TOP ACTIVATIONS
MAX = 0.095

lake nearby . But they didn â t know
It was dark and he didn â t know
to dance , but he didn 't like to learn .
the picture . But he didn 't know how to use
a hard one . She didn 't know the answer .
being careful . But Mary didn 't always listen .
to fly , but he didn 't have any wings .
couldn 't move . He didn 't have enough oxygen in
the water , but he didn 't like to dry off
was very confused . She didn 't know what to do
his toys , but he didn 't listen .
was very lonely because he didn 't have any friends .
play outside , but he didn 't like to clean up
bunny felt lonely because it didn 't have any bunny friends
in the woods . He didn 't know where to go
every day . But she didn 't like to listen to
the test . But she didn 't do well because she
feeling very confused . She didn 't understand why she felt
to sew something but she didn 't know how . She
day , however , he didn 't feel like z ipping

MIN ACTIVATIONS
MIN = -0.092

be safe and hugged the firefighter tightly . After
was a driver or a firefighter or a policeman .
police officer and hugged their dolls . The police officer smiled
wants to play ," one of the moms said .
him . She thanked the firefighter . She checked Tom for
lived alone in a small cottage . He didn 't have
. What happened ?" one of them asked .
are you ?" Sara says into the phone . She holds
and lived in a small cottage . One day
and dad in a small cottage . One day
their mom and thank her for the jazz CD . They
is ours now !" one of the big kids says .
her . They thank her for finding the photo . They
happy and thanked the water worm for his help . The
happy and he thanked the nurse for being so kind .
are you ?" Ben says into the phone .
Once there was a three - year - old who found
and grand pa ," one of the kids said .
the bird ," said one of his friends .
war , okay ?" one of them said .

INTERVAL 0.048 - 0.095
CONTAINS 1.467%

trucks . They will not run . They will be sad
around the park . They gigg led as they ran ,
. But he slipped and fell . He hit his head
B enny was sad and didn 't know what to do
and higher , while Speed went faster and faster .

INTERVAL 0.001 - 0.048
CONTAINS 45.963%

. " But I like the knob . It
searched high and low , but he couldn 't find any
to rot ! Lily had been careless and left them out
. The blocks fell down and the pictures on the wall
So Mom my went back to the store .

INTERVAL -0.045 - 0.001
CONTAINS 51.104%

He found many wonderful things , but
better . He was no longer hungry and he was happy
in me and love me . You are my best friend
were twins . They liked to play together , but sometimes
Lu cy 's mom said that if she took the medicine

INTERVAL -0.092 - -0.045
CONTAINS 1.466%

Lily ," the teacher said with a smile . " I
to , but she listened to her mom .
careful of dogs . Some of them are not friendly ."
mom and dad in the house . They hugged him and
about to take a sip of her tea , she heard
Token lake
Token ID13546
Feature activation-1.70e-02

Pos logit contributions
 guys+0.045
 plunge+0.043
 trigger+0.041
ived+0.040
t+0.040
Neg logit contributions
 whose-0.050
 who-0.046
elope-0.042
 named-0.041
 heaven-0.040
Token nearby
Token ID6716
Feature activation+9.35e-03

Pos logit contributions
 whose+0.029
 who+0.025
elope+0.024
 named+0.023
 spe+0.023
Neg logit contributions
 guys-0.034
 plunge-0.031
 tournament-0.030
boards-0.029
 trigger-0.028
Token.
Token ID13
Feature activation+3.12e-02

Pos logit contributions
 guys+0.019
 plunge+0.017
 tournament+0.016
boards+0.016
 trigger+0.015
Neg logit contributions
 whose-0.016
 who-0.013
elope-0.013
 spe-0.013
 named-0.012
Token But
Token ID887
Feature activation+1.43e-02

Pos logit contributions
 guys+0.050
 plunge+0.046
boards+0.042
 tournament+0.042
t+0.040
Neg logit contributions
 whose-0.062
 spe-0.055
elope-0.054
 who-0.053
 heaven-0.052
Token they
Token ID484
Feature activation+4.10e-02

Pos logit contributions
 guys+0.024
 plunge+0.022
 tournament+0.019
 competition+0.018
 first+0.018
Neg logit contributions
 whose-0.026
aron-0.025
 spe-0.024
sm-0.024
 stret-0.024
Token didn
Token ID1422
Feature activation+9.44e-02

Pos logit contributions
 guys+0.071
 plunge+0.067
boards+0.064
 tournament+0.063
 trigger+0.062
Neg logit contributions
 whose-0.079
 who-0.072
 named-0.069
elope-0.066
 spe-0.061
Tokenâ
Token ID22940
Feature activation+5.36e-02

Pos logit contributions
 guys+0.110
 plunge+0.091
boards+0.082
 tournament+0.081
 trigger+0.076
Neg logit contributions
 whose-0.239
 who-0.218
 named-0.209
elope-0.209
 spe-0.204
Token
Token ID26391
Feature activation+4.04e-02

Pos logit contributions
 guys+0.091
 plunge+0.086
boards+0.079
 trigger+0.076
 tournament+0.076
Neg logit contributions
 whose-0.104
 who-0.091
elope-0.091
 named-0.089
 heaven-0.088
Token
Token ID8151
Feature activation+4.72e-02

Pos logit contributions
 guys+0.078
 plunge+0.068
boards+0.067
 tournament+0.065
t+0.065
Neg logit contributions
 whose-0.072
 who-0.060
 spe-0.060
 heaven-0.059
elope-0.059
Tokent
Token ID83
Feature activation+5.71e-02

Pos logit contributions
 guys+0.010
 plunge+0.004
t+0.002
boards+0.001
 tournament-0.001
Neg logit contributions
 whose-0.162
elope-0.149
 who-0.148
 spe-0.148
 heaven-0.147
Token know
Token ID760
Feature activation+9.45e-03

Pos logit contributions
 guys+0.101
 plunge+0.098
boards+0.093
 tournament+0.089
 trigger+0.088
Neg logit contributions
 whose-0.105
 who-0.098
 named-0.092
elope-0.090
 heaven-0.088
Token It
Token ID632
Feature activation+5.36e-02

Pos logit contributions
 guys+0.065
 plunge+0.063
 tournament+0.058
 trigger+0.053
boards+0.053
Neg logit contributions
 whose-0.070
 who-0.061
elope-0.059
 named-0.058
house-0.057
Token was
Token ID373
Feature activation+1.08e-02

Pos logit contributions
 guys+0.101
 plunge+0.094
 tournament+0.094
boards+0.088
 trigger+0.085
Neg logit contributions
 whose-0.094
 who-0.082
elope-0.082
 named-0.078
 spe-0.077
Token dark
Token ID3223
Feature activation+2.05e-02

Pos logit contributions
 guys+0.018
 plunge+0.017
boards+0.015
t+0.015
 tournament+0.014
Neg logit contributions
 whose-0.022
elope-0.019
 who-0.019
oc-0.018
 heaven-0.018
Token and
Token ID290
Feature activation-1.59e-03

Pos logit contributions
 guys+0.038
 plunge+0.033
boards+0.033
 tournament+0.031
board+0.030
Neg logit contributions
 whose-0.039
elope-0.032
 who-0.032
 named-0.031
 heaven-0.031
Token he
Token ID339
Feature activation+5.10e-02

Pos logit contributions
 whose+0.003
 who+0.003
elope+0.003
 spe+0.002
 named+0.002
Neg logit contributions
 guys-0.003
 plunge-0.003
 tournament-0.002
boards-0.002
 trigger-0.002
Token didn
Token ID1422
Feature activation+9.42e-02

Pos logit contributions
 guys+0.081
 plunge+0.074
 tournament+0.069
boards+0.068
 trigger+0.064
Neg logit contributions
 whose-0.107
 who-0.095
elope-0.092
 named-0.090
 spe-0.088
Tokenâ
Token ID22940
Feature activation+5.50e-02

Pos logit contributions
 guys+0.111
 plunge+0.092
 tournament+0.088
boards+0.084
 trigger+0.076
Neg logit contributions
 whose-0.233
 who-0.214
elope-0.207
 named-0.204
 spe-0.201
Token
Token ID26391
Feature activation+4.60e-02

Pos logit contributions
 guys+0.087
 plunge+0.082
boards+0.075
 tournament+0.073
 trigger+0.072
Neg logit contributions
 whose-0.111
elope-0.100
 who-0.099
 named-0.096
 heaven-0.096
Token
Token ID8151
Feature activation+4.54e-02

Pos logit contributions
 guys+0.073
 plunge+0.063
boards+0.061
t+0.059
 tournament+0.058
Neg logit contributions
 whose-0.099
 who-0.085
 spe-0.083
elope-0.083
 heaven-0.082
Tokent
Token ID83
Feature activation+5.55e-02

Pos logit contributions
 guys+0.013
 plunge+0.007
boards+0.002
 tournament+0.001
t+0.001
Neg logit contributions
 whose-0.153
 who-0.141
elope-0.140
 spe-0.138
 heaven-0.137
Token know
Token ID760
Feature activation+1.05e-02

Pos logit contributions
 guys+0.099
 plunge+0.092
 tournament+0.087
boards+0.086
 trigger+0.081
Neg logit contributions
 whose-0.105
 who-0.093
elope-0.088
 named-0.087
 heaven-0.085
Token to
Token ID284
Feature activation-5.19e-03

Pos logit contributions
 guys+0.035
 plunge+0.031
 tournament+0.029
boards+0.028
 trigger+0.026
Neg logit contributions
 whose-0.050
 who-0.044
elope-0.044
 named-0.042
 spe-0.042
Token dance
Token ID9280
Feature activation+3.67e-02

Pos logit contributions
 whose+0.012
 who+0.011
elope+0.011
 named+0.011
 spe+0.011
Neg logit contributions
 guys-0.007
 plunge-0.006
 tournament-0.005
boards-0.005
 trigger-0.005
Token,
Token ID11
Feature activation+1.60e-02

Pos logit contributions
 guys+0.077
 plunge+0.076
 tournament+0.069
 trigger+0.069
boards+0.067
Neg logit contributions
 whose-0.057
 who-0.050
 named-0.045
 heaven-0.043
 spe-0.042
Token but
Token ID475
Feature activation+7.30e-03

Pos logit contributions
 guys+0.025
 plunge+0.022
 tournament+0.021
boards+0.020
 trigger+0.020
Neg logit contributions
 whose-0.035
 who-0.031
elope-0.029
 named-0.029
 spe-0.029
Token he
Token ID339
Feature activation+4.83e-02

Pos logit contributions
 guys+0.012
 plunge+0.011
boards+0.010
 tournament+0.010
 trigger+0.010
Neg logit contributions
 whose-0.015
 who-0.013
 named-0.013
elope-0.013
 spe-0.012
Token didn
Token ID1422
Feature activation+9.34e-02

Pos logit contributions
 guys+0.081
 plunge+0.072
 tournament+0.068
boards+0.066
t+0.064
Neg logit contributions
 whose-0.098
 who-0.084
elope-0.083
 spe-0.081
 heaven-0.080
Token't
Token ID470
Feature activation+6.45e-02

Pos logit contributions
 guys+0.120
 plunge+0.103
 tournament+0.092
boards+0.091
 trigger+0.089
Neg logit contributions
 whose-0.220
 who-0.200
 named-0.192
elope-0.188
 heaven-0.187
Token like
Token ID588
Feature activation+2.34e-02

Pos logit contributions
 plunge+0.116
boards+0.116
 guys+0.114
 tournament+0.105
 trigger+0.105
Neg logit contributions
 whose-0.112
 who-0.108
 named-0.100
 heaven-0.096
elope-0.093
Token to
Token ID284
Feature activation+1.50e-02

Pos logit contributions
 guys+0.041
 plunge+0.039
 tournament+0.037
 trigger+0.036
boards+0.036
Neg logit contributions
 whose-0.044
 who-0.040
 named-0.036
 heaven-0.035
 spe-0.035
Token learn
Token ID2193
Feature activation+2.68e-02

Pos logit contributions
boards+0.024
 guys+0.022
 plunge+0.021
 trigger+0.021
 tournament+0.021
Neg logit contributions
 whose-0.029
 who-0.028
 named-0.026
 heaven-0.026
elope-0.024
Token.
Token ID13
Feature activation+3.12e-02

Pos logit contributions
 guys+0.051
 plunge+0.045
boards+0.043
 tournament+0.041
board+0.039
Neg logit contributions
 whose-0.047
elope-0.044
 spe-0.041
 named-0.040
 who-0.040
Token the
Token ID262
Feature activation+1.76e-02

Pos logit contributions
 guys+0.032
 plunge+0.029
boards+0.027
 tournament+0.026
 trigger+0.026
Neg logit contributions
 whose-0.035
elope-0.031
 who-0.030
 named-0.029
 heaven-0.029
Token picture
Token ID4286
Feature activation-2.15e-03

Pos logit contributions
 guys+0.033
 plunge+0.031
 tournament+0.030
boards+0.029
ived+0.027
Neg logit contributions
 whose-0.031
 who-0.027
 spe-0.025
elope-0.025
 named-0.025
Token.
Token ID13
Feature activation+3.43e-02

Pos logit contributions
 whose+0.004
 who+0.004
elope+0.003
 named+0.003
 spe+0.003
Neg logit contributions
 guys-0.004
 plunge-0.004
 tournament-0.003
boards-0.003
 trigger-0.003
Token But
Token ID887
Feature activation+1.32e-02

Pos logit contributions
 guys+0.052
 plunge+0.047
 tournament+0.043
boards+0.043
 trigger+0.040
Neg logit contributions
 whose-0.075
 who-0.066
elope-0.065
 named-0.063
 spe-0.062
Token he
Token ID339
Feature activation+5.36e-02

Pos logit contributions
 guys+0.022
 plunge+0.019
 tournament+0.017
t+0.017
boards+0.017
Neg logit contributions
 whose-0.025
elope-0.023
 spe-0.023
 who-0.022
 heaven-0.022
Token didn
Token ID1422
Feature activation+9.32e-02

Pos logit contributions
 guys+0.087
 plunge+0.079
 tournament+0.073
boards+0.072
 trigger+0.068
Neg logit contributions
 whose-0.112
 who-0.098
elope-0.095
 named-0.093
 spe-0.092
Token't
Token ID470
Feature activation+5.85e-02

Pos logit contributions
 guys+0.121
 plunge+0.103
 tournament+0.093
boards+0.090
 trigger+0.087
Neg logit contributions
 whose-0.221
 who-0.200
 named-0.193
elope-0.189
house-0.188
Token know
Token ID760
Feature activation+1.21e-02

Pos logit contributions
boards+0.122
 plunge+0.121
 guys+0.110
 trigger+0.108
 tournament+0.108
Neg logit contributions
 who-0.089
 whose-0.088
 named-0.081
 heaven-0.075
house-0.069
Token how
Token ID703
Feature activation+7.65e-03

Pos logit contributions
 guys+0.023
boards+0.021
 plunge+0.020
ly+0.018
 rocks+0.018
Neg logit contributions
elope-0.020
 heaven-0.018
 spe-0.018
 stret-0.017
oc-0.016
Token to
Token ID284
Feature activation+7.49e-03

Pos logit contributions
 guys+0.012
 plunge+0.010
 tournament+0.009
boards+0.009
t+0.009
Neg logit contributions
 whose-0.017
 who-0.015
elope-0.015
 named-0.014
 spe-0.014
Token use
Token ID779
Feature activation+1.69e-02

Pos logit contributions
 guys+0.013
 plunge+0.011
boards+0.011
 tournament+0.011
 trigger+0.010
Neg logit contributions
 whose-0.015
 who-0.014
elope-0.013
 named-0.013
 spe-0.012
Token a
Token ID257
Feature activation+6.56e-03

Pos logit contributions
 guys+0.007
 plunge+0.006
 competition+0.006
 first+0.006
t+0.006
Neg logit contributions
 whose-0.009
oc-0.009
elope-0.008
 who-0.008
aron-0.008
Token hard
Token ID1327
Feature activation+5.05e-02

Pos logit contributions
 guys+0.011
 plunge+0.010
 tournament+0.009
boards+0.009
 trigger+0.008
Neg logit contributions
 whose-0.014
 who-0.012
elope-0.012
 heaven-0.011
 named-0.011
Token one
Token ID530
Feature activation+2.09e-02

Pos logit contributions
 plunge+0.072
 guys+0.068
boards+0.065
 tournament+0.062
 trigger+0.060
Neg logit contributions
 whose-0.103
 who-0.094
 named-0.091
 heaven-0.090
elope-0.089
Token.
Token ID13
Feature activation+3.16e-02

Pos logit contributions
 guys+0.034
 plunge+0.030
 competition+0.029
t+0.029
board+0.029
Neg logit contributions
 whose-0.038
 stret-0.035
elope-0.035
 heaven-0.034
 spe-0.034
Token She
Token ID1375
Feature activation+2.46e-02

Pos logit contributions
 guys+0.063
 plunge+0.060
 tournament+0.056
boards+0.054
 trigger+0.053
Neg logit contributions
 whose-0.054
 who-0.046
elope-0.043
 named-0.043
 heaven-0.042
Token didn
Token ID1422
Feature activation+9.28e-02

Pos logit contributions
 guys+0.040
 plunge+0.037
 tournament+0.034
boards+0.033
 trigger+0.032
Neg logit contributions
 whose-0.051
 who-0.045
elope-0.044
 named-0.043
 spe-0.042
Token't
Token ID470
Feature activation+5.57e-02

Pos logit contributions
 guys+0.108
 plunge+0.091
 tournament+0.082
boards+0.081
 trigger+0.074
Neg logit contributions
 whose-0.234
 who-0.213
elope-0.204
 named-0.204
 heaven-0.199
Token know
Token ID760
Feature activation+7.76e-03

Pos logit contributions
 guys+0.098
 plunge+0.093
boards+0.087
 tournament+0.087
 trigger+0.081
Neg logit contributions
 whose-0.106
 who-0.094
elope-0.089
 named-0.088
 heaven-0.086
Token the
Token ID262
Feature activation-4.21e-03

Pos logit contributions
 guys+0.015
 plunge+0.013
boards+0.012
ly+0.012
 first+0.011
Neg logit contributions
elope-0.012
oc-0.012
 stret-0.011
aron-0.011
 spe-0.011
Token answer
Token ID3280
Feature activation+8.67e-03

Pos logit contributions
 whose+0.009
 who+0.008
elope+0.007
 named+0.007
 heaven+0.007
Neg logit contributions
 guys-0.006
 plunge-0.006
 tournament-0.005
ived-0.005
boards-0.005
Token.
Token ID13
Feature activation+2.49e-02

Pos logit contributions
 guys+0.015
 plunge+0.013
boards+0.012
board+0.012
t+0.012
Neg logit contributions
 whose-0.017
elope-0.015
 spe-0.015
 heaven-0.014
 stret-0.014
Token being
Token ID852
Feature activation-1.18e-02

Pos logit contributions
 whose+0.053
elope+0.050
oc+0.049
 spe+0.048
aron+0.046
Neg logit contributions
 guys-0.063
 plunge-0.053
boards-0.050
 tournament-0.050
 competition-0.048
Token careful
Token ID8161
Feature activation+3.03e-02

Pos logit contributions
 whose+0.022
oc+0.021
elope+0.020
 spe+0.019
 stret+0.018
Neg logit contributions
 guys-0.021
 competition-0.017
 plunge-0.017
 tournament-0.016
boards-0.016
Token.
Token ID13
Feature activation+2.83e-02

Pos logit contributions
 guys+0.058
 plunge+0.052
boards+0.049
t+0.048
 tournament+0.048
Neg logit contributions
 whose-0.054
elope-0.046
 spe-0.045
 who-0.044
 named-0.044
Token But
Token ID887
Feature activation+1.26e-02

Pos logit contributions
 guys+0.048
 plunge+0.044
boards+0.043
 tournament+0.040
t+0.040
Neg logit contributions
 whose-0.053
 spe-0.045
 who-0.045
 heaven-0.044
 named-0.043
Token Mary
Token ID5335
Feature activation+2.71e-02

Pos logit contributions
 guys+0.017
 plunge+0.016
 first+0.013
 competition+0.013
t+0.013
Neg logit contributions
 whose-0.026
 stret-0.026
oc-0.024
 spe-0.024
 heaven-0.024
Token didn
Token ID1422
Feature activation+9.26e-02

Pos logit contributions
 guys+0.039
t+0.030
 plunge+0.030
ede+0.029
boards+0.028
Neg logit contributions
 whose-0.060
 heaven-0.052
 stret-0.052
 spe-0.051
elope-0.051
Token't
Token ID470
Feature activation+5.52e-02

Pos logit contributions
 guys+0.113
 plunge+0.094
 tournament+0.085
boards+0.083
 trigger+0.081
Neg logit contributions
 whose-0.229
 who-0.209
 named-0.201
elope-0.198
 heaven-0.196
Token always
Token ID1464
Feature activation+4.09e-02

Pos logit contributions
 guys+0.086
 plunge+0.079
boards+0.073
 tournament+0.073
 trigger+0.068
Neg logit contributions
 whose-0.117
 who-0.105
elope-0.100
 named-0.099
 heaven-0.097
Token listen
Token ID6004
Feature activation+4.49e-02

Pos logit contributions
 guys+0.060
 plunge+0.053
 tournament+0.048
boards+0.045
t+0.045
Neg logit contributions
 whose-0.091
elope-0.079
 who-0.078
 spe-0.077
 named-0.076
Token.
Token ID13
Feature activation+2.89e-02

Pos logit contributions
 guys+0.078
 plunge+0.071
 tournament+0.066
boards+0.066
t+0.062
Neg logit contributions
 whose-0.088
 who-0.076
elope-0.075
 named-0.072
 spe-0.072
Token
Token ID220
Feature activation+2.29e-02

Pos logit contributions
 guys+0.048
 plunge+0.043
boards+0.043
 tournament+0.040
board+0.040
Neg logit contributions
 whose-0.056
 spe-0.049
 who-0.048
 stret-0.046
 named-0.046
Token to
Token ID284
Feature activation-4.21e-03

Pos logit contributions
 guys+0.080
 plunge+0.072
 tournament+0.068
boards+0.067
 trigger+0.064
Neg logit contributions
 whose-0.109
 who-0.096
elope-0.092
 named-0.091
 spe-0.089
Token fly
Token ID6129
Feature activation+3.31e-02

Pos logit contributions
 whose+0.010
 who+0.009
elope+0.008
 named+0.008
 heaven+0.008
Neg logit contributions
 guys-0.006
 plunge-0.005
boards-0.005
 tournament-0.005
 trigger-0.004
Token,
Token ID11
Feature activation+1.87e-02

Pos logit contributions
 guys+0.064
 plunge+0.059
 tournament+0.056
boards+0.056
 trigger+0.054
Neg logit contributions
 whose-0.059
 who-0.051
elope-0.048
 named-0.047
 heaven-0.046
Token but
Token ID475
Feature activation+4.95e-03

Pos logit contributions
 guys+0.034
 plunge+0.031
 tournament+0.029
boards+0.028
 trigger+0.027
Neg logit contributions
 whose-0.035
 who-0.030
elope-0.030
 spe-0.029
 named-0.029
Token he
Token ID339
Feature activation+5.04e-02

Pos logit contributions
 guys+0.009
 plunge+0.008
t+0.007
 tournament+0.007
 competition+0.006
Neg logit contributions
 whose-0.009
aron-0.008
 who-0.008
elope-0.008
 stret-0.008
Token didn
Token ID1422
Feature activation+9.24e-02

Pos logit contributions
 guys+0.081
 plunge+0.073
 tournament+0.067
boards+0.065
t+0.064
Neg logit contributions
 whose-0.105
 who-0.091
elope-0.088
 heaven-0.088
 spe-0.088
Token't
Token ID470
Feature activation+5.77e-02

Pos logit contributions
 guys+0.111
 plunge+0.093
boards+0.086
 tournament+0.085
 trigger+0.078
Neg logit contributions
 whose-0.227
 who-0.208
 named-0.200
elope-0.200
 heaven-0.196
Token have
Token ID423
Feature activation+2.66e-02

Pos logit contributions
 guys+0.103
boards+0.101
 plunge+0.100
 tournament+0.093
 trigger+0.091
Neg logit contributions
 whose-0.102
 who-0.095
 named-0.089
elope-0.088
 heaven-0.087
Token any
Token ID597
Feature activation+1.76e-02

Pos logit contributions
 guys+0.050
 plunge+0.045
 tournament+0.041
boards+0.040
t+0.039
Neg logit contributions
 whose-0.049
elope-0.042
 who-0.042
 named-0.040
oc-0.039
Token wings
Token ID12098
Feature activation+3.30e-03

Pos logit contributions
 guys+0.031
 plunge+0.028
 tournament+0.026
boards+0.026
 trigger+0.025
Neg logit contributions
 whose-0.034
 who-0.030
elope-0.029
 named-0.028
 spe-0.028
Token.
Token ID13
Feature activation+3.64e-02

Pos logit contributions
 guys+0.006
 plunge+0.006
 tournament+0.005
boards+0.005
 trigger+0.005
Neg logit contributions
 whose-0.006
 who-0.005
elope-0.005
 named-0.005
 spe-0.005
Token couldn
Token ID3521
Feature activation+6.70e-02

Pos logit contributions
 guys+0.049
 plunge+0.045
 tournament+0.042
boards+0.041
 trigger+0.039
Neg logit contributions
 whose-0.068
 who-0.060
elope-0.058
 named-0.057
 spe-0.056
Token't
Token ID470
Feature activation+5.80e-02

Pos logit contributions
 guys+0.089
 plunge+0.075
 tournament+0.069
boards+0.069
 trigger+0.067
Neg logit contributions
 whose-0.153
 who-0.140
 named-0.137
elope-0.137
house-0.136
Token move
Token ID1445
Feature activation+4.72e-02

Pos logit contributions
boards+0.099
 guys+0.089
 tournament+0.088
 plunge+0.088
 trigger+0.084
Neg logit contributions
 whose-0.110
 who-0.110
 named-0.104
elope-0.097
 heaven-0.095
Token.
Token ID13
Feature activation+3.10e-02

Pos logit contributions
 guys+0.096
 plunge+0.091
 tournament+0.087
boards+0.085
board+0.082
Neg logit contributions
 whose-0.077
 who-0.067
 named-0.061
elope-0.061
 spe-0.060
Token He
Token ID679
Feature activation+4.17e-02

Pos logit contributions
 guys+0.052
 plunge+0.047
boards+0.046
t+0.043
 tournament+0.043
Neg logit contributions
 whose-0.060
 spe-0.052
 who-0.052
 heaven-0.051
elope-0.051
Token didn
Token ID1422
Feature activation+9.23e-02

Pos logit contributions
 guys+0.068
 plunge+0.063
 tournament+0.059
boards+0.058
 trigger+0.055
Neg logit contributions
 whose-0.086
 who-0.076
elope-0.074
 named-0.073
 spe-0.070
Token't
Token ID470
Feature activation+5.42e-02

Pos logit contributions
 guys+0.109
 plunge+0.091
 tournament+0.084
boards+0.083
 trigger+0.076
Neg logit contributions
 whose-0.229
 who-0.209
 named-0.201
elope-0.201
 spe-0.196
Token have
Token ID423
Feature activation+2.66e-02

Pos logit contributions
 guys+0.094
 plunge+0.094
boards+0.093
 tournament+0.087
board+0.083
Neg logit contributions
 whose-0.099
 who-0.092
 named-0.087
elope-0.083
 heaven-0.083
Token enough
Token ID1576
Feature activation+1.46e-02

Pos logit contributions
 guys+0.047
 plunge+0.043
 tournament+0.040
boards+0.039
 trigger+0.037
Neg logit contributions
 whose-0.052
 who-0.045
elope-0.044
 named-0.042
 spe-0.042
Token oxygen
Token ID11863
Feature activation+1.48e-02

Pos logit contributions
 guys+0.024
 plunge+0.022
 tournament+0.021
boards+0.020
 trigger+0.020
Neg logit contributions
 whose-0.029
 who-0.026
 named-0.025
 spe-0.024
 heaven-0.024
Token in
Token ID287
Feature activation-2.39e-02

Pos logit contributions
 guys+0.025
 plunge+0.023
 tournament+0.022
boards+0.021
 trigger+0.020
Neg logit contributions
 whose-0.029
 who-0.026
elope-0.025
 named-0.024
 spe-0.024
Token the
Token ID262
Feature activation+2.36e-02

Pos logit contributions
 whose+0.019
elope+0.017
 who+0.015
aron+0.015
 spe+0.015
Neg logit contributions
 guys-0.022
 plunge-0.020
 tournament-0.020
boards-0.018
 competition-0.018
Token water
Token ID1660
Feature activation+1.51e-03

Pos logit contributions
 guys+0.039
 plunge+0.037
 tournament+0.033
 trigger+0.033
boards+0.033
Neg logit contributions
 whose-0.047
 who-0.042
 named-0.039
elope-0.039
 heaven-0.039
Token,
Token ID11
Feature activation+1.20e-02

Pos logit contributions
 guys+0.003
 plunge+0.003
 tournament+0.003
boards+0.003
 trigger+0.003
Neg logit contributions
 whose-0.002
 who-0.002
 named-0.002
elope-0.002
 heaven-0.002
Token but
Token ID475
Feature activation+1.00e-02

Pos logit contributions
 guys+0.022
 plunge+0.020
 tournament+0.019
boards+0.018
 trigger+0.018
Neg logit contributions
 whose-0.023
 who-0.020
elope-0.019
 named-0.019
 spe-0.019
Token he
Token ID339
Feature activation+4.81e-02

Pos logit contributions
 guys+0.015
 plunge+0.013
 tournament+0.012
boards+0.012
 trigger+0.011
Neg logit contributions
 whose-0.022
 who-0.020
elope-0.019
 named-0.019
 spe-0.018
Token didn
Token ID1422
Feature activation+9.22e-02

Pos logit contributions
 guys+0.077
t+0.064
 plunge+0.063
 tournament+0.062
boards+0.059
Neg logit contributions
 whose-0.099
 heaven-0.086
 spe-0.085
elope-0.084
 who-0.084
Token't
Token ID470
Feature activation+5.71e-02

Pos logit contributions
 guys+0.116
 plunge+0.099
 tournament+0.088
boards+0.087
 trigger+0.083
Neg logit contributions
 whose-0.223
 who-0.203
 named-0.195
elope-0.191
house-0.190
Token like
Token ID588
Feature activation+1.74e-02

Pos logit contributions
 guys+0.095
 plunge+0.092
boards+0.086
 tournament+0.083
 trigger+0.080
Neg logit contributions
 whose-0.114
 who-0.103
 named-0.097
elope-0.095
 heaven-0.094
Token to
Token ID284
Feature activation+7.75e-03

Pos logit contributions
 guys+0.028
 plunge+0.025
boards+0.023
 tournament+0.023
 trigger+0.022
Neg logit contributions
 whose-0.036
elope-0.032
 who-0.031
 named-0.030
 spe-0.030
Token dry
Token ID5894
Feature activation+3.01e-02

Pos logit contributions
 guys+0.011
boards+0.010
 plunge+0.010
 tournament+0.010
 trigger+0.009
Neg logit contributions
 whose-0.017
 who-0.016
 named-0.015
 heaven-0.015
elope-0.014
Token off
Token ID572
Feature activation-1.14e-02

Pos logit contributions
 guys+0.059
 plunge+0.055
 tournament+0.054
boards+0.052
t+0.050
Neg logit contributions
 whose-0.052
 who-0.044
elope-0.041
 named-0.041
 heaven-0.040
Token was
Token ID373
Feature activation-8.04e-04

Pos logit contributions
 guys+0.057
 plunge+0.052
 tournament+0.048
boards+0.048
 trigger+0.045
Neg logit contributions
 whose-0.071
 who-0.062
elope-0.060
 named-0.059
 spe-0.058
Token very
Token ID845
Feature activation-1.64e-02

Pos logit contributions
 whose+0.001
elope+0.001
oc+0.001
 spe+0.001
 who+0.001
Neg logit contributions
 guys-0.002
 plunge-0.001
 tournament-0.001
t-0.001
 competition-0.001
Token confused
Token ID10416
Feature activation+4.60e-02

Pos logit contributions
 whose+0.026
 who+0.021
elope+0.021
 spe+0.020
 named+0.019
Neg logit contributions
 guys-0.035
 plunge-0.033
 tournament-0.031
boards-0.030
 trigger-0.029
Token.
Token ID13
Feature activation+2.80e-02

Pos logit contributions
 guys+0.083
 plunge+0.074
boards+0.070
 tournament+0.068
t+0.067
Neg logit contributions
 whose-0.085
elope-0.075
 spe-0.073
 who-0.071
 named-0.070
Token She
Token ID1375
Feature activation+2.33e-02

Pos logit contributions
 guys+0.045
 plunge+0.041
boards+0.039
board+0.036
t+0.036
Neg logit contributions
 whose-0.057
 who-0.049
elope-0.048
 spe-0.048
 heaven-0.047
Token didn
Token ID1422
Feature activation+9.21e-02

Pos logit contributions
 guys+0.041
 plunge+0.041
 tournament+0.039
boards+0.037
 trigger+0.036
Neg logit contributions
 whose-0.045
 who-0.041
 named-0.040
elope-0.038
house-0.034
Token't
Token ID470
Feature activation+5.66e-02

Pos logit contributions
 guys+0.109
 plunge+0.092
 tournament+0.083
boards+0.083
 trigger+0.075
Neg logit contributions
 whose-0.228
 who-0.210
elope-0.202
 named-0.202
 heaven-0.198
Token know
Token ID760
Feature activation+5.19e-03

Pos logit contributions
 plunge+0.118
boards+0.118
 guys+0.114
 tournament+0.111
 trigger+0.106
Neg logit contributions
 whose-0.083
 who-0.080
 named-0.073
 heaven-0.070
elope-0.070
Token what
Token ID644
Feature activation+1.34e-02

Pos logit contributions
 guys+0.009
 plunge+0.008
 first+0.006
 rocks+0.006
boards+0.006
Neg logit contributions
oc-0.009
aron-0.009
elope-0.009
 stret-0.009
house-0.008
Token to
Token ID284
Feature activation-6.74e-03

Pos logit contributions
 guys+0.019
 plunge+0.016
boards+0.014
 tournament+0.014
t+0.014
Neg logit contributions
 whose-0.030
elope-0.027
 spe-0.026
 who-0.026
 heaven-0.026
Token do
Token ID466
Feature activation+2.87e-02

Pos logit contributions
 whose+0.013
 who+0.012
 named+0.011
 heaven+0.010
elope+0.010
Neg logit contributions
boards-0.011
 tournament-0.011
ived-0.011
 guys-0.011
 plunge-0.010
Token his
Token ID465
Feature activation+4.83e-03

Pos logit contributions
 whose+0.034
elope+0.033
 spe+0.030
oc+0.029
 named+0.029
Neg logit contributions
 guys-0.033
 plunge-0.028
boards-0.026
 tournament-0.024
 trigger-0.024
Token toys
Token ID14958
Feature activation-6.95e-03

Pos logit contributions
 guys+0.008
 plunge+0.007
boards+0.006
 tournament+0.006
 trigger+0.006
Neg logit contributions
 whose-0.010
elope-0.009
 who-0.009
 spe-0.009
 named-0.008
Token,
Token ID11
Feature activation-1.59e-03

Pos logit contributions
 whose+0.012
 who+0.010
elope+0.010
 spe+0.010
 named+0.010
Neg logit contributions
 guys-0.013
 plunge-0.012
 tournament-0.011
boards-0.011
t-0.011
Token but
Token ID475
Feature activation+1.42e-03

Pos logit contributions
 whose+0.003
elope+0.003
 spe+0.003
 who+0.003
oc+0.003
Neg logit contributions
 guys-0.003
 plunge-0.002
boards-0.002
 tournament-0.002
t-0.002
Token he
Token ID339
Feature activation+5.05e-02

Pos logit contributions
 guys+0.002
 plunge+0.002
 tournament+0.002
boards+0.002
 trigger+0.002
Neg logit contributions
 whose-0.003
 who-0.003
elope-0.002
 named-0.002
 spe-0.002
Token didn
Token ID1422
Feature activation+9.21e-02

Pos logit contributions
 guys+0.081
 plunge+0.070
 tournament+0.066
t+0.064
boards+0.064
Neg logit contributions
 whose-0.106
 who-0.091
elope-0.090
 spe-0.090
 heaven-0.088
Token't
Token ID470
Feature activation+5.81e-02

Pos logit contributions
 guys+0.128
 plunge+0.113
 tournament+0.101
boards+0.101
 trigger+0.096
Neg logit contributions
 whose-0.203
 who-0.186
 named-0.178
house-0.176
 heaven-0.175
Token listen
Token ID6004
Feature activation+4.49e-02

Pos logit contributions
boards+0.099
 plunge+0.098
 guys+0.091
 tournament+0.087
 trigger+0.086
Neg logit contributions
 whose-0.108
 who-0.108
 named-0.100
 heaven-0.096
elope-0.089
Token.
Token ID13
Feature activation+2.71e-02

Pos logit contributions
 guys+0.087
 plunge+0.083
 tournament+0.077
boards+0.075
 trigger+0.073
Neg logit contributions
 whose-0.079
 who-0.069
elope-0.063
 named-0.062
 heaven-0.062
Token
Token ID198
Feature activation+1.10e-02

Pos logit contributions
 guys+0.049
 plunge+0.044
boards+0.043
 tournament+0.042
board+0.040
Neg logit contributions
 whose-0.049
 spe-0.042
 who-0.042
elope-0.042
 heaven-0.040
Token
Token ID198
Feature activation+1.59e-02

Pos logit contributions
 guys+0.019
 plunge+0.018
t+0.017
boards+0.017
 tournament+0.017
Neg logit contributions
 whose-0.020
 spe-0.017
elope-0.017
 who-0.017
 heaven-0.016
Token was
Token ID373
Feature activation-1.50e-02

Pos logit contributions
 guys+0.008
t+0.006
board+0.006
 tournament+0.006
boards+0.006
Neg logit contributions
 whose-0.010
 heaven-0.010
 stret-0.010
 spe-0.010
 bruised-0.009
Token very
Token ID845
Feature activation-2.94e-02

Pos logit contributions
 whose+0.031
elope+0.030
oc+0.029
aron+0.028
 heaven+0.027
Neg logit contributions
 guys-0.023
 plunge-0.019
 first-0.019
t-0.018
 race-0.018
Token lonely
Token ID21757
Feature activation+4.41e-02

Pos logit contributions
 whose+0.056
elope+0.049
 who+0.047
 heaven+0.046
 spe+0.044
Neg logit contributions
 guys-0.053
 plunge-0.048
 tournament-0.044
t-0.044
 competition-0.041
Token because
Token ID780
Feature activation-2.05e-02

Pos logit contributions
 guys+0.073
boards+0.057
 tournament+0.057
t+0.057
 plunge+0.057
Neg logit contributions
 whose-0.088
elope-0.081
 spe-0.078
bugs-0.074
 stret-0.073
Token he
Token ID339
Feature activation+4.40e-02

Pos logit contributions
 whose+0.049
 who+0.043
elope+0.043
 spe+0.042
 named+0.041
Neg logit contributions
 guys-0.027
 plunge-0.023
 tournament-0.021
boards-0.021
t-0.019
Token didn
Token ID1422
Feature activation+9.21e-02

Pos logit contributions
 guys+0.082
 plunge+0.080
 tournament+0.074
boards+0.074
 trigger+0.072
Neg logit contributions
 whose-0.079
 who-0.070
 named-0.067
elope-0.066
 spe-0.062
Token't
Token ID470
Feature activation+5.48e-02

Pos logit contributions
 guys+0.107
 plunge+0.093
boards+0.083
 tournament+0.082
 trigger+0.076
Neg logit contributions
 whose-0.229
 who-0.210
 named-0.203
elope-0.201
 heaven-0.200
Token have
Token ID423
Feature activation+1.94e-02

Pos logit contributions
 plunge+0.097
 guys+0.094
boards+0.094
 tournament+0.087
 trigger+0.084
Neg logit contributions
 whose-0.100
 who-0.094
 named-0.089
 heaven-0.086
elope-0.083
Token any
Token ID597
Feature activation+1.14e-02

Pos logit contributions
 guys+0.037
 plunge+0.032
 tournament+0.029
boards+0.028
t+0.027
Neg logit contributions
 whose-0.037
elope-0.032
 who-0.031
oc-0.030
 spe-0.030
Token friends
Token ID2460
Feature activation+1.02e-03

Pos logit contributions
 guys+0.020
 plunge+0.018
 tournament+0.016
boards+0.016
 trigger+0.015
Neg logit contributions
 whose-0.023
elope-0.020
 who-0.019
 spe-0.019
 named-0.018
Token.
Token ID13
Feature activation+2.31e-02

Pos logit contributions
 guys+0.002
 plunge+0.002
 tournament+0.001
boards+0.001
t+0.001
Neg logit contributions
 whose-0.002
elope-0.002
 spe-0.002
 who-0.002
 heaven-0.002
Token play
Token ID711
Feature activation+3.09e-02

Pos logit contributions
 whose+0.016
 who+0.015
elope+0.014
 named+0.014
 spe+0.014
Neg logit contributions
 guys-0.008
 plunge-0.007
 tournament-0.006
boards-0.006
 trigger-0.006
Token outside
Token ID2354
Feature activation-1.89e-02

Pos logit contributions
 guys+0.059
 plunge+0.057
 tournament+0.052
boards+0.051
 trigger+0.051
Neg logit contributions
 whose-0.055
 who-0.048
 named-0.045
 heaven-0.042
house-0.042
Token,
Token ID11
Feature activation+1.72e-02

Pos logit contributions
 whose+0.033
elope+0.029
 who+0.028
 heaven+0.028
 spe+0.027
Neg logit contributions
 guys-0.036
 plunge-0.032
 tournament-0.030
boards-0.030
t-0.028
Token but
Token ID475
Feature activation+8.61e-03

Pos logit contributions
 guys+0.029
 plunge+0.027
 tournament+0.025
boards+0.025
 trigger+0.023
Neg logit contributions
 whose-0.035
 who-0.030
elope-0.029
 named-0.028
 spe-0.028
Token he
Token ID339
Feature activation+4.77e-02

Pos logit contributions
 guys+0.012
 plunge+0.011
 tournament+0.010
boards+0.010
 trigger+0.009
Neg logit contributions
 whose-0.019
 who-0.017
elope-0.017
 named-0.016
 spe-0.016
Token didn
Token ID1422
Feature activation+9.20e-02

Pos logit contributions
 guys+0.079
 plunge+0.066
 tournament+0.065
t+0.065
boards+0.063
Neg logit contributions
 whose-0.097
 who-0.082
 spe-0.082
 heaven-0.082
elope-0.082
Token't
Token ID470
Feature activation+5.78e-02

Pos logit contributions
 guys+0.116
 plunge+0.100
 tournament+0.088
boards+0.085
 trigger+0.083
Neg logit contributions
 whose-0.223
 who-0.202
 named-0.194
house-0.191
elope-0.191
Token like
Token ID588
Feature activation+1.78e-02

Pos logit contributions
 plunge+0.101
 guys+0.099
boards+0.096
 tournament+0.090
 trigger+0.088
Neg logit contributions
 whose-0.108
 who-0.100
 named-0.094
 heaven-0.091
elope-0.089
Token to
Token ID284
Feature activation+9.48e-03

Pos logit contributions
 guys+0.028
 plunge+0.025
 tournament+0.023
boards+0.023
 trigger+0.021
Neg logit contributions
 whose-0.038
 who-0.033
elope-0.033
 named-0.032
 spe-0.031
Token clean
Token ID3424
Feature activation+1.62e-02

Pos logit contributions
 guys+0.013
 plunge+0.013
boards+0.013
 tournament+0.012
 trigger+0.012
Neg logit contributions
 whose-0.020
 who-0.019
 named-0.018
 heaven-0.018
elope-0.017
Token up
Token ID510
Feature activation-9.18e-03

Pos logit contributions
 guys+0.030
 plunge+0.027
 tournament+0.025
boards+0.025
 trigger+0.024
Neg logit contributions
 whose-0.031
 who-0.026
elope-0.026
 named-0.025
 spe-0.025
Token bunny
Token ID44915
Feature activation+3.21e-02

Pos logit contributions
 whose+0.024
 who+0.021
elope+0.020
 spe+0.020
 named+0.019
Neg logit contributions
 guys-0.026
boards-0.025
 plunge-0.025
 tournament-0.024
t-0.023
Token felt
Token ID2936
Feature activation+1.46e-02

Pos logit contributions
 guys+0.050
 plunge+0.041
 tournament+0.040
boards+0.039
t+0.037
Neg logit contributions
 whose-0.069
 spe-0.059
 who-0.058
elope-0.058
 heaven-0.058
Token lonely
Token ID21757
Feature activation+5.56e-02

Pos logit contributions
 guys+0.024
 plunge+0.022
 trigger+0.019
 tournament+0.018
t+0.018
Neg logit contributions
 whose-0.029
elope-0.027
oc-0.026
 stret-0.025
house-0.024
Token because
Token ID780
Feature activation-1.27e-02

Pos logit contributions
 guys+0.105
 plunge+0.092
 tournament+0.087
boards+0.087
t+0.082
Neg logit contributions
 whose-0.101
elope-0.087
 spe-0.084
 who-0.083
 named-0.081
Token it
Token ID340
Feature activation+4.85e-02

Pos logit contributions
 whose+0.029
elope+0.026
 who+0.025
 stret+0.025
 spe+0.024
Neg logit contributions
 guys-0.018
 plunge-0.016
 tournament-0.014
boards-0.014
t-0.013
Token didn
Token ID1422
Feature activation+9.20e-02

Pos logit contributions
 guys+0.089
 plunge+0.084
 tournament+0.079
boards+0.078
 trigger+0.076
Neg logit contributions
 whose-0.090
 who-0.080
elope-0.076
 named-0.075
 heaven-0.071
Token't
Token ID470
Feature activation+5.56e-02

Pos logit contributions
 guys+0.108
 plunge+0.094
boards+0.086
 tournament+0.084
 trigger+0.077
Neg logit contributions
 whose-0.228
 who-0.208
 named-0.200
elope-0.199
 heaven-0.198
Token have
Token ID423
Feature activation+2.97e-02

Pos logit contributions
boards+0.102
 plunge+0.098
board+0.090
 guys+0.090
 tournament+0.089
Neg logit contributions
 whose-0.095
 who-0.093
 named-0.089
 heaven-0.089
 spe-0.081
Token any
Token ID597
Feature activation+1.55e-02

Pos logit contributions
 guys+0.053
 plunge+0.047
 tournament+0.043
boards+0.043
 trigger+0.041
Neg logit contributions
 whose-0.058
 who-0.050
elope-0.049
 named-0.047
 spe-0.047
Token bunny
Token ID44915
Feature activation+1.93e-03

Pos logit contributions
 guys+0.031
 plunge+0.029
 tournament+0.028
boards+0.028
board+0.026
Neg logit contributions
 whose-0.026
 who-0.022
 named-0.021
 heaven-0.020
elope-0.020
Token friends
Token ID2460
Feature activation+3.69e-03

Pos logit contributions
 guys+0.003
 plunge+0.003
 tournament+0.003
boards+0.003
t+0.003
Neg logit contributions
 whose-0.004
elope-0.003
 who-0.003
 spe-0.003
 named-0.003
Token in
Token ID287
Feature activation-1.77e-02

Pos logit contributions
 guys+0.051
 plunge+0.043
boards+0.041
 trigger+0.039
 tournament+0.039
Neg logit contributions
 whose-0.063
elope-0.059
 spe-0.054
oc-0.053
 heaven-0.052
Token the
Token ID262
Feature activation+1.95e-02

Pos logit contributions
 whose+0.032
elope+0.027
 who+0.026
aron+0.026
oc+0.025
Neg logit contributions
 guys-0.032
 plunge-0.029
 tournament-0.027
 boulder-0.026
 surface-0.026
Token woods
Token ID16479
Feature activation-2.02e-02

Pos logit contributions
 guys+0.035
 plunge+0.032
 tournament+0.031
ived+0.031
t+0.030
Neg logit contributions
 whose-0.035
 who-0.031
elope-0.030
 heaven-0.030
 named-0.030
Token.
Token ID13
Feature activation+3.95e-02

Pos logit contributions
 whose+0.040
elope+0.035
 spe+0.034
 stret+0.032
 who+0.032
Neg logit contributions
 guys-0.033
 plunge-0.029
boards-0.028
 tournament-0.028
t-0.028
Token He
Token ID679
Feature activation+4.21e-02

Pos logit contributions
 plunge+0.071
 guys+0.071
 tournament+0.066
boards+0.060
ok+0.060
Neg logit contributions
 whose-0.072
 who-0.063
 named-0.061
house-0.059
elope-0.059
Token didn
Token ID1422
Feature activation+9.19e-02

Pos logit contributions
 guys+0.070
 plunge+0.066
 tournament+0.063
boards+0.061
 trigger+0.057
Neg logit contributions
 whose-0.086
 who-0.077
 named-0.074
elope-0.074
 spe-0.068
Token't
Token ID470
Feature activation+5.61e-02

Pos logit contributions
 guys+0.099
 plunge+0.083
 tournament+0.074
boards+0.073
 trigger+0.065
Neg logit contributions
 whose-0.238
 who-0.218
elope-0.211
 named-0.210
 heaven-0.206
Token know
Token ID760
Feature activation+9.05e-03

Pos logit contributions
 guys+0.105
 plunge+0.103
boards+0.100
 tournament+0.097
 trigger+0.091
Neg logit contributions
 whose-0.097
 who-0.088
 named-0.083
elope-0.081
 heaven-0.081
Token where
Token ID810
Feature activation-2.79e-03

Pos logit contributions
 guys+0.017
 plunge+0.014
 rocks+0.013
boards+0.013
 first+0.012
Neg logit contributions
elope-0.015
house-0.014
 stret-0.014
aron-0.014
oc-0.014
Token to
Token ID284
Feature activation-1.47e-04

Pos logit contributions
 whose+0.006
elope+0.006
 who+0.006
aron+0.005
 heaven+0.005
Neg logit contributions
 guys-0.004
 plunge-0.004
boards-0.003
 tournament-0.003
t-0.003
Token go
Token ID467
Feature activation+4.75e-02

Pos logit contributions
 whose+0.000
 who+0.000
elope+0.000
 named+0.000
 heaven+0.000
Neg logit contributions
 guys-0.000
boards-0.000
 plunge-0.000
 tournament-0.000
board-0.000
Token every
Token ID790
Feature activation+1.78e-02

Pos logit contributions
 guys+0.062
 plunge+0.055
 tournament+0.052
boards+0.051
 competition+0.049
Neg logit contributions
 whose-0.063
elope-0.055
 who-0.053
 spe-0.053
 named-0.052
Token day
Token ID1110
Feature activation+2.08e-02

Pos logit contributions
 guys+0.023
 plunge+0.020
boards+0.019
 tournament+0.018
 trigger+0.017
Neg logit contributions
 whose-0.043
 who-0.039
elope-0.037
 named-0.037
 spe-0.036
Token.
Token ID13
Feature activation+2.43e-02

Pos logit contributions
 guys+0.038
 plunge+0.033
boards+0.032
 tournament+0.031
t+0.031
Neg logit contributions
 whose-0.039
elope-0.034
 who-0.033
 spe-0.032
 heaven-0.032
Token But
Token ID887
Feature activation+7.19e-03

Pos logit contributions
 guys+0.035
 plunge+0.030
boards+0.029
 tournament+0.028
board+0.028
Neg logit contributions
 whose-0.053
 spe-0.047
 who-0.046
elope-0.046
 heaven-0.044
Token she
Token ID673
Feature activation+4.68e-02

Pos logit contributions
 guys+0.009
 plunge+0.008
 tournament+0.007
 competition+0.007
t+0.006
Neg logit contributions
 whose-0.017
elope-0.015
 stret-0.015
aron-0.015
 spe-0.015
Token didn
Token ID1422
Feature activation+9.19e-02

Pos logit contributions
 guys+0.077
 plunge+0.065
 tournament+0.063
t+0.061
boards+0.061
Neg logit contributions
 whose-0.097
 who-0.082
elope-0.082
 heaven-0.081
 spe-0.081
Token't
Token ID470
Feature activation+5.69e-02

Pos logit contributions
 guys+0.110
 plunge+0.094
 tournament+0.082
boards+0.081
 trigger+0.079
Neg logit contributions
 whose-0.228
 who-0.208
 named-0.199
elope-0.196
 heaven-0.194
Token like
Token ID588
Feature activation+1.21e-02

Pos logit contributions
 guys+0.101
 plunge+0.093
 tournament+0.086
boards+0.086
 trigger+0.081
Neg logit contributions
 whose-0.110
 who-0.096
elope-0.092
 named-0.090
 spe-0.089
Token to
Token ID284
Feature activation+7.45e-03

Pos logit contributions
 guys+0.023
 plunge+0.021
 tournament+0.020
boards+0.019
t+0.019
Neg logit contributions
 whose-0.022
elope-0.019
 who-0.018
oc-0.018
 named-0.018
Token listen
Token ID6004
Feature activation+4.39e-02

Pos logit contributions
 guys+0.010
 plunge+0.010
boards+0.009
 tournament+0.009
 trigger+0.008
Neg logit contributions
 whose-0.017
 who-0.015
 named-0.014
elope-0.014
 heaven-0.014
Token to
Token ID284
Feature activation-2.25e-02

Pos logit contributions
 guys+0.072
 plunge+0.066
 tournament+0.062
boards+0.060
 trigger+0.058
Neg logit contributions
 whose-0.090
 who-0.080
elope-0.076
 named-0.074
 heaven-0.073
Token the
Token ID262
Feature activation+8.19e-03

Pos logit contributions
 guys+0.041
 plunge+0.039
 tournament+0.037
boards+0.036
 trigger+0.035
Neg logit contributions
 whose-0.031
 who-0.026
elope-0.025
 named-0.024
 heaven-0.024
Token test
Token ID1332
Feature activation+2.24e-03

Pos logit contributions
 guys+0.011
 tournament+0.010
 plunge+0.010
 trigger+0.009
ived+0.009
Neg logit contributions
 whose-0.017
 who-0.016
 heaven-0.014
 named-0.014
 stret-0.014
Token.
Token ID13
Feature activation+3.49e-02

Pos logit contributions
 guys+0.004
 plunge+0.003
 tournament+0.003
boards+0.003
board+0.003
Neg logit contributions
 whose-0.004
 who-0.004
elope-0.004
 spe-0.004
 named-0.004
Token But
Token ID887
Feature activation+1.83e-02

Pos logit contributions
 guys+0.068
 plunge+0.065
 tournament+0.060
 trigger+0.058
boards+0.057
Neg logit contributions
 whose-0.061
 who-0.052
 named-0.049
 heaven-0.048
elope-0.048
Token she
Token ID673
Feature activation+4.94e-02

Pos logit contributions
 guys+0.034
 plunge+0.031
 tournament+0.028
boards+0.028
t+0.027
Neg logit contributions
 whose-0.033
elope-0.029
 who-0.028
 spe-0.028
 heaven-0.027
Token didn
Token ID1422
Feature activation+9.17e-02

Pos logit contributions
 guys+0.079
 plunge+0.070
 tournament+0.065
boards+0.065
t+0.061
Neg logit contributions
 whose-0.104
 who-0.091
elope-0.089
 spe-0.087
 heaven-0.086
Token't
Token ID470
Feature activation+5.65e-02

Pos logit contributions
 guys+0.126
 plunge+0.109
 tournament+0.097
 trigger+0.096
boards+0.094
Neg logit contributions
 whose-0.207
 who-0.190
 named-0.182
house-0.178
 heaven-0.177
Token do
Token ID466
Feature activation+1.91e-02

Pos logit contributions
 plunge+0.101
 guys+0.096
boards+0.096
 trigger+0.091
 tournament+0.088
Neg logit contributions
 whose-0.101
 who-0.101
 named-0.090
 heaven-0.088
elope-0.083
Token well
Token ID880
Feature activation+3.19e-02

Pos logit contributions
 guys+0.033
 plunge+0.031
 tournament+0.029
boards+0.028
 trigger+0.027
Neg logit contributions
 whose-0.037
 who-0.033
elope-0.031
 named-0.030
 heaven-0.030
Token because
Token ID780
Feature activation-1.31e-02

Pos logit contributions
 guys+0.060
 plunge+0.056
 tournament+0.052
boards+0.052
 trigger+0.050
Neg logit contributions
 whose-0.057
 who-0.050
elope-0.046
 named-0.046
 heaven-0.045
Token she
Token ID673
Feature activation+3.43e-02

Pos logit contributions
 whose+0.026
elope+0.023
 who+0.023
 spe+0.022
 named+0.021
Neg logit contributions
 guys-0.022
 plunge-0.020
 tournament-0.019
boards-0.019
t-0.018
Token feeling
Token ID4203
Feature activation+2.07e-03

Pos logit contributions
 guys+0.016
 plunge+0.014
 competition+0.014
 tournament+0.013
t+0.012
Neg logit contributions
 whose-0.022
oc-0.021
elope-0.021
 spe-0.019
aron-0.019
Token very
Token ID845
Feature activation-2.10e-02

Pos logit contributions
 guys+0.003
 plunge+0.003
 competition+0.003
 tournament+0.003
t+0.003
Neg logit contributions
 whose-0.004
elope-0.004
oc-0.004
aron-0.004
 stret-0.003
Token confused
Token ID10416
Feature activation+4.95e-02

Pos logit contributions
 whose+0.033
 who+0.027
elope+0.026
 named+0.025
 heaven+0.025
Neg logit contributions
 guys-0.045
 plunge-0.042
 tournament-0.040
boards-0.040
 trigger-0.038
Token.
Token ID13
Feature activation+2.84e-02

Pos logit contributions
 guys+0.090
 plunge+0.079
boards+0.076
 tournament+0.073
board+0.072
Neg logit contributions
 whose-0.090
elope-0.081
 spe-0.079
 who-0.075
 named-0.074
Token She
Token ID1375
Feature activation+2.58e-02

Pos logit contributions
 guys+0.053
 plunge+0.048
 tournament+0.045
boards+0.045
 trigger+0.043
Neg logit contributions
 whose-0.052
 who-0.045
elope-0.044
 named-0.042
 spe-0.042
Token didn
Token ID1422
Feature activation+9.17e-02

Pos logit contributions
 plunge+0.047
 guys+0.046
 tournament+0.043
boards+0.041
 trigger+0.041
Neg logit contributions
 whose-0.049
 who-0.045
 named-0.043
elope-0.040
house-0.037
Token't
Token ID470
Feature activation+5.85e-02

Pos logit contributions
 guys+0.113
 plunge+0.098
 tournament+0.086
boards+0.086
 trigger+0.081
Neg logit contributions
 whose-0.222
 who-0.204
 named-0.194
elope-0.192
 heaven-0.192
Token understand
Token ID1833
Feature activation+9.39e-03

Pos logit contributions
 plunge+0.123
boards+0.118
 guys+0.117
 tournament+0.111
 trigger+0.109
Neg logit contributions
 whose-0.089
 who-0.086
 named-0.077
 heaven-0.074
elope-0.070
Token why
Token ID1521
Feature activation+1.08e-02

Pos logit contributions
 guys+0.019
boards+0.015
 plunge+0.015
ly+0.015
board+0.015
Neg logit contributions
elope-0.014
 spe-0.014
 whose-0.014
oc-0.013
 stret-0.013
Token she
Token ID673
Feature activation+3.94e-02

Pos logit contributions
 guys+0.019
 tournament+0.015
 plunge+0.015
boards+0.015
t+0.014
Neg logit contributions
 whose-0.021
elope-0.019
oc-0.018
 spe-0.018
 stret-0.018
Token felt
Token ID2936
Feature activation+1.94e-02

Pos logit contributions
 guys+0.070
 plunge+0.065
 tournament+0.061
boards+0.059
 trigger+0.057
Neg logit contributions
 whose-0.076
 who-0.067
elope-0.064
 named-0.063
 spe-0.061
Token to
Token ID284
Feature activation+2.40e-03

Pos logit contributions
 guys+0.048
 plunge+0.043
boards+0.039
 tournament+0.039
t+0.037
Neg logit contributions
 whose-0.066
elope-0.059
 who-0.057
oc-0.056
 spe-0.055
Token sew
Token ID34249
Feature activation+1.64e-02

Pos logit contributions
 guys+0.003
 plunge+0.003
 tournament+0.003
boards+0.003
 trigger+0.002
Neg logit contributions
 whose-0.006
 who-0.005
elope-0.005
 spe-0.005
 named-0.005
Token something
Token ID1223
Feature activation+1.89e-02

Pos logit contributions
 guys+0.031
 plunge+0.026
boards+0.025
ly+0.024
 competition+0.024
Neg logit contributions
 whose-0.030
elope-0.027
 spe-0.025
oc-0.025
 who-0.025
Token but
Token ID475
Feature activation+1.30e-02

Pos logit contributions
 guys+0.034
 plunge+0.031
boards+0.028
 tournament+0.028
t+0.027
Neg logit contributions
 whose-0.036
elope-0.031
 who-0.030
 named-0.029
 spe-0.029
Token she
Token ID673
Feature activation+4.21e-02

Pos logit contributions
 guys+0.022
 plunge+0.020
 tournament+0.019
boards+0.018
 trigger+0.017
Neg logit contributions
 whose-0.026
 who-0.023
elope-0.022
 named-0.021
 spe-0.021
Token didn
Token ID1422
Feature activation+9.17e-02

Pos logit contributions
 guys+0.058
 plunge+0.048
t+0.045
boards+0.045
 tournament+0.045
Neg logit contributions
 whose-0.098
 who-0.084
elope-0.084
 spe-0.083
 heaven-0.083
Token't
Token ID470
Feature activation+6.17e-02

Pos logit contributions
 guys+0.121
 plunge+0.103
 tournament+0.095
boards+0.092
 trigger+0.088
Neg logit contributions
 whose-0.214
 who-0.196
 named-0.186
house-0.184
 heaven-0.184
Token know
Token ID760
Feature activation+9.28e-03

Pos logit contributions
 plunge+0.122
boards+0.121
 guys+0.118
 trigger+0.113
 tournament+0.112
Neg logit contributions
 whose-0.093
 who-0.089
 named-0.083
 heaven-0.083
elope-0.077
Token how
Token ID703
Feature activation+1.31e-02

Pos logit contributions
 guys+0.017
boards+0.016
 plunge+0.016
 first+0.014
ly+0.014
Neg logit contributions
elope-0.014
oc-0.014
 stret-0.013
 spe-0.013
aron-0.012
Token.
Token ID13
Feature activation+3.74e-02

Pos logit contributions
 guys+0.021
 plunge+0.019
boards+0.017
t+0.017
 tournament+0.017
Neg logit contributions
 whose-0.027
elope-0.024
 who-0.023
 named-0.023
oc-0.022
Token She
Token ID1375
Feature activation+3.11e-02

Pos logit contributions
 guys+0.068
 plunge+0.062
boards+0.058
 tournament+0.058
board+0.054
Neg logit contributions
 whose-0.070
 who-0.060
elope-0.058
 named-0.057
 spe-0.057
Token day
Token ID1110
Feature activation+2.32e-02

Pos logit contributions
 guys+0.009
 plunge+0.007
 tournament+0.005
t+0.005
board+0.005
Neg logit contributions
 whose-0.037
 spe-0.034
 stret-0.034
 heaven-0.033
elope-0.033
Token,
Token ID11
Feature activation+1.24e-02

Pos logit contributions
 guys+0.047
 plunge+0.044
 tournament+0.042
boards+0.041
 trigger+0.040
Neg logit contributions
 whose-0.039
 who-0.032
 named-0.031
elope-0.031
 spe-0.029
Token however
Token ID2158
Feature activation+2.76e-02

Pos logit contributions
 guys+0.020
 plunge+0.018
 tournament+0.017
boards+0.017
 trigger+0.016
Neg logit contributions
 whose-0.026
 who-0.023
elope-0.022
 named-0.022
 spe-0.021
Token,
Token ID11
Feature activation+1.74e-02

Pos logit contributions
 guys+0.052
 plunge+0.048
 tournament+0.045
boards+0.044
 trigger+0.042
Neg logit contributions
 whose-0.050
 who-0.043
elope-0.042
 heaven-0.040
 spe-0.040
Token he
Token ID339
Feature activation+5.64e-02

Pos logit contributions
 guys+0.026
 plunge+0.023
 tournament+0.021
boards+0.020
 trigger+0.019
Neg logit contributions
 whose-0.038
elope-0.034
 who-0.034
 heaven-0.033
 spe-0.033
Token didn
Token ID1422
Feature activation+9.14e-02

Pos logit contributions
 guys+0.095
 plunge+0.088
 tournament+0.082
boards+0.081
 trigger+0.078
Neg logit contributions
 whose-0.113
 who-0.100
elope-0.096
 named-0.095
 heaven-0.091
Token't
Token ID470
Feature activation+6.06e-02

Pos logit contributions
 guys+0.120
 plunge+0.100
 tournament+0.093
boards+0.091
 trigger+0.088
Neg logit contributions
 whose-0.217
 who-0.198
 named-0.190
elope-0.185
house-0.183
Token feel
Token ID1254
Feature activation+1.44e-02

Pos logit contributions
 guys+0.104
 plunge+0.102
boards+0.100
 tournament+0.094
 trigger+0.091
Neg logit contributions
 whose-0.112
 who-0.106
 named-0.099
elope-0.096
 heaven-0.095
Token like
Token ID588
Feature activation-4.80e-03

Pos logit contributions
 guys+0.026
 plunge+0.024
 tournament+0.021
boards+0.020
 trigger+0.020
Neg logit contributions
 whose-0.028
elope-0.024
 who-0.023
oc-0.023
 named-0.022
Token z
Token ID1976
Feature activation+2.56e-02

Pos logit contributions
 whose+0.009
elope+0.008
 who+0.008
oc+0.008
 named+0.007
Neg logit contributions
 guys-0.009
 plunge-0.008
boards-0.007
 tournament-0.007
t-0.007
Tokenipping
Token ID4501
Feature activation+3.13e-02

Pos logit contributions
 guys+0.042
 plunge+0.037
 tournament+0.036
boards+0.036
 trigger+0.034
Neg logit contributions
 whose-0.052
 who-0.045
 named-0.043
 spe-0.043
elope-0.042
Token be
Token ID307
Feature activation-3.01e-02

Pos logit contributions
 whose+0.063
 named+0.060
 who+0.058
elope+0.054
 heaven+0.054
Neg logit contributions
boards-0.057
 guys-0.057
 plunge-0.054
 tournament-0.051
 trigger-0.051
Token safe
Token ID3338
Feature activation-8.87e-03

Pos logit contributions
 whose+0.060
elope+0.054
 spe+0.052
oc+0.050
 who+0.049
Neg logit contributions
 guys-0.052
 plunge-0.043
 tournament-0.042
 competition-0.040
boards-0.038
Token and
Token ID290
Feature activation-3.41e-02

Pos logit contributions
 whose+0.017
elope+0.015
 spe+0.014
 who+0.014
oc+0.014
Neg logit contributions
 guys-0.015
 plunge-0.013
 tournament-0.013
boards-0.012
t-0.012
Token hugged
Token ID41130
Feature activation-9.15e-03

Pos logit contributions
 whose+0.067
 who+0.057
elope+0.057
 spe+0.055
 heaven+0.054
Neg logit contributions
 guys-0.059
 plunge-0.054
 tournament-0.049
boards-0.047
t-0.046
Token the
Token ID262
Feature activation-3.05e-02

Pos logit contributions
 whose+0.018
 spe+0.017
elope+0.017
house+0.016
 who+0.015
Neg logit contributions
 guys-0.015
 plunge-0.012
ly-0.011
boards-0.010
 trigger-0.010
Token firefighter
Token ID43105
Feature activation-9.21e-02

Pos logit contributions
 whose+0.061
elope+0.052
 who+0.051
 named+0.049
 spe+0.049
Neg logit contributions
 guys-0.053
 plunge-0.048
 tournament-0.044
 trigger-0.043
boards-0.042
Token tightly
Token ID17707
Feature activation-3.06e-02

Pos logit contributions
 whose+0.201
 spe+0.195
elope+0.178
 Chick+0.175
Pe+0.172
Neg logit contributions
 guys-0.114
ly-0.097
 plunge-0.094
 first-0.091
 tournament-0.091
Token.
Token ID13
Feature activation+2.80e-03

Pos logit contributions
 whose+0.062
elope+0.055
 spe+0.053
oc+0.051
 heaven+0.051
Neg logit contributions
 guys-0.048
 plunge-0.043
boards-0.039
ly-0.039
t-0.038
Token
Token ID198
Feature activation-2.38e-02

Pos logit contributions
 guys+0.004
 tournament+0.003
 Want+0.003
boards+0.003
board+0.003
Neg logit contributions
 whose-0.006
 spe-0.005
 stret-0.005
elope-0.005
 cigarette-0.005
Token
Token ID198
Feature activation-1.90e-02

Pos logit contributions
 whose+0.046
 spe+0.044
 bruised+0.039
 heaven+0.039
elope+0.038
Neg logit contributions
 guys-0.034
 tournament-0.033
 plunge-0.032
t-0.031
boards-0.030
TokenAfter
Token ID3260
Feature activation-3.09e-02

Pos logit contributions
 whose+0.035
 spe+0.031
elope+0.030
 who+0.029
 heaven+0.029
Neg logit contributions
 guys-0.032
 tournament-0.030
 plunge-0.029
t-0.028
boards-0.027
Token was
Token ID373
Feature activation-2.55e-02

Pos logit contributions
 guys+0.035
 plunge+0.033
 tournament+0.031
boards+0.030
 trigger+0.029
Neg logit contributions
 whose-0.036
 who-0.031
elope-0.030
 named-0.029
 spe-0.029
Token a
Token ID257
Feature activation-2.68e-02

Pos logit contributions
 whose+0.042
elope+0.039
oc+0.035
 spe+0.034
 heaven+0.033
Neg logit contributions
 guys-0.054
 plunge-0.046
 tournament-0.045
 competition-0.042
boards-0.042
Token driver
Token ID4639
Feature activation-4.83e-02

Pos logit contributions
 whose+0.054
 who+0.047
elope+0.047
 heaven+0.044
 spe+0.044
Neg logit contributions
 guys-0.045
 plunge-0.040
 tournament-0.038
boards-0.037
 trigger-0.035
Token or
Token ID393
Feature activation-5.48e-02

Pos logit contributions
 whose+0.096
elope+0.095
 spe+0.087
 stret+0.086
 Chick+0.085
Neg logit contributions
 guys-0.079
board-0.062
t-0.061
 tournament-0.059
boards-0.057
Token a
Token ID257
Feature activation-3.12e-02

Pos logit contributions
 whose+0.082
elope+0.075
oc+0.067
 spe+0.066
aron+0.065
Neg logit contributions
 guys-0.124
 plunge-0.105
 tournament-0.104
boards-0.097
 trigger-0.096
Token firefighter
Token ID43105
Feature activation-8.43e-02

Pos logit contributions
 whose+0.062
elope+0.054
 who+0.052
 heaven+0.051
 spe+0.050
Neg logit contributions
 guys-0.054
 plunge-0.046
 tournament-0.046
boards-0.042
 trigger-0.042
Token or
Token ID393
Feature activation-5.47e-02

Pos logit contributions
 whose+0.170
elope+0.152
 spe+0.145
 Chick+0.142
 stret+0.139
Neg logit contributions
 guys-0.142
 tournament-0.106
board-0.102
 plunge-0.098
t-0.097
Token a
Token ID257
Feature activation-3.14e-02

Pos logit contributions
 whose+0.083
elope+0.077
oc+0.069
aron+0.068
 spe+0.068
Neg logit contributions
 guys-0.123
 plunge-0.103
 tournament-0.101
 trigger-0.095
boards-0.094
Token policeman
Token ID32166
Feature activation-3.85e-02

Pos logit contributions
 whose+0.063
elope+0.055
 who+0.052
 heaven+0.051
 spe+0.050
Neg logit contributions
 guys-0.055
 plunge-0.046
 tournament-0.046
 trigger-0.043
boards-0.042
Token.
Token ID13
Feature activation+5.45e-03

Pos logit contributions
 whose+0.070
elope+0.064
 spe+0.060
 heaven+0.057
 who+0.056
Neg logit contributions
 guys-0.072
 plunge-0.059
 tournament-0.058
boards-0.058
board-0.056
Token
Token ID198
Feature activation+4.29e-03

Pos logit contributions
 guys+0.010
 plunge+0.009
 tournament+0.009
boards+0.009
 trigger+0.008
Neg logit contributions
 whose-0.010
 who-0.009
elope-0.008
 spe-0.008
 named-0.008
Token police
Token ID1644
Feature activation-3.14e-02

Pos logit contributions
 whose+0.049
 who+0.044
 named+0.041
elope+0.040
 heaven+0.039
Neg logit contributions
 guys-0.055
 plunge-0.052
boards-0.048
 tournament-0.048
 trigger-0.045
Token officer
Token ID3818
Feature activation-4.93e-02

Pos logit contributions
 whose+0.063
elope+0.058
 spe+0.057
 heaven+0.052
 named+0.052
Neg logit contributions
 guys-0.052
boards-0.043
 plunge-0.043
 tournament-0.042
board-0.041
Token and
Token ID290
Feature activation-2.36e-02

Pos logit contributions
 whose+0.105
 spe+0.100
elope+0.094
 Chick+0.089
 stret+0.088
Neg logit contributions
 guys-0.069
 tournament-0.057
 plunge-0.056
ly-0.055
board-0.055
Token hugged
Token ID41130
Feature activation-1.54e-02

Pos logit contributions
 whose+0.049
elope+0.044
 spe+0.042
aron+0.042
oc+0.041
Neg logit contributions
 guys-0.036
 tournament-0.031
 plunge-0.030
 competition-0.027
board-0.026
Token their
Token ID511
Feature activation-4.24e-02

Pos logit contributions
 whose+0.040
elope+0.036
 spe+0.036
 who+0.035
 named+0.035
Neg logit contributions
 guys-0.017
 plunge-0.013
boards-0.012
 tournament-0.012
 trigger-0.011
Token dolls
Token ID36062
Feature activation-8.36e-02

Pos logit contributions
 whose+0.079
elope+0.067
 who+0.067
 spe+0.064
 heaven+0.063
Neg logit contributions
 guys-0.080
 plunge-0.071
 tournament-0.067
boards-0.066
 trigger-0.065
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
 whose+0.175
 spe+0.162
elope+0.159
 named+0.141
 Chick+0.141
Neg logit contributions
 guys-0.125
 tournament-0.106
 plunge-0.103
boards-0.099
board-0.097
Token The
Token ID383
Feature activation-2.47e-02

Pos logit contributions
 whose+0.032
 spe+0.029
elope+0.029
house+0.028
 who+0.028
Neg logit contributions
 guys-0.019
 tournament-0.017
boards-0.016
 plunge-0.015
 trigger-0.015
Token police
Token ID1644
Feature activation-1.26e-02

Pos logit contributions
 whose+0.046
 who+0.040
elope+0.038
 named+0.038
 spe+0.037
Neg logit contributions
 guys-0.045
 plunge-0.042
 tournament-0.039
boards-0.039
 trigger-0.037
Token officer
Token ID3818
Feature activation-2.27e-02

Pos logit contributions
 whose+0.026
elope+0.024
 spe+0.023
 heaven+0.022
 who+0.021
Neg logit contributions
 guys-0.020
 plunge-0.017
boards-0.017
 tournament-0.016
 trigger-0.016
Token smiled
Token ID13541
Feature activation-3.59e-03

Pos logit contributions
 whose+0.047
elope+0.044
 spe+0.042
 heaven+0.041
 Chick+0.040
Neg logit contributions
 guys-0.033
boards-0.029
 plunge-0.028
board-0.027
 tournament-0.027
Token wants
Token ID3382
Feature activation+1.67e-02

Pos logit contributions
 guys+0.000
 plunge+0.000
 tournament+0.000
boards+0.000
 trigger+0.000
Neg logit contributions
 whose-0.000
 who-0.000
elope-0.000
 spe-0.000
 named-0.000
Token to
Token ID284
Feature activation-2.41e-02

Pos logit contributions
 guys+0.025
 plunge+0.022
boards+0.020
 tournament+0.020
 trigger+0.018
Neg logit contributions
 whose-0.037
 who-0.033
elope-0.033
 spe-0.031
 named-0.031
Token play
Token ID711
Feature activation+1.51e-02

Pos logit contributions
 whose+0.061
 who+0.053
elope+0.053
 spe+0.051
oc+0.050
Neg logit contributions
 guys-0.030
 plunge-0.026
 tournament-0.023
 competition-0.020
boards-0.019
Token,"
Token ID553
Feature activation-4.84e-02

Pos logit contributions
 guys+0.033
 plunge+0.031
 tournament+0.029
boards+0.029
 trigger+0.028
Neg logit contributions
 whose-0.023
 who-0.020
elope-0.018
 named-0.018
 heaven-0.018
Token one
Token ID530
Feature activation-1.18e-02

Pos logit contributions
 whose+0.105
elope+0.095
 spe+0.095
house+0.093
oc+0.090
Neg logit contributions
 guys-0.062
 plunge-0.055
 tournament-0.052
Hey-0.050
t-0.047
Token of
Token ID286
Feature activation-8.30e-02

Pos logit contributions
 whose+0.023
elope+0.020
 spe+0.019
 heaven+0.019
 who+0.019
Neg logit contributions
 guys-0.020
 plunge-0.018
 tournament-0.017
boards-0.017
t-0.017
Token the
Token ID262
Feature activation-2.77e-02

Pos logit contributions
 whose+0.157
oc+0.149
 spe+0.146
elope+0.145
house+0.145
Neg logit contributions
 guys-0.132
 plunge-0.123
Hey-0.109
 trigger-0.108
Stop-0.102
Token moms
Token ID34015
Feature activation-3.71e-02

Pos logit contributions
 whose+0.048
 who+0.041
elope+0.039
 named+0.039
 spe+0.037
Neg logit contributions
 guys-0.054
 plunge-0.050
 tournament-0.047
boards-0.047
 trigger-0.044
Token said
Token ID531
Feature activation-2.58e-02

Pos logit contributions
 whose+0.077
 who+0.068
elope+0.066
 named+0.064
 spe+0.063
Neg logit contributions
 guys-0.060
 plunge-0.054
 tournament-0.051
boards-0.050
 trigger-0.047
Token.
Token ID13
Feature activation-2.02e-02

Pos logit contributions
 whose+0.054
elope+0.051
 spe+0.051
oc+0.048
 heaven+0.047
Neg logit contributions
 guys-0.034
 plunge-0.031
ly-0.030
t-0.030
boards-0.029
Token
Token ID198
Feature activation-2.77e-02

Pos logit contributions
 whose+0.039
 spe+0.034
elope+0.034
house+0.033
 heaven+0.033
Neg logit contributions
 guys-0.030
boards-0.028
 tournament-0.028
 plunge-0.027
Hey-0.026
Token him
Token ID683
Feature activation-4.01e-02

Pos logit contributions
 whose+0.039
elope+0.035
 spe+0.034
 who+0.034
house+0.034
Neg logit contributions
 guys-0.013
 plunge-0.010
boards-0.008
 trigger-0.008
 tournament-0.008
Token.
Token ID13
Feature activation-5.52e-03

Pos logit contributions
 whose+0.087
 spe+0.084
elope+0.078
 heaven+0.075
 named+0.073
Neg logit contributions
 guys-0.055
ly-0.046
 plunge-0.044
board-0.042
 trigger-0.042
Token She
Token ID1375
Feature activation-1.91e-02

Pos logit contributions
 whose+0.011
 spe+0.010
elope+0.010
 who+0.010
 heaven+0.010
Neg logit contributions
 guys-0.007
boards-0.007
 plunge-0.007
 tournament-0.007
board-0.006
Token thanked
Token ID26280
Feature activation-3.18e-02

Pos logit contributions
 whose+0.044
 heaven+0.043
 spe+0.041
elope+0.041
 stret+0.041
Neg logit contributions
 guys-0.018
board-0.016
boards-0.015
 tournament-0.015
t-0.013
Token the
Token ID262
Feature activation-2.22e-02

Pos logit contributions
 whose+0.090
elope+0.082
house+0.082
 spe+0.080
 who+0.079
Neg logit contributions
 guys-0.028
 plunge-0.021
 tournament-0.015
boards-0.014
 trigger-0.014
Token firefighter
Token ID43105
Feature activation-8.22e-02

Pos logit contributions
 whose+0.045
elope+0.039
 who+0.038
 heaven+0.037
 named+0.037
Neg logit contributions
 guys-0.037
 plunge-0.034
 tournament-0.031
boards-0.031
 trigger-0.030
Token.
Token ID13
Feature activation-1.64e-02

Pos logit contributions
 spe+0.180
 whose+0.177
elope+0.162
Pe+0.162
 stret+0.160
Neg logit contributions
 guys-0.099
ly-0.083
 first-0.080
board-0.080
 plunge-0.074
Token She
Token ID1375
Feature activation-1.95e-02

Pos logit contributions
 whose+0.037
 spe+0.034
elope+0.033
 heaven+0.032
 stret+0.032
Neg logit contributions
 guys-0.016
boards-0.016
 plunge-0.015
Hi-0.015
 tournament-0.015
Token checked
Token ID10667
Feature activation+1.61e-04

Pos logit contributions
 whose+0.043
 heaven+0.040
elope+0.039
 spe+0.038
 stret+0.037
Neg logit contributions
 guys-0.023
board-0.021
boards-0.021
 tournament-0.020
 plunge-0.018
Token Tom
Token ID4186
Feature activation+1.36e-02

Pos logit contributions
 guys+0.000
 plunge+0.000
boards+0.000
ly+0.000
 trigger+0.000
Neg logit contributions
 whose-0.000
elope-0.000
 spe-0.000
house-0.000
 heaven-0.000
Token for
Token ID329
Feature activation-4.28e-02

Pos logit contributions
 guys+0.020
 plunge+0.018
boards+0.017
t+0.016
board+0.016
Neg logit contributions
 whose-0.028
 spe-0.026
elope-0.025
 named-0.024
 heaven-0.024
Token lived
Token ID5615
Feature activation-4.46e-03

Pos logit contributions
 whose+0.014
elope+0.012
 stret+0.012
 spe+0.012
 heaven+0.012
Neg logit contributions
 guys-0.010
 plunge-0.008
 tournament-0.008
boards-0.008
t-0.008
Token alone
Token ID3436
Feature activation-4.65e-03

Pos logit contributions
 whose+0.009
elope+0.008
 spe+0.007
oc+0.007
 stret+0.007
Neg logit contributions
 guys-0.007
 plunge-0.007
 tournament-0.006
boards-0.006
 competition-0.006
Token in
Token ID287
Feature activation-3.62e-02

Pos logit contributions
 whose+0.009
elope+0.008
 spe+0.008
 stret+0.008
 heaven+0.008
Neg logit contributions
 guys-0.007
 plunge-0.006
 tournament-0.006
boards-0.006
t-0.006
Token a
Token ID257
Feature activation+3.98e-03

Pos logit contributions
 whose+0.068
aron+0.060
 stret+0.057
oc+0.056
elope+0.056
Neg logit contributions
 guys-0.062
 plunge-0.056
 tournament-0.055
 recess-0.052
 competition-0.050
Token small
Token ID1402
Feature activation-2.38e-04

Pos logit contributions
 guys+0.006
 tournament+0.006
 plunge+0.006
 competition+0.005
boards+0.005
Neg logit contributions
 whose-0.008
 who-0.007
elope-0.007
 spe-0.007
aron-0.007
Token cottage
Token ID36856
Feature activation-8.18e-02

Pos logit contributions
 whose+0.001
elope+0.000
 who+0.000
hes+0.000
 spe+0.000
Neg logit contributions
 guys-0.000
 tournament-0.000
 plunge-0.000
 competition-0.000
board-0.000
Token.
Token ID13
Feature activation+1.29e-02

Pos logit contributions
 whose+0.172
 Chick+0.156
elope+0.153
 stret+0.150
 pap+0.149
Neg logit contributions
 guys-0.101
 plunge-0.095
boards-0.092
t-0.092
board-0.090
Token He
Token ID679
Feature activation+7.84e-03

Pos logit contributions
 guys+0.014
 tournament+0.013
boards+0.012
board+0.011
 plunge+0.011
Neg logit contributions
 whose-0.029
 spe-0.028
 stret-0.026
elope-0.026
 bruised-0.026
Token didn
Token ID1422
Feature activation+6.60e-02

Pos logit contributions
 guys+0.011
 plunge+0.009
 tournament+0.009
boards+0.008
board+0.008
Neg logit contributions
 whose-0.017
 heaven-0.015
 stret-0.015
 spe-0.015
elope-0.014
Token't
Token ID470
Feature activation+3.36e-02

Pos logit contributions
 guys+0.064
 plunge+0.053
 tournament+0.047
boards+0.046
 trigger+0.041
Neg logit contributions
 whose-0.179
 who-0.163
elope-0.159
 named-0.157
 heaven-0.155
Token have
Token ID423
Feature activation+5.72e-03

Pos logit contributions
 guys+0.053
 plunge+0.047
 tournament+0.043
boards+0.042
t+0.040
Neg logit contributions
 whose-0.073
 who-0.062
elope-0.062
 spe-0.060
 named-0.059
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
 whose+0.004
 who+0.004
elope+0.004
 named+0.004
 heaven+0.004
Neg logit contributions
 guys-0.002
 plunge-0.002
boards-0.002
 tournament-0.002
 trigger-0.002
Token What
Token ID1867
Feature activation+9.95e-04

Pos logit contributions
 whose+0.035
elope+0.032
 who+0.031
 spe+0.031
 stret+0.030
Neg logit contributions
 guys-0.019
 plunge-0.016
 tournament-0.015
boards-0.014
t-0.013
Token happened
Token ID3022
Feature activation+5.10e-02

Pos logit contributions
 guys+0.001
 plunge+0.001
 tournament+0.001
boards+0.001
t+0.001
Neg logit contributions
 whose-0.002
elope-0.002
 who-0.002
 spe-0.002
 named-0.002
Token?"
Token ID1701
Feature activation-4.17e-02

Pos logit contributions
 guys+0.087
 plunge+0.082
boards+0.078
 tournament+0.076
 trigger+0.075
Neg logit contributions
 whose-0.101
 who-0.090
 named-0.085
elope-0.082
 heaven-0.081
Token one
Token ID530
Feature activation-1.39e-02

Pos logit contributions
 whose+0.082
 spe+0.072
elope+0.072
oc+0.071
aron+0.070
Neg logit contributions
 guys-0.066
 plunge-0.057
 tournament-0.053
Hey-0.050
t-0.050
Token of
Token ID286
Feature activation-8.13e-02

Pos logit contributions
 whose+0.027
elope+0.023
 who+0.022
 spe+0.022
 heaven+0.022
Neg logit contributions
 guys-0.024
 plunge-0.022
 tournament-0.020
boards-0.020
t-0.020
Token them
Token ID606
Feature activation-2.33e-02

Pos logit contributions
oc+0.148
 whose+0.147
elope+0.142
house+0.139
 spe+0.136
Neg logit contributions
 guys-0.134
 plunge-0.124
Hey-0.112
 trigger-0.110
Stop-0.107
Token asked
Token ID1965
Feature activation-2.92e-02

Pos logit contributions
 whose+0.045
 who+0.039
 named+0.037
elope+0.037
 heaven+0.034
Neg logit contributions
 guys-0.042
 plunge-0.039
 tournament-0.037
boards-0.036
 trigger-0.034
Token.
Token ID13
Feature activation-3.09e-02

Pos logit contributions
 whose+0.055
 spe+0.048
elope+0.048
oc+0.047
 heaven+0.047
Neg logit contributions
 guys-0.051
 plunge-0.045
boards-0.043
 trigger-0.040
 tournament-0.040
Token
Token ID198
Feature activation-3.21e-02

Pos logit contributions
 whose+0.058
elope+0.051
 spe+0.051
 heaven+0.049
oc+0.049
Neg logit contributions
 guys-0.050
 plunge-0.045
boards-0.044
 tournament-0.042
t-0.042
Token
Token ID198
Feature activation-2.32e-02

Pos logit contributions
 whose+0.060
 spe+0.051
elope+0.050
 who+0.050
 heaven+0.049
Neg logit contributions
 guys-0.053
 plunge-0.049
 tournament-0.047
t-0.046
boards-0.046
Token are
Token ID389
Feature activation-1.20e-02

Pos logit contributions
 whose+0.061
 who+0.054
elope+0.052
 named+0.051
 spe+0.051
Neg logit contributions
 guys-0.041
 plunge-0.037
 tournament-0.034
boards-0.034
 trigger-0.032
Token you
Token ID345
Feature activation-1.64e-02

Pos logit contributions
 whose+0.032
elope+0.029
 who+0.029
 spe+0.028
 heaven+0.028
Neg logit contributions
 guys-0.012
 plunge-0.010
 tournament-0.009
boards-0.009
t-0.007
Token?"
Token ID1701
Feature activation-3.89e-02

Pos logit contributions
 whose+0.028
 who+0.025
 named+0.024
elope+0.022
 heaven+0.021
Neg logit contributions
 guys-0.032
 plunge-0.030
boards-0.029
 trigger-0.029
 tournament-0.029
Token Sara
Token ID24799
Feature activation-3.92e-02

Pos logit contributions
 whose+0.069
elope+0.066
house+0.066
sm+0.064
oc+0.063
Neg logit contributions
 guys-0.061
 plunge-0.052
Hi-0.050
Hey-0.049
 Move-0.047
Token says
Token ID1139
Feature activation-2.15e-02

Pos logit contributions
 whose+0.082
 who+0.072
elope+0.069
 named+0.068
 heaven+0.067
Neg logit contributions
 guys-0.064
 plunge-0.059
 tournament-0.055
boards-0.053
 trigger-0.051
Token into
Token ID656
Feature activation-8.12e-02

Pos logit contributions
 whose+0.042
elope+0.038
 spe+0.037
oc+0.036
 heaven+0.035
Neg logit contributions
 guys-0.035
 plunge-0.032
boards-0.029
t-0.029
ived-0.028
Token the
Token ID262
Feature activation-1.72e-02

Pos logit contributions
oc+0.165
 whose+0.160
elope+0.157
house+0.156
c+0.143
Neg logit contributions
 guys-0.123
 plunge-0.093
 recess-0.092
 start-0.092
Stop-0.091
Token phone
Token ID3072
Feature activation-4.44e-02

Pos logit contributions
 whose+0.034
 who+0.029
elope+0.029
 spe+0.028
 named+0.028
Neg logit contributions
 guys-0.030
 plunge-0.027
 tournament-0.025
boards-0.025
 trigger-0.024
Token.
Token ID13
Feature activation-2.86e-02

Pos logit contributions
 whose+0.084
elope+0.076
 spe+0.074
 heaven+0.069
 who+0.069
Neg logit contributions
 guys-0.074
board-0.064
boards-0.064
 plunge-0.064
 tournament-0.061
Token She
Token ID1375
Feature activation-2.44e-02

Pos logit contributions
 whose+0.064
elope+0.060
oc+0.059
 spe+0.058
house+0.056
Neg logit contributions
 guys-0.029
t-0.026
Hi-0.025
 Move-0.025
boards-0.025
Token holds
Token ID6622
Feature activation-4.55e-03

Pos logit contributions
 whose+0.052
 who+0.046
elope+0.046
 named+0.044
 spe+0.044
Neg logit contributions
 guys-0.037
 plunge-0.033
 tournament-0.031
boards-0.030
 trigger-0.028
Token and
Token ID290
Feature activation-3.83e-02

Pos logit contributions
 whose+0.103
elope+0.096
 stret+0.095
 spe+0.095
hes+0.091
Neg logit contributions
 guys-0.076
ly-0.059
boards-0.057
board-0.055
 plunge-0.051
Token lived
Token ID5615
Feature activation-8.35e-03

Pos logit contributions
 whose+0.064
 stret+0.064
 spe+0.057
oc+0.055
 heaven+0.055
Neg logit contributions
 guys-0.071
 plunge-0.061
t-0.059
boards-0.058
board-0.057
Token in
Token ID287
Feature activation-4.66e-02

Pos logit contributions
 whose+0.016
elope+0.015
oc+0.014
 spe+0.014
 stret+0.014
Neg logit contributions
 guys-0.013
 plunge-0.012
 tournament-0.011
 competition-0.011
t-0.011
Token a
Token ID257
Feature activation-1.58e-03

Pos logit contributions
 whose+0.094
oc+0.085
aron+0.085
 stret+0.084
elope+0.081
Neg logit contributions
 guys-0.075
 plunge-0.059
 recess-0.059
 tournament-0.056
 start-0.054
Token small
Token ID1402
Feature activation+2.28e-03

Pos logit contributions
 whose+0.003
elope+0.003
 who+0.003
 spe+0.003
 named+0.002
Neg logit contributions
 guys-0.003
 plunge-0.002
 tournament-0.002
boards-0.002
 competition-0.002
Token cottage
Token ID36856
Feature activation-8.10e-02

Pos logit contributions
 guys+0.003
 tournament+0.003
 plunge+0.002
board+0.002
boards+0.002
Neg logit contributions
 whose-0.005
elope-0.005
 who-0.005
 spe-0.004
 stret-0.004
Token.
Token ID13
Feature activation+1.31e-02

Pos logit contributions
 whose+0.174
 stret+0.174
 Chick+0.166
elope+0.163
 pap+0.161
Neg logit contributions
 guys-0.082
 first-0.077
 plunge-0.077
board-0.077
t-0.076
Token
Token ID198
Feature activation+4.66e-03

Pos logit contributions
 guys+0.025
 plunge+0.023
 tournament+0.022
boards+0.022
board+0.021
Neg logit contributions
 whose-0.023
 who-0.019
elope-0.019
 spe-0.018
 named-0.018
Token
Token ID198
Feature activation+7.07e-03

Pos logit contributions
 guys+0.008
 plunge+0.007
t+0.007
 tournament+0.007
boards+0.007
Neg logit contributions
 whose-0.009
 spe-0.007
elope-0.007
 who-0.007
 heaven-0.007
TokenOne
Token ID3198
Feature activation+2.29e-03

Pos logit contributions
 guys+0.011
 plunge+0.010
 tournament+0.010
boards+0.009
 trigger+0.009
Neg logit contributions
 whose-0.015
 who-0.013
elope-0.013
 named-0.012
 spe-0.012
Token day
Token ID1110
Feature activation+8.27e-03

Pos logit contributions
 guys+0.002
 plunge+0.001
t+0.001
board+0.001
 tournament+0.001
Neg logit contributions
 whose-0.007
 stret-0.006
 spe-0.006
aron-0.006
elope-0.006
Token and
Token ID290
Feature activation-2.33e-02

Pos logit contributions
 spe+0.082
elope+0.080
 whose+0.080
 stret+0.078
oc+0.073
Neg logit contributions
 guys-0.042
 first-0.035
 tournament-0.032
board-0.031
boards-0.030
Token dad
Token ID9955
Feature activation-3.49e-02

Pos logit contributions
 whose+0.044
elope+0.041
 spe+0.040
oc+0.040
house+0.038
Neg logit contributions
 guys-0.042
 plunge-0.035
 tournament-0.035
boards-0.031
 competition-0.030
Token in
Token ID287
Feature activation-4.28e-02

Pos logit contributions
 spe+0.072
elope+0.072
 whose+0.071
 stret+0.069
 Chick+0.066
Neg logit contributions
 guys-0.045
 tournament-0.038
 first-0.038
 plunge-0.037
t-0.036
Token a
Token ID257
Feature activation+2.99e-03

Pos logit contributions
 whose+0.086
aron+0.080
elope+0.078
 chick+0.074
 stret+0.074
Neg logit contributions
 guys-0.062
 tournament-0.055
 recess-0.054
 plunge-0.053
 start-0.053
Token small
Token ID1402
Feature activation+3.48e-03

Pos logit contributions
 guys+0.005
 plunge+0.005
 tournament+0.005
 competition+0.004
boards+0.004
Neg logit contributions
 whose-0.006
elope-0.005
aron-0.005
 who-0.005
 spe-0.005
Token cottage
Token ID36856
Feature activation-8.09e-02

Pos logit contributions
 guys+0.005
 tournament+0.004
 plunge+0.004
 competition+0.004
board+0.003
Neg logit contributions
 whose-0.008
elope-0.007
 who-0.007
aron-0.007
hes-0.007
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
 whose+0.169
 Chick+0.162
elope+0.161
 stret+0.158
 spe+0.153
Neg logit contributions
 guys-0.097
 plunge-0.090
t-0.086
boards-0.085
board-0.085
Token
Token ID198
Feature activation+3.07e-03

Pos logit contributions
 guys+0.018
 plunge+0.016
boards+0.016
 tournament+0.016
board+0.015
Neg logit contributions
 whose-0.020
 spe-0.018
 who-0.017
elope-0.017
 heaven-0.016
Token
Token ID198
Feature activation+3.01e-03

Pos logit contributions
 guys+0.005
 plunge+0.005
t+0.005
 tournament+0.004
boards+0.004
Neg logit contributions
 whose-0.006
 spe-0.005
elope-0.005
 heaven-0.005
 who-0.005
TokenOne
Token ID3198
Feature activation+8.23e-03

Pos logit contributions
 guys+0.005
 plunge+0.004
 tournament+0.004
boards+0.004
 trigger+0.004
Neg logit contributions
 whose-0.006
 who-0.006
elope-0.005
 named-0.005
 heaven-0.005
Token day
Token ID1110
Feature activation+4.07e-03

Pos logit contributions
 guys+0.006
 plunge+0.004
t+0.004
 tournament+0.004
board+0.003
Neg logit contributions
 whose-0.024
 stret-0.022
 spe-0.022
aron-0.021
 heaven-0.021
Token their
Token ID511
Feature activation-3.93e-02

Pos logit contributions
 whose+0.019
 spe+0.018
elope+0.017
oc+0.016
house+0.016
Neg logit contributions
 guys-0.017
 plunge-0.013
ly-0.012
boards-0.012
 trigger-0.012
Token mom
Token ID1995
Feature activation-5.80e-02

Pos logit contributions
 whose+0.067
 who+0.057
elope+0.056
 named+0.053
 spe+0.053
Neg logit contributions
 guys-0.078
 plunge-0.072
 tournament-0.068
boards-0.067
 trigger-0.064
Token and
Token ID290
Feature activation-2.97e-02

Pos logit contributions
 whose+0.125
 spe+0.124
elope+0.117
 Chick+0.111
 rob+0.107
Neg logit contributions
 guys-0.077
ly-0.066
board-0.061
boards-0.058
 plunge-0.055
Token thank
Token ID5875
Feature activation-1.21e-02

Pos logit contributions
 whose+0.062
elope+0.058
oc+0.055
house+0.054
 spe+0.054
Neg logit contributions
 guys-0.048
 plunge-0.038
 tournament-0.037
 decide-0.033
 start-0.032
Token her
Token ID607
Feature activation-4.88e-02

Pos logit contributions
 whose+0.025
elope+0.022
 spe+0.022
 who+0.022
oc+0.021
Neg logit contributions
 guys-0.019
 plunge-0.017
 tournament-0.015
boards-0.014
 competition-0.014
Token for
Token ID329
Feature activation-7.93e-02

Pos logit contributions
 whose+0.100
elope+0.093
 spe+0.092
 heaven+0.083
oc+0.083
Neg logit contributions
 guys-0.076
 plunge-0.064
 tournament-0.061
boards-0.058
t-0.057
Token the
Token ID262
Feature activation-2.44e-02

Pos logit contributions
elope+0.143
oc+0.141
 whose+0.141
 spe+0.131
house+0.130
Neg logit contributions
 guys-0.133
 plunge-0.118
 sidelines-0.113
 tournament-0.110
 competition-0.105
Token jazz
Token ID21274
Feature activation-1.89e-02

Pos logit contributions
 whose+0.050
 who+0.043
elope+0.043
 named+0.041
 spe+0.041
Neg logit contributions
 guys-0.040
 plunge-0.037
 tournament-0.034
boards-0.033
 trigger-0.032
Token CD
Token ID6458
Feature activation-3.20e-02

Pos logit contributions
 whose+0.036
 who+0.031
elope+0.030
 named+0.029
 spe+0.029
Neg logit contributions
 guys-0.034
 plunge-0.031
 tournament-0.029
boards-0.029
 trigger-0.027
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
 whose+0.060
elope+0.053
 spe+0.051
 who+0.049
 heaven+0.048
Neg logit contributions
 guys-0.057
 plunge-0.050
boards-0.049
 tournament-0.049
board-0.048
Token They
Token ID1119
Feature activation-1.33e-02

Pos logit contributions
 whose+0.028
 spe+0.026
elope+0.026
sm+0.025
oc+0.025
Neg logit contributions
 guys-0.014
 tournament-0.012
boards-0.012
 Move-0.011
 plunge-0.011
Token is
Token ID318
Feature activation-5.21e-03

Pos logit contributions
 guys+0.026
 plunge+0.024
 tournament+0.022
boards+0.022
 trigger+0.020
Neg logit contributions
 whose-0.033
 who-0.028
elope-0.028
 named-0.027
 spe-0.027
Token ours
Token ID16903
Feature activation-2.96e-02

Pos logit contributions
 whose+0.014
 who+0.013
elope+0.013
 named+0.012
 spe+0.012
Neg logit contributions
 guys-0.005
 plunge-0.004
 tournament-0.004
boards-0.004
 trigger-0.003
Token now
Token ID783
Feature activation+1.67e-03

Pos logit contributions
 whose+0.060
elope+0.051
 who+0.051
 spe+0.049
 named+0.049
Neg logit contributions
 guys-0.050
 plunge-0.045
 tournament-0.041
boards-0.041
 trigger-0.039
Token!"
Token ID2474
Feature activation-2.55e-02

Pos logit contributions
 guys+0.003
 plunge+0.003
 tournament+0.003
boards+0.003
 trigger+0.002
Neg logit contributions
 whose-0.003
 who-0.003
elope-0.003
 named-0.003
 spe-0.003
Token one
Token ID530
Feature activation-5.79e-03

Pos logit contributions
 whose+0.051
elope+0.045
 who+0.043
 spe+0.043
oc+0.041
Neg logit contributions
 guys-0.043
 plunge-0.037
 tournament-0.037
boards-0.035
t-0.035
Token of
Token ID286
Feature activation-7.92e-02

Pos logit contributions
 whose+0.009
 who+0.008
 named+0.007
elope+0.007
 heaven+0.007
Neg logit contributions
 guys-0.012
 plunge-0.011
boards-0.011
 tournament-0.011
 trigger-0.010
Token the
Token ID262
Feature activation-2.68e-02

Pos logit contributions
 whose+0.145
elope+0.140
 spe+0.135
oc+0.133
house+0.125
Neg logit contributions
 guys-0.137
 plunge-0.124
 trigger-0.113
 tournament-0.111
Hey-0.108
Token big
Token ID1263
Feature activation-1.96e-02

Pos logit contributions
 whose+0.047
 who+0.043
 named+0.040
 heaven+0.037
elope+0.036
Neg logit contributions
 guys-0.050
 plunge-0.046
boards-0.044
 tournament-0.044
ede-0.042
Token kids
Token ID3988
Feature activation-2.97e-02

Pos logit contributions
 whose+0.037
 who+0.034
 named+0.032
 heaven+0.030
elope+0.029
Neg logit contributions
 guys-0.033
 plunge-0.032
boards-0.030
t-0.030
 tournament-0.029
Token says
Token ID1139
Feature activation-1.79e-02

Pos logit contributions
 whose+0.059
 who+0.055
 named+0.050
elope+0.048
 heaven+0.047
Neg logit contributions
 guys-0.051
 plunge-0.046
 tournament-0.045
boards-0.044
 trigger-0.041
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
 whose+0.032
elope+0.027
 who+0.027
 spe+0.026
 named+0.026
Neg logit contributions
 guys-0.033
 plunge-0.031
boards-0.029
 tournament-0.028
 trigger-0.027
Token her
Token ID607
Feature activation-5.53e-02

Pos logit contributions
 whose+0.041
 spe+0.037
elope+0.037
house+0.035
oc+0.035
Neg logit contributions
 guys-0.031
 plunge-0.025
ly-0.023
boards-0.023
t-0.022
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
 whose+0.119
 spe+0.111
elope+0.110
house+0.105
oc+0.104
Neg logit contributions
 guys-0.073
ly-0.060
 plunge-0.060
 trigger-0.058
 first-0.052
Token They
Token ID1119
Feature activation-1.72e-02

Pos logit contributions
 whose+0.023
 spe+0.021
 stret+0.020
elope+0.020
 who+0.020
Neg logit contributions
 guys-0.014
 plunge-0.012
 tournament-0.012
 Want-0.012
boards-0.012
Token thank
Token ID5875
Feature activation-7.42e-03

Pos logit contributions
 whose+0.038
elope+0.033
 spe+0.032
 who+0.032
 heaven+0.031
Neg logit contributions
 guys-0.025
 plunge-0.022
 tournament-0.020
boards-0.019
 competition-0.018
Token her
Token ID607
Feature activation-4.90e-02

Pos logit contributions
 whose+0.016
elope+0.015
 spe+0.014
oc+0.014
 who+0.014
Neg logit contributions
 guys-0.011
 plunge-0.009
 tournament-0.008
boards-0.008
t-0.008
Token for
Token ID329
Feature activation-7.89e-02

Pos logit contributions
 whose+0.103
elope+0.099
 spe+0.098
oc+0.090
house+0.087
Neg logit contributions
 guys-0.075
 plunge-0.057
 tournament-0.056
board-0.055
boards-0.054
Token finding
Token ID4917
Feature activation-3.96e-02

Pos logit contributions
oc+0.153
elope+0.153
house+0.152
 whose+0.151
c+0.140
Neg logit contributions
 guys-0.118
 plunge-0.105
 sidelines-0.105
 tournament-0.095
Stop-0.093
Token the
Token ID262
Feature activation-2.87e-02

Pos logit contributions
 whose+0.079
elope+0.075
oc+0.073
 spe+0.071
house+0.069
Neg logit contributions
 guys-0.063
 plunge-0.055
boards-0.048
ly-0.047
Hey-0.045
Token photo
Token ID4590
Feature activation-2.71e-02

Pos logit contributions
 whose+0.058
elope+0.051
 who+0.049
 named+0.047
oc+0.047
Neg logit contributions
 guys-0.049
 plunge-0.045
 tournament-0.040
 trigger-0.039
boards-0.039
Token.
Token ID13
Feature activation-1.87e-02

Pos logit contributions
 whose+0.052
elope+0.045
 spe+0.043
 who+0.042
oc+0.042
Neg logit contributions
 guys-0.047
 plunge-0.042
boards-0.041
 tournament-0.041
board-0.040
Token They
Token ID1119
Feature activation-1.72e-02

Pos logit contributions
 whose+0.040
 spe+0.038
elope+0.038
 stret+0.037
oc+0.036
Neg logit contributions
 guys-0.020
Hi-0.018
 Move-0.017
 tournament-0.017
 Want-0.017
Token happy
Token ID3772
Feature activation-5.82e-03

Pos logit contributions
 whose+0.067
 who+0.056
elope+0.055
 spe+0.052
 heaven+0.052
Neg logit contributions
 guys-0.080
 plunge-0.074
 tournament-0.070
boards-0.068
t-0.066
Token and
Token ID290
Feature activation-3.47e-02

Pos logit contributions
 whose+0.011
elope+0.009
 spe+0.009
 who+0.009
 named+0.009
Neg logit contributions
 guys-0.011
 plunge-0.009
 tournament-0.009
boards-0.009
board-0.008
Token thanked
Token ID26280
Feature activation-3.99e-02

Pos logit contributions
 whose+0.068
elope+0.058
 who+0.057
 spe+0.055
 heaven+0.055
Neg logit contributions
 guys-0.059
 plunge-0.054
 tournament-0.050
boards-0.047
 competition-0.045
Token the
Token ID262
Feature activation-3.53e-02

Pos logit contributions
 whose+0.082
house+0.071
 spe+0.071
elope+0.071
oc+0.070
Neg logit contributions
 guys-0.065
 plunge-0.056
 tournament-0.050
boards-0.046
 competition-0.046
Token water
Token ID1660
Feature activation-5.07e-02

Pos logit contributions
 whose+0.071
elope+0.060
 who+0.060
 spe+0.057
 named+0.057
Neg logit contributions
 guys-0.060
 plunge-0.054
 tournament-0.051
boards-0.049
 trigger-0.048
Tokenworm
Token ID25323
Feature activation-7.87e-02

Pos logit contributions
 whose+0.103
elope+0.093
 spe+0.090
 heaven+0.086
 who+0.085
Neg logit contributions
 guys-0.077
 plunge-0.073
 tournament-0.066
boards-0.065
board-0.064
Token for
Token ID329
Feature activation-5.77e-02

Pos logit contributions
 whose+0.168
 spe+0.163
elope+0.156
 Chick+0.147
aron+0.146
Neg logit contributions
 guys-0.097
 plunge-0.093
 tournament-0.080
ly-0.078
 competition-0.076
Token his
Token ID465
Feature activation-1.29e-02

Pos logit contributions
 whose+0.111
elope+0.097
oc+0.097
house+0.096
 spe+0.093
Neg logit contributions
 guys-0.098
 plunge-0.089
 tournament-0.081
 sidelines-0.076
 competition-0.075
Token help
Token ID1037
Feature activation-9.27e-03

Pos logit contributions
 whose+0.027
 who+0.024
elope+0.023
 spe+0.023
 named+0.022
Neg logit contributions
 guys-0.020
 plunge-0.018
 tournament-0.016
boards-0.015
 competition-0.015
Token.
Token ID13
Feature activation+7.12e-03

Pos logit contributions
 whose+0.019
 spe+0.016
elope+0.016
 who+0.016
 named+0.015
Neg logit contributions
 guys-0.015
 plunge-0.013
boards-0.012
t-0.012
 tournament-0.011
Token The
Token ID383
Feature activation-1.37e-02

Pos logit contributions
 guys+0.009
 tournament+0.009
boards+0.008
 plunge+0.008
board+0.008
Neg logit contributions
 whose-0.014
 spe-0.013
 stret-0.012
 bruised-0.012
 cigarette-0.012
Token happy
Token ID3772
Feature activation+1.75e-02

Pos logit contributions
 whose+0.040
oc+0.038
elope+0.035
 spe+0.034
 extingu+0.033
Neg logit contributions
 plunge-0.023
 competition-0.023
 guys-0.022
 first-0.020
ived-0.020
Token and
Token ID290
Feature activation-2.34e-02

Pos logit contributions
 guys+0.031
 plunge+0.027
 tournament+0.026
boards+0.026
t+0.024
Neg logit contributions
 whose-0.034
elope-0.029
 who-0.028
 spe-0.028
 named-0.027
Token he
Token ID339
Feature activation+1.26e-02

Pos logit contributions
 whose+0.047
elope+0.041
 who+0.040
 heaven+0.040
 spe+0.039
Neg logit contributions
 guys-0.038
 plunge-0.035
 tournament-0.033
boards-0.031
t-0.030
Token thanked
Token ID26280
Feature activation-2.40e-02

Pos logit contributions
 guys+0.019
 plunge+0.016
 tournament+0.016
boards+0.015
board+0.014
Neg logit contributions
 whose-0.027
elope-0.023
 heaven-0.023
 who-0.023
 spe-0.022
Token the
Token ID262
Feature activation-2.23e-02

Pos logit contributions
 whose+0.043
elope+0.037
 spe+0.035
house+0.035
oc+0.035
Neg logit contributions
 guys-0.045
 plunge-0.041
 tournament-0.037
 competition-0.036
boards-0.035
Token nurse
Token ID15849
Feature activation-7.86e-02

Pos logit contributions
 whose+0.044
 who+0.038
elope+0.037
 named+0.036
 spe+0.036
Neg logit contributions
 guys-0.039
 plunge-0.035
 tournament-0.033
boards-0.032
 trigger-0.031
Token for
Token ID329
Feature activation-5.77e-02

Pos logit contributions
 whose+0.167
 spe+0.164
elope+0.153
 stret+0.145
 heaven+0.144
Neg logit contributions
 guys-0.098
 plunge-0.089
ly-0.083
board-0.081
 tournament-0.080
Token being
Token ID852
Feature activation-3.78e-02

Pos logit contributions
 whose+0.106
elope+0.100
oc+0.098
house+0.093
 spe+0.092
Neg logit contributions
 guys-0.097
 plunge-0.092
 tournament-0.084
 sidelines-0.080
 competition-0.080
Token so
Token ID523
Feature activation-4.94e-02

Pos logit contributions
 whose+0.077
elope+0.075
oc+0.075
 spe+0.067
 stret+0.067
Neg logit contributions
 guys-0.053
 plunge-0.047
 competition-0.045
 tournament-0.044
Hey-0.043
Token kind
Token ID1611
Feature activation+2.89e-03

Pos logit contributions
 whose+0.081
elope+0.071
 heaven+0.066
oc+0.065
 who+0.065
Neg logit contributions
 guys-0.096
 plunge-0.093
 tournament-0.084
t-0.082
boards-0.082
Token.
Token ID13
Feature activation+7.40e-03

Pos logit contributions
 guys+0.005
 plunge+0.005
boards+0.005
 tournament+0.004
t+0.004
Neg logit contributions
 whose-0.005
elope-0.005
 who-0.005
 spe-0.004
 named-0.004
Token are
Token ID389
Feature activation+2.31e-03

Pos logit contributions
 whose+0.026
 who+0.023
 named+0.021
elope+0.021
 heaven+0.021
Neg logit contributions
 guys-0.022
 plunge-0.022
 trigger-0.020
 tournament-0.020
boards-0.019
Token you
Token ID345
Feature activation-6.42e-03

Pos logit contributions
 guys+0.003
 plunge+0.003
boards+0.002
 trigger+0.002
 tournament+0.002
Neg logit contributions
 whose-0.006
 who-0.005
 named-0.005
elope-0.005
 heaven-0.005
Token?"
Token ID1701
Feature activation-4.36e-02

Pos logit contributions
 whose+0.012
 who+0.010
 named+0.010
elope+0.009
 heaven+0.009
Neg logit contributions
 guys-0.012
 plunge-0.011
boards-0.011
 trigger-0.011
 tournament-0.011
Token Ben
Token ID3932
Feature activation-1.67e-02

Pos logit contributions
 whose+0.083
elope+0.074
 spe+0.072
 stret+0.072
oc+0.071
Neg logit contributions
 guys-0.070
 plunge-0.061
 tournament-0.059
t-0.056
Hey-0.054
Token says
Token ID1139
Feature activation-2.24e-02

Pos logit contributions
 whose+0.034
 who+0.030
elope+0.028
 named+0.028
 heaven+0.028
Neg logit contributions
 guys-0.028
 plunge-0.026
 tournament-0.024
boards-0.024
 trigger-0.023
Token into
Token ID656
Feature activation-7.86e-02

Pos logit contributions
 whose+0.044
elope+0.040
 spe+0.038
oc+0.037
 heaven+0.037
Neg logit contributions
 guys-0.037
 plunge-0.033
boards-0.030
t-0.030
ly-0.029
Token the
Token ID262
Feature activation-1.06e-02

Pos logit contributions
 whose+0.136
elope+0.126
oc+0.120
house+0.117
 spe+0.116
Neg logit contributions
 guys-0.147
 plunge-0.123
 tournament-0.122
 trigger-0.121
 competition-0.113
Token phone
Token ID3072
Feature activation-4.29e-02

Pos logit contributions
 whose+0.021
 who+0.019
elope+0.018
 named+0.018
 heaven+0.017
Neg logit contributions
 guys-0.018
 plunge-0.016
boards-0.015
 tournament-0.015
t-0.014
Token.
Token ID13
Feature activation-2.84e-02

Pos logit contributions
 whose+0.079
elope+0.068
 spe+0.067
 who+0.065
 heaven+0.064
Neg logit contributions
 guys-0.077
 plunge-0.068
boards-0.066
 tournament-0.065
board-0.064
Token
Token ID198
Feature activation-2.55e-02

Pos logit contributions
 whose+0.061
elope+0.056
 spe+0.053
 stret+0.053
 heaven+0.052
Neg logit contributions
 guys-0.037
boards-0.031
t-0.031
 plunge-0.030
board-0.030
Token
Token ID198
Feature activation-1.68e-02

Pos logit contributions
 whose+0.052
 spe+0.046
elope+0.045
 stret+0.044
 who+0.043
Neg logit contributions
 guys-0.036
 plunge-0.033
t-0.033
 tournament-0.032
boards-0.032
TokenOnce
Token ID7454
Feature activation-1.48e-02

Pos logit contributions
 guys+0.001
 plunge+0.001
 tournament+0.001
boards+0.001
board+0.001
Neg logit contributions
 whose-0.001
 spe-0.001
 who-0.001
elope-0.001
 heaven-0.001
Token there
Token ID612
Feature activation-1.00e-02

Pos logit contributions
 whose+0.037
 spe+0.033
elope+0.033
 who+0.032
 heaven+0.032
Neg logit contributions
 guys-0.016
 plunge-0.014
t-0.013
 tournament-0.012
boards-0.012
Token was
Token ID373
Feature activation-2.21e-02

Pos logit contributions
 whose+0.022
 heaven+0.021
 stret+0.021
 spe+0.021
aron+0.020
Neg logit contributions
 guys-0.012
 plunge-0.012
t-0.011
boards-0.010
board-0.009
Token a
Token ID257
Feature activation-2.05e-02

Pos logit contributions
 whose+0.035
elope+0.031
oc+0.031
 spe+0.029
 who+0.029
Neg logit contributions
 guys-0.045
 plunge-0.042
 tournament-0.038
boards-0.037
 competition-0.036
Token three
Token ID1115
Feature activation-5.28e-02

Pos logit contributions
 whose+0.041
 heaven+0.035
elope+0.035
 spe+0.033
aron+0.033
Neg logit contributions
 guys-0.034
 tournament-0.028
 plunge-0.027
 competition-0.025
 trigger-0.024
Token-
Token ID12
Feature activation-7.83e-02

Pos logit contributions
 whose+0.103
 heaven+0.096
 spe+0.091
 bruised+0.088
elope+0.088
Neg logit contributions
 guys-0.087
board-0.074
ly-0.070
boards-0.068
 plunge-0.059
Tokenyear
Token ID1941
Feature activation-4.54e-02

Pos logit contributions
 whose+0.134
elope+0.126
 spe+0.121
 heaven+0.117
 stret+0.114
Neg logit contributions
 guys-0.128
t-0.120
 plunge-0.118
boards-0.117
ok-0.113
Token-
Token ID12
Feature activation-5.62e-02

Pos logit contributions
 whose+0.087
 who+0.073
elope+0.073
 heaven+0.070
 spe+0.066
Neg logit contributions
 guys-0.083
 plunge-0.073
ly-0.071
 tournament-0.070
board-0.069
Tokenold
Token ID727
Feature activation-6.45e-02

Pos logit contributions
 whose+0.078
 spe+0.068
elope+0.067
 heaven+0.062
 who+0.060
Neg logit contributions
 guys-0.117
boards-0.111
 plunge-0.110
t-0.110
board-0.105
Token who
Token ID508
Feature activation-4.10e-02

Pos logit contributions
 whose+0.102
 spe+0.100
 heaven+0.093
elope+0.093
hes+0.092
Neg logit contributions
 guys-0.120
ly-0.105
board-0.101
boards-0.091
 plunge-0.090
Token found
Token ID1043
Feature activation-1.90e-02

Pos logit contributions
 whose+0.085
 stret+0.080
 heaven+0.078
 chick+0.075
 spe+0.074
Neg logit contributions
 guys-0.053
t-0.047
board-0.045
boards-0.044
ly-0.039
Token and
Token ID290
Feature activation-3.57e-02

Pos logit contributions
 whose+0.081
 spe+0.074
elope+0.074
 stret+0.070
 paramed+0.068
Neg logit contributions
 guys-0.065
ly-0.047
 plunge-0.047
boards-0.047
 tournament-0.046
Token grand
Token ID4490
Feature activation-8.31e-03

Pos logit contributions
 whose+0.054
elope+0.047
 spe+0.044
 who+0.043
oc+0.042
Neg logit contributions
 guys-0.079
 tournament-0.067
 plunge-0.067
boards-0.064
board-0.062
Tokenpa
Token ID8957
Feature activation-2.68e-02

Pos logit contributions
 whose+0.013
 who+0.011
elope+0.010
 named+0.010
 heaven+0.010
Neg logit contributions
 guys-0.018
 plunge-0.017
 tournament-0.016
boards-0.016
 trigger-0.015
Token,"
Token ID553
Feature activation-4.30e-02

Pos logit contributions
 whose+0.053
 spe+0.048
elope+0.047
 stret+0.044
oc+0.044
Neg logit contributions
 guys-0.044
 plunge-0.035
 tournament-0.034
boards-0.033
ly-0.032
Token one
Token ID530
Feature activation-7.39e-03

Pos logit contributions
 whose+0.082
elope+0.078
oc+0.076
 spe+0.073
house+0.073
Neg logit contributions
 guys-0.068
 tournament-0.056
 plunge-0.052
Hey-0.051
Hi-0.050
Token of
Token ID286
Feature activation-7.82e-02

Pos logit contributions
 whose+0.015
elope+0.014
 spe+0.013
 heaven+0.013
 who+0.013
Neg logit contributions
 guys-0.011
 plunge-0.010
t-0.010
board-0.009
boards-0.009
Token the
Token ID262
Feature activation-1.61e-02

Pos logit contributions
 spe+0.164
elope+0.163
 whose+0.158
oc+0.157
house+0.156
Neg logit contributions
 guys-0.105
 plunge-0.093
Hey-0.084
 trigger-0.081
Stop-0.080
Token kids
Token ID3988
Feature activation-3.69e-02

Pos logit contributions
 whose+0.033
elope+0.029
 who+0.028
 spe+0.027
 named+0.026
Neg logit contributions
 guys-0.027
 plunge-0.024
 tournament-0.023
boards-0.022
 trigger-0.021
Token said
Token ID531
Feature activation-1.77e-02

Pos logit contributions
 whose+0.081
elope+0.075
 spe+0.074
 heaven+0.071
oc+0.070
Neg logit contributions
 guys-0.050
 plunge-0.045
boards-0.041
 tournament-0.039
board-0.039
Token.
Token ID13
Feature activation-2.16e-02

Pos logit contributions
 whose+0.037
elope+0.035
 spe+0.034
oc+0.033
 heaven+0.032
Neg logit contributions
 guys-0.024
 plunge-0.022
ly-0.022
boards-0.021
t-0.021
Token
Token ID198
Feature activation-2.25e-02

Pos logit contributions
 whose+0.042
elope+0.039
 spe+0.038
 heaven+0.036
 who+0.036
Neg logit contributions
 guys-0.032
boards-0.030
 tournament-0.028
t-0.028
 plunge-0.027
Token the
Token ID262
Feature activation-1.11e-02

Pos logit contributions
 whose+0.029
elope+0.026
 who+0.025
 named+0.024
oc+0.024
Neg logit contributions
 guys-0.030
 plunge-0.027
 tournament-0.025
boards-0.025
 competition-0.024
Token bird
Token ID6512
Feature activation-1.70e-02

Pos logit contributions
 whose+0.024
 who+0.020
elope+0.020
 named+0.019
 heaven+0.019
Neg logit contributions
 guys-0.018
 plunge-0.016
 tournament-0.015
boards-0.014
 trigger-0.014
Token,"
Token ID553
Feature activation-3.52e-02

Pos logit contributions
 whose+0.032
elope+0.028
 spe+0.027
 heaven+0.026
 who+0.026
Neg logit contributions
 guys-0.030
 plunge-0.026
t-0.024
 tournament-0.024
boards-0.024
Token said
Token ID531
Feature activation-3.50e-02

Pos logit contributions
 whose+0.071
 spe+0.067
elope+0.064
 heaven+0.061
oc+0.061
Neg logit contributions
 guys-0.052
 plunge-0.044
 tournament-0.043
Hey-0.042
boards-0.040
Token one
Token ID530
Feature activation-2.06e-02

Pos logit contributions
 whose+0.068
oc+0.061
 spe+0.060
elope+0.058
 who+0.057
Neg logit contributions
 guys-0.056
 plunge-0.050
 competition-0.046
t-0.045
 tournament-0.042
Token of
Token ID286
Feature activation-7.81e-02

Pos logit contributions
 whose+0.041
elope+0.037
 heaven+0.037
 spe+0.037
 stret+0.036
Neg logit contributions
 guys-0.030
 plunge-0.028
ly-0.026
board-0.026
t-0.025
Token his
Token ID465
Feature activation-1.97e-02

Pos logit contributions
 whose+0.140
oc+0.137
 spe+0.134
house+0.132
elope+0.130
Neg logit contributions
 guys-0.123
 plunge-0.114
Hey-0.106
 tournament-0.102
 trigger-0.102
Token friends
Token ID2460
Feature activation-3.31e-02

Pos logit contributions
 whose+0.037
 who+0.032
elope+0.031
 heaven+0.031
 spe+0.030
Neg logit contributions
 guys-0.035
 plunge-0.032
 tournament-0.029
boards-0.028
 trigger-0.028
Token.
Token ID13
Feature activation-4.87e-03

Pos logit contributions
 whose+0.062
 spe+0.055
elope+0.055
 heaven+0.053
oc+0.052
Neg logit contributions
 guys-0.055
 plunge-0.052
boards-0.048
 tournament-0.047
board-0.046
Token
Token ID198
Feature activation-1.78e-02

Pos logit contributions
 whose+0.009
 spe+0.008
elope+0.008
 who+0.007
 heaven+0.007
Neg logit contributions
 guys-0.008
 plunge-0.008
 tournament-0.007
boards-0.007
board-0.007
Token
Token ID198
Feature activation-1.21e-02

Pos logit contributions
 whose+0.033
 spe+0.030
 who+0.028
 bruised+0.028
 heaven+0.028
Neg logit contributions
 guys-0.029
 plunge-0.027
 tournament-0.027
boards-0.026
t-0.026
Token war
Token ID1175
Feature activation+1.07e-02

Pos logit contributions
 guys+0.044
 plunge+0.041
boards+0.038
 tournament+0.037
 trigger+0.036
Neg logit contributions
 whose-0.058
 who-0.051
elope-0.049
 named-0.049
 heaven-0.048
Token,
Token ID11
Feature activation-2.21e-02

Pos logit contributions
 guys+0.018
 plunge+0.016
 tournament+0.015
boards+0.015
 trigger+0.014
Neg logit contributions
 whose-0.022
 who-0.019
elope-0.018
 named-0.018
 spe-0.018
Token okay
Token ID8788
Feature activation+2.57e-02

Pos logit contributions
 whose+0.044
elope+0.039
 who+0.038
 spe+0.037
 named+0.037
Neg logit contributions
 guys-0.038
 plunge-0.033
 tournament-0.031
boards-0.030
 trigger-0.028
Token?"
Token ID1701
Feature activation-3.86e-02

Pos logit contributions
 guys+0.044
 plunge+0.038
 tournament+0.035
boards+0.034
t+0.033
Neg logit contributions
 whose-0.052
elope-0.045
 who-0.045
 spe-0.044
 heaven-0.043
Token one
Token ID530
Feature activation-8.58e-03

Pos logit contributions
 whose+0.073
elope+0.066
aron+0.065
oc+0.064
 spe+0.064
Neg logit contributions
 guys-0.061
 plunge-0.054
 tournament-0.053
Hey-0.051
 competition-0.049
Token of
Token ID286
Feature activation-7.80e-02

Pos logit contributions
 whose+0.016
elope+0.014
 who+0.014
 heaven+0.013
 spe+0.013
Neg logit contributions
 guys-0.015
 plunge-0.014
 tournament-0.013
boards-0.013
t-0.012
Token them
Token ID606
Feature activation-1.67e-02

Pos logit contributions
 whose+0.164
elope+0.154
oc+0.147
 spe+0.146
house+0.144
Neg logit contributions
 guys-0.118
 plunge-0.106
 tournament-0.093
 trigger-0.092
Hey-0.089
Token said
Token ID531
Feature activation-1.49e-02

Pos logit contributions
 whose+0.034
elope+0.030
 who+0.030
 spe+0.029
 heaven+0.029
Neg logit contributions
 guys-0.027
 plunge-0.024
boards-0.023
 tournament-0.022
 trigger-0.021
Token.
Token ID13
Feature activation-1.95e-02

Pos logit contributions
 whose+0.030
elope+0.028
 spe+0.027
oc+0.027
 heaven+0.026
Neg logit contributions
 guys-0.022
 plunge-0.020
ly-0.019
boards-0.018
t-0.018
Token
Token ID198
Feature activation-3.19e-02

Pos logit contributions
 whose+0.037
elope+0.032
 spe+0.032
 who+0.031
 heaven+0.031
Neg logit contributions
 guys-0.032
 plunge-0.029
boards-0.028
 tournament-0.028
t-0.026
Token
Token ID198
Feature activation-2.09e-02

Pos logit contributions
 whose+0.065
 spe+0.058
elope+0.055
 heaven+0.055
 bruised+0.054
Neg logit contributions
 guys-0.046
 plunge-0.043
 tournament-0.040
t-0.039
boards-0.039
Token trucks
Token ID13960
Feature activation-1.27e-02

Pos logit contributions
 whose+0.060
elope+0.056
 who+0.052
 named+0.051
 spe+0.050
Neg logit contributions
 guys-0.046
 plunge-0.039
 tournament-0.036
boards-0.035
 trigger-0.034
Token.
Token ID13
Feature activation+1.94e-02

Pos logit contributions
 whose+0.022
 who+0.019
elope+0.019
 named+0.018
 spe+0.018
Neg logit contributions
 guys-0.025
 plunge-0.023
 tournament-0.021
boards-0.021
 trigger-0.020
Token They
Token ID1119
Feature activation+8.39e-03

Pos logit contributions
 guys+0.033
 plunge+0.028
 tournament+0.027
boards+0.026
 Move+0.026
Neg logit contributions
 whose-0.037
 spe-0.032
elope-0.032
 who-0.031
 stret-0.030
Token will
Token ID481
Feature activation+2.38e-02

Pos logit contributions
 guys+0.013
 plunge+0.012
boards+0.011
 tournament+0.011
 trigger+0.010
Neg logit contributions
 whose-0.018
 who-0.016
 named-0.015
elope-0.015
 heaven-0.015
Token not
Token ID407
Feature activation+5.70e-02

Pos logit contributions
 guys+0.036
 plunge+0.033
 tournament+0.030
boards+0.030
 trigger+0.028
Neg logit contributions
 whose-0.051
 who-0.045
elope-0.044
 named-0.043
 spe-0.043
Token run
Token ID1057
Feature activation+5.03e-02

Pos logit contributions
boards+0.086
 guys+0.086
 plunge+0.086
 tournament+0.076
board+0.075
Neg logit contributions
 whose-0.117
 who-0.113
 named-0.104
 heaven-0.100
house-0.098
Token.
Token ID13
Feature activation+1.70e-02

Pos logit contributions
 guys+0.086
 plunge+0.082
 tournament+0.075
boards+0.075
board+0.070
Neg logit contributions
 whose-0.097
 who-0.086
 named-0.081
 heaven-0.079
elope-0.078
Token They
Token ID1119
Feature activation+1.02e-02

Pos logit contributions
 guys+0.028
 plunge+0.023
 tournament+0.022
boards+0.022
 trigger+0.021
Neg logit contributions
 whose-0.034
elope-0.030
 spe-0.030
 who-0.030
 named-0.028
Token will
Token ID481
Feature activation+2.37e-02

Pos logit contributions
 guys+0.015
 plunge+0.014
 tournament+0.013
boards+0.013
 trigger+0.012
Neg logit contributions
 whose-0.022
 who-0.020
elope-0.019
 named-0.019
 spe-0.019
Token be
Token ID307
Feature activation+2.50e-03

Pos logit contributions
 guys+0.036
 plunge+0.032
 tournament+0.029
boards+0.028
 trigger+0.027
Neg logit contributions
 whose-0.052
 who-0.046
elope-0.045
 named-0.044
 spe-0.044
Token sad
Token ID6507
Feature activation+3.80e-02

Pos logit contributions
 guys+0.004
 competition+0.003
 mine+0.003
 start+0.003
 plunge+0.003
Neg logit contributions
 whose-0.005
elope-0.005
oc-0.005
 spe-0.005
 chick-0.004
Token around
Token ID1088
Feature activation-6.38e-04

Pos logit contributions
 guys+0.094
 plunge+0.091
boards+0.090
 trigger+0.090
board+0.087
Neg logit contributions
 whose-0.085
 who-0.082
 named-0.072
 where-0.064
 stret-0.061
Token the
Token ID262
Feature activation+2.89e-02

Pos logit contributions
 whose+0.001
 who+0.001
elope+0.001
 spe+0.001
 named+0.001
Neg logit contributions
 guys-0.001
 plunge-0.001
 tournament-0.001
boards-0.001
 trigger-0.001
Token park
Token ID3952
Feature activation-9.78e-03

Pos logit contributions
 guys+0.047
 plunge+0.043
 tournament+0.040
boards+0.039
 trigger+0.037
Neg logit contributions
 whose-0.060
 who-0.052
elope-0.051
 spe-0.049
 named-0.049
Token.
Token ID13
Feature activation+1.46e-02

Pos logit contributions
 whose+0.016
 who+0.014
 named+0.013
elope+0.013
house+0.012
Neg logit contributions
 guys-0.020
 plunge-0.019
 tournament-0.018
boards-0.017
 trigger-0.017
Token They
Token ID1119
Feature activation+1.87e-02

Pos logit contributions
 guys+0.030
 plunge+0.028
 tournament+0.026
boards+0.026
 trigger+0.025
Neg logit contributions
 whose-0.025
 who-0.021
 named-0.020
elope-0.020
 spe-0.018
Token gigg
Token ID30442
Feature activation+4.97e-02

Pos logit contributions
 guys+0.033
 plunge+0.030
boards+0.028
 tournament+0.028
 trigger+0.028
Neg logit contributions
 whose-0.036
 who-0.033
 named-0.031
elope-0.029
 spe-0.029
Tokenled
Token ID992
Feature activation+7.78e-03

Pos logit contributions
 plunge+0.095
 guys+0.093
 tournament+0.089
boards+0.083
t+0.081
Neg logit contributions
 whose-0.087
 who-0.075
 named-0.068
elope-0.062
 spe-0.061
Token as
Token ID355
Feature activation-3.89e-02

Pos logit contributions
 guys+0.015
 plunge+0.013
 tournament+0.013
boards+0.012
 trigger+0.012
Neg logit contributions
 whose-0.014
elope-0.012
 who-0.012
 heaven-0.011
 spe-0.011
Token they
Token ID484
Feature activation+2.43e-02

Pos logit contributions
 whose+0.080
elope+0.071
 heaven+0.071
 who+0.069
oc+0.068
Neg logit contributions
 guys-0.063
 plunge-0.056
 tournament-0.052
t-0.050
boards-0.050
Token ran
Token ID4966
Feature activation+5.05e-02

Pos logit contributions
 guys+0.043
 plunge+0.041
boards+0.037
 trigger+0.037
 tournament+0.037
Neg logit contributions
 whose-0.046
 who-0.042
 named-0.040
 spe-0.037
elope-0.037
Token,
Token ID11
Feature activation-9.95e-04

Pos logit contributions
 guys+0.105
 plunge+0.098
boards+0.095
 tournament+0.094
ede+0.092
Neg logit contributions
 whose-0.077
 who-0.074
 named-0.067
 where-0.061
house-0.056
Token.
Token ID13
Feature activation-1.55e-03

Pos logit contributions
 whose+0.078
elope+0.067
 spe+0.065
 who+0.064
 heaven+0.062
Neg logit contributions
 guys-0.065
 plunge-0.059
boards-0.057
t-0.056
 tournament-0.055
Token But
Token ID887
Feature activation-4.49e-03

Pos logit contributions
 whose+0.003
elope+0.003
 who+0.003
 spe+0.003
 heaven+0.003
Neg logit contributions
 guys-0.002
 plunge-0.002
boards-0.002
t-0.002
 tournament-0.002
Token he
Token ID339
Feature activation+3.65e-02

Pos logit contributions
 whose+0.008
elope+0.007
 spe+0.007
 heaven+0.007
 who+0.007
Neg logit contributions
 guys-0.008
 plunge-0.008
t-0.007
 tournament-0.007
boards-0.007
Token slipped
Token ID18859
Feature activation+3.69e-02

Pos logit contributions
 guys+0.046
 plunge+0.039
t+0.037
boards+0.037
board+0.036
Neg logit contributions
 whose-0.084
 heaven-0.078
elope-0.075
 spe-0.073
 stret-0.073
Token and
Token ID290
Feature activation+2.60e-02

Pos logit contributions
 guys+0.074
 plunge+0.068
 tournament+0.065
boards+0.064
 trigger+0.061
Neg logit contributions
 whose-0.063
 who-0.054
elope-0.051
 named-0.050
 spe-0.049
Token fell
Token ID3214
Feature activation+4.99e-02

Pos logit contributions
 guys+0.035
 plunge+0.032
boards+0.028
 tournament+0.027
t+0.027
Neg logit contributions
 whose-0.061
elope-0.054
 who-0.053
 heaven-0.051
 spe-0.051
Token.
Token ID13
Feature activation+5.16e-03

Pos logit contributions
 guys+0.103
 tournament+0.095
 plunge+0.094
boards+0.087
 competition+0.084
Neg logit contributions
 whose-0.082
 who-0.072
 named-0.067
 spe-0.066
elope-0.064
Token He
Token ID679
Feature activation+2.95e-02

Pos logit contributions
 guys+0.008
boards+0.008
 plunge+0.007
t+0.007
board+0.007
Neg logit contributions
 whose-0.010
elope-0.009
 who-0.009
 spe-0.008
 heaven-0.008
Token hit
Token ID2277
Feature activation+7.68e-03

Pos logit contributions
 guys+0.039
 plunge+0.034
boards+0.031
t+0.030
 trigger+0.030
Neg logit contributions
 whose-0.068
elope-0.061
 heaven-0.059
 who-0.059
 spe-0.057
Token his
Token ID465
Feature activation+1.07e-02

Pos logit contributions
 guys+0.017
 plunge+0.015
boards+0.014
 tournament+0.014
 trigger+0.014
Neg logit contributions
 whose-0.012
elope-0.010
 who-0.010
 spe-0.009
 named-0.009
Token head
Token ID1182
Feature activation-6.74e-03

Pos logit contributions
 guys+0.014
 plunge+0.013
 trigger+0.011
 surface+0.010
 tournament+0.010
Neg logit contributions
 whose-0.025
elope-0.022
 who-0.022
 named-0.022
 heaven-0.021
TokenB
Token ID33
Feature activation+6.91e-02

Pos logit contributions
 guys+0.028
 plunge+0.027
 tournament+0.024
boards+0.023
 trigger+0.023
Neg logit contributions
 whose-0.020
 who-0.018
 named-0.016
oc-0.016
house-0.016
Tokenenny
Token ID11870
Feature activation+2.62e-02

Pos logit contributions
 guys+0.108
 plunge+0.103
 competition+0.089
boards+0.088
 sidelines+0.088
Neg logit contributions
 whose-0.140
 who-0.127
oc-0.125
elope-0.124
house-0.122
Token was
Token ID373
Feature activation-4.89e-03

Pos logit contributions
 guys+0.041
 plunge+0.036
 tournament+0.034
boards+0.033
 trigger+0.031
Neg logit contributions
 whose-0.056
 who-0.049
elope-0.048
 spe-0.047
 named-0.047
Token sad
Token ID6507
Feature activation+4.78e-02

Pos logit contributions
 whose+0.010
oc+0.009
elope+0.008
 spe+0.008
 stret+0.008
Neg logit contributions
 guys-0.007
 plunge-0.007
 competition-0.006
ived-0.006
 surface-0.006
Token and
Token ID290
Feature activation-1.33e-02

Pos logit contributions
 guys+0.099
 plunge+0.093
 tournament+0.088
boards+0.086
 trigger+0.083
Neg logit contributions
 whose-0.079
 who-0.068
elope-0.063
 named-0.062
 heaven-0.060
Token didn
Token ID1422
Feature activation+7.29e-02

Pos logit contributions
 whose+0.028
 who+0.025
 named+0.024
elope+0.024
 heaven+0.023
Neg logit contributions
 guys-0.022
 plunge-0.020
 tournament-0.018
boards-0.018
 trigger-0.017
Token't
Token ID470
Feature activation+3.49e-02

Pos logit contributions
 guys+0.090
 plunge+0.075
boards+0.071
 tournament+0.069
board+0.062
Neg logit contributions
 whose-0.175
 who-0.159
elope-0.155
 named-0.155
 heaven-0.152
Token know
Token ID760
Feature activation-5.56e-03

Pos logit contributions
boards+0.075
 plunge+0.074
 guys+0.070
 tournament+0.069
 sidelines+0.067
Neg logit contributions
 whose-0.051
 who-0.049
 named-0.045
 heaven-0.042
oc-0.038
Token what
Token ID644
Feature activation+5.20e-03

Pos logit contributions
elope+0.010
aron+0.009
 spe+0.009
 stret+0.008
oc+0.008
Neg logit contributions
 guys-0.010
 plunge-0.009
boards-0.008
ly-0.008
 rocks-0.007
Token to
Token ID284
Feature activation-1.31e-02

Pos logit contributions
 guys+0.007
 plunge+0.006
 tournament+0.006
boards+0.006
t+0.005
Neg logit contributions
 whose-0.012
elope-0.011
 who-0.010
 heaven-0.010
 spe-0.010
Token do
Token ID466
Feature activation+1.86e-02

Pos logit contributions
 whose+0.025
 who+0.023
 named+0.021
elope+0.019
 heaven+0.019
Neg logit contributions
 guys-0.022
boards-0.022
 tournament-0.021
 plunge-0.020
ived-0.020
Token and
Token ID290
Feature activation+8.84e-03

Pos logit contributions
 guys+0.026
 plunge+0.024
 tournament+0.022
boards+0.022
 trigger+0.021
Neg logit contributions
 whose-0.022
 who-0.018
elope-0.018
 named-0.017
 spe-0.017
Token higher
Token ID2440
Feature activation+8.10e-03

Pos logit contributions
 guys+0.015
 plunge+0.014
boards+0.013
 tournament+0.013
 trigger+0.013
Neg logit contributions
 whose-0.017
 who-0.015
 named-0.015
elope-0.014
 spe-0.014
Token,
Token ID11
Feature activation-4.82e-03

Pos logit contributions
 guys+0.017
 plunge+0.015
 tournament+0.014
boards+0.014
 trigger+0.014
Neg logit contributions
 whose-0.014
 who-0.011
elope-0.011
 named-0.011
 spe-0.011
Token while
Token ID981
Feature activation-1.45e-02

Pos logit contributions
 whose+0.009
 who+0.007
elope+0.007
 named+0.007
 spe+0.007
Neg logit contributions
 guys-0.009
 plunge-0.008
 tournament-0.008
boards-0.008
 trigger-0.007
Token Speed
Token ID8729
Feature activation+5.77e-02

Pos logit contributions
 whose+0.025
 who+0.021
elope+0.021
 named+0.020
 spe+0.020
Neg logit contributions
 guys-0.028
 plunge-0.026
 tournament-0.025
boards-0.024
 trigger-0.023
Token went
Token ID1816
Feature activation+4.82e-02

Pos logit contributions
 guys+0.086
 plunge+0.078
 tournament+0.072
boards+0.071
 trigger+0.067
Neg logit contributions
 whose-0.126
 who-0.112
elope-0.109
 named-0.106
 spe-0.105
Token faster
Token ID5443
Feature activation+3.59e-02

Pos logit contributions
 guys+0.112
boards+0.099
 tournament+0.099
 plunge+0.096
 trigger+0.096
Neg logit contributions
 whose-0.063
 who-0.060
 named-0.058
 where-0.056
house-0.047
Token and
Token ID290
Feature activation+2.53e-03

Pos logit contributions
 guys+0.082
 plunge+0.078
boards+0.074
 tournament+0.073
 trigger+0.071
Neg logit contributions
 whose-0.051
 who-0.045
 named-0.039
elope-0.038
 spe-0.037
Token faster
Token ID5443
Feature activation+2.96e-02

Pos logit contributions
 guys+0.004
 plunge+0.004
boards+0.004
board+0.004
 trigger+0.004
Neg logit contributions
 whose-0.005
 who-0.004
 named-0.004
 spe-0.004
elope-0.004
Token.
Token ID13
Feature activation+2.40e-02

Pos logit contributions
 guys+0.066
 plunge+0.064
boards+0.061
 tournament+0.060
board+0.058
Neg logit contributions
 whose-0.042
 who-0.037
 named-0.032
elope-0.031
 spe-0.031
Token
Token ID198
Feature activation+9.52e-03

Pos logit contributions
 guys+0.048
 plunge+0.045
 tournament+0.042
boards+0.042
board+0.040
Neg logit contributions
 whose-0.041
 who-0.035
elope-0.033
 named-0.032
 spe-0.031
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
 whose+0.033
elope+0.030
 spe+0.030
oc+0.028
 heaven+0.028
Neg logit contributions
 guys-0.022
t-0.020
ly-0.020
 plunge-0.020
boards-0.019
Token
Token ID198
Feature activation-1.50e-02

Pos logit contributions
 whose+0.027
elope+0.023
 spe+0.023
 who+0.023
 heaven+0.022
Neg logit contributions
 guys-0.024
boards-0.022
 plunge-0.022
t-0.021
 tournament-0.021
Token
Token ID198
Feature activation-5.44e-03

Pos logit contributions
 whose+0.030
 spe+0.029
elope+0.026
 heaven+0.026
 who+0.025
Neg logit contributions
 guys-0.020
t-0.019
 plunge-0.019
boards-0.018
 tournament-0.018
Token"
Token ID1
Feature activation-1.93e-02

Pos logit contributions
 whose+0.010
 spe+0.009
elope+0.009
 who+0.009
 heaven+0.008
Neg logit contributions
 guys-0.009
 plunge-0.008
 tournament-0.008
boards-0.008
t-0.008
TokenBut
Token ID1537
Feature activation-1.90e-02

Pos logit contributions
 whose+0.039
 who+0.035
elope+0.032
 named+0.032
 spe+0.032
Neg logit contributions
 guys-0.034
 plunge-0.031
 tournament-0.028
boards-0.028
 trigger-0.027
Token I
Token ID314
Feature activation+2.30e-02

Pos logit contributions
 whose+0.043
elope+0.040
oc+0.039
 stret+0.039
 heaven+0.039
Neg logit contributions
 guys-0.026
 plunge-0.023
 tournament-0.018
 trigger-0.017
 competition-0.017
Token like
Token ID588
Feature activation+1.20e-02

Pos logit contributions
 guys+0.032
 plunge+0.028
 tournament+0.026
boards+0.025
t+0.025
Neg logit contributions
 whose-0.053
 who-0.046
elope-0.046
 spe-0.044
 heaven-0.044
Token the
Token ID262
Feature activation-1.87e-02

Pos logit contributions
 guys+0.018
 plunge+0.016
boards+0.014
 tournament+0.014
 competition+0.013
Neg logit contributions
 whose-0.025
elope-0.024
oc-0.023
aron-0.022
 stret-0.022
Token knob
Token ID36842
Feature activation-3.40e-02

Pos logit contributions
 whose+0.041
 who+0.036
elope+0.035
 named+0.034
 spe+0.034
Neg logit contributions
 guys-0.029
 plunge-0.026
boards-0.023
 tournament-0.023
 trigger-0.022
Token.
Token ID13
Feature activation+7.79e-03

Pos logit contributions
 whose+0.065
elope+0.056
 who+0.054
 named+0.053
 spe+0.053
Neg logit contributions
 guys-0.060
 plunge-0.053
boards-0.050
 tournament-0.048
board-0.048
Token It
Token ID632
Feature activation+1.84e-02

Pos logit contributions
 guys+0.009
 plunge+0.007
boards+0.006
board+0.006
 Move+0.006
Neg logit contributions
 whose-0.019
elope-0.017
 stret-0.017
 who-0.017
 spe-0.016
Token searched
Token ID16499
Feature activation+3.23e-02

Pos logit contributions
 guys+0.043
 plunge+0.034
boards+0.032
 tournament+0.032
board+0.030
Neg logit contributions
 whose-0.073
 heaven-0.066
elope-0.064
 stret-0.064
 who-0.063
Token high
Token ID1029
Feature activation+3.56e-02

Pos logit contributions
 guys+0.058
 plunge+0.052
 tournament+0.048
boards+0.048
t+0.045
Neg logit contributions
 whose-0.062
 who-0.053
elope-0.053
 heaven-0.051
 spe-0.050
Token and
Token ID290
Feature activation+1.61e-02

Pos logit contributions
 guys+0.071
 plunge+0.066
 tournament+0.062
boards+0.061
 trigger+0.059
Neg logit contributions
 whose-0.060
 who-0.051
elope-0.049
 named-0.048
 spe-0.047
Token low
Token ID1877
Feature activation+4.55e-02

Pos logit contributions
 guys+0.029
 plunge+0.027
 tournament+0.025
boards+0.024
 trigger+0.024
Neg logit contributions
 whose-0.031
 who-0.027
elope-0.026
 named-0.026
 spe-0.025
Token,
Token ID11
Feature activation+1.44e-02

Pos logit contributions
 guys+0.082
 plunge+0.073
boards+0.069
 tournament+0.066
 trigger+0.064
Neg logit contributions
 whose-0.087
elope-0.074
 who-0.073
 heaven-0.072
 named-0.071
Token but
Token ID475
Feature activation+2.67e-02

Pos logit contributions
 guys+0.023
 plunge+0.021
 tournament+0.019
boards+0.019
t+0.018
Neg logit contributions
 whose-0.030
elope-0.026
 who-0.025
 heaven-0.025
 named-0.024
Token he
Token ID339
Feature activation+5.89e-02

Pos logit contributions
 guys+0.044
 plunge+0.041
 tournament+0.038
boards+0.038
 trigger+0.037
Neg logit contributions
 whose-0.053
 who-0.048
 named-0.045
elope-0.045
 spe-0.042
Token couldn
Token ID3521
Feature activation+7.08e-02

Pos logit contributions
 guys+0.086
 plunge+0.076
boards+0.069
 tournament+0.069
t+0.065
Neg logit contributions
 whose-0.132
 who-0.116
elope-0.114
 heaven-0.112
 spe-0.111
Token't
Token ID470
Feature activation+5.97e-02

Pos logit contributions
 guys+0.095
 plunge+0.081
 tournament+0.072
 trigger+0.072
boards+0.071
Neg logit contributions
 whose-0.161
 who-0.147
elope-0.144
house-0.144
 named-0.143
Token find
Token ID1064
Feature activation-3.29e-03

Pos logit contributions
 guys+0.089
boards+0.085
 plunge+0.084
 tournament+0.081
 trigger+0.076
Neg logit contributions
 whose-0.124
 who-0.120
 named-0.110
elope-0.110
 heaven-0.106
Token any
Token ID597
Feature activation+1.30e-02

Pos logit contributions
 whose+0.007
elope+0.007
 stret+0.007
 named+0.006
 spe+0.006
Neg logit contributions
 guys-0.005
 plunge-0.004
 trigger-0.004
boards-0.003
t-0.003
Token to
Token ID284
Feature activation-1.67e-02

Pos logit contributions
 guys+0.025
 plunge+0.023
boards+0.021
 tournament+0.020
t+0.020
Neg logit contributions
 whose-0.047
elope-0.042
 who-0.042
oc-0.040
 heaven-0.040
Token rot
Token ID5724
Feature activation+1.78e-02

Pos logit contributions
 whose+0.036
elope+0.031
 who+0.031
 named+0.029
 heaven+0.029
Neg logit contributions
 guys-0.026
 plunge-0.024
 tournament-0.021
boards-0.021
 trigger-0.020
Token!
Token ID0
Feature activation+2.43e-02

Pos logit contributions
 guys+0.032
 plunge+0.028
boards+0.027
 tournament+0.026
 trigger+0.025
Neg logit contributions
 whose-0.035
elope-0.030
 who-0.030
 named-0.029
 heaven-0.028
Token Lily
Token ID20037
Feature activation+1.52e-02

Pos logit contributions
 guys+0.047
 plunge+0.044
 tournament+0.041
boards+0.040
 trigger+0.038
Neg logit contributions
 whose-0.043
 who-0.037
elope-0.036
 named-0.035
 heaven-0.034
Token had
Token ID550
Feature activation+1.34e-02

Pos logit contributions
 guys+0.025
 plunge+0.023
 tournament+0.021
boards+0.021
board+0.020
Neg logit contributions
 whose-0.031
 who-0.027
elope-0.026
 spe-0.026
 heaven-0.026
Token been
Token ID587
Feature activation+2.19e-03

Pos logit contributions
 guys+0.024
 plunge+0.022
 tournament+0.021
boards+0.021
t+0.020
Neg logit contributions
 whose-0.025
elope-0.022
 who-0.021
oc-0.020
 named-0.020
Token careless
Token ID36138
Feature activation+2.29e-02

Pos logit contributions
 guys+0.003
 plunge+0.003
 competition+0.003
 tournament+0.003
t+0.003
Neg logit contributions
 whose-0.004
elope-0.004
oc-0.004
aron-0.004
 who-0.003
Token and
Token ID290
Feature activation-9.43e-03

Pos logit contributions
 guys+0.042
 plunge+0.038
boards+0.036
 tournament+0.036
t+0.034
Neg logit contributions
 whose-0.042
elope-0.036
 who-0.035
 spe-0.034
 named-0.033
Token left
Token ID1364
Feature activation-8.25e-03

Pos logit contributions
 whose+0.021
elope+0.019
 who+0.019
 spe+0.018
 heaven+0.018
Neg logit contributions
 guys-0.013
 plunge-0.011
 tournament-0.011
boards-0.011
t-0.010
Token them
Token ID606
Feature activation+2.67e-03

Pos logit contributions
 whose+0.016
elope+0.014
oc+0.014
 spe+0.013
 who+0.013
Neg logit contributions
 guys-0.014
 plunge-0.012
boards-0.012
t-0.012
 trigger-0.011
Token out
Token ID503
Feature activation-1.93e-02

Pos logit contributions
 guys+0.004
 plunge+0.004
 tournament+0.004
boards+0.004
t+0.003
Neg logit contributions
 whose-0.005
elope-0.005
 who-0.005
 spe-0.005
 named-0.004
Token.
Token ID13
Feature activation+2.91e-02

Pos logit contributions
 guys+0.018
 plunge+0.017
 tournament+0.016
boards+0.015
 trigger+0.015
Neg logit contributions
 whose-0.016
 who-0.013
elope-0.013
 named-0.013
 spe-0.013
Token The
Token ID383
Feature activation+4.06e-03

Pos logit contributions
 guys+0.057
 plunge+0.055
 tournament+0.051
 trigger+0.047
ede+0.047
Neg logit contributions
 whose-0.050
 who-0.043
 named-0.041
elope-0.040
 heaven-0.038
Token blocks
Token ID7021
Feature activation-3.33e-03

Pos logit contributions
 guys+0.007
 plunge+0.006
 tournament+0.006
boards+0.006
ede+0.005
Neg logit contributions
 whose-0.008
 who-0.007
 named-0.007
elope-0.007
 heaven-0.006
Token fell
Token ID3214
Feature activation+5.52e-02

Pos logit contributions
 whose+0.006
 who+0.006
 named+0.005
 spe+0.005
house+0.005
Neg logit contributions
 guys-0.006
 plunge-0.005
 tournament-0.005
boards-0.005
 trigger-0.005
Token down
Token ID866
Feature activation+3.16e-03

Pos logit contributions
 guys+0.087
 plunge+0.080
 tournament+0.077
boards+0.072
board+0.067
Neg logit contributions
 whose-0.114
 who-0.102
 named-0.096
 spe-0.096
elope-0.095
Token and
Token ID290
Feature activation+1.83e-02

Pos logit contributions
 guys+0.006
 plunge+0.006
boards+0.005
 tournament+0.005
t+0.005
Neg logit contributions
 whose-0.006
 who-0.005
elope-0.005
 named-0.004
 heaven-0.004
Token the
Token ID262
Feature activation+7.40e-03

Pos logit contributions
 guys+0.031
 plunge+0.028
 tournament+0.027
boards+0.026
 trigger+0.024
Neg logit contributions
 whose-0.037
 who-0.032
elope-0.031
 named-0.031
 spe-0.031
Token pictures
Token ID5986
Feature activation-3.43e-03

Pos logit contributions
 guys+0.012
 plunge+0.011
 tournament+0.010
boards+0.010
 trigger+0.009
Neg logit contributions
 whose-0.015
 who-0.013
elope-0.013
 named-0.012
 spe-0.012
Token on
Token ID319
Feature activation-2.69e-02

Pos logit contributions
 whose+0.007
 who+0.006
 named+0.006
 spe+0.006
elope+0.006
Neg logit contributions
 guys-0.006
 plunge-0.005
 tournament-0.005
boards-0.005
 trigger-0.004
Token the
Token ID262
Feature activation+2.64e-02

Pos logit contributions
 whose+0.047
elope+0.040
 who+0.039
 spe+0.039
oc+0.038
Neg logit contributions
 guys-0.053
 plunge-0.044
 trigger-0.044
 tournament-0.042
boards-0.042
Token wall
Token ID3355
Feature activation-9.63e-03

Pos logit contributions
 guys+0.040
 plunge+0.037
 tournament+0.034
boards+0.033
 trigger+0.031
Neg logit contributions
 whose-0.057
 who-0.051
elope-0.049
 named-0.048
 spe-0.047
Token
Token ID198
Feature activation-6.54e-03

Pos logit contributions
 guys+0.017
 plunge+0.016
boards+0.016
t+0.016
board+0.014
Neg logit contributions
 whose-0.021
 spe-0.019
elope-0.018
 heaven-0.018
 who-0.017
Token
Token ID198
Feature activation-3.92e-03

Pos logit contributions
 whose+0.012
 spe+0.010
elope+0.010
 who+0.010
 heaven+0.009
Neg logit contributions
 guys-0.012
 plunge-0.011
boards-0.011
t-0.011
 tournament-0.010
TokenSo
Token ID2396
Feature activation-6.12e-03

Pos logit contributions
 whose+0.008
 who+0.007
elope+0.007
 spe+0.006
 named+0.006
Neg logit contributions
 guys-0.007
 plunge-0.006
 tournament-0.006
boards-0.006
t-0.005
Token Mom
Token ID11254
Feature activation-2.79e-03

Pos logit contributions
 whose+0.013
elope+0.011
 who+0.011
 heaven+0.011
 spe+0.010
Neg logit contributions
 guys-0.010
 plunge-0.009
 tournament-0.008
t-0.008
boards-0.008
Tokenmy
Token ID1820
Feature activation+9.35e-03

Pos logit contributions
 whose+0.006
elope+0.005
 spe+0.005
 heaven+0.005
 who+0.005
Neg logit contributions
 guys-0.004
 plunge-0.004
boards-0.004
 tournament-0.004
board-0.004
Token went
Token ID1816
Feature activation+3.18e-02

Pos logit contributions
 guys+0.016
 plunge+0.014
 tournament+0.013
boards+0.013
board+0.013
Neg logit contributions
 whose-0.018
elope-0.016
 who-0.016
 heaven-0.015
 spe-0.015
Token back
Token ID736
Feature activation+3.12e-03

Pos logit contributions
 guys+0.053
 plunge+0.047
 tournament+0.044
boards+0.043
 trigger+0.042
Neg logit contributions
 whose-0.066
 who-0.059
 named-0.057
elope-0.055
 heaven-0.055
Token to
Token ID284
Feature activation-3.28e-02

Pos logit contributions
 guys+0.004
 plunge+0.003
 tournament+0.003
boards+0.003
board+0.003
Neg logit contributions
 whose-0.008
elope-0.007
 spe-0.007
 who-0.007
 named-0.006
Token the
Token ID262
Feature activation+2.74e-02

Pos logit contributions
 whose+0.061
elope+0.057
 spe+0.054
oc+0.053
aron+0.052
Neg logit contributions
 guys-0.057
 plunge-0.051
 tournament-0.047
 sidelines-0.047
 start-0.046
Token store
Token ID3650
Feature activation-2.30e-02

Pos logit contributions
 guys+0.047
 plunge+0.044
 tournament+0.040
boards+0.040
 trigger+0.038
Neg logit contributions
 whose-0.054
 who-0.047
elope-0.045
 named-0.044
 heaven-0.044
Token.
Token ID13
Feature activation+2.20e-02

Pos logit contributions
 whose+0.048
 spe+0.044
elope+0.044
 stret+0.040
oc+0.040
Neg logit contributions
 guys-0.033
boards-0.031
board-0.029
 tournament-0.029
t-0.029
Token
Token ID220
Feature activation+1.89e-02

Pos logit contributions
 guys+0.029
 plunge+0.027
boards+0.027
t+0.026
 tournament+0.024
Neg logit contributions
 whose-0.035
 spe-0.033
 heaven-0.030
 named-0.030
elope-0.030
Token
Token ID220
Feature activation+1.95e-02

Pos logit contributions
 guys+0.031
 plunge+0.029
boards+0.029
t+0.027
 tournament+0.026
Neg logit contributions
 whose-0.036
 spe-0.033
 heaven-0.030
 named-0.030
elope-0.030
Token
Token ID198
Feature activation-1.09e-02

Pos logit contributions
 guys+0.032
 plunge+0.030
boards+0.030
t+0.029
 tournament+0.027
Neg logit contributions
 whose-0.037
 spe-0.034
 named-0.031
 heaven-0.031
elope-0.031
Token
Token ID198
Feature activation-1.63e-03

Pos logit contributions
 whose+0.018
 who+0.015
elope+0.015
 spe+0.014
 named+0.014
Neg logit contributions
 guys-0.022
 plunge-0.021
 tournament-0.019
boards-0.019
t-0.018
TokenHe
Token ID1544
Feature activation+2.44e-02

Pos logit contributions
 whose+0.003
 who+0.002
elope+0.002
 named+0.002
 heaven+0.002
Neg logit contributions
 guys-0.003
 plunge-0.003
 trigger-0.003
 tournament-0.003
boards-0.003
Token found
Token ID1043
Feature activation-6.19e-04

Pos logit contributions
 guys+0.040
 plunge+0.036
 tournament+0.034
boards+0.033
 trigger+0.033
Neg logit contributions
 whose-0.050
 who-0.044
elope-0.043
 named-0.042
 spe-0.041
Token many
Token ID867
Feature activation-1.39e-02

Pos logit contributions
 whose+0.001
elope+0.001
 heaven+0.001
 who+0.001
 spe+0.001
Neg logit contributions
 guys-0.001
 plunge-0.001
boards-0.001
 tournament-0.001
 trigger-0.001
Token wonderful
Token ID7932
Feature activation+1.96e-02

Pos logit contributions
 whose+0.028
elope+0.024
 who+0.024
 named+0.023
 heaven+0.023
Neg logit contributions
 guys-0.024
 plunge-0.021
boards-0.020
 tournament-0.019
board-0.018
Token things
Token ID1243
Feature activation-9.51e-03

Pos logit contributions
 guys+0.029
 plunge+0.027
 tournament+0.025
 trigger+0.024
boards+0.024
Neg logit contributions
 whose-0.042
 who-0.038
elope-0.036
 named-0.035
 spe-0.035
Token,
Token ID11
Feature activation-2.94e-03

Pos logit contributions
 whose+0.017
 who+0.015
elope+0.014
 named+0.014
 spe+0.014
Neg logit contributions
 guys-0.018
 plunge-0.016
 tournament-0.016
boards-0.015
 trigger-0.015
Token but
Token ID475
Feature activation+8.71e-03

Pos logit contributions
 whose+0.006
elope+0.005
 who+0.005
 heaven+0.005
 named+0.005
Neg logit contributions
 guys-0.005
 plunge-0.005
boards-0.004
 tournament-0.004
board-0.004
Token better
Token ID1365
Feature activation+2.55e-03

Pos logit contributions
 whose+0.048
elope+0.045
house+0.040
 stret+0.039
 spe+0.038
Neg logit contributions
 guys-0.042
 plunge-0.039
 trigger-0.034
 decide-0.034
 tournament-0.033
Token.
Token ID13
Feature activation+5.83e-03

Pos logit contributions
 guys+0.004
 plunge+0.004
 tournament+0.004
t+0.004
boards+0.004
Neg logit contributions
 whose-0.005
elope-0.004
 spe-0.004
 who-0.004
 named-0.004
Token He
Token ID679
Feature activation+6.90e-03

Pos logit contributions
 guys+0.008
boards+0.007
 plunge+0.007
 tournament+0.007
board+0.007
Neg logit contributions
 whose-0.012
 spe-0.011
 heaven-0.011
 who-0.010
elope-0.010
Token was
Token ID373
Feature activation-2.32e-02

Pos logit contributions
 guys+0.009
 tournament+0.008
boards+0.007
board+0.007
 plunge+0.007
Neg logit contributions
 whose-0.015
 stret-0.013
 heaven-0.013
elope-0.013
 spe-0.013
Token no
Token ID645
Feature activation-7.52e-03

Pos logit contributions
oc+0.050
 whose+0.048
 extingu+0.045
elope+0.045
 stret+0.044
Neg logit contributions
 first-0.028
 mine-0.026
 guys-0.026
 plunge-0.025
 back-0.024
Token longer
Token ID2392
Feature activation-1.40e-02

Pos logit contributions
 whose+0.017
 who+0.015
elope+0.015
 named+0.014
 spe+0.014
Neg logit contributions
 guys-0.011
 plunge-0.010
 tournament-0.009
boards-0.009
 trigger-0.008
Token hungry
Token ID14720
Feature activation+8.06e-03

Pos logit contributions
 whose+0.030
elope+0.027
oc+0.025
 stret+0.025
house+0.024
Neg logit contributions
 guys-0.021
 plunge-0.017
 tournament-0.016
ly-0.016
ived-0.016
Token and
Token ID290
Feature activation-1.90e-02

Pos logit contributions
 guys+0.016
 plunge+0.015
 tournament+0.014
boards+0.014
 trigger+0.014
Neg logit contributions
 whose-0.013
 who-0.012
elope-0.011
 named-0.010
 heaven-0.010
Token he
Token ID339
Feature activation+1.81e-02

Pos logit contributions
 whose+0.044
elope+0.041
 stret+0.040
oc+0.038
aron+0.038
Neg logit contributions
 guys-0.024
 plunge-0.020
 tournament-0.019
t-0.018
boards-0.018
Token was
Token ID373
Feature activation-2.45e-02

Pos logit contributions
 guys+0.026
 tournament+0.020
 plunge+0.020
boards+0.020
board+0.020
Neg logit contributions
 whose-0.040
 stret-0.034
 heaven-0.034
elope-0.034
 spe-0.033
Token happy
Token ID3772
Feature activation+1.38e-02

Pos logit contributions
 whose+0.050
oc+0.048
elope+0.044
 extingu+0.044
 stret+0.042
Neg logit contributions
 guys-0.034
 first-0.030
 plunge-0.030
 mine-0.029
 competition-0.028
Token in
Token ID287
Feature activation-4.79e-02

Pos logit contributions
 guys+0.003
 plunge+0.003
 tournament+0.003
boards+0.003
 trigger+0.002
Neg logit contributions
 whose-0.003
 who-0.003
elope-0.002
 named-0.002
 spe-0.002
Token me
Token ID502
Feature activation+3.38e-03

Pos logit contributions
 whose+0.096
elope+0.088
 stret+0.088
 spe+0.085
house+0.082
Neg logit contributions
 guys-0.073
 plunge-0.063
 tournament-0.061
 competition-0.053
 mine-0.052
Token and
Token ID290
Feature activation-1.69e-02

Pos logit contributions
 guys+0.006
 plunge+0.005
boards+0.004
 tournament+0.004
board+0.004
Neg logit contributions
 whose-0.007
 spe-0.006
 stret-0.006
elope-0.006
 named-0.006
Token love
Token ID1842
Feature activation+9.47e-03

Pos logit contributions
 whose+0.037
elope+0.032
 who+0.031
 spe+0.031
 named+0.030
Neg logit contributions
 guys-0.025
 plunge-0.022
 tournament-0.021
boards-0.019
 competition-0.018
Token me
Token ID502
Feature activation-1.15e-02

Pos logit contributions
 guys+0.016
 plunge+0.014
 tournament+0.013
boards+0.013
 trigger+0.012
Neg logit contributions
 whose-0.019
 who-0.017
elope-0.017
 named-0.016
 spe-0.016
Token.
Token ID13
Feature activation+3.59e-04

Pos logit contributions
 whose+0.025
 spe+0.023
 stret+0.022
elope+0.022
 paramed+0.021
Neg logit contributions
 guys-0.017
 plunge-0.013
t-0.012
ly-0.012
boards-0.012
Token You
Token ID921
Feature activation+1.33e-02

Pos logit contributions
 guys+0.000
 plunge+0.000
 tournament+0.000
boards+0.000
 Move+0.000
Neg logit contributions
 whose-0.001
 spe-0.001
elope-0.001
 stret-0.001
 who-0.001
Token are
Token ID389
Feature activation-1.42e-02

Pos logit contributions
 guys+0.019
 plunge+0.017
 tournament+0.016
boards+0.015
 trigger+0.014
Neg logit contributions
 whose-0.030
 who-0.027
elope-0.026
 named-0.025
 spe-0.025
Token my
Token ID616
Feature activation-2.99e-02

Pos logit contributions
oc+0.030
 whose+0.028
 stret+0.027
elope+0.027
 spe+0.025
Neg logit contributions
 guys-0.022
 mine-0.018
 first-0.017
 plunge-0.017
 tournament-0.017
Token best
Token ID1266
Feature activation+9.90e-03

Pos logit contributions
 whose+0.059
elope+0.052
oc+0.049
 who+0.049
 spe+0.049
Neg logit contributions
 guys-0.052
 plunge-0.045
 tournament-0.041
 competition-0.039
 trigger-0.038
Token friend
Token ID1545
Feature activation-1.35e-02

Pos logit contributions
 guys+0.017
 plunge+0.014
 tournament+0.014
t+0.013
 trigger+0.013
Neg logit contributions
 whose-0.020
elope-0.017
 spe-0.016
 who-0.016
 heaven-0.016
Token were
Token ID547
Feature activation-2.52e-02

Pos logit contributions
 whose+0.001
elope+0.001
 who+0.001
 spe+0.001
 heaven+0.000
Neg logit contributions
 guys-0.000
 plunge-0.000
 tournament-0.000
boards-0.000
Hey-0.000
Token twins
Token ID20345
Feature activation-4.95e-02

Pos logit contributions
 whose+0.059
oc+0.058
 spe+0.057
aron+0.056
elope+0.055
Neg logit contributions
 guys-0.030
 plunge-0.024
 tournament-0.024
 competition-0.024
 first-0.021
Token.
Token ID13
Feature activation-9.61e-04

Pos logit contributions
elope+0.086
 stret+0.085
 whose+0.083
 spe+0.081
oc+0.081
Neg logit contributions
 guys-0.066
 first-0.059
t-0.059
 tournament-0.055
 competition-0.053
Token They
Token ID1119
Feature activation-1.04e-02

Pos logit contributions
 whose+0.002
elope+0.002
 who+0.002
 spe+0.002
 heaven+0.002
Neg logit contributions
 guys-0.001
 plunge-0.001
boards-0.001
 tournament-0.001
t-0.001
Token liked
Token ID8288
Feature activation+1.50e-02

Pos logit contributions
 whose+0.019
elope+0.017
 spe+0.017
 heaven+0.016
 stret+0.016
Neg logit contributions
 guys-0.019
t-0.016
 plunge-0.015
 tournament-0.015
boards-0.015
Token to
Token ID284
Feature activation-5.71e-03

Pos logit contributions
 guys+0.020
 plunge+0.017
 tournament+0.016
boards+0.016
 competition+0.014
Neg logit contributions
 whose-0.035
elope-0.032
 who-0.031
oc-0.030
 spe-0.030
Token play
Token ID711
Feature activation+2.70e-02

Pos logit contributions
 whose+0.014
 who+0.013
elope+0.012
 named+0.012
 spe+0.012
Neg logit contributions
 guys-0.007
 plunge-0.006
boards-0.005
 tournament-0.005
 trigger-0.005
Token together
Token ID1978
Feature activation+1.32e-02

Pos logit contributions
 guys+0.052
 plunge+0.049
 tournament+0.046
boards+0.045
 trigger+0.044
Neg logit contributions
 whose-0.048
 who-0.041
elope-0.039
 named-0.038
 heaven-0.037
Token,
Token ID11
Feature activation+1.43e-02

Pos logit contributions
 guys+0.024
 plunge+0.021
 tournament+0.020
boards+0.020
 competition+0.019
Neg logit contributions
 whose-0.024
elope-0.022
 spe-0.021
 who-0.020
 heaven-0.020
Token but
Token ID475
Feature activation-8.27e-03

Pos logit contributions
 guys+0.024
 plunge+0.021
 tournament+0.020
boards+0.020
t+0.018
Neg logit contributions
 whose-0.029
elope-0.026
 spe-0.025
 heaven-0.024
 who-0.024
Token sometimes
Token ID3360
Feature activation+4.14e-02

Pos logit contributions
 whose+0.017
 who+0.015
elope+0.014
 named+0.014
 spe+0.014
Neg logit contributions
 guys-0.014
 plunge-0.013
 tournament-0.012
boards-0.012
 trigger-0.011
TokenLu
Token ID25596
Feature activation+2.21e-03

Pos logit contributions
 guys+0.005
t+0.005
 plunge+0.005
boards+0.005
Hey+0.005
Neg logit contributions
 whose-0.005
elope-0.005
 spe-0.005
 heaven-0.004
 named-0.004
Tokency
Token ID948
Feature activation-8.55e-03

Pos logit contributions
 guys+0.001
ok+0.001
ly+0.001
board+0.001
t+0.001
Neg logit contributions
 whose-0.006
 stret-0.005
 named-0.005
 who-0.005
 spe-0.005
Token's
Token ID338
Feature activation-1.53e-02

Pos logit contributions
 whose+0.019
 heaven+0.017
 stret+0.017
 spe+0.016
elope+0.016
Neg logit contributions
 guys-0.011
board-0.010
boards-0.009
 plunge-0.009
 tournament-0.009
Token mom
Token ID1995
Feature activation-1.32e-02

Pos logit contributions
 whose+0.033
elope+0.028
aron+0.027
 who+0.027
oc+0.026
Neg logit contributions
 guys-0.024
 plunge-0.021
board-0.019
 start-0.019
 tournament-0.018
Token said
Token ID531
Feature activation-1.65e-02

Pos logit contributions
 whose+0.030
 heaven+0.028
 stret+0.026
 spe+0.026
elope+0.026
Neg logit contributions
 guys-0.015
board-0.015
boards-0.014
 plunge-0.013
 tournament-0.013
Token that
Token ID326
Feature activation-6.38e-03

Pos logit contributions
 whose+0.036
elope+0.034
oc+0.032
house+0.031
 heaven+0.031
Neg logit contributions
 guys-0.025
 plunge-0.021
t-0.019
boards-0.019
ly-0.019
Token if
Token ID611
Feature activation+1.54e-02

Pos logit contributions
 whose+0.013
 stret+0.012
elope+0.012
oc+0.011
aron+0.011
Neg logit contributions
 guys-0.010
 plunge-0.008
boards-0.008
t-0.007
 competition-0.007
Token she
Token ID673
Feature activation+3.98e-02

Pos logit contributions
 guys+0.023
 plunge+0.021
t+0.018
boards+0.017
 tournament+0.017
Neg logit contributions
 whose-0.034
elope-0.030
oc-0.030
 who-0.029
 named-0.029
Token took
Token ID1718
Feature activation+1.71e-02

Pos logit contributions
 guys+0.065
 plunge+0.059
 tournament+0.054
boards+0.054
 trigger+0.051
Neg logit contributions
 whose-0.082
 who-0.072
elope-0.070
 named-0.068
 spe-0.068
Token the
Token ID262
Feature activation+1.28e-02

Pos logit contributions
 guys+0.032
 plunge+0.028
 competition+0.024
ly+0.024
boards+0.024
Neg logit contributions
 whose-0.032
elope-0.028
oc-0.027
 who-0.026
 named-0.026
Token medicine
Token ID9007
Feature activation+2.51e-02

Pos logit contributions
 guys+0.024
 plunge+0.022
boards+0.020
 tournament+0.020
 trigger+0.020
Neg logit contributions
 whose-0.024
elope-0.020
 who-0.020
 named-0.019
 spe-0.019
Token Lily
Token ID20037
Feature activation-6.26e-03

Pos logit contributions
 whose+0.019
oc+0.017
elope+0.017
 spe+0.017
 extingu+0.016
Neg logit contributions
 guys-0.016
 plunge-0.013
 competition-0.012
 mine-0.012
Hey-0.012
Token,"
Token ID553
Feature activation-4.22e-02

Pos logit contributions
 whose+0.013
 spe+0.012
elope+0.011
 Chick+0.010
sm+0.010
Neg logit contributions
 guys-0.010
t-0.008
 tournament-0.008
 plunge-0.008
ly-0.007
Token the
Token ID262
Feature activation-3.49e-02

Pos logit contributions
 whose+0.082
elope+0.072
 who+0.070
 spe+0.070
 heaven+0.067
Neg logit contributions
 guys-0.072
 plunge-0.064
 tournament-0.061
boards-0.059
 trigger-0.056
Token teacher
Token ID4701
Feature activation-3.53e-02

Pos logit contributions
 whose+0.074
 who+0.068
 named+0.065
elope+0.063
 heaven+0.061
Neg logit contributions
 guys-0.055
 plunge-0.049
 tournament-0.044
boards-0.044
 trigger-0.042
Token said
Token ID531
Feature activation-2.16e-02

Pos logit contributions
 whose+0.077
elope+0.071
 spe+0.069
 heaven+0.069
oc+0.065
Neg logit contributions
 guys-0.047
 plunge-0.041
boards-0.041
board-0.039
 tournament-0.038
Token with
Token ID351
Feature activation-5.69e-02

Pos logit contributions
 whose+0.046
elope+0.043
oc+0.043
 spe+0.041
 heaven+0.040
Neg logit contributions
 guys-0.028
ly-0.026
 plunge-0.025
t-0.024
boards-0.024
Token a
Token ID257
Feature activation-2.19e-02

Pos logit contributions
 whose+0.099
elope+0.088
oc+0.082
house+0.079
 who+0.078
Neg logit contributions
 guys-0.111
 plunge-0.098
 tournament-0.094
 trigger-0.093
 competition-0.088
Token smile
Token ID8212
Feature activation-1.41e-02

Pos logit contributions
 whose+0.049
elope+0.043
 who+0.042
 heaven+0.040
 named+0.039
Neg logit contributions
 guys-0.030
 plunge-0.028
 tournament-0.026
 competition-0.025
board-0.025
Token.
Token ID13
Feature activation-1.53e-02

Pos logit contributions
 whose+0.027
elope+0.024
 spe+0.023
 who+0.023
 heaven+0.022
Neg logit contributions
 guys-0.024
 plunge-0.021
boards-0.020
 tournament-0.019
board-0.019
Token "
Token ID366
Feature activation-2.65e-02

Pos logit contributions
 whose+0.028
elope+0.023
 who+0.023
 spe+0.023
 heaven+0.022
Neg logit contributions
 guys-0.028
 plunge-0.026
boards-0.025
 tournament-0.025
board-0.023
TokenI
Token ID40
Feature activation-1.28e-03

Pos logit contributions
 whose+0.057
 who+0.050
elope+0.048
 named+0.047
 heaven+0.047
Neg logit contributions
 guys-0.042
 plunge-0.038
 tournament-0.034
boards-0.034
 trigger-0.033
Token to
Token ID284
Feature activation-6.59e-03

Pos logit contributions
 guys+0.043
 plunge+0.038
boards+0.034
 tournament+0.034
t+0.032
Neg logit contributions
 whose-0.067
elope-0.059
 who-0.059
 spe-0.056
 named-0.056
Token,
Token ID11
Feature activation-1.27e-02

Pos logit contributions
 whose+0.015
 who+0.013
elope+0.013
 named+0.013
 spe+0.012
Neg logit contributions
 guys-0.010
 plunge-0.009
boards-0.008
 tournament-0.008
 trigger-0.007
Token but
Token ID475
Feature activation-2.31e-02

Pos logit contributions
 whose+0.028
elope+0.025
oc+0.024
 spe+0.024
 heaven+0.023
Neg logit contributions
 guys-0.019
 plunge-0.016
boards-0.015
 tournament-0.015
t-0.014
Token she
Token ID673
Feature activation+1.46e-02

Pos logit contributions
 whose+0.050
oc+0.048
elope+0.047
 spe+0.046
 stret+0.046
Neg logit contributions
 guys-0.030
 plunge-0.026
 tournament-0.023
 competition-0.023
 start-0.023
Token listened
Token ID16399
Feature activation+3.47e-02

Pos logit contributions
 guys+0.023
 plunge+0.020
 tournament+0.019
boards+0.019
t+0.018
Neg logit contributions
 whose-0.031
 who-0.027
elope-0.026
 heaven-0.026
 spe-0.026
Token to
Token ID284
Feature activation-5.26e-02

Pos logit contributions
 guys+0.061
 plunge+0.056
 tournament+0.052
boards+0.050
 trigger+0.049
Neg logit contributions
 whose-0.069
 who-0.061
elope-0.057
 named-0.056
 spe-0.055
Token her
Token ID607
Feature activation-1.91e-02

Pos logit contributions
 whose+0.096
 spe+0.090
oc+0.086
elope+0.084
house+0.082
Neg logit contributions
 guys-0.097
 plunge-0.081
 sidelines-0.074
 start-0.074
 tournament-0.072
Token mom
Token ID1995
Feature activation-2.57e-02

Pos logit contributions
 whose+0.038
 spe+0.032
elope+0.032
 who+0.032
 named+0.031
Neg logit contributions
 guys-0.033
 plunge-0.027
board-0.025
 tournament-0.025
 competition-0.025
Token.
Token ID13
Feature activation+3.85e-03

Pos logit contributions
 whose+0.049
 spe+0.045
elope+0.043
 heaven+0.042
 named+0.040
Neg logit contributions
 guys-0.041
 plunge-0.037
boards-0.035
board-0.035
ly-0.034
Token
Token ID198
Feature activation-6.77e-03

Pos logit contributions
 guys+0.006
boards+0.005
 plunge+0.005
 tournament+0.005
board+0.005
Neg logit contributions
 whose-0.008
 spe-0.007
elope-0.007
 who-0.007
 heaven-0.006
Token
Token ID198
Feature activation-6.95e-03

Pos logit contributions
 whose+0.012
 spe+0.011
elope+0.010
 who+0.010
 heaven+0.010
Neg logit contributions
 guys-0.012
 plunge-0.011
 tournament-0.010
boards-0.010
t-0.010
Token careful
Token ID8161
Feature activation+1.49e-02

Pos logit contributions
 spe+0.029
elope+0.028
 whose+0.028
 Wil+0.028
 stret+0.028
Neg logit contributions
 first-0.015
 me-0.015
 guys-0.015
 mine-0.015
 right-0.014
Token of
Token ID286
Feature activation-3.71e-02

Pos logit contributions
 guys+0.026
 plunge+0.024
boards+0.022
 tournament+0.022
t+0.021
Neg logit contributions
 whose-0.029
elope-0.024
 who-0.024
 spe-0.024
 named-0.023
Token dogs
Token ID6844
Feature activation-1.99e-02

Pos logit contributions
 whose+0.082
elope+0.079
house+0.073
oc+0.072
 named+0.072
Neg logit contributions
 guys-0.052
 plunge-0.041
Stop-0.035
 mine-0.034
 first-0.034
Token.
Token ID13
Feature activation+1.92e-04

Pos logit contributions
 whose+0.037
elope+0.033
 spe+0.032
 who+0.030
 named+0.030
Neg logit contributions
 guys-0.036
 plunge-0.031
 tournament-0.030
boards-0.029
t-0.028
Token Some
Token ID2773
Feature activation-1.06e-02

Pos logit contributions
 guys+0.000
 plunge+0.000
 tournament+0.000
boards+0.000
 Move+0.000
Neg logit contributions
 whose-0.000
elope-0.000
 spe-0.000
 who-0.000
 stret-0.000
Token of
Token ID286
Feature activation-6.19e-02

Pos logit contributions
 whose+0.024
elope+0.022
 who+0.021
 spe+0.020
 named+0.020
Neg logit contributions
 guys-0.015
 plunge-0.013
 tournament-0.012
boards-0.012
board-0.011
Token them
Token ID606
Feature activation+1.05e-02

Pos logit contributions
 whose+0.122
elope+0.117
 spe+0.108
oc+0.107
house+0.106
Neg logit contributions
 guys-0.099
 plunge-0.087
 tournament-0.077
 trigger-0.071
Stop-0.070
Token are
Token ID389
Feature activation-1.96e-02

Pos logit contributions
 guys+0.015
 plunge+0.013
boards+0.012
 tournament+0.011
t+0.011
Neg logit contributions
 whose-0.024
elope-0.021
 who-0.021
 spe-0.020
 named-0.020
Token not
Token ID407
Feature activation-2.18e-03

Pos logit contributions
 whose+0.039
elope+0.036
oc+0.035
 who+0.032
 heaven+0.031
Neg logit contributions
 guys-0.032
 plunge-0.025
 tournament-0.024
 mine-0.023
 trigger-0.023
Token friendly
Token ID8030
Feature activation+2.44e-03

Pos logit contributions
 whose+0.004
elope+0.004
oc+0.004
 spe+0.004
house+0.004
Neg logit contributions
 guys-0.004
 plunge-0.003
ly-0.003
 tournament-0.003
 mine-0.003
Token."
Token ID526
Feature activation-2.46e-02

Pos logit contributions
 guys+0.005
 plunge+0.004
 tournament+0.004
boards+0.004
 trigger+0.004
Neg logit contributions
 whose-0.004
 who-0.004
elope-0.004
 spe-0.004
 named-0.004
Token mom
Token ID1995
Feature activation-3.40e-02

Pos logit contributions
 guys+0.014
 plunge+0.012
 tournament+0.012
 trail+0.011
 competition+0.011
Neg logit contributions
 whose-0.018
elope-0.015
 who-0.015
 spe-0.015
aron-0.015
Token and
Token ID290
Feature activation-1.35e-02

Pos logit contributions
 whose+0.069
 spe+0.068
elope+0.066
 de+0.059
 heaven+0.059
Neg logit contributions
 guys-0.048
boards-0.041
 plunge-0.040
board-0.040
ly-0.037
Token dad
Token ID9955
Feature activation-2.67e-02

Pos logit contributions
 whose+0.027
elope+0.026
 spe+0.025
oc+0.024
house+0.024
Neg logit contributions
 guys-0.021
 plunge-0.019
 tournament-0.017
t-0.016
boards-0.016
Token in
Token ID287
Feature activation-4.03e-02

Pos logit contributions
 whose+0.053
 spe+0.050
elope+0.049
 heaven+0.045
oc+0.044
Neg logit contributions
 guys-0.040
 plunge-0.037
t-0.034
boards-0.033
 tournament-0.033
Token the
Token ID262
Feature activation+4.49e-03

Pos logit contributions
 whose+0.082
elope+0.071
house+0.067
bugs+0.066
 Chick+0.065
Neg logit contributions
 plunge-0.055
 guys-0.053
t-0.050
 try-0.047
 start-0.047
Token house
Token ID2156
Feature activation-4.81e-02

Pos logit contributions
 guys+0.008
 plunge+0.007
 tournament+0.007
boards+0.006
 competition+0.006
Neg logit contributions
 whose-0.009
 who-0.007
elope-0.007
 spe-0.007
aron-0.007
Token.
Token ID13
Feature activation+3.47e-04

Pos logit contributions
 whose+0.098
elope+0.091
 spe+0.088
oc+0.085
 chick+0.083
Neg logit contributions
 guys-0.067
 plunge-0.065
boards-0.063
t-0.061
board-0.059
Token They
Token ID1119
Feature activation+6.11e-03

Pos logit contributions
 guys+0.001
boards+0.001
 plunge+0.001
t+0.000
board+0.000
Neg logit contributions
 whose-0.001
 spe-0.001
elope-0.001
 who-0.001
 heaven-0.001
Token hugged
Token ID41130
Feature activation+1.79e-03

Pos logit contributions
 guys+0.009
 plunge+0.008
boards+0.007
 tournament+0.007
t+0.007
Neg logit contributions
 whose-0.013
elope-0.012
 heaven-0.011
 spe-0.011
oc-0.011
Token him
Token ID683
Feature activation-2.74e-02

Pos logit contributions
 guys+0.003
 plunge+0.002
boards+0.002
 trigger+0.002
Stop+0.002
Neg logit contributions
 whose-0.004
elope-0.004
 spe-0.004
house-0.003
oc-0.003
Token and
Token ID290
Feature activation-1.87e-02

Pos logit contributions
 spe+0.060
 whose+0.060
elope+0.056
 heaven+0.055
 stret+0.052
Neg logit contributions
 guys-0.036
 plunge-0.026
 first-0.025
ly-0.025
board-0.024
Token about
Token ID546
Feature activation-1.10e-02

Pos logit contributions
 guys+0.013
 plunge+0.012
 competition+0.012
boards+0.011
 tournament+0.011
Neg logit contributions
 whose-0.014
oc-0.014
elope-0.013
 spe-0.012
 who-0.012
Token to
Token ID284
Feature activation-9.97e-03

Pos logit contributions
 whose+0.027
elope+0.025
oc+0.025
 who+0.024
 spe+0.024
Neg logit contributions
 guys-0.013
 plunge-0.010
 tournament-0.009
boards-0.009
 competition-0.009
Token take
Token ID1011
Feature activation+2.23e-02

Pos logit contributions
 whose+0.024
elope+0.021
oc+0.021
 who+0.020
 spe+0.020
Neg logit contributions
 guys-0.013
 plunge-0.012
 tournament-0.010
 competition-0.010
ede-0.009
Token a
Token ID257
Feature activation+2.04e-02

Pos logit contributions
 guys+0.047
 plunge+0.041
boards+0.038
 competition+0.036
 tournament+0.036
Neg logit contributions
 whose-0.039
elope-0.033
 who-0.032
oc-0.031
 spe-0.030
Token sip
Token ID31145
Feature activation+2.91e-02

Pos logit contributions
 guys+0.032
 plunge+0.029
 tournament+0.026
boards+0.026
 trigger+0.024
Neg logit contributions
 whose-0.044
 who-0.038
elope-0.038
 named-0.036
 spe-0.036
Token of
Token ID286
Feature activation-4.84e-02

Pos logit contributions
 guys+0.058
 plunge+0.053
 tournament+0.051
boards+0.049
 trigger+0.048
Neg logit contributions
 whose-0.049
 who-0.042
elope-0.040
 named-0.039
 spe-0.039
Token her
Token ID607
Feature activation+1.13e-02

Pos logit contributions
 whose+0.094
elope+0.090
oc+0.089
 who+0.081
house+0.079
Neg logit contributions
 guys-0.079
 plunge-0.078
 competition-0.064
 start-0.064
boards-0.062
Token tea
Token ID8887
Feature activation+1.14e-03

Pos logit contributions
 guys+0.020
 plunge+0.018
boards+0.016
board+0.016
 competition+0.016
Neg logit contributions
 whose-0.022
elope-0.019
 who-0.019
 spe-0.018
oc-0.018
Token,
Token ID11
Feature activation+1.02e-02

Pos logit contributions
 guys+0.002
 plunge+0.002
boards+0.002
 tournament+0.002
board+0.002
Neg logit contributions
 whose-0.002
 who-0.002
elope-0.002
 spe-0.002
 named-0.002
Token she
Token ID673
Feature activation+2.52e-02

Pos logit contributions
 guys+0.015
 plunge+0.012
boards+0.010
 competition+0.010
Hey+0.010
Neg logit contributions
oc-0.022
 whose-0.022
elope-0.021
aron-0.020
 stret-0.019
Token heard
Token ID2982
Feature activation+1.80e-03

Pos logit contributions
 guys+0.036
 plunge+0.030
boards+0.029
 tournament+0.028
board+0.027
Neg logit contributions
 whose-0.056
elope-0.049
 who-0.048
 spe-0.048
 heaven-0.047