TOP ACTIVATIONS
MAX = 16.095

. The toy was a laser . Tim liked the laser
had given her special cool gears which made it easier for
strange . It was a mask ! It was lying on
saw a man selling colorful fireworks . She asked her mom
day , she found a mask on the floor . The
my . Tim my loved vehicles , especially cars . One
, they saw a big motorcycle parked on the street .
's mom bought her a candle for her birthday . It
named Tim found a shiny trophy in the forest . He
to play with his toy cars . One day , he
named Tim found a toy motorcycle . It was red and
excited to get a sc ooter . She wanted to use
her parents gave her a microphone as a gift , and
he found lots of colourful gems ! He was very excited
street . They saw a motorcycle parked on the side of
got a big box of blocks . Mom and Dad decided
They like to play with magnets . Magn ets are things
to play with his toy cars and trucks . One day
sky and saw a shining gem in the clouds . She
They played with their toy cars and dolls . They had

MIN ACTIVATIONS
MIN = -31.131

When Daisy put the magn ifying glass down , the cater
't know the rh in oc eros was wild . Can
am taking the rh in oc eros to a new home
he would take the av oc ados and scatter them around
give to the rh in oc eros . Lily walked to
her mom my watched in amaz ement as the machine flew
it to the rh in oc eros . When he tasted
quiet compared to the noisy se ag ull s outside .
that the bad rh in oc eros was now nice .
you go , my d arl ings . Enjoy your lunch
grass and rye grass and al f alf a and cl
flashlight , and a magn ifying glass . As
go ! Everyone watched in amaz ement as it took off
twenty - eight , twenty - nine , thirty , thirty
them and never threw a tant rum again . <|endoftext|> Once
eddy bear and watched in amaz ement as it shrunk an
She takes out a magn ifying glass . She looks at
air . He watched with amaz ement as the z ig
't touch the rh in oc eros ! It might bite
to eat the y ummy ins ides . From that day

INTERVAL 4.289 - 16.095
CONTAINS 17.081%

!" The person sighed , " Well ,
. The man was spraying water on the flowers . Tim
?" The red rose replied " I 'm bouncing
explored all the slides and swings . Meanwhile Dan grabbed a
l aces and pretty ear rings . She worked very hard

INTERVAL -7.518 - 4.289
CONTAINS 77.789%

play neat games . One day , the
. G lor ia was very sad .
, I have a lime !" Tom said . He took
writing adventures together . <|endoftext|> One day , Little Joe was
A few weeks later , Adam heard about a new doctor

INTERVAL -19.324 - -7.518
CONTAINS 5.122%

was healthy again . So , the little girl and her
was surprised , but asked the old man if he was
with it , but we can learn about it ," she
on it ! J ill quickly glued the
smiled and said , " Yes , it is . Did

INTERVAL -31.131 - -19.324
CONTAINS 0.007%

that the bad rh in oc eros was now nice .
give to the rh in oc eros . Lily walked to
quiet compared to the noisy se ag ull s outside .
he would take the av oc ados and scatter them around
am taking the rh in oc eros to a new home
Token.
Token ID13
Feature activation+5.64e+00

Pos logit contributions
es+0.108
le+0.104
ices+0.096
ymes+0.096
les+0.095
Neg logit contributions
 disl-0.176
 Cr-0.155
 Twe-0.147
 Fro-0.144
 Joey-0.141
Token The
Token ID383
Feature activation+6.91e+00

Pos logit contributions
es+0.079
 on+0.078
 again+0.077
y+0.073
m+0.073
Neg logit contributions
 disl-0.061
 majesty-0.035
 Majesty-0.035
 Cr-0.034
 Fro-0.032
Token toy
Token ID13373
Feature activation+1.20e+01

Pos logit contributions
 on+0.041
es+0.038
 again+0.038
y+0.035
m+0.032
Neg logit contributions
 disl-0.131
 Cr-0.102
 majesty-0.098
 Fro-0.098
 Fre-0.097
Token was
Token ID373
Feature activation+6.75e+00

Pos logit contributions
es+0.103
 again+0.097
le+0.097
m+0.091
ices+0.089
Neg logit contributions
 disl-0.185
 Cr-0.145
 Joey-0.136
 Twe-0.135
 Fro-0.135
Token a
Token ID257
Feature activation+8.62e+00

Pos logit contributions
 on+0.071
es+0.069
 again+0.066
y+0.062
m+0.062
Neg logit contributions
 disl-0.100
 Cr-0.069
 majesty-0.067
 Joey-0.067
 Majesty-0.065
Token laser
Token ID12855
Feature activation+1.61e+01

Pos logit contributions
es+0.097
 again+0.091
 on+0.088
le+0.086
m+0.086
Neg logit contributions
 disl-0.117
 Cr-0.083
 Joey-0.078
 Fro-0.077
 Twe-0.075
Token.
Token ID13
Feature activation+5.99e+00

Pos logit contributions
packs+0.141
ices+0.136
pr+0.132
ymes+0.130
es+0.130
Neg logit contributions
 disl-0.205
 Twe-0.180
 This-0.178
 Cr-0.171
 Fro-0.167
Token Tim
Token ID5045
Feature activation+9.62e+00

Pos logit contributions
es+0.091
 again+0.088
 on+0.088
m+0.085
y+0.083
Neg logit contributions
 disl-0.057
 majesty-0.031
 Cr-0.030
 Majesty-0.030
 Fro-0.029
Token liked
Token ID8288
Feature activation+6.78e+00

Pos logit contributions
es+0.095
 again+0.090
le+0.085
ices+0.083
ing+0.083
Neg logit contributions
 disl-0.141
 Cr-0.103
 Joey-0.097
 Twe-0.097
 Fro-0.096
Token the
Token ID262
Feature activation+7.98e+00

Pos logit contributions
es+0.073
 again+0.070
 on+0.069
y+0.064
m+0.063
Neg logit contributions
 disl-0.095
 Cr-0.068
 Joey-0.064
 majesty-0.063
 Fro-0.063
Token laser
Token ID12855
Feature activation+1.46e+01

Pos logit contributions
es+0.090
 again+0.080
le+0.078
m+0.076
y+0.075
Neg logit contributions
 disl-0.113
 Cr-0.081
 Joey-0.077
 Twe-0.075
 Fro-0.074
Token had
Token ID550
Feature activation+5.73e+00

Pos logit contributions
ymes+0.125
es+0.118
ices+0.117
ities+0.115
packs+0.113
Neg logit contributions
 disl-0.121
 Joey-0.102
 Jon-0.094
 Twe-0.090
 Joe-0.090
Token given
Token ID1813
Feature activation+6.87e+00

Pos logit contributions
 on+0.058
es+0.056
 again+0.055
m+0.050
y+0.048
Neg logit contributions
 disl-0.088
 Cr-0.064
 Joey-0.060
 Fro-0.060
 Madd-0.059
Token her
Token ID607
Feature activation+8.25e+00

Pos logit contributions
 again+0.065
 on+0.064
es+0.064
le+0.057
ing+0.056
Neg logit contributions
 disl-0.109
 majesty-0.078
 Cr-0.077
 Fro-0.075
 Majesty-0.074
Token special
Token ID2041
Feature activation+8.29e+00

Pos logit contributions
es+0.094
 again+0.089
 on+0.086
le+0.084
m+0.084
Neg logit contributions
 disl-0.111
 Cr-0.079
 Joey-0.073
 Fro-0.073
 Twe-0.071
Token cool
Token ID3608
Feature activation+8.49e+00

Pos logit contributions
es+0.080
 again+0.068
le+0.067
m+0.067
y+0.065
Neg logit contributions
 disl-0.129
 Cr-0.094
 pleasure-0.092
 Joey-0.091
 majesty-0.089
Token gears
Token ID28713
Feature activation+1.57e+01

Pos logit contributions
es+0.075
 again+0.065
le+0.063
m+0.063
y+0.061
Neg logit contributions
 disl-0.138
 Cr-0.103
 Joey-0.099
 Twe-0.098
 pleasure-0.097
Token which
Token ID543
Feature activation+6.08e+00

Pos logit contributions
es+0.128
le+0.113
 again+0.111
ymes+0.110
m+0.108
Neg logit contributions
 disl-0.253
 Cr-0.193
 Joey-0.189
 Twe-0.184
 pleasure-0.179
Token made
Token ID925
Feature activation+4.86e+00

Pos logit contributions
es+0.056
 again+0.052
 on+0.050
le+0.049
y+0.048
Neg logit contributions
 disl-0.095
 Cr-0.071
 Joey-0.067
 Fro-0.067
 majesty-0.066
Token it
Token ID340
Feature activation+8.17e+00

Pos logit contributions
es+0.061
 again+0.057
m+0.056
le+0.056
y+0.055
Neg logit contributions
 disl-0.058
 Cr-0.039
 Joey-0.038
 Twe-0.036
 Fro-0.036
Token easier
Token ID4577
Feature activation+8.57e+00

Pos logit contributions
es+0.088
 again+0.086
 on+0.083
le+0.079
y+0.078
Neg logit contributions
 disl-0.114
 Cr-0.083
 Fro-0.078
 Joey-0.077
 majesty-0.076
Token for
Token ID329
Feature activation+4.45e+00

Pos logit contributions
es+0.079
le+0.070
m+0.069
ymes+0.069
ices+0.069
Neg logit contributions
 disl-0.128
 Cr-0.092
 Joey-0.092
 Twe-0.089
 Fro-0.087
Token strange
Token ID6283
Feature activation+9.79e+00

Pos logit contributions
es+0.134
ices+0.120
packs+0.118
 again+0.117
m+0.117
Neg logit contributions
 disl-0.115
 Cr-0.077
 Joey-0.077
 Fro-0.073
 Twe-0.071
Token.
Token ID13
Feature activation+4.87e+00

Pos logit contributions
es+0.077
ologist+0.070
ymes+0.070
ices+0.070
m+0.069
Neg logit contributions
 disl-0.147
 Joey-0.114
 Joe-0.110
 Cr-0.106
 J-0.105
Token It
Token ID632
Feature activation+7.68e+00

Pos logit contributions
es+0.064
 again+0.062
 on+0.062
boards+0.059
ices+0.057
Neg logit contributions
 disl-0.057
 majesty-0.034
 Majesty-0.032
 Cr-0.032
 Fro-0.031
Token was
Token ID373
Feature activation+4.99e+00

Pos logit contributions
es+0.063
 again+0.057
 on+0.054
le+0.053
m+0.053
Neg logit contributions
 disl-0.128
 Cr-0.098
 Joey-0.094
 Fro-0.092
 Twe-0.091
Token a
Token ID257
Feature activation+7.54e+00

Pos logit contributions
 on+0.051
 again+0.049
es+0.048
y+0.043
m+0.042
Neg logit contributions
 disl-0.077
 majesty-0.053
 Cr-0.053
 Majesty-0.051
APP-0.049
Token mask
Token ID9335
Feature activation+1.57e+01

Pos logit contributions
es+0.082
 again+0.078
 on+0.076
m+0.073
y+0.073
Neg logit contributions
 disl-0.105
 Cr-0.075
 Joey-0.070
 Fro-0.069
 Twe-0.067
Token!
Token ID0
Feature activation+3.88e+00

Pos logit contributions
es+0.148
ymes+0.147
ices+0.144
packs+0.140
le+0.135
Neg logit contributions
 disl-0.206
 Cr-0.157
 Joey-0.156
 Twe-0.155
 Fro-0.153
Token It
Token ID632
Feature activation+7.58e+00

Pos logit contributions
es+0.051
 on+0.049
 again+0.049
boards+0.047
 and+0.045
Neg logit contributions
 disl-0.046
 majesty-0.029
 Majesty-0.028
 pleasure-0.025
icol-0.025
Token was
Token ID373
Feature activation+5.29e+00

Pos logit contributions
es+0.056
 again+0.051
 on+0.050
le+0.047
y+0.047
Neg logit contributions
 disl-0.134
 Cr-0.103
 majesty-0.099
 Joey-0.098
 pleasure-0.098
Token lying
Token ID9105
Feature activation+1.03e+01

Pos logit contributions
 on+0.053
es+0.048
 again+0.046
 and+0.042
y+0.042
Neg logit contributions
 disl-0.087
 majesty-0.061
 Cr-0.060
 Majesty-0.059
APP-0.057
Token on
Token ID319
Feature activation+3.82e+00

Pos logit contributions
es+0.065
ices+0.060
le+0.052
ities+0.051
ymes+0.050
Neg logit contributions
 disl-0.158
 Joey-0.147
 Cr-0.139
 Twe-0.138
 Fro-0.137
Token saw
Token ID2497
Feature activation+6.17e+00

Pos logit contributions
 on+0.032
 again+0.028
es+0.027
m+0.027
 and+0.026
Neg logit contributions
 disl-0.060
 Cr-0.045
 pleasure-0.045
 Majesty-0.043
 majesty-0.043
Token a
Token ID257
Feature activation+7.12e+00

Pos logit contributions
 on+0.058
 again+0.055
es+0.055
ing+0.050
m+0.049
Neg logit contributions
 disl-0.101
 majesty-0.075
icol-0.071
 Majesty-0.071
 pleasure-0.070
Token man
Token ID582
Feature activation+1.26e+01

Pos logit contributions
es+0.078
 again+0.073
 on+0.070
le+0.069
m+0.069
Neg logit contributions
 disl-0.099
 Cr-0.071
 Joey-0.067
 Fro-0.066
 Twe-0.065
Token selling
Token ID6301
Feature activation+9.33e+00

Pos logit contributions
es+0.120
boards+0.111
ymes+0.109
ices+0.107
les+0.106
Neg logit contributions
 disl-0.176
 Cr-0.136
 Twe-0.128
 Fro-0.128
 Joey-0.125
Token colorful
Token ID20239
Feature activation+8.89e+00

Pos logit contributions
es+0.089
 again+0.085
 on+0.083
m+0.079
le+0.077
Neg logit contributions
 disl-0.143
 Cr-0.104
 Joey-0.099
 Fro-0.098
 majesty-0.097
Token fireworks
Token ID26056
Feature activation+1.56e+01

Pos logit contributions
es+0.084
 again+0.077
m+0.073
le+0.073
y+0.071
Neg logit contributions
 disl-0.136
 Cr-0.102
 Twe-0.097
 Joey-0.096
 Fro-0.093
Token.
Token ID13
Feature activation+4.39e+00

Pos logit contributions
es+0.117
ymes+0.111
ices+0.111
le+0.104
Will+0.102
Neg logit contributions
 disl-0.235
 Joey-0.191
 Cr-0.191
 Twe-0.186
 J-0.181
Token She
Token ID1375
Feature activation+6.42e+00

Pos logit contributions
 again+0.043
 on+0.040
 and+0.039
y+0.037
m+0.037
Neg logit contributions
 disl-0.069
 Majesty-0.052
 majesty-0.052
 Fre-0.050
 pleasure-0.049
Token asked
Token ID1965
Feature activation+6.67e+00

Pos logit contributions
es+0.048
 again+0.045
y+0.044
 on+0.043
m+0.042
Neg logit contributions
 disl-0.115
 pleasure-0.086
 Cr-0.086
 majesty-0.082
 Fro-0.081
Token her
Token ID607
Feature activation+6.17e+00

Pos logit contributions
es+0.086
 again+0.080
le+0.078
 on+0.078
m+0.078
Neg logit contributions
 disl-0.079
 Cr-0.055
 Joey-0.051
 Fro-0.050
 Twe-0.050
Token mom
Token ID1995
Feature activation+8.69e+00

Pos logit contributions
es+0.076
 again+0.070
le+0.069
 on+0.068
m+0.067
Neg logit contributions
 disl-0.078
 Cr-0.054
 Joey-0.051
 Fro-0.050
 Twe-0.049
Token day
Token ID1110
Feature activation+6.47e+00

Pos logit contributions
es+0.083
 again+0.072
ymes+0.069
le+0.067
ices+0.067
Neg logit contributions
 disl-0.101
 Cr-0.073
 Joey-0.072
 Fro-0.071
 Twe-0.069
Token,
Token ID11
Feature activation+3.83e+00

Pos logit contributions
es+0.053
 again+0.049
le+0.047
ymes+0.045
m+0.045
Neg logit contributions
 disl-0.103
 Cr-0.080
 Fro-0.078
 Joey-0.077
 Madd-0.075
Token she
Token ID673
Feature activation+5.99e+00

Pos logit contributions
es+0.050
 again+0.047
 on+0.046
le+0.045
m+0.045
Neg logit contributions
 disl-0.046
 Cr-0.031
 Joey-0.028
 Fro-0.028
 Twe-0.027
Token found
Token ID1043
Feature activation+7.36e+00

Pos logit contributions
es+0.055
 again+0.051
 on+0.048
le+0.048
m+0.047
Neg logit contributions
 disl-0.094
 Cr-0.071
 Joey-0.067
 Fro-0.066
 Twe-0.065
Token a
Token ID257
Feature activation+8.20e+00

Pos logit contributions
es+0.073
 on+0.072
 again+0.070
m+0.064
ing+0.063
Neg logit contributions
 disl-0.117
 Cr-0.081
 majesty-0.080
icol-0.077
 Joey-0.077
Token mask
Token ID9335
Feature activation+1.55e+01

Pos logit contributions
es+0.095
 again+0.088
le+0.085
 on+0.083
m+0.083
Neg logit contributions
 disl-0.109
 Cr-0.077
 Joey-0.073
 Fro-0.072
 Twe-0.071
Token on
Token ID319
Feature activation+4.27e+00

Pos logit contributions
ymes+0.148
ices+0.144
packs+0.141
ins+0.141
eness+0.131
Neg logit contributions
 disl-0.170
 This-0.162
 Twe-0.151
 this-0.148
 Fro-0.144
Token the
Token ID262
Feature activation+4.53e+00

Pos logit contributions
es+0.054
 again+0.051
 on+0.051
le+0.049
y+0.048
Neg logit contributions
 disl-0.054
 Cr-0.036
 majesty-0.033
 Joey-0.033
 pleasure-0.032
Token floor
Token ID4314
Feature activation+1.02e+01

Pos logit contributions
es+0.037
 again+0.037
 on+0.036
le+0.033
y+0.033
Neg logit contributions
 disl-0.075
 Cr-0.057
 Joey-0.054
 pleasure-0.052
 Twe-0.052
Token.
Token ID13
Feature activation+4.82e+00

Pos logit contributions
ymes+0.090
es+0.082
le+0.081
les+0.076
eness+0.074
Neg logit contributions
 disl-0.135
 J-0.110
 Jill-0.104
 This-0.104
 Sandy-0.102
Token The
Token ID383
Feature activation+6.71e+00

Pos logit contributions
es+0.060
 again+0.056
 on+0.055
m+0.053
y+0.053
Neg logit contributions
 disl-0.063
 Cr-0.042
 majesty-0.039
 Joey-0.038
 Twe-0.038
Tokenmy
Token ID1820
Feature activation+8.42e+00

Pos logit contributions
es+0.049
boards+0.041
ymes+0.036
ing+0.035
cases+0.035
Neg logit contributions
 disl-0.137
 Cr-0.108
 Joey-0.108
 Fro-0.107
 Twe-0.106
Token.
Token ID13
Feature activation+3.17e+00

Pos logit contributions
es+0.048
boards+0.039
 again+0.039
le+0.038
ymes+0.036
Neg logit contributions
 disl-0.159
 Cr-0.125
 Twe-0.122
 Fro-0.120
 Joey-0.120
Token Tim
Token ID5045
Feature activation+7.98e+00

Pos logit contributions
es+0.051
 again+0.048
le+0.047
 on+0.047
m+0.046
Neg logit contributions
 disl-0.029
 Cr-0.016
 Joey-0.015
 Fro-0.014
 Twe-0.014
Tokenmy
Token ID1820
Feature activation+8.25e+00

Pos logit contributions
es+0.039
 again+0.030
ing+0.028
le+0.026
boards+0.026
Neg logit contributions
 disl-0.157
 Joey-0.124
 Cr-0.123
 Twe-0.121
 Fro-0.121
Token loved
Token ID6151
Feature activation+6.34e+00

Pos logit contributions
es+0.083
 again+0.078
 on+0.077
y+0.075
m+0.073
Neg logit contributions
 disl-0.123
 Cr-0.092
 Joey-0.085
 Fro-0.085
 majesty-0.083
Token vehicles
Token ID5672
Feature activation+1.54e+01

Pos logit contributions
es+0.054
 on+0.053
 again+0.053
m+0.047
y+0.046
Neg logit contributions
 disl-0.101
 Cr-0.075
 majesty-0.072
 pleasure-0.072
 Joey-0.072
Token,
Token ID11
Feature activation+5.79e+00

Pos logit contributions
es+0.147
ymes+0.143
ices+0.140
le+0.140
les+0.134
Neg logit contributions
 disl-0.208
 Cr-0.166
 Twe-0.163
 Joey-0.156
 Fro-0.152
Token especially
Token ID2592
Feature activation+7.34e+00

Pos logit contributions
es+0.056
 again+0.051
 on+0.049
le+0.049
m+0.048
Neg logit contributions
 disl-0.089
 Cr-0.066
 Joey-0.062
 Fro-0.062
 Twe-0.061
Token cars
Token ID5006
Feature activation+1.44e+01

Pos logit contributions
es+0.084
 again+0.082
le+0.079
m+0.077
ymes+0.076
Neg logit contributions
 disl-0.096
 Cr-0.066
 Twe-0.066
 Joey-0.063
 Fro-0.062
Token.
Token ID13
Feature activation+3.99e+00

Pos logit contributions
ymes+0.134
pr+0.129
ices+0.127
le+0.122
es+0.113
Neg logit contributions
 disl-0.183
 Twe-0.152
 This-0.146
 Cr-0.144
 The-0.140
Token One
Token ID1881
Feature activation+7.80e+00

Pos logit contributions
es+0.043
 again+0.042
 on+0.040
m+0.039
y+0.039
Neg logit contributions
 disl-0.056
 Cr-0.038
 majesty-0.037
 Fro-0.036
 Joey-0.036
Token,
Token ID11
Feature activation+4.02e+00

Pos logit contributions
es+0.055
le+0.050
 again+0.049
ymes+0.049
les+0.046
Neg logit contributions
 disl-0.094
 Cr-0.072
 Joey-0.070
 Twe-0.068
 Fro-0.068
Token they
Token ID484
Feature activation+6.83e+00

Pos logit contributions
es+0.044
 again+0.041
 on+0.040
le+0.039
m+0.039
Neg logit contributions
 disl-0.056
 Cr-0.040
 Joey-0.038
 Fro-0.038
 Twe-0.037
Token saw
Token ID2497
Feature activation+6.27e+00

Pos logit contributions
es+0.068
 again+0.061
le+0.059
 on+0.058
ing+0.057
Neg logit contributions
 disl-0.101
 Cr-0.077
 Joey-0.074
 Fro-0.072
 Twe-0.071
Token a
Token ID257
Feature activation+8.62e+00

Pos logit contributions
 on+0.059
es+0.059
 again+0.057
ing+0.053
y+0.050
Neg logit contributions
 disl-0.101
 majesty-0.073
 Cr-0.071
 Majesty-0.069
LL-0.069
Token big
Token ID1263
Feature activation+7.68e+00

Pos logit contributions
es+0.102
 again+0.096
 on+0.092
le+0.091
m+0.091
Neg logit contributions
 disl-0.112
 Cr-0.078
 Joey-0.073
 Fro-0.072
 Twe-0.071
Token motorcycle
Token ID18757
Feature activation+1.54e+01

Pos logit contributions
es+0.068
 again+0.065
 on+0.063
y+0.060
le+0.060
Neg logit contributions
 disl-0.122
 Cr-0.091
 Joey-0.085
 Fro-0.085
 majesty-0.084
Token parked
Token ID19584
Feature activation+8.79e+00

Pos logit contributions
ymes+0.137
ices+0.131
es+0.130
eness+0.124
packs+0.123
Neg logit contributions
 disl-0.195
 Cr-0.173
 Twe-0.170
 This-0.168
LL-0.158
Token on
Token ID319
Feature activation+4.28e+00

Pos logit contributions
es+0.076
le+0.063
les+0.062
ices+0.059
eness+0.058
Neg logit contributions
 disl-0.127
 Cr-0.112
 Twe-0.112
 Joey-0.108
 J-0.104
Token the
Token ID262
Feature activation+4.52e+00

Pos logit contributions
es+0.053
 again+0.052
 on+0.051
le+0.049
y+0.048
Neg logit contributions
 disl-0.054
 Cr-0.036
 majesty-0.035
 Fro-0.033
 Joey-0.033
Token street
Token ID4675
Feature activation+1.04e+01

Pos logit contributions
 again+0.037
 on+0.037
es+0.036
y+0.034
m+0.033
Neg logit contributions
 disl-0.075
 Cr-0.057
 Fro-0.053
 majesty-0.052
 Joey-0.052
Token.
Token ID13
Feature activation+4.46e+00

Pos logit contributions
es+0.089
ymes+0.081
le+0.078
les+0.072
pr+0.068
Neg logit contributions
 disl-0.164
 J-0.131
 Cr-0.129
 Twe-0.126
 This-0.122
Token's
Token ID338
Feature activation+6.97e+00

Pos logit contributions
es+0.060
 again+0.054
le+0.050
m+0.050
 on+0.049
Neg logit contributions
 disl-0.132
 Cr-0.100
 Joey-0.098
 Twe-0.096
 Fro-0.096
Token mom
Token ID1995
Feature activation+9.58e+00

Pos logit contributions
es+0.096
le+0.089
 again+0.087
les+0.085
y+0.083
Neg logit contributions
 disl-0.077
 Cr-0.052
 Fro-0.050
 pleasure-0.049
 Joey-0.048
Token bought
Token ID5839
Feature activation+7.19e+00

Pos logit contributions
es+0.073
ymes+0.065
le+0.061
 again+0.060
ices+0.059
Neg logit contributions
 disl-0.157
 Joey-0.126
 Cr-0.124
 Twe-0.122
 J-0.117
Token her
Token ID607
Feature activation+7.51e+00

Pos logit contributions
es+0.078
 again+0.074
 on+0.073
m+0.069
y+0.069
Neg logit contributions
 disl-0.106
 Cr-0.072
 majesty-0.071
 Fro-0.068
 Joey-0.068
Token a
Token ID257
Feature activation+7.60e+00

Pos logit contributions
 on+0.075
es+0.074
 again+0.072
m+0.065
y+0.065
Neg logit contributions
 disl-0.113
 Cr-0.081
 majesty-0.079
 Fro-0.077
 Joey-0.075
Token candle
Token ID26839
Feature activation+1.54e+01

Pos logit contributions
es+0.081
 again+0.078
 on+0.076
m+0.073
y+0.073
Neg logit contributions
 disl-0.107
 Cr-0.076
 Joey-0.071
 Fro-0.070
 Twe-0.069
Token for
Token ID329
Feature activation+5.77e+00

Pos logit contributions
es+0.117
ymes+0.109
ices+0.106
le+0.098
 again+0.097
Neg logit contributions
 disl-0.239
 Joey-0.190
 Cr-0.189
 Twe-0.184
 Fro-0.181
Token her
Token ID607
Feature activation+7.36e+00

Pos logit contributions
es+0.061
 again+0.057
 on+0.056
m+0.053
le+0.052
Neg logit contributions
 disl-0.084
 Cr-0.059
 Joey-0.056
 Fro-0.056
 majesty-0.055
Token birthday
Token ID10955
Feature activation+1.14e+01

Pos logit contributions
es+0.100
les+0.089
ing+0.089
le+0.089
m+0.087
Neg logit contributions
 disl-0.086
 pleasure-0.055
 Cr-0.052
 Joey-0.052
 Twe-0.051
Token.
Token ID13
Feature activation+4.80e+00

Pos logit contributions
es+0.111
ymes+0.108
le+0.096
ices+0.096
les+0.093
Neg logit contributions
 disl-0.144
 This-0.118
 Twe-0.118
 Joey-0.117
 J-0.116
Token It
Token ID632
Feature activation+7.60e+00

Pos logit contributions
 again+0.055
 on+0.054
es+0.053
m+0.050
y+0.049
Neg logit contributions
 disl-0.065
 majesty-0.044
 Cr-0.044
 Majesty-0.044
 Fre-0.042
Token named
Token ID3706
Feature activation+4.32e+00

Pos logit contributions
es+0.130
 again+0.121
 on+0.118
y+0.115
le+0.115
Neg logit contributions
 disl-0.166
 Cr-0.119
 Joey-0.111
 Fro-0.110
 majesty-0.109
Token Tim
Token ID5045
Feature activation+8.04e+00

Pos logit contributions
 on+0.048
es+0.047
y+0.044
my+0.043
 again+0.042
Neg logit contributions
 disl-0.064
 Majesty-0.043
 majesty-0.042
icol-0.040
 talented-0.040
Token found
Token ID1043
Feature activation+7.57e+00

Pos logit contributions
es+0.076
 again+0.071
le+0.066
ing+0.066
ymes+0.065
Neg logit contributions
 disl-0.121
 Cr-0.089
 Joey-0.087
 Twe-0.086
 Fro-0.085
Token a
Token ID257
Feature activation+7.95e+00

Pos logit contributions
 on+0.066
es+0.060
 again+0.057
ing+0.050
m+0.048
Neg logit contributions
 disl-0.140
 majesty-0.110
 Majesty-0.106
icol-0.104
 pleasure-0.100
Token shiny
Token ID22441
Feature activation+8.65e+00

Pos logit contributions
 again+0.078
 on+0.078
es+0.077
y+0.075
m+0.074
Neg logit contributions
 disl-0.116
 Cr-0.083
 Joey-0.076
 majesty-0.074
 J-0.074
Token trophy
Token ID16383
Feature activation+1.53e+01

Pos logit contributions
es+0.088
 again+0.079
m+0.076
le+0.076
 on+0.075
Neg logit contributions
 disl-0.127
 Cr-0.094
 Joey-0.089
 Fro-0.088
 Twe-0.088
Token in
Token ID287
Feature activation+4.73e+00

Pos logit contributions
es+0.106
ices+0.095
le+0.093
ymes+0.091
m+0.088
Neg logit contributions
 disl-0.236
 Cr-0.201
 Twe-0.193
 Fro-0.189
 Joey-0.188
Token the
Token ID262
Feature activation+4.10e+00

Pos logit contributions
es+0.049
 on+0.048
 again+0.047
y+0.044
le+0.042
Neg logit contributions
 disl-0.069
 majesty-0.050
 Majesty-0.048
 Cr-0.047
 pleasure-0.047
Token forest
Token ID8222
Feature activation+1.07e+01

Pos logit contributions
 on+0.026
 again+0.025
y+0.023
st+0.022
my+0.022
Neg logit contributions
 disl-0.076
 Cr-0.057
 majesty-0.056
 Joey-0.055
 Madd-0.055
Token.
Token ID13
Feature activation+4.95e+00

Pos logit contributions
es+0.055
 again+0.047
le+0.047
les+0.043
m+0.042
Neg logit contributions
 disl-0.206
 Cr-0.164
 Joey-0.158
 Fro-0.158
 Twe-0.157
Token He
Token ID679
Feature activation+6.72e+00

Pos logit contributions
es+0.061
 on+0.061
 again+0.060
m+0.057
y+0.056
Neg logit contributions
 disl-0.060
 majesty-0.038
 Majesty-0.038
 Cr-0.037
icol-0.035
Token to
Token ID284
Feature activation+5.49e+00

Pos logit contributions
 on+0.051
es+0.049
 again+0.049
m+0.043
y+0.043
Neg logit contributions
 disl-0.100
 Cr-0.074
 majesty-0.073
 pleasure-0.072
 Joey-0.071
Token play
Token ID711
Feature activation+9.07e+00

Pos logit contributions
 on+0.044
es+0.042
 again+0.041
le+0.038
 and+0.038
Neg logit contributions
 disl-0.084
 Cr-0.066
 Fro-0.062
 Fre-0.062
 pleasure-0.062
Token with
Token ID351
Feature activation+6.09e+00

Pos logit contributions
es+0.073
m+0.071
y+0.070
packs+0.066
le+0.064
Neg logit contributions
 disl-0.142
 Cr-0.112
 Fro-0.107
 Twe-0.106
 Joey-0.102
Token his
Token ID465
Feature activation+6.58e+00

Pos logit contributions
es+0.068
 on+0.064
 again+0.063
y+0.059
le+0.059
Neg logit contributions
 disl-0.083
 Cr-0.059
 pleasure-0.057
 Joey-0.056
 majesty-0.055
Token toy
Token ID13373
Feature activation+1.05e+01

Pos logit contributions
es+0.051
 again+0.046
le+0.045
m+0.042
y+0.041
Neg logit contributions
 disl-0.114
 Cr-0.088
 Joey-0.084
 Fro-0.084
 Twe-0.083
Token cars
Token ID5006
Feature activation+1.53e+01

Pos logit contributions
le+0.109
m+0.104
pr+0.104
es+0.103
Today+0.098
Neg logit contributions
 disl-0.122
 Cr-0.108
 Twe-0.105
 Fro-0.103
 Nem-0.099
Token.
Token ID13
Feature activation+4.60e+00

Pos logit contributions
ymes+0.159
ices+0.156
Will+0.152
le+0.150
es+0.150
Neg logit contributions
 disl-0.154
 Twe-0.138
 Cr-0.137
 The-0.124
 Fro-0.123
Token One
Token ID1881
Feature activation+7.79e+00

Pos logit contributions
es+0.056
 again+0.053
 on+0.051
le+0.050
m+0.050
Neg logit contributions
 disl-0.059
 Cr-0.040
 Joey-0.038
 Fro-0.037
 majesty-0.037
Token day
Token ID1110
Feature activation+6.92e+00

Pos logit contributions
es+0.087
 again+0.075
ymes+0.072
le+0.072
les+0.070
Neg logit contributions
 disl-0.110
 Cr-0.080
 Joey-0.078
 Fro-0.077
 Twe-0.076
Token,
Token ID11
Feature activation+4.54e+00

Pos logit contributions
es+0.062
le+0.057
 again+0.056
ymes+0.055
les+0.052
Neg logit contributions
 disl-0.107
 Cr-0.083
 Joey-0.081
 Twe-0.079
 Fro-0.079
Token he
Token ID339
Feature activation+6.79e+00

Pos logit contributions
es+0.066
 again+0.062
 on+0.060
le+0.060
m+0.060
Neg logit contributions
 disl-0.048
 Cr-0.030
 Joey-0.027
 Fro-0.027
 Twe-0.026
Token named
Token ID3706
Feature activation+4.62e+00

Pos logit contributions
es+0.128
 again+0.121
le+0.115
ymes+0.113
ing+0.113
Neg logit contributions
 disl-0.122
 Cr-0.084
 Twe-0.078
 Joey-0.078
 Fro-0.077
Token Tim
Token ID5045
Feature activation+8.17e+00

Pos logit contributions
es+0.061
 on+0.061
 again+0.057
y+0.057
m+0.056
Neg logit contributions
 disl-0.055
 Majesty-0.034
 majesty-0.032
icol-0.032
 Cr-0.032
Token found
Token ID1043
Feature activation+7.75e+00

Pos logit contributions
es+0.075
 again+0.068
le+0.064
ing+0.063
m+0.062
Neg logit contributions
 disl-0.127
 Cr-0.094
 Joey-0.091
 Twe-0.090
 Fro-0.089
Token a
Token ID257
Feature activation+7.91e+00

Pos logit contributions
 on+0.071
 again+0.063
es+0.063
ing+0.057
m+0.055
Neg logit contributions
 disl-0.138
 majesty-0.104
 Majesty-0.101
icol-0.099
 pleasure-0.097
Token toy
Token ID13373
Feature activation+1.19e+01

Pos logit contributions
es+0.080
 again+0.080
 on+0.079
y+0.076
m+0.075
Neg logit contributions
 disl-0.113
 Cr-0.081
 Joey-0.075
 Fro-0.074
 majesty-0.072
Token motorcycle
Token ID18757
Feature activation+1.52e+01

Pos logit contributions
es+0.106
le+0.101
ymes+0.095
ices+0.094
les+0.092
Neg logit contributions
 disl-0.162
 Cr-0.143
 Twe-0.137
 Fro-0.133
 Joey-0.132
Token.
Token ID13
Feature activation+5.19e+00

Pos logit contributions
ymes+0.125
ices+0.119
le+0.118
eness+0.114
es+0.114
Neg logit contributions
 disl-0.207
 Twe-0.187
 This-0.185
 Cr-0.185
 Joey-0.168
Token It
Token ID632
Feature activation+7.42e+00

Pos logit contributions
es+0.073
 again+0.072
 on+0.072
y+0.067
m+0.067
Neg logit contributions
 disl-0.055
 majesty-0.032
 Cr-0.031
 Majesty-0.031
 Fro-0.029
Token was
Token ID373
Feature activation+6.04e+00

Pos logit contributions
es+0.050
 on+0.047
 again+0.046
y+0.042
m+0.041
Neg logit contributions
 disl-0.138
 Cr-0.106
 majesty-0.103
 Joey-0.101
 pleasure-0.101
Token red
Token ID2266
Feature activation+9.60e+00

Pos logit contributions
es+0.063
 on+0.061
 again+0.060
m+0.056
y+0.056
Neg logit contributions
 disl-0.088
 Cr-0.062
 Joey-0.059
 majesty-0.058
 Fro-0.058
Token and
Token ID290
Feature activation+4.00e+00

Pos logit contributions
es+0.089
ymes+0.087
pr+0.086
le+0.076
packs+0.076
Neg logit contributions
 disl-0.112
 Twe-0.108
 This-0.108
 Cr-0.101
 Joey-0.100
Token excited
Token ID6568
Feature activation+7.21e+00

Pos logit contributions
 on+0.026
m+0.026
y+0.022
ing+0.020
 next+0.020
Neg logit contributions
 disl-0.048
icol-0.041
 tal-0.040
 Cr-0.039
 Joey-0.035
Token to
Token ID284
Feature activation+5.63e+00

Pos logit contributions
es+0.066
 again+0.057
le+0.055
m+0.054
 on+0.054
Neg logit contributions
 disl-0.114
 Cr-0.086
 Joey-0.084
 Twe-0.081
 Fro-0.081
Token get
Token ID651
Feature activation+6.59e+00

Pos logit contributions
 on+0.040
 and+0.035
 again+0.034
es+0.033
.+0.031
Neg logit contributions
 disl-0.095
 Cr-0.076
 Fro-0.075
icol-0.074
 majesty-0.071
Token a
Token ID257
Feature activation+7.36e+00

Pos logit contributions
 on+0.062
 again+0.058
es+0.057
m+0.054
ing+0.052
Neg logit contributions
 disl-0.108
 majesty-0.077
 Cr-0.076
icol-0.075
 Majesty-0.074
Token sc
Token ID629
Feature activation+7.03e+00

Pos logit contributions
es+0.087
ices+0.073
 again+0.072
le+0.072
y+0.070
Neg logit contributions
 disl-0.098
 Cr-0.070
 Joey-0.068
 pleasure-0.068
 Fro-0.068
Tokenooter
Token ID25141
Feature activation+1.52e+01

Pos logit contributions
es+0.060
m+0.057
 on+0.057
 again+0.056
ing+0.055
Neg logit contributions
 disl-0.115
 Cr-0.085
 Joey-0.081
 Twe-0.080
 Madd-0.078
Token.
Token ID13
Feature activation+4.55e+00

Pos logit contributions
es+0.114
ymes+0.101
ices+0.096
le+0.091
m+0.085
Neg logit contributions
 disl-0.251
 Twe-0.203
 Cr-0.199
 Joey-0.192
 J-0.190
Token She
Token ID1375
Feature activation+6.21e+00

Pos logit contributions
es+0.049
 again+0.047
 on+0.046
m+0.044
y+0.043
Neg logit contributions
 disl-0.065
 Cr-0.045
 majesty-0.043
 Fro-0.042
 Majesty-0.041
Token wanted
Token ID2227
Feature activation+6.66e+00

Pos logit contributions
es+0.052
 on+0.048
 again+0.047
y+0.045
le+0.045
Neg logit contributions
 disl-0.105
 Cr-0.081
 Fro-0.076
 Joey-0.075
 pleasure-0.073
Token to
Token ID284
Feature activation+5.17e+00

Pos logit contributions
es+0.076
le+0.068
 again+0.067
y+0.066
m+0.065
Neg logit contributions
 disl-0.090
 Cr-0.065
 Joey-0.062
 Twe-0.061
 Fro-0.060
Token use
Token ID779
Feature activation+7.86e+00

Pos logit contributions
 on+0.043
 again+0.039
es+0.036
 and+0.035
le+0.035
Neg logit contributions
 disl-0.087
 Cr-0.067
 Fro-0.065
icol-0.064
 majesty-0.064
Token her
Token ID607
Feature activation+6.14e+00

Pos logit contributions
es+0.041
 again+0.040
 on+0.039
m+0.037
y+0.037
Neg logit contributions
 disl-0.048
 Cr-0.033
 Joey-0.031
 majesty-0.031
 Fro-0.030
Token parents
Token ID3397
Feature activation+9.79e+00

Pos logit contributions
es+0.079
 again+0.072
le+0.071
ices+0.071
m+0.070
Neg logit contributions
 disl-0.072
 majesty-0.047
 pleasure-0.046
 Cr-0.045
 Fro-0.044
Token gave
Token ID2921
Feature activation+5.53e+00

Pos logit contributions
es+0.113
ymes+0.106
ices+0.100
 again+0.098
le+0.096
Neg logit contributions
 disl-0.118
 Joey-0.093
 Cr-0.088
 Twe-0.087
 J-0.086
Token her
Token ID607
Feature activation+7.62e+00

Pos logit contributions
es+0.068
 again+0.062
le+0.060
 on+0.060
m+0.060
Neg logit contributions
 disl-0.070
 Cr-0.048
 Joey-0.045
 Fro-0.045
 Twe-0.044
Token a
Token ID257
Feature activation+7.81e+00

Pos logit contributions
es+0.090
 again+0.085
 on+0.082
le+0.081
m+0.080
Neg logit contributions
 disl-0.100
 Cr-0.069
 Joey-0.065
 Fro-0.064
 Twe-0.063
Token microphone
Token ID21822
Feature activation+1.52e+01

Pos logit contributions
es+0.084
 again+0.080
 on+0.078
m+0.075
le+0.075
Neg logit contributions
 disl-0.109
 Cr-0.079
 Joey-0.074
 Fro-0.073
 Twe-0.071
Token as
Token ID355
Feature activation+5.28e+00

Pos logit contributions
es+0.174
ymes+0.167
ices+0.163
m+0.161
le+0.160
Neg logit contributions
 disl-0.185
 Cr-0.133
 Joey-0.129
 This-0.124
 Twe-0.124
Token a
Token ID257
Feature activation+7.43e+00

Pos logit contributions
es+0.062
 again+0.058
 on+0.057
le+0.055
y+0.055
Neg logit contributions
 disl-0.070
 Cr-0.049
 Joey-0.045
 Fro-0.045
 majesty-0.044
Token gift
Token ID6979
Feature activation+1.14e+01

Pos logit contributions
es+0.087
le+0.076
ices+0.074
m+0.073
 again+0.073
Neg logit contributions
 disl-0.101
 Cr-0.071
 pleasure-0.070
 majesty-0.068
 Fro-0.068
Token,
Token ID11
Feature activation+5.53e+00

Pos logit contributions
ices+0.085
ymes+0.085
es+0.084
ud+0.078
m+0.077
Neg logit contributions
 disl-0.161
 Twe-0.131
 J-0.128
 Cr-0.128
 This-0.126
Token and
Token ID290
Feature activation+3.98e+00

Pos logit contributions
es+0.036
 again+0.030
le+0.029
m+0.028
y+0.028
Neg logit contributions
 disl-0.102
 Cr-0.081
 Joey-0.078
 Twe-0.077
 Fro-0.077
Token he
Token ID339
Feature activation+5.67e+00

Pos logit contributions
es+0.073
 again+0.071
 on+0.069
m+0.066
y+0.065
Neg logit contributions
 disl-0.117
 Cr-0.081
 majesty-0.080
 Majesty-0.077
icol-0.077
Token found
Token ID1043
Feature activation+6.77e+00

Pos logit contributions
es+0.058
 again+0.055
 on+0.052
m+0.050
y+0.050
Neg logit contributions
 disl-0.089
 Cr-0.063
 Twe-0.058
 Joey-0.058
 majesty-0.058
Token lots
Token ID6041
Feature activation+7.99e+00

Pos logit contributions
es+0.069
 on+0.063
 again+0.062
ing+0.056
le+0.054
Neg logit contributions
 disl-0.115
 Cr-0.076
LL-0.075
icol-0.075
 majesty-0.074
Token of
Token ID286
Feature activation+5.96e+00

Pos logit contributions
es+0.059
ymes+0.050
ices+0.050
m+0.049
 again+0.048
Neg logit contributions
 disl-0.130
 Joey-0.104
 Cr-0.102
 Fro-0.098
 Madd-0.097
Token colourful
Token ID44799
Feature activation+8.52e+00

Pos logit contributions
es+0.068
 again+0.064
y+0.060
m+0.060
 on+0.060
Neg logit contributions
 disl-0.079
 Cr-0.056
 Joey-0.054
 Fro-0.052
 Twe-0.051
Token gems
Token ID23685
Feature activation+1.52e+01

Pos logit contributions
es+0.082
 again+0.079
m+0.079
le+0.075
y+0.075
Neg logit contributions
 disl-0.119
 Cr-0.087
 Joey-0.087
 majesty-0.083
 Twe-0.082
Token!
Token ID0
Feature activation+3.11e+00

Pos logit contributions
ymes+0.110
es+0.104
ices+0.102
le+0.102
Will+0.098
Neg logit contributions
 disl-0.225
 Joey-0.193
 Cr-0.187
 Twe-0.177
 Fro-0.176
Token He
Token ID679
Feature activation+6.34e+00

Pos logit contributions
es+0.032
 again+0.030
 on+0.030
boards+0.029
 and+0.027
Neg logit contributions
 disl-0.048
 majesty-0.032
 Majesty-0.031
 talented-0.030
LL-0.028
Token was
Token ID373
Feature activation+5.13e+00

Pos logit contributions
es+0.052
 again+0.048
 on+0.045
y+0.043
le+0.043
Neg logit contributions
 disl-0.109
 Cr-0.082
 Joey-0.077
 Fro-0.077
 Twe-0.076
Token very
Token ID845
Feature activation+2.44e+00

Pos logit contributions
 on+0.043
es+0.038
 and+0.037
 again+0.036
m+0.030
Neg logit contributions
 disl-0.097
icol-0.068
 majesty-0.066
 Cr-0.065
APP-0.065
Token excited
Token ID6568
Feature activation+6.56e+00

Pos logit contributions
 on+0.019
 and+0.017
es+0.017
 again+0.015
m+0.015
Neg logit contributions
 disl-0.041
icol-0.032
liv-0.031
 Cr-0.030
€-0.030
Token street
Token ID4675
Feature activation+1.01e+01

Pos logit contributions
 on+0.036
 again+0.036
y+0.034
es+0.034
ing+0.032
Neg logit contributions
 disl-0.083
 Cr-0.063
 Fro-0.060
 majesty-0.060
 pleasure-0.059
Token.
Token ID13
Feature activation+3.38e+00

Pos logit contributions
es+0.076
ymes+0.070
le+0.068
les+0.060
pr+0.059
Neg logit contributions
 disl-0.162
 J-0.130
 Joey-0.129
 Cr-0.129
 Twe-0.126
Token They
Token ID1119
Feature activation+6.88e+00

Pos logit contributions
es+0.043
 again+0.043
 on+0.041
y+0.040
m+0.040
Neg logit contributions
 disl-0.040
 Cr-0.026
 Fro-0.026
 majesty-0.024
 Madd-0.023
Token saw
Token ID2497
Feature activation+6.63e+00

Pos logit contributions
es+0.068
 again+0.062
le+0.060
ymes+0.058
ing+0.057
Neg logit contributions
 disl-0.101
 Cr-0.075
 Joey-0.074
 Twe-0.071
 Fro-0.070
Token a
Token ID257
Feature activation+8.23e+00

Pos logit contributions
es+0.077
 again+0.073
 on+0.070
le+0.069
m+0.069
Neg logit contributions
 disl-0.088
 Cr-0.062
 Joey-0.058
 Fro-0.057
 Twe-0.056
Token motorcycle
Token ID18757
Feature activation+1.52e+01

Pos logit contributions
es+0.101
 again+0.093
le+0.090
 on+0.088
m+0.088
Neg logit contributions
 disl-0.104
 Cr-0.072
 Joey-0.068
 Fro-0.066
 Twe-0.066
Token parked
Token ID19584
Feature activation+8.24e+00

Pos logit contributions
ymes+0.156
ices+0.149
es+0.147
le+0.142
ities+0.137
Neg logit contributions
 disl-0.175
 Twe-0.150
 This-0.146
 Cr-0.146
 J-0.139
Token on
Token ID319
Feature activation+4.25e+00

Pos logit contributions
es+0.072
le+0.061
les+0.056
ices+0.055
ymes+0.054
Neg logit contributions
 disl-0.120
 Twe-0.105
 Cr-0.103
 Joey-0.102
 J-0.098
Token the
Token ID262
Feature activation+4.80e+00

Pos logit contributions
es+0.058
 again+0.055
 on+0.054
le+0.053
y+0.052
Neg logit contributions
 disl-0.048
 Cr-0.031
 Joey-0.028
 Fro-0.028
 majesty-0.027
Token side
Token ID1735
Feature activation+9.13e+00

Pos logit contributions
es+0.045
 again+0.043
 on+0.042
m+0.040
le+0.040
Neg logit contributions
 disl-0.074
 Cr-0.055
 Fro-0.051
 Joey-0.051
 majesty-0.050
Token of
Token ID286
Feature activation+2.60e+00

Pos logit contributions
es+0.073
ymes+0.068
le+0.061
pr+0.058
les+0.055
Neg logit contributions
 disl-0.137
 J-0.118
 Joe-0.117
 Joey-0.117
 Cr-0.111
Token got
Token ID1392
Feature activation+6.11e+00

Pos logit contributions
es+0.054
 again+0.050
le+0.047
m+0.047
 on+0.046
Neg logit contributions
 disl-0.092
 Cr-0.069
 Joey-0.067
 Twe-0.065
 Fro-0.065
Token a
Token ID257
Feature activation+8.64e+00

Pos logit contributions
 on+0.059
 again+0.055
es+0.054
m+0.049
ing+0.047
Neg logit contributions
 disl-0.100
 majesty-0.072
 Cr-0.070
icol-0.069
 Majesty-0.068
Token big
Token ID1263
Feature activation+7.96e+00

Pos logit contributions
es+0.094
 again+0.086
le+0.083
 on+0.083
m+0.082
Neg logit contributions
 disl-0.122
 Cr-0.087
 Joey-0.083
 Fro-0.082
 Twe-0.080
Token box
Token ID3091
Feature activation+1.42e+01

Pos logit contributions
es+0.072
 again+0.064
le+0.061
m+0.061
 on+0.060
Neg logit contributions
 disl-0.127
 Cr-0.096
 Joey-0.092
 Fro-0.090
 Twe-0.089
Token of
Token ID286
Feature activation+5.54e+00

Pos logit contributions
es+0.114
ymes+0.107
le+0.096
 again+0.092
les+0.092
Neg logit contributions
 disl-0.215
 Joey-0.175
 Cr-0.168
 Twe-0.166
 Sus-0.162
Token blocks
Token ID7021
Feature activation+1.52e+01

Pos logit contributions
es+0.048
 again+0.044
 on+0.042
le+0.041
m+0.040
Neg logit contributions
 disl-0.090
 Cr-0.068
 Joey-0.065
 Fro-0.064
 Twe-0.063
Token.
Token ID13
Feature activation+3.98e+00

Pos logit contributions
es+0.095
ymes+0.087
le+0.079
ices+0.075
Will+0.072
Neg logit contributions
 disl-0.262
 Joey-0.211
 Cr-0.210
 Twe-0.205
 J-0.198
Token Mom
Token ID11254
Feature activation+8.45e+00

Pos logit contributions
 again+0.052
es+0.051
 on+0.050
m+0.049
y+0.047
Neg logit contributions
 disl-0.047
 Cr-0.030
 majesty-0.029
 Fro-0.028
 Majesty-0.027
Token and
Token ID290
Feature activation+3.46e+00

Pos logit contributions
es+0.049
ymes+0.047
 again+0.045
le+0.043
ices+0.041
Neg logit contributions
 disl-0.146
 Joey-0.121
 Cr-0.113
 Joe-0.111
 Twe-0.111
Token Dad
Token ID17415
Feature activation+9.68e+00

Pos logit contributions
 on+0.044
 and+0.041
 again+0.041
m+0.041
y+0.039
Neg logit contributions
 disl-0.044
 majesty-0.030
 Fro-0.029
 Majesty-0.029
 Cr-0.028
Token decided
Token ID3066
Feature activation+5.99e+00

Pos logit contributions
es+0.109
 again+0.105
ymes+0.105
le+0.100
ices+0.098
Neg logit contributions
 disl-0.116
 Joey-0.087
 Cr-0.079
 Jon-0.076
 Sus-0.075
Token They
Token ID1119
Feature activation+5.68e+00

Pos logit contributions
es+0.039
 again+0.036
 on+0.035
le+0.035
m+0.035
Neg logit contributions
 disl-0.038
 Cr-0.026
 Joey-0.024
 Fro-0.024
 Twe-0.023
Token like
Token ID588
Feature activation+5.28e+00

Pos logit contributions
 on+0.045
es+0.043
y+0.042
 again+0.042
le+0.042
Neg logit contributions
 disl-0.092
 Cr-0.071
icol-0.070
 Fro-0.069
 Joey-0.068
Token to
Token ID284
Feature activation+4.55e+00

Pos logit contributions
es+0.052
 again+0.048
 on+0.047
le+0.045
m+0.045
Neg logit contributions
 disl-0.079
 Cr-0.058
 Joey-0.055
 Fro-0.055
 Twe-0.054
Token play
Token ID711
Feature activation+7.83e+00

Pos logit contributions
es+0.056
 again+0.052
m+0.050
ing+0.050
le+0.050
Neg logit contributions
 disl-0.058
 Cr-0.040
 Joey-0.037
 Fro-0.037
 Twe-0.036
Token with
Token ID351
Feature activation+5.72e+00

Pos logit contributions
m+0.064
es+0.059
iness+0.059
bars+0.058
ier+0.058
Neg logit contributions
 disl-0.117
 Cr-0.096
 Fro-0.093
 Twe-0.087
 Nem-0.086
Token magnets
Token ID37446
Feature activation+1.52e+01

Pos logit contributions
es+0.052
 again+0.049
m+0.046
le+0.046
ing+0.044
Neg logit contributions
 disl-0.091
 Cr-0.068
 Joey-0.065
 Fro-0.064
 Twe-0.064
Token.
Token ID13
Feature activation+3.70e+00

Pos logit contributions
Will+0.131
ices+0.131
le+0.124
pr+0.123
Today+0.120
Neg logit contributions
 disl-0.174
 Cr-0.153
 Fro-0.144
 Av-0.139
 Twe-0.135
Token Magn
Token ID14872
Feature activation+8.83e+00

Pos logit contributions
es+0.047
 again+0.044
 on+0.043
le+0.042
m+0.042
Neg logit contributions
 disl-0.046
 Cr-0.031
 Joey-0.029
 Fro-0.028
 Twe-0.028
Tokenets
Token ID1039
Feature activation+7.41e+00

Pos logit contributions
es+0.053
 again+0.047
 on+0.044
le+0.043
y+0.042
Neg logit contributions
 disl-0.166
 Cr-0.132
 Joey-0.126
 Fro-0.125
 Twe-0.124
Token are
Token ID389
Feature activation+4.72e+00

Pos logit contributions
es+0.078
 again+0.074
le+0.073
m+0.072
y+0.071
Neg logit contributions
 disl-0.104
 Cr-0.072
 Joey-0.068
 Twe-0.066
 majesty-0.065
Token things
Token ID1243
Feature activation+1.15e+01

Pos logit contributions
es+0.050
 again+0.047
le+0.046
m+0.045
y+0.045
Neg logit contributions
 disl-0.067
 Cr-0.048
 Fro-0.045
 Joey-0.045
 majesty-0.044
Token to
Token ID284
Feature activation+5.42e+00

Pos logit contributions
es+0.049
 on+0.049
 again+0.047
m+0.043
y+0.042
Neg logit contributions
 disl-0.094
 Cr-0.069
 majesty-0.067
 Joey-0.067
 pleasure-0.066
Token play
Token ID711
Feature activation+8.77e+00

Pos logit contributions
es+0.049
 on+0.048
 again+0.047
le+0.043
y+0.042
Neg logit contributions
 disl-0.080
 Cr-0.060
 Joey-0.057
 Fro-0.056
 pleasure-0.056
Token with
Token ID351
Feature activation+5.81e+00

Pos logit contributions
es+0.072
m+0.071
y+0.069
packs+0.066
le+0.064
Neg logit contributions
 disl-0.134
 Cr-0.106
 Fro-0.101
 Twe-0.099
 This-0.095
Token his
Token ID465
Feature activation+6.39e+00

Pos logit contributions
es+0.070
 again+0.065
 on+0.065
le+0.062
y+0.062
Neg logit contributions
 disl-0.075
 Cr-0.052
 Joey-0.049
 Fro-0.048
 pleasure-0.048
Token toy
Token ID13373
Feature activation+1.04e+01

Pos logit contributions
es+0.053
le+0.049
 again+0.049
m+0.044
y+0.044
Neg logit contributions
 disl-0.107
 Cr-0.081
 Fro-0.079
 Joey-0.078
 Twe-0.076
Token cars
Token ID5006
Feature activation+1.52e+01

Pos logit contributions
le+0.111
pr+0.105
m+0.103
es+0.102
Today+0.097
Neg logit contributions
 disl-0.116
 Cr-0.105
 Fro-0.101
 Twe-0.100
 Nem-0.095
Token and
Token ID290
Feature activation+3.78e+00

Pos logit contributions
ymes+0.160
ices+0.156
le+0.154
eness+0.150
Will+0.150
Neg logit contributions
 disl-0.150
 Cr-0.133
 Twe-0.131
 The-0.124
 Fro-0.121
Token trucks
Token ID13960
Feature activation+1.31e+01

Pos logit contributions
es+0.025
 on+0.024
 again+0.023
y+0.021
m+0.020
Neg logit contributions
 disl-0.069
 Cr-0.054
 Joey-0.052
 pleasure-0.051
 Fro-0.051
Token.
Token ID13
Feature activation+4.57e+00

Pos logit contributions
ymes+0.119
le+0.115
es+0.115
ices+0.110
pr+0.108
Neg logit contributions
 disl-0.163
 Cr-0.134
 Twe-0.129
 This-0.125
 Fro-0.120
Token One
Token ID1881
Feature activation+7.73e+00

Pos logit contributions
es+0.057
 again+0.054
 on+0.052
le+0.051
m+0.051
Neg logit contributions
 disl-0.057
 Cr-0.039
 Joey-0.036
 Fro-0.036
 Twe-0.035
Token day
Token ID1110
Feature activation+6.97e+00

Pos logit contributions
es+0.085
 again+0.074
le+0.070
ymes+0.070
les+0.069
Neg logit contributions
 disl-0.110
 Cr-0.079
 Joey-0.077
 Fro-0.076
 Twe-0.074
Token sky
Token ID6766
Feature activation+1.23e+01

Pos logit contributions
es+0.057
le+0.048
ices+0.046
 again+0.046
y+0.044
Neg logit contributions
 disl-0.082
 Cr-0.058
 Twe-0.057
 Joey-0.057
 majesty-0.056
Token and
Token ID290
Feature activation+3.85e+00

Pos logit contributions
es+0.106
ymes+0.101
ests+0.093
ices+0.092
ins+0.086
Neg logit contributions
 disl-0.182
 J-0.146
 Twe-0.144
 Sus-0.141
 Joey-0.139
Token saw
Token ID2497
Feature activation+5.92e+00

Pos logit contributions
 again+0.035
 on+0.033
es+0.033
le+0.029
m+0.029
Neg logit contributions
 disl-0.062
 Cr-0.047
 Fro-0.045
 majesty-0.045
 Joey-0.044
Token a
Token ID257
Feature activation+7.76e+00

Pos logit contributions
es+0.063
 again+0.062
 on+0.061
ing+0.056
m+0.055
Neg logit contributions
 disl-0.085
 Cr-0.060
 majesty-0.058
 Fro-0.057
 Joey-0.056
Token shining
Token ID22751
Feature activation+9.42e+00

Pos logit contributions
es+0.084
 again+0.080
 on+0.077
m+0.075
y+0.075
Neg logit contributions
 disl-0.108
 Cr-0.077
 Joey-0.072
 Fro-0.071
 Twe-0.070
Token gem
Token ID16840
Feature activation+1.51e+01

Pos logit contributions
es+0.100
 again+0.086
m+0.084
le+0.083
 on+0.082
Neg logit contributions
 disl-0.135
 Cr-0.101
 Joey-0.096
 Twe-0.096
 Fro-0.094
Token in
Token ID287
Feature activation+3.47e+00

Pos logit contributions
ices+0.123
es+0.115
packs+0.112
ud+0.111
eness+0.110
Neg logit contributions
 disl-0.174
 Twe-0.166
 Cr-0.154
 Fro-0.148
 Gret-0.146
Token the
Token ID262
Feature activation+3.84e+00

Pos logit contributions
es+0.048
 again+0.046
 on+0.044
le+0.044
m+0.044
Neg logit contributions
 disl-0.038
 Cr-0.025
 Joey-0.023
 Fro-0.022
 Twe-0.022
Token clouds
Token ID15114
Feature activation+1.19e+01

Pos logit contributions
es+0.036
 again+0.030
le+0.029
ices+0.028
m+0.028
Neg logit contributions
 disl-0.061
 Cr-0.046
 Twe-0.044
 Joey-0.044
 pleasure-0.043
Token.
Token ID13
Feature activation+4.66e+00

Pos logit contributions
es+0.100
ymes+0.092
ices+0.084
ests+0.078
ities+0.077
Neg logit contributions
 disl-0.177
 Joey-0.141
 J-0.139
 Twe-0.138
 Cr-0.137
Token She
Token ID1375
Feature activation+6.50e+00

Pos logit contributions
 again+0.039
 on+0.036
es+0.035
 and+0.034
m+0.032
Neg logit contributions
 disl-0.078
 majesty-0.058
 Majesty-0.056
 Cr-0.055
chie-0.055
Token They
Token ID1119
Feature activation+6.66e+00

Pos logit contributions
es+0.058
 again+0.053
le+0.052
ing+0.051
y+0.051
Neg logit contributions
 disl-0.058
 Cr-0.040
 Joey-0.038
 Twe-0.037
 Fro-0.037
Token played
Token ID2826
Feature activation+8.18e+00

Pos logit contributions
es+0.074
 again+0.069
ing+0.068
le+0.067
ices+0.066
Neg logit contributions
 disl-0.087
 Cr-0.066
 Fro-0.062
 Twe-0.062
 Joey-0.062
Token with
Token ID351
Feature activation+5.94e+00

Pos logit contributions
y+0.057
m+0.056
le+0.055
es+0.053
ing+0.052
Neg logit contributions
 disl-0.133
 Cr-0.107
 Fro-0.105
 Twe-0.099
 Joey-0.097
Token their
Token ID511
Feature activation+6.59e+00

Pos logit contributions
es+0.069
 again+0.064
 on+0.062
le+0.061
m+0.061
Neg logit contributions
 disl-0.080
 Cr-0.056
 Joey-0.053
 Fro-0.052
 majesty-0.051
Token toy
Token ID13373
Feature activation+1.08e+01

Pos logit contributions
es+0.065
le+0.061
 again+0.057
ices+0.057
ier+0.056
Neg logit contributions
 disl-0.099
 Fro-0.074
 Cr-0.074
 Twe-0.072
 pleasure-0.071
Token cars
Token ID5006
Feature activation+1.51e+01

Pos logit contributions
le+0.133
pr+0.128
inning+0.120
ge+0.119
Today+0.119
Neg logit contributions
 Fro-0.096
 Cr-0.090
 Twe-0.090
 disl-0.086
 Bub-0.086
Token and
Token ID290
Feature activation+4.02e+00

Pos logit contributions
Will+0.172
ices+0.162
eness+0.161
le+0.156
ymes+0.155
Neg logit contributions
 disl-0.124
 The-0.122
 Twe-0.118
 Fro-0.117
 our-0.116
Token dolls
Token ID36062
Feature activation+1.23e+01

Pos logit contributions
es+0.034
 again+0.031
le+0.030
ing+0.030
m+0.030
Neg logit contributions
 disl-0.065
 Cr-0.050
 Fro-0.047
 Joey-0.047
 Twe-0.047
Token.
Token ID13
Feature activation+4.83e+00

Pos logit contributions
ices+0.121
eness+0.118
ymes+0.117
Today+0.115
le+0.113
Neg logit contributions
 disl-0.128
 Fro-0.102
 The-0.098
 Twe-0.095
 Cr-0.095
Token They
Token ID1119
Feature activation+6.66e+00

Pos logit contributions
es+0.065
le+0.060
ymes+0.059
ing+0.058
 again+0.058
Neg logit contributions
 disl-0.055
 Cr-0.036
 Twe-0.036
 Joey-0.035
 This-0.034
Token had
Token ID550
Feature activation+6.05e+00

Pos logit contributions
es+0.065
 again+0.060
ing+0.060
le+0.059
ices+0.058
Neg logit contributions
 disl-0.095
 Cr-0.074
 Fro-0.070
 Twe-0.069
 Joey-0.069
Token When
Token ID1649
Feature activation-9.74e+00

Pos logit contributions
 disl+0.141
 majesty+0.093
 Cr+0.093
icol+0.091
 pleasure+0.089
Neg logit contributions
es-0.108
 again-0.103
 on-0.100
y-0.093
m-0.091
Token Daisy
Token ID40355
Feature activation-6.65e+00

Pos logit contributions
 disl+0.148
 Cr+0.104
 pleasure+0.098
 majesty+0.097
 Fro+0.097
Neg logit contributions
 on-0.098
 again-0.097
es-0.096
y-0.081
m-0.080
Token put
Token ID1234
Feature activation-7.03e+00

Pos logit contributions
 disl+0.107
 Cr+0.081
 Joey+0.077
 Fro+0.077
 Twe+0.075
Neg logit contributions
es-0.058
 again-0.053
 on-0.050
le-0.049
m-0.049
Token the
Token ID262
Feature activation-7.73e+00

Pos logit contributions
 disl+0.116
 Cr+0.089
 Joey+0.086
 Fro+0.085
 Twe+0.084
Neg logit contributions
es-0.057
 again-0.052
le-0.049
m-0.049
y-0.048
Token magn
Token ID7842
Feature activation-5.38e+00

Pos logit contributions
 disl+0.117
 Cr+0.086
 Joey+0.082
 Fro+0.082
 majesty+0.081
Neg logit contributions
es-0.076
 again-0.067
le-0.064
y-0.063
m-0.063
Tokenifying
Token ID4035
Feature activation-2.31e+01

Pos logit contributions
 disl+0.046
 Joey+0.040
 Cr+0.038
 This+0.037
 J+0.036
Neg logit contributions
es-0.061
ices-0.060
m-0.059
ymes-0.059
 again-0.059
Token glass
Token ID5405
Feature activation-5.00e+00

Pos logit contributions
 disl+0.424
 Majesty+0.310
 majesty+0.301
 talented+0.298
 Cr+0.293
Neg logit contributions
 again-0.185
 on-0.184
y-0.158
es-0.152
 and-0.151
Token down
Token ID866
Feature activation-8.63e+00

Pos logit contributions
 disl+0.080
 Joey+0.061
 Cr+0.061
 Madd+0.059
 Fro+0.058
Neg logit contributions
es-0.038
le-0.033
 again-0.033
ymes-0.033
ices-0.033
Token,
Token ID11
Feature activation-7.15e+00

Pos logit contributions
 disl+0.138
 Cr+0.104
 Joey+0.099
 Fro+0.098
 Twe+0.097
Neg logit contributions
es-0.076
 again-0.070
 on-0.066
le-0.066
m-0.065
Token the
Token ID262
Feature activation-8.61e+00

Pos logit contributions
 disl+0.122
 Cr+0.090
 majesty+0.088
icol+0.087
LL+0.085
Neg logit contributions
es-0.062
 on-0.061
 again-0.060
le-0.049
ing-0.048
Token cater
Token ID20825
Feature activation-7.84e+00

Pos logit contributions
 disl+0.127
 Cr+0.092
 majesty+0.090
 Joey+0.090
 Fro+0.088
Neg logit contributions
es-0.086
 again-0.075
le-0.073
ices-0.072
y-0.072
Token't
Token ID470
Feature activation-1.20e+01

Pos logit contributions
es+0.052
 again+0.051
 on+0.049
m+0.043
ing+0.041
Neg logit contributions
 disl-0.118
 Cr-0.088
icol-0.086
 majesty-0.086
 Fro-0.085
Token know
Token ID760
Feature activation-8.78e+00

Pos logit contributions
 disl+0.163
 Cr+0.116
 Fro+0.109
 Joey+0.106
icol+0.106
Neg logit contributions
es-0.134
 again-0.132
 on-0.127
le-0.122
y-0.121
Token the
Token ID262
Feature activation-1.15e+01

Pos logit contributions
 disl+0.119
 Cr+0.083
 Joey+0.080
 Twe+0.078
 Fro+0.077
Neg logit contributions
es-0.097
m-0.090
le-0.089
 again-0.089
y-0.088
Token rh
Token ID9529
Feature activation-1.16e+01

Pos logit contributions
 disl+0.171
 Cr+0.126
 Joey+0.119
 Fro+0.118
 Twe+0.116
Neg logit contributions
es-0.114
 again-0.106
 on-0.101
le-0.100
m-0.099
Tokenin
Token ID259
Feature activation-9.05e+00

Pos logit contributions
 disl+0.193
 Cr+0.158
 Twe+0.148
 Fro+0.147
 Joey+0.145
Neg logit contributions
es-0.067
 again-0.061
boards-0.058
Today-0.057
ices-0.056
Tokenoc
Token ID420
Feature activation-2.24e+01

Pos logit contributions
 disl+0.142
 Cr+0.106
 Joey+0.100
 Fro+0.099
 Twe+0.098
Neg logit contributions
es-0.083
 again-0.077
 on-0.073
le-0.072
m-0.072
Tokeneros
Token ID27498
Feature activation-6.12e+00

Pos logit contributions
 disl+0.267
 Cr+0.177
 Joey+0.165
 Fro+0.164
 Twe+0.158
Neg logit contributions
es-0.290
 again-0.276
 on-0.264
le-0.262
m-0.260
Token was
Token ID373
Feature activation-1.05e+01

Pos logit contributions
 disl+0.099
 Cr+0.075
 Joey+0.072
 Fro+0.071
 Twe+0.070
Neg logit contributions
es-0.051
 again-0.046
le-0.045
m-0.044
 on-0.044
Token wild
Token ID4295
Feature activation-6.38e+00

Pos logit contributions
 disl+0.164
 Cr+0.121
 majesty+0.113
 Fro+0.113
 Joey+0.112
Neg logit contributions
 again-0.098
es-0.097
 on-0.096
y-0.086
m-0.085
Token.
Token ID13
Feature activation-9.12e+00

Pos logit contributions
 disl+0.113
 Joey+0.087
 Cr+0.086
 Twe+0.085
 Fro+0.083
Neg logit contributions
es-0.042
m-0.035
ymes-0.034
ices-0.034
le-0.034
Token Can
Token ID1680
Feature activation-1.05e+01

Pos logit contributions
 disl+0.124
 majesty+0.082
icol+0.079
 Majesty+0.077
 talented+0.077
Neg logit contributions
es-0.100
 again-0.097
 on-0.090
m-0.087
y-0.086
Token am
Token ID716
Feature activation-1.03e+01

Pos logit contributions
 disl+0.147
 Cr+0.112
 Joey+0.105
 Fro+0.104
 majesty+0.103
Neg logit contributions
es-0.083
 again-0.083
 on-0.079
le-0.077
m-0.076
Token taking
Token ID2263
Feature activation-1.05e+01

Pos logit contributions
 disl+0.152
icol+0.115
 Cr+0.109
 Fro+0.099
 Joey+0.098
Neg logit contributions
 on-0.114
 again-0.106
es-0.099
 and-0.090
.-0.089
Token the
Token ID262
Feature activation-1.10e+01

Pos logit contributions
 disl+0.139
 Cr+0.097
 Joey+0.090
 Fro+0.090
 majesty+0.087
Neg logit contributions
es-0.125
 again-0.119
 on-0.117
le-0.112
y-0.108
Token rh
Token ID9529
Feature activation-1.08e+01

Pos logit contributions
 disl+0.158
 Cr+0.115
 Joey+0.111
 Fro+0.109
 Twe+0.108
Neg logit contributions
es-0.117
 again-0.103
le-0.099
m-0.098
y-0.097
Tokenin
Token ID259
Feature activation-8.88e+00

Pos logit contributions
 disl+0.186
 Cr+0.152
 Twe+0.144
 Fro+0.144
 Joey+0.142
Neg logit contributions
es-0.061
 again-0.057
 on-0.051
boards-0.050
Today-0.049
Tokenoc
Token ID420
Feature activation-2.19e+01

Pos logit contributions
 disl+0.130
 Cr+0.097
 Joey+0.091
 Fro+0.090
 Twe+0.090
Neg logit contributions
es-0.089
 again-0.080
le-0.077
m-0.076
 on-0.076
Tokeneros
Token ID27498
Feature activation-6.73e+00

Pos logit contributions
 disl+0.258
 Cr+0.170
 Joey+0.158
 Fro+0.156
 Twe+0.150
Neg logit contributions
es-0.287
 again-0.273
 on-0.261
le-0.259
y-0.258
Token to
Token ID284
Feature activation-1.06e+01

Pos logit contributions
 disl+0.110
 Cr+0.083
 Joey+0.079
 Fro+0.078
 Twe+0.077
Neg logit contributions
es-0.057
 again-0.052
 on-0.049
le-0.049
m-0.048
Token a
Token ID257
Feature activation-8.28e+00

Pos logit contributions
 disl+0.150
icol+0.108
 Cr+0.102
 Madd+0.099
APP+0.099
Neg logit contributions
 again-0.111
 on-0.106
es-0.100
 and-0.093
 later-0.090
Token new
Token ID649
Feature activation-8.96e+00

Pos logit contributions
 disl+0.116
 Cr+0.083
 Joey+0.078
 Fro+0.077
 majesty+0.075
Neg logit contributions
es-0.088
 again-0.086
 on-0.082
le-0.079
y-0.079
Token home
Token ID1363
Feature activation-6.03e+00

Pos logit contributions
 disl+0.134
 Cr+0.099
 Joey+0.094
 Fro+0.092
 Twe+0.091
Neg logit contributions
es-0.089
 again-0.082
 on-0.078
le-0.078
m-0.077
Token he
Token ID339
Feature activation-8.32e+00

Pos logit contributions
 disl+0.184
 Cr+0.134
 Fro+0.125
 majesty+0.124
 Joey+0.123
Neg logit contributions
es-0.119
 again-0.114
 on-0.110
y-0.104
le-0.104
Token would
Token ID561
Feature activation-9.38e+00

Pos logit contributions
 disl+0.141
 Cr+0.108
 Joey+0.103
 Fro+0.102
 Twe+0.101
Neg logit contributions
es-0.066
 again-0.060
 on-0.056
le-0.055
m-0.055
Token take
Token ID1011
Feature activation-8.43e+00

Pos logit contributions
 disl+0.127
 Cr+0.091
 Fro+0.084
 Joey+0.084
 Twe+0.082
Neg logit contributions
es-0.106
 again-0.100
 on-0.097
le-0.095
y-0.093
Token the
Token ID262
Feature activation-9.85e+00

Pos logit contributions
 disl+0.111
 Cr+0.077
 Joey+0.072
 Fro+0.071
 Twe+0.069
Neg logit contributions
es-0.100
 again-0.094
 on-0.091
le-0.089
m-0.088
Token av
Token ID1196
Feature activation-1.19e+01

Pos logit contributions
 disl+0.141
 Cr+0.103
 Joey+0.102
 pleasure+0.101
 Fro+0.098
Neg logit contributions
es-0.107
 again-0.089
le-0.087
m-0.087
y-0.086
Tokenoc
Token ID420
Feature activation-2.14e+01

Pos logit contributions
 disl+0.169
 Cr+0.127
 Joey+0.119
 Fro+0.117
 Twe+0.117
Neg logit contributions
es-0.117
 again-0.111
m-0.104
 on-0.104
le-0.102
Tokenados
Token ID22484
Feature activation-4.04e+00

Pos logit contributions
 disl+0.325
 Cr+0.240
 Joey+0.227
 Fro+0.227
 Twe+0.221
Neg logit contributions
es-0.208
 again-0.192
 on-0.182
le-0.180
y-0.179
Token and
Token ID290
Feature activation-9.13e+00

Pos logit contributions
 disl+0.057
 Cr+0.044
 Joey+0.044
 Fro+0.041
 Twe+0.041
Neg logit contributions
es-0.038
le-0.034
ymes-0.034
m-0.033
ices-0.033
Token scatter
Token ID41058
Feature activation-6.61e+00

Pos logit contributions
 disl+0.136
 Cr+0.100
 Fro+0.096
 Joey+0.092
 majesty+0.092
Neg logit contributions
es-0.091
 again-0.086
 on-0.084
y-0.077
le-0.077
Token them
Token ID606
Feature activation-5.69e+00

Pos logit contributions
 disl+0.093
 Cr+0.069
 Joey+0.066
 Twe+0.063
 Fro+0.063
Neg logit contributions
es-0.070
 again-0.064
m-0.062
le-0.061
 on-0.060
Token around
Token ID1088
Feature activation-8.31e+00

Pos logit contributions
 disl+0.093
 Joey+0.073
 Cr+0.072
 Twe+0.069
 Fro+0.068
Neg logit contributions
es-0.040
m-0.037
ices-0.036
ymes-0.036
le-0.035
Token give
Token ID1577
Feature activation-1.08e+01

Pos logit contributions
 disl+0.170
icol+0.137
 Cr+0.133
 pleasure+0.124
 majesty+0.123
Neg logit contributions
 again-0.116
 on-0.114
le-0.104
es-0.104
 and-0.099
Token to
Token ID284
Feature activation-9.64e+00

Pos logit contributions
 disl+0.151
 Cr+0.108
 majesty+0.103
 Fro+0.101
icol+0.100
Neg logit contributions
es-0.117
 again-0.115
 on-0.112
le-0.106
y-0.103
Token the
Token ID262
Feature activation-1.11e+01

Pos logit contributions
 disl+0.130
icol+0.103
LL+0.101
 Cr+0.097
 Fre+0.093
Neg logit contributions
 again-0.099
es-0.093
 on-0.091
 and-0.084
my-0.081
Token rh
Token ID9529
Feature activation-1.09e+01

Pos logit contributions
 disl+0.171
 Cr+0.127
 Joey+0.121
 Fro+0.120
 Twe+0.119
Neg logit contributions
es-0.105
 again-0.094
le-0.091
 on-0.090
y-0.089
Tokenin
Token ID259
Feature activation-7.94e+00

Pos logit contributions
 disl+0.186
 Cr+0.151
 Fro+0.142
 Twe+0.140
 majesty+0.139
Neg logit contributions
es-0.061
 again-0.056
 on-0.056
boards-0.051
Today-0.051
Tokenoc
Token ID420
Feature activation-2.13e+01

Pos logit contributions
 disl+0.132
 Cr+0.099
 Joey+0.095
 Fro+0.093
 majesty+0.093
Neg logit contributions
es-0.067
 again-0.063
 on-0.060
y-0.057
le-0.057
Tokeneros
Token ID27498
Feature activation-6.56e+00

Pos logit contributions
 disl+0.249
 Cr+0.164
 Joey+0.153
 Fro+0.151
 Twe+0.146
Neg logit contributions
es-0.281
 again-0.267
 on-0.255
le-0.253
y-0.251
Token.
Token ID13
Feature activation-9.04e+00

Pos logit contributions
 disl+0.115
 Cr+0.089
 Joey+0.084
 Fro+0.084
 majesty+0.083
Neg logit contributions
es-0.049
 again-0.045
 on-0.042
le-0.040
y-0.040
Token Lily
Token ID20037
Feature activation-4.85e+00

Pos logit contributions
 disl+0.120
 majesty+0.078
 Cr+0.075
 talented+0.074
 pleasure+0.074
Neg logit contributions
es-0.101
 again-0.098
 on-0.091
y-0.087
m-0.087
Token walked
Token ID6807
Feature activation-4.41e+00

Pos logit contributions
 disl+0.087
 Cr+0.069
 Joey+0.065
 pleasure+0.064
 Twe+0.064
Neg logit contributions
es-0.035
 again-0.032
 on-0.029
y-0.028
le-0.028
Token to
Token ID284
Feature activation-7.65e+00

Pos logit contributions
 disl+0.062
 Cr+0.051
 Joey+0.050
 Fro+0.049
 J+0.047
Neg logit contributions
es-0.042
ymes-0.038
ities-0.036
ices-0.036
le-0.036
Token her
Token ID607
Feature activation-1.41e+01

Pos logit contributions
es+0.033
 again+0.029
m+0.029
ices+0.028
le+0.028
Neg logit contributions
 disl-0.064
 Cr-0.048
 Fro-0.046
 Joey-0.046
 J-0.044
Token mom
Token ID1995
Feature activation-8.73e+00

Pos logit contributions
 disl+0.221
 Cr+0.169
 Joey+0.155
 Fro+0.152
 Twe+0.149
Neg logit contributions
es-0.129
 again-0.127
 on-0.124
y-0.114
m-0.113
Tokenmy
Token ID1820
Feature activation-8.80e+00

Pos logit contributions
 disl+0.148
 Cr+0.113
 Joey+0.113
 Twe+0.110
 Fro+0.109
Neg logit contributions
es-0.061
ymes-0.053
le-0.051
ices-0.051
 again-0.050
Token watched
Token ID7342
Feature activation-1.12e+01

Pos logit contributions
 disl+0.148
 Joey+0.112
 Cr+0.112
 Twe+0.108
 Fro+0.107
Neg logit contributions
es-0.064
 again-0.056
ymes-0.056
le-0.054
ices-0.054
Token in
Token ID287
Feature activation-9.00e+00

Pos logit contributions
 disl+0.177
 Cr+0.133
 Fro+0.125
 Joey+0.125
 majesty+0.123
Neg logit contributions
es-0.102
 again-0.095
 on-0.091
le-0.089
y-0.087
Token amaz
Token ID40642
Feature activation-2.07e+01

Pos logit contributions
 disl+0.121
 Cr+0.085
 Joey+0.081
 Fro+0.079
 Twe+0.078
Neg logit contributions
es-0.103
 again-0.094
le-0.092
 on-0.091
m-0.091
Tokenement
Token ID972
Feature activation-7.82e+00

Pos logit contributions
 disl+0.386
 Cr+0.302
 Joey+0.292
 Twe+0.286
 Fro+0.285
Neg logit contributions
es-0.127
 again-0.107
 on-0.103
m-0.100
le-0.099
Token as
Token ID355
Feature activation-9.78e+00

Pos logit contributions
 disl+0.142
 Cr+0.110
 Joey+0.109
 Twe+0.106
 Fro+0.105
Neg logit contributions
es-0.048
 again-0.040
m-0.039
le-0.038
ymes-0.038
Token the
Token ID262
Feature activation-9.38e+00

Pos logit contributions
 disl+0.130
 Cr+0.092
 Fro+0.085
 Joey+0.083
 majesty+0.082
Neg logit contributions
es-0.114
 again-0.109
 on-0.105
le-0.101
y-0.100
Token machine
Token ID4572
Feature activation-3.77e+00

Pos logit contributions
 disl+0.131
 Cr+0.092
 Joey+0.090
 pleasure+0.087
 Twe+0.087
Neg logit contributions
es-0.107
 again-0.091
y-0.090
le-0.089
ices-0.088
Token flew
Token ID13112
Feature activation-6.83e+00

Pos logit contributions
 disl+0.057
 Cr+0.041
 Joey+0.041
 J+0.039
 Twe+0.039
Neg logit contributions
es-0.033
ymes-0.030
ices-0.029
le-0.029
m-0.028
Token it
Token ID340
Feature activation-6.33e+00

Pos logit contributions
 disl+0.176
 Cr+0.123
LL+0.119
 majesty+0.117
icol+0.116
Neg logit contributions
es-0.136
 again-0.135
 on-0.131
le-0.124
ing-0.120
Token to
Token ID284
Feature activation-9.94e+00

Pos logit contributions
 disl+0.100
 Cr+0.074
 Fro+0.070
 Joey+0.070
 majesty+0.069
Neg logit contributions
es-0.058
 again-0.057
 on-0.054
le-0.050
y-0.050
Token the
Token ID262
Feature activation-1.09e+01

Pos logit contributions
 disl+0.137
icol+0.096
LL+0.093
 Cr+0.093
 majesty+0.089
Neg logit contributions
 again-0.106
 on-0.102
es-0.101
le-0.091
 and-0.090
Token rh
Token ID9529
Feature activation-9.52e+00

Pos logit contributions
 disl+0.166
 Cr+0.122
 Joey+0.116
 Fro+0.114
 Twe+0.112
Neg logit contributions
es-0.105
 again-0.100
 on-0.095
le-0.092
m-0.092
Tokenin
Token ID259
Feature activation-7.53e+00

Pos logit contributions
 disl+0.163
 Cr+0.132
 Fro+0.125
 Twe+0.124
 majesty+0.122
Neg logit contributions
es-0.054
 again-0.048
 on-0.048
boards-0.045
Today-0.044
Tokenoc
Token ID420
Feature activation-2.00e+01

Pos logit contributions
 disl+0.113
 Cr+0.084
 Joey+0.079
 Fro+0.079
 Twe+0.077
Neg logit contributions
es-0.073
 again-0.066
 on-0.064
le-0.063
m-0.063
Tokeneros
Token ID27498
Feature activation-5.97e+00

Pos logit contributions
 disl+0.237
 Cr+0.155
 Joey+0.145
 Fro+0.144
 Twe+0.138
Neg logit contributions
es-0.264
 again-0.252
 on-0.238
le-0.237
y-0.236
Token.
Token ID13
Feature activation-8.94e+00

Pos logit contributions
 disl+0.117
 Cr+0.094
 Joey+0.090
 Fro+0.089
 Twe+0.088
Neg logit contributions
es-0.031
 again-0.027
 on-0.024
le-0.024
m-0.023
Token When
Token ID1649
Feature activation-8.21e+00

Pos logit contributions
 disl+0.115
 majesty+0.073
 talented+0.069
 Majesty+0.069
icol+0.069
Neg logit contributions
es-0.103
 again-0.101
 on-0.093
m-0.088
y-0.088
Token he
Token ID339
Feature activation-7.05e+00

Pos logit contributions
 disl+0.120
 Cr+0.078
 majesty+0.078
 pleasure+0.076
icol+0.075
Neg logit contributions
 again-0.089
 on-0.089
es-0.087
ing-0.073
m-0.073
Token tasted
Token ID29187
Feature activation-6.02e+00

Pos logit contributions
 disl+0.110
 Cr+0.084
 Joey+0.080
 Fro+0.079
 Twe+0.077
Neg logit contributions
es-0.064
 again-0.058
 on-0.055
le-0.055
m-0.054
Token quiet
Token ID5897
Feature activation-1.60e+01

Pos logit contributions
es+0.050
 again+0.049
 on+0.046
y+0.044
le+0.043
Neg logit contributions
 disl-0.106
 Cr-0.080
 Joey-0.075
 Fro-0.075
 Twe-0.074
Token compared
Token ID3688
Feature activation-1.39e+01

Pos logit contributions
 disl+0.322
 Cr+0.257
 Joey+0.249
 Fro+0.247
 Twe+0.244
Neg logit contributions
es-0.075
 again-0.062
 on-0.056
le-0.055
m-0.054
Token to
Token ID284
Feature activation-1.12e+01

Pos logit contributions
 disl+0.205
 Cr+0.150
 Joey+0.142
 Fro+0.141
 Twe+0.138
Neg logit contributions
es-0.139
 again-0.130
 on-0.124
le-0.122
m-0.121
Token the
Token ID262
Feature activation-1.24e+01

Pos logit contributions
 disl+0.146
 Cr+0.108
 Fro+0.097
 Joey+0.096
 Twe+0.095
Neg logit contributions
es-0.130
 again-0.126
 on-0.123
le-0.117
y-0.115
Token noisy
Token ID31210
Feature activation-1.13e+01

Pos logit contributions
 disl+0.186
 Cr+0.134
 Joey+0.130
 Fro+0.127
 majesty+0.126
Neg logit contributions
es-0.125
 again-0.111
le-0.107
m-0.106
y-0.105
Token se
Token ID384
Feature activation-1.99e+01

Pos logit contributions
 disl+0.180
 Cr+0.132
 Joey+0.128
 Fro+0.125
 Twe+0.124
Neg logit contributions
es-0.104
 again-0.091
m-0.088
le-0.088
 on-0.087
Tokenag
Token ID363
Feature activation-1.17e+01

Pos logit contributions
 disl+0.329
 Cr+0.260
 Joey+0.252
 Fro+0.248
 Twe+0.246
Neg logit contributions
es-0.160
le-0.148
 again-0.145
y-0.139
les-0.137
Tokenull
Token ID724
Feature activation-4.67e+00

Pos logit contributions
 disl+0.190
 Cr+0.148
 pleasure+0.139
 Twe+0.138
icol+0.138
Neg logit contributions
es-0.106
y-0.094
 on-0.093
 again-0.092
le-0.089
Tokens
Token ID82
Feature activation-9.84e+00

Pos logit contributions
 disl+0.089
 Cr+0.069
 Joey+0.067
 Fro+0.067
 Twe+0.066
Neg logit contributions
es-0.027
 again-0.023
 on-0.021
le-0.021
m-0.021
Token outside
Token ID2354
Feature activation-8.91e+00

Pos logit contributions
 disl+0.175
 Cr+0.131
 Joey+0.130
 pleasure+0.129
 majesty+0.127
Neg logit contributions
es-0.065
le-0.057
m-0.055
 again-0.053
ymes-0.053
Token.
Token ID13
Feature activation-1.02e+01

Pos logit contributions
 disl+0.168
 Cr+0.132
 Joey+0.129
 Fro+0.126
 Twe+0.126
Neg logit contributions
es-0.052
 again-0.042
le-0.041
m-0.040
 on-0.038
Token that
Token ID326
Feature activation-8.98e+00

Pos logit contributions
 disl+0.167
 Cr+0.130
 Fro+0.124
 Joey+0.123
 majesty+0.122
Neg logit contributions
es-0.067
 again-0.063
 on-0.059
y-0.056
le-0.055
Token the
Token ID262
Feature activation-1.07e+01

Pos logit contributions
 disl+0.127
 Cr+0.090
 majesty+0.086
 Fro+0.086
icol+0.083
Neg logit contributions
es-0.097
 again-0.096
 on-0.092
m-0.084
y-0.084
Token bad
Token ID2089
Feature activation-9.81e+00

Pos logit contributions
 disl+0.156
 Cr+0.114
 Joey+0.108
 Fro+0.107
 Twe+0.105
Neg logit contributions
es-0.109
 again-0.100
 on-0.096
le-0.095
m-0.094
Token rh
Token ID9529
Feature activation-1.01e+01

Pos logit contributions
 disl+0.153
 Cr+0.116
 Fro+0.110
 Joey+0.108
 Twe+0.107
Neg logit contributions
es-0.087
 again-0.085
 on-0.080
le-0.077
y-0.077
Tokenin
Token ID259
Feature activation-8.44e+00

Pos logit contributions
 disl+0.177
 Cr+0.144
 Twe+0.136
 Joey+0.135
 Fro+0.134
Neg logit contributions
es-0.054
 again-0.050
packs-0.046
boards-0.046
 on-0.045
Tokenoc
Token ID420
Feature activation-1.96e+01

Pos logit contributions
 disl+0.130
 Cr+0.097
 Joey+0.092
 Fro+0.091
 Twe+0.090
Neg logit contributions
es-0.079
 again-0.072
 on-0.069
le-0.068
m-0.067
Tokeneros
Token ID27498
Feature activation-5.42e+00

Pos logit contributions
 disl+0.233
 Cr+0.155
 Joey+0.144
 Fro+0.142
 Twe+0.138
Neg logit contributions
es-0.256
 again-0.242
 on-0.233
le-0.231
m-0.230
Token was
Token ID373
Feature activation-9.62e+00

Pos logit contributions
 disl+0.085
 Cr+0.063
 Joey+0.061
 Fro+0.060
 Twe+0.059
Neg logit contributions
es-0.048
 again-0.043
m-0.041
le-0.041
 on-0.041
Token now
Token ID783
Feature activation-9.06e+00

Pos logit contributions
 disl+0.146
 Cr+0.107
icol+0.103
 majesty+0.103
 Fro+0.102
Neg logit contributions
 again-0.100
 on-0.099
es-0.090
m-0.083
y-0.080
Token nice
Token ID3621
Feature activation-5.90e+00

Pos logit contributions
 disl+0.136
 Cr+0.102
 Fro+0.096
 Joey+0.094
 majesty+0.093
Neg logit contributions
es-0.088
 again-0.085
 on-0.082
y-0.077
m-0.077
Token.
Token ID13
Feature activation-8.76e+00

Pos logit contributions
 disl+0.106
 Joey+0.084
 Cr+0.083
 Fro+0.081
 pleasure+0.080
Neg logit contributions
es-0.038
le-0.032
ymes-0.031
m-0.030
ices-0.029
Token you
Token ID345
Feature activation-1.42e+01

Pos logit contributions
 on+0.039
 again+0.039
es+0.037
m+0.032
 and+0.031
Neg logit contributions
 disl-0.056
icol-0.040
 Majesty-0.038
 majesty-0.038
 Cr-0.037
Token go
Token ID467
Feature activation-1.10e+01

Pos logit contributions
 disl+0.213
 Cr+0.159
icol+0.148
 Fro+0.147
 Twe+0.147
Neg logit contributions
es-0.139
 again-0.138
 on-0.135
le-0.125
y-0.124
Token,
Token ID11
Feature activation-9.72e+00

Pos logit contributions
 disl+0.181
 Cr+0.134
 Joey+0.126
 Fro+0.125
 majesty+0.125
Neg logit contributions
 again-0.096
es-0.095
 on-0.093
m-0.084
le-0.083
Token my
Token ID616
Feature activation-1.07e+01

Pos logit contributions
 disl+0.138
 Cr+0.098
icol+0.089
 Joey+0.089
 Fro+0.087
Neg logit contributions
 again-0.105
 on-0.102
es-0.102
le-0.092
m-0.090
Token d
Token ID288
Feature activation-1.15e+01

Pos logit contributions
 disl+0.158
 Cr+0.116
 Joey+0.109
 Fro+0.106
 Twe+0.105
Neg logit contributions
es-0.105
 again-0.102
 on-0.098
le-0.094
y-0.093
Tokenarl
Token ID7063
Feature activation-1.95e+01

Pos logit contributions
 disl+0.177
 Cr+0.131
 Joey+0.125
 Fro+0.123
 Twe+0.121
Neg logit contributions
es-0.110
 again-0.101
 on-0.097
le-0.096
m-0.095
Tokenings
Token ID654
Feature activation-7.81e+00

Pos logit contributions
 disl+0.343
 Cr+0.268
 Joey+0.255
 Fro+0.249
 Twe+0.247
Neg logit contributions
es-0.151
 again-0.137
 on-0.134
y-0.131
ing-0.127
Token.
Token ID13
Feature activation-1.00e+01

Pos logit contributions
 disl+0.129
 Cr+0.098
 Joey+0.094
 Fro+0.093
 Twe+0.092
Neg logit contributions
es-0.064
 again-0.058
le-0.055
 on-0.054
m-0.054
Token Enjoy
Token ID18179
Feature activation-9.91e+00

Pos logit contributions
 disl+0.126
 Joey+0.075
str+0.075
 Cr+0.075
 Fro+0.074
Neg logit contributions
es-0.122
 on-0.111
 again-0.109
Will-0.105
m-0.104
Token your
Token ID534
Feature activation-1.09e+01

Pos logit contributions
 disl+0.118
 Cr+0.083
 Joey+0.074
 pleasure+0.072
 Twe+0.071
Neg logit contributions
es-0.132
 again-0.130
 on-0.129
le-0.125
les-0.121
Token lunch
Token ID9965
Feature activation-6.12e+00

Pos logit contributions
 disl+0.163
 Cr+0.122
 Joey+0.115
 Fro+0.114
 Twe+0.112
Neg logit contributions
es-0.103
 again-0.099
 on-0.095
le-0.091
m-0.090
Token grass
Token ID8701
Feature activation-6.80e+00

Pos logit contributions
 disl+0.095
 Cr+0.073
 Joey+0.073
 Fro+0.071
 Twe+0.071
Neg logit contributions
es-0.032
 again-0.030
le-0.028
ymes-0.027
m-0.027
Token and
Token ID290
Feature activation-1.01e+01

Pos logit contributions
 disl+0.123
 Joey+0.097
 Cr+0.097
 Twe+0.096
 Fro+0.095
Neg logit contributions
es-0.037
le-0.032
ymes-0.032
ices-0.030
 again-0.030
Token rye
Token ID47553
Feature activation-1.18e+01

Pos logit contributions
 disl+0.156
 Cr+0.121
 Fro+0.110
 Joey+0.109
 Twe+0.108
Neg logit contributions
es-0.093
 on-0.089
 again-0.088
y-0.079
le-0.079
Token grass
Token ID8701
Feature activation-6.16e+00

Pos logit contributions
 disl+0.207
 Cr+0.170
 Fro+0.153
 Ag+0.148
 Joey+0.148
Neg logit contributions
 on-0.083
es-0.081
 again-0.079
 and-0.073
le-0.069
Token and
Token ID290
Feature activation-9.96e+00

Pos logit contributions
 disl+0.113
 Cr+0.088
 Joey+0.088
 Fro+0.086
 Twe+0.086
Neg logit contributions
es-0.034
le-0.029
 again-0.029
ymes-0.028
ices-0.028
Token al
Token ID435
Feature activation-1.93e+01

Pos logit contributions
 disl+0.155
 Cr+0.120
 Fro+0.110
 Joey+0.109
 Twe+0.107
Neg logit contributions
es-0.091
 again-0.086
 on-0.086
le-0.077
y-0.077
Tokenf
Token ID69
Feature activation-9.43e+00

Pos logit contributions
 disl+0.339
 Cr+0.263
 Joey+0.252
 Fro+0.250
 Twe+0.246
Neg logit contributions
es-0.141
 again-0.127
 on-0.119
le-0.118
m-0.117
Tokenalf
Token ID1604
Feature activation-7.48e+00

Pos logit contributions
 disl+0.160
 Cr+0.123
 Joey+0.118
 Fro+0.117
 Twe+0.115
Neg logit contributions
es-0.073
 again-0.066
 on-0.063
le-0.061
m-0.061
Tokena
Token ID64
Feature activation-5.85e+00

Pos logit contributions
 disl+0.130
 Cr+0.101
 Fro+0.096
 Joey+0.095
 Twe+0.094
Neg logit contributions
es-0.057
 again-0.051
 on-0.049
le-0.048
y-0.048
Token and
Token ID290
Feature activation-1.02e+01

Pos logit contributions
 disl+0.104
 Cr+0.080
 Joey+0.078
 Fro+0.077
 majesty+0.077
Neg logit contributions
es-0.039
 again-0.035
 on-0.032
le-0.032
m-0.032
Token cl
Token ID537
Feature activation-1.01e+01

Pos logit contributions
 disl+0.151
 Cr+0.114
 Joey+0.103
LL+0.102
 Fro+0.102
Neg logit contributions
es-0.103
 on-0.097
 again-0.095
y-0.088
le-0.085
Token flashlight
Token ID38371
Feature activation-2.35e+00

Pos logit contributions
 disl+0.114
 Cr+0.085
 Joey+0.080
 Fro+0.079
 Twe+0.078
Neg logit contributions
es-0.070
 again-0.065
 on-0.063
le-0.061
m-0.061
Token,
Token ID11
Feature activation-5.87e+00

Pos logit contributions
 disl+0.039
 Joey+0.029
 Cr+0.029
 Twe+0.028
 majesty+0.028
Neg logit contributions
es-0.017
ymes-0.016
ices-0.015
m-0.015
le-0.015
Token and
Token ID290
Feature activation-7.66e+00

Pos logit contributions
 disl+0.100
 Cr+0.076
 Joey+0.074
 Twe+0.074
 Fro+0.073
Neg logit contributions
es-0.043
 again-0.039
m-0.038
le-0.038
y-0.037
Token a
Token ID257
Feature activation-7.34e+00

Pos logit contributions
 disl+0.111
 Cr+0.080
 Joey+0.075
 Fro+0.075
 majesty+0.073
Neg logit contributions
es-0.081
 again-0.076
 on-0.074
le-0.070
y-0.070
Token magn
Token ID7842
Feature activation-5.14e+00

Pos logit contributions
 disl+0.112
 Cr+0.082
 Joey+0.079
 Fro+0.078
 majesty+0.077
Neg logit contributions
es-0.071
 again-0.064
le-0.062
 on-0.061
m-0.060
Tokenifying
Token ID4035
Feature activation-1.91e+01

Pos logit contributions
 disl+0.055
 Joey+0.044
 Cr+0.042
 J+0.042
 Fre+0.041
Neg logit contributions
es-0.054
 again-0.051
ymes-0.051
ices-0.050
m-0.050
Token glass
Token ID5405
Feature activation-5.30e+00

Pos logit contributions
 disl+0.356
 Majesty+0.259
 majesty+0.257
 talented+0.252
 Cr+0.251
Neg logit contributions
 again-0.146
 on-0.142
y-0.118
 and-0.116
 pieces-0.110
Token.
Token ID13
Feature activation-7.43e+00

Pos logit contributions
 disl+0.092
 Joey+0.071
 Cr+0.071
 Madd+0.069
 Twe+0.069
Neg logit contributions
es-0.032
m-0.027
 again-0.026
ices-0.026
ymes-0.026
Token
Token ID198
Feature activation-8.48e+00

Pos logit contributions
 disl+0.103
 Cr+0.068
 majesty+0.065
 Fro+0.064
 Joey+0.063
Neg logit contributions
es-0.084
 again-0.080
 on-0.077
m-0.072
y-0.072
Token
Token ID198
Feature activation-8.37e+00

Pos logit contributions
 disl+0.140
 Cr+0.105
 majesty+0.100
icol+0.099
 pleasure+0.097
Neg logit contributions
es-0.076
 again-0.070
 on-0.066
m-0.065
y-0.064
TokenAs
Token ID1722
Feature activation-6.94e+00

Pos logit contributions
 disl+0.149
 Cr+0.117
 Joey+0.112
 Fro+0.111
 pleasure+0.110
Neg logit contributions
es-0.059
 again-0.051
 on-0.049
y-0.048
m-0.048
Token go
Token ID467
Feature activation-9.13e+00

Pos logit contributions
 disl+0.202
icol+0.165
 Cr+0.159
LL+0.152
APP+0.147
Neg logit contributions
 on-0.130
 again-0.129
 and-0.112
es-0.111
le-0.110
Token!
Token ID0
Feature activation-1.06e+01

Pos logit contributions
 disl+0.162
 Cr+0.124
 majesty+0.117
 Fro+0.116
 Joey+0.116
Neg logit contributions
es-0.067
 again-0.066
 on-0.064
le-0.058
m-0.057
Token Everyone
Token ID11075
Feature activation-5.95e+00

Pos logit contributions
 disl+0.142
 Cr+0.092
 majesty+0.092
icol+0.088
 Majesty+0.087
Neg logit contributions
es-0.123
 again-0.117
 on-0.112
y-0.108
m-0.107
Token watched
Token ID7342
Feature activation-8.67e+00

Pos logit contributions
 disl+0.099
 Cr+0.076
 Joey+0.072
 Fro+0.072
 Twe+0.071
Neg logit contributions
es-0.049
 again-0.045
 on-0.042
le-0.041
y-0.041
Token in
Token ID287
Feature activation-7.75e+00

Pos logit contributions
 disl+0.133
 Cr+0.099
 Joey+0.095
 Fro+0.093
 Twe+0.092
Neg logit contributions
es-0.082
 again-0.075
 on-0.071
le-0.071
m-0.071
Token amaz
Token ID40642
Feature activation-1.91e+01

Pos logit contributions
 disl+0.107
 Cr+0.074
 Joey+0.074
 pleasure+0.073
 Fro+0.071
Neg logit contributions
es-0.085
le-0.075
m-0.074
y-0.074
ing-0.074
Tokenement
Token ID972
Feature activation-7.11e+00

Pos logit contributions
 disl+0.345
 Cr+0.267
 Joey+0.261
 Twe+0.253
 pleasure+0.251
Neg logit contributions
es-0.124
 again-0.103
 on-0.102
m-0.101
y-0.098
Token as
Token ID355
Feature activation-9.67e+00

Pos logit contributions
 disl+0.127
 Cr+0.098
 Joey+0.096
 Fro+0.093
 Twe+0.093
Neg logit contributions
es-0.047
 again-0.041
m-0.040
le-0.039
 on-0.038
Token it
Token ID340
Feature activation-5.04e+00

Pos logit contributions
 disl+0.127
 Cr+0.090
 Fro+0.085
 majesty+0.082
icol+0.080
Neg logit contributions
es-0.113
 again-0.111
 on-0.108
le-0.101
ing-0.099
Token took
Token ID1718
Feature activation-7.79e+00

Pos logit contributions
 disl+0.075
 Cr+0.054
 Joey+0.054
 Fro+0.052
 Fre+0.051
Neg logit contributions
es-0.044
m-0.041
ices-0.040
 again-0.040
ymes-0.039
Token off
Token ID572
Feature activation-7.30e+00

Pos logit contributions
 disl+0.110
 Cr+0.079
 Joey+0.074
 Fro+0.073
 Twe+0.072
Neg logit contributions
es-0.084
 again-0.078
 on-0.075
le-0.074
m-0.074
Token twenty
Token ID8208
Feature activation-8.42e+00

Pos logit contributions
 disl+0.134
icol+0.105
 Cr+0.100
 majesty+0.097
 Twe+0.094
Neg logit contributions
es-0.086
 again-0.085
 on-0.084
m-0.082
 and-0.076
Token-
Token ID12
Feature activation-1.93e+01

Pos logit contributions
 disl+0.124
 Cr+0.085
 majesty+0.082
 Fro+0.082
 Fre+0.082
Neg logit contributions
es-0.078
 again-0.075
 on-0.069
ing-0.068
m-0.068
Tokeneight
Token ID26022
Feature activation-6.16e+00

Pos logit contributions
 disl+0.311
 Cr+0.237
 Joey+0.227
 Fro+0.226
 majesty+0.222
Neg logit contributions
es-0.169
 again-0.154
le-0.148
 on-0.147
y-0.145
Token,
Token ID11
Feature activation-9.92e+00

Pos logit contributions
 disl+0.095
 Cr+0.070
 Joey+0.069
 Fro+0.068
 J+0.067
Neg logit contributions
es-0.051
 again-0.048
le-0.048
 on-0.046
m-0.045
Token twenty
Token ID8208
Feature activation-9.28e+00

Pos logit contributions
 disl+0.155
icol+0.113
 Cr+0.113
 majesty+0.110
 Fro+0.107
Neg logit contributions
es-0.090
 again-0.087
 on-0.085
m-0.082
y-0.077
Token-
Token ID12
Feature activation-1.89e+01

Pos logit contributions
 disl+0.145
 Cr+0.101
 majesty+0.101
 Fre+0.101
 Fro+0.099
Neg logit contributions
es-0.075
 again-0.074
 on-0.066
m-0.066
ing-0.065
Tokennine
Token ID30888
Feature activation-3.39e+00

Pos logit contributions
 disl+0.298
 Cr+0.224
 Joey+0.213
 Fro+0.212
 majesty+0.208
Neg logit contributions
es-0.171
 again-0.157
 on-0.150
le-0.149
m-0.147
Token,
Token ID11
Feature activation-9.42e+00

Pos logit contributions
 disl+0.055
 Cr+0.041
 Joey+0.040
 Fro+0.039
 Twe+0.039
Neg logit contributions
es-0.027
 again-0.026
 on-0.024
ices-0.024
ymes-0.024
Token thirty
Token ID12277
Feature activation-9.26e+00

Pos logit contributions
 disl+0.152
 Cr+0.110
 majesty+0.109
icol+0.108
 Fro+0.108
Neg logit contributions
es-0.081
 again-0.078
 on-0.078
m-0.073
y-0.069
Token,
Token ID11
Feature activation-9.01e+00

Pos logit contributions
 disl+0.155
 Cr+0.113
 majesty+0.111
 Joey+0.110
 Fro+0.110
Neg logit contributions
es-0.067
 again-0.066
 on-0.060
m-0.058
ymes-0.057
Token thirty
Token ID12277
Feature activation-8.89e+00

Pos logit contributions
 disl+0.147
 Cr+0.106
 Fro+0.104
 majesty+0.104
icol+0.104
Neg logit contributions
es-0.078
 on-0.074
 again-0.074
m-0.068
y-0.065
Token them
Token ID606
Feature activation-4.69e+00

Pos logit contributions
 disl+0.093
 Cr+0.065
 Joey+0.062
 Fro+0.061
 Twe+0.060
Neg logit contributions
es-0.080
 again-0.075
 on-0.072
le-0.072
y-0.071
Token and
Token ID290
Feature activation-9.25e+00

Pos logit contributions
 disl+0.076
 Joey+0.057
 Cr+0.057
 pleasure+0.056
 Twe+0.055
Neg logit contributions
es-0.034
les-0.032
ices-0.031
le-0.031
ymes-0.030
Token never
Token ID1239
Feature activation-7.84e+00

Pos logit contributions
 disl+0.123
 Cr+0.097
 Fro+0.091
icol+0.090
 Joey+0.090
Neg logit contributions
 again-0.098
es-0.097
 on-0.094
 and-0.083
m-0.081
Token threw
Token ID9617
Feature activation-7.13e+00

Pos logit contributions
 disl+0.106
 Cr+0.075
 Joey+0.070
 Fro+0.069
 Twe+0.068
Neg logit contributions
es-0.090
 again-0.082
le-0.080
 on-0.080
m-0.079
Token a
Token ID257
Feature activation-7.54e+00

Pos logit contributions
 disl+0.098
 Cr+0.071
 Joey+0.068
 Twe+0.067
 Fro+0.066
Neg logit contributions
es-0.078
 again-0.070
m-0.069
le-0.068
y-0.067
Token tant
Token ID24246
Feature activation-1.87e+01

Pos logit contributions
 disl+0.107
 Cr+0.075
 Fro+0.074
 Joey+0.073
 pleasure+0.072
Neg logit contributions
es-0.082
 again-0.069
ices-0.068
le-0.067
m-0.066
Tokenrum
Token ID6582
Feature activation-7.94e+00

Pos logit contributions
 disl+0.294
 Cr+0.218
 Joey+0.206
 Fro+0.204
 Twe+0.201
Neg logit contributions
es-0.170
 again-0.159
 on-0.153
m-0.148
le-0.147
Token again
Token ID757
Feature activation-6.16e+00

Pos logit contributions
 disl+0.147
 Cr+0.117
 Joey+0.116
 Twe+0.115
 Fro+0.111
Neg logit contributions
es-0.038
le-0.034
m-0.032
ymes-0.032
 again-0.031
Token.
Token ID13
Feature activation-7.99e+00

Pos logit contributions
 disl+0.114
 Joey+0.087
 Cr+0.086
 Twe+0.085
 Fro+0.084
Neg logit contributions
es-0.036
ymes-0.032
le-0.030
boards-0.030
m-0.030
Token<|endoftext|>
Token ID50256
Feature activation-3.83e+00

Pos logit contributions
 disl+0.125
 majesty+0.092
 talented+0.089
chie+0.089
 Fre+0.088
Neg logit contributions
 again-0.068
es-0.064
Today-0.058
m-0.058
my-0.056
TokenOnce
Token ID7454
Feature activation-8.85e+00

Pos logit contributions
 disl+0.043
 Cr+0.030
 Fro+0.028
 Joey+0.028
 Twe+0.027
Neg logit contributions
es-0.048
le-0.046
 again-0.044
y-0.044
ing-0.043
Tokeneddy
Token ID21874
Feature activation-8.90e+00

Pos logit contributions
 disl+0.239
 Cr+0.187
 Joey+0.178
 Fro+0.177
 pleasure+0.175
Neg logit contributions
es-0.080
 again-0.070
y-0.067
le-0.065
 on-0.063
Token bear
Token ID6842
Feature activation-4.63e+00

Pos logit contributions
 disl+0.154
 Cr+0.119
 Joey+0.114
 Fro+0.113
 Twe+0.112
Neg logit contributions
es-0.066
 again-0.060
 on-0.056
m-0.055
le-0.055
Token and
Token ID290
Feature activation-8.70e+00

Pos logit contributions
 disl+0.078
 Cr+0.059
 Joey+0.059
 Twe+0.058
 Fro+0.057
Neg logit contributions
es-0.032
 again-0.030
ymes-0.029
le-0.029
m-0.028
Token watched
Token ID7342
Feature activation-8.86e+00

Pos logit contributions
 disl+0.134
 Cr+0.103
 Fro+0.096
 Joey+0.094
LL+0.094
Neg logit contributions
es-0.084
 on-0.078
 again-0.078
le-0.068
y-0.068
Token in
Token ID287
Feature activation-7.07e+00

Pos logit contributions
 disl+0.131
 Cr+0.093
 majesty+0.088
 Fro+0.087
 pleasure+0.084
Neg logit contributions
es-0.093
 again-0.092
 on-0.088
le-0.085
ing-0.080
Token amaz
Token ID40642
Feature activation-1.87e+01

Pos logit contributions
 disl+0.089
 Cr+0.060
 Joey+0.057
 Fro+0.056
 pleasure+0.055
Neg logit contributions
es-0.088
 again-0.079
le-0.079
m-0.078
y-0.078
Tokenement
Token ID972
Feature activation-6.42e+00

Pos logit contributions
 disl+0.335
 Cr+0.258
 Joey+0.252
 Twe+0.247
 pleasure+0.243
Neg logit contributions
es-0.123
 on-0.102
 again-0.102
m-0.101
y-0.098
Token as
Token ID355
Feature activation-8.53e+00

Pos logit contributions
 disl+0.123
 Cr+0.097
 Joey+0.095
 Fro+0.093
 Twe+0.093
Neg logit contributions
es-0.034
 again-0.028
m-0.027
le-0.026
 on-0.026
Token it
Token ID340
Feature activation-4.87e+00

Pos logit contributions
 disl+0.115
 Cr+0.082
 Fro+0.075
 Joey+0.074
 majesty+0.073
Neg logit contributions
es-0.099
 again-0.094
 on-0.091
le-0.087
y-0.086
Token shrunk
Token ID38900
Feature activation-5.36e+00

Pos logit contributions
 disl+0.067
 Cr+0.048
 Joey+0.048
 Madd+0.048
 Fro+0.047
Neg logit contributions
es-0.045
ices-0.043
ymes-0.043
m-0.042
packs-0.042
Token an
Token ID281
Feature activation-9.07e+00

Pos logit contributions
 disl+0.093
 Joey+0.072
 Cr+0.071
 Twe+0.070
 Fro+0.069
Neg logit contributions
es-0.037
m-0.033
 again-0.031
 on-0.029
le-0.029
Token She
Token ID1375
Feature activation-5.07e+00

Pos logit contributions
 disl+0.080
 Cr+0.055
 Fro+0.051
 Joey+0.051
 Twe+0.050
Neg logit contributions
es-0.095
le-0.093
 again-0.089
m-0.087
ymes-0.087
Token takes
Token ID2753
Feature activation-6.51e+00

Pos logit contributions
 disl+0.074
 Cr+0.054
 Joey+0.051
 Fro+0.050
 majesty+0.049
Neg logit contributions
es-0.052
 again-0.048
 on-0.046
le-0.046
m-0.046
Token out
Token ID503
Feature activation-4.95e+00

Pos logit contributions
 disl+0.094
 Cr+0.068
 Joey+0.065
 Fro+0.064
 Twe+0.063
Neg logit contributions
es-0.068
 again-0.063
 on-0.061
le-0.060
m-0.060
Token a
Token ID257
Feature activation-5.48e+00

Pos logit contributions
 disl+0.058
 Cr+0.039
 Joey+0.037
 Fro+0.036
 Twe+0.035
Neg logit contributions
es-0.063
 again-0.060
le-0.058
m-0.058
y-0.057
Token magn
Token ID7842
Feature activation-3.41e+00

Pos logit contributions
 disl+0.076
 Cr+0.053
 Joey+0.052
 pleasure+0.051
 Fro+0.050
Neg logit contributions
es-0.060
le-0.053
 again-0.053
m-0.052
y-0.051
Tokenifying
Token ID4035
Feature activation-1.84e+01

Pos logit contributions
 disl+0.038
 Cr+0.029
 Joey+0.028
 Fre+0.028
 J+0.028
Neg logit contributions
es-0.037
 again-0.036
m-0.035
ices-0.033
ymes-0.033
Token glass
Token ID5405
Feature activation-2.36e+00

Pos logit contributions
 disl+0.336
 Majesty+0.243
 Jon+0.239
 majesty+0.237
 Joey+0.237
Neg logit contributions
 again-0.145
 on-0.136
 pieces-0.115
y-0.113
es-0.112
Token.
Token ID13
Feature activation-6.09e+00

Pos logit contributions
 disl+0.039
 Cr+0.030
 Joey+0.029
 Fro+0.029
 Madd+0.029
Neg logit contributions
es-0.015
ices-0.013
ymes-0.013
m-0.013
le-0.013
Token She
Token ID1375
Feature activation-4.65e+00

Pos logit contributions
 disl+0.074
 Cr+0.049
 Joey+0.046
 Fro+0.045
 Twe+0.044
Neg logit contributions
es-0.078
 again-0.074
 on-0.071
le-0.070
m-0.070
Token looks
Token ID3073
Feature activation-5.05e+00

Pos logit contributions
 disl+0.069
 Cr+0.051
 Joey+0.048
 Fro+0.048
 Twe+0.047
Neg logit contributions
es-0.047
 again-0.043
 on-0.041
le-0.041
m-0.040
Token at
Token ID379
Feature activation-6.26e+00

Pos logit contributions
 disl+0.092
 Cr+0.071
 Fro+0.068
 Joey+0.068
 Twe+0.067
Neg logit contributions
es-0.035
 again-0.032
 on-0.031
le-0.029
y-0.028
Token air
Token ID1633
Feature activation-1.78e+01

Pos logit contributions
es+0.062
 again+0.058
 on+0.056
le+0.054
m+0.054
Neg logit contributions
 disl-0.071
 Cr-0.049
 Fro-0.046
 majesty-0.045
 Joey-0.045
Token.
Token ID13
Feature activation-1.16e+01

Pos logit contributions
 disl+0.346
 Cr+0.275
 Joey+0.269
 Twe+0.263
 Fro+0.263
Neg logit contributions
es-0.092
 again-0.072
le-0.067
m-0.066
 on-0.063
Token He
Token ID679
Feature activation-7.90e+00

Pos logit contributions
 disl+0.157
 majesty+0.104
 Cr+0.103
icol+0.101
 pleasure+0.099
Neg logit contributions
es-0.126
 again-0.122
 on-0.118
y-0.110
m-0.109
Token watched
Token ID7342
Feature activation-9.61e+00

Pos logit contributions
 disl+0.128
 Cr+0.100
 Joey+0.094
 pleasure+0.092
 Fro+0.092
Neg logit contributions
es-0.070
 again-0.066
 on-0.063
le-0.061
y-0.058
Token with
Token ID351
Feature activation-9.28e+00

Pos logit contributions
 disl+0.134
 Cr+0.094
 Fro+0.087
 Joey+0.086
 majesty+0.086
Neg logit contributions
es-0.107
 again-0.104
 on-0.099
le-0.097
y-0.094
Token amaz
Token ID40642
Feature activation-1.81e+01

Pos logit contributions
 disl+0.129
 Cr+0.093
 majesty+0.085
 Fro+0.084
APP+0.084
Neg logit contributions
 again-0.104
es-0.101
 on-0.101
le-0.092
y-0.088
Tokenement
Token ID972
Feature activation-5.96e+00

Pos logit contributions
 disl+0.320
 Cr+0.247
 Joey+0.241
 Twe+0.234
 pleasure+0.231
Neg logit contributions
es-0.122
m-0.102
 on-0.102
 again-0.101
y-0.099
Token as
Token ID355
Feature activation-8.78e+00

Pos logit contributions
 disl+0.106
 Cr+0.082
 Joey+0.080
 Fro+0.078
 Twe+0.078
Neg logit contributions
es-0.040
 again-0.035
m-0.034
le-0.033
ymes-0.032
Token the
Token ID262
Feature activation-8.61e+00

Pos logit contributions
 disl+0.116
 Cr+0.081
 Fro+0.075
 Joey+0.074
 majesty+0.073
Neg logit contributions
es-0.103
 again-0.099
 on-0.096
le-0.091
y-0.090
Token z
Token ID1976
Feature activation-8.79e+00

Pos logit contributions
 disl+0.124
 Cr+0.088
 Joey+0.086
 pleasure+0.084
 majesty+0.083
Neg logit contributions
es-0.095
 again-0.081
y-0.080
le-0.079
ices-0.077
Tokenig
Token ID328
Feature activation-5.54e+00

Pos logit contributions
 disl+0.163
 Cr+0.128
 Joey+0.123
 Fro+0.122
 Twe+0.121
Neg logit contributions
es-0.057
 again-0.051
 on-0.047
le-0.047
m-0.045
Token't
Token ID470
Feature activation-7.49e+00

Pos logit contributions
 disl+0.140
 majesty+0.098
 Cr+0.097
 Majesty+0.096
 pleasure+0.095
Neg logit contributions
es-0.101
 on-0.098
 again-0.096
m-0.094
ing-0.088
Token touch
Token ID3638
Feature activation-6.75e+00

Pos logit contributions
 disl+0.098
 Cr+0.068
 majesty+0.064
 Fro+0.064
icol+0.064
Neg logit contributions
 again-0.086
es-0.085
 on-0.083
y-0.081
le-0.080
Token the
Token ID262
Feature activation-8.53e+00

Pos logit contributions
 disl+0.082
 Cr+0.055
 Joey+0.051
 Fro+0.051
 majesty+0.050
Neg logit contributions
es-0.087
 again-0.084
 on-0.081
le-0.079
y-0.079
Token rh
Token ID9529
Feature activation-6.95e+00

Pos logit contributions
 disl+0.128
 Cr+0.093
 Joey+0.089
 Fro+0.089
 Twe+0.088
Neg logit contributions
es-0.085
 again-0.076
le-0.073
m-0.072
 on-0.071
Tokenin
Token ID259
Feature activation-5.56e+00

Pos logit contributions
 disl+0.110
 Cr+0.088
 Twe+0.085
 Fro+0.083
 majesty+0.081
Neg logit contributions
 again-0.041
es-0.040
boards-0.040
packs-0.039
Today-0.039
Tokenoc
Token ID420
Feature activation-1.79e+01

Pos logit contributions
 disl+0.075
 Cr+0.055
 Twe+0.051
 Joey+0.051
 Fro+0.051
Neg logit contributions
es-0.058
 again-0.053
ices-0.052
ymes-0.051
m-0.051
Tokeneros
Token ID27498
Feature activation-2.98e+00

Pos logit contributions
 disl+0.211
 Cr+0.139
 Joey+0.130
 Fro+0.128
 Twe+0.123
Neg logit contributions
es-0.236
 again-0.224
 on-0.214
le-0.213
m-0.212
Token!
Token ID0
Feature activation-9.14e+00

Pos logit contributions
 disl+0.039
 Cr+0.027
 Joey+0.026
 Fro+0.026
 Twe+0.026
Neg logit contributions
es-0.032
ices-0.030
m-0.029
ymes-0.029
 again-0.028
Token It
Token ID632
Feature activation-6.21e+00

Pos logit contributions
 disl+0.107
 majesty+0.065
icol+0.064
 Cr+0.063
 Majesty+0.062
Neg logit contributions
es-0.119
 again-0.109
m-0.106
 on-0.106
y-0.103
Token might
Token ID1244
Feature activation-8.86e+00

Pos logit contributions
 disl+0.109
 Cr+0.085
 Joey+0.082
 pleasure+0.081
 Fro+0.080
Neg logit contributions
es-0.048
 again-0.044
 on-0.042
le-0.041
y-0.041
Token bite
Token ID13197
Feature activation-6.30e+00

Pos logit contributions
 disl+0.144
icol+0.116
 Majesty+0.114
 majesty+0.111
 Cr+0.110
Neg logit contributions
 on-0.077
 again-0.074
le-0.065
 and-0.064
y-0.064
Token to
Token ID284
Feature activation-1.30e+01

Pos logit contributions
 disl+0.312
 Cr+0.236
icol+0.225
 majesty+0.223
 Fro+0.221
Neg logit contributions
 again-0.160
 on-0.152
es-0.149
y-0.133
le-0.132
Token eat
Token ID4483
Feature activation-1.17e+01

Pos logit contributions
 disl+0.188
 Cr+0.139
icol+0.135
 Fro+0.130
 majesty+0.129
Neg logit contributions
 again-0.140
 on-0.130
es-0.126
le-0.122
 and-0.113
Token the
Token ID262
Feature activation-1.19e+01

Pos logit contributions
 disl+0.161
 Cr+0.115
 Joey+0.109
 Fro+0.107
 Twe+0.106
Neg logit contributions
es-0.129
 again-0.119
 on-0.115
le-0.114
m-0.114
Token y
Token ID331
Feature activation-1.57e+01

Pos logit contributions
 disl+0.168
 Cr+0.121
 Joey+0.115
 Fro+0.113
 Twe+0.112
Neg logit contributions
es-0.128
 again-0.116
le-0.111
 on-0.111
y-0.110
Tokenummy
Token ID13513
Feature activation-1.16e+01

Pos logit contributions
 disl+0.184
 Cr+0.124
 Joey+0.123
 Twe+0.115
 Fro+0.113
Neg logit contributions
es-0.207
 on-0.187
 again-0.187
m-0.181
ymes-0.179
Token ins
Token ID1035
Feature activation-1.78e+01

Pos logit contributions
 disl+0.164
 Joey+0.117
 Cr+0.116
 Twe+0.110
 Fro+0.109
Neg logit contributions
es-0.126
 again-0.109
m-0.105
ices-0.105
ymes-0.105
Tokenides
Token ID1460
Feature activation-8.97e+00

Pos logit contributions
 disl+0.269
 Cr+0.200
 Fro+0.189
 Joey+0.186
 Twe+0.184
Neg logit contributions
es-0.174
 again-0.161
le-0.156
y-0.153
m-0.152
Token.
Token ID13
Feature activation-1.08e+01

Pos logit contributions
 disl+0.161
 Joey+0.127
 Cr+0.126
 Twe+0.121
 Fro+0.120
Neg logit contributions
es-0.054
 again-0.045
le-0.045
ymes-0.044
m-0.043
Token From
Token ID3574
Feature activation-7.42e+00

Pos logit contributions
 disl+0.151
 Cr+0.098
 majesty+0.098
icol+0.095
 talented+0.094
Neg logit contributions
es-0.116
 again-0.113
 on-0.105
m-0.102
y-0.102
Token that
Token ID326
Feature activation-7.50e+00

Pos logit contributions
 disl+0.123
 Cr+0.092
 majesty+0.089
 Fro+0.086
 pleasure+0.086
Neg logit contributions
 again-0.065
 on-0.063
es-0.060
le-0.056
y-0.056
Token day
Token ID1110
Feature activation-6.01e+00

Pos logit contributions
 disl+0.124
 Cr+0.094
 Joey+0.089
 Fro+0.089
 Twe+0.087
Neg logit contributions
es-0.064
 again-0.058
 on-0.055
le-0.054
m-0.054
Token!"
Token ID2474
Feature activation-2.45e+00

Pos logit contributions
 disl+0.013
 Cr+0.009
 Joey+0.009
 Twe+0.008
 Fro+0.008
Neg logit contributions
es-0.010
 again-0.009
m-0.009
le-0.009
 on-0.008
Token
Token ID220
Feature activation-4.74e+00

Pos logit contributions
 disl+0.032
 Cr+0.021
 majesty+0.021
 Majesty+0.020
 Fro+0.020
Neg logit contributions
es-0.030
 again-0.029
 on-0.028
m-0.027
ing-0.026
Token
Token ID198
Feature activation-2.46e+00

Pos logit contributions
 disl+0.085
 Cr+0.063
icol+0.062
 majesty+0.062
 talented+0.060
Neg logit contributions
es-0.040
 again-0.037
 on-0.034
ing-0.032
m-0.030
Token
Token ID198
Feature activation-2.24e+00

Pos logit contributions
 disl+0.040
 Cr+0.029
 majesty+0.028
icol+0.027
 pleasure+0.027
Neg logit contributions
es-0.023
 again-0.022
 on-0.021
m-0.020
ing-0.019
TokenThe
Token ID464
Feature activation-1.81e+00

Pos logit contributions
 disl+0.033
 Cr+0.024
 Joey+0.022
 Fro+0.022
 majesty+0.022
Neg logit contributions
es-0.023
 again-0.022
 on-0.021
le-0.020
m-0.020
Token person
Token ID1048
Feature activation+4.29e+00

Pos logit contributions
 disl+0.028
 Cr+0.020
 Joey+0.019
 Fro+0.019
 Twe+0.019
Neg logit contributions
es-0.018
 again-0.017
 on-0.016
m-0.016
le-0.015
Token sighed
Token ID21893
Feature activation+2.07e+00

Pos logit contributions
es+0.046
ymes+0.042
ices+0.042
packs+0.041
 again+0.041
Neg logit contributions
 disl-0.055
 Cr-0.041
 Joey-0.040
 Fro-0.039
 Madd-0.038
Token,
Token ID11
Feature activation+6.48e-01

Pos logit contributions
es+0.012
ymes+0.010
ices+0.009
m+0.009
boards+0.009
Neg logit contributions
 disl-0.038
 Joey-0.031
 Cr-0.031
 Twe-0.030
 Fro-0.029
Token "
Token ID366
Feature activation+3.48e-01

Pos logit contributions
es+0.006
 again+0.006
 on+0.005
m+0.005
y+0.005
Neg logit contributions
 disl-0.010
 Cr-0.008
 Fro-0.007
 majesty-0.007
 Joey-0.007
TokenWell
Token ID5779
Feature activation-3.13e-01

Pos logit contributions
es+0.004
 again+0.003
 on+0.003
le+0.003
y+0.003
Neg logit contributions
 disl-0.005
 Cr-0.004
 Joey-0.004
 Fro-0.004
 Twe-0.004
Token,
Token ID11
Feature activation-9.25e-01

Pos logit contributions
 disl+0.006
 Cr+0.005
icol+0.004
 Fro+0.004
 Twe+0.004
Neg logit contributions
es-0.002
 again-0.002
 on-0.002
le-0.002
m-0.002
Token.
Token ID13
Feature activation+3.46e+00

Pos logit contributions
ymes+0.089
es+0.085
le+0.079
ices+0.074
pr+0.071
Neg logit contributions
 disl-0.170
 Joey-0.143
 Cr-0.142
 Fro-0.141
 Twe-0.140
Token The
Token ID383
Feature activation+4.67e+00

Pos logit contributions
es+0.051
 again+0.050
 on+0.050
m+0.047
y+0.047
Neg logit contributions
 disl-0.034
 majesty-0.019
 Majesty-0.019
 Cr-0.018
 pleasure-0.017
Token man
Token ID582
Feature activation+9.56e+00

Pos logit contributions
es+0.051
 again+0.046
le+0.044
y+0.043
 on+0.043
Neg logit contributions
 disl-0.069
 Cr-0.049
 Joey-0.046
 Fro-0.046
 majesty-0.045
Token was
Token ID373
Feature activation+5.15e+00

Pos logit contributions
ices+0.116
ymes+0.113
es+0.113
ities+0.110
eness+0.109
Neg logit contributions
 disl-0.105
 Cr-0.077
 Joey-0.075
 Twe-0.072
 Fro-0.070
Token spraying
Token ID40170
Feature activation+8.78e+00

Pos logit contributions
 on+0.051
es+0.042
m+0.041
 again+0.040
y+0.038
Neg logit contributions
 disl-0.088
icol-0.062
 majesty-0.062
 Majesty-0.061
 Cr-0.061
Token water
Token ID1660
Feature activation+1.06e+01

Pos logit contributions
es+0.098
 again+0.089
le+0.086
m+0.085
y+0.085
Neg logit contributions
 disl-0.121
 Cr-0.087
 Joey-0.083
 Fro-0.081
 Twe-0.080
Token on
Token ID319
Feature activation+1.88e+00

Pos logit contributions
es+0.067
ymes+0.065
ices+0.063
le+0.058
ologist+0.057
Neg logit contributions
 disl-0.174
 Cr-0.146
 Fro-0.145
 Joey-0.144
 Twe-0.141
Token the
Token ID262
Feature activation+3.05e+00

Pos logit contributions
es+0.026
 again+0.025
 on+0.024
le+0.024
m+0.024
Neg logit contributions
 disl-0.021
 Cr-0.013
 Joey-0.012
 Fro-0.012
 Twe-0.012
Token flowers
Token ID12734
Feature activation+1.02e+01

Pos logit contributions
es+0.031
 again+0.029
 on+0.028
le+0.028
m+0.027
Neg logit contributions
 disl-0.045
 Cr-0.033
 Joey-0.031
 Fro-0.031
 Twe-0.030
Token.
Token ID13
Feature activation+2.96e+00

Pos logit contributions
ymes+0.079
es+0.073
le+0.070
ices+0.069
pr+0.067
Neg logit contributions
 disl-0.154
 Joey-0.123
 Cr-0.121
 Fro-0.120
 J-0.117
Token Tim
Token ID5045
Feature activation+7.04e+00

Pos logit contributions
 again+0.038
es+0.038
 on+0.038
boards+0.036
 and+0.035
Neg logit contributions
 disl-0.033
 majesty-0.022
 Majesty-0.021
 pleasure-0.020
icol-0.019
Token?"
Token ID1701
Feature activation+2.82e+00

Pos logit contributions
es+0.049
 again+0.047
 on+0.046
le+0.043
y+0.043
Neg logit contributions
 disl-0.080
 Cr-0.058
 Joey-0.055
 Fro-0.055
 majesty-0.055
Token
Token ID198
Feature activation+2.67e+00

Pos logit contributions
es+0.044
 again+0.041
le+0.041
y+0.041
m+0.041
Neg logit contributions
 disl-0.027
 Cr-0.015
 Joey-0.014
 Fro-0.013
 Twe-0.013
Token
Token ID198
Feature activation+2.49e+00

Pos logit contributions
es+0.027
 again+0.026
 on+0.025
m+0.024
le+0.024
Neg logit contributions
 disl-0.040
 Cr-0.029
 majesty-0.027
 Joey-0.027
 Fro-0.027
TokenThe
Token ID464
Feature activation+4.36e+00

Pos logit contributions
es+0.024
 again+0.022
m+0.021
le+0.021
 on+0.021
Neg logit contributions
 disl-0.038
 Cr-0.028
 Joey-0.026
 Fro-0.026
 Twe-0.026
Token red
Token ID2266
Feature activation+6.30e+00

Pos logit contributions
es+0.041
 again+0.038
 on+0.036
le+0.036
m+0.036
Neg logit contributions
 disl-0.068
 Cr-0.051
 Joey-0.048
 Fro-0.047
 Twe-0.047
Token rose
Token ID8278
Feature activation+1.03e+01

Pos logit contributions
es+0.067
 again+0.059
le+0.057
m+0.056
ices+0.055
Neg logit contributions
 disl-0.088
 Cr-0.064
 Fro-0.062
 Twe-0.061
 Joey-0.059
Token replied
Token ID8712
Feature activation+7.47e+00

Pos logit contributions
es+0.112
 again+0.100
le+0.099
ices+0.099
m+0.098
Neg logit contributions
 disl-0.142
 Cr-0.101
 Joey-0.096
 Fro-0.096
 Twe-0.095
Token "
Token ID366
Feature activation+5.38e+00

Pos logit contributions
es+0.058
 again+0.053
 on+0.050
le+0.048
y+0.047
Neg logit contributions
 disl-0.130
 Cr-0.099
 Joey-0.095
 Fro-0.094
 majesty-0.093
TokenI
Token ID40
Feature activation+5.23e+00

Pos logit contributions
es+0.051
 again+0.047
 on+0.045
le+0.044
m+0.044
Neg logit contributions
 disl-0.083
 Cr-0.062
 Joey-0.059
 Fro-0.058
 Twe-0.057
Token'm
Token ID1101
Feature activation+3.82e+00

Pos logit contributions
 on+0.053
es+0.052
y+0.051
m+0.051
 again+0.050
Neg logit contributions
 disl-0.073
 Cr-0.055
icol-0.054
 Majesty-0.053
 majesty-0.053
Token bouncing
Token ID30713
Feature activation+8.81e+00

Pos logit contributions
 on+0.036
 again+0.027
 and+0.026
 in+0.023
 under+0.023
Neg logit contributions
 disl-0.067
icol-0.048
roc-0.047
 majesty-0.046
 rightful-0.046
Token explored
Token ID18782
Feature activation+3.94e+00

Pos logit contributions
es+0.004
 on+0.004
 again+0.004
y+0.004
m+0.004
Neg logit contributions
 disl-0.009
 Cr-0.006
 majesty-0.006
 pleasure-0.006
 Majesty-0.006
Token all
Token ID477
Feature activation+8.21e-02

Pos logit contributions
es+0.054
 again+0.050
le+0.049
m+0.049
 on+0.048
Neg logit contributions
 disl-0.044
 Cr-0.029
 Joey-0.027
 Fro-0.026
 Twe-0.026
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
es+0.001
 again+0.001
 on+0.001
y+0.001
m+0.001
Neg logit contributions
 disl-0.001
 Cr-0.001
 majesty-0.001
 Fro-0.001
icol-0.001
Token slides
Token ID19392
Feature activation+7.27e+00

Pos logit contributions
es+0.018
 again+0.016
ities+0.015
ier+0.015
le+0.015
Neg logit contributions
 disl-0.017
 Joey-0.011
 talented-0.010
 Fre-0.010
 Twe-0.010
Token and
Token ID290
Feature activation-5.85e-02

Pos logit contributions
es+0.052
ymes+0.051
Will+0.048
le+0.047
ices+0.047
Neg logit contributions
 disl-0.109
 Twe-0.091
 Joey-0.089
 Fro-0.088
 J-0.087
Token swings
Token ID26728
Feature activation+5.79e+00

Pos logit contributions
 disl+0.001
 Cr+0.001
 Joey+0.001
 Fro+0.001
 majesty+0.001
Neg logit contributions
es-0.001
 again-0.001
 on-0.001
m-0.001
le-0.001
Token.
Token ID13
Feature activation-2.86e-02

Pos logit contributions
ymes+0.042
es+0.041
ologist+0.041
ices+0.040
ities+0.039
Neg logit contributions
 disl-0.084
 Twe-0.073
 Fro-0.071
 Sandy-0.070
 Cr-0.070
Token Meanwhile
Token ID11214
Feature activation+2.95e+00

Pos logit contributions
 disl+0.000
 Cr+0.000
 majesty+0.000
 Fro+0.000
 Twe+0.000
Neg logit contributions
es-0.000
 again-0.000
 on-0.000
m-0.000
y-0.000
Token Dan
Token ID6035
Feature activation+5.04e+00

Pos logit contributions
es+0.022
 again+0.020
 on+0.019
le+0.019
m+0.019
Neg logit contributions
 disl-0.051
 Cr-0.039
 Joey-0.038
 Fro-0.037
 Twe-0.037
Token grabbed
Token ID13176
Feature activation+3.02e+00

Pos logit contributions
es+0.047
 again+0.042
 on+0.041
ymes+0.041
le+0.041
Neg logit contributions
 disl-0.074
 Cr-0.054
 Joey-0.053
 Fro-0.053
 J-0.051
Token a
Token ID257
Feature activation+3.98e+00

Pos logit contributions
es+0.034
 on+0.033
 again+0.032
le+0.030
y+0.030
Neg logit contributions
 disl-0.043
 Cr-0.029
 majesty-0.028
 Twe-0.027
 Joey-0.027
Tokenl
Token ID75
Feature activation+4.74e+00

Pos logit contributions
es+0.039
 again+0.036
m+0.035
 on+0.033
ices+0.033
Neg logit contributions
 disl-0.071
 Cr-0.053
 Twe-0.051
 Joey-0.050
 Fro-0.050
Tokenaces
Token ID2114
Feature activation+7.13e+00

Pos logit contributions
Will+0.051
Today+0.050
m+0.044
 tighter+0.043
Did+0.043
Neg logit contributions
 disl-0.051
 Twe-0.039
 This-0.038
 The-0.034
 Cr-0.033
Token and
Token ID290
Feature activation-1.72e+00

Pos logit contributions
es+0.051
ymes+0.050
ices+0.047
le+0.045
ud+0.045
Neg logit contributions
 disl-0.110
 Cr-0.085
 Twe-0.085
 Joey-0.084
 J-0.081
Token pretty
Token ID2495
Feature activation+1.69e+00

Pos logit contributions
 disl+0.027
 Cr+0.020
 Joey+0.019
 Twe+0.018
 Fro+0.018
Neg logit contributions
es-0.016
 again-0.015
le-0.014
m-0.014
y-0.014
Token ear
Token ID1027
Feature activation+3.35e+00

Pos logit contributions
es+0.015
m+0.015
ing+0.014
ymes+0.013
ices+0.013
Neg logit contributions
 disl-0.025
 Twe-0.018
 majesty-0.018
 Cr-0.017
 Majesty-0.017
Tokenrings
Token ID33173
Feature activation+7.18e+00

Pos logit contributions
es+0.029
m+0.028
ices+0.028
ymes+0.028
le+0.028
Neg logit contributions
 disl-0.046
 Twe-0.035
 Cr-0.034
 majesty-0.033
 J-0.033
Token.
Token ID13
Feature activation-6.61e-01

Pos logit contributions
ymes+0.057
ices+0.054
ud+0.054
Today+0.050
le+0.050
Neg logit contributions
 disl-0.104
 Twe-0.078
 This-0.077
 pleasure-0.077
 Cr-0.075
Token She
Token ID1375
Feature activation+1.08e+00

Pos logit contributions
 disl+0.008
 Cr+0.006
 Joey+0.005
 Twe+0.005
 Fro+0.005
Neg logit contributions
es-0.008
 again-0.008
le-0.007
 on-0.007
y-0.007
Token worked
Token ID3111
Feature activation+2.55e+00

Pos logit contributions
es+0.011
ing+0.010
 again+0.010
m+0.010
ymes+0.010
Neg logit contributions
 disl-0.015
 Cr-0.010
 Twe-0.010
 Fro-0.010
 Joey-0.010
Token very
Token ID845
Feature activation-8.10e-01

Pos logit contributions
es+0.029
le+0.027
ices+0.027
ymes+0.027
m+0.027
Neg logit contributions
 disl-0.028
 Cr-0.021
 Joey-0.020
 Twe-0.020
 J-0.019
Token hard
Token ID1327
Feature activation+2.41e+00

Pos logit contributions
 disl+0.011
 Cr+0.007
 Twe+0.007
 talented+0.007
 Joey+0.007
Neg logit contributions
es-0.009
m-0.008
berries-0.008
packs-0.008
ices-0.008
Token play
Token ID711
Feature activation+4.66e+00

Pos logit contributions
 on+0.009
 again+0.009
es+0.009
 and+0.008
 while+0.008
Neg logit contributions
 disl-0.015
 Cr-0.011
icol-0.010
LL-0.010
APP-0.010
Token neat
Token ID15049
Feature activation+6.28e+00

Pos logit contributions
es+0.034
packs+0.032
m+0.032
y+0.032
ing+0.030
Neg logit contributions
 disl-0.075
 Cr-0.059
 Fro-0.056
 Twe-0.055
 Joey-0.055
Token games
Token ID1830
Feature activation+7.98e+00

Pos logit contributions
es+0.041
m+0.041
Today+0.038
 again+0.037
pr+0.036
Neg logit contributions
 disl-0.108
 Cr-0.080
 Twe-0.078
 Fro-0.077
 Joey-0.077
Token.
Token ID13
Feature activation+1.49e+00

Pos logit contributions
ymes+0.073
eness+0.069
ices+0.069
els+0.068
les+0.066
Neg logit contributions
 disl-0.097
 Cr-0.074
 Jill-0.074
 Av-0.074
 Fro-0.073
Token
Token ID220
Feature activation-6.31e-02

Pos logit contributions
es+0.016
 again+0.015
 on+0.014
m+0.014
y+0.014
Neg logit contributions
 disl-0.021
 Cr-0.015
 Joey-0.014
 Fro-0.014
 majesty-0.014
Token
Token ID198
Feature activation+1.34e+00

Pos logit contributions
 disl+0.001
 Cr+0.001
 Joey+0.001
 Fro+0.001
 majesty+0.001
Neg logit contributions
es-0.001
 again-0.001
 on-0.001
m-0.001
le-0.001
Token
Token ID198
Feature activation+1.15e+00

Pos logit contributions
es+0.018
le+0.016
 again+0.016
ymes+0.016
les+0.016
Neg logit contributions
 disl-0.014
 Cr-0.010
 Joey-0.009
 Fro-0.009
 Twe-0.009
TokenOne
Token ID3198
Feature activation+4.09e+00

Pos logit contributions
es+0.010
ier+0.009
 again+0.009
le+0.009
les+0.008
Neg logit contributions
 disl-0.019
 Cr-0.014
 Twe-0.014
LL-0.013
 This-0.013
Token day
Token ID1110
Feature activation+4.32e+00

Pos logit contributions
es+0.039
 again+0.036
 on+0.034
le+0.034
m+0.033
Neg logit contributions
 disl-0.063
 Cr-0.047
 Joey-0.045
 Fro-0.044
 Twe-0.043
Token,
Token ID11
Feature activation+2.41e+00

Pos logit contributions
es+0.038
 again+0.034
le+0.033
ymes+0.033
m+0.032
Neg logit contributions
 disl-0.067
 Cr-0.052
 Joey-0.050
 Twe-0.050
 Fro-0.049
Token the
Token ID262
Feature activation+2.34e+00

Pos logit contributions
es+0.024
 again+0.023
 on+0.023
m+0.021
y+0.021
Neg logit contributions
 disl-0.036
 Cr-0.026
 Joey-0.025
 majesty-0.024
 Fro-0.024
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
es+0.022
ymes+0.019
packs+0.018
ices+0.018
m+0.018
Neg logit contributions
 disl-0.042
 Twe-0.037
 Joey-0.036
 Sus-0.034
 Cr-0.034
Token
Token ID220
Feature activation-2.98e+00

Pos logit contributions
 disl+0.023
 majesty+0.016
 Cr+0.016
icol+0.016
 Majesty+0.015
Neg logit contributions
es-0.013
 again-0.013
m-0.012
 on-0.012
Today-0.011
Token
Token ID198
Feature activation-1.62e+00

Pos logit contributions
 disl+0.051
 Cr+0.038
icol+0.037
 majesty+0.036
 Fro+0.035
Neg logit contributions
es-0.026
 again-0.024
 on-0.022
m-0.022
ing-0.020
Token
Token ID198
Feature activation-1.43e+00

Pos logit contributions
 disl+0.028
 Cr+0.021
icol+0.020
 majesty+0.020
 Majesty+0.020
Neg logit contributions
es-0.013
 again-0.012
 on-0.012
m-0.012
Today-0.011
TokenG
Token ID38
Feature activation-1.42e+00

Pos logit contributions
 disl+0.026
 Cr+0.020
 Joey+0.019
 pleasure+0.019
 majesty+0.019
Neg logit contributions
es-0.010
 again-0.009
 on-0.009
le-0.009
m-0.009
Tokenlor
Token ID4685
Feature activation+3.55e+00

Pos logit contributions
 disl+0.021
 Cr+0.016
 Joey+0.015
 Fro+0.015
 Twe+0.014
Neg logit contributions
es-0.014
 again-0.013
y-0.013
le-0.013
m-0.013
Tokenia
Token ID544
Feature activation+3.03e+00

Pos logit contributions
es+0.035
 again+0.033
le+0.030
y+0.030
 on+0.030
Neg logit contributions
 disl-0.058
 Cr-0.044
 Joey-0.040
 pleasure-0.040
 Twe-0.039
Token was
Token ID373
Feature activation+8.28e-01

Pos logit contributions
es+0.027
 again+0.024
 on+0.023
m+0.023
le+0.023
Neg logit contributions
 disl-0.047
 Cr-0.035
 Joey-0.034
 Fro-0.034
 Twe-0.033
Token very
Token ID845
Feature activation-2.47e+00

Pos logit contributions
 on+0.008
 again+0.008
es+0.007
m+0.007
 and+0.006
Neg logit contributions
 disl-0.014
 Cr-0.010
icol-0.010
 majesty-0.010
 Joey-0.009
Token sad
Token ID6507
Feature activation+2.81e+00

Pos logit contributions
 disl+0.041
icol+0.034
 Cr+0.033
 majesty+0.030
APP+0.030
Neg logit contributions
 on-0.021
 again-0.019
m-0.018
 and-0.017
y-0.017
Token.
Token ID13
Feature activation-1.05e-01

Pos logit contributions
es+0.022
ymes+0.021
le+0.018
ices+0.018
m+0.018
Neg logit contributions
 disl-0.045
 Joey-0.035
 Cr-0.034
 Twe-0.034
 Fro-0.034
Token,
Token ID11
Feature activation-5.97e-01

Pos logit contributions
es+0.007
 again+0.007
 on+0.006
le+0.006
y+0.006
Neg logit contributions
 disl-0.019
 Cr-0.015
 Joey-0.014
 Fro-0.014
 majesty-0.014
Token I
Token ID314
Feature activation+2.58e+00

Pos logit contributions
 disl+0.008
icol+0.005
 Cr+0.005
LL+0.005
APP+0.005
Neg logit contributions
 again-0.007
 on-0.007
es-0.007
m-0.006
 and-0.006
Token have
Token ID423
Feature activation+1.29e+00

Pos logit contributions
es+0.026
 on+0.025
m+0.024
 again+0.024
y+0.023
Neg logit contributions
 disl-0.039
 Cr-0.029
 Joey-0.028
 majesty-0.027
 Twe-0.027
Token a
Token ID257
Feature activation+2.51e+00

Pos logit contributions
 on+0.012
 again+0.011
es+0.010
 pieces+0.009
 and+0.009
Neg logit contributions
 disl-0.022
 Cr-0.016
 Madd-0.015
 Joey-0.015
APP-0.015
Token lime
Token ID28738
Feature activation+8.33e+00

Pos logit contributions
es+0.021
 again+0.021
 on+0.021
m+0.019
y+0.019
Neg logit contributions
 disl-0.040
 Cr-0.031
 Joey-0.028
 Twe-0.028
 Fro-0.028
Token!"
Token ID2474
Feature activation+3.48e-01

Pos logit contributions
es+0.086
 again+0.079
le+0.076
 on+0.075
m+0.075
Neg logit contributions
 disl-0.119
 Cr-0.087
 Joey-0.082
 Fro-0.082
 Twe-0.080
Token Tom
Token ID4186
Feature activation+4.93e+00

Pos logit contributions
 on+0.004
 again+0.003
es+0.003
 and+0.003
 while+0.003
Neg logit contributions
 disl-0.005
 Majesty-0.004
 majesty-0.004
 pleasure-0.004
icol-0.004
Token said
Token ID531
Feature activation+5.06e+00

Pos logit contributions
es+0.058
 again+0.054
le+0.052
ymes+0.052
 on+0.051
Neg logit contributions
 disl-0.062
 Cr-0.045
 Fro-0.043
 Joey-0.043
 Twe-0.041
Token.
Token ID13
Feature activation+6.94e-01

Pos logit contributions
es+0.026
 again+0.021
le+0.020
m+0.020
 on+0.019
Neg logit contributions
 disl-0.099
 Cr-0.080
 Joey-0.077
 Fro-0.076
 Twe-0.076
Token He
Token ID679
Feature activation+4.39e+00

Pos logit contributions
es+0.008
 again+0.007
 on+0.007
m+0.007
y+0.007
Neg logit contributions
 disl-0.010
 Cr-0.007
 majesty-0.006
 Majesty-0.006
 Joey-0.006
Token took
Token ID1718
Feature activation+3.61e+00

Pos logit contributions
es+0.041
 again+0.038
le+0.036
 on+0.036
m+0.035
Neg logit contributions
 disl-0.067
 Cr-0.050
 Joey-0.048
 Fro-0.048
 Twe-0.047
Token writing
Token ID3597
Feature activation+2.06e+00

Pos logit contributions
 disl+0.009
 Cr+0.006
 Joey+0.006
 J+0.006
 talented+0.005
Neg logit contributions
es-0.007
m-0.006
le-0.006
y-0.006
 again-0.006
Token adventures
Token ID17545
Feature activation+2.25e+00

Pos logit contributions
es+0.013
m+0.012
le+0.011
 again+0.011
y+0.011
Neg logit contributions
 disl-0.037
 Cr-0.028
 Joey-0.027
 J-0.027
 Fro-0.027
Token together
Token ID1978
Feature activation+5.71e-01

Pos logit contributions
es+0.013
m+0.011
le+0.011
ices+0.011
 again+0.010
Neg logit contributions
 disl-0.041
 Cr-0.032
 Joey-0.031
 Twe-0.030
 J-0.030
Token.
Token ID13
Feature activation-2.99e+00

Pos logit contributions
es+0.004
m+0.003
ymes+0.003
le+0.003
ices+0.003
Neg logit contributions
 disl-0.010
 Joey-0.008
 Cr-0.008
 J-0.007
 pleasure-0.007
Token<|endoftext|>
Token ID50256
Feature activation+2.36e+00

Pos logit contributions
 disl+0.045
 majesty+0.031
 Cr+0.030
 Majesty+0.029
 Joey+0.029
Neg logit contributions
es-0.029
 again-0.029
 on-0.029
m-0.027
Today-0.026
TokenOne
Token ID3198
Feature activation+1.85e-01

Pos logit contributions
es+0.027
le+0.027
ymes+0.025
 again+0.025
pr+0.025
Neg logit contributions
 disl-0.026
 Cr-0.020
 Joey-0.019
 Fro-0.019
 J-0.018
Token day
Token ID1110
Feature activation+1.83e-01

Pos logit contributions
 on+0.001
 again+0.001
y+0.001
m+0.001
es+0.001
Neg logit contributions
 disl-0.003
 Cr-0.003
icol-0.003
 majesty-0.003
 Twe-0.003
Token,
Token ID11
Feature activation-3.03e-01

Pos logit contributions
es+0.001
 on+0.001
 again+0.001
y+0.001
ing+0.001
Neg logit contributions
 disl-0.004
 Cr-0.003
 majesty-0.003
 pleasure-0.003
 Majesty-0.003
Token Little
Token ID7703
Feature activation+1.30e+00

Pos logit contributions
 disl+0.005
 majesty+0.004
 Majesty+0.004
 Cr+0.003
icol+0.003
Neg logit contributions
 on-0.003
es-0.003
y-0.003
 again-0.003
m-0.002
Token Joe
Token ID5689
Feature activation+2.74e+00

Pos logit contributions
es+0.019
 again+0.019
 on+0.019
m+0.018
y+0.018
Neg logit contributions
 disl-0.013
 Cr-0.008
 majesty-0.007
 Fro-0.006
 Majesty-0.006
Token was
Token ID373
Feature activation+6.40e-01

Pos logit contributions
es+0.018
 again+0.017
 on+0.016
y+0.016
le+0.015
Neg logit contributions
 disl-0.050
 Cr-0.040
 Fro-0.037
 majesty-0.037
 pleasure-0.037
Token A
Token ID317
Feature activation-6.73e+00

Pos logit contributions
 disl+0.145
 majesty+0.098
 Cr+0.097
icol+0.093
 talented+0.092
Neg logit contributions
es-0.104
 again-0.101
 on-0.093
y-0.090
m-0.088
Token few
Token ID1178
Feature activation-8.46e+00

Pos logit contributions
 disl+0.091
 Cr+0.065
 Joey+0.063
 Fro+0.062
 pleasure+0.060
Neg logit contributions
es-0.076
 again-0.068
le-0.068
m-0.066
y-0.065
Token weeks
Token ID2745
Feature activation-5.87e+00

Pos logit contributions
 disl+0.132
 Joey+0.099
 Cr+0.095
 majesty+0.094
 Madd+0.093
Neg logit contributions
es-0.062
m-0.060
y-0.058
 again-0.056
Today-0.055
Token later
Token ID1568
Feature activation-7.02e+00

Pos logit contributions
 disl+0.099
 Cr+0.078
 Joey+0.078
 Twe+0.075
 Jon+0.074
Neg logit contributions
es-0.040
ymes-0.037
 again-0.035
le-0.035
y-0.034
Token,
Token ID11
Feature activation-6.82e+00

Pos logit contributions
 disl+0.119
 Cr+0.091
 Joey+0.087
 Fro+0.086
 Twe+0.085
Neg logit contributions
es-0.056
 again-0.050
 on-0.048
le-0.047
m-0.047
Token Adam
Token ID7244
Feature activation-3.99e+00

Pos logit contributions
 disl+0.092
 Cr+0.065
 Joey+0.061
 Fro+0.060
 Twe+0.059
Neg logit contributions
es-0.078
 again-0.073
 on-0.071
le-0.069
m-0.069
Token heard
Token ID2982
Feature activation-5.81e+00

Pos logit contributions
 disl+0.067
 Cr+0.051
 Joey+0.048
 Fro+0.048
 Twe+0.047
Neg logit contributions
es-0.033
 again-0.030
 on-0.028
le-0.028
m-0.027
Token about
Token ID546
Feature activation-6.59e+00

Pos logit contributions
 disl+0.077
 Cr+0.054
 Joey+0.050
 Fro+0.050
 Twe+0.049
Neg logit contributions
es-0.068
 again-0.064
 on-0.061
le-0.061
m-0.060
Token a
Token ID257
Feature activation-4.62e+00

Pos logit contributions
 disl+0.082
 Cr+0.056
 Joey+0.053
 Fro+0.051
 Twe+0.050
Neg logit contributions
es-0.082
 again-0.075
le-0.074
m-0.074
y-0.073
Token new
Token ID649
Feature activation-5.06e+00

Pos logit contributions
 disl+0.057
 Cr+0.038
 Joey+0.037
 Fro+0.037
 pleasure+0.036
Neg logit contributions
es-0.059
le-0.053
 again-0.052
y-0.051
m-0.051
Token doctor
Token ID6253
Feature activation+3.38e-01

Pos logit contributions
 disl+0.077
 Cr+0.056
 Joey+0.054
 Fro+0.053
 Twe+0.052
Neg logit contributions
es-0.050
 again-0.044
m-0.043
le-0.043
 on-0.043
Token was
Token ID373
Feature activation-1.06e+01

Pos logit contributions
 disl+0.122
 Cr+0.091
 Joey+0.088
 Twe+0.086
 Fro+0.086
Neg logit contributions
es-0.061
 again-0.055
m-0.053
 on-0.052
le-0.052
Token healthy
Token ID5448
Feature activation-6.64e+00

Pos logit contributions
 disl+0.158
 Cr+0.118
 Fro+0.111
 majesty+0.107
 Joey+0.106
Neg logit contributions
 again-0.104
es-0.103
 on-0.102
y-0.092
m-0.091
Token again
Token ID757
Feature activation-7.84e+00

Pos logit contributions
 disl+0.114
 Joey+0.092
 pleasure+0.089
 Cr+0.087
 Twe+0.087
Neg logit contributions
es-0.041
ymes-0.037
ices-0.034
pr-0.033
le-0.032
Token.
Token ID13
Feature activation-9.75e+00

Pos logit contributions
 disl+0.153
 Cr+0.119
 Joey+0.118
 Fro+0.115
 Twe+0.115
Neg logit contributions
es-0.041
le-0.032
 again-0.031
m-0.030
ymes-0.030
Token So
Token ID1406
Feature activation-8.76e+00

Pos logit contributions
 disl+0.143
 majesty+0.099
 Cr+0.095
icol+0.094
 Majesty+0.092
Neg logit contributions
 again-0.097
es-0.095
 on-0.085
y-0.084
Today-0.083
Token,
Token ID11
Feature activation-8.74e+00

Pos logit contributions
 disl+0.145
 Cr+0.105
 majesty+0.100
 Fro+0.099
 pleasure+0.096
Neg logit contributions
es-0.077
 again-0.076
 on-0.074
y-0.066
le-0.066
Token the
Token ID262
Feature activation-9.27e+00

Pos logit contributions
 disl+0.121
 Cr+0.081
 majesty+0.078
 Fro+0.076
 pleasure+0.074
Neg logit contributions
es-0.099
 again-0.097
 on-0.095
le-0.088
y-0.087
Token little
Token ID1310
Feature activation-9.36e+00

Pos logit contributions
 disl+0.127
 Cr+0.090
 Joey+0.087
 Twe+0.084
 pleasure+0.084
Neg logit contributions
es-0.108
 again-0.094
le-0.093
y-0.091
ices-0.091
Token girl
Token ID2576
Feature activation-4.18e+00

Pos logit contributions
 disl+0.159
 Cr+0.124
 Joey+0.121
 Twe+0.118
 Fro+0.117
Neg logit contributions
es-0.075
 again-0.062
m-0.059
le-0.059
 on-0.059
Token and
Token ID290
Feature activation-8.09e+00

Pos logit contributions
 disl+0.067
 Cr+0.051
 Joey+0.049
 Fro+0.049
 Twe+0.048
Neg logit contributions
es-0.034
 again-0.031
m-0.030
le-0.030
 on-0.029
Token her
Token ID607
Feature activation-6.65e+00

Pos logit contributions
 disl+0.107
 Cr+0.069
 majesty+0.068
icol+0.066
 pleasure+0.065
Neg logit contributions
es-0.099
 again-0.097
 on-0.095
y-0.089
m-0.086
Token was
Token ID373
Feature activation-7.78e+00

Pos logit contributions
 disl+0.075
 Cr+0.057
 Joey+0.054
 Fro+0.053
 Twe+0.053
Neg logit contributions
es-0.038
 again-0.035
 on-0.033
le-0.032
m-0.032
Token surprised
Token ID6655
Feature activation-7.23e+00

Pos logit contributions
 disl+0.122
 Cr+0.089
 majesty+0.085
icol+0.083
 Joey+0.080
Neg logit contributions
 again-0.079
 on-0.078
es-0.075
m-0.069
y-0.065
Token,
Token ID11
Feature activation-6.57e+00

Pos logit contributions
 disl+0.132
 Cr+0.104
 Joey+0.101
 Fro+0.099
 Twe+0.098
Neg logit contributions
es-0.049
 again-0.039
 on-0.038
le-0.038
m-0.038
Token but
Token ID475
Feature activation-7.94e+00

Pos logit contributions
 disl+0.129
 majesty+0.102
 Cr+0.102
 Majesty+0.098
 Fro+0.097
Neg logit contributions
 again-0.036
 on-0.034
es-0.030
 and-0.028
m-0.026
Token asked
Token ID1965
Feature activation-5.65e+00

Pos logit contributions
 disl+0.124
 Cr+0.087
 majesty+0.086
icol+0.083
 pleasure+0.082
Neg logit contributions
 again-0.079
es-0.077
 on-0.077
m-0.068
ing-0.066
Token the
Token ID262
Feature activation-8.80e+00

Pos logit contributions
 disl+0.073
 Cr+0.051
 Joey+0.047
 Fro+0.047
 Twe+0.046
Neg logit contributions
es-0.068
 again-0.064
 on-0.062
le-0.061
m-0.061
Token old
Token ID1468
Feature activation-9.35e+00

Pos logit contributions
 disl+0.133
 Cr+0.098
 Joey+0.094
 Fro+0.093
 pleasure+0.091
Neg logit contributions
es-0.092
le-0.077
 again-0.075
y-0.075
 on-0.074
Token man
Token ID582
Feature activation-2.89e+00

Pos logit contributions
 disl+0.154
 Cr+0.117
 Fro+0.110
 majesty+0.110
 Joey+0.110
Neg logit contributions
 again-0.076
es-0.075
 on-0.069
m-0.067
y-0.067
Token if
Token ID611
Feature activation-6.46e+00

Pos logit contributions
 disl+0.044
 Cr+0.033
 Joey+0.032
 Fro+0.031
 Twe+0.030
Neg logit contributions
es-0.027
le-0.023
ymes-0.023
m-0.023
 again-0.023
Token he
Token ID339
Feature activation-4.81e+00

Pos logit contributions
 disl+0.102
 majesty+0.072
icol+0.072
 Cr+0.071
 pleasure+0.070
Neg logit contributions
 again-0.060
es-0.060
 on-0.059
ing-0.052
m-0.052
Token was
Token ID373
Feature activation-6.48e+00

Pos logit contributions
 disl+0.068
 Cr+0.049
 Joey+0.049
 Fro+0.047
 Twe+0.047
Neg logit contributions
es-0.047
ices-0.043
 again-0.043
ymes-0.043
ing-0.043
Token with
Token ID351
Feature activation-1.00e+01

Pos logit contributions
 disl+0.172
 Cr+0.136
 Joey+0.129
 Fro+0.128
 Twe+0.128
Neg logit contributions
es-0.058
 again-0.048
m-0.047
le-0.046
y-0.046
Token it
Token ID340
Feature activation-5.57e+00

Pos logit contributions
 disl+0.119
 Cr+0.079
 Fro+0.074
 Joey+0.072
 majesty+0.071
Neg logit contributions
es-0.132
 again-0.129
 on-0.124
le-0.117
y-0.115
Token,
Token ID11
Feature activation-8.76e+00

Pos logit contributions
 disl+0.076
 Twe+0.060
 Cr+0.058
 my+0.057
 your+0.057
Neg logit contributions
es-0.051
ices-0.050
ymes-0.047
m-0.045
ities-0.044
Token but
Token ID475
Feature activation-1.02e+01

Pos logit contributions
 disl+0.153
 Cr+0.117
 Joey+0.111
 Fro+0.111
 majesty+0.110
Neg logit contributions
es-0.065
 again-0.063
 on-0.060
le-0.054
y-0.053
Token we
Token ID356
Feature activation-7.84e+00

Pos logit contributions
 disl+0.132
icol+0.085
 Cr+0.085
LL+0.080
APP+0.080
Neg logit contributions
 again-0.125
es-0.123
 on-0.122
y-0.108
m-0.107
Token can
Token ID460
Feature activation-1.02e+01

Pos logit contributions
 disl+0.127
 Cr+0.097
icol+0.096
 majesty+0.092
 Fro+0.092
Neg logit contributions
es-0.066
 again-0.064
 on-0.063
le-0.060
y-0.059
Token learn
Token ID2193
Feature activation-8.51e+00

Pos logit contributions
 disl+0.144
 Cr+0.104
 Fro+0.099
 Joey+0.097
icol+0.097
Neg logit contributions
 again-0.107
es-0.107
 on-0.100
le-0.100
m-0.096
Token about
Token ID546
Feature activation-8.28e+00

Pos logit contributions
 disl+0.123
 Cr+0.088
 Twe+0.084
 Joey+0.080
 Fro+0.079
Neg logit contributions
es-0.085
m-0.082
le-0.079
y-0.077
ices-0.077
Token it
Token ID340
Feature activation-4.45e+00

Pos logit contributions
 disl+0.118
 Cr+0.086
 Fro+0.082
 Joey+0.082
 majesty+0.078
Neg logit contributions
es-0.088
 again-0.084
 on-0.079
le-0.075
y-0.074
Token,"
Token ID553
Feature activation-8.66e+00

Pos logit contributions
 disl+0.067
 Cr+0.049
 your+0.049
 my+0.049
 Twe+0.049
Neg logit contributions
ices-0.034
m-0.033
ud-0.032
ymes-0.031
es-0.030
Token she
Token ID673
Feature activation-7.53e+00

Pos logit contributions
 disl+0.124
icol+0.090
 majesty+0.089
 pleasure+0.087
 Majesty+0.085
Neg logit contributions
 again-0.091
es-0.090
 on-0.086
m-0.081
y-0.078
Token on
Token ID319
Feature activation-1.09e+01

Pos logit contributions
 disl+0.071
 Cr+0.056
 Joey+0.055
 Twe+0.054
 Fro+0.053
Neg logit contributions
es-0.021
 again-0.018
m-0.018
ices-0.017
ymes-0.017
Token it
Token ID340
Feature activation-6.68e+00

Pos logit contributions
 disl+0.134
 Cr+0.090
 Fro+0.083
 majesty+0.082
 Joey+0.080
Neg logit contributions
es-0.138
 again-0.135
 on-0.131
le-0.126
y-0.125
Token!
Token ID0
Feature activation-9.47e+00

Pos logit contributions
 disl+0.127
 Cr+0.101
 Joey+0.099
 Twe+0.097
 Fro+0.096
Neg logit contributions
es-0.035
m-0.028
 again-0.028
le-0.028
ymes-0.027
Token
Token ID220
Feature activation-1.07e+01

Pos logit contributions
 disl+0.138
 majesty+0.093
 Majesty+0.088
icol+0.087
 Cr+0.086
Neg logit contributions
es-0.100
 again-0.097
 on-0.090
m-0.084
Today-0.083
Token
Token ID198
Feature activation-9.18e+00

Pos logit contributions
 disl+0.187
 Cr+0.141
icol+0.139
 majesty+0.135
 Majesty+0.133
Neg logit contributions
es-0.093
 again-0.079
 on-0.076
m-0.072
ing-0.071
Token
Token ID198
Feature activation-8.83e+00

Pos logit contributions
 disl+0.148
 Cr+0.108
 majesty+0.105
icol+0.104
 Majesty+0.102
Neg logit contributions
es-0.084
 again-0.078
m-0.074
 on-0.073
Today-0.069
TokenJ
Token ID41
Feature activation-8.82e+00

Pos logit contributions
 disl+0.147
 Cr+0.111
 majesty+0.107
 Joey+0.105
icol+0.105
Neg logit contributions
es-0.073
 again-0.066
 on-0.062
m-0.062
y-0.060
Tokenill
Token ID359
Feature activation-5.20e+00

Pos logit contributions
 disl+0.152
 Cr+0.117
 Joey+0.112
 Fro+0.111
 Twe+0.110
Neg logit contributions
es-0.068
 again-0.062
 on-0.058
y-0.057
m-0.057
Token quickly
Token ID2952
Feature activation-5.39e+00

Pos logit contributions
 disl+0.084
 Cr+0.063
 Joey+0.061
 Fro+0.060
 Twe+0.059
Neg logit contributions
es-0.044
 again-0.039
 on-0.038
m-0.037
le-0.037
Token glued
Token ID39783
Feature activation-3.01e+00

Pos logit contributions
 disl+0.084
 Cr+0.062
 Joey+0.059
 Fro+0.058
 Twe+0.057
Neg logit contributions
es-0.051
 again-0.047
 on-0.045
le-0.044
y-0.044
Token the
Token ID262
Feature activation-6.53e+00

Pos logit contributions
 disl+0.033
 Cr+0.021
 Joey+0.019
 Fro+0.019
 Twe+0.019
Neg logit contributions
es-0.042
 again-0.039
le-0.038
m-0.038
 on-0.038
Token smiled
Token ID13541
Feature activation-7.27e+00

Pos logit contributions
 disl+0.061
 Joey+0.046
 Cr+0.044
 J+0.044
 Fro+0.044
Neg logit contributions
es-0.044
ymes-0.041
ices-0.041
packs-0.039
le-0.039
Token and
Token ID290
Feature activation-9.06e+00

Pos logit contributions
 disl+0.136
 Cr+0.110
 Joey+0.109
 Twe+0.106
 Fro+0.105
Neg logit contributions
es-0.040
ymes-0.031
ices-0.031
m-0.029
boards-0.029
Token said
Token ID531
Feature activation-6.13e+00

Pos logit contributions
 disl+0.159
 Cr+0.120
 majesty+0.116
 Majesty+0.113
 Fro+0.112
Neg logit contributions
es-0.073
 again-0.071
 on-0.069
y-0.057
ing-0.057
Token,
Token ID11
Feature activation-7.36e+00

Pos logit contributions
 disl+0.114
 Cr+0.089
 Fro+0.086
 majesty+0.085
 Joey+0.084
Neg logit contributions
es-0.043
 again-0.041
 on-0.038
ing-0.034
y-0.032
Token "
Token ID366
Feature activation-7.92e+00

Pos logit contributions
 disl+0.092
 Cr+0.062
 Fro+0.057
 majesty+0.057
 Joey+0.056
Neg logit contributions
es-0.091
 again-0.089
 on-0.086
m-0.082
y-0.081
TokenYes
Token ID5297
Feature activation-7.97e+00

Pos logit contributions
 disl+0.123
 Cr+0.091
 majesty+0.088
 Fro+0.087
 Joey+0.087
Neg logit contributions
es-0.072
 again-0.069
m-0.066
y-0.065
 on-0.065
Token,
Token ID11
Feature activation-8.84e+00

Pos logit contributions
 disl+0.150
 Cr+0.118
 Fro+0.112
 Joey+0.109
 majesty+0.108
Neg logit contributions
 again-0.051
es-0.050
 on-0.045
le-0.042
ing-0.041
Token it
Token ID340
Feature activation-5.47e+00

Pos logit contributions
 disl+0.115
 Cr+0.081
 Fro+0.075
 Joey+0.072
 majesty+0.071
Neg logit contributions
es-0.103
 again-0.103
 on-0.099
le-0.094
ing-0.093
Token is
Token ID318
Feature activation-7.50e+00

Pos logit contributions
 disl+0.083
 Cr+0.058
 Joey+0.057
 majesty+0.057
 Fro+0.055
Neg logit contributions
es-0.050
 again-0.047
 on-0.045
m-0.045
y-0.044
Token.
Token ID13
Feature activation-7.96e+00

Pos logit contributions
 disl+0.130
 Cr+0.102
 Fro+0.097
 majesty+0.093
 Joey+0.091
Neg logit contributions
es-0.057
 again-0.057
 on-0.057
y-0.050
le-0.049
Token Did
Token ID7731
Feature activation-8.33e+00

Pos logit contributions
 disl+0.103
 Fro+0.068
 majesty+0.066
 Cr+0.066
 Majesty+0.064
Neg logit contributions
es-0.085
 again-0.080
 on-0.077
Will-0.075
ing-0.074
Token that
Token ID326
Feature activation-8.98e+00

Pos logit contributions
 disl+0.167
 Cr+0.130
 Fro+0.124
 Joey+0.123
 majesty+0.122
Neg logit contributions
es-0.067
 again-0.063
 on-0.059
y-0.056
le-0.055
Token the
Token ID262
Feature activation-1.07e+01

Pos logit contributions
 disl+0.127
 Cr+0.090
 majesty+0.086
 Fro+0.086
icol+0.083
Neg logit contributions
es-0.097
 again-0.096
 on-0.092
m-0.084
y-0.084
Token bad
Token ID2089
Feature activation-9.81e+00

Pos logit contributions
 disl+0.156
 Cr+0.114
 Joey+0.108
 Fro+0.107
 Twe+0.105
Neg logit contributions
es-0.109
 again-0.100
 on-0.096
le-0.095
m-0.094
Token rh
Token ID9529
Feature activation-1.01e+01

Pos logit contributions
 disl+0.153
 Cr+0.116
 Fro+0.110
 Joey+0.108
 Twe+0.107
Neg logit contributions
es-0.087
 again-0.085
 on-0.080
le-0.077
y-0.077
Tokenin
Token ID259
Feature activation-8.44e+00

Pos logit contributions
 disl+0.177
 Cr+0.144
 Twe+0.136
 Joey+0.135
 Fro+0.134
Neg logit contributions
es-0.054
 again-0.050
packs-0.046
boards-0.046
 on-0.045
Tokenoc
Token ID420
Feature activation-1.96e+01

Pos logit contributions
 disl+0.130
 Cr+0.097
 Joey+0.092
 Fro+0.091
 Twe+0.090
Neg logit contributions
es-0.079
 again-0.072
 on-0.069
le-0.068
m-0.067
Tokeneros
Token ID27498
Feature activation-5.42e+00

Pos logit contributions
 disl+0.233
 Cr+0.155
 Joey+0.144
 Fro+0.142
 Twe+0.138
Neg logit contributions
es-0.256
 again-0.242
 on-0.233
le-0.231
m-0.230
Token was
Token ID373
Feature activation-9.62e+00

Pos logit contributions
 disl+0.085
 Cr+0.063
 Joey+0.061
 Fro+0.060
 Twe+0.059
Neg logit contributions
es-0.048
 again-0.043
m-0.041
le-0.041
 on-0.041
Token now
Token ID783
Feature activation-9.06e+00

Pos logit contributions
 disl+0.146
 Cr+0.107
icol+0.103
 majesty+0.103
 Fro+0.102
Neg logit contributions
 again-0.100
 on-0.099
es-0.090
m-0.083
y-0.080
Token nice
Token ID3621
Feature activation-5.90e+00

Pos logit contributions
 disl+0.136
 Cr+0.102
 Fro+0.096
 Joey+0.094
 majesty+0.093
Neg logit contributions
es-0.088
 again-0.085
 on-0.082
y-0.077
m-0.077
Token.
Token ID13
Feature activation-8.76e+00

Pos logit contributions
 disl+0.106
 Joey+0.084
 Cr+0.083
 Fro+0.081
 pleasure+0.080
Neg logit contributions
es-0.038
le-0.032
ymes-0.031
m-0.030
ices-0.029
Token give
Token ID1577
Feature activation-1.08e+01

Pos logit contributions
 disl+0.170
icol+0.137
 Cr+0.133
 pleasure+0.124
 majesty+0.123
Neg logit contributions
 again-0.116
 on-0.114
le-0.104
es-0.104
 and-0.099
Token to
Token ID284
Feature activation-9.64e+00

Pos logit contributions
 disl+0.151
 Cr+0.108
 majesty+0.103
 Fro+0.101
icol+0.100
Neg logit contributions
es-0.117
 again-0.115
 on-0.112
le-0.106
y-0.103
Token the
Token ID262
Feature activation-1.11e+01

Pos logit contributions
 disl+0.130
icol+0.103
LL+0.101
 Cr+0.097
 Fre+0.093
Neg logit contributions
 again-0.099
es-0.093
 on-0.091
 and-0.084
my-0.081
Token rh
Token ID9529
Feature activation-1.09e+01

Pos logit contributions
 disl+0.171
 Cr+0.127
 Joey+0.121
 Fro+0.120
 Twe+0.119
Neg logit contributions
es-0.105
 again-0.094
le-0.091
 on-0.090
y-0.089
Tokenin
Token ID259
Feature activation-7.94e+00

Pos logit contributions
 disl+0.186
 Cr+0.151
 Fro+0.142
 Twe+0.140
 majesty+0.139
Neg logit contributions
es-0.061
 again-0.056
 on-0.056
boards-0.051
Today-0.051
Tokenoc
Token ID420
Feature activation-2.13e+01

Pos logit contributions
 disl+0.132
 Cr+0.099
 Joey+0.095
 Fro+0.093
 majesty+0.093
Neg logit contributions
es-0.067
 again-0.063
 on-0.060
y-0.057
le-0.057
Tokeneros
Token ID27498
Feature activation-6.56e+00

Pos logit contributions
 disl+0.249
 Cr+0.164
 Joey+0.153
 Fro+0.151
 Twe+0.146
Neg logit contributions
es-0.281
 again-0.267
 on-0.255
le-0.253
y-0.251
Token.
Token ID13
Feature activation-9.04e+00

Pos logit contributions
 disl+0.115
 Cr+0.089
 Joey+0.084
 Fro+0.084
 majesty+0.083
Neg logit contributions
es-0.049
 again-0.045
 on-0.042
le-0.040
y-0.040
Token Lily
Token ID20037
Feature activation-4.85e+00

Pos logit contributions
 disl+0.120
 majesty+0.078
 Cr+0.075
 talented+0.074
 pleasure+0.074
Neg logit contributions
es-0.101
 again-0.098
 on-0.091
y-0.087
m-0.087
Token walked
Token ID6807
Feature activation-4.41e+00

Pos logit contributions
 disl+0.087
 Cr+0.069
 Joey+0.065
 pleasure+0.064
 Twe+0.064
Neg logit contributions
es-0.035
 again-0.032
 on-0.029
y-0.028
le-0.028
Token to
Token ID284
Feature activation-7.65e+00

Pos logit contributions
 disl+0.062
 Cr+0.051
 Joey+0.050
 Fro+0.049
 J+0.047
Neg logit contributions
es-0.042
ymes-0.038
ities-0.036
ices-0.036
le-0.036
Token quiet
Token ID5897
Feature activation-1.60e+01

Pos logit contributions
es+0.050
 again+0.049
 on+0.046
y+0.044
le+0.043
Neg logit contributions
 disl-0.106
 Cr-0.080
 Joey-0.075
 Fro-0.075
 Twe-0.074
Token compared
Token ID3688
Feature activation-1.39e+01

Pos logit contributions
 disl+0.322
 Cr+0.257
 Joey+0.249
 Fro+0.247
 Twe+0.244
Neg logit contributions
es-0.075
 again-0.062
 on-0.056
le-0.055
m-0.054
Token to
Token ID284
Feature activation-1.12e+01

Pos logit contributions
 disl+0.205
 Cr+0.150
 Joey+0.142
 Fro+0.141
 Twe+0.138
Neg logit contributions
es-0.139
 again-0.130
 on-0.124
le-0.122
m-0.121
Token the
Token ID262
Feature activation-1.24e+01

Pos logit contributions
 disl+0.146
 Cr+0.108
 Fro+0.097
 Joey+0.096
 Twe+0.095
Neg logit contributions
es-0.130
 again-0.126
 on-0.123
le-0.117
y-0.115
Token noisy
Token ID31210
Feature activation-1.13e+01

Pos logit contributions
 disl+0.186
 Cr+0.134
 Joey+0.130
 Fro+0.127
 majesty+0.126
Neg logit contributions
es-0.125
 again-0.111
le-0.107
m-0.106
y-0.105
Token se
Token ID384
Feature activation-1.99e+01

Pos logit contributions
 disl+0.180
 Cr+0.132
 Joey+0.128
 Fro+0.125
 Twe+0.124
Neg logit contributions
es-0.104
 again-0.091
m-0.088
le-0.088
 on-0.087
Tokenag
Token ID363
Feature activation-1.17e+01

Pos logit contributions
 disl+0.329
 Cr+0.260
 Joey+0.252
 Fro+0.248
 Twe+0.246
Neg logit contributions
es-0.160
le-0.148
 again-0.145
y-0.139
les-0.137
Tokenull
Token ID724
Feature activation-4.67e+00

Pos logit contributions
 disl+0.190
 Cr+0.148
 pleasure+0.139
 Twe+0.138
icol+0.138
Neg logit contributions
es-0.106
y-0.094
 on-0.093
 again-0.092
le-0.089
Tokens
Token ID82
Feature activation-9.84e+00

Pos logit contributions
 disl+0.089
 Cr+0.069
 Joey+0.067
 Fro+0.067
 Twe+0.066
Neg logit contributions
es-0.027
 again-0.023
 on-0.021
le-0.021
m-0.021
Token outside
Token ID2354
Feature activation-8.91e+00

Pos logit contributions
 disl+0.175
 Cr+0.131
 Joey+0.130
 pleasure+0.129
 majesty+0.127
Neg logit contributions
es-0.065
le-0.057
m-0.055
 again-0.053
ymes-0.053
Token.
Token ID13
Feature activation-1.02e+01

Pos logit contributions
 disl+0.168
 Cr+0.132
 Joey+0.129
 Fro+0.126
 Twe+0.126
Neg logit contributions
es-0.052
 again-0.042
le-0.041
m-0.040
 on-0.038
Token he
Token ID339
Feature activation-8.32e+00

Pos logit contributions
 disl+0.184
 Cr+0.134
 Fro+0.125
 majesty+0.124
 Joey+0.123
Neg logit contributions
es-0.119
 again-0.114
 on-0.110
y-0.104
le-0.104
Token would
Token ID561
Feature activation-9.38e+00

Pos logit contributions
 disl+0.141
 Cr+0.108
 Joey+0.103
 Fro+0.102
 Twe+0.101
Neg logit contributions
es-0.066
 again-0.060
 on-0.056
le-0.055
m-0.055
Token take
Token ID1011
Feature activation-8.43e+00

Pos logit contributions
 disl+0.127
 Cr+0.091
 Fro+0.084
 Joey+0.084
 Twe+0.082
Neg logit contributions
es-0.106
 again-0.100
 on-0.097
le-0.095
y-0.093
Token the
Token ID262
Feature activation-9.85e+00

Pos logit contributions
 disl+0.111
 Cr+0.077
 Joey+0.072
 Fro+0.071
 Twe+0.069
Neg logit contributions
es-0.100
 again-0.094
 on-0.091
le-0.089
m-0.088
Token av
Token ID1196
Feature activation-1.19e+01

Pos logit contributions
 disl+0.141
 Cr+0.103
 Joey+0.102
 pleasure+0.101
 Fro+0.098
Neg logit contributions
es-0.107
 again-0.089
le-0.087
m-0.087
y-0.086
Tokenoc
Token ID420
Feature activation-2.14e+01

Pos logit contributions
 disl+0.169
 Cr+0.127
 Joey+0.119
 Fro+0.117
 Twe+0.117
Neg logit contributions
es-0.117
 again-0.111
m-0.104
 on-0.104
le-0.102
Tokenados
Token ID22484
Feature activation-4.04e+00

Pos logit contributions
 disl+0.325
 Cr+0.240
 Joey+0.227
 Fro+0.227
 Twe+0.221
Neg logit contributions
es-0.208
 again-0.192
 on-0.182
le-0.180
y-0.179
Token and
Token ID290
Feature activation-9.13e+00

Pos logit contributions
 disl+0.057
 Cr+0.044
 Joey+0.044
 Fro+0.041
 Twe+0.041
Neg logit contributions
es-0.038
le-0.034
ymes-0.034
m-0.033
ices-0.033
Token scatter
Token ID41058
Feature activation-6.61e+00

Pos logit contributions
 disl+0.136
 Cr+0.100
 Fro+0.096
 Joey+0.092
 majesty+0.092
Neg logit contributions
es-0.091
 again-0.086
 on-0.084
y-0.077
le-0.077
Token them
Token ID606
Feature activation-5.69e+00

Pos logit contributions
 disl+0.093
 Cr+0.069
 Joey+0.066
 Twe+0.063
 Fro+0.063
Neg logit contributions
es-0.070
 again-0.064
m-0.062
le-0.061
 on-0.060
Token around
Token ID1088
Feature activation-8.31e+00

Pos logit contributions
 disl+0.093
 Joey+0.073
 Cr+0.072
 Twe+0.069
 Fro+0.068
Neg logit contributions
es-0.040
m-0.037
ices-0.036
ymes-0.036
le-0.035
Token am
Token ID716
Feature activation-1.03e+01

Pos logit contributions
 disl+0.147
 Cr+0.112
 Joey+0.105
 Fro+0.104
 majesty+0.103
Neg logit contributions
es-0.083
 again-0.083
 on-0.079
le-0.077
m-0.076
Token taking
Token ID2263
Feature activation-1.05e+01

Pos logit contributions
 disl+0.152
icol+0.115
 Cr+0.109
 Fro+0.099
 Joey+0.098
Neg logit contributions
 on-0.114
 again-0.106
es-0.099
 and-0.090
.-0.089
Token the
Token ID262
Feature activation-1.10e+01

Pos logit contributions
 disl+0.139
 Cr+0.097
 Joey+0.090
 Fro+0.090
 majesty+0.087
Neg logit contributions
es-0.125
 again-0.119
 on-0.117
le-0.112
y-0.108
Token rh
Token ID9529
Feature activation-1.08e+01

Pos logit contributions
 disl+0.158
 Cr+0.115
 Joey+0.111
 Fro+0.109
 Twe+0.108
Neg logit contributions
es-0.117
 again-0.103
le-0.099
m-0.098
y-0.097
Tokenin
Token ID259
Feature activation-8.88e+00

Pos logit contributions
 disl+0.186
 Cr+0.152
 Twe+0.144
 Fro+0.144
 Joey+0.142
Neg logit contributions
es-0.061
 again-0.057
 on-0.051
boards-0.050
Today-0.049
Tokenoc
Token ID420
Feature activation-2.19e+01

Pos logit contributions
 disl+0.130
 Cr+0.097
 Joey+0.091
 Fro+0.090
 Twe+0.090
Neg logit contributions
es-0.089
 again-0.080
le-0.077
m-0.076
 on-0.076
Tokeneros
Token ID27498
Feature activation-6.73e+00

Pos logit contributions
 disl+0.258
 Cr+0.170
 Joey+0.158
 Fro+0.156
 Twe+0.150
Neg logit contributions
es-0.287
 again-0.273
 on-0.261
le-0.259
y-0.258
Token to
Token ID284
Feature activation-1.06e+01

Pos logit contributions
 disl+0.110
 Cr+0.083
 Joey+0.079
 Fro+0.078
 Twe+0.077
Neg logit contributions
es-0.057
 again-0.052
 on-0.049
le-0.049
m-0.048
Token a
Token ID257
Feature activation-8.28e+00

Pos logit contributions
 disl+0.150
icol+0.108
 Cr+0.102
 Madd+0.099
APP+0.099
Neg logit contributions
 again-0.111
 on-0.106
es-0.100
 and-0.093
 later-0.090
Token new
Token ID649
Feature activation-8.96e+00

Pos logit contributions
 disl+0.116
 Cr+0.083
 Joey+0.078
 Fro+0.077
 majesty+0.075
Neg logit contributions
es-0.088
 again-0.086
 on-0.082
le-0.079
y-0.079
Token home
Token ID1363
Feature activation-6.03e+00

Pos logit contributions
 disl+0.134
 Cr+0.099
 Joey+0.094
 Fro+0.092
 Twe+0.091
Neg logit contributions
es-0.089
 again-0.082
 on-0.078
le-0.078
m-0.077