishment-0.052
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
 much+0.026
lessly+0.023
br+0.023
 wonderful+0.023
On+0.022
Neg logit contributions
ados-0.015
 Cr-0.015
ishment-0.014
 Majesty-0.013
lee-0.013
Token hole
Token ID7604
Feature activation+5.16e-02

Pos logit contributions
 much+0.044
lessly+0.040
On+0.040
br+0.040
In+0.039
Neg logit contributions
ados-0.032
ishment-0.030
 Cr-0.030
 Majesty-0.029
gy-0.028
Token big
Token ID1263
Feature activation-2.24e-02

Pos logit contributions
ados+0.044
 Cr+0.044
ishment+0.041
 Majesty+0.040
icans+0.039
Neg logit contributions
 much-0.045
 wonderful-0.039
On-0.037
 hard-0.037
In-0.036
Token garden
Token ID11376
Feature activation+6.87e-03

Pos logit contributions
 Cr+0.047
ados+0.046
cess+0.045
amb+0.044
 Majesty+0.044
Neg logit contributions
 much-0.038
 wonderful-0.034
 big-0.033
 hard-0.032
 bad-0.032
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
 much+0.009
On+0.007
 wonderful+0.006
lessly+0.006
In+0.006
Neg logit contributions
ados-0.017
 Cr-0.017
 Majesty-0.017
ishment-0.016
lee-0.016
Token Suddenly
Token ID24975
Feature activation+4.13e-02

Pos logit contributions
ishment+0.024
ados+0.024
ans+0.024
 Cr+0.024
 Majesty+0.024
Neg logit contributions
 much-0.023
On-0.019
In-0.019
lessly-0.018
 hard-0.018
Token,
Token ID11
Feature activation+3.96e-02

Pos logit contributions
 much+0.072
 wonderful+0.060
br+0.058
lessly+0.058
On+0.056
Neg logit contributions
 Cr-0.081
ados-0.080
ishment-0.080
 Majesty-0.078
lee-0.073
Token everything
Token ID2279
Feature activation+9.29e-02

Pos logit contributions
 much+0.068
 wonderful+0.057
lessly+0.057
On+0.055
br+0.054
Neg logit contributions
ados-0.077
 Cr-0.076
 Majesty-0.074
ishment-0.074
lee-0.069
Token started
Token ID2067
Feature activation+2.23e-02

Pos logit contributions
 much+0.158
br+0.140
lessly+0.140
On+0.138
arest+0.138
Neg logit contributions
 Cr-0.145
 knees-0.144
lee-0.143
ados-0.142
ishment-0.135
Token to
Token ID284
Feature activation+7.60e-03

Pos logit contributions
 much+0.043
 wonderful+0.037
lessly+0.036
On+0.035
br+0.035
Neg logit contributions
ados-0.039
 Cr-0.039
 Majesty-0.038
ishment-0.037
lee-0.035
Token shake
Token ID13279
Feature activation+2.21e-02

Pos logit contributions
 much+0.016
lessly+0.014
 wonderful+0.014
br+0.014
On+0.013
Neg logit contributions
 Cr-0.011
ados-0.011
ishment-0.011
 Majesty-0.011
 Fro-0.010
Token.
Token ID13
Feature activation-4.93e-04

Pos logit contributions
 much+0.035
In+0.032
br+0.032
 wonderful+0.031
lessly+0.031
Neg logit contributions
ados-0.041
ishment-0.040
 Cr-0.039
gy-0.038
lee-0.037
Token The
Token ID383
Feature activation+3.15e-02

Pos logit contributions
ishment+0.001
 Majesty+0.001
 Cr+0.001
ados+0.001
ans+0.001
Neg logit contributions
 much-0.001
In-0.001
On-0.001
lessly-0.001
 hard-0.001
Token when
Token ID618
Feature activation+5.62e-02

Pos logit contributions
 much+0.070
 wonderful+0.060
lessly+0.060
br+0.058
On+0.058
Neg logit contributions
ados-0.071
 Cr-0.071
ishment-0.068
 Majesty-0.068
lee-0.063
Token he
Token ID339
Feature activation+1.98e-02

Pos logit contributions
 much+0.095
lessly+0.080
 wonderful+0.080
On+0.077
br+0.077
Neg logit contributions
ados-0.110
 Cr-0.109
 Majesty-0.106
ishment-0.106
lee-0.099
Token was
Token ID373
Feature activation+3.38e-02

Pos logit contributions
 much+0.035
lessly+0.033
 wonderful+0.029
br+0.029
 hard+0.027
Neg logit contributions
 Cr-0.036
 Fro-0.034
ishment-0.034
 fro-0.033
ados-0.033
Token gone
Token ID3750
Feature activation+2.23e-02

Pos logit contributions
br+0.049
 much+0.048
lessly+0.048
In+0.045
 wonderful+0.045
Neg logit contributions
 Majesty-0.058
lee-0.058
 Fro-0.057
 Cr-0.056
ishment-0.055
Token,
Token ID11
Feature activation+3.99e-02

Pos logit contributions
 much+0.044
lessly+0.039
 wonderful+0.038
In+0.038
br+0.037
Neg logit contributions
ados-0.037
 Cr-0.036
ishment-0.035
 Majesty-0.035
lee-0.033
Token something
Token ID1223
Feature activation+9.29e-02

Pos logit contributions
 much+0.070
lessly+0.061
 wonderful+0.060
br+0.059
On+0.059
Neg logit contributions
ados-0.074
 Cr-0.074
 Majesty-0.070
ishment-0.070
 Fro-0.066
Token magical
Token ID10883
Feature activation+3.56e-02

Pos logit contributions
 much+0.101
On+0.099
lessly+0.098
Finally+0.097
In+0.092
Neg logit contributions
 Cr-0.190
 Fro-0.179
lee-0.178
 Nem-0.177
 ot-0.172
Token happened
Token ID3022
Feature activation+3.90e-04

Pos logit contributions
 much+0.056
lessly+0.046
On+0.045
In+0.044
 wonderful+0.043
Neg logit contributions
 Cr-0.071
ados-0.071
ishment-0.068
lee-0.068
ican-0.066
Token.
Token ID13
Feature activation+2.34e-03

Pos logit contributions
 much+0.001
 wonderful+0.001
lessly+0.001
br+0.001
In+0.001
Neg logit contributions
 Cr-0.001
ados-0.001
ishment-0.001
 Majesty-0.001
lee-0.001
Token A
Token ID317
Feature activation+5.70e-02

Pos logit contributions
 much+0.005
In+0.004
On+0.004
lessly+0.004
 wonderful+0.004
Neg logit contributions
 Majesty-0.004
ishment-0.004
ados-0.004
ans-0.004
ishes-0.004
Token great
Token ID1049
Feature activation+1.62e-02

Pos logit contributions
lessly+0.077
 much+0.071
On+0.067
In+0.067
hest+0.061
Neg logit contributions
 Majesty-0.116
 Cr-0.114
 Fro-0.108
 fro-0.108
ados-0.106
Token to
Token ID284
Feature activation-3.40e-02

Pos logit contributions
 Majesty+0.003
ados+0.003
 Cr+0.003
ishment+0.003
gy+0.003
Neg logit contributions
 much-0.003
 wonderful-0.002
On-0.002
 hard-0.002
lessly-0.002
Token join
Token ID4654
Feature activation-1.26e-02

Pos logit contributions
ados+0.066
 Majesty+0.063
ishment+0.061
 Cr+0.058
gy+0.057
Neg logit contributions
 much-0.064
 wonderful-0.056
On-0.052
 lot-0.052
 hard-0.052
Token them
Token ID606
Feature activation+8.21e-03

Pos logit contributions
 Majesty+0.027
ados+0.025
ishment+0.025
 Cr+0.024
gy+0.023
Neg logit contributions
 much-0.022
 wonderful-0.018
 on-0.018
 hard-0.017
On-0.017
Token,
Token ID11
Feature activation-1.48e-03

Pos logit contributions
 much+0.013
 wonderful+0.010
lessly+0.010
On+0.010
 hard+0.009
Neg logit contributions
ados-0.018
 Cr-0.018
 Majesty-0.018
ishment-0.017
lee-0.016
Token but
Token ID475
Feature activation+2.97e-02

Pos logit contributions
ados+0.003
 Cr+0.003
 Majesty+0.003
ishment+0.003
lee+0.003
Neg logit contributions
 much-0.003
 wonderful-0.002
lessly-0.002
br-0.002
On-0.002
Token something
Token ID1223
Feature activation+9.28e-02

Pos logit contributions
 much+0.056
lessly+0.049
 wonderful+0.048
br+0.047
On+0.047
Neg logit contributions
 Cr-0.052
ados-0.051
ishment-0.050
 Majesty-0.049
 Fro-0.046
Token was
Token ID373
Feature activation+5.69e-02

Pos logit contributions
Finally+0.117
ifying+0.111
arest+0.108
On+0.108
 much+0.103
Neg logit contributions
lee-0.167
 Cr-0.165
 Fro-0.155
 D-0.154
 ot-0.153
Token different
Token ID1180
Feature activation+3.83e-02

Pos logit contributions
arest+0.080
Finally+0.077
br+0.073
lessly+0.071
 much+0.071
Neg logit contributions
 Cr-0.109
 Fro-0.105
ishment-0.098
 Harry-0.098
gy-0.097
Token.
Token ID13
Feature activation-2.55e-03

Pos logit contributions
 much+0.068
Finally+0.064
In+0.062
arest+0.061
br+0.061
Neg logit contributions
ados-0.065
 Cr-0.062
ishment-0.061
lee-0.059
keeping-0.059
Token Her
Token ID2332
Feature activation+8.55e-03

Pos logit contributions
ishment+0.005
 Majesty+0.005
ados+0.004
ans+0.004
keeping+0.004
Neg logit contributions
 much-0.005
In-0.004
On-0.004
lessly-0.004
 lot-0.004
Token friends
Token ID2460
Feature activation+4.32e-02

Pos logit contributions
 much+0.016
 wonderful+0.014
 hard+0.014
 bad+0.013
 big+0.013
Neg logit contributions
 Cr-0.016
ados-0.016
ishment-0.015
 Majesty-0.014
 Rib-0.014
Token she
Token ID673
Feature activation+5.23e-03

Pos logit contributions
 much+0.010
 wonderful+0.009
lessly+0.008
On+0.008
 hard+0.008
Neg logit contributions
 Cr-0.009
ados-0.009
 Majesty-0.009
ishment-0.009
lee-0.008
Token worked
Token ID3111
Feature activation+1.75e-02

Pos logit contributions
 much+0.007
 wonderful+0.006
lessly+0.006
On+0.006
br+0.006
Neg logit contributions
ados-0.012
 Cr-0.012
ishment-0.011
 Majesty-0.011
lee-0.011
Token,
Token ID11
Feature activation+1.70e-03

Pos logit contributions
Over+0.025
br+0.025
In+0.025
arest+0.025
 much+0.024
Neg logit contributions
ados-0.033
ishment-0.030
 Cr-0.029
lee-0.029
gy-0.028
Token but
Token ID475
Feature activation+3.62e-02

Pos logit contributions
 much+0.003
lessly+0.002
 wonderful+0.002
On+0.002
 hard+0.002
Neg logit contributions
ados-0.003
 Cr-0.003
 Majesty-0.003
ishment-0.003
lee-0.003
Token then
Token ID788
Feature activation+2.67e-02

Pos logit contributions
 much+0.067
lessly+0.058
 wonderful+0.057
br+0.056
On+0.055
Neg logit contributions
ados-0.065
 Cr-0.064
ishment-0.062
 Majesty-0.062
lee-0.058
Token something
Token ID1223
Feature activation+9.28e-02

Pos logit contributions
 much+0.044
 wonderful+0.036
lessly+0.035
On+0.035
br+0.034
Neg logit contributions
ados-0.054
 Cr-0.054
ishment-0.053
 Majesty-0.053
lee-0.049
Token bad
Token ID2089
Feature activation+1.73e-02

Pos logit contributions
ris+0.100
arest+0.100
On+0.098
ifying+0.098
 much+0.096
Neg logit contributions
lee-0.166
 Cr-0.165
 Freddy-0.163
 Fro-0.161
 Nem-0.160
Token happened
Token ID3022
Feature activation+4.77e-06

Pos logit contributions
 much+0.025
 wonderful+0.021
lessly+0.020
On+0.020
In+0.019
Neg logit contributions
ados-0.037
 Cr-0.035
lee-0.034
ishment-0.034
 Harry-0.033
Token.
Token ID13
Feature activation+4.25e-03

Feature not active on prev token;
no predictions were affected.
Token The
Token ID383
Feature activation+3.50e-02

Pos logit contributions
 much+0.009
On+0.008
In+0.008
lessly+0.007
 hard+0.007
Neg logit contributions
 Majesty-0.007
ishment-0.007
ans-0.007
 Cr-0.007
ados-0.007
Token apple
Token ID17180
Feature activation+4.89e-02

Pos logit contributions
 much+0.074
lessly+0.066
 wonderful+0.064
br+0.064
On+0.063
Neg logit contributions
ados-0.053
 Majesty-0.051
 Cr-0.051
ishment-0.050
lee-0.046
Token they
Token ID484
Feature activation+3.30e-02

Pos logit contributions
 much+0.132
lessly+0.127
br+0.125
ching+0.121
 wonderful+0.118
Neg logit contributions
 Cr-0.092
ados-0.087
ishment-0.083
gy-0.081
 Majesty-0.081
Token reached
Token ID4251
Feature activation-6.24e-04

Pos logit contributions
 much+0.062
br+0.059
lessly+0.058
 wonderful+0.056
ching+0.054
Neg logit contributions
 Cr-0.055
 Fro-0.048
lee-0.046
 fro-0.046
ishment-0.046
Token the
Token ID262
Feature activation+1.62e-02

Pos logit contributions
 Cr+0.001
ados+0.001
ishment+0.001
 Majesty+0.001
 Fro+0.001
Neg logit contributions
 much-0.001
lessly-0.001
br-0.001
 wonderful-0.001
In-0.001
Token stand
Token ID1302
Feature activation+3.86e-02

Pos logit contributions
lessly+0.031
 much+0.031
ching+0.028
lic+0.028
br+0.027
Neg logit contributions
 Majesty-0.025
ishment-0.022
 Cr-0.022
 exp-0.022
 fro-0.022
Token,
Token ID11
Feature activation+3.72e-02

Pos logit contributions
 much+0.072
 wonderful+0.062
lessly+0.062
On+0.061
br+0.060
Neg logit contributions
ados-0.067
 Cr-0.066
 Majesty-0.064
ishment-0.064
lee-0.060
Token things
Token ID1243
Feature activation+9.27e-02

Pos logit contributions
 much+0.087
br+0.082
lessly+0.081
ching+0.078
 wonderful+0.078
Neg logit contributions
 Cr-0.045
ados-0.043
ishment-0.040
 Harry-0.038
 Majesty-0.037
Token weren
Token ID6304
Feature activation+3.46e-02

Pos logit contributions
 much+0.150
br+0.130
Finally+0.130
On+0.128
One+0.127
Neg logit contributions
 Cr-0.153
 Harry-0.149
ados-0.148
 Sammy-0.147
lee-0.146
Token't
Token ID470
Feature activation+6.13e-02

Pos logit contributions
 wonderful+0.067
 much+0.066
lessly+0.064
br+0.062
 importantly+0.061
Neg logit contributions
 Cr-0.045
ados-0.038
 Harry-0.036
ican-0.036
 Twe-0.035
Token as
Token ID355
Feature activation+5.80e-02

Pos logit contributions
Finally+0.093
In+0.089
Over+0.089
arest+0.088
br+0.086
Neg logit contributions
 Harry-0.101
 Cr-0.098
ishment-0.094
 Nem-0.093
ados-0.092
Token expected
Token ID2938
Feature activation+2.09e-02

Pos logit contributions
br+0.063
ching+0.061
In+0.058
arest+0.057
On+0.056
Neg logit contributions
 Cr-0.125
 Harry-0.120
 Nem-0.115
 Sammy-0.114
 Joey-0.113
Token.
Token ID13
Feature activation+5.15e-03

Pos logit contributions
 much+0.035
 wonderful+0.031
On+0.031
lessly+0.031
In+0.031
Neg logit contributions
 Cr-0.038
ados-0.037
lee-0.035
ishment-0.035
 Harry-0.034
Token they
Token ID484
Feature activation+2.52e-02

Pos logit contributions
 much+0.094
lessly+0.081
 wonderful+0.079
br+0.077
On+0.077
Neg logit contributions
ados-0.108
 Cr-0.108
 Majesty-0.104
ishment-0.103
lee-0.097
Token reached
Token ID4251
Feature activation+1.38e-03

Pos logit contributions
 much+0.046
lessly+0.045
 wonderful+0.044
 valuable+0.044
br+0.044
Neg logit contributions
 Cr-0.041
 Fro-0.039
 fro-0.037
lee-0.035
 Rib-0.034
Token the
Token ID262
Feature activation+1.91e-02

Pos logit contributions
 much+0.003
lessly+0.003
 wonderful+0.003
br+0.003
On+0.003
Neg logit contributions
 Cr-0.002
ados-0.002
ishment-0.002
 Majesty-0.002
 Fro-0.002
Token bottom
Token ID4220
Feature activation+4.43e-02

Pos logit contributions
lessly+0.041
lic+0.039
br+0.038
ching+0.038
 importantly+0.038
Neg logit contributions
 Majesty-0.021
ASH-0.021
 fro-0.020
ican-0.020
 Cr-0.020
Token,
Token ID11
Feature activation+3.36e-02

Pos logit contributions
 much+0.084
lessly+0.076
 wonderful+0.076
On+0.073
In+0.073
Neg logit contributions
ados-0.073
 Cr-0.073
ishment-0.068
 Majesty-0.066
 Fro-0.066
Token something
Token ID1223
Feature activation+9.27e-02

Pos logit contributions
 much+0.058
lessly+0.049
 wonderful+0.049
br+0.048
On+0.048
Neg logit contributions
ados-0.064
 Cr-0.064
ishment-0.062
 Majesty-0.062
lee-0.058
Token bad
Token ID2089
Feature activation+2.03e-02

Pos logit contributions
lessly+0.122
ifying+0.122
Finally+0.119
On+0.115
arest+0.115
Neg logit contributions
 Cr-0.159
 Fro-0.152
 Nem-0.151
 ot-0.147
 Freddy-0.145
Token happened
Token ID3022
Feature activation+2.35e-03

Pos logit contributions
 much+0.031
lessly+0.025
 wonderful+0.025
On+0.025
In+0.024
Neg logit contributions
 Cr-0.042
ados-0.041
ishment-0.039
 Fro-0.039
 Harry-0.038
Token.
Token ID13
Feature activation+7.37e-03

Pos logit contributions
 much+0.004
 wonderful+0.004
lessly+0.004
br+0.003
In+0.003
Neg logit contributions
 Cr-0.004
ados-0.004
ishment-0.004
 Majesty-0.004
gy-0.004
Token Tim
Token ID5045
Feature activation+1.53e-02

Pos logit contributions
 much+0.019
lessly+0.016
In+0.016
On+0.016
 wonderful+0.016
Neg logit contributions
 Majesty-0.009
ados-0.009
ishment-0.009
 Cr-0.008
lee-0.007
Token's
Token ID338
Feature activation+1.20e-02

Pos logit contributions
 much+0.026
 wonderful+0.022
lessly+0.022
br+0.021
On+0.021
Neg logit contributions
ados-0.030
 Cr-0.029
ishment-0.029
 Majesty-0.029
lee-0.027
Token give
Token ID1577
Feature activation-5.56e-02

Pos logit contributions
ados+0.158
 Cr+0.154
ishment+0.153
 Majesty+0.151
lee+0.143
Neg logit contributions
 much-0.160
 wonderful-0.136
On-0.130
 hard-0.128
lessly-0.127
Token to
Token ID284
Feature activation-6.70e-02

Pos logit contributions
 Majesty+0.102
ishment+0.100
 Cr+0.098
ados+0.097
cess+0.090
Neg logit contributions
 much-0.105
 wonderful-0.088
 hard-0.085
lessly-0.084
 lot-0.080
Token the
Token ID262
Feature activation-4.15e-02

Pos logit contributions
ishment+0.130
ados+0.124
amb+0.123
 Cr+0.121
 Majesty+0.120
Neg logit contributions
 much-0.127
 wonderful-0.106
 lot-0.098
 hard-0.097
 bad-0.093
Token rh
Token ID9529
Feature activation-7.28e-02

Pos logit contributions
ados+0.066
 Cr+0.066
 Majesty+0.064
ishment+0.063
lee+0.058
Neg logit contributions
 much-0.085
 wonderful-0.073
lessly-0.073
On-0.071
br-0.071
Tokenin
Token ID259
Feature activation-5.42e-02

Pos logit contributions
ados+0.161
 Cr+0.159
 Majesty+0.155
ishment+0.154
 Fro+0.145
Neg logit contributions
 much-0.104
 wonderful-0.086
lessly-0.085
On-0.082
br-0.080
Tokenoc
Token ID420
Feature activation-1.45e-01

Pos logit contributions
ishment+0.095
ados+0.091
 Majesty+0.089
 Cr+0.088
lee+0.087
Neg logit contributions
 much-0.111
 wonderful-0.093
br-0.090
 hard-0.089
On-0.088
Tokeneros
Token ID27498
Feature activation-5.96e-02

Pos logit contributions
 Jenna+0.144
ishment+0.135
lee+0.133
 Cr+0.132
 Rachel+0.132
Neg logit contributions
 much-0.326
br-0.299
 hard-0.298
ier-0.288
lessly-0.288
Token.
Token ID13
Feature activation-5.43e-02

Pos logit contributions
ishment+0.131
ados+0.129
 Cr+0.127
 Majesty+0.126
lee+0.120
Neg logit contributions
 much-0.092
 wonderful-0.073
lessly-0.068
 hard-0.067
On-0.066
Token Lily
Token ID20037
Feature activation-3.83e-02

Pos logit contributions
ados+0.108
ishment+0.107
 Majesty+0.105
ishes+0.102
urg+0.102
Neg logit contributions
 much-0.095
On-0.079
He-0.075
In-0.074
lessly-0.069
Token walked
Token ID6807
Feature activation-3.05e-02

Pos logit contributions
ados+0.103
 Cr+0.101
ishment+0.098
 Majesty+0.094
ican+0.094
Neg logit contributions
 much-0.040
 wonderful-0.031
 hard-0.030
 had-0.030
 also-0.029
Token to
Token ID284
Feature activation-5.40e-02

Pos logit contributions
ados+0.062
 Cr+0.061
 Majesty+0.060
ishment+0.060
lee+0.056
Neg logit contributions
 much-0.051
lessly-0.042
 wonderful-0.042
On-0.041
In-0.040
Token stick
Token ID4859
Feature activation-2.96e-02

Pos logit contributions
ishment+0.174
ados+0.174
 Cr+0.173
 Majesty+0.170
ican+0.162
Neg logit contributions
 much-0.142
 wonderful-0.116
On-0.115
 hard-0.113
ching-0.109
Token the
Token ID262
Feature activation-4.98e-02

Pos logit contributions
 Majesty+0.059
ishment+0.057
 Cr+0.055
ados+0.055
cess+0.054
Neg logit contributions
 much-0.053
 hard-0.045
 wonderful-0.043
lessly-0.042
br-0.040
Token mustache
Token ID49303
Feature activation-3.44e-02

Pos logit contributions
ados+0.087
 Cr+0.086
ishment+0.084
 Majesty+0.083
lee+0.078
Neg logit contributions
 much-0.095
 wonderful-0.081
lessly-0.080
br-0.078
On-0.078
Token on
Token ID319
Feature activation-4.63e-02

Pos logit contributions
 Cr+0.071
ados+0.071
ishment+0.070
 Majesty+0.069
lee+0.066
Neg logit contributions
 much-0.055
lessly-0.045
 wonderful-0.044
br-0.043
On-0.043
Token her
Token ID607
Feature activation-7.95e-02

Pos logit contributions
 Majesty+0.084
 Cr+0.083
ishment+0.082
ados+0.082
lee+0.077
Neg logit contributions
 much-0.089
 wonderful-0.074
 hard-0.072
On-0.071
 lot-0.070
Token upper
Token ID6727
Feature activation-1.42e-01

Pos logit contributions
 Cr+0.138
ishment+0.127
ados+0.123
ican+0.117
icans+0.115
Neg logit contributions
 much-0.163
 hard-0.147
 wonderful-0.146
 big-0.140
 bad-0.138
Token lip
Token ID10645
Feature activation-4.50e-02

Pos logit contributions
ishment+0.224
 Cr+0.223
icans+0.200
ados+0.200
ican+0.198
Neg logit contributions
 much-0.293
He-0.244
 hard-0.237
 big-0.234
ching-0.234
Token with
Token ID351
Feature activation-5.80e-03

Pos logit contributions
 Cr+0.101
ados+0.100
ishment+0.099
 Majesty+0.098
lee+0.093
Neg logit contributions
 much-0.065
lessly-0.051
 wonderful-0.050
br-0.049
On-0.048
Token some
Token ID617
Feature activation+4.09e-03

Pos logit contributions
ados+0.011
 Cr+0.011
 Majesty+0.011
ishment+0.011
lee+0.010
Neg logit contributions
 much-0.010
lessly-0.008
On-0.008
 wonderful-0.008
br-0.008
Token tape
Token ID9154
Feature activation-1.25e-02

Pos logit contributions
 much+0.007
On+0.006
lessly+0.006
In+0.006
 wonderful+0.006
Neg logit contributions
ados-0.007
 Majesty-0.007
 Cr-0.007
ishment-0.007
lee-0.006
Token.
Token ID13
Feature activation-4.75e-02

Pos logit contributions
 Cr+0.028
ados+0.028
 Majesty+0.027
ishment+0.027
lee+0.026
Neg logit contributions
 much-0.018
lessly-0.014
 wonderful-0.014
br-0.013
On-0.013
Token't
Token ID470
Feature activation-5.32e-02

Pos logit contributions
 much+0.048
 wonderful+0.039
br+0.038
 hard+0.037
lessly+0.036
Neg logit contributions
ishment-0.058
ados-0.055
 Majesty-0.055
 Cr-0.054
gy-0.052
Token know
Token ID760
Feature activation-2.80e-02

Pos logit contributions
 Cr+0.099
ados+0.098
 Majesty+0.096
ishment+0.093
lee+0.088
Neg logit contributions
 much-0.093
lessly-0.080
 wonderful-0.079
On-0.078
br-0.078
Token the
Token ID262
Feature activation-2.63e-02

Pos logit contributions
ados+0.057
 Cr+0.056
 Majesty+0.055
ishment+0.054
lee+0.051
Neg logit contributions
 much-0.045
lessly-0.038
 wonderful-0.038
On-0.037
br-0.036
Token rh
Token ID9529
Feature activation-6.14e-02

Pos logit contributions
ados+0.048
 Majesty+0.047
 Cr+0.047
ishment+0.045
 Fro+0.043
Neg logit contributions
 much-0.046
lessly-0.040
On-0.040
In-0.039
br-0.039
Tokenin
Token ID259
Feature activation-4.57e-02

Pos logit contributions
ados+0.125
 Cr+0.120
ishment+0.115
 Majesty+0.114
ishes+0.112
Neg logit contributions
 much-0.099
 wonderful-0.085
lessly-0.084
On-0.084
In-0.081
Tokenoc
Token ID420
Feature activation-1.40e-01

Pos logit contributions
 Cr+0.062
ados+0.061
 Majesty+0.059
ishment+0.057
gy+0.054
Neg logit contributions
 much-0.104
lessly-0.093
 wonderful-0.091
On-0.090
In-0.089
Tokeneros
Token ID27498
Feature activation-3.81e-02

Pos logit contributions
 Cr+0.120
ishment+0.120
lee+0.118
 Jenna+0.118
 Fro+0.116
Neg logit contributions
 much-0.337
lessly-0.306
br-0.306
 hard-0.303
ier-0.300
Token was
Token ID373
Feature activation+1.12e-04

Pos logit contributions
ados+0.091
 Cr+0.091
 Majesty+0.088
ishment+0.087
lee+0.083
Neg logit contributions
 much-0.047
lessly-0.038
 wonderful-0.037
On-0.035
br-0.035
Token wild
Token ID4295
Feature activation-5.12e-02

Pos logit contributions
 much+0.000
lessly+0.000
br+0.000
In+0.000
On+0.000
Neg logit contributions
 Cr-0.000
ados-0.000
 Majesty-0.000
ishment-0.000
gy-0.000
Token.
Token ID13
Feature activation-5.01e-02

Pos logit contributions
 Cr+0.115
ados+0.113
 Majesty+0.113
ishment+0.112
lee+0.106
Neg logit contributions
 much-0.073
 wonderful-0.059
lessly-0.058
 hard-0.055
br-0.054
Token Can
Token ID1680
Feature activation-6.77e-02

Pos logit contributions
ados+0.094
 Majesty+0.092
ishment+0.092
ishes+0.090
ans+0.088
Neg logit contributions
 much-0.096
On-0.078
In-0.077
He-0.074
lessly-0.072
Token he
Token ID339
Feature activation-4.77e-02

Pos logit contributions
ados+0.118
ishment+0.117
 Cr+0.116
 Majesty+0.115
lee+0.109
Neg logit contributions
 much-0.079
 wonderful-0.063
 hard-0.058
On-0.057
br-0.057
Token would
Token ID561
Feature activation-7.18e-02

Pos logit contributions
ados+0.112
 Cr+0.110
ishment+0.108
 Majesty+0.107
lee+0.102
Neg logit contributions
 much-0.064
 wonderful-0.050
lessly-0.049
On-0.048
br-0.047
Token take
Token ID1011
Feature activation-6.30e-02

Pos logit contributions
ados+0.131
 Cr+0.129
ishment+0.125
 Majesty+0.125
lee+0.117
Neg logit contributions
 much-0.132
 wonderful-0.112
lessly-0.111
On-0.108
br-0.107
Token the
Token ID262
Feature activation-4.10e-02

Pos logit contributions
ados+0.115
 Cr+0.114
ishment+0.112
 Majesty+0.111
lee+0.103
Neg logit contributions
 much-0.116
 wonderful-0.099
lessly-0.097
br-0.095
On-0.093
Token av
Token ID1196
Feature activation-9.68e-02

Pos logit contributions
ados+0.071
 Cr+0.070
 Majesty+0.068
ishment+0.068
lee+0.062
Neg logit contributions
 much-0.078
lessly-0.067
 wonderful-0.066
On-0.065
In-0.065
Tokenoc
Token ID420
Feature activation-1.38e-01

Pos logit contributions
 Cr+0.156
 Majesty+0.154
ishment+0.151
ados+0.148
lee+0.143
Neg logit contributions
 much-0.197
br-0.171
On-0.167
 wonderful-0.166
lessly-0.164
Tokenados
Token ID22484
Feature activation-2.29e-02

Pos logit contributions
 Fro+0.092
 Cr+0.088
 Rib+0.080
 fro+0.074
ishment+0.073
Neg logit contributions
 much-0.378
lessly-0.348
br-0.348
 hard-0.343
 wonderful-0.334
Token and
Token ID290
Feature activation-6.40e-02

Pos logit contributions
ados+0.041
 Cr+0.040
ishment+0.038
 Majesty+0.037
gy+0.035
Neg logit contributions
 much-0.042
 wonderful-0.037
lessly-0.036
br-0.035
In-0.035
Token scatter
Token ID41058
Feature activation-1.91e-02

Pos logit contributions
 Cr+0.109
ados+0.109
ishment+0.107
 Majesty+0.106
lee+0.099
Neg logit contributions
 much-0.124
 wonderful-0.107
lessly-0.104
On-0.102
br-0.101
Token them
Token ID606
Feature activation-1.54e-02

Pos logit contributions
ados+0.031
 Cr+0.030
ishment+0.028
 Majesty+0.027
lee+0.026
Neg logit contributions
 much-0.039
lessly-0.034
 wonderful-0.034
On-0.034
In-0.033
Token around
Token ID1088
Feature activation-4.96e-02

Pos logit contributions
ados+0.033
 Cr+0.032
ishment+0.032
 Majesty+0.031
gy+0.030
Neg logit contributions
 much-0.022
lessly-0.018
 wonderful-0.018
br-0.018
In-0.018
Token She
Token ID1375
Feature activation-1.63e-02

Pos logit contributions
ans+0.065
ishment+0.065
ados+0.065
 Majesty+0.062
ishes+0.062
Neg logit contributions
 much-0.065
On-0.054
In-0.052
He-0.050
lessly-0.050
Token loved
Token ID6151
Feature activation-5.50e-02

Pos logit contributions
 Cr+0.038
ados+0.038
 Majesty+0.037
ishment+0.037
lee+0.036
Neg logit contributions
 much-0.021
lessly-0.017
 wonderful-0.016
br-0.016
On-0.015
Token to
Token ID284
Feature activation-5.85e-02

Pos logit contributions
ishment+0.135
 Majesty+0.125
cess+0.119
ASH+0.119
 Cr+0.119
Neg logit contributions
 much-0.084
 wonderful-0.070
 hard-0.068
 big-0.063
 lot-0.063
Token eat
Token ID4483
Feature activation-4.01e-02

Pos logit contributions
ishment+0.111
ados+0.110
 Cr+0.106
 Majesty+0.101
ASH+0.097
Neg logit contributions
 much-0.114
 wonderful-0.100
 hard-0.094
On-0.093
 lot-0.092
Token av
Token ID1196
Feature activation-8.64e-02

Pos logit contributions
 Majesty+0.074
ishment+0.073
 Cr+0.073
ados+0.071
gy+0.068
Neg logit contributions
 much-0.075
 wonderful-0.064
 hard-0.060
br-0.060
On-0.060
Tokenoc
Token ID420
Feature activation-1.36e-01

Pos logit contributions
 Cr+0.132
 Majesty+0.130
ishment+0.128
ados+0.128
lee+0.119
Neg logit contributions
 much-0.186
 wonderful-0.159
br-0.158
On-0.156
In-0.153
Tokenados
Token ID22484
Feature activation-1.59e-02

Pos logit contributions
 Fro+0.089
ishment+0.089
 Cr+0.082
gy+0.080
 Rib+0.080
Neg logit contributions
 much-0.365
br-0.339
 hard-0.328
 wonderful-0.325
ier-0.312
Token.
Token ID13
Feature activation-3.64e-02

Pos logit contributions
ados+0.031
 Cr+0.029
ishment+0.028
 Majesty+0.027
 Fro+0.026
Neg logit contributions
 much-0.027
lessly-0.023
 wonderful-0.023
br-0.022
In-0.022
Token One
Token ID1881
Feature activation+2.72e-02

Pos logit contributions
keeping+0.085
ados+0.085
 Majesty+0.084
urg+0.081
ishment+0.080
Neg logit contributions
 much-0.051
On-0.042
In-0.039
One-0.038
 wonderful-0.037
Token day
Token ID1110
Feature activation+1.51e-02

Pos logit contributions
 much+0.041
lessly+0.034
 wonderful+0.034
br+0.032
On+0.032
Neg logit contributions
ados-0.059
 Cr-0.058
 Majesty-0.056
ishment-0.056
lee-0.053
Token,
Token ID11
Feature activation-5.29e-03

Pos logit contributions
 much+0.027
 wonderful+0.023
lessly+0.022
br+0.022
On+0.022
Neg logit contributions
ados-0.028
 Cr-0.028
ishment-0.028
 Majesty-0.028
lee-0.026
Token am
Token ID716
Feature activation-1.27e-02

Pos logit contributions
 Cr+0.081
 Majesty+0.079
ados+0.075
ishment+0.075
 Fro+0.075
Neg logit contributions
 much-0.055
lessly-0.049
br-0.046
 wonderful-0.045
On-0.044
Token taking
Token ID2263
Feature activation-6.92e-02

Pos logit contributions
ados+0.028
 Cr+0.028
 Majesty+0.028
ishment+0.027
lee+0.026
Neg logit contributions
 much-0.018
lessly-0.015
 wonderful-0.014
On-0.014
br-0.014
Token the
Token ID262
Feature activation-4.49e-02

Pos logit contributions
ados+0.128
 Cr+0.127
ishment+0.125
 Majesty+0.124
lee+0.116
Neg logit contributions
 much-0.127
 wonderful-0.108
lessly-0.104
br-0.102
 hard-0.101
Token rh
Token ID9529
Feature activation-6.28e-02

Pos logit contributions
ados+0.077
 Cr+0.076
 Majesty+0.074
ishment+0.073
 Fro+0.068
Neg logit contributions
 much-0.086
lessly-0.074
 wonderful-0.073
On-0.072
In-0.071
Tokenin
Token ID259
Feature activation-5.58e-02

Pos logit contributions
ados+0.136
 Cr+0.133
 Majesty+0.128
ishment+0.128
icans+0.121
Neg logit contributions
 much-0.093
 wonderful-0.078
lessly-0.077
On-0.075
In-0.073
Tokenoc
Token ID420
Feature activation-1.36e-01

Pos logit contributions
ados+0.082
 Cr+0.081
ishment+0.079
 Majesty+0.078
lee+0.072
Neg logit contributions
 much-0.123
 wonderful-0.107
lessly-0.105
br-0.104
On-0.103
Tokeneros
Token ID27498
Feature activation-5.83e-02

Pos logit contributions
 Cr+0.124
 Jenna+0.121
ishment+0.121
 Fro+0.117
 Po+0.115
Neg logit contributions
 much-0.325
br-0.297
 hard-0.293
lessly-0.292
ier-0.286
Token to
Token ID284
Feature activation-5.80e-02

Pos logit contributions
ados+0.114
 Cr+0.113
ishment+0.111
 Majesty+0.110
lee+0.104
Neg logit contributions
 much-0.100
 wonderful-0.083
lessly-0.081
br-0.079
On-0.079
Token a
Token ID257
Feature activation-2.78e-02

Pos logit contributions
ados+0.106
 Cr+0.102
ishment+0.102
 Majesty+0.099
lee+0.096
Neg logit contributions
 much-0.110
 wonderful-0.093
lessly-0.089
On-0.088
br-0.087
Token new
Token ID649
Feature activation-6.07e-02

Pos logit contributions
 Majesty+0.060
 Cr+0.059
ishment+0.057
ados+0.057
 Fro+0.055
Neg logit contributions
 much-0.036
lessly-0.036
In-0.031
br-0.030
On-0.030
Token home
Token ID1363
Feature activation-2.93e-02

Pos logit contributions
ados+0.100
 Cr+0.098
ishment+0.094
 Majesty+0.093
lee+0.088
Neg logit contributions
 much-0.124
 wonderful-0.108
lessly-0.104
On-0.104
br-0.102
Token't
Token ID470
Feature activation-4.99e-02

Pos logit contributions
ados+0.143
 Cr+0.142
 Majesty+0.138
ishment+0.137
lee+0.130
Neg logit contributions
 much-0.104
 wonderful-0.085
lessly-0.085
On-0.082
br-0.081
Token cry
Token ID3960
Feature activation-8.03e-02

Pos logit contributions
ados+0.084
 Cr+0.082
ishment+0.081
 Majesty+0.081
lee+0.074
Neg logit contributions
 much-0.100
 wonderful-0.086
lessly-0.085
On-0.083
br-0.082
Token,
Token ID11
Feature activation-4.93e-02

Pos logit contributions
ados+0.174
ishment+0.172
 Cr+0.171
 Majesty+0.168
icans+0.160
Neg logit contributions
 much-0.126
lessly-0.099
 hard-0.096
 wonderful-0.094
 bad-0.089
Token boys
Token ID6510
Feature activation-5.96e-02

Pos logit contributions
ishment+0.089
ados+0.088
 Majesty+0.086
lee+0.080
gy+0.079
Neg logit contributions
 much-0.099
 wonderful-0.085
br-0.078
 hard-0.078
lessly-0.077
Token.
Token ID13
Feature activation-5.44e-02

Pos logit contributions
ados+0.132
 Cr+0.131
 Majesty+0.128
ishment+0.128
lee+0.120
Neg logit contributions
 much-0.087
 wonderful-0.070
lessly-0.069
br-0.065
On-0.065
Token Acc
Token ID6366
Feature activation-1.34e-01

Pos logit contributions
ishment+0.103
ados+0.103
 Majesty+0.097
icans+0.094
keeping+0.094
Neg logit contributions
 much-0.103
In-0.083
He-0.080
 wonderful-0.080
It-0.079
Tokenidents
Token ID3231
Feature activation-5.54e-04

Pos logit contributions
ados+0.147
keeping+0.147
 Fro+0.146
alk+0.146
 Cr+0.144
Neg logit contributions
 much-0.275
 hard-0.248
 wrong-0.242
 bad-0.241
 better-0.237
Token happen
Token ID1645
Feature activation-3.39e-02

Pos logit contributions
 Cr+0.001
 disl+0.001
ados+0.001
ors+0.001
 Twe+0.001
Neg logit contributions
 much-0.001
On-0.001
In-0.001
br-0.001
 security-0.001
Token.
Token ID13
Feature activation-5.16e-02

Pos logit contributions
ados+0.070
 Cr+0.069
 Majesty+0.067
ishment+0.067
lee+0.063
Neg logit contributions
 much-0.053
lessly-0.045
 wonderful-0.044
On-0.044
br-0.043
Token I
Token ID314
Feature activation-2.53e-02

Pos logit contributions
ados+0.094
ishment+0.093
ican+0.089
icans+0.088
ans+0.087
Neg logit contributions
 much-0.102
lessly-0.081
In-0.081
He-0.080
 wonderful-0.080
Token have
Token ID423
Feature activation-1.06e-02

Pos logit contributions
 Cr+0.047
gy+0.045
 Majesty+0.045
 Fro+0.045
 disl+0.043
Neg logit contributions
 much-0.040
br-0.036
lessly-0.035
On-0.034
In-0.033
Token She
Token ID1375
Feature activation-1.13e-02

Pos logit contributions
ados+0.057
 Majesty+0.057
ans+0.056
ishment+0.056
ishes+0.053
Neg logit contributions
 much-0.057
On-0.047
In-0.045
lessly-0.043
 wonderful-0.043
Token loved
Token ID6151
Feature activation-4.89e-02

Pos logit contributions
ados+0.027
 Cr+0.027
 Majesty+0.026
ishment+0.026
lee+0.025
Neg logit contributions
 much-0.014
lessly-0.011
 wonderful-0.011
br-0.010
On-0.010
Token to
Token ID284
Feature activation-5.48e-02

Pos logit contributions
ishment+0.122
 Majesty+0.115
ASH+0.108
 Cr+0.108
cess+0.108
Neg logit contributions
 much-0.073
 wonderful-0.061
 hard-0.058
 big-0.055
 lot-0.053
Token eat
Token ID4483
Feature activation-3.55e-02

Pos logit contributions
ishment+0.108
ados+0.105
 Cr+0.101
 Majesty+0.097
ASH+0.094
Neg logit contributions
 much-0.105
 wonderful-0.091
 hard-0.086
On-0.085
 lot-0.084
Token av
Token ID1196
Feature activation-8.22e-02

Pos logit contributions
 Majesty+0.067
ishment+0.066
 Cr+0.066
ados+0.065
gy+0.062
Neg logit contributions
 much-0.065
 wonderful-0.055
 hard-0.052
br-0.051
On-0.051
Tokenoc
Token ID420
Feature activation-1.34e-01

Pos logit contributions
 Cr+0.124
 Majesty+0.123
ados+0.121
ishment+0.121
lee+0.113
Neg logit contributions
 much-0.177
 wonderful-0.152
br-0.151
On-0.149
In-0.147
Tokenados
Token ID22484
Feature activation-1.22e-02

Pos logit contributions
ishment+0.090
 Fro+0.089
gy+0.083
 Rib+0.082
 Cr+0.082
Neg logit contributions
 much-0.352
br-0.327
 hard-0.318
 wonderful-0.315
ier-0.305
Token because
Token ID780
Feature activation+1.81e-02

Pos logit contributions
ados+0.023
 Cr+0.022
ishment+0.021
 Majesty+0.021
 Fro+0.020
Neg logit contributions
 much-0.021
lessly-0.018
 wonderful-0.018
br-0.017
In-0.017
Token they
Token ID484
Feature activation+1.11e-03

Pos logit contributions
 much+0.032
lessly+0.028
 wonderful+0.028
br+0.027
On+0.027
Neg logit contributions
ados-0.034
 Cr-0.033
ishment-0.030
 Majesty-0.030
lee-0.029
Token were
Token ID547
Feature activation+1.50e-02

Pos logit contributions
 much+0.001
lessly+0.001
br+0.001
ching+0.001
On+0.001
Neg logit contributions
 Cr-0.003
ados-0.003
 Majesty-0.002
ishment-0.002
gy-0.002
Token y
Token ID331
Feature activation-6.34e-02

Pos logit contributions
 much+0.017
 wonderful+0.013
lessly+0.012
On+0.012
br+0.012
Neg logit contributions
ados-0.038
 Cr-0.038
ishment-0.037
 Majesty-0.037
lee-0.035
Token it
Token ID340
Feature activation-1.17e-02

Pos logit contributions
 Majesty+0.098
ishment+0.097
 Cr+0.097
ados+0.097
ican+0.089
Neg logit contributions
 much-0.124
 wonderful-0.107
lessly-0.102
 hard-0.102
 lot-0.096
Token to
Token ID284
Feature activation-6.23e-02

Pos logit contributions
ishment+0.024
ados+0.024
 Majesty+0.023
 Cr+0.023
ican+0.022
Neg logit contributions
 much-0.021
 wonderful-0.017
 hard-0.016
lessly-0.015
 bad-0.015
Token the
Token ID262
Feature activation-5.14e-02

Pos logit contributions
ados+0.101
ishment+0.099
 Majesty+0.097
 Cr+0.096
amb+0.090
Neg logit contributions
 much-0.130
 wonderful-0.112
 hard-0.105
lessly-0.104
 lot-0.104
Token rh
Token ID9529
Feature activation-5.86e-02

Pos logit contributions
ados+0.087
 Cr+0.086
 Majesty+0.084
ishment+0.083
lee+0.076
Neg logit contributions
 much-0.100
lessly-0.087
 wonderful-0.086
On-0.084
br-0.084
Tokenin
Token ID259
Feature activation-6.13e-02

Pos logit contributions
ados+0.123
 Cr+0.121
 Majesty+0.117
ishment+0.117
gy+0.110
Neg logit contributions
 much-0.088
 wonderful-0.075
lessly-0.075
On-0.073
In-0.071
Tokenoc
Token ID420
Feature activation-1.32e-01

Pos logit contributions
ados+0.103
 Cr+0.099
ishment+0.098
 Majesty+0.095
lee+0.092
Neg logit contributions
 much-0.127
 wonderful-0.107
On-0.103
lessly-0.103
 hard-0.102
Tokeneros
Token ID27498
Feature activation-5.52e-02

Pos logit contributions
 Jenna+0.123
ishment+0.120
 Cr+0.119
lee+0.114
 Po+0.114
Neg logit contributions
 much-0.307
 hard-0.280
br-0.273
lessly-0.272
 wonderful-0.269
Token.
Token ID13
Feature activation-4.47e-02

Pos logit contributions
ados+0.130
ishment+0.127
 Cr+0.126
 Majesty+0.124
lee+0.118
Neg logit contributions
 much-0.077
 wonderful-0.059
lessly-0.056
On-0.054
 hard-0.054
Token When
Token ID1649
Feature activation+1.27e-02

Pos logit contributions
ishment+0.086
ados+0.084
 Majesty+0.083
ishes+0.081
ans+0.080
Neg logit contributions
 much-0.082
On-0.067
In-0.065
He-0.064
lessly-0.061
Token he
Token ID339
Feature activation-1.32e-02

Pos logit contributions
 much+0.020
 wonderful+0.016
 hard+0.015
 lot+0.014
br+0.014
Neg logit contributions
ishment-0.029
 Majesty-0.027
ados-0.027
ans-0.027
amb-0.026
Token tasted
Token ID29187
Feature activation-8.48e-03

Pos logit contributions
 Cr+0.028
ados+0.027
 Majesty+0.027
ishment+0.026
 Fro+0.026
Neg logit contributions
 much-0.020
lessly-0.017
 wonderful-0.016
br-0.015
On-0.015
Token,"
Token ID553
Feature activation-4.93e-02

Pos logit contributions
ados+0.070
 Cr+0.067
 Majesty+0.064
ishment+0.064
 Fro+0.058
Neg logit contributions
 much-0.077
lessly-0.071
In-0.068
On-0.068
 wonderful-0.068
Token said
Token ID531
Feature activation-2.89e-02

Pos logit contributions
 Majesty+0.089
ados+0.087
ishment+0.084
lee+0.080
ans+0.080
Neg logit contributions
 much-0.096
 wonderful-0.079
 hard-0.078
 bad-0.077
On-0.076
Token the
Token ID262
Feature activation-1.21e-02

Pos logit contributions
 Majesty+0.048
ishment+0.047
ados+0.046
ans+0.043
ishes+0.043
Neg logit contributions
 much-0.061
 hard-0.050
 wonderful-0.050
 bad-0.049
br-0.049
Token rh
Token ID9529
Feature activation-4.25e-02

Pos logit contributions
ados+0.021
 Cr+0.021
ishment+0.020
 Majesty+0.020
lee+0.019
Neg logit contributions
 much-0.023
 wonderful-0.020
lessly-0.020
br-0.019
On-0.019
Tokenin
Token ID259
Feature activation-3.36e-02

Pos logit contributions
ados+0.087
 Cr+0.086
 Majesty+0.082
ishment+0.081
 Rib+0.078
Neg logit contributions
 much-0.066
 wonderful-0.057
lessly-0.056
On-0.055
In-0.054
Tokenoc
Token ID420
Feature activation-1.30e-01

Pos logit contributions
ados+0.062
 Cr+0.062
 Majesty+0.060
ishment+0.060
lee+0.056
Neg logit contributions
 much-0.060
 wonderful-0.051
lessly-0.051
On-0.049
br-0.049
Tokeneros
Token ID27498
Feature activation-2.26e-02

Pos logit contributions
 Jenna+0.146
ishment+0.134
 Rachel+0.131
lee+0.131
 Harry+0.128
Neg logit contributions
 much-0.280
 hard-0.263
br-0.263
ier-0.260
lessly-0.252
Token.
Token ID13
Feature activation-4.57e-02

Pos logit contributions
ados+0.047
 Cr+0.047
 Majesty+0.046
ishment+0.045
lee+0.043
Neg logit contributions
 much-0.035
 wonderful-0.029
lessly-0.029
On-0.028
br-0.028
Token
Token ID198
Feature activation+1.12e-02

Pos logit contributions
ados+0.096
ishment+0.094
 Majesty+0.094
 Cr+0.092
lee+0.087
Neg logit contributions
 much-0.073
lessly-0.059
On-0.058
 wonderful-0.057
br-0.056
Token
Token ID198
Feature activation+5.37e-03

Pos logit contributions
 much+0.015
 wonderful+0.012
lessly+0.012
br+0.012
On+0.012
Neg logit contributions
ados-0.025
 Cr-0.025
 Majesty-0.024
ishment-0.024
lee-0.023
TokenThe
Token ID464
Feature activation-1.94e-03

Pos logit contributions
 much+0.007
 wonderful+0.005
lessly+0.005
On+0.005
br+0.005
Neg logit contributions
ados-0.013
 Cr-0.013
 Majesty-0.013
ishment-0.013
lee-0.012
Token
Token ID198
Feature activation-1.28e-02

Pos logit contributions
ados+0.031
 Cr+0.031
 Majesty+0.030
ishment+0.030
lee+0.028
Neg logit contributions
 much-0.018
 wonderful-0.014
lessly-0.014
On-0.014
br-0.014
Token"
Token ID1
Feature activation-2.20e-02

Pos logit contributions
ados+0.032
 Cr+0.032
ishment+0.031
 Majesty+0.031
lee+0.029
Neg logit contributions
 much-0.015
 wonderful-0.012
lessly-0.011
On-0.011
In-0.011
TokenThe
Token ID464
Feature activation-1.66e-02

Pos logit contributions
 Cr+0.046
ados+0.044
ishment+0.043
 Majesty+0.042
 Rib+0.041
Neg logit contributions
 much-0.036
lessly-0.029
 wonderful-0.029
 hard-0.028
br-0.027
Token rh
Token ID9529
Feature activation-4.36e-02

Pos logit contributions
 Majesty+0.027
ados+0.027
 Cr+0.027
ishment+0.025
 Fro+0.024
Neg logit contributions
 much-0.033
lessly-0.029
On-0.028
In-0.028
br-0.028
Tokenin
Token ID259
Feature activation-3.57e-02

Pos logit contributions
ados+0.091
 Cr+0.088
 Majesty+0.085
ishment+0.083
ican+0.080
Neg logit contributions
 much-0.069
lessly-0.058
 wonderful-0.058
On-0.057
In-0.055
Tokenoc
Token ID420
Feature activation-1.28e-01

Pos logit contributions
ados+0.052
 Cr+0.051
 Majesty+0.050
ishment+0.049
lee+0.045
Neg logit contributions
 much-0.078
lessly-0.068
 wonderful-0.068
On-0.067
br-0.066
Tokeneros
Token ID27498
Feature activation-3.15e-02

Pos logit contributions
 Jenna+0.132
ishment+0.130
lee+0.128
 Rachel+0.118
 Cr+0.115
Neg logit contributions
 much-0.280
br-0.264
 hard-0.262
ier-0.256
lessly-0.252
Token is
Token ID318
Feature activation+4.48e-03

Pos logit contributions
ados+0.069
 Cr+0.069
 Majesty+0.067
ishment+0.067
lee+0.063
Neg logit contributions
 much-0.045
lessly-0.036
 wonderful-0.036
On-0.035
br-0.035
Token in
Token ID287
Feature activation-2.69e-02

Pos logit contributions
 much+0.006
lessly+0.006
In+0.006
On+0.005
br+0.005
Neg logit contributions
 Cr-0.009
 Majesty-0.009
ados-0.009
ishment-0.009
 Fro-0.009
Token there
Token ID612
Feature activation-1.54e-02

Pos logit contributions
ados+0.041
 Cr+0.040
ishment+0.038
 Majesty+0.038
 Fro+0.035
Neg logit contributions
 much-0.055
lessly-0.051
br-0.048
 wonderful-0.048
In-0.048
Token,
Token ID11
Feature activation-3.91e-02

Pos logit contributions
ados+0.027
 Cr+0.027
 Majesty+0.026
ishment+0.026
 Fro+0.024
Neg logit contributions
 much-0.028
lessly-0.025
 wonderful-0.024
br-0.024
On-0.023
Token't
Token ID470
Feature activation-2.27e-02

Pos logit contributions
 much+0.003
lessly+0.002
 wonderful+0.002
On+0.002
br+0.002
Neg logit contributions
 Cr-0.003
ados-0.003
 Fro-0.002
ican-0.002
gy-0.002
Token touch
Token ID3638
Feature activation-4.25e-02

Pos logit contributions
ados+0.039
 Cr+0.038
 Majesty+0.037
ishment+0.037
lee+0.034
Neg logit contributions
 much-0.045
 wonderful-0.038
lessly-0.038
On-0.037
br-0.037
Token the
Token ID262
Feature activation-3.25e-02

Pos logit contributions
 Cr+0.075
 Majesty+0.074
ados+0.074
ishment+0.074
lee+0.068
Neg logit contributions
 much-0.081
 wonderful-0.068
lessly-0.066
br-0.065
 hard-0.064
Token rh
Token ID9529
Feature activation-4.58e-02

Pos logit contributions
ados+0.052
 Cr+0.050
 Majesty+0.049
ishment+0.049
 Fro+0.045
Neg logit contributions
 much-0.067
lessly-0.058
 wonderful-0.057
On-0.057
In-0.056
Tokenin
Token ID259
Feature activation-3.93e-02

Pos logit contributions
ados+0.098
 Cr+0.094
 Majesty+0.090
ishment+0.090
ican+0.086
Neg logit contributions
 much-0.071
 wonderful-0.060
lessly-0.060
On-0.058
In-0.056
Tokenoc
Token ID420
Feature activation-1.26e-01

Pos logit contributions
ados+0.056
 Cr+0.055
 Majesty+0.053
ishment+0.053
lee+0.048
Neg logit contributions
 much-0.088
 wonderful-0.077
lessly-0.077
On-0.075
br-0.075
Tokeneros
Token ID27498
Feature activation-3.75e-02

Pos logit contributions
 Jenna+0.124
ishment+0.117
lee+0.116
 Rachel+0.115
 Cr+0.114
Neg logit contributions
 much-0.286
br-0.268
 hard-0.265
ier-0.262
ching-0.255
Token!
Token ID0
Feature activation-5.01e-02

Pos logit contributions
 Cr+0.074
ados+0.074
ishment+0.072
 Majesty+0.072
lee+0.068
Neg logit contributions
 much-0.063
 wonderful-0.052
lessly-0.051
br-0.050
On-0.049
Token It
Token ID632
Feature activation+9.99e-03

Pos logit contributions
ishment+0.087
ados+0.086
 Majesty+0.082
lee+0.078
ishes+0.077
Neg logit contributions
 much-0.102
On-0.083
In-0.083
lessly-0.082
He-0.081
Token might
Token ID1244
Feature activation-6.28e-03

Pos logit contributions
 much+0.016
lessly+0.013
 wonderful+0.013
On+0.012
br+0.012
Neg logit contributions
ados-0.021
 Cr-0.021
 Majesty-0.020
ishment-0.020
lee-0.019
Token bite
Token ID13197
Feature activation-2.88e-02

Pos logit contributions
 Cr+0.011
ados+0.011
 Majesty+0.010
 Fro+0.010
gy+0.010
Neg logit contributions
 much-0.011
lessly-0.010
On-0.010
 wonderful-0.009
In-0.009
Token.
Token ID13
Feature activation-4.44e-02

Pos logit contributions
ados+0.061
 Cr+0.061
 Majesty+0.059
ishment+0.059
lee+0.055
Neg logit contributions
 much-0.053
 wonderful-0.044
lessly-0.044
On-0.042
br-0.042
Token And
Token ID843
Feature activation-2.71e-02

Pos logit contributions
ados+0.076
ishment+0.073
lee+0.071
 Cr+0.070
 Majesty+0.069
Neg logit contributions
 much-0.089
On-0.074
In-0.074
 wonderful-0.073
br-0.072
Token put
Token ID1234
Feature activation-4.09e-02

Pos logit contributions
 Cr+0.044
ados+0.044
 Majesty+0.044
ishment+0.042
 Fro+0.039
Neg logit contributions
 much-0.053
lessly-0.048
br-0.046
 wonderful-0.045
ching-0.045
Token on
Token ID319
Feature activation-4.94e-02

Pos logit contributions
ados+0.066
 Cr+0.064
 Majesty+0.063
ishment+0.062
lee+0.057
Neg logit contributions
 much-0.084
lessly-0.072
 wonderful-0.072
On-0.071
br-0.070
Token your
Token ID534
Feature activation-8.03e-02

Pos logit contributions
 Cr+0.078
ishment+0.076
ados+0.074
 Majesty+0.072
ican+0.071
Neg logit contributions
 much-0.107
 wonderful-0.094
 hard-0.092
 lot-0.086
lessly-0.086
Token swe
Token ID3490
Feature activation-1.25e-01

Pos logit contributions
 Cr+0.125
ados+0.123
ishment+0.118
 Majesty+0.114
lee+0.107
Neg logit contributions
 much-0.171
 wonderful-0.153
 hard-0.145
br-0.144
lessly-0.144
Tokenaters
Token ID8605
Feature activation-3.36e-02

Pos logit contributions
 Cr+0.195
ican+0.182
 Rib+0.171
ados+0.169
icans+0.167
Neg logit contributions
 much-0.244
 lot-0.208
On-0.207
 wonderful-0.207
In-0.198
Token,
Token ID11
Feature activation-5.42e-02

Pos logit contributions
ados+0.063
 Cr+0.062
 Majesty+0.061
ishment+0.061
lee+0.057
Neg logit contributions
 much-0.059
 wonderful-0.050
lessly-0.050
On-0.048
br-0.048
Token or
Token ID393
Feature activation-6.92e-02

Pos logit contributions
ados+0.100
 Cr+0.100
 Majesty+0.097
ishment+0.097
lee+0.090
Neg logit contributions
 much-0.100
 wonderful-0.084
lessly-0.082
On-0.080
 hard-0.079
Token you
Token ID345
Feature activation-1.30e-02

Pos logit contributions
ados+0.122
 Cr+0.120
 Majesty+0.117
ishment+0.116
lee+0.108
Neg logit contributions
 much-0.130
lessly-0.112
 wonderful-0.111
On-0.108
br-0.107
Token will
Token ID481
Feature activation-4.39e-02

Pos logit contributions
 Cr+0.026
 Majesty+0.026
ados+0.026
gy+0.026
ishment+0.025
Neg logit contributions
 much-0.018
lessly-0.016
 wonderful-0.015
On-0.015
br-0.014
Token Did
Token ID7731
Feature activation-3.83e-02

Pos logit contributions
ishment+0.075
ados+0.072
ans+0.070
icans+0.067
 Majesty+0.067
Neg logit contributions
 much-0.076
In-0.065
br-0.061
lessly-0.060
It-0.059
Token you
Token ID345
Feature activation-3.93e-02

Pos logit contributions
ados+0.059
ishment+0.058
 Cr+0.057
 Majesty+0.057
keeping+0.053
Neg logit contributions
 much-0.082
 wonderful-0.072
 hard-0.068
br-0.067
lessly-0.066
Token know
Token ID760
Feature activation-6.31e-03

Pos logit contributions
ados+0.074
 Cr+0.074
 Majesty+0.072
ishment+0.071
lee+0.067
Neg logit contributions
 much-0.069
 wonderful-0.058
lessly-0.058
On-0.056
br-0.056
Token that
Token ID326
Feature activation-1.18e-02

Pos logit contributions
ados+0.011
 Cr+0.011
 Majesty+0.010
ishment+0.010
lee+0.009
Neg logit contributions
 much-0.011
lessly-0.011
On-0.010
In-0.010
br-0.010
Token av
Token ID1196
Feature activation-7.54e-02

Pos logit contributions
ados+0.020
 Cr+0.020
 Majesty+0.019
ishment+0.019
lee+0.018
Neg logit contributions
 much-0.023
 wonderful-0.020
lessly-0.020
On-0.019
br-0.019
Tokenoc
Token ID420
Feature activation-1.23e-01

Pos logit contributions
ados+0.106
 Cr+0.105
 Majesty+0.101
ishment+0.100
lee+0.091
Neg logit contributions
 much-0.170
 wonderful-0.149
lessly-0.148
On-0.145
br-0.144
Tokenados
Token ID22484
Feature activation+8.05e-05

Pos logit contributions
ishment+0.064
 Fro+0.059
 Cr+0.052
 Rib+0.049
 fro+0.045
Neg logit contributions
 much-0.359
br-0.335
 hard-0.325
lessly-0.322
 wonderful-0.322
Token are
Token ID389
Feature activation+6.97e-03

Pos logit contributions
 much+0.000
lessly+0.000
On+0.000
 wonderful+0.000
In+0.000
Neg logit contributions
ados-0.000
 Cr-0.000
 Majesty-0.000
ishment-0.000
ishes-0.000
Token very
Token ID845
Feature activation-3.02e-03

Pos logit contributions
lessly+0.009
 much+0.009
On+0.008
Over+0.008
ching+0.008
Neg logit contributions
ados-0.015
 Cr-0.015
 Majesty-0.014
ishment-0.013
 Harry-0.013
Token healthy
Token ID5448
Feature activation-6.41e-02

Pos logit contributions
 Cr+0.008
ados+0.008
 Majesty+0.007
ishment+0.007
lee+0.007
Neg logit contributions
 much-0.003
lessly-0.002
br-0.002
On-0.002
ching-0.002
Token for
Token ID329
Feature activation-3.33e-02

Pos logit contributions
ados+0.123
 Cr+0.122
 Majesty+0.119
ishment+0.118
lee+0.111
Neg logit contributions
 much-0.111
 wonderful-0.093
lessly-0.093
On-0.090
br-0.089
Tokens
Token ID82
Feature activation-2.18e-02

Pos logit contributions
 Cr+0.072
ados+0.067
 Fro+0.067
lee+0.065
gy+0.064
Neg logit contributions
 much-0.042
 wonderful-0.038
br-0.036
lessly-0.035
On-0.033
Token wrong
Token ID2642
Feature activation-3.66e-02

Pos logit contributions
ados+0.046
 Cr+0.046
 Majesty+0.045
ishment+0.044
lee+0.042
Neg logit contributions
 much-0.033
lessly-0.028
br-0.027
On-0.027
 wonderful-0.027
Token,
Token ID11
Feature activation-1.87e-02

Pos logit contributions
ados+0.066
 Cr+0.066
 Majesty+0.064
ishment+0.064
lee+0.059
Neg logit contributions
 much-0.066
lessly-0.058
 wonderful-0.056
br-0.055
On-0.054
Token rh
Token ID9529
Feature activation-4.05e-02

Pos logit contributions
 Cr+0.027
ados+0.027
 Majesty+0.026
ishment+0.026
 Fro+0.024
Neg logit contributions
 much-0.039
lessly-0.035
br-0.034
On-0.034
 wonderful-0.034
Tokenin
Token ID259
Feature activation-3.00e-02

Pos logit contributions
ados+0.079
 Cr+0.075
 Majesty+0.073
ican+0.072
 Fro+0.071
Neg logit contributions
 much-0.068
lessly-0.059
On-0.057
 wonderful-0.057
In-0.055
Tokenoc
Token ID420
Feature activation-1.22e-01

Pos logit contributions
 Cr+0.050
 Majesty+0.048
ados+0.048
ishment+0.047
 Fro+0.045
Neg logit contributions
 much-0.057
lessly-0.052
 wonderful-0.049
On-0.048
br-0.048
Tokeneros
Token ID27498
Feature activation-3.01e-02

Pos logit contributions
ishment+0.126
 Jenna+0.106
 Cr+0.104
 Harry+0.098
lee+0.096
Neg logit contributions
 much-0.284
br-0.277
 hard-0.264
ier-0.259
lessly-0.257
Token?
Token ID30
Feature activation-3.40e-02

Pos logit contributions
ados+0.051
 Cr+0.051
 Majesty+0.049
ishment+0.048
lee+0.045
Neg logit contributions
 much-0.058
lessly-0.051
 wonderful-0.050
On-0.049
br-0.048
Tokenâ
Token ID22940
Feature activation-6.43e-02

Pos logit contributions
ados+0.055
ishment+0.053
 Majesty+0.053
 Cr+0.051
lee+0.049
Neg logit contributions
 much-0.070
lessly-0.059
On-0.059
 wonderful-0.059
In-0.058
Token€
Token ID26391
Feature activation-6.00e-02

Pos logit contributions
ados+0.092
 Cr+0.089
 Majesty+0.087
ishment+0.085
 Fro+0.078
Neg logit contributions
 much-0.142
lessly-0.126
 wonderful-0.125
In-0.122
On-0.122
Token said
Token ID531
Feature activation-2.16e-03

Pos logit contributions
ados+0.129
ishment+0.126
 Cr+0.125
 Majesty+0.120
lee+0.114
Neg logit contributions
 much-0.096
On-0.075
In-0.075
 wonderful-0.075
br-0.074
Token that
Token ID326
Feature activation-1.07e-02

Pos logit contributions
ados+0.126
 Cr+0.124
 Majesty+0.122
ishment+0.121
lee+0.114
Neg logit contributions
 much-0.092
 wonderful-0.075
lessly-0.075
On-0.071
br-0.071
Token the
Token ID262
Feature activation-9.06e-03

Pos logit contributions
 Cr+0.019
ados+0.019
 Majesty+0.018
ishment+0.018
lee+0.017
Neg logit contributions
 much-0.019
lessly-0.017
br-0.016
On-0.016
 wonderful-0.016
Token bad
Token ID2089
Feature activation-4.25e-02

Pos logit contributions
ados+0.016
 Cr+0.016
 Majesty+0.016
ishment+0.016
lee+0.015
Neg logit contributions
 much-0.016
lessly-0.014
On-0.014
br-0.014
In-0.014
Token rh
Token ID9529
Feature activation-3.92e-02

Pos logit contributions
ados+0.084
 Cr+0.083
ishment+0.081
 Majesty+0.080
lee+0.075
Neg logit contributions
 much-0.073
 wonderful-0.062
lessly-0.059
 hard-0.058
br-0.057
Tokenin
Token ID259
Feature activation-2.86e-02

Pos logit contributions
ados+0.082
 Cr+0.081
 Majesty+0.077
ishment+0.075
ican+0.073
Neg logit contributions
 much-0.059
 wonderful-0.051
On-0.050
lessly-0.049
In-0.048
Tokenoc
Token ID420
Feature activation-1.22e-01

Pos logit contributions
 Cr+0.041
ados+0.040
 Majesty+0.039
ishment+0.038
gy+0.036
Neg logit contributions
 much-0.062
lessly-0.055
 wonderful-0.055
On-0.054
br-0.053
Tokeneros
Token ID27498
Feature activation-2.06e-02

Pos logit contributions
ishment+0.109
 Cr+0.102
lee+0.099
 Fro+0.098
 Jenna+0.096
Neg logit contributions
 much-0.301
lessly-0.276
br-0.273
 hard-0.270
ier-0.269
Token was
Token ID373
Feature activation+1.01e-02

Pos logit contributions
ados+0.049
 Cr+0.049
 Majesty+0.048
ishment+0.048
lee+0.046
Neg logit contributions
 much-0.025
lessly-0.020
 wonderful-0.019
On-0.019
br-0.019
Token now
Token ID783
Feature activation-1.90e-02

Pos logit contributions
 much+0.014
br+0.013
On+0.013
lessly+0.013
In+0.012
Neg logit contributions
 Cr-0.021
 Majesty-0.020
ados-0.019
lee-0.019
ishment-0.019
Token nice
Token ID3621
Feature activation-3.78e-02

Pos logit contributions
ados+0.037
 Cr+0.037
 Majesty+0.036
ishment+0.035
lee+0.034
Neg logit contributions
 much-0.027
br-0.026
On-0.025
In-0.025
lessly-0.025
Token.
Token ID13
Feature activation-3.54e-02

Pos logit contributions
ados+0.073
 Cr+0.071
 Majesty+0.069
ishment+0.069
lee+0.065
Neg logit contributions
 much-0.065
lessly-0.055
 wonderful-0.055
On-0.054
br-0.053
Token to
Token ID284
Feature activation-5.29e-02

Pos logit contributions
ados+0.064
 Cr+0.063
ishment+0.062
 Majesty+0.062
lee+0.057
Neg logit contributions
 much-0.059
 wonderful-0.049
lessly-0.049
On-0.048
br-0.047
Token see
Token ID766
Feature activation-1.92e-02

Pos logit contributions
ados+0.135
 Majesty+0.124
ishment+0.122
amb+0.118
 Cr+0.116
Neg logit contributions
 much-0.077
 wonderful-0.068
On-0.064
 big-0.060
 hard-0.059
Token the
Token ID262
Feature activation-1.13e-02

Pos logit contributions
 Cr+0.037
ados+0.036
ishment+0.035
 Majesty+0.035
 Fro+0.033
Neg logit contributions
 much-0.031
lessly-0.029
br-0.028
In-0.027
On-0.027
Token rh
Token ID9529
Feature activation-3.77e-02

Pos logit contributions
ados+0.020
 Cr+0.020
 Majesty+0.020
ishment+0.019
icans+0.019
Neg logit contributions
 much-0.020
lessly-0.018
br-0.017
In-0.017
On-0.017
Tokenin
Token ID259
Feature activation-2.60e-02

Pos logit contributions
ados+0.075
 Cr+0.072
ishment+0.070
 Majesty+0.069
icans+0.068
Neg logit contributions
 much-0.061
lessly-0.053
 wonderful-0.053
On-0.049
br-0.048
Tokenoc
Token ID420
Feature activation-1.21e-01

Pos logit contributions
 Cr+0.028
ados+0.027
ishment+0.025
 Majesty+0.024
gy+0.024
Neg logit contributions
 much-0.065
lessly-0.062
 wonderful-0.059
br-0.058
In-0.058
Tokeneros
Token ID27498
Feature activation-3.42e-02

Pos logit contributions
 Jenna+0.134
 Rachel+0.123
lee+0.119
 Po+0.118
ishment+0.117
Neg logit contributions
 much-0.265
br-0.245
 hard-0.244
ier-0.237
 security-0.234
Token.
Token ID13
Feature activation-3.59e-02

Pos logit contributions
ados+0.073
 Cr+0.073
 Majesty+0.071
ishment+0.071
lee+0.067
Neg logit contributions
 much-0.052
 wonderful-0.042
lessly-0.042
br-0.040
On-0.040
Token Tim
Token ID5045
Feature activation-3.63e-02

Pos logit contributions
 Majesty+0.063
ados+0.062
ishment+0.057
ishes+0.054
ans+0.053
Neg logit contributions
 much-0.075
On-0.067
In-0.064
 lot-0.059
 wonderful-0.059
Tokenmy
Token ID1820
Feature activation-2.67e-02

Pos logit contributions
ados+0.073
 Cr+0.072
 Majesty+0.070
ishment+0.069
lee+0.064
Neg logit contributions
 much-0.061
 wonderful-0.051
On-0.050
lessly-0.050
In-0.049
Token was
Token ID373
Feature activation+1.78e-02

Pos logit contributions
ados+0.061
 Cr+0.059
 Majesty+0.058
ishment+0.058
lee+0.054
Neg logit contributions
 much-0.038
 wonderful-0.031
On-0.030
lessly-0.029
In-0.029
Token come
Token ID1282
Feature activation-9.57e-02

Pos logit contributions
 much+0.094
lessly+0.090
br+0.090
ching+0.088
In+0.087
Neg logit contributions
ados-0.057
 Cr-0.055
ishment-0.052
 Majesty-0.051
 Harry-0.049
Token in
Token ID287
Feature activation-6.92e-02

Pos logit contributions
ados+0.225
ishment+0.210
 Cr+0.203
 Majesty+0.203
roc+0.194
Neg logit contributions
 much-0.146
 wonderful-0.116
 on-0.110
On-0.106
 hard-0.105
Token,"
Token ID553
Feature activation-6.51e-02

Pos logit contributions
ados+0.143
 Cr+0.142
 Majesty+0.138
ishment+0.138
lee+0.130
Neg logit contributions
 much-0.113
 wonderful-0.093
lessly-0.090
On-0.089
br-0.086
Token said
Token ID531
Feature activation-3.97e-02

Pos logit contributions
ados+0.121
 Majesty+0.121
ishment+0.120
 Cr+0.111
ans+0.110
Neg logit contributions
 much-0.125
 wonderful-0.102
On-0.099
 hard-0.099
In-0.097
Token his
Token ID465
Feature activation-5.49e-02

Pos logit contributions
ishment+0.070
ados+0.070
 Majesty+0.068
 Cr+0.065
ans+0.064
Neg logit contributions
 much-0.080
 wonderful-0.066
 hard-0.064
lessly-0.064
br-0.061
Token grand
Token ID4490
Feature activation-1.21e-01

Pos logit contributions
ados+0.081
 Cr+0.080
ishment+0.077
 Majesty+0.076
lee+0.070
Neg logit contributions
 much-0.121
 wonderful-0.106
lessly-0.104
On-0.102
br-0.101
Tokenpa
Token ID8957
Feature activation-4.18e-02

Pos logit contributions
 Cr+0.167
ados+0.150
 Rib+0.146
 Fro+0.142
ican+0.130
Neg logit contributions
 much-0.283
 wonderful-0.261
 hard-0.254
 bad-0.237
lessly-0.237
Token.
Token ID13
Feature activation-3.79e-02

Pos logit contributions
ados+0.085
 Cr+0.084
 Majesty+0.082
ishment+0.082
lee+0.076
Neg logit contributions
 much-0.068
 wonderful-0.056
lessly-0.056
On-0.054
br-0.054
Token They
Token ID1119
Feature activation-5.92e-03

Pos logit contributions
ados+0.088
ishment+0.085
 Majesty+0.085
 Cr+0.084
ishes+0.080
Neg logit contributions
 much-0.053
On-0.042
lessly-0.041
In-0.040
 wonderful-0.040
Token all
Token ID477
Feature activation+4.89e-03

Pos logit contributions
 Cr+0.011
ados+0.011
ishment+0.010
 Majesty+0.010
lee+0.010
Neg logit contributions
 much-0.010
br-0.009
lessly-0.009
 wonderful-0.009
ching-0.008
Token turned
Token ID2900
Feature activation-6.19e-03

Pos logit contributions
 much+0.008
br+0.007
 wonderful+0.007
lessly+0.007
On+0.007
Neg logit contributions
 Cr-0.009
ados-0.009
lee-0.009
ishment-0.009
 Majesty-0.008
Token Unicorn
Token ID39481
Feature activation-3.25e-02

Pos logit contributions
ados+0.045
ishment+0.042
 Cr+0.041
 Majesty+0.040
gy+0.038
Neg logit contributions
 much-0.078
 wonderful-0.070
lessly-0.066
 hard-0.065
On-0.064
Token!"
Token ID2474
Feature activation-3.69e-02

Pos logit contributions
ishment+0.070
ados+0.070
 Cr+0.070
 Majesty+0.066
icans+0.065
Neg logit contributions
 much-0.051
br-0.041
 wonderful-0.041
lessly-0.040
 hard-0.038
Token The
Token ID383
Feature activation-1.19e-02

Pos logit contributions
ados+0.078
 Majesty+0.078
ishment+0.076
ieties+0.072
ishes+0.072
Neg logit contributions
 much-0.061
On-0.047
 wonderful-0.046
lessly-0.045
In-0.044
Token rh
Token ID9529
Feature activation-3.68e-02

Pos logit contributions
ados+0.020
 Cr+0.019
ishment+0.019
 Majesty+0.019
lee+0.017
Neg logit contributions
 much-0.024
 wonderful-0.021
lessly-0.020
br-0.020
On-0.020
Tokenin
Token ID259
Feature activation-3.17e-02

Pos logit contributions
ados+0.077
 Cr+0.077
 Majesty+0.074
ishment+0.073
 Rib+0.070
Neg logit contributions
 much-0.056
lessly-0.047
 wonderful-0.047
On-0.045
In-0.043
Tokenoc
Token ID420
Feature activation-1.21e-01

Pos logit contributions
ados+0.051
 Cr+0.049
ishment+0.048
 Majesty+0.047
lee+0.044
Neg logit contributions
 much-0.066
 wonderful-0.057
lessly-0.056
On-0.056
br-0.056
Tokeneros
Token ID27498
Feature activation-2.63e-02

Pos logit contributions
 Jenna+0.152
ishment+0.141
 Rachel+0.140
 Harry+0.137
lee+0.131
Neg logit contributions
 much-0.236
ier-0.231
br-0.228
 hard-0.226
 security-0.218
Token said
Token ID531
Feature activation-7.70e-03

Pos logit contributions
ados+0.058
 Cr+0.056
ishment+0.056
 Majesty+0.055
keeping+0.052
Neg logit contributions
 much-0.040
 wonderful-0.032
lessly-0.031
On-0.031
 hard-0.030
Token,
Token ID11
Feature activation-4.95e-03

Pos logit contributions
ishment+0.018
ados+0.018
 Majesty+0.018
 Cr+0.017
icans+0.017
Neg logit contributions
 much-0.011
lessly-0.008
 wonderful-0.008
 hard-0.008
br-0.008
Token feeling
Token ID4203
Feature activation+3.82e-02

Pos logit contributions
ados+0.010
ishment+0.010
 Cr+0.010
 Majesty+0.010
ishes+0.009
Neg logit contributions
 much-0.008
On-0.007
lessly-0.007
 hard-0.006
 wonderful-0.006
Token much
Token ID881
Feature activation+2.18e-02

Pos logit contributions
On+0.043
 much+0.042
br+0.042
In+0.042
lessly+0.041
Neg logit contributions
 Cr-0.085
ados-0.080
 Majesty-0.080
 Fro-0.078
lee-0.077
Token there
Token ID612
Feature activation-9.90e-03

Pos logit contributions
 Cr+0.025
ados+0.024
 Majesty+0.023
ishment+0.023
 Fro+0.022
Neg logit contributions
 much-0.024
 wonderful-0.021
lessly-0.020
br-0.020
In-0.020
Token was
Token ID373
Feature activation-1.51e-02

Pos logit contributions
ados+0.025
 Cr+0.024
 Majesty+0.024
ishment+0.024
lee+0.023
Neg logit contributions
 much-0.012
 wonderful-0.009
lessly-0.009
On-0.008
In-0.008
Token a
Token ID257
Feature activation+1.44e-03

Pos logit contributions
 Cr+0.032
ados+0.031
 Majesty+0.031
ishment+0.030
 Fro+0.029
Neg logit contributions
 much-0.022
lessly-0.019
br-0.018
 wonderful-0.018
On-0.017
Token rh
Token ID9529
Feature activation-4.39e-02

Pos logit contributions
 much+0.002
lessly+0.002
br+0.002
In+0.002
On+0.002
Neg logit contributions
 Majesty-0.003
 Cr-0.003
ados-0.003
ishment-0.003
 Fro-0.003
Tokenin
Token ID259
Feature activation-3.82e-02

Pos logit contributions
ados+0.091
 Cr+0.088
ishment+0.084
 Majesty+0.083
ican+0.082
Neg logit contributions
 much-0.068
 wonderful-0.059
lessly-0.057
On-0.055
In-0.054
Tokenoc
Token ID420
Feature activation-1.21e-01

Pos logit contributions
 Cr+0.048
ados+0.048
 Majesty+0.046
ishment+0.045
gy+0.041
Neg logit contributions
 much-0.090
lessly-0.081
 wonderful-0.080
On-0.078
br-0.078
Tokeneros
Token ID27498
Feature activation-3.66e-02

Pos logit contributions
ishment+0.119
 Jenna+0.114
 Cr+0.111
lee+0.109
 Po+0.106
Neg logit contributions
 much-0.277
br-0.261
ier-0.257
 hard-0.252
lessly-0.251
Token who
Token ID508
Feature activation-1.06e-02

Pos logit contributions
ados+0.076
 Cr+0.075
 Majesty+0.073
ishment+0.073
lee+0.069
Neg logit contributions
 much-0.058
 wonderful-0.048
lessly-0.048
On-0.046
br-0.046
Token was
Token ID373
Feature activation+7.55e-03

Pos logit contributions
 Cr+0.023
ados+0.022
gy+0.022
 Majesty+0.022
ishment+0.021
Neg logit contributions
 much-0.015
lessly-0.013
br-0.012
 wonderful-0.012
On-0.012
Token always
Token ID1464
Feature activation-3.35e-03

Pos logit contributions
 much+0.007
lessly+0.007
br+0.006
 wonderful+0.006
On+0.006
Neg logit contributions
 Cr-0.019
ados-0.019
 Majesty-0.019
ishment-0.018
gy-0.018
Token naughty
Token ID45128
Feature activation-4.30e-02

Pos logit contributions
 Cr+0.006
ados+0.006
ishment+0.006
 Majesty+0.006
gy+0.006
Neg logit contributions
 much-0.005
br-0.005
lessly-0.005
In-0.005
On-0.005
Token going
Token ID1016
Feature activation-1.40e-02

Pos logit contributions
 much+0.043
lessly+0.038
On+0.037
 wonderful+0.036
br+0.036
Neg logit contributions
 Cr-0.041
ados-0.040
 Majesty-0.039
ishment-0.038
gy-0.036
Token on
Token ID319
Feature activation-2.03e-03

Pos logit contributions
 Cr+0.026
ados+0.026
 Majesty+0.025
ishment+0.025
gy+0.023
Neg logit contributions
 much-0.025
lessly-0.021
 wonderful-0.021
br-0.020
On-0.020
Token a
Token ID257
Feature activation+1.67e-03

Pos logit contributions
ados+0.005
 Cr+0.004
 Majesty+0.004
ishment+0.004
lee+0.004
Neg logit contributions
 much-0.003
 wonderful-0.002
On-0.002
lessly-0.002
 hard-0.002
Token trip
Token ID5296
Feature activation+1.54e-02

Pos logit contributions
 much+0.003
lessly+0.002
 wonderful+0.002
In+0.002
On+0.002
Neg logit contributions
 Cr-0.003
 Majesty-0.003
ados-0.003
ishment-0.003
gy-0.003
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
 much+0.026
 wonderful+0.024
lessly+0.023
br+0.023
In+0.022
Neg logit contributions
 Cr-0.027
ados-0.027
ishment-0.026
gy-0.026
keeping-0.025
Token
Token ID198
Feature activation+4.84e-02

Pos logit contributions
ados+0.025
 Majesty+0.024
 Cr+0.024
ishment+0.024
lee+0.023
Neg logit contributions
 much-0.013
On-0.010
 wonderful-0.010
In-0.010
lessly-0.009
Token
Token ID198
Feature activation+4.23e-02

Pos logit contributions
lessly+0.084
 much+0.082
 wonderful+0.079
br+0.078
 terrible+0.076
Neg logit contributions
 Cr-0.073
 Fro-0.072
 Rib-0.070
 Av-0.065
 Harry-0.064
Token"
Token ID1
Feature activation+1.38e-02

Pos logit contributions
 much+0.048
lessly+0.045
 wonderful+0.042
 terrible+0.039
br+0.038
Neg logit contributions
 Cr-0.090
ishment-0.087
 Rib-0.086
ados-0.086
 Majesty-0.084
TokenLet
Token ID5756
Feature activation-4.39e-03

Pos logit contributions
 much+0.027
lessly+0.024
 wonderful+0.024
 hard+0.023
 bad+0.023
Neg logit contributions
 Cr-0.023
 Rib-0.021
ASH-0.021
ados-0.021
ishment-0.020
Token's
Token ID338
Feature activation-4.31e-02

Pos logit contributions
ados+0.010
ishment+0.010
 Cr+0.010
 Majesty+0.010
keeping+0.009
Neg logit contributions
 much-0.007
 wonderful-0.006
 bad-0.006
 hard-0.005
 big-0.005
Token load
Token ID3440
Feature activation-1.52e-02

Pos logit contributions
ados+0.085
 Cr+0.082
ishment+0.080
 Majesty+0.079
lee+0.076
Neg logit contributions
 much-0.076
 wonderful-0.064
On-0.062
In-0.060
br-0.060
Token needed
Token ID2622
Feature activation+3.59e-02

Pos logit contributions
ados+0.015
 Cr+0.015
ishment+0.015
 Majesty+0.015
icans+0.014
Neg logit contributions
 much-0.011
 wonderful-0.009
lessly-0.009
On-0.008
 hard-0.008
Token it
Token ID340
Feature activation+3.28e-02

Pos logit contributions
 much+0.064
lessly+0.058
 wonderful+0.056
On+0.055
br+0.055
Neg logit contributions
ados-0.064
 Cr-0.064
 Majesty-0.060
ishment-0.059
 Fro-0.057
Token very
Token ID845
Feature activation+2.48e-02

Pos logit contributions
 much+0.056
br+0.052
lessly+0.051
On+0.050
 wonderful+0.049
Neg logit contributions
ados-0.056
 Cr-0.055
 Majesty-0.053
ishment-0.052
gy-0.052
Token much
Token ID881
Feature activation+2.93e-02

Pos logit contributions
 much+0.019
br+0.016
lessly+0.016
On+0.015
In+0.014
Neg logit contributions
 Cr-0.066
 Majesty-0.065
ados-0.065
ishment-0.064
lee-0.062
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
In+0.048
 much+0.047
lessly+0.046
On+0.046
Over+0.045
Neg logit contributions
ados-0.051
ishment-0.050
 Cr-0.049
 Majesty-0.047
keeping-0.044
Token After
Token ID2293
Feature activation+3.86e-02

Pos logit contributions
 Majesty+0.024
ishment+0.023
ans+0.022
icans+0.022
ican+0.022
Neg logit contributions
 much-0.023
In-0.019
On-0.018
It-0.018
lessly-0.018
Token that
Token ID326
Feature activation+2.39e-02

Pos logit contributions
 much+0.060
lessly+0.052
 wonderful+0.051
br+0.050
On+0.049
Neg logit contributions
 Cr-0.080
ados-0.080
 Majesty-0.075
ishment-0.075
lee-0.072
Token,
Token ID11
Feature activation+2.95e-02

Pos logit contributions
 much+0.045
lessly+0.039
 wonderful+0.039
On+0.038
In+0.038
Neg logit contributions
 Cr-0.042
ados-0.042
ishment-0.040
 Majesty-0.039
 Fro-0.037
Token the
Token ID262
Feature activation+3.68e-02

Pos logit contributions
 much+0.052
 wonderful+0.042
 hard+0.041
On+0.039
 lot+0.039
Neg logit contributions
 Majesty-0.061
ishment-0.060
ados-0.060
 Cr-0.058
ans-0.058
Token bunny
Token ID44915
Feature activation+4.53e-03

Pos logit contributions
 much+0.070
lessly+0.062
br+0.058
On+0.058
In+0.057
Neg logit contributions
 Cr-0.062
 Majesty-0.062
ados-0.062
ishment-0.061
 Fro-0.057
Token sat
Token ID3332
Feature activation-1.24e-03

Pos logit contributions
 much+0.006
 wonderful+0.005
On+0.004
In+0.004
 hard+0.004
Neg logit contributions
ados-0.011
 Cr-0.011
ishment-0.011
 Majesty-0.010
icans-0.010
Token of
Token ID286
Feature activation-2.90e-02

Pos logit contributions
 much+0.023
 wonderful+0.020
On+0.020
lessly+0.020
In+0.019
Neg logit contributions
ados-0.037
 Cr-0.036
ishment-0.035
 Majesty-0.034
lee-0.034
Token the
Token ID262
Feature activation+3.58e-03

Pos logit contributions
 Cr+0.049
ados+0.049
 Majesty+0.049
ishment+0.048
lee+0.045
Neg logit contributions
 much-0.057
 wonderful-0.049
lessly-0.046
 hard-0.046
On-0.046
Token window
Token ID4324
Feature activation+1.65e-02

Pos logit contributions
 much+0.007
lessly+0.006
 wonderful+0.006
On+0.006
br+0.006
Neg logit contributions
ados-0.006
 Cr-0.006
 Majesty-0.006
ishment-0.006
lee-0.005
Token?"
Token ID1701
Feature activation-1.85e-02

Pos logit contributions
 much+0.029
 wonderful+0.024
lessly+0.024
br+0.023
On+0.023
Neg logit contributions
ados-0.031
 Cr-0.031
ishment-0.030
 Majesty-0.030
lee-0.028
Token
Token ID198
Feature activation+3.88e-02

Pos logit contributions
ados+0.043
 Cr+0.043
ishment+0.042
 Majesty+0.042
gy+0.040
Neg logit contributions
 much-0.025
 wonderful-0.020
lessly-0.019
On-0.019
In-0.018
Token
Token ID198
Feature activation+3.63e-02

Pos logit contributions
 much+0.053
 wonderful+0.043
lessly+0.043
br+0.041
On+0.041
Neg logit contributions
ados-0.088
 Cr-0.087
 Majesty-0.085
ishment-0.085
lee-0.081
Token"
Token ID1
Feature activation+3.40e-02

Pos logit contributions
 much+0.047
 wonderful+0.036
On+0.036
lessly+0.035
In+0.035
Neg logit contributions
ados-0.088
 Cr-0.086
ishment-0.086
 Majesty-0.085
lee-0.080
TokenWe
Token ID1135
Feature activation+1.00e-02

Pos logit contributions
 much+0.048
 wonderful+0.038
lessly+0.038
 hard+0.035
br+0.034
Neg logit contributions
 Cr-0.078
ados-0.073
 Rib-0.071
ican-0.071
icans-0.070
Token had
Token ID550
Feature activation+1.55e-02

Pos logit contributions
 much+0.016
lessly+0.013
br+0.013
 wonderful+0.013
On+0.013
Neg logit contributions
 Cr-0.020
ados-0.020
 Majesty-0.020
ishment-0.020
lee-0.019
Token a
Token ID257
Feature activation+3.67e-02

Pos logit contributions
 much+0.023
 wonderful+0.019
 hard+0.017
br+0.017
lessly+0.017
Neg logit contributions
ados-0.035
 Cr-0.034
ishment-0.034
 Majesty-0.034
gy-0.032
Token plan
Token ID1410
Feature activation+3.02e-02

Pos logit contributions
lessly+0.052
 much+0.051
In+0.044
On+0.044
br+0.042
Neg logit contributions
 Majesty-0.077
 Cr-0.076
ados-0.072
 Fro-0.071
gy-0.071
Token why
Token ID1521
Feature activation+4.26e-02

Pos logit contributions
 much+0.015
br+0.013
lessly+0.013
 wonderful+0.013
On+0.013
Neg logit contributions
ados-0.016
 Cr-0.016
 Majesty-0.015
ishment-0.015
lee-0.014
Token his
Token ID465
Feature activation+2.53e-03

Pos logit contributions
 much+0.075
 wonderful+0.063
lessly+0.063
On+0.061
br+0.060
Neg logit contributions
ados-0.081
 Cr-0.080
 Majesty-0.078
ishment-0.078
lee-0.073
Token friend
Token ID1545
Feature activation+7.08e-03

Pos logit contributions
 much+0.005
 wonderful+0.004
 hard+0.004
 lot+0.004
 bad+0.004
Neg logit contributions
ados-0.005
 Cr-0.005
ishment-0.004
 Majesty-0.004
icans-0.004
Token the
Token ID262
Feature activation+3.14e-02

Pos logit contributions
 much+0.009
lessly+0.008
 wonderful+0.007
On+0.007
br+0.007
Neg logit contributions
ados-0.016
 Cr-0.016
 Majesty-0.016
ishment-0.016
lee-0.015
Token frog
Token ID21264
Feature activation+1.57e-02

Pos logit contributions
 much+0.066
 wonderful+0.058
lessly+0.056
br+0.055
On+0.055
Neg logit contributions
ados-0.050
 Cr-0.049
ishment-0.048
 Majesty-0.047
lee-0.044
Token was
Token ID373
Feature activation+3.47e-02

Pos logit contributions
 much+0.020
lessly+0.015
 wonderful+0.015
On+0.015
br+0.015
Neg logit contributions
ados-0.037
 Cr-0.037
 Majesty-0.036
ishment-0.036
lee-0.034
Token so
Token ID523
Feature activation+3.47e-02

Pos logit contributions
 much+0.055
lessly+0.048
br+0.047
On+0.047
In+0.046
Neg logit contributions
 Cr-0.068
ados-0.067
 Majesty-0.066
ishment-0.065
lee-0.063
Token encouraging
Token ID12577
Feature activation-1.01e-02

Pos logit contributions
 much+0.043
br+0.040
On+0.038
lessly+0.038
In+0.037
Neg logit contributions
 Cr-0.079
 Majesty-0.074
ados-0.073
lee-0.073
ishment-0.072
Token.
Token ID13
Feature activation-3.05e-03

Pos logit contributions
 Majesty+0.013
ados+0.013
 Cr+0.013
ishment+0.013
gy+0.011
Neg logit contributions
 much-0.024
 wonderful-0.021
lessly-0.021
 hard-0.021
On-0.020
Token Joe
Token ID5689
Feature activation+8.12e-03

Pos logit contributions
ados+0.006
ishment+0.006
 Majesty+0.006
 Cr+0.006
icans+0.005
Neg logit contributions
 much-0.005
lessly-0.004
On-0.004
 wonderful-0.004
In-0.004
Token had
Token ID550
Feature activation+2.70e-02

Pos logit contributions
 much+0.011
 wonderful+0.009
lessly+0.009
On+0.008
In+0.008
Neg logit contributions
ados-0.019
 Cr-0.018
ishment-0.018
 Majesty-0.018
icans-0.017
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
br+0.019
 much+0.018
In+0.018
 wonderful+0.018
arest+0.018
Neg logit contributions
 Cr-0.017
ishment-0.017
ados-0.017
lee-0.016
gy-0.016
Token They
Token ID1119
Feature activation+6.31e-03

Pos logit contributions
ados+0.032
 Cr+0.031
 Majesty+0.031
ishment+0.030
lee+0.028
Neg logit contributions
 much-0.050
 wonderful-0.043
lessly-0.043
On-0.042
In-0.042
Token knew
Token ID2993
Feature activation+2.87e-02

Pos logit contributions
br+0.012
 much+0.011
lessly+0.010
arest+0.010
ching+0.010
Neg logit contributions
 Cr-0.010
lee-0.010
ishment-0.010
gy-0.009
 Fro-0.009
Token that
Token ID326
Feature activation+2.33e-02

Pos logit contributions
 much+0.055
br+0.052
lessly+0.051
On+0.050
In+0.049
Neg logit contributions
 Cr-0.048
ados-0.045
 Fro-0.042
ishment-0.041
 Rib-0.041
Token Max
Token ID5436
Feature activation+8.12e-03

Pos logit contributions
 much+0.046
 wonderful+0.039
lessly+0.039
On+0.038
br+0.038
Neg logit contributions
ados-0.040
 Cr-0.039
 Majesty-0.038
ishment-0.038
lee-0.035
Token was
Token ID373
Feature activation+3.69e-02

Pos logit contributions
 much+0.010
lessly+0.009
br+0.008
On+0.008
 wonderful+0.008
Neg logit contributions
 Cr-0.019
ados-0.019
ishment-0.018
gy-0.018
 Majesty-0.018
Token still
Token ID991
Feature activation+1.59e-02

Pos logit contributions
 much+0.045
lessly+0.040
br+0.039
On+0.039
In+0.036
Neg logit contributions
 Cr-0.088
ados-0.085
ishment-0.081
 Majesty-0.080
 Fro-0.080
Token very
Token ID845
Feature activation+2.22e-02

Pos logit contributions
 much+0.025
 wonderful+0.020
lessly+0.020
On+0.019
br+0.019
Neg logit contributions
ados-0.034
 Cr-0.033
 Majesty-0.033
ishment-0.033
lee-0.031
Token little
Token ID1310
Feature activation-1.37e-02

Pos logit contributions
 much+0.021
br+0.020
On+0.020
In+0.019
lessly+0.019
Neg logit contributions
 Cr-0.054
ados-0.052
 Majesty-0.051
ishment-0.051
lee-0.050
Token,
Token ID11
Feature activation-2.97e-03

Pos logit contributions
ados+0.026
 Cr+0.026
 Majesty+0.025
ishment+0.025
lee+0.023
Neg logit contributions
 much-0.024
 wonderful-0.020
lessly-0.020
On-0.019
br-0.019
Token and
Token ID290
Feature activation-6.12e-03

Pos logit contributions
ados+0.006
 Cr+0.006
 Majesty+0.006
ishment+0.006
lee+0.006
Neg logit contributions
 much-0.005
 wonderful-0.004
lessly-0.004
On-0.004
br-0.003
Token very
Token ID845
Feature activation+4.76e-02

Pos logit contributions
 much+0.048
br+0.044
lessly+0.043
On+0.041
In+0.040
Neg logit contributions
 Cr-0.109
ados-0.108
 Majesty-0.106
ishment-0.103
lee-0.103
Token happy
Token ID3772
Feature activation-2.03e-02

Pos logit contributions
 much+0.059
br+0.055
lessly+0.054
On+0.053
ching+0.052
Neg logit contributions
 Cr-0.103
 Majesty-0.101
ados-0.101
ishment-0.097
lee-0.097
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
 Cr+0.047
ados+0.046
 Majesty+0.046
ishment+0.046
lee+0.043
Neg logit contributions
 much-0.028
 wonderful-0.022
lessly-0.021
On-0.021
 hard-0.021
Token She
Token ID1375
Feature activation+8.65e-03

Pos logit contributions
ados+0.028
 Cr+0.028
ishment+0.027
 Majesty+0.027
lee+0.025
Neg logit contributions
 much-0.025
 wonderful-0.020
lessly-0.020
On-0.020
br-0.020
Token said
Token ID531
Feature activation+2.18e-02

Pos logit contributions
 much+0.014
 wonderful+0.012
lessly+0.012
On+0.011
br+0.011
Neg logit contributions
ados-0.018
 Cr-0.017
ishment-0.017
 Majesty-0.017
 Fro-0.016
Token,
Token ID11
Feature activation+6.86e-03

Pos logit contributions
 much+0.036
 hard+0.028
br+0.027
 wonderful+0.027
 bad+0.025
Neg logit contributions
ishment-0.054
gy-0.050
keeping-0.049
ans-0.049
ci-0.048
Token "
Token ID366
Feature activation-5.76e-03

Pos logit contributions
 much+0.011
lessly+0.009
 wonderful+0.009
On+0.009
br+0.009
Neg logit contributions
ados-0.014
ishment-0.014
 Majesty-0.014
 Cr-0.014
gy-0.013
TokenLook
Token ID8567
Feature activation-1.86e-02

Pos logit contributions
ados+0.012
 Cr+0.012
 Majesty+0.012
ishment+0.012
lee+0.011
Neg logit contributions
 much-0.009
lessly-0.007
 wonderful-0.007
br-0.007
On-0.007
Token,
Token ID11
Feature activation-2.14e-03

Pos logit contributions
keeping+0.041
 Cr+0.041
ishment+0.040
ados+0.039
 Majesty+0.039
Neg logit contributions
 much-0.028
 wonderful-0.024
 hard-0.021
 else-0.020
br-0.020
Token Spot
Token ID15899
Feature activation-1.88e-02

Pos logit contributions
ados+0.003
ishment+0.003
 Cr+0.003
 Majesty+0.003
lee+0.003
Neg logit contributions
 much-0.005
 wonderful-0.004
br-0.004
lessly-0.004
On-0.004
Token,
Token ID11
Feature activation+1.28e-02

Pos logit contributions
 Cr+0.043
ados+0.043
ishment+0.043
 Majesty+0.042
lee+0.041
Neg logit contributions
 much-0.026
 wonderful-0.021
 hard-0.020
br-0.020
ching-0.018
Token cloud
Token ID6279
Feature activation+3.79e-02

Pos logit contributions
lessly+0.057
 much+0.056
In+0.052
On+0.051
br+0.047
Neg logit contributions
 Majesty-0.075
 Cr-0.071
gy-0.069
ados-0.069
 Fro-0.068
Token,
Token ID11
Feature activation+1.06e-02

Pos logit contributions
 much+0.067
 wonderful+0.056
lessly+0.056
On+0.055
br+0.054
Neg logit contributions
ados-0.071
 Cr-0.071
 Majesty-0.068
ishment-0.068
lee-0.064
Token Lily
Token ID20037
Feature activation-9.59e-04

Pos logit contributions
 much+0.024
 wonderful+0.021
lessly+0.021
On+0.021
br+0.021
Neg logit contributions
ados-0.015
 Cr-0.014
 Majesty-0.014
ishment-0.014
lee-0.013
Token.
Token ID13
Feature activation-9.45e-03

Pos logit contributions
 Cr+0.002
ados+0.002
ishment+0.002
 Majesty+0.002
icans+0.002
Neg logit contributions
 much-0.001
 wonderful-0.001
lessly-0.001
 hard-0.001
br-0.001
Token It
Token ID632
Feature activation+3.81e-02

Pos logit contributions
ados+0.018
keeping+0.017
ans+0.016
ishment+0.016
 Majesty+0.016
Neg logit contributions
 much-0.017
In-0.014
lessly-0.014
It-0.014
 wonderful-0.013
Token's
Token ID338
Feature activation+2.45e-02

Pos logit contributions
 much+0.073
 wonderful+0.063
lessly+0.060
br+0.060
 hard+0.059
Neg logit contributions
ados-0.069
 Cr-0.066
 Majesty-0.065
ishment-0.065
lee-0.060
Token fog
Token ID19558
Feature activation+1.49e-02

Pos logit contributions
 much+0.033
lessly+0.030
br+0.029
On+0.028
In+0.027
Neg logit contributions
 Cr-0.053
ishment-0.051
ados-0.050
 Fro-0.050
 Majesty-0.049
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
 much+0.041
 wonderful+0.037
lessly+0.037
br+0.036
On+0.036
Neg logit contributions
ados-0.013
 Cr-0.013
ishment-0.012
 Majesty-0.012
lee-0.010
Token It
Token ID632
Feature activation+3.58e-02

Pos logit contributions
ados+0.025
 Majesty+0.023
ishment+0.023
keeping+0.022
 Cr+0.022
Neg logit contributions
 much-0.029
lessly-0.024
In-0.024
 wonderful-0.023
On-0.023
Token makes
Token ID1838
Feature activation+1.21e-02

Pos logit contributions
 much+0.064
 wonderful+0.055
lessly+0.054
br+0.053
On+0.052
Neg logit contributions
ados-0.068
 Cr-0.066
 Majesty-0.065
ishment-0.065
lee-0.060
Token it
Token ID340
Feature activation+3.15e-02

Pos logit contributions
 much+0.023
 wonderful+0.019
lessly+0.018
 hard+0.018
br+0.018
Neg logit contributions
ados-0.023
 Cr-0.023
ishment-0.022
 Majesty-0.022
gy-0.020
Token Finally
Token ID9461
Feature activation+3.24e-02

Pos logit contributions
ados+0.048
 Majesty+0.046
ishment+0.045
 Cr+0.045
ishes+0.044
Neg logit contributions
 much-0.046
lessly-0.038
On-0.037
In-0.036
 wonderful-0.035
Token,
Token ID11
Feature activation+1.45e-02

Pos logit contributions
 much+0.062
lessly+0.056
 wonderful+0.055
On+0.054
In+0.053
Neg logit contributions
ados-0.055
 Cr-0.054
 Majesty-0.051
ishment-0.050
 Fro-0.048
Token he
Token ID339
Feature activation+1.22e-02

Pos logit contributions
 much+0.024
 wonderful+0.020
On+0.019
lessly+0.019
 hard+0.019
Neg logit contributions
ados-0.030
 Majesty-0.029
ishment-0.029
 Cr-0.029
lee-0.028
Token went
Token ID1816
Feature activation-1.40e-02

Pos logit contributions
 much+0.020
lessly+0.018
 wonderful+0.017
br+0.016
On+0.016
Neg logit contributions
 Cr-0.024
 Fro-0.023
lee-0.022
gy-0.022
 Majesty-0.022
Token to
Token ID284
Feature activation-4.45e-02

Pos logit contributions
ados+0.021
 Cr+0.021
ishment+0.020
 Majesty+0.020
 Fro+0.019
Neg logit contributions
 much-0.029
 wonderful-0.026
lessly-0.026
br-0.026
In-0.025
Token the
Token ID262
Feature activation-2.68e-02

Pos logit contributions
ados+0.094
ishment+0.088
 Majesty+0.088
lee+0.085
ishes+0.085
Neg logit contributions
 much-0.078
 wonderful-0.065
 hard-0.062
 bad-0.062
On-0.061
Token doctor
Token ID6253
Feature activation-4.05e-02

Pos logit contributions
 Majesty+0.041
ados+0.041
 Cr+0.040
ishment+0.038
 Fro+0.036
Neg logit contributions
 much-0.056
lessly-0.051
br-0.048
 wonderful-0.048
On-0.047
Token even
Token ID772
Feature activation-1.86e-02

Pos logit contributions
 Cr+0.096
ados+0.096
 Majesty+0.092
ishment+0.091
lee+0.086
Neg logit contributions
 much-0.056
On-0.042
 wonderful-0.041
lessly-0.041
 hard-0.040
Token though
Token ID996
Feature activation+1.51e-02

Pos logit contributions
 Cr+0.036
ados+0.036
ishment+0.036
 Majesty+0.034
 Fro+0.033
Neg logit contributions
 much-0.030
lessly-0.026
br-0.025
 wonderful-0.025
In-0.024
Token his
Token ID465
Feature activation-1.81e-02

Pos logit contributions
 much+0.025
lessly+0.022
 wonderful+0.021
br+0.021
On+0.021
Neg logit contributions
ados-0.029
 Cr-0.029
 Majesty-0.028
ishment-0.028
 Fro-0.026
Token wife
Token ID3656
Feature activation-2.44e-02

Pos logit contributions
 Cr+0.021
ados+0.021
ishment+0.019
 Majesty+0.019
lee+0.017
Neg logit contributions
 much-0.046
 wonderful-0.041
lessly-0.040
 hard-0.039
On-0.039
Token sun
Token ID4252
Feature activation+1.31e-02

Pos logit contributions
ados+0.012
 Cr+0.012
ishment+0.011
 Majesty+0.011
lee+0.011
Neg logit contributions
 much-0.013
lessly-0.012
 wonderful-0.012
On-0.011
br-0.011
Token.
Token ID13
Feature activation-1.89e-03

Pos logit contributions
 much+0.017
lessly+0.013
 wonderful+0.013
br+0.013
On+0.013
Neg logit contributions
 Cr-0.031
ados-0.030
 Majesty-0.030
ishment-0.030
lee-0.028
Token When
Token ID1649
Feature activation+5.31e-02

Pos logit contributions
ishment+0.003
 Majesty+0.003
ados+0.003
 Cr+0.003
ans+0.003
Neg logit contributions
 much-0.004
lessly-0.003
On-0.003
In-0.003
 wonderful-0.003
Token he
Token ID339
Feature activation+2.28e-02

Pos logit contributions
 much+0.088
lessly+0.080
 wonderful+0.077
br+0.076
On+0.075
Neg logit contributions
 Cr-0.102
ados-0.101
 Majesty-0.094
ishment-0.094
 Fro-0.090
Token woke
Token ID19092
Feature activation+2.72e-03

Pos logit contributions
 much+0.045
lessly+0.042
 wonderful+0.039
br+0.038
On+0.037
Neg logit contributions
 Cr-0.036
ados-0.034
 Fro-0.034
ishment-0.033
 Majesty-0.033
Token up
Token ID510
Feature activation+2.53e-02

Pos logit contributions
 much+0.005
 wonderful+0.004
 hard+0.004
lessly+0.004
 bad+0.004
Neg logit contributions
 Cr-0.005
ados-0.005
 Majesty-0.005
ishment-0.005
keeping-0.005
Token,
Token ID11
Feature activation+3.42e-02

Pos logit contributions
 much+0.046
 wonderful+0.039
lessly+0.039
On+0.038
br+0.038
Neg logit contributions
ados-0.047
 Cr-0.046
 Majesty-0.045
ishment-0.045
lee-0.042
Token all
Token ID477
Feature activation+4.30e-02

Pos logit contributions
 much+0.061
lessly+0.055
br+0.054
 wonderful+0.053
On+0.051
Neg logit contributions
 Cr-0.063
ados-0.062
ishment-0.057
 Majesty-0.057
 Fro-0.055
Token his
Token ID465
Feature activation+9.93e-03

Pos logit contributions
 much+0.076
 wonderful+0.063
lessly+0.063
On+0.060
br+0.059
Neg logit contributions
ados-0.084
 Cr-0.083
 Majesty-0.082
ishment-0.081
icans-0.075
Token candy
Token ID18550
Feature activation+5.83e-02

Pos logit contributions
 much+0.021
 wonderful+0.019
lessly+0.018
On+0.018
br+0.018
Neg logit contributions
ados-0.015
 Cr-0.015
ishment-0.014
 Majesty-0.014
lee-0.013
Token was
Token ID373
Feature activation+5.73e-02

Pos logit contributions
 much+0.096
lessly+0.087
 wonderful+0.083
On+0.081
In+0.079
Neg logit contributions
ados-0.111
 Cr-0.099
 Majesty-0.098
 knees-0.098
ishment-0.098
Token them
Token ID606
Feature activation+1.15e-02

Pos logit contributions
ados+0.023
 Cr+0.023
ishment+0.022
 Majesty+0.022
lee+0.020
Neg logit contributions
 much-0.021
lessly-0.018
 wonderful-0.018
On-0.018
br-0.018
Token when
Token ID618
Feature activation+1.11e-02

Pos logit contributions
 much+0.018
br+0.016
lessly+0.016
In+0.015
 wonderful+0.015
Neg logit contributions
ados-0.023
 Cr-0.022
ishment-0.022
 Majesty-0.022
lee-0.020
Token they
Token ID484
Feature activation+1.23e-03

Pos logit contributions
 much+0.020
 wonderful+0.017
lessly+0.016
On+0.016
br+0.016
Neg logit contributions
ados-0.021
 Cr-0.021
ishment-0.020
 Majesty-0.020
lee-0.019
Token were
Token ID547
Feature activation+2.15e-02

Pos logit contributions
 much+0.002
lessly+0.002
br+0.002
 wonderful+0.001
On+0.001
Neg logit contributions
 Cr-0.003
ados-0.003
 Majesty-0.002
ishment-0.002
lee-0.002
Token the
Token ID262
Feature activation+2.37e-02

Pos logit contributions
 much+0.028
br+0.026
On+0.025
lessly+0.025
In+0.025
Neg logit contributions
ados-0.045
 Majesty-0.044
 Cr-0.044
ishment-0.044
lee-0.043
Token right
Token ID826
Feature activation-3.69e-03

Pos logit contributions
 much+0.029
lessly+0.026
br+0.025
On+0.025
In+0.023
Neg logit contributions
 Majesty-0.054
ados-0.053
ishment-0.052
 Cr-0.051
 Fro-0.048
Token temperature
Token ID5951
Feature activation+2.06e-02

Pos logit contributions
ados+0.007
ishment+0.007
 Majesty+0.007
 Cr+0.006
gy+0.006
Neg logit contributions
 much-0.007
br-0.006
lessly-0.006
On-0.006
 wonderful-0.006
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
 much+0.031
 wonderful+0.027
lessly+0.027
On+0.026
br+0.026
Neg logit contributions
ados-0.042
 Cr-0.041
ishment-0.040
 Majesty-0.040
lee-0.038
Token<|endoftext|>
Token ID50256
Feature activation+9.61e-03

Pos logit contributions
ados+0.037
ishment+0.037
 Majesty+0.037
 Cr+0.036
ans+0.035
Neg logit contributions
 much-0.020
In-0.014
On-0.014
lessly-0.014
 wonderful-0.014
TokenOnce
Token ID7454
Feature activation+1.09e-02

Pos logit contributions
 much+0.016
lessly+0.014
 wonderful+0.014
br+0.013
On+0.013
Neg logit contributions
 Cr-0.018
ados-0.018
 Fro-0.017
 Rib-0.017
ishment-0.017
Token upon
Token ID2402
Feature activation+1.62e-03

Pos logit contributions
 much+0.017
lessly+0.014
 wonderful+0.014
br+0.014
On+0.013
Neg logit contributions
 Cr-0.022
ados-0.022
 Majesty-0.022
ishment-0.022
lee-0.021
Token away
Token ID1497
Feature activation+5.78e-03

Pos logit contributions
ados+0.057
 Cr+0.057
 Majesty+0.056
ishment+0.056
lee+0.052
Neg logit contributions
 much-0.051
lessly-0.043
 wonderful-0.043
On-0.041
br-0.041
Token and
Token ID290
Feature activation-3.30e-02

Pos logit contributions
 much+0.011
 wonderful+0.010
In+0.010
br+0.010
arest+0.009
Neg logit contributions
ados-0.009
 Cr-0.009
ishment-0.009
gy-0.008
 Fro-0.008
Token ran
Token ID4966
Feature activation-2.73e-02

Pos logit contributions
ados+0.065
 Cr+0.065
 Majesty+0.063
ishment+0.063
lee+0.059
Neg logit contributions
 much-0.055
 wonderful-0.046
lessly-0.046
On-0.044
br-0.044
Token back
Token ID736
Feature activation-3.69e-02

Pos logit contributions
ados+0.047
 Cr+0.046
 Majesty+0.044
ishment+0.044
gy+0.043
Neg logit contributions
 much-0.050
 wonderful-0.045
In-0.043
br-0.043
On-0.043
Token to
Token ID284
Feature activation-4.38e-02

Pos logit contributions
ados+0.066
 Cr+0.065
ishment+0.064
 Majesty+0.064
lee+0.059
Neg logit contributions
 much-0.070
 wonderful-0.059
lessly-0.059
On-0.058
 hard-0.057
Token his
Token ID465
Feature activation-4.38e-02

Pos logit contributions
ados+0.091
ishment+0.086
ishes+0.083
amb+0.081
 Majesty+0.080
Neg logit contributions
 much-0.080
 wonderful-0.066
 hard-0.063
 bad-0.060
 lot-0.060
Token castle
Token ID16669
Feature activation+4.32e-03

Pos logit contributions
 Cr+0.075
ados+0.072
ishment+0.068
icans+0.065
amb+0.064
Neg logit contributions
 much-0.090
 wonderful-0.080
 hard-0.077
 big-0.074
 bad-0.073
Token where
Token ID810
Feature activation+2.68e-02

Pos logit contributions
 much+0.007
 wonderful+0.006
lessly+0.006
br+0.005
In+0.005
Neg logit contributions
ados-0.009
 Majesty-0.009
 Cr-0.008
ishment-0.008
gy-0.008
Token he
Token ID339
Feature activation-5.89e-03

Pos logit contributions
 much+0.040
 wonderful+0.030
lessly+0.029
 hard+0.029
On+0.027
Neg logit contributions
ados-0.062
ishment-0.062
 Majesty-0.060
 Cr-0.059
amb-0.057
Token was
Token ID373
Feature activation+7.44e-03

Pos logit contributions
 Cr+0.013
 Majesty+0.013
ados+0.012
ishment+0.012
gy+0.012
Neg logit contributions
 much-0.008
lessly-0.007
 wonderful-0.007
On-0.006
br-0.006
Token safe
Token ID3338
Feature activation-1.85e-02

Pos logit contributions
 much+0.012
lessly+0.010
 wonderful+0.010
On+0.010
In+0.010
Neg logit contributions
ados-0.015
 Cr-0.015
 Majesty-0.014
ishment-0.014
gy-0.013
Token.
Token ID13
Feature activation-3.09e-02

Pos logit contributions
ados+0.040
 Cr+0.040
 Majesty+0.040
ishment+0.039
gy+0.037
Neg logit contributions
 much-0.027
br-0.023
lessly-0.023
 wonderful-0.023
On-0.022
Token<|endoftext|>
Token ID50256
Feature activation-1.19e-02

Pos logit contributions
ados+0.070
ishment+0.068
 Majesty+0.068
 Cr+0.067
lee+0.064
Neg logit contributions
 much-0.046
On-0.035
 wonderful-0.035
lessly-0.035
In-0.034
TokenL
Token ID43
Feature activation-5.62e-02

Pos logit contributions
 Cr+0.023
ados+0.023
 Fro+0.021
ishment+0.021
 Rib+0.021
Neg logit contributions
 much-0.019
lessly-0.017
 wonderful-0.017
br-0.016
On-0.016
Tokenily
Token ID813
Feature activation-4.80e-02

Pos logit contributions
 Cr+0.112
ados+0.111
 Majesty+0.108
ishment+0.108
ican+0.101
Neg logit contributions
 much-0.101
 wonderful-0.083
lessly-0.081
On-0.080
In-0.079
Token and
Token ID290
Feature activation-6.28e-02

Pos logit contributions
ados+0.116
 Cr+0.114
ishment+0.112
 Majesty+0.111
ican+0.103
Neg logit contributions
 much-0.064
 wonderful-0.051
In-0.049
On-0.047
 hard-0.047
Token Ben
Token ID3932
Feature activation-3.67e-02

Pos logit contributions
 Majesty+0.139
ishment+0.132
ados+0.124
ans+0.124
ieties+0.123
Neg logit contributions
 much-0.116
 wonderful-0.092
 big-0.090
 bad-0.089
 on-0.088
Token were
Token ID547
Feature activation-5.03e-03

Pos logit contributions
ados+0.089
 Cr+0.088
 Majesty+0.087
ishment+0.087
lee+0.082
Neg logit contributions
 much-0.046
 wonderful-0.036
lessly-0.034
On-0.033
br-0.033
Token playing
Token ID2712
Feature activation-1.32e-02

Pos logit contributions
ados+0.011
 Cr+0.011
ishment+0.011
 Majesty+0.011
ican+0.011
Neg logit contributions
 much-0.008
 wonderful-0.006
 hard-0.006
 lot-0.006
In-0.005
Token in
Token ID287
Feature activation-1.80e-02

Pos logit contributions
lee+0.037
 Majesty+0.037
ishment+0.036
 Cr+0.036
ados+0.036
Neg logit contributions
 much-0.012
 wonderful-0.009
 on-0.008
On-0.008
 hard-0.008
Token the
Token ID262
Feature activation-4.46e-02

Pos logit contributions
 Majesty+0.041
ados+0.039
ishment+0.038
 Cr+0.038
amb+0.037
Neg logit contributions
 much-0.029
 wonderful-0.024
On-0.024
 hard-0.023
In-0.022
Token park
Token ID3952
Feature activation-2.48e-02

Pos logit contributions
ados+0.092
 Cr+0.091
ishment+0.089
 Majesty+0.088
cess+0.085
Neg logit contributions
 much-0.075
 wonderful-0.066
On-0.061
In-0.061
 hard-0.060
Token want
Token ID765
Feature activation-4.10e-02

Pos logit contributions
 Majesty+0.094
 Cr+0.093
ados+0.090
ishment+0.089
gy+0.087
Neg logit contributions
 much-0.085
lessly-0.076
br-0.073
On-0.070
 wonderful-0.070
Token a
Token ID257
Feature activation-2.54e-02

Pos logit contributions
ados+0.073
 Cr+0.072
ishment+0.072
 Majesty+0.071
lee+0.066
Neg logit contributions
 much-0.078
 wonderful-0.066
lessly-0.064
br-0.063
On-0.063
Token hug
Token ID16225
Feature activation-5.93e-02

Pos logit contributions
 Cr+0.049
 Majesty+0.048
ados+0.047
ishment+0.045
 Fro+0.045
Neg logit contributions
 much-0.041
lessly-0.039
In-0.035
On-0.035
br-0.033
Token after
Token ID706
Feature activation-4.03e-02

Pos logit contributions
ados+0.121
 Cr+0.121
ishment+0.119
 Majesty+0.118
lee+0.112
Neg logit contributions
 much-0.097
 wonderful-0.079
lessly-0.078
br-0.076
On-0.075
Token playing
Token ID2712
Feature activation-5.57e-02

Pos logit contributions
 Cr+0.066
ishment+0.066
 Majesty+0.065
ados+0.064
gy+0.060
Neg logit contributions
 much-0.083
 wonderful-0.070
 hard-0.067
lessly-0.067
On-0.066
Token in
Token ID287
Feature activation-5.01e-02

Pos logit contributions
ishment+0.123
 Cr+0.123
 Majesty+0.123
ados+0.122
lee+0.120
Neg logit contributions
 much-0.083
 wonderful-0.067
 hard-0.062
br-0.061
On-0.059
Token the
Token ID262
Feature activation-5.60e-02

Pos logit contributions
ados+0.079
 Cr+0.078
 Majesty+0.076
ishment+0.075
lee+0.070
Neg logit contributions
 much-0.106
 wonderful-0.092
lessly-0.089
On-0.088
br-0.087
Token rain
Token ID6290
Feature activation-4.12e-02

Pos logit contributions
ados+0.095
 Cr+0.094
 Majesty+0.091
ishment+0.091
lee+0.084
Neg logit contributions
 much-0.110
lessly-0.094
 wonderful-0.094
On-0.091
br-0.091
Token."
Token ID526
Feature activation-5.60e-02

Pos logit contributions
ados+0.085
 Cr+0.084
ishment+0.081
 Majesty+0.081
lee+0.077
Neg logit contributions
 much-0.067
 wonderful-0.055
lessly-0.054
br-0.053
On-0.052
Token Lily
Token ID20037
Feature activation-3.22e-02

Pos logit contributions
 Majesty+0.148
ishment+0.147
ados+0.145
ishes+0.140
urg+0.138
Neg logit contributions
 much-0.062
On-0.044
He-0.044
In-0.042
It-0.037
Token smiled
Token ID13541
Feature activation-3.29e-02

Pos logit contributions
ados+0.087
 Cr+0.080
 Majesty+0.079
ishment+0.079
keeping+0.076
Neg logit contributions
 much-0.038
 had-0.031
 wonderful-0.030
 also-0.030
On-0.030
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
ados+0.036
 Cr+0.036
 Majesty+0.035
ishment+0.035
lee+0.032
Neg logit contributions
 much-0.043
 wonderful-0.037
lessly-0.037
br-0.036
On-0.035
Token rabbit
Token ID22746
Feature activation-1.74e-02

Pos logit contributions
lessly+0.021
 much+0.021
br+0.020
On+0.020
In+0.020
Neg logit contributions
 Cr-0.014
ados-0.013
 Majesty-0.013
ishment-0.012
 Fro-0.012
Token home
Token ID1363
Feature activation+8.28e-03

Pos logit contributions
ados+0.034
ishment+0.034
 Cr+0.033
 Majesty+0.033
lee+0.031
Neg logit contributions
 much-0.031
 wonderful-0.026
lessly-0.024
 hard-0.024
On-0.024
Token to
Token ID284
Feature activation-3.90e-02

Pos logit contributions
 much+0.012
 wonderful+0.010
lessly+0.010
br+0.010
On+0.010
Neg logit contributions
ados-0.018
 Cr-0.017
 Majesty-0.017
ishment-0.017
lee-0.016
Token her
Token ID607
Feature activation-3.72e-02

Pos logit contributions
ados+0.063
 Cr+0.060
ishment+0.060
 Majesty+0.059
icans+0.054
Neg logit contributions
 much-0.083
 wonderful-0.072
lessly-0.068
On-0.067
 hard-0.067
Token Mum
Token ID38367
Feature activation-4.76e-02

Pos logit contributions
ados+0.060
 Cr+0.060
ishment+0.057
 Majesty+0.055
lee+0.052
Neg logit contributions
 much-0.078
 wonderful-0.068
On-0.064
lessly-0.064
 hard-0.064
Token.
Token ID13
Feature activation-1.85e-02

Pos logit contributions
ados+0.113
 Cr+0.113
 Majesty+0.113
ishment+0.110
ican+0.103
Neg logit contributions
 much-0.061
 wonderful-0.048
On-0.045
lessly-0.045
 hard-0.043
Token But
Token ID887
Feature activation+2.49e-02

Pos logit contributions
ishment+0.040
ados+0.040
 Majesty+0.039
 Cr+0.038
icans+0.037
Neg logit contributions
 much-0.030
On-0.023
lessly-0.023
In-0.023
 wonderful-0.022
Token,
Token ID11
Feature activation+2.65e-02

Pos logit contributions
 much+0.043
 wonderful+0.035
lessly+0.034
On+0.034
 hard+0.033
Neg logit contributions
ados-0.050
 Majesty-0.048
 Cr-0.048
ishment-0.048
lee-0.045
Token before
Token ID878
Feature activation+3.77e-02

Pos logit contributions
 much+0.047
 wonderful+0.039
lessly+0.039
On+0.038
br+0.037
Neg logit contributions
ados-0.050
 Cr-0.050
 Majesty-0.049
ishment-0.049
lee-0.045
Token she
Token ID673
Feature activation+2.75e-03

Pos logit contributions
 much+0.068
lessly+0.063
 wonderful+0.062
br+0.060
In+0.059
Neg logit contributions
ados-0.064
 Cr-0.064
 Fro-0.058
lee-0.058
ishment-0.058
Token,
Token ID11
Feature activation-1.52e-02

Pos logit contributions
ados+0.009
 Cr+0.009
 Majesty+0.009
ishment+0.008
 Fro+0.008
Neg logit contributions
 much-0.009
lessly-0.008
 wonderful-0.008
On-0.008
br-0.008
Token there
Token ID612
Feature activation+8.71e-03

Pos logit contributions
 Cr+0.032
ados+0.032
gy+0.032
 Majesty+0.031
ishment+0.031
Neg logit contributions
 much-0.021
lessly-0.018
br-0.018
 wonderful-0.017
On-0.016
Token was
Token ID373
Feature activation-1.08e-02

Pos logit contributions
 much+0.012
lessly+0.011
br+0.010
 wonderful+0.010
On+0.009
Neg logit contributions
 Cr-0.018
 Fro-0.018
gy-0.018
ados-0.017
 Majesty-0.017
Token a
Token ID257
Feature activation-3.01e-03

Pos logit contributions
ishment+0.029
ados+0.029
 Majesty+0.029
 Cr+0.028
ishes+0.027
Neg logit contributions
 much-0.013
 wonderful-0.009
On-0.008
In-0.008
 hard-0.008
Token little
Token ID1310
Feature activation-4.81e-02

Pos logit contributions
ados+0.007
 Cr+0.007
ishment+0.007
 Majesty+0.007
lee+0.006
Neg logit contributions
 much-0.004
 wonderful-0.003
lessly-0.003
On-0.003
br-0.003
Token boy
Token ID2933
Feature activation-4.76e-02

Pos logit contributions
ados+0.098
ishment+0.096
 Majesty+0.096
 Cr+0.095
keeping+0.094
Neg logit contributions
 much-0.081
 wonderful-0.070
 hard-0.068
 lot-0.066
 big-0.065
Token named
Token ID3706
Feature activation-6.90e-02

Pos logit contributions
ados+0.094
 Majesty+0.092
ishment+0.090
 Cr+0.088
icans+0.081
Neg logit contributions
 much-0.090
 wonderful-0.071
On-0.069
In-0.069
 hard-0.069
Token Tim
Token ID5045
Feature activation-4.79e-02

Pos logit contributions
ishment+0.100
ados+0.097
 Majesty+0.092
ieties+0.087
ican+0.084
Neg logit contributions
 much-0.167
 wonderful-0.140
 hard-0.139
In-0.136
On-0.135
Tokenmy
Token ID1820
Feature activation-3.86e-02

Pos logit contributions
 Cr+0.072
ados+0.072
ishment+0.070
gy+0.070
 Majesty+0.068
Neg logit contributions
 much-0.096
br-0.087
lessly-0.086
 wonderful-0.084
On-0.081
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
 Cr+0.076
ados+0.076
gy+0.074
ishment+0.073
 Majesty+0.073
Neg logit contributions
 much-0.060
lessly-0.053
br-0.052
 wonderful-0.051
On-0.049
Token Tim
Token ID5045
Feature activation-3.01e-02

Pos logit contributions
 Majesty+0.016
ados+0.015
ishment+0.015
 Cr+0.014
lee+0.013
Neg logit contributions
 much-0.032
On-0.028
 wonderful-0.028
lessly-0.028
In-0.027
Token turned
Token ID2900
Feature activation-6.35e-03

Pos logit contributions
 much+0.031
 wonderful+0.026
lessly+0.025
br+0.025
On+0.024
Neg logit contributions
 Cr-0.050
ados-0.050
 Majesty-0.048
ishment-0.048
lee-0.046
Token out
Token ID503
Feature activation-1.02e-02

Pos logit contributions
ados+0.012
 Cr+0.011
ishment+0.011
 Majesty+0.011
lee+0.010
Neg logit contributions
 much-0.011
 wonderful-0.010
On-0.010
lessly-0.010
In-0.010
Token that
Token ID326
Feature activation+1.25e-03

Pos logit contributions
ados+0.018
 Cr+0.017
ishment+0.017
lee+0.016
 Majesty+0.016
Neg logit contributions
 much-0.018
br-0.016
In-0.016
 wonderful-0.016
On-0.016
Token the
Token ID262
Feature activation-6.19e-03

Pos logit contributions
 much+0.002
lessly+0.002
 wonderful+0.002
On+0.002
br+0.002
Neg logit contributions
ados-0.002
 Cr-0.002
ishment-0.002
 Majesty-0.002
lee-0.002
Token av
Token ID1196
Feature activation-6.37e-02

Pos logit contributions
ados+0.009
 Cr+0.009
 Majesty+0.009
ishment+0.009
 Fro+0.008
Neg logit contributions
 much-0.013
lessly-0.012
On-0.011
br-0.011
 wonderful-0.011
Tokenoc
Token ID420
Feature activation-1.17e-01

Pos logit contributions
 Cr+0.101
ados+0.098
 Majesty+0.097
ishment+0.096
lee+0.090
Neg logit contributions
 much-0.134
br-0.114
 wonderful-0.114
lessly-0.113
On-0.111
Tokenados
Token ID22484
Feature activation+2.21e-02

Pos logit contributions
 Fro+0.076
 Cr+0.070
 Rib+0.066
 fro+0.064
ishment+0.064
Neg logit contributions
 much-0.316
br-0.291
lessly-0.288
ier-0.288
 hard-0.286
Token were
Token ID547
Feature activation+2.08e-02

Pos logit contributions
 much+0.031
 wonderful+0.026
lessly+0.025
br+0.024
On+0.024
Neg logit contributions
ados-0.048
 Cr-0.047
ishment-0.045
 Majesty-0.044
gy-0.044
Token bad
Token ID2089
Feature activation-3.63e-02

Pos logit contributions
br+0.026
 much+0.026
On+0.025
In+0.025
arest+0.024
Neg logit contributions
ados-0.045
 Cr-0.043
lee-0.041
ishment-0.041
 Majesty-0.041
Token and
Token ID290
Feature activation-1.28e-02

Pos logit contributions
 Cr+0.081
ados+0.078
ishment+0.078
 Majesty+0.077
ican+0.073
Neg logit contributions
 much-0.055
 wonderful-0.044
lessly-0.043
 hard-0.042
br-0.040
Token made
Token ID925
Feature activation+5.87e-03

Pos logit contributions
ados+0.027
 Cr+0.027
 Majesty+0.026
ishment+0.026
lee+0.025
Neg logit contributions
 much-0.020
 wonderful-0.016
lessly-0.016
On-0.015
br-0.015
Token there
Token ID612
Feature activation-9.90e-03

Pos logit contributions
 Cr+0.025
ados+0.024
 Majesty+0.023
ishment+0.023
 Fro+0.022
Neg logit contributions
 much-0.024
 wonderful-0.021
lessly-0.020
br-0.020
In-0.020
Token was
Token ID373
Feature activation-1.51e-02

Pos logit contributions
ados+0.025
 Cr+0.024
 Majesty+0.024
ishment+0.024
lee+0.023
Neg logit contributions
 much-0.012
 wonderful-0.009
lessly-0.009
On-0.008
In-0.008
Token a
Token ID257
Feature activation+1.44e-03

Pos logit contributions
 Cr+0.032
ados+0.031
 Majesty+0.031
ishment+0.030
 Fro+0.029
Neg logit contributions
 much-0.022
lessly-0.019
br-0.018
 wonderful-0.018
On-0.017
Token rh
Token ID9529
Feature activation-4.39e-02

Pos logit contributions
 much+0.002
lessly+0.002
br+0.002
In+0.002
On+0.002
Neg logit contributions
 Majesty-0.003
 Cr-0.003
ados-0.003
ishment-0.003
 Fro-0.003
Tokenin
Token ID259
Feature activation-3.82e-02

Pos logit contributions
ados+0.091
 Cr+0.088
ishment+0.084
 Majesty+0.083
ican+0.082
Neg logit contributions
 much-0.068
 wonderful-0.059
lessly-0.057
On-0.055
In-0.054
Tokenoc
Token ID420
Feature activation-1.21e-01

Pos logit contributions
 Cr+0.048
ados+0.048
 Majesty+0.046
ishment+0.045
gy+0.041
Neg logit contributions
 much-0.090
lessly-0.081
 wonderful-0.080
On-0.078
br-0.078
Tokeneros
Token ID27498
Feature activation-3.66e-02

Pos logit contributions
ishment+0.119
 Jenna+0.114
 Cr+0.111
lee+0.109
 Po+0.106
Neg logit contributions
 much-0.277
br-0.261
ier-0.257
 hard-0.252
lessly-0.251
Token who
Token ID508
Feature activation-1.06e-02

Pos logit contributions
ados+0.076
 Cr+0.075
 Majesty+0.073
ishment+0.073
lee+0.069
Neg logit contributions
 much-0.058
 wonderful-0.048
lessly-0.048
On-0.046
br-0.046
Token was
Token ID373
Feature activation+7.55e-03

Pos logit contributions
 Cr+0.023
ados+0.022
gy+0.022
 Majesty+0.022
ishment+0.021
Neg logit contributions
 much-0.015
lessly-0.013
br-0.012
 wonderful-0.012
On-0.012
Token always
Token ID1464
Feature activation-3.35e-03

Pos logit contributions
 much+0.007
lessly+0.007
br+0.006
 wonderful+0.006
On+0.006
Neg logit contributions
 Cr-0.019
ados-0.019
 Majesty-0.019
ishment-0.018
gy-0.018
Token naughty
Token ID45128
Feature activation-4.30e-02

Pos logit contributions
 Cr+0.006
ados+0.006
ishment+0.006
 Majesty+0.006
gy+0.006
Neg logit contributions
 much-0.005
br-0.005
lessly-0.005
In-0.005
On-0.005
Token big
Token ID1263
Feature activation-3.36e-02

Pos logit contributions
 Cr+0.008
 Majesty+0.008
ados+0.008
 fro+0.007
 Fro+0.007
Neg logit contributions
lessly-0.008
 much-0.008
In-0.007
On-0.007
br-0.006
Token,
Token ID11
Feature activation-2.27e-02

Pos logit contributions
ados+0.057
 Cr+0.056
 Majesty+0.055
ishment+0.055
lee+0.050
Neg logit contributions
 much-0.066
 wonderful-0.056
lessly-0.056
On-0.055
br-0.054
Token beautiful
Token ID4950
Feature activation-4.27e-02

Pos logit contributions
 Cr+0.045
ados+0.044
ishment+0.042
 Harry+0.040
lee+0.040
Neg logit contributions
 much-0.033
lessly-0.030
br-0.029
In-0.029
t-0.028
Token rainbow
Token ID27223
Feature activation-1.63e-03

Pos logit contributions
ados+0.069
 Cr+0.069
ishment+0.067
 Majesty+0.066
lee+0.061
Neg logit contributions
 much-0.087
 wonderful-0.076
lessly-0.073
br-0.072
On-0.072
Token-
Token ID12
Feature activation-6.09e-02

Pos logit contributions
ados+0.003
 Cr+0.003
ishment+0.003
 Majesty+0.003
lee+0.003
Neg logit contributions
 much-0.002
 wonderful-0.002
lessly-0.002
On-0.002
In-0.002
Tokencol
Token ID4033
Feature activation-1.09e-01

Pos logit contributions
ados+0.102
 Cr+0.100
 Majesty+0.098
ishment+0.098
lee+0.090
Neg logit contributions
 much-0.122
 wonderful-0.104
lessly-0.104
br-0.101
On-0.101
Tokenoured
Token ID8167
Feature activation-5.70e-02

Pos logit contributions
 Cr+0.171
 Majesty+0.165
 Fro+0.165
 Harry+0.159
ados+0.157
Neg logit contributions
 much-0.195
lessly-0.185
br-0.184
 wonderful-0.172
lic-0.170
Token butterfly
Token ID35113
Feature activation-3.21e-02

Pos logit contributions
ishment+0.100
 Cr+0.100
ados+0.100
 Majesty+0.100
lee+0.091
Neg logit contributions
 much-0.108
 wonderful-0.092
lessly-0.090
br-0.089
On-0.086
Token!
Token ID0
Feature activation-4.25e-02

Pos logit contributions
 Cr+0.074
ishment+0.073
ados+0.073
 Majesty+0.072
 Fro+0.067
Neg logit contributions
 much-0.045
br-0.036
 wonderful-0.035
lessly-0.035
On-0.033
Token The
Token ID383
Feature activation+6.27e-04

Pos logit contributions
ishment+0.078
 Majesty+0.078
ados+0.075
ans+0.073
ishes+0.072
Neg logit contributions
 much-0.084
On-0.070
lessly-0.067
In-0.067
It-0.064
Token little
Token ID1310
Feature activation-3.80e-02

Pos logit contributions
 much+0.001
lessly+0.001
On+0.001
 wonderful+0.001
br+0.001
Neg logit contributions
ados-0.001
 Cr-0.001
 Majesty-0.001
ishment-0.001
lee-0.001
Token't
Token ID470
Feature activation-4.99e-02

Pos logit contributions
ados+0.143
 Cr+0.142
 Majesty+0.138
ishment+0.137
lee+0.130
Neg logit contributions
 much-0.104
 wonderful-0.085
lessly-0.085
On-0.082
br-0.081
Token cry
Token ID3960
Feature activation-8.03e-02

Pos logit contributions
ados+0.084
 Cr+0.082
ishment+0.081
 Majesty+0.081
lee+0.074
Neg logit contributions
 much-0.100
 wonderful-0.086
lessly-0.085
On-0.083
br-0.082
Token,
Token ID11
Feature activation-4.93e-02

Pos logit contributions
ados+0.174
ishment+0.172
 Cr+0.171
 Majesty+0.168
icans+0.160
Neg logit contributions
 much-0.126
lessly-0.099
 hard-0.096
 wonderful-0.094
 bad-0.089
Token boys
Token ID6510
Feature activation-5.96e-02

Pos logit contributions
ishment+0.089
ados+0.088
 Majesty+0.086
lee+0.080
gy+0.079
Neg logit contributions
 much-0.099
 wonderful-0.085
br-0.078
 hard-0.078
lessly-0.077
Token.
Token ID13
Feature activation-5.44e-02

Pos logit contributions
ados+0.132
 Cr+0.131
 Majesty+0.128
ishment+0.128
lee+0.120
Neg logit contributions
 much-0.087
 wonderful-0.070
lessly-0.069
br-0.065
On-0.065
Token Acc
Token ID6366
Feature activation-1.34e-01

Pos logit contributions
ishment+0.103
ados+0.103
 Majesty+0.097
icans+0.094
keeping+0.094
Neg logit contributions
 much-0.103
In-0.083
He-0.080
 wonderful-0.080
It-0.079
Tokenidents
Token ID3231
Feature activation-5.54e-04

Pos logit contributions
ados+0.147
keeping+0.147
 Fro+0.146
alk+0.146
 Cr+0.144
Neg logit contributions
 much-0.275
 hard-0.248
 wrong-0.242
 bad-0.241
 better-0.237
Token happen
Token ID1645
Feature activation-3.39e-02

Pos logit contributions
 Cr+0.001
 disl+0.001
ados+0.001
ors+0.001
 Twe+0.001
Neg logit contributions
 much-0.001
On-0.001
In-0.001
br-0.001
 security-0.001
Token.
Token ID13
Feature activation-5.16e-02

Pos logit contributions
ados+0.070
 Cr+0.069
 Majesty+0.067
ishment+0.067
lee+0.063
Neg logit contributions
 much-0.053
lessly-0.045
 wonderful-0.044
On-0.044
br-0.043
Token I
Token ID314
Feature activation-2.53e-02

Pos logit contributions
ados+0.094
ishment+0.093
ican+0.089
icans+0.088
ans+0.087
Neg logit contributions
 much-0.102
lessly-0.081
In-0.081
He-0.080
 wonderful-0.080
Token have
Token ID423
Feature activation-1.06e-02

Pos logit contributions
 Cr+0.047
gy+0.045
 Majesty+0.045
 Fro+0.045
 disl+0.043
Neg logit contributions
 much-0.040
br-0.036
lessly-0.035
On-0.034
In-0.033
TokenK
Token ID42
Feature activation-1.12e-01

Pos logit contributions
 much+0.044
 wonderful+0.036
lessly+0.034
On+0.033
br+0.033
Neg logit contributions
ados-0.059
 Cr-0.057
 Majesty-0.056
ishment-0.056
lee-0.053
Tokenitty
Token ID9760
Feature activation-1.01e-01

Pos logit contributions
ados+0.188
 Cr+0.184
ishment+0.176
 Majesty+0.172
lee+0.159
Neg logit contributions
 much-0.223
 wonderful-0.194
lessly-0.193
In-0.189
On-0.188
Token wanted
Token ID2227
Feature activation-4.84e-02

Pos logit contributions
ados+0.259
ishment+0.257
 Cr+0.256
 Majesty+0.247
lee+0.233
Neg logit contributions
 much-0.113
 wonderful-0.084
br-0.081
In-0.080
lessly-0.079
Token to
Token ID284
Feature activation-7.50e-02

Pos logit contributions
ishment+0.098
 Majesty+0.097
ados+0.097
 Cr+0.094
lee+0.089
Neg logit contributions
 much-0.085
 wonderful-0.071
 hard-0.067
On-0.064
 bad-0.063
Token introduce
Token ID10400
Feature activation-7.44e-02

Pos logit contributions
ados+0.161
ishment+0.160
 Cr+0.149
 Majesty+0.148
lee+0.146
Neg logit contributions
 much-0.123
 wonderful-0.105
On-0.095
 bad-0.094
 big-0.092
Token Dog
Token ID8532
Feature activation-1.05e-01

Pos logit contributions
 Majesty+0.116
ishment+0.113
ados+0.107
 Cr+0.106
lee+0.099
Neg logit contributions
 much-0.164
 wonderful-0.139
lessly-0.138
 hard-0.138
In-0.132
Tokengy
Token ID1360
Feature activation-9.94e-02

Pos logit contributions
ados+0.167
ishment+0.162
 Majesty+0.160
 Cr+0.156
lee+0.147
Neg logit contributions
 much-0.226
 wonderful-0.195
On-0.188
ching-0.188
 hard-0.185
Token to
Token ID284
Feature activation-6.56e-02

Pos logit contributions
 Cr+0.190
ados+0.190
ishment+0.188
 Majesty+0.186
lee+0.176
Neg logit contributions
 much-0.175
 wonderful-0.146
On-0.141
lessly-0.139
 hard-0.139
Token her
Token ID607
Feature activation-5.73e-02

Pos logit contributions
ados+0.111
 Cr+0.108
ishment+0.106
 Majesty+0.106
lee+0.098
Neg logit contributions
 much-0.131
 wonderful-0.113
lessly-0.111
On-0.109
br-0.107
Token ball
Token ID2613
Feature activation-4.73e-02

Pos logit contributions
ados+0.115
 Cr+0.114
 Majesty+0.112
ishment+0.111
lee+0.104
Neg logit contributions
 much-0.093
lessly-0.078
 wonderful-0.078
br-0.075
On-0.075
Token.
Token ID13
Feature activation-4.89e-02

Pos logit contributions
ados+0.106
 Majesty+0.106
ishment+0.104
 Cr+0.103
lee+0.099
Neg logit contributions
 much-0.069
lessly-0.054
On-0.053
 wonderful-0.053
br-0.051