TOP ACTIVATIONS
MAX = 7.848

" W oof , wo of !" Spot bark
" W oof , wo of , I 'm
O uch !" She cries out . She pulls back her
. Ben cried out in pain . He let
" Mir ror , mirror , make Anna big
the head . Tom cries out in pain and falls to
the child l aug heed in delight . "
said , " W oof , wo of , wo of
said , " W oof , wo of !"
his heel . He cried out loud . Sam
'm sorry !" Sara said , hugging her brother . "
's hand . Jill cried out in pain and dropped her
falls down . He cries out loud . L
the ground . Max cried out . Lily ran to help
's hand . Tom cries out . He lets go of
her finger . Lily cried out loud . "
, okay ?" mom says , hugging Anna .
says , " W oof , wo of , my name
five , six , seven , eight , nine , ten
!" " Bang , bang , bang !" Sam

MIN ACTIVATIONS
MIN = -8.161

began to sew . She se wed the piece of cloth
She told him how she se wed , glued , and
help . Together , they se wed a patch onto the
She cut and se wed the fabric and put
to show everyone . He se wed together parts of it
needle and thread . She se wed a hole in the
asked his friend , a se ag ull named Tim my
and said goodbye to her se ag ull friends . She
own two hands . She se wed it with bright colors
and learned something new about se ag ull s . <|endoftext|>
a needle and thread and se wed Teddy 's eye back
watched as her mom carefully se wed Ted 's arm back
shore and saw lots of se ag ull s flying in
his friends , but a se ag ull swoop ed down
One day , a friendly se ah orse sw am over
it , so she could j ingle them around . Mom
and white cloth and carefully se wed them together .
J enny spotted a se ag ull on the sand
gently took the shirt and se wed it back together .
and some buttons . I se wed them together and stuffed

INTERVAL 3.845 - 7.848
CONTAINS 1.569%

hope the sun will come out tomorrow . <|endoftext|> Anna and
hugged her and said , " It 's okay , Lily
them , " B oys , you can 't be happy
hugged him back and said , " Okay , Tom ,
His mom my said ,

INTERVAL -0.157 - 3.845
CONTAINS 50.903%

Lily went on an adventure in the forest with their snacks
L ily started cleaning , but she noticed something strange
their hands . But the bread and jam are still too
hug to make you feel better ," her mom my said
. He set the fan on high and ran to the

INTERVAL -4.159 - -0.157
CONTAINS 47.153%

a new word : Subway . Sam had never heard of
his toy cars . His dad took out a big box
The raven flew away and Tim kept marching until he
more important to be kind and help others . Benny and
couldn 't find it anywhere . She looked under the bed

INTERVAL -8.161 - -4.159
CONTAINS 0.375%

They played together and did lots of fun things . Every
my was so happy and excited to play with it .
said , ' I don â t know the
and couldn 't wait to show off her new dress .
park . Lily was so excited because she loved going down
Token
Token ID198
Feature activation+8.42e-01

Pos logit contributions
 Mil+0.095
 lobby+0.091
illi+0.091
pit+0.091
wic+0.090
Neg logit contributions
isdom-0.063
ercise-0.061
ly-0.055
bye-0.055
night-0.054
Token
Token ID198
Feature activation+2.51e-01

Pos logit contributions
 Fl+0.015
 Sn+0.015
 Mil+0.014
 Jenkins+0.014
 Ell+0.014
Neg logit contributions
isdom-0.028
ercise-0.027
elling-0.026
weet-0.026
off-0.025
Token"
Token ID1
Feature activation+5.07e+00

Pos logit contributions
 Fl+0.007
 Sn+0.006
 Ell+0.006
 Mil+0.006
 Jenkins+0.006
Neg logit contributions
isdom-0.007
ercise-0.006
elling-0.006
weet-0.006
off-0.006
TokenW
Token ID54
Feature activation-3.52e+00

Pos logit contributions
 Fl+0.105
 Ell+0.104
 Sn+0.104
 Jenkins+0.104
 Mil+0.102
Neg logit contributions
ercise-0.138
bye-0.132
isdom-0.132
ww-0.131
off-0.128
Tokenoof
Token ID37711
Feature activation-1.19e+00

Pos logit contributions
isdom+0.047
ercise+0.047
elling+0.044
weet+0.042
off+0.039
Neg logit contributions
 Fl-0.133
 Sn-0.126
 Mil-0.120
 Ell-0.120
 Frost-0.120
Token,
Token ID11
Feature activation+7.85e+00

Pos logit contributions
isdom+0.036
ercise+0.033
elling+0.032
weet+0.032
ully+0.031
Neg logit contributions
 Fl-0.027
 Sn-0.027
 Mil-0.025
 Ell-0.025
 Jenkins-0.024
Token wo
Token ID24486
Feature activation-1.73e+00

Pos logit contributions
 Fl+0.204
 Sn+0.203
 Jenkins+0.195
 Ell+0.192
 Mil+0.191
Neg logit contributions
isdom-0.203
ercise-0.184
weet-0.183
elling-0.178
ully-0.171
Tokenof
Token ID1659
Feature activation+9.14e-01

Pos logit contributions
isdom+0.037
ercise+0.033
 melodies+0.032
elling+0.031
ully+0.030
Neg logit contributions
 Fl-0.054
 Sn-0.050
 Jenkins-0.048
 Ell-0.048
 Lee-0.047
Token!"
Token ID2474
Feature activation+1.33e+00

Pos logit contributions
 Fl+0.021
 Sn+0.019
 Ell+0.018
 Lee+0.018
 Mil+0.018
Neg logit contributions
isdom-0.028
ercise-0.027
elling-0.026
weet-0.025
ully-0.025
Token Spot
Token ID15899
Feature activation+2.47e-01

Pos logit contributions
 Sn+0.020
 Fl+0.019
 Jenkins+0.018
 Mil+0.018
 Ell+0.017
Neg logit contributions
isdom-0.047
ercise-0.045
weet-0.043
elling-0.043
night-0.043
Token bark
Token ID21405
Feature activation+5.63e-01

Pos logit contributions
 plun+0.007
 Sn+0.007
 lobby+0.007
 bathroom+0.007
 Mil+0.007
Neg logit contributions
isdom-0.004
ercise-0.004
weet-0.004
ly-0.004
ully-0.004
Token
Token ID198
Feature activation+1.08e-01

Pos logit contributions
 Mil+0.046
 Sn+0.043
 Esk+0.042
 Fl+0.042
 Ell+0.041
Neg logit contributions
isdom-0.058
ercise-0.056
weet-0.053
elling-0.051
night-0.050
Token
Token ID198
Feature activation-5.15e-01

Pos logit contributions
 Fl+0.002
 Sn+0.002
 Ell+0.002
 Mil+0.002
 Jenkins+0.002
Neg logit contributions
isdom-0.004
ercise-0.004
elling-0.004
weet-0.004
ully-0.003
Token"
Token ID1
Feature activation+3.49e+00

Pos logit contributions
isdom+0.017
elling+0.017
weet+0.016
ercise+0.016
ully+0.015
Neg logit contributions
 Fl-0.011
 Sn-0.010
 Lee-0.009
 Jenkins-0.009
 Ell-0.009
TokenW
Token ID54
Feature activation-4.17e+00

Pos logit contributions
 Fl+0.071
 Lee+0.068
 Jenkins+0.068
 Sn+0.067
 Ell+0.066
Neg logit contributions
ercise-0.103
isdom-0.098
weet-0.097
ww-0.095
 melodies-0.093
Tokenoof
Token ID37711
Feature activation-1.57e+00

Pos logit contributions
ercise+0.059
isdom+0.056
elling+0.054
weet+0.052
ully+0.051
Neg logit contributions
 Fl-0.148
 Sn-0.140
 Jenkins-0.135
 Lee-0.132
 Mil-0.131
Token,
Token ID11
Feature activation+7.52e+00

Pos logit contributions
isdom+0.045
ercise+0.042
elling+0.041
weet+0.041
ully+0.039
Neg logit contributions
 Fl-0.038
 Sn-0.037
 Ell-0.034
 Mil-0.034
 Jenkins-0.034
Token wo
Token ID24486
Feature activation-2.19e+00

Pos logit contributions
 Fl+0.189
 Sn+0.180
 Ell+0.168
 Mil+0.167
 Lee+0.165
Neg logit contributions
isdom-0.213
ercise-0.198
elling-0.196
weet-0.189
ully-0.184
Tokenof
Token ID1659
Feature activation+5.24e-01

Pos logit contributions
isdom+0.047
ercise+0.041
elling+0.038
ully+0.038
 melodies+0.038
Neg logit contributions
 Fl-0.069
 Sn-0.065
 Jenkins-0.062
 Mil-0.061
 L-0.061
Token,
Token ID11
Feature activation+6.14e+00

Pos logit contributions
 Fl+0.013
 Sn+0.013
 Ell+0.012
 Lee+0.012
 Jenkins+0.012
Neg logit contributions
isdom-0.015
ercise-0.014
elling-0.013
weet-0.013
ully-0.013
Token I
Token ID314
Feature activation+1.47e+00

Pos logit contributions
 Fl+0.154
 Sn+0.147
 Ell+0.137
 Mil+0.136
 Jenkins+0.133
Neg logit contributions
isdom-0.175
ercise-0.162
elling-0.159
weet-0.154
ully-0.150
Token'm
Token ID1101
Feature activation+5.66e-01

Pos logit contributions
 Fl+0.028
 Sn+0.027
 Jenkins+0.026
 Mil+0.026
 Ell+0.025
Neg logit contributions
isdom-0.048
ercise-0.046
weet-0.043
bye-0.043
night-0.043
TokenO
Token ID46
Feature activation-1.24e+00

Pos logit contributions
 Fl+0.095
 Sn+0.092
 Jenkins+0.088
 Ell+0.086
 Lee+0.084
Neg logit contributions
ercise-0.116
isdom-0.114
bye-0.107
ww-0.107
weet-0.106
Tokenuch
Token ID794
Feature activation+1.40e-01

Pos logit contributions
isdom+0.027
ercise+0.024
elling+0.024
weet+0.024
ully+0.022
Neg logit contributions
 Fl-0.039
 Sn-0.037
 Mil-0.036
 Ell-0.036
 Jenkins-0.035
Token!"
Token ID2474
Feature activation+1.77e+00

Pos logit contributions
 Fl+0.004
 Sn+0.004
 Ell+0.004
 Mil+0.004
 Jenkins+0.004
Neg logit contributions
isdom-0.003
elling-0.003
ercise-0.003
weet-0.003
ock-0.003
Token She
Token ID1375
Feature activation+3.17e+00

Pos logit contributions
 Sn+0.034
 Jenkins+0.033
 Esk+0.029
 Fl+0.029
 plun+0.028
Neg logit contributions
isdom-0.051
ercise-0.048
weet-0.047
night-0.047
elling-0.045
Token cries
Token ID24691
Feature activation+2.30e+00

Pos logit contributions
 Sn+0.086
 Fl+0.084
 Jenkins+0.083
 Ell+0.080
 Lee+0.077
Neg logit contributions
isdom-0.076
ercise-0.073
elling-0.070
weet-0.066
night-0.064
Token out
Token ID503
Feature activation+7.49e+00

Pos logit contributions
 Sn+0.053
 Fl+0.052
 Ell+0.050
 Jenkins+0.049
 Mil+0.049
Neg logit contributions
isdom-0.059
ly-0.057
elling-0.057
weet-0.056
night-0.056
Token.
Token ID13
Feature activation+4.17e+00

Pos logit contributions
 Sn+0.191
 Fl+0.184
 Jenkins+0.177
 Mil+0.173
 Ell+0.172
Neg logit contributions
isdom-0.178
ly-0.168
night-0.163
weet-0.162
elling-0.161
Token She
Token ID1375
Feature activation+3.23e+00

Pos logit contributions
 Esk+0.101
 Sn+0.100
 lobby+0.095
 Jenkins+0.090
 plun+0.090
Neg logit contributions
isdom-0.092
weet-0.081
iveness-0.077
ercise-0.077
ocked-0.076
Token pulls
Token ID16194
Feature activation-3.80e-01

Pos logit contributions
 Sn+0.087
 Jenkins+0.084
 Ell+0.082
 Fl+0.081
 Lee+0.077
Neg logit contributions
isdom-0.075
ercise-0.072
elling-0.070
ets-0.064
les-0.063
Token back
Token ID736
Feature activation-1.18e-01

Pos logit contributions
ock+0.008
elling+0.008
weet+0.008
isdom+0.008
ercise+0.008
Neg logit contributions
 Sn-0.010
 Fl-0.010
 Jenkins-0.009
 lobby-0.009
 Ell-0.009
Token her
Token ID607
Feature activation+8.87e-01

Pos logit contributions
isdom+0.003
elling+0.003
ercise+0.003
off+0.003
ock+0.003
Neg logit contributions
 Sn-0.003
 Fl-0.003
 Jenkins-0.003
 Mil-0.003
sed-0.003
Token.
Token ID13
Feature activation+2.81e+00

Pos logit contributions
 Fl+0.032
 Sn+0.030
 Ell+0.027
 Mil+0.027
 Jenkins+0.027
Neg logit contributions
isdom-0.055
ercise-0.051
elling-0.050
weet-0.049
ully-0.048
Token
Token ID198
Feature activation+9.23e-01

Pos logit contributions
 Sn+0.056
 Fl+0.055
 Ell+0.051
 Jenkins+0.051
 Mil+0.048
Neg logit contributions
isdom-0.089
ercise-0.082
weet-0.081
elling-0.080
ully-0.077
Token
Token ID198
Feature activation+4.50e-01

Pos logit contributions
 Fl+0.017
 Sn+0.016
 Ell+0.015
 Jenkins+0.015
 Mil+0.015
Neg logit contributions
isdom-0.031
ercise-0.029
elling-0.029
weet-0.029
off-0.028
TokenBen
Token ID11696
Feature activation+1.52e+00

Pos logit contributions
 Fl+0.011
 Sn+0.010
 Mil+0.010
 Ell+0.010
 Jenkins+0.010
Neg logit contributions
isdom-0.013
ercise-0.012
elling-0.012
weet-0.012
ully-0.011
Token cried
Token ID16896
Feature activation+1.83e+00

Pos logit contributions
 Sn+0.035
 Ell+0.035
 Jenkins+0.034
 Fl+0.033
 Flor+0.033
Neg logit contributions
ercise-0.037
isdom-0.036
ly-0.036
les-0.035
weet-0.034
Token out
Token ID503
Feature activation+7.48e+00

Pos logit contributions
 Fl+0.042
 Sn+0.042
 Mil+0.040
 Ell+0.039
 Jenkins+0.039
Neg logit contributions
isdom-0.051
ercise-0.048
elling-0.048
weet-0.047
ock-0.047
Token in
Token ID287
Feature activation+5.37e+00

Pos logit contributions
 Sn+0.192
 Fl+0.190
 Ell+0.181
 Mil+0.181
 Jenkins+0.178
Neg logit contributions
isdom-0.187
weet-0.168
elling-0.167
ercise-0.164
night-0.161
Token pain
Token ID2356
Feature activation+2.22e+00

Pos logit contributions
 Fl+0.121
 Sn+0.118
 Ell+0.112
 Mil+0.110
 Jenkins+0.109
Neg logit contributions
isdom-0.156
ercise-0.144
weet-0.144
elling-0.142
off-0.137
Token.
Token ID13
Feature activation+3.22e+00

Pos logit contributions
 Fl+0.053
 Sn+0.053
 Ell+0.051
 Mil+0.050
 Flor+0.050
Neg logit contributions
isdom-0.058
ly-0.054
ock-0.054
elling-0.053
ercise-0.053
Token He
Token ID679
Feature activation+2.54e+00

Pos logit contributions
 Sn+0.089
 Fl+0.083
 Ell+0.081
 Jenkins+0.079
 Flor+0.078
Neg logit contributions
isdom-0.075
weet-0.064
ercise-0.063
elling-0.063
iveness-0.063
Token let
Token ID1309
Feature activation-1.26e+00

Pos logit contributions
 Sn+0.051
 Fl+0.049
 Jenkins+0.049
 Lee+0.047
 Ell+0.047
Neg logit contributions
isdom-0.077
ercise-0.075
elling-0.071
weet-0.070
ly-0.069
Token
Token ID198
Feature activation+1.11e+00

Pos logit contributions
 Sn+0.067
 Fl+0.065
 Jenkins+0.064
 Mil+0.063
 Ell+0.061
Neg logit contributions
isdom-0.087
weet-0.079
ercise-0.077
elling-0.076
iveness-0.073
Token
Token ID198
Feature activation+5.28e-01

Pos logit contributions
 Fl+0.020
 Sn+0.019
 Jenkins+0.017
 Ell+0.017
 Mil+0.017
Neg logit contributions
isdom-0.038
ercise-0.036
weet-0.035
elling-0.035
off-0.034
Token"
Token ID1
Feature activation+3.98e+00

Pos logit contributions
 Fl+0.013
 Sn+0.012
 Ell+0.011
 Mil+0.011
 Jenkins+0.011
Neg logit contributions
isdom-0.016
ercise-0.014
elling-0.014
weet-0.014
ully-0.013
TokenMir
Token ID27453
Feature activation+1.08e+00

Pos logit contributions
 Fl+0.098
 Sn+0.094
 Jenkins+0.091
 Ell+0.091
 Mil+0.089
Neg logit contributions
ercise-0.104
isdom-0.103
weet-0.096
elling-0.096
off-0.095
Tokenror
Token ID1472
Feature activation+4.04e+00

Pos logit contributions
 Fl+0.030
 Sn+0.029
 Ell+0.026
 Jenkins+0.026
 Mil+0.025
Neg logit contributions
isdom-0.030
elling-0.026
ercise-0.025
weet-0.025
iper-0.024
Token,
Token ID11
Feature activation+7.46e+00

Pos logit contributions
 Sn+0.110
 Fl+0.109
 Frost+0.101
 Ell+0.100
 Jenkins+0.100
Neg logit contributions
isdom-0.094
elling-0.080
ercise-0.077
ww-0.075
heart-0.075
Token mirror
Token ID10162
Feature activation+2.28e+00

Pos logit contributions
 Fl+0.146
 Sn+0.142
 Jenkins+0.134
 Ell+0.126
 Lee+0.123
Neg logit contributions
isdom-0.234
elling-0.226
weet-0.224
ercise-0.220
ock-0.209
Token,
Token ID11
Feature activation+6.41e+00

Pos logit contributions
 Sn+0.057
 Fl+0.055
 Jenkins+0.052
 Ell+0.050
 Mil+0.050
Neg logit contributions
isdom-0.061
ercise-0.055
elling-0.054
weet-0.052
ww-0.051
Token make
Token ID787
Feature activation-2.22e+00

Pos logit contributions
 Fl+0.155
 Sn+0.154
 Jenkins+0.151
 Ell+0.141
 Mil+0.139
Neg logit contributions
isdom-0.170
ercise-0.162
weet-0.161
elling-0.159
off-0.152
Token Anna
Token ID11735
Feature activation+3.15e-01

Pos logit contributions
isdom+0.051
ercise+0.047
elling+0.046
weet+0.044
ully+0.043
Neg logit contributions
 Fl-0.067
 Sn-0.065
 Ell-0.062
 Mil-0.061
 Jenkins-0.060
Token big
Token ID1263
Feature activation+5.86e-01

Pos logit contributions
 Fl+0.006
 Sn+0.006
 Ell+0.006
 Mil+0.006
 Jenkins+0.005
Neg logit contributions
isdom-0.010
ercise-0.010
elling-0.010
weet-0.009
ully-0.009
Token the
Token ID262
Feature activation+2.46e-01

Pos logit contributions
 Sn+0.089
 Fl+0.089
 Jenkins+0.084
 Ell+0.082
 Mil+0.082
Neg logit contributions
isdom-0.130
ercise-0.121
weet-0.119
elling-0.118
off-0.113
Token head
Token ID1182
Feature activation+2.66e+00

Pos logit contributions
 Fl+0.006
 Sn+0.006
 Ell+0.005
 Mil+0.005
 Jenkins+0.005
Neg logit contributions
isdom-0.007
ercise-0.007
elling-0.007
weet-0.007
ully-0.006
Token.
Token ID13
Feature activation+2.33e+00

Pos logit contributions
 Fl+0.052
 Sn+0.050
 Ell+0.046
 Jenkins+0.045
 Mil+0.045
Neg logit contributions
isdom-0.087
ercise-0.082
elling-0.081
weet-0.081
ully-0.077
Token Tom
Token ID4186
Feature activation+8.20e-01

Pos logit contributions
 Sn+0.049
 Fl+0.048
 Jenkins+0.045
 Ell+0.044
 Mil+0.044
Neg logit contributions
isdom-0.071
ercise-0.065
weet-0.064
elling-0.064
night-0.060
Token cries
Token ID24691
Feature activation+1.96e+00

Pos logit contributions
 Sn+0.019
 Ell+0.019
 Jenkins+0.019
 Fl+0.018
 Mil+0.018
Neg logit contributions
isdom-0.020
elling-0.020
ercise-0.019
weet-0.019
off-0.018
Token out
Token ID503
Feature activation+7.46e+00

Pos logit contributions
 Sn+0.050
 Fl+0.049
 Ell+0.048
 Jenkins+0.047
 Mil+0.047
Neg logit contributions
isdom-0.048
weet-0.046
elling-0.045
ercise-0.045
night-0.044
Token in
Token ID287
Feature activation+5.17e+00

Pos logit contributions
 Sn+0.206
 Fl+0.203
 Mil+0.195
 Ell+0.193
 Jenkins+0.192
Neg logit contributions
isdom-0.173
weet-0.156
elling-0.154
ercise-0.153
night-0.149
Token pain
Token ID2356
Feature activation+1.85e+00

Pos logit contributions
 Fl+0.113
 Sn+0.111
 Ell+0.103
 Mil+0.102
 Jenkins+0.101
Neg logit contributions
isdom-0.157
ercise-0.146
elling-0.144
weet-0.144
off-0.137
Token and
Token ID290
Feature activation-1.25e+00

Pos logit contributions
 Sn+0.045
 Fl+0.045
 Ell+0.044
 Flor+0.043
 Mil+0.042
Neg logit contributions
isdom-0.046
ly-0.043
weet-0.043
ock-0.042
elling-0.042
Token falls
Token ID8953
Feature activation+9.65e-01

Pos logit contributions
ercise+0.030
isdom+0.029
elling+0.028
weet+0.028
night+0.027
Neg logit contributions
 Jenkins-0.031
 Sn-0.030
 Ell-0.028
 Fl-0.027
illi-0.027
Token to
Token ID284
Feature activation+2.91e+00

Pos logit contributions
 Fl+0.025
 Sn+0.024
 Mil+0.023
 Ell+0.023
 Jenkins+0.023
Neg logit contributions
isdom-0.024
ercise-0.023
weet-0.023
elling-0.023
ock-0.022
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
isdom+0.022
weet+0.020
ercise+0.020
elling+0.020
night+0.019
Neg logit contributions
 Sn-0.020
 Fl-0.019
 Jenkins-0.019
 Lee-0.018
 plun-0.018
Token child
Token ID1200
Feature activation-8.82e-01

Pos logit contributions
 Fl+0.031
 Sn+0.030
 Mil+0.028
 Ell+0.027
 Jenkins+0.027
Neg logit contributions
isdom-0.039
elling-0.036
weet-0.036
ercise-0.036
ully-0.034
Token l
Token ID300
Feature activation+1.54e+00

Pos logit contributions
isdom+0.030
ercise+0.028
elling+0.028
weet+0.027
off+0.026
Neg logit contributions
 Fl-0.016
 Sn-0.016
 Jenkins-0.014
 Lee-0.014
 Mil-0.014
Tokenaug
Token ID7493
Feature activation+2.88e-01

Pos logit contributions
 Fl+0.045
 Sn+0.044
 Lee+0.040
 Jenkins+0.039
 Ell+0.039
Neg logit contributions
isdom-0.038
elling-0.037
weet-0.033
iper-0.033
ully-0.033
Tokenheed
Token ID23616
Feature activation+3.60e+00

Pos logit contributions
 Fl+0.008
 Sn+0.008
 Ell+0.007
 Mil+0.007
 Jenkins+0.007
Neg logit contributions
isdom-0.007
ercise-0.007
elling-0.007
weet-0.006
ully-0.006
Token in
Token ID287
Feature activation+7.45e+00

Pos logit contributions
 Fl+0.081
 Sn+0.077
 Lee+0.073
 Mil+0.072
 Ell+0.071
Neg logit contributions
isdom-0.106
elling-0.100
ercise-0.099
weet-0.096
night-0.095
Token delight
Token ID10974
Feature activation+1.53e+00

Pos logit contributions
 Fl+0.183
 Sn+0.177
 Mil+0.165
 Ell+0.165
 Jenkins+0.164
Neg logit contributions
isdom-0.210
ercise-0.194
elling-0.191
weet-0.188
off-0.179
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
 Fl+0.030
 Sn+0.029
 Ell+0.027
 Mil+0.026
 Jenkins+0.026
Neg logit contributions
isdom-0.051
ercise-0.048
elling-0.047
weet-0.046
ully-0.045
Token
Token ID198
Feature activation+6.83e-01

Pos logit contributions
 Fl+0.015
 Sn+0.015
 Jenkins+0.013
 Mil+0.013
 Ell+0.012
Neg logit contributions
isdom-0.038
weet-0.035
ercise-0.035
elling-0.034
night-0.033
Token
Token ID198
Feature activation-2.87e-01

Pos logit contributions
 Fl+0.012
 Sn+0.012
 Jenkins+0.010
 Mil+0.010
 Ell+0.010
Neg logit contributions
isdom-0.024
ercise-0.022
weet-0.022
elling-0.022
off-0.021
Token"
Token ID1
Feature activation+2.55e+00

Pos logit contributions
isdom+0.008
ercise+0.007
elling+0.007
weet+0.007
ully+0.007
Neg logit contributions
 Fl-0.007
 Sn-0.007
 Ell-0.007
 Mil-0.007
 Jenkins-0.006
Token said
Token ID531
Feature activation+1.09e+00

Pos logit contributions
 Jenkins+0.047
 Sn+0.046
 Lee+0.045
 Ell+0.042
 Me+0.042
Neg logit contributions
isdom-0.046
ercise-0.046
night-0.041
ited-0.040
weet-0.040
Token,
Token ID11
Feature activation+5.77e+00

Pos logit contributions
 Sn+0.029
 Jenkins+0.027
 Fl+0.026
 bathroom+0.026
 plun+0.025
Neg logit contributions
isdom-0.026
ercise-0.024
night-0.023
weet-0.022
elling-0.022
Token "
Token ID366
Feature activation+4.56e+00

Pos logit contributions
 Megan+0.097
 Jenkins+0.097
 Mil+0.094
 Sn+0.092
 lobby+0.091
Neg logit contributions
isdom-0.178
ercise-0.168
weet-0.162
night-0.150
elling-0.149
TokenW
Token ID54
Feature activation-3.39e+00

Pos logit contributions
 Fl+0.097
 Sn+0.093
 Ell+0.084
 Mil+0.084
 Jenkins+0.083
Neg logit contributions
isdom-0.148
ercise-0.137
elling-0.135
weet-0.134
ully-0.129
Tokenoof
Token ID37711
Feature activation-1.19e+00

Pos logit contributions
ercise+0.045
isdom+0.045
weet+0.041
elling+0.041
ully+0.039
Neg logit contributions
 Fl-0.125
 Sn-0.119
 Jenkins-0.114
 Mil-0.113
 Ell-0.113
Token,
Token ID11
Feature activation+7.44e+00

Pos logit contributions
isdom+0.035
ercise+0.032
weet+0.032
elling+0.031
night+0.030
Neg logit contributions
 Fl-0.028
 Sn-0.027
 Mil-0.026
 Ell-0.025
 Jenkins-0.025
Token wo
Token ID24486
Feature activation-2.18e+00

Pos logit contributions
 Sn+0.201
 Fl+0.201
 Jenkins+0.195
 Ell+0.189
 Mil+0.188
Neg logit contributions
isdom-0.182
ercise-0.165
weet-0.164
elling-0.157
off-0.149
Tokenof
Token ID1659
Feature activation+6.42e-01

Pos logit contributions
isdom+0.046
ercise+0.041
 melodies+0.038
elling+0.038
ully+0.038
Neg logit contributions
 Fl-0.068
 Sn-0.065
 Jenkins-0.062
 Ell-0.061
 L-0.060
Token,
Token ID11
Feature activation+6.64e+00

Pos logit contributions
 Fl+0.016
 Sn+0.015
 Ell+0.014
 Mil+0.014
 Jenkins+0.014
Neg logit contributions
isdom-0.018
ercise-0.017
elling-0.017
weet-0.016
ully-0.016
Token wo
Token ID24486
Feature activation-2.40e+00

Pos logit contributions
 Sn+0.174
 Fl+0.174
 Jenkins+0.171
 Mil+0.165
 Ell+0.164
Neg logit contributions
isdom-0.163
ercise-0.150
weet-0.149
elling-0.142
off-0.136
Tokenof
Token ID1659
Feature activation+5.26e-01

Pos logit contributions
isdom+0.052
ercise+0.045
ully+0.042
elling+0.042
 melodies+0.042
Neg logit contributions
 Fl-0.075
 Sn-0.072
 Jenkins-0.068
 Ell-0.067
 L-0.066
Token said
Token ID531
Feature activation+1.58e+00

Pos logit contributions
isdom+0.043
ercise+0.041
weet+0.039
elling+0.038
night+0.036
Neg logit contributions
 Sn-0.045
 Fl-0.045
 Jenkins-0.043
 Mil-0.041
 Ell-0.041
Token,
Token ID11
Feature activation+5.74e+00

Pos logit contributions
 Sn+0.042
 Jenkins+0.041
 Fl+0.040
 bathroom+0.038
 plun+0.038
Neg logit contributions
isdom-0.038
ercise-0.034
night-0.032
weet-0.032
bye-0.031
Token "
Token ID366
Feature activation+4.35e+00

Pos logit contributions
 Fl+0.085
 Jenkins+0.081
 Sn+0.081
 Megan+0.079
 Mil+0.077
Neg logit contributions
isdom-0.197
ercise-0.185
weet-0.182
elling-0.171
iveness-0.170
TokenW
Token ID54
Feature activation-3.25e+00

Pos logit contributions
 Fl+0.098
 Sn+0.098
 Ell+0.086
 Mil+0.085
 Lee+0.084
Neg logit contributions
isdom-0.141
elling-0.126
ercise-0.124
iper-0.122
ully-0.121
Tokenoof
Token ID37711
Feature activation-1.04e+00

Pos logit contributions
ercise+0.045
isdom+0.041
weet+0.038
ully+0.038
elling+0.038
Neg logit contributions
 Fl-0.117
 Sn-0.112
 Ell-0.110
 Mil-0.108
 Lee-0.108
Token,
Token ID11
Feature activation+7.44e+00

Pos logit contributions
isdom+0.031
ercise+0.029
weet+0.028
elling+0.028
ully+0.027
Neg logit contributions
 Fl-0.024
 Sn-0.023
 Mil-0.022
 Ell-0.021
 Jenkins-0.021
Token wo
Token ID24486
Feature activation-2.10e+00

Pos logit contributions
 Fl+0.186
 Sn+0.177
 Ell+0.165
 Mil+0.164
 Lee+0.163
Neg logit contributions
isdom-0.212
ercise-0.199
elling-0.197
weet-0.188
ully-0.186
Tokenof
Token ID1659
Feature activation+1.00e+00

Pos logit contributions
isdom+0.044
ercise+0.040
ully+0.038
elling+0.037
 melodies+0.037
Neg logit contributions
 Fl-0.064
 Sn-0.062
 Jenkins-0.058
 Ell-0.058
 Lee-0.057
Token!"
Token ID2474
Feature activation+1.48e+00

Pos logit contributions
 Fl+0.024
 Sn+0.023
 Ell+0.021
 Mil+0.021
 Jenkins+0.021
Neg logit contributions
isdom-0.029
ercise-0.027
elling-0.027
weet-0.026
ully-0.025
Token
Token ID198
Feature activation+1.94e-01

Pos logit contributions
 Fl+0.025
 Sn+0.024
 Ell+0.021
 Mil+0.021
 Jenkins+0.021
Neg logit contributions
isdom-0.053
ercise-0.050
elling-0.049
weet-0.049
ully-0.047
Token
Token ID198
Feature activation-3.28e-01

Pos logit contributions
 Fl+0.003
 Sn+0.003
 Ell+0.003
 Mil+0.003
 Jenkins+0.003
Neg logit contributions
isdom-0.007
ercise-0.007
elling-0.006
weet-0.006
ully-0.006
Token his
Token ID465
Feature activation+2.15e+00

Pos logit contributions
 Sn+0.128
 Jenkins+0.126
 Fl+0.122
 Flor+0.121
 Ell+0.120
Neg logit contributions
isdom-0.091
weet-0.089
ock-0.079
elling-0.077
off-0.076
Token heel
Token ID24703
Feature activation+1.28e+00

Pos logit contributions
 Fl+0.043
 Sn+0.041
 Ell+0.038
 Mil+0.038
 Jenkins+0.037
Neg logit contributions
isdom-0.072
ercise-0.067
elling-0.066
weet-0.065
ully-0.063
Token.
Token ID13
Feature activation+2.44e+00

Pos logit contributions
 Fl+0.029
 Sn+0.029
 Mil+0.028
 Ell+0.028
 Jenkins+0.027
Neg logit contributions
isdom-0.034
weet-0.033
ercise-0.032
ock-0.032
elling-0.032
Token He
Token ID679
Feature activation+2.73e+00

Pos logit contributions
 Sn+0.066
 Fl+0.061
 Flor+0.059
 Jenkins+0.059
 t+0.058
Neg logit contributions
isdom-0.059
weet-0.051
ully-0.050
elling-0.050
ercise-0.049
Token cried
Token ID16896
Feature activation+2.21e+00

Pos logit contributions
 Sn+0.058
 Jenkins+0.057
 Lee+0.055
 Fl+0.055
 Ell+0.053
Neg logit contributions
isdom-0.077
ercise-0.074
weet-0.071
elling-0.070
night-0.069
Token out
Token ID503
Feature activation+7.41e+00

Pos logit contributions
 Fl+0.052
 Sn+0.051
 Mil+0.050
 Ell+0.049
 Jenkins+0.049
Neg logit contributions
isdom-0.059
weet-0.056
ercise-0.055
elling-0.055
ock-0.055
Token loud
Token ID7812
Feature activation+1.53e+00

Pos logit contributions
 Sn+0.197
 Fl+0.193
 Mil+0.189
 Ell+0.185
 Jenkins+0.185
Neg logit contributions
isdom-0.177
weet-0.162
elling-0.155
ercise-0.153
night-0.152
Token.
Token ID13
Feature activation+2.87e+00

Pos logit contributions
 Fl+0.034
 Sn+0.033
 Mil+0.031
 Ell+0.031
 Jenkins+0.031
Neg logit contributions
isdom-0.045
ercise-0.042
elling-0.042
weet-0.041
night-0.040
Token
Token ID198
Feature activation+1.22e+00

Pos logit contributions
 Sn+0.071
 Fl+0.065
 Flor+0.064
 Jenkins+0.063
 Mil+0.062
Neg logit contributions
isdom-0.073
ully-0.062
weet-0.062
ercise-0.062
elling-0.060
Token
Token ID198
Feature activation+6.17e-01

Pos logit contributions
 Sn+0.024
 Fl+0.024
 Jenkins+0.022
 Lee+0.022
 Ell+0.022
Neg logit contributions
isdom-0.038
weet-0.035
elling-0.035
ercise-0.035
off-0.034
TokenSam
Token ID16305
Feature activation+1.21e+00

Pos logit contributions
 Fl+0.016
 Sn+0.016
 Ell+0.015
 Mil+0.015
 Jenkins+0.015
Neg logit contributions
isdom-0.017
ercise-0.015
elling-0.015
weet-0.015
ully-0.014
Token'm
Token ID1101
Feature activation+1.33e+00

Pos logit contributions
 Sn+0.034
 Fl+0.034
 Lee+0.030
 Mil+0.030
 Ell+0.030
Neg logit contributions
isdom-0.068
ercise-0.063
weet-0.061
elling-0.061
night-0.060
Token sorry
Token ID7926
Feature activation-1.87e-01

Pos logit contributions
 Sn+0.027
 Jenkins+0.026
 Fl+0.026
 Lee+0.025
 Ell+0.024
Neg logit contributions
isdom-0.040
weet-0.039
ercise-0.038
elling-0.037
ock-0.035
Token!"
Token ID2474
Feature activation+2.39e+00

Pos logit contributions
isdom+0.005
ercise+0.005
elling+0.005
weet+0.005
ock+0.004
Neg logit contributions
 Sn-0.004
 Fl-0.004
 Jenkins-0.004
 Mil-0.004
 Ell-0.004
Token Sara
Token ID24799
Feature activation+1.13e+00

Pos logit contributions
 Sn+0.027
 Jenkins+0.025
 Fl+0.024
 Lee+0.021
 Ell+0.020
Neg logit contributions
isdom-0.091
weet-0.086
elling-0.085
night-0.085
ercise-0.085
Token said
Token ID531
Feature activation+2.07e+00

Pos logit contributions
 Sn+0.036
 Jenkins+0.034
 Fl+0.034
 Ell+0.033
 lobby+0.032
Neg logit contributions
isdom-0.019
ly-0.018
weet-0.018
elling-0.017
ercise-0.017
Token,
Token ID11
Feature activation+7.40e+00

Pos logit contributions
 Sn+0.050
 Fl+0.049
 Mil+0.045
 Jenkins+0.045
 Ell+0.045
Neg logit contributions
isdom-0.056
elling-0.051
ercise-0.051
night-0.050
ly-0.050
Token hugging
Token ID46292
Feature activation-1.08e+00

Pos logit contributions
 Sn+0.152
 Fl+0.151
 Mil+0.150
 Jenkins+0.147
 Ell+0.146
Neg logit contributions
isdom-0.200
weet-0.196
ercise-0.187
ly-0.185
 melody-0.180
Token her
Token ID607
Feature activation+3.18e+00

Pos logit contributions
isdom+0.027
ercise+0.026
elling+0.026
ock+0.025
night+0.025
Neg logit contributions
 Sn-0.026
 Fl-0.024
 Ell-0.024
 Jenkins-0.024
 plun-0.024
Token brother
Token ID3956
Feature activation-1.36e-01

Pos logit contributions
 Sn+0.072
 Ell+0.070
 Mil+0.069
 Fl+0.069
 lobby+0.066
Neg logit contributions
isdom-0.083
ercise-0.078
elling-0.077
ly-0.076
ully-0.075
Token.
Token ID13
Feature activation+3.19e+00

Pos logit contributions
isdom+0.003
ly+0.003
night+0.003
ercise+0.003
weet+0.003
Neg logit contributions
 Sn-0.003
 Mil-0.003
 Ell-0.003
 Fl-0.003
 Jenkins-0.003
Token "
Token ID366
Feature activation+5.20e+00

Pos logit contributions
 Sn+0.069
 Esk+0.065
 Ell+0.065
 Fl+0.065
 lobby+0.063
Neg logit contributions
isdom-0.088
weet-0.080
ercise-0.078
elling-0.075
iveness-0.074
Token's
Token ID338
Feature activation+2.37e+00

Pos logit contributions
isdom+0.000
ercise+0.000
elling+0.000
weet+0.000
ully+0.000
Neg logit contributions
 Fl-0.000
 Sn-0.000
 Ell-0.000
 Mil-0.000
 Jenkins-0.000
Token hand
Token ID1021
Feature activation+7.07e-01

Pos logit contributions
 Fl+0.048
 Sn+0.048
 Ell+0.046
 Jenkins+0.044
 Mil+0.043
Neg logit contributions
isdom-0.072
ercise-0.067
ully-0.066
elling-0.065
weet-0.065
Token.
Token ID13
Feature activation+2.30e+00

Pos logit contributions
 Fl+0.015
 Sn+0.014
 Ell+0.014
 Mil+0.013
 Jenkins+0.013
Neg logit contributions
isdom-0.022
ercise-0.020
weet-0.020
elling-0.020
ully-0.019
Token Jill
Token ID22772
Feature activation+2.81e-01

Pos logit contributions
 Fl+0.049
 Sn+0.049
 Jenkins+0.043
 Ell+0.043
 Mil+0.042
Neg logit contributions
isdom-0.072
weet-0.065
elling-0.065
ercise-0.065
ully-0.062
Token cried
Token ID16896
Feature activation+2.03e+00

Pos logit contributions
 Sn+0.007
 Jenkins+0.006
 Fl+0.006
 Ell+0.006
 Mil+0.006
Neg logit contributions
isdom-0.007
weet-0.007
ercise-0.007
ly-0.007
elling-0.006
Token out
Token ID503
Feature activation+7.38e+00

Pos logit contributions
 Fl+0.053
 Sn+0.053
 Mil+0.051
 Ell+0.050
 Jenkins+0.050
Neg logit contributions
isdom-0.050
ercise-0.046
weet-0.046
elling-0.046
night-0.044
Token in
Token ID287
Feature activation+5.42e+00

Pos logit contributions
 Sn+0.199
 Fl+0.198
 Mil+0.189
 Ell+0.186
 Jenkins+0.184
Neg logit contributions
isdom-0.179
weet-0.160
ercise-0.158
elling-0.158
night-0.152
Token pain
Token ID2356
Feature activation+2.16e+00

Pos logit contributions
 Fl+0.118
 Sn+0.115
 Ell+0.107
 Mil+0.107
 Jenkins+0.105
Neg logit contributions
isdom-0.166
ercise-0.154
elling-0.152
weet-0.151
off-0.145
Token and
Token ID290
Feature activation-1.42e+00

Pos logit contributions
 Sn+0.057
 Fl+0.057
 Ell+0.054
 Mil+0.054
 Jenkins+0.053
Neg logit contributions
isdom-0.051
ly-0.047
weet-0.046
elling-0.046
ercise-0.045
Token dropped
Token ID5710
Feature activation+5.08e-01

Pos logit contributions
isdom+0.036
ercise+0.035
weet+0.035
ly+0.034
night+0.034
Neg logit contributions
 Sn-0.033
 Jenkins-0.033
 Fl-0.030
 Ell-0.030
 Me-0.029
Token her
Token ID607
Feature activation+1.74e+00

Pos logit contributions
 Sn+0.012
 Fl+0.012
 Jenkins+0.011
 Ell+0.011
 Mil+0.011
Neg logit contributions
isdom-0.014
ercise-0.013
elling-0.013
weet-0.012
off-0.012
Token falls
Token ID8953
Feature activation+1.22e+00

Pos logit contributions
 Fl+0.060
 Sn+0.059
 Jenkins+0.056
 Ell+0.056
 Mil+0.055
Neg logit contributions
isdom-0.074
ercise-0.070
elling-0.068
weet-0.067
off-0.064
Token down
Token ID866
Feature activation+5.39e+00

Pos logit contributions
 Fl+0.032
 Sn+0.031
 Mil+0.030
 Ell+0.030
 Jenkins+0.030
Neg logit contributions
isdom-0.030
ercise-0.028
elling-0.028
weet-0.028
ock-0.027
Token.
Token ID13
Feature activation+2.69e+00

Pos logit contributions
 Fl+0.134
 Mil+0.133
 Sn+0.132
 Flor+0.130
 Ell+0.129
Neg logit contributions
ock-0.119
weet-0.117
isdom-0.117
elling-0.109
ear-0.108
Token He
Token ID679
Feature activation+2.83e+00

Pos logit contributions
 Sn+0.057
 Fl+0.056
 Jenkins+0.054
 Ell+0.052
 Mil+0.052
Neg logit contributions
isdom-0.075
weet-0.071
elling-0.068
ercise-0.067
ock-0.065
Token cries
Token ID24691
Feature activation+2.56e+00

Pos logit contributions
 Fl+0.070
 Sn+0.068
 Ell+0.064
 Jenkins+0.064
 Mil+0.063
Neg logit contributions
isdom-0.078
ercise-0.073
elling-0.071
weet-0.070
off-0.067
Token out
Token ID503
Feature activation+7.38e+00

Pos logit contributions
 Fl+0.055
 Sn+0.055
 Ell+0.052
 Mil+0.052
 Jenkins+0.052
Neg logit contributions
isdom-0.074
weet-0.070
ercise-0.069
elling-0.069
ock-0.068
Token loud
Token ID7812
Feature activation+2.00e+00

Pos logit contributions
 Sn+0.196
 Fl+0.192
 Mil+0.184
 Jenkins+0.183
 Ell+0.182
Neg logit contributions
isdom-0.177
weet-0.162
elling-0.156
ercise-0.154
night-0.153
Token.
Token ID13
Feature activation+3.31e+00

Pos logit contributions
 Fl+0.041
 Sn+0.041
 Ell+0.038
 Mil+0.037
 Jenkins+0.037
Neg logit contributions
isdom-0.063
ercise-0.058
elling-0.058
weet-0.057
night-0.055
Token
Token ID198
Feature activation+1.21e+00

Pos logit contributions
 Sn+0.073
 Fl+0.069
 Jenkins+0.069
 Flor+0.067
 Mil+0.067
Neg logit contributions
isdom-0.083
weet-0.076
iveness-0.072
elling-0.070
ercise-0.070
Token
Token ID198
Feature activation+9.80e-01

Pos logit contributions
 Sn+0.024
 Fl+0.023
 Jenkins+0.022
 Ell+0.022
 Mil+0.022
Neg logit contributions
isdom-0.038
weet-0.035
elling-0.034
ercise-0.034
off-0.033
TokenL
Token ID43
Feature activation+1.32e+00

Pos logit contributions
 Fl+0.025
 Sn+0.024
 Ell+0.023
 Jenkins+0.023
 Mil+0.023
Neg logit contributions
isdom-0.026
ercise-0.024
elling-0.023
weet-0.023
off-0.023
Token the
Token ID262
Feature activation+7.99e-01

Pos logit contributions
 Jenkins+0.064
 Sn+0.061
 Mil+0.059
illi+0.057
robe+0.057
Neg logit contributions
isdom-0.049
weet-0.048
ock-0.046
away-0.045
ercise-0.043
Token ground
Token ID2323
Feature activation+3.36e+00

Pos logit contributions
 Ell+0.017
 Mil+0.017
 Sn+0.017
 Fl+0.017
 Mir+0.016
Neg logit contributions
ercise-0.022
isdom-0.021
bye-0.020
elling-0.020
weet-0.020
Token.
Token ID13
Feature activation+1.91e+00

Pos logit contributions
 Sn+0.087
 Fl+0.084
 Mil+0.083
 Ell+0.083
 Jenkins+0.080
Neg logit contributions
isdom-0.075
ock-0.073
ly-0.072
weet-0.071
ear-0.070
Token Max
Token ID5436
Feature activation+5.07e-01

Pos logit contributions
 Sn+0.044
 Mil+0.044
 Fl+0.044
 Jenkins+0.043
 Megan+0.043
Neg logit contributions
isdom-0.050
ercise-0.045
weet-0.044
night-0.043
elling-0.043
Token cried
Token ID16896
Feature activation+1.76e+00

Pos logit contributions
 Jenkins+0.013
 Ell+0.013
 Sn+0.013
 Mil+0.012
 Flor+0.012
Neg logit contributions
ly-0.010
ercise-0.010
ets-0.010
les-0.010
night-0.009
Token out
Token ID503
Feature activation+7.37e+00

Pos logit contributions
 Fl+0.042
 Sn+0.041
 Mil+0.041
 Jenkins+0.040
 Ell+0.040
Neg logit contributions
isdom-0.046
weet-0.043
ercise-0.043
ock-0.043
elling-0.043
Token.
Token ID13
Feature activation+2.52e+00

Pos logit contributions
 Sn+0.206
 Fl+0.205
 Mil+0.201
 Ell+0.197
 Jenkins+0.196
Neg logit contributions
isdom-0.163
weet-0.146
elling-0.142
ercise-0.141
night-0.141
Token Lily
Token ID20037
Feature activation+7.22e-01

Pos logit contributions
 Mil+0.061
 Megan+0.061
 Sn+0.060
 Jenkins+0.059
 Ell+0.058
Neg logit contributions
isdom-0.058
ercise-0.051
weet-0.050
night-0.049
iveness-0.048
Token ran
Token ID4966
Feature activation-1.36e-01

Pos logit contributions
 Sn+0.021
 Ell+0.020
 Mil+0.020
 Jenkins+0.020
 Flor+0.020
Neg logit contributions
ly-0.013
les-0.012
night-0.012
ercise-0.012
ets-0.012
Token to
Token ID284
Feature activation+2.11e+00

Pos logit contributions
ercise+0.002
night+0.002
ly+0.002
isdom+0.002
ear+0.002
Neg logit contributions
 Mil-0.004
 Sn-0.004
 Fl-0.004
 Mir-0.004
 Jenkins-0.004
Token help
Token ID1037
Feature activation-4.18e-01

Pos logit contributions
 Jenkins+0.062
 Mil+0.062
 Sn+0.061
pit+0.059
tub+0.059
Neg logit contributions
isdom-0.036
weet-0.033
ock-0.032
ercise-0.032
night-0.029
Token's
Token ID338
Feature activation+1.88e+00

Pos logit contributions
 Fl+0.008
 Sn+0.008
 Ell+0.008
 Mil+0.008
 Jenkins+0.007
Neg logit contributions
isdom-0.010
ercise-0.009
elling-0.009
weet-0.009
ully-0.008
Token hand
Token ID1021
Feature activation+8.99e-01

Pos logit contributions
 Sn+0.037
 Fl+0.037
 Ell+0.035
 Mil+0.033
 Jenkins+0.033
Neg logit contributions
isdom-0.059
ercise-0.055
elling-0.055
weet-0.055
bye-0.053
Token.
Token ID13
Feature activation+2.38e+00

Pos logit contributions
 Fl+0.018
 Sn+0.017
 Ell+0.016
 Mil+0.016
 Jenkins+0.015
Neg logit contributions
isdom-0.030
ercise-0.028
elling-0.027
weet-0.027
ully-0.026
Token Tom
Token ID4186
Feature activation+3.49e-01

Pos logit contributions
 Sn+0.058
 Fl+0.057
 Jenkins+0.056
 Ell+0.054
 Mil+0.052
Neg logit contributions
isdom-0.064
weet-0.058
ercise-0.058
elling-0.057
ear-0.053
Token cries
Token ID24691
Feature activation+1.94e+00

Pos logit contributions
 Sn+0.010
 Ell+0.009
 Jenkins+0.009
 Mil+0.009
 Fl+0.009
Neg logit contributions
isdom-0.007
ercise-0.007
elling-0.007
weet-0.007
off-0.007
Token out
Token ID503
Feature activation+7.36e+00

Pos logit contributions
 Sn+0.048
 Fl+0.047
 Jenkins+0.046
 Ell+0.046
 Mil+0.045
Neg logit contributions
isdom-0.048
weet-0.046
elling-0.046
ercise-0.046
night-0.045
Token.
Token ID13
Feature activation+2.69e+00

Pos logit contributions
 Fl+0.188
 Sn+0.188
 Jenkins+0.177
 Ell+0.176
 Mil+0.176
Neg logit contributions
isdom-0.186
weet-0.168
elling-0.168
ercise-0.167
night-0.162
Token He
Token ID679
Feature activation+2.19e+00

Pos logit contributions
 Sn+0.064
 Jenkins+0.063
 t+0.058
 Ell+0.058
 wra+0.058
Neg logit contributions
isdom-0.067
weet-0.060
ercise-0.058
elling-0.056
ear-0.055
Token lets
Token ID8781
Feature activation-6.72e-01

Pos logit contributions
 Sn+0.050
 Fl+0.049
 Jenkins+0.048
 Ell+0.047
 Mil+0.046
Neg logit contributions
isdom-0.062
ercise-0.059
elling-0.057
weet-0.055
off-0.053
Token go
Token ID467
Feature activation-1.84e+00

Pos logit contributions
isdom+0.015
ercise+0.015
weet+0.014
ock+0.014
elling+0.014
Neg logit contributions
 Sn-0.018
 Jenkins-0.018
 Fl-0.017
 Ell-0.017
 Mil-0.017
Token of
Token ID286
Feature activation+3.52e-01

Pos logit contributions
isdom+0.029
elling+0.027
weet+0.026
ock+0.026
ercise+0.026
Neg logit contributions
 Fl-0.063
 Sn-0.063
 Jenkins-0.060
 Mil-0.060
 Ell-0.059
Token her
Token ID607
Feature activation+1.57e+00

Pos logit contributions
 Sn+0.000
 Fl+0.000
 Jenkins+0.000
 Ell+0.000
 Mil+0.000
Neg logit contributions
isdom-0.001
ercise-0.001
elling-0.001
weet-0.001
ear-0.001
Token finger
Token ID7660
Feature activation-1.02e-01

Pos logit contributions
 Fl+0.029
 Sn+0.029
 Ell+0.026
 Jenkins+0.026
 Mil+0.026
Neg logit contributions
isdom-0.053
ercise-0.050
elling-0.049
weet-0.049
off-0.047
Token.
Token ID13
Feature activation+2.07e+00

Pos logit contributions
isdom+0.003
ercise+0.003
elling+0.003
weet+0.003
ully+0.003
Neg logit contributions
 Fl-0.002
 Sn-0.002
 Ell-0.002
 Mil-0.002
 Jenkins-0.002
Token Lily
Token ID20037
Feature activation+6.50e-01

Pos logit contributions
 Sn+0.044
 Fl+0.043
 Jenkins+0.041
 Ell+0.039
 Mil+0.039
Neg logit contributions
isdom-0.061
elling-0.056
weet-0.055
ercise-0.054
iveness-0.051
Token cried
Token ID16896
Feature activation+1.91e+00

Pos logit contributions
 Sn+0.015
 Jenkins+0.015
 Lee+0.014
 Ell+0.014
 Mil+0.013
Neg logit contributions
isdom-0.016
ly-0.015
weet-0.015
ercise-0.015
ets-0.014
Token out
Token ID503
Feature activation+7.36e+00

Pos logit contributions
 Fl+0.040
 Sn+0.039
 Mil+0.037
 Ell+0.037
 Jenkins+0.036
Neg logit contributions
isdom-0.059
ercise-0.055
elling-0.055
weet-0.054
night-0.052
Token loud
Token ID7812
Feature activation+1.48e+00

Pos logit contributions
 Sn+0.204
 Fl+0.202
 Mil+0.195
 Ell+0.191
 Jenkins+0.190
Neg logit contributions
isdom-0.173
weet-0.154
elling-0.151
ercise-0.150
night-0.145
Token.
Token ID13
Feature activation+2.64e+00

Pos logit contributions
 Fl+0.030
 Sn+0.029
 Mil+0.027
 Ell+0.027
 Jenkins+0.027
Neg logit contributions
isdom-0.047
ercise-0.044
elling-0.044
weet-0.043
night-0.041
Token
Token ID198
Feature activation+9.20e-01

Pos logit contributions
 Sn+0.060
 Fl+0.056
 t+0.053
 plun+0.053
 Mil+0.052
Neg logit contributions
isdom-0.073
weet-0.065
elling-0.065
ercise-0.064
iveness-0.062
Token
Token ID198
Feature activation+4.82e-01

Pos logit contributions
 Fl+0.017
 Sn+0.017
 Jenkins+0.015
 Ell+0.015
 Mil+0.015
Neg logit contributions
isdom-0.031
ercise-0.028
weet-0.028
elling-0.028
off-0.027
Token"
Token ID1
Feature activation+3.87e+00

Pos logit contributions
 Fl+0.012
 Sn+0.011
 Ell+0.010
 Mil+0.010
 Jenkins+0.010
Neg logit contributions
isdom-0.014
ercise-0.013
elling-0.013
weet-0.013
ully-0.012
Token,
Token ID11
Feature activation+4.99e+00

Pos logit contributions
isdom+0.022
ercise+0.020
elling+0.020
weet+0.020
ully+0.019
Neg logit contributions
 Fl-0.013
 Sn-0.012
 Ell-0.011
 Mil-0.011
 Jenkins-0.011
Token okay
Token ID8788
Feature activation-8.15e-01

Pos logit contributions
 Fl+0.109
 Sn+0.109
 Jenkins+0.105
 Ell+0.101
 Mil+0.099
Neg logit contributions
isdom-0.146
weet-0.134
ercise-0.133
elling-0.129
ock-0.124
Token?"
Token ID1701
Feature activation+2.57e+00

Pos logit contributions
isdom+0.019
ercise+0.018
elling+0.017
weet+0.017
ully+0.016
Neg logit contributions
 Fl-0.024
 Sn-0.023
 Ell-0.022
 Mil-0.022
 Jenkins-0.022
Token mom
Token ID1995
Feature activation-2.84e-01

Pos logit contributions
 Sn+0.045
 Fl+0.043
 Jenkins+0.042
 plun+0.041
 Ell+0.039
Neg logit contributions
isdom-0.083
ercise-0.075
weet-0.074
night-0.074
bye-0.072
Token says
Token ID1139
Feature activation+3.87e+00

Pos logit contributions
isdom+0.007
elling+0.006
ercise+0.006
weet+0.006
off+0.006
Neg logit contributions
 Fl-0.008
 Sn-0.008
 Ell-0.008
 Mil-0.008
 Jenkins-0.008
Token,
Token ID11
Feature activation+7.35e+00

Pos logit contributions
 Sn+0.101
 Fl+0.097
 Mil+0.091
 Jenkins+0.091
 Ell+0.090
Neg logit contributions
isdom-0.095
ly-0.091
night-0.086
elling-0.086
weet-0.083
Token hugging
Token ID46292
Feature activation-6.17e-01

Pos logit contributions
 Mil+0.150
 Fl+0.150
 Sn+0.145
 Jenkins+0.144
 Ell+0.144
Neg logit contributions
isdom-0.202
weet-0.189
ercise-0.181
ly-0.176
iveness-0.174
Token Anna
Token ID11735
Feature activation+1.42e+00

Pos logit contributions
isdom+0.019
ly+0.019
night+0.018
ock+0.018
elling+0.018
Neg logit contributions
 Sn-0.011
 plun-0.010
 Fl-0.010
 Mil-0.009
 Esk-0.009
Token.
Token ID13
Feature activation+3.34e+00

Pos logit contributions
 Sn+0.036
 Mil+0.035
 Fl+0.034
 plun+0.034
 Ell+0.034
Neg logit contributions
isdom-0.033
ly-0.031
night-0.031
weet-0.030
off-0.030
Token
Token ID198
Feature activation+7.22e-01

Pos logit contributions
 Esk+0.084
 Sn+0.081
 plun+0.079
 lobby+0.076
 Mil+0.076
Neg logit contributions
isdom-0.069
weet-0.065
night-0.065
ercise-0.061
elling-0.061
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
 Sn+0.016
 Jenkins+0.015
 Lee+0.015
 Mil+0.015
 Fl+0.015
Neg logit contributions
isdom-0.019
weet-0.018
off-0.017
elling-0.017
ercise-0.017
Token says
Token ID1139
Feature activation+2.43e+00

Pos logit contributions
 Sn+0.024
 Jenkins+0.023
 Fl+0.023
 Lee+0.022
 Ell+0.022
Neg logit contributions
ercise-0.028
isdom-0.028
elling-0.026
weet-0.026
night-0.025
Token,
Token ID11
Feature activation+5.04e+00

Pos logit contributions
 Sn+0.060
 Jenkins+0.059
 Fl+0.056
 bathroom+0.055
 Mil+0.054
Neg logit contributions
isdom-0.064
ercise-0.058
weet-0.056
elling-0.055
bye-0.054
Token "
Token ID366
Feature activation+4.73e+00

Pos logit contributions
 Fl+0.067
 Sn+0.066
 Jenkins+0.065
 Ell+0.062
 Mil+0.061
Neg logit contributions
isdom-0.185
ercise-0.176
weet-0.173
elling-0.165
ully-0.161
TokenW
Token ID54
Feature activation-3.07e+00

Pos logit contributions
 Fl+0.104
 Sn+0.100
 Mil+0.089
 Ell+0.088
 Jenkins+0.084
Neg logit contributions
isdom-0.155
elling-0.141
ercise-0.139
weet-0.135
iper-0.135
Tokenoof
Token ID37711
Feature activation-8.13e-01

Pos logit contributions
ercise+0.042
isdom+0.042
elling+0.040
weet+0.038
ully+0.036
Neg logit contributions
 Fl-0.112
 Sn-0.105
 Lee-0.101
 Frost-0.101
 Mil-0.099
Token,
Token ID11
Feature activation+7.35e+00

Pos logit contributions
isdom+0.024
ercise+0.022
elling+0.022
weet+0.022
ully+0.021
Neg logit contributions
 Fl-0.019
 Sn-0.018
 Ell-0.017
 Mil-0.017
 Jenkins-0.017
Token wo
Token ID24486
Feature activation-1.86e+00

Pos logit contributions
 Fl+0.184
 Sn+0.175
 Ell+0.162
 Mil+0.162
 Lee+0.160
Neg logit contributions
isdom-0.210
ercise-0.195
elling-0.194
weet-0.186
ully-0.182
Tokenof
Token ID1659
Feature activation+9.18e-01

Pos logit contributions
isdom+0.040
ercise+0.035
 melodies+0.034
elling+0.033
ully+0.032
Neg logit contributions
 Fl-0.057
 Sn-0.054
 Jenkins-0.052
 L-0.051
 Mil-0.051
Token,
Token ID11
Feature activation+6.53e+00

Pos logit contributions
 Fl+0.023
 Sn+0.021
 Ell+0.020
 Lee+0.020
 Mil+0.019
Neg logit contributions
isdom-0.026
ercise-0.025
elling-0.024
weet-0.023
ully-0.023
Token my
Token ID616
Feature activation+3.28e+00

Pos logit contributions
 Fl+0.165
 Sn+0.159
 Ell+0.149
 Mil+0.148
 Jenkins+0.147
Neg logit contributions
isdom-0.181
ercise-0.168
elling-0.164
weet-0.162
ully-0.155
Token name
Token ID1438
Feature activation+1.53e+00

Pos logit contributions
 Fl+0.067
 Sn+0.066
 Mil+0.062
 Ell+0.062
 Jenkins+0.061
Neg logit contributions
isdom-0.104
ercise-0.096
weet-0.094
elling-0.094
bye-0.091
Token five
Token ID1936
Feature activation+1.82e+00

Pos logit contributions
 Fl+0.106
 Sn+0.101
 Ell+0.093
 Jenkins+0.093
 Mil+0.092
Neg logit contributions
isdom-0.163
ercise-0.153
elling-0.150
weet-0.149
ully-0.142
Token,
Token ID11
Feature activation+5.19e+00

Pos logit contributions
 Fl+0.044
 Sn+0.044
 Jenkins+0.040
 Ell+0.039
 Lee+0.038
Neg logit contributions
isdom-0.051
ercise-0.047
elling-0.047
weet-0.046
off-0.044
Token six
Token ID2237
Feature activation+1.55e+00

Pos logit contributions
 Fl+0.109
 Sn+0.104
 Ell+0.096
 Jenkins+0.096
 Mil+0.095
Neg logit contributions
isdom-0.165
ercise-0.155
elling-0.152
weet-0.150
ully-0.144
Token,
Token ID11
Feature activation+5.79e+00

Pos logit contributions
 Fl+0.036
 Sn+0.036
 Jenkins+0.033
 Ell+0.032
 Mil+0.031
Neg logit contributions
isdom-0.045
ercise-0.041
elling-0.041
weet-0.040
off-0.039
Token seven
Token ID3598
Feature activation+1.19e-01

Pos logit contributions
 Fl+0.145
 Sn+0.140
 Jenkins+0.132
 Ell+0.131
 Mil+0.129
Neg logit contributions
isdom-0.158
ercise-0.148
elling-0.144
weet-0.143
off-0.135
Token,
Token ID11
Feature activation+7.34e+00

Pos logit contributions
 Fl+0.003
 Sn+0.003
 Jenkins+0.002
 Ell+0.002
 Mil+0.002
Neg logit contributions
isdom-0.004
ercise-0.003
elling-0.003
weet-0.003
off-0.003
Token eight
Token ID3624
Feature activation+2.61e+00

Pos logit contributions
 Fl+0.151
 Sn+0.144
 Jenkins+0.135
 Ell+0.133
 Mil+0.130
Neg logit contributions
isdom-0.233
ercise-0.220
elling-0.215
weet-0.214
off-0.204
Token,
Token ID11
Feature activation+5.54e+00

Pos logit contributions
 Fl+0.061
 Sn+0.061
 Jenkins+0.057
 Ell+0.055
 Mil+0.053
Neg logit contributions
isdom-0.073
ercise-0.068
elling-0.067
weet-0.066
off-0.064
Token nine
Token ID5193
Feature activation+2.23e+00

Pos logit contributions
 Fl+0.110
 Sn+0.105
 Jenkins+0.097
 Ell+0.096
 Mil+0.095
Neg logit contributions
isdom-0.181
ercise-0.171
elling-0.168
weet-0.166
off-0.159
Token,
Token ID11
Feature activation+5.51e+00

Pos logit contributions
 Fl+0.049
 Sn+0.048
 Jenkins+0.044
 Ell+0.044
 Mil+0.043
Neg logit contributions
isdom-0.068
ercise-0.063
elling-0.062
weet-0.062
off-0.059
Token ten
Token ID3478
Feature activation+2.85e+00

Pos logit contributions
 Fl+0.098
 Sn+0.093
 Ell+0.084
 Mil+0.083
 Jenkins+0.083
Neg logit contributions
isdom-0.194
ercise-0.183
elling-0.179
weet-0.178
ully-0.172
Token!"
Token ID2474
Feature activation+2.31e+00

Pos logit contributions
 Sn+0.033
 Mil+0.033
 Jenkins+0.032
 Fl+0.031
 bathroom+0.031
Neg logit contributions
isdom-0.015
ercise-0.013
bye-0.013
weet-0.013
ly-0.012
Token
Token ID198
Feature activation+1.40e+00

Pos logit contributions
 Sn+0.049
 Fl+0.048
 Jenkins+0.046
 Ell+0.044
 Lee+0.042
Neg logit contributions
isdom-0.070
ercise-0.064
weet-0.063
elling-0.062
off-0.060
Token
Token ID198
Feature activation+7.29e-01

Pos logit contributions
 Sn+0.029
 Fl+0.028
 Jenkins+0.028
 Lee+0.027
 Ell+0.027
Neg logit contributions
isdom-0.042
elling-0.038
ercise-0.038
weet-0.038
off-0.038
Token"
Token ID1
Feature activation+4.68e+00

Pos logit contributions
 Fl+0.020
 Sn+0.020
 Ell+0.020
 Jenkins+0.019
 Mil+0.019
Neg logit contributions
isdom-0.017
ercise-0.017
elling-0.016
weet-0.015
off-0.015
TokenBang
Token ID43984
Feature activation-6.97e-01

Pos logit contributions
 Fl+0.124
 Sn+0.120
 Jenkins+0.119
 Lee+0.116
 Ell+0.116
Neg logit contributions
ercise-0.114
isdom-0.108
weet-0.105
ww-0.103
bye-0.100
Token,
Token ID11
Feature activation+7.33e+00

Pos logit contributions
isdom+0.019
ercise+0.018
elling+0.018
weet+0.017
ully+0.017
Neg logit contributions
 Fl-0.018
 Sn-0.017
 Ell-0.016
 Mil-0.016
 Lee-0.016
Token bang
Token ID20188
Feature activation+8.16e-01

Pos logit contributions
 Fl+0.172
 Sn+0.166
 Ell+0.155
 Jenkins+0.154
 Mil+0.154
Neg logit contributions
isdom-0.215
ercise-0.200
elling-0.196
weet-0.195
ully-0.185
Token,
Token ID11
Feature activation+6.61e+00

Pos logit contributions
 Fl+0.022
 Sn+0.021
 Ell+0.020
 Mil+0.020
 Jenkins+0.019
Neg logit contributions
isdom-0.021
ercise-0.020
elling-0.019
weet-0.019
ully-0.018
Token bang
Token ID20188
Feature activation+1.12e-01

Pos logit contributions
 Fl+0.152
 Sn+0.147
 Ell+0.137
 Mil+0.136
 Jenkins+0.136
Neg logit contributions
isdom-0.197
ercise-0.184
elling-0.180
weet-0.178
ully-0.171
Token!"
Token ID2474
Feature activation+2.37e+00

Pos logit contributions
 Fl+0.003
 Sn+0.003
 Ell+0.003
 Mil+0.003
 Jenkins+0.003
Neg logit contributions
isdom-0.003
ercise-0.003
elling-0.003
weet-0.003
ully-0.003
Token Sam
Token ID3409
Feature activation+1.09e+00

Pos logit contributions
 Sn+0.043
 Fl+0.040
 Jenkins+0.040
 Ell+0.036
 Lee+0.035
Neg logit contributions
isdom-0.078
ercise-0.072
weet-0.071
elling-0.069
night-0.068
Token began
Token ID2540
Feature activation-9.69e-01

Pos logit contributions
isdom+0.013
ercise+0.013
night+0.012
iper+0.012
ully+0.012
Neg logit contributions
 Lee-0.012
 Sn-0.011
 Jenkins-0.011
 Fl-0.011
 Frost-0.010
Token to
Token ID284
Feature activation+1.76e+00

Pos logit contributions
isdom+0.022
ercise+0.020
weet+0.019
elling+0.018
ully+0.018
Neg logit contributions
 Fl-0.028
 Sn-0.028
 Jenkins-0.027
 Lee-0.026
 Ell-0.026
Token sew
Token ID34249
Feature activation-1.24e+00

Pos logit contributions
 Fl+0.039
 Sn+0.037
 Ell+0.035
 Mil+0.034
 t+0.032
Neg logit contributions
isdom-0.056
elling-0.052
ercise-0.052
weet-0.050
ully-0.049
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
isdom+0.024
ercise+0.023
ly+0.023
 melodies+0.023
ock+0.023
Neg logit contributions
 Lee-0.033
 Jenkins-0.033
sed-0.032
 Sn-0.032
 Fl-0.031
Token She
Token ID1375
Feature activation+6.28e-01

Pos logit contributions
isdom+0.048
ercise+0.044
elling+0.044
weet+0.044
off+0.042
Neg logit contributions
 Fl-0.033
 Sn-0.032
 Mil-0.030
 Jenkins-0.030
 Lee-0.029
Token se
Token ID384
Feature activation-7.74e+00

Pos logit contributions
 Fl+0.013
 Sn+0.013
 Lee+0.013
 Jenkins+0.013
 Mil+0.012
Neg logit contributions
isdom-0.019
ercise-0.018
elling-0.017
weet-0.017
ully-0.017
Tokenwed
Token ID19103
Feature activation-2.30e+00

Pos logit contributions
weet+0.182
isdom+0.177
ully+0.166
elling+0.165
iveness+0.164
Neg logit contributions
uzz-0.154
 Fl-0.149
 Megan-0.143
 Ell-0.143
 L-0.141
Token the
Token ID262
Feature activation-1.09e-01

Pos logit contributions
isdom+0.061
elling+0.058
ercise+0.058
ock+0.055
weet+0.055
Neg logit contributions
 Fl-0.055
 Sn-0.054
 Jenkins-0.052
 Lee-0.051
 Mil-0.051
Token piece
Token ID3704
Feature activation-1.18e+00

Pos logit contributions
isdom+0.003
elling+0.003
ercise+0.003
weet+0.002
ock+0.002
Neg logit contributions
 Fl-0.003
 Lee-0.003
 Mil-0.003
 Sn-0.003
 Jenkins-0.003
Token of
Token ID286
Feature activation+1.58e+00

Pos logit contributions
isdom+0.033
ercise+0.031
elling+0.030
weet+0.030
ully+0.029
Neg logit contributions
 Fl-0.029
 Sn-0.028
 Ell-0.027
 Mil-0.026
 Jenkins-0.026
Token cloth
Token ID16270
Feature activation+1.34e-01

Pos logit contributions
 Fl+0.038
 Sn+0.036
 Jenkins+0.035
 Mil+0.034
 Ell+0.034
Neg logit contributions
isdom-0.045
ercise-0.042
elling-0.041
weet-0.041
ully-0.039
Token She
Token ID1375
Feature activation+2.04e+00

Pos logit contributions
 Sn+0.039
 Fl+0.039
 Ell+0.036
 Mil+0.036
 Jenkins+0.036
Neg logit contributions
isdom-0.044
weet-0.040
elling-0.040
ercise-0.040
ear-0.037
Token told
Token ID1297
Feature activation-9.29e-01

Pos logit contributions
 Fl+0.047
 Sn+0.046
 Jenkins+0.044
 Lee+0.042
 Mil+0.041
Neg logit contributions
isdom-0.060
ercise-0.056
elling-0.053
weet-0.052
off-0.051
Token him
Token ID683
Feature activation+1.24e+00

Pos logit contributions
isdom+0.030
ercise+0.028
elling+0.027
weet+0.027
ully+0.026
Neg logit contributions
 Fl-0.020
 Sn-0.019
 Ell-0.018
 Mil-0.017
 Jenkins-0.017
Token how
Token ID703
Feature activation+1.04e+00

Pos logit contributions
 Sn+0.034
 Fl+0.034
 Jenkins+0.032
 Mil+0.031
 Ell+0.031
Neg logit contributions
isdom-0.030
ercise-0.027
weet-0.026
elling-0.026
off-0.025
Token she
Token ID673
Feature activation+7.51e-01

Pos logit contributions
 Fl+0.025
 Sn+0.023
 Ell+0.022
 Mil+0.022
 Jenkins+0.021
Neg logit contributions
isdom-0.031
ercise-0.029
elling-0.028
weet-0.028
ully-0.027
Token se
Token ID384
Feature activation-7.61e+00

Pos logit contributions
 Fl+0.016
 Sn+0.016
 Jenkins+0.015
 Lee+0.015
 Mil+0.015
Neg logit contributions
isdom-0.023
ercise-0.022
elling-0.021
off-0.020
ully-0.020
Tokenwed
Token ID19103
Feature activation-2.50e+00

Pos logit contributions
weet+0.169
ww+0.157
isdom+0.153
ully+0.152
elling+0.151
Neg logit contributions
 Fl-0.170
 L-0.167
 pret-0.165
 Ell-0.163
 Mil-0.163
Token,
Token ID11
Feature activation+2.42e+00

Pos logit contributions
isdom+0.072
ercise+0.067
elling+0.067
weet+0.065
ock+0.063
Neg logit contributions
 Fl-0.058
 Sn-0.056
 Jenkins-0.052
 Mil-0.051
 Ell-0.051
Token glued
Token ID39783
Feature activation-2.22e+00

Pos logit contributions
 Fl+0.052
 Sn+0.049
 Mil+0.046
 Ell+0.046
 Lee+0.044
Neg logit contributions
isdom-0.077
ercise-0.073
elling-0.072
ully-0.069
weet-0.069
Token,
Token ID11
Feature activation+2.52e+00

Pos logit contributions
isdom+0.062
ercise+0.058
elling+0.057
weet+0.056
ock+0.054
Neg logit contributions
 Fl-0.052
 Sn-0.051
 Jenkins-0.049
 Mil-0.047
 Ell-0.047
Token and
Token ID290
Feature activation-1.54e+00

Pos logit contributions
 Fl+0.055
 Sn+0.053
 Mil+0.050
 Ell+0.049
 Mir+0.048
Neg logit contributions
isdom-0.079
ercise-0.073
elling-0.072
ully-0.070
weet-0.070
Token help
Token ID1037
Feature activation-7.94e-01

Pos logit contributions
 Fl+0.007
 Sn+0.007
 Ell+0.006
 Mil+0.006
 Jenkins+0.006
Neg logit contributions
isdom-0.011
ercise-0.011
elling-0.010
weet-0.010
ully-0.010
Token.
Token ID13
Feature activation-1.02e+00

Pos logit contributions
isdom+0.026
ercise+0.024
elling+0.024
weet+0.024
off+0.023
Neg logit contributions
 Fl-0.016
 Sn-0.015
 Mil-0.014
 Ell-0.014
 Jenkins-0.014
Token Together
Token ID17083
Feature activation-2.57e+00

Pos logit contributions
isdom+0.028
weet+0.025
ercise+0.025
elling+0.024
night+0.023
Neg logit contributions
 Sn-0.022
 Fl-0.022
 plun-0.021
 Mil-0.021
 Esk-0.020
Token,
Token ID11
Feature activation-1.37e+00

Pos logit contributions
isdom+0.092
ercise+0.088
elling+0.087
weet+0.085
off+0.082
Neg logit contributions
 Fl-0.049
 Sn-0.044
 Ell-0.042
 Mil-0.040
 Jenkins-0.040
Token they
Token ID484
Feature activation-1.19e+00

Pos logit contributions
isdom+0.041
ercise+0.038
weet+0.038
elling+0.037
ully+0.036
Neg logit contributions
 Fl-0.028
 Sn-0.028
 Jenkins-0.026
 Mil-0.025
 Lee-0.025
Token se
Token ID384
Feature activation-7.49e+00

Pos logit contributions
isdom+0.034
ercise+0.032
elling+0.030
weet+0.030
ully+0.030
Neg logit contributions
 Fl-0.029
 Sn-0.028
 Jenkins-0.026
 Mil-0.026
 Lee-0.026
Tokenwed
Token ID19103
Feature activation-2.82e+00

Pos logit contributions
weet+0.181
isdom+0.171
elling+0.169
ww+0.163
iveness+0.161
Neg logit contributions
 Megan-0.141
uzz-0.140
 Fl-0.139
 Mil-0.137
 L-0.134
Token a
Token ID257
Feature activation-1.32e+00

Pos logit contributions
isdom+0.073
elling+0.069
ercise+0.069
ully+0.066
weet+0.065
Neg logit contributions
 Fl-0.067
 Sn-0.067
 Jenkins-0.064
 Lee-0.063
 Mil-0.062
Token patch
Token ID8529
Feature activation+2.59e-01

Pos logit contributions
isdom+0.039
ercise+0.037
weet+0.035
elling+0.035
ully+0.034
Neg logit contributions
 Fl-0.030
 Sn-0.029
 Jenkins-0.027
 Lee-0.027
 Mil-0.027
Token onto
Token ID4291
Feature activation+1.09e+00

Pos logit contributions
 Fl+0.007
 Sn+0.007
 Ell+0.007
 Mil+0.007
 Jenkins+0.007
Neg logit contributions
isdom-0.006
ercise-0.006
elling-0.006
weet-0.006
ully-0.005
Token the
Token ID262
Feature activation+1.91e-01

Pos logit contributions
 Jenkins+0.022
 Fl+0.022
 Sn+0.022
 Lee+0.021
 Mil+0.021
Neg logit contributions
isdom-0.032
weet-0.029
ercise-0.029
elling-0.028
ully-0.028
Token
Token ID198
Feature activation-1.09e+00

Pos logit contributions
isdom+0.051
ercise+0.048
elling+0.047
weet+0.046
ully+0.044
Neg logit contributions
 Fl-0.032
 Sn-0.030
 Ell-0.028
 Mil-0.028
 Jenkins-0.027
Token
Token ID198
Feature activation-1.60e+00

Pos logit contributions
isdom+0.041
ercise+0.038
elling+0.038
weet+0.037
ully+0.036
Neg logit contributions
 Fl-0.017
 Sn-0.016
 Ell-0.015
 Mil-0.014
 Jenkins-0.014
TokenShe
Token ID3347
Feature activation+1.41e-01

Pos logit contributions
isdom+0.047
elling+0.045
ercise+0.041
night+0.041
ully+0.040
Neg logit contributions
 Fl-0.040
 Sn-0.038
 Ell-0.034
 Jenkins-0.034
 Mil-0.034
Token cut
Token ID2005
Feature activation-1.01e+00

Pos logit contributions
 Fl+0.003
 Sn+0.003
 Jenkins+0.003
 Mil+0.003
 Lee+0.003
Neg logit contributions
isdom-0.004
ercise-0.004
elling-0.004
weet-0.004
ully-0.004
Token and
Token ID290
Feature activation-2.94e+00

Pos logit contributions
isdom+0.028
elling+0.027
ercise+0.026
ock+0.025
weet+0.025
Neg logit contributions
 Fl-0.022
 Sn-0.022
 Jenkins-0.022
 Lee-0.021
 Mil-0.020
Token se
Token ID384
Feature activation-7.45e+00

Pos logit contributions
isdom+0.093
ercise+0.087
elling+0.086
weet+0.084
ully+0.081
Neg logit contributions
 Fl-0.063
 Sn-0.060
 Ell-0.056
 Mil-0.056
 Jenkins-0.055
Tokenwed
Token ID19103
Feature activation-1.96e+00

Pos logit contributions
weet+0.184
elling+0.173
isdom+0.170
iveness+0.166
mmm+0.165
Neg logit contributions
uzz-0.135
 Fl-0.131
 pret-0.126
 L-0.125
 Megan-0.124
Token the
Token ID262
Feature activation-2.77e-02

Pos logit contributions
isdom+0.046
elling+0.044
ock+0.044
ercise+0.044
ully+0.042
Neg logit contributions
 Fl-0.049
 Sn-0.049
 Jenkins-0.048
 Lee-0.047
 Mil-0.045
Token fabric
Token ID9664
Feature activation+6.48e-01

Pos logit contributions
isdom+0.001
elling+0.001
ercise+0.001
weet+0.001
ock+0.001
Neg logit contributions
 Fl-0.001
 Sn-0.001
 Jenkins-0.001
 Lee-0.001
 Frost-0.001
Token and
Token ID290
Feature activation-2.32e+00

Pos logit contributions
 Fl+0.015
 Sn+0.014
 Ell+0.013
 Jenkins+0.013
 Mil+0.013
Neg logit contributions
isdom-0.019
ercise-0.018
elling-0.018
weet-0.017
ully-0.017
Token put
Token ID1234
Feature activation-9.78e-01

Pos logit contributions
isdom+0.064
ercise+0.061
weet+0.058
elling+0.057
ully+0.056
Neg logit contributions
 Fl-0.055
 Sn-0.054
 Jenkins-0.053
 Lee-0.051
 Mil-0.049
Token to
Token ID284
Feature activation+5.79e-01

Pos logit contributions
 Fl+0.016
 Ell+0.015
 Sn+0.015
 Mil+0.015
 L+0.014
Neg logit contributions
isdom-0.025
elling-0.024
ercise-0.024
weet-0.023
ully-0.023
Token show
Token ID905
Feature activation-4.02e+00

Pos logit contributions
 Fl+0.011
 Ell+0.011
 Sn+0.010
 t+0.010
 Mil+0.010
Neg logit contributions
isdom-0.019
elling-0.019
ercise-0.018
ww-0.017
night-0.017
Token everyone
Token ID2506
Feature activation-1.82e+00

Pos logit contributions
isdom+0.116
ercise+0.110
elling+0.109
weet+0.106
ully+0.101
Neg logit contributions
 Fl-0.098
 Sn-0.092
 Ell-0.090
 Mil-0.087
 Lee-0.085
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
isdom+0.053
ercise+0.049
elling+0.048
weet+0.047
off+0.045
Neg logit contributions
 Fl-0.044
 Sn-0.042
 Ell-0.039
 Mil-0.039
 Jenkins-0.039
Token He
Token ID679
Feature activation+1.26e-01

Pos logit contributions
isdom+0.046
ercise+0.042
elling+0.041
weet+0.041
off+0.040
Neg logit contributions
 Fl-0.029
 Sn-0.028
 Mil-0.026
 Jenkins-0.026
 Lee-0.025
Token se
Token ID384
Feature activation-7.43e+00

Pos logit contributions
 Fl+0.003
 Sn+0.003
 Jenkins+0.002
 Lee+0.002
 Mil+0.002
Neg logit contributions
isdom-0.004
ercise-0.004
elling-0.004
weet-0.004
ully-0.004
Tokenwed
Token ID19103
Feature activation-2.41e+00

Pos logit contributions
weet+0.177
isdom+0.163
elling+0.162
ww+0.157
ercise+0.155
Neg logit contributions
uzz-0.151
 Megan-0.138
 Ell-0.136
 Fl-0.133
 L-0.131
Token together
Token ID1978
Feature activation-1.13e+00

Pos logit contributions
isdom+0.070
ercise+0.065
elling+0.064
weet+0.062
ully+0.061
Neg logit contributions
 Fl-0.057
 Sn-0.055
 Jenkins-0.051
 Mil-0.051
 Ell-0.051
Token parts
Token ID3354
Feature activation-1.01e+00

Pos logit contributions
isdom+0.031
ercise+0.028
elling+0.028
weet+0.027
ully+0.026
Neg logit contributions
 Fl-0.028
 Sn-0.028
 Jenkins-0.026
 Mil-0.026
 Ell-0.026
Token of
Token ID286
Feature activation+8.87e-01

Pos logit contributions
isdom+0.024
ercise+0.022
elling+0.021
weet+0.021
ully+0.020
Neg logit contributions
 Fl-0.029
 Sn-0.028
 Ell-0.027
 Mil-0.027
 Jenkins-0.026
Token it
Token ID340
Feature activation+3.00e-01

Pos logit contributions
 Fl+0.021
 Sn+0.020
 Jenkins+0.019
 Mil+0.019
 Lee+0.019
Neg logit contributions
isdom-0.026
ercise-0.023
weet-0.023
elling-0.022
ully-0.022
Token needle
Token ID17598
Feature activation-7.53e-01

Pos logit contributions
isdom+0.038
ercise+0.036
weet+0.034
elling+0.033
ully+0.033
Neg logit contributions
 Fl-0.034
 Sn-0.033
 Mil-0.031
 Ell-0.031
 Jenkins-0.031
Token and
Token ID290
Feature activation-1.97e+00

Pos logit contributions
isdom+0.022
ercise+0.020
elling+0.020
weet+0.019
ully+0.019
Neg logit contributions
 Fl-0.018
 Sn-0.017
 Ell-0.016
 Mil-0.016
 Jenkins-0.016
Token thread
Token ID4704
Feature activation-1.68e+00

Pos logit contributions
isdom+0.068
ercise+0.064
elling+0.063
weet+0.062
ully+0.060
Neg logit contributions
 Fl-0.036
 Sn-0.035
 Ell-0.032
 Mil-0.031
 Jenkins-0.031
Token.
Token ID13
Feature activation-6.51e-01

Pos logit contributions
isdom+0.049
ercise+0.047
elling+0.045
weet+0.045
ully+0.044
Neg logit contributions
 Fl-0.038
 Sn-0.037
 Jenkins-0.035
 Mil-0.035
 Ell-0.034
Token She
Token ID1375
Feature activation+6.70e-01

Pos logit contributions
isdom+0.019
ercise+0.017
elling+0.017
weet+0.017
off+0.016
Neg logit contributions
 Fl-0.015
 Sn-0.015
 Jenkins-0.014
 Mil-0.014
 Ell-0.014
Token se
Token ID384
Feature activation-7.30e+00

Pos logit contributions
 Fl+0.015
 Sn+0.015
 Jenkins+0.014
 Lee+0.014
 Mil+0.014
Neg logit contributions
isdom-0.020
ercise-0.019
weet-0.017
ully-0.017
elling-0.017
Tokenwed
Token ID19103
Feature activation-2.30e+00

Pos logit contributions
isdom+0.163
weet+0.162
mmm+0.160
elling+0.157
very+0.155
Neg logit contributions
uzz-0.152
 Fl-0.141
 L-0.137
 Megan-0.132
 Ann-0.131
Token a
Token ID257
Feature activation-9.53e-01

Pos logit contributions
isdom+0.071
ercise+0.066
elling+0.065
weet+0.064
ully+0.062
Neg logit contributions
 Fl-0.050
 Sn-0.048
 Ell-0.045
 Jenkins-0.045
 Mil-0.045
Token hole
Token ID7604
Feature activation+3.16e+00

Pos logit contributions
isdom+0.027
ercise+0.025
elling+0.025
weet+0.024
ully+0.023
Neg logit contributions
 Fl-0.023
 Sn-0.022
 Ell-0.021
 Mil-0.021
 Jenkins-0.021
Token in
Token ID287
Feature activation+3.34e+00

Pos logit contributions
 Fl+0.058
 Sn+0.053
 Ell+0.049
 Mil+0.049
 Jenkins+0.047
Neg logit contributions
isdom-0.111
ercise-0.104
elling-0.102
weet-0.101
ully-0.098
Token the
Token ID262
Feature activation+1.17e+00

Pos logit contributions
 Jenkins+0.076
 Fl+0.074
 Lee+0.074
 Mil+0.074
 Sn+0.074
Neg logit contributions
isdom-0.084
weet-0.081
ock-0.076
elling-0.076
ercise-0.074
Token asked
Token ID1965
Feature activation-2.97e-01

Pos logit contributions
isdom+0.049
ercise+0.046
elling+0.046
weet+0.045
ully+0.043
Neg logit contributions
 Fl-0.031
 Sn-0.030
 Ell-0.028
 Mil-0.027
 Jenkins-0.027
Token his
Token ID465
Feature activation+1.07e+00

Pos logit contributions
isdom+0.008
ercise+0.007
weet+0.007
elling+0.007
ully+0.007
Neg logit contributions
 Sn-0.007
 Fl-0.007
 Jenkins-0.007
 Mil-0.007
 Ell-0.007
Token friend
Token ID1545
Feature activation-2.22e+00

Pos logit contributions
 Sn+0.031
 Fl+0.030
 Ell+0.028
 Jenkins+0.028
 Mil+0.027
Neg logit contributions
isdom-0.025
ercise-0.023
ully-0.022
elling-0.022
off-0.021
Token,
Token ID11
Feature activation+2.93e+00

Pos logit contributions
isdom+0.063
ercise+0.058
weet+0.057
elling+0.056
ully+0.056
Neg logit contributions
 Sn-0.052
 Fl-0.050
 Mil-0.047
 Jenkins-0.047
 Ell-0.046
Token a
Token ID257
Feature activation-4.50e-01

Pos logit contributions
 lobby+0.067
 tiles+0.061
 Sn+0.061
 wra+0.060
 Mil+0.058
Neg logit contributions
isdom-0.075
ully-0.071
weet-0.070
ercise-0.069
 Harry-0.066
Token se
Token ID384
Feature activation-7.27e+00

Pos logit contributions
isdom+0.011
weet+0.010
ercise+0.010
ully+0.010
ww+0.010
Neg logit contributions
 Sn-0.012
 Fl-0.011
 Jenkins-0.011
 Ell-0.010
 Mil-0.010
Tokenag
Token ID363
Feature activation-1.88e-01

Pos logit contributions
isdom+0.124
elling+0.118
ercise+0.118
iveness+0.109
 melodies+0.105
Neg logit contributions
 Fl-0.213
 Mil-0.203
 Ell-0.200
 L-0.199
uzz-0.198
Tokenull
Token ID724
Feature activation-2.47e+00

Pos logit contributions
isdom+0.004
ercise+0.004
weet+0.004
elling+0.004
ully+0.003
Neg logit contributions
 Fl-0.006
 Sn-0.006
 Ell-0.005
 Jenkins-0.005
 Mil-0.005
Token named
Token ID3706
Feature activation-3.41e-01

Pos logit contributions
isdom+0.082
ercise+0.078
elling+0.077
weet+0.073
off+0.072
Neg logit contributions
 Fl-0.052
 Sn-0.048
 Ell-0.043
 Lee-0.042
 Mil-0.041
Token Tim
Token ID5045
Feature activation-1.20e+00

Pos logit contributions
isdom+0.008
weet+0.007
ully+0.007
ercise+0.007
elling+0.007
Neg logit contributions
 Sn-0.010
 Fl-0.010
 Jenkins-0.009
 Megan-0.009
 Mil-0.009
Tokenmy
Token ID1820
Feature activation-1.96e+00

Pos logit contributions
isdom+0.029
ercise+0.026
elling+0.026
weet+0.025
off+0.024
Neg logit contributions
 Fl-0.035
 Sn-0.034
 Ell-0.032
 Mil-0.032
 Jenkins-0.032
Token and
Token ID290
Feature activation-3.98e+00

Pos logit contributions
 Fl+0.034
 Sn+0.033
 Ell+0.030
 Mil+0.030
 Jenkins+0.029
Neg logit contributions
isdom-0.041
ercise-0.038
elling-0.038
weet-0.037
ully-0.035
Token said
Token ID531
Feature activation+6.53e-02

Pos logit contributions
isdom+0.119
ercise+0.112
weet+0.108
elling+0.108
ully+0.104
Neg logit contributions
 Fl-0.087
 Sn-0.085
 Jenkins-0.080
 Mil-0.078
 Ell-0.077
Token goodbye
Token ID24829
Feature activation-2.02e+00

Pos logit contributions
 Fl+0.002
 Sn+0.002
 Jenkins+0.002
 Mil+0.002
 Lee+0.002
Neg logit contributions
isdom-0.001
ercise-0.001
elling-0.001
weet-0.001
night-0.001
Token to
Token ID284
Feature activation+5.38e-03

Pos logit contributions
isdom+0.056
ercise+0.052
elling+0.050
weet+0.050
night+0.048
Neg logit contributions
 Fl-0.050
 Sn-0.048
 Mil-0.045
 Jenkins-0.045
 Ell-0.045
Token her
Token ID607
Feature activation-2.06e-01

Pos logit contributions
 Fl+0.000
 Sn+0.000
 Jenkins+0.000
 Mil+0.000
 Ell+0.000
Neg logit contributions
isdom-0.000
ercise-0.000
weet-0.000
elling-0.000
ully-0.000
Token se
Token ID384
Feature activation-7.25e+00

Pos logit contributions
isdom+0.006
ercise+0.006
elling+0.006
weet+0.006
ully+0.005
Neg logit contributions
 Fl-0.005
 Sn-0.005
 Ell-0.004
 Mil-0.004
 Jenkins-0.004
Tokenag
Token ID363
Feature activation-9.08e-01

Pos logit contributions
weet+0.123
isdom+0.121
elling+0.117
ercise+0.117
iveness+0.112
Neg logit contributions
 Fl-0.201
uzz-0.199
 Sn-0.189
 Mil-0.188
 L-0.185
Tokenull
Token ID724
Feature activation-3.37e+00

Pos logit contributions
isdom+0.023
ercise+0.021
elling+0.021
weet+0.020
ully+0.020
Neg logit contributions
 Fl-0.025
 Sn-0.024
 Ell-0.023
 Mil-0.023
 Jenkins-0.022
Token friends
Token ID2460
Feature activation-2.20e+00

Pos logit contributions
isdom+0.110
ercise+0.104
elling+0.103
weet+0.099
off+0.095
Neg logit contributions
 Fl-0.072
 Sn-0.068
 Ell-0.063
 Mil-0.060
 Jenkins-0.060
Token.
Token ID13
Feature activation-1.61e+00

Pos logit contributions
isdom+0.072
ercise+0.067
elling+0.066
weet+0.066
ully+0.063
Neg logit contributions
 Fl-0.044
 Sn-0.042
 Ell-0.039
 Mil-0.039
 Jenkins-0.038
Token She
Token ID1375
Feature activation+2.75e-02

Pos logit contributions
isdom+0.047
elling+0.044
ercise+0.043
weet+0.043
night+0.041
Neg logit contributions
 Fl-0.036
 Sn-0.035
 Jenkins-0.033
 Mil-0.032
 Lee-0.032
Token own
Token ID898
Feature activation+3.22e-01

Pos logit contributions
 Fl+0.020
 Sn+0.020
 Mil+0.018
 Jenkins+0.018
 Ell+0.018
Neg logit contributions
isdom-0.032
ercise-0.030
elling-0.029
weet-0.029
ully-0.028
Token two
Token ID734
Feature activation-1.05e+00

Pos logit contributions
 Fl+0.007
 Sn+0.007
 Ell+0.007
 Mil+0.007
 Jenkins+0.006
Neg logit contributions
isdom-0.010
ercise-0.009
elling-0.009
weet-0.009
ully-0.008
Token hands
Token ID2832
Feature activation-8.40e-01

Pos logit contributions
isdom+0.031
ercise+0.029
elling+0.028
weet+0.028
ully+0.027
Neg logit contributions
 Fl-0.024
 Sn-0.023
 Mil-0.022
 Ell-0.022
 Jenkins-0.022
Token.
Token ID13
Feature activation-1.55e+00

Pos logit contributions
isdom+0.026
ercise+0.024
elling+0.024
weet+0.024
ully+0.023
Neg logit contributions
 Fl-0.018
 Sn-0.018
 Ell-0.016
 Mil-0.016
 Jenkins-0.016
Token She
Token ID1375
Feature activation+7.65e-01

Pos logit contributions
isdom+0.047
weet+0.043
ercise+0.043
elling+0.042
off+0.040
Neg logit contributions
 Fl-0.032
 Sn-0.032
 Mil-0.030
 Jenkins-0.029
 plun-0.029
Token se
Token ID384
Feature activation-7.24e+00

Pos logit contributions
 Fl+0.016
 Sn+0.015
 Jenkins+0.015
 Lee+0.014
 Mil+0.014
Neg logit contributions
isdom-0.024
ercise-0.023
elling-0.022
weet-0.022
iper-0.021
Tokenwed
Token ID19103
Feature activation-2.36e+00

Pos logit contributions
weet+0.159
isdom+0.155
elling+0.151
ww+0.148
iveness+0.148
Neg logit contributions
 Fl-0.152
uzz-0.149
 pret-0.149
 Mil-0.149
 Megan-0.148
Token it
Token ID340
Feature activation+2.12e-01

Pos logit contributions
isdom+0.069
ercise+0.065
elling+0.064
weet+0.063
ully+0.061
Neg logit contributions
 Fl-0.053
 Sn-0.051
 Jenkins-0.048
 Mil-0.048
 Ell-0.047
Token with
Token ID351
Feature activation+1.38e+00

Pos logit contributions
 Fl+0.005
 Sn+0.005
 Ell+0.004
 Mil+0.004
 Jenkins+0.004
Neg logit contributions
isdom-0.007
ercise-0.006
elling-0.006
weet-0.006
ully-0.006
Token bright
Token ID6016
Feature activation-1.36e+00

Pos logit contributions
 Fl+0.031
 Sn+0.030
 Ell+0.028
 Mil+0.028
 Jenkins+0.028
Neg logit contributions
isdom-0.042
ercise-0.039
elling-0.038
weet-0.038
ully-0.036
Token colors
Token ID7577
Feature activation-5.62e-02

Pos logit contributions
isdom+0.041
ercise+0.038
weet+0.037
elling+0.036
off+0.035
Neg logit contributions
 Fl-0.032
 Sn-0.030
 Ell-0.029
 Mil-0.028
 t-0.027
Token and
Token ID290
Feature activation-3.59e+00

Pos logit contributions
isdom+0.078
ercise+0.073
elling+0.072
weet+0.071
ully+0.069
Neg logit contributions
 Fl-0.050
 Sn-0.048
 Ell-0.044
 Mil-0.043
 Jenkins-0.043
Token learned
Token ID4499
Feature activation-2.93e+00

Pos logit contributions
isdom+0.112
ercise+0.104
elling+0.103
weet+0.101
ully+0.097
Neg logit contributions
 Fl-0.079
 Sn-0.075
 Ell-0.070
 Mil-0.070
 Jenkins-0.069
Token something
Token ID1223
Feature activation+3.81e-01

Pos logit contributions
isdom+0.083
ercise+0.078
elling+0.078
weet+0.076
ully+0.074
Neg logit contributions
 Fl-0.075
 Sn-0.070
 Ell-0.068
 Mil-0.063
 Jenkins-0.063
Token new
Token ID649
Feature activation-2.14e+00

Pos logit contributions
 Fl+0.010
 Sn+0.009
 Mil+0.009
 Ell+0.009
 Jenkins+0.009
Neg logit contributions
isdom-0.010
ercise-0.010
elling-0.009
weet-0.009
off-0.009
Token about
Token ID546
Feature activation+9.77e-01

Pos logit contributions
isdom+0.065
ercise+0.060
elling+0.059
weet+0.058
off+0.057
Neg logit contributions
 Fl-0.048
 Sn-0.047
 Mil-0.043
 Ell-0.043
 Jenkins-0.042
Token se
Token ID384
Feature activation-7.23e+00

Pos logit contributions
 Fl+0.023
 Sn+0.023
 Jenkins+0.021
 Mil+0.021
 Lee+0.021
Neg logit contributions
isdom-0.028
weet-0.026
ercise-0.025
elling-0.025
ully-0.024
Tokenag
Token ID363
Feature activation+2.96e-01

Pos logit contributions
weet+0.131
ww+0.128
elling+0.126
isdom+0.124
mmm+0.122
Neg logit contributions
uzz-0.150
 pret-0.149
 Mil-0.147
 L-0.146
ows-0.143
Tokenull
Token ID724
Feature activation-2.99e+00

Pos logit contributions
 Fl+0.009
 Sn+0.008
 Ell+0.008
 Mil+0.008
 Jenkins+0.008
Neg logit contributions
isdom-0.007
ercise-0.006
elling-0.006
weet-0.006
ully-0.006
Tokens
Token ID82
Feature activation+1.66e+00

Pos logit contributions
isdom+0.085
ercise+0.079
elling+0.078
weet+0.072
night+0.070
Neg logit contributions
 Fl-0.076
 Sn-0.070
 Ell-0.066
 Mil-0.064
 Lee-0.063
Token.
Token ID13
Feature activation-1.47e+00

Pos logit contributions
 Fl+0.035
 Sn+0.034
 Mil+0.031
 Ell+0.031
 Jenkins+0.031
Neg logit contributions
isdom-0.053
ercise-0.049
elling-0.048
weet-0.048
ully-0.046
Token<|endoftext|>
Token ID50256
Feature activation+9.48e-01

Pos logit contributions
isdom+0.046
ercise+0.043
elling+0.042
weet+0.042
off+0.040
Neg logit contributions
 Fl-0.030
 Sn-0.029
 Mil-0.027
 Jenkins-0.027
 Ell-0.027
Token a
Token ID257
Feature activation-2.37e+00

Pos logit contributions
isdom+0.100
ercise+0.092
elling+0.090
weet+0.090
ully+0.087
Neg logit contributions
 Fl-0.070
 Sn-0.067
 Ell-0.062
 Mil-0.059
 Jenkins-0.058
Token needle
Token ID17598
Feature activation-8.47e-01

Pos logit contributions
isdom+0.078
ercise+0.073
elling+0.072
weet+0.068
ully+0.067
Neg logit contributions
 Fl-0.051
 Sn-0.047
 Ell-0.045
 Jenkins-0.043
 t-0.042
Token and
Token ID290
Feature activation-2.88e+00

Pos logit contributions
isdom+0.026
ercise+0.024
elling+0.024
weet+0.023
ully+0.022
Neg logit contributions
 Fl-0.019
 Sn-0.019
 Ell-0.017
 Lee-0.017
 Jenkins-0.017
Token thread
Token ID4704
Feature activation-1.51e+00

Pos logit contributions
isdom+0.102
elling+0.094
ercise+0.093
weet+0.092
off+0.090
Neg logit contributions
 Fl-0.057
 Sn-0.052
 Ell-0.048
 t-0.047
 Mil-0.045
Token and
Token ID290
Feature activation-2.50e+00

Pos logit contributions
isdom+0.035
ercise+0.033
elling+0.032
ock+0.032
weet+0.032
Neg logit contributions
 Fl-0.041
 Sn-0.040
 Jenkins-0.040
 Mil-0.039
 Lee-0.038
Token se
Token ID384
Feature activation-7.14e+00

Pos logit contributions
isdom+0.085
elling+0.078
ercise+0.078
weet+0.076
off+0.074
Neg logit contributions
 Fl-0.051
 Sn-0.048
 Ell-0.044
 Mil-0.042
 t-0.042
Tokenwed
Token ID19103
Feature activation-2.19e+00

Pos logit contributions
weet+0.171
isdom+0.166
iveness+0.163
mmm+0.159
elling+0.159
Neg logit contributions
 Fl-0.151
 L-0.139
 Sn-0.137
uzz-0.135
 t-0.133
Token Teddy
Token ID29345
Feature activation-2.08e+00

Pos logit contributions
isdom+0.057
elling+0.055
ercise+0.055
ock+0.053
weet+0.052
Neg logit contributions
 Jenkins-0.049
 Fl-0.049
 Mil-0.049
 Lee-0.048
 Sn-0.048
Token's
Token ID338
Feature activation+6.11e-01

Pos logit contributions
isdom+0.055
ercise+0.053
elling+0.050
weet+0.050
off+0.049
Neg logit contributions
 Fl-0.051
 Sn-0.050
 Mil-0.049
 Jenkins-0.048
 Lee-0.048
Token eye
Token ID4151
Feature activation+2.69e-01

Pos logit contributions
 Fl+0.014
 Mil+0.013
 Jenkins+0.013
 Sn+0.013
 Lee+0.013
Neg logit contributions
isdom-0.018
ercise-0.017
elling-0.016
night-0.016
weet-0.016
Token back
Token ID736
Feature activation-3.62e-01

Pos logit contributions
 Fl+0.005
 Sn+0.004
 Ell+0.004
 Mil+0.004
 t+0.004
Neg logit contributions
isdom-0.010
ercise-0.009
weet-0.009
elling-0.009
ully-0.009
Token watched
Token ID7342
Feature activation-1.55e-01

Pos logit contributions
isdom+0.003
ercise+0.003
elling+0.003
weet+0.003
ully+0.003
Neg logit contributions
 Fl-0.003
 Sn-0.002
 Mil-0.002
 Ell-0.002
 Jenkins-0.002
Token as
Token ID355
Feature activation-1.98e-01

Pos logit contributions
isdom+0.005
ercise+0.005
elling+0.004
weet+0.004
off+0.004
Neg logit contributions
 Fl-0.003
 Sn-0.003
 Ell-0.003
 Mil-0.003
 Jenkins-0.003
Token her
Token ID607
Feature activation-4.01e-01

Pos logit contributions
isdom+0.006
weet+0.005
elling+0.005
ercise+0.005
ully+0.005
Neg logit contributions
 Sn-0.004
 Fl-0.004
 Jenkins-0.004
 Ell-0.004
 Mil-0.004
Token mom
Token ID1995
Feature activation-3.38e+00

Pos logit contributions
isdom+0.014
ercise+0.013
elling+0.013
night+0.013
weet+0.013
Neg logit contributions
 Fl-0.006
 Mil-0.006
 Sn-0.006
 Ell-0.006
 Mir-0.006
Token carefully
Token ID7773
Feature activation-8.72e-01

Pos logit contributions
isdom+0.101
ercise+0.095
elling+0.093
weet+0.091
ully+0.089
Neg logit contributions
 Fl-0.077
 Sn-0.074
 Mil-0.069
 Jenkins-0.069
 Ell-0.068
Token se
Token ID384
Feature activation-7.09e+00

Pos logit contributions
isdom+0.026
ercise+0.025
elling+0.024
weet+0.023
ully+0.023
Neg logit contributions
 Fl-0.019
 Sn-0.019
 Jenkins-0.018
 Mil-0.017
 Lee-0.017
Tokenwed
Token ID19103
Feature activation-2.23e+00

Pos logit contributions
weet+0.168
elling+0.160
isdom+0.159
mmm+0.159
ww+0.157
Neg logit contributions
 Fl-0.145
 L-0.137
uzz-0.136
 Sn-0.130
 Mil-0.130
Token Ted
Token ID11396
Feature activation-1.09e+00

Pos logit contributions
isdom+0.060
elling+0.057
ercise+0.057
ock+0.054
ully+0.054
Neg logit contributions
 Fl-0.050
 Sn-0.050
 Jenkins-0.048
 Mil-0.047
 Lee-0.047
Token's
Token ID338
Feature activation+2.03e-01

Pos logit contributions
isdom+0.028
ercise+0.027
elling+0.026
weet+0.025
off+0.025
Neg logit contributions
 Fl-0.028
 Sn-0.027
 Mil-0.026
 Jenkins-0.026
 Ell-0.026
Token arm
Token ID3211
Feature activation-1.06e+00

Pos logit contributions
 Fl+0.004
 Sn+0.004
 Mil+0.004
 Jenkins+0.004
 Lee+0.004
Neg logit contributions
isdom-0.006
ercise-0.006
elling-0.006
weet-0.005
night-0.005
Token back
Token ID736
Feature activation-3.81e-01

Pos logit contributions
isdom+0.034
ercise+0.032
elling+0.031
weet+0.031
ully+0.030
Neg logit contributions
 Fl-0.023
 Sn-0.022
 Ell-0.020
 Mil-0.019
 Jenkins-0.019
Token shore
Token ID15191
Feature activation+1.44e+00

Pos logit contributions
isdom+0.045
elling+0.039
ercise+0.039
weet+0.039
ully+0.037
Neg logit contributions
 Fl-0.025
 Sn-0.024
 Mil-0.023
 Ell-0.023
 bathroom-0.022
Token and
Token ID290
Feature activation-2.96e+00

Pos logit contributions
 Fl+0.040
 Sn+0.039
 Ell+0.036
 Jenkins+0.036
 Mil+0.035
Neg logit contributions
isdom-0.035
ercise-0.032
weet-0.032
elling-0.031
off-0.030
Token saw
Token ID2497
Feature activation-2.97e-01

Pos logit contributions
ercise+0.078
weet+0.076
isdom+0.075
night+0.073
bye+0.071
Neg logit contributions
 Sn-0.065
 plun-0.062
 Fl-0.061
 Jenkins-0.061
 Lee-0.059
Token lots
Token ID6041
Feature activation-2.01e+00

Pos logit contributions
isdom+0.007
elling+0.007
weet+0.007
ercise+0.007
ock+0.007
Neg logit contributions
 Sn-0.008
 Jenkins-0.007
 Fl-0.007
 Lee-0.007
 plun-0.006
Token of
Token ID286
Feature activation+2.30e+00

Pos logit contributions
isdom+0.046
ercise+0.041
elling+0.039
weet+0.038
ully+0.037
Neg logit contributions
 Fl-0.062
 Sn-0.060
 Ell-0.058
 Mil-0.058
 Jenkins-0.056
Token se
Token ID384
Feature activation-7.09e+00

Pos logit contributions
 Fl+0.063
 Sn+0.062
 Lee+0.059
 Jenkins+0.058
 Ell+0.054
Neg logit contributions
isdom-0.054
elling-0.053
weet-0.052
ercise-0.052
ock-0.051
Tokenag
Token ID363
Feature activation+2.92e-01

Pos logit contributions
isdom+0.139
elling+0.127
weet+0.121
ercise+0.120
iveness+0.119
Neg logit contributions
 Mil-0.164
 Fl-0.159
 L-0.152
 pret-0.151
 Megan-0.149
Tokenull
Token ID724
Feature activation-2.37e+00

Pos logit contributions
 Fl+0.009
 Sn+0.008
 Ell+0.008
 Jenkins+0.008
 Mil+0.008
Neg logit contributions
isdom-0.007
ercise-0.006
elling-0.006
weet-0.006
ully-0.006
Tokens
Token ID82
Feature activation+1.77e+00

Pos logit contributions
isdom+0.065
ercise+0.059
elling+0.057
weet+0.054
night+0.053
Neg logit contributions
 Fl-0.064
 Sn-0.061
 Ell-0.057
 Mil-0.057
 Jenkins-0.056
Token flying
Token ID7348
Feature activation-1.02e+00

Pos logit contributions
 Fl+0.043
 Sn+0.043
 Mil+0.040
 Ell+0.040
 Mir+0.039
Neg logit contributions
isdom-0.047
weet-0.045
ully-0.043
ercise-0.043
elling-0.043
Token in
Token ID287
Feature activation+4.63e+00

Pos logit contributions
isdom+0.029
ercise+0.028
elling+0.027
weet+0.027
ully+0.026
Neg logit contributions
 Fl-0.024
 Sn-0.023
 Lee-0.022
 Mil-0.022
 Ell-0.021
Token his
Token ID465
Feature activation+2.01e-01

Pos logit contributions
 Fl+0.054
 Sn+0.052
 Ell+0.048
 Mil+0.048
 Jenkins+0.048
Neg logit contributions
isdom-0.064
ercise-0.059
elling-0.058
weet-0.057
ully-0.055
Token friends
Token ID2460
Feature activation-1.88e+00

Pos logit contributions
 Fl+0.005
 Sn+0.005
 Ell+0.005
 Jenkins+0.005
 Mil+0.005
Neg logit contributions
isdom-0.005
ercise-0.005
elling-0.005
ully-0.005
weet-0.005
Token,
Token ID11
Feature activation+1.95e+00

Pos logit contributions
isdom+0.058
ercise+0.054
weet+0.053
elling+0.052
ully+0.051
Neg logit contributions
 Fl-0.041
 Sn-0.039
 Mil-0.036
 Ell-0.036
 Jenkins-0.036
Token but
Token ID475
Feature activation-7.80e-01

Pos logit contributions
 Fl+0.038
 Sn+0.037
 Jenkins+0.034
 Mil+0.034
 Ell+0.033
Neg logit contributions
isdom-0.063
weet-0.059
ercise-0.058
ully-0.056
elling-0.056
Token a
Token ID257
Feature activation-1.84e-01

Pos logit contributions
isdom+0.020
ercise+0.019
ully+0.017
weet+0.017
elling+0.017
Neg logit contributions
 Fl-0.020
 Sn-0.020
 Jenkins-0.020
 Mil-0.019
 Ell-0.018
Token se
Token ID384
Feature activation-7.05e+00

Pos logit contributions
isdom+0.005
weet+0.004
ww+0.004
ercise+0.004
ully+0.004
Neg logit contributions
 Fl-0.005
 Sn-0.005
 Ell-0.004
 Jenkins-0.004
 Megan-0.004
Tokenag
Token ID363
Feature activation-4.05e-02

Pos logit contributions
isdom+0.118
elling+0.117
ercise+0.114
weet+0.106
 melodies+0.106
Neg logit contributions
 Fl-0.196
 Mil-0.192
 L-0.188
 Ell-0.188
uzz-0.182
Tokenull
Token ID724
Feature activation-2.28e+00

Pos logit contributions
isdom+0.001
ercise+0.001
elling+0.001
weet+0.001
ully+0.001
Neg logit contributions
 Fl-0.001
 Sn-0.001
 Ell-0.001
 Mil-0.001
 Jenkins-0.001
Token swoop
Token ID38527
Feature activation+5.82e-01

Pos logit contributions
isdom+0.071
elling+0.066
ercise+0.066
weet+0.062
night+0.061
Neg logit contributions
 Fl-0.053
 Sn-0.049
 Ell-0.045
 Mil-0.043
 t-0.043
Tokened
Token ID276
Feature activation+9.37e-01

Pos logit contributions
 Fl+0.011
 Sn+0.011
 Ell+0.010
 Mil+0.010
 Jenkins+0.010
Neg logit contributions
isdom-0.019
ercise-0.018
elling-0.018
weet-0.018
ully-0.017
Token down
Token ID866
Feature activation+5.57e+00

Pos logit contributions
 Fl+0.022
 Sn+0.021
 Ell+0.020
 Mil+0.020
 Jenkins+0.019
Neg logit contributions
isdom-0.028
ercise-0.026
elling-0.025
weet-0.025
ully-0.024
Token One
Token ID1881
Feature activation-1.47e+00

Pos logit contributions
isdom+0.037
ercise+0.034
elling+0.034
weet+0.033
ully+0.032
Neg logit contributions
 Fl-0.028
 Sn-0.027
 Ell-0.025
 Mil-0.025
 Jenkins-0.024
Token day
Token ID1110
Feature activation+1.06e+00

Pos logit contributions
isdom+0.041
ercise+0.038
elling+0.035
weet+0.033
leness+0.033
Neg logit contributions
 Fl-0.040
 Mil-0.037
 Sn-0.036
 Ell-0.036
 L-0.036
Token,
Token ID11
Feature activation-2.74e-01

Pos logit contributions
 Sn+0.025
 Fl+0.025
 Jenkins+0.024
 Mil+0.023
 Lee+0.023
Neg logit contributions
isdom-0.028
ercise-0.026
night-0.025
weet-0.025
elling-0.024
Token a
Token ID257
Feature activation-1.41e+00

Pos logit contributions
isdom+0.008
ercise+0.007
weet+0.007
elling+0.007
ully+0.007
Neg logit contributions
 Fl-0.006
 Sn-0.006
 Jenkins-0.006
 Lee-0.005
 Mil-0.005
Token friendly
Token ID8030
Feature activation-3.03e+00

Pos logit contributions
isdom+0.042
ercise+0.039
elling+0.038
weet+0.038
ully+0.037
Neg logit contributions
 Fl-0.032
 Sn-0.031
 Ell-0.029
 Jenkins-0.029
 Mil-0.029
Token se
Token ID384
Feature activation-7.01e+00

Pos logit contributions
isdom+0.088
ercise+0.081
elling+0.081
weet+0.080
ully+0.077
Neg logit contributions
 Fl-0.071
 Sn-0.069
 Jenkins-0.063
 Ell-0.063
 Mil-0.063
Tokenah
Token ID993
Feature activation-1.31e+00

Pos logit contributions
isdom+0.125
elling+0.123
ercise+0.122
iveness+0.109
weet+0.109
Neg logit contributions
 Mil-0.182
 Ell-0.178
 Fl-0.178
uzz-0.175
 Megan-0.173
Tokenorse
Token ID7615
Feature activation-3.38e+00

Pos logit contributions
isdom+0.042
ercise+0.041
elling+0.041
weet+0.037
iveness+0.036
Neg logit contributions
 Fl-0.026
 Mil-0.024
 Ell-0.023
 Mir-0.023
 Sn-0.023
Token sw
Token ID1509
Feature activation-2.69e+00

Pos logit contributions
isdom+0.117
ercise+0.111
elling+0.110
weet+0.104
 melodies+0.102
Neg logit contributions
 Fl-0.061
 Sn-0.056
 Ell-0.052
 Mil-0.051
 Lee-0.050
Tokenam
Token ID321
Feature activation-1.27e+00

Pos logit contributions
isdom+0.058
weet+0.055
ercise+0.052
elling+0.051
ock+0.050
Neg logit contributions
 Fl-0.079
 Mil-0.076
 Sn-0.076
 Jenkins-0.073
 Ell-0.072
Token over
Token ID625
Feature activation+2.45e+00

Pos logit contributions
isdom+0.042
elling+0.037
ercise+0.037
weet+0.036
iper+0.034
Neg logit contributions
 Fl-0.026
 Sn-0.025
 Mil-0.023
 Ell-0.023
 Jenkins-0.023
Token it
Token ID340
Feature activation-4.58e-01

Pos logit contributions
 Fl+0.070
 Sn+0.068
 Mil+0.063
 Ell+0.062
 Jenkins+0.062
Neg logit contributions
isdom-0.100
ercise-0.093
elling-0.092
weet-0.091
ully-0.087
Token,
Token ID11
Feature activation+2.42e+00

Pos logit contributions
isdom+0.015
ercise+0.014
elling+0.014
weet+0.014
ully+0.013
Neg logit contributions
 Fl-0.009
 Sn-0.009
 Ell-0.008
 Mil-0.008
 Jenkins-0.008
Token so
Token ID523
Feature activation-2.92e+00

Pos logit contributions
 Fl+0.050
 Sn+0.048
 Jenkins+0.044
 Mil+0.044
 Ell+0.044
Neg logit contributions
isdom-0.078
ercise-0.072
weet-0.071
elling-0.071
ully-0.067
Token she
Token ID673
Feature activation-5.39e-01

Pos logit contributions
isdom+0.091
ercise+0.085
elling+0.084
weet+0.083
ully+0.080
Neg logit contributions
 Fl-0.064
 Sn-0.061
 Ell-0.056
 Mil-0.056
 Jenkins-0.056
Token could
Token ID714
Feature activation-1.54e+00

Pos logit contributions
isdom+0.015
ercise+0.014
elling+0.013
night+0.013
iper+0.013
Neg logit contributions
 Fl-0.013
 Sn-0.012
 Jenkins-0.012
 Lee-0.012
 Mil-0.011
Token j
Token ID474
Feature activation-6.99e+00

Pos logit contributions
isdom+0.045
ercise+0.042
elling+0.041
weet+0.041
ully+0.039
Neg logit contributions
 Fl-0.036
 Sn-0.035
 Ell-0.032
 Mil-0.032
 Jenkins-0.032
Tokeningle
Token ID17697
Feature activation-1.60e+00

Pos logit contributions
weet+0.120
isdom+0.119
ercise+0.117
elling+0.104
 melodies+0.103
Neg logit contributions
 Fl-0.221
 Megan-0.213
 Mil-0.213
 Ell-0.212
 Sn-0.211
Token them
Token ID606
Feature activation-3.23e-01

Pos logit contributions
isdom+0.043
ercise+0.040
weet+0.040
elling+0.039
off+0.038
Neg logit contributions
 Fl-0.038
 Sn-0.037
 Jenkins-0.036
 Mil-0.034
 Lee-0.034
Token around
Token ID1088
Feature activation+4.81e-01

Pos logit contributions
isdom+0.010
ercise+0.009
elling+0.009
weet+0.009
ully+0.009
Neg logit contributions
 Fl-0.007
 Sn-0.007
 Mil-0.006
 Ell-0.006
 Jenkins-0.006
Token.
Token ID13
Feature activation-1.23e+00

Pos logit contributions
 Fl+0.012
 Sn+0.012
 Jenkins+0.011
 Mil+0.011
 plun+0.011
Neg logit contributions
isdom-0.012
weet-0.011
ercise-0.011
 melodies-0.011
night-0.011
Token Mom
Token ID11254
Feature activation-1.60e+00

Pos logit contributions
isdom+0.032
elling+0.030
ercise+0.029
weet+0.029
night+0.028
Neg logit contributions
 Fl-0.030
 Sn-0.029
 plun-0.028
 Mil-0.027
 Lee-0.027
Token and
Token ID290
Feature activation-2.83e+00

Pos logit contributions
isdom+0.059
ercise+0.055
elling+0.054
weet+0.053
off+0.051
Neg logit contributions
 Fl-0.040
 Sn-0.037
 Ell-0.035
 Mil-0.034
 Jenkins-0.034
Token white
Token ID2330
Feature activation-2.71e+00

Pos logit contributions
isdom+0.098
elling+0.092
ercise+0.089
weet+0.089
off+0.087
Neg logit contributions
 Fl-0.055
 Sn-0.051
 Mil-0.048
 Ell-0.048
 t-0.046
Token cloth
Token ID16270
Feature activation-6.12e-01

Pos logit contributions
isdom+0.070
ercise+0.064
elling+0.063
weet+0.061
ully+0.059
Neg logit contributions
 Fl-0.074
 Sn-0.071
 Ell-0.067
 Mil-0.067
 Jenkins-0.067
Token and
Token ID290
Feature activation-2.60e+00

Pos logit contributions
isdom+0.016
ercise+0.015
elling+0.015
ully+0.015
weet+0.014
Neg logit contributions
 Fl-0.015
 Sn-0.015
 Jenkins-0.014
 Mil-0.014
 Ell-0.014
Token carefully
Token ID7773
Feature activation-7.85e-01

Pos logit contributions
isdom+0.086
elling+0.079
ercise+0.079
weet+0.077
off+0.075
Neg logit contributions
 Fl-0.055
 Sn-0.051
 Ell-0.048
 Mil-0.048
 Mir-0.045
Token se
Token ID384
Feature activation-6.95e+00

Pos logit contributions
isdom+0.024
ercise+0.022
elling+0.022
weet+0.022
ully+0.021
Neg logit contributions
 Fl-0.017
 Sn-0.017
 Jenkins-0.015
 Ell-0.015
 Mil-0.015
Tokenwed
Token ID19103
Feature activation-2.26e+00

Pos logit contributions
weet+0.167
isdom+0.160
elling+0.160
iveness+0.155
mmm+0.150
Neg logit contributions
 Fl-0.138
 pret-0.137
 L-0.133
 Mil-0.132
 Sn-0.128
Token them
Token ID606
Feature activation+1.94e-01

Pos logit contributions
isdom+0.057
ercise+0.054
elling+0.053
ock+0.051
weet+0.051
Neg logit contributions
 Fl-0.056
 Sn-0.055
 Jenkins-0.054
 Lee-0.053
 Mil-0.051
Token together
Token ID1978
Feature activation-8.79e-01

Pos logit contributions
 Fl+0.005
 Sn+0.004
 Jenkins+0.004
 Mil+0.004
 Ell+0.004
Neg logit contributions
isdom-0.006
ercise-0.005
elling-0.005
weet-0.005
ully-0.005
Token.
Token ID13
Feature activation-9.21e-01

Pos logit contributions
isdom+0.026
ercise+0.024
weet+0.023
elling+0.023
ully+0.022
Neg logit contributions
 Fl-0.019
 Sn-0.019
 Jenkins-0.018
 Lee-0.018
 Mil-0.018
Token
Token ID198
Feature activation-4.94e-01

Pos logit contributions
isdom+0.027
ercise+0.026
elling+0.024
weet+0.024
off+0.024
Neg logit contributions
 Fl-0.020
 Sn-0.020
 Mil-0.019
 Jenkins-0.018
 Ell-0.018
Token
Token ID198
Feature activation-1.32e+00

Pos logit contributions
isdom+0.031
ercise+0.029
elling+0.028
weet+0.028
off+0.027
Neg logit contributions
 Fl-0.015
 Sn-0.014
 Ell-0.012
 Mil-0.012
 Jenkins-0.012
TokenJ
Token ID41
Feature activation-5.95e-01

Pos logit contributions
isdom+0.038
elling+0.036
ercise+0.034
weet+0.033
ully+0.033
Neg logit contributions
 Sn-0.031
 Fl-0.031
 Mil-0.030
 Ell-0.029
 Jenkins-0.029
Tokenenny
Token ID11870
Feature activation-6.06e-01

Pos logit contributions
isdom+0.017
ercise+0.016
elling+0.015
weet+0.015
 melodies+0.014
Neg logit contributions
 Fl-0.013
 Sn-0.013
 Mil-0.013
 Jenkins-0.013
 Lee-0.013
Token spotted
Token ID13489
Feature activation-2.08e-01

Pos logit contributions
isdom+0.019
ercise+0.018
elling+0.017
weet+0.017
ully+0.017
Neg logit contributions
 Fl-0.013
 Sn-0.012
 Jenkins-0.011
 Mil-0.011
 Ell-0.011
Token a
Token ID257
Feature activation+5.33e-02

Pos logit contributions
isdom+0.006
weet+0.005
ercise+0.005
elling+0.005
ock+0.005
Neg logit contributions
 Sn-0.005
 Fl-0.005
 Jenkins-0.004
 Lee-0.004
 Mil-0.004
Token se
Token ID384
Feature activation-6.93e+00

Pos logit contributions
 Fl+0.001
 Sn+0.001
 Mir+0.001
 Mil+0.001
 Lee+0.001
Neg logit contributions
isdom-0.001
ercise-0.001
ww-0.001
weet-0.001
elling-0.001
Tokenag
Token ID363
Feature activation+4.17e-01

Pos logit contributions
isdom+0.126
ercise+0.112
elling+0.112
weet+0.102
iveness+0.099
Neg logit contributions
 Fl-0.200
 Mil-0.199
 Megan-0.193
 Ell-0.193
 Sn-0.189
Tokenull
Token ID724
Feature activation-1.47e+00

Pos logit contributions
 Fl+0.013
 Sn+0.012
 Jenkins+0.012
 Ell+0.012
 Lee+0.012
Neg logit contributions
isdom-0.009
ercise-0.008
weet-0.008
elling-0.008
ully-0.008
Token on
Token ID319
Feature activation+3.22e+00

Pos logit contributions
isdom+0.049
ercise+0.046
elling+0.045
night+0.042
weet+0.042
Neg logit contributions
 Fl-0.030
 Sn-0.028
 Ell-0.026
 Mil-0.025
 Jenkins-0.025
Token the
Token ID262
Feature activation+3.09e-01

Pos logit contributions
 Fl+0.063
 Sn+0.061
 Jenkins+0.056
 Ell+0.055
 Mil+0.055
Neg logit contributions
isdom-0.106
ercise-0.099
elling-0.097
weet-0.097
ully-0.093
Token sand
Token ID6450
Feature activation+3.50e+00

Pos logit contributions
 Fl+0.007
 Sn+0.007
 Ell+0.006
 Mil+0.006
 Jenkins+0.006
Neg logit contributions
isdom-0.009
ercise-0.009
elling-0.008
weet-0.008
ully-0.008
Token gently
Token ID15165
Feature activation-5.93e-01

Pos logit contributions
 Fl+0.022
 Sn+0.021
 Jenkins+0.020
 Mil+0.020
 Ell+0.020
Neg logit contributions
isdom-0.030
ercise-0.028
elling-0.027
weet-0.027
ully-0.026
Token took
Token ID1718
Feature activation-3.03e+00

Pos logit contributions
isdom+0.018
ercise+0.017
elling+0.017
weet+0.016
ully+0.016
Neg logit contributions
 Fl-0.013
 Sn-0.012
 Jenkins-0.012
 Mil-0.012
 Ell-0.011
Token the
Token ID262
Feature activation-3.85e-01

Pos logit contributions
isdom+0.100
ercise+0.093
elling+0.091
weet+0.091
ully+0.088
Neg logit contributions
 Fl-0.063
 Sn-0.060
 Ell-0.056
 Mil-0.054
 Jenkins-0.053
Token shirt
Token ID10147
Feature activation-1.70e+00

Pos logit contributions
isdom+0.013
ercise+0.012
elling+0.011
weet+0.011
ully+0.011
Neg logit contributions
 Fl-0.008
 Sn-0.007
 Ell-0.007
 t-0.007
 Jenkins-0.007
Token and
Token ID290
Feature activation-2.96e+00

Pos logit contributions
isdom+0.046
ercise+0.043
elling+0.042
weet+0.041
ully+0.040
Neg logit contributions
 Fl-0.043
 Sn-0.042
 Mil-0.039
 Ell-0.039
 Jenkins-0.039
Token se
Token ID384
Feature activation-6.92e+00

Pos logit contributions
isdom+0.085
ercise+0.082
elling+0.077
weet+0.076
ully+0.074
Neg logit contributions
 Fl-0.066
 Sn-0.065
 Jenkins-0.064
 Mil-0.062
 Lee-0.060
Tokenwed
Token ID19103
Feature activation-2.20e+00

Pos logit contributions
weet+0.167
isdom+0.157
iveness+0.152
elling+0.151
mmm+0.149
Neg logit contributions
 Fl-0.148
uzz-0.141
 L-0.138
 Sn-0.134
 Mil-0.132
Token it
Token ID340
Feature activation-5.64e-02

Pos logit contributions
isdom+0.053
ercise+0.050
elling+0.050
ock+0.048
weet+0.047
Neg logit contributions
 Sn-0.056
 Fl-0.056
 Jenkins-0.055
 Lee-0.054
 Mil-0.053
Token back
Token ID736
Feature activation-9.99e-01

Pos logit contributions
isdom+0.002
ercise+0.001
elling+0.001
weet+0.001
off+0.001
Neg logit contributions
 Fl-0.001
 Sn-0.001
 Mil-0.001
 Jenkins-0.001
 Lee-0.001
Token together
Token ID1978
Feature activation-1.06e+00

Pos logit contributions
isdom+0.031
ercise+0.028
elling+0.028
weet+0.028
ully+0.027
Neg logit contributions
 Fl-0.023
 Sn-0.022
 Ell-0.020
 Mil-0.020
 Jenkins-0.020
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
isdom+0.027
ercise+0.025
weet+0.025
night+0.025
elling+0.024
Neg logit contributions
 Fl-0.025
 Sn-0.025
 Mil-0.024
 Lee-0.023
 Jenkins-0.023
Token and
Token ID290
Feature activation-1.06e+00

Pos logit contributions
 Fl+0.005
 Sn+0.005
 Ell+0.005
 Mil+0.005
 Jenkins+0.005
Neg logit contributions
isdom-0.007
ercise-0.006
elling-0.006
weet-0.006
off-0.006
Token some
Token ID617
Feature activation+4.81e-01

Pos logit contributions
isdom+0.036
ercise+0.033
elling+0.033
weet+0.032
ully+0.032
Neg logit contributions
 Fl-0.021
 Sn-0.020
 Ell-0.018
 Mil-0.018
 Lee-0.017
Token buttons
Token ID12163
Feature activation+1.66e-01

Pos logit contributions
 Fl+0.011
 Sn+0.010
 Ell+0.010
 Mil+0.010
 Jenkins+0.009
Neg logit contributions
isdom-0.015
ercise-0.014
elling-0.013
weet-0.013
ully-0.013
Token.
Token ID13
Feature activation+4.68e-01

Pos logit contributions
 Fl+0.003
 Sn+0.003
 Ell+0.003
 Mil+0.003
 Lee+0.003
Neg logit contributions
isdom-0.005
ercise-0.005
elling-0.005
weet-0.005
ully-0.005
Token I
Token ID314
Feature activation+1.63e+00

Pos logit contributions
 Fl+0.010
 Sn+0.010
 Ell+0.009
 Mil+0.009
 Jenkins+0.009
Neg logit contributions
isdom-0.014
ercise-0.013
elling-0.013
weet-0.013
ully-0.012
Token se
Token ID384
Feature activation-6.90e+00

Pos logit contributions
 Fl+0.035
 Sn+0.033
 Jenkins+0.032
 Lee+0.032
 Mil+0.030
Neg logit contributions
isdom-0.051
ercise-0.048
elling-0.046
off-0.045
weet-0.045
Tokenwed
Token ID19103
Feature activation-2.18e+00

Pos logit contributions
weet+0.150
ully+0.150
isdom+0.150
elling+0.146
iveness+0.142
Neg logit contributions
 pret-0.152
 Fl-0.149
 L-0.148
 Mil-0.146
 Ann-0.141
Token them
Token ID606
Feature activation+1.01e+00

Pos logit contributions
isdom+0.067
ercise+0.062
elling+0.061
weet+0.061
ully+0.059
Neg logit contributions
 Fl-0.049
 Sn-0.047
 Ell-0.044
 Mil-0.043
 Jenkins-0.042
Token together
Token ID1978
Feature activation-1.24e-01

Pos logit contributions
 Fl+0.023
 Sn+0.022
 Ell+0.020
 Mil+0.020
 Jenkins+0.019
Neg logit contributions
isdom-0.031
ercise-0.029
elling-0.029
weet-0.028
ully-0.027
Token and
Token ID290
Feature activation-2.16e+00

Pos logit contributions
isdom+0.004
ercise+0.003
elling+0.003
weet+0.003
ully+0.003
Neg logit contributions
 Fl-0.003
 Sn-0.003
 Ell-0.003
 Mil-0.003
 Jenkins-0.002
Token stuffed
Token ID22259
Feature activation-2.06e+00

Pos logit contributions
isdom+0.063
ercise+0.059
elling+0.058
weet+0.057
off+0.054
Neg logit contributions
 Fl-0.050
 Sn-0.049
 Jenkins-0.045
 Ell-0.045
 Mil-0.045
Token hope
Token ID2911
Feature activation-2.16e+00

Pos logit contributions
 Jenkins+0.025
 Sn+0.024
 Fl+0.024
 Lee+0.024
 Mil+0.023
Neg logit contributions
isdom-0.033
ercise-0.033
bye-0.032
weet-0.031
ock-0.031
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
isdom+0.066
ercise+0.062
weet+0.061
elling+0.061
night+0.058
Neg logit contributions
 Fl-0.047
 Sn-0.046
 Jenkins-0.042
 Mil-0.041
 Ell-0.041
Token sun
Token ID4252
Feature activation+1.11e+00

Pos logit contributions
 Fl+0.045
 Sn+0.044
 Mil+0.042
 Ell+0.041
 Jenkins+0.041
Neg logit contributions
isdom-0.033
ercise-0.031
elling-0.030
weet-0.030
ully-0.028
Token will
Token ID481
Feature activation+1.23e+00

Pos logit contributions
 Fl+0.023
 Sn+0.022
 Ell+0.021
 Jenkins+0.021
 Mil+0.021
Neg logit contributions
isdom-0.034
ercise-0.033
elling-0.032
weet-0.031
off-0.031
Token come
Token ID1282
Feature activation+1.64e+00

Pos logit contributions
 Fl+0.029
 Sn+0.028
 Jenkins+0.026
 Mil+0.026
 Ell+0.026
Neg logit contributions
isdom-0.036
ercise-0.033
elling-0.033
weet-0.032
ully-0.031
Token out
Token ID503
Feature activation+4.56e+00

Pos logit contributions
 Fl+0.031
 Sn+0.030
 Ell+0.026
 Jenkins+0.025
 Lee+0.024
Neg logit contributions
isdom-0.058
ercise-0.054
elling-0.053
weet-0.052
off-0.051
Token tomorrow
Token ID9439
Feature activation+7.41e-01

Pos logit contributions
 Fl+0.092
 Sn+0.088
 Ell+0.080
 Mil+0.078
 L+0.078
Neg logit contributions
isdom-0.158
ercise-0.150
elling-0.140
ully-0.139
iper-0.134
Token.
Token ID13
Feature activation+9.82e-01

Pos logit contributions
 Fl+0.014
 Sn+0.013
 Ell+0.012
 Mil+0.012
 Jenkins+0.012
Neg logit contributions
isdom-0.025
ercise-0.024
elling-0.023
weet-0.023
ully-0.022
Token<|endoftext|>
Token ID50256
Feature activation+1.65e+00

Pos logit contributions
 Fl+0.019
 Sn+0.019
 Jenkins+0.019
 Ell+0.018
 Lee+0.018
Neg logit contributions
isdom-0.029
weet-0.027
ercise-0.027
elling-0.027
bye-0.026
TokenAnna
Token ID31160
Feature activation+9.20e-01

Pos logit contributions
 Mil+0.034
 Fl+0.033
 Sn+0.033
 Ell+0.033
sed+0.032
Neg logit contributions
elling-0.043
off-0.043
isdom-0.042
ock-0.042
weet-0.041
Token and
Token ID290
Feature activation-3.15e+00

Pos logit contributions
 Sn+0.023
 Fl+0.023
 Jenkins+0.023
 Ell+0.022
 Mil+0.022
Neg logit contributions
isdom-0.024
ercise-0.022
elling-0.021
night-0.021
off-0.021
Token hugged
Token ID41130
Feature activation-1.28e+00

Pos logit contributions
 Jenkins+0.055
 Sn+0.054
 Lee+0.052
 Me+0.051
 Fl+0.050
Neg logit contributions
isdom-0.045
ercise-0.041
elling-0.040
ully-0.040
weet-0.040
Token her
Token ID607
Feature activation+2.88e+00

Pos logit contributions
isdom+0.038
elling+0.035
ercise+0.035
weet+0.035
ock+0.034
Neg logit contributions
 Fl-0.028
 Sn-0.027
 Mil-0.026
 Jenkins-0.025
 Ell-0.025
Token and
Token ID290
Feature activation-1.64e+00

Pos logit contributions
 Fl+0.065
 Sn+0.063
 Mil+0.063
 Ell+0.061
 Jenkins+0.060
Neg logit contributions
isdom-0.084
ercise-0.078
elling-0.076
weet-0.075
night-0.073
Token said
Token ID531
Feature activation+1.31e+00

Pos logit contributions
isdom+0.043
ercise+0.039
weet+0.038
elling+0.038
night+0.036
Neg logit contributions
 Fl-0.042
 Sn-0.042
 Jenkins-0.040
 Ell-0.039
 Mil-0.039
Token,
Token ID11
Feature activation+5.59e+00

Pos logit contributions
 Sn+0.034
 Jenkins+0.033
 Fl+0.032
 Mil+0.031
 plun+0.031
Neg logit contributions
isdom-0.032
night-0.028
ercise-0.027
elling-0.027
weet-0.027
Token "
Token ID366
Feature activation+4.31e+00

Pos logit contributions
 Jenkins+0.086
 Mil+0.084
 Megan+0.082
 Fl+0.081
 Sn+0.081
Neg logit contributions
isdom-0.185
weet-0.173
ercise-0.171
elling-0.160
iveness-0.159
TokenIt
Token ID1026
Feature activation+5.97e-01

Pos logit contributions
 Fl+0.075
 Sn+0.072
 Ell+0.063
 Mil+0.063
 Jenkins+0.061
Neg logit contributions
isdom-0.158
ercise-0.147
elling-0.144
weet-0.142
ully-0.140
Token's
Token ID338
Feature activation+2.14e+00

Pos logit contributions
 Sn+0.017
 Mil+0.017
 Lee+0.017
 Fl+0.017
 Jenkins+0.017
Neg logit contributions
isdom-0.012
elling-0.012
ercise-0.011
off-0.011
weet-0.011
Token okay
Token ID8788
Feature activation+2.03e-01

Pos logit contributions
 Fl+0.041
 Sn+0.038
 Ell+0.034
 Jenkins+0.034
 Mil+0.033
Neg logit contributions
isdom-0.075
ercise-0.070
elling-0.069
weet-0.068
ully-0.067
Token,
Token ID11
Feature activation+5.15e+00

Pos logit contributions
 Sn+0.005
 Fl+0.005
 Mil+0.005
 Ell+0.004
 Jenkins+0.004
Neg logit contributions
isdom-0.006
elling-0.005
weet-0.005
night-0.005
ercise-0.005
Token Lily
Token ID20037
Feature activation+1.07e+00

Pos logit contributions
 Fl+0.078
 Sn+0.078
 Jenkins+0.076
 Mil+0.074
 Frost+0.068
Neg logit contributions
isdom-0.179
weet-0.174
elling-0.170
ercise-0.165
ock-0.162
Token them
Token ID606
Feature activation+1.88e+00

Pos logit contributions
isdom+0.013
ercise+0.012
elling+0.012
weet+0.012
ully+0.011
Neg logit contributions
 Fl-0.012
 Sn-0.011
 Jenkins-0.010
 Mil-0.010
 Ell-0.010
Token,
Token ID11
Feature activation+4.58e+00

Pos logit contributions
 Fl+0.050
 Sn+0.048
 Ell+0.045
 Mil+0.045
 Jenkins+0.045
Neg logit contributions
isdom-0.050
ercise-0.046
elling-0.045
weet-0.044
ully-0.042
Token "
Token ID366
Feature activation+3.66e+00

Pos logit contributions
 Fl+0.065
 Sn+0.063
 Jenkins+0.062
 Mil+0.061
 Megan+0.059
Neg logit contributions
isdom-0.168
weet-0.157
ercise-0.151
iveness-0.145
elling-0.145
TokenB
Token ID33
Feature activation-1.38e+00

Pos logit contributions
 Fl+0.066
 Sn+0.065
 Ell+0.059
 Mil+0.057
 Jenkins+0.055
Neg logit contributions
isdom-0.128
ercise-0.117
elling-0.117
night-0.116
iper-0.114
Tokenoys
Token ID19417
Feature activation+7.07e-01

Pos logit contributions
isdom+0.039
ercise+0.036
elling+0.035
weet+0.035
ully+0.033
Neg logit contributions
 Fl-0.035
 Sn-0.033
 Ell-0.031
 Mil-0.031
 Jenkins-0.031
Token,
Token ID11
Feature activation+5.71e+00

Pos logit contributions
 Fl+0.016
 Sn+0.016
 Mil+0.015
 Jenkins+0.015
 Ell+0.015
Neg logit contributions
isdom-0.021
ercise-0.019
elling-0.019
weet-0.019
off-0.018
Token you
Token ID345
Feature activation+2.14e+00

Pos logit contributions
 Fl+0.143
 Sn+0.141
 Jenkins+0.136
 Mil+0.131
 Ell+0.130
Neg logit contributions
isdom-0.156
ercise-0.143
weet-0.143
elling-0.140
off-0.134
Token can
Token ID460
Feature activation-5.98e-01

Pos logit contributions
 Fl+0.039
 Sn+0.038
 Mil+0.035
 Jenkins+0.034
 Ell+0.034
Neg logit contributions
isdom-0.075
ercise-0.070
elling-0.069
weet-0.068
off-0.066
Token't
Token ID470
Feature activation-2.59e+00

Pos logit contributions
isdom+0.019
ercise+0.018
elling+0.018
weet+0.017
ully+0.017
Neg logit contributions
 Fl-0.013
 Sn-0.012
 Ell-0.011
 Jenkins-0.011
 Mil-0.011
Token be
Token ID307
Feature activation+5.99e-01

Pos logit contributions
isdom+0.085
elling+0.080
ercise+0.079
weet+0.077
iper+0.077
Neg logit contributions
 Fl-0.050
 Sn-0.048
 Ell-0.045
 Jenkins-0.043
 t-0.042
Token happy
Token ID3772
Feature activation-1.81e+00

Pos logit contributions
 Fl+0.015
 Sn+0.014
 Jenkins+0.013
 Mil+0.013
 Ell+0.013
Neg logit contributions
isdom-0.017
ercise-0.016
weet-0.015
elling-0.015
off-0.015
Token hugged
Token ID41130
Feature activation-1.39e+00

Pos logit contributions
 Fl+0.027
 Sn+0.027
 Jenkins+0.025
 Mil+0.025
 Ell+0.025
Neg logit contributions
isdom-0.033
ercise-0.031
elling-0.030
weet-0.030
ully-0.029
Token him
Token ID683
Feature activation+2.09e+00

Pos logit contributions
isdom+0.041
ercise+0.039
elling+0.038
weet+0.037
off+0.036
Neg logit contributions
 Fl-0.033
 Sn-0.032
 Ell-0.030
 Mil-0.030
 Lee-0.030
Token back
Token ID736
Feature activation+1.18e+00

Pos logit contributions
 Fl+0.054
 Sn+0.053
 Mil+0.050
 Ell+0.050
 Jenkins+0.049
Neg logit contributions
isdom-0.055
ercise-0.051
elling-0.050
weet-0.049
ully-0.047
Token and
Token ID290
Feature activation-3.00e+00

Pos logit contributions
 Fl+0.025
 Sn+0.023
 Lee+0.022
 Ell+0.022
 Jenkins+0.021
Neg logit contributions
isdom-0.039
ercise-0.038
elling-0.037
weet-0.036
ully-0.035
Token said
Token ID531
Feature activation+1.19e+00

Pos logit contributions
isdom+0.085
ercise+0.079
elling+0.078
weet+0.077
ully+0.073
Neg logit contributions
 Fl-0.074
 Sn-0.071
 Ell-0.067
 Mil-0.066
 Jenkins-0.065
Token,
Token ID11
Feature activation+4.77e+00

Pos logit contributions
 Sn+0.027
 Fl+0.027
 Jenkins+0.026
 Mil+0.025
 Ell+0.024
Neg logit contributions
isdom-0.035
ercise-0.032
elling-0.030
weet-0.030
night-0.030
Token "
Token ID366
Feature activation+3.27e+00

Pos logit contributions
 Fl+0.058
 Sn+0.054
 Mil+0.052
 Jenkins+0.051
 Ell+0.048
Neg logit contributions
isdom-0.186
ercise-0.174
weet-0.172
elling-0.167
ully-0.163
TokenOkay
Token ID16454
Feature activation+2.63e-01

Pos logit contributions
 Fl+0.052
 Sn+0.051
 Ell+0.045
 Mil+0.044
 Jenkins+0.042
Neg logit contributions
isdom-0.121
elling-0.114
ercise-0.111
weet-0.109
iper-0.106
Token,
Token ID11
Feature activation+2.56e+00

Pos logit contributions
 Fl+0.006
 Sn+0.006
 Mil+0.006
 Jenkins+0.006
 Flor+0.005
Neg logit contributions
isdom-0.007
ercise-0.007
elling-0.007
weet-0.006
bye-0.006
Token Tom
Token ID4186
Feature activation-2.45e-01

Pos logit contributions
 Fl+0.054
 Sn+0.052
 Ell+0.048
 Mil+0.048
 Jenkins+0.047
Neg logit contributions
isdom-0.082
ercise-0.076
elling-0.075
weet-0.074
ully-0.072
Token,
Token ID11
Feature activation+4.05e+00

Pos logit contributions
isdom+0.008
ercise+0.007
elling+0.007
weet+0.007
ully+0.007
Neg logit contributions
 Fl-0.005
 Sn-0.005
 Mil-0.005
 Ell-0.005
 Jenkins-0.005
Token
Token ID26391
Feature activation-1.94e-04

Pos logit contributions
isdom+0.083
weet+0.079
ercise+0.075
elling+0.074
 melodies+0.073
Neg logit contributions
 Fl-0.084
 Sn-0.081
 Lee-0.078
 Ell-0.078
 Jenkins-0.076
Token His
Token ID2399
Feature activation+1.89e+00

Pos logit contributions
isdom+0.000
ercise+0.000
weet+0.000
off+0.000
ully+0.000
Neg logit contributions
 Fl-0.000
 Sn-0.000
 Ell-0.000
 Mil-0.000
 Flor-0.000
Token mom
Token ID1995
Feature activation-1.71e+00

Pos logit contributions
 Fl+0.043
 Sn+0.042
 Ell+0.041
 Mil+0.040
 Flor+0.040
Neg logit contributions
isdom-0.055
ercise-0.051
elling-0.048
bye-0.047
weet-0.047
Tokenmy
Token ID1820
Feature activation-1.77e+00

Pos logit contributions
isdom+0.044
ercise+0.041
elling+0.040
weet+0.038
night+0.037
Neg logit contributions
 Fl-0.047
 Sn-0.045
 Ell-0.043
 Jenkins-0.042
 Lee-0.042
Token said
Token ID531
Feature activation+1.11e+00

Pos logit contributions
isdom+0.045
ercise+0.041
elling+0.040
weet+0.039
ully+0.038
Neg logit contributions
 Fl-0.048
 Sn-0.047
 Mil-0.045
 Jenkins-0.044
 Ell-0.043
Token,
Token ID11
Feature activation+4.69e+00

Pos logit contributions
 Jenkins+0.029
 Sn+0.028
 Fl+0.027
 bathroom+0.027
 plun+0.026
Neg logit contributions
isdom-0.026
ercise-0.023
night-0.023
ly-0.023
ww-0.023
Token
Token ID6184
Feature activation-5.06e-01

Pos logit contributions
 Fl+0.061
 Sn+0.057
 Jenkins+0.055
 Mil+0.054
 Flor+0.053
Neg logit contributions
isdom-0.172
weet-0.162
ercise-0.160
elling-0.155
ully-0.151
Token
Token ID95
Feature activation-1.19e+00

Pos logit contributions
isdom+0.014
ercise+0.013
elling+0.013
weet+0.013
ully+0.012
Neg logit contributions
 Fl-0.012
 Sn-0.012
 Ell-0.011
 Mil-0.011
 Jenkins-0.011
Token
Token ID26391
Feature activation+5.17e-01

Pos logit contributions
isdom+0.031
ercise+0.028
elling+0.028
weet+0.028
ully+0.026
Neg logit contributions
 Fl-0.032
 Sn-0.031
 Ell-0.029
 Mil-0.029
 Jenkins-0.029
Token
Token ID129
Feature activation-1.59e+00

Pos logit contributions
 Fl+0.013
 Sn+0.013
 Ell+0.012
 Mil+0.012
 Flor+0.012
Neg logit contributions
isdom-0.014
ercise-0.013
weet-0.012
off-0.012
elling-0.012
Token
Token ID241
Feature activation+3.99e+00

Pos logit contributions
isdom+0.047
elling+0.044
weet+0.043
ercise+0.042
night+0.042
Neg logit contributions
 Fl-0.035
 Sn-0.034
 Mil-0.031
 Ell-0.030
 Mir-0.029
Token Lily
Token ID20037
Feature activation-2.14e+00

Pos logit contributions
isdom+0.105
ercise+0.098
weet+0.096
elling+0.096
ully+0.092
Neg logit contributions
 Fl-0.061
 Sn-0.059
 Mil-0.054
 Jenkins-0.054
 Ell-0.053
Token went
Token ID1816
Feature activation-1.50e+00

Pos logit contributions
isdom+0.063
ercise+0.059
elling+0.057
weet+0.057
ully+0.055
Neg logit contributions
 Fl-0.050
 Sn-0.048
 Ell-0.045
 Mil-0.044
 Jenkins-0.044
Token on
Token ID319
Feature activation+9.77e-01

Pos logit contributions
isdom+0.051
elling+0.046
ercise+0.045
weet+0.045
ully+0.042
Neg logit contributions
 Fl-0.032
 Sn-0.031
 Ell-0.028
 Lee-0.028
 Mil-0.027
Token an
Token ID281
Feature activation-3.41e+00

Pos logit contributions
 Fl+0.020
 Sn+0.019
 Ell+0.017
 Jenkins+0.017
 Mil+0.017
Neg logit contributions
isdom-0.032
ercise-0.030
elling-0.030
weet-0.030
ully-0.029
Token adventure
Token ID8855
Feature activation-1.54e+00

Pos logit contributions
isdom+0.095
elling+0.093
leness+0.088
iveness+0.085
reci+0.081
Neg logit contributions
 t-0.074
 hiding-0.066
 hide-0.066
 Fl-0.066
 p-0.061
Token in
Token ID287
Feature activation+1.81e+00

Pos logit contributions
isdom+0.054
elling+0.052
ercise+0.050
weet+0.048
iveness+0.046
Neg logit contributions
 Fl-0.029
 Sn-0.027
 Ell-0.026
 Mil-0.025
 Lee-0.024
Token the
Token ID262
Feature activation-1.07e+00

Pos logit contributions
 Fl+0.039
 Sn+0.039
 Jenkins+0.037
 Mil+0.036
 Ell+0.036
Neg logit contributions
isdom-0.054
weet-0.049
ercise-0.049
elling-0.047
ully-0.047
Token forest
Token ID8222
Feature activation+9.19e-01

Pos logit contributions
isdom+0.040
elling+0.035
weet+0.035
ercise+0.034
ear+0.034
Neg logit contributions
 Fl-0.019
 Sn-0.016
 t-0.015
 pant-0.015
 bathroom-0.015
Token with
Token ID351
Feature activation+3.77e-01

Pos logit contributions
 Fl+0.021
 Sn+0.021
 Jenkins+0.019
 Ell+0.019
 Mil+0.019
Neg logit contributions
isdom-0.026
weet-0.024
ercise-0.024
off-0.023
ully-0.023
Token their
Token ID511
Feature activation+1.59e+00

Pos logit contributions
 Sn+0.009
 Jenkins+0.008
 Fl+0.008
 Mil+0.008
 plun+0.008
Neg logit contributions
isdom-0.010
ercise-0.009
weet-0.009
ully-0.009
elling-0.009
Token snacks
Token ID28487
Feature activation+5.09e-01

Pos logit contributions
 Sn+0.040
 Fl+0.040
 Mil+0.038
 Ell+0.037
 Jenkins+0.037
Neg logit contributions
isdom-0.042
ercise-0.040
elling-0.038
weet-0.037
ully-0.036
Token
Token ID198
Feature activation-1.72e+00

Pos logit contributions
isdom+0.054
ercise+0.051
weet+0.050
elling+0.049
off+0.048
Neg logit contributions
 Fl-0.028
 Sn-0.027
 Mil-0.024
 Ell-0.024
 Jenkins-0.024
TokenL
Token ID43
Feature activation-3.97e-01

Pos logit contributions
isdom+0.045
ercise+0.042
elling+0.041
weet+0.040
ully+0.038
Neg logit contributions
 Fl-0.047
 Sn-0.045
 Ell-0.042
 Mil-0.042
 Jenkins-0.042
Tokenily
Token ID813
Feature activation-3.29e-01

Pos logit contributions
isdom+0.014
ercise+0.014
elling+0.013
weet+0.013
ully+0.013
Neg logit contributions
 Fl-0.007
 Sn-0.006
 Ell-0.006
 Mil-0.006
 Jenkins-0.006
Token started
Token ID2067
Feature activation-1.02e+00

Pos logit contributions
isdom+0.011
ercise+0.011
elling+0.010
weet+0.010
ully+0.010
Neg logit contributions
 Fl-0.006
 Sn-0.006
 Ell-0.005
 Mil-0.005
 Jenkins-0.005
Token cleaning
Token ID12724
Feature activation+6.92e-01

Pos logit contributions
isdom+0.025
ercise+0.022
weet+0.022
elling+0.021
off+0.021
Neg logit contributions
 Fl-0.028
 Sn-0.027
 Jenkins-0.025
 Mil-0.025
 Ell-0.025
Token,
Token ID11
Feature activation+7.33e-01

Pos logit contributions
 Fl+0.018
 Sn+0.018
 Jenkins+0.017
 Lee+0.017
 Mil+0.017
Neg logit contributions
isdom-0.015
elling-0.015
ercise-0.014
heart-0.014
ock-0.014
Token but
Token ID475
Feature activation-1.42e+00

Pos logit contributions
 Fl+0.016
 Sn+0.016
 Jenkins+0.015
 Mil+0.015
 Ell+0.015
Neg logit contributions
isdom-0.022
ercise-0.020
weet-0.020
elling-0.020
ully-0.019
Token she
Token ID673
Feature activation-6.90e-01

Pos logit contributions
isdom+0.037
ercise+0.035
weet+0.033
elling+0.033
night+0.031
Neg logit contributions
 Fl-0.037
 Sn-0.036
 Jenkins-0.034
 Mil-0.034
 Ell-0.033
Token noticed
Token ID6810
Feature activation-1.01e+00

Pos logit contributions
isdom+0.020
ercise+0.018
iper+0.017
night+0.017
ully+0.017
Neg logit contributions
 Sn-0.016
 Fl-0.016
 Lee-0.015
 Jenkins-0.015
 Ell-0.015
Token something
Token ID1223
Feature activation+7.04e-01

Pos logit contributions
isdom+0.023
ercise+0.021
elling+0.021
weet+0.020
ully+0.019
Neg logit contributions
 Fl-0.030
 Sn-0.029
 Mil-0.028
 Jenkins-0.028
 Ell-0.027
Token strange
Token ID6283
Feature activation-1.14e+00

Pos logit contributions
 Fl+0.018
 Sn+0.018
 Lee+0.017
 Jenkins+0.016
 Mil+0.016
Neg logit contributions
isdom-0.018
ercise-0.017
elling-0.017
weet-0.016
ock-0.016
Token their
Token ID511
Feature activation+9.26e-01

Pos logit contributions
isdom+0.037
ercise+0.035
night+0.035
weet+0.034
ock+0.033
Neg logit contributions
 Sn-0.039
 Fl-0.038
 Jenkins-0.037
 Ell-0.036
 Lee-0.035
Token hands
Token ID2832
Feature activation-7.89e-02

Pos logit contributions
 Fl+0.020
 Sn+0.019
 Ell+0.018
 Jenkins+0.018
 Mil+0.017
Neg logit contributions
isdom-0.029
ercise-0.027
elling-0.026
weet-0.026
off-0.025
Token.
Token ID13
Feature activation+9.86e-01

Pos logit contributions
isdom+0.002
ercise+0.002
weet+0.002
elling+0.002
night+0.002
Neg logit contributions
 Fl-0.002
 Sn-0.002
 Mil-0.002
 Ell-0.002
 Jenkins-0.002
Token But
Token ID887
Feature activation+4.20e-01

Pos logit contributions
 Sn+0.021
 Jenkins+0.021
 t+0.020
 Esk+0.020
 Fl+0.019
Neg logit contributions
isdom-0.025
ercise-0.024
night-0.023
weet-0.023
elling-0.023
Token the
Token ID262
Feature activation+8.49e-01

Pos logit contributions
 Jenkins+0.012
 Sn+0.011
 Esk+0.011
 plun+0.011
 Lee+0.011
Neg logit contributions
ercise-0.008
isdom-0.008
night-0.008
weet-0.007
iper-0.007
Token bread
Token ID8509
Feature activation+2.09e-01

Pos logit contributions
 Fl+0.020
 Sn+0.019
 Ell+0.018
 Mil+0.018
 Jenkins+0.018
Neg logit contributions
isdom-0.024
ercise-0.023
weet-0.022
elling-0.022
night-0.021
Token and
Token ID290
Feature activation-5.26e-01

Pos logit contributions
 Sn+0.004
 Fl+0.004
 Jenkins+0.004
 Ell+0.004
 Lee+0.004
Neg logit contributions
isdom-0.006
elling-0.006
ercise-0.006
weet-0.005
ets-0.005
Token jam
Token ID16853
Feature activation+8.07e-01

Pos logit contributions
isdom+0.014
ercise+0.013
elling+0.013
weet+0.013
night+0.012
Neg logit contributions
 Fl-0.013
 Sn-0.013
 Jenkins-0.012
 Ell-0.012
 Mil-0.012
Token are
Token ID389
Feature activation+2.07e+00

Pos logit contributions
 Sn+0.016
 Jenkins+0.016
 Fl+0.016
 Lee+0.015
 Ell+0.015
Neg logit contributions
isdom-0.023
ercise-0.023
elling-0.022
ock-0.022
ets-0.022
Token still
Token ID991
Feature activation+6.08e-01

Pos logit contributions
 Fl+0.047
 Sn+0.046
 Lee+0.044
 Ell+0.044
 Jenkins+0.043
Neg logit contributions
isdom-0.059
ercise-0.056
weet-0.054
elling-0.054
ock-0.050
Token too
Token ID1165
Feature activation+2.91e+00

Pos logit contributions
 Fl+0.014
 Sn+0.014
 Ell+0.013
 Lee+0.013
 Mil+0.013
Neg logit contributions
isdom-0.017
ercise-0.016
elling-0.016
weet-0.016
ully-0.015
Token hug
Token ID16225
Feature activation-1.49e+00

Pos logit contributions
isdom+0.028
ercise+0.026
elling+0.026
weet+0.025
ully+0.024
Neg logit contributions
 Fl-0.025
 Sn-0.023
 Ell-0.022
 Jenkins-0.022
 Mil-0.022
Token to
Token ID284
Feature activation+1.66e+00

Pos logit contributions
isdom+0.045
ercise+0.042
elling+0.042
weet+0.040
ully+0.040
Neg logit contributions
 Fl-0.034
 Sn-0.033
 Ell-0.030
 Lee-0.030
 Jenkins-0.030
Token make
Token ID787
Feature activation-2.81e+00

Pos logit contributions
 Fl+0.044
 Sn+0.042
 Ell+0.039
 Mil+0.039
 Lee+0.038
Neg logit contributions
isdom-0.045
ercise-0.042
elling-0.041
weet-0.040
ully-0.039
Token you
Token ID345
Feature activation-4.78e-01

Pos logit contributions
isdom+0.075
ercise+0.069
elling+0.067
weet+0.066
ully+0.064
Neg logit contributions
 Fl-0.075
 Sn-0.072
 Ell-0.068
 Mil-0.067
 Jenkins-0.066
Token feel
Token ID1254
Feature activation+4.72e-02

Pos logit contributions
isdom+0.018
ercise+0.017
elling+0.016
ully+0.016
weet+0.016
Neg logit contributions
 Fl-0.008
 Sn-0.007
 Ell-0.007
 Mil-0.006
 Jenkins-0.006
Token better
Token ID1365
Feature activation-1.53e-02

Pos logit contributions
 Fl+0.001
 Sn+0.001
 Ell+0.001
 Mil+0.001
 Jenkins+0.001
Neg logit contributions
isdom-0.001
ercise-0.001
elling-0.001
weet-0.001
ully-0.001
Token,"
Token ID553
Feature activation+3.39e-01

Pos logit contributions
isdom+0.001
ercise+0.000
elling+0.000
weet+0.000
ully+0.000
Neg logit contributions
 Fl-0.000
 Sn-0.000
 Ell-0.000
 Jenkins-0.000
 Lee-0.000
Token her
Token ID607
Feature activation+1.96e+00

Pos logit contributions
 Fl+0.007
 Sn+0.007
 Jenkins+0.006
 Mil+0.006
 Ell+0.006
Neg logit contributions
isdom-0.011
ercise-0.010
elling-0.010
weet-0.010
ully-0.009
Token mom
Token ID1995
Feature activation-1.85e+00

Pos logit contributions
 Sn+0.040
 Fl+0.037
 plun+0.034
 Jenkins+0.034
 Mil+0.034
Neg logit contributions
isdom-0.060
iper-0.053
ully-0.052
weet-0.051
night-0.051
Tokenmy
Token ID1820
Feature activation-1.92e+00

Pos logit contributions
isdom+0.049
ercise+0.047
elling+0.045
weet+0.044
ully+0.043
Neg logit contributions
 Fl-0.049
 Sn-0.046
 Ell-0.045
 Mil-0.044
 Jenkins-0.044
Token said
Token ID531
Feature activation+1.53e+00

Pos logit contributions
isdom+0.052
ercise+0.048
elling+0.047
weet+0.046
ully+0.044
Neg logit contributions
 Fl-0.050
 Sn-0.048
 Ell-0.046
 Mil-0.045
 Lee-0.045
Token.
Token ID13
Feature activation+3.09e-01

Pos logit contributions
isdom+0.049
ercise+0.046
elling+0.046
weet+0.045
ully+0.044
Neg logit contributions
 Fl-0.027
 Sn-0.025
 Ell-0.023
 Mil-0.023
 Jenkins-0.023
Token He
Token ID679
Feature activation+1.11e+00

Pos logit contributions
 Fl+0.007
 Sn+0.006
 Ell+0.006
 Mil+0.006
 Jenkins+0.006
Neg logit contributions
isdom-0.010
ercise-0.009
elling-0.009
weet-0.009
ully-0.008
Token set
Token ID900
Feature activation-2.41e+00

Pos logit contributions
 Sn+0.027
 Fl+0.027
 Jenkins+0.026
 Lee+0.025
 Ell+0.024
Neg logit contributions
isdom-0.030
ercise-0.029
elling-0.026
ully-0.026
weet-0.026
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
isdom+0.060
ercise+0.057
elling+0.055
weet+0.054
ully+0.052
Neg logit contributions
 Fl-0.064
 Sn-0.063
 Jenkins-0.060
 Ell-0.059
 Mil-0.058
Token fan
Token ID4336
Feature activation-8.62e-01

Pos logit contributions
 Fl+0.003
 Sn+0.003
 Mil+0.003
 Flor+0.003
 Jenkins+0.003
Neg logit contributions
ercise-0.005
ock-0.004
elling-0.004
isdom-0.004
off-0.004
Token on
Token ID319
Feature activation+1.32e+00

Pos logit contributions
isdom+0.026
ercise+0.024
elling+0.024
weet+0.023
ully+0.023
Neg logit contributions
 Fl-0.020
 Sn-0.019
 Ell-0.017
 Mil-0.017
 Jenkins-0.017
Token high
Token ID1029
Feature activation+2.53e-01

Pos logit contributions
 Sn+0.030
 Fl+0.030
 Ell+0.028
 Jenkins+0.027
 Mil+0.027
Neg logit contributions
isdom-0.037
weet-0.034
ercise-0.033
ully-0.033
elling-0.032
Token and
Token ID290
Feature activation-2.99e+00

Pos logit contributions
 Fl+0.005
 Sn+0.005
 Ell+0.004
 Mil+0.004
 Jenkins+0.004
Neg logit contributions
isdom-0.009
ercise-0.008
weet-0.008
elling-0.008
ully-0.008
Token ran
Token ID4966
Feature activation-1.21e+00

Pos logit contributions
ercise+0.084
isdom+0.082
weet+0.076
night+0.074
elling+0.074
Neg logit contributions
 Jenkins-0.066
 Sn-0.066
 Fl-0.065
 Lee-0.061
 Ell-0.060
Token to
Token ID284
Feature activation+1.27e+00

Pos logit contributions
ercise+0.020
ly+0.020
ear+0.019
away+0.019
night+0.019
Neg logit contributions
 Sn-0.037
 Fl-0.036
 Mil-0.036
 Jenkins-0.035
 Mir-0.035
Token the
Token ID262
Feature activation+3.31e-01

Pos logit contributions
 Sn+0.031
 Fl+0.030
 Jenkins+0.030
 Lee+0.028
 Ell+0.027
Neg logit contributions
isdom-0.033
weet-0.031
ercise-0.031
off-0.029
ear-0.028
Token a
Token ID257
Feature activation-1.85e+00

Pos logit contributions
isdom+0.021
ercise+0.020
elling+0.019
weet+0.019
ully+0.018
Neg logit contributions
 Fl-0.017
 Sn-0.016
 Ell-0.015
 Mil-0.015
 Jenkins-0.015
Token new
Token ID649
Feature activation-2.01e+00

Pos logit contributions
isdom+0.051
elling+0.047
ercise+0.047
weet+0.045
ully+0.044
Neg logit contributions
 Fl-0.047
 Sn-0.045
 Ell-0.043
 Jenkins-0.042
 Mil-0.042
Token word
Token ID1573
Feature activation-2.93e-01

Pos logit contributions
isdom+0.056
ercise+0.051
elling+0.049
weet+0.049
ully+0.047
Neg logit contributions
 Fl-0.051
 Sn-0.049
 Mil-0.046
 Ell-0.046
 Jenkins-0.045
Token:
Token ID25
Feature activation+2.20e+00

Pos logit contributions
isdom+0.009
ercise+0.008
elling+0.008
weet+0.008
ully+0.008
Neg logit contributions
 Fl-0.006
 Sn-0.006
 Mil-0.006
 Ell-0.006
 Jenkins-0.006
Token Subway
Token ID38923
Feature activation-6.12e-01

Pos logit contributions
 Fl+0.042
 Sn+0.039
 Ell+0.036
 Mil+0.036
 Lee+0.035
Neg logit contributions
isdom-0.074
ercise-0.070
elling-0.070
weet-0.068
ully-0.066
Token.
Token ID13
Feature activation-5.59e-01

Pos logit contributions
isdom+0.018
ercise+0.017
elling+0.016
weet+0.016
off+0.016
Neg logit contributions
 Fl-0.014
 Sn-0.014
 Mil-0.013
 Jenkins-0.013
 Ell-0.013
Token Sam
Token ID3409
Feature activation-3.72e-01

Pos logit contributions
isdom+0.019
ercise+0.017
elling+0.017
weet+0.017
off+0.017
Neg logit contributions
 Fl-0.011
 Sn-0.010
 Mil-0.010
 Lee-0.010
 Jenkins-0.010
Token had
Token ID550
Feature activation-1.87e-01

Pos logit contributions
isdom+0.013
ercise+0.012
elling+0.012
weet+0.012
off+0.012
Neg logit contributions
 Fl-0.006
 Sn-0.006
 Mil-0.006
 Jenkins-0.006
 Lee-0.005
Token never
Token ID1239
Feature activation-2.91e+00

Pos logit contributions
isdom+0.006
elling+0.006
ercise+0.006
weet+0.005
night+0.005
Neg logit contributions
 Fl-0.004
 Sn-0.003
 Ell-0.003
 Mil-0.003
 Lee-0.003
Token heard
Token ID2982
Feature activation-7.38e-01

Pos logit contributions
isdom+0.093
elling+0.090
ercise+0.089
iper+0.084
ww+0.083
Neg logit contributions
 Fl-0.054
 holding-0.049
 Ell-0.048
 Sn-0.048
 t-0.048
Token of
Token ID286
Feature activation+1.44e+00

Pos logit contributions
isdom+0.020
ercise+0.019
elling+0.018
weet+0.018
ully+0.017
Neg logit contributions
 Fl-0.019
 Sn-0.018
 Ell-0.017
 Mil-0.017
 Jenkins-0.017
Token his
Token ID465
Feature activation+3.10e-01

Pos logit contributions
isdom+0.005
ercise+0.005
weet+0.005
elling+0.005
ully+0.004
Neg logit contributions
 Fl-0.005
 Sn-0.005
 Jenkins-0.005
 Mil-0.005
 Lee-0.005
Token toy
Token ID13373
Feature activation-2.53e-01

Pos logit contributions
 Fl+0.006
 Sn+0.006
 Mil+0.006
 Ell+0.006
 Jenkins+0.006
Neg logit contributions
isdom-0.009
ercise-0.009
elling-0.009
weet-0.009
ully-0.008
Token cars
Token ID5006
Feature activation-9.95e-01

Pos logit contributions
isdom+0.008
ercise+0.008
elling+0.007
weet+0.007
ully+0.007
Neg logit contributions
 Fl-0.005
 Sn-0.005
 Mil-0.005
 Ell-0.005
 Jenkins-0.004
Token.
Token ID13
Feature activation-8.56e-01

Pos logit contributions
isdom+0.032
ercise+0.030
elling+0.030
weet+0.029
ully+0.028
Neg logit contributions
 Fl-0.021
 Sn-0.020
 Ell-0.018
 Mil-0.018
 Jenkins-0.018
Token His
Token ID2399
Feature activation+7.76e-01

Pos logit contributions
isdom+0.022
ercise+0.020
elling+0.020
weet+0.019
iveness+0.018
Neg logit contributions
 Fl-0.021
 Sn-0.021
 Mil-0.020
 Jenkins-0.020
 Flor-0.019
Token dad
Token ID9955
Feature activation-2.31e+00

Pos logit contributions
 Fl+0.019
 Sn+0.019
 Mil+0.018
 Jenkins+0.018
 Ell+0.017
Neg logit contributions
isdom-0.020
ercise-0.020
elling-0.019
ully-0.018
night-0.018
Token took
Token ID1718
Feature activation-2.81e+00

Pos logit contributions
isdom+0.074
ercise+0.069
elling+0.066
weet+0.066
ully+0.065
Neg logit contributions
 Fl-0.047
 Sn-0.046
 Mil-0.043
 Jenkins-0.043
 Ell-0.040
Token out
Token ID503
Feature activation+2.56e+00

Pos logit contributions
isdom+0.080
ercise+0.073
elling+0.072
weet+0.071
ully+0.069
Neg logit contributions
 Fl-0.071
 Sn-0.068
 Ell-0.065
 Mil-0.062
 Lee-0.061
Token a
Token ID257
Feature activation-1.73e+00

Pos logit contributions
 Fl+0.046
 Sn+0.043
 Ell+0.040
 Mil+0.039
 Lee+0.038
Neg logit contributions
isdom-0.090
ercise-0.085
elling-0.084
weet-0.083
ully-0.080
Token big
Token ID1263
Feature activation-1.77e+00

Pos logit contributions
isdom+0.052
ercise+0.050
weet+0.048
elling+0.048
off+0.046
Neg logit contributions
 Fl-0.037
 Sn-0.036
 Mil-0.034
 Ell-0.033
 Jenkins-0.033
Token box
Token ID3091
Feature activation+1.33e+00

Pos logit contributions
isdom+0.060
ercise+0.057
elling+0.055
weet+0.055
ully+0.053
Neg logit contributions
 Fl-0.033
 Sn-0.032
 Mil-0.029
 Ell-0.029
 Jenkins-0.028
Token
Token ID198
Feature activation-1.26e+00

Pos logit contributions
isdom+0.032
ercise+0.030
weet+0.030
elling+0.030
off+0.029
Neg logit contributions
 Fl-0.017
 Sn-0.016
 Ell-0.014
 Jenkins-0.014
 Mil-0.014
TokenThe
Token ID464
Feature activation+4.34e-01

Pos logit contributions
isdom+0.033
elling+0.030
ercise+0.030
weet+0.029
ully+0.028
Neg logit contributions
 Fl-0.034
 Sn-0.033
 Mil-0.031
 Ell-0.031
 Jenkins-0.031
Token raven
Token ID37735
Feature activation-1.24e+00

Pos logit contributions
 Fl+0.011
 Sn+0.011
 Mil+0.010
 Ell+0.010
 Jenkins+0.010
Neg logit contributions
isdom-0.012
ercise-0.011
elling-0.011
weet-0.011
off-0.010
Token flew
Token ID13112
Feature activation-1.98e+00

Pos logit contributions
isdom+0.042
ercise+0.040
elling+0.039
weet+0.039
ully+0.037
Neg logit contributions
 Fl-0.024
 Sn-0.022
 Ell-0.021
 Mil-0.020
 Jenkins-0.019
Token away
Token ID1497
Feature activation+2.95e+00

Pos logit contributions
isdom+0.052
ercise+0.048
elling+0.047
weet+0.046
ully+0.044
Neg logit contributions
 Fl-0.053
 Sn-0.051
 Ell-0.048
 Mil-0.048
 Jenkins-0.048
Token and
Token ID290
Feature activation-3.14e+00

Pos logit contributions
 Sn+0.074
 Fl+0.073
 Lee+0.069
 Mil+0.069
 Jenkins+0.068
Neg logit contributions
isdom-0.074
weet-0.067
night-0.065
ercise-0.065
elling-0.064
Token Tim
Token ID5045
Feature activation-1.37e+00

Pos logit contributions
isdom+0.090
ercise+0.086
weet+0.083
elling+0.082
night+0.081
Neg logit contributions
 Sn-0.067
 Fl-0.066
 Jenkins-0.065
 Lee-0.063
 Mil-0.062
Token kept
Token ID4030
Feature activation-1.22e+00

Pos logit contributions
isdom+0.040
ercise+0.037
weet+0.037
elling+0.036
ully+0.036
Neg logit contributions
 Fl-0.030
 Sn-0.029
 Mil-0.028
 Jenkins-0.028
 Ell-0.027
Token marching
Token ID26409
Feature activation-1.32e+00

Pos logit contributions
isdom+0.040
ercise+0.037
elling+0.037
weet+0.036
ully+0.035
Neg logit contributions
 Fl-0.026
 Sn-0.025
 Ell-0.023
 Mil-0.022
 Jenkins-0.022
Token until
Token ID1566
Feature activation+2.26e-01

Pos logit contributions
isdom+0.036
ercise+0.034
elling+0.033
weet+0.033
ock+0.033
Neg logit contributions
 Fl-0.032
 Sn-0.030
 Mil-0.029
 Jenkins-0.029
 Lee-0.028
Token he
Token ID339
Feature activation+8.67e-03

Pos logit contributions
 Fl+0.005
 Sn+0.005
 Jenkins+0.005
 Mil+0.005
 Lee+0.005
Neg logit contributions
isdom-0.006
ercise-0.006
weet-0.005
elling-0.005
night-0.005
Token more
Token ID517
Feature activation+1.61e+00

Pos logit contributions
 Fl+0.012
 Sn+0.012
 Ell+0.011
 Mil+0.011
 Jenkins+0.011
Neg logit contributions
isdom-0.014
ercise-0.013
elling-0.013
weet-0.013
ully-0.012
Token important
Token ID1593
Feature activation-1.52e+00

Pos logit contributions
 Fl+0.040
 Ell+0.035
 t+0.035
 holding+0.035
 hiding+0.035
Neg logit contributions
isdom-0.041
elling-0.040
ercise-0.038
weet-0.038
bye-0.037
Token to
Token ID284
Feature activation+8.36e-01

Pos logit contributions
isdom+0.039
ercise+0.036
elling+0.035
weet+0.035
ully+0.033
Neg logit contributions
 Fl-0.041
 Sn-0.040
 Ell-0.038
 Mil-0.038
 Jenkins-0.037
Token be
Token ID307
Feature activation-1.06e+00

Pos logit contributions
 Fl+0.019
 Sn+0.019
 Ell+0.017
 Mil+0.017
 Jenkins+0.017
Neg logit contributions
isdom-0.025
ercise-0.023
elling-0.023
weet-0.022
ully-0.022
Token kind
Token ID1611
Feature activation-2.20e+00

Pos logit contributions
isdom+0.030
ercise+0.028
elling+0.026
weet+0.026
off+0.025
Neg logit contributions
 Fl-0.026
 Sn-0.026
 Jenkins-0.025
 Mil-0.024
 Lee-0.024
Token and
Token ID290
Feature activation-2.74e+00

Pos logit contributions
isdom+0.059
ercise+0.055
elling+0.054
weet+0.053
ully+0.051
Neg logit contributions
 Fl-0.057
 Sn-0.055
 Ell-0.052
 Mil-0.052
 Jenkins-0.051
Token help
Token ID1037
Feature activation-1.52e+00

Pos logit contributions
isdom+0.083
elling+0.078
ercise+0.076
weet+0.075
ully+0.074
Neg logit contributions
 Fl-0.062
 Sn-0.058
 Ell-0.055
 Mil-0.053
 Jenkins-0.051
Token others
Token ID1854
Feature activation-1.52e+00

Pos logit contributions
isdom+0.044
ercise+0.041
elling+0.040
weet+0.040
ully+0.038
Neg logit contributions
 Fl-0.037
 Sn-0.035
 Ell-0.033
 Mil-0.033
 Jenkins-0.032
Token.
Token ID13
Feature activation-1.60e+00

Pos logit contributions
isdom+0.045
ercise+0.041
elling+0.040
weet+0.040
off+0.039
Neg logit contributions
 Fl-0.035
 Sn-0.034
 Mil-0.032
 Jenkins-0.032
 Ell-0.031
Token Benny
Token ID44275
Feature activation-1.73e+00

Pos logit contributions
isdom+0.049
ercise+0.047
elling+0.045
weet+0.044
ully+0.043
Neg logit contributions
 Fl-0.038
 Sn-0.036
 Ell-0.033
 Mil-0.031
 Jenkins-0.031
Token and
Token ID290
Feature activation-2.46e+00

Pos logit contributions
isdom+0.056
ercise+0.052
elling+0.051
weet+0.050
ully+0.049
Neg logit contributions
 Fl-0.036
 Sn-0.034
 Ell-0.032
 Mil-0.032
 Jenkins-0.031
Token couldn
Token ID3521
Feature activation-2.81e+00

Pos logit contributions
isdom+0.060
ercise+0.056
weet+0.055
elling+0.053
ully+0.053
Neg logit contributions
 Sn-0.051
 Fl-0.051
 Jenkins-0.048
 Mil-0.047
 Ell-0.046
Token't
Token ID470
Feature activation-2.61e+00

Pos logit contributions
isdom+0.085
ercise+0.079
elling+0.078
weet+0.077
ully+0.074
Neg logit contributions
 Fl-0.062
 Sn-0.060
 Mil-0.056
 Ell-0.056
 Jenkins-0.055
Token find
Token ID1064
Feature activation-2.43e-01

Pos logit contributions
isdom+0.083
ercise+0.078
weet+0.076
elling+0.076
ully+0.074
Neg logit contributions
 Fl-0.054
 Sn-0.052
 Jenkins-0.048
 Mil-0.048
 Ell-0.047
Token it
Token ID340
Feature activation-1.96e-01

Pos logit contributions
isdom+0.007
ercise+0.007
elling+0.007
weet+0.007
ully+0.006
Neg logit contributions
 Fl-0.006
 Sn-0.005
 Ell-0.005
 Mil-0.005
 Jenkins-0.005
Token anywhere
Token ID6609
Feature activation+5.45e-01

Pos logit contributions
isdom+0.006
ercise+0.006
elling+0.006
weet+0.006
ully+0.006
Neg logit contributions
 Fl-0.004
 Sn-0.004
 Mil-0.004
 Jenkins-0.003
 Ell-0.003
Token.
Token ID13
Feature activation-9.83e-01

Pos logit contributions
 Sn+0.014
 Mil+0.014
 Lee+0.013
 Fl+0.013
 Mir+0.013
Neg logit contributions
isdom-0.013
weet-0.012
off-0.012
night-0.012
ercise-0.012
Token She
Token ID1375
Feature activation+5.59e-01

Pos logit contributions
isdom+0.027
ercise+0.025
elling+0.025
weet+0.024
off+0.024
Neg logit contributions
 Sn-0.022
 Fl-0.021
 Mil-0.020
 Frost-0.020
 Jenkins-0.020
Token looked
Token ID3114
Feature activation+1.09e+00

Pos logit contributions
 Fl+0.011
 Sn+0.011
 Jenkins+0.011
 Lee+0.011
 Mil+0.011
Neg logit contributions
isdom-0.017
ercise-0.016
night-0.015
elling-0.015
ully-0.015
Token under
Token ID739
Feature activation+2.24e+00

Pos logit contributions
 Fl+0.023
 Sn+0.022
 Ell+0.020
 Mil+0.020
 Jenkins+0.020
Neg logit contributions
isdom-0.035
ercise-0.033
elling-0.032
weet-0.032
ully-0.030
Token the
Token ID262
Feature activation-2.86e-01

Pos logit contributions
 Sn+0.054
 Fl+0.053
 Mil+0.049
 Jenkins+0.049
 Ell+0.048
Neg logit contributions
isdom-0.062
ercise-0.056
elling-0.056
weet-0.056
ully-0.054
Token bed
Token ID3996
Feature activation+2.99e+00

Pos logit contributions
isdom+0.010
ercise+0.009
elling+0.009
weet+0.009
ully+0.009
Neg logit contributions
 Fl-0.005
 Sn-0.005
 Mil-0.005
 Ell-0.005
 Jenkins-0.004
Token They
Token ID1119
Feature activation-2.89e-01

Pos logit contributions
isdom+0.030
ercise+0.028
elling+0.028
weet+0.027
off+0.026
Neg logit contributions
 Fl-0.026
 Sn-0.025
 Mil-0.024
 Jenkins-0.024
 Ell-0.023
Token played
Token ID2826
Feature activation-2.02e+00

Pos logit contributions
isdom+0.008
ercise+0.008
weet+0.007
ully+0.007
elling+0.007
Neg logit contributions
 Fl-0.007
 Sn-0.007
 Jenkins-0.007
 Mil-0.007
 Lee-0.006
Token together
Token ID1978
Feature activation-1.97e+00

Pos logit contributions
isdom+0.051
ercise+0.049
weet+0.045
 melodies+0.044
ear+0.044
Neg logit contributions
 Sn-0.051
 Fl-0.051
 Jenkins-0.049
 Mil-0.048
 Ell-0.047
Token and
Token ID290
Feature activation-3.83e+00

Pos logit contributions
isdom+0.051
ercise+0.047
weet+0.045
elling+0.045
off+0.043
Neg logit contributions
 Fl-0.052
 Sn-0.051
 Jenkins-0.048
 Mil-0.048
 Ell-0.048
Token did
Token ID750
Feature activation-2.49e+00

Pos logit contributions
isdom+0.114
ercise+0.109
weet+0.108
bye+0.100
night+0.100
Neg logit contributions
 Sn-0.080
 Fl-0.080
 Jenkins-0.075
 Mil-0.073
 plun-0.073
Token lots
Token ID6041
Feature activation-4.19e+00

Pos logit contributions
isdom+0.070
ercise+0.064
weet+0.062
elling+0.059
off+0.058
Neg logit contributions
 Sn-0.059
 Fl-0.059
 Jenkins-0.056
 Mil-0.054
 Lee-0.054
Token of
Token ID286
Feature activation-1.42e-01

Pos logit contributions
isdom+0.103
ercise+0.097
elling+0.091
ully+0.088
weet+0.086
Neg logit contributions
 Fl-0.124
 Sn-0.117
 Ell-0.113
 Mil-0.109
 Jenkins-0.107
Token fun
Token ID1257
Feature activation-3.10e+00

Pos logit contributions
isdom+0.003
ercise+0.003
 melodies+0.003
weet+0.003
ock+0.003
Neg logit contributions
 Sn-0.004
 Fl-0.004
 Mil-0.004
 Jenkins-0.004
 Lee-0.004
Token things
Token ID1243
Feature activation-5.73e-01

Pos logit contributions
isdom+0.092
ercise+0.086
elling+0.084
weet+0.083
off+0.080
Neg logit contributions
 Fl-0.072
 Sn-0.069
 Ell-0.064
 Mil-0.064
 Jenkins-0.064
Token.
Token ID13
Feature activation-1.20e+00

Pos logit contributions
isdom+0.017
ercise+0.016
weet+0.016
elling+0.016
off+0.015
Neg logit contributions
 Fl-0.013
 Sn-0.012
 Mil-0.011
 Jenkins-0.011
 Ell-0.011
Token Every
Token ID3887
Feature activation-3.28e+00

Pos logit contributions
isdom+0.030
ercise+0.028
elling+0.027
weet+0.026
off+0.025
Neg logit contributions
 Fl-0.033
 Sn-0.032
 Mil-0.030
 Jenkins-0.030
 Ell-0.030
Tokenmy
Token ID1820
Feature activation-1.24e+00

Pos logit contributions
isdom+0.014
ercise+0.013
elling+0.013
weet+0.013
off+0.012
Neg logit contributions
 Fl-0.015
 Sn-0.014
 Jenkins-0.013
 Ell-0.013
 Mil-0.013
Token was
Token ID373
Feature activation+1.05e+00

Pos logit contributions
isdom+0.048
ercise+0.046
elling+0.045
weet+0.044
ully+0.043
Neg logit contributions
 Fl-0.017
 Sn-0.017
 Jenkins-0.014
 Mil-0.014
 Ell-0.014
Token so
Token ID523
Feature activation-1.01e+00

Pos logit contributions
 Sn+0.029
 Fl+0.029
 Jenkins+0.028
 Lee+0.028
 plun+0.028
Neg logit contributions
weet-0.021
isdom-0.021
elling-0.018
ercise-0.018
ully-0.018
Token happy
Token ID3772
Feature activation-4.51e+00

Pos logit contributions
isdom+0.029
weet+0.027
ercise+0.027
elling+0.027
bye+0.026
Neg logit contributions
 Sn-0.023
 Fl-0.023
 Jenkins-0.021
 Lee-0.021
 Ell-0.020
Token and
Token ID290
Feature activation-4.36e+00

Pos logit contributions
isdom+0.131
ercise+0.123
elling+0.121
weet+0.117
ully+0.113
Neg logit contributions
 Fl-0.111
 Sn-0.104
 Ell-0.099
 Mil-0.098
 Jenkins-0.097
Token excited
Token ID6568
Feature activation-4.35e+00

Pos logit contributions
isdom+0.149
elling+0.140
ercise+0.138
weet+0.134
ock+0.134
Neg logit contributions
 Fl-0.088
 Sn-0.081
 Ell-0.077
 Mil-0.075
 L-0.070
Token to
Token ID284
Feature activation-7.40e-02

Pos logit contributions
isdom+0.151
ercise+0.144
elling+0.141
weet+0.138
iper+0.134
Neg logit contributions
 Fl-0.083
 Ell-0.075
 Sn-0.072
 Jenkins-0.070
 Lee-0.070
Token play
Token ID711
Feature activation-1.20e+00

Pos logit contributions
elling+0.003
isdom+0.003
ercise+0.003
heart+0.003
ww+0.003
Neg logit contributions
 t-0.001
 Fl-0.001
 Ell-0.001
 L-0.001
 Mil-0.001
Token with
Token ID351
Feature activation-1.16e-01

Pos logit contributions
isdom+0.038
ercise+0.036
elling+0.035
weet+0.034
off+0.034
Neg logit contributions
 Fl-0.025
 Sn-0.024
 Mil-0.022
 Jenkins-0.022
 Ell-0.022
Token it
Token ID340
Feature activation-2.63e-01

Pos logit contributions
isdom+0.003
ercise+0.003
elling+0.003
weet+0.003
ully+0.003
Neg logit contributions
 Fl-0.003
 Sn-0.003
 Jenkins-0.003
 Mil-0.003
 Ell-0.003
Token.
Token ID13
Feature activation-1.69e+00

Pos logit contributions
isdom+0.009
ercise+0.009
elling+0.009
weet+0.008
ully+0.008
Neg logit contributions
 Fl-0.005
 Sn-0.005
 Ell-0.004
 Mil-0.004
 Jenkins-0.004
Token said
Token ID531
Feature activation+1.67e+00

Pos logit contributions
isdom+0.043
ercise+0.038
elling+0.037
weet+0.036
ully+0.035
Neg logit contributions
 Fl-0.060
 Sn-0.059
 Mil-0.055
 Jenkins-0.055
 Ell-0.055
Token,
Token ID11
Feature activation+3.97e+00

Pos logit contributions
 Sn+0.041
 Fl+0.040
 Mil+0.039
 Jenkins+0.038
 Mir+0.037
Neg logit contributions
isdom-0.046
ercise-0.041
night-0.040
elling-0.039
ly-0.038
Token '
Token ID705
Feature activation+3.09e+00

Pos logit contributions
 Fl+0.054
 Sn+0.053
 Mil+0.051
 Jenkins+0.047
 Megan+0.044
Neg logit contributions
isdom-0.148
ercise-0.137
weet-0.134
elling-0.133
iveness-0.130
TokenI
Token ID40
Feature activation+1.36e+00

Pos logit contributions
 Fl+0.064
 Sn+0.061
 Ell+0.057
 Jenkins+0.056
 Mil+0.056
Neg logit contributions
isdom-0.098
ercise-0.093
elling-0.090
weet-0.089
off-0.087
Token don
Token ID836
Feature activation-1.25e+00

Pos logit contributions
 Fl+0.023
 Sn+0.023
 Mil+0.021
 Jenkins+0.020
 Lee+0.020
Neg logit contributions
isdom-0.048
ercise-0.045
elling-0.044
weet-0.043
off-0.043
Tokenâ
Token ID22940
Feature activation-4.51e+00

Pos logit contributions
isdom+0.046
ercise+0.044
elling+0.043
weet+0.043
night+0.042
Neg logit contributions
 Sn-0.019
 Fl-0.019
 Ell-0.016
 Jenkins-0.015
 Lee-0.015
Token
Token ID26391
Feature activation-7.46e-01

Pos logit contributions
isdom+0.110
elling+0.101
weet+0.101
ercise+0.097
iper+0.092
Neg logit contributions
 Fl-0.109
 Sn-0.109
 Lee-0.102
 Mil-0.102
 Me-0.101
Token
Token ID8151
Feature activation-1.92e+00

Pos logit contributions
isdom+0.022
ercise+0.020
bye+0.019
off+0.019
weet+0.019
Neg logit contributions
 Fl-0.017
 Sn-0.016
 Ell-0.016
 Mil-0.016
 Flor-0.015
Tokent
Token ID83
Feature activation-1.44e+00

Pos logit contributions
isdom+0.047
ercise+0.043
elling+0.042
weet+0.042
ully+0.040
Neg logit contributions
 Fl-0.053
 Sn-0.051
 Mil-0.049
 Ell-0.048
 Mir-0.047
Token know
Token ID760
Feature activation+8.94e-02

Pos logit contributions
isdom+0.039
ercise+0.037
elling+0.037
ully+0.034
weet+0.034
Neg logit contributions
 Fl-0.037
 Sn-0.034
 Ell-0.033
 Jenkins-0.032
 Lee-0.031
Token the
Token ID262
Feature activation+8.07e-01

Pos logit contributions
 Fl+0.002
 Sn+0.002
 Jenkins+0.002
 Mil+0.002
 Ell+0.002
Neg logit contributions
isdom-0.003
ercise-0.002
elling-0.002
weet-0.002
off-0.002
Token and
Token ID290
Feature activation-3.09e+00

Pos logit contributions
isdom+0.074
ercise+0.069
elling+0.067
weet+0.067
ully+0.064
Neg logit contributions
 Fl-0.065
 Sn-0.062
 Jenkins-0.058
 Mil-0.058
 Ell-0.058
Token couldn
Token ID3521
Feature activation-3.11e+00

Pos logit contributions
isdom+0.094
elling+0.087
ercise+0.086
weet+0.083
ully+0.082
Neg logit contributions
 Fl-0.072
 Sn-0.068
 Ell-0.065
 Mil-0.063
 Jenkins-0.061
Token't
Token ID470
Feature activation-2.75e+00

Pos logit contributions
isdom+0.095
ercise+0.089
elling+0.087
weet+0.086
ully+0.083
Neg logit contributions
 Fl-0.069
 Sn-0.066
 Ell-0.061
 Mil-0.061
 Jenkins-0.061
Token wait
Token ID4043
Feature activation+5.27e-01

Pos logit contributions
isdom+0.074
ercise+0.068
elling+0.067
weet+0.065
ully+0.063
Neg logit contributions
 Fl-0.072
 Sn-0.070
 Ell-0.066
 Mil-0.065
 Jenkins-0.065
Token to
Token ID284
Feature activation+4.67e-01

Pos logit contributions
 Fl+0.013
 Sn+0.012
 Ell+0.012
 Mil+0.012
 Jenkins+0.011
Neg logit contributions
isdom-0.015
elling-0.014
ercise-0.014
weet-0.014
ully-0.014
Token show
Token ID905
Feature activation-4.42e+00

Pos logit contributions
 Fl+0.011
 Sn+0.010
 Ell+0.010
 Mil+0.010
 t+0.009
Neg logit contributions
isdom-0.014
elling-0.014
ercise-0.013
ully-0.012
weet-0.012
Token off
Token ID572
Feature activation+1.11e+00

Pos logit contributions
isdom+0.132
ercise+0.124
elling+0.123
weet+0.121
ully+0.117
Neg logit contributions
 Fl-0.105
 Sn-0.098
 Ell-0.096
 Mil-0.092
 Flor-0.089
Token her
Token ID607
Feature activation+3.16e-01

Pos logit contributions
 Fl+0.026
 Sn+0.025
 Ell+0.023
 Mil+0.023
 Jenkins+0.023
Neg logit contributions
isdom-0.033
ercise-0.030
elling-0.030
weet-0.029
ully-0.028
Token new
Token ID649
Feature activation-1.34e+00

Pos logit contributions
 Fl+0.008
 Sn+0.007
 Jenkins+0.007
 Mil+0.007
 Lee+0.007
Neg logit contributions
isdom-0.009
ercise-0.008
elling-0.008
weet-0.008
off-0.008
Token dress
Token ID6576
Feature activation-1.96e+00

Pos logit contributions
isdom+0.040
ercise+0.037
weet+0.035
elling+0.035
off+0.035
Neg logit contributions
 Fl-0.031
 Sn-0.030
 Jenkins-0.027
 Mil-0.027
 Ell-0.027
Token.
Token ID13
Feature activation-1.60e+00

Pos logit contributions
isdom+0.068
ercise+0.064
elling+0.063
weet+0.062
ully+0.059
Neg logit contributions
 Fl-0.037
 Sn-0.035
 Ell-0.033
 Mil-0.032
 Jenkins-0.031
Token park
Token ID3952
Feature activation+8.09e-01

Pos logit contributions
isdom+0.012
ercise+0.011
elling+0.011
weet+0.011
ully+0.010
Neg logit contributions
 Fl-0.008
 Sn-0.007
 Ell-0.007
 Mil-0.007
 Jenkins-0.007
Token.
Token ID13
Feature activation-9.24e-01

Pos logit contributions
 Fl+0.018
 Sn+0.018
 Mil+0.016
 Ell+0.016
 Jenkins+0.016
Neg logit contributions
isdom-0.024
ercise-0.023
elling-0.022
weet-0.022
off-0.021
Token Lily
Token ID20037
Feature activation-5.87e-02

Pos logit contributions
isdom+0.031
ercise+0.030
elling+0.029
weet+0.029
night+0.028
Neg logit contributions
 Fl-0.015
 Sn-0.014
 Mil-0.014
 Jenkins-0.013
 Lee-0.013
Token was
Token ID373
Feature activation+9.95e-01

Pos logit contributions
isdom+0.002
ercise+0.002
off+0.002
weet+0.002
iper+0.002
Neg logit contributions
 Fl-0.001
 Sn-0.001
 Mil-0.001
 Jenkins-0.001
 Lee-0.001
Token so
Token ID523
Feature activation-8.39e-01

Pos logit contributions
 Jenkins+0.025
 Sn+0.024
 Fl+0.024
 Mil+0.024
 plun+0.024
Neg logit contributions
weet-0.021
isdom-0.021
ercise-0.019
elling-0.019
ocked-0.018
Token excited
Token ID6568
Feature activation-4.88e+00

Pos logit contributions
isdom+0.025
weet+0.024
ercise+0.024
elling+0.023
off+0.023
Neg logit contributions
 Fl-0.018
 Sn-0.018
 Jenkins-0.017
 Lee-0.016
 Mil-0.016
Token because
Token ID780
Feature activation-1.47e+00

Pos logit contributions
isdom+0.173
ercise+0.172
elling+0.163
leness+0.155
reci+0.155
Neg logit contributions
 Fl-0.089
 Ell-0.081
 L-0.075
 Lee-0.075
 Jenkins-0.073
Token she
Token ID673
Feature activation+2.18e-01

Pos logit contributions
isdom+0.052
ercise+0.048
elling+0.047
weet+0.046
ully+0.046
Neg logit contributions
 Fl-0.029
 Sn-0.027
 Ell-0.025
 Mil-0.024
 Jenkins-0.023
Token loved
Token ID6151
Feature activation-2.22e+00

Pos logit contributions
 Fl+0.005
 Sn+0.005
 Lee+0.005
 Jenkins+0.004
 Mil+0.004
Neg logit contributions
isdom-0.006
ercise-0.006
weet-0.006
night-0.006
off-0.006
Token going
Token ID1016
Feature activation-1.52e+00

Pos logit contributions
isdom+0.068
elling+0.063
ercise+0.063
weet+0.060
ully+0.059
Neg logit contributions
 Fl-0.051
 Sn-0.049
 Ell-0.045
 Mil-0.045
 Lee-0.044
Token down
Token ID866
Feature activation+1.37e+00

Pos logit contributions
isdom+0.053
elling+0.048
ercise+0.047
weet+0.047
iper+0.045
Neg logit contributions
 Fl-0.030
 Sn-0.030
 Lee-0.027
 Ell-0.027
 Jenkins-0.026