TOP ACTIVATIONS
MAX = 0.085

of cheese and sauce and topp ings . The people who
monkeys and elephants and gir aff es . They were very
the air . Lily and True think he is crazy .
sund ae with lots of topp ings . Tim my was
, sauce , cheese and topp ings . She showed them
monkeys and elephants and gir aff es . They had fun
monkeys and elephants and gir aff es , too . They
lions and elephants and gir aff es . Anna was very
lions and monkeys and gir aff es . They
water . The mer maid smiled at Melody .
castle so much . The mer maid said , " I
their tank . The bad guys run away and Ben and
" Free mel on . Enjoy !" They were happy .
in the sea that the mer maid carefully chose . It
faces and shapes with the topp ings . "
ashes . They laugh and g iggle . They feel the
're welcome , kids ! Enjoy the show !"
anas available for feeding the gor illas ." She said to
One day , Sara and Coco go to the park with
S ki pping mer rily along , Hawk came

MIN ACTIVATIONS
MIN = -0.080

and said " thank you " to her mom my for
understand what " mod est " meant , but he was
would whisper " thank you " to whoever put it there
he said " thank you " to his mom .
know what " mod est " meant , but he knew
a big " thank you " and smiled . Mama p
about who has the sh ini est gem or the best
really understand what " value " meant , but he knew
understanding now what " repeat " meant . <|endoftext|> Once upon
, " You 're welcome " before returning to his stable
for explaining what " trade " meant . From that day
and said " thank you " to its friends . The
remembered to say " please " whenever she wanted something .
He said " thank you " to Tina and told her
He even said " sorry " when he didn 't mean
and put on her sh ini est shoes .
Mia said " thank you " for the fun she was
wanted to say " hello " too , so he ran
boy said " thank you " and Lily felt good for
't know what " sort " meant , but his mom

INTERVAL 0.044 - 0.085
CONTAINS 0.239%

L ily and Tom are scared . They drop
The bird noticed Lucy and ch ir ped at her .
did something very special and everyone started to applaud him .
S ara and Ben are scared . They do
m ak r ut and pand an and curry leaf and

INTERVAL 0.002 - 0.044
CONTAINS 42.186%

and Rod went to the park . They saw a big
a little girl named Sue . They loved to play and
to touch it . " Tom , no ,
dog for a walk . He also played in his bedroom
It was huge , and Red could tell it was a

INTERVAL -0.039 - 0.002
CONTAINS 57.172%

buy some candy . Lily saw a big red l oll
blanket and Lily 's sandwich . She was upset and started
away his cubes and went to bed with his favorite cube
. <|endoftext|> One day , there was a little girl named
Tom â € ™ s mum heard him complaining

INTERVAL -0.080 - -0.039
CONTAINS 0.402%

." Anna smiled and said , " I 'm
silly idea . He thought it would be fun to come
apple . It looked juicy and sweet . Tom said ,
L ily was happy that she used her words and made
the yellow boat . From then on , the island stayed
Token of
Token ID286
Feature activation+3.65e-03

Pos logit contributions
wheel+0.015
 sill+0.015
hot+0.013
 aback+0.013
icle+0.012
Neg logit contributions
ls-0.042
cks-0.040
 vows-0.040
irs-0.037
 nations-0.037
Token cheese
Token ID9891
Feature activation+3.18e-03

Pos logit contributions
ls+0.007
cks+0.006
 vows+0.006
ves+0.006
irs+0.005
Neg logit contributions
 sill-0.006
 operation-0.005
 cleaner-0.005
 aback-0.005
wheel-0.005
Token and
Token ID290
Feature activation-1.59e-03

Pos logit contributions
ls+0.007
cks+0.006
 vows+0.006
irs+0.006
 nations+0.006
Neg logit contributions
wheel-0.004
 sill-0.004
hot-0.004
icle-0.004
bar-0.004
Token sauce
Token ID10746
Feature activation+3.06e-03

Pos logit contributions
 sill+0.002
wheel+0.002
hot+0.002
 cleaner+0.002
icle+0.002
Neg logit contributions
ls-0.003
cks-0.003
irs-0.003
 vows-0.003
its-0.003
Token and
Token ID290
Feature activation+6.10e-03

Pos logit contributions
ls+0.006
cks+0.006
irs+0.006
 vows+0.006
 nations+0.005
Neg logit contributions
wheel-0.004
 sill-0.004
hot-0.004
icle-0.004
bar-0.004
Token topp
Token ID23126
Feature activation+8.50e-02

Pos logit contributions
ls+0.013
irs+0.012
cks+0.012
 vows+0.012
ves+0.011
Neg logit contributions
 sill-0.008
wheel-0.007
 cleaner-0.007
hot-0.007
 vest-0.007
Tokenings
Token ID654
Feature activation+2.03e-02

Pos logit contributions
irs+0.141
ls+0.140
 nations+0.134
 arrest+0.127
 risking+0.127
Neg logit contributions
est-0.132
icle-0.132
 sill-0.121
bar-0.115
uit-0.113
Token.
Token ID13
Feature activation+1.80e-02

Pos logit contributions
ls+0.039
cks+0.036
 vows+0.035
irs+0.033
 nations+0.033
Neg logit contributions
hot-0.032
wheel-0.029
 sill-0.029
icle-0.028
uit-0.027
Token The
Token ID383
Feature activation+9.86e-03

Pos logit contributions
ls+0.029
cks+0.027
 vows+0.026
irs+0.024
ves+0.024
Neg logit contributions
wheel-0.033
 sill-0.031
hot-0.030
uster-0.030
 aback-0.030
Token people
Token ID661
Feature activation+4.38e-02

Pos logit contributions
ls+0.018
cks+0.016
 vows+0.016
irs+0.015
ves+0.015
Neg logit contributions
wheel-0.016
 sill-0.016
hot-0.015
icle-0.015
uster-0.015
Token who
Token ID508
Feature activation+3.53e-02

Pos logit contributions
ls+0.080
 vows+0.074
irs+0.072
cks+0.072
ves+0.069
Neg logit contributions
wheel-0.068
hot-0.064
 sill-0.063
he-0.060
boat-0.058
Token monkeys
Token ID26697
Feature activation+4.37e-02

Pos logit contributions
ls+0.029
irs+0.028
cks+0.028
its+0.027
 vows+0.027
Neg logit contributions
 sill-0.023
wheel-0.022
 3-0.021
 bear-0.020
my-0.020
Token and
Token ID290
Feature activation+2.64e-02

Pos logit contributions
ls+0.100
 vows+0.099
irs+0.098
heit+0.091
cks+0.091
Neg logit contributions
 sill-0.047
wheel-0.046
hot-0.042
bar-0.040
my-0.038
Token elephants
Token ID25368
Feature activation+4.92e-02

Pos logit contributions
ls+0.048
irs+0.047
cks+0.046
 vows+0.045
its+0.045
Neg logit contributions
 sill-0.042
wheel-0.040
 3-0.037
 vest-0.036
hot-0.036
Token and
Token ID290
Feature activation+2.31e-02

Pos logit contributions
ls+0.106
 vows+0.102
irs+0.102
cks+0.097
heit+0.097
Neg logit contributions
 sill-0.061
wheel-0.060
hot-0.056
bar-0.052
my-0.049
Token gir
Token ID37370
Feature activation+5.36e-02

Pos logit contributions
ls+0.042
irs+0.040
cks+0.039
 vows+0.038
its+0.038
Neg logit contributions
 sill-0.038
wheel-0.035
 vest-0.032
 3-0.032
hot-0.032
Tokenaff
Token ID2001
Feature activation+8.17e-02

Pos logit contributions
 vows+0.078
cks+0.077
ls+0.077
 spills+0.075
irs+0.074
Neg logit contributions
 sill-0.087
wheel-0.086
est-0.084
hot-0.082
bar-0.082
Tokenes
Token ID274
Feature activation+2.93e-02

Pos logit contributions
 passports+0.143
 vows+0.137
 spills+0.134
heit+0.133
 hides+0.127
Neg logit contributions
ah-0.109
bird-0.104
my-0.104
ter-0.100
est-0.099
Token.
Token ID13
Feature activation+2.56e-02

Pos logit contributions
ls+0.061
cks+0.058
 vows+0.057
irs+0.057
heit+0.054
Neg logit contributions
 sill-0.038
wheel-0.037
hot-0.036
uit-0.032
est-0.032
Token They
Token ID1119
Feature activation+3.27e-02

Pos logit contributions
ls+0.042
cks+0.038
 vows+0.037
ils+0.034
irs+0.034
Neg logit contributions
 sill-0.047
wheel-0.046
hot-0.045
icle-0.043
uster-0.043
Token were
Token ID547
Feature activation+7.44e-03

Pos logit contributions
ls+0.063
irs+0.061
cks+0.060
 vows+0.056
its+0.055
Neg logit contributions
wheel-0.048
 sill-0.048
my-0.044
hot-0.043
 happiest-0.041
Token very
Token ID845
Feature activation+1.77e-02

Pos logit contributions
ls+0.016
 vows+0.015
irs+0.015
cks+0.014
ves+0.014
Neg logit contributions
 sill-0.010
wheel-0.009
 happiest-0.008
hot-0.008
bar-0.008
Token the
Token ID262
Feature activation-6.01e-03

Pos logit contributions
ls+0.058
 vows+0.053
cks+0.052
ves+0.049
irs+0.048
Neg logit contributions
 sill-0.043
wheel-0.040
hot-0.040
 aback-0.039
 vest-0.038
Token air
Token ID1633
Feature activation+1.59e-02

Pos logit contributions
wheel+0.010
hot+0.009
icle+0.009
uster+0.009
 sill+0.009
Neg logit contributions
ls-0.011
cks-0.010
 runs-0.010
 vows-0.010
 nations-0.010
Token.
Token ID13
Feature activation+1.01e-02

Pos logit contributions
ls+0.030
cks+0.027
 vows+0.026
irs+0.026
ves+0.025
Neg logit contributions
 sill-0.026
wheel-0.026
hot-0.024
icle-0.023
bar-0.023
Token Lily
Token ID20037
Feature activation+1.75e-02

Pos logit contributions
ls+0.021
cks+0.019
 vows+0.019
ves+0.018
irs+0.018
Neg logit contributions
wheel-0.014
 sill-0.013
hot-0.013
uster-0.012
icle-0.012
Token and
Token ID290
Feature activation+1.02e-02

Pos logit contributions
irs+0.040
ls+0.040
cks+0.040
ves+0.039
 vows+0.038
Neg logit contributions
wheel-0.017
 sill-0.017
 aback-0.016
my-0.016
 vest-0.016
Token True
Token ID6407
Feature activation+8.15e-02

Pos logit contributions
ls+0.023
cks+0.022
 vows+0.021
irs+0.020
ves+0.020
Neg logit contributions
 sill-0.011
wheel-0.011
hot-0.011
 aback-0.011
 Vest-0.010
Token think
Token ID892
Feature activation+2.49e-02

Pos logit contributions
ls+0.175
ves+0.166
irs+0.164
cks+0.158
 pulp+0.146
Neg logit contributions
 sill-0.097
hot-0.095
wheel-0.095
 expert-0.093
 3-0.092
Token he
Token ID339
Feature activation-4.45e-03

Pos logit contributions
cks+0.048
ls+0.046
 vows+0.043
irs+0.043
 cor+0.041
Neg logit contributions
hot-0.035
wheel-0.035
 sill-0.033
 operation-0.032
 vest-0.032
Token is
Token ID318
Feature activation+8.49e-03

Pos logit contributions
wheel+0.008
 sill+0.008
hot+0.008
 Vest+0.008
 vest+0.008
Neg logit contributions
ls-0.007
cks-0.006
 vows-0.006
irs-0.006
ves-0.006
Token crazy
Token ID7165
Feature activation-4.06e-03

Pos logit contributions
ls+0.019
 vows+0.017
ves+0.016
cks+0.016
irs+0.016
Neg logit contributions
wheel-0.011
 sill-0.011
hot-0.010
 happiest-0.010
 Vest-0.010
Token.
Token ID13
Feature activation+4.50e-03

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.006
 aback+0.006
est+0.006
Neg logit contributions
ls-0.008
cks-0.007
 vows-0.007
irs-0.007
ves-0.007
Token sund
Token ID37437
Feature activation+1.75e-02

Pos logit contributions
ls+0.014
 vows+0.013
cks+0.012
 cor+0.012
ves+0.012
Neg logit contributions
uster-0.011
 aback-0.011
wheel-0.011
 Vest-0.011
 sill-0.010
Tokenae
Token ID3609
Feature activation+1.62e-02

Pos logit contributions
ls+0.030
 vows+0.029
ves+0.029
cks+0.028
ils+0.027
Neg logit contributions
 aback-0.028
wheel-0.027
hot-0.026
 sill-0.026
 Vest-0.025
Token with
Token ID351
Feature activation+2.28e-02

Pos logit contributions
ls+0.031
cks+0.029
 vows+0.028
irs+0.027
ves+0.026
Neg logit contributions
wheel-0.025
 sill-0.024
hot-0.023
icle-0.022
uster-0.022
Token lots
Token ID6041
Feature activation+1.11e-02

Pos logit contributions
ls+0.050
cks+0.046
ves+0.043
 vows+0.043
 nations+0.043
Neg logit contributions
 sill-0.030
wheel-0.029
hot-0.029
icle-0.028
bar-0.027
Token of
Token ID286
Feature activation+1.96e-02

Pos logit contributions
ls+0.029
cks+0.028
 vows+0.027
irs+0.026
 nations+0.026
Neg logit contributions
wheel-0.009
 sill-0.009
hot-0.008
icle-0.007
est-0.007
Token topp
Token ID23126
Feature activation+8.08e-02

Pos logit contributions
ls+0.041
cks+0.040
 nations+0.037
irs+0.037
 vows+0.036
Neg logit contributions
 sill-0.026
wheel-0.025
icle-0.024
est-0.024
 cleaner-0.023
Tokenings
Token ID654
Feature activation+4.34e-03

Pos logit contributions
ls+0.146
irs+0.141
 nations+0.140
cks+0.134
 countries+0.127
Neg logit contributions
icle-0.126
est-0.121
 sill-0.116
uit-0.111
bar-0.108
Token.
Token ID13
Feature activation+3.67e-03

Pos logit contributions
ls+0.007
cks+0.007
 vows+0.006
ves+0.006
irs+0.006
Neg logit contributions
wheel-0.008
 sill-0.007
uster-0.007
 aback-0.007
hot-0.007
Token Tim
Token ID5045
Feature activation-1.36e-02

Pos logit contributions
ls+0.007
cks+0.006
 vows+0.006
irs+0.006
 runs+0.006
Neg logit contributions
wheel-0.005
 sill-0.005
uster-0.005
hot-0.005
 Vest-0.005
Tokenmy
Token ID1820
Feature activation+2.37e-02

Pos logit contributions
wheel+0.013
uster+0.013
hot+0.012
 sill+0.012
 aback+0.010
Neg logit contributions
ls-0.032
cks-0.032
 runs-0.031
ils-0.030
its-0.030
Token was
Token ID373
Feature activation+2.26e-03

Pos logit contributions
ls+0.044
cks+0.041
irs+0.040
 vows+0.038
 nations+0.037
Neg logit contributions
wheel-0.038
 sill-0.037
hot-0.035
 vest-0.034
est-0.034
Token,
Token ID11
Feature activation-1.64e-02

Pos logit contributions
ls+0.015
cks+0.013
 vows+0.013
ves+0.012
 nations+0.012
Neg logit contributions
wheel-0.013
 sill-0.012
uster-0.012
hot-0.011
 Vest-0.011
Token sauce
Token ID10746
Feature activation+8.69e-03

Pos logit contributions
wheel+0.027
 sill+0.026
uster+0.026
hot+0.025
 aback+0.025
Neg logit contributions
ls-0.029
cks-0.026
 vows-0.026
ves-0.024
 points-0.024
Token,
Token ID11
Feature activation+4.94e-03

Pos logit contributions
ls+0.018
cks+0.018
 vows+0.017
irs+0.017
 nations+0.016
Neg logit contributions
wheel-0.011
 sill-0.011
hot-0.011
icle-0.010
bar-0.010
Token cheese
Token ID9891
Feature activation+2.11e-02

Pos logit contributions
ls+0.010
cks+0.009
 vows+0.009
irs+0.008
ves+0.008
Neg logit contributions
wheel-0.007
 sill-0.007
hot-0.007
uster-0.006
 aback-0.006
Token and
Token ID290
Feature activation+7.90e-03

Pos logit contributions
ls+0.046
cks+0.044
 vows+0.042
irs+0.042
 nations+0.040
Neg logit contributions
wheel-0.025
 sill-0.025
hot-0.024
icle-0.023
bar-0.022
Token topp
Token ID23126
Feature activation+8.04e-02

Pos logit contributions
ls+0.017
cks+0.016
 vows+0.015
irs+0.015
ves+0.014
Neg logit contributions
 sill-0.011
wheel-0.011
hot-0.010
icle-0.010
bar-0.010
Tokenings
Token ID654
Feature activation+1.95e-02

Pos logit contributions
ls+0.132
irs+0.128
 nations+0.124
 boarding+0.120
 arrest+0.118
Neg logit contributions
icle-0.132
est-0.131
 sill-0.124
hot-0.117
uit-0.115
Token.
Token ID13
Feature activation+1.00e-02

Pos logit contributions
ls+0.036
cks+0.033
 vows+0.032
 nations+0.030
irs+0.030
Neg logit contributions
wheel-0.032
hot-0.031
 sill-0.031
icle-0.029
 aback-0.028
Token She
Token ID1375
Feature activation+6.83e-03

Pos logit contributions
ls+0.017
cks+0.015
 vows+0.015
irs+0.014
ves+0.014
Neg logit contributions
wheel-0.018
 sill-0.017
hot-0.016
uster-0.016
 aback-0.016
Token showed
Token ID3751
Feature activation+1.13e-02

Pos logit contributions
ls+0.013
cks+0.012
irs+0.011
 vows+0.011
 nations+0.011
Neg logit contributions
wheel-0.011
 sill-0.010
hot-0.010
icle-0.010
bar-0.009
Token them
Token ID606
Feature activation+2.18e-02

Pos logit contributions
ls+0.013
cks+0.012
 vows+0.011
ves+0.010
 nations+0.010
Neg logit contributions
wheel-0.025
 sill-0.025
hot-0.025
 aback-0.024
icle-0.024
Token monkeys
Token ID26697
Feature activation+3.15e-02

Pos logit contributions
ls+0.055
cks+0.053
its+0.049
irs+0.049
 vows+0.049
Neg logit contributions
 sill-0.050
wheel-0.048
 3-0.046
hot-0.044
 vest-0.044
Token and
Token ID290
Feature activation+1.76e-02

Pos logit contributions
ls+0.072
 vows+0.071
irs+0.069
cks+0.068
heit+0.065
Neg logit contributions
 sill-0.033
wheel-0.032
hot-0.030
uit-0.027
my-0.027
Token elephants
Token ID25368
Feature activation+4.63e-02

Pos logit contributions
ls+0.034
its+0.033
cks+0.033
irs+0.033
 vows+0.031
Neg logit contributions
 sill-0.026
wheel-0.023
 3-0.022
 vest-0.022
 bear-0.022
Token and
Token ID290
Feature activation+1.87e-02

Pos logit contributions
ls+0.097
 vows+0.094
irs+0.094
cks+0.093
heit+0.091
Neg logit contributions
 sill-0.058
wheel-0.055
hot-0.053
uit-0.047
bar-0.047
Token gir
Token ID37370
Feature activation+5.10e-02

Pos logit contributions
ls+0.035
irs+0.034
cks+0.034
its+0.033
 vows+0.032
Neg logit contributions
 sill-0.030
wheel-0.027
 vest-0.025
 3-0.025
 happiest-0.025
Tokenaff
Token ID2001
Feature activation+7.90e-02

Pos logit contributions
ls+0.073
cks+0.072
 vows+0.072
 spills+0.070
 passports+0.069
Neg logit contributions
 sill-0.086
wheel-0.085
est-0.083
hot-0.079
bar-0.079
Tokenes
Token ID274
Feature activation+3.01e-02

Pos logit contributions
 passports+0.138
 vows+0.132
heit+0.130
 spills+0.129
 hides+0.120
Neg logit contributions
ah-0.105
my-0.102
bird-0.102
est-0.097
ter-0.096
Token.
Token ID13
Feature activation+2.64e-02

Pos logit contributions
ls+0.061
cks+0.060
 vows+0.057
irs+0.057
heit+0.055
Neg logit contributions
 sill-0.040
wheel-0.038
hot-0.038
uit-0.034
est-0.034
Token They
Token ID1119
Feature activation+3.01e-02

Pos logit contributions
ls+0.044
cks+0.040
 vows+0.039
ils+0.036
ves+0.035
Neg logit contributions
 sill-0.048
wheel-0.047
hot-0.046
icle-0.044
uster-0.044
Token had
Token ID550
Feature activation-2.22e-03

Pos logit contributions
ls+0.059
cks+0.057
irs+0.056
its+0.051
 vows+0.050
Neg logit contributions
 sill-0.045
wheel-0.044
hot-0.041
my-0.040
 happiest-0.040
Token fun
Token ID1257
Feature activation+9.61e-04

Pos logit contributions
 sill+0.003
 3+0.002
 so+0.002
 happiest+0.002
wheel+0.002
Neg logit contributions
ls-0.005
irs-0.005
cks-0.005
its-0.005
 vows-0.005
Token monkeys
Token ID26697
Feature activation+3.02e-02

Pos logit contributions
ls+0.009
 vows+0.009
cks+0.009
irs+0.008
its+0.008
Neg logit contributions
 sill-0.007
wheel-0.006
hot-0.006
bar-0.006
est-0.006
Token and
Token ID290
Feature activation+2.07e-02

Pos logit contributions
ls+0.063
 vows+0.063
irs+0.060
cks+0.059
ves+0.057
Neg logit contributions
wheel-0.037
 sill-0.035
hot-0.032
bar-0.032
uit-0.031
Token elephants
Token ID25368
Feature activation+4.19e-02

Pos logit contributions
irs+0.039
ls+0.039
its+0.037
cks+0.036
 vows+0.036
Neg logit contributions
 sill-0.032
wheel-0.028
 3-0.028
 bear-0.026
my-0.026
Token and
Token ID290
Feature activation+2.26e-02

Pos logit contributions
ls+0.089
 vows+0.086
irs+0.083
cks+0.083
ves+0.079
Neg logit contributions
wheel-0.051
 sill-0.050
hot-0.047
bar-0.045
uit-0.043
Token gir
Token ID37370
Feature activation+4.91e-02

Pos logit contributions
ls+0.041
irs+0.040
cks+0.038
its+0.037
 vows+0.037
Neg logit contributions
 sill-0.037
wheel-0.033
 3-0.031
 happiest-0.031
 vest-0.031
Tokenaff
Token ID2001
Feature activation+7.85e-02

Pos logit contributions
ls+0.070
cks+0.068
 vows+0.067
irs+0.064
 spills+0.063
Neg logit contributions
wheel-0.086
 sill-0.085
est-0.082
hot-0.082
bar-0.081
Tokenes
Token ID274
Feature activation+3.22e-02

Pos logit contributions
 passports+0.130
 vows+0.125
 spills+0.124
heit+0.114
 hides+0.113
Neg logit contributions
ah-0.111
my-0.104
bird-0.103
uit-0.100
ter-0.100
Token,
Token ID11
Feature activation+2.56e-03

Pos logit contributions
ls+0.067
cks+0.064
 vows+0.062
irs+0.061
its+0.058
Neg logit contributions
 sill-0.041
wheel-0.040
hot-0.039
uit-0.036
est-0.034
Token too
Token ID1165
Feature activation+1.80e-02

Pos logit contributions
ls+0.005
irs+0.005
 vows+0.005
cks+0.005
ves+0.005
Neg logit contributions
 sill-0.004
wheel-0.003
hot-0.003
bar-0.003
icle-0.003
Token.
Token ID13
Feature activation+1.53e-02

Pos logit contributions
 vows+0.042
ls+0.039
irs+0.039
ils+0.039
cks+0.038
Neg logit contributions
 sill-0.018
wheel-0.016
 handy-0.016
hot-0.015
 stump-0.014
Token They
Token ID1119
Feature activation+3.69e-02

Pos logit contributions
ls+0.026
cks+0.024
 vows+0.023
ves+0.022
ils+0.021
Neg logit contributions
 sill-0.027
wheel-0.026
hot-0.025
icle-0.024
uster-0.024
Token lions
Token ID31420
Feature activation+3.21e-02

Pos logit contributions
ls+0.056
cks+0.053
its+0.051
irs+0.050
 vows+0.050
Neg logit contributions
 sill-0.048
wheel-0.045
 3-0.044
hot-0.044
 so-0.042
Token and
Token ID290
Feature activation+6.47e-03

Pos logit contributions
ls+0.073
 vows+0.071
cks+0.069
irs+0.068
its+0.064
Neg logit contributions
wheel-0.035
 sill-0.033
hot-0.033
uit-0.030
est-0.030
Token elephants
Token ID25368
Feature activation+4.64e-02

Pos logit contributions
ls+0.013
cks+0.013
its+0.012
irs+0.012
 vows+0.012
Neg logit contributions
 sill-0.009
wheel-0.009
 3-0.008
 vest-0.008
my-0.008
Token and
Token ID290
Feature activation+1.75e-02

Pos logit contributions
 vows+0.099
ls+0.099
irs+0.097
cks+0.096
heit+0.096
Neg logit contributions
wheel-0.053
 sill-0.052
hot-0.052
my-0.046
uit-0.046
Token gir
Token ID37370
Feature activation+4.97e-02

Pos logit contributions
ls+0.033
cks+0.033
irs+0.032
its+0.030
 vows+0.030
Neg logit contributions
 sill-0.027
wheel-0.026
 vest-0.024
 3-0.024
est-0.024
Tokenaff
Token ID2001
Feature activation+7.83e-02

Pos logit contributions
ls+0.069
cks+0.069
 vows+0.067
 spills+0.063
irs+0.062
Neg logit contributions
wheel-0.089
hot-0.086
 sill-0.086
est-0.085
icle-0.083
Tokenes
Token ID274
Feature activation+2.89e-02

Pos logit contributions
 vows+0.139
 passports+0.135
heit+0.133
 spills+0.129
 hides+0.122
Neg logit contributions
uit-0.109
my-0.109
hot-0.108
ah-0.104
ock-0.101
Token.
Token ID13
Feature activation+1.87e-02

Pos logit contributions
ls+0.059
cks+0.057
 vows+0.055
irs+0.054
heit+0.052
Neg logit contributions
wheel-0.038
hot-0.038
 sill-0.038
uit-0.034
est-0.033
Token Anna
Token ID11735
Feature activation+2.43e-02

Pos logit contributions
ls+0.033
cks+0.033
irs+0.032
 vows+0.028
 nations+0.028
Neg logit contributions
 sill-0.031
hot-0.029
 aback-0.028
 3-0.027
inter-0.026
Token was
Token ID373
Feature activation-1.91e-03

Pos logit contributions
cks+0.049
irs+0.048
ls+0.048
its+0.042
 vows+0.041
Neg logit contributions
 sill-0.032
my-0.032
wheel-0.032
 3-0.031
 vest-0.030
Token very
Token ID845
Feature activation+1.74e-02

Pos logit contributions
wheel+0.003
 sill+0.003
hot+0.002
uster+0.002
icle+0.002
Neg logit contributions
ls-0.004
cks-0.004
 vows-0.004
ves-0.003
irs-0.003
Token lions
Token ID31420
Feature activation+3.23e-02

Pos logit contributions
wheel+0.003
 sill+0.003
hot+0.003
icle+0.003
 vest+0.003
Neg logit contributions
ls-0.003
cks-0.003
 vows-0.003
irs-0.003
ves-0.003
Token and
Token ID290
Feature activation+1.02e-02

Pos logit contributions
ls+0.067
 vows+0.063
cks+0.062
irs+0.061
ves+0.057
Neg logit contributions
wheel-0.043
 sill-0.042
hot-0.040
bar-0.037
icle-0.037
Token monkeys
Token ID26697
Feature activation+4.58e-02

Pos logit contributions
ls+0.021
cks+0.020
its+0.019
irs+0.019
 vows+0.019
Neg logit contributions
 sill-0.014
wheel-0.014
 3-0.013
icle-0.012
bar-0.012
Token and
Token ID290
Feature activation+2.55e-02

Pos logit contributions
ls+0.097
 vows+0.094
irs+0.092
cks+0.088
heit+0.086
Neg logit contributions
wheel-0.059
 sill-0.057
hot-0.052
bar-0.050
uit-0.047
Token gir
Token ID37370
Feature activation+4.90e-02

Pos logit contributions
ls+0.049
cks+0.045
irs+0.044
its+0.044
ves+0.043
Neg logit contributions
 sill-0.040
wheel-0.038
 3-0.036
 vest-0.034
hot-0.034
Tokenaff
Token ID2001
Feature activation+7.79e-02

Pos logit contributions
ls+0.070
 vows+0.068
cks+0.068
irs+0.065
 spills+0.064
Neg logit contributions
wheel-0.086
 sill-0.082
hot-0.081
bar-0.080
est-0.080
Tokenes
Token ID274
Feature activation+2.99e-02

Pos logit contributions
 vows+0.130
 passports+0.129
 spills+0.126
 hides+0.123
heit+0.122
Neg logit contributions
ah-0.108
my-0.105
uit-0.105
hot-0.103
bird-0.102
Token.
Token ID13
Feature activation+1.76e-02

Pos logit contributions
ls+0.060
cks+0.058
 vows+0.056
irs+0.054
heit+0.052
Neg logit contributions
wheel-0.040
 sill-0.040
hot-0.040
uit-0.036
 aback-0.035
Token
Token ID198
Feature activation+1.15e-02

Pos logit contributions
ls+0.028
cks+0.026
 vows+0.025
ves+0.023
irs+0.023
Neg logit contributions
 sill-0.032
wheel-0.032
hot-0.031
uster-0.030
icle-0.030
Token
Token ID198
Feature activation+1.44e-02

Pos logit contributions
ls+0.026
 vows+0.025
cks+0.024
ils+0.023
 nations+0.023
Neg logit contributions
wheel-0.013
 sill-0.013
hot-0.012
uster-0.011
 handy-0.011
TokenThey
Token ID2990
Feature activation+2.80e-02

Pos logit contributions
ls+0.030
 vows+0.028
cks+0.027
ils+0.025
 nations+0.024
Neg logit contributions
hot-0.021
wheel-0.021
 sill-0.020
 handy-0.019
bar-0.019
Token water
Token ID1660
Feature activation+3.03e-03

Pos logit contributions
ls+0.015
cks+0.015
ves+0.014
 vows+0.013
irs+0.013
Neg logit contributions
 sill-0.013
wheel-0.012
 vest-0.012
est-0.011
hot-0.011
Token.
Token ID13
Feature activation+1.12e-03

Pos logit contributions
ls+0.006
cks+0.006
 vows+0.005
irs+0.005
ves+0.005
Neg logit contributions
 sill-0.004
wheel-0.004
hot-0.004
est-0.004
icle-0.004
Token
Token ID198
Feature activation-4.20e-04

Pos logit contributions
ls+0.002
 vows+0.002
cks+0.002
irs+0.002
 nations+0.002
Neg logit contributions
wheel-0.002
icle-0.002
 sill-0.002
bar-0.002
Aid-0.002
Token
Token ID198
Feature activation+5.00e-03

Pos logit contributions
wheel+0.001
 sill+0.001
hot+0.001
uster+0.001
icle+0.001
Neg logit contributions
ls-0.001
cks-0.001
 vows-0.001
irs-0.001
ves-0.001
TokenThe
Token ID464
Feature activation+5.94e-03

Pos logit contributions
ls+0.010
cks+0.009
 vows+0.009
irs+0.008
ves+0.008
Neg logit contributions
wheel-0.008
 sill-0.007
hot-0.007
uster-0.007
 aback-0.007
Token mer
Token ID4017
Feature activation+7.72e-02

Pos logit contributions
ls+0.012
cks+0.012
irs+0.011
ves+0.011
 vows+0.010
Neg logit contributions
 sill-0.009
wheel-0.008
 vest-0.008
hot-0.008
 Vest-0.007
Tokenmaid
Token ID23151
Feature activation+3.07e-02

Pos logit contributions
ls+0.136
cks+0.131
irs+0.122
ves+0.121
 runs+0.118
Neg logit contributions
 sill-0.120
wheel-0.116
est-0.115
uster-0.112
 expert-0.109
Token smiled
Token ID13541
Feature activation-9.42e-03

Pos logit contributions
cks+0.057
ls+0.057
irs+0.053
its+0.051
 vows+0.049
Neg logit contributions
 sill-0.045
wheel-0.044
bar-0.042
est-0.041
 3-0.040
Token at
Token ID379
Feature activation+8.02e-03

Pos logit contributions
wheel+0.018
Aid+0.015
icle+0.015
hot+0.015
uster+0.015
Neg logit contributions
ls-0.016
 vows-0.014
 points-0.014
 their-0.013
cks-0.013
Token Melody
Token ID38906
Feature activation+3.71e-03

Pos logit contributions
ls+0.014
cks+0.013
 vows+0.013
irs+0.012
ves+0.012
Neg logit contributions
wheel-0.013
 sill-0.013
hot-0.012
uster-0.012
icle-0.012
Token.
Token ID13
Feature activation-8.50e-03

Pos logit contributions
ls+0.008
cks+0.008
 vows+0.008
irs+0.008
its+0.007
Neg logit contributions
 sill-0.004
wheel-0.004
est-0.004
hot-0.004
 aback-0.004
Token castle
Token ID16669
Feature activation-3.11e-03

Pos logit contributions
 sill+0.013
wheel+0.012
hot+0.011
 vest+0.011
uster+0.011
Neg logit contributions
ls-0.017
cks-0.015
 vows-0.015
irs-0.014
ves-0.014
Token so
Token ID523
Feature activation-5.55e-03

Pos logit contributions
uster+0.005
hot+0.005
wheel+0.005
Aid+0.005
 aback+0.005
Neg logit contributions
ls-0.005
cks-0.004
 vows-0.004
ves-0.004
 runs-0.004
Token much
Token ID881
Feature activation-1.60e-02

Pos logit contributions
 sill+0.008
wheel+0.007
hot+0.007
bar+0.006
 cleaner+0.006
Neg logit contributions
cks-0.011
ls-0.011
 vows-0.011
irs-0.010
ils-0.010
Token.
Token ID13
Feature activation-9.51e-03

Pos logit contributions
wheel+0.024
 sill+0.024
hot+0.023
uster+0.022
icle+0.022
Neg logit contributions
ls-0.031
cks-0.028
 vows-0.027
irs-0.026
ves-0.026
Token The
Token ID383
Feature activation+8.45e-03

Pos logit contributions
wheel+0.013
uster+0.012
 sill+0.012
Aid+0.012
hot+0.011
Neg logit contributions
ls-0.019
 vows-0.018
cks-0.017
 their-0.016
 nations-0.016
Token mer
Token ID4017
Feature activation+7.70e-02

Pos logit contributions
cks+0.017
ls+0.016
irs+0.015
ves+0.015
 vows+0.014
Neg logit contributions
 sill-0.013
wheel-0.012
 vest-0.012
est-0.011
 Vest-0.011
Tokenmaid
Token ID23151
Feature activation+2.81e-02

Pos logit contributions
ls+0.137
cks+0.130
irs+0.128
ves+0.124
 runs+0.118
Neg logit contributions
 sill-0.122
est-0.117
wheel-0.109
icle-0.103
uster-0.103
Token said
Token ID531
Feature activation-5.19e-03

Pos logit contributions
cks+0.055
ls+0.054
irs+0.053
 vows+0.050
 nations+0.049
Neg logit contributions
wheel-0.038
 sill-0.036
bar-0.035
hot-0.034
 vest-0.034
Token,
Token ID11
Feature activation-1.67e-02

Pos logit contributions
wheel+0.008
 sill+0.008
hot+0.007
uster+0.007
 aback+0.007
Neg logit contributions
ls-0.010
cks-0.009
 vows-0.009
irs-0.009
ves-0.009
Token "
Token ID366
Feature activation-6.61e-04

Pos logit contributions
wheel+0.025
 sill+0.024
uster+0.023
hot+0.023
 aback+0.022
Neg logit contributions
ls-0.032
cks-0.029
 vows-0.029
ves-0.027
irs-0.027
TokenI
Token ID40
Feature activation+1.15e-02

Pos logit contributions
wheel+0.001
 sill+0.001
hot+0.001
uster+0.001
icle+0.001
Neg logit contributions
ls-0.001
cks-0.001
 vows-0.001
irs-0.001
ves-0.001
Token their
Token ID511
Feature activation+2.89e-02

Pos logit contributions
ls+0.053
 vows+0.047
ves+0.046
cks+0.046
ils+0.043
Neg logit contributions
 sill-0.042
hot-0.039
wheel-0.038
 aback-0.037
 vest-0.037
Token tank
Token ID6873
Feature activation+3.36e-02

Pos logit contributions
ls+0.049
cks+0.047
irs+0.045
ves+0.044
ils+0.042
Neg logit contributions
 sill-0.048
 vest-0.047
 knee-0.044
wheel-0.043
inter-0.043
Token.
Token ID13
Feature activation+1.47e-02

Pos logit contributions
ls+0.065
irs+0.062
cks+0.062
 vows+0.061
ves+0.058
Neg logit contributions
 sill-0.049
wheel-0.047
hot-0.044
bar-0.043
 vest-0.042
Token The
Token ID383
Feature activation+1.45e-02

Pos logit contributions
ls+0.027
cks+0.025
 vows+0.024
irs+0.023
ves+0.023
Neg logit contributions
wheel-0.024
 sill-0.023
hot-0.022
uster-0.021
 aback-0.021
Token bad
Token ID2089
Feature activation+1.72e-02

Pos logit contributions
ls+0.030
cks+0.027
 vows+0.027
 nations+0.025
ves+0.025
Neg logit contributions
wheel-0.021
 sill-0.020
hot-0.019
uster-0.019
 aback-0.018
Token guys
Token ID3730
Feature activation+7.62e-02

Pos logit contributions
ls+0.031
cks+0.029
 vows+0.028
irs+0.026
ves+0.026
Neg logit contributions
wheel-0.029
 sill-0.028
hot-0.027
uster-0.026
icle-0.026
Token run
Token ID1057
Feature activation+1.97e-02

Pos logit contributions
 vows+0.123
irs+0.117
ls+0.116
 pulp+0.109
ves+0.109
Neg logit contributions
wheel-0.123
he-0.111
 sill-0.107
boat-0.107
 beam-0.106
Token away
Token ID1497
Feature activation+2.75e-02

Pos logit contributions
ls+0.044
cks+0.042
 vows+0.041
irs+0.040
ves+0.039
Neg logit contributions
wheel-0.023
 sill-0.023
hot-0.022
 aback-0.021
uster-0.020
Token and
Token ID290
Feature activation+9.08e-03

Pos logit contributions
ls+0.062
cks+0.060
irs+0.059
 vows+0.059
ves+0.056
Neg logit contributions
 sill-0.032
wheel-0.029
 aback-0.027
hot-0.026
 handy-0.026
Token Ben
Token ID3932
Feature activation+3.01e-02

Pos logit contributions
ls+0.016
ves+0.015
irs+0.015
 vows+0.015
cks+0.014
Neg logit contributions
 sill-0.015
wheel-0.014
 knee-0.013
 vest-0.013
hot-0.013
Token and
Token ID290
Feature activation+1.99e-02

Pos logit contributions
irs+0.050
ls+0.048
 vows+0.046
cks+0.045
ves+0.043
Neg logit contributions
 sill-0.050
wheel-0.049
 knee-0.047
 aback-0.046
 vest-0.046
Token "
Token ID366
Feature activation-3.76e-03

Pos logit contributions
ls+0.007
ils+0.007
cks+0.007
irs+0.007
 vows+0.006
Neg logit contributions
 sill-0.002
hot-0.002
wheel-0.002
 3-0.002
 handy-0.002
TokenFree
Token ID11146
Feature activation+2.76e-02

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.006
icle+0.005
bar+0.005
Neg logit contributions
ls-0.007
cks-0.007
 vows-0.007
ves-0.006
irs-0.006
Token mel
Token ID7758
Feature activation+2.57e-03

Pos logit contributions
ls+0.050
cks+0.043
irs+0.040
 vows+0.039
ves+0.037
Neg logit contributions
wheel-0.047
 sill-0.047
hot-0.045
icle-0.044
est-0.044
Tokenon
Token ID261
Feature activation+7.79e-03

Pos logit contributions
ls+0.005
cks+0.005
 vows+0.005
irs+0.005
 nations+0.005
Neg logit contributions
wheel-0.004
hot-0.003
 sill-0.003
bar-0.003
icle-0.003
Token.
Token ID13
Feature activation+3.40e-02

Pos logit contributions
ls+0.015
cks+0.015
 vows+0.014
irs+0.014
 nations+0.013
Neg logit contributions
wheel-0.012
hot-0.011
 sill-0.011
bar-0.010
icle-0.010
Token Enjoy
Token ID18179
Feature activation+7.62e-02

Pos logit contributions
ls+0.072
cks+0.066
 vows+0.064
ves+0.061
irs+0.060
Neg logit contributions
wheel-0.046
 sill-0.046
hot-0.044
uster-0.041
icle-0.041
Token!"
Token ID2474
Feature activation+1.07e-02

Pos logit contributions
ls+0.139
cks+0.122
irs+0.120
 vows+0.117
 nations+0.111
Neg logit contributions
 sill-0.110
icle-0.105
est-0.100
uit-0.098
wheel-0.098
Token They
Token ID1119
Feature activation+2.72e-02

Pos logit contributions
ls+0.020
cks+0.018
 vows+0.018
ves+0.017
irs+0.017
Neg logit contributions
wheel-0.017
 sill-0.017
hot-0.016
uster-0.016
bar-0.016
Token were
Token ID547
Feature activation+1.91e-02

Pos logit contributions
ls+0.053
cks+0.049
irs+0.046
ves+0.043
its+0.042
Neg logit contributions
wheel-0.043
 sill-0.042
hot-0.042
 3-0.040
uit-0.038
Token happy
Token ID3772
Feature activation+1.88e-02

Pos logit contributions
ls+0.048
irs+0.044
ves+0.043
ils+0.042
cks+0.041
Neg logit contributions
 sill-0.022
wheel-0.018
 hesitant-0.017
hot-0.016
 handy-0.016
Token.
Token ID13
Feature activation+9.03e-03

Pos logit contributions
ls+0.044
cks+0.043
 vows+0.042
irs+0.042
heit+0.041
Neg logit contributions
 sill-0.021
wheel-0.019
hot-0.017
 vest-0.017
 cleaner-0.016
Token in
Token ID287
Feature activation+1.06e-02

Pos logit contributions
wheel+0.016
 sill+0.015
hot+0.015
uster+0.014
icle+0.014
Neg logit contributions
ls-0.021
cks-0.019
 vows-0.018
 nations-0.017
irs-0.017
Token the
Token ID262
Feature activation-1.00e-02

Pos logit contributions
ls+0.021
cks+0.019
 vows+0.019
ves+0.018
ils+0.017
Neg logit contributions
 sill-0.016
wheel-0.016
hot-0.015
 aback-0.014
icle-0.014
Token sea
Token ID5417
Feature activation+1.68e-02

Pos logit contributions
wheel+0.014
 sill+0.013
hot+0.013
uster+0.013
 aback+0.012
Neg logit contributions
ls-0.021
cks-0.019
 vows-0.019
irs-0.017
 nations-0.017
Token that
Token ID326
Feature activation-2.53e-02

Pos logit contributions
ls+0.033
cks+0.030
 vows+0.029
irs+0.028
ves+0.027
Neg logit contributions
 sill-0.025
wheel-0.025
hot-0.024
bar-0.023
 aback-0.023
Token the
Token ID262
Feature activation+7.04e-03

Pos logit contributions
 sill+0.043
wheel+0.043
hot+0.040
 aback+0.038
icle+0.038
Neg logit contributions
ls-0.045
cks-0.041
 vows-0.039
irs-0.037
ves-0.036
Token mer
Token ID4017
Feature activation+7.56e-02

Pos logit contributions
ls+0.014
cks+0.013
irs+0.012
ves+0.012
 vows+0.012
Neg logit contributions
 sill-0.011
wheel-0.010
est-0.009
 vest-0.009
 3-0.009
Tokenmaid
Token ID23151
Feature activation+2.85e-02

Pos logit contributions
ls+0.136
irs+0.136
cks+0.135
ves+0.129
 runs+0.129
Neg logit contributions
 sill-0.111
est-0.107
imm-0.093
boat-0.092
wheel-0.090
Token carefully
Token ID7773
Feature activation+1.39e-02

Pos logit contributions
cks+0.054
ls+0.053
irs+0.052
its+0.049
 vows+0.049
Neg logit contributions
wheel-0.040
 sill-0.040
boat-0.036
bar-0.035
est-0.035
Token chose
Token ID7690
Feature activation-1.34e-02

Pos logit contributions
ls+0.026
cks+0.024
irs+0.023
 vows+0.022
 nations+0.022
Neg logit contributions
 sill-0.023
wheel-0.022
hot-0.020
bar-0.020
 aback-0.020
Token.
Token ID13
Feature activation-2.84e-03

Pos logit contributions
 sill+0.019
wheel+0.018
hot+0.017
 aback+0.017
icle+0.016
Neg logit contributions
ls-0.027
cks-0.026
 vows-0.024
irs-0.024
ves-0.023
Token It
Token ID632
Feature activation-1.28e-02

Pos logit contributions
wheel+0.004
 sill+0.004
hot+0.004
 vest+0.004
Aid+0.004
Neg logit contributions
ls-0.006
cks-0.005
 vows-0.005
irs-0.005
 nations-0.005
Token faces
Token ID6698
Feature activation+1.87e-02

Pos logit contributions
ls+0.044
 vows+0.039
cks+0.039
irs+0.039
ves+0.034
Neg logit contributions
 sill-0.070
est-0.068
wheel-0.065
 vest-0.064
hot-0.062
Token and
Token ID290
Feature activation+5.47e-03

Pos logit contributions
ls+0.042
cks+0.039
 vows+0.038
irs+0.036
ves+0.035
Neg logit contributions
wheel-0.023
 sill-0.023
hot-0.021
icle-0.020
uster-0.020
Token shapes
Token ID15268
Feature activation+2.02e-02

Pos logit contributions
ls+0.011
cks+0.010
irs+0.010
 vows+0.009
ves+0.008
Neg logit contributions
 sill-0.009
wheel-0.009
 cleaner-0.008
 vest-0.008
hot-0.008
Token with
Token ID351
Feature activation+3.43e-02

Pos logit contributions
ls+0.042
cks+0.039
irs+0.038
 vows+0.038
heit+0.037
Neg logit contributions
 sill-0.029
wheel-0.027
hot-0.025
icle-0.025
 cleaner-0.024
Token the
Token ID262
Feature activation+9.60e-03

Pos logit contributions
ls+0.068
cks+0.062
 vows+0.059
ves+0.058
irs+0.056
Neg logit contributions
 sill-0.050
hot-0.047
icle-0.045
 3-0.044
 cleaner-0.044
Token topp
Token ID23126
Feature activation+7.56e-02

Pos logit contributions
ls+0.018
cks+0.016
 vows+0.016
irs+0.015
ves+0.015
Neg logit contributions
 sill-0.015
wheel-0.015
hot-0.014
icle-0.014
 vest-0.014
Tokenings
Token ID654
Feature activation+3.07e-03

Pos logit contributions
ls+0.129
irs+0.119
cks+0.114
 nations+0.111
 boarding+0.108
Neg logit contributions
est-0.127
icle-0.126
 sill-0.126
uit-0.112
bar-0.112
Token.
Token ID13
Feature activation+1.60e-02

Pos logit contributions
ls+0.005
cks+0.005
 vows+0.005
irs+0.004
ves+0.004
Neg logit contributions
wheel-0.005
 sill-0.005
hot-0.005
uster-0.005
icle-0.005
Token
Token ID198
Feature activation+1.05e-02

Pos logit contributions
ls+0.033
cks+0.030
 vows+0.030
ves+0.028
irs+0.028
Neg logit contributions
 sill-0.023
wheel-0.022
hot-0.021
uster-0.020
icle-0.020
Token
Token ID198
Feature activation+1.76e-02

Pos logit contributions
ls+0.023
cks+0.022
 vows+0.022
ils+0.020
 nations+0.020
Neg logit contributions
wheel-0.013
 sill-0.012
hot-0.012
uster-0.011
icle-0.011
Token"
Token ID1
Feature activation-5.25e-04

Pos logit contributions
ls+0.037
cks+0.035
 vows+0.034
ils+0.031
irs+0.031
Neg logit contributions
hot-0.024
wheel-0.023
 sill-0.023
uster-0.022
 handy-0.021
Tokenashes
Token ID7465
Feature activation+1.18e-02

Pos logit contributions
ls+0.007
cks+0.006
 vows+0.005
 runs+0.005
ves+0.005
Neg logit contributions
 Tooth-0.014
 Vest-0.014
 vest-0.014
wheel-0.014
 sill-0.014
Token.
Token ID13
Feature activation+1.77e-02

Pos logit contributions
ls+0.023
 vows+0.022
cks+0.022
irs+0.021
ves+0.020
Neg logit contributions
wheel-0.017
 sill-0.017
hot-0.016
 aback-0.015
icle-0.015
Token They
Token ID1119
Feature activation+4.58e-02

Pos logit contributions
ls+0.032
cks+0.029
 vows+0.027
irs+0.027
 nations+0.026
Neg logit contributions
 sill-0.030
wheel-0.028
hot-0.028
icle-0.027
uster-0.027
Token laugh
Token ID6487
Feature activation+3.02e-02

Pos logit contributions
ls+0.094
cks+0.085
 vows+0.082
irs+0.081
ves+0.080
Neg logit contributions
wheel-0.068
 sill-0.066
hot-0.060
 beam-0.058
 vest-0.057
Token and
Token ID290
Feature activation+5.13e-03

Pos logit contributions
ls+0.061
cks+0.056
 vows+0.055
ves+0.052
irs+0.051
Neg logit contributions
wheel-0.043
 sill-0.042
hot-0.040
uster-0.039
icle-0.038
Token g
Token ID308
Feature activation+7.49e-02

Pos logit contributions
ls+0.010
cks+0.009
 vows+0.009
irs+0.008
ves+0.008
Neg logit contributions
wheel-0.008
 sill-0.008
hot-0.008
 vest-0.007
 aback-0.007
Tokeniggle
Token ID24082
Feature activation+2.55e-02

Pos logit contributions
ls+0.170
cks+0.152
 vows+0.152
 cor+0.149
ves+0.145
Neg logit contributions
wheel-0.082
 sill-0.080
icle-0.075
uster-0.075
inter-0.075
Token.
Token ID13
Feature activation+1.61e-02

Pos logit contributions
ls+0.049
cks+0.046
 vows+0.044
irs+0.044
ves+0.041
Neg logit contributions
 sill-0.038
wheel-0.038
hot-0.037
est-0.034
uster-0.033
Token They
Token ID1119
Feature activation+3.50e-02

Pos logit contributions
ls+0.037
cks+0.035
irs+0.033
ils+0.033
 vows+0.033
Neg logit contributions
 sill-0.019
hot-0.017
 3-0.016
 aback-0.015
wheel-0.015
Token feel
Token ID1254
Feature activation-9.37e-03

Pos logit contributions
ls+0.068
cks+0.062
 vows+0.058
irs+0.057
ves+0.056
Neg logit contributions
wheel-0.057
 sill-0.055
hot-0.051
 vest-0.049
 aback-0.049
Token the
Token ID262
Feature activation-1.56e-02

Pos logit contributions
wheel+0.015
 sill+0.014
bar+0.013
hot+0.013
uster+0.013
Neg logit contributions
ls-0.018
cks-0.017
 vows-0.016
irs-0.015
 runs-0.015
Token're
Token ID821
Feature activation+1.66e-03

Pos logit contributions
ls+0.023
cks+0.021
ves+0.019
 vows+0.018
irs+0.018
Neg logit contributions
wheel-0.026
hot-0.026
 sill-0.025
 aback-0.024
 Vest-0.024
Token welcome
Token ID7062
Feature activation+2.61e-02

Pos logit contributions
ls+0.004
cks+0.004
 vows+0.004
 nations+0.004
irs+0.004
Neg logit contributions
wheel-0.002
uster-0.002
 sill-0.002
bar-0.001
hot-0.001
Token,
Token ID11
Feature activation-2.02e-03

Pos logit contributions
ls+0.054
cks+0.052
 vows+0.049
irs+0.049
ves+0.047
Neg logit contributions
 sill-0.035
wheel-0.033
hot-0.033
 aback-0.031
uit-0.031
Token kids
Token ID3988
Feature activation+9.17e-03

Pos logit contributions
wheel+0.003
 sill+0.003
hot+0.003
uster+0.003
 aback+0.003
Neg logit contributions
ls-0.004
cks-0.003
 vows-0.003
ves-0.003
irs-0.003
Token!
Token ID0
Feature activation+4.32e-03

Pos logit contributions
ls+0.015
cks+0.014
 vows+0.014
irs+0.012
ves+0.012
Neg logit contributions
wheel-0.016
 sill-0.016
hot-0.015
uster-0.015
 aback-0.015
Token Enjoy
Token ID18179
Feature activation+7.48e-02

Pos logit contributions
ls+0.009
cks+0.008
 vows+0.008
 runs+0.008
irs+0.008
Neg logit contributions
wheel-0.006
 sill-0.006
hot-0.005
uster-0.005
 vest-0.005
Token the
Token ID262
Feature activation-2.97e-03

Pos logit contributions
ls+0.140
cks+0.121
irs+0.119
 vows+0.115
 pulp+0.114
Neg logit contributions
 sill-0.109
uit-0.100
wheel-0.099
icle-0.097
 handy-0.097
Token show
Token ID905
Feature activation+1.46e-02

Pos logit contributions
wheel+0.005
 sill+0.004
 vest+0.004
est+0.004
hot+0.004
Neg logit contributions
ls-0.006
cks-0.005
irs-0.005
 vows-0.005
ves-0.005
Token!"
Token ID2474
Feature activation+9.43e-03

Pos logit contributions
ls+0.028
cks+0.025
 vows+0.024
irs+0.023
ves+0.022
Neg logit contributions
wheel-0.023
 sill-0.023
hot-0.022
icle-0.021
est-0.020
Token
Token ID198
Feature activation+6.01e-03

Pos logit contributions
ls+0.020
cks+0.019
 vows+0.018
irs+0.017
ils+0.017
Neg logit contributions
 sill-0.013
wheel-0.013
hot-0.012
 aback-0.011
uster-0.011
Token
Token ID198
Feature activation+1.68e-02

Pos logit contributions
ls+0.013
 vows+0.012
cks+0.012
irs+0.011
ils+0.011
Neg logit contributions
wheel-0.008
 sill-0.007
hot-0.007
uster-0.006
 aback-0.006
Tokenanas
Token ID15991
Feature activation+4.84e-02

Pos logit contributions
ls+0.058
cks+0.052
 vows+0.050
irs+0.047
 nations+0.046
Neg logit contributions
wheel-0.064
 sill-0.063
hot-0.060
uster-0.059
icle-0.058
Token available
Token ID1695
Feature activation+1.01e-02

Pos logit contributions
ls+0.090
cks+0.082
 vows+0.075
irs+0.073
 nations+0.072
Neg logit contributions
wheel-0.078
hot-0.078
icle-0.073
 sill-0.072
uit-0.071
Token for
Token ID329
Feature activation+1.93e-02

Pos logit contributions
ls+0.022
cks+0.020
 vows+0.019
irs+0.019
 nations+0.018
Neg logit contributions
wheel-0.013
hot-0.013
 sill-0.012
icle-0.012
uit-0.012
Token feeding
Token ID13017
Feature activation+4.21e-02

Pos logit contributions
ls+0.038
 vows+0.032
cks+0.032
its+0.029
ves+0.029
Neg logit contributions
wheel-0.029
icle-0.029
hot-0.028
 operation-0.028
 sill-0.028
Token the
Token ID262
Feature activation+2.64e-02

Pos logit contributions
ls+0.074
cks+0.067
 vows+0.064
irs+0.059
ves+0.059
Neg logit contributions
hot-0.070
wheel-0.069
 sill-0.068
icle-0.067
 aback-0.064
Token gor
Token ID30344
Feature activation+7.47e-02

Pos logit contributions
irs+0.043
ls+0.042
cks+0.039
packs+0.036
ils+0.036
Neg logit contributions
 sill-0.047
est-0.046
 3-0.044
 happiest-0.041
 operation-0.041
Tokenillas
Token ID25314
Feature activation+4.70e-02

Pos logit contributions
 vows+0.117
ls+0.112
 runs+0.110
 spills+0.106
irs+0.105
Neg logit contributions
bar-0.110
ive-0.109
mallow-0.109
 sill-0.106
wheel-0.105
Token."
Token ID526
Feature activation-3.59e-04

Pos logit contributions
ls+0.091
cks+0.084
 vows+0.080
irs+0.078
ves+0.077
Neg logit contributions
wheel-0.070
 sill-0.069
hot-0.068
icle-0.063
 handy-0.062
Token She
Token ID1375
Feature activation-3.90e-03

Pos logit contributions
wheel+0.000
 sill+0.000
hot+0.000
uster+0.000
 aback+0.000
Neg logit contributions
ls-0.001
cks-0.001
 vows-0.001
irs-0.001
ves-0.001
Token said
Token ID531
Feature activation+4.07e-03

Pos logit contributions
wheel+0.007
 sill+0.007
hot+0.006
bar+0.006
 vest+0.006
Neg logit contributions
ls-0.007
cks-0.006
irs-0.006
 vows-0.006
 nations-0.005
Token to
Token ID284
Feature activation+9.14e-03

Pos logit contributions
ls+0.009
cks+0.009
irs+0.008
 nations+0.008
 vows+0.008
Neg logit contributions
wheel-0.005
hot-0.005
 sill-0.005
icle-0.005
 aback-0.004
TokenOne
Token ID3198
Feature activation-2.59e-03

Pos logit contributions
ls+0.031
cks+0.030
irs+0.029
 vows+0.029
ils+0.027
Neg logit contributions
 sill-0.015
hot-0.015
wheel-0.014
est-0.013
Whe-0.012
Token day
Token ID1110
Feature activation+1.31e-02

Pos logit contributions
wheel+0.004
 aback+0.004
uster+0.004
bar+0.004
hot+0.004
Neg logit contributions
ls-0.005
 vows-0.005
cks-0.005
ves-0.005
 runs-0.004
Token,
Token ID11
Feature activation-4.66e-03

Pos logit contributions
cks+0.040
irs+0.037
its+0.036
 nations+0.036
ils+0.036
Neg logit contributions
est-0.004
 3-0.004
hot-0.004
icle-0.003
 aback-0.003
Token Sara
Token ID24799
Feature activation+1.60e-02

Pos logit contributions
 sill+0.006
 3+0.006
icle+0.005
hot+0.005
Whe+0.005
Neg logit contributions
cks-0.010
irs-0.009
ls-0.009
 nations-0.009
ils-0.009
Token and
Token ID290
Feature activation+8.64e-03

Pos logit contributions
cks+0.034
irs+0.033
ls+0.033
 vows+0.032
ves+0.031
Neg logit contributions
 sill-0.020
my-0.019
wheel-0.019
 vest-0.019
est-0.018
Token Coco
Token ID48222
Feature activation+7.47e-02

Pos logit contributions
ls+0.017
cks+0.016
 vows+0.015
irs+0.015
ves+0.015
Neg logit contributions
wheel-0.012
hot-0.012
 sill-0.012
 vest-0.012
 Vest-0.011
Token go
Token ID467
Feature activation+8.70e-03

Pos logit contributions
cks+0.173
irs+0.157
ves+0.156
ls+0.154
ants+0.150
Neg logit contributions
hot-0.078
my-0.076
 happiest-0.075
wheel-0.075
 vest-0.074
Token to
Token ID284
Feature activation+2.18e-03

Pos logit contributions
ls+0.016
cks+0.015
 vows+0.014
irs+0.013
ves+0.013
Neg logit contributions
wheel-0.014
 sill-0.014
hot-0.013
uster-0.013
 aback-0.013
Token the
Token ID262
Feature activation-8.93e-03

Pos logit contributions
ls+0.004
cks+0.004
 vows+0.004
ves+0.004
irs+0.004
Neg logit contributions
wheel-0.003
 sill-0.003
hot-0.003
 aback-0.003
 vest-0.003
Token park
Token ID3952
Feature activation+1.71e-02

Pos logit contributions
wheel+0.015
 sill+0.015
hot+0.014
uster+0.014
 aback+0.014
Neg logit contributions
ls-0.016
 vows-0.014
cks-0.014
 nations-0.013
ves-0.013
Token with
Token ID351
Feature activation+2.22e-02

Pos logit contributions
ls+0.031
cks+0.028
 vows+0.027
ves+0.025
 nations+0.025
Neg logit contributions
wheel-0.028
 sill-0.027
hot-0.027
uster-0.027
icle-0.026
Token
Token ID198
Feature activation-6.39e-03

Pos logit contributions
ls+0.023
cks+0.021
irs+0.019
ves+0.019
 vows+0.019
Neg logit contributions
wheel-0.022
 sill-0.022
hot-0.021
icle-0.021
uster-0.020
Token
Token ID198
Feature activation-2.64e-03

Pos logit contributions
wheel+0.011
 sill+0.011
hot+0.010
icle+0.010
uster+0.010
Neg logit contributions
ls-0.011
cks-0.010
ves-0.010
 vows-0.010
irs-0.009
TokenS
Token ID50
Feature activation+1.05e-02

Pos logit contributions
 sill+0.004
wheel+0.004
icle+0.004
hot+0.004
uster+0.004
Neg logit contributions
ls-0.005
cks-0.004
 vows-0.004
ves-0.004
irs-0.004
Tokenki
Token ID4106
Feature activation-1.54e-02

Pos logit contributions
ls+0.023
cks+0.021
irs+0.020
 vows+0.020
ils+0.019
Neg logit contributions
 sill-0.014
wheel-0.013
hot-0.012
 knee-0.012
icle-0.012
Tokenpping
Token ID2105
Feature activation-6.54e-03

Pos logit contributions
wheel+0.026
 sill+0.025
hot+0.024
bar+0.024
est+0.023
Neg logit contributions
ls-0.027
cks-0.025
 vows-0.025
irs-0.023
 nations-0.022
Token mer
Token ID4017
Feature activation+7.47e-02

Pos logit contributions
wheel+0.011
 sill+0.010
hot+0.010
icle+0.010
uster+0.010
Neg logit contributions
ls-0.012
cks-0.011
 vows-0.010
ves-0.010
 runs-0.010
Tokenrily
Token ID28904
Feature activation+1.03e-02

Pos logit contributions
ls+0.129
cks+0.118
 vows+0.117
irs+0.117
 nations+0.116
Neg logit contributions
wheel-0.107
uster-0.107
est-0.106
 sill-0.105
imm-0.102
Token along
Token ID1863
Feature activation+1.15e-02

Pos logit contributions
ls+0.019
cks+0.017
 vows+0.016
irs+0.016
 nations+0.015
Neg logit contributions
wheel-0.017
 sill-0.017
hot-0.016
 aback-0.016
icle-0.015
Token,
Token ID11
Feature activation-1.96e-02

Pos logit contributions
ls+0.020
cks+0.019
 vows+0.018
ves+0.017
 nations+0.017
Neg logit contributions
wheel-0.019
 sill-0.019
hot-0.018
uster-0.018
icle-0.018
Token Hawk
Token ID26698
Feature activation+1.27e-02

Pos logit contributions
wheel+0.029
hot+0.028
 sill+0.028
icle+0.028
uster+0.028
Neg logit contributions
ls-0.037
cks-0.034
 vows-0.033
 runs-0.032
 cor-0.032
Token came
Token ID1625
Feature activation-3.10e-03

Pos logit contributions
ls+0.024
cks+0.022
 vows+0.021
irs+0.020
 nations+0.019
Neg logit contributions
wheel-0.020
 sill-0.020
hot-0.019
bar-0.018
 aback-0.018
Token and
Token ID290
Feature activation-1.71e-02

Pos logit contributions
wheel+0.027
 sill+0.026
icle+0.025
uster+0.025
bar+0.025
Neg logit contributions
ls-0.036
 vows-0.031
 runs-0.030
cks-0.030
 points-0.029
Token said
Token ID531
Feature activation+3.39e-03

Pos logit contributions
wheel+0.032
 sill+0.031
hot+0.030
uster+0.030
icle+0.030
Neg logit contributions
ls-0.028
cks-0.025
 vows-0.024
ves-0.022
 runs-0.022
Token "
Token ID366
Feature activation-3.33e-02

Pos logit contributions
cks+0.008
ls+0.008
 vows+0.007
irs+0.007
 nations+0.007
Neg logit contributions
wheel-0.004
hot-0.004
 sill-0.004
 aback-0.003
 knee-0.003
Tokenthank
Token ID40716
Feature activation+1.11e-03

Pos logit contributions
wheel+0.054
uster+0.054
 sill+0.053
 vest+0.052
 aback+0.051
Neg logit contributions
ls-0.053
cks-0.047
its-0.047
ves-0.045
 vows-0.045
Token you
Token ID345
Feature activation-1.55e-02

Pos logit contributions
ls+0.001
cks+0.000
 runs+0.000
ils+0.000
 them+0.000
Neg logit contributions
 sill-0.003
uster-0.003
inter-0.003
wheel-0.003
boat-0.003
Token"
Token ID1
Feature activation-8.01e-02

Pos logit contributions
wheel+0.030
Aid+0.030
Whe+0.029
 sill+0.029
 Vest+0.029
Neg logit contributions
ls-0.020
 vows-0.020
 their-0.019
 them-0.018
ves-0.017
Token to
Token ID284
Feature activation+3.88e-03

Pos logit contributions
 Vest+0.154
icle+0.154
uster+0.153
bar+0.153
initely+0.152
Neg logit contributions
ls-0.111
 they-0.091
 their-0.082
s-0.082
 runs-0.080
Token her
Token ID607
Feature activation-7.06e-03

Pos logit contributions
ls+0.006
cks+0.006
irs+0.005
 vows+0.005
 runs+0.005
Neg logit contributions
wheel-0.007
 sill-0.007
hot-0.007
 aback-0.007
uster-0.007
Token mom
Token ID1995
Feature activation-4.04e-02

Pos logit contributions
 aback+0.015
wheel+0.015
initely+0.015
 sill+0.014
hot+0.014
Neg logit contributions
ls-0.009
 their-0.008
 they-0.007
 vows-0.007
ies-0.007
Tokenmy
Token ID1820
Feature activation-2.98e-02

Pos logit contributions
uster+0.040
wheel+0.039
Aid+0.038
 Vest+0.038
Whe+0.037
Neg logit contributions
ls-0.091
cks-0.084
 their-0.083
 runs-0.083
ies-0.081
Token for
Token ID329
Feature activation+8.88e-04

Pos logit contributions
wheel+0.061
 sill+0.058
Aid+0.058
icle+0.058
uster+0.057
Neg logit contributions
ls-0.040
cks-0.034
 vows-0.033
 runs-0.031
 nations-0.031
Token understand
Token ID1833
Feature activation-1.56e-02

Pos logit contributions
wheel+0.001
 sill+0.001
bar+0.001
hot+0.001
icle+0.001
Neg logit contributions
ls-0.001
 vows-0.001
cks-0.001
 runs-0.001
 nations-0.001
Token what
Token ID644
Feature activation+9.64e-03

Pos logit contributions
wheel+0.026
 sill+0.025
uster+0.024
hot+0.024
bar+0.024
Neg logit contributions
ls-0.028
cks-0.026
 vows-0.024
 nations-0.023
ves-0.023
Token "
Token ID366
Feature activation-3.60e-02

Pos logit contributions
ls+0.017
cks+0.016
 vows+0.015
ves+0.015
 nations+0.014
Neg logit contributions
wheel-0.016
 sill-0.016
uster-0.015
hot-0.015
 aback-0.015
Tokenmod
Token ID4666
Feature activation-2.58e-02

Pos logit contributions
uster+0.051
wheel+0.050
 sill+0.049
 aback+0.048
 Vest+0.047
Neg logit contributions
ls-0.070
cks-0.064
ves-0.060
 vows-0.060
its-0.058
Tokenest
Token ID395
Feature activation-1.77e-02

Pos logit contributions
wheel+0.016
 sill+0.013
hot+0.013
Aid+0.013
uster+0.012
Neg logit contributions
ls-0.073
 vows-0.067
cks-0.067
 nations-0.065
its-0.065
Token"
Token ID1
Feature activation-7.98e-02

Pos logit contributions
wheel+0.028
 sill+0.028
hot+0.027
uster+0.026
icle+0.026
Neg logit contributions
ls-0.033
cks-0.030
 vows-0.029
irs-0.027
ves-0.027
Token meant
Token ID4001
Feature activation-2.18e-02

Pos logit contributions
uster+0.140
Aid+0.136
 Vest+0.135
 knee+0.129
initely+0.128
Neg logit contributions
ls-0.127
ves-0.105
 vows-0.102
 runs-0.098
 they-0.098
Token,
Token ID11
Feature activation-3.34e-02

Pos logit contributions
wheel+0.030
 sill+0.030
hot+0.029
icle+0.027
 aback+0.027
Neg logit contributions
ls-0.045
cks-0.042
 vows-0.040
irs-0.039
ils-0.037
Token but
Token ID475
Feature activation-1.95e-02

Pos logit contributions
Aid+0.038
uster+0.038
wheel+0.038
 Vest+0.038
 aback+0.037
Neg logit contributions
ls-0.070
 vows-0.063
ves-0.063
 points-0.063
cks-0.062
Token he
Token ID339
Feature activation-2.66e-03

Pos logit contributions
wheel+0.028
 sill+0.027
uster+0.026
hot+0.026
 aback+0.025
Neg logit contributions
ls-0.039
cks-0.036
 vows-0.035
ves-0.033
 nations-0.033
Token was
Token ID373
Feature activation-9.54e-03

Pos logit contributions
wheel+0.005
 sill+0.004
hot+0.004
 aback+0.004
icle+0.004
Neg logit contributions
ls-0.005
cks-0.004
 vows-0.004
irs-0.004
 nations-0.004
Token would
Token ID561
Feature activation+2.66e-02

Pos logit contributions
 sill+0.003
wheel+0.003
bar+0.003
 aback+0.003
 vest+0.003
Neg logit contributions
ls-0.004
cks-0.004
irs-0.004
 vows-0.003
 nations-0.003
Token whisper
Token ID31992
Feature activation+7.85e-03

Pos logit contributions
ls+0.053
cks+0.047
 vows+0.044
ves+0.043
irs+0.043
Neg logit contributions
 sill-0.042
wheel-0.041
hot-0.038
 vest-0.037
bar-0.037
Token "
Token ID366
Feature activation-2.99e-02

Pos logit contributions
ls+0.015
cks+0.014
 vows+0.014
irs+0.013
ves+0.013
Neg logit contributions
wheel-0.012
 sill-0.012
hot-0.011
 aback-0.010
uster-0.010
Tokenthank
Token ID40716
Feature activation-5.84e-03

Pos logit contributions
wheel+0.043
 sill+0.041
uster+0.040
hot+0.039
 aback+0.039
Neg logit contributions
ls-0.058
cks-0.054
 vows-0.052
irs-0.049
ves-0.049
Token you
Token ID345
Feature activation-6.76e-03

Pos logit contributions
wheel+0.013
 sill+0.012
uster+0.012
hot+0.012
icle+0.012
Neg logit contributions
ls-0.008
cks-0.007
 vows-0.006
ves-0.006
irs-0.006
Token"
Token ID1
Feature activation-7.96e-02

Pos logit contributions
wheel+0.013
 sill+0.013
hot+0.012
 aback+0.012
uster+0.012
Neg logit contributions
ls-0.010
 vows-0.009
cks-0.009
ves-0.008
irs-0.008
Token to
Token ID284
Feature activation+8.08e-03

Pos logit contributions
uster+0.137
 knee+0.136
icle+0.136
 Vest+0.136
bar+0.135
Neg logit contributions
ls-0.123
 vows-0.101
ves-0.098
 points-0.093
 runs-0.092
Token whoever
Token ID16958
Feature activation+1.01e-02

Pos logit contributions
ls+0.013
cks+0.012
 vows+0.012
irs+0.011
ves+0.011
Neg logit contributions
wheel-0.015
 sill-0.014
hot-0.014
uster-0.014
 aback-0.013
Token put
Token ID1234
Feature activation-2.80e-02

Pos logit contributions
ls+0.018
cks+0.017
irs+0.016
 vows+0.016
its+0.014
Neg logit contributions
wheel-0.017
 sill-0.017
hot-0.016
 aback-0.015
est-0.015
Token it
Token ID340
Feature activation-2.61e-02

Pos logit contributions
wheel+0.052
 sill+0.050
hot+0.048
uster+0.048
 aback+0.046
Neg logit contributions
ls-0.046
cks-0.041
 vows-0.039
ves-0.037
irs-0.036
Token there
Token ID612
Feature activation-1.06e-02

Pos logit contributions
wheel+0.036
 sill+0.035
hot+0.033
uster+0.032
 aback+0.032
Neg logit contributions
ls-0.054
cks-0.050
 vows-0.049
irs-0.046
ves-0.046
Token he
Token ID339
Feature activation-2.71e-02

Pos logit contributions
ls+0.012
cks+0.011
 vows+0.010
irs+0.010
ves+0.010
Neg logit contributions
wheel-0.008
 sill-0.008
hot-0.007
 aback-0.007
uster-0.007
Token said
Token ID531
Feature activation-5.98e-04

Pos logit contributions
wheel+0.052
 sill+0.051
hot+0.049
uster+0.048
icle+0.048
Neg logit contributions
ls-0.042
cks-0.037
 vows-0.037
ves-0.033
irs-0.033
Token "
Token ID366
Feature activation-4.07e-02

Pos logit contributions
wheel+0.001
 sill+0.001
uster+0.001
hot+0.001
bar+0.001
Neg logit contributions
ls-0.001
 vows-0.001
cks-0.001
ves-0.001
 runs-0.001
Tokenthank
Token ID40716
Feature activation-1.77e-03

Pos logit contributions
uster+0.058
wheel+0.056
 knee+0.055
 operation+0.055
inter+0.054
Neg logit contributions
ls-0.069
 vows-0.069
cks-0.067
 cor-0.065
ils-0.064
Token you
Token ID345
Feature activation-7.69e-03

Pos logit contributions
wheel+0.004
uster+0.004
inter+0.004
 sill+0.004
bar+0.004
Neg logit contributions
ls-0.002
cks-0.001
 vows-0.001
 cor-0.001
ils-0.001
Token"
Token ID1
Feature activation-7.85e-02

Pos logit contributions
wheel+0.016
 sill+0.016
 aback+0.016
Aid+0.016
uster+0.015
Neg logit contributions
 vows-0.010
ls-0.009
ves-0.008
cks-0.007
 cor-0.007
Token to
Token ID284
Feature activation+7.74e-03

Pos logit contributions
 knee+0.138
initely+0.136
uster+0.136
ivering+0.135
 operation+0.134
Neg logit contributions
ls-0.112
 they-0.090
ves-0.089
 vows-0.087
 runs-0.085
Token his
Token ID465
Feature activation+1.59e-03

Pos logit contributions
ls+0.013
cks+0.012
 vows+0.012
irs+0.011
ves+0.011
Neg logit contributions
hot-0.013
wheel-0.013
 sill-0.013
 aback-0.013
uster-0.012
Token mom
Token ID1995
Feature activation-2.09e-02

Pos logit contributions
ls+0.003
 vows+0.002
cks+0.002
 runs+0.002
ves+0.002
Neg logit contributions
wheel-0.003
hot-0.003
uster-0.003
 aback-0.003
 sill-0.003
Token.
Token ID13
Feature activation-1.33e-03

Pos logit contributions
wheel+0.040
uster+0.039
Aid+0.038
 aback+0.038
 sill+0.038
Neg logit contributions
ls-0.029
 vows-0.027
cks-0.026
 runs-0.024
 nations-0.023
Token
Token ID198
Feature activation-1.02e-02

Pos logit contributions
wheel+0.002
 sill+0.002
hot+0.002
 aback+0.002
uster+0.002
Neg logit contributions
ls-0.003
cks-0.002
 vows-0.002
irs-0.002
ves-0.002
Token know
Token ID760
Feature activation-3.34e-04

Pos logit contributions
 sill+0.006
bar+0.006
wheel+0.006
icle+0.006
 Vest+0.006
Neg logit contributions
ls-0.005
 vows-0.004
 runs-0.004
cks-0.004
 points-0.004
Token what
Token ID644
Feature activation+3.11e-03

Pos logit contributions
wheel+0.001
 sill+0.001
hot+0.001
uster+0.001
 aback+0.001
Neg logit contributions
ls-0.001
cks-0.000
 vows-0.000
irs-0.000
ves-0.000
Token "
Token ID366
Feature activation-3.65e-02

Pos logit contributions
ls+0.005
cks+0.005
 vows+0.005
ves+0.005
 nations+0.004
Neg logit contributions
 sill-0.006
wheel-0.005
uster-0.005
 aback-0.005
hot-0.005
Tokenmod
Token ID4666
Feature activation-2.56e-02

Pos logit contributions
 sill+0.052
wheel+0.051
uster+0.051
 Vest+0.048
 aback+0.048
Neg logit contributions
ls-0.071
cks-0.065
ves-0.060
 vows-0.060
its-0.059
Tokenest
Token ID395
Feature activation-8.69e-03

Pos logit contributions
wheel+0.019
 sill+0.016
Aid+0.016
 handy+0.016
uit+0.015
Neg logit contributions
ls-0.068
its-0.062
cks-0.061
 runs-0.061
 nations-0.060
Token"
Token ID1
Feature activation-7.80e-02

Pos logit contributions
wheel+0.013
 sill+0.012
hot+0.012
uster+0.011
icle+0.011
Neg logit contributions
ls-0.017
cks-0.016
 vows-0.015
irs-0.015
ves-0.014
Token meant
Token ID4001
Feature activation-2.42e-02

Pos logit contributions
uster+0.142
Aid+0.140
 Vest+0.138
initely+0.133
 knee+0.132
Neg logit contributions
ls-0.114
ves-0.092
 they-0.090
 their-0.088
s-0.087
Token,
Token ID11
Feature activation-3.17e-02

Pos logit contributions
wheel+0.038
 sill+0.037
hot+0.035
uster+0.035
Aid+0.034
Neg logit contributions
ls-0.045
cks-0.041
 vows-0.041
ves-0.038
 nations-0.037
Token but
Token ID475
Feature activation-2.22e-02

Pos logit contributions
Aid+0.033
 sill+0.033
wheel+0.033
iddle+0.033
 Vest+0.032
Neg logit contributions
ls-0.071
cks-0.063
 vows-0.063
ves-0.062
 they-0.062
Token he
Token ID339
Feature activation-2.88e-03

Pos logit contributions
wheel+0.036
 sill+0.035
uster+0.035
 aback+0.033
inter+0.032
Neg logit contributions
ls-0.040
cks-0.035
 vows-0.034
 runs-0.034
 their-0.034
Token knew
Token ID2993
Feature activation-2.12e-03

Pos logit contributions
wheel+0.005
 sill+0.005
hot+0.005
uster+0.005
 aback+0.005
Neg logit contributions
ls-0.005
cks-0.004
 vows-0.004
ves-0.004
irs-0.004
Token a
Token ID257
Feature activation+1.17e-02

Pos logit contributions
cks+0.002
ls+0.002
irs+0.002
 vows+0.002
 nations+0.002
Neg logit contributions
wheel-0.001
 sill-0.001
hot-0.001
 aback-0.001
icle-0.001
Token big
Token ID1263
Feature activation-1.57e-02

Pos logit contributions
ls+0.020
 vows+0.018
cks+0.018
ves+0.016
irs+0.016
Neg logit contributions
wheel-0.021
 sill-0.020
hot-0.019
uster-0.019
 aback-0.019
Token "
Token ID366
Feature activation-3.06e-02

Pos logit contributions
wheel+0.027
hot+0.026
uster+0.025
 sill+0.025
bar+0.024
Neg logit contributions
ls-0.028
 vows-0.026
 runs-0.026
 points-0.024
 nations-0.024
Tokenthank
Token ID40716
Feature activation-6.65e-03

Pos logit contributions
wheel+0.044
uster+0.043
 sill+0.042
 Vest+0.042
 vest+0.042
Neg logit contributions
ls-0.057
cks-0.053
 vows-0.052
ves-0.050
irs-0.049
Token you
Token ID345
Feature activation-1.38e-02

Pos logit contributions
wheel+0.016
 sill+0.015
uster+0.015
 vest+0.015
bar+0.015
Neg logit contributions
ls-0.007
cks-0.006
 vows-0.006
ves-0.005
 nations-0.005
Token"
Token ID1
Feature activation-7.80e-02

Pos logit contributions
wheel+0.029
 sill+0.028
Aid+0.027
 aback+0.027
 Vest+0.027
Neg logit contributions
ls-0.018
 vows-0.017
cks-0.015
ves-0.015
 nations-0.014
Token and
Token ID290
Feature activation-1.03e-02

Pos logit contributions
 Vest+0.138
uster+0.138
Aid+0.134
bar+0.134
wheel+0.134
Neg logit contributions
ls-0.122
 vows-0.099
ves-0.095
 runs-0.093
 points-0.093
Token smiled
Token ID13541
Feature activation-9.85e-03

Pos logit contributions
wheel+0.017
 sill+0.017
hot+0.015
 aback+0.015
 cleaner+0.015
Neg logit contributions
ls-0.019
cks-0.018
irs-0.016
 nations-0.016
 vows-0.015
Token.
Token ID13
Feature activation-6.71e-03

Pos logit contributions
wheel+0.020
Aid+0.018
uster+0.018
bar+0.018
hot+0.018
Neg logit contributions
ls-0.014
 vows-0.013
cks-0.012
 their-0.012
 points-0.011
Token Mama
Token ID40084
Feature activation-5.56e-03

Pos logit contributions
wheel+0.009
 sill+0.009
hot+0.008
uster+0.008
 aback+0.008
Neg logit contributions
ls-0.014
cks-0.013
 vows-0.013
irs-0.012
ves-0.012
Token p
Token ID279
Feature activation+4.23e-02

Pos logit contributions
wheel+0.010
 sill+0.009
hot+0.009
uster+0.009
 aback+0.009
Neg logit contributions
ls-0.010
cks-0.009
 vows-0.008
irs-0.008
ves-0.008
Token about
Token ID546
Feature activation+8.18e-03

Pos logit contributions
wheel+0.007
 sill+0.007
hot+0.006
 aback+0.006
 cleaner+0.006
Neg logit contributions
ls-0.012
cks-0.011
 vows-0.011
ves-0.010
irs-0.010
Token who
Token ID508
Feature activation+9.39e-04

Pos logit contributions
ls+0.018
cks+0.017
 vows+0.016
ves+0.016
irs+0.015
Neg logit contributions
wheel-0.010
 sill-0.010
 operation-0.010
 3-0.009
 happiest-0.009
Token has
Token ID468
Feature activation-2.04e-02

Pos logit contributions
ls+0.002
 vows+0.002
cks+0.002
irs+0.001
ves+0.001
Neg logit contributions
wheel-0.001
 sill-0.001
 aback-0.001
hot-0.001
 operation-0.001
Token the
Token ID262
Feature activation-3.81e-02

Pos logit contributions
 sill+0.027
wheel+0.026
 aback+0.025
 cleaner+0.024
hot+0.023
Neg logit contributions
ls-0.044
cks-0.042
 vows-0.039
irs-0.038
ves-0.038
Token sh
Token ID427
Feature activation-2.38e-02

Pos logit contributions
wheel+0.060
hot+0.057
uster+0.054
 sill+0.053
 aback+0.053
Neg logit contributions
ls-0.068
 vows-0.064
 nations-0.062
cks-0.060
 cor-0.060
Tokenini
Token ID5362
Feature activation-7.71e-02

Pos logit contributions
hot+0.026
wheel+0.026
 Vest+0.025
 aback+0.024
 vest+0.024
Neg logit contributions
ls-0.054
cks-0.052
its-0.050
ves-0.049
irs-0.045
Tokenest
Token ID395
Feature activation-8.41e-03

Pos logit contributions
wheel+0.066
uster+0.066
hot+0.065
 handy+0.060
uit+0.055
Neg logit contributions
ls-0.173
 vows-0.167
 runs-0.165
 cor-0.164
 points-0.162
Token gem
Token ID16840
Feature activation-1.90e-02

Pos logit contributions
wheel+0.014
 sill+0.013
hot+0.013
uster+0.012
 aback+0.012
Neg logit contributions
ls-0.015
cks-0.014
 vows-0.014
ves-0.013
irs-0.013
Token or
Token ID393
Feature activation-9.87e-03

Pos logit contributions
wheel+0.029
 sill+0.028
hot+0.027
 vest+0.025
 aback+0.025
Neg logit contributions
ls-0.036
cks-0.034
 vows-0.033
irs-0.032
ves-0.031
Token the
Token ID262
Feature activation-1.78e-02

Pos logit contributions
 sill+0.014
wheel+0.013
 vest+0.013
 happiest+0.012
bar+0.012
Neg logit contributions
ls-0.021
cks-0.019
 vows-0.018
ves-0.018
irs-0.018
Token best
Token ID1266
Feature activation+5.69e-03

Pos logit contributions
wheel+0.028
 sill+0.026
hot+0.026
uster+0.025
 aback+0.025
Neg logit contributions
ls-0.033
cks-0.031
 vows-0.030
 nations-0.028
 cor-0.028
Token really
Token ID1107
Feature activation+1.25e-02

Pos logit contributions
wheel+0.003
 sill+0.003
icle+0.003
uit+0.003
bar+0.003
Neg logit contributions
ls-0.002
 vows-0.002
cks-0.002
 runs-0.002
 nations-0.002
Token understand
Token ID1833
Feature activation-1.46e-02

Pos logit contributions
ls+0.025
cks+0.023
 vows+0.023
irs+0.021
ves+0.021
Neg logit contributions
wheel-0.018
 sill-0.018
hot-0.017
uster-0.016
 aback-0.016
Token what
Token ID644
Feature activation+7.38e-03

Pos logit contributions
wheel+0.026
 sill+0.026
uster+0.024
hot+0.024
bar+0.024
Neg logit contributions
ls-0.024
cks-0.022
 vows-0.021
ves-0.020
 nations-0.020
Token "
Token ID366
Feature activation-4.25e-02

Pos logit contributions
ls+0.013
cks+0.012
 vows+0.012
ves+0.011
 nations+0.011
Neg logit contributions
 sill-0.012
wheel-0.012
uster-0.012
hot-0.011
 aback-0.011
Tokenvalue
Token ID8367
Feature activation-3.57e-03

Pos logit contributions
uster+0.062
 sill+0.059
wheel+0.059
 Vest+0.057
 knee+0.057
Neg logit contributions
ls-0.080
cks-0.072
its-0.068
ves-0.067
 vows-0.065
Token"
Token ID1
Feature activation-7.69e-02

Pos logit contributions
wheel+0.006
hot+0.006
 sill+0.006
uster+0.006
icle+0.006
Neg logit contributions
ls-0.006
cks-0.006
 vows-0.005
irs-0.005
 nations-0.005
Token meant
Token ID4001
Feature activation-3.05e-02

Pos logit contributions
uster+0.144
 Vest+0.138
Aid+0.136
initely+0.132
 knee+0.131
Neg logit contributions
ls-0.111
 they-0.089
 their-0.088
ves-0.087
 them-0.087
Token,
Token ID11
Feature activation-2.87e-02

Pos logit contributions
wheel+0.051
 sill+0.050
Aid+0.047
uster+0.047
hot+0.047
Neg logit contributions
ls-0.053
cks-0.048
 vows-0.046
ves-0.044
 points-0.043
Token but
Token ID475
Feature activation-2.16e-02

Pos logit contributions
wheel+0.034
 aback+0.033
Aid+0.033
uster+0.033
 Vest+0.033
Neg logit contributions
ls-0.057
 their-0.054
 they-0.053
 cor-0.052
ves-0.052
Token he
Token ID339
Feature activation-4.01e-03

Pos logit contributions
uster+0.039
wheel+0.039
 aback+0.037
hot+0.036
 sill+0.036
Neg logit contributions
ls-0.034
 their-0.031
 vows-0.030
 runs-0.029
 they-0.029
Token knew
Token ID2993
Feature activation-1.10e-03

Pos logit contributions
wheel+0.007
 sill+0.007
hot+0.007
uster+0.007
 aback+0.007
Neg logit contributions
ls-0.006
cks-0.006
 vows-0.006
ves-0.005
ils-0.005
Token understanding
Token ID4547
Feature activation-7.91e-04

Pos logit contributions
wheel+0.073
hot+0.070
uster+0.070
icle+0.068
inter+0.065
Neg logit contributions
ls-0.080
cks-0.076
 vows-0.073
 points-0.071
 runs-0.071
Token now
Token ID783
Feature activation-2.90e-02

Pos logit contributions
wheel+0.001
 sill+0.001
hot+0.001
uster+0.001
 aback+0.001
Neg logit contributions
ls-0.002
cks-0.001
 vows-0.001
irs-0.001
ves-0.001
Token what
Token ID644
Feature activation+8.70e-03

Pos logit contributions
wheel+0.044
 sill+0.043
hot+0.041
uster+0.040
 aback+0.039
Neg logit contributions
ls-0.057
cks-0.052
 vows-0.051
irs-0.048
ves-0.047
Token "
Token ID366
Feature activation-3.56e-02

Pos logit contributions
ls+0.015
cks+0.014
 vows+0.013
irs+0.012
ves+0.012
Neg logit contributions
wheel-0.015
 sill-0.015
hot-0.014
 aback-0.014
 vest-0.014
Tokenrepeat
Token ID44754
Feature activation-4.50e-03

Pos logit contributions
wheel+0.053
uster+0.052
 sill+0.051
 vest+0.050
 Vest+0.050
Neg logit contributions
ls-0.066
cks-0.060
 vows-0.057
ves-0.057
irs-0.054
Token"
Token ID1
Feature activation-7.63e-02

Pos logit contributions
wheel+0.007
 sill+0.007
hot+0.007
uster+0.007
 aback+0.007
Neg logit contributions
ls-0.008
cks-0.007
 vows-0.007
irs-0.007
ves-0.007
Token meant
Token ID4001
Feature activation-3.15e-02

Pos logit contributions
uster+0.129
 Vest+0.128
icle+0.124
wheel+0.124
Aid+0.124
Neg logit contributions
ls-0.124
 vows-0.099
ves-0.097
 runs-0.097
 points-0.097
Token.
Token ID13
Feature activation-1.69e-02

Pos logit contributions
wheel+0.048
 sill+0.047
hot+0.045
uster+0.043
 aback+0.043
Neg logit contributions
ls-0.061
cks-0.056
 vows-0.054
irs-0.051
ves-0.051
Token<|endoftext|>
Token ID50256
Feature activation-2.79e-02

Pos logit contributions
wheel+0.029
 sill+0.027
uster+0.027
 Vest+0.026
 vest+0.026
Neg logit contributions
ls-0.027
irs-0.025
 vows-0.024
cks-0.024
 runs-0.023
TokenOnce
Token ID7454
Feature activation+1.99e-02

Pos logit contributions
wheel+0.051
 sill+0.050
hot+0.047
uster+0.047
bar+0.046
Neg logit contributions
ls-0.046
cks-0.041
 vows-0.039
irs-0.037
ves-0.037
Token upon
Token ID2402
Feature activation-1.76e-02

Pos logit contributions
ls+0.036
cks+0.034
 vows+0.033
ves+0.030
irs+0.030
Neg logit contributions
wheel-0.031
 sill-0.031
hot-0.030
uster-0.029
 aback-0.028
Token,
Token ID11
Feature activation-2.11e-02

Pos logit contributions
wheel+0.001
 sill+0.001
hot+0.001
 aback+0.001
uster+0.001
Neg logit contributions
ls-0.002
cks-0.002
 vows-0.002
irs-0.002
 nations-0.002
Token "
Token ID366
Feature activation-2.14e-02

Pos logit contributions
wheel+0.032
 sill+0.031
hot+0.030
uster+0.029
 aback+0.029
Neg logit contributions
ls-0.040
 vows-0.037
cks-0.036
ves-0.034
irs-0.033
TokenYou
Token ID1639
Feature activation+3.99e-03

Pos logit contributions
wheel+0.036
 knee+0.034
inter+0.033
 vest+0.033
 operation+0.033
Neg logit contributions
ls-0.033
 vows-0.032
cks-0.032
irs-0.030
 cor-0.030
Token're
Token ID821
Feature activation-7.42e-03

Pos logit contributions
ls+0.006
 vows+0.006
cks+0.005
 nations+0.005
irs+0.005
Neg logit contributions
wheel-0.008
 sill-0.007
hot-0.007
uster-0.007
icle-0.007
Token welcome
Token ID7062
Feature activation+1.08e-02

Pos logit contributions
uster+0.012
wheel+0.011
inter+0.011
Aid+0.011
 vest+0.011
Neg logit contributions
cks-0.013
 their-0.013
 vows-0.011
 runs-0.011
 our-0.011
Token"
Token ID1
Feature activation-7.62e-02

Pos logit contributions
ls+0.017
 vows+0.015
cks+0.014
 cor+0.014
 runs+0.014
Neg logit contributions
wheel-0.021
 sill-0.019
bar-0.019
hot-0.019
Aid-0.019
Token before
Token ID878
Feature activation+1.06e-02

Pos logit contributions
wheel+0.125
 sill+0.116
 vest+0.116
icle+0.115
 knee+0.115
Neg logit contributions
ls-0.139
 vows-0.115
cks-0.113
 cor-0.110
 points-0.109
Token returning
Token ID8024
Feature activation+6.61e-03

Pos logit contributions
ls+0.020
 vows+0.020
ils+0.019
cks+0.019
 nations+0.019
Neg logit contributions
wheel-0.016
 sill-0.015
hot-0.014
 handy-0.014
uit-0.014
Token to
Token ID284
Feature activation-6.56e-04

Pos logit contributions
ls+0.012
cks+0.011
 vows+0.011
irs+0.010
ves+0.010
Neg logit contributions
wheel-0.011
 sill-0.011
hot-0.010
uster-0.010
 aback-0.010
Token his
Token ID465
Feature activation-9.29e-03

Pos logit contributions
wheel+0.001
 sill+0.001
hot+0.001
uster+0.001
 aback+0.001
Neg logit contributions
ls-0.001
cks-0.001
 vows-0.001
irs-0.001
ves-0.001
Token stable
Token ID8245
Feature activation-5.58e-03

Pos logit contributions
 sill+0.013
wheel+0.013
hot+0.012
 vest+0.012
 aback+0.011
Neg logit contributions
ls-0.019
cks-0.018
 vows-0.017
irs-0.017
ves-0.017
Token for
Token ID329
Feature activation+5.47e-03

Pos logit contributions
wheel+0.014
 sill+0.014
icle+0.013
uster+0.013
Aid+0.013
Neg logit contributions
ls-0.017
 vows-0.015
cks-0.015
 runs-0.014
ils-0.014
Token explaining
Token ID11170
Feature activation+1.35e-02

Pos logit contributions
ls+0.009
cks+0.009
 vows+0.008
irs+0.008
 nations+0.008
Neg logit contributions
wheel-0.009
 sill-0.009
uster-0.009
hot-0.009
 aback-0.008
Token what
Token ID644
Feature activation+1.90e-02

Pos logit contributions
ls+0.026
cks+0.024
 vows+0.023
irs+0.022
ves+0.021
Neg logit contributions
wheel-0.021
 sill-0.021
hot-0.020
 aback-0.019
icle-0.019
Token "
Token ID366
Feature activation-4.58e-02

Pos logit contributions
ls+0.035
cks+0.035
irs+0.031
 vows+0.031
its+0.030
Neg logit contributions
wheel-0.031
hot-0.029
 sill-0.028
 vest-0.028
 Vest-0.027
Tokentrade
Token ID25351
Feature activation+1.26e-03

Pos logit contributions
 sill+0.062
uster+0.060
 knee+0.058
wheel+0.057
 Vest+0.056
Neg logit contributions
ls-0.092
cks-0.082
ves-0.078
 vows-0.078
ils-0.077
Token"
Token ID1
Feature activation-7.58e-02

Pos logit contributions
ls+0.002
cks+0.002
 vows+0.002
irs+0.002
ves+0.002
Neg logit contributions
wheel-0.002
 sill-0.002
hot-0.002
uster-0.002
 aback-0.002
Token meant
Token ID4001
Feature activation-2.33e-02

Pos logit contributions
 Vest+0.132
uster+0.131
bar+0.130
 knee+0.128
Aid+0.127
Neg logit contributions
ls-0.111
ves-0.092
 runs-0.088
 they-0.088
 vows-0.087
Token.
Token ID13
Feature activation-9.24e-03

Pos logit contributions
wheel+0.037
 sill+0.037
hot+0.035
Aid+0.034
uster+0.034
Neg logit contributions
ls-0.042
cks-0.038
 vows-0.038
ves-0.035
irs-0.035
Token From
Token ID3574
Feature activation-2.20e-02

Pos logit contributions
wheel+0.014
 sill+0.014
hot+0.013
uster+0.013
 aback+0.013
Neg logit contributions
ls-0.018
cks-0.016
 vows-0.016
irs-0.015
ves-0.015
Token that
Token ID326
Feature activation-3.59e-02

Pos logit contributions
wheel+0.035
 sill+0.034
uster+0.034
est+0.033
inter+0.033
Neg logit contributions
ls-0.043
cks-0.039
 vows-0.035
 their-0.035
 nations-0.034
Token day
Token ID1110
Feature activation-2.24e-02

Pos logit contributions
wheel+0.054
 sill+0.051
uster+0.050
hot+0.048
 aback+0.048
Neg logit contributions
ls-0.069
 vows-0.063
ves-0.062
 runs-0.062
cks-0.061
Token and
Token ID290
Feature activation-2.18e-02

Pos logit contributions
wheel+0.011
 sill+0.010
uster+0.010
hot+0.010
icle+0.009
Neg logit contributions
ls-0.014
cks-0.013
 vows-0.012
 points-0.012
 runs-0.012
Token said
Token ID531
Feature activation+6.75e-03

Pos logit contributions
wheel+0.031
 sill+0.031
hot+0.028
 aback+0.027
 vest+0.026
Neg logit contributions
ls-0.045
cks-0.043
irs-0.040
 vows-0.040
 nations-0.039
Token "
Token ID366
Feature activation-3.40e-02

Pos logit contributions
ls+0.014
cks+0.013
 vows+0.012
irs+0.012
 nations+0.012
Neg logit contributions
wheel-0.009
 sill-0.009
hot-0.009
 aback-0.008
icle-0.008
Tokenthank
Token ID40716
Feature activation-1.45e-03

Pos logit contributions
uster+0.047
wheel+0.047
 knee+0.046
 operation+0.044
inter+0.044
Neg logit contributions
ls-0.062
 vows-0.058
cks-0.058
ves-0.054
 cor-0.054
Token you
Token ID345
Feature activation-1.52e-02

Pos logit contributions
wheel+0.003
 sill+0.003
uster+0.003
 vest+0.003
bar+0.003
Neg logit contributions
ls-0.002
cks-0.001
 vows-0.001
ils-0.001
ves-0.001
Token"
Token ID1
Feature activation-7.54e-02

Pos logit contributions
wheel+0.032
Aid+0.031
 sill+0.031
 aback+0.030
 Vest+0.030
Neg logit contributions
ls-0.019
 vows-0.019
cks-0.016
ves-0.016
 nations-0.015
Token to
Token ID284
Feature activation+2.81e-03

Pos logit contributions
wheel+0.132
uster+0.132
 Vest+0.132
 sill+0.131
Aid+0.130
Neg logit contributions
ls-0.120
 vows-0.097
ves-0.093
 they-0.091
 their-0.091
Token its
Token ID663
Feature activation-7.29e-03

Pos logit contributions
ls+0.005
cks+0.005
 vows+0.004
irs+0.004
 runs+0.004
Neg logit contributions
wheel-0.005
 sill-0.005
hot-0.005
uster-0.005
 aback-0.004
Token friends
Token ID2460
Feature activation-3.65e-03

Pos logit contributions
wheel+0.013
hot+0.013
uster+0.013
 sill+0.012
 aback+0.012
Neg logit contributions
ls-0.012
 vows-0.011
cks-0.010
 nations-0.010
 runs-0.010
Token.
Token ID13
Feature activation-2.49e-03

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.006
uster+0.006
 aback+0.006
Neg logit contributions
ls-0.006
cks-0.006
 vows-0.006
ves-0.005
irs-0.005
Token The
Token ID383
Feature activation-5.29e-03

Pos logit contributions
wheel+0.004
 sill+0.004
hot+0.004
uster+0.004
 aback+0.004
Neg logit contributions
ls-0.005
cks-0.004
 vows-0.004
irs-0.004
ves-0.004
Token remembered
Token ID12086
Feature activation-3.53e-03

Pos logit contributions
wheel+0.034
 sill+0.033
hot+0.032
uster+0.031
icle+0.031
Neg logit contributions
ls-0.030
cks-0.027
 vows-0.026
irs-0.024
ves-0.024
Token to
Token ID284
Feature activation+3.62e-03

Pos logit contributions
wheel+0.005
 sill+0.005
hot+0.005
 aback+0.005
icle+0.005
Neg logit contributions
ls-0.007
cks-0.007
 vows-0.006
ves-0.006
irs-0.006
Token say
Token ID910
Feature activation-4.32e-03

Pos logit contributions
ls+0.006
cks+0.006
 vows+0.006
irs+0.005
ves+0.005
Neg logit contributions
wheel-0.006
 sill-0.006
hot-0.006
uster-0.006
 aback-0.006
Token "
Token ID366
Feature activation-5.60e-02

Pos logit contributions
wheel+0.007
 sill+0.007
hot+0.007
uster+0.006
 aback+0.006
Neg logit contributions
ls-0.008
cks-0.007
 vows-0.007
ves-0.006
irs-0.006
Tokenplease
Token ID29688
Feature activation+1.36e-02

Pos logit contributions
 sill+0.075
 knee+0.073
wheel+0.073
uster+0.073
 vest+0.073
Neg logit contributions
ls-0.105
cks-0.096
 vows-0.091
irs-0.091
ves-0.090
Token"
Token ID1
Feature activation-7.51e-02

Pos logit contributions
ls+0.023
cks+0.020
 vows+0.020
irs+0.018
ves+0.018
Neg logit contributions
wheel-0.025
 sill-0.024
hot-0.023
uster-0.022
icle-0.022
Token whenever
Token ID8797
Feature activation+1.21e-02

Pos logit contributions
 Vest+0.125
uster+0.123
Aid+0.122
bar+0.121
 vest+0.118
Neg logit contributions
ls-0.119
 vows-0.099
ves-0.098
 they-0.094
 runs-0.093
Token she
Token ID673
Feature activation-1.05e-02

Pos logit contributions
ls+0.022
cks+0.021
 vows+0.020
irs+0.019
ves+0.018
Neg logit contributions
wheel-0.020
 sill-0.019
hot-0.019
 aback-0.018
icle-0.018
Token wanted
Token ID2227
Feature activation-1.92e-02

Pos logit contributions
wheel+0.021
 sill+0.020
hot+0.020
 aback+0.019
uster+0.019
Neg logit contributions
ls-0.016
cks-0.014
 vows-0.014
irs-0.013
ves-0.012
Token something
Token ID1223
Feature activation+8.55e-03

Pos logit contributions
wheel+0.030
 sill+0.030
hot+0.029
 aback+0.028
icle+0.027
Neg logit contributions
ls-0.037
cks-0.034
 vows-0.032
irs-0.031
ves-0.030
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
ls+0.015
cks+0.014
 vows+0.013
ves+0.013
irs+0.012
Neg logit contributions
wheel-0.014
 sill-0.014
hot-0.013
uster-0.013
icle-0.013
Token He
Token ID679
Feature activation+1.90e-03

Pos logit contributions
wheel+0.011
hot+0.009
uster+0.009
Aid+0.009
icle+0.009
Neg logit contributions
ls-0.019
 vows-0.018
cks-0.017
 runs-0.017
 points-0.017
Token said
Token ID531
Feature activation+5.51e-03

Pos logit contributions
ls+0.003
cks+0.003
 vows+0.003
irs+0.003
 nations+0.003
Neg logit contributions
wheel-0.003
 sill-0.003
hot-0.003
bar-0.003
 aback-0.003
Token "
Token ID366
Feature activation-2.34e-02

Pos logit contributions
ls+0.011
cks+0.011
 vows+0.010
irs+0.010
ves+0.010
Neg logit contributions
wheel-0.008
 sill-0.007
hot-0.007
 aback-0.007
icle-0.007
Tokenthank
Token ID40716
Feature activation+1.82e-03

Pos logit contributions
wheel+0.035
 sill+0.034
uster+0.033
 knee+0.033
 vest+0.033
Neg logit contributions
ls-0.041
cks-0.039
 vows-0.037
irs-0.036
ves-0.035
Token you
Token ID345
Feature activation-1.19e-02

Pos logit contributions
ls+0.002
cks+0.002
 vows+0.002
 nations+0.001
ves+0.001
Neg logit contributions
wheel-0.004
 sill-0.004
uster-0.004
icle-0.004
hot-0.004
Token"
Token ID1
Feature activation-7.51e-02

Pos logit contributions
wheel+0.026
 sill+0.025
Aid+0.025
 aback+0.024
 Vest+0.024
Neg logit contributions
ls-0.014
 vows-0.013
ves-0.012
cks-0.011
 their-0.011
Token to
Token ID284
Feature activation+7.31e-03

Pos logit contributions
 Vest+0.128
uster+0.127
Aid+0.126
initely+0.126
wheel+0.126
Neg logit contributions
ls-0.121
 they-0.094
 vows-0.093
ves-0.093
 runs-0.091
Token Tina
Token ID35903
Feature activation-2.29e-02

Pos logit contributions
ls+0.013
cks+0.012
 vows+0.011
irs+0.011
ves+0.011
Neg logit contributions
wheel-0.012
 sill-0.012
hot-0.012
uster-0.011
 aback-0.011
Token and
Token ID290
Feature activation+4.42e-03

Pos logit contributions
wheel+0.044
 sill+0.043
Aid+0.042
hot+0.042
icle+0.041
Neg logit contributions
ls-0.034
cks-0.029
 vows-0.029
ves-0.026
 runs-0.026
Token told
Token ID1297
Feature activation+1.95e-02

Pos logit contributions
ls+0.007
cks+0.007
 vows+0.006
irs+0.006
ves+0.006
Neg logit contributions
wheel-0.008
 sill-0.008
hot-0.008
uster-0.007
 aback-0.007
Token her
Token ID607
Feature activation+1.08e-02

Pos logit contributions
ls+0.028
cks+0.025
 vows+0.024
ves+0.022
irs+0.022
Neg logit contributions
wheel-0.040
 sill-0.039
hot-0.038
uster-0.037
 aback-0.037
Token He
Token ID679
Feature activation-3.67e-03

Pos logit contributions
wheel+0.010
 sill+0.009
hot+0.009
uster+0.009
 cleaner+0.008
Neg logit contributions
ls-0.015
 vows-0.014
cks-0.014
irs-0.013
 nations-0.013
Token even
Token ID772
Feature activation-1.10e-02

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.006
 aback+0.006
bar+0.005
Neg logit contributions
ls-0.007
cks-0.006
 vows-0.006
irs-0.006
ves-0.005
Token said
Token ID531
Feature activation-4.21e-03

Pos logit contributions
wheel+0.019
 sill+0.019
hot+0.018
 aback+0.017
uster+0.017
Neg logit contributions
ls-0.019
cks-0.018
 vows-0.017
irs-0.016
ves-0.016
Token "
Token ID366
Feature activation-2.80e-02

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.005
 aback+0.005
icle+0.005
Neg logit contributions
ls-0.009
cks-0.008
 vows-0.008
irs-0.008
 nations-0.007
Tokensorry
Token ID41599
Feature activation-1.15e-02

Pos logit contributions
wheel+0.042
 sill+0.041
uster+0.040
 knee+0.040
 vest+0.039
Neg logit contributions
ls-0.050
cks-0.047
 vows-0.046
ves-0.044
irs-0.044
Token"
Token ID1
Feature activation-7.46e-02

Pos logit contributions
 sill+0.023
wheel+0.023
uster+0.022
bar+0.022
Aid+0.022
Neg logit contributions
ls-0.015
 vows-0.014
ves-0.013
cks-0.013
 nations-0.012
Token when
Token ID618
Feature activation+1.52e-02

Pos logit contributions
 Vest+0.123
Aid+0.122
uster+0.121
initely+0.119
 knee+0.118
Neg logit contributions
ls-0.114
ves-0.096
 vows-0.092
 they-0.092
 their-0.091
Token he
Token ID339
Feature activation+1.45e-04

Pos logit contributions
ls+0.033
cks+0.031
 vows+0.030
irs+0.028
ils+0.028
Neg logit contributions
wheel-0.020
 sill-0.019
hot-0.018
icle-0.017
 vest-0.017
Token didn
Token ID1422
Feature activation-3.93e-03

Pos logit contributions
ls+0.000
cks+0.000
irs+0.000
 vows+0.000
 nations+0.000
Neg logit contributions
wheel-0.000
 sill-0.000
hot-0.000
 vest-0.000
est-0.000
Token't
Token ID470
Feature activation-1.27e-02

Pos logit contributions
wheel+0.007
 sill+0.006
hot+0.006
icle+0.006
uster+0.006
Neg logit contributions
ls-0.007
cks-0.006
 vows-0.006
 nations-0.006
ils-0.006
Token mean
Token ID1612
Feature activation-2.00e-03

Pos logit contributions
wheel+0.020
 sill+0.019
hot+0.018
 aback+0.017
icle+0.017
Neg logit contributions
ls-0.026
cks-0.024
 vows-0.023
ves-0.022
irs-0.022
Token and
Token ID290
Feature activation-1.23e-02

Pos logit contributions
wheel+0.040
Aid+0.040
uster+0.039
 aback+0.039
 sill+0.039
Neg logit contributions
ls-0.046
 vows-0.041
ves-0.040
cks-0.039
ils-0.037
Token put
Token ID1234
Feature activation-2.23e-02

Pos logit contributions
wheel+0.020
 sill+0.019
 vest+0.018
 cleaner+0.017
 3+0.017
Neg logit contributions
cks-0.023
ls-0.023
irs-0.020
its-0.020
 nations-0.019
Token on
Token ID319
Feature activation+3.46e-03

Pos logit contributions
wheel+0.045
 sill+0.044
hot+0.043
uster+0.042
 aback+0.041
Neg logit contributions
ls-0.033
cks-0.029
 vows-0.028
irs-0.025
ves-0.025
Token her
Token ID607
Feature activation-2.49e-02

Pos logit contributions
ls+0.007
cks+0.006
its+0.006
 nations+0.006
 vows+0.006
Neg logit contributions
 sill-0.005
wheel-0.005
 vest-0.005
hot-0.005
 Vest-0.005
Token sh
Token ID427
Feature activation-2.86e-02

Pos logit contributions
wheel+0.039
 sill+0.038
hot+0.037
uster+0.035
 aback+0.035
Neg logit contributions
ls-0.047
cks-0.043
 vows-0.042
ves-0.040
irs-0.039
Tokenini
Token ID5362
Feature activation-7.46e-02

Pos logit contributions
hot+0.041
wheel+0.038
 happiest+0.036
 Boy+0.035
 Doctor+0.034
Neg logit contributions
cks-0.057
ves-0.054
 vows-0.052
its-0.050
ls-0.049
Tokenest
Token ID395
Feature activation-9.91e-03

Pos logit contributions
wheel+0.105
hot+0.098
 sill+0.092
 hesitant+0.090
uster+0.090
Neg logit contributions
ls-0.148
 vows-0.146
ves-0.131
ils-0.131
cks-0.130
Token shoes
Token ID10012
Feature activation-9.58e-03

Pos logit contributions
wheel+0.014
 sill+0.014
hot+0.013
 vest+0.013
uster+0.013
Neg logit contributions
ls-0.020
cks-0.019
 vows-0.018
irs-0.017
ves-0.017
Token.
Token ID13
Feature activation-6.52e-03

Pos logit contributions
wheel+0.016
 sill+0.016
hot+0.015
uster+0.015
 aback+0.015
Neg logit contributions
ls-0.017
cks-0.015
 vows-0.015
ves-0.014
irs-0.014
Token
Token ID198
Feature activation-6.13e-03

Pos logit contributions
wheel+0.010
 sill+0.010
hot+0.009
icle+0.009
bar+0.009
Neg logit contributions
ls-0.012
 vows-0.011
cks-0.011
irs-0.010
 runs-0.010
Token
Token ID198
Feature activation+1.30e-03

Pos logit contributions
wheel+0.008
 sill+0.008
hot+0.008
uster+0.007
 aback+0.007
Neg logit contributions
ls-0.013
cks-0.012
 vows-0.012
 nations-0.011
irs-0.011
Token Mia
Token ID32189
Feature activation+2.04e-02

Pos logit contributions
wheel+0.003
 sill+0.003
hot+0.003
uster+0.003
 aback+0.003
Neg logit contributions
ls-0.003
cks-0.003
 vows-0.003
irs-0.003
ves-0.003
Token said
Token ID531
Feature activation+5.28e-03

Pos logit contributions
ls+0.039
cks+0.039
irs+0.037
 vows+0.035
 nations+0.034
Neg logit contributions
wheel-0.031
 sill-0.028
 vest-0.027
hot-0.026
bar-0.026
Token "
Token ID366
Feature activation-2.23e-02

Pos logit contributions
cks+0.012
ls+0.012
irs+0.011
 nations+0.010
 vows+0.010
Neg logit contributions
wheel-0.007
 sill-0.006
hot-0.006
est-0.006
 aback-0.006
Tokenthank
Token ID40716
Feature activation+3.34e-03

Pos logit contributions
wheel+0.035
 aback+0.033
uster+0.033
 sill+0.033
 knee+0.032
Neg logit contributions
ls-0.038
 vows-0.036
cks-0.036
ves-0.034
irs-0.034
Token you
Token ID345
Feature activation-1.00e-02

Pos logit contributions
ls+0.004
cks+0.003
 vows+0.002
 runs+0.002
ils+0.002
Neg logit contributions
wheel-0.008
uster-0.008
 sill-0.008
inter-0.008
icle-0.008
Token"
Token ID1
Feature activation-7.40e-02

Pos logit contributions
wheel+0.021
 aback+0.021
Aid+0.020
 sill+0.020
uster+0.019
Neg logit contributions
ls-0.013
 vows-0.013
ves-0.011
 their-0.010
 nations-0.010
Token for
Token ID329
Feature activation+8.70e-03

Pos logit contributions
uster+0.145
bar+0.141
 Vest+0.141
Aid+0.138
initely+0.137
Neg logit contributions
ls-0.107
 vows-0.082
 they-0.081
 runs-0.081
ves-0.080
Token the
Token ID262
Feature activation+2.80e-03

Pos logit contributions
ls+0.014
cks+0.014
 vows+0.013
irs+0.012
ves+0.012
Neg logit contributions
wheel-0.015
 sill-0.015
hot-0.014
uster-0.014
 aback-0.014
Token fun
Token ID1257
Feature activation+6.80e-03

Pos logit contributions
ls+0.005
 vows+0.005
cks+0.004
 runs+0.004
 points+0.004
Neg logit contributions
wheel-0.005
 sill-0.004
hot-0.004
uster-0.004
bar-0.004
Token she
Token ID673
Feature activation-1.03e-02

Pos logit contributions
ls+0.014
cks+0.013
 vows+0.012
irs+0.012
 nations+0.011
Neg logit contributions
wheel-0.010
 sill-0.010
hot-0.009
est-0.009
 vest-0.009
Token was
Token ID373
Feature activation-2.36e-02

Pos logit contributions
wheel+0.020
 sill+0.019
hot+0.019
uster+0.018
 aback+0.018
Neg logit contributions
ls-0.016
cks-0.014
 vows-0.014
irs-0.013
ves-0.013
Token wanted
Token ID2227
Feature activation-1.45e-02

Pos logit contributions
wheel+0.017
 sill+0.017
hot+0.016
 aback+0.016
bar+0.016
Neg logit contributions
ls-0.019
cks-0.018
 vows-0.017
irs-0.017
ves-0.016
Token to
Token ID284
Feature activation-1.26e-02

Pos logit contributions
wheel+0.027
uster+0.027
 sill+0.026
 Vest+0.026
hot+0.025
Neg logit contributions
ls-0.022
cks-0.019
 vows-0.019
 their-0.018
 nations-0.018
Token say
Token ID910
Feature activation-2.70e-03

Pos logit contributions
wheel+0.018
 sill+0.018
hot+0.016
 aback+0.016
icle+0.016
Neg logit contributions
ls-0.028
cks-0.025
 vows-0.023
ves-0.023
irs-0.022
Token "
Token ID366
Feature activation-4.31e-02

Pos logit contributions
wheel+0.006
uster+0.006
 sill+0.006
hot+0.006
Aid+0.006
Neg logit contributions
ls-0.003
 vows-0.003
cks-0.003
ves-0.002
 runs-0.002
Tokenhello
Token ID31373
Feature activation+1.51e-02

Pos logit contributions
wheel+0.062
uster+0.062
 knee+0.060
 sill+0.060
 Vest+0.059
Neg logit contributions
ls-0.075
 vows-0.067
 runs-0.066
cks-0.066
 cor-0.064
Token"
Token ID1
Feature activation-7.40e-02

Pos logit contributions
ls+0.020
cks+0.017
 vows+0.016
 runs+0.015
 nations+0.015
Neg logit contributions
wheel-0.031
 sill-0.031
Aid-0.030
uster-0.030
 aback-0.029
Token too
Token ID1165
Feature activation-2.07e-02

Pos logit contributions
 Vest+0.134
Aid+0.133
uster+0.132
initely+0.127
 operation+0.126
Neg logit contributions
ls-0.111
 they-0.089
 runs-0.088
 points-0.088
 their-0.087
Token,
Token ID11
Feature activation-2.00e-02

Pos logit contributions
wheel+0.031
 sill+0.030
hot+0.029
uster+0.028
 aback+0.028
Neg logit contributions
ls-0.041
cks-0.038
 vows-0.037
irs-0.035
ves-0.034
Token so
Token ID523
Feature activation+1.16e-02

Pos logit contributions
Aid+0.025
wheel+0.024
 Vest+0.023
uster+0.023
 aback+0.023
Neg logit contributions
ls-0.042
 runs-0.039
cks-0.039
 their-0.038
 points-0.038
Token he
Token ID339
Feature activation+6.71e-03

Pos logit contributions
ls+0.025
cks+0.023
 vows+0.022
irs+0.021
ves+0.021
Neg logit contributions
wheel-0.016
 sill-0.015
hot-0.014
uster-0.014
 aback-0.014
Token ran
Token ID4966
Feature activation+1.34e-03

Pos logit contributions
cks+0.011
ls+0.011
irs+0.010
 nations+0.009
 vows+0.009
Neg logit contributions
wheel-0.012
 sill-0.012
hot-0.011
 3-0.011
bar-0.011
Token boy
Token ID2933
Feature activation+1.98e-02

Pos logit contributions
ls+0.011
 vows+0.010
cks+0.010
 runs+0.010
 nations+0.010
Neg logit contributions
wheel-0.006
hot-0.006
 sill-0.006
uster-0.006
 aback-0.005
Token said
Token ID531
Feature activation+6.21e-03

Pos logit contributions
ls+0.031
 vows+0.027
cks+0.026
ves+0.025
 runs+0.024
Neg logit contributions
wheel-0.038
 sill-0.037
uster-0.037
hot-0.037
icle-0.035
Token "
Token ID366
Feature activation-2.21e-02

Pos logit contributions
ls+0.012
cks+0.011
 vows+0.011
ves+0.010
irs+0.010
Neg logit contributions
wheel-0.010
 sill-0.009
hot-0.009
uster-0.009
 aback-0.009
Tokenthank
Token ID40716
Feature activation+9.89e-04

Pos logit contributions
uster+0.030
wheel+0.030
 knee+0.029
 operation+0.029
inter+0.029
Neg logit contributions
ls-0.040
cks-0.038
 vows-0.037
ves-0.035
irs-0.035
Token you
Token ID345
Feature activation-1.23e-02

Pos logit contributions
ls+0.001
cks+0.001
 runs+0.001
 vows+0.001
 nations+0.001
Neg logit contributions
uster-0.002
wheel-0.002
 sill-0.002
inter-0.002
icle-0.002
Token"
Token ID1
Feature activation-7.39e-02

Pos logit contributions
wheel+0.026
Aid+0.026
 aback+0.026
 sill+0.025
 Vest+0.025
Neg logit contributions
ls-0.014
 vows-0.014
 their-0.012
ves-0.011
 nations-0.011
Token and
Token ID290
Feature activation-3.61e-03

Pos logit contributions
initely+0.144
uster+0.144
 Vest+0.143
icle+0.142
 operation+0.141
Neg logit contributions
ls-0.105
 they-0.079
 runs-0.076
s-0.076
 their-0.073
Token Lily
Token ID20037
Feature activation-5.39e-03

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.006
 aback+0.006
icle+0.006
Neg logit contributions
ls-0.006
cks-0.006
 vows-0.005
irs-0.005
ves-0.005
Token felt
Token ID2936
Feature activation-1.38e-02

Pos logit contributions
 sill+0.010
uster+0.010
wheel+0.010
icle+0.010
hot+0.010
Neg logit contributions
ls-0.008
 vows-0.007
cks-0.007
 runs-0.007
ves-0.006
Token good
Token ID922
Feature activation-2.32e-02

Pos logit contributions
uster+0.023
icle+0.023
bar+0.022
uit+0.022
inter+0.021
Neg logit contributions
ls-0.024
 their-0.022
cks-0.021
 runs-0.021
 vows-0.020
Token for
Token ID329
Feature activation+1.58e-03

Pos logit contributions
 sill+0.046
uster+0.045
wheel+0.045
 aback+0.045
bar+0.045
Neg logit contributions
ls-0.033
 vows-0.027
cks-0.026
 runs-0.025
 points-0.024
Token't
Token ID470
Feature activation-3.25e-03

Pos logit contributions
ls+0.015
cks+0.013
 vows+0.013
irs+0.012
ves+0.012
Neg logit contributions
wheel-0.017
 sill-0.017
hot-0.016
uster-0.016
icle-0.016
Token know
Token ID760
Feature activation+3.47e-03

Pos logit contributions
wheel+0.006
 sill+0.006
bar+0.006
icle+0.006
uster+0.006
Neg logit contributions
ls-0.005
cks-0.005
 vows-0.004
 runs-0.004
 nations-0.004
Token what
Token ID644
Feature activation+8.47e-03

Pos logit contributions
ls+0.005
cks+0.005
 vows+0.005
ves+0.004
irs+0.004
Neg logit contributions
wheel-0.007
 sill-0.006
hot-0.006
uster-0.006
 aback-0.006
Token "
Token ID366
Feature activation-3.17e-02

Pos logit contributions
ls+0.013
ves+0.012
 vows+0.012
 their+0.011
cks+0.011
Neg logit contributions
 sill-0.016
wheel-0.015
uster-0.015
 aback-0.015
est-0.014
Tokensort
Token ID30619
Feature activation+1.67e-03

Pos logit contributions
wheel+0.046
 sill+0.045
uster+0.044
hot+0.042
 aback+0.042
Neg logit contributions
ls-0.062
cks-0.057
 vows-0.054
ves-0.053
its-0.051
Token"
Token ID1
Feature activation-7.39e-02

Pos logit contributions
ls+0.003
cks+0.003
 vows+0.002
irs+0.002
ves+0.002
Neg logit contributions
wheel-0.003
 sill-0.003
hot-0.003
uster-0.003
icle-0.003
Token meant
Token ID4001
Feature activation-3.38e-02

Pos logit contributions
uster+0.134
 Vest+0.129
Aid+0.129
wheel+0.125
initely+0.123
Neg logit contributions
ls-0.115
ves-0.091
 vows-0.091
 points-0.088
 runs-0.087
Token,
Token ID11
Feature activation-3.04e-02

Pos logit contributions
wheel+0.056
 sill+0.054
hot+0.052
uster+0.050
 aback+0.050
Neg logit contributions
ls-0.061
cks-0.056
 vows-0.054
irs-0.051
ves-0.051
Token but
Token ID475
Feature activation-1.73e-02

Pos logit contributions
wheel+0.034
Aid+0.033
 aback+0.031
 sill+0.031
 Vest+0.031
Neg logit contributions
ls-0.066
 vows-0.061
cks-0.060
 their-0.059
 points-0.059
Token his
Token ID465
Feature activation+7.80e-03

Pos logit contributions
wheel+0.026
 sill+0.025
uster+0.024
hot+0.024
 aback+0.023
Neg logit contributions
ls-0.034
cks-0.031
 vows-0.030
ves-0.028
 runs-0.028
Token mom
Token ID1995
Feature activation-1.12e-02

Pos logit contributions
ls+0.013
 vows+0.012
cks+0.011
 nations+0.011
 runs+0.011
Neg logit contributions
wheel-0.014
hot-0.014
 aback-0.013
 sill-0.013
uster-0.013
Token
Token ID198
Feature activation+9.33e-03

Pos logit contributions
ls+0.014
cks+0.013
 vows+0.012
ves+0.012
irs+0.012
Neg logit contributions
wheel-0.010
 sill-0.010
hot-0.010
uster-0.009
icle-0.009
Token
Token ID198
Feature activation+1.85e-02

Pos logit contributions
ls+0.020
 vows+0.020
cks+0.019
ils+0.018
 nations+0.018
Neg logit contributions
wheel-0.011
 sill-0.011
hot-0.011
 aback-0.010
uster-0.010
TokenL
Token ID43
Feature activation-6.88e-03

Pos logit contributions
ls+0.044
 vows+0.043
cks+0.041
irs+0.040
ils+0.039
Neg logit contributions
wheel-0.020
hot-0.020
 sill-0.019
 aback-0.017
 handy-0.017
Tokenily
Token ID813
Feature activation+1.64e-02

Pos logit contributions
wheel+0.008
 sill+0.007
hot+0.007
uster+0.007
icle+0.006
Neg logit contributions
ls-0.016
cks-0.015
 vows-0.015
irs-0.014
 cor-0.014
Token and
Token ID290
Feature activation+3.79e-03

Pos logit contributions
ls+0.038
cks+0.037
irs+0.036
 vows+0.036
ves+0.035
Neg logit contributions
wheel-0.017
 sill-0.017
 aback-0.016
hot-0.015
 vest-0.014
Token Tom
Token ID4186
Feature activation+4.53e-02

Pos logit contributions
ls+0.007
cks+0.007
 vows+0.006
ves+0.006
irs+0.006
Neg logit contributions
wheel-0.006
 sill-0.006
hot-0.006
 aback-0.005
icle-0.005
Token are
Token ID389
Feature activation+1.83e-02

Pos logit contributions
ls+0.073
cks+0.064
 vows+0.063
ves+0.062
irs+0.062
Neg logit contributions
wheel-0.085
 sill-0.084
hot-0.081
 aback-0.080
 beam-0.075
Token scared
Token ID12008
Feature activation+3.62e-03

Pos logit contributions
ls+0.041
 vows+0.039
irs+0.037
cks+0.037
ves+0.036
Neg logit contributions
 sill-0.023
wheel-0.022
hot-0.020
 aback-0.020
 knee-0.019
Token.
Token ID13
Feature activation+8.36e-03

Pos logit contributions
ls+0.007
cks+0.006
 vows+0.006
ves+0.006
irs+0.006
Neg logit contributions
wheel-0.006
 sill-0.006
hot-0.006
uster-0.005
 aback-0.005
Token They
Token ID1119
Feature activation+3.25e-02

Pos logit contributions
ls+0.012
cks+0.011
 vows+0.011
irs+0.010
ves+0.010
Neg logit contributions
 sill-0.017
hot-0.016
wheel-0.016
 aback-0.016
icle-0.015
Token drop
Token ID4268
Feature activation+1.58e-02

Pos logit contributions
ls+0.069
cks+0.063
irs+0.062
ves+0.062
 vows+0.061
Neg logit contributions
wheel-0.045
hot-0.042
 sill-0.041
 aback-0.040
 beam-0.039
TokenThe
Token ID464
Feature activation+1.36e-02

Pos logit contributions
ls+0.008
cks+0.007
 vows+0.007
 nations+0.007
irs+0.007
Neg logit contributions
hot-0.004
wheel-0.004
 sill-0.004
 aback-0.004
Aid-0.004
Token bird
Token ID6512
Feature activation+5.65e-03

Pos logit contributions
ls+0.035
cks+0.033
 vows+0.032
irs+0.032
ils+0.030
Neg logit contributions
 sill-0.012
wheel-0.012
est-0.010
 vest-0.010
icle-0.010
Token noticed
Token ID6810
Feature activation-2.13e-02

Pos logit contributions
ls+0.009
 vows+0.009
cks+0.008
irs+0.008
 nations+0.008
Neg logit contributions
wheel-0.010
 sill-0.010
bar-0.009
est-0.009
hot-0.009
Token Lucy
Token ID22162
Feature activation+3.75e-03

Pos logit contributions
wheel+0.027
 sill+0.026
hot+0.026
 aback+0.025
icle+0.025
Neg logit contributions
ls-0.045
cks-0.044
 vows-0.042
irs-0.039
 nations-0.039
Token and
Token ID290
Feature activation-8.44e-03

Pos logit contributions
ls+0.008
 vows+0.007
cks+0.007
irs+0.007
ves+0.006
Neg logit contributions
wheel-0.005
 sill-0.005
hot-0.005
bar-0.005
 aback-0.005
Token ch
Token ID442
Feature activation+4.38e-02

Pos logit contributions
wheel+0.014
 sill+0.013
hot+0.013
bar+0.012
 aback+0.012
Neg logit contributions
ls-0.015
cks-0.014
 vows-0.014
irs-0.014
its-0.013
Tokenir
Token ID343
Feature activation+5.71e-03

Pos logit contributions
 vows+0.080
ls+0.075
ves+0.073
 phones+0.071
 passports+0.067
Neg logit contributions
 aback-0.065
uster-0.064
 sill-0.064
wheel-0.062
hot-0.062
Tokenped
Token ID9124
Feature activation+2.04e-02

Pos logit contributions
ls+0.009
 vows+0.008
cks+0.008
 passports+0.007
irs+0.007
Neg logit contributions
wheel-0.011
 sill-0.011
est-0.010
bar-0.010
hot-0.010
Token at
Token ID379
Feature activation+7.18e-03

Pos logit contributions
ls+0.041
cks+0.039
 vows+0.037
irs+0.037
ves+0.036
Neg logit contributions
 sill-0.028
wheel-0.028
hot-0.027
 aback-0.026
est-0.025
Token her
Token ID607
Feature activation+6.42e-03

Pos logit contributions
ls+0.013
cks+0.012
 vows+0.012
ves+0.011
 nations+0.011
Neg logit contributions
 sill-0.011
hot-0.011
wheel-0.011
 aback-0.011
icle-0.010
Token.
Token ID13
Feature activation-8.87e-03

Pos logit contributions
ls+0.011
cks+0.010
 vows+0.010
irs+0.009
ves+0.009
Neg logit contributions
wheel-0.011
 sill-0.011
hot-0.010
uster-0.010
 aback-0.010
Token did
Token ID750
Feature activation+1.56e-02

Pos logit contributions
ls+0.026
cks+0.025
 vows+0.023
irs+0.023
ves+0.021
Neg logit contributions
wheel-0.025
 sill-0.024
hot-0.023
 vest-0.023
bar-0.022
Token something
Token ID1223
Feature activation+3.01e-02

Pos logit contributions
ls+0.032
cks+0.029
 vows+0.029
irs+0.028
 nations+0.027
Neg logit contributions
wheel-0.024
 sill-0.022
 vest-0.020
 knee-0.020
hot-0.020
Token very
Token ID845
Feature activation+2.01e-02

Pos logit contributions
ls+0.051
cks+0.043
ves+0.042
 vows+0.042
 points+0.040
Neg logit contributions
 sill-0.054
uster-0.053
hot-0.051
wheel-0.051
bar-0.050
Token special
Token ID2041
Feature activation-1.84e-02

Pos logit contributions
ls+0.039
cks+0.036
 vows+0.035
irs+0.033
ves+0.033
Neg logit contributions
wheel-0.031
 sill-0.030
hot-0.029
uster-0.028
 aback-0.027
Token and
Token ID290
Feature activation-3.20e-03

Pos logit contributions
wheel+0.033
 sill+0.033
uster+0.033
hot+0.032
 aback+0.032
Neg logit contributions
ls-0.029
cks-0.026
 vows-0.025
ves-0.024
ils-0.024
Token everyone
Token ID2506
Feature activation+4.59e-02

Pos logit contributions
wheel+0.005
 sill+0.005
hot+0.005
 aback+0.005
uster+0.005
Neg logit contributions
ls-0.006
cks-0.005
 vows-0.005
irs-0.005
ves-0.005
Token started
Token ID2067
Feature activation+1.97e-02

Pos logit contributions
ls+0.082
cks+0.082
irs+0.078
 vows+0.076
ves+0.073
Neg logit contributions
wheel-0.075
hot-0.068
 sill-0.068
boat-0.066
 expert-0.065
Token to
Token ID284
Feature activation+1.08e-02

Pos logit contributions
ls+0.045
 vows+0.041
cks+0.041
ves+0.039
irs+0.039
Neg logit contributions
 sill-0.024
wheel-0.024
 3-0.021
bar-0.021
 vest-0.020
Token applaud
Token ID22517
Feature activation+4.02e-02

Pos logit contributions
ls+0.020
cks+0.018
 vows+0.018
irs+0.017
ves+0.016
Neg logit contributions
wheel-0.017
 sill-0.017
hot-0.017
uster-0.016
 aback-0.016
Token him
Token ID683
Feature activation+2.08e-02

Pos logit contributions
ls+0.075
cks+0.068
 vows+0.066
irs+0.062
ves+0.062
Neg logit contributions
wheel-0.065
 sill-0.064
hot-0.062
icle-0.059
uster-0.058
Token.
Token ID13
Feature activation+8.05e-03

Pos logit contributions
ls+0.037
cks+0.034
 vows+0.033
irs+0.031
ves+0.031
Neg logit contributions
wheel-0.035
 sill-0.034
hot-0.033
uster-0.031
icle-0.031
Token
Token ID198
Feature activation+6.88e-03

Pos logit contributions
ls+0.012
 vows+0.011
cks+0.011
ils+0.011
 nations+0.011
Neg logit contributions
 sill-0.006
wheel-0.006
hot-0.006
 aback-0.006
icle-0.005
Token
Token ID198
Feature activation+1.35e-02

Pos logit contributions
ls+0.016
 vows+0.015
cks+0.015
ils+0.015
 nations+0.014
Neg logit contributions
wheel-0.007
 sill-0.007
hot-0.007
 aback-0.006
 handy-0.006
TokenS
Token ID50
Feature activation+1.79e-02

Pos logit contributions
 vows+0.028
ls+0.027
cks+0.026
irs+0.026
ils+0.026
Neg logit contributions
hot-0.018
wheel-0.017
 sill-0.016
 handy-0.015
bar-0.015
Tokenara
Token ID3301
Feature activation+1.88e-02

Pos logit contributions
ls+0.031
cks+0.031
 vows+0.030
irs+0.028
 nations+0.028
Neg logit contributions
wheel-0.027
 sill-0.026
uit-0.026
hot-0.025
icle-0.025
Token and
Token ID290
Feature activation+5.93e-03

Pos logit contributions
 vows+0.044
ls+0.044
irs+0.044
cks+0.043
ves+0.041
Neg logit contributions
wheel-0.018
 sill-0.018
 aback-0.016
hot-0.015
 knee-0.014
Token Ben
Token ID3932
Feature activation+4.73e-02

Pos logit contributions
ls+0.012
cks+0.011
 vows+0.011
ves+0.010
irs+0.010
Neg logit contributions
wheel-0.009
 sill-0.009
hot-0.008
icle-0.008
 vest-0.008
Token are
Token ID389
Feature activation+9.48e-03

Pos logit contributions
ls+0.084
irs+0.077
ves+0.076
 vows+0.076
cks+0.075
Neg logit contributions
wheel-0.077
 sill-0.074
hot-0.073
 aback-0.073
 beam-0.070
Token scared
Token ID12008
Feature activation+2.66e-03

Pos logit contributions
ls+0.022
 vows+0.021
irs+0.020
cks+0.019
ves+0.019
Neg logit contributions
 sill-0.011
wheel-0.011
hot-0.010
 knee-0.009
 aback-0.009
Token.
Token ID13
Feature activation+8.09e-03

Pos logit contributions
ls+0.005
 vows+0.005
cks+0.005
ves+0.005
irs+0.005
Neg logit contributions
 sill-0.004
wheel-0.004
hot-0.004
uster-0.003
 aback-0.003
Token They
Token ID1119
Feature activation+3.21e-02

Pos logit contributions
ls+0.013
cks+0.012
irs+0.012
ils+0.011
 vows+0.011
Neg logit contributions
 sill-0.015
hot-0.014
 aback-0.014
icle-0.014
inter-0.013
Token do
Token ID466
Feature activation+3.67e-02

Pos logit contributions
ls+0.065
irs+0.061
 vows+0.061
ves+0.060
cks+0.058
Neg logit contributions
wheel-0.045
hot-0.042
 sill-0.042
 aback-0.040
 beam-0.040
Token m
Token ID285
Feature activation+3.91e-02

Pos logit contributions
 sill+0.005
wheel+0.005
hot+0.004
bar+0.004
 vest+0.004
Neg logit contributions
ls-0.005
cks-0.005
 vows-0.005
irs-0.004
ves-0.004
Tokenak
Token ID461
Feature activation-1.84e-03

Pos logit contributions
ls+0.080
cks+0.071
 vows+0.070
 nations+0.068
 runs+0.066
Neg logit contributions
wheel-0.057
bar-0.055
 sill-0.055
icle-0.053
uster-0.053
Tokenr
Token ID81
Feature activation+5.40e-02

Pos logit contributions
wheel+0.003
 sill+0.003
hot+0.003
bar+0.003
 aback+0.002
Neg logit contributions
ls-0.004
cks-0.003
 vows-0.003
irs-0.003
 nations-0.003
Tokenut
Token ID315
Feature activation-7.07e-03

Pos logit contributions
ls+0.088
cks+0.078
 nations+0.075
 vows+0.074
 passports+0.072
Neg logit contributions
 sill-0.090
wheel-0.089
bar-0.087
icle-0.085
est-0.084
Token and
Token ID290
Feature activation-5.77e-04

Pos logit contributions
wheel+0.010
 sill+0.010
hot+0.010
bar+0.010
uster+0.009
Neg logit contributions
ls-0.014
cks-0.013
 vows-0.013
 nations-0.012
ves-0.012
Token pand
Token ID19798
Feature activation+5.26e-02

Pos logit contributions
 sill+0.001
wheel+0.001
bar+0.001
hot+0.001
 vest+0.001
Neg logit contributions
ls-0.001
cks-0.001
irs-0.001
 vows-0.001
 nations-0.001
Tokenan
Token ID272
Feature activation+1.50e-02

Pos logit contributions
ls+0.079
 vows+0.070
cks+0.068
 runs+0.065
 points+0.062
Neg logit contributions
wheel-0.105
 sill-0.100
uster-0.098
bar-0.095
hot-0.095
Token and
Token ID290
Feature activation+8.86e-03

Pos logit contributions
ls+0.028
cks+0.026
 vows+0.024
irs+0.024
 nations+0.023
Neg logit contributions
wheel-0.023
 sill-0.023
hot-0.022
bar-0.022
est-0.021
Token curry
Token ID34611
Feature activation+2.64e-02

Pos logit contributions
ls+0.016
cks+0.015
irs+0.014
 vows+0.013
ves+0.013
Neg logit contributions
 sill-0.015
wheel-0.014
bar-0.014
hot-0.013
 vest-0.013
Token leaf
Token ID12835
Feature activation+6.02e-03

Pos logit contributions
ls+0.051
cks+0.050
irs+0.046
 vows+0.045
 nations+0.045
Neg logit contributions
wheel-0.038
 sill-0.037
hot-0.036
est-0.033
icle-0.033
Token and
Token ID290
Feature activation+2.78e-03

Pos logit contributions
ls+0.011
cks+0.011
 vows+0.010
irs+0.010
 nations+0.010
Neg logit contributions
wheel-0.009
 sill-0.009
hot-0.009
bar-0.009
icle-0.008
Token and
Token ID290
Feature activation+7.01e-03

Pos logit contributions
wheel+0.007
 sill+0.007
 vest+0.007
my+0.007
hot+0.007
Neg logit contributions
ls-0.009
cks-0.009
 vows-0.009
irs-0.008
ves-0.008
Token Rod
Token ID6882
Feature activation+4.94e-02

Pos logit contributions
ls+0.014
cks+0.013
 vows+0.013
 runs+0.012
ves+0.012
Neg logit contributions
wheel-0.010
 sill-0.010
uster-0.009
hot-0.009
 aback-0.009
Token went
Token ID1816
Feature activation+2.04e-03

Pos logit contributions
cks+0.071
ls+0.069
irs+0.065
 vows+0.061
 pulp+0.056
Neg logit contributions
wheel-0.096
hot-0.093
 sill-0.091
 aback-0.088
est-0.087
Token to
Token ID284
Feature activation+4.34e-03

Pos logit contributions
ls+0.004
cks+0.004
 vows+0.004
irs+0.003
ves+0.003
Neg logit contributions
wheel-0.003
 sill-0.003
hot-0.003
 aback-0.003
uster-0.003
Token the
Token ID262
Feature activation-6.82e-03

Pos logit contributions
ls+0.008
cks+0.007
 vows+0.007
irs+0.007
ves+0.007
Neg logit contributions
wheel-0.007
 sill-0.007
hot-0.006
uster-0.006
 aback-0.006
Token park
Token ID3952
Feature activation+1.89e-02

Pos logit contributions
wheel+0.011
 sill+0.011
hot+0.010
uster+0.010
 aback+0.010
Neg logit contributions
ls-0.012
cks-0.011
 vows-0.011
 nations-0.010
irs-0.010
Token.
Token ID13
Feature activation+7.55e-03

Pos logit contributions
ls+0.032
cks+0.029
 vows+0.028
ves+0.026
 nations+0.026
Neg logit contributions
wheel-0.033
 sill-0.032
uster-0.031
hot-0.031
icle-0.030
Token They
Token ID1119
Feature activation+1.96e-02

Pos logit contributions
ls+0.010
cks+0.009
 vows+0.009
 runs+0.008
 nations+0.008
Neg logit contributions
wheel-0.015
 sill-0.015
uster-0.014
hot-0.014
Aid-0.014
Token saw
Token ID2497
Feature activation-5.22e-03

Pos logit contributions
ls+0.037
cks+0.036
 vows+0.034
irs+0.033
its+0.032
Neg logit contributions
wheel-0.030
hot-0.029
 sill-0.028
 vest-0.027
 Vest-0.027
Token a
Token ID257
Feature activation+3.20e-02

Pos logit contributions
wheel+0.008
 sill+0.008
hot+0.008
uster+0.007
 aback+0.007
Neg logit contributions
ls-0.010
cks-0.009
 vows-0.009
irs-0.008
ves-0.008
Token big
Token ID1263
Feature activation-6.86e-03

Pos logit contributions
ls+0.053
 vows+0.046
cks+0.046
ves+0.043
 nations+0.042
Neg logit contributions
wheel-0.058
 sill-0.058
hot-0.055
 aback-0.054
uster-0.054
Token a
Token ID257
Feature activation+2.52e-02

Pos logit contributions
wheel+0.033
 sill+0.032
uster+0.032
 aback+0.031
est+0.031
Neg logit contributions
ls-0.034
cks-0.031
 their-0.030
 cor-0.029
 runs-0.029
Token little
Token ID1310
Feature activation+2.29e-03

Pos logit contributions
ls+0.041
 vows+0.037
 cor+0.034
cks+0.034
 runs+0.034
Neg logit contributions
wheel-0.046
 sill-0.044
hot-0.043
 aback-0.043
uster-0.043
Token girl
Token ID2576
Feature activation+6.52e-04

Pos logit contributions
ls+0.004
 runs+0.004
 cor+0.004
 nations+0.004
 vows+0.004
Neg logit contributions
wheel-0.004
uit-0.003
uster-0.003
hot-0.003
 sill-0.003
Token named
Token ID3706
Feature activation-1.41e-02

Pos logit contributions
ls+0.002
cks+0.001
 vows+0.001
irs+0.001
ves+0.001
Neg logit contributions
 sill-0.001
wheel-0.001
hot-0.001
est-0.001
 aback-0.001
Token Sue
Token ID26089
Feature activation-7.73e-04

Pos logit contributions
wheel+0.015
 sill+0.015
hot+0.015
 aback+0.013
uster+0.013
Neg logit contributions
ls-0.033
cks-0.032
 vows-0.031
ves-0.029
its-0.029
Token.
Token ID13
Feature activation+5.61e-03

Pos logit contributions
 sill+0.001
wheel+0.001
hot+0.001
my+0.001
 aback+0.001
Neg logit contributions
ls-0.002
 vows-0.001
cks-0.001
irs-0.001
ves-0.001
Token They
Token ID1119
Feature activation+2.17e-02

Pos logit contributions
ls+0.011
cks+0.010
 vows+0.010
irs+0.009
ves+0.009
Neg logit contributions
wheel-0.008
 sill-0.008
hot-0.008
icle-0.007
uster-0.007
Token loved
Token ID6151
Feature activation+1.71e-02

Pos logit contributions
ls+0.043
cks+0.040
irs+0.036
ves+0.035
its+0.035
Neg logit contributions
hot-0.033
wheel-0.033
 sill-0.033
my-0.030
 happiest-0.030
Token to
Token ID284
Feature activation+1.24e-02

Pos logit contributions
ls+0.042
cks+0.041
its+0.038
ves+0.038
 vows+0.038
Neg logit contributions
 sill-0.016
wheel-0.015
 3-0.015
hot-0.015
 operation-0.015
Token play
Token ID711
Feature activation-1.79e-03

Pos logit contributions
ls+0.029
cks+0.026
irs+0.024
 vows+0.024
ves+0.024
Neg logit contributions
 sill-0.016
wheel-0.015
 vest-0.014
icle-0.013
hot-0.013
Token and
Token ID290
Feature activation+6.86e-03

Pos logit contributions
 sill+0.003
wheel+0.003
uster+0.003
bar+0.003
icle+0.003
Neg logit contributions
ls-0.003
cks-0.003
ves-0.003
 vows-0.003
ils-0.003
Token to
Token ID284
Feature activation-3.55e-03

Pos logit contributions
wheel+0.010
 sill+0.010
hot+0.009
 aback+0.008
bar+0.008
Neg logit contributions
ls-0.021
 vows-0.019
cks-0.019
ves-0.018
irs-0.018
Token touch
Token ID3638
Feature activation-9.69e-04

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.005
icle+0.005
bar+0.005
Neg logit contributions
ls-0.007
cks-0.006
 vows-0.006
ves-0.006
irs-0.006
Token it
Token ID340
Feature activation-2.60e-02

Pos logit contributions
wheel+0.002
 sill+0.002
hot+0.002
uster+0.002
 aback+0.002
Neg logit contributions
ls-0.002
cks-0.001
 vows-0.001
irs-0.001
ves-0.001
Token.
Token ID13
Feature activation-2.89e-03

Pos logit contributions
wheel+0.049
uster+0.048
 sill+0.048
Aid+0.047
 Vest+0.047
Neg logit contributions
ls-0.041
cks-0.035
 vows-0.032
ves-0.031
irs-0.031
Token
Token ID198
Feature activation-1.56e-03

Pos logit contributions
 sill+0.003
wheel+0.003
hot+0.003
 aback+0.003
icle+0.003
Neg logit contributions
ls-0.007
cks-0.006
 vows-0.006
ils-0.006
ves-0.006
Token
Token ID198
Feature activation+9.31e-03

Pos logit contributions
wheel+0.002
 sill+0.002
hot+0.002
 aback+0.002
uster+0.002
Neg logit contributions
ls-0.004
 vows-0.003
cks-0.003
ils-0.003
 nations-0.003
Token"
Token ID1
Feature activation-5.90e-03

Pos logit contributions
ls+0.018
 vows+0.016
cks+0.016
 cor+0.015
irs+0.015
Neg logit contributions
wheel-0.015
hot-0.015
 sill-0.014
 handy-0.013
 aback-0.013
TokenTom
Token ID13787
Feature activation-1.80e-02

Pos logit contributions
wheel+0.008
 sill+0.008
hot+0.008
icle+0.007
uster+0.007
Neg logit contributions
ls-0.012
cks-0.011
 vows-0.011
irs-0.010
ves-0.010
Token,
Token ID11
Feature activation+1.37e-02

Pos logit contributions
wheel+0.032
uster+0.031
 sill+0.031
hot+0.030
Aid+0.030
Neg logit contributions
ls-0.029
cks-0.027
 runs-0.025
 vows-0.025
 points-0.024
Token no
Token ID645
Feature activation-1.77e-02

Pos logit contributions
ls+0.022
cks+0.020
 vows+0.020
ves+0.018
 nations+0.018
Neg logit contributions
wheel-0.025
 sill-0.024
hot-0.023
uster-0.023
 aback-0.023
Token,
Token ID11
Feature activation+2.76e-03

Pos logit contributions
wheel+0.027
 sill+0.026
hot+0.025
uster+0.024
icle+0.024
Neg logit contributions
ls-0.035
cks-0.032
 vows-0.031
irs-0.030
ves-0.029
Token dog
Token ID3290
Feature activation+3.78e-04

Pos logit contributions
wheel+0.021
 sill+0.021
hot+0.020
 aback+0.019
uster+0.019
Neg logit contributions
ls-0.023
cks-0.022
 vows-0.021
irs-0.020
ves-0.020
Token for
Token ID329
Feature activation-2.53e-03

Pos logit contributions
ls+0.001
cks+0.001
 vows+0.001
irs+0.001
ves+0.001
Neg logit contributions
wheel-0.001
 sill-0.001
hot-0.000
uster-0.000
 aback-0.000
Token a
Token ID257
Feature activation-3.46e-03

Pos logit contributions
wheel+0.003
 sill+0.003
hot+0.003
icle+0.003
 aback+0.003
Neg logit contributions
ls-0.006
cks-0.005
 vows-0.005
 nations-0.005
ves-0.004
Token walk
Token ID2513
Feature activation-1.70e-02

Pos logit contributions
wheel+0.006
 sill+0.006
hot+0.005
uster+0.005
 aback+0.005
Neg logit contributions
ls-0.006
cks-0.006
 vows-0.005
irs-0.005
ves-0.005
Token.
Token ID13
Feature activation-1.48e-05

Pos logit contributions
wheel+0.034
Aid+0.034
 Vest+0.032
 sill+0.032
uster+0.031
Neg logit contributions
ls-0.024
cks-0.019
 vows-0.019
 their-0.019
ves-0.018
Token He
Token ID679
Feature activation+7.53e-03

Pos logit contributions
wheel+0.000
 sill+0.000
est+0.000
hot+0.000
uster+0.000
Neg logit contributions
ls-0.000
cks-0.000
 vows-0.000
irs-0.000
ves-0.000
Token also
Token ID635
Feature activation+1.34e-03

Pos logit contributions
ls+0.013
cks+0.012
 vows+0.011
irs+0.011
ves+0.011
Neg logit contributions
wheel-0.013
 sill-0.013
hot-0.012
 aback-0.012
bar-0.012
Token played
Token ID2826
Feature activation-1.30e-02

Pos logit contributions
ls+0.002
cks+0.002
 vows+0.002
irs+0.002
ves+0.002
Neg logit contributions
wheel-0.002
 sill-0.002
hot-0.002
 aback-0.002
bar-0.002
Token in
Token ID287
Feature activation+1.38e-03

Pos logit contributions
uster+0.024
Aid+0.024
 sill+0.023
bar+0.023
inter+0.023
Neg logit contributions
ls-0.020
ves-0.019
 them-0.018
 their-0.018
cks-0.017
Token his
Token ID465
Feature activation-5.06e-03

Pos logit contributions
ls+0.002
cks+0.002
 vows+0.002
irs+0.002
ves+0.002
Neg logit contributions
wheel-0.003
hot-0.002
 sill-0.002
uster-0.002
Aid-0.002
Token bedroom
Token ID14043
Feature activation-5.21e-03

Pos logit contributions
wheel+0.008
 sill+0.008
hot+0.007
uster+0.007
 aback+0.007
Neg logit contributions
ls-0.010
cks-0.009
 vows-0.009
ves-0.008
 nations-0.008
Token It
Token ID632
Feature activation-5.33e-03

Pos logit contributions
 sill+0.014
wheel+0.013
iddle+0.013
est+0.013
icle+0.012
Neg logit contributions
ls-0.017
 vows-0.015
 runs-0.014
irs-0.014
 points-0.014
Token was
Token ID373
Feature activation-2.03e-03

Pos logit contributions
wheel+0.008
 sill+0.008
hot+0.008
bar+0.008
est+0.007
Neg logit contributions
ls-0.010
cks-0.009
 vows-0.009
irs-0.009
 nations-0.009
Token huge
Token ID3236
Feature activation-1.97e-02

Pos logit contributions
wheel+0.003
 sill+0.003
hot+0.002
uster+0.002
 aback+0.002
Neg logit contributions
ls-0.004
cks-0.004
 vows-0.004
irs-0.004
ves-0.004
Token,
Token ID11
Feature activation-3.55e-02

Pos logit contributions
wheel+0.030
 sill+0.028
hot+0.028
uster+0.027
icle+0.027
Neg logit contributions
ls-0.039
cks-0.035
 vows-0.034
 points-0.032
 runs-0.032
Token and
Token ID290
Feature activation-8.21e-03

Pos logit contributions
wheel+0.055
 sill+0.054
uster+0.053
hot+0.052
icle+0.051
Neg logit contributions
ls-0.067
cks-0.060
 vows-0.058
 points-0.055
ves-0.055
Token Red
Token ID2297
Feature activation+1.30e-02

Pos logit contributions
wheel+0.014
 sill+0.014
uster+0.013
icle+0.013
hot+0.013
Neg logit contributions
ls-0.014
cks-0.013
 vows-0.012
ves-0.012
irs-0.011
Token could
Token ID714
Feature activation+3.29e-02

Pos logit contributions
ls+0.023
cks+0.021
 vows+0.020
irs+0.020
 nations+0.019
Neg logit contributions
wheel-0.022
 sill-0.021
hot-0.021
bar-0.020
 aback-0.020
Token tell
Token ID1560
Feature activation+1.93e-02

Pos logit contributions
ls+0.054
cks+0.049
 vows+0.047
irs+0.044
ves+0.044
Neg logit contributions
wheel-0.060
 sill-0.058
hot-0.057
uster-0.055
 aback-0.055
Token it
Token ID340
Feature activation-9.22e-03

Pos logit contributions
ls+0.039
cks+0.036
 vows+0.034
ves+0.033
irs+0.033
Neg logit contributions
wheel-0.028
 sill-0.027
hot-0.026
 aback-0.026
icle-0.025
Token was
Token ID373
Feature activation-7.40e-03

Pos logit contributions
wheel+0.011
 sill+0.011
est+0.010
hot+0.010
 aback+0.009
Neg logit contributions
ls-0.020
cks-0.019
 vows-0.018
irs-0.018
 pulp-0.018
Token a
Token ID257
Feature activation+1.73e-02

Pos logit contributions
wheel+0.010
 sill+0.010
hot+0.009
 aback+0.009
icle+0.009
Neg logit contributions
ls-0.016
cks-0.014
 vows-0.014
irs-0.013
ves-0.013
Token buy
Token ID2822
Feature activation+4.80e-03

Pos logit contributions
ls+0.014
cks+0.013
 vows+0.013
irs+0.012
 runs+0.012
Neg logit contributions
wheel-0.016
 sill-0.015
uster-0.015
hot-0.014
bar-0.014
Token some
Token ID617
Feature activation+2.60e-03

Pos logit contributions
ls+0.010
cks+0.009
 vows+0.009
irs+0.008
 nations+0.008
Neg logit contributions
wheel-0.007
 sill-0.007
hot-0.006
icle-0.006
 aback-0.006
Token candy
Token ID18550
Feature activation+1.41e-02

Pos logit contributions
ls+0.004
cks+0.004
 vows+0.004
irs+0.004
ves+0.004
Neg logit contributions
wheel-0.004
 sill-0.004
hot-0.004
 vest-0.004
icle-0.004
Token.
Token ID13
Feature activation+6.06e-03

Pos logit contributions
ls+0.026
cks+0.024
 vows+0.023
irs+0.022
 nations+0.021
Neg logit contributions
wheel-0.023
 sill-0.022
hot-0.022
icle-0.020
uster-0.020
Token Lily
Token ID20037
Feature activation+9.11e-03

Pos logit contributions
ls+0.012
cks+0.011
 vows+0.011
irs+0.010
ves+0.010
Neg logit contributions
wheel-0.009
 sill-0.009
hot-0.008
uster-0.008
 aback-0.008
Token saw
Token ID2497
Feature activation-1.35e-02

Pos logit contributions
ls+0.015
cks+0.014
 vows+0.013
irs+0.013
 nations+0.012
Neg logit contributions
wheel-0.016
 sill-0.016
hot-0.015
 aback-0.015
bar-0.015
Token a
Token ID257
Feature activation+2.46e-02

Pos logit contributions
wheel+0.021
 sill+0.020
hot+0.019
uster+0.019
 aback+0.019
Neg logit contributions
ls-0.026
cks-0.024
 vows-0.023
ves-0.022
irs-0.022
Token big
Token ID1263
Feature activation-1.15e-02

Pos logit contributions
ls+0.041
 vows+0.036
 cor+0.032
ves+0.032
cks+0.032
Neg logit contributions
 sill-0.045
wheel-0.045
hot-0.043
 aback-0.043
uster-0.043
Token red
Token ID2266
Feature activation-8.84e-03

Pos logit contributions
wheel+0.020
 sill+0.020
uster+0.019
 aback+0.019
hot+0.018
Neg logit contributions
ls-0.020
 vows-0.017
 runs-0.017
 points-0.016
 cor-0.016
Token l
Token ID300
Feature activation+1.91e-03

Pos logit contributions
wheel+0.014
 sill+0.014
 aback+0.013
uster+0.013
hot+0.013
Neg logit contributions
ls-0.016
 vows-0.015
 runs-0.014
 cor-0.013
ves-0.013
Tokenoll
Token ID692
Feature activation-4.24e-03

Pos logit contributions
ls+0.004
ves+0.004
cks+0.004
ils+0.004
 vows+0.004
Neg logit contributions
 aback-0.002
 sill-0.002
 handy-0.002
 cleaner-0.002
icle-0.002
Token blanket
Token ID18447
Feature activation+3.44e-03

Pos logit contributions
ls+0.019
cks+0.018
 vows+0.017
irs+0.017
ves+0.016
Neg logit contributions
wheel-0.014
 sill-0.014
 vest-0.013
hot-0.012
icle-0.012
Token and
Token ID290
Feature activation+2.69e-03

Pos logit contributions
ls+0.007
cks+0.006
 vows+0.006
ves+0.005
 runs+0.005
Neg logit contributions
wheel-0.005
 sill-0.005
uster-0.005
Aid-0.005
hot-0.005
Token Lily
Token ID20037
Feature activation+1.59e-02

Pos logit contributions
ls+0.005
cks+0.005
irs+0.004
 vows+0.004
 nations+0.004
Neg logit contributions
wheel-0.004
 sill-0.004
 vest-0.004
hot-0.004
 cleaner-0.004
Token's
Token ID338
Feature activation+3.11e-03

Pos logit contributions
ls+0.030
cks+0.028
irs+0.028
 vows+0.027
 nations+0.027
Neg logit contributions
wheel-0.025
 sill-0.024
hot-0.023
 knee-0.022
 vest-0.022
Token sandwich
Token ID20433
Feature activation+1.92e-02

Pos logit contributions
ls+0.006
 vows+0.005
cks+0.005
ves+0.005
 nations+0.005
Neg logit contributions
wheel-0.005
 sill-0.005
hot-0.005
 aback-0.005
uster-0.005
Token.
Token ID13
Feature activation-1.20e-03

Pos logit contributions
ls+0.032
cks+0.031
 vows+0.029
irs+0.029
 nations+0.028
Neg logit contributions
wheel-0.034
 sill-0.033
hot-0.030
 vest-0.030
est-0.030
Token She
Token ID1375
Feature activation+1.12e-02

Pos logit contributions
wheel+0.001
 sill+0.001
hot+0.001
uster+0.001
 aback+0.001
Neg logit contributions
ls-0.003
cks-0.003
 vows-0.002
irs-0.002
ves-0.002
Token was
Token ID373
Feature activation-4.49e-04

Pos logit contributions
cks+0.023
irs+0.023
ls+0.023
 nations+0.022
 vows+0.021
Neg logit contributions
wheel-0.014
 vest-0.013
 knee-0.012
 sill-0.012
 beam-0.012
Token upset
Token ID9247
Feature activation-1.11e-02

Pos logit contributions
wheel+0.001
hot+0.001
uster+0.001
 sill+0.001
icle+0.001
Neg logit contributions
ls-0.001
cks-0.001
 vows-0.001
 runs-0.001
ves-0.001
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
wheel+0.016
 sill+0.016
 Vest+0.015
bar+0.015
uster+0.015
Neg logit contributions
ls-0.023
cks-0.019
 their-0.018
 runs-0.018
 points-0.018
Token started
Token ID2067
Feature activation+2.12e-02

Pos logit contributions
wheel+0.017
 sill+0.016
 knee+0.015
hot+0.015
 vest+0.015
Neg logit contributions
ls-0.022
irs-0.022
cks-0.022
 vows-0.022
 nations-0.020
Token away
Token ID1497
Feature activation+5.32e-03

Pos logit contributions
wheel+0.075
ivering+0.069
 stump+0.068
ooting+0.068
uster+0.067
Neg logit contributions
ls-0.039
 their-0.039
 them-0.037
cks-0.032
 turns-0.028
Token his
Token ID465
Feature activation-2.39e-02

Pos logit contributions
ls+0.007
 their+0.007
 vows+0.007
 cor+0.006
cks+0.006
Neg logit contributions
wheel-0.011
uster-0.010
 sill-0.010
hot-0.010
bar-0.010
Token cubes
Token ID34896
Feature activation-1.78e-02

Pos logit contributions
wheel+0.030
hot+0.030
uster+0.029
 sill+0.027
 aback+0.026
Neg logit contributions
ls-0.053
 vows-0.048
cks-0.048
 points-0.046
 nations-0.045
Token and
Token ID290
Feature activation-7.70e-03

Pos logit contributions
 Labrador+0.031
wheel+0.030
Aid+0.030
initely+0.030
Whe+0.030
Neg logit contributions
ls-0.029
 they-0.022
 their-0.022
packs-0.022
cks-0.021
Token went
Token ID1816
Feature activation-7.32e-03

Pos logit contributions
wheel+0.013
 sill+0.013
 vest+0.012
hot+0.012
bar+0.012
Neg logit contributions
ls-0.013
cks-0.013
 vows-0.012
irs-0.011
 nations-0.011
Token to
Token ID284
Feature activation+9.33e-04

Pos logit contributions
wheel+0.010
 sill+0.010
hot+0.009
uster+0.009
 aback+0.009
Neg logit contributions
ls-0.016
cks-0.014
 vows-0.014
irs-0.013
ves-0.013
Token bed
Token ID3996
Feature activation+8.45e-03

Pos logit contributions
ls+0.002
cks+0.002
 vows+0.002
ves+0.002
 nations+0.002
Neg logit contributions
wheel-0.001
 sill-0.001
 vest-0.001
hot-0.001
 aback-0.001
Token with
Token ID351
Feature activation+4.26e-03

Pos logit contributions
ls+0.017
 vows+0.015
cks+0.015
ves+0.015
irs+0.014
Neg logit contributions
wheel-0.012
 sill-0.012
hot-0.012
icle-0.011
uster-0.011
Token his
Token ID465
Feature activation-2.76e-03

Pos logit contributions
ls+0.007
 their+0.006
 vows+0.006
cks+0.006
irs+0.005
Neg logit contributions
wheel-0.008
uster-0.008
bar-0.007
hot-0.007
inter-0.007
Token favorite
Token ID4004
Feature activation+9.91e-04

Pos logit contributions
wheel+0.004
 sill+0.004
hot+0.004
uster+0.004
 aback+0.004
Neg logit contributions
ls-0.005
cks-0.005
 vows-0.005
 nations-0.004
irs-0.004
Token cube
Token ID23441
Feature activation-2.03e-03

Pos logit contributions
ls+0.002
 vows+0.002
cks+0.002
 nations+0.002
 points+0.002
Neg logit contributions
wheel-0.002
 sill-0.001
hot-0.001
uster-0.001
 aback-0.001
Token.
Token ID13
Feature activation-9.13e-03

Pos logit contributions
wheel+0.008
Aid+0.008
icle+0.008
hot+0.008
uster+0.008
Neg logit contributions
ls-0.006
 vows-0.005
cks-0.005
ves-0.005
 their-0.005
Token<|endoftext|>
Token ID50256
Feature activation-2.27e-02

Pos logit contributions
wheel+0.012
 sill+0.012
hot+0.011
uster+0.011
bar+0.011
Neg logit contributions
ls-0.019
cks-0.018
 vows-0.017
irs-0.016
ves-0.016
TokenOne
Token ID3198
Feature activation-8.47e-03

Pos logit contributions
wheel+0.042
 sill+0.041
hot+0.039
uster+0.039
bar+0.038
Neg logit contributions
ls-0.037
cks-0.033
 vows-0.031
irs-0.030
ves-0.029
Token day
Token ID1110
Feature activation+1.20e-02

Pos logit contributions
uster+0.013
wheel+0.013
hot+0.013
 aback+0.012
uit+0.012
Neg logit contributions
ls-0.016
 runs-0.014
cks-0.014
 their-0.014
 vows-0.014
Token,
Token ID11
Feature activation-3.74e-03

Pos logit contributions
cks+0.031
 vows+0.030
 nations+0.029
ils+0.029
ls+0.029
Neg logit contributions
hot-0.008
wheel-0.008
icle-0.008
 aback-0.007
bar-0.007
Token there
Token ID612
Feature activation+1.43e-03

Pos logit contributions
wheel+0.005
 sill+0.005
hot+0.005
uster+0.004
 aback+0.004
Neg logit contributions
ls-0.008
cks-0.007
 vows-0.007
irs-0.007
ves-0.007
Token was
Token ID373
Feature activation-1.31e-02

Pos logit contributions
ls+0.003
cks+0.002
 vows+0.002
irs+0.002
 nations+0.002
Neg logit contributions
wheel-0.002
 sill-0.002
hot-0.002
icle-0.002
 aback-0.002
Token a
Token ID257
Feature activation+8.90e-03

Pos logit contributions
wheel+0.024
uster+0.023
 sill+0.022
 aback+0.022
bar+0.022
Neg logit contributions
ls-0.020
 their-0.019
cks-0.018
 cor-0.017
 vows-0.017
Token little
Token ID1310
Feature activation-6.33e-03

Pos logit contributions
ls+0.013
 vows+0.011
 cor+0.011
 runs+0.010
 nations+0.010
Neg logit contributions
 aback-0.018
wheel-0.018
 sill-0.018
bar-0.017
icle-0.017
Token girl
Token ID2576
Feature activation-1.55e-02

Pos logit contributions
wheel+0.012
 sill+0.011
uit+0.011
 aback+0.011
iddle+0.010
Neg logit contributions
ls-0.011
 runs-0.009
 cor-0.009
 floats-0.009
 their-0.009
Token named
Token ID3706
Feature activation-2.69e-02

Pos logit contributions
wheel+0.023
 sill+0.023
hot+0.022
uster+0.021
 aback+0.021
Neg logit contributions
ls-0.031
cks-0.028
 vows-0.027
ves-0.026
irs-0.025
Token
Token ID198
Feature activation-6.34e-03

Pos logit contributions
ls+0.032
cks+0.029
 vows+0.029
irs+0.027
 nations+0.026
Neg logit contributions
wheel-0.026
 sill-0.025
hot-0.024
 aback-0.023
 vest-0.023
Token
Token ID198
Feature activation+2.52e-03

Pos logit contributions
wheel+0.010
 sill+0.010
hot+0.009
uster+0.009
icle+0.009
Neg logit contributions
ls-0.012
cks-0.011
 vows-0.010
ves-0.010
irs-0.010
TokenTom
Token ID13787
Feature activation+1.69e-03

Pos logit contributions
ls+0.004
cks+0.004
ves+0.003
 vows+0.003
irs+0.003
Neg logit contributions
 sill-0.005
wheel-0.005
uster-0.004
 aback-0.004
icle-0.004
Tokenâ
Token ID22940
Feature activation-2.45e-02

Pos logit contributions
ls+0.003
cks+0.003
 vows+0.002
irs+0.002
ves+0.002
Neg logit contributions
wheel-0.003
 sill-0.003
hot-0.003
uster-0.003
 aback-0.003
Token€
Token ID26391
Feature activation+1.62e-02

Pos logit contributions
uster+0.028
 vest+0.027
 sill+0.026
 brand+0.026
 3+0.026
Neg logit contributions
cks-0.049
 runs-0.046
ils-0.045
 vows-0.045
ls-0.044
Tokenâ„¢
Token ID8151
Feature activation-6.03e-03

Pos logit contributions
ls+0.029
cks+0.026
 vows+0.026
irs+0.024
 nations+0.024
Neg logit contributions
wheel-0.027
 sill-0.026
hot-0.025
uster-0.024
 aback-0.024
Tokens
Token ID82
Feature activation+1.68e-02

Pos logit contributions
wheel+0.009
 sill+0.009
Aid+0.008
hot+0.008
uster+0.008
Neg logit contributions
ls-0.012
cks-0.010
 vows-0.010
ves-0.010
irs-0.010
Token mum
Token ID25682
Feature activation+2.31e-04

Pos logit contributions
ls+0.033
cks+0.030
 vows+0.029
irs+0.027
ves+0.027
Neg logit contributions
wheel-0.026
 sill-0.025
hot-0.024
uster-0.023
 aback-0.023
Token heard
Token ID2982
Feature activation+1.89e-03

Pos logit contributions
ls+0.000
cks+0.000
 vows+0.000
irs+0.000
ves+0.000
Neg logit contributions
wheel-0.000
 sill-0.000
hot-0.000
 aback-0.000
uster-0.000
Token him
Token ID683
Feature activation+8.68e-03

Pos logit contributions
ls+0.003
cks+0.003
 vows+0.003
irs+0.003
ves+0.003
Neg logit contributions
wheel-0.003
 sill-0.003
hot-0.003
uster-0.003
 aback-0.003
Token complaining
Token ID18705
Feature activation+4.25e-03

Pos logit contributions
ls+0.016
cks+0.014
 vows+0.014
irs+0.013
ves+0.013
Neg logit contributions
wheel-0.014
 sill-0.014
hot-0.013
uster-0.013
 aback-0.013
Token."
Token ID526
Feature activation+6.73e-04

Pos logit contributions
 sill+0.003
wheel+0.003
hot+0.003
est+0.003
icle+0.003
Neg logit contributions
ls-0.004
cks-0.004
 vows-0.003
irs-0.003
ves-0.003
Token
Token ID198
Feature activation+1.13e-03

Pos logit contributions
ls+0.001
cks+0.001
 vows+0.001
irs+0.001
ves+0.001
Neg logit contributions
wheel-0.001
 sill-0.001
hot-0.001
uster-0.001
 aback-0.001
Token
Token ID198
Feature activation+7.70e-03

Pos logit contributions
ls+0.002
cks+0.002
 vows+0.002
irs+0.002
 nations+0.002
Neg logit contributions
wheel-0.002
 sill-0.002
hot-0.001
uster-0.001
 aback-0.001
TokenAnna
Token ID31160
Feature activation+1.65e-02

Pos logit contributions
ls+0.015
cks+0.014
 vows+0.014
irs+0.013
 nations+0.012
Neg logit contributions
 sill-0.012
wheel-0.011
hot-0.011
uster-0.010
 vest-0.010
Token smiled
Token ID13541
Feature activation-1.11e-02

Pos logit contributions
ls+0.030
cks+0.028
 vows+0.026
irs+0.026
ves+0.025
Neg logit contributions
wheel-0.027
 sill-0.026
hot-0.025
 aback-0.024
 vest-0.024
Token and
Token ID290
Feature activation-3.90e-02

Pos logit contributions
wheel+0.024
bar+0.022
icle+0.022
uster+0.022
roach+0.021
Neg logit contributions
ls-0.017
 points-0.014
 their-0.014
 runs-0.013
cks-0.013
Token said
Token ID531
Feature activation+3.35e-03

Pos logit contributions
wheel+0.071
 sill+0.069
hot+0.067
 aback+0.065
uster+0.064
Neg logit contributions
ls-0.064
cks-0.058
 vows-0.056
irs-0.053
ves-0.052
Token,
Token ID11
Feature activation-2.72e-02

Pos logit contributions
ls+0.007
cks+0.007
 vows+0.007
irs+0.006
 nations+0.006
Neg logit contributions
wheel-0.004
 sill-0.004
hot-0.004
 aback-0.004
icle-0.004
Token "
Token ID366
Feature activation-1.40e-02

Pos logit contributions
wheel+0.038
 sill+0.037
hot+0.035
uster+0.035
 aback+0.034
Neg logit contributions
ls-0.056
cks-0.051
 vows-0.050
ves-0.047
irs-0.047
TokenI
Token ID40
Feature activation+2.43e-03

Pos logit contributions
uster+0.019
wheel+0.019
 operation+0.019
icle+0.018
bar+0.018
Neg logit contributions
ls-0.026
cks-0.025
 vows-0.025
 points-0.024
 runs-0.023
Token'm
Token ID1101
Feature activation-4.75e-03

Pos logit contributions
ls+0.004
cks+0.004
 vows+0.004
ves+0.004
irs+0.004
Neg logit contributions
wheel-0.004
 sill-0.004
hot-0.004
uster-0.004
icle-0.004
Token silly
Token ID14397
Feature activation+3.89e-03

Pos logit contributions
ls+0.029
cks+0.026
 vows+0.026
ves+0.024
irs+0.024
Neg logit contributions
wheel-0.025
 sill-0.025
hot-0.024
uster-0.023
 aback-0.023
Token idea
Token ID2126
Feature activation-7.98e-03

Pos logit contributions
ls+0.008
cks+0.007
 vows+0.007
ves+0.006
 nations+0.006
Neg logit contributions
wheel-0.006
 sill-0.006
hot-0.006
uster-0.005
 aback-0.005
Token.
Token ID13
Feature activation-2.13e-03

Pos logit contributions
wheel+0.012
 sill+0.012
hot+0.012
icle+0.011
bar+0.011
Neg logit contributions
ls-0.016
cks-0.014
 vows-0.014
irs-0.013
 nations-0.013
Token He
Token ID679
Feature activation+9.42e-03

Pos logit contributions
wheel+0.003
 sill+0.002
uster+0.002
Aid+0.002
hot+0.002
Neg logit contributions
ls-0.005
cks-0.004
 vows-0.004
irs-0.004
 runs-0.004
Token thought
Token ID1807
Feature activation+8.19e-03

Pos logit contributions
ls+0.016
cks+0.016
irs+0.015
 vows+0.014
 nations+0.013
Neg logit contributions
wheel-0.016
 sill-0.015
bar-0.015
hot-0.015
 vest-0.015
Token it
Token ID340
Feature activation-4.43e-02

Pos logit contributions
ls+0.015
cks+0.014
 vows+0.013
irs+0.012
 nations+0.012
Neg logit contributions
wheel-0.013
 sill-0.013
hot-0.012
uster-0.012
icle-0.012
Token would
Token ID561
Feature activation+2.24e-02

Pos logit contributions
wheel+0.086
 sill+0.085
uster+0.084
hot+0.082
icle+0.080
Neg logit contributions
ls-0.066
cks-0.058
 vows-0.057
ves-0.053
 runs-0.051
Token be
Token ID307
Feature activation-9.00e-03

Pos logit contributions
ls+0.040
cks+0.036
 vows+0.035
irs+0.033
ves+0.033
Neg logit contributions
wheel-0.038
 sill-0.037
hot-0.035
uster-0.034
 aback-0.034
Token fun
Token ID1257
Feature activation-9.59e-03

Pos logit contributions
wheel+0.013
 sill+0.013
hot+0.012
 aback+0.012
uster+0.012
Neg logit contributions
ls-0.018
cks-0.017
 vows-0.016
ves-0.015
irs-0.015
Token to
Token ID284
Feature activation+1.14e-02

Pos logit contributions
wheel+0.014
 sill+0.014
hot+0.013
 aback+0.013
uster+0.012
Neg logit contributions
ls-0.019
cks-0.018
 vows-0.017
irs-0.016
ves-0.016
Token come
Token ID1282
Feature activation+2.35e-02

Pos logit contributions
ls+0.024
cks+0.021
 vows+0.020
irs+0.019
 nations+0.019
Neg logit contributions
wheel-0.017
 sill-0.017
bar-0.015
icle-0.015
 vest-0.015
Token apple
Token ID17180
Feature activation-1.33e-02

Pos logit contributions
wheel+0.016
uster+0.016
hot+0.015
 sill+0.015
uit+0.014
Neg logit contributions
ls-0.021
cks-0.019
 vows-0.019
 points-0.018
 runs-0.018
Token.
Token ID13
Feature activation+1.26e-02

Pos logit contributions
wheel+0.021
 sill+0.020
uster+0.019
hot+0.019
 aback+0.019
Neg logit contributions
ls-0.025
cks-0.023
 vows-0.022
ves-0.021
 nations-0.021
Token It
Token ID632
Feature activation-1.02e-02

Pos logit contributions
ls+0.020
cks+0.018
 vows+0.017
irs+0.016
ves+0.016
Neg logit contributions
 sill-0.024
wheel-0.024
hot-0.023
 aback-0.022
icle-0.022
Token looked
Token ID3114
Feature activation+1.36e-02

Pos logit contributions
wheel+0.017
 sill+0.017
hot+0.016
 vest+0.015
icle+0.015
Neg logit contributions
ls-0.018
cks-0.017
 vows-0.016
irs-0.016
 nations-0.016
Token juicy
Token ID35075
Feature activation-2.10e-02

Pos logit contributions
ls+0.028
cks+0.026
 vows+0.025
irs+0.024
ves+0.024
Neg logit contributions
wheel-0.019
 sill-0.018
hot-0.017
uster-0.017
icle-0.017
Token and
Token ID290
Feature activation-4.56e-02

Pos logit contributions
wheel+0.035
uster+0.032
 sill+0.032
Aid+0.031
bar+0.030
Neg logit contributions
ls-0.040
cks-0.035
 vows-0.033
 points-0.032
 runs-0.032
Token sweet
Token ID6029
Feature activation-1.14e-02

Pos logit contributions
wheel+0.064
 sill+0.063
hot+0.060
 vest+0.056
 aback+0.056
Neg logit contributions
ls-0.092
cks-0.086
 vows-0.085
irs-0.082
 nations-0.081
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
 sill+0.018
wheel+0.018
hot+0.017
est+0.017
icle+0.016
Neg logit contributions
ls-0.021
cks-0.020
 vows-0.019
irs-0.019
ves-0.018
Token Tom
Token ID4186
Feature activation+4.46e-03

Pos logit contributions
ls+0.017
cks+0.016
 vows+0.015
irs+0.014
ils+0.014
Neg logit contributions
 sill-0.020
wheel-0.020
hot-0.020
 aback-0.019
uster-0.019
Token said
Token ID531
Feature activation+3.41e-03

Pos logit contributions
ls+0.009
cks+0.008
 vows+0.008
irs+0.008
 nations+0.008
Neg logit contributions
wheel-0.007
 sill-0.006
hot-0.006
 aback-0.006
 vest-0.006
Token,
Token ID11
Feature activation-1.81e-02

Pos logit contributions
ls+0.007
cks+0.007
irs+0.007
 vows+0.007
 nations+0.006
Neg logit contributions
wheel-0.004
 sill-0.004
hot-0.004
 aback-0.004
icle-0.004
TokenL
Token ID43
Feature activation-8.25e-03

Pos logit contributions
ls+0.010
cks+0.010
 vows+0.009
irs+0.009
 cor+0.009
Neg logit contributions
wheel-0.007
 sill-0.006
hot-0.006
uster-0.006
 vest-0.006
Tokenily
Token ID813
Feature activation-1.22e-03

Pos logit contributions
wheel+0.011
 sill+0.011
hot+0.011
uster+0.010
bar+0.010
Neg logit contributions
ls-0.017
cks-0.016
 vows-0.015
irs-0.015
ves-0.015
Token was
Token ID373
Feature activation-1.05e-02

Pos logit contributions
wheel+0.002
 sill+0.002
hot+0.002
uster+0.002
icle+0.002
Neg logit contributions
ls-0.002
 vows-0.002
cks-0.002
ves-0.002
 runs-0.002
Token happy
Token ID3772
Feature activation-1.58e-03

Pos logit contributions
uster+0.018
hot+0.017
inter+0.017
icle+0.017
wheel+0.017
Neg logit contributions
cks-0.017
ls-0.017
 vows-0.016
 their-0.015
 runs-0.015
Token that
Token ID326
Feature activation-3.96e-02

Pos logit contributions
uster+0.003
wheel+0.003
bar+0.003
hot+0.003
 sill+0.003
Neg logit contributions
ls-0.003
 vows-0.002
cks-0.002
 their-0.002
 they-0.002
Token she
Token ID673
Feature activation-3.99e-02

Pos logit contributions
wheel+0.077
 sill+0.075
hot+0.073
uster+0.072
icle+0.071
Neg logit contributions
ls-0.061
cks-0.054
 vows-0.052
irs-0.048
ves-0.048
Token used
Token ID973
Feature activation-1.47e-02

Pos logit contributions
 sill+0.080
icle+0.077
wheel+0.076
uster+0.075
bar+0.074
Neg logit contributions
ls-0.059
 vows-0.050
cks-0.049
 runs-0.047
ils-0.046
Token her
Token ID607
Feature activation-1.91e-02

Pos logit contributions
wheel+0.029
 sill+0.029
hot+0.028
uster+0.027
 aback+0.027
Neg logit contributions
ls-0.022
cks-0.020
 vows-0.019
irs-0.017
ves-0.017
Token words
Token ID2456
Feature activation-8.17e-03

Pos logit contributions
wheel+0.031
 sill+0.030
hot+0.029
uster+0.028
icle+0.028
Neg logit contributions
ls-0.036
cks-0.033
 vows-0.032
ves-0.030
 nations-0.029
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
wheel+0.014
 sill+0.014
uster+0.014
 Vest+0.014
Aid+0.014
Neg logit contributions
ls-0.013
 vows-0.011
cks-0.011
 their-0.011
ves-0.011
Token made
Token ID925
Feature activation-1.49e-02

Pos logit contributions
wheel+0.029
 sill+0.027
hot+0.025
 cleaner+0.025
 vest+0.025
Neg logit contributions
ls-0.029
cks-0.028
 vows-0.025
irs-0.025
its-0.024
Token the
Token ID262
Feature activation-8.01e-03

Pos logit contributions
ls+0.022
cks+0.019
 vows+0.019
ves+0.019
irs+0.019
Neg logit contributions
 sill-0.015
wheel-0.013
hot-0.013
 3-0.013
icle-0.013
Token yellow
Token ID7872
Feature activation+2.13e-02

Pos logit contributions
 sill+0.011
 handy+0.010
 happiest+0.010
wheel+0.010
 vest+0.010
Neg logit contributions
ls-0.016
cks-0.016
irs-0.015
its-0.014
ves-0.014
Token boat
Token ID8848
Feature activation-4.52e-03

Pos logit contributions
cks+0.047
ls+0.044
irs+0.040
heit+0.040
ves+0.040
Neg logit contributions
boat-0.026
est-0.025
 sill-0.025
 vest-0.024
 handy-0.023
Token.
Token ID13
Feature activation-1.50e-03

Pos logit contributions
wheel+0.007
 sill+0.007
hot+0.007
bar+0.006
uster+0.006
Neg logit contributions
ls-0.008
cks-0.008
 vows-0.008
irs-0.007
ves-0.007
Token From
Token ID3574
Feature activation-2.67e-02

Pos logit contributions
wheel+0.003
 sill+0.002
hot+0.002
uster+0.002
 aback+0.002
Neg logit contributions
ls-0.003
cks-0.002
 vows-0.002
irs-0.002
ves-0.002
Token then
Token ID788
Feature activation-4.53e-02

Pos logit contributions
wheel+0.042
 sill+0.040
hot+0.038
uster+0.038
 aback+0.037
Neg logit contributions
ls-0.053
cks-0.048
 vows-0.046
ves-0.043
 nations-0.043
Token on
Token ID319
Feature activation+1.30e-03

Pos logit contributions
 sill+0.085
wheel+0.085
uster+0.080
 aback+0.078
 Vest+0.078
Neg logit contributions
ls-0.073
cks-0.066
ves-0.060
 vows-0.059
 runs-0.059
Token,
Token ID11
Feature activation-1.85e-02

Pos logit contributions
cks+0.003
ls+0.003
irs+0.003
 vows+0.003
its+0.003
Neg logit contributions
est-0.001
 sill-0.001
hot-0.001
wheel-0.001
icle-0.001
Token the
Token ID262
Feature activation+6.72e-03

Pos logit contributions
wheel+0.039
 sill+0.039
hot+0.037
 aback+0.036
icle+0.036
Neg logit contributions
ls-0.025
cks-0.022
 vows-0.022
irs-0.019
ves-0.019
Token island
Token ID7022
Feature activation+2.35e-02

Pos logit contributions
ls+0.013
cks+0.013
irs+0.012
 vows+0.012
ves+0.011
Neg logit contributions
 sill-0.010
 handy-0.009
 happiest-0.009
est-0.009
wheel-0.009
Token stayed
Token ID9658
Feature activation-1.44e-02

Pos logit contributions
ls+0.039
cks+0.036
 vows+0.034
irs+0.033
ves+0.032
Neg logit contributions
wheel-0.041
 sill-0.041
hot-0.039
 aback-0.038
icle-0.037