TOP ACTIVATIONS
MAX = 0.147

his head out of his bur row and saw something new
who lived in his cozy bur row . He loved to
to venture out from his bur row and explore the forest
N ina was panic - str icken . She screamed for
Benny lived in a cozy bur row with his family .
mom called out , " Mill ie , come home !"
was struggling . Mill ie tried to reach the
there ?", asked the wood pe cker . The
should never come close to an owl again !".
the sunshine . Mill ie was so excited that
fluffy and lived in a bur row in the forest .
cry coming from outside his bur row . He
" Who 's there ?" Tim my asked .
" What happened ?" Tim my asked .
mist and into their cozy bur rows . The end .
of friendly ducks came to Gig i 's rescue . They
, " What happened , Gig i ? Are you okay
able to escape from his bur row and play in the
. One day , Stri pe y saw his friend ,
peek ed out of his bur row . He

MIN ACTIVATIONS
MIN = -0.109

The kids played a lot of fun and interesting
were so colorful and the stories were so fun . She
Da isy started making videos and put them up on
characters and watching the funny video . She went to the
a funny face . The sandwiches are spicy ! They have
She played games and watched videos on the computer all day
and arrows . They made them from sticks and strings and
They shared food and laughed a lot . The
cheered very loudly because the dance was so good . Everyone
taught her friends and her sisters how to build them too
the pictures and said the names of the things she saw
funny animals and the silly jokes . But sometimes they wanted
diamond . They said the names of the shapes and looked
a game . She won a prize ! It was a
talked to them and made them talk back .
dolls ' hands and made them say , " I do
fan . They pretend the shapes are flying . They have
. They both think their shapes are good . But they
pushed the buttons and the images changed back to the way
my and daddy and made them smile . One day ,

INTERVAL 0.083 - 0.147
CONTAINS 0.026%

for him . Tim my started to complain to
eating their ice cream , Tim my 's mom told him
" What is it , Mum ?" she asked .
hoped to find another rare rad ish . They hoped to
it forever . Tim my played with his ball

INTERVAL 0.019 - 0.083
CONTAINS 19.719%

that cared for them . The family was very happy ,
scared of the farmer . But eventually , they learned to
saw Lily . He was surprised and said , " Who
a talking bird . The bird said , " Hi ,
L ily shrugged again and said , " No

INTERVAL -0.045 - 0.019
CONTAINS 78.086%

felt like he was going to be discovered .
." Lily smiled and said , " I love you too
sat down at a big table . They had delicious food
again . She hoped her eyes would get better soon .
and a big paper . He dipped his brush in red

INTERVAL -0.109 - -0.045
CONTAINS 2.170%

the mess went away and everything was clean again . The
animals and fill in the numbers . Ana was so excited
swings and slides . She couldn 't wait to play ,
guitar , imagining all the music she could make . She
equipment to cook up some pretend food . She measured out
Token his
Token ID465
Feature activation+2.12e-02

Pos logit contributions
bur+0.118
ppa+0.116
rying+0.116
gie+0.114
ior+0.114
Neg logit contributions
 vows-0.070
 prize-0.067
 great-0.064
 trophy-0.061
 are-0.060
Token head
Token ID1182
Feature activation+1.40e-02

Pos logit contributions
rying+0.044
bur+0.044
ppa+0.043
i+0.041
ind+0.041
Neg logit contributions
 vows-0.035
 prize-0.031
 trophy-0.031
 contest-0.030
apy-0.028
Token out
Token ID503
Feature activation+5.47e-03

Pos logit contributions
bur+0.027
rying+0.026
ppa+0.026
ind+0.025
i+0.025
Neg logit contributions
 vows-0.025
 prize-0.022
 contest-0.022
 trophy-0.022
cakes-0.021
Token of
Token ID286
Feature activation+2.67e-02

Pos logit contributions
bur+0.011
rying+0.011
ppa+0.011
i+0.011
ind+0.011
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.008
Token his
Token ID465
Feature activation+3.33e-02

Pos logit contributions
ppa+0.061
rying+0.061
bur+0.060
ety+0.058
i+0.058
Neg logit contributions
 vows-0.037
 prize-0.035
 contest-0.033
 trophy-0.033
apy-0.031
Token bur
Token ID4356
Feature activation+1.24e-01

Pos logit contributions
rying+0.066
bur+0.066
ppa+0.065
ety+0.061
i+0.060
Neg logit contributions
 vows-0.058
 prize-0.053
 trophy-0.052
 contest-0.051
apy-0.048
Tokenrow
Token ID808
Feature activation+5.43e-02

Pos logit contributions
ior+0.148
ppa+0.129
ety+0.129
ind+0.124
 Owl+0.124
Neg logit contributions
ades-0.243
uits-0.238
 vows-0.221
ade-0.217
 are-0.213
Token and
Token ID290
Feature activation+2.81e-02

Pos logit contributions
bur+0.116
ppa+0.113
ind+0.113
rying+0.113
ior+0.111
Neg logit contributions
 vows-0.079
case-0.071
cakes-0.071
 prize-0.069
 contest-0.069
Token saw
Token ID2497
Feature activation+2.13e-02

Pos logit contributions
bur+0.056
rying+0.055
ppa+0.054
ind+0.054
ety+0.052
Neg logit contributions
 vows-0.049
 prize-0.043
apy-0.042
 trophy-0.042
 contest-0.041
Token something
Token ID1223
Feature activation-2.76e-02

Pos logit contributions
bur+0.049
rying+0.049
ppa+0.048
ind+0.046
ety+0.046
Neg logit contributions
 vows-0.030
 prize-0.026
 trophy-0.025
 contest-0.025
apy-0.025
Token new
Token ID649
Feature activation+1.60e-02

Pos logit contributions
 vows+0.046
 Prize+0.039
 contest+0.038
 prize+0.038
cakes+0.038
Neg logit contributions
rying-0.054
i-0.053
bur-0.053
ind-0.052
ppa-0.051
Token who
Token ID508
Feature activation+6.54e-03

Pos logit contributions
bur+0.091
rying+0.087
ppa+0.085
ior+0.084
ind+0.081
Neg logit contributions
 contest-0.081
 vows-0.080
 prize-0.078
 trophy-0.077
case-0.076
Token lived
Token ID5615
Feature activation+2.95e-02

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
i+0.014
ind+0.014
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.008
 trophy-0.008
apy-0.008
Token in
Token ID287
Feature activation+4.26e-03

Pos logit contributions
bur+0.059
ppa+0.058
ior+0.058
gie+0.056
i+0.056
Neg logit contributions
 vows-0.046
 contest-0.045
 prize-0.043
 trophy-0.042
apy-0.041
Token his
Token ID465
Feature activation+3.98e-02

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.010
i+0.009
ind+0.009
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token cozy
Token ID37438
Feature activation+7.81e-02

Pos logit contributions
rying+0.082
ppa+0.078
bur+0.077
gie+0.072
ener+0.072
Neg logit contributions
 vows-0.068
 prize-0.063
 contest-0.062
 tea-0.060
 trophy-0.060
Token bur
Token ID4356
Feature activation+1.22e-01

Pos logit contributions
rying+0.140
bur+0.131
ppa+0.130
eking+0.123
ior+0.119
Neg logit contributions
 vows-0.147
 tea-0.137
 prize-0.135
 team-0.134
 lot-0.132
Tokenrow
Token ID808
Feature activation+7.41e-02

Pos logit contributions
ior+0.159
fred+0.130
 Tooth+0.130
ppa+0.129
bur+0.128
Neg logit contributions
ades-0.233
 vows-0.214
uits-0.214
ade-0.206
case-0.201
Token.
Token ID13
Feature activation+1.72e-02

Pos logit contributions
bur+0.171
ior+0.169
ppa+0.163
rying+0.159
gie+0.159
Neg logit contributions
 vows-0.089
case-0.088
 contest-0.082
 trophy-0.082
 prize-0.080
Token He
Token ID679
Feature activation+2.82e-02

Pos logit contributions
rying+0.039
bur+0.038
ppa+0.037
i+0.036
ind+0.036
Neg logit contributions
 vows-0.025
 prize-0.022
 contest-0.022
 trophy-0.022
cakes-0.021
Token loved
Token ID6151
Feature activation+2.91e-02

Pos logit contributions
rying+0.068
bur+0.068
ppa+0.065
ind+0.062
ior+0.062
Neg logit contributions
 vows-0.038
 prize-0.030
 contest-0.029
apy-0.029
 trophy-0.029
Token to
Token ID284
Feature activation+2.62e-04

Pos logit contributions
ppa+0.063
rying+0.062
bur+0.061
cker+0.059
ener+0.058
Neg logit contributions
 vows-0.044
 prize-0.041
 trophy-0.039
 contest-0.039
 tea-0.038
Token to
Token ID284
Feature activation-1.47e-02

Pos logit contributions
bur+0.063
ppa+0.062
ind+0.061
rying+0.061
ior+0.059
Neg logit contributions
 vows-0.039
 prize-0.036
 contest-0.035
 trophy-0.035
 joke-0.033
Token venture
Token ID13189
Feature activation+4.52e-02

Pos logit contributions
 vows+0.022
cakes+0.019
 prize+0.019
 trophy+0.019
 contest+0.019
Neg logit contributions
bur-0.032
rying-0.031
ppa-0.030
i-0.030
ind-0.029
Token out
Token ID503
Feature activation+4.81e-02

Pos logit contributions
ppa+0.103
bur+0.101
gie+0.097
ior+0.097
ind+0.097
Neg logit contributions
 contest-0.062
 prize-0.060
 tea-0.058
 vows-0.057
 are-0.053
Token from
Token ID422
Feature activation+5.70e-02

Pos logit contributions
ppa+0.120
bur+0.118
ior+0.113
ind+0.111
ety+0.110
Neg logit contributions
 contest-0.055
 prize-0.052
 are-0.051
 tea-0.051
apy-0.049
Token his
Token ID465
Feature activation+4.15e-02

Pos logit contributions
ppa+0.153
bur+0.137
i+0.135
rying+0.135
ety+0.135
Neg logit contributions
 contest-0.065
 prize-0.064
 tea-0.058
 festival-0.056
 trophy-0.055
Token bur
Token ID4356
Feature activation+1.22e-01

Pos logit contributions
rying+0.072
ppa+0.071
bur+0.067
cker+0.066
ior+0.066
Neg logit contributions
 prize-0.080
 vows-0.079
 tea-0.075
 contest-0.074
 third-0.074
Tokenrow
Token ID808
Feature activation+6.77e-02

Pos logit contributions
ior+0.166
ppa+0.145
 bruised+0.141
pless+0.138
eled+0.137
Neg logit contributions
ades-0.214
ade-0.208
uits-0.208
 parties-0.189
br-0.187
Token and
Token ID290
Feature activation+4.05e-02

Pos logit contributions
ior+0.168
ind+0.163
bur+0.160
ppa+0.159
gie+0.154
Neg logit contributions
case-0.073
 contest-0.072
uits-0.065
cakes-0.063
 vows-0.063
Token explore
Token ID7301
Feature activation+2.41e-02

Pos logit contributions
ind+0.099
ppa+0.098
bur+0.098
rying+0.095
ior+0.093
Neg logit contributions
 vows-0.050
 prize-0.046
 celebrate-0.043
 contest-0.043
 are-0.043
Token the
Token ID262
Feature activation+7.83e-02

Pos logit contributions
ppa+0.060
bur+0.059
rying+0.056
ety+0.056
cker+0.055
Neg logit contributions
 vows-0.028
 prize-0.027
 contest-0.026
 trophy-0.025
 are-0.025
Token forest
Token ID8222
Feature activation+1.95e-02

Pos logit contributions
ppa+0.180
ior+0.166
cker+0.165
owing+0.164
rying+0.163
Neg logit contributions
 great-0.117
 lot-0.115
 funny-0.104
 big-0.102
 tea-0.097
TokenN
Token ID45
Feature activation+1.98e-02

Pos logit contributions
 vows+0.000
 prize+0.000
 contest+0.000
 trophy+0.000
cakes+0.000
Neg logit contributions
bur-0.000
rying-0.000
ppa-0.000
ind-0.000
i-0.000
Tokenina
Token ID1437
Feature activation+1.27e-02

Pos logit contributions
bur+0.036
rying+0.034
ppa+0.033
ind+0.032
gie+0.031
Neg logit contributions
 vows-0.039
 prize-0.033
 trophy-0.033
 contest-0.033
cakes-0.033
Token was
Token ID373
Feature activation+3.30e-03

Pos logit contributions
bur+0.028
rying+0.027
ppa+0.027
ind+0.026
i+0.026
Neg logit contributions
 vows-0.020
 prize-0.017
 contest-0.017
 trophy-0.017
cakes-0.016
Token panic
Token ID13619
Feature activation-8.05e-04

Pos logit contributions
bur+0.006
rying+0.006
ppa+0.006
i+0.006
ind+0.006
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token-
Token ID12
Feature activation+5.36e-02

Pos logit contributions
 vows+0.002
 prize+0.001
 contest+0.001
 trophy+0.001
cakes+0.001
Neg logit contributions
rying-0.001
bur-0.001
ppa-0.001
i-0.001
ind-0.001
Tokenstr
Token ID2536
Feature activation+1.18e-01

Pos logit contributions
ior+0.099
bur+0.098
ppa+0.094
ind+0.093
gie+0.092
Neg logit contributions
apy-0.082
cakes-0.081
 contest-0.078
case-0.076
 vows-0.074
Tokenicken
Token ID5973
Feature activation+2.46e-02

Pos logit contributions
ior+0.155
 axe+0.147
oscope+0.140
 seen+0.139
 since+0.135
Neg logit contributions
ades-0.214
 vows-0.199
�-0.197
apy-0.188
ics-0.182
Token.
Token ID13
Feature activation+1.82e-02

Pos logit contributions
bur+0.050
rying+0.049
ppa+0.049
ind+0.047
i+0.046
Neg logit contributions
 vows-0.041
 prize-0.037
 contest-0.036
 trophy-0.036
cakes-0.035
Token She
Token ID1375
Feature activation+3.09e-02

Pos logit contributions
bur+0.044
rying+0.043
ppa+0.043
ind+0.041
i+0.041
Neg logit contributions
 vows-0.024
 contest-0.020
 prize-0.020
 trophy-0.019
apy-0.019
Token screamed
Token ID25421
Feature activation-1.23e-02

Pos logit contributions
bur+0.068
rying+0.067
ppa+0.065
ind+0.063
ior+0.061
Neg logit contributions
 vows-0.048
apy-0.041
 prize-0.040
 joke-0.039
 contest-0.039
Token for
Token ID329
Feature activation+1.84e-02

Pos logit contributions
 vows+0.025
 prize+0.023
 contest+0.023
 trophy+0.023
cakes+0.022
Neg logit contributions
rying-0.020
bur-0.020
ppa-0.020
i-0.019
ind-0.019
Token Benny
Token ID44275
Feature activation+3.40e-02

Pos logit contributions
bur+0.033
rying+0.033
ppa+0.033
i+0.032
ind+0.032
Neg logit contributions
 vows-0.026
 prize-0.024
 trophy-0.024
 contest-0.024
apy-0.023
Token lived
Token ID5615
Feature activation+3.11e-02

Pos logit contributions
rying+0.085
bur+0.084
ppa+0.081
ener+0.078
ind+0.077
Neg logit contributions
 vows-0.039
 are-0.031
 joke-0.031
case-0.031
 trophy-0.031
Token in
Token ID287
Feature activation+1.26e-02

Pos logit contributions
bur+0.065
ppa+0.065
ior+0.064
gie+0.062
i+0.062
Neg logit contributions
 contest-0.045
 vows-0.044
 prize-0.043
 trophy-0.041
apy-0.040
Token a
Token ID257
Feature activation+1.42e-02

Pos logit contributions
rying+0.031
ppa+0.031
bur+0.030
i+0.029
ind+0.029
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.014
 trophy-0.014
apy-0.013
Token cozy
Token ID37438
Feature activation+6.54e-02

Pos logit contributions
rying+0.033
bur+0.033
ppa+0.033
i+0.032
gie+0.031
Neg logit contributions
 vows-0.019
 contest-0.017
 prize-0.017
 trophy-0.016
apy-0.015
Token bur
Token ID4356
Feature activation+1.18e-01

Pos logit contributions
rying+0.128
bur+0.120
ppa+0.117
eking+0.116
cker+0.110
Neg logit contributions
 vows-0.109
 team-0.106
 prize-0.106
 lot-0.104
 tea-0.104
Tokenrow
Token ID808
Feature activation+7.96e-02

Pos logit contributions
ior+0.156
shadow+0.139
ppa+0.130
gie+0.129
 Tooth+0.127
Neg logit contributions
ade-0.205
uits-0.203
ades-0.203
 tea-0.194
case-0.192
Token with
Token ID351
Feature activation+1.02e-02

Pos logit contributions
ior+0.183
bur+0.181
ppa+0.175
gie+0.171
umper+0.166
Neg logit contributions
case-0.100
 contest-0.100
 trophy-0.091
 prize-0.088
 vows-0.087
Token his
Token ID465
Feature activation+3.57e-02

Pos logit contributions
rying+0.023
bur+0.023
ppa+0.023
i+0.022
ind+0.022
Neg logit contributions
 vows-0.015
 prize-0.013
 contest-0.013
 trophy-0.013
apy-0.012
Token family
Token ID1641
Feature activation+3.32e-02

Pos logit contributions
rying+0.083
ppa+0.079
bur+0.078
ior+0.077
umper+0.075
Neg logit contributions
 vows-0.050
 prize-0.048
 trophy-0.044
 lot-0.043
 contest-0.043
Token.
Token ID13
Feature activation+1.10e-02

Pos logit contributions
rying+0.073
bur+0.073
ppa+0.073
ior+0.069
ind+0.069
Neg logit contributions
 vows-0.045
 trophy-0.043
 prize-0.043
 contest-0.041
 tea-0.039
Token mom
Token ID1995
Feature activation+4.61e-02

Pos logit contributions
bur+0.016
rying+0.016
ppa+0.016
i+0.015
ind+0.015
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.009
 trophy-0.009
cakes-0.009
Token called
Token ID1444
Feature activation+2.67e-03

Pos logit contributions
rying+0.098
ind+0.097
bur+0.095
ior+0.093
cker+0.092
Neg logit contributions
 vows-0.062
 were-0.059
 contest-0.058
cakes-0.057
 are-0.057
Token out
Token ID503
Feature activation-1.79e-02

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.004
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token,
Token ID11
Feature activation+2.90e-02

Pos logit contributions
 vows+0.037
 trophy+0.034
 prize+0.033
 contest+0.033
cakes+0.033
Neg logit contributions
rying-0.029
i-0.027
bur-0.027
ind-0.027
ppa-0.027
Token "
Token ID366
Feature activation+7.14e-02

Pos logit contributions
bur+0.087
rying+0.085
ppa+0.085
ind+0.084
cker+0.082
Neg logit contributions
 vows-0.019
apy-0.014
 contest-0.013
 prize-0.012
cakes-0.012
TokenMill
Token ID22603
Feature activation+1.16e-01

Pos logit contributions
ppa+0.133
rying+0.132
cker+0.132
asured+0.131
ishing+0.129
Neg logit contributions
Everyone-0.100
Happy-0.098
 vows-0.094
 were-0.094
Mine-0.093
Tokenie
Token ID494
Feature activation+9.05e-03

Pos logit contributions
oscope+0.207
 territory+0.192
ior+0.186
 crank+0.181
cker+0.181
Neg logit contributions
 tea-0.135
 are-0.133
 parties-0.124
 were-0.124
 they-0.123
Token,
Token ID11
Feature activation+1.52e-02

Pos logit contributions
bur+0.021
rying+0.021
ppa+0.020
ind+0.020
i+0.020
Neg logit contributions
 vows-0.013
 prize-0.011
 contest-0.011
 trophy-0.011
cakes-0.010
Token come
Token ID1282
Feature activation+4.01e-02

Pos logit contributions
bur+0.033
ppa+0.033
rying+0.032
ind+0.031
i+0.031
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.020
 trophy-0.020
 are-0.019
Token home
Token ID1363
Feature activation+3.13e-02

Pos logit contributions
ppa+0.083
bur+0.080
cker+0.077
i+0.076
ior+0.075
Neg logit contributions
 vows-0.061
 prize-0.059
 celebrate-0.059
 blast-0.057
 contest-0.056
Token!"
Token ID2474
Feature activation+3.01e-02

Pos logit contributions
bur+0.063
ppa+0.062
rying+0.059
cker+0.059
gie+0.058
Neg logit contributions
 vows-0.051
 prize-0.047
 contest-0.046
cakes-0.044
 trophy-0.044
Token was
Token ID373
Feature activation-1.93e-03

Pos logit contributions
 vows+0.027
 prize+0.023
 trophy+0.022
 contest+0.021
 Prize+0.021
Neg logit contributions
rying-0.055
bur-0.055
i-0.054
ppa-0.053
ety-0.052
Token struggling
Token ID9648
Feature activation+3.38e-02

Pos logit contributions
 vows+0.004
 prize+0.003
 trophy+0.003
 contest+0.003
cakes+0.003
Neg logit contributions
bur-0.004
rying-0.004
ppa-0.004
i-0.003
ind-0.003
Token.
Token ID13
Feature activation+3.48e-02

Pos logit contributions
bur+0.075
ppa+0.074
ior+0.071
rying+0.070
ind+0.069
Neg logit contributions
 vows-0.045
 contest-0.045
 prize-0.044
 trophy-0.043
case-0.042
Token
Token ID198
Feature activation+2.82e-02

Pos logit contributions
rying+0.095
ppa+0.094
bur+0.093
ind+0.092
i+0.089
Neg logit contributions
 vows-0.032
 Everyone-0.031
apy-0.030
cakes-0.029
 contest-0.028
Token
Token ID198
Feature activation+3.34e-02

Pos logit contributions
rying+0.077
bur+0.074
ppa+0.074
i+0.073
ind+0.071
Neg logit contributions
 vows-0.026
apy-0.023
 contest-0.023
 prize-0.023
case-0.022
TokenMill
Token ID22603
Feature activation+1.16e-01

Pos logit contributions
bur+0.058
rying+0.057
ppa+0.054
i+0.053
ior+0.052
Neg logit contributions
 vows-0.061
apy-0.061
case-0.058
 contest-0.058
 Everyone-0.058
Tokenie
Token ID494
Feature activation+5.97e-02

Pos logit contributions
 property+0.215
 territory+0.211
 spine+0.208
rying+0.206
shadow+0.201
Neg logit contributions
 were-0.134
 vows-0.125
 are-0.115
ade-0.110
 tea-0.108
Token tried
Token ID3088
Feature activation+1.28e-02

Pos logit contributions
bur+0.139
rying+0.133
ind+0.124
ppa+0.123
umper+0.122
Neg logit contributions
 vows-0.081
case-0.074
 contest-0.071
apy-0.070
 were-0.067
Token to
Token ID284
Feature activation+8.96e-03

Pos logit contributions
bur+0.025
rying+0.025
ppa+0.025
ind+0.024
i+0.024
Neg logit contributions
 vows-0.022
 prize-0.020
 contest-0.020
 trophy-0.020
cakes-0.019
Token reach
Token ID3151
Feature activation+1.78e-02

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.019
ind+0.018
i+0.018
Neg logit contributions
 vows-0.014
 prize-0.012
 contest-0.012
 trophy-0.012
apy-0.011
Token the
Token ID262
Feature activation-1.50e-02

Pos logit contributions
ppa+0.040
rying+0.039
bur+0.039
ind+0.038
i+0.037
Neg logit contributions
 vows-0.025
 prize-0.023
 contest-0.023
 trophy-0.022
apy-0.021
Token there
Token ID612
Feature activation+2.37e-02

Pos logit contributions
ppa+0.074
bur+0.073
rying+0.071
ior+0.070
ety+0.068
Neg logit contributions
 contest-0.066
 vows-0.066
 prize-0.066
 trophy-0.064
 festival-0.059
Token?",
Token ID35379
Feature activation+3.58e-02

Pos logit contributions
ppa+0.040
rying+0.040
bur+0.040
ind+0.039
i+0.038
Neg logit contributions
 vows-0.045
 prize-0.043
 contest-0.043
 trophy-0.042
cakes-0.040
Token asked
Token ID1965
Feature activation+2.84e-02

Pos logit contributions
rying+0.078
bur+0.078
ind+0.075
ppa+0.075
ety+0.072
Neg logit contributions
 vows-0.052
apy-0.050
 prize-0.049
 contest-0.049
 trophy-0.049
Token the
Token ID262
Feature activation+4.39e-02

Pos logit contributions
rying+0.070
bur+0.068
ind+0.067
ppa+0.067
ety+0.064
Neg logit contributions
 vows-0.034
 prize-0.032
 contest-0.031
 trophy-0.031
apy-0.030
Token wood
Token ID4898
Feature activation+6.61e-02

Pos logit contributions
rying+0.101
ppa+0.097
bur+0.097
ind+0.093
ety+0.092
Neg logit contributions
 prize-0.062
 trophy-0.062
 contest-0.062
 vows-0.059
 third-0.057
Tokenpe
Token ID431
Feature activation+1.15e-01

Pos logit contributions
bur+0.104
ind+0.102
ior+0.101
ety+0.099
umper+0.097
Neg logit contributions
 vows-0.123
 trophy-0.123
 contest-0.120
 prize-0.120
case-0.119
Tokencker
Token ID15280
Feature activation+7.31e-02

Pos logit contributions
ior+0.131
bur+0.130
athy+0.119
umper+0.119
ind+0.118
Neg logit contributions
 laugh-0.234
 vows-0.232
ves-0.224
 trophy-0.222
 joke-0.219
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
bur+0.183
ind+0.177
ior+0.170
ppa+0.169
umper+0.168
Neg logit contributions
 laugh-0.076
 vows-0.074
 trophy-0.069
 prize-0.068
 g-0.066
Token
Token ID198
Feature activation+1.52e-02

Pos logit contributions
bur+0.026
rying+0.026
ppa+0.026
ind+0.025
i+0.025
Neg logit contributions
 vows-0.014
 prize-0.012
 contest-0.012
 trophy-0.012
apy-0.011
Token
Token ID198
Feature activation+1.03e-02

Pos logit contributions
rying+0.038
bur+0.037
ppa+0.037
i+0.036
ind+0.036
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
 trophy-0.016
apy-0.016
TokenThe
Token ID464
Feature activation+5.01e-02

Pos logit contributions
bur+0.023
rying+0.022
ppa+0.022
i+0.022
ind+0.021
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.014
 trophy-0.013
apy-0.013
Token should
Token ID815
Feature activation+6.65e-03

Pos logit contributions
bur+0.017
rying+0.016
ppa+0.016
ind+0.016
i+0.016
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.009
 trophy-0.009
apy-0.009
Token never
Token ID1239
Feature activation+2.49e-02

Pos logit contributions
bur+0.016
rying+0.016
ppa+0.015
ind+0.015
i+0.015
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.007
Token come
Token ID1282
Feature activation+4.75e-02

Pos logit contributions
bur+0.063
ppa+0.063
rying+0.062
ind+0.062
i+0.060
Neg logit contributions
 vows-0.027
 prize-0.027
 contest-0.026
 joke-0.025
 trophy-0.025
Token close
Token ID1969
Feature activation+6.90e-02

Pos logit contributions
ior+0.102
ppa+0.102
bur+0.098
i+0.096
ind+0.094
Neg logit contributions
 prize-0.064
 vows-0.062
 contest-0.060
 join-0.058
 celebrate-0.057
Token to
Token ID284
Feature activation+5.97e-02

Pos logit contributions
ppa+0.166
ior+0.163
cker+0.157
bur+0.156
gie+0.154
Neg logit contributions
 prize-0.073
 vows-0.072
 contest-0.072
 trophy-0.066
 are-0.062
Token an
Token ID281
Feature activation+1.15e-01

Pos logit contributions
rying+0.156
ppa+0.155
bur+0.154
ior+0.151
ishing+0.151
Neg logit contributions
 are-0.056
 prize-0.056
 celebrate-0.053
 tea-0.052
 contest-0.051
Token owl
Token ID39610
Feature activation+4.67e-02

Pos logit contributions
bur+0.196
rying+0.191
ishing+0.180
ppa+0.179
eking+0.166
Neg logit contributions
 prize-0.203
 idea-0.195
 great-0.185
 contest-0.183
 surprise-0.180
Token again
Token ID757
Feature activation+5.99e-02

Pos logit contributions
bur+0.096
ppa+0.092
ind+0.092
rying+0.091
ior+0.089
Neg logit contributions
 prize-0.070
 contest-0.070
 vows-0.070
 trophy-0.067
case-0.063
Token!".
Token ID48220
Feature activation+1.86e-02

Pos logit contributions
bur+0.137
ppa+0.133
gie+0.131
ior+0.128
rying+0.128
Neg logit contributions
 vows-0.075
 prize-0.074
 contest-0.073
 win-0.070
 celebrate-0.068
Token
Token ID198
Feature activation+7.97e-03

Pos logit contributions
bur+0.047
rying+0.047
ppa+0.046
ind+0.046
i+0.045
Neg logit contributions
 vows-0.021
 contest-0.019
 prize-0.019
cakes-0.018
 trophy-0.018
Token
Token ID198
Feature activation-6.03e-03

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.018
i+0.018
ind+0.018
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.009
 trophy-0.009
cakes-0.009
Token the
Token ID262
Feature activation+3.42e-02

Pos logit contributions
ppa+0.037
rying+0.037
bur+0.037
i+0.034
ind+0.034
Neg logit contributions
 vows-0.020
 prize-0.018
 contest-0.018
 trophy-0.017
apy-0.017
Token sunshine
Token ID34488
Feature activation+1.50e-02

Pos logit contributions
ppa+0.080
rying+0.078
bur+0.077
ety+0.072
i+0.072
Neg logit contributions
 vows-0.050
 prize-0.044
 trophy-0.044
 contest-0.043
 are-0.041
Token.
Token ID13
Feature activation+4.07e-02

Pos logit contributions
bur+0.031
rying+0.031
ppa+0.031
ind+0.029
i+0.029
Neg logit contributions
 vows-0.024
 prize-0.022
 contest-0.022
 trophy-0.021
cakes-0.021
Token
Token ID198
Feature activation+1.37e-02

Pos logit contributions
ppa+0.117
rying+0.116
bur+0.115
ind+0.112
i+0.109
Neg logit contributions
 Everyone-0.034
 vows-0.032
apy-0.031
cakes-0.028
case-0.028
Token
Token ID198
Feature activation+3.38e-02

Pos logit contributions
rying+0.034
bur+0.033
ppa+0.033
i+0.032
ind+0.032
Neg logit contributions
 vows-0.017
 prize-0.014
 contest-0.014
apy-0.014
 trophy-0.014
TokenMill
Token ID22603
Feature activation+1.14e-01

Pos logit contributions
bur+0.062
rying+0.061
ppa+0.059
i+0.058
ior+0.057
Neg logit contributions
 vows-0.060
apy-0.056
 contest-0.056
case-0.055
 Everyone-0.054
Tokenie
Token ID494
Feature activation+5.20e-02

Pos logit contributions
 property+0.215
 territory+0.205
 spine+0.204
rying+0.203
shadow+0.201
Neg logit contributions
 were-0.132
 vows-0.122
 are-0.112
ade-0.106
 parties-0.105
Token was
Token ID373
Feature activation+2.03e-02

Pos logit contributions
bur+0.118
rying+0.112
ppa+0.112
ior+0.107
umper+0.105
Neg logit contributions
 vows-0.075
 contest-0.064
 were-0.062
apy-0.061
case-0.061
Token so
Token ID523
Feature activation-8.05e-03

Pos logit contributions
bur+0.045
ppa+0.045
rying+0.044
ind+0.043
i+0.042
Neg logit contributions
 vows-0.029
 contest-0.026
 prize-0.025
 trophy-0.024
apy-0.024
Token excited
Token ID6568
Feature activation+3.32e-02

Pos logit contributions
 vows+0.013
 prize+0.011
 trophy+0.011
cakes+0.011
 contest+0.011
Neg logit contributions
rying-0.017
bur-0.017
ppa-0.017
i-0.016
ind-0.016
Token that
Token ID326
Feature activation+1.45e-02

Pos logit contributions
bur+0.076
ppa+0.076
rying+0.073
umper+0.071
ind+0.070
Neg logit contributions
 vows-0.044
 prize-0.042
 contest-0.042
cakes-0.042
 trophy-0.039
Token fluffy
Token ID39145
Feature activation+3.22e-02

Pos logit contributions
rying+0.074
ppa+0.071
bur+0.070
ind+0.068
ener+0.067
Neg logit contributions
 vows-0.036
apy-0.035
 trophy-0.032
 prize-0.032
 joke-0.031
Token and
Token ID290
Feature activation+1.50e-02

Pos logit contributions
rying+0.078
bur+0.078
ppa+0.077
cker+0.072
shadow+0.070
Neg logit contributions
 vows-0.040
 tea-0.035
 are-0.034
 prize-0.034
 lot-0.034
Token lived
Token ID5615
Feature activation+1.82e-02

Pos logit contributions
rying+0.034
bur+0.034
ppa+0.033
ind+0.032
i+0.032
Neg logit contributions
 vows-0.021
 prize-0.019
apy-0.019
 trophy-0.019
 contest-0.018
Token in
Token ID287
Feature activation+1.36e-02

Pos logit contributions
bur+0.035
ppa+0.034
rying+0.034
i+0.033
ior+0.033
Neg logit contributions
 vows-0.031
 contest-0.029
 prize-0.029
 trophy-0.028
apy-0.027
Token a
Token ID257
Feature activation+1.08e-02

Pos logit contributions
rying+0.034
ppa+0.034
bur+0.033
i+0.032
ind+0.032
Neg logit contributions
 vows-0.016
 prize-0.015
 contest-0.014
 trophy-0.014
apy-0.013
Token bur
Token ID4356
Feature activation+1.12e-01

Pos logit contributions
bur+0.026
rying+0.026
ppa+0.025
i+0.025
ind+0.024
Neg logit contributions
 vows-0.014
 prize-0.012
 contest-0.012
 trophy-0.012
apy-0.011
Tokenrow
Token ID808
Feature activation+7.12e-02

Pos logit contributions
ior+0.152
shadow+0.133
 Tooth+0.128
ppa+0.124
bur+0.121
Neg logit contributions
ade-0.196
ades-0.194
uits-0.188
 lot-0.184
br-0.183
Token in
Token ID287
Feature activation+2.64e-02

Pos logit contributions
ior+0.174
bur+0.173
ppa+0.166
gie+0.159
ety+0.158
Neg logit contributions
 contest-0.080
case-0.079
 trophy-0.070
 vows-0.070
 prize-0.068
Token the
Token ID262
Feature activation+7.34e-02

Pos logit contributions
ppa+0.069
rying+0.069
bur+0.066
i+0.065
ener+0.064
Neg logit contributions
 vows-0.026
 prize-0.026
 contest-0.025
 trophy-0.024
 are-0.023
Token forest
Token ID8222
Feature activation+3.91e-02

Pos logit contributions
rying+0.172
ppa+0.161
ener+0.157
ishing+0.155
owing+0.154
Neg logit contributions
 lot-0.107
 great-0.104
 tea-0.104
 third-0.099
 contest-0.094
Token.
Token ID13
Feature activation+1.29e-03

Pos logit contributions
bur+0.095
ppa+0.094
ior+0.091
umper+0.089
rying+0.088
Neg logit contributions
 vows-0.046
 contest-0.045
 are-0.042
case-0.042
 prize-0.041
Token cry
Token ID3960
Feature activation+1.34e-02

Pos logit contributions
 vows+0.046
cakes+0.039
 contest+0.037
 prize+0.037
 trophy+0.037
Neg logit contributions
 owl-0.057
ind-0.057
rying-0.057
 Owl-0.055
gie-0.055
Token coming
Token ID2406
Feature activation+3.43e-02

Pos logit contributions
bur+0.026
ppa+0.026
rying+0.026
ind+0.025
i+0.024
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.021
 trophy-0.020
apy-0.020
Token from
Token ID422
Feature activation+4.62e-02

Pos logit contributions
ppa+0.078
bur+0.076
ishing+0.070
i+0.069
rying+0.069
Neg logit contributions
 vows-0.046
 prize-0.044
 contest-0.042
 are-0.041
 trophy-0.041
Token outside
Token ID2354
Feature activation-4.22e-03

Pos logit contributions
ppa+0.116
rying+0.106
ety+0.105
bur+0.105
i+0.103
Neg logit contributions
 prize-0.056
 contest-0.056
 trophy-0.052
 festival-0.052
 tea-0.050
Token his
Token ID465
Feature activation+3.92e-02

Pos logit contributions
 vows+0.008
 prize+0.007
 contest+0.007
 trophy+0.007
cakes+0.007
Neg logit contributions
rying-0.008
bur-0.008
ppa-0.007
i-0.007
ind-0.007
Token bur
Token ID4356
Feature activation+1.12e-01

Pos logit contributions
rying+0.087
ppa+0.083
bur+0.082
cker+0.080
gie+0.077
Neg logit contributions
 prize-0.059
 vows-0.058
 trophy-0.055
case-0.053
 tea-0.052
Tokenrow
Token ID808
Feature activation+5.77e-02

Pos logit contributions
ior+0.130
ppa+0.127
shadow+0.126
 afar+0.126
pless+0.120
Neg logit contributions
ades-0.187
ade-0.181
uits-0.179
br-0.177
cakes-0.166
Token.
Token ID13
Feature activation+1.81e-02

Pos logit contributions
bur+0.138
ior+0.137
ppa+0.136
ind+0.136
rying+0.132
Neg logit contributions
case-0.066
 vows-0.061
 contest-0.059
cakes-0.058
 prize-0.056
Token
Token ID198
Feature activation+8.94e-03

Pos logit contributions
rying+0.042
bur+0.042
ppa+0.041
ind+0.041
i+0.040
Neg logit contributions
 vows-0.025
 prize-0.022
apy-0.021
 trophy-0.021
 contest-0.021
Token
Token ID198
Feature activation+2.70e-03

Pos logit contributions
bur+0.021
rying+0.021
ppa+0.021
i+0.021
ind+0.020
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.010
 trophy-0.010
apy-0.009
TokenHe
Token ID1544
Feature activation+4.04e-02

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.005
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token"
Token ID1
Feature activation+1.24e-02

Pos logit contributions
bur+0.047
rying+0.047
i+0.046
ppa+0.046
ind+0.044
Neg logit contributions
 vows-0.029
apy-0.027
case-0.027
cakes-0.027
 prize-0.027
TokenWho
Token ID8241
Feature activation-1.83e-02

Pos logit contributions
rying+0.023
bur+0.022
ppa+0.022
i+0.021
ind+0.021
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.021
 trophy-0.020
cakes-0.020
Token's
Token ID338
Feature activation+5.97e-03

Pos logit contributions
 vows+0.024
 prize+0.020
cakes+0.020
 trophy+0.020
apy+0.020
Neg logit contributions
bur-0.043
ppa-0.042
rying-0.041
i-0.041
ind-0.040
Token there
Token ID612
Feature activation+2.47e-02

Pos logit contributions
bur+0.011
rying+0.010
ppa+0.010
i+0.010
ind+0.010
Neg logit contributions
 vows-0.012
 prize-0.011
 contest-0.010
 trophy-0.010
cakes-0.010
Token?"
Token ID1701
Feature activation+3.02e-02

Pos logit contributions
ppa+0.044
rying+0.044
bur+0.043
ind+0.042
i+0.041
Neg logit contributions
 vows-0.045
 prize-0.043
 contest-0.043
 trophy-0.042
 are-0.040
Token Tim
Token ID5045
Feature activation+1.12e-01

Pos logit contributions
rying+0.073
bur+0.072
ind+0.071
ppa+0.070
i+0.066
Neg logit contributions
apy-0.040
 vows-0.037
 prize-0.036
 trophy-0.036
 contest-0.036
Tokenmy
Token ID1820
Feature activation+8.58e-02

Pos logit contributions
ind+0.143
 predators+0.142
rying+0.141
cker+0.137
 property+0.126
Neg logit contributions
 laugh-0.211
 g-0.207
 joke-0.203
 third-0.196
case-0.195
Token asked
Token ID1965
Feature activation+1.70e-02

Pos logit contributions
bur+0.182
rying+0.178
ior+0.171
ind+0.170
 property+0.166
Neg logit contributions
 g-0.114
 dance-0.110
 laugh-0.109
 joke-0.109
 third-0.105
Token.
Token ID13
Feature activation-2.71e-03

Pos logit contributions
bur+0.038
rying+0.037
ppa+0.037
ind+0.036
i+0.035
Neg logit contributions
 vows-0.025
 prize-0.022
 contest-0.022
 trophy-0.022
apy-0.022
Token
Token ID198
Feature activation+1.90e-02

Pos logit contributions
 vows+0.004
 prize+0.004
 contest+0.003
 trophy+0.003
cakes+0.003
Neg logit contributions
bur-0.006
rying-0.006
ppa-0.006
i-0.006
gie-0.006
Token
Token ID198
Feature activation+1.08e-02

Pos logit contributions
rying+0.049
bur+0.048
ppa+0.047
i+0.047
ind+0.046
Neg logit contributions
 vows-0.021
 prize-0.018
 contest-0.018
apy-0.017
cakes-0.017
Token
Token ID198
Feature activation+1.99e-02

Pos logit contributions
rying+0.040
bur+0.040
ppa+0.039
i+0.038
ind+0.038
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
apy-0.015
 trophy-0.015
Token"
Token ID1
Feature activation+1.23e-02

Pos logit contributions
bur+0.045
rying+0.045
ppa+0.044
i+0.043
ind+0.042
Neg logit contributions
 vows-0.027
apy-0.025
cakes-0.025
 contest-0.024
 prize-0.024
TokenWhat
Token ID2061
Feature activation-4.10e-02

Pos logit contributions
rying+0.022
bur+0.022
ppa+0.021
i+0.021
ind+0.021
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.021
 trophy-0.021
apy-0.021
Token happened
Token ID3022
Feature activation+2.74e-02

Pos logit contributions
 vows+0.076
cakes+0.065
 prize+0.065
uits+0.063
 contest+0.061
Neg logit contributions
my-0.076
bur-0.071
ety-0.069
i-0.069
rying-0.066
Token?"
Token ID1701
Feature activation+2.51e-02

Pos logit contributions
bur+0.058
ppa+0.058
rying+0.056
ind+0.055
i+0.054
Neg logit contributions
 contest-0.040
 prize-0.040
 vows-0.040
 trophy-0.040
 joke-0.037
Token Tim
Token ID5045
Feature activation+1.12e-01

Pos logit contributions
rying+0.054
bur+0.054
ppa+0.052
ind+0.052
i+0.049
Neg logit contributions
apy-0.037
 vows-0.037
 contest-0.036
 prize-0.035
 trophy-0.035
Tokenmy
Token ID1820
Feature activation+9.24e-02

Pos logit contributions
ind+0.149
rying+0.145
 predators+0.145
orns+0.139
cker+0.139
Neg logit contributions
 laugh-0.210
 g-0.204
 joke-0.201
 third-0.191
 smile-0.188
Token asked
Token ID1965
Feature activation+1.99e-02

Pos logit contributions
bur+0.209
rying+0.207
 property+0.195
orns+0.193
ind+0.192
Neg logit contributions
 g-0.110
 cl-0.108
 laugh-0.107
 dance-0.107
 joke-0.106
Token.
Token ID13
Feature activation-4.68e-04

Pos logit contributions
bur+0.045
rying+0.045
ind+0.044
ppa+0.044
i+0.042
Neg logit contributions
 vows-0.027
 contest-0.025
 prize-0.025
 trophy-0.024
apy-0.024
Token
Token ID198
Feature activation+2.08e-02

Pos logit contributions
 vows+0.001
 prize+0.001
 contest+0.001
 trophy+0.001
cakes+0.001
Neg logit contributions
bur-0.001
rying-0.001
ppa-0.001
i-0.001
ind-0.001
Token
Token ID198
Feature activation+7.50e-03

Pos logit contributions
rying+0.054
bur+0.053
ppa+0.052
i+0.052
ind+0.051
Neg logit contributions
 vows-0.022
 contest-0.019
 prize-0.019
apy-0.019
cakes-0.018
Token mist
Token ID4020
Feature activation+5.69e-03

Pos logit contributions
rying+0.054
ppa+0.054
bur+0.053
i+0.051
ety+0.049
Neg logit contributions
 vows-0.051
 contest-0.047
 prize-0.047
 trophy-0.046
 festival-0.045
Token and
Token ID290
Feature activation+2.73e-02

Pos logit contributions
bur+0.012
rying+0.011
ppa+0.011
i+0.011
ind+0.011
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.008
Token into
Token ID656
Feature activation+2.53e-03

Pos logit contributions
bur+0.057
ppa+0.056
rying+0.055
ind+0.054
i+0.052
Neg logit contributions
 vows-0.045
 contest-0.040
 prize-0.040
apy-0.038
 trophy-0.038
Token their
Token ID511
Feature activation+1.87e-02

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.004
 prize-0.003
 contest-0.003
 trophy-0.003
cakes-0.003
Token cozy
Token ID37438
Feature activation+6.79e-02

Pos logit contributions
bur+0.034
rying+0.034
ppa+0.034
i+0.031
gie+0.031
Neg logit contributions
 vows-0.036
 prize-0.032
 contest-0.031
 trophy-0.031
apy-0.030
Token bur
Token ID4356
Feature activation+1.11e-01

Pos logit contributions
ppa+0.134
bur+0.134
rying+0.130
umper+0.127
ior+0.123
Neg logit contributions
 vows-0.114
 tea-0.104
 prize-0.101
 lot-0.097
 dance-0.097
Tokenrows
Token ID8516
Feature activation+2.30e-02

Pos logit contributions
ior+0.152
ppa+0.126
umper+0.123
athy+0.122
 Tooth+0.120
Neg logit contributions
uits-0.217
ades-0.215
 vows-0.204
apy-0.197
ves-0.197
Token.
Token ID13
Feature activation+6.63e-03

Pos logit contributions
bur+0.047
ppa+0.046
rying+0.045
ind+0.044
ior+0.043
Neg logit contributions
 vows-0.037
 prize-0.034
 contest-0.033
 trophy-0.033
cakes-0.032
Token The
Token ID383
Feature activation+3.06e-02

Pos logit contributions
bur+0.015
rying+0.015
ppa+0.015
i+0.015
ind+0.015
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.007
Token end
Token ID886
Feature activation-7.77e-04

Pos logit contributions
bur+0.062
rying+0.061
ppa+0.061
ior+0.057
i+0.056
Neg logit contributions
 vows-0.053
 prize-0.049
 contest-0.048
 trophy-0.046
 festival-0.044
Token.
Token ID13
Feature activation+7.33e-03

Pos logit contributions
 vows+0.001
 prize+0.001
 trophy+0.001
 contest+0.001
cakes+0.001
Neg logit contributions
bur-0.001
rying-0.001
ppa-0.001
i-0.001
ind-0.001
Token of
Token ID286
Feature activation+3.91e-02

Pos logit contributions
 vows+0.030
 trophy+0.026
 prize+0.026
apy+0.025
cakes+0.025
Neg logit contributions
rying-0.034
i-0.033
bur-0.033
ppa-0.033
ind-0.031
Token friendly
Token ID8030
Feature activation+1.12e-02

Pos logit contributions
bur+0.078
rying+0.076
ppa+0.076
ety+0.072
ior+0.070
Neg logit contributions
 vows-0.065
 contest-0.062
 prize-0.062
 joke-0.058
 great-0.058
Token ducks
Token ID39694
Feature activation+1.11e-02

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.018
ind+0.017
i+0.017
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.020
 trophy-0.020
cakes-0.019
Token came
Token ID1625
Feature activation+2.00e-02

Pos logit contributions
bur+0.022
ppa+0.022
rying+0.022
ind+0.021
i+0.021
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
 trophy-0.016
apy-0.015
Token to
Token ID284
Feature activation+1.47e-02

Pos logit contributions
ppa+0.038
bur+0.038
rying+0.036
ior+0.035
ind+0.035
Neg logit contributions
 vows-0.035
 prize-0.032
 contest-0.031
 trophy-0.030
apy-0.029
Token Gig
Token ID19525
Feature activation+1.11e-01

Pos logit contributions
rying+0.031
bur+0.031
ppa+0.031
ind+0.029
i+0.029
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.021
 trophy-0.020
cakes-0.019
Tokeni
Token ID72
Feature activation+3.24e-02

Pos logit contributions
asured+0.113
oscope+0.111
 property+0.103
 axe+0.102
keeping+0.096
Neg logit contributions
 vows-0.233
 tea-0.209
 they-0.207
 are-0.205
 were-0.202
Token's
Token ID338
Feature activation+2.91e-02

Pos logit contributions
bur+0.064
ppa+0.063
rying+0.061
ind+0.061
ior+0.059
Neg logit contributions
 vows-0.052
 prize-0.048
 contest-0.047
 trophy-0.047
 are-0.045
Token rescue
Token ID9992
Feature activation+2.02e-02

Pos logit contributions
ppa+0.054
bur+0.054
rying+0.053
i+0.050
umper+0.050
Neg logit contributions
 vows-0.055
 prize-0.050
 contest-0.048
 trophy-0.047
 joke-0.046
Token.
Token ID13
Feature activation+2.56e-02

Pos logit contributions
bur+0.042
rying+0.041
ppa+0.041
ind+0.040
ety+0.039
Neg logit contributions
 vows-0.032
 prize-0.029
 contest-0.028
 trophy-0.027
cakes-0.027
Token They
Token ID1119
Feature activation-1.24e-02

Pos logit contributions
rying+0.051
bur+0.051
ppa+0.050
ind+0.049
i+0.047
Neg logit contributions
 vows-0.044
 prize-0.039
cakes-0.038
 contest-0.038
apy-0.037
Token,
Token ID11
Feature activation+2.67e-02

Pos logit contributions
rying+0.095
bur+0.094
cker+0.093
ppa+0.091
ind+0.091
Neg logit contributions
 vows-0.046
 prize-0.039
 are-0.039
 contest-0.038
 tea-0.036
Token "
Token ID366
Feature activation+7.25e-02

Pos logit contributions
bur+0.078
rying+0.077
ind+0.077
ppa+0.077
i+0.075
Neg logit contributions
 vows-0.018
 prize-0.015
 contest-0.015
 trophy-0.013
apy-0.013
TokenWhat
Token ID2061
Feature activation-1.73e-02

Pos logit contributions
rying+0.149
ishing+0.147
ior+0.146
owing+0.145
cker+0.144
Neg logit contributions
Mine-0.086
Me-0.079
 vows-0.079
 contest-0.077
Everyone-0.077
Token happened
Token ID3022
Feature activation+4.04e-02

Pos logit contributions
 vows+0.031
 prize+0.027
cakes+0.027
 trophy+0.027
 contest+0.027
Neg logit contributions
bur-0.032
i-0.031
ppa-0.031
rying-0.031
ety-0.030
Token,
Token ID11
Feature activation+2.17e-02

Pos logit contributions
bur+0.094
ppa+0.094
rying+0.090
ind+0.089
ior+0.088
Neg logit contributions
 contest-0.052
 prize-0.050
 vows-0.049
 trophy-0.048
 joke-0.045
Token Gig
Token ID19525
Feature activation+1.11e-01

Pos logit contributions
rying+0.036
bur+0.035
ppa+0.033
ind+0.032
cker+0.032
Neg logit contributions
 vows-0.045
 prize-0.042
 trophy-0.040
 contest-0.039
cakes-0.039
Tokeni
Token ID72
Feature activation+5.55e-02

Pos logit contributions
oscope+0.117
keeping+0.112
rying+0.106
umbling+0.102
 property+0.100
Neg logit contributions
 vows-0.230
 are-0.205
 they-0.196
 tea-0.195
 were-0.193
Token?
Token ID30
Feature activation+3.66e-02

Pos logit contributions
bur+0.109
rying+0.106
ppa+0.103
ind+0.103
ior+0.102
Neg logit contributions
 contest-0.085
 vows-0.085
 are-0.084
 prize-0.079
 trophy-0.079
Token Are
Token ID4231
Feature activation+3.54e-02

Pos logit contributions
bur+0.080
rying+0.078
ppa+0.076
ind+0.075
i+0.074
Neg logit contributions
 vows-0.055
apy-0.052
cakes-0.049
case-0.049
 contest-0.049
Token you
Token ID345
Feature activation+5.06e-02

Pos logit contributions
rying+0.073
bur+0.071
ind+0.070
ior+0.070
cker+0.069
Neg logit contributions
 vows-0.055
 contest-0.053
 prize-0.052
 trophy-0.051
 are-0.051
Token okay
Token ID8788
Feature activation+3.97e-02

Pos logit contributions
ior+0.099
bur+0.098
rying+0.096
ind+0.094
ppa+0.093
Neg logit contributions
 vows-0.075
 are-0.073
apy-0.073
 prize-0.073
 celebrate-0.072
Token able
Token ID1498
Feature activation+2.04e-02

Pos logit contributions
bur+0.031
rying+0.030
ppa+0.030
i+0.029
ind+0.029
Neg logit contributions
 vows-0.031
 contest-0.029
 prize-0.028
 trophy-0.028
apy-0.027
Token to
Token ID284
Feature activation-5.13e-03

Pos logit contributions
bur+0.041
ppa+0.040
rying+0.040
ind+0.039
i+0.038
Neg logit contributions
 vows-0.034
 prize-0.031
 contest-0.030
 trophy-0.030
cakes-0.029
Token escape
Token ID6654
Feature activation+1.47e-02

Pos logit contributions
 vows+0.008
 prize+0.006
 contest+0.006
cakes+0.006
 trophy+0.006
Neg logit contributions
bur-0.011
rying-0.011
ppa-0.011
i-0.011
ind-0.011
Token from
Token ID422
Feature activation+4.03e-02

Pos logit contributions
bur+0.029
ppa+0.028
rying+0.028
ind+0.027
i+0.027
Neg logit contributions
 vows-0.025
 prize-0.023
 trophy-0.023
 contest-0.023
cakes-0.022
Token his
Token ID465
Feature activation+2.67e-03

Pos logit contributions
ppa+0.096
bur+0.093
rying+0.092
ety+0.091
ior+0.090
Neg logit contributions
 vows-0.050
 prize-0.050
 contest-0.049
 trophy-0.047
apy-0.043
Token bur
Token ID4356
Feature activation+1.10e-01

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.005
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Tokenrow
Token ID808
Feature activation+4.20e-02

Pos logit contributions
ior+0.130
ppa+0.121
ety+0.110
bur+0.109
 Tooth+0.106
Neg logit contributions
ades-0.222
uits-0.216
 vows-0.205
 prize-0.204
ade-0.203
Token and
Token ID290
Feature activation+1.89e-02

Pos logit contributions
bur+0.085
ppa+0.083
rying+0.082
ind+0.082
ior+0.080
Neg logit contributions
 vows-0.066
 prize-0.060
 contest-0.060
 trophy-0.059
cakes-0.059
Token play
Token ID711
Feature activation-3.02e-02

Pos logit contributions
bur+0.042
rying+0.041
ppa+0.041
ind+0.040
i+0.039
Neg logit contributions
 vows-0.029
 prize-0.026
 trophy-0.025
 contest-0.025
apy-0.024
Token in
Token ID287
Feature activation-8.57e-03

Pos logit contributions
 vows+0.066
cakes+0.056
apy+0.055
 Prize+0.055
 trophy+0.055
Neg logit contributions
rying-0.048
bur-0.044
ind-0.042
ppa-0.042
i-0.042
Token the
Token ID262
Feature activation+3.20e-02

Pos logit contributions
 vows+0.015
cakes+0.013
 prize+0.013
 contest+0.013
 trophy+0.013
Neg logit contributions
bur-0.017
rying-0.017
ppa-0.016
ind-0.016
i-0.016
Token.
Token ID13
Feature activation+3.35e-02

Pos logit contributions
bur+0.005
rying+0.004
ppa+0.004
i+0.004
ind+0.004
Neg logit contributions
 vows-0.004
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token One
Token ID1881
Feature activation+3.38e-02

Pos logit contributions
rying+0.083
ppa+0.081
ind+0.078
bur+0.077
i+0.076
Neg logit contributions
 vows-0.040
 prize-0.037
 contest-0.035
 Everyone-0.035
 are-0.035
Token day
Token ID1110
Feature activation+1.95e-03

Pos logit contributions
rying+0.084
ppa+0.082
bur+0.078
ind+0.076
ener+0.076
Neg logit contributions
 prize-0.039
 vows-0.039
 contest-0.038
 joke-0.037
 trophy-0.036
Token,
Token ID11
Feature activation+2.67e-02

Pos logit contributions
bur+0.004
rying+0.004
ppa+0.004
i+0.004
ind+0.004
Neg logit contributions
 vows-0.003
 prize-0.002
 contest-0.002
 trophy-0.002
cakes-0.002
Token Stri
Token ID26137
Feature activation+3.40e-02

Pos logit contributions
rying+0.054
ppa+0.052
ind+0.052
bur+0.051
cker+0.048
Neg logit contributions
 vows-0.043
apy-0.042
 prize-0.041
 contest-0.040
 trophy-0.039
Tokenpe
Token ID431
Feature activation+1.10e-01

Pos logit contributions
rying+0.063
ind+0.058
ety+0.058
ppa+0.058
bur+0.057
Neg logit contributions
 vows-0.061
 prize-0.056
ves-0.055
case-0.055
 contest-0.055
Tokeny
Token ID88
Feature activation+5.75e-02

Pos logit contributions
ior+0.169
rying+0.168
 Owl+0.167
ppa+0.165
 Tooth+0.163
Neg logit contributions
 were-0.187
 are-0.182
 vows-0.181
ades-0.169
 joke-0.167
Token saw
Token ID2497
Feature activation+4.52e-02

Pos logit contributions
rying+0.140
bur+0.133
ind+0.128
ppa+0.126
ishing+0.123
Neg logit contributions
 vows-0.070
case-0.068
 contest-0.064
ves-0.062
 team-0.061
Token his
Token ID465
Feature activation+2.20e-02

Pos logit contributions
rying+0.144
ppa+0.133
ener+0.132
ind+0.131
ior+0.131
Neg logit contributions
apy-0.024
 prize-0.021
 contest-0.021
 vows-0.020
 tea-0.020
Token friend
Token ID1545
Feature activation+1.98e-02

Pos logit contributions
rying+0.046
ppa+0.045
bur+0.043
ior+0.041
umper+0.041
Neg logit contributions
 vows-0.037
 prize-0.035
 trophy-0.033
 contest-0.032
 joke-0.031
Token,
Token ID11
Feature activation-9.03e-03

Pos logit contributions
rying+0.044
bur+0.043
ppa+0.043
ind+0.042
i+0.040
Neg logit contributions
 vows-0.028
 contest-0.025
 prize-0.025
 trophy-0.024
cakes-0.024
Token peek
Token ID27185
Feature activation-1.84e-02

Pos logit contributions
 vows+0.023
 prize+0.021
 contest+0.020
 trophy+0.020
cakes+0.020
Neg logit contributions
rying-0.024
bur-0.024
i-0.024
ppa-0.024
ind-0.023
Tokened
Token ID276
Feature activation+6.77e-03

Pos logit contributions
 vows+0.041
 trophy+0.039
 prize+0.039
 contest+0.039
 Prize+0.038
Neg logit contributions
rying-0.027
i-0.025
ppa-0.024
bur-0.024
ind-0.024
Token out
Token ID503
Feature activation+2.65e-03

Pos logit contributions
bur+0.012
rying+0.012
ppa+0.012
i+0.011
ind+0.011
Neg logit contributions
 vows-0.013
 prize-0.012
 contest-0.012
 trophy-0.011
cakes-0.011
Token of
Token ID286
Feature activation+2.08e-02

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.004
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token his
Token ID465
Feature activation+2.28e-02

Pos logit contributions
rying+0.050
ppa+0.050
bur+0.048
ind+0.048
i+0.047
Neg logit contributions
 vows-0.026
 prize-0.025
 contest-0.023
 trophy-0.023
apy-0.021
Token bur
Token ID4356
Feature activation+1.10e-01

Pos logit contributions
rying+0.045
bur+0.044
ppa+0.044
i+0.041
ind+0.041
Neg logit contributions
 vows-0.040
 prize-0.038
 trophy-0.037
 contest-0.036
case-0.034
Tokenrow
Token ID808
Feature activation+5.02e-02

Pos logit contributions
ior+0.139
 Owl+0.129
ppa+0.127
 afar+0.126
 reckless+0.122
Neg logit contributions
uits-0.204
ades-0.202
ade-0.183
 vows-0.183
br-0.177
Token.
Token ID13
Feature activation+2.86e-03

Pos logit contributions
bur+0.111
ind+0.110
ppa+0.109
ior+0.109
rying+0.108
Neg logit contributions
 vows-0.067
case-0.063
cakes-0.060
 contest-0.060
 prize-0.060
Token
Token ID198
Feature activation+1.41e-03

Pos logit contributions
bur+0.006
rying+0.006
ppa+0.006
i+0.006
ind+0.006
Neg logit contributions
 vows-0.004
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token
Token ID198
Feature activation-8.45e-03

Pos logit contributions
bur+0.003
rying+0.003
ppa+0.003
i+0.003
ind+0.003
Neg logit contributions
 vows-0.002
 prize-0.002
 contest-0.002
 trophy-0.002
cakes-0.002
TokenHe
Token ID1544
Feature activation+7.85e-03

Pos logit contributions
 vows+0.015
 prize+0.014
 trophy+0.013
 contest+0.013
cakes+0.013
Neg logit contributions
bur-0.016
ppa-0.016
rying-0.016
ind-0.015
i-0.015
Token
Token ID198
Feature activation-7.36e-03

Pos logit contributions
 vows+0.012
 prize+0.010
 contest+0.010
 trophy+0.010
apy+0.010
Neg logit contributions
bur-0.011
rying-0.011
ppa-0.010
i-0.010
ind-0.010
Token
Token ID198
Feature activation-2.17e-02

Pos logit contributions
 vows+0.012
 prize+0.010
 trophy+0.010
 contest+0.010
cakes+0.010
Neg logit contributions
bur-0.016
rying-0.015
ppa-0.015
ind-0.015
i-0.015
TokenThe
Token ID464
Feature activation-3.20e-02

Pos logit contributions
 vows+0.043
 prize+0.038
 trophy+0.037
 contest+0.037
 tea+0.036
Neg logit contributions
bur-0.038
rying-0.037
ind-0.036
my-0.035
ppa-0.035
Token kids
Token ID3988
Feature activation-4.02e-02

Pos logit contributions
apy+0.076
 vows+0.070
case+0.065
ades+0.065
�+0.065
Neg logit contributions
bur-0.039
ppa-0.038
ind-0.037
 owl-0.037
rying-0.037
Token played
Token ID2826
Feature activation-8.43e-02

Pos logit contributions
 vows+0.071
 prize+0.065
apy+0.064
 trophy+0.064
ades+0.063
Neg logit contributions
i-0.074
rying-0.074
bur-0.072
ppa-0.071
my-0.070
Token a
Token ID257
Feature activation-1.09e-01

Pos logit contributions
 vows+0.174
apy+0.162
cakes+0.154
Mine+0.153
�+0.150
Neg logit contributions
rying-0.110
 asking-0.103
ishing-0.100
 forth-0.097
ting-0.095
Token lot
Token ID1256
Feature activation-2.84e-02

Pos logit contributions
apy+0.159
cakes+0.149
 vows+0.148
�+0.146
 Both+0.141
Neg logit contributions
ind-0.210
rying-0.167
nie-0.167
ppa-0.165
ich-0.161
Token of
Token ID286
Feature activation-4.86e-02

Pos logit contributions
 vows+0.063
apy+0.057
Mine+0.055
 trophy+0.053
 prize+0.053
Neg logit contributions
rying-0.043
bur-0.041
ppa-0.040
i-0.040
ind-0.039
Token fun
Token ID1257
Feature activation-5.17e-02

Pos logit contributions
 vows+0.067
apy+0.058
cakes+0.054
�+0.053
case+0.049
Neg logit contributions
rying-0.103
ind-0.102
ishing-0.098
ior-0.097
my-0.097
Token and
Token ID290
Feature activation-1.36e-02

Pos logit contributions
 vows+0.091
Mine+0.079
cakes+0.073
 trophy+0.072
apy+0.072
Neg logit contributions
rying-0.095
ind-0.089
i-0.088
ishing-0.087
ise-0.087
Token interesting
Token ID3499
Feature activation-4.54e-02

Pos logit contributions
 vows+0.022
 trophy+0.019
 prize+0.019
 contest+0.019
ades+0.019
Neg logit contributions
bur-0.027
rying-0.027
i-0.026
ppa-0.026
gie-0.025
Token were
Token ID547
Feature activation-3.66e-02

Pos logit contributions
 vows+0.058
 prize+0.050
 Prize+0.050
 trophy+0.048
 contest+0.047
Neg logit contributions
i-0.112
bur-0.109
my-0.108
rying-0.105
ppa-0.105
Token so
Token ID523
Feature activation-6.11e-02

Pos logit contributions
 vows+0.060
 trophy+0.055
apy+0.055
 prize+0.055
 Prize+0.055
Neg logit contributions
bur-0.069
i-0.067
ppa-0.066
rying-0.066
ind-0.065
Token colorful
Token ID20239
Feature activation-3.07e-02

Pos logit contributions
 mat+0.096
 Prize+0.096
 trophy+0.095
 vows+0.095
 prize+0.095
Neg logit contributions
ind-0.105
i-0.095
my-0.093
ppa-0.088
ety-0.087
Token and
Token ID290
Feature activation-2.12e-02

Pos logit contributions
 vows+0.066
apy+0.059
 Prize+0.059
 trophy+0.058
 contest+0.058
Neg logit contributions
i-0.044
rying-0.044
bur-0.043
ind-0.041
ppa-0.041
Token the
Token ID262
Feature activation+1.02e-02

Pos logit contributions
 vows+0.031
 prize+0.027
 contest+0.026
 trophy+0.026
ades+0.025
Neg logit contributions
bur-0.045
ppa-0.044
rying-0.044
i-0.044
ind-0.043
Token stories
Token ID3923
Feature activation-1.09e-01

Pos logit contributions
bur+0.020
rying+0.020
ppa+0.019
i+0.018
ind+0.018
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
 trophy-0.016
cakes-0.015
Token were
Token ID547
Feature activation-3.30e-02

Pos logit contributions
 Prize+0.186
 vows+0.182
 coach+0.180
ades+0.177
apy+0.174
Neg logit contributions
my-0.158
i-0.150
 since-0.145
bur-0.142
 owl-0.141
Token so
Token ID523
Feature activation-5.94e-02

Pos logit contributions
 vows+0.055
 contest+0.050
apy+0.050
 Prize+0.050
 trophy+0.049
Neg logit contributions
bur-0.064
i-0.062
rying-0.061
ppa-0.060
ind-0.060
Token fun
Token ID1257
Feature activation-2.83e-02

Pos logit contributions
 Prize+0.092
 trophy+0.091
 vows+0.091
 prize+0.090
 contest+0.090
Neg logit contributions
ind-0.105
i-0.096
my-0.090
ppa-0.089
rying-0.088
Token.
Token ID13
Feature activation-4.52e-03

Pos logit contributions
 vows+0.058
apy+0.052
 trophy+0.052
 Prize+0.051
 contest+0.051
Neg logit contributions
rying-0.045
bur-0.043
i-0.043
ind-0.041
ppa-0.041
Token She
Token ID1375
Feature activation-2.25e-02

Pos logit contributions
 vows+0.007
 prize+0.006
 trophy+0.006
 contest+0.006
apy+0.005
Neg logit contributions
bur-0.010
rying-0.010
ppa-0.010
i-0.010
ind-0.009
Token
Token ID198
Feature activation-2.56e-02

Pos logit contributions
 vows+0.032
 prize+0.028
 trophy+0.028
 contest+0.027
cakes+0.026
Neg logit contributions
bur-0.035
ppa-0.035
rying-0.034
ind-0.033
i-0.033
TokenDa
Token ID26531
Feature activation+1.44e-02

Pos logit contributions
 vows+0.053
 prize+0.047
 trophy+0.047
 contest+0.044
cakes+0.044
Neg logit contributions
ppa-0.042
bur-0.041
ind-0.041
rying-0.040
i-0.038
Tokenisy
Token ID13560
Feature activation-3.24e-02

Pos logit contributions
bur+0.027
rying+0.026
ppa+0.025
ind+0.024
i+0.024
Neg logit contributions
 vows-0.027
 prize-0.025
 contest-0.024
 trophy-0.024
cakes-0.023
Token started
Token ID2067
Feature activation-2.98e-02

Pos logit contributions
 vows+0.058
 prize+0.055
 trophy+0.054
cakes+0.054
 contest+0.053
Neg logit contributions
i-0.058
ppa-0.056
rying-0.055
bur-0.055
ind-0.054
Token making
Token ID1642
Feature activation-5.18e-02

Pos logit contributions
 vows+0.065
cakes+0.061
 trophy+0.061
 prize+0.060
ades+0.059
Neg logit contributions
rying-0.042
i-0.041
ind-0.040
bur-0.039
ppa-0.038
Token videos
Token ID5861
Feature activation-1.06e-01

Pos logit contributions
 vows+0.091
 trophy+0.082
case+0.082
cakes+0.081
 Prize+0.081
Neg logit contributions
i-0.093
ind-0.089
rying-0.088
bur-0.086
ppa-0.086
Token and
Token ID290
Feature activation-1.27e-02

Pos logit contributions
 vows+0.268
Mine+0.242
apy+0.240
 Prize+0.231
ades+0.226
Neg logit contributions
my-0.113
 owl-0.098
rying-0.093
 since-0.093
ting-0.092
Token put
Token ID1234
Feature activation-2.96e-02

Pos logit contributions
 vows+0.022
 prize+0.020
 trophy+0.020
 contest+0.019
cakes+0.019
Neg logit contributions
rying-0.024
bur-0.024
ppa-0.023
i-0.023
ind-0.022
Token them
Token ID606
Feature activation-5.90e-02

Pos logit contributions
 vows+0.049
apy+0.044
 trophy+0.043
 Prize+0.043
 prize+0.043
Neg logit contributions
bur-0.059
i-0.056
ppa-0.055
rying-0.055
ind-0.054
Token up
Token ID510
Feature activation-9.33e-03

Pos logit contributions
 vows+0.124
 Prize+0.115
apy+0.113
Mine+0.113
cakes+0.112
Neg logit contributions
rying-0.087
bur-0.086
i-0.081
ppa-0.079
ind-0.078
Token on
Token ID319
Feature activation-2.99e-02

Pos logit contributions
 vows+0.018
 prize+0.016
 trophy+0.016
cakes+0.015
 contest+0.015
Neg logit contributions
bur-0.017
rying-0.017
ppa-0.016
i-0.016
ind-0.016
Token characters
Token ID3435
Feature activation-6.31e-02

Pos logit contributions
 vows+0.032
apy+0.031
cakes+0.024
ades+0.024
case+0.024
Neg logit contributions
bur-0.064
ind-0.062
rying-0.062
my-0.061
gie-0.060
Token and
Token ID290
Feature activation-3.95e-03

Pos logit contributions
 vows+0.137
apy+0.124
ades+0.124
 Prize+0.121
cakes+0.120
Neg logit contributions
rying-0.092
i-0.091
bur-0.085
ppa-0.081
my-0.079
Token watching
Token ID4964
Feature activation-5.65e-02

Pos logit contributions
 vows+0.007
 prize+0.006
 contest+0.006
 trophy+0.006
cakes+0.006
Neg logit contributions
bur-0.008
rying-0.007
ppa-0.007
i-0.007
ind-0.007
Token the
Token ID262
Feature activation-4.28e-02

Pos logit contributions
 vows+0.095
apy+0.088
case+0.086
 Prize+0.086
 prize+0.085
Neg logit contributions
i-0.103
ind-0.101
rying-0.097
bur-0.095
my-0.095
Token funny
Token ID8258
Feature activation-5.63e-02

Pos logit contributions
apy+0.052
 vows+0.052
uits+0.044
ades+0.041
case+0.040
Neg logit contributions
ind-0.099
my-0.095
bur-0.094
rying-0.091
 owl-0.091
Token video
Token ID2008
Feature activation-1.06e-01

Pos logit contributions
apy+0.074
 vows+0.072
uits+0.070
case+0.067
 Prize+0.064
Neg logit contributions
ind-0.116
i-0.112
my-0.111
ping-0.111
gie-0.110
Token.
Token ID13
Feature activation-2.57e-02

Pos logit contributions
 vows+0.233
apy+0.217
Mine+0.211
 Prize+0.210
 disco+0.206
Neg logit contributions
my-0.122
rying-0.122
i-0.120
 forth-0.111
ting-0.109
Token She
Token ID1375
Feature activation-1.83e-02

Pos logit contributions
 vows+0.047
 trophy+0.045
 prize+0.044
ades+0.042
 contest+0.041
Neg logit contributions
bur-0.045
my-0.044
ety-0.044
i-0.044
rying-0.043
Token went
Token ID1816
Feature activation-1.45e-02

Pos logit contributions
 vows+0.034
 prize+0.031
 contest+0.031
cakes+0.031
 trophy+0.031
Neg logit contributions
bur-0.032
i-0.031
ppa-0.031
rying-0.031
ind-0.029
Token to
Token ID284
Feature activation-2.57e-02

Pos logit contributions
 vows+0.032
apy+0.029
 trophy+0.029
 prize+0.028
 contest+0.028
Neg logit contributions
rying-0.022
bur-0.021
ppa-0.020
i-0.020
ind-0.019
Token the
Token ID262
Feature activation-3.15e-02

Pos logit contributions
 vows+0.043
cakes+0.040
ades+0.040
apy+0.038
case+0.035
Neg logit contributions
bur-0.050
rying-0.049
i-0.047
ind-0.047
my-0.046
Token a
Token ID257
Feature activation-4.26e-02

Pos logit contributions
 vows+0.068
 Prize+0.063
 contest+0.061
 prize+0.060
 trophy+0.060
Neg logit contributions
bur-0.074
i-0.074
ppa-0.073
ind-0.070
rying-0.069
Token funny
Token ID8258
Feature activation-3.82e-02

Pos logit contributions
 vows+0.060
cakes+0.054
 Prize+0.053
 contest+0.053
uits+0.052
Neg logit contributions
ind-0.088
ppa-0.086
bur-0.085
cker-0.084
i-0.083
Token face
Token ID1986
Feature activation-2.09e-02

Pos logit contributions
 vows+0.061
 contest+0.056
 Prize+0.055
cakes+0.054
case+0.053
Neg logit contributions
i-0.071
bur-0.071
ind-0.070
cker-0.070
ppa-0.069
Token.
Token ID13
Feature activation-4.56e-02

Pos logit contributions
 vows+0.041
 prize+0.037
 contest+0.037
 trophy+0.037
 Prize+0.036
Neg logit contributions
rying-0.035
bur-0.034
i-0.034
ppa-0.034
ind-0.032
Token The
Token ID383
Feature activation-1.58e-02

Pos logit contributions
 trophy+0.083
 prize+0.081
 contest+0.080
 vows+0.077
ades+0.077
Neg logit contributions
ior-0.072
ety-0.063
gie-0.063
i-0.062
ind-0.061
Token sandwiches
Token ID29777
Feature activation-1.05e-01

Pos logit contributions
 vows+0.021
apy+0.019
 contest+0.018
 Prize+0.018
 prize+0.018
Neg logit contributions
bur-0.036
ppa-0.034
i-0.034
rying-0.034
ind-0.033
Token are
Token ID389
Feature activation-2.17e-02

Pos logit contributions
 Prize+0.155
igsaw+0.152
 vows+0.148
ival+0.148
books+0.133
Neg logit contributions
 forth-0.194
i-0.192
my-0.184
bur-0.182
 bruised-0.172
Token spicy
Token ID26880
Feature activation-1.07e-02

Pos logit contributions
 vows+0.036
 contest+0.032
 Prize+0.032
 prize+0.031
 trophy+0.031
Neg logit contributions
bur-0.045
ppa-0.043
i-0.043
rying-0.042
ind-0.041
Token!
Token ID0
Feature activation-4.92e-02

Pos logit contributions
 vows+0.021
 contest+0.019
 prize+0.019
 trophy+0.019
apy+0.018
Neg logit contributions
bur-0.018
rying-0.018
i-0.018
ppa-0.017
ind-0.017
Token They
Token ID1119
Feature activation-5.18e-02

Pos logit contributions
 vows+0.083
 trophy+0.083
 prize+0.083
 contest+0.082
ades+0.075
Neg logit contributions
ior-0.084
ppa-0.074
bur-0.074
ety-0.073
ind-0.072
Token have
Token ID423
Feature activation-1.34e-02

Pos logit contributions
 vows+0.072
cakes+0.072
ades+0.070
 contest+0.068
 prize+0.065
Neg logit contributions
i-0.111
bur-0.108
cker-0.104
ppa-0.103
rying-0.102
Token She
Token ID1375
Feature activation-2.40e-02

Pos logit contributions
 vows+0.007
 prize+0.006
 contest+0.006
 trophy+0.006
apy+0.005
Neg logit contributions
bur-0.009
rying-0.009
ppa-0.009
i-0.008
ety-0.008
Token played
Token ID2826
Feature activation-7.55e-02

Pos logit contributions
 vows+0.048
 prize+0.046
 contest+0.045
 trophy+0.045
cakes+0.045
Neg logit contributions
ppa-0.037
i-0.037
bur-0.036
rying-0.035
ind-0.034
Token games
Token ID1830
Feature activation-7.28e-02

Pos logit contributions
 vows+0.180
apy+0.156
Mine+0.150
cakes+0.149
 Prize+0.148
Neg logit contributions
 owl-0.089
 asking-0.089
rying-0.086
 forth-0.083
ishing-0.082
Token and
Token ID290
Feature activation-9.77e-03

Pos logit contributions
 vows+0.183
apy+0.175
Mine+0.163
ades+0.161
 Sorry+0.160
Neg logit contributions
my-0.078
rying-0.069
 owl-0.068
 since-0.067
 asking-0.066
Token watched
Token ID7342
Feature activation-4.92e-02

Pos logit contributions
 vows+0.016
 prize+0.014
 trophy+0.014
 contest+0.014
ades+0.014
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.019
i-0.019
ind-0.018
Token videos
Token ID5861
Feature activation-1.04e-01

Pos logit contributions
 vows+0.095
 Prize+0.089
case+0.085
ades+0.083
�+0.082
Neg logit contributions
ind-0.073
rying-0.072
 asking-0.072
i-0.072
ting-0.071
Token on
Token ID319
Feature activation-3.32e-02

Pos logit contributions
 vows+0.258
apy+0.243
Mine+0.235
ades+0.223
 Prize+0.223
Neg logit contributions
my-0.103
ting-0.102
 since-0.087
 forth-0.084
rying-0.084
Token the
Token ID262
Feature activation-1.73e-02

Pos logit contributions
 vows+0.066
apy+0.060
cakes+0.058
 Prize+0.058
ades+0.058
Neg logit contributions
ind-0.054
bur-0.053
i-0.052
ppa-0.050
my-0.048
Token computer
Token ID3644
Feature activation-6.08e-02

Pos logit contributions
 vows+0.027
apy+0.024
 prize+0.023
 contest+0.022
 Prize+0.022
Neg logit contributions
bur-0.036
ind-0.036
rying-0.036
ppa-0.035
ior-0.034
Token all
Token ID477
Feature activation+6.95e-03

Pos logit contributions
 vows+0.127
apy+0.117
ades+0.111
 prize+0.108
 Prize+0.108
Neg logit contributions
rying-0.089
my-0.088
i-0.085
bur-0.084
 forth-0.080
Token day
Token ID1110
Feature activation-2.44e-02

Pos logit contributions
bur+0.014
rying+0.013
ppa+0.013
i+0.013
ind+0.013
Neg logit contributions
 vows-0.012
 prize-0.011
 contest-0.011
 trophy-0.011
cakes-0.010
Token and
Token ID290
Feature activation-8.38e-03

Pos logit contributions
 vows+0.037
apy+0.033
 prize+0.033
cakes+0.033
 contest+0.032
Neg logit contributions
bur-0.030
rying-0.030
ppa-0.029
i-0.029
ind-0.027
Token arrows
Token ID20507
Feature activation-2.72e-02

Pos logit contributions
 vows+0.013
 contest+0.011
cakes+0.011
 prize+0.011
 trophy+0.011
Neg logit contributions
bur-0.018
ppa-0.018
rying-0.017
i-0.017
ind-0.017
Token.
Token ID13
Feature activation-2.85e-02

Pos logit contributions
 vows+0.057
apy+0.052
cakes+0.052
 Prize+0.050
 prize+0.050
Neg logit contributions
bur-0.042
rying-0.041
i-0.041
ppa-0.040
cker-0.038
Token They
Token ID1119
Feature activation-1.94e-02

Pos logit contributions
 vows+0.044
apy+0.038
 prize+0.038
 trophy+0.038
 contest+0.035
Neg logit contributions
bur-0.060
ety-0.059
ior-0.058
rying-0.058
my-0.058
Token made
Token ID925
Feature activation-3.93e-02

Pos logit contributions
 vows+0.038
cakes+0.035
 prize+0.034
apy+0.033
 trophy+0.033
Neg logit contributions
bur-0.034
ppa-0.034
i-0.033
ety-0.033
rying-0.032
Token them
Token ID606
Feature activation-1.04e-01

Pos logit contributions
 vows+0.062
cakes+0.057
�+0.057
 contest+0.055
apy+0.054
Neg logit contributions
ind-0.076
rying-0.074
i-0.073
bur-0.073
ppa-0.073
Token from
Token ID422
Feature activation+1.58e-02

Pos logit contributions
 vows+0.185
�+0.183
cakes+0.182
books+0.169
apy+0.166
Neg logit contributions
my-0.177
rying-0.166
 forth-0.165
ety-0.164
i-0.162
Token sticks
Token ID16461
Feature activation-1.47e-02

Pos logit contributions
bur+0.036
rying+0.036
ppa+0.036
i+0.035
ind+0.034
Neg logit contributions
 vows-0.022
 prize-0.020
 contest-0.019
 trophy-0.019
 Prize-0.017
Token and
Token ID290
Feature activation+9.48e-03

Pos logit contributions
 vows+0.033
 prize+0.029
cakes+0.029
 contest+0.029
apy+0.029
Neg logit contributions
bur-0.022
rying-0.022
ppa-0.021
i-0.020
ind-0.020
Token strings
Token ID13042
Feature activation-3.48e-02

Pos logit contributions
bur+0.020
rying+0.020
ppa+0.020
ind+0.019
i+0.019
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.013
 trophy-0.013
apy-0.013
Token and
Token ID290
Feature activation+4.43e-03

Pos logit contributions
 vows+0.076
cakes+0.068
apy+0.067
 Prize+0.067
 prize+0.067
Neg logit contributions
rying-0.052
bur-0.051
i-0.049
ppa-0.048
cker-0.047
Token They
Token ID1119
Feature activation-3.27e-02

Pos logit contributions
 vows+0.037
 prize+0.032
 trophy+0.032
 contest+0.030
apy+0.029
Neg logit contributions
bur-0.047
ety-0.045
ior-0.045
rying-0.045
gie-0.044
Token shared
Token ID4888
Feature activation-4.47e-02

Pos logit contributions
 vows+0.063
 prize+0.061
apy+0.061
ades+0.059
 trophy+0.059
Neg logit contributions
i-0.054
bur-0.053
ppa-0.053
rying-0.053
my-0.048
Token food
Token ID2057
Feature activation-4.37e-02

Pos logit contributions
�+0.074
 vows+0.073
 Prize+0.073
apy+0.072
 contest+0.071
Neg logit contributions
bur-0.078
my-0.076
i-0.074
ppa-0.073
ind-0.072
Token and
Token ID290
Feature activation-4.63e-03

Pos logit contributions
 vows+0.102
Mine+0.097
 Prize+0.097
apy+0.096
 contest+0.093
Neg logit contributions
bur-0.055
i-0.054
ppa-0.052
rying-0.051
my-0.047
Token laughed
Token ID13818
Feature activation-6.09e-02

Pos logit contributions
 vows+0.007
 prize+0.006
 contest+0.006
 trophy+0.006
apy+0.006
Neg logit contributions
bur-0.010
rying-0.010
ppa-0.010
i-0.010
ind-0.009
Token a
Token ID257
Feature activation-1.03e-01

Pos logit contributions
 vows+0.140
 Prize+0.136
Mine+0.136
 contest+0.135
 prize+0.133
Neg logit contributions
rying-0.066
i-0.066
ping-0.060
ind-0.060
 since-0.059
Token lot
Token ID1256
Feature activation-2.42e-02

Pos logit contributions
cakes+0.135
 vows+0.131
case+0.127
apy+0.127
hips+0.126
Neg logit contributions
ind-0.163
my-0.155
 owl-0.154
bur-0.151
ppa-0.150
Token.
Token ID13
Feature activation-1.98e-02

Pos logit contributions
 vows+0.051
apy+0.047
Mine+0.047
 contest+0.045
 Prize+0.045
Neg logit contributions
rying-0.038
ppa-0.036
i-0.036
bur-0.035
ind-0.035
Token
Token ID198
Feature activation-1.33e-02

Pos logit contributions
 vows+0.033
 prize+0.030
 trophy+0.030
 contest+0.029
ades+0.028
Neg logit contributions
bur-0.038
ior-0.036
rying-0.036
ety-0.036
gie-0.036
Token
Token ID198
Feature activation-2.90e-02

Pos logit contributions
 vows+0.022
 prize+0.019
 trophy+0.019
 contest+0.019
cakes+0.018
Neg logit contributions
bur-0.027
ppa-0.026
rying-0.026
ind-0.026
i-0.025
TokenThe
Token ID464
Feature activation-1.82e-02

Pos logit contributions
 vows+0.066
 prize+0.060
 trophy+0.059
cakes+0.058
 contest+0.056
Neg logit contributions
ind-0.041
bur-0.040
ppa-0.040
rying-0.039
cker-0.036
Token cheered
Token ID34767
Feature activation-4.00e-02

Pos logit contributions
 vows+0.058
ades+0.055
 prize+0.053
case+0.053
cakes+0.053
Neg logit contributions
i-0.060
bur-0.057
ppa-0.057
rying-0.056
 forth-0.056
Token very
Token ID845
Feature activation-6.26e-02

Pos logit contributions
 vows+0.096
case+0.092
apy+0.092
cakes+0.091
 Prize+0.090
Neg logit contributions
rying-0.049
i-0.047
ind-0.045
my-0.041
 forth-0.040
Token loudly
Token ID23112
Feature activation-3.59e-02

Pos logit contributions
cakes+0.100
�+0.096
 vows+0.094
Mine+0.092
uits+0.092
Neg logit contributions
ind-0.120
i-0.112
rying-0.111
ppa-0.104
 aware-0.097
Token because
Token ID780
Feature activation-3.14e-02

Pos logit contributions
 vows+0.075
apy+0.072
 trophy+0.071
 prize+0.069
cakes+0.069
Neg logit contributions
rying-0.054
i-0.050
ind-0.048
bur-0.048
gie-0.047
Token the
Token ID262
Feature activation-5.30e-02

Pos logit contributions
 vows+0.038
ades+0.029
 prize+0.028
 Prize+0.028
cakes+0.027
Neg logit contributions
bur-0.073
rying-0.071
my-0.071
ind-0.070
 owl-0.070
Token dance
Token ID9280
Feature activation-1.03e-01

Pos logit contributions
 vows+0.080
apy+0.079
ades+0.073
cakes+0.073
case+0.067
Neg logit contributions
 owl-0.098
rying-0.096
my-0.093
 forth-0.093
ind-0.092
Token was
Token ID373
Feature activation-3.74e-02

Pos logit contributions
 vows+0.184
apy+0.180
Mine+0.174
ades+0.169
 trophy+0.162
Neg logit contributions
i-0.144
rying-0.143
ting-0.134
row-0.131
 owl-0.131
Token so
Token ID523
Feature activation-6.09e-02

Pos logit contributions
 vows+0.075
cakes+0.067
Mine+0.066
apy+0.065
 prize+0.065
Neg logit contributions
bur-0.063
rying-0.062
ppa-0.057
i-0.057
my-0.056
Token good
Token ID922
Feature activation-2.33e-02

Pos logit contributions
 vows+0.110
�+0.108
 tray+0.105
 mat+0.101
 prize+0.099
Neg logit contributions
ind-0.095
rying-0.088
ety-0.087
 aware-0.083
my-0.083
Token.
Token ID13
Feature activation-3.33e-02

Pos logit contributions
 vows+0.050
apy+0.045
Mine+0.043
 prize+0.043
 Prize+0.043
Neg logit contributions
rying-0.037
i-0.035
bur-0.035
ppa-0.033
ind-0.033
Token Everyone
Token ID11075
Feature activation-4.42e-02

Pos logit contributions
 vows+0.053
 trophy+0.047
 prize+0.047
apy+0.046
ades+0.043
Neg logit contributions
ior-0.064
bur-0.064
my-0.064
ety-0.063
gie-0.059
Token taught
Token ID7817
Feature activation+1.28e-02

Pos logit contributions
 vows+0.022
 prize+0.021
 contest+0.020
cakes+0.020
 trophy+0.020
Neg logit contributions
bur-0.024
i-0.023
rying-0.023
ppa-0.023
ind-0.022
Token her
Token ID607
Feature activation-3.87e-02

Pos logit contributions
rying+0.029
bur+0.029
ppa+0.028
ind+0.027
cker+0.027
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
 trophy-0.016
cakes-0.015
Token friends
Token ID2460
Feature activation-5.64e-02

Pos logit contributions
 vows+0.078
 Prize+0.072
 contest+0.071
Mine+0.069
 prize+0.067
Neg logit contributions
i-0.056
 owl-0.054
my-0.054
ppa-0.054
rying-0.053
Token and
Token ID290
Feature activation-9.29e-03

Pos logit contributions
 vows+0.123
 Prize+0.109
 prize+0.108
 contest+0.108
apy+0.108
Neg logit contributions
my-0.080
i-0.080
rying-0.079
bur-0.074
ind-0.072
Token her
Token ID607
Feature activation-4.16e-02

Pos logit contributions
 vows+0.014
 prize+0.013
 contest+0.013
 trophy+0.012
cakes+0.012
Neg logit contributions
bur-0.020
rying-0.019
ppa-0.019
i-0.019
ind-0.018
Token sisters
Token ID15153
Feature activation-1.03e-01

Pos logit contributions
 vows+0.089
 Prize+0.081
Mine+0.081
cakes+0.079
apy+0.079
Neg logit contributions
 owl-0.054
 axe-0.053
rying-0.051
i-0.051
my-0.051
Token how
Token ID703
Feature activation-2.46e-02

Pos logit contributions
 vows+0.199
 Prize+0.182
apy+0.174
 Bang+0.174
 disco+0.173
Neg logit contributions
my-0.154
 aware-0.152
rying-0.147
i-0.136
 asking-0.135
Token to
Token ID284
Feature activation-3.20e-03

Pos logit contributions
 vows+0.054
 prize+0.048
 trophy+0.046
 Prize+0.046
 contest+0.046
Neg logit contributions
rying-0.039
i-0.035
ppa-0.035
ety-0.034
bur-0.034
Token build
Token ID1382
Feature activation-4.92e-02

Pos logit contributions
 vows+0.005
 prize+0.004
 contest+0.004
cakes+0.004
 trophy+0.004
Neg logit contributions
bur-0.007
rying-0.007
ppa-0.007
i-0.007
ind-0.007
Token them
Token ID606
Feature activation-5.57e-02

Pos logit contributions
 vows+0.097
 Prize+0.081
cakes+0.080
 trophy+0.078
apy+0.077
Neg logit contributions
rying-0.086
bur-0.081
i-0.080
my-0.079
ishing-0.077
Token too
Token ID1165
Feature activation-2.38e-02

Pos logit contributions
 vows+0.119
 Prize+0.096
Mine+0.096
apy+0.094
cakes+0.093
Neg logit contributions
rying-0.100
my-0.085
 forth-0.085
bur-0.084
i-0.083
Token the
Token ID262
Feature activation-3.78e-03

Pos logit contributions
 vows+0.006
 prize+0.005
 contest+0.005
 trophy+0.005
cakes+0.005
Neg logit contributions
bur-0.008
rying-0.008
ppa-0.008
i-0.008
ind-0.007
Token pictures
Token ID5986
Feature activation-5.50e-02

Pos logit contributions
 vows+0.005
apy+0.004
 prize+0.004
 contest+0.004
 trophy+0.004
Neg logit contributions
bur-0.009
rying-0.008
ppa-0.008
ind-0.008
i-0.008
Token and
Token ID290
Feature activation+6.94e-03

Pos logit contributions
 vows+0.130
 Prize+0.118
Mine+0.117
apy+0.115
ades+0.114
Neg logit contributions
my-0.064
i-0.063
rying-0.061
bur-0.059
 owl-0.059
Token said
Token ID531
Feature activation-6.51e-02

Pos logit contributions
bur+0.013
rying+0.013
ppa+0.013
ind+0.012
i+0.012
Neg logit contributions
 vows-0.013
 prize-0.011
 contest-0.011
 trophy-0.011
cakes-0.011
Token the
Token ID262
Feature activation-1.72e-02

Pos logit contributions
Mine+0.132
�+0.131
case+0.127
 vows+0.126
 blast+0.125
Neg logit contributions
i-0.082
 owl-0.081
 Owl-0.074
ppa-0.073
 asking-0.071
Token names
Token ID3891
Feature activation-1.02e-01

Pos logit contributions
 vows+0.025
apy+0.024
cakes+0.022
ades+0.022
 trophy+0.021
Neg logit contributions
bur-0.035
ppa-0.035
rying-0.035
ind-0.034
i-0.034
Token of
Token ID286
Feature activation-2.60e-02

Pos logit contributions
 Prize+0.207
�+0.207
 vows+0.205
apy+0.200
Mine+0.199
Neg logit contributions
my-0.131
i-0.121
 owl-0.111
bur-0.107
ting-0.103
Token the
Token ID262
Feature activation-1.25e-02

Pos logit contributions
 vows+0.046
cakes+0.042
apy+0.042
case+0.041
ades+0.040
Neg logit contributions
bur-0.048
i-0.047
ind-0.046
ppa-0.046
rying-0.045
Token things
Token ID1243
Feature activation-7.72e-02

Pos logit contributions
 vows+0.018
apy+0.017
 trophy+0.016
cakes+0.016
 prize+0.016
Neg logit contributions
bur-0.026
rying-0.026
ppa-0.026
ind-0.026
i-0.025
Token she
Token ID673
Feature activation+1.00e-02

Pos logit contributions
 vows+0.153
 Prize+0.144
apy+0.139
 blast+0.137
Mine+0.137
Neg logit contributions
i-0.120
my-0.110
rying-0.109
bur-0.107
 owl-0.104
Token saw
Token ID2497
Feature activation+2.61e-03

Pos logit contributions
bur+0.020
rying+0.020
ppa+0.019
ind+0.018
i+0.018
Neg logit contributions
 vows-0.017
 prize-0.016
 contest-0.015
 trophy-0.015
cakes-0.015
Token funny
Token ID8258
Feature activation-5.21e-02

Pos logit contributions
 vows+0.081
apy+0.081
ades+0.067
ves+0.067
 Prize+0.064
Neg logit contributions
my-0.102
bur-0.098
 owl-0.094
ind-0.090
ior-0.089
Token animals
Token ID4695
Feature activation-4.57e-02

Pos logit contributions
 vows+0.076
apy+0.070
 Prize+0.068
 prize+0.067
 contest+0.067
Neg logit contributions
my-0.105
ind-0.100
ping-0.099
ior-0.098
 owl-0.097
Token and
Token ID290
Feature activation-1.29e-02

Pos logit contributions
 vows+0.107
Mine+0.099
apy+0.097
 prize+0.095
 Prize+0.095
Neg logit contributions
i-0.063
rying-0.060
bur-0.059
my-0.056
ppa-0.055
Token the
Token ID262
Feature activation-2.35e-02

Pos logit contributions
 vows+0.021
 prize+0.019
 contest+0.019
 trophy+0.019
ades+0.018
Neg logit contributions
bur-0.026
ppa-0.025
i-0.025
rying-0.025
ety-0.024
Token silly
Token ID14397
Feature activation-2.85e-02

Pos logit contributions
 vows+0.042
apy+0.039
 prize+0.037
cakes+0.037
 trophy+0.036
Neg logit contributions
bur-0.043
rying-0.040
ind-0.040
i-0.039
gie-0.039
Token jokes
Token ID14532
Feature activation-1.02e-01

Pos logit contributions
 vows+0.052
apy+0.048
 prize+0.048
 trophy+0.047
 contest+0.047
Neg logit contributions
i-0.048
ind-0.048
bur-0.047
rying-0.047
gie-0.047
Token.
Token ID13
Feature activation-2.24e-02

Pos logit contributions
 vows+0.220
igsaw+0.217
 Prize+0.215
Mine+0.211
ades+0.206
Neg logit contributions
i-0.114
ting-0.107
my-0.101
bur-0.097
gie-0.097
Token But
Token ID887
Feature activation+1.71e-02

Pos logit contributions
 vows+0.039
 prize+0.035
 trophy+0.035
 contest+0.033
apy+0.033
Neg logit contributions
bur-0.044
ety-0.043
my-0.042
ior-0.042
rying-0.039
Token sometimes
Token ID3360
Feature activation-2.68e-02

Pos logit contributions
rying+0.035
bur+0.034
ppa+0.034
ind+0.033
i+0.032
Neg logit contributions
 vows-0.029
 prize-0.026
 contest-0.026
 trophy-0.025
apy-0.025
Token they
Token ID484
Feature activation-2.97e-02

Pos logit contributions
 vows+0.035
cakes+0.031
ades+0.029
 prize+0.029
 trophy+0.028
Neg logit contributions
i-0.063
bur-0.061
ppa-0.060
rying-0.059
ety-0.058
Token wanted
Token ID2227
Feature activation-3.11e-02

Pos logit contributions
 vows+0.056
 prize+0.052
cakes+0.050
ades+0.049
 trophy+0.049
Neg logit contributions
bur-0.054
i-0.053
ppa-0.051
ety-0.050
rying-0.050
Token diamond
Token ID15291
Feature activation-3.83e-02

Pos logit contributions
 vows+0.084
cakes+0.082
ades+0.074
apy+0.072
ves+0.069
Neg logit contributions
 owl-0.103
bur-0.099
cker-0.098
 axe-0.097
my-0.097
Token.
Token ID13
Feature activation-1.54e-02

Pos logit contributions
 vows+0.076
apy+0.070
cakes+0.069
Mine+0.069
ades+0.068
Neg logit contributions
i-0.060
rying-0.059
bur-0.059
cker-0.057
gie-0.055
Token They
Token ID1119
Feature activation-5.02e-02

Pos logit contributions
 vows+0.022
 trophy+0.020
 prize+0.020
 contest+0.019
cakes+0.018
Neg logit contributions
bur-0.034
ety-0.033
ppa-0.033
rying-0.033
i-0.033
Token said
Token ID531
Feature activation-7.40e-02

Pos logit contributions
 vows+0.084
cakes+0.081
apy+0.079
 prize+0.078
ades+0.078
Neg logit contributions
i-0.095
bur-0.094
my-0.092
ppa-0.088
cker-0.087
Token the
Token ID262
Feature activation-2.41e-02

Pos logit contributions
�+0.166
case+0.156
cakes+0.150
Mine+0.149
books+0.146
Neg logit contributions
i-0.082
 owl-0.080
 Owl-0.072
 asking-0.071
ener-0.068
Token names
Token ID3891
Feature activation-1.02e-01

Pos logit contributions
 vows+0.037
apy+0.034
cakes+0.034
ades+0.031
ves+0.029
Neg logit contributions
bur-0.049
rying-0.047
 owl-0.047
cker-0.047
my-0.046
Token of
Token ID286
Feature activation-3.02e-02

Pos logit contributions
 vows+0.205
�+0.203
 Prize+0.195
Mine+0.190
apy+0.190
Neg logit contributions
my-0.131
i-0.122
 owl-0.111
ener-0.107
ie-0.106
Token the
Token ID262
Feature activation-2.21e-02

Pos logit contributions
 vows+0.055
cakes+0.051
case+0.051
apy+0.049
 prize+0.047
Neg logit contributions
bur-0.054
i-0.053
ind-0.052
rying-0.050
ppa-0.050
Token shapes
Token ID15268
Feature activation-1.03e-01

Pos logit contributions
 vows+0.034
apy+0.031
cakes+0.030
ades+0.028
case+0.027
Neg logit contributions
bur-0.045
rying-0.044
i-0.043
ind-0.043
my-0.043
Token and
Token ID290
Feature activation-8.87e-03

Pos logit contributions
 vows+0.224
Mine+0.219
Goal+0.218
apy+0.217
�+0.217
Neg logit contributions
i-0.126
my-0.116
rying-0.106
cker-0.101
 owl-0.101
Token looked
Token ID3114
Feature activation-4.17e-02

Pos logit contributions
 vows+0.013
 prize+0.012
 contest+0.011
cakes+0.011
 trophy+0.011
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.018
i-0.018
ind-0.018
Token a
Token ID257
Feature activation-7.83e-02

Pos logit contributions
 vows+0.113
cakes+0.095
apy+0.094
Mine+0.094
 Prize+0.093
Neg logit contributions
rying-0.060
 owl-0.054
ishing-0.053
bur-0.051
ppa-0.051
Token game
Token ID983
Feature activation-4.13e-02

Pos logit contributions
 vows+0.100
uits+0.091
apy+0.088
cakes+0.086
 Both+0.086
Neg logit contributions
ind-0.173
rying-0.154
ppa-0.153
 owl-0.153
ich-0.147
Token.
Token ID13
Feature activation-7.28e-03

Pos logit contributions
 vows+0.091
apy+0.075
 trophy+0.074
 prize+0.073
 Prize+0.073
Neg logit contributions
rying-0.065
bur-0.060
my-0.058
ppa-0.057
i-0.057
Token She
Token ID1375
Feature activation+3.84e-03

Pos logit contributions
 vows+0.012
 prize+0.010
 trophy+0.010
 contest+0.010
ades+0.010
Neg logit contributions
bur-0.015
ppa-0.015
rying-0.015
ety-0.014
i-0.014
Token won
Token ID1839
Feature activation-2.33e-02

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
i+0.007
ind+0.007
Neg logit contributions
 vows-0.007
 prize-0.006
 contest-0.006
 trophy-0.006
cakes-0.006
Token a
Token ID257
Feature activation-1.01e-01

Pos logit contributions
 vows+0.046
 trophy+0.040
 prize+0.038
apy+0.038
ades+0.038
Neg logit contributions
bur-0.042
rying-0.041
ppa-0.040
i-0.039
my-0.038
Token prize
Token ID11596
Feature activation-2.68e-02

Pos logit contributions
uits+0.128
 vows+0.119
apy+0.117
 are+0.106
 Everybody+0.099
Neg logit contributions
ind-0.207
ety-0.195
 owl-0.193
rying-0.192
ppa-0.186
Token!
Token ID0
Feature activation-1.07e-02

Pos logit contributions
 vows+0.059
apy+0.053
Mine+0.050
ades+0.050
 trophy+0.049
Neg logit contributions
rying-0.041
bur-0.040
i-0.039
ppa-0.039
ety-0.036
Token It
Token ID632
Feature activation-3.60e-02

Pos logit contributions
 vows+0.018
 prize+0.015
 trophy+0.015
 contest+0.015
ades+0.015
Neg logit contributions
bur-0.022
ppa-0.021
ety-0.021
rying-0.021
my-0.020
Token was
Token ID373
Feature activation-2.68e-02

Pos logit contributions
 vows+0.074
apy+0.065
 prize+0.064
 trophy+0.064
ades+0.063
Neg logit contributions
bur-0.060
i-0.058
my-0.057
rying-0.055
ety-0.055
Token a
Token ID257
Feature activation-6.62e-02

Pos logit contributions
 vows+0.055
 trophy+0.047
ades+0.047
apy+0.046
cakes+0.046
Neg logit contributions
bur-0.047
i-0.042
ppa-0.042
rying-0.042
ety-0.042
Token talked
Token ID6619
Feature activation-5.57e-02

Pos logit contributions
 vows+0.069
 prize+0.069
 trophy+0.068
 contest+0.067
 Prize+0.065
Neg logit contributions
ppa-0.054
i-0.053
bur-0.052
ety-0.048
rying-0.048
Token to
Token ID284
Feature activation-1.16e-02

Pos logit contributions
 vows+0.134
�+0.133
 Prize+0.131
apy+0.131
 trophy+0.130
Neg logit contributions
my-0.056
bur-0.048
rying-0.047
i-0.047
ppa-0.047
Token them
Token ID606
Feature activation-7.02e-02

Pos logit contributions
 vows+0.017
 prize+0.015
 trophy+0.015
 contest+0.015
cakes+0.015
Neg logit contributions
bur-0.025
ppa-0.025
i-0.024
rying-0.024
ind-0.024
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
apy+0.171
 vows+0.171
Mine+0.164
 Prize+0.162
�+0.159
Neg logit contributions
i-0.076
rying-0.073
my-0.072
bur-0.063
 owl-0.062
Token made
Token ID925
Feature activation-3.69e-02

Pos logit contributions
 vows+0.030
 prize+0.028
 trophy+0.027
 contest+0.027
ades+0.027
Neg logit contributions
bur-0.029
ppa-0.029
rying-0.028
i-0.028
ety-0.026
Token them
Token ID606
Feature activation-1.01e-01

Pos logit contributions
 vows+0.055
 Prize+0.052
 trophy+0.052
 prize+0.051
 contest+0.051
Neg logit contributions
i-0.075
ind-0.074
rying-0.074
bur-0.073
ppa-0.073
Token talk
Token ID1561
Feature activation-6.20e-02

Pos logit contributions
�+0.163
 Prize+0.156
 vows+0.149
Mine+0.146
ival+0.142
Neg logit contributions
my-0.189
rying-0.186
i-0.173
ety-0.166
bur-0.165
Token back
Token ID736
Feature activation-1.68e-02

Pos logit contributions
apy+0.148
�+0.147
 Prize+0.142
 vows+0.142
Mine+0.141
Neg logit contributions
my-0.065
rying-0.065
ind-0.061
i-0.060
 owl-0.058
Token.
Token ID13
Feature activation-1.41e-02

Pos logit contributions
 vows+0.033
 contest+0.030
 prize+0.030
apy+0.030
 trophy+0.030
Neg logit contributions
rying-0.028
bur-0.028
ind-0.027
i-0.027
ppa-0.027
Token
Token ID198
Feature activation+9.07e-03

Pos logit contributions
 vows+0.023
 prize+0.021
 trophy+0.021
 contest+0.020
cakes+0.019
Neg logit contributions
bur-0.029
ppa-0.028
rying-0.027
ety-0.027
i-0.027
Token
Token ID198
Feature activation+9.30e-03

Pos logit contributions
bur+0.021
rying+0.021
ppa+0.021
i+0.021
ind+0.020
Neg logit contributions
 vows-0.012
 prize-0.010
 contest-0.010
 trophy-0.010
apy-0.010
Token dolls
Token ID36062
Feature activation-2.86e-02

Pos logit contributions
apy+0.034
 vows+0.034
cakes+0.031
ades+0.031
case+0.031
Neg logit contributions
bur-0.048
ppa-0.048
rying-0.046
i-0.046
ind-0.046
Token'
Token ID6
Feature activation-4.06e-03

Pos logit contributions
 vows+0.061
 Prize+0.055
apy+0.055
Mine+0.055
cakes+0.054
Neg logit contributions
rying-0.044
bur-0.043
i-0.042
ppa-0.042
ind-0.039
Token hands
Token ID2832
Feature activation+9.05e-04

Pos logit contributions
 vows+0.006
 prize+0.006
 trophy+0.006
 contest+0.006
apy+0.006
Neg logit contributions
bur-0.008
rying-0.008
ppa-0.008
ind-0.008
i-0.008
Token and
Token ID290
Feature activation-1.42e-02

Pos logit contributions
bur+0.002
rying+0.002
ppa+0.002
i+0.001
ind+0.001
Neg logit contributions
 vows-0.002
 prize-0.002
 contest-0.002
 trophy-0.002
cakes-0.002
Token made
Token ID925
Feature activation-4.93e-02

Pos logit contributions
 vows+0.024
 prize+0.022
 contest+0.022
 trophy+0.022
cakes+0.022
Neg logit contributions
bur-0.027
ppa-0.027
i-0.026
rying-0.026
cker-0.025
Token them
Token ID606
Feature activation-1.01e-01

Pos logit contributions
�+0.075
 vows+0.075
 trophy+0.072
 Prize+0.071
 contest+0.071
Neg logit contributions
i-0.093
ind-0.092
rying-0.091
ppa-0.090
bur-0.089
Token say
Token ID910
Feature activation-9.12e-02

Pos logit contributions
�+0.154
 Prize+0.136
Mine+0.134
 vows+0.130
cakes+0.126
Neg logit contributions
rying-0.194
my-0.190
i-0.189
 aware-0.174
bur-0.174
Token,
Token ID11
Feature activation-4.56e-02

Pos logit contributions
Mine+0.184
case+0.169
�+0.165
 trophy+0.158
igsaw+0.157
Neg logit contributions
i-0.120
 owl-0.109
 asking-0.107
ppa-0.106
rying-0.102
Token "
Token ID366
Feature activation-1.86e-02

Pos logit contributions
 vows+0.070
 prize+0.065
 trophy+0.063
case+0.063
 contest+0.062
Neg logit contributions
gie-0.089
rying-0.088
bur-0.086
ppa-0.085
i-0.084
TokenI
Token ID40
Feature activation-4.88e-02

Pos logit contributions
 vows+0.030
 trophy+0.028
 prize+0.028
apy+0.027
 contest+0.027
Neg logit contributions
bur-0.038
ppa-0.037
ind-0.036
i-0.035
ety-0.035
Token do
Token ID466
Feature activation-5.06e-02

Pos logit contributions
cakes+0.091
apy+0.088
 trophy+0.087
ades+0.087
 vows+0.086
Neg logit contributions
i-0.081
bur-0.080
rying-0.074
my-0.074
 seen-0.074
Token fan
Token ID4336
Feature activation-1.72e-02

Pos logit contributions
 vows+0.071
 Prize+0.057
cakes+0.057
apy+0.056
case+0.054
Neg logit contributions
bur-0.082
my-0.076
 axe-0.075
ind-0.074
 owl-0.074
Token.
Token ID13
Feature activation-3.40e-02

Pos logit contributions
 vows+0.033
apy+0.029
 prize+0.029
 trophy+0.029
cakes+0.028
Neg logit contributions
rying-0.031
bur-0.030
i-0.029
ppa-0.028
ind-0.028
Token They
Token ID1119
Feature activation-6.04e-02

Pos logit contributions
 vows+0.056
 trophy+0.050
 prize+0.048
 contest+0.046
 festival+0.045
Neg logit contributions
gie-0.067
bur-0.064
ety-0.063
rying-0.063
my-0.063
Token pretend
Token ID16614
Feature activation-5.27e-02

Pos logit contributions
cakes+0.109
 vows+0.106
ades+0.101
apy+0.093
ival+0.088
Neg logit contributions
my-0.115
bur-0.114
i-0.110
 forth-0.109
ety-0.104
Token the
Token ID262
Feature activation-4.34e-02

Pos logit contributions
 vows+0.107
 Prize+0.099
�+0.098
Mine+0.095
 prize+0.093
Neg logit contributions
bur-0.070
rying-0.069
 owl-0.069
i-0.068
 forth-0.068
Token shapes
Token ID15268
Feature activation-1.01e-01

Pos logit contributions
 vows+0.069
apy+0.061
cakes+0.059
 Prize+0.058
uits+0.057
Neg logit contributions
bur-0.086
 owl-0.078
my-0.078
 axe-0.077
ind-0.075
Token are
Token ID389
Feature activation-1.07e-02

Pos logit contributions
 vows+0.196
�+0.187
 Prize+0.186
ival+0.184
cakes+0.183
Neg logit contributions
i-0.143
rying-0.136
cker-0.135
my-0.134
bur-0.130
Token flying
Token ID7348
Feature activation-2.80e-02

Pos logit contributions
 vows+0.021
 prize+0.019
cakes+0.019
 trophy+0.019
 contest+0.019
Neg logit contributions
bur-0.019
rying-0.018
ppa-0.018
i-0.017
ind-0.017
Token.
Token ID13
Feature activation-3.26e-02

Pos logit contributions
 vows+0.064
cakes+0.057
apy+0.057
 trophy+0.055
 prize+0.054
Neg logit contributions
rying-0.040
bur-0.039
i-0.038
ind-0.037
ety-0.036
Token They
Token ID1119
Feature activation-6.73e-02

Pos logit contributions
 vows+0.052
 trophy+0.047
 prize+0.045
 contest+0.042
 festival+0.042
Neg logit contributions
gie-0.066
bur-0.064
ety-0.064
my-0.063
rying-0.063
Token have
Token ID423
Feature activation-4.50e-02

Pos logit contributions
cakes+0.118
 vows+0.110
ades+0.107
apy+0.099
ival+0.095
Neg logit contributions
bur-0.129
my-0.129
i-0.127
 forth-0.123
cker-0.119
Token.
Token ID13
Feature activation-5.14e-02

Pos logit contributions
 vows+0.132
 Prize+0.123
cakes+0.121
apy+0.121
 prize+0.118
Neg logit contributions
rying-0.072
i-0.069
my-0.065
bur-0.063
cker-0.061
Token They
Token ID1119
Feature activation-4.54e-02

Pos logit contributions
 vows+0.089
 prize+0.084
 trophy+0.083
kin+0.081
ades+0.081
Neg logit contributions
ior-0.090
ety-0.079
gie-0.077
my-0.076
bur-0.074
Token both
Token ID1111
Feature activation-3.74e-02

Pos logit contributions
 vows+0.069
cakes+0.068
apy+0.063
ades+0.062
ves+0.062
Neg logit contributions
i-0.094
my-0.093
bur-0.092
rying-0.088
ppa-0.088
Token think
Token ID892
Feature activation-5.39e-02

Pos logit contributions
 vows+0.052
cakes+0.051
ades+0.047
apy+0.045
 prize+0.044
Neg logit contributions
i-0.082
rying-0.081
my-0.081
bur-0.080
cker-0.079
Token their
Token ID511
Feature activation-4.59e-02

Pos logit contributions
 vows+0.102
 Prize+0.092
Mine+0.089
�+0.087
cakes+0.084
Neg logit contributions
i-0.081
rying-0.076
my-0.075
 owl-0.074
 asking-0.074
Token shapes
Token ID15268
Feature activation-9.94e-02

Pos logit contributions
cakes+0.081
ades+0.071
apy+0.071
ival+0.071
 Prize+0.071
Neg logit contributions
ind-0.081
i-0.074
 owl-0.072
bur-0.071
ener-0.070
Token are
Token ID389
Feature activation-3.48e-02

Pos logit contributions
 vows+0.133
 Prize+0.128
cakes+0.120
apy+0.120
ival+0.119
Neg logit contributions
my-0.211
i-0.203
cker-0.197
rying-0.194
bur-0.191
Token good
Token ID922
Feature activation-1.86e-02

Pos logit contributions
 vows+0.058
cakes+0.053
apy+0.051
 Prize+0.050
case+0.050
Neg logit contributions
bur-0.067
rying-0.067
i-0.066
ppa-0.066
cker-0.063
Token.
Token ID13
Feature activation-2.63e-02

Pos logit contributions
 vows+0.039
apy+0.035
cakes+0.034
ades+0.034
 trophy+0.034
Neg logit contributions
rying-0.030
i-0.029
bur-0.028
ppa-0.027
ety-0.027
Token But
Token ID887
Feature activation-4.00e-03

Pos logit contributions
 vows+0.039
 trophy+0.037
 prize+0.037
 contest+0.035
ades+0.033
Neg logit contributions
ior-0.055
bur-0.053
ety-0.053
my-0.050
ind-0.050
Token they
Token ID484
Feature activation-3.17e-02

Pos logit contributions
 vows+0.006
 prize+0.006
 trophy+0.006
 contest+0.006
cakes+0.006
Neg logit contributions
bur-0.008
rying-0.008
ppa-0.008
i-0.008
ind-0.008
Token pushed
Token ID7121
Feature activation+6.40e-03

Pos logit contributions
 vows+0.068
 prize+0.064
 trophy+0.061
 contest+0.060
 Prize+0.059
Neg logit contributions
ppa-0.057
i-0.057
my-0.057
rying-0.055
bur-0.055
Token the
Token ID262
Feature activation-3.51e-02

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
ind+0.013
i+0.013
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.008
 trophy-0.008
cakes-0.008
Token buttons
Token ID12163
Feature activation-3.81e-02

Pos logit contributions
 vows+0.046
apy+0.044
 prize+0.039
ves+0.039
 Prize+0.038
Neg logit contributions
my-0.074
ind-0.074
rying-0.073
ener-0.072
bur-0.071
Token and
Token ID290
Feature activation-8.03e-03

Pos logit contributions
 vows+0.088
 Prize+0.076
 prize+0.076
cakes+0.075
 contest+0.074
Neg logit contributions
rying-0.055
bur-0.053
i-0.051
my-0.049
gie-0.047
Token the
Token ID262
Feature activation-3.85e-02

Pos logit contributions
 vows+0.015
 prize+0.013
 trophy+0.013
 contest+0.013
cakes+0.012
Neg logit contributions
bur-0.015
rying-0.015
ppa-0.014
i-0.014
gie-0.014
Token images
Token ID4263
Feature activation-9.94e-02

Pos logit contributions
 vows+0.071
apy+0.068
 Prize+0.065
ades+0.065
ves+0.064
Neg logit contributions
my-0.058
ener-0.058
 owl-0.057
ind-0.056
rying-0.056
Token changed
Token ID3421
Feature activation-2.46e-02

Pos logit contributions
 vows+0.180
 Prize+0.177
 prize+0.155
 festival+0.155
 coach+0.155
Neg logit contributions
rying-0.156
 forth-0.153
i-0.152
my-0.148
ener-0.144
Token back
Token ID736
Feature activation+2.64e-03

Pos logit contributions
 vows+0.047
 prize+0.043
 contest+0.043
 trophy+0.043
cakes+0.042
Neg logit contributions
rying-0.043
bur-0.041
i-0.041
ind-0.040
ppa-0.039
Token to
Token ID284
Feature activation-2.71e-02

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.005
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token the
Token ID262
Feature activation-2.33e-02

Pos logit contributions
 vows+0.045
cakes+0.042
ades+0.040
 trophy+0.040
 prize+0.039
Neg logit contributions
rying-0.052
bur-0.051
ind-0.050
i-0.049
my-0.048
Token way
Token ID835
Feature activation-1.54e-02

Pos logit contributions
 vows+0.031
apy+0.029
 prize+0.026
ves+0.026
ades+0.025
Neg logit contributions
ind-0.052
rying-0.051
bur-0.051
my-0.050
ppa-0.049
Tokenmy
Token ID1820
Feature activation-1.05e-03

Pos logit contributions
rying+0.032
bur+0.031
ppa+0.031
ind+0.030
cker+0.028
Neg logit contributions
 vows-0.046
 prize-0.042
 contest-0.042
 trophy-0.042
cakes-0.041
Token and
Token ID290
Feature activation-3.18e-03

Pos logit contributions
 vows+0.002
 prize+0.002
 contest+0.002
 trophy+0.002
apy+0.002
Neg logit contributions
bur-0.002
rying-0.002
ppa-0.002
i-0.002
ind-0.002
Token daddy
Token ID35822
Feature activation-2.56e-02

Pos logit contributions
 vows+0.006
 prize+0.005
 contest+0.005
 trophy+0.005
cakes+0.005
Neg logit contributions
bur-0.006
ppa-0.006
rying-0.006
i-0.006
ind-0.006
Token and
Token ID290
Feature activation-1.09e-02

Pos logit contributions
 vows+0.050
 prize+0.046
apy+0.045
cakes+0.045
 contest+0.045
Neg logit contributions
bur-0.044
i-0.044
rying-0.043
ppa-0.043
my-0.041
Token made
Token ID925
Feature activation-3.88e-02

Pos logit contributions
 vows+0.017
 prize+0.015
 contest+0.015
 trophy+0.015
ades+0.015
Neg logit contributions
bur-0.023
ppa-0.022
i-0.022
rying-0.022
ety-0.021
Token them
Token ID606
Feature activation-9.93e-02

Pos logit contributions
 vows+0.067
 Prize+0.058
 prize+0.058
case+0.058
 trophy+0.057
Neg logit contributions
i-0.074
rying-0.071
ind-0.071
ppa-0.071
bur-0.070
Token smile
Token ID8212
Feature activation-3.90e-02

Pos logit contributions
 vows+0.163
�+0.148
 Prize+0.144
books+0.143
case+0.140
Neg logit contributions
my-0.188
rying-0.178
 forth-0.168
i-0.161
bur-0.157
Token.
Token ID13
Feature activation-5.41e-03

Pos logit contributions
 vows+0.083
 contest+0.080
 prize+0.079
cakes+0.079
ades+0.078
Neg logit contributions
i-0.055
rying-0.054
bur-0.052
ppa-0.051
ind-0.051
Token One
Token ID1881
Feature activation-7.31e-03

Pos logit contributions
 vows+0.008
 prize+0.007
 trophy+0.007
 contest+0.007
cakes+0.007
Neg logit contributions
bur-0.012
rying-0.012
ppa-0.012
i-0.011
ind-0.011
Token day
Token ID1110
Feature activation-4.31e-02

Pos logit contributions
 vows+0.015
 prize+0.013
cakes+0.013
 trophy+0.013
 contest+0.013
Neg logit contributions
bur-0.012
rying-0.012
i-0.012
ppa-0.012
ind-0.011
Token,
Token ID11
Feature activation-2.35e-02

Pos logit contributions
 vows+0.089
ades+0.085
case+0.084
 trophy+0.084
cakes+0.081
Neg logit contributions
i-0.065
ppa-0.057
bur-0.057
my-0.055
 Owl-0.054
Token for
Token ID329
Feature activation+1.82e-02

Pos logit contributions
 vows+0.004
 prize+0.003
 contest+0.003
 trophy+0.003
apy+0.003
Neg logit contributions
bur-0.004
rying-0.004
ppa-0.004
i-0.004
ind-0.004
Token him
Token ID683
Feature activation+7.40e-03

Pos logit contributions
rying+0.037
bur+0.037
ppa+0.036
ind+0.035
i+0.035
Neg logit contributions
 vows-0.030
 prize-0.028
 contest-0.027
 trophy-0.027
apy-0.026
Token.
Token ID13
Feature activation+2.13e-02

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
ind+0.014
i+0.014
Neg logit contributions
 vows-0.013
 prize-0.012
 contest-0.011
 trophy-0.011
cakes-0.011
Token
Token ID198
Feature activation+2.47e-02

Pos logit contributions
rying+0.057
ppa+0.056
bur+0.055
ind+0.055
i+0.054
Neg logit contributions
 vows-0.021
cakes-0.019
 contest-0.019
 prize-0.018
apy-0.018
Token
Token ID198
Feature activation+2.86e-02

Pos logit contributions
rying+0.065
bur+0.064
ppa+0.063
i+0.062
ind+0.061
Neg logit contributions
 vows-0.024
 prize-0.022
 contest-0.021
apy-0.021
case-0.021
TokenTim
Token ID14967
Feature activation+8.65e-02

Pos logit contributions
rying+0.064
bur+0.063
i+0.062
ppa+0.061
ener+0.060
Neg logit contributions
case-0.039
apy-0.039
 vows-0.038
ades-0.037
cakes-0.037
Tokenmy
Token ID1820
Feature activation+5.04e-02

Pos logit contributions
rying+0.130
ind+0.120
keeping+0.119
 predators+0.118
shadow+0.117
Neg logit contributions
 were-0.147
 game-0.144
 laugh-0.142
 are-0.142
 joke-0.141
Token started
Token ID2067
Feature activation+1.97e-03

Pos logit contributions
rying+0.122
bur+0.120
ind+0.111
ppa+0.108
keeping+0.107
Neg logit contributions
 vows-0.060
case-0.054
 contest-0.054
 were-0.054
 joke-0.052
Token to
Token ID284
Feature activation+4.04e-03

Pos logit contributions
bur+0.004
rying+0.003
ppa+0.003
i+0.003
ind+0.003
Neg logit contributions
 vows-0.004
 prize-0.003
 contest-0.003
 trophy-0.003
cakes-0.003
Token complain
Token ID13121
Feature activation+8.59e-03

Pos logit contributions
bur+0.008
rying+0.008
ppa+0.008
i+0.008
ind+0.008
Neg logit contributions
 vows-0.007
 prize-0.006
 contest-0.006
 trophy-0.006
cakes-0.006
Token to
Token ID284
Feature activation+2.04e-02

Pos logit contributions
bur+0.017
rying+0.017
ppa+0.016
i+0.016
ind+0.016
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.013
 trophy-0.013
cakes-0.013
Token eating
Token ID6600
Feature activation-1.79e-02

Pos logit contributions
bur+0.021
rying+0.021
ppa+0.021
ind+0.020
i+0.020
Neg logit contributions
 vows-0.025
 prize-0.023
 contest-0.023
 trophy-0.023
cakes-0.022
Token their
Token ID511
Feature activation+2.41e-03

Pos logit contributions
 vows+0.032
 contest+0.027
 prize+0.027
case+0.026
 Prize+0.026
Neg logit contributions
bur-0.035
i-0.033
rying-0.033
ppa-0.032
ind-0.031
Token ice
Token ID4771
Feature activation+8.60e-03

Pos logit contributions
bur+0.005
rying+0.004
ppa+0.004
i+0.004
ind+0.004
Neg logit contributions
 vows-0.004
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token cream
Token ID8566
Feature activation-1.88e-02

Pos logit contributions
bur+0.017
rying+0.017
ppa+0.017
ind+0.016
i+0.016
Neg logit contributions
 vows-0.014
 prize-0.013
 contest-0.013
 trophy-0.013
cakes-0.013
Token,
Token ID11
Feature activation-1.48e-02

Pos logit contributions
 vows+0.032
 prize+0.027
 contest+0.027
 Prize+0.027
apy+0.027
Neg logit contributions
bur-0.038
i-0.036
rying-0.036
ppa-0.036
ety-0.034
Token Tim
Token ID5045
Feature activation+8.57e-02

Pos logit contributions
 vows+0.028
 prize+0.024
 contest+0.024
 trophy+0.023
cakes+0.023
Neg logit contributions
bur-0.028
rying-0.026
ppa-0.026
i-0.026
gie-0.026
Tokenmy
Token ID1820
Feature activation+5.13e-02

Pos logit contributions
rying+0.115
ind+0.109
 predators+0.099
cker+0.096
 property+0.093
Neg logit contributions
 were-0.172
 team-0.162
case-0.159
 are-0.159
 third-0.156
Token's
Token ID338
Feature activation+4.22e-03

Pos logit contributions
rying+0.113
bur+0.106
ind+0.105
ior+0.098
cker+0.096
Neg logit contributions
 vows-0.075
 contest-0.065
 trophy-0.065
case-0.065
apy-0.065
Token mom
Token ID1995
Feature activation+4.04e-02

Pos logit contributions
bur+0.009
rying+0.009
ppa+0.009
i+0.009
ind+0.009
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token told
Token ID1297
Feature activation+2.05e-03

Pos logit contributions
rying+0.080
ind+0.079
bur+0.077
ior+0.073
cker+0.073
Neg logit contributions
 vows-0.063
cakes-0.059
 contest-0.056
 were-0.055
 are-0.054
Token him
Token ID683
Feature activation-3.14e-02

Pos logit contributions
bur+0.003
rying+0.003
ppa+0.003
i+0.003
ind+0.003
Neg logit contributions
 vows-0.004
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token"
Token ID1
Feature activation+2.75e-02

Pos logit contributions
bur+0.011
rying+0.011
ppa+0.011
i+0.011
ind+0.011
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.009
 trophy-0.008
cakes-0.008
TokenWhat
Token ID2061
Feature activation-3.00e-02

Pos logit contributions
rying+0.056
ppa+0.055
i+0.054
bur+0.053
ind+0.052
Neg logit contributions
 vows-0.043
Mine-0.040
 contest-0.039
cakes-0.039
apy-0.039
Token is
Token ID318
Feature activation+1.04e-02

Pos logit contributions
 vows+0.056
 prize+0.048
cakes+0.048
 trophy+0.047
 contest+0.047
Neg logit contributions
my-0.052
i-0.051
rying-0.050
bur-0.050
ppa-0.049
Token it
Token ID340
Feature activation+5.53e-03

Pos logit contributions
bur+0.023
rying+0.022
ppa+0.022
i+0.021
ind+0.021
Neg logit contributions
 vows-0.016
 prize-0.015
 contest-0.015
 trophy-0.014
apy-0.014
Token,
Token ID11
Feature activation-1.48e-02

Pos logit contributions
bur+0.009
rying+0.009
ppa+0.009
i+0.009
ind+0.009
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.010
 trophy-0.010
cakes-0.010
Token Mum
Token ID38367
Feature activation+8.63e-02

Pos logit contributions
 vows+0.024
 contest+0.022
 prize+0.022
 trophy+0.022
cakes+0.021
Neg logit contributions
bur-0.029
i-0.029
rying-0.029
ppa-0.028
ind-0.028
Token?"
Token ID1701
Feature activation+4.68e-03

Pos logit contributions
ind+0.195
ppa+0.183
eled+0.183
gie+0.181
rying+0.179
Neg logit contributions
 contest-0.101
 are-0.094
 celebrate-0.093
 parties-0.091
 trophy-0.086
Token she
Token ID673
Feature activation+6.98e-02

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.010
i+0.009
ind+0.009
Neg logit contributions
 vows-0.007
 prize-0.006
 contest-0.006
 trophy-0.006
cakes-0.006
Token asked
Token ID1965
Feature activation+1.85e-02

Pos logit contributions
bur+0.138
rying+0.138
ind+0.129
ishing+0.124
ior+0.124
Neg logit contributions
 vows-0.107
 third-0.103
 funny-0.098
 contest-0.097
 dance-0.096
Token.
Token ID13
Feature activation-8.53e-03

Pos logit contributions
bur+0.041
ppa+0.040
rying+0.039
ind+0.039
cker+0.038
Neg logit contributions
 vows-0.027
 prize-0.024
 contest-0.024
apy-0.023
 trophy-0.023
Token
Token ID198
Feature activation-1.19e-02

Pos logit contributions
 vows+0.013
 prize+0.012
 trophy+0.012
 contest+0.012
cakes+0.011
Neg logit contributions
bur-0.018
rying-0.018
ppa-0.018
i-0.017
ind-0.017
Token hoped
Token ID10719
Feature activation+1.76e-02

Pos logit contributions
 vows+0.029
 prize+0.026
 trophy+0.026
cakes+0.026
 contest+0.026
Neg logit contributions
bur-0.025
ppa-0.024
rying-0.024
i-0.024
ety-0.023
Token to
Token ID284
Feature activation+2.87e-02

Pos logit contributions
bur+0.047
rying+0.046
ppa+0.046
ind+0.045
ior+0.044
Neg logit contributions
 vows-0.019
 prize-0.016
 contest-0.016
 trophy-0.015
cakes-0.015
Token find
Token ID1064
Feature activation+1.68e-02

Pos logit contributions
rying+0.070
ppa+0.069
bur+0.068
i+0.067
ior+0.066
Neg logit contributions
 vows-0.035
 prize-0.033
 contest-0.032
 celebrate-0.031
 trophy-0.031
Token another
Token ID1194
Feature activation+4.38e-02

Pos logit contributions
rying+0.040
ppa+0.040
bur+0.039
ind+0.038
i+0.038
Neg logit contributions
 vows-0.022
 prize-0.020
 contest-0.019
 trophy-0.019
apy-0.018
Token rare
Token ID4071
Feature activation+4.15e-02

Pos logit contributions
ppa+0.095
rying+0.093
bur+0.089
ind+0.088
ior+0.087
Neg logit contributions
 prize-0.070
 vows-0.065
 trophy-0.064
 contest-0.064
 lot-0.062
Token rad
Token ID2511
Feature activation+8.50e-02

Pos logit contributions
ppa+0.089
rying+0.086
bur+0.085
ior+0.080
ind+0.080
Neg logit contributions
 vows-0.068
 prize-0.066
 trophy-0.063
 contest-0.062
 joke-0.058
Tokenish
Token ID680
Feature activation-1.50e-03

Pos logit contributions
ppa+0.134
eking+0.130
oscope+0.127
rying+0.127
shadow+0.126
Neg logit contributions
 prize-0.154
 trophy-0.146
 are-0.146
 vows-0.144
 lot-0.141
Token.
Token ID13
Feature activation+4.23e-03

Pos logit contributions
 vows+0.003
 prize+0.002
 contest+0.002
 trophy+0.002
apy+0.002
Neg logit contributions
bur-0.003
rying-0.003
ppa-0.003
i-0.003
ind-0.003
Token They
Token ID1119
Feature activation-8.81e-03

Pos logit contributions
bur+0.011
rying+0.011
ppa+0.010
i+0.010
ind+0.010
Neg logit contributions
 vows-0.005
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token hoped
Token ID10719
Feature activation+2.44e-02

Pos logit contributions
 vows+0.018
 prize+0.016
 trophy+0.016
 contest+0.016
cakes+0.016
Neg logit contributions
bur-0.015
ppa-0.015
rying-0.014
i-0.014
ety-0.013
Token to
Token ID284
Feature activation+3.25e-02

Pos logit contributions
rying+0.064
bur+0.064
ppa+0.064
ind+0.062
ior+0.061
Neg logit contributions
 vows-0.026
 prize-0.023
 contest-0.022
 trophy-0.020
cakes-0.020
Token it
Token ID340
Feature activation+1.77e-02

Pos logit contributions
rying+0.101
ppa+0.100
cker+0.098
ind+0.097
ior+0.097
Neg logit contributions
 prize-0.034
 trophy-0.032
 vows-0.031
 contest-0.029
 great-0.027
Token forever
Token ID8097
Feature activation+4.80e-02

Pos logit contributions
bur+0.036
rying+0.036
ppa+0.036
ind+0.035
i+0.034
Neg logit contributions
 vows-0.027
 prize-0.026
 trophy-0.025
 contest-0.025
cakes-0.023
Token.
Token ID13
Feature activation+2.41e-02

Pos logit contributions
bur+0.133
ind+0.131
ior+0.130
umper+0.128
rying+0.127
Neg logit contributions
 prize-0.039
 trophy-0.034
 are-0.032
 great-0.031
 vows-0.031
Token
Token ID198
Feature activation+1.40e-02

Pos logit contributions
rying+0.068
ppa+0.066
ind+0.066
bur+0.065
i+0.064
Neg logit contributions
 vows-0.021
 prize-0.019
cakes-0.018
 contest-0.018
 trophy-0.018
Token
Token ID198
Feature activation+2.40e-02

Pos logit contributions
rying+0.034
bur+0.034
ppa+0.034
i+0.033
ind+0.032
Neg logit contributions
 vows-0.017
 prize-0.015
 contest-0.015
 trophy-0.014
apy-0.014
TokenTim
Token ID14967
Feature activation+8.76e-02

Pos logit contributions
rying+0.052
i+0.051
bur+0.051
ppa+0.050
ener+0.049
Neg logit contributions
 vows-0.033
case-0.033
apy-0.032
 prize-0.032
 contest-0.032
Tokenmy
Token ID1820
Feature activation+3.86e-02

Pos logit contributions
rying+0.130
ind+0.125
shadow+0.123
 predators+0.123
ich+0.121
Neg logit contributions
 are-0.148
 were-0.146
 game-0.145
 laugh-0.144
 joke-0.141
Token played
Token ID2826
Feature activation-3.42e-02

Pos logit contributions
bur+0.085
rying+0.085
ind+0.082
ppa+0.079
ior+0.077
Neg logit contributions
 vows-0.055
 contest-0.048
 joke-0.046
 prize-0.046
case-0.045
Token with
Token ID351
Feature activation+1.04e-04

Pos logit contributions
 vows+0.083
cakes+0.068
apy+0.067
Mine+0.066
 Prize+0.066
Neg logit contributions
rying-0.047
bur-0.045
 owl-0.042
ishing-0.041
 forth-0.041
Token his
Token ID465
Feature activation-2.76e-02

Pos logit contributions
bur+0.000
rying+0.000
ppa+0.000
i+0.000
ind+0.000
Neg logit contributions
 vows-0.000
 prize-0.000
 contest-0.000
 trophy-0.000
cakes-0.000
Token ball
Token ID2613
Feature activation+1.02e-02

Pos logit contributions
 vows+0.045
cakes+0.038
ades+0.035
apy+0.034
 Prize+0.034
Neg logit contributions
bur-0.057
ety-0.055
rying-0.054
ind-0.054
 axe-0.054
Token that
Token ID326
Feature activation-2.05e-02

Pos logit contributions
 vows+0.003
 prize+0.003
 contest+0.003
 trophy+0.003
cakes+0.003
Neg logit contributions
bur-0.003
rying-0.003
ppa-0.003
i-0.003
ind-0.003
Token cared
Token ID19951
Feature activation-3.73e-02

Pos logit contributions
 vows+0.034
 prize+0.032
 trophy+0.032
 contest+0.030
cakes+0.030
Neg logit contributions
bur-0.041
i-0.040
ppa-0.039
rying-0.039
cker-0.038
Token for
Token ID329
Feature activation+1.84e-02

Pos logit contributions
 vows+0.084
Mine+0.082
 trophy+0.079
cakes+0.078
 contest+0.078
Neg logit contributions
rying-0.048
i-0.043
bur-0.043
ind-0.042
ppa-0.041
Token them
Token ID606
Feature activation-2.02e-02

Pos logit contributions
rying+0.044
bur+0.043
ppa+0.043
ind+0.041
i+0.041
Neg logit contributions
 vows-0.024
 prize-0.021
 contest-0.020
 trophy-0.019
apy-0.019
Token.
Token ID13
Feature activation-7.37e-03

Pos logit contributions
 vows+0.040
apy+0.037
 trophy+0.036
 prize+0.036
 contest+0.036
Neg logit contributions
rying-0.034
bur-0.034
ppa-0.033
i-0.033
ind-0.032
Token The
Token ID383
Feature activation+2.05e-02

Pos logit contributions
 vows+0.011
 prize+0.010
 trophy+0.010
 contest+0.009
cakes+0.009
Neg logit contributions
bur-0.016
rying-0.016
ppa-0.015
i-0.015
ind-0.015
Token family
Token ID1641
Feature activation-1.64e-02

Pos logit contributions
rying+0.039
bur+0.037
ppa+0.037
i+0.036
ety+0.035
Neg logit contributions
 vows-0.039
 prize-0.034
 contest-0.033
cakes-0.032
 trophy-0.032
Token was
Token ID373
Feature activation-6.08e-03

Pos logit contributions
 vows+0.029
 prize+0.027
 trophy+0.026
 contest+0.026
cakes+0.026
Neg logit contributions
bur-0.031
rying-0.030
i-0.030
ppa-0.030
ind-0.029
Token very
Token ID845
Feature activation-1.38e-02

Pos logit contributions
 vows+0.010
 prize+0.009
 trophy+0.009
cakes+0.009
apy+0.008
Neg logit contributions
bur-0.013
rying-0.012
ppa-0.012
ind-0.012
i-0.012
Token happy
Token ID3772
Feature activation+8.26e-03

Pos logit contributions
 vows+0.022
 prize+0.020
 trophy+0.019
cakes+0.019
 contest+0.019
Neg logit contributions
rying-0.029
ppa-0.028
ind-0.028
bur-0.028
i-0.027
Token,
Token ID11
Feature activation-5.00e-03

Pos logit contributions
bur+0.015
ppa+0.014
rying+0.014
ind+0.014
i+0.014
Neg logit contributions
 vows-0.016
 prize-0.014
 contest-0.014
 trophy-0.014
cakes-0.014
Token scared
Token ID12008
Feature activation+2.52e-02

Pos logit contributions
bur+0.026
rying+0.026
ppa+0.025
ind+0.024
i+0.024
Neg logit contributions
 vows-0.020
 prize-0.017
 contest-0.017
 trophy-0.017
apy-0.017
Token of
Token ID286
Feature activation+1.89e-02

Pos logit contributions
bur+0.059
ppa+0.059
rying+0.056
ind+0.054
cker+0.053
Neg logit contributions
 vows-0.033
 prize-0.030
 contest-0.030
apy-0.030
 trophy-0.029
Token the
Token ID262
Feature activation+2.96e-02

Pos logit contributions
bur+0.041
ppa+0.041
rying+0.041
ind+0.039
ety+0.039
Neg logit contributions
 vows-0.028
 prize-0.026
 contest-0.025
 trophy-0.024
apy-0.023
Token farmer
Token ID18739
Feature activation+3.98e-02

Pos logit contributions
bur+0.053
rying+0.053
ppa+0.052
ety+0.049
umper+0.048
Neg logit contributions
 vows-0.056
 prize-0.051
 contest-0.051
 joke-0.049
 tea-0.048
Token.
Token ID13
Feature activation+8.14e-03

Pos logit contributions
bur+0.083
ppa+0.081
ind+0.080
rying+0.080
ior+0.075
Neg logit contributions
 vows-0.062
 prize-0.057
 contest-0.057
 trophy-0.055
 are-0.053
Token But
Token ID887
Feature activation+3.89e-02

Pos logit contributions
bur+0.017
rying+0.017
ppa+0.017
ind+0.017
i+0.016
Neg logit contributions
 vows-0.013
 prize-0.011
 contest-0.011
 trophy-0.011
cakes-0.011
Token eventually
Token ID4191
Feature activation-8.37e-03

Pos logit contributions
rying+0.076
bur+0.075
ppa+0.074
ind+0.074
umper+0.070
Neg logit contributions
 vows-0.065
 contest-0.060
 prize-0.059
apy-0.058
 trophy-0.058
Token,
Token ID11
Feature activation+1.70e-02

Pos logit contributions
 vows+0.014
cakes+0.012
 trophy+0.012
 prize+0.012
 contest+0.012
Neg logit contributions
bur-0.017
i-0.017
ppa-0.017
rying-0.017
cker-0.016
Token they
Token ID484
Feature activation-1.03e-02

Pos logit contributions
rying+0.039
bur+0.039
ppa+0.039
ind+0.038
ety+0.037
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.021
 trophy-0.020
apy-0.020
Token learned
Token ID4499
Feature activation+2.35e-04

Pos logit contributions
 vows+0.018
 prize+0.016
 trophy+0.016
 contest+0.016
cakes+0.016
Neg logit contributions
bur-0.020
ppa-0.020
rying-0.020
i-0.019
cker-0.018
Token to
Token ID284
Feature activation+2.24e-02

Pos logit contributions
bur+0.000
rying+0.000
ppa+0.000
i+0.000
ind+0.000
Neg logit contributions
 vows-0.000
 prize-0.000
 contest-0.000
 trophy-0.000
cakes-0.000
Token saw
Token ID2497
Feature activation+5.66e-03

Pos logit contributions
bur+0.081
ind+0.081
ppa+0.081
rying+0.080
umper+0.075
Neg logit contributions
 vows-0.055
 contest-0.050
 trophy-0.050
apy-0.049
 they-0.049
Token Lily
Token ID20037
Feature activation+4.52e-03

Pos logit contributions
bur+0.012
rying+0.012
ppa+0.012
i+0.012
ind+0.012
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.007
 trophy-0.007
cakes-0.007
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
bur+0.008
rying+0.008
ppa+0.008
i+0.008
ind+0.008
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.007
Token He
Token ID679
Feature activation+1.76e-02

Pos logit contributions
 vows+0.025
 prize+0.022
 contest+0.021
 trophy+0.021
apy+0.021
Neg logit contributions
bur-0.023
rying-0.023
ppa-0.023
gie-0.022
ety-0.022
Token was
Token ID373
Feature activation+1.71e-02

Pos logit contributions
rying+0.037
bur+0.037
ppa+0.035
ind+0.035
i+0.034
Neg logit contributions
 vows-0.028
 prize-0.025
 trophy-0.024
 contest-0.024
apy-0.024
Token surprised
Token ID6655
Feature activation+4.09e-02

Pos logit contributions
rying+0.034
bur+0.034
ppa+0.033
i+0.032
ior+0.032
Neg logit contributions
 vows-0.029
 prize-0.026
 contest-0.025
 trophy-0.025
apy-0.024
Token and
Token ID290
Feature activation+1.54e-02

Pos logit contributions
bur+0.100
ppa+0.100
cker+0.094
oscope+0.093
rying+0.092
Neg logit contributions
 prize-0.043
 vows-0.043
 they-0.043
 trophy-0.043
 contest-0.041
Token said
Token ID531
Feature activation-3.93e-02

Pos logit contributions
bur+0.031
rying+0.030
ppa+0.030
ind+0.029
i+0.028
Neg logit contributions
 vows-0.026
 prize-0.023
 contest-0.023
 trophy-0.023
apy-0.022
Token,
Token ID11
Feature activation-7.60e-03

Pos logit contributions
 vows+0.077
cakes+0.069
Mine+0.069
 prize+0.068
case+0.068
Neg logit contributions
i-0.062
rying-0.060
 Owl-0.059
 owl-0.058
ppa-0.058
Token "
Token ID366
Feature activation+1.89e-02

Pos logit contributions
 vows+0.009
 prize+0.008
 contest+0.008
 trophy+0.008
cakes+0.007
Neg logit contributions
bur-0.019
rying-0.018
ppa-0.018
i-0.018
gie-0.018
TokenWho
Token ID8241
Feature activation-1.11e-02

Pos logit contributions
rying+0.038
bur+0.037
ppa+0.037
i+0.036
ind+0.035
Neg logit contributions
 vows-0.031
 trophy-0.028
 contest-0.028
 prize-0.028
cakes-0.028
Token a
Token ID257
Feature activation-1.44e-02

Pos logit contributions
rying+0.026
bur+0.025
ppa+0.025
i+0.024
ind+0.024
Neg logit contributions
 vows-0.013
 prize-0.011
 contest-0.011
 trophy-0.011
apy-0.011
Token talking
Token ID3375
Feature activation-2.46e-02

Pos logit contributions
 vows+0.024
cakes+0.021
 prize+0.020
 contest+0.020
apy+0.020
Neg logit contributions
bur-0.029
rying-0.028
ppa-0.028
ind-0.027
i-0.027
Token bird
Token ID6512
Feature activation+3.72e-02

Pos logit contributions
 vows+0.045
apy+0.041
cakes+0.039
Mine+0.039
ades+0.039
Neg logit contributions
bur-0.042
rying-0.041
 owl-0.041
ind-0.040
ppa-0.040
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
ppa+0.084
bur+0.084
ior+0.084
rying+0.080
ind+0.078
Neg logit contributions
 contest-0.047
 prize-0.046
 vows-0.046
 joke-0.044
 trophy-0.043
Token The
Token ID383
Feature activation+1.53e-02

Pos logit contributions
 vows+0.023
 prize+0.020
 trophy+0.020
 contest+0.020
ades+0.019
Neg logit contributions
bur-0.023
rying-0.023
gie-0.023
ior-0.022
ppa-0.022
Token bird
Token ID6512
Feature activation+3.33e-02

Pos logit contributions
rying+0.030
bur+0.029
ppa+0.029
i+0.028
ind+0.028
Neg logit contributions
 vows-0.028
 prize-0.026
 contest-0.026
 trophy-0.025
cakes-0.024
Token said
Token ID531
Feature activation-3.23e-02

Pos logit contributions
rying+0.086
bur+0.085
ppa+0.084
ior+0.080
ind+0.080
Neg logit contributions
 vows-0.036
apy-0.032
 contest-0.031
 prize-0.031
 are-0.031
Token,
Token ID11
Feature activation+5.45e-03

Pos logit contributions
 vows+0.063
Mine+0.059
cakes+0.057
case+0.056
 prize+0.056
Neg logit contributions
i-0.050
 Owl-0.050
 owl-0.049
bur-0.047
ppa-0.047
Token "
Token ID366
Feature activation+3.40e-02

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
i+0.014
ind+0.014
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.004
cakes-0.004
TokenHi
Token ID17250
Feature activation+9.75e-03

Pos logit contributions
rying+0.073
ppa+0.068
ishing+0.064
i+0.064
ind+0.064
Neg logit contributions
 vows-0.052
Mine-0.050
cakes-0.048
 contest-0.048
 prize-0.047
Token,
Token ID11
Feature activation+4.93e-03

Pos logit contributions
bur+0.022
rying+0.022
ppa+0.022
ind+0.021
i+0.021
Neg logit contributions
 vows-0.014
 prize-0.012
 contest-0.012
 trophy-0.012
cakes-0.011
Token
Token ID198
Feature activation-1.15e-02

Pos logit contributions
 vows+0.018
 prize+0.016
 trophy+0.016
 contest+0.015
ades+0.014
Neg logit contributions
bur-0.023
ppa-0.023
rying-0.023
i-0.022
ety-0.022
Token
Token ID198
Feature activation-2.31e-02

Pos logit contributions
 vows+0.020
 prize+0.017
 trophy+0.017
 contest+0.017
cakes+0.016
Neg logit contributions
bur-0.023
ppa-0.023
rying-0.022
ind-0.022
ety-0.022
TokenL
Token ID43
Feature activation-5.81e-03

Pos logit contributions
 vows+0.050
 prize+0.046
 trophy+0.044
 contest+0.044
cakes+0.043
Neg logit contributions
ppa-0.037
ind-0.036
bur-0.035
rying-0.034
ety-0.033
Tokenily
Token ID813
Feature activation-5.97e-03

Pos logit contributions
 vows+0.010
 prize+0.009
 trophy+0.009
apy+0.009
 contest+0.009
Neg logit contributions
rying-0.012
ppa-0.012
bur-0.012
i-0.011
ind-0.011
Token shrugged
Token ID28271
Feature activation+6.35e-03

Pos logit contributions
 vows+0.011
 prize+0.010
 contest+0.010
 trophy+0.009
cakes+0.009
Neg logit contributions
bur-0.011
rying-0.011
ppa-0.011
i-0.011
ind-0.010
Token again
Token ID757
Feature activation+4.31e-02

Pos logit contributions
bur+0.012
rying+0.012
ppa+0.011
ind+0.011
i+0.011
Neg logit contributions
 vows-0.012
 prize-0.011
 contest-0.010
 trophy-0.010
cakes-0.010
Token and
Token ID290
Feature activation+2.44e-02

Pos logit contributions
bur+0.105
ppa+0.100
rying+0.098
umper+0.097
ind+0.097
Neg logit contributions
 vows-0.052
 prize-0.051
 contest-0.047
 trophy-0.046
 joke-0.045
Token said
Token ID531
Feature activation-3.72e-02

Pos logit contributions
bur+0.048
ind+0.048
rying+0.047
ppa+0.046
cker+0.044
Neg logit contributions
 vows-0.041
 contest-0.037
 prize-0.037
 trophy-0.035
cakes-0.035
Token,
Token ID11
Feature activation-3.78e-03

Pos logit contributions
 vows+0.071
cakes+0.066
Mine+0.065
 trophy+0.065
 prize+0.064
Neg logit contributions
i-0.059
rying-0.058
ppa-0.056
bur-0.052
ener-0.052
Token "
Token ID366
Feature activation+2.11e-02

Pos logit contributions
 vows+0.004
 prize+0.004
 contest+0.004
 trophy+0.004
cakes+0.003
Neg logit contributions
bur-0.009
rying-0.009
ppa-0.009
i-0.009
ind-0.009
TokenNo
Token ID2949
Feature activation-1.42e-03

Pos logit contributions
rying+0.046
ppa+0.045
bur+0.045
i+0.043
ind+0.043
Neg logit contributions
 vows-0.031
 prize-0.027
Mine-0.027
 contest-0.027
apy-0.027
Token felt
Token ID2936
Feature activation+9.33e-04

Pos logit contributions
rying+0.053
bur+0.052
ppa+0.052
ind+0.050
ior+0.050
Neg logit contributions
 vows-0.040
 prize-0.036
apy-0.035
 contest-0.034
 trophy-0.034
Token like
Token ID588
Feature activation+1.49e-02

Pos logit contributions
bur+0.002
rying+0.002
ppa+0.002
i+0.002
ind+0.002
Neg logit contributions
 vows-0.002
 prize-0.001
 contest-0.001
 trophy-0.001
cakes-0.001
Token he
Token ID339
Feature activation+2.18e-02

Pos logit contributions
bur+0.032
rying+0.032
ppa+0.032
ind+0.030
i+0.030
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.020
 trophy-0.020
apy-0.019
Token was
Token ID373
Feature activation+1.61e-02

Pos logit contributions
bur+0.051
ppa+0.051
rying+0.051
ind+0.049
ior+0.048
Neg logit contributions
 vows-0.029
 prize-0.025
 contest-0.024
 trophy-0.024
 are-0.023
Token going
Token ID1016
Feature activation+2.51e-02

Pos logit contributions
bur+0.028
ppa+0.028
rying+0.028
ind+0.027
i+0.027
Neg logit contributions
 vows-0.030
 prize-0.028
 contest-0.028
 trophy-0.027
apy-0.027
Token to
Token ID284
Feature activation-9.30e-03

Pos logit contributions
ppa+0.052
bur+0.051
rying+0.050
ior+0.049
ind+0.049
Neg logit contributions
 vows-0.039
 prize-0.038
 contest-0.038
 trophy-0.036
cakes-0.033
Token be
Token ID307
Feature activation+1.92e-02

Pos logit contributions
 vows+0.015
cakes+0.013
 contest+0.013
 trophy+0.013
 prize+0.013
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.018
i-0.018
ind-0.018
Token discovered
Token ID5071
Feature activation+2.51e-02

Pos logit contributions
bur+0.037
rying+0.036
ppa+0.036
i+0.035
ind+0.035
Neg logit contributions
 vows-0.033
 prize-0.030
 contest-0.030
 trophy-0.029
apy-0.029
Token.
Token ID13
Feature activation+2.60e-02

Pos logit contributions
ppa+0.053
bur+0.052
rying+0.051
ind+0.050
i+0.049
Neg logit contributions
 vows-0.039
 prize-0.037
 contest-0.035
 trophy-0.035
cakes-0.034
Token
Token ID198
Feature activation+1.41e-02

Pos logit contributions
rying+0.068
ppa+0.067
bur+0.067
ind+0.067
i+0.066
Neg logit contributions
 vows-0.026
 Everyone-0.024
 prize-0.024
apy-0.024
case-0.023
Token
Token ID198
Feature activation+2.83e-03

Pos logit contributions
rying+0.035
bur+0.035
ppa+0.034
i+0.034
ind+0.033
Neg logit contributions
 vows-0.017
 prize-0.015
 contest-0.014
apy-0.014
 trophy-0.014
Token."
Token ID526
Feature activation-5.62e-03

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.013
i+0.013
ind+0.013
Neg logit contributions
 vows-0.014
 prize-0.012
 contest-0.012
 trophy-0.012
cakes-0.012
Token Lily
Token ID20037
Feature activation-2.80e-02

Pos logit contributions
 vows+0.009
 prize+0.008
 trophy+0.008
 contest+0.008
 Prize+0.007
Neg logit contributions
bur-0.012
ppa-0.012
rying-0.012
i-0.011
ety-0.011
Token smiled
Token ID13541
Feature activation-1.78e-03

Pos logit contributions
 vows+0.053
 contest+0.053
 prize+0.052
 Prize+0.050
 trophy+0.050
Neg logit contributions
ppa-0.048
i-0.047
bur-0.047
my-0.045
ety-0.043
Token and
Token ID290
Feature activation-2.13e-02

Pos logit contributions
 vows+0.004
 prize+0.003
 contest+0.003
 trophy+0.003
cakes+0.003
Neg logit contributions
bur-0.003
rying-0.003
ppa-0.003
i-0.003
ind-0.003
Token said
Token ID531
Feature activation-4.61e-02

Pos logit contributions
 vows+0.043
 contest+0.041
 prize+0.040
 trophy+0.040
ades+0.040
Neg logit contributions
ppa-0.035
bur-0.034
i-0.034
rying-0.032
ety-0.031
Token,
Token ID11
Feature activation-1.54e-02

Pos logit contributions
 vows+0.092
Mine+0.092
case+0.089
 blast+0.088
 festival+0.087
Neg logit contributions
i-0.066
ppa-0.064
rying-0.057
my-0.057
ener-0.056
Token "
Token ID366
Feature activation+4.10e-03

Pos logit contributions
 vows+0.020
 prize+0.018
 contest+0.017
 trophy+0.017
ades+0.016
Neg logit contributions
ppa-0.036
bur-0.036
rying-0.035
i-0.034
gie-0.034
TokenI
Token ID40
Feature activation-3.14e-02

Pos logit contributions
bur+0.008
rying+0.008
ppa+0.008
i+0.007
ind+0.007
Neg logit contributions
 vows-0.007
 prize-0.007
 contest-0.007
 trophy-0.006
cakes-0.006
Token love
Token ID1842
Feature activation+3.03e-03

Pos logit contributions
 vows+0.054
 trophy+0.052
cakes+0.052
apy+0.052
ades+0.052
Neg logit contributions
bur-0.058
ppa-0.056
my-0.056
i-0.056
rying-0.053
Token you
Token ID345
Feature activation-1.83e-02

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.006
 prize-0.006
 contest-0.006
 trophy-0.006
cakes-0.005
Token too
Token ID1165
Feature activation+4.40e-03

Pos logit contributions
 vows+0.037
apy+0.034
 prize+0.034
 contest+0.034
cakes+0.034
Neg logit contributions
bur-0.030
ppa-0.030
i-0.029
my-0.028
rying-0.028
Token sat
Token ID3332
Feature activation+2.55e-02

Pos logit contributions
bur+0.015
rying+0.015
ppa+0.015
ind+0.014
i+0.014
Neg logit contributions
 vows-0.013
 prize-0.012
 contest-0.012
 trophy-0.012
cakes-0.011
Token down
Token ID866
Feature activation-2.14e-02

Pos logit contributions
bur+0.050
ppa+0.050
gie+0.048
cker+0.048
rying+0.047
Neg logit contributions
 vows-0.042
 contest-0.038
 prize-0.038
 trophy-0.038
apy-0.037
Token at
Token ID379
Feature activation+1.26e-03

Pos logit contributions
 vows+0.048
 prize+0.043
 Prize+0.043
 trophy+0.043
apy+0.043
Neg logit contributions
rying-0.031
bur-0.030
i-0.028
ind-0.027
ppa-0.027
Token a
Token ID257
Feature activation-5.05e-02

Pos logit contributions
bur+0.003
rying+0.003
ppa+0.003
i+0.003
ind+0.003
Neg logit contributions
 vows-0.002
 prize-0.002
 contest-0.002
 trophy-0.002
cakes-0.002
Token big
Token ID1263
Feature activation-2.55e-02

Pos logit contributions
 vows+0.083
apy+0.074
cakes+0.071
 Everyone+0.069
 Everybody+0.067
Neg logit contributions
ind-0.097
bur-0.092
ppa-0.090
rying-0.089
 owl-0.089
Token table
Token ID3084
Feature activation+3.85e-03

Pos logit contributions
 vows+0.040
apy+0.035
cakes+0.034
ades+0.032
 Prize+0.031
Neg logit contributions
bur-0.054
ind-0.052
i-0.051
rying-0.051
ppa-0.050
Token.
Token ID13
Feature activation-3.46e-02

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
i+0.007
ind+0.006
Neg logit contributions
 vows-0.007
 prize-0.007
 contest-0.006
 trophy-0.006
cakes-0.006
Token They
Token ID1119
Feature activation-2.04e-02

Pos logit contributions
 vows+0.055
 trophy+0.050
 prize+0.049
 contest+0.047
ades+0.045
Neg logit contributions
ety-0.068
ior-0.066
gie-0.066
bur-0.066
rying-0.065
Token had
Token ID550
Feature activation-1.45e-02

Pos logit contributions
 vows+0.038
 prize+0.036
 contest+0.035
 trophy+0.035
cakes+0.034
Neg logit contributions
bur-0.037
ppa-0.037
i-0.036
rying-0.035
ety-0.033
Token delicious
Token ID12625
Feature activation-1.75e-02

Pos logit contributions
 vows+0.023
 trophy+0.021
 prize+0.021
 contest+0.021
apy+0.021
Neg logit contributions
bur-0.030
ppa-0.029
rying-0.029
i-0.028
ind-0.028
Token food
Token ID2057
Feature activation-2.28e-02

Pos logit contributions
 vows+0.023
 trophy+0.020
 Prize+0.020
 contest+0.020
 prize+0.020
Neg logit contributions
bur-0.040
i-0.039
rying-0.038
ppa-0.038
ind-0.037
Token again
Token ID757
Feature activation+4.18e-02

Pos logit contributions
 vows+0.032
apy+0.028
 prize+0.028
 Prize+0.027
 trophy+0.027
Neg logit contributions
rying-0.024
bur-0.024
ppa-0.024
i-0.023
ety-0.022
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
bur+0.105
rying+0.101
ppa+0.100
umper+0.096
gie+0.096
Neg logit contributions
 vows-0.047
 prize-0.043
 contest-0.042
 are-0.040
 trophy-0.038
Token She
Token ID1375
Feature activation+4.06e-03

Pos logit contributions
rying+0.036
bur+0.036
ppa+0.035
i+0.034
ind+0.034
Neg logit contributions
 vows-0.017
apy-0.014
 prize-0.014
 contest-0.014
 trophy-0.014
Token hoped
Token ID10719
Feature activation+2.18e-02

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
i+0.007
ind+0.007
Neg logit contributions
 vows-0.008
 prize-0.007
 contest-0.007
 trophy-0.007
cakes-0.006
Token her
Token ID607
Feature activation-3.62e-03

Pos logit contributions
rying+0.054
bur+0.054
ppa+0.053
ind+0.052
cker+0.051
Neg logit contributions
 vows-0.027
 prize-0.024
 contest-0.023
cakes-0.023
 trophy-0.023
Token eyes
Token ID2951
Feature activation-1.95e-02

Pos logit contributions
 vows+0.006
 contest+0.005
 prize+0.005
 trophy+0.005
apy+0.005
Neg logit contributions
bur-0.008
ppa-0.008
rying-0.008
i-0.007
ind-0.007
Token would
Token ID561
Feature activation-9.24e-03

Pos logit contributions
 vows+0.030
 prize+0.027
 contest+0.026
 trophy+0.026
 Prize+0.026
Neg logit contributions
bur-0.042
rying-0.041
ppa-0.040
i-0.040
ety-0.039
Token get
Token ID651
Feature activation+2.97e-02

Pos logit contributions
 vows+0.015
cakes+0.013
 prize+0.013
 contest+0.013
 trophy+0.013
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.018
i-0.018
ety-0.017
Token better
Token ID1365
Feature activation+4.46e-02

Pos logit contributions
rying+0.065
bur+0.064
ppa+0.063
ind+0.062
ior+0.061
Neg logit contributions
 vows-0.043
 prize-0.038
apy-0.037
 contest-0.037
 tea-0.037
Token soon
Token ID2582
Feature activation+2.05e-02

Pos logit contributions
bur+0.110
ind+0.104
rying+0.104
gie+0.104
umper+0.103
Neg logit contributions
 vows-0.051
 prize-0.048
 contest-0.045
 are-0.044
 trophy-0.044
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
bur+0.044
rying+0.043
ppa+0.042
ind+0.042
i+0.041
Neg logit contributions
 vows-0.032
 prize-0.029
 contest-0.028
 trophy-0.027
cakes-0.026
Token and
Token ID290
Feature activation+4.52e-03

Pos logit contributions
 vows+0.024
 prize+0.022
 contest+0.022
 trophy+0.022
 Prize+0.021
Neg logit contributions
bur-0.023
rying-0.023
ppa-0.022
i-0.022
ind-0.021
Token a
Token ID257
Feature activation-2.63e-02

Pos logit contributions
bur+0.009
rying+0.009
ppa+0.009
i+0.009
ind+0.009
Neg logit contributions
 vows-0.008
 prize-0.007
 contest-0.007
 trophy-0.007
cakes-0.006
Token big
Token ID1263
Feature activation-9.98e-03

Pos logit contributions
 vows+0.042
cakes+0.036
 prize+0.035
 contest+0.034
 trophy+0.034
Neg logit contributions
bur-0.053
ppa-0.052
rying-0.051
ind-0.050
i-0.050
Token paper
Token ID3348
Feature activation-6.58e-03

Pos logit contributions
 vows+0.016
cakes+0.014
 prize+0.014
 contest+0.013
 trophy+0.013
Neg logit contributions
bur-0.021
rying-0.020
ppa-0.020
i-0.019
ind-0.019
Token.
Token ID13
Feature activation+7.86e-03

Pos logit contributions
 vows+0.012
 prize+0.010
 contest+0.010
 trophy+0.010
cakes+0.010
Neg logit contributions
bur-0.012
rying-0.012
ppa-0.012
i-0.012
ind-0.011
Token He
Token ID679
Feature activation-2.15e-02

Pos logit contributions
bur+0.018
rying+0.018
ppa+0.018
i+0.017
ind+0.017
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.009
 trophy-0.009
cakes-0.009
Token dipped
Token ID35300
Feature activation+2.47e-02

Pos logit contributions
 vows+0.039
 prize+0.037
 contest+0.036
 trophy+0.036
cakes+0.035
Neg logit contributions
bur-0.038
i-0.037
rying-0.037
ppa-0.037
ind-0.036
Token his
Token ID465
Feature activation+9.49e-03

Pos logit contributions
ppa+0.056
rying+0.056
bur+0.055
ind+0.053
ior+0.052
Neg logit contributions
 vows-0.034
 prize-0.030
 trophy-0.030
apy-0.030
 contest-0.029
Token brush
Token ID14093
Feature activation+2.58e-03

Pos logit contributions
bur+0.018
rying+0.018
ppa+0.017
ind+0.017
i+0.017
Neg logit contributions
 vows-0.017
 prize-0.016
 contest-0.015
 trophy-0.015
apy-0.015
Token in
Token ID287
Feature activation+1.25e-02

Pos logit contributions
bur+0.005
rying+0.004
ppa+0.004
i+0.004
ind+0.004
Neg logit contributions
 vows-0.005
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token red
Token ID2266
Feature activation+1.41e-03

Pos logit contributions
rying+0.028
bur+0.028
ppa+0.027
ind+0.026
i+0.026
Neg logit contributions
 vows-0.018
 prize-0.017
 trophy-0.016
 contest-0.016
apy-0.015
Token the
Token ID262
Feature activation+1.50e-02

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
i+0.014
ind+0.013
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
apy-0.008
Token mess
Token ID2085
Feature activation-4.95e-02

Pos logit contributions
bur+0.029
ppa+0.029
rying+0.029
i+0.027
ety+0.027
Neg logit contributions
 vows-0.026
 prize-0.024
 contest-0.024
 trophy-0.024
cakes-0.023
Token went
Token ID1816
Feature activation-1.12e-02

Pos logit contributions
 vows+0.089
 prize+0.078
 Prize+0.077
 trophy+0.076
 contest+0.075
Neg logit contributions
rying-0.094
i-0.089
bur-0.088
ppa-0.084
gie-0.082
Token away
Token ID1497
Feature activation-2.67e-02

Pos logit contributions
 vows+0.024
 prize+0.021
 trophy+0.021
apy+0.021
cakes+0.021
Neg logit contributions
rying-0.018
bur-0.018
ind-0.016
ppa-0.016
i-0.016
Token and
Token ID290
Feature activation+8.94e-03

Pos logit contributions
 vows+0.056
cakes+0.050
 contest+0.050
 trophy+0.049
 prize+0.049
Neg logit contributions
rying-0.044
bur-0.041
i-0.040
ppa-0.039
ind-0.038
Token everything
Token ID2279
Feature activation-5.58e-02

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.019
ind+0.018
i+0.018
Neg logit contributions
 vows-0.014
 prize-0.012
 contest-0.012
 trophy-0.012
cakes-0.011
Token was
Token ID373
Feature activation+3.82e-03

Pos logit contributions
 vows+0.112
 Prize+0.107
 prize+0.099
Mine+0.097
uits+0.096
Neg logit contributions
rying-0.089
i-0.082
bur-0.081
 forth-0.079
my-0.079
Token clean
Token ID3424
Feature activation-7.75e-03

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
i+0.006
ind+0.006
Neg logit contributions
 vows-0.007
 prize-0.007
 contest-0.007
 trophy-0.006
cakes-0.006
Token again
Token ID757
Feature activation+2.91e-02

Pos logit contributions
 vows+0.015
 prize+0.013
 contest+0.013
 trophy+0.013
apy+0.013
Neg logit contributions
bur-0.014
rying-0.014
ppa-0.013
i-0.013
ind-0.013
Token.
Token ID13
Feature activation-5.43e-03

Pos logit contributions
bur+0.066
ppa+0.065
rying+0.064
ind+0.062
umper+0.062
Neg logit contributions
 vows-0.040
 prize-0.036
 contest-0.035
apy-0.034
 are-0.033
Token The
Token ID383
Feature activation-9.34e-03

Pos logit contributions
 vows+0.008
 prize+0.007
 trophy+0.007
 contest+0.007
cakes+0.006
Neg logit contributions
bur-0.012
rying-0.012
ppa-0.012
i-0.011
ind-0.011
Token animals
Token ID4695
Feature activation-2.98e-02

Pos logit contributions
 vows+0.027
apy+0.025
cakes+0.023
 trophy+0.023
 prize+0.023
Neg logit contributions
rying-0.031
bur-0.031
ppa-0.030
i-0.030
ind-0.030
Token and
Token ID290
Feature activation-5.65e-03

Pos logit contributions
 vows+0.060
apy+0.052
 prize+0.052
cakes+0.051
 trophy+0.051
Neg logit contributions
rying-0.052
bur-0.049
i-0.049
ppa-0.048
ind-0.045
Token fill
Token ID6070
Feature activation-3.84e-02

Pos logit contributions
 vows+0.008
 prize+0.007
 contest+0.007
 trophy+0.007
cakes+0.007
Neg logit contributions
bur-0.012
rying-0.012
ppa-0.012
i-0.012
ind-0.012
Token in
Token ID287
Feature activation-3.21e-02

Pos logit contributions
 vows+0.066
 Prize+0.058
 trophy+0.058
 contest+0.057
apy+0.057
Neg logit contributions
bur-0.073
i-0.073
rying-0.071
ind-0.071
ppa-0.068
Token the
Token ID262
Feature activation-2.15e-02

Pos logit contributions
 vows+0.056
cakes+0.050
apy+0.048
 contest+0.048
 Prize+0.047
Neg logit contributions
bur-0.059
rying-0.058
ind-0.058
i-0.057
my-0.057
Token numbers
Token ID3146
Feature activation-5.18e-02

Pos logit contributions
 vows+0.039
apy+0.036
cakes+0.034
 prize+0.034
 trophy+0.033
Neg logit contributions
rying-0.038
bur-0.037
ind-0.037
ppa-0.036
my-0.036
Token.
Token ID13
Feature activation-3.07e-02

Pos logit contributions
 vows+0.116
 Prize+0.101
apy+0.100
 joke+0.098
 prize+0.098
Neg logit contributions
rying-0.075
i-0.072
bur-0.070
my-0.067
ppa-0.065
Token Ana
Token ID17639
Feature activation-3.20e-02

Pos logit contributions
 vows+0.050
 trophy+0.050
 prize+0.047
 contest+0.045
ades+0.045
Neg logit contributions
i-0.058
rying-0.057
bur-0.056
ppa-0.056
ior-0.055
Token was
Token ID373
Feature activation-3.26e-02

Pos logit contributions
 vows+0.057
 prize+0.054
 trophy+0.053
cakes+0.052
 contest+0.052
Neg logit contributions
i-0.058
ppa-0.055
rying-0.055
bur-0.055
ind-0.053
Token so
Token ID523
Feature activation-5.13e-02

Pos logit contributions
 vows+0.066
ades+0.061
cakes+0.059
 trophy+0.058
 prize+0.058
Neg logit contributions
rying-0.052
bur-0.051
ppa-0.049
i-0.049
my-0.048
Token excited
Token ID6568
Feature activation-1.55e-03

Pos logit contributions
 vows+0.110
ades+0.101
cakes+0.096
 prize+0.095
ves+0.094
Neg logit contributions
 aware-0.071
rying-0.067
i-0.065
my-0.065
ind-0.062
Token swings
Token ID26728
Feature activation-1.70e-02

Pos logit contributions
 vows+0.001
 prize+0.001
 contest+0.001
 trophy+0.001
cakes+0.001
Neg logit contributions
bur-0.001
rying-0.001
ppa-0.001
ind-0.001
i-0.001
Token and
Token ID290
Feature activation+4.99e-03

Pos logit contributions
 vows+0.037
 prize+0.032
 trophy+0.032
apy+0.032
 Prize+0.032
Neg logit contributions
bur-0.027
rying-0.027
i-0.026
ppa-0.024
ety-0.024
Token slides
Token ID19392
Feature activation-1.68e-02

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.010
i+0.010
ind+0.010
Neg logit contributions
 vows-0.008
 prize-0.007
 contest-0.007
 trophy-0.007
cakes-0.007
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
 vows+0.035
 prize+0.031
 trophy+0.031
 contest+0.030
apy+0.030
Neg logit contributions
bur-0.028
rying-0.028
i-0.026
ppa-0.025
ety-0.025
Token She
Token ID1375
Feature activation-3.75e-04

Pos logit contributions
 vows+0.018
 trophy+0.016
 prize+0.016
 contest+0.016
ades+0.015
Neg logit contributions
bur-0.023
rying-0.022
ppa-0.022
i-0.022
ind-0.021
Token couldn
Token ID3521
Feature activation-5.58e-02

Pos logit contributions
 vows+0.001
 prize+0.001
 contest+0.001
 trophy+0.001
cakes+0.001
Neg logit contributions
bur-0.001
rying-0.001
ppa-0.001
i-0.001
ind-0.001
Token't
Token ID470
Feature activation-1.83e-02

Pos logit contributions
 vows+0.110
 props+0.089
 trophy+0.088
 prize+0.084
ades+0.083
Neg logit contributions
bur-0.097
my-0.091
 Owl-0.089
i-0.088
rying-0.088
Token wait
Token ID4043
Feature activation-1.78e-02

Pos logit contributions
 vows+0.029
cakes+0.026
apy+0.026
ades+0.025
 trophy+0.024
Neg logit contributions
rying-0.038
bur-0.038
ppa-0.037
i-0.037
cker-0.035
Token to
Token ID284
Feature activation+2.26e-03

Pos logit contributions
 vows+0.039
cakes+0.035
 trophy+0.035
 prize+0.035
apy+0.035
Neg logit contributions
rying-0.028
bur-0.026
i-0.025
ppa-0.025
ind-0.023
Token play
Token ID711
Feature activation-4.27e-02

Pos logit contributions
bur+0.006
rying+0.005
ppa+0.005
i+0.005
ind+0.005
Neg logit contributions
 vows-0.003
 prize-0.002
 contest-0.002
 trophy-0.002
cakes-0.002
Token,
Token ID11
Feature activation+7.93e-04

Pos logit contributions
 vows+0.100
apy+0.086
Mine+0.083
cakes+0.083
 Prize+0.082
Neg logit contributions
rying-0.062
bur-0.057
i-0.055
ppa-0.051
 forth-0.051
Token guitar
Token ID10047
Feature activation-3.39e-02

Pos logit contributions
 vows+0.039
apy+0.036
cakes+0.035
 contest+0.033
 prize+0.033
Neg logit contributions
ind-0.052
bur-0.051
ppa-0.050
rying-0.049
i-0.049
Token,
Token ID11
Feature activation+3.99e-03

Pos logit contributions
 vows+0.070
apy+0.064
 prize+0.063
cakes+0.062
 trophy+0.062
Neg logit contributions
rying-0.053
i-0.051
bur-0.051
ppa-0.050
ind-0.048
Token imagining
Token ID34140
Feature activation-3.79e-02

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
i+0.007
ind+0.007
Neg logit contributions
 vows-0.008
 prize-0.007
 contest-0.007
 trophy-0.007
cakes-0.007
Token all
Token ID477
Feature activation-1.85e-02

Pos logit contributions
 vows+0.068
 Prize+0.059
 trophy+0.058
 contest+0.058
cakes+0.058
Neg logit contributions
rying-0.069
i-0.068
bur-0.066
ppa-0.065
ind-0.064
Token the
Token ID262
Feature activation-1.67e-02

Pos logit contributions
 vows+0.034
apy+0.029
 prize+0.029
 contest+0.028
ades+0.028
Neg logit contributions
bur-0.035
rying-0.034
i-0.033
ind-0.032
my-0.032
Token music
Token ID2647
Feature activation-7.18e-02

Pos logit contributions
 vows+0.022
apy+0.021
cakes+0.020
 contest+0.019
 prize+0.019
Neg logit contributions
bur-0.038
ind-0.037
rying-0.037
ppa-0.037
i-0.037
Token she
Token ID673
Feature activation+3.34e-03

Pos logit contributions
 vows+0.135
apy+0.124
Mine+0.120
 Prize+0.120
ades+0.117
Neg logit contributions
i-0.116
my-0.113
rying-0.112
bur-0.111
 owl-0.107
Token could
Token ID714
Feature activation-4.49e-02

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
i+0.007
ind+0.007
Neg logit contributions
 vows-0.005
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token make
Token ID787
Feature activation-4.79e-02

Pos logit contributions
 vows+0.070
cakes+0.064
apy+0.061
 Prize+0.061
 prize+0.058
Neg logit contributions
bur-0.091
rying-0.090
i-0.088
cker-0.086
ind-0.084
Token.
Token ID13
Feature activation-1.34e-02

Pos logit contributions
 vows+0.091
 Prize+0.080
 trophy+0.080
apy+0.079
 prize+0.078
Neg logit contributions
i-0.081
rying-0.080
bur-0.077
ind-0.076
ppa-0.076
Token She
Token ID1375
Feature activation-1.48e-02

Pos logit contributions
 vows+0.022
 prize+0.020
 trophy+0.019
 contest+0.019
ades+0.018
Neg logit contributions
bur-0.026
ppa-0.026
rying-0.026
ior-0.025
ind-0.025
Token equipment
Token ID5112
Feature activation-1.58e-02

Pos logit contributions
 vows+0.025
cakes+0.022
 contest+0.021
 Prize+0.021
 prize+0.021
Neg logit contributions
bur-0.031
rying-0.030
ppa-0.029
i-0.029
gie-0.029
Token to
Token ID284
Feature activation-1.90e-02

Pos logit contributions
 vows+0.033
apy+0.029
 prize+0.029
 trophy+0.029
 contest+0.029
Neg logit contributions
bur-0.025
rying-0.025
ppa-0.023
i-0.023
ety-0.022
Token cook
Token ID4255
Feature activation-2.86e-02

Pos logit contributions
 vows+0.031
cakes+0.026
 prize+0.026
 contest+0.025
 trophy+0.025
Neg logit contributions
bur-0.040
rying-0.039
ppa-0.037
i-0.037
cker-0.036
Token up
Token ID510
Feature activation-1.94e-02

Pos logit contributions
 vows+0.051
 Prize+0.045
 prize+0.045
 trophy+0.045
 contest+0.043
Neg logit contributions
bur-0.053
rying-0.051
i-0.051
ppa-0.050
ind-0.048
Token some
Token ID617
Feature activation-8.60e-03

Pos logit contributions
 vows+0.035
 prize+0.030
 trophy+0.030
 Prize+0.030
 contest+0.030
Neg logit contributions
bur-0.037
rying-0.036
i-0.035
ppa-0.035
ind-0.034
Token pretend
Token ID16614
Feature activation-6.06e-02

Pos logit contributions
 vows+0.014
 prize+0.012
 trophy+0.012
 contest+0.012
 Prize+0.012
Neg logit contributions
rying-0.017
bur-0.017
ppa-0.017
i-0.017
ind-0.017
Token food
Token ID2057
Feature activation-5.41e-02

Pos logit contributions
 vows+0.105
 Prize+0.097
apy+0.093
 prize+0.093
Mine+0.093
Neg logit contributions
i-0.103
bur-0.102
rying-0.101
ind-0.098
cker-0.097
Token.
Token ID13
Feature activation-1.40e-02

Pos logit contributions
 vows+0.114
apy+0.104
 Prize+0.102
Mine+0.102
 trophy+0.101
Neg logit contributions
bur-0.081
i-0.080
rying-0.079
ppa-0.073
my-0.073
Token She
Token ID1375
Feature activation-1.18e-02

Pos logit contributions
 vows+0.024
 prize+0.021
 trophy+0.021
 contest+0.020
ades+0.020
Neg logit contributions
bur-0.027
rying-0.027
ppa-0.027
ety-0.026
i-0.026
Token measured
Token ID8630
Feature activation+3.25e-02

Pos logit contributions
 vows+0.022
 prize+0.020
 trophy+0.020
 contest+0.020
cakes+0.019
Neg logit contributions
bur-0.021
ppa-0.021
rying-0.021
i-0.021
ind-0.020
Token out
Token ID503
Feature activation-1.68e-02

Pos logit contributions
rying+0.078
ppa+0.077
bur+0.076
ind+0.073
cker+0.072
Neg logit contributions
 vows-0.040
 prize-0.036
 contest-0.035
cakes-0.034
apy-0.034