TOP ACTIVATIONS
MAX = 7.155

the cake and have a big hug . <|endoftext|> L ily
they both always had a big smile on their faces .
achievement . She had a big smile on her face and
. They all had a big party to celebrate . <|endoftext|>
each other and had a big smile .
. They all had a big party to celebrate the volcano
happy . She had a big party with her friends .
Max nod and say , " Deal , mom . Thank
married . They had a big party with their toys .
park . They have a big toy taxi . They are
ily and Tom had a big , happy marriage . They
and the mouse had a big disagreement . Then , they
the strawberry and had a big party .
back home and had a big dinner . Tim and his
ute . She had a big smile on her face because
She says he has a big imagination . He says he
You can both have a big piece ." She cut the
chair . She had a big , happy smile on her
Carl . They had a big party to celebrate . <|endoftext|>
L ila and R ani smiled and hugged each other .

MIN ACTIVATIONS
MIN = -10.666

be enough to make the ostr ich happy , so he
the zoo to see the ostr ich . She observed it
Ben wanted to touch the ostr ich , but his mom
to let him touch the ostr ich . His dad said
me introduce you to the ostr ich . This is M
if they could see the ostr ich . "
apple and slowly approached the ostr ich .
went outside and saw the ostr ich walking around . "
so excited and asked the ostr ich what was happening .
They wanted to see the ostr ich . They
want to see the big ostr ich with the long neck
be funny to tease the ostr ich , so he prepared
" Can we ride the ostr ich , mom ?" Ben
Before the race , the ostr ich felt embarrassed because he
if he could borrow the ostr ich .
I want to ride the ostr ich !" Ben said .
," Doug said to the ostr ich . The
his favorite animal was the ostr ich . The ostr ich
ily wanted to feed the ostr ich too . She asked
the race started , the ostr ich ran faster than he

INTERVAL 2.700 - 7.155
CONTAINS 5.230%

was scared . They asked Lily why she gave
are the best costumes ever . They thank their mom and
the tower like it 's a king !" he said .
all day . He had a lot of toys and treats
himself clean . He felt much better !

INTERVAL -1.755 - 2.700
CONTAINS 80.879%

. L ily said , " Let 's find
felt scared and sad . They did not know how to
from inside . It was a loud scream !
to Jimmy , " Don 't be scared , I won
told her she could use it for her pretend play .

INTERVAL -6.210 - -1.755
CONTAINS 13.844%

top . " Let 's go sled ding !" Anna said
wise owl looked at the bird 's wing and sighed .
there . She asked her mother to go but her mother
, they see a big club on the grass . It
ily was sad because she couldn 't stand up to play

INTERVAL -10.666 - -6.210
CONTAINS 0.047%

in the rain . The ostr ich was wet from the
owers in his hands . G ently , Sam reached out
to get rid of the fle a . The
, duck ," said the oct opus . " Do you
joy , knowing now why m ama had been so secretive
Token the
Token ID262
Feature activation+2.58e+00

Pos logit contributions
 likes+0.038
 They+0.033
 liked+0.028
 fun+0.025
 and+0.025
Neg logit contributions
erk-0.091
otion-0.090
illa-0.089
ow-0.089
ately-0.088
Token cake
Token ID12187
Feature activation+8.89e-01

Pos logit contributions
 They+0.061
 likes+0.054
 and+0.052
 with+0.049
+0.049
Neg logit contributions
otion-0.060
iqu-0.059
erk-0.058
wen-0.057
unct-0.057
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
 likes+0.006
 They+0.005
 liked+0.003
Let+0.003
 fun+0.002
Neg logit contributions
erk-0.035
ow-0.035
ately-0.034
illa-0.034
otion-0.034
Token have
Token ID423
Feature activation+2.78e+00

Pos logit contributions
 likes+0.020
 They+0.019
 and+0.019
 with+0.017
 nice+0.016
Neg logit contributions
ately-0.036
otion-0.036
erk-0.036
iqu-0.036
ow-0.035
Token a
Token ID257
Feature activation+5.80e+00

Pos logit contributions
 likes+0.046
 They+0.039
 with+0.035
 and+0.034
 than+0.034
Neg logit contributions
abella-0.076
erk-0.074
 hesitation-0.073
wen-0.071
abel-0.070
Token big
Token ID1263
Feature activation+7.16e+00

Pos logit contributions
 They+0.075
 likes+0.070
 and+0.064
 with+0.060
 holes+0.054
Neg logit contributions
iqu-0.191
erk-0.190
 hesitation-0.184
otion-0.184
ous-0.181
Token hug
Token ID16225
Feature activation+2.19e+00

Pos logit contributions
 They+0.159
 likes+0.141
They+0.138
 with+0.133
 shapes+0.130
Neg logit contributions
erk-0.168
 hesitation-0.165
ow-0.163
otion-0.163
ama-0.156
Token.
Token ID13
Feature activation+2.68e+00

Pos logit contributions
 likes+0.015
 and+0.014
 They+0.013
 with+0.010
 liked+0.008
Neg logit contributions
iqu-0.091
ately-0.089
otion-0.089
wen-0.088
erk-0.088
Token<|endoftext|>
Token ID50256
Feature activation+5.39e-01

Pos logit contributions
 likes+0.020
 and+0.019
 with+0.016
 games+0.015
 nice+0.014
Neg logit contributions
otion-0.103
iqu-0.101
antis-0.099
erk-0.099
wen-0.099
TokenL
Token ID43
Feature activation-1.45e+00

Pos logit contributions
 likes+0.010
 games+0.009
 fair+0.009
 nice+0.009
 They+0.009
Neg logit contributions
otion-0.015
izz-0.014
ow-0.014
erk-0.013
antis-0.013
Tokenily
Token ID813
Feature activation+3.29e+00

Pos logit contributions
iqu+0.035
ately+0.033
otion+0.033
used+0.033
ous+0.032
Neg logit contributions
 and-0.036
 likes-0.036
 They-0.035
 with-0.034
-0.032
Token they
Token ID484
Feature activation+3.82e+00

Pos logit contributions
 likes+0.009
 They+0.008
 and+0.008
 with+0.008
 nice+0.007
Neg logit contributions
iqu-0.018
ately-0.018
otion-0.018
erk-0.018
wen-0.018
Token both
Token ID1111
Feature activation+2.96e+00

Pos logit contributions
 likes+0.060
 They+0.059
 and+0.058
 with+0.054
 nice+0.049
Neg logit contributions
iqu-0.121
ately-0.119
otion-0.119
wen-0.118
erk-0.118
Token always
Token ID1464
Feature activation+1.02e+00

Pos logit contributions
 likes+0.040
 They+0.040
 and+0.040
 with+0.037
 nice+0.033
Neg logit contributions
erk-0.096
ately-0.095
iqu-0.094
ous-0.094
ow-0.094
Token had
Token ID550
Feature activation+2.40e+00

Pos logit contributions
 likes+0.017
 They+0.017
 and+0.016
 with+0.015
+0.014
Neg logit contributions
ately-0.031
iqu-0.031
erk-0.030
otion-0.030
used-0.030
Token a
Token ID257
Feature activation+5.81e+00

Pos logit contributions
 likes+0.039
 They+0.028
 and+0.026
 boy+0.026
 with+0.025
Neg logit contributions
ow-0.069
 hesitation-0.069
ately-0.068
erk-0.068
iqu-0.066
Token big
Token ID1263
Feature activation+6.87e+00

Pos logit contributions
 likes+0.071
 They+0.070
 and+0.061
 with+0.060
 shapes+0.052
Neg logit contributions
iqu-0.200
erk-0.194
 hesitation-0.189
ately-0.186
ous-0.185
Token smile
Token ID8212
Feature activation+1.27e+00

Pos logit contributions
 They+0.125
 likes+0.121
 with+0.116
 shapes+0.110
They+0.110
Neg logit contributions
 hesitation-0.181
erk-0.180
ow-0.176
tha-0.171
ama-0.170
Token on
Token ID319
Feature activation+1.87e+00

Pos logit contributions
 and+0.013
 likes+0.012
 They+0.012
 with+0.011
 liked+0.009
Neg logit contributions
iqu-0.049
otion-0.048
ately-0.048
wen-0.048
erk-0.047
Token their
Token ID511
Feature activation-6.22e-01

Pos logit contributions
 likes+0.025
 and+0.020
 liked+0.019
 boy+0.018
 They+0.018
Neg logit contributions
iqu-0.061
ow-0.060
wen-0.059
otion-0.058
ately-0.058
Token faces
Token ID6698
Feature activation+2.24e+00

Pos logit contributions
ately+0.018
iqu+0.018
unct+0.018
 hesitation+0.017
tha+0.017
Neg logit contributions
 likes-0.011
 They-0.011
 with-0.010
 and-0.009
-0.009
Token.
Token ID13
Feature activation+2.01e+00

Pos logit contributions
 likes+0.015
 and+0.014
 They+0.014
 with+0.011
 liked+0.008
Neg logit contributions
iqu-0.093
otion-0.091
ately-0.091
wen-0.091
erk-0.090
Token achievement
Token ID13293
Feature activation+1.40e+00

Pos logit contributions
iqu+0.023
ately+0.022
otion+0.022
erk+0.022
wen+0.022
Neg logit contributions
 likes-0.010
 They-0.009
 and-0.009
 with-0.008
 liked-0.007
Token.
Token ID13
Feature activation+4.59e-01

Pos logit contributions
 likes+0.015
 They+0.014
 and+0.011
 green+0.010
 nice+0.010
Neg logit contributions
ately-0.051
ous-0.050
otion-0.050
wen-0.050
erk-0.050
Token She
Token ID1375
Feature activation+2.36e+00

Pos logit contributions
 likes+0.006
 and+0.006
 with+0.006
 games+0.005
 nice+0.005
Neg logit contributions
otion-0.015
used-0.015
ately-0.015
iqu-0.015
ous-0.015
Token had
Token ID550
Feature activation+1.93e+00

Pos logit contributions
 They+0.042
 likes+0.041
 games+0.036
 holes+0.036
 nice+0.035
Neg logit contributions
ately-0.066
erk-0.065
wen-0.065
ous-0.064
iqu-0.064
Token a
Token ID257
Feature activation+5.90e+00

Pos logit contributions
 likes+0.039
 They+0.037
 and+0.034
 with+0.033
 grass+0.030
Neg logit contributions
ately-0.049
wen-0.049
erk-0.049
 hesitation-0.048
iqu-0.048
Token big
Token ID1263
Feature activation+6.80e+00

Pos logit contributions
 They+0.088
 likes+0.084
 and+0.074
 with+0.071
 grass+0.065
Neg logit contributions
iqu-0.187
erk-0.180
 hesitation-0.180
antis-0.172
tha-0.172
Token smile
Token ID8212
Feature activation+1.77e+00

Pos logit contributions
 They+0.138
 likes+0.129
They+0.125
+0.114
 with+0.114
Neg logit contributions
 hesitation-0.171
erk-0.168
iqu-0.162
tha-0.159
otion-0.156
Token on
Token ID319
Feature activation+2.29e+00

Pos logit contributions
 likes+0.013
 and+0.013
 They+0.012
 with+0.010
 liked+0.008
Neg logit contributions
iqu-0.072
ately-0.071
otion-0.071
wen-0.070
erk-0.070
Token her
Token ID607
Feature activation-1.48e+00

Pos logit contributions
 likes+0.045
 They+0.040
 and+0.036
 boy+0.036
 liked+0.036
Neg logit contributions
otion-0.061
ately-0.060
iqu-0.059
wen-0.059
used-0.059
Token face
Token ID1986
Feature activation+8.10e-01

Pos logit contributions
ately+0.047
iqu+0.046
erk+0.045
ous+0.045
otion+0.045
Neg logit contributions
 likes-0.023
 They-0.023
 and-0.020
 with-0.019
 liked-0.019
Token and
Token ID290
Feature activation+1.06e+00

Pos logit contributions
 and+0.003
 likes+0.003
 They+0.002
 with+0.002
 liked+0.000
Neg logit contributions
iqu-0.037
otion-0.036
ately-0.036
wen-0.036
erk-0.035
Token.
Token ID13
Feature activation+1.78e+00

Pos logit contributions
 likes+0.026
 They+0.022
 liked+0.017
 fun+0.017
 nice+0.016
Neg logit contributions
ow-0.074
erk-0.072
illa-0.072
iqu-0.072
ately-0.072
Token They
Token ID1119
Feature activation+3.90e+00

Pos logit contributions
 likes+0.019
 nice+0.017
 games+0.016
 fair+0.016
 pretty+0.016
Neg logit contributions
ous-0.062
ow-0.060
otion-0.059
ama-0.059
utt-0.058
Token all
Token ID477
Feature activation+3.77e+00

Pos logit contributions
 likes+0.059
 They+0.057
 and+0.056
 with+0.051
 nice+0.047
Neg logit contributions
iqu-0.127
ately-0.126
otion-0.125
erk-0.123
wen-0.123
Token had
Token ID550
Feature activation+2.97e+00

Pos logit contributions
 likes+0.064
 They+0.063
 and+0.062
 with+0.059
 games+0.054
Neg logit contributions
erk-0.109
ous-0.106
ow-0.105
otion-0.105
iqu-0.104
Token a
Token ID257
Feature activation+5.62e+00

Pos logit contributions
 likes+0.060
 They+0.048
 girl+0.045
 Friends+0.044
 boy+0.042
Neg logit contributions
ow-0.070
 hesitation-0.069
erk-0.069
ately-0.067
illa-0.064
Token big
Token ID1263
Feature activation+6.75e+00

Pos logit contributions
 They+0.075
 likes+0.073
 and+0.065
 with+0.060
 grass+0.053
Neg logit contributions
iqu-0.186
erk-0.178
 hesitation-0.173
antis-0.172
ama-0.172
Token party
Token ID2151
Feature activation+2.17e+00

Pos logit contributions
 They+0.131
 likes+0.122
They+0.117
 with+0.114
 shapes+0.108
Neg logit contributions
 hesitation-0.168
erk-0.166
iqu-0.162
otion-0.158
tha-0.158
Token to
Token ID284
Feature activation-4.48e-01

Pos logit contributions
 likes+0.026
 They+0.022
 grass+0.018
 green+0.017
 holes+0.016
Neg logit contributions
ately-0.076
ow-0.075
ous-0.075
erk-0.075
icking-0.075
Token celebrate
Token ID10648
Feature activation+1.88e+00

Pos logit contributions
iqu+0.015
ately+0.015
otion+0.015
wen+0.015
erk+0.015
Neg logit contributions
 likes-0.006
 and-0.006
 They-0.006
 with-0.005
 liked-0.005
Token.
Token ID13
Feature activation+2.24e+00

Pos logit contributions
 likes+0.023
 They+0.019
 liked+0.014
 green+0.014
 grass+0.013
Neg logit contributions
ately-0.064
erk-0.063
illa-0.063
icking-0.062
wen-0.062
Token<|endoftext|>
Token ID50256
Feature activation+1.40e+00

Pos logit contributions
 likes+0.029
 games+0.025
 nice+0.025
 fair+0.024
 shapes+0.024
Neg logit contributions
otion-0.071
ow-0.071
ous-0.070
erk-0.070
izz-0.069
Token each
Token ID1123
Feature activation+1.06e+00

Pos logit contributions
 likes+0.019
 They+0.013
 fun+0.010
 nice+0.010
 green+0.009
Neg logit contributions
ately-0.099
ous-0.093
ow-0.093
otion-0.093
erk-0.092
Token other
Token ID584
Feature activation+2.68e+00

Pos logit contributions
 likes+0.014
 They+0.014
 and+0.012
 with+0.012
 fun+0.011
Neg logit contributions
ately-0.035
otion-0.035
wen-0.034
erk-0.034
iqu-0.034
Token and
Token ID290
Feature activation+1.19e+00

Pos logit contributions
 likes+0.022
 They+0.018
 liked+0.012
 fun+0.011
+0.010
Neg logit contributions
ately-0.103
ow-0.102
ous-0.101
erk-0.101
icking-0.100
Token had
Token ID550
Feature activation+2.87e+00

Pos logit contributions
 likes+0.018
 They+0.018
 and+0.018
 with+0.016
 nice+0.015
Neg logit contributions
iqu-0.038
ately-0.038
otion-0.038
wen-0.037
erk-0.037
Token a
Token ID257
Feature activation+5.71e+00

Pos logit contributions
 likes+0.059
 They+0.047
 than+0.047
 with+0.046
 boy+0.046
Neg logit contributions
abella-0.071
erk-0.069
wen-0.069
ow-0.068
 hesitation-0.064
Token big
Token ID1263
Feature activation+6.74e+00

Pos logit contributions
 They+0.071
 likes+0.071
 and+0.064
 with+0.059
 liked+0.050
Neg logit contributions
iqu-0.198
erk-0.192
 hesitation-0.188
ately-0.188
ous-0.187
Token smile
Token ID8212
Feature activation+1.82e+00

Pos logit contributions
 They+0.146
 likes+0.136
 with+0.126
They+0.122
 and+0.121
Neg logit contributions
 hesitation-0.170
erk-0.166
iqu-0.161
ow-0.160
otion-0.157
Token.
Token ID13
Feature activation+2.16e+00

Pos logit contributions
 and+0.019
 likes+0.019
 They+0.018
 with+0.016
 liked+0.013
Neg logit contributions
iqu-0.069
otion-0.068
ately-0.068
wen-0.067
used-0.066
Token
Token ID220
Feature activation+2.19e-01

Pos logit contributions
 games+0.030
 likes+0.030
 fair+0.029
 fun+0.029
 nice+0.027
Neg logit contributions
otion-0.065
ous-0.063
ama-0.062
ately-0.061
ancer-0.061
Token
Token ID198
Feature activation+1.31e+00

Pos logit contributions
 likes+0.002
 and+0.001
 games+0.001
 green+0.001
 nice+0.001
Neg logit contributions
otion-0.009
iqu-0.009
wen-0.009
erk-0.008
ow-0.008
Token
Token ID198
Feature activation-4.42e-02

Pos logit contributions
 likes+0.016
 fair+0.012
 and+0.012
 than+0.012
 piles+0.012
Neg logit contributions
otion-0.045
wen-0.044
izz-0.044
ous-0.043
erk-0.043
Token.
Token ID13
Feature activation+1.48e+00

Pos logit contributions
iqu+0.002
ately+0.002
erk+0.002
otion+0.002
ous+0.002
Neg logit contributions
 likes-0.001
 They-0.001
 and-0.001
 liked-0.001
 with-0.001
Token They
Token ID1119
Feature activation+3.65e+00

Pos logit contributions
 likes+0.013
 and+0.011
 nice+0.010
 with+0.010
 games+0.010
Neg logit contributions
ately-0.056
otion-0.056
iqu-0.055
erk-0.055
ous-0.055
Token all
Token ID477
Feature activation+3.46e+00

Pos logit contributions
 likes+0.057
 They+0.056
 and+0.055
 with+0.051
 nice+0.046
Neg logit contributions
iqu-0.117
ately-0.116
otion-0.115
wen-0.114
erk-0.114
Token had
Token ID550
Feature activation+2.52e+00

Pos logit contributions
 likes+0.057
 They+0.056
 and+0.055
 with+0.052
 games+0.048
Neg logit contributions
erk-0.103
ately-0.102
ous-0.101
iqu-0.101
ow-0.101
Token a
Token ID257
Feature activation+5.73e+00

Pos logit contributions
 likes+0.045
 They+0.037
 with+0.033
 and+0.033
 boy+0.030
Neg logit contributions
 hesitation-0.071
ately-0.069
ow-0.069
wen-0.068
iqu-0.068
Token big
Token ID1263
Feature activation+6.73e+00

Pos logit contributions
 They+0.082
 likes+0.081
 and+0.071
 with+0.068
 liked+0.060
Neg logit contributions
iqu-0.187
erk-0.180
 hesitation-0.177
wen-0.173
ama-0.173
Token party
Token ID2151
Feature activation+2.36e+00

Pos logit contributions
 They+0.136
 likes+0.130
 with+0.119
They+0.118
 and+0.113
Neg logit contributions
 hesitation-0.169
erk-0.168
iqu-0.161
ow-0.161
otion-0.159
Token to
Token ID284
Feature activation-2.94e-01

Pos logit contributions
 likes+0.025
 They+0.022
 grass+0.017
 green+0.016
 holes+0.015
Neg logit contributions
ous-0.087
ately-0.086
erk-0.085
ow-0.084
icking-0.084
Token celebrate
Token ID10648
Feature activation+2.06e+00

Pos logit contributions
iqu+0.010
ately+0.009
otion+0.009
wen+0.009
erk+0.009
Neg logit contributions
 likes-0.004
 and-0.004
 They-0.004
 with-0.004
 liked-0.004
Token the
Token ID262
Feature activation+4.87e-01

Pos logit contributions
 likes+0.025
 They+0.022
 green+0.016
 liked+0.016
 holes+0.015
Neg logit contributions
ately-0.070
erk-0.069
ous-0.068
illa-0.068
wen-0.067
Token volcano
Token ID32410
Feature activation+1.00e-01

Pos logit contributions
 They+0.007
 likes+0.007
 and+0.007
 with+0.006
 liked+0.006
Neg logit contributions
iqu-0.016
otion-0.015
ately-0.015
erk-0.015
antis-0.015
Token happy
Token ID3772
Feature activation+3.77e+00

Pos logit contributions
 They+0.032
 likes+0.031
 and+0.028
 games+0.025
 ball+0.024
Neg logit contributions
 hesitation-0.068
iqu-0.068
otion-0.068
erk-0.066
ow-0.066
Token.
Token ID13
Feature activation+1.60e+00

Pos logit contributions
 likes+0.050
 They+0.046
 proper+0.036
Let+0.035
 bases+0.035
Neg logit contributions
ous-0.120
otion-0.119
ately-0.117
ow-0.114
 hesitation-0.113
Token She
Token ID1375
Feature activation+2.79e+00

Pos logit contributions
 likes+0.020
 and+0.019
 with+0.018
 games+0.017
 nice+0.016
Neg logit contributions
otion-0.055
iqu-0.054
ately-0.053
antis-0.053
ow-0.052
Token had
Token ID550
Feature activation+2.21e+00

Pos logit contributions
 They+0.048
 likes+0.042
 games+0.041
 piles+0.041
 with+0.040
Neg logit contributions
wen-0.077
erk-0.077
iqu-0.076
ately-0.076
ous-0.075
Token a
Token ID257
Feature activation+5.58e+00

Pos logit contributions
 likes+0.036
 They+0.035
 and+0.033
 with+0.029
 boy+0.026
Neg logit contributions
 hesitation-0.064
ow-0.064
iqu-0.063
wen-0.063
erk-0.063
Token big
Token ID1263
Feature activation+6.73e+00

Pos logit contributions
 They+0.059
 likes+0.057
 and+0.053
 with+0.048
 liked+0.038
Neg logit contributions
iqu-0.204
erk-0.197
otion-0.196
 hesitation-0.195
wen-0.194
Token party
Token ID2151
Feature activation+1.91e+00

Pos logit contributions
 They+0.145
 likes+0.132
They+0.126
 with+0.125
 and+0.120
Neg logit contributions
 hesitation-0.162
otion-0.159
erk-0.158
ow-0.157
tha-0.151
Token with
Token ID351
Feature activation+7.53e-01

Pos logit contributions
 likes+0.019
 They+0.019
 grass+0.013
 and+0.012
 green+0.012
Neg logit contributions
ow-0.069
ately-0.069
otion-0.068
erk-0.068
ous-0.068
Token her
Token ID607
Feature activation-1.19e-01

Pos logit contributions
 and+0.010
 likes+0.009
 They+0.009
 with+0.009
 nice+0.008
Neg logit contributions
iqu-0.027
otion-0.027
ately-0.027
wen-0.026
used-0.026
Token friends
Token ID2460
Feature activation+2.44e+00

Pos logit contributions
iqu+0.004
ately+0.004
otion+0.004
erk+0.004
wen+0.004
Neg logit contributions
 likes-0.002
 They-0.002
 and-0.002
 with-0.002
 liked-0.001
Token.
Token ID13
Feature activation+2.24e+00

Pos logit contributions
 likes+0.020
 They+0.019
 and+0.016
 with+0.013
 nice+0.012
Neg logit contributions
ately-0.094
iqu-0.094
otion-0.094
used-0.093
erk-0.092
Token Max
Token ID5436
Feature activation+2.82e+00

Pos logit contributions
iqu+0.002
wen+0.002
ately+0.002
otion+0.002
ous+0.002
Neg logit contributions
 and-0.001
 They-0.001
 likes-0.001
 with-0.001
-0.001
Token nod
Token ID18666
Feature activation+5.24e+00

Pos logit contributions
 They+0.059
 likes+0.058
 with+0.056
 and+0.056
 games+0.055
Neg logit contributions
ow-0.068
iqu-0.066
unct-0.065
erk-0.065
 hesitation-0.065
Token and
Token ID290
Feature activation+1.24e+00

Pos logit contributions
 likes+0.038
 They+0.028
 games+0.025
 grass+0.023
 green+0.021
Neg logit contributions
ately-0.202
erk-0.199
otion-0.199
ow-0.198
ous-0.195
Token say
Token ID910
Feature activation+1.22e+00

Pos logit contributions
 likes+0.026
 They+0.025
 and+0.024
 with+0.023
 nice+0.022
Neg logit contributions
iqu-0.033
ately-0.032
erk-0.032
unct-0.031
otion-0.031
Token,
Token ID11
Feature activation+2.22e+00

Pos logit contributions
 likes+0.015
 They+0.014
 and+0.014
 with+0.013
 liked+0.011
Neg logit contributions
iqu-0.043
ately-0.043
otion-0.042
ous-0.041
erk-0.041
Token "
Token ID366
Feature activation+6.73e+00

Pos logit contributions
 likes+0.022
 They+0.020
 and+0.020
 with+0.017
 fun+0.015
Neg logit contributions
otion-0.082
iqu-0.082
ately-0.082
ous-0.081
erk-0.080
TokenDeal
Token ID45776
Feature activation+2.70e+00

Pos logit contributions
 and+0.139
 They+0.128
 piles+0.125
 likes+0.125
 holes+0.123
Neg logit contributions
iqu-0.157
mallow-0.156
ately-0.154
wen-0.154
tha-0.153
Token,
Token ID11
Feature activation+1.39e+00

Pos logit contributions
 likes+0.033
 They+0.031
 and+0.029
 liked+0.025
 with+0.025
Neg logit contributions
ately-0.093
ous-0.092
otion-0.092
iqu-0.092
used-0.092
Token mom
Token ID1995
Feature activation+1.58e+00

Pos logit contributions
 likes+0.031
 They+0.030
 and+0.030
 with+0.028
 liked+0.027
Neg logit contributions
iqu-0.034
otion-0.034
ately-0.034
erk-0.033
wen-0.033
Token.
Token ID13
Feature activation+4.83e+00

Pos logit contributions
 likes+0.017
 They+0.017
 grass+0.015
 games+0.015
 holes+0.015
Neg logit contributions
ous-0.054
ow-0.053
illa-0.053
erk-0.053
ately-0.053
Token Thank
Token ID6952
Feature activation+1.17e+00

Pos logit contributions
 and+0.085
 likes+0.077
 different+0.074
 nice+0.074
 with+0.074
Neg logit contributions
ately-0.135
otion-0.133
used-0.133
ous-0.133
iqu-0.132
Token married
Token ID6405
Feature activation+1.03e+00

Pos logit contributions
iqu+0.009
ow+0.009
ous+0.009
aro+0.009
ately+0.009
Neg logit contributions
 likes-0.005
 They-0.005
 and-0.004
 with-0.004
 liked-0.004
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
 likes+0.010
 They+0.010
 and+0.007
 green+0.007
 liked+0.006
Neg logit contributions
ately-0.037
ous-0.036
ow-0.036
illa-0.036
erk-0.035
Token They
Token ID1119
Feature activation+3.78e+00

Pos logit contributions
 likes+0.011
 and+0.009
 with+0.008
 nice+0.008
 liked+0.007
Neg logit contributions
otion-0.036
iqu-0.036
ately-0.036
wen-0.036
erk-0.035
Token had
Token ID550
Feature activation+2.68e+00

Pos logit contributions
 likes+0.059
 They+0.058
 and+0.056
 with+0.052
 nice+0.047
Neg logit contributions
iqu-0.118
ately-0.118
otion-0.117
erk-0.115
wen-0.115
Token a
Token ID257
Feature activation+5.34e+00

Pos logit contributions
 likes+0.045
 They+0.038
 and+0.034
 with+0.034
 grass+0.031
Neg logit contributions
 hesitation-0.074
ow-0.073
erk-0.072
abella-0.071
wen-0.070
Token big
Token ID1263
Feature activation+6.70e+00

Pos logit contributions
 They+0.069
 likes+0.067
 and+0.063
 with+0.060
 shapes+0.050
Neg logit contributions
iqu-0.173
 hesitation-0.166
erk-0.165
tha-0.164
wen-0.164
Token party
Token ID2151
Feature activation+1.97e+00

Pos logit contributions
 They+0.133
They+0.120
 likes+0.117
 with+0.115
Let+0.110
Neg logit contributions
 hesitation-0.164
tha-0.159
otion-0.158
erk-0.157
ow-0.156
Token with
Token ID351
Feature activation+7.40e-01

Pos logit contributions
 likes+0.020
 They+0.018
 grass+0.014
 holes+0.013
 green+0.013
Neg logit contributions
ous-0.070
ow-0.070
ately-0.070
erk-0.068
icking-0.068
Token their
Token ID511
Feature activation+6.25e-01

Pos logit contributions
 likes+0.009
 They+0.009
 and+0.009
 with+0.008
 liked+0.007
Neg logit contributions
iqu-0.026
ately-0.025
otion-0.025
wen-0.025
erk-0.025
Token toys
Token ID14958
Feature activation+1.97e+00

Pos logit contributions
 They+0.008
 likes+0.008
 and+0.008
 with+0.007
 liked+0.006
Neg logit contributions
iqu-0.021
ately-0.020
aro-0.020
ous-0.020
erk-0.020
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
 likes+0.009
 They+0.008
 and+0.005
 with+0.003
 nice+0.003
Neg logit contributions
ately-0.083
iqu-0.083
otion-0.082
ous-0.082
erk-0.081
Token park
Token ID3952
Feature activation+1.15e+00

Pos logit contributions
 They+0.036
 likes+0.036
 and+0.033
 than+0.032
 with+0.032
Neg logit contributions
iqu-0.057
wen-0.055
otion-0.055
antis-0.055
unct-0.055
Token.
Token ID13
Feature activation+2.81e+00

Pos logit contributions
 likes+0.012
 They+0.011
 and+0.009
 nice+0.008
 pretty+0.008
Neg logit contributions
ow-0.040
ately-0.040
erk-0.040
otion-0.040
aro-0.038
Token They
Token ID1119
Feature activation+3.67e+00

Pos logit contributions
 likes+0.017
 and+0.015
 with+0.013
 nice+0.010
 fair+0.010
Neg logit contributions
otion-0.107
erk-0.104
iqu-0.104
antis-0.104
ately-0.104
Token have
Token ID423
Feature activation+2.45e+00

Pos logit contributions
 They+0.060
 and+0.056
 likes+0.056
 with+0.055
 games+0.050
Neg logit contributions
erk-0.102
otion-0.101
ow-0.101
 hesitation-0.099
iqu-0.099
Token a
Token ID257
Feature activation+5.47e+00

Pos logit contributions
 likes+0.036
 They+0.033
 with+0.028
 shows+0.028
 But+0.026
Neg logit contributions
 hesitation-0.072
ow-0.068
erk-0.066
 injuries-0.066
abella-0.065
Token big
Token ID1263
Feature activation+6.66e+00

Pos logit contributions
 They+0.065
 likes+0.063
 and+0.059
 with+0.058
 than+0.047
Neg logit contributions
iqu-0.178
erk-0.175
 hesitation-0.173
otion-0.172
wen-0.170
Token toy
Token ID13373
Feature activation+1.60e+00

Pos logit contributions
 They+0.111
 with+0.101
 likes+0.100
They+0.094
+0.090
Neg logit contributions
 hesitation-0.183
otion-0.180
erk-0.180
ow-0.176
tha-0.173
Token taxi
Token ID17536
Feature activation-6.68e-01

Pos logit contributions
 likes+0.021
 They+0.020
 and+0.017
 nice+0.016
 with+0.016
Neg logit contributions
ately-0.054
otion-0.053
iqu-0.052
ous-0.052
ow-0.052
Token.
Token ID13
Feature activation+2.62e+00

Pos logit contributions
ow+0.025
ately+0.025
iqu+0.025
ous+0.025
otion+0.025
Neg logit contributions
 likes-0.006
 They-0.005
 and-0.005
 nice-0.004
 with-0.004
Token They
Token ID1119
Feature activation+3.33e+00

Pos logit contributions
 likes+0.018
 and+0.014
 with+0.011
 nice+0.011
 fair+0.010
Neg logit contributions
otion-0.102
ately-0.099
iqu-0.098
antis-0.097
erk-0.097
Token are
Token ID389
Feature activation-1.52e-02

Pos logit contributions
 They+0.052
 likes+0.051
 and+0.051
 with+0.050
+0.044
Neg logit contributions
iqu-0.097
erk-0.096
otion-0.096
ow-0.096
unct-0.093
Tokenily
Token ID813
Feature activation+2.82e+00

Pos logit contributions
otion+0.034
ately+0.033
iqu+0.033
wen+0.032
erk+0.032
Neg logit contributions
 likes-0.031
 They-0.031
 and-0.030
 with-0.029
 green-0.027
Token and
Token ID290
Feature activation-6.47e-01

Pos logit contributions
 They+0.027
 likes+0.023
 nice+0.022
 fun+0.022
 games+0.022
Neg logit contributions
ately-0.098
ow-0.097
wen-0.096
illa-0.095
erk-0.095
Token Tom
Token ID4186
Feature activation+2.87e+00

Pos logit contributions
iqu+0.020
ately+0.020
otion+0.020
wen+0.019
erk+0.019
Neg logit contributions
 and-0.012
 likes-0.011
 They-0.011
 with-0.010
 liked-0.010
Token had
Token ID550
Feature activation+2.60e+00

Pos logit contributions
 They+0.045
 likes+0.045
 and+0.042
 with+0.041
 fun+0.037
Neg logit contributions
ately-0.087
iqu-0.086
ow-0.085
erk-0.085
otion-0.085
Token a
Token ID257
Feature activation+5.90e+00

Pos logit contributions
 likes+0.042
 They+0.035
 and+0.031
 with+0.030
 boy+0.028
Neg logit contributions
 hesitation-0.078
ow-0.076
iqu-0.074
abella-0.074
erk-0.074
Token big
Token ID1263
Feature activation+6.64e+00

Pos logit contributions
 likes+0.067
 They+0.066
 and+0.063
 with+0.057
 liked+0.047
Neg logit contributions
iqu-0.212
otion-0.206
ately-0.204
erk-0.204
wen-0.204
Token,
Token ID11
Feature activation+4.27e-01

Pos logit contributions
 They+0.141
 likes+0.132
 with+0.125
 and+0.123
+0.117
Neg logit contributions
 hesitation-0.166
otion-0.165
ow-0.163
erk-0.163
iqu-0.159
Token happy
Token ID3772
Feature activation+3.61e+00

Pos logit contributions
 They+0.005
 likes+0.005
 and+0.004
 with+0.004
+0.004
Neg logit contributions
iqu-0.015
ately-0.015
erk-0.014
otion-0.014
ous-0.014
Token marriage
Token ID4845
Feature activation+8.50e-01

Pos logit contributions
 likes+0.074
 They+0.064
 holes+0.057
 liked+0.057
 shapes+0.056
Neg logit contributions
ous-0.093
otion-0.091
 hesitation-0.091
ately-0.090
ow-0.089
Token.
Token ID13
Feature activation+2.00e+00

Pos logit contributions
 likes+0.008
 They+0.007
 and+0.006
 green+0.005
 grass+0.005
Neg logit contributions
ous-0.032
ately-0.032
iqu-0.031
otion-0.031
erk-0.031
Token They
Token ID1119
Feature activation+3.91e+00

Pos logit contributions
 likes+0.013
 and+0.009
 with+0.008
 nice+0.008
 liked+0.007
Neg logit contributions
otion-0.079
ately-0.077
iqu-0.076
ous-0.075
antis-0.074
Token and
Token ID290
Feature activation-1.07e+00

Pos logit contributions
 They+0.010
 likes+0.010
 and+0.009
 nice+0.009
 fun+0.009
Neg logit contributions
ately-0.018
erk-0.018
ow-0.018
iqu-0.018
wen-0.017
Token the
Token ID262
Feature activation-1.00e+00

Pos logit contributions
iqu+0.041
ately+0.040
otion+0.040
wen+0.040
erk+0.040
Neg logit contributions
 likes-0.011
 and-0.010
 They-0.010
 with-0.009
 nice-0.007
Token mouse
Token ID10211
Feature activation+1.57e+00

Pos logit contributions
iqu+0.034
otion+0.034
ately+0.034
wen+0.034
used+0.033
Neg logit contributions
 likes-0.015
 and-0.015
 They-0.014
 with-0.013
 nice-0.012
Token had
Token ID550
Feature activation+2.45e+00

Pos logit contributions
 likes+0.028
 They+0.027
 and+0.025
 with+0.024
 nice+0.024
Neg logit contributions
ately-0.046
erk-0.045
ow-0.044
iqu-0.044
otion-0.044
Token a
Token ID257
Feature activation+5.92e+00

Pos logit contributions
 likes+0.040
 They+0.032
 with+0.030
 and+0.029
 girl+0.028
Neg logit contributions
 hesitation-0.075
erk-0.071
ow-0.070
ately-0.070
iqu-0.069
Token big
Token ID1263
Feature activation+6.64e+00

Pos logit contributions
 They+0.081
 likes+0.078
 and+0.073
 with+0.072
 shapes+0.058
Neg logit contributions
iqu-0.192
erk-0.187
 hesitation-0.187
wen-0.183
tha-0.180
Token disagreement
Token ID25800
Feature activation+1.27e+00

Pos logit contributions
 They+0.138
They+0.128
 likes+0.126
 with+0.126
+0.118
Neg logit contributions
 hesitation-0.164
erk-0.160
ow-0.157
otion-0.153
igh-0.152
Token.
Token ID13
Feature activation+7.70e-01

Pos logit contributions
 likes+0.014
 They+0.012
 and+0.010
 green+0.009
 nice+0.009
Neg logit contributions
otion-0.046
ately-0.046
iqu-0.046
ous-0.046
erk-0.046
Token Then
Token ID3244
Feature activation-8.92e-01

Pos logit contributions
 likes+0.009
 nice+0.007
 and+0.007
 games+0.007
 pretty+0.006
Neg logit contributions
ately-0.027
otion-0.027
iqu-0.026
antis-0.026
ow-0.026
Token,
Token ID11
Feature activation-2.07e+00

Pos logit contributions
iqu+0.031
ately+0.031
otion+0.031
used+0.030
wen+0.030
Neg logit contributions
 likes-0.011
 They-0.010
 and-0.010
 with-0.009
 liked-0.008
Token they
Token ID484
Feature activation+1.84e+00

Pos logit contributions
iqu+0.084
wen+0.082
otion+0.081
erk+0.080
ately+0.080
Neg logit contributions
 and-0.022
 They-0.021
 with-0.020
 likes-0.018
-0.015
Token the
Token ID262
Feature activation+3.99e-01

Pos logit contributions
 likes+0.014
 They+0.013
 and+0.013
 with+0.012
 liked+0.010
Neg logit contributions
iqu-0.048
ately-0.048
otion-0.047
wen-0.047
erk-0.047
Token strawberry
Token ID41236
Feature activation-1.66e+00

Pos logit contributions
 likes+0.006
 They+0.006
 and+0.006
 with+0.005
 liked+0.005
Neg logit contributions
iqu-0.013
ately-0.013
otion-0.013
wen-0.013
erk-0.013
Token and
Token ID290
Feature activation+5.87e-01

Pos logit contributions
ately+0.059
erk+0.058
ous+0.057
comb+0.057
icking+0.057
Neg logit contributions
 likes-0.019
 They-0.018
 liked-0.013
 nice-0.013
-0.012
Token had
Token ID550
Feature activation+2.12e+00

Pos logit contributions
 likes+0.007
 They+0.007
 and+0.007
 with+0.006
 nice+0.005
Neg logit contributions
ately-0.020
iqu-0.020
ous-0.020
erk-0.020
otion-0.020
Token a
Token ID257
Feature activation+5.27e+00

Pos logit contributions
 likes+0.039
 They+0.032
 and+0.030
 with+0.029
 liked+0.026
Neg logit contributions
erk-0.061
wen-0.061
ow-0.060
ately-0.059
iqu-0.059
Token big
Token ID1263
Feature activation+6.63e+00

Pos logit contributions
 likes+0.067
 They+0.066
 and+0.060
 with+0.055
 liked+0.048
Neg logit contributions
iqu-0.184
erk-0.178
ous-0.175
wen-0.175
 hesitation-0.174
Token party
Token ID2151
Feature activation+1.89e+00

Pos logit contributions
 They+0.140
 likes+0.136
 with+0.123
 and+0.121
 shapes+0.118
Neg logit contributions
 hesitation-0.167
erk-0.166
iqu-0.163
ow-0.158
otion-0.157
Token.
Token ID13
Feature activation+1.70e+00

Pos logit contributions
 likes+0.024
 They+0.021
 grass+0.016
 and+0.016
 liked+0.016
Neg logit contributions
ous-0.066
ately-0.066
erk-0.065
ow-0.064
iqu-0.064
Token
Token ID220
Feature activation-3.17e-01

Pos logit contributions
 likes+0.019
 and+0.016
 nice+0.015
 games+0.015
 with+0.014
Neg logit contributions
otion-0.061
ately-0.060
wen-0.060
used-0.060
iqu-0.060
Token
Token ID198
Feature activation+8.03e-01

Pos logit contributions
otion+0.013
iqu+0.013
wen+0.013
ately+0.013
erk+0.013
Neg logit contributions
 likes-0.002
 and-0.002
 They-0.001
 with-0.001
 games-0.001
Token
Token ID198
Feature activation-3.84e-01

Pos logit contributions
 likes+0.009
 and+0.007
 They+0.007
 fair+0.006
 games+0.006
Neg logit contributions
wen-0.029
otion-0.029
aro-0.029
erk-0.029
izz-0.029
Token back
Token ID736
Feature activation+9.54e-01

Pos logit contributions
 likes+0.013
 They+0.011
 liked+0.010
 and+0.010
 shapes+0.010
Neg logit contributions
ately-0.021
otion-0.021
ow-0.021
iqu-0.021
erk-0.021
Token home
Token ID1363
Feature activation+8.55e-01

Pos logit contributions
 likes+0.013
 They+0.012
 and+0.011
 with+0.010
 liked+0.010
Neg logit contributions
ately-0.032
iqu-0.032
erk-0.032
otion-0.032
wen-0.031
Token and
Token ID290
Feature activation-6.03e-03

Pos logit contributions
 likes+0.007
 They+0.006
 and+0.004
 grass+0.004
 green+0.004
Neg logit contributions
ately-0.033
erk-0.033
iqu-0.033
ous-0.033
ow-0.032
Token had
Token ID550
Feature activation+2.38e+00

Pos logit contributions
iqu+0.000
otion+0.000
wen+0.000
ately+0.000
used+0.000
Neg logit contributions
 and-0.000
 They-0.000
 likes-0.000
 with-0.000
 liked-0.000
Token a
Token ID257
Feature activation+5.47e+00

Pos logit contributions
 likes+0.045
 They+0.035
 than+0.034
 and+0.034
 with+0.033
Neg logit contributions
erk-0.065
ow-0.064
abella-0.064
iqu-0.063
wen-0.062
Token big
Token ID1263
Feature activation+6.63e+00

Pos logit contributions
 likes+0.054
 They+0.053
 and+0.050
 with+0.044
 liked+0.036
Neg logit contributions
iqu-0.207
erk-0.201
otion-0.200
ately-0.199
wen-0.199
Token dinner
Token ID8073
Feature activation+1.22e+00

Pos logit contributions
 They+0.138
 likes+0.132
 with+0.122
 and+0.120
 shapes+0.117
Neg logit contributions
erk-0.168
 hesitation-0.166
iqu-0.164
otion-0.163
ow-0.163
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
 likes+0.017
 They+0.015
 and+0.012
 green+0.011
 grass+0.011
Neg logit contributions
ately-0.041
erk-0.041
ous-0.040
otion-0.040
ow-0.040
Token Tim
Token ID5045
Feature activation+2.32e+00

Pos logit contributions
 likes+0.017
 and+0.016
 games+0.014
 with+0.014
 nice+0.013
Neg logit contributions
iqu-0.049
otion-0.048
erk-0.048
ous-0.048
antis-0.048
Token and
Token ID290
Feature activation-1.25e+00

Pos logit contributions
 They+0.034
 likes+0.030
 games+0.027
 with+0.027
 nice+0.026
Neg logit contributions
wen-0.075
ately-0.074
erk-0.074
ow-0.074
iqu-0.073
Token his
Token ID465
Feature activation-1.10e+00

Pos logit contributions
iqu+0.052
ately+0.051
otion+0.050
used+0.050
wen+0.050
Neg logit contributions
 They-0.011
 and-0.011
 likes-0.010
 with-0.009
-0.008
Tokenute
Token ID1133
Feature activation-2.20e+00

Pos logit contributions
iqu+0.071
otion+0.068
ately+0.068
wen+0.067
erk+0.066
Neg logit contributions
 likes-0.111
 and-0.110
 They-0.109
 with-0.104
 nice-0.099
Token.
Token ID13
Feature activation+6.68e-01

Pos logit contributions
ately+0.086
otion+0.086
ous+0.085
iqu+0.085
erk+0.084
Neg logit contributions
 likes-0.018
 They-0.016
 and-0.013
 liked-0.011
 fun-0.011
Token She
Token ID1375
Feature activation+2.35e+00

Pos logit contributions
 likes+0.009
 and+0.009
 with+0.008
 fun+0.008
 nice+0.008
Neg logit contributions
ately-0.022
otion-0.022
iqu-0.022
ous-0.022
used-0.022
Token had
Token ID550
Feature activation+1.81e+00

Pos logit contributions
 They+0.039
 likes+0.039
 and+0.036
 with+0.034
 nice+0.032
Neg logit contributions
ately-0.072
iqu-0.072
wen-0.071
erk-0.070
used-0.070
Token a
Token ID257
Feature activation+5.36e+00

Pos logit contributions
 likes+0.034
 They+0.032
 and+0.029
 with+0.028
 liked+0.025
Neg logit contributions
wen-0.051
ately-0.051
iqu-0.050
erk-0.050
ow-0.050
Token big
Token ID1263
Feature activation+6.63e+00

Pos logit contributions
 They+0.072
 likes+0.070
 and+0.063
 with+0.059
 shapes+0.051
Neg logit contributions
iqu-0.182
erk-0.176
wen-0.174
 hesitation-0.174
ous-0.171
Token smile
Token ID8212
Feature activation+1.76e+00

Pos logit contributions
 They+0.144
 likes+0.131
They+0.125
 with+0.122
 shapes+0.119
Neg logit contributions
 hesitation-0.163
erk-0.157
tha-0.154
iqu-0.153
ow-0.152
Token on
Token ID319
Feature activation+2.19e+00

Pos logit contributions
 and+0.020
 likes+0.017
 with+0.016
 They+0.016
 liked+0.013
Neg logit contributions
iqu-0.070
otion-0.067
ately-0.066
wen-0.066
erk-0.066
Token her
Token ID607
Feature activation-1.57e+00

Pos logit contributions
 likes+0.043
 They+0.038
 and+0.035
 liked+0.035
 boy+0.034
Neg logit contributions
otion-0.059
ately-0.057
ow-0.057
wen-0.057
iqu-0.057
Token face
Token ID1986
Feature activation+9.41e-01

Pos logit contributions
ately+0.051
iqu+0.051
wen+0.050
ous+0.049
erk+0.049
Neg logit contributions
 likes-0.024
 They-0.023
 and-0.021
 with-0.020
 liked-0.019
Token because
Token ID780
Feature activation-1.13e+00

Pos logit contributions
 and+0.003
 with+0.001
 likes+0.001
 They+0.001
 liked-0.001
Neg logit contributions
iqu-0.045
otion-0.044
wen-0.044
ately-0.043
aro-0.043
Token She
Token ID1375
Feature activation+3.19e+00

Pos logit contributions
 likes+0.023
 and+0.021
 with+0.017
 games+0.017
 They+0.016
Neg logit contributions
iqu-0.098
otion-0.098
wen-0.097
antis-0.096
ately-0.096
Token says
Token ID1139
Feature activation-1.30e-01

Pos logit contributions
 They+0.052
 with+0.049
 games+0.047
 likes+0.047
 and+0.046
Neg logit contributions
iqu-0.095
erk-0.091
wen-0.090
otion-0.089
ow-0.088
Token he
Token ID339
Feature activation+1.77e+00

Pos logit contributions
iqu+0.004
wen+0.004
ately+0.004
used+0.004
erk+0.004
Neg logit contributions
 and-0.002
 likes-0.002
 They-0.002
 with-0.002
 nice-0.002
Token has
Token ID468
Feature activation+2.20e+00

Pos logit contributions
 They+0.018
 with+0.016
 and+0.016
 games+0.015
 likes+0.014
Neg logit contributions
iqu-0.064
erk-0.063
wen-0.063
ow-0.063
otion-0.062
Token a
Token ID257
Feature activation+5.44e+00

Pos logit contributions
 They+0.032
 likes+0.032
 and+0.029
 with+0.028
 games+0.023
Neg logit contributions
wen-0.069
iqu-0.068
ately-0.068
erk-0.068
ow-0.068
Token big
Token ID1263
Feature activation+6.60e+00

Pos logit contributions
 They+0.079
 likes+0.079
 and+0.075
 with+0.070
 liked+0.062
Neg logit contributions
iqu-0.179
otion-0.173
erk-0.172
wen-0.172
ately-0.172
Token imagination
Token ID13843
Feature activation+2.37e-01

Pos logit contributions
 They+0.130
 likes+0.122
 with+0.115
 and+0.112
They+0.109
Neg logit contributions
 hesitation-0.173
otion-0.173
erk-0.170
iqu-0.169
ately-0.167
Token.
Token ID13
Feature activation+2.27e+00

Pos logit contributions
 likes+0.001
 They+0.001
 and+0.001
 with+0.001
 nice+0.001
Neg logit contributions
iqu-0.010
ately-0.010
otion-0.010
wen-0.010
erk-0.010
Token He
Token ID679
Feature activation+2.47e+00

Pos logit contributions
 likes+0.019
 and+0.018
 They+0.016
 with+0.014
 nice+0.012
Neg logit contributions
iqu-0.090
otion-0.089
ately-0.089
wen-0.088
erk-0.087
Token says
Token ID1139
Feature activation-1.11e-01

Pos logit contributions
 They+0.035
 with+0.033
 and+0.032
 likes+0.032
 nice+0.031
Neg logit contributions
iqu-0.078
erk-0.075
wen-0.074
otion-0.074
ow-0.074
Token he
Token ID339
Feature activation+1.25e+00

Pos logit contributions
iqu+0.004
wen+0.003
ately+0.003
used+0.003
otion+0.003
Neg logit contributions
 and-0.002
 likes-0.002
 They-0.002
 with-0.002
 nice-0.002
Token You
Token ID921
Feature activation+2.03e+00

Pos logit contributions
 likes+0.030
 and+0.029
 They+0.026
 with+0.025
 nice+0.022
Neg logit contributions
iqu-0.105
otion-0.104
ately-0.104
wen-0.102
erk-0.102
Token can
Token ID460
Feature activation-1.48e+00

Pos logit contributions
 They+0.034
 likes+0.034
 and+0.033
 with+0.031
 grass+0.029
Neg logit contributions
otion-0.059
iqu-0.059
ately-0.059
ow-0.058
erk-0.057
Token both
Token ID1111
Feature activation+1.08e+00

Pos logit contributions
iqu+0.049
otion+0.048
ately+0.048
wen+0.048
erk+0.047
Neg logit contributions
 likes-0.022
 and-0.021
 They-0.021
 with-0.019
 liked-0.017
Token have
Token ID423
Feature activation+1.80e+00

Pos logit contributions
 They+0.017
 likes+0.017
 and+0.016
 grass+0.014
 with+0.014
Neg logit contributions
ow-0.032
ous-0.032
ately-0.031
erk-0.031
used-0.031
Token a
Token ID257
Feature activation+5.65e+00

Pos logit contributions
 likes+0.029
 They+0.028
 and+0.024
 liked+0.022
 with+0.022
Neg logit contributions
 hesitation-0.052
ately-0.052
erk-0.051
wen-0.051
ow-0.051
Token big
Token ID1263
Feature activation+6.60e+00

Pos logit contributions
 They+0.086
 likes+0.084
 and+0.079
 with+0.072
 liked+0.066
Neg logit contributions
iqu-0.182
erk-0.176
otion-0.175
ous-0.174
ately-0.173
Token piece
Token ID3704
Feature activation+9.53e-01

Pos logit contributions
 They+0.145
 likes+0.133
They+0.126
 with+0.121
 and+0.119
Neg logit contributions
erk-0.158
 hesitation-0.157
otion-0.156
ow-0.155
unct-0.152
Token."
Token ID526
Feature activation+2.30e+00

Pos logit contributions
 likes+0.017
 They+0.017
 liked+0.014
 sounds+0.014
 grass+0.014
Neg logit contributions
ow-0.027
otion-0.027
ous-0.026
ately-0.026
erk-0.026
Token She
Token ID1375
Feature activation+2.88e+00

Pos logit contributions
 likes+0.029
 games+0.028
 fair+0.024
 nice+0.024
 shapes+0.023
Neg logit contributions
otion-0.075
antis-0.074
ately-0.074
ama-0.074
iqu-0.072
Token cut
Token ID2005
Feature activation-8.22e-01

Pos logit contributions
 They+0.056
 likes+0.056
 and+0.049
 fun+0.048
 nice+0.048
Neg logit contributions
ately-0.076
iqu-0.075
erk-0.075
wen-0.073
otion-0.072
Token the
Token ID262
Feature activation+1.21e-01

Pos logit contributions
iqu+0.029
ately+0.029
otion+0.029
wen+0.028
erk+0.028
Neg logit contributions
 likes-0.010
 and-0.010
 They-0.010
 with-0.009
 liked-0.008
Token chair
Token ID5118
Feature activation+4.79e-01

Pos logit contributions
 They+0.006
They+0.006
 likes+0.006
 and+0.005
 with+0.005
Neg logit contributions
erk-0.007
iqu-0.007
ama-0.007
ow-0.007
ately-0.007
Token.
Token ID13
Feature activation+5.84e-01

Pos logit contributions
 likes+0.004
 They+0.004
 and+0.003
 with+0.003
 nice+0.002
Neg logit contributions
iqu-0.019
ately-0.019
erk-0.018
otion-0.018
wen-0.018
Token She
Token ID1375
Feature activation+1.88e+00

Pos logit contributions
 likes+0.008
 and+0.007
 They+0.007
 with+0.006
 nice+0.006
Neg logit contributions
iqu-0.020
ately-0.020
otion-0.020
erk-0.020
used-0.020
Token had
Token ID550
Feature activation+1.47e+00

Pos logit contributions
 They+0.031
 likes+0.031
 and+0.029
 with+0.027
 nice+0.025
Neg logit contributions
iqu-0.058
ately-0.057
erk-0.057
wen-0.056
otion-0.056
Token a
Token ID257
Feature activation+5.36e+00

Pos logit contributions
 likes+0.028
 They+0.027
 and+0.025
 with+0.023
 liked+0.021
Neg logit contributions
iqu-0.041
ately-0.041
erk-0.041
wen-0.041
 hesitation-0.040
Token big
Token ID1263
Feature activation+6.59e+00

Pos logit contributions
 They+0.074
 likes+0.070
 and+0.065
 with+0.060
 liked+0.051
Neg logit contributions
iqu-0.183
erk-0.178
 hesitation-0.175
wen-0.174
ately-0.172
Token,
Token ID11
Feature activation+2.60e-01

Pos logit contributions
 They+0.146
 likes+0.130
They+0.125
 with+0.122
+0.118
Neg logit contributions
 hesitation-0.166
erk-0.164
iqu-0.157
ow-0.156
otion-0.154
Token happy
Token ID3772
Feature activation+3.38e+00

Pos logit contributions
 They+0.004
 likes+0.004
 and+0.003
 with+0.003
+0.003
Neg logit contributions
iqu-0.008
erk-0.008
ately-0.008
 hesitation-0.008
antis-0.008
Token smile
Token ID8212
Feature activation+2.03e+00

Pos logit contributions
 likes+0.071
 They+0.069
They+0.059
 liked+0.058
 shapes+0.057
Neg logit contributions
ous-0.085
 hesitation-0.083
erk-0.083
ow-0.079
ately-0.078
Token on
Token ID319
Feature activation+1.43e+00

Pos logit contributions
 and+0.024
 likes+0.023
 They+0.022
 with+0.020
 liked+0.017
Neg logit contributions
iqu-0.075
otion-0.074
ately-0.073
wen-0.073
erk-0.072
Token her
Token ID607
Feature activation-1.56e+00

Pos logit contributions
 likes+0.027
 They+0.024
 and+0.023
 liked+0.023
 boy+0.022
Neg logit contributions
otion-0.040
iqu-0.039
ow-0.039
used-0.039
unct-0.038
Token Carl
Token ID8124
Feature activation+1.58e+00

Pos logit contributions
 likes+0.001
 and+0.001
 They+0.001
 with+0.001
 nice+0.001
Neg logit contributions
iqu-0.001
ately-0.001
aro-0.001
erk-0.001
ous-0.001
Token.
Token ID13
Feature activation+1.84e+00

Pos logit contributions
 They+0.017
 likes+0.017
 games+0.015
Let+0.015
 grass+0.015
Neg logit contributions
ow-0.053
erk-0.050
ately-0.050
 hesitation-0.050
owing-0.050
Token They
Token ID1119
Feature activation+4.22e+00

Pos logit contributions
 likes+0.020
 games+0.018
 nice+0.018
 fair+0.017
 and+0.016
Neg logit contributions
aro-0.065
otion-0.063
ow-0.062
antis-0.061
iqu-0.061
Token had
Token ID550
Feature activation+3.26e+00

Pos logit contributions
 likes+0.067
 They+0.063
 and+0.061
 with+0.058
 nice+0.053
Neg logit contributions
iqu-0.131
ately-0.131
otion-0.130
erk-0.129
wen-0.129
Token a
Token ID257
Feature activation+5.82e+00

Pos logit contributions
 likes+0.063
 They+0.051
 with+0.048
 and+0.047
 girl+0.047
Neg logit contributions
ow-0.085
 hesitation-0.085
erk-0.083
ver-0.080
ately-0.080
Token big
Token ID1263
Feature activation+6.59e+00

Pos logit contributions
 likes+0.075
 They+0.074
 and+0.066
 with+0.063
 shapes+0.053
Neg logit contributions
iqu-0.196
erk-0.189
 hesitation-0.188
wen-0.185
tha-0.184
Token party
Token ID2151
Feature activation+2.49e+00

Pos logit contributions
 They+0.134
 likes+0.127
 with+0.121
They+0.115
 shapes+0.112
Neg logit contributions
 hesitation-0.168
erk-0.164
ow-0.156
tha-0.156
ama-0.154
Token to
Token ID284
Feature activation-2.88e-01

Pos logit contributions
 likes+0.029
 They+0.025
 grass+0.021
 green+0.020
 holes+0.020
Neg logit contributions
ately-0.087
ow-0.087
ous-0.087
icking-0.086
erk-0.086
Token celebrate
Token ID10648
Feature activation+1.92e+00

Pos logit contributions
iqu+0.010
otion+0.009
ately+0.009
wen+0.009
used+0.009
Neg logit contributions
 likes-0.004
 and-0.004
 They-0.004
 with-0.004
 nice-0.004
Token.
Token ID13
Feature activation+1.92e+00

Pos logit contributions
 likes+0.021
 They+0.017
 green+0.013
 and+0.012
 liked+0.012
Neg logit contributions
ately-0.070
erk-0.068
aro-0.067
iqu-0.067
icking-0.067
Token<|endoftext|>
Token ID50256
Feature activation+9.11e-01

Pos logit contributions
 likes+0.019
 and+0.015
 games+0.015
 nice+0.015
 fair+0.014
Neg logit contributions
aro-0.070
otion-0.069
ow-0.069
iqu-0.068
antis-0.068
Token L
Token ID406
Feature activation-3.33e+00

Pos logit contributions
 likes+0.021
 games+0.016
 and+0.015
 with+0.013
 fair+0.012
Neg logit contributions
otion-0.128
iqu-0.128
ately-0.126
erk-0.126
wen-0.125
Tokenila
Token ID10102
Feature activation+2.98e+00

Pos logit contributions
iqu+0.066
used+0.062
 hesitation+0.062
unct+0.061
ous+0.061
Neg logit contributions
 and-0.102
 likes-0.096
 They-0.094
 with-0.091
-0.088
Token and
Token ID290
Feature activation-3.85e-01

Pos logit contributions
 They+0.025
 fun+0.023
 nice+0.021
 games+0.021
 holes+0.020
Neg logit contributions
ately-0.108
ow-0.105
ver-0.104
illa-0.103
wen-0.102
Token R
Token ID371
Feature activation-4.24e+00

Pos logit contributions
iqu+0.014
otion+0.013
ately+0.013
wen+0.013
used+0.013
Neg logit contributions
 They-0.006
 and-0.005
 likes-0.005
 with-0.005
 each-0.004
Tokenani
Token ID3216
Feature activation+2.20e+00

Pos logit contributions
iqu+0.073
otion+0.071
used+0.069
wen+0.068
ately+0.068
Neg logit contributions
 and-0.133
 likes-0.132
 They-0.130
 with-0.123
-0.118
Token smiled
Token ID13541
Feature activation+6.59e+00

Pos logit contributions
 They+0.038
 likes+0.036
 fun+0.034
 with+0.034
 nice+0.034
Neg logit contributions
ately-0.061
erk-0.060
ow-0.060
ous-0.058
otion-0.058
Token and
Token ID290
Feature activation+2.46e+00

Pos logit contributions
 likes+0.062
 games+0.056
 grass+0.051
 bases+0.046
Let+0.043
Neg logit contributions
ous-0.227
icking-0.223
ately-0.219
ow-0.218
ver-0.213
Token hugged
Token ID41130
Feature activation+2.57e+00

Pos logit contributions
 likes+0.043
 and+0.040
 They+0.039
 with+0.037
 games+0.035
Neg logit contributions
ately-0.069
iqu-0.068
erk-0.068
ous-0.068
ow-0.067
Token each
Token ID1123
Feature activation+1.93e+00

Pos logit contributions
 likes+0.021
 They+0.019
 and+0.019
 with+0.015
 liked+0.013
Neg logit contributions
iqu-0.102
ately-0.101
otion-0.100
erk-0.099
wen-0.099
Token other
Token ID584
Feature activation+2.58e+00

Pos logit contributions
 likes+0.031
 They+0.029
 with+0.028
 and+0.025
 liked+0.025
Neg logit contributions
 hesitation-0.056
ately-0.055
wen-0.055
otion-0.054
illa-0.054
Token.
Token ID13
Feature activation+3.58e+00

Pos logit contributions
 likes+0.027
 They+0.023
 liked+0.019
 fun+0.018
Let+0.017
Neg logit contributions
ow-0.089
ately-0.088
erk-0.088
icking-0.087
ous-0.087
Token be
Token ID307
Feature activation-1.45e+00

Pos logit contributions
iqu+0.009
ately+0.009
otion+0.009
wen+0.009
erk+0.009
Neg logit contributions
 likes-0.004
 and-0.004
 They-0.004
 with-0.004
 liked-0.004
Token enough
Token ID1576
Feature activation+2.96e-01

Pos logit contributions
iqu+0.044
otion+0.042
erk+0.042
ately+0.042
wen+0.042
Neg logit contributions
 likes-0.025
 They-0.025
 and-0.024
 with-0.022
-0.020
Token to
Token ID284
Feature activation-1.91e+00

Pos logit contributions
 likes+0.003
 They+0.003
 and+0.003
 with+0.003
 liked+0.002
Neg logit contributions
ately-0.011
iqu-0.011
otion-0.010
erk-0.010
ous-0.010
Token make
Token ID787
Feature activation-1.38e+00

Pos logit contributions
wen+0.064
iqu+0.064
otion+0.064
ately+0.063
ous+0.062
Neg logit contributions
 and-0.031
 with-0.028
 likes-0.028
 They-0.028
 nice-0.025
Token the
Token ID262
Feature activation-1.12e+00

Pos logit contributions
iqu+0.048
otion+0.047
ately+0.047
wen+0.046
erk+0.046
Neg logit contributions
 likes-0.018
 They-0.017
 and-0.017
 with-0.015
 liked-0.014
Token ostr
Token ID42387
Feature activation-1.07e+01

Pos logit contributions
iqu+0.027
otion+0.026
ately+0.026
wen+0.025
ous+0.025
Neg logit contributions
 and-0.028
 likes-0.028
 They-0.027
 with-0.026
 nice-0.025
Tokenich
Token ID488
Feature activation-2.92e+00

Pos logit contributions
otion+0.237
 hesitation+0.233
izz+0.215
erk+0.211
abella+0.211
Neg logit contributions
 and-0.283
 with-0.268
 likes-0.268
-0.251
 They-0.248
Token happy
Token ID3772
Feature activation+2.24e+00

Pos logit contributions
iqu+0.091
otion+0.089
erk+0.089
ately+0.089
ow+0.089
Neg logit contributions
 likes-0.047
 They-0.045
 and-0.043
 with-0.039
 liked-0.038
Token,
Token ID11
Feature activation+9.07e-01

Pos logit contributions
 likes+0.027
 They+0.025
 and+0.019
 nice+0.019
 grass+0.019
Neg logit contributions
ately-0.078
ous-0.076
erk-0.076
otion-0.076
ow-0.075
Token so
Token ID523
Feature activation-2.54e-01

Pos logit contributions
 likes+0.014
 They+0.013
 and+0.011
 with+0.011
 liked+0.011
Neg logit contributions
ately-0.028
 hesitation-0.028
iqu-0.027
erk-0.027
used-0.027
Token he
Token ID339
Feature activation+6.92e-01

Pos logit contributions
iqu+0.008
otion+0.008
wen+0.008
ately+0.008
erk+0.008
Neg logit contributions
 and-0.004
 likes-0.004
 They-0.004
 with-0.004
-0.004
Token the
Token ID262
Feature activation-5.14e-01

Pos logit contributions
iqu+0.049
ately+0.048
otion+0.048
wen+0.048
erk+0.048
Neg logit contributions
 likes-0.010
 and-0.010
 They-0.010
 with-0.008
 nice-0.007
Token zoo
Token ID26626
Feature activation-2.13e+00

Pos logit contributions
iqu+0.019
otion+0.019
ately+0.019
wen+0.019
erk+0.019
Neg logit contributions
 likes-0.006
 and-0.006
 They-0.005
 with-0.005
 nice-0.004
Token to
Token ID284
Feature activation-1.87e+00

Pos logit contributions
ow+0.077
ately+0.075
otion+0.075
erk+0.074
iqu+0.074
Neg logit contributions
 likes-0.023
 They-0.020
 nice-0.015
 fun-0.015
 and-0.014
Token see
Token ID766
Feature activation-3.48e-01

Pos logit contributions
iqu+0.068
ately+0.066
wen+0.066
otion+0.065
ous+0.064
Neg logit contributions
 and-0.025
 likes-0.025
 They-0.024
 with-0.022
 nice-0.020
Token the
Token ID262
Feature activation-8.41e-01

Pos logit contributions
iqu+0.014
ately+0.013
otion+0.013
wen+0.013
erk+0.013
Neg logit contributions
 likes-0.003
 and-0.003
 They-0.003
 with-0.003
 nice-0.002
Token ostr
Token ID42387
Feature activation-1.06e+01

Pos logit contributions
iqu+0.025
otion+0.024
ately+0.024
wen+0.024
used+0.024
Neg logit contributions
 likes-0.016
 and-0.016
 They-0.016
 with-0.015
 nice-0.014
Tokenich
Token ID488
Feature activation-3.58e+00

Pos logit contributions
otion+0.221
 hesitation+0.221
erk+0.210
iqu+0.203
izz+0.199
Neg logit contributions
 and-0.294
 with-0.280
 likes-0.277
-0.267
 They-0.263
Token.
Token ID13
Feature activation-4.17e-01

Pos logit contributions
iqu+0.148
ately+0.146
otion+0.146
wen+0.145
erk+0.144
Neg logit contributions
 likes-0.024
 and-0.023
 They-0.022
 with-0.018
 liked-0.013
Token She
Token ID1375
Feature activation+7.52e-01

Pos logit contributions
ow+0.013
ous+0.013
used+0.013
otion+0.013
ately+0.013
Neg logit contributions
 likes-0.006
 fun-0.005
 and-0.005
 nice-0.005
 with-0.005
Token observed
Token ID6515
Feature activation+4.95e-01

Pos logit contributions
 likes+0.008
 They+0.008
 and+0.008
 with+0.007
 nice+0.006
Neg logit contributions
iqu-0.028
ately-0.027
otion-0.027
wen-0.027
erk-0.027
Token it
Token ID340
Feature activation-1.11e+00

Pos logit contributions
 and+0.004
 likes+0.004
 They+0.004
 with+0.003
 nice+0.002
Neg logit contributions
iqu-0.020
otion-0.020
ately-0.020
wen-0.020
erk-0.020
TokenBen
Token ID11696
Feature activation+1.20e+00

Pos logit contributions
wen+0.007
otion+0.007
abella+0.007
iqu+0.007
antis+0.007
Neg logit contributions
 likes-0.005
 and-0.005
 They-0.005
 fun-0.005
 shapes-0.005
Token wanted
Token ID2227
Feature activation+8.42e-01

Pos logit contributions
 They+0.019
 nice+0.017
 fun+0.017
 new+0.017
 likes+0.016
Neg logit contributions
ow-0.033
ately-0.033
used-0.031
erk-0.031
wen-0.031
Token to
Token ID284
Feature activation-2.46e+00

Pos logit contributions
 and+0.007
 They+0.006
 likes+0.006
 with+0.005
+0.004
Neg logit contributions
iqu-0.035
otion-0.035
ately-0.034
used-0.034
wen-0.034
Token touch
Token ID3638
Feature activation-1.76e-02

Pos logit contributions
iqu+0.085
otion+0.083
ately+0.083
wen+0.082
erk+0.081
Neg logit contributions
 and-0.035
 likes-0.035
 They-0.034
 with-0.031
 nice-0.028
Token the
Token ID262
Feature activation-1.60e+00

Pos logit contributions
iqu+0.001
otion+0.001
wen+0.001
ately+0.001
ous+0.001
Neg logit contributions
 and-0.000
 They-0.000
 likes-0.000
 with-0.000
 green-0.000
Token ostr
Token ID42387
Feature activation-1.05e+01

Pos logit contributions
iqu+0.037
otion+0.036
ately+0.036
erk+0.035
wen+0.035
Neg logit contributions
 and-0.042
 likes-0.042
 They-0.040
 with-0.039
 nice-0.038
Tokenich
Token ID488
Feature activation-3.13e+00

Pos logit contributions
 hesitation+0.248
otion+0.246
izz+0.228
erk+0.226
abella+0.224
Neg logit contributions
 and-0.273
 with-0.258
 likes-0.252
-0.240
 They-0.231
Token,
Token ID11
Feature activation-1.01e-01

Pos logit contributions
iqu+0.132
wen+0.131
otion+0.128
ately+0.128
used+0.126
Neg logit contributions
 and-0.026
 likes-0.021
 with-0.021
 They-0.021
 nice-0.014
Token but
Token ID475
Feature activation-2.86e+00

Pos logit contributions
iqu+0.003
ately+0.003
otion+0.003
ow+0.003
erk+0.003
Neg logit contributions
 likes-0.001
 They-0.001
 and-0.001
 with-0.001
 liked-0.001
Token his
Token ID465
Feature activation-1.89e+00

Pos logit contributions
iqu+0.119
ous+0.114
otion+0.114
wen+0.113
used+0.112
Neg logit contributions
 and-0.032
 likes-0.029
 They-0.028
 with-0.027
 liked-0.024
Token mom
Token ID1995
Feature activation-4.85e-01

Pos logit contributions
otion+0.064
iqu+0.062
used+0.061
ately+0.061
wen+0.060
Neg logit contributions
 and-0.033
 likes-0.033
 They-0.029
 green-0.029
 with-0.029
Token to
Token ID284
Feature activation-2.93e+00

Pos logit contributions
iqu+0.045
ately+0.044
wen+0.044
otion+0.044
erk+0.043
Neg logit contributions
 and-0.018
 likes-0.018
 They-0.017
 with-0.016
 nice-0.014
Token let
Token ID1309
Feature activation-2.40e+00

Pos logit contributions
iqu+0.092
otion+0.090
wen+0.089
ately+0.089
ous+0.088
Neg logit contributions
 and-0.055
 likes-0.051
 with-0.051
 They-0.051
 nice-0.046
Token him
Token ID683
Feature activation-3.32e+00

Pos logit contributions
iqu+0.070
ately+0.068
otion+0.068
wen+0.067
erk+0.067
Neg logit contributions
 likes-0.046
 and-0.045
 They-0.045
 with-0.042
 nice-0.038
Token touch
Token ID3638
Feature activation-2.01e-01

Pos logit contributions
iqu+0.107
ately+0.105
otion+0.105
wen+0.104
erk+0.103
Neg logit contributions
 likes-0.052
 and-0.051
 They-0.051
 with-0.046
 liked-0.042
Token the
Token ID262
Feature activation-5.30e-01

Pos logit contributions
iqu+0.009
otion+0.009
wen+0.009
ately+0.008
used+0.008
Neg logit contributions
 and-0.002
 They-0.001
 likes-0.001
 with-0.001
-0.001
Token ostr
Token ID42387
Feature activation-1.04e+01

Pos logit contributions
iqu+0.011
otion+0.011
ately+0.011
wen+0.010
erk+0.010
Neg logit contributions
 likes-0.015
 and-0.015
 They-0.014
 with-0.014
 nice-0.013
Tokenich
Token ID488
Feature activation-4.10e+00

Pos logit contributions
otion+0.242
 hesitation+0.239
izz+0.221
abella+0.218
erk+0.217
Neg logit contributions
 and-0.271
 with-0.253
 likes-0.251
-0.241
 They-0.231
Token.
Token ID13
Feature activation+3.50e-01

Pos logit contributions
iqu+0.178
wen+0.175
ately+0.173
otion+0.173
used+0.170
Neg logit contributions
 and-0.028
 likes-0.023
 They-0.022
 with-0.020
 nice-0.012
Token His
Token ID2399
Feature activation-1.48e+00

Pos logit contributions
 likes+0.007
 and+0.006
 fun+0.006
 games+0.006
 with+0.006
Neg logit contributions
ately-0.009
ow-0.009
otion-0.009
iqu-0.009
erk-0.009
Token dad
Token ID9955
Feature activation+7.62e-01

Pos logit contributions
otion+0.045
iqu+0.045
used+0.044
ately+0.044
ous+0.043
Neg logit contributions
 and-0.030
 likes-0.029
 They-0.028
 with-0.026
 nice-0.025
Token said
Token ID531
Feature activation-1.05e+00

Pos logit contributions
 and+0.012
 likes+0.012
 They+0.011
 with+0.011
 liked+0.010
Neg logit contributions
iqu-0.025
otion-0.025
ately-0.025
wen-0.025
ous-0.024
Token me
Token ID502
Feature activation-2.92e+00

Pos logit contributions
 likes+0.004
 They+0.003
 games+0.003
 with+0.003
 liked+0.003
Neg logit contributions
wen-0.010
ow-0.010
ately-0.010
iqu-0.010
ama-0.010
Token introduce
Token ID10400
Feature activation+7.99e-01

Pos logit contributions
iqu+0.099
otion+0.098
wen+0.097
ately+0.097
antis+0.094
Neg logit contributions
 and-0.047
 likes-0.044
 They-0.043
 with-0.042
 nice-0.037
Token you
Token ID345
Feature activation+7.47e-01

Pos logit contributions
 likes+0.012
 and+0.012
 They+0.011
 with+0.010
 nice+0.009
Neg logit contributions
iqu-0.027
otion-0.026
ately-0.026
wen-0.026
erk-0.026
Token to
Token ID284
Feature activation-1.98e-01

Pos logit contributions
 likes+0.010
 They+0.009
 and+0.008
 liked+0.007
 with+0.007
Neg logit contributions
iqu-0.025
ow-0.025
ately-0.025
wen-0.025
used-0.025
Token the
Token ID262
Feature activation-5.00e-01

Pos logit contributions
iqu+0.008
otion+0.008
ately+0.008
wen+0.008
erk+0.008
Neg logit contributions
 and-0.002
 likes-0.001
 They-0.001
 with-0.001
 nice-0.001
Token ostr
Token ID42387
Feature activation-1.03e+01

Pos logit contributions
otion+0.011
iqu+0.011
ately+0.011
used+0.011
erk+0.011
Neg logit contributions
 and-0.013
 likes-0.013
 They-0.012
 nice-0.012
 with-0.012
Tokenich
Token ID488
Feature activation-2.62e+00

Pos logit contributions
 hesitation+0.246
otion+0.238
erk+0.217
izz+0.214
iqu+0.212
Neg logit contributions
 and-0.265
 with-0.247
 likes-0.239
-0.231
 They-0.220
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
ately+0.095
iqu+0.095
ow+0.095
otion+0.094
ous+0.094
Neg logit contributions
 likes-0.027
 They-0.025
 and-0.023
 with-0.020
 fun-0.019
Token This
Token ID770
Feature activation-8.69e-01

Pos logit contributions
 They+0.017
 likes+0.017
 and+0.016
 with+0.015
+0.013
Neg logit contributions
iqu-0.049
ately-0.048
otion-0.048
wen-0.048
erk-0.048
Token is
Token ID318
Feature activation-8.57e-01

Pos logit contributions
iqu+0.022
otion+0.022
ately+0.022
wen+0.021
erk+0.021
Neg logit contributions
 likes-0.019
 They-0.019
 and-0.019
 with-0.018
 liked-0.017
Token M
Token ID337
Feature activation-4.85e+00

Pos logit contributions
iqu+0.032
ately+0.032
otion+0.032
wen+0.032
erk+0.031
Neg logit contributions
 likes-0.009
 and-0.009
 They-0.008
 with-0.007
 nice-0.006
Token if
Token ID611
Feature activation-2.77e+00

Pos logit contributions
iqu+0.131
wen+0.130
ately+0.129
otion+0.127
unct+0.126
Neg logit contributions
 and-0.048
 likes-0.044
 They-0.044
 with-0.043
-0.036
Token they
Token ID484
Feature activation-8.92e-01

Pos logit contributions
iqu+0.101
wen+0.097
otion+0.096
erk+0.096
ately+0.095
Neg logit contributions
 and-0.038
 They-0.037
 with-0.036
 likes-0.036
-0.032
Token could
Token ID714
Feature activation-3.29e+00

Pos logit contributions
iqu+0.029
wen+0.029
otion+0.029
ately+0.028
used+0.028
Neg logit contributions
 likes-0.015
 and-0.015
 They-0.014
 with-0.013
 liked-0.012
Token see
Token ID766
Feature activation-5.24e-01

Pos logit contributions
iqu+0.123
wen+0.119
ately+0.118
otion+0.116
ous+0.115
Neg logit contributions
 and-0.051
 with-0.046
 They-0.045
 likes-0.042
-0.039
Token the
Token ID262
Feature activation-9.16e-01

Pos logit contributions
iqu+0.020
ately+0.020
otion+0.019
wen+0.019
used+0.019
Neg logit contributions
 likes-0.006
 and-0.006
 They-0.005
 with-0.005
 nice-0.004
Token ostr
Token ID42387
Feature activation-1.03e+01

Pos logit contributions
iqu+0.023
ately+0.023
otion+0.023
wen+0.022
used+0.022
Neg logit contributions
 likes-0.021
 and-0.021
 They-0.020
 with-0.019
 nice-0.019
Tokenich
Token ID488
Feature activation-3.85e+00

Pos logit contributions
otion+0.232
 hesitation+0.230
erk+0.215
izz+0.215
iqu+0.211
Neg logit contributions
 and-0.271
 likes-0.253
 with-0.249
-0.235
 They-0.232
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
iqu+0.168
wen+0.167
ately+0.165
otion+0.162
antis+0.161
Neg logit contributions
 and-0.026
 likes-0.021
 They-0.020
 with-0.020
 nice-0.010
Token
Token ID198
Feature activation-8.76e-01

Pos logit contributions
 likes+0.010
 and+0.009
 games+0.008
 nice+0.008
 fun+0.007
Neg logit contributions
otion-0.038
ately-0.038
ow-0.037
used-0.037
iqu-0.037
Token
Token ID198
Feature activation-1.73e+00

Pos logit contributions
otion+0.036
wen+0.035
iqu+0.035
ately+0.035
erk+0.035
Neg logit contributions
 likes-0.006
 and-0.004
 They-0.004
 games-0.003
 with-0.003
Token"
Token ID1
Feature activation+1.70e+00

Pos logit contributions
used+0.058
aro+0.057
otion+0.056
wen+0.056
izz+0.055
Neg logit contributions
 likes-0.022
 and-0.019
 They-0.019
 fun-0.017
 games-0.017
Token apple
Token ID17180
Feature activation-3.38e+00

Pos logit contributions
iqu+0.004
ately+0.004
otion+0.004
used+0.004
 hesitation+0.004
Neg logit contributions
 They-0.003
 likes-0.003
 and-0.003
 with-0.003
 liked-0.002
Token and
Token ID290
Feature activation-8.61e-01

Pos logit contributions
ately+0.135
otion+0.134
iqu+0.134
erk+0.133
ow+0.133
Neg logit contributions
 likes-0.025
 They-0.020
 and-0.014
 liked-0.013
 fun-0.012
Token slowly
Token ID6364
Feature activation-4.90e-01

Pos logit contributions
iqu+0.026
ately+0.026
erk+0.025
used+0.025
otion+0.025
Neg logit contributions
 likes-0.015
 They-0.014
 and-0.014
 with-0.012
 nice-0.012
Token approached
Token ID10448
Feature activation-8.25e-01

Pos logit contributions
iqu+0.014
ately+0.014
otion+0.014
wen+0.014
erk+0.014
Neg logit contributions
 likes-0.009
 and-0.009
 They-0.009
 with-0.008
 liked-0.008
Token the
Token ID262
Feature activation-1.53e+00

Pos logit contributions
iqu+0.029
ately+0.029
otion+0.029
wen+0.028
used+0.028
Neg logit contributions
 likes-0.010
 They-0.010
 and-0.010
 with-0.009
 liked-0.008
Token ostr
Token ID42387
Feature activation-1.02e+01

Pos logit contributions
iqu+0.043
ately+0.043
otion+0.042
wen+0.042
erk+0.041
Neg logit contributions
 likes-0.030
 They-0.030
 and-0.029
 with-0.027
 liked-0.025
Tokenich
Token ID488
Feature activation-3.40e+00

Pos logit contributions
otion+0.214
 hesitation+0.202
izz+0.186
iqu+0.186
erk+0.185
Neg logit contributions
 and-0.295
 likes-0.280
 with-0.274
 They-0.268
-0.262
Token.
Token ID13
Feature activation-6.63e-01

Pos logit contributions
iqu+0.136
ately+0.135
otion+0.134
erk+0.133
used+0.132
Neg logit contributions
 likes-0.026
 They-0.024
 and-0.023
 with-0.018
 liked-0.016
Token
Token ID220
Feature activation-1.17e+00

Pos logit contributions
used+0.021
ately+0.021
iqu+0.021
ow+0.021
otion+0.020
Neg logit contributions
 likes-0.010
 and-0.009
 nice-0.009
 pretty-0.008
 games-0.008
Token
Token ID198
Feature activation-8.23e-01

Pos logit contributions
iqu+0.050
otion+0.050
ately+0.050
wen+0.049
erk+0.049
Neg logit contributions
 likes-0.006
 and-0.004
 They-0.004
 with-0.003
 nice-0.002
Token
Token ID198
Feature activation-1.63e+00

Pos logit contributions
wen+0.034
otion+0.034
ately+0.034
iqu+0.034
used+0.034
Neg logit contributions
 likes-0.005
 and-0.004
 They-0.004
 with-0.003
 liked-0.002
Token went
Token ID1816
Feature activation-4.36e-01

Pos logit contributions
 likes+0.031
 and+0.031
 They+0.030
 with+0.028
 liked+0.026
Neg logit contributions
iqu-0.054
otion-0.053
ately-0.053
wen-0.052
erk-0.052
Token outside
Token ID2354
Feature activation+1.86e+00

Pos logit contributions
iqu+0.015
ately+0.015
otion+0.015
erk+0.015
wen+0.015
Neg logit contributions
 likes-0.006
 They-0.005
 and-0.005
 with-0.004
 liked-0.004
Token and
Token ID290
Feature activation-5.18e-01

Pos logit contributions
 likes+0.018
 They+0.014
 nice+0.011
 liked+0.010
 fun+0.010
Neg logit contributions
ately-0.070
erk-0.069
ow-0.069
otion-0.068
ous-0.068
Token saw
Token ID2497
Feature activation+1.92e-01

Pos logit contributions
iqu+0.020
otion+0.020
wen+0.020
ately+0.019
ous+0.019
Neg logit contributions
 and-0.006
 They-0.006
 likes-0.005
 with-0.005
 liked-0.005
Token the
Token ID262
Feature activation-1.12e+00

Pos logit contributions
 and+0.002
 They+0.002
 likes+0.002
 with+0.001
 nice+0.001
Neg logit contributions
iqu-0.008
ately-0.008
otion-0.008
wen-0.008
used-0.008
Token ostr
Token ID42387
Feature activation-1.01e+01

Pos logit contributions
iqu+0.023
otion+0.023
ately+0.023
used+0.022
erk+0.022
Neg logit contributions
 and-0.031
 likes-0.031
 They-0.030
 with-0.029
 nice-0.028
Tokenich
Token ID488
Feature activation-2.73e+00

Pos logit contributions
 hesitation+0.219
otion+0.217
erk+0.207
iqu+0.200
abella+0.194
Neg logit contributions
 and-0.278
 likes-0.259
 with-0.255
-0.243
 They-0.238
Token walking
Token ID6155
Feature activation+3.53e-01

Pos logit contributions
iqu+0.106
ately+0.104
otion+0.104
wen+0.103
erk+0.102
Neg logit contributions
 likes-0.026
 and-0.026
 They-0.025
 with-0.021
 liked-0.018
Token around
Token ID1088
Feature activation+1.71e+00

Pos logit contributions
 likes+0.006
 They+0.005
 and+0.005
 fun+0.004
 nice+0.004
Neg logit contributions
ow-0.011
iqu-0.011
used-0.011
ately-0.011
erk-0.011
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
 likes+0.019
 They+0.016
 and+0.013
 nice+0.012
 with+0.011
Neg logit contributions
ately-0.062
otion-0.062
used-0.061
erk-0.061
iqu-0.061
Token "
Token ID366
Feature activation+1.20e+00

Pos logit contributions
ous+0.005
iqu+0.005
ately+0.005
otion+0.005
used+0.005
Neg logit contributions
 likes-0.002
 and-0.002
 nice-0.002
 fun-0.002
 with-0.002
Token so
Token ID523
Feature activation-2.64e-01

Pos logit contributions
iqu+0.059
ately+0.059
otion+0.058
wen+0.057
erk+0.057
Neg logit contributions
 and-0.032
 likes-0.032
 They-0.031
 with-0.030
 nice-0.027
Token excited
Token ID6568
Feature activation+1.32e+00

Pos logit contributions
iqu+0.009
otion+0.008
erk+0.008
used+0.008
ous+0.008
Neg logit contributions
 likes-0.004
 They-0.004
 and-0.003
 with-0.003
 grass-0.003
Token and
Token ID290
Feature activation-9.38e-01

Pos logit contributions
 likes+0.019
 They+0.016
 liked+0.013
 and+0.013
 nice+0.013
Neg logit contributions
ately-0.045
ous-0.044
iqu-0.044
otion-0.043
wen-0.043
Token asked
Token ID1965
Feature activation-2.14e+00

Pos logit contributions
iqu+0.027
ately+0.027
ous+0.027
used+0.027
erk+0.026
Neg logit contributions
 likes-0.017
 They-0.016
 and-0.016
 with-0.014
-0.013
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
iqu+0.073
otion+0.071
ately+0.071
wen+0.071
erk+0.070
Neg logit contributions
 likes-0.030
 and-0.030
 They-0.029
 with-0.027
 nice-0.024
Token ostr
Token ID42387
Feature activation-1.01e+01

Pos logit contributions
iqu+0.048
otion+0.047
ately+0.047
wen+0.046
erk+0.046
Neg logit contributions
 likes-0.023
 and-0.022
 They-0.022
 with-0.020
 nice-0.018
Tokenich
Token ID488
Feature activation-3.37e+00

Pos logit contributions
otion+0.237
 hesitation+0.213
izz+0.213
erk+0.209
unct+0.189
Neg logit contributions
 and-0.265
 with-0.248
 likes-0.247
-0.228
 They-0.226
Token what
Token ID644
Feature activation-7.43e-01

Pos logit contributions
iqu+0.115
wen+0.115
otion+0.113
ately+0.113
izz+0.110
Neg logit contributions
 and-0.052
 They-0.048
 likes-0.048
 with-0.047
-0.041
Token was
Token ID373
Feature activation-2.54e+00

Pos logit contributions
iqu+0.024
otion+0.023
ately+0.023
erk+0.023
ous+0.023
Neg logit contributions
 likes-0.011
 They-0.011
 and-0.010
 with-0.009
 nice-0.008
Token happening
Token ID5836
Feature activation-1.66e-01

Pos logit contributions
iqu+0.069
ately+0.068
otion+0.067
wen+0.067
erk+0.066
Neg logit contributions
 and-0.054
 likes-0.053
 They-0.052
 with-0.051
 nice-0.047
Token.
Token ID13
Feature activation-5.03e-01

Pos logit contributions
iqu+0.007
ately+0.007
otion+0.007
wen+0.006
erk+0.006
Neg logit contributions
 likes-0.001
 They-0.001
 and-0.001
 with-0.001
 liked-0.001
Token They
Token ID1119
Feature activation+1.96e+00

Pos logit contributions
 likes+0.014
 and+0.011
 games+0.010
 fair+0.009
 toy+0.009
Neg logit contributions
otion-0.071
ately-0.070
erk-0.068
iqu-0.068
antis-0.068
Token wanted
Token ID2227
Feature activation+5.11e-01

Pos logit contributions
 likes+0.027
 and+0.027
 They+0.026
 liked+0.023
 with+0.023
Neg logit contributions
iqu-0.069
otion-0.069
ately-0.067
wen-0.067
ous-0.067
Token to
Token ID284
Feature activation-1.70e+00

Pos logit contributions
 and+0.004
 They+0.004
 likes+0.004
 with+0.004
 nice+0.003
Neg logit contributions
iqu-0.021
otion-0.021
ately-0.020
wen-0.020
used-0.020
Token see
Token ID766
Feature activation+4.62e-01

Pos logit contributions
iqu+0.055
ately+0.054
otion+0.054
wen+0.053
erk+0.053
Neg logit contributions
 likes-0.027
 and-0.027
 They-0.027
 with-0.025
 nice-0.022
Token the
Token ID262
Feature activation-6.55e-01

Pos logit contributions
 and+0.005
 likes+0.005
 They+0.004
 with+0.004
 nice+0.003
Neg logit contributions
iqu-0.018
ately-0.018
otion-0.018
wen-0.018
used-0.017
Token ostr
Token ID42387
Feature activation-1.01e+01

Pos logit contributions
iqu+0.020
ately+0.020
otion+0.020
wen+0.019
erk+0.019
Neg logit contributions
 likes-0.012
 and-0.012
 They-0.011
 with-0.011
 nice-0.010
Tokenich
Token ID488
Feature activation-2.96e+00

Pos logit contributions
otion+0.232
 hesitation+0.231
izz+0.216
erk+0.215
abella+0.211
Neg logit contributions
 and-0.269
 likes-0.251
 with-0.244
-0.230
 They-0.225
Token.
Token ID13
Feature activation+1.94e+00

Pos logit contributions
iqu+0.114
wen+0.112
ately+0.111
otion+0.111
used+0.109
Neg logit contributions
 and-0.032
 likes-0.031
 They-0.029
 with-0.027
 nice-0.022
Token
Token ID198
Feature activation-3.36e-01

Pos logit contributions
 likes+0.016
 games+0.013
 and+0.013
 fair+0.012
 nice+0.012
Neg logit contributions
otion-0.070
ately-0.069
ow-0.068
erk-0.068
used-0.068
Token
Token ID198
Feature activation-1.15e+00

Pos logit contributions
iqu+0.014
otion+0.014
ately+0.014
wen+0.014
erk+0.014
Neg logit contributions
 likes-0.002
 and-0.001
 They-0.001
 with-0.001
 liked-0.001
TokenThey
Token ID2990
Feature activation+2.66e+00

Pos logit contributions
iqu+0.042
wen+0.041
otion+0.041
ately+0.041
used+0.041
Neg logit contributions
 likes-0.013
 and-0.012
 They-0.011
 with-0.010
 games-0.009
Token want
Token ID765
Feature activation+6.34e-01

Pos logit contributions
 likes+0.019
 and+0.019
 They+0.019
 with+0.017
 nice+0.015
Neg logit contributions
iqu-0.041
otion-0.040
ately-0.040
wen-0.040
erk-0.040
Token to
Token ID284
Feature activation-1.81e+00

Pos logit contributions
 likes+0.007
 They+0.006
 and+0.006
 with+0.005
 liked+0.005
Neg logit contributions
iqu-0.023
ately-0.023
otion-0.023
wen-0.023
erk-0.023
Token see
Token ID766
Feature activation+7.24e-01

Pos logit contributions
iqu+0.061
ately+0.060
otion+0.060
wen+0.059
erk+0.058
Neg logit contributions
 likes-0.027
 and-0.027
 They-0.026
 with-0.024
 nice-0.021
Token the
Token ID262
Feature activation+1.56e-01

Pos logit contributions
 likes+0.010
 They+0.009
 and+0.009
 with+0.008
 liked+0.008
Neg logit contributions
iqu-0.025
ately-0.024
otion-0.024
wen-0.024
erk-0.024
Token big
Token ID1263
Feature activation+1.11e+00

Pos logit contributions
 likes+0.002
 and+0.002
 They+0.002
 with+0.002
 liked+0.002
Neg logit contributions
iqu-0.005
ately-0.005
otion-0.005
wen-0.005
erk-0.005
Token ostr
Token ID42387
Feature activation-1.01e+01

Pos logit contributions
 They+0.018
 likes+0.018
 with+0.016
 and+0.016
+0.015
Neg logit contributions
otion-0.032
ous-0.032
iqu-0.032
ately-0.032
 hesitation-0.031
Tokenich
Token ID488
Feature activation-2.88e+00

Pos logit contributions
 hesitation+0.230
otion+0.227
izz+0.216
erk+0.213
abella+0.209
Neg logit contributions
 and-0.262
 likes-0.246
 with-0.244
-0.223
 They-0.222
Token with
Token ID351
Feature activation+2.59e-01

Pos logit contributions
iqu+0.112
otion+0.111
ately+0.111
erk+0.109
wen+0.109
Neg logit contributions
 likes-0.025
 They-0.023
 and-0.023
 with-0.019
 liked-0.016
Token the
Token ID262
Feature activation+1.75e+00

Pos logit contributions
 likes+0.003
 They+0.003
 and+0.003
 with+0.003
 liked+0.002
Neg logit contributions
iqu-0.009
otion-0.009
ately-0.009
erk-0.009
used-0.009
Token long
Token ID890
Feature activation+1.53e+00

Pos logit contributions
 likes+0.029
 and+0.028
 They+0.027
 with+0.025
 nice+0.024
Neg logit contributions
iqu-0.056
otion-0.055
ately-0.055
wen-0.054
used-0.054
Token neck
Token ID7393
Feature activation-2.17e+00

Pos logit contributions
 likes+0.025
 They+0.024
 and+0.024
 with+0.022
 nice+0.020
Neg logit contributions
iqu-0.048
ately-0.047
otion-0.047
wen-0.047
erk-0.046
Token be
Token ID307
Feature activation-1.16e+00

Pos logit contributions
 likes+0.003
 They+0.003
 and+0.003
 with+0.002
 liked+0.002
Neg logit contributions
iqu-0.007
otion-0.007
ately-0.007
erk-0.007
wen-0.007
Token funny
Token ID8258
Feature activation+2.62e+00

Pos logit contributions
iqu+0.042
otion+0.041
wen+0.041
ately+0.041
erk+0.041
Neg logit contributions
 likes-0.013
 They-0.013
 and-0.012
 with-0.011
 liked-0.009
Token to
Token ID284
Feature activation-1.66e+00

Pos logit contributions
 likes+0.024
 They+0.023
 and+0.016
+0.015
 liked+0.015
Neg logit contributions
iqu-0.098
ous-0.098
ately-0.098
erk-0.097
otion-0.097
Token tease
Token ID34691
Feature activation+6.83e-01

Pos logit contributions
iqu+0.055
ately+0.054
otion+0.054
wen+0.054
used+0.053
Neg logit contributions
 likes-0.025
 and-0.025
 They-0.024
 with-0.022
 liked-0.020
Token the
Token ID262
Feature activation-2.76e-01

Pos logit contributions
 likes+0.011
 They+0.011
 and+0.010
 with+0.009
 liked+0.009
Neg logit contributions
iqu-0.022
ately-0.022
otion-0.021
wen-0.021
used-0.021
Token ostr
Token ID42387
Feature activation-1.01e+01

Pos logit contributions
iqu+0.008
ately+0.007
otion+0.007
wen+0.007
erk+0.007
Neg logit contributions
 likes-0.006
 They-0.006
 and-0.006
 with-0.005
 liked-0.005
Tokenich
Token ID488
Feature activation-2.12e+00

Pos logit contributions
otion+0.219
 hesitation+0.212
izz+0.194
iqu+0.193
erk+0.192
Neg logit contributions
 and-0.282
 likes-0.266
 with-0.265
 They-0.251
-0.249
Token,
Token ID11
Feature activation+2.44e-02

Pos logit contributions
iqu+0.085
ately+0.084
otion+0.084
erk+0.083
used+0.083
Neg logit contributions
 likes-0.016
 They-0.014
 and-0.014
 with-0.011
 liked-0.009
Token so
Token ID523
Feature activation-4.71e-01

Pos logit contributions
 likes+0.000
 They+0.000
 and+0.000
 with+0.000
 nice+0.000
Neg logit contributions
iqu-0.001
otion-0.001
ately-0.001
erk-0.001
wen-0.001
Token he
Token ID339
Feature activation-1.90e-01

Pos logit contributions
iqu+0.015
otion+0.015
ately+0.015
wen+0.015
erk+0.015
Neg logit contributions
 and-0.008
 They-0.008
 likes-0.008
 with-0.007
-0.007
Token prepared
Token ID5597
Feature activation-2.83e-01

Pos logit contributions
iqu+0.006
ately+0.006
otion+0.006
wen+0.006
erk+0.006
Neg logit contributions
 likes-0.003
 They-0.003
 and-0.003
 with-0.003
 nice-0.003
Token"
Token ID1
Feature activation+1.72e+00

Pos logit contributions
izz+0.016
abella+0.015
ama+0.014
ules+0.014
ister+0.014
Neg logit contributions
 likes-0.009
 games-0.008
 toy-0.008
 shapes-0.008
 sounds-0.008
TokenCan
Token ID6090
Feature activation-2.17e+00

Pos logit contributions
 likes+0.029
 and+0.028
 They+0.028
 with+0.025
 nice+0.023
Neg logit contributions
iqu-0.053
otion-0.053
ately-0.052
wen-0.052
used-0.051
Token we
Token ID356
Feature activation-1.37e+00

Pos logit contributions
iqu+0.074
wen+0.073
otion+0.072
erk+0.072
ately+0.071
Neg logit contributions
 and-0.033
 likes-0.033
 They-0.033
 with-0.031
-0.028
Token ride
Token ID6594
Feature activation-1.41e-01

Pos logit contributions
iqu+0.048
otion+0.048
wen+0.047
ately+0.047
erk+0.045
Neg logit contributions
 and-0.021
 They-0.020
 likes-0.020
 with-0.019
-0.016
Token the
Token ID262
Feature activation-8.56e-01

Pos logit contributions
iqu+0.005
ately+0.005
otion+0.005
used+0.005
erk+0.005
Neg logit contributions
 likes-0.002
 They-0.001
 and-0.001
 with-0.001
 liked-0.001
Token ostr
Token ID42387
Feature activation-1.01e+01

Pos logit contributions
iqu+0.018
otion+0.017
ately+0.017
erk+0.017
used+0.017
Neg logit contributions
 and-0.024
 likes-0.024
 They-0.023
 with-0.023
 nice-0.022
Tokenich
Token ID488
Feature activation-3.52e+00

Pos logit contributions
otion+0.221
 hesitation+0.213
erk+0.202
izz+0.197
iqu+0.196
Neg logit contributions
 and-0.271
 likes-0.256
 with-0.254
 They-0.240
-0.238
Token,
Token ID11
Feature activation-3.85e-01

Pos logit contributions
iqu+0.120
otion+0.117
ately+0.117
wen+0.116
erk+0.114
Neg logit contributions
 and-0.051
 likes-0.051
 They-0.049
 with-0.046
 liked-0.040
Token mom
Token ID1995
Feature activation-4.70e-01

Pos logit contributions
otion+0.010
iqu+0.010
ately+0.010
ous+0.009
erk+0.009
Neg logit contributions
 likes-0.008
 They-0.008
 and-0.008
 with-0.007
 liked-0.007
Token?"
Token ID1701
Feature activation-8.82e-01

Pos logit contributions
otion+0.012
iqu+0.012
ately+0.011
erk+0.011
ous+0.011
Neg logit contributions
 likes-0.010
 They-0.010
 and-0.010
 with-0.009
 grass-0.009
Token Ben
Token ID3932
Feature activation-1.04e-01

Pos logit contributions
otion+0.024
ately+0.024
 hesitation+0.024
used+0.023
izz+0.023
Neg logit contributions
 likes-0.016
 and-0.014
 games-0.013
 They-0.013
 with-0.013
TokenBefore
Token ID8421
Feature activation-1.48e+00

Pos logit contributions
wen+0.027
ules+0.026
erk+0.026
antis+0.026
ow+0.026
Neg logit contributions
 likes-0.015
 and-0.014
 They-0.014
 with-0.012
 green-0.012
Token the
Token ID262
Feature activation-1.68e+00

Pos logit contributions
iqu+0.060
otion+0.058
erk+0.057
ately+0.057
wen+0.057
Neg logit contributions
 and-0.018
 They-0.018
 with-0.015
-0.014
 fun-0.014
Token race
Token ID3234
Feature activation-1.79e+00

Pos logit contributions
iqu+0.059
otion+0.058
ately+0.057
erk+0.057
wen+0.057
Neg logit contributions
 and-0.026
 nice-0.025
 likes-0.024
 fun-0.024
 fair-0.024
Token,
Token ID11
Feature activation-3.03e+00

Pos logit contributions
iqu+0.074
wen+0.071
otion+0.071
erk+0.071
ately+0.070
Neg logit contributions
 and-0.016
 They-0.015
 likes-0.014
 with-0.013
 liked-0.010
Token the
Token ID262
Feature activation-2.20e+00

Pos logit contributions
iqu+0.130
otion+0.126
wen+0.126
erk+0.124
ately+0.123
Neg logit contributions
 and-0.027
 They-0.026
 with-0.023
 likes-0.021
-0.018
Token ostr
Token ID42387
Feature activation-1.00e+01

Pos logit contributions
iqu+0.070
otion+0.069
ately+0.068
wen+0.067
erk+0.067
Neg logit contributions
 and-0.041
 likes-0.039
 They-0.038
 nice-0.037
 with-0.036
Tokenich
Token ID488
Feature activation-1.85e+00

Pos logit contributions
 hesitation+0.217
otion+0.211
erk+0.201
iqu+0.195
izz+0.188
Neg logit contributions
 and-0.276
 likes-0.267
 with-0.261
-0.247
 They-0.244
Token felt
Token ID2936
Feature activation+1.91e-01

Pos logit contributions
iqu+0.060
ately+0.059
otion+0.058
wen+0.058
erk+0.058
Neg logit contributions
 likes-0.028
 They-0.028
 and-0.027
 with-0.025
 nice-0.023
Token embarrassed
Token ID21100
Feature activation+2.12e+00

Pos logit contributions
 likes+0.003
 They+0.003
 and+0.003
 with+0.003
 liked+0.002
Neg logit contributions
iqu-0.006
otion-0.006
ately-0.006
erk-0.006
wen-0.006
Token because
Token ID780
Feature activation-2.26e+00

Pos logit contributions
 likes+0.026
 They+0.023
 and+0.019
 with+0.018
 liked+0.018
Neg logit contributions
ately-0.075
otion-0.075
iqu-0.074
ous-0.074
erk-0.073
Token he
Token ID339
Feature activation-1.25e+00

Pos logit contributions
iqu+0.097
unct+0.091
arse+0.091
ately+0.090
istent+0.089
Neg logit contributions
 and-0.029
 with-0.026
 They-0.021
-0.019
 big-0.019
Token if
Token ID611
Feature activation-2.69e+00

Pos logit contributions
iqu+0.107
wen+0.106
ately+0.103
otion+0.102
unct+0.102
Neg logit contributions
 and-0.052
 likes-0.046
 They-0.046
 with-0.045
-0.039
Token he
Token ID339
Feature activation-1.69e+00

Pos logit contributions
iqu+0.100
otion+0.098
erk+0.097
wen+0.097
izz+0.096
Neg logit contributions
 and-0.035
 with-0.033
 They-0.032
 likes-0.031
 nice-0.028
Token could
Token ID714
Feature activation-3.11e+00

Pos logit contributions
iqu+0.055
otion+0.054
wen+0.053
ately+0.053
used+0.052
Neg logit contributions
 likes-0.029
 and-0.028
 They-0.026
 with-0.025
 liked-0.024
Token borrow
Token ID8804
Feature activation-6.20e-02

Pos logit contributions
iqu+0.110
ately+0.107
otion+0.107
wen+0.106
antis+0.104
Neg logit contributions
 and-0.051
 with-0.045
 likes-0.045
 They-0.044
-0.040
Token the
Token ID262
Feature activation-1.61e-01

Pos logit contributions
iqu+0.002
ately+0.002
otion+0.002
ow+0.002
used+0.002
Neg logit contributions
 likes-0.001
 They-0.001
 and-0.001
 liked-0.001
 with-0.001
Token ostr
Token ID42387
Feature activation-1.00e+01

Pos logit contributions
iqu+0.004
ately+0.004
otion+0.004
wen+0.004
erk+0.004
Neg logit contributions
 and-0.004
 likes-0.004
 They-0.004
 with-0.004
 nice-0.004
Tokenich
Token ID488
Feature activation-3.27e+00

Pos logit contributions
 hesitation+0.236
otion+0.223
erk+0.203
unct+0.200
izz+0.197
Neg logit contributions
 and-0.251
 with-0.238
 likes-0.236
-0.216
 They-0.208
Token.
Token ID13
Feature activation+1.34e-01

Pos logit contributions
iqu+0.136
otion+0.134
ately+0.133
wen+0.133
used+0.131
Neg logit contributions
 and-0.024
 likes-0.023
 They-0.021
 with-0.019
 nice-0.013
Token
Token ID220
Feature activation-7.65e-04

Pos logit contributions
 likes+0.002
 and+0.001
 nice+0.001
 games+0.001
 fun+0.001
Neg logit contributions
used-0.005
ous-0.005
ately-0.005
ow-0.004
iqu-0.004
Token
Token ID198
Feature activation-1.13e-01

Pos logit contributions
iqu+0.000
ately+0.000
otion+0.000
wen+0.000
erk+0.000
Neg logit contributions
 likes-0.000
 and-0.000
 They-0.000
 with-0.000
 liked-0.000
Token
Token ID198
Feature activation-1.03e+00

Pos logit contributions
wen+0.005
ately+0.005
iqu+0.005
otion+0.005
erk+0.004
Neg logit contributions
 likes-0.001
 They-0.001
 and-0.001
 with-0.000
 games-0.000
Token I
Token ID314
Feature activation+5.44e-01

Pos logit contributions
iqu+0.032
wen+0.031
otion+0.031
erk+0.031
ules+0.031
Neg logit contributions
 and-0.015
 likes-0.014
 They-0.013
 with-0.013
 nice-0.011
Token want
Token ID765
Feature activation+7.72e-01

Pos logit contributions
 likes+0.010
 and+0.010
 They+0.010
 with+0.009
 liked+0.009
Neg logit contributions
iqu-0.016
otion-0.016
ately-0.016
ous-0.016
wen-0.016
Token to
Token ID284
Feature activation-1.51e+00

Pos logit contributions
 and+0.007
 likes+0.007
 They+0.006
 with+0.006
 nice+0.005
Neg logit contributions
iqu-0.031
otion-0.030
ately-0.030
wen-0.030
erk-0.030
Token ride
Token ID6594
Feature activation+3.33e-01

Pos logit contributions
iqu+0.053
otion+0.052
ately+0.051
wen+0.050
erk+0.050
Neg logit contributions
 and-0.023
 likes-0.022
 They-0.021
 with-0.021
-0.019
Token the
Token ID262
Feature activation-6.25e-01

Pos logit contributions
 likes+0.004
 They+0.004
 and+0.004
 with+0.003
 liked+0.003
Neg logit contributions
iqu-0.012
ately-0.012
otion-0.011
used-0.011
wen-0.011
Token ostr
Token ID42387
Feature activation-1.00e+01

Pos logit contributions
iqu+0.013
otion+0.012
ately+0.012
erk+0.012
wen+0.012
Neg logit contributions
 likes-0.018
 and-0.018
 They-0.017
 with-0.017
 nice-0.016
Tokenich
Token ID488
Feature activation-2.28e+00

Pos logit contributions
otion+0.219
 hesitation+0.215
erk+0.200
iqu+0.198
izz+0.195
Neg logit contributions
 and-0.272
 with-0.253
 likes-0.252
-0.242
 They-0.239
Token!"
Token ID2474
Feature activation+2.81e-01

Pos logit contributions
iqu+0.084
ately+0.084
otion+0.083
wen+0.082
erk+0.082
Neg logit contributions
 likes-0.024
 They-0.023
 and-0.022
 with-0.019
 nice-0.017
Token Ben
Token ID3932
Feature activation+9.96e-01

Pos logit contributions
 likes+0.006
 and+0.005
 than+0.005
 games+0.005
 shapes+0.005
Neg logit contributions
ately-0.007
otion-0.007
 hesitation-0.007
izz-0.007
iqu-0.007
Token said
Token ID531
Feature activation-4.62e-01

Pos logit contributions
 likes+0.017
 They+0.016
 and+0.014
 fun+0.014
 games+0.013
Neg logit contributions
ately-0.030
ow-0.030
erk-0.029
iqu-0.029
wen-0.029
Token.
Token ID13
Feature activation+2.46e-01

Pos logit contributions
iqu+0.019
ately+0.019
otion+0.019
wen+0.019
erk+0.019
Neg logit contributions
 likes-0.003
 and-0.003
 They-0.003
 with-0.002
 liked-0.002
Token,"
Token ID553
Feature activation-4.96e-01

Pos logit contributions
iqu+0.009
otion+0.009
ately+0.009
used+0.009
erk+0.009
Neg logit contributions
 likes-0.003
 They-0.003
 and-0.003
 with-0.003
 liked-0.003
Token Doug
Token ID15115
Feature activation-1.06e+00

Pos logit contributions
iqu+0.015
otion+0.014
ately+0.014
wen+0.014
erk+0.014
Neg logit contributions
 likes-0.009
 and-0.009
 They-0.009
 with-0.008
 liked-0.008
Token said
Token ID531
Feature activation-1.55e+00

Pos logit contributions
iqu+0.035
otion+0.034
ately+0.034
wen+0.033
ous+0.033
Neg logit contributions
 and-0.017
 likes-0.017
 They-0.016
 with-0.015
 liked-0.014
Token to
Token ID284
Feature activation-3.44e+00

Pos logit contributions
iqu+0.064
wen+0.063
otion+0.063
ately+0.063
erk+0.062
Neg logit contributions
 and-0.012
 They-0.010
 likes-0.010
 with-0.010
 nice-0.006
Token the
Token ID262
Feature activation-2.54e+00

Pos logit contributions
iqu+0.131
ately+0.124
wen+0.124
otion+0.123
erk+0.122
Neg logit contributions
 and-0.044
 They-0.041
 likes-0.040
 with-0.039
-0.035
Token ostr
Token ID42387
Feature activation-9.94e+00

Pos logit contributions
iqu+0.067
otion+0.066
ately+0.065
wen+0.064
erk+0.063
Neg logit contributions
 and-0.059
 likes-0.058
 They-0.056
 with-0.054
 nice-0.053
Tokenich
Token ID488
Feature activation-3.37e+00

Pos logit contributions
otion+0.225
 hesitation+0.221
izz+0.200
erk+0.193
ancer+0.192
Neg logit contributions
 and-0.263
 with-0.246
 likes-0.245
-0.234
 They-0.225
Token.
Token ID13
Feature activation-7.55e-01

Pos logit contributions
iqu+0.147
wen+0.147
otion+0.146
ately+0.145
izz+0.142
Neg logit contributions
 and-0.021
 with-0.016
 likes-0.015
 They-0.015
-0.008
Token
Token ID198
Feature activation-1.40e+00

Pos logit contributions
iqu+0.027
ately+0.027
used+0.027
otion+0.027
erk+0.027
Neg logit contributions
 likes-0.008
 and-0.007
 They-0.007
 with-0.006
 games-0.006
Token
Token ID198
Feature activation-1.89e+00

Pos logit contributions
wen+0.056
iqu+0.056
ately+0.056
used+0.056
otion+0.056
Neg logit contributions
 likes-0.010
 and-0.007
 They-0.007
 games-0.006
 with-0.005
TokenThe
Token ID464
Feature activation-2.28e+00

Pos logit contributions
used+0.064
wen+0.061
ately+0.061
iqu+0.061
antis+0.060
Neg logit contributions
 likes-0.026
 They-0.023
 and-0.023
 fun-0.021
 games-0.021
Token his
Token ID465
Feature activation-2.09e+00

Pos logit contributions
iqu+0.093
wen+0.090
ous+0.088
ately+0.088
erk+0.086
Neg logit contributions
 and-0.030
 likes-0.028
 They-0.028
 with-0.026
 liked-0.022
Token favorite
Token ID4004
Feature activation+1.31e-01

Pos logit contributions
iqu+0.065
otion+0.065
ately+0.064
wen+0.063
used+0.063
Neg logit contributions
 likes-0.037
 and-0.036
 They-0.035
 with-0.033
 liked-0.030
Token animal
Token ID5044
Feature activation-3.10e+00

Pos logit contributions
 likes+0.002
 They+0.002
 and+0.002
 with+0.002
 fun+0.001
Neg logit contributions
otion-0.004
ately-0.004
iqu-0.004
erk-0.004
wen-0.004
Token was
Token ID373
Feature activation-2.75e+00

Pos logit contributions
iqu+0.112
otion+0.111
ately+0.111
erk+0.110
wen+0.109
Neg logit contributions
 likes-0.033
 They-0.032
 and-0.031
 with-0.026
 fun-0.024
Token the
Token ID262
Feature activation+1.17e+00

Pos logit contributions
ately+0.103
iqu+0.103
otion+0.101
used+0.101
wen+0.100
Neg logit contributions
 and-0.032
 likes-0.031
 They-0.030
 with-0.028
 nice-0.024
Token ostr
Token ID42387
Feature activation-9.93e+00

Pos logit contributions
 likes+0.020
 and+0.020
 They+0.019
 with+0.018
 nice+0.017
Neg logit contributions
ately-0.038
otion-0.038
iqu-0.038
used-0.037
wen-0.036
Tokenich
Token ID488
Feature activation-2.55e+00

Pos logit contributions
 hesitation+0.232
otion+0.223
erk+0.208
abella+0.206
izz+0.204
Neg logit contributions
 and-0.254
 with-0.244
 likes-0.244
-0.219
 They-0.216
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
iqu+0.106
ately+0.105
otion+0.105
wen+0.104
used+0.103
Neg logit contributions
 likes-0.017
 and-0.017
 They-0.016
 with-0.013
 nice-0.009
Token The
Token ID383
Feature activation-1.95e-01

Pos logit contributions
 likes+0.005
 and+0.004
 games+0.004
 fun+0.004
 with+0.004
Neg logit contributions
otion-0.013
iqu-0.013
antis-0.013
ately-0.013
erk-0.013
Token ostr
Token ID42387
Feature activation-9.85e+00

Pos logit contributions
iqu+0.004
ately+0.004
otion+0.004
wen+0.004
used+0.004
Neg logit contributions
 likes-0.005
 and-0.005
 They-0.005
 with-0.005
 nice-0.005
Tokenich
Token ID488
Feature activation-2.46e+00

Pos logit contributions
 hesitation+0.219
otion+0.207
erk+0.195
iqu+0.193
izz+0.189
Neg logit contributions
 and-0.271
 likes-0.268
 with-0.256
 They-0.239
-0.239
Tokenily
Token ID813
Feature activation+2.31e+00

Pos logit contributions
iqu+0.050
used+0.047
ous+0.046
ately+0.046
wen+0.046
Neg logit contributions
 and-0.034
 likes-0.033
 They-0.032
 with-0.030
 liked-0.028
Token wanted
Token ID2227
Feature activation+7.19e-01

Pos logit contributions
 They+0.046
 likes+0.042
 games+0.041
 nice+0.041
 fun+0.040
Neg logit contributions
ow-0.060
iqu-0.059
ately-0.059
erk-0.059
wen-0.057
Token to
Token ID284
Feature activation-2.50e+00

Pos logit contributions
 and+0.006
 likes+0.006
 They+0.006
 with+0.005
 fun+0.004
Neg logit contributions
iqu-0.029
otion-0.029
ately-0.029
wen-0.029
used-0.028
Token feed
Token ID3745
Feature activation-1.63e+00

Pos logit contributions
iqu+0.085
otion+0.083
ately+0.083
wen+0.082
erk+0.081
Neg logit contributions
 and-0.037
 likes-0.037
 They-0.036
 with-0.033
 nice-0.029
Token the
Token ID262
Feature activation-1.95e+00

Pos logit contributions
iqu+0.074
wen+0.071
ous+0.071
ately+0.071
otion+0.071
Neg logit contributions
 and-0.012
 with-0.009
 They-0.008
 likes-0.007
-0.006
Token ostr
Token ID42387
Feature activation-9.93e+00

Pos logit contributions
iqu+0.041
otion+0.040
ately+0.040
used+0.039
erk+0.039
Neg logit contributions
 and-0.055
 likes-0.054
 They-0.053
 with-0.051
 nice-0.049
Tokenich
Token ID488
Feature activation-2.80e+00

Pos logit contributions
otion+0.231
 hesitation+0.224
izz+0.210
erk+0.206
iqu+0.203
Neg logit contributions
 and-0.262
 with-0.241
 likes-0.240
-0.231
 They-0.225
Token too
Token ID1165
Feature activation+1.06e+00

Pos logit contributions
iqu+0.108
otion+0.108
ately+0.108
erk+0.107
ow+0.106
Neg logit contributions
 likes-0.024
 They-0.022
 and-0.020
 with-0.016
 liked-0.015
Token.
Token ID13
Feature activation+1.37e+00

Pos logit contributions
 and+0.007
 likes+0.007
 They+0.007
 with+0.005
 nice+0.004
Neg logit contributions
iqu-0.044
otion-0.044
ately-0.044
wen-0.043
erk-0.043
Token She
Token ID1375
Feature activation+2.53e+00

Pos logit contributions
 likes+0.020
 games+0.019
 and+0.018
 nice+0.018
 fun+0.018
Neg logit contributions
ately-0.043
ow-0.042
iqu-0.042
otion-0.042
used-0.042
Token asked
Token ID1965
Feature activation-1.67e+00

Pos logit contributions
 likes+0.042
 They+0.042
 and+0.041
 with+0.039
 nice+0.036
Neg logit contributions
iqu-0.077
ately-0.076
wen-0.075
erk-0.075
otion-0.074
Token the
Token ID262
Feature activation-1.85e+00

Pos logit contributions
iqu+0.039
otion+0.038
ately+0.038
wen+0.038
erk+0.037
Neg logit contributions
 and-0.013
 They-0.013
 likes-0.012
 with-0.011
-0.010
Token race
Token ID3234
Feature activation-1.70e+00

Pos logit contributions
iqu+0.062
otion+0.060
ately+0.060
wen+0.059
erk+0.059
Neg logit contributions
 and-0.032
 likes-0.031
 nice-0.030
 green-0.029
 fun-0.029
Token started
Token ID2067
Feature activation-7.20e-01

Pos logit contributions
iqu+0.062
ately+0.061
otion+0.061
wen+0.060
erk+0.060
Neg logit contributions
 likes-0.020
 and-0.019
 They-0.019
 with-0.017
 liked-0.014
Token,
Token ID11
Feature activation-2.44e+00

Pos logit contributions
iqu+0.028
otion+0.027
ately+0.027
wen+0.027
erk+0.027
Neg logit contributions
 and-0.008
 They-0.007
 likes-0.007
 with-0.006
-0.005
Token the
Token ID262
Feature activation-2.03e+00

Pos logit contributions
iqu+0.101
wen+0.098
otion+0.097
ately+0.097
erk+0.097
Neg logit contributions
 and-0.022
 They-0.021
 likes-0.019
 with-0.019
-0.014
Token ostr
Token ID42387
Feature activation-9.91e+00

Pos logit contributions
iqu+0.057
otion+0.056
ately+0.055
wen+0.055
erk+0.054
Neg logit contributions
 and-0.046
 likes-0.044
 nice-0.042
 They-0.042
 green-0.041
Tokenich
Token ID488
Feature activation-1.15e+00

Pos logit contributions
 hesitation+0.217
otion+0.214
erk+0.203
iqu+0.196
izz+0.191
Neg logit contributions
 and-0.267
 likes-0.256
 with-0.251
-0.235
 They-0.231
Token ran
Token ID4966
Feature activation+1.26e+00

Pos logit contributions
ately+0.035
iqu+0.035
erk+0.034
wen+0.034
ow+0.034
Neg logit contributions
 They-0.019
 likes-0.018
 and-0.016
 nice-0.015
 with-0.015
Token faster
Token ID5443
Feature activation+1.39e+00

Pos logit contributions
 likes+0.025
 They+0.020
 shapes+0.019
 liked+0.019
 draws+0.018
Neg logit contributions
ow-0.034
used-0.033
ous-0.032
ately-0.032
 hesitation-0.032
Token than
Token ID621
Feature activation-2.11e+00

Pos logit contributions
 likes+0.015
 They+0.014
 pretty+0.010
 nice+0.009
This+0.009
Neg logit contributions
ately-0.050
ge-0.046
ow-0.046
iously-0.046
 hesitation-0.046
Token he
Token ID339
Feature activation-1.61e+00

Pos logit contributions
iqu+0.063
wen+0.058
otion+0.058
used+0.057
ama+0.057
Neg logit contributions
 and-0.050
 with-0.045
 They-0.043
 likes-0.042
 fun-0.041
Token was
Token ID373
Feature activation-1.58e+00

Pos logit contributions
 likes+0.009
 They+0.009
 and+0.009
 with+0.008
 nice+0.007
Neg logit contributions
iqu-0.026
ately-0.025
otion-0.025
wen-0.025
erk-0.025
Token scared
Token ID12008
Feature activation+2.15e+00

Pos logit contributions
iqu+0.052
ately+0.052
otion+0.051
wen+0.050
used+0.050
Neg logit contributions
 likes-0.025
 and-0.025
 They-0.024
 with-0.022
 nice-0.021
Token.
Token ID13
Feature activation+2.00e+00

Pos logit contributions
 likes+0.026
 They+0.022
 liked+0.018
 games+0.018
 grass+0.017
Neg logit contributions
otion-0.076
ately-0.076
iqu-0.075
ous-0.074
ow-0.073
Token
Token ID198
Feature activation+1.92e-01

Pos logit contributions
 likes+0.018
 and+0.015
 games+0.013
 with+0.012
 shapes+0.011
Neg logit contributions
iqu-0.075
otion-0.075
ately-0.074
erk-0.074
antis-0.073
Token
Token ID198
Feature activation-9.82e-01

Pos logit contributions
 likes+0.001
 and+0.001
 They+0.001
 with+0.001
 games+0.001
Neg logit contributions
iqu-0.008
otion-0.008
wen-0.008
ately-0.008
erk-0.008
TokenThey
Token ID2990
Feature activation+3.24e+00

Pos logit contributions
wen+0.031
izz+0.030
iqu+0.030
erk+0.030
ama+0.030
Neg logit contributions
 likes-0.015
 and-0.013
 They-0.012
 shapes-0.012
 games-0.012
Token asked
Token ID1965
Feature activation-1.32e+00

Pos logit contributions
 and+0.051
 They+0.047
 likes+0.047
 with+0.044
 liked+0.043
Neg logit contributions
iqu-0.110
otion-0.109
ous-0.107
used-0.107
wen-0.106
Token Lily
Token ID20037
Feature activation-4.68e-01

Pos logit contributions
iqu+0.046
wen+0.045
otion+0.044
ately+0.044
used+0.044
Neg logit contributions
 and-0.020
 They-0.019
 likes-0.019
 with-0.017
 nice-0.015
Token why
Token ID1521
Feature activation-1.80e+00

Pos logit contributions
iqu+0.016
otion+0.016
ately+0.016
erk+0.015
wen+0.015
Neg logit contributions
 likes-0.006
 They-0.006
 and-0.006
 with-0.005
 fun-0.005
Token she
Token ID673
Feature activation-2.10e+00

Pos logit contributions
used+0.066
iqu+0.065
unct+0.064
ately+0.063
wen+0.062
Neg logit contributions
 and-0.028
 They-0.025
 with-0.024
 likes-0.023
 liked-0.021
Token gave
Token ID2921
Feature activation-1.10e+00

Pos logit contributions
iqu+0.086
otion+0.085
ately+0.085
wen+0.084
used+0.084
Neg logit contributions
 likes-0.018
 and-0.018
 They-0.015
 with-0.013
 liked-0.013
Token are
Token ID389
Feature activation+4.44e-01

Pos logit contributions
 They+0.047
 and+0.044
 with+0.043
 likes+0.042
+0.040
Neg logit contributions
iqu-0.073
erk-0.073
otion-0.072
ow-0.072
illa-0.070
Token the
Token ID262
Feature activation+3.33e+00

Pos logit contributions
 likes+0.006
 They+0.006
 and+0.005
 with+0.005
+0.004
Neg logit contributions
iqu-0.014
otion-0.014
erk-0.014
 hesitation-0.014
wen-0.014
Token best
Token ID1266
Feature activation+1.32e+00

Pos logit contributions
 They+0.058
 likes+0.058
 and+0.056
 with+0.052
 liked+0.048
Neg logit contributions
iqu-0.099
otion-0.095
ately-0.095
wen-0.095
erk-0.094
Token costumes
Token ID24138
Feature activation+1.74e+00

Pos logit contributions
 likes+0.017
 They+0.015
 and+0.014
 liked+0.012
 with+0.012
Neg logit contributions
otion-0.045
iqu-0.045
ous-0.045
ately-0.045
erk-0.044
Token ever
Token ID1683
Feature activation+3.64e-01

Pos logit contributions
 likes+0.032
 They+0.032
 grass+0.028
 green+0.027
 and+0.027
Neg logit contributions
ous-0.048
otion-0.047
ately-0.047
ow-0.046
erk-0.045
Token.
Token ID13
Feature activation+3.01e+00

Pos logit contributions
 They+0.003
 likes+0.003
 and+0.003
 with+0.002
 nice+0.002
Neg logit contributions
ately-0.014
iqu-0.014
otion-0.014
ous-0.014
erk-0.014
Token They
Token ID1119
Feature activation+3.67e+00

Pos logit contributions
 likes+0.019
 and+0.016
 with+0.013
 games+0.013
 nice+0.012
Neg logit contributions
otion-0.115
ately-0.113
iqu-0.113
antis-0.112
erk-0.112
Token thank
Token ID5875
Feature activation-3.04e+00

Pos logit contributions
 They+0.063
 and+0.059
 with+0.059
 likes+0.058
+0.054
Neg logit contributions
erk-0.100
iqu-0.100
ow-0.099
otion-0.099
 hesitation-0.097
Token their
Token ID511
Feature activation-6.27e-01

Pos logit contributions
iqu+0.118
wen+0.115
otion+0.114
erk+0.114
ately+0.113
Neg logit contributions
 and-0.034
 They-0.034
 with-0.032
 likes-0.030
-0.027
Token mom
Token ID1995
Feature activation+1.04e+00

Pos logit contributions
iqu+0.016
ately+0.016
otion+0.016
wen+0.016
erk+0.016
Neg logit contributions
 likes-0.014
 and-0.014
 They-0.013
 with-0.013
 liked-0.012
Token and
Token ID290
Feature activation+1.42e+00

Pos logit contributions
 likes+0.003
 They+0.002
 and+0.000
 with-0.000
 fun-0.001
Neg logit contributions
ately-0.046
iqu-0.046
erk-0.045
otion-0.045
wen-0.045
Token the
Token ID262
Feature activation-5.32e-01

Pos logit contributions
iqu+0.064
otion+0.063
ately+0.063
wen+0.062
erk+0.062
Neg logit contributions
 likes-0.025
 and-0.023
 They-0.023
 with-0.019
 liked-0.019
Token tower
Token ID10580
Feature activation-1.78e+00

Pos logit contributions
otion+0.014
iqu+0.014
antis+0.014
ous+0.014
used+0.014
Neg logit contributions
 They-0.010
 likes-0.009
 and-0.009
 with-0.008
 liked-0.008
Token like
Token ID588
Feature activation+1.04e+00

Pos logit contributions
ately+0.059
ous+0.058
otion+0.058
ow+0.058
erk+0.057
Neg logit contributions
 likes-0.023
 They-0.023
 and-0.020
 nice-0.019
 grass-0.019
Token it
Token ID340
Feature activation+3.97e-01

Pos logit contributions
 likes+0.016
 They+0.015
 and+0.014
 liked+0.013
 with+0.012
Neg logit contributions
aro-0.032
ous-0.032
otion-0.032
ately-0.031
ow-0.031
Token's
Token ID338
Feature activation-8.33e-01

Pos logit contributions
 They+0.006
 likes+0.006
 and+0.005
 grass+0.005
 with+0.005
Neg logit contributions
ous-0.012
ow-0.012
otion-0.012
used-0.011
iqu-0.011
Token a
Token ID257
Feature activation+3.55e+00

Pos logit contributions
iqu+0.026
ous+0.026
otion+0.026
ow+0.026
ately+0.025
Neg logit contributions
 likes-0.013
 They-0.012
 and-0.011
 liked-0.010
 with-0.010
Token king
Token ID5822
Feature activation-4.50e-01

Pos logit contributions
 They+0.050
 likes+0.049
 and+0.047
 with+0.042
 liked+0.038
Neg logit contributions
iqu-0.115
ous-0.112
otion-0.111
erk-0.111
antis-0.110
Token!"
Token ID2474
Feature activation+2.30e-02

Pos logit contributions
ow+0.015
ous+0.015
otion+0.015
ately+0.014
erk+0.014
Neg logit contributions
 They-0.006
 likes-0.006
 and-0.005
 grass-0.005
 with-0.005
Token he
Token ID339
Feature activation+9.31e-01

Pos logit contributions
 likes+0.001
 nice+0.000
 and+0.000
 fair+0.000
 pretty+0.000
Neg logit contributions
ow-0.001
ately-0.001
iqu-0.001
aro-0.001
otion-0.001
Token said
Token ID531
Feature activation-8.08e-02

Pos logit contributions
 likes+0.017
 They+0.017
 and+0.016
 with+0.015
 nice+0.014
Neg logit contributions
ately-0.026
iqu-0.026
ow-0.026
erk-0.025
wen-0.025
Token.
Token ID13
Feature activation-5.14e-01

Pos logit contributions
iqu+0.003
ately+0.003
otion+0.003
wen+0.003
erk+0.003
Neg logit contributions
 likes-0.001
 and-0.001
 They-0.001
 with-0.000
 liked-0.000
Token all
Token ID477
Feature activation+1.55e+00

Pos logit contributions
 likes+0.010
 They+0.009
 and+0.007
 shapes+0.007
 green+0.007
Neg logit contributions
ately-0.024
otion-0.023
ous-0.023
erk-0.023
wen-0.023
Token day
Token ID1110
Feature activation+7.02e-02

Pos logit contributions
 likes+0.027
 They+0.027
 and+0.026
 piles+0.023
 with+0.022
Neg logit contributions
ow-0.043
erk-0.042
otion-0.042
ous-0.041
aro-0.041
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
 likes+0.001
 They+0.001
 and+0.001
 with+0.001
 liked+0.001
Neg logit contributions
ately-0.002
iqu-0.002
otion-0.002
ous-0.002
wen-0.002
Token He
Token ID679
Feature activation+2.12e+00

Pos logit contributions
 likes+0.010
 and+0.009
 with+0.009
 games+0.008
 nice+0.008
Neg logit contributions
otion-0.037
ow-0.037
wen-0.036
erk-0.036
ous-0.036
Token had
Token ID550
Feature activation+1.46e+00

Pos logit contributions
 likes+0.035
 They+0.035
 and+0.034
 with+0.031
 nice+0.029
Neg logit contributions
iqu-0.065
ately-0.064
otion-0.064
wen-0.064
erk-0.064
Token a
Token ID257
Feature activation+4.55e+00

Pos logit contributions
 likes+0.025
 They+0.024
 and+0.021
 with+0.019
 girl+0.019
Neg logit contributions
ow-0.039
erk-0.039
 hesitation-0.038
wen-0.038
iqu-0.037
Token lot
Token ID1256
Feature activation-8.75e-01

Pos logit contributions
 They+0.054
 likes+0.050
 and+0.047
 with+0.045
 shapes+0.038
Neg logit contributions
iqu-0.153
erk-0.146
 hesitation-0.145
ama-0.144
antis-0.143
Token of
Token ID286
Feature activation+2.71e+00

Pos logit contributions
iqu+0.024
ately+0.024
otion+0.024
ow+0.024
erk+0.023
Neg logit contributions
 likes-0.017
 They-0.017
 and-0.015
 with-0.014
 liked-0.014
Token toys
Token ID14958
Feature activation+8.82e-01

Pos logit contributions
 likes+0.023
 They+0.022
 and+0.020
 with+0.018
 liked+0.014
Neg logit contributions
iqu-0.102
otion-0.101
erk-0.101
 hesitation-0.100
ow-0.099
Token and
Token ID290
Feature activation+2.20e-03

Pos logit contributions
 They+0.010
 likes+0.010
 and+0.007
 shapes+0.007
 sounds+0.007
Neg logit contributions
ately-0.031
ow-0.031
otion-0.031
erk-0.031
iqu-0.030
Token treats
Token ID18432
Feature activation+1.99e-01

Pos logit contributions
 likes+0.000
 They+0.000
 and+0.000
 with+0.000
 nice+0.000
Neg logit contributions
iqu-0.000
ately-0.000
otion-0.000
wen-0.000
erk-0.000
Token himself
Token ID2241
Feature activation-9.98e-01

Pos logit contributions
 likes+0.011
 They+0.009
 liked+0.008
 games+0.008
 and+0.008
Neg logit contributions
ately-0.017
aro-0.017
izz-0.017
iqu-0.017
otion-0.017
Token clean
Token ID3424
Feature activation+7.95e-01

Pos logit contributions
iqu+0.032
icking+0.031
erk+0.031
otion+0.031
ow+0.031
Neg logit contributions
 They-0.015
 likes-0.015
-0.012
 and-0.011
 liked-0.011
Token.
Token ID13
Feature activation+7.37e-01

Pos logit contributions
 likes+0.011
 They+0.009
 liked+0.008
+0.008
 fun+0.007
Neg logit contributions
ately-0.026
otion-0.025
icking-0.025
erk-0.025
iqu-0.025
Token He
Token ID679
Feature activation+1.73e+00

Pos logit contributions
 likes+0.011
 and+0.010
 games+0.009
 with+0.009
 nice+0.009
Neg logit contributions
iqu-0.024
ately-0.023
otion-0.023
erk-0.023
wen-0.023
Token felt
Token ID2936
Feature activation+2.02e+00

Pos logit contributions
 They+0.033
 likes+0.032
 with+0.028
 and+0.028
 nice+0.027
Neg logit contributions
iqu-0.046
ately-0.046
erk-0.046
wen-0.045
izz-0.044
Token much
Token ID881
Feature activation+2.84e+00

Pos logit contributions
 likes+0.033
 They+0.030
 and+0.026
 games+0.026
 shapes+0.025
Neg logit contributions
otion-0.059
iqu-0.058
 hesitation-0.058
izz-0.057
erk-0.056
Token better
Token ID1365
Feature activation+1.03e+00

Pos logit contributions
 likes+0.063
 They+0.062
 games+0.055
 liked+0.053
 and+0.051
Neg logit contributions
iqu-0.067
 hesitation-0.067
otion-0.063
izz-0.062
icking-0.061
Token!
Token ID0
Feature activation+1.54e+00

Pos logit contributions
 likes+0.010
 They+0.010
 and+0.008
 with+0.007
 nice+0.007
Neg logit contributions
ately-0.039
iqu-0.039
otion-0.038
erk-0.038
used-0.038
Token
Token ID220
Feature activation+1.04e-01

Pos logit contributions
 likes+0.025
 and+0.024
 games+0.022
 with+0.021
 nice+0.021
Neg logit contributions
iqu-0.047
ately-0.046
erk-0.046
wen-0.046
otion-0.045
Token
Token ID198
Feature activation+9.43e-01

Pos logit contributions
 likes+0.001
 and+0.001
 They+0.000
 games+0.000
 with+0.000
Neg logit contributions
iqu-0.004
otion-0.004
wen-0.004
erk-0.004
ately-0.004
Token
Token ID198
Feature activation-6.42e-01

Pos logit contributions
 likes+0.008
 They+0.006
 and+0.006
 games+0.005
 shapes+0.005
Neg logit contributions
wen-0.036
erk-0.036
ately-0.036
otion-0.035
izz-0.035
Token.
Token ID13
Feature activation+8.13e-01

Pos logit contributions
 likes+0.006
 They+0.005
 and+0.005
 with+0.004
 fun+0.004
Neg logit contributions
iqu-0.026
otion-0.026
ately-0.025
erk-0.025
ous-0.025
Token
Token ID198
Feature activation-8.90e-02

Pos logit contributions
 likes+0.009
 and+0.007
 games+0.007
 fun+0.006
 They+0.006
Neg logit contributions
otion-0.029
iqu-0.029
ately-0.029
ous-0.029
erk-0.029
Token
Token ID198
Feature activation-7.53e-01

Pos logit contributions
izz+0.003
wen+0.003
otion+0.003
iqu+0.003
erk+0.003
Neg logit contributions
 likes-0.001
 games-0.001
 and-0.001
 shapes-0.001
 They-0.001
TokenL
Token ID43
Feature activation-1.46e+00

Pos logit contributions
izz+0.022
wen+0.021
iqu+0.021
otion+0.020
ately+0.020
Neg logit contributions
 likes-0.013
 and-0.012
 They-0.011
 green-0.011
 shapes-0.011
Tokenily
Token ID813
Feature activation+2.09e+00

Pos logit contributions
iqu+0.040
ately+0.039
otion+0.039
wen+0.038
erk+0.038
Neg logit contributions
 likes-0.031
 and-0.030
 They-0.030
 with-0.028
 liked-0.026
Token said
Token ID531
Feature activation-2.58e-01

Pos logit contributions
 They+0.036
 likes+0.035
 fun+0.031
 games+0.031
 nice+0.030
Neg logit contributions
ately-0.062
iqu-0.062
erk-0.060
ow-0.060
wen-0.060
Token,
Token ID11
Feature activation+4.90e-01

Pos logit contributions
otion+0.009
iqu+0.009
ately+0.009
ous+0.009
used+0.009
Neg logit contributions
 likes-0.003
 They-0.003
 and-0.003
 with-0.002
 fun-0.002
Token "
Token ID366
Feature activation+3.04e+00

Pos logit contributions
 likes+0.005
 and+0.004
 They+0.004
 with+0.003
 fun+0.003
Neg logit contributions
iqu-0.019
otion-0.019
ately-0.019
wen-0.018
erk-0.018
TokenLet
Token ID5756
Feature activation+2.42e-01

Pos logit contributions
 likes+0.047
 and+0.046
 They+0.045
 with+0.041
 nice+0.037
Neg logit contributions
iqu-0.100
ately-0.098
otion-0.098
wen-0.097
erk-0.096
Token's
Token ID338
Feature activation-1.49e+00

Pos logit contributions
 likes+0.003
 They+0.003
 liked+0.002
 games+0.002
 and+0.002
Neg logit contributions
iqu-0.008
unct-0.008
ow-0.008
wen-0.008
otion-0.008
Token find
Token ID1064
Feature activation+8.93e-02

Pos logit contributions
iqu+0.051
otion+0.051
ately+0.051
wen+0.050
ous+0.050
Neg logit contributions
 and-0.021
 They-0.021
 likes-0.020
 with-0.019
 nice-0.017
Token felt
Token ID2936
Feature activation+2.19e+00

Pos logit contributions
 and+0.048
 likes+0.047
 They+0.046
 with+0.041
 liked+0.040
Neg logit contributions
iqu-0.100
otion-0.099
ately-0.097
wen-0.097
used-0.096
Token scared
Token ID12008
Feature activation+2.65e+00

Pos logit contributions
 likes+0.044
 They+0.042
 and+0.041
 with+0.038
 games+0.036
Neg logit contributions
iqu-0.060
otion-0.059
ow-0.057
erk-0.057
 hesitation-0.057
Token and
Token ID290
Feature activation-1.38e+00

Pos logit contributions
 likes+0.018
 They+0.011
 liked+0.007
 games+0.006
 shapes+0.006
Neg logit contributions
ately-0.109
otion-0.108
ous-0.107
ow-0.105
iqu-0.105
Token sad
Token ID6507
Feature activation+2.83e+00

Pos logit contributions
iqu+0.036
wen+0.036
ately+0.036
otion+0.035
ous+0.034
Neg logit contributions
 likes-0.031
 and-0.031
 They-0.031
 with-0.029
 nice-0.027
Token.
Token ID13
Feature activation+1.96e+00

Pos logit contributions
 likes+0.029
 They+0.024
 and+0.021
 liked+0.019
 with+0.019
Neg logit contributions
ately-0.105
ous-0.104
otion-0.103
iqu-0.102
erk-0.101
Token They
Token ID1119
Feature activation+2.52e+00

Pos logit contributions
 likes+0.013
 and+0.010
 games+0.007
 with+0.007
 nice+0.007
Neg logit contributions
ately-0.080
iqu-0.080
otion-0.079
antis-0.078
used-0.077
Token did
Token ID750
Feature activation-5.07e-01

Pos logit contributions
 and+0.043
 likes+0.042
 They+0.042
 with+0.037
 liked+0.037
Neg logit contributions
iqu-0.080
otion-0.079
ately-0.079
wen-0.078
used-0.078
Token not
Token ID407
Feature activation-1.37e+00

Pos logit contributions
iqu+0.013
ately+0.013
otion+0.013
wen+0.012
used+0.012
Neg logit contributions
 likes-0.012
 and-0.012
 They-0.012
 with-0.011
 nice-0.010
Token know
Token ID760
Feature activation+7.90e-02

Pos logit contributions
iqu+0.039
otion+0.038
ately+0.038
wen+0.037
erk+0.037
Neg logit contributions
 likes-0.027
 and-0.027
 They-0.027
 with-0.025
 liked-0.023
Token how
Token ID703
Feature activation+3.59e-01

Pos logit contributions
 and+0.001
 with+0.001
 They+0.001
 each+0.001
 fun+0.001
Neg logit contributions
unct-0.003
used-0.003
wen-0.003
istent-0.003
iqu-0.003
Token to
Token ID284
Feature activation-3.60e+00

Pos logit contributions
 and+0.003
 likes+0.003
 They+0.003
 with+0.003
 nice+0.002
Neg logit contributions
iqu-0.014
otion-0.014
ately-0.014
wen-0.014
used-0.014
Token from
Token ID422
Feature activation-1.59e+00

Pos logit contributions
iqu+0.081
otion+0.079
wen+0.078
ately+0.078
used+0.077
Neg logit contributions
 and-0.049
 They-0.046
 with-0.044
 likes-0.041
 nice-0.038
Token inside
Token ID2641
Feature activation-6.03e-01

Pos logit contributions
iqu+0.055
otion+0.054
ately+0.054
wen+0.053
erk+0.053
Neg logit contributions
 likes-0.021
 They-0.020
 and-0.020
 with-0.017
 nice-0.016
Token.
Token ID13
Feature activation-6.56e-01

Pos logit contributions
iqu+0.024
otion+0.024
ately+0.024
wen+0.023
erk+0.023
Neg logit contributions
 likes-0.005
 and-0.005
 They-0.005
 with-0.004
 liked-0.003
Token It
Token ID632
Feature activation-8.16e-01

Pos logit contributions
used+0.021
ately+0.021
otion+0.021
iqu+0.021
erk+0.021
Neg logit contributions
 likes-0.009
 and-0.008
 They-0.008
 games-0.008
 fun-0.007
Token was
Token ID373
Feature activation-2.55e+00

Pos logit contributions
iqu+0.033
ately+0.033
otion+0.033
wen+0.032
used+0.032
Neg logit contributions
 and-0.007
 likes-0.007
 They-0.006
 with-0.006
 liked-0.005
Token a
Token ID257
Feature activation+1.74e+00

Pos logit contributions
ately+0.109
unct+0.107
used+0.107
iqu+0.107
otion+0.107
Neg logit contributions
 and-0.024
 with-0.019
 They-0.018
 nice-0.015
 green-0.015
Token loud
Token ID7812
Feature activation+1.41e+00

Pos logit contributions
 and+0.020
 likes+0.020
 They+0.019
 with+0.018
 nice+0.017
Neg logit contributions
ately-0.064
iqu-0.064
otion-0.064
wen-0.063
used-0.063
Token scream
Token ID8196
Feature activation-1.73e+00

Pos logit contributions
 likes+0.024
 They+0.023
 and+0.022
 with+0.021
 liked+0.020
Neg logit contributions
otion-0.043
iqu-0.042
ous-0.042
ately-0.042
erk-0.041
Token!
Token ID0
Feature activation-1.86e-01

Pos logit contributions
iqu+0.070
unct+0.068
wen+0.068
used+0.067
ately+0.067
Neg logit contributions
 and-0.019
 with-0.016
 They-0.016
 likes-0.014
 nice-0.011
Token
Token ID220
Feature activation-7.28e-01

Pos logit contributions
otion+0.005
used+0.005
ately+0.005
iqu+0.005
erk+0.005
Neg logit contributions
 likes-0.004
 and-0.003
 games-0.003
 fun-0.003
 shapes-0.003
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
otion+0.029
wen+0.028
iqu+0.028
erk+0.028
ately+0.028
Neg logit contributions
 likes-0.006
 games-0.004
 and-0.004
 fair-0.004
 green-0.004
Token to
Token ID284
Feature activation-2.52e+00

Pos logit contributions
iqu+0.066
ately+0.064
wen+0.064
otion+0.064
erk+0.063
Neg logit contributions
 and-0.020
 likes-0.019
 They-0.019
 with-0.018
 nice-0.015
Token Jimmy
Token ID12963
Feature activation-1.34e+00

Pos logit contributions
iqu+0.076
antis+0.071
otion+0.071
ately+0.071
wen+0.071
Neg logit contributions
 and-0.051
 They-0.049
 likes-0.047
 with-0.046
-0.044
Token,
Token ID11
Feature activation-1.29e-01

Pos logit contributions
iqu+0.052
otion+0.051
ately+0.051
wen+0.051
erk+0.050
Neg logit contributions
 and-0.013
 likes-0.013
 They-0.012
 with-0.011
 nice-0.009
Token "
Token ID366
Feature activation+9.50e-01

Pos logit contributions
iqu+0.005
ately+0.005
otion+0.005
wen+0.005
erk+0.005
Neg logit contributions
 and-0.001
 likes-0.001
 They-0.001
 with-0.001
-0.001
TokenDon
Token ID3987
Feature activation-3.08e+00

Pos logit contributions
 likes+0.016
 and+0.016
 They+0.015
 with+0.014
+0.013
Neg logit contributions
iqu-0.030
otion-0.030
ately-0.029
erk-0.029
wen-0.029
Token't
Token ID470
Feature activation-1.42e+00

Pos logit contributions
iqu+0.066
erk+0.060
ately+0.060
antis+0.059
unct+0.059
Neg logit contributions
 and-0.092
 They-0.088
 with-0.087
-0.086
 likes-0.083
Token be
Token ID307
Feature activation-1.31e+00

Pos logit contributions
iqu+0.037
otion+0.037
wen+0.037
ately+0.037
erk+0.035
Neg logit contributions
 and-0.032
 likes-0.031
 They-0.031
 with-0.030
 nice-0.028
Token scared
Token ID12008
Feature activation+1.06e-01

Pos logit contributions
iqu+0.033
otion+0.032
ately+0.032
wen+0.032
erk+0.032
Neg logit contributions
 likes-0.030
 They-0.029
 and-0.029
 with-0.027
 liked-0.026
Token,
Token ID11
Feature activation-3.72e-01

Pos logit contributions
 likes+0.001
 They+0.001
 and+0.001
 with+0.001
 liked+0.001
Neg logit contributions
iqu-0.004
otion-0.004
ately-0.004
ous-0.004
used-0.004
Token I
Token ID314
Feature activation-2.19e-01

Pos logit contributions
iqu+0.011
wen+0.011
ately+0.011
otion+0.011
erk+0.011
Neg logit contributions
 and-0.007
 likes-0.007
 They-0.007
 with-0.006
 nice-0.006
Token won
Token ID1839
Feature activation-3.34e+00

Pos logit contributions
otion+0.007
iqu+0.007
ately+0.007
wen+0.007
unct+0.007
Neg logit contributions
 and-0.004
 likes-0.004
 They-0.003
 with-0.003
-0.003
Token told
Token ID1297
Feature activation-6.10e-01

Pos logit contributions
 likes+0.005
 They+0.005
 and+0.005
 with+0.004
 nice+0.004
Neg logit contributions
iqu-0.009
ately-0.009
otion-0.009
wen-0.009
erk-0.009
Token her
Token ID607
Feature activation-7.13e-01

Pos logit contributions
iqu+0.021
ately+0.021
otion+0.021
wen+0.020
erk+0.020
Neg logit contributions
 likes-0.008
 and-0.008
 They-0.008
 with-0.007
 liked-0.007
Token she
Token ID673
Feature activation+1.73e-01

Pos logit contributions
iqu+0.027
wen+0.026
used+0.026
ately+0.026
erk+0.026
Neg logit contributions
 and-0.009
 They-0.009
 likes-0.008
 with-0.008
 nice-0.007
Token could
Token ID714
Feature activation-1.98e+00

Pos logit contributions
 likes+0.003
 and+0.003
 They+0.003
 with+0.002
 liked+0.002
Neg logit contributions
iqu-0.006
otion-0.006
ately-0.006
wen-0.006
used-0.006
Token use
Token ID779
Feature activation+8.32e-01

Pos logit contributions
iqu+0.066
otion+0.065
ately+0.065
wen+0.064
used+0.063
Neg logit contributions
 and-0.032
 likes-0.031
 They-0.030
 with-0.029
 liked-0.025
Token it
Token ID340
Feature activation-4.84e-01

Pos logit contributions
 likes+0.010
 They+0.009
 and+0.009
 with+0.008
 liked+0.007
Neg logit contributions
iqu-0.030
ately-0.030
otion-0.030
wen-0.029
erk-0.029
Token for
Token ID329
Feature activation+1.07e-02

Pos logit contributions
iqu+0.018
ately+0.018
otion+0.018
wen+0.018
erk+0.018
Neg logit contributions
 likes-0.005
 and-0.005
 They-0.005
 with-0.004
 liked-0.003
Token her
Token ID607
Feature activation-3.38e-01

Pos logit contributions
 and+0.000
 fun+0.000
 with+0.000
 They+0.000
 nice+0.000
Neg logit contributions
iqu-0.000
used-0.000
otion-0.000
ous-0.000
wen-0.000
Token pretend
Token ID16614
Feature activation-4.98e-01

Pos logit contributions
iqu+0.011
ately+0.011
otion+0.011
erk+0.011
used+0.011
Neg logit contributions
 likes-0.005
 They-0.005
 and-0.004
 with-0.004
 liked-0.004
Token play
Token ID711
Feature activation+1.23e+00

Pos logit contributions
iqu+0.013
ately+0.012
erk+0.012
ous+0.012
ow+0.012
Neg logit contributions
 They-0.010
 likes-0.010
 and-0.009
 with-0.009
-0.009
Token.
Token ID13
Feature activation+5.78e-01

Pos logit contributions
 likes+0.014
 They+0.014
 and+0.010
 liked+0.009
+0.009
Neg logit contributions
otion-0.043
ow-0.042
erk-0.042
ately-0.041
aro-0.040
Token top
Token ID1353
Feature activation-1.82e+00

Pos logit contributions
 likes+0.004
 They+0.004
 and+0.004
 liked+0.004
 games+0.004
Neg logit contributions
otion-0.005
wen-0.005
ately-0.005
aro-0.005
iqu-0.005
Token.
Token ID13
Feature activation+8.98e-01

Pos logit contributions
iqu+0.071
ately+0.071
otion+0.071
wen+0.070
erk+0.069
Neg logit contributions
 likes-0.015
 They-0.014
 and-0.013
 with-0.011
 liked-0.010
Token "
Token ID366
Feature activation+1.67e+00

Pos logit contributions
 likes+0.012
 fair+0.012
 than+0.011
 games+0.011
 nice+0.011
Neg logit contributions
otion-0.027
abella-0.025
izz-0.025
ately-0.024
erk-0.024
TokenLet
Token ID5756
Feature activation+6.24e-02

Pos logit contributions
 likes+0.025
 and+0.025
 They+0.022
 with+0.022
 new+0.021
Neg logit contributions
izz-0.051
erk-0.051
wen-0.051
otion-0.050
ately-0.050
Token's
Token ID338
Feature activation-1.42e+00

Pos logit contributions
 likes+0.001
 They+0.001
 than+0.001
 with+0.001
 and+0.001
Neg logit contributions
ow-0.002
wen-0.002
otion-0.002
iqu-0.002
used-0.002
Token go
Token ID467
Feature activation-1.81e+00

Pos logit contributions
iqu+0.049
otion+0.048
ately+0.047
wen+0.047
ous+0.046
Neg logit contributions
 and-0.021
 likes-0.021
 They-0.021
 with-0.019
 nice-0.017
Token sled
Token ID46822
Feature activation-2.77e+00

Pos logit contributions
iqu+0.066
ately+0.065
otion+0.065
wen+0.064
erk+0.064
Neg logit contributions
 likes-0.020
 They-0.019
 and-0.018
 with-0.016
 liked-0.014
Tokending
Token ID12083
Feature activation-2.00e+00

Pos logit contributions
iqu+0.080
ately+0.080
otion+0.079
ous+0.078
wen+0.078
Neg logit contributions
 likes-0.051
 They-0.048
 and-0.047
 with-0.043
 nice-0.042
Token!"
Token ID2474
Feature activation+7.06e-01

Pos logit contributions
iqu+0.072
ately+0.071
otion+0.071
wen+0.070
used+0.070
Neg logit contributions
 likes-0.024
 They-0.022
 and-0.022
 with-0.019
 liked-0.018
Token Anna
Token ID11735
Feature activation+1.85e+00

Pos logit contributions
 likes+0.014
 nice+0.012
 fair+0.012
 games+0.012
 liked+0.012
Neg logit contributions
otion-0.017
ately-0.017
ow-0.016
wen-0.016
izz-0.016
Token said
Token ID531
Feature activation-2.76e-01

Pos logit contributions
 likes+0.031
 They+0.029
 nice+0.027
 games+0.026
 fun+0.026
Neg logit contributions
ately-0.054
ow-0.054
erk-0.053
wen-0.052
iqu-0.052
Token wise
Token ID10787
Feature activation-2.24e+00

Pos logit contributions
iqu+0.024
otion+0.023
wen+0.023
ately+0.023
used+0.023
Neg logit contributions
 and-0.010
 likes-0.010
 They-0.009
 with-0.009
 nice-0.008
Token owl
Token ID39610
Feature activation-9.97e-01

Pos logit contributions
iqu+0.075
ately+0.074
otion+0.074
wen+0.073
erk+0.072
Neg logit contributions
 likes-0.032
 and-0.031
 They-0.031
 with-0.028
 liked-0.025
Token looked
Token ID3114
Feature activation+2.64e+00

Pos logit contributions
iqu+0.031
ately+0.031
otion+0.031
ow+0.030
erk+0.030
Neg logit contributions
 They-0.016
 likes-0.015
 and-0.014
 with-0.013
 games-0.013
Token at
Token ID379
Feature activation-2.48e-01

Pos logit contributions
 They+0.048
 likes+0.044
 games+0.043
 shapes+0.042
Let+0.040
Neg logit contributions
iqu-0.074
icking-0.069
unct-0.068
 hesitation-0.067
used-0.067
Token the
Token ID262
Feature activation-8.12e-01

Pos logit contributions
iqu+0.010
otion+0.010
ately+0.010
wen+0.010
used+0.010
Neg logit contributions
 and-0.002
 They-0.002
 likes-0.002
 with-0.002
-0.001
Token bird
Token ID6512
Feature activation-2.28e+00

Pos logit contributions
iqu+0.026
otion+0.026
ately+0.026
wen+0.025
erk+0.025
Neg logit contributions
 likes-0.013
 and-0.013
 They-0.012
 with-0.011
 nice-0.010
Token's
Token ID338
Feature activation-1.91e+00

Pos logit contributions
iqu+0.099
ately+0.098
otion+0.098
erk+0.097
used+0.096
Neg logit contributions
 likes-0.010
 They-0.009
 and-0.007
 with-0.004
 liked-0.003
Token wing
Token ID8539
Feature activation-1.55e+00

Pos logit contributions
iqu+0.044
ately+0.043
otion+0.042
erk+0.042
wen+0.041
Neg logit contributions
 likes-0.047
 They-0.047
 and-0.045
 with-0.043
 liked-0.041
Token and
Token ID290
Feature activation-5.27e-01

Pos logit contributions
ately+0.064
iqu+0.064
erk+0.063
otion+0.063
ous+0.063
Neg logit contributions
 likes-0.009
 They-0.009
 and-0.006
 with-0.004
 fun-0.004
Token sighed
Token ID21893
Feature activation+1.65e+00

Pos logit contributions
iqu+0.016
ately+0.016
otion+0.016
erk+0.016
wen+0.016
Neg logit contributions
 likes-0.009
 They-0.009
 and-0.009
 with-0.008
 nice-0.007
Token.
Token ID13
Feature activation+5.59e-01

Pos logit contributions
 likes+0.016
 They+0.014
 and+0.012
 games+0.010
 fun+0.010
Neg logit contributions
iqu-0.062
ately-0.061
erk-0.061
otion-0.061
ous-0.061
Token there
Token ID612
Feature activation-2.33e-01

Pos logit contributions
otion+0.103
ately+0.101
ous+0.101
wen+0.101
iqu+0.099
Neg logit contributions
 and-0.027
 with-0.025
 nice-0.023
 They-0.021
 fun-0.021
Token.
Token ID13
Feature activation+2.01e-01

Pos logit contributions
iqu+0.010
otion+0.010
ately+0.010
wen+0.010
used+0.009
Neg logit contributions
 and-0.001
 likes-0.001
 They-0.001
 with-0.001
 nice-0.001
Token She
Token ID1375
Feature activation+1.01e+00

Pos logit contributions
 likes+0.003
 and+0.002
 games+0.002
 nice+0.002
 fun+0.002
Neg logit contributions
ately-0.006
used-0.006
ow-0.006
iqu-0.006
otion-0.006
Token asked
Token ID1965
Feature activation-1.29e+00

Pos logit contributions
 likes+0.016
 They+0.016
 and+0.015
 with+0.014
 nice+0.013
Neg logit contributions
iqu-0.032
ately-0.032
wen-0.031
erk-0.031
otion-0.031
Token her
Token ID607
Feature activation-1.65e+00

Pos logit contributions
iqu+0.045
ately+0.044
otion+0.044
wen+0.044
erk+0.043
Neg logit contributions
 likes-0.018
 and-0.017
 They-0.017
 with-0.015
 liked-0.014
Token mother
Token ID2802
Feature activation-1.85e+00

Pos logit contributions
iqu+0.048
otion+0.047
ately+0.047
wen+0.046
used+0.046
Neg logit contributions
 and-0.033
 likes-0.033
 They-0.032
 with-0.030
 nice-0.029
Token to
Token ID284
Feature activation-2.76e+00

Pos logit contributions
iqu+0.066
wen+0.065
ately+0.064
otion+0.063
used+0.063
Neg logit contributions
 and-0.027
 likes-0.025
 They-0.024
 with-0.024
-0.020
Token go
Token ID467
Feature activation-2.20e+00

Pos logit contributions
iqu+0.093
otion+0.089
ous+0.089
ately+0.088
wen+0.088
Neg logit contributions
 and-0.050
 with-0.046
 They-0.044
 likes-0.043
 nice-0.040
Token but
Token ID475
Feature activation-2.62e+00

Pos logit contributions
iqu+0.087
otion+0.086
ately+0.085
wen+0.085
ous+0.084
Neg logit contributions
 and-0.022
 likes-0.020
 They-0.019
 with-0.019
-0.014
Token her
Token ID607
Feature activation-1.65e+00

Pos logit contributions
iqu+0.103
antis+0.097
ous+0.097
ules+0.096
wen+0.096
Neg logit contributions
 and-0.038
 with-0.034
 They-0.029
 likes-0.028
 liked-0.027
Token mother
Token ID2802
Feature activation-1.81e+00

Pos logit contributions
otion+0.047
aro+0.045
iqu+0.044
izz+0.044
ous+0.044
Neg logit contributions
 and-0.038
 likes-0.036
 with-0.034
 nice-0.033
 They-0.033
Token,
Token ID11
Feature activation-2.82e+00

Pos logit contributions
iqu+0.131
wen+0.127
ately+0.126
otion+0.126
erk+0.125
Neg logit contributions
 and-0.027
 They-0.026
 likes-0.025
 with-0.023
-0.018
Token they
Token ID484
Feature activation+1.25e+00

Pos logit contributions
iqu+0.100
unct+0.097
otion+0.097
wen+0.097
erk+0.097
Neg logit contributions
 and-0.043
 They-0.042
 likes-0.038
 with-0.038
 fun-0.034
Token see
Token ID766
Feature activation+1.95e-01

Pos logit contributions
 likes+0.022
 They+0.021
 shapes+0.020
 with+0.020
 and+0.020
Neg logit contributions
otion-0.034
ow-0.033
ately-0.033
used-0.033
erk-0.033
Token a
Token ID257
Feature activation-1.96e-01

Pos logit contributions
 likes+0.002
 They+0.002
 and+0.002
 with+0.002
 liked+0.002
Neg logit contributions
iqu-0.007
otion-0.007
ately-0.007
wen-0.007
erk-0.007
Token big
Token ID1263
Feature activation+1.96e+00

Pos logit contributions
ately+0.008
iqu+0.008
otion+0.008
wen+0.008
used+0.008
Neg logit contributions
 and-0.001
 likes-0.001
 They-0.001
 with-0.001
 nice-0.001
Token club
Token ID3430
Feature activation-1.99e+00

Pos logit contributions
 likes+0.030
 They+0.030
 and+0.029
 with+0.027
+0.025
Neg logit contributions
iqu-0.061
otion-0.061
ately-0.060
erk-0.059
ous-0.059
Token on
Token ID319
Feature activation-5.71e-01

Pos logit contributions
otion+0.071
iqu+0.068
used+0.067
ow+0.067
ately+0.067
Neg logit contributions
 likes-0.023
 They-0.022
 and-0.018
 fun-0.016
 nice-0.016
Token the
Token ID262
Feature activation-1.67e-01

Pos logit contributions
iqu+0.024
ately+0.023
otion+0.023
wen+0.023
erk+0.023
Neg logit contributions
 and-0.004
 They-0.004
 likes-0.004
 with-0.003
 nice-0.003
Token grass
Token ID8701
Feature activation-1.69e+00

Pos logit contributions
wen+0.004
iqu+0.004
ately+0.004
tha+0.004
unct+0.004
Neg logit contributions
 likes-0.003
 They-0.003
 and-0.003
 with-0.003
 liked-0.003
Token.
Token ID13
Feature activation-2.90e-01

Pos logit contributions
iqu+0.074
ately+0.072
wen+0.072
unct+0.072
otion+0.072
Neg logit contributions
 and-0.010
 They-0.009
 likes-0.008
 with-0.007
-0.004
Token It
Token ID632
Feature activation-4.53e-01

Pos logit contributions
otion+0.010
ately+0.009
ow+0.009
used+0.009
iqu+0.009
Neg logit contributions
 likes-0.004
 and-0.003
 nice-0.003
 with-0.003
 games-0.003
Tokenily
Token ID813
Feature activation+1.69e+00

Pos logit contributions
otion+0.053
ately+0.052
iqu+0.052
wen+0.051
erk+0.050
Neg logit contributions
 They-0.048
 likes-0.048
 and-0.046
 with-0.044
 fun-0.041
Token was
Token ID373
Feature activation-5.40e-01

Pos logit contributions
 They+0.026
 likes+0.023
 games+0.022
 with+0.021
 nice+0.021
Neg logit contributions
wen-0.051
ately-0.051
iqu-0.050
ow-0.050
unct-0.050
Token sad
Token ID6507
Feature activation+2.43e+00

Pos logit contributions
iqu+0.019
ately+0.019
otion+0.019
wen+0.019
ous+0.019
Neg logit contributions
 and-0.007
 likes-0.007
 They-0.006
 with-0.006
 nice-0.006
Token because
Token ID780
Feature activation-1.55e+00

Pos logit contributions
 likes+0.034
 They+0.031
 games+0.026
 and+0.026
 liked+0.025
Neg logit contributions
ately-0.083
ous-0.081
otion-0.081
iqu-0.081
erk-0.078
Token she
Token ID673
Feature activation-4.05e-01

Pos logit contributions
iqu+0.063
erk+0.059
ately+0.059
wen+0.058
owing+0.058
Neg logit contributions
 and-0.023
 with-0.021
 They-0.017
-0.016
 green-0.016
Token couldn
Token ID3521
Feature activation-4.57e+00

Pos logit contributions
iqu+0.012
ately+0.012
otion+0.012
wen+0.012
erk+0.012
Neg logit contributions
 likes-0.007
 and-0.007
 They-0.007
 with-0.006
 liked-0.006
Token't
Token ID470
Feature activation-3.02e+00

Pos logit contributions
iqu+0.102
 hesitation+0.100
ately+0.100
erk+0.092
ules+0.091
Neg logit contributions
 and-0.133
 They-0.131
 with-0.128
-0.127
 likes-0.122
Token stand
Token ID1302
Feature activation-1.37e+00

Pos logit contributions
iqu+0.110
wen+0.105
otion+0.103
ately+0.102
used+0.102
Neg logit contributions
 and-0.048
 with-0.043
 likes-0.041
 They-0.040
 liked-0.037
Token up
Token ID510
Feature activation+1.52e+00

Pos logit contributions
ately+0.051
otion+0.050
wen+0.050
ous+0.049
iqu+0.049
Neg logit contributions
 and-0.020
 with-0.019
 nice-0.015
 likes-0.015
 pretty-0.015
Token to
Token ID284
Feature activation-1.83e+00

Pos logit contributions
 and+0.012
 likes+0.011
 They+0.011
 with+0.010
 nice+0.007
Neg logit contributions
iqu-0.062
otion-0.061
ately-0.061
wen-0.061
used-0.060
Token play
Token ID711
Feature activation+1.86e+00

Pos logit contributions
iqu+0.074
wen+0.071
otion+0.070
ately+0.069
ules+0.069
Neg logit contributions
 and-0.023
 with-0.020
 likes-0.019
 They-0.018
-0.017
Token in
Token ID287
Feature activation+1.56e+00

Pos logit contributions
 likes+0.029
 They+0.024
 piles+0.022
 shapes+0.022
 fun+0.022
Neg logit contributions
ow-0.053
aro-0.052
used-0.051
ately-0.051
ous-0.050
Token the
Token ID262
Feature activation+8.68e-01

Pos logit contributions
 likes+0.020
 They+0.016
 and+0.015
 liked+0.014
 with+0.013
Neg logit contributions
otion-0.054
erk-0.053
ow-0.053
wen-0.053
iqu-0.053
Token rain
Token ID6290
Feature activation-1.66e+00

Pos logit contributions
 likes+0.014
 They+0.013
 and+0.013
 with+0.012
 liked+0.011
Neg logit contributions
iqu-0.026
wen-0.026
ow-0.026
unct-0.026
antis-0.025
Token.
Token ID13
Feature activation-1.03e-01

Pos logit contributions
ow+0.061
iqu+0.060
ous+0.060
erk+0.060
otion+0.059
Neg logit contributions
 likes-0.017
 They-0.015
 and-0.013
 nice-0.011
 fun-0.010
Token The
Token ID383
Feature activation-9.37e-01

Pos logit contributions
otion+0.004
ow+0.004
ately+0.004
ous+0.004
antis+0.004
Neg logit contributions
 likes-0.001
 and-0.001
 games-0.001
 fun-0.001
 with-0.001
Token ostr
Token ID42387
Feature activation-9.60e+00

Pos logit contributions
iqu+0.026
otion+0.025
ately+0.025
used+0.024
wen+0.024
Neg logit contributions
 and-0.022
 likes-0.021
 They-0.020
 nice-0.019
 green-0.019
Tokenich
Token ID488
Feature activation-1.50e+00

Pos logit contributions
 hesitation+0.206
otion+0.192
erk+0.187
iqu+0.184
ately+0.176
Neg logit contributions
 and-0.270
 likes-0.263
 with-0.255
 They-0.244
-0.241
Token was
Token ID373
Feature activation-2.71e+00

Pos logit contributions
ately+0.051
iqu+0.051
erk+0.050
wen+0.050
otion+0.050
Neg logit contributions
 They-0.018
 likes-0.017
 and-0.015
 with-0.014
 nice-0.014
Token wet
Token ID9583
Feature activation+2.40e+00

Pos logit contributions
ately+0.096
iqu+0.095
wen+0.094
otion+0.094
ous+0.092
Neg logit contributions
 and-0.040
 with-0.037
 likes-0.037
 They-0.036
 nice-0.034
Token from
Token ID422
Feature activation-2.59e+00

Pos logit contributions
 likes+0.012
 They+0.010
 and+0.006
 with+0.004
 fun+0.004
Neg logit contributions
ately-0.101
iqu-0.101
otion-0.101
ous-0.100
erk-0.099
Token the
Token ID262
Feature activation+4.22e-01

Pos logit contributions
iqu+0.108
ately+0.106
wen+0.105
otion+0.103
used+0.103
Neg logit contributions
 and-0.026
 likes-0.021
 with-0.021
 They-0.020
 green-0.019
Tokenowers
Token ID3618
Feature activation-4.36e-01

Pos logit contributions
iqu+0.061
otion+0.059
ately+0.059
wen+0.058
erk+0.057
Neg logit contributions
 likes-0.087
 and-0.086
 They-0.086
 with-0.082
-0.077
Token in
Token ID287
Feature activation+7.84e-01

Pos logit contributions
iqu+0.018
ately+0.018
otion+0.018
wen+0.017
erk+0.017
Neg logit contributions
 likes-0.003
 and-0.003
 They-0.003
 with-0.002
 liked-0.002
Token his
Token ID465
Feature activation-8.14e-01

Pos logit contributions
 likes+0.009
 They+0.008
 and+0.008
 with+0.007
 liked+0.006
Neg logit contributions
iqu-0.029
ately-0.029
otion-0.029
erk-0.028
wen-0.028
Token hands
Token ID2832
Feature activation+2.82e-01

Pos logit contributions
ow+0.022
iqu+0.021
ately+0.021
erk+0.021
used+0.020
Neg logit contributions
 They-0.016
 likes-0.016
 and-0.015
 with-0.014
They-0.014
Token.
Token ID13
Feature activation-6.69e-01

Pos logit contributions
 and+0.002
 likes+0.001
 They+0.001
 with+0.001
+0.001
Neg logit contributions
iqu-0.012
otion-0.012
wen-0.012
ately-0.012
erk-0.012
Token G
Token ID402
Feature activation-6.59e+00

Pos logit contributions
iqu+0.024
ately+0.023
used+0.023
erk+0.023
ow+0.023
Neg logit contributions
 likes-0.008
 and-0.007
 nice-0.006
 with-0.006
 They-0.006
Tokenently
Token ID1473
Feature activation-8.05e-02

Pos logit contributions
 hesitation+0.097
otion+0.087
unct+0.087
used+0.085
iqu+0.085
Neg logit contributions
 and-0.222
 likes-0.215
 They-0.203
-0.198
 with-0.196
Token,
Token ID11
Feature activation-2.41e+00

Pos logit contributions
used+0.003
ately+0.003
iqu+0.003
ous+0.003
 hesitation+0.003
Neg logit contributions
 likes-0.001
 They-0.001
 and-0.001
 fun-0.001
 games-0.001
Token Sam
Token ID3409
Feature activation+2.80e-01

Pos logit contributions
iqu+0.095
otion+0.095
wen+0.094
ous+0.091
unct+0.091
Neg logit contributions
 and-0.030
 with-0.026
 They-0.023
 likes-0.021
-0.020
Token reached
Token ID4251
Feature activation-3.17e+00

Pos logit contributions
 They+0.005
 likes+0.005
 and+0.004
 with+0.004
 fun+0.004
Neg logit contributions
iqu-0.009
ately-0.008
erk-0.008
used-0.008
wen-0.008
Token out
Token ID503
Feature activation-3.59e-01

Pos logit contributions
iqu+0.104
ately+0.102
otion+0.102
erk+0.101
used+0.101
Neg logit contributions
 likes-0.049
 They-0.046
 and-0.045
 with-0.040
 liked-0.039
Token to
Token ID284
Feature activation-3.08e+00

Pos logit contributions
 likes+0.011
 They+0.011
 and+0.010
 with+0.009
 liked+0.008
Neg logit contributions
iqu-0.041
ately-0.041
otion-0.040
wen-0.040
erk-0.040
Token get
Token ID651
Feature activation-1.62e+00

Pos logit contributions
iqu+0.091
ately+0.089
otion+0.089
wen+0.088
erk+0.088
Neg logit contributions
 likes-0.057
 They-0.055
 and-0.055
 with-0.050
 liked-0.047
Token rid
Token ID5755
Feature activation+7.73e-01

Pos logit contributions
iqu+0.058
ately+0.057
otion+0.057
wen+0.056
erk+0.056
Neg logit contributions
 likes-0.020
 and-0.020
 They-0.020
 with-0.018
 nice-0.015
Token of
Token ID286
Feature activation+1.51e-01

Pos logit contributions
 likes+0.015
 They+0.014
 and+0.014
 fun+0.013
 liked+0.013
Neg logit contributions
otion-0.022
ately-0.022
iqu-0.021
ous-0.021
ow-0.021
Token the
Token ID262
Feature activation-9.96e-01

Pos logit contributions
 and+0.001
 They+0.001
 likes+0.001
 with+0.001
+0.001
Neg logit contributions
iqu-0.006
wen-0.006
ous-0.006
otion-0.006
used-0.006
Token fle
Token ID5104
Feature activation-6.24e+00

Pos logit contributions
iqu+0.027
ately+0.027
otion+0.026
used+0.026
wen+0.026
Neg logit contributions
 likes-0.020
 They-0.020
 and-0.020
 with-0.018
 liked-0.017
Tokena
Token ID64
Feature activation-2.28e+00

Pos logit contributions
iqu+0.138
ately+0.135
otion+0.134
wen+0.131
erk+0.130
Neg logit contributions
 likes-0.162
 They-0.160
 and-0.160
 with-0.150
 nice-0.143
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
ately+0.088
iqu+0.088
otion+0.088
erk+0.087
ow+0.087
Neg logit contributions
 likes-0.019
 They-0.018
 and-0.016
 with-0.013
 liked-0.013
Token
Token ID198
Feature activation-2.05e-01

Pos logit contributions
 likes+0.015
 games+0.014
 and+0.013
 nice+0.012
 fun+0.012
Neg logit contributions
otion-0.048
ately-0.048
antis-0.047
iqu-0.047
ow-0.046
Token
Token ID198
Feature activation-1.39e+00

Pos logit contributions
iqu+0.008
otion+0.008
wen+0.008
ately+0.008
erk+0.008
Neg logit contributions
 likes-0.001
 and-0.001
 They-0.001
 games-0.001
 with-0.001
TokenThe
Token ID464
Feature activation-1.31e+00

Pos logit contributions
wen+0.042
otion+0.042
iqu+0.042
antis+0.041
izz+0.041
Neg logit contributions
 likes-0.022
 They-0.021
 and-0.021
 games-0.020
 fun-0.018
Token,
Token ID11
Feature activation-1.45e+00

Pos logit contributions
iqu+0.052
otion+0.051
ately+0.051
wen+0.051
erk+0.050
Neg logit contributions
 likes-0.014
 and-0.014
 They-0.013
 with-0.012
 nice-0.010
Token duck
Token ID22045
Feature activation-1.39e+00

Pos logit contributions
iqu+0.046
ately+0.046
wen+0.046
used+0.045
otion+0.045
Neg logit contributions
 likes-0.025
 and-0.024
 They-0.024
 with-0.022
 nice-0.021
Token,"
Token ID553
Feature activation-6.12e-01

Pos logit contributions
iqu+0.041
ow+0.041
erk+0.041
ous+0.041
otion+0.041
Neg logit contributions
 They-0.023
 likes-0.023
 and-0.020
 games-0.020
 fun-0.020
Token said
Token ID531
Feature activation-2.95e+00

Pos logit contributions
otion+0.018
iqu+0.018
ately+0.018
used+0.018
erk+0.018
Neg logit contributions
 likes-0.010
 and-0.010
 They-0.009
 with-0.009
 fun-0.008
Token the
Token ID262
Feature activation-2.55e+00

Pos logit contributions
iqu+0.104
ately+0.101
otion+0.101
wen+0.100
erk+0.099
Neg logit contributions
 likes-0.039
 and-0.039
 They-0.039
 with-0.035
 nice-0.031
Token oct
Token ID19318
Feature activation-7.78e+00

Pos logit contributions
iqu+0.082
otion+0.080
ately+0.080
erk+0.079
used+0.078
Neg logit contributions
 likes-0.039
 They-0.038
 and-0.038
 with-0.034
 liked-0.031
Tokenopus
Token ID25790
Feature activation-1.49e+00

Pos logit contributions
iqu+0.138
ately+0.135
otion+0.132
wen+0.131
 hesitation+0.129
Neg logit contributions
 likes-0.238
 and-0.236
 They-0.229
 with-0.228
-0.215
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
iqu+0.060
ately+0.059
otion+0.059
erk+0.059
used+0.058
Neg logit contributions
 likes-0.011
 They-0.010
 and-0.010
 with-0.008
 fun-0.006
Token "
Token ID366
Feature activation+1.99e+00

Pos logit contributions
otion+0.032
erk+0.031
ow+0.031
used+0.030
ous+0.030
Neg logit contributions
 likes-0.014
 games-0.013
 fun-0.012
 and-0.012
 shapes-0.011
TokenDo
Token ID5211
Feature activation-6.83e-01

Pos logit contributions
 likes+0.036
 and+0.035
 They+0.035
 fun+0.034
 nice+0.032
Neg logit contributions
otion-0.056
used-0.054
ately-0.053
erk-0.053
antis-0.052
Token you
Token ID345
Feature activation-6.09e-01

Pos logit contributions
iqu+0.022
otion+0.022
ately+0.022
wen+0.021
erk+0.021
Neg logit contributions
 likes-0.011
 and-0.010
 They-0.010
 with-0.009
 liked-0.009
Token joy
Token ID8716
Feature activation+1.97e+00

Pos logit contributions
 likes+0.025
 They+0.024
 and+0.023
 with+0.022
 liked+0.021
Neg logit contributions
 hesitation-0.032
iqu-0.031
otion-0.031
ow-0.031
used-0.031
Token,
Token ID11
Feature activation+1.18e+00

Pos logit contributions
 likes+0.015
 and+0.015
 They+0.014
 with+0.012
 liked+0.009
Neg logit contributions
iqu-0.080
otion-0.078
ately-0.078
wen-0.077
erk-0.077
Token knowing
Token ID6970
Feature activation+4.12e-01

Pos logit contributions
 likes+0.015
 They+0.014
 and+0.012
 games+0.011
 with+0.011
Neg logit contributions
ately-0.040
used-0.040
iqu-0.040
ous-0.039
erk-0.039
Token now
Token ID783
Feature activation+9.81e-03

Pos logit contributions
 and+0.006
 likes+0.006
 They+0.006
 with+0.006
 nice+0.005
Neg logit contributions
iqu-0.014
otion-0.014
ately-0.013
wen-0.013
used-0.013
Token why
Token ID1521
Feature activation-1.11e+00

Pos logit contributions
 and+0.000
 likes+0.000
 They+0.000
 with+0.000
 nice+0.000
Neg logit contributions
iqu-0.000
otion-0.000
ately-0.000
wen-0.000
erk-0.000
Token m
Token ID285
Feature activation-7.64e+00

Pos logit contributions
iqu+0.039
otion+0.037
wen+0.037
ately+0.037
unct+0.037
Neg logit contributions
 and-0.017
 They-0.016
 likes-0.016
 with-0.015
 nice-0.013
Tokenama
Token ID1689
Feature activation-1.94e+00

Pos logit contributions
 hesitation+0.124
otion+0.112
iqu+0.105
comb+0.103
idget+0.102
Neg logit contributions
 and-0.241
 with-0.216
-0.215
"-0.205
 likes-0.205
Token had
Token ID550
Feature activation+1.52e-01

Pos logit contributions
iqu+0.069
otion+0.069
ately+0.068
wen+0.067
unct+0.067
Neg logit contributions
 and-0.026
 likes-0.025
 They-0.023
 with-0.022
 liked-0.020
Token been
Token ID587
Feature activation-9.69e-01

Pos logit contributions
 likes+0.003
 They+0.003
 and+0.003
 with+0.003
 liked+0.003
Neg logit contributions
iqu-0.004
ately-0.004
otion-0.004
wen-0.004
erk-0.004
Token so
Token ID523
Feature activation-9.59e-01

Pos logit contributions
iqu+0.028
ately+0.027
otion+0.027
wen+0.027
erk+0.027
Neg logit contributions
 likes-0.019
 and-0.018
 They-0.018
 with-0.017
 liked-0.016
Token secretive
Token ID32654
Feature activation+1.70e+00

Pos logit contributions
otion+0.034
ately+0.033
wen+0.033
iqu+0.032
ous+0.032
Neg logit contributions
 and-0.013
 likes-0.013
 with-0.013
 nice-0.012
 They-0.012