TOP ACTIVATIONS
MAX = 5.958

his head out of his bur row and saw something new
to venture out from his bur row and explore the forest
who lived in his cozy bur row . He loved to
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
should never come close to an owl again !".
there ?", asked the wood pe cker . The
the sunshine . Mill ie was so excited that
" Who 's there ?" Tim my asked .
cry coming from outside his bur row . He
fluffy and lived in a bur row in the forest .
" What happened ?" Tim my asked .
mist and into their cozy bur rows . The end .
able to escape from his bur row and play in the
. One day , Stri pe y saw his friend ,
iver . Mill ie was too curious and
of friendly ducks came to Gig i 's rescue . They
, " What happened , Gig i ? Are you okay

MIN ACTIVATIONS
MIN = -4.451

were so colorful and the stories were so fun . She
The kids played a lot of fun and interesting
a funny face . The sandwiches are spicy ! They have
Da isy started making videos and put them up on
characters and watching the funny video . She went to the
She played games and watched videos on the computer all day
cheered very loudly because the dance was so good . Everyone
They shared food and laughed a lot . The
the pictures and said the names of the things she saw
funny animals and the silly jokes . But sometimes they wanted
taught her friends and her sisters how to build them too
diamond . They said the names of the shapes and looked
and arrows . They made them from sticks and strings and
fan . They pretend the shapes are flying . They have
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
takes a sip . The juice is sweet and cold .
pushed the buttons and the images changed back to the way
. They both think their shapes are good . But they

INTERVAL 3.356 - 5.958
CONTAINS 0.027%

feels a burn in his tum my . He is angry
was washed and dried , Ang ie and her mum headed
. " Hi Tweet ie , do you want
are you , Lily ?" Tim called out . He looked
walking down the aisle , Tim my saw a big ,

INTERVAL 0.753 - 3.356
CONTAINS 19.943%

But first , let 's find some food for your tum
bear was so sad , he had wanted to hang out
rock . The lizard is green and has a long tail
surface . He said goodbye to the butterfly and ran off
. He went on his way feeling strong and full of

INTERVAL -1.849 - 0.753
CONTAINS 77.881%

. Jack y was excited ! Jack y took
and saw a fluffy brown puppy inside . The puppy w
for his kingdom . He was loyal and brave and had
trusts Lily . He moves his hand and shows his work
glad that Amy helped them to play together again . They

INTERVAL -4.451 - -1.849
CONTAINS 2.148%

celebrate with him . They played games and ate cake .
who liked to play outside . One day , they went
apple was not y ummy . It was bitter and hard
kept rubbing , and the colors started to look more and
polite . He did not say hello or please or thank
Token his
Token ID465
Feature activation+8.64e-01

Pos logit contributions
bur+0.117
ppa+0.116
rying+0.115
gie+0.114
ior+0.114
Neg logit contributions
 vows-0.071
 prize-0.067
 great-0.064
 trophy-0.062
 are-0.061
Token head
Token ID1182
Feature activation+5.51e-01

Pos logit contributions
rying+0.044
bur+0.043
ppa+0.043
ind+0.041
i+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+2.00e-01

Pos logit contributions
bur+0.025
rying+0.025
ppa+0.025
ind+0.024
i+0.024
Neg logit contributions
 vows-0.024
 prize-0.022
 contest-0.021
 trophy-0.021
cakes-0.021
Token of
Token ID286
Feature activation+1.04e+00

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.010
ind+0.009
i+0.009
Neg logit contributions
 vows-0.008
 prize-0.007
 contest-0.007
 trophy-0.007
cakes-0.007
Token his
Token ID465
Feature activation+1.36e+00

Pos logit contributions
ppa+0.058
rying+0.058
bur+0.057
ety+0.055
i+0.055
Neg logit contributions
 vows-0.036
 prize-0.033
 contest-0.032
 trophy-0.032
apy-0.030
Token bur
Token ID4356
Feature activation+5.04e+00

Pos logit contributions
rying+0.066
bur+0.066
ppa+0.065
ety+0.061
i+0.060
Neg logit contributions
 vows-0.059
 prize-0.053
 trophy-0.052
 contest-0.051
apy-0.049
Tokenrow
Token ID808
Feature activation+2.20e+00

Pos logit contributions
ior+0.147
ety+0.128
ppa+0.128
 Owl+0.123
ind+0.123
Neg logit contributions
ades-0.244
uits-0.239
 vows-0.222
ade-0.217
 are-0.213
Token and
Token ID290
Feature activation+1.12e+00

Pos logit contributions
bur+0.115
ppa+0.113
ind+0.113
rying+0.112
ior+0.111
Neg logit contributions
 vows-0.079
cakes-0.069
 contest-0.069
 prize-0.069
case-0.068
Token saw
Token ID2497
Feature activation+8.51e-01

Pos logit contributions
bur+0.055
rying+0.054
ppa+0.053
ind+0.053
ety+0.051
Neg logit contributions
 vows-0.048
 prize-0.042
apy-0.041
 trophy-0.041
 contest-0.040
Token something
Token ID1223
Feature activation-1.15e+00

Pos logit contributions
bur+0.048
rying+0.048
ppa+0.047
ind+0.045
ety+0.045
Neg logit contributions
 vows-0.029
 prize-0.026
 contest-0.025
 trophy-0.025
apy-0.025
Token new
Token ID649
Feature activation+6.30e-01

Pos logit contributions
 vows+0.048
 Prize+0.040
 contest+0.040
 prize+0.039
cakes+0.039
Neg logit contributions
rying-0.055
i-0.054
bur-0.054
ind-0.053
ppa-0.052
Token to
Token ID284
Feature activation-5.81e-01

Pos logit contributions
bur+0.064
ppa+0.062
ind+0.062
rying+0.062
ior+0.060
Neg logit contributions
 vows-0.039
 prize-0.036
 contest-0.036
 trophy-0.035
 joke-0.033
Token venture
Token ID13189
Feature activation+1.83e+00

Pos logit contributions
 vows+0.021
cakes+0.018
 prize+0.018
 contest+0.018
 trophy+0.018
Neg logit contributions
bur-0.031
rying-0.030
ppa-0.029
i-0.029
ind-0.029
Token out
Token ID503
Feature activation+1.96e+00

Pos logit contributions
ppa+0.102
bur+0.100
ior+0.097
gie+0.096
ind+0.096
Neg logit contributions
 contest-0.061
 prize-0.059
 tea-0.058
 vows-0.057
 are-0.053
Token from
Token ID422
Feature activation+2.31e+00

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
 vows-0.049
Token his
Token ID465
Feature activation+1.70e+00

Pos logit contributions
ppa+0.152
bur+0.136
rying+0.134
i+0.134
ety+0.134
Neg logit contributions
 contest-0.064
 prize-0.064
 tea-0.059
 festival-0.056
 stage-0.055
Token bur
Token ID4356
Feature activation+4.97e+00

Pos logit contributions
rying+0.072
ppa+0.071
bur+0.067
ior+0.066
cker+0.066
Neg logit contributions
 prize-0.080
 vows-0.080
 tea-0.075
 contest-0.075
 third-0.074
Tokenrow
Token ID808
Feature activation+2.76e+00

Pos logit contributions
ior+0.166
ppa+0.144
 bruised+0.140
pless+0.137
 afar+0.135
Neg logit contributions
ades-0.215
uits-0.209
ade-0.208
 parties-0.189
br-0.187
Token and
Token ID290
Feature activation+1.65e+00

Pos logit contributions
ior+0.168
ind+0.163
bur+0.160
ppa+0.159
gie+0.154
Neg logit contributions
 contest-0.072
case-0.070
uits-0.065
 vows-0.063
cakes-0.063
Token explore
Token ID7301
Feature activation+9.62e-01

Pos logit contributions
ind+0.099
ppa+0.098
bur+0.098
rying+0.095
ior+0.094
Neg logit contributions
 vows-0.050
 prize-0.045
 celebrate-0.043
 contest-0.043
 are-0.043
Token the
Token ID262
Feature activation+3.19e+00

Pos logit contributions
ppa+0.058
bur+0.058
rying+0.055
ety+0.055
ior+0.054
Neg logit contributions
 vows-0.027
 prize-0.026
 contest-0.026
 trophy-0.024
 are-0.024
Token forest
Token ID8222
Feature activation+8.03e-01

Pos logit contributions
ppa+0.180
ior+0.167
owing+0.165
cker+0.164
rying+0.163
Neg logit contributions
 great-0.116
 lot-0.115
 funny-0.103
 big-0.101
 tea-0.098
Token who
Token ID508
Feature activation+2.69e-01

Pos logit contributions
bur+0.090
rying+0.086
ppa+0.084
ior+0.083
ind+0.080
Neg logit contributions
 vows-0.079
 contest-0.079
 prize-0.076
 trophy-0.075
case-0.073
Token lived
Token ID5615
Feature activation+1.19e+00

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
ind+0.014
i+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+1.81e-01

Pos logit contributions
bur+0.058
ppa+0.057
ior+0.057
gie+0.055
rying+0.055
Neg logit contributions
 vows-0.046
 contest-0.044
 prize-0.042
 trophy-0.042
apy-0.041
Token his
Token ID465
Feature activation+1.64e+00

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.010
ind+0.010
i+0.010
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.005
apy-0.005
Token cozy
Token ID37438
Feature activation+3.17e+00

Pos logit contributions
rying+0.082
ppa+0.079
bur+0.077
gie+0.072
ener+0.072
Neg logit contributions
 vows-0.068
 prize-0.063
 contest-0.062
 tea-0.061
 trophy-0.060
Token bur
Token ID4356
Feature activation+4.96e+00

Pos logit contributions
rying+0.139
bur+0.130
ppa+0.129
eking+0.122
ior+0.119
Neg logit contributions
 vows-0.147
 tea-0.137
 prize-0.134
 team-0.133
 lot-0.131
Tokenrow
Token ID808
Feature activation+3.02e+00

Pos logit contributions
ior+0.158
fred+0.130
 Tooth+0.129
ppa+0.127
shadow+0.127
Neg logit contributions
ades-0.234
 vows-0.216
uits-0.215
ade-0.206
apy-0.199
Token.
Token ID13
Feature activation+7.10e-01

Pos logit contributions
bur+0.171
ior+0.170
ppa+0.163
rying+0.159
gie+0.159
Neg logit contributions
 vows-0.090
case-0.085
 contest-0.081
 trophy-0.081
 prize-0.079
Token He
Token ID679
Feature activation+1.15e+00

Pos logit contributions
rying+0.039
bur+0.038
ppa+0.038
ind+0.036
i+0.036
Neg logit contributions
 vows-0.026
 prize-0.022
 contest-0.022
 trophy-0.022
apy-0.021
Token loved
Token ID6151
Feature activation+1.18e+00

Pos logit contributions
rying+0.068
bur+0.068
ppa+0.065
ind+0.063
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+7.06e-03

Pos logit contributions
ppa+0.063
rying+0.062
bur+0.061
cker+0.058
ior+0.058
Neg logit contributions
 vows-0.045
 prize-0.040
 trophy-0.039
 contest-0.039
 tea-0.039
TokenN
Token ID45
Feature activation+7.96e-01

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+5.21e-01

Pos logit contributions
bur+0.035
rying+0.033
ppa+0.033
ind+0.032
gie+0.031
Neg logit contributions
 vows-0.038
 prize-0.033
 trophy-0.033
 contest-0.032
cakes-0.032
Token was
Token ID373
Feature activation+1.45e-01

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
apy-0.016
Token panic
Token ID13619
Feature activation-1.50e-02

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
ind+0.006
i+0.006
Neg logit contributions
 vows-0.006
 prize-0.006
 contest-0.006
 trophy-0.005
cakes-0.005
Token-
Token ID12
Feature activation+2.22e+00

Pos logit contributions
 vows+0.001
 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+4.81e+00

Pos logit contributions
ior+0.101
bur+0.100
ppa+0.095
ind+0.094
gie+0.093
Neg logit contributions
apy-0.084
cakes-0.083
 contest-0.079
 vows-0.076
case-0.076
Tokenicken
Token ID5973
Feature activation+1.02e+00

Pos logit contributions
ior+0.155
 axe+0.147
oscope+0.140
 seen+0.136
 since+0.135
Neg logit contributions
ades-0.214
 vows-0.200
�-0.197
apy-0.188
ics-0.180
Token.
Token ID13
Feature activation+7.41e-01

Pos logit contributions
bur+0.051
rying+0.050
ppa+0.050
ind+0.048
ety+0.047
Neg logit contributions
 vows-0.042
 prize-0.037
 contest-0.037
 trophy-0.036
cakes-0.035
Token She
Token ID1375
Feature activation+1.26e+00

Pos logit contributions
bur+0.044
rying+0.043
ppa+0.043
ind+0.041
i+0.040
Neg logit contributions
 vows-0.024
 contest-0.020
 prize-0.020
apy-0.019
 trophy-0.019
Token screamed
Token ID25421
Feature activation-4.94e-01

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
 contest-0.039
 joke-0.039
Token for
Token ID329
Feature activation+7.41e-01

Pos logit contributions
 vows+0.025
 prize+0.023
 contest+0.023
 trophy+0.022
cakes+0.022
Neg logit contributions
rying-0.020
bur-0.019
ppa-0.019
i-0.019
ind-0.019
Token Benny
Token ID44275
Feature activation+1.40e+00

Pos logit contributions
bur+0.034
rying+0.034
ppa+0.034
ind+0.032
i+0.032
Neg logit contributions
 vows-0.027
 prize-0.025
 contest-0.024
 trophy-0.024
apy-0.024
Token lived
Token ID5615
Feature activation+1.26e+00

Pos logit contributions
rying+0.086
bur+0.085
ppa+0.082
ener+0.079
ind+0.079
Neg logit contributions
 vows-0.039
 are-0.032
 joke-0.031
 contest-0.031
 trophy-0.031
Token in
Token ID287
Feature activation+5.37e-01

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-0.042
 trophy-0.041
apy-0.040
Token a
Token ID257
Feature activation+5.93e-01

Pos logit contributions
rying+0.032
ppa+0.032
bur+0.032
i+0.031
ind+0.030
Neg logit contributions
 vows-0.016
 prize-0.015
 contest-0.014
 trophy-0.014
apy-0.013
Token cozy
Token ID37438
Feature activation+2.67e+00

Pos logit contributions
rying+0.034
bur+0.034
ppa+0.033
i+0.032
gie+0.032
Neg logit contributions
 vows-0.019
 contest-0.017
 prize-0.017
 trophy-0.017
apy-0.016
Token bur
Token ID4356
Feature activation+4.80e+00

Pos logit contributions
rying+0.127
bur+0.120
ppa+0.117
eking+0.116
cker+0.110
Neg logit contributions
 vows-0.109
 team-0.106
 prize-0.106
 tea-0.105
 lot-0.104
Tokenrow
Token ID808
Feature activation+3.26e+00

Pos logit contributions
ior+0.156
shadow+0.140
ppa+0.129
gie+0.127
 Tooth+0.126
Neg logit contributions
ade-0.205
uits-0.204
ades-0.204
 tea-0.195
 parties-0.191
Token with
Token ID351
Feature activation+4.15e-01

Pos logit contributions
ior+0.184
bur+0.181
ppa+0.175
gie+0.171
umper+0.167
Neg logit contributions
 contest-0.099
case-0.097
 trophy-0.090
 vows-0.088
 prize-0.087
Token his
Token ID465
Feature activation+1.46e+00

Pos logit contributions
rying+0.023
bur+0.023
ppa+0.023
ind+0.022
i+0.022
Neg logit contributions
 vows-0.015
 prize-0.013
 contest-0.012
 trophy-0.012
apy-0.012
Token family
Token ID1641
Feature activation+1.34e+00

Pos logit contributions
rying+0.083
ppa+0.079
bur+0.078
ior+0.077
umper+0.075
Neg logit contributions
 vows-0.051
 prize-0.048
 trophy-0.044
 lot-0.043
 contest-0.043
Token.
Token ID13
Feature activation+4.50e-01

Pos logit contributions
rying+0.072
bur+0.072
ppa+0.072
ior+0.068
ind+0.068
Neg logit contributions
 vows-0.045
 trophy-0.042
 prize-0.042
 contest-0.041
 tea-0.039
Token mom
Token ID1995
Feature activation+1.86e+00

Pos logit contributions
bur+0.018
rying+0.018
ppa+0.017
i+0.017
ind+0.017
Neg logit contributions
 vows-0.012
 prize-0.010
 contest-0.010
 trophy-0.010
apy-0.010
Token called
Token ID1444
Feature activation+9.66e-02

Pos logit contributions
rying+0.097
ind+0.096
bur+0.094
ior+0.092
cker+0.091
Neg logit contributions
 vows-0.061
 were-0.058
 contest-0.057
cakes-0.056
 are-0.056
Token out
Token ID503
Feature activation-7.41e-01

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-0.003
 trophy-0.003
cakes-0.003
Token,
Token ID11
Feature activation+1.15e+00

Pos logit contributions
 vows+0.038
 trophy+0.034
 contest+0.034
 prize+0.034
cakes+0.033
Neg logit contributions
rying-0.029
ind-0.027
i-0.027
bur-0.027
ppa-0.027
Token "
Token ID366
Feature activation+2.89e+00

Pos logit contributions
bur+0.084
rying+0.082
ppa+0.082
ind+0.081
cker+0.079
Neg logit contributions
 vows-0.019
apy-0.014
 contest-0.013
 prize-0.012
cakes-0.012
TokenMill
Token ID22603
Feature activation+4.74e+00

Pos logit contributions
ppa+0.131
asured+0.130
rying+0.130
cker+0.130
ishing+0.127
Neg logit contributions
Everyone-0.098
Happy-0.098
 vows-0.094
 were-0.093
 celebrate-0.092
Tokenie
Token ID494
Feature activation+3.65e-01

Pos logit contributions
oscope+0.208
 territory+0.192
ior+0.186
 crank+0.181
ringe+0.180
Neg logit contributions
 tea-0.137
 are-0.134
 were-0.126
 parties-0.125
 they-0.125
Token,
Token ID11
Feature activation+6.35e-01

Pos logit contributions
bur+0.020
rying+0.020
ppa+0.020
ind+0.019
i+0.019
Neg logit contributions
 vows-0.013
 prize-0.011
 contest-0.011
 trophy-0.010
apy-0.010
Token come
Token ID1282
Feature activation+1.64e+00

Pos logit contributions
bur+0.034
ppa+0.033
rying+0.033
ind+0.032
i+0.032
Neg logit contributions
 vows-0.024
 prize-0.021
 contest-0.021
 trophy-0.020
 are-0.020
Token home
Token ID1363
Feature activation+1.29e+00

Pos logit contributions
ppa+0.083
bur+0.080
cker+0.077
i+0.076
ior+0.076
Neg logit contributions
 vows-0.061
 celebrate-0.059
 prize-0.059
 blast-0.057
 contest-0.056
Token!"
Token ID2474
Feature activation+1.21e+00

Pos logit contributions
bur+0.064
ppa+0.062
rying+0.060
cker+0.059
gie+0.059
Neg logit contributions
 vows-0.052
 prize-0.047
 contest-0.046
cakes-0.045
 trophy-0.044
Token was
Token ID373
Feature activation-9.23e-02

Pos logit contributions
 vows+0.028
 prize+0.023
 trophy+0.022
 contest+0.022
 Prize+0.021
Neg logit contributions
rying-0.056
bur-0.056
i-0.055
ppa-0.054
ety-0.053
Token struggling
Token ID9648
Feature activation+1.41e+00

Pos logit contributions
 vows+0.004
 prize+0.004
 contest+0.004
 trophy+0.004
cakes+0.004
Neg logit contributions
bur-0.004
rying-0.004
ppa-0.004
ind-0.004
i-0.004
Token.
Token ID13
Feature activation+1.42e+00

Pos logit contributions
bur+0.077
ppa+0.076
ior+0.073
rying+0.071
ind+0.070
Neg logit contributions
 vows-0.046
 contest-0.045
 prize-0.045
 trophy-0.044
apy-0.041
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
rying+0.094
ppa+0.093
bur+0.093
ind+0.091
i+0.089
Neg logit contributions
 vows-0.032
 Everyone-0.030
apy-0.030
cakes-0.029
 contest-0.028
Token
Token ID198
Feature activation+1.36e+00

Pos logit contributions
rying+0.076
bur+0.074
ppa+0.073
i+0.072
ind+0.071
Neg logit contributions
 vows-0.026
apy-0.023
 contest-0.023
 prize-0.022
ades-0.022
TokenMill
Token ID22603
Feature activation+4.73e+00

Pos logit contributions
bur+0.058
rying+0.057
ppa+0.054
i+0.053
ior+0.053
Neg logit contributions
 vows-0.061
apy-0.061
 contest-0.058
ades-0.058
 Everyone-0.058
Tokenie
Token ID494
Feature activation+2.45e+00

Pos logit contributions
 property+0.216
 territory+0.212
 spine+0.208
rying+0.205
shadow+0.202
Neg logit contributions
 were-0.135
 vows-0.126
 are-0.116
ade-0.110
 tea-0.110
Token tried
Token ID3088
Feature activation+5.39e-01

Pos logit contributions
bur+0.140
rying+0.135
ind+0.125
ior+0.124
ppa+0.124
Neg logit contributions
 vows-0.082
case-0.072
 contest-0.071
apy-0.071
 were-0.068
Token to
Token ID284
Feature activation+3.83e-01

Pos logit contributions
bur+0.026
rying+0.026
ppa+0.026
ind+0.025
i+0.024
Neg logit contributions
 vows-0.022
 prize-0.021
 contest-0.020
 trophy-0.020
apy-0.019
Token reach
Token ID3151
Feature activation+7.30e-01

Pos logit contributions
bur+0.020
rying+0.020
ppa+0.020
ind+0.019
i+0.019
Neg logit contributions
 vows-0.014
 prize-0.013
 contest-0.013
 trophy-0.012
apy-0.012
Token the
Token ID262
Feature activation-6.22e-01

Pos logit contributions
ppa+0.040
rying+0.040
bur+0.040
ind+0.038
ior+0.037
Neg logit contributions
 vows-0.025
 prize-0.023
 contest-0.023
 trophy-0.022
apy-0.021
Token should
Token ID815
Feature activation+2.72e-01

Pos logit contributions
bur+0.016
rying+0.016
ppa+0.016
ind+0.015
i+0.015
Neg logit contributions
 vows-0.011
 prize-0.009
 contest-0.009
 trophy-0.009
apy-0.009
Token never
Token ID1239
Feature activation+9.95e-01

Pos logit contributions
bur+0.016
rying+0.015
ppa+0.015
ind+0.015
i+0.015
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
apy-0.007
Token come
Token ID1282
Feature activation+1.93e+00

Pos logit contributions
bur+0.062
ppa+0.061
rying+0.061
ind+0.060
ior+0.058
Neg logit contributions
 vows-0.027
 prize-0.026
 contest-0.025
 joke-0.025
 trophy-0.024
Token close
Token ID1969
Feature activation+2.80e+00

Pos logit contributions
ior+0.102
ppa+0.102
bur+0.097
i+0.095
ind+0.094
Neg logit contributions
 prize-0.063
 vows-0.062
 contest-0.060
 join-0.058
 celebrate-0.058
Token to
Token ID284
Feature activation+2.43e+00

Pos logit contributions
ppa+0.165
ior+0.162
cker+0.156
bur+0.155
gie+0.153
Neg logit contributions
 vows-0.073
 prize-0.072
 contest-0.072
 trophy-0.066
 are-0.063
Token an
Token ID281
Feature activation+4.69e+00

Pos logit contributions
rying+0.156
ppa+0.154
bur+0.153
ior+0.151
ishing+0.150
Neg logit contributions
 are-0.056
 prize-0.055
 celebrate-0.054
 tea-0.053
 contest-0.050
Token owl
Token ID39610
Feature activation+1.92e+00

Pos logit contributions
bur+0.196
rying+0.191
ishing+0.180
ppa+0.179
eking+0.167
Neg logit contributions
 prize-0.203
 idea-0.195
 great-0.184
 contest-0.184
 surprise-0.181
Token again
Token ID757
Feature activation+2.44e+00

Pos logit contributions
bur+0.097
ppa+0.093
ind+0.093
rying+0.092
ior+0.090
Neg logit contributions
 vows-0.071
 contest-0.071
 prize-0.071
 trophy-0.067
 celebrate-0.063
Token!".
Token ID48220
Feature activation+7.78e-01

Pos logit contributions
bur+0.137
ppa+0.132
gie+0.131
ior+0.129
rying+0.128
Neg logit contributions
 vows-0.076
 prize-0.073
 contest-0.073
 win-0.069
 celebrate-0.069
Token
Token ID198
Feature activation+3.27e-01

Pos logit contributions
bur+0.048
rying+0.048
ppa+0.047
ind+0.047
i+0.046
Neg logit contributions
 vows-0.022
 contest-0.019
 prize-0.019
cakes-0.019
apy-0.018
Token
Token ID198
Feature activation-2.13e-01

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.019
i+0.018
ind+0.018
Neg logit contributions
 vows-0.011
 prize-0.009
 contest-0.009
 trophy-0.009
apy-0.009
Token there
Token ID612
Feature activation+9.45e-01

Pos logit contributions
ppa+0.072
bur+0.072
rying+0.070
ior+0.069
ety+0.068
Neg logit contributions
 vows-0.066
 contest-0.065
 prize-0.064
 trophy-0.062
 festival-0.058
Token?",
Token ID35379
Feature activation+1.44e+00

Pos logit contributions
rying+0.039
ppa+0.039
bur+0.039
ind+0.038
i+0.037
Neg logit contributions
 vows-0.045
 prize-0.042
 contest-0.042
 trophy-0.041
cakes-0.039
Token asked
Token ID1965
Feature activation+1.15e+00

Pos logit contributions
rying+0.077
bur+0.077
ind+0.074
ppa+0.074
ety+0.071
Neg logit contributions
 vows-0.052
apy-0.050
 prize-0.049
 contest-0.049
 trophy-0.048
Token the
Token ID262
Feature activation+1.79e+00

Pos logit contributions
rying+0.069
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-0.030
apy-0.030
Token wood
Token ID4898
Feature activation+2.70e+00

Pos logit contributions
rying+0.101
ppa+0.097
bur+0.097
ind+0.093
ety+0.093
Neg logit contributions
 prize-0.063
 contest-0.062
 trophy-0.062
 vows-0.060
 third-0.056
Tokenpe
Token ID431
Feature activation+4.67e+00

Pos logit contributions
bur+0.104
ind+0.102
ior+0.101
ety+0.099
umper+0.097
Neg logit contributions
 vows-0.124
 trophy-0.123
 contest-0.120
 prize-0.120
case-0.117
Tokencker
Token ID15280
Feature activation+2.97e+00

Pos logit contributions
ior+0.131
bur+0.130
athy+0.119
umper+0.118
ind+0.118
Neg logit contributions
 laugh-0.234
 vows-0.232
ves-0.223
 trophy-0.220
ades-0.218
Token.
Token ID13
Feature activation+4.21e-01

Pos logit contributions
bur+0.182
ind+0.177
ior+0.171
ppa+0.169
umper+0.168
Neg logit contributions
 laugh-0.075
 vows-0.074
 trophy-0.067
 prize-0.067
apy-0.066
Token
Token ID198
Feature activation+6.09e-01

Pos logit contributions
bur+0.025
rying+0.025
ppa+0.024
ind+0.024
i+0.024
Neg logit contributions
 vows-0.013
 prize-0.011
 contest-0.011
 trophy-0.011
apy-0.011
Token
Token ID198
Feature activation+4.21e-01

Pos logit contributions
rying+0.037
bur+0.037
ppa+0.036
i+0.035
ind+0.035
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
apy-0.015
 trophy-0.015
TokenThe
Token ID464
Feature activation+2.05e+00

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-0.014
 contest-0.014
 trophy-0.013
apy-0.013
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
ppa+0.034
bur+0.034
rying+0.034
ind+0.032
i+0.032
Neg logit contributions
 vows-0.020
 prize-0.017
 contest-0.017
 trophy-0.016
apy-0.016
Token sunshine
Token ID34488
Feature activation+5.97e-01

Pos logit contributions
ppa+0.077
rying+0.075
bur+0.074
ety+0.070
i+0.070
Neg logit contributions
 vows-0.049
 prize-0.043
 trophy-0.042
 contest-0.042
 are-0.040
Token.
Token ID13
Feature activation+1.66e+00

Pos logit contributions
bur+0.030
rying+0.030
ppa+0.030
ind+0.029
i+0.028
Neg logit contributions
 vows-0.024
 prize-0.021
 contest-0.021
 trophy-0.021
cakes-0.020
Token
Token ID198
Feature activation+5.50e-01

Pos logit contributions
ppa+0.117
rying+0.116
bur+0.114
ind+0.112
i+0.109
Neg logit contributions
 Everyone-0.033
 vows-0.033
apy-0.031
cakes-0.027
 Everybody-0.027
Token
Token ID198
Feature activation+1.38e+00

Pos logit contributions
rying+0.033
bur+0.033
ppa+0.032
i+0.032
ind+0.031
Neg logit contributions
 vows-0.016
 prize-0.014
 contest-0.014
apy-0.013
 trophy-0.013
TokenMill
Token ID22603
Feature activation+4.63e+00

Pos logit contributions
bur+0.062
rying+0.061
ppa+0.059
i+0.058
ior+0.058
Neg logit contributions
 vows-0.060
apy-0.057
 contest-0.056
case-0.054
 Everyone-0.054
Tokenie
Token ID494
Feature activation+2.12e+00

Pos logit contributions
 property+0.216
 territory+0.206
 spine+0.205
rying+0.202
shadow+0.202
Neg logit contributions
 were-0.133
 vows-0.123
 are-0.113
ade-0.106
 tea-0.106
Token was
Token ID373
Feature activation+8.29e-01

Pos logit contributions
bur+0.118
rying+0.112
ppa+0.112
ior+0.107
umper+0.106
Neg logit contributions
 vows-0.075
 contest-0.064
 were-0.062
 they-0.061
apy-0.061
Token so
Token ID523
Feature activation-3.34e-01

Pos logit contributions
bur+0.045
ppa+0.044
rying+0.044
ind+0.043
ior+0.042
Neg logit contributions
 vows-0.029
 contest-0.026
 prize-0.026
apy-0.025
 trophy-0.025
Token excited
Token ID6568
Feature activation+1.36e+00

Pos logit contributions
 vows+0.013
 prize+0.012
cakes+0.011
 trophy+0.011
 contest+0.011
Neg logit contributions
rying-0.017
bur-0.017
ppa-0.017
i-0.017
ind-0.017
Token that
Token ID326
Feature activation+6.06e-01

Pos logit contributions
bur+0.076
ppa+0.076
rying+0.073
umper+0.071
ind+0.071
Neg logit contributions
 vows-0.045
 prize-0.042
 contest-0.042
cakes-0.041
 trophy-0.038
Token"
Token ID1
Feature activation+4.90e-01

Pos logit contributions
bur+0.048
rying+0.048
i+0.047
ppa+0.047
ind+0.045
Neg logit contributions
 vows-0.030
apy-0.028
cakes-0.027
case-0.027
 prize-0.027
TokenWho
Token ID8241
Feature activation-7.31e-01

Pos logit contributions
rying+0.022
bur+0.021
ppa+0.021
i+0.021
ind+0.021
Neg logit contributions
 vows-0.022
 prize-0.020
 contest-0.020
 trophy-0.020
cakes-0.020
Token's
Token ID338
Feature activation+2.37e-01

Pos logit contributions
 vows+0.023
 prize+0.020
cakes+0.019
 trophy+0.019
apy+0.019
Neg logit contributions
bur-0.042
ppa-0.041
rying-0.040
i-0.040
ind-0.039
Token there
Token ID612
Feature activation+9.98e-01

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.010
ind+0.010
i+0.010
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.010
 trophy-0.010
apy-0.010
Token?"
Token ID1701
Feature activation+1.22e+00

Pos logit contributions
rying+0.044
ppa+0.044
bur+0.043
ind+0.042
i+0.041
Neg logit contributions
 vows-0.044
 prize-0.042
 contest-0.042
 trophy-0.041
 are-0.040
Token Tim
Token ID5045
Feature activation+4.56e+00

Pos logit contributions
rying+0.073
bur+0.071
ind+0.070
ppa+0.070
i+0.065
Neg logit contributions
apy-0.040
 vows-0.038
 prize-0.036
 contest-0.036
 trophy-0.036
Tokenmy
Token ID1820
Feature activation+3.49e+00

Pos logit contributions
ind+0.143
 predators+0.141
rying+0.140
cker+0.136
 property+0.127
Neg logit contributions
 laugh-0.212
 g-0.208
 joke-0.203
 were-0.196
 third-0.196
Token asked
Token ID1965
Feature activation+7.00e-01

Pos logit contributions
bur+0.182
rying+0.179
ior+0.172
ind+0.171
 property+0.168
Neg logit contributions
 g-0.112
 dance-0.109
 laugh-0.107
 joke-0.107
 cl-0.105
Token.
Token ID13
Feature activation-1.19e-01

Pos logit contributions
bur+0.038
rying+0.037
ppa+0.037
ind+0.037
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+7.72e-01

Pos logit contributions
 vows+0.004
 prize+0.004
 contest+0.004
 trophy+0.004
cakes+0.004
Neg logit contributions
bur-0.006
rying-0.006
ppa-0.006
i-0.006
gie-0.006
Token
Token ID198
Feature activation+4.57e-01

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 cry
Token ID3960
Feature activation+5.44e-01

Pos logit contributions
 vows+0.046
cakes+0.038
 contest+0.037
 prize+0.037
uits+0.037
Neg logit contributions
 owl-0.056
ind-0.056
rying-0.056
 Owl-0.055
gie-0.054
Token coming
Token ID2406
Feature activation+1.40e+00

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-0.020
 trophy-0.020
apy-0.019
Token from
Token ID422
Feature activation+1.85e+00

Pos logit contributions
ppa+0.078
bur+0.076
ishing+0.070
i+0.069
ind+0.069
Neg logit contributions
 vows-0.047
 prize-0.044
 contest-0.042
 are-0.041
 laugh-0.041
Token outside
Token ID2354
Feature activation-1.69e-01

Pos logit contributions
ppa+0.113
ety+0.103
rying+0.103
bur+0.103
i+0.100
Neg logit contributions
 prize-0.055
 contest-0.055
 festival-0.051
 trophy-0.051
 vows-0.050
Token his
Token ID465
Feature activation+1.61e+00

Pos logit contributions
 vows+0.008
 prize+0.007
 contest+0.007
 trophy+0.007
cakes+0.007
Neg logit contributions
rying-0.007
bur-0.007
ppa-0.007
i-0.007
ind-0.007
Token bur
Token ID4356
Feature activation+4.56e+00

Pos logit contributions
rying+0.087
ppa+0.084
bur+0.082
cker+0.080
gie+0.077
Neg logit contributions
 prize-0.059
 vows-0.059
 trophy-0.055
 tea-0.053
case-0.052
Tokenrow
Token ID808
Feature activation+2.35e+00

Pos logit contributions
ior+0.129
shadow+0.126
ppa+0.126
 afar+0.125
years+0.120
Neg logit contributions
ades-0.188
ade-0.181
uits-0.180
br-0.177
cakes-0.165
Token.
Token ID13
Feature activation+7.47e-01

Pos logit contributions
ior+0.137
bur+0.137
ind+0.136
ppa+0.136
rying+0.132
Neg logit contributions
case-0.063
 vows-0.061
 contest-0.059
cakes-0.057
 prize-0.055
Token
Token ID198
Feature activation+3.59e-01

Pos logit contributions
rying+0.042
bur+0.042
ppa+0.041
ind+0.041
i+0.040
Neg logit contributions
 vows-0.026
 prize-0.022
apy-0.022
 contest-0.022
 trophy-0.021
Token
Token ID198
Feature activation+1.28e-01

Pos logit contributions
bur+0.021
rying+0.021
ppa+0.021
i+0.020
ind+0.020
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.010
 trophy-0.009
apy-0.009
TokenHe
Token ID1544
Feature activation+1.64e+00

Pos logit contributions
bur+0.006
rying+0.006
ppa+0.006
ind+0.006
i+0.006
Neg logit contributions
 vows-0.005
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.004
Token fluffy
Token ID39145
Feature activation+1.31e+00

Pos logit contributions
rying+0.075
ppa+0.072
bur+0.071
ind+0.069
ener+0.068
Neg logit contributions
 vows-0.037
apy-0.035
 trophy-0.033
 prize-0.032
 contest-0.032
Token and
Token ID290
Feature activation+6.33e-01

Pos logit contributions
rying+0.078
bur+0.077
ppa+0.076
cker+0.072
shadow+0.070
Neg logit contributions
 vows-0.040
 tea-0.035
 are-0.034
 tag-0.034
 prize-0.034
Token lived
Token ID5615
Feature activation+7.35e-01

Pos logit contributions
rying+0.035
bur+0.035
ppa+0.034
ind+0.033
i+0.033
Neg logit contributions
 vows-0.022
 prize-0.019
apy-0.019
 trophy-0.019
 contest-0.019
Token in
Token ID287
Feature activation+5.74e-01

Pos logit contributions
bur+0.035
ppa+0.034
rying+0.033
ior+0.033
i+0.033
Neg logit contributions
 vows-0.031
 contest-0.029
 prize-0.028
 trophy-0.028
apy-0.027
Token a
Token ID257
Feature activation+4.50e-01

Pos logit contributions
rying+0.035
ppa+0.035
bur+0.035
i+0.033
ind+0.033
Neg logit contributions
 vows-0.017
 prize-0.015
 contest-0.014
 trophy-0.014
apy-0.013
Token bur
Token ID4356
Feature activation+4.56e+00

Pos logit contributions
bur+0.027
rying+0.026
ppa+0.026
i+0.025
ind+0.025
Neg logit contributions
 vows-0.014
 contest-0.012
 prize-0.012
 trophy-0.012
apy-0.011
Tokenrow
Token ID808
Feature activation+2.91e+00

Pos logit contributions
ior+0.152
shadow+0.134
 Tooth+0.128
ppa+0.123
bur+0.120
Neg logit contributions
ade-0.196
ades-0.194
uits-0.189
 lot-0.183
br-0.183
Token in
Token ID287
Feature activation+1.08e+00

Pos logit contributions
ior+0.175
bur+0.174
ppa+0.167
gie+0.160
ety+0.160
Neg logit contributions
 contest-0.079
case-0.077
 vows-0.071
 trophy-0.069
 prize-0.067
Token the
Token ID262
Feature activation+3.00e+00

Pos logit contributions
ppa+0.070
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+1.59e+00

Pos logit contributions
rying+0.172
ppa+0.161
ener+0.157
ishing+0.155
owing+0.155
Neg logit contributions
 lot-0.107
 tea-0.104
 great-0.104
 third-0.098
 contest-0.094
Token.
Token ID13
Feature activation+6.51e-02

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-0.044
 are-0.042
case-0.040
 prize-0.040
Token
Token ID198
Feature activation+8.25e-01

Pos logit contributions
rying+0.039
bur+0.039
ppa+0.038
i+0.038
ind+0.037
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.015
apy-0.015
 trophy-0.015
Token"
Token ID1
Feature activation+4.85e-01

Pos logit contributions
bur+0.046
rying+0.046
ppa+0.044
i+0.044
ind+0.043
Neg logit contributions
 vows-0.027
apy-0.026
cakes-0.025
 contest-0.025
 prize-0.024
TokenWhat
Token ID2061
Feature activation-1.65e+00

Pos logit contributions
rying+0.022
bur+0.021
ppa+0.021
i+0.020
ind+0.020
Neg logit contributions
 vows-0.022
 contest-0.020
 prize-0.020
apy-0.020
 trophy-0.020
Token happened
Token ID3022
Feature activation+1.11e+00

Pos logit contributions
 vows+0.076
cakes+0.064
 prize+0.064
uits+0.063
 contest+0.061
Neg logit contributions
my-0.076
bur-0.070
ety-0.069
i-0.068
rying-0.066
Token?"
Token ID1701
Feature activation+1.01e+00

Pos logit contributions
bur+0.058
ppa+0.057
rying+0.056
ind+0.055
i+0.053
Neg logit contributions
 vows-0.040
 contest-0.040
 prize-0.040
 trophy-0.039
 joke-0.036
Token Tim
Token ID5045
Feature activation+4.55e+00

Pos logit contributions
rying+0.053
bur+0.053
ppa+0.051
ind+0.051
i+0.048
Neg logit contributions
 vows-0.037
apy-0.037
 contest-0.035
 prize-0.035
 trophy-0.034
Tokenmy
Token ID1820
Feature activation+3.76e+00

Pos logit contributions
ind+0.148
rying+0.144
 predators+0.144
orns+0.138
cker+0.138
Neg logit contributions
 laugh-0.211
 g-0.205
 joke-0.201
 third-0.191
 smile-0.191
Token asked
Token ID1965
Feature activation+8.14e-01

Pos logit contributions
bur+0.209
rying+0.208
 property+0.197
orns+0.193
ind+0.193
Neg logit contributions
 g-0.108
 cl-0.108
 laugh-0.105
 dance-0.105
 joke-0.104
Token.
Token ID13
Feature activation-2.62e-02

Pos logit contributions
bur+0.046
rying+0.045
ind+0.044
ppa+0.044
i+0.042
Neg logit contributions
 vows-0.027
 contest-0.025
 prize-0.024
 trophy-0.024
apy-0.024
Token
Token ID198
Feature activation+8.48e-01

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+3.24e-01

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+2.17e-01

Pos logit contributions
rying+0.054
ppa+0.053
bur+0.053
i+0.050
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+1.09e+00

Pos logit contributions
bur+0.011
rying+0.011
ppa+0.011
ind+0.010
i+0.010
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.007
Token into
Token ID656
Feature activation+8.72e-02

Pos logit contributions
bur+0.055
ppa+0.055
rying+0.054
ind+0.053
i+0.051
Neg logit contributions
 vows-0.044
 contest-0.039
 prize-0.039
apy-0.038
 trophy-0.037
Token their
Token ID511
Feature activation+7.63e-01

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.004
ind+0.004
i+0.004
Neg logit contributions
 vows-0.003
 prize-0.003
 contest-0.003
 trophy-0.003
cakes-0.003
Token cozy
Token ID37438
Feature activation+2.74e+00

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-0.032
 trophy-0.031
apy-0.030
Token bur
Token ID4356
Feature activation+4.51e+00

Pos logit contributions
ppa+0.132
bur+0.132
rying+0.128
umper+0.126
ior+0.122
Neg logit contributions
 vows-0.114
 tea-0.103
 prize-0.100
 dance-0.096
 lot-0.096
Tokenrows
Token ID8516
Feature activation+9.09e-01

Pos logit contributions
ior+0.151
ppa+0.124
umper+0.121
athy+0.121
 Tooth+0.119
Neg logit contributions
uits-0.218
ades-0.215
 vows-0.205
apy-0.197
ves-0.196
Token.
Token ID13
Feature activation+2.69e-01

Pos logit contributions
bur+0.045
ppa+0.044
rying+0.044
ind+0.043
ior+0.042
Neg logit contributions
 vows-0.037
 prize-0.032
 contest-0.032
 trophy-0.031
cakes-0.031
Token The
Token ID383
Feature activation+1.24e+00

Pos logit contributions
bur+0.015
rying+0.015
ppa+0.015
ind+0.015
i+0.015
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
apy-0.007
Token end
Token ID886
Feature activation-3.04e-02

Pos logit contributions
bur+0.061
rying+0.061
ppa+0.060
ior+0.057
ety+0.056
Neg logit contributions
 vows-0.053
 prize-0.048
 contest-0.047
 trophy-0.045
 festival-0.044
Token.
Token ID13
Feature activation+3.03e-01

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 able
Token ID1498
Feature activation+8.22e-01

Pos logit contributions
bur+0.030
rying+0.029
ppa+0.029
ind+0.028
i+0.028
Neg logit contributions
 vows-0.031
 contest-0.028
 prize-0.027
 trophy-0.027
apy-0.026
Token to
Token ID284
Feature activation-2.15e-01

Pos logit contributions
bur+0.040
ppa+0.040
rying+0.039
ind+0.038
i+0.037
Neg logit contributions
 vows-0.034
 prize-0.031
 contest-0.030
 trophy-0.030
apy-0.029
Token escape
Token ID6654
Feature activation+5.91e-01

Pos logit contributions
 vows+0.008
 prize+0.007
 contest+0.007
cakes+0.007
 trophy+0.006
Neg logit contributions
bur-0.012
rying-0.012
ppa-0.011
i-0.011
ind-0.011
Token from
Token ID422
Feature activation+1.63e+00

Pos logit contributions
bur+0.028
ppa+0.028
rying+0.027
ind+0.026
i+0.026
Neg logit contributions
 vows-0.025
 prize-0.023
 contest-0.022
 trophy-0.022
apy-0.021
Token his
Token ID465
Feature activation+1.15e-01

Pos logit contributions
ppa+0.094
bur+0.092
rying+0.091
ety+0.090
ior+0.089
Neg logit contributions
 vows-0.050
 prize-0.049
 contest-0.048
 trophy-0.046
apy-0.042
Token bur
Token ID4356
Feature activation+4.49e+00

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
ind+0.005
i+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+1.71e+00

Pos logit contributions
ior+0.129
ppa+0.119
ety+0.109
bur+0.108
 Tooth+0.105
Neg logit contributions
ades-0.223
uits-0.217
 vows-0.207
 prize-0.203
br-0.203
Token and
Token ID290
Feature activation+7.69e-01

Pos logit contributions
bur+0.085
ppa+0.083
rying+0.082
ind+0.082
ior+0.081
Neg logit contributions
 vows-0.066
 prize-0.060
 contest-0.060
 trophy-0.059
cakes-0.058
Token play
Token ID711
Feature activation-1.24e+00

Pos logit contributions
bur+0.041
rying+0.041
ppa+0.041
ind+0.040
i+0.039
Neg logit contributions
 vows-0.029
 prize-0.025
 contest-0.024
 trophy-0.024
apy-0.024
Token in
Token ID287
Feature activation-3.63e-01

Pos logit contributions
 vows+0.067
cakes+0.057
apy+0.055
 Prize+0.055
 trophy+0.055
Neg logit contributions
rying-0.049
bur-0.044
ind-0.043
ppa-0.042
i-0.042
Token the
Token ID262
Feature activation+1.31e+00

Pos logit contributions
 vows+0.016
cakes+0.014
 prize+0.013
 contest+0.013
 trophy+0.013
Neg logit contributions
bur-0.018
rying-0.017
ppa-0.016
ind-0.016
i-0.016
Token.
Token ID13
Feature activation+1.40e+00

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
apy-0.004
Token One
Token ID1881
Feature activation+1.42e+00

Pos logit contributions
rying+0.085
ppa+0.083
ind+0.080
bur+0.078
i+0.077
Neg logit contributions
 vows-0.042
 prize-0.037
 contest-0.036
 are-0.036
 Everyone-0.036
Token day
Token ID1110
Feature activation+8.17e-02

Pos logit contributions
rying+0.086
ppa+0.084
bur+0.080
ind+0.079
ener+0.078
Neg logit contributions
 vows-0.040
 prize-0.040
 contest-0.039
 joke-0.038
 trophy-0.036
Token,
Token ID11
Feature activation+1.11e+00

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-0.003
 contest-0.002
 trophy-0.002
cakes-0.002
Token Stri
Token ID26137
Feature activation+1.39e+00

Pos logit contributions
rying+0.056
ppa+0.053
ind+0.053
bur+0.052
cker+0.050
Neg logit contributions
 vows-0.044
apy-0.042
 prize-0.041
 contest-0.041
 are-0.039
Tokenpe
Token ID431
Feature activation+4.49e+00

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
ades-0.055
 contest-0.054
Tokeny
Token ID88
Feature activation+2.36e+00

Pos logit contributions
ior+0.169
rying+0.167
 Owl+0.167
ppa+0.164
 Tooth+0.163
Neg logit contributions
 were-0.187
 are-0.182
 vows-0.182
ades-0.169
 joke-0.166
Token saw
Token ID2497
Feature activation+1.85e+00

Pos logit contributions
rying+0.141
bur+0.134
ind+0.129
ppa+0.127
ishing+0.124
Neg logit contributions
 vows-0.071
case-0.067
 contest-0.064
ves-0.062
 prize-0.061
Token his
Token ID465
Feature activation+9.09e-01

Pos logit contributions
rying+0.144
ppa+0.133
ener+0.132
ior+0.131
ind+0.131
Neg logit contributions
apy-0.024
 vows-0.021
 prize-0.021
 tea-0.021
 contest-0.020
Token friend
Token ID1545
Feature activation+7.93e-01

Pos logit contributions
rying+0.046
ppa+0.045
bur+0.044
ior+0.042
ind+0.041
Neg logit contributions
 vows-0.038
 prize-0.036
 trophy-0.033
 contest-0.033
 joke-0.031
Token,
Token ID11
Feature activation-3.81e-01

Pos logit contributions
rying+0.043
bur+0.042
ppa+0.042
ind+0.042
i+0.039
Neg logit contributions
 vows-0.028
 contest-0.025
 prize-0.025
 trophy-0.024
cakes-0.023
Tokeniver
Token ID1428
Feature activation+3.53e-01

Pos logit contributions
bur+0.074
ior+0.073
ener+0.073
ppa+0.072
gie+0.069
Neg logit contributions
ades-0.082
apy-0.079
case-0.078
 vows-0.077
 contest-0.076
Token.
Token ID13
Feature activation+1.67e+00

Pos logit contributions
bur+0.017
ppa+0.017
rying+0.017
ind+0.016
i+0.016
Neg logit contributions
 vows-0.015
 prize-0.013
 contest-0.013
 trophy-0.013
apy-0.012
Token
Token ID220
Feature activation+1.04e-01

Pos logit contributions
ppa+0.114
bur+0.114
rying+0.114
ind+0.112
i+0.107
Neg logit contributions
 Everyone-0.035
 vows-0.035
apy-0.033
cakes-0.030
 Everybody-0.029
Token
Token ID198
Feature activation+1.08e+00

Pos logit contributions
bur+0.006
rying+0.006
ppa+0.006
ind+0.006
i+0.006
Neg logit contributions
 vows-0.004
 prize-0.003
 contest-0.003
 trophy-0.003
cakes-0.003
Token
Token ID198
Feature activation+1.23e+00

Pos logit contributions
rying+0.072
bur+0.070
ppa+0.069
i+0.069
ind+0.068
Neg logit contributions
 vows-0.025
apy-0.021
 contest-0.021
 prize-0.021
ades-0.020
TokenMill
Token ID22603
Feature activation+4.48e+00

Pos logit contributions
bur+0.056
rying+0.054
ppa+0.052
i+0.052
ior+0.050
Neg logit contributions
 vows-0.054
apy-0.051
 contest-0.048
cakes-0.048
 Everyone-0.048
Tokenie
Token ID494
Feature activation+2.50e+00

Pos logit contributions
 property+0.205
 territory+0.197
 spine+0.190
rying+0.186
wood+0.185
Neg logit contributions
 were-0.139
 vows-0.129
 are-0.117
 danced-0.110
 tea-0.108
Token was
Token ID373
Feature activation+1.31e+00

Pos logit contributions
bur+0.143
rying+0.137
ind+0.132
ppa+0.130
umper+0.129
Neg logit contributions
 vows-0.081
apy-0.066
 were-0.065
 joke-0.065
case-0.065
Token too
Token ID1165
Feature activation+1.77e+00

Pos logit contributions
bur+0.067
rying+0.065
ppa+0.065
ior+0.064
ety+0.063
Neg logit contributions
 vows-0.049
apy-0.043
 contest-0.043
 prize-0.042
 laugh-0.042
Token curious
Token ID11040
Feature activation+9.25e-01

Pos logit contributions
bur+0.095
rying+0.089
ppa+0.088
ior+0.086
oscope+0.086
Neg logit contributions
apy-0.060
 vows-0.054
 great-0.054
 laugh-0.053
 lot-0.053
Token and
Token ID290
Feature activation+1.16e+00

Pos logit contributions
bur+0.049
ppa+0.049
rying+0.048
ind+0.046
cker+0.045
Neg logit contributions
 vows-0.035
 prize-0.032
 contest-0.031
 trophy-0.030
cakes-0.030
Token of
Token ID286
Feature activation+1.58e+00

Pos logit contributions
 vows+0.032
 trophy+0.027
 prize+0.027
apy+0.026
cakes+0.026
Neg logit contributions
rying-0.035
i-0.034
bur-0.034
ppa-0.034
ind-0.032
Token friendly
Token ID8030
Feature activation+4.30e-01

Pos logit contributions
bur+0.077
rying+0.075
ppa+0.075
ety+0.071
ior+0.070
Neg logit contributions
 vows-0.065
 contest-0.062
 prize-0.061
 joke-0.058
 lot-0.057
Token ducks
Token ID39694
Feature activation+3.92e-01

Pos logit contributions
bur+0.018
rying+0.017
ppa+0.017
ind+0.016
i+0.016
Neg logit contributions
 vows-0.021
 prize-0.019
 contest-0.019
 trophy-0.019
cakes-0.018
Token came
Token ID1625
Feature activation+8.05e-01

Pos logit contributions
bur+0.020
rying+0.019
ppa+0.019
ind+0.019
i+0.018
Neg logit contributions
 vows-0.016
 prize-0.014
 contest-0.014
 trophy-0.014
apy-0.013
Token to
Token ID284
Feature activation+5.54e-01

Pos logit contributions
ppa+0.038
bur+0.037
rying+0.035
ior+0.035
ind+0.034
Neg logit contributions
 vows-0.035
 prize-0.031
 contest-0.031
 trophy-0.030
apy-0.029
Token Gig
Token ID19525
Feature activation+4.48e+00

Pos logit contributions
rying+0.028
bur+0.028
ppa+0.028
ind+0.027
i+0.027
Neg logit contributions
 vows-0.022
 prize-0.019
 contest-0.019
 trophy-0.018
cakes-0.018
Tokeni
Token ID72
Feature activation+1.33e+00

Pos logit contributions
asured+0.113
oscope+0.112
 property+0.103
 axe+0.102
beh+0.095
Neg logit contributions
 vows-0.233
 tea-0.209
 they-0.206
 are-0.204
 were-0.202
Token's
Token ID338
Feature activation+1.18e+00

Pos logit contributions
bur+0.064
ppa+0.063
rying+0.062
ind+0.061
ior+0.060
Neg logit contributions
 vows-0.053
 prize-0.048
 contest-0.047
 trophy-0.047
 are-0.046
Token rescue
Token ID9992
Feature activation+7.99e-01

Pos logit contributions
ppa+0.054
bur+0.053
rying+0.052
i+0.049
umper+0.049
Neg logit contributions
 vows-0.055
 prize-0.050
 contest-0.048
 trophy-0.047
 joke-0.046
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
bur+0.041
rying+0.040
ppa+0.040
ind+0.039
ety+0.038
Neg logit contributions
 vows-0.031
 prize-0.028
 contest-0.027
 trophy-0.026
cakes-0.026
Token They
Token ID1119
Feature activation-5.38e-01

Pos logit contributions
rying+0.050
bur+0.050
ppa+0.049
ind+0.048
i+0.046
Neg logit contributions
 vows-0.044
 prize-0.038
cakes-0.037
 contest-0.037
apy-0.037
Token,
Token ID11
Feature activation+1.06e+00

Pos logit contributions
rying+0.093
bur+0.093
cker+0.091
ppa+0.090
ind+0.090
Neg logit contributions
 vows-0.046
 prize-0.039
 are-0.038
 contest-0.037
 tea-0.036
Token "
Token ID366
Feature activation+2.92e+00

Pos logit contributions
bur+0.076
rying+0.075
ind+0.075
ppa+0.074
i+0.073
Neg logit contributions
 vows-0.018
 prize-0.015
 contest-0.015
 trophy-0.013
apy-0.013
TokenWhat
Token ID2061
Feature activation-6.79e-01

Pos logit contributions
rying+0.147
ior+0.145
ishing+0.145
owing+0.144
asured+0.143
Neg logit contributions
Mine-0.085
 vows-0.079
Me-0.078
 tag-0.077
 contest-0.076
Token happened
Token ID3022
Feature activation+1.63e+00

Pos logit contributions
 vows+0.030
 prize+0.026
cakes+0.026
 contest+0.026
 trophy+0.026
Neg logit contributions
bur-0.031
ppa-0.030
i-0.030
rying-0.029
ety-0.029
Token,
Token ID11
Feature activation+8.70e-01

Pos logit contributions
bur+0.093
ppa+0.093
rying+0.089
ind+0.088
ior+0.087
Neg logit contributions
 contest-0.051
 vows-0.050
 prize-0.049
 trophy-0.048
 joke-0.045
Token Gig
Token ID19525
Feature activation+4.47e+00

Pos logit contributions
rying+0.035
bur+0.034
ppa+0.033
ind+0.032
cker+0.032
Neg logit contributions
 vows-0.044
 prize-0.041
 trophy-0.039
 contest-0.039
cakes-0.038
Tokeni
Token ID72
Feature activation+2.25e+00

Pos logit contributions
oscope+0.117
keeping+0.109
rying+0.105
umbling+0.103
 property+0.100
Neg logit contributions
 vows-0.229
 are-0.204
 they-0.196
 tea-0.195
 were-0.193
Token?
Token ID30
Feature activation+1.51e+00

Pos logit contributions
bur+0.109
rying+0.105
ind+0.103
ppa+0.103
ior+0.102
Neg logit contributions
 vows-0.085
 contest-0.084
 are-0.084
 prize-0.078
 trophy-0.078
Token Are
Token ID4231
Feature activation+1.46e+00

Pos logit contributions
bur+0.080
rying+0.079
ppa+0.076
ind+0.075
i+0.074
Neg logit contributions
 vows-0.056
apy-0.052
cakes-0.050
 contest-0.049
case-0.049
Token you
Token ID345
Feature activation+2.07e+00

Pos logit contributions
rying+0.074
bur+0.072
ind+0.071
ior+0.070
cker+0.069
Neg logit contributions
 vows-0.056
 contest-0.053
 prize-0.053
 are-0.052
 trophy-0.052
Token okay
Token ID8788
Feature activation+1.60e+00

Pos logit contributions
ior+0.099
bur+0.098
rying+0.096
ind+0.094
ppa+0.092
Neg logit contributions
 vows-0.076
 are-0.074
apy-0.074
 prize-0.073
 celebrate-0.073
Token were
Token ID547
Feature activation-1.52e+00

Pos logit contributions
 vows+0.059
 Prize+0.050
 prize+0.050
 trophy+0.049
 contest+0.047
Neg logit contributions
i-0.113
bur-0.110
my-0.109
rying-0.106
ppa-0.106
Token so
Token ID523
Feature activation-2.50e+00

Pos logit contributions
 vows+0.062
apy+0.056
 trophy+0.056
 prize+0.056
 Prize+0.056
Neg logit contributions
bur-0.070
i-0.068
ppa-0.067
ind-0.066
rying-0.066
Token colorful
Token ID20239
Feature activation-1.28e+00

Pos logit contributions
 Prize+0.096
 mat+0.096
 vows+0.096
 trophy+0.096
 prize+0.095
Neg logit contributions
ind-0.105
i-0.094
my-0.093
ppa-0.087
ety-0.087
Token and
Token ID290
Feature activation-8.66e-01

Pos logit contributions
 vows+0.068
apy+0.061
 Prize+0.060
 contest+0.060
 trophy+0.060
Neg logit contributions
i-0.045
rying-0.045
bur-0.044
ind-0.042
ppa-0.041
Token the
Token ID262
Feature activation+4.12e-01

Pos logit contributions
 vows+0.031
 prize+0.027
 contest+0.027
 trophy+0.026
ades+0.026
Neg logit contributions
bur-0.045
ppa-0.044
rying-0.044
i-0.044
ind-0.043
Token stories
Token ID3923
Feature activation-4.45e+00

Pos logit contributions
bur+0.020
rying+0.019
ppa+0.019
ind+0.018
i+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-1.37e+00

Pos logit contributions
 Prize+0.187
 vows+0.183
 coach+0.181
ades+0.179
apy+0.174
Neg logit contributions
my-0.160
i-0.150
 since-0.147
bur-0.142
 owl-0.142
Token so
Token ID523
Feature activation-2.43e+00

Pos logit contributions
 vows+0.056
apy+0.051
 contest+0.051
 Prize+0.051
 trophy+0.050
Neg logit contributions
bur-0.065
i-0.062
rying-0.061
ppa-0.061
ind-0.060
Token fun
Token ID1257
Feature activation-1.18e+00

Pos logit contributions
 vows+0.092
 Prize+0.092
 trophy+0.091
 contest+0.091
 prize+0.091
Neg logit contributions
ind-0.105
i-0.095
my-0.091
ppa-0.088
rying-0.088
Token.
Token ID13
Feature activation-1.80e-01

Pos logit contributions
 vows+0.059
apy+0.053
 trophy+0.052
 Prize+0.052
 contest+0.052
Neg logit contributions
rying-0.046
bur-0.044
i-0.043
ind-0.042
ppa-0.041
Token She
Token ID1375
Feature activation-9.35e-01

Pos logit contributions
 vows+0.006
 prize+0.006
 trophy+0.005
 contest+0.005
apy+0.005
Neg logit contributions
bur-0.010
rying-0.010
ppa-0.010
i-0.009
ind-0.009
Token
Token ID198
Feature activation-2.99e-01

Pos logit contributions
 vows+0.010
 prize+0.009
 contest+0.009
 trophy+0.009
apy+0.009
Neg logit contributions
bur-0.009
rying-0.009
ppa-0.009
i-0.009
ind-0.009
Token
Token ID198
Feature activation-8.57e-01

Pos logit contributions
 vows+0.012
 prize+0.010
 trophy+0.010
 contest+0.010
cakes+0.009
Neg logit contributions
bur-0.016
rying-0.015
ppa-0.015
ind-0.015
i-0.015
TokenThe
Token ID464
Feature activation-1.29e+00

Pos logit contributions
 vows+0.042
 prize+0.037
 trophy+0.036
 contest+0.036
 tea+0.035
Neg logit contributions
bur-0.037
ind-0.035
rying-0.035
my-0.034
ppa-0.034
Token kids
Token ID3988
Feature activation-1.65e+00

Pos logit contributions
apy+0.075
 vows+0.070
ades+0.065
�+0.064
Mine+0.064
Neg logit contributions
bur-0.038
ppa-0.038
ind-0.037
 owl-0.037
my-0.037
Token played
Token ID2826
Feature activation-3.42e+00

Pos logit contributions
 vows+0.072
 prize+0.065
apy+0.065
ades+0.064
 trophy+0.064
Neg logit contributions
i-0.075
rying-0.074
bur-0.072
ppa-0.071
my-0.071
Token a
Token ID257
Feature activation-4.41e+00

Pos logit contributions
 vows+0.174
apy+0.161
cakes+0.153
Mine+0.153
�+0.150
Neg logit contributions
rying-0.109
 asking-0.101
ishing-0.099
 forth-0.097
ting-0.094
Token lot
Token ID1256
Feature activation-1.13e+00

Pos logit contributions
apy+0.159
 vows+0.149
cakes+0.148
�+0.146
 Both+0.141
Neg logit contributions
ind-0.208
nie-0.167
rying-0.165
ppa-0.163
ich-0.159
Token of
Token ID286
Feature activation-1.97e+00

Pos logit contributions
 vows+0.062
apy+0.055
Mine+0.053
 trophy+0.052
 prize+0.051
Neg logit contributions
rying-0.042
bur-0.041
ppa-0.039
i-0.039
ind-0.039
Token fun
Token ID1257
Feature activation-2.10e+00

Pos logit contributions
 vows+0.067
apy+0.058
cakes+0.054
�+0.053
 coach+0.049
Neg logit contributions
rying-0.102
ind-0.101
ishing-0.097
my-0.097
ior-0.096
Token and
Token ID290
Feature activation-5.42e-01

Pos logit contributions
 vows+0.091
Mine+0.078
cakes+0.072
 trophy+0.071
apy+0.071
Neg logit contributions
rying-0.094
ind-0.088
i-0.087
ishing-0.087
ise-0.086
Token interesting
Token ID3499
Feature activation-1.84e+00

Pos logit contributions
 vows+0.021
 trophy+0.019
 prize+0.019
ades+0.019
 contest+0.018
Neg logit contributions
bur-0.026
rying-0.026
i-0.026
ppa-0.025
ind-0.025
Token a
Token ID257
Feature activation-1.74e+00

Pos logit contributions
 vows+0.067
 Prize+0.062
 contest+0.061
 prize+0.060
 trophy+0.059
Neg logit contributions
bur-0.074
i-0.073
ppa-0.072
ind-0.070
rying-0.068
Token funny
Token ID8258
Feature activation-1.56e+00

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-0.082
Token face
Token ID1986
Feature activation-8.64e-01

Pos logit contributions
 vows+0.061
 contest+0.056
 Prize+0.055
cakes+0.054
uits+0.053
Neg logit contributions
i-0.071
bur-0.070
ind-0.070
cker-0.070
ppa-0.069
Token.
Token ID13
Feature activation-1.87e+00

Pos logit contributions
 vows+0.042
 prize+0.038
 contest+0.037
 Prize+0.037
 trophy+0.037
Neg logit contributions
rying-0.035
bur-0.035
i-0.035
ppa-0.035
ind-0.033
Token The
Token ID383
Feature activation-6.59e-01

Pos logit contributions
 trophy+0.084
 prize+0.081
 contest+0.081
ades+0.079
 vows+0.079
Neg logit contributions
ior-0.072
ety-0.063
gie-0.062
i-0.062
ind-0.061
Token sandwiches
Token ID29777
Feature activation-4.32e+00

Pos logit contributions
 vows+0.022
apy+0.019
 contest+0.019
 Prize+0.018
 prize+0.018
Neg logit contributions
bur-0.036
ppa-0.035
i-0.034
rying-0.034
ind-0.034
Token are
Token ID389
Feature activation-9.06e-01

Pos logit contributions
 Prize+0.156
igsaw+0.151
 vows+0.150
ival+0.148
ades+0.135
Neg logit contributions
 forth-0.195
i-0.192
my-0.186
bur-0.182
 bruised-0.173
Token spicy
Token ID26880
Feature activation-4.51e-01

Pos logit contributions
 vows+0.037
 contest+0.033
 Prize+0.033
 prize+0.032
 trophy+0.031
Neg logit contributions
bur-0.045
ppa-0.043
i-0.043
rying-0.043
ind-0.042
Token!
Token ID0
Feature activation-2.02e+00

Pos logit contributions
 vows+0.022
 contest+0.019
 prize+0.019
 trophy+0.019
apy+0.019
Neg logit contributions
bur-0.019
rying-0.019
i-0.018
ppa-0.018
ind-0.017
Token They
Token ID1119
Feature activation-2.12e+00

Pos logit contributions
 vows+0.085
 prize+0.084
 trophy+0.084
 contest+0.083
ades+0.076
Neg logit contributions
ior-0.084
ppa-0.074
ety-0.074
bur-0.074
ind-0.072
Token have
Token ID423
Feature activation-5.60e-01

Pos logit contributions
 vows+0.074
cakes+0.072
ades+0.072
 contest+0.068
 Prize+0.065
Neg logit contributions
i-0.111
bur-0.108
cker-0.105
ppa-0.103
rying-0.102
Token
Token ID198
Feature activation-1.03e+00

Pos logit contributions
 vows+0.033
 prize+0.029
 trophy+0.028
 contest+0.027
cakes+0.026
Neg logit contributions
bur-0.036
ppa-0.035
rying-0.034
ind-0.033
ety-0.033
TokenDa
Token ID26531
Feature activation+6.21e-01

Pos logit contributions
 vows+0.053
 prize+0.047
 trophy+0.046
 contest+0.044
cakes+0.043
Neg logit contributions
ppa-0.042
ind-0.040
bur-0.040
rying-0.040
ety-0.038
Tokenisy
Token ID13560
Feature activation-1.30e+00

Pos logit contributions
bur+0.028
rying+0.027
ppa+0.026
ind+0.025
i+0.025
Neg logit contributions
 vows-0.029
 prize-0.026
 contest-0.025
 trophy-0.025
cakes-0.025
Token started
Token ID2067
Feature activation-1.20e+00

Pos logit contributions
 vows+0.057
 prize+0.054
 trophy+0.053
cakes+0.053
 contest+0.053
Neg logit contributions
i-0.057
ppa-0.055
rying-0.055
bur-0.054
ind-0.053
Token making
Token ID1642
Feature activation-2.09e+00

Pos logit contributions
 vows+0.064
cakes+0.060
 trophy+0.059
 prize+0.059
ades+0.059
Neg logit contributions
rying-0.041
i-0.040
ind-0.039
bur-0.039
ppa-0.037
Token videos
Token ID5861
Feature activation-4.30e+00

Pos logit contributions
 vows+0.091
 trophy+0.081
 Prize+0.080
cakes+0.080
case+0.079
Neg logit contributions
i-0.092
ind-0.088
rying-0.087
bur-0.085
ppa-0.085
Token and
Token ID290
Feature activation-5.19e-01

Pos logit contributions
 vows+0.268
Mine+0.241
apy+0.239
 Prize+0.230
ades+0.226
Neg logit contributions
my-0.114
 owl-0.098
 since-0.093
rying-0.093
ting-0.090
Token put
Token ID1234
Feature activation-1.22e+00

Pos logit contributions
 vows+0.022
 prize+0.020
 trophy+0.019
 contest+0.019
ades+0.019
Neg logit contributions
rying-0.024
bur-0.024
ppa-0.023
i-0.023
ind-0.023
Token them
Token ID606
Feature activation-2.39e+00

Pos logit contributions
 vows+0.050
apy+0.044
 trophy+0.043
 Prize+0.043
 prize+0.043
Neg logit contributions
bur-0.059
i-0.056
ppa-0.056
rying-0.056
ind-0.055
Token up
Token ID510
Feature activation-3.85e-01

Pos logit contributions
 vows+0.123
 Prize+0.113
apy+0.112
Mine+0.111
cakes+0.111
Neg logit contributions
rying-0.087
bur-0.085
i-0.080
ppa-0.079
ind-0.078
Token on
Token ID319
Feature activation-1.21e+00

Pos logit contributions
 vows+0.018
 prize+0.016
 trophy+0.016
cakes+0.016
 contest+0.016
Neg logit contributions
bur-0.017
rying-0.017
ppa-0.016
i-0.016
ind-0.016
Token characters
Token ID3435
Feature activation-2.58e+00

Pos logit contributions
 vows+0.032
apy+0.031
ades+0.024
cakes+0.024
uits+0.023
Neg logit contributions
bur-0.063
ind-0.062
rying-0.061
my-0.061
gie-0.059
Token and
Token ID290
Feature activation-1.66e-01

Pos logit contributions
 vows+0.138
ades+0.125
apy+0.125
 Prize+0.121
Mine+0.120
Neg logit contributions
rying-0.092
i-0.091
bur-0.085
ppa-0.081
my-0.080
Token watching
Token ID4964
Feature activation-2.29e+00

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-0.008
ppa-0.008
i-0.007
ind-0.007
Token the
Token ID262
Feature activation-1.74e+00

Pos logit contributions
 vows+0.095
apy+0.087
 Prize+0.085
 prize+0.084
case+0.084
Neg logit contributions
i-0.102
ind-0.101
rying-0.097
my-0.096
bur-0.095
Token funny
Token ID8258
Feature activation-2.30e+00

Pos logit contributions
apy+0.052
 vows+0.052
uits+0.044
ades+0.041
ves+0.039
Neg logit contributions
ind-0.098
my-0.095
bur-0.093
rying-0.090
 owl-0.090
Token video
Token ID2008
Feature activation-4.29e+00

Pos logit contributions
apy+0.075
 vows+0.072
uits+0.071
case+0.065
 Prize+0.064
Neg logit contributions
ind-0.116
my-0.111
i-0.111
ping-0.110
gie-0.109
Token.
Token ID13
Feature activation-1.03e+00

Pos logit contributions
 vows+0.232
apy+0.215
Mine+0.209
 Prize+0.208
 disco+0.204
Neg logit contributions
my-0.124
rying-0.122
i-0.119
 forth-0.112
ting-0.108
Token She
Token ID1375
Feature activation-7.40e-01

Pos logit contributions
 vows+0.047
 trophy+0.044
 prize+0.043
ades+0.042
 contest+0.041
Neg logit contributions
bur-0.044
my-0.043
ety-0.043
i-0.043
rying-0.042
Token went
Token ID1816
Feature activation-6.00e-01

Pos logit contributions
 vows+0.034
 prize+0.031
 contest+0.031
cakes+0.030
apy+0.030
Neg logit contributions
bur-0.032
i-0.031
ppa-0.031
rying-0.031
ind-0.029
Token to
Token ID284
Feature activation-1.05e+00

Pos logit contributions
 vows+0.033
apy+0.030
 trophy+0.029
 prize+0.029
 contest+0.029
Neg logit contributions
rying-0.022
bur-0.021
ppa-0.020
ind-0.020
i-0.020
Token the
Token ID262
Feature activation-1.27e+00

Pos logit contributions
 vows+0.044
ades+0.040
cakes+0.040
apy+0.039
ves+0.035
Neg logit contributions
bur-0.050
rying-0.049
i-0.047
ind-0.047
my-0.047
Token She
Token ID1375
Feature activation-9.82e-01

Pos logit contributions
 vows+0.006
 prize+0.005
 contest+0.005
 trophy+0.005
apy+0.005
Neg logit contributions
bur-0.008
rying-0.008
ppa-0.008
i-0.008
ety-0.008
Token played
Token ID2826
Feature activation-3.06e+00

Pos logit contributions
 vows+0.048
 prize+0.046
 contest+0.045
 trophy+0.045
apy+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-2.95e+00

Pos logit contributions
 vows+0.179
apy+0.154
Mine+0.148
cakes+0.147
 Prize+0.146
Neg logit contributions
 owl-0.089
 asking-0.087
rying-0.085
 forth-0.083
ishing-0.082
Token and
Token ID290
Feature activation-3.96e-01

Pos logit contributions
 vows+0.183
apy+0.173
Mine+0.161
ades+0.161
 Sorry+0.159
Neg logit contributions
my-0.078
rying-0.069
 owl-0.068
 since-0.067
bur-0.065
Token watched
Token ID7342
Feature activation-1.99e+00

Pos logit contributions
 vows+0.016
 prize+0.014
 trophy+0.014
ades+0.014
 contest+0.014
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.019
i-0.018
ind-0.018
Token videos
Token ID5861
Feature activation-4.21e+00

Pos logit contributions
 vows+0.095
 Prize+0.088
case+0.083
ades+0.082
�+0.081
Neg logit contributions
ind-0.073
rying-0.072
 asking-0.071
i-0.071
ting-0.070
Token on
Token ID319
Feature activation-1.33e+00

Pos logit contributions
 vows+0.257
apy+0.241
Mine+0.233
ades+0.222
 Prize+0.220
Neg logit contributions
my-0.105
ting-0.101
 since-0.088
 forth-0.085
 owl-0.084
Token the
Token ID262
Feature activation-6.76e-01

Pos logit contributions
 vows+0.065
apy+0.058
ades+0.057
 Prize+0.056
cakes+0.056
Neg logit contributions
ind-0.053
bur-0.052
i-0.051
ppa-0.049
my-0.048
Token computer
Token ID3644
Feature activation-2.44e+00

Pos logit contributions
 vows+0.026
apy+0.023
 prize+0.022
 contest+0.021
 Prize+0.021
Neg logit contributions
ind-0.034
bur-0.034
rying-0.034
ppa-0.033
ior-0.032
Token all
Token ID477
Feature activation+2.91e-01

Pos logit contributions
 vows+0.125
apy+0.115
ades+0.109
 prize+0.106
 Prize+0.105
Neg logit contributions
my-0.088
rying-0.088
i-0.083
bur-0.083
 forth-0.079
Token day
Token ID1110
Feature activation-9.88e-01

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
ind+0.013
i+0.013
Neg logit contributions
 vows-0.013
 prize-0.011
 contest-0.011
 trophy-0.011
cakes-0.011
Token cheered
Token ID34767
Feature activation-1.62e+00

Pos logit contributions
 vows+0.059
ades+0.056
 prize+0.054
 contest+0.053
cakes+0.053
Neg logit contributions
i-0.061
bur-0.057
ppa-0.057
 forth-0.057
rying-0.057
Token very
Token ID845
Feature activation-2.53e+00

Pos logit contributions
 vows+0.096
apy+0.091
cakes+0.090
case+0.090
 Prize+0.089
Neg logit contributions
rying-0.049
i-0.047
ind-0.045
my-0.041
 forth-0.041
Token loudly
Token ID23112
Feature activation-1.49e+00

Pos logit contributions
cakes+0.099
�+0.095
 vows+0.094
uits+0.092
Mine+0.091
Neg logit contributions
ind-0.118
i-0.110
rying-0.110
ppa-0.103
 aware-0.096
Token because
Token ID780
Feature activation-1.27e+00

Pos logit contributions
 vows+0.077
apy+0.073
 trophy+0.071
ades+0.070
 prize+0.070
Neg logit contributions
rying-0.055
i-0.051
ind-0.049
bur-0.048
gie-0.047
Token the
Token ID262
Feature activation-2.16e+00

Pos logit contributions
 vows+0.038
ades+0.029
 prize+0.027
 Prize+0.027
cakes+0.027
Neg logit contributions
bur-0.073
rying-0.071
my-0.071
ind-0.070
 owl-0.069
Token dance
Token ID9280
Feature activation-4.21e+00

Pos logit contributions
 vows+0.080
apy+0.079
ades+0.074
cakes+0.073
uits+0.067
Neg logit contributions
 owl-0.098
rying-0.096
my-0.094
 forth-0.093
ind-0.092
Token was
Token ID373
Feature activation-1.53e+00

Pos logit contributions
 vows+0.185
apy+0.180
Mine+0.174
ades+0.169
uits+0.163
Neg logit contributions
rying-0.143
i-0.143
ting-0.133
my-0.132
row-0.131
Token so
Token ID523
Feature activation-2.47e+00

Pos logit contributions
 vows+0.076
cakes+0.067
Mine+0.066
apy+0.066
 prize+0.066
Neg logit contributions
bur-0.063
rying-0.062
my-0.057
ppa-0.057
i-0.056
Token good
Token ID922
Feature activation-9.70e-01

Pos logit contributions
 vows+0.110
�+0.108
 tray+0.105
 mat+0.100
 prize+0.099
Neg logit contributions
ind-0.095
rying-0.087
ety-0.086
 aware-0.083
my-0.083
Token.
Token ID13
Feature activation-1.35e+00

Pos logit contributions
 vows+0.051
apy+0.046
Mine+0.044
 prize+0.044
 Prize+0.044
Neg logit contributions
rying-0.038
i-0.036
bur-0.036
ind-0.034
ppa-0.034
Token Everyone
Token ID11075
Feature activation-1.82e+00

Pos logit contributions
 vows+0.053
 trophy+0.047
 prize+0.046
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 They
Token ID1119
Feature activation-1.36e+00

Pos logit contributions
 vows+0.037
 prize+0.032
 trophy+0.032
 contest+0.030
ades+0.030
Neg logit contributions
bur-0.047
ety-0.046
ior-0.045
rying-0.045
gie-0.044
Token shared
Token ID4888
Feature activation-1.84e+00

Pos logit contributions
 vows+0.065
apy+0.062
 prize+0.062
ades+0.061
 trophy+0.060
Neg logit contributions
i-0.054
bur-0.054
ppa-0.054
rying-0.054
my-0.050
Token food
Token ID2057
Feature activation-1.78e+00

Pos logit contributions
�+0.075
 vows+0.075
 Prize+0.074
apy+0.073
 contest+0.072
Neg logit contributions
bur-0.078
my-0.077
i-0.074
ppa-0.073
ind-0.072
Token and
Token ID290
Feature activation-2.03e-01

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-0.048
Token laughed
Token ID13818
Feature activation-2.47e+00

Pos logit contributions
 vows+0.007
 prize+0.006
 contest+0.006
 trophy+0.006
apy+0.006
Neg logit contributions
bur-0.011
rying-0.011
ppa-0.011
i-0.010
ind-0.010
Token a
Token ID257
Feature activation-4.21e+00

Pos logit contributions
 vows+0.140
 Prize+0.135
Mine+0.135
 contest+0.135
 prize+0.132
Neg logit contributions
rying-0.066
i-0.065
ind-0.060
ping-0.060
 since-0.059
Token lot
Token ID1256
Feature activation-9.81e-01

Pos logit contributions
cakes+0.135
 vows+0.133
apy+0.127
hips+0.126
 progressed+0.126
Neg logit contributions
ind-0.163
my-0.155
 owl-0.154
bur-0.150
ppa-0.149
Token.
Token ID13
Feature activation-8.19e-01

Pos logit contributions
 vows+0.051
apy+0.046
Mine+0.046
 contest+0.045
 Prize+0.044
Neg logit contributions
rying-0.038
ppa-0.036
i-0.035
bur-0.035
ind-0.035
Token
Token ID198
Feature activation-5.52e-01

Pos logit contributions
 vows+0.034
 prize+0.031
 trophy+0.031
 contest+0.030
ades+0.029
Neg logit contributions
bur-0.039
ior-0.037
rying-0.037
ety-0.036
my-0.036
Token
Token ID198
Feature activation-1.17e+00

Pos logit contributions
 vows+0.023
 prize+0.020
 trophy+0.019
 contest+0.019
cakes+0.019
Neg logit contributions
bur-0.028
ppa-0.027
rying-0.027
ind-0.026
i-0.026
TokenThe
Token ID464
Feature activation-7.25e-01

Pos logit contributions
 vows+0.065
 prize+0.059
 trophy+0.058
cakes+0.057
 contest+0.056
Neg logit contributions
ind-0.041
bur-0.040
ppa-0.039
rying-0.039
cker-0.036
Token the
Token ID262
Feature activation-1.41e-01

Pos logit contributions
 vows+0.005
 prize+0.005
 contest+0.005
 trophy+0.005
cakes+0.005
Neg logit contributions
bur-0.007
rying-0.007
ppa-0.007
i-0.007
ind-0.007
Token pictures
Token ID5986
Feature activation-2.24e+00

Pos logit contributions
 vows+0.005
apy+0.004
 prize+0.004
 contest+0.004
 trophy+0.004
Neg logit contributions
bur-0.008
rying-0.008
ppa-0.008
ind-0.008
i-0.007
Token and
Token ID290
Feature activation+2.49e-01

Pos logit contributions
 vows+0.131
 Prize+0.118
Mine+0.116
apy+0.115
ades+0.114
Neg logit contributions
my-0.065
i-0.063
rying-0.061
bur-0.059
 owl-0.059
Token said
Token ID531
Feature activation-2.67e+00

Pos logit contributions
bur+0.011
rying+0.011
ppa+0.011
ind+0.011
i+0.011
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.010
 trophy-0.010
cakes-0.010
Token the
Token ID262
Feature activation-6.89e-01

Pos logit contributions
Mine+0.133
�+0.132
 vows+0.128
case+0.126
 blast+0.126
Neg logit contributions
i-0.082
 owl-0.081
 Owl-0.075
ppa-0.073
 asking-0.070
Token names
Token ID3891
Feature activation-4.18e+00

Pos logit contributions
 vows+0.025
apy+0.024
ades+0.022
cakes+0.022
 trophy+0.021
Neg logit contributions
bur-0.035
ppa-0.034
rying-0.034
ind-0.034
i-0.033
Token of
Token ID286
Feature activation-1.08e+00

Pos logit contributions
�+0.208
 Prize+0.207
 vows+0.206
apy+0.200
Mine+0.199
Neg logit contributions
my-0.133
i-0.121
 owl-0.111
bur-0.106
ie-0.104
Token the
Token ID262
Feature activation-5.11e-01

Pos logit contributions
 vows+0.047
apy+0.043
cakes+0.043
ades+0.042
case+0.041
Neg logit contributions
bur-0.049
i-0.047
ind-0.047
ppa-0.046
rying-0.045
Token things
Token ID1243
Feature activation-3.16e+00

Pos logit contributions
 vows+0.019
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+3.96e-01

Pos logit contributions
 vows+0.155
 Prize+0.145
apy+0.140
 blast+0.138
Mine+0.137
Neg logit contributions
i-0.120
my-0.112
rying-0.109
bur-0.107
 owl-0.105
Token saw
Token ID2497
Feature activation+8.57e-02

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.019
ind+0.018
i+0.018
Neg logit contributions
 vows-0.017
 prize-0.015
 contest-0.015
 trophy-0.015
cakes-0.014
Token funny
Token ID8258
Feature activation-2.11e+00

Pos logit contributions
 vows+0.081
apy+0.080
ades+0.067
ves+0.066
 Prize+0.064
Neg logit contributions
my-0.102
bur-0.096
 owl-0.093
ind-0.089
 axe-0.089
Token animals
Token ID4695
Feature activation-1.87e+00

Pos logit contributions
 vows+0.077
apy+0.070
 Prize+0.067
 contest+0.067
 prize+0.067
Neg logit contributions
my-0.105
ind-0.099
ior-0.098
ping-0.098
oscope-0.097
Token and
Token ID290
Feature activation-5.38e-01

Pos logit contributions
 vows+0.108
Mine+0.099
apy+0.097
 Prize+0.095
 prize+0.095
Neg logit contributions
i-0.063
rying-0.060
bur-0.060
my-0.057
ppa-0.055
Token the
Token ID262
Feature activation-9.57e-01

Pos logit contributions
 vows+0.021
 prize+0.020
 contest+0.019
 trophy+0.019
ades+0.018
Neg logit contributions
bur-0.026
ppa-0.026
i-0.026
rying-0.025
ety-0.025
Token silly
Token ID14397
Feature activation-1.17e+00

Pos logit contributions
 vows+0.043
apy+0.039
 prize+0.037
cakes+0.037
ades+0.036
Neg logit contributions
bur-0.042
ind-0.040
rying-0.040
my-0.039
gie-0.039
Token jokes
Token ID14532
Feature activation-4.18e+00

Pos logit contributions
 vows+0.052
apy+0.049
 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-9.28e-01

Pos logit contributions
 vows+0.221
igsaw+0.216
 Prize+0.215
Mine+0.211
ades+0.208
Neg logit contributions
i-0.113
ting-0.107
my-0.103
 owl-0.097
ping-0.097
Token But
Token ID887
Feature activation+6.98e-01

Pos logit contributions
 vows+0.040
 prize+0.035
 trophy+0.035
 contest+0.034
apy+0.033
Neg logit contributions
bur-0.044
ety-0.043
my-0.043
ior-0.042
rying-0.040
Token sometimes
Token ID3360
Feature activation-1.09e+00

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-1.22e+00

Pos logit contributions
 vows+0.035
cakes+0.030
ades+0.029
 prize+0.029
 trophy+0.028
Neg logit contributions
i-0.062
bur-0.061
ppa-0.059
rying-0.059
my-0.058
Token wanted
Token ID2227
Feature activation-1.26e+00

Pos logit contributions
 vows+0.056
 prize+0.052
ades+0.050
cakes+0.050
apy+0.049
Neg logit contributions
bur-0.054
i-0.053
ppa-0.051
ety-0.051
rying-0.050
Token taught
Token ID7817
Feature activation+5.28e-01

Pos logit contributions
 vows+0.022
 prize+0.020
 contest+0.019
cakes+0.019
 trophy+0.019
Neg logit contributions
bur-0.023
rying-0.022
ppa-0.022
i-0.022
ind-0.022
Token her
Token ID607
Feature activation-1.54e+00

Pos logit contributions
rying+0.029
bur+0.029
ppa+0.029
ind+0.028
cker+0.027
Neg logit contributions
 vows-0.019
 prize-0.017
 contest-0.016
 trophy-0.016
cakes-0.015
Token friends
Token ID2460
Feature activation-2.26e+00

Pos logit contributions
 vows+0.077
 Prize+0.070
 contest+0.069
Mine+0.068
 prize+0.066
Neg logit contributions
i-0.055
my-0.054
 owl-0.053
ppa-0.053
 axe-0.052
Token and
Token ID290
Feature activation-3.77e-01

Pos logit contributions
 vows+0.122
 Prize+0.107
 contest+0.106
 prize+0.106
apy+0.106
Neg logit contributions
my-0.080
i-0.078
rying-0.078
bur-0.073
ind-0.071
Token her
Token ID607
Feature activation-1.67e+00

Pos logit contributions
 vows+0.014
 prize+0.013
 contest+0.012
 trophy+0.012
cakes+0.012
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.019
i-0.019
ind-0.018
Token sisters
Token ID15153
Feature activation-4.18e+00

Pos logit contributions
 vows+0.088
 Prize+0.079
Mine+0.079
apy+0.078
cakes+0.078
Neg logit contributions
 owl-0.053
 axe-0.052
rying-0.051
my-0.050
i-0.050
Token how
Token ID703
Feature activation-9.81e-01

Pos logit contributions
 vows+0.199
 Prize+0.181
apy+0.174
 disco+0.173
 Bang+0.173
Neg logit contributions
my-0.155
 aware-0.153
rying-0.146
i-0.134
 asking-0.133
Token to
Token ID284
Feature activation-1.24e-01

Pos logit contributions
 vows+0.053
 prize+0.047
 trophy+0.045
 Prize+0.045
 contest+0.045
Neg logit contributions
rying-0.038
i-0.034
ppa-0.034
ety-0.034
ind-0.033
Token build
Token ID1382
Feature activation-2.00e+00

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-0.006
i-0.006
ind-0.006
Token them
Token ID606
Feature activation-2.24e+00

Pos logit contributions
 vows+0.098
 Prize+0.080
cakes+0.079
 trophy+0.078
apy+0.077
Neg logit contributions
rying-0.085
bur-0.081
my-0.080
i-0.080
ishing-0.077
Token too
Token ID1165
Feature activation-9.49e-01

Pos logit contributions
 vows+0.117
 Prize+0.094
Mine+0.094
apy+0.092
cakes+0.091
Neg logit contributions
rying-0.099
my-0.085
 forth-0.085
bur-0.083
ishing-0.082
Token diamond
Token ID15291
Feature activation-1.57e+00

Pos logit contributions
 vows+0.086
cakes+0.083
ades+0.076
apy+0.073
ves+0.070
Neg logit contributions
 owl-0.104
bur-0.099
cker-0.099
 axe-0.098
my-0.098
Token.
Token ID13
Feature activation-6.43e-01

Pos logit contributions
 vows+0.077
apy+0.071
Mine+0.070
cakes+0.070
ades+0.069
Neg logit contributions
i-0.061
rying-0.059
bur-0.059
cker-0.058
gie-0.056
Token They
Token ID1119
Feature activation-2.06e+00

Pos logit contributions
 vows+0.023
 trophy+0.021
 prize+0.020
 contest+0.020
cakes+0.018
Neg logit contributions
bur-0.035
ety-0.034
ppa-0.034
rying-0.034
i-0.033
Token said
Token ID531
Feature activation-3.01e+00

Pos logit contributions
 vows+0.085
cakes+0.082
apy+0.080
ades+0.079
 prize+0.079
Neg logit contributions
i-0.096
bur-0.094
my-0.093
ppa-0.089
ety-0.088
Token the
Token ID262
Feature activation-9.79e-01

Pos logit contributions
�+0.165
case+0.154
cakes+0.149
Mine+0.148
books+0.146
Neg logit contributions
i-0.082
 owl-0.080
 Owl-0.072
 asking-0.070
ener-0.067
Token names
Token ID3891
Feature activation-4.17e+00

Pos logit contributions
 vows+0.037
apy+0.034
cakes+0.034
ades+0.031
uits+0.029
Neg logit contributions
bur-0.048
rying-0.047
 owl-0.046
my-0.046
cker-0.046
Token of
Token ID286
Feature activation-1.26e+00

Pos logit contributions
 vows+0.207
�+0.204
 Prize+0.196
apy+0.191
Mine+0.191
Neg logit contributions
my-0.132
i-0.121
 owl-0.112
ie-0.107
ener-0.106
Token the
Token ID262
Feature activation-9.02e-01

Pos logit contributions
 vows+0.056
cakes+0.052
case+0.051
apy+0.050
 prize+0.048
Neg logit contributions
bur-0.054
i-0.054
ind-0.053
rying-0.051
ppa-0.050
Token shapes
Token ID15268
Feature activation-4.22e+00

Pos logit contributions
 vows+0.034
apy+0.031
cakes+0.030
ades+0.028
uits+0.027
Neg logit contributions
bur-0.044
rying-0.044
my-0.043
ind-0.043
 owl-0.043
Token and
Token ID290
Feature activation-3.81e-01

Pos logit contributions
 vows+0.226
Mine+0.220
Goal+0.218
�+0.218
apy+0.218
Neg logit contributions
i-0.126
my-0.117
rying-0.106
 owl-0.102
cker-0.101
Token looked
Token ID3114
Feature activation-1.72e+00

Pos logit contributions
 vows+0.014
 prize+0.012
 contest+0.012
cakes+0.012
 trophy+0.012
Neg logit contributions
bur-0.020
rying-0.020
ppa-0.019
i-0.019
ind-0.018
Token and
Token ID290
Feature activation-3.60e-01

Pos logit contributions
 vows+0.037
apy+0.033
 prize+0.033
cakes+0.032
 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-1.13e+00

Pos logit contributions
 vows+0.013
 contest+0.012
cakes+0.012
 prize+0.011
 trophy+0.011
Neg logit contributions
bur-0.019
ppa-0.019
rying-0.018
i-0.018
ind-0.018
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
 vows+0.059
apy+0.053
cakes+0.053
 Prize+0.051
 prize+0.051
Neg logit contributions
bur-0.043
rying-0.042
i-0.041
ppa-0.041
cker-0.039
Token They
Token ID1119
Feature activation-8.06e-01

Pos logit contributions
 vows+0.044
apy+0.038
 prize+0.038
 trophy+0.038
 contest+0.036
Neg logit contributions
bur-0.060
ety-0.060
ior-0.059
my-0.058
rying-0.058
Token made
Token ID925
Feature activation-1.59e+00

Pos logit contributions
 vows+0.039
cakes+0.036
 prize+0.035
apy+0.034
ades+0.034
Neg logit contributions
bur-0.035
ppa-0.034
i-0.034
ety-0.033
rying-0.032
Token them
Token ID606
Feature activation-4.17e+00

Pos logit contributions
 vows+0.062
�+0.057
cakes+0.057
 contest+0.055
apy+0.054
Neg logit contributions
ind-0.076
rying-0.074
bur-0.073
i-0.073
ppa-0.072
Token from
Token ID422
Feature activation+6.33e-01

Pos logit contributions
 vows+0.183
�+0.180
cakes+0.178
books+0.166
apy+0.164
Neg logit contributions
my-0.176
 forth-0.164
rying-0.164
ety-0.163
i-0.160
Token sticks
Token ID16461
Feature activation-6.02e-01

Pos logit contributions
bur+0.036
rying+0.035
ppa+0.035
i+0.034
ind+0.033
Neg logit contributions
 vows-0.022
 prize-0.019
 contest-0.019
 trophy-0.019
 Prize-0.017
Token and
Token ID290
Feature activation+3.70e-01

Pos logit contributions
 vows+0.033
cakes+0.029
 prize+0.029
apy+0.029
 contest+0.029
Neg logit contributions
bur-0.022
rying-0.022
ppa-0.020
i-0.020
ind-0.020
Token strings
Token ID13042
Feature activation-1.43e+00

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.019
ind+0.018
i+0.018
Neg logit contributions
 vows-0.015
 prize-0.013
 contest-0.013
 trophy-0.013
apy-0.012
Token and
Token ID290
Feature activation+1.64e-01

Pos logit contributions
 vows+0.077
cakes+0.069
apy+0.068
 Prize+0.068
 prize+0.067
Neg logit contributions
rying-0.052
bur-0.051
i-0.049
ppa-0.048
cker-0.047
Token fan
Token ID4336
Feature activation-6.68e-01

Pos logit contributions
 vows+0.072
 Prize+0.057
cakes+0.057
apy+0.056
uits+0.055
Neg logit contributions
bur-0.082
my-0.076
 axe-0.075
ind-0.074
 owl-0.074
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
 vows+0.032
apy+0.027
 prize+0.027
 trophy+0.027
cakes+0.027
Neg logit contributions
rying-0.029
bur-0.029
i-0.028
ppa-0.027
ind-0.027
Token They
Token ID1119
Feature activation-2.46e+00

Pos logit contributions
 vows+0.056
 trophy+0.049
 prize+0.047
 contest+0.046
 festival+0.045
Neg logit contributions
gie-0.067
bur-0.064
my-0.063
ety-0.063
ior-0.063
Token pretend
Token ID16614
Feature activation-2.14e+00

Pos logit contributions
cakes+0.109
 vows+0.107
ades+0.102
apy+0.093
ival+0.088
Neg logit contributions
my-0.116
bur-0.114
 forth-0.110
i-0.110
ety-0.104
Token the
Token ID262
Feature activation-1.77e+00

Pos logit contributions
 vows+0.107
 Prize+0.098
�+0.097
Mine+0.095
 prize+0.092
Neg logit contributions
bur-0.070
rying-0.069
 owl-0.069
 forth-0.068
i-0.068
Token shapes
Token ID15268
Feature activation-4.11e+00

Pos logit contributions
 vows+0.070
apy+0.061
cakes+0.059
 Prize+0.058
uits+0.058
Neg logit contributions
bur-0.086
my-0.079
 owl-0.078
 axe-0.077
 forth-0.075
Token are
Token ID389
Feature activation-4.68e-01

Pos logit contributions
 vows+0.197
�+0.188
 Prize+0.186
ival+0.184
cakes+0.183
Neg logit contributions
i-0.142
my-0.136
rying-0.136
cker-0.135
 forth-0.131
Token flying
Token ID7348
Feature activation-1.14e+00

Pos logit contributions
 vows+0.023
 prize+0.020
cakes+0.020
 trophy+0.020
 contest+0.020
Neg logit contributions
bur-0.020
rying-0.020
ppa-0.019
i-0.018
ind-0.018
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
 vows+0.064
cakes+0.057
apy+0.057
 trophy+0.054
 prize+0.054
Neg logit contributions
rying-0.040
bur-0.039
i-0.037
ind-0.037
ety-0.037
Token They
Token ID1119
Feature activation-2.75e+00

Pos logit contributions
 vows+0.052
 trophy+0.047
 prize+0.044
 contest+0.042
 festival+0.042
Neg logit contributions
gie-0.066
ety-0.064
bur-0.064
my-0.063
rying-0.062
Token have
Token ID423
Feature activation-1.85e+00

Pos logit contributions
cakes+0.118
 vows+0.111
ades+0.108
apy+0.100
ival+0.095
Neg logit contributions
my-0.130
bur-0.129
i-0.126
 forth-0.124
cker-0.118
Token a
Token ID257
Feature activation-3.17e+00

Pos logit contributions
 vows+0.114
cakes+0.095
apy+0.095
Mine+0.094
 Prize+0.093
Neg logit contributions
rying-0.060
 owl-0.055
ishing-0.053
bur-0.051
ppa-0.050
Token game
Token ID983
Feature activation-1.68e+00

Pos logit contributions
 vows+0.101
uits+0.091
apy+0.088
 Both+0.086
cakes+0.086
Neg logit contributions
ind-0.171
rying-0.152
 owl-0.151
ppa-0.151
ich-0.145
Token.
Token ID13
Feature activation-2.87e-01

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-0.059
ppa-0.057
i-0.057
Token She
Token ID1375
Feature activation+1.57e-01

Pos logit contributions
 vows+0.012
 prize+0.010
 trophy+0.010
 contest+0.010
ades+0.010
Neg logit contributions
bur-0.014
ppa-0.014
rying-0.014
ety-0.014
i-0.014
Token won
Token ID1839
Feature activation-9.15e-01

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
ind+0.007
i+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-4.09e+00

Pos logit contributions
 vows+0.044
 trophy+0.038
ades+0.036
apy+0.036
 prize+0.036
Neg logit contributions
bur-0.041
rying-0.039
ppa-0.039
i-0.038
my-0.037
Token prize
Token ID11596
Feature activation-1.08e+00

Pos logit contributions
uits+0.128
 vows+0.120
apy+0.116
 are+0.106
 widened+0.099
Neg logit contributions
ind-0.205
ety-0.194
 owl-0.191
rying-0.190
ppa-0.184
Token!
Token ID0
Feature activation-4.34e-01

Pos logit contributions
 vows+0.059
apy+0.052
ades+0.049
Mine+0.049
 trophy+0.048
Neg logit contributions
rying-0.041
bur-0.040
i-0.039
ppa-0.039
ety-0.036
Token It
Token ID632
Feature activation-1.45e+00

Pos logit contributions
 vows+0.018
 prize+0.015
 trophy+0.015
 contest+0.015
ades+0.015
Neg logit contributions
bur-0.022
ety-0.021
ppa-0.021
rying-0.021
my-0.021
Token was
Token ID373
Feature activation-1.08e+00

Pos logit contributions
 vows+0.074
apy+0.064
 prize+0.063
ades+0.063
uits+0.063
Neg logit contributions
bur-0.059
my-0.057
i-0.057
rying-0.055
ety-0.055
Token a
Token ID257
Feature activation-2.69e+00

Pos logit contributions
 vows+0.055
ades+0.047
 trophy+0.046
apy+0.046
cakes+0.045
Neg logit contributions
bur-0.046
ppa-0.042
i-0.042
rying-0.042
my-0.041
Token talked
Token ID6619
Feature activation-2.26e+00

Pos logit contributions
 vows+0.070
 prize+0.069
 trophy+0.068
 contest+0.068
apy+0.066
Neg logit contributions
ppa-0.055
i-0.054
bur-0.052
ety-0.049
my-0.049
Token to
Token ID284
Feature activation-4.75e-01

Pos logit contributions
 vows+0.134
�+0.133
 Prize+0.131
apy+0.130
 trophy+0.129
Neg logit contributions
my-0.056
bur-0.047
rying-0.047
ppa-0.047
i-0.047
Token them
Token ID606
Feature activation-2.83e+00

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-0.025
rying-0.025
ind-0.024
Token and
Token ID290
Feature activation-7.02e-01

Pos logit contributions
 vows+0.169
apy+0.169
Mine+0.162
 Prize+0.160
�+0.157
Neg logit contributions
i-0.075
my-0.073
rying-0.072
bur-0.063
 owl-0.062
Token made
Token ID925
Feature activation-1.49e+00

Pos logit contributions
 vows+0.032
 prize+0.029
ades+0.029
 contest+0.029
 trophy+0.029
Neg logit contributions
bur-0.030
ppa-0.030
rying-0.029
i-0.029
ety-0.028
Token them
Token ID606
Feature activation-4.09e+00

Pos logit contributions
 vows+0.055
 Prize+0.051
 prize+0.051
 trophy+0.051
 contest+0.050
Neg logit contributions
i-0.074
ind-0.074
rying-0.073
bur-0.073
ppa-0.072
Token talk
Token ID1561
Feature activation-2.52e+00

Pos logit contributions
�+0.162
 Prize+0.154
 vows+0.149
Mine+0.144
ival+0.140
Neg logit contributions
my-0.189
rying-0.185
i-0.171
ety-0.166
bur-0.164
Token back
Token ID736
Feature activation-6.66e-01

Pos logit contributions
apy+0.147
�+0.146
 vows+0.141
 Prize+0.141
Mine+0.140
Neg logit contributions
my-0.066
rying-0.065
ind-0.062
i-0.060
 owl-0.059
Token.
Token ID13
Feature activation-5.98e-01

Pos logit contributions
 vows+0.032
apy+0.029
 contest+0.029
 prize+0.029
 trophy+0.029
Neg logit contributions
rying-0.027
bur-0.027
ind-0.027
i-0.026
ppa-0.026
Token
Token ID198
Feature activation+3.47e-01

Pos logit contributions
 vows+0.024
 prize+0.022
 trophy+0.022
 contest+0.021
cakes+0.020
Neg logit contributions
bur-0.030
ppa-0.029
rying-0.028
ety-0.028
i-0.028
Token
Token ID198
Feature activation+3.75e-01

Pos logit contributions
bur+0.020
rying+0.020
ppa+0.020
i+0.019
ind+0.019
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.009
 trophy-0.009
apy-0.009
Token dolls
Token ID36062
Feature activation-1.14e+00

Pos logit contributions
apy+0.035
 vows+0.034
ades+0.032
cakes+0.031
 trophy+0.030
Neg logit contributions
bur-0.049
ppa-0.048
rying-0.047
ind-0.047
i-0.046
Token'
Token ID6
Feature activation-1.59e-01

Pos logit contributions
 vows+0.060
apy+0.054
 Prize+0.054
Mine+0.054
 contest+0.053
Neg logit contributions
rying-0.043
bur-0.042
ppa-0.041
i-0.041
ind-0.039
Token hands
Token ID2832
Feature activation+5.31e-02

Pos logit contributions
 vows+0.006
 prize+0.006
 contest+0.005
 trophy+0.005
apy+0.005
Neg logit contributions
bur-0.008
rying-0.008
ppa-0.008
ind-0.008
i-0.008
Token and
Token ID290
Feature activation-6.09e-01

Pos logit contributions
bur+0.002
rying+0.002
ppa+0.002
i+0.002
ind+0.002
Neg logit contributions
 vows-0.003
 prize-0.002
 contest-0.002
 trophy-0.002
cakes-0.002
Token made
Token ID925
Feature activation-2.00e+00

Pos logit contributions
 vows+0.026
 prize+0.023
 contest+0.023
 trophy+0.023
ades+0.023
Neg logit contributions
bur-0.028
ppa-0.028
i-0.027
rying-0.027
ety-0.026
Token them
Token ID606
Feature activation-4.08e+00

Pos logit contributions
�+0.075
 vows+0.075
 trophy+0.071
 Prize+0.071
 contest+0.070
Neg logit contributions
i-0.092
ind-0.092
rying-0.090
ppa-0.090
bur-0.089
Token say
Token ID910
Feature activation-3.74e+00

Pos logit contributions
�+0.153
 Prize+0.135
Mine+0.133
 vows+0.130
cakes+0.124
Neg logit contributions
rying-0.192
my-0.190
i-0.187
 aware-0.173
bur-0.173
Token,
Token ID11
Feature activation-1.87e+00

Pos logit contributions
Mine+0.185
case+0.167
�+0.166
 trophy+0.158
igsaw+0.157
Neg logit contributions
i-0.120
 owl-0.109
 asking-0.106
ppa-0.106
rying-0.101
Token "
Token ID366
Feature activation-7.78e-01

Pos logit contributions
 vows+0.071
 prize+0.065
 trophy+0.063
 contest+0.062
case+0.062
Neg logit contributions
gie-0.089
rying-0.088
bur-0.086
ppa-0.085
 owl-0.084
TokenI
Token ID40
Feature activation-2.01e+00

Pos logit contributions
 vows+0.031
 trophy+0.028
 prize+0.028
apy+0.028
 contest+0.027
Neg logit contributions
bur-0.039
ppa-0.037
ind-0.037
ety-0.036
i-0.036
Token do
Token ID466
Feature activation-2.06e+00

Pos logit contributions
cakes+0.092
apy+0.089
ades+0.089
 trophy+0.088
 vows+0.087
Neg logit contributions
i-0.081
bur-0.080
my-0.075
rying-0.074
ppa-0.074
Token takes
Token ID2753
Feature activation-4.29e-01

Pos logit contributions
apy+0.123
 vows+0.120
 contest+0.115
 prize+0.113
 Prize+0.112
Neg logit contributions
i-0.091
rying-0.089
my-0.087
bur-0.087
ind-0.083
Token a
Token ID257
Feature activation-2.37e+00

Pos logit contributions
 vows+0.019
 prize+0.016
 trophy+0.016
 Prize+0.016
 contest+0.016
Neg logit contributions
bur-0.020
rying-0.019
ppa-0.019
i-0.019
my-0.019
Token sip
Token ID31145
Feature activation-1.51e+00

Pos logit contributions
 vows+0.093
 Prize+0.068
 parties+0.067
 Everybody+0.066
 Everyone+0.065
Neg logit contributions
my-0.120
ety-0.116
rying-0.109
bur-0.108
row-0.107
Token.
Token ID13
Feature activation-1.77e+00

Pos logit contributions
 vows+0.085
 Prize+0.078
 prize+0.075
 contest+0.074
 trophy+0.073
Neg logit contributions
i-0.050
my-0.048
rying-0.047
bur-0.046
ety-0.044
Token The
Token ID383
Feature activation-1.75e+00

Pos logit contributions
 vows+0.083
 prize+0.078
 trophy+0.076
 contest+0.073
 festival+0.071
Neg logit contributions
bur-0.065
gie-0.064
 Owl-0.064
ior-0.064
ety-0.062
Token juice
Token ID13135
Feature activation-4.06e+00

Pos logit contributions
 vows+0.070
 Prize+0.063
ival+0.061
ades+0.061
case+0.060
Neg logit contributions
my-0.080
bur-0.074
ety-0.073
i-0.071
ener-0.069
Token is
Token ID318
Feature activation-9.95e-01

Pos logit contributions
ival+0.203
 Prize+0.199
 vows+0.192
igsaw+0.183
ades+0.179
Neg logit contributions
my-0.127
i-0.126
 forth-0.119
rying-0.116
bur-0.112
Token sweet
Token ID6029
Feature activation+1.31e-01

Pos logit contributions
 vows+0.042
 Prize+0.037
 contest+0.037
 prize+0.037
 trophy+0.036
Neg logit contributions
bur-0.048
ppa-0.047
i-0.046
rying-0.046
ety-0.044
Token and
Token ID290
Feature activation-1.90e-01

Pos logit contributions
bur+0.006
rying+0.006
ppa+0.006
i+0.006
ind+0.005
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.005
apy-0.005
Token cold
Token ID4692
Feature activation-9.12e-02

Pos logit contributions
 vows+0.007
 contest+0.006
 prize+0.006
 trophy+0.006
cakes+0.006
Neg logit contributions
bur-0.010
rying-0.010
ppa-0.010
i-0.010
ind-0.009
Token.
Token ID13
Feature activation-1.34e+00

Pos logit contributions
 vows+0.004
 prize+0.004
 contest+0.004
 trophy+0.004
apy+0.004
Neg logit contributions
bur-0.004
rying-0.004
ppa-0.004
i-0.004
ind-0.004
Token pushed
Token ID7121
Feature activation+2.85e-01

Pos logit contributions
 vows+0.067
 prize+0.063
 trophy+0.060
 contest+0.059
 Prize+0.058
Neg logit contributions
ppa-0.056
my-0.056
i-0.056
rying-0.055
bur-0.054
Token the
Token ID262
Feature activation-1.42e+00

Pos logit contributions
bur+0.015
rying+0.015
ppa+0.015
ind+0.015
i+0.015
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.009
 trophy-0.009
apy-0.009
Token buttons
Token ID12163
Feature activation-1.52e+00

Pos logit contributions
 vows+0.046
apy+0.044
ades+0.038
 prize+0.038
ves+0.038
Neg logit contributions
my-0.074
ind-0.073
rying-0.073
ener-0.072
bur-0.070
Token and
Token ID290
Feature activation-3.28e-01

Pos logit contributions
 vows+0.086
 Prize+0.074
 prize+0.073
cakes+0.072
 contest+0.072
Neg logit contributions
rying-0.054
bur-0.052
i-0.050
my-0.048
gie-0.046
Token the
Token ID262
Feature activation-1.56e+00

Pos logit contributions
 vows+0.015
 prize+0.013
 trophy+0.013
 contest+0.013
ades+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-4.05e+00

Pos logit contributions
 vows+0.072
apy+0.067
ades+0.065
 Prize+0.065
ves+0.064
Neg logit contributions
my-0.058
ener-0.057
 owl-0.057
ind-0.056
rying-0.056
Token changed
Token ID3421
Feature activation-1.01e+00

Pos logit contributions
 vows+0.180
 Prize+0.177
 festival+0.154
 coach+0.154
 prize+0.154
Neg logit contributions
rying-0.156
 forth-0.155
i-0.152
my-0.149
ener-0.144
Token back
Token ID736
Feature activation+1.08e-01

Pos logit contributions
 vows+0.048
 prize+0.044
 contest+0.043
 trophy+0.043
cakes+0.043
Neg logit contributions
rying-0.043
bur-0.041
i-0.041
ind-0.040
ppa-0.039
Token to
Token ID284
Feature activation-1.11e+00

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
ind+0.005
i+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-9.48e-01

Pos logit contributions
 vows+0.046
cakes+0.042
ades+0.041
 trophy+0.040
apy+0.039
Neg logit contributions
rying-0.052
bur-0.051
ind-0.051
i-0.049
my-0.049
Token way
Token ID835
Feature activation-6.18e-01

Pos logit contributions
 vows+0.031
apy+0.029
 prize+0.026
ves+0.025
ades+0.025
Neg logit contributions
ind-0.052
rying-0.051
bur-0.050
my-0.050
ppa-0.049
Token.
Token ID13
Feature activation-2.10e+00

Pos logit contributions
 vows+0.133
 Prize+0.123
apy+0.121
cakes+0.120
 prize+0.118
Neg logit contributions
rying-0.072
i-0.069
my-0.066
bur-0.063
cker-0.062
Token They
Token ID1119
Feature activation-1.87e+00

Pos logit contributions
 vows+0.090
 prize+0.084
 trophy+0.083
kin+0.082
ades+0.082
Neg logit contributions
ior-0.090
ety-0.079
my-0.077
gie-0.076
bur-0.074
Token both
Token ID1111
Feature activation-1.53e+00

Pos logit contributions
 vows+0.070
cakes+0.069
apy+0.064
ades+0.064
ves+0.063
Neg logit contributions
my-0.094
i-0.094
bur-0.092
rying-0.088
ppa-0.088
Token think
Token ID892
Feature activation-2.19e+00

Pos logit contributions
 vows+0.052
cakes+0.051
ades+0.048
apy+0.046
 prize+0.044
Neg logit contributions
i-0.082
my-0.081
rying-0.081
bur-0.080
cker-0.079
Token their
Token ID511
Feature activation-1.86e+00

Pos logit contributions
 vows+0.102
 Prize+0.092
Mine+0.089
�+0.088
cakes+0.084
Neg logit contributions
i-0.080
rying-0.075
my-0.075
 owl-0.074
ind-0.074
Token shapes
Token ID15268
Feature activation-4.05e+00

Pos logit contributions
cakes+0.081
ades+0.071
apy+0.071
ival+0.070
 Prize+0.070
Neg logit contributions
ind-0.081
i-0.074
 owl-0.072
bur-0.070
ener-0.070
Token are
Token ID389
Feature activation-1.44e+00

Pos logit contributions
 vows+0.133
 Prize+0.128
apy+0.120
cakes+0.119
ival+0.119
Neg logit contributions
my-0.212
i-0.202
cker-0.197
rying-0.193
bur-0.190
Token good
Token ID922
Feature activation-7.78e-01

Pos logit contributions
 vows+0.059
cakes+0.054
apy+0.052
 Prize+0.051
 contest+0.051
Neg logit contributions
bur-0.068
rying-0.067
i-0.066
ppa-0.066
cker-0.064
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
 vows+0.040
apy+0.036
ades+0.035
cakes+0.035
 trophy+0.034
Neg logit contributions
rying-0.030
i-0.029
bur-0.029
ppa-0.028
ety-0.028
Token But
Token ID887
Feature activation-1.60e-01

Pos logit contributions
 vows+0.040
 prize+0.037
 trophy+0.037
 contest+0.035
ades+0.033
Neg logit contributions
ior-0.055
ety-0.053
bur-0.053
my-0.051
ind-0.050
Token they
Token ID484
Feature activation-1.29e+00

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-0.008
Token feels
Token ID5300
Feature activation+4.60e-01

Pos logit contributions
bur+0.002
rying+0.002
ppa+0.002
i+0.002
ind+0.002
Neg logit contributions
 vows-0.001
 prize-0.001
 contest-0.001
 trophy-0.001
cakes-0.001
Token a
Token ID257
Feature activation+3.27e-01

Pos logit contributions
bur+0.023
rying+0.023
ppa+0.022
ind+0.022
i+0.022
Neg logit contributions
 vows-0.019
 prize-0.016
 contest-0.016
apy-0.016
 trophy-0.016
Token burn
Token ID4245
Feature activation+9.84e-01

Pos logit contributions
bur+0.018
rying+0.017
ppa+0.017
i+0.016
ind+0.016
Neg logit contributions
 vows-0.012
 prize-0.011
 contest-0.011
 trophy-0.010
apy-0.010
Token in
Token ID287
Feature activation+7.73e-01

Pos logit contributions
ppa+0.051
bur+0.051
rying+0.049
ind+0.048
ety+0.048
Neg logit contributions
 vows-0.037
 prize-0.033
 contest-0.032
 trophy-0.032
 are-0.032
Token his
Token ID465
Feature activation+6.96e-01

Pos logit contributions
rying+0.043
ppa+0.042
bur+0.041
ind+0.040
i+0.040
Neg logit contributions
 vows-0.027
 prize-0.025
apy-0.024
 trophy-0.024
 contest-0.024
Token tum
Token ID11814
Feature activation+3.41e+00

Pos logit contributions
rying+0.033
bur+0.032
ppa+0.032
ind+0.030
i+0.030
Neg logit contributions
 vows-0.031
 prize-0.028
 contest-0.028
 trophy-0.027
apy-0.027
Tokenmy
Token ID1820
Feature activation+1.50e+00

Pos logit contributions
rying+0.129
ind+0.124
 lamb+0.121
cker+0.110
ppa+0.109
Neg logit contributions
 are-0.175
cakes-0.164
ades-0.154
 were-0.154
books-0.150
Token.
Token ID13
Feature activation+5.04e-01

Pos logit contributions
bur+0.082
rying+0.081
ppa+0.079
ind+0.079
umper+0.075
Neg logit contributions
 vows-0.049
 are-0.046
 prize-0.046
 trophy-0.044
 contest-0.043
Token He
Token ID679
Feature activation+3.69e-01

Pos logit contributions
rying+0.025
bur+0.025
ppa+0.025
ind+0.024
i+0.024
Neg logit contributions
 vows-0.021
 prize-0.018
 contest-0.018
apy-0.018
 trophy-0.018
Token is
Token ID318
Feature activation+1.13e+00

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-0.012
Token angry
Token ID7954
Feature activation+1.03e+00

Pos logit contributions
bur+0.058
rying+0.057
ppa+0.055
i+0.054
ior+0.054
Neg logit contributions
 vows-0.043
apy-0.039
 contest-0.038
 tea-0.038
 prize-0.037
Token was
Token ID373
Feature activation-7.39e-01

Pos logit contributions
 vows+0.024
 prize+0.020
 trophy+0.020
 contest+0.020
apy+0.020
Neg logit contributions
bur-0.029
ppa-0.027
rying-0.027
i-0.027
gie-0.026
Token washed
Token ID18989
Feature activation+4.72e-01

Pos logit contributions
 vows+0.034
 prize+0.030
 Prize+0.029
 trophy+0.029
 contest+0.029
Neg logit contributions
bur-0.035
rying-0.033
ppa-0.033
i-0.031
ind-0.030
Token and
Token ID290
Feature activation+7.30e-01

Pos logit contributions
bur+0.025
rying+0.025
ppa+0.025
ind+0.024
i+0.023
Neg logit contributions
 vows-0.018
 prize-0.015
 contest-0.015
 trophy-0.015
apy-0.015
Token dried
Token ID16577
Feature activation+1.19e+00

Pos logit contributions
bur+0.039
ppa+0.038
rying+0.038
ind+0.037
ior+0.036
Neg logit contributions
 vows-0.027
apy-0.025
 prize-0.024
 contest-0.024
 trophy-0.024
Token,
Token ID11
Feature activation+1.08e+00

Pos logit contributions
bur+0.067
rying+0.065
ppa+0.065
ety+0.063
cker+0.062
Neg logit contributions
 vows-0.042
apy-0.037
 prize-0.035
 trophy-0.032
 are-0.032
Token Ang
Token ID2895
Feature activation+3.56e+00

Pos logit contributions
bur+0.049
rying+0.049
ppa+0.048
ind+0.046
cker+0.046
Neg logit contributions
 vows-0.047
apy-0.045
 prize-0.044
 contest-0.042
 trophy-0.041
Tokenie
Token ID494
Feature activation+3.39e-01

Pos logit contributions
 territory+0.146
ior+0.138
 Owl+0.133
 property+0.132
 afar+0.128
Neg logit contributions
 vows-0.135
 were-0.118
 are-0.116
 tea-0.114
kin-0.113
Token and
Token ID290
Feature activation+9.81e-01

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-0.012
 contest-0.012
 trophy-0.012
apy-0.011
Token her
Token ID607
Feature activation-2.38e-01

Pos logit contributions
rying+0.061
bur+0.060
ppa+0.060
ind+0.060
ior+0.057
Neg logit contributions
 vows-0.028
apy-0.024
 prize-0.023
 trophy-0.022
 contest-0.021
Token mum
Token ID25682
Feature activation+2.27e-01

Pos logit contributions
 vows+0.010
 contest+0.009
 prize+0.009
cakes+0.009
 trophy+0.009
Neg logit contributions
bur-0.011
rying-0.011
ppa-0.011
i-0.011
ind-0.011
Token headed
Token ID9153
Feature activation-5.68e-01

Pos logit contributions
bur+0.012
rying+0.012
ppa+0.012
ind+0.011
i+0.011
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.007
 trophy-0.007
cakes-0.007
Token.
Token ID13
Feature activation+5.69e-01

Pos logit contributions
bur+0.100
ppa+0.099
ior+0.098
rying+0.096
ind+0.096
Neg logit contributions
 vows-0.046
 contest-0.044
 prize-0.042
 are-0.040
 trophy-0.040
Token
Token ID198
Feature activation+2.98e-01

Pos logit contributions
bur+0.034
rying+0.034
ppa+0.034
ind+0.033
i+0.032
Neg logit contributions
 vows-0.017
 prize-0.015
 contest-0.014
cakes-0.014
 trophy-0.014
Token
Token ID198
Feature activation+6.43e-01

Pos logit contributions
bur+0.017
rying+0.017
ppa+0.017
ind+0.016
i+0.016
Neg logit contributions
 vows-0.010
 prize-0.008
 contest-0.008
 trophy-0.008
apy-0.008
Token"
Token ID1
Feature activation+6.40e-01

Pos logit contributions
bur+0.033
rying+0.033
ppa+0.032
i+0.031
ind+0.031
Neg logit contributions
 vows-0.024
 contest-0.022
 prize-0.021
 trophy-0.021
apy-0.021
TokenHi
Token ID17250
Feature activation+1.30e+00

Pos logit contributions
rying+0.029
ppa+0.028
bur+0.028
ind+0.028
i+0.027
Neg logit contributions
 vows-0.029
 prize-0.026
 contest-0.026
cakes-0.025
 trophy-0.025
Token Tweet
Token ID18752
Feature activation+3.87e+00

Pos logit contributions
ppa+0.074
rying+0.074
bur+0.072
ind+0.071
cker+0.070
Neg logit contributions
 vows-0.040
 prize-0.040
 contest-0.037
 trophy-0.036
 Prize-0.034
Tokenie
Token ID494
Feature activation+2.73e+00

Pos logit contributions
rying+0.132
oscope+0.128
keeping+0.127
ind+0.123
bur+0.121
Neg logit contributions
 are-0.163
 prize-0.162
 team-0.158
 trophy-0.156
 laugh-0.152
Token,
Token ID11
Feature activation+4.14e-01

Pos logit contributions
bur+0.178
rying+0.178
ind+0.174
ppa+0.171
umper+0.169
Neg logit contributions
 prize-0.051
 are-0.047
 contest-0.046
 vows-0.046
 trophy-0.043
Token do
Token ID466
Feature activation-6.62e-01

Pos logit contributions
bur+0.022
rying+0.022
ppa+0.022
ind+0.021
i+0.021
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.014
 trophy-0.014
cakes-0.013
Token you
Token ID345
Feature activation+4.70e-01

Pos logit contributions
 vows+0.036
 trophy+0.032
 prize+0.032
cakes+0.032
 contest+0.031
Neg logit contributions
bur-0.023
ppa-0.023
rying-0.023
i-0.022
ind-0.022
Token want
Token ID765
Feature activation+6.27e-01

Pos logit contributions
bur+0.024
ppa+0.024
rying+0.024
ind+0.023
i+0.023
Neg logit contributions
 vows-0.018
 prize-0.017
 contest-0.016
 trophy-0.016
 joke-0.015
Token are
Token ID389
Feature activation-3.04e-01

Pos logit contributions
 vows+0.036
 trophy+0.029
 prize+0.029
 contest+0.028
apy+0.028
Neg logit contributions
my-0.054
bur-0.053
rying-0.052
i-0.052
ety-0.052
Token you
Token ID345
Feature activation+3.55e-01

Pos logit contributions
 vows+0.015
 prize+0.014
 trophy+0.014
 contest+0.014
apy+0.013
Neg logit contributions
bur-0.012
rying-0.012
ppa-0.012
i-0.011
ind-0.011
Token,
Token ID11
Feature activation-7.74e-01

Pos logit contributions
bur+0.017
ppa+0.017
rying+0.016
ind+0.016
i+0.016
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.014
 trophy-0.014
cakes-0.013
Token Lily
Token ID20037
Feature activation+1.94e+00

Pos logit contributions
 vows+0.035
ades+0.029
 contest+0.029
 trophy+0.028
apy+0.028
Neg logit contributions
bur-0.036
rying-0.034
ppa-0.034
ety-0.033
i-0.033
Token?"
Token ID1701
Feature activation+1.02e+00

Pos logit contributions
rying+0.098
ind+0.097
bur+0.096
ppa+0.094
gie+0.090
Neg logit contributions
 contest-0.068
 vows-0.064
 trophy-0.063
 prize-0.062
case-0.060
Token Tim
Token ID5045
Feature activation+3.48e+00

Pos logit contributions
rying+0.063
bur+0.061
ind+0.060
ppa+0.060
cker+0.056
Neg logit contributions
 vows-0.030
apy-0.030
 contest-0.028
 prize-0.027
cakes-0.026
Token called
Token ID1444
Feature activation-5.63e-01

Pos logit contributions
ind+0.190
rying+0.184
ishing+0.172
 property+0.171
bur+0.170
Neg logit contributions
 tag-0.101
 laugh-0.099
 g-0.098
 joke-0.094
 cl-0.094
Token out
Token ID503
Feature activation-1.60e+00

Pos logit contributions
 vows+0.026
 trophy+0.022
 prize+0.022
ades+0.022
apy+0.021
Neg logit contributions
rying-0.026
bur-0.026
ppa-0.025
i-0.024
ety-0.024
Token.
Token ID13
Feature activation-2.91e-01

Pos logit contributions
 vows+0.089
 Prize+0.078
 trophy+0.078
Mine+0.078
ades+0.077
Neg logit contributions
rying-0.053
 owl-0.051
 Owl-0.050
i-0.050
my-0.049
Token He
Token ID679
Feature activation+7.13e-01

Pos logit contributions
 vows+0.011
 prize+0.009
 trophy+0.009
 contest+0.009
ades+0.009
Neg logit contributions
bur-0.015
rying-0.015
ppa-0.015
ety-0.014
gie-0.014
Token looked
Token ID3114
Feature activation+3.61e-01

Pos logit contributions
bur+0.036
rying+0.036
ppa+0.034
ind+0.034
ior+0.032
Neg logit contributions
 vows-0.029
 prize-0.025
 contest-0.025
 trophy-0.025
apy-0.024
Token walking
Token ID6155
Feature activation-4.44e-02

Pos logit contributions
bur+0.018
rying+0.017
ppa+0.017
ind+0.017
i+0.016
Neg logit contributions
 vows-0.025
 contest-0.023
 prize-0.023
 trophy-0.023
cakes-0.022
Token down
Token ID866
Feature activation-9.24e-01

Pos logit contributions
 vows+0.002
 prize+0.002
 contest+0.002
 trophy+0.002
cakes+0.002
Neg logit contributions
bur-0.002
rying-0.002
ppa-0.002
i-0.002
ind-0.002
Token the
Token ID262
Feature activation+3.52e-01

Pos logit contributions
 vows+0.047
 trophy+0.040
 joke+0.039
ades+0.038
 prize+0.038
Neg logit contributions
bur-0.039
rying-0.035
my-0.035
i-0.034
ety-0.034
Token aisle
Token ID28960
Feature activation+7.04e-01

Pos logit contributions
rying+0.016
bur+0.016
ppa+0.016
i+0.016
ind+0.015
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.014
 trophy-0.014
cakes-0.013
Token,
Token ID11
Feature activation-8.24e-01

Pos logit contributions
bur+0.042
rying+0.042
ppa+0.042
ind+0.041
i+0.040
Neg logit contributions
 vows-0.021
 contest-0.019
 prize-0.019
 trophy-0.018
cakes-0.017
Token Tim
Token ID5045
Feature activation+3.78e+00

Pos logit contributions
 vows+0.034
 prize+0.027
 trophy+0.027
 contest+0.026
ades+0.026
Neg logit contributions
bur-0.042
rying-0.040
gie-0.040
i-0.040
ety-0.040
Tokenmy
Token ID1820
Feature activation+2.74e+00

Pos logit contributions
 predators+0.149
rying+0.147
ind+0.141
cker+0.135
iously+0.135
Neg logit contributions
 were-0.155
 are-0.148
 team-0.138
case-0.138
 game-0.137
Token saw
Token ID2497
Feature activation+1.21e-01

Pos logit contributions
rying+0.160
bur+0.150
ind+0.149
ior+0.142
cker+0.140
Neg logit contributions
 vows-0.078
 they-0.075
 contest-0.073
 were-0.073
case-0.072
Token a
Token ID257
Feature activation-1.07e+00

Pos logit contributions
bur+0.007
rying+0.007
ppa+0.007
ind+0.006
i+0.006
Neg logit contributions
 vows-0.004
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.003
Token big
Token ID1263
Feature activation-3.39e-01

Pos logit contributions
 vows+0.042
cakes+0.035
apy+0.035
uits+0.034
 prize+0.033
Neg logit contributions
bur-0.053
ppa-0.052
ind-0.052
rying-0.051
 owl-0.050
Token,
Token ID11
Feature activation+1.03e+00

Pos logit contributions
 vows+0.014
 prize+0.012
apy+0.012
cakes+0.012
 contest+0.012
Neg logit contributions
bur-0.016
rying-0.016
ppa-0.016
ind-0.015
i-0.015
Token But
Token ID887
Feature activation+2.54e+00

Pos logit contributions
bur+0.104
ppa+0.103
rying+0.103
ind+0.100
i+0.098
Neg logit contributions
 vows-0.064
 Everyone-0.061
 prize-0.058
 Prize-0.057
 contest-0.056
Token first
Token ID717
Feature activation+1.41e+00

Pos logit contributions
ppa+0.153
ior+0.148
ind+0.146
bur+0.145
rying+0.140
Neg logit contributions
 prize-0.088
 contest-0.081
 trophy-0.080
 are-0.078
 thank-0.076
Token,
Token ID11
Feature activation+1.99e+00

Pos logit contributions
bur+0.093
ppa+0.092
ind+0.092
rying+0.090
ior+0.088
Neg logit contributions
 prize-0.036
 vows-0.034
 contest-0.033
 are-0.033
 trophy-0.033
Token let
Token ID1309
Feature activation+1.36e+00

Pos logit contributions
ppa+0.111
ind+0.110
bur+0.110
ior+0.106
rying+0.106
Neg logit contributions
 prize-0.070
 vows-0.066
 contest-0.066
 are-0.064
 trophy-0.064
Token's
Token ID338
Feature activation+8.77e-02

Pos logit contributions
rying+0.074
bur+0.071
ppa+0.071
cker+0.071
ind+0.070
Neg logit contributions
 vows-0.045
 are-0.043
 prize-0.043
 contest-0.042
 Everyone-0.041
Token find
Token ID1064
Feature activation+1.21e+00

Pos logit contributions
bur+0.005
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 some
Token ID617
Feature activation+4.24e-01

Pos logit contributions
rying+0.072
ppa+0.071
bur+0.071
ind+0.068
cker+0.067
Neg logit contributions
 vows-0.037
 prize-0.036
 contest-0.034
apy-0.034
 tea-0.033
Token food
Token ID2057
Feature activation-2.20e-01

Pos logit contributions
bur+0.022
rying+0.022
ppa+0.022
ind+0.021
i+0.021
Neg logit contributions
 vows-0.016
 prize-0.015
 contest-0.014
 trophy-0.014
apy-0.014
Token for
Token ID329
Feature activation+1.21e+00

Pos logit contributions
 vows+0.011
 prize+0.010
 contest+0.009
 trophy+0.009
apy+0.009
Neg logit contributions
bur-0.009
rying-0.009
ppa-0.009
i-0.009
ind-0.008
Token your
Token ID534
Feature activation+1.04e+00

Pos logit contributions
rying+0.059
bur+0.057
ppa+0.055
cker+0.054
ety+0.054
Neg logit contributions
 vows-0.049
 prize-0.048
 contest-0.045
apy-0.044
 trophy-0.044
Token tum
Token ID11814
Feature activation+3.83e+00

Pos logit contributions
rying+0.053
bur+0.053
ppa+0.052
ind+0.050
i+0.050
Neg logit contributions
 vows-0.042
 prize-0.038
 contest-0.037
 trophy-0.036
 joke-0.035
Token bear
Token ID6842
Feature activation+2.79e-01

Pos logit contributions
bur+0.053
rying+0.053
ppa+0.052
ind+0.049
i+0.047
Neg logit contributions
 vows-0.053
 prize-0.050
 contest-0.050
 trophy-0.050
apy-0.046
Token was
Token ID373
Feature activation+1.21e+00

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
ind+0.013
i+0.013
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.010
 trophy-0.010
cakes-0.010
Token so
Token ID523
Feature activation+1.44e-01

Pos logit contributions
rying+0.068
bur+0.067
ppa+0.066
i+0.065
ior+0.064
Neg logit contributions
 vows-0.040
 contest-0.035
 prize-0.035
 trophy-0.034
apy-0.034
Token sad
Token ID6507
Feature activation+7.63e-01

Pos logit contributions
bur+0.008
rying+0.008
ppa+0.008
ind+0.008
i+0.008
Neg logit contributions
 vows-0.005
 prize-0.004
 contest-0.004
 trophy-0.004
cakes-0.004
Token,
Token ID11
Feature activation+1.35e+00

Pos logit contributions
bur+0.040
ppa+0.039
rying+0.038
ind+0.037
ety+0.036
Neg logit contributions
 vows-0.029
 prize-0.027
 trophy-0.026
 contest-0.026
apy-0.025
Token he
Token ID339
Feature activation+8.08e-01

Pos logit contributions
rying+0.075
ind+0.073
bur+0.073
ppa+0.072
ishing+0.070
Neg logit contributions
 vows-0.045
 prize-0.041
 trophy-0.040
apy-0.040
 contest-0.039
Token had
Token ID550
Feature activation+4.65e-01

Pos logit contributions
bur+0.038
rying+0.038
ppa+0.036
ind+0.036
i+0.034
Neg logit contributions
 vows-0.036
 prize-0.032
 trophy-0.031
 contest-0.031
apy-0.030
Token wanted
Token ID2227
Feature activation+1.24e+00

Pos logit contributions
rying+0.021
bur+0.021
ppa+0.021
ind+0.020
i+0.020
Neg logit contributions
 vows-0.021
 prize-0.019
 contest-0.019
 trophy-0.018
apy-0.018
Token to
Token ID284
Feature activation-3.60e-01

Pos logit contributions
rying+0.069
ppa+0.068
ind+0.067
bur+0.066
i+0.064
Neg logit contributions
 vows-0.044
 prize-0.042
 contest-0.041
 trophy-0.039
 joke-0.037
Token hang
Token ID8181
Feature activation+2.11e-01

Pos logit contributions
 vows+0.013
cakes+0.011
 contest+0.011
apy+0.011
 prize+0.011
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.019
i-0.018
ind-0.018
Tokenout
Token ID448
Feature activation-3.46e-02

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.010
ind+0.009
i+0.009
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.008
Token rock
Token ID3881
Feature activation+1.30e+00

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.014
i+0.013
ind+0.013
Neg logit contributions
 vows-0.015
 prize-0.013
 contest-0.013
 trophy-0.013
cakes-0.012
Token.
Token ID13
Feature activation+3.66e-01

Pos logit contributions
ppa+0.066
bur+0.066
rying+0.064
ind+0.064
ior+0.063
Neg logit contributions
 vows-0.049
 contest-0.045
 prize-0.045
 trophy-0.044
cakes-0.041
Token The
Token ID383
Feature activation+3.85e-01

Pos logit contributions
bur+0.020
rying+0.019
ppa+0.019
ind+0.019
i+0.018
Neg logit contributions
 vows-0.014
 prize-0.012
 contest-0.012
 trophy-0.011
apy-0.011
Token lizard
Token ID42406
Feature activation-1.20e+00

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.018
ind+0.018
i+0.018
Neg logit contributions
 vows-0.016
 prize-0.015
 contest-0.014
 trophy-0.014
apy-0.014
Token is
Token ID318
Feature activation+1.08e+00

Pos logit contributions
 vows+0.051
cakes+0.046
 prize+0.045
apy+0.045
 contest+0.045
Neg logit contributions
i-0.055
rying-0.054
bur-0.054
ppa-0.052
cker-0.052
Token green
Token ID4077
Feature activation+1.25e+00

Pos logit contributions
rying+0.058
bur+0.057
ppa+0.056
ior+0.054
ind+0.054
Neg logit contributions
 vows-0.039
 prize-0.035
 contest-0.034
 trophy-0.034
apy-0.033
Token and
Token ID290
Feature activation+4.19e-01

Pos logit contributions
ppa+0.066
bur+0.066
rying+0.064
ind+0.061
ior+0.060
Neg logit contributions
 vows-0.047
 prize-0.045
 trophy-0.044
 contest-0.043
 are-0.041
Token has
Token ID468
Feature activation+5.53e-01

Pos logit contributions
bur+0.022
rying+0.022
ppa+0.022
ind+0.021
i+0.021
Neg logit contributions
 vows-0.016
 prize-0.014
 contest-0.014
 trophy-0.014
apy-0.013
Token a
Token ID257
Feature activation-1.87e-01

Pos logit contributions
rying+0.031
bur+0.031
ppa+0.030
ind+0.029
i+0.029
Neg logit contributions
 vows-0.019
 prize-0.017
 contest-0.016
 trophy-0.016
apy-0.016
Token long
Token ID890
Feature activation+1.16e+00

Pos logit contributions
 vows+0.007
 contest+0.006
cakes+0.006
 prize+0.006
 trophy+0.006
Neg logit contributions
bur-0.010
rying-0.010
ppa-0.010
ind-0.009
i-0.009
Token tail
Token ID7894
Feature activation+3.77e-01

Pos logit contributions
rying+0.055
bur+0.054
ppa+0.053
ind+0.051
ior+0.049
Neg logit contributions
 vows-0.052
 prize-0.047
 trophy-0.046
 contest-0.045
apy-0.045
Token surface
Token ID4417
Feature activation+3.15e-01

Pos logit contributions
bur+0.022
rying+0.021
ppa+0.021
i+0.020
ind+0.020
Neg logit contributions
 vows-0.015
 prize-0.014
 contest-0.013
 trophy-0.013
apy-0.012
Token.
Token ID13
Feature activation+3.65e-01

Pos logit contributions
bur+0.016
rying+0.016
ppa+0.016
ind+0.015
i+0.015
Neg logit contributions
 vows-0.012
 prize-0.011
 contest-0.011
 trophy-0.011
cakes-0.010
Token He
Token ID679
Feature activation+4.09e-01

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.018
ind+0.018
i+0.018
Neg logit contributions
 vows-0.015
 prize-0.013
 contest-0.013
 trophy-0.013
cakes-0.012
Token said
Token ID531
Feature activation-1.11e+00

Pos logit contributions
bur+0.020
rying+0.020
ppa+0.019
ind+0.019
i+0.018
Neg logit contributions
 vows-0.017
 prize-0.015
 contest-0.015
 trophy-0.015
apy-0.015
Token goodbye
Token ID24829
Feature activation+1.85e+00

Pos logit contributions
 vows+0.044
cakes+0.039
Mine+0.039
 prize+0.038
 contest+0.038
Neg logit contributions
rying-0.051
i-0.050
ppa-0.050
bur-0.048
ener-0.047
Token to
Token ID284
Feature activation+8.92e-01

Pos logit contributions
bur+0.109
umper+0.107
ppa+0.105
ind+0.105
rying+0.103
Neg logit contributions
 vows-0.061
 prize-0.053
 contest-0.048
 trophy-0.047
 they-0.046
Token the
Token ID262
Feature activation-5.22e-01

Pos logit contributions
rying+0.053
ppa+0.053
bur+0.053
ind+0.052
ety+0.050
Neg logit contributions
 vows-0.027
 prize-0.026
 trophy-0.025
 contest-0.024
 are-0.022
Token butterfly
Token ID35113
Feature activation+1.14e-01

Pos logit contributions
 vows+0.021
cakes+0.018
apy+0.018
ades+0.017
 contest+0.017
Neg logit contributions
rying-0.026
bur-0.026
ppa-0.025
i-0.025
ind-0.025
Token and
Token ID290
Feature activation+2.06e-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-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token ran
Token ID4966
Feature activation-2.87e-01

Pos logit contributions
bur+0.010
rying+0.010
ppa+0.009
ind+0.009
i+0.009
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
apy-0.008
Token off
Token ID572
Feature activation-8.82e-01

Pos logit contributions
 vows+0.015
 contest+0.014
 prize+0.014
 trophy+0.013
apy+0.013
Neg logit contributions
bur-0.011
rying-0.011
ppa-0.010
i-0.010
ind-0.010
Token.
Token ID13
Feature activation+2.09e-02

Pos logit contributions
bur+0.099
rying+0.099
umper+0.096
ppa+0.095
ind+0.095
Neg logit contributions
 vows-0.063
 prize-0.052
 contest-0.048
 trophy-0.048
cakes-0.047
Token He
Token ID679
Feature activation+3.88e-01

Pos logit contributions
bur+0.001
rying+0.001
ppa+0.001
i+0.001
ind+0.001
Neg logit contributions
 vows-0.001
 prize-0.001
 contest-0.001
 trophy-0.001
cakes-0.001
Token went
Token ID1816
Feature activation+6.26e-01

Pos logit contributions
bur+0.018
rying+0.018
ppa+0.018
ind+0.017
i+0.017
Neg logit contributions
 vows-0.017
 prize-0.015
 contest-0.015
 trophy-0.015
apy-0.014
Token on
Token ID319
Feature activation+1.73e-01

Pos logit contributions
bur+0.027
ppa+0.027
rying+0.027
i+0.026
ind+0.026
Neg logit contributions
 vows-0.029
 prize-0.027
 contest-0.026
 trophy-0.026
cakes-0.025
Token his
Token ID465
Feature activation+8.27e-01

Pos logit contributions
bur+0.008
rying+0.008
ppa+0.008
ind+0.008
i+0.008
Neg logit contributions
 vows-0.007
 prize-0.007
 contest-0.006
 trophy-0.006
cakes-0.006
Token way
Token ID835
Feature activation+1.09e+00

Pos logit contributions
rying+0.044
bur+0.043
ppa+0.043
i+0.041
ind+0.041
Neg logit contributions
 vows-0.032
 prize-0.029
 contest-0.028
 trophy-0.028
 joke-0.026
Token feeling
Token ID4203
Feature activation+2.19e-01

Pos logit contributions
ppa+0.060
bur+0.060
rying+0.059
ind+0.058
ior+0.058
Neg logit contributions
 vows-0.036
 prize-0.034
 trophy-0.032
 contest-0.032
apy-0.030
Token strong
Token ID1913
Feature activation+2.28e+00

Pos logit contributions
bur+0.011
rying+0.011
ppa+0.010
ind+0.010
i+0.010
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
apy-0.008
Token and
Token ID290
Feature activation+1.91e+00

Pos logit contributions
ppa+0.134
bur+0.133
ety+0.127
ind+0.126
rying+0.125
Neg logit contributions
 prize-0.066
 vows-0.066
 contest-0.061
 are-0.061
 trophy-0.060
Token full
Token ID1336
Feature activation-2.18e-01

Pos logit contributions
bur+0.110
ppa+0.109
ind+0.106
umper+0.105
rying+0.103
Neg logit contributions
 vows-0.062
apy-0.057
 prize-0.056
 contest-0.055
 laugh-0.055
Token of
Token ID286
Feature activation+1.00e-01

Pos logit contributions
 vows+0.008
 prize+0.007
 contest+0.007
 trophy+0.007
cakes+0.007
Neg logit contributions
bur-0.011
rying-0.011
ppa-0.011
i-0.011
ind-0.010
Token.
Token ID13
Feature activation-1.70e+00

Pos logit contributions
 vows+0.004
 prize+0.004
 contest+0.003
 trophy+0.003
apy+0.003
Neg logit contributions
bur-0.004
rying-0.004
ppa-0.003
i-0.003
ind-0.003
Token Jack
Token ID3619
Feature activation+4.06e-01

Pos logit contributions
 vows+0.089
 prize+0.079
ves+0.075
apy+0.074
 trophy+0.073
Neg logit contributions
my-0.072
ior-0.066
ety-0.065
bur-0.064
umper-0.060
Tokeny
Token ID88
Feature activation-9.61e-01

Pos logit contributions
rying+0.019
bur+0.019
ppa+0.018
ind+0.018
i+0.017
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
 trophy-0.016
cakes-0.015
Token was
Token ID373
Feature activation-6.01e-01

Pos logit contributions
 vows+0.046
 prize+0.043
 contest+0.042
apy+0.041
 trophy+0.041
Neg logit contributions
i-0.039
ppa-0.039
bur-0.038
rying-0.038
my-0.037
Token excited
Token ID6568
Feature activation+7.06e-01

Pos logit contributions
 vows+0.029
 prize+0.025
ades+0.024
cakes+0.024
 trophy+0.024
Neg logit contributions
bur-0.026
rying-0.026
ppa-0.026
i-0.025
my-0.024
Token!
Token ID0
Feature activation-8.87e-01

Pos logit contributions
bur+0.034
ppa+0.034
rying+0.034
ind+0.033
cker+0.032
Neg logit contributions
 vows-0.029
 prize-0.027
 contest-0.027
 trophy-0.026
cakes-0.026
Token
Token ID198
Feature activation-5.91e-01

Pos logit contributions
 vows+0.042
 prize+0.038
 contest+0.037
 trophy+0.036
apy+0.035
Neg logit contributions
bur-0.038
my-0.038
ety-0.037
ior-0.037
rying-0.036
Token
Token ID198
Feature activation-1.18e+00

Pos logit contributions
 vows+0.025
 prize+0.022
 trophy+0.021
 contest+0.021
 Prize+0.020
Neg logit contributions
bur-0.030
ppa-0.028
rying-0.028
ind-0.028
i-0.028
TokenJack
Token ID14295
Feature activation+1.60e+00

Pos logit contributions
 vows+0.059
 prize+0.054
apy+0.050
 contest+0.049
 Prize+0.049
Neg logit contributions
my-0.051
ind-0.050
ppa-0.049
bur-0.048
ety-0.047
Tokeny
Token ID88
Feature activation-2.98e-01

Pos logit contributions
rying+0.055
bur+0.051
ppa+0.051
ind+0.049
gie+0.047
Neg logit contributions
 vows-0.085
 trophy-0.074
 are-0.074
 contest-0.074
cakes-0.074
Token took
Token ID1718
Feature activation-4.13e-01

Pos logit contributions
 vows+0.015
 prize+0.014
 contest+0.013
 trophy+0.013
apy+0.013
Neg logit contributions
bur-0.012
ppa-0.012
rying-0.012
i-0.011
ind-0.011
Token and
Token ID290
Feature activation+6.11e-01

Pos logit contributions
bur+0.008
rying+0.008
ppa+0.008
ind+0.008
i+0.008
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.009
 trophy-0.009
cakes-0.009
Token saw
Token ID2497
Feature activation-3.31e-01

Pos logit contributions
bur+0.028
rying+0.027
ppa+0.027
ind+0.027
i+0.026
Neg logit contributions
 vows-0.028
 prize-0.025
 contest-0.025
apy-0.024
 trophy-0.024
Token a
Token ID257
Feature activation-1.70e+00

Pos logit contributions
 vows+0.013
 prize+0.011
 contest+0.011
 trophy+0.011
cakes+0.010
Neg logit contributions
bur-0.017
ppa-0.017
rying-0.017
i-0.017
ind-0.016
Token fluffy
Token ID39145
Feature activation+1.18e-01

Pos logit contributions
 vows+0.063
cakes+0.055
apy+0.052
uits+0.051
 contest+0.050
Neg logit contributions
ind-0.085
bur-0.083
 owl-0.082
ppa-0.082
rying-0.080
Token brown
Token ID7586
Feature activation+1.27e-01

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
ind+0.005
i+0.005
Neg logit contributions
 vows-0.005
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token puppy
Token ID26188
Feature activation-5.10e-02

Pos logit contributions
bur+0.006
rying+0.006
ppa+0.006
ind+0.006
i+0.006
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token inside
Token ID2641
Feature activation+3.50e-01

Pos logit contributions
 vows+0.002
 prize+0.002
 contest+0.002
 trophy+0.002
cakes+0.002
Neg logit contributions
bur-0.002
rying-0.002
ppa-0.002
i-0.002
ind-0.002
Token.
Token ID13
Feature activation+1.09e-01

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-0.012
apy-0.012
Token The
Token ID383
Feature activation+1.29e-01

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-0.003
 contest-0.003
 trophy-0.003
cakes-0.003
Token puppy
Token ID26188
Feature activation-6.22e-01

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
ind+0.005
i+0.005
Neg logit contributions
 vows-0.007
 prize-0.006
 contest-0.006
 trophy-0.006
cakes-0.006
Token w
Token ID266
Feature activation-5.38e-01

Pos logit contributions
 vows+0.027
 contest+0.024
 prize+0.024
 trophy+0.024
cakes+0.023
Neg logit contributions
bur-0.029
ppa-0.028
i-0.028
rying-0.028
gie-0.027
Token for
Token ID329
Feature activation+6.09e-01

Pos logit contributions
bur+0.027
rying+0.026
ppa+0.026
ind+0.025
i+0.025
Neg logit contributions
 vows-0.023
 prize-0.021
 contest-0.020
 trophy-0.020
cakes-0.019
Token his
Token ID465
Feature activation+2.74e-01

Pos logit contributions
bur+0.030
rying+0.030
ppa+0.029
ind+0.028
ety+0.028
Neg logit contributions
 vows-0.025
 prize-0.023
 contest-0.022
 trophy-0.022
apy-0.021
Token kingdom
Token ID13239
Feature activation+1.08e-01

Pos logit contributions
bur+0.015
rying+0.014
ppa+0.014
ind+0.014
i+0.014
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.009
 trophy-0.009
cakes-0.008
Token.
Token ID13
Feature activation+8.18e-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
apy-0.004
Token He
Token ID679
Feature activation+4.05e-01

Pos logit contributions
rying+0.047
bur+0.047
ppa+0.046
ind+0.045
i+0.044
Neg logit contributions
 vows-0.027
 prize-0.023
 contest-0.023
 trophy-0.023
apy-0.022
Token was
Token ID373
Feature activation+6.26e-01

Pos logit contributions
bur+0.019
rying+0.019
ppa+0.019
ind+0.018
i+0.018
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.016
 trophy-0.015
cakes-0.015
Token loyal
Token ID9112
Feature activation+9.09e-01

Pos logit contributions
bur+0.032
rying+0.031
ppa+0.031
ind+0.030
i+0.030
Neg logit contributions
 vows-0.025
 prize-0.022
 contest-0.022
 trophy-0.022
apy-0.021
Token and
Token ID290
Feature activation+7.60e-01

Pos logit contributions
bur+0.044
rying+0.043
ppa+0.043
ind+0.041
cker+0.040
Neg logit contributions
 vows-0.039
 prize-0.036
 contest-0.034
 trophy-0.034
cakes-0.032
Token brave
Token ID14802
Feature activation+1.52e+00

Pos logit contributions
bur+0.038
rying+0.037
ppa+0.036
ind+0.035
i+0.035
Neg logit contributions
 vows-0.032
 prize-0.029
 contest-0.028
 trophy-0.028
apy-0.027
Token and
Token ID290
Feature activation+9.04e-01

Pos logit contributions
bur+0.079
ppa+0.076
rying+0.074
ind+0.073
cker+0.072
Neg logit contributions
 vows-0.061
 prize-0.056
 trophy-0.053
 contest-0.052
 are-0.049
Token had
Token ID550
Feature activation-2.99e-01

Pos logit contributions
bur+0.046
rying+0.045
ppa+0.044
ind+0.043
i+0.042
Neg logit contributions
 vows-0.037
 prize-0.033
 contest-0.032
 trophy-0.032
apy-0.032
Token trusts
Token ID31976
Feature activation+1.28e+00

Pos logit contributions
 vows+0.038
apy+0.035
 prize+0.034
 contest+0.033
 trophy+0.033
Neg logit contributions
bur-0.039
rying-0.038
i-0.038
my-0.038
ior-0.037
Token Lily
Token ID20037
Feature activation-2.53e-02

Pos logit contributions
rying+0.087
ind+0.084
ppa+0.083
bur+0.081
cker+0.081
Neg logit contributions
 vows-0.028
 prize-0.027
 contest-0.026
 trophy-0.024
 tea-0.023
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
 vows+0.001
 prize+0.001
 contest+0.001
 trophy+0.001
apy+0.001
Neg logit contributions
bur-0.001
rying-0.001
ppa-0.001
i-0.001
ind-0.001
Token He
Token ID679
Feature activation-1.56e+00

Pos logit contributions
 vows+0.008
 prize+0.007
 contest+0.007
 trophy+0.007
ades+0.006
Neg logit contributions
bur-0.006
rying-0.006
ppa-0.006
ety-0.006
ior-0.006
Token moves
Token ID6100
Feature activation-3.10e-02

Pos logit contributions
 vows+0.073
apy+0.072
 contest+0.068
 prize+0.067
cakes+0.067
Neg logit contributions
bur-0.062
i-0.062
rying-0.059
ppa-0.058
my-0.058
Token his
Token ID465
Feature activation+6.46e-01

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 hand
Token ID1021
Feature activation+1.18e+00

Pos logit contributions
rying+0.029
bur+0.029
ppa+0.028
i+0.027
ind+0.027
Neg logit contributions
 vows-0.030
 prize-0.028
 trophy-0.027
 contest-0.027
 joke-0.026
Token and
Token ID290
Feature activation-3.39e-01

Pos logit contributions
bur+0.060
ppa+0.059
rying+0.058
ind+0.057
i+0.055
Neg logit contributions
 vows-0.045
 contest-0.041
 prize-0.041
 trophy-0.040
apy-0.039
Token shows
Token ID2523
Feature activation+2.59e-01

Pos logit contributions
 vows+0.014
 prize+0.012
 contest+0.012
cakes+0.012
 trophy+0.012
Neg logit contributions
bur-0.017
rying-0.017
ppa-0.016
i-0.016
ind-0.016
Token his
Token ID465
Feature activation-1.46e-01

Pos logit contributions
bur+0.014
rying+0.014
ppa+0.013
ind+0.013
i+0.013
Neg logit contributions
 vows-0.010
 prize-0.009
 contest-0.009
 trophy-0.008
cakes-0.008
Token work
Token ID670
Feature activation-1.27e+00

Pos logit contributions
 vows+0.006
 contest+0.006
 prize+0.005
cakes+0.005
 trophy+0.005
Neg logit contributions
bur-0.007
rying-0.007
ppa-0.007
ind-0.006
i-0.006
Token glad
Token ID9675
Feature activation-1.13e+00

Pos logit contributions
 vows+0.086
cakes+0.080
ades+0.080
 trophy+0.078
 prize+0.078
Neg logit contributions
bur-0.060
ppa-0.058
i-0.058
my-0.058
rying-0.057
Token that
Token ID326
Feature activation-2.31e+00

Pos logit contributions
 vows+0.045
 Prize+0.039
apy+0.039
 trophy+0.038
ades+0.038
Neg logit contributions
i-0.057
rying-0.055
bur-0.054
ppa-0.052
ety-0.052
Token Amy
Token ID14235
Feature activation-8.03e-01

Pos logit contributions
 vows+0.087
ades+0.084
cakes+0.076
apy+0.076
�+0.073
Neg logit contributions
my-0.111
i-0.108
 owl-0.106
 asking-0.106
 forth-0.105
Token helped
Token ID4193
Feature activation-9.50e-01

Pos logit contributions
 vows+0.036
 contest+0.033
 prize+0.033
apy+0.033
 trophy+0.033
Neg logit contributions
bur-0.035
i-0.035
ppa-0.035
rying-0.034
ind-0.033
Token them
Token ID606
Feature activation-1.76e+00

Pos logit contributions
 vows+0.041
apy+0.038
 trophy+0.036
 Prize+0.035
 prize+0.035
Neg logit contributions
rying-0.043
bur-0.043
i-0.043
ppa-0.042
my-0.041
Token to
Token ID284
Feature activation-8.40e-01

Pos logit contributions
 vows+0.093
apy+0.081
cakes+0.079
 Prize+0.078
 contest+0.077
Neg logit contributions
rying-0.074
my-0.068
bur-0.066
i-0.065
ety-0.062
Token play
Token ID711
Feature activation-2.51e+00

Pos logit contributions
 vows+0.032
cakes+0.029
apy+0.028
 contest+0.027
 prize+0.026
Neg logit contributions
bur-0.045
rying-0.043
ppa-0.042
i-0.041
ind-0.041
Token together
Token ID1978
Feature activation-1.50e+00

Pos logit contributions
 vows+0.147
apy+0.133
cakes+0.125
 Prize+0.122
ades+0.118
Neg logit contributions
rying-0.079
my-0.070
ishing-0.068
ind-0.066
 asking-0.063
Token again
Token ID757
Feature activation+6.30e-01

Pos logit contributions
 vows+0.081
apy+0.077
cakes+0.074
ades+0.070
 Prize+0.069
Neg logit contributions
rying-0.055
i-0.052
bur-0.052
ppa-0.050
ind-0.049
Token.
Token ID13
Feature activation-1.42e+00

Pos logit contributions
bur+0.032
rying+0.031
ppa+0.031
ind+0.030
i+0.030
Neg logit contributions
 vows-0.025
 prize-0.023
 contest-0.022
 trophy-0.022
apy-0.021
Token They
Token ID1119
Feature activation-1.94e+00

Pos logit contributions
 vows+0.063
 trophy+0.057
 prize+0.057
 contest+0.055
ades+0.054
Neg logit contributions
my-0.063
bur-0.062
ior-0.062
ety-0.060
rying-0.058
Token celebrate
Token ID10648
Feature activation-1.34e+00

Pos logit contributions
 vows+0.014
apy+0.012
cakes+0.012
 prize+0.012
 trophy+0.012
Neg logit contributions
bur-0.017
rying-0.016
ppa-0.016
ind-0.015
i-0.015
Token with
Token ID351
Feature activation-8.40e-01

Pos logit contributions
 vows+0.065
apy+0.060
 contest+0.057
 Prize+0.057
cakes+0.057
Neg logit contributions
bur-0.054
i-0.053
ind-0.052
rying-0.052
ppa-0.050
Token him
Token ID683
Feature activation-1.28e+00

Pos logit contributions
 vows+0.038
 contest+0.034
 prize+0.034
 Prize+0.034
cakes+0.033
Neg logit contributions
bur-0.037
ppa-0.035
i-0.035
ind-0.034
my-0.034
Token.
Token ID13
Feature activation-6.33e-01

Pos logit contributions
 vows+0.064
apy+0.058
 contest+0.057
cakes+0.057
 prize+0.057
Neg logit contributions
bur-0.050
i-0.049
rying-0.049
ppa-0.048
my-0.046
Token They
Token ID1119
Feature activation-1.76e+00

Pos logit contributions
 vows+0.024
 prize+0.020
apy+0.020
 trophy+0.020
 contest+0.020
Neg logit contributions
bur-0.034
ety-0.032
ior-0.031
rying-0.031
ppa-0.031
Token played
Token ID2826
Feature activation-3.00e+00

Pos logit contributions
 vows+0.073
apy+0.072
ades+0.072
 prize+0.071
cakes+0.069
Neg logit contributions
i-0.081
bur-0.081
my-0.079
ppa-0.079
rying-0.074
Token games
Token ID1830
Feature activation-2.29e+00

Pos logit contributions
 vows+0.134
apy+0.122
Mine+0.113
cakes+0.112
 disco+0.110
Neg logit contributions
rying-0.106
my-0.106
 forth-0.106
ping-0.106
ior-0.104
Token and
Token ID290
Feature activation-5.61e-01

Pos logit contributions
 vows+0.135
apy+0.132
Mine+0.127
ades+0.118
 Prize+0.118
Neg logit contributions
my-0.064
bur-0.062
rying-0.060
i-0.054
ppa-0.054
Token ate
Token ID15063
Feature activation-1.62e+00

Pos logit contributions
 vows+0.023
 prize+0.021
 trophy+0.020
ades+0.020
 contest+0.020
Neg logit contributions
bur-0.027
ppa-0.026
rying-0.026
i-0.025
ety-0.025
Token cake
Token ID12187
Feature activation-2.00e+00

Pos logit contributions
 vows+0.061
 Prize+0.052
 contest+0.050
apy+0.049
case+0.049
Neg logit contributions
bur-0.078
ior-0.076
ind-0.074
i-0.073
my-0.073
Token.
Token ID13
Feature activation-8.57e-02

Pos logit contributions
 vows+0.091
Mine+0.089
 Prize+0.087
apy+0.086
 contest+0.080
Neg logit contributions
bur-0.086
i-0.082
ppa-0.080
my-0.078
rying-0.077
Token who
Token ID508
Feature activation-1.94e+00

Pos logit contributions
bur+0.023
rying+0.023
ppa+0.022
ind+0.021
i+0.021
Neg logit contributions
 vows-0.031
 prize-0.028
 contest-0.028
 trophy-0.027
apy-0.027
Token liked
Token ID8288
Feature activation-5.95e-01

Pos logit contributions
 vows+0.097
 prize+0.095
 trophy+0.091
 Prize+0.090
ades+0.090
Neg logit contributions
my-0.077
i-0.076
bur-0.075
ety-0.073
ppa-0.070
Token to
Token ID284
Feature activation-1.86e+00

Pos logit contributions
 vows+0.031
 prize+0.028
apy+0.027
 contest+0.027
 trophy+0.027
Neg logit contributions
bur-0.023
rying-0.022
ind-0.021
ppa-0.021
i-0.021
Token play
Token ID711
Feature activation-1.62e+00

Pos logit contributions
 vows+0.073
cakes+0.065
 Prize+0.062
 prize+0.062
ades+0.062
Neg logit contributions
bur-0.089
i-0.087
my-0.087
cker-0.085
ety-0.082
Token outside
Token ID2354
Feature activation-2.47e-01

Pos logit contributions
 vows+0.098
cakes+0.084
 Prize+0.083
 prize+0.080
apy+0.079
Neg logit contributions
rying-0.051
ishing-0.051
ind-0.050
bur-0.047
i-0.045
Token.
Token ID13
Feature activation-1.87e+00

Pos logit contributions
 vows+0.012
 prize+0.011
 trophy+0.010
cakes+0.010
 contest+0.010
Neg logit contributions
rying-0.011
bur-0.010
i-0.010
ind-0.010
ppa-0.010
Token One
Token ID1881
Feature activation+2.51e-01

Pos logit contributions
 vows+0.093
apy+0.092
ades+0.090
 prize+0.090
 trophy+0.090
Neg logit contributions
ior-0.070
my-0.068
ety-0.065
bur-0.064
i-0.061
Token day
Token ID1110
Feature activation-1.76e+00

Pos logit contributions
bur+0.012
rying+0.012
ppa+0.012
ind+0.011
i+0.011
Neg logit contributions
 vows-0.011
 prize-0.010
 contest-0.010
 trophy-0.009
apy-0.009
Token,
Token ID11
Feature activation-1.99e+00

Pos logit contributions
 vows+0.081
 trophy+0.076
 prize+0.073
 contest+0.073
case+0.071
Neg logit contributions
i-0.071
bur-0.067
my-0.065
ety-0.065
ppa-0.064
Token they
Token ID484
Feature activation-2.43e-01

Pos logit contributions
 vows+0.060
 trophy+0.054
ades+0.054
 contest+0.053
 prize+0.052
Neg logit contributions
i-0.108
bur-0.108
ety-0.105
my-0.104
ppa-0.104
Token went
Token ID1816
Feature activation-6.38e-02

Pos logit contributions
 vows+0.013
 prize+0.012
 trophy+0.012
 contest+0.012
apy+0.011
Neg logit contributions
bur-0.009
rying-0.009
ppa-0.009
i-0.009
ety-0.009
Token apple
Token ID17180
Feature activation-1.51e+00

Pos logit contributions
rying+0.024
bur+0.023
ppa+0.023
ind+0.022
i+0.022
Neg logit contributions
 vows-0.024
 prize-0.022
 contest-0.022
 trophy-0.022
cakes-0.021
Token was
Token ID373
Feature activation+2.88e-01

Pos logit contributions
 vows+0.071
 Prize+0.063
ades+0.060
 prize+0.060
 trophy+0.060
Neg logit contributions
bur-0.064
i-0.063
my-0.060
cker-0.060
ppa-0.059
Token not
Token ID407
Feature activation+5.96e-01

Pos logit contributions
bur+0.016
rying+0.015
ppa+0.015
ind+0.015
i+0.015
Neg logit contributions
 vows-0.011
 prize-0.009
 contest-0.009
 trophy-0.009
apy-0.009
Token y
Token ID331
Feature activation+1.07e-01

Pos logit contributions
bur+0.033
rying+0.033
ppa+0.032
ind+0.032
i+0.031
Neg logit contributions
 vows-0.021
 prize-0.019
 contest-0.018
 trophy-0.018
apy-0.017
Tokenummy
Token ID13513
Feature activation-3.46e-03

Pos logit contributions
bur+0.004
rying+0.004
ppa+0.004
ind+0.004
i+0.004
Neg logit contributions
 vows-0.005
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token.
Token ID13
Feature activation-2.17e+00

Pos logit contributions
 vows+0.000
 prize+0.000
 contest+0.000
 trophy+0.000
apy+0.000
Neg logit contributions
bur-0.000
rying-0.000
ppa-0.000
i-0.000
ind-0.000
Token It
Token ID632
Feature activation-1.23e+00

Pos logit contributions
 vows+0.102
 trophy+0.098
 prize+0.097
ades+0.096
 contest+0.094
Neg logit contributions
ior-0.077
ppa-0.074
 Owl-0.073
my-0.070
ety-0.070
Token was
Token ID373
Feature activation+1.67e-01

Pos logit contributions
 vows+0.057
 prize+0.051
 Prize+0.051
ades+0.050
 contest+0.050
Neg logit contributions
bur-0.054
i-0.053
my-0.051
ety-0.050
cker-0.050
Token bitter
Token ID12922
Feature activation+1.90e-01

Pos logit contributions
bur+0.009
rying+0.009
ppa+0.009
ind+0.009
i+0.009
Neg logit contributions
 vows-0.006
 prize-0.005
 contest-0.005
 trophy-0.005
cakes-0.005
Token and
Token ID290
Feature activation-2.68e-01

Pos logit contributions
bur+0.009
rying+0.008
ppa+0.008
ind+0.008
i+0.008
Neg logit contributions
 vows-0.009
 prize-0.008
 contest-0.008
 trophy-0.008
cakes-0.008
Token hard
Token ID1327
Feature activation-3.92e-01

Pos logit contributions
 vows+0.011
 prize+0.010
 contest+0.010
 trophy+0.009
ades+0.009
Neg logit contributions
bur-0.013
rying-0.013
ppa-0.013
i-0.013
ind-0.012
Token kept
Token ID4030
Feature activation+3.38e-01

Pos logit contributions
 vows+0.033
 prize+0.030
 contest+0.029
 trophy+0.029
apy+0.028
Neg logit contributions
bur-0.035
i-0.034
ppa-0.034
rying-0.034
ind-0.032
Token rubbing
Token ID27714
Feature activation+8.65e-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-0.012
 contest-0.012
 trophy-0.012
apy-0.012
Token,
Token ID11
Feature activation+1.53e+00

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-0.003
 contest-0.003
 trophy-0.003
cakes-0.003
Token and
Token ID290
Feature activation+9.47e-01

Pos logit contributions
ind+0.075
bur+0.074
rying+0.073
ppa+0.072
ior+0.069
Neg logit contributions
 vows-0.059
 contest-0.056
apy-0.055
 prize-0.054
 trophy-0.054
Token the
Token ID262
Feature activation+4.73e-01

Pos logit contributions
bur+0.044
rying+0.043
ppa+0.043
ind+0.042
ior+0.040
Neg logit contributions
 vows-0.042
apy-0.038
 contest-0.038
 prize-0.037
 trophy-0.036
Token colors
Token ID7577
Feature activation-2.67e+00

Pos logit contributions
bur+0.026
rying+0.025
ppa+0.025
ind+0.024
i+0.024
Neg logit contributions
 vows-0.018
 prize-0.016
 contest-0.015
 trophy-0.015
cakes-0.014
Token started
Token ID2067
Feature activation-6.89e-01

Pos logit contributions
 vows+0.107
 Prize+0.101
 prize+0.093
 festival+0.091
 contest+0.091
Neg logit contributions
i-0.130
bur-0.124
my-0.123
rying-0.122
cker-0.118
Token to
Token ID284
Feature activation-3.41e-01

Pos logit contributions
 vows+0.035
 prize+0.031
 trophy+0.031
 contest+0.031
 Prize+0.030
Neg logit contributions
rying-0.027
bur-0.027
i-0.026
ppa-0.026
ind-0.025
Token look
Token ID804
Feature activation-6.40e-01

Pos logit contributions
 vows+0.012
 prize+0.010
cakes+0.010
 contest+0.010
 trophy+0.010
Neg logit contributions
bur-0.019
rying-0.019
ppa-0.018
i-0.018
cker-0.018
Token more
Token ID517
Feature activation+8.87e-01

Pos logit contributions
 vows+0.029
 prize+0.026
 contest+0.026
 Prize+0.025
cakes+0.025
Neg logit contributions
rying-0.029
i-0.027
bur-0.027
ppa-0.027
ind-0.027
Token and
Token ID290
Feature activation+8.08e-01

Pos logit contributions
bur+0.049
rying+0.047
ppa+0.047
ind+0.045
gie+0.044
Neg logit contributions
 vows-0.032
 prize-0.029
 trophy-0.029
 contest-0.029
cakes-0.027
Token polite
Token ID23507
Feature activation+2.91e-01

Pos logit contributions
bur+0.066
ind+0.064
rying+0.063
ppa+0.062
ior+0.061
Neg logit contributions
 vows-0.046
 prize-0.045
 contest-0.044
 trophy-0.043
 joke-0.041
Token.
Token ID13
Feature activation+5.21e-01

Pos logit contributions
bur+0.015
rying+0.014
ppa+0.014
ind+0.014
i+0.014
Neg logit contributions
 vows-0.012
 prize-0.011
 contest-0.010
 trophy-0.010
cakes-0.010
Token He
Token ID679
Feature activation+9.39e-01

Pos logit contributions
rying+0.031
bur+0.031
ppa+0.030
ind+0.030
i+0.030
Neg logit contributions
 vows-0.016
 prize-0.014
 contest-0.014
cakes-0.014
 trophy-0.013
Token did
Token ID750
Feature activation-8.54e-01

Pos logit contributions
rying+0.047
bur+0.046
ppa+0.044
ind+0.043
ior+0.042
Neg logit contributions
 vows-0.040
 prize-0.034
 contest-0.033
 trophy-0.033
 joke-0.032
Token not
Token ID407
Feature activation-8.03e-02

Pos logit contributions
 vows+0.044
cakes+0.040
ades+0.038
apy+0.038
 Prize+0.038
Neg logit contributions
bur-0.034
rying-0.033
i-0.033
ppa-0.033
my-0.031
Token say
Token ID910
Feature activation-2.36e+00

Pos logit contributions
 vows+0.003
 prize+0.003
 contest+0.003
apy+0.003
cakes+0.003
Neg logit contributions
bur-0.004
rying-0.004
ppa-0.004
i-0.004
ind-0.004
Token hello
Token ID23748
Feature activation+1.66e-01

Pos logit contributions
 vows+0.116
cakes+0.108
case+0.103
apy+0.102
Mine+0.102
Neg logit contributions
 owl-0.082
 Owl-0.081
bur-0.080
i-0.078
ppa-0.076
Token or
Token ID393
Feature activation+1.71e-01

Pos logit contributions
bur+0.008
rying+0.007
ppa+0.007
ind+0.007
i+0.007
Neg logit contributions
 vows-0.007
 prize-0.007
 contest-0.007
 trophy-0.007
cakes-0.006
Token please
Token ID3387
Feature activation-8.81e-01

Pos logit contributions
bur+0.009
rying+0.009
ppa+0.009
ind+0.008
i+0.008
Neg logit contributions
 vows-0.007
 prize-0.006
 contest-0.006
 trophy-0.006
cakes-0.005
Token or
Token ID393
Feature activation+8.83e-02

Pos logit contributions
 vows+0.041
cakes+0.037
apy+0.037
 trophy+0.036
 prize+0.036
Neg logit contributions
rying-0.038
bur-0.037
ppa-0.036
i-0.036
ety-0.035
Token thank
Token ID5875
Feature activation+1.13e+00

Pos logit contributions
bur+0.005
rying+0.005
ppa+0.005
i+0.004
ind+0.004
Neg logit contributions
 vows-0.003
 prize-0.003
 contest-0.003
 trophy-0.003
cakes-0.003