TOP ACTIVATIONS
MAX = 0.100

and Jimmy ran to the checkout counter . At
As they walked to the checkout , Lily said , "
When they reached the checkout , Alice 's mom picked
took the beef to the checkout counter and paid for it
As they walked to the checkout , Tim my noticed his
and the onion to the checkout , and he bought them
and looked at the ost ric hes . They saw one
shelf and ran to the checkout . "
When they got to the checkout , Mom my saw the
when Anna opened the soap drawer , it was empty !
needed and went to the checkout . Tom put his t
and took them to the checkout . Jack was
managed to get to the checkout . The baby was so
She followed Mom to the checkout . She hoped they would
cold it got or <|endoftext|> Once there was a little girl
happy . She opened the kit and started blowing bubbles .
off they went to the checkout . P hew , Mum
When they got to the checkout , Tim my 's mom
and they went to the checkout . The little boy smiled
happy and tired . <|endoftext|> Once upon a time , there

MIN ACTIVATIONS
MIN = -0.095

until one day , something extraordinary happened ! O
wished it could do something exciting , but it couldn 't
One day , something exciting happened . A big storm
One day , something exciting happened : a modern l
, but I 'm too shy to ask the other cats
was an ordinary yard . Nobody was sure how big it
walk , Alice found something exciting . It was a special
But one day , something amazing happened ! A giant paper
it . Every day something exciting would happen on the board
life until one day something exciting happened . She was playing
. Let 's do something exciting !" So they decided to
but D ucky was too shy . He decided to wash
One day , something very exciting happened . Lily 's mom
. But then , something amazing happened . The sprayed gum
, but he was too shy to ask . Suddenly ,
filthy . But then something amazing happened . Suddenly the comb
, but she was too shy . " Oh
but Nem o was too curious . He sw am closer
then one day , something amazing happened . A man came
Lily 's brother did something amazing ! He danced and sang

INTERVAL 0.051 - 0.100
CONTAINS 1.567%

close to nature . <|endoftext|> Once upon a time there were
." They walked to the house with the v
met a toy boat and said hello . Suddenly , he
Spot w agged his tail . He l icked
, Mo ira ?" she asked . Mo ira

INTERVAL 0.003 - 0.051
CONTAINS 41.812%

, brilliant furniture ! Jimmy was excited . He grabbed some
ummy ! With excitement , the little girl sang all the
Thank you for this wonderful breakfast !" Mom says .
When she was done playing , the little girl waved
cream from the freezer ?" Lily was very excited to help

INTERVAL -0.046 - 0.003
CONTAINS 54.028%

thoughtful . He asked the little fish why he was so
. They lost their toys , their clothes , their books
. Max wanted to get his ball back
where they kept their toys and books . They made a
beef jer ky . When she came back , she used

INTERVAL -0.095 - -0.046
CONTAINS 2.594%

game for smart people . You have to move the pieces
to explore and find some new friends . He
. " We are so lucky to find them ."
not move . She feels sad . " Mom
The little girl smiled , happy to have her Mom my
Token and
Token ID290
Feature activation-2.33e-02

Pos logit contributions
ail+0.104
 lobby+0.098
 babys+0.098
 reception+0.098
 kitchen+0.097
Neg logit contributions
 than-0.061
 wanna-0.046
ust-0.044
ear-0.044
icated-0.044
Token Jimmy
Token ID12963
Feature activation+5.69e-03

Pos logit contributions
 than+0.037
 arrow+0.026
 want+0.026
 since+0.025
 because+0.025
Neg logit contributions
illi-0.051
ail-0.050
 lobby-0.048
 babys-0.047
uka-0.046
Token ran
Token ID4966
Feature activation+1.89e-03

Pos logit contributions
 lobby+0.012
illi+0.012
 babys+0.012
ail+0.011
 reception+0.011
Neg logit contributions
 than-0.009
 want-0.007
 like-0.006
 because-0.006
 as-0.006
Token to
Token ID284
Feature activation+5.84e-02

Pos logit contributions
illi+0.004
ail+0.004
 babys+0.004
 lobby+0.004
 reception+0.004
Neg logit contributions
 than-0.003
 want-0.002
ust-0.002
 hour-0.002
ear-0.002
Token the
Token ID262
Feature activation+2.79e-02

Pos logit contributions
ail+0.116
illi+0.112
 lobby+0.106
 salon+0.106
 babys+0.105
Neg logit contributions
 than-0.102
 want-0.083
 like-0.077
 because-0.076
ear-0.075
Token checkout
Token ID28006
Feature activation+1.00e-01

Pos logit contributions
illi+0.044
ail+0.044
ili+0.042
uka+0.040
loe+0.040
Neg logit contributions
 than-0.056
 arrow-0.050
 target-0.049
 like-0.045
 since-0.045
Token counter
Token ID3753
Feature activation+5.99e-02

Pos logit contributions
illi+0.245
ail+0.242
 lobby+0.235
 babys+0.234
 reception+0.230
Neg logit contributions
 than-0.134
 want-0.084
ear-0.082
ets-0.080
 hour-0.080
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
illi+0.151
ail+0.149
 lobby+0.146
 babys+0.145
 reception+0.143
Neg logit contributions
 than-0.075
 want-0.045
ear-0.045
ets-0.043
 hour-0.043
Token
Token ID198
Feature activation-1.12e-02

Pos logit contributions
 than+0.021
 want+0.015
ear+0.015
 hour+0.015
ets+0.015
Neg logit contributions
illi-0.021
ail-0.021
 lobby-0.020
 babys-0.020
 reception-0.019
Token
Token ID198
Feature activation-1.65e-02

Pos logit contributions
 than+0.019
 want+0.014
ear+0.014
 hour+0.014
 wanna+0.013
Neg logit contributions
ail-0.022
illi-0.022
 lobby-0.021
 babys-0.021
 salon-0.021
TokenAt
Token ID2953
Feature activation+5.58e-03

Pos logit contributions
 than+0.035
ets+0.026
 arrow+0.026
 want+0.026
 target+0.025
Neg logit contributions
illi-0.030
ail-0.027
 lobby-0.027
uka-0.027
 babys-0.027
TokenAs
Token ID1722
Feature activation-1.42e-02

Pos logit contributions
 than+0.018
ets+0.013
 want+0.013
 arrow+0.012
 like+0.012
Neg logit contributions
illi-0.020
ail-0.019
 salon-0.018
 babys-0.018
 reception-0.018
Token they
Token ID484
Feature activation-3.41e-03

Pos logit contributions
 than+0.021
 since+0.014
 because+0.014
 hour+0.014
 like+0.013
Neg logit contributions
illi-0.033
ail-0.033
 lobby-0.031
 babys-0.031
uka-0.031
Token walked
Token ID6807
Feature activation+2.42e-02

Pos logit contributions
 than+0.006
 want+0.005
ear+0.005
 hour+0.005
ets+0.005
Neg logit contributions
illi-0.006
ail-0.006
 lobby-0.006
 babys-0.006
 reception-0.006
Token to
Token ID284
Feature activation+4.77e-02

Pos logit contributions
illi+0.053
uka+0.049
ail+0.049
acey+0.049
 babys+0.049
Neg logit contributions
 than-0.041
 like-0.029
 because-0.028
 want-0.028
 hour-0.028
Token the
Token ID262
Feature activation+2.60e-02

Pos logit contributions
ail+0.102
illi+0.098
acey+0.094
omm+0.093
uka+0.090
Neg logit contributions
 than-0.075
 want-0.063
 because-0.060
 like-0.060
 as-0.059
Token checkout
Token ID28006
Feature activation+9.73e-02

Pos logit contributions
illi+0.051
ail+0.051
acey+0.049
ili+0.049
uka+0.047
Neg logit contributions
 than-0.046
 arrow-0.040
 target-0.037
 hour-0.036
 like-0.035
Token,
Token ID11
Feature activation-5.76e-04

Pos logit contributions
illi+0.177
ail+0.169
 Stacy+0.162
uka+0.161
ili+0.160
Neg logit contributions
 than-0.195
 want-0.141
 because-0.139
 hour-0.138
ets-0.137
Token Lily
Token ID20037
Feature activation+2.19e-03

Pos logit contributions
 than+0.001
 because+0.001
 as+0.001
 since+0.001
 after+0.001
Neg logit contributions
ail-0.001
illi-0.001
uka-0.001
 salon-0.001
 lobby-0.001
Token said
Token ID531
Feature activation+4.62e-02

Pos logit contributions
illi+0.005
 lobby+0.005
ail+0.005
 babys+0.005
 reception+0.005
Neg logit contributions
 than-0.003
 since-0.002
 want-0.002
 because-0.002
ets-0.002
Token,
Token ID11
Feature activation+1.07e-02

Pos logit contributions
illi+0.112
 lobby+0.108
ail+0.107
uka+0.105
 babys+0.103
Neg logit contributions
 than-0.066
 want-0.045
 like-0.045
 as-0.043
 because-0.043
Token "
Token ID366
Feature activation-2.25e-02

Pos logit contributions
illi+0.023
ail+0.022
 lobby+0.022
uka+0.021
 salon+0.021
Neg logit contributions
 than-0.018
 because-0.013
 want-0.013
 like-0.012
 since-0.012
Token
Token ID198
Feature activation-1.93e-02

Pos logit contributions
 than+0.025
ear+0.017
 hour+0.017
 want+0.017
ust+0.016
Neg logit contributions
ail-0.033
 lobby-0.033
illi-0.033
 babys-0.032
 Stacy-0.032
TokenWhen
Token ID2215
Feature activation+6.04e-03

Pos logit contributions
 than+0.035
ets+0.026
 want+0.026
 arrow+0.025
ear+0.025
Neg logit contributions
illi-0.038
ail-0.036
 lobby-0.035
 babys-0.035
 reception-0.035
Token they
Token ID484
Feature activation-9.13e-03

Pos logit contributions
ail+0.012
illi+0.012
 babys+0.011
uka+0.011
 lobby+0.011
Neg logit contributions
 than-0.011
 hour-0.008
 because-0.008
 since-0.008
 want-0.008
Token reached
Token ID4251
Feature activation+1.31e-02

Pos logit contributions
 than+0.016
 want+0.012
 hour+0.011
ets+0.011
 since+0.011
Neg logit contributions
illi-0.018
ail-0.018
 lobby-0.018
 babys-0.018
 reception-0.017
Token the
Token ID262
Feature activation+2.53e-02

Pos logit contributions
illi+0.027
 babys+0.027
ail+0.027
 reception+0.026
 styl+0.026
Neg logit contributions
 than-0.020
 because-0.016
 as-0.016
 like-0.015
 after-0.015
Token checkout
Token ID28006
Feature activation+9.50e-02

Pos logit contributions
ail+0.037
illi+0.036
aby+0.035
ili+0.034
 Stacy+0.033
Neg logit contributions
 than-0.058
 like-0.047
 want-0.047
 because-0.047
 hour-0.046
Token,
Token ID11
Feature activation-1.98e-03

Pos logit contributions
illi+0.158
ail+0.154
 babys+0.148
 lobby+0.147
uka+0.143
Neg logit contributions
 than-0.203
 want-0.154
ets-0.150
 hour-0.149
ear-0.149
Token Alice
Token ID14862
Feature activation-1.90e-02

Pos logit contributions
 than+0.004
 because+0.003
 since+0.003
 like+0.003
 want+0.003
Neg logit contributions
ail-0.004
illi-0.003
 babys-0.003
uka-0.003
 lobby-0.003
Token's
Token ID338
Feature activation+3.42e-02

Pos logit contributions
 than+0.030
 want+0.023
 since+0.021
 because+0.021
 like+0.021
Neg logit contributions
illi-0.040
 lobby-0.039
ail-0.039
 babys-0.038
 reception-0.037
Token mom
Token ID1995
Feature activation-7.65e-03

Pos logit contributions
illi+0.053
ili+0.049
ail+0.048
uka+0.048
 Stacy+0.047
Neg logit contributions
 than-0.078
 want-0.064
 hour-0.062
 because-0.062
 arrow-0.061
Token picked
Token ID6497
Feature activation+3.76e-02

Pos logit contributions
 than+0.011
 want+0.008
 since+0.008
 because+0.008
 like+0.008
Neg logit contributions
illi-0.017
 lobby-0.016
ail-0.016
 babys-0.016
 Stacy-0.016
Token took
Token ID1718
Feature activation+1.14e-02

Pos logit contributions
 than+0.027
 want+0.020
 arrow+0.019
 like+0.019
ets+0.018
Neg logit contributions
illi-0.040
ail-0.040
 babys-0.039
 lobby-0.039
uka-0.038
Token the
Token ID262
Feature activation+2.57e-02

Pos logit contributions
ail+0.025
 babys+0.024
 salon+0.024
illi+0.024
 lobby+0.024
Neg logit contributions
 than-0.018
 like-0.013
 arrow-0.013
ets-0.013
 want-0.013
Token beef
Token ID12023
Feature activation+2.97e-02

Pos logit contributions
illi+0.047
ail+0.046
 Stacy+0.044
uka+0.044
 lobby+0.043
Neg logit contributions
 than-0.051
 arrow-0.040
 want-0.039
 hour-0.038
 target-0.037
Token to
Token ID284
Feature activation+4.65e-02

Pos logit contributions
ail+0.054
illi+0.053
 lobby+0.052
 babys+0.052
 reception+0.051
Neg logit contributions
 than-0.056
ear-0.044
 want-0.043
ust-0.042
ets-0.042
Token the
Token ID262
Feature activation+2.66e-02

Pos logit contributions
ail+0.094
illi+0.089
 lobby+0.085
 babys+0.084
 salon+0.083
Neg logit contributions
 than-0.087
 want-0.066
 like-0.065
 because-0.064
 arrow-0.064
Token checkout
Token ID28006
Feature activation+9.48e-02

Pos logit contributions
ail+0.048
illi+0.046
ili+0.043
 Stacy+0.042
loe+0.042
Neg logit contributions
 than-0.052
 target-0.043
 arrow-0.043
 like-0.041
 hour-0.041
Token counter
Token ID3753
Feature activation+5.81e-02

Pos logit contributions
illi+0.163
ail+0.159
 lobby+0.152
 babys+0.152
 reception+0.148
Neg logit contributions
 than-0.197
 want-0.149
ear-0.146
ets-0.145
 hour-0.145
Token and
Token ID290
Feature activation-3.04e-02

Pos logit contributions
illi+0.152
ail+0.151
 lobby+0.148
 babys+0.147
 reception+0.145
Neg logit contributions
 than-0.065
 want-0.037
ear-0.037
 hour-0.035
ets-0.035
Token paid
Token ID3432
Feature activation+2.91e-02

Pos logit contributions
 than+0.048
 want+0.035
 since+0.035
 because+0.035
 like+0.034
Neg logit contributions
ail-0.066
illi-0.065
 babys-0.061
 lobby-0.061
ili-0.060
Token for
Token ID329
Feature activation+3.26e-02

Pos logit contributions
illi+0.066
 lobby+0.065
ail+0.065
 babys+0.065
 salon+0.064
Neg logit contributions
 than-0.044
 want-0.029
ear-0.029
 like-0.028
ets-0.028
Token it
Token ID340
Feature activation+1.06e-02

Pos logit contributions
ail+0.067
illi+0.065
 babys+0.062
 lobby+0.062
 salon+0.061
Neg logit contributions
 than-0.059
 hour-0.043
 want-0.042
 because-0.041
ear-0.041
TokenAs
Token ID1722
Feature activation-1.60e-02

Pos logit contributions
 than+0.021
ets+0.018
 want+0.016
ear+0.016
 target+0.015
Neg logit contributions
illi-0.020
ail-0.019
 kitchen-0.019
 babys-0.019
Clar-0.018
Token they
Token ID484
Feature activation-6.08e-03

Pos logit contributions
 than+0.027
ets+0.020
ear+0.020
 want+0.020
ust+0.019
Neg logit contributions
illi-0.033
ail-0.033
 babys-0.032
 lobby-0.032
 reception-0.031
Token walked
Token ID6807
Feature activation+2.16e-02

Pos logit contributions
 than+0.011
 want+0.008
 hour+0.008
ear+0.008
ets+0.008
Neg logit contributions
illi-0.012
ail-0.012
 lobby-0.011
 babys-0.011
 Stacy-0.011
Token to
Token ID284
Feature activation+4.77e-02

Pos logit contributions
illi+0.047
uka+0.044
acey+0.044
ail+0.044
 Stacy+0.044
Neg logit contributions
 than-0.036
 like-0.026
 as-0.026
 because-0.025
 since-0.025
Token the
Token ID262
Feature activation+2.60e-02

Pos logit contributions
ail+0.103
illi+0.096
omm+0.090
acey+0.090
 Stacy+0.090
Neg logit contributions
 than-0.075
 want-0.062
 because-0.060
 like-0.059
 as-0.059
Token checkout
Token ID28006
Feature activation+9.46e-02

Pos logit contributions
ail+0.045
illi+0.042
 Stacy+0.041
aby+0.041
ili+0.040
Neg logit contributions
 than-0.051
 arrow-0.041
 because-0.041
 hour-0.040
 target-0.040
Token,
Token ID11
Feature activation-3.71e-04

Pos logit contributions
illi+0.181
ail+0.175
 Stacy+0.170
ili+0.167
uka+0.167
Neg logit contributions
 than-0.179
 because-0.127
 want-0.126
 hour-0.123
 as-0.122
Token Tim
Token ID5045
Feature activation+6.36e-03

Pos logit contributions
 than+0.000
 because+0.000
 like+0.000
 since+0.000
 want+0.000
Neg logit contributions
illi-0.001
ail-0.001
 lobby-0.001
 reception-0.001
 Stacy-0.001
Tokenmy
Token ID1820
Feature activation-1.27e-02

Pos logit contributions
illi+0.013
 lobby+0.012
ail+0.012
 reception+0.012
 babys+0.012
Neg logit contributions
 than-0.011
 want-0.008
 since-0.008
ear-0.008
ets-0.008
Token noticed
Token ID6810
Feature activation-2.04e-02

Pos logit contributions
 than+0.021
 want+0.015
 since+0.015
 because+0.015
 arrow+0.015
Neg logit contributions
illi-0.027
ail-0.026
 lobby-0.025
 babys-0.025
ili-0.024
Token his
Token ID465
Feature activation+1.79e-02

Pos logit contributions
 than+0.032
 because+0.023
 arrow+0.023
 like+0.022
 since+0.022
Neg logit contributions
illi-0.045
ail-0.045
 Stacy-0.042
 lobby-0.042
 reception-0.042
Token and
Token ID290
Feature activation-2.20e-02

Pos logit contributions
ail+0.053
illi+0.051
 babys+0.050
 reception+0.050
 lobby+0.050
Neg logit contributions
 than-0.040
ear-0.029
 hour-0.028
ust-0.028
 want-0.028
Token the
Token ID262
Feature activation+2.92e-02

Pos logit contributions
 than+0.039
 want+0.028
ear+0.027
ets+0.027
 hour+0.027
Neg logit contributions
illi-0.045
ail-0.044
 lobby-0.042
 babys-0.042
 reception-0.041
Token onion
Token ID21670
Feature activation+1.61e-02

Pos logit contributions
illi+0.052
ail+0.051
 lobby+0.049
 babys+0.048
 reception+0.047
Neg logit contributions
 than-0.059
 want-0.045
 hour-0.044
 arrow-0.043
ets-0.043
Token to
Token ID284
Feature activation+4.24e-02

Pos logit contributions
illi+0.033
ail+0.033
 lobby+0.032
 babys+0.031
 reception+0.031
Neg logit contributions
 than-0.027
 want-0.020
ear-0.019
 hour-0.019
ets-0.019
Token the
Token ID262
Feature activation+2.07e-02

Pos logit contributions
ail+0.090
illi+0.090
 babys+0.085
 lobby+0.085
 reception+0.083
Neg logit contributions
 than-0.071
 want-0.053
 like-0.052
 arrow-0.052
 because-0.051
Token checkout
Token ID28006
Feature activation+9.37e-02

Pos logit contributions
illi+0.030
ail+0.030
 lobby+0.027
 babys+0.027
 Stacy+0.027
Neg logit contributions
 than-0.049
 want-0.039
 hour-0.038
 arrow-0.038
 target-0.037
Token,
Token ID11
Feature activation-1.36e-02

Pos logit contributions
illi+0.181
ail+0.180
 lobby+0.174
 babys+0.173
 reception+0.170
Neg logit contributions
 than-0.171
 want-0.125
ear-0.124
ets-0.122
 hour-0.121
Token and
Token ID290
Feature activation-3.18e-02

Pos logit contributions
 than+0.018
ear+0.012
 hour+0.012
 want+0.011
ust+0.011
Neg logit contributions
illi-0.032
ail-0.032
 lobby-0.031
 babys-0.031
 reception-0.031
Token he
Token ID339
Feature activation-1.74e-02

Pos logit contributions
 than+0.051
 want+0.036
 since+0.035
 arrow+0.034
ear+0.034
Neg logit contributions
illi-0.070
ail-0.069
 babys-0.066
 lobby-0.066
 reception-0.064
Token bought
Token ID5839
Feature activation+2.97e-02

Pos logit contributions
 than+0.029
 want+0.021
 like+0.020
 arrow+0.020
 because+0.020
Neg logit contributions
illi-0.036
ail-0.035
 lobby-0.035
 babys-0.035
 reception-0.034
Token them
Token ID606
Feature activation+8.13e-03

Pos logit contributions
illi+0.061
ail+0.060
 babys+0.059
 lobby+0.059
 salon+0.058
Neg logit contributions
 than-0.052
 like-0.038
 want-0.037
ear-0.037
 because-0.037
Token and
Token ID290
Feature activation-1.79e-02

Pos logit contributions
illi+0.087
ail+0.086
 babys+0.083
 lobby+0.083
 reception+0.081
Neg logit contributions
 than-0.074
 want-0.053
ear-0.053
ets-0.053
 hour-0.052
Token looked
Token ID3114
Feature activation+1.41e-03

Pos logit contributions
 than+0.030
 want+0.023
 because+0.022
 like+0.022
 since+0.021
Neg logit contributions
ail-0.037
illi-0.037
 babys-0.035
 lobby-0.034
 reception-0.034
Token at
Token ID379
Feature activation+3.38e-02

Pos logit contributions
ail+0.003
illi+0.003
 lobby+0.003
 babys+0.003
 reception+0.003
Neg logit contributions
 than-0.002
ear-0.001
 hour-0.001
icated-0.001
ust-0.001
Token the
Token ID262
Feature activation+2.77e-02

Pos logit contributions
ail+0.078
illi+0.075
 reception+0.075
 babys+0.074
 salon+0.073
Neg logit contributions
 than-0.050
 because-0.037
 each-0.036
 arrow-0.035
 like-0.034
Token ost
Token ID23619
Feature activation-3.36e-03

Pos logit contributions
 Stacy+0.052
ail+0.051
acey+0.051
uka+0.049
illi+0.049
Neg logit contributions
 than-0.056
 want-0.042
 like-0.041
 hour-0.038
 because-0.037
Tokenric
Token ID1173
Feature activation+9.30e-02

Pos logit contributions
 than+0.009
ets+0.007
ust+0.007
 because+0.007
ear+0.007
Neg logit contributions
illi-0.004
 babys-0.004
 Stacy-0.004
uka-0.004
 reception-0.004
Tokenhes
Token ID956
Feature activation+3.43e-02

Pos logit contributions
 babys+0.129
 salon+0.116
ail+0.115
 reception+0.113
 lobby+0.112
Neg logit contributions
 than-0.229
ear-0.187
ets-0.185
 want-0.183
 like-0.180
Token.
Token ID13
Feature activation+1.25e-03

Pos logit contributions
illi+0.090
ail+0.089
 lobby+0.086
 babys+0.086
uka+0.085
Neg logit contributions
 than-0.040
 want-0.023
ets-0.022
ear-0.021
 hour-0.021
Token They
Token ID1119
Feature activation-1.04e-02

Pos logit contributions
ail+0.004
illi+0.004
 babys+0.003
uka+0.003
 salon+0.003
Neg logit contributions
 than-0.001
 because-0.001
 want-0.001
 like-0.001
ear-0.001
Token saw
Token ID2497
Feature activation+5.04e-03

Pos logit contributions
 than+0.018
 want+0.014
 like+0.013
 arrow+0.013
 because+0.013
Neg logit contributions
illi-0.021
ail-0.021
 lobby-0.020
 babys-0.020
 reception-0.020
Token one
Token ID530
Feature activation-3.23e-02

Pos logit contributions
ail+0.013
illi+0.012
acey+0.012
loe+0.012
uka+0.012
Neg logit contributions
 than-0.007
 like-0.005
 each-0.005
 arrow-0.005
 because-0.005
Token shelf
Token ID18316
Feature activation+6.97e-02

Pos logit contributions
illi+0.049
ail+0.048
 lobby+0.046
 babys+0.045
uka+0.044
Neg logit contributions
 than-0.055
 want-0.041
 hour-0.041
 arrow-0.041
ear-0.040
Token and
Token ID290
Feature activation-2.06e-02

Pos logit contributions
ail+0.161
 lobby+0.158
illi+0.157
 kitchen+0.156
 salon+0.156
Neg logit contributions
 than-0.088
 wanna-0.066
ear-0.066
 want-0.064
ust-0.063
Token ran
Token ID4966
Feature activation-2.97e-03

Pos logit contributions
 than+0.036
 want+0.026
ear+0.026
ets+0.025
 hour+0.025
Neg logit contributions
illi-0.042
ail-0.041
 lobby-0.039
 babys-0.039
 reception-0.038
Token to
Token ID284
Feature activation+5.40e-02

Pos logit contributions
 than+0.006
ust+0.005
 hour+0.005
icated+0.005
 want+0.004
Neg logit contributions
illi-0.005
ail-0.005
 lobby-0.005
 reception-0.005
 babys-0.005
Token the
Token ID262
Feature activation+2.47e-02

Pos logit contributions
ail+0.109
illi+0.108
 lobby+0.103
 babys+0.103
 salon+0.102
Neg logit contributions
 than-0.094
 want-0.074
ear-0.069
 arrow-0.068
 like-0.067
Token checkout
Token ID28006
Feature activation+9.22e-02

Pos logit contributions
ail+0.035
illi+0.033
ili+0.031
aila+0.030
acey+0.030
Neg logit contributions
 than-0.057
 arrow-0.047
 because-0.046
 like-0.045
 want-0.045
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
illi+0.218
ail+0.215
 lobby+0.209
 babys+0.208
 reception+0.205
Neg logit contributions
 than-0.130
 want-0.085
ear-0.084
ets-0.083
 hour-0.082
Token
Token ID220
Feature activation+2.22e-02

Pos logit contributions
 than+0.027
 want+0.021
ear+0.021
ets+0.020
 hour+0.020
Neg logit contributions
illi-0.017
ail-0.017
 lobby-0.016
 babys-0.016
 reception-0.015
Token
Token ID198
Feature activation-6.50e-03

Pos logit contributions
 lobby+0.048
 babys+0.047
illi+0.047
 reception+0.047
 salon+0.047
Neg logit contributions
 than-0.034
ear-0.024
 want-0.024
 because-0.023
 like-0.022
Token
Token ID198
Feature activation-1.30e-02

Pos logit contributions
 than+0.011
 want+0.008
ear+0.008
 hour+0.008
 since+0.008
Neg logit contributions
illi-0.013
ail-0.013
 lobby-0.013
 babys-0.013
 salon-0.013
Token"
Token ID1
Feature activation-1.74e-02

Pos logit contributions
 than+0.028
ets+0.021
 arrow+0.021
icated+0.020
 want+0.020
Neg logit contributions
illi-0.021
 kitchen-0.020
uka-0.019
ail-0.019
 Stacy-0.019
Token When
Token ID1649
Feature activation+1.52e-02

Pos logit contributions
 than+0.021
 because+0.016
 want+0.015
 like+0.015
 hour+0.014
Neg logit contributions
ail-0.028
illi-0.027
ili-0.025
 lobby-0.025
 babys-0.025
Token they
Token ID484
Feature activation-1.46e-03

Pos logit contributions
ail+0.037
lor+0.034
illi+0.034
lo+0.033
ili+0.033
Neg logit contributions
 than-0.017
 after-0.015
 because-0.015
 as-0.015
 hour-0.013
Token got
Token ID1392
Feature activation+4.69e-02

Pos logit contributions
 than+0.002
 want+0.002
 like+0.001
 since+0.001
 because+0.001
Neg logit contributions
ail-0.003
illi-0.003
 lobby-0.003
 Stacy-0.003
aby-0.003
Token to
Token ID284
Feature activation+4.26e-02

Pos logit contributions
illi+0.119
aby+0.117
ail+0.117
 Stacy+0.115
ili+0.114
Neg logit contributions
 than-0.051
 after-0.037
 because-0.036
 as-0.035
 like-0.035
Token the
Token ID262
Feature activation+2.80e-02

Pos logit contributions
ail+0.092
illi+0.086
uffy+0.080
uka+0.080
 Stacy+0.079
Neg logit contributions
 than-0.074
 want-0.057
 like-0.057
 because-0.056
 as-0.054
Token checkout
Token ID28006
Feature activation+9.20e-02

Pos logit contributions
ail+0.047
illi+0.044
 Stacy+0.043
loe+0.043
ili+0.043
Neg logit contributions
 than-0.058
 like-0.046
 target-0.045
 arrow-0.045
 want-0.044
Token,
Token ID11
Feature activation-3.58e-03

Pos logit contributions
illi+0.208
ail+0.206
ili+0.200
 Stacy+0.198
 babys+0.196
Neg logit contributions
 than-0.142
 want-0.090
 because-0.089
 as-0.086
 like-0.085
Token Mom
Token ID11254
Feature activation+9.48e-03

Pos logit contributions
 than+0.006
 because+0.005
 like+0.005
 after+0.005
 as+0.005
Neg logit contributions
ail-0.007
illi-0.007
 babys-0.007
lo-0.006
ili-0.006
Tokenmy
Token ID1820
Feature activation-1.14e-02

Pos logit contributions
illi+0.021
 lobby+0.021
 reception+0.021
ail+0.020
 babys+0.020
Neg logit contributions
 than-0.014
 want-0.010
 since-0.010
 because-0.010
 like-0.009
Token saw
Token ID2497
Feature activation+7.96e-03

Pos logit contributions
 than+0.017
 want+0.012
 since+0.012
 because+0.012
 like+0.012
Neg logit contributions
illi-0.025
 lobby-0.024
ail-0.024
 Stacy-0.023
ili-0.023
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
ail+0.017
 babys+0.016
 reception+0.015
erman+0.015
 lobby+0.014
Neg logit contributions
 than-0.013
 like-0.011
 as-0.011
 because-0.011
 and-0.010
Token when
Token ID618
Feature activation+1.22e-02

Pos logit contributions
 than+0.020
 since+0.014
 because+0.014
 as+0.014
 after+0.013
Neg logit contributions
ail-0.039
illi-0.038
 lobby-0.037
 babys-0.037
uka-0.036
Token Anna
Token ID11735
Feature activation+1.17e-02

Pos logit contributions
ail+0.033
illi+0.032
 babys+0.031
ili+0.031
uka+0.031
Neg logit contributions
 than-0.012
 after-0.009
 because-0.008
 as-0.008
 since-0.008
Token opened
Token ID4721
Feature activation+2.45e-02

Pos logit contributions
illi+0.025
 lobby+0.024
ail+0.024
 babys+0.023
 reception+0.023
Neg logit contributions
 than-0.018
 want-0.014
 since-0.013
 because-0.013
ets-0.013
Token the
Token ID262
Feature activation+3.19e-02

Pos logit contributions
illi+0.048
 lobby+0.046
ail+0.045
 reception+0.045
uka+0.045
Neg logit contributions
 than-0.044
 because-0.035
 as-0.034
 like-0.033
 since-0.032
Token soap
Token ID19533
Feature activation+5.01e-02

Pos logit contributions
illi+0.044
ail+0.042
ili+0.039
uka+0.038
 Stacy+0.037
Neg logit contributions
 than-0.077
 want-0.063
 like-0.062
ets-0.061
 arrow-0.061
Token drawer
Token ID33451
Feature activation+9.13e-02

Pos logit contributions
illi+0.122
ail+0.116
 babys+0.115
 lobby+0.114
uka+0.113
Neg logit contributions
 than-0.068
 because-0.044
 since-0.043
 like-0.041
 want-0.041
Token,
Token ID11
Feature activation+1.03e-02

Pos logit contributions
illi+0.225
uka+0.212
ili+0.212
 lobby+0.211
 babys+0.210
Neg logit contributions
 than-0.121
 because-0.084
 since-0.079
 and-0.076
 like-0.076
Token it
Token ID340
Feature activation-6.80e-03

Pos logit contributions
ail+0.022
illi+0.021
 babys+0.020
 lobby+0.020
 reception+0.020
Neg logit contributions
 than-0.017
 because-0.012
 like-0.012
 as-0.012
 since-0.012
Token was
Token ID373
Feature activation+1.15e-02

Pos logit contributions
 than+0.011
 because+0.009
 want+0.008
 since+0.008
 like+0.008
Neg logit contributions
illi-0.014
 lobby-0.013
 babys-0.013
ili-0.013
 reception-0.013
Token empty
Token ID6565
Feature activation-3.13e-02

Pos logit contributions
illi+0.022
ail+0.022
 lobby+0.021
 babys+0.021
 reception+0.020
Neg logit contributions
 than-0.022
 want-0.016
 hour-0.015
ear-0.015
ets-0.015
Token!
Token ID0
Feature activation-1.56e-02

Pos logit contributions
 than+0.041
ear+0.033
 arrow+0.031
ust+0.031
 want+0.031
Neg logit contributions
 lobby-0.069
ail-0.068
 kitchen-0.068
illi-0.068
 babys-0.065
Token needed
Token ID2622
Feature activation-1.51e-02

Pos logit contributions
 than+0.045
ear+0.033
 want+0.033
 hour+0.032
ets+0.032
Neg logit contributions
illi-0.047
ail-0.046
 lobby-0.044
 babys-0.044
 reception-0.043
Token and
Token ID290
Feature activation-2.92e-02

Pos logit contributions
 than+0.023
ust+0.018
ear+0.017
 target+0.017
ets+0.017
Neg logit contributions
illi-0.031
ail-0.031
 babys-0.030
 kitchen-0.030
 lobby-0.030
Token went
Token ID1816
Feature activation+3.24e-02

Pos logit contributions
 than+0.050
 want+0.037
 arrow+0.035
ear+0.035
 since+0.035
Neg logit contributions
illi-0.061
ail-0.059
 lobby-0.057
 babys-0.056
uka-0.056
Token to
Token ID284
Feature activation+5.02e-02

Pos logit contributions
illi+0.072
ail+0.069
uka+0.067
 Stacy+0.066
 lobby+0.066
Neg logit contributions
 than-0.052
 want-0.035
 because-0.035
 like-0.035
ets-0.034
Token the
Token ID262
Feature activation+2.53e-02

Pos logit contributions
ail+0.105
illi+0.100
omm+0.093
uka+0.091
uffy+0.091
Neg logit contributions
 than-0.085
 want-0.070
 like-0.066
 arrow-0.066
 because-0.065
Token checkout
Token ID28006
Feature activation+9.05e-02

Pos logit contributions
ail+0.048
illi+0.046
loe+0.044
ili+0.044
 Stacy+0.043
Neg logit contributions
 than-0.046
 target-0.039
 arrow-0.039
 like-0.036
 want-0.035
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
illi+0.224
ail+0.221
 lobby+0.215
 babys+0.215
 reception+0.211
Neg logit contributions
 than-0.118
 want-0.073
ear-0.071
ets-0.069
 hour-0.069
Token Tom
Token ID4186
Feature activation+5.65e-03

Pos logit contributions
 than+0.022
 want+0.016
ets+0.015
 hour+0.015
ear+0.015
Neg logit contributions
illi-0.027
 lobby-0.026
ail-0.026
 babys-0.026
 reception-0.025
Token put
Token ID1234
Feature activation+3.02e-02

Pos logit contributions
illi+0.012
 lobby+0.012
ail+0.012
 babys+0.012
aby+0.011
Neg logit contributions
 than-0.009
 want-0.006
 since-0.006
 because-0.006
 like-0.006
Token his
Token ID465
Feature activation+3.66e-02

Pos logit contributions
ail+0.071
 babys+0.069
aby+0.068
Sab+0.067
 salon+0.067
Neg logit contributions
 than-0.044
 like-0.032
 as-0.032
 because-0.029
 after-0.029
Token t
Token ID256
Feature activation+4.30e-03

Pos logit contributions
illi+0.072
ili+0.068
ail+0.067
aby+0.066
 Stacy+0.066
Neg logit contributions
 than-0.068
 want-0.050
 because-0.050
 arrow-0.050
 hour-0.049
Token and
Token ID290
Feature activation-2.71e-02

Pos logit contributions
 than+0.014
ust+0.011
 arrow+0.011
 target+0.011
icated+0.011
Neg logit contributions
illi-0.021
ail-0.021
 babys-0.020
 lobby-0.020
 reception-0.020
Token took
Token ID1718
Feature activation+8.88e-03

Pos logit contributions
 than+0.045
 want+0.032
 since+0.031
 arrow+0.031
 because+0.030
Neg logit contributions
illi-0.059
ail-0.057
 babys-0.055
 lobby-0.054
 reception-0.054
Token them
Token ID606
Feature activation+5.57e-03

Pos logit contributions
ail+0.018
illi+0.018
 babys+0.018
 salon+0.018
 lobby+0.017
Neg logit contributions
 than-0.016
ear-0.011
 want-0.011
ets-0.011
 like-0.011
Token to
Token ID284
Feature activation+4.35e-02

Pos logit contributions
ail+0.009
illi+0.009
 babys+0.009
 lobby+0.009
 reception+0.009
Neg logit contributions
 than-0.011
 want-0.009
 hour-0.009
ear-0.009
 wanna-0.009
Token the
Token ID262
Feature activation+2.48e-02

Pos logit contributions
ail+0.084
illi+0.082
 babys+0.075
 lobby+0.075
 salon+0.074
Neg logit contributions
 than-0.085
 want-0.065
 like-0.063
 because-0.063
ear-0.062
Token checkout
Token ID28006
Feature activation+8.99e-02

Pos logit contributions
ail+0.040
illi+0.039
aby+0.037
 Stacy+0.036
ili+0.036
Neg logit contributions
 than-0.053
 like-0.044
 want-0.043
 hour-0.042
 because-0.042
Token.
Token ID13
Feature activation-9.78e-03

Pos logit contributions
illi+0.217
ail+0.214
 lobby+0.209
 babys+0.208
 reception+0.204
Neg logit contributions
 than-0.123
 want-0.078
ear-0.076
ets-0.074
 hour-0.074
Token
Token ID198
Feature activation-3.90e-03

Pos logit contributions
 than+0.018
 want+0.013
ets+0.013
ear+0.013
 hour+0.013
Neg logit contributions
illi-0.019
ail-0.019
 lobby-0.018
 babys-0.018
 Stacy-0.018
Token
Token ID198
Feature activation-9.97e-03

Pos logit contributions
 than+0.006
ear+0.005
 want+0.005
 hour+0.004
ets+0.004
Neg logit contributions
illi-0.008
ail-0.008
 lobby-0.008
 babys-0.008
 salon-0.008
TokenJack
Token ID14295
Feature activation-8.93e-03

Pos logit contributions
 than+0.022
ets+0.016
 want+0.016
 arrow+0.016
 because+0.016
Neg logit contributions
illi-0.016
ail-0.015
uka-0.015
 kitchen-0.015
 Stacy-0.014
Token was
Token ID373
Feature activation+1.68e-02

Pos logit contributions
 than+0.016
 since+0.011
 want+0.011
ear+0.011
 because+0.011
Neg logit contributions
illi-0.018
 lobby-0.017
 babys-0.017
ail-0.017
uka-0.017
Token managed
Token ID5257
Feature activation-1.51e-02

Pos logit contributions
 than+0.039
 since+0.028
 want+0.028
 arrow+0.027
 because+0.027
Neg logit contributions
illi-0.051
ail-0.050
 babys-0.048
 lobby-0.047
 reception-0.046
Token to
Token ID284
Feature activation+2.99e-02

Pos logit contributions
 than+0.020
 want+0.012
ear+0.012
 hour+0.012
ets+0.012
Neg logit contributions
illi-0.037
ail-0.037
 lobby-0.036
 babys-0.035
 reception-0.035
Token get
Token ID651
Feature activation+3.13e-02

Pos logit contributions
illi+0.061
ail+0.060
 babys+0.058
 lobby+0.058
 reception+0.057
Neg logit contributions
 than-0.052
 want-0.039
 like-0.037
ear-0.036
 arrow-0.036
Token to
Token ID284
Feature activation+4.64e-02

Pos logit contributions
illi+0.063
ail+0.062
 lobby+0.060
 babys+0.060
 salon+0.059
Neg logit contributions
 than-0.055
 want-0.041
 like-0.040
ear-0.040
 because-0.039
Token the
Token ID262
Feature activation+2.51e-02

Pos logit contributions
illi+0.089
ail+0.087
 lobby+0.083
 babys+0.083
 reception+0.082
Neg logit contributions
 than-0.087
 want-0.066
ear-0.064
 hour-0.062
 arrow-0.062
Token checkout
Token ID28006
Feature activation+8.96e-02

Pos logit contributions
illi+0.036
ail+0.035
 lobby+0.033
 babys+0.033
 reception+0.032
Neg logit contributions
 than-0.059
 want-0.047
ear-0.046
 hour-0.046
ets-0.046
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
illi+0.209
ail+0.207
 lobby+0.204
 babys+0.200
 reception+0.199
Neg logit contributions
 than-0.126
 arrow-0.083
ear-0.083
 want-0.082
ust-0.082
Token The
Token ID383
Feature activation+2.19e-02

Pos logit contributions
 than+0.025
 want+0.017
ear+0.017
 hour+0.017
ets+0.017
Neg logit contributions
illi-0.031
ail-0.030
 lobby-0.030
 babys-0.029
 reception-0.029
Token baby
Token ID5156
Feature activation+1.25e-02

Pos logit contributions
ail+0.036
illi+0.036
 Stacy+0.034
ili+0.033
uka+0.033
Neg logit contributions
 than-0.045
 hour-0.037
 want-0.036
 because-0.034
 since-0.034
Token was
Token ID373
Feature activation+2.44e-02

Pos logit contributions
illi+0.024
ail+0.023
 lobby+0.023
 babys+0.022
 reception+0.022
Neg logit contributions
 than-0.023
 want-0.017
 since-0.017
 because-0.016
 hour-0.016
Token so
Token ID523
Feature activation+1.44e-03

Pos logit contributions
ail+0.061
illi+0.059
 lobby+0.057
 Stacy+0.057
 babys+0.057
Neg logit contributions
 than-0.033
 like-0.022
 because-0.022
 want-0.021
 as-0.020
Token She
Token ID1375
Feature activation-3.05e-03

Pos logit contributions
illi+0.005
ail+0.005
 babys+0.005
 lobby+0.005
 Stacy+0.005
Neg logit contributions
 than-0.007
ets-0.005
ear-0.005
 hour-0.005
 want-0.005
Token followed
Token ID3940
Feature activation+1.65e-02

Pos logit contributions
 than+0.005
ear+0.004
 hour+0.004
icated+0.004
 target+0.004
Neg logit contributions
illi-0.006
ail-0.006
 babys-0.006
uka-0.006
 Stacy-0.006
Token Mom
Token ID11254
Feature activation+6.55e-03

Pos logit contributions
illi+0.029
ail+0.029
 lobby+0.028
 salon+0.026
uka+0.026
Neg logit contributions
 than-0.032
 because-0.026
 want-0.025
ear-0.025
 like-0.025
Token to
Token ID284
Feature activation+6.02e-02

Pos logit contributions
illi+0.017
ail+0.017
 lobby+0.017
 babys+0.017
 reception+0.016
Neg logit contributions
 than-0.008
 want-0.005
ets-0.004
 like-0.004
 because-0.004
Token the
Token ID262
Feature activation+1.75e-02

Pos logit contributions
ail+0.133
illi+0.124
uffy+0.119
 lobby+0.119
lor+0.118
Neg logit contributions
 than-0.096
 like-0.079
 want-0.079
 because-0.078
 as-0.078
Token checkout
Token ID28006
Feature activation+8.95e-02

Pos logit contributions
ail+0.027
illi+0.026
ili+0.025
uka+0.024
acey+0.024
Neg logit contributions
 than-0.039
 hour-0.031
 want-0.031
 arrow-0.031
 like-0.030
Token.
Token ID13
Feature activation+4.18e-03

Pos logit contributions
illi+0.220
ail+0.217
 lobby+0.211
 babys+0.210
 reception+0.207
Neg logit contributions
 than-0.119
 want-0.074
ear-0.072
ets-0.070
 hour-0.070
Token She
Token ID1375
Feature activation-8.50e-03

Pos logit contributions
illi+0.008
ail+0.008
 lobby+0.008
 babys+0.008
 reception+0.007
Neg logit contributions
 than-0.008
 want-0.006
ear-0.006
 hour-0.006
ets-0.006
Token hoped
Token ID10719
Feature activation-2.46e-02

Pos logit contributions
 than+0.014
 want+0.010
 like+0.009
 because+0.009
ets+0.009
Neg logit contributions
ail-0.018
illi-0.018
 lobby-0.017
 babys-0.017
 reception-0.017
Token they
Token ID484
Feature activation-1.78e-02

Pos logit contributions
 than+0.042
 because+0.034
 as+0.032
 like+0.032
 since+0.031
Neg logit contributions
illi-0.050
ail-0.049
 lobby-0.048
ili-0.046
 babys-0.046
Token would
Token ID561
Feature activation+1.96e-02

Pos logit contributions
 than+0.025
 want+0.018
 like+0.016
 because+0.016
 since+0.015
Neg logit contributions
ail-0.043
illi-0.042
 babys-0.042
 lobby-0.041
 reception-0.041
Token cold
Token ID4692
Feature activation+2.84e-03

Pos logit contributions
illi+0.057
ail+0.057
 lobby+0.054
 babys+0.054
 reception+0.053
Neg logit contributions
 than-0.051
 want-0.037
ear-0.036
 hour-0.036
ets-0.036
Token it
Token ID340
Feature activation+1.91e-02

Pos logit contributions
illi+0.006
ail+0.006
 lobby+0.006
 babys+0.006
 reception+0.006
Neg logit contributions
 than-0.004
ear-0.003
 want-0.003
 hour-0.003
ets-0.003
Token got
Token ID1392
Feature activation+4.56e-02

Pos logit contributions
illi+0.033
ail+0.032
 lobby+0.031
 babys+0.031
 reception+0.030
Neg logit contributions
 than-0.039
ear-0.030
 hour-0.029
 want-0.029
ets-0.029
Token or
Token ID393
Feature activation+2.01e-02

Pos logit contributions
ail+0.095
 babys+0.089
illi+0.087
 reception+0.086
 kitchen+0.086
Neg logit contributions
 than-0.074
 hour-0.055
ear-0.054
ets-0.052
 want-0.052
Token<|endoftext|>
Token ID50256
Feature activation+5.84e-02

Pos logit contributions
illi+0.033
ail+0.033
 lobby+0.032
 babys+0.032
 kitchen+0.031
Neg logit contributions
 than-0.040
ear-0.031
ets-0.031
 hour-0.031
 want-0.030
TokenOnce
Token ID7454
Feature activation+8.93e-02

Pos logit contributions
 salon+0.098
ail+0.096
 babys+0.094
 reception+0.092
illi+0.092
Neg logit contributions
 than-0.117
 like-0.093
 because-0.091
 since-0.088
 and-0.088
Token there
Token ID612
Feature activation+5.01e-02

Pos logit contributions
illi+0.170
 reception+0.165
 lobby+0.165
 babys+0.163
 Stacy+0.159
Neg logit contributions
 than-0.162
 want-0.124
 because-0.120
 hour-0.118
ust-0.117
Token was
Token ID373
Feature activation+1.51e-04

Pos logit contributions
illi+0.103
 reception+0.103
ail+0.102
 babys+0.101
 Stacy+0.101
Neg logit contributions
 than-0.084
 because-0.063
 like-0.063
 want-0.061
 since-0.060
Token a
Token ID257
Feature activation-3.22e-02

Pos logit contributions
illi+0.000
 kitchen+0.000
 lobby+0.000
uka+0.000
 babys+0.000
Neg logit contributions
 than-0.000
ets-0.000
 target-0.000
ust-0.000
ear-0.000
Token little
Token ID1310
Feature activation-4.32e-02

Pos logit contributions
 than+0.055
 want+0.040
 hour+0.038
ear+0.038
 arrow+0.037
Neg logit contributions
illi-0.066
ail-0.066
 lobby-0.063
 babys-0.062
 reception-0.062
Token girl
Token ID2576
Feature activation+8.76e-03

Pos logit contributions
 than+0.090
 want+0.069
ear+0.068
 hour+0.067
ets+0.067
Neg logit contributions
illi-0.073
ail-0.071
 lobby-0.069
 babys-0.068
 reception-0.067
Token happy
Token ID3772
Feature activation-7.01e-02

Pos logit contributions
ail+0.002
 lobby+0.002
illi+0.002
 babys+0.002
 reception+0.002
Neg logit contributions
 than-0.002
 want-0.001
 like-0.001
ear-0.001
 hour-0.001
Token.
Token ID13
Feature activation-9.30e-04

Pos logit contributions
 than+0.094
ust+0.081
 hour+0.078
ets+0.077
 wanna+0.074
Neg logit contributions
ail-0.150
 babys-0.147
 kitchen-0.147
illi-0.145
 salon-0.142
Token She
Token ID1375
Feature activation-4.36e-03

Pos logit contributions
 than+0.002
 want+0.001
 because+0.001
ear+0.001
 since+0.001
Neg logit contributions
illi-0.002
ail-0.002
 lobby-0.002
 reception-0.002
 babys-0.002
Token opened
Token ID4721
Feature activation+1.30e-02

Pos logit contributions
 than+0.008
 hour+0.006
ear+0.006
ets+0.006
 want+0.006
Neg logit contributions
illi-0.008
ail-0.008
 babys-0.008
 lobby-0.008
 reception-0.008
Token the
Token ID262
Feature activation+2.89e-02

Pos logit contributions
illi+0.026
 babys+0.026
ail+0.026
 lobby+0.025
 reception+0.025
Neg logit contributions
 than-0.022
 as-0.017
 because-0.017
 like-0.016
 since-0.016
Token kit
Token ID6220
Feature activation+8.92e-02

Pos logit contributions
illi+0.048
ili+0.046
ail+0.046
uka+0.044
aby+0.044
Neg logit contributions
 than-0.057
 arrow-0.049
 target-0.046
 like-0.046
 want-0.045
Token and
Token ID290
Feature activation-1.88e-02

Pos logit contributions
illi+0.249
ail+0.247
 lobby+0.240
 babys+0.240
 reception+0.236
Neg logit contributions
 than-0.087
 want-0.044
ear-0.042
 hour-0.040
ets-0.039
Token started
Token ID2067
Feature activation+2.85e-03

Pos logit contributions
 than+0.027
 since+0.020
 arrow+0.020
 want+0.019
 because+0.019
Neg logit contributions
illi-0.040
ail-0.040
 babys-0.040
 lobby-0.040
omm-0.039
Token blowing
Token ID19280
Feature activation+1.42e-03

Pos logit contributions
illi+0.007
ail+0.007
 lobby+0.007
uka+0.007
ili+0.007
Neg logit contributions
 than-0.003
 as-0.002
 because-0.002
 like-0.002
 and-0.002
Token bubbles
Token ID25037
Feature activation-9.17e-03

Pos logit contributions
illi+0.003
ail+0.003
 babys+0.003
 lobby+0.003
 reception+0.003
Neg logit contributions
 than-0.002
 like-0.002
 want-0.002
 arrow-0.002
 because-0.002
Token.
Token ID13
Feature activation+7.40e-04

Pos logit contributions
 than+0.014
ear+0.010
ust+0.010
 hour+0.010
 wanna+0.010
Neg logit contributions
ail-0.019
illi-0.019
 lobby-0.018
 reception-0.018
 babys-0.018
Token off
Token ID572
Feature activation+3.81e-04

Pos logit contributions
 than+0.038
 want+0.027
 arrow+0.026
 since+0.026
 because+0.026
Neg logit contributions
illi-0.050
ail-0.050
 babys-0.047
 lobby-0.046
ili-0.046
Token they
Token ID484
Feature activation-1.38e-02

Pos logit contributions
illi+0.001
ail+0.001
 babys+0.001
 lobby+0.001
uka+0.001
Neg logit contributions
 than-0.001
 want-0.000
 because-0.000
ets-0.000
 hour-0.000
Token went
Token ID1816
Feature activation+3.34e-02

Pos logit contributions
 than+0.021
 want+0.015
ets+0.014
 hour+0.014
ear+0.014
Neg logit contributions
illi-0.031
ail-0.030
 babys-0.029
 lobby-0.029
 reception-0.029
Token to
Token ID284
Feature activation+4.47e-02

Pos logit contributions
illi+0.078
ail+0.077
 lobby+0.074
 babys+0.074
 reception+0.073
Neg logit contributions
 than-0.049
 want-0.032
ear-0.031
ets-0.031
 hour-0.030
Token the
Token ID262
Feature activation+1.92e-02

Pos logit contributions
ail+0.086
illi+0.083
 babys+0.078
 reception+0.077
uka+0.076
Neg logit contributions
 than-0.082
 want-0.067
 like-0.064
 because-0.063
ear-0.061
Token checkout
Token ID28006
Feature activation+8.90e-02

Pos logit contributions
illi+0.027
ail+0.027
 Stacy+0.024
ili+0.024
aby+0.024
Neg logit contributions
 than-0.045
 want-0.036
 arrow-0.036
 hour-0.036
 target-0.036
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
illi+0.189
ail+0.187
 lobby+0.184
 babys+0.180
 reception+0.179
Neg logit contributions
 than-0.145
 want-0.103
ear-0.102
ust-0.101
 arrow-0.100
Token P
Token ID350
Feature activation+2.48e-02

Pos logit contributions
 than+0.021
 want+0.016
ear+0.015
 hour+0.015
ets+0.015
Neg logit contributions
illi-0.021
ail-0.021
 lobby-0.020
 babys-0.020
 reception-0.020
Tokenhew
Token ID6391
Feature activation-2.04e-02

Pos logit contributions
ail+0.035
illi+0.033
uka+0.029
 lobby+0.029
 babys+0.028
Neg logit contributions
 than-0.061
 arrow-0.049
 target-0.048
 hour-0.048
 want-0.048
Token,
Token ID11
Feature activation-4.66e-03

Pos logit contributions
 than+0.030
 want+0.020
ets+0.020
 since+0.019
ear+0.019
Neg logit contributions
illi-0.047
 lobby-0.046
 babys-0.045
 reception-0.045
ail-0.045
Token Mum
Token ID38367
Feature activation-4.52e-03

Pos logit contributions
 than+0.008
 because+0.006
 want+0.006
 since+0.006
 like+0.006
Neg logit contributions
illi-0.009
ail-0.009
 lobby-0.009
 babys-0.009
 reception-0.009
TokenWhen
Token ID2215
Feature activation+9.22e-03

Pos logit contributions
 than+0.027
ets+0.022
 want+0.019
 target+0.019
eting+0.018
Neg logit contributions
illi-0.025
ail-0.024
 babys-0.023
ili-0.022
uka-0.022
Token they
Token ID484
Feature activation-1.05e-02

Pos logit contributions
illi+0.021
ail+0.021
 lobby+0.020
 babys+0.020
 reception+0.020
Neg logit contributions
 than-0.014
 want-0.009
 hour-0.009
 because-0.009
 arrow-0.009
Token got
Token ID1392
Feature activation+3.73e-02

Pos logit contributions
 than+0.019
 want+0.015
 since+0.014
ear+0.014
 like+0.014
Neg logit contributions
ail-0.020
illi-0.020
 lobby-0.019
 babys-0.019
 Stacy-0.019
Token to
Token ID284
Feature activation+3.93e-02

Pos logit contributions
illi+0.088
 Stacy+0.084
ail+0.084
aby+0.082
 lobby+0.082
Neg logit contributions
 than-0.053
 want-0.036
 like-0.036
 because-0.036
 as-0.034
Token the
Token ID262
Feature activation+2.00e-02

Pos logit contributions
ail+0.071
illi+0.069
 lobby+0.064
 babys+0.064
 reception+0.064
Neg logit contributions
 than-0.079
 want-0.062
 arrow-0.060
 like-0.060
ear-0.059
Token checkout
Token ID28006
Feature activation+8.83e-02

Pos logit contributions
ail+0.031
illi+0.031
 Stacy+0.029
ili+0.028
aby+0.028
Neg logit contributions
 than-0.044
 arrow-0.035
 target-0.035
 like-0.035
 want-0.034
Token,
Token ID11
Feature activation+1.73e-03

Pos logit contributions
illi+0.197
ail+0.190
ili+0.185
 Stacy+0.185
 babys+0.184
Neg logit contributions
 than-0.142
 want-0.093
 because-0.090
 like-0.089
 hour-0.089
Token Tim
Token ID5045
Feature activation+1.09e-02

Pos logit contributions
illi+0.004
ail+0.004
 lobby+0.004
 babys+0.004
 reception+0.004
Neg logit contributions
 than-0.002
 because-0.001
 want-0.001
 arrow-0.001
 since-0.001
Tokenmy
Token ID1820
Feature activation-7.20e-03

Pos logit contributions
illi+0.023
 lobby+0.023
 reception+0.022
 babys+0.022
ail+0.022
Neg logit contributions
 than-0.018
 want-0.013
 since-0.013
ets-0.013
ear-0.012
Token's
Token ID338
Feature activation+3.34e-02

Pos logit contributions
 than+0.012
 want+0.009
 since+0.008
ear+0.008
 arrow+0.008
Neg logit contributions
illi-0.015
ail-0.015
 lobby-0.014
 babys-0.014
 reception-0.014
Token mom
Token ID1995
Feature activation-3.19e-03

Pos logit contributions
illi+0.051
ili+0.046
ail+0.045
 Stacy+0.045
uka+0.045
Neg logit contributions
 than-0.076
 want-0.062
 arrow-0.061
 hour-0.061
 because-0.059
Token and
Token ID290
Feature activation-3.20e-02

Pos logit contributions
illi+0.087
ail+0.086
 lobby+0.083
 babys+0.082
 salon+0.082
Neg logit contributions
 than-0.049
 want-0.031
ear-0.031
 hour-0.031
 arrow-0.030
Token they
Token ID484
Feature activation-2.86e-02

Pos logit contributions
 than+0.057
 want+0.041
ear+0.040
ets+0.039
 hour+0.039
Neg logit contributions
illi-0.064
ail-0.063
 lobby-0.061
 babys-0.061
 reception-0.059
Token went
Token ID1816
Feature activation+2.91e-02

Pos logit contributions
 than+0.048
 want+0.034
ear+0.034
ets+0.033
 hour+0.033
Neg logit contributions
illi-0.060
ail-0.059
 lobby-0.057
 babys-0.057
 reception-0.056
Token to
Token ID284
Feature activation+3.96e-02

Pos logit contributions
illi+0.073
ail+0.070
 babys+0.069
uka+0.068
 lobby+0.068
Neg logit contributions
 than-0.036
 want-0.022
ets-0.022
 because-0.021
 like-0.021
Token the
Token ID262
Feature activation+1.41e-02

Pos logit contributions
ail+0.078
illi+0.076
 babys+0.072
 lobby+0.072
 reception+0.071
Neg logit contributions
 than-0.069
 want-0.057
 like-0.053
 because-0.052
ear-0.051
Token checkout
Token ID28006
Feature activation+8.80e-02

Pos logit contributions
ail+0.022
illi+0.021
aby+0.020
ili+0.020
 Stacy+0.019
Neg logit contributions
 than-0.030
 like-0.025
 want-0.024
 target-0.024
 arrow-0.024
Token.
Token ID13
Feature activation-1.34e-02

Pos logit contributions
illi+0.188
ail+0.185
 lobby+0.181
 babys+0.179
 reception+0.177
Neg logit contributions
 than-0.143
 want-0.100
ear-0.099
 arrow-0.098
 hour-0.097
Token The
Token ID383
Feature activation+1.97e-02

Pos logit contributions
 than+0.026
 want+0.020
ear+0.019
 wanna+0.019
 because+0.019
Neg logit contributions
ail-0.025
illi-0.024
 lobby-0.023
 babys-0.023
 reception-0.023
Token little
Token ID1310
Feature activation+1.42e-02

Pos logit contributions
ail+0.034
illi+0.033
aby+0.031
ili+0.031
 lobby+0.030
Neg logit contributions
 than-0.040
 hour-0.033
 want-0.033
 like-0.032
 because-0.030
Token boy
Token ID2933
Feature activation+2.37e-02

Pos logit contributions
illi+0.027
ail+0.027
 lobby+0.025
 babys+0.025
 reception+0.025
Neg logit contributions
 than-0.027
 want-0.020
 hour-0.019
 arrow-0.019
 like-0.019
Token smiled
Token ID13541
Feature activation-2.93e-02

Pos logit contributions
illi+0.046
ail+0.045
 lobby+0.044
 babys+0.043
 reception+0.042
Neg logit contributions
 than-0.044
 want-0.032
ear-0.031
ets-0.031
 hour-0.031
Token happy
Token ID3772
Feature activation-5.68e-02

Pos logit contributions
 than+0.009
ear+0.007
 want+0.007
ets+0.006
 hour+0.006
Neg logit contributions
illi-0.010
ail-0.010
 babys-0.009
 lobby-0.009
 reception-0.009
Token and
Token ID290
Feature activation+4.39e-03

Pos logit contributions
 than+0.086
ust+0.069
ets+0.069
 wanna+0.066
ear+0.066
Neg logit contributions
ail-0.116
 lobby-0.115
 babys-0.114
 reception-0.113
 kitchen-0.112
Token tired
Token ID10032
Feature activation-1.72e-02

Pos logit contributions
illi+0.009
ail+0.009
 babys+0.009
 lobby+0.008
 salon+0.008
Neg logit contributions
 than-0.008
 want-0.006
 because-0.005
 like-0.005
ear-0.005
Token.
Token ID13
Feature activation-7.46e-03

Pos logit contributions
 than+0.025
ear+0.018
 arrow+0.018
ust+0.017
 want+0.017
Neg logit contributions
illi-0.037
 lobby-0.037
 reception-0.036
 babys-0.036
ail-0.036
Token<|endoftext|>
Token ID50256
Feature activation+4.80e-02

Pos logit contributions
 than+0.014
 want+0.010
ets+0.010
 hour+0.010
ear+0.010
Neg logit contributions
illi-0.014
ail-0.014
 babys-0.013
 lobby-0.013
 Stacy-0.013
TokenOnce
Token ID7454
Feature activation+8.79e-02

Pos logit contributions
 salon+0.121
 babys+0.115
ail+0.114
 reception+0.112
illi+0.110
Neg logit contributions
 than-0.062
 like-0.042
 and-0.042
 because-0.041
 want-0.037
Token upon
Token ID2402
Feature activation-1.19e-02

Pos logit contributions
illi+0.174
 lobby+0.171
 reception+0.170
 babys+0.167
 salon+0.164
Neg logit contributions
 than-0.151
 want-0.115
 because-0.113
ust-0.110
 hour-0.110
Token a
Token ID257
Feature activation-1.69e-03

Pos logit contributions
 than+0.025
ets+0.020
 hour+0.019
ear+0.019
 want+0.019
Neg logit contributions
illi-0.019
ail-0.018
 lobby-0.018
 babys-0.017
 kitchen-0.017
Token time
Token ID640
Feature activation+3.76e-02

Pos logit contributions
 than+0.003
 arrow+0.003
icated+0.003
ear+0.003
 target+0.003
Neg logit contributions
ail-0.003
illi-0.003
uffy-0.003
 kitchen-0.003
 lobby-0.003
Token,
Token ID11
Feature activation+2.95e-02

Pos logit contributions
illi+0.079
ail+0.076
 lobby+0.075
 babys+0.074
 reception+0.074
Neg logit contributions
 than-0.064
 want-0.045
ear-0.044
 hour-0.043
 because-0.043
Token there
Token ID612
Feature activation+4.18e-02

Pos logit contributions
 reception+0.062
 babys+0.062
 lobby+0.061
illi+0.060
ail+0.060
Neg logit contributions
 than-0.051
 like-0.036
 want-0.036
 because-0.035
 hour-0.034
Token until
Token ID1566
Feature activation+1.14e-02

Pos logit contributions
 than+0.063
 want+0.048
ear+0.047
 hour+0.047
ets+0.047
Neg logit contributions
illi-0.053
ail-0.052
 lobby-0.050
 babys-0.050
 reception-0.049
Token one
Token ID530
Feature activation-2.96e-02

Pos logit contributions
illi+0.022
ail+0.022
 lobby+0.021
 babys+0.020
uka+0.020
Neg logit contributions
 than-0.022
 want-0.016
 hour-0.016
 because-0.016
 like-0.016
Token day
Token ID1110
Feature activation+2.73e-02

Pos logit contributions
 than+0.052
ets+0.039
ear+0.038
 want+0.037
 target+0.037
Neg logit contributions
illi-0.058
ail-0.057
 babys-0.056
 lobby-0.056
 reception-0.054
Token,
Token ID11
Feature activation-1.43e-02

Pos logit contributions
illi+0.056
ail+0.055
 lobby+0.054
 babys+0.053
 reception+0.051
Neg logit contributions
 than-0.048
 want-0.035
ear-0.034
 hour-0.033
 like-0.033
Token something
Token ID1223
Feature activation-4.33e-02

Pos logit contributions
 than+0.032
 want+0.025
ear+0.024
 hour+0.024
ets+0.024
Neg logit contributions
illi-0.022
ail-0.022
 lobby-0.021
 babys-0.021
 reception-0.020
Token extraordinary
Token ID11359
Feature activation-9.49e-02

Pos logit contributions
 than+0.090
ear+0.070
 want+0.067
 hour+0.067
ets+0.067
Neg logit contributions
illi-0.071
ail-0.070
 babys-0.068
 lobby-0.067
 reception-0.067
Token happened
Token ID3022
Feature activation-6.56e-03

Pos logit contributions
 than+0.200
ear+0.163
 hour+0.163
ust+0.162
 wanna+0.159
Neg logit contributions
ail-0.136
illi-0.135
 lobby-0.128
 babys-0.126
 reception-0.125
Token!
Token ID0
Feature activation-3.81e-02

Pos logit contributions
 than+0.009
 hour+0.008
ust+0.007
 arrow+0.007
ets+0.007
Neg logit contributions
ail-0.013
 kitchen-0.013
illi-0.013
 lobby-0.013
 babys-0.012
Token
Token ID198
Feature activation-2.11e-02

Pos logit contributions
 than+0.075
 want+0.057
ear+0.055
 hour+0.054
ets+0.054
Neg logit contributions
illi-0.070
ail-0.069
 lobby-0.066
 babys-0.065
 reception-0.064
Token
Token ID198
Feature activation-2.62e-02

Pos logit contributions
 than+0.038
 want+0.028
ear+0.027
 hour+0.027
ets+0.026
Neg logit contributions
illi-0.042
ail-0.041
 lobby-0.040
 babys-0.040
 reception-0.039
TokenO
Token ID46
Feature activation+4.36e-03

Pos logit contributions
 than+0.048
icated+0.036
 arrow+0.036
ets+0.035
ear+0.035
Neg logit contributions
illi-0.049
ail-0.047
 Stacy-0.045
 babys-0.045
 reception-0.045
Token wished
Token ID16555
Feature activation-2.80e-02

Pos logit contributions
illi+0.027
ail+0.027
 lobby+0.026
 babys+0.026
 reception+0.025
Neg logit contributions
 than-0.023
ear-0.017
 want-0.016
 hour-0.016
ets-0.016
Token it
Token ID340
Feature activation+1.01e-03

Pos logit contributions
 than+0.045
 want+0.031
ear+0.030
 hour+0.030
ets+0.030
Neg logit contributions
illi-0.061
ail-0.060
 lobby-0.059
 babys-0.058
 reception-0.057
Token could
Token ID714
Feature activation+2.39e-02

Pos logit contributions
illi+0.002
ail+0.002
 lobby+0.002
 babys+0.002
 reception+0.002
Neg logit contributions
 than-0.002
 want-0.001
ear-0.001
ets-0.001
 hour-0.001
Token do
Token ID466
Feature activation+8.59e-03

Pos logit contributions
illi+0.045
ail+0.044
 lobby+0.043
 babys+0.043
 reception+0.042
Neg logit contributions
 than-0.045
 want-0.033
ear-0.033
 hour-0.032
ets-0.032
Token something
Token ID1223
Feature activation-2.68e-02

Pos logit contributions
illi+0.015
ail+0.015
 babys+0.015
 lobby+0.015
 reception+0.014
Neg logit contributions
 than-0.018
 want-0.013
ear-0.013
ets-0.013
 because-0.013
Token exciting
Token ID7895
Feature activation-9.31e-02

Pos logit contributions
 than+0.048
 wanna+0.040
ear+0.040
 hour+0.039
affe+0.038
Neg logit contributions
ail-0.045
illi-0.043
 kitchen-0.040
 reception-0.040
 babys-0.040
Token,
Token ID11
Feature activation-3.12e-02

Pos logit contributions
 wanna+0.141
 than+0.132
ust+0.132
 want+0.125
ever+0.122
Neg logit contributions
ail-0.154
illi-0.151
 kitchen-0.146
 lobby-0.145
 office-0.144
Token but
Token ID475
Feature activation-3.08e-02

Pos logit contributions
 than+0.048
ear+0.039
ets+0.039
ust+0.039
 wanna+0.034
Neg logit contributions
 kitchen-0.060
 salon-0.058
 lobby-0.058
 babys-0.058
 reception-0.057
Token it
Token ID340
Feature activation-3.26e-02

Pos logit contributions
 than+0.053
 want+0.038
 hour+0.037
 arrow+0.036
ear+0.036
Neg logit contributions
illi-0.065
ail-0.064
 lobby-0.061
 babys-0.061
 reception-0.060
Token couldn
Token ID3521
Feature activation+7.78e-03

Pos logit contributions
 than+0.062
 want+0.045
ear+0.045
ets+0.044
 hour+0.044
Neg logit contributions
illi-0.061
ail-0.061
 lobby-0.058
 babys-0.058
 reception-0.057
Token't
Token ID470
Feature activation-4.03e-02

Pos logit contributions
illi+0.011
 lobby+0.010
ail+0.010
 babys+0.010
 reception+0.010
Neg logit contributions
 than-0.018
 want-0.015
 because-0.015
ear-0.014
 hour-0.014
Token
Token ID198
Feature activation-2.53e-02

Pos logit contributions
 than+0.031
 want+0.022
ear+0.021
 hour+0.021
 because+0.021
Neg logit contributions
ail-0.038
illi-0.038
 babys-0.037
 lobby-0.037
 reception-0.036
TokenOne
Token ID3198
Feature activation-3.01e-02

Pos logit contributions
 than+0.044
ets+0.033
 want+0.032
ear+0.031
 arrow+0.030
Neg logit contributions
illi-0.052
 lobby-0.049
 reception-0.048
 kitchen-0.047
 salon-0.046
Token day
Token ID1110
Feature activation+2.72e-02

Pos logit contributions
 than+0.054
ets+0.039
ear+0.039
 target+0.039
 arrow+0.038
Neg logit contributions
illi-0.059
ail-0.058
 lobby-0.057
 babys-0.056
 reception-0.055
Token,
Token ID11
Feature activation-1.53e-02

Pos logit contributions
illi+0.052
ail+0.051
 lobby+0.049
 babys+0.049
 reception+0.048
Neg logit contributions
 than-0.051
 want-0.037
ear-0.037
ets-0.037
 hour-0.036
Token something
Token ID1223
Feature activation-4.77e-02

Pos logit contributions
 than+0.027
 because+0.020
 want+0.020
 like+0.020
 hour+0.019
Neg logit contributions
ail-0.032
illi-0.031
 lobby-0.029
 babys-0.029
 salon-0.029
Token exciting
Token ID7895
Feature activation-9.30e-02

Pos logit contributions
 than+0.098
ear+0.076
 want+0.073
ets+0.072
 since+0.072
Neg logit contributions
ail-0.080
illi-0.080
 babys-0.077
 reception-0.076
 lobby-0.075
Token happened
Token ID3022
Feature activation-9.04e-03

Pos logit contributions
 than+0.201
ust+0.173
ear+0.170
 wanna+0.166
 want+0.161
Neg logit contributions
ail-0.125
illi-0.119
 lobby-0.117
 babys-0.115
 reception-0.115
Token.
Token ID13
Feature activation-3.18e-02

Pos logit contributions
 than+0.014
ust+0.011
 arrow+0.011
 hour+0.011
ets+0.011
Neg logit contributions
ail-0.017
 kitchen-0.017
illi-0.017
 lobby-0.016
 babys-0.016
Token A
Token ID317
Feature activation-3.13e-02

Pos logit contributions
 than+0.067
ust+0.049
 want+0.049
ets+0.049
ear+0.049
Neg logit contributions
illi-0.054
 lobby-0.053
 babys-0.052
 reception-0.051
ail-0.051
Token big
Token ID1263
Feature activation-5.26e-02

Pos logit contributions
 than+0.045
 hour+0.035
 arrow+0.035
 want+0.033
 target+0.032
Neg logit contributions
illi-0.070
ail-0.068
uka-0.065
 salon-0.064
ili-0.063
Token storm
Token ID6388
Feature activation-3.74e-02

Pos logit contributions
 than+0.105
 want+0.080
 arrow+0.079
 hour+0.078
 because+0.077
Neg logit contributions
illi-0.097
ail-0.095
uka-0.088
 babys-0.087
 lobby-0.087
Token
Token ID198
Feature activation-2.24e-02

Pos logit contributions
 than+0.027
 hour+0.018
 want+0.018
ear+0.018
 because+0.018
Neg logit contributions
 lobby-0.040
illi-0.040
ail-0.039
 salon-0.039
 reception-0.039
TokenOne
Token ID3198
Feature activation-2.94e-02

Pos logit contributions
 than+0.041
 want+0.030
ear+0.029
ets+0.028
 wanna+0.028
Neg logit contributions
ail-0.044
illi-0.043
 babys-0.041
 Stacy-0.040
 kitchen-0.040
Token day
Token ID1110
Feature activation+2.89e-02

Pos logit contributions
 than+0.048
 want+0.033
ear+0.033
ets+0.033
 hour+0.032
Neg logit contributions
illi-0.063
ail-0.062
 babys-0.061
 lobby-0.060
 reception-0.059
Token,
Token ID11
Feature activation-1.29e-02

Pos logit contributions
illi+0.065
 lobby+0.063
ail+0.062
 salon+0.061
uka+0.060
Neg logit contributions
 than-0.045
 because-0.031
 want-0.031
 since-0.031
 like-0.030
Token something
Token ID1223
Feature activation-4.61e-02

Pos logit contributions
 than+0.027
 because+0.021
 since+0.021
 arrow+0.021
 like+0.021
Neg logit contributions
illi-0.022
 lobby-0.022
ail-0.021
uka-0.020
 reception-0.020
Token exciting
Token ID7895
Feature activation-9.27e-02

Pos logit contributions
 than+0.091
ear+0.069
 want+0.067
ets+0.066
 hour+0.065
Neg logit contributions
ail-0.082
illi-0.082
 babys-0.079
 reception-0.077
 lobby-0.076
Token happened
Token ID3022
Feature activation-8.14e-03

Pos logit contributions
 than+0.196
ear+0.162
ust+0.162
 wanna+0.156
 target+0.156
Neg logit contributions
ail-0.136
illi-0.131
 babys-0.128
 reception-0.126
 lobby-0.124
Token:
Token ID25
Feature activation+8.25e-04

Pos logit contributions
 than+0.012
ets+0.009
ust+0.009
 hour+0.009
 arrow+0.009
Neg logit contributions
ail-0.017
illi-0.016
 kitchen-0.016
 babys-0.016
 lobby-0.016
Token a
Token ID257
Feature activation-3.01e-02

Pos logit contributions
ail+0.002
illi+0.002
 lobby+0.002
 salon+0.002
 reception+0.002
Neg logit contributions
 than-0.001
 because-0.001
 like-0.001
 arrow-0.001
 since-0.001
Token modern
Token ID3660
Feature activation-4.79e-02

Pos logit contributions
 than+0.046
 arrow+0.038
 target+0.035
 like+0.035
 want+0.034
Neg logit contributions
ail-0.064
illi-0.063
lo-0.060
loe-0.059
ili-0.059
Token l
Token ID300
Feature activation-1.27e-02

Pos logit contributions
 than+0.100
 because+0.077
 arrow+0.077
 like+0.076
 want+0.075
Neg logit contributions
illi-0.084
ail-0.084
uka-0.077
ili-0.075
lo-0.075
Token,
Token ID11
Feature activation-2.71e-02

Pos logit contributions
ail+0.021
 salon+0.021
illi+0.021
 kitchen+0.020
 cabinet+0.020
Neg logit contributions
 than-0.018
 wanna-0.014
ear-0.014
ust-0.013
 enjoyable-0.013
Token but
Token ID475
Feature activation-2.55e-02

Pos logit contributions
 than+0.036
ear+0.023
ets+0.023
 hour+0.021
ust+0.021
Neg logit contributions
illi-0.065
ail-0.064
 babys-0.064
 salon-0.063
 reception-0.062
Token I
Token ID314
Feature activation-2.88e-02

Pos logit contributions
 than+0.033
 want+0.021
 arrow+0.020
 because+0.020
 like+0.019
Neg logit contributions
illi-0.064
ail-0.063
 lobby-0.062
 babys-0.061
 reception-0.061
Token'm
Token ID1101
Feature activation+1.69e-02

Pos logit contributions
 than+0.045
 hour+0.034
ear+0.031
 arrow+0.031
ets+0.030
Neg logit contributions
illi-0.060
ail-0.060
 babys-0.058
uka-0.056
 Stacy-0.056
Token too
Token ID1165
Feature activation-1.76e-02

Pos logit contributions
illi+0.033
ail+0.033
 lobby+0.032
 babys+0.031
 reception+0.031
Neg logit contributions
 than-0.031
 want-0.023
ear-0.022
 like-0.022
 because-0.022
Token shy
Token ID15800
Feature activation-9.20e-02

Pos logit contributions
 than+0.039
ets+0.032
ear+0.030
 hour+0.030
 want+0.030
Neg logit contributions
illi-0.026
ail-0.026
 babys-0.025
 lobby-0.024
 kitchen-0.024
Token to
Token ID284
Feature activation+3.32e-02

Pos logit contributions
 arrow+0.157
 than+0.154
ust+0.147
 target+0.145
 enjoyable+0.140
Neg logit contributions
 kitchen-0.126
ail-0.121
 salon-0.120
illi-0.118
 babys-0.118
Token ask
Token ID1265
Feature activation+3.69e-02

Pos logit contributions
illi+0.064
ail+0.064
 babys+0.062
 reception+0.060
 lobby+0.060
Neg logit contributions
 than-0.060
 hour-0.043
ear-0.043
ets-0.043
ust-0.041
Token the
Token ID262
Feature activation+1.55e-02

Pos logit contributions
illi+0.088
 lobby+0.087
ail+0.086
 babys+0.084
 salon+0.083
Neg logit contributions
 than-0.054
 because-0.036
ear-0.035
 want-0.035
 like-0.035
Token other
Token ID584
Feature activation+8.76e-03

Pos logit contributions
illi+0.027
ail+0.027
 lobby+0.026
uka+0.025
 babys+0.025
Neg logit contributions
 than-0.032
 want-0.025
 hour-0.024
 arrow-0.023
 like-0.023
Token cats
Token ID11875
Feature activation+5.31e-03

Pos logit contributions
illi+0.015
ail+0.014
 babys+0.014
 lobby+0.014
 reception+0.013
Neg logit contributions
 than-0.018
ear-0.014
 want-0.014
ets-0.014
 hour-0.014
Token was
Token ID373
Feature activation-7.72e-03

Pos logit contributions
 than+0.075
ear+0.059
 want+0.058
ets+0.058
 hour+0.057
Neg logit contributions
illi-0.051
ail-0.050
 lobby-0.049
 babys-0.047
 reception-0.046
Token an
Token ID281
Feature activation-5.92e-02

Pos logit contributions
 than+0.014
 want+0.010
 hour+0.010
ear+0.010
 like+0.010
Neg logit contributions
illi-0.015
ail-0.015
 lobby-0.014
 babys-0.014
 reception-0.014
Token ordinary
Token ID8850
Feature activation-5.05e-02

Pos logit contributions
 than+0.123
ets+0.100
 target+0.099
ust+0.097
ever+0.095
Neg logit contributions
 lobby-0.091
 kitchen-0.091
 office-0.089
 babys-0.088
 reception-0.088
Token yard
Token ID12699
Feature activation-6.82e-03

Pos logit contributions
 than+0.115
ust+0.097
ear+0.096
ets+0.093
icated+0.091
Neg logit contributions
 kitchen-0.071
 lobby-0.071
 babys-0.068
ail-0.067
 cabinet-0.066
Token.
Token ID13
Feature activation-4.03e-02

Pos logit contributions
 than+0.011
ust+0.009
ear+0.009
 wanna+0.009
ets+0.009
Neg logit contributions
 lobby-0.013
 kitchen-0.013
illi-0.012
 cabinet-0.012
 reception-0.012
Token Nobody
Token ID15658
Feature activation-9.17e-02

Pos logit contributions
 than+0.076
ets+0.055
 want+0.055
ear+0.054
ust+0.054
Neg logit contributions
illi-0.077
 lobby-0.073
ail-0.073
 babys-0.072
 kitchen-0.070
Token was
Token ID373
Feature activation+1.84e-02

Pos logit contributions
 than+0.146
 target+0.120
icated+0.119
 arrow+0.116
ear+0.116
Neg logit contributions
illi-0.177
ail-0.161
 lobby-0.159
uka-0.159
 babys-0.156
Token sure
Token ID1654
Feature activation-3.55e-02

Pos logit contributions
illi+0.034
ail+0.033
 lobby+0.032
 babys+0.032
 reception+0.031
Neg logit contributions
 than-0.037
 want-0.027
ear-0.026
 hour-0.026
 like-0.026
Token how
Token ID703
Feature activation+9.45e-03

Pos logit contributions
 than+0.062
 target+0.049
ets+0.047
ear+0.047
 hour+0.046
Neg logit contributions
illi-0.067
ail-0.065
 lobby-0.063
 kitchen-0.062
 salon-0.061
Token big
Token ID1263
Feature activation-4.12e-02

Pos logit contributions
ail+0.020
illi+0.020
 lobby+0.019
 kitchen+0.019
 reception+0.019
Neg logit contributions
 than-0.015
 target-0.011
ets-0.011
ear-0.010
 arrow-0.010
Token it
Token ID340
Feature activation-9.60e-03

Pos logit contributions
 than+0.085
ust+0.079
ear+0.077
 wanna+0.075
ets+0.072
Neg logit contributions
 kitchen-0.056
 lobby-0.053
illi-0.051
 salon-0.049
 wardrobe-0.049
Token walk
Token ID2513
Feature activation-7.89e-03

Pos logit contributions
 than+0.067
 want+0.047
ear+0.047
ets+0.046
ust+0.045
Neg logit contributions
illi-0.085
ail-0.084
 lobby-0.081
 babys-0.081
 reception-0.079
Token,
Token ID11
Feature activation-1.68e-02

Pos logit contributions
 than+0.013
 like+0.008
 want+0.008
 because+0.008
 since+0.008
Neg logit contributions
illi-0.018
ail-0.018
 babys-0.017
uka-0.017
 lobby-0.017
Token Alice
Token ID14862
Feature activation-2.60e-02

Pos logit contributions
 than+0.035
 because+0.026
 like+0.026
 want+0.026
 as+0.026
Neg logit contributions
ail-0.031
illi-0.028
 babys-0.027
uka-0.027
 lobby-0.027
Token found
Token ID1043
Feature activation-3.53e-03

Pos logit contributions
 than+0.035
 want+0.028
 since+0.026
 like+0.026
 wanted+0.026
Neg logit contributions
illi-0.061
 lobby-0.057
ail-0.057
 babys-0.057
omm-0.057
Token something
Token ID1223
Feature activation-3.16e-02

Pos logit contributions
 than+0.003
 arrow+0.002
 like+0.002
 because+0.002
 as+0.002
Neg logit contributions
 salon-0.010
 lobby-0.010
ail-0.010
 babys-0.010
illi-0.009
Token exciting
Token ID7895
Feature activation-9.11e-02

Pos logit contributions
 than+0.061
ear+0.046
 want+0.046
ets+0.046
 hour+0.045
Neg logit contributions
illi-0.058
ail-0.056
 babys-0.054
 lobby-0.054
 reception-0.053
Token.
Token ID13
Feature activation-2.45e-02

Pos logit contributions
 than+0.134
ust+0.120
 wanna+0.118
ear+0.117
 hour+0.115
Neg logit contributions
ail-0.171
illi-0.169
 lobby-0.166
 kitchen-0.164
 babys-0.158
Token It
Token ID632
Feature activation-2.23e-02

Pos logit contributions
 than+0.038
 want+0.027
ear+0.026
 because+0.025
 like+0.025
Neg logit contributions
ail-0.055
illi-0.055
 babys-0.052
 lobby-0.052
uka-0.051
Token was
Token ID373
Feature activation-5.82e-04

Pos logit contributions
 than+0.038
 because+0.028
 like+0.028
 arrow+0.027
 want+0.026
Neg logit contributions
illi-0.047
 salon-0.047
 babys-0.046
 lobby-0.046
ail-0.045
Token a
Token ID257
Feature activation-3.44e-02

Pos logit contributions
 than+0.001
 like+0.001
 because+0.001
 arrow+0.001
 since+0.001
Neg logit contributions
ail-0.001
illi-0.001
 lobby-0.001
 babys-0.001
 salon-0.001
Token special
Token ID2041
Feature activation-5.69e-02

Pos logit contributions
 than+0.064
 arrow+0.048
 want+0.046
 target+0.045
 like+0.045
Neg logit contributions
illi-0.068
ail-0.067
 lobby-0.062
uka-0.062
ili-0.061
Token But
Token ID887
Feature activation-1.67e-02

Pos logit contributions
 than+0.046
 want+0.033
ear+0.032
ets+0.032
 hour+0.032
Neg logit contributions
illi-0.055
ail-0.053
 lobby-0.052
 babys-0.052
 reception-0.051
Token one
Token ID530
Feature activation-3.37e-02

Pos logit contributions
 than+0.031
 want+0.023
 hour+0.022
 arrow+0.022
ear+0.022
Neg logit contributions
illi-0.033
ail-0.032
 babys-0.031
 lobby-0.031
 reception-0.030
Token day
Token ID1110
Feature activation+2.18e-02

Pos logit contributions
 than+0.062
ets+0.049
ear+0.047
 wanna+0.045
ust+0.045
Neg logit contributions
illi-0.062
 lobby-0.060
ail-0.059
 babys-0.059
 kitchen-0.058
Token,
Token ID11
Feature activation-1.05e-02

Pos logit contributions
illi+0.046
ail+0.045
 lobby+0.043
 babys+0.043
 reception+0.042
Neg logit contributions
 than-0.038
 want-0.027
ear-0.026
 arrow-0.026
 hour-0.026
Token something
Token ID1223
Feature activation-4.30e-02

Pos logit contributions
 than+0.018
 arrow+0.013
 want+0.013
 like+0.013
 because+0.013
Neg logit contributions
ail-0.022
illi-0.022
 babys-0.021
 lobby-0.020
uka-0.020
Token amazing
Token ID4998
Feature activation-9.08e-02

Pos logit contributions
 than+0.093
ear+0.073
ets+0.070
 since+0.070
 wanna+0.069
Neg logit contributions
ail-0.066
illi-0.065
 babys-0.064
 reception-0.063
 lobby-0.062
Token happened
Token ID3022
Feature activation-4.94e-03

Pos logit contributions
 than+0.204
ust+0.177
 wanna+0.173
 hour+0.173
ear+0.169
Neg logit contributions
ail-0.110
illi-0.103
 lobby-0.096
 reception-0.094
 babys-0.094
Token!
Token ID0
Feature activation-3.41e-02

Pos logit contributions
 than+0.007
 hour+0.006
ust+0.006
ets+0.005
 arrow+0.005
Neg logit contributions
ail-0.010
 kitchen-0.010
illi-0.010
 lobby-0.010
 babys-0.009
Token A
Token ID317
Feature activation-2.97e-02

Pos logit contributions
 than+0.066
 want+0.048
ets+0.047
ear+0.047
 hour+0.046
Neg logit contributions
illi-0.064
ail-0.062
 lobby-0.061
 babys-0.061
 reception-0.059
Token giant
Token ID6175
Feature activation-5.33e-02

Pos logit contributions
 than+0.045
 arrow+0.035
 hour+0.034
 want+0.033
 target+0.031
Neg logit contributions
illi-0.066
ail-0.064
ili-0.062
uka-0.061
 lobby-0.060
Token paper
Token ID3348
Feature activation-1.91e-02

Pos logit contributions
 than+0.114
ear+0.089
ust+0.088
 want+0.088
ets+0.088
Neg logit contributions
illi-0.084
ail-0.083
 lobby-0.081
 babys-0.080
 reception-0.078
Token it
Token ID340
Feature activation-3.32e-03

Pos logit contributions
illi+0.004
 kitchen+0.004
 lobby+0.004
ail+0.004
aby+0.004
Neg logit contributions
 than-0.007
ust-0.007
 wanna-0.006
ets-0.006
 want-0.006
Token.
Token ID13
Feature activation-2.84e-02

Pos logit contributions
 than+0.005
 wanna+0.003
ear+0.003
ust+0.003
 want+0.003
Neg logit contributions
illi-0.007
ail-0.007
 lobby-0.007
 reception-0.007
 babys-0.007
Token Every
Token ID3887
Feature activation-9.68e-03

Pos logit contributions
 than+0.051
ets+0.036
 want+0.036
ust+0.036
ear+0.035
Neg logit contributions
illi-0.057
 lobby-0.055
ail-0.054
 babys-0.054
 kitchen-0.053
Token day
Token ID1110
Feature activation+2.98e-02

Pos logit contributions
 than+0.020
ust+0.015
ear+0.015
ets+0.015
 wanna+0.014
Neg logit contributions
 lobby-0.016
illi-0.016
ail-0.016
 kitchen-0.016
 salon-0.015
Token something
Token ID1223
Feature activation-3.53e-02

Pos logit contributions
illi+0.054
ail+0.052
 lobby+0.051
 babys+0.051
 reception+0.050
Neg logit contributions
 than-0.058
ets-0.044
ear-0.043
ust-0.043
 want-0.043
Token exciting
Token ID7895
Feature activation-9.01e-02

Pos logit contributions
 than+0.070
ear+0.055
 wanna+0.055
 since+0.053
ets+0.053
Neg logit contributions
ail-0.058
illi-0.057
 babys-0.055
 reception-0.054
 lobby-0.053
Token would
Token ID561
Feature activation-3.89e-03

Pos logit contributions
 than+0.175
ust+0.166
 wanna+0.160
 hour+0.153
ear+0.153
Neg logit contributions
ail-0.122
illi-0.118
 lobby-0.113
 reception-0.109
 babys-0.107
Token happen
Token ID1645
Feature activation-3.48e-02

Pos logit contributions
 than+0.008
ust+0.007
ear+0.007
ets+0.007
eting+0.007
Neg logit contributions
 salon-0.005
 reception-0.005
 babys-0.005
 lobby-0.005
 kitchen-0.005
Token on
Token ID319
Feature activation+8.28e-03

Pos logit contributions
 than+0.050
 arrow+0.045
 target+0.043
icated+0.042
affe+0.042
Neg logit contributions
ail-0.066
illi-0.065
 kitchen-0.064
 lobby-0.062
 Stacy-0.062
Token the
Token ID262
Feature activation+1.15e-02

Pos logit contributions
illi+0.014
ail+0.014
 lobby+0.013
 babys+0.013
 reception+0.013
Neg logit contributions
 than-0.017
 want-0.013
ear-0.013
ets-0.013
 hour-0.013
Token board
Token ID3096
Feature activation+2.07e-02

Pos logit contributions
illi+0.016
 lobby+0.016
 kitchen+0.016
ail+0.016
 salon+0.015
Neg logit contributions
 than-0.027
ear-0.021
ust-0.021
 want-0.021
 wanna-0.021
Token life
Token ID1204
Feature activation-3.33e-02

Pos logit contributions
 than+0.110
 want+0.083
ear+0.082
ets+0.082
 hour+0.081
Neg logit contributions
illi-0.090
ail-0.089
 lobby-0.085
 babys-0.085
 reception-0.083
Token until
Token ID1566
Feature activation+1.05e-02

Pos logit contributions
 than+0.054
 want+0.036
ear+0.035
ets+0.035
 hour+0.035
Neg logit contributions
illi-0.073
ail-0.072
 lobby-0.070
 babys-0.070
 reception-0.068
Token one
Token ID530
Feature activation-2.78e-02

Pos logit contributions
ail+0.024
illi+0.023
uka+0.021
 Stacy+0.021
lo+0.021
Neg logit contributions
 than-0.016
 because-0.012
 like-0.012
 hour-0.012
 after-0.012
Token day
Token ID1110
Feature activation+2.57e-02

Pos logit contributions
 than+0.048
ets+0.034
ear+0.034
 want+0.034
 arrow+0.033
Neg logit contributions
illi-0.057
ail-0.056
 babys-0.055
 lobby-0.054
 reception-0.053
Token something
Token ID1223
Feature activation-3.69e-02

Pos logit contributions
ail+0.059
illi+0.058
 lobby+0.056
 babys+0.055
uka+0.055
Neg logit contributions
 than-0.040
 because-0.027
 like-0.026
 want-0.025
ear-0.025
Token exciting
Token ID7895
Feature activation-9.00e-02

Pos logit contributions
 than+0.072
ear+0.053
 want+0.053
 hour+0.052
ets+0.052
Neg logit contributions
illi-0.067
ail-0.066
 lobby-0.064
 babys-0.064
 reception-0.063
Token happened
Token ID3022
Feature activation-1.13e-03

Pos logit contributions
 than+0.185
ust+0.161
 wanna+0.160
ear+0.159
 hour+0.157
Neg logit contributions
ail-0.124
illi-0.121
 lobby-0.120
 reception-0.116
 babys-0.114
Token.
Token ID13
Feature activation-2.91e-02

Pos logit contributions
 than+0.002
 arrow+0.001
 hour+0.001
ust+0.001
affe+0.001
Neg logit contributions
ail-0.002
 kitchen-0.002
illi-0.002
 lobby-0.002
 babys-0.002
Token She
Token ID1375
Feature activation-2.75e-02

Pos logit contributions
 than+0.049
 want+0.037
 because+0.035
ear+0.035
 like+0.035
Neg logit contributions
ail-0.062
illi-0.058
 babys-0.058
 reception-0.056
 lobby-0.056
Token was
Token ID373
Feature activation+5.56e-03

Pos logit contributions
 than+0.050
 want+0.035
ear+0.035
 hour+0.035
ets+0.035
Neg logit contributions
illi-0.054
ail-0.054
 lobby-0.052
 babys-0.052
 reception-0.051
Token playing
Token ID2712
Feature activation-3.22e-03

Pos logit contributions
ail+0.013
illi+0.013
lo+0.012
uffy+0.012
 lobby+0.012
Neg logit contributions
 than-0.008
 like-0.007
 because-0.007
 want-0.006
 as-0.006
Token.
Token ID13
Feature activation-4.29e-02

Pos logit contributions
 than+0.031
 want+0.019
ear+0.018
ets+0.018
 hour+0.018
Neg logit contributions
illi-0.058
ail-0.057
 lobby-0.055
 babys-0.055
 reception-0.054
Token Let
Token ID3914
Feature activation+4.46e-03

Pos logit contributions
 than+0.064
 want+0.045
ear+0.043
 hour+0.042
ets+0.041
Neg logit contributions
illi-0.097
ail-0.096
 lobby-0.093
 babys-0.092
 reception-0.090
Token's
Token ID338
Feature activation-6.08e-03

Pos logit contributions
illi+0.010
ail+0.010
 lobby+0.010
 babys+0.010
uka+0.009
Neg logit contributions
 than-0.007
 want-0.005
ear-0.005
ets-0.004
 hour-0.004
Token do
Token ID466
Feature activation+1.38e-02

Pos logit contributions
 than+0.010
 want+0.007
ear+0.007
ets+0.007
 hour+0.007
Neg logit contributions
illi-0.013
ail-0.013
 lobby-0.013
 babys-0.012
 reception-0.012
Token something
Token ID1223
Feature activation-3.54e-02

Pos logit contributions
illi+0.028
 babys+0.027
ail+0.027
uka+0.026
 lobby+0.026
Neg logit contributions
 than-0.024
ear-0.018
 want-0.018
 arrow-0.017
 because-0.017
Token exciting
Token ID7895
Feature activation-8.97e-02

Pos logit contributions
 than+0.061
 target+0.047
ets+0.046
ear+0.046
 arrow+0.045
Neg logit contributions
illi-0.068
ail-0.065
 lobby-0.064
 reception-0.063
 babys-0.062
Token!"
Token ID2474
Feature activation+1.91e-02

Pos logit contributions
ust+0.117
 than+0.115
 target+0.114
 arrow+0.114
 wanna+0.110
Neg logit contributions
illi-0.170
ail-0.163
 lobby-0.157
lo-0.154
 kitchen-0.153
Token So
Token ID1406
Feature activation-2.68e-03

Pos logit contributions
illi+0.032
ail+0.031
 babys+0.030
 lobby+0.030
 reception+0.029
Neg logit contributions
 than-0.041
 want-0.031
ear-0.031
 hour-0.030
ets-0.030
Token they
Token ID484
Feature activation-2.47e-02

Pos logit contributions
 than+0.005
 want+0.004
ear+0.004
 hour+0.004
ets+0.004
Neg logit contributions
illi-0.005
ail-0.005
 lobby-0.005
 babys-0.005
 reception-0.005
Token decided
Token ID3066
Feature activation-1.73e-02

Pos logit contributions
 than+0.045
ear+0.032
 want+0.031
 hour+0.031
ets+0.031
Neg logit contributions
illi-0.049
ail-0.049
 lobby-0.047
 babys-0.047
 reception-0.046
Token to
Token ID284
Feature activation+2.34e-02

Pos logit contributions
 than+0.025
 hour+0.018
ets+0.018
ear+0.017
 want+0.017
Neg logit contributions
ail-0.038
illi-0.038
 babys-0.037
 lobby-0.037
 reception-0.037
Token but
Token ID475
Feature activation-2.39e-02

Pos logit contributions
 than+0.036
ear+0.026
ust+0.025
ets+0.025
 hour+0.024
Neg logit contributions
 babys-0.056
 kitchen-0.055
ail-0.055
illi-0.055
 Stacy-0.054
Token D
Token ID360
Feature activation+1.88e-03

Pos logit contributions
 than+0.044
 want+0.032
 since+0.030
 because+0.030
ear+0.030
Neg logit contributions
illi-0.048
ail-0.047
 lobby-0.046
 babys-0.045
 reception-0.044
Tokenucky
Token ID5309
Feature activation-2.40e-03

Pos logit contributions
ail+0.003
illi+0.003
uka+0.003
 Stacy+0.003
 babys+0.003
Neg logit contributions
 than-0.004
 hour-0.003
 arrow-0.003
ear-0.003
 target-0.003
Token was
Token ID373
Feature activation+1.47e-02

Pos logit contributions
 than+0.004
 want+0.003
ear+0.003
 hour+0.003
ets+0.003
Neg logit contributions
illi-0.005
ail-0.005
 lobby-0.005
 babys-0.005
 reception-0.004
Token too
Token ID1165
Feature activation-9.44e-03

Pos logit contributions
illi+0.032
ail+0.031
 babys+0.030
 lobby+0.030
 reception+0.030
Neg logit contributions
 than-0.024
 want-0.016
ear-0.016
ets-0.016
 hour-0.016
Token shy
Token ID15800
Feature activation-8.97e-02

Pos logit contributions
 than+0.019
ets+0.015
ear+0.015
 hour+0.014
 want+0.014
Neg logit contributions
illi-0.016
ail-0.016
 babys-0.015
 lobby-0.015
 reception-0.015
Token.
Token ID13
Feature activation-7.62e-03

Pos logit contributions
 than+0.162
 arrow+0.159
 target+0.151
 hour+0.149
 enjoyable+0.144
Neg logit contributions
ail-0.123
 babys-0.110
 salon-0.108
 kitchen-0.107
illi-0.105
Token He
Token ID679
Feature activation-1.54e-02

Pos logit contributions
 than+0.010
 want+0.006
ear+0.006
ets+0.006
 because+0.006
Neg logit contributions
illi-0.019
ail-0.019
 lobby-0.018
 babys-0.018
 reception-0.018
Token decided
Token ID3066
Feature activation-1.95e-02

Pos logit contributions
 than+0.028
ear+0.020
 hour+0.020
ets+0.019
 want+0.019
Neg logit contributions
illi-0.031
ail-0.030
 babys-0.029
 lobby-0.029
 reception-0.028
Token to
Token ID284
Feature activation+2.40e-02

Pos logit contributions
 than+0.031
 hour+0.024
ets+0.024
ust+0.023
ear+0.023
Neg logit contributions
ail-0.040
 babys-0.039
 reception-0.038
 salon-0.038
 kitchen-0.038
Token wash
Token ID13502
Feature activation+7.39e-03

Pos logit contributions
illi+0.048
ail+0.047
 lobby+0.046
 babys+0.046
 reception+0.045
Neg logit contributions
 than-0.042
 want-0.030
ear-0.030
 hour-0.030
ets-0.029
Token One
Token ID1881
Feature activation-2.72e-02

Pos logit contributions
 than+0.033
 want+0.023
ear+0.022
 hour+0.022
ets+0.022
Neg logit contributions
illi-0.050
ail-0.049
 lobby-0.048
 babys-0.047
 reception-0.047
Token day
Token ID1110
Feature activation+2.77e-02

Pos logit contributions
 than+0.059
ets+0.050
 target+0.049
ear+0.047
 wanna+0.046
Neg logit contributions
ail-0.039
 kitchen-0.037
illi-0.037
 babys-0.037
 lobby-0.036
Token,
Token ID11
Feature activation-8.73e-03

Pos logit contributions
illi+0.053
ail+0.052
 babys+0.051
 lobby+0.050
 reception+0.049
Neg logit contributions
 than-0.051
 want-0.038
ear-0.037
ets-0.037
 hour-0.036
Token something
Token ID1223
Feature activation-4.80e-02

Pos logit contributions
 than+0.016
 want+0.012
 like+0.012
 because+0.012
 hour+0.012
Neg logit contributions
illi-0.017
ail-0.017
 lobby-0.016
 reception-0.016
uka-0.015
Token very
Token ID845
Feature activation-2.57e-02

Pos logit contributions
 than+0.097
ear+0.074
 want+0.073
ets+0.071
 since+0.070
Neg logit contributions
illi-0.082
ail-0.082
 babys-0.078
 reception-0.077
 lobby-0.077
Token exciting
Token ID7895
Feature activation-8.93e-02

Pos logit contributions
 than+0.046
ets+0.033
ear+0.033
 want+0.032
 since+0.032
Neg logit contributions
ail-0.050
illi-0.049
 lobby-0.047
 babys-0.047
 reception-0.046
Token happened
Token ID3022
Feature activation-4.40e-03

Pos logit contributions
 than+0.192
ust+0.170
ear+0.164
 wanna+0.161
 hour+0.160
Neg logit contributions
ail-0.118
illi-0.113
 lobby-0.111
 babys-0.109
 reception-0.106
Token.
Token ID13
Feature activation-2.48e-02

Pos logit contributions
 than+0.007
ust+0.006
 hour+0.006
ets+0.006
affe+0.006
Neg logit contributions
 kitchen-0.008
ail-0.008
 babys-0.008
illi-0.007
 lobby-0.007
Token Lily
Token ID20037
Feature activation-4.66e-04

Pos logit contributions
 than+0.038
 want+0.029
 because+0.029
 like+0.028
ear+0.027
Neg logit contributions
ail-0.053
illi-0.053
 lobby-0.050
uka-0.049
 salon-0.049
Token's
Token ID338
Feature activation+2.94e-02

Pos logit contributions
 than+0.001
 hour+0.001
ear+0.001
ets+0.001
ust+0.001
Neg logit contributions
ail-0.001
illi-0.001
 babys-0.001
 lobby-0.001
 kitchen-0.001
Token mom
Token ID1995
Feature activation-1.26e-02

Pos logit contributions
illi+0.050
ail+0.048
 lobby+0.046
 babys+0.046
 reception+0.045
Neg logit contributions
 than-0.062
 want-0.048
ear-0.047
 arrow-0.047
 hour-0.046
Token.
Token ID13
Feature activation-3.54e-03

Pos logit contributions
 than+0.088
ear+0.077
 arrow+0.073
 wanna+0.073
ets+0.071
Neg logit contributions
ail-0.110
 kitchen-0.109
 lobby-0.107
 cabinet-0.105
 babys-0.105
Token But
Token ID887
Feature activation-5.96e-03

Pos logit contributions
 than+0.007
ets+0.005
 hour+0.005
ear+0.005
 want+0.005
Neg logit contributions
ail-0.006
illi-0.006
 lobby-0.006
 babys-0.006
 kitchen-0.006
Token then
Token ID788
Feature activation+8.27e-03

Pos logit contributions
 than+0.011
ets+0.010
ear+0.009
ust+0.009
 wanna+0.009
Neg logit contributions
ail-0.010
 kitchen-0.009
illi-0.009
 lobby-0.009
 reception-0.009
Token,
Token ID11
Feature activation-4.85e-03

Pos logit contributions
illi+0.016
ail+0.016
 lobby+0.016
 babys+0.016
 reception+0.015
Neg logit contributions
 than-0.015
 want-0.010
ets-0.010
ear-0.010
 hour-0.010
Token something
Token ID1223
Feature activation-3.63e-02

Pos logit contributions
 than+0.009
ets+0.007
 hour+0.007
ear+0.007
ust+0.007
Neg logit contributions
illi-0.009
ail-0.009
 lobby-0.008
 babys-0.008
 reception-0.008
Token amazing
Token ID4998
Feature activation-8.89e-02

Pos logit contributions
 than+0.076
ear+0.061
 want+0.057
icated+0.057
ets+0.057
Neg logit contributions
ail-0.058
illi-0.056
 babys-0.053
 lobby-0.053
 reception-0.053
Token happened
Token ID3022
Feature activation-4.49e-03

Pos logit contributions
 than+0.202
 hour+0.171
ear+0.170
ust+0.168
 wanna+0.166
Neg logit contributions
ail-0.114
illi-0.103
 babys-0.100
 reception-0.096
 lobby-0.094
Token.
Token ID13
Feature activation-1.65e-02

Pos logit contributions
 than+0.006
 hour+0.005
ets+0.005
ust+0.005
icated+0.005
Neg logit contributions
ail-0.009
 kitchen-0.009
illi-0.009
 babys-0.009
 lobby-0.009
Token The
Token ID383
Feature activation+1.57e-02

Pos logit contributions
 than+0.032
ets+0.023
 want+0.023
 hour+0.023
ear+0.023
Neg logit contributions
illi-0.030
ail-0.030
 lobby-0.029
 babys-0.029
 kitchen-0.028
Token sprayed
Token ID35729
Feature activation-6.58e-03

Pos logit contributions
illi+0.027
ail+0.027
 babys+0.026
 lobby+0.026
 reception+0.025
Neg logit contributions
 than-0.032
 want-0.024
ear-0.024
ets-0.024
 hour-0.024
Token gum
Token ID27142
Feature activation+3.87e-02

Pos logit contributions
 than+0.013
ust+0.010
ear+0.010
 want+0.010
 hour+0.009
Neg logit contributions
ail-0.011
illi-0.011
 lobby-0.011
 kitchen-0.011
 babys-0.011
Token,
Token ID11
Feature activation-1.90e-02

Pos logit contributions
 than+0.014
ear+0.011
ets+0.010
 hour+0.010
 wanna+0.010
Neg logit contributions
illi-0.016
ail-0.016
 babys-0.015
 salon-0.015
 kitchen-0.015
Token but
Token ID475
Feature activation-2.10e-02

Pos logit contributions
 than+0.027
ear+0.019
ust+0.018
ets+0.018
 hour+0.017
Neg logit contributions
illi-0.042
 babys-0.042
 kitchen-0.042
 lobby-0.041
 salon-0.041
Token he
Token ID339
Feature activation-2.93e-02

Pos logit contributions
 than+0.023
 because+0.016
 arrow+0.015
 as+0.015
 since+0.014
Neg logit contributions
ail-0.057
illi-0.057
 lobby-0.054
acey-0.054
 Stacy-0.053
Token was
Token ID373
Feature activation+1.42e-02

Pos logit contributions
 than+0.046
 arrow+0.033
 because+0.033
 want+0.033
 since+0.032
Neg logit contributions
 lobby-0.063
illi-0.063
 reception-0.061
 babys-0.060
ail-0.060
Token too
Token ID1165
Feature activation-1.26e-02

Pos logit contributions
illi+0.031
ail+0.030
 babys+0.029
 lobby+0.029
 reception+0.028
Neg logit contributions
 than-0.023
 want-0.016
ear-0.016
ets-0.016
 hour-0.016
Token shy
Token ID15800
Feature activation-8.89e-02

Pos logit contributions
 than+0.025
ets+0.020
ear+0.019
 hour+0.019
 want+0.019
Neg logit contributions
illi-0.022
ail-0.021
 babys-0.021
 lobby-0.020
uka-0.020
Token to
Token ID284
Feature activation+3.26e-02

Pos logit contributions
 than+0.153
 arrow+0.152
 hour+0.148
 target+0.147
 enjoyable+0.144
Neg logit contributions
ail-0.119
 kitchen-0.113
 salon-0.111
 cabinet-0.110
 office-0.110
Token ask
Token ID1265
Feature activation+3.89e-02

Pos logit contributions
illi+0.066
ail+0.065
 babys+0.063
 lobby+0.063
 reception+0.062
Neg logit contributions
 than-0.057
ear-0.040
 want-0.040
 hour-0.040
ets-0.039
Token.
Token ID13
Feature activation-1.49e-02

Pos logit contributions
illi+0.102
ail+0.100
 lobby+0.099
 salon+0.096
 babys+0.095
Neg logit contributions
 than-0.050
 because-0.032
 like-0.030
 since-0.029
 hour-0.029
Token Suddenly
Token ID24975
Feature activation-9.11e-04

Pos logit contributions
 than+0.022
 because+0.018
 since+0.016
 as+0.015
 So+0.015
Neg logit contributions
illi-0.033
 lobby-0.032
ail-0.032
acey-0.031
ili-0.031
Token,
Token ID11
Feature activation+2.62e-03

Pos logit contributions
 than+0.001
 because+0.001
 arrow+0.001
 as+0.001
 like+0.001
Neg logit contributions
illi-0.002
ail-0.002
 lobby-0.002
uka-0.002
 salon-0.002
Token filthy
Token ID35677
Feature activation-4.14e-02

Pos logit contributions
illi+0.018
ail+0.017
 lobby+0.017
 babys+0.016
 reception+0.016
Neg logit contributions
 than-0.016
 want-0.011
ear-0.011
 like-0.011
 hour-0.011
Token.
Token ID13
Feature activation-1.92e-02

Pos logit contributions
 than+0.055
ear+0.042
 hour+0.042
 want+0.041
 wanna+0.041
Neg logit contributions
illi-0.089
ail-0.089
 lobby-0.088
 kitchen-0.087
 babys-0.085
Token But
Token ID887
Feature activation-1.18e-02

Pos logit contributions
 than+0.040
 want+0.030
ear+0.030
 hour+0.029
ets+0.029
Neg logit contributions
illi-0.033
ail-0.032
 lobby-0.031
 babys-0.031
 reception-0.030
Token then
Token ID788
Feature activation+5.64e-03

Pos logit contributions
 than+0.022
 want+0.016
 since+0.016
ear+0.015
 because+0.015
Neg logit contributions
illi-0.023
ail-0.023
 lobby-0.022
 babys-0.022
 reception-0.021
Token something
Token ID1223
Feature activation-3.81e-02

Pos logit contributions
illi+0.011
ail+0.011
 babys+0.011
 lobby+0.011
uka+0.010
Neg logit contributions
 than-0.010
 since-0.008
 want-0.007
 because-0.007
 like-0.007
Token amazing
Token ID4998
Feature activation-8.88e-02

Pos logit contributions
 than+0.076
ear+0.059
 want+0.057
ets+0.056
 hour+0.055
Neg logit contributions
illi-0.066
ail-0.066
 babys-0.063
 lobby-0.063
 reception-0.062
Token happened
Token ID3022
Feature activation-4.40e-03

Pos logit contributions
 than+0.187
 hour+0.155
ear+0.152
ust+0.151
 want+0.149
Neg logit contributions
ail-0.131
illi-0.124
 reception-0.116
 babys-0.115
 lobby-0.114
Token.
Token ID13
Feature activation-2.31e-02

Pos logit contributions
 than+0.006
 hour+0.004
ets+0.004
ust+0.004
ear+0.004
Neg logit contributions
ail-0.010
illi-0.010
 lobby-0.009
 kitchen-0.009
 babys-0.009
Token Suddenly
Token ID24975
Feature activation-1.05e-03

Pos logit contributions
 than+0.044
 want+0.033
ear+0.033
 hour+0.032
ets+0.032
Neg logit contributions
illi-0.043
ail-0.042
 lobby-0.040
 babys-0.040
 reception-0.039
Token the
Token ID262
Feature activation+2.47e-02

Pos logit contributions
 than+0.002
 since+0.001
 like+0.001
 because+0.001
 want+0.001
Neg logit contributions
illi-0.002
ail-0.002
uka-0.002
 lobby-0.002
 salon-0.002
Token comb
Token ID1974
Feature activation+1.43e-02

Pos logit contributions
illi+0.042
 lobby+0.042
ail+0.041
 reception+0.038
uka+0.038
Neg logit contributions
 than-0.052
 arrow-0.043
 want-0.040
 like-0.039
 hour-0.039
Token,
Token ID11
Feature activation-1.79e-02

Pos logit contributions
illi+0.006
ail+0.006
 lobby+0.006
 babys+0.006
 reception+0.006
Neg logit contributions
 than-0.004
ear-0.003
 want-0.003
 hour-0.003
ets-0.003
Token but
Token ID475
Feature activation-2.27e-02

Pos logit contributions
 than+0.021
ear+0.013
ets+0.013
 hour+0.012
ust+0.012
Neg logit contributions
illi-0.045
 babys-0.044
 lobby-0.044
ail-0.044
 reception-0.043
Token she
Token ID673
Feature activation-2.98e-02

Pos logit contributions
 than+0.036
 because+0.030
 since+0.028
 as+0.028
 like+0.027
Neg logit contributions
illi-0.049
ail-0.049
 lobby-0.047
 babys-0.047
uka-0.045
Token was
Token ID373
Feature activation+1.61e-02

Pos logit contributions
 than+0.042
 because+0.031
 want+0.030
 since+0.029
ust+0.029
Neg logit contributions
 lobby-0.068
illi-0.067
 babys-0.065
 reception-0.065
 kitchen-0.063
Token too
Token ID1165
Feature activation-1.35e-02

Pos logit contributions
ail+0.034
illi+0.034
 lobby+0.033
 babys+0.032
 reception+0.032
Neg logit contributions
 than-0.027
 want-0.020
 because-0.019
 like-0.019
 hour-0.018
Token shy
Token ID15800
Feature activation-8.86e-02

Pos logit contributions
 than+0.026
 want+0.020
ear+0.019
 hour+0.019
 because+0.018
Neg logit contributions
illi-0.025
ail-0.025
 lobby-0.024
 babys-0.024
 reception-0.023
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
 than+0.142
 arrow+0.138
 hour+0.134
 target+0.131
 enjoyable+0.123
Neg logit contributions
ail-0.141
 salon-0.135
illi-0.134
 kitchen-0.133
 babys-0.130
Token
Token ID198
Feature activation-1.29e-02

Pos logit contributions
 than+0.021
 because+0.016
ear+0.015
 want+0.015
 since+0.015
Neg logit contributions
 lobby-0.034
illi-0.034
ail-0.033
 babys-0.033
 reception-0.033
Token
Token ID198
Feature activation-1.69e-02

Pos logit contributions
 than+0.017
ear+0.011
 want+0.011
 because+0.011
 like+0.010
Neg logit contributions
 lobby-0.031
 babys-0.030
 salon-0.030
 reception-0.030
illi-0.030
Token"
Token ID1
Feature activation-2.00e-02

Pos logit contributions
 than+0.026
 want+0.018
ear+0.018
 hour+0.017
ets+0.017
Neg logit contributions
illi-0.038
ail-0.037
 lobby-0.037
 babys-0.036
 reception-0.036
TokenOh
Token ID5812
Feature activation-1.95e-02

Pos logit contributions
 than+0.036
 want+0.026
ear+0.026
 hour+0.026
ust+0.025
Neg logit contributions
ail-0.040
illi-0.040
 lobby-0.038
 babys-0.038
 reception-0.037
Token but
Token ID475
Feature activation-2.14e-02

Pos logit contributions
 than+0.038
ear+0.030
ust+0.029
ets+0.029
 hour+0.027
Neg logit contributions
 kitchen-0.054
 babys-0.052
 lobby-0.051
 reception-0.051
ail-0.050
Token Nem
Token ID22547
Feature activation-1.83e-03

Pos logit contributions
 than+0.037
 want+0.026
ear+0.026
ets+0.026
 hour+0.025
Neg logit contributions
illi-0.044
ail-0.043
 lobby-0.042
 babys-0.042
 reception-0.041
Tokeno
Token ID78
Feature activation-7.15e-03

Pos logit contributions
 than+0.004
 hour+0.003
ear+0.003
 want+0.003
ets+0.003
Neg logit contributions
ail-0.003
illi-0.003
 babys-0.003
uka-0.003
 Stacy-0.003
Token was
Token ID373
Feature activation+1.52e-02

Pos logit contributions
 than+0.014
ear+0.010
 hour+0.010
ets+0.010
 want+0.010
Neg logit contributions
ail-0.013
illi-0.013
 babys-0.012
 lobby-0.012
 reception-0.012
Token too
Token ID1165
Feature activation-1.15e-02

Pos logit contributions
illi+0.029
ail+0.028
 babys+0.028
 lobby+0.027
 reception+0.027
Neg logit contributions
 than-0.027
ets-0.021
ear-0.020
 hour-0.020
 want-0.020
Token curious
Token ID11040
Feature activation-8.85e-02

Pos logit contributions
 than+0.022
ets+0.020
 hour+0.018
ear+0.018
 since+0.017
Neg logit contributions
illi-0.018
ail-0.018
 babys-0.017
uka-0.017
 reception-0.017
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
 than+0.144
 wanna+0.139
ust+0.138
ear+0.132
ever+0.132
Neg logit contributions
ail-0.124
 kitchen-0.123
 office-0.118
 cabinet-0.116
 babys-0.114
Token He
Token ID679
Feature activation-2.02e-02

Pos logit contributions
 than+0.021
 hour+0.014
 want+0.014
ets+0.014
ear+0.014
Neg logit contributions
ail-0.033
illi-0.033
 lobby-0.032
 babys-0.032
 reception-0.031
Token sw
Token ID1509
Feature activation-2.11e-02

Pos logit contributions
 than+0.041
ear+0.030
ets+0.030
 hour+0.030
 want+0.029
Neg logit contributions
ail-0.036
illi-0.036
 babys-0.034
 reception-0.034
 Stacy-0.033
Tokenam
Token ID321
Feature activation-1.40e-02

Pos logit contributions
 than+0.046
 hour+0.038
 since+0.037
 want+0.036
icated+0.035
Neg logit contributions
ail-0.035
illi-0.031
 lobby-0.029
uffy-0.028
uka-0.028
Token closer
Token ID5699
Feature activation-3.10e-02

Pos logit contributions
 than+0.026
ear+0.020
 hour+0.020
 want+0.020
ets+0.019
Neg logit contributions
ail-0.026
illi-0.025
 lobby-0.024
 babys-0.024
 reception-0.024
Token then
Token ID788
Feature activation-1.33e-03

Pos logit contributions
 than+0.033
 because+0.022
 hour+0.022
 want+0.022
 arrow+0.022
Neg logit contributions
illi-0.053
ail-0.052
 lobby-0.050
 babys-0.049
 reception-0.049
Token one
Token ID530
Feature activation-3.10e-02

Pos logit contributions
 than+0.002
 because+0.001
 arrow+0.001
 like+0.001
 want+0.001
Neg logit contributions
illi-0.003
ail-0.003
 lobby-0.003
 babys-0.003
 salon-0.003
Token day
Token ID1110
Feature activation+1.76e-02

Pos logit contributions
 than+0.051
 want+0.035
ear+0.035
ets+0.034
 hour+0.034
Neg logit contributions
illi-0.067
ail-0.066
 lobby-0.064
 babys-0.064
 reception-0.062
Token,
Token ID11
Feature activation-1.25e-02

Pos logit contributions
illi+0.036
ail+0.036
 lobby+0.034
 babys+0.034
 salon+0.034
Neg logit contributions
 than-0.031
 want-0.022
ear-0.021
 arrow-0.021
 because-0.021
Token something
Token ID1223
Feature activation-3.88e-02

Pos logit contributions
 than+0.020
 because+0.015
 arrow+0.014
 like+0.014
 want+0.014
Neg logit contributions
ail-0.028
illi-0.028
 lobby-0.026
 babys-0.026
 salon-0.026
Token amazing
Token ID4998
Feature activation-8.84e-02

Pos logit contributions
 than+0.084
ear+0.065
 want+0.063
 since+0.062
ets+0.062
Neg logit contributions
ail-0.061
illi-0.061
 babys-0.058
 reception-0.057
 lobby-0.057
Token happened
Token ID3022
Feature activation-4.50e-03

Pos logit contributions
 than+0.204
 hour+0.172
ust+0.171
 wanna+0.171
ear+0.171
Neg logit contributions
ail-0.104
illi-0.096
 babys-0.090
 reception-0.089
 lobby-0.088
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
 than+0.007
 hour+0.006
ust+0.006
ets+0.005
 arrow+0.005
Neg logit contributions
ail-0.009
 kitchen-0.009
illi-0.008
 lobby-0.008
 babys-0.008
Token A
Token ID317
Feature activation-2.56e-02

Pos logit contributions
 than+0.044
 want+0.032
ets+0.032
ear+0.032
ust+0.032
Neg logit contributions
illi-0.040
 lobby-0.038
ail-0.038
 babys-0.038
 reception-0.037
Token man
Token ID582
Feature activation-1.22e-02

Pos logit contributions
 than+0.036
 arrow+0.028
 hour+0.027
 want+0.026
 target+0.026
Neg logit contributions
illi-0.057
ail-0.055
ili-0.052
uka-0.052
loe-0.052
Token came
Token ID1625
Feature activation+1.75e-02

Pos logit contributions
 than+0.026
ear+0.020
 want+0.019
 hour+0.019
ets+0.019
Neg logit contributions
illi-0.020
ail-0.020
 lobby-0.019
 babys-0.019
 reception-0.019
Token Lily
Token ID20037
Feature activation-2.48e-03

Pos logit contributions
 than+0.009
 because+0.008
 like+0.008
 want+0.007
 as+0.007
Neg logit contributions
ail-0.010
illi-0.010
 lobby-0.009
 reception-0.009
uka-0.009
Token's
Token ID338
Feature activation+3.02e-02

Pos logit contributions
 than+0.005
 hour+0.004
ear+0.003
ets+0.003
ust+0.003
Neg logit contributions
ail-0.005
illi-0.005
 babys-0.004
 lobby-0.004
 kitchen-0.004
Token brother
Token ID3956
Feature activation-5.52e-03

Pos logit contributions
illi+0.043
ail+0.041
 lobby+0.040
 babys+0.039
 reception+0.038
Neg logit contributions
 than-0.072
 want-0.057
ear-0.056
 hour-0.056
 arrow-0.055
Token did
Token ID750
Feature activation+9.38e-03

Pos logit contributions
 than+0.010
 want+0.007
 because+0.007
 arrow+0.007
 since+0.007
Neg logit contributions
illi-0.011
ail-0.011
 lobby-0.011
 reception-0.010
 salon-0.010
Token something
Token ID1223
Feature activation-3.44e-02

Pos logit contributions
illi+0.017
ail+0.017
 lobby+0.016
 babys+0.016
 reception+0.016
Neg logit contributions
 than-0.019
 want-0.014
ear-0.014
 like-0.013
 because-0.013
Token amazing
Token ID4998
Feature activation-8.84e-02

Pos logit contributions
 than+0.074
ear+0.058
ets+0.057
 hour+0.057
 since+0.056
Neg logit contributions
illi-0.054
ail-0.051
 babys-0.051
 salon-0.048
 lobby-0.048
Token!
Token ID0
Feature activation-3.09e-02

Pos logit contributions
 than+0.131
 target+0.113
 wanna+0.110
ust+0.108
 hour+0.108
Neg logit contributions
ail-0.168
illi-0.166
 babys-0.154
uka-0.153
 salon-0.150
Token He
Token ID679
Feature activation-2.00e-02

Pos logit contributions
 than+0.048
ear+0.031
ust+0.031
ets+0.031
 arrow+0.030
Neg logit contributions
illi-0.068
 babys-0.067
ail-0.067
 lobby-0.066
 kitchen-0.065
Token danced
Token ID39480
Feature activation-3.53e-02

Pos logit contributions
 than+0.040
 hour+0.031
ear+0.030
ets+0.030
ust+0.029
Neg logit contributions
ail-0.035
illi-0.035
 babys-0.034
 Stacy-0.032
acey-0.032
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
 than+0.057
ust+0.041
ear+0.040
 hour+0.040
 want+0.040
Neg logit contributions
illi-0.073
ail-0.071
 babys-0.069
 reception-0.069
 lobby-0.068
Token sang
Token ID25889
Feature activation-1.80e-02

Pos logit contributions
 than+0.025
 want+0.018
ear+0.017
ets+0.017
 hour+0.017
Neg logit contributions
illi-0.029
ail-0.029
 lobby-0.028
 babys-0.028
 reception-0.027
Token close
Token ID1969
Feature activation-2.98e-02

Pos logit contributions
 than+0.028
 want+0.020
ear+0.020
ets+0.020
 hour+0.020
Neg logit contributions
illi-0.030
ail-0.029
 lobby-0.028
 babys-0.028
 reception-0.027
Token to
Token ID284
Feature activation+5.51e-02

Pos logit contributions
 than+0.043
 hour+0.034
 arrow+0.033
icated+0.032
 want+0.032
Neg logit contributions
ail-0.063
illi-0.060
 lobby-0.060
 reception-0.059
 babys-0.059
Token nature
Token ID3450
Feature activation-1.11e-02

Pos logit contributions
illi+0.107
ail+0.105
 babys+0.101
 lobby+0.100
 salon+0.098
Neg logit contributions
 than-0.106
 want-0.078
ear-0.076
 hour-0.075
ets-0.074
Token.
Token ID13
Feature activation-1.57e-02

Pos logit contributions
 than+0.014
 want+0.009
ear+0.009
 hour+0.008
ets+0.008
Neg logit contributions
illi-0.027
ail-0.027
 lobby-0.026
 babys-0.026
 reception-0.026
Token<|endoftext|>
Token ID50256
Feature activation+3.44e-02

Pos logit contributions
 than+0.029
 want+0.022
ear+0.021
ets+0.021
 hour+0.021
Neg logit contributions
illi-0.030
ail-0.030
 lobby-0.029
 babys-0.028
 reception-0.028
TokenOnce
Token ID7454
Feature activation+7.48e-02

Pos logit contributions
 salon+0.065
 babys+0.063
ail+0.063
 reception+0.062
illi+0.060
Neg logit contributions
 than-0.064
 like-0.049
 because-0.048
 want-0.047
 and-0.047
Token upon
Token ID2402
Feature activation-2.45e-02

Pos logit contributions
illi+0.139
 lobby+0.135
 reception+0.134
 babys+0.132
 Stacy+0.129
Neg logit contributions
 than-0.140
 want-0.107
 because-0.104
 hour-0.103
 since-0.101
Token a
Token ID257
Feature activation-1.22e-02

Pos logit contributions
 than+0.051
ets+0.039
ear+0.039
 hour+0.038
 want+0.038
Neg logit contributions
illi-0.041
ail-0.038
 lobby-0.038
 babys-0.037
 kitchen-0.037
Token time
Token ID640
Feature activation+2.55e-02

Pos logit contributions
 than+0.024
 arrow+0.021
 target+0.020
ear+0.020
icated+0.020
Neg logit contributions
illi-0.019
ail-0.019
uffy-0.018
 kitchen-0.018
 lobby-0.017
Token there
Token ID612
Feature activation+3.62e-02

Pos logit contributions
illi+0.055
ail+0.053
 lobby+0.052
 babys+0.052
 reception+0.051
Neg logit contributions
 than-0.043
 want-0.030
 because-0.029
 hour-0.028
ear-0.028
Token were
Token ID547
Feature activation+8.22e-03

Pos logit contributions
 reception+0.085
 salon+0.084
 babys+0.084
ail+0.083
illi+0.083
Neg logit contributions
 than-0.050
 because-0.038
 like-0.037
 want-0.036
 wanted-0.034
Token."
Token ID526
Feature activation+2.54e-02

Pos logit contributions
 than+0.096
ust+0.087
 wanna+0.085
ets+0.085
 arrow+0.084
Neg logit contributions
 kitchen-0.125
illi-0.119
ail-0.118
 salon-0.116
 lobby-0.116
Token
Token ID198
Feature activation+6.97e-03

Pos logit contributions
illi+0.040
ail+0.039
 babys+0.039
 lobby+0.038
 kitchen+0.037
Neg logit contributions
 than-0.055
ets-0.044
ear-0.043
 arrow-0.043
ust-0.043
Token
Token ID198
Feature activation-3.14e-05

Pos logit contributions
illi+0.014
ail+0.014
 lobby+0.014
 babys+0.013
 reception+0.013
Neg logit contributions
 than-0.012
 want-0.009
ear-0.009
 hour-0.008
 arrow-0.008
TokenThey
Token ID2990
Feature activation-2.12e-03

Pos logit contributions
 than+0.000
 wanna+0.000
ets+0.000
eting+0.000
 want+0.000
Neg logit contributions
illi-0.000
ail-0.000
 kitchen-0.000
 salon-0.000
 lobby-0.000
Token walked
Token ID6807
Feature activation+9.12e-03

Pos logit contributions
 than+0.004
 want+0.003
ear+0.002
ets+0.002
 arrow+0.002
Neg logit contributions
illi-0.004
ail-0.004
 lobby-0.004
 babys-0.004
 reception-0.004
Token to
Token ID284
Feature activation+5.73e-02

Pos logit contributions
illi+0.021
ail+0.021
 babys+0.021
 lobby+0.020
uka+0.020
Neg logit contributions
 than-0.014
 want-0.009
 like-0.009
ear-0.009
ets-0.009
Token the
Token ID262
Feature activation+2.73e-02

Pos logit contributions
ail+0.120
illi+0.114
 lobby+0.109
 salon+0.107
 reception+0.107
Neg logit contributions
 than-0.092
 want-0.077
 like-0.076
 because-0.074
 each-0.072
Token house
Token ID2156
Feature activation+4.36e-02

Pos logit contributions
loe+0.044
ail+0.043
ili+0.043
illi+0.042
 Stacy+0.042
Neg logit contributions
 than-0.053
 arrow-0.046
 target-0.044
 hour-0.042
 like-0.041
Token with
Token ID351
Feature activation+1.08e-02

Pos logit contributions
illi+0.120
ail+0.118
 babys+0.115
 lobby+0.114
uka+0.113
Neg logit contributions
 than-0.046
 want-0.024
ear-0.023
 hour-0.022
ets-0.022
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
ail+0.024
illi+0.024
 salon+0.023
ili+0.023
uka+0.022
Neg logit contributions
 than-0.015
 like-0.012
 each-0.012
 because-0.011
 as-0.011
Token v
Token ID410
Feature activation+4.53e-02

Pos logit contributions
illi+0.045
ail+0.044
loe+0.044
 Stacy+0.043
aby+0.042
Neg logit contributions
 than-0.047
 arrow-0.040
 like-0.039
 want-0.038
 hour-0.035
Token met
Token ID1138
Feature activation+1.85e-02

Pos logit contributions
 than+0.028
 want+0.020
ear+0.020
 hour+0.020
ets+0.020
Neg logit contributions
illi-0.030
ail-0.029
 lobby-0.028
 babys-0.028
 reception-0.027
Token a
Token ID257
Feature activation-2.63e-02

Pos logit contributions
illi+0.041
ail+0.040
 salon+0.039
 lobby+0.039
 babys+0.039
Neg logit contributions
 than-0.030
 like-0.022
 arrow-0.021
 want-0.021
ear-0.021
Token toy
Token ID13373
Feature activation-1.09e-02

Pos logit contributions
 than+0.044
 arrow+0.033
 want+0.033
 target+0.033
 like+0.031
Neg logit contributions
illi-0.056
ail-0.054
uka-0.051
ili-0.050
loe-0.050
Token boat
Token ID8848
Feature activation-1.37e-02

Pos logit contributions
 than+0.023
ear+0.018
ust+0.018
ets+0.018
 want+0.018
Neg logit contributions
illi-0.017
ail-0.017
 babys-0.017
 lobby-0.017
 reception-0.016
Token and
Token ID290
Feature activation-2.97e-02

Pos logit contributions
 than+0.021
ear+0.016
ust+0.016
 hour+0.016
 wanna+0.015
Neg logit contributions
ail-0.028
 lobby-0.028
 babys-0.027
illi-0.027
 reception-0.027
Token said
Token ID531
Feature activation+5.57e-02

Pos logit contributions
 than+0.054
ear+0.038
 hour+0.038
ust+0.038
ets+0.038
Neg logit contributions
illi-0.058
ail-0.057
 lobby-0.056
 babys-0.056
 reception-0.055
Token hello
Token ID23748
Feature activation-3.15e-02

Pos logit contributions
illi+0.120
ail+0.116
 lobby+0.114
 babys+0.113
 salon+0.110
Neg logit contributions
 than-0.093
 want-0.067
ear-0.065
 like-0.064
 arrow-0.063
Token.
Token ID13
Feature activation+2.55e-04

Pos logit contributions
 than+0.045
 hour+0.035
ets+0.034
 wanna+0.031
 want+0.031
Neg logit contributions
ail-0.069
illi-0.068
 babys-0.067
 reception-0.066
 lobby-0.066
Token Suddenly
Token ID24975
Feature activation+6.82e-03

Pos logit contributions
illi+0.001
ail+0.001
 lobby+0.001
 babys+0.001
 reception+0.000
Neg logit contributions
 than-0.000
 want-0.000
ear-0.000
 hour-0.000
ets-0.000
Token,
Token ID11
Feature activation+7.27e-03

Pos logit contributions
illi+0.016
ail+0.015
 lobby+0.015
 salon+0.015
 babys+0.015
Neg logit contributions
 than-0.010
 arrow-0.007
 want-0.007
 like-0.007
 because-0.007
Token he
Token ID339
Feature activation-1.46e-02

Pos logit contributions
ail+0.017
illi+0.017
 salon+0.016
 babys+0.016
 lobby+0.016
Neg logit contributions
 than-0.010
 arrow-0.008
 like-0.007
 because-0.007
 as-0.007
Token
Token ID198
Feature activation+7.50e-03

Pos logit contributions
illi+0.057
ail+0.056
 lobby+0.054
 babys+0.054
 reception+0.052
Neg logit contributions
 than-0.060
 want-0.044
ear-0.044
ets-0.043
 hour-0.043
Token
Token ID198
Feature activation+9.04e-04

Pos logit contributions
illi+0.017
 lobby+0.017
ail+0.016
 salon+0.016
 reception+0.016
Neg logit contributions
 than-0.011
ear-0.008
 arrow-0.008
 want-0.007
 hour-0.007
TokenSpot
Token ID32565
Feature activation+1.53e-02

Pos logit contributions
illi+0.002
ail+0.002
 babys+0.002
 lobby+0.002
 reception+0.002
Neg logit contributions
 than-0.002
 want-0.001
ets-0.001
ear-0.001
 hour-0.001
Token w
Token ID266
Feature activation-2.94e-03

Pos logit contributions
illi+0.029
ail+0.029
 lobby+0.028
 babys+0.028
 reception+0.027
Neg logit contributions
 than-0.028
 want-0.021
ear-0.020
ets-0.020
 hour-0.020
Tokenagged
Token ID14655
Feature activation-1.71e-02

Pos logit contributions
 than+0.006
 want+0.005
ear+0.005
 hour+0.005
ets+0.005
Neg logit contributions
illi-0.005
ail-0.005
 lobby-0.005
 babys-0.005
 reception-0.004
Token his
Token ID465
Feature activation+7.16e-02

Pos logit contributions
 than+0.027
 want+0.017
 arrow+0.017
 because+0.017
ear+0.017
Neg logit contributions
illi-0.040
ail-0.039
 lobby-0.037
 babys-0.037
uka-0.037
Token tail
Token ID7894
Feature activation+1.64e-02

Pos logit contributions
ail+0.157
illi+0.154
 babys+0.152
 lobby+0.150
 kitchen+0.148
Neg logit contributions
 than-0.109
ear-0.079
 want-0.077
 since-0.075
ets-0.075
Token.
Token ID13
Feature activation-3.28e-03

Pos logit contributions
ail+0.038
illi+0.038
 babys+0.037
 lobby+0.036
 kitchen+0.036
Neg logit contributions
 than-0.022
 hour-0.014
ear-0.014
 wanna-0.014
ust-0.014
Token He
Token ID679
Feature activation+1.49e-03

Pos logit contributions
 than+0.004
 want+0.003
ear+0.003
ets+0.003
 hour+0.002
Neg logit contributions
illi-0.008
ail-0.008
 babys-0.008
 lobby-0.008
 reception-0.008
Token l
Token ID300
Feature activation+4.89e-03

Pos logit contributions
illi+0.003
ail+0.003
 babys+0.003
 lobby+0.003
 reception+0.002
Neg logit contributions
 than-0.003
ear-0.002
 hour-0.002
 want-0.002
ets-0.002
Tokenicked
Token ID9484
Feature activation+3.00e-02

Pos logit contributions
ail+0.008
illi+0.008
 babys+0.008
 lobby+0.008
 reception+0.008
Neg logit contributions
 than-0.010
ear-0.008
ets-0.008
 want-0.008
 arrow-0.007
Token,
Token ID11
Feature activation-2.38e-02

Pos logit contributions
 than+0.025
 want+0.017
ear+0.017
ets+0.016
 hour+0.016
Neg logit contributions
illi-0.031
ail-0.030
 lobby-0.029
 babys-0.029
 reception-0.029
Token Mo
Token ID4270
Feature activation-9.28e-03

Pos logit contributions
 than+0.057
 want+0.045
ear+0.044
 arrow+0.044
 because+0.044
Neg logit contributions
illi-0.033
ail-0.033
 lobby-0.032
 babys-0.031
 salon-0.030
Tokenira
Token ID8704
Feature activation-1.02e-02

Pos logit contributions
 than+0.018
 want+0.013
ear+0.013
 since+0.013
 because+0.013
Neg logit contributions
illi-0.017
 lobby-0.017
 babys-0.017
 salon-0.016
ail-0.016
Token?"
Token ID1701
Feature activation+3.97e-02

Pos logit contributions
 than+0.017
 want+0.012
ear+0.012
ets+0.012
 hour+0.011
Neg logit contributions
illi-0.022
ail-0.021
 lobby-0.021
 babys-0.021
 reception-0.020
Token she
Token ID673
Feature activation+1.14e-03

Pos logit contributions
illi+0.075
 lobby+0.075
 salon+0.073
ail+0.072
acey+0.068
Neg logit contributions
 than-0.074
 because-0.058
 arrow-0.058
 want-0.057
 like-0.053
Token asked
Token ID1965
Feature activation+5.99e-02

Pos logit contributions
 lobby+0.003
illi+0.003
ail+0.003
 salon+0.003
lo+0.003
Neg logit contributions
 than-0.001
 arrow-0.001
 because-0.001
 want-0.001
 since-0.001
Token.
Token ID13
Feature activation+1.91e-03

Pos logit contributions
 lobby+0.176
 salon+0.171
illi+0.171
 babys+0.161
uka+0.161
Neg logit contributions
 than-0.061
 because-0.034
 as-0.034
 like-0.031
 and-0.029
Token
Token ID198
Feature activation-1.50e-03

Pos logit contributions
 salon+0.004
 lobby+0.004
illi+0.004
ail+0.003
acey+0.003
Neg logit contributions
 than-0.003
 because-0.003
 want-0.003
 arrow-0.003
 as-0.003
Token
Token ID198
Feature activation-5.78e-03

Pos logit contributions
 than+0.002
ear+0.001
 arrow+0.001
 want+0.001
 wanna+0.001
Neg logit contributions
 salon-0.004
 lobby-0.004
illi-0.003
 babys-0.003
 register-0.003
TokenMo
Token ID16632
Feature activation+1.22e-02

Pos logit contributions
 than+0.009
 arrow+0.007
ear+0.006
 want+0.006
 wanna+0.006
Neg logit contributions
 lobby-0.012
illi-0.012
 salon-0.012
ail-0.012
 babys-0.012
Tokenira
Token ID8704
Feature activation+4.98e-04

Pos logit contributions
 lobby+0.020
 babys+0.020
illi+0.020
 salon+0.019
 kitchen+0.019
Neg logit contributions
 than-0.025
 want-0.019
ear-0.019
 arrow-0.019
 since-0.019
Token,
Token ID11
Feature activation-2.52e-02

Pos logit contributions
 than+0.105
ear+0.084
ust+0.082
 want+0.082
ets+0.081
Neg logit contributions
illi-0.076
ail-0.076
 lobby-0.075
 babys-0.074
 reception-0.071
Token brilliant
Token ID10457
Feature activation-5.81e-02

Pos logit contributions
 than+0.042
ear+0.033
ust+0.033
ets+0.031
 want+0.031
Neg logit contributions
 lobby-0.048
illi-0.047
 kitchen-0.047
 babys-0.047
 reception-0.046
Token furniture
Token ID13091
Feature activation-7.57e-03

Pos logit contributions
 than+0.122
ear+0.096
 want+0.095
ust+0.095
ets+0.093
Neg logit contributions
illi-0.093
ail-0.092
 lobby-0.092
 babys-0.090
 reception-0.087
Token!
Token ID0
Feature activation-2.24e-02

Pos logit contributions
 than+0.011
ear+0.008
 want+0.007
ust+0.007
 hour+0.007
Neg logit contributions
illi-0.017
ail-0.017
 lobby-0.017
 babys-0.016
 reception-0.016
Token Jimmy
Token ID12963
Feature activation-5.07e-04

Pos logit contributions
 than+0.044
 arrow+0.033
ets+0.032
 want+0.032
ear+0.032
Neg logit contributions
illi-0.042
 lobby-0.040
 babys-0.039
ail-0.039
 reception-0.038
Token was
Token ID373
Feature activation+1.56e-02

Pos logit contributions
 than+0.001
 want+0.001
ear+0.001
ets+0.001
 hour+0.001
Neg logit contributions
illi-0.001
ail-0.001
 lobby-0.001
 babys-0.001
 reception-0.001
Token excited
Token ID6568
Feature activation-6.74e-02

Pos logit contributions
ail+0.041
illi+0.040
uffy+0.040
uka+0.039
lo+0.039
Neg logit contributions
 than-0.019
 like-0.014
 because-0.013
 want-0.012
 as-0.011
Token.
Token ID13
Feature activation-6.43e-03

Pos logit contributions
 than+0.104
ust+0.095
 arrow+0.089
ear+0.088
icated+0.087
Neg logit contributions
 kitchen-0.124
ail-0.120
 babys-0.117
 reception-0.115
 lobby-0.111
Token He
Token ID679
Feature activation-1.30e-02

Pos logit contributions
 than+0.008
 want+0.005
ear+0.005
ets+0.005
 hour+0.005
Neg logit contributions
illi-0.016
ail-0.016
 lobby-0.015
 babys-0.015
 reception-0.015
Token grabbed
Token ID13176
Feature activation+2.20e-02

Pos logit contributions
 than+0.026
 hour+0.019
ear+0.019
icated+0.019
ets+0.018
Neg logit contributions
ail-0.023
illi-0.023
 babys-0.022
 reception-0.022
 Stacy-0.021
Token some
Token ID617
Feature activation+1.92e-03

Pos logit contributions
ail+0.047
 salon+0.047
illi+0.046
 babys+0.045
 lobby+0.045
Neg logit contributions
 than-0.034
 as-0.026
 like-0.026
 arrow-0.026
 because-0.025
Tokenummy
Token ID13513
Feature activation-3.91e-02

Pos logit contributions
 than+0.085
 arrow+0.077
 target+0.077
 want+0.075
 hour+0.071
Neg logit contributions
ail-0.045
illi-0.041
omm-0.038
uffy-0.036
izz-0.034
Token!
Token ID0
Feature activation-1.71e-02

Pos logit contributions
ust+0.054
 than+0.052
 hour+0.050
 wanna+0.049
icated+0.048
Neg logit contributions
illi-0.073
 kitchen-0.072
 lobby-0.070
ail-0.068
 reception-0.067
Token With
Token ID2080
Feature activation-7.03e-03

Pos logit contributions
 than+0.034
 want+0.025
ear+0.025
 hour+0.025
ets+0.025
Neg logit contributions
illi-0.031
ail-0.030
 lobby-0.029
 babys-0.029
 reception-0.028
Token excitement
Token ID14067
Feature activation-3.43e-02

Pos logit contributions
 than+0.013
 arrow+0.010
 like+0.009
 want+0.009
 hour+0.009
Neg logit contributions
ail-0.014
illi-0.014
 lobby-0.014
 babys-0.013
uka-0.013
Token,
Token ID11
Feature activation+6.41e-03

Pos logit contributions
 than+0.059
 want+0.041
ear+0.040
ets+0.040
 hour+0.039
Neg logit contributions
illi-0.072
ail-0.070
 lobby-0.069
 babys-0.068
uka-0.067
Token the
Token ID262
Feature activation+3.79e-02

Pos logit contributions
ail+0.015
illi+0.014
 lobby+0.014
acey+0.014
aby+0.014
Neg logit contributions
 than-0.009
 after-0.008
 as-0.008
 because-0.007
 like-0.007
Token little
Token ID1310
Feature activation+2.02e-02

Pos logit contributions
illi+0.080
ail+0.079
 Stacy+0.074
uka+0.074
 lobby+0.074
Neg logit contributions
 than-0.065
 want-0.048
 hour-0.047
 arrow-0.044
 like-0.044
Token girl
Token ID2576
Feature activation+1.66e-02

Pos logit contributions
illi+0.035
ail+0.034
 lobby+0.033
 babys+0.032
uka+0.032
Neg logit contributions
 than-0.042
 want-0.032
 hour-0.031
ear-0.031
ets-0.031
Token sang
Token ID25889
Feature activation-2.08e-02

Pos logit contributions
illi+0.035
ail+0.035
 lobby+0.034
 babys+0.034
 reception+0.033
Neg logit contributions
 than-0.028
 want-0.019
ear-0.019
 hour-0.019
ets-0.019
Token all
Token ID477
Feature activation-1.60e-02

Pos logit contributions
 than+0.036
ear+0.026
 want+0.026
 like+0.025
 because+0.025
Neg logit contributions
illi-0.044
ail-0.044
 lobby-0.043
 babys-0.042
uka-0.041
Token the
Token ID262
Feature activation+3.73e-02

Pos logit contributions
 than+0.036
 want+0.028
ear+0.027
ust+0.027
 arrow+0.027
Neg logit contributions
illi-0.025
ail-0.024
 lobby-0.023
 babys-0.023
 reception-0.022
Token Thank
Token ID6952
Feature activation+1.59e-02

Pos logit contributions
 than+0.055
ets+0.043
ust+0.042
 hour+0.041
 arrow+0.041
Neg logit contributions
illi-0.065
 Stacy-0.061
uka-0.060
 babys-0.060
 lobby-0.059
Token you
Token ID345
Feature activation+1.00e-02

Pos logit contributions
illi+0.037
ail+0.037
 lobby+0.036
 babys+0.036
 reception+0.035
Neg logit contributions
 than-0.023
 want-0.015
ear-0.015
 hour-0.014
ets-0.014
Token for
Token ID329
Feature activation+4.96e-02

Pos logit contributions
illi+0.022
ail+0.022
 babys+0.021
 lobby+0.021
 reception+0.021
Neg logit contributions
 than-0.016
 want-0.011
ear-0.011
ets-0.011
 hour-0.010
Token this
Token ID428
Feature activation+2.68e-02

Pos logit contributions
ail+0.107
illi+0.103
 lobby+0.099
uffy+0.097
 salon+0.097
Neg logit contributions
 than-0.085
 hour-0.060
 like-0.060
ear-0.059
 because-0.059
Token wonderful
Token ID7932
Feature activation-3.08e-02

Pos logit contributions
ail+0.039
illi+0.039
 babys+0.037
 kitchen+0.037
 lobby+0.037
Neg logit contributions
 than-0.061
ear-0.049
ust-0.049
ets-0.048
 want-0.047
Token breakfast
Token ID12607
Feature activation+5.03e-02

Pos logit contributions
 than+0.070
 want+0.054
ear+0.054
ets+0.053
 hour+0.053
Neg logit contributions
illi-0.047
ail-0.046
 lobby-0.044
 babys-0.044
 reception-0.043
Token!"
Token ID2474
Feature activation+3.75e-02

Pos logit contributions
illi+0.117
ail+0.114
 lobby+0.113
 kitchen+0.110
 reception+0.110
Neg logit contributions
 than-0.061
ust-0.047
ear-0.047
 arrow-0.046
 want-0.044
Token Mom
Token ID11254
Feature activation+1.53e-02

Pos logit contributions
illi+0.055
ail+0.054
 babys+0.053
 lobby+0.052
 reception+0.050
Neg logit contributions
 than-0.087
ets-0.069
ear-0.068
 want-0.068
 hour-0.067
Token says
Token ID1139
Feature activation+5.76e-02

Pos logit contributions
illi+0.028
ail+0.026
 babys+0.026
 lobby+0.025
 kitchen+0.025
Neg logit contributions
 than-0.031
 hour-0.023
ear-0.023
ust-0.023
ets-0.022
Token.
Token ID13
Feature activation+7.35e-03

Pos logit contributions
illi+0.143
ail+0.142
 babys+0.138
 lobby+0.137
 reception+0.135
Neg logit contributions
 than-0.074
 want-0.045
ear-0.045
ets-0.043
 hour-0.043
Token
Token ID198
Feature activation+1.13e-03

Pos logit contributions
illi+0.013
ail+0.013
 babys+0.012
 lobby+0.012
 reception+0.012
Neg logit contributions
 than-0.015
 want-0.011
ear-0.011
ets-0.011
 hour-0.011
Token
Token ID198
Feature activation-9.28e-03

Pos logit contributions
 than+0.005
ear+0.003
 want+0.003
 hour+0.003
 because+0.003
Neg logit contributions
 lobby-0.008
 babys-0.008
 salon-0.008
 reception-0.008
illi-0.008
TokenWhen
Token ID2215
Feature activation+9.34e-03

Pos logit contributions
 than+0.016
 want+0.011
ear+0.011
 hour+0.011
ets+0.011
Neg logit contributions
illi-0.020
ail-0.019
 lobby-0.019
 babys-0.019
 reception-0.018
Token she
Token ID673
Feature activation-2.60e-03

Pos logit contributions
ail+0.022
illi+0.022
acey+0.021
 babys+0.021
 lobby+0.021
Neg logit contributions
 than-0.012
 after-0.010
 because-0.010
 as-0.010
 since-0.010
Token was
Token ID373
Feature activation+3.41e-02

Pos logit contributions
 than+0.005
 want+0.004
ear+0.004
ets+0.004
 hour+0.004
Neg logit contributions
illi-0.005
ail-0.005
 lobby-0.005
 babys-0.005
 reception-0.004
Token done
Token ID1760
Feature activation+3.08e-02

Pos logit contributions
illi+0.058
ail+0.057
 lobby+0.055
 babys+0.055
 reception+0.054
Neg logit contributions
 than-0.071
 want-0.055
ear-0.054
ets-0.053
 hour-0.053
Token playing
Token ID2712
Feature activation+2.39e-02

Pos logit contributions
illi+0.075
ail+0.071
 reception+0.069
 lobby+0.069
uka+0.069
Neg logit contributions
 than-0.040
 because-0.030
 like-0.030
 as-0.028
 want-0.026
Token,
Token ID11
Feature activation+7.57e-03

Pos logit contributions
illi+0.053
ail+0.051
 babys+0.050
 lobby+0.049
uka+0.049
Neg logit contributions
 than-0.039
 like-0.027
 want-0.027
 because-0.027
 hour-0.026
Token the
Token ID262
Feature activation+2.99e-02

Pos logit contributions
illi+0.018
ail+0.018
 lobby+0.017
acey+0.017
omm+0.017
Neg logit contributions
 than-0.010
 because-0.009
 as-0.009
 since-0.008
 after-0.008
Token little
Token ID1310
Feature activation+1.82e-02

Pos logit contributions
illi+0.065
 lobby+0.062
ail+0.062
 babys+0.060
 salon+0.060
Neg logit contributions
 than-0.051
 arrow-0.037
 want-0.037
 hour-0.035
 since-0.035
Token girl
Token ID2576
Feature activation+1.21e-02

Pos logit contributions
ail+0.031
illi+0.031
 babys+0.030
 lobby+0.030
 reception+0.029
Neg logit contributions
 than-0.037
ear-0.028
ets-0.028
 want-0.028
 hour-0.027
Token waved
Token ID26834
Feature activation-2.67e-02

Pos logit contributions
illi+0.023
ail+0.023
 lobby+0.022
 babys+0.022
 reception+0.021
Neg logit contributions
 than-0.023
 want-0.017
ear-0.016
 hour-0.016
ets-0.016
Token cream
Token ID8566
Feature activation+4.40e-02

Pos logit contributions
illi+0.063
ail+0.062
 lobby+0.059
 babys+0.059
 reception+0.057
Neg logit contributions
 than-0.097
ear-0.077
 want-0.076
ets-0.075
 arrow-0.075
Token from
Token ID422
Feature activation+3.83e-02

Pos logit contributions
illi+0.082
ail+0.081
 lobby+0.078
 babys+0.078
 reception+0.076
Neg logit contributions
 than-0.083
ear-0.062
 want-0.061
ets-0.060
 hour-0.059
Token the
Token ID262
Feature activation+1.59e-02

Pos logit contributions
ail+0.080
illi+0.078
 babys+0.072
 lobby+0.072
 reception+0.071
Neg logit contributions
 than-0.068
 because-0.051
 like-0.050
 hour-0.049
 want-0.048
Token freezer
Token ID30967
Feature activation+7.46e-02

Pos logit contributions
ail+0.023
illi+0.022
ili+0.020
aby+0.020
loe+0.019
Neg logit contributions
 than-0.038
 like-0.031
 hour-0.031
 want-0.031
 because-0.029
Token?"
Token ID1701
Feature activation+3.55e-02

Pos logit contributions
illi+0.153
ail+0.150
 babys+0.144
 lobby+0.144
 reception+0.141
Neg logit contributions
 than-0.131
 want-0.093
ear-0.090
 hour-0.090
ets-0.089
Token Lily
Token ID20037
Feature activation+1.50e-02

Pos logit contributions
illi+0.073
 lobby+0.072
ail+0.071
 reception+0.069
uka+0.068
Neg logit contributions
 than-0.058
 because-0.045
 want-0.044
 since-0.042
ear-0.042
Token was
Token ID373
Feature activation+2.75e-02

Pos logit contributions
illi+0.029
ail+0.029
 babys+0.027
 lobby+0.027
 reception+0.027
Neg logit contributions
 than-0.028
ear-0.020
 want-0.020
ets-0.020
 hour-0.020
Token very
Token ID845
Feature activation+1.03e-02

Pos logit contributions
ail+0.061
illi+0.058
 lobby+0.056
 reception+0.055
uka+0.055
Neg logit contributions
 than-0.047
 like-0.037
 want-0.037
 because-0.036
 as-0.033
Token excited
Token ID6568
Feature activation-5.86e-02

Pos logit contributions
illi+0.022
ail+0.022
 lobby+0.021
 reception+0.021
 salon+0.021
Neg logit contributions
 than-0.017
 want-0.014
 like-0.012
 hour-0.012
 because-0.012
Token to
Token ID284
Feature activation+5.11e-02

Pos logit contributions
 than+0.085
 arrow+0.078
 target+0.077
ust+0.077
ever+0.073
Neg logit contributions
 kitchen-0.112
ail-0.111
 babys-0.109
 reception-0.107
 salon-0.106
Token help
Token ID1037
Feature activation+3.78e-02

Pos logit contributions
illi+0.089
ail+0.088
 babys+0.085
 lobby+0.084
 reception+0.082
Neg logit contributions
 than-0.105
ets-0.077
ust-0.077
ear-0.077
 hour-0.076
Token thoughtful
Token ID22677
Feature activation-6.35e-02

Pos logit contributions
 than+0.015
ets+0.012
 hour+0.012
ear+0.012
 since+0.012
Neg logit contributions
illi-0.013
ail-0.013
 babys-0.013
 lobby-0.013
 reception-0.012
Token.
Token ID13
Feature activation-2.29e-02

Pos logit contributions
 than+0.104
 wanna+0.090
 hour+0.089
ust+0.088
ear+0.087
Neg logit contributions
ail-0.107
illi-0.105
 babys-0.103
 reception-0.102
 cabinet-0.102
Token He
Token ID679
Feature activation-1.42e-02

Pos logit contributions
 than+0.043
 want+0.032
 hour+0.031
ust+0.031
ets+0.031
Neg logit contributions
illi-0.043
ail-0.042
 lobby-0.042
 babys-0.041
 reception-0.041
Token asked
Token ID1965
Feature activation+4.74e-02

Pos logit contributions
 than+0.027
 hour+0.020
ear+0.020
ust+0.019
ets+0.019
Neg logit contributions
illi-0.026
ail-0.026
 babys-0.025
 lobby-0.025
 reception-0.025
Token the
Token ID262
Feature activation+1.85e-02

Pos logit contributions
illi+0.095
ail+0.093
 lobby+0.090
 salon+0.090
 babys+0.089
Neg logit contributions
 than-0.089
 want-0.067
 because-0.067
 like-0.066
ear-0.065
Token little
Token ID1310
Feature activation+1.83e-04

Pos logit contributions
illi+0.041
ail+0.041
 lobby+0.039
 babys+0.039
 reception+0.038
Neg logit contributions
 than-0.029
 want-0.020
ear-0.019
 hour-0.019
ets-0.019
Token fish
Token ID5916
Feature activation+3.14e-03

Pos logit contributions
ail+0.000
 babys+0.000
illi+0.000
 reception+0.000
 lobby+0.000
Neg logit contributions
 than-0.000
ets-0.000
ust-0.000
ear-0.000
 hour-0.000
Token why
Token ID1521
Feature activation+3.87e-02

Pos logit contributions
illi+0.008
 lobby+0.008
ail+0.008
 babys+0.008
 salon+0.007
Neg logit contributions
 than-0.004
 want-0.003
 like-0.003
 because-0.002
ear-0.002
Token he
Token ID339
Feature activation-9.68e-03

Pos logit contributions
illi+0.086
ail+0.085
 lobby+0.082
 babys+0.081
 reception+0.079
Neg logit contributions
 than-0.063
 want-0.044
 because-0.042
 like-0.042
 since-0.041
Token was
Token ID373
Feature activation+1.88e-02

Pos logit contributions
 than+0.019
 hour+0.015
ear+0.015
ets+0.014
ust+0.014
Neg logit contributions
illi-0.017
ail-0.016
 babys-0.016
 lobby-0.016
 reception-0.015
Token so
Token ID523
Feature activation-1.19e-03

Pos logit contributions
ail+0.041
illi+0.041
 lobby+0.040
 reception+0.038
 salon+0.038
Neg logit contributions
 than-0.032
 like-0.024
 because-0.023
 want-0.023
 arrow-0.020
Token.
Token ID13
Feature activation+3.07e-03

Pos logit contributions
 than+0.004
ear+0.003
ust+0.003
 wanna+0.003
 hour+0.003
Neg logit contributions
 babys-0.008
ail-0.008
illi-0.008
 kitchen-0.007
 lobby-0.007
Token They
Token ID1119
Feature activation-4.24e-03

Pos logit contributions
illi+0.008
ail+0.008
 lobby+0.008
 babys+0.008
 reception+0.008
Neg logit contributions
 than-0.004
 want-0.002
ear-0.002
 hour-0.002
ets-0.002
Token lost
Token ID2626
Feature activation-1.65e-02

Pos logit contributions
 than+0.008
ear+0.006
 hour+0.005
ets+0.005
 want+0.005
Neg logit contributions
illi-0.008
ail-0.008
 babys-0.008
 lobby-0.008
 reception-0.008
Token their
Token ID511
Feature activation+3.41e-02

Pos logit contributions
 than+0.029
 because+0.020
 like+0.020
 want+0.019
 arrow+0.019
Neg logit contributions
illi-0.036
ail-0.035
uka-0.033
 salon-0.033
 babys-0.033
Token toys
Token ID14958
Feature activation+5.08e-04

Pos logit contributions
illi+0.059
ail+0.058
 lobby+0.055
 babys+0.055
 reception+0.054
Neg logit contributions
 than-0.070
 want-0.053
ear-0.052
 hour-0.052
ets-0.052
Token,
Token ID11
Feature activation-6.57e-03

Pos logit contributions
ail+0.001
illi+0.001
 lobby+0.001
 kitchen+0.001
 salon+0.001
Neg logit contributions
 than-0.001
ear-0.001
 wanna-0.001
ust-0.000
icated-0.000
Token their
Token ID511
Feature activation+2.63e-02

Pos logit contributions
 than+0.008
ear+0.005
 want+0.005
ets+0.005
 hour+0.005
Neg logit contributions
illi-0.016
ail-0.016
 babys-0.016
 lobby-0.016
 reception-0.016
Token clothes
Token ID8242
Feature activation+9.66e-03

Pos logit contributions
illi+0.044
ail+0.042
 lobby+0.040
uka+0.039
 babys+0.039
Neg logit contributions
 than-0.057
 want-0.044
 hour-0.043
 arrow-0.042
ear-0.042
Token,
Token ID11
Feature activation-8.42e-03

Pos logit contributions
illi+0.023
ail+0.022
 lobby+0.022
 babys+0.021
uka+0.021
Neg logit contributions
 than-0.014
 want-0.009
ets-0.009
ear-0.009
 hour-0.009
Token their
Token ID511
Feature activation+2.52e-02

Pos logit contributions
 than+0.013
 want+0.009
 because+0.009
 like+0.009
 hour+0.009
Neg logit contributions
illi-0.019
ail-0.019
 lobby-0.018
 babys-0.018
uka-0.018
Token books
Token ID3835
Feature activation+6.59e-03

Pos logit contributions
illi+0.044
ail+0.042
uka+0.041
 Stacy+0.040
 lobby+0.040
Neg logit contributions
 than-0.053
 want-0.040
 arrow-0.039
 hour-0.039
 like-0.038
Token.
Token ID13
Feature activation-1.03e-02

Pos logit contributions
 than+0.025
ust+0.020
 wanna+0.019
ear+0.019
 want+0.018
Neg logit contributions
 salon-0.033
 lobby-0.033
illi-0.033
ail-0.033
 kitchen-0.033
Token
Token ID220
Feature activation+2.25e-02

Pos logit contributions
 than+0.018
 want+0.013
ear+0.012
 because+0.012
 arrow+0.012
Neg logit contributions
illi-0.021
ail-0.021
 lobby-0.020
 babys-0.020
 reception-0.020
Token
Token ID198
Feature activation-8.48e-03

Pos logit contributions
illi+0.044
ail+0.043
 lobby+0.042
 babys+0.042
 reception+0.041
Neg logit contributions
 than-0.041
 want-0.030
ear-0.029
ets-0.028
 hour-0.028
Token
Token ID198
Feature activation-1.59e-02

Pos logit contributions
 than+0.014
ear+0.010
 want+0.009
 since+0.009
 hour+0.009
Neg logit contributions
 lobby-0.018
illi-0.018
ail-0.018
 babys-0.018
 salon-0.017
TokenMax
Token ID11518
Feature activation-5.82e-03

Pos logit contributions
 than+0.036
 want+0.028
ets+0.028
 like+0.026
 hour+0.026
Neg logit contributions
ail-0.024
illi-0.024
 Stacy-0.023
 babys-0.023
 reception-0.022
Token wanted
Token ID2227
Feature activation-2.63e-02

Pos logit contributions
 than+0.011
 want+0.008
ear+0.008
ets+0.008
 hour+0.008
Neg logit contributions
illi-0.011
ail-0.011
 lobby-0.011
 babys-0.011
 reception-0.010
Token to
Token ID284
Feature activation+4.54e-02

Pos logit contributions
 than+0.033
 want+0.020
ear+0.019
 hour+0.018
 arrow+0.018
Neg logit contributions
illi-0.067
ail-0.067
 lobby-0.065
 babys-0.064
 reception-0.063
Token get
Token ID651
Feature activation+3.32e-02

Pos logit contributions
illi+0.084
ail+0.083
 babys+0.082
 lobby+0.079
 reception+0.078
Neg logit contributions
 than-0.088
ets-0.065
 hour-0.064
ust-0.063
ear-0.063
Token his
Token ID465
Feature activation+2.73e-02

Pos logit contributions
illi+0.065
ail+0.064
 lobby+0.063
 reception+0.060
 babys+0.060
Neg logit contributions
 than-0.061
 want-0.047
 arrow-0.045
ear-0.044
 like-0.044
Token ball
Token ID2613
Feature activation+1.60e-02

Pos logit contributions
illi+0.057
ail+0.056
 lobby+0.055
 babys+0.054
 reception+0.053
Neg logit contributions
 than-0.046
 want-0.033
ear-0.032
 hour-0.031
ets-0.031
Token back
Token ID736
Feature activation+5.89e-03

Pos logit contributions
ail+0.026
 babys+0.025
 salon+0.024
 kitchen+0.024
illi+0.023
Neg logit contributions
 than-0.033
ear-0.027
ets-0.026
 wanna-0.026
ust-0.025
Token where
Token ID810
Feature activation+8.82e-03

Pos logit contributions
 than+0.026
ear+0.018
ets+0.018
 want+0.017
 hour+0.017
Neg logit contributions
illi-0.043
ail-0.041
 lobby-0.041
 babys-0.041
 salon-0.040
Token they
Token ID484
Feature activation-3.10e-02

Pos logit contributions
ail+0.020
illi+0.020
 babys+0.019
 lobby+0.019
 reception+0.018
Neg logit contributions
 than-0.013
 want-0.010
 arrow-0.009
 like-0.009
 because-0.009
Token kept
Token ID4030
Feature activation+9.83e-03

Pos logit contributions
 than+0.052
ear+0.036
 want+0.036
 hour+0.036
ets+0.035
Neg logit contributions
illi-0.065
ail-0.064
 lobby-0.062
 babys-0.062
 reception-0.061
Token their
Token ID511
Feature activation+2.43e-02

Pos logit contributions
illi+0.019
ail+0.019
 babys+0.018
 lobby+0.018
 reception+0.018
Neg logit contributions
 than-0.019
 want-0.013
 arrow-0.013
 like-0.013
 because-0.013
Token toys
Token ID14958
Feature activation+1.67e-03

Pos logit contributions
ail+0.042
illi+0.041
 babys+0.040
 lobby+0.040
 kitchen+0.038
Neg logit contributions
 than-0.049
ear-0.038
 want-0.037
 wanna-0.037
ust-0.037
Token and
Token ID290
Feature activation-2.21e-02

Pos logit contributions
ail+0.003
 kitchen+0.003
illi+0.003
 lobby+0.003
 salon+0.003
Neg logit contributions
 than-0.003
 wanna-0.002
ear-0.002
icated-0.002
 hour-0.002
Token books
Token ID3835
Feature activation-2.32e-03

Pos logit contributions
 than+0.043
 want+0.032
ear+0.032
ets+0.031
 hour+0.031
Neg logit contributions
illi-0.041
ail-0.040
 lobby-0.038
 babys-0.038
 reception-0.037
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
 than+0.003
 wanna+0.002
ear+0.002
 want+0.002
ust+0.002
Neg logit contributions
illi-0.005
ail-0.005
 lobby-0.005
 salon-0.005
 reception-0.005
Token They
Token ID1119
Feature activation-2.09e-02

Pos logit contributions
 than+0.027
 want+0.019
ear+0.018
 hour+0.018
ets+0.018
Neg logit contributions
illi-0.038
ail-0.038
 lobby-0.037
 babys-0.036
 reception-0.036
Token made
Token ID925
Feature activation+5.89e-03

Pos logit contributions
 than+0.036
ear+0.026
ets+0.024
 hour+0.024
ust+0.023
Neg logit contributions
illi-0.045
ail-0.043
 lobby-0.042
 babys-0.042
 salon-0.041
Token a
Token ID257
Feature activation-1.90e-02

Pos logit contributions
illi+0.012
ail+0.012
 babys+0.012
uka+0.012
 lobby+0.011
Neg logit contributions
 than-0.010
 want-0.007
ear-0.007
 like-0.007
 arrow-0.007
Token beef
Token ID12023
Feature activation+1.40e-02

Pos logit contributions
 than+0.007
ust+0.006
ear+0.006
ets+0.006
 want+0.006
Neg logit contributions
illi-0.006
 babys-0.006
ail-0.006
 lobby-0.006
 kitchen-0.006
Token jer
Token ID13665
Feature activation-1.54e-02

Pos logit contributions
ail+0.031
illi+0.030
 babys+0.030
 kitchen+0.029
 lobby+0.029
Neg logit contributions
 than-0.020
ear-0.016
ust-0.015
ets-0.015
 wanna-0.015
Tokenky
Token ID2584
Feature activation-2.73e-02

Pos logit contributions
 than+0.026
 want+0.019
 hour+0.019
ust+0.018
ear+0.018
Neg logit contributions
illi-0.032
ail-0.032
 lobby-0.030
 babys-0.030
uka-0.029
Token.
Token ID13
Feature activation-5.53e-04

Pos logit contributions
 than+0.040
ust+0.031
ear+0.029
 want+0.028
 hour+0.028
Neg logit contributions
illi-0.058
ail-0.058
 babys-0.058
 lobby-0.057
 kitchen-0.056
Token When
Token ID1649
Feature activation+1.08e-02

Pos logit contributions
 than+0.001
 want+0.001
ear+0.001
 hour+0.001
ets+0.001
Neg logit contributions
illi-0.001
ail-0.001
 lobby-0.001
 babys-0.001
 reception-0.001
Token she
Token ID673
Feature activation-2.60e-03

Pos logit contributions
illi+0.026
ail+0.026
acey+0.025
ili+0.025
 Stacy+0.024
Neg logit contributions
 than-0.014
 because-0.011
 after-0.010
 hour-0.010
 since-0.010
Token came
Token ID1625
Feature activation+3.81e-02

Pos logit contributions
 than+0.004
 want+0.003
 because+0.003
 since+0.003
 like+0.003
Neg logit contributions
illi-0.005
 lobby-0.005
ail-0.005
 reception-0.005
 Stacy-0.005
Token back
Token ID736
Feature activation+1.17e-02

Pos logit contributions
illi+0.068
 lobby+0.064
ail+0.064
 babys+0.063
 reception+0.062
Neg logit contributions
 than-0.078
 want-0.059
ear-0.059
 arrow-0.057
 since-0.057
Token,
Token ID11
Feature activation+1.27e-02

Pos logit contributions
illi+0.031
 lobby+0.030
ail+0.030
ili+0.029
 salon+0.029
Neg logit contributions
 than-0.014
 because-0.010
 after-0.008
 as-0.008
 want-0.008
Token she
Token ID673
Feature activation-1.60e-02

Pos logit contributions
illi+0.030
ail+0.030
 lobby+0.028
acey+0.028
ili+0.028
Neg logit contributions
 than-0.019
 because-0.015
 arrow-0.014
 like-0.013
 as-0.013
Token used
Token ID973
Feature activation-1.18e-02

Pos logit contributions
 than+0.023
 because+0.018
 want+0.018
 since+0.017
 like+0.017
Neg logit contributions
illi-0.035
 lobby-0.034
lo-0.033
ail-0.033
ili-0.032
Token game
Token ID983
Feature activation-3.96e-02

Pos logit contributions
 than+0.056
ear+0.044
ets+0.043
 want+0.043
ust+0.043
Neg logit contributions
illi-0.049
 babys-0.048
 lobby-0.048
ail-0.047
 kitchen-0.046
Token for
Token ID329
Feature activation+1.86e-02

Pos logit contributions
ust+0.055
 than+0.054
 wanna+0.046
ear+0.046
 matter+0.044
Neg logit contributions
illi-0.077
 lobby-0.077
 reception-0.076
 kitchen-0.074
ail-0.073
Token smart
Token ID4451
Feature activation-5.72e-02

Pos logit contributions
illi+0.038
ail+0.038
 lobby+0.037
 babys+0.036
 salon+0.035
Neg logit contributions
 than-0.032
 hour-0.023
ear-0.023
 want-0.023
 because-0.022
Token people
Token ID661
Feature activation-3.50e-02

Pos logit contributions
ust+0.099
 than+0.087
 arrow+0.072
 enjoyable+0.071
 wanna+0.071
Neg logit contributions
 kitchen-0.092
 lobby-0.092
 reception-0.091
 office-0.089
 cabinet-0.088
Token.
Token ID13
Feature activation-2.88e-02

Pos logit contributions
 than+0.044
ust+0.036
 hour+0.034
 arrow+0.033
 target+0.032
Neg logit contributions
illi-0.077
ail-0.072
 babys-0.071
 reception-0.071
 lobby-0.071
Token You
Token ID921
Feature activation-5.49e-02

Pos logit contributions
 than+0.049
ets+0.035
 hour+0.033
ust+0.033
 want+0.033
Neg logit contributions
illi-0.060
 lobby-0.056
 Stacy-0.056
 babys-0.056
 reception-0.056
Token have
Token ID423
Feature activation-3.34e-02

Pos logit contributions
 than+0.111
 hour+0.087
ear+0.083
ust+0.080
 enjoyable+0.079
Neg logit contributions
illi-0.094
ail-0.088
 lobby-0.084
acey-0.084
 Stacy-0.083
Token to
Token ID284
Feature activation+2.33e-02

Pos logit contributions
 than+0.058
ust+0.047
 hour+0.046
ear+0.044
 want+0.043
Neg logit contributions
illi-0.061
 kitchen-0.060
 lobby-0.058
ail-0.058
 salon-0.056
Token move
Token ID1445
Feature activation-3.23e-02

Pos logit contributions
illi+0.040
 kitchen+0.038
ail+0.038
 lobby+0.038
 babys+0.038
Neg logit contributions
 than-0.045
ust-0.034
ets-0.034
ear-0.033
 hour-0.032
Token the
Token ID262
Feature activation+2.63e-02

Pos logit contributions
 than+0.060
 want+0.044
ear+0.043
 hour+0.042
ets+0.042
Neg logit contributions
illi-0.062
ail-0.061
 lobby-0.059
 babys-0.059
 reception-0.057
Token pieces
Token ID5207
Feature activation+1.18e-03

Pos logit contributions
illi+0.037
ail+0.036
 kitchen+0.036
 lobby+0.036
 babys+0.035
Neg logit contributions
 than-0.061
ear-0.050
ust-0.049
 want-0.047
 wanna-0.047
Token to
Token ID284
Feature activation+1.43e-02

Pos logit contributions
 than+0.049
ets+0.041
 hour+0.041
ust+0.040
ear+0.036
Neg logit contributions
ail-0.048
 kitchen-0.048
 reception-0.048
 babys-0.047
 salon-0.046
Token explore
Token ID7301
Feature activation-1.72e-02

Pos logit contributions
illi+0.030
ail+0.030
 lobby+0.029
 babys+0.029
 reception+0.028
Neg logit contributions
 than-0.024
 want-0.016
ear-0.016
ets-0.016
 hour-0.016
Token and
Token ID290
Feature activation-4.41e-02

Pos logit contributions
 than+0.040
ust+0.033
ets+0.033
ear+0.033
 wanna+0.033
Neg logit contributions
ail-0.022
 lobby-0.022
illi-0.022
 kitchen-0.021
 reception-0.020
Token find
Token ID1064
Feature activation-5.56e-03

Pos logit contributions
 than+0.081
 want+0.061
ear+0.058
 arrow+0.057
 like+0.057
Neg logit contributions
illi-0.088
ail-0.086
 babys-0.082
 lobby-0.082
uka-0.080
Token some
Token ID617
Feature activation-1.72e-02

Pos logit contributions
 than+0.010
 want+0.007
 arrow+0.007
ear+0.007
 like+0.007
Neg logit contributions
illi-0.011
ail-0.011
 babys-0.011
 salon-0.011
 lobby-0.011
Token new
Token ID649
Feature activation-4.73e-02

Pos logit contributions
 than+0.034
ear+0.026
 since+0.025
ets+0.025
 want+0.025
Neg logit contributions
illi-0.030
 lobby-0.029
ail-0.029
 babys-0.029
 kitchen-0.028
Token friends
Token ID2460
Feature activation-1.48e-02

Pos logit contributions
 than+0.099
ets+0.089
ear+0.088
icated+0.087
 hour+0.087
Neg logit contributions
ail-0.061
 lobby-0.061
 kitchen-0.061
 wardrobe-0.059
 babys-0.059
Token.
Token ID13
Feature activation-2.93e-02

Pos logit contributions
 than+0.023
 hour+0.018
ear+0.018
ust+0.017
ets+0.017
Neg logit contributions
illi-0.029
ail-0.029
 lobby-0.028
 kitchen-0.028
 babys-0.028
Token
Token ID198
Feature activation-1.91e-02

Pos logit contributions
 than+0.057
ear+0.041
 hour+0.041
ets+0.041
 want+0.041
Neg logit contributions
illi-0.055
ail-0.054
 lobby-0.052
 babys-0.051
 reception-0.050
Token
Token ID198
Feature activation-2.42e-02

Pos logit contributions
 than+0.032
 want+0.023
ear+0.022
 hour+0.022
 like+0.021
Neg logit contributions
illi-0.039
ail-0.039
 babys-0.039
 lobby-0.039
 salon-0.038
TokenHe
Token ID1544
Feature activation-2.62e-02

Pos logit contributions
 than+0.040
ets+0.028
ear+0.027
 want+0.026
 arrow+0.026
Neg logit contributions
illi-0.051
 reception-0.048
ail-0.048
 lobby-0.048
uka-0.047
Token.
Token ID13
Feature activation+1.56e-02

Pos logit contributions
illi+0.162
ail+0.160
 babys+0.155
 lobby+0.155
 reception+0.152
Neg logit contributions
 than-0.083
 want-0.050
ear-0.050
ets-0.049
 hour-0.048
Token "
Token ID366
Feature activation-9.15e-03

Pos logit contributions
illi+0.028
ail+0.028
 lobby+0.027
 babys+0.027
 reception+0.026
Neg logit contributions
 than-0.031
 want-0.023
ear-0.023
ets-0.023
 hour-0.023
TokenWe
Token ID1135
Feature activation-3.23e-02

Pos logit contributions
 than+0.015
ets+0.012
 arrow+0.012
ear+0.011
ust+0.011
Neg logit contributions
illi-0.018
 lobby-0.017
uka-0.016
ail-0.016
 babys-0.016
Token are
Token ID389
Feature activation+1.58e-02

Pos logit contributions
 than+0.057
ear+0.040
 hour+0.040
ets+0.039
 want+0.039
Neg logit contributions
illi-0.065
ail-0.064
 lobby-0.061
 babys-0.061
 reception-0.060
Token so
Token ID523
Feature activation-6.46e-03

Pos logit contributions
ail+0.032
illi+0.032
 lobby+0.031
 babys+0.030
 salon+0.030
Neg logit contributions
 than-0.029
 want-0.021
 like-0.021
 because-0.020
ear-0.019
Token lucky
Token ID9670
Feature activation-6.11e-02

Pos logit contributions
 than+0.010
 want+0.008
 like+0.007
 hour+0.007
ust+0.007
Neg logit contributions
ail-0.014
illi-0.014
 lobby-0.014
 babys-0.014
 Stacy-0.013
Token to
Token ID284
Feature activation+3.70e-02

Pos logit contributions
ust+0.095
 than+0.094
 target+0.094
 arrow+0.090
 matter+0.086
Neg logit contributions
 kitchen-0.107
 reception-0.104
illi-0.104
 lobby-0.099
 Ana-0.098
Token find
Token ID1064
Feature activation-1.00e-03

Pos logit contributions
ail+0.091
illi+0.090
 lobby+0.090
 babys+0.088
 reception+0.085
Neg logit contributions
 than-0.047
 want-0.039
 like-0.034
 hour-0.031
ear-0.031
Token them
Token ID606
Feature activation-3.25e-03

Pos logit contributions
 than+0.002
 want+0.001
ear+0.001
ets+0.001
 like+0.001
Neg logit contributions
illi-0.002
ail-0.002
 lobby-0.002
 babys-0.002
 salon-0.002
Token."
Token ID526
Feature activation+2.50e-02

Pos logit contributions
 than+0.004
 want+0.003
ear+0.003
 arrow+0.003
 hour+0.003
Neg logit contributions
illi-0.008
ail-0.008
 lobby-0.008
 babys-0.007
 reception-0.007
Token
Token ID198
Feature activation+8.59e-03

Pos logit contributions
illi+0.043
ail+0.042
 lobby+0.040
 babys+0.040
 reception+0.039
Neg logit contributions
 than-0.052
ets-0.040
 want-0.040
ear-0.039
ust-0.039
Token not
Token ID407
Feature activation-2.76e-02

Pos logit contributions
illi+0.042
ail+0.042
 lobby+0.040
 babys+0.039
 reception+0.038
Neg logit contributions
 than-0.055
ets-0.042
ear-0.042
 hour-0.042
 want-0.042
Token move
Token ID1445
Feature activation-2.16e-02

Pos logit contributions
 than+0.060
ear+0.051
ets+0.050
elly+0.050
der+0.049
Neg logit contributions
ail-0.028
 babys-0.028
illi-0.028
 reception-0.028
 kitchen-0.027
Token.
Token ID13
Feature activation-9.38e-03

Pos logit contributions
 than+0.030
 hour+0.021
 want+0.020
ear+0.020
ets+0.020
Neg logit contributions
illi-0.049
ail-0.048
 lobby-0.046
 babys-0.046
 reception-0.045
Token She
Token ID1375
Feature activation-9.62e-03

Pos logit contributions
 than+0.015
 want+0.011
ear+0.011
 hour+0.010
 because+0.010
Neg logit contributions
ail-0.020
illi-0.020
 lobby-0.019
 babys-0.019
 reception-0.018
Token feels
Token ID5300
Feature activation-8.73e-03

Pos logit contributions
 than+0.018
 want+0.014
ets+0.013
ear+0.013
 arrow+0.013
Neg logit contributions
illi-0.018
ail-0.018
 babys-0.017
 lobby-0.017
 reception-0.017
Token sad
Token ID6507
Feature activation-4.94e-02

Pos logit contributions
 than+0.017
 like+0.014
 want+0.014
 because+0.013
 as+0.013
Neg logit contributions
ail-0.017
illi-0.017
 salon-0.016
 lobby-0.016
 reception-0.016
Token.
Token ID13
Feature activation+7.00e-04

Pos logit contributions
 than+0.067
ust+0.063
 wanna+0.062
 target+0.060
ear+0.058
Neg logit contributions
 kitchen-0.093
ail-0.089
 babys-0.089
 wardrobe-0.088
 lobby-0.087
Token
Token ID198
Feature activation+1.33e-03

Pos logit contributions
ail+0.002
illi+0.002
 lobby+0.002
 reception+0.001
 salon+0.001
Neg logit contributions
 than-0.001
 want-0.001
 because-0.001
ear-0.001
 like-0.001
Token
Token ID198
Feature activation-3.88e-03

Pos logit contributions
illi+0.003
 lobby+0.003
ail+0.003
 salon+0.003
 babys+0.003
Neg logit contributions
 than-0.002
ear-0.001
 want-0.001
 hour-0.001
 arrow-0.001
Token"
Token ID1
Feature activation+3.92e-03

Pos logit contributions
 than+0.007
ets+0.005
 want+0.005
ear+0.005
 hour+0.005
Neg logit contributions
illi-0.008
ail-0.008
 lobby-0.007
 babys-0.007
 reception-0.007
TokenMom
Token ID29252
Feature activation-2.58e-03

Pos logit contributions
ail+0.009
 lobby+0.008
illi+0.008
 babys+0.008
 reception+0.008
Neg logit contributions
 than-0.006
 want-0.004
 hour-0.004
 arrow-0.004
 like-0.004
TokenThe
Token ID464
Feature activation+2.79e-02

Pos logit contributions
 than+0.022
 want+0.016
ear+0.015
ets+0.015
 hour+0.015
Neg logit contributions
illi-0.025
ail-0.025
 lobby-0.024
 babys-0.024
 reception-0.023
Token little
Token ID1310
Feature activation+1.33e-02

Pos logit contributions
illi+0.056
ail+0.055
 lobby+0.053
uka+0.053
 Stacy+0.051
Neg logit contributions
 than-0.047
 hour-0.038
 want-0.037
 arrow-0.035
 since-0.034
Token girl
Token ID2576
Feature activation+1.49e-02

Pos logit contributions
illi+0.022
ail+0.022
 lobby+0.021
 babys+0.020
 reception+0.020
Neg logit contributions
 than-0.028
 want-0.022
ear-0.021
 hour-0.021
ets-0.021
Token smiled
Token ID13541
Feature activation-3.09e-02

Pos logit contributions
illi+0.029
ail+0.028
 lobby+0.027
 babys+0.027
 reception+0.027
Neg logit contributions
 than-0.027
 want-0.020
ear-0.019
 hour-0.019
ets-0.019
Token,
Token ID11
Feature activation-1.86e-03

Pos logit contributions
 than+0.038
ets+0.027
 hour+0.027
icated+0.026
 wanna+0.026
Neg logit contributions
ail-0.073
illi-0.071
 babys-0.070
 Stacy-0.069
 lobby-0.068
Token happy
Token ID3772
Feature activation-5.31e-02

Pos logit contributions
 than+0.003
ets+0.002
ear+0.002
ust+0.002
 hour+0.002
Neg logit contributions
illi-0.004
 babys-0.004
ail-0.004
 Stacy-0.003
 lobby-0.003
Token to
Token ID284
Feature activation+4.41e-02

Pos logit contributions
 than+0.080
ust+0.064
ets+0.062
 wanna+0.062
ear+0.061
Neg logit contributions
ail-0.109
 babys-0.106
illi-0.105
 reception-0.103
 kitchen-0.103
Token have
Token ID423
Feature activation-6.40e-03

Pos logit contributions
illi+0.100
ail+0.099
 lobby+0.097
 babys+0.093
 reception+0.093
Neg logit contributions
 than-0.069
 want-0.050
 like-0.046
 hour-0.046
ear-0.046
Token her
Token ID607
Feature activation+2.32e-02

Pos logit contributions
 than+0.012
 want+0.009
ear+0.009
ets+0.009
 hour+0.009
Neg logit contributions
illi-0.012
ail-0.012
 lobby-0.011
 babys-0.011
 reception-0.011
Token Mom
Token ID11254
Feature activation+1.39e-02

Pos logit contributions
illi+0.043
ail+0.042
 lobby+0.041
 babys+0.041
 reception+0.040
Neg logit contributions
 than-0.045
 want-0.033
ear-0.033
 hour-0.032
ets-0.032
Tokenmy
Token ID1820
Feature activation+3.09e-03

Pos logit contributions
illi+0.028
 lobby+0.027
ail+0.027
 babys+0.026
 reception+0.026
Neg logit contributions
 than-0.026
 want-0.019
 like-0.018
 since-0.018
 because-0.018