TOP ACTIVATIONS
MAX = 0.087

the cat 's friend called on the telephone . The friend
and says , " Come on , Max . Let 's
. " Come on , Tom , you can
Tim my 's mom called on the phone . Tim my
and says , " Come on , Ben , it 's
. " Come on , L ila !" Ben
this is fun ! Come on , Tom , fill some
. " Come on , children ," Dad said
That was fun ! Come on , Mia !"
. " Come on , we can do it
thought he would just knock on the window and see if
repair your mask . Come on , let 's go to
. " Come on , Mia !" Sam said
Lily 's friend called her on the phone and asked if
. " Come on , Lily !" Tom said
. " Come on , Ben , it 's
. " Come on , Lily , it 's
. " Come on , Lily !" Tom said
. " Come on , Lily !" he said
to help you . Come on , let 's go inside

MIN ACTIVATIONS
MIN = -0.101

knew to be careful around volcan oes . <|endoftext|> Once upon
was a grand door . Bes ide the door , there
he replied . Fr anny carefully helped her dad
to enjoy ." Fr anny was no longer confused
't know . Luc as started to complain "
it back . Fr ust rated , Jane went
a nice home in a terr arium . They learned more
Tim my loved going on elev ators and always dreamed of
flew away . Luc as continued his walk with
enjoy it ." Fr anny understood and carefully put
read it !" Luc ia smiled and said :
Sara and Ben , " Gu ess what , kids .
little girl all about how volcan oes work . She taught
every day and touch the terr ac otta pot . Maybe
just wanted to write about volcan oes . We like volcan
just wanted to write about volcan oes . We like volcan
The next day , Tri x ie was surprised to
The little bird watched Sab rina with wonder as she
They want to write about volcan oes . They
They want to write about volcan oes . They

INTERVAL 0.040 - 0.087
CONTAINS 1.781%

held his sword tight and shouted " Come and fight me
little shaky at first but with a bit of practice he
the countryside , and every day he whist led a tune
him . One day , his mum said they
the way , Ruby was having so much fun that she

INTERVAL -0.007 - 0.040
CONTAINS 63.790%

her over and over again and she flew off , leaving
drum ming sounded perfect too ! <|endoftext|> Once there was a
saw a fish swimming around in the water . Exc ited
ya with an ignorant look and said , " You can
started pushing buttons and adjusting the settings on the television .

INTERVAL -0.054 - -0.007
CONTAINS 33.998%

les . They got so wet that their rain
Why are you so worried ?" His mom
it all tick ly . That sounded like lots of fun
home happy . <|endoftext|> Jake was a naughty boy . He
, Tim my ! Want some ?" replied Lily .

INTERVAL -0.101 - -0.054
CONTAINS 0.431%

excited . She said , " Can I help you cut
outside in the sun . One day , he walked over
shiny . One day , the boy found
a friend . So , one day he decided to go
bloom ed and the carrots grew big . And Benny was
Token the
Token ID262
Feature activation+1.41e-02

Pos logit contributions
ust+0.008
Really+0.007
Okay+0.007
Deal+0.007
 rightful+0.007
Neg logit contributions
rell-0.005
hered-0.005
hed-0.005
iren-0.005
opl-0.004
Token cat
Token ID3797
Feature activation+2.71e-02

Pos logit contributions
rell+0.022
hered+0.022
hed+0.021
on+0.019
iren+0.019
Neg logit contributions
ust-0.031
Okay-0.025
Really-0.025
urious-0.025
 rightful-0.025
Token's
Token ID338
Feature activation-2.63e-02

Pos logit contributions
hered+0.038
rell+0.037
hed+0.035
on+0.033
 +0.033
Neg logit contributions
ust-0.065
Really-0.051
urious-0.051
 rightful-0.051
Okay-0.050
Token friend
Token ID1545
Feature activation+5.12e-02

Pos logit contributions
ust+0.054
Really+0.041
 rightful+0.040
urious+0.040
Deal+0.039
Neg logit contributions
hered-0.047
rell-0.045
hed-0.043
 on-0.043
 -0.042
Token called
Token ID1444
Feature activation+3.51e-02

Pos logit contributions
rell+0.063
hered+0.061
hed+0.057
iren+0.055
 crash+0.052
Neg logit contributions
ust-0.127
urious-0.101
Really-0.101
Okay-0.100
ara-0.099
Token on
Token ID319
Feature activation+8.69e-02

Pos logit contributions
hed+0.048
rell+0.048
hered+0.048
iren+0.043
on+0.041
Neg logit contributions
ust-0.082
 rightful-0.066
Really-0.063
urious-0.063
Deal-0.061
Token the
Token ID262
Feature activation+3.22e-02

Pos logit contributions
hed+0.144
rell+0.143
hered+0.137
iren+0.122
ched+0.120
Neg logit contributions
ust-0.173
 rightful-0.148
Years-0.145
urious-0.142
Really-0.141
Token telephone
Token ID11426
Feature activation+1.65e-02

Pos logit contributions
hered+0.047
rell+0.047
hed+0.047
on+0.043
iren+0.042
Neg logit contributions
ust-0.074
 rightful-0.060
Really-0.059
Okay-0.058
urious-0.058
Token.
Token ID13
Feature activation+2.46e-02

Pos logit contributions
hered+0.022
rell+0.022
hed+0.021
on+0.019
iren+0.019
Neg logit contributions
ust-0.040
Really-0.032
urious-0.031
 rightful-0.031
Okay-0.031
Token The
Token ID383
Feature activation+1.52e-02

Pos logit contributions
hered+0.032
rell+0.030
hed+0.030
on+0.027
 falling+0.027
Neg logit contributions
ust-0.059
Really-0.050
Okay-0.048
urious-0.048
 rightful-0.048
Token friend
Token ID1545
Feature activation+4.19e-02

Pos logit contributions
rell+0.026
hed+0.026
hered+0.025
 onwards+0.024
 onward+0.023
Neg logit contributions
ust-0.029
Okay-0.025
Deal-0.024
Really-0.024
urious-0.024
Token and
Token ID290
Feature activation+2.18e-02

Pos logit contributions
rell+0.054
hered+0.052
iren+0.048
irens+0.048
quin+0.047
Neg logit contributions
ust-0.094
Deal-0.072
Okay-0.072
Really-0.071
urious-0.071
Token says
Token ID1139
Feature activation+3.60e-02

Pos logit contributions
hered+0.035
rell+0.033
iren+0.031
hed+0.031
on+0.030
Neg logit contributions
ust-0.039
Really-0.036
 rightful-0.034
Deal-0.034
Okay-0.033
Token,
Token ID11
Feature activation+9.72e-03

Pos logit contributions
rell+0.029
hered+0.029
hed+0.026
iren+0.022
 +0.020
Neg logit contributions
ust-0.107
Really-0.091
Deal-0.088
Okay-0.088
 rightful-0.086
Token "
Token ID366
Feature activation-3.66e-02

Pos logit contributions
rell+0.015
hered+0.015
hed+0.014
iren+0.014
ons+0.013
Neg logit contributions
ust-0.021
Really-0.018
Okay-0.016
Deal-0.016
 rightful-0.016
TokenCome
Token ID16773
Feature activation+3.18e-02

Pos logit contributions
ust+0.075
 rightful+0.057
urious+0.056
 former+0.054
Really+0.051
Neg logit contributions
hered-0.068
hed-0.065
rell-0.064
on-0.060
 -0.060
Token on
Token ID319
Feature activation+8.43e-02

Pos logit contributions
rell+0.029
hed+0.024
iren+0.021
hered+0.021
irens+0.020
Neg logit contributions
ust-0.086
Really-0.075
Deal-0.074
Okay-0.073
ara-0.073
Token,
Token ID11
Feature activation-1.20e-02

Pos logit contributions
hed+0.101
rell+0.100
hered+0.091
quin+0.088
iren+0.084
Neg logit contributions
ust-0.201
 rightful-0.172
ara-0.164
Really-0.162
Deal-0.161
Token Max
Token ID5436
Feature activation+2.14e-02

Pos logit contributions
ust+0.033
urious+0.027
Really+0.027
 rightful+0.027
 former+0.026
Neg logit contributions
hered-0.013
rell-0.012
 crash-0.011
 -0.011
hed-0.011
Token.
Token ID13
Feature activation-7.50e-03

Pos logit contributions
hered+0.025
rell+0.024
hed+0.023
 +0.021
on+0.021
Neg logit contributions
ust-0.057
Really-0.047
 rightful-0.046
urious-0.046
Okay-0.045
Token Let
Token ID3914
Feature activation+3.66e-02

Pos logit contributions
ust+0.015
Really+0.012
Okay+0.012
Deal+0.012
 rightful+0.012
Neg logit contributions
rell-0.013
hered-0.012
hed-0.012
iren-0.012
irens-0.011
Token's
Token ID338
Feature activation-3.29e-02

Pos logit contributions
hered+0.045
rell+0.043
iren+0.043
hed+0.041
on+0.041
Neg logit contributions
ust-0.092
urious-0.075
Okay-0.073
 rightful-0.072
Deal-0.071
Token.
Token ID13
Feature activation+9.86e-03

Pos logit contributions
hered+0.024
rell+0.024
hed+0.023
iren+0.021
 +0.021
Neg logit contributions
ust-0.044
Really-0.035
 rightful-0.035
urious-0.035
Okay-0.034
Token
Token ID198
Feature activation+7.55e-03

Pos logit contributions
 +0.011
hered+0.009
 on+0.008
rell+0.008
on+0.008
Neg logit contributions
ust-0.029
urious-0.024
 rightful-0.024
Deal-0.023
 former-0.023
Token
Token ID198
Feature activation-6.53e-03

Pos logit contributions
 +0.008
rell+0.007
hered+0.007
on+0.007
hed+0.007
Neg logit contributions
ust-0.021
 rightful-0.017
Really-0.017
 former-0.017
Deal-0.017
Token"
Token ID1
Feature activation-3.10e-02

Pos logit contributions
ust+0.016
 former+0.013
 rightful+0.013
Really+0.012
urious+0.012
Neg logit contributions
hered-0.009
 -0.009
hed-0.009
 on-0.008
rell-0.008
TokenCome
Token ID16773
Feature activation+3.15e-02

Pos logit contributions
ust+0.072
 former+0.059
 rightful+0.059
urious+0.056
ae+0.054
Neg logit contributions
hered-0.048
hed-0.045
 on-0.041
rell-0.039
iren-0.039
Token on
Token ID319
Feature activation+8.36e-02

Pos logit contributions
rell+0.028
hed+0.025
iren+0.021
hered+0.021
irens+0.020
Neg logit contributions
ust-0.087
Really-0.075
Deal-0.074
ara-0.072
Okay-0.072
Token,
Token ID11
Feature activation-8.28e-03

Pos logit contributions
rell+0.091
hed+0.088
hered+0.084
iren+0.076
quin+0.074
Neg logit contributions
ust-0.211
 rightful-0.179
ara-0.176
ae-0.172
gan-0.169
Token Tom
Token ID4186
Feature activation+1.36e-02

Pos logit contributions
ust+0.021
urious+0.018
 former+0.018
 rightful+0.017
Really+0.017
Neg logit contributions
hered-0.010
 crash-0.010
 on-0.010
 gun-0.010
 -0.010
Token,
Token ID11
Feature activation-1.68e-02

Pos logit contributions
hered+0.010
rell+0.010
hed+0.009
on+0.008
 +0.008
Neg logit contributions
ust-0.041
Really-0.035
 rightful-0.034
urious-0.034
Okay-0.034
Token you
Token ID345
Feature activation+5.94e-03

Pos logit contributions
ust+0.038
 former+0.034
urious+0.033
 rightful+0.033
Really+0.030
Neg logit contributions
 on-0.027
 crash-0.026
hered-0.025
 -0.024
 out-0.024
Token can
Token ID460
Feature activation+5.07e-05

Pos logit contributions
hered+0.009
rell+0.009
hed+0.009
 +0.009
 crash+0.009
Neg logit contributions
ust-0.013
Really-0.011
 rightful-0.011
Okay-0.010
urious-0.010
Token Tim
Token ID5045
Feature activation-1.13e-02

Pos logit contributions
rell+0.003
hed+0.003
hered+0.003
iren+0.003
igh+0.003
Neg logit contributions
ust-0.002
Really-0.002
Okay-0.002
 rightful-0.002
Years-0.002
Tokenmy
Token ID1820
Feature activation+1.58e-02

Pos logit contributions
ust+0.029
Really+0.023
 rightful+0.023
Okay+0.023
urious+0.023
Neg logit contributions
hered-0.014
rell-0.014
hed-0.013
 -0.013
on-0.012
Token's
Token ID338
Feature activation-2.07e-02

Pos logit contributions
rell+0.025
hered+0.024
iren+0.023
hed+0.022
 crash+0.022
Neg logit contributions
ust-0.034
urious-0.027
Okay-0.026
 rightful-0.026
Really-0.026
Token mom
Token ID1995
Feature activation+1.66e-02

Pos logit contributions
ust+0.039
 rightful+0.029
urious+0.029
Really+0.029
Okay+0.028
Neg logit contributions
hered-0.039
rell-0.039
hed-0.038
on-0.037
 -0.036
Token called
Token ID1444
Feature activation+3.15e-02

Pos logit contributions
rell+0.023
hered+0.023
hed+0.021
iren+0.020
on+0.020
Neg logit contributions
ust-0.039
urious-0.031
Okay-0.030
Really-0.030
 rightful-0.030
Token on
Token ID319
Feature activation+8.31e-02

Pos logit contributions
rell+0.046
hed+0.045
hered+0.044
lers+0.041
on+0.041
Neg logit contributions
ust-0.069
 rightful-0.053
Really-0.051
urious-0.051
Deal-0.051
Token the
Token ID262
Feature activation+3.31e-02

Pos logit contributions
rell+0.115
hed+0.110
hered+0.110
on+0.097
iren+0.095
Neg logit contributions
ust-0.194
 rightful-0.162
urious-0.158
Really-0.157
Years-0.156
Token phone
Token ID3072
Feature activation+1.11e-02

Pos logit contributions
hered+0.053
rell+0.052
hed+0.052
on+0.049
ons+0.047
Neg logit contributions
ust-0.069
 rightful-0.057
Really-0.055
Okay-0.055
urious-0.053
Token.
Token ID13
Feature activation+2.12e-02

Pos logit contributions
hered+0.015
rell+0.015
hed+0.015
on+0.014
 +0.013
Neg logit contributions
ust-0.026
Really-0.021
 rightful-0.021
urious-0.021
Okay-0.020
Token Tim
Token ID5045
Feature activation-1.49e-02

Pos logit contributions
hered+0.039
hed+0.037
igh+0.036
rell+0.036
on+0.035
Neg logit contributions
ust-0.035
Really-0.030
Okay-0.029
urious-0.028
Deal-0.027
Tokenmy
Token ID1820
Feature activation+5.06e-03

Pos logit contributions
ust+0.036
urious+0.029
Really+0.029
 rightful+0.028
Okay+0.028
Neg logit contributions
hered-0.021
rell-0.020
hed-0.019
on-0.018
 -0.018
Token and
Token ID290
Feature activation+3.22e-02

Pos logit contributions
rell+0.054
hered+0.053
iren+0.049
hed+0.048
ons+0.048
Neg logit contributions
ust-0.069
Really-0.053
Okay-0.051
urious-0.050
Deal-0.050
Token says
Token ID1139
Feature activation+3.76e-02

Pos logit contributions
hered+0.049
rell+0.047
on+0.046
hed+0.045
iren+0.044
Neg logit contributions
ust-0.070
Really-0.057
Deal-0.056
Okay-0.056
 rightful-0.055
Token,
Token ID11
Feature activation+1.49e-02

Pos logit contributions
hered+0.033
rell+0.033
hed+0.030
iren+0.026
on+0.025
Neg logit contributions
ust-0.111
Really-0.093
Okay-0.090
Deal-0.090
 rightful-0.089
Token "
Token ID366
Feature activation-2.99e-02

Pos logit contributions
hered+0.025
rell+0.024
hed+0.023
iren+0.022
on+0.022
Neg logit contributions
ust-0.031
Really-0.026
Okay-0.024
Deal-0.024
 rightful-0.023
TokenCome
Token ID16773
Feature activation+2.71e-02

Pos logit contributions
ust+0.055
 rightful+0.040
urious+0.039
 former+0.039
Really+0.039
Neg logit contributions
hered-0.060
rell-0.058
hed-0.057
 -0.055
on-0.054
Token on
Token ID319
Feature activation+8.24e-02

Pos logit contributions
rell+0.021
hed+0.018
hered+0.016
iren+0.015
irens+0.014
Neg logit contributions
ust-0.078
Really-0.067
Deal-0.067
Okay-0.066
 rightful-0.065
Token,
Token ID11
Feature activation-1.01e-03

Pos logit contributions
rell+0.081
hed+0.080
hered+0.076
iren+0.067
on+0.063
Neg logit contributions
ust-0.223
 rightful-0.186
ara-0.180
Really-0.179
ae-0.178
Token Ben
Token ID3932
Feature activation+1.40e-02

Pos logit contributions
ust+0.003
urious+0.002
 former+0.002
 rightful+0.002
Really+0.002
Neg logit contributions
hered-0.001
 on-0.001
 -0.001
 crash-0.001
rell-0.001
Token,
Token ID11
Feature activation-1.45e-02

Pos logit contributions
hered+0.013
rell+0.012
hed+0.011
 +0.010
on+0.010
Neg logit contributions
ust-0.041
Really-0.034
 rightful-0.033
urious-0.033
Okay-0.033
Token it
Token ID340
Feature activation+3.42e-04

Pos logit contributions
ust+0.033
urious+0.027
 rightful+0.026
 former+0.026
Really+0.025
Neg logit contributions
hered-0.023
 on-0.022
 crash-0.022
 -0.021
rell-0.021
Token's
Token ID338
Feature activation-9.50e-03

Pos logit contributions
hered+0.000
rell+0.000
hed+0.000
 +0.000
 on+0.000
Neg logit contributions
ust-0.001
Really-0.001
 rightful-0.001
urious-0.001
Okay-0.001
Token.
Token ID13
Feature activation+6.57e-03

Pos logit contributions
ust+0.022
Really+0.018
 rightful+0.018
urious+0.018
Okay+0.017
Neg logit contributions
hered-0.011
rell-0.011
hed-0.010
on-0.010
 -0.010
Token
Token ID198
Feature activation+1.37e-02

Pos logit contributions
 +0.007
 on+0.005
iren+0.005
on+0.005
 crash+0.005
Neg logit contributions
ust-0.020
 rightful-0.016
 former-0.016
urious-0.016
Deal-0.016
Token
Token ID198
Feature activation-9.60e-04

Pos logit contributions
 +0.014
hered+0.014
rell+0.014
hed+0.013
on+0.013
Neg logit contributions
ust-0.038
 rightful-0.031
Really-0.031
 former-0.030
Deal-0.030
Token"
Token ID1
Feature activation-3.44e-02

Pos logit contributions
ust+0.002
 former+0.002
 rightful+0.002
Really+0.002
urious+0.002
Neg logit contributions
hered-0.001
 -0.001
iren-0.001
rell-0.001
 on-0.001
TokenCome
Token ID16773
Feature activation+2.71e-02

Pos logit contributions
ust+0.082
 former+0.069
 rightful+0.067
urious+0.062
asured+0.061
Neg logit contributions
hered-0.051
 on-0.047
hed-0.046
 -0.045
iren-0.045
Token on
Token ID319
Feature activation+8.22e-02

Pos logit contributions
rell+0.037
hed+0.033
hered+0.029
iren+0.029
ons+0.029
Neg logit contributions
ust-0.063
Really-0.053
Deal-0.052
Okay-0.051
 rightful-0.051
Token,
Token ID11
Feature activation-7.22e-03

Pos logit contributions
rell+0.088
hed+0.084
hered+0.076
quin+0.070
iren+0.069
Neg logit contributions
ust-0.214
 rightful-0.182
ara-0.177
ae-0.173
Really-0.173
Token L
Token ID406
Feature activation-2.32e-02

Pos logit contributions
ust+0.017
 former+0.015
 rightful+0.014
urious+0.014
Deal+0.014
Neg logit contributions
 crash-0.011
 on-0.011
 -0.010
hered-0.010
 gun-0.010
Tokenila
Token ID10102
Feature activation+1.07e-02

Pos logit contributions
ust+0.038
 former+0.031
 rightful+0.031
Really+0.031
urious+0.028
Neg logit contributions
hered-0.049
on-0.048
rell-0.047
hed-0.047
 on-0.047
Token!"
Token ID2474
Feature activation-7.93e-03

Pos logit contributions
rell+0.009
hered+0.009
hed+0.008
iren+0.008
on+0.007
Neg logit contributions
ust-0.030
 rightful-0.025
Deal-0.025
urious-0.025
Okay-0.025
Token Ben
Token ID3932
Feature activation+1.68e-02

Pos logit contributions
ust+0.019
Really+0.015
 rightful+0.015
urious+0.015
Okay+0.015
Neg logit contributions
hered-0.011
rell-0.011
hed-0.010
 -0.010
on-0.010
Token this
Token ID428
Feature activation+1.09e-02

Pos logit contributions
rell+0.014
hed+0.014
hered+0.014
iren+0.013
irens+0.012
Neg logit contributions
ust-0.019
Really-0.015
 rightful-0.014
Deal-0.014
Okay-0.014
Token is
Token ID318
Feature activation+6.31e-04

Pos logit contributions
hered+0.017
rell+0.017
hed+0.016
on+0.015
iren+0.015
Neg logit contributions
ust-0.024
Really-0.019
 rightful-0.019
urious-0.019
Okay-0.019
Token fun
Token ID1257
Feature activation+1.93e-02

Pos logit contributions
hered+0.001
rell+0.001
hed+0.001
on+0.001
 +0.001
Neg logit contributions
ust-0.002
Really-0.001
 rightful-0.001
urious-0.001
Okay-0.001
Token!
Token ID0
Feature activation-1.05e-02

Pos logit contributions
rell+0.026
hered+0.026
hed+0.025
 +0.024
iren+0.023
Neg logit contributions
ust-0.046
Really-0.037
 rightful-0.037
urious-0.036
Okay-0.036
Token Come
Token ID7911
Feature activation+1.29e-02

Pos logit contributions
ust+0.026
urious+0.021
 rightful+0.021
Really+0.020
 former+0.020
Neg logit contributions
hered-0.014
rell-0.013
hed-0.013
 -0.012
on-0.012
Token on
Token ID319
Feature activation+8.21e-02

Pos logit contributions
rell+0.012
hed+0.010
hered+0.010
iren+0.009
ons+0.008
Neg logit contributions
ust-0.036
Really-0.031
Okay-0.030
Deal-0.030
 rightful-0.030
Token,
Token ID11
Feature activation-1.55e-02

Pos logit contributions
rell+0.086
hed+0.079
hered+0.076
iren+0.068
quin+0.065
Neg logit contributions
ust-0.218
 rightful-0.183
ara-0.179
Really-0.175
ae-0.173
Token Tom
Token ID4186
Feature activation+2.77e-03

Pos logit contributions
ust+0.036
urious+0.030
 former+0.030
 rightful+0.029
Really+0.028
Neg logit contributions
hered-0.024
 crash-0.023
 on-0.022
 gun-0.022
 -0.022
Token,
Token ID11
Feature activation-2.75e-02

Pos logit contributions
hered+0.003
rell+0.003
hed+0.003
on+0.003
 +0.003
Neg logit contributions
ust-0.007
Really-0.006
 rightful-0.006
urious-0.006
Okay-0.006
Token fill
Token ID6070
Feature activation-8.47e-03

Pos logit contributions
ust+0.062
urious+0.051
 former+0.050
 rightful+0.049
Really+0.047
Neg logit contributions
 on-0.044
hered-0.044
 crash-0.043
 -0.042
on-0.041
Token some
Token ID617
Feature activation-9.08e-03

Pos logit contributions
ust+0.023
Really+0.018
urious+0.018
 rightful+0.018
Okay+0.018
Neg logit contributions
hered-0.010
rell-0.009
hed-0.009
on-0.009
 -0.009
Token.
Token ID13
Feature activation+5.58e-03

Pos logit contributions
hered+0.001
rell+0.001
hed+0.001
 on+0.001
 +0.001
Neg logit contributions
ust-0.001
Really-0.001
 former-0.001
 rightful-0.001
urious-0.001
Token
Token ID198
Feature activation+4.12e-03

Pos logit contributions
 +0.006
hered+0.005
rell+0.005
 on+0.005
iren+0.005
Neg logit contributions
ust-0.016
urious-0.013
 rightful-0.013
 former-0.013
Deal-0.012
Token
Token ID198
Feature activation-9.11e-03

Pos logit contributions
hered+0.005
rell+0.005
 +0.004
hed+0.004
on+0.004
Neg logit contributions
ust-0.011
Really-0.009
 rightful-0.009
urious-0.009
Deal-0.009
Token"
Token ID1
Feature activation-3.76e-02

Pos logit contributions
ust+0.023
 former+0.018
 rightful+0.018
urious+0.018
Really+0.018
Neg logit contributions
hered-0.012
 -0.012
 on-0.011
iren-0.011
on-0.011
TokenCome
Token ID16773
Feature activation+2.69e-02

Pos logit contributions
ust+0.086
 former+0.066
urious+0.066
 rightful+0.066
ae+0.062
Neg logit contributions
hered-0.062
hed-0.056
 on-0.054
iren-0.053
rell-0.052
Token on
Token ID319
Feature activation+8.20e-02

Pos logit contributions
rell+0.027
hed+0.023
hered+0.020
iren+0.019
ons+0.019
Neg logit contributions
ust-0.072
Really-0.062
Deal-0.062
 rightful-0.060
Okay-0.060
Token,
Token ID11
Feature activation-1.21e-02

Pos logit contributions
rell+0.092
hed+0.091
hered+0.082
iren+0.076
quin+0.076
Neg logit contributions
ust-0.204
 rightful-0.174
ara-0.170
ae-0.165
Really-0.163
Token children
Token ID1751
Feature activation+4.17e-02

Pos logit contributions
ust+0.030
 former+0.027
urious+0.026
 rightful+0.025
Really+0.025
Neg logit contributions
 crash-0.016
 on-0.016
 gun-0.015
 -0.015
rell-0.014
Token,"
Token ID553
Feature activation-1.87e-02

Pos logit contributions
hered+0.035
rell+0.033
hed+0.031
 +0.028
on+0.028
Neg logit contributions
ust-0.125
Really-0.105
 rightful-0.103
urious-0.103
 former-0.102
Token Dad
Token ID17415
Feature activation+1.72e-02

Pos logit contributions
ust+0.046
urious+0.036
 rightful+0.035
Really+0.035
 former+0.035
Neg logit contributions
hered-0.026
rell-0.026
 -0.025
hed-0.024
 on-0.024
Token said
Token ID531
Feature activation-4.10e-03

Pos logit contributions
hered+0.027
rell+0.026
hed+0.025
on+0.024
 +0.024
Neg logit contributions
ust-0.039
Really-0.030
urious-0.030
 rightful-0.030
Okay-0.030
TokenThat
Token ID2504
Feature activation+9.48e-03

Pos logit contributions
ust+0.054
 rightful+0.041
 former+0.040
urious+0.040
Really+0.039
Neg logit contributions
hered-0.050
rell-0.048
hed-0.048
 -0.045
 crash-0.044
Token was
Token ID373
Feature activation+2.68e-03

Pos logit contributions
hered+0.015
rell+0.014
hed+0.014
on+0.013
iren+0.013
Neg logit contributions
ust-0.021
Really-0.017
urious-0.017
Okay-0.016
 rightful-0.016
Token fun
Token ID1257
Feature activation+2.34e-02

Pos logit contributions
hered+0.005
rell+0.005
hed+0.005
on+0.005
iren+0.005
Neg logit contributions
ust-0.005
Really-0.004
 rightful-0.004
Deal-0.004
urious-0.004
Token!
Token ID0
Feature activation-1.15e-02

Pos logit contributions
hered+0.027
rell+0.026
hed+0.025
on+0.023
 +0.023
Neg logit contributions
ust-0.062
Really-0.050
 rightful-0.050
urious-0.050
Okay-0.050
Token Come
Token ID7911
Feature activation+1.32e-02

Pos logit contributions
ust+0.026
urious+0.020
 rightful+0.020
Really+0.020
Okay+0.020
Neg logit contributions
hered-0.018
rell-0.017
hed-0.017
 -0.016
on-0.016
Token on
Token ID319
Feature activation+8.18e-02

Pos logit contributions
rell+0.010
hed+0.009
hered+0.009
iren+0.008
ons+0.007
Neg logit contributions
ust-0.039
Really-0.033
Deal-0.033
Okay-0.033
 rightful-0.032
Token,
Token ID11
Feature activation-1.86e-02

Pos logit contributions
rell+0.082
hed+0.080
hered+0.073
quin+0.064
iren+0.064
Neg logit contributions
ust-0.221
 rightful-0.185
ara-0.180
Really-0.178
ae-0.175
Token Mia
Token ID32189
Feature activation-5.49e-03

Pos logit contributions
ust+0.048
 former+0.042
urious+0.041
 rightful+0.039
Really+0.039
Neg logit contributions
 crash-0.023
 on-0.023
hered-0.023
 -0.022
 gun-0.021
Token!"
Token ID2474
Feature activation-1.06e-02

Pos logit contributions
ust+0.016
Really+0.014
 rightful+0.014
urious+0.014
 former+0.014
Neg logit contributions
hered-0.005
rell-0.004
hed-0.004
 on-0.004
on-0.004
Token
Token ID198
Feature activation-1.24e-02

Pos logit contributions
ust+0.026
Really+0.021
 rightful+0.021
urious+0.021
Okay+0.021
Neg logit contributions
hered-0.014
rell-0.014
hed-0.013
 -0.013
on-0.013
Token
Token ID198
Feature activation-2.03e-02

Pos logit contributions
ust+0.034
 rightful+0.028
Really+0.028
 former+0.028
urious+0.027
Neg logit contributions
hered-0.013
 -0.013
rell-0.013
hed-0.012
on-0.012
Token.
Token ID13
Feature activation+8.39e-03

Pos logit contributions
hered+0.002
rell+0.002
hed+0.002
 +0.002
 on+0.002
Neg logit contributions
ust-0.005
Really-0.004
 rightful-0.004
urious-0.004
Okay-0.004
Token
Token ID198
Feature activation+7.08e-03

Pos logit contributions
hered+0.011
rell+0.011
hed+0.010
 +0.010
on+0.010
Neg logit contributions
ust-0.021
 rightful-0.017
Really-0.017
urious-0.017
Okay-0.017
Token
Token ID198
Feature activation-9.82e-03

Pos logit contributions
hered+0.009
rell+0.008
hed+0.008
 +0.008
on+0.008
Neg logit contributions
ust-0.018
Really-0.015
 rightful-0.015
urious-0.015
Okay-0.015
Token"
Token ID1
Feature activation-4.20e-02

Pos logit contributions
ust+0.020
Really+0.015
Okay+0.015
urious+0.015
 rightful+0.014
Neg logit contributions
rell-0.018
hered-0.018
hed-0.017
on-0.016
 crash-0.016
TokenCome
Token ID16773
Feature activation+2.48e-02

Pos logit contributions
ust+0.094
 rightful+0.076
 former+0.075
urious+0.073
asured+0.068
Neg logit contributions
hered-0.071
hed-0.067
rell-0.063
 -0.063
 on-0.062
Token on
Token ID319
Feature activation+8.13e-02

Pos logit contributions
rell+0.021
hed+0.018
hered+0.017
iren+0.015
ons+0.015
Neg logit contributions
ust-0.070
Really-0.060
Deal-0.060
Okay-0.059
 rightful-0.058
Token,
Token ID11
Feature activation-9.13e-03

Pos logit contributions
rell+0.089
hed+0.084
hered+0.082
iren+0.074
on+0.070
Neg logit contributions
ust-0.208
 rightful-0.175
ara-0.170
Really-0.168
ae-0.167
Token we
Token ID356
Feature activation+4.39e-03

Pos logit contributions
ust+0.020
 former+0.017
urious+0.016
 rightful+0.016
Really+0.016
Neg logit contributions
 crash-0.015
hered-0.014
 gun-0.014
 on-0.014
 -0.014
Token can
Token ID460
Feature activation+8.59e-04

Pos logit contributions
hered+0.008
rell+0.008
hed+0.008
 +0.008
 on+0.007
Neg logit contributions
ust-0.009
Really-0.007
 rightful-0.006
urious-0.006
Okay-0.006
Token do
Token ID466
Feature activation+9.47e-03

Pos logit contributions
hered+0.001
rell+0.001
hed+0.001
 +0.001
 crash+0.001
Neg logit contributions
ust-0.002
Really-0.002
urious-0.002
 rightful-0.002
Okay-0.002
Token it
Token ID340
Feature activation-8.12e-03

Pos logit contributions
hered+0.013
rell+0.013
hed+0.012
iren+0.011
on+0.011
Neg logit contributions
ust-0.023
Really-0.019
 rightful-0.018
Deal-0.018
urious-0.018
Token thought
Token ID1807
Feature activation+5.08e-03

Pos logit contributions
ust+0.008
Really+0.007
 rightful+0.007
 former+0.007
Deal+0.007
Neg logit contributions
 -0.003
 on-0.003
hered-0.003
hed-0.003
on-0.003
Token he
Token ID339
Feature activation+4.52e-03

Pos logit contributions
hered+0.006
rell+0.005
hed+0.005
on+0.005
 +0.005
Neg logit contributions
ust-0.014
Really-0.011
 rightful-0.011
urious-0.011
Okay-0.011
Token would
Token ID561
Feature activation+1.21e-02

Pos logit contributions
hered+0.006
 +0.006
rell+0.006
hed+0.006
on+0.006
Neg logit contributions
ust-0.011
 rightful-0.009
Really-0.009
 former-0.009
Okay-0.008
Token just
Token ID655
Feature activation-1.51e-02

Pos logit contributions
 crash+0.017
hered+0.016
rell+0.016
 +0.016
 on+0.016
Neg logit contributions
ust-0.029
Really-0.024
urious-0.024
Deal-0.023
Okay-0.023
Token knock
Token ID10643
Feature activation+1.49e-02

Pos logit contributions
ust+0.035
Really+0.028
urious+0.028
 rightful+0.027
Okay+0.027
Neg logit contributions
hered-0.022
rell-0.021
 -0.021
 on-0.021
hed-0.021
Token on
Token ID319
Feature activation+8.11e-02

Pos logit contributions
hered+0.014
rell+0.014
hed+0.012
iren+0.011
 crash+0.010
Neg logit contributions
ust-0.043
Really-0.035
 rightful-0.035
urious-0.035
Okay-0.035
Token the
Token ID262
Feature activation+4.02e-02

Pos logit contributions
hered+0.092
rell+0.090
hed+0.084
iren+0.074
on+0.072
Neg logit contributions
ust-0.217
 rightful-0.177
Really-0.175
urious-0.175
Okay-0.172
Token window
Token ID4324
Feature activation+9.29e-03

Pos logit contributions
hered+0.072
hed+0.069
rell+0.068
on+0.063
ons+0.061
Neg logit contributions
ust-0.081
 rightful-0.064
Really-0.062
urious-0.061
Okay-0.059
Token and
Token ID290
Feature activation+1.67e-02

Pos logit contributions
hered+0.012
rell+0.011
hed+0.011
iren+0.010
on+0.010
Neg logit contributions
ust-0.024
 rightful-0.019
urious-0.019
Really-0.019
Okay-0.019
Token see
Token ID766
Feature activation-2.24e-03

Pos logit contributions
hered+0.022
rell+0.021
hed+0.020
 +0.020
 on+0.020
Neg logit contributions
ust-0.042
Really-0.034
 rightful-0.034
urious-0.033
Deal-0.033
Token if
Token ID611
Feature activation+9.15e-03

Pos logit contributions
ust+0.005
Okay+0.004
urious+0.004
Really+0.004
 rightful+0.004
Neg logit contributions
 on-0.003
 -0.003
hered-0.003
on-0.003
rell-0.003
Token repair
Token ID9185
Feature activation-1.25e-02

Pos logit contributions
hered+0.018
rell+0.017
hed+0.016
 +0.016
 crash+0.016
Neg logit contributions
ust-0.030
Really-0.024
urious-0.024
 rightful-0.024
Okay-0.023
Token your
Token ID534
Feature activation-1.08e-02

Pos logit contributions
ust+0.031
Really+0.026
 rightful+0.025
urious+0.025
Deal+0.025
Neg logit contributions
hered-0.016
rell-0.016
hed-0.015
iren-0.014
 -0.013
Token mask
Token ID9335
Feature activation+9.00e-03

Pos logit contributions
ust+0.028
 rightful+0.024
Really+0.023
 former+0.023
urious+0.023
Neg logit contributions
hered-0.013
rell-0.013
hed-0.012
on-0.011
 -0.011
Token.
Token ID13
Feature activation+4.17e-04

Pos logit contributions
hered+0.011
rell+0.011
hed+0.010
 on+0.010
on+0.010
Neg logit contributions
ust-0.023
Really-0.019
urious-0.019
 rightful-0.019
Okay-0.018
Token Come
Token ID7911
Feature activation+1.48e-02

Pos logit contributions
hered+0.001
rell+0.001
 +0.001
hed+0.001
on+0.000
Neg logit contributions
ust-0.001
urious-0.001
 rightful-0.001
 former-0.001
Really-0.001
Token on
Token ID319
Feature activation+8.11e-02

Pos logit contributions
rell+0.014
hed+0.012
hered+0.012
iren+0.011
ons+0.010
Neg logit contributions
ust-0.040
Really-0.035
Deal-0.034
Okay-0.034
 rightful-0.033
Token,
Token ID11
Feature activation-2.22e-02

Pos logit contributions
hed+0.105
rell+0.104
hered+0.096
quin+0.090
ged+0.082
Neg logit contributions
ust-0.182
 rightful-0.161
ara-0.157
Really-0.147
Deal-0.147
Token let
Token ID1309
Feature activation+3.87e-02

Pos logit contributions
ust+0.050
urious+0.041
 former+0.041
 rightful+0.039
Really+0.037
Neg logit contributions
 crash-0.037
hered-0.035
 gun-0.034
 on-0.034
 -0.034
Token's
Token ID338
Feature activation-3.03e-02

Pos logit contributions
hered+0.052
rell+0.050
hed+0.048
iren+0.046
 onwards+0.043
Neg logit contributions
ust-0.095
urious-0.077
 rightful-0.074
Okay-0.073
Really-0.073
Token go
Token ID467
Feature activation-5.29e-04

Pos logit contributions
ust+0.071
Really+0.057
urious+0.055
Okay+0.054
 rightful+0.054
Neg logit contributions
hered-0.045
rell-0.043
 on-0.042
 crash-0.042
hed-0.042
Token to
Token ID284
Feature activation-2.07e-03

Pos logit contributions
ust+0.001
Really+0.001
urious+0.001
 rightful+0.001
Okay+0.001
Neg logit contributions
hered-0.001
rell-0.001
hed-0.001
 -0.001
 on-0.001
Token.
Token ID13
Feature activation-9.42e-04

Pos logit contributions
ust+0.024
Really+0.019
 rightful+0.019
urious+0.019
Okay+0.019
Neg logit contributions
hered-0.013
rell-0.013
hed-0.012
on-0.012
 -0.011
Token
Token ID198
Feature activation+5.33e-03

Pos logit contributions
ust+0.003
 rightful+0.002
urious+0.002
Deal+0.002
 former+0.002
Neg logit contributions
 -0.001
on-0.001
rell-0.001
hered-0.001
 on-0.001
Token
Token ID198
Feature activation-9.23e-03

Pos logit contributions
hered+0.006
rell+0.006
 +0.006
hed+0.006
on+0.006
Neg logit contributions
ust-0.014
Really-0.012
 rightful-0.012
Deal-0.011
urious-0.011
Token"
Token ID1
Feature activation-3.88e-02

Pos logit contributions
ust+0.021
 rightful+0.017
 former+0.017
Really+0.016
urious+0.016
Neg logit contributions
hered-0.014
 -0.013
on-0.013
rell-0.013
hed-0.013
TokenCome
Token ID16773
Feature activation+2.80e-02

Pos logit contributions
ust+0.095
 rightful+0.076
 former+0.075
urious+0.073
asured+0.071
Neg logit contributions
hered-0.058
hed-0.054
on-0.047
iren-0.046
 -0.046
Token on
Token ID319
Feature activation+8.09e-02

Pos logit contributions
rell+0.027
hed+0.023
hered+0.021
iren+0.020
irens+0.020
Neg logit contributions
ust-0.076
Really-0.065
Deal-0.064
Okay-0.064
 rightful-0.063
Token,
Token ID11
Feature activation-1.29e-02

Pos logit contributions
rell+0.088
hed+0.087
hered+0.082
iren+0.072
quin+0.071
Neg logit contributions
ust-0.207
 rightful-0.176
ara-0.169
Really-0.166
ae-0.165
Token Mia
Token ID32189
Feature activation+7.43e-04

Pos logit contributions
ust+0.033
 former+0.028
urious+0.027
 rightful+0.027
Really+0.026
Neg logit contributions
 crash-0.017
 on-0.016
 gun-0.016
hered-0.016
 -0.015
Token!"
Token ID2474
Feature activation-9.66e-03

Pos logit contributions
hered+0.001
rell+0.001
hed+0.001
 +0.000
on+0.000
Neg logit contributions
ust-0.002
Really-0.002
 rightful-0.002
urious-0.002
Okay-0.002
Token Sam
Token ID3409
Feature activation+9.32e-03

Pos logit contributions
ust+0.021
Really+0.017
Okay+0.017
urious+0.017
Deal+0.016
Neg logit contributions
hered-0.015
rell-0.015
hed-0.014
iren-0.013
on-0.013
Token said
Token ID531
Feature activation+1.73e-03

Pos logit contributions
rell+0.015
hered+0.015
hed+0.014
on+0.013
iren+0.013
Neg logit contributions
ust-0.020
Okay-0.016
urious-0.015
Deal-0.015
Really-0.015
Token Lily
Token ID20037
Feature activation+3.83e-03

Pos logit contributions
ust+0.023
Really+0.020
Okay+0.019
Deal+0.019
ara+0.018
Neg logit contributions
rell-0.022
hered-0.021
hed-0.020
iren-0.020
opl-0.019
Token's
Token ID338
Feature activation-2.34e-02

Pos logit contributions
hered+0.005
rell+0.005
hed+0.004
iren+0.004
on+0.004
Neg logit contributions
ust-0.010
urious-0.008
Really-0.008
 rightful-0.008
Okay-0.008
Token friend
Token ID1545
Feature activation+5.01e-02

Pos logit contributions
ust+0.048
Really+0.036
 rightful+0.036
urious+0.035
Deal+0.035
Neg logit contributions
hered-0.041
rell-0.041
hed-0.039
 -0.038
on-0.038
Token called
Token ID1444
Feature activation+4.05e-02

Pos logit contributions
rell+0.059
hered+0.055
hed+0.055
iren+0.051
 falling+0.049
Neg logit contributions
ust-0.127
Okay-0.101
Really-0.101
ara-0.101
urious-0.101
Token her
Token ID607
Feature activation+2.55e-03

Pos logit contributions
hed+0.062
rell+0.061
hered+0.059
iren+0.056
on+0.054
Neg logit contributions
ust-0.088
 rightful-0.068
Really-0.067
urious-0.065
Deal-0.065
Token on
Token ID319
Feature activation+8.08e-02

Pos logit contributions
rell+0.004
hered+0.004
hed+0.004
iren+0.003
on+0.003
Neg logit contributions
ust-0.006
Really-0.005
 rightful-0.005
urious-0.005
Okay-0.005
Token the
Token ID262
Feature activation+3.05e-02

Pos logit contributions
hed+0.131
rell+0.126
hered+0.118
ched+0.108
on+0.107
Neg logit contributions
ust-0.167
 rightful-0.140
urious-0.134
 former-0.133
Really-0.133
Token phone
Token ID3072
Feature activation+1.92e-02

Pos logit contributions
hered+0.060
hed+0.059
rell+0.056
ez+0.055
med+0.055
Neg logit contributions
ust-0.054
 rightful-0.041
urious-0.041
Okay-0.040
Really-0.038
Token and
Token ID290
Feature activation+2.17e-02

Pos logit contributions
hered+0.024
rell+0.023
hed+0.023
on+0.020
 crash+0.020
Neg logit contributions
ust-0.047
urious-0.037
Okay-0.037
 rightful-0.037
Really-0.037
Token asked
Token ID1965
Feature activation+2.14e-02

Pos logit contributions
hered+0.030
rell+0.029
hed+0.028
 +0.027
 on+0.026
Neg logit contributions
ust-0.053
Really-0.042
urious-0.042
 rightful-0.042
Okay-0.041
Token if
Token ID611
Feature activation+1.29e-02

Pos logit contributions
hered+0.026
rell+0.026
hed+0.024
on+0.023
iren+0.022
Neg logit contributions
ust-0.055
Really-0.045
 rightful-0.044
urious-0.044
Okay-0.044
Token.
Token ID13
Feature activation+2.23e-02

Pos logit contributions
ust+0.026
Really+0.021
 rightful+0.021
urious+0.021
Okay+0.020
Neg logit contributions
hered-0.013
rell-0.013
hed-0.012
on-0.012
 -0.012
Token
Token ID198
Feature activation+1.07e-02

Pos logit contributions
hered+0.027
rell+0.027
hed+0.025
 +0.024
on+0.024
Neg logit contributions
ust-0.058
Really-0.046
 rightful-0.046
urious-0.046
Okay-0.045
Token
Token ID198
Feature activation-2.87e-03

Pos logit contributions
hered+0.013
rell+0.013
hed+0.012
 +0.012
on+0.012
Neg logit contributions
ust-0.028
Really-0.022
 rightful-0.022
urious-0.022
Okay-0.022
Token"
Token ID1
Feature activation-2.86e-02

Pos logit contributions
ust+0.006
 rightful+0.005
Really+0.005
 former+0.005
urious+0.005
Neg logit contributions
hered-0.005
rell-0.005
hed-0.005
 -0.004
on-0.004
TokenCome
Token ID16773
Feature activation+3.06e-02

Pos logit contributions
ust+0.064
 rightful+0.051
 former+0.051
urious+0.050
Deal+0.047
Neg logit contributions
hered-0.046
hed-0.043
 on-0.041
rell-0.040
 -0.039
Token on
Token ID319
Feature activation+8.06e-02

Pos logit contributions
rell+0.029
hed+0.025
hered+0.022
iren+0.021
ons+0.021
Neg logit contributions
ust-0.084
Really-0.071
Deal-0.070
Okay-0.070
 rightful-0.069
Token,
Token ID11
Feature activation-5.45e-03

Pos logit contributions
rell+0.086
hed+0.083
hered+0.081
iren+0.071
on+0.070
Neg logit contributions
ust-0.208
 rightful-0.175
ara-0.168
 former-0.168
Really-0.165
Token Lily
Token ID20037
Feature activation+7.01e-03

Pos logit contributions
ust+0.014
urious+0.012
 former+0.012
 rightful+0.011
Really+0.011
Neg logit contributions
 crash-0.007
 on-0.007
hered-0.007
 -0.006
rell-0.006
Token!"
Token ID2474
Feature activation-3.07e-03

Pos logit contributions
hered+0.008
rell+0.008
hed+0.008
on+0.007
 +0.007
Neg logit contributions
ust-0.018
Really-0.015
 rightful-0.015
urious-0.015
Okay-0.014
Token Tom
Token ID4186
Feature activation+1.08e-02

Pos logit contributions
ust+0.006
Okay+0.005
Really+0.005
Deal+0.005
urious+0.005
Neg logit contributions
rell-0.005
hered-0.005
hed-0.005
iren-0.005
on-0.005
Token said
Token ID531
Feature activation+9.57e-03

Pos logit contributions
rell+0.015
hered+0.015
hed+0.014
on+0.014
iren+0.014
Neg logit contributions
ust-0.025
Okay-0.020
urious-0.020
Deal-0.019
Really-0.019
Token.
Token ID13
Feature activation+8.79e-03

Pos logit contributions
hered+0.009
rell+0.009
hed+0.008
iren+0.008
on+0.008
Neg logit contributions
ust-0.033
Really-0.027
 rightful-0.027
urious-0.027
Okay-0.027
Token
Token ID198
Feature activation+1.06e-02

Pos logit contributions
 +0.011
hered+0.010
 on+0.010
hed+0.010
rell+0.009
Neg logit contributions
ust-0.024
 rightful-0.020
urious-0.019
 former-0.019
asured-0.018
Token
Token ID198
Feature activation-4.52e-03

Pos logit contributions
hered+0.012
rell+0.011
 +0.011
hed+0.011
on+0.011
Neg logit contributions
ust-0.028
 rightful-0.023
Really-0.023
 former-0.023
urious-0.023
Token"
Token ID1
Feature activation-3.72e-02

Pos logit contributions
ust+0.009
 rightful+0.007
Really+0.007
urious+0.007
 former+0.007
Neg logit contributions
hered-0.008
rell-0.008
hed-0.008
 -0.007
on-0.007
TokenCome
Token ID16773
Feature activation+3.15e-02

Pos logit contributions
ust+0.081
 rightful+0.062
 former+0.061
urious+0.060
asured+0.056
Neg logit contributions
hered-0.067
hed-0.063
rell-0.059
 on-0.057
 -0.056
Token on
Token ID319
Feature activation+8.06e-02

Pos logit contributions
rell+0.031
hed+0.025
hered+0.022
iren+0.022
irens+0.021
Neg logit contributions
ust-0.084
Really-0.072
Deal-0.072
ara-0.071
Okay-0.071
Token,
Token ID11
Feature activation-1.00e-02

Pos logit contributions
hed+0.092
rell+0.091
hered+0.083
quin+0.076
iren+0.072
Neg logit contributions
ust-0.200
 rightful-0.169
ara-0.167
ae-0.161
Really-0.158
Token Ben
Token ID3932
Feature activation+1.82e-02

Pos logit contributions
ust+0.026
 former+0.022
urious+0.022
 rightful+0.021
Really+0.021
Neg logit contributions
hered-0.013
 on-0.012
 crash-0.012
rell-0.012
 -0.011
Token,
Token ID11
Feature activation-2.07e-02

Pos logit contributions
rell+0.016
hered+0.016
hed+0.014
iren+0.013
on+0.013
Neg logit contributions
ust-0.053
 rightful-0.044
Really-0.044
urious-0.044
Okay-0.043
Token it
Token ID340
Feature activation+5.69e-03

Pos logit contributions
ust+0.045
 former+0.037
 rightful+0.037
urious+0.037
Really+0.035
Neg logit contributions
hered-0.034
 on-0.034
 crash-0.033
on-0.032
 -0.032
Token's
Token ID338
Feature activation-9.88e-03

Pos logit contributions
hered+0.006
rell+0.006
hed+0.006
 +0.005
on+0.005
Neg logit contributions
ust-0.015
Really-0.013
 rightful-0.013
urious-0.012
 former-0.012
Token.
Token ID13
Feature activation+8.36e-03

Pos logit contributions
hered+0.004
rell+0.004
hed+0.004
 +0.004
 on+0.004
Neg logit contributions
ust-0.009
Really-0.007
 rightful-0.007
urious-0.007
 former-0.007
Token
Token ID198
Feature activation+4.33e-03

Pos logit contributions
 +0.009
hered+0.007
rell+0.007
 on+0.007
hed+0.007
Neg logit contributions
ust-0.024
 rightful-0.020
 former-0.020
urious-0.019
asured-0.019
Token
Token ID198
Feature activation-8.17e-03

Pos logit contributions
 +0.005
hered+0.004
rell+0.004
hed+0.004
on+0.004
Neg logit contributions
ust-0.012
 rightful-0.010
 former-0.010
Really-0.010
Deal-0.010
Token"
Token ID1
Feature activation-3.63e-02

Pos logit contributions
ust+0.020
 former+0.017
 rightful+0.017
Really+0.016
urious+0.016
Neg logit contributions
hered-0.011
 -0.010
rell-0.010
 on-0.010
hed-0.010
TokenCome
Token ID16773
Feature activation+2.71e-02

Pos logit contributions
ust+0.080
 former+0.065
 rightful+0.063
urious+0.061
asured+0.060
Neg logit contributions
hered-0.060
hed-0.054
 -0.053
 on-0.053
rell-0.052
Token on
Token ID319
Feature activation+8.05e-02

Pos logit contributions
rell+0.020
hed+0.016
hered+0.014
iren+0.013
ons+0.012
Neg logit contributions
ust-0.080
Deal-0.069
Really-0.069
Okay-0.067
ara-0.067
Token,
Token ID11
Feature activation-8.16e-03

Pos logit contributions
rell+0.084
hed+0.084
hered+0.078
iren+0.070
quin+0.068
Neg logit contributions
ust-0.207
ara-0.175
 rightful-0.175
ae-0.169
gan-0.167
Token Lily
Token ID20037
Feature activation+1.12e-02

Pos logit contributions
ust+0.020
 former+0.018
urious+0.018
 rightful+0.017
Really+0.017
Neg logit contributions
 on-0.010
 -0.010
 crash-0.010
hered-0.010
rell-0.009
Token,
Token ID11
Feature activation-1.64e-02

Pos logit contributions
hered+0.009
rell+0.009
hed+0.008
on+0.007
 +0.007
Neg logit contributions
ust-0.034
Really-0.028
 rightful-0.028
urious-0.028
Okay-0.028
Token it
Token ID340
Feature activation+8.45e-03

Pos logit contributions
ust+0.036
 former+0.032
 rightful+0.031
urious+0.030
Really+0.029
Neg logit contributions
 on-0.027
 crash-0.026
hered-0.026
 -0.025
 out-0.024
Token's
Token ID338
Feature activation-1.05e-02

Pos logit contributions
rell+0.008
hered+0.007
hed+0.007
 +0.007
 on+0.006
Neg logit contributions
ust-0.024
Really-0.021
 rightful-0.021
 former-0.020
Okay-0.020
Token.
Token ID13
Feature activation+1.50e-02

Pos logit contributions
ust+0.023
Really+0.019
urious+0.019
 rightful+0.019
Okay+0.018
Neg logit contributions
hered-0.011
rell-0.011
hed-0.011
 on-0.010
 -0.010
Token
Token ID198
Feature activation+8.87e-03

Pos logit contributions
hered+0.018
rell+0.017
hed+0.016
 +0.016
on+0.015
Neg logit contributions
ust-0.040
 rightful-0.032
urious-0.032
Really-0.032
Deal-0.031
Token
Token ID198
Feature activation-5.04e-03

Pos logit contributions
hered+0.011
rell+0.010
hed+0.010
 +0.010
on+0.009
Neg logit contributions
ust-0.023
Really-0.019
 rightful-0.019
urious-0.018
Deal-0.018
Token"
Token ID1
Feature activation-3.07e-02

Pos logit contributions
ust+0.011
 rightful+0.008
Really+0.008
urious+0.008
 former+0.008
Neg logit contributions
hered-0.008
rell-0.008
hed-0.008
 -0.008
on-0.008
TokenCome
Token ID16773
Feature activation+3.23e-02

Pos logit contributions
ust+0.069
 rightful+0.054
 former+0.054
urious+0.053
Deal+0.050
Neg logit contributions
hered-0.051
hed-0.047
rell-0.045
 on-0.044
iren-0.043
Token on
Token ID319
Feature activation+8.05e-02

Pos logit contributions
rell+0.031
hed+0.026
iren+0.022
hered+0.022
ons+0.022
Neg logit contributions
ust-0.087
Really-0.074
Deal-0.074
ara-0.073
Okay-0.073
Token,
Token ID11
Feature activation-6.81e-03

Pos logit contributions
rell+0.087
hed+0.085
hered+0.079
quin+0.073
iren+0.070
Neg logit contributions
ust-0.204
 rightful-0.173
ara-0.170
ae-0.164
 former-0.162
Token Lily
Token ID20037
Feature activation+1.21e-02

Pos logit contributions
ust+0.018
urious+0.015
 former+0.015
 rightful+0.014
Really+0.014
Neg logit contributions
hered-0.008
 crash-0.008
 on-0.008
rell-0.008
 -0.008
Token!"
Token ID2474
Feature activation-6.22e-03

Pos logit contributions
hered+0.011
rell+0.011
hed+0.010
iren+0.009
on+0.009
Neg logit contributions
ust-0.035
Really-0.029
 rightful-0.029
urious-0.028
Okay-0.028
Token Tom
Token ID4186
Feature activation+1.43e-02

Pos logit contributions
ust+0.012
Really+0.010
Okay+0.010
Deal+0.009
urious+0.009
Neg logit contributions
rell-0.011
hered-0.011
hed-0.010
iren-0.010
on-0.010
Token said
Token ID531
Feature activation+6.95e-03

Pos logit contributions
rell+0.021
hered+0.021
hed+0.020
on+0.019
iren+0.019
Neg logit contributions
ust-0.033
Okay-0.025
urious-0.025
Deal-0.025
Really-0.025
Token.
Token ID13
Feature activation+1.34e-02

Pos logit contributions
hered+0.005
rell+0.005
hed+0.005
on+0.004
 +0.004
Neg logit contributions
ust-0.009
Really-0.007
urious-0.007
 rightful-0.007
Okay-0.007
Token
Token ID198
Feature activation+7.60e-03

Pos logit contributions
hered+0.016
 +0.016
rell+0.016
hed+0.015
iren+0.015
Neg logit contributions
ust-0.035
urious-0.028
 rightful-0.028
Deal-0.027
 former-0.027
Token
Token ID198
Feature activation-4.85e-03

Pos logit contributions
hered+0.009
rell+0.008
 +0.008
hed+0.008
on+0.008
Neg logit contributions
ust-0.020
Really-0.016
 rightful-0.016
urious-0.016
Deal-0.016
Token"
Token ID1
Feature activation-3.73e-02

Pos logit contributions
ust+0.010
 rightful+0.008
 former+0.008
Really+0.008
urious+0.008
Neg logit contributions
hered-0.008
rell-0.008
hed-0.008
 -0.008
iren-0.008
TokenCome
Token ID16773
Feature activation+3.11e-02

Pos logit contributions
ust+0.083
 rightful+0.065
 former+0.065
urious+0.063
Deal+0.060
Neg logit contributions
hered-0.061
hed-0.055
iren-0.054
 on-0.054
 crash-0.053
Token on
Token ID319
Feature activation+8.04e-02

Pos logit contributions
rell+0.031
hed+0.027
iren+0.023
ons+0.023
hered+0.022
Neg logit contributions
ust-0.083
Really-0.071
Deal-0.071
Okay-0.069
ara-0.069
Token,
Token ID11
Feature activation-8.91e-03

Pos logit contributions
rell+0.089
hed+0.088
hered+0.080
quin+0.073
iren+0.069
Neg logit contributions
ust-0.204
 rightful-0.175
ara-0.169
ae-0.164
Really-0.162
Token Lily
Token ID20037
Feature activation+9.50e-03

Pos logit contributions
ust+0.024
 former+0.021
urious+0.021
 rightful+0.020
Really+0.020
Neg logit contributions
 crash-0.010
hered-0.010
 on-0.010
 gun-0.009
 -0.009
Token!"
Token ID2474
Feature activation-3.48e-03

Pos logit contributions
rell+0.010
hered+0.010
hed+0.009
iren+0.008
on+0.008
Neg logit contributions
ust-0.026
 rightful-0.021
urious-0.021
Deal-0.021
Okay-0.021
Token he
Token ID339
Feature activation-1.37e-02

Pos logit contributions
ust+0.007
Really+0.005
Okay+0.005
Deal+0.005
 rightful+0.005
Neg logit contributions
hered-0.006
rell-0.006
hed-0.006
on-0.006
iren-0.005
Token said
Token ID531
Feature activation+4.85e-03

Pos logit contributions
ust+0.032
Really+0.025
urious+0.025
Okay+0.025
 rightful+0.025
Neg logit contributions
hered-0.020
rell-0.020
hed-0.019
on-0.018
iren-0.018
Token to
Token ID284
Feature activation+1.66e-02

Pos logit contributions
hered+0.016
rell+0.016
hed+0.016
on+0.015
 +0.015
Neg logit contributions
ust-0.021
 rightful-0.016
 former-0.016
urious-0.016
Okay-0.015
Token help
Token ID1037
Feature activation+4.10e-04

Pos logit contributions
hered+0.026
rell+0.025
 crash+0.024
 +0.023
 on+0.023
Neg logit contributions
ust-0.038
Really-0.031
urious-0.030
Deal-0.030
Okay-0.029
Token you
Token ID345
Feature activation+7.50e-03

Pos logit contributions
hered+0.001
 on+0.001
rell+0.001
 +0.000
 crash+0.000
Neg logit contributions
ust-0.001
Really-0.001
Deal-0.001
 former-0.001
Okay-0.001
Token.
Token ID13
Feature activation-2.76e-03

Pos logit contributions
hered+0.011
rell+0.011
hed+0.010
on+0.010
 +0.010
Neg logit contributions
ust-0.018
Really-0.014
 rightful-0.014
urious-0.014
Okay-0.014
Token Come
Token ID7911
Feature activation+1.44e-02

Pos logit contributions
ust+0.006
Really+0.005
 rightful+0.005
Okay+0.005
urious+0.005
Neg logit contributions
hered-0.004
rell-0.004
hed-0.004
on-0.004
 crash-0.004
Token on
Token ID319
Feature activation+8.03e-02

Pos logit contributions
rell+0.016
hed+0.013
hered+0.013
on+0.012
iren+0.012
Neg logit contributions
ust-0.038
Really-0.032
Deal-0.032
Okay-0.032
 rightful-0.032
Token,
Token ID11
Feature activation-1.52e-02

Pos logit contributions
hed+0.096
rell+0.094
hered+0.088
quin+0.081
iren+0.079
Neg logit contributions
ust-0.193
 rightful-0.168
ara-0.162
 former-0.158
eter-0.155
Token let
Token ID1309
Feature activation+3.90e-02

Pos logit contributions
ust+0.034
urious+0.027
 former+0.026
 rightful+0.026
Really+0.026
Neg logit contributions
hered-0.025
 crash-0.024
 on-0.024
 -0.024
rell-0.023
Token's
Token ID338
Feature activation-3.42e-02

Pos logit contributions
hered+0.045
rell+0.043
hed+0.041
iren+0.039
 crash+0.037
Neg logit contributions
ust-0.103
urious-0.084
 rightful-0.081
Okay-0.080
Really-0.080
Token go
Token ID467
Feature activation-1.46e-03

Pos logit contributions
ust+0.077
Really+0.061
urious+0.059
 rightful+0.059
Okay+0.058
Neg logit contributions
hered-0.053
rell-0.052
hed-0.050
 -0.049
 on-0.048
Token inside
Token ID2641
Feature activation-2.04e-02

Pos logit contributions
ust+0.004
Really+0.003
 rightful+0.003
urious+0.003
Okay+0.003
Neg logit contributions
hered-0.002
rell-0.002
hed-0.002
 -0.002
on-0.002
Token knew
Token ID2993
Feature activation-3.30e-02

Pos logit contributions
hered+0.018
rell+0.018
hed+0.017
on+0.016
iren+0.016
Neg logit contributions
ust-0.027
Really-0.020
 rightful-0.020
urious-0.020
Okay-0.020
Token to
Token ID284
Feature activation-7.78e-03

Pos logit contributions
ust+0.093
urious+0.079
Really+0.079
Okay+0.078
Deal+0.077
Neg logit contributions
 on-0.033
 -0.029
hered-0.029
 gun-0.028
 falling-0.027
Token be
Token ID307
Feature activation-5.65e-03

Pos logit contributions
ust+0.018
Really+0.015
urious+0.014
Okay+0.013
ara+0.013
Neg logit contributions
 crash-0.011
 -0.011
 on-0.011
hered-0.011
rell-0.011
Token careful
Token ID8161
Feature activation-2.46e-02

Pos logit contributions
ust+0.013
Really+0.010
urious+0.010
 rightful+0.010
Okay+0.010
Neg logit contributions
hered-0.009
rell-0.009
hed-0.008
 on-0.008
 -0.008
Token around
Token ID1088
Feature activation+1.88e-02

Pos logit contributions
ust+0.057
urious+0.044
 rightful+0.043
Really+0.043
Okay+0.043
Neg logit contributions
hered-0.037
rell-0.037
hed-0.034
iren-0.033
on-0.032
Token volcan
Token ID17516
Feature activation-1.01e-01

Pos logit contributions
hered+0.017
rell+0.016
hed+0.015
 on+0.015
on+0.014
Neg logit contributions
ust-0.055
Really-0.046
Okay-0.045
 rightful-0.045
urious-0.045
Tokenoes
Token ID3028
Feature activation-9.83e-03

Pos logit contributions
ust+0.173
Really+0.158
 rightful+0.145
Okay+0.143
Deal+0.136
Neg logit contributions
rell-0.203
hered-0.188
hed-0.185
 on-0.182
iren-0.180
Token.
Token ID13
Feature activation+3.65e-03

Pos logit contributions
ust+0.026
Really+0.022
 rightful+0.021
urious+0.021
Okay+0.021
Neg logit contributions
hered-0.011
rell-0.011
hed-0.010
 on-0.010
 -0.010
Token<|endoftext|>
Token ID50256
Feature activation+2.86e-02

Pos logit contributions
hered+0.004
rell+0.004
hed+0.004
 +0.004
on+0.004
Neg logit contributions
ust-0.009
Really-0.008
 rightful-0.008
urious-0.007
Okay-0.007
TokenOnce
Token ID7454
Feature activation-1.73e-02

Pos logit contributions
rell+0.043
hered+0.043
 gun+0.039
 crash+0.039
hed+0.039
Neg logit contributions
ust-0.062
Really-0.049
urious-0.048
Okay-0.048
 rightful-0.048
Token upon
Token ID2402
Feature activation-1.75e-02

Pos logit contributions
ust+0.031
urious+0.022
Really+0.022
 rightful+0.022
Okay+0.021
Neg logit contributions
hered-0.035
rell-0.034
hed-0.033
iren-0.032
on-0.032
Token was
Token ID373
Feature activation-1.58e-02

Pos logit contributions
hered+0.013
hed+0.013
 +0.013
rell+0.013
 on+0.012
Neg logit contributions
ust-0.027
Really-0.022
 rightful-0.022
Deal-0.022
 former-0.022
Token a
Token ID257
Feature activation-2.60e-02

Pos logit contributions
ust+0.047
Really+0.039
urious+0.039
 rightful+0.038
Okay+0.038
Neg logit contributions
hered-0.013
rell-0.013
hed-0.011
 -0.011
 on-0.011
Token grand
Token ID4490
Feature activation+1.30e-03

Pos logit contributions
ust+0.060
Really+0.046
urious+0.046
 rightful+0.046
Okay+0.045
Neg logit contributions
hered-0.039
rell-0.038
hed-0.036
 -0.035
on-0.035
Token door
Token ID3420
Feature activation-1.38e-02

Pos logit contributions
rell+0.002
hered+0.002
on+0.002
hed+0.002
 crash+0.002
Neg logit contributions
ust-0.003
Really-0.002
Okay-0.002
urious-0.002
Deal-0.002
Token.
Token ID13
Feature activation+4.21e-03

Pos logit contributions
ust+0.034
Really+0.027
 rightful+0.027
urious+0.026
Okay+0.026
Neg logit contributions
hered-0.019
rell-0.018
hed-0.017
 -0.016
on-0.016
Token Bes
Token ID30837
Feature activation-9.93e-02

Pos logit contributions
 +0.006
rell+0.005
hered+0.005
hed+0.005
 on+0.005
Neg logit contributions
ust-0.011
Deal-0.009
 rightful-0.009
Okay-0.008
Really-0.008
Tokenide
Token ID485
Feature activation-5.07e-02

Pos logit contributions
ust+0.128
Deal+0.125
Really+0.122
Okay+0.111
 rightful+0.104
Neg logit contributions
rell-0.231
hed-0.211
hered-0.208
iren-0.204
 -0.201
Token the
Token ID262
Feature activation+2.25e-02

Pos logit contributions
ust+0.119
Really+0.101
Okay+0.098
 rightful+0.097
Deal+0.097
Neg logit contributions
 on-0.072
rell-0.072
hed-0.070
hered-0.070
on-0.067
Token door
Token ID3420
Feature activation-1.50e-03

Pos logit contributions
 on+0.027
hered+0.027
rell+0.027
 +0.025
 photos+0.025
Neg logit contributions
ust-0.057
Really-0.047
Deal-0.045
Okay-0.044
urious-0.044
Token,
Token ID11
Feature activation-2.16e-02

Pos logit contributions
ust+0.004
Really+0.004
 former+0.003
Okay+0.003
Deal+0.003
Neg logit contributions
 on-0.002
 -0.002
rell-0.001
hed-0.001
on-0.001
Token there
Token ID612
Feature activation+1.42e-02

Pos logit contributions
ust+0.059
 rightful+0.049
urious+0.048
Deal+0.048
Okay+0.048
Neg logit contributions
 on-0.023
 -0.023
hered-0.022
rell-0.021
hed-0.021
Token he
Token ID339
Feature activation-1.62e-02

Pos logit contributions
ust+0.031
urious+0.025
 rightful+0.024
Really+0.024
 former+0.024
Neg logit contributions
 -0.012
hered-0.012
rell-0.012
on-0.012
hed-0.012
Token replied
Token ID8712
Feature activation+6.38e-03

Pos logit contributions
ust+0.040
Really+0.032
 rightful+0.032
 former+0.032
urious+0.032
Neg logit contributions
hered-0.022
rell-0.021
 -0.020
hed-0.020
 on-0.019
Token.
Token ID13
Feature activation-1.23e-03

Pos logit contributions
rell+0.010
hered+0.010
hed+0.009
iren+0.009
 crash+0.008
Neg logit contributions
ust-0.014
 rightful-0.011
Really-0.011
urious-0.011
Okay-0.011
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
ust+0.003
urious+0.003
 rightful+0.003
Deal+0.003
Really+0.003
Neg logit contributions
hered-0.001
 -0.001
rell-0.001
hed-0.001
on-0.001
Token
Token ID198
Feature activation-1.96e-02

Pos logit contributions
ust+0.029
 rightful+0.024
Deal+0.023
urious+0.023
Really+0.023
Neg logit contributions
 -0.011
hered-0.010
rell-0.009
on-0.009
hed-0.009
TokenFr
Token ID6732
Feature activation-9.91e-02

Pos logit contributions
ust+0.041
 rightful+0.033
Deal+0.032
urious+0.031
 former+0.031
Neg logit contributions
 -0.032
hered-0.031
on-0.029
 on-0.029
rell-0.028
Tokenanny
Token ID7737
Feature activation+5.30e-03

Pos logit contributions
Really+0.183
Okay+0.154
Deal+0.152
 rightful+0.152
ust+0.141
Neg logit contributions
rell-0.154
ons-0.141
on-0.140
iren-0.139
irens-0.131
Token carefully
Token ID7773
Feature activation+1.07e-02

Pos logit contributions
hered+0.007
hed+0.007
rell+0.007
on+0.006
 +0.006
Neg logit contributions
ust-0.013
Really-0.011
 rightful-0.011
 former-0.010
urious-0.010
Token helped
Token ID4193
Feature activation-1.87e-02

Pos logit contributions
hered+0.017
rell+0.017
hed+0.016
 +0.015
 crash+0.015
Neg logit contributions
ust-0.023
Really-0.018
urious-0.018
 rightful-0.018
Okay-0.017
Token her
Token ID607
Feature activation-3.64e-02

Pos logit contributions
ust+0.051
Really+0.042
 rightful+0.041
urious+0.041
Deal+0.041
Neg logit contributions
hered-0.021
rell-0.020
hed-0.019
 -0.018
on-0.018
Token dad
Token ID9955
Feature activation-8.67e-03

Pos logit contributions
ust+0.072
Really+0.054
 rightful+0.053
Okay+0.052
urious+0.052
Neg logit contributions
hered-0.067
rell-0.066
hed-0.064
 -0.062
 on-0.062
Token to
Token ID284
Feature activation-1.13e-02

Pos logit contributions
ust+0.038
Really+0.031
urious+0.030
 rightful+0.030
Okay+0.030
Neg logit contributions
hered-0.022
rell-0.021
hed-0.021
 -0.020
 on-0.020
Token enjoy
Token ID2883
Feature activation+1.93e-03

Pos logit contributions
ust+0.027
Really+0.021
urious+0.021
Okay+0.020
Deal+0.020
Neg logit contributions
hered-0.017
 crash-0.016
 -0.016
on-0.016
rell-0.015
Token."
Token ID526
Feature activation-7.34e-03

Pos logit contributions
hered+0.002
rell+0.002
hed+0.002
 on+0.002
 +0.002
Neg logit contributions
ust-0.005
Really-0.004
urious-0.004
Okay-0.004
 rightful-0.004
Token
Token ID220
Feature activation-1.22e-02

Pos logit contributions
ust+0.020
 rightful+0.016
Really+0.016
urious+0.016
Deal+0.016
Neg logit contributions
hered-0.008
rell-0.008
hed-0.007
 -0.007
on-0.007
Token
Token ID198
Feature activation-6.09e-03

Pos logit contributions
ust+0.033
Really+0.028
 rightful+0.027
Deal+0.027
Okay+0.027
Neg logit contributions
rell-0.013
hered-0.013
 -0.013
hed-0.012
on-0.012
TokenFr
Token ID6732
Feature activation-9.81e-02

Pos logit contributions
ust+0.017
 rightful+0.014
urious+0.014
Deal+0.013
Really+0.013
Neg logit contributions
hered-0.007
 -0.007
rell-0.006
hed-0.006
on-0.006
Tokenanny
Token ID7737
Feature activation-3.99e-03

Pos logit contributions
Really+0.173
 rightful+0.153
Deal+0.152
Okay+0.145
ust+0.144
Neg logit contributions
rell-0.156
on-0.146
iren-0.141
ons-0.141
hed-0.139
Token was
Token ID373
Feature activation-7.24e-03

Pos logit contributions
ust+0.011
Really+0.009
 rightful+0.009
 former+0.008
urious+0.008
Neg logit contributions
hered-0.005
hed-0.005
rell-0.004
on-0.004
 -0.004
Token no
Token ID645
Feature activation-2.19e-02

Pos logit contributions
ust+0.019
 rightful+0.015
Really+0.015
urious+0.014
 former+0.014
Neg logit contributions
rell-0.009
hered-0.009
hed-0.009
iren-0.008
 gun-0.008
Token longer
Token ID2392
Feature activation-2.82e-03

Pos logit contributions
ust+0.048
Really+0.039
urious+0.037
 rightful+0.037
Deal+0.037
Neg logit contributions
hered-0.035
rell-0.032
 on-0.031
hed-0.031
 -0.030
Token confused
Token ID10416
Feature activation-1.94e-02

Pos logit contributions
ust+0.007
 rightful+0.006
urious+0.006
 former+0.006
Really+0.006
Neg logit contributions
rell-0.003
hered-0.003
hed-0.003
iren-0.003
on-0.003
Token't
Token ID470
Feature activation+8.64e-03

Pos logit contributions
hered+0.011
rell+0.011
hed+0.010
lers+0.009
 gun+0.009
Neg logit contributions
ust-0.035
urious-0.027
Years-0.027
 rightful-0.027
Really-0.026
Token know
Token ID760
Feature activation-1.26e-02

Pos logit contributions
hered+0.015
rell+0.014
hed+0.014
 +0.013
 on+0.013
Neg logit contributions
ust-0.018
Really-0.014
urious-0.014
 rightful-0.014
Okay-0.014
Token.
Token ID13
Feature activation+1.35e-02

Pos logit contributions
ust+0.028
Really+0.022
 rightful+0.022
urious+0.021
Okay+0.021
Neg logit contributions
hered-0.020
rell-0.019
hed-0.019
on-0.018
 -0.018
Token
Token ID198
Feature activation+2.61e-04

Pos logit contributions
hered+0.013
rell+0.013
 +0.013
hed+0.013
on+0.012
Neg logit contributions
ust-0.038
 rightful-0.031
Really-0.030
 former-0.030
Okay-0.030
Token
Token ID198
Feature activation-1.22e-02

Pos logit contributions
hered+0.000
rell+0.000
hed+0.000
 +0.000
on+0.000
Neg logit contributions
ust-0.001
Really-0.001
 rightful-0.001
urious-0.001
Okay-0.001
TokenLuc
Token ID22946
Feature activation-9.50e-02

Pos logit contributions
ust+0.025
 rightful+0.020
Really+0.020
 former+0.019
Deal+0.019
Neg logit contributions
hered-0.021
rell-0.020
hed-0.020
 -0.019
on-0.019
Tokenas
Token ID292
Feature activation+3.26e-02

Pos logit contributions
Really+0.147
Okay+0.140
Deal+0.133
 rightful+0.133
ust+0.129
Neg logit contributions
on-0.183
ons-0.180
igh-0.176
 on-0.173
lers-0.171
Token started
Token ID2067
Feature activation-1.71e-03

Pos logit contributions
hered+0.047
rell+0.046
hed+0.044
 +0.041
on+0.041
Neg logit contributions
ust-0.077
Really-0.061
 rightful-0.061
urious-0.060
Okay-0.060
Token to
Token ID284
Feature activation-1.32e-02

Pos logit contributions
ust+0.003
urious+0.003
 rightful+0.003
 former+0.003
Really+0.002
Neg logit contributions
rell-0.003
hered-0.003
hed-0.003
on-0.003
iren-0.003
Token complain
Token ID13121
Feature activation-9.74e-03

Pos logit contributions
ust+0.033
Really+0.026
 rightful+0.026
urious+0.026
Okay+0.026
Neg logit contributions
hered-0.017
rell-0.017
hed-0.016
on-0.015
 -0.015
Token "
Token ID366
Feature activation-2.92e-02

Pos logit contributions
ust+0.026
Really+0.022
 rightful+0.022
urious+0.022
Deal+0.022
Neg logit contributions
hered-0.010
rell-0.010
 on-0.010
hed-0.010
 -0.009
Token it
Token ID340
Feature activation+1.83e-02

Pos logit contributions
ust+0.015
 rightful+0.012
Really+0.012
urious+0.012
Okay+0.012
Neg logit contributions
hered-0.007
rell-0.007
hed-0.006
iren-0.006
 crash-0.006
Token back
Token ID736
Feature activation-1.06e-02

Pos logit contributions
hered+0.022
rell+0.022
hed+0.021
iren+0.020
on+0.020
Neg logit contributions
ust-0.048
 rightful-0.038
urious-0.037
Okay-0.036
Deal-0.036
Token.
Token ID13
Feature activation+8.33e-03

Pos logit contributions
ust+0.028
Really+0.023
urious+0.023
Okay+0.022
 rightful+0.022
Neg logit contributions
hered-0.012
rell-0.011
 on-0.011
hed-0.011
 -0.011
Token
Token ID198
Feature activation-2.94e-03

Pos logit contributions
 +0.009
hered+0.008
rell+0.008
hed+0.008
on+0.007
Neg logit contributions
ust-0.024
 rightful-0.019
urious-0.019
Really-0.019
 former-0.019
Token
Token ID198
Feature activation-1.35e-02

Pos logit contributions
ust+0.008
 rightful+0.006
Really+0.006
urious+0.006
 former+0.006
Neg logit contributions
hered-0.003
rell-0.003
 -0.003
hed-0.003
on-0.003
TokenFr
Token ID6732
Feature activation-9.46e-02

Pos logit contributions
ust+0.028
 rightful+0.023
 former+0.022
Really+0.021
eter+0.021
Neg logit contributions
 -0.021
hered-0.021
hed-0.021
on-0.020
rell-0.019
Tokenust
Token ID436
Feature activation-8.13e-02

Pos logit contributions
Really+0.062
 rightful+0.034
igor+0.026
Okay+0.022
Deal+0.018
Neg logit contributions
rell-0.249
ons-0.234
hed-0.232
iren-0.231
hered-0.231
Tokenrated
Token ID4111
Feature activation+2.37e-02

Pos logit contributions
ust+0.152
Really+0.129
Deal+0.122
 rightful+0.121
 former+0.120
Neg logit contributions
 on-0.137
hered-0.133
hed-0.131
rell-0.129
 crash-0.125
Token,
Token ID11
Feature activation-1.60e-02

Pos logit contributions
rell+0.019
hered+0.018
on+0.016
hed+0.016
iren+0.016
Neg logit contributions
ust-0.069
urious-0.057
Really-0.057
Okay-0.057
 rightful-0.056
Token Jane
Token ID12091
Feature activation-1.27e-02

Pos logit contributions
ust+0.039
urious+0.030
 rightful+0.030
Really+0.030
Okay+0.029
Neg logit contributions
hered-0.022
rell-0.021
 -0.021
hed-0.021
 on-0.021
Token went
Token ID1816
Feature activation+1.28e-03

Pos logit contributions
ust+0.031
Really+0.024
 rightful+0.024
urious+0.024
Okay+0.024
Neg logit contributions
hered-0.018
rell-0.017
hed-0.016
on-0.015
 -0.015
Token a
Token ID257
Feature activation-1.32e-02

Pos logit contributions
hered+0.004
rell+0.004
hed+0.004
iren+0.004
on+0.004
Neg logit contributions
ust-0.006
 rightful-0.005
Really-0.005
urious-0.005
Okay-0.005
Token nice
Token ID3621
Feature activation-1.70e-02

Pos logit contributions
ust+0.025
Really+0.019
 rightful+0.019
 former+0.018
Okay+0.018
Neg logit contributions
rell-0.024
hed-0.024
hered-0.024
irens-0.023
iren-0.022
Token home
Token ID1363
Feature activation-3.49e-02

Pos logit contributions
ust+0.036
 rightful+0.028
Really+0.028
Okay+0.027
urious+0.027
Neg logit contributions
hered-0.028
rell-0.028
hed-0.027
iren-0.025
on-0.025
Token in
Token ID287
Feature activation+5.65e-03

Pos logit contributions
ust+0.085
 rightful+0.067
Really+0.067
urious+0.066
Deal+0.066
Neg logit contributions
hered-0.047
rell-0.047
hed-0.044
 -0.041
iren-0.041
Token a
Token ID257
Feature activation-2.63e-02

Pos logit contributions
hered+0.006
rell+0.006
hed+0.005
on+0.005
iren+0.005
Neg logit contributions
ust-0.016
Really-0.013
 rightful-0.013
urious-0.013
Okay-0.012
Token terr
Token ID8812
Feature activation-9.35e-02

Pos logit contributions
ust+0.060
Really+0.047
 rightful+0.046
urious+0.046
Okay+0.046
Neg logit contributions
hered-0.040
rell-0.040
hed-0.038
on-0.036
 -0.036
Tokenarium
Token ID17756
Feature activation-2.60e-02

Pos logit contributions
ust+0.165
Really+0.156
Okay+0.134
Deal+0.125
iring+0.120
Neg logit contributions
hered-0.171
 on-0.161
igh-0.155
e-0.154
hed-0.152
Token.
Token ID13
Feature activation+8.53e-04

Pos logit contributions
ust+0.070
Really+0.059
urious+0.057
Okay+0.057
 rightful+0.056
Neg logit contributions
hered-0.028
rell-0.027
 on-0.026
hed-0.026
 -0.025
Token They
Token ID1119
Feature activation+4.30e-03

Pos logit contributions
hered+0.001
rell+0.001
hed+0.001
on+0.001
iren+0.001
Neg logit contributions
ust-0.002
Really-0.002
 rightful-0.002
urious-0.002
Okay-0.002
Token learned
Token ID4499
Feature activation-3.59e-02

Pos logit contributions
hered+0.005
rell+0.005
hed+0.005
 +0.005
 on+0.005
Neg logit contributions
ust-0.011
Really-0.009
urious-0.009
 rightful-0.009
Okay-0.009
Token more
Token ID517
Feature activation-3.79e-02

Pos logit contributions
ust+0.088
Really+0.069
 rightful+0.069
urious+0.068
 former+0.068
Neg logit contributions
hered-0.050
rell-0.049
hed-0.047
on-0.044
iren-0.043
Token Tim
Token ID5045
Feature activation-4.14e-02

Pos logit contributions
ust+0.021
Really+0.016
 rightful+0.016
urious+0.016
Okay+0.016
Neg logit contributions
hered-0.014
rell-0.014
hed-0.013
on-0.012
iren-0.012
Tokenmy
Token ID1820
Feature activation-1.93e-02

Pos logit contributions
ust+0.104
Really+0.084
 rightful+0.083
urious+0.082
Okay+0.082
Neg logit contributions
hered-0.054
rell-0.053
hed-0.050
on-0.047
 -0.047
Token loved
Token ID6151
Feature activation-2.40e-02

Pos logit contributions
ust+0.042
urious+0.032
 rightful+0.032
Really+0.032
Okay+0.032
Neg logit contributions
hered-0.031
rell-0.031
hed-0.029
iren-0.028
 -0.028
Token going
Token ID1016
Feature activation-1.75e-02

Pos logit contributions
ust+0.066
Really+0.053
 rightful+0.053
urious+0.053
Okay+0.052
Neg logit contributions
hered-0.026
rell-0.026
hed-0.024
on-0.024
 on-0.024
Token on
Token ID319
Feature activation+3.60e-02

Pos logit contributions
ust+0.043
Really+0.034
 rightful+0.034
urious+0.034
Okay+0.033
Neg logit contributions
hered-0.024
rell-0.023
hed-0.022
 -0.020
on-0.020
Token elev
Token ID7662
Feature activation-9.31e-02

Pos logit contributions
hered+0.053
rell+0.052
hed+0.049
on+0.047
 +0.047
Neg logit contributions
ust-0.084
Really-0.066
 rightful-0.066
urious-0.066
Okay-0.065
Tokenators
Token ID2024
Feature activation-5.28e-03

Pos logit contributions
ust+0.176
Really+0.143
 rightful+0.130
Okay+0.128
 former+0.126
Neg logit contributions
 on-0.171
rell-0.170
hed-0.164
irens-0.163
iren-0.161
Token and
Token ID290
Feature activation+1.06e-02

Pos logit contributions
ust+0.014
Really+0.012
 rightful+0.012
urious+0.012
Okay+0.012
Neg logit contributions
hered-0.006
rell-0.006
hed-0.005
 on-0.005
on-0.005
Token always
Token ID1464
Feature activation-1.73e-02

Pos logit contributions
hered+0.013
rell+0.013
hed+0.012
on+0.011
 +0.011
Neg logit contributions
ust-0.027
Really-0.022
 rightful-0.022
urious-0.022
Okay-0.022
Token dreamed
Token ID27947
Feature activation-3.56e-02

Pos logit contributions
ust+0.044
Really+0.035
urious+0.035
Okay+0.034
 former+0.034
Neg logit contributions
hered-0.022
 on-0.022
 -0.022
rell-0.022
hed-0.021
Token of
Token ID286
Feature activation-5.60e-03

Pos logit contributions
ust+0.095
Really+0.079
urious+0.079
 rightful+0.078
Okay+0.077
Neg logit contributions
rell-0.039
hered-0.039
hed-0.037
 on-0.036
iren-0.035
Token flew
Token ID13112
Feature activation-1.00e-02

Pos logit contributions
hered+0.001
rell+0.001
hed+0.001
 +0.001
on+0.001
Neg logit contributions
ust-0.002
Really-0.001
urious-0.001
 rightful-0.001
Okay-0.001
Token away
Token ID1497
Feature activation-2.69e-02

Pos logit contributions
ust+0.028
 rightful+0.023
Okay+0.022
Really+0.022
 former+0.022
Neg logit contributions
rell-0.010
hered-0.009
on-0.009
hed-0.009
iren-0.008
Token.
Token ID13
Feature activation-1.02e-02

Pos logit contributions
ust+0.070
Really+0.057
 rightful+0.056
urious+0.056
Okay+0.056
Neg logit contributions
hered-0.032
rell-0.031
hed-0.030
 -0.028
on-0.028
Token
Token ID198
Feature activation-9.92e-03

Pos logit contributions
ust+0.029
 rightful+0.024
Really+0.024
urious+0.024
Okay+0.024
Neg logit contributions
hered-0.009
rell-0.009
 -0.009
hed-0.009
on-0.008
Token
Token ID198
Feature activation-2.13e-02

Pos logit contributions
ust+0.027
Really+0.022
 rightful+0.022
urious+0.022
Okay+0.022
Neg logit contributions
hered-0.010
rell-0.010
hed-0.009
on-0.009
 -0.009
TokenLuc
Token ID22946
Feature activation-9.27e-02

Pos logit contributions
ust+0.045
 rightful+0.035
 former+0.034
Really+0.034
Deal+0.033
Neg logit contributions
hered-0.036
hed-0.035
 -0.035
on-0.034
rell-0.034
Tokenas
Token ID292
Feature activation+2.20e-02

Pos logit contributions
Really+0.114
ust+0.112
Okay+0.110
 rightful+0.109
Deal+0.107
Neg logit contributions
hered-0.200
rell-0.197
hed-0.196
ons-0.192
on-0.192
Token continued
Token ID3767
Feature activation-8.73e-03

Pos logit contributions
hered+0.030
rell+0.030
hed+0.028
iren+0.027
on+0.026
Neg logit contributions
ust-0.053
Really-0.042
 rightful-0.041
urious-0.041
Okay-0.041
Token his
Token ID465
Feature activation-3.94e-02

Pos logit contributions
ust+0.019
 rightful+0.016
 former+0.016
urious+0.015
Years+0.015
Neg logit contributions
rell-0.012
hered-0.011
hed-0.011
on-0.010
iren-0.010
Token walk
Token ID2513
Feature activation-1.80e-02

Pos logit contributions
ust+0.079
Really+0.060
urious+0.058
Okay+0.058
 rightful+0.058
Neg logit contributions
hered-0.072
rell-0.071
hed-0.067
 -0.066
 on-0.066
Token with
Token ID351
Feature activation+2.26e-02

Pos logit contributions
ust+0.051
 rightful+0.042
 former+0.042
Really+0.041
Okay+0.041
Neg logit contributions
rell-0.016
hered-0.016
hed-0.014
on-0.014
iren-0.013
Token enjoy
Token ID2883
Feature activation+7.38e-03

Pos logit contributions
hered+0.011
rell+0.010
hed+0.010
 +0.010
on+0.010
Neg logit contributions
ust-0.015
Really-0.012
urious-0.011
Okay-0.011
 rightful-0.011
Token it
Token ID340
Feature activation-1.27e-03

Pos logit contributions
hered+0.009
rell+0.009
hed+0.009
 +0.008
on+0.008
Neg logit contributions
ust-0.019
Really-0.015
urious-0.015
 rightful-0.015
Okay-0.015
Token."
Token ID526
Feature activation-3.50e-03

Pos logit contributions
ust+0.003
Really+0.002
 rightful+0.002
urious+0.002
Okay+0.002
Neg logit contributions
hered-0.002
rell-0.002
hed-0.002
on-0.002
 -0.002
Token
Token ID198
Feature activation-9.17e-03

Pos logit contributions
ust+0.009
Really+0.007
 rightful+0.007
urious+0.007
Okay+0.007
Neg logit contributions
hered-0.004
rell-0.004
hed-0.004
iren-0.004
 crash-0.004
Token
Token ID198
Feature activation-1.25e-02

Pos logit contributions
ust+0.025
 rightful+0.021
Really+0.021
 former+0.020
Deal+0.020
Neg logit contributions
 -0.009
hered-0.009
rell-0.009
on-0.009
hed-0.009
TokenFr
Token ID6732
Feature activation-9.24e-02

Pos logit contributions
ust+0.025
 rightful+0.020
 former+0.019
urious+0.018
Really+0.018
Neg logit contributions
hered-0.022
 -0.021
on-0.021
hed-0.020
iren-0.020
Tokenanny
Token ID7737
Feature activation-1.65e-03

Pos logit contributions
Really+0.072
Okay+0.043
 rightful+0.042
igor+0.039
How+0.038
Neg logit contributions
rell-0.234
on-0.225
iren-0.221
ons-0.221
opl-0.215
Token understood
Token ID7247
Feature activation-3.71e-02

Pos logit contributions
ust+0.004
Really+0.003
 rightful+0.003
 former+0.003
Okay+0.003
Neg logit contributions
hered-0.002
hed-0.002
rell-0.002
on-0.002
 on-0.002
Token and
Token ID290
Feature activation+1.01e-02

Pos logit contributions
ust+0.101
Really+0.083
 rightful+0.083
urious+0.082
Okay+0.082
Neg logit contributions
hered-0.039
rell-0.038
hed-0.036
 on-0.035
 -0.035
Token carefully
Token ID7773
Feature activation+2.86e-03

Pos logit contributions
hered+0.013
hed+0.013
 +0.013
 on+0.013
rell+0.013
Neg logit contributions
ust-0.025
Really-0.020
urious-0.020
 rightful-0.020
Okay-0.019
Token put
Token ID1234
Feature activation+3.91e-03

Pos logit contributions
hered+0.004
rell+0.004
hed+0.004
on+0.004
 +0.004
Neg logit contributions
ust-0.007
Really-0.005
 rightful-0.005
urious-0.005
Deal-0.005
Token read
Token ID1100
Feature activation-9.05e-04

Pos logit contributions
ust+0.060
Really+0.047
urious+0.046
Okay+0.046
 rightful+0.046
Neg logit contributions
hered-0.038
rell-0.038
 -0.036
hed-0.035
 crash-0.035
Token it
Token ID340
Feature activation+1.09e-03

Pos logit contributions
ust+0.002
Really+0.002
 rightful+0.002
urious+0.002
Okay+0.002
Neg logit contributions
hered-0.001
rell-0.001
hed-0.001
on-0.001
 -0.001
Token!"
Token ID2474
Feature activation-8.00e-03

Pos logit contributions
rell+0.001
hered+0.001
hed+0.001
 on+0.001
 +0.001
Neg logit contributions
ust-0.003
Really-0.002
 rightful-0.002
urious-0.002
Okay-0.002
Token
Token ID198
Feature activation-2.45e-02

Pos logit contributions
ust+0.017
Really+0.014
Okay+0.014
urious+0.014
Deal+0.014
Neg logit contributions
rell-0.012
hered-0.012
hed-0.011
 falling-0.011
iren-0.010
Token
Token ID198
Feature activation-2.80e-02

Pos logit contributions
ust+0.053
 rightful+0.041
Really+0.041
urious+0.040
 former+0.040
Neg logit contributions
hered-0.040
rell-0.039
hed-0.038
 -0.037
on-0.037
TokenLuc
Token ID22946
Feature activation-9.18e-02

Pos logit contributions
ust+0.055
 rightful+0.042
 former+0.041
Really+0.041
urious+0.040
Neg logit contributions
hered-0.053
hed-0.049
rell-0.049
 -0.048
on-0.048
Tokenia
Token ID544
Feature activation-5.66e-03

Pos logit contributions
Really+0.136
Okay+0.127
 rightful+0.127
ust+0.121
 former+0.117
Neg logit contributions
ons-0.183
on-0.183
hered-0.178
rell-0.177
igh-0.175
Token smiled
Token ID13541
Feature activation+7.30e-03

Pos logit contributions
ust+0.015
 rightful+0.012
Really+0.012
 former+0.012
Deal+0.012
Neg logit contributions
hered-0.007
hed-0.006
rell-0.006
 -0.006
 on-0.006
Token and
Token ID290
Feature activation+2.17e-02

Pos logit contributions
hered+0.007
rell+0.007
hed+0.006
 +0.006
 on+0.006
Neg logit contributions
ust-0.021
Really-0.017
Deal-0.017
 rightful-0.017
urious-0.017
Token said
Token ID531
Feature activation+2.39e-02

Pos logit contributions
hered+0.028
 +0.028
hed+0.028
 on+0.027
rell+0.026
Neg logit contributions
ust-0.057
urious-0.045
 rightful-0.045
 former-0.045
Really-0.043
Token:
Token ID25
Feature activation+1.55e-02

Pos logit contributions
rell+0.028
hered+0.026
hed+0.024
iren+0.023
 crash+0.023
Neg logit contributions
ust-0.063
Really-0.052
Okay-0.051
Deal-0.050
 rightful-0.050
Token Sara
Token ID24799
Feature activation-8.73e-03

Pos logit contributions
hered+0.003
rell+0.003
hed+0.002
on+0.002
 +0.002
Neg logit contributions
ust-0.005
Really-0.004
 rightful-0.004
urious-0.004
Okay-0.003
Token and
Token ID290
Feature activation+2.70e-02

Pos logit contributions
ust+0.023
Really+0.018
 rightful+0.018
urious+0.018
Okay+0.018
Neg logit contributions
hered-0.011
rell-0.010
hed-0.010
iren-0.009
 crash-0.009
Token Ben
Token ID3932
Feature activation+1.72e-02

Pos logit contributions
hered+0.036
rell+0.034
 +0.034
 on+0.034
hed+0.033
Neg logit contributions
ust-0.069
urious-0.056
 rightful-0.054
Really-0.054
 former-0.053
Token,
Token ID11
Feature activation-3.42e-02

Pos logit contributions
hered+0.025
rell+0.024
hed+0.023
on+0.022
 +0.022
Neg logit contributions
ust-0.041
Really-0.032
 rightful-0.032
urious-0.032
Okay-0.031
Token "
Token ID366
Feature activation-4.47e-02

Pos logit contributions
ust+0.092
urious+0.077
 rightful+0.073
 former+0.073
Really+0.072
Neg logit contributions
hered-0.039
 -0.039
 on-0.038
rell-0.036
 crash-0.035
TokenGu
Token ID8205
Feature activation-9.14e-02

Pos logit contributions
ust+0.109
 rightful+0.090
urious+0.088
 former+0.087
asured+0.083
Neg logit contributions
hered-0.065
hed-0.062
 -0.057
 on-0.055
rell-0.053
Tokeness
Token ID408
Feature activation-1.05e-02

Pos logit contributions
Really+0.136
ust+0.135
Okay+0.103
igor+0.103
urious+0.101
Neg logit contributions
rell-0.176
 on-0.171
,-0.168
hed-0.163
 off-0.162
Token what
Token ID644
Feature activation-1.61e-02

Pos logit contributions
ust+0.025
Really+0.020
Okay+0.020
urious+0.020
 rightful+0.020
Neg logit contributions
hered-0.015
rell-0.015
 on-0.014
hed-0.014
on-0.014
Token,
Token ID11
Feature activation-4.13e-02

Pos logit contributions
ust+0.038
 former+0.031
urious+0.030
Okay+0.030
 rightful+0.030
Neg logit contributions
 on-0.023
hered-0.023
on-0.022
rell-0.022
 -0.022
Token kids
Token ID3988
Feature activation+2.88e-02

Pos logit contributions
ust+0.103
urious+0.091
 former+0.085
 rightful+0.083
Okay+0.082
Neg logit contributions
 on-0.056
 -0.050
,-0.049
 sorry-0.048
 falling-0.047
Token.
Token ID13
Feature activation-7.50e-03

Pos logit contributions
hered+0.038
rell+0.035
hed+0.035
 on+0.035
on+0.033
Neg logit contributions
ust-0.073
Really-0.062
 former-0.060
urious-0.060
 rightful-0.059
Token little
Token ID1310
Feature activation+7.19e-03

Pos logit contributions
 +0.019
rell+0.018
 on+0.018
 crash+0.017
on+0.017
Neg logit contributions
ust-0.035
Deal-0.029
Okay-0.029
Really-0.029
 rightful-0.029
Token girl
Token ID2576
Feature activation-4.90e-03

Pos logit contributions
 on+0.011
 +0.011
rell+0.011
hered+0.011
 arms+0.011
Neg logit contributions
ust-0.016
Deal-0.012
Really-0.012
Okay-0.011
 rightful-0.011
Token all
Token ID477
Feature activation-7.07e-03

Pos logit contributions
ust+0.010
urious+0.007
 rightful+0.007
Really+0.007
Deal+0.007
Neg logit contributions
hered-0.009
rell-0.009
hed-0.008
iren-0.008
 crash-0.008
Token about
Token ID546
Feature activation+1.74e-04

Pos logit contributions
ust+0.016
urious+0.012
Really+0.012
 rightful+0.012
Okay+0.012
Neg logit contributions
hered-0.011
rell-0.011
hed-0.010
iren-0.010
on-0.010
Token how
Token ID703
Feature activation-2.76e-02

Pos logit contributions
rell+0.000
hered+0.000
hed+0.000
 +0.000
 on+0.000
Neg logit contributions
ust-0.000
Really-0.000
Okay-0.000
 rightful-0.000
urious-0.000
Token volcan
Token ID17516
Feature activation-9.12e-02

Pos logit contributions
ust+0.074
Really+0.062
Okay+0.061
 rightful+0.060
Deal+0.060
Neg logit contributions
 on-0.029
 -0.029
on-0.027
rell-0.027
 crash-0.026
Tokenoes
Token ID3028
Feature activation-1.08e-02

Pos logit contributions
ust+0.162
 rightful+0.139
Really+0.138
Okay+0.135
 former+0.131
Neg logit contributions
rell-0.179
hered-0.166
hed-0.166
 on-0.165
on-0.162
Token work
Token ID670
Feature activation-4.23e-03

Pos logit contributions
ust+0.025
Really+0.020
 rightful+0.020
Okay+0.020
urious+0.020
Neg logit contributions
hered-0.016
rell-0.016
hed-0.015
 on-0.014
 -0.014
Token.
Token ID13
Feature activation+5.71e-03

Pos logit contributions
ust+0.011
Really+0.009
 rightful+0.008
urious+0.008
Okay+0.008
Neg logit contributions
hered-0.005
rell-0.005
hed-0.005
 -0.005
on-0.005
Token She
Token ID1375
Feature activation-2.02e-02

Pos logit contributions
 +0.006
rell+0.006
hed+0.005
hered+0.005
on+0.005
Neg logit contributions
ust-0.016
 rightful-0.013
Deal-0.013
urious-0.013
Okay-0.013
Token taught
Token ID7817
Feature activation-2.11e-03

Pos logit contributions
ust+0.052
Really+0.043
 rightful+0.042
urious+0.040
Okay+0.040
Neg logit contributions
hed-0.025
on-0.025
hered-0.024
 on-0.024
 -0.023
Token every
Token ID790
Feature activation-2.68e-02

Pos logit contributions
ust+0.082
Really+0.067
 rightful+0.066
urious+0.066
Okay+0.065
Neg logit contributions
hered-0.036
rell-0.035
hed-0.033
 -0.031
on-0.031
Token day
Token ID1110
Feature activation+5.55e-03

Pos logit contributions
ust+0.064
urious+0.051
Really+0.050
 rightful+0.050
Okay+0.050
Neg logit contributions
hered-0.038
rell-0.038
hed-0.036
iren-0.033
on-0.033
Token and
Token ID290
Feature activation-1.51e-02

Pos logit contributions
hered+0.006
rell+0.006
hed+0.006
 on+0.005
on+0.005
Neg logit contributions
ust-0.015
Really-0.012
urious-0.012
 rightful-0.012
Okay-0.012
Token touch
Token ID3638
Feature activation-7.34e-03

Pos logit contributions
ust+0.035
urious+0.027
Really+0.027
Okay+0.026
Deal+0.026
Neg logit contributions
hered-0.023
 -0.022
rell-0.022
 on-0.022
hed-0.021
Token the
Token ID262
Feature activation+2.74e-02

Pos logit contributions
ust+0.020
Really+0.017
 rightful+0.017
urious+0.016
Okay+0.016
Neg logit contributions
hered-0.008
rell-0.007
hed-0.007
iren-0.006
 crash-0.006
Token terr
Token ID8812
Feature activation-9.12e-02

Pos logit contributions
hered+0.042
rell+0.042
hed+0.040
on+0.038
 +0.037
Neg logit contributions
ust-0.062
Really-0.049
 rightful-0.048
urious-0.048
Okay-0.048
Tokenac
Token ID330
Feature activation-1.24e-02

Pos logit contributions
ust+0.177
Okay+0.161
Really+0.158
Years+0.143
Deal+0.140
Neg logit contributions
hered-0.145
 on-0.143
 out-0.131
on-0.128
e-0.128
Tokenotta
Token ID12375
Feature activation-1.58e-02

Pos logit contributions
ust+0.024
Really+0.018
 rightful+0.017
urious+0.017
Okay+0.017
Neg logit contributions
hered-0.024
rell-0.023
hed-0.023
 -0.022
on-0.022
Token pot
Token ID1787
Feature activation-1.35e-02

Pos logit contributions
ust+0.039
Really+0.031
Okay+0.031
 rightful+0.030
urious+0.030
Neg logit contributions
hered-0.022
rell-0.021
hed-0.021
on-0.020
 -0.020
Token.
Token ID13
Feature activation-5.17e-03

Pos logit contributions
ust+0.035
Really+0.028
urious+0.028
 rightful+0.028
Okay+0.028
Neg logit contributions
hered-0.017
rell-0.016
hed-0.016
 on-0.015
on-0.015
Token Maybe
Token ID6674
Feature activation-3.11e-02

Pos logit contributions
ust+0.014
urious+0.012
 rightful+0.012
Really+0.011
Okay+0.011
Neg logit contributions
 -0.006
rell-0.006
hed-0.005
hered-0.005
on-0.005
Token just
Token ID655
Feature activation-4.02e-04

Pos logit contributions
hered+0.047
rell+0.047
hed+0.044
iren+0.043
on+0.043
Neg logit contributions
ust-0.053
Really-0.040
 rightful-0.039
urious-0.039
Okay-0.039
Token wanted
Token ID2227
Feature activation+1.68e-02

Pos logit contributions
ust+0.001
Really+0.001
 rightful+0.001
urious+0.001
Okay+0.001
Neg logit contributions
hered-0.001
rell-0.001
hed-0.001
on-0.001
 -0.001
Token to
Token ID284
Feature activation+1.07e-02

Pos logit contributions
hered+0.023
rell+0.022
hed+0.021
 +0.020
on+0.020
Neg logit contributions
ust-0.041
Really-0.033
urious-0.032
 rightful-0.032
Okay-0.032
Token write
Token ID3551
Feature activation-6.00e-03

Pos logit contributions
 crash+0.014
hered+0.013
 +0.013
rell+0.012
on+0.012
Neg logit contributions
ust-0.028
Really-0.023
urious-0.023
Deal-0.022
Okay-0.022
Token about
Token ID546
Feature activation+1.10e-02

Pos logit contributions
ust+0.016
Really+0.013
urious+0.012
 rightful+0.012
Okay+0.012
Neg logit contributions
hered-0.007
rell-0.007
hed-0.007
on-0.006
 -0.006
Token volcan
Token ID17516
Feature activation-9.09e-02

Pos logit contributions
 on+0.010
 +0.010
on+0.010
hered+0.010
rell+0.010
Neg logit contributions
ust-0.031
Okay-0.026
urious-0.025
Deal-0.025
Really-0.025
Tokenoes
Token ID3028
Feature activation-5.86e-03

Pos logit contributions
ust+0.157
Really+0.129
 rightful+0.125
Okay+0.120
 former+0.117
Neg logit contributions
rell-0.186
hered-0.176
hed-0.172
 on-0.168
iren-0.168
Token.
Token ID13
Feature activation-5.72e-03

Pos logit contributions
ust+0.014
Really+0.011
urious+0.011
 rightful+0.011
Okay+0.011
Neg logit contributions
hered-0.008
rell-0.008
hed-0.007
on-0.007
 -0.007
Token We
Token ID775
Feature activation+2.53e-02

Pos logit contributions
ust+0.014
urious+0.011
 rightful+0.011
Years+0.011
Deal+0.010
Neg logit contributions
 -0.008
 on-0.007
hered-0.007
rell-0.007
 crash-0.007
Token like
Token ID588
Feature activation-7.24e-03

Pos logit contributions
hered+0.043
rell+0.042
hed+0.041
 +0.039
on+0.039
Neg logit contributions
ust-0.053
Really-0.042
 rightful-0.041
urious-0.041
Okay-0.039
Token volcan
Token ID17516
Feature activation-8.68e-02

Pos logit contributions
ust+0.019
Okay+0.015
urious+0.015
Really+0.015
Deal+0.015
Neg logit contributions
rell-0.008
 on-0.008
hered-0.008
on-0.008
 -0.008
Token just
Token ID655
Feature activation+1.36e-03

Pos logit contributions
hered+0.049
rell+0.049
hed+0.046
on+0.045
iren+0.045
Neg logit contributions
ust-0.060
Really-0.045
 rightful-0.045
urious-0.045
Okay-0.045
Token wanted
Token ID2227
Feature activation+1.72e-02

Pos logit contributions
hered+0.003
rell+0.003
hed+0.003
iren+0.002
on+0.002
Neg logit contributions
ust-0.002
Really-0.002
 rightful-0.002
urious-0.002
Okay-0.002
Token to
Token ID284
Feature activation+1.26e-02

Pos logit contributions
hered+0.023
rell+0.022
hed+0.021
 +0.020
on+0.020
Neg logit contributions
ust-0.043
Really-0.034
urious-0.034
 rightful-0.034
Okay-0.033
Token write
Token ID3551
Feature activation-6.86e-03

Pos logit contributions
 crash+0.016
hered+0.015
 +0.015
on+0.015
rell+0.015
Neg logit contributions
ust-0.033
Really-0.027
urious-0.026
Deal-0.026
Okay-0.026
Token about
Token ID546
Feature activation+1.39e-02

Pos logit contributions
ust+0.018
Really+0.015
urious+0.015
 rightful+0.015
Okay+0.015
Neg logit contributions
hered-0.008
rell-0.008
hed-0.007
 on-0.007
on-0.007
Token volcan
Token ID17516
Feature activation-9.04e-02

Pos logit contributions
 on+0.011
on+0.011
 +0.010
rell+0.010
ons+0.010
Neg logit contributions
ust-0.042
Okay-0.035
urious-0.035
Deal-0.034
Really-0.033
Tokenoes
Token ID3028
Feature activation-6.54e-03

Pos logit contributions
ust+0.158
Really+0.134
 rightful+0.129
Okay+0.124
 former+0.120
Neg logit contributions
rell-0.182
hered-0.172
hed-0.169
iren-0.166
on-0.165
Token.
Token ID13
Feature activation-3.63e-03

Pos logit contributions
ust+0.016
Really+0.013
urious+0.013
 rightful+0.013
Okay+0.013
Neg logit contributions
hered-0.009
rell-0.008
hed-0.008
on-0.008
 on-0.008
Token We
Token ID775
Feature activation+2.72e-02

Pos logit contributions
ust+0.009
urious+0.007
 rightful+0.007
Years+0.007
Deal+0.007
Neg logit contributions
 -0.005
rell-0.004
hered-0.004
 on-0.004
 crash-0.004
Token like
Token ID588
Feature activation-8.11e-03

Pos logit contributions
hered+0.045
rell+0.044
hed+0.043
 +0.041
on+0.040
Neg logit contributions
ust-0.058
Really-0.046
urious-0.045
 rightful-0.045
 former-0.043
Token volcan
Token ID17516
Feature activation-8.70e-02

Pos logit contributions
ust+0.022
Okay+0.018
Deal+0.018
urious+0.017
Really+0.017
Neg logit contributions
 on-0.009
rell-0.009
on-0.009
 -0.008
 crash-0.008
Token
Token ID198
Feature activation-1.90e-02

Pos logit contributions
ust+0.011
Really+0.009
urious+0.009
 rightful+0.009
Okay+0.008
Neg logit contributions
hered-0.006
rell-0.006
hed-0.006
 crash-0.005
on-0.005
TokenThe
Token ID464
Feature activation+7.05e-03

Pos logit contributions
ust+0.040
 rightful+0.031
Really+0.031
urious+0.031
Deal+0.030
Neg logit contributions
hered-0.032
rell-0.031
hed-0.030
 -0.029
on-0.029
Token next
Token ID1306
Feature activation-3.89e-02

Pos logit contributions
rell+0.013
hered+0.013
hed+0.013
iren+0.012
 +0.011
Neg logit contributions
ust-0.014
Really-0.011
 rightful-0.011
Okay-0.010
urious-0.010
Token day
Token ID1110
Feature activation+2.77e-02

Pos logit contributions
ust+0.116
 rightful+0.094
 former+0.094
Really+0.092
urious+0.092
Neg logit contributions
hered-0.037
 on-0.034
on-0.032
rell-0.032
 -0.031
Token,
Token ID11
Feature activation-1.81e-02

Pos logit contributions
rell+0.024
hered+0.024
hed+0.022
on+0.020
iren+0.019
Neg logit contributions
ust-0.080
Really-0.066
 rightful-0.066
Okay-0.065
urious-0.065
Token Tri
Token ID7563
Feature activation-8.99e-02

Pos logit contributions
ust+0.044
Really+0.035
 rightful+0.035
Okay+0.034
 former+0.034
Neg logit contributions
hered-0.025
rell-0.025
hed-0.024
on-0.022
iren-0.022
Tokenx
Token ID87
Feature activation-1.30e-02

Pos logit contributions
ust+0.169
Really+0.157
Deal+0.150
Okay+0.150
 rightful+0.145
Neg logit contributions
rell-0.154
hed-0.145
hered-0.143
ons-0.138
on-0.137
Tokenie
Token ID494
Feature activation-2.58e-02

Pos logit contributions
ust+0.021
Really+0.014
urious+0.014
 rightful+0.014
Okay+0.014
Neg logit contributions
hered-0.029
rell-0.028
hed-0.027
 -0.026
on-0.026
Token was
Token ID373
Feature activation-3.49e-03

Pos logit contributions
ust+0.063
Really+0.050
 rightful+0.049
urious+0.049
Okay+0.049
Neg logit contributions
hered-0.035
rell-0.035
hed-0.033
 -0.032
on-0.032
Token surprised
Token ID6655
Feature activation-3.56e-02

Pos logit contributions
ust+0.008
 rightful+0.007
 former+0.007
asured+0.007
urious+0.006
Neg logit contributions
rell-0.005
hered-0.005
hed-0.004
iren-0.004
 trigger-0.004
Token to
Token ID284
Feature activation-2.82e-02

Pos logit contributions
ust+0.101
Really+0.089
Deal+0.088
 former+0.087
 rightful+0.087
Neg logit contributions
 on-0.033
hered-0.030
,-0.028
 off-0.027
 -0.026
Token
Token ID198
Feature activation-1.79e-02

Pos logit contributions
ust+0.019
Really+0.016
 rightful+0.016
urious+0.015
Okay+0.015
Neg logit contributions
hered-0.009
rell-0.009
hed-0.009
 -0.008
on-0.008
TokenThe
Token ID464
Feature activation+6.41e-03

Pos logit contributions
ust+0.038
 rightful+0.029
Deal+0.028
urious+0.028
Really+0.028
Neg logit contributions
hered-0.030
 -0.029
rell-0.029
hed-0.028
on-0.028
Token little
Token ID1310
Feature activation+1.49e-02

Pos logit contributions
hered+0.010
rell+0.010
hed+0.009
on+0.009
 +0.009
Neg logit contributions
ust-0.015
Really-0.011
 rightful-0.011
urious-0.011
Okay-0.011
Token bird
Token ID6512
Feature activation-1.70e-02

Pos logit contributions
hered+0.022
rell+0.021
 on+0.020
hed+0.020
 +0.020
Neg logit contributions
ust-0.036
Really-0.028
 rightful-0.027
urious-0.027
Deal-0.027
Token watched
Token ID7342
Feature activation-2.43e-02

Pos logit contributions
ust+0.040
Really+0.032
 rightful+0.032
Okay+0.031
urious+0.031
Neg logit contributions
hered-0.024
rell-0.024
hed-0.023
 -0.022
on-0.022
Token Sab
Token ID9910
Feature activation-8.98e-02

Pos logit contributions
ust+0.065
Really+0.053
urious+0.052
 rightful+0.052
Okay+0.052
Neg logit contributions
hered-0.028
rell-0.027
hed-0.026
 -0.024
on-0.024
Tokenrina
Token ID22267
Feature activation-3.44e-02

Pos logit contributions
ust+0.168
Really+0.164
Deal+0.162
Okay+0.162
 rightful+0.150
Neg logit contributions
rell-0.141
hered-0.139
on-0.129
hed-0.127
ons-0.127
Token with
Token ID351
Feature activation+5.06e-02

Pos logit contributions
ust+0.087
Really+0.070
 rightful+0.070
urious+0.069
Okay+0.069
Neg logit contributions
hered-0.043
rell-0.042
hed-0.040
on-0.038
 -0.038
Token wonder
Token ID4240
Feature activation-3.08e-02

Pos logit contributions
rell+0.086
hed+0.081
iren+0.079
hered+0.077
irens+0.074
Neg logit contributions
ust-0.099
 rightful-0.082
Really-0.078
 former-0.077
 appreciate-0.074
Token as
Token ID355
Feature activation-2.17e-02

Pos logit contributions
ust+0.075
Really+0.062
Okay+0.061
urious+0.061
 rightful+0.060
Neg logit contributions
hered-0.039
 on-0.039
rell-0.038
hed-0.037
 -0.037
Token she
Token ID673
Feature activation-7.10e-03

Pos logit contributions
ust+0.059
Really+0.048
urious+0.048
Okay+0.047
 rightful+0.047
Neg logit contributions
hered-0.023
rell-0.023
 on-0.022
hed-0.021
 -0.021
Token They
Token ID1119
Feature activation+6.05e-03

Pos logit contributions
 +0.011
hered+0.010
rell+0.010
 on+0.009
hed+0.009
Neg logit contributions
ust-0.023
 rightful-0.018
Deal-0.018
 former-0.018
urious-0.018
Token want
Token ID765
Feature activation+5.76e-03

Pos logit contributions
rell+0.010
hered+0.009
hed+0.009
 crash+0.009
 +0.009
Neg logit contributions
ust-0.013
Really-0.011
 rightful-0.010
urious-0.010
Okay-0.010
Token to
Token ID284
Feature activation-1.72e-03

Pos logit contributions
hered+0.008
rell+0.008
hed+0.007
 +0.007
on+0.007
Neg logit contributions
ust-0.014
Really-0.011
 rightful-0.011
urious-0.011
Okay-0.011
Token write
Token ID3551
Feature activation-9.30e-03

Pos logit contributions
ust+0.004
Really+0.004
urious+0.003
Okay+0.003
Deal+0.003
Neg logit contributions
 crash-0.002
rell-0.002
hered-0.002
 -0.002
on-0.002
Token about
Token ID546
Feature activation+9.25e-03

Pos logit contributions
ust+0.024
Really+0.020
 rightful+0.020
Deal+0.019
Okay+0.019
Neg logit contributions
hered-0.011
rell-0.011
hed-0.010
iren-0.009
on-0.009
Token volcan
Token ID17516
Feature activation-8.95e-02

Pos logit contributions
 on+0.008
rell+0.008
 +0.008
hered+0.007
on+0.007
Neg logit contributions
ust-0.027
Okay-0.023
urious-0.022
Really-0.022
Deal-0.022
Tokenoes
Token ID3028
Feature activation-8.19e-03

Pos logit contributions
ust+0.150
Really+0.123
 rightful+0.117
Okay+0.115
Deal+0.110
Neg logit contributions
rell-0.188
hered-0.180
hed-0.174
 on-0.171
iren-0.171
Token.
Token ID13
Feature activation+7.32e-03

Pos logit contributions
ust+0.022
Really+0.018
 rightful+0.017
urious+0.017
Deal+0.017
Neg logit contributions
hered-0.009
rell-0.009
hed-0.009
iren-0.008
 -0.008
Token
Token ID198
Feature activation-2.58e-03

Pos logit contributions
 +0.008
hered+0.007
rell+0.007
 on+0.007
hed+0.006
Neg logit contributions
ust-0.021
 rightful-0.017
 former-0.017
urious-0.017
Deal-0.016
Token
Token ID198
Feature activation-1.98e-02

Pos logit contributions
ust+0.007
 rightful+0.006
 former+0.006
Really+0.006
urious+0.006
Neg logit contributions
 -0.003
hered-0.003
rell-0.002
hed-0.002
on-0.002
TokenThey
Token ID2990
Feature activation-2.27e-03

Pos logit contributions
ust+0.041
 former+0.032
 rightful+0.032
Really+0.030
urious+0.030
Neg logit contributions
hered-0.034
 -0.032
 on-0.032
hed-0.032
rell-0.031
Token They
Token ID1119
Feature activation+4.24e-03

Pos logit contributions
 +0.004
hered+0.004
rell+0.004
 on+0.003
hed+0.003
Neg logit contributions
ust-0.010
urious-0.008
 rightful-0.008
Deal-0.008
asured-0.008
Token want
Token ID765
Feature activation+9.18e-03

Pos logit contributions
hered+0.006
 +0.006
rell+0.006
hed+0.006
 crash+0.006
Neg logit contributions
ust-0.009
Really-0.008
urious-0.007
 rightful-0.007
eter-0.007
Token to
Token ID284
Feature activation+3.26e-03

Pos logit contributions
hered+0.011
rell+0.011
 on+0.010
hed+0.010
 +0.010
Neg logit contributions
ust-0.024
Really-0.019
Deal-0.019
urious-0.019
Okay-0.019
Token write
Token ID3551
Feature activation-9.57e-03

Pos logit contributions
hered+0.004
rell+0.004
 crash+0.004
 +0.004
on+0.004
Neg logit contributions
ust-0.008
Really-0.006
urious-0.006
Okay-0.006
Deal-0.006
Token about
Token ID546
Feature activation+1.14e-02

Pos logit contributions
ust+0.025
Really+0.021
 rightful+0.020
urious+0.020
Okay+0.020
Neg logit contributions
hered-0.011
rell-0.011
hed-0.010
on-0.010
 -0.010
Token volcan
Token ID17516
Feature activation-8.95e-02

Pos logit contributions
rell+0.010
 +0.010
 on+0.010
hered+0.009
 crash+0.009
Neg logit contributions
ust-0.033
Okay-0.027
urious-0.027
Really-0.027
Deal-0.026
Tokenoes
Token ID3028
Feature activation-4.81e-03

Pos logit contributions
ust+0.151
Really+0.125
 rightful+0.120
Okay+0.116
Deal+0.112
Neg logit contributions
rell-0.184
hered-0.176
hed-0.171
 on-0.168
iren-0.168
Token.
Token ID13
Feature activation+3.45e-03

Pos logit contributions
ust+0.012
Really+0.010
 rightful+0.010
Deal+0.010
urious+0.010
Neg logit contributions
hered-0.006
rell-0.006
hed-0.005
iren-0.005
on-0.005
Token
Token ID198
Feature activation+5.84e-04

Pos logit contributions
 +0.004
hered+0.003
rell+0.003
 on+0.003
 onwards+0.003
Neg logit contributions
ust-0.010
urious-0.008
 rightful-0.008
Deal-0.008
asured-0.007
Token
Token ID198
Feature activation-1.30e-02

Pos logit contributions
hered+0.001
rell+0.001
 +0.001
hed+0.001
on+0.001
Neg logit contributions
ust-0.002
Really-0.001
 rightful-0.001
urious-0.001
Deal-0.001
TokenThey
Token ID2990
Feature activation-1.31e-03

Pos logit contributions
ust+0.029
 rightful+0.023
 former+0.022
urious+0.022
Really+0.021
Neg logit contributions
hered-0.020
 -0.020
 on-0.019
on-0.019
iren-0.019
Token held
Token ID2714
Feature activation+1.86e-02

Pos logit contributions
hered+0.020
rell+0.020
hed+0.019
 +0.018
on+0.018
Neg logit contributions
ust-0.028
Really-0.022
urious-0.022
 rightful-0.022
Okay-0.021
Token his
Token ID465
Feature activation-4.79e-03

Pos logit contributions
rell+0.027
hered+0.027
iren+0.023
hed+0.022
irens+0.021
Neg logit contributions
ust-0.041
urious-0.034
Really-0.033
 rightful-0.032
Deal-0.032
Token sword
Token ID8429
Feature activation+1.53e-02

Pos logit contributions
ust+0.009
 rightful+0.007
urious+0.007
Really+0.007
 former+0.007
Neg logit contributions
rell-0.009
hered-0.009
hed-0.009
iren-0.008
 -0.008
Token tight
Token ID5381
Feature activation+3.82e-02

Pos logit contributions
rell+0.027
hered+0.027
iren+0.026
irens+0.025
hed+0.024
Neg logit contributions
ust-0.033
urious-0.024
Years-0.022
 rightful-0.022
 former-0.022
Token and
Token ID290
Feature activation+2.85e-02

Pos logit contributions
rell+0.061
hered+0.060
iren+0.057
 crash+0.055
on+0.054
Neg logit contributions
ust-0.084
urious-0.062
Deal-0.061
Okay-0.061
 rightful-0.060
Token shouted
Token ID17293
Feature activation+5.66e-02

Pos logit contributions
hered+0.040
rell+0.039
hed+0.037
iren+0.034
on+0.034
Neg logit contributions
ust-0.068
Really-0.055
 rightful-0.054
Okay-0.054
urious-0.053
Token "
Token ID366
Feature activation-1.49e-02

Pos logit contributions
rell+0.073
hered+0.070
hed+0.066
iren+0.063
ons+0.060
Neg logit contributions
ust-0.142
Really-0.113
 rightful-0.110
Deal-0.108
Okay-0.108
TokenCome
Token ID16773
Feature activation+3.04e-02

Pos logit contributions
ust+0.033
 rightful+0.027
 former+0.026
Deal+0.025
Really+0.025
Neg logit contributions
hered-0.024
rell-0.023
hed-0.023
on-0.022
 crash-0.021
Token and
Token ID290
Feature activation+2.27e-02

Pos logit contributions
rell+0.032
hed+0.028
hered+0.027
iren+0.025
ons+0.024
Neg logit contributions
ust-0.080
Really-0.068
 rightful-0.066
Deal-0.066
Okay-0.065
Token fight
Token ID1907
Feature activation+4.03e-02

Pos logit contributions
hered+0.034
rell+0.033
hed+0.032
 +0.030
on+0.030
Neg logit contributions
ust-0.053
Really-0.041
urious-0.041
 rightful-0.041
Okay-0.040
Token me
Token ID502
Feature activation+3.24e-03

Pos logit contributions
rell+0.064
hered+0.064
hed+0.060
iren+0.058
on+0.057
Neg logit contributions
ust-0.088
Really-0.068
 rightful-0.067
urious-0.067
Okay-0.066
Token little
Token ID1310
Feature activation-8.61e-03

Pos logit contributions
ust+0.062
Really+0.049
urious+0.048
 rightful+0.048
Okay+0.048
Neg logit contributions
hered-0.038
rell-0.037
hed-0.035
 -0.034
on-0.033
Token shaky
Token ID35335
Feature activation-1.09e-02

Pos logit contributions
ust+0.023
Really+0.019
urious+0.019
 rightful+0.019
Okay+0.019
Neg logit contributions
hered-0.010
rell-0.009
hed-0.009
 -0.008
on-0.008
Token at
Token ID379
Feature activation-3.63e-02

Pos logit contributions
ust+0.029
Really+0.024
urious+0.024
 rightful+0.024
Deal+0.023
Neg logit contributions
hered-0.013
rell-0.012
hed-0.011
 -0.011
on-0.011
Token first
Token ID717
Feature activation-1.15e-02

Pos logit contributions
ust+0.101
Really+0.082
Okay+0.080
urious+0.080
 rightful+0.080
Neg logit contributions
rell-0.040
hered-0.039
 on-0.038
hed-0.037
 -0.037
Token but
Token ID475
Feature activation+7.61e-04

Pos logit contributions
ust+0.035
Really+0.030
Deal+0.029
Okay+0.029
urious+0.029
Neg logit contributions
hered-0.010
rell-0.009
 on-0.008
 crash-0.008
hed-0.008
Token with
Token ID351
Feature activation+4.76e-02

Pos logit contributions
hered+0.001
 +0.001
rell+0.001
 on+0.001
hed+0.001
Neg logit contributions
ust-0.002
urious-0.002
Really-0.002
 former-0.002
 rightful-0.002
Token a
Token ID257
Feature activation+4.42e-03

Pos logit contributions
hered+0.055
rell+0.054
hed+0.051
iren+0.046
on+0.045
Neg logit contributions
ust-0.125
 rightful-0.103
Really-0.101
urious-0.100
Okay-0.100
Token bit
Token ID1643
Feature activation-5.04e-03

Pos logit contributions
rell+0.007
hed+0.007
hered+0.007
ons+0.006
on+0.006
Neg logit contributions
ust-0.009
Really-0.008
 rightful-0.007
Okay-0.007
 former-0.007
Token of
Token ID286
Feature activation+1.44e-02

Pos logit contributions
ust+0.013
Really+0.010
 rightful+0.010
urious+0.010
Okay+0.010
Neg logit contributions
hered-0.006
rell-0.006
hed-0.006
on-0.006
 -0.005
Token practice
Token ID3357
Feature activation+1.80e-02

Pos logit contributions
hered+0.023
rell+0.021
hed+0.021
on+0.019
iren+0.018
Neg logit contributions
ust-0.030
 rightful-0.025
 former-0.024
Okay-0.024
Really-0.024
Token he
Token ID339
Feature activation-7.52e-03

Pos logit contributions
hered+0.021
rell+0.021
hed+0.019
on+0.017
iren+0.017
Neg logit contributions
ust-0.046
 rightful-0.038
Really-0.037
Okay-0.037
Deal-0.037
Token the
Token ID262
Feature activation+8.20e-03

Pos logit contributions
hered+0.011
rell+0.010
hed+0.010
iren+0.008
on+0.008
Neg logit contributions
ust-0.028
Really-0.024
urious-0.024
 rightful-0.024
 former-0.023
Token countryside
Token ID25708
Feature activation-2.52e-02

Pos logit contributions
hered+0.012
rell+0.012
hed+0.011
 +0.011
on+0.011
Neg logit contributions
ust-0.019
Really-0.015
 rightful-0.015
Deal-0.015
Okay-0.015
Token,
Token ID11
Feature activation-4.19e-02

Pos logit contributions
ust+0.061
 rightful+0.049
urious+0.049
Really+0.048
Deal+0.048
Neg logit contributions
hered-0.034
rell-0.033
hed-0.030
on-0.029
iren-0.029
Token and
Token ID290
Feature activation+1.01e-02

Pos logit contributions
ust+0.110
Really+0.091
 rightful+0.089
Okay+0.088
Deal+0.088
Neg logit contributions
hered-0.049
rell-0.048
hed-0.044
on-0.041
iren-0.041
Token every
Token ID790
Feature activation-9.36e-03

Pos logit contributions
hered+0.014
rell+0.013
hed+0.013
iren+0.012
on+0.012
Neg logit contributions
ust-0.025
Really-0.020
 rightful-0.020
urious-0.019
Okay-0.019
Token day
Token ID1110
Feature activation+4.28e-02

Pos logit contributions
ust+0.021
urious+0.017
Really+0.016
Okay+0.016
 rightful+0.016
Neg logit contributions
rell-0.014
hered-0.014
hed-0.014
iren-0.012
irens-0.012
Token he
Token ID339
Feature activation-2.59e-02

Pos logit contributions
hered+0.058
rell+0.057
hed+0.054
iren+0.050
on+0.049
Neg logit contributions
ust-0.103
Really-0.084
 rightful-0.083
Okay-0.081
urious-0.080
Token whist
Token ID32262
Feature activation+2.11e-02

Pos logit contributions
ust+0.067
Really+0.053
 rightful+0.052
urious+0.052
Okay+0.051
Neg logit contributions
hed-0.033
 on-0.033
hered-0.033
rell-0.032
 gun-0.031
Tokenled
Token ID992
Feature activation-3.91e-03

Pos logit contributions
hered+0.027
rell+0.026
hed+0.024
 +0.024
on+0.023
Neg logit contributions
ust-0.054
urious-0.043
Really-0.042
 rightful-0.042
Okay-0.042
Token a
Token ID257
Feature activation-2.42e-02

Pos logit contributions
ust+0.010
Really+0.008
 rightful+0.008
urious+0.008
Okay+0.008
Neg logit contributions
hered-0.005
rell-0.005
hed-0.005
on-0.004
iren-0.004
Token tune
Token ID14009
Feature activation+2.46e-02

Pos logit contributions
ust+0.048
Really+0.037
 rightful+0.036
Okay+0.036
 former+0.035
Neg logit contributions
rell-0.044
hered-0.043
hed-0.041
iren-0.040
irens-0.040
Token him
Token ID683
Feature activation-2.45e-02

Pos logit contributions
hered+0.013
rell+0.012
hed+0.011
iren+0.011
 crash+0.010
Neg logit contributions
ust-0.021
urious-0.017
 rightful-0.017
Really-0.017
Deal-0.016
Token.
Token ID13
Feature activation+8.98e-03

Pos logit contributions
ust+0.066
Really+0.056
Okay+0.055
 rightful+0.055
urious+0.054
Neg logit contributions
rell-0.026
hered-0.026
 on-0.025
 -0.024
hed-0.024
Token
Token ID198
Feature activation-8.68e-03

Pos logit contributions
 +0.010
rell+0.009
hered+0.008
hed+0.008
on+0.008
Neg logit contributions
ust-0.026
Really-0.021
 rightful-0.021
 former-0.021
urious-0.020
Token
Token ID198
Feature activation-1.45e-02

Pos logit contributions
ust+0.024
 rightful+0.021
 former+0.020
Really+0.020
urious+0.020
Neg logit contributions
 -0.009
hered-0.008
rell-0.008
on-0.008
hed-0.008
TokenOne
Token ID3198
Feature activation-5.26e-02

Pos logit contributions
ust+0.029
 former+0.023
 rightful+0.023
Really+0.022
urious+0.021
Neg logit contributions
 -0.025
rell-0.025
hered-0.025
on-0.024
hed-0.024
Token day
Token ID1110
Feature activation+4.89e-02

Pos logit contributions
ust+0.137
Really+0.113
 rightful+0.111
 former+0.109
urious+0.109
Neg logit contributions
hered-0.062
rell-0.060
hed-0.057
on-0.056
 on-0.056
Token,
Token ID11
Feature activation-6.27e-03

Pos logit contributions
rell+0.079
opl+0.075
hed+0.070
hered+0.068
iren+0.068
Neg logit contributions
ust-0.088
ara-0.080
Really-0.078
Okay-0.075
lly-0.071
Token his
Token ID465
Feature activation-3.80e-02

Pos logit contributions
ust+0.012
Really+0.011
Okay+0.011
Deal+0.011
 rightful+0.010
Neg logit contributions
rell-0.011
hered-0.010
hed-0.010
opl-0.009
iren-0.009
Token mum
Token ID25682
Feature activation+1.46e-02

Pos logit contributions
ust+0.082
Really+0.064
Deal+0.062
Okay+0.062
urious+0.062
Neg logit contributions
hered-0.063
rell-0.059
 gun-0.058
 on-0.058
 crash-0.056
Token said
Token ID531
Feature activation+3.93e-02

Pos logit contributions
hered+0.021
rell+0.021
hed+0.020
on+0.019
 +0.019
Neg logit contributions
ust-0.035
Really-0.028
 rightful-0.027
urious-0.027
Deal-0.027
Token they
Token ID484
Feature activation+3.18e-02

Pos logit contributions
rell+0.052
hed+0.047
hered+0.047
opl+0.044
iren+0.041
Neg logit contributions
ust-0.096
Really-0.080
Okay-0.077
Deal-0.075
 rightful-0.074
Token the
Token ID262
Feature activation+1.53e-02

Pos logit contributions
hered+0.044
rell+0.042
hed+0.042
iren+0.037
 gun+0.037
Neg logit contributions
ust-0.083
 rightful-0.070
 former-0.068
urious-0.067
Years-0.067
Token way
Token ID835
Feature activation+2.51e-02

Pos logit contributions
hed+0.024
hered+0.023
on+0.022
rell+0.022
iren+0.021
Neg logit contributions
ust-0.033
 rightful-0.028
 former-0.027
urious-0.027
Okay-0.026
Token,
Token ID11
Feature activation-6.09e-03

Pos logit contributions
rell+0.025
hered+0.024
hed+0.024
iren+0.022
irens+0.020
Neg logit contributions
ust-0.068
 rightful-0.055
urious-0.054
Okay-0.054
Really-0.053
Token Ruby
Token ID10888
Feature activation-1.28e-02

Pos logit contributions
ust+0.015
Really+0.012
 rightful+0.012
urious+0.012
Okay+0.011
Neg logit contributions
hered-0.008
rell-0.008
hed-0.008
on-0.007
iren-0.007
Token was
Token ID373
Feature activation+1.51e-04

Pos logit contributions
ust+0.030
Really+0.024
 rightful+0.023
urious+0.023
Okay+0.023
Neg logit contributions
hered-0.019
rell-0.018
hed-0.017
on-0.016
 -0.016
Token having
Token ID1719
Feature activation+4.78e-02

Pos logit contributions
rell+0.000
hered+0.000
hed+0.000
iren+0.000
 gun+0.000
Neg logit contributions
ust-0.000
 rightful-0.000
 former-0.000
Really-0.000
urious-0.000
Token so
Token ID523
Feature activation+3.03e-03

Pos logit contributions
hered+0.059
rell+0.057
hed+0.054
iren+0.053
on+0.051
Neg logit contributions
ust-0.122
 rightful-0.099
Really-0.097
 former-0.096
Okay-0.096
Token much
Token ID881
Feature activation-1.97e-02

Pos logit contributions
hered+0.004
rell+0.004
hed+0.004
 gun+0.004
iren+0.003
Neg logit contributions
ust-0.008
Really-0.006
urious-0.006
Okay-0.006
Deal-0.006
Token fun
Token ID1257
Feature activation-8.05e-05

Pos logit contributions
ust+0.030
Really+0.020
 rightful+0.020
Okay+0.020
Deal+0.019
Neg logit contributions
hered-0.044
rell-0.043
hed-0.043
on-0.041
 -0.040
Token that
Token ID326
Feature activation-2.77e-04

Pos logit contributions
ust+0.000
Really+0.000
 rightful+0.000
urious+0.000
Deal+0.000
Neg logit contributions
hered-0.000
rell-0.000
hed-0.000
 -0.000
iren-0.000
Token she
Token ID673
Feature activation-2.05e-02

Pos logit contributions
ust+0.001
Really+0.001
 rightful+0.001
Okay+0.000
urious+0.000
Neg logit contributions
hered-0.000
rell-0.000
hed-0.000
iren-0.000
on-0.000
Token her
Token ID607
Feature activation-4.35e-02

Pos logit contributions
ust+0.010
urious+0.008
Really+0.008
Okay+0.008
 rightful+0.008
Neg logit contributions
hered-0.002
rell-0.002
 -0.002
 on-0.002
on-0.002
Token over
Token ID625
Feature activation+3.65e-03

Pos logit contributions
ust+0.109
Really+0.088
urious+0.088
Okay+0.087
 rightful+0.087
Neg logit contributions
hered-0.056
rell-0.054
 on-0.053
 -0.051
hed-0.051
Token and
Token ID290
Feature activation+6.95e-03

Pos logit contributions
hered+0.004
rell+0.004
hed+0.004
on+0.004
 on+0.004
Neg logit contributions
ust-0.010
Really-0.008
 rightful-0.008
urious-0.008
Okay-0.008
Token over
Token ID625
Feature activation+1.94e-02

Pos logit contributions
hered+0.009
hed+0.008
 on+0.008
rell+0.008
 +0.008
Neg logit contributions
ust-0.018
urious-0.015
Really-0.014
 rightful-0.014
Okay-0.014
Token again
Token ID757
Feature activation-2.38e-03

Pos logit contributions
hered+0.023
 on+0.023
 +0.022
on+0.021
hed+0.021
Neg logit contributions
ust-0.053
urious-0.042
Really-0.042
Deal-0.041
 rightful-0.041
Token and
Token ID290
Feature activation+5.38e-03

Pos logit contributions
ust+0.007
urious+0.006
Really+0.006
Okay+0.006
Deal+0.006
Neg logit contributions
 on-0.002
hered-0.002
 -0.002
on-0.002
hed-0.001
Token she
Token ID673
Feature activation-1.97e-02

Pos logit contributions
hered+0.007
 on+0.007
hed+0.007
 +0.007
on+0.006
Neg logit contributions
ust-0.014
urious-0.011
 rightful-0.011
Really-0.011
Okay-0.011
Token flew
Token ID13112
Feature activation-8.81e-03

Pos logit contributions
ust+0.050
Really+0.041
urious+0.040
 rightful+0.039
Okay+0.039
Neg logit contributions
hed-0.026
hered-0.025
 -0.024
rell-0.024
on-0.024
Token off
Token ID572
Feature activation-2.07e-03

Pos logit contributions
ust+0.025
 rightful+0.020
Really+0.020
Okay+0.020
 former+0.020
Neg logit contributions
rell-0.008
hered-0.008
hed-0.008
on-0.007
iren-0.007
Token,
Token ID11
Feature activation-3.98e-02

Pos logit contributions
ust+0.004
 rightful+0.003
 former+0.003
Really+0.003
eter+0.003
Neg logit contributions
rell-0.003
hered-0.003
hed-0.003
iren-0.003
 trigger-0.003
Token leaving
Token ID4305
Feature activation-7.10e-04

Pos logit contributions
ust+0.099
Really+0.081
 rightful+0.080
Okay+0.079
 former+0.079
Neg logit contributions
rell-0.050
hered-0.050
hed-0.046
iren-0.045
on-0.043
Token drum
Token ID13026
Feature activation+3.46e-02

Pos logit contributions
ust+0.009
 rightful+0.007
urious+0.007
Okay+0.007
Really+0.007
Neg logit contributions
hered-0.006
rell-0.006
hed-0.006
on-0.006
iren-0.006
Tokenming
Token ID2229
Feature activation+2.22e-02

Pos logit contributions
hered+0.052
rell+0.051
hed+0.049
on+0.046
 +0.046
Neg logit contributions
ust-0.079
Really-0.062
 rightful-0.061
urious-0.061
Okay-0.060
Token sounded
Token ID14846
Feature activation-3.15e-02

Pos logit contributions
hered+0.032
rell+0.032
hed+0.029
iren+0.028
 +0.028
Neg logit contributions
ust-0.051
 rightful-0.040
Really-0.040
Okay-0.040
urious-0.040
Token perfect
Token ID2818
Feature activation-7.91e-03

Pos logit contributions
ust+0.072
Really+0.058
urious+0.057
 rightful+0.056
Okay+0.056
Neg logit contributions
hered-0.047
rell-0.046
hed-0.044
 -0.042
 on-0.042
Token too
Token ID1165
Feature activation+5.87e-03

Pos logit contributions
ust+0.022
Really+0.019
urious+0.018
Okay+0.018
 former+0.018
Neg logit contributions
 on-0.008
hered-0.008
hed-0.008
rell-0.007
on-0.007
Token!
Token ID0
Feature activation+4.09e-03

Pos logit contributions
hered+0.007
rell+0.007
hed+0.006
 on+0.006
 +0.006
Neg logit contributions
ust-0.015
Really-0.013
urious-0.013
Deal-0.013
 rightful-0.013
Token<|endoftext|>
Token ID50256
Feature activation+2.37e-02

Pos logit contributions
rell+0.005
 +0.005
hered+0.005
hed+0.005
on+0.005
Neg logit contributions
ust-0.010
Really-0.008
 rightful-0.008
Deal-0.008
Okay-0.008
TokenOnce
Token ID7454
Feature activation-1.64e-02

Pos logit contributions
rell+0.035
hered+0.035
 crash+0.032
hed+0.031
 gun+0.031
Neg logit contributions
ust-0.052
Really-0.042
urious-0.041
Okay-0.040
 rightful-0.040
Token there
Token ID612
Feature activation+2.41e-02

Pos logit contributions
ust+0.030
Really+0.022
 rightful+0.022
Okay+0.021
urious+0.021
Neg logit contributions
hered-0.032
rell-0.032
hed-0.031
 -0.031
on-0.030
Token was
Token ID373
Feature activation-8.10e-03

Pos logit contributions
hered+0.035
rell+0.034
hed+0.033
 +0.033
on+0.032
Neg logit contributions
ust-0.057
Really-0.045
 rightful-0.045
 former-0.045
urious-0.044
Token a
Token ID257
Feature activation-2.49e-02

Pos logit contributions
ust+0.019
urious+0.015
Really+0.015
Okay+0.014
 former+0.014
Neg logit contributions
hered-0.012
rell-0.011
iren-0.011
 crash-0.011
 gun-0.010
Token saw
Token ID2497
Feature activation-1.67e-02

Pos logit contributions
ust+0.025
Really+0.019
urious+0.019
 rightful+0.019
Okay+0.019
Neg logit contributions
hered-0.016
rell-0.016
hed-0.015
iren-0.014
 -0.014
Token a
Token ID257
Feature activation-1.10e-02

Pos logit contributions
ust+0.043
Really+0.035
 rightful+0.034
 former+0.034
urious+0.034
Neg logit contributions
hered-0.020
rell-0.020
hed-0.018
iren-0.017
 crash-0.017
Token fish
Token ID5916
Feature activation-3.63e-03

Pos logit contributions
ust+0.025
Really+0.020
 rightful+0.020
urious+0.019
Okay+0.019
Neg logit contributions
hered-0.016
rell-0.016
hed-0.016
on-0.015
 -0.015
Token swimming
Token ID14899
Feature activation-1.43e-02

Pos logit contributions
ust+0.009
urious+0.007
Really+0.007
 rightful+0.006
Deal+0.006
Neg logit contributions
rell-0.005
hered-0.005
hed-0.004
iren-0.004
 -0.004
Token around
Token ID1088
Feature activation-8.76e-04

Pos logit contributions
ust+0.034
urious+0.027
Okay+0.027
 rightful+0.026
Really+0.026
Neg logit contributions
rell-0.020
hered-0.019
 crash-0.017
hed-0.017
iren-0.017
Token in
Token ID287
Feature activation+2.24e-02

Pos logit contributions
ust+0.002
Really+0.002
 rightful+0.002
urious+0.002
Okay+0.002
Neg logit contributions
rell-0.001
hered-0.001
hed-0.001
iren-0.001
 crash-0.001
Token the
Token ID262
Feature activation+1.44e-02

Pos logit contributions
rell+0.025
hered+0.024
hed+0.023
iren+0.022
on+0.020
Neg logit contributions
ust-0.059
urious-0.049
 rightful-0.049
Really-0.049
 former-0.048
Token water
Token ID1660
Feature activation-1.88e-02

Pos logit contributions
hered+0.021
rell+0.020
hed+0.020
on+0.019
iren+0.018
Neg logit contributions
ust-0.034
 rightful-0.027
Really-0.027
urious-0.026
Okay-0.026
Token.
Token ID13
Feature activation+1.52e-02

Pos logit contributions
ust+0.045
 rightful+0.035
urious+0.035
Really+0.035
Okay+0.034
Neg logit contributions
hered-0.026
rell-0.026
hed-0.024
 crash-0.023
iren-0.023
Token Exc
Token ID25268
Feature activation-2.01e-03

Pos logit contributions
hered+0.022
rell+0.021
hed+0.020
on+0.019
iren+0.019
Neg logit contributions
ust-0.036
Really-0.029
urious-0.028
Okay-0.028
 rightful-0.028
Tokenited
Token ID863
Feature activation+6.73e-03

Pos logit contributions
ust+0.004
Really+0.003
 rightful+0.003
 former+0.003
urious+0.003
Neg logit contributions
hered-0.003
rell-0.003
hed-0.003
iren-0.003
on-0.003
Tokenya
Token ID3972
Feature activation-7.24e-03

Pos logit contributions
ust+0.098
Really+0.084
eter+0.079
 former+0.079
Okay+0.078
Neg logit contributions
 walking-0.079
 photos-0.077
 on-0.076
hed-0.075
hered-0.074
Token with
Token ID351
Feature activation+4.83e-02

Pos logit contributions
ust+0.021
Really+0.017
 rightful+0.017
urious+0.017
Okay+0.017
Neg logit contributions
hered-0.007
rell-0.007
hed-0.006
on-0.006
 -0.006
Token an
Token ID281
Feature activation-1.91e-02

Pos logit contributions
rell+0.077
hered+0.072
iren+0.070
hed+0.068
irens+0.064
Neg logit contributions
ust-0.099
 rightful-0.080
Really-0.078
urious-0.078
 former-0.076
Token ignorant
Token ID20109
Feature activation+2.10e-03

Pos logit contributions
ust+0.033
urious+0.024
 rightful+0.023
 former+0.022
asured+0.022
Neg logit contributions
hered-0.041
hed-0.038
rell-0.038
iren-0.036
 crash-0.036
Token look
Token ID804
Feature activation-1.99e-02

Pos logit contributions
hered+0.003
rell+0.003
hed+0.003
on+0.003
iren+0.003
Neg logit contributions
ust-0.005
Really-0.004
urious-0.004
 rightful-0.004
Okay-0.003
Token and
Token ID290
Feature activation+1.72e-02

Pos logit contributions
ust+0.048
urious+0.037
 rightful+0.037
Really+0.037
Deal+0.036
Neg logit contributions
rell-0.028
hered-0.027
hed-0.024
iren-0.024
 crash-0.024
Token said
Token ID531
Feature activation+1.90e-02

Pos logit contributions
hered+0.023
rell+0.023
 +0.023
hed+0.022
 on+0.022
Neg logit contributions
ust-0.042
Really-0.033
urious-0.032
Okay-0.032
 rightful-0.032
Token,
Token ID11
Feature activation-2.40e-03

Pos logit contributions
hered+0.018
rell+0.018
hed+0.016
on+0.014
iren+0.014
Neg logit contributions
ust-0.054
Really-0.045
 rightful-0.045
urious-0.044
Okay-0.044
Token "
Token ID366
Feature activation-5.38e-02

Pos logit contributions
ust+0.006
 rightful+0.005
urious+0.005
Really+0.005
Deal+0.005
Neg logit contributions
hered-0.003
rell-0.003
hed-0.003
 -0.003
on-0.003
TokenYou
Token ID1639
Feature activation-2.20e-03

Pos logit contributions
ust+0.113
 rightful+0.100
 former+0.094
asured+0.087
igor+0.086
Neg logit contributions
hed-0.082
hered-0.081
 -0.079
 on-0.075
on-0.074
Token can
Token ID460
Feature activation+7.89e-04

Pos logit contributions
ust+0.005
Really+0.004
 rightful+0.004
urious+0.004
Okay+0.004
Neg logit contributions
hered-0.003
rell-0.003
hed-0.003
on-0.003
 -0.003
Token started
Token ID2067
Feature activation-7.96e-03

Pos logit contributions
ust+0.040
 rightful+0.033
Really+0.033
 former+0.033
Deal+0.032
Neg logit contributions
hered-0.017
 on-0.016
on-0.016
 -0.016
hed-0.016
Token pushing
Token ID7796
Feature activation+1.51e-02

Pos logit contributions
ust+0.014
urious+0.011
 former+0.010
asured+0.010
 rightful+0.010
Neg logit contributions
rell-0.015
hered-0.014
hed-0.014
on-0.013
 trigger-0.013
Token buttons
Token ID12163
Feature activation+2.80e-03

Pos logit contributions
rell+0.017
hered+0.017
hed+0.016
on+0.015
iren+0.014
Neg logit contributions
ust-0.039
Really-0.032
urious-0.031
Okay-0.031
 rightful-0.031
Token and
Token ID290
Feature activation+2.08e-02

Pos logit contributions
hered+0.004
rell+0.004
hed+0.003
 +0.003
on+0.003
Neg logit contributions
ust-0.007
urious-0.005
Okay-0.005
Really-0.005
eter-0.005
Token adjusting
Token ID22000
Feature activation-1.87e-02

Pos logit contributions
rell+0.026
hered+0.026
hed+0.024
iren+0.021
on+0.021
Neg logit contributions
ust-0.050
Really-0.042
urious-0.041
Okay-0.040
 rightful-0.040
Token the
Token ID262
Feature activation+3.78e-02

Pos logit contributions
ust+0.048
Really+0.039
urious+0.039
 rightful+0.039
Okay+0.038
Neg logit contributions
hered-0.023
rell-0.022
hed-0.021
on-0.019
iren-0.019
Token settings
Token ID6460
Feature activation+2.01e-02

Pos logit contributions
hered+0.054
rell+0.049
on+0.049
hed+0.047
ez+0.044
Neg logit contributions
ust-0.083
urious-0.069
Really-0.065
Okay-0.064
 rightful-0.064
Token on
Token ID319
Feature activation+5.06e-02

Pos logit contributions
hered+0.026
rell+0.025
hed+0.024
 +0.022
iren+0.022
Neg logit contributions
ust-0.050
Really-0.040
 rightful-0.039
urious-0.039
Okay-0.039
Token the
Token ID262
Feature activation+3.39e-02

Pos logit contributions
hered+0.048
rell+0.046
hed+0.043
on+0.039
 +0.039
Neg logit contributions
ust-0.145
Really-0.120
 rightful-0.119
urious-0.118
Okay-0.117
Token television
Token ID5581
Feature activation+1.50e-02

Pos logit contributions
hered+0.046
rell+0.042
on+0.040
ez+0.040
pped+0.039
Neg logit contributions
ust-0.071
urious-0.060
 rightful-0.059
Okay-0.058
Deal-0.057
Token.
Token ID13
Feature activation+1.45e-02

Pos logit contributions
hered+0.019
rell+0.019
hed+0.018
 +0.017
on+0.017
Neg logit contributions
ust-0.038
Really-0.031
 rightful-0.030
urious-0.030
Okay-0.030
Tokenles
Token ID829
Feature activation+6.03e-04

Pos logit contributions
ust+0.061
urious+0.047
 rightful+0.046
Okay+0.046
Really+0.045
Neg logit contributions
hered-0.037
rell-0.033
on-0.033
hed-0.033
 -0.032
Token.
Token ID13
Feature activation+4.86e-03

Pos logit contributions
rell+0.001
hered+0.001
iren+0.001
hed+0.001
irens+0.001
Neg logit contributions
ust-0.001
 rightful-0.001
 former-0.001
urious-0.001
Okay-0.001
Token
Token ID198
Feature activation-1.86e-03

Pos logit contributions
hered+0.005
rell+0.004
hed+0.004
 gun+0.004
iren+0.004
Neg logit contributions
ust-0.014
Really-0.012
urious-0.011
Okay-0.011
 rightful-0.011
Token
Token ID198
Feature activation-1.12e-02

Pos logit contributions
ust+0.004
Really+0.003
urious+0.003
Okay+0.003
 rightful+0.003
Neg logit contributions
hered-0.003
rell-0.003
hed-0.003
 gun-0.003
 crash-0.002
TokenThey
Token ID2990
Feature activation+1.16e-02

Pos logit contributions
ust+0.021
Really+0.016
 rightful+0.016
urious+0.016
Okay+0.015
Neg logit contributions
hered-0.021
rell-0.021
hed-0.020
on-0.019
 -0.019
Token got
Token ID1392
Feature activation-9.56e-03

Pos logit contributions
hered+0.015
rell+0.015
iren+0.013
hed+0.013
on+0.013
Neg logit contributions
ust-0.029
Okay-0.023
Really-0.023
 rightful-0.023
urious-0.023
Token so
Token ID523
Feature activation+9.71e-03

Pos logit contributions
ust+0.023
 rightful+0.018
Okay+0.018
eter+0.017
Really+0.017
Neg logit contributions
hered-0.013
rell-0.013
opl-0.012
on-0.012
hed-0.011
Token wet
Token ID9583
Feature activation-7.37e-03

Pos logit contributions
hered+0.012
rell+0.011
hed+0.011
 +0.010
 on+0.010
Neg logit contributions
ust-0.025
Really-0.021
 rightful-0.021
urious-0.020
Deal-0.020
Token that
Token ID326
Feature activation+9.89e-03

Pos logit contributions
ust+0.019
Really+0.015
Okay+0.015
Deal+0.015
 rightful+0.015
Neg logit contributions
hered-0.008
rell-0.008
on-0.008
 -0.008
hed-0.007
Token their
Token ID511
Feature activation-2.64e-03

Pos logit contributions
rell+0.015
hered+0.015
iren+0.014
hed+0.014
on+0.013
Neg logit contributions
ust-0.022
 rightful-0.018
Really-0.017
Okay-0.017
urious-0.017
Token rain
Token ID6290
Feature activation+8.99e-03

Pos logit contributions
ust+0.006
 rightful+0.005
Really+0.005
urious+0.005
Okay+0.005
Neg logit contributions
hered-0.004
rell-0.004
hed-0.004
on-0.003
 -0.003
Token Why
Token ID4162
Feature activation-2.19e-02

Pos logit contributions
hered+0.009
rell+0.008
 +0.008
hed+0.008
on+0.008
Neg logit contributions
ust-0.015
 rightful-0.012
urious-0.012
Deal-0.012
Okay-0.012
Token are
Token ID389
Feature activation+5.74e-04

Pos logit contributions
ust+0.054
Really+0.045
 rightful+0.044
urious+0.044
 former+0.044
Neg logit contributions
rell-0.028
hered-0.027
 on-0.026
hed-0.026
 -0.026
Token you
Token ID345
Feature activation+3.05e-02

Pos logit contributions
rell+0.001
hered+0.001
 on+0.001
on+0.001
 +0.001
Neg logit contributions
ust-0.001
urious-0.001
 rightful-0.001
Really-0.001
Okay-0.001
Token so
Token ID523
Feature activation+2.42e-02

Pos logit contributions
hered+0.036
rell+0.036
hed+0.035
iren+0.030
 +0.029
Neg logit contributions
ust-0.081
urious-0.062
 former-0.061
Really-0.060
 rightful-0.060
Token worried
Token ID7960
Feature activation-1.46e-02

Pos logit contributions
hered+0.030
rell+0.030
hed+0.028
on+0.028
 +0.027
Neg logit contributions
ust-0.060
Really-0.050
 rightful-0.049
urious-0.049
Okay-0.049
Token?"
Token ID1701
Feature activation-1.51e-02

Pos logit contributions
ust+0.032
Really+0.025
 rightful+0.024
urious+0.024
Okay+0.024
Neg logit contributions
hered-0.024
rell-0.024
hed-0.023
on-0.022
 -0.022
Token
Token ID220
Feature activation-2.15e-02

Pos logit contributions
ust+0.040
Really+0.033
urious+0.032
 rightful+0.032
Okay+0.032
Neg logit contributions
hered-0.018
rell-0.017
hed-0.016
 crash-0.015
iren-0.015
Token
Token ID198
Feature activation-1.85e-02

Pos logit contributions
ust+0.058
Really+0.048
 rightful+0.048
Deal+0.048
Okay+0.047
Neg logit contributions
 -0.023
rell-0.023
hered-0.023
hed-0.021
on-0.021
Token
Token ID198
Feature activation-2.10e-02

Pos logit contributions
ust+0.047
Really+0.037
 rightful+0.037
urious+0.037
Okay+0.036
Neg logit contributions
hered-0.024
rell-0.024
hed-0.022
 -0.021
on-0.021
TokenHis
Token ID6653
Feature activation-4.47e-02

Pos logit contributions
ust+0.053
 former+0.044
 rightful+0.044
Really+0.043
Deal+0.043
Neg logit contributions
hered-0.025
 -0.024
on-0.023
rell-0.022
hed-0.022
Token mom
Token ID1995
Feature activation+2.23e-02

Pos logit contributions
ust+0.089
Really+0.067
 rightful+0.066
urious+0.065
Okay+0.065
Neg logit contributions
hered-0.082
rell-0.081
hed-0.078
on-0.074
 -0.074
Token it
Token ID340
Feature activation+9.61e-03

Pos logit contributions
ust+0.020
 rightful+0.015
Deal+0.015
urious+0.015
Really+0.015
Neg logit contributions
rell-0.015
hered-0.014
iren-0.013
hed-0.013
 crash-0.013
Token all
Token ID477
Feature activation-4.59e-03

Pos logit contributions
hered+0.014
rell+0.014
hed+0.013
on+0.012
iren+0.012
Neg logit contributions
ust-0.023
Really-0.018
 rightful-0.018
urious-0.017
Okay-0.017
Token tick
Token ID4378
Feature activation+1.02e-02

Pos logit contributions
ust+0.012
Really+0.010
 rightful+0.010
urious+0.010
Okay+0.010
Neg logit contributions
hered-0.005
rell-0.005
hed-0.005
on-0.005
 -0.005
Tokenly
Token ID306
Feature activation+6.82e-03

Pos logit contributions
hered+0.013
rell+0.013
hed+0.013
on+0.011
 +0.011
Neg logit contributions
ust-0.026
Really-0.021
 rightful-0.021
urious-0.020
Okay-0.020
Token.
Token ID13
Feature activation+2.31e-03

Pos logit contributions
hered+0.009
rell+0.009
iren+0.009
hed+0.008
 crash+0.008
Neg logit contributions
ust-0.016
urious-0.012
 rightful-0.012
 former-0.012
Really-0.012
Token That
Token ID1320
Feature activation-1.10e-02

Pos logit contributions
hered+0.003
rell+0.003
hed+0.003
 +0.002
on+0.002
Neg logit contributions
ust-0.006
Really-0.005
 rightful-0.005
urious-0.005
Okay-0.005
Token sounded
Token ID14846
Feature activation-1.72e-02

Pos logit contributions
ust+0.027
Really+0.022
 rightful+0.021
urious+0.021
Okay+0.021
Neg logit contributions
hered-0.015
rell-0.015
hed-0.014
on-0.013
 -0.013
Token like
Token ID588
Feature activation-8.07e-04

Pos logit contributions
ust+0.040
Really+0.031
 rightful+0.031
urious+0.031
Okay+0.030
Neg logit contributions
hered-0.026
rell-0.025
hed-0.024
on-0.023
 -0.023
Token lots
Token ID6041
Feature activation+8.41e-03

Pos logit contributions
ust+0.002
Really+0.002
 rightful+0.002
urious+0.002
Okay+0.002
Neg logit contributions
hered-0.001
rell-0.001
hed-0.001
on-0.001
 -0.001
Token of
Token ID286
Feature activation+7.21e-03

Pos logit contributions
hered+0.010
rell+0.010
hed+0.010
 +0.009
on+0.009
Neg logit contributions
ust-0.021
Really-0.017
 rightful-0.017
urious-0.017
Okay-0.017
Token fun
Token ID1257
Feature activation+1.38e-02

Pos logit contributions
hered+0.011
rell+0.011
hed+0.010
on+0.010
iren+0.010
Neg logit contributions
ust-0.016
Really-0.013
 rightful-0.013
urious-0.012
 former-0.012
Token home
Token ID1363
Feature activation-4.90e-02

Pos logit contributions
ust+0.003
 rightful+0.002
 former+0.002
Years+0.002
Deal+0.002
Neg logit contributions
rell-0.002
hered-0.002
hed-0.002
on-0.002
ons-0.002
Token happy
Token ID3772
Feature activation-2.72e-02

Pos logit contributions
ust+0.126
Really+0.102
urious+0.101
Okay+0.099
 rightful+0.099
Neg logit contributions
hered-0.062
rell-0.060
hed-0.057
 -0.055
 on-0.054
Token.
Token ID13
Feature activation+5.01e-03

Pos logit contributions
ust+0.077
urious+0.063
Really+0.062
Okay+0.061
 rightful+0.061
Neg logit contributions
 on-0.028
hered-0.028
hed-0.027
rell-0.026
on-0.025
Token<|endoftext|>
Token ID50256
Feature activation+2.54e-02

Pos logit contributions
hered+0.006
rell+0.006
hed+0.006
 +0.005
on+0.005
Neg logit contributions
ust-0.013
Really-0.011
 rightful-0.010
urious-0.010
Okay-0.010
TokenJake
Token ID43930
Feature activation-5.91e-03

Pos logit contributions
rell+0.039
hered+0.039
 crash+0.035
 gun+0.035
hed+0.035
Neg logit contributions
ust-0.054
Really-0.043
urious-0.042
Okay-0.041
 rightful-0.041
Token was
Token ID373
Feature activation-7.98e-03

Pos logit contributions
ust+0.015
Really+0.012
 rightful+0.012
urious+0.012
Okay+0.012
Neg logit contributions
hered-0.008
rell-0.008
hed-0.007
on-0.007
 -0.007
Token a
Token ID257
Feature activation-3.80e-02

Pos logit contributions
ust+0.019
 former+0.016
 rightful+0.015
asured+0.015
urious+0.015
Neg logit contributions
rell-0.011
hered-0.010
hed-0.010
iren-0.009
 trigger-0.009
Token naughty
Token ID45128
Feature activation-1.83e-02

Pos logit contributions
ust+0.097
urious+0.077
Really+0.075
 former+0.075
 rightful+0.075
Neg logit contributions
hered-0.045
 -0.045
 on-0.044
 crash-0.042
on-0.042
Token boy
Token ID2933
Feature activation+1.58e-02

Pos logit contributions
ust+0.040
urious+0.031
 rightful+0.031
Really+0.031
 former+0.031
Neg logit contributions
hered-0.029
rell-0.028
 on-0.028
 gun-0.027
 crash-0.027
Token.
Token ID13
Feature activation-2.58e-03

Pos logit contributions
rell+0.022
hered+0.022
hed+0.021
iren+0.020
 crash+0.019
Neg logit contributions
ust-0.037
Really-0.029
 rightful-0.029
urious-0.029
Deal-0.029
Token He
Token ID679
Feature activation-2.59e-02

Pos logit contributions
ust+0.007
Really+0.006
 rightful+0.006
 former+0.006
Deal+0.006
Neg logit contributions
 -0.003
rell-0.002
on-0.002
hed-0.002
 crash-0.002
Token,
Token ID11
Feature activation-4.11e-02

Pos logit contributions
hered+0.031
rell+0.030
hed+0.027
 +0.027
 crash+0.027
Neg logit contributions
ust-0.066
Deal-0.052
Really-0.052
Okay-0.052
 rightful-0.051
Token Tim
Token ID5045
Feature activation-1.45e-02

Pos logit contributions
ust+0.097
 rightful+0.077
urious+0.076
Really+0.076
 former+0.074
Neg logit contributions
rell-0.059
hered-0.059
hed-0.055
 -0.055
on-0.054
Tokenmy
Token ID1820
Feature activation-2.14e-03

Pos logit contributions
ust+0.039
Really+0.033
 former+0.032
 rightful+0.032
Okay+0.031
Neg logit contributions
rell-0.016
hered-0.015
hed-0.014
 -0.014
on-0.014
Token!
Token ID0
Feature activation-3.59e-03

Pos logit contributions
ust+0.006
Really+0.005
 former+0.005
urious+0.005
 rightful+0.005
Neg logit contributions
hered-0.002
rell-0.002
hed-0.002
 on-0.002
on-0.002
Token Want
Token ID16168
Feature activation-1.32e-02

Pos logit contributions
ust+0.008
Really+0.006
Okay+0.006
 rightful+0.006
urious+0.006
Neg logit contributions
hered-0.006
rell-0.005
hed-0.005
iren-0.005
on-0.005
Token some
Token ID617
Feature activation-9.15e-03

Pos logit contributions
ust+0.027
Really+0.021
urious+0.020
Okay+0.020
 rightful+0.020
Neg logit contributions
hered-0.023
hed-0.022
rell-0.021
iren-0.020
 crash-0.020
Token?"
Token ID1701
Feature activation-9.28e-03

Pos logit contributions
ust+0.019
Really+0.015
 rightful+0.015
Okay+0.015
urious+0.015
Neg logit contributions
hered-0.015
rell-0.015
hed-0.014
 -0.013
iren-0.013
Token replied
Token ID8712
Feature activation-2.76e-03

Pos logit contributions
ust+0.020
Really+0.015
 rightful+0.015
urious+0.015
Okay+0.015
Neg logit contributions
hered-0.015
rell-0.015
hed-0.015
iren-0.014
on-0.014
Token Lily
Token ID20037
Feature activation-4.79e-03

Pos logit contributions
ust+0.005
 rightful+0.004
Really+0.004
Okay+0.003
urious+0.003
Neg logit contributions
rell-0.005
hed-0.005
hered-0.005
iren-0.005
 crash-0.005
Token.
Token ID13
Feature activation+1.28e-02

Pos logit contributions
ust+0.011
 rightful+0.008
urious+0.008
Really+0.008
Okay+0.008
Neg logit contributions
rell-0.007
hered-0.007
hed-0.007
iren-0.007
irens-0.007
Token
Token ID220
Feature activation-1.04e-02

Pos logit contributions
hered+0.015
rell+0.014
hed+0.014
lers+0.014
 photos+0.013
Neg logit contributions
ust-0.030
Really-0.027
Okay-0.026
Deal-0.025
urious-0.024
Token excited
Token ID6568
Feature activation-1.47e-02

Pos logit contributions
ust+0.007
 rightful+0.006
Really+0.006
urious+0.006
 former+0.006
Neg logit contributions
hered-0.004
rell-0.004
hed-0.004
iren-0.003
 gun-0.003
Token.
Token ID13
Feature activation-2.92e-03

Pos logit contributions
ust+0.039
Really+0.033
 rightful+0.032
Okay+0.032
urious+0.032
Neg logit contributions
hered-0.017
rell-0.016
hed-0.015
 -0.015
 on-0.015
Token She
Token ID1375
Feature activation-2.80e-02

Pos logit contributions
ust+0.008
Deal+0.007
 rightful+0.007
 former+0.006
Really+0.006
Neg logit contributions
 -0.003
rell-0.003
hed-0.003
 on-0.003
hered-0.003
Token said
Token ID531
Feature activation+3.16e-02

Pos logit contributions
ust+0.073
 rightful+0.060
Really+0.059
 former+0.058
Deal+0.057
Neg logit contributions
hed-0.034
 -0.034
hered-0.033
 on-0.032
on-0.032
Token,
Token ID11
Feature activation+9.05e-03

Pos logit contributions
hered+0.021
rell+0.021
hed+0.018
iren+0.016
on+0.015
Neg logit contributions
ust-0.098
Really-0.083
 rightful-0.082
Okay-0.082
urious-0.081
Token "
Token ID366
Feature activation-5.43e-02

Pos logit contributions
hered+0.013
rell+0.013
hed+0.012
iren+0.011
on+0.011
Neg logit contributions
ust-0.021
Really-0.017
Okay-0.017
 rightful-0.016
urious-0.016
TokenCan
Token ID6090
Feature activation-1.99e-02

Pos logit contributions
ust+0.114
 rightful+0.091
 former+0.088
urious+0.082
asured+0.079
Neg logit contributions
hered-0.092
hed-0.091
 -0.091
rell-0.089
on-0.087
Token I
Token ID314
Feature activation+1.67e-04

Pos logit contributions
ust+0.046
urious+0.037
 former+0.036
 rightful+0.036
Deal+0.034
Neg logit contributions
 -0.030
hered-0.030
on-0.029
rell-0.029
 on-0.029
Token help
Token ID1037
Feature activation-7.92e-03

Pos logit contributions
hered+0.000
rell+0.000
on+0.000
hed+0.000
 +0.000
Neg logit contributions
ust-0.000
Really-0.000
urious-0.000
 rightful-0.000
Okay-0.000
Token you
Token ID345
Feature activation+4.59e-03

Pos logit contributions
ust+0.018
Really+0.014
 rightful+0.014
urious+0.014
Okay+0.014
Neg logit contributions
hered-0.012
rell-0.012
hed-0.012
on-0.011
 -0.011
Token cut
Token ID2005
Feature activation-1.17e-02

Pos logit contributions
hered+0.008
rell+0.008
hed+0.007
on+0.007
 on+0.007
Neg logit contributions
ust-0.010
Really-0.008
 rightful-0.007
Okay-0.007
urious-0.007
Token outside
Token ID2354
Feature activation-1.81e-02

Pos logit contributions
rell+0.024
hered+0.024
hed+0.022
 +0.021
iren+0.021
Neg logit contributions
ust-0.036
Really-0.029
Deal-0.029
Okay-0.028
urious-0.028
Token in
Token ID287
Feature activation+1.62e-02

Pos logit contributions
ust+0.036
urious+0.028
 rightful+0.028
Deal+0.027
Really+0.027
Neg logit contributions
hered-0.032
rell-0.032
hed-0.029
iren-0.029
 crash-0.027
Token the
Token ID262
Feature activation+4.72e-03

Pos logit contributions
hered+0.018
rell+0.017
hed+0.017
iren+0.014
 gun+0.014
Neg logit contributions
ust-0.043
 rightful-0.036
urious-0.036
Really-0.035
Okay-0.034
Token sun
Token ID4252
Feature activation-1.25e-02

Pos logit contributions
hered+0.007
rell+0.007
hed+0.007
 +0.006
on+0.006
Neg logit contributions
ust-0.011
Really-0.009
 rightful-0.008
urious-0.008
Okay-0.008
Token.
Token ID13
Feature activation+9.80e-03

Pos logit contributions
ust+0.028
 rightful+0.022
urious+0.022
Really+0.022
Okay+0.021
Neg logit contributions
hered-0.019
rell-0.018
hed-0.017
iren-0.017
 crash-0.016
Token One
Token ID1881
Feature activation-5.55e-02

Pos logit contributions
hered+0.014
rell+0.013
hed+0.012
on+0.012
iren+0.012
Neg logit contributions
ust-0.024
Really-0.019
 rightful-0.019
urious-0.019
Okay-0.019
Token day
Token ID1110
Feature activation+3.90e-02

Pos logit contributions
ust+0.142
Really+0.116
 rightful+0.114
urious+0.113
Deal+0.112
Neg logit contributions
hered-0.069
rell-0.068
hed-0.064
on-0.061
 -0.061
Token,
Token ID11
Feature activation-1.35e-02

Pos logit contributions
rell+0.050
ishly+0.040
opl+0.039
hered+0.038
lers+0.038
Neg logit contributions
ust-0.093
Okay-0.083
Really-0.082
ara-0.080
Deal-0.076
Token he
Token ID339
Feature activation-3.29e-02

Pos logit contributions
ust+0.028
Really+0.024
Okay+0.024
Deal+0.022
 rightful+0.022
Neg logit contributions
rell-0.023
hered-0.021
hed-0.020
iren-0.019
lers-0.019
Token walked
Token ID6807
Feature activation+1.77e-03

Pos logit contributions
ust+0.078
Really+0.062
 rightful+0.061
Deal+0.061
urious+0.060
Neg logit contributions
hered-0.048
rell-0.046
hed-0.045
 on-0.042
 -0.042
Token over
Token ID625
Feature activation+5.31e-03

Pos logit contributions
rell+0.002
hered+0.002
hed+0.002
on+0.002
 crash+0.002
Neg logit contributions
ust-0.004
Okay-0.003
 rightful-0.003
urious-0.003
Really-0.003
Token shiny
Token ID22441
Feature activation-5.41e-03

Pos logit contributions
hered+0.026
hed+0.024
rell+0.024
iren+0.022
on+0.021
Neg logit contributions
ust-0.039
Really-0.032
 rightful-0.031
Okay-0.031
Deal-0.030
Token.
Token ID13
Feature activation+1.66e-02

Pos logit contributions
ust+0.014
Really+0.011
 rightful+0.011
urious+0.011
Okay+0.011
Neg logit contributions
hered-0.007
rell-0.007
hed-0.006
on-0.006
 -0.006
Token
Token ID220
Feature activation-1.29e-02

Pos logit contributions
hered+0.019
rell+0.019
hed+0.018
 +0.017
on+0.017
Neg logit contributions
ust-0.044
Really-0.036
 rightful-0.035
urious-0.035
Okay-0.035
Token
Token ID198
Feature activation-9.03e-03

Pos logit contributions
ust+0.035
Really+0.030
 rightful+0.030
Okay+0.030
 former+0.030
Neg logit contributions
 -0.013
rell-0.013
hered-0.012
on-0.012
hed-0.012
Token
Token ID198
Feature activation-1.41e-02

Pos logit contributions
ust+0.024
 rightful+0.020
Really+0.020
 former+0.019
urious+0.019
Neg logit contributions
hered-0.010
 -0.010
rell-0.010
hed-0.009
on-0.009
TokenOne
Token ID3198
Feature activation-5.67e-02

Pos logit contributions
ust+0.027
 rightful+0.020
Really+0.020
 former+0.020
urious+0.020
Neg logit contributions
hered-0.026
rell-0.026
hed-0.025
 -0.025
on-0.024
Token day
Token ID1110
Feature activation+3.75e-02

Pos logit contributions
ust+0.152
Really+0.126
 rightful+0.123
Deal+0.122
Okay+0.121
Neg logit contributions
hered-0.063
rell-0.062
 on-0.059
on-0.058
hed-0.058
Token,
Token ID11
Feature activation-1.44e-02

Pos logit contributions
rell+0.051
hered+0.045
opl+0.044
hed+0.043
iren+0.041
Neg logit contributions
ust-0.082
Really-0.075
Okay-0.071
ara-0.068
Deal-0.068
Token the
Token ID262
Feature activation+8.46e-03

Pos logit contributions
ust+0.035
Really+0.031
Okay+0.029
Deal+0.029
 rightful+0.028
Neg logit contributions
rell-0.019
hered-0.018
hed-0.017
iren-0.016
opl-0.014
Token boy
Token ID2933
Feature activation+1.90e-02

Pos logit contributions
hered+0.018
rell+0.018
hed+0.017
 +0.017
on+0.017
Neg logit contributions
ust-0.014
Really-0.010
 rightful-0.010
urious-0.009
Deal-0.009
Token found
Token ID1043
Feature activation-2.42e-02

Pos logit contributions
hered+0.028
rell+0.027
hed+0.026
on+0.025
 +0.025
Neg logit contributions
ust-0.045
Really-0.036
 rightful-0.035
Deal-0.034
urious-0.034
Token a
Token ID257
Feature activation-4.96e-03

Pos logit contributions
ust+0.000
 rightful+0.000
 former+0.000
Really+0.000
urious+0.000
Neg logit contributions
hered-0.000
rell-0.000
hed-0.000
iren-0.000
irens-0.000
Token friend
Token ID1545
Feature activation+2.72e-02

Pos logit contributions
ust+0.010
Really+0.008
urious+0.008
Okay+0.007
 rightful+0.007
Neg logit contributions
hered-0.009
rell-0.008
hed-0.008
 -0.008
 on-0.008
Token.
Token ID13
Feature activation+1.42e-02

Pos logit contributions
hered+0.037
rell+0.037
hed+0.035
iren+0.033
on+0.033
Neg logit contributions
ust-0.066
 rightful-0.052
Really-0.052
urious-0.052
Deal-0.051
Token So
Token ID1406
Feature activation+1.65e-02

Pos logit contributions
 +0.016
rell+0.014
hered+0.013
hed+0.011
on+0.011
Neg logit contributions
ust-0.041
 former-0.033
 rightful-0.033
Really-0.033
urious-0.033
Token,
Token ID11
Feature activation+6.64e-03

Pos logit contributions
hered+0.018
rell+0.018
hed+0.017
iren+0.016
irens+0.014
Neg logit contributions
ust-0.044
Really-0.038
 rightful-0.037
Deal-0.037
Okay-0.037
Token one
Token ID530
Feature activation-5.60e-02

Pos logit contributions
rell+0.012
hered+0.012
hed+0.011
iren+0.010
opl+0.010
Neg logit contributions
ust-0.013
Really-0.011
Okay-0.010
Deal-0.010
 rightful-0.010
Token day
Token ID1110
Feature activation+5.33e-02

Pos logit contributions
ust+0.152
Really+0.126
 rightful+0.125
 former+0.125
Deal+0.123
Neg logit contributions
hered-0.059
 on-0.056
rell-0.055
on-0.055
 -0.053
Token he
Token ID339
Feature activation-2.82e-02

Pos logit contributions
rell+0.066
hed+0.062
hered+0.060
iren+0.056
opl+0.055
Neg logit contributions
ust-0.131
Really-0.113
Okay-0.108
 rightful-0.105
Deal-0.104
Token decided
Token ID3066
Feature activation-6.08e-03

Pos logit contributions
ust+0.076
Really+0.064
Deal+0.062
 former+0.061
 rightful+0.061
Neg logit contributions
hered-0.032
 on-0.032
 gun-0.031
 -0.029
hed-0.029
Token to
Token ID284
Feature activation-5.51e-03

Pos logit contributions
ust+0.015
Really+0.012
urious+0.012
 rightful+0.012
Okay+0.012
Neg logit contributions
hered-0.008
rell-0.008
hed-0.007
 -0.007
 on-0.007
Token go
Token ID467
Feature activation-5.38e-04

Pos logit contributions
ust+0.013
Really+0.010
Deal+0.010
urious+0.010
Okay+0.010
Neg logit contributions
hered-0.009
rell-0.008
 -0.008
 crash-0.008
hed-0.008
Token bloom
Token ID29955
Feature activation-3.77e-02

Pos logit contributions
hered+0.011
rell+0.011
hed+0.010
iren+0.009
 +0.009
Neg logit contributions
ust-0.018
Really-0.015
 rightful-0.014
urious-0.014
Deal-0.014
Tokened
Token ID276
Feature activation-1.47e-02

Pos logit contributions
ust+0.108
Really+0.090
 rightful+0.089
urious+0.089
Okay+0.088
Neg logit contributions
hered-0.035
rell-0.034
hed-0.032
on-0.029
 -0.029
Token and
Token ID290
Feature activation+1.59e-02

Pos logit contributions
ust+0.038
Really+0.031
 rightful+0.031
urious+0.031
Okay+0.030
Neg logit contributions
hered-0.017
rell-0.017
hed-0.016
on-0.015
 -0.015
Token the
Token ID262
Feature activation+2.37e-02

Pos logit contributions
hered+0.023
rell+0.022
iren+0.021
hed+0.021
irens+0.020
Neg logit contributions
ust-0.036
Really-0.030
 rightful-0.030
 former-0.029
Okay-0.028
Token carrots
Token ID34397
Feature activation+7.13e-03

Pos logit contributions
hered+0.033
rell+0.032
hed+0.031
 +0.029
on+0.029
Neg logit contributions
ust-0.057
Really-0.046
 rightful-0.045
urious-0.045
Okay-0.044
Token grew
Token ID6348
Feature activation-5.75e-02

Pos logit contributions
hered+0.009
rell+0.009
hed+0.009
iren+0.008
 +0.008
Neg logit contributions
ust-0.017
Really-0.014
 rightful-0.014
Deal-0.014
urious-0.014
Token big
Token ID1263
Feature activation+5.37e-03

Pos logit contributions
ust+0.140
 rightful+0.110
Really+0.110
urious+0.110
 former+0.108
Neg logit contributions
hered-0.080
rell-0.077
hed-0.074
on-0.070
iren-0.070
Token.
Token ID13
Feature activation+7.14e-03

Pos logit contributions
hered+0.006
rell+0.006
hed+0.006
on+0.006
iren+0.005
Neg logit contributions
ust-0.014
Really-0.011
 rightful-0.011
urious-0.011
Okay-0.011
Token And
Token ID843
Feature activation-1.40e-02

Pos logit contributions
hered+0.011
iren+0.010
rell+0.010
hed+0.010
 falling+0.010
Neg logit contributions
ust-0.016
Really-0.013
 former-0.013
 rightful-0.012
Okay-0.012
Token Benny
Token ID44275
Feature activation-1.38e-02

Pos logit contributions
ust+0.033
Really+0.026
 rightful+0.026
Okay+0.026
urious+0.026
Neg logit contributions
hered-0.020
rell-0.020
hed-0.019
iren-0.018
on-0.018
Token was
Token ID373
Feature activation+3.49e-03

Pos logit contributions
ust+0.030
Really+0.023
 rightful+0.023
urious+0.023
Deal+0.023
Neg logit contributions
hered-0.022
rell-0.022
hed-0.020
iren-0.020
on-0.020