TOP ACTIVATIONS
MAX = 0.162

She wore a pink a pron with flowers on it .
put on her blue a pron and climbed on a stool
Tom wore his a pron proudly every day . It
put on a pink a pron and climbed on a stool
He puts on his a pron and hat again .
Lily wore a pink a pron and Ben wore a blue
cy put on her a pron and started to mix the
She put on her a pron and went into the kitchen
a chef hat and a pron . " I
She put on an a pron so she was ready to
She put on her a pron and started to clean .
loved wearing her lovely a pron every day . One day
He put on his a pron and started to mix the
, Lily wore her a pron proudly , knowing that she
my put on her a pron and showed it to her
He put on the a pron and picked up a spat
Lily put on the a pron and felt very proud of
She put on her a pron and asked her mum what
She put on her a pron with a big zip .
Lily loved wearing the a pron and felt like a real

MIN ACTIVATIONS
MIN = -0.187

, but sometimes , the endings are not . <|endoftext|> Once
lead to problems and bad endings . <|endoftext|> There was a
searches can lead to happy endings - but sometimes it just
fighting can lead to bad endings . <|endoftext|> One day ,
will never lead to bad endings . <|endoftext|> Once upon a
, there are still bad endings . <|endoftext|> Once there was
Not all dreams have happy endings ." The
Not all dreams have happy endings ." The
impatient can lead to bad endings . Don â € ™
scary things can have happy endings . <|endoftext|> Once upon a
our dreams can have sad endings . <|endoftext|> Once upon a
and gave them all happy endings . Then
her tips and knew the dangers of the world . <|endoftext|>
warned his friends about the dangers of them . <|endoftext|> Once
She did not like bad endings . <|endoftext|> It was Lily
You don 't know what dangers are outside !" Buzz y
and make up your own endings too . What do you
. You never know what dangers lur k around the corner
farmer 's warnings about the dangers outside of the farm .
something without thinking about the consequences . Matt had no idea

INTERVAL 0.074 - 0.162
CONTAINS 1.258%

fix it , please ?" Her mom looked at the broken
and ran to her mom 's room . " Mom my
listen and share . She also said they had to be
bird agreed , and they both lived happily ever after ,
and the people . She also taught them some words in

INTERVAL -0.013 - 0.074
CONTAINS 63.953%

, but she was shy . Her mom
your cr ay ons made a new poem for you .
her wings . She pe ck ed at the cage door
and had fun at the wedding . <|endoftext|> Once upon a
and she couldn 't believe her eyes . She saw big

INTERVAL -0.100 - -0.013
CONTAINS 34.658%

. <|endoftext|> An nie was a happy girl . She loved
When it was time to go home , Sus ie was
brave was good . <|endoftext|> Once upon a time , there
was very excited ! He went to a party with all
was so excited to find a special screw lying in the

INTERVAL -0.187 - -0.100
CONTAINS 0.131%

money or you â € ™ ll lose it ! â
regular and quiet , and nobody paid attention .
animals were worried . The thunder and lightning were loud and
mom , " that 's why they call it a medal
cried . " Why did you do that ,
Token She
Token ID1375
Feature activation+4.30e-02

Pos logit contributions
bons+0.020
age+0.020
ringe+0.020
ages+0.019
 cand+0.018
Neg logit contributions
 but-0.016
 unless-0.015
 Little-0.015
 thunder-0.014
 Sam-0.014
Token wore
Token ID12408
Feature activation+5.26e-02

Pos logit contributions
bons+0.100
ringe+0.096
age+0.092
cards+0.089
 cand+0.088
Neg logit contributions
 but-0.039
 unless-0.035
 Tony-0.035
 Little-0.034
?-0.034
Token a
Token ID257
Feature activation+1.50e-02

Pos logit contributions
age+0.141
ringe+0.135
bons+0.130
acked+0.129
rolley+0.126
Neg logit contributions
 but-0.030
 the-0.030
 thunder-0.030
 Little-0.028
 Ben-0.027
Token pink
Token ID11398
Feature activation+1.21e-01

Pos logit contributions
bons+0.031
ringe+0.028
age+0.028
cream+0.027
checked+0.027
Neg logit contributions
 but-0.019
?-0.018
 thunder-0.017
 time-0.016
 there-0.016
Token a
Token ID257
Feature activation+5.91e-03

Pos logit contributions
bons+0.249
ages+0.235
checked+0.231
cream+0.231
cards+0.226
Neg logit contributions
 but-0.165
?-0.154
!-0.137
 thunder-0.132
 unless-0.126
Tokenpron
Token ID31186
Feature activation+1.62e-01

Pos logit contributions
bons+0.012
ringe+0.011
cream+0.011
checked+0.011
age+0.011
Neg logit contributions
 but-0.008
?-0.008
 thunder-0.007
 time-0.007
!-0.007
Token with
Token ID351
Feature activation+2.89e-02

Pos logit contributions
bons+0.359
ringe+0.345
age+0.335
 cand+0.329
 ham+0.325
Neg logit contributions
 unless-0.159
 but-0.147
 thunder-0.136
 Tony-0.136
?-0.127
Token flowers
Token ID12734
Feature activation+2.15e-02

Pos logit contributions
ringe+0.065
age+0.065
 Amen+0.061
bons+0.059
checked+0.056
Neg logit contributions
 Little-0.027
 thunder-0.027
 Ben-0.027
 Sam-0.026
 but-0.026
Token on
Token ID319
Feature activation+1.37e-02

Pos logit contributions
bons+0.054
ringe+0.054
age+0.050
 cash+0.049
 cand+0.049
Neg logit contributions
 but-0.015
 unless-0.015
!-0.013
?-0.012
 behind-0.012
Token it
Token ID340
Feature activation+1.63e-02

Pos logit contributions
bons+0.031
ringe+0.030
age+0.030
 cand+0.028
 ham+0.028
Neg logit contributions
 unless-0.013
 but-0.012
 Tony-0.012
 thunder-0.012
 Little-0.011
Token.
Token ID13
Feature activation+6.26e-03

Pos logit contributions
bons+0.041
ringe+0.040
age+0.040
 cand+0.039
 ham+0.038
Neg logit contributions
 unless-0.011
 but-0.009
 thunder-0.009
 Tony-0.009
 Jay-0.008
Token put
Token ID1234
Feature activation+3.97e-02

Pos logit contributions
bons+0.101
ringe+0.099
age+0.095
 cand+0.090
cards+0.090
Neg logit contributions
 but-0.046
 Tony-0.043
 unless-0.043
 Little-0.041
?-0.041
Token on
Token ID319
Feature activation+3.21e-02

Pos logit contributions
age+0.111
bons+0.107
ringe+0.105
ages+0.102
lets+0.100
Neg logit contributions
 but-0.018
 the-0.016
 Ben-0.015
 Little-0.015
 unless-0.015
Token her
Token ID607
Feature activation+7.26e-02

Pos logit contributions
age+0.083
ringe+0.080
 Amen+0.077
bons+0.076
acked+0.073
Neg logit contributions
 the-0.023
 Little-0.022
 but-0.021
 Sam-0.021
 Ben-0.021
Token blue
Token ID4171
Feature activation+9.45e-02

Pos logit contributions
bons+0.120
ringe+0.112
age+0.112
acked+0.104
 cand+0.104
Neg logit contributions
 unless-0.113
 but-0.111
 thunder-0.106
?-0.106
 Tony-0.103
Token a
Token ID257
Feature activation+1.95e-03

Pos logit contributions
bons+0.162
checked+0.159
ages+0.155
age+0.153
ringe+0.152
Neg logit contributions
 but-0.143
?-0.142
!-0.122
,-0.119
 Sam-0.119
Tokenpron
Token ID31186
Feature activation+1.60e-01

Pos logit contributions
bons+0.004
ringe+0.004
age+0.003
checked+0.003
ages+0.003
Neg logit contributions
 but-0.003
?-0.003
 time-0.002
 unless-0.002
 thunder-0.002
Token and
Token ID290
Feature activation+3.54e-02

Pos logit contributions
bons+0.332
age+0.319
ringe+0.318
 cand+0.304
 ham+0.299
Neg logit contributions
 unless-0.181
 thunder-0.163
 Tony-0.160
 but-0.154
 Jay-0.152
Token climbed
Token ID19952
Feature activation-2.99e-02

Pos logit contributions
bons+0.073
age+0.072
ringe+0.072
acked+0.065
cards+0.065
Neg logit contributions
 but-0.039
 unless-0.037
 Little-0.037
 Sam-0.037
 Tony-0.037
Token on
Token ID319
Feature activation+8.72e-03

Pos logit contributions
 but+0.025
 unless+0.025
 behind+0.023
!+0.023
 Tony+0.023
Neg logit contributions
ringe-0.069
age-0.069
bons-0.069
 cand-0.066
ages-0.065
Token a
Token ID257
Feature activation-1.93e-02

Pos logit contributions
bons+0.020
ringe+0.019
age+0.019
 cand+0.018
ages+0.018
Neg logit contributions
 unless-0.008
 but-0.007
 Tony-0.007
 thunder-0.007
 Little-0.007
Token stool
Token ID38753
Feature activation+6.66e-02

Pos logit contributions
 unless+0.030
 but+0.028
 thunder+0.027
 Tony+0.027
 Jay+0.026
Neg logit contributions
bons-0.032
ringe-0.031
age-0.030
 cand-0.029
 ham-0.028
Token
Token ID198
Feature activation-1.52e-02

Pos logit contributions
 unless+0.021
 thunder+0.019
 but+0.019
 Tony+0.019
aph+0.018
Neg logit contributions
bons-0.027
age-0.026
ringe-0.025
 cand-0.024
 ham-0.023
TokenTom
Token ID13787
Feature activation-2.18e-02

Pos logit contributions
 unless+0.018
 but+0.017
 Tony+0.016
 thunder+0.016
 Little+0.015
Neg logit contributions
bons-0.030
ringe-0.030
 cand-0.029
age-0.028
 ham-0.028
Token wore
Token ID12408
Feature activation+4.98e-02

Pos logit contributions
 unless+0.025
 but+0.024
 Tony+0.024
 Little+0.023
 thunder+0.023
Neg logit contributions
bons-0.044
ringe-0.043
age-0.041
 cand-0.040
 ham-0.039
Token his
Token ID465
Feature activation+6.60e-02

Pos logit contributions
bons+0.114
ringe+0.112
age+0.112
 cand+0.107
 ham+0.106
Neg logit contributions
 unless-0.043
 but-0.041
 Tony-0.039
 thunder-0.038
 Little-0.036
Token a
Token ID257
Feature activation+5.65e-03

Pos logit contributions
bons+0.109
ringe+0.103
age+0.099
 cand+0.098
 ham+0.096
Neg logit contributions
 unless-0.103
 Tony-0.095
 thunder-0.094
 but-0.093
 Jay-0.092
Tokenpron
Token ID31186
Feature activation+1.60e-01

Pos logit contributions
bons+0.007
ringe+0.006
age+0.006
 cand+0.006
ages+0.006
Neg logit contributions
 but-0.011
 unless-0.011
 thunder-0.011
?-0.011
 Tony-0.010
Token proudly
Token ID23017
Feature activation+7.47e-02

Pos logit contributions
bons+0.321
age+0.308
ringe+0.307
 cand+0.294
 ham+0.287
Neg logit contributions
 unless-0.191
 thunder-0.173
 Tony-0.171
 but-0.164
 Jay-0.162
Token every
Token ID790
Feature activation-2.19e-02

Pos logit contributions
bons+0.159
ringe+0.153
age+0.152
 cand+0.147
 ham+0.144
Neg logit contributions
 unless-0.079
 thunder-0.072
 Tony-0.071
 but-0.068
 Jay-0.067
Token day
Token ID1110
Feature activation-1.02e-02

Pos logit contributions
 unless+0.030
 but+0.027
 Tony+0.027
 thunder+0.027
 Jay+0.026
Neg logit contributions
bons-0.040
ringe-0.039
age-0.038
 cand-0.037
 ham-0.036
Token.
Token ID13
Feature activation+7.06e-03

Pos logit contributions
 unless+0.011
 thunder+0.010
ulu+0.010
aph+0.009
 Tony+0.009
Neg logit contributions
bons-0.022
age-0.021
ringe-0.020
 cand-0.020
 ham-0.020
Token It
Token ID632
Feature activation+3.35e-02

Pos logit contributions
bons+0.010
ringe+0.010
age+0.010
 cand+0.010
 ham+0.009
Neg logit contributions
 unless-0.012
 but-0.012
 Tony-0.011
 thunder-0.011
 Little-0.011
Token put
Token ID1234
Feature activation+3.70e-02

Pos logit contributions
bons+0.102
ringe+0.098
age+0.094
cards+0.091
 cand+0.090
Neg logit contributions
 but-0.043
 unless-0.040
 Tony-0.039
 Little-0.038
 thunder-0.037
Token on
Token ID319
Feature activation+3.15e-02

Pos logit contributions
age+0.090
bons+0.085
ringe+0.082
ages+0.081
lets+0.080
Neg logit contributions
 but-0.030
 the-0.030
 there-0.028
 Ben-0.028
 Little-0.027
Token a
Token ID257
Feature activation+1.63e-03

Pos logit contributions
age+0.078
ringe+0.074
 Amen+0.072
bons+0.069
cards+0.069
Neg logit contributions
 the-0.026
 but-0.025
 Little-0.024
 thunder-0.024
 Ben-0.023
Token pink
Token ID11398
Feature activation+1.13e-01

Pos logit contributions
bons+0.003
ringe+0.003
age+0.003
checked+0.003
ages+0.003
Neg logit contributions
 but-0.002
?-0.002
 unless-0.002
 thunder-0.002
 behind-0.002
Token a
Token ID257
Feature activation-4.83e-03

Pos logit contributions
bons+0.228
ages+0.222
cards+0.216
ringe+0.214
checked+0.214
Neg logit contributions
 but-0.145
?-0.139
!-0.126
 thunder-0.116
,-0.114
Tokenpron
Token ID31186
Feature activation+1.60e-01

Pos logit contributions
 but+0.007
?+0.006
!+0.006
 thunder+0.006
 unless+0.005
Neg logit contributions
bons-0.010
ringe-0.009
age-0.009
checked-0.009
ages-0.009
Token and
Token ID290
Feature activation+3.21e-02

Pos logit contributions
bons+0.357
ringe+0.345
 cand+0.328
age+0.325
 ham+0.324
Neg logit contributions
 unless-0.155
 but-0.153
 Tony-0.132
 behind-0.127
 thunder-0.127
Token climbed
Token ID19952
Feature activation-2.99e-02

Pos logit contributions
bons+0.069
ringe+0.068
age+0.067
cards+0.062
acked+0.061
Neg logit contributions
 but-0.033
 unless-0.031
 Little-0.031
 Sam-0.030
 Tony-0.030
Token on
Token ID319
Feature activation+1.09e-02

Pos logit contributions
 unless+0.028
 but+0.028
 behind+0.026
!+0.026
 Tony+0.025
Neg logit contributions
ringe-0.066
bons-0.066
age-0.066
 cand-0.063
ages-0.060
Token a
Token ID257
Feature activation-2.15e-02

Pos logit contributions
bons+0.024
ringe+0.023
age+0.023
 cand+0.022
 ham+0.022
Neg logit contributions
 unless-0.011
 but-0.010
 thunder-0.010
 Tony-0.010
 Jay-0.009
Token stool
Token ID38753
Feature activation+6.70e-02

Pos logit contributions
 unless+0.034
 thunder+0.031
 Tony+0.031
 but+0.031
 Jay+0.030
Neg logit contributions
bons-0.035
ringe-0.033
age-0.033
 cand-0.031
 ham-0.031
Token He
Token ID679
Feature activation+2.99e-02

Pos logit contributions
bons+0.022
ringe+0.021
age+0.021
 cand+0.020
 ham+0.019
Neg logit contributions
 unless-0.021
 but-0.020
 thunder-0.019
 Tony-0.019
 Jay-0.018
Token puts
Token ID7584
Feature activation+2.79e-02

Pos logit contributions
bons+0.056
ringe+0.053
age+0.053
 cand+0.051
 ham+0.050
Neg logit contributions
 unless-0.040
 but-0.036
 thunder-0.036
 Tony-0.035
 Jay-0.033
Token on
Token ID319
Feature activation+3.20e-02

Pos logit contributions
bons+0.063
age+0.062
ringe+0.061
 cand+0.058
ages+0.057
Neg logit contributions
 unless-0.025
 but-0.023
 thunder-0.022
 Tony-0.022
 Little-0.021
Token his
Token ID465
Feature activation+6.16e-02

Pos logit contributions
bons+0.076
ringe+0.075
age+0.074
 cand+0.071
 ham+0.070
Neg logit contributions
 unless-0.025
 but-0.023
 thunder-0.022
 Tony-0.022
 Little-0.021
Token a
Token ID257
Feature activation+5.47e-04

Pos logit contributions
bons+0.095
ringe+0.088
age+0.088
acked+0.084
 cand+0.082
Neg logit contributions
 unless-0.101
 but-0.100
 thunder-0.095
?-0.094
 Tony-0.093
Tokenpron
Token ID31186
Feature activation+1.59e-01

Pos logit contributions
bons+0.001
ringe+0.001
checked+0.001
age+0.001
ages+0.001
Neg logit contributions
 but-0.001
 unless-0.001
?-0.001
 thunder-0.001
 behind-0.001
Token and
Token ID290
Feature activation+3.77e-02

Pos logit contributions
bons+0.360
ringe+0.347
age+0.335
 cand+0.332
 ham+0.328
Neg logit contributions
 unless-0.148
 but-0.138
 Tony-0.127
 thunder-0.123
?-0.119
Token hat
Token ID6877
Feature activation+5.14e-02

Pos logit contributions
bons+0.072
age+0.070
ringe+0.069
acked+0.064
 cand+0.064
Neg logit contributions
 unless-0.048
 but-0.045
 thunder-0.045
 Tony-0.044
?-0.043
Token again
Token ID757
Feature activation-5.73e-02

Pos logit contributions
bons+0.126
ringe+0.121
age+0.118
 cand+0.116
 ham+0.115
Neg logit contributions
 unless-0.039
 but-0.036
 Tony-0.032
 thunder-0.031
 either-0.029
Token.
Token ID13
Feature activation+2.90e-02

Pos logit contributions
 unless+0.044
 thunder+0.039
 Tony+0.038
aph+0.036
 Jay+0.036
Neg logit contributions
bons-0.138
age-0.132
ringe-0.132
 cand-0.127
 ham-0.127
Token
Token ID198
Feature activation+1.33e-02

Pos logit contributions
bons+0.044
ringe+0.041
age+0.040
 cand+0.039
 ham+0.038
Neg logit contributions
 unless-0.050
 but-0.047
 Tony-0.046
 thunder-0.046
 Jay-0.044
Token Lily
Token ID20037
Feature activation+1.44e-02

Pos logit contributions
bons+0.027
ringe+0.026
age+0.025
 cand+0.024
 ham+0.023
Neg logit contributions
 unless-0.025
 but-0.023
 Tony-0.023
 thunder-0.022
 Little-0.022
Token wore
Token ID12408
Feature activation+5.49e-02

Pos logit contributions
bons+0.027
ringe+0.026
age+0.026
 cand+0.025
 ham+0.025
Neg logit contributions
 unless-0.019
 thunder-0.017
 but-0.017
 Tony-0.017
 Jay-0.016
Token a
Token ID257
Feature activation+1.92e-02

Pos logit contributions
ringe+0.122
age+0.121
bons+0.121
ages+0.114
acked+0.113
Neg logit contributions
 but-0.051
 thunder-0.048
 unless-0.047
 behind-0.043
 Little-0.043
Token pink
Token ID11398
Feature activation+1.26e-01

Pos logit contributions
bons+0.037
ringe+0.034
cream+0.034
checked+0.033
age+0.033
Neg logit contributions
 but-0.026
 thunder-0.023
?-0.023
 unless-0.022
 time-0.022
Token a
Token ID257
Feature activation+7.38e-03

Pos logit contributions
bons+0.234
ages+0.229
checked+0.225
cream+0.218
cards+0.217
Neg logit contributions
 but-0.184
?-0.168
!-0.157
 unless-0.153
 thunder-0.151
Tokenpron
Token ID31186
Feature activation+1.58e-01

Pos logit contributions
bons+0.015
ringe+0.014
checked+0.014
cream+0.014
ages+0.014
Neg logit contributions
 but-0.010
?-0.008
 time-0.008
 thunder-0.008
!-0.008
Token and
Token ID290
Feature activation+3.17e-02

Pos logit contributions
bons+0.349
ringe+0.337
 cand+0.318
age+0.314
 ham+0.314
Neg logit contributions
 but-0.158
 unless-0.156
 Tony-0.132
?-0.131
 behind-0.130
Token Ben
Token ID3932
Feature activation-2.03e-02

Pos logit contributions
bons+0.069
ringe+0.066
age+0.066
 cand+0.062
acked+0.061
Neg logit contributions
 unless-0.032
 but-0.030
 thunder-0.030
 Tony-0.030
 Little-0.028
Token wore
Token ID12408
Feature activation+5.65e-02

Pos logit contributions
 unless+0.027
 but+0.025
 Tony+0.024
 thunder+0.024
 Jay+0.023
Neg logit contributions
bons-0.038
ringe-0.036
age-0.036
 cand-0.034
 ham-0.033
Token a
Token ID257
Feature activation+1.41e-02

Pos logit contributions
ringe+0.121
age+0.121
bons+0.119
 cand+0.112
checked+0.111
Neg logit contributions
 Tony-0.054
 but-0.052
 thunder-0.051
 unless-0.049
 Little-0.049
Token blue
Token ID4171
Feature activation+9.94e-02

Pos logit contributions
bons+0.029
checked+0.028
ringe+0.027
cream+0.026
age+0.026
Neg logit contributions
 but-0.019
?-0.016
 thunder-0.016
!-0.015
 time-0.015
Tokency
Token ID948
Feature activation+7.93e-02

Pos logit contributions
 unless+0.007
 behind+0.007
?+0.007
 but+0.007
!+0.006
Neg logit contributions
bons-0.017
age-0.017
ringe-0.017
 cand-0.016
 receipt-0.016
Token put
Token ID1234
Feature activation+3.67e-02

Pos logit contributions
bons+0.162
ringe+0.156
age+0.147
 cand+0.144
 ham+0.141
Neg logit contributions
 unless-0.092
 but-0.088
 Tony-0.083
 thunder-0.081
?-0.080
Token on
Token ID319
Feature activation+3.24e-02

Pos logit contributions
age+0.090
bons+0.087
ringe+0.084
checked+0.082
 Amen+0.081
Neg logit contributions
 but-0.027
 the-0.027
 Ben-0.026
 Sam-0.024
 Little-0.024
Token her
Token ID607
Feature activation+7.24e-02

Pos logit contributions
age+0.077
ringe+0.074
 Amen+0.071
bons+0.071
acked+0.068
Neg logit contributions
 the-0.027
 Little-0.027
 thunder-0.026
 but-0.026
 Ben-0.026
Token a
Token ID257
Feature activation-1.67e-03

Pos logit contributions
bons+0.104
ringe+0.097
age+0.095
 cand+0.089
acked+0.088
Neg logit contributions
 unless-0.127
 but-0.123
 thunder-0.120
?-0.116
 Tony-0.116
Tokenpron
Token ID31186
Feature activation+1.58e-01

Pos logit contributions
 but+0.002
 unless+0.002
?+0.002
 thunder+0.002
 behind+0.002
Neg logit contributions
bons-0.003
ringe-0.003
age-0.003
cream-0.003
acked-0.003
Token and
Token ID290
Feature activation+2.93e-02

Pos logit contributions
bons+0.335
ringe+0.322
age+0.310
 cand+0.309
 ham+0.305
Neg logit contributions
 unless-0.169
 but-0.160
 Tony-0.148
 thunder-0.146
?-0.141
Token started
Token ID2067
Feature activation+4.90e-02

Pos logit contributions
bons+0.061
ringe+0.060
age+0.059
acked+0.054
 Amen+0.053
Neg logit contributions
 but-0.032
 unless-0.031
 Sam-0.030
 thunder-0.030
 Little-0.030
Token to
Token ID284
Feature activation+1.24e-02

Pos logit contributions
bons+0.109
ringe+0.108
age+0.104
acked+0.097
 saddle+0.096
Neg logit contributions
 thunder-0.047
 but-0.046
 unless-0.046
 Little-0.042
 the-0.042
Token mix
Token ID5022
Feature activation+5.37e-02

Pos logit contributions
ringe+0.023
bons+0.023
acked+0.023
age+0.023
cards+0.022
Neg logit contributions
 thunder-0.016
 but-0.015
?-0.015
 notice-0.015
 unless-0.015
Token the
Token ID262
Feature activation+3.00e-03

Pos logit contributions
age+0.130
ringe+0.128
bons+0.127
ages+0.117
 saddle+0.117
Neg logit contributions
 unless-0.042
 but-0.041
 thunder-0.035
 Tony-0.035
?-0.035
Token She
Token ID1375
Feature activation+3.90e-02

Pos logit contributions
ringe+0.010
bons+0.010
age+0.009
 cand+0.009
cards+0.009
Neg logit contributions
 but-0.005
 unless-0.005
 Sam-0.005
 Joe-0.004
 Little-0.004
Token put
Token ID1234
Feature activation+3.63e-02

Pos logit contributions
bons+0.089
age+0.085
ringe+0.084
cards+0.079
 cand+0.076
Neg logit contributions
 Tony-0.036
 but-0.036
 unless-0.034
 Little-0.034
 Ben-0.034
Token on
Token ID319
Feature activation+2.66e-02

Pos logit contributions
age+0.095
bons+0.087
ringe+0.087
checked+0.085
ages+0.084
Neg logit contributions
 the-0.027
 Ben-0.026
 but-0.025
 there-0.025
 Sam-0.024
Token her
Token ID607
Feature activation+6.90e-02

Pos logit contributions
age+0.070
ringe+0.066
 Amen+0.064
acked+0.063
cards+0.062
Neg logit contributions
 the-0.020
 Ben-0.018
 thunder-0.018
 Sam-0.018
 Little-0.017
Token a
Token ID257
Feature activation-3.46e-03

Pos logit contributions
bons+0.117
ringe+0.111
age+0.110
 cand+0.103
 ham+0.101
Neg logit contributions
 unless-0.104
 but-0.099
 thunder-0.096
 Tony-0.096
?-0.094
Tokenpron
Token ID31186
Feature activation+1.56e-01

Pos logit contributions
 but+0.005
?+0.004
 unless+0.004
 thunder+0.004
!+0.004
Neg logit contributions
bons-0.007
ringe-0.006
age-0.006
checked-0.006
acked-0.006
Token and
Token ID290
Feature activation+2.70e-02

Pos logit contributions
bons+0.324
ringe+0.311
age+0.306
 cand+0.297
 ham+0.293
Neg logit contributions
 unless-0.176
 but-0.159
 thunder-0.156
 Tony-0.156
 Jay-0.146
Token went
Token ID1816
Feature activation-3.25e-02

Pos logit contributions
bons+0.055
ringe+0.054
age+0.054
acked+0.049
cards+0.049
Neg logit contributions
 unless-0.030
 but-0.029
 Tony-0.028
 Little-0.028
 thunder-0.028
Token into
Token ID656
Feature activation+7.44e-03

Pos logit contributions
 but+0.031
 behind+0.029
 unless+0.029
?+0.027
!+0.027
Neg logit contributions
bons-0.074
ringe-0.071
age-0.070
 cand-0.069
 ham-0.068
Token the
Token ID262
Feature activation-3.04e-03

Pos logit contributions
bons+0.019
ringe+0.018
age+0.018
 cand+0.018
 ham+0.018
Neg logit contributions
 unless-0.005
 but-0.004
 thunder-0.004
 Tony-0.004
 Jay-0.003
Token kitchen
Token ID9592
Feature activation+8.39e-02

Pos logit contributions
 thunder+0.004
 storm+0.004
?+0.004
 Little+0.004
 Ben+0.003
Neg logit contributions
bons-0.006
lets-0.006
ages-0.006
ringe-0.006
age-0.005
Token a
Token ID257
Feature activation+1.38e-02

Pos logit contributions
age+0.087
bons+0.086
ringe+0.086
 cand+0.081
ages+0.080
Neg logit contributions
 unless-0.033
 Tony-0.032
 but-0.032
 thunder-0.032
 Sam-0.030
Token chef
Token ID21221
Feature activation+7.63e-02

Pos logit contributions
bons+0.028
ringe+0.025
age+0.025
checked+0.024
cream+0.023
Neg logit contributions
 but-0.019
?-0.017
 behind-0.017
 unless-0.017
 thunder-0.016
Token hat
Token ID6877
Feature activation+6.78e-02

Pos logit contributions
bons+0.173
ringe+0.160
 cand+0.159
age+0.158
acked+0.155
Neg logit contributions
 unless-0.073
 but-0.073
?-0.066
 Tony-0.065
 behind-0.062
Token and
Token ID290
Feature activation+4.10e-02

Pos logit contributions
bons+0.164
ringe+0.156
 cand+0.151
age+0.150
 ham+0.148
Neg logit contributions
 unless-0.057
 but-0.054
 Tony-0.046
?-0.046
 thunder-0.045
Token a
Token ID257
Feature activation+1.41e-02

Pos logit contributions
bons+0.079
age+0.077
ringe+0.075
acked+0.071
 cand+0.069
Neg logit contributions
 unless-0.052
 but-0.050
 Tony-0.049
 thunder-0.049
?-0.047
Tokenpron
Token ID31186
Feature activation+1.56e-01

Pos logit contributions
bons+0.026
age+0.023
ringe+0.023
acked+0.022
cream+0.022
Neg logit contributions
 but-0.022
 thunder-0.020
?-0.020
 unless-0.019
 Tony-0.019
Token.
Token ID13
Feature activation+4.55e-02

Pos logit contributions
bons+0.397
ringe+0.383
age+0.374
 cand+0.369
 ham+0.364
Neg logit contributions
 unless-0.103
 but-0.089
 Tony-0.082
 thunder-0.081
?-0.075
Token
Token ID198
Feature activation+2.31e-02

Pos logit contributions
bons+0.077
ringe+0.073
age+0.071
 cand+0.068
 ham+0.067
Neg logit contributions
 unless-0.070
 but-0.065
 Tony-0.064
 thunder-0.064
 Jay-0.061
Token
Token ID198
Feature activation+2.07e-02

Pos logit contributions
bons+0.044
ringe+0.042
age+0.042
 cand+0.040
 ham+0.040
Neg logit contributions
 unless-0.030
 thunder-0.027
 but-0.027
 Tony-0.026
 Jay-0.025
Token"
Token ID1
Feature activation+8.74e-02

Pos logit contributions
bons+0.038
ringe+0.037
 cand+0.036
age+0.035
 ham+0.034
Neg logit contributions
 unless-0.028
 but-0.026
 Tony-0.026
?-0.025
 thunder-0.025
TokenI
Token ID40
Feature activation-1.32e-02

Pos logit contributions
bons+0.179
ringe+0.174
age+0.166
 cand+0.156
 presents+0.155
Neg logit contributions
ila-0.092
 but-0.092
 unless-0.091
Little-0.090
 they-0.085
Token She
Token ID1375
Feature activation+3.49e-02

Pos logit contributions
 but+0.001
 unless+0.001
 Little+0.001
 thunder+0.001
 anymore+0.001
Neg logit contributions
ringe-0.001
bons-0.001
age-0.001
 ham-0.001
 cand-0.001
Token put
Token ID1234
Feature activation+3.55e-02

Pos logit contributions
bons+0.082
ringe+0.076
cards+0.074
age+0.073
 cand+0.070
Neg logit contributions
 but-0.031
 Little-0.030
 unless-0.028
?-0.028
 Tony-0.027
Token on
Token ID319
Feature activation+2.89e-02

Pos logit contributions
age+0.081
bons+0.078
ringe+0.076
ages+0.073
 cand+0.072
Neg logit contributions
 but-0.033
 unless-0.031
 Little-0.030
?-0.029
 Ben-0.028
Token an
Token ID281
Feature activation-3.81e-02

Pos logit contributions
age+0.066
ringe+0.065
bons+0.062
 Amen+0.061
acked+0.060
Neg logit contributions
 Little-0.025
 but-0.025
 thunder-0.025
 unless-0.025
 the-0.023
Token a
Token ID257
Feature activation-4.85e-03

Pos logit contributions
 unless+0.058
 but+0.057
 thunder+0.054
?+0.054
 Little+0.052
Neg logit contributions
bons-0.063
ringe-0.063
age-0.061
acked-0.057
 cand-0.056
Tokenpron
Token ID31186
Feature activation+1.56e-01

Pos logit contributions
 but+0.009
 unless+0.008
 thunder+0.008
?+0.008
 Tony+0.008
Neg logit contributions
bons-0.007
ringe-0.007
age-0.006
acked-0.006
checked-0.006
Token so
Token ID523
Feature activation+7.41e-02

Pos logit contributions
bons+0.323
ringe+0.310
age+0.299
 cand+0.296
 ham+0.292
Neg logit contributions
 unless-0.175
 but-0.164
 Tony-0.155
 thunder-0.153
?-0.145
Token she
Token ID673
Feature activation-1.26e-02

Pos logit contributions
bons+0.160
ringe+0.156
age+0.152
 cand+0.146
 ham+0.145
Neg logit contributions
 unless-0.077
 but-0.070
 thunder-0.069
 Tony-0.068
 Little-0.064
Token was
Token ID373
Feature activation+7.71e-03

Pos logit contributions
 unless+0.014
 but+0.013
 Tony+0.013
 thunder+0.013
?+0.012
Neg logit contributions
bons-0.026
ringe-0.025
age-0.024
 cand-0.023
 ham-0.023
Token ready
Token ID3492
Feature activation+5.00e-02

Pos logit contributions
bons+0.016
ringe+0.015
age+0.015
 cand+0.015
 ham+0.014
Neg logit contributions
 unless-0.009
 but-0.008
 thunder-0.008
?-0.008
 Tony-0.007
Token to
Token ID284
Feature activation+1.53e-04

Pos logit contributions
bons+0.077
age+0.071
ringe+0.069
 cand+0.067
 ham+0.066
Neg logit contributions
 unless-0.079
 thunder-0.076
 Tony-0.076
aph-0.075
ulu-0.074
Token She
Token ID1375
Feature activation+2.96e-02

Pos logit contributions
bons+0.004
ringe+0.003
age+0.003
 cand+0.003
 ham+0.003
Neg logit contributions
 unless-0.005
 but-0.004
 thunder-0.004
 Tony-0.004
 Jay-0.004
Token put
Token ID1234
Feature activation+3.28e-02

Pos logit contributions
bons+0.062
ringe+0.058
age+0.057
 cand+0.055
 ham+0.054
Neg logit contributions
 unless-0.034
 but-0.032
 Tony-0.031
 thunder-0.031
 Little-0.030
Token on
Token ID319
Feature activation+2.63e-02

Pos logit contributions
age+0.071
bons+0.070
ringe+0.069
 ham+0.066
ages+0.065
Neg logit contributions
 but-0.032
 unless-0.031
 thunder-0.029
 Little-0.028
?-0.027
Token her
Token ID607
Feature activation+6.70e-02

Pos logit contributions
age+0.054
ringe+0.054
bons+0.053
 ham+0.050
acked+0.049
Neg logit contributions
 unless-0.029
 but-0.027
 thunder-0.027
 Little-0.026
 Tony-0.025
Token a
Token ID257
Feature activation-5.20e-03

Pos logit contributions
bons+0.103
ringe+0.097
age+0.095
 cand+0.092
 ham+0.090
Neg logit contributions
 unless-0.112
 Tony-0.105
 thunder-0.103
 but-0.101
 Jay-0.101
Tokenpron
Token ID31186
Feature activation+1.56e-01

Pos logit contributions
 but+0.008
 unless+0.008
 thunder+0.008
?+0.008
 storm+0.007
Neg logit contributions
bons-0.009
ringe-0.008
age-0.008
acked-0.008
cream-0.007
Token and
Token ID290
Feature activation+2.58e-02

Pos logit contributions
bons+0.320
age+0.309
ringe+0.306
 cand+0.293
 ham+0.286
Neg logit contributions
 unless-0.177
 thunder-0.161
 Tony-0.158
 but-0.150
 Jay-0.150
Token started
Token ID2067
Feature activation+4.37e-02

Pos logit contributions
bons+0.050
ringe+0.049
age+0.048
 cand+0.045
 ham+0.045
Neg logit contributions
 unless-0.032
 but-0.030
 thunder-0.029
 Tony-0.029
 Little-0.028
Token to
Token ID284
Feature activation+8.50e-03

Pos logit contributions
bons+0.084
ringe+0.081
age+0.079
 cand+0.076
 ham+0.075
Neg logit contributions
 unless-0.056
 but-0.052
 thunder-0.052
 Tony-0.051
 Little-0.049
Token clean
Token ID3424
Feature activation+3.84e-02

Pos logit contributions
bons+0.015
ringe+0.015
age+0.014
 cand+0.014
 ham+0.014
Neg logit contributions
 unless-0.012
 but-0.011
 Tony-0.011
 thunder-0.011
 Jay-0.010
Token.
Token ID13
Feature activation+2.00e-03

Pos logit contributions
bons+0.069
ringe+0.063
 cand+0.061
age+0.060
 ham+0.059
Neg logit contributions
 unless-0.056
 Tony-0.051
aph-0.051
 thunder-0.051
ulu-0.050
Token loved
Token ID6151
Feature activation+2.33e-02

Pos logit contributions
bons+0.048
ringe+0.046
age+0.043
 cand+0.043
 ham+0.042
Neg logit contributions
 unless-0.037
 thunder-0.035
 but-0.035
 Tony-0.034
?-0.033
Token wearing
Token ID5762
Feature activation+4.96e-02

Pos logit contributions
age+0.056
ringe+0.056
bons+0.053
acked+0.052
 receipt+0.051
Neg logit contributions
 thunder-0.023
 but-0.019
 storms-0.019
 Sam-0.018
 the-0.018
Token her
Token ID607
Feature activation+7.66e-02

Pos logit contributions
age+0.097
ringe+0.096
bons+0.095
acked+0.090
ages+0.090
Neg logit contributions
 thunder-0.058
 but-0.056
 unless-0.054
 Tony-0.052
 Little-0.052
Token lovely
Token ID14081
Feature activation+6.78e-02

Pos logit contributions
bons+0.115
ringe+0.109
age+0.106
 cand+0.102
 ham+0.100
Neg logit contributions
 unless-0.132
 Tony-0.122
 thunder-0.121
 but-0.121
 Jay-0.117
Token a
Token ID257
Feature activation+3.34e-03

Pos logit contributions
bons+0.114
ringe+0.112
age+0.108
cream+0.104
ages+0.102
Neg logit contributions
 but-0.098
 thunder-0.095
?-0.093
 unless-0.093
!-0.089
Tokenpron
Token ID31186
Feature activation+1.55e-01

Pos logit contributions
bons+0.007
ringe+0.007
checked+0.006
cream+0.006
age+0.006
Neg logit contributions
 but-0.004
?-0.004
!-0.004
 thunder-0.004
 unless-0.004
Token every
Token ID790
Feature activation-1.97e-02

Pos logit contributions
bons+0.324
ringe+0.310
age+0.309
 cand+0.298
 ham+0.292
Neg logit contributions
 unless-0.173
 Tony-0.156
 thunder-0.156
 but-0.151
 Jay-0.147
Token day
Token ID1110
Feature activation-2.71e-03

Pos logit contributions
 unless+0.027
 Tony+0.025
 but+0.025
 thunder+0.024
 Jay+0.024
Neg logit contributions
bons-0.036
ringe-0.034
age-0.034
 cand-0.033
 ham-0.032
Token.
Token ID13
Feature activation-4.86e-03

Pos logit contributions
 unless+0.002
 thunder+0.002
aph+0.002
 Tony+0.002
 Jay+0.002
Neg logit contributions
bons-0.006
age-0.006
 cand-0.006
ringe-0.005
 ham-0.005
Token One
Token ID1881
Feature activation+1.33e-02

Pos logit contributions
 but+0.007
 unless+0.006
?+0.006
 Little+0.006
 Sam+0.006
Neg logit contributions
ringe-0.009
bons-0.009
ages-0.009
age-0.009
 cand-0.008
Token day
Token ID1110
Feature activation+5.91e-03

Pos logit contributions
bons+0.024
age+0.023
ringe+0.022
 cand+0.021
 ham+0.021
Neg logit contributions
 unless-0.019
 Tony-0.017
 but-0.017
 thunder-0.017
 Jay-0.017
Token He
Token ID679
Feature activation+2.19e-02

Pos logit contributions
ringe+0.016
bons+0.015
age+0.015
 cand+0.014
cards+0.014
Neg logit contributions
 but-0.012
 unless-0.012
 Little-0.012
 Sam-0.012
 Tony-0.011
Token put
Token ID1234
Feature activation+3.61e-02

Pos logit contributions
bons+0.048
ringe+0.047
age+0.044
cards+0.043
 receipt+0.042
Neg logit contributions
 but-0.022
 unless-0.021
!-0.020
?-0.020
 forgot-0.019
Token on
Token ID319
Feature activation+2.92e-02

Pos logit contributions
age+0.107
ringe+0.100
bons+0.098
ages+0.097
checked+0.096
Neg logit contributions
 the-0.017
 there-0.012
 but-0.012
 Ben-0.011
 Sam-0.011
Token his
Token ID465
Feature activation+6.08e-02

Pos logit contributions
age+0.079
ringe+0.078
 Amen+0.074
lets+0.073
cards+0.073
Neg logit contributions
 the-0.021
 but-0.015
 Little-0.015
 Sam-0.014
 thunder-0.014
Token a
Token ID257
Feature activation-3.62e-03

Pos logit contributions
bons+0.098
ringe+0.094
age+0.093
acked+0.086
 cand+0.084
Neg logit contributions
 unless-0.095
 but-0.094
 thunder-0.091
?-0.091
 Tony-0.086
Tokenpron
Token ID31186
Feature activation+1.55e-01

Pos logit contributions
 but+0.006
?+0.005
 time+0.005
 thunder+0.005
!+0.005
Neg logit contributions
bons-0.006
ringe-0.006
checked-0.006
age-0.006
acked-0.006
Token and
Token ID290
Feature activation+2.88e-02

Pos logit contributions
bons+0.346
ringe+0.333
 cand+0.318
age+0.316
 ham+0.315
Neg logit contributions
 unless-0.149
 but-0.145
 Tony-0.127
 thunder-0.123
 behind-0.123
Token started
Token ID2067
Feature activation+4.73e-02

Pos logit contributions
ringe+0.061
bons+0.061
age+0.060
acked+0.055
cards+0.055
Neg logit contributions
 but-0.030
 thunder-0.029
 unless-0.029
 Little-0.029
 Sam-0.028
Token to
Token ID284
Feature activation+1.05e-02

Pos logit contributions
ringe+0.106
bons+0.105
age+0.101
 cand+0.093
acked+0.093
Neg logit contributions
 thunder-0.046
 unless-0.043
 but-0.043
!-0.042
 Little-0.042
Token mix
Token ID5022
Feature activation+5.18e-02

Pos logit contributions
ringe+0.020
bons+0.019
age+0.019
acked+0.019
cards+0.018
Neg logit contributions
 thunder-0.014
 but-0.013
 unless-0.013
?-0.013
 notice-0.012
Token the
Token ID262
Feature activation-2.86e-04

Pos logit contributions
age+0.139
ringe+0.137
bons+0.132
 Amen+0.127
ages+0.125
Neg logit contributions
 but-0.031
 unless-0.029
!-0.026
 Tony-0.025
 Little-0.024
Token,
Token ID11
Feature activation-5.26e-02

Pos logit contributions
 unless+0.007
aph+0.007
 thunder+0.006
 Tony+0.006
 expect+0.006
Neg logit contributions
bons-0.013
 cand-0.013
age-0.012
ringe-0.012
 ham-0.012
Token Lily
Token ID20037
Feature activation-1.13e-02

Pos logit contributions
 unless+0.055
 Tony+0.052
 thunder+0.050
 Jay+0.050
 expect+0.047
Neg logit contributions
bons-0.109
 cand-0.107
 ham-0.105
ringe-0.103
 cash-0.101
Token wore
Token ID12408
Feature activation+4.20e-02

Pos logit contributions
 unless+0.013
 but+0.013
 Tony+0.012
 thunder+0.012
 Little+0.012
Neg logit contributions
bons-0.022
ringe-0.022
age-0.021
 cand-0.021
 ham-0.020
Token her
Token ID607
Feature activation+7.25e-02

Pos logit contributions
age+0.098
ringe+0.095
bons+0.094
cream+0.093
acked+0.092
Neg logit contributions
 but-0.034
 thunder-0.032
 unless-0.032
 Sam-0.031
 Little-0.031
Token a
Token ID257
Feature activation+5.61e-03

Pos logit contributions
bons+0.123
ringe+0.117
age+0.113
 cand+0.111
 ham+0.110
Neg logit contributions
 unless-0.109
 Tony-0.100
 thunder-0.100
 but-0.098
 Jay-0.096
Tokenpron
Token ID31186
Feature activation+1.55e-01

Pos logit contributions
bons+0.007
ringe+0.007
age+0.006
cream+0.006
acked+0.006
Neg logit contributions
 but-0.011
 unless-0.011
 thunder-0.010
?-0.010
 Tony-0.010
Token proudly
Token ID23017
Feature activation+7.90e-02

Pos logit contributions
bons+0.290
ringe+0.276
age+0.273
 cand+0.263
 ham+0.258
Neg logit contributions
 unless-0.206
 thunder-0.187
 but-0.186
 Tony-0.186
 Jay-0.176
Token,
Token ID11
Feature activation-4.31e-02

Pos logit contributions
bons+0.175
ringe+0.168
age+0.165
 cand+0.161
 ham+0.159
Neg logit contributions
 unless-0.079
 but-0.071
 Tony-0.068
 thunder-0.068
?-0.063
Token knowing
Token ID6970
Feature activation-3.26e-02

Pos logit contributions
 unless+0.047
 but+0.043
 thunder+0.042
 Tony+0.042
 Jay+0.039
Neg logit contributions
bons-0.091
ringe-0.088
age-0.086
 cand-0.083
 ham-0.082
Token that
Token ID326
Feature activation-2.13e-02

Pos logit contributions
 unless+0.034
 Tony+0.031
 thunder+0.030
 but+0.030
 Jay+0.029
Neg logit contributions
bons-0.068
 cand-0.065
ringe-0.065
age-0.065
 ham-0.063
Token she
Token ID673
Feature activation-3.91e-02

Pos logit contributions
 unless+0.020
 but+0.018
 thunder+0.018
 Tony+0.017
 anyone+0.017
Neg logit contributions
bons-0.049
ringe-0.048
age-0.048
acked-0.045
ages-0.044
Tokenmy
Token ID1820
Feature activation+2.57e-02

Pos logit contributions
bons+0.089
ringe+0.083
age+0.082
 cand+0.078
 ham+0.076
Neg logit contributions
 unless-0.117
 but-0.109
 Tony-0.109
 thunder-0.108
 Jay-0.104
Token put
Token ID1234
Feature activation+3.55e-02

Pos logit contributions
bons+0.051
ringe+0.048
age+0.048
 cand+0.047
 ham+0.047
Neg logit contributions
 unless-0.031
 thunder-0.027
 but-0.027
aph-0.026
 Tony-0.026
Token on
Token ID319
Feature activation+3.47e-02

Pos logit contributions
bons+0.077
age+0.077
ringe+0.076
 cand+0.070
ages+0.070
Neg logit contributions
 but-0.034
 unless-0.033
 Little-0.032
?-0.031
 thunder-0.031
Token her
Token ID607
Feature activation+7.26e-02

Pos logit contributions
ringe+0.077
age+0.077
bons+0.075
ages+0.070
 cand+0.070
Neg logit contributions
 unless-0.032
 but-0.031
 thunder-0.030
 Little-0.030
 Tony-0.030
Token a
Token ID257
Feature activation-2.90e-03

Pos logit contributions
bons+0.129
ringe+0.122
age+0.120
 cand+0.116
 ham+0.114
Neg logit contributions
 unless-0.104
 Tony-0.094
 thunder-0.093
 but-0.092
 anymore-0.091
Tokenpron
Token ID31186
Feature activation+1.55e-01

Pos logit contributions
 unless+0.004
 but+0.004
 thunder+0.004
?+0.003
 Tony+0.003
Neg logit contributions
bons-0.006
ringe-0.005
age-0.005
ages-0.005
 cand-0.005
Token and
Token ID290
Feature activation+2.05e-02

Pos logit contributions
bons+0.333
ringe+0.322
age+0.312
 cand+0.308
 ham+0.303
Neg logit contributions
 unless-0.160
 but-0.147
 Tony-0.141
 thunder-0.139
?-0.133
Token showed
Token ID3751
Feature activation+3.02e-02

Pos logit contributions
bons+0.041
ringe+0.039
age+0.039
 cand+0.037
 ham+0.036
Neg logit contributions
 unless-0.025
 but-0.023
 Tony-0.023
 thunder-0.022
 Little-0.022
Token it
Token ID340
Feature activation+2.14e-02

Pos logit contributions
ringe+0.066
bons+0.064
age+0.063
 ham+0.060
ages+0.060
Neg logit contributions
 unless-0.029
 Little-0.028
 Tony-0.028
 but-0.027
 anyone-0.027
Token to
Token ID284
Feature activation+2.19e-02

Pos logit contributions
ringe+0.047
bons+0.046
age+0.044
 Amen+0.043
 ham+0.043
Neg logit contributions
 unless-0.022
 but-0.022
 Tony-0.021
 Sam-0.020
!-0.020
Token her
Token ID607
Feature activation+4.27e-02

Pos logit contributions
bons+0.044
ringe+0.042
age+0.041
 cand+0.040
 ham+0.040
Neg logit contributions
 unless-0.026
 but-0.023
 thunder-0.023
 Tony-0.023
 anymore-0.022
Token He
Token ID679
Feature activation+4.22e-02

Pos logit contributions
bons+0.102
ringe+0.098
age+0.096
 cand+0.093
 ham+0.092
Neg logit contributions
 unless-0.068
 but-0.062
 Tony-0.061
 thunder-0.061
 Jay-0.058
Token put
Token ID1234
Feature activation+3.81e-02

Pos logit contributions
bons+0.084
ringe+0.080
age+0.079
 cand+0.075
 ham+0.073
Neg logit contributions
 unless-0.052
 but-0.049
 Tony-0.048
 thunder-0.047
 Jay-0.045
Token on
Token ID319
Feature activation+3.45e-02

Pos logit contributions
age+0.099
bons+0.098
ringe+0.094
ages+0.091
 cand+0.091
Neg logit contributions
 unless-0.023
 but-0.022
 Tony-0.020
 Ben-0.019
 behind-0.019
Token the
Token ID262
Feature activation+1.32e-02

Pos logit contributions
age+0.092
bons+0.090
ringe+0.089
ages+0.085
 cand+0.084
Neg logit contributions
 but-0.018
 Sam-0.017
 Tony-0.017
 Ben-0.016
 unless-0.016
Token a
Token ID257
Feature activation-1.59e-03

Pos logit contributions
bons+0.019
ringe+0.018
age+0.018
 cand+0.016
acked+0.016
Neg logit contributions
 unless-0.023
 but-0.022
 thunder-0.022
?-0.021
 Tony-0.021
Tokenpron
Token ID31186
Feature activation+1.55e-01

Pos logit contributions
 but+0.003
?+0.003
 thunder+0.003
 unless+0.003
!+0.003
Neg logit contributions
bons-0.002
ringe-0.002
age-0.002
checked-0.002
acked-0.002
Token and
Token ID290
Feature activation+3.74e-02

Pos logit contributions
bons+0.344
ringe+0.331
age+0.322
 cand+0.317
 ham+0.313
Neg logit contributions
 unless-0.152
 but-0.139
 Tony-0.131
 thunder-0.129
?-0.122
Token picked
Token ID6497
Feature activation+4.43e-02

Pos logit contributions
bons+0.075
age+0.072
ringe+0.072
 cand+0.067
acked+0.065
Neg logit contributions
 unless-0.045
 but-0.042
 thunder-0.041
 Tony-0.041
 Little-0.039
Token up
Token ID510
Feature activation+4.68e-02

Pos logit contributions
bons+0.098
age+0.098
ringe+0.097
 cand+0.089
ages+0.087
Neg logit contributions
 unless-0.043
 Tony-0.042
 but-0.041
 Ben-0.038
 Little-0.038
Token a
Token ID257
Feature activation-8.65e-03

Pos logit contributions
bons+0.106
ringe+0.102
age+0.100
 cand+0.097
 ham+0.096
Neg logit contributions
 unless-0.045
 but-0.039
 thunder-0.039
 Tony-0.039
 Jay-0.035
Token spat
Token ID15246
Feature activation-5.91e-03

Pos logit contributions
 but+0.016
?+0.015
 unless+0.015
 thunder+0.014
!+0.014
Neg logit contributions
bons-0.013
ringe-0.012
age-0.011
checked-0.011
ages-0.011
Token Lily
Token ID20037
Feature activation+2.70e-03

Pos logit contributions
bons+0.005
ringe+0.005
age+0.005
 cand+0.005
 ham+0.004
Neg logit contributions
 unless-0.005
 but-0.005
 Tony-0.005
 thunder-0.005
 Little-0.005
Token put
Token ID1234
Feature activation+3.81e-02

Pos logit contributions
bons+0.005
ringe+0.005
age+0.005
 cand+0.005
 ham+0.005
Neg logit contributions
 unless-0.003
 but-0.003
 Tony-0.003
 thunder-0.003
?-0.003
Token on
Token ID319
Feature activation+3.65e-02

Pos logit contributions
age+0.081
bons+0.080
ringe+0.078
ages+0.074
 cand+0.073
Neg logit contributions
 unless-0.039
 but-0.039
 thunder-0.035
?-0.035
 Little-0.035
Token the
Token ID262
Feature activation+1.42e-02

Pos logit contributions
age+0.078
ringe+0.077
bons+0.076
acked+0.071
ages+0.071
Neg logit contributions
 unless-0.037
 but-0.036
 thunder-0.035
 Tony-0.035
 Little-0.034
Token a
Token ID257
Feature activation-2.78e-03

Pos logit contributions
bons+0.021
ringe+0.020
age+0.020
 cand+0.019
 ham+0.018
Neg logit contributions
 unless-0.024
 but-0.023
 thunder-0.022
 Tony-0.022
?-0.021
Tokenpron
Token ID31186
Feature activation+1.54e-01

Pos logit contributions
 but+0.005
 unless+0.005
?+0.005
 thunder+0.005
 Tony+0.005
Neg logit contributions
bons-0.004
ringe-0.003
age-0.003
ages-0.003
 cand-0.003
Token and
Token ID290
Feature activation+3.06e-02

Pos logit contributions
bons+0.335
ringe+0.323
age+0.313
 cand+0.308
 ham+0.306
Neg logit contributions
 unless-0.158
 but-0.147
 Tony-0.138
 thunder-0.136
?-0.129
Token felt
Token ID2936
Feature activation-1.44e-02

Pos logit contributions
bons+0.059
ringe+0.057
age+0.057
 cand+0.053
 ham+0.052
Neg logit contributions
 unless-0.039
 but-0.036
 thunder-0.036
 Tony-0.035
 Little-0.034
Token very
Token ID845
Feature activation+7.42e-02

Pos logit contributions
 unless+0.020
 Tony+0.018
 but+0.018
 thunder+0.018
 Jay+0.017
Neg logit contributions
bons-0.027
ringe-0.025
age-0.025
 cand-0.024
 ham-0.024
Token proud
Token ID6613
Feature activation+4.01e-02

Pos logit contributions
bons+0.120
age+0.113
ringe+0.112
 cand+0.111
 ham+0.108
Neg logit contributions
 unless-0.112
 Tony-0.106
 thunder-0.104
 but-0.102
aph-0.102
Token of
Token ID286
Feature activation+3.73e-03

Pos logit contributions
bons+0.080
 cand+0.078
 ham+0.075
age+0.074
 presents+0.073
Neg logit contributions
 unless-0.043
aph-0.040
 thunder-0.039
 Tony-0.038
 lur-0.038
Token She
Token ID1375
Feature activation+3.46e-02

Pos logit contributions
ringe+0.009
bons+0.009
age+0.009
 cand+0.008
cards+0.008
Neg logit contributions
 but-0.008
 unless-0.008
 Little-0.008
 Tony-0.007
 Joe-0.007
Token put
Token ID1234
Feature activation+3.35e-02

Pos logit contributions
bons+0.082
ringe+0.076
age+0.074
cards+0.072
 cand+0.069
Neg logit contributions
 but-0.032
 Little-0.032
 Tony-0.031
?-0.029
 forgot-0.029
Token on
Token ID319
Feature activation+2.59e-02

Pos logit contributions
age+0.081
bons+0.078
ringe+0.077
ages+0.073
checked+0.072
Neg logit contributions
 but-0.026
 Little-0.025
 unless-0.025
 thunder-0.023
 Ben-0.023
Token her
Token ID607
Feature activation+6.71e-02

Pos logit contributions
age+0.062
ringe+0.061
bons+0.058
acked+0.056
 Amen+0.056
Neg logit contributions
 Little-0.022
 thunder-0.021
 the-0.020
 but-0.020
 Sam-0.019
Token a
Token ID257
Feature activation-4.95e-03

Pos logit contributions
bons+0.116
ringe+0.110
age+0.108
 cand+0.104
 ham+0.102
Neg logit contributions
 unless-0.099
 but-0.092
 thunder-0.091
 Tony-0.091
 Jay-0.086
Tokenpron
Token ID31186
Feature activation+1.54e-01

Pos logit contributions
 but+0.009
 unless+0.009
?+0.009
 thunder+0.009
 Tony+0.008
Neg logit contributions
bons-0.007
ringe-0.006
age-0.006
acked-0.006
ages-0.006
Token and
Token ID290
Feature activation+2.36e-02

Pos logit contributions
bons+0.332
ringe+0.319
age+0.310
 cand+0.305
 ham+0.302
Neg logit contributions
 unless-0.161
 but-0.150
 Tony-0.142
 thunder-0.140
?-0.132
Token asked
Token ID1965
Feature activation+4.90e-02

Pos logit contributions
bons+0.048
ringe+0.047
age+0.046
acked+0.042
 cand+0.042
Neg logit contributions
 unless-0.027
 but-0.027
 Little-0.026
 Tony-0.026
 thunder-0.025
Token her
Token ID607
Feature activation+5.16e-02

Pos logit contributions
bons+0.093
ringe+0.087
 cand+0.087
age+0.086
 ham+0.085
Neg logit contributions
 unless-0.061
 thunder-0.056
 Tony-0.055
aph-0.054
 but-0.054
Token mum
Token ID25682
Feature activation+2.77e-02

Pos logit contributions
bons+0.093
ringe+0.089
 cand+0.088
 ham+0.088
age+0.087
Neg logit contributions
 unless-0.069
 thunder-0.063
 but-0.061
 anymore-0.059
 Tony-0.059
Token what
Token ID644
Feature activation-5.15e-02

Pos logit contributions
bons+0.067
ringe+0.065
age+0.064
 cand+0.061
 ham+0.060
Neg logit contributions
 unless-0.023
 but-0.020
 Tony-0.019
 thunder-0.019
?-0.017
Token She
Token ID1375
Feature activation+3.71e-02

Pos logit contributions
bons+0.014
ringe+0.014
age+0.013
cream+0.013
cards+0.013
Neg logit contributions
 but-0.012
 unless-0.011
 Sam-0.011
 Little-0.011
 Ben-0.011
Token put
Token ID1234
Feature activation+3.23e-02

Pos logit contributions
bons+0.089
ringe+0.083
age+0.080
cards+0.079
 cand+0.077
Neg logit contributions
 but-0.031
 unless-0.029
?-0.029
 Little-0.028
 thunder-0.028
Token on
Token ID319
Feature activation+2.68e-02

Pos logit contributions
age+0.081
bons+0.078
 saddle+0.075
ringe+0.075
 Amen+0.075
Neg logit contributions
 the-0.024
 but-0.023
 Ben-0.023
 there-0.022
 Sam-0.022
Token her
Token ID607
Feature activation+6.83e-02

Pos logit contributions
age+0.067
ringe+0.066
 Amen+0.064
bons+0.063
cards+0.062
Neg logit contributions
 the-0.020
 thunder-0.018
 but-0.017
 Ben-0.017
 Little-0.017
Token a
Token ID257
Feature activation-4.07e-03

Pos logit contributions
bons+0.119
ringe+0.110
age+0.109
acked+0.102
 cand+0.102
Neg logit contributions
 unless-0.100
 but-0.100
?-0.096
 thunder-0.095
 Tony-0.093
Tokenpron
Token ID31186
Feature activation+1.54e-01

Pos logit contributions
 but+0.005
?+0.004
 unless+0.004
 thunder+0.004
 behind+0.004
Neg logit contributions
bons-0.009
ringe-0.009
age-0.008
acked-0.008
checked-0.008
Token with
Token ID351
Feature activation+2.28e-02

Pos logit contributions
bons+0.313
ringe+0.299
age+0.292
 cand+0.286
 ham+0.281
Neg logit contributions
 unless-0.181
 but-0.166
 Tony-0.161
 thunder-0.160
?-0.151
Token a
Token ID257
Feature activation-4.04e-03

Pos logit contributions
ringe+0.054
age+0.054
bons+0.051
 Amen+0.050
cards+0.048
Neg logit contributions
 thunder-0.019
 Ben-0.018
 the-0.018
 Little-0.018
 Sam-0.018
Token big
Token ID1263
Feature activation+1.32e-02

Pos logit contributions
 but+0.004
?+0.004
 thunder+0.004
!+0.004
 storm+0.004
Neg logit contributions
bons-0.010
ringe-0.009
checked-0.008
acked-0.008
cream-0.008
Token zip
Token ID19974
Feature activation+2.41e-02

Pos logit contributions
bons+0.027
ringe+0.025
age+0.025
cream+0.025
checked+0.024
Neg logit contributions
 but-0.017
 thunder-0.017
?-0.016
 storm-0.016
!-0.015
Token.
Token ID13
Feature activation+6.62e-03

Pos logit contributions
bons+0.051
ringe+0.049
age+0.049
 cand+0.047
 ham+0.046
Neg logit contributions
 unless-0.027
 Tony-0.024
 thunder-0.024
 but-0.023
 Jay-0.022
Token Lily
Token ID20037
Feature activation-6.04e-04

Pos logit contributions
 but+0.007
 unless+0.006
 Little+0.006
 Sam+0.006
 Ben+0.006
Neg logit contributions
bons-0.015
ringe-0.015
age-0.014
ages-0.014
cards-0.014
Token loved
Token ID6151
Feature activation+2.61e-02

Pos logit contributions
 but+0.001
 unless+0.001
 Tony+0.001
 Little+0.001
 thunder+0.001
Neg logit contributions
bons-0.001
ringe-0.001
age-0.001
cards-0.001
 cand-0.001
Token wearing
Token ID5762
Feature activation+4.55e-02

Pos logit contributions
age+0.059
ringe+0.059
bons+0.059
acked+0.055
cards+0.054
Neg logit contributions
 thunder-0.025
 but-0.024
 unless-0.024
 Little-0.022
 Tony-0.022
Token the
Token ID262
Feature activation+1.24e-02

Pos logit contributions
age+0.107
ringe+0.105
bons+0.105
acked+0.101
 cand+0.099
Neg logit contributions
 thunder-0.036
 but-0.035
 unless-0.034
 Tony-0.032
 Little-0.032
Token a
Token ID257
Feature activation+1.22e-03

Pos logit contributions
bons+0.023
ringe+0.022
age+0.022
 cand+0.021
 ham+0.021
Neg logit contributions
 unless-0.016
 but-0.015
 thunder-0.015
 Tony-0.015
?-0.014
Tokenpron
Token ID31186
Feature activation+1.54e-01

Pos logit contributions
bons+0.002
ringe+0.002
age+0.001
cream+0.001
checked+0.001
Neg logit contributions
 but-0.002
?-0.002
 thunder-0.002
 unless-0.002
!-0.002
Token and
Token ID290
Feature activation+1.83e-02

Pos logit contributions
bons+0.319
age+0.308
ringe+0.303
 cand+0.295
 ham+0.287
Neg logit contributions
 unless-0.170
 thunder-0.156
 Tony-0.154
 Jay-0.149
ulu-0.146
Token felt
Token ID2936
Feature activation-1.09e-02

Pos logit contributions
bons+0.037
ringe+0.036
age+0.036
acked+0.033
 cand+0.033
Neg logit contributions
 unless-0.021
 but-0.020
 thunder-0.020
 Tony-0.019
 Little-0.019
Token like
Token ID588
Feature activation+1.84e-02

Pos logit contributions
 unless+0.013
 but+0.012
 thunder+0.012
 Tony+0.012
 Jay+0.011
Neg logit contributions
bons-0.022
ringe-0.021
age-0.020
 cand-0.020
 ham-0.019
Token a
Token ID257
Feature activation-2.17e-02

Pos logit contributions
bons+0.036
 cand+0.034
ringe+0.033
 ham+0.033
age+0.033
Neg logit contributions
 unless-0.023
 Tony-0.020
 but-0.020
aph-0.020
 thunder-0.019
Token real
Token ID1103
Feature activation+1.31e-02

Pos logit contributions
 unless+0.029
 but+0.028
 thunder+0.028
 Tony+0.027
?+0.025
Neg logit contributions
bons-0.041
ringe-0.038
age-0.037
 cand-0.036
acked-0.035
Token,
Token ID11
Feature activation-6.64e-02

Pos logit contributions
bons+0.049
 cand+0.045
 ham+0.044
age+0.044
 presents+0.043
Neg logit contributions
ulu-0.026
 Jas-0.026
 unless-0.026
azy-0.025
ila-0.025
Token but
Token ID475
Feature activation-6.67e-02

Pos logit contributions
 unless+0.064
aph+0.061
 Tony+0.058
azy+0.058
ulu+0.058
Neg logit contributions
bons-0.141
age-0.130
 cand-0.128
 ham-0.126
ringe-0.124
Token sometimes
Token ID3360
Feature activation-1.28e-02

Pos logit contributions
 unless+0.072
 but+0.065
 thunder+0.063
 Tony+0.063
 Jay+0.059
Neg logit contributions
bons-0.142
ringe-0.137
age-0.135
 cand-0.130
 ham-0.129
Token,
Token ID11
Feature activation-6.42e-02

Pos logit contributions
ulu+0.015
aph+0.014
 Jas+0.014
azy+0.014
 unless+0.014
Neg logit contributions
bons-0.023
 cand-0.023
 ham-0.022
 letters-0.021
 packages-0.021
Token the
Token ID262
Feature activation-4.09e-02

Pos logit contributions
 unless+0.065
ulu+0.061
 Tony+0.061
aph+0.061
 Jas+0.061
Neg logit contributions
bons-0.130
 cand-0.121
age-0.117
 ham-0.117
ringe-0.116
Token endings
Token ID38168
Feature activation-1.87e-01

Pos logit contributions
 unless+0.054
 Tony+0.050
 Jay+0.048
 Jas+0.047
 but+0.046
Neg logit contributions
bons-0.077
age-0.074
ringe-0.072
 cand-0.072
 ham-0.071
Token are
Token ID389
Feature activation-2.49e-03

Pos logit contributions
 Tony+0.247
 thunder+0.245
aph+0.241
 unless+0.240
 Little+0.236
Neg logit contributions
bons-0.300
age-0.287
 cand-0.275
 receipt-0.256
 stickers-0.255
Token not
Token ID407
Feature activation-9.82e-02

Pos logit contributions
 unless+0.003
 Tony+0.003
 thunder+0.003
 Jas+0.003
 Jay+0.003
Neg logit contributions
bons-0.005
age-0.004
ringe-0.004
 cand-0.004
 ham-0.004
Token.
Token ID13
Feature activation-2.83e-02

Pos logit contributions
 Tony+0.118
 Jay+0.116
 Jas+0.116
 unless+0.116
ulu+0.112
Neg logit contributions
bons-0.179
age-0.170
 cand-0.167
 ham-0.163
ringe-0.162
Token<|endoftext|>
Token ID50256
Feature activation-2.94e-02

Pos logit contributions
 unless+0.037
 thunder+0.033
 but+0.033
 Tony+0.033
 Jay+0.031
Neg logit contributions
bons-0.054
ringe-0.051
age-0.051
 cand-0.048
 ham-0.048
TokenOnce
Token ID7454
Feature activation-2.73e-02

Pos logit contributions
 unless+0.052
 expect+0.047
 thunder+0.047
 storms+0.046
 forgetting+0.045
Neg logit contributions
bons-0.042
acked-0.040
age-0.039
Here-0.037
 ham-0.037
Token lead
Token ID1085
Feature activation-7.62e-02

Pos logit contributions
 unless+0.013
 Tony+0.012
 thunder+0.012
 but+0.012
 Jay+0.011
Neg logit contributions
bons-0.018
age-0.017
ringe-0.017
 cand-0.016
 ham-0.016
Token to
Token ID284
Feature activation-2.53e-03

Pos logit contributions
 unless+0.108
 thunder+0.105
 Jas+0.104
 echoed+0.104
 Tony+0.103
Neg logit contributions
bons-0.127
age-0.116
ringe-0.113
 cand-0.112
 ham-0.107
Token problems
Token ID2761
Feature activation-6.83e-02

Pos logit contributions
 unless+0.003
 Tony+0.003
 Jay+0.003
 Jas+0.003
azy+0.003
Neg logit contributions
bons-0.004
age-0.004
 cand-0.004
ringe-0.004
 ham-0.004
Token and
Token ID290
Feature activation-2.02e-02

Pos logit contributions
 thunder+0.083
 Jas+0.082
ulu+0.082
aph+0.080
 Tony+0.078
Neg logit contributions
bons-0.127
age-0.118
 cand-0.117
ages-0.113
ringe-0.110
Token bad
Token ID2089
Feature activation-5.14e-02

Pos logit contributions
 unless+0.024
 but+0.021
 thunder+0.021
 Tony+0.021
?+0.019
Neg logit contributions
bons-0.042
ringe-0.040
age-0.039
 cand-0.038
 ham-0.037
Token endings
Token ID38168
Feature activation-1.85e-01

Pos logit contributions
 unless+0.081
ulu+0.079
aph+0.076
azy+0.076
 thunder+0.075
Neg logit contributions
bons-0.078
 cand-0.073
age-0.072
ages-0.070
ringe-0.069
Token.
Token ID13
Feature activation-2.38e-02

Pos logit contributions
aph+0.259
 thunder+0.247
 Tony+0.240
 Little+0.238
 Jas+0.235
Neg logit contributions
age-0.286
 cand-0.282
bons-0.279
 receipt-0.260
ages-0.253
Token<|endoftext|>
Token ID50256
Feature activation-2.69e-02

Pos logit contributions
 unless+0.029
 but+0.027
 thunder+0.026
 Tony+0.026
 Jay+0.025
Neg logit contributions
bons-0.047
ringe-0.045
age-0.044
 cand-0.043
 ham-0.042
TokenThere
Token ID1858
Feature activation-1.38e-02

Pos logit contributions
 unless+0.048
 thunder+0.043
 expect+0.043
 storms+0.042
 forgetting+0.041
Neg logit contributions
bons-0.039
acked-0.037
age-0.036
Here-0.034
 ham-0.033
Token was
Token ID373
Feature activation-1.51e-02

Pos logit contributions
 unless+0.023
 thunder+0.022
aph+0.021
 storms+0.020
ierce+0.020
Neg logit contributions
 cand-0.020
age-0.018
bons-0.018
 ham-0.018
acked-0.017
Token a
Token ID257
Feature activation-3.35e-02

Pos logit contributions
 unless+0.017
 but+0.015
 thunder+0.015
 Tony+0.015
 Jay+0.014
Neg logit contributions
bons-0.032
ringe-0.031
age-0.030
 cand-0.029
 ham-0.029
Token searches
Token ID15455
Feature activation-4.30e-02

Pos logit contributions
ulu+0.027
aph+0.027
 Jas+0.026
 unless+0.026
 Tony+0.025
Neg logit contributions
bons-0.042
 cand-0.041
 ham-0.039
age-0.039
ringe-0.038
Token can
Token ID460
Feature activation-7.78e-03

Pos logit contributions
aph+0.057
 Jas+0.056
ulu+0.053
azy+0.053
 unless+0.053
Neg logit contributions
bons-0.076
 cand-0.072
 presents-0.068
 ham-0.068
 packages-0.068
Token lead
Token ID1085
Feature activation-7.37e-02

Pos logit contributions
 unless+0.011
 Tony+0.010
 Jas+0.010
 thunder+0.010
 Jay+0.010
Neg logit contributions
bons-0.013
age-0.013
ringe-0.013
 cand-0.012
 ham-0.012
Token to
Token ID284
Feature activation+1.91e-03

Pos logit contributions
 unless+0.102
 Jas+0.095
 Tony+0.094
 thunder+0.094
ulu+0.094
Neg logit contributions
bons-0.130
age-0.118
ringe-0.116
 cand-0.114
 ham-0.111
Token happy
Token ID3772
Feature activation+3.74e-02

Pos logit contributions
bons+0.003
 cand+0.003
ringe+0.003
age+0.003
 ham+0.003
Neg logit contributions
 unless-0.002
 Jas-0.002
 Tony-0.002
ulu-0.002
aph-0.002
Token endings
Token ID38168
Feature activation-1.85e-01

Pos logit contributions
bons+0.065
age+0.059
 cand+0.059
ringe+0.057
 ham+0.056
Neg logit contributions
 unless-0.052
ulu-0.051
 Jas-0.050
 Tony-0.050
azy-0.049
Token -
Token ID532
Feature activation-3.63e-02

Pos logit contributions
aph+0.236
 Jas+0.222
 thunder+0.217
 Tony+0.213
 Tyler+0.211
Neg logit contributions
bons-0.324
age-0.315
 cand-0.297
ages-0.279
 presents-0.276
Token but
Token ID475
Feature activation-7.01e-02

Pos logit contributions
 unless+0.039
 Tony+0.035
 thunder+0.035
 Jas+0.034
aph+0.034
Neg logit contributions
bons-0.075
age-0.070
 cand-0.069
ringe-0.068
 ham-0.067
Token sometimes
Token ID3360
Feature activation-1.66e-02

Pos logit contributions
 unless+0.069
 but+0.062
 Tony+0.060
 thunder+0.059
?+0.055
Neg logit contributions
bons-0.159
ringe-0.153
age-0.150
 cand-0.145
 ham-0.143
Token it
Token ID340
Feature activation-1.61e-02

Pos logit contributions
ulu+0.021
 Jas+0.020
aph+0.019
ila+0.019
azy+0.019
Neg logit contributions
bons-0.030
 cand-0.030
 ham-0.028
 packages-0.028
 letters-0.027
Token just
Token ID655
Feature activation-2.04e-02

Pos logit contributions
 Jas+0.026
 unless+0.026
 thunder+0.025
 Tony+0.025
ulu+0.024
Neg logit contributions
age-0.022
bons-0.022
ringe-0.020
 cand-0.020
ages-0.020
Token fighting
Token ID4330
Feature activation-3.61e-02

Pos logit contributions
 unless+0.004
 thunder+0.004
 but+0.004
 Tony+0.004
 Sam+0.004
Neg logit contributions
bons-0.010
ringe-0.010
age-0.010
 cand-0.009
acked-0.009
Token can
Token ID460
Feature activation-8.84e-03

Pos logit contributions
 unless+0.053
 Tony+0.051
 Jay+0.049
 thunder+0.049
 Jas+0.049
Neg logit contributions
bons-0.061
ringe-0.057
age-0.057
 cand-0.054
 ham-0.053
Token lead
Token ID1085
Feature activation-7.22e-02

Pos logit contributions
 unless+0.011
 but+0.010
 thunder+0.010
 Tony+0.009
?+0.009
Neg logit contributions
bons-0.018
ringe-0.017
age-0.017
 cand-0.016
 ham-0.016
Token to
Token ID284
Feature activation+2.66e-03

Pos logit contributions
 unless+0.108
 Tony+0.103
 Jay+0.100
 thunder+0.100
 Jas+0.100
Neg logit contributions
bons-0.121
ringe-0.110
age-0.110
 cand-0.106
 ham-0.103
Token bad
Token ID2089
Feature activation-4.60e-02

Pos logit contributions
bons+0.005
 cand+0.004
ringe+0.004
 ham+0.004
age+0.004
Neg logit contributions
 Tony-0.004
 unless-0.004
 Jay-0.004
ulu-0.004
 Jas-0.003
Token endings
Token ID38168
Feature activation-1.84e-01

Pos logit contributions
 unless+0.075
 Tony+0.069
 but+0.069
 thunder+0.068
 Jay+0.067
Neg logit contributions
bons-0.073
ringe-0.068
age-0.067
 cand-0.065
 ham-0.063
Token.
Token ID13
Feature activation+1.95e-03

Pos logit contributions
aph+0.256
 Tony+0.242
 Little+0.242
 Jay+0.240
 thunder+0.239
Neg logit contributions
bons-0.306
 cand-0.290
age-0.289
ages-0.275
 letters-0.271
Token<|endoftext|>
Token ID50256
Feature activation-9.00e-03

Pos logit contributions
bons+0.004
ringe+0.004
age+0.004
 cand+0.004
 ham+0.004
Neg logit contributions
 unless-0.002
 but-0.002
 Tony-0.002
 thunder-0.002
 Little-0.002
TokenOne
Token ID3198
Feature activation+2.70e-02

Pos logit contributions
 unless+0.016
 thunder+0.015
 expect+0.015
 storms+0.015
iness+0.015
Neg logit contributions
bons-0.013
age-0.012
acked-0.011
ringe-0.011
Here-0.011
Token day
Token ID1110
Feature activation+1.83e-02

Pos logit contributions
bons+0.034
age+0.034
 ham+0.032
 dollar+0.032
 cand+0.030
Neg logit contributions
 unless-0.050
 Jay-0.046
 Jas-0.046
aph-0.045
 Tony-0.044
Token,
Token ID11
Feature activation-1.78e-02

Pos logit contributions
 ham+0.032
 cand+0.032
acked+0.031
bons+0.031
ages+0.031
Neg logit contributions
 unless-0.023
 thunder-0.021
 Jas-0.021
aph-0.020
 expect-0.019
Token will
Token ID481
Feature activation+1.10e-02

Pos logit contributions
 Jas+0.094
aph+0.091
 Tony+0.088
 unless+0.088
ulu+0.087
Neg logit contributions
age-0.111
bons-0.111
 cand-0.106
 receipt-0.101
 presents-0.099
Token never
Token ID1239
Feature activation-7.61e-02

Pos logit contributions
bons+0.019
age+0.018
ringe+0.017
 cand+0.017
 receipt+0.016
Neg logit contributions
 unless-0.016
 Tony-0.015
 Jas-0.015
 thunder-0.015
 Jay-0.015
Token lead
Token ID1085
Feature activation-8.15e-02

Pos logit contributions
 Jas+0.114
 Jay+0.112
 Tony+0.110
 Little+0.108
azy+0.107
Neg logit contributions
age-0.123
 cand-0.116
bons-0.115
 ham-0.108
ringe-0.106
Token to
Token ID284
Feature activation-3.11e-03

Pos logit contributions
 Jas+0.123
 Tony+0.118
ulu+0.118
 Jay+0.118
 unless+0.117
Neg logit contributions
bons-0.129
 cand-0.115
age-0.113
ringe-0.107
 ham-0.106
Token bad
Token ID2089
Feature activation-5.44e-02

Pos logit contributions
 Jas+0.004
 Jay+0.004
 Tony+0.004
azy+0.004
aph+0.004
Neg logit contributions
bons-0.006
 cand-0.005
age-0.005
 ham-0.005
ringe-0.005
Token endings
Token ID38168
Feature activation-1.83e-01

Pos logit contributions
ulu+0.092
 Jas+0.090
azy+0.087
 Jay+0.085
 Tony+0.084
Neg logit contributions
bons-0.081
 cand-0.076
age-0.071
ages-0.067
 ham-0.067
Token.
Token ID13
Feature activation-2.13e-02

Pos logit contributions
aph+0.229
 thunder+0.228
 Jas+0.228
ulu+0.216
 Little+0.214
Neg logit contributions
bons-0.301
age-0.299
 cand-0.289
 ham-0.268
 presents-0.268
Token<|endoftext|>
Token ID50256
Feature activation-2.42e-02

Pos logit contributions
 unless+0.023
 but+0.021
 Tony+0.020
 Little+0.020
 thunder+0.019
Neg logit contributions
bons-0.046
ringe-0.045
 cand-0.043
age-0.043
 ham-0.042
TokenOnce
Token ID7454
Feature activation-2.80e-02

Pos logit contributions
 unless+0.044
 thunder+0.041
 expect+0.041
 storms+0.040
iness+0.039
Neg logit contributions
bons-0.033
acked-0.030
age-0.030
Here-0.029
 ham-0.028
Token upon
Token ID2402
Feature activation-3.35e-03

Pos logit contributions
 thunder+0.046
 echoing+0.045
Run+0.044
 unless+0.044
 resur+0.044
Neg logit contributions
 dollar-0.033
ushes-0.032
 presents-0.031
ossible-0.031
 cand-0.030
Token a
Token ID257
Feature activation-4.68e-02

Pos logit contributions
 unless+0.005
 Tony+0.005
 Jas+0.005
 Jay+0.005
aph+0.005
Neg logit contributions
bons-0.006
age-0.005
 ham-0.005
 cand-0.005
ringe-0.005
Token,
Token ID11
Feature activation-6.28e-02

Pos logit contributions
 unless+0.052
ulu+0.051
 Jas+0.051
 thunder+0.050
aph+0.050
Neg logit contributions
bons-0.063
age-0.060
ringe-0.058
 cand-0.057
ages-0.056
Token there
Token ID612
Feature activation-2.64e-02

Pos logit contributions
 unless+0.066
ulu+0.064
aph+0.064
 Jas+0.063
 thunder+0.061
Neg logit contributions
bons-0.124
 cand-0.115
age-0.114
 ham-0.113
ringe-0.112
Token are
Token ID389
Feature activation-8.36e-04

Pos logit contributions
 unless+0.039
 thunder+0.036
 Jas+0.036
aph+0.036
ulu+0.036
Neg logit contributions
bons-0.043
age-0.040
 cand-0.040
ringe-0.040
 ham-0.038
Token still
Token ID991
Feature activation+2.45e-02

Pos logit contributions
 unless+0.001
 but+0.001
 thunder+0.001
 Tony+0.001
 Jay+0.001
Neg logit contributions
bons-0.002
ringe-0.002
age-0.001
 cand-0.001
 ham-0.001
Token bad
Token ID2089
Feature activation-4.71e-02

Pos logit contributions
bons+0.047
age+0.045
ringe+0.045
 cand+0.043
 ham+0.042
Neg logit contributions
 unless-0.031
 Tony-0.028
 but-0.028
 thunder-0.027
 Jay-0.027
Token endings
Token ID38168
Feature activation-1.83e-01

Pos logit contributions
 unless+0.085
ulu+0.084
 Tony+0.080
aph+0.079
 Jas+0.079
Neg logit contributions
bons-0.065
ringe-0.059
 cand-0.058
age-0.058
 ham-0.055
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
aph+0.278
 Jas+0.243
 gust+0.239
ulu+0.236
 resur+0.231
Neg logit contributions
bons-0.281
age-0.265
 cand-0.262
 presents-0.260
 gifts-0.254
Token<|endoftext|>
Token ID50256
Feature activation-1.89e-02

Pos logit contributions
 unless+0.012
 but+0.011
 Tony+0.011
 thunder+0.011
 Little+0.010
Neg logit contributions
bons-0.022
ringe-0.021
age-0.020
 cand-0.020
 ham-0.019
TokenOnce
Token ID7454
Feature activation-2.20e-02

Pos logit contributions
 unless+0.033
 thunder+0.030
 expect+0.030
 storms+0.029
 but+0.028
Neg logit contributions
bons-0.028
acked-0.026
age-0.026
ringe-0.025
 ham-0.024
Token there
Token ID612
Feature activation-3.01e-03

Pos logit contributions
 thunder+0.035
 unless+0.034
 echoing+0.034
 resur+0.033
Run+0.033
Neg logit contributions
 dollar-0.028
acked-0.026
ushes-0.026
 presents-0.026
ossible-0.026
Token was
Token ID373
Feature activation-1.61e-02

Pos logit contributions
 unless+0.005
 thunder+0.005
aph+0.005
 storms+0.005
iving+0.005
Neg logit contributions
 cand-0.003
bons-0.003
age-0.003
 ham-0.003
acked-0.003
Token Not
Token ID1892
Feature activation-7.13e-02

Pos logit contributions
 unless+0.038
 but+0.035
 Tony+0.035
 Little+0.034
 thunder+0.033
Neg logit contributions
bons-0.053
ringe-0.052
 cand-0.051
age-0.050
 ham-0.048
Token all
Token ID477
Feature activation-1.24e-02

Pos logit contributions
 unless+0.083
 Tony+0.079
 Jas+0.076
 Jay+0.074
 Little+0.073
Neg logit contributions
bons-0.137
 cand-0.132
age-0.128
 ham-0.127
ringe-0.126
Token dreams
Token ID10625
Feature activation-8.44e-02

Pos logit contributions
 Jas+0.015
 unless+0.015
aph+0.015
 Tony+0.015
ulu+0.014
Neg logit contributions
bons-0.023
age-0.022
 cand-0.021
 presents-0.021
 letters-0.020
Token have
Token ID423
Feature activation-9.52e-03

Pos logit contributions
 unless+0.096
 Tony+0.095
aph+0.094
 Jas+0.093
ulu+0.093
Neg logit contributions
bons-0.168
age-0.160
ages-0.148
 cand-0.148
ringe-0.145
Token happy
Token ID3772
Feature activation+4.20e-02

Pos logit contributions
 unless+0.013
 Jas+0.012
aph+0.012
 Tony+0.012
ulu+0.012
Neg logit contributions
bons-0.018
 cand-0.016
age-0.016
 ham-0.015
 presents-0.015
Token endings
Token ID38168
Feature activation-1.82e-01

Pos logit contributions
bons+0.073
 cand+0.066
age+0.066
ringe+0.064
 ham+0.062
Neg logit contributions
 unless-0.062
 Tony-0.058
ulu-0.056
aph-0.056
 Jay-0.056
Token."
Token ID526
Feature activation+3.28e-02

Pos logit contributions
aph+0.270
 Tony+0.262
 Jas+0.260
 thunder+0.251
 Tyler+0.251
Neg logit contributions
bons-0.286
age-0.275
 cand-0.253
ages-0.241
 presents-0.238
Token
Token ID220
Feature activation+2.40e-02

Pos logit contributions
bons+0.052
age+0.048
ringe+0.047
 cand+0.045
 ham+0.045
Neg logit contributions
 unless-0.054
 thunder-0.050
 Tony-0.048
 but-0.048
 expect-0.048
Token
Token ID198
Feature activation-2.52e-02

Pos logit contributions
bons+0.040
age+0.039
ringe+0.037
ages+0.035
acked+0.035
Neg logit contributions
 unless-0.037
 thunder-0.034
 but-0.033
 storms-0.032
 Tony-0.032
Token
Token ID198
Feature activation-2.57e-02

Pos logit contributions
 unless+0.036
 thunder+0.033
 but+0.031
 Tony+0.031
 anymore+0.030
Neg logit contributions
bons-0.045
age-0.043
ringe-0.042
 cand-0.040
 ham-0.040
TokenThe
Token ID464
Feature activation-1.75e-02

Pos logit contributions
 unless+0.033
 but+0.030
 thunder+0.030
 Tony+0.030
 Jay+0.028
Neg logit contributions
bons-0.050
ringe-0.047
age-0.047
 cand-0.045
 ham-0.044
Token Not
Token ID1892
Feature activation-7.72e-02

Pos logit contributions
 unless+0.053
 but+0.049
 Tony+0.049
 thunder+0.048
 Little+0.046
Neg logit contributions
bons-0.070
ringe-0.067
age-0.065
 cand-0.064
 ham-0.062
Token all
Token ID477
Feature activation-2.03e-02

Pos logit contributions
 unless+0.091
 Tony+0.087
 Jas+0.082
 Jay+0.080
 Little+0.080
Neg logit contributions
bons-0.149
 cand-0.141
age-0.139
ringe-0.137
 ham-0.137
Token dreams
Token ID10625
Feature activation-9.04e-02

Pos logit contributions
 unless+0.023
 Jas+0.023
ulu+0.022
aph+0.022
 Tony+0.022
Neg logit contributions
bons-0.040
age-0.036
 cand-0.036
 presents-0.035
 ham-0.035
Token have
Token ID423
Feature activation-1.25e-02

Pos logit contributions
 unless+0.103
 Tony+0.099
 Jas+0.094
aph+0.094
ulu+0.093
Neg logit contributions
bons-0.183
age-0.174
 cand-0.163
ringe-0.163
ages-0.161
Token happy
Token ID3772
Feature activation+3.74e-02

Pos logit contributions
 unless+0.017
 Tony+0.015
 Jas+0.015
ulu+0.015
aph+0.015
Neg logit contributions
bons-0.023
 cand-0.021
age-0.021
 ham-0.020
ringe-0.020
Token endings
Token ID38168
Feature activation-1.82e-01

Pos logit contributions
bons+0.064
age+0.058
 cand+0.058
ringe+0.057
 ham+0.055
Neg logit contributions
 unless-0.056
 Tony-0.052
 but-0.051
 thunder-0.050
ulu-0.050
Token."
Token ID526
Feature activation+2.92e-02

Pos logit contributions
aph+0.246
 Tony+0.243
 thunder+0.238
 Jas+0.238
ulu+0.229
Neg logit contributions
bons-0.315
age-0.298
 cand-0.281
ages-0.267
 presents-0.267
Token
Token ID220
Feature activation+2.40e-02

Pos logit contributions
bons+0.046
age+0.043
ringe+0.042
 ham+0.040
 cand+0.039
Neg logit contributions
 unless-0.047
 thunder-0.044
 Tony-0.042
 but-0.042
 expect-0.042
Token
Token ID198
Feature activation-2.79e-02

Pos logit contributions
bons+0.040
age+0.039
ringe+0.037
ages+0.035
acked+0.035
Neg logit contributions
 unless-0.037
 thunder-0.034
 but-0.033
 storms-0.032
 Tony-0.032
Token
Token ID198
Feature activation-2.88e-02

Pos logit contributions
 unless+0.034
 but+0.031
 thunder+0.031
 Tony+0.031
 Jay+0.029
Neg logit contributions
bons-0.055
ringe-0.053
age-0.052
 cand-0.050
 ham-0.050
TokenThe
Token ID464
Feature activation-1.94e-02

Pos logit contributions
 unless+0.036
 but+0.033
 thunder+0.032
 Tony+0.032
 Jay+0.030
Neg logit contributions
bons-0.057
ringe-0.055
age-0.053
 cand-0.052
 ham-0.051
Token impatient
Token ID33440
Feature activation+1.12e-03

Pos logit contributions
 unless+0.020
 Tony+0.019
 but+0.018
 Jas+0.018
 Jay+0.018
Neg logit contributions
bons-0.029
age-0.028
ringe-0.027
 ham-0.027
 cand-0.027
Token can
Token ID460
Feature activation-6.44e-03

Pos logit contributions
bons+0.002
age+0.002
 cand+0.001
acked+0.001
 dollar+0.001
Neg logit contributions
 Jas-0.002
ulu-0.002
aph-0.002
 Jay-0.002
 resur-0.002
Token lead
Token ID1085
Feature activation-7.03e-02

Pos logit contributions
 unless+0.009
 Tony+0.008
 Jas+0.008
 thunder+0.008
 Jay+0.008
Neg logit contributions
bons-0.011
age-0.011
ringe-0.011
 cand-0.010
 ham-0.010
Token to
Token ID284
Feature activation+5.34e-03

Pos logit contributions
 unless+0.099
 Jas+0.097
ulu+0.095
 Tony+0.094
 echoed+0.094
Neg logit contributions
bons-0.121
age-0.108
ringe-0.105
 cand-0.103
 ham-0.101
Token bad
Token ID2089
Feature activation-4.62e-02

Pos logit contributions
bons+0.009
 cand+0.009
ringe+0.009
age+0.008
 ham+0.008
Neg logit contributions
 Jas-0.007
 unless-0.007
 Jay-0.007
 Tony-0.007
ulu-0.007
Token endings
Token ID38168
Feature activation-1.80e-01

Pos logit contributions
 unless+0.076
ulu+0.071
 Tony+0.071
 but+0.071
 Jas+0.070
Neg logit contributions
bons-0.071
ringe-0.064
age-0.064
 cand-0.063
 ham-0.061
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
aph+0.251
 Jas+0.238
 thunder+0.236
 Little+0.235
 Tony+0.227
Neg logit contributions
bons-0.285
age-0.277
 cand-0.262
ages-0.260
 occasions-0.248
Token Don
Token ID2094
Feature activation-6.33e-02

Pos logit contributions
 unless+0.012
 but+0.011
 Tony+0.011
 Little+0.011
 thunder+0.010
Neg logit contributions
bons-0.021
ringe-0.020
 cand-0.019
age-0.019
 ham-0.019
Tokenâ
Token ID22940
Feature activation-4.26e-02

Pos logit contributions
 unless+0.101
 Tony+0.099
 Jas+0.095
 Jay+0.092
 but+0.092
Neg logit contributions
age-0.100
bons-0.092
ringe-0.083
ages-0.079
 cand-0.078
Token€
Token ID26391
Feature activation-4.87e-03

Pos logit contributions
 unless+0.069
 but+0.064
 Tony+0.064
 thunder+0.063
 Jay+0.061
Neg logit contributions
bons-0.068
ringe-0.064
age-0.064
 cand-0.060
 ham-0.059
Tokenâ„¢
Token ID8151
Feature activation-9.83e-02

Pos logit contributions
 unless+0.008
 thunder+0.008
ulu+0.007
 but+0.007
 Jay+0.007
Neg logit contributions
age-0.008
ages-0.007
bons-0.007
ringe-0.007
lets-0.006
Token scary
Token ID14343
Feature activation-5.06e-02

Pos logit contributions
 unless+0.005
 Tony+0.005
 Jas+0.005
 Jay+0.005
 thunder+0.005
Neg logit contributions
bons-0.011
 cand-0.011
ringe-0.011
 ham-0.011
age-0.011
Token things
Token ID1243
Feature activation-7.03e-02

Pos logit contributions
ulu+0.087
aph+0.086
 Jas+0.085
 unless+0.085
 Tony+0.083
Neg logit contributions
bons-0.070
 cand-0.064
age-0.063
ages-0.060
ringe-0.060
Token can
Token ID460
Feature activation-1.26e-02

Pos logit contributions
 Jas+0.088
 Tony+0.086
 unless+0.085
ulu+0.083
aph+0.082
Neg logit contributions
bons-0.127
 cand-0.121
age-0.119
ringe-0.112
 packages-0.112
Token have
Token ID423
Feature activation-6.09e-03

Pos logit contributions
 unless+0.017
 Tony+0.016
 Jas+0.016
 thunder+0.015
 Jay+0.015
Neg logit contributions
bons-0.022
age-0.022
ringe-0.021
 cand-0.021
 ham-0.020
Token happy
Token ID3772
Feature activation+3.70e-02

Pos logit contributions
 Tony+0.008
 Jas+0.008
 Jay+0.008
 unless+0.008
aph+0.008
Neg logit contributions
bons-0.011
 cand-0.010
age-0.010
 ham-0.009
 presents-0.009
Token endings
Token ID38168
Feature activation-1.79e-01

Pos logit contributions
bons+0.063
 cand+0.059
age+0.055
 ham+0.054
ages+0.054
Neg logit contributions
ulu-0.052
 unless-0.052
aph-0.051
 Tony-0.051
 Jas-0.051
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
aph+0.228
ulu+0.212
 Jas+0.212
 Tony+0.206
 thunder+0.202
Neg logit contributions
bons-0.329
 cand-0.304
age-0.301
 letters-0.288
 packages-0.288
Token<|endoftext|>
Token ID50256
Feature activation-1.89e-02

Pos logit contributions
 unless+0.016
 Tony+0.014
 but+0.014
 Little+0.014
 thunder+0.014
Neg logit contributions
bons-0.024
ringe-0.023
age-0.022
 cand-0.022
 ham-0.021
TokenOnce
Token ID7454
Feature activation-2.23e-02

Pos logit contributions
 unless+0.034
 thunder+0.032
 expect+0.032
 storms+0.031
 forgetting+0.031
Neg logit contributions
bons-0.026
acked-0.024
age-0.023
Here-0.023
 ham-0.022
Token upon
Token ID2402
Feature activation-1.08e-03

Pos logit contributions
 thunder+0.037
 unless+0.035
 echoing+0.035
 resur+0.035
Run+0.034
Neg logit contributions
 dollar-0.027
ossible-0.025
acked-0.025
ushes-0.024
 cand-0.024
Token a
Token ID257
Feature activation-4.41e-02

Pos logit contributions
 unless+0.002
 Tony+0.001
 Jas+0.001
 Jay+0.001
aph+0.001
Neg logit contributions
bons-0.002
age-0.002
 ham-0.002
 cand-0.002
ringe-0.002
Token our
Token ID674
Feature activation+3.84e-02

Pos logit contributions
bons+0.005
 cand+0.005
ringe+0.005
 ham+0.005
age+0.005
Neg logit contributions
 unless-0.002
 Tony-0.002
 Jas-0.002
 Jay-0.002
 thunder-0.002
Token dreams
Token ID10625
Feature activation-8.20e-02

Pos logit contributions
bons+0.064
ringe+0.061
age+0.060
 cand+0.059
 ham+0.057
Neg logit contributions
 unless-0.059
 Tony-0.054
 but-0.054
 thunder-0.053
 Jas-0.052
Token can
Token ID460
Feature activation-7.53e-03

Pos logit contributions
 Tony+0.125
aph+0.118
 Jas+0.117
 Jay+0.116
 unless+0.116
Neg logit contributions
bons-0.137
age-0.136
 cand-0.120
ages-0.116
ringe-0.115
Token have
Token ID423
Feature activation-5.82e-03

Pos logit contributions
 Tony+0.011
 unless+0.011
 Jas+0.011
 Jay+0.010
 Little+0.010
Neg logit contributions
age-0.012
bons-0.012
ringe-0.011
 cand-0.011
 ham-0.010
Token sad
Token ID6507
Feature activation-1.51e-03

Pos logit contributions
 unless+0.008
 Tony+0.008
 Jay+0.008
 Jas+0.007
aph+0.007
Neg logit contributions
bons-0.011
 cand-0.010
age-0.009
 ham-0.009
 presents-0.009
Token endings
Token ID38168
Feature activation-1.76e-01

Pos logit contributions
 Jas+0.002
ulu+0.002
 Tony+0.002
azy+0.002
 Jay+0.002
Neg logit contributions
 cand-0.003
bons-0.003
age-0.003
 ham-0.003
 presents-0.002
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
aph+0.248
 Tony+0.235
 Jas+0.233
ulu+0.231
 Jay+0.223
Neg logit contributions
bons-0.293
age-0.284
 cand-0.280
 presents-0.264
 gifts-0.257
Token<|endoftext|>
Token ID50256
Feature activation-1.13e-02

Pos logit contributions
 unless+0.012
 but+0.011
 Tony+0.011
 thunder+0.011
 Little+0.011
Neg logit contributions
bons-0.022
ringe-0.021
age-0.020
 cand-0.020
 ham-0.019
TokenOnce
Token ID7454
Feature activation-1.77e-02

Pos logit contributions
 unless+0.022
iness+0.021
 thunder+0.021
 storms+0.021
itive+0.021
Neg logit contributions
bons-0.013
age-0.012
acked-0.012
Here-0.011
 ham-0.010
Token upon
Token ID2402
Feature activation+1.79e-03

Pos logit contributions
 thunder+0.025
 unless+0.025
 echoing+0.024
 echoed+0.024
 resur+0.024
Neg logit contributions
 dollar-0.025
 cand-0.024
acked-0.024
 ham-0.024
ushes-0.024
Token a
Token ID257
Feature activation-4.05e-02

Pos logit contributions
bons+0.003
age+0.003
 ham+0.003
ringe+0.003
 cand+0.003
Neg logit contributions
 unless-0.002
 Tony-0.002
 Jay-0.002
 Jas-0.002
aph-0.002
Token and
Token ID290
Feature activation+3.77e-03

Pos logit contributions
 unless+0.064
 Tony+0.057
 thunder+0.056
ulu+0.056
aph+0.055
Neg logit contributions
bons-0.103
age-0.096
ringe-0.095
 cand-0.094
 ham-0.091
Token gave
Token ID2921
Feature activation+2.41e-02

Pos logit contributions
bons+0.007
ringe+0.007
age+0.007
 cand+0.007
 ham+0.007
Neg logit contributions
 unless-0.005
 but-0.004
 thunder-0.004
 Tony-0.004
?-0.004
Token them
Token ID606
Feature activation+1.12e-02

Pos logit contributions
bons+0.050
ringe+0.048
age+0.048
 cand+0.046
 ham+0.045
Neg logit contributions
 unless-0.027
 but-0.025
 Tony-0.025
 thunder-0.024
 Jay-0.023
Token all
Token ID477
Feature activation+3.04e-02

Pos logit contributions
bons+0.022
ringe+0.021
age+0.021
 cand+0.020
 ham+0.019
Neg logit contributions
 unless-0.014
 Tony-0.013
 but-0.013
 thunder-0.013
 Jay-0.012
Token happy
Token ID3772
Feature activation+5.82e-02

Pos logit contributions
bons+0.064
ringe+0.064
age+0.062
 cand+0.060
 ham+0.059
Neg logit contributions
 unless-0.031
 but-0.029
 Tony-0.029
 thunder-0.029
?-0.027
Token endings
Token ID38168
Feature activation-1.75e-01

Pos logit contributions
bons+0.107
 cand+0.100
age+0.097
ringe+0.097
 ham+0.096
Neg logit contributions
 unless-0.081
 Tony-0.072
ulu-0.072
 but-0.071
 thunder-0.070
Token.
Token ID13
Feature activation-1.39e-02

Pos logit contributions
aph+0.237
 Samuel+0.224
 thunder+0.224
 Little+0.221
 Tony+0.218
Neg logit contributions
bons-0.291
age-0.285
 cand-0.273
ages-0.259
 presents-0.253
Token
Token ID220
Feature activation+2.21e-02

Pos logit contributions
 unless+0.019
 but+0.017
 thunder+0.017
 Tony+0.017
 Jay+0.016
Neg logit contributions
bons-0.026
ringe-0.025
age-0.024
 cand-0.023
 ham-0.023
Token
Token ID198
Feature activation-2.70e-02

Pos logit contributions
bons+0.039
age+0.037
ringe+0.036
acked+0.034
ages+0.034
Neg logit contributions
 unless-0.032
 thunder-0.030
 but-0.029
 Tony-0.028
 storms-0.028
Token
Token ID198
Feature activation-2.70e-02

Pos logit contributions
 unless+0.032
 but+0.029
 Tony+0.029
 thunder+0.028
 Jay+0.027
Neg logit contributions
bons-0.055
ringe-0.053
age-0.052
 cand-0.050
 ham-0.050
TokenThen
Token ID6423
Feature activation+1.16e-02

Pos logit contributions
 unless+0.037
 Tony+0.035
 but+0.034
 thunder+0.034
 Little+0.033
Neg logit contributions
bons-0.049
ringe-0.048
 cand-0.046
age-0.045
 ham-0.044
Token her
Token ID607
Feature activation+3.56e-02

Pos logit contributions
bons+0.018
ringe+0.016
age+0.016
 cand+0.016
 ham+0.015
Neg logit contributions
 unless-0.018
ulu-0.017
 Tony-0.017
aph-0.017
azy-0.017
Token tips
Token ID9040
Feature activation-4.91e-02

Pos logit contributions
bons+0.073
age+0.071
ringe+0.070
 cand+0.068
ages+0.067
Neg logit contributions
 unless-0.038
 Tony-0.037
ulu-0.036
 thunder-0.036
 Jas-0.035
Token and
Token ID290
Feature activation-1.48e-02

Pos logit contributions
 unless+0.055
 Tony+0.054
aph+0.053
 Jay+0.053
 Jas+0.053
Neg logit contributions
bons-0.095
age-0.091
ringe-0.085
 cand-0.083
cream-0.081
Token knew
Token ID2993
Feature activation-1.67e-02

Pos logit contributions
 unless+0.017
 but+0.016
 thunder+0.016
 Tony+0.015
?+0.014
Neg logit contributions
bons-0.031
ringe-0.030
age-0.028
acked-0.028
 cand-0.027
Token the
Token ID262
Feature activation-3.39e-02

Pos logit contributions
 unless+0.020
 Tony+0.019
 resur+0.019
 thunder+0.019
ulu+0.019
Neg logit contributions
bons-0.030
cream-0.029
 cand-0.029
age-0.029
ringe-0.027
Token dangers
Token ID16169
Feature activation-1.69e-01

Pos logit contributions
 unless+0.051
 Tony+0.047
 but+0.046
 Jay+0.045
ulu+0.044
Neg logit contributions
bons-0.058
age-0.054
ringe-0.054
 cand-0.052
 ham-0.051
Token of
Token ID286
Feature activation-3.41e-02

Pos logit contributions
 Tony+0.246
aph+0.243
 Jas+0.228
 Jay+0.228
 unless+0.216
Neg logit contributions
bons-0.276
age-0.274
cream-0.256
 cand-0.254
ages-0.241
Token the
Token ID262
Feature activation-4.59e-02

Pos logit contributions
 unless+0.039
ulu+0.037
 Tony+0.036
aph+0.036
 Jay+0.034
Neg logit contributions
bons-0.068
 cand-0.063
ringe-0.061
 ham-0.061
age-0.059
Token world
Token ID995
Feature activation-8.14e-02

Pos logit contributions
 unless+0.062
 Tony+0.059
 Jay+0.057
 Jas+0.056
ulu+0.056
Neg logit contributions
bons-0.083
age-0.078
ringe-0.077
 cand-0.076
 ham-0.075
Token.
Token ID13
Feature activation-1.81e-02

Pos logit contributions
 Tony+0.101
ulu+0.098
 Jay+0.092
aph+0.092
 Jas+0.092
Neg logit contributions
bons-0.154
age-0.153
cream-0.143
ages-0.141
 cand-0.139
Token<|endoftext|>
Token ID50256
Feature activation-1.53e-02

Pos logit contributions
 unless+0.020
 but+0.019
 Tony+0.018
 thunder+0.018
 Little+0.017
Neg logit contributions
bons-0.038
ringe-0.037
age-0.035
 cand-0.035
 ham-0.034
Token warned
Token ID7728
Feature activation-1.94e-02

Pos logit contributions
 unless+0.016
 but+0.015
 Tony+0.015
 thunder+0.015
 Jay+0.014
Neg logit contributions
bons-0.024
ringe-0.023
age-0.023
 cand-0.022
 ham-0.022
Token his
Token ID465
Feature activation+1.43e-02

Pos logit contributions
 unless+0.027
 but+0.025
 thunder+0.025
 Tony+0.024
 Jay+0.023
Neg logit contributions
bons-0.035
ringe-0.034
age-0.033
 cand-0.032
 ham-0.031
Token friends
Token ID2460
Feature activation-5.90e-02

Pos logit contributions
bons+0.023
ringe+0.022
age+0.022
 cand+0.021
 ham+0.020
Neg logit contributions
 unless-0.023
 but-0.021
 thunder-0.021
 Tony-0.021
 Jas-0.020
Token about
Token ID546
Feature activation-7.39e-03

Pos logit contributions
 Jas+0.079
 thunder+0.077
ulu+0.076
 unless+0.075
aph+0.075
Neg logit contributions
age-0.099
bons-0.095
 cand-0.091
ages-0.090
 ham-0.087
Token the
Token ID262
Feature activation-4.37e-02

Pos logit contributions
 unless+0.008
ulu+0.008
aph+0.008
 Jas+0.008
 Tony+0.008
Neg logit contributions
bons-0.014
 cand-0.013
 ham-0.013
ringe-0.013
age-0.013
Token dangers
Token ID16169
Feature activation-1.68e-01

Pos logit contributions
 unless+0.062
 Jas+0.057
 Tony+0.057
 Jay+0.056
ulu+0.055
Neg logit contributions
bons-0.076
age-0.071
 ham-0.070
ringe-0.069
 cand-0.069
Token of
Token ID286
Feature activation-3.51e-02

Pos logit contributions
aph+0.256
 Jas+0.255
 Tony+0.241
 Jay+0.233
 thunder+0.233
Neg logit contributions
bons-0.254
age-0.247
 cand-0.230
cream-0.223
 dollar-0.219
Token them
Token ID606
Feature activation-3.40e-02

Pos logit contributions
 unless+0.040
aph+0.036
ulu+0.035
 Tony+0.035
 Jas+0.035
Neg logit contributions
bons-0.071
 cand-0.064
 ham-0.064
ringe-0.063
age-0.062
Token.
Token ID13
Feature activation-1.97e-02

Pos logit contributions
 Jas+0.041
aph+0.039
ulu+0.038
 Jay+0.037
 Tony+0.037
Neg logit contributions
bons-0.064
age-0.063
 cand-0.062
ages-0.061
 ham-0.058
Token<|endoftext|>
Token ID50256
Feature activation-1.68e-02

Pos logit contributions
 unless+0.026
 thunder+0.024
 but+0.024
 Tony+0.024
 Jay+0.022
Neg logit contributions
bons-0.037
ringe-0.035
age-0.035
 cand-0.033
 ham-0.033
TokenOnce
Token ID7454
Feature activation-2.16e-02

Pos logit contributions
 unless+0.033
 thunder+0.032
 storms+0.031
itive+0.031
 echoing+0.030
Neg logit contributions
bons-0.020
acked-0.019
age-0.018
Here-0.017
 ham-0.017
Token She
Token ID1375
Feature activation+3.65e-02

Pos logit contributions
bons+0.020
ringe+0.018
age+0.018
 ham+0.017
 cand+0.017
Neg logit contributions
 unless-0.026
 thunder-0.024
 Tony-0.024
 but-0.023
 Jay-0.023
Token did
Token ID750
Feature activation+3.71e-02

Pos logit contributions
bons+0.076
ringe+0.073
age+0.072
 cand+0.070
 ham+0.069
Neg logit contributions
 unless-0.041
 but-0.037
 thunder-0.037
 Tony-0.036
 Jay-0.034
Token not
Token ID407
Feature activation-6.27e-02

Pos logit contributions
bons+0.068
age+0.065
ringe+0.065
 cand+0.063
 ham+0.062
Neg logit contributions
 unless-0.046
 Tony-0.045
 Jay-0.044
aph-0.043
 Jas-0.043
Token like
Token ID588
Feature activation+9.60e-04

Pos logit contributions
 unless+0.077
 Tony+0.069
 Jay+0.067
 but+0.067
 Jas+0.066
Neg logit contributions
bons-0.120
age-0.118
ringe-0.115
 cand-0.111
 ham-0.111
Token bad
Token ID2089
Feature activation-3.68e-02

Pos logit contributions
 cand+0.002
bons+0.002
 ham+0.002
 presents+0.002
 cash+0.002
Neg logit contributions
 unless-0.001
 Tony-0.001
aph-0.001
 echoed-0.001
olt-0.001
Token endings
Token ID38168
Feature activation-1.68e-01

Pos logit contributions
 unless+0.066
 Tony+0.063
ulu+0.061
 Jay+0.061
 thunder+0.061
Neg logit contributions
bons-0.050
 cand-0.049
ringe-0.045
 ham-0.044
age-0.044
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
aph+0.277
 Tony+0.261
 Jas+0.253
 Samuel+0.253
ulu+0.252
Neg logit contributions
 cand-0.246
age-0.216
 ham-0.213
bons-0.210
 letters-0.209
Token<|endoftext|>
Token ID50256
Feature activation-6.29e-03

Pos logit contributions
bons+0.018
ringe+0.017
age+0.017
 ham+0.016
 cand+0.016
Neg logit contributions
 unless-0.016
 thunder-0.014
 but-0.014
 Tony-0.014
 anymore-0.014
TokenIt
Token ID1026
Feature activation+2.48e-02

Pos logit contributions
 unless+0.010
 thunder+0.009
 but+0.009
 expect+0.009
 Jas+0.009
Neg logit contributions
bons-0.010
 ham-0.009
ringe-0.009
acked-0.009
age-0.009
Token was
Token ID373
Feature activation-1.63e-02

Pos logit contributions
bons+0.049
ringe+0.047
age+0.046
 cand+0.045
 ham+0.044
Neg logit contributions
 unless-0.031
 but-0.028
 thunder-0.027
 Tony-0.027
 Jay-0.026
Token Lily
Token ID20037
Feature activation-1.42e-02

Pos logit contributions
 thunder+0.014
 unless+0.014
 but+0.014
 Little+0.013
 Tony+0.013
Neg logit contributions
ringe-0.038
bons-0.038
age-0.037
 cand-0.035
ages-0.035
Token You
Token ID921
Feature activation-6.63e-02

Pos logit contributions
 unless+0.081
 but+0.075
 Tony+0.074
 thunder+0.074
 Jay+0.070
Neg logit contributions
bons-0.094
ringe-0.090
age-0.088
 cand-0.085
 ham-0.083
Token don
Token ID836
Feature activation-7.07e-02

Pos logit contributions
 unless+0.095
 Jas+0.092
 Tony+0.092
 thunder+0.089
 Jay+0.086
Neg logit contributions
age-0.112
bons-0.106
ringe-0.103
 cand-0.100
ages-0.100
Token't
Token ID470
Feature activation-6.61e-02

Pos logit contributions
 unless+0.108
 Tony+0.105
 thunder+0.101
 but+0.101
 Jay+0.100
Neg logit contributions
age-0.114
bons-0.113
ringe-0.104
acked-0.099
ages-0.099
Token know
Token ID760
Feature activation-7.53e-04

Pos logit contributions
 unless+0.089
 Tony+0.085
 Jay+0.082
 thunder+0.081
 Jas+0.080
Neg logit contributions
bons-0.119
age-0.118
ringe-0.111
 cand-0.106
 ham-0.103
Token what
Token ID644
Feature activation-7.10e-02

Pos logit contributions
olt+0.001
 Jas+0.001
 resur+0.001
aph+0.001
 notice+0.001
Neg logit contributions
 cand-0.001
 ham-0.001
 presents-0.001
cream-0.001
bons-0.001
Token dangers
Token ID16169
Feature activation-1.67e-01

Pos logit contributions
 Jas+0.110
aph+0.108
ulu+0.103
 unless+0.101
ill+0.101
Neg logit contributions
bons-0.103
age-0.103
ages-0.100
 cand-0.099
 ham-0.099
Token are
Token ID389
Feature activation-1.37e-02

Pos logit contributions
 Jas+0.253
 Tony+0.240
aph+0.236
 Jay+0.226
 Ali+0.215
Neg logit contributions
bons-0.267
age-0.257
 cand-0.245
acked-0.238
 dollar-0.229
Token outside
Token ID2354
Feature activation-3.76e-02

Pos logit contributions
 Jas+0.019
 Jay+0.018
 Tony+0.018
aph+0.018
ulu+0.017
Neg logit contributions
age-0.024
bons-0.023
ages-0.022
 cand-0.022
 letters-0.021
Token!"
Token ID2474
Feature activation+3.49e-02

Pos logit contributions
aph+0.050
 Jas+0.047
 Jay+0.044
 lur+0.043
 thunder+0.043
Neg logit contributions
bons-0.064
age-0.061
 cand-0.059
 presents-0.059
 ham-0.058
Token Buzz
Token ID15753
Feature activation-3.46e-02

Pos logit contributions
bons+0.070
ringe+0.067
age+0.065
 cand+0.063
 ham+0.062
Neg logit contributions
 unless-0.043
 but-0.040
 Tony-0.039
 thunder-0.038
 Jay-0.037
Tokeny
Token ID88
Feature activation+8.18e-02

Pos logit contributions
 unless+0.052
 thunder+0.047
 but+0.047
 Tony+0.046
 Jas+0.045
Neg logit contributions
bons-0.058
age-0.056
ringe-0.056
 cand-0.053
 ham-0.053
Token and
Token ID290
Feature activation+1.65e-02

Pos logit contributions
bons+0.056
ringe+0.052
 cand+0.051
age+0.051
 ham+0.050
Neg logit contributions
 unless-0.031
 thunder-0.030
ulu-0.030
aph-0.029
 Tony-0.029
Token make
Token ID787
Feature activation+6.21e-03

Pos logit contributions
bons+0.033
ringe+0.033
age+0.032
acked+0.032
 cand+0.030
Neg logit contributions
 unless-0.020
 but-0.019
 expect-0.018
 thunder-0.018
 anyone-0.018
Token up
Token ID510
Feature activation+3.89e-02

Pos logit contributions
bons+0.011
ringe+0.011
age+0.011
 cand+0.010
 ham+0.010
Neg logit contributions
 unless-0.009
 but-0.008
 thunder-0.008
 Tony-0.008
 Jay-0.007
Token your
Token ID534
Feature activation+7.08e-02

Pos logit contributions
bons+0.073
ringe+0.068
age+0.068
 cand+0.067
 ham+0.065
Neg logit contributions
 unless-0.050
 Tony-0.046
 thunder-0.045
 but-0.045
 Jay-0.045
Token own
Token ID898
Feature activation+5.52e-02

Pos logit contributions
bons+0.100
ringe+0.097
age+0.094
 cand+0.088
acked+0.088
Neg logit contributions
 unless-0.125
 but-0.119
 thunder-0.118
 Tony-0.115
?-0.113
Token endings
Token ID38168
Feature activation-1.66e-01

Pos logit contributions
bons+0.069
ringe+0.069
age+0.065
 ham+0.062
 cand+0.061
Neg logit contributions
 unless-0.104
 but-0.100
 thunder-0.099
?-0.097
 Tony-0.096
Token too
Token ID1165
Feature activation-1.33e-02

Pos logit contributions
aph+0.219
 Tony+0.206
 Jas+0.204
 Jay+0.202
ulu+0.200
Neg logit contributions
bons-0.292
 cand-0.276
age-0.266
 letters-0.265
 presents-0.264
Token.
Token ID13
Feature activation+6.86e-03

Pos logit contributions
ulu+0.019
 Jas+0.018
aph+0.018
 Tony+0.018
 Jay+0.018
Neg logit contributions
bons-0.021
ages-0.020
age-0.020
 ham-0.020
 cand-0.020
Token What
Token ID1867
Feature activation-5.86e-02

Pos logit contributions
bons+0.012
age+0.012
 cand+0.012
ringe+0.012
acked+0.012
Neg logit contributions
 unless-0.009
 but-0.009
 Tony-0.008
 Sam-0.008
 Little-0.008
Token do
Token ID466
Feature activation+6.89e-03

Pos logit contributions
 unless+0.067
 thunder+0.060
 Tony+0.060
 Jas+0.059
 but+0.059
Neg logit contributions
bons-0.118
ringe-0.111
 cand-0.111
 ham-0.110
age-0.109
Token you
Token ID345
Feature activation-7.14e-02

Pos logit contributions
bons+0.015
ringe+0.014
age+0.014
 cand+0.014
 ham+0.014
Neg logit contributions
 unless-0.007
 thunder-0.006
 Tony-0.006
 but-0.006
 Jay-0.006
Token.
Token ID13
Feature activation-3.52e-02

Pos logit contributions
 unless+0.020
 Tony+0.019
 thunder+0.019
 but+0.018
 Jas+0.018
Neg logit contributions
bons-0.026
age-0.025
ringe-0.025
 cand-0.024
 ham-0.023
Token You
Token ID921
Feature activation-6.03e-02

Pos logit contributions
 unless+0.051
 but+0.047
 thunder+0.047
 Tony+0.047
 Jay+0.045
Neg logit contributions
bons-0.061
ringe-0.058
age-0.057
 cand-0.055
 ham-0.054
Token never
Token ID1239
Feature activation-5.52e-02

Pos logit contributions
 unless+0.084
 Jas+0.081
 thunder+0.080
 Tony+0.078
 Little+0.075
Neg logit contributions
age-0.104
bons-0.099
ringe-0.096
ages-0.091
 cand-0.089
Token know
Token ID760
Feature activation+2.02e-03

Pos logit contributions
 unless+0.072
 Jas+0.071
 Tony+0.068
 Little+0.068
 Jay+0.068
Neg logit contributions
age-0.096
bons-0.093
ringe-0.088
 ham-0.087
 cand-0.086
Token what
Token ID644
Feature activation-6.74e-02

Pos logit contributions
bons+0.003
 ham+0.003
 cand+0.003
cream+0.003
 presents+0.003
Neg logit contributions
 Jas-0.003
olt-0.003
ulu-0.003
 resur-0.002
 notice-0.002
Token dangers
Token ID16169
Feature activation-1.66e-01

Pos logit contributions
 Jas+0.099
aph+0.096
ulu+0.094
 unless+0.089
olt+0.089
Neg logit contributions
bons-0.108
age-0.103
 ham-0.101
 cand-0.100
ages-0.099
Token lur
Token ID20605
Feature activation-1.47e-01

Pos logit contributions
 Jas+0.259
aph+0.227
 Tony+0.227
 thunder+0.214
 Jay+0.214
Neg logit contributions
bons-0.261
age-0.246
 cand-0.235
 dollar-0.233
acked-0.230
Tokenk
Token ID74
Feature activation-4.15e-03

Pos logit contributions
 thunder+0.251
 Jas+0.248
 Little+0.246
 Tony+0.240
 unless+0.239
Neg logit contributions
age-0.209
bons-0.202
ringe-0.200
acked-0.182
ages-0.181
Token around
Token ID1088
Feature activation-2.09e-02

Pos logit contributions
 Jas+0.005
 thunder+0.005
 Jay+0.005
ulu+0.005
 Tony+0.005
Neg logit contributions
age-0.007
bons-0.007
ages-0.007
ringe-0.007
acked-0.006
Token the
Token ID262
Feature activation-3.26e-02

Pos logit contributions
 Jas+0.027
aph+0.025
ulu+0.024
 thunder+0.023
 Jay+0.023
Neg logit contributions
bons-0.039
age-0.034
ringe-0.033
 letters-0.033
 ham-0.032
Token corner
Token ID5228
Feature activation+1.42e-02

Pos logit contributions
 unless+0.051
 but+0.048
 thunder+0.047
 Tony+0.047
 Little+0.045
Neg logit contributions
bons-0.053
ringe-0.051
age-0.050
 cand-0.048
 ham-0.047
Token farmer
Token ID18739
Feature activation-7.35e-03

Pos logit contributions
 unless+0.027
 but+0.025
 thunder+0.025
 Tony+0.024
 Jay+0.023
Neg logit contributions
bons-0.038
ringe-0.036
age-0.036
 cand-0.035
 ham-0.034
Token's
Token ID338
Feature activation+6.45e-02

Pos logit contributions
 unless+0.008
 thunder+0.008
 Tony+0.007
 Jas+0.007
 Jay+0.007
Neg logit contributions
bons-0.015
age-0.014
ringe-0.014
 cand-0.014
 ham-0.014
Token warnings
Token ID14601
Feature activation-9.18e-02

Pos logit contributions
bons+0.112
ringe+0.109
acked+0.103
 cand+0.102
age+0.101
Neg logit contributions
 unless-0.096
 thunder-0.093
 but-0.091
 Tony-0.086
 storms-0.084
Token about
Token ID546
Feature activation-1.13e-02

Pos logit contributions
aph+0.095
 unless+0.095
 Jas+0.094
 Tony+0.093
 thunder+0.092
Neg logit contributions
bons-0.184
age-0.184
 cand-0.169
ages-0.167
ringe-0.166
Token the
Token ID262
Feature activation-4.53e-02

Pos logit contributions
 unless+0.013
aph+0.012
ulu+0.012
 Jas+0.012
 echoed+0.012
Neg logit contributions
bons-0.022
 ham-0.020
 cand-0.020
ringe-0.020
age-0.019
Token dangers
Token ID16169
Feature activation-1.65e-01

Pos logit contributions
 unless+0.064
 but+0.059
 Tony+0.058
 thunder+0.058
 Jay+0.055
Neg logit contributions
bons-0.081
ringe-0.077
age-0.076
 cand-0.073
 ham-0.072
Token outside
Token ID2354
Feature activation-3.44e-02

Pos logit contributions
aph+0.239
 Jas+0.234
 Tony+0.223
 thunder+0.220
 Jay+0.219
Neg logit contributions
bons-0.266
age-0.252
 cand-0.240
cream-0.234
 dollar-0.230
Token of
Token ID286
Feature activation-2.40e-02

Pos logit contributions
aph+0.037
 Jas+0.035
ulu+0.033
 unless+0.033
 Jay+0.032
Neg logit contributions
bons-0.068
age-0.066
 cand-0.063
ringe-0.062
 ham-0.061
Token the
Token ID262
Feature activation-4.45e-02

Pos logit contributions
 unless+0.024
aph+0.023
 Jas+0.022
 echoed+0.022
 Tony+0.022
Neg logit contributions
bons-0.051
 ham-0.046
ringe-0.046
 cand-0.045
age-0.044
Token farm
Token ID5318
Feature activation+1.43e-02

Pos logit contributions
 unless+0.066
 but+0.061
 Tony+0.061
 thunder+0.059
 Jay+0.058
Neg logit contributions
bons-0.077
ringe-0.072
age-0.072
 cand-0.069
 ham-0.068
Token.
Token ID13
Feature activation-1.28e-02

Pos logit contributions
bons+0.031
age+0.031
 cand+0.030
ringe+0.029
 ham+0.029
Neg logit contributions
 unless-0.012
aph-0.012
 Jas-0.012
ulu-0.012
 Tony-0.012
Token something
Token ID1223
Feature activation-6.81e-02

Pos logit contributions
 Jas+0.085
ulu+0.084
 unless+0.082
 echoed+0.081
aph+0.080
Neg logit contributions
bons-0.148
ringe-0.132
 ham-0.131
 cand-0.127
age-0.127
Token without
Token ID1231
Feature activation-7.16e-02

Pos logit contributions
 Jas+0.099
ulu+0.087
 Tony+0.086
aph+0.085
ila+0.083
Neg logit contributions
age-0.104
bons-0.102
 cand-0.102
ages-0.096
 ham-0.093
Token thinking
Token ID3612
Feature activation-5.78e-02

Pos logit contributions
 unless+0.096
ulu+0.091
aph+0.091
 Jas+0.091
 Tony+0.088
Neg logit contributions
bons-0.129
ringe-0.117
 cand-0.116
 ham-0.116
age-0.112
Token about
Token ID546
Feature activation-1.54e-02

Pos logit contributions
aph+0.073
 Jas+0.072
ulu+0.069
 resur+0.066
Run+0.065
Neg logit contributions
bons-0.101
age-0.097
 letters-0.090
 cand-0.088
 dollar-0.087
Token the
Token ID262
Feature activation-5.40e-02

Pos logit contributions
 Jas+0.018
ulu+0.018
 unless+0.018
aph+0.017
olt+0.016
Neg logit contributions
bons-0.030
 ham-0.027
 cand-0.027
age-0.026
ringe-0.026
Token consequences
Token ID6948
Feature activation-1.63e-01

Pos logit contributions
 unless+0.075
 Jas+0.073
 Tony+0.071
 Sam+0.069
 Jake+0.067
Neg logit contributions
bons-0.089
 cand-0.084
age-0.081
 ham-0.080
 saddle-0.078
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
aph+0.245
 Jas+0.229
 thunder+0.224
 storm+0.219
 resur+0.214
Neg logit contributions
bons-0.235
age-0.204
 dollar-0.203
acked-0.195
 cand-0.193
Token Matt
Token ID4705
Feature activation-6.11e-02

Pos logit contributions
 unless+0.022
 Tony+0.020
 but+0.020
 thunder+0.020
 Little+0.019
Neg logit contributions
bons-0.032
ringe-0.031
age-0.030
 cand-0.030
 ham-0.029
Token had
Token ID550
Feature activation+2.93e-02

Pos logit contributions
 unless+0.105
 thunder+0.099
 but+0.097
 Tony+0.096
 Jas+0.096
Neg logit contributions
bons-0.090
age-0.089
ringe-0.084
acked-0.078
ages-0.076
Token no
Token ID645
Feature activation-6.40e-02

Pos logit contributions
bons+0.052
ringe+0.049
age+0.049
 cand+0.047
 ham+0.046
Neg logit contributions
 unless-0.042
 but-0.038
 Tony-0.038
 thunder-0.038
 Jay-0.037
Token idea
Token ID2126
Feature activation-5.54e-04

Pos logit contributions
 unless+0.082
 Tony+0.075
 thunder+0.074
 but+0.074
 Jay+0.072
Neg logit contributions
bons-0.123
ringe-0.116
age-0.115
 cand-0.111
 ham-0.109
Token fix
Token ID4259
Feature activation-7.85e-03

Pos logit contributions
 unless+0.072
 Tony+0.067
 Jay+0.064
 thunder+0.064
 but+0.063
Neg logit contributions
bons-0.102
age-0.098
ringe-0.098
 cand-0.093
 ham-0.091
Token it
Token ID340
Feature activation+2.00e-02

Pos logit contributions
 unless+0.007
 but+0.006
 Tony+0.006
 thunder+0.006
 Jay+0.006
Neg logit contributions
bons-0.018
ringe-0.017
age-0.017
 cand-0.017
 ham-0.017
Token,
Token ID11
Feature activation-5.46e-02

Pos logit contributions
age+0.039
bons+0.038
ringe+0.038
 cand+0.037
 ham+0.035
Neg logit contributions
 Tony-0.022
 Jay-0.022
 Jas-0.022
 lur-0.020
 unless-0.019
Token please
Token ID3387
Feature activation+4.24e-02

Pos logit contributions
 unless+0.079
aph+0.073
 Tony+0.072
 lur+0.072
 Jay+0.072
Neg logit contributions
bons-0.086
 ham-0.085
 cand-0.083
ringe-0.081
age-0.078
Token?"
Token ID1701
Feature activation+3.66e-02

Pos logit contributions
bons+0.092
ringe+0.090
age+0.087
 ham+0.086
 cand+0.085
Neg logit contributions
 unless-0.040
 Tony-0.037
 thunder-0.035
 Jay-0.035
aph-0.035
Token Her
Token ID2332
Feature activation+8.20e-02

Pos logit contributions
bons+0.055
ringe+0.052
age+0.050
 cand+0.048
 ham+0.047
Neg logit contributions
 unless-0.064
 but-0.062
 Tony-0.060
 thunder-0.060
 Little-0.058
Token mom
Token ID1995
Feature activation+4.66e-02

Pos logit contributions
bons+0.146
ringe+0.143
age+0.138
 cand+0.136
 ham+0.133
Neg logit contributions
 unless-0.117
 Tony-0.104
 but-0.102
 thunder-0.102
 Jay-0.099
Token looked
Token ID3114
Feature activation+2.64e-02

Pos logit contributions
bons+0.094
ringe+0.089
age+0.087
 cand+0.083
ages+0.081
Neg logit contributions
 unless-0.057
 but-0.056
 thunder-0.052
 Tony-0.052
?-0.050
Token at
Token ID379
Feature activation+3.39e-02

Pos logit contributions
bons+0.062
ringe+0.060
age+0.059
 cand+0.057
 ham+0.056
Neg logit contributions
 unless-0.024
 but-0.021
 thunder-0.020
 Tony-0.020
?-0.019
Token the
Token ID262
Feature activation+1.38e-03

Pos logit contributions
bons+0.061
Here+0.054
 ham+0.053
 cand+0.053
ringe+0.053
Neg logit contributions
 unless-0.045
 resur-0.044
aph-0.044
iving-0.043
 sur-0.043
Token broken
Token ID5445
Feature activation+2.37e-02

Pos logit contributions
bons+0.002
ringe+0.002
ages+0.002
acked+0.002
age+0.002
Neg logit contributions
 but-0.002
 unless-0.002
 anymore-0.002
 thunder-0.002
 either-0.002
Token and
Token ID290
Feature activation+1.58e-02

Pos logit contributions
bons+0.057
ringe+0.054
age+0.054
 cand+0.054
 ham+0.052
Neg logit contributions
 unless-0.031
 thunder-0.029
 Tony-0.029
 Jas-0.028
 Jay-0.027
Token ran
Token ID4966
Feature activation-3.33e-02

Pos logit contributions
bons+0.029
ringe+0.028
age+0.028
 cand+0.027
 ham+0.026
Neg logit contributions
 unless-0.021
 but-0.019
 Tony-0.019
 thunder-0.019
 Jay-0.018
Token to
Token ID284
Feature activation+2.50e-02

Pos logit contributions
 but+0.035
 unless+0.035
 behind+0.032
 Tony+0.032
!+0.032
Neg logit contributions
bons-0.071
ringe-0.070
age-0.067
 ham-0.067
 cand-0.067
Token her
Token ID607
Feature activation+5.06e-02

Pos logit contributions
bons+0.052
ringe+0.050
age+0.048
 ham+0.047
 cand+0.047
Neg logit contributions
 unless-0.027
 anymore-0.023
 thunder-0.023
iness-0.023
 Tony-0.023
Token mom
Token ID1995
Feature activation+1.93e-02

Pos logit contributions
bons+0.090
ringe+0.086
age+0.085
 cand+0.082
 ham+0.081
Neg logit contributions
 unless-0.073
 but-0.066
 thunder-0.066
 Tony-0.066
 Jay-0.063
Token's
Token ID338
Feature activation+7.81e-02

Pos logit contributions
bons+0.042
ringe+0.040
age+0.040
 cand+0.039
 ham+0.038
Neg logit contributions
 unless-0.021
 but-0.020
 Tony-0.018
?-0.017
 Little-0.017
Token room
Token ID2119
Feature activation+6.68e-02

Pos logit contributions
bons+0.141
age+0.129
ringe+0.128
cream+0.125
acked+0.123
Neg logit contributions
 but-0.112
 unless-0.112
 thunder-0.106
 Tony-0.103
 Little-0.103
Token.
Token ID13
Feature activation+6.31e-03

Pos logit contributions
bons+0.141
age+0.138
ringe+0.136
 cand+0.135
 ham+0.132
Neg logit contributions
 unless-0.066
 thunder-0.061
 Tony-0.061
 Jay-0.059
aph-0.058
Token "
Token ID366
Feature activation+4.43e-02

Pos logit contributions
bons+0.012
ringe+0.012
age+0.011
 cand+0.010
cards+0.010
Neg logit contributions
 but-0.009
 Little-0.009
 unless-0.009
 Sam-0.008
 Ben-0.008
TokenMom
Token ID29252
Feature activation+4.43e-02

Pos logit contributions
bons+0.068
ages+0.068
ringe+0.068
cards+0.066
 cand+0.066
Neg logit contributions
Little-0.067
 unless-0.066
 thunder-0.066
 Little-0.065
 but-0.065
Tokenmy
Token ID1820
Feature activation+1.48e-02

Pos logit contributions
bons+0.082
ringe+0.079
age+0.078
 cand+0.076
 ham+0.075
Neg logit contributions
 unless-0.059
 thunder-0.053
 Tony-0.052
 but-0.051
aph-0.050
Token listen
Token ID6004
Feature activation-2.99e-02

Pos logit contributions
ringe+0.024
bons+0.023
acked+0.023
cards+0.023
cream+0.022
Neg logit contributions
 but-0.014
?-0.014
 unless-0.013
 thunder-0.013
 Sam-0.012
Token and
Token ID290
Feature activation+2.97e-03

Pos logit contributions
 unless+0.041
 Tony+0.038
 thunder+0.037
 but+0.037
 Jay+0.036
Neg logit contributions
bons-0.054
ringe-0.051
age-0.051
 cand-0.049
 ham-0.048
Token share
Token ID2648
Feature activation+6.45e-02

Pos logit contributions
bons+0.007
ringe+0.006
acked+0.006
heddar+0.006
age+0.006
Neg logit contributions
 but-0.003
 unless-0.003
?-0.003
 thunder-0.003
 Sam-0.003
Token.
Token ID13
Feature activation+3.19e-02

Pos logit contributions
bons+0.152
ringe+0.147
age+0.146
 cand+0.140
 ham+0.139
Neg logit contributions
 unless-0.055
 but-0.048
 thunder-0.046
 Tony-0.046
?-0.042
Token She
Token ID1375
Feature activation+4.80e-02

Pos logit contributions
bons+0.046
ringe+0.044
age+0.042
 ham+0.042
 cand+0.041
Neg logit contributions
 unless-0.054
 thunder-0.050
 Tony-0.049
 expect-0.048
aph-0.048
Token also
Token ID635
Feature activation+1.24e-01

Pos logit contributions
bons+0.098
ringe+0.094
age+0.092
 cand+0.088
 ham+0.086
Neg logit contributions
 unless-0.056
 but-0.052
 Tony-0.051
 thunder-0.050
?-0.048
Token said
Token ID531
Feature activation+4.52e-02

Pos logit contributions
bons+0.240
ringe+0.228
age+0.223
 cand+0.213
 ham+0.209
Neg logit contributions
 unless-0.161
 but-0.150
 Tony-0.145
 thunder-0.144
?-0.141
Token they
Token ID484
Feature activation-1.58e-02

Pos logit contributions
 cand+0.097
 ham+0.090
bons+0.087
 cash+0.084
 letters+0.083
Neg logit contributions
 unless-0.046
aph-0.044
?!-0.041
 Tony-0.040
 behind-0.038
Token had
Token ID550
Feature activation+3.74e-02

Pos logit contributions
 unless+0.013
 but+0.013
 either+0.011
 anymore+0.011
 anyone+0.011
Neg logit contributions
bons-0.038
ringe-0.036
age-0.035
 ham-0.034
 cand-0.034
Token to
Token ID284
Feature activation+2.02e-02

Pos logit contributions
bons+0.073
ringe+0.071
age+0.070
acked+0.065
 cand+0.065
Neg logit contributions
 unless-0.047
 but-0.044
 thunder-0.044
 Tony-0.043
?-0.041
Token be
Token ID307
Feature activation+6.80e-04

Pos logit contributions
bons+0.038
ringe+0.037
age+0.035
 cand+0.035
acked+0.034
Neg logit contributions
 unless-0.026
 but-0.025
 thunder-0.024
 Tony-0.024
?-0.024
Token bird
Token ID6512
Feature activation-2.94e-02

Pos logit contributions
bons+0.062
age+0.057
ringe+0.056
 cand+0.053
 ham+0.051
Neg logit contributions
 unless-0.081
 Tony-0.076
 but-0.072
 Jay-0.071
 expect-0.070
Token agreed
Token ID4987
Feature activation+4.91e-02

Pos logit contributions
 unless+0.032
 but+0.031
 Tony+0.028
 thunder+0.028
!+0.027
Neg logit contributions
bons-0.062
ringe-0.060
age-0.057
 cand-0.056
 ham-0.056
Token,
Token ID11
Feature activation-3.83e-02

Pos logit contributions
age+0.088
bons+0.088
 cand+0.088
ages+0.082
 ham+0.081
Neg logit contributions
aph-0.060
 unless-0.059
ulu-0.058
 thunder-0.058
azy-0.058
Token and
Token ID290
Feature activation+1.25e-02

Pos logit contributions
 unless+0.041
 thunder+0.036
 Tony+0.036
?+0.035
aph+0.035
Neg logit contributions
bons-0.080
age-0.076
ringe-0.076
 cand-0.075
 ham-0.073
Token they
Token ID484
Feature activation-1.63e-02

Pos logit contributions
bons+0.030
ringe+0.028
age+0.028
 cand+0.028
 ham+0.028
Neg logit contributions
 unless-0.010
 thunder-0.008
 Tony-0.008
 but-0.008
?-0.008
Token both
Token ID1111
Feature activation+7.48e-02

Pos logit contributions
 unless+0.019
 Tony+0.018
 but+0.018
 thunder+0.017
 Jay+0.017
Neg logit contributions
bons-0.032
ringe-0.032
age-0.031
 cand-0.029
 ham-0.029
Token lived
Token ID5615
Feature activation-1.53e-02

Pos logit contributions
bons+0.130
ringe+0.123
age+0.123
 cand+0.118
 ham+0.116
Neg logit contributions
 unless-0.111
 but-0.101
 thunder-0.100
 Tony-0.098
 Jay-0.094
Token happily
Token ID18177
Feature activation+3.74e-02

Pos logit contributions
 unless+0.025
 but+0.024
 thunder+0.023
 Tony+0.023
 Jay+0.022
Neg logit contributions
bons-0.024
ringe-0.023
age-0.022
 cand-0.021
 ham-0.021
Token ever
Token ID1683
Feature activation-3.95e-02

Pos logit contributions
bons+0.083
ringe+0.079
age+0.079
 cand+0.077
 ham+0.076
Neg logit contributions
 unless-0.037
 but-0.033
 Tony-0.032
 thunder-0.032
 Jay-0.030
Token after
Token ID706
Feature activation-2.46e-02

Pos logit contributions
 unless+0.041
 thunder+0.037
 Tony+0.037
 but+0.036
 Jay+0.035
Neg logit contributions
bons-0.084
ringe-0.081
age-0.080
 cand-0.078
 ham-0.078
Token,
Token ID11
Feature activation-6.50e-02

Pos logit contributions
aph+0.034
ulu+0.031
 Jas+0.031
 unless+0.031
 Tony+0.031
Neg logit contributions
bons-0.042
 cand-0.039
ages-0.037
 presents-0.036
age-0.036
Token and
Token ID290
Feature activation+1.53e-02

Pos logit contributions
 unless+0.035
 Tony+0.031
 thunder+0.030
aph+0.029
 Jay+0.029
Neg logit contributions
bons-0.077
ringe-0.073
 cand-0.073
 ham-0.072
age-0.071
Token the
Token ID262
Feature activation-5.52e-03

Pos logit contributions
bons+0.034
ringe+0.033
age+0.033
 cand+0.031
 ham+0.031
Neg logit contributions
 unless-0.015
 but-0.013
 thunder-0.013
 Tony-0.013
 Jay-0.012
Token people
Token ID661
Feature activation-8.33e-02

Pos logit contributions
 unless+0.008
 but+0.008
 thunder+0.008
 Tony+0.008
?+0.007
Neg logit contributions
bons-0.009
ringe-0.009
age-0.009
acked-0.008
 cand-0.008
Token.
Token ID13
Feature activation+2.73e-02

Pos logit contributions
 unless+0.061
 but+0.053
 Tony+0.050
 thunder+0.050
 Jay+0.045
Neg logit contributions
bons-0.206
ringe-0.199
age-0.196
 cand-0.190
 ham-0.188
Token She
Token ID1375
Feature activation+4.37e-02

Pos logit contributions
bons+0.040
ringe+0.037
age+0.036
 ham+0.035
 cand+0.035
Neg logit contributions
 unless-0.048
 thunder-0.044
 Tony-0.043
 but-0.043
 expect-0.042
Token also
Token ID635
Feature activation+1.21e-01

Pos logit contributions
bons+0.083
ringe+0.080
age+0.079
 cand+0.076
 ham+0.075
Neg logit contributions
 unless-0.057
 but-0.052
 thunder-0.051
 Tony-0.051
 Jay-0.048
Token taught
Token ID7817
Feature activation+3.01e-02

Pos logit contributions
bons+0.208
ringe+0.197
age+0.194
 cand+0.188
 ham+0.185
Neg logit contributions
 unless-0.180
 thunder-0.164
 but-0.164
 Tony-0.163
 Jay-0.156
Token them
Token ID606
Feature activation+7.10e-03

Pos logit contributions
bons+0.057
 cand+0.052
ringe+0.051
 ham+0.051
age+0.049
Neg logit contributions
 unless-0.041
 but-0.035
 thunder-0.034
?-0.034
?!-0.034
Token some
Token ID617
Feature activation+2.15e-02

Pos logit contributions
bons+0.014
ringe+0.014
age+0.013
 cand+0.013
 ham+0.013
Neg logit contributions
 unless-0.009
 but-0.008
 thunder-0.008
 Tony-0.008
 Jay-0.007
Token words
Token ID2456
Feature activation-3.71e-02

Pos logit contributions
bons+0.033
ringe+0.031
age+0.030
 cand+0.029
 ham+0.028
Neg logit contributions
 unless-0.036
 but-0.034
 thunder-0.034
 Tony-0.034
 Jay-0.032
Token in
Token ID287
Feature activation+5.08e-03

Pos logit contributions
 unless+0.033
 but+0.029
 Tony+0.028
 thunder+0.028
 Jay+0.026
Neg logit contributions
bons-0.086
ringe-0.083
age-0.082
 cand-0.079
 ham-0.078
Token,
Token ID11
Feature activation-3.29e-02

Pos logit contributions
bons+0.026
ringe+0.025
age+0.025
 cand+0.024
 ham+0.024
Neg logit contributions
 unless-0.015
 thunder-0.014
 Tony-0.014
ulu-0.013
 storms-0.013
Token but
Token ID475
Feature activation-3.87e-02

Pos logit contributions
 unless+0.022
aph+0.021
iness+0.021
azy+0.020
olt+0.019
Neg logit contributions
bons-0.071
 ham-0.071
 cand-0.071
age-0.070
 saddle-0.068
Token she
Token ID673
Feature activation-9.76e-03

Pos logit contributions
 unless+0.048
 thunder+0.040
aph+0.040
 anymore+0.040
?!+0.039
Neg logit contributions
bons-0.071
ringe-0.070
 ham-0.069
age-0.068
 cand-0.067
Token was
Token ID373
Feature activation+7.40e-03

Pos logit contributions
 unless+0.013
 thunder+0.012
 storms+0.011
 but+0.011
 Tony+0.011
Neg logit contributions
age-0.017
ringe-0.017
bons-0.017
 ham-0.016
 cand-0.016
Token shy
Token ID15800
Feature activation-9.04e-03

Pos logit contributions
bons+0.012
age+0.012
ringe+0.012
 ham+0.012
 saddle+0.011
Neg logit contributions
 unless-0.009
iness-0.009
 Tony-0.009
aph-0.008
 Little-0.008
Token.
Token ID13
Feature activation+1.56e-02

Pos logit contributions
Little+0.013
ulu+0.013
aph+0.013
 drown+0.012
azy+0.012
Neg logit contributions
 ham-0.013
 cand-0.013
lets-0.012
age-0.012
 presents-0.012
Token
Token ID220
Feature activation+3.57e-02

Pos logit contributions
bons+0.023
ringe+0.022
age+0.021
 ham+0.020
 cand+0.020
Neg logit contributions
 unless-0.027
 thunder-0.025
 Tony-0.024
 but-0.024
 expect-0.023
Token
Token ID198
Feature activation-1.10e-02

Pos logit contributions
bons+0.056
age+0.054
ringe+0.052
acked+0.050
ages+0.049
Neg logit contributions
 unless-0.056
 thunder-0.053
 storm-0.050
 storms-0.050
 resur-0.049
Token
Token ID198
Feature activation-1.18e-02

Pos logit contributions
 unless+0.015
 thunder+0.013
 but+0.013
 Tony+0.013
 anymore+0.012
Neg logit contributions
bons-0.021
age-0.019
ringe-0.019
 cand-0.018
 ham-0.018
TokenHer
Token ID9360
Feature activation+6.18e-02

Pos logit contributions
 unless+0.016
 but+0.015
 Tony+0.015
?+0.015
 thunder+0.015
Neg logit contributions
bons-0.022
ringe-0.021
 cand-0.021
 ham-0.020
age-0.019
Token mom
Token ID1995
Feature activation+2.70e-02

Pos logit contributions
bons+0.105
ringe+0.100
age+0.099
 cand+0.095
 ham+0.094
Neg logit contributions
 unless-0.094
 but-0.085
 thunder-0.084
 Tony-0.084
 Jay-0.080
Token your
Token ID534
Feature activation+6.42e-02

Pos logit contributions
 unless+0.045
aph+0.042
iness+0.041
ulu+0.040
 Tony+0.039
Neg logit contributions
 ham-0.071
 cand-0.069
bons-0.069
ringe-0.064
 presents-0.064
Token cr
Token ID1067
Feature activation+4.77e-02

Pos logit contributions
bons+0.093
ringe+0.088
age+0.086
 cand+0.082
 ham+0.080
Neg logit contributions
 unless-0.113
 but-0.106
 thunder-0.105
 Tony-0.105
 Jay-0.101
Tokenay
Token ID323
Feature activation+7.59e-02

Pos logit contributions
 ham+0.081
 cash+0.079
 cand+0.079
ringe+0.079
bons+0.076
Neg logit contributions
?-0.065
!-0.064
ill-0.061
 unless-0.061
 Jas-0.061
Tokenons
Token ID684
Feature activation+1.70e-02

Pos logit contributions
ringe+0.102
bons+0.101
age+0.095
 ham+0.092
 cand+0.092
Neg logit contributions
 unless-0.133
?-0.133
!-0.131
 thunder-0.129
 Tony-0.127
Token made
Token ID925
Feature activation+1.38e-02

Pos logit contributions
bons+0.038
ringe+0.036
age+0.036
 cand+0.035
 ham+0.034
Neg logit contributions
 unless-0.017
 but-0.015
 Tony-0.015
 thunder-0.015
 Jay-0.014
Token a
Token ID257
Feature activation-9.50e-03

Pos logit contributions
ringe+0.030
bons+0.030
age+0.029
 saddle+0.027
checked+0.027
Neg logit contributions
 unless-0.014
 thunder-0.013
 but-0.013
?-0.012
 Tony-0.012
Token new
Token ID649
Feature activation+3.88e-02

Pos logit contributions
 thunder+0.012
 but+0.012
!+0.011
 storm+0.011
 unless+0.011
Neg logit contributions
bons-0.019
ringe-0.018
cream-0.018
age-0.017
acked-0.017
Token poem
Token ID21247
Feature activation+2.42e-02

Pos logit contributions
ringe+0.062
bons+0.061
acked+0.057
checked+0.056
Here+0.056
Neg logit contributions
 but-0.065
!-0.063
?-0.062
 unless-0.061
 thunder-0.059
Token for
Token ID329
Feature activation+1.34e-02

Pos logit contributions
bons+0.053
ringe+0.051
age+0.050
 cand+0.048
 ham+0.048
Neg logit contributions
 unless-0.025
 but-0.022
 thunder-0.022
 Tony-0.022
 Jay-0.020
Token you
Token ID345
Feature activation-7.63e-02

Pos logit contributions
bons+0.027
ringe+0.026
age+0.025
 cand+0.025
 ham+0.024
Neg logit contributions
 unless-0.016
 but-0.015
 Tony-0.014
 thunder-0.014
 Jay-0.014
Token.
Token ID13
Feature activation+1.23e-02

Pos logit contributions
 unless+0.085
 thunder+0.076
 Tony+0.076
 but+0.074
 Jay+0.073
Neg logit contributions
bons-0.157
age-0.149
ringe-0.148
 cand-0.144
 ham-0.143
Token her
Token ID607
Feature activation+5.36e-02

Pos logit contributions
 unless+0.012
aph+0.011
 Tony+0.011
 expect+0.011
 Jas+0.011
Neg logit contributions
bons-0.018
 cand-0.017
 ham-0.016
ringe-0.016
age-0.016
Token wings
Token ID12098
Feature activation-2.96e-02

Pos logit contributions
bons+0.082
ringe+0.077
age+0.075
 cand+0.070
 ham+0.069
Neg logit contributions
 unless-0.090
 but-0.086
 thunder-0.085
 anymore-0.081
 behind-0.081
Token.
Token ID13
Feature activation+2.83e-02

Pos logit contributions
 Tony+0.026
 unless+0.026
 Jay+0.026
 Jas+0.025
 thunder+0.025
Neg logit contributions
bons-0.065
age-0.064
ringe-0.061
 cand-0.061
 ham-0.059
Token She
Token ID1375
Feature activation+4.31e-02

Pos logit contributions
bons+0.034
ringe+0.032
age+0.031
 ham+0.029
 cand+0.029
Neg logit contributions
 unless-0.056
 thunder-0.052
 Tony-0.051
ulu-0.050
 expect-0.050
Token pe
Token ID613
Feature activation+2.49e-02

Pos logit contributions
bons+0.086
ringe+0.082
age+0.081
 cand+0.078
 ham+0.077
Neg logit contributions
 unless-0.052
 but-0.048
 thunder-0.047
 Tony-0.047
 Jay-0.044
Tokenck
Token ID694
Feature activation-1.51e-04

Pos logit contributions
bons+0.048
age+0.045
 cand+0.044
 ham+0.044
ringe+0.044
Neg logit contributions
 unless-0.031
ulu-0.029
 but-0.028
ila-0.028
 Tony-0.028
Tokened
Token ID276
Feature activation+5.64e-02

Pos logit contributions
 unless+0.000
 thunder+0.000
aph+0.000
 expect+0.000
?!+0.000
Neg logit contributions
bons-0.000
 cand-0.000
 ham-0.000
acked-0.000
ringe-0.000
Token at
Token ID379
Feature activation+1.72e-02

Pos logit contributions
bons+0.117
ringe+0.111
 cand+0.108
 ham+0.108
age+0.107
Neg logit contributions
 unless-0.062
 Tony-0.055
 thunder-0.054
aph-0.053
ulu-0.053
Token the
Token ID262
Feature activation-1.49e-02

Pos logit contributions
bons+0.037
ringe+0.035
 ham+0.035
 cash+0.035
 cand+0.034
Neg logit contributions
 unless-0.017
 echoed-0.016
 expect-0.015
iving-0.015
yt-0.015
Token cage
Token ID17186
Feature activation+1.41e-03

Pos logit contributions
 thunder+0.021
 but+0.021
 unless+0.020
 storm+0.019
 anymore+0.019
Neg logit contributions
bons-0.027
ringe-0.025
age-0.024
acked-0.023
 cand-0.023
Token door
Token ID3420
Feature activation+3.86e-02

Pos logit contributions
bons+0.003
age+0.003
ringe+0.003
 cand+0.003
 ham+0.003
Neg logit contributions
 unless-0.001
 Tony-0.001
 thunder-0.001
 Jay-0.001
 expect-0.001
Token and
Token ID290
Feature activation+5.01e-03

Pos logit contributions
 unless+0.025
 thunder+0.023
 Tony+0.022
 expect+0.022
?+0.022
Neg logit contributions
bons-0.029
age-0.027
ringe-0.027
 cand-0.026
 ham-0.025
Token had
Token ID550
Feature activation+4.01e-02

Pos logit contributions
bons+0.009
ringe+0.008
age+0.008
 cand+0.008
 ham+0.008
Neg logit contributions
 unless-0.007
 but-0.007
 Tony-0.006
 thunder-0.006
?-0.006
Token fun
Token ID1257
Feature activation+4.38e-03

Pos logit contributions
bons+0.077
ringe+0.074
age+0.073
 cand+0.070
 ham+0.069
Neg logit contributions
 unless-0.052
 but-0.047
 thunder-0.047
 Tony-0.047
 Jay-0.044
Token at
Token ID379
Feature activation+1.53e-03

Pos logit contributions
bons+0.006
 cand+0.005
age+0.005
ages+0.005
lets+0.005
Neg logit contributions
 unless-0.008
ulu-0.007
aph-0.007
 Tony-0.007
 expect-0.007
Token the
Token ID262
Feature activation-3.23e-02

Pos logit contributions
bons+0.003
 cand+0.003
ringe+0.003
 presents+0.003
 ham+0.002
Neg logit contributions
 unless-0.002
iness-0.002
 echoed-0.002
 lur-0.001
 Jas-0.001
Token wedding
Token ID10614
Feature activation+1.83e-02

Pos logit contributions
 unless+0.048
 but+0.044
 Tony+0.044
 Jas+0.042
 thunder+0.042
Neg logit contributions
bons-0.055
ringe-0.052
age-0.052
 ham-0.050
 cand-0.050
Token.
Token ID13
Feature activation-8.15e-03

Pos logit contributions
bons+0.033
age+0.032
 cand+0.031
ages+0.030
ringe+0.030
Neg logit contributions
ulu-0.024
 unless-0.024
 thunder-0.024
 expect-0.024
ila-0.023
Token<|endoftext|>
Token ID50256
Feature activation-1.39e-02

Pos logit contributions
 unless+0.011
 but+0.011
 Tony+0.010
 thunder+0.010
 Little+0.010
Neg logit contributions
bons-0.015
ringe-0.014
age-0.014
 cand-0.014
 ham-0.013
TokenOnce
Token ID7454
Feature activation-1.73e-02

Pos logit contributions
 unless+0.029
iness+0.027
itive+0.027
 expect+0.027
 storms+0.027
Neg logit contributions
bons-0.015
age-0.014
acked-0.014
Here-0.012
 ham-0.011
Token upon
Token ID2402
Feature activation+7.96e-05

Pos logit contributions
 thunder+0.027
 unless+0.027
 resur+0.026
 echoing+0.026
 echoed+0.025
Neg logit contributions
 dollar-0.021
acked-0.020
ushes-0.020
ossible-0.020
 ham-0.019
Token a
Token ID257
Feature activation-4.04e-02

Pos logit contributions
bons+0.000
age+0.000
 ham+0.000
ringe+0.000
 cand+0.000
Neg logit contributions
 unless-0.000
 Jay-0.000
 Tony-0.000
 Jas-0.000
aph-0.000
Token and
Token ID290
Feature activation+8.51e-03

Pos logit contributions
bons+0.001
age+0.001
ringe+0.001
 cand+0.001
ages+0.001
Neg logit contributions
 unless-0.001
 thunder-0.000
 Tony-0.000
 Jay-0.000
aph-0.000
Token she
Token ID673
Feature activation-9.89e-03

Pos logit contributions
bons+0.016
ringe+0.015
age+0.015
 cand+0.015
 ham+0.015
Neg logit contributions
 unless-0.011
 thunder-0.010
 Tony-0.009
 but-0.009
 anymore-0.009
Token couldn
Token ID3521
Feature activation-3.68e-02

Pos logit contributions
 unless+0.013
 thunder+0.012
 Tony+0.012
 but+0.012
 anymore+0.011
Neg logit contributions
bons-0.018
age-0.018
ringe-0.018
 cand-0.017
 ham-0.017
Token't
Token ID470
Feature activation-6.43e-02

Pos logit contributions
 unless+0.058
 Tony+0.055
 but+0.055
 thunder+0.053
 Jas+0.052
Neg logit contributions
bons-0.057
age-0.056
ringe-0.050
acked-0.048
 cand-0.048
Token believe
Token ID1975
Feature activation-3.71e-02

Pos logit contributions
 thunder+0.097
 Tony+0.097
 unless+0.095
 Jas+0.095
 Little+0.093
Neg logit contributions
age-0.101
bons-0.092
ringe-0.083
 saddle-0.083
 Amen-0.079
Token her
Token ID607
Feature activation+3.14e-02

Pos logit contributions
olt+0.071
 drown+0.071
oke+0.069
 swarm+0.068
iving+0.067
Neg logit contributions
 presents-0.033
 cand-0.031
 jewelry-0.031
 novels-0.031
 gifts-0.031
Token eyes
Token ID2951
Feature activation-1.15e-02

Pos logit contributions
bons+0.032
ringe+0.029
 cand+0.029
 presents+0.029
 packages+0.028
Neg logit contributions
 unless-0.067
ulu-0.063
 but-0.061
 Tony-0.061
 expect-0.060
Token.
Token ID13
Feature activation+1.99e-03

Pos logit contributions
 Tony+0.014
ulu+0.013
aph+0.013
 Jay+0.013
 Jas+0.012
Neg logit contributions
bons-0.022
 cand-0.022
age-0.021
cream-0.020
 ham-0.020
Token She
Token ID1375
Feature activation+2.89e-02

Pos logit contributions
bons+0.003
ringe+0.003
age+0.003
 cand+0.003
 ham+0.003
Neg logit contributions
 unless-0.003
 but-0.003
 thunder-0.003
 Tony-0.003
 Little-0.003
Token saw
Token ID2497
Feature activation-9.96e-03

Pos logit contributions
bons+0.055
ringe+0.053
age+0.052
 cand+0.051
 ham+0.050
Neg logit contributions
 unless-0.038
 thunder-0.033
 but-0.033
 Tony-0.033
 anymore-0.032
Token big
Token ID1263
Feature activation+7.61e-03

Pos logit contributions
 unless+0.015
 Tony+0.013
 but+0.013
 thunder+0.013
?+0.013
Neg logit contributions
bons-0.017
 cand-0.016
ringe-0.016
age-0.016
 ham-0.016
Token.
Token ID13
Feature activation-1.65e-02

Pos logit contributions
ulu+0.046
ila+0.046
otion+0.046
azy+0.045
 Jas+0.043
Neg logit contributions
 cand-0.064
 ham-0.063
bons-0.061
lets-0.056
age-0.056
Token<|endoftext|>
Token ID50256
Feature activation-2.44e-02

Pos logit contributions
 unless+0.026
 thunder+0.025
 expect+0.023
 but+0.023
 storms+0.023
Neg logit contributions
bons-0.027
age-0.025
ringe-0.025
 ham-0.023
acked-0.023
TokenAn
Token ID2025
Feature activation-3.89e-02

Pos logit contributions
 unless+0.046
 expect+0.042
 thunder+0.042
 storms+0.041
iness+0.041
Neg logit contributions
bons-0.032
acked-0.030
age-0.029
Here-0.028
 ham-0.027
Tokennie
Token ID11952
Feature activation+4.69e-02

Pos logit contributions
 unless+0.052
 thunder+0.047
 but+0.046
 Tony+0.045
 forgetting+0.044
Neg logit contributions
bons-0.073
age-0.068
ringe-0.067
acked-0.065
 cand-0.065
Token was
Token ID373
Feature activation+2.87e-03

Pos logit contributions
bons+0.084
age+0.080
ringe+0.077
 ham+0.076
 cand+0.075
Neg logit contributions
 unless-0.065
 thunder-0.060
aph-0.058
 but-0.057
 anymore-0.056
Token a
Token ID257
Feature activation-1.71e-02

Pos logit contributions
bons+0.006
ringe+0.006
age+0.005
 cand+0.005
 ham+0.005
Neg logit contributions
 unless-0.003
 but-0.003
 thunder-0.003
 Tony-0.003
 Jay-0.003
Token happy
Token ID3772
Feature activation+6.22e-02

Pos logit contributions
 unless+0.023
 either+0.021
 expect+0.020
 anymore+0.020
 Tony+0.020
Neg logit contributions
 ham-0.029
bons-0.028
ringe-0.028
age-0.028
 cash-0.028
Token girl
Token ID2576
Feature activation+1.49e-02

Pos logit contributions
 ham+0.100
 cand+0.096
bons+0.096
age+0.095
 cash+0.094
Neg logit contributions
 unless-0.093
 expect-0.083
ulu-0.079
azy-0.078
 either-0.078
Token.
Token ID13
Feature activation+8.04e-03

Pos logit contributions
bons+0.030
age+0.029
 ham+0.028
 cand+0.028
ringe+0.028
Neg logit contributions
 unless-0.015
aph-0.015
 thunder-0.015
 storms-0.014
ulu-0.014
Token She
Token ID1375
Feature activation+3.20e-02

Pos logit contributions
bons+0.011
ringe+0.010
age+0.010
 cand+0.009
 ham+0.009
Neg logit contributions
 unless-0.015
 thunder-0.014
 but-0.014
 Tony-0.014
 Jay-0.013
Token loved
Token ID6151
Feature activation+2.26e-02

Pos logit contributions
bons+0.049
age+0.046
ringe+0.043
 cand+0.043
 ham+0.043
Neg logit contributions
 unless-0.054
 thunder-0.049
aph-0.049
 Tony-0.048
 anymore-0.047
TokenWhen
Token ID2215
Feature activation-1.14e-02

Pos logit contributions
 unless+0.041
 but+0.038
 thunder+0.037
 Tony+0.037
 Jas+0.036
Neg logit contributions
bons-0.052
ringe-0.051
age-0.048
 ham-0.047
 cand-0.047
Token it
Token ID340
Feature activation-6.20e-03

Pos logit contributions
 unless+0.012
 Tony+0.010
 but+0.009
 thunder+0.009
 expect+0.009
Neg logit contributions
bons-0.024
 cand-0.024
age-0.022
ringe-0.022
 ham-0.022
Token was
Token ID373
Feature activation-3.48e-02

Pos logit contributions
 unless+0.011
 thunder+0.010
 Tony+0.009
 storms+0.009
 but+0.009
Neg logit contributions
acked-0.009
age-0.009
bons-0.008
 cand-0.008
cream-0.007
Token time
Token ID640
Feature activation-4.33e-02

Pos logit contributions
 unless+0.032
 Jay+0.028
aph+0.028
 Tony+0.027
 lur+0.026
Neg logit contributions
bons-0.077
acked-0.071
 presents-0.070
 cand-0.070
age-0.070
Token to
Token ID284
Feature activation-8.40e-03

Pos logit contributions
 unless+0.079
 thunder+0.074
aph+0.073
 storms+0.071
 Tony+0.071
Neg logit contributions
age-0.051
bons-0.049
 cand-0.049
 presents-0.046
ringe-0.045
Token go
Token ID467
Feature activation-3.53e-02

Pos logit contributions
 unless+0.014
 lur+0.013
 lurking+0.013
 spiders+0.013
azy+0.012
Neg logit contributions
bons-0.012
 cash-0.011
age-0.011
 cand-0.011
 receipt-0.010
Token home
Token ID1363
Feature activation+4.55e-02

Pos logit contributions
 unless+0.066
 thunder+0.063
 Tony+0.061
 echoed+0.060
azy+0.060
Neg logit contributions
bons-0.042
age-0.042
ringe-0.038
 cand-0.037
 presents-0.035
Token,
Token ID11
Feature activation-6.52e-02

Pos logit contributions
 cand+0.076
age+0.072
 presents+0.071
 cash+0.070
bons+0.069
Neg logit contributions
aph-0.056
 thunder-0.056
azy-0.056
 unless-0.055
Run-0.054
Token Sus
Token ID8932
Feature activation-5.34e-02

Pos logit contributions
 unless+0.090
 lurking+0.087
azy+0.084
 thunder+0.081
 expect+0.081
Neg logit contributions
bons-0.105
 cand-0.105
 cash-0.100
 presents-0.099
 packages-0.095
Tokenie
Token ID494
Feature activation-2.56e-02

Pos logit contributions
 unless+0.092
 thunder+0.089
 but+0.085
 Tony+0.084
 expect+0.083
Neg logit contributions
bons-0.076
age-0.075
ringe-0.073
acked-0.071
 cand-0.070
Token was
Token ID373
Feature activation-1.69e-03

Pos logit contributions
 unless+0.036
 thunder+0.033
 but+0.031
aph+0.031
 anymore+0.031
Neg logit contributions
bons-0.045
age-0.044
ringe-0.043
 cand-0.042
 ham-0.041
Token brave
Token ID14802
Feature activation-4.69e-02

Pos logit contributions
 unless+0.035
 but+0.033
 thunder+0.033
 Tony+0.032
 Jay+0.030
Neg logit contributions
bons-0.054
ringe-0.052
age-0.051
 cand-0.049
 ham-0.048
Token was
Token ID373
Feature activation-2.30e-02

Pos logit contributions
 unless+0.062
aph+0.062
ulu+0.061
 Tony+0.058
 Jay+0.058
Neg logit contributions
bons-0.086
age-0.080
ringe-0.079
 cand-0.078
 ham-0.075
Token good
Token ID922
Feature activation+1.53e-02

Pos logit contributions
aph+0.030
 unless+0.029
 Jay+0.029
 Tony+0.029
ulu+0.027
Neg logit contributions
bons-0.041
age-0.038
ringe-0.037
 ham-0.036
 cand-0.036
Token.
Token ID13
Feature activation-8.83e-03

Pos logit contributions
bons+0.024
 cand+0.024
ringe+0.023
age+0.022
ages+0.022
Neg logit contributions
 unless-0.022
 thunder-0.022
ulu-0.022
Little-0.022
aph-0.021
Token<|endoftext|>
Token ID50256
Feature activation-1.23e-02

Pos logit contributions
 unless+0.011
 but+0.010
 Tony+0.010
 Little+0.010
 thunder+0.010
Neg logit contributions
bons-0.017
ringe-0.017
age-0.016
 cand-0.016
 ham-0.015
TokenOnce
Token ID7454
Feature activation-1.49e-02

Pos logit contributions
 unless+0.024
 expect+0.022
iness+0.022
itive+0.022
 thunder+0.022
Neg logit contributions
bons-0.015
age-0.014
acked-0.014
Here-0.013
ringe-0.012
Token upon
Token ID2402
Feature activation+4.60e-03

Pos logit contributions
 unless+0.023
 thunder+0.023
 resur+0.023
Run+0.023
 echoing+0.022
Neg logit contributions
 dollar-0.018
ushes-0.018
ossible-0.018
 presents-0.017
acked-0.017
Token a
Token ID257
Feature activation-3.76e-02

Pos logit contributions
bons+0.008
age+0.007
 ham+0.007
ringe+0.007
 cand+0.007
Neg logit contributions
 unless-0.007
 Tony-0.006
 Jay-0.006
 Jas-0.006
aph-0.006
Token time
Token ID640
Feature activation-8.84e-03

Pos logit contributions
 Jay+0.042
 unless+0.042
 Tony+0.040
aph+0.039
 Jas+0.039
Neg logit contributions
age-0.073
bons-0.073
 ham-0.069
acked-0.068
ringe-0.067
Token,
Token ID11
Feature activation-2.90e-02

Pos logit contributions
 unless+0.014
 echoing+0.014
 thunder+0.014
 resur+0.014
 expect+0.013
Neg logit contributions
 dollar-0.010
 cand-0.010
 ham-0.009
age-0.009
bons-0.009
Token there
Token ID612
Feature activation-1.85e-03

Pos logit contributions
 unless+0.028
 Tony+0.025
 thunder+0.024
 Jas+0.024
 storms+0.024
Neg logit contributions
ringe-0.058
age-0.058
 ham-0.058
bons-0.058
acked-0.058
Token was
Token ID373
Feature activation-5.79e-03

Pos logit contributions
 unless+0.039
 but+0.036
 thunder+0.036
 Tony+0.036
 Jay+0.034
Neg logit contributions
bons-0.047
ringe-0.045
age-0.044
 cand-0.043
 ham-0.042
Token very
Token ID845
Feature activation+4.81e-02

Pos logit contributions
 unless+0.008
 but+0.008
 thunder+0.008
 Tony+0.007
 Little+0.007
Neg logit contributions
bons-0.011
ringe-0.010
age-0.010
 cand-0.010
 ham-0.009
Token excited
Token ID6568
Feature activation+4.45e-02

Pos logit contributions
bons+0.094
ringe+0.090
age+0.089
 cand+0.086
 ham+0.084
Neg logit contributions
 unless-0.061
 but-0.055
 thunder-0.055
 Tony-0.055
 Jay-0.051
Token!
Token ID0
Feature activation-2.01e-02

Pos logit contributions
bons+0.080
 cand+0.075
age+0.074
 ham+0.072
ages+0.072
Neg logit contributions
ulu-0.057
 unless-0.056
aph-0.054
ila-0.054
azy-0.053
Token He
Token ID679
Feature activation+1.53e-02

Pos logit contributions
 unless+0.030
 but+0.030
 Tony+0.029
 Little+0.028
 thunder+0.028
Neg logit contributions
bons-0.034
ringe-0.033
age-0.032
 cand-0.031
 ham-0.030
Token went
Token ID1816
Feature activation-2.68e-02

Pos logit contributions
bons+0.028
ringe+0.027
age+0.027
 cand+0.026
 ham+0.025
Neg logit contributions
 unless-0.021
 but-0.019
 thunder-0.019
 Tony-0.019
 Jay-0.018
Token to
Token ID284
Feature activation+2.54e-02

Pos logit contributions
 but+0.029
 unless+0.028
 behind+0.026
 Tony+0.025
 thunder+0.025
Neg logit contributions
bons-0.060
ringe-0.057
age-0.055
 cand-0.055
 ham-0.054
Token a
Token ID257
Feature activation-2.39e-02

Pos logit contributions
bons+0.055
ringe+0.052
age+0.051
 cand+0.051
 ham+0.050
Neg logit contributions
 unless-0.026
 but-0.022
 thunder-0.022
 anymore-0.021
 Tony-0.021
Token party
Token ID2151
Feature activation+8.49e-03

Pos logit contributions
 unless+0.029
 but+0.028
 thunder+0.027
?+0.026
 Tony+0.026
Neg logit contributions
bons-0.050
ringe-0.048
age-0.046
ages-0.044
acked-0.043
Token with
Token ID351
Feature activation+6.48e-03

Pos logit contributions
bons+0.013
age+0.012
ringe+0.012
 cand+0.012
 ham+0.011
Neg logit contributions
 unless-0.014
 thunder-0.013
ulu-0.013
aph-0.013
 Tony-0.012
Token all
Token ID477
Feature activation+3.11e-02

Pos logit contributions
age+0.013
bons+0.013
ringe+0.013
ages+0.012
acked+0.011
Neg logit contributions
 unless-0.007
 Tony-0.007
 thunder-0.007
 but-0.007
 anyone-0.007
Token was
Token ID373
Feature activation+1.53e-02

Pos logit contributions
bons+0.073
ringe+0.070
age+0.069
 cand+0.066
 ham+0.065
Neg logit contributions
 unless-0.049
 but-0.045
 Tony-0.045
 thunder-0.044
 Jay-0.042
Token so
Token ID523
Feature activation+6.79e-02

Pos logit contributions
bons+0.032
ringe+0.031
age+0.031
 cand+0.030
 ham+0.029
Neg logit contributions
 unless-0.017
 but-0.016
 thunder-0.016
 Tony-0.015
 Little-0.015
Token excited
Token ID6568
Feature activation+5.24e-02

Pos logit contributions
bons+0.130
ringe+0.124
age+0.122
 cand+0.118
 ham+0.116
Neg logit contributions
 unless-0.089
 but-0.081
 thunder-0.080
 Tony-0.080
 Jay-0.075
Token to
Token ID284
Feature activation+1.22e-02

Pos logit contributions
bons+0.080
age+0.076
 cand+0.074
ages+0.070
cream+0.070
Neg logit contributions
 unless-0.079
ulu-0.079
azy-0.075
aph-0.075
 drown-0.074
Token find
Token ID1064
Feature activation-9.13e-03

Pos logit contributions
bons+0.024
age+0.023
ringe+0.022
 cand+0.021
 ham+0.021
Neg logit contributions
 unless-0.016
 but-0.014
 thunder-0.014
 Tony-0.014
 anymore-0.013
Token a
Token ID257
Feature activation-1.89e-02

Pos logit contributions
 unless+0.011
 thunder+0.010
 Tony+0.010
 but+0.010
aph+0.010
Neg logit contributions
bons-0.018
ringe-0.017
 cand-0.016
age-0.016
 ham-0.016
Token special
Token ID2041
Feature activation+4.09e-02

Pos logit contributions
 unless+0.024
 but+0.023
 thunder+0.022
 Tony+0.022
?+0.021
Neg logit contributions
bons-0.037
ringe-0.035
age-0.034
 cand-0.033
acked-0.033
Token screw
Token ID9580
Feature activation+2.73e-02

Pos logit contributions
bons+0.072
ringe+0.071
age+0.066
acked+0.066
ages+0.066
Neg logit contributions
 but-0.059
 unless-0.058
 thunder-0.055
?-0.055
 Tony-0.053
Token lying
Token ID9105
Feature activation-1.04e-02

Pos logit contributions
bons+0.055
age+0.054
ringe+0.053
 cand+0.051
 ham+0.049
Neg logit contributions
 unless-0.030
 thunder-0.030
 Tony-0.030
 Jay-0.028
 Little-0.028
Token in
Token ID287
Feature activation-7.03e-03

Pos logit contributions
 unless+0.014
 expect+0.014
 Tony+0.014
 Jas+0.014
 thunder+0.014
Neg logit contributions
bons-0.018
age-0.017
ringe-0.017
 ham-0.016
 cand-0.016
Token the
Token ID262
Feature activation-1.36e-02

Pos logit contributions
 unless+0.007
aph+0.007
 thunder+0.006
 echoed+0.006
 Tony+0.006
Neg logit contributions
bons-0.016
ringe-0.014
 cand-0.013
 ham-0.013
age-0.013
Token money
Token ID1637
Feature activation+2.58e-02

Pos logit contributions
bons+0.078
age+0.075
ringe+0.073
acked+0.065
checked+0.064
Neg logit contributions
 unless-0.124
 but-0.120
?-0.115
 anymore-0.114
 either-0.113
Token or
Token ID393
Feature activation-2.47e-02

Pos logit contributions
bons+0.053
age+0.050
ringe+0.049
 cand+0.049
ages+0.048
Neg logit contributions
 thunder-0.029
 Jas-0.025
 storms-0.025
ulu-0.024
 lur-0.024
Token you
Token ID345
Feature activation-7.13e-02

Pos logit contributions
 unless+0.032
 but+0.029
 Tony+0.028
 thunder+0.028
 Jay+0.027
Neg logit contributions
bons-0.048
ringe-0.046
age-0.045
 cand-0.043
 ham-0.043
Tokenâ
Token ID22940
Feature activation-5.85e-02

Pos logit contributions
 unless+0.093
 thunder+0.089
 Tony+0.085
 but+0.083
 Jas+0.082
Neg logit contributions
bons-0.132
age-0.128
ringe-0.124
 cand-0.120
 ham-0.118
Token€
Token ID26391
Feature activation-2.03e-02

Pos logit contributions
 unless+0.075
 thunder+0.067
 but+0.067
 Tony+0.067
?+0.065
Neg logit contributions
bons-0.111
ringe-0.107
 cand-0.104
age-0.103
 ham-0.102
Tokenâ„¢
Token ID8151
Feature activation-1.11e-01

Pos logit contributions
ulu+0.032
 unless+0.032
 thunder+0.032
 but+0.030
 Tony+0.029
Neg logit contributions
age-0.032
ages-0.032
bons-0.032
ringe-0.031
cream-0.027
Tokenll
Token ID297
Feature activation-2.66e-02

Pos logit contributions
 thunder+0.196
 storms+0.184
 unless+0.180
 expect+0.177
 storm+0.175
Neg logit contributions
age-0.152
acked-0.142
bons-0.141
ages-0.140
 dollar-0.138
Token lose
Token ID4425
Feature activation-2.09e-02

Pos logit contributions
 unless+0.035
 thunder+0.033
 Tony+0.033
 but+0.031
 Jay+0.031
Neg logit contributions
bons-0.050
age-0.048
ringe-0.048
 cand-0.045
 ham-0.043
Token it
Token ID340
Feature activation-5.73e-04

Pos logit contributions
 thunder+0.021
 unless+0.020
aph+0.020
 Jas+0.020
 Tony+0.020
Neg logit contributions
bons-0.044
ringe-0.042
 cand-0.040
age-0.040
 ham-0.040
Token!
Token ID0
Feature activation-3.70e-02

Pos logit contributions
 Jas+0.001
 thunder+0.001
 Jay+0.001
 Tony+0.001
aph+0.001
Neg logit contributions
bons-0.001
age-0.001
ringe-0.001
 cand-0.001
ages-0.001
Tokenâ
Token ID22940
Feature activation-4.36e-02

Pos logit contributions
 unless+0.058
 but+0.055
 Tony+0.054
 thunder+0.053
 Little+0.051
Neg logit contributions
bons-0.060
ringe-0.057
age-0.056
 cand-0.054
 ham-0.053
Token regular
Token ID3218
Feature activation+2.51e-02

Pos logit contributions
 unless+0.026
 Tony+0.025
aph+0.024
 Jay+0.023
 expect+0.023
Neg logit contributions
bons-0.039
age-0.038
ringe-0.037
 cand-0.036
 ham-0.035
Token and
Token ID290
Feature activation-1.60e-02

Pos logit contributions
 cand+0.039
bons+0.037
 presents+0.034
 gifts+0.032
ages+0.032
Neg logit contributions
aph-0.039
azy-0.037
ulu-0.037
Little-0.036
 anybody-0.035
Token quiet
Token ID5897
Feature activation-5.77e-03

Pos logit contributions
 unless+0.019
aph+0.017
 Tony+0.016
azy+0.016
 expect+0.015
Neg logit contributions
bons-0.031
 cand-0.030
 ham-0.030
ringe-0.029
age-0.028
Token,
Token ID11
Feature activation-6.75e-02

Pos logit contributions
aph+0.009
ulu+0.008
ila+0.008
azy+0.008
 Tony+0.008
Neg logit contributions
 cand-0.009
bons-0.009
age-0.009
 presents-0.008
acked-0.008
Token and
Token ID290
Feature activation-7.64e-03

Pos logit contributions
aph+0.077
 unless+0.074
ulu+0.073
azy+0.073
 Tony+0.072
Neg logit contributions
bons-0.131
 cand-0.124
age-0.123
 ham-0.121
ringe-0.119
Token nobody
Token ID8168
Feature activation-1.14e-01

Pos logit contributions
 unless+0.009
aph+0.008
 Tony+0.008
 Jay+0.007
?+0.007
Neg logit contributions
bons-0.015
 cand-0.015
 ham-0.014
ringe-0.014
 cash-0.014
Token paid
Token ID3432
Feature activation-1.18e-02

Pos logit contributions
 unless+0.184
aph+0.174
 storms+0.172
 thunder+0.171
 Little+0.170
Neg logit contributions
age-0.168
acked-0.147
checked-0.141
ages-0.133
aid-0.132
Token attention
Token ID3241
Feature activation-3.69e-02

Pos logit contributions
 unless+0.019
 resur+0.019
?!+0.018
Run+0.018
 lur+0.018
Neg logit contributions
bons-0.016
 cand-0.015
 presents-0.014
ringe-0.014
 gifts-0.014
Token.
Token ID13
Feature activation-8.96e-03

Pos logit contributions
aph+0.068
ulu+0.062
 storm+0.062
 thunder+0.061
 lur+0.060
Neg logit contributions
age-0.041
bons-0.039
 presents-0.037
 ham-0.037
 cand-0.035
Token
Token ID198
Feature activation-2.52e-02

Pos logit contributions
 unless+0.008
 but+0.008
 Little+0.007
 thunder+0.007
 Tony+0.007
Neg logit contributions
bons-0.021
ringe-0.020
age-0.020
 cand-0.019
 ham-0.019
Token
Token ID198
Feature activation-2.41e-02

Pos logit contributions
 unless+0.036
 thunder+0.034
 Tony+0.033
 storms+0.032
 but+0.032
Neg logit contributions
bons-0.043
age-0.042
ringe-0.040
 cand-0.039
acked-0.038
Token animals
Token ID4695
Feature activation-7.62e-02

Pos logit contributions
 unless+0.039
 Tony+0.036
 but+0.034
 Jay+0.034
 Jas+0.034
Neg logit contributions
bons-0.043
age-0.041
ringe-0.040
 cand-0.039
 ham-0.038
Token were
Token ID547
Feature activation+1.11e-02

Pos logit contributions
 unless+0.106
 Tony+0.098
aph+0.097
 Jas+0.095
 thunder+0.093
Neg logit contributions
age-0.134
bons-0.117
ages-0.117
 cand-0.116
ringe-0.112
Token worried
Token ID7960
Feature activation-9.42e-03

Pos logit contributions
bons+0.021
age+0.021
ringe+0.020
 cand+0.019
ages+0.019
Neg logit contributions
 unless-0.014
 Tony-0.013
aph-0.012
 Jay-0.012
 but-0.012
Token.
Token ID13
Feature activation+2.36e-03

Pos logit contributions
aph+0.014
ulu+0.013
ila+0.012
azy+0.012
 Jas+0.012
Neg logit contributions
 cand-0.014
age-0.013
bons-0.013
 letters-0.013
 presents-0.013
Token The
Token ID383
Feature activation-1.75e-02

Pos logit contributions
bons+0.003
ringe+0.003
age+0.003
 ham+0.003
 cand+0.003
Neg logit contributions
 unless-0.004
 thunder-0.004
 Tony-0.004
ulu-0.004
 but-0.004
Token thunder
Token ID18355
Feature activation-1.14e-01

Pos logit contributions
 unless+0.026
 Tony+0.024
 but+0.023
 Jay+0.023
 Jas+0.023
Neg logit contributions
bons-0.030
age-0.028
ringe-0.028
 cand-0.027
 ham-0.027
Token and
Token ID290
Feature activation+3.45e-03

Pos logit contributions
 unless+0.171
aph+0.167
 Tony+0.162
ulu+0.154
 Jas+0.153
Neg logit contributions
age-0.188
bons-0.172
 cand-0.168
acked-0.165
ages-0.159
Token lightning
Token ID14357
Feature activation-8.36e-02

Pos logit contributions
bons+0.007
ringe+0.007
 cand+0.007
 ham+0.007
age+0.007
Neg logit contributions
 unless-0.003
aph-0.003
 Tony-0.003
?-0.003
?!-0.003
Token were
Token ID547
Feature activation+2.85e-03

Pos logit contributions
 Tony+0.135
aph+0.135
 unless+0.133
ulu+0.124
 Jas+0.122
Neg logit contributions
age-0.129
bons-0.120
 cand-0.114
acked-0.112
ages-0.110
Token loud
Token ID7812
Feature activation-2.93e-02

Pos logit contributions
bons+0.005
age+0.005
ringe+0.005
 cand+0.005
ages+0.004
Neg logit contributions
 unless-0.004
aph-0.004
 Tony-0.004
 Jay-0.003
ulu-0.003
Token and
Token ID290
Feature activation-1.66e-02

Pos logit contributions
ulu+0.041
aph+0.039
ila+0.038
 unless+0.037
 Tony+0.037
Neg logit contributions
bons-0.054
age-0.051
 cand-0.050
ages-0.047
 ham-0.047
Token mom
Token ID1995
Feature activation+3.25e-02

Pos logit contributions
bons+0.105
ringe+0.102
age+0.100
 cand+0.097
 ham+0.096
Neg logit contributions
 unless-0.083
 but-0.074
 Tony-0.074
 thunder-0.073
 Jay-0.069
Token,
Token ID11
Feature activation-3.26e-02

Pos logit contributions
bons+0.075
ringe+0.072
age+0.072
 cand+0.069
 ham+0.068
Neg logit contributions
 unless-0.029
 thunder-0.025
 but-0.025
 Tony-0.025
 Jay-0.023
Token "
Token ID366
Feature activation+4.42e-02

Pos logit contributions
 unless+0.042
aph+0.037
 thunder+0.037
 Tony+0.037
 anymore+0.036
Neg logit contributions
bons-0.060
ringe-0.057
age-0.057
 cand-0.056
 ham-0.056
Tokenthat
Token ID5562
Feature activation-1.45e-02

Pos logit contributions
bons+0.079
ringe+0.076
age+0.074
 cand+0.073
 ham+0.071
Neg logit contributions
 unless-0.063
 but-0.058
 Tony-0.057
 thunder-0.056
?-0.053
Token's
Token ID338
Feature activation+4.67e-02

Pos logit contributions
 unless+0.022
 Tony+0.020
 Jas+0.020
 thunder+0.020
aph+0.020
Neg logit contributions
bons-0.024
age-0.023
ringe-0.023
 cand-0.022
 ham-0.022
Token why
Token ID1521
Feature activation-1.08e-01

Pos logit contributions
bons+0.097
ringe+0.091
age+0.090
 ham+0.089
 cand+0.088
Neg logit contributions
 unless-0.051
 Tony-0.047
 Jay-0.046
 thunder-0.044
 but-0.044
Token they
Token ID484
Feature activation-5.82e-02

Pos logit contributions
 unless+0.130
aph+0.118
 behind+0.112
ulu+0.110
 but+0.110
Neg logit contributions
 cand-0.195
bons-0.193
 ham-0.188
ages-0.176
 presents-0.176
Token call
Token ID869
Feature activation-4.08e-02

Pos logit contributions
 unless+0.069
 Tony+0.064
 thunder+0.062
 Jas+0.062
 Jay+0.061
Neg logit contributions
bons-0.114
age-0.108
 cand-0.107
ringe-0.106
 ham-0.102
Token it
Token ID340
Feature activation-2.69e-03

Pos logit contributions
 unless+0.044
 Tony+0.038
aph+0.038
 but+0.038
ulu+0.037
Neg logit contributions
bons-0.084
ringe-0.079
age-0.079
 cand-0.078
 ham-0.076
Token a
Token ID257
Feature activation-3.71e-02

Pos logit contributions
 unless+0.003
 Tony+0.003
 thunder+0.003
 but+0.003
 Jas+0.003
Neg logit contributions
bons-0.005
age-0.005
ringe-0.005
 cand-0.005
 ham-0.005
Token medal
Token ID18279
Feature activation-6.83e-03

Pos logit contributions
 unless+0.055
 but+0.051
 thunder+0.051
 Tony+0.051
 Jay+0.048
Neg logit contributions
bons-0.064
ringe-0.061
age-0.059
 cand-0.057
 ham-0.056
Token cried
Token ID16896
Feature activation-2.15e-02

Pos logit contributions
bons+0.034
ringe+0.033
 cand+0.032
 ham+0.032
age+0.031
Neg logit contributions
 unless-0.033
 Tony-0.030
 thunder-0.030
aph-0.030
 but-0.029
Token.
Token ID13
Feature activation+1.80e-02

Pos logit contributions
 unless+0.017
 Tony+0.016
 Jay+0.015
 Jas+0.014
ulu+0.014
Neg logit contributions
bons-0.050
age-0.049
ringe-0.049
 cand-0.047
 ham-0.047
Token
Token ID198
Feature activation-1.05e-03

Pos logit contributions
bons+0.034
ringe+0.032
age+0.032
 cand+0.030
 ham+0.030
Neg logit contributions
 unless-0.024
 but-0.023
 Tony-0.022
 thunder-0.022
 Little-0.021
Token
Token ID198
Feature activation+1.54e-03

Pos logit contributions
 unless+0.001
 thunder+0.001
 but+0.001
 Tony+0.001
aph+0.001
Neg logit contributions
bons-0.002
age-0.002
ringe-0.002
 cand-0.002
 ham-0.002
Token"
Token ID1
Feature activation+6.91e-02

Pos logit contributions
bons+0.003
ringe+0.003
cards+0.003
 cand+0.003
age+0.003
Neg logit contributions
 unless-0.002
 but-0.002
ulu-0.002
?-0.002
ila-0.002
TokenWhy
Token ID5195
Feature activation-1.04e-01

Pos logit contributions
bons+0.118
ringe+0.112
age+0.110
 cand+0.107
 ham+0.105
Neg logit contributions
 unless-0.105
 Tony-0.096
 but-0.096
 thunder-0.095
 Jay-0.092
Token did
Token ID750
Feature activation+4.36e-03

Pos logit contributions
 unless+0.167
aph+0.159
 Jay+0.152
 Tony+0.151
 storms+0.150
Neg logit contributions
age-0.149
 ham-0.149
 cand-0.148
ages-0.147
ringe-0.137
Token you
Token ID345
Feature activation-6.16e-02

Pos logit contributions
bons+0.008
 cand+0.008
 ham+0.007
ringe+0.007
age+0.007
Neg logit contributions
 unless-0.006
aph-0.005
 but-0.005
ulu-0.005
 Tony-0.005
Token do
Token ID466
Feature activation+1.74e-02

Pos logit contributions
 unless+0.074
 Tony+0.067
 thunder+0.066
 but+0.065
 Jay+0.064
Neg logit contributions
bons-0.122
ringe-0.119
age-0.118
 cand-0.114
 ham-0.111
Token that
Token ID326
Feature activation-1.94e-02

Pos logit contributions
bons+0.036
ringe+0.035
age+0.035
 cand+0.034
 ham+0.033
Neg logit contributions
 unless-0.019
 but-0.016
 Tony-0.016
 thunder-0.016
 Jay-0.016
Token,
Token ID11
Feature activation-4.65e-02

Pos logit contributions
 unless+0.020
 Jas+0.019
 Jay+0.019
 Tony+0.019
 lur+0.018
Neg logit contributions
 cand-0.037
age-0.037
 ham-0.036
bons-0.036
ringe-0.036