TOP ACTIVATIONS
MAX = 0.110

The le opard toy costs $ 10 ."
he said it was only $ 10 .
the price - it was $ 5 . Sally was so
, " This block is ten inches long . This block
price tag . It said $ 1 . 99 per pound
, " This is number ten ." But he shows Lily
, " It is number ten . It is my favorite
said , " It costs ten dollars to buy the rabbit
doing ? This is not fuel for your truck ! This
said " T oys for sale . One coin each ."
have a label that says ' cars '. I will put
the cars are not for sale . They are only for
These toys are not for sale . They are part of
They are also tools for math . We can use them
you need a tutor for math . A tutor is a
. He is not for sale . He is my friend
expensive flavor . It costs ten dollars for one cone ."
they were going to learn math . Tim my didn 't
. " My car is cooler than yours !"
, I want to learn math !" Her Mom said ,

MIN ACTIVATIONS
MIN = -0.099

listen . She threw a tant rum in the store .
draw and shared the cr ay ons . They were very
and I shared my cr ay ons with Ben . They
sad . She threw a tant rum and cried loudly .
. As Daisy â s gaze passed by ,
. He kept throwing a tant rum . His mom was
her feet and threw a tant rum . She grabbed the
to cry and threw a tant rum . She didn 't
then on everyone in the me adow was happy , and
kept crying and throwing a tant rum . Finally
of the animals in the me adow soon learned how to
of the day in the me adow , wondering what adventure
, Sarah shared her cr ay ons with Tim my and
He lived in a sunny me adow near a large bucket
of the day in the me adow , enjoying Gina 's
She cried and threw a tant rum . Her mom tried
chair and takes a cr ay on and a paper .
. With a red cr ay on she carefully drew a
their merry way through the me adow , enjoying the sight
friends and share the cr ay ons and the paper ."

INTERVAL 0.058 - 0.110
CONTAINS 0.114%

mom said he could earn money by doing chores . So
. They liked to solve puzzles and r iddles . One
this prize if you take five steps . It 's a
" Like scissors or knives or guns ," Dad
a new book in the library . It has many pictures

INTERVAL 0.006 - 0.058
CONTAINS 36.684%

all alone . The spider asked the skin if it could
ate them . He wrapped his trunk around them and gave
cut est surprise of all a
They hug the man and say goodbye . They go
mom my was happy that Lily was interested in music ,

INTERVAL -0.046 - 0.006
CONTAINS 62.422%

. It was no longer good to eat .
the very top . The bald man was very grateful to
smelled really nice . He had fun playing with the bubbles
is busy playing with the ball . He thinks the kids
a break , lie down and enjoy the sunshine .

INTERVAL -0.099 - -0.046
CONTAINS 0.780%

nerves , and had a wonderful time . All the people
bark ed , " Let me go , let me go
are even more flexible than I thought ! â
I can help . All you need to do is promise
. " Got you !" Mom says . "
TokenThe
Token ID464
Feature activation+2.76e-02

Pos logit contributions
 stall+0.057
mary+0.056
field+0.055
 rightful+0.055
 bank+0.054
Neg logit contributions
hing-0.053
Ta-0.049
 ah-0.048
 applause-0.045
aid-0.045
Token le
Token ID443
Feature activation+2.09e-02

Pos logit contributions
field+0.045
mary+0.043
chard+0.043
 stall+0.039
 rightful+0.038
Neg logit contributions
 ah-0.047
hing-0.047
Ta-0.046
 applause-0.045
aid-0.044
Tokenopard
Token ID15478
Feature activation+9.10e-03

Pos logit contributions
 rightful+0.035
field+0.035
mary+0.035
 stall+0.034
chard+0.034
Neg logit contributions
hing-0.037
 ah-0.035
Ta-0.033
aid-0.033
ickets-0.032
Token toy
Token ID13373
Feature activation+1.75e-02

Pos logit contributions
chard+0.016
field+0.015
 rightful+0.015
 stall+0.015
mary+0.015
Neg logit contributions
hing-0.015
 ah-0.014
 applause-0.013
aid-0.013
ez-0.013
Token costs
Token ID3484
Feature activation+7.36e-02

Pos logit contributions
 rightful+0.032
chard+0.032
mary+0.031
field+0.030
 stall+0.029
Neg logit contributions
hing-0.028
 ah-0.027
 boom-0.024
 bang-0.023
 Stop-0.023
Token $
Token ID720
Feature activation+1.10e-01

Pos logit contributions
field+0.145
mary+0.140
 stall+0.132
chard+0.128
 rightful+0.126
Neg logit contributions
aid-0.107
 ah-0.103
hing-0.102
ez-0.100
 applause-0.097
Token10
Token ID940
Feature activation+7.14e-02

Pos logit contributions
field+0.186
mary+0.177
 stall+0.176
 rightful+0.167
chard+0.162
Neg logit contributions
hing-0.199
Ta-0.197
aid-0.188
 ah-0.181
 applause-0.174
Token."
Token ID526
Feature activation+2.34e-02

Pos logit contributions
field+0.122
mary+0.118
 rightful+0.117
chard+0.116
 stall+0.103
Neg logit contributions
hing-0.120
 ah-0.115
 boom-0.108
 bang-0.107
aid-0.106
Token
Token ID220
Feature activation-9.77e-03

Pos logit contributions
 stall+0.042
mary+0.041
field+0.041
 rightful+0.040
 bank+0.040
Neg logit contributions
hing-0.039
 ah-0.037
Ta-0.036
 boom-0.033
 applause-0.033
Token
Token ID198
Feature activation+1.09e-02

Pos logit contributions
hing+0.018
 ah+0.017
Ta+0.017
ickets+0.016
 boom+0.016
Neg logit contributions
 stall-0.015
field-0.015
 rightful-0.015
mary-0.015
chard-0.015
Token
Token ID198
Feature activation+1.66e-02

Pos logit contributions
 stall+0.013
mary+0.013
field+0.012
 rightful+0.012
 bank+0.012
Neg logit contributions
hing-0.025
 ah-0.024
Ta-0.023
 applause-0.022
 boom-0.022
Token he
Token ID339
Feature activation+4.82e-03

Pos logit contributions
 stall+0.007
field+0.007
 rightful+0.007
mary+0.007
 bank+0.007
Neg logit contributions
 ah-0.008
hing-0.008
 applause-0.007
Ta-0.007
 boom-0.007
Token said
Token ID531
Feature activation-7.50e-03

Pos logit contributions
 stall+0.009
field+0.009
chard+0.009
 rightful+0.009
 bank+0.008
Neg logit contributions
 ah-0.007
hing-0.006
aid-0.006
 applause-0.006
Ta-0.006
Token it
Token ID340
Feature activation+1.78e-02

Pos logit contributions
hing+0.015
 ah+0.015
Ta+0.014
 applause+0.014
 boom+0.014
Neg logit contributions
 stall-0.010
field-0.010
mary-0.010
 rightful-0.010
 bank-0.010
Token was
Token ID373
Feature activation+3.37e-02

Pos logit contributions
 stall+0.031
chard+0.030
field+0.030
 rightful+0.030
 stalls+0.028
Neg logit contributions
hing-0.029
 ah-0.028
 applause-0.025
aid-0.024
ez-0.024
Token only
Token ID691
Feature activation+4.43e-02

Pos logit contributions
 bank+0.071
field+0.069
 stall+0.069
mary+0.065
 stalls+0.065
Neg logit contributions
 sorry-0.040
 ah-0.039
 applause-0.038
 relief-0.037
hing-0.036
Token $
Token ID720
Feature activation+1.01e-01

Pos logit contributions
 stall+0.073
field+0.073
mary+0.071
chard+0.069
 rightful+0.069
Neg logit contributions
hing-0.077
 ah-0.075
 applause-0.071
 boom-0.070
Ta-0.068
Token10
Token ID940
Feature activation+6.16e-02

Pos logit contributions
field+0.158
 stall+0.155
mary+0.153
 rightful+0.151
 shelf+0.146
Neg logit contributions
hing-0.188
Ta-0.184
 ah-0.177
aid-0.171
 boom-0.166
Token.
Token ID13
Feature activation-8.52e-03

Pos logit contributions
chard+0.077
field+0.077
 rightful+0.077
mary+0.075
 stall+0.074
Neg logit contributions
hing-0.132
 ah-0.129
 applause-0.120
 boom-0.119
aid-0.117
Token
Token ID220
Feature activation-1.80e-02

Pos logit contributions
hing+0.015
 ah+0.014
Ta+0.014
 applause+0.013
ickets+0.013
Neg logit contributions
 stall-0.014
mary-0.014
field-0.014
 rightful-0.014
chard-0.014
Token
Token ID198
Feature activation-2.29e-03

Pos logit contributions
hing+0.037
 ah+0.035
Ta+0.034
ickets+0.032
 boom+0.032
Neg logit contributions
 stall-0.025
field-0.025
 rightful-0.025
mary-0.025
chard-0.024
Token
Token ID198
Feature activation+6.45e-04

Pos logit contributions
hing+0.006
 ah+0.006
Ta+0.005
 boom+0.005
 applause+0.005
Neg logit contributions
 stall-0.002
mary-0.002
field-0.002
chard-0.002
 shelf-0.002
Token the
Token ID262
Feature activation+1.95e-02

Pos logit contributions
 rightful+0.027
field+0.027
 stall+0.025
chard+0.024
mary+0.024
Neg logit contributions
hing-0.020
 ah-0.018
aid-0.016
 applause-0.016
ez-0.016
Token price
Token ID2756
Feature activation+2.90e-02

Pos logit contributions
mary+0.032
field+0.032
 stall+0.029
chard+0.029
 rightful+0.028
Neg logit contributions
hing-0.034
 ah-0.033
 applause-0.032
Ta-0.032
 boom-0.030
Token -
Token ID532
Feature activation+6.59e-03

Pos logit contributions
field+0.056
mary+0.056
 rightful+0.053
chard+0.052
 stall+0.051
Neg logit contributions
hing-0.042
 ah-0.041
 applause-0.037
aid-0.037
Ta-0.035
Token it
Token ID340
Feature activation-8.75e-03

Pos logit contributions
mary+0.012
field+0.012
 rightful+0.011
 stall+0.011
 bank+0.011
Neg logit contributions
 ah-0.010
hing-0.010
 applause-0.010
Ta-0.009
aid-0.009
Token was
Token ID373
Feature activation+2.01e-02

Pos logit contributions
hing+0.016
 ah+0.015
 applause+0.013
 boom+0.013
ickets+0.013
Neg logit contributions
 stall-0.015
chard-0.014
 rightful-0.014
field-0.014
mary-0.013
Token $
Token ID720
Feature activation+9.75e-02

Pos logit contributions
field+0.038
 stall+0.036
mary+0.035
 bank+0.034
 stalls+0.033
Neg logit contributions
 ah-0.028
 applause-0.028
hing-0.028
 sorry-0.026
 boom-0.026
Token5
Token ID20
Feature activation+8.61e-02

Pos logit contributions
field+0.145
mary+0.143
 stall+0.143
 rightful+0.138
chard+0.133
Neg logit contributions
hing-0.191
Ta-0.184
 ah-0.180
aid-0.170
 boom-0.168
Token.
Token ID13
Feature activation-3.55e-03

Pos logit contributions
chard+0.162
field+0.161
mary+0.155
 rightful+0.152
 stall+0.140
Neg logit contributions
hing-0.126
 ah-0.118
ay-0.115
inking-0.112
ong-0.109
Token Sally
Token ID25737
Feature activation-1.19e-02

Pos logit contributions
 ah+0.005
hing+0.005
Ta+0.005
 applause+0.005
ickets+0.005
Neg logit contributions
field-0.007
mary-0.007
 stall-0.006
 rightful-0.006
chard-0.006
Token was
Token ID373
Feature activation-1.01e-02

Pos logit contributions
hing+0.021
 ah+0.021
Ta+0.019
ez+0.018
 applause+0.018
Neg logit contributions
 rightful-0.019
 stall-0.019
chard-0.018
field-0.018
mary-0.017
Token so
Token ID523
Feature activation+4.40e-03

Pos logit contributions
hing+0.018
 ah+0.018
Ta+0.017
 applause+0.016
 boom+0.016
Neg logit contributions
field-0.016
mary-0.016
 stall-0.016
 rightful-0.015
 shelf-0.015
Token,
Token ID11
Feature activation+6.04e-02

Pos logit contributions
 stall+0.006
mary+0.006
chard+0.006
field+0.006
 rightful+0.006
Neg logit contributions
hing-0.012
Ta-0.011
 ah-0.011
 applause-0.011
 boom-0.011
Token "
Token ID366
Feature activation+4.93e-02

Pos logit contributions
 rightful+0.072
 stall+0.071
field+0.070
mary+0.068
 bank+0.067
Neg logit contributions
hing-0.136
 ah-0.133
Ta-0.125
 boom-0.124
 applause-0.122
TokenThis
Token ID1212
Feature activation+2.33e-02

Pos logit contributions
 rightful+0.087
mary+0.087
 stall+0.087
field+0.086
chard+0.083
Neg logit contributions
hing-0.086
Ta-0.081
 ah-0.077
 applause-0.072
aid-0.072
Token block
Token ID2512
Feature activation+4.38e-02

Pos logit contributions
mary+0.038
 rightful+0.037
chard+0.037
field+0.037
 stall+0.037
Neg logit contributions
hing-0.043
 ah-0.041
 boom-0.038
Ta-0.038
 applause-0.037
Token is
Token ID318
Feature activation+4.15e-02

Pos logit contributions
chard+0.075
mary+0.074
 stall+0.074
field+0.074
 rightful+0.074
Neg logit contributions
hing-0.076
 ah-0.072
 boom-0.068
 applause-0.065
ickets-0.065
Token ten
Token ID3478
Feature activation+9.71e-02

Pos logit contributions
field+0.081
 stall+0.078
mary+0.078
 bank+0.075
 rightful+0.074
Neg logit contributions
 boom-0.062
hing-0.059
 ah-0.058
 applause-0.056
 bang-0.053
Token inches
Token ID8331
Feature activation+8.15e-02

Pos logit contributions
mary+0.171
field+0.170
chard+0.167
 rightful+0.161
 stall+0.151
Neg logit contributions
 ah-0.159
 boom-0.158
hing-0.157
 applause-0.145
 bang-0.142
Token long
Token ID890
Feature activation+3.69e-02

Pos logit contributions
 rightful+0.148
field+0.145
chard+0.145
mary+0.142
 stall+0.134
Neg logit contributions
 boom-0.126
hing-0.114
ong-0.112
ay-0.108
ch-0.103
Token.
Token ID13
Feature activation+6.27e-03

Pos logit contributions
chard+0.056
 rightful+0.055
field+0.055
mary+0.054
 stall+0.051
Neg logit contributions
hing-0.071
 ah-0.068
 boom-0.067
 applause-0.064
ez-0.063
Token This
Token ID770
Feature activation+2.07e-02

Pos logit contributions
 stall+0.012
mary+0.012
field+0.012
 rightful+0.012
chard+0.012
Neg logit contributions
hing-0.009
 ah-0.009
Ta-0.008
 boom-0.008
 applause-0.008
Token block
Token ID2512
Feature activation+3.50e-02

Pos logit contributions
mary+0.036
 stall+0.035
 rightful+0.035
field+0.035
chard+0.034
Neg logit contributions
hing-0.036
 ah-0.034
Ta-0.032
 boom-0.032
 applause-0.031
Token price
Token ID2756
Feature activation+3.01e-02

Pos logit contributions
hing+0.005
 ah+0.005
 applause+0.005
Ta+0.004
 boom+0.004
Neg logit contributions
mary-0.007
field-0.006
 stall-0.006
 rightful-0.006
chard-0.006
Token tag
Token ID7621
Feature activation+3.73e-02

Pos logit contributions
 rightful+0.047
field+0.047
mary+0.045
chard+0.044
 stall+0.041
Neg logit contributions
hing-0.056
 ah-0.055
 applause-0.051
 boom-0.049
aid-0.048
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
 rightful+0.066
field+0.063
chard+0.060
mary+0.056
 stall+0.056
Neg logit contributions
hing-0.061
 ah-0.061
 applause-0.056
 boom-0.054
 bang-0.052
Token It
Token ID632
Feature activation-5.27e-03

Pos logit contributions
 stall+0.016
field+0.016
 rightful+0.016
 bank+0.015
mary+0.015
Neg logit contributions
hing-0.019
 ah-0.018
Ta-0.018
 boom-0.017
 applause-0.017
Token said
Token ID531
Feature activation-9.58e-04

Pos logit contributions
 ah+0.008
hing+0.007
 bang+0.007
apy+0.007
Ta+0.007
Neg logit contributions
 rightful-0.010
 stall-0.010
field-0.009
chard-0.009
 buyer-0.009
Token $
Token ID720
Feature activation+9.63e-02

Pos logit contributions
hing+0.002
Ta+0.002
 ah+0.002
 boom+0.002
 applause+0.002
Neg logit contributions
 stall-0.001
mary-0.001
field-0.001
 rightful-0.001
chard-0.001
Token1
Token ID16
Feature activation+4.91e-02

Pos logit contributions
field+0.142
 stall+0.140
mary+0.139
 rightful+0.137
chard+0.132
Neg logit contributions
hing-0.192
Ta-0.182
 ah-0.181
aid-0.171
 boom-0.170
Token.
Token ID13
Feature activation+2.42e-02

Pos logit contributions
chard+0.085
field+0.084
 rightful+0.081
 stall+0.078
 bank+0.075
Neg logit contributions
hing-0.089
 ah-0.084
aid-0.076
 applause-0.075
ez-0.074
Token99
Token ID2079
Feature activation-1.19e-02

Pos logit contributions
 rightful+0.038
field+0.038
 stall+0.037
 bank+0.037
mary+0.036
Neg logit contributions
hing-0.044
 ah-0.043
Ta-0.042
 boom-0.040
 applause-0.040
Token per
Token ID583
Feature activation+1.08e-02

Pos logit contributions
hing+0.024
 ah+0.023
Ta+0.022
 applause+0.021
 boom+0.021
Neg logit contributions
 stall-0.017
chard-0.017
field-0.017
mary-0.017
 rightful-0.017
Token pound
Token ID14896
Feature activation+3.13e-02

Pos logit contributions
 stall+0.019
mary+0.019
 rightful+0.018
field+0.018
 bank+0.018
Neg logit contributions
hing-0.018
 ah-0.017
Ta-0.017
 boom-0.016
 applause-0.016
Token,
Token ID11
Feature activation+4.83e-02

Pos logit contributions
hing+0.007
Ta+0.007
 ah+0.007
 boom+0.006
 applause+0.006
Neg logit contributions
 stall-0.004
mary-0.004
chard-0.004
 rightful-0.004
field-0.004
Token "
Token ID366
Feature activation+3.61e-02

Pos logit contributions
 rightful+0.063
field+0.060
 stall+0.060
mary+0.058
 bank+0.056
Neg logit contributions
hing-0.105
 ah-0.103
 boom-0.097
Ta-0.096
 applause-0.094
TokenThis
Token ID1212
Feature activation+2.23e-02

Pos logit contributions
 stall+0.068
field+0.067
mary+0.067
 rightful+0.066
chard+0.065
Neg logit contributions
hing-0.059
Ta-0.055
 ah-0.054
 applause-0.050
aid-0.049
Token is
Token ID318
Feature activation+3.30e-02

Pos logit contributions
chard+0.042
 rightful+0.041
field+0.041
mary+0.040
 stall+0.037
Neg logit contributions
 ah-0.033
hing-0.033
 applause-0.032
Ta-0.030
 boom-0.030
Token number
Token ID1271
Feature activation+5.94e-02

Pos logit contributions
field+0.074
 stall+0.072
 bank+0.071
mary+0.069
 rightful+0.067
Neg logit contributions
 ah-0.038
 boom-0.036
 applause-0.035
Ta-0.033
 sorry-0.033
Token ten
Token ID3478
Feature activation+9.48e-02

Pos logit contributions
field+0.101
 rightful+0.100
chard+0.099
mary+0.098
 stall+0.096
Neg logit contributions
hing-0.105
 ah-0.103
 applause-0.094
 boom-0.094
ickets-0.089
Token."
Token ID526
Feature activation+3.53e-02

Pos logit contributions
field+0.162
chard+0.161
 rightful+0.156
mary+0.155
 bank+0.141
Neg logit contributions
 ah-0.159
hing-0.154
 boom-0.153
 applause-0.153
 bang-0.142
Token But
Token ID887
Feature activation-4.19e-03

Pos logit contributions
field+0.060
mary+0.059
 stall+0.057
chard+0.056
 rightful+0.056
Neg logit contributions
hing-0.060
 ah-0.059
Ta-0.057
 applause-0.056
 boom-0.054
Token he
Token ID339
Feature activation+2.44e-02

Pos logit contributions
hing+0.008
 ah+0.008
Ta+0.007
 boom+0.007
 applause+0.007
Neg logit contributions
mary-0.007
 stall-0.006
field-0.006
 rightful-0.006
 bank-0.006
Token shows
Token ID2523
Feature activation-1.44e-03

Pos logit contributions
 stall+0.043
field+0.043
mary+0.042
chard+0.042
 rightful+0.041
Neg logit contributions
hing-0.040
 ah-0.039
Ta-0.037
 applause-0.036
 boom-0.035
Token Lily
Token ID20037
Feature activation+3.09e-02

Pos logit contributions
hing+0.003
 ah+0.002
Ta+0.002
 boom+0.002
 applause+0.002
Neg logit contributions
 stall-0.003
mary-0.002
field-0.002
 rightful-0.002
chard-0.002
Token,
Token ID11
Feature activation+3.67e-02

Pos logit contributions
hing+0.013
Ta+0.013
 ah+0.012
 applause+0.012
ickets+0.012
Neg logit contributions
 stall-0.006
mary-0.006
chard-0.006
field-0.006
 rightful-0.006
Token "
Token ID366
Feature activation+4.15e-02

Pos logit contributions
 rightful+0.043
 stall+0.042
field+0.041
mary+0.041
 bank+0.039
Neg logit contributions
hing-0.085
 ah-0.083
Ta-0.077
 boom-0.077
 applause-0.076
TokenIt
Token ID1026
Feature activation-2.59e-03

Pos logit contributions
 rightful+0.070
 stall+0.069
field+0.069
mary+0.069
chard+0.065
Neg logit contributions
hing-0.075
Ta-0.072
 ah-0.067
aid-0.066
ickets-0.064
Token is
Token ID318
Feature activation+4.50e-02

Pos logit contributions
hing+0.004
 ah+0.004
 boom+0.004
 bang+0.003
ickets+0.003
Neg logit contributions
 rightful-0.005
chard-0.005
 stall-0.005
field-0.005
mary-0.005
Token number
Token ID1271
Feature activation+6.18e-02

Pos logit contributions
field+0.099
 bank+0.093
bank+0.092
mary+0.092
mer+0.092
Neg logit contributions
 boom-0.049
 sorry-0.045
 ah-0.044
 applause-0.043
 lightning-0.042
Token ten
Token ID3478
Feature activation+9.26e-02

Pos logit contributions
field+0.104
 rightful+0.103
chard+0.099
mary+0.097
 stall+0.097
Neg logit contributions
hing-0.114
 ah-0.107
 boom-0.103
 applause-0.098
ickets-0.097
Token.
Token ID13
Feature activation+1.83e-02

Pos logit contributions
chard+0.156
field+0.155
 rightful+0.148
mary+0.146
 stall+0.131
Neg logit contributions
hing-0.157
 boom-0.156
 ah-0.154
 applause-0.148
 bang-0.145
Token It
Token ID632
Feature activation+9.21e-03

Pos logit contributions
field+0.033
 stall+0.033
mary+0.033
 rightful+0.033
 bank+0.032
Neg logit contributions
hing-0.030
 ah-0.028
Ta-0.027
 boom-0.026
 applause-0.026
Token is
Token ID318
Feature activation+3.93e-02

Pos logit contributions
chard+0.019
 rightful+0.019
field+0.018
 stall+0.018
mary+0.017
Neg logit contributions
hing-0.014
 ah-0.013
 boom-0.012
 bang-0.011
ickets-0.011
Token my
Token ID616
Feature activation+1.77e-02

Pos logit contributions
field+0.082
mary+0.077
 bank+0.076
 stall+0.074
bank+0.074
Neg logit contributions
 boom-0.050
 ah-0.046
 applause-0.045
 bang-0.044
 sorry-0.043
Token favorite
Token ID4004
Feature activation+1.44e-02

Pos logit contributions
mary+0.028
field+0.026
chard+0.026
 stall+0.025
 rightful+0.024
Neg logit contributions
 ah-0.030
 applause-0.030
hing-0.029
 boom-0.029
Ta-0.028
Token said
Token ID531
Feature activation+1.99e-03

Pos logit contributions
hing+0.033
 ah+0.032
Ta+0.031
 boom+0.030
 applause+0.029
Neg logit contributions
 stall-0.022
mary-0.021
field-0.021
 rightful-0.021
chard-0.020
Token,
Token ID11
Feature activation+3.69e-02

Pos logit contributions
 stall+0.003
mary+0.002
field+0.002
 rightful+0.002
chard+0.002
Neg logit contributions
hing-0.004
 ah-0.004
Ta-0.004
 boom-0.004
 applause-0.004
Token "
Token ID366
Feature activation+2.74e-02

Pos logit contributions
 rightful+0.049
field+0.047
 stall+0.047
mary+0.045
 bank+0.044
Neg logit contributions
hing-0.079
 ah-0.078
 boom-0.072
 applause-0.071
Ta-0.070
TokenIt
Token ID1026
Feature activation-1.06e-02

Pos logit contributions
 stall+0.045
mary+0.044
field+0.044
 rightful+0.044
chard+0.043
Neg logit contributions
hing-0.050
 ah-0.047
Ta-0.046
 applause-0.043
 boom-0.043
Token costs
Token ID3484
Feature activation+7.10e-02

Pos logit contributions
hing+0.021
 ah+0.020
 boom+0.018
Ta+0.018
 applause+0.018
Neg logit contributions
 stall-0.017
chard-0.016
field-0.016
 rightful-0.016
mary-0.015
Token ten
Token ID3478
Feature activation+8.93e-02

Pos logit contributions
field+0.143
mary+0.137
 stall+0.131
chard+0.129
 rightful+0.126
Neg logit contributions
 ah-0.102
hing-0.100
aid-0.097
 applause-0.096
Ta-0.092
Token dollars
Token ID5054
Feature activation+7.25e-02

Pos logit contributions
field+0.159
chard+0.155
mary+0.153
 rightful+0.147
 stall+0.134
Neg logit contributions
 ah-0.144
hing-0.140
 applause-0.138
 boom-0.134
 bang-0.132
Token to
Token ID284
Feature activation-3.28e-03

Pos logit contributions
mary+0.140
field+0.132
 rightful+0.130
chard+0.126
 stall+0.123
Neg logit contributions
hing-0.105
 ah-0.101
ay-0.096
 Stop-0.093
aid-0.091
Token buy
Token ID2822
Feature activation+4.74e-02

Pos logit contributions
hing+0.005
 ah+0.005
 applause+0.005
aid+0.005
Ta+0.005
Neg logit contributions
mary-0.006
field-0.006
 stall-0.006
chard-0.005
 rightful-0.005
Token the
Token ID262
Feature activation+1.58e-02

Pos logit contributions
field+0.096
mary+0.089
 rightful+0.085
 stall+0.085
chard+0.084
Neg logit contributions
 ah-0.065
hing-0.065
aid-0.060
 applause-0.058
 boom-0.057
Token rabbit
Token ID22746
Feature activation-2.82e-03

Pos logit contributions
mary+0.024
field+0.023
chard+0.021
 stall+0.021
 rightful+0.020
Neg logit contributions
 ah-0.028
hing-0.027
 applause-0.027
Ta-0.025
 boom-0.025
Token doing
Token ID1804
Feature activation-1.47e-03

Pos logit contributions
hing+0.112
Ta+0.110
aid+0.103
 applause+0.101
ickets+0.098
Neg logit contributions
 stall-0.094
field-0.093
chard-0.088
 bank-0.086
mary-0.085
Token?
Token ID30
Feature activation+1.49e-02

Pos logit contributions
hing+0.003
Ta+0.003
 ah+0.003
 applause+0.003
aid+0.003
Neg logit contributions
 stall-0.002
mary-0.002
field-0.002
 rightful-0.002
chard-0.002
Token This
Token ID770
Feature activation+1.47e-02

Pos logit contributions
 stall+0.026
mary+0.026
field+0.026
 rightful+0.025
chard+0.025
Neg logit contributions
hing-0.025
 ah-0.023
Ta-0.023
 applause-0.022
 boom-0.021
Token is
Token ID318
Feature activation+2.65e-02

Pos logit contributions
mary+0.023
chard+0.022
 stall+0.022
 rightful+0.022
field+0.022
Neg logit contributions
hing-0.029
 ah-0.027
 boom-0.026
Ta-0.025
 applause-0.025
Token not
Token ID407
Feature activation+3.27e-02

Pos logit contributions
 stall+0.048
field+0.048
mary+0.047
 bank+0.046
 rightful+0.046
Neg logit contributions
 boom-0.041
hing-0.041
 ah-0.040
 applause-0.037
Ta-0.037
Token fuel
Token ID5252
Feature activation+8.92e-02

Pos logit contributions
mary+0.061
 stall+0.060
field+0.060
 rightful+0.059
chard+0.058
Neg logit contributions
hing-0.053
 ah-0.049
 boom-0.047
Ta-0.046
 applause-0.045
Token for
Token ID329
Feature activation-4.17e-03

Pos logit contributions
mary+0.152
chard+0.146
 rightful+0.141
 stall+0.141
field+0.139
Neg logit contributions
hing-0.164
 boom-0.150
 ah-0.143
 applause-0.135
 bang-0.134
Token your
Token ID534
Feature activation+1.77e-02

Pos logit contributions
hing+0.008
Ta+0.007
 ah+0.007
aid+0.007
ickets+0.007
Neg logit contributions
 stall-0.007
 shelf-0.007
field-0.006
chard-0.006
 bank-0.006
Token truck
Token ID7779
Feature activation+5.49e-02

Pos logit contributions
mary+0.027
 stall+0.026
field+0.026
chard+0.025
 rightful+0.025
Neg logit contributions
hing-0.034
 ah-0.033
 boom-0.031
 applause-0.031
Ta-0.030
Token!
Token ID0
Feature activation-5.64e-03

Pos logit contributions
mary+0.081
chard+0.079
 stall+0.078
 rightful+0.078
field+0.077
Neg logit contributions
hing-0.111
 boom-0.103
 ah-0.101
 bang-0.094
ickets-0.094
Token This
Token ID770
Feature activation+1.32e-02

Pos logit contributions
hing+0.009
 ah+0.008
Ta+0.008
 applause+0.007
 boom+0.007
Neg logit contributions
 stall-0.011
mary-0.011
field-0.011
 rightful-0.011
chard-0.010
Token said
Token ID531
Feature activation+1.98e-02

Pos logit contributions
 rightful+0.002
 stall+0.002
field+0.002
mary+0.002
chard+0.002
Neg logit contributions
 ah-0.002
hing-0.002
 applause-0.002
Ta-0.002
aid-0.002
Token "
Token ID366
Feature activation+6.94e-02

Pos logit contributions
field+0.028
 rightful+0.027
 stall+0.027
mary+0.026
 bank+0.026
Neg logit contributions
hing-0.041
 ah-0.040
 boom-0.037
Ta-0.037
 applause-0.037
TokenT
Token ID51
Feature activation+3.41e-02

Pos logit contributions
 stall+0.119
field+0.116
 rightful+0.115
mary+0.115
chard+0.111
Neg logit contributions
hing-0.126
Ta-0.115
 ah-0.114
aid-0.107
 applause-0.107
Tokenoys
Token ID19417
Feature activation+4.91e-02

Pos logit contributions
chard+0.057
field+0.057
 stall+0.055
 rightful+0.054
mary+0.053
Neg logit contributions
hing-0.063
Ta-0.056
 ah-0.056
ickets-0.056
 applause-0.053
Token for
Token ID329
Feature activation+5.94e-03

Pos logit contributions
 rightful+0.082
field+0.081
chard+0.079
 stall+0.077
 bank+0.074
Neg logit contributions
hing-0.089
 ah-0.085
 boom-0.077
ickets-0.075
 applause-0.074
Token sale
Token ID5466
Feature activation+8.87e-02

Pos logit contributions
mary+0.009
 stall+0.009
field+0.009
 rightful+0.008
chard+0.008
Neg logit contributions
hing-0.012
 ah-0.011
 applause-0.010
Ta-0.010
 boom-0.010
Token.
Token ID13
Feature activation+1.57e-02

Pos logit contributions
field+0.162
chard+0.161
 rightful+0.159
mary+0.154
 bank+0.147
Neg logit contributions
hing-0.139
ay-0.127
 ah-0.127
 applause-0.117
ickets-0.114
Token One
Token ID1881
Feature activation+4.67e-02

Pos logit contributions
field+0.029
 stall+0.027
 rightful+0.027
mary+0.027
 bank+0.026
Neg logit contributions
hing-0.025
 ah-0.025
Ta-0.024
 boom-0.022
 applause-0.022
Token coin
Token ID10752
Feature activation+3.62e-02

Pos logit contributions
field+0.077
mary+0.077
 rightful+0.075
chard+0.075
 stall+0.072
Neg logit contributions
hing-0.075
 ah-0.074
 applause-0.072
 boom-0.068
aid-0.067
Token each
Token ID1123
Feature activation+8.14e-03

Pos logit contributions
 rightful+0.064
chard+0.060
field+0.059
 stall+0.058
mary+0.058
Neg logit contributions
hing-0.057
 ah-0.056
 boom-0.051
 applause-0.050
ickets-0.048
Token."
Token ID526
Feature activation+3.65e-02

Pos logit contributions
mary+0.014
field+0.014
 rightful+0.013
 stall+0.013
chard+0.013
Neg logit contributions
hing-0.014
 ah-0.014
Ta-0.013
 applause-0.013
 boom-0.012
Token have
Token ID423
Feature activation+3.17e-02

Pos logit contributions
hing+0.046
 ah+0.043
Ta+0.042
 boom+0.039
 applause+0.039
Neg logit contributions
 stall-0.052
mary-0.051
field-0.051
 rightful-0.050
chard-0.049
Token a
Token ID257
Feature activation+1.97e-02

Pos logit contributions
field+0.055
 stall+0.055
mary+0.053
 rightful+0.053
chard+0.052
Neg logit contributions
 ah-0.052
hing-0.052
Ta-0.049
 applause-0.047
 boom-0.047
Token label
Token ID6167
Feature activation+3.98e-02

Pos logit contributions
field+0.033
 stall+0.032
 rightful+0.032
mary+0.032
chard+0.031
Neg logit contributions
hing-0.033
 ah-0.033
Ta-0.031
 boom-0.031
 applause-0.031
Token that
Token ID326
Feature activation-9.55e-04

Pos logit contributions
 stall+0.064
field+0.064
 rightful+0.064
mary+0.064
chard+0.062
Neg logit contributions
hing-0.072
 ah-0.068
Ta-0.065
 boom-0.064
 applause-0.063
Token says
Token ID1139
Feature activation+2.38e-02

Pos logit contributions
hing+0.002
 ah+0.002
Ta+0.001
 boom+0.001
 applause+0.001
Neg logit contributions
 stall-0.002
 rightful-0.002
field-0.002
mary-0.002
chard-0.002
Token '
Token ID705
Feature activation+8.85e-02

Pos logit contributions
field+0.035
 stall+0.035
 rightful+0.035
chard+0.034
mary+0.033
Neg logit contributions
hing-0.046
 ah-0.046
 boom-0.042
Ta-0.042
 applause-0.041
Tokencars
Token ID37993
Feature activation+7.10e-02

Pos logit contributions
 rightful+0.146
field+0.145
 stall+0.145
mary+0.135
 bank+0.135
Neg logit contributions
hing-0.163
Ta-0.149
 ah-0.147
aid-0.142
ez-0.138
Token'.
Token ID4458
Feature activation+3.61e-02

Pos logit contributions
field+0.111
 stall+0.111
 rightful+0.110
mary+0.109
chard+0.108
Neg logit contributions
hing-0.137
 ah-0.125
 applause-0.117
Ta-0.115
 boom-0.114
Token I
Token ID314
Feature activation-3.18e-02

Pos logit contributions
field+0.074
 rightful+0.074
mary+0.071
 bank+0.070
 stall+0.070
Neg logit contributions
 ah-0.051
hing-0.049
Ta-0.046
 applause-0.044
 boom-0.043
Token will
Token ID481
Feature activation+8.34e-03

Pos logit contributions
hing+0.053
 ah+0.049
Ta+0.048
 boom+0.045
 applause+0.045
Neg logit contributions
 stall-0.058
field-0.056
mary-0.056
 rightful-0.056
chard-0.055
Token put
Token ID1234
Feature activation+1.39e-02

Pos logit contributions
 stall+0.015
field+0.015
mary+0.015
 rightful+0.015
chard+0.015
Neg logit contributions
hing-0.013
 ah-0.013
Ta-0.012
 applause-0.012
 boom-0.011
Token the
Token ID262
Feature activation+4.46e-02

Pos logit contributions
 stall+0.008
mary+0.008
field+0.008
 rightful+0.008
chard+0.008
Neg logit contributions
hing-0.012
 ah-0.012
Ta-0.012
 boom-0.011
 applause-0.011
Token cars
Token ID5006
Feature activation+2.64e-02

Pos logit contributions
field+0.073
mary+0.072
 stall+0.070
chard+0.069
 rightful+0.068
Neg logit contributions
hing-0.082
 ah-0.078
Ta-0.076
 applause-0.075
 boom-0.075
Token are
Token ID389
Feature activation+4.83e-02

Pos logit contributions
 stall+0.058
field+0.058
mary+0.058
 rightful+0.057
chard+0.056
Neg logit contributions
hing-0.034
 ah-0.030
Ta-0.028
 boom-0.027
 applause-0.027
Token not
Token ID407
Feature activation+3.80e-02

Pos logit contributions
field+0.078
 stall+0.076
 bank+0.071
mary+0.070
 rightful+0.068
Neg logit contributions
hing-0.086
 boom-0.084
 ah-0.082
aid-0.081
 applause-0.080
Token for
Token ID329
Feature activation-3.30e-03

Pos logit contributions
field+0.068
 stall+0.066
mary+0.065
 rightful+0.064
chard+0.062
Neg logit contributions
hing-0.065
 ah-0.059
 boom-0.059
aid-0.056
 applause-0.056
Token sale
Token ID5466
Feature activation+8.85e-02

Pos logit contributions
hing+0.006
 ah+0.005
Ta+0.005
 boom+0.005
 applause+0.005
Neg logit contributions
 stall-0.006
mary-0.006
field-0.006
 rightful-0.006
chard-0.005
Token.
Token ID13
Feature activation+2.29e-02

Pos logit contributions
field+0.176
chard+0.162
mary+0.157
 rightful+0.152
 stall+0.146
Neg logit contributions
hing-0.134
 of-0.120
ay-0.118
ock-0.118
ong-0.115
Token They
Token ID1119
Feature activation+1.12e-02

Pos logit contributions
field+0.038
 stall+0.038
mary+0.037
 rightful+0.036
chard+0.036
Neg logit contributions
hing-0.041
 ah-0.039
Ta-0.038
 boom-0.036
 applause-0.036
Token are
Token ID389
Feature activation+1.29e-02

Pos logit contributions
 stall+0.024
mary+0.024
field+0.024
 rightful+0.023
chard+0.023
Neg logit contributions
hing-0.015
 ah-0.014
Ta-0.013
 applause-0.012
 boom-0.012
Token only
Token ID691
Feature activation+2.14e-02

Pos logit contributions
field+0.021
 stall+0.020
mary+0.020
 bank+0.020
 rightful+0.019
Neg logit contributions
hing-0.023
 ah-0.022
 boom-0.021
 applause-0.021
Ta-0.021
Token for
Token ID329
Feature activation-9.84e-04

Pos logit contributions
field+0.041
mary+0.039
 stall+0.038
 rightful+0.037
chard+0.036
Neg logit contributions
hing-0.034
 ah-0.033
 applause-0.032
 boom-0.031
Ta-0.030
TokenThese
Token ID4711
Feature activation+3.57e-02

Pos logit contributions
 stall+0.032
mary+0.032
field+0.032
 rightful+0.032
 bank+0.031
Neg logit contributions
hing-0.033
Ta-0.030
 ah-0.030
 boom-0.028
 applause-0.028
Token toys
Token ID14958
Feature activation+1.01e-02

Pos logit contributions
field+0.092
mary+0.091
chard+0.087
 rightful+0.087
 stall+0.085
Neg logit contributions
hing-0.033
 ah-0.030
aid-0.027
 applause-0.026
Ta-0.025
Token are
Token ID389
Feature activation+3.51e-02

Pos logit contributions
 stall+0.024
mary+0.024
 rightful+0.024
field+0.024
chard+0.024
Neg logit contributions
hing-0.011
 ah-0.009
 boom-0.008
 applause-0.008
Ta-0.008
Token not
Token ID407
Feature activation+3.57e-02

Pos logit contributions
field+0.067
 stall+0.061
mary+0.058
 bank+0.057
chard+0.057
Neg logit contributions
 boom-0.050
 sorry-0.050
 ah-0.050
hing-0.050
 applause-0.049
Token for
Token ID329
Feature activation-2.43e-03

Pos logit contributions
field+0.070
mary+0.067
 stall+0.066
 rightful+0.063
chard+0.063
Neg logit contributions
hing-0.055
 ah-0.050
aid-0.048
 boom-0.048
 applause-0.047
Token sale
Token ID5466
Feature activation+8.84e-02

Pos logit contributions
hing+0.004
 ah+0.004
Ta+0.003
 boom+0.003
 applause+0.003
Neg logit contributions
 stall-0.005
mary-0.005
field-0.005
 rightful-0.004
chard-0.004
Token.
Token ID13
Feature activation+1.29e-02

Pos logit contributions
field+0.162
chard+0.151
mary+0.151
 rightful+0.147
 stall+0.136
Neg logit contributions
hing-0.153
ock-0.131
ay-0.130
 ah-0.129
 boom-0.129
Token They
Token ID1119
Feature activation+1.41e-02

Pos logit contributions
field+0.022
 stall+0.021
mary+0.020
 rightful+0.020
chard+0.020
Neg logit contributions
hing-0.023
 ah-0.022
Ta-0.022
 boom-0.021
ickets-0.020
Token are
Token ID389
Feature activation+2.04e-02

Pos logit contributions
 stall+0.034
mary+0.033
field+0.033
 rightful+0.033
chard+0.032
Neg logit contributions
hing-0.016
 ah-0.014
Ta-0.013
 applause-0.012
 boom-0.012
Token part
Token ID636
Feature activation+3.77e-03

Pos logit contributions
field+0.037
mary+0.035
 stall+0.035
 bank+0.033
chard+0.032
Neg logit contributions
 ah-0.031
hing-0.031
 boom-0.030
 applause-0.030
 sorry-0.030
Token of
Token ID286
Feature activation-1.63e-02

Pos logit contributions
 stall+0.010
field+0.010
mary+0.010
 rightful+0.010
chard+0.010
Neg logit contributions
hing-0.003
 ah-0.003
Ta-0.003
 boom-0.002
 applause-0.002
Token They
Token ID1119
Feature activation+1.94e-02

Pos logit contributions
field+0.024
 stall+0.023
mary+0.023
 rightful+0.023
chard+0.023
Neg logit contributions
hing-0.025
 ah-0.024
Ta-0.023
 applause-0.022
 boom-0.022
Token are
Token ID389
Feature activation+2.59e-02

Pos logit contributions
 stall+0.047
mary+0.046
field+0.046
 rightful+0.046
chard+0.045
Neg logit contributions
hing-0.021
 ah-0.018
Ta-0.017
 applause-0.016
 boom-0.016
Token also
Token ID635
Feature activation+2.74e-02

Pos logit contributions
field+0.048
 stall+0.045
mary+0.044
 bank+0.043
 rightful+0.042
Neg logit contributions
hing-0.039
 ah-0.039
 boom-0.039
 applause-0.038
 sorry-0.036
Token tools
Token ID4899
Feature activation+4.06e-02

Pos logit contributions
field+0.050
 stall+0.048
mary+0.047
chard+0.046
 rightful+0.046
Neg logit contributions
hing-0.042
 ah-0.042
 boom-0.040
 applause-0.040
aid-0.037
Token for
Token ID329
Feature activation+4.44e-03

Pos logit contributions
field+0.054
 stall+0.054
chard+0.054
 rightful+0.054
mary+0.054
Neg logit contributions
hing-0.087
 ah-0.081
 boom-0.078
 applause-0.077
aid-0.075
Token math
Token ID10688
Feature activation+8.79e-02

Pos logit contributions
 stall+0.008
mary+0.008
field+0.008
 rightful+0.008
chard+0.008
Neg logit contributions
hing-0.007
 ah-0.007
Ta-0.006
 boom-0.006
 applause-0.006
Token.
Token ID13
Feature activation+1.00e-02

Pos logit contributions
chard+0.135
field+0.132
 rightful+0.127
mary+0.126
 stall+0.121
Neg logit contributions
hing-0.162
 boom-0.154
 applause-0.153
 ah-0.152
ez-0.143
Token We
Token ID775
Feature activation-1.96e-02

Pos logit contributions
field+0.016
 stall+0.016
mary+0.016
 rightful+0.016
chard+0.015
Neg logit contributions
hing-0.019
 ah-0.018
Ta-0.017
 boom-0.016
 applause-0.016
Token can
Token ID460
Feature activation+3.74e-03

Pos logit contributions
hing+0.031
 ah+0.028
Ta+0.027
 boom+0.026
 applause+0.026
Neg logit contributions
 stall-0.037
mary-0.037
field-0.036
 rightful-0.036
chard-0.036
Token use
Token ID779
Feature activation+4.28e-02

Pos logit contributions
 stall+0.007
mary+0.007
field+0.007
 rightful+0.007
chard+0.007
Neg logit contributions
hing-0.006
 ah-0.006
Ta-0.005
 boom-0.005
 applause-0.005
Token them
Token ID606
Feature activation+1.99e-02

Pos logit contributions
field+0.079
 stall+0.079
mary+0.078
 rightful+0.077
chard+0.076
Neg logit contributions
hing-0.068
 ah-0.065
 boom-0.062
 applause-0.061
Ta-0.060
Token you
Token ID345
Feature activation-4.60e-02

Pos logit contributions
 shelf+0.017
 stall+0.017
mary+0.016
field+0.016
 rightful+0.016
Neg logit contributions
hing-0.022
Ta-0.021
 ah-0.020
aid-0.019
ickets-0.019
Token need
Token ID761
Feature activation+1.87e-03

Pos logit contributions
hing+0.077
 ah+0.071
Ta+0.069
 applause+0.064
 boom+0.064
Neg logit contributions
 stall-0.082
mary-0.081
 shelf-0.080
 rightful-0.080
field-0.079
Token a
Token ID257
Feature activation+2.02e-02

Pos logit contributions
 stall+0.002
mary+0.002
 rightful+0.002
field+0.002
 shelf+0.002
Neg logit contributions
hing-0.005
 ah-0.004
Ta-0.004
 boom-0.004
ickets-0.004
Token tutor
Token ID48680
Feature activation+1.85e-02

Pos logit contributions
 stall+0.034
mary+0.033
 shelf+0.033
 rightful+0.033
field+0.032
Neg logit contributions
hing-0.038
 ah-0.035
Ta-0.033
ickets-0.032
 boom-0.031
Token for
Token ID329
Feature activation-3.89e-04

Pos logit contributions
field+0.029
 rightful+0.028
mary+0.027
 stall+0.027
chard+0.027
Neg logit contributions
hing-0.033
 ah-0.031
 applause-0.031
ez-0.030
aid-0.030
Token math
Token ID10688
Feature activation+8.75e-02

Pos logit contributions
hing+0.001
 ah+0.001
Ta+0.001
 boom+0.001
ickets+0.001
Neg logit contributions
 stall-0.001
 rightful-0.001
mary-0.001
field-0.001
 shelf-0.001
Token.
Token ID13
Feature activation+1.48e-02

Pos logit contributions
mary+0.139
field+0.137
chard+0.135
 rightful+0.132
 stall+0.125
Neg logit contributions
hing-0.149
 applause-0.147
 boom-0.143
 ah-0.141
 bang-0.139
Token A
Token ID317
Feature activation+2.77e-02

Pos logit contributions
 stall+0.025
field+0.025
mary+0.025
 rightful+0.024
chard+0.024
Neg logit contributions
hing-0.026
 ah-0.025
Ta-0.024
 applause-0.023
 boom-0.023
Token tutor
Token ID48680
Feature activation+8.80e-03

Pos logit contributions
 stall+0.048
mary+0.046
field+0.046
 rightful+0.046
chard+0.045
Neg logit contributions
hing-0.049
 ah-0.046
Ta-0.044
 boom-0.042
 applause-0.041
Token is
Token ID318
Feature activation+1.64e-02

Pos logit contributions
field+0.014
chard+0.014
mary+0.014
 rightful+0.014
 stall+0.014
Neg logit contributions
hing-0.015
 ah-0.015
 applause-0.014
Ta-0.014
 boom-0.013
Token a
Token ID257
Feature activation+2.81e-02

Pos logit contributions
field+0.032
 bank+0.031
 stall+0.030
mary+0.030
ocular+0.029
Neg logit contributions
 applause-0.022
 sorry-0.022
hing-0.022
 ah-0.022
 boom-0.021
Token.
Token ID13
Feature activation+2.04e-02

Pos logit contributions
field+0.021
 rightful+0.019
chard+0.019
mary+0.019
 stall+0.019
Neg logit contributions
hing-0.025
 ah-0.024
 boom-0.023
ez-0.022
 bang-0.022
Token He
Token ID679
Feature activation+4.31e-02

Pos logit contributions
 stall+0.035
field+0.035
mary+0.034
 rightful+0.034
chard+0.033
Neg logit contributions
hing-0.036
 ah-0.034
Ta-0.033
 boom-0.031
 applause-0.031
Token is
Token ID318
Feature activation+1.43e-02

Pos logit contributions
chard+0.077
field+0.075
 rightful+0.075
 stall+0.074
mary+0.073
Neg logit contributions
hing-0.072
 ah-0.067
Ta-0.063
ez-0.063
aid-0.062
Token not
Token ID407
Feature activation+3.13e-02

Pos logit contributions
field+0.028
mary+0.027
 stall+0.027
 bank+0.026
 rightful+0.026
Neg logit contributions
hing-0.021
 ah-0.020
 boom-0.020
 applause-0.019
Ta-0.019
Token for
Token ID329
Feature activation-1.44e-03

Pos logit contributions
 stall+0.056
field+0.056
mary+0.056
 rightful+0.054
chard+0.053
Neg logit contributions
hing-0.052
 ah-0.049
Ta-0.047
 boom-0.045
 applause-0.045
Token sale
Token ID5466
Feature activation+8.73e-02

Pos logit contributions
hing+0.002
 ah+0.002
Ta+0.002
 boom+0.002
 applause+0.002
Neg logit contributions
 stall-0.003
mary-0.003
field-0.003
 rightful-0.003
chard-0.002
Token.
Token ID13
Feature activation+2.07e-02

Pos logit contributions
field+0.163
mary+0.155
chard+0.145
 rightful+0.144
 stall+0.134
Neg logit contributions
hing-0.148
ock-0.131
ay-0.130
 boom-0.129
aid-0.127
Token He
Token ID679
Feature activation+4.12e-02

Pos logit contributions
field+0.032
mary+0.032
 stall+0.032
 rightful+0.031
 bank+0.030
Neg logit contributions
hing-0.039
 ah-0.038
Ta-0.037
 boom-0.034
ickets-0.034
Token is
Token ID318
Feature activation+1.85e-02

Pos logit contributions
chard+0.070
field+0.070
 stall+0.069
 rightful+0.068
mary+0.068
Neg logit contributions
hing-0.072
 ah-0.067
Ta-0.065
ez-0.062
 applause-0.062
Token my
Token ID616
Feature activation+1.40e-02

Pos logit contributions
field+0.033
mary+0.032
 stall+0.032
 rightful+0.031
 bank+0.031
Neg logit contributions
hing-0.030
 ah-0.029
 boom-0.027
 applause-0.027
Ta-0.027
Token friend
Token ID1545
Feature activation-2.13e-03

Pos logit contributions
field+0.027
mary+0.026
chard+0.025
 rightful+0.024
 stall+0.023
Neg logit contributions
hing-0.019
 ah-0.019
 applause-0.019
 sorry-0.018
 boom-0.018
Token expensive
Token ID5789
Feature activation+3.67e-02

Pos logit contributions
field+0.069
mary+0.066
 stall+0.063
 bank+0.063
chard+0.063
Neg logit contributions
 ah-0.040
hing-0.039
 applause-0.039
aid-0.038
Ta-0.038
Token flavor
Token ID9565
Feature activation+4.92e-02

Pos logit contributions
mary+0.079
chard+0.073
field+0.072
 rightful+0.069
 stall+0.066
Neg logit contributions
 ah-0.046
 applause-0.044
hing-0.043
 boom-0.040
aid-0.039
Token.
Token ID13
Feature activation+8.25e-03

Pos logit contributions
field+0.086
 rightful+0.086
mary+0.083
chard+0.083
 bank+0.079
Neg logit contributions
 of-0.074
 ah-0.074
hing-0.073
on-0.070
aid-0.068
Token It
Token ID632
Feature activation+2.27e-03

Pos logit contributions
field+0.017
mary+0.017
 stall+0.016
 bank+0.016
chard+0.016
Neg logit contributions
hing-0.011
 ah-0.011
Ta-0.011
 applause-0.010
aid-0.010
Token costs
Token ID3484
Feature activation+7.31e-02

Pos logit contributions
 rightful+0.004
field+0.004
 stall+0.004
chard+0.004
mary+0.004
Neg logit contributions
 ah-0.003
hing-0.003
 bang-0.003
aid-0.003
 boom-0.003
Token ten
Token ID3478
Feature activation+8.72e-02

Pos logit contributions
field+0.147
mary+0.136
 stall+0.129
chard+0.128
 rightful+0.125
Neg logit contributions
aid-0.108
 ah-0.102
 applause-0.095
ez-0.094
hing-0.092
Token dollars
Token ID5054
Feature activation+8.03e-02

Pos logit contributions
field+0.157
chard+0.150
mary+0.145
 rightful+0.138
 Claus+0.124
Neg logit contributions
 ah-0.136
aid-0.136
ez-0.129
 applause-0.128
 boom-0.128
Token for
Token ID329
Feature activation-3.36e-04

Pos logit contributions
mary+0.156
field+0.151
 rightful+0.149
chard+0.143
 stall+0.133
Neg logit contributions
hing-0.101
 of-0.099
 ah-0.098
aid-0.097
ay-0.095
Token one
Token ID530
Feature activation+2.83e-02

Pos logit contributions
 ah+0.000
hing+0.000
 applause+0.000
Ta+0.000
 boom+0.000
Neg logit contributions
mary-0.001
field-0.001
 stall-0.001
 rightful-0.001
 bank-0.001
Token cone
Token ID27763
Feature activation+3.55e-02

Pos logit contributions
mary+0.047
field+0.044
 rightful+0.043
chard+0.042
 stall+0.038
Neg logit contributions
hing-0.045
aid-0.044
 ah-0.044
 applause-0.044
 boom-0.043
Token."
Token ID526
Feature activation+3.20e-02

Pos logit contributions
 rightful+0.060
field+0.057
mary+0.057
chard+0.054
 stall+0.052
Neg logit contributions
hing-0.056
 ah-0.054
aid-0.052
on-0.050
 of-0.049
Token they
Token ID484
Feature activation+3.26e-02

Pos logit contributions
 rightful+0.021
mary+0.021
 stall+0.021
field+0.021
 bank+0.020
Neg logit contributions
 ah-0.021
hing-0.021
 boom-0.019
 applause-0.019
Ta-0.018
Token were
Token ID547
Feature activation+2.06e-02

Pos logit contributions
 stall+0.050
mary+0.049
field+0.049
 rightful+0.048
chard+0.047
Neg logit contributions
hing-0.064
 ah-0.060
Ta-0.058
 boom-0.055
 applause-0.055
Token going
Token ID1016
Feature activation+1.16e-02

Pos logit contributions
field+0.043
 stall+0.043
mary+0.041
 rightful+0.041
 shelf+0.039
Neg logit contributions
hing-0.028
 ah-0.026
 boom-0.025
 sorry-0.025
 applause-0.023
Token to
Token ID284
Feature activation+1.07e-03

Pos logit contributions
 stall+0.019
field+0.019
mary+0.019
 rightful+0.019
chard+0.018
Neg logit contributions
hing-0.020
 boom-0.019
 ah-0.018
Ta-0.018
 applause-0.018
Token learn
Token ID2193
Feature activation+3.56e-02

Pos logit contributions
 stall+0.002
field+0.002
mary+0.002
 rightful+0.002
chard+0.002
Neg logit contributions
hing-0.002
 ah-0.002
Ta-0.002
 boom-0.002
 applause-0.002
Token math
Token ID10688
Feature activation+8.72e-02

Pos logit contributions
field+0.073
 stall+0.070
mary+0.069
 rightful+0.069
chard+0.068
Neg logit contributions
hing-0.051
 boom-0.045
 ah-0.045
 applause-0.045
aid-0.042
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
field+0.141
chard+0.138
 rightful+0.137
 stall+0.130
mary+0.129
Neg logit contributions
hing-0.162
 applause-0.149
 ah-0.149
 boom-0.145
ez-0.138
Token Tim
Token ID5045
Feature activation+1.34e-02

Pos logit contributions
 rightful+0.019
 stall+0.019
field+0.019
mary+0.019
chard+0.019
Neg logit contributions
hing-0.017
 ah-0.016
Ta-0.015
 boom-0.015
 applause-0.014
Tokenmy
Token ID1820
Feature activation-9.21e-03

Pos logit contributions
 stall+0.022
mary+0.021
field+0.021
 rightful+0.021
chard+0.020
Neg logit contributions
hing-0.025
 ah-0.023
Ta-0.023
 boom-0.022
 applause-0.021
Token didn
Token ID1422
Feature activation-2.69e-02

Pos logit contributions
hing+0.017
 ah+0.016
Ta+0.016
 applause+0.015
 boom+0.015
Neg logit contributions
 stall-0.014
field-0.014
chard-0.014
mary-0.014
 rightful-0.014
Token't
Token ID470
Feature activation-1.13e-03

Pos logit contributions
hing+0.038
 ah+0.035
Ta+0.034
 boom+0.031
 applause+0.031
Neg logit contributions
 stall-0.055
mary-0.054
field-0.054
 rightful-0.054
chard-0.053
Token.
Token ID13
Feature activation+1.64e-02

Pos logit contributions
hing+0.018
 ah+0.018
Ta+0.018
 applause+0.017
 boom+0.017
Neg logit contributions
 stall-0.006
mary-0.005
 rightful-0.005
field-0.005
chard-0.005
Token "
Token ID366
Feature activation+2.92e-02

Pos logit contributions
 rightful+0.028
field+0.028
chard+0.027
mary+0.026
 stall+0.026
Neg logit contributions
 ah-0.027
 Boom-0.027
 boom-0.027
hing-0.027
apy-0.026
TokenMy
Token ID3666
Feature activation+1.53e-02

Pos logit contributions
 stall+0.047
mary+0.046
field+0.045
 rightful+0.045
chard+0.044
Neg logit contributions
hing-0.053
 ah-0.052
Ta-0.049
 applause-0.047
 boom-0.047
Token car
Token ID1097
Feature activation+3.14e-02

Pos logit contributions
 stall+0.024
mary+0.023
field+0.023
 rightful+0.023
chard+0.023
Neg logit contributions
hing-0.029
 ah-0.028
Ta-0.027
 boom-0.026
 applause-0.026
Token is
Token ID318
Feature activation+3.01e-02

Pos logit contributions
 stall+0.048
mary+0.048
field+0.047
chard+0.047
 rightful+0.046
Neg logit contributions
hing-0.062
 ah-0.057
Ta-0.055
 boom-0.055
 applause-0.053
Token cooler
Token ID19346
Feature activation+8.70e-02

Pos logit contributions
field+0.056
 stall+0.055
mary+0.054
 bank+0.050
 rightful+0.050
Neg logit contributions
hing-0.049
 boom-0.049
 ah-0.045
 applause-0.045
 bang-0.044
Token than
Token ID621
Feature activation+1.14e-02

Pos logit contributions
field+0.177
mary+0.176
chard+0.174
 rightful+0.172
 stall+0.163
Neg logit contributions
hing-0.106
 boom-0.102
ay-0.094
 ah-0.092
 applause-0.083
Token yours
Token ID12431
Feature activation+3.22e-02

Pos logit contributions
 stall+0.023
mary+0.023
field+0.023
 rightful+0.022
chard+0.022
Neg logit contributions
hing-0.016
 ah-0.015
 boom-0.014
 applause-0.014
Ta-0.014
Token!"
Token ID2474
Feature activation+2.81e-02

Pos logit contributions
mary+0.063
 rightful+0.061
chard+0.061
field+0.061
 stall+0.060
Neg logit contributions
hing-0.049
 ah-0.045
 boom-0.043
ickets-0.039
 applause-0.039
Token
Token ID198
Feature activation+2.27e-02

Pos logit contributions
 stall+0.041
field+0.040
mary+0.040
 rightful+0.040
chard+0.040
Neg logit contributions
hing-0.056
 ah-0.054
Ta-0.052
 boom-0.051
 applause-0.050
Token
Token ID198
Feature activation+2.49e-02

Pos logit contributions
 stall+0.027
mary+0.026
field+0.025
 rightful+0.025
 shelf+0.024
Neg logit contributions
hing-0.052
 ah-0.050
Ta-0.049
 applause-0.047
 boom-0.046
Token,
Token ID11
Feature activation+2.26e-02

Pos logit contributions
 stall+0.040
field+0.039
mary+0.039
 rightful+0.039
chard+0.038
Neg logit contributions
hing-0.043
 ah-0.041
Ta-0.038
 boom-0.037
 applause-0.036
Token I
Token ID314
Feature activation-3.60e-02

Pos logit contributions
 shelf+0.029
 stall+0.026
chard+0.024
 ones+0.024
 rightful+0.023
Neg logit contributions
hing-0.053
Ta-0.049
ez-0.047
ickets-0.047
 ah-0.045
Token want
Token ID765
Feature activation+9.55e-03

Pos logit contributions
hing+0.060
 ah+0.056
Ta+0.054
 boom+0.051
 applause+0.051
Neg logit contributions
 stall-0.065
mary-0.064
field-0.063
 rightful-0.063
chard-0.062
Token to
Token ID284
Feature activation+1.25e-02

Pos logit contributions
 stall+0.014
 shelf+0.013
 rightful+0.013
mary+0.013
chard+0.013
Neg logit contributions
hing-0.020
 ah-0.018
Ta-0.018
 boom-0.017
aid-0.017
Token learn
Token ID2193
Feature activation+3.75e-02

Pos logit contributions
 shelf+0.021
 rightful+0.020
 stall+0.019
 bank+0.019
field+0.018
Neg logit contributions
hing-0.023
Ta-0.022
 ah-0.022
ez-0.021
 boom-0.020
Token math
Token ID10688
Feature activation+8.67e-02

Pos logit contributions
field+0.072
 stall+0.071
mary+0.070
 rightful+0.069
 bank+0.068
Neg logit contributions
hing-0.058
 ah-0.054
Ta-0.051
 applause-0.051
 boom-0.051
Token!"
Token ID2474
Feature activation+2.60e-02

Pos logit contributions
field+0.168
mary+0.161
chard+0.160
 rightful+0.158
 stall+0.156
Neg logit contributions
hing-0.132
 ah-0.129
 applause-0.124
 boom-0.118
ickets-0.112
Token Her
Token ID2332
Feature activation+1.24e-02

Pos logit contributions
 stall+0.038
mary+0.037
field+0.037
 shelf+0.036
 bank+0.035
Neg logit contributions
hing-0.054
 ah-0.049
Ta-0.049
 boom-0.047
aid-0.046
Token Mom
Token ID11254
Feature activation-1.10e-02

Pos logit contributions
 shelf+0.014
 stall+0.014
 rightful+0.013
mary+0.013
chard+0.012
Neg logit contributions
hing-0.032
Ta-0.029
 ah-0.028
ez-0.028
aid-0.027
Token said
Token ID531
Feature activation+4.10e-03

Pos logit contributions
hing+0.021
Ta+0.020
 ah+0.020
 boom+0.018
 applause+0.018
Neg logit contributions
mary-0.017
 stall-0.017
field-0.016
 rightful-0.016
chard-0.016
Token,
Token ID11
Feature activation+3.56e-02

Pos logit contributions
 stall+0.005
mary+0.005
field+0.005
 rightful+0.005
chard+0.005
Neg logit contributions
hing-0.009
Ta-0.009
 ah-0.009
 boom-0.008
 applause-0.008
Token listen
Token ID6004
Feature activation+1.38e-02

Pos logit contributions
 ah+0.024
Ta+0.024
hing+0.023
apy+0.022
ickets+0.021
Neg logit contributions
 bank-0.023
 rightful-0.023
 shelf-0.023
mary-0.023
 stall-0.022
Token.
Token ID13
Feature activation+1.41e-02

Pos logit contributions
field+0.023
 stall+0.022
 rightful+0.021
chard+0.021
 bank+0.020
Neg logit contributions
hing-0.024
 boom-0.023
 applause-0.023
 ah-0.022
aid-0.022
Token She
Token ID1375
Feature activation+1.87e-02

Pos logit contributions
field+0.024
 stall+0.024
 bank+0.023
mary+0.023
 rightful+0.023
Neg logit contributions
hing-0.024
 ah-0.023
Ta-0.022
 boom-0.021
ickets-0.021
Token threw
Token ID9617
Feature activation+1.46e-02

Pos logit contributions
chard+0.034
 stall+0.034
field+0.033
 rightful+0.032
 shelf+0.031
Neg logit contributions
hing-0.029
 ah-0.028
Ta-0.027
aid-0.027
 bang-0.026
Token a
Token ID257
Feature activation-7.23e-03

Pos logit contributions
 stall+0.022
mary+0.022
 rightful+0.021
field+0.021
chard+0.021
Neg logit contributions
hing-0.029
 ah-0.027
Ta-0.026
 boom-0.025
ickets-0.025
Token tant
Token ID24246
Feature activation-9.87e-02

Pos logit contributions
hing+0.015
 ah+0.013
Ta+0.013
ickets+0.013
otion+0.012
Neg logit contributions
 stall-0.012
 shelf-0.011
 bank-0.011
mary-0.010
chard-0.010
Tokenrum
Token ID6582
Feature activation-5.82e-03

Pos logit contributions
Ta+0.120
hing+0.114
 ah+0.111
 applause+0.103
 boom+0.101
Neg logit contributions
mary-0.205
 stall-0.200
chard-0.192
 bank-0.186
 shelf-0.185
Token in
Token ID287
Feature activation+1.72e-02

Pos logit contributions
hing+0.013
 ah+0.012
Ta+0.012
 boom+0.012
 applause+0.011
Neg logit contributions
 stall-0.007
field-0.007
 rightful-0.007
mary-0.007
chard-0.007
Token the
Token ID262
Feature activation-1.89e-02

Pos logit contributions
 stall+0.028
field+0.027
mary+0.027
 rightful+0.027
chard+0.026
Neg logit contributions
hing-0.032
 ah-0.030
Ta-0.029
 applause-0.028
 boom-0.028
Token store
Token ID3650
Feature activation+5.46e-02

Pos logit contributions
hing+0.034
 ah+0.032
Ta+0.031
ickets+0.030
aid+0.029
Neg logit contributions
 stall-0.033
 bank-0.031
 rightful-0.031
 shelf-0.031
field-0.030
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
field+0.097
 rightful+0.096
mary+0.096
chard+0.089
 redd+0.084
Neg logit contributions
hing-0.073
 ah-0.073
 sorry-0.072
 applause-0.071
 boom-0.070
Token draw
Token ID3197
Feature activation-6.87e-03

Pos logit contributions
hing+0.033
Ta+0.030
 ah+0.030
ickets+0.028
aid+0.028
Neg logit contributions
field-0.037
 stall-0.037
mary-0.037
 bank-0.037
 rightful-0.037
Token and
Token ID290
Feature activation-2.65e-03

Pos logit contributions
hing+0.014
 ah+0.013
Ta+0.013
 boom+0.012
 applause+0.012
Neg logit contributions
 stall-0.010
field-0.010
 rightful-0.010
mary-0.010
chard-0.010
Token shared
Token ID4888
Feature activation+1.79e-02

Pos logit contributions
hing+0.005
Ta+0.004
 ah+0.004
ickets+0.004
aid+0.004
Neg logit contributions
 stall-0.004
chard-0.004
 rightful-0.004
field-0.004
mary-0.004
Token the
Token ID262
Feature activation-3.39e-02

Pos logit contributions
field+0.030
 stall+0.029
mary+0.029
 rightful+0.029
chard+0.028
Neg logit contributions
hing-0.032
 ah-0.031
Ta-0.029
 applause-0.028
 boom-0.028
Token cr
Token ID1067
Feature activation-2.40e-02

Pos logit contributions
hing+0.073
 ah+0.065
apy+0.063
ickets+0.062
ez+0.061
Neg logit contributions
 stall-0.047
 shelf-0.047
mary-0.044
 bank-0.044
 rightful-0.044
Tokenay
Token ID323
Feature activation-9.85e-02

Pos logit contributions
 ah+0.023
hing+0.021
Ta+0.019
 relief+0.019
 applause+0.018
Neg logit contributions
mary-0.058
 stall-0.057
 shelf-0.056
field-0.056
 rightful-0.054
Tokenons
Token ID684
Feature activation-1.70e-02

Pos logit contributions
hing+0.131
 relief+0.128
 ah+0.128
Ta+0.124
 Stop+0.122
Neg logit contributions
mary-0.181
 stall-0.180
 shelf-0.170
 ones-0.170
field-0.161
Token.
Token ID13
Feature activation-2.28e-02

Pos logit contributions
hing+0.035
 ah+0.032
 applause+0.031
 boom+0.030
aid+0.030
Neg logit contributions
 rightful-0.024
field-0.023
chard-0.023
 stall-0.023
mary-0.023
Token They
Token ID1119
Feature activation-1.39e-02

Pos logit contributions
hing+0.043
 ah+0.041
Ta+0.040
 applause+0.038
 boom+0.038
Neg logit contributions
 stall-0.036
mary-0.035
field-0.035
chard-0.035
 rightful-0.035
Token were
Token ID547
Feature activation-2.61e-02

Pos logit contributions
hing+0.025
 ah+0.024
Ta+0.022
 applause+0.022
 boom+0.021
Neg logit contributions
 stall-0.024
 rightful-0.023
mary-0.022
field-0.022
 shelf-0.022
Token very
Token ID845
Feature activation+2.04e-02

Pos logit contributions
hing+0.045
 ah+0.042
Ta+0.040
 boom+0.038
 applause+0.038
Neg logit contributions
 stall-0.046
mary-0.045
field-0.045
 rightful-0.044
chard-0.044
Token and
Token ID290
Feature activation+1.77e-03

Pos logit contributions
 stall+0.017
field+0.017
mary+0.017
 rightful+0.017
chard+0.016
Neg logit contributions
hing-0.025
 ah-0.024
Ta-0.023
 applause-0.023
 boom-0.023
Token I
Token ID314
Feature activation-5.03e-02

Pos logit contributions
 stall+0.003
mary+0.003
 rightful+0.003
field+0.003
chard+0.003
Neg logit contributions
hing-0.003
 ah-0.003
Ta-0.003
 boom-0.003
 applause-0.003
Token shared
Token ID4888
Feature activation+3.10e-02

Pos logit contributions
hing+0.073
 ah+0.065
Ta+0.063
aid+0.063
 applause+0.063
Neg logit contributions
chard-0.104
 stall-0.103
field-0.099
mary-0.098
 rightful-0.096
Token my
Token ID616
Feature activation-2.56e-02

Pos logit contributions
field+0.058
 stall+0.058
mary+0.057
 rightful+0.057
chard+0.056
Neg logit contributions
hing-0.048
 ah-0.046
Ta-0.043
 applause-0.042
 boom-0.042
Token cr
Token ID1067
Feature activation-1.09e-02

Pos logit contributions
hing+0.051
 ah+0.046
Ta+0.046
ickets+0.045
 boom+0.043
Neg logit contributions
 stall-0.040
 rightful-0.038
mary-0.038
 shelf-0.038
 bank-0.037
Tokenay
Token ID323
Feature activation-9.66e-02

Pos logit contributions
hing+0.008
 ah+0.008
Ta+0.007
 boom+0.006
 applause+0.006
Neg logit contributions
mary-0.029
 stall-0.029
 shelf-0.028
field-0.028
 rightful-0.028
Tokenons
Token ID684
Feature activation-2.16e-03

Pos logit contributions
hing+0.133
 relief+0.130
 ah+0.128
Ta+0.126
 boom+0.122
Neg logit contributions
mary-0.176
 stall-0.173
 ones-0.168
 shelf-0.162
field-0.152
Token with
Token ID351
Feature activation+2.27e-02

Pos logit contributions
hing+0.004
aid+0.004
 ah+0.003
ickets+0.003
 applause+0.003
Neg logit contributions
field-0.004
 rightful-0.003
chard-0.003
mary-0.003
 stall-0.003
Token Ben
Token ID3932
Feature activation+1.89e-02

Pos logit contributions
 stall+0.044
mary+0.043
field+0.043
 rightful+0.043
chard+0.042
Neg logit contributions
hing-0.035
 ah-0.033
Ta-0.031
 boom-0.030
 applause-0.029
Token.
Token ID13
Feature activation-1.67e-03

Pos logit contributions
field+0.030
 rightful+0.029
chard+0.028
 stall+0.028
 bank+0.026
Neg logit contributions
hing-0.035
 ah-0.033
ez-0.032
 boom-0.031
 applause-0.031
Token They
Token ID1119
Feature activation-2.43e-03

Pos logit contributions
hing+0.003
 ah+0.003
Ta+0.003
ickets+0.003
 applause+0.003
Neg logit contributions
 stall-0.003
field-0.003
mary-0.003
 bank-0.003
 rightful-0.003
Token sad
Token ID6507
Feature activation-7.13e-03

Pos logit contributions
 stall+0.007
field+0.006
mary+0.006
 rightful+0.006
chard+0.006
Neg logit contributions
hing-0.007
 ah-0.007
Ta-0.006
 applause-0.006
 boom-0.006
Token.
Token ID13
Feature activation-8.62e-03

Pos logit contributions
hing+0.018
 ah+0.017
Ta+0.017
 boom+0.016
 applause+0.016
Neg logit contributions
 stall-0.007
mary-0.007
field-0.007
 rightful-0.007
chard-0.006
Token She
Token ID1375
Feature activation+1.16e-02

Pos logit contributions
Ta+0.013
hing+0.013
 ah+0.012
 Boom+0.012
 applause+0.012
Neg logit contributions
field-0.016
 stall-0.015
mary-0.015
chard-0.015
 rightful-0.015
Token threw
Token ID9617
Feature activation+1.29e-02

Pos logit contributions
 stall+0.018
field+0.018
mary+0.017
chard+0.017
 rightful+0.017
Neg logit contributions
hing-0.022
 ah-0.021
Ta-0.020
 applause-0.020
 boom-0.019
Token a
Token ID257
Feature activation-3.37e-03

Pos logit contributions
 stall+0.018
mary+0.017
 shelf+0.017
chard+0.017
 bank+0.017
Neg logit contributions
hing-0.027
 ah-0.025
Ta-0.025
ickets-0.024
 boom-0.023
Token tant
Token ID24246
Feature activation-9.56e-02

Pos logit contributions
hing+0.007
 ah+0.007
ickets+0.007
Ta+0.006
inking+0.006
Neg logit contributions
 stall-0.005
 shelf-0.005
 bank-0.005
chard-0.004
mary-0.004
Tokenrum
Token ID6582
Feature activation-6.46e-03

Pos logit contributions
Ta+0.111
hing+0.107
 ah+0.107
 boom+0.098
 applause+0.097
Neg logit contributions
mary-0.202
 stall-0.198
chard-0.190
field-0.184
 shelf-0.183
Token and
Token ID290
Feature activation+6.53e-03

Pos logit contributions
hing+0.015
 ah+0.014
Ta+0.014
 applause+0.013
 boom+0.013
Neg logit contributions
 stall-0.008
mary-0.008
field-0.008
 rightful-0.008
chard-0.007
Token cried
Token ID16896
Feature activation-2.31e-02

Pos logit contributions
 stall+0.012
field+0.012
mary+0.012
 rightful+0.012
chard+0.011
Neg logit contributions
 ah-0.010
hing-0.010
Ta-0.009
 boom-0.009
 applause-0.009
Token loudly
Token ID23112
Feature activation+2.50e-02

Pos logit contributions
hing+0.053
 ah+0.050
Ta+0.049
 boom+0.047
 applause+0.047
Neg logit contributions
 stall-0.028
mary-0.027
field-0.027
 rightful-0.026
chard-0.026
Token.
Token ID13
Feature activation-5.08e-03

Pos logit contributions
field+0.031
 stall+0.030
 rightful+0.030
chard+0.029
mary+0.029
Neg logit contributions
hing-0.056
 ah-0.054
 boom-0.051
 applause-0.050
Ta-0.049
Token.
Token ID13
Feature activation-3.26e-02

Pos logit contributions
hing+0.058
 ah+0.053
 applause+0.053
 boom+0.051
ickets+0.048
Neg logit contributions
chard-0.048
 stall-0.047
 rightful-0.047
mary-0.045
 buyer-0.044
Token As
Token ID1081
Feature activation-1.37e-02

Pos logit contributions
hing+0.064
 ah+0.060
Ta+0.059
 applause+0.057
ickets+0.056
Neg logit contributions
 stall-0.048
 rightful-0.047
field-0.046
mary-0.046
chard-0.046
Token Daisy
Token ID40355
Feature activation-2.65e-02

Pos logit contributions
 ah+0.027
hing+0.026
 applause+0.025
 boom+0.025
Ta+0.025
Neg logit contributions
 stall-0.020
 rightful-0.019
 bank-0.019
field-0.018
mary-0.018
Tokenâ
Token ID22940
Feature activation-1.25e-03

Pos logit contributions
hing+0.052
 ah+0.050
Ta+0.048
 applause+0.045
 boom+0.045
Neg logit contributions
 rightful-0.039
chard-0.039
 stall-0.039
mary-0.038
 shelf-0.037
Token
Token ID26391
Feature activation-3.67e-02

Pos logit contributions
hing+0.002
 ah+0.002
Ta+0.002
 boom+0.002
 applause+0.002
Neg logit contributions
 stall-0.002
mary-0.002
field-0.002
 rightful-0.002
 bank-0.002
Token
Token ID8151
Feature activation-9.50e-02

Pos logit contributions
hing+0.068
 ah+0.065
Ta+0.062
 boom+0.060
ickets+0.060
Neg logit contributions
 rightful-0.058
chard-0.057
 stall-0.056
mary-0.055
 shelf-0.054
Tokens
Token ID82
Feature activation-2.07e-02

Pos logit contributions
hing+0.125
 ah+0.119
Ta+0.116
 applause+0.109
 boom+0.107
Neg logit contributions
 stall-0.202
mary-0.199
field-0.198
chard-0.192
 bank-0.190
Token gaze
Token ID17841
Feature activation-3.49e-02

Pos logit contributions
hing+0.041
Ta+0.039
 ah+0.037
aid+0.035
 boom+0.034
Neg logit contributions
 stall-0.032
 rightful-0.031
 bank-0.031
mary-0.031
field-0.031
Token passed
Token ID3804
Feature activation+6.45e-03

Pos logit contributions
hing+0.064
 ah+0.060
Ta+0.057
 boom+0.056
 applause+0.055
Neg logit contributions
 stall-0.056
 rightful-0.055
field-0.055
mary-0.055
 shelf-0.053
Token by
Token ID416
Feature activation-2.54e-02

Pos logit contributions
field+0.011
 stall+0.011
 rightful+0.011
mary+0.010
chard+0.010
Neg logit contributions
hing-0.011
 ah-0.011
 applause-0.010
 boom-0.010
Ta-0.010
Token,
Token ID11
Feature activation-2.70e-02

Pos logit contributions
hing+0.046
 ah+0.045
 applause+0.042
 boom+0.041
Ta+0.040
Neg logit contributions
 stall-0.041
field-0.040
 rightful-0.040
chard-0.039
mary-0.039
Token.
Token ID13
Feature activation+1.36e-02

Pos logit contributions
field+0.030
chard+0.028
 rightful+0.028
 stall+0.027
mary+0.027
Neg logit contributions
hing-0.033
 boom-0.032
 applause-0.031
 ah-0.030
aid-0.030
Token He
Token ID679
Feature activation+3.02e-02

Pos logit contributions
mary+0.027
field+0.026
chard+0.024
 bank+0.024
 rightful+0.023
Neg logit contributions
hing-0.020
Ta-0.019
 ah-0.019
 applause-0.019
 relief-0.018
Token kept
Token ID4030
Feature activation-1.49e-02

Pos logit contributions
field+0.056
 stall+0.056
chard+0.056
 rightful+0.055
mary+0.054
Neg logit contributions
hing-0.044
 ah-0.043
Ta-0.043
aid-0.041
 bang-0.040
Token throwing
Token ID9644
Feature activation+2.24e-02

Pos logit contributions
hing+0.026
 ah+0.024
Ta+0.024
ickets+0.022
 boom+0.022
Neg logit contributions
 stall-0.026
mary-0.025
field-0.025
 rightful-0.025
chard-0.025
Token a
Token ID257
Feature activation-4.73e-03

Pos logit contributions
field+0.041
mary+0.039
 rightful+0.038
 stall+0.037
chard+0.036
Neg logit contributions
hing-0.039
 ah-0.037
 boom-0.035
 applause-0.034
aid-0.034
Token tant
Token ID24246
Feature activation-9.44e-02

Pos logit contributions
hing+0.010
 ah+0.010
Ta+0.009
ickets+0.009
ez+0.009
Neg logit contributions
 stall-0.007
 shelf-0.006
 bank-0.006
chard-0.006
mary-0.006
Tokenrum
Token ID6582
Feature activation-5.82e-03

Pos logit contributions
Ta+0.102
hing+0.099
 ah+0.097
 applause+0.087
 boom+0.084
Neg logit contributions
 stall-0.210
mary-0.207
chard-0.199
 bank-0.197
 shelf-0.196
Token.
Token ID13
Feature activation+7.39e-03

Pos logit contributions
hing+0.013
 ah+0.012
 boom+0.011
ickets+0.011
 applause+0.011
Neg logit contributions
mary-0.008
field-0.007
 stall-0.007
 rightful-0.007
chard-0.007
Token His
Token ID2399
Feature activation+1.94e-02

Pos logit contributions
mary+0.012
field+0.012
 stall+0.011
chard+0.011
 rightful+0.011
Neg logit contributions
hing-0.013
 ah-0.013
Ta-0.013
 boom-0.012
 applause-0.012
Token mom
Token ID1995
Feature activation-9.67e-03

Pos logit contributions
 stall+0.025
 rightful+0.024
field+0.023
mary+0.023
 shelf+0.023
Neg logit contributions
hing-0.045
 ah-0.042
Ta-0.041
ickets-0.039
 boom-0.039
Token was
Token ID373
Feature activation+5.89e-03

Pos logit contributions
hing+0.019
 ah+0.018
Ta+0.017
 boom+0.016
 applause+0.016
Neg logit contributions
 stall-0.015
field-0.015
 rightful-0.015
mary-0.015
chard-0.014
Token her
Token ID607
Feature activation-2.14e-02

Pos logit contributions
hing+0.012
 ah+0.012
Ta+0.011
 boom+0.011
 applause+0.011
Neg logit contributions
 stall-0.012
field-0.011
mary-0.011
 rightful-0.011
chard-0.011
Token feet
Token ID3625
Feature activation-2.48e-02

Pos logit contributions
hing+0.033
 ah+0.033
 applause+0.031
 boom+0.030
Ta+0.030
Neg logit contributions
mary-0.038
field-0.037
 rightful-0.037
 stall-0.037
chard-0.036
Token and
Token ID290
Feature activation+2.98e-03

Pos logit contributions
hing+0.055
 ah+0.051
Ta+0.049
 boom+0.049
 applause+0.048
Neg logit contributions
 stall-0.031
 rightful-0.031
field-0.031
mary-0.031
chard-0.029
Token threw
Token ID9617
Feature activation+1.48e-02

Pos logit contributions
 rightful+0.006
 stall+0.006
field+0.006
mary+0.005
 shelf+0.005
Neg logit contributions
 ah-0.005
hing-0.005
 boom-0.004
Ta-0.004
 applause-0.004
Token a
Token ID257
Feature activation-7.18e-03

Pos logit contributions
field+0.025
 stall+0.025
 rightful+0.025
mary+0.025
chard+0.024
Neg logit contributions
hing-0.026
 ah-0.025
Ta-0.023
 applause-0.023
 boom-0.023
Token tant
Token ID24246
Feature activation-9.42e-02

Pos logit contributions
hing+0.014
Ta+0.013
 ah+0.013
ickets+0.012
ez+0.011
Neg logit contributions
 stall-0.012
 shelf-0.012
 bank-0.012
chard-0.011
mary-0.011
Tokenrum
Token ID6582
Feature activation-4.97e-03

Pos logit contributions
Ta+0.102
hing+0.100
 ah+0.098
 applause+0.089
 boom+0.087
Neg logit contributions
 stall-0.209
mary-0.209
chard-0.199
field-0.197
 bank-0.197
Token.
Token ID13
Feature activation-1.00e-03

Pos logit contributions
hing+0.011
 ah+0.011
 boom+0.010
Ta+0.010
 applause+0.010
Neg logit contributions
 stall-0.006
field-0.006
 rightful-0.006
mary-0.006
chard-0.005
Token She
Token ID1375
Feature activation+6.38e-03

Pos logit contributions
hing+0.002
 ah+0.002
Ta+0.001
 applause+0.001
 boom+0.001
Neg logit contributions
 stall-0.002
field-0.002
 rightful-0.002
mary-0.002
chard-0.002
Token grabbed
Token ID13176
Feature activation+1.41e-02

Pos logit contributions
 stall+0.012
field+0.012
 rightful+0.012
mary+0.011
chard+0.011
Neg logit contributions
hing-0.010
 ah-0.010
Ta-0.009
 applause-0.009
 boom-0.009
Token the
Token ID262
Feature activation+5.32e-03

Pos logit contributions
 stall+0.021
mary+0.021
chard+0.020
 bank+0.020
field+0.020
Neg logit contributions
hing-0.028
 ah-0.026
Ta-0.026
ickets-0.025
 boom-0.024
Token to
Token ID284
Feature activation+1.57e-03

Pos logit contributions
 stall+0.005
mary+0.005
field+0.005
 rightful+0.004
chard+0.004
Neg logit contributions
hing-0.009
 ah-0.009
Ta-0.009
 boom-0.008
 applause-0.008
Token cry
Token ID3960
Feature activation-2.45e-02

Pos logit contributions
 stall+0.003
mary+0.003
 rightful+0.003
 shelf+0.003
 bank+0.003
Neg logit contributions
hing-0.002
 ah-0.002
Ta-0.002
ickets-0.002
 boom-0.002
Token and
Token ID290
Feature activation+1.06e-02

Pos logit contributions
hing+0.061
 ah+0.059
Ta+0.058
 applause+0.055
ickets+0.054
Neg logit contributions
 stall-0.024
mary-0.023
field-0.022
 rightful-0.022
 shelf-0.022
Token threw
Token ID9617
Feature activation+1.88e-02

Pos logit contributions
 stall+0.016
mary+0.016
field+0.016
 rightful+0.016
chard+0.015
Neg logit contributions
hing-0.021
 ah-0.020
Ta-0.019
 boom-0.018
 applause-0.018
Token a
Token ID257
Feature activation+3.71e-04

Pos logit contributions
 stall+0.027
 shelf+0.026
mary+0.026
 bank+0.026
chard+0.025
Neg logit contributions
hing-0.039
 ah-0.036
Ta-0.035
ickets-0.034
 boom-0.032
Token tant
Token ID24246
Feature activation-9.38e-02

Pos logit contributions
 shelf+0.001
 stall+0.001
 bank+0.000
chard+0.000
mary+0.000
Neg logit contributions
hing-0.001
 ah-0.001
ickets-0.001
Ta-0.001
aded-0.001
Tokenrum
Token ID6582
Feature activation-4.81e-03

Pos logit contributions
Ta+0.105
hing+0.102
 ah+0.101
 applause+0.091
 boom+0.089
Neg logit contributions
mary-0.205
 stall-0.201
chard-0.194
 shelf-0.191
field-0.190
Token.
Token ID13
Feature activation+3.45e-03

Pos logit contributions
hing+0.012
 ah+0.011
Ta+0.011
 boom+0.011
 applause+0.010
Neg logit contributions
 stall-0.005
field-0.005
mary-0.005
 rightful-0.005
chard-0.004
Token She
Token ID1375
Feature activation+1.16e-02

Pos logit contributions
 stall+0.006
field+0.006
 rightful+0.006
mary+0.006
chard+0.006
Neg logit contributions
hing-0.006
 ah-0.005
Ta-0.005
 boom-0.005
 applause-0.005
Token didn
Token ID1422
Feature activation-3.22e-02

Pos logit contributions
 stall+0.020
field+0.019
 rightful+0.019
mary+0.019
chard+0.019
Neg logit contributions
hing-0.020
 ah-0.019
Ta-0.018
 boom-0.018
 applause-0.017
Token't
Token ID470
Feature activation-7.66e-03

Pos logit contributions
hing+0.051
 ah+0.050
Ta+0.047
 applause+0.045
 boom+0.044
Neg logit contributions
mary-0.058
 stall-0.057
 shelf-0.057
field-0.056
 bank-0.055
Token then
Token ID788
Feature activation-2.30e-02

Pos logit contributions
 stall+0.009
mary+0.009
field+0.009
 rightful+0.009
chard+0.009
Neg logit contributions
hing-0.009
 ah-0.008
Ta-0.008
 boom-0.008
 applause-0.008
Token on
Token ID319
Feature activation-1.48e-02

Pos logit contributions
hing+0.042
Ta+0.041
 ah+0.041
 applause+0.037
ickets+0.037
Neg logit contributions
 stall-0.036
field-0.036
mary-0.035
 bank-0.034
 shelf-0.034
Token everyone
Token ID2506
Feature activation-5.93e-02

Pos logit contributions
 ah+0.026
hing+0.026
 boom+0.024
 applause+0.024
apy+0.024
Neg logit contributions
 rightful-0.024
 stall-0.023
chard-0.023
mary-0.023
field-0.022
Token in
Token ID287
Feature activation+7.48e-03

Pos logit contributions
hing+0.131
 ah+0.124
Ta+0.122
 boom+0.116
 applause+0.116
Neg logit contributions
 stall-0.075
mary-0.073
field-0.072
 rightful-0.071
chard-0.069
Token the
Token ID262
Feature activation-3.10e-02

Pos logit contributions
 stall+0.011
mary+0.011
field+0.011
 rightful+0.011
chard+0.011
Neg logit contributions
hing-0.015
 ah-0.014
Ta-0.013
 applause-0.013
 boom-0.013
Token me
Token ID502
Feature activation-9.28e-02

Pos logit contributions
hing+0.058
 ah+0.055
Ta+0.054
 applause+0.053
 boom+0.052
Neg logit contributions
 stall-0.047
chard-0.046
mary-0.046
field-0.045
 rightful-0.044
Tokenadow
Token ID4584
Feature activation-4.79e-02

Pos logit contributions
hing+0.154
 ah+0.144
Ta+0.140
 boom+0.131
 applause+0.130
Neg logit contributions
 stall-0.168
mary-0.165
field-0.165
 rightful-0.163
chard-0.159
Token was
Token ID373
Feature activation-3.72e-02

Pos logit contributions
hing+0.098
 ah+0.094
Ta+0.088
 applause+0.087
 boom+0.086
Neg logit contributions
 stall-0.067
mary-0.065
 rightful-0.064
chard-0.064
field-0.063
Token happy
Token ID3772
Feature activation-3.72e-02

Pos logit contributions
hing+0.069
 ah+0.065
Ta+0.061
 applause+0.061
 boom+0.060
Neg logit contributions
 stall-0.060
field-0.058
 shelf-0.057
mary-0.057
 rightful-0.057
Token,
Token ID11
Feature activation-3.54e-02

Pos logit contributions
hing+0.077
 ah+0.075
 applause+0.071
 boom+0.070
ickets+0.068
Neg logit contributions
 stall-0.051
chard-0.050
mary-0.050
 rightful-0.049
field-0.048
Token and
Token ID290
Feature activation-1.53e-02

Pos logit contributions
hing+0.069
 ah+0.069
 applause+0.064
 boom+0.063
Ta+0.061
Neg logit contributions
 stall-0.052
mary-0.051
chard-0.051
field-0.050
 rightful-0.050
Token kept
Token ID4030
Feature activation-1.28e-02

Pos logit contributions
 stall+0.027
field+0.026
 rightful+0.026
chard+0.025
mary+0.025
Neg logit contributions
hing-0.028
 ah-0.027
Ta-0.027
 boom-0.025
ez-0.025
Token crying
Token ID13774
Feature activation-1.56e-02

Pos logit contributions
hing+0.023
Ta+0.021
 ah+0.021
ickets+0.020
 boom+0.019
Neg logit contributions
 stall-0.022
mary-0.022
field-0.022
 rightful-0.021
chard-0.021
Token and
Token ID290
Feature activation+4.57e-03

Pos logit contributions
hing+0.035
 ah+0.033
Ta+0.032
 boom+0.031
 applause+0.031
Neg logit contributions
 stall-0.019
field-0.019
mary-0.019
 rightful-0.018
chard-0.018
Token throwing
Token ID9644
Feature activation+2.41e-02

Pos logit contributions
 stall+0.008
mary+0.008
field+0.008
 rightful+0.008
chard+0.008
Neg logit contributions
hing-0.008
 ah-0.007
Ta-0.007
 boom-0.007
 applause-0.007
Token a
Token ID257
Feature activation+2.76e-03

Pos logit contributions
field+0.047
 rightful+0.045
 stall+0.045
chard+0.043
mary+0.043
Neg logit contributions
hing-0.039
 ah-0.036
aid-0.033
 applause-0.033
 boom-0.033
Token tant
Token ID24246
Feature activation-9.26e-02

Pos logit contributions
 stall+0.005
 shelf+0.005
mary+0.004
 bank+0.004
chard+0.004
Neg logit contributions
hing-0.005
 ah-0.005
Ta-0.005
ickets-0.005
 applause-0.004
Tokenrum
Token ID6582
Feature activation-3.60e-03

Pos logit contributions
 ah+0.102
Ta+0.102
hing+0.101
 applause+0.093
 boom+0.091
Neg logit contributions
mary-0.200
 stall-0.196
chard-0.189
 shelf-0.186
field-0.184
Token.
Token ID13
Feature activation-2.34e-03

Pos logit contributions
hing+0.008
 ah+0.008
Ta+0.008
 boom+0.008
 applause+0.007
Neg logit contributions
 stall-0.004
field-0.004
mary-0.004
 rightful-0.004
chard-0.004
Token
Token ID198
Feature activation+1.13e-02

Pos logit contributions
hing+0.005
 ah+0.004
Ta+0.004
 boom+0.004
 applause+0.004
Neg logit contributions
 stall-0.003
field-0.003
mary-0.003
 rightful-0.003
chard-0.003
Token
Token ID198
Feature activation+1.70e-02

Pos logit contributions
 stall+0.013
mary+0.012
field+0.012
 rightful+0.012
 shelf+0.012
Neg logit contributions
hing-0.027
 ah-0.026
Ta-0.025
 applause-0.024
 boom-0.024
TokenFinally
Token ID11158
Feature activation+9.95e-03

Pos logit contributions
mary+0.025
 stall+0.024
 shelf+0.024
 rightful+0.023
chard+0.023
Neg logit contributions
hing-0.035
 ah-0.035
 applause-0.031
Ta-0.031
 boom-0.031
Token of
Token ID286
Feature activation-3.61e-02

Pos logit contributions
hing+0.049
 ah+0.047
Ta+0.047
 boom+0.043
aid+0.043
Neg logit contributions
 stall-0.035
field-0.035
mary-0.034
 rightful-0.034
chard-0.033
Token the
Token ID262
Feature activation-1.52e-02

Pos logit contributions
hing+0.071
 ah+0.067
Ta+0.066
 boom+0.062
 applause+0.062
Neg logit contributions
 stall-0.054
mary-0.053
field-0.053
 rightful-0.052
chard-0.051
Token animals
Token ID4695
Feature activation-4.88e-02

Pos logit contributions
hing+0.027
 ah+0.026
Ta+0.025
 applause+0.024
 boom+0.024
Neg logit contributions
 stall-0.025
mary-0.025
field-0.025
 rightful-0.024
chard-0.024
Token in
Token ID287
Feature activation+8.43e-03

Pos logit contributions
hing+0.096
Ta+0.094
 ah+0.091
 boom+0.086
aid+0.085
Neg logit contributions
 stall-0.071
field-0.071
mary-0.069
chard-0.067
 bank-0.067
Token the
Token ID262
Feature activation-3.04e-02

Pos logit contributions
mary+0.015
 rightful+0.014
field+0.014
 stall+0.014
chard+0.014
Neg logit contributions
hing-0.015
 ah-0.014
 applause-0.013
 boom-0.013
Ta-0.013
Token me
Token ID502
Feature activation-9.20e-02

Pos logit contributions
hing+0.065
 ah+0.062
Ta+0.061
 applause+0.059
 boom+0.059
Neg logit contributions
mary-0.039
 stall-0.038
field-0.038
chard-0.037
 rightful-0.036
Tokenadow
Token ID4584
Feature activation-4.29e-02

Pos logit contributions
hing+0.151
 ah+0.142
Ta+0.137
 boom+0.129
 applause+0.128
Neg logit contributions
 stall-0.168
mary-0.165
field-0.164
 rightful-0.162
chard-0.159
Token soon
Token ID2582
Feature activation-1.46e-02

Pos logit contributions
hing+0.087
 ah+0.083
Ta+0.079
 applause+0.076
 boom+0.076
Neg logit contributions
 stall-0.062
mary-0.060
 rightful-0.059
field-0.059
chard-0.058
Token learned
Token ID4499
Feature activation+1.97e-02

Pos logit contributions
hing+0.026
 ah+0.025
 applause+0.023
 boom+0.022
ez+0.022
Neg logit contributions
 rightful-0.024
chard-0.024
 shelf-0.024
 stall-0.023
mary-0.023
Token how
Token ID703
Feature activation-6.17e-03

Pos logit contributions
field+0.039
chard+0.039
 stall+0.039
mary+0.038
 shelf+0.037
Neg logit contributions
hing-0.027
 applause-0.025
 ah-0.024
 boom-0.024
 relief-0.022
Token to
Token ID284
Feature activation-6.13e-03

Pos logit contributions
hing+0.012
 ah+0.012
 boom+0.011
 applause+0.011
Ta+0.011
Neg logit contributions
 stall-0.009
field-0.009
 shelf-0.008
mary-0.008
 bank-0.008
Token of
Token ID286
Feature activation-3.85e-02

Pos logit contributions
hing+0.048
Ta+0.046
 ah+0.044
 boom+0.039
 applause+0.039
Neg logit contributions
 stall-0.096
field-0.094
mary-0.092
chard-0.091
 rightful-0.090
Token the
Token ID262
Feature activation-3.28e-02

Pos logit contributions
hing+0.079
 ah+0.074
Ta+0.074
 boom+0.069
 applause+0.069
Neg logit contributions
 stall-0.056
field-0.054
mary-0.054
 rightful-0.053
chard-0.052
Token day
Token ID1110
Feature activation-4.23e-02

Pos logit contributions
hing+0.067
 ah+0.064
Ta+0.061
ickets+0.059
aid+0.057
Neg logit contributions
 stall-0.049
field-0.048
 bank-0.047
 rightful-0.047
 shelf-0.047
Token in
Token ID287
Feature activation-5.17e-03

Pos logit contributions
hing+0.071
 ah+0.067
Ta+0.062
 boom+0.061
 applause+0.060
Neg logit contributions
 stall-0.075
 rightful-0.075
mary-0.075
field-0.073
chard-0.072
Token the
Token ID262
Feature activation-3.62e-02

Pos logit contributions
hing+0.008
 ah+0.008
 applause+0.008
 boom+0.008
 relief+0.007
Neg logit contributions
mary-0.009
 stall-0.009
chard-0.009
 rightful-0.009
field-0.009
Token me
Token ID502
Feature activation-9.20e-02

Pos logit contributions
hing+0.074
 ah+0.070
Ta+0.069
 boom+0.065
 applause+0.065
Neg logit contributions
 stall-0.052
mary-0.051
field-0.050
 rightful-0.050
chard-0.049
Tokenadow
Token ID4584
Feature activation-4.35e-02

Pos logit contributions
hing+0.147
 ah+0.137
Ta+0.132
 boom+0.124
 applause+0.124
Neg logit contributions
 stall-0.172
mary-0.169
field-0.168
 rightful-0.167
chard-0.164
Token,
Token ID11
Feature activation-2.95e-02

Pos logit contributions
hing+0.088
 ah+0.084
 applause+0.077
 boom+0.077
ickets+0.075
Neg logit contributions
mary-0.060
 stall-0.060
 rightful-0.060
chard-0.058
 shelf-0.056
Token wondering
Token ID11263
Feature activation+1.22e-03

Pos logit contributions
hing+0.053
 ah+0.052
 boom+0.047
 applause+0.047
Ta+0.047
Neg logit contributions
 stall-0.047
mary-0.047
 rightful-0.046
field-0.045
 shelf-0.044
Token what
Token ID644
Feature activation-6.21e-03

Pos logit contributions
mary+0.002
 stall+0.002
field+0.002
 rightful+0.002
 bank+0.002
Neg logit contributions
hing-0.002
 ah-0.002
 boom-0.001
 applause-0.001
aid-0.001
Token adventure
Token ID8855
Feature activation+3.46e-04

Pos logit contributions
 ah+0.010
hing+0.009
 applause+0.009
Ta+0.008
aid+0.008
Neg logit contributions
mary-0.012
field-0.011
 stall-0.011
 bank-0.011
 rightful-0.010
Token,
Token ID11
Feature activation-1.30e-02

Pos logit contributions
 stall+0.013
mary+0.013
field+0.012
 shelf+0.012
 bank+0.012
Neg logit contributions
hing-0.026
 ah-0.024
Ta-0.024
 boom-0.023
 applause-0.023
Token Sarah
Token ID10490
Feature activation-7.17e-03

Pos logit contributions
hing+0.021
 ah+0.020
Ta+0.019
 boom+0.018
 applause+0.018
Neg logit contributions
 stall-0.024
mary-0.024
field-0.024
 rightful-0.023
chard-0.023
Token shared
Token ID4888
Feature activation+2.30e-02

Pos logit contributions
hing+0.010
 ah+0.010
 bang+0.009
Ta+0.009
ez+0.009
Neg logit contributions
 rightful-0.014
 stall-0.013
chard-0.013
field-0.013
lands-0.012
Token her
Token ID607
Feature activation-3.46e-02

Pos logit contributions
field+0.049
 rightful+0.046
mary+0.046
 stall+0.045
 bank+0.044
Neg logit contributions
hing-0.031
 ah-0.031
 applause-0.028
aid-0.027
Ta-0.027
Token cr
Token ID1067
Feature activation-9.67e-03

Pos logit contributions
hing+0.072
 ah+0.065
Ta+0.063
ickets+0.063
 boom+0.062
Neg logit contributions
 stall-0.054
 shelf-0.050
 rightful-0.050
field-0.048
 bank-0.048
Tokenay
Token ID323
Feature activation-9.13e-02

Pos logit contributions
 ah+0.008
hing+0.008
 boom+0.007
Ta+0.007
 applause+0.006
Neg logit contributions
 stall-0.025
mary-0.024
 shelf-0.024
 rightful-0.024
field-0.024
Tokenons
Token ID684
Feature activation-1.56e-02

Pos logit contributions
hing+0.125
 ah+0.122
 boom+0.119
 relief+0.111
Ta+0.110
Neg logit contributions
 stall-0.177
mary-0.168
 shelf-0.164
 ones-0.157
field-0.157
Token with
Token ID351
Feature activation+1.00e-02

Pos logit contributions
hing+0.029
aid+0.026
 ah+0.026
 applause+0.025
ickets+0.025
Neg logit contributions
 rightful-0.025
field-0.024
chard-0.023
mary-0.023
 stall-0.023
Token Tim
Token ID5045
Feature activation+1.90e-03

Pos logit contributions
 stall+0.019
mary+0.019
field+0.019
 rightful+0.019
chard+0.018
Neg logit contributions
hing-0.016
 ah-0.015
Ta-0.014
 applause-0.013
 boom-0.013
Tokenmy
Token ID1820
Feature activation-1.42e-02

Pos logit contributions
 stall+0.004
field+0.004
 rightful+0.004
chard+0.004
mary+0.004
Neg logit contributions
hing-0.002
 ah-0.002
ez-0.002
aid-0.002
ickets-0.002
Token and
Token ID290
Feature activation-2.40e-02

Pos logit contributions
hing+0.023
ez+0.021
 ah+0.021
 applause+0.020
on+0.020
Neg logit contributions
 rightful-0.024
chard-0.024
field-0.024
mary-0.023
 stall-0.023
Token He
Token ID679
Feature activation+2.49e-02

Pos logit contributions
hing+0.016
Ta+0.014
 Boom+0.013
ay+0.013
ez+0.013
Neg logit contributions
mary-0.018
chard-0.018
 rightful-0.017
field-0.016
 seller-0.016
Token lived
Token ID5615
Feature activation-3.68e-03

Pos logit contributions
 stall+0.047
 rightful+0.046
chard+0.045
field+0.045
mary+0.043
Neg logit contributions
hing-0.038
Ta-0.034
 ah-0.034
ez-0.034
 applause-0.032
Token in
Token ID287
Feature activation+5.30e-03

Pos logit contributions
hing+0.006
 ah+0.006
Ta+0.006
 boom+0.006
aid+0.005
Neg logit contributions
 stall-0.006
mary-0.006
 rightful-0.006
field-0.006
 bank-0.006
Token a
Token ID257
Feature activation-2.24e-02

Pos logit contributions
 stall+0.008
field+0.007
 rightful+0.007
 shelf+0.007
mary+0.007
Neg logit contributions
hing-0.011
 ah-0.010
Ta-0.010
ickets-0.009
 boom-0.009
Token sunny
Token ID27737
Feature activation-7.14e-02

Pos logit contributions
hing+0.044
 ah+0.042
Ta+0.041
 boom+0.039
 applause+0.039
Neg logit contributions
 stall-0.033
mary-0.033
field-0.032
 rightful-0.032
chard-0.031
Token me
Token ID502
Feature activation-9.10e-02

Pos logit contributions
hing+0.157
 ah+0.150
Ta+0.146
 boom+0.140
 applause+0.139
Neg logit contributions
 stall-0.091
mary-0.088
field-0.087
 rightful-0.086
chard-0.084
Tokenadow
Token ID4584
Feature activation-2.68e-02

Pos logit contributions
hing+0.165
 ah+0.159
Ta+0.153
 applause+0.146
 boom+0.145
Neg logit contributions
 stall-0.153
field-0.150
mary-0.150
 rightful-0.142
chard-0.140
Token near
Token ID1474
Feature activation+5.80e-03

Pos logit contributions
hing+0.056
 ah+0.053
 boom+0.050
Ta+0.050
 applause+0.049
Neg logit contributions
 rightful-0.036
mary-0.035
 stall-0.035
 bank-0.033
field-0.033
Token a
Token ID257
Feature activation-1.77e-02

Pos logit contributions
mary+0.011
field+0.011
 rightful+0.011
 stall+0.011
chard+0.011
Neg logit contributions
hing-0.009
 ah-0.008
Ta-0.008
 applause-0.008
 boom-0.008
Token large
Token ID1588
Feature activation-3.02e-02

Pos logit contributions
hing+0.033
 ah+0.031
 boom+0.031
Ta+0.031
 applause+0.030
Neg logit contributions
 stall-0.026
 rightful-0.026
mary-0.026
field-0.025
 bank-0.025
Token bucket
Token ID19236
Feature activation+3.04e-03

Pos logit contributions
hing+0.059
 boom+0.057
 ah+0.056
 applause+0.054
Ta+0.051
Neg logit contributions
mary-0.041
 rightful-0.041
chard-0.039
 stall-0.038
field-0.038
Token of
Token ID286
Feature activation-3.42e-02

Pos logit contributions
hing+0.047
Ta+0.046
 ah+0.043
 boom+0.039
 applause+0.038
Neg logit contributions
 stall-0.091
field-0.090
mary-0.089
 rightful-0.086
 shelf-0.085
Token the
Token ID262
Feature activation-3.06e-02

Pos logit contributions
hing+0.079
Ta+0.074
 ah+0.072
ickets+0.071
aid+0.069
Neg logit contributions
 stall-0.043
mary-0.041
field-0.041
 shelf-0.039
chard-0.039
Token day
Token ID1110
Feature activation-4.31e-02

Pos logit contributions
hing+0.058
 ah+0.055
Ta+0.054
aid+0.050
 boom+0.050
Neg logit contributions
 stall-0.049
field-0.048
mary-0.047
 rightful-0.047
 bank-0.046
Token in
Token ID287
Feature activation-3.74e-03

Pos logit contributions
hing+0.074
 ah+0.070
Ta+0.068
 boom+0.064
 applause+0.063
Neg logit contributions
 stall-0.075
mary-0.073
field-0.073
 rightful-0.072
chard-0.071
Token the
Token ID262
Feature activation-3.54e-02

Pos logit contributions
hing+0.007
 ah+0.006
 applause+0.006
 boom+0.006
Ta+0.006
Neg logit contributions
mary-0.006
 stall-0.006
 rightful-0.006
chard-0.006
field-0.006
Token me
Token ID502
Feature activation-9.07e-02

Pos logit contributions
hing+0.075
 ah+0.071
Ta+0.070
 applause+0.068
 boom+0.067
Neg logit contributions
 stall-0.046
mary-0.046
field-0.045
chard-0.045
 rightful-0.044
Tokenadow
Token ID4584
Feature activation-4.18e-02

Pos logit contributions
hing+0.143
 ah+0.133
Ta+0.128
 boom+0.120
 applause+0.120
Neg logit contributions
 stall-0.171
mary-0.168
field-0.167
 rightful-0.167
chard-0.164
Token,
Token ID11
Feature activation-2.45e-02

Pos logit contributions
hing+0.085
 ah+0.082
 applause+0.076
 boom+0.075
Ta+0.074
Neg logit contributions
 stall-0.057
 rightful-0.056
mary-0.056
chard-0.055
field-0.054
Token enjoying
Token ID13226
Feature activation-2.73e-02

Pos logit contributions
hing+0.048
 ah+0.047
Ta+0.043
 applause+0.043
 boom+0.043
Neg logit contributions
 stall-0.036
 rightful-0.035
mary-0.035
field-0.035
chard-0.034
Token Gina
Token ID43002
Feature activation-2.74e-02

Pos logit contributions
hing+0.053
 ah+0.050
Ta+0.048
 boom+0.046
 applause+0.046
Neg logit contributions
 stall-0.042
mary-0.041
field-0.041
 rightful-0.040
chard-0.039
Token's
Token ID338
Feature activation-4.11e-02

Pos logit contributions
hing+0.061
 ah+0.057
 applause+0.054
Ta+0.053
 boom+0.053
Neg logit contributions
 stall-0.034
 rightful-0.034
chard-0.033
field-0.032
mary-0.032
Token She
Token ID1375
Feature activation+1.31e-02

Pos logit contributions
field+0.003
 stall+0.003
 rightful+0.003
chard+0.003
mary+0.003
Neg logit contributions
hing-0.003
Ta-0.003
 ah-0.003
 boom-0.003
ickets-0.003
Token cried
Token ID16896
Feature activation-1.76e-02

Pos logit contributions
 stall+0.025
chard+0.025
field+0.024
 rightful+0.023
boxes+0.022
Neg logit contributions
hing-0.018
Ta-0.018
 ah-0.017
 bang-0.017
ez-0.017
Token and
Token ID290
Feature activation+1.20e-02

Pos logit contributions
hing+0.043
 ah+0.043
Ta+0.042
 applause+0.039
ickets+0.039
Neg logit contributions
mary-0.017
 stall-0.017
 shelf-0.016
 bank-0.016
chard-0.015
Token threw
Token ID9617
Feature activation+1.73e-02

Pos logit contributions
 stall+0.021
field+0.020
mary+0.020
 rightful+0.020
chard+0.019
Neg logit contributions
hing-0.020
 ah-0.020
Ta-0.018
 applause-0.018
 boom-0.018
Token a
Token ID257
Feature activation-4.85e-03

Pos logit contributions
 stall+0.028
mary+0.027
 bank+0.026
 shelf+0.026
chard+0.026
Neg logit contributions
hing-0.033
 ah-0.031
Ta-0.030
ickets-0.028
 boom-0.028
Token tant
Token ID24246
Feature activation-9.05e-02

Pos logit contributions
hing+0.010
 ah+0.009
ickets+0.009
Ta+0.009
otion+0.008
Neg logit contributions
 stall-0.008
 shelf-0.007
 bank-0.007
chard-0.007
mary-0.006
Tokenrum
Token ID6582
Feature activation-7.39e-03

Pos logit contributions
Ta+0.105
hing+0.098
 ah+0.098
 applause+0.089
 boom+0.086
Neg logit contributions
mary-0.195
 stall-0.192
chard-0.185
 shelf-0.180
 bank-0.179
Token.
Token ID13
Feature activation-5.39e-03

Pos logit contributions
hing+0.018
 ah+0.017
 boom+0.016
Ta+0.016
 applause+0.016
Neg logit contributions
 stall-0.008
field-0.008
 rightful-0.007
mary-0.007
chard-0.007
Token Her
Token ID2332
Feature activation+3.83e-03

Pos logit contributions
hing+0.010
 ah+0.010
Ta+0.009
 boom+0.009
 applause+0.009
Neg logit contributions
 stall-0.009
mary-0.009
field-0.008
 rightful-0.008
chard-0.008
Token mom
Token ID1995
Feature activation-1.42e-02

Pos logit contributions
 rightful+0.004
 stall+0.004
 shelf+0.004
 bank+0.004
mary+0.004
Neg logit contributions
hing-0.010
Ta-0.009
 ah-0.009
ickets-0.009
 boom-0.008
Token tried
Token ID3088
Feature activation+1.40e-02

Pos logit contributions
hing+0.030
 ah+0.029
Ta+0.028
 applause+0.027
 boom+0.027
Neg logit contributions
mary-0.019
 stall-0.019
field-0.018
 bank-0.018
 rightful-0.017
Token chair
Token ID5118
Feature activation+1.97e-02

Pos logit contributions
hing+0.030
 ah+0.028
Ta+0.028
 applause+0.026
 boom+0.026
Neg logit contributions
mary-0.022
 stall-0.022
field-0.022
 rightful-0.021
chard-0.021
Token and
Token ID290
Feature activation+2.84e-03

Pos logit contributions
 rightful+0.030
mary+0.029
chard+0.029
field+0.029
 stall+0.028
Neg logit contributions
hing-0.036
 ah-0.034
 boom-0.033
 applause-0.033
aid-0.032
Token takes
Token ID2753
Feature activation+5.63e-04

Pos logit contributions
 stall+0.005
mary+0.005
field+0.005
 rightful+0.005
chard+0.005
Neg logit contributions
hing-0.005
 ah-0.005
Ta-0.004
 boom-0.004
 applause-0.004
Token a
Token ID257
Feature activation+1.46e-03

Pos logit contributions
 stall+0.001
mary+0.001
 shelf+0.001
 bank+0.001
 rightful+0.001
Neg logit contributions
hing-0.001
 ah-0.001
Ta-0.001
ickets-0.001
 boom-0.001
Token cr
Token ID1067
Feature activation-3.78e-03

Pos logit contributions
 shelf+0.002
 stall+0.002
 bank+0.002
mary+0.002
 aisle+0.002
Neg logit contributions
hing-0.003
ickets-0.003
 ah-0.003
agged-0.003
ez-0.003
Tokenay
Token ID323
Feature activation-8.88e-02

Pos logit contributions
 ah+0.004
hing+0.003
 applause+0.003
Ta+0.003
 boom+0.003
Neg logit contributions
 stall-0.009
 shelf-0.009
mary-0.009
field-0.009
 rightful-0.008
Tokenon
Token ID261
Feature activation+5.73e-03

Pos logit contributions
 ah+0.125
 relief+0.116
hing+0.115
 sidelines+0.113
Ta+0.109
Neg logit contributions
 stall-0.147
 shelf-0.146
mary-0.138
 ones-0.138
.-0.137
Token and
Token ID290
Feature activation+5.53e-03

Pos logit contributions
 stall+0.007
 rightful+0.007
mary+0.007
field+0.007
chard+0.007
Neg logit contributions
hing-0.013
 ah-0.012
Ta-0.012
 boom-0.011
 applause-0.011
Token a
Token ID257
Feature activation-4.67e-03

Pos logit contributions
 stall+0.009
mary+0.008
field+0.008
 rightful+0.008
chard+0.008
Neg logit contributions
hing-0.011
 ah-0.010
Ta-0.010
 boom-0.009
 applause-0.009
Token paper
Token ID3348
Feature activation+2.34e-02

Pos logit contributions
hing+0.011
ickets+0.009
Ta+0.009
ez+0.009
 ah+0.009
Neg logit contributions
 stall-0.007
 shelf-0.007
 bank-0.006
mary-0.006
field-0.006
Token.
Token ID13
Feature activation+7.84e-03

Pos logit contributions
 rightful+0.033
chard+0.031
mary+0.031
field+0.031
 stall+0.030
Neg logit contributions
hing-0.048
 ah-0.047
 boom-0.044
 applause-0.043
aid-0.043
Token.
Token ID13
Feature activation-5.02e-03

Pos logit contributions
hing+0.059
 ah+0.056
Ta+0.054
 boom+0.053
 applause+0.053
Neg logit contributions
 stall-0.024
 rightful-0.024
field-0.024
mary-0.023
chard-0.022
Token With
Token ID2080
Feature activation+1.83e-02

Pos logit contributions
hing+0.008
 ah+0.008
Ta+0.008
 applause+0.007
ickets+0.007
Neg logit contributions
field-0.009
 stall-0.009
 rightful-0.008
chard-0.008
mary-0.008
Token a
Token ID257
Feature activation-4.14e-03

Pos logit contributions
 stall+0.027
mary+0.026
chard+0.025
field+0.025
 rightful+0.025
Neg logit contributions
hing-0.037
 ah-0.034
Ta-0.034
ickets-0.032
 boom-0.032
Token red
Token ID2266
Feature activation-1.55e-02

Pos logit contributions
hing+0.010
ickets+0.009
otion+0.009
ez+0.009
ags+0.009
Neg logit contributions
 stall-0.005
 shelf-0.005
mary-0.004
field-0.004
 buyer-0.004
Token cr
Token ID1067
Feature activation-9.16e-03

Pos logit contributions
hing+0.031
Ta+0.029
 ah+0.028
ickets+0.028
ez+0.026
Neg logit contributions
 shelf-0.024
 stall-0.023
 bank-0.021
 ones-0.021
field-0.020
Tokenay
Token ID323
Feature activation-8.87e-02

Pos logit contributions
 ah+0.011
 boom+0.010
 relief+0.010
hing+0.010
 applause+0.009
Neg logit contributions
mary-0.019
 stall-0.018
ocular-0.018
 shelf-0.018
field-0.017
Tokenon
Token ID261
Feature activation-4.50e-03

Pos logit contributions
 sidelines+0.135
 ah+0.132
hing+0.129
Ta+0.128
 relief+0.126
Neg logit contributions
.-0.129
ine-0.120
 one-0.120
 every-0.118
 ones-0.113
Token she
Token ID673
Feature activation-1.29e-02

Pos logit contributions
hing+0.010
Ta+0.009
 ah+0.009
 applause+0.009
 boom+0.008
Neg logit contributions
 stall-0.006
mary-0.006
 shelf-0.006
field-0.005
 bank-0.005
Token carefully
Token ID7773
Feature activation+2.67e-02

Pos logit contributions
hing+0.027
 ah+0.026
Ta+0.025
 boom+0.024
 applause+0.024
Neg logit contributions
 stall-0.018
mary-0.017
field-0.017
 rightful-0.017
chard-0.017
Token drew
Token ID9859
Feature activation-3.98e-04

Pos logit contributions
 stall+0.039
field+0.038
 rightful+0.038
mary+0.038
chard+0.037
Neg logit contributions
hing-0.054
 ah-0.051
Ta-0.049
 applause-0.048
 boom-0.047
Token a
Token ID257
Feature activation-5.02e-03

Pos logit contributions
hing+0.001
 ah+0.001
Ta+0.001
 boom+0.001
 applause+0.001
Neg logit contributions
 stall-0.001
field-0.001
 rightful-0.001
mary-0.001
chard-0.001
Token their
Token ID511
Feature activation-1.74e-02

Pos logit contributions
hing+0.006
 ah+0.005
 applause+0.005
 boom+0.005
apy+0.005
Neg logit contributions
 rightful-0.008
chard-0.008
 stall-0.007
mary-0.007
 shelf-0.007
Token merry
Token ID44570
Feature activation-6.07e-02

Pos logit contributions
hing+0.037
 ah+0.035
Ta+0.034
 applause+0.033
 boom+0.033
Neg logit contributions
 stall-0.023
mary-0.023
field-0.023
chard-0.022
 rightful-0.022
Token way
Token ID835
Feature activation-1.53e-02

Pos logit contributions
hing+0.115
 ah+0.108
Ta+0.105
 boom+0.100
 applause+0.099
Neg logit contributions
 stall-0.096
mary-0.094
field-0.094
 rightful-0.093
chard-0.090
Token through
Token ID832
Feature activation-8.43e-03

Pos logit contributions
hing+0.031
 ah+0.028
 boom+0.027
 applause+0.027
ickets+0.026
Neg logit contributions
 stall-0.022
mary-0.021
 rightful-0.021
chard-0.021
field-0.020
Token the
Token ID262
Feature activation-4.41e-02

Pos logit contributions
hing+0.013
 ah+0.013
 applause+0.012
 boom+0.011
ez+0.011
Neg logit contributions
mary-0.016
chard-0.016
 rightful-0.015
 stall-0.015
field-0.015
Token me
Token ID502
Feature activation-8.86e-02

Pos logit contributions
hing+0.092
 ah+0.087
Ta+0.086
 applause+0.082
 boom+0.082
Neg logit contributions
 stall-0.061
mary-0.060
chard-0.059
field-0.059
 rightful-0.058
Tokenadow
Token ID4584
Feature activation-4.33e-02

Pos logit contributions
hing+0.139
 ah+0.128
Ta+0.123
 applause+0.116
 boom+0.116
Neg logit contributions
 stall-0.169
mary-0.166
field-0.164
 rightful-0.164
chard-0.162
Token,
Token ID11
Feature activation-2.91e-02

Pos logit contributions
hing+0.095
 ah+0.090
 applause+0.084
 boom+0.084
ickets+0.083
Neg logit contributions
 stall-0.054
 rightful-0.053
mary-0.053
chard-0.053
 shelf-0.050
Token enjoying
Token ID13226
Feature activation-2.96e-02

Pos logit contributions
hing+0.053
 ah+0.050
Ta+0.048
 applause+0.046
 boom+0.046
Neg logit contributions
 stall-0.048
 rightful-0.047
mary-0.047
field-0.046
chard-0.045
Token the
Token ID262
Feature activation-5.02e-02

Pos logit contributions
hing+0.053
 ah+0.052
 applause+0.048
Ta+0.047
 boom+0.046
Neg logit contributions
 stall-0.048
mary-0.048
field-0.047
 rightful-0.047
chard-0.046
Token sight
Token ID6504
Feature activation-5.23e-02

Pos logit contributions
hing+0.087
 ah+0.082
Ta+0.079
 boom+0.076
ickets+0.075
Neg logit contributions
 stall-0.087
 rightful-0.086
field-0.085
mary-0.085
 shelf-0.083
Token friends
Token ID2460
Feature activation-7.29e-03

Pos logit contributions
 stall+0.008
mary+0.008
field+0.008
 rightful+0.008
chard+0.008
Neg logit contributions
hing-0.017
 ah-0.016
Ta-0.016
 boom-0.015
 applause-0.015
Token and
Token ID290
Feature activation+1.06e-02

Pos logit contributions
hing+0.013
 ah+0.012
 boom+0.012
 applause+0.011
aid+0.011
Neg logit contributions
field-0.012
mary-0.012
 rightful-0.011
 bank-0.011
 stall-0.011
Token share
Token ID2648
Feature activation+3.60e-02

Pos logit contributions
 rightful+0.019
 shelf+0.018
 stall+0.018
chard+0.018
field+0.018
Neg logit contributions
hing-0.019
Ta-0.017
 ah-0.017
ickets-0.016
ez-0.016
Token the
Token ID262
Feature activation-2.88e-02

Pos logit contributions
field+0.058
 stall+0.055
mary+0.055
 rightful+0.053
chard+0.053
Neg logit contributions
hing-0.066
 ah-0.065
 boom-0.063
 applause-0.061
Ta-0.059
Token cr
Token ID1067
Feature activation-1.59e-02

Pos logit contributions
hing+0.062
 ah+0.057
ickets+0.054
Ta+0.054
aid+0.054
Neg logit contributions
 shelf-0.041
 stall-0.040
 rightful-0.038
field-0.038
 bank-0.037
Tokenay
Token ID323
Feature activation-8.80e-02

Pos logit contributions
 ah+0.014
hing+0.013
Ta+0.012
 applause+0.011
 relief+0.010
Neg logit contributions
mary-0.039
 shelf-0.039
 stall-0.039
field-0.039
 rightful-0.038
Tokenons
Token ID684
Feature activation-4.67e-03

Pos logit contributions
 ah+0.128
hing+0.127
 relief+0.127
Ta+0.119
 applause+0.114
Neg logit contributions
mary-0.146
 shelf-0.146
 stall-0.146
 ones-0.144
boxes-0.134
Token and
Token ID290
Feature activation+1.68e-03

Pos logit contributions
hing+0.009
 ah+0.009
aid+0.009
 boom+0.008
 applause+0.008
Neg logit contributions
field-0.007
 rightful-0.006
mary-0.006
chard-0.006
 stall-0.006
Token the
Token ID262
Feature activation-1.48e-02

Pos logit contributions
 rightful+0.003
 stall+0.003
 shelf+0.003
mary+0.002
 bank+0.002
Neg logit contributions
hing-0.003
Ta-0.003
 ah-0.003
ickets-0.003
aid-0.003
Token paper
Token ID3348
Feature activation+1.59e-02

Pos logit contributions
hing+0.029
 ah+0.027
Ta+0.026
ickets+0.024
 boom+0.024
Neg logit contributions
 stall-0.023
 rightful-0.022
field-0.022
mary-0.022
 shelf-0.022
Token."
Token ID526
Feature activation+3.30e-02

Pos logit contributions
 stall+0.018
field+0.018
chard+0.018
mary+0.017
 rightful+0.017
Neg logit contributions
hing-0.036
 ah-0.035
 boom-0.034
 applause-0.033
Ta-0.032
Token mom
Token ID1995
Feature activation-9.17e-04

Pos logit contributions
mary+0.046
field+0.044
chard+0.043
 stall+0.043
 rightful+0.040
Neg logit contributions
hing-0.043
 ah-0.043
Ta-0.041
 applause-0.040
 boom-0.040
Token said
Token ID531
Feature activation+8.77e-03

Pos logit contributions
hing+0.002
 ah+0.002
Ta+0.002
aid+0.001
 boom+0.001
Neg logit contributions
 stall-0.002
field-0.001
 rightful-0.001
mary-0.001
chard-0.001
Token he
Token ID339
Feature activation+6.77e-02

Pos logit contributions
field+0.014
 stall+0.014
 rightful+0.014
mary+0.014
chard+0.013
Neg logit contributions
hing-0.016
 ah-0.016
Ta-0.015
 boom-0.015
 applause-0.014
Token could
Token ID714
Feature activation+1.87e-02

Pos logit contributions
 stall+0.116
field+0.114
mary+0.107
 rightful+0.104
chard+0.103
Neg logit contributions
hing-0.107
 ah-0.104
aid-0.103
ez-0.102
Ta-0.101
Token earn
Token ID5160
Feature activation+6.71e-02

Pos logit contributions
mary+0.040
field+0.039
 stall+0.038
chard+0.038
 stalls+0.037
Neg logit contributions
hing-0.023
 bang-0.021
aid-0.020
 sorry-0.020
 applause-0.019
Token money
Token ID1637
Feature activation+6.07e-02

Pos logit contributions
field+0.142
mary+0.133
 stall+0.126
 rightful+0.121
chard+0.121
Neg logit contributions
hing-0.098
aid-0.095
 ah-0.093
 applause-0.090
 boom-0.087
Token by
Token ID416
Feature activation-1.02e-02

Pos logit contributions
field+0.138
mary+0.132
 rightful+0.118
 stall+0.116
chard+0.116
Neg logit contributions
aid-0.076
 of-0.069
hing-0.068
ock-0.059
ay-0.059
Token doing
Token ID1804
Feature activation+1.67e-02

Pos logit contributions
 ah+0.016
hing+0.016
 applause+0.014
 boom+0.014
 sorry+0.014
Neg logit contributions
mary-0.020
field-0.019
 stall-0.018
chard-0.017
 rightful-0.017
Token chores
Token ID46173
Feature activation+5.17e-02

Pos logit contributions
field+0.036
mary+0.034
chard+0.033
 stall+0.032
 rightful+0.030
Neg logit contributions
hing-0.023
 ah-0.021
 applause-0.020
 sorry-0.020
 bang-0.020
Token.
Token ID13
Feature activation+6.88e-03

Pos logit contributions
mary+0.095
 rightful+0.094
field+0.091
 stall+0.087
chard+0.086
Neg logit contributions
hing-0.084
ock-0.071
he-0.070
ay-0.067
 boom-0.067
Token So
Token ID1406
Feature activation+2.85e-02

Pos logit contributions
 stall+0.010
field+0.010
mary+0.010
 rightful+0.010
chard+0.009
Neg logit contributions
hing-0.014
 ah-0.013
Ta-0.013
 boom-0.012
 applause-0.012
Token.
Token ID13
Feature activation-5.06e-03

Pos logit contributions
hing+0.034
 ah+0.033
 applause+0.031
 boom+0.031
ez+0.030
Neg logit contributions
field-0.027
 rightful-0.026
 stall-0.025
mary-0.025
 bank-0.024
Token They
Token ID1119
Feature activation+7.51e-03

Pos logit contributions
hing+0.009
Ta+0.009
 applause+0.009
 ah+0.009
 boom+0.008
Neg logit contributions
field-0.008
mary-0.008
 stall-0.008
 bank-0.008
chard-0.008
Token liked
Token ID8288
Feature activation+9.66e-03

Pos logit contributions
 stall+0.012
field+0.011
 rightful+0.011
mary+0.011
chard+0.011
Neg logit contributions
hing-0.015
 ah-0.014
Ta-0.013
 applause-0.013
 boom-0.013
Token to
Token ID284
Feature activation-8.39e-03

Pos logit contributions
 stall+0.010
mary+0.010
chard+0.009
field+0.009
 rightful+0.009
Neg logit contributions
hing-0.024
 ah-0.022
Ta-0.022
ickets-0.021
 boom-0.021
Token solve
Token ID8494
Feature activation+5.26e-02

Pos logit contributions
hing+0.014
Ta+0.014
 ah+0.013
ez+0.013
aid+0.012
Neg logit contributions
 shelf-0.014
mary-0.014
 stall-0.014
 bank-0.014
 rightful-0.014
Token puzzles
Token ID24367
Feature activation+6.10e-02

Pos logit contributions
field+0.100
 rightful+0.098
 stall+0.095
chard+0.094
 seller+0.093
Neg logit contributions
hing-0.075
 boom-0.074
 ah-0.071
 applause-0.070
 bang-0.066
Token and
Token ID290
Feature activation-1.38e-03

Pos logit contributions
 rightful+0.107
mary+0.103
chard+0.101
field+0.100
 redd+0.098
Neg logit contributions
hing-0.089
 boom-0.086
 of-0.085
 applause-0.082
aid-0.075
Token r
Token ID374
Feature activation+1.83e-03

Pos logit contributions
hing+0.002
 ah+0.002
Ta+0.002
 boom+0.002
 applause+0.002
Neg logit contributions
 stall-0.002
mary-0.002
field-0.002
 rightful-0.002
chard-0.002
Tokeniddles
Token ID29319
Feature activation+1.66e-02

Pos logit contributions
 stall+0.003
mary+0.003
field+0.003
 rightful+0.003
chard+0.003
Neg logit contributions
hing-0.003
 ah-0.003
Ta-0.003
 applause-0.003
 boom-0.003
Token.
Token ID13
Feature activation+5.41e-03

Pos logit contributions
 rightful+0.023
field+0.023
chard+0.023
 stall+0.021
mary+0.021
Neg logit contributions
hing-0.035
 ah-0.032
 applause-0.031
aid-0.030
 boom-0.030
Token One
Token ID1881
Feature activation+3.58e-02

Pos logit contributions
field+0.007
mary+0.007
 stall+0.007
chard+0.007
 rightful+0.007
Neg logit contributions
hing-0.011
 ah-0.011
 applause-0.011
Ta-0.011
 Boom-0.010
Token this
Token ID428
Feature activation-2.33e-03

Pos logit contributions
mary+0.076
field+0.076
 stall+0.075
 rightful+0.073
chard+0.070
Neg logit contributions
hing-0.069
 ah-0.068
 boom-0.063
 applause-0.062
Ta-0.058
Token prize
Token ID11596
Feature activation+3.68e-02

Pos logit contributions
hing+0.003
 ah+0.003
 applause+0.003
 boom+0.003
Ta+0.003
Neg logit contributions
mary-0.005
field-0.005
 rightful-0.005
 stall-0.004
chard-0.004
Token if
Token ID611
Feature activation+1.22e-02

Pos logit contributions
mary+0.066
 rightful+0.064
field+0.062
 stall+0.061
chard+0.061
Neg logit contributions
hing-0.057
 ah-0.056
 applause-0.052
 boom-0.051
ickets-0.051
Token you
Token ID345
Feature activation-3.06e-02

Pos logit contributions
mary+0.029
 stall+0.029
field+0.028
 rightful+0.028
 bank+0.027
Neg logit contributions
 ah-0.012
hing-0.012
 applause-0.011
Ta-0.010
 boom-0.010
Token take
Token ID1011
Feature activation+1.28e-02

Pos logit contributions
hing+0.045
 ah+0.038
Ta+0.037
 applause+0.036
 boom+0.035
Neg logit contributions
mary-0.064
 stall-0.064
field-0.062
 rightful-0.061
chard-0.061
Token five
Token ID1936
Feature activation+6.99e-02

Pos logit contributions
 stall+0.022
mary+0.022
field+0.022
 rightful+0.021
chard+0.021
Neg logit contributions
hing-0.022
 ah-0.021
Ta-0.020
 boom-0.019
 applause-0.019
Token steps
Token ID4831
Feature activation+1.13e-02

Pos logit contributions
field+0.131
mary+0.126
 rightful+0.124
chard+0.121
 stall+0.115
Neg logit contributions
hing-0.112
 ah-0.107
 applause-0.105
 boom-0.100
 bang-0.097
Token.
Token ID13
Feature activation+4.19e-03

Pos logit contributions
 rightful+0.020
mary+0.019
field+0.019
 stall+0.019
 bank+0.018
Neg logit contributions
hing-0.020
 ah-0.018
 boom-0.018
 applause-0.016
ickets-0.016
Token It
Token ID632
Feature activation-2.28e-04

Pos logit contributions
 stall+0.007
mary+0.007
field+0.007
 rightful+0.007
chard+0.007
Neg logit contributions
hing-0.007
 ah-0.007
Ta-0.006
 boom-0.006
 applause-0.006
Token's
Token ID338
Feature activation+2.60e-02

Pos logit contributions
hing+0.000
 ah+0.000
Ta+0.000
 boom+0.000
ickets+0.000
Neg logit contributions
chard-0.000
 stall-0.000
 rightful-0.000
field-0.000
mary-0.000
Token a
Token ID257
Feature activation+2.27e-02

Pos logit contributions
 stall+0.050
field+0.050
 bank+0.048
mary+0.048
 rightful+0.046
Neg logit contributions
hing-0.037
 boom-0.035
 applause-0.034
 sorry-0.033
 ah-0.033
Token
Token ID198
Feature activation+2.35e-02

Pos logit contributions
 rightful+0.030
mary+0.029
field+0.029
 bank+0.028
 stall+0.028
Neg logit contributions
hing-0.034
 ah-0.033
Ta-0.032
 boom-0.031
 applause-0.030
Token
Token ID198
Feature activation+2.48e-02

Pos logit contributions
 stall+0.026
mary+0.024
field+0.024
 shelf+0.023
 rightful+0.022
Neg logit contributions
hing-0.057
 ah-0.055
Ta-0.053
 applause-0.052
 boom-0.050
Token"
Token ID1
Feature activation+3.16e-02

Pos logit contributions
 stall+0.033
mary+0.033
 rightful+0.033
field+0.033
chard+0.032
Neg logit contributions
hing-0.053
 ah-0.050
Ta-0.049
 boom-0.047
 applause-0.046
TokenLike
Token ID7594
Feature activation+1.97e-02

Pos logit contributions
 stall+0.048
 rightful+0.048
mary+0.048
field+0.048
 bank+0.046
Neg logit contributions
hing-0.061
Ta-0.058
 ah-0.057
 applause-0.054
aid-0.053
Token scissors
Token ID41786
Feature activation+1.39e-02

Pos logit contributions
 stall+0.037
mary+0.036
field+0.036
 rightful+0.035
chard+0.035
Neg logit contributions
hing-0.032
 ah-0.030
Ta-0.028
 boom-0.027
 applause-0.027
Token or
Token ID393
Feature activation+6.08e-02

Pos logit contributions
 stall+0.020
 rightful+0.019
field+0.019
mary+0.019
chard+0.019
Neg logit contributions
hing-0.029
 ah-0.027
 boom-0.026
Ta-0.025
 applause-0.025
Token knives
Token ID23110
Feature activation+2.60e-02

Pos logit contributions
 stall+0.097
mary+0.094
 rightful+0.093
field+0.093
 shelf+0.093
Neg logit contributions
hing-0.114
 ah-0.105
Ta-0.103
 boom-0.097
ickets-0.097
Token or
Token ID393
Feature activation+5.70e-02

Pos logit contributions
 rightful+0.042
mary+0.040
 stall+0.040
field+0.039
chard+0.038
Neg logit contributions
hing-0.051
 ah-0.046
 boom-0.045
aid-0.042
ickets-0.042
Token guns
Token ID6541
Feature activation+7.32e-03

Pos logit contributions
 stall+0.094
mary+0.092
field+0.091
 rightful+0.090
chard+0.088
Neg logit contributions
hing-0.104
 ah-0.098
Ta-0.095
 boom-0.090
 applause-0.089
Token,"
Token ID553
Feature activation+3.61e-02

Pos logit contributions
 rightful+0.011
mary+0.011
 stall+0.011
field+0.011
chard+0.010
Neg logit contributions
hing-0.015
 ah-0.013
 boom-0.013
Ta-0.013
 applause-0.012
Token Dad
Token ID17415
Feature activation-8.39e-03

Pos logit contributions
 stall+0.048
field+0.046
chard+0.045
mary+0.045
 rightful+0.045
Neg logit contributions
hing-0.080
 ah-0.073
Ta-0.073
ickets-0.069
 boom-0.069
Token a
Token ID257
Feature activation+2.19e-02

Pos logit contributions
hing+0.017
 ah+0.016
Ta+0.015
 boom+0.015
 applause+0.015
Neg logit contributions
 stall-0.013
mary-0.012
 rightful-0.012
field-0.012
chard-0.012
Token new
Token ID649
Feature activation+2.07e-03

Pos logit contributions
mary+0.037
field+0.037
 rightful+0.037
 stall+0.036
 bank+0.035
Neg logit contributions
hing-0.034
 ah-0.034
 boom-0.033
Ta-0.032
 applause-0.032
Token book
Token ID1492
Feature activation+2.58e-02

Pos logit contributions
mary+0.004
field+0.004
 rightful+0.004
chard+0.004
 stall+0.004
Neg logit contributions
 ah-0.003
hing-0.003
 applause-0.003
 boom-0.003
Ta-0.003
Token in
Token ID287
Feature activation+2.97e-02

Pos logit contributions
 rightful+0.047
field+0.045
mary+0.045
 bank+0.044
 stall+0.044
Neg logit contributions
hing-0.042
 boom-0.037
Ta-0.037
 ah-0.036
ickets-0.035
Token the
Token ID262
Feature activation-1.88e-03

Pos logit contributions
mary+0.065
field+0.062
chard+0.061
 bank+0.059
 rightful+0.058
Neg logit contributions
 applause-0.035
 ah-0.035
 boom-0.032
hing-0.031
Ta-0.030
Token library
Token ID5888
Feature activation+5.97e-02

Pos logit contributions
Ta+0.003
hing+0.003
 applause+0.003
 boom+0.003
 ah+0.003
Neg logit contributions
mary-0.003
field-0.003
chard-0.003
 rightful-0.003
 stall-0.003
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
mary+0.097
 rightful+0.096
 ju+0.095
field+0.094
chard+0.092
Neg logit contributions
 of-0.083
 applause-0.080
hing-0.080
 boom-0.079
 ah-0.079
Token It
Token ID632
Feature activation-8.40e-04

Pos logit contributions
 rightful+0.025
field+0.024
chard+0.024
 stall+0.023
mary+0.023
Neg logit contributions
 ah-0.009
 Boom-0.009
hing-0.009
Ta-0.008
apy-0.008
Token has
Token ID468
Feature activation+4.42e-02

Pos logit contributions
hing+0.001
 ah+0.001
Ta+0.001
 bang+0.001
 boom+0.001
Neg logit contributions
chard-0.002
 rightful-0.002
field-0.002
 stall-0.002
 buyer-0.002
Token many
Token ID867
Feature activation+2.51e-02

Pos logit contributions
field+0.073
 stall+0.073
mary+0.073
 rightful+0.071
chard+0.070
Neg logit contributions
hing-0.078
 ah-0.074
Ta-0.074
 applause-0.069
 boom-0.069
Token pictures
Token ID5986
Feature activation-4.39e-03

Pos logit contributions
field+0.046
mary+0.045
 stall+0.044
chard+0.044
 rightful+0.044
Neg logit contributions
hing-0.041
 ah-0.039
Ta-0.038
 applause-0.036
 boom-0.035
Token all
Token ID477
Feature activation-2.72e-02

Pos logit contributions
 rightful+0.018
 stall+0.018
mary+0.018
field+0.018
 shelf+0.017
Neg logit contributions
hing-0.016
 ah-0.014
 boom-0.013
 applause-0.013
ez-0.012
Token alone
Token ID3436
Feature activation-1.19e-03

Pos logit contributions
 ah+0.054
Ta+0.054
hing+0.054
aid+0.049
ickets+0.049
Neg logit contributions
mary-0.037
field-0.037
chard-0.036
 stall-0.036
 rightful-0.036
Token.
Token ID13
Feature activation-1.73e-03

Pos logit contributions
hing+0.003
 ah+0.003
 boom+0.002
 applause+0.002
ez+0.002
Neg logit contributions
 stall-0.001
 rightful-0.001
mary-0.001
field-0.001
 shelf-0.001
Token The
Token ID383
Feature activation+9.86e-03

Pos logit contributions
hing+0.003
 ah+0.002
Ta+0.002
 applause+0.002
 boom+0.002
Neg logit contributions
 stall-0.003
field-0.003
 rightful-0.003
mary-0.003
chard-0.003
Token spider
Token ID19230
Feature activation-2.33e-02

Pos logit contributions
 shelf+0.018
mary+0.016
 stall+0.016
chard+0.015
 rightful+0.015
Neg logit contributions
hing-0.020
 ah-0.017
Ta-0.016
aid-0.016
leaf-0.015
Token asked
Token ID1965
Feature activation+1.01e-02

Pos logit contributions
hing+0.046
 ah+0.044
Ta+0.042
 boom+0.041
 applause+0.041
Neg logit contributions
 stall-0.034
 rightful-0.033
field-0.032
mary-0.032
chard-0.032
Token the
Token ID262
Feature activation+2.91e-02

Pos logit contributions
 stall+0.015
mary+0.015
field+0.015
 rightful+0.015
chard+0.014
Neg logit contributions
hing-0.020
 ah-0.019
Ta-0.018
 boom-0.018
 applause-0.017
Token skin
Token ID4168
Feature activation-2.25e-02

Pos logit contributions
 shelf+0.056
 stall+0.055
mary+0.055
 rightful+0.054
field+0.053
Neg logit contributions
hing-0.049
 ah-0.043
Ta-0.041
aid-0.039
 boom-0.037
Token if
Token ID611
Feature activation+9.59e-03

Pos logit contributions
hing+0.046
 ah+0.044
Ta+0.041
 boom+0.041
 applause+0.040
Neg logit contributions
 stall-0.032
 rightful-0.031
field-0.031
mary-0.030
 bank-0.029
Token it
Token ID340
Feature activation+2.20e-03

Pos logit contributions
 stall+0.018
mary+0.018
field+0.017
 bank+0.017
 rightful+0.017
Neg logit contributions
 ah-0.015
hing-0.015
 boom-0.014
Ta-0.013
 applause-0.013
Token could
Token ID714
Feature activation+2.10e-02

Pos logit contributions
 stall+0.003
 rightful+0.003
field+0.003
mary+0.003
 bank+0.003
Neg logit contributions
hing-0.004
 ah-0.004
Ta-0.004
ez-0.004
aid-0.004
Token ate
Token ID15063
Feature activation+4.41e-03

Pos logit contributions
 ah+0.000
 applause+0.000
 bang+0.000
hing+0.000
aid+0.000
Neg logit contributions
field-0.001
 rightful-0.001
 stall-0.001
 shelf-0.001
mary-0.001
Token them
Token ID606
Feature activation-2.70e-03

Pos logit contributions
field+0.009
 rightful+0.009
 stall+0.009
mary+0.009
 shelf+0.009
Neg logit contributions
hing-0.006
 ah-0.006
 boom-0.005
 applause-0.005
aid-0.005
Token.
Token ID13
Feature activation+8.97e-03

Pos logit contributions
hing+0.006
 ah+0.005
aid+0.005
 boom+0.005
 applause+0.005
Neg logit contributions
field-0.004
 rightful-0.004
 stall-0.004
chard-0.003
mary-0.003
Token He
Token ID679
Feature activation+2.13e-02

Pos logit contributions
 rightful+0.015
chard+0.015
field+0.015
 bank+0.014
 stall+0.014
Neg logit contributions
 ah-0.015
hing-0.014
 Boom-0.014
 boom-0.014
apy-0.014
Token wrapped
Token ID12908
Feature activation+4.64e-03

Pos logit contributions
 stall+0.040
 rightful+0.040
field+0.039
chard+0.038
 shelf+0.038
Neg logit contributions
 ah-0.031
aid-0.028
hing-0.027
Ta-0.027
 applause-0.027
Token his
Token ID465
Feature activation+5.96e-03

Pos logit contributions
field+0.009
 rightful+0.009
 stall+0.009
mary+0.008
 shelf+0.008
Neg logit contributions
hing-0.007
 ah-0.007
Ta-0.006
 boom-0.006
 applause-0.006
Token trunk
Token ID21427
Feature activation+2.05e-02

Pos logit contributions
 stall+0.009
field+0.009
mary+0.009
 rightful+0.009
chard+0.009
Neg logit contributions
hing-0.011
 ah-0.010
Ta-0.010
 boom-0.010
 applause-0.010
Token around
Token ID1088
Feature activation-8.25e-03

Pos logit contributions
 rightful+0.035
field+0.035
 stall+0.033
mary+0.033
chard+0.031
Neg logit contributions
hing-0.034
aid-0.032
 boom-0.030
Ta-0.029
 ah-0.029
Token them
Token ID606
Feature activation-4.38e-03

Pos logit contributions
 ah+0.013
hing+0.013
 applause+0.012
 boom+0.012
ez+0.011
Neg logit contributions
 rightful-0.016
field-0.015
 stall-0.015
mary-0.014
chard-0.014
Token and
Token ID290
Feature activation-3.24e-03

Pos logit contributions
hing+0.007
aid+0.006
 boom+0.006
 ah+0.006
ez+0.006
Neg logit contributions
 rightful-0.008
field-0.008
 stall-0.007
 buyer-0.007
chard-0.007
Token gave
Token ID2921
Feature activation+9.24e-04

Pos logit contributions
 ah+0.006
hing+0.005
 applause+0.005
aid+0.005
Ta+0.005
Neg logit contributions
 stall-0.006
field-0.005
 rightful-0.005
mary-0.005
 shelf-0.005
Token cut
Token ID2005
Feature activation+1.85e-02

Pos logit contributions
 stall+0.016
 bank+0.016
 shelf+0.016
 rightful+0.015
 ones+0.015
Neg logit contributions
hing-0.022
Ta-0.020
 ah-0.019
ickets-0.019
aid-0.019
Tokenest
Token ID395
Feature activation-2.17e-02

Pos logit contributions
 stall+0.030
mary+0.029
field+0.029
 rightful+0.028
 bank+0.028
Neg logit contributions
hing-0.034
 ah-0.033
Ta-0.032
 boom-0.030
 applause-0.030
Token surprise
Token ID5975
Feature activation+8.25e-03

Pos logit contributions
hing+0.041
Ta+0.040
 ah+0.037
ickets+0.036
 boom+0.035
Neg logit contributions
 stall-0.034
 bank-0.034
 shelf-0.033
mary-0.033
 rightful-0.032
Token of
Token ID286
Feature activation-2.22e-02

Pos logit contributions
 stall+0.010
chard+0.010
 rightful+0.010
mary+0.010
field+0.010
Neg logit contributions
hing-0.018
 ah-0.017
 applause-0.016
 boom-0.016
Ta-0.015
Token all
Token ID477
Feature activation-2.71e-02

Pos logit contributions
hing+0.043
Ta+0.041
 ah+0.040
 boom+0.038
ickets+0.037
Neg logit contributions
 stall-0.034
mary-0.033
field-0.033
 rightful-0.033
chard-0.032
Token
Token ID6184
Feature activation+6.37e-03

Pos logit contributions
hing+0.052
 ah+0.049
Ta+0.048
 boom+0.046
 applause+0.046
Neg logit contributions
 stall-0.042
mary-0.041
field-0.041
 rightful-0.040
chard-0.040
Token
Token ID95
Feature activation+1.81e-02

Pos logit contributions
 stall+0.010
mary+0.010
field+0.010
 rightful+0.009
 shelf+0.009
Neg logit contributions
hing-0.012
 ah-0.012
Ta-0.011
 boom-0.011
 applause-0.011
Token
Token ID26391
Feature activation-2.78e-02

Pos logit contributions
 stall+0.033
mary+0.032
 rightful+0.032
field+0.032
 shelf+0.031
Neg logit contributions
hing-0.030
 ah-0.029
Ta-0.027
 boom-0.026
 applause-0.025
Token
Token ID447
Feature activation+3.49e-03

Pos logit contributions
hing+0.055
 ah+0.054
Ta+0.050
 boom+0.049
ickets+0.049
Neg logit contributions
 rightful-0.040
 stall-0.040
chard-0.039
 bank-0.038
mary-0.038
Token
Token ID250
Feature activation+7.72e-03

Pos logit contributions
 stall+0.005
 rightful+0.005
mary+0.005
field+0.005
chard+0.005
Neg logit contributions
hing-0.007
 ah-0.007
Ta-0.007
 boom-0.006
 applause-0.006
Token a
Token ID257
Feature activation+6.92e-04

Pos logit contributions
 stall+0.013
mary+0.013
field+0.013
 rightful+0.013
chard+0.013
Neg logit contributions
hing-0.014
 ah-0.013
Ta-0.012
 boom-0.012
 applause-0.012
Token
Token ID198
Feature activation+2.87e-02

Pos logit contributions
 stall+0.033
mary+0.032
field+0.031
 rightful+0.031
 shelf+0.030
Neg logit contributions
hing-0.060
 ah-0.057
Ta-0.055
 applause-0.053
 boom-0.053
TokenThey
Token ID2990
Feature activation+7.05e-03

Pos logit contributions
field+0.045
 stall+0.045
mary+0.044
 rightful+0.044
chard+0.043
Neg logit contributions
hing-0.055
 ah-0.051
Ta-0.051
 boom-0.048
 applause-0.047
Token hug
Token ID16225
Feature activation-2.74e-02

Pos logit contributions
 stall+0.014
mary+0.014
field+0.014
 rightful+0.014
 bank+0.014
Neg logit contributions
hing-0.010
 ah-0.009
Ta-0.009
 boom-0.008
 applause-0.008
Token the
Token ID262
Feature activation+1.24e-02

Pos logit contributions
hing+0.061
 ah+0.058
Ta+0.057
 boom+0.054
 applause+0.054
Neg logit contributions
 stall-0.035
mary-0.034
field-0.033
 rightful-0.033
chard-0.032
Token man
Token ID582
Feature activation-4.23e-04

Pos logit contributions
 stall+0.018
 rightful+0.017
field+0.017
mary+0.017
 shelf+0.017
Neg logit contributions
hing-0.026
 ah-0.024
Ta-0.024
 boom-0.022
ickets-0.022
Token and
Token ID290
Feature activation+5.92e-03

Pos logit contributions
hing+0.001
 ah+0.001
 boom+0.001
 applause+0.001
Ta+0.001
Neg logit contributions
 rightful-0.001
field-0.001
 stall-0.001
chard-0.001
mary-0.001
Token say
Token ID910
Feature activation-1.29e-02

Pos logit contributions
 stall+0.013
mary+0.013
field+0.013
 rightful+0.013
chard+0.013
Neg logit contributions
hing-0.007
 ah-0.007
Ta-0.007
 applause-0.006
 boom-0.006
Token goodbye
Token ID24829
Feature activation-6.78e-03

Pos logit contributions
hing+0.023
Ta+0.023
 ah+0.020
ickets+0.020
ez+0.019
Neg logit contributions
 stall-0.021
mary-0.021
chard-0.020
 rightful-0.019
 bank-0.019
Token.
Token ID13
Feature activation+2.20e-02

Pos logit contributions
hing+0.014
 boom+0.013
 ah+0.013
aid+0.013
 applause+0.013
Neg logit contributions
 stall-0.009
field-0.009
 rightful-0.009
chard-0.008
mary-0.008
Token They
Token ID1119
Feature activation+3.50e-03

Pos logit contributions
 rightful+0.035
field+0.035
mary+0.034
 bank+0.034
 stall+0.034
Neg logit contributions
hing-0.038
 ah-0.038
 boom-0.037
Ta-0.036
 applause-0.036
Token go
Token ID467
Feature activation-1.51e-02

Pos logit contributions
 stall+0.008
mary+0.007
field+0.007
chard+0.007
 rightful+0.007
Neg logit contributions
hing-0.005
 ah-0.004
Ta-0.004
 applause-0.004
 boom-0.004
Token mom
Token ID1995
Feature activation-1.06e-02

Pos logit contributions
 stall+0.011
mary+0.010
 rightful+0.010
 shelf+0.010
field+0.010
Neg logit contributions
hing-0.020
 ah-0.019
Ta-0.019
 boom-0.018
ickets-0.018
Tokenmy
Token ID1820
Feature activation-7.04e-03

Pos logit contributions
hing+0.021
 ah+0.020
Ta+0.020
 boom+0.019
 applause+0.019
Neg logit contributions
mary-0.015
 stall-0.015
field-0.015
 rightful-0.014
chard-0.014
Token was
Token ID373
Feature activation+8.56e-04

Pos logit contributions
hing+0.014
 ah+0.013
Ta+0.013
 applause+0.012
 boom+0.012
Neg logit contributions
 stall-0.011
 rightful-0.010
field-0.010
mary-0.010
chard-0.010
Token happy
Token ID3772
Feature activation-1.82e-02

Pos logit contributions
 stall+0.001
field+0.001
 rightful+0.001
 bank+0.001
mary+0.001
Neg logit contributions
hing-0.002
 ah-0.001
Ta-0.001
 applause-0.001
 boom-0.001
Token that
Token ID326
Feature activation-2.29e-02

Pos logit contributions
hing+0.036
 ah+0.035
 applause+0.033
 boom+0.033
Ta+0.032
Neg logit contributions
 stall-0.027
field-0.026
mary-0.026
 rightful-0.026
 bank-0.025
Token Lily
Token ID20037
Feature activation+2.12e-02

Pos logit contributions
 ah+0.033
hing+0.032
 applause+0.029
 boom+0.028
apy+0.027
Neg logit contributions
 stall-0.049
field-0.047
 bank-0.045
 rightful-0.045
mary-0.044
Token was
Token ID373
Feature activation-1.89e-02

Pos logit contributions
 stall+0.035
chard+0.033
 rightful+0.032
field+0.032
 bank+0.030
Neg logit contributions
hing-0.041
 ah-0.037
 applause-0.035
Ta-0.035
ez-0.034
Token interested
Token ID4609
Feature activation-8.16e-04

Pos logit contributions
hing+0.031
 ah+0.029
Ta+0.028
 boom+0.027
 applause+0.027
Neg logit contributions
 stall-0.035
field-0.034
mary-0.033
 rightful-0.033
 bank-0.033
Token in
Token ID287
Feature activation+1.10e-02

Pos logit contributions
hing+0.001
 ah+0.001
 applause+0.001
 boom+0.001
ez+0.001
Neg logit contributions
field-0.002
 bank-0.002
 stall-0.002
 rightful-0.002
mary-0.001
Token music
Token ID2647
Feature activation+4.58e-03

Pos logit contributions
 stall+0.019
field+0.018
mary+0.018
 rightful+0.018
chard+0.018
Neg logit contributions
hing-0.019
 ah-0.018
Ta-0.017
 applause-0.017
 boom-0.017
Token,
Token ID11
Feature activation-6.49e-03

Pos logit contributions
 stall+0.006
 rightful+0.006
chard+0.006
field+0.006
mary+0.006
Neg logit contributions
hing-0.010
 ah-0.009
 applause-0.009
 boom-0.009
ickets-0.008
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
field+0.035
 stall+0.035
 rightful+0.033
chard+0.033
mary+0.033
Neg logit contributions
hing-0.033
 ah-0.032
 applause-0.029
 boom-0.029
aid-0.027
Token It
Token ID632
Feature activation-1.32e-02

Pos logit contributions
hing+0.019
 ah+0.018
Ta+0.018
 applause+0.017
 boom+0.016
Neg logit contributions
 stall-0.021
field-0.021
mary-0.021
 rightful-0.020
 bank-0.020
Token was
Token ID373
Feature activation+9.18e-03

Pos logit contributions
hing+0.026
 ah+0.025
Ta+0.024
 boom+0.023
 applause+0.023
Neg logit contributions
 stall-0.021
field-0.019
 rightful-0.019
chard-0.019
 bank-0.018
Token no
Token ID645
Feature activation+1.83e-02

Pos logit contributions
 stall+0.016
field+0.016
 bank+0.015
 rightful+0.014
mary+0.014
Neg logit contributions
hing-0.015
 ah-0.015
 boom-0.014
 applause-0.014
Ta-0.014
Token longer
Token ID2392
Feature activation+3.77e-02

Pos logit contributions
 stall+0.029
 rightful+0.029
 shelf+0.028
mary+0.028
 bank+0.028
Neg logit contributions
hing-0.036
Ta-0.033
 ah-0.033
ickets-0.031
 boom-0.030
Token good
Token ID922
Feature activation+5.85e-03

Pos logit contributions
 stall+0.061
field+0.060
mary+0.059
 rightful+0.058
chard+0.057
Neg logit contributions
hing-0.069
 ah-0.066
Ta-0.063
 applause-0.061
 boom-0.061
Token to
Token ID284
Feature activation-3.13e-02

Pos logit contributions
 stall+0.008
mary+0.007
field+0.007
 rightful+0.007
chard+0.007
Neg logit contributions
hing-0.013
 ah-0.012
Ta-0.012
 applause-0.011
 boom-0.011
Token eat
Token ID4483
Feature activation+2.49e-02

Pos logit contributions
hing+0.059
Ta+0.056
 ah+0.054
ickets+0.051
 boom+0.050
Neg logit contributions
 rightful-0.050
 shelf-0.050
 stall-0.050
mary-0.049
field-0.049
Token.
Token ID13
Feature activation-1.62e-02

Pos logit contributions
field+0.042
 rightful+0.040
 stall+0.039
mary+0.038
chard+0.037
Neg logit contributions
 ah-0.041
hing-0.041
 boom-0.038
 applause-0.038
 relief-0.035
Token
Token ID198
Feature activation-6.81e-03

Pos logit contributions
hing+0.031
 ah+0.029
Ta+0.029
 applause+0.027
 boom+0.027
Neg logit contributions
 stall-0.025
field-0.025
mary-0.024
 rightful-0.024
chard-0.023
Token
Token ID198
Feature activation-1.95e-03

Pos logit contributions
hing+0.017
 ah+0.016
Ta+0.015
 boom+0.015
 applause+0.015
Neg logit contributions
 stall-0.007
mary-0.007
 shelf-0.007
field-0.006
 rightful-0.006
Token the
Token ID262
Feature activation-1.91e-02

Pos logit contributions
hing+0.017
 ah+0.016
Ta+0.015
 applause+0.014
 boom+0.014
Neg logit contributions
mary-0.016
 stall-0.016
field-0.015
 rightful-0.015
chard-0.015
Token very
Token ID845
Feature activation+4.18e-03

Pos logit contributions
hing+0.036
 boom+0.033
 ah+0.032
Ta+0.032
 relief+0.032
Neg logit contributions
mary-0.030
field-0.027
chard-0.025
 stall-0.025
 rightful-0.025
Token top
Token ID1353
Feature activation+9.27e-03

Pos logit contributions
mary+0.007
field+0.006
 stall+0.006
chard+0.006
 rightful+0.006
Neg logit contributions
apy-0.007
hing-0.006
 boom-0.006
 ah-0.006
aid-0.006
Token.
Token ID13
Feature activation-1.02e-02

Pos logit contributions
 rightful+0.017
mary+0.017
chard+0.017
esty+0.016
 stall+0.015
Neg logit contributions
hing-0.013
 of-0.013
on-0.012
 boom-0.012
ay-0.012
Token The
Token ID383
Feature activation+6.04e-03

Pos logit contributions
hing+0.017
 ah+0.016
Ta+0.016
 applause+0.015
 boom+0.015
Neg logit contributions
 rightful-0.018
 stall-0.018
mary-0.018
field-0.018
chard-0.017
Token bald
Token ID28273
Feature activation-1.00e-02

Pos logit contributions
mary+0.012
field+0.012
 stall+0.011
chard+0.011
 rightful+0.011
Neg logit contributions
hing-0.009
Ta-0.009
 ah-0.008
 boom-0.008
 applause-0.008
Token man
Token ID582
Feature activation-1.66e-02

Pos logit contributions
hing+0.022
 ah+0.020
Ta+0.020
 boom+0.020
aid+0.020
Neg logit contributions
mary-0.013
field-0.013
chard-0.013
 stall-0.012
 rightful-0.012
Token was
Token ID373
Feature activation-9.39e-03

Pos logit contributions
hing+0.031
 ah+0.030
Ta+0.027
aid+0.027
ez+0.026
Neg logit contributions
 rightful-0.027
 stall-0.026
chard-0.025
field-0.025
 shelf-0.024
Token very
Token ID845
Feature activation+3.28e-02

Pos logit contributions
hing+0.017
 ah+0.016
Ta+0.016
 boom+0.015
 applause+0.015
Neg logit contributions
 stall-0.016
mary-0.015
field-0.015
 rightful-0.015
chard-0.015
Token grateful
Token ID14066
Feature activation+1.12e-02

Pos logit contributions
 stall+0.069
field+0.069
mary+0.069
 rightful+0.067
 bank+0.067
Neg logit contributions
hing-0.044
 ah-0.041
Ta-0.038
 applause-0.036
 boom-0.036
Token to
Token ID284
Feature activation-1.02e-02

Pos logit contributions
chard+0.022
mary+0.022
 bank+0.021
 stall+0.021
 rightful+0.020
Neg logit contributions
 applause-0.014
hing-0.013
 of-0.013
 boom-0.013
aid-0.013
Token smelled
Token ID37609
Feature activation+1.12e-02

Pos logit contributions
 stall+0.014
mary+0.014
field+0.014
 rightful+0.014
 bank+0.013
Neg logit contributions
hing-0.018
 ah-0.017
Ta-0.016
 boom-0.015
 applause-0.015
Token really
Token ID1107
Feature activation+3.13e-02

Pos logit contributions
 stall+0.018
mary+0.018
field+0.018
 rightful+0.018
chard+0.017
Neg logit contributions
hing-0.020
 ah-0.019
Ta-0.019
 boom-0.018
 applause-0.018
Token nice
Token ID3621
Feature activation+1.05e-02

Pos logit contributions
 stall+0.065
field+0.064
chard+0.062
mary+0.061
 rightful+0.061
Neg logit contributions
hing-0.046
 ah-0.043
 boom-0.039
 applause-0.039
apy-0.038
Token.
Token ID13
Feature activation-5.79e-03

Pos logit contributions
chard+0.014
field+0.014
 stall+0.014
 rightful+0.013
mary+0.013
Neg logit contributions
hing-0.023
 ah-0.021
 applause-0.020
 boom-0.020
ickets-0.020
Token He
Token ID679
Feature activation+2.00e-02

Pos logit contributions
hing+0.011
 ah+0.010
Ta+0.010
 boom+0.009
 applause+0.009
Neg logit contributions
 rightful-0.009
 stall-0.009
field-0.009
mary-0.009
chard-0.009
Token had
Token ID550
Feature activation+5.38e-03

Pos logit contributions
 stall+0.034
 rightful+0.033
field+0.032
mary+0.032
chard+0.032
Neg logit contributions
hing-0.036
 ah-0.034
Ta-0.033
 applause-0.031
 boom-0.031
Token fun
Token ID1257
Feature activation-1.71e-02

Pos logit contributions
 stall+0.008
field+0.008
mary+0.008
 rightful+0.008
chard+0.008
Neg logit contributions
hing-0.010
 ah-0.010
Ta-0.009
 applause-0.009
 boom-0.009
Token playing
Token ID2712
Feature activation-1.32e-02

Pos logit contributions
Ta+0.039
hing+0.036
 ah+0.033
aid+0.033
ickets+0.033
Neg logit contributions
 ones-0.021
mary-0.021
field-0.021
 shelf-0.021
 bank-0.020
Token with
Token ID351
Feature activation+1.10e-02

Pos logit contributions
hing+0.032
Ta+0.031
 ah+0.030
ickets+0.029
aid+0.028
Neg logit contributions
 stall-0.014
mary-0.013
 shelf-0.013
 bank-0.013
field-0.013
Token the
Token ID262
Feature activation-3.61e-03

Pos logit contributions
 stall+0.017
mary+0.016
field+0.016
 rightful+0.016
chard+0.016
Neg logit contributions
hing-0.021
 ah-0.020
Ta-0.020
 boom-0.019
 applause-0.019
Token bubbles
Token ID25037
Feature activation-1.41e-02

Pos logit contributions
hing+0.006
 ah+0.006
Ta+0.006
aid+0.005
 boom+0.005
Neg logit contributions
 stall-0.006
 rightful-0.006
 shelf-0.006
mary-0.006
field-0.006
Token is
Token ID318
Feature activation-2.03e-03

Pos logit contributions
 stall+0.048
field+0.047
chard+0.047
 rightful+0.046
mary+0.046
Neg logit contributions
hing-0.046
 ah-0.044
Ta-0.043
 applause-0.041
 boom-0.041
Token busy
Token ID8179
Feature activation+1.88e-02

Pos logit contributions
hing+0.004
 ah+0.004
Ta+0.004
ickets+0.003
 applause+0.003
Neg logit contributions
 stall-0.003
chard-0.003
mary-0.003
 rightful-0.003
field-0.003
Token playing
Token ID2712
Feature activation-4.13e-03

Pos logit contributions
 stall+0.025
mary+0.025
field+0.024
 rightful+0.024
 shelf+0.024
Neg logit contributions
hing-0.040
Ta-0.038
 ah-0.038
 boom-0.035
 applause-0.035
Token with
Token ID351
Feature activation+1.65e-02

Pos logit contributions
hing+0.010
 ah+0.009
Ta+0.009
 boom+0.009
 applause+0.009
Neg logit contributions
 stall-0.005
mary-0.005
field-0.005
 rightful-0.004
chard-0.004
Token the
Token ID262
Feature activation+1.76e-03

Pos logit contributions
 stall+0.025
mary+0.025
field+0.025
 rightful+0.025
chard+0.024
Neg logit contributions
hing-0.032
 ah-0.030
Ta-0.029
 boom-0.028
 applause-0.028
Token ball
Token ID2613
Feature activation+2.82e-03

Pos logit contributions
 shelf+0.003
 ones+0.003
 stall+0.003
 bank+0.003
 rightful+0.003
Neg logit contributions
hing-0.003
 ah-0.003
Ta-0.003
ez-0.003
aid-0.002
Token.
Token ID13
Feature activation+6.11e-03

Pos logit contributions
 rightful+0.004
 stall+0.004
mary+0.004
field+0.004
chard+0.003
Neg logit contributions
hing-0.006
 boom-0.006
 ah-0.006
 applause-0.005
ickets-0.005
Token He
Token ID679
Feature activation+2.42e-02

Pos logit contributions
 stall+0.007
mary+0.007
 rightful+0.007
field+0.007
chard+0.007
Neg logit contributions
hing-0.014
 ah-0.013
Ta-0.013
 boom-0.012
 applause-0.012
Token thinks
Token ID6834
Feature activation-5.78e-03

Pos logit contributions
 stall+0.045
field+0.044
chard+0.044
 rightful+0.043
mary+0.043
Neg logit contributions
hing-0.039
 ah-0.037
Ta-0.036
 applause-0.035
 boom-0.035
Token the
Token ID262
Feature activation+3.97e-02

Pos logit contributions
hing+0.012
Ta+0.012
 ah+0.011
ickets+0.010
aid+0.010
Neg logit contributions
 stall-0.008
 shelf-0.008
mary-0.008
chard-0.008
 rightful-0.008
Token kids
Token ID3988
Feature activation+2.71e-03

Pos logit contributions
 shelf+0.062
 stall+0.060
 ones+0.059
 bank+0.059
 rightful+0.058
Neg logit contributions
hing-0.075
 ah-0.071
Ta-0.071
ez-0.068
aid-0.066
Token a
Token ID257
Feature activation-2.86e-03

Pos logit contributions
hing+0.028
 ah+0.026
Ta+0.025
ickets+0.024
 boom+0.024
Neg logit contributions
mary-0.018
 stall-0.018
 bank-0.017
 ones-0.016
 rightful-0.016
Token break
Token ID2270
Feature activation+1.16e-03

Pos logit contributions
hing+0.006
 ah+0.006
ickets+0.005
Ta+0.005
ez+0.005
Neg logit contributions
 stall-0.004
 shelf-0.004
field-0.004
mary-0.004
chard-0.004
Token,
Token ID11
Feature activation-1.32e-02

Pos logit contributions
 rightful+0.002
field+0.002
 stall+0.002
chard+0.002
mary+0.002
Neg logit contributions
hing-0.002
 ah-0.002
 boom-0.002
 applause-0.002
aid-0.002
Token lie
Token ID6486
Feature activation-6.10e-03

Pos logit contributions
hing+0.027
 ah+0.026
Ta+0.025
 applause+0.024
 boom+0.024
Neg logit contributions
 stall-0.019
mary-0.018
field-0.018
 rightful-0.018
chard-0.017
Token down
Token ID866
Feature activation+1.39e-02

Pos logit contributions
hing+0.010
 ah+0.010
 boom+0.009
aid+0.009
apy+0.008
Neg logit contributions
 rightful-0.011
 shelf-0.010
 stall-0.010
mary-0.009
field-0.009
Token and
Token ID290
Feature activation-7.83e-03

Pos logit contributions
 rightful+0.026
 stall+0.024
field+0.024
mary+0.024
 shelf+0.024
Neg logit contributions
hing-0.021
 boom-0.019
 ah-0.019
 applause-0.018
apy-0.017
Token enjoy
Token ID2883
Feature activation-1.87e-02

Pos logit contributions
hing+0.013
 ah+0.012
Ta+0.012
 boom+0.011
 applause+0.011
Neg logit contributions
 stall-0.014
mary-0.014
field-0.014
 rightful-0.014
chard-0.013
Token the
Token ID262
Feature activation-2.47e-02

Pos logit contributions
 ah+0.028
hing+0.027
 applause+0.026
 boom+0.024
 relief+0.023
Neg logit contributions
mary-0.035
 stall-0.035
 bank-0.034
 rightful-0.034
field-0.033
Token sunshine
Token ID34488
Feature activation-3.23e-02

Pos logit contributions
hing+0.039
 ah+0.036
Ta+0.035
 applause+0.034
 boom+0.033
Neg logit contributions
 stall-0.046
mary-0.046
field-0.045
 rightful-0.045
chard-0.045
Token.
Token ID13
Feature activation-2.17e-02

Pos logit contributions
hing+0.066
 ah+0.059
 applause+0.057
ickets+0.057
 boom+0.056
Neg logit contributions
 rightful-0.047
 stall-0.045
chard-0.045
mary-0.042
 bank-0.042
Token
Token ID198
Feature activation-4.97e-03

Pos logit contributions
hing+0.043
 ah+0.041
Ta+0.040
 boom+0.038
 applause+0.038
Neg logit contributions
 stall-0.032
mary-0.032
field-0.031
 rightful-0.031
chard-0.031
Token nerves
Token ID25377
Feature activation-2.23e-02

Pos logit contributions
hing+0.026
 ah+0.024
Ta+0.023
ickets+0.022
aid+0.022
Neg logit contributions
 rightful-0.021
 stall-0.021
field-0.020
mary-0.020
 bank-0.020
Token,
Token ID11
Feature activation-2.13e-02

Pos logit contributions
hing+0.048
 ah+0.045
 applause+0.042
 boom+0.042
Ta+0.041
Neg logit contributions
 stall-0.030
mary-0.029
 rightful-0.029
chard-0.029
field-0.029
Token and
Token ID290
Feature activation-1.86e-02

Pos logit contributions
hing+0.045
 ah+0.043
Ta+0.041
 applause+0.041
 boom+0.040
Neg logit contributions
 stall-0.028
mary-0.028
field-0.028
 rightful-0.027
chard-0.027
Token had
Token ID550
Feature activation-1.30e-02

Pos logit contributions
hing+0.037
 ah+0.036
Ta+0.034
 applause+0.033
 boom+0.033
Neg logit contributions
 stall-0.027
mary-0.027
field-0.026
 rightful-0.026
chard-0.026
Token a
Token ID257
Feature activation-1.85e-02

Pos logit contributions
hing+0.022
 ah+0.022
 applause+0.020
Ta+0.020
 boom+0.019
Neg logit contributions
 stall-0.023
mary-0.022
field-0.022
 shelf-0.022
chard-0.022
Token wonderful
Token ID7932
Feature activation-4.99e-02

Pos logit contributions
hing+0.031
 ah+0.029
Ta+0.028
 boom+0.026
ickets+0.026
Neg logit contributions
 stall-0.034
mary-0.033
field-0.033
 rightful-0.033
chard-0.032
Token time
Token ID640
Feature activation+7.96e-05

Pos logit contributions
hing+0.100
 ah+0.093
Ta+0.092
ickets+0.087
aid+0.085
Neg logit contributions
 stall-0.077
 rightful-0.074
field-0.074
mary-0.072
 shelf-0.072
Token.
Token ID13
Feature activation-3.48e-02

Pos logit contributions
 stall+0.000
field+0.000
mary+0.000
 rightful+0.000
 bank+0.000
Neg logit contributions
hing-0.000
Ta-0.000
 ah-0.000
 boom-0.000
 applause-0.000
Token All
Token ID1439
Feature activation-2.68e-02

Pos logit contributions
hing+0.065
 ah+0.062
Ta+0.059
ickets+0.057
 applause+0.057
Neg logit contributions
mary-0.056
 stall-0.055
chard-0.054
 rightful-0.054
field-0.053
Token the
Token ID262
Feature activation-1.59e-02

Pos logit contributions
hing+0.049
Ta+0.048
 ah+0.047
aid+0.043
 boom+0.043
Neg logit contributions
 stall-0.042
field-0.042
mary-0.041
 rightful-0.041
chard-0.039
Token people
Token ID661
Feature activation-5.94e-02

Pos logit contributions
hing+0.030
 ah+0.028
Ta+0.027
 boom+0.026
aid+0.025
Neg logit contributions
 stall-0.026
 rightful-0.025
field-0.025
mary-0.025
 bank-0.024
Token bark
Token ID21405
Feature activation-9.32e-03

Pos logit contributions
 stall+0.006
 rightful+0.005
mary+0.005
field+0.005
chard+0.005
Neg logit contributions
hing-0.007
 ah-0.007
Ta-0.006
 boom-0.006
 applause-0.006
Tokened
Token ID276
Feature activation-7.54e-03

Pos logit contributions
hing+0.011
 ah+0.010
Ta+0.009
 boom+0.009
 applause+0.009
Neg logit contributions
field-0.021
 stall-0.021
 rightful-0.021
mary-0.021
chard-0.021
Token,
Token ID11
Feature activation+8.71e-03

Pos logit contributions
hing+0.014
 ah+0.013
 boom+0.013
 applause+0.012
Ta+0.011
Neg logit contributions
field-0.013
 stall-0.012
mary-0.012
 rightful-0.012
chard-0.012
Token "
Token ID366
Feature activation+1.95e-02

Pos logit contributions
 rightful+0.011
 stall+0.011
field+0.011
mary+0.011
chard+0.010
Neg logit contributions
hing-0.018
 ah-0.018
 boom-0.017
 applause-0.017
Ta-0.017
TokenLet
Token ID5756
Feature activation-2.12e-02

Pos logit contributions
 stall+0.028
 shelf+0.026
 rightful+0.026
 bank+0.026
chard+0.025
Neg logit contributions
 ah-0.039
hing-0.038
 applause-0.035
 boom-0.035
apy-0.034
Token me
Token ID502
Feature activation-5.42e-02

Pos logit contributions
hing+0.052
 ah+0.049
Ta+0.048
 boom+0.046
 applause+0.046
Neg logit contributions
 stall-0.022
mary-0.021
field-0.021
 rightful-0.021
chard-0.020
Token go
Token ID467
Feature activation+6.51e-03

Pos logit contributions
Ta+0.110
hing+0.104
 ah+0.103
 applause+0.096
ez+0.095
Neg logit contributions
 bank-0.076
 stall-0.075
 shelf-0.074
field-0.072
mary-0.067
Token,
Token ID11
Feature activation-3.00e-03

Pos logit contributions
 stall+0.010
field+0.010
mary+0.010
 bank+0.009
 rightful+0.009
Neg logit contributions
hing-0.013
 ah-0.012
Ta-0.012
 applause-0.011
aid-0.011
Token let
Token ID1309
Feature activation-3.66e-02

Pos logit contributions
hing+0.006
Ta+0.006
 ah+0.006
ez+0.005
aid+0.005
Neg logit contributions
 shelf-0.004
 stall-0.004
chard-0.004
field-0.004
 rightful-0.004
Token me
Token ID502
Feature activation-5.03e-02

Pos logit contributions
hing+0.085
 ah+0.082
Ta+0.080
 applause+0.077
 boom+0.076
Neg logit contributions
 stall-0.041
mary-0.039
field-0.039
 rightful-0.039
 bank-0.038
Token go
Token ID467
Feature activation+6.74e-03

Pos logit contributions
Ta+0.100
hing+0.096
 ah+0.096
ez+0.089
 applause+0.088
Neg logit contributions
 bank-0.072
 stall-0.071
 shelf-0.070
field-0.069
mary-0.065
Token are
Token ID389
Feature activation-9.86e-03

Pos logit contributions
hing+0.087
 ah+0.081
Ta+0.079
 boom+0.074
 applause+0.074
Neg logit contributions
 stall-0.103
mary-0.101
field-0.101
 rightful-0.100
chard-0.098
Token even
Token ID772
Feature activation+5.84e-03

Pos logit contributions
hing+0.018
 ah+0.017
Ta+0.016
 applause+0.016
 boom+0.016
Neg logit contributions
 stall-0.016
mary-0.016
field-0.016
 rightful-0.016
chard-0.015
Token more
Token ID517
Feature activation+1.18e-02

Pos logit contributions
 stall+0.009
mary+0.009
 rightful+0.009
field+0.009
chard+0.009
Neg logit contributions
hing-0.011
 ah-0.010
Ta-0.010
 boom-0.010
 applause-0.009
Token flexible
Token ID12846
Feature activation+1.32e-02

Pos logit contributions
 stall+0.020
field+0.020
mary+0.020
chard+0.019
 rightful+0.019
Neg logit contributions
hing-0.021
 ah-0.020
 boom-0.019
 applause-0.019
Ta-0.018
Token than
Token ID621
Feature activation-1.64e-02

Pos logit contributions
 stall+0.018
mary+0.018
field+0.018
 rightful+0.018
chard+0.018
Neg logit contributions
hing-0.027
 ah-0.026
 applause-0.024
 boom-0.024
Ta-0.023
Token I
Token ID314
Feature activation-4.75e-02

Pos logit contributions
hing+0.028
 ah+0.026
Ta+0.025
 applause+0.024
 boom+0.024
Neg logit contributions
 stall-0.029
mary-0.029
field-0.028
 rightful-0.028
chard-0.027
Token thought
Token ID1807
Feature activation-1.71e-02

Pos logit contributions
hing+0.076
 ah+0.071
Ta+0.067
 applause+0.064
 boom+0.063
Neg logit contributions
 stall-0.089
mary-0.087
field-0.086
 rightful-0.086
chard-0.086
Token!
Token ID0
Feature activation-6.23e-03

Pos logit contributions
hing+0.029
 ah+0.027
Ta+0.026
 boom+0.025
 applause+0.025
Neg logit contributions
 stall-0.030
field-0.029
mary-0.029
 rightful-0.029
chard-0.029
Tokenâ
Token ID22940
Feature activation+1.35e-02

Pos logit contributions
hing+0.009
 ah+0.009
Ta+0.009
ickets+0.008
 applause+0.008
Neg logit contributions
field-0.012
 stall-0.012
mary-0.012
 rightful-0.012
 bank-0.012
Token
Token ID26391
Feature activation-1.41e-02

Pos logit contributions
 stall+0.025
mary+0.024
field+0.024
 rightful+0.024
chard+0.024
Neg logit contributions
hing-0.023
 ah-0.021
Ta-0.020
 applause-0.019
 boom-0.019
Token
Token ID198
Feature activation+1.94e-03

Pos logit contributions
 ah+0.024
hing+0.024
ickets+0.021
Ta+0.021
 boom+0.021
Neg logit contributions
 rightful-0.024
chard-0.024
 stall-0.023
mary-0.023
 bank-0.022
Token I
Token ID314
Feature activation-4.92e-02

Pos logit contributions
 stall+0.003
mary+0.003
field+0.003
 rightful+0.003
chard+0.003
Neg logit contributions
hing-0.003
 ah-0.003
Ta-0.003
 boom-0.003
 applause-0.003
Token can
Token ID460
Feature activation-1.21e-02

Pos logit contributions
hing+0.085
 ah+0.080
Ta+0.077
 boom+0.073
 applause+0.073
Neg logit contributions
 stall-0.086
mary-0.084
field-0.084
 rightful-0.083
chard-0.082
Token help
Token ID1037
Feature activation-9.50e-03

Pos logit contributions
hing+0.018
 ah+0.017
Ta+0.017
 boom+0.016
 applause+0.015
Neg logit contributions
 stall-0.023
field-0.023
mary-0.023
 rightful-0.023
 shelf-0.023
Token.
Token ID13
Feature activation+2.22e-03

Pos logit contributions
hing+0.012
 ah+0.011
Ta+0.010
 boom+0.010
 applause+0.010
Neg logit contributions
 stall-0.021
mary-0.021
field-0.021
 rightful-0.021
chard-0.020
Token All
Token ID1439
Feature activation-1.37e-02

Pos logit contributions
 stall+0.004
mary+0.004
field+0.004
 rightful+0.004
chard+0.004
Neg logit contributions
hing-0.004
 ah-0.004
Ta-0.004
 boom-0.003
 applause-0.003
Token you
Token ID345
Feature activation-5.03e-02

Pos logit contributions
hing+0.026
 ah+0.024
Ta+0.024
 boom+0.022
 applause+0.022
Neg logit contributions
 stall-0.022
mary-0.021
field-0.021
 rightful-0.021
 shelf-0.020
Token need
Token ID761
Feature activation-1.15e-02

Pos logit contributions
hing+0.093
 ah+0.089
Ta+0.088
 applause+0.081
 boom+0.081
Neg logit contributions
 stall-0.078
field-0.078
mary-0.078
 bank-0.076
 rightful-0.075
Token to
Token ID284
Feature activation-4.22e-03

Pos logit contributions
hing+0.023
 ah+0.022
Ta+0.022
 boom+0.021
 applause+0.020
Neg logit contributions
 stall-0.016
mary-0.016
field-0.016
 rightful-0.016
chard-0.015
Token do
Token ID466
Feature activation+2.29e-02

Pos logit contributions
hing+0.007
 ah+0.006
Ta+0.006
 boom+0.006
 applause+0.006
Neg logit contributions
 stall-0.008
mary-0.008
field-0.008
 rightful-0.008
chard-0.008
Token is
Token ID318
Feature activation-9.83e-03

Pos logit contributions
 stall+0.038
field+0.037
mary+0.037
 rightful+0.036
chard+0.036
Neg logit contributions
hing-0.042
 ah-0.040
Ta-0.037
 boom-0.037
 applause-0.036
Token promise
Token ID6991
Feature activation-3.68e-03

Pos logit contributions
hing+0.018
 ah+0.017
Ta+0.016
 boom+0.016
 applause+0.015
Neg logit contributions
 stall-0.016
mary-0.016
field-0.016
 rightful-0.016
chard-0.015
Token.
Token ID13
Feature activation+9.58e-03

Pos logit contributions
 rightful+0.015
 stall+0.015
field+0.014
chard+0.014
mary+0.014
Neg logit contributions
hing-0.015
 ah-0.014
 boom-0.013
aid-0.013
 applause-0.013
Token
Token ID198
Feature activation+2.13e-02

Pos logit contributions
 rightful+0.017
field+0.016
 bank+0.016
chard+0.016
 stall+0.015
Neg logit contributions
 ah-0.016
hing-0.016
Ta-0.015
 boom-0.015
 Boom-0.015
Token
Token ID198
Feature activation+2.06e-02

Pos logit contributions
 stall+0.025
mary+0.024
field+0.023
 shelf+0.022
 rightful+0.022
Neg logit contributions
hing-0.050
 ah-0.048
Ta-0.046
 applause-0.045
 boom-0.044
Token"
Token ID1
Feature activation+2.52e-02

Pos logit contributions
 stall+0.026
mary+0.025
field+0.025
 rightful+0.025
chard+0.024
Neg logit contributions
hing-0.046
 ah-0.044
Ta-0.042
 applause-0.041
 boom-0.041
TokenGot
Token ID30074
Feature activation-1.69e-02

Pos logit contributions
 stall+0.043
mary+0.040
chard+0.039
 shelf+0.039
field+0.039
Neg logit contributions
hing-0.045
 ah-0.041
ickets-0.039
 boom-0.039
 applause-0.038
Token you
Token ID345
Feature activation-4.74e-02

Pos logit contributions
hing+0.027
Ta+0.025
 ah+0.024
ickets+0.023
 applause+0.023
Neg logit contributions
 stall-0.032
mary-0.031
field-0.030
chard-0.030
 bank-0.029
Token!"
Token ID2474
Feature activation+2.22e-02

Pos logit contributions
hing+0.104
Ta+0.101
 ah+0.097
 applause+0.094
aid+0.094
Neg logit contributions
 stall-0.062
mary-0.057
 shelf-0.057
field-0.057
 bank-0.056
Token Mom
Token ID11254
Feature activation-1.92e-02

Pos logit contributions
 stall+0.033
mary+0.032
field+0.032
 rightful+0.032
chard+0.031
Neg logit contributions
hing-0.044
 ah-0.042
Ta-0.041
 boom-0.039
 applause-0.038
Token says
Token ID1139
Feature activation-4.43e-03

Pos logit contributions
hing+0.035
 ah+0.032
Ta+0.032
 applause+0.030
 boom+0.030
Neg logit contributions
 stall-0.032
mary-0.031
field-0.031
 rightful-0.030
 shelf-0.030
Token.
Token ID13
Feature activation+2.03e-02

Pos logit contributions
hing+0.011
 ah+0.011
Ta+0.010
 boom+0.010
 applause+0.010
Neg logit contributions
 stall-0.004
field-0.004
 rightful-0.004
mary-0.004
chard-0.004
Token "
Token ID366
Feature activation+2.24e-02

Pos logit contributions
 rightful+0.036
field+0.034
 bank+0.032
chard+0.032
mary+0.031
Neg logit contributions
 ah-0.034
 boom-0.033
hing-0.033
 Boom-0.032
 bang-0.031