TOP ACTIVATIONS
MAX = 5.566

could see lots of av oc ados that the supplier had
they saw a rh in oc eros . They tell their
he saw a rh in oc eros ! It looked very
couldn 't find any av oc ados . Finally , she
saw a big rh in oc eros . The rh in
they could grow more av oc ados and share them with
saw a big rh in oc eros . It was dirty
at that big rh in oc eros !" Billy said ,
suddenly saw a rh in oc eros in front of him
didn 't like wet av oc ados , so he decided
so glad the rh in oc eros went away . He
into a big rh in oc eros . The rh in
?" The huge rh in oc eros thought for a moment
that boss y rh in oc eros . <|endoftext|> D ee
they saw a rh in oc eros in the field .
saw a big rh in oc eros at the park .
a very clever rh in oc eros ." <|endoftext|> Once upon
Unicorn !" The rh in oc eros said , feeling much
It is a rh in oc eros . It is bright
she could request some av oc ados from the store .

MIN ACTIVATIONS
MIN = -3.699

a shiny thing in its be ak . It looked like
piece of meat in its be ak . She was very
beautiful white feather in its be ak . The
yellow corn cob in his be ak ! He dropped it
bright green olive in its be ak . It was a
had Pip o in its be ak . It was flying
red and had a yellow be ak . He could talk
had a feather in its be ak . It flew to
and white and had a be ak and fl ippers .
it had something in its be ak .
holding the carrot in its be ak . Benny and Lily
It put its be ak into the crack and
a little envelope in its be ak . Tim opened the
dropped the car from its be ak . The car fell
the needle out of its be ak . After a few
. It had a long be ak and shiny eyes .
had a loop in its be ak . The bird started
it hurt Twe ety 's be ak . Twe ety learned
pipe got stuck on his be ak !
had got stuck in its be ak ! The

INTERVAL 3.250 - 5.566
CONTAINS 0.004%

played with the rh in oc eros for a while ,
big , gray rh in oc eros . He lived in
Daddy , and three - year - old little Sus ie
trapped with the rh in oc eros . They looked for
The rh in oc eros nodded and the little

INTERVAL 0.934 - 3.250
CONTAINS 5.868%

all o o hed and ah hed as they looked at
park . Every day he would slide down , faster and
the wagon as it drove around the garden . The tough
had made her mom wait too long . She felt a
Ben shouted as he jumped out from behind the tree .

INTERVAL -1.383 - 0.934
CONTAINS 92.631%

about the colors . We just want to eat the ice
a friend . But the balloon was so big and it
. She climbs out . She is wet too .
young boy in the ocean . The sailor was in danger
girl named Amy went for a walk with her mom .

INTERVAL -3.699 - -1.383
CONTAINS 1.496%

they could play together and be happy . She hugged the
bald old men should not be afraid to go out and
ted the rabbit softly . To his surprise , the rabbit
he had to leave it be . That night
day on , Tim and Sue would meet every night to
Token could
Token ID714
Feature activation+4.66e-01

Pos logit contributions
ver+0.008
hand+0.007
 chief+0.007
 Even+0.007
 department+0.007
Neg logit contributions
 fru-0.007
 skirts-0.007
 ey-0.007
 skirt-0.007
 makeup-0.006
Token see
Token ID766
Feature activation-6.25e-01

Pos logit contributions
ver+0.019
hand+0.018
 chief+0.017
 department+0.017
rolled+0.016
Neg logit contributions
 ey-0.013
 fru-0.012
 skirts-0.012
 skirt-0.011
 makeup-0.011
Token lots
Token ID6041
Feature activation+1.67e+00

Pos logit contributions
 ey+0.021
 skirts+0.021
 fru+0.020
 skirt+0.018
 ol+0.018
Neg logit contributions
ver-0.021
hand-0.020
 chief-0.019
rolled-0.019
 department-0.018
Token of
Token ID286
Feature activation+1.24e+00

Pos logit contributions
ver+0.031
hand+0.025
 chief+0.025
rolled+0.025
 department+0.022
Neg logit contributions
 ey-0.084
 skirts-0.083
 fru-0.082
 skirt-0.076
 makeup-0.075
Token av
Token ID1196
Feature activation+2.98e+00

Pos logit contributions
ver+0.050
 happily+0.048
 chief+0.047
hand+0.047
 Even+0.046
Neg logit contributions
 ey-0.033
 skirts-0.032
 fru-0.029
ems-0.029
 skirt-0.028
Tokenoc
Token ID420
Feature activation+5.57e+00

Pos logit contributions
ver+0.076
hand+0.068
 chief+0.065
 department+0.062
rolled+0.061
Neg logit contributions
 ey-0.130
 skirts-0.126
 fru-0.125
 skirt-0.114
ems-0.112
Tokenados
Token ID22484
Feature activation+8.16e-02

Pos logit contributions
ver+0.310
hand+0.275
 tow+0.274
 sadly+0.273
 attendant+0.273
Neg logit contributions
 ey-0.084
 fru-0.074
 ol-0.071
 skirts-0.057
 brace-0.051
Token that
Token ID326
Feature activation-1.67e-01

Pos logit contributions
ver+0.003
hand+0.002
 chief+0.002
rolled+0.002
 happily+0.002
Neg logit contributions
 ey-0.003
 skirts-0.003
 fru-0.003
 skirt-0.003
ems-0.003
Token the
Token ID262
Feature activation-8.24e-01

Pos logit contributions
 ey+0.006
 skirts+0.006
 fru+0.006
 skirt+0.006
ems+0.005
Neg logit contributions
ver-0.005
hand-0.005
 chief-0.005
 happily-0.005
rolled-0.004
Token supplier
Token ID22693
Feature activation+9.25e-02

Pos logit contributions
 ey+0.026
 skirts+0.025
 fru+0.024
 skirt+0.022
 makeup+0.021
Neg logit contributions
ver-0.032
hand-0.029
rolled-0.028
 chief-0.028
 department-0.027
Token had
Token ID550
Feature activation-8.19e-01

Pos logit contributions
ver+0.003
hand+0.003
 chief+0.003
 department+0.003
 Even+0.003
Neg logit contributions
 ey-0.003
 fru-0.003
 skirts-0.003
 skirt-0.003
ems-0.003
Token they
Token ID484
Feature activation+4.45e-01

Pos logit contributions
ver+0.040
hand+0.037
 chief+0.035
 department+0.034
rolled+0.034
Neg logit contributions
 skirts-0.039
 fru-0.037
 ey-0.037
----0.034
 ol-0.034
Token saw
Token ID2497
Feature activation-2.63e-01

Pos logit contributions
ver+0.016
hand+0.016
 chief+0.015
rolled+0.015
 Even+0.015
Neg logit contributions
 skirts-0.014
 ey-0.014
 fru-0.013
 skirt-0.012
ems-0.012
Token a
Token ID257
Feature activation+3.91e-01

Pos logit contributions
 skirts+0.008
 ey+0.008
 fru+0.008
 ol+0.007
 da+0.007
Neg logit contributions
ver-0.010
hand-0.008
 chief-0.008
rolled-0.008
 Even-0.008
Token rh
Token ID9529
Feature activation+2.87e+00

Pos logit contributions
ver+0.016
hand+0.015
rolled+0.014
 chief+0.014
uttered+0.014
Neg logit contributions
 ey-0.011
 fru-0.011
 skirts-0.010
 skirt-0.010
 da-0.009
Tokenin
Token ID259
Feature activation+1.26e+00

Pos logit contributions
ver+0.093
rolled+0.091
 Even+0.091
hand+0.090
 sadly+0.085
Neg logit contributions
 ey-0.092
 skirts-0.087
 fru-0.087
 da-0.082
robat-0.079
Tokenoc
Token ID420
Feature activation+4.89e+00

Pos logit contributions
ver+0.042
uttered+0.036
hand+0.035
rolled+0.035
 Even+0.034
Neg logit contributions
 ey-0.042
 fru-0.041
 da-0.039
 skirts-0.038
 ol-0.038
Tokeneros
Token ID27498
Feature activation+1.13e+00

Pos logit contributions
ver+0.193
 Even+0.169
case+0.160
 happily+0.157
 sadly+0.155
Neg logit contributions
 ey-0.146
 fru-0.142
ution-0.125
 ol-0.123
 da-0.122
Token.
Token ID13
Feature activation+9.57e-02

Pos logit contributions
ver+0.042
hand+0.038
 Even+0.038
rolled+0.038
 chief+0.037
Neg logit contributions
 skirts-0.034
 ey-0.032
 fru-0.031
 skirt-0.030
 makeup-0.029
Token They
Token ID1119
Feature activation+1.86e-01

Pos logit contributions
ver+0.003
hand+0.002
 chief+0.002
 happily+0.002
rolled+0.002
Neg logit contributions
 ey-0.004
 skirts-0.004
 fru-0.004
 skirt-0.004
ems-0.004
Token tell
Token ID1560
Feature activation-1.24e-01

Pos logit contributions
hand+0.008
ver+0.007
 chief+0.007
rolled+0.007
 department+0.007
Neg logit contributions
 ey-0.005
 skirts-0.005
 fru-0.005
 skirt-0.005
ems-0.004
Token their
Token ID511
Feature activation-1.40e-01

Pos logit contributions
 skirts+0.003
 fru+0.003
 ey+0.003
 da+0.003
 ol+0.003
Neg logit contributions
ver-0.005
hand-0.004
case-0.004
rolled-0.004
 department-0.004
Token he
Token ID339
Feature activation+1.31e-01

Pos logit contributions
ver+0.006
hand+0.006
 department+0.006
rolled+0.006
 chief+0.006
Neg logit contributions
 ey-0.003
 fru-0.003
 skirts-0.003
----0.003
 ol-0.003
Token saw
Token ID2497
Feature activation-4.02e-01

Pos logit contributions
ver+0.004
hand+0.004
 chief+0.004
rolled+0.004
 Even+0.004
Neg logit contributions
 ey-0.004
 skirts-0.004
 fru-0.004
 skirt-0.004
ems-0.004
Token a
Token ID257
Feature activation+6.22e-01

Pos logit contributions
 ey+0.012
 fru+0.011
 jam+0.011
 da+0.011
 ol+0.011
Neg logit contributions
ver-0.016
rolled-0.015
hand-0.014
uttered-0.013
 department-0.013
Token rh
Token ID9529
Feature activation+2.84e+00

Pos logit contributions
ver+0.025
hand+0.023
rolled+0.021
 chief+0.021
 Even+0.021
Neg logit contributions
 ey-0.019
 fru-0.018
 skirts-0.018
 skirt-0.017
 makeup-0.016
Tokenin
Token ID259
Feature activation+1.55e+00

Pos logit contributions
rolled+0.098
ver+0.095
hand+0.094
 Even+0.091
 Together+0.088
Neg logit contributions
 ey-0.091
 fru-0.081
 da-0.080
 jam-0.079
 skirts-0.078
Tokenoc
Token ID420
Feature activation+4.85e+00

Pos logit contributions
ver+0.057
hand+0.049
uttered+0.048
rolled+0.048
 Even+0.045
Neg logit contributions
 ey-0.051
 fru-0.049
 da-0.046
 ol-0.045
 jam-0.044
Tokeneros
Token ID27498
Feature activation+1.14e+00

Pos logit contributions
ver+0.198
 Even+0.163
rolled+0.158
case+0.152
 Hours+0.152
Neg logit contributions
 ey-0.154
 fru-0.142
 ol-0.129
 da-0.127
 jam-0.119
Token!
Token ID0
Feature activation-2.85e-01

Pos logit contributions
ver+0.046
 Even+0.040
hand+0.040
 chief+0.040
rolled+0.039
Neg logit contributions
 ey-0.032
 skirts-0.030
 fru-0.028
 skirt-0.028
 doing-0.027
Token It
Token ID632
Feature activation+9.40e-01

Pos logit contributions
 ey+0.009
 fru+0.009
 skirts+0.008
---+0.008
 ol+0.008
Neg logit contributions
ver-0.010
hand-0.009
 chief-0.009
 department-0.009
rolled-0.009
Token looked
Token ID3114
Feature activation-4.98e-01

Pos logit contributions
ver+0.032
hand+0.029
 chief+0.028
 department+0.027
rolled+0.026
Neg logit contributions
 fru-0.032
 ey-0.031
 skirts-0.030
 skirt-0.028
----0.026
Token very
Token ID845
Feature activation+7.47e-02

Pos logit contributions
 ey+0.017
 skirts+0.017
 fru+0.017
 skirt+0.015
 makeup+0.014
Neg logit contributions
ver-0.017
hand-0.016
 chief-0.015
rolled-0.015
 department-0.015
Token couldn
Token ID3521
Feature activation-1.23e-01

Pos logit contributions
 ey+0.011
 skirts+0.010
 fru+0.010
 skirt+0.009
ems+0.009
Neg logit contributions
ver-0.009
hand-0.008
 chief-0.008
 happily-0.008
 sadly-0.008
Token't
Token ID470
Feature activation-2.25e-02

Pos logit contributions
 ey+0.004
---+0.004
 doing+0.004
 makeup+0.004
 skirts+0.004
Neg logit contributions
 chief-0.003
 department-0.003
ver-0.003
hand-0.003
year-0.003
Token find
Token ID1064
Feature activation-4.37e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.001
 skirt+0.001
 makeup+0.001
Neg logit contributions
ver-0.001
hand-0.001
 chief-0.001
 department-0.001
rolled-0.001
Token any
Token ID597
Feature activation+3.27e-01

Pos logit contributions
 skirts+0.013
 ey+0.013
 fru+0.012
 skirt+0.011
 makeup+0.011
Neg logit contributions
ver-0.017
 chief-0.016
hand-0.016
rolled-0.015
 department-0.015
Token av
Token ID1196
Feature activation+2.36e+00

Pos logit contributions
ver+0.012
hand+0.011
 chief+0.011
rolled+0.011
 Even+0.010
Neg logit contributions
 ey-0.011
 skirts-0.010
 fru-0.010
 skirt-0.009
 makeup-0.009
Tokenoc
Token ID420
Feature activation+4.80e+00

Pos logit contributions
ver+0.054
hand+0.047
 chief+0.045
 happily+0.042
rolled+0.042
Neg logit contributions
 ey-0.109
 skirts-0.107
 fru-0.104
 skirt-0.098
ems-0.095
Tokenados
Token ID22484
Feature activation-3.10e-01

Pos logit contributions
ver+0.250
hand+0.228
 Even+0.223
 tow+0.222
 department+0.222
Neg logit contributions
 ey-0.082
 fru-0.073
 ol-0.065
 skirts-0.061
 makeup-0.052
Token.
Token ID13
Feature activation-6.04e-01

Pos logit contributions
 ey+0.012
 skirts+0.012
 fru+0.011
 skirt+0.010
ems+0.010
Neg logit contributions
ver-0.010
hand-0.009
 chief-0.008
 happily-0.008
rolled-0.008
Token Finally
Token ID9461
Feature activation-3.43e-01

Pos logit contributions
 ey+0.022
 fru+0.021
 skirts+0.021
 makeup+0.019
 skirt+0.019
Neg logit contributions
ver-0.019
 chief-0.017
hand-0.017
 department-0.016
rolled-0.015
Token,
Token ID11
Feature activation-4.44e-01

Pos logit contributions
 ey+0.013
 skirts+0.013
 fru+0.013
 skirt+0.012
ems+0.011
Neg logit contributions
ver-0.010
hand-0.009
 chief-0.009
rolled-0.009
 happily-0.009
Token she
Token ID673
Feature activation-3.20e-01

Pos logit contributions
 skirts+0.011
 ey+0.011
 fru+0.011
 skirt+0.010
 makeup+0.010
Neg logit contributions
ver-0.018
hand-0.017
 chief-0.017
 department-0.017
rolled-0.016
Token saw
Token ID2497
Feature activation-3.12e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.003
ems+0.003
Neg logit contributions
ver-0.006
hand-0.006
 chief-0.006
 Even-0.006
 department-0.006
Token a
Token ID257
Feature activation+4.91e-01

Pos logit contributions
 skirts+0.010
 fru+0.010
 ey+0.010
 sunglasses+0.009
 da+0.009
Neg logit contributions
ver-0.012
rolled-0.010
hand-0.010
uttered-0.009
 chief-0.009
Token big
Token ID1263
Feature activation+6.28e-01

Pos logit contributions
ver+0.019
hand+0.017
 chief+0.016
rolled+0.016
 Even+0.016
Neg logit contributions
 ey-0.015
 fru-0.015
 skirts-0.015
 skirt-0.013
 makeup-0.013
Token rh
Token ID9529
Feature activation+2.90e+00

Pos logit contributions
ver+0.021
hand+0.019
 chief+0.019
rolled+0.018
 happily+0.018
Neg logit contributions
 ey-0.022
 skirts-0.022
 fru-0.021
 skirt-0.020
 makeup-0.019
Tokenin
Token ID259
Feature activation+1.37e+00

Pos logit contributions
rolled+0.097
ver+0.095
hand+0.095
 Even+0.093
 Together+0.090
Neg logit contributions
 ey-0.091
 skirts-0.083
 fru-0.082
 da-0.081
 jam-0.079
Tokenoc
Token ID420
Feature activation+4.78e+00

Pos logit contributions
ver+0.050
hand+0.042
uttered+0.042
rolled+0.041
 Even+0.039
Neg logit contributions
 ey-0.045
 fru-0.042
 da-0.041
 ol-0.040
 jam-0.039
Tokeneros
Token ID27498
Feature activation+1.17e+00

Pos logit contributions
ver+0.186
 Even+0.157
 sadly+0.147
rolled+0.147
 happily+0.145
Neg logit contributions
 ey-0.152
 fru-0.140
 ol-0.126
 da-0.125
ution-0.122
Token.
Token ID13
Feature activation+4.83e-02

Pos logit contributions
ver+0.048
 Even+0.041
hand+0.041
 department+0.041
 chief+0.040
Neg logit contributions
 ey-0.032
 skirts-0.031
 doing-0.029
 skirt-0.029
 makeup-0.028
Token The
Token ID383
Feature activation+9.21e-02

Pos logit contributions
ver+0.002
hand+0.002
 chief+0.001
uttered+0.001
 safely+0.001
Neg logit contributions
 ey-0.002
 fru-0.002
 skirts-0.001
 ol-0.001
 makeup-0.001
Token rh
Token ID9529
Feature activation+2.05e+00

Pos logit contributions
ver+0.003
hand+0.002
 department+0.002
 chief+0.002
rolled+0.002
Neg logit contributions
 ey-0.004
 fru-0.004
 skirts-0.003
 prett-0.003
 skirt-0.003
Tokenin
Token ID259
Feature activation+5.14e-01

Pos logit contributions
ver+0.059
hand+0.059
rolled+0.056
 Even+0.053
 department+0.052
Neg logit contributions
 ey-0.077
 fru-0.073
 skirts-0.071
 makeup-0.065
ems-0.065
Token they
Token ID484
Feature activation+6.03e-01

Pos logit contributions
ver+0.034
hand+0.031
 chief+0.030
 happily+0.029
 sadly+0.028
Neg logit contributions
 ey-0.060
 skirts-0.058
 fru-0.056
 skirt-0.053
ems-0.052
Token could
Token ID714
Feature activation+6.19e-01

Pos logit contributions
hand+0.023
ver+0.022
rolled+0.021
 chief+0.021
 Even+0.021
Neg logit contributions
 fru-0.017
 skirts-0.017
 ey-0.016
ems-0.015
 skirt-0.015
Token grow
Token ID1663
Feature activation-7.53e-01

Pos logit contributions
ver+0.024
hand+0.022
 chief+0.022
rolled+0.021
 department+0.021
Neg logit contributions
 ey-0.019
 skirts-0.018
 fru-0.018
 skirt-0.016
 makeup-0.016
Token more
Token ID517
Feature activation+4.18e-01

Pos logit contributions
 ey+0.031
 skirts+0.030
 fru+0.030
 skirt+0.028
ems+0.027
Neg logit contributions
ver-0.021
hand-0.018
 chief-0.018
 happily-0.018
 sadly-0.017
Token av
Token ID1196
Feature activation+2.61e+00

Pos logit contributions
 happily+0.015
 quickly+0.014
 safely+0.014
ver+0.014
 chief+0.013
Neg logit contributions
 ey-0.013
 skirts-0.013
ems-0.012
 fru-0.011
 skirt-0.011
Tokenoc
Token ID420
Feature activation+4.78e+00

Pos logit contributions
ver+0.056
hand+0.049
 chief+0.047
 happily+0.044
 Even+0.043
Neg logit contributions
 ey-0.123
 skirts-0.121
 fru-0.118
 skirt-0.112
 makeup-0.108
Tokenados
Token ID22484
Feature activation-3.40e-01

Pos logit contributions
ver+0.263
 tow+0.236
 Even+0.236
case+0.235
 sadly+0.234
Neg logit contributions
 ey-0.066
 fru-0.065
 ol-0.058
 skirts-0.047
 brace-0.046
Token and
Token ID290
Feature activation+1.71e-01

Pos logit contributions
 ey+0.014
 skirts+0.013
 fru+0.013
 skirt+0.012
 makeup+0.012
Neg logit contributions
ver-0.010
hand-0.009
 chief-0.008
 happily-0.008
 department-0.008
Token share
Token ID2648
Feature activation-1.17e+00

Pos logit contributions
ver+0.006
hand+0.005
 chief+0.005
 happily+0.005
 Even+0.005
Neg logit contributions
 ey-0.006
 skirts-0.006
 fru-0.005
 skirt-0.005
ems-0.005
Token them
Token ID606
Feature activation-1.53e+00

Pos logit contributions
 ey+0.048
 skirts+0.047
 fru+0.045
 skirt+0.042
ems+0.041
Neg logit contributions
ver-0.033
hand-0.029
 chief-0.029
 happily-0.027
 Even-0.027
Token with
Token ID351
Feature activation-1.09e+00

Pos logit contributions
 skirts+0.058
 fru+0.056
 ey+0.056
 skirt+0.052
 makeup+0.050
Neg logit contributions
ver-0.048
hand-0.044
 chief-0.043
rolled-0.042
 department-0.042
Token saw
Token ID2497
Feature activation-3.60e-01

Pos logit contributions
ver+0.012
hand+0.011
 chief+0.011
 department+0.011
 Even+0.011
Neg logit contributions
 ey-0.009
 skirts-0.009
 fru-0.008
 skirt-0.007
 makeup-0.007
Token a
Token ID257
Feature activation+6.61e-01

Pos logit contributions
 skirts+0.014
 ey+0.013
 fru+0.013
 da+0.013
 skirt+0.012
Neg logit contributions
ver-0.012
hand-0.010
 chief-0.010
rolled-0.010
 department-0.009
Token big
Token ID1263
Feature activation+6.87e-01

Pos logit contributions
ver+0.025
hand+0.023
 chief+0.022
rolled+0.022
 Even+0.022
Neg logit contributions
 ey-0.021
 skirts-0.020
 fru-0.020
 skirt-0.018
 makeup-0.017
Token rh
Token ID9529
Feature activation+3.06e+00

Pos logit contributions
ver+0.022
hand+0.020
 chief+0.020
 happily+0.019
 Even+0.019
Neg logit contributions
 ey-0.025
 skirts-0.024
 fru-0.023
 skirt-0.022
ems-0.021
Tokenin
Token ID259
Feature activation+1.42e+00

Pos logit contributions
hand+0.108
 Even+0.107
rolled+0.106
ver+0.106
 Together+0.104
Neg logit contributions
 ey-0.087
 skirts-0.082
 fru-0.081
 da-0.081
P-0.078
Tokenoc
Token ID420
Feature activation+4.74e+00

Pos logit contributions
ver+0.045
hand+0.039
rolled+0.036
uttered+0.036
 department+0.036
Neg logit contributions
 ey-0.053
 fru-0.051
 skirts-0.049
 da-0.048
 skirt-0.047
Tokeneros
Token ID27498
Feature activation+1.12e+00

Pos logit contributions
ver+0.194
 Even+0.166
 Hours+0.156
case+0.155
 sadly+0.153
Neg logit contributions
 ey-0.139
 fru-0.130
 da-0.121
 ol-0.115
 brace-0.111
Token.
Token ID13
Feature activation-1.08e-01

Pos logit contributions
ver+0.044
hand+0.039
 chief+0.038
 Even+0.038
 department+0.038
Neg logit contributions
 ey-0.032
 skirts-0.032
 skirt-0.030
 fru-0.029
 makeup-0.029
Token It
Token ID632
Feature activation+6.65e-01

Pos logit contributions
 ey+0.004
 skirts+0.004
 fru+0.004
 skirt+0.004
 makeup+0.004
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.003
 department-0.002
rolled-0.002
Token was
Token ID373
Feature activation+1.53e-01

Pos logit contributions
ver+0.021
hand+0.019
 chief+0.018
 department+0.017
rolled+0.017
Neg logit contributions
 ey-0.025
 skirts-0.025
 fru-0.025
 skirt-0.022
 makeup-0.021
Token dirty
Token ID11841
Feature activation-8.00e-01

Pos logit contributions
ver+0.005
hand+0.004
 chief+0.004
 happily+0.004
 Even+0.004
Neg logit contributions
 ey-0.006
 skirts-0.005
 fru-0.005
 skirt-0.005
ems-0.005
Token at
Token ID379
Feature activation+2.23e-01

Pos logit contributions
ver+0.011
 sadly+0.010
 happily+0.010
 chief+0.010
hand+0.010
Neg logit contributions
 ey-0.016
 skirts-0.015
 fru-0.014
 skirt-0.013
ems-0.013
Token that
Token ID326
Feature activation+1.47e+00

Pos logit contributions
ver+0.008
hand+0.007
 department+0.007
 chief+0.007
rolled+0.007
Neg logit contributions
 ey-0.007
 skirts-0.007
 fru-0.007
 makeup-0.006
 da-0.006
Token big
Token ID1263
Feature activation+6.57e-01

Pos logit contributions
ver+0.046
hand+0.044
 department+0.041
uttered+0.041
rolled+0.041
Neg logit contributions
 fru-0.051
 ey-0.050
 skirts-0.048
ems-0.045
 prett-0.045
Token rh
Token ID9529
Feature activation+3.31e+00

Pos logit contributions
ver+0.020
hand+0.018
 chief+0.018
 happily+0.017
 Even+0.017
Neg logit contributions
 ey-0.025
 skirts-0.025
 fru-0.024
 skirt-0.022
ems-0.021
Tokenin
Token ID259
Feature activation+1.93e+00

Pos logit contributions
ver+0.102
hand+0.101
 Even+0.099
rolled+0.094
 department+0.093
Neg logit contributions
 ey-0.117
 skirts-0.110
 fru-0.108
 da-0.101
ems-0.100
Tokenoc
Token ID420
Feature activation+4.74e+00

Pos logit contributions
ver+0.056
hand+0.052
 Even+0.049
 department+0.048
 happily+0.048
Neg logit contributions
 ey-0.071
 fru-0.068
 skirts-0.067
ems-0.064
 skirt-0.062
Tokeneros
Token ID27498
Feature activation+1.37e+00

Pos logit contributions
ver+0.191
case+0.168
 Even+0.165
 tow+0.162
 happily+0.159
Neg logit contributions
 ey-0.137
 fru-0.127
 ol-0.123
 da-0.111
 jewelry-0.111
Token!"
Token ID2474
Feature activation+4.17e-01

Pos logit contributions
ver+0.055
hand+0.053
 Even+0.050
 chief+0.050
 department+0.049
Neg logit contributions
 ey-0.036
 skirts-0.035
 fru-0.034
 skirt-0.031
ems-0.031
Token Billy
Token ID15890
Feature activation+8.29e-01

Pos logit contributions
ver+0.015
hand+0.014
 chief+0.013
 department+0.013
 happily+0.012
Neg logit contributions
 ey-0.014
 skirts-0.013
 fru-0.013
 skirt-0.012
 makeup-0.011
Token said
Token ID531
Feature activation+7.03e-01

Pos logit contributions
ver+0.034
hand+0.032
 chief+0.032
 department+0.031
rolled+0.030
Neg logit contributions
 skirts-0.022
 ey-0.021
 fru-0.021
 skirt-0.019
 makeup-0.018
Token,
Token ID11
Feature activation+3.34e-02

Pos logit contributions
hand+0.026
ver+0.026
 department+0.026
 Even+0.026
 chief+0.025
Neg logit contributions
 fru-0.017
 skirts-0.015
 makeup-0.015
 skirt-0.015
 ey-0.014
Token suddenly
Token ID6451
Feature activation-4.61e-01

Pos logit contributions
ver+0.001
hand+0.001
 chief+0.001
 happily+0.001
rolled+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.000
ems-0.000
Token saw
Token ID2497
Feature activation-4.62e-01

Pos logit contributions
 ey+0.015
 skirts+0.015
 fru+0.015
 skirt+0.014
ems+0.013
Neg logit contributions
ver-0.016
hand-0.015
 chief-0.014
 department-0.014
 Even-0.014
Token a
Token ID257
Feature activation+5.91e-01

Pos logit contributions
 ey+0.016
 skirts+0.016
 fru+0.015
 makeup+0.015
 skirt+0.015
Neg logit contributions
ver-0.016
 chief-0.014
hand-0.014
 department-0.014
rolled-0.014
Token rh
Token ID9529
Feature activation+2.81e+00

Pos logit contributions
ver+0.024
hand+0.022
 chief+0.021
rolled+0.021
 Even+0.020
Neg logit contributions
 ey-0.018
 skirts-0.017
 fru-0.017
 skirt-0.015
 makeup-0.014
Tokenin
Token ID259
Feature activation+1.30e+00

Pos logit contributions
rolled+0.102
ver+0.100
 Even+0.100
 Hours+0.098
hand+0.098
Neg logit contributions
 ey-0.079
 da-0.070
 fru-0.070
P-0.068
 jam-0.066
Tokenoc
Token ID420
Feature activation+4.73e+00

Pos logit contributions
ver+0.047
hand+0.039
uttered+0.039
 department+0.038
rolled+0.037
Neg logit contributions
 ey-0.044
 fru-0.042
 da-0.040
 ol-0.039
 jam-0.038
Tokeneros
Token ID27498
Feature activation+1.03e+00

Pos logit contributions
ver+0.196
 Even+0.159
case+0.152
 Hours+0.151
 Together+0.151
Neg logit contributions
 ey-0.145
 fru-0.134
 da-0.120
 jewelry-0.118
 brace-0.114
Token in
Token ID287
Feature activation-4.37e-01

Pos logit contributions
ver+0.041
hand+0.036
 Even+0.035
 chief+0.035
 department+0.035
Neg logit contributions
 ey-0.030
 skirts-0.029
 skirt-0.027
 fru-0.027
 makeup-0.026
Token front
Token ID2166
Feature activation+3.40e-01

Pos logit contributions
 ey+0.015
 skirts+0.014
 fru+0.014
 skirt+0.013
 makeup+0.013
Neg logit contributions
ver-0.016
hand-0.014
 chief-0.014
 department-0.013
rolled-0.013
Token of
Token ID286
Feature activation+4.37e-01

Pos logit contributions
ver+0.006
hand+0.005
 chief+0.005
 department+0.004
rolled+0.004
Neg logit contributions
 ey-0.018
 skirts-0.017
 fru-0.017
 skirt-0.016
 makeup-0.016
Token him
Token ID683
Feature activation-1.79e-01

Pos logit contributions
ver+0.013
 chief+0.012
hand+0.011
 department+0.011
 Even+0.011
Neg logit contributions
 ey-0.017
 skirts-0.017
 fru-0.016
 skirt-0.015
 makeup-0.015
Token didn
Token ID1422
Feature activation+6.14e-02

Pos logit contributions
ver+0.008
hand+0.008
 chief+0.008
 department+0.007
rolled+0.007
Neg logit contributions
 skirts-0.007
 ey-0.007
 fru-0.007
 skirt-0.006
ems-0.006
Token't
Token ID470
Feature activation+8.19e-02

Pos logit contributions
 chief+0.002
hand+0.002
 department+0.002
 brigade+0.001
ver+0.001
Neg logit contributions
 ey-0.002
----0.002
 skirts-0.002
 makeup-0.002
rys-0.002
Token like
Token ID588
Feature activation-2.64e-01

Pos logit contributions
ver+0.002
 happily+0.002
 Even+0.002
 quickly+0.001
 safely+0.001
Neg logit contributions
 ey-0.004
 fru-0.004
 skirts-0.004
eking-0.003
 skirt-0.003
Token wet
Token ID9583
Feature activation+1.75e-01

Pos logit contributions
 ey+0.010
 skirts+0.009
 fru+0.009
ems+0.009
 skirt+0.009
Neg logit contributions
ver-0.008
hand-0.007
 happily-0.007
 chief-0.007
 Even-0.007
Token av
Token ID1196
Feature activation+2.79e+00

Pos logit contributions
 happily+0.006
 sadly+0.006
 quickly+0.006
hand+0.005
 Even+0.005
Neg logit contributions
 ey-0.005
 skirts-0.005
 fru-0.005
ems-0.005
 skirt-0.005
Tokenoc
Token ID420
Feature activation+4.70e+00

Pos logit contributions
ver+0.052
 happily+0.042
hand+0.041
 Even+0.040
 chief+0.039
Neg logit contributions
 ey-0.139
 skirts-0.137
 fru-0.132
 skirt-0.128
 makeup-0.123
Tokenados
Token ID22484
Feature activation+1.38e-02

Pos logit contributions
ver+0.244
hand+0.227
 chief+0.225
 department+0.219
 tow+0.217
Neg logit contributions
 ey-0.082
 fru-0.075
 skirts-0.066
 ol-0.065
 makeup-0.059
Token,
Token ID11
Feature activation-6.01e-01

Pos logit contributions
ver+0.000
 happily+0.000
 quickly+0.000
 sadly+0.000
hand+0.000
Neg logit contributions
 ey-0.001
 fru-0.001
 skirts-0.001
 skirt-0.001
ems-0.001
Token so
Token ID523
Feature activation-1.06e+00

Pos logit contributions
 ey+0.026
 fru+0.024
reath+0.023
 skirts+0.023
ems+0.023
Neg logit contributions
 quickly-0.015
 sadly-0.015
 Even-0.014
ver-0.013
 happily-0.013
Token he
Token ID339
Feature activation+3.64e-01

Pos logit contributions
 ey+0.045
 skirts+0.042
 fru+0.041
ems+0.038
 skirt+0.037
Neg logit contributions
ver-0.029
 sadly-0.027
 happily-0.027
hand-0.026
 quickly-0.026
Token decided
Token ID3066
Feature activation-5.37e-01

Pos logit contributions
ver+0.013
hand+0.012
 chief+0.011
rolled+0.011
 department+0.011
Neg logit contributions
 skirts-0.012
 ey-0.012
 fru-0.012
 skirt-0.011
 makeup-0.011
Token so
Token ID523
Feature activation-7.36e-01

Pos logit contributions
ver+0.006
hand+0.006
 department+0.006
 chief+0.005
rolled+0.005
Neg logit contributions
 fru-0.004
 skirts-0.004
 doing-0.004
 ey-0.004
 prett-0.003
Token glad
Token ID9675
Feature activation+4.93e-01

Pos logit contributions
 fru+0.018
 ey+0.017
 skirts+0.015
 prett+0.014
 doing+0.014
Neg logit contributions
hand-0.031
ver-0.031
 department-0.031
 brigade-0.029
 chief-0.029
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
ver+0.015
hand+0.014
 chief+0.013
 happily+0.012
rolled+0.012
Neg logit contributions
 ey-0.019
 skirts-0.019
 fru-0.018
 skirt-0.017
ems-0.016
Token rh
Token ID9529
Feature activation+2.62e+00

Pos logit contributions
ver+0.004
hand+0.004
rolled+0.004
uttered+0.003
 Even+0.003
Neg logit contributions
 fru-0.004
 ey-0.004
 skirts-0.004
 prett-0.003
 makeup-0.003
Tokenin
Token ID259
Feature activation+1.12e+00

Pos logit contributions
hand+0.093
rolled+0.092
 Together+0.091
 Even+0.090
ver+0.086
Neg logit contributions
 ey-0.070
 fru-0.069
b-0.064
eking-0.061
 ol-0.060
Tokenoc
Token ID420
Feature activation+4.68e+00

Pos logit contributions
ver+0.035
hand+0.031
rolled+0.031
uttered+0.031
 Even+0.030
Neg logit contributions
 fru-0.039
 ey-0.038
 skirts-0.034
 da-0.033
ems-0.033
Tokeneros
Token ID27498
Feature activation+1.03e+00

Pos logit contributions
ver+0.194
 Even+0.166
case+0.164
rolled+0.156
 Together+0.155
Neg logit contributions
 ey-0.129
 fru-0.128
 ol-0.109
ution-0.107
 brace-0.106
Token went
Token ID1816
Feature activation+2.98e-01

Pos logit contributions
ver+0.037
hand+0.035
rolled+0.035
 Even+0.034
 chief+0.033
Neg logit contributions
 fru-0.029
 skirts-0.028
 ey-0.027
 skirt-0.026
ems-0.025
Token away
Token ID1497
Feature activation+3.92e-01

Pos logit contributions
ver+0.010
 chief+0.008
hand+0.008
 department+0.008
 Even+0.008
Neg logit contributions
 ey-0.011
 skirts-0.011
 fru-0.010
 skirt-0.010
 makeup-0.010
Token.
Token ID13
Feature activation-3.61e-01

Pos logit contributions
ver+0.014
hand+0.013
 chief+0.013
rolled+0.012
 department+0.012
Neg logit contributions
 skirts-0.012
 ey-0.012
 fru-0.011
 skirt-0.011
 makeup-0.010
Token He
Token ID679
Feature activation+2.55e-01

Pos logit contributions
 ey+0.013
 fru+0.012
 skirts+0.011
---+0.010
ems+0.010
Neg logit contributions
ver-0.011
 chief-0.011
hand-0.011
 department-0.010
 brigade-0.010
Token into
Token ID656
Feature activation-1.79e-01

Pos logit contributions
ver+0.029
hand+0.026
 chief+0.025
 department+0.024
 brigade+0.023
Neg logit contributions
 skirts-0.029
 ey-0.029
 fru-0.027
 skirt-0.026
 makeup-0.025
Token a
Token ID257
Feature activation+1.24e-01

Pos logit contributions
 ey+0.007
 skirts+0.007
 fru+0.007
 skirt+0.006
 makeup+0.006
Neg logit contributions
ver-0.006
hand-0.005
 chief-0.005
 department-0.005
rolled-0.005
Token big
Token ID1263
Feature activation+1.94e-01

Pos logit contributions
ver+0.004
hand+0.004
 chief+0.004
 happily+0.004
 Even+0.004
Neg logit contributions
 ey-0.004
 skirts-0.004
 fru-0.004
 skirt-0.004
ems-0.004
Token rh
Token ID9529
Feature activation+3.04e+00

Pos logit contributions
ver+0.005
 chief+0.005
 happily+0.005
hand+0.005
 sadly+0.005
Neg logit contributions
 skirts-0.007
 ey-0.007
 fru-0.007
ems-0.006
 skirt-0.006
Tokenin
Token ID259
Feature activation+1.60e+00

Pos logit contributions
ver+0.101
hand+0.098
rolled+0.096
 Even+0.090
 department+0.088
Neg logit contributions
 ey-0.107
 skirts-0.097
 skirt-0.094
 fru-0.093
 da-0.092
Tokenoc
Token ID420
Feature activation+4.67e+00

Pos logit contributions
ver+0.053
hand+0.045
rolled+0.044
uttered+0.044
 chief+0.042
Neg logit contributions
 ey-0.060
 fru-0.055
 skirts-0.055
 skirt-0.054
 da-0.052
Tokeneros
Token ID27498
Feature activation+1.14e+00

Pos logit contributions
ver+0.182
 Even+0.143
rolled+0.143
hand+0.139
 happily+0.136
Neg logit contributions
 ey-0.165
 fru-0.146
 ol-0.134
 da-0.132
 skirts-0.126
Token.
Token ID13
Feature activation-2.94e-01

Pos logit contributions
ver+0.045
hand+0.040
 chief+0.039
rolled+0.038
 Even+0.038
Neg logit contributions
 ey-0.034
 skirts-0.033
 skirt-0.031
 fru-0.030
 makeup-0.029
Token The
Token ID383
Feature activation-1.33e-01

Pos logit contributions
 ey+0.011
 fru+0.011
 skirts+0.010
 skirt+0.010
 makeup+0.009
Neg logit contributions
ver-0.009
hand-0.008
 chief-0.008
 department-0.008
 brigade-0.007
Token rh
Token ID9529
Feature activation+2.13e+00

Pos logit contributions
 ey+0.005
 fru+0.005
 skirts+0.005
 ol+0.004
 skirt+0.004
Neg logit contributions
ver-0.004
hand-0.004
rolled-0.003
uttered-0.003
 chief-0.003
Tokenin
Token ID259
Feature activation+5.31e-01

Pos logit contributions
hand+0.066
ver+0.065
rolled+0.062
 department+0.058
 Even+0.058
Neg logit contributions
 ey-0.078
 fru-0.072
 skirts-0.072
 skirt-0.066
 ol-0.065
Token?"
Token ID1701
Feature activation+1.08e+00

Pos logit contributions
 ey+0.064
 skirts+0.063
 fru+0.060
 skirt+0.054
ems+0.052
Neg logit contributions
ver-0.097
hand-0.092
 chief-0.090
rolled-0.087
 happily-0.087
Token The
Token ID383
Feature activation+5.99e-01

Pos logit contributions
ver+0.028
hand+0.025
 chief+0.025
rolled+0.023
 department+0.023
Neg logit contributions
 ey-0.046
 skirts-0.045
 fru-0.044
 skirt-0.041
ems-0.040
Token huge
Token ID3236
Feature activation+2.80e-01

Pos logit contributions
ver+0.024
hand+0.021
rolled+0.020
 Even+0.020
 chief+0.020
Neg logit contributions
 ey-0.019
 skirts-0.018
 fru-0.018
 skirt-0.016
 makeup-0.015
Token rh
Token ID9529
Feature activation+3.08e+00

Pos logit contributions
ver+0.010
hand+0.009
 chief+0.009
rolled+0.008
 Even+0.008
Neg logit contributions
 ey-0.010
 skirts-0.009
 fru-0.009
 skirt-0.008
 makeup-0.008
Tokenin
Token ID259
Feature activation+1.42e+00

Pos logit contributions
rolled+0.106
hand+0.106
ver+0.103
 Even+0.102
 Together+0.101
Neg logit contributions
 ey-0.095
 fru-0.089
 skirts-0.082
 da-0.080
 jam-0.080
Tokenoc
Token ID420
Feature activation+4.66e+00

Pos logit contributions
ver+0.050
hand+0.046
 department+0.043
rolled+0.043
 chief+0.043
Neg logit contributions
 ey-0.046
 fru-0.045
 skirts-0.042
 skirt-0.040
ems-0.039
Tokeneros
Token ID27498
Feature activation+1.27e+00

Pos logit contributions
ver+0.188
 Even+0.159
case+0.153
rolled+0.151
 Together+0.150
Neg logit contributions
 ey-0.149
 fru-0.137
 ol-0.124
 da-0.117
 mel-0.114
Token thought
Token ID1807
Feature activation+1.78e-01

Pos logit contributions
ver+0.053
hand+0.050
rolled+0.047
 chief+0.047
 department+0.047
Neg logit contributions
 ey-0.032
 fru-0.032
 skirts-0.031
 skirt-0.028
ems-0.027
Token for
Token ID329
Feature activation+6.13e-01

Pos logit contributions
ver+0.005
hand+0.005
 chief+0.005
rolled+0.005
 happily+0.004
Neg logit contributions
 ey-0.007
 skirts-0.007
 fru-0.007
 skirt-0.006
ems-0.006
Token a
Token ID257
Feature activation-1.10e-02

Pos logit contributions
ver+0.017
hand+0.015
 chief+0.015
rolled+0.014
 Even+0.014
Neg logit contributions
 ey-0.025
 skirts-0.025
 fru-0.025
 skirt-0.022
 makeup-0.022
Token moment
Token ID2589
Feature activation-6.65e-02

Pos logit contributions
 ey+0.000
 skirts+0.000
 fru+0.000
 skirt+0.000
ems+0.000
Neg logit contributions
ver-0.000
hand-0.000
 chief-0.000
 happily-0.000
 department-0.000
Token that
Token ID326
Feature activation+1.08e+00

Pos logit contributions
ver+0.003
hand+0.003
 chief+0.003
rolled+0.003
 department+0.003
Neg logit contributions
 ey-0.003
 skirts-0.003
 fru-0.003
 skirt-0.003
 makeup-0.003
Token boss
Token ID6478
Feature activation-9.85e-01

Pos logit contributions
ver+0.039
hand+0.037
 chief+0.035
rolled+0.035
 department+0.034
Neg logit contributions
 ey-0.034
 skirts-0.034
 fru-0.034
 skirt-0.030
 makeup-0.029
Tokeny
Token ID88
Feature activation-8.84e-02

Pos logit contributions
 ey+0.034
 skirts+0.033
 fru+0.032
ems+0.030
 skirt+0.030
Neg logit contributions
ver-0.032
hand-0.031
 chief-0.030
 department-0.028
rolled-0.028
Token rh
Token ID9529
Feature activation+2.86e+00

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.003
ems+0.003
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.003
rolled-0.003
 Even-0.003
Tokenin
Token ID259
Feature activation+1.69e+00

Pos logit contributions
hand+0.094
 Together+0.092
 Even+0.091
ver+0.090
rolled+0.090
Neg logit contributions
 ey-0.091
 fru-0.085
 skirts-0.083
eking-0.080
ems-0.077
Tokenoc
Token ID420
Feature activation+4.64e+00

Pos logit contributions
ver+0.050
hand+0.046
rolled+0.046
 Even+0.043
 chief+0.043
Neg logit contributions
 ey-0.059
 fru-0.058
 skirts-0.057
ems-0.055
 skirt-0.052
Tokeneros
Token ID27498
Feature activation+1.22e+00

Pos logit contributions
ver+0.180
case+0.164
 Even+0.155
 tow+0.151
 sadly+0.149
Neg logit contributions
 ey-0.132
 fru-0.128
 ol-0.119
ution-0.119
 brace-0.115
Token.
Token ID13
Feature activation-2.89e-01

Pos logit contributions
ver+0.040
hand+0.038
rolled+0.036
 Even+0.036
 chief+0.036
Neg logit contributions
 skirts-0.040
 ey-0.039
 fru-0.038
ems-0.036
 skirt-0.036
Token<|endoftext|>
Token ID50256
Feature activation+6.14e-01

Pos logit contributions
 ey+0.010
 fru+0.009
 skirts+0.008
---+0.008
 ol+0.008
Neg logit contributions
ver-0.009
 chief-0.009
hand-0.009
 department-0.009
 quickly-0.008
TokenD
Token ID35
Feature activation+4.39e-01

Pos logit contributions
ver+0.023
 chief+0.021
hand+0.021
 department+0.020
 sadly+0.020
Neg logit contributions
 ey-0.019
 skirts-0.017
 fru-0.017
 skirt-0.016
----0.016
Tokenee
Token ID1453
Feature activation+8.44e-01

Pos logit contributions
ver+0.014
 chief+0.013
hand+0.013
 department+0.013
 sadly+0.012
Neg logit contributions
 ey-0.016
 skirts-0.015
 fru-0.014
 skirt-0.014
----0.013
Token they
Token ID484
Feature activation+7.54e-01

Pos logit contributions
 skirts+0.012
 ey+0.012
 skirt+0.011
 fru+0.011
 doing+0.011
Neg logit contributions
ver-0.018
 department-0.015
ittle-0.015
 chief-0.015
itt-0.015
Token saw
Token ID2497
Feature activation-3.21e-01

Pos logit contributions
ver+0.029
hand+0.027
 chief+0.027
 department+0.026
 Even+0.026
Neg logit contributions
 ey-0.022
 skirts-0.022
 fru-0.021
 skirt-0.019
ems-0.018
Token a
Token ID257
Feature activation+6.77e-01

Pos logit contributions
 skirts+0.011
 ey+0.010
 fru+0.010
 makeup+0.010
 da+0.010
Neg logit contributions
ver-0.012
 chief-0.010
hand-0.010
 department-0.010
rolled-0.010
Token rh
Token ID9529
Feature activation+3.06e+00

Pos logit contributions
ver+0.028
hand+0.025
rolled+0.024
 chief+0.024
 Even+0.024
Neg logit contributions
 ey-0.020
 skirts-0.019
 fru-0.019
 skirt-0.018
 makeup-0.017
Tokenin
Token ID259
Feature activation+1.42e+00

Pos logit contributions
 Even+0.110
ver+0.109
hand+0.108
 Hours+0.106
rolled+0.105
Neg logit contributions
 ey-0.081
P-0.079
 da-0.077
 skirts-0.075
 fru-0.073
Tokenoc
Token ID420
Feature activation+4.62e+00

Pos logit contributions
ver+0.050
uttered+0.041
hand+0.041
rolled+0.040
 department+0.040
Neg logit contributions
 ey-0.048
 fru-0.045
 da-0.044
 ol-0.043
 skirts-0.042
Tokeneros
Token ID27498
Feature activation+1.14e+00

Pos logit contributions
ver+0.206
 Even+0.174
case+0.166
 Together+0.165
 Hours+0.163
Neg logit contributions
 ey-0.120
 fru-0.105
 ol-0.099
 da-0.096
 jewelry-0.095
Token in
Token ID287
Feature activation-3.21e-01

Pos logit contributions
ver+0.045
 Even+0.039
hand+0.039
 chief+0.039
 department+0.039
Neg logit contributions
 ey-0.032
 skirts-0.032
 skirt-0.029
 fru-0.028
 makeup-0.028
Token the
Token ID262
Feature activation-7.58e-01

Pos logit contributions
 ey+0.011
 skirts+0.011
 fru+0.010
 skirt+0.010
 makeup+0.009
Neg logit contributions
ver-0.012
hand-0.010
 chief-0.010
 department-0.010
rolled-0.009
Token field
Token ID2214
Feature activation+4.24e-02

Pos logit contributions
 ey+0.019
 skirts+0.017
 fru+0.017
 skirt+0.016
 prett+0.015
Neg logit contributions
ver-0.036
uttered-0.030
hand-0.030
rolled-0.030
 chief-0.030
Token.
Token ID13
Feature activation-2.61e-01

Pos logit contributions
ver+0.002
hand+0.001
 chief+0.001
 department+0.001
 Even+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
 makeup-0.001
Token saw
Token ID2497
Feature activation-2.82e-01

Pos logit contributions
 ey+0.015
 skirts+0.015
 fru+0.014
 skirt+0.013
ems+0.012
Neg logit contributions
ver-0.015
hand-0.013
 chief-0.013
 department-0.012
rolled-0.012
Token a
Token ID257
Feature activation+6.49e-01

Pos logit contributions
 skirts+0.011
 ey+0.011
 fru+0.011
 skirt+0.010
 makeup+0.010
Neg logit contributions
ver-0.008
hand-0.007
 chief-0.007
rolled-0.007
 department-0.007
Token big
Token ID1263
Feature activation+7.00e-01

Pos logit contributions
ver+0.023
hand+0.021
 chief+0.021
 happily+0.020
 department+0.020
Neg logit contributions
 ey-0.021
 skirts-0.021
 fru-0.020
ems-0.018
 skirt-0.018
Token rh
Token ID9529
Feature activation+2.83e+00

Pos logit contributions
ver+0.020
 chief+0.020
 happily+0.019
hand+0.019
 quickly+0.019
Neg logit contributions
 skirts-0.025
 ey-0.024
 fru-0.024
ems-0.023
----0.021
Tokenin
Token ID259
Feature activation+1.43e+00

Pos logit contributions
ver+0.087
hand+0.085
rolled+0.083
 Even+0.080
 department+0.077
Neg logit contributions
 ey-0.102
 skirts-0.097
 fru-0.093
 skirt-0.092
 da-0.089
Tokenoc
Token ID420
Feature activation+4.61e+00

Pos logit contributions
ver+0.045
hand+0.039
rolled+0.037
uttered+0.036
 chief+0.035
Neg logit contributions
 ey-0.055
 fru-0.052
 skirts-0.050
 da-0.048
 skirt-0.048
Tokeneros
Token ID27498
Feature activation+1.26e+00

Pos logit contributions
ver+0.182
 Even+0.150
rolled+0.144
hand+0.144
 Together+0.143
Neg logit contributions
 ey-0.149
 fru-0.136
 da-0.124
 ol-0.123
 jewelry-0.116
Token at
Token ID379
Feature activation+1.30e-01

Pos logit contributions
ver+0.045
hand+0.040
 chief+0.039
 Even+0.038
rolled+0.038
Neg logit contributions
 ey-0.043
 skirts-0.041
 fru-0.039
 skirt-0.038
 makeup-0.036
Token the
Token ID262
Feature activation-1.55e-02

Pos logit contributions
ver+0.004
hand+0.004
 chief+0.004
 happily+0.003
rolled+0.003
Neg logit contributions
 ey-0.005
 skirts-0.005
 fru-0.005
 skirt-0.004
ems-0.004
Token park
Token ID3952
Feature activation-4.98e-01

Pos logit contributions
 ey+0.000
 skirts+0.000
 fru+0.000
 prett+0.000
 skirt+0.000
Neg logit contributions
ver-0.001
uttered-0.001
hand-0.001
 sadly-0.001
rolled-0.001
Token.
Token ID13
Feature activation-9.57e-02

Pos logit contributions
 ey+0.016
 skirts+0.016
 fru+0.015
 skirt+0.014
 makeup+0.014
Neg logit contributions
ver-0.018
hand-0.016
 chief-0.016
 department-0.015
rolled-0.015
Token a
Token ID257
Feature activation+4.74e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.002
 makeup+0.002
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.002
rolled-0.002
 department-0.002
Token very
Token ID845
Feature activation-2.56e-01

Pos logit contributions
ver+0.021
hand+0.020
rolled+0.020
uttered+0.019
 chief+0.018
Neg logit contributions
 fru-0.012
 skirts-0.011
 ey-0.011
 skirt-0.011
 prett-0.010
Token clever
Token ID14169
Feature activation+2.97e-01

Pos logit contributions
 fru+0.007
 ey+0.007
 skirts+0.007
 skirt+0.006
 makeup+0.006
Neg logit contributions
ver-0.010
hand-0.010
rolled-0.009
 chief-0.009
 department-0.009
Token rh
Token ID9529
Feature activation+2.77e+00

Pos logit contributions
ver+0.012
rolled+0.011
hand+0.011
uttered+0.010
alled+0.010
Neg logit contributions
 skirts-0.008
 skirt-0.008
 fru-0.008
 ey-0.008
 sunglasses-0.007
Tokenin
Token ID259
Feature activation+1.11e+00

Pos logit contributions
rolled+0.101
 Even+0.096
hand+0.096
 Together+0.092
ver+0.089
Neg logit contributions
 fru-0.076
 skirts-0.075
 ey-0.074
ems-0.072
P-0.071
Tokenoc
Token ID420
Feature activation+4.60e+00

Pos logit contributions
ver+0.034
rolled+0.032
hand+0.032
uttered+0.031
 Even+0.029
Neg logit contributions
 fru-0.039
 skirts-0.038
 ey-0.037
ems-0.036
 skirt-0.035
Tokeneros
Token ID27498
Feature activation+9.91e-01

Pos logit contributions
ver+0.167
 Even+0.157
rolled+0.149
case+0.146
 sadly+0.145
Neg logit contributions
 fru-0.129
 ey-0.128
 ol-0.120
ution-0.112
 brace-0.112
Token."
Token ID526
Feature activation+7.65e-01

Pos logit contributions
ver+0.037
rolled+0.037
hand+0.036
 Even+0.035
 chief+0.034
Neg logit contributions
 skirts-0.027
 fru-0.026
ems-0.024
 skirt-0.024
 ey-0.023
Token<|endoftext|>
Token ID50256
Feature activation+9.26e-01

Pos logit contributions
ver+0.026
 chief+0.024
hand+0.023
rolled+0.022
 department+0.022
Neg logit contributions
 ey-0.026
 skirts-0.026
 fru-0.025
 skirt-0.023
 ol-0.023
TokenOnce
Token ID7454
Feature activation-8.59e-01

Pos logit contributions
ver+0.029
hand+0.027
 chief+0.027
 department+0.025
rolled+0.025
Neg logit contributions
 ey-0.034
 skirts-0.033
 fru-0.032
 skirt-0.030
 makeup-0.029
Token upon
Token ID2402
Feature activation-9.71e-01

Pos logit contributions
 ey+0.021
 skirts+0.021
 fru+0.020
 skirt+0.018
ems+0.017
Neg logit contributions
ver-0.037
hand-0.035
 chief-0.035
rolled-0.033
 happily-0.033
Token Unicorn
Token ID39481
Feature activation+8.35e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.001
 skirt+0.001
 makeup+0.001
Neg logit contributions
ver-0.001
hand-0.001
rolled-0.001
 chief-0.001
uttered-0.001
Token!"
Token ID2474
Feature activation-2.78e-02

Pos logit contributions
ver+0.030
hand+0.029
 chief+0.028
rolled+0.028
 Even+0.028
Neg logit contributions
 skirts-0.025
 fru-0.024
 ey-0.023
ems-0.023
 skirt-0.023
Token The
Token ID383
Feature activation+6.33e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.001
 skirt+0.001
 makeup+0.001
Neg logit contributions
ver-0.001
hand-0.001
 chief-0.001
 department-0.001
rolled-0.001
Token rh
Token ID9529
Feature activation+2.98e+00

Pos logit contributions
ver+0.025
hand+0.023
 chief+0.022
rolled+0.021
 Even+0.021
Neg logit contributions
 ey-0.019
 skirts-0.019
 fru-0.018
 skirt-0.017
ems-0.016
Tokenin
Token ID259
Feature activation+1.59e+00

Pos logit contributions
hand+0.097
ver+0.097
rolled+0.093
 department+0.091
 Even+0.091
Neg logit contributions
 ey-0.091
 fru-0.089
 skirts-0.081
 da-0.080
 ol-0.078
Tokenoc
Token ID420
Feature activation+4.60e+00

Pos logit contributions
ver+0.053
hand+0.047
 department+0.045
uttered+0.044
 chief+0.043
Neg logit contributions
 fru-0.054
 ey-0.051
 skirts-0.048
 scar-0.047
 da-0.047
Tokeneros
Token ID27498
Feature activation+1.30e+00

Pos logit contributions
ver+0.182
case+0.152
 Even+0.149
 tow+0.142
rolled+0.141
Neg logit contributions
 ey-0.151
 fru-0.143
 ol-0.128
 da-0.125
 jewelry-0.121
Token said
Token ID531
Feature activation+8.45e-01

Pos logit contributions
ver+0.064
hand+0.062
rolled+0.060
 tow+0.059
 department+0.059
Neg logit contributions
 fru-0.022
 skirts-0.019
 ey-0.018
 da-0.017
 skirt-0.016
Token,
Token ID11
Feature activation+5.60e-02

Pos logit contributions
ver+0.031
hand+0.030
 Even+0.029
 department+0.029
 chief+0.029
Neg logit contributions
 fru-0.023
 skirts-0.021
 skirt-0.020
 makeup-0.019
 brace-0.018
Token feeling
Token ID4203
Feature activation-6.79e-01

Pos logit contributions
ver+0.002
hand+0.002
 chief+0.002
 department+0.002
rolled+0.002
Neg logit contributions
 ey-0.002
 fru-0.002
 skirts-0.002
 skirt-0.001
 makeup-0.001
Token much
Token ID881
Feature activation+1.35e+00

Pos logit contributions
 fru+0.023
 skirts+0.022
 ey+0.021
 skirt+0.020
 makeup+0.019
Neg logit contributions
ver-0.024
hand-0.023
 department-0.022
rolled-0.022
 chief-0.022
Token It
Token ID632
Feature activation+6.62e-01

Pos logit contributions
 ey+0.005
 skirts+0.004
 fru+0.004
 skirt+0.004
 makeup+0.004
Neg logit contributions
ver-0.004
hand-0.003
 chief-0.003
 department-0.003
rolled-0.003
Token is
Token ID318
Feature activation-7.98e-02

Pos logit contributions
ver+0.026
hand+0.024
 chief+0.023
rolled+0.023
 department+0.022
Neg logit contributions
 ey-0.020
 skirts-0.019
 fru-0.019
 skirt-0.017
ems-0.016
Token a
Token ID257
Feature activation+2.82e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.003
ems+0.003
Neg logit contributions
ver-0.002
hand-0.002
 chief-0.002
 happily-0.002
 department-0.002
Token rh
Token ID9529
Feature activation+2.51e+00

Pos logit contributions
ver+0.010
hand+0.009
 chief+0.009
rolled+0.009
 Even+0.009
Neg logit contributions
 ey-0.009
 skirts-0.009
 fru-0.009
 skirt-0.008
 makeup-0.008
Tokenin
Token ID259
Feature activation+4.97e-01

Pos logit contributions
ver+0.080
rolled+0.079
hand+0.078
 Even+0.076
 Together+0.072
Neg logit contributions
 ey-0.088
 skirts-0.083
 fru-0.081
 skirt-0.077
 da-0.076
Tokenoc
Token ID420
Feature activation+4.59e+00

Pos logit contributions
ver+0.014
hand+0.013
rolled+0.012
 chief+0.012
 Even+0.012
Neg logit contributions
 ey-0.020
 fru-0.019
 skirts-0.019
 skirt-0.018
 da-0.017
Tokeneros
Token ID27498
Feature activation+4.75e-01

Pos logit contributions
ver+0.177
 Even+0.151
rolled+0.143
 happily+0.143
 sadly+0.142
Neg logit contributions
 ey-0.150
 fru-0.140
 ol-0.122
 da-0.119
 brace-0.117
Token.
Token ID13
Feature activation-2.03e-01

Pos logit contributions
ver+0.018
hand+0.017
rolled+0.016
 chief+0.016
 Even+0.016
Neg logit contributions
 ey-0.014
 skirts-0.014
 fru-0.013
 skirt-0.013
 makeup-0.012
Token It
Token ID632
Feature activation+7.65e-01

Pos logit contributions
 ey+0.008
 skirts+0.007
 fru+0.007
 skirt+0.007
 makeup+0.006
Neg logit contributions
ver-0.006
hand-0.006
 chief-0.006
 department-0.005
rolled-0.005
Token is
Token ID318
Feature activation-1.68e-02

Pos logit contributions
ver+0.031
hand+0.028
 chief+0.027
rolled+0.027
 department+0.026
Neg logit contributions
 ey-0.023
 skirts-0.022
 fru-0.022
 skirt-0.019
ems-0.018
Token bright
Token ID6016
Feature activation-1.99e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.001
 skirt+0.001
ems+0.001
Neg logit contributions
ver-0.001
hand-0.000
 chief-0.000
 happily-0.000
 sadly-0.000
Token she
Token ID673
Feature activation+5.98e-01

Pos logit contributions
 ey+0.018
 skirts+0.017
 fru+0.017
 skirt+0.015
ems+0.015
Neg logit contributions
ver-0.021
hand-0.019
 chief-0.019
 happily-0.018
 department-0.018
Token could
Token ID714
Feature activation+1.19e+00

Pos logit contributions
hand+0.024
rolled+0.023
 chief+0.023
ver+0.022
 attendant+0.022
Neg logit contributions
 fru-0.016
 skirts-0.014
 ey-0.014
 skirt-0.013
 makeup-0.013
Token request
Token ID2581
Feature activation-5.35e-02

Pos logit contributions
ver+0.047
hand+0.046
 chief+0.045
 department+0.044
uttered+0.044
Neg logit contributions
 ey-0.029
 makeup-0.029
 fru-0.028
 skirts-0.028
 wear-0.026
Token some
Token ID617
Feature activation+7.11e-01

Pos logit contributions
 skirts+0.002
 fru+0.002
 ey+0.002
 makeup+0.002
 ol+0.002
Neg logit contributions
ver-0.002
hand-0.002
 chief-0.002
rolled-0.002
 department-0.002
Token av
Token ID1196
Feature activation+2.57e+00

Pos logit contributions
ver+0.026
hand+0.024
 chief+0.023
 happily+0.023
 Even+0.022
Neg logit contributions
 ey-0.023
 skirts-0.022
 fru-0.022
 skirt-0.020
ems-0.019
Tokenoc
Token ID420
Feature activation+4.57e+00

Pos logit contributions
ver+0.061
hand+0.055
 chief+0.053
rolled+0.050
 department+0.050
Neg logit contributions
 ey-0.114
 skirts-0.111
 fru-0.110
 skirt-0.102
ems-0.100
Tokenados
Token ID22484
Feature activation+3.05e-01

Pos logit contributions
ver+0.244
hand+0.224
 Even+0.220
 tow+0.218
rolled+0.216
Neg logit contributions
 ey-0.069
 fru-0.066
 ol-0.058
 skirts-0.055
 makeup-0.048
Token from
Token ID422
Feature activation+1.12e+00

Pos logit contributions
ver+0.009
hand+0.008
 chief+0.008
 happily+0.007
 department+0.007
Neg logit contributions
 ey-0.013
 skirts-0.012
 fru-0.012
 skirt-0.011
ems-0.011
Token the
Token ID262
Feature activation-1.67e-01

Pos logit contributions
ver+0.043
hand+0.040
 chief+0.039
rolled+0.037
 department+0.037
Neg logit contributions
 ey-0.034
 skirts-0.034
 fru-0.032
 skirt-0.030
 makeup-0.028
Token store
Token ID3650
Feature activation-4.41e-02

Pos logit contributions
 ey+0.007
 skirts+0.007
 fru+0.006
ems+0.006
 skirt+0.006
Neg logit contributions
 chief-0.005
ver-0.004
hand-0.004
 mayor-0.004
 department-0.004
Token.
Token ID13
Feature activation-2.80e-03

Pos logit contributions
 skirts+0.001
 ey+0.001
 fru+0.001
 skirt+0.001
 makeup+0.001
Neg logit contributions
ver-0.002
hand-0.001
 chief-0.001
rolled-0.001
 Even-0.001
Token a
Token ID257
Feature activation-7.21e-01

Pos logit contributions
 ey+0.023
 skirts+0.023
 fru+0.022
 skirt+0.020
ems+0.020
Neg logit contributions
ver-0.018
hand-0.017
 chief-0.016
rolled-0.015
 department-0.015
Token shiny
Token ID22441
Feature activation-7.90e-01

Pos logit contributions
 skirts+0.023
 ey+0.023
 fru+0.021
ems+0.021
---+0.019
Neg logit contributions
ver-0.024
 happily-0.023
 quickly-0.023
 sadly-0.023
 tow-0.022
Token thing
Token ID1517
Feature activation+6.55e-03

Pos logit contributions
 skirts+0.022
 ey+0.022
 fru+0.021
ems+0.021
---+0.020
Neg logit contributions
 happily-0.028
 sadly-0.027
ver-0.027
rolled-0.027
 quickly-0.026
Token in
Token ID287
Feature activation-5.74e-01

Pos logit contributions
ver+0.000
hand+0.000
 chief+0.000
 happily+0.000
rolled+0.000
Neg logit contributions
 ey-0.000
 skirts-0.000
 fru-0.000
 skirt-0.000
ems-0.000
Token its
Token ID663
Feature activation-3.79e-01

Pos logit contributions
 ey+0.021
 skirts+0.020
 fru+0.020
 skirt+0.018
ems+0.018
Neg logit contributions
ver-0.019
hand-0.017
 chief-0.017
 happily-0.016
rolled-0.016
Token be
Token ID307
Feature activation-3.70e+00

Pos logit contributions
 skirts+0.013
 ey+0.013
 fru+0.012
ems+0.012
 makeup+0.011
Neg logit contributions
ver-0.012
hand-0.011
 happily-0.011
rolled-0.011
 safely-0.011
Tokenak
Token ID461
Feature activation-1.89e+00

Pos logit contributions
 ey+0.107
 fru+0.102
 skirts+0.102
 skirt+0.091
ems+0.086
Neg logit contributions
ver-0.147
hand-0.132
 happily-0.132
 chief-0.129
 safely-0.128
Token.
Token ID13
Feature activation+2.59e-03

Pos logit contributions
 ey+0.061
 skirts+0.061
 fru+0.057
 skirt+0.054
ems+0.051
Neg logit contributions
ver-0.068
hand-0.062
 chief-0.062
 department-0.059
 Even-0.059
Token It
Token ID632
Feature activation+7.26e-01

Pos logit contributions
ver+0.000
hand+0.000
 chief+0.000
 Even+0.000
rolled+0.000
Neg logit contributions
 ey-0.000
 skirts-0.000
 fru-0.000
 skirt-0.000
ems-0.000
Token looked
Token ID3114
Feature activation-2.50e-01

Pos logit contributions
ver+0.024
hand+0.022
 chief+0.021
 department+0.020
rolled+0.020
Neg logit contributions
 ey-0.026
 skirts-0.025
 fru-0.025
 skirt-0.023
ems-0.022
Token like
Token ID588
Feature activation-6.02e-01

Pos logit contributions
 ey+0.009
 skirts+0.009
 fru+0.008
ems+0.008
 skirt+0.008
Neg logit contributions
 happily-0.007
ver-0.007
 sadly-0.007
 quickly-0.007
 chief-0.007
Token piece
Token ID3704
Feature activation+1.14e+00

Pos logit contributions
 ey+0.012
 skirts+0.011
 fru+0.011
ems+0.010
---+0.009
Neg logit contributions
ver-0.015
 chief-0.014
hand-0.014
 happily-0.014
 sadly-0.014
Token of
Token ID286
Feature activation+1.61e-01

Pos logit contributions
ver+0.024
hand+0.021
 chief+0.020
rolled+0.019
 department+0.018
Neg logit contributions
 ey-0.054
 skirts-0.054
 fru-0.051
 skirt-0.051
 makeup-0.049
Token meat
Token ID6174
Feature activation+1.06e+00

Pos logit contributions
ver+0.005
 happily+0.005
hand+0.005
 tow+0.005
 quickly+0.005
Neg logit contributions
 ey-0.005
 skirts-0.005
ems-0.004
----0.004
 fru-0.004
Token in
Token ID287
Feature activation-7.35e-01

Pos logit contributions
ver+0.036
hand+0.033
 chief+0.032
 Even+0.031
rolled+0.030
Neg logit contributions
 ey-0.037
 skirts-0.037
 fru-0.035
 skirt-0.033
 makeup-0.032
Token its
Token ID663
Feature activation-2.15e-01

Pos logit contributions
 ey+0.028
 skirts+0.027
 fru+0.027
 skirt+0.025
ems+0.025
Neg logit contributions
ver-0.022
hand-0.021
 chief-0.020
 happily-0.019
 Even-0.019
Token be
Token ID307
Feature activation-3.70e+00

Pos logit contributions
 ey+0.007
 skirts+0.007
 fru+0.007
ems+0.006
 skirt+0.006
Neg logit contributions
ver-0.008
hand-0.007
 chief-0.007
 happily-0.007
 Even-0.007
Tokenak
Token ID461
Feature activation-2.02e+00

Pos logit contributions
 ey+0.123
 fru+0.112
 skirts+0.111
 skirt+0.101
ems+0.098
Neg logit contributions
ver-0.130
 happily-0.122
 safely-0.115
 quickly-0.114
te-0.114
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
 ey+0.070
 skirts+0.069
 fru+0.066
 skirt+0.061
ems+0.059
Neg logit contributions
ver-0.069
hand-0.063
 chief-0.062
 Even-0.059
 department-0.058
Token She
Token ID1375
Feature activation+3.05e-01

Pos logit contributions
 ey+0.004
 skirts+0.004
 fru+0.004
 skirt+0.004
ems+0.003
Neg logit contributions
ver-0.004
hand-0.003
 chief-0.003
rolled-0.003
 Even-0.003
Token was
Token ID373
Feature activation+4.05e-01

Pos logit contributions
ver+0.013
hand+0.013
 chief+0.012
 department+0.012
 attendant+0.012
Neg logit contributions
 skirts-0.008
 fru-0.008
 ey-0.007
 skirt-0.007
 da-0.007
Token very
Token ID845
Feature activation-2.79e-01

Pos logit contributions
ver+0.015
hand+0.015
 department+0.014
 chief+0.014
rolled+0.013
Neg logit contributions
 ey-0.012
 skirts-0.012
 fru-0.012
 skirt-0.011
 makeup-0.010
Token beautiful
Token ID4950
Feature activation-4.28e-01

Pos logit contributions
 ey+0.018
 fru+0.017
 skirts+0.017
 skirt+0.016
 makeup+0.014
Neg logit contributions
ver-0.029
hand-0.027
 chief-0.026
rolled-0.026
 department-0.025
Token white
Token ID2330
Feature activation-5.53e-01

Pos logit contributions
 ey+0.013
 skirts+0.013
 fru+0.012
ems+0.012
---+0.010
Neg logit contributions
ver-0.015
 happily-0.015
hand-0.015
 sadly-0.014
rolled-0.014
Token feather
Token ID17972
Feature activation-4.31e-01

Pos logit contributions
 ey+0.014
 skirts+0.014
 fru+0.013
 skirt+0.011
ems+0.011
Neg logit contributions
ver-0.023
hand-0.022
 chief-0.022
 happily-0.021
rolled-0.021
Token in
Token ID287
Feature activation-4.51e-01

Pos logit contributions
 skirts+0.015
 ey+0.015
 fru+0.014
 skirt+0.014
 makeup+0.013
Neg logit contributions
ver-0.014
hand-0.013
 chief-0.013
 Even-0.013
rolled-0.013
Token its
Token ID663
Feature activation-3.38e-01

Pos logit contributions
 ey+0.015
 skirts+0.015
 fru+0.014
ems+0.013
 skirt+0.013
Neg logit contributions
ver-0.016
hand-0.015
 chief-0.014
 happily-0.014
 Even-0.014
Token be
Token ID307
Feature activation-3.67e+00

Pos logit contributions
 ey+0.011
 skirts+0.011
 fru+0.011
ems+0.010
 skirt+0.010
Neg logit contributions
ver-0.011
hand-0.011
 happily-0.011
 chief-0.010
 Even-0.010
Tokenak
Token ID461
Feature activation-1.95e+00

Pos logit contributions
 ey+0.113
 fru+0.103
 skirts+0.102
 skirt+0.090
ems+0.089
Neg logit contributions
ver-0.141
 happily-0.131
hand-0.129
 safely-0.125
rolled-0.124
Token.
Token ID13
Feature activation-2.22e-01

Pos logit contributions
 skirts+0.063
 ey+0.062
 fru+0.059
 skirt+0.056
 makeup+0.053
Neg logit contributions
ver-0.070
 chief-0.064
hand-0.063
 Even-0.061
rolled-0.060
Token
Token ID198
Feature activation-4.20e-02

Pos logit contributions
 ey+0.009
 skirts+0.009
 fru+0.009
 skirt+0.008
 makeup+0.008
Neg logit contributions
ver-0.006
 chief-0.006
hand-0.006
 department-0.005
rolled-0.005
Token
Token ID198
Feature activation-8.24e-02

Pos logit contributions
 ey+0.002
 skirts+0.001
 fru+0.001
 skirt+0.001
---+0.001
Neg logit contributions
ver-0.001
 chief-0.001
 department-0.001
hand-0.001
 brigade-0.001
TokenThe
Token ID464
Feature activation+1.77e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.002
 makeup+0.002
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.003
 department-0.002
rolled-0.002
Token yellow
Token ID7872
Feature activation-4.44e-01

Pos logit contributions
 ey+0.008
 skirts+0.008
 fru+0.007
ems+0.007
 skirt+0.007
Neg logit contributions
ver-0.008
 chief-0.008
hand-0.008
 happily-0.008
 sadly-0.007
Token corn
Token ID11676
Feature activation-2.19e-01

Pos logit contributions
 ey+0.014
 skirts+0.013
 fru+0.013
 skirt+0.012
 makeup+0.011
Neg logit contributions
ver-0.017
hand-0.016
 chief-0.015
 department-0.015
rolled-0.015
Token cob
Token ID22843
Feature activation+8.65e-01

Pos logit contributions
 ey+0.008
 skirts+0.007
 fru+0.007
 skirt+0.007
ems+0.006
Neg logit contributions
ver-0.007
hand-0.007
 chief-0.007
 Even-0.006
rolled-0.006
Token in
Token ID287
Feature activation-7.60e-01

Pos logit contributions
ver+0.034
hand+0.031
 chief+0.030
 Even+0.030
rolled+0.030
Neg logit contributions
 ey-0.026
 skirts-0.025
 fru-0.025
 skirt-0.022
ems-0.021
Token his
Token ID465
Feature activation-5.12e-01

Pos logit contributions
 ey+0.024
 skirts+0.023
 fru+0.023
 skirt+0.021
 makeup+0.020
Neg logit contributions
ver-0.029
hand-0.026
 chief-0.026
 department-0.025
rolled-0.024
Token be
Token ID307
Feature activation-3.66e+00

Pos logit contributions
 ey+0.018
 skirts+0.018
 fru+0.017
ems+0.016
 skirt+0.016
Neg logit contributions
ver-0.017
hand-0.015
 chief-0.015
 happily-0.015
rolled-0.015
Tokenak
Token ID461
Feature activation-2.03e+00

Pos logit contributions
 ey+0.109
 skirts+0.102
 fru+0.101
 skirt+0.090
ems+0.087
Neg logit contributions
ver-0.142
 happily-0.132
hand-0.130
 safely-0.126
 quickly-0.125
Token!
Token ID0
Feature activation-4.23e-01

Pos logit contributions
 skirts+0.061
 ey+0.060
 fru+0.057
 skirt+0.054
 makeup+0.051
Neg logit contributions
ver-0.077
hand-0.070
 chief-0.070
 Even-0.067
rolled-0.067
Token He
Token ID679
Feature activation+3.02e-01

Pos logit contributions
 ey+0.014
 fru+0.014
 skirts+0.013
 ol+0.012
 makeup+0.012
Neg logit contributions
ver-0.014
hand-0.013
 chief-0.013
 department-0.012
rolled-0.012
Token dropped
Token ID5710
Feature activation+3.98e-01

Pos logit contributions
ver+0.012
hand+0.012
 chief+0.011
 department+0.011
 mayor+0.010
Neg logit contributions
 fru-0.009
 skirts-0.008
 ey-0.008
 skirt-0.007
 da-0.007
Token it
Token ID340
Feature activation-3.88e-01

Pos logit contributions
ver+0.018
hand+0.015
 chief+0.015
rolled+0.015
case+0.015
Neg logit contributions
 ey-0.011
 fru-0.010
 skirts-0.010
 ol-0.009
 jam-0.009
Token bright
Token ID6016
Feature activation-2.43e-01

Pos logit contributions
 ey+0.014
 skirts+0.013
 fru+0.013
 skirt+0.012
 makeup+0.011
Neg logit contributions
ver-0.018
hand-0.017
 chief-0.017
rolled-0.016
 Even-0.016
Token green
Token ID4077
Feature activation-3.61e-01

Pos logit contributions
 skirts+0.007
 ey+0.007
 fru+0.007
ems+0.006
---+0.006
Neg logit contributions
ver-0.009
 happily-0.009
hand-0.008
 sadly-0.008
 chief-0.008
Token olive
Token ID19450
Feature activation-8.85e-02

Pos logit contributions
 ey+0.010
 skirts+0.010
 fru+0.009
 skirt+0.008
ems+0.008
Neg logit contributions
ver-0.015
hand-0.014
 chief-0.013
 happily-0.013
rolled-0.013
Token in
Token ID287
Feature activation-4.39e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.003
 makeup+0.003
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.003
rolled-0.003
 Even-0.003
Token its
Token ID663
Feature activation-2.56e-01

Pos logit contributions
 ey+0.015
 skirts+0.015
 fru+0.014
ems+0.013
 skirt+0.013
Neg logit contributions
ver-0.014
hand-0.014
 happily-0.013
 chief-0.013
 Even-0.013
Token be
Token ID307
Feature activation-3.63e+00

Pos logit contributions
 skirts+0.008
 ey+0.008
 fru+0.008
ems+0.007
 skirt+0.007
Neg logit contributions
ver-0.009
hand-0.008
 happily-0.008
 chief-0.008
 Even-0.008
Tokenak
Token ID461
Feature activation-1.92e+00

Pos logit contributions
 ey+0.109
 fru+0.101
 skirts+0.101
 skirt+0.089
ems+0.087
Neg logit contributions
ver-0.141
 happily-0.129
hand-0.127
 safely-0.124
 chief-0.123
Token.
Token ID13
Feature activation-9.04e-02

Pos logit contributions
 skirts+0.063
 ey+0.062
 fru+0.060
 skirt+0.056
 makeup+0.054
Neg logit contributions
ver-0.067
hand-0.061
 chief-0.061
 Even-0.059
rolled-0.058
Token It
Token ID632
Feature activation+8.45e-01

Pos logit contributions
 ey+0.003
 fru+0.003
 skirts+0.003
 skirt+0.003
 makeup+0.003
Neg logit contributions
ver-0.003
 chief-0.003
hand-0.003
 department-0.003
te-0.002
Token was
Token ID373
Feature activation+1.94e-01

Pos logit contributions
ver+0.030
hand+0.027
 chief+0.026
rolled+0.025
 department+0.025
Neg logit contributions
 ey-0.028
 fru-0.028
 skirts-0.027
 skirt-0.025
ems-0.024
Token a
Token ID257
Feature activation+4.17e-01

Pos logit contributions
ver+0.006
hand+0.006
 chief+0.006
rolled+0.005
 happily+0.005
Neg logit contributions
 ey-0.007
 skirts-0.007
 fru-0.007
 skirt-0.006
ems-0.006
Token had
Token ID550
Feature activation-7.09e-01

Pos logit contributions
ver+0.020
hand+0.019
 chief+0.018
rolled+0.017
 Even+0.017
Neg logit contributions
 ey-0.025
 skirts-0.025
 fru-0.025
 skirt-0.023
ems-0.022
Token Pip
Token ID25149
Feature activation-9.43e-01

Pos logit contributions
 ey+0.026
 skirts+0.026
 fru+0.025
 skirt+0.023
ems+0.022
Neg logit contributions
ver-0.023
hand-0.021
 chief-0.020
rolled-0.019
 happily-0.019
Tokeno
Token ID78
Feature activation-1.29e+00

Pos logit contributions
 ey+0.037
 skirts+0.037
 fru+0.036
 skirt+0.033
ems+0.032
Neg logit contributions
ver-0.027
hand-0.025
 chief-0.024
rolled-0.023
 Even-0.023
Token in
Token ID287
Feature activation-8.82e-01

Pos logit contributions
 skirts+0.043
 ey+0.041
 fru+0.040
 skirt+0.038
ems+0.037
Neg logit contributions
ver-0.045
hand-0.041
 chief-0.041
 Even-0.039
 department-0.039
Token its
Token ID663
Feature activation-7.36e-01

Pos logit contributions
 ey+0.032
 skirts+0.031
 fru+0.031
 skirt+0.028
ems+0.028
Neg logit contributions
ver-0.028
hand-0.026
 chief-0.025
 happily-0.025
 Even-0.024
Token be
Token ID307
Feature activation-3.60e+00

Pos logit contributions
 skirts+0.027
 ey+0.027
ems+0.026
 fru+0.026
alsa+0.024
Neg logit contributions
 happily-0.021
 sadly-0.020
 tow-0.020
rolled-0.020
 safely-0.019
Tokenak
Token ID461
Feature activation-1.88e+00

Pos logit contributions
 ey+0.111
 skirts+0.104
 fru+0.103
 skirt+0.093
ems+0.090
Neg logit contributions
ver-0.136
 happily-0.125
hand-0.122
rolled-0.120
 safely-0.119
Token.
Token ID13
Feature activation-1.22e-01

Pos logit contributions
 skirts+0.062
 ey+0.061
 fru+0.057
 skirt+0.056
 makeup+0.053
Neg logit contributions
ver-0.068
hand-0.061
 chief-0.060
 Even-0.058
 department-0.057
Token It
Token ID632
Feature activation+7.28e-01

Pos logit contributions
 ey+0.005
 skirts+0.005
 fru+0.005
 skirt+0.005
ems+0.005
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.003
 Even-0.003
 happily-0.002
Token was
Token ID373
Feature activation+7.02e-02

Pos logit contributions
ver+0.024
hand+0.022
 chief+0.021
rolled+0.020
 department+0.020
Neg logit contributions
 ey-0.026
 skirts-0.025
 fru-0.025
 skirt-0.023
ems-0.022
Token flying
Token ID7348
Feature activation+6.07e-02

Pos logit contributions
ver+0.002
 happily+0.002
 chief+0.002
 sadly+0.002
hand+0.002
Neg logit contributions
 ey-0.003
 skirts-0.003
 fru-0.003
 skirt-0.003
ems-0.003
Token red
Token ID2266
Feature activation-5.32e-01

Pos logit contributions
 ey+0.044
 skirts+0.039
 fru+0.036
ems+0.035
 skirt+0.035
Neg logit contributions
ver-0.045
 happily-0.042
 quickly-0.042
 sadly-0.040
 Even-0.040
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
 skirts+0.017
 ey+0.016
 fru+0.015
 skirt+0.015
 makeup+0.014
Neg logit contributions
ver-0.021
rolled-0.019
hand-0.019
 chief-0.019
 brigade-0.017
Token had
Token ID550
Feature activation-7.26e-01

Pos logit contributions
 ey+0.038
 skirts+0.035
 fru+0.033
 skirt+0.032
ems+0.031
Neg logit contributions
ver-0.038
 happily-0.034
 chief-0.033
hand-0.033
 quickly-0.033
Token a
Token ID257
Feature activation-6.92e-01

Pos logit contributions
 ey+0.028
 skirts+0.027
 fru+0.027
 skirt+0.025
ems+0.024
Neg logit contributions
ver-0.022
hand-0.020
 chief-0.019
rolled-0.018
 happily-0.018
Token yellow
Token ID7872
Feature activation-8.49e-01

Pos logit contributions
 ey+0.020
 skirts+0.019
 fru+0.018
ems+0.017
 skirt+0.016
Neg logit contributions
ver-0.027
 happily-0.025
hand-0.025
 chief-0.025
 Even-0.025
Token be
Token ID307
Feature activation-3.59e+00

Pos logit contributions
 ey+0.024
 skirts+0.023
 fru+0.022
ems+0.020
 skirt+0.019
Neg logit contributions
ver-0.032
hand-0.031
 happily-0.031
 Even-0.030
rolled-0.030
Tokenak
Token ID461
Feature activation-1.61e+00

Pos logit contributions
 ey+0.108
 fru+0.099
 skirts+0.098
 skirt+0.088
ems+0.084
Neg logit contributions
ver-0.142
hand-0.129
 happily-0.127
 chief-0.126
rolled-0.123
Token.
Token ID13
Feature activation-3.50e-01

Pos logit contributions
 skirts+0.053
 ey+0.052
 fru+0.050
 skirt+0.047
 makeup+0.045
Neg logit contributions
ver-0.057
hand-0.052
 chief-0.051
 Even-0.050
rolled-0.049
Token He
Token ID679
Feature activation+5.41e-02

Pos logit contributions
 ey+0.014
 skirts+0.014
 fru+0.014
eking+0.013
 skirt+0.013
Neg logit contributions
ver-0.009
 Even-0.009
 happily-0.009
hand-0.008
 Together-0.008
Token could
Token ID714
Feature activation-1.15e-01

Pos logit contributions
ver+0.002
hand+0.002
 chief+0.002
 department+0.002
rolled+0.002
Neg logit contributions
 skirts-0.001
 fru-0.001
 ey-0.001
 skirt-0.001
 da-0.001
Token talk
Token ID1561
Feature activation+8.28e-01

Pos logit contributions
 ey+0.004
 skirts+0.004
 fru+0.003
 skirt+0.003
 makeup+0.003
Neg logit contributions
ver-0.004
hand-0.004
 chief-0.004
 department-0.004
rolled-0.004
Token had
Token ID550
Feature activation-7.01e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.002
ems+0.002
Neg logit contributions
ver-0.002
hand-0.002
 chief-0.002
 happily-0.002
 sadly-0.002
Token a
Token ID257
Feature activation-8.10e-01

Pos logit contributions
 ey+0.029
 skirts+0.028
 fru+0.028
 skirt+0.026
ems+0.025
Neg logit contributions
ver-0.019
hand-0.017
 chief-0.017
 happily-0.016
rolled-0.016
Token feather
Token ID17972
Feature activation-4.73e-01

Pos logit contributions
 ey+0.025
 skirts+0.024
 fru+0.023
ems+0.021
 skirt+0.020
Neg logit contributions
ver-0.030
hand-0.028
 chief-0.028
 happily-0.027
 sadly-0.027
Token in
Token ID287
Feature activation-8.35e-01

Pos logit contributions
 ey+0.018
 skirts+0.017
 fru+0.017
 skirt+0.016
ems+0.015
Neg logit contributions
ver-0.015
hand-0.014
 chief-0.013
 Even-0.013
rolled-0.013
Token its
Token ID663
Feature activation-5.24e-01

Pos logit contributions
 ey+0.030
 skirts+0.029
 fru+0.029
 skirt+0.026
ems+0.026
Neg logit contributions
ver-0.027
hand-0.025
 chief-0.024
 happily-0.024
 Even-0.023
Token be
Token ID307
Feature activation-3.56e+00

Pos logit contributions
 skirts+0.019
 ey+0.019
 fru+0.018
ems+0.017
---+0.016
Neg logit contributions
 happily-0.015
ver-0.015
 sadly-0.014
 Even-0.014
 safely-0.014
Tokenak
Token ID461
Feature activation-1.86e+00

Pos logit contributions
 ey+0.117
 fru+0.108
 skirts+0.105
ems+0.094
 skirt+0.094
Neg logit contributions
ver-0.125
 happily-0.119
 safely-0.112
rolled-0.110
 quickly-0.110
Token.
Token ID13
Feature activation-1.84e-01

Pos logit contributions
 skirts+0.061
 ey+0.060
 fru+0.057
 skirt+0.055
 makeup+0.052
Neg logit contributions
ver-0.066
hand-0.060
 chief-0.060
 Even-0.056
rolled-0.056
Token It
Token ID632
Feature activation+7.88e-01

Pos logit contributions
 ey+0.008
 skirts+0.008
 fru+0.008
 skirt+0.007
ems+0.007
Neg logit contributions
ver-0.005
hand-0.004
 chief-0.004
 Even-0.004
 happily-0.004
Token flew
Token ID13112
Feature activation+2.15e-01

Pos logit contributions
ver+0.028
hand+0.026
 chief+0.025
rolled+0.024
 department+0.024
Neg logit contributions
 ey-0.026
 skirts-0.025
 fru-0.025
 skirt-0.023
ems-0.022
Token to
Token ID284
Feature activation-4.52e-01

Pos logit contributions
ver+0.007
 chief+0.007
hand+0.006
 Even+0.006
itt+0.006
Neg logit contributions
 skirts-0.008
 ey-0.007
 fru-0.007
 skirt-0.007
 prett-0.007
Token and
Token ID290
Feature activation-9.83e-01

Pos logit contributions
 ey+0.012
 skirts+0.012
 fru+0.011
 skirt+0.010
 makeup+0.010
Neg logit contributions
ver-0.011
hand-0.009
 chief-0.009
rolled-0.009
 department-0.009
Token white
Token ID2330
Feature activation-1.49e-01

Pos logit contributions
 ey+0.031
 skirts+0.029
ems+0.028
 skirt+0.026
reath+0.026
Neg logit contributions
 quickly-0.034
 happily-0.033
 sadly-0.032
ver-0.032
 chief-0.031
Token and
Token ID290
Feature activation-9.95e-01

Pos logit contributions
 ey+0.005
 skirts+0.005
 fru+0.005
 skirt+0.005
 makeup+0.004
Neg logit contributions
ver-0.005
hand-0.005
 chief-0.005
rolled-0.005
 department-0.004
Token had
Token ID550
Feature activation-6.98e-01

Pos logit contributions
 ey+0.036
 skirts+0.034
ems+0.031
 skirt+0.030
 fru+0.030
Neg logit contributions
ver-0.031
 quickly-0.030
 happily-0.030
 chief-0.029
 sadly-0.028
Token a
Token ID257
Feature activation-6.18e-01

Pos logit contributions
 ey+0.022
 skirts+0.022
 fru+0.021
 skirt+0.019
 makeup+0.018
Neg logit contributions
ver-0.027
hand-0.025
 chief-0.024
rolled-0.023
 sadly-0.023
Token be
Token ID307
Feature activation-3.56e+00

Pos logit contributions
 ey+0.018
 skirts+0.017
 fru+0.017
 skirt+0.015
 makeup+0.014
Neg logit contributions
ver-0.025
hand-0.023
 chief-0.023
rolled-0.022
 happily-0.022
Tokenak
Token ID461
Feature activation-1.29e+00

Pos logit contributions
 ey+0.103
 skirts+0.097
 fru+0.096
 skirt+0.087
ems+0.083
Neg logit contributions
ver-0.141
hand-0.128
 happily-0.128
 chief-0.126
rolled-0.125
Token and
Token ID290
Feature activation-8.72e-01

Pos logit contributions
 ey+0.042
 skirts+0.042
 fru+0.040
 skirt+0.037
 makeup+0.036
Neg logit contributions
ver-0.046
hand-0.042
 chief-0.041
 Even-0.040
rolled-0.039
Token fl
Token ID781
Feature activation-6.55e-01

Pos logit contributions
 ey+0.032
 skirts+0.031
 fru+0.030
 skirt+0.028
 makeup+0.027
Neg logit contributions
ver-0.029
hand-0.026
 chief-0.025
rolled-0.024
 department-0.024
Tokenippers
Token ID16415
Feature activation-7.68e-01

Pos logit contributions
 ey+0.024
 skirts+0.021
 fru+0.021
eking+0.020
ems+0.019
Neg logit contributions
hand-0.021
 chief-0.020
ver-0.019
 mayor-0.019
 department-0.019
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
 skirts+0.025
 ey+0.025
 fru+0.024
 skirt+0.022
 makeup+0.021
Neg logit contributions
ver-0.027
hand-0.025
 chief-0.025
 department-0.024
 Even-0.024
Token it
Token ID340
Feature activation-7.60e-01

Pos logit contributions
 ey+0.010
 skirts+0.010
 fru+0.010
 skirt+0.009
 da+0.009
Neg logit contributions
ver-0.012
hand-0.011
 chief-0.011
rolled-0.011
 department-0.011
Token had
Token ID550
Feature activation-1.09e+00

Pos logit contributions
 ey+0.026
 fru+0.025
 skirts+0.025
 skirt+0.023
ems+0.022
Neg logit contributions
ver-0.026
hand-0.024
 chief-0.023
rolled-0.022
 department-0.022
Token something
Token ID1223
Feature activation-3.28e-01

Pos logit contributions
 ey+0.039
 skirts+0.039
 fru+0.038
 skirt+0.035
 makeup+0.033
Neg logit contributions
ver-0.036
hand-0.032
 chief-0.032
rolled-0.030
 department-0.030
Token in
Token ID287
Feature activation-6.97e-01

Pos logit contributions
 ey+0.012
 skirts+0.011
 fru+0.011
ems+0.010
 skirt+0.010
Neg logit contributions
ver-0.011
hand-0.010
 chief-0.010
 happily-0.010
 sadly-0.010
Token its
Token ID663
Feature activation-1.70e-02

Pos logit contributions
 ey+0.026
 skirts+0.026
 fru+0.025
 skirt+0.023
ems+0.022
Neg logit contributions
ver-0.022
hand-0.020
 chief-0.020
 happily-0.019
 Even-0.019
Token be
Token ID307
Feature activation-3.55e+00

Pos logit contributions
 skirts+0.001
 ey+0.001
 fru+0.001
ems+0.001
 skirt+0.001
Neg logit contributions
ver-0.001
 happily-0.000
 Even-0.000
 sadly-0.000
hand-0.000
Tokenak
Token ID461
Feature activation-1.76e+00

Pos logit contributions
 ey+0.107
 skirts+0.102
 fru+0.101
 skirt+0.090
ems+0.086
Neg logit contributions
ver-0.135
 happily-0.123
hand-0.122
 safely-0.119
 chief-0.117
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
 ey+0.060
 skirts+0.059
 fru+0.057
 skirt+0.053
ems+0.051
Neg logit contributions
ver-0.060
hand-0.055
 chief-0.054
 Even-0.052
rolled-0.052
Token
Token ID220
Feature activation+8.79e-02

Pos logit contributions
 ey+0.010
 fru+0.010
 skirts+0.009
 ol+0.008
---+0.008
Neg logit contributions
ver-0.012
 department-0.011
 chief-0.011
hand-0.011
te-0.010
Token
Token ID198
Feature activation-1.57e-01

Pos logit contributions
 chief+0.003
hand+0.003
 department+0.003
 mayor+0.003
ver+0.003
Neg logit contributions
 ey-0.003
 fru-0.002
 skirts-0.002
----0.002
ems-0.002
Token
Token ID198
Feature activation-1.61e-01

Pos logit contributions
 ey+0.005
 fru+0.005
 skirts+0.005
---+0.004
ems+0.004
Neg logit contributions
 department-0.005
 chief-0.005
ver-0.005
hand-0.005
 brigade-0.005
Token holding
Token ID4769
Feature activation-6.18e-01

Pos logit contributions
ver+0.017
hand+0.016
 happily+0.015
 chief+0.015
 sadly+0.015
Neg logit contributions
 ey-0.021
 skirts-0.021
 fru-0.021
 skirt-0.018
ems-0.018
Token the
Token ID262
Feature activation-5.41e-01

Pos logit contributions
 fru+0.016
 skirts+0.016
 makeup+0.015
 ey+0.015
 skirt+0.015
Neg logit contributions
ver-0.026
 department-0.025
 chief-0.024
hand-0.023
 brigade-0.023
Token carrot
Token ID40562
Feature activation+1.71e-01

Pos logit contributions
 ey+0.018
 skirts+0.018
 fru+0.016
ems+0.016
---+0.015
Neg logit contributions
ver-0.018
hand-0.017
 happily-0.017
 chief-0.017
 sadly-0.017
Token in
Token ID287
Feature activation-4.80e-01

Pos logit contributions
ver+0.006
hand+0.006
 chief+0.006
 Even+0.006
rolled+0.006
Neg logit contributions
 skirts-0.005
 ey-0.005
 skirt-0.005
 fru-0.005
 makeup-0.004
Token its
Token ID663
Feature activation-1.66e-01

Pos logit contributions
 ey+0.017
 skirts+0.016
 fru+0.016
 skirt+0.015
ems+0.014
Neg logit contributions
ver-0.016
hand-0.015
 chief-0.015
rolled-0.014
 happily-0.014
Token be
Token ID307
Feature activation-3.54e+00

Pos logit contributions
 skirts+0.006
 ey+0.006
 fru+0.005
ems+0.005
 skirt+0.005
Neg logit contributions
ver-0.005
 happily-0.005
 sadly-0.005
hand-0.005
 Even-0.005
Tokenak
Token ID461
Feature activation-1.83e+00

Pos logit contributions
 ey+0.118
 fru+0.110
 skirts+0.110
ems+0.099
 skirt+0.098
Neg logit contributions
ver-0.123
 happily-0.117
 safely-0.112
 quickly-0.110
hand-0.109
Token.
Token ID13
Feature activation-3.08e-01

Pos logit contributions
 skirts+0.058
 ey+0.057
 fru+0.055
 skirt+0.052
 makeup+0.049
Neg logit contributions
ver-0.066
hand-0.061
 chief-0.061
 Even-0.058
 department-0.057
Token Benny
Token ID44275
Feature activation-4.49e-01

Pos logit contributions
 fru+0.011
 skirts+0.010
 ey+0.010
 skirt+0.009
 makeup+0.009
Neg logit contributions
ver-0.010
hand-0.010
 chief-0.009
te-0.009
 mayor-0.009
Token and
Token ID290
Feature activation-7.72e-01

Pos logit contributions
 fru+0.012
 skirts+0.011
 ey+0.011
 skirt+0.010
 da+0.010
Neg logit contributions
ver-0.019
hand-0.018
 chief-0.017
 department-0.017
 tow-0.017
Token Lily
Token ID20037
Feature activation-5.55e-01

Pos logit contributions
 ey+0.033
 fru+0.030
 skirts+0.030
eking+0.029
reath+0.028
Neg logit contributions
 happily-0.020
 sadly-0.019
 quickly-0.019
 Even-0.018
ver-0.018
Token
Token ID198
Feature activation+1.40e-01

Pos logit contributions
ver+0.023
hand+0.021
 chief+0.021
 department+0.020
rolled+0.019
Neg logit contributions
 ey-0.031
 fru-0.030
 skirts-0.030
 skirt-0.027
 makeup-0.027
Token
Token ID198
Feature activation+2.75e-02

Pos logit contributions
ver+0.004
 chief+0.004
hand+0.004
 department+0.004
 brigade+0.004
Neg logit contributions
 ey-0.005
 skirts-0.005
 fru-0.005
----0.004
 skirt-0.004
TokenIt
Token ID1026
Feature activation+3.59e-01

Pos logit contributions
ver+0.001
hand+0.001
 chief+0.001
 happily+0.001
rolled+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
ems-0.001
Token put
Token ID1234
Feature activation-6.97e-01

Pos logit contributions
ver+0.014
hand+0.013
 mayor+0.012
 chief+0.012
itt+0.012
Neg logit contributions
 fru-0.011
 skirts-0.010
 ey-0.009
 prett-0.009
 skirt-0.009
Token its
Token ID663
Feature activation-1.45e-01

Pos logit contributions
 ey+0.027
 skirts+0.026
 fru+0.025
 skirt+0.024
ems+0.023
Neg logit contributions
ver-0.021
hand-0.019
 chief-0.019
 happily-0.018
rolled-0.018
Token be
Token ID307
Feature activation-3.54e+00

Pos logit contributions
 skirts+0.005
 ey+0.005
 fru+0.004
ems+0.004
 skirt+0.004
Neg logit contributions
ver-0.005
 chief-0.005
 happily-0.005
hand-0.004
 safely-0.004
Tokenak
Token ID461
Feature activation-1.81e+00

Pos logit contributions
 ey+0.111
 fru+0.102
 skirts+0.100
 skirt+0.090
ems+0.090
Neg logit contributions
ver-0.135
 happily-0.126
 safely-0.123
hand-0.122
 quickly-0.120
Token into
Token ID656
Feature activation-4.50e-01

Pos logit contributions
 skirts+0.061
 ey+0.056
 fru+0.055
 skirt+0.054
 makeup+0.052
Neg logit contributions
ver-0.060
 Even-0.057
 chief-0.057
hand-0.056
 mayor-0.054
Token the
Token ID262
Feature activation-2.80e-01

Pos logit contributions
 ey+0.018
 skirts+0.018
 fru+0.017
 skirt+0.016
ems+0.016
Neg logit contributions
ver-0.012
hand-0.011
 chief-0.011
 happily-0.011
 Even-0.010
Token crack
Token ID8469
Feature activation-9.05e-01

Pos logit contributions
 skirts+0.011
 ey+0.010
ems+0.010
 fru+0.009
 skirt+0.009
Neg logit contributions
 chief-0.008
hand-0.008
 happily-0.007
 safely-0.007
ver-0.007
Token and
Token ID290
Feature activation+8.01e-02

Pos logit contributions
 ey+0.033
 skirts+0.032
 fru+0.031
 skirt+0.029
 makeup+0.027
Neg logit contributions
ver-0.030
hand-0.027
 chief-0.026
rolled-0.026
 Even-0.025
Token a
Token ID257
Feature activation-8.53e-01

Pos logit contributions
 ey+0.024
 skirts+0.024
 fru+0.024
 skirt+0.022
 makeup+0.021
Neg logit contributions
ver-0.017
hand-0.016
 chief-0.015
 department-0.014
rolled-0.014
Token little
Token ID1310
Feature activation-4.69e-01

Pos logit contributions
 ey+0.028
 skirts+0.028
 fru+0.026
ems+0.024
 skirt+0.023
Neg logit contributions
ver-0.030
 chief-0.027
 happily-0.027
hand-0.027
 sadly-0.027
Token envelope
Token ID22878
Feature activation+4.54e-01

Pos logit contributions
 ey+0.015
 skirts+0.014
 fru+0.014
 skirt+0.013
 makeup+0.012
Neg logit contributions
ver-0.018
hand-0.016
 chief-0.016
rolled-0.015
 Even-0.015
Token in
Token ID287
Feature activation-8.05e-01

Pos logit contributions
ver+0.014
hand+0.013
 chief+0.012
rolled+0.012
 Even+0.012
Neg logit contributions
 ey-0.017
 skirts-0.017
 fru-0.016
 skirt-0.015
ems-0.015
Token its
Token ID663
Feature activation-4.67e-01

Pos logit contributions
 ey+0.030
 skirts+0.029
 fru+0.028
 skirt+0.026
ems+0.025
Neg logit contributions
ver-0.026
hand-0.024
 chief-0.023
 happily-0.022
rolled-0.022
Token be
Token ID307
Feature activation-3.53e+00

Pos logit contributions
 ey+0.017
 skirts+0.017
 fru+0.016
ems+0.015
 skirt+0.015
Neg logit contributions
ver-0.014
 happily-0.013
 sadly-0.013
hand-0.013
 Even-0.013
Tokenak
Token ID461
Feature activation-1.92e+00

Pos logit contributions
 ey+0.115
 skirts+0.105
 fru+0.104
 skirt+0.095
ems+0.091
Neg logit contributions
ver-0.131
 happily-0.120
rolled-0.115
hand-0.114
 safely-0.114
Token.
Token ID13
Feature activation-2.21e-01

Pos logit contributions
 skirts+0.065
 ey+0.065
 fru+0.062
 skirt+0.058
 makeup+0.056
Neg logit contributions
ver-0.065
hand-0.060
 chief-0.059
 Even-0.056
 department-0.056
Token Tim
Token ID5045
Feature activation-6.67e-01

Pos logit contributions
 ey+0.008
 fru+0.008
 skirts+0.008
 ol+0.007
 makeup+0.007
Neg logit contributions
ver-0.007
hand-0.007
 chief-0.006
rolled-0.006
 happily-0.006
Token opened
Token ID4721
Feature activation-6.13e-01

Pos logit contributions
 fru+0.018
 skirts+0.018
 ey+0.018
 skirt+0.016
 da+0.016
Neg logit contributions
hand-0.026
ver-0.025
 chief-0.023
 tow-0.023
 department-0.023
Token the
Token ID262
Feature activation-4.46e-01

Pos logit contributions
 ey+0.017
 skirts+0.016
 fru+0.015
 skirt+0.014
 da+0.013
Neg logit contributions
ver-0.026
hand-0.024
 chief-0.024
 department-0.024
 brigade-0.023
Token dropped
Token ID5710
Feature activation+2.92e-01

Pos logit contributions
ver+0.031
hand+0.028
 chief+0.028
 happily+0.028
 sadly+0.027
Neg logit contributions
 ey-0.034
 skirts-0.033
 fru-0.032
 skirt-0.029
ems-0.029
Token the
Token ID262
Feature activation-4.62e-01

Pos logit contributions
ver+0.014
rolled+0.013
hand+0.012
 chief+0.012
case+0.012
Neg logit contributions
 ey-0.007
 skirts-0.007
 fru-0.007
 ol-0.006
 skirt-0.006
Token car
Token ID1097
Feature activation+4.93e-01

Pos logit contributions
 ey+0.016
 skirts+0.016
 fru+0.015
 skirt+0.014
 makeup+0.013
Neg logit contributions
ver-0.016
hand-0.015
 chief-0.014
 Even-0.014
rolled-0.014
Token from
Token ID422
Feature activation+6.96e-01

Pos logit contributions
ver+0.019
hand+0.017
 chief+0.017
rolled+0.017
 Even+0.017
Neg logit contributions
 skirts-0.015
 ey-0.015
 skirt-0.013
 fru-0.013
 makeup-0.013
Token its
Token ID663
Feature activation-8.27e-02

Pos logit contributions
ver+0.026
hand+0.023
 chief+0.022
rolled+0.022
 department+0.022
Neg logit contributions
 ey-0.023
 skirts-0.022
 fru-0.022
 skirt-0.020
 makeup-0.019
Token be
Token ID307
Feature activation-3.53e+00

Pos logit contributions
 ey+0.003
 skirts+0.002
 fru+0.002
 skirt+0.002
ems+0.002
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.003
 happily-0.003
rolled-0.003
Tokenak
Token ID461
Feature activation-1.90e+00

Pos logit contributions
 ey+0.100
 skirts+0.094
 fru+0.094
 skirt+0.083
ems+0.080
Neg logit contributions
ver-0.143
hand-0.131
 happily-0.130
 chief-0.128
rolled-0.126
Token.
Token ID13
Feature activation+4.58e-02

Pos logit contributions
 skirts+0.056
 ey+0.055
 skirt+0.050
 fru+0.050
 makeup+0.048
Neg logit contributions
ver-0.073
 chief-0.067
hand-0.067
rolled-0.064
 mayor-0.064
Token The
Token ID383
Feature activation+2.29e-02

Pos logit contributions
ver+0.001
hand+0.001
 chief+0.001
 department+0.001
rolled+0.001
Neg logit contributions
 ey-0.002
 fru-0.002
 skirts-0.002
 skirt-0.002
ems-0.001
Token car
Token ID1097
Feature activation+8.30e-01

Pos logit contributions
ver+0.001
hand+0.001
rolled+0.001
 Even+0.001
 chief+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
 makeup-0.001
Token fell
Token ID3214
Feature activation+6.03e-01

Pos logit contributions
ver+0.032
hand+0.030
 Even+0.028
 chief+0.028
rolled+0.027
Neg logit contributions
 skirts-0.023
 ey-0.023
 fru-0.022
 skirt-0.021
 brace-0.020
Token the
Token ID262
Feature activation-4.06e-02

Pos logit contributions
 skirts+0.006
 fru+0.006
 ey+0.005
 makeup+0.005
 ol+0.005
Neg logit contributions
ver-0.006
hand-0.006
 chief-0.006
case-0.006
 Even-0.006
Token needle
Token ID17598
Feature activation+4.64e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.001
 disl+0.001
ems+0.001
Neg logit contributions
ver-0.001
't-0.001
 happily-0.001
 safely-0.001
 sadly-0.001
Token out
Token ID503
Feature activation+6.16e-01

Pos logit contributions
ver+0.015
hand+0.014
 chief+0.013
rolled+0.013
 Even+0.013
Neg logit contributions
 skirts-0.017
 ey-0.017
 fru-0.016
 skirt-0.015
 makeup-0.014
Token of
Token ID286
Feature activation-1.74e-01

Pos logit contributions
ver+0.011
hand+0.009
 chief+0.008
 happily+0.008
 Even+0.007
Neg logit contributions
 ey-0.032
 skirts-0.031
 fru-0.031
 skirt-0.029
ems-0.028
Token its
Token ID663
Feature activation+3.80e-01

Pos logit contributions
 ey+0.007
 skirts+0.006
 fru+0.006
ems+0.006
 skirt+0.006
Neg logit contributions
ver-0.005
hand-0.005
 happily-0.005
 chief-0.005
 sadly-0.005
Token be
Token ID307
Feature activation-3.53e+00

Pos logit contributions
 happily+0.011
ver+0.011
 sadly+0.011
 safely+0.010
rolled+0.010
Neg logit contributions
 ey-0.014
 skirts-0.013
 fru-0.013
ems-0.012
----0.012
Tokenak
Token ID461
Feature activation-1.74e+00

Pos logit contributions
 ey+0.124
 fru+0.114
 skirts+0.110
 skirt+0.101
ems+0.095
Neg logit contributions
ver-0.126
 happily-0.116
 safely-0.113
 quickly-0.111
 sadly-0.108
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
 ey+0.060
 skirts+0.060
 fru+0.058
 skirt+0.054
 makeup+0.052
Neg logit contributions
ver-0.057
hand-0.053
 chief-0.052
rolled-0.049
 Even-0.049
Token After
Token ID2293
Feature activation-7.85e-01

Pos logit contributions
 ey+0.004
 fru+0.004
 skirts+0.004
ems+0.003
 skirt+0.003
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.003
rolled-0.003
 department-0.003
Token a
Token ID257
Feature activation-6.07e-01

Pos logit contributions
 ey+0.029
 skirts+0.029
 fru+0.028
 makeup+0.026
 ol+0.026
Neg logit contributions
ver-0.024
hand-0.021
 chief-0.021
 department-0.020
rolled-0.020
Token few
Token ID1178
Feature activation-7.69e-01

Pos logit contributions
 ey+0.026
 skirts+0.025
 fru+0.023
ems+0.022
 skirt+0.022
Neg logit contributions
ver-0.017
hand-0.015
 chief-0.015
 happily-0.015
 quickly-0.015
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
ver+0.004
hand+0.004
 chief+0.004
 happily+0.004
 Even+0.003
Neg logit contributions
 ey-0.005
 skirts-0.005
 fru-0.005
 skirt-0.004
ems-0.004
Token It
Token ID632
Feature activation+4.85e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.000
 skirt+0.000
ems+0.000
Neg logit contributions
ver-0.000
hand-0.000
 chief-0.000
 Even-0.000
 happily-0.000
Token had
Token ID550
Feature activation-4.70e-01

Pos logit contributions
ver+0.014
hand+0.012
 chief+0.012
 happily+0.011
rolled+0.011
Neg logit contributions
 ey-0.020
 skirts-0.019
 fru-0.019
 skirt-0.018
ems-0.017
Token a
Token ID257
Feature activation-7.00e-01

Pos logit contributions
 ey+0.017
 skirts+0.017
 fru+0.017
 skirt+0.015
 makeup+0.015
Neg logit contributions
ver-0.016
hand-0.014
 chief-0.014
 department-0.013
rolled-0.013
Token long
Token ID890
Feature activation-1.70e+00

Pos logit contributions
 ey+0.022
 skirts+0.022
 fru+0.020
ems+0.019
 skirt+0.018
Neg logit contributions
ver-0.025
 chief-0.023
hand-0.023
 happily-0.023
 sadly-0.023
Token be
Token ID307
Feature activation-3.52e+00

Pos logit contributions
 skirts+0.055
 ey+0.055
 fru+0.053
ems+0.048
 ol+0.046
Neg logit contributions
ver-0.056
 happily-0.055
 Even-0.054
 sadly-0.054
rolled-0.053
Tokenak
Token ID461
Feature activation-1.49e+00

Pos logit contributions
 ey+0.097
 skirts+0.092
 fru+0.091
 skirt+0.081
ems+0.077
Neg logit contributions
ver-0.145
hand-0.132
 happily-0.130
 chief-0.129
rolled-0.128
Token and
Token ID290
Feature activation-1.15e+00

Pos logit contributions
 ey+0.055
 skirts+0.053
 fru+0.051
 skirt+0.048
 makeup+0.046
Neg logit contributions
ver-0.048
hand-0.044
 chief-0.043
 department-0.041
 happily-0.040
Token shiny
Token ID22441
Feature activation-1.93e-01

Pos logit contributions
 ey+0.046
 skirts+0.045
 fru+0.044
 skirt+0.041
 makeup+0.040
Neg logit contributions
ver-0.033
hand-0.030
 chief-0.029
 department-0.027
rolled-0.027
Token eyes
Token ID2951
Feature activation+4.88e-03

Pos logit contributions
 ey+0.006
 skirts+0.006
 fru+0.005
ems+0.005
---+0.005
Neg logit contributions
ver-0.007
 happily-0.007
 sadly-0.007
hand-0.007
rolled-0.007
Token.
Token ID13
Feature activation-2.41e-02

Pos logit contributions
ver+0.000
 chief+0.000
hand+0.000
 department+0.000
 Even+0.000
Neg logit contributions
 skirts-0.000
 ey-0.000
 fru-0.000
 skirt-0.000
 makeup-0.000
Token had
Token ID550
Feature activation-6.26e-01

Pos logit contributions
ver+0.019
hand+0.017
 chief+0.017
 happily+0.016
 Even+0.016
Neg logit contributions
 ey-0.025
 skirts-0.024
 fru-0.024
 skirt-0.022
ems-0.021
Token a
Token ID257
Feature activation-6.83e-01

Pos logit contributions
 ey+0.026
 skirts+0.025
 fru+0.025
 skirt+0.023
 makeup+0.022
Neg logit contributions
ver-0.018
hand-0.016
 chief-0.015
 department-0.014
rolled-0.014
Token loop
Token ID9052
Feature activation-2.48e-01

Pos logit contributions
 ey+0.023
 skirts+0.023
 fru+0.022
ems+0.021
 skirt+0.019
Neg logit contributions
ver-0.023
 chief-0.021
 happily-0.021
hand-0.020
 sadly-0.020
Token in
Token ID287
Feature activation-7.32e-01

Pos logit contributions
 ey+0.009
 skirts+0.009
 fru+0.008
 skirt+0.008
 makeup+0.008
Neg logit contributions
ver-0.008
hand-0.007
 chief-0.007
 department-0.007
 Even-0.007
Token its
Token ID663
Feature activation-5.45e-01

Pos logit contributions
 ey+0.025
 skirts+0.025
 fru+0.024
 skirt+0.022
 makeup+0.021
Neg logit contributions
ver-0.026
hand-0.023
 chief-0.023
 department-0.022
rolled-0.022
Token be
Token ID307
Feature activation-3.52e+00

Pos logit contributions
 ey+0.019
 skirts+0.019
 fru+0.018
ems+0.017
 skirt+0.016
Neg logit contributions
ver-0.017
 happily-0.016
hand-0.016
 Even-0.016
rolled-0.016
Tokenak
Token ID461
Feature activation-2.08e+00

Pos logit contributions
 ey+0.119
 fru+0.112
 skirts+0.105
 skirt+0.097
ems+0.094
Neg logit contributions
ver-0.128
 happily-0.117
 safely-0.114
rolled-0.112
hand-0.110
Token.
Token ID13
Feature activation-3.67e-01

Pos logit contributions
 skirts+0.067
 ey+0.065
 fru+0.061
 skirt+0.059
 makeup+0.056
Neg logit contributions
ver-0.075
hand-0.070
 chief-0.069
 department-0.066
 Even-0.065
Token The
Token ID383
Feature activation-1.33e-02

Pos logit contributions
 ey+0.015
 skirts+0.014
 fru+0.014
 skirt+0.013
ems+0.013
Neg logit contributions
ver-0.010
hand-0.010
 chief-0.009
 department-0.009
rolled-0.009
Token bird
Token ID6512
Feature activation-3.92e-02

Pos logit contributions
 ey+0.000
 fru+0.000
 skirts+0.000
ems+0.000
 makeup+0.000
Neg logit contributions
ver-0.000
 happily-0.000
hand-0.000
 chief-0.000
rolled-0.000
Token started
Token ID2067
Feature activation+2.19e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.001
 skirt+0.001
 makeup+0.001
Neg logit contributions
ver-0.001
hand-0.001
 chief-0.001
 happily-0.001
rolled-0.001
Token it
Token ID340
Feature activation-8.02e-01

Pos logit contributions
 ey+0.011
 skirts+0.011
 fru+0.011
 skirt+0.010
ems+0.009
Neg logit contributions
ver-0.010
hand-0.009
 chief-0.009
 happily-0.008
rolled-0.008
Token hurt
Token ID5938
Feature activation-7.19e-01

Pos logit contributions
 ey+0.027
 fru+0.026
 skirts+0.026
 skirt+0.024
 ol+0.022
Neg logit contributions
ver-0.028
hand-0.027
 chief-0.025
rolled-0.024
 Even-0.023
Token Twe
Token ID24205
Feature activation+1.49e+00

Pos logit contributions
 skirts+0.023
 ey+0.022
 fru+0.022
 makeup+0.021
 skirt+0.021
Neg logit contributions
ver-0.026
 chief-0.025
hand-0.023
 department-0.022
 mayor-0.022
Tokenety
Token ID2963
Feature activation-1.36e+00

Pos logit contributions
ver+0.066
hand+0.062
 happily+0.059
 chief+0.059
rolled+0.059
Neg logit contributions
 ey-0.037
 skirts-0.035
 fru-0.034
 skirt-0.029
 makeup-0.028
Token's
Token ID338
Feature activation-2.33e-01

Pos logit contributions
 ey+0.049
 skirts+0.048
 fru+0.047
 skirt+0.044
ems+0.042
Neg logit contributions
ver-0.044
hand-0.040
 chief-0.039
rolled-0.037
 Even-0.037
Token be
Token ID307
Feature activation-3.50e+00

Pos logit contributions
 ey+0.008
 skirts+0.008
 fru+0.008
ems+0.007
 skirt+0.007
Neg logit contributions
ver-0.008
hand-0.007
 happily-0.007
 chief-0.007
 sadly-0.007
Tokenak
Token ID461
Feature activation-1.99e+00

Pos logit contributions
 ey+0.100
 skirts+0.093
 fru+0.090
 skirt+0.080
ems+0.078
Neg logit contributions
ver-0.144
 happily-0.133
hand-0.131
 sadly-0.128
 quickly-0.127
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
 skirts+0.056
 skirt+0.052
 ey+0.050
 fru+0.049
 makeup+0.047
Neg logit contributions
ver-0.079
 chief-0.075
hand-0.073
 Even-0.072
rolled-0.072
Token Twe
Token ID24205
Feature activation+1.50e+00

Pos logit contributions
 ey+0.015
 fru+0.015
 skirts+0.014
 makeup+0.013
 skirt+0.013
Neg logit contributions
ver-0.014
hand-0.012
 chief-0.012
 department-0.012
 brigade-0.011
Tokenety
Token ID2963
Feature activation-6.13e-01

Pos logit contributions
ver+0.064
hand+0.059
 happily+0.058
rolled+0.057
 Even+0.057
Neg logit contributions
 ey-0.040
 skirts-0.039
 fru-0.037
 skirt-0.033
 makeup-0.031
Token learned
Token ID4499
Feature activation-5.06e-02

Pos logit contributions
 fru+0.018
 ey+0.018
 skirts+0.018
 skirt+0.017
ems+0.015
Neg logit contributions
ver-0.023
hand-0.022
 chief-0.021
 tow-0.020
 department-0.020
Token pipe
Token ID12656
Feature activation-3.46e-01

Pos logit contributions
 skirts+0.024
 fru+0.023
 ey+0.022
ems+0.020
 skirt+0.019
Neg logit contributions
 chief-0.025
 department-0.024
 quickly-0.024
ver-0.024
hand-0.023
Token got
Token ID1392
Feature activation-2.31e-01

Pos logit contributions
 ey+0.012
 skirts+0.012
 fru+0.011
 skirt+0.011
 makeup+0.010
Neg logit contributions
ver-0.011
hand-0.011
 chief-0.010
rolled-0.010
 Even-0.010
Token stuck
Token ID7819
Feature activation-7.04e-01

Pos logit contributions
 skirts+0.007
 ey+0.007
 fru+0.007
 prett+0.007
 ol+0.006
Neg logit contributions
ver-0.008
hand-0.008
 chief-0.008
 Even-0.007
rolled-0.007
Token on
Token ID319
Feature activation+5.95e-01

Pos logit contributions
 skirts+0.022
 ey+0.021
 fru+0.019
 skirt+0.019
 makeup+0.018
Neg logit contributions
ver-0.025
 chief-0.024
hand-0.024
 Even-0.023
rolled-0.023
Token his
Token ID465
Feature activation-2.68e-01

Pos logit contributions
ver+0.026
 chief+0.023
hand+0.022
ittle+0.022
uttered+0.022
Neg logit contributions
 ey-0.014
 skirts-0.014
 ol-0.014
 fru-0.014
 makeup-0.013
Token be
Token ID307
Feature activation-3.50e+00

Pos logit contributions
 ey+0.009
 skirts+0.009
 fru+0.009
ems+0.008
 skirt+0.008
Neg logit contributions
ver-0.009
hand-0.008
 chief-0.008
 happily-0.008
rolled-0.008
Tokenak
Token ID461
Feature activation-1.95e+00

Pos logit contributions
 ey+0.098
 fru+0.091
 skirts+0.091
 skirt+0.079
ems+0.076
Neg logit contributions
ver-0.148
hand-0.133
 happily-0.132
 chief-0.130
rolled-0.128
Token!
Token ID0
Feature activation-5.26e-01

Pos logit contributions
 skirts+0.058
 ey+0.055
 skirt+0.052
 fru+0.051
 makeup+0.049
Neg logit contributions
ver-0.072
 chief-0.070
hand-0.069
 mayor-0.065
rolled-0.065
Token
Token ID220
Feature activation+1.43e-01

Pos logit contributions
 ey+0.018
 fru+0.017
 skirts+0.016
 ol+0.015
 makeup+0.015
Neg logit contributions
ver-0.018
hand-0.017
 chief-0.017
 department-0.016
 brigade-0.015
Token
Token ID198
Feature activation-1.99e-01

Pos logit contributions
 chief+0.005
hand+0.005
 department+0.004
ver+0.004
 mayor+0.004
Neg logit contributions
 ey-0.005
 skirts-0.004
 fru-0.004
----0.004
ems-0.004
Token
Token ID198
Feature activation-2.41e-01

Pos logit contributions
 ey+0.007
 fru+0.007
 skirts+0.007
---+0.006
 skirt+0.006
Neg logit contributions
ver-0.006
 chief-0.006
hand-0.006
 department-0.005
 brigade-0.005
Token had
Token ID550
Feature activation-6.83e-01

Pos logit contributions
ver+0.012
hand+0.011
 chief+0.011
 Even+0.010
 department+0.010
Neg logit contributions
 ey-0.013
 skirts-0.013
 fru-0.013
 skirt-0.012
ems-0.011
Token got
Token ID1392
Feature activation-1.71e-01

Pos logit contributions
 ey+0.025
 skirts+0.024
 fru+0.024
 skirt+0.022
ems+0.021
Neg logit contributions
ver-0.022
hand-0.020
 chief-0.020
 happily-0.019
rolled-0.019
Token stuck
Token ID7819
Feature activation-4.25e-01

Pos logit contributions
 skirts+0.006
 ey+0.006
 fru+0.006
 makeup+0.005
 skirt+0.005
Neg logit contributions
ver-0.006
hand-0.005
 chief-0.005
 Even-0.005
rolled-0.005
Token in
Token ID287
Feature activation-3.00e-01

Pos logit contributions
 skirts+0.014
 ey+0.014
 fru+0.013
 skirt+0.013
 makeup+0.012
Neg logit contributions
ver-0.014
hand-0.013
 chief-0.013
 Even-0.013
rolled-0.012
Token its
Token ID663
Feature activation+1.16e-01

Pos logit contributions
 ey+0.011
 skirts+0.011
 fru+0.011
 skirt+0.010
 makeup+0.010
Neg logit contributions
ver-0.010
hand-0.009
 chief-0.008
rolled-0.008
 department-0.008
Token be
Token ID307
Feature activation-3.48e+00

Pos logit contributions
ver+0.004
hand+0.004
 chief+0.003
 happily+0.003
 Even+0.003
Neg logit contributions
 ey-0.004
 skirts-0.004
 fru-0.004
 skirt-0.004
ems-0.003
Tokenak
Token ID461
Feature activation-1.75e+00

Pos logit contributions
 ey+0.094
 skirts+0.088
 fru+0.087
 skirt+0.077
ems+0.073
Neg logit contributions
ver-0.149
hand-0.136
 happily-0.133
 chief-0.133
rolled-0.130
Token!
Token ID0
Feature activation-3.49e-01

Pos logit contributions
 skirts+0.055
 ey+0.054
 fru+0.050
 skirt+0.049
 makeup+0.047
Neg logit contributions
ver-0.062
hand-0.058
 chief-0.058
rolled-0.056
 Even-0.056
Token
Token ID198
Feature activation-7.04e-02

Pos logit contributions
 ey+0.013
 fru+0.012
 skirts+0.011
 makeup+0.011
 ol+0.010
Neg logit contributions
ver-0.011
hand-0.010
 chief-0.010
 department-0.010
 brigade-0.009
Token
Token ID198
Feature activation-1.58e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.002
---+0.002
Neg logit contributions
ver-0.002
 chief-0.002
hand-0.002
 department-0.002
rolled-0.002
TokenThe
Token ID464
Feature activation+1.34e-01

Pos logit contributions
 ey+0.006
 skirts+0.006
 fru+0.006
 skirt+0.005
ems+0.005
Neg logit contributions
ver-0.005
hand-0.004
 chief-0.004
 happily-0.004
 Even-0.004
Token played
Token ID2826
Feature activation+7.98e-01

Pos logit contributions
hand+0.013
ver+0.013
 chief+0.012
 department+0.012
itt+0.012
Neg logit contributions
 skirts-0.010
 skirt-0.009
 fru-0.009
 sunglasses-0.009
ems-0.009
Token with
Token ID351
Feature activation-5.09e-01

Pos logit contributions
ver+0.017
hand+0.015
 chief+0.015
 department+0.014
rolled+0.014
Neg logit contributions
 skirts-0.037
 ey-0.037
 fru-0.036
 skirt-0.034
 makeup-0.033
Token the
Token ID262
Feature activation-4.56e-02

Pos logit contributions
 skirts+0.012
 fru+0.012
 da+0.011
 makeup+0.011
 ol+0.011
Neg logit contributions
ver-0.023
hand-0.021
rolled-0.021
 chief-0.020
 department-0.020
Token rh
Token ID9529
Feature activation+2.22e+00

Pos logit contributions
 ey+0.002
 fru+0.002
 skirts+0.002
 skirt+0.001
 makeup+0.001
Neg logit contributions
ver-0.002
hand-0.001
 chief-0.001
rolled-0.001
 Even-0.001
Tokenin
Token ID259
Feature activation+9.83e-01

Pos logit contributions
hand+0.075
ver+0.074
 Even+0.074
 Together+0.073
rolled+0.071
Neg logit contributions
 ey-0.067
 fru-0.063
 skirts-0.061
b-0.059
eking-0.058
Tokenoc
Token ID420
Feature activation+3.95e+00

Pos logit contributions
ver+0.036
uttered+0.032
hand+0.031
rolled+0.030
 Even+0.029
Neg logit contributions
 fru-0.028
 da-0.027
 ey-0.027
 ol-0.026
 skirts-0.026
Tokeneros
Token ID27498
Feature activation+5.64e-01

Pos logit contributions
ver+0.163
case+0.134
 Even+0.130
 happily+0.125
 Together+0.124
Neg logit contributions
 ey-0.123
 fru-0.114
 ol-0.099
ution-0.098
 brace-0.097
Token for
Token ID329
Feature activation-3.05e-01

Pos logit contributions
ver+0.020
rolled+0.019
hand+0.019
 Even+0.018
 chief+0.018
Neg logit contributions
 skirts-0.018
 skirt-0.016
 da-0.016
 ol-0.015
 fru-0.015
Token a
Token ID257
Feature activation-3.50e-01

Pos logit contributions
 ey+0.012
 skirts+0.012
 fru+0.012
 skirt+0.011
 makeup+0.010
Neg logit contributions
ver-0.009
hand-0.008
 chief-0.008
rolled-0.007
 department-0.007
Token while
Token ID981
Feature activation+3.68e-02

Pos logit contributions
 ey+0.011
 skirts+0.011
 fru+0.011
 skirt+0.010
 makeup+0.009
Neg logit contributions
ver-0.013
hand-0.012
 chief-0.012
rolled-0.011
 Even-0.011
Token,
Token ID11
Feature activation+6.65e-02

Pos logit contributions
ver+0.001
hand+0.001
 chief+0.001
rolled+0.001
 department+0.001
Neg logit contributions
 skirts-0.001
 ey-0.001
 fru-0.001
 skirt-0.001
 makeup-0.001
Token big
Token ID1263
Feature activation+4.08e-01

Pos logit contributions
ver+0.013
hand+0.013
 chief+0.012
rolled+0.012
 Even+0.012
Neg logit contributions
 ey-0.012
 skirts-0.012
 fru-0.012
 skirt-0.011
 makeup-0.010
Token,
Token ID11
Feature activation+2.26e-01

Pos logit contributions
ver+0.013
 chief+0.012
hand+0.012
 happily+0.012
 Even+0.012
Neg logit contributions
 ey-0.014
 skirts-0.014
 fru-0.014
 skirt-0.012
ems-0.012
Token gray
Token ID12768
Feature activation+6.64e-01

Pos logit contributions
ver+0.008
 chief+0.007
 happily+0.007
hand+0.007
 quickly+0.007
Neg logit contributions
 ey-0.007
 skirts-0.007
 fru-0.007
ems-0.006
 skirt-0.006
Token rh
Token ID9529
Feature activation+2.98e+00

Pos logit contributions
ver+0.026
hand+0.023
rolled+0.021
 chief+0.021
 Even+0.021
Neg logit contributions
 ey-0.022
 skirts-0.021
 fru-0.020
 skirt-0.020
 makeup-0.019
Tokenin
Token ID259
Feature activation+1.11e+00

Pos logit contributions
hand+0.101
ver+0.098
rolled+0.097
 department+0.092
 Even+0.091
Neg logit contributions
 ey-0.098
 skirts-0.092
 fru-0.088
 skirt-0.085
 da-0.085
Tokenoc
Token ID420
Feature activation+4.36e+00

Pos logit contributions
ver+0.033
hand+0.030
rolled+0.028
 department+0.027
uttered+0.027
Neg logit contributions
 ey-0.042
 skirts-0.041
 fru-0.041
 skirt-0.039
 da-0.038
Tokeneros
Token ID27498
Feature activation+7.79e-01

Pos logit contributions
ver+0.174
 Even+0.144
 sadly+0.140
rolled+0.139
hand+0.138
Neg logit contributions
 ey-0.140
 fru-0.129
 ol-0.118
 da-0.118
 jewelry-0.114
Token.
Token ID13
Feature activation-1.56e-01

Pos logit contributions
ver+0.028
hand+0.026
 department+0.025
 chief+0.024
rolled+0.024
Neg logit contributions
 skirts-0.024
 ey-0.024
 fru-0.023
 skirt-0.022
 makeup-0.022
Token He
Token ID679
Feature activation+3.51e-02

Pos logit contributions
 ey+0.006
 skirts+0.006
 fru+0.006
 skirt+0.006
 makeup+0.005
Neg logit contributions
ver-0.004
hand-0.004
 chief-0.004
 department-0.004
 sadly-0.004
Token lived
Token ID5615
Feature activation+1.12e+00

Pos logit contributions
ver+0.001
 chief+0.001
hand+0.001
 happily+0.001
rolled+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
ems-0.001
Token in
Token ID287
Feature activation-4.64e-01

Pos logit contributions
hand+0.041
ver+0.041
 Even+0.037
 chief+0.037
 department+0.037
Neg logit contributions
 ey-0.033
 skirts-0.033
 fru-0.031
 skirt-0.029
 prett-0.028
Token Daddy
Token ID26926
Feature activation-3.87e-01

Pos logit contributions
 ey+0.008
 skirts+0.008
 fru+0.008
 skirt+0.007
 makeup+0.007
Neg logit contributions
ver-0.007
hand-0.006
 chief-0.006
rolled-0.006
 Even-0.006
Token,
Token ID11
Feature activation-3.91e-01

Pos logit contributions
 ey+0.014
 skirts+0.014
 fru+0.014
 skirt+0.013
 makeup+0.012
Neg logit contributions
ver-0.012
hand-0.011
 chief-0.011
rolled-0.010
 department-0.010
Token and
Token ID290
Feature activation-9.14e-01

Pos logit contributions
 ey+0.014
 skirts+0.014
 fru+0.014
 skirt+0.013
ems+0.012
Neg logit contributions
ver-0.013
hand-0.012
 chief-0.011
rolled-0.011
 happily-0.011
Token three
Token ID1115
Feature activation+6.01e-01

Pos logit contributions
 ey+0.038
 skirts+0.035
 fru+0.034
 skirt+0.032
ems+0.032
Neg logit contributions
ver-0.026
hand-0.023
 happily-0.023
 chief-0.023
 sadly-0.022
Token-
Token ID12
Feature activation+1.23e+00

Pos logit contributions
ver+0.022
hand+0.020
 chief+0.019
rolled+0.019
 department+0.018
Neg logit contributions
 skirts-0.020
 ey-0.019
 fru-0.019
 skirt-0.017
 makeup-0.017
Tokenyear
Token ID1941
Feature activation+3.29e+00

Pos logit contributions
ver+0.027
 Even+0.023
rolled+0.022
 sadly+0.022
hand+0.021
Neg logit contributions
 skirts-0.056
 fru-0.055
 ol-0.053
 makeup-0.052
 ey-0.052
Token-
Token ID12
Feature activation+5.70e-01

Pos logit contributions
ver+0.136
hand+0.118
 department+0.114
 Even+0.112
 surely+0.112
Neg logit contributions
 fru-0.098
 skirts-0.095
 ey-0.092
 ol-0.092
 da-0.092
Tokenold
Token ID727
Feature activation+9.44e-01

Pos logit contributions
ver+0.013
 Even+0.011
 sadly+0.011
rolled+0.011
 department+0.011
Neg logit contributions
 skirts-0.025
 fru-0.025
 ol-0.024
 ey-0.024
 makeup-0.023
Token little
Token ID1310
Feature activation+4.64e-01

Pos logit contributions
ver+0.037
hand+0.033
rolled+0.033
 Even+0.032
 chief+0.032
Neg logit contributions
 skirts-0.028
 fru-0.027
 ey-0.026
 skirt-0.024
 ol-0.024
Token Sus
Token ID8932
Feature activation+2.79e-01

Pos logit contributions
ver+0.020
hand+0.018
rolled+0.017
 chief+0.017
 Even+0.017
Neg logit contributions
 skirts-0.013
 ey-0.013
 fru-0.012
 skirt-0.011
 makeup-0.011
Tokenie
Token ID494
Feature activation-6.70e-01

Pos logit contributions
ver+0.011
hand+0.010
 chief+0.010
 happily+0.010
rolled+0.009
Neg logit contributions
 ey-0.009
 skirts-0.008
 fru-0.008
 skirt-0.007
ems-0.007
Token trapped
Token ID13640
Feature activation+1.40e-01

Pos logit contributions
ver+0.004
hand+0.004
rolled+0.004
 Even+0.004
 chief+0.004
Neg logit contributions
 skirts-0.003
 ey-0.003
 fru-0.003
 prett-0.003
 doing-0.003
Token with
Token ID351
Feature activation-6.11e-01

Pos logit contributions
ver+0.006
 Even+0.005
rolled+0.005
hand+0.005
 chief+0.005
Neg logit contributions
 skirts-0.004
 ey-0.004
 fru-0.003
 doing-0.003
 makeup-0.003
Token the
Token ID262
Feature activation-1.14e-01

Pos logit contributions
 skirts+0.015
 fru+0.014
 clothing+0.013
 sunglasses+0.013
 ey+0.013
Neg logit contributions
ver-0.026
 Together-0.023
 department-0.023
hand-0.023
 Even-0.023
Token rh
Token ID9529
Feature activation+1.95e+00

Pos logit contributions
 ey+0.004
 fru+0.004
 skirts+0.004
 skirt+0.003
 prett+0.003
Neg logit contributions
ver-0.004
hand-0.004
rolled-0.003
 Even-0.003
 happily-0.003
Tokenin
Token ID259
Feature activation+8.63e-01

Pos logit contributions
 Even+0.066
hand+0.065
 Together+0.064
ver+0.063
rolled+0.063
Neg logit contributions
 ey-0.058
 fru-0.054
 skirts-0.052
eking-0.051
b-0.050
Tokenoc
Token ID420
Feature activation+3.93e+00

Pos logit contributions
ver+0.030
hand+0.027
uttered+0.026
rolled+0.026
 Even+0.026
Neg logit contributions
 ey-0.025
 fru-0.025
 da-0.025
 skirts-0.023
 ol-0.023
Tokeneros
Token ID27498
Feature activation+4.81e-01

Pos logit contributions
ver+0.156
 Even+0.129
case+0.128
 happily+0.125
 sadly+0.122
Neg logit contributions
 ey-0.125
 fru-0.116
ution-0.103
 ol-0.103
eking-0.101
Token.
Token ID13
Feature activation-1.21e-01

Pos logit contributions
rolled+0.019
ver+0.019
 Even+0.018
hand+0.018
uttered+0.017
Neg logit contributions
 skirts-0.012
 skirt-0.010
 da-0.010
 fru-0.010
 but-0.010
Token They
Token ID1119
Feature activation+3.99e-02

Pos logit contributions
 fru+0.004
 ey+0.004
 skirts+0.004
---+0.004
 makeup+0.004
Neg logit contributions
ver-0.004
hand-0.003
 chief-0.003
rolled-0.003
 department-0.003
Token looked
Token ID3114
Feature activation-5.14e-01

Pos logit contributions
ver+0.002
hand+0.001
 chief+0.001
 department+0.001
rolled+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
 makeup-0.001
Token for
Token ID329
Feature activation+1.03e+00

Pos logit contributions
 ey+0.019
 skirts+0.019
 fru+0.018
 skirt+0.017
ems+0.016
Neg logit contributions
ver-0.016
hand-0.015
 chief-0.014
rolled-0.014
 Even-0.014
Token
Token ID198
Feature activation+8.05e-01

Pos logit contributions
ver+0.043
hand+0.039
 chief+0.038
 department+0.037
rolled+0.035
Neg logit contributions
 ey-0.064
 skirts-0.062
 fru-0.062
 skirt-0.057
 makeup-0.056
Token
Token ID198
Feature activation+4.77e-01

Pos logit contributions
ver+0.027
 chief+0.026
 department+0.026
hand+0.024
 brigade+0.024
Neg logit contributions
 ey-0.026
 fru-0.025
 skirts-0.024
----0.023
 makeup-0.022
TokenThe
Token ID464
Feature activation+4.44e-01

Pos logit contributions
ver+0.018
 department+0.017
 chief+0.017
uttered+0.016
hand+0.016
Neg logit contributions
 ey-0.013
 skirts-0.013
 fru-0.013
----0.012
 skirt-0.012
Token rh
Token ID9529
Feature activation+2.61e+00

Pos logit contributions
ver+0.016
hand+0.013
uttered+0.013
rolled+0.013
 department+0.013
Neg logit contributions
 ey-0.015
 fru-0.015
 skirts-0.014
 da-0.013
 skirt-0.013
Tokenin
Token ID259
Feature activation+1.12e+00

Pos logit contributions
ver+0.076
hand+0.075
rolled+0.072
 Even+0.069
 department+0.068
Neg logit contributions
 ey-0.099
 fru-0.092
 skirts-0.090
ems-0.082
 skirt-0.082
Tokenoc
Token ID420
Feature activation+4.37e+00

Pos logit contributions
ver+0.035
hand+0.031
uttered+0.030
 department+0.030
rolled+0.029
Neg logit contributions
 fru-0.039
 ey-0.038
 skirts-0.033
 da-0.033
 scar-0.032
Tokeneros
Token ID27498
Feature activation+9.98e-01

Pos logit contributions
ver+0.162
 Even+0.135
case+0.132
rolled+0.129
hand+0.129
Neg logit contributions
 ey-0.151
 fru-0.140
 ol-0.123
 skirts-0.121
ution-0.120
Token nodded
Token ID14464
Feature activation+1.58e-01

Pos logit contributions
ver+0.040
hand+0.038
rolled+0.037
 department+0.036
 tow+0.036
Neg logit contributions
 fru-0.026
 ey-0.024
 skirts-0.024
 skirt-0.022
 makeup-0.020
Token and
Token ID290
Feature activation+2.47e-02

Pos logit contributions
ver+0.005
hand+0.004
 chief+0.004
rolled+0.004
 Even+0.004
Neg logit contributions
 ey-0.006
 skirts-0.006
 fru-0.006
 skirt-0.005
ems-0.005
Token the
Token ID262
Feature activation-7.04e-01

Pos logit contributions
ver+0.001
hand+0.001
 chief+0.001
rolled+0.001
 department+0.001
Neg logit contributions
 fru-0.001
 skirts-0.001
 ey-0.001
 skirt-0.000
 da-0.000
Token little
Token ID1310
Feature activation+1.32e-01

Pos logit contributions
 ey+0.024
 fru+0.023
 skirts+0.023
 skirt+0.021
 makeup+0.020
Neg logit contributions
ver-0.026
hand-0.022
rolled-0.021
 chief-0.021
uttered-0.021
Token all
Token ID477
Feature activation+3.29e-01

Pos logit contributions
ver+0.014
hand+0.014
 chief+0.013
 department+0.012
 Even+0.012
Neg logit contributions
 skirts-0.017
 ey-0.016
 fru-0.016
 skirt-0.016
 sunglasses-0.015
Token o
Token ID267
Feature activation+7.81e-02

Pos logit contributions
ver+0.011
hand+0.010
 chief+0.010
 department+0.009
rolled+0.009
Neg logit contributions
 ey-0.011
 skirts-0.011
 fru-0.011
 skirt-0.010
ems-0.010
Tokeno
Token ID78
Feature activation+2.69e-01

Pos logit contributions
ver+0.003
 chief+0.003
hand+0.003
 sadly+0.003
 department+0.003
Neg logit contributions
 ey-0.002
 skirts-0.002
 fru-0.002
ems-0.002
 skirt-0.002
Tokenhed
Token ID704
Feature activation+8.87e-01

Pos logit contributions
ver+0.009
 chief+0.008
 department+0.008
hand+0.008
 mayor+0.008
Neg logit contributions
 skirts-0.009
 fru-0.009
 ey-0.008
 da-0.008
 skirt-0.008
Token and
Token ID290
Feature activation-1.40e-01

Pos logit contributions
ver+0.030
hand+0.027
 chief+0.026
rolled+0.025
 Even+0.025
Neg logit contributions
 skirts-0.032
 ey-0.031
 fru-0.031
 skirt-0.029
 makeup-0.027
Token ah
Token ID29042
Feature activation+1.33e+00

Pos logit contributions
 skirts+0.005
 ey+0.005
 fru+0.004
 skirt+0.004
 makeup+0.004
Neg logit contributions
ver-0.005
hand-0.005
 chief-0.005
 department-0.004
 Even-0.004
Tokenhed
Token ID704
Feature activation+8.22e-01

Pos logit contributions
ver+0.028
hand+0.024
 chief+0.024
 department+0.022
rolled+0.021
Neg logit contributions
 ey-0.063
 skirts-0.062
 fru-0.061
 skirt-0.057
ems-0.056
Token as
Token ID355
Feature activation-4.40e-01

Pos logit contributions
ver+0.027
hand+0.024
 chief+0.023
rolled+0.022
 Even+0.022
Neg logit contributions
 skirts-0.030
 ey-0.029
 fru-0.029
 skirt-0.027
 makeup-0.026
Token they
Token ID484
Feature activation+7.11e-01

Pos logit contributions
 skirts+0.014
 fru+0.013
 makeup+0.012
 skirt+0.012
 ol+0.011
Neg logit contributions
ver-0.016
rolled-0.015
 chief-0.015
hand-0.015
 Even-0.015
Token looked
Token ID3114
Feature activation+2.49e-01

Pos logit contributions
ver+0.025
hand+0.023
 chief+0.023
 Even+0.022
 department+0.022
Neg logit contributions
 skirts-0.023
 ey-0.022
 fru-0.022
 skirt-0.021
ems-0.020
Token at
Token ID379
Feature activation+2.12e-01

Pos logit contributions
ver+0.008
hand+0.007
 chief+0.007
rolled+0.007
 Even+0.007
Neg logit contributions
 ey-0.009
 skirts-0.009
 fru-0.009
 skirt-0.008
ems-0.008
Token park
Token ID3952
Feature activation-9.30e-01

Pos logit contributions
 skirts+0.028
 fru+0.028
 ey+0.028
ems+0.025
 skirt+0.024
Neg logit contributions
ver-0.031
hand-0.030
 chief-0.029
 Even-0.029
 happily-0.029
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
 skirts+0.030
 ey+0.030
 fru+0.029
 skirt+0.026
 makeup+0.025
Neg logit contributions
ver-0.033
hand-0.031
 chief-0.029
 department-0.029
rolled-0.028
Token Every
Token ID3887
Feature activation+3.35e-02

Pos logit contributions
 ey+0.006
 skirts+0.005
 fru+0.005
 skirt+0.005
 makeup+0.005
Neg logit contributions
ver-0.004
hand-0.003
 chief-0.003
 department-0.003
rolled-0.003
Token day
Token ID1110
Feature activation-3.00e-01

Pos logit contributions
ver+0.002
hand+0.001
 chief+0.001
 department+0.001
rolled+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
 makeup-0.001
Token he
Token ID339
Feature activation+6.85e-01

Pos logit contributions
 ey+0.009
 skirts+0.009
 fru+0.009
 ol+0.008
 skirt+0.008
Neg logit contributions
ver-0.011
hand-0.010
 chief-0.010
 department-0.010
rolled-0.010
Token would
Token ID561
Feature activation+1.24e+00

Pos logit contributions
ver+0.024
hand+0.023
 chief+0.022
 Even+0.021
 department+0.021
Neg logit contributions
 skirts-0.022
 ey-0.022
 fru-0.021
 skirt-0.019
ems-0.019
Token slide
Token ID10649
Feature activation+5.83e-01

Pos logit contributions
ver+0.051
hand+0.049
 chief+0.047
 department+0.046
 brigade+0.044
Neg logit contributions
 ey-0.034
 skirts-0.033
 fru-0.030
 skirt-0.030
 makeup-0.027
Token down
Token ID866
Feature activation+8.89e-01

Pos logit contributions
ver+0.017
hand+0.015
 happily+0.014
 chief+0.014
rolled+0.014
Neg logit contributions
 ey-0.024
 skirts-0.023
 fru-0.023
 skirt-0.021
ems-0.021
Token,
Token ID11
Feature activation+2.87e-01

Pos logit contributions
ver+0.039
 chief+0.035
hand+0.035
 department+0.035
 brigade+0.035
Neg logit contributions
 ey-0.023
 skirts-0.020
 fru-0.019
 ol-0.018
 doing-0.017
Token faster
Token ID5443
Feature activation+5.23e-03

Pos logit contributions
ver+0.011
hand+0.010
 chief+0.010
rolled+0.009
 department+0.009
Neg logit contributions
 ey-0.009
 skirts-0.009
 fru-0.009
 skirt-0.008
ems-0.008
Token and
Token ID290
Feature activation+5.70e-02

Pos logit contributions
 happily+0.000
 quickly+0.000
 safely+0.000
ver+0.000
hand+0.000
Neg logit contributions
 fru-0.000
 ey-0.000
 skirts-0.000
 skirt-0.000
ems-0.000
Token the
Token ID262
Feature activation+3.98e-02

Pos logit contributions
 skirts+0.004
 clothing+0.004
 fru+0.003
 makeup+0.003
 sunglasses+0.003
Neg logit contributions
ver-0.010
 chief-0.009
 department-0.009
ittle-0.009
case-0.008
Token wagon
Token ID31860
Feature activation+5.91e-01

Pos logit contributions
ver+0.002
hand+0.001
 chief+0.001
 Even+0.001
te+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
 sunglasses-0.001
Token as
Token ID355
Feature activation-3.97e-01

Pos logit contributions
ver+0.021
ittle+0.020
 Thief+0.020
 department+0.020
hand+0.019
Neg logit contributions
 but-0.016
 skirts-0.015
 prett-0.015
 skirt-0.014
 than-0.013
Token it
Token ID340
Feature activation+4.46e-01

Pos logit contributions
 skirts+0.010
 pretty+0.008
 ol+0.008
 fru+0.008
 doing+0.008
Neg logit contributions
 Even-0.015
hand-0.015
ishly-0.015
 chief-0.015
 Sadly-0.015
Token drove
Token ID10357
Feature activation+1.70e+00

Pos logit contributions
 chief+0.015
hand+0.015
 Even+0.015
ver+0.015
 mayor+0.014
Neg logit contributions
 skirts-0.013
 fru-0.013
 skirt-0.012
 ey-0.012
 prett-0.011
Token around
Token ID1088
Feature activation+1.22e+00

Pos logit contributions
ver+0.063
 chief+0.058
 Even+0.056
itt+0.056
 department+0.055
Neg logit contributions
 skirts-0.052
 ey-0.046
 fru-0.045
----0.045
 skirt-0.045
Token the
Token ID262
Feature activation+2.29e-01

Pos logit contributions
ver+0.048
hand+0.042
 chief+0.042
 department+0.041
 Even+0.041
Neg logit contributions
 skirts-0.035
 ey-0.035
 fru-0.033
 skirt-0.031
 makeup-0.030
Token garden
Token ID11376
Feature activation-5.07e-01

Pos logit contributions
ver+0.011
uttered+0.009
hand+0.009
te+0.009
 chief+0.009
Neg logit contributions
 ey-0.006
 skirts-0.006
 skirt-0.005
 fru-0.005
 makeup-0.005
Token.
Token ID13
Feature activation-2.89e-01

Pos logit contributions
 skirts+0.014
 ey+0.013
 fru+0.013
 skirt+0.012
 makeup+0.011
Neg logit contributions
ver-0.020
hand-0.018
 chief-0.018
 Even-0.018
rolled-0.018
Token The
Token ID383
Feature activation-1.02e-01

Pos logit contributions
 ey+0.008
 skirts+0.008
 fru+0.007
---+0.007
 makeup+0.007
Neg logit contributions
 chief-0.010
ver-0.010
 department-0.010
hand-0.009
 brigade-0.009
Token tough
Token ID5802
Feature activation-5.96e-01

Pos logit contributions
 skirts+0.003
 ey+0.003
 sunglasses+0.003
 skirt+0.003
 fru+0.003
Neg logit contributions
ver-0.004
hand-0.004
uttered-0.003
te-0.003
 chief-0.003
Token had
Token ID550
Feature activation-7.44e-02

Pos logit contributions
ver+0.003
hand+0.003
 chief+0.003
rolled+0.003
 department+0.003
Neg logit contributions
 skirts-0.003
 ey-0.003
 fru-0.003
 skirt-0.003
ems-0.002
Token made
Token ID925
Feature activation-9.19e-01

Pos logit contributions
 ey+0.003
 skirts+0.003
 fru+0.003
 skirt+0.003
 makeup+0.002
Neg logit contributions
ver-0.002
hand-0.002
 chief-0.002
rolled-0.002
 Even-0.002
Token her
Token ID607
Feature activation+1.78e-01

Pos logit contributions
 skirts+0.031
 ey+0.030
 fru+0.030
 makeup+0.028
 skirt+0.028
Neg logit contributions
ver-0.032
 chief-0.029
hand-0.028
rolled-0.028
 department-0.028
Token mom
Token ID1995
Feature activation-4.45e-01

Pos logit contributions
ver+0.006
hand+0.006
 chief+0.006
 Even+0.005
rolled+0.005
Neg logit contributions
 ey-0.006
 skirts-0.006
 fru-0.006
 skirt-0.005
 makeup-0.005
Token wait
Token ID4043
Feature activation-1.38e+00

Pos logit contributions
 ey+0.017
 skirts+0.017
 fru+0.016
ems+0.015
 skirt+0.015
Neg logit contributions
ver-0.013
hand-0.012
 chief-0.012
 happily-0.012
 sadly-0.012
Token too
Token ID1165
Feature activation+9.38e-01

Pos logit contributions
 ey+0.053
 skirts+0.050
 fru+0.050
 skirt+0.046
ems+0.045
Neg logit contributions
ver-0.042
hand-0.038
 chief-0.037
 happily-0.037
 sadly-0.036
Token long
Token ID890
Feature activation-1.91e-01

Pos logit contributions
ver+0.036
 chief+0.033
hand+0.032
 department+0.032
rolled+0.032
Neg logit contributions
 skirts-0.028
 ey-0.027
 fru-0.026
 skirt-0.024
 makeup-0.023
Token.
Token ID13
Feature activation-7.86e-02

Pos logit contributions
 skirts+0.007
 ey+0.007
 fru+0.006
 skirt+0.006
ems+0.006
Neg logit contributions
ver-0.006
hand-0.006
 chief-0.006
 Even-0.005
rolled-0.005
Token She
Token ID1375
Feature activation+4.56e-01

Pos logit contributions
 skirts+0.002
 fru+0.002
 ey+0.002
 skirt+0.002
 makeup+0.002
Neg logit contributions
ver-0.003
 chief-0.003
hand-0.003
rolled-0.003
 department-0.003
Token felt
Token ID2936
Feature activation-2.38e-01

Pos logit contributions
ver+0.019
hand+0.017
 chief+0.017
 department+0.017
uttered+0.016
Neg logit contributions
 skirts-0.012
 fru-0.012
 skirt-0.011
 ey-0.011
 da-0.010
Token a
Token ID257
Feature activation+4.68e-01

Pos logit contributions
 ey+0.008
 fru+0.008
 skirts+0.008
 skirt+0.007
 makeup+0.007
Neg logit contributions
ver-0.009
hand-0.008
 department-0.008
 chief-0.008
rolled-0.008
Token Ben
Token ID3932
Feature activation-6.34e-01

Pos logit contributions
ver+0.003
 happily+0.003
 sadly+0.003
 Even+0.003
 quickly+0.003
Neg logit contributions
 ey-0.004
 skirts-0.003
 fru-0.003
eking-0.003
reath-0.003
Token shouted
Token ID17293
Feature activation-5.64e-01

Pos logit contributions
 skirts+0.017
 ey+0.017
 fru+0.017
 skirt+0.015
ems+0.014
Neg logit contributions
ver-0.026
hand-0.024
 chief-0.024
rolled-0.023
 department-0.023
Token as
Token ID355
Feature activation-3.23e-02

Pos logit contributions
 skirts+0.012
 skirt+0.011
 makeup+0.011
 fru+0.011
 but+0.010
Neg logit contributions
ver-0.025
rolled-0.024
hand-0.023
itt-0.023
 chief-0.023
Token he
Token ID339
Feature activation+7.46e-01

Pos logit contributions
 ey+0.001
 fru+0.001
 skirts+0.000
 skirt+0.000
 ol+0.000
Neg logit contributions
hand-0.002
rolled-0.002
ver-0.002
 department-0.001
 chief-0.001
Token jumped
Token ID11687
Feature activation-5.09e-01

Pos logit contributions
ver+0.027
hand+0.026
 chief+0.026
 Even+0.024
rolled+0.024
Neg logit contributions
 ey-0.023
 skirts-0.023
 fru-0.022
 skirt-0.020
ems-0.020
Token out
Token ID503
Feature activation+1.08e+00

Pos logit contributions
 ey+0.017
 skirts+0.017
 skirt+0.016
 fru+0.016
 makeup+0.015
Neg logit contributions
ver-0.018
hand-0.016
 chief-0.016
rolled-0.016
 department-0.015
Token from
Token ID422
Feature activation+9.29e-01

Pos logit contributions
ver+0.024
hand+0.020
 chief+0.019
rolled+0.019
 Even+0.017
Neg logit contributions
 ey-0.052
 skirts-0.050
 fru-0.049
 skirt-0.047
 makeup-0.045
Token behind
Token ID2157
Feature activation-3.10e-01

Pos logit contributions
ver+0.031
hand+0.030
 chief+0.029
 happily+0.028
 sadly+0.027
Neg logit contributions
 ey-0.032
 skirts-0.031
 fru-0.031
 skirt-0.028
ems-0.027
Token the
Token ID262
Feature activation+1.83e-01

Pos logit contributions
 ey+0.011
 skirts+0.010
 fru+0.010
 skirt+0.009
 makeup+0.009
Neg logit contributions
ver-0.011
hand-0.010
 chief-0.010
rolled-0.009
 department-0.009
Token tree
Token ID5509
Feature activation+3.21e-01

Pos logit contributions
ver+0.006
hand+0.005
 chief+0.005
 happily+0.005
 Even+0.005
Neg logit contributions
 ey-0.007
 skirts-0.007
 fru-0.007
 skirt-0.006
ems-0.006
Token.
Token ID13
Feature activation+5.22e-02

Pos logit contributions
ver+0.013
hand+0.012
rolled+0.011
 chief+0.011
 Even+0.011
Neg logit contributions
 ey-0.009
 skirts-0.009
 fru-0.008
 skirt-0.008
 makeup-0.007
Token about
Token ID546
Feature activation+1.37e+00

Pos logit contributions
ver+0.023
hand+0.022
rolled+0.021
 chief+0.020
 department+0.019
Neg logit contributions
 skirts-0.025
 ey-0.025
 fru-0.024
ems-0.022
 skirt-0.022
Token the
Token ID262
Feature activation+6.51e-01

Pos logit contributions
ver+0.047
hand+0.043
 chief+0.042
 happily+0.040
rolled+0.040
Neg logit contributions
 ey-0.048
 skirts-0.046
 fru-0.045
 skirt-0.042
ems-0.040
Token colors
Token ID7577
Feature activation+3.02e-01

Pos logit contributions
ver+0.024
hand+0.023
 chief+0.023
 happily+0.022
 department+0.022
Neg logit contributions
 ey-0.019
 skirts-0.019
 fru-0.018
ems-0.017
 skirt-0.016
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
ver+0.009
hand+0.008
 chief+0.008
rolled+0.008
 Even+0.008
Neg logit contributions
 ey-0.011
 skirts-0.011
 fru-0.011
 skirt-0.010
 makeup-0.010
Token We
Token ID775
Feature activation+1.09e+00

Pos logit contributions
ver+0.008
hand+0.008
 chief+0.008
rolled+0.008
 happily+0.007
Neg logit contributions
 ey-0.008
 skirts-0.008
 fru-0.008
ems-0.007
 makeup-0.007
Token just
Token ID655
Feature activation+4.98e-01

Pos logit contributions
hand+0.044
ver+0.042
rolled+0.039
 chief+0.039
 department+0.039
Neg logit contributions
 fru-0.029
 skirts-0.028
 ey-0.027
ems-0.026
 makeup-0.025
Token want
Token ID765
Feature activation-3.73e-01

Pos logit contributions
ver+0.018
hand+0.016
 chief+0.016
rolled+0.015
 department+0.015
Neg logit contributions
 ey-0.016
 skirts-0.016
 fru-0.016
 skirt-0.014
ems-0.014
Token to
Token ID284
Feature activation-2.04e-01

Pos logit contributions
 skirts+0.013
 ey+0.013
 fru+0.013
 skirt+0.012
 makeup+0.012
Neg logit contributions
ver-0.013
hand-0.011
 chief-0.011
rolled-0.011
 Even-0.010
Token eat
Token ID4483
Feature activation-3.95e-01

Pos logit contributions
 ey+0.006
 skirts+0.006
 fru+0.006
 skirt+0.006
 makeup+0.006
Neg logit contributions
ver-0.008
hand-0.007
 chief-0.007
 department-0.007
uttered-0.006
Token the
Token ID262
Feature activation+3.53e-01

Pos logit contributions
 ey+0.015
 skirts+0.015
 fru+0.014
 skirt+0.013
ems+0.013
Neg logit contributions
ver-0.012
hand-0.011
 chief-0.011
 happily-0.010
 sadly-0.010
Token ice
Token ID4771
Feature activation-1.03e+00

Pos logit contributions
ver+0.011
hand+0.011
 chief+0.010
 happily+0.010
rolled+0.010
Neg logit contributions
 ey-0.013
 skirts-0.012
ems-0.011
 fru-0.011
 skirt-0.011
Token a
Token ID257
Feature activation+2.80e-01

Pos logit contributions
 ey+0.023
 skirts+0.022
 fru+0.021
 skirt+0.020
 makeup+0.019
Neg logit contributions
ver-0.035
hand-0.032
 department-0.032
 chief-0.031
uttered-0.030
Token friend
Token ID1545
Feature activation+2.30e-01

Pos logit contributions
ver+0.012
hand+0.011
rolled+0.010
 Even+0.010
uttered+0.010
Neg logit contributions
 skirts-0.008
 ey-0.007
 fru-0.007
 skirt-0.007
 makeup-0.006
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
ver+0.006
hand+0.005
 happily+0.005
 chief+0.005
 sadly+0.005
Neg logit contributions
 ey-0.010
 fru-0.010
 skirts-0.010
 skirt-0.009
ems-0.008
Token But
Token ID887
Feature activation+3.40e-01

Pos logit contributions
ver+0.003
hand+0.003
 chief+0.003
 sadly+0.003
 happily+0.003
Neg logit contributions
 ey-0.004
 fru-0.004
 skirts-0.004
 skirt-0.003
 makeup-0.003
Token the
Token ID262
Feature activation-8.41e-01

Pos logit contributions
ver+0.012
hand+0.012
 chief+0.011
 department+0.011
 Even+0.011
Neg logit contributions
 ey-0.010
 skirts-0.010
 fru-0.009
 skirt-0.009
 makeup-0.008
Token balloon
Token ID21190
Feature activation+3.67e-01

Pos logit contributions
 skirts+0.028
 ey+0.027
 fru+0.027
 skirt+0.027
 sunglasses+0.025
Neg logit contributions
ver-0.031
hand-0.028
 Even-0.027
rolled-0.026
 chief-0.026
Token was
Token ID373
Feature activation+2.59e-01

Pos logit contributions
ver+0.012
hand+0.012
 Even+0.011
 chief+0.011
rolled+0.011
Neg logit contributions
 fru-0.012
 ey-0.012
 skirts-0.012
 skirt-0.011
 makeup-0.010
Token so
Token ID523
Feature activation-8.27e-01

Pos logit contributions
ver+0.009
hand+0.009
rolled+0.008
 chief+0.008
 Even+0.008
Neg logit contributions
 skirts-0.009
 ey-0.009
 fru-0.009
 skirt-0.008
 makeup-0.008
Token big
Token ID1263
Feature activation+7.83e-01

Pos logit contributions
 fru+0.021
 ey+0.020
 skirts+0.020
 pretty+0.017
 prett+0.017
Neg logit contributions
hand-0.035
ver-0.035
 chief-0.033
 department-0.032
 Even-0.031
Token and
Token ID290
Feature activation-6.55e-01

Pos logit contributions
ver+0.020
hand+0.017
 chief+0.017
 happily+0.017
 Even+0.016
Neg logit contributions
 ey-0.035
 skirts-0.033
 fru-0.033
 skirt-0.031
ems-0.029
Token it
Token ID340
Feature activation-5.50e-01

Pos logit contributions
 ey+0.022
 skirts+0.021
 fru+0.020
 skirt+0.018
ems+0.018
Neg logit contributions
ver-0.024
hand-0.022
 chief-0.021
 happily-0.021
 sadly-0.020
Token.
Token ID13
Feature activation+1.22e-01

Pos logit contributions
rolled+0.014
hand+0.014
ver+0.014
 department+0.014
uttered+0.014
Neg logit contributions
 skirts-0.005
 but-0.004
 ey-0.004
 fru-0.004
 than-0.004
Token She
Token ID1375
Feature activation+3.43e-01

Pos logit contributions
ver+0.003
hand+0.003
 chief+0.003
 Even+0.003
 happily+0.003
Neg logit contributions
 ey-0.005
 skirts-0.005
 fru-0.005
 skirt-0.004
ems-0.004
Token climbs
Token ID34332
Feature activation+2.63e-01

Pos logit contributions
ver+0.016
hand+0.015
rolled+0.014
 chief+0.014
te+0.014
Neg logit contributions
 ey-0.009
 skirts-0.008
 fru-0.008
 skirt-0.007
 scar-0.007
Token out
Token ID503
Feature activation+9.02e-01

Pos logit contributions
ver+0.010
 chief+0.009
 Even+0.008
 department+0.008
rolled+0.008
Neg logit contributions
 skirts-0.009
 ey-0.008
 fru-0.008
 jam-0.008
 ol-0.008
Token.
Token ID13
Feature activation-2.71e-01

Pos logit contributions
ver+0.024
 chief+0.021
hand+0.021
rolled+0.020
 Even+0.019
Neg logit contributions
 ey-0.038
 skirts-0.038
 fru-0.036
 skirt-0.035
 makeup-0.033
Token She
Token ID1375
Feature activation+2.14e-01

Pos logit contributions
 ey+0.010
 skirts+0.010
 fru+0.009
 skirt+0.009
 makeup+0.008
Neg logit contributions
ver-0.009
hand-0.008
 chief-0.008
rolled-0.007
 department-0.007
Token is
Token ID318
Feature activation+7.99e-02

Pos logit contributions
ver+0.010
hand+0.010
 chief+0.009
rolled+0.009
te+0.009
Neg logit contributions
 ey-0.005
 skirts-0.005
 fru-0.005
 scar-0.004
 jam-0.004
Token wet
Token ID9583
Feature activation-2.73e-01

Pos logit contributions
ver+0.003
hand+0.003
 chief+0.002
 Even+0.002
rolled+0.002
Neg logit contributions
 ey-0.003
 skirts-0.003
 fru-0.003
 skirt-0.002
 makeup-0.002
Token too
Token ID1165
Feature activation+3.88e-02

Pos logit contributions
 ey+0.009
 skirts+0.009
 fru+0.009
 skirt+0.008
 makeup+0.008
Neg logit contributions
ver-0.009
hand-0.008
rolled-0.008
 chief-0.008
 Even-0.008
Token.
Token ID13
Feature activation-1.50e-01

Pos logit contributions
hand+0.002
ver+0.002
rolled+0.002
 chief+0.001
 department+0.001
Neg logit contributions
 skirts-0.001
 fru-0.001
 ey-0.001
 skirt-0.001
 jam-0.001
Token
Token ID198
Feature activation-1.79e-01

Pos logit contributions
 ey+0.007
 skirts+0.006
 fru+0.006
 skirt+0.006
ems+0.006
Neg logit contributions
ver-0.004
 Even-0.003
hand-0.003
 chief-0.003
 happily-0.003
Token young
Token ID1862
Feature activation+4.84e-01

Pos logit contributions
ver+0.011
hand+0.010
 Even+0.010
rolled+0.010
 chief+0.010
Neg logit contributions
 ey-0.009
 fru-0.009
 skirts-0.008
 skirt-0.008
 makeup-0.007
Token boy
Token ID2933
Feature activation+6.41e-01

Pos logit contributions
ver+0.020
hand+0.019
rolled+0.019
uttered+0.018
 Even+0.018
Neg logit contributions
 fru-0.013
 ey-0.013
 skirts-0.013
 skirt-0.012
 da-0.011
Token in
Token ID287
Feature activation-3.99e-02

Pos logit contributions
ver+0.023
hand+0.020
 chief+0.020
 Even+0.020
 department+0.019
Neg logit contributions
 ey-0.021
 skirts-0.021
 fru-0.019
 skirt-0.019
 makeup-0.018
Token the
Token ID262
Feature activation-3.07e-01

Pos logit contributions
 ey+0.001
 skirts+0.001
 fru+0.001
 skirt+0.001
 makeup+0.001
Neg logit contributions
ver-0.001
hand-0.001
 chief-0.001
rolled-0.001
 department-0.001
Token ocean
Token ID9151
Feature activation-6.01e-01

Pos logit contributions
 ey+0.010
 skirts+0.010
 fru+0.010
ems+0.009
 skirt+0.009
Neg logit contributions
ver-0.011
hand-0.010
 chief-0.010
 happily-0.010
 Even-0.009
Token.
Token ID13
Feature activation-2.09e-01

Pos logit contributions
 ey+0.020
 skirts+0.020
 fru+0.019
 skirt+0.018
 makeup+0.017
Neg logit contributions
ver-0.021
hand-0.019
 chief-0.018
 Even-0.018
rolled-0.018
Token The
Token ID383
Feature activation+1.56e-01

Pos logit contributions
 ey+0.007
 fru+0.006
 skirts+0.006
 ol+0.005
---+0.005
Neg logit contributions
ver-0.007
hand-0.007
 chief-0.007
te-0.006
 department-0.006
Token sailor
Token ID43272
Feature activation-2.86e-02

Pos logit contributions
ver+0.006
hand+0.006
rolled+0.006
 Even+0.006
uttered+0.006
Neg logit contributions
 ey-0.004
 skirts-0.004
 fru-0.004
 skirt-0.004
 prett-0.004
Token was
Token ID373
Feature activation+4.44e-01

Pos logit contributions
 fru+0.001
 skirts+0.000
 but+0.000
 doing+0.000
 da+0.000
Neg logit contributions
hand-0.001
ver-0.001
itt-0.001
uggle-0.001
 Even-0.001
Token in
Token ID287
Feature activation+3.35e-02

Pos logit contributions
ver+0.018
hand+0.018
 department+0.016
 brigade+0.016
 Even+0.016
Neg logit contributions
 doing-0.012
 skirts-0.011
 fru-0.011
 ey-0.011
 prett-0.010
Token danger
Token ID3514
Feature activation-1.27e-03

Pos logit contributions
ver+0.001
hand+0.001
 chief+0.001
rolled+0.001
 department+0.001
Neg logit contributions
 ey-0.001
 skirts-0.001
 fru-0.001
 skirt-0.001
 makeup-0.001
Token girl
Token ID2576
Feature activation+6.78e-03

Pos logit contributions
ver+0.011
hand+0.011
rolled+0.010
 chief+0.010
 Even+0.010
Neg logit contributions
 ey-0.006
 skirts-0.006
 fru-0.006
 skirt-0.005
 makeup-0.005
Token named
Token ID3706
Feature activation+3.48e-01

Pos logit contributions
ver+0.000
hand+0.000
 chief+0.000
 department+0.000
rolled+0.000
Neg logit contributions
 ey-0.000
 skirts-0.000
 fru-0.000
 skirt-0.000
 makeup-0.000
Token Amy
Token ID14235
Feature activation-1.89e-01

Pos logit contributions
ver+0.015
hand+0.014
 chief+0.014
 department+0.013
rolled+0.013
Neg logit contributions
 ey-0.009
 skirts-0.009
 fru-0.009
 skirt-0.008
 makeup-0.008
Token went
Token ID1816
Feature activation+1.57e-01

Pos logit contributions
 ey+0.008
 skirts+0.008
 fru+0.008
 skirt+0.007
ems+0.007
Neg logit contributions
ver-0.005
hand-0.004
 happily-0.004
 chief-0.004
 Even-0.004
Token for
Token ID329
Feature activation-2.02e-01

Pos logit contributions
ver+0.005
hand+0.004
 chief+0.004
 Even+0.004
rolled+0.004
Neg logit contributions
 ey-0.006
 skirts-0.006
 fru-0.006
 skirt-0.006
 makeup-0.005
Token a
Token ID257
Feature activation+5.16e-02

Pos logit contributions
 ey+0.011
 fru+0.010
 skirts+0.010
ems+0.010
 skirt+0.009
Neg logit contributions
ver-0.003
hand-0.003
 happily-0.003
 quickly-0.002
 safely-0.002
Token walk
Token ID2513
Feature activation-5.12e-01

Pos logit contributions
ver+0.002
hand+0.002
 chief+0.002
rolled+0.002
 Even+0.002
Neg logit contributions
 ey-0.002
 skirts-0.002
 fru-0.002
 skirt-0.001
ems-0.001
Token with
Token ID351
Feature activation-5.09e-01

Pos logit contributions
 skirts+0.017
 ey+0.016
 fru+0.016
 skirt+0.015
 makeup+0.015
Neg logit contributions
ver-0.018
hand-0.016
 chief-0.016
 department-0.016
 Even-0.015
Token her
Token ID607
Feature activation-1.73e-01

Pos logit contributions
 ey+0.014
 fru+0.013
 skirts+0.013
ems+0.012
 skirt+0.011
Neg logit contributions
ver-0.020
hand-0.019
 happily-0.019
 chief-0.019
 Even-0.019
Token mom
Token ID1995
Feature activation-9.33e-01

Pos logit contributions
 ey+0.008
 skirts+0.008
 fru+0.008
 skirt+0.007
ems+0.007
Neg logit contributions
ver-0.004
hand-0.003
 chief-0.003
 happily-0.003
rolled-0.003
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
 ey+0.045
 fru+0.043
 skirts+0.040
 disl+0.038
ems+0.037
Neg logit contributions
ver-0.022
 happily-0.019
hand-0.019
 quickly-0.018
 chief-0.018
Token they
Token ID484
Feature activation+8.16e-01

Pos logit contributions
 ey+0.015
 skirts+0.014
 fru+0.014
 skirt+0.013
ems+0.012
Neg logit contributions
ver-0.017
hand-0.016
 chief-0.016
 happily-0.015
 Even-0.015
Token could
Token ID714
Feature activation+7.03e-01

Pos logit contributions
hand+0.035
ver+0.034
 chief+0.034
rolled+0.033
 Even+0.033
Neg logit contributions
 skirts-0.019
 fru-0.016
----0.015
 skirt-0.015
 ey-0.015
Token play
Token ID711
Feature activation+3.11e-01

Pos logit contributions
ver+0.032
year+0.031
hand+0.030
 chief+0.030
uttered+0.029
Neg logit contributions
 wear-0.013
 skirts-0.013
 skirt-0.012
 fru-0.012
 ey-0.012
Token together
Token ID1978
Feature activation+1.12e-01

Pos logit contributions
ver+0.008
hand+0.007
 chief+0.007
 happily+0.007
 sadly+0.006
Neg logit contributions
 ey-0.014
 skirts-0.013
 fru-0.013
 skirt-0.012
ems-0.012
Token and
Token ID290
Feature activation+2.33e-01

Pos logit contributions
ver+0.004
hand+0.004
rolled+0.003
 chief+0.003
 department+0.003
Neg logit contributions
 skirts-0.004
 ey-0.004
 fru-0.003
 skirt-0.003
 makeup-0.003
Token be
Token ID307
Feature activation-2.33e+00

Pos logit contributions
ver+0.007
hand+0.007
 chief+0.007
 happily+0.007
 sadly+0.006
Neg logit contributions
 ey-0.008
 skirts-0.008
 fru-0.008
 skirt-0.007
ems-0.007
Token happy
Token ID3772
Feature activation-6.93e-03

Pos logit contributions
 ey+0.083
 skirts+0.078
 fru+0.076
 skirt+0.070
ems+0.068
Neg logit contributions
ver-0.079
hand-0.072
 chief-0.071
 happily-0.071
 sadly-0.068
Token.
Token ID13
Feature activation+6.48e-03

Pos logit contributions
 ey+0.000
 skirts+0.000
 fru+0.000
 skirt+0.000
 makeup+0.000
Neg logit contributions
ver-0.000
hand-0.000
 chief-0.000
rolled-0.000
 Even-0.000
Token She
Token ID1375
Feature activation+1.23e-01

Pos logit contributions
ver+0.000
hand+0.000
 Even+0.000
 chief+0.000
 happily+0.000
Neg logit contributions
 ey-0.000
 skirts-0.000
 fru-0.000
 skirt-0.000
ems-0.000
Token hugged
Token ID41130
Feature activation+3.74e-01

Pos logit contributions
ver+0.005
hand+0.004
 chief+0.004
rolled+0.004
 department+0.004
Neg logit contributions
 ey-0.004
 skirts-0.004
 fru-0.004
 skirt-0.003
ems-0.003
Token the
Token ID262
Feature activation-4.01e-01

Pos logit contributions
ver+0.015
hand+0.014
 chief+0.014
rolled+0.014
 department+0.013
Neg logit contributions
 skirts-0.011
 ey-0.011
 fru-0.010
 skirt-0.010
 makeup-0.009
Token bald
Token ID28273
Feature activation-2.35e-01

Pos logit contributions
 ey+0.006
 fru+0.006
 skirts+0.006
 skirt+0.005
---+0.005
Neg logit contributions
ver-0.004
 happily-0.004
hand-0.004
 chief-0.004
 quickly-0.003
Token old
Token ID1468
Feature activation-6.88e-01

Pos logit contributions
 ey+0.007
 skirts+0.007
 fru+0.007
 skirt+0.006
ems+0.006
Neg logit contributions
ver-0.009
hand-0.008
 chief-0.008
rolled-0.008
 happily-0.008
Token men
Token ID1450
Feature activation-3.68e-01

Pos logit contributions
 ey+0.023
 skirts+0.022
 fru+0.021
 skirt+0.019
ems+0.019
Neg logit contributions
ver-0.025
hand-0.023
 chief-0.022
 happily-0.022
 Even-0.021
Token should
Token ID815
Feature activation+7.52e-01

Pos logit contributions
 ey+0.013
 skirts+0.012
 fru+0.012
 skirt+0.011
ems+0.011
Neg logit contributions
ver-0.012
hand-0.011
 chief-0.011
rolled-0.011
 Even-0.010
Token not
Token ID407
Feature activation+3.65e-01

Pos logit contributions
ver+0.027
hand+0.026
 chief+0.025
 department+0.025
rolled+0.024
Neg logit contributions
 ey-0.023
 skirts-0.023
 fru-0.021
 skirt-0.021
 makeup-0.020
Token be
Token ID307
Feature activation-1.92e+00

Pos logit contributions
ver+0.014
hand+0.013
 chief+0.012
rolled+0.012
 department+0.012
Neg logit contributions
 ey-0.011
 skirts-0.011
 fru-0.010
 skirt-0.010
 makeup-0.009
Token afraid
Token ID7787
Feature activation+4.60e-01

Pos logit contributions
 ey+0.067
 skirts+0.065
 fru+0.063
 skirt+0.058
ems+0.056
Neg logit contributions
ver-0.066
hand-0.060
 chief-0.059
 happily-0.056
rolled-0.056
Token to
Token ID284
Feature activation-4.82e-01

Pos logit contributions
ver+0.011
hand+0.010
 chief+0.010
rolled+0.009
 Even+0.009
Neg logit contributions
 skirts-0.020
 ey-0.020
 fru-0.019
 skirt-0.018
 makeup-0.018
Token go
Token ID467
Feature activation-1.58e-01

Pos logit contributions
 ey+0.017
 skirts+0.016
 fru+0.016
 skirt+0.014
ems+0.014
Neg logit contributions
ver-0.017
hand-0.015
 chief-0.015
 happily-0.014
 Even-0.014
Token out
Token ID503
Feature activation+7.50e-01

Pos logit contributions
 ey+0.006
 skirts+0.006
 fru+0.006
 skirt+0.005
 makeup+0.005
Neg logit contributions
ver-0.005
hand-0.004
 chief-0.004
 Even-0.004
rolled-0.004
Token and
Token ID290
Feature activation+8.86e-01

Pos logit contributions
ver+0.022
hand+0.020
 chief+0.019
rolled+0.018
 Even+0.018
Neg logit contributions
 ey-0.029
 skirts-0.029
 fru-0.028
 skirt-0.026
ems-0.025
Tokented
Token ID1513
Feature activation+1.61e+00

Pos logit contributions
 skirts+0.006
 fru+0.006
 ey+0.006
 skirt+0.005
 sunglasses+0.005
Neg logit contributions
ver-0.007
 chief-0.007
case-0.007
 department-0.007
 Even-0.006
Token the
Token ID262
Feature activation+3.00e-01

Pos logit contributions
ver+0.063
hand+0.057
 department+0.057
 chief+0.056
rolled+0.055
Neg logit contributions
 skirts-0.045
 ey-0.044
 fru-0.043
 skirt-0.040
 ol-0.039
Token rabbit
Token ID22746
Feature activation+3.40e-01

Pos logit contributions
ver+0.009
hand+0.008
 chief+0.008
 happily+0.008
 department+0.008
Neg logit contributions
 ey-0.012
 skirts-0.011
 fru-0.011
ems-0.010
 skirt-0.010
Token softly
Token ID26625
Feature activation+9.17e-01

Pos logit contributions
ver+0.012
hand+0.011
 chief+0.010
rolled+0.010
 department+0.010
Neg logit contributions
 skirts-0.012
 ey-0.011
 fru-0.011
 skirt-0.011
 makeup-0.010
Token.
Token ID13
Feature activation-2.32e-03

Pos logit contributions
ver+0.027
hand+0.025
 chief+0.024
 happily+0.024
 sadly+0.023
Neg logit contributions
 ey-0.036
 skirts-0.035
 fru-0.034
 skirt-0.031
ems-0.030
Token To
Token ID1675
Feature activation-1.48e+00

Pos logit contributions
 fru+0.000
 ey+0.000
 skirts+0.000
 ol+0.000
 makeup+0.000
Neg logit contributions
ver-0.000
 chief-0.000
hand-0.000
te-0.000
 department-0.000
Token his
Token ID465
Feature activation+6.26e-01

Pos logit contributions
 ey+0.048
 skirts+0.047
 fru+0.046
 skirt+0.042
ems+0.040
Neg logit contributions
ver-0.053
hand-0.050
 chief-0.048
 department-0.046
rolled-0.046
Token surprise
Token ID5975
Feature activation-1.27e+00

Pos logit contributions
ver+0.027
 chief+0.024
hand+0.023
rolled+0.023
 department+0.022
Neg logit contributions
 ey-0.018
 skirts-0.017
 skirt-0.016
 fru-0.016
 makeup-0.014
Token,
Token ID11
Feature activation+2.31e-01

Pos logit contributions
 ey+0.053
 skirts+0.052
 fru+0.050
 skirt+0.047
ems+0.046
Neg logit contributions
ver-0.035
hand-0.031
 chief-0.030
 happily-0.029
 sadly-0.028
Token the
Token ID262
Feature activation-4.29e-01

Pos logit contributions
hand+0.009
ver+0.009
 chief+0.009
rolled+0.009
 department+0.009
Neg logit contributions
 fru-0.006
 ey-0.006
 skirts-0.005
 skirt-0.005
 ol-0.005
Token rabbit
Token ID22746
Feature activation-2.46e-01

Pos logit contributions
 ey+0.016
 skirts+0.015
 fru+0.015
 skirt+0.013
ems+0.013
Neg logit contributions
ver-0.014
hand-0.013
 chief-0.013
 happily-0.012
 Even-0.012
Token he
Token ID339
Feature activation-3.62e-01

Pos logit contributions
ver+0.003
hand+0.003
rolled+0.003
 chief+0.003
 Even+0.003
Neg logit contributions
 skirts-0.003
 fru-0.003
 ey-0.003
 skirt-0.003
ems-0.003
Token had
Token ID550
Feature activation-5.91e-01

Pos logit contributions
 fru+0.008
 skirts+0.007
 prett+0.006
 skirt+0.006
 sunglasses+0.006
Neg logit contributions
hand-0.016
ver-0.015
itt-0.015
rolled-0.014
 Even-0.014
Token to
Token ID284
Feature activation-1.11e+00

Pos logit contributions
 skirts+0.023
 ey+0.023
 fru+0.023
 skirt+0.021
 makeup+0.021
Neg logit contributions
ver-0.017
hand-0.015
 chief-0.015
rolled-0.014
 department-0.014
Token leave
Token ID2666
Feature activation+4.35e-01

Pos logit contributions
 ey+0.036
 skirts+0.035
 fru+0.034
 skirt+0.032
 makeup+0.031
Neg logit contributions
ver-0.040
hand-0.037
 chief-0.036
 department-0.035
rolled-0.035
Token it
Token ID340
Feature activation-7.73e-02

Pos logit contributions
ver+0.015
hand+0.014
 chief+0.013
rolled+0.013
 department+0.013
Neg logit contributions
 ey-0.014
 skirts-0.014
 fru-0.014
 skirt-0.012
 makeup-0.012
Token be
Token ID307
Feature activation-2.50e+00

Pos logit contributions
 ey+0.003
 skirts+0.002
 fru+0.002
 skirt+0.002
 makeup+0.002
Neg logit contributions
ver-0.003
hand-0.003
 chief-0.002
rolled-0.002
 Even-0.002
Token.
Token ID13
Feature activation-4.36e-02

Pos logit contributions
 ey+0.097
 skirts+0.089
 fru+0.087
 skirt+0.081
ems+0.079
Neg logit contributions
ver-0.079
 happily-0.072
hand-0.071
 chief-0.070
 sadly-0.068
Token
Token ID198
Feature activation-1.70e-01

Pos logit contributions
 ey+0.002
 skirts+0.002
 fru+0.002
 skirt+0.002
ems+0.001
Neg logit contributions
ver-0.001
hand-0.001
 chief-0.001
 department-0.001
 happily-0.001
Token
Token ID198
Feature activation-1.86e-01

Pos logit contributions
 ey+0.007
 skirts+0.006
 fru+0.006
 skirt+0.006
ems+0.006
Neg logit contributions
ver-0.005
hand-0.004
 chief-0.004
 department-0.004
rolled-0.004
TokenThat
Token ID2504
Feature activation+1.07e-01

Pos logit contributions
 ey+0.007
 skirts+0.007
 fru+0.007
 skirt+0.006
 makeup+0.006
Neg logit contributions
ver-0.006
hand-0.005
 chief-0.005
 Even-0.005
rolled-0.005
Token night
Token ID1755
Feature activation-7.91e-01

Pos logit contributions
ver+0.005
hand+0.004
rolled+0.004
 chief+0.004
 department+0.004
Neg logit contributions
 skirts-0.003
 ey-0.003
 fru-0.003
 skirt-0.003
ems-0.002
Token day
Token ID1110
Feature activation-7.00e-01

Pos logit contributions
ver+0.037
 happily+0.033
 chief+0.033
hand+0.033
 Even+0.032
Neg logit contributions
 ey-0.037
 skirts-0.036
 fru-0.034
ems-0.030
 skirt-0.030
Token on
Token ID319
Feature activation+1.14e+00

Pos logit contributions
 ey+0.024
 skirts+0.023
 fru+0.022
 skirt+0.021
ems+0.020
Neg logit contributions
ver-0.024
hand-0.022
 chief-0.022
rolled-0.021
 department-0.021
Token,
Token ID11
Feature activation+1.14e-01

Pos logit contributions
ver+0.031
hand+0.028
 chief+0.027
 happily+0.026
 Even+0.025
Neg logit contributions
 ey-0.048
 skirts-0.047
 fru-0.046
 skirt-0.043
ems-0.042
Token Tim
Token ID5045
Feature activation-4.94e-01

Pos logit contributions
ver+0.004
hand+0.004
 chief+0.004
rolled+0.003
 department+0.003
Neg logit contributions
 skirts-0.004
 fru-0.004
 ey-0.004
 ol-0.003
 makeup-0.003
Token and
Token ID290
Feature activation-7.72e-01

Pos logit contributions
 ey+0.018
 skirts+0.017
 fru+0.017
 skirt+0.016
ems+0.015
Neg logit contributions
ver-0.016
hand-0.015
 chief-0.014
rolled-0.014
 department-0.013
Token Sue
Token ID26089
Feature activation-1.66e+00

Pos logit contributions
 ey+0.029
 skirts+0.028
 fru+0.027
 skirt+0.025
ems+0.024
Neg logit contributions
ver-0.025
hand-0.023
 chief-0.022
 happily-0.021
 Even-0.021
Token would
Token ID561
Feature activation+9.26e-01

Pos logit contributions
 skirts+0.052
 ey+0.050
 fru+0.049
 skirt+0.046
ems+0.046
Neg logit contributions
hand-0.059
ver-0.058
 chief-0.052
 department-0.051
rolled-0.051
Token meet
Token ID1826
Feature activation-2.18e-01

Pos logit contributions
ver+0.037
hand+0.035
 chief+0.032
keeper+0.031
 department+0.031
Neg logit contributions
 ey-0.027
 skirts-0.027
 fru-0.024
 skirt-0.024
ems-0.023
Token every
Token ID790
Feature activation+7.24e-03

Pos logit contributions
 skirts+0.007
 ey+0.007
 fru+0.007
 skirt+0.007
 da+0.006
Neg logit contributions
ver-0.007
hand-0.007
rolled-0.007
 chief-0.006
 tow-0.006
Token night
Token ID1755
Feature activation+7.63e-01

Pos logit contributions
ver+0.000
hand+0.000
rolled+0.000
 Even+0.000
 chief+0.000
Neg logit contributions
 ey-0.000
 skirts-0.000
 fru-0.000
 skirt-0.000
 makeup-0.000
Token to
Token ID284
Feature activation-3.61e-01

Pos logit contributions
ver+0.023
hand+0.021
 chief+0.020
 happily+0.019
rolled+0.019
Neg logit contributions
 ey-0.030
 skirts-0.029
 fru-0.028
 skirt-0.026
ems-0.025