TOP ACTIVATIONS
MAX = 0.133

the same thing . Everyone they asked said there was no
with their toys . They also made some new friends .
discussing their images . They even found a pretty butterfly and
made Lily smile . They also taught her some moves .
around the room . He even flew it around his grandma
in their basket . They also hang some pictures and drawings
and a doll . They also liked to look at the
to the music . They even stayed and danced around the
each of them . She even put on a little note
for fixing it . They also said sorry to Aunt ie
them . They also realized that pengu ins were
ia and Ben smiled . They thanked Mom and took their
with her coins . She even had enough money for a
about all the fun things they would do . They were
lots of fun . They even found a peaceful solution to
on the walls . She also liked the food , especially
the right place . They even made a group of sticks
and a slide . They also had a flashlight that made
and family , and how he could be more thoughtful to
around the block . He even waved to the neighbors as

MIN ACTIVATIONS
MIN = -0.136

good friends and share the cr ay ons and the paper
They decide to share the cr ay ons . They color
it reapp ear on the h anger . <|endoftext|> Tom and
he decided to remove the seaw eed from the water so
to draw and shared the cr ay ons . They were
go with a stranger . Str angers can be bad and
still have to remove the cr ay on marks . White
book ! You spoil the cr ay ons ! You spoil
they say goodbye to the oct opus . They hug it
make the waiter drop the pizz as . They said sorry
not like to share his cr ay ons with his sister
something new with the melted cr ay ons . Do you
stretches or hop on the tr amp oline . Everyone at
him if he took her cr ay ons . He said
and put it on the h anger . The sock stays
, and I shared my cr ay ons with Ben .
They tried to get the oct opus off Tom , but
'm trying to get the cr ay ons from the cabinet
he wanted to keep the oct opus anyway . " I
on Tom and snatched the fl ute from his hand .

INTERVAL 0.066 - 0.133
CONTAINS 3.242%

a beautiful bird . She had colorful feathers of all textures
He was so excited ! He grabbed the bone and ran
tore open the envelope . He pulled out a small wrapped
all free to take . She quickly grabbed the expensive book
be a butterfly , so they fl uttered their arms and

INTERVAL -0.002 - 0.066
CONTAINS 47.432%

one was around . He looked around and saw a big
best friends from that day on . The
The mill had a wheel that turned and made noise .
to tending the garden , knowing that the hook would be
His parents said that they would try to open the chest

INTERVAL -0.069 - -0.002
CONTAINS 47.685%

L ily shook her head . She did not want
lost the key ." B enny thought for
Sue 's house . " Look , Sue !
bathrooms and d usted the windows . Eventually
the nice walk in the park . At the

INTERVAL -0.136 - -0.069
CONTAINS 1.641%

wouldn 't fall off . T eddy asked Rabbit
to climb it ! Slow ly , step by
is a balloon ." They ran to the big
it ! Go away !" The twins were scared
't hurt you ." He takes them out of
Token the
Token ID262
Feature activation+4.56e-02

Pos logit contributions
 pretended+0.112
 built+0.109
 buried+0.108
 found+0.105
wed+0.104
Neg logit contributions
arl-0.163
ay-0.150
 Today-0.149
 Nice-0.145
andel-0.140
Token same
Token ID976
Feature activation+4.69e-02

Pos logit contributions
 pretended+0.081
 found+0.080
 put+0.079
 built+0.079
 buried+0.077
Neg logit contributions
arl-0.091
ay-0.085
 Today-0.083
 Nice-0.081
andel-0.078
Token thing
Token ID1517
Feature activation+1.35e-02

Pos logit contributions
 pretended+0.089
 built+0.086
 found+0.086
 buried+0.084
 punished+0.083
Neg logit contributions
arl-0.088
ay-0.083
 Today-0.081
 Nice-0.079
andel-0.076
Token.
Token ID13
Feature activation-7.36e-03

Pos logit contributions
 pretended+0.023
 built+0.022
 found+0.022
 punished+0.022
 buried+0.022
Neg logit contributions
arl-0.026
ay-0.025
 Nice-0.025
 Today-0.024
omed-0.023
Token Everyone
Token ID11075
Feature activation+6.00e-02

Pos logit contributions
arl+0.014
andel+0.013
ay+0.013
oral+0.012
ifying+0.012
Neg logit contributions
 found-0.013
 put-0.013
 pretended-0.013
 tried-0.012
 shared-0.012
Token they
Token ID484
Feature activation+1.10e-01

Pos logit contributions
 pretended+0.076
wed+0.073
 buried+0.073
 least+0.072
 built+0.072
Neg logit contributions
ay-0.126
 Nice-0.125
arl-0.123
omed-0.121
ore-0.119
Token asked
Token ID1965
Feature activation+4.22e-02

Pos logit contributions
wed+0.116
 pretended+0.108
 punished+0.103
 buried+0.103
 least+0.102
Neg logit contributions
arl-0.243
omed-0.236
ay-0.234
ifying-0.228
arry-0.216
Token said
Token ID531
Feature activation+2.75e-02

Pos logit contributions
 pretended+0.057
 built+0.055
 buried+0.054
 found+0.054
 punished+0.053
Neg logit contributions
arl-0.100
ay-0.096
 Today-0.094
 Nice-0.093
omed-0.089
Token there
Token ID612
Feature activation+4.22e-02

Pos logit contributions
 pretended+0.045
 found+0.044
 built+0.043
 put+0.043
 buried+0.042
Neg logit contributions
arl-0.060
ay-0.056
 Today-0.054
 Nice-0.053
andel-0.052
Token was
Token ID373
Feature activation+5.26e-02

Pos logit contributions
 pretended+0.058
 built+0.055
 found+0.054
 punished+0.054
 buried+0.053
Neg logit contributions
arl-0.096
ay-0.094
 Today-0.093
 Nice-0.092
omed-0.087
Token no
Token ID645
Feature activation+3.31e-02

Pos logit contributions
 pretended+0.073
 found+0.069
 built+0.069
 buried+0.068
 put+0.067
Neg logit contributions
arl-0.124
ay-0.117
 Today-0.116
 Nice-0.115
andel-0.110
Token with
Token ID351
Feature activation+7.62e-02

Pos logit contributions
arl+0.050
 Today+0.047
ay+0.047
 Nice+0.045
omed+0.042
Neg logit contributions
 pretended-0.057
 found-0.056
 built-0.056
 buried-0.055
 punished-0.054
Token their
Token ID511
Feature activation+5.79e-02

Pos logit contributions
 pretended+0.105
 built+0.101
 found+0.097
 punished+0.097
 buried+0.096
Neg logit contributions
arl-0.182
ay-0.172
 Today-0.165
 Nice-0.163
ifying-0.159
Token toys
Token ID14958
Feature activation+1.02e-02

Pos logit contributions
 pretended+0.091
 built+0.089
 found+0.089
 put+0.085
 punished+0.084
Neg logit contributions
arl-0.127
ay-0.120
 Today-0.116
 Nice-0.113
ifying-0.110
Token.
Token ID13
Feature activation+4.92e-03

Pos logit contributions
 pretended+0.020
 found+0.019
 built+0.019
 punished+0.018
wed+0.018
Neg logit contributions
arl-0.018
ay-0.017
 Today-0.016
ifying-0.015
 Nice-0.015
Token They
Token ID1119
Feature activation+1.02e-01

Pos logit contributions
 pretended+0.009
 put+0.009
 found+0.009
 built+0.008
 played+0.008
Neg logit contributions
andel-0.009
arl-0.009
ay-0.008
omed-0.008
umm-0.008
Token also
Token ID635
Feature activation+1.08e-01

Pos logit contributions
wed+0.133
asured+0.127
ishing+0.120
 least+0.117
 able+0.115
Neg logit contributions
arl-0.197
 Today-0.183
ifying-0.180
ay-0.174
l-0.171
Token made
Token ID925
Feature activation+3.21e-02

Pos logit contributions
wed+0.110
 least+0.100
ie+0.099
ilia+0.098
ty+0.095
Neg logit contributions
arl-0.237
 Today-0.222
oral-0.203
ifying-0.202
useum-0.199
Token some
Token ID617
Feature activation+2.08e-02

Pos logit contributions
 pretended+0.052
 built+0.051
 found+0.051
 remembered+0.050
 buried+0.049
Neg logit contributions
arl-0.065
ay-0.062
 Today-0.059
andel-0.057
 Nice-0.056
Token new
Token ID649
Feature activation+5.46e-03

Pos logit contributions
 pretended+0.030
 found+0.029
 built+0.029
 put+0.028
 buried+0.028
Neg logit contributions
arl-0.049
ay-0.046
 Today-0.045
 Nice-0.044
andel-0.043
Token friends
Token ID2460
Feature activation+1.72e-02

Pos logit contributions
 built+0.008
 punished+0.008
 pretended+0.008
 found+0.008
wed+0.008
Neg logit contributions
ay-0.012
 Today-0.011
arl-0.011
 Nice-0.011
andel-0.010
Token.
Token ID13
Feature activation-9.47e-03

Pos logit contributions
 pretended+0.034
 punished+0.033
wed+0.033
 built+0.033
 found+0.032
Neg logit contributions
arl-0.027
ay-0.027
 Today-0.026
 Nice-0.026
ifying-0.024
Token discussing
Token ID11142
Feature activation+6.14e-02

Pos logit contributions
arl+0.067
andel+0.063
ifying+0.062
 horizon+0.059
ay+0.059
Neg logit contributions
 found-0.029
 pretended-0.025
 put-0.025
 buried-0.024
 built-0.024
Token their
Token ID511
Feature activation+6.35e-02

Pos logit contributions
 pretended+0.094
 found+0.087
 built+0.087
 buried+0.087
 punished+0.085
Neg logit contributions
arl-0.132
ay-0.129
 Today-0.125
 Nice-0.125
ifying-0.118
Token images
Token ID4263
Feature activation-9.47e-03

Pos logit contributions
 pretended+0.105
 found+0.102
 built+0.101
 put+0.098
 buried+0.097
Neg logit contributions
arl-0.132
ay-0.126
 Today-0.123
 Nice-0.119
ifying-0.114
Token.
Token ID13
Feature activation-7.79e-04

Pos logit contributions
arl+0.017
ay+0.017
 Today+0.016
 Nice+0.015
ifying+0.015
Neg logit contributions
 pretended-0.018
 found-0.017
 built-0.017
 punished-0.017
 buried-0.017
Token They
Token ID1119
Feature activation+1.02e-01

Pos logit contributions
arl+0.001
andel+0.001
ay+0.001
omed+0.001
ifying+0.001
Neg logit contributions
 pretended-0.002
 found-0.002
 put-0.002
 built-0.002
 shared-0.001
Token even
Token ID772
Feature activation+1.08e-01

Pos logit contributions
wed+0.116
 punished+0.105
asured+0.104
 buried+0.102
 seen+0.101
Neg logit contributions
ay-0.210
arl-0.207
 Today-0.206
ifying-0.203
omed-0.196
Token found
Token ID1043
Feature activation+4.66e-02

Pos logit contributions
 buried+0.091
 least+0.087
wed+0.082
ilia+0.079
 permission+0.079
Neg logit contributions
arl-0.229
omed-0.229
br-0.228
 Today-0.226
ay-0.223
Token a
Token ID257
Feature activation+1.99e-02

Pos logit contributions
 pretended+0.070
 punished+0.066
 built+0.065
wed+0.063
 found+0.063
Neg logit contributions
ay-0.101
arl-0.099
 Nice-0.092
 Today-0.091
ifying-0.091
Token pretty
Token ID2495
Feature activation+1.93e-02

Pos logit contributions
 pretended+0.040
 found+0.039
 built+0.038
 put+0.038
 buried+0.038
Neg logit contributions
arl-0.036
ay-0.033
 Today-0.032
 Nice-0.031
andel-0.030
Token butterfly
Token ID35113
Feature activation-1.44e-03

Pos logit contributions
 punished+0.036
wed+0.034
 pretended+0.034
 built+0.033
 found+0.033
Neg logit contributions
ay-0.037
arl-0.035
 Today-0.035
 Nice-0.034
andel-0.032
Token and
Token ID290
Feature activation+6.28e-02

Pos logit contributions
arl+0.003
ay+0.003
 Today+0.003
 Nice+0.003
ifying+0.003
Neg logit contributions
 pretended-0.002
 punished-0.002
wed-0.002
 built-0.002
 found-0.002
Token made
Token ID925
Feature activation+2.46e-02

Pos logit contributions
wed+0.127
 permission+0.127
 seen+0.123
 pretended+0.120
 built+0.120
Neg logit contributions
 Nice-0.154
 Today-0.154
ay-0.147
br-0.146
omed-0.143
Token Lily
Token ID20037
Feature activation+5.17e-02

Pos logit contributions
 pretended+0.033
 found+0.031
 built+0.031
 buried+0.030
 put+0.030
Neg logit contributions
arl-0.061
ay-0.058
 Today-0.056
 Nice-0.055
andel-0.054
Token smile
Token ID8212
Feature activation+1.45e-02

Pos logit contributions
 buried+0.079
 built+0.079
wed+0.077
 punished+0.076
 pretended+0.075
Neg logit contributions
 Today-0.104
ay-0.100
arl-0.098
 Nice-0.096
oles-0.088
Token.
Token ID13
Feature activation-6.64e-03

Pos logit contributions
 pretended+0.026
 built+0.026
 buried+0.026
 found+0.025
 punished+0.025
Neg logit contributions
arl-0.028
ay-0.026
 Today-0.026
 Nice-0.025
ifying-0.024
Token They
Token ID1119
Feature activation+9.54e-02

Pos logit contributions
andel+0.013
arl+0.012
ifying+0.012
ay+0.012
oles+0.011
Neg logit contributions
 found-0.012
 put-0.012
 pretended-0.011
 drew-0.011
 shared-0.011
Token also
Token ID635
Feature activation+1.08e-01

Pos logit contributions
 permission+0.117
wed+0.115
asured+0.110
 seen+0.109
 punished+0.105
Neg logit contributions
arl-0.181
ifying-0.179
ay-0.174
l-0.168
omed-0.168
Token taught
Token ID7817
Feature activation+1.09e-02

Pos logit contributions
 permission+0.108
wed+0.098
wy+0.090
ilia+0.090
 buried+0.089
Neg logit contributions
arl-0.216
l-0.200
ifying-0.196
omed-0.196
oral-0.190
Token her
Token ID607
Feature activation+4.46e-02

Pos logit contributions
 pretended+0.012
 built+0.012
 found+0.012
 buried+0.011
 put+0.011
Neg logit contributions
arl-0.029
ay-0.028
 Today-0.027
 Nice-0.027
andel-0.026
Token some
Token ID617
Feature activation+3.00e-02

Pos logit contributions
 pretended+0.052
 found+0.049
 built+0.049
 buried+0.048
 punished+0.046
Neg logit contributions
arl-0.114
ay-0.109
 Today-0.108
 Nice-0.107
oles-0.102
Token moves
Token ID6100
Feature activation-1.13e-02

Pos logit contributions
 put+0.052
 pretended+0.051
 found+0.050
 built+0.050
 buried+0.049
Neg logit contributions
arl-0.061
 Today-0.056
ay-0.056
 Nice-0.054
arry-0.053
Token.
Token ID13
Feature activation-1.67e-02

Pos logit contributions
arl+0.023
ay+0.021
 Today+0.021
 Nice+0.021
andel+0.020
Neg logit contributions
 pretended-0.020
 found-0.019
 built-0.019
 put-0.019
 buried-0.019
Token around
Token ID1088
Feature activation+4.80e-02

Pos logit contributions
 pretended+0.136
 punished+0.122
 buried+0.117
 put+0.115
 found+0.115
Neg logit contributions
arl-0.153
ay-0.149
 Today-0.146
 Nice-0.138
omed-0.135
Token the
Token ID262
Feature activation+3.08e-02

Pos logit contributions
 pretended+0.079
 punished+0.076
 built+0.073
wed+0.072
 buried+0.072
Neg logit contributions
arl-0.098
 Today-0.096
ay-0.095
 Nice-0.092
ifying-0.085
Token room
Token ID2119
Feature activation+1.85e-02

Pos logit contributions
 pretended+0.060
 found+0.057
 built+0.057
 punished+0.056
wed+0.056
Neg logit contributions
arl-0.054
ay-0.052
 Today-0.049
 Nice-0.048
andel-0.047
Token.
Token ID13
Feature activation-7.48e-03

Pos logit contributions
 pretended+0.035
 punished+0.034
wed+0.033
 buried+0.033
 found+0.032
Neg logit contributions
arl-0.031
ay-0.030
 Today-0.030
 Nice-0.028
omed-0.028
Token He
Token ID679
Feature activation+9.64e-02

Pos logit contributions
arl+0.014
andel+0.012
ay+0.012
omed+0.011
oral+0.011
Neg logit contributions
 found-0.015
 pretended-0.015
 put-0.015
 built-0.014
 tried-0.014
Token even
Token ID772
Feature activation+1.08e-01

Pos logit contributions
 permission+0.112
wed+0.108
 least+0.107
 seen+0.106
 punished+0.105
Neg logit contributions
 Today-0.189
omed-0.181
 Nice-0.181
ay-0.180
 On-0.176
Token flew
Token ID13112
Feature activation+1.47e-02

Pos logit contributions
 least+0.091
 permission+0.085
 buried+0.080
 punished+0.076
 pretended+0.075
Neg logit contributions
arl-0.232
omed-0.228
Exc-0.222
elly-0.220
oms-0.218
Token it
Token ID340
Feature activation+1.77e-02

Pos logit contributions
 pretended+0.023
 built+0.022
 put+0.022
 punished+0.022
 found+0.021
Neg logit contributions
arl-0.033
ay-0.031
 Today-0.030
 Nice-0.029
omed-0.028
Token around
Token ID1088
Feature activation+1.91e-02

Pos logit contributions
 pretended+0.028
 found+0.027
 built+0.027
 put+0.027
 punished+0.026
Neg logit contributions
arl-0.038
ay-0.036
 Today-0.035
 Nice-0.035
omed-0.033
Token his
Token ID465
Feature activation+2.61e-02

Pos logit contributions
 pretended+0.030
 punished+0.030
 built+0.029
wed+0.029
 found+0.028
Neg logit contributions
arl-0.039
ay-0.038
 Today-0.038
 Nice-0.037
andel-0.034
Token grandma
Token ID49890
Feature activation+3.22e-02

Pos logit contributions
 pretended+0.046
 built+0.046
wed+0.046
 punished+0.046
 found+0.044
Neg logit contributions
ay-0.048
 Today-0.046
arl-0.045
 Nice-0.043
 horizon-0.042
Token in
Token ID287
Feature activation+4.67e-02

Pos logit contributions
 pretended+0.039
 found+0.037
 punished+0.037
 built+0.036
wed+0.036
Neg logit contributions
arl-0.038
ay-0.035
 Today-0.034
 Nice-0.033
ifying-0.032
Token their
Token ID511
Feature activation+5.58e-02

Pos logit contributions
 pretended+0.067
 built+0.063
 found+0.062
 buried+0.061
 punished+0.061
Neg logit contributions
arl-0.109
ay-0.105
 Today-0.103
 Nice-0.098
ifying-0.096
Token basket
Token ID7988
Feature activation-5.77e-03

Pos logit contributions
 pretended+0.095
 built+0.092
 found+0.091
 punished+0.089
 put+0.089
Neg logit contributions
arl-0.112
ay-0.107
 Today-0.105
 Nice-0.099
ifying-0.099
Token.
Token ID13
Feature activation-6.39e-04

Pos logit contributions
arl+0.011
ay+0.010
 Today+0.010
 Nice+0.010
ifying+0.009
Neg logit contributions
 pretended-0.011
 found-0.010
 built-0.010
 put-0.010
 buried-0.010
Token They
Token ID1119
Feature activation+9.94e-02

Pos logit contributions
andel+0.001
arl+0.001
ay+0.001
omed+0.001
anger+0.001
Neg logit contributions
 put-0.001
 pretended-0.001
 found-0.001
 built-0.001
 played-0.001
Token also
Token ID635
Feature activation+1.08e-01

Pos logit contributions
wed+0.123
asured+0.117
 least+0.109
ishing+0.108
 permission+0.107
Neg logit contributions
arl-0.196
ifying-0.193
 Today-0.186
ay-0.179
 On-0.176
Token hang
Token ID8181
Feature activation-9.97e-03

Pos logit contributions
wed+0.105
 least+0.095
ie+0.095
 pretended+0.095
ilia+0.092
Neg logit contributions
arl-0.229
 Today-0.218
ifying-0.206
oral-0.205
omed-0.201
Token some
Token ID617
Feature activation+6.91e-03

Pos logit contributions
arl+0.023
 Today+0.021
ay+0.021
 Nice+0.021
andel+0.020
Neg logit contributions
 pretended-0.015
 found-0.015
 built-0.014
 put-0.014
 buried-0.014
Token pictures
Token ID5986
Feature activation-2.28e-02

Pos logit contributions
 pretended+0.011
 found+0.011
 built+0.010
 put+0.010
 buried+0.010
Neg logit contributions
arl-0.015
ay-0.014
 Today-0.014
 Nice-0.014
andel-0.013
Token and
Token ID290
Feature activation+5.90e-02

Pos logit contributions
arl+0.045
ay+0.040
 Today+0.040
 Nice+0.040
andel+0.038
Neg logit contributions
 pretended-0.042
 found-0.041
 built-0.041
 put-0.041
 buried-0.040
Token drawings
Token ID23388
Feature activation-1.20e-02

Pos logit contributions
 punished+0.077
wed+0.075
 buried+0.073
 least+0.073
 built+0.070
Neg logit contributions
arl-0.116
 Today-0.114
ay-0.113
ifying-0.112
lights-0.108
Token and
Token ID290
Feature activation+8.95e-02

Pos logit contributions
 pretended+0.047
 punished+0.044
 built+0.044
 buried+0.044
 put+0.044
Neg logit contributions
arl-0.051
ay-0.050
 Today-0.048
 Nice-0.046
ifying-0.043
Token a
Token ID257
Feature activation+4.42e-02

Pos logit contributions
wed+0.111
 buried+0.105
 punished+0.102
 built+0.102
 pretended+0.100
Neg logit contributions
arl-0.193
 Today-0.189
ay-0.185
 Nice-0.185
ifying-0.178
Token doll
Token ID3654
Feature activation+2.65e-02

Pos logit contributions
 pretended+0.086
 found+0.084
 built+0.083
 put+0.082
 buried+0.082
Neg logit contributions
arl-0.082
ay-0.075
 Today-0.073
 Nice-0.072
andel-0.069
Token.
Token ID13
Feature activation+2.42e-03

Pos logit contributions
 pretended+0.049
 built+0.048
 found+0.048
 buried+0.048
 punished+0.047
Neg logit contributions
arl-0.047
ay-0.045
 Today-0.044
 Nice-0.042
ifying-0.041
Token They
Token ID1119
Feature activation+9.76e-02

Pos logit contributions
 pretended+0.005
 put+0.005
 found+0.005
 built+0.004
 played+0.004
Neg logit contributions
arl-0.004
andel-0.004
ay-0.004
omed-0.004
oral-0.004
Token also
Token ID635
Feature activation+1.08e-01

Pos logit contributions
wed+0.129
asured+0.122
 punished+0.120
 buried+0.118
 permission+0.117
Neg logit contributions
arl-0.186
ay-0.182
 Today-0.180
ifying-0.174
l-0.167
Token liked
Token ID8288
Feature activation+4.20e-02

Pos logit contributions
wed+0.117
 buried+0.112
 least+0.106
 punished+0.102
 pretended+0.100
Neg logit contributions
arl-0.230
 Today-0.223
ay-0.210
br-0.200
ifying-0.199
Token to
Token ID284
Feature activation+6.03e-02

Pos logit contributions
 pretended+0.072
 found+0.070
 buried+0.069
 built+0.069
 punished+0.068
Neg logit contributions
arl-0.084
ay-0.078
 Nice-0.076
 Today-0.075
andel-0.071
Token look
Token ID804
Feature activation+2.70e-02

Pos logit contributions
 buried+0.090
 punished+0.089
wed+0.087
 pretended+0.086
 built+0.086
Neg logit contributions
arl-0.128
 Today-0.123
ay-0.123
 Nice-0.110
arry-0.105
Token at
Token ID379
Feature activation+3.23e-02

Pos logit contributions
 pretended+0.043
 found+0.042
 put+0.041
 built+0.041
 buried+0.040
Neg logit contributions
arl-0.060
ay-0.056
 Today-0.054
 Nice-0.054
andel-0.052
Token the
Token ID262
Feature activation+2.57e-03

Pos logit contributions
 pretended+0.044
 built+0.043
 found+0.042
 punished+0.041
 buried+0.041
Neg logit contributions
arl-0.076
ay-0.074
 Today-0.070
 Nice-0.069
ifying-0.068
Token to
Token ID284
Feature activation+9.47e-02

Pos logit contributions
arl+0.111
ay+0.105
 Today+0.102
 Nice+0.101
omed+0.096
Neg logit contributions
 pretended-0.101
 punished-0.098
 found-0.096
 built-0.096
 put-0.094
Token the
Token ID262
Feature activation+4.03e-02

Pos logit contributions
 pretended+0.127
wed+0.125
 built+0.116
 buried+0.110
 punished+0.110
Neg logit contributions
arl-0.209
 Today-0.203
ay-0.195
 Nice-0.187
ifying-0.182
Token music
Token ID2647
Feature activation-1.12e-02

Pos logit contributions
 pretended+0.076
 found+0.074
 built+0.073
 put+0.072
 buried+0.071
Neg logit contributions
arl-0.077
ay-0.071
 Today-0.069
 Nice-0.068
andel-0.065
Token.
Token ID13
Feature activation-3.92e-03

Pos logit contributions
arl+0.022
ay+0.021
 Today+0.021
 Nice+0.020
ifying+0.019
Neg logit contributions
 pretended-0.019
 found-0.019
 built-0.018
 buried-0.018
 punished-0.018
Token They
Token ID1119
Feature activation+1.01e-01

Pos logit contributions
arl+0.007
andel+0.006
ay+0.006
omed+0.006
oral+0.006
Neg logit contributions
 found-0.008
 pretended-0.008
 put-0.008
 built-0.008
 shared-0.007
Token even
Token ID772
Feature activation+1.07e-01

Pos logit contributions
wed+0.107
 buried+0.105
 punished+0.099
 built+0.097
 least+0.095
Neg logit contributions
arl-0.229
ifying-0.221
ay-0.220
 Today-0.219
omed-0.210
Token stayed
Token ID9658
Feature activation+3.05e-02

Pos logit contributions
 buried+0.098
 least+0.088
wed+0.083
 built+0.080
 punished+0.080
Neg logit contributions
arl-0.248
omed-0.235
ay-0.230
oms-0.229
br-0.228
Token and
Token ID290
Feature activation+6.13e-02

Pos logit contributions
wed+0.057
 pretended+0.055
 built+0.052
 shared+0.050
 fought+0.050
Neg logit contributions
arl-0.053
ay-0.049
 Today-0.048
ifying-0.046
omed-0.046
Token danced
Token ID39480
Feature activation-1.40e-02

Pos logit contributions
wed+0.062
wy+0.057
 buried+0.055
 punished+0.054
 pretended+0.052
Neg logit contributions
arl-0.139
 Nice-0.133
 Today-0.131
ifying-0.129
omed-0.129
Token around
Token ID1088
Feature activation+1.26e-02

Pos logit contributions
arl+0.030
ay+0.028
 Today+0.028
 Nice+0.027
andel+0.026
Neg logit contributions
 pretended-0.023
 found-0.022
 built-0.022
 put-0.022
 buried-0.022
Token the
Token ID262
Feature activation+8.87e-04

Pos logit contributions
 pretended+0.017
 found+0.016
 built+0.016
 put+0.016
 buried+0.016
Neg logit contributions
arl-0.031
ay-0.029
 Today-0.029
 Nice-0.028
andel-0.027
Token each
Token ID1123
Feature activation+5.72e-02

Pos logit contributions
 pretended+0.057
 found+0.053
 built+0.053
 buried+0.052
 punished+0.051
Neg logit contributions
arl-0.096
ay-0.091
 Today-0.088
andel-0.087
 Nice-0.086
Token of
Token ID286
Feature activation+4.76e-02

Pos logit contributions
 pretended+0.109
 built+0.102
 buried+0.101
 punished+0.101
 found+0.100
Neg logit contributions
ay-0.103
arl-0.102
 Today-0.100
 Nice-0.093
andel-0.091
Token them
Token ID606
Feature activation+3.56e-02

Pos logit contributions
 pretended+0.070
 built+0.064
 found+0.064
 punished+0.063
 buried+0.062
Neg logit contributions
arl-0.111
ay-0.106
 Today-0.101
andel-0.101
 Nice-0.099
Token.
Token ID13
Feature activation-4.94e-03

Pos logit contributions
 pretended+0.062
 punished+0.059
 built+0.058
 found+0.058
wed+0.057
Neg logit contributions
arl-0.062
ay-0.060
 Today-0.059
ifying-0.058
oles-0.056
Token She
Token ID1375
Feature activation+9.64e-02

Pos logit contributions
arl+0.009
ay+0.008
andel+0.008
omed+0.007
oral+0.007
Neg logit contributions
 put-0.010
 found-0.010
 pretended-0.010
 built-0.010
 tried-0.009
Token even
Token ID772
Feature activation+1.07e-01

Pos logit contributions
 permission+0.116
 seen+0.114
 least+0.105
 punished+0.103
wed+0.103
Neg logit contributions
ay-0.193
 Today-0.185
oral-0.184
oles-0.182
omed-0.181
Token put
Token ID1234
Feature activation+4.24e-02

Pos logit contributions
 least+0.097
 permission+0.093
 buried+0.089
 pretended+0.089
 punished+0.085
Neg logit contributions
oral-0.226
br-0.223
omed-0.222
ay-0.218
arl-0.216
Token on
Token ID319
Feature activation+1.35e-02

Pos logit contributions
 pretended+0.065
 punished+0.059
 built+0.059
 forgot+0.058
 buried+0.057
Neg logit contributions
ay-0.094
arl-0.093
ifying-0.086
 Today-0.085
omed-0.084
Token a
Token ID257
Feature activation+1.66e-02

Pos logit contributions
 pretended+0.021
 punished+0.020
 built+0.019
 forgot+0.019
 buried+0.019
Neg logit contributions
ay-0.028
arl-0.027
 Today-0.026
andel-0.026
ifying-0.025
Token little
Token ID1310
Feature activation+1.81e-02

Pos logit contributions
 pretended+0.027
 found+0.026
 built+0.026
 put+0.025
 buried+0.025
Neg logit contributions
arl-0.036
ay-0.034
 Today-0.033
 Nice-0.033
andel-0.032
Token note
Token ID3465
Feature activation-5.70e-03

Pos logit contributions
 pretended+0.029
 built+0.027
 punished+0.027
 found+0.026
wed+0.026
Neg logit contributions
arl-0.039
ay-0.038
 Today-0.037
 Nice-0.035
andel-0.035
Token for
Token ID329
Feature activation+6.14e-02

Pos logit contributions
 pretended+0.139
 built+0.136
 found+0.133
 punished+0.131
wed+0.129
Neg logit contributions
arl-0.168
ay-0.158
 Today-0.157
 Nice-0.150
ifying-0.146
Token fixing
Token ID18682
Feature activation+1.94e-02

Pos logit contributions
 pretended+0.081
 built+0.076
 found+0.074
wed+0.072
 buried+0.072
Neg logit contributions
arl-0.148
 Today-0.131
ay-0.130
 Nice-0.126
andel-0.124
Token it
Token ID340
Feature activation+2.30e-02

Pos logit contributions
 pretended+0.031
 built+0.030
 found+0.029
 buried+0.029
 shared+0.028
Neg logit contributions
ay-0.041
arl-0.040
 Today-0.037
andel-0.036
ifying-0.036
Token.
Token ID13
Feature activation+3.85e-03

Pos logit contributions
 pretended+0.044
 found+0.042
 built+0.042
 buried+0.041
 punished+0.040
Neg logit contributions
arl-0.043
ay-0.040
 Today-0.039
 Nice-0.037
ifying-0.036
Token They
Token ID1119
Feature activation+1.01e-01

Pos logit contributions
 found+0.008
 pretended+0.008
 put+0.008
 built+0.008
 shared+0.007
Neg logit contributions
arl-0.007
andel-0.006
ay-0.006
omed-0.006
ifying-0.006
Token also
Token ID635
Feature activation+1.07e-01

Pos logit contributions
asured+0.125
wed+0.108
 permission+0.108
ishing+0.106
 seen+0.106
Neg logit contributions
ifying-0.192
ay-0.191
 On-0.182
arl-0.176
 Today-0.174
Token said
Token ID531
Feature activation+2.33e-02

Pos logit contributions
ty+0.096
i+0.091
anut+0.086
bur+0.085
asured+0.084
Neg logit contributions
oral-0.221
arl-0.217
ay-0.217
 Today-0.207
-0.200
Token sorry
Token ID7926
Feature activation+1.64e-02

Pos logit contributions
 pretended+0.040
 found+0.039
 built+0.039
 buried+0.038
 put+0.038
Neg logit contributions
arl-0.048
ay-0.045
 Today-0.044
 Nice-0.043
andel-0.041
Token to
Token ID284
Feature activation+3.57e-02

Pos logit contributions
 pretended+0.029
 buried+0.029
 built+0.029
 punished+0.028
 found+0.028
Neg logit contributions
arl-0.032
 Today-0.030
 Nice-0.030
ay-0.029
omed-0.026
Token Aunt
Token ID38074
Feature activation-1.93e-03

Pos logit contributions
 pretended+0.055
 built+0.054
 buried+0.053
 found+0.052
wed+0.050
Neg logit contributions
arl-0.079
ay-0.073
 Today-0.072
 Nice-0.071
andel-0.068
Tokenie
Token ID494
Feature activation+2.39e-02

Pos logit contributions
arl+0.005
ay+0.005
 Today+0.005
 Nice+0.005
andel+0.004
Neg logit contributions
 pretended-0.002
 found-0.002
 built-0.002
 buried-0.002
 put-0.002
Token them
Token ID606
Feature activation+6.08e-02

Pos logit contributions
 pretended+0.064
 found+0.061
 built+0.061
 buried+0.059
 put+0.059
Neg logit contributions
arl-0.112
ay-0.104
 Today-0.103
 Nice-0.102
andel-0.098
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
 pretended+0.110
 built+0.107
 found+0.105
 punished+0.103
 buried+0.103
Neg logit contributions
arl-0.114
 Today-0.106
 Nice-0.105
ay-0.105
ifying-0.098
Token
Token ID198
Feature activation-8.95e-03

Pos logit contributions
 found+0.025
 pretended+0.025
 put+0.024
 built+0.023
 shared+0.023
Neg logit contributions
arl-0.021
andel-0.019
ay-0.018
omed-0.017
ifying-0.016
Token
Token ID198
Feature activation-1.58e-02

Pos logit contributions
arl+0.015
ifying+0.015
umm+0.014
andel+0.014
 Nice+0.014
Neg logit contributions
 found-0.019
 put-0.018
 built-0.017
 learned-0.017
 seen-0.017
TokenThey
Token ID2990
Feature activation+9.89e-02

Pos logit contributions
arl+0.028
ay+0.026
andel+0.026
 Nice+0.026
omed+0.024
Neg logit contributions
 found-0.031
 put-0.030
 pretended-0.030
 built-0.030
 shared-0.029
Token also
Token ID635
Feature activation+1.07e-01

Pos logit contributions
 pretended+0.101
wed+0.100
 built+0.098
 punished+0.095
 seen+0.095
Neg logit contributions
arl-0.224
ay-0.211
ifying-0.210
omed-0.207
 Today-0.205
Token realized
Token ID6939
Feature activation+4.07e-02

Pos logit contributions
wed+0.096
 pretended+0.090
 built+0.089
asured+0.083
 buried+0.081
Neg logit contributions
arl-0.238
 Today-0.224
omed-0.222
oral-0.218
ifying-0.217
Token that
Token ID326
Feature activation+4.67e-02

Pos logit contributions
 pretended+0.061
 found+0.059
 built+0.058
 put+0.057
 buried+0.056
Neg logit contributions
arl-0.094
ay-0.088
 Today-0.086
 Nice-0.085
andel-0.082
Token pengu
Token ID38373
Feature activation-2.75e-02

Pos logit contributions
 pretended+0.072
 found+0.070
 built+0.069
 buried+0.067
 put+0.067
Neg logit contributions
arl-0.101
 Today-0.095
ay-0.095
 Nice-0.095
andel-0.089
Tokenins
Token ID1040
Feature activation+1.51e-02

Pos logit contributions
arl+0.053
ay+0.049
 Today+0.047
 Nice+0.046
andel+0.045
Neg logit contributions
 pretended-0.052
 found-0.050
 built-0.050
 put-0.049
 buried-0.049
Token were
Token ID547
Feature activation+4.55e-02

Pos logit contributions
 pretended+0.024
 built+0.022
 found+0.022
 put+0.022
 buried+0.022
Neg logit contributions
arl-0.030
ay-0.029
oles-0.028
 Nice-0.028
ifying-0.028
Tokenia
Token ID544
Feature activation+9.74e-02

Pos logit contributions
 pretended+0.010
 punished+0.008
 built+0.008
wed+0.008
 found+0.008
Neg logit contributions
arl-0.018
ay-0.016
 Today-0.016
andel-0.016
 Nice-0.015
Token and
Token ID290
Feature activation+8.62e-02

Pos logit contributions
 punished+0.150
 pretended+0.140
 buried+0.139
 built+0.136
 cleaned+0.136
Neg logit contributions
 Today-0.194
arl-0.190
ay-0.189
 Nice-0.184
oles-0.179
Token Ben
Token ID3932
Feature activation+7.56e-02

Pos logit contributions
 built+0.134
 pretended+0.133
wed+0.132
 punished+0.131
 buried+0.129
Neg logit contributions
arl-0.176
 Nice-0.167
 Today-0.162
ay-0.161
oles-0.152
Token smiled
Token ID13541
Feature activation+2.68e-02

Pos logit contributions
 built+0.094
 buried+0.094
 pretended+0.093
wed+0.090
 punished+0.089
Neg logit contributions
arl-0.176
 Today-0.166
ay-0.162
 Nice-0.160
omed-0.158
Token.
Token ID13
Feature activation+7.04e-03

Pos logit contributions
 pretended+0.039
 found+0.037
 put+0.037
 built+0.035
 buried+0.034
Neg logit contributions
arl-0.065
ay-0.060
andel-0.058
 Today-0.058
 Nice-0.057
Token They
Token ID1119
Feature activation+1.07e-01

Pos logit contributions
 pretended+0.013
 found+0.012
 put+0.012
 played+0.012
 shared+0.011
Neg logit contributions
andel-0.014
ay-0.013
arl-0.013
ork-0.012
oral-0.012
Token thanked
Token ID26280
Feature activation+3.10e-02

Pos logit contributions
wed+0.133
 permission+0.125
 least+0.123
 punished+0.122
 built+0.117
Neg logit contributions
arl-0.210
omed-0.201
ay-0.201
ifying-0.198
arry-0.191
Token Mom
Token ID11254
Feature activation+2.30e-02

Pos logit contributions
 pretended+0.048
 found+0.046
 built+0.046
 buried+0.045
 punished+0.044
Neg logit contributions
arl-0.070
ay-0.066
 Today-0.064
 Nice-0.064
andel-0.061
Token and
Token ID290
Feature activation+6.24e-02

Pos logit contributions
 pretended+0.037
 buried+0.037
 found+0.036
 built+0.036
 punished+0.036
Neg logit contributions
arl-0.050
ay-0.047
 Today-0.046
 Nice-0.045
omed-0.043
Token took
Token ID1718
Feature activation+4.46e-02

Pos logit contributions
 built+0.115
wed+0.114
 buried+0.114
 pretended+0.114
 punished+0.111
Neg logit contributions
arl-0.105
ay-0.086
ifying-0.085
 Nice-0.083
 Today-0.083
Token their
Token ID511
Feature activation+3.18e-02

Pos logit contributions
 pretended+0.071
 built+0.069
 buried+0.067
 punished+0.066
 found+0.065
Neg logit contributions
ay-0.095
arl-0.094
 Today-0.085
andel-0.084
 Nice-0.081
Token with
Token ID351
Feature activation+5.61e-02

Pos logit contributions
 pretended+0.040
 punished+0.037
 found+0.037
 buried+0.037
 built+0.036
Neg logit contributions
arl-0.047
ay-0.045
 Today-0.043
 Nice-0.042
omed-0.041
Token her
Token ID607
Feature activation+4.38e-02

Pos logit contributions
 pretended+0.083
 punished+0.080
 built+0.079
 forgot+0.077
 found+0.076
Neg logit contributions
arl-0.121
ay-0.121
 Today-0.109
ifying-0.109
andel-0.106
Token coins
Token ID10796
Feature activation-9.53e-05

Pos logit contributions
 pretended+0.070
 built+0.069
 found+0.067
 punished+0.066
wed+0.066
Neg logit contributions
arl-0.091
ay-0.089
 Today-0.085
 Nice-0.083
ifying-0.082
Token.
Token ID13
Feature activation-2.69e-03

Pos logit contributions
arl+0.000
ay+0.000
ifying+0.000
 Today+0.000
omed+0.000
Neg logit contributions
 pretended-0.000
 punished-0.000
 built-0.000
 found-0.000
wed-0.000
Token She
Token ID1375
Feature activation+9.38e-02

Pos logit contributions
arl+0.005
ay+0.005
andel+0.005
ifying+0.004
omed+0.004
Neg logit contributions
 found-0.005
 put-0.005
 pretended-0.005
 built-0.005
 tried-0.005
Token even
Token ID772
Feature activation+1.07e-01

Pos logit contributions
 permission+0.121
wed+0.116
 seen+0.115
 least+0.113
 punished+0.112
Neg logit contributions
 Today-0.174
useum-0.168
oms-0.168
ay-0.168
 On-0.167
Token had
Token ID550
Feature activation+6.92e-02

Pos logit contributions
 least+0.094
 permission+0.082
 punished+0.078
 buried+0.074
 behave+0.068
Neg logit contributions
Exc-0.221
br-0.218
arl-0.217
omed-0.214
l-0.213
Token enough
Token ID1576
Feature activation+3.69e-02

Pos logit contributions
 pretended+0.101
wed+0.094
 punished+0.093
 remember+0.092
 least+0.092
Neg logit contributions
ifying-0.118
ay-0.118
omed-0.117
ork-0.117
arl-0.114
Token money
Token ID1637
Feature activation+4.80e-03

Pos logit contributions
 pretended+0.059
 found+0.054
 built+0.054
 punished+0.054
 buried+0.052
Neg logit contributions
arl-0.081
ay-0.076
 Today-0.071
andel-0.069
 Nice-0.069
Token for
Token ID329
Feature activation+2.00e-02

Pos logit contributions
 pretended+0.009
 built+0.008
 punished+0.008
 found+0.008
 buried+0.008
Neg logit contributions
arl-0.010
ay-0.009
 Nice-0.008
 Today-0.008
omed-0.008
Token a
Token ID257
Feature activation+2.05e-02

Pos logit contributions
 pretended+0.022
 built+0.020
 found+0.020
 buried+0.019
 punished+0.019
Neg logit contributions
arl-0.054
ay-0.051
 Today-0.050
 Nice-0.049
andel-0.049
Token about
Token ID546
Feature activation+6.55e-02

Pos logit contributions
wed+0.123
 pretended+0.118
 built+0.116
 buried+0.115
 punished+0.115
Neg logit contributions
arl-0.223
 Nice-0.211
 Today-0.211
ay-0.208
ifying-0.202
Token all
Token ID477
Feature activation+5.56e-02

Pos logit contributions
 pretended+0.090
 built+0.083
 found+0.083
wed+0.082
 buried+0.082
Neg logit contributions
arl-0.151
 Nice-0.144
ay-0.142
 Today-0.142
ifying-0.133
Token the
Token ID262
Feature activation+3.14e-02

Pos logit contributions
 pretended+0.104
 found+0.095
 buried+0.095
 punished+0.095
 built+0.095
Neg logit contributions
arl-0.105
ay-0.102
 Today-0.099
 Nice-0.095
omed-0.090
Token fun
Token ID1257
Feature activation+1.73e-02

Pos logit contributions
 pretended+0.058
 found+0.056
 built+0.055
 put+0.054
 buried+0.054
Neg logit contributions
arl-0.060
ay-0.057
 Today-0.055
 Nice-0.054
andel-0.052
Token things
Token ID1243
Feature activation+2.43e-02

Pos logit contributions
 pretended+0.032
 punished+0.030
 found+0.030
 built+0.030
 buried+0.030
Neg logit contributions
arl-0.031
ay-0.031
 Today-0.030
 Nice-0.030
oles-0.028
Token they
Token ID484
Feature activation+1.07e-01

Pos logit contributions
 pretended+0.045
 built+0.042
wed+0.042
 punished+0.042
 found+0.041
Neg logit contributions
arl-0.045
ay-0.043
 Nice-0.041
 Today-0.041
omed-0.039
Token would
Token ID561
Feature activation+7.99e-02

Pos logit contributions
wed+0.123
 punished+0.115
 pretended+0.114
 buried+0.104
 permission+0.100
Neg logit contributions
arl-0.226
ay-0.223
ifying-0.216
 Today-0.210
 Nice-0.205
Token do
Token ID466
Feature activation+3.53e-02

Pos logit contributions
 pretended+0.092
wed+0.089
 punished+0.087
 buried+0.080
 built+0.079
Neg logit contributions
arl-0.197
 Today-0.189
ay-0.186
 Nice-0.175
ifying-0.172
Token.
Token ID13
Feature activation-1.08e-02

Pos logit contributions
 pretended+0.067
 punished+0.064
 buried+0.064
wed+0.063
 found+0.062
Neg logit contributions
arl-0.059
ay-0.058
 Today-0.056
 Nice-0.054
omed-0.051
Token They
Token ID1119
Feature activation+9.41e-02

Pos logit contributions
arl+0.019
andel+0.016
ay+0.016
omed+0.015
ifying+0.014
Neg logit contributions
 found-0.023
 pretended-0.023
 built-0.022
 put-0.022
 shared-0.021
Token were
Token ID547
Feature activation+5.12e-02

Pos logit contributions
wed+0.106
 punished+0.102
 seen+0.101
asured+0.099
 permission+0.098
Neg logit contributions
ay-0.181
arl-0.177
 Today-0.176
ifying-0.174
arry-0.166
Token lots
Token ID6041
Feature activation+1.54e-02

Pos logit contributions
 pretended+0.108
wed+0.108
 punished+0.105
 buried+0.103
 built+0.099
Neg logit contributions
ay-0.105
 Today-0.100
arl-0.099
 Nice-0.099
omed-0.093
Token of
Token ID286
Feature activation+4.67e-02

Pos logit contributions
 pretended+0.037
 found+0.036
 built+0.036
 put+0.036
 buried+0.035
Neg logit contributions
arl-0.022
ay-0.019
 Today-0.019
 Nice-0.018
andel-0.017
Token fun
Token ID1257
Feature activation+1.23e-02

Pos logit contributions
 pretended+0.085
 punished+0.079
 found+0.079
 buried+0.078
 least+0.077
Neg logit contributions
arl-0.086
ay-0.084
 Today-0.081
 Nice-0.077
andel-0.075
Token.
Token ID13
Feature activation-1.03e-02

Pos logit contributions
 pretended+0.024
 found+0.023
 punished+0.023
 buried+0.023
 built+0.023
Neg logit contributions
arl-0.021
ay-0.020
 Today-0.019
 Nice-0.018
oles-0.018
Token They
Token ID1119
Feature activation+9.70e-02

Pos logit contributions
arl+0.018
andel+0.016
ay+0.016
omed+0.015
ifying+0.014
Neg logit contributions
 found-0.021
 pretended-0.021
 put-0.021
 built-0.021
 played-0.020
Token even
Token ID772
Feature activation+1.06e-01

Pos logit contributions
wed+0.108
 punished+0.107
 buried+0.103
asured+0.102
 permission+0.101
Neg logit contributions
ifying-0.194
ay-0.191
 Today-0.189
arl-0.188
 Nice-0.181
Token found
Token ID1043
Feature activation+5.00e-02

Pos logit contributions
 permission+0.090
 buried+0.089
 least+0.088
wed+0.074
 punished+0.072
Neg logit contributions
arl-0.230
br-0.225
omed-0.223
 Nice-0.221
l-0.218
Token a
Token ID257
Feature activation+2.37e-02

Pos logit contributions
 pretended+0.078
 built+0.072
 punished+0.070
wed+0.069
 forgot+0.069
Neg logit contributions
ay-0.103
arl-0.102
 Nice-0.095
ifying-0.095
andel-0.094
Token peaceful
Token ID12309
Feature activation+1.14e-02

Pos logit contributions
 pretended+0.046
 found+0.045
 built+0.045
 put+0.044
 buried+0.044
Neg logit contributions
arl-0.043
ay-0.040
 Today-0.039
 Nice-0.038
andel-0.037
Token solution
Token ID4610
Feature activation+7.04e-03

Pos logit contributions
 pretended+0.022
 punished+0.022
wed+0.021
 built+0.021
 found+0.021
Neg logit contributions
arl-0.020
ay-0.020
 Today-0.019
 Nice-0.018
andel-0.018
Token to
Token ID284
Feature activation+5.17e-02

Pos logit contributions
 pretended+0.013
 punished+0.013
wed+0.012
 found+0.012
 built+0.012
Neg logit contributions
arl-0.012
ay-0.012
 Nice-0.011
 Today-0.011
ifying-0.011
Token on
Token ID319
Feature activation+3.53e-02

Pos logit contributions
 pretended+0.031
 found+0.030
 built+0.030
 buried+0.030
 punished+0.030
Neg logit contributions
arl-0.033
ay-0.031
 Today-0.030
 Nice-0.030
omed-0.028
Token the
Token ID262
Feature activation+3.46e-02

Pos logit contributions
 pretended+0.045
 found+0.043
 built+0.043
 buried+0.042
 put+0.041
Neg logit contributions
arl-0.088
ay-0.084
 Today-0.082
 Nice-0.080
andel-0.078
Token walls
Token ID7714
Feature activation+1.30e-04

Pos logit contributions
 pretended+0.064
 found+0.062
 built+0.061
 put+0.060
 punished+0.060
Neg logit contributions
arl-0.067
ay-0.063
 Today-0.061
 Nice-0.059
andel-0.057
Token.
Token ID13
Feature activation+1.43e-03

Pos logit contributions
 pretended+0.000
 found+0.000
 punished+0.000
 buried+0.000
 built+0.000
Neg logit contributions
arl-0.000
ay-0.000
 Today-0.000
 Nice-0.000
omed-0.000
Token She
Token ID1375
Feature activation+9.97e-02

Pos logit contributions
 pretended+0.003
 found+0.003
 put+0.003
 built+0.003
 played+0.003
Neg logit contributions
arl-0.003
andel-0.002
ay-0.002
omed-0.002
ifying-0.002
Token also
Token ID635
Feature activation+1.06e-01

Pos logit contributions
 permission+0.116
wed+0.110
 buried+0.107
 punished+0.107
 seen+0.105
Neg logit contributions
 Today-0.193
ay-0.188
omed-0.186
oms-0.185
oral-0.183
Token liked
Token ID8288
Feature activation+4.52e-02

Pos logit contributions
wed+0.096
 buried+0.095
 pretended+0.088
wy+0.083
 punished+0.082
Neg logit contributions
arl-0.233
 Today-0.225
ay-0.220
oral-0.217
omed-0.217
Token the
Token ID262
Feature activation+1.93e-02

Pos logit contributions
 pretended+0.077
 punished+0.075
 buried+0.075
wed+0.074
 found+0.074
Neg logit contributions
arl-0.086
ay-0.082
 Nice-0.080
 Today-0.077
andel-0.076
Token food
Token ID2057
Feature activation-9.69e-03

Pos logit contributions
 pretended+0.036
 found+0.035
 built+0.034
wed+0.034
 punished+0.034
Neg logit contributions
arl-0.036
ay-0.034
 Today-0.033
 Nice-0.032
andel-0.031
Token,
Token ID11
Feature activation+4.74e-02

Pos logit contributions
ay+0.018
arl+0.018
 Nice+0.017
 Today+0.017
oles+0.016
Neg logit contributions
 pretended-0.017
 punished-0.017
wed-0.016
 built-0.016
 found-0.016
Token especially
Token ID2592
Feature activation+6.64e-02

Pos logit contributions
wed+0.099
 punished+0.098
 remembered+0.094
 found+0.093
 buried+0.092
Neg logit contributions
 Nice-0.066
 Today-0.064
ay-0.060
arl-0.059
andel-0.055
Token the
Token ID262
Feature activation+2.53e-02

Pos logit contributions
 pretended+0.060
 built+0.057
 found+0.057
 buried+0.055
 punished+0.054
Neg logit contributions
arl-0.106
ay-0.101
 Today-0.098
 Nice-0.095
ifying-0.093
Token right
Token ID826
Feature activation+6.92e-03

Pos logit contributions
 pretended+0.050
 found+0.048
 built+0.048
 put+0.047
 buried+0.046
Neg logit contributions
arl-0.046
ay-0.043
 Today-0.042
 Nice-0.040
andel-0.039
Token place
Token ID1295
Feature activation+3.96e-03

Pos logit contributions
 pretended+0.013
 found+0.013
 built+0.013
 put+0.013
 buried+0.013
Neg logit contributions
arl-0.013
ay-0.012
 Today-0.012
 Nice-0.011
andel-0.011
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
 pretended+0.008
 found+0.007
 built+0.007
 punished+0.007
 buried+0.007
Neg logit contributions
arl-0.007
ay-0.007
 Today-0.007
 Nice-0.006
ifying-0.006
Token They
Token ID1119
Feature activation+9.58e-02

Pos logit contributions
arl+0.021
andel+0.018
ay+0.017
omed+0.016
ifying+0.016
Neg logit contributions
 found-0.024
 put-0.023
 pretended-0.023
 built-0.023
 shared-0.022
Token even
Token ID772
Feature activation+1.06e-01

Pos logit contributions
wed+0.119
 punished+0.112
 permission+0.104
 least+0.103
asured+0.102
Neg logit contributions
ifying-0.182
ay-0.177
arl-0.173
omed-0.173
 Today-0.168
Token made
Token ID925
Feature activation+3.08e-02

Pos logit contributions
 least+0.087
 permission+0.076
 buried+0.074
 punished+0.068
wed+0.067
Neg logit contributions
omed-0.229
arl-0.227
br-0.218
ay-0.213
pour-0.213
Token a
Token ID257
Feature activation+1.77e-02

Pos logit contributions
 pretended+0.051
 remembered+0.048
wed+0.047
 forgot+0.046
 built+0.046
Neg logit contributions
ay-0.059
arl-0.056
andel-0.054
 Today-0.053
oles-0.053
Token group
Token ID1448
Feature activation+2.95e-03

Pos logit contributions
 pretended+0.034
 found+0.033
 built+0.033
 put+0.033
 buried+0.033
Neg logit contributions
arl-0.033
ay-0.030
 Today-0.030
 Nice-0.029
andel-0.028
Token of
Token ID286
Feature activation+2.90e-02

Pos logit contributions
 pretended+0.008
wed+0.008
 punished+0.008
 remembered+0.008
 found+0.008
Neg logit contributions
ay-0.003
arl-0.002
 Nice-0.002
 Today-0.002
andel-0.002
Token sticks
Token ID16461
Feature activation-5.60e-03

Pos logit contributions
 pretended+0.051
 built+0.048
wed+0.048
 found+0.048
 buried+0.047
Neg logit contributions
arl-0.056
ay-0.053
 Nice-0.051
andel-0.050
 Today-0.050
Token and
Token ID290
Feature activation+7.26e-02

Pos logit contributions
arl+0.010
ay+0.009
 Today+0.009
 Nice+0.009
andel+0.009
Neg logit contributions
 pretended-0.008
 found-0.008
 built-0.007
 put-0.007
 buried-0.007
Token a
Token ID257
Feature activation+3.83e-02

Pos logit contributions
wed+0.117
 punished+0.114
 least+0.108
 buried+0.104
 cleaned+0.103
Neg logit contributions
 Nice-0.133
 Today-0.132
arl-0.128
ay-0.123
 Lots-0.120
Token slide
Token ID10649
Feature activation-3.66e-03

Pos logit contributions
 pretended+0.064
 found+0.062
 put+0.061
 built+0.061
 buried+0.060
Neg logit contributions
arl-0.082
ay-0.076
 Today-0.075
 Nice-0.074
andel-0.072
Token.
Token ID13
Feature activation-7.24e-03

Pos logit contributions
arl+0.008
ay+0.007
 Today+0.007
 Nice+0.007
andel+0.007
Neg logit contributions
 pretended-0.006
 found-0.006
 built-0.006
 put-0.006
 buried-0.006
Token They
Token ID1119
Feature activation+9.23e-02

Pos logit contributions
arl+0.014
ay+0.014
andel+0.013
omed+0.012
oral+0.012
Neg logit contributions
 pretended-0.013
 found-0.013
 put-0.013
 built-0.012
 played-0.012
Token also
Token ID635
Feature activation+1.06e-01

Pos logit contributions
 punished+0.145
asured+0.141
wed+0.139
 buried+0.134
 permission+0.133
Neg logit contributions
 Today-0.159
ay-0.153
arl-0.151
ifying-0.144
 sky-0.141
Token had
Token ID550
Feature activation+6.61e-02

Pos logit contributions
wed+0.139
 punished+0.137
 buried+0.137
 least+0.124
 pretended+0.124
Neg logit contributions
 Today-0.214
arl-0.205
ay-0.193
oms-0.184
 sky-0.182
Token a
Token ID257
Feature activation+3.30e-02

Pos logit contributions
 pretended+0.106
 punished+0.103
wed+0.101
 buried+0.099
 built+0.096
Neg logit contributions
arl-0.129
ay-0.126
 Today-0.119
ifying-0.116
 Nice-0.113
Token flashlight
Token ID38371
Feature activation-2.03e-02

Pos logit contributions
 pretended+0.066
 found+0.064
 built+0.063
 put+0.063
 buried+0.062
Neg logit contributions
arl-0.060
ay-0.055
 Today-0.053
 Nice-0.053
andel-0.051
Token that
Token ID326
Feature activation+5.38e-02

Pos logit contributions
arl+0.046
ay+0.043
 Today+0.042
 Nice+0.041
andel+0.040
Neg logit contributions
 pretended-0.031
 found-0.030
 built-0.030
 put-0.029
 buried-0.029
Token made
Token ID925
Feature activation+1.15e-02

Pos logit contributions
 punished+0.083
 pretended+0.082
wed+0.080
 built+0.078
 buried+0.078
Neg logit contributions
arl-0.105
ay-0.104
 Nice-0.101
 Today-0.101
oles-0.095
Token and
Token ID290
Feature activation+8.45e-02

Pos logit contributions
 pretended+0.110
wed+0.104
 buried+0.104
 punished+0.103
 built+0.103
Neg logit contributions
arl-0.153
 Today-0.146
ay-0.146
 Nice-0.143
ifying-0.138
Token family
Token ID1641
Feature activation+5.85e-02

Pos logit contributions
wed+0.115
 buried+0.104
 punished+0.103
 least+0.102
 pretended+0.100
Neg logit contributions
 Nice-0.170
arl-0.164
 Today-0.161
ay-0.157
oles-0.149
Token,
Token ID11
Feature activation+4.58e-02

Pos logit contributions
 pretended+0.097
wed+0.092
 buried+0.090
 punished+0.090
 built+0.088
Neg logit contributions
ay-0.104
arl-0.100
 Nice-0.099
oles-0.097
 Today-0.096
Token and
Token ID290
Feature activation+6.76e-02

Pos logit contributions
wed+0.072
 pretended+0.071
 buried+0.070
 punished+0.069
 found+0.069
Neg logit contributions
arl-0.090
 Nice-0.089
ay-0.087
 Today-0.085
ifying-0.079
Token how
Token ID703
Feature activation+2.61e-02

Pos logit contributions
wed+0.108
 pretended+0.104
 buried+0.102
 punished+0.101
 built+0.099
Neg logit contributions
 Nice-0.128
arl-0.125
ay-0.122
 Today-0.118
ifying-0.113
Token he
Token ID339
Feature activation+1.06e-01

Pos logit contributions
 pretended+0.047
 built+0.043
 buried+0.043
 found+0.043
 punished+0.042
Neg logit contributions
arl-0.053
ay-0.050
 Today-0.048
 Nice-0.047
ifying-0.045
Token could
Token ID714
Feature activation+6.88e-02

Pos logit contributions
 permission+0.107
wed+0.098
 seen+0.098
 punished+0.095
 least+0.092
Neg logit contributions
arl-0.212
 Nice-0.211
ay-0.206
br-0.205
arry-0.203
Token be
Token ID307
Feature activation+4.84e-02

Pos logit contributions
 pretended+0.091
wed+0.089
 punished+0.082
 built+0.080
 found+0.079
Neg logit contributions
arl-0.153
 Today-0.151
ay-0.145
oles-0.137
 Nice-0.137
Token more
Token ID517
Feature activation+8.25e-03

Pos logit contributions
 pretended+0.072
wed+0.071
 least+0.066
 buried+0.066
 built+0.066
Neg logit contributions
arl-0.094
ay-0.091
 Nice-0.086
 Today-0.086
ifying-0.085
Token thoughtful
Token ID22677
Feature activation-3.41e-03

Pos logit contributions
 pretended+0.013
 built+0.012
 found+0.012
wed+0.012
 buried+0.012
Neg logit contributions
arl-0.018
ay-0.016
 Today-0.016
 Nice-0.015
elly-0.015
Token to
Token ID284
Feature activation+4.76e-02

Pos logit contributions
arl+0.006
ay+0.006
 Today+0.006
 Nice+0.006
elly+0.005
Neg logit contributions
 pretended-0.006
 built-0.006
 found-0.006
 buried-0.006
 punished-0.006
Token around
Token ID1088
Feature activation+2.46e-02

Pos logit contributions
 pretended+0.031
 found+0.030
 built+0.029
 put+0.029
 buried+0.029
Neg logit contributions
arl-0.039
ay-0.037
 Today-0.036
 Nice-0.035
andel-0.034
Token the
Token ID262
Feature activation+7.46e-03

Pos logit contributions
 pretended+0.037
 built+0.035
 found+0.035
 punished+0.035
 buried+0.035
Neg logit contributions
arl-0.055
ay-0.052
 Today-0.052
 Nice-0.050
andel-0.048
Token block
Token ID2512
Feature activation-7.42e-03

Pos logit contributions
 pretended+0.015
 found+0.015
 built+0.015
 put+0.015
 buried+0.014
Neg logit contributions
arl-0.013
ay-0.012
 Today-0.012
 Nice-0.011
andel-0.011
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
arl+0.014
ay+0.013
 Today+0.013
 Nice+0.012
andel+0.012
Neg logit contributions
 pretended-0.014
 found-0.013
 punished-0.013
 put-0.013
 built-0.013
Token He
Token ID679
Feature activation+9.07e-02

Pos logit contributions
arl+0.023
andel+0.019
ay+0.019
omed+0.018
ifying+0.017
Neg logit contributions
 found-0.027
 pretended-0.027
 put-0.026
 built-0.026
 shared-0.025
Token even
Token ID772
Feature activation+1.06e-01

Pos logit contributions
 least+0.097
 permission+0.096
wed+0.096
 punished+0.095
 buried+0.089
Neg logit contributions
ay-0.182
 Today-0.178
 Nice-0.173
ifying-0.173
omed-0.173
Token waved
Token ID26834
Feature activation+7.56e-03

Pos logit contributions
 least+0.089
 permission+0.080
 buried+0.076
 punished+0.074
 share+0.069
Neg logit contributions
omed-0.227
arl-0.227
ay-0.225
br-0.223
lic-0.217
Token to
Token ID284
Feature activation+3.31e-02

Pos logit contributions
 pretended+0.013
 built+0.013
 found+0.013
 punished+0.012
 buried+0.012
Neg logit contributions
arl-0.015
ay-0.014
 Nice-0.014
 Today-0.014
andel-0.013
Token the
Token ID262
Feature activation+2.92e-03

Pos logit contributions
 pretended+0.047
 punished+0.044
 built+0.044
 buried+0.044
wed+0.043
Neg logit contributions
arl-0.075
ay-0.074
 Today-0.072
 Nice-0.071
andel-0.068
Token neighbors
Token ID12020
Feature activation+1.08e-02

Pos logit contributions
 pretended+0.005
 found+0.005
 built+0.005
 put+0.005
 buried+0.005
Neg logit contributions
arl-0.006
ay-0.005
 Today-0.005
 Nice-0.005
andel-0.005
Token as
Token ID355
Feature activation+3.57e-02

Pos logit contributions
 pretended+0.018
 found+0.017
 built+0.017
 punished+0.017
 buried+0.017
Neg logit contributions
arl-0.022
ay-0.021
 Today-0.021
 Nice-0.021
ifying-0.020
Token good
Token ID922
Feature activation-3.16e-02

Pos logit contributions
 pretended+0.008
wed+0.008
 built+0.008
 buried+0.007
 imagined+0.007
Neg logit contributions
arl-0.008
ay-0.007
apping-0.007
 onwards-0.007
aps-0.006
Token friends
Token ID2460
Feature activation-3.74e-02

Pos logit contributions
arl+0.063
ay+0.059
 Today+0.057
 Nice+0.054
elly+0.052
Neg logit contributions
 pretended-0.057
 built-0.056
 found-0.055
 buried-0.055
 put-0.054
Token and
Token ID290
Feature activation+1.70e-02

Pos logit contributions
arl+0.073
ay+0.068
 Today+0.066
 Nice+0.065
andel+0.062
Neg logit contributions
 pretended-0.068
 found-0.067
 built-0.066
 put-0.065
 buried-0.065
Token share
Token ID2648
Feature activation-1.86e-02

Pos logit contributions
wed+0.025
et+0.024
wy+0.024
 pretended+0.023
 built+0.023
Neg logit contributions
arl-0.035
ay-0.030
 Today-0.029
 Nice-0.029
 Sorry-0.028
Token the
Token ID262
Feature activation-4.68e-02

Pos logit contributions
arl+0.040
ay+0.038
 Today+0.037
 Nice+0.036
andel+0.035
Neg logit contributions
 pretended-0.030
 built-0.029
 found-0.029
 buried-0.028
 put-0.028
Token cr
Token ID1067
Feature activation-1.36e-01

Pos logit contributions
arl+0.091
ay+0.089
 Today+0.085
andel+0.079
 Nice+0.079
Neg logit contributions
 pretended-0.083
 punished-0.080
 found-0.078
 built-0.078
 shared-0.077
Tokenay
Token ID323
Feature activation-7.33e-02

Pos logit contributions
arl+0.070
 Nice+0.067
 Today+0.047
ifying+0.036
andel+0.028
Neg logit contributions
 built-0.431
 found-0.423
 put-0.420
 pretended-0.417
wed-0.413
Tokenons
Token ID684
Feature activation-7.03e-02

Pos logit contributions
arl+0.185
ay+0.175
 Today+0.171
 Nice+0.168
andel+0.164
Neg logit contributions
 pretended-0.094
 found-0.091
 built-0.089
 put-0.088
 buried-0.087
Token and
Token ID290
Feature activation+1.41e-02

Pos logit contributions
arl+0.123
ay+0.117
 Today+0.110
 Nice+0.106
ifying+0.102
Neg logit contributions
 pretended-0.142
 built-0.138
 found-0.137
 punished-0.134
 buried-0.134
Token the
Token ID262
Feature activation-4.08e-02

Pos logit contributions
wed+0.021
 punished+0.021
 found+0.020
 pretended+0.020
 buried+0.020
Neg logit contributions
arl-0.027
ay-0.026
 Today-0.025
 Nice-0.024
ifying-0.024
Token paper
Token ID3348
Feature activation-6.47e-02

Pos logit contributions
arl+0.081
ay+0.077
 Today+0.075
 Nice+0.071
andel+0.071
Neg logit contributions
 pretended-0.070
 found-0.067
 built-0.067
 punished-0.067
wed-0.066
Token They
Token ID1119
Feature activation+5.86e-02

Pos logit contributions
andel+0.124
arl+0.107
oles+0.107
anger+0.104
ane+0.103
Neg logit contributions
 put-0.086
 pretended-0.085
 made-0.085
 shared-0.083
 found-0.083
Token decide
Token ID5409
Feature activation-4.08e-03

Pos logit contributions
asured+0.084
 pretended+0.083
 seen+0.082
wed+0.081
 built+0.081
Neg logit contributions
arl-0.118
ay-0.103
 Today-0.101
ifying-0.093
omed-0.093
Token to
Token ID284
Feature activation+4.31e-02

Pos logit contributions
arl+0.008
 Today+0.007
ay+0.007
 Nice+0.007
omed+0.007
Neg logit contributions
 pretended-0.007
 built-0.007
 found-0.007
 buried-0.007
 punished-0.007
Token share
Token ID2648
Feature activation-1.48e-02

Pos logit contributions
 pretended+0.052
 seen+0.051
 remembered+0.047
 buried+0.046
 punished+0.046
Neg logit contributions
arl-0.103
ay-0.102
 Today-0.088
�-0.083
 Bang-0.081
Token the
Token ID262
Feature activation-4.46e-02

Pos logit contributions
arl+0.031
ay+0.030
 Today+0.029
 Nice+0.028
ifying+0.027
Neg logit contributions
 pretended-0.023
 built-0.022
 punished-0.022
 found-0.021
 buried-0.021
Token cr
Token ID1067
Feature activation-1.34e-01

Pos logit contributions
arl+0.092
ay+0.089
 Today+0.087
 Nice+0.082
andel+0.079
Neg logit contributions
 pretended-0.074
 punished-0.073
 built-0.071
 found-0.070
wed-0.069
Tokenay
Token ID323
Feature activation-7.26e-02

Pos logit contributions
arl+0.076
 Nice+0.062
 Today+0.050
ifying+0.040
omed+0.031
Neg logit contributions
 built-0.412
 put-0.406
 found-0.405
wed-0.401
 pretended-0.401
Tokenons
Token ID684
Feature activation-6.62e-02

Pos logit contributions
arl+0.179
ay+0.166
 Today+0.164
 Nice+0.162
andel+0.157
Neg logit contributions
 pretended-0.097
 found-0.094
 built-0.093
 put-0.092
 buried-0.090
Token.
Token ID13
Feature activation-5.13e-02

Pos logit contributions
arl+0.109
ay+0.105
 Today+0.098
 Nice+0.094
elly+0.090
Neg logit contributions
 pretended-0.137
 built-0.133
 found-0.132
 punished-0.131
 buried-0.128
Token They
Token ID1119
Feature activation+5.60e-02

Pos logit contributions
andel+0.121
oles+0.106
arl+0.103
ifying+0.099
anes+0.098
Neg logit contributions
 put-0.095
 found-0.093
 pretended-0.091
 made-0.090
 learned-0.090
Token color
Token ID3124
Feature activation-3.68e-02

Pos logit contributions
 seen+0.077
asured+0.073
 pretended+0.072
 built+0.070
 able+0.070
Neg logit contributions
arl-0.112
ay-0.105
 Today-0.101
 On-0.093
ifying-0.093
Token it
Token ID340
Feature activation-1.90e-02

Pos logit contributions
ay+0.036
arl+0.035
 Today+0.034
andel+0.033
 Nice+0.032
Neg logit contributions
 pretended-0.021
 built-0.021
 remembered-0.019
 buried-0.019
 found-0.019
Token reapp
Token ID24578
Feature activation-6.90e-02

Pos logit contributions
arl+0.038
 Today+0.037
ay+0.037
 Nice+0.036
br+0.033
Neg logit contributions
 punished-0.028
wed-0.028
 pretended-0.028
 built-0.028
 fought-0.027
Tokenear
Token ID451
Feature activation-6.04e-02

Pos logit contributions
arl+0.134
ay+0.125
 Today+0.121
 Nice+0.118
andel+0.115
Neg logit contributions
 pretended-0.129
 found-0.125
 built-0.124
 put-0.122
 buried-0.121
Token on
Token ID319
Feature activation-3.39e-02

Pos logit contributions
arl+0.124
ay+0.115
 Today+0.112
 Nice+0.110
andel+0.107
Neg logit contributions
 pretended-0.106
 found-0.103
 built-0.102
 put-0.101
 buried-0.100
Token the
Token ID262
Feature activation-4.92e-02

Pos logit contributions
arl+0.093
ay+0.088
 Today+0.086
 Nice+0.085
andel+0.083
Neg logit contributions
 pretended-0.036
 found-0.035
 put-0.034
 built-0.034
 buried-0.033
Token h
Token ID289
Feature activation-1.33e-01

Pos logit contributions
arl+0.114
ay+0.107
 Today+0.104
 Nice+0.103
andel+0.100
Neg logit contributions
 pretended-0.073
 found-0.071
 built-0.070
 put-0.068
 buried-0.068
Tokenanger
Token ID2564
Feature activation-7.14e-02

Pos logit contributions
arl+0.120
 Nice+0.117
 Today+0.111
ay+0.098
ifying+0.096
Neg logit contributions
 pretended-0.363
 built-0.360
 put-0.357
 found-0.356
 buried-0.346
Token.
Token ID13
Feature activation-5.74e-02

Pos logit contributions
arl+0.134
ay+0.126
 Today+0.122
 Nice+0.118
andel+0.113
Neg logit contributions
 pretended-0.134
 found-0.130
 built-0.129
 buried-0.127
 punished-0.127
Token<|endoftext|>
Token ID50256
Feature activation-5.30e-02

Pos logit contributions
andel+0.122
oles+0.115
eways+0.115
ifying+0.111
omed+0.111
Neg logit contributions
 put-0.094
 found-0.092
 pretended-0.090
 played-0.089
 her-0.088
TokenTom
Token ID13787
Feature activation+3.59e-02

Pos logit contributions
arl+0.094
andel+0.092
eeper+0.083
lights+0.079
 Nice+0.077
Neg logit contributions
 found-0.119
 made-0.112
 put-0.109
 tried-0.107
 played-0.106
Token and
Token ID290
Feature activation+3.58e-02

Pos logit contributions
ts+0.053
 punished+0.052
 able+0.047
 permission+0.047
eling+0.046
Neg logit contributions
 Today-0.069
ay-0.069
arl-0.063
elly-0.063
-0.063
Token he
Token ID339
Feature activation+6.16e-02

Pos logit contributions
arl+0.059
ay+0.056
 Today+0.055
 Nice+0.054
andel+0.051
Neg logit contributions
 pretended-0.043
 found-0.041
 built-0.041
 put-0.040
 buried-0.040
Token decided
Token ID3066
Feature activation+7.53e-03

Pos logit contributions
 seen+0.069
 least+0.069
 supervision+0.066
 permission+0.066
eling+0.064
Neg logit contributions
useum-0.117
RR-0.115
oral-0.115
Exc-0.114
way-0.113
Token to
Token ID284
Feature activation+4.53e-02

Pos logit contributions
 pretended+0.016
wed+0.016
 built+0.015
 least+0.015
 buried+0.015
Neg logit contributions
arl-0.011
 Nice-0.010
 Today-0.009
ay-0.009
fall-0.009
Token remove
Token ID4781
Feature activation-2.30e-02

Pos logit contributions
 pretended+0.060
 remembered+0.057
 seen+0.056
wed+0.055
 found+0.054
Neg logit contributions
arl-0.102
ay-0.101
 Today-0.097
arry-0.089
 On-0.088
Token the
Token ID262
Feature activation-4.84e-02

Pos logit contributions
arl+0.054
ay+0.053
 Today+0.050
andel+0.050
 Nice+0.049
Neg logit contributions
 pretended-0.031
 built-0.029
 punished-0.029
 found-0.029
 shared-0.028
Token seaw
Token ID32085
Feature activation-1.32e-01

Pos logit contributions
arl+0.099
ay+0.095
 Today+0.090
 Nice+0.088
andel+0.086
Neg logit contributions
 pretended-0.082
 punished-0.080
 built-0.078
 found-0.077
 shared-0.077
Tokeneed
Token ID2308
Feature activation-6.83e-02

Pos logit contributions
arl+0.184
 Today+0.170
 Nice+0.168
ay+0.163
ifying+0.150
Neg logit contributions
 pretended-0.305
 put-0.303
 built-0.303
 found-0.302
 buried-0.299
Token from
Token ID422
Feature activation-1.30e-02

Pos logit contributions
arl+0.126
ay+0.117
 Today+0.113
 Nice+0.109
andel+0.108
Neg logit contributions
 pretended-0.131
 found-0.126
 built-0.125
 punished-0.124
 shared-0.122
Token the
Token ID262
Feature activation-4.23e-02

Pos logit contributions
arl+0.028
ay+0.027
 Today+0.026
andel+0.025
 Nice+0.025
Neg logit contributions
 pretended-0.018
 punished-0.017
 found-0.017
 forgot-0.017
 shared-0.016
Token water
Token ID1660
Feature activation-5.61e-02

Pos logit contributions
arl+0.088
ay+0.081
 Today+0.079
 Nice+0.077
andel+0.075
Neg logit contributions
 pretended-0.073
 found-0.069
 built-0.069
 punished-0.068
 put-0.067
Token so
Token ID523
Feature activation-3.21e-02

Pos logit contributions
arl+0.117
ay+0.109
 Today+0.106
 Nice+0.103
andel+0.100
Neg logit contributions
 pretended-0.096
 found-0.093
 built-0.091
 put-0.090
 buried-0.089
Token to
Token ID284
Feature activation+3.53e-02

Pos logit contributions
 pretended+0.017
 punished+0.017
 found+0.016
 buried+0.016
 put+0.016
Neg logit contributions
arl-0.021
ay-0.019
 Today-0.019
 Nice-0.019
andel-0.018
Token draw
Token ID3197
Feature activation-4.80e-02

Pos logit contributions
 punished+0.050
wed+0.047
 seen+0.045
 pretended+0.043
wy+0.042
Neg logit contributions
 Today-0.073
ay-0.067
arl-0.067
�-0.066
 Nice-0.063
Token and
Token ID290
Feature activation+2.14e-02

Pos logit contributions
arl+0.106
ay+0.100
 Today+0.097
 Nice+0.096
andel+0.093
Neg logit contributions
 pretended-0.075
 found-0.073
 built-0.072
 put-0.071
 buried-0.071
Token shared
Token ID4888
Feature activation-8.42e-03

Pos logit contributions
wed+0.025
 punished+0.025
wy+0.023
eling+0.022
 pretended+0.021
Neg logit contributions
 Nice-0.047
ay-0.045
arl-0.044
 Today-0.044
ifying-0.042
Token the
Token ID262
Feature activation-4.86e-02

Pos logit contributions
arl+0.018
ay+0.018
 Today+0.017
 Nice+0.017
andel+0.016
Neg logit contributions
 pretended-0.013
 built-0.012
 punished-0.012
 found-0.012
 buried-0.012
Token cr
Token ID1067
Feature activation-1.32e-01

Pos logit contributions
arl+0.096
ay+0.093
 Today+0.090
 Nice+0.087
andel+0.083
Neg logit contributions
 pretended-0.086
 built-0.082
 found-0.082
 punished-0.082
 put-0.081
Tokenay
Token ID323
Feature activation-7.32e-02

Pos logit contributions
arl+0.068
 Nice+0.048
 Today+0.046
ifying+0.030
andel+0.022
Neg logit contributions
 built-0.422
 found-0.416
 pretended-0.414
 put-0.412
wed-0.405
Tokenons
Token ID684
Feature activation-6.07e-02

Pos logit contributions
arl+0.180
ay+0.169
 Today+0.166
 Nice+0.163
andel+0.159
Neg logit contributions
 pretended-0.098
 found-0.095
 built-0.093
 put-0.092
 buried-0.091
Token.
Token ID13
Feature activation-6.44e-02

Pos logit contributions
arl+0.103
ay+0.102
 Today+0.095
 Nice+0.093
oles+0.088
Neg logit contributions
 pretended-0.120
 built-0.116
 punished-0.116
 found-0.115
 buried-0.112
Token They
Token ID1119
Feature activation+5.12e-02

Pos logit contributions
arl+0.115
ay+0.095
andel+0.095
omed+0.092
oles+0.092
Neg logit contributions
 built-0.136
 pretended-0.136
 found-0.134
 put-0.133
 shared-0.130
Token were
Token ID547
Feature activation+1.36e-02

Pos logit contributions
 permission+0.079
 punished+0.074
asured+0.073
 seen+0.069
eling+0.068
Neg logit contributions
ay-0.075
 sky-0.074
l-0.071
ifying-0.070
 onward-0.069
Token go
Token ID467
Feature activation-1.56e-02

Pos logit contributions
 pretended+0.033
 built+0.031
 buried+0.030
 found+0.030
wed+0.029
Neg logit contributions
arl-0.066
 Today-0.063
ay-0.061
 Nice-0.060
arry-0.058
Token with
Token ID351
Feature activation-4.67e-03

Pos logit contributions
arl+0.035
ay+0.032
 Today+0.031
 Nice+0.031
andel+0.030
Neg logit contributions
 pretended-0.025
 built-0.024
 found-0.024
 buried-0.023
 put-0.023
Token a
Token ID257
Feature activation-1.81e-02

Pos logit contributions
arl+0.010
ay+0.010
 Today+0.009
 Nice+0.009
andel+0.009
Neg logit contributions
 pretended-0.007
 built-0.007
 found-0.007
 buried-0.006
wed-0.006
Token stranger
Token ID16195
Feature activation-3.35e-02

Pos logit contributions
arl+0.038
ay+0.036
 Today+0.035
 Nice+0.034
andel+0.034
Neg logit contributions
 found-0.031
 pretended-0.031
 put-0.030
 punished-0.029
 built-0.029
Token.
Token ID13
Feature activation-3.45e-02

Pos logit contributions
arl+0.064
ay+0.060
 Today+0.060
 Nice+0.058
ifying+0.056
Neg logit contributions
 pretended-0.059
 built-0.058
wed-0.056
 found-0.056
 buried-0.056
Token Str
Token ID4285
Feature activation-1.31e-01

Pos logit contributions
arl+0.054
andel+0.052
ay+0.051
omed+0.047
oles+0.046
Neg logit contributions
 put-0.071
 pretended-0.071
 found-0.069
 punished-0.067
 built-0.067
Tokenangers
Token ID6606
Feature activation-1.68e-02

Pos logit contributions
 Nice+0.196
ay+0.187
 Today+0.183
arl+0.181
ifying+0.172
Neg logit contributions
wed-0.266
 pretended-0.263
 built-0.261
 punished-0.260
 found-0.260
Token can
Token ID460
Feature activation+1.10e-02

Pos logit contributions
arl+0.036
ay+0.033
 Today+0.031
omed+0.030
 Nice+0.030
Neg logit contributions
 pretended-0.028
 buried-0.026
 built-0.026
 found-0.025
 punished-0.025
Token be
Token ID307
Feature activation+9.29e-03

Pos logit contributions
 pretended+0.016
 built+0.015
wed+0.015
 found+0.014
 buried+0.014
Neg logit contributions
arl-0.026
ay-0.024
 Today-0.024
 Nice-0.023
arry-0.022
Token bad
Token ID2089
Feature activation-3.25e-02

Pos logit contributions
 pretended+0.015
 built+0.014
 least+0.014
wed+0.014
 spent+0.014
Neg logit contributions
arl-0.017
ay-0.015
ifying-0.015
 Today-0.014
omed-0.014
Token and
Token ID290
Feature activation+2.51e-02

Pos logit contributions
arl+0.069
ay+0.065
 Today+0.064
 Nice+0.063
andel+0.059
Neg logit contributions
 pretended-0.053
 built-0.052
 found-0.051
 buried-0.051
 put-0.050
Token still
Token ID991
Feature activation+5.19e-02

Pos logit contributions
wed+0.056
 pretended+0.055
 buried+0.054
 built+0.052
asured+0.052
Neg logit contributions
arl-0.073
ay-0.071
ifying-0.066
br-0.064
arry-0.062
Token have
Token ID423
Feature activation+3.26e-02

Pos logit contributions
 pretended+0.072
 buried+0.064
wed+0.064
 spent+0.062
 punished+0.061
Neg logit contributions
arl-0.108
ay-0.105
 Today-0.102
 Nice-0.095
elly-0.094
Token to
Token ID284
Feature activation+3.67e-02

Pos logit contributions
 pretended+0.058
 buried+0.054
 built+0.053
 found+0.051
 punished+0.051
Neg logit contributions
arl-0.060
ay-0.055
ifying-0.052
elly-0.050
andel-0.050
Token remove
Token ID4781
Feature activation-2.48e-02

Pos logit contributions
 pretended+0.049
 found+0.042
 built+0.042
 buried+0.041
 remembered+0.040
Neg logit contributions
arl-0.093
ay-0.083
 Today-0.083
arry-0.075
andel-0.074
Token the
Token ID262
Feature activation-5.33e-02

Pos logit contributions
arl+0.064
ay+0.060
 Today+0.059
 Nice+0.058
andel+0.057
Neg logit contributions
 pretended-0.030
 found-0.029
 built-0.029
 put-0.028
 buried-0.028
Token cr
Token ID1067
Feature activation-1.30e-01

Pos logit contributions
arl+0.120
 Nice+0.110
ay+0.109
 Today+0.109
arry+0.104
Neg logit contributions
 pretended-0.084
 found-0.083
 put-0.081
 built-0.081
 buried-0.080
Tokenay
Token ID323
Feature activation-7.60e-02

Pos logit contributions
 Nice+0.088
arl+0.080
 Today+0.058
Really+0.049
 Hello+0.047
Neg logit contributions
 built-0.385
 put-0.375
 found-0.374
 made-0.372
wed-0.369
Tokenon
Token ID261
Feature activation-8.08e-02

Pos logit contributions
arl+0.211
 Nice+0.198
 Today+0.196
ifying+0.189
andel+0.186
Neg logit contributions
 pretended-0.075
 found-0.075
 built-0.075
 put-0.074
 made-0.067
Token marks
Token ID8849
Feature activation-7.88e-02

Pos logit contributions
arl+0.170
 Nice+0.158
 Today+0.155
ay+0.154
andel+0.150
Neg logit contributions
 pretended-0.134
 found-0.132
 put-0.132
 built-0.130
 buried-0.128
Token.
Token ID13
Feature activation-4.10e-02

Pos logit contributions
arl+0.166
 Nice+0.154
 Today+0.153
ay+0.152
andel+0.147
Neg logit contributions
 pretended-0.130
 put-0.129
 found-0.128
 built-0.127
 buried-0.123
Token White
Token ID2635
Feature activation-3.19e-02

Pos logit contributions
arl+0.067
andel+0.063
omed+0.062
oles+0.061
ay+0.061
Neg logit contributions
 put-0.080
 pretended-0.080
 found-0.078
 built-0.077
 least-0.075
Token book
Token ID1492
Feature activation-8.56e-02

Pos logit contributions
arl+0.070
ay+0.070
 Today+0.066
 Nice+0.060
andel+0.058
Neg logit contributions
 pretended-0.107
 punished-0.105
 built-0.103
 found-0.103
 buried-0.102
Token!
Token ID0
Feature activation-3.76e-02

Pos logit contributions
arl+0.172
ay+0.159
 Today+0.155
 Nice+0.153
andel+0.148
Neg logit contributions
 pretended-0.153
 found-0.150
 built-0.148
 put-0.147
 buried-0.145
Token You
Token ID921
Feature activation+3.92e-02

Pos logit contributions
arl+0.061
andel+0.056
ay+0.056
omed+0.055
ifying+0.053
Neg logit contributions
 found-0.077
 put-0.076
 pretended-0.076
 built-0.074
 shared-0.071
Token spoil
Token ID20851
Feature activation-3.37e-02

Pos logit contributions
et+0.056
 pretended+0.054
othy+0.054
asured+0.053
pa+0.053
Neg logit contributions
ay-0.071
ifying-0.068
arl-0.067
omed-0.059
br-0.057
Token the
Token ID262
Feature activation-4.78e-02

Pos logit contributions
arl+0.085
ay+0.081
 Today+0.078
 Nice+0.076
andel+0.075
Neg logit contributions
 pretended-0.043
 built-0.041
 found-0.041
 buried-0.040
 put-0.039
Token cr
Token ID1067
Feature activation-1.29e-01

Pos logit contributions
arl+0.073
ay+0.072
 Today+0.067
 Nice+0.063
andel+0.060
Neg logit contributions
 pretended-0.105
 punished-0.101
 found-0.101
 built-0.101
 buried-0.100
Tokenay
Token ID323
Feature activation-6.81e-02

Pos logit contributions
arl+0.056
 Nice+0.044
 Today+0.033
ifying+0.023
andel+0.020
Neg logit contributions
 built-0.414
 found-0.411
 pretended-0.409
 put-0.407
wed-0.400
Tokenons
Token ID684
Feature activation-5.75e-02

Pos logit contributions
arl+0.157
ay+0.156
 Today+0.146
 Nice+0.141
andel+0.139
Neg logit contributions
 pretended-0.101
 found-0.096
 buried-0.095
 built-0.095
 punished-0.094
Token!
Token ID0
Feature activation-3.99e-02

Pos logit contributions
arl+0.097
ay+0.096
 Today+0.085
ifying+0.080
elly+0.078
Neg logit contributions
 pretended-0.121
 built-0.113
 found-0.111
wed-0.110
 punished-0.109
Token You
Token ID921
Feature activation+3.71e-02

Pos logit contributions
arl+0.066
andel+0.061
omed+0.060
ay+0.059
 Nice+0.058
Neg logit contributions
 found-0.080
 put-0.079
 pretended-0.079
 built-0.078
 shared-0.075
Token spoil
Token ID20851
Feature activation-3.41e-02

Pos logit contributions
 pretended+0.053
et+0.053
othy+0.052
asured+0.052
pa+0.051
Neg logit contributions
ay-0.067
arl-0.064
ifying-0.062
omed-0.055
br-0.055
Token they
Token ID484
Feature activation+4.62e-02

Pos logit contributions
arl+0.046
ay+0.043
 Today+0.042
 Nice+0.041
omed+0.039
Neg logit contributions
 pretended-0.046
 built-0.045
 found-0.045
 punished-0.045
 buried-0.044
Token say
Token ID910
Feature activation-2.32e-02

Pos logit contributions
wed+0.065
 punished+0.065
 built+0.062
 seen+0.062
 pretended+0.061
Neg logit contributions
arl-0.099
 Today-0.091
ay-0.089
ifying-0.088
 Nice-0.084
Token goodbye
Token ID24829
Feature activation-5.08e-02

Pos logit contributions
arl+0.046
ay+0.042
andel+0.042
oky+0.041
ifying+0.040
Neg logit contributions
 found-0.043
 pretended-0.043
 put-0.043
 shared-0.042
 built-0.041
Token to
Token ID284
Feature activation-1.11e-02

Pos logit contributions
arl+0.116
ay+0.108
 Today+0.105
 Nice+0.104
andel+0.102
Neg logit contributions
 pretended-0.079
 found-0.077
 built-0.075
 put-0.075
 buried-0.074
Token the
Token ID262
Feature activation-4.52e-02

Pos logit contributions
arl+0.026
 Today+0.025
ay+0.025
 Nice+0.024
andel+0.024
Neg logit contributions
 pretended-0.015
 punished-0.015
 built-0.014
 found-0.014
 buried-0.014
Token oct
Token ID19318
Feature activation-1.28e-01

Pos logit contributions
arl+0.100
ay+0.093
 Today+0.091
 Nice+0.089
andel+0.087
Neg logit contributions
 pretended-0.073
 found-0.071
 built-0.070
 put-0.069
 buried-0.068
Tokenopus
Token ID25790
Feature activation-4.31e-02

Pos logit contributions
arl+0.201
 Today+0.200
ifying+0.171
andel+0.169
 Nice+0.166
Neg logit contributions
 found-0.267
 buried-0.266
 built-0.264
 pretended-0.261
 put-0.254
Token.
Token ID13
Feature activation-4.93e-02

Pos logit contributions
arl+0.073
 Today+0.069
ay+0.069
 Nice+0.067
omed+0.061
Neg logit contributions
 pretended-0.084
 punished-0.083
 built-0.082
 found-0.082
 buried-0.080
Token They
Token ID1119
Feature activation+5.35e-02

Pos logit contributions
andel+0.099
arl+0.098
ay+0.093
oles+0.092
arry+0.090
Neg logit contributions
 pretended-0.091
 put-0.090
 found-0.087
 played-0.085
 made-0.083
Token hug
Token ID16225
Feature activation-2.86e-02

Pos logit contributions
wed+0.077
 punished+0.076
 built+0.075
 seen+0.074
 pretended+0.071
Neg logit contributions
arl-0.111
 Today-0.099
ay-0.099
ifying-0.093
 Nice-0.092
Token it
Token ID340
Feature activation-4.37e-02

Pos logit contributions
arl+0.076
ay+0.072
 Today+0.071
 Nice+0.070
andel+0.068
Neg logit contributions
 pretended-0.032
 found-0.031
 built-0.031
 put-0.030
 buried-0.030
Token make
Token ID787
Feature activation-3.31e-02

Pos logit contributions
 pretended+0.019
 built+0.019
 buried+0.018
 found+0.018
wed+0.017
Neg logit contributions
arl-0.045
ay-0.041
 Today-0.039
 Nice-0.039
arry-0.038
Token the
Token ID262
Feature activation-5.00e-02

Pos logit contributions
arl+0.078
ay+0.073
 Today+0.072
 Nice+0.070
andel+0.069
Neg logit contributions
 pretended-0.048
 found-0.047
 built-0.046
 buried-0.045
 put-0.045
Token waiter
Token ID46612
Feature activation-4.20e-02

Pos logit contributions
arl+0.094
ay+0.085
 Today+0.082
oral+0.078
 Nice+0.077
Neg logit contributions
 pretended-0.098
 built-0.094
 found-0.093
wed-0.092
 punished-0.091
Token drop
Token ID4268
Feature activation-5.28e-02

Pos logit contributions
arl+0.082
ay+0.077
 Today+0.076
 Nice+0.073
oles+0.069
Neg logit contributions
 pretended-0.072
 built-0.071
wed-0.069
 found-0.069
 buried-0.068
Token the
Token ID262
Feature activation-5.28e-02

Pos logit contributions
arl+0.136
ay+0.128
 Today+0.126
 Nice+0.124
andel+0.121
Neg logit contributions
 pretended-0.065
 found-0.062
 built-0.061
 put-0.060
 buried-0.059
Token pizz
Token ID38748
Feature activation-1.27e-01

Pos logit contributions
arl+0.118
ay+0.112
 Today+0.105
andel+0.102
 Nice+0.101
Neg logit contributions
 pretended-0.084
 found-0.080
 built-0.079
 punished-0.079
 put-0.077
Tokenas
Token ID292
Feature activation-7.06e-02

Pos logit contributions
arl+0.232
 Today+0.227
 Nice+0.227
andel+0.209
ay+0.209
Neg logit contributions
 pretended-0.236
 found-0.235
 put-0.233
 built-0.233
 buried-0.227
Token.
Token ID13
Feature activation-5.22e-02

Pos logit contributions
arl+0.134
ay+0.124
 Today+0.121
 Nice+0.117
ifying+0.113
Neg logit contributions
 pretended-0.133
 found-0.129
 built-0.128
 put-0.124
 buried-0.124
Token They
Token ID1119
Feature activation+4.91e-02

Pos logit contributions
andel+0.122
ay+0.111
omed+0.110
arl+0.107
anger+0.107
Neg logit contributions
 pretended-0.078
 found-0.077
 put-0.076
 learned-0.074
 made-0.071
Token said
Token ID531
Feature activation-2.25e-02

Pos logit contributions
wed+0.059
asured+0.059
 permission+0.057
pa+0.056
 least+0.055
Neg logit contributions
arl-0.091
ifying-0.085
omed-0.085
l-0.082
Exc-0.081
Token sorry
Token ID7926
Feature activation-2.94e-02

Pos logit contributions
arl+0.044
ay+0.041
 Today+0.040
 Nice+0.039
andel+0.038
Neg logit contributions
 pretended-0.041
 found-0.040
 built-0.040
 put-0.040
 buried-0.039
Token not
Token ID407
Feature activation+2.02e-02

Pos logit contributions
 pretended+0.002
 buried+0.002
wed+0.002
 punished+0.002
 found+0.002
Neg logit contributions
 Today-0.004
arl-0.004
ay-0.003
 Nice-0.003
ork-0.003
Token like
Token ID588
Feature activation-4.47e-03

Pos logit contributions
 pretended+0.025
 buried+0.024
 punished+0.023
 built+0.022
wed+0.022
Neg logit contributions
arl-0.049
ay-0.047
 Today-0.047
andel-0.043
arry-0.043
Token to
Token ID284
Feature activation+3.29e-02

Pos logit contributions
arl+0.010
ay+0.009
 Nice+0.009
 Today+0.009
andel+0.009
Neg logit contributions
 pretended-0.007
 found-0.007
 built-0.007
 punished-0.006
 buried-0.006
Token share
Token ID2648
Feature activation-2.26e-02

Pos logit contributions
 buried+0.037
 pretended+0.036
 remembered+0.036
 punished+0.035
 built+0.035
Neg logit contributions
arl-0.076
ay-0.076
 Today-0.073
andel-0.068
arry-0.063
Token his
Token ID465
Feature activation-2.22e-02

Pos logit contributions
arl+0.048
ay+0.045
 Today+0.044
 Nice+0.043
andel+0.041
Neg logit contributions
 pretended-0.037
 found-0.036
 built-0.036
 buried-0.035
 put-0.035
Token cr
Token ID1067
Feature activation-1.27e-01

Pos logit contributions
arl+0.053
ay+0.051
 Today+0.050
 Nice+0.048
andel+0.047
Neg logit contributions
 pretended-0.030
 found-0.029
 built-0.029
 punished-0.029
 put-0.028
Tokenay
Token ID323
Feature activation-6.46e-02

Pos logit contributions
arl+0.056
 Nice+0.039
 Today+0.030
ifying+0.022
andel+0.016
Neg logit contributions
 built-0.415
 found-0.411
 pretended-0.410
 put-0.408
wed-0.400
Tokenons
Token ID684
Feature activation-6.98e-02

Pos logit contributions
ay+0.150
arl+0.150
 Today+0.139
 Nice+0.134
andel+0.133
Neg logit contributions
 pretended-0.093
 buried-0.088
 found-0.088
 punished-0.088
 built-0.087
Token with
Token ID351
Feature activation-1.85e-02

Pos logit contributions
arl+0.111
ay+0.109
 Today+0.101
 Nice+0.096
elly+0.092
Neg logit contributions
 pretended-0.147
 built-0.145
 found-0.144
 buried-0.139
 punished-0.139
Token his
Token ID465
Feature activation-1.63e-02

Pos logit contributions
arl+0.046
ay+0.043
 Today+0.042
 Nice+0.042
andel+0.041
Neg logit contributions
 pretended-0.024
 found-0.023
 built-0.023
 buried-0.022
 put-0.022
Token sister
Token ID6621
Feature activation-2.96e-02

Pos logit contributions
arl+0.039
ay+0.038
 Today+0.036
 Nice+0.035
andel+0.034
Neg logit contributions
 pretended-0.022
 built-0.021
 found-0.021
 punished-0.021
 buried-0.020
Token something
Token ID1223
Feature activation-2.78e-02

Pos logit contributions
arl+0.010
ay+0.010
 Today+0.009
andel+0.009
 Nice+0.009
Neg logit contributions
 pretended-0.007
 built-0.006
 found-0.006
 buried-0.006
 punished-0.006
Token new
Token ID649
Feature activation-3.54e-02

Pos logit contributions
arl+0.060
ay+0.056
 Today+0.055
 Nice+0.054
andel+0.052
Neg logit contributions
 pretended-0.045
 found-0.044
 built-0.044
 put-0.042
 buried-0.042
Token with
Token ID351
Feature activation-1.78e-02

Pos logit contributions
arl+0.063
ay+0.062
 Today+0.061
 Nice+0.059
elly+0.055
Neg logit contributions
 punished-0.066
 pretended-0.066
 built-0.064
 found-0.064
 buried-0.063
Token the
Token ID262
Feature activation-4.26e-02

Pos logit contributions
arl+0.040
ay+0.039
ifying+0.037
 Today+0.036
andel+0.036
Neg logit contributions
 pretended-0.026
 found-0.025
 built-0.024
 punished-0.024
 buried-0.024
Token melted
Token ID24178
Feature activation-5.31e-02

Pos logit contributions
arl+0.090
ay+0.089
 Today+0.084
andel+0.081
ifying+0.079
Neg logit contributions
 pretended-0.066
 built-0.064
 punished-0.064
wed-0.063
 found-0.063
Token cr
Token ID1067
Feature activation-1.27e-01

Pos logit contributions
ay+0.116
arl+0.113
andel+0.106
 Today+0.105
ifying+0.099
Neg logit contributions
 pretended-0.083
 punished-0.083
 built-0.080
 found-0.079
 buried-0.078
Tokenay
Token ID323
Feature activation-7.21e-02

Pos logit contributions
arl+0.060
 Nice+0.057
 Today+0.043
arry+0.023
ifying+0.019
Neg logit contributions
 built-0.401
 found-0.395
 pretended-0.393
 put-0.391
wed-0.388
Tokenons
Token ID684
Feature activation-6.59e-02

Pos logit contributions
arl+0.180
ay+0.172
 Today+0.166
 Nice+0.164
andel+0.160
Neg logit contributions
 pretended-0.094
 found-0.090
 built-0.089
 put-0.088
 buried-0.087
Token.
Token ID13
Feature activation-3.51e-02

Pos logit contributions
arl+0.121
ay+0.113
 Today+0.107
ifying+0.103
 Nice+0.101
Neg logit contributions
 pretended-0.127
 found-0.122
 built-0.122
 punished-0.120
 buried-0.118
Token Do
Token ID2141
Feature activation+2.44e-02

Pos logit contributions
arl+0.056
andel+0.053
ay+0.052
oles+0.052
omed+0.049
Neg logit contributions
 pretended-0.074
 put-0.073
 found-0.069
 built-0.069
 cleaned-0.067
Token you
Token ID345
Feature activation+2.23e-02

Pos logit contributions
 pretended+0.041
 built+0.039
 found+0.039
 buried+0.039
 punished+0.038
Neg logit contributions
arl-0.052
ay-0.048
 Today-0.047
 Nice-0.047
arry-0.044
Token stretches
Token ID23687
Feature activation-4.99e-02

Pos logit contributions
arl+0.047
ay+0.044
 Today+0.043
 Nice+0.042
andel+0.041
Neg logit contributions
 pretended-0.031
 found-0.030
 built-0.030
 put-0.030
 buried-0.029
Token or
Token ID393
Feature activation+2.16e-02

Pos logit contributions
arl+0.109
ay+0.102
 Today+0.100
 Nice+0.098
andel+0.095
Neg logit contributions
 pretended-0.080
 found-0.077
 built-0.076
 put-0.075
 buried-0.075
Token hop
Token ID1725
Feature activation-5.07e-02

Pos logit contributions
wed+0.027
 built+0.025
 pretended+0.025
 buried+0.024
 found+0.023
Neg logit contributions
arl-0.047
ifying-0.046
 Nice-0.046
 Today-0.045
ay-0.042
Token on
Token ID319
Feature activation-3.98e-02

Pos logit contributions
arl+0.111
ay+0.103
 Today+0.102
 Nice+0.100
andel+0.098
Neg logit contributions
 pretended-0.081
 found-0.080
 put-0.079
 built-0.078
 buried-0.077
Token the
Token ID262
Feature activation-4.58e-02

Pos logit contributions
arl+0.117
ay+0.110
 Today+0.108
 Nice+0.107
andel+0.104
Neg logit contributions
 pretended-0.035
 found-0.034
 put-0.033
 built-0.033
 buried-0.031
Token tr
Token ID491
Feature activation-1.26e-01

Pos logit contributions
arl+0.092
ay+0.085
 Today+0.082
 Nice+0.081
andel+0.079
Neg logit contributions
 pretended-0.083
 found-0.081
 put-0.080
 built-0.080
 buried-0.078
Tokenamp
Token ID696
Feature activation-7.59e-02

Pos logit contributions
arl+0.161
 Nice+0.147
 Today+0.129
ay+0.122
andel+0.121
Neg logit contributions
 built-0.310
 pretended-0.305
 found-0.302
 buried-0.295
 put-0.295
Tokenoline
Token ID14453
Feature activation-7.57e-02

Pos logit contributions
arl+0.127
 Nice+0.111
 Today+0.110
ay+0.109
ifying+0.105
Neg logit contributions
 pretended-0.159
 built-0.159
 found-0.158
 put-0.154
 buried-0.151
Token.
Token ID13
Feature activation-6.34e-02

Pos logit contributions
arl+0.142
ay+0.132
 Today+0.129
 Nice+0.126
andel+0.121
Neg logit contributions
 pretended-0.143
 found-0.139
 built-0.137
 put-0.136
 buried-0.135
Token Everyone
Token ID11075
Feature activation+3.76e-03

Pos logit contributions
arl+0.121
omed+0.102
lights+0.100
andel+0.100
ifying+0.099
Neg logit contributions
 found-0.121
 put-0.116
 learned-0.113
 made-0.113
 always-0.112
Token at
Token ID379
Feature activation-6.52e-03

Pos logit contributions
wed+0.005
 punished+0.005
 buried+0.005
 pretended+0.005
 built+0.005
Neg logit contributions
 Nice-0.007
ay-0.007
ore-0.007
 Today-0.007
oles-0.007
Token him
Token ID683
Feature activation-4.88e-03

Pos logit contributions
arl+0.021
ay+0.020
 Today+0.019
 Nice+0.019
andel+0.018
Neg logit contributions
 pretended-0.008
 built-0.008
 found-0.008
 buried-0.008
 punished-0.007
Token if
Token ID611
Feature activation-2.10e-03

Pos logit contributions
arl+0.011
 Nice+0.010
 Today+0.010
ay+0.010
omed+0.009
Neg logit contributions
 built-0.007
 pretended-0.007
 buried-0.007
 punished-0.007
 found-0.007
Token he
Token ID339
Feature activation+5.03e-02

Pos logit contributions
 Nice+0.003
arl+0.003
 Today+0.003
ay+0.003
oles+0.003
Neg logit contributions
wed-0.004
 pretended-0.004
 built-0.004
 punished-0.004
 buried-0.004
Token took
Token ID1718
Feature activation-1.62e-03

Pos logit contributions
 punished+0.077
 permission+0.074
 least+0.074
wed+0.072
eling+0.072
Neg logit contributions
ay-0.088
 Nice-0.088
elly-0.081
 Today-0.079
omed-0.079
Token her
Token ID607
Feature activation-3.29e-02

Pos logit contributions
ay+0.003
arl+0.003
 Today+0.003
andel+0.003
 Nice+0.003
Neg logit contributions
 built-0.003
 forgot-0.003
 pretended-0.002
 buried-0.002
 punished-0.002
Token cr
Token ID1067
Feature activation-1.26e-01

Pos logit contributions
arl+0.083
ay+0.078
 Today+0.077
 Nice+0.076
andel+0.074
Neg logit contributions
 pretended-0.042
 found-0.041
 built-0.040
 put-0.040
 buried-0.039
Tokenay
Token ID323
Feature activation-6.77e-02

Pos logit contributions
arl+0.056
 Nice+0.041
 Today+0.032
andel+0.019
omed+0.016
Neg logit contributions
 built-0.406
 found-0.405
 pretended-0.403
 put-0.400
wed-0.397
Tokenons
Token ID684
Feature activation-6.83e-02

Pos logit contributions
arl+0.163
 Today+0.148
 Nice+0.148
ay+0.146
andel+0.143
Neg logit contributions
 pretended-0.094
 found-0.093
 built-0.091
 put-0.090
 buried-0.087
Token.
Token ID13
Feature activation-6.07e-02

Pos logit contributions
arl+0.130
ay+0.126
 Today+0.118
 Nice+0.111
ifying+0.109
Neg logit contributions
 pretended-0.127
 built-0.121
 found-0.119
 punished-0.118
 put-0.116
Token He
Token ID679
Feature activation+4.77e-02

Pos logit contributions
andel+0.138
ifying+0.123
arl+0.123
plets+0.122
omed+0.120
Neg logit contributions
 found-0.103
 put-0.101
 pretended-0.100
 tried-0.094
 shared-0.092
Token said
Token ID531
Feature activation-1.37e-02

Pos logit contributions
 least+0.075
 permission+0.073
eling+0.069
wed+0.068
 seen+0.067
Neg logit contributions
oral-0.072
Exc-0.071
l-0.069
omed-0.069
ay-0.066
Token and
Token ID290
Feature activation+2.47e-02

Pos logit contributions
arl+0.133
ay+0.123
 Today+0.120
 Nice+0.118
andel+0.114
Neg logit contributions
 pretended-0.124
 found-0.122
 built-0.120
 put-0.119
 buried-0.118
Token put
Token ID1234
Feature activation-6.38e-03

Pos logit contributions
wed+0.028
 seen+0.027
 built+0.026
 punished+0.026
wy+0.026
Neg logit contributions
arl-0.054
 Today-0.051
ay-0.051
ifying-0.049
 Nice-0.048
Token it
Token ID340
Feature activation-3.07e-02

Pos logit contributions
ay+0.014
arl+0.014
 Today+0.013
andel+0.012
ifying+0.012
Neg logit contributions
 pretended-0.010
 built-0.009
 punished-0.009
 forgot-0.009
 buried-0.009
Token on
Token ID319
Feature activation-3.11e-02

Pos logit contributions
arl+0.064
ay+0.059
 Today+0.056
 Nice+0.054
omed+0.054
Neg logit contributions
 pretended-0.052
 punished-0.049
 built-0.049
 found-0.049
 put-0.047
Token the
Token ID262
Feature activation-4.57e-02

Pos logit contributions
arl+0.088
ay+0.082
 Nice+0.082
 Today+0.081
arry+0.079
Neg logit contributions
 pretended-0.031
 found-0.031
 put-0.031
 built-0.029
 buried-0.028
Token h
Token ID289
Feature activation-1.26e-01

Pos logit contributions
arl+0.098
ay+0.091
 Today+0.089
 Nice+0.087
andel+0.085
Neg logit contributions
 pretended-0.076
 found-0.074
 built-0.074
 put-0.072
 buried-0.071
Tokenanger
Token ID2564
Feature activation-6.98e-02

Pos logit contributions
arl+0.095
 Nice+0.086
 Today+0.084
ay+0.079
ifying+0.069
Neg logit contributions
 pretended-0.365
 built-0.359
 put-0.358
 found-0.357
 buried-0.354
Token.
Token ID13
Feature activation-4.88e-02

Pos logit contributions
arl+0.129
ay+0.121
 Today+0.117
 Nice+0.113
andel+0.109
Neg logit contributions
 pretended-0.135
 found-0.131
 built-0.129
 put-0.127
 buried-0.127
Token The
Token ID383
Feature activation-3.77e-02

Pos logit contributions
andel+0.109
ifying+0.105
arl+0.103
oles+0.102
eways+0.101
Neg logit contributions
 put-0.075
 found-0.072
 cleaned-0.071
 played-0.067
 drew-0.065
Token sock
Token ID32263
Feature activation-9.41e-03

Pos logit contributions
arl+0.082
ay+0.077
 Today+0.076
 Nice+0.072
andel+0.071
Neg logit contributions
 built-0.061
 pretended-0.059
 found-0.058
 shared-0.058
 punished-0.058
Token stays
Token ID14768
Feature activation-1.70e-02

Pos logit contributions
ay+0.015
oms+0.014
 Today+0.014
arl+0.014
br+0.013
Neg logit contributions
 seen-0.018
 punished-0.018
 pretended-0.017
 built-0.017
wed-0.017
Token,
Token ID11
Feature activation+1.88e-02

Pos logit contributions
arl+0.131
ay+0.122
 Today+0.120
 Nice+0.119
andel+0.115
Neg logit contributions
 pretended-0.093
 found-0.090
 built-0.089
 put-0.089
 buried-0.087
Token and
Token ID290
Feature activation+2.11e-02

Pos logit contributions
 pretended+0.030
 built+0.030
wed+0.029
 buried+0.029
 found+0.029
Neg logit contributions
arl-0.039
ay-0.036
 Today-0.036
 Nice-0.036
ifying-0.034
Token I
Token ID314
Feature activation+4.67e-02

Pos logit contributions
wed+0.031
 built+0.029
 buried+0.029
 pretended+0.029
 punished+0.028
Neg logit contributions
arl-0.045
ay-0.042
 Today-0.042
 Nice-0.041
ifying-0.039
Token shared
Token ID4888
Feature activation-5.75e-03

Pos logit contributions
ts+0.073
 buried+0.067
wed+0.065
 pretended+0.065
 built+0.064
Neg logit contributions
 Today-0.093
ay-0.093
arl-0.093
arry-0.085
oral-0.084
Token my
Token ID616
Feature activation-1.33e-02

Pos logit contributions
arl+0.014
ay+0.014
 Today+0.013
 Nice+0.013
andel+0.013
Neg logit contributions
 pretended-0.007
 built-0.007
 found-0.007
 buried-0.007
 punished-0.007
Token cr
Token ID1067
Feature activation-1.26e-01

Pos logit contributions
arl+0.030
ay+0.028
 Today+0.027
 Nice+0.026
andel+0.026
Neg logit contributions
 pretended-0.020
 built-0.019
 punished-0.019
 found-0.019
 buried-0.019
Tokenay
Token ID323
Feature activation-6.14e-02

Pos logit contributions
arl+0.048
 Nice+0.035
 Today+0.033
ifying+0.016
andel+0.012
Neg logit contributions
 built-0.408
 pretended-0.406
 found-0.406
 put-0.405
wed-0.398
Tokenons
Token ID684
Feature activation-6.79e-02

Pos logit contributions
arl+0.146
ay+0.143
 Today+0.133
 Nice+0.131
andel+0.129
Neg logit contributions
 pretended-0.087
 found-0.083
 buried-0.082
 built-0.082
 punished-0.081
Token with
Token ID351
Feature activation-1.93e-02

Pos logit contributions
arl+0.121
ay+0.118
 Today+0.109
 Nice+0.105
ifying+0.101
Neg logit contributions
 pretended-0.133
 built-0.130
 found-0.129
 punished-0.127
 buried-0.126
Token Ben
Token ID3932
Feature activation-3.63e-02

Pos logit contributions
arl+0.046
ay+0.043
 Today+0.042
 Nice+0.041
andel+0.040
Neg logit contributions
 pretended-0.028
 found-0.026
 built-0.026
 buried-0.026
 put-0.025
Token.
Token ID13
Feature activation-4.34e-02

Pos logit contributions
arl+0.064
ay+0.061
 Today+0.059
 Nice+0.057
ifying+0.054
Neg logit contributions
 pretended-0.069
 built-0.069
 found-0.068
 buried-0.068
 punished-0.066
Token They
Token ID1119
Feature activation+5.22e-02

Pos logit contributions
andel+0.107
arl+0.100
ay+0.092
omed+0.091
br+0.091
Neg logit contributions
 found-0.097
 pretended-0.089
 put-0.088
 made-0.087
 thought-0.086
Token tried
Token ID3088
Feature activation+1.89e-03

Pos logit contributions
wed+0.058
 least+0.057
 built+0.056
 pretended+0.056
asured+0.049
Neg logit contributions
arl-0.127
ay-0.110
omed-0.109
ifying-0.107
 Nice-0.105
Token to
Token ID284
Feature activation+4.02e-02

Pos logit contributions
 pretended+0.003
 found+0.003
 built+0.003
 put+0.003
 buried+0.003
Neg logit contributions
arl-0.004
ay-0.004
 Today-0.004
 Nice-0.004
andel-0.004
Token get
Token ID651
Feature activation-7.81e-03

Pos logit contributions
 built+0.061
 pretended+0.056
wed+0.056
 drew+0.053
 shared+0.053
Neg logit contributions
arl-0.091
ay-0.074
 Nice-0.071
 Today-0.071
andel-0.070
Token the
Token ID262
Feature activation-4.39e-02

Pos logit contributions
arl+0.014
ay+0.013
ore+0.013
 Nice+0.013
 Today+0.012
Neg logit contributions
 pretended-0.013
 built-0.013
 imagined-0.013
wed-0.013
 spent-0.012
Token oct
Token ID19318
Feature activation-1.26e-01

Pos logit contributions
arl+0.096
ay+0.089
 Today+0.087
 Nice+0.086
andel+0.083
Neg logit contributions
 pretended-0.072
 found-0.070
 built-0.069
 put-0.068
 buried-0.067
Tokenopus
Token ID25790
Feature activation-5.05e-02

Pos logit contributions
 Today+0.196
arl+0.194
 Nice+0.163
andel+0.162
ifying+0.159
Neg logit contributions
 found-0.266
 buried-0.265
 built-0.264
 pretended-0.260
 put-0.254
Token off
Token ID572
Feature activation-5.33e-02

Pos logit contributions
arl+0.111
ay+0.102
 Today+0.100
 Nice+0.099
andel+0.093
Neg logit contributions
 pretended-0.077
 built-0.076
 found-0.072
 spent-0.071
 shared-0.070
Token Tom
Token ID4186
Feature activation-3.17e-02

Pos logit contributions
arl+0.147
 Today+0.136
ay+0.135
 Nice+0.134
andel+0.131
Neg logit contributions
 pretended-0.057
 found-0.057
 put-0.056
 built-0.054
 buried-0.053
Token,
Token ID11
Feature activation+1.65e-02

Pos logit contributions
arl+0.076
ay+0.073
 Today+0.071
 Nice+0.069
andel+0.066
Neg logit contributions
 pretended-0.043
 built-0.041
 found-0.041
 buried-0.040
 punished-0.040
Token but
Token ID475
Feature activation+3.56e-03

Pos logit contributions
wed+0.037
 built+0.035
 pretended+0.035
 shared+0.034
 buried+0.034
Neg logit contributions
arl-0.024
 Today-0.021
 Nice-0.021
ifying-0.019
ay-0.018
Token'm
Token ID1101
Feature activation+8.57e-03

Pos logit contributions
wed+0.073
ts+0.073
 forth+0.070
et+0.070
 punished+0.069
Neg logit contributions
 Today-0.063
ay-0.061
arl-0.058
ore-0.058
elly-0.057
Token trying
Token ID2111
Feature activation-2.84e-04

Pos logit contributions
wed+0.013
 pretended+0.012
 shared+0.011
 imagined+0.011
 found+0.011
Neg logit contributions
arl-0.019
 Today-0.018
ay-0.017
andel-0.017
 Nice-0.016
Token to
Token ID284
Feature activation+4.10e-02

Pos logit contributions
arl+0.001
 Today+0.000
ay+0.000
 Nice+0.000
ifying+0.000
Neg logit contributions
 pretended-0.001
 punished-0.001
 found-0.001
wed-0.001
 built-0.001
Token get
Token ID651
Feature activation-6.56e-03

Pos logit contributions
wed+0.054
 pretended+0.054
 remembered+0.050
 punished+0.050
 forgot+0.049
Neg logit contributions
ay-0.091
arl-0.086
 Today-0.079
arry-0.077
andel-0.077
Token the
Token ID262
Feature activation-4.56e-02

Pos logit contributions
arl+0.013
ay+0.012
ifying+0.011
andel+0.011
ore+0.011
Neg logit contributions
 pretended-0.011
 forgot-0.010
wed-0.010
 imagined-0.010
 remembered-0.010
Token cr
Token ID1067
Feature activation-1.25e-01

Pos logit contributions
arl+0.097
ay+0.094
 Today+0.090
 Nice+0.087
ifying+0.084
Neg logit contributions
 pretended-0.073
 found-0.072
 built-0.071
 punished-0.071
 put-0.071
Tokenay
Token ID323
Feature activation-6.39e-02

Pos logit contributions
arl+0.066
 Nice+0.065
 Today+0.045
andel+0.035
ifying+0.034
Neg logit contributions
 built-0.384
 found-0.374
 put-0.371
 pretended-0.371
 made-0.367
Tokenons
Token ID684
Feature activation-5.88e-02

Pos logit contributions
arl+0.155
ay+0.144
 Today+0.142
 Nice+0.140
andel+0.136
Neg logit contributions
 pretended-0.089
 found-0.086
 built-0.085
 put-0.084
 buried-0.082
Token from
Token ID422
Feature activation-1.57e-02

Pos logit contributions
arl+0.119
ay+0.114
 Today+0.107
ifying+0.100
 Nice+0.100
Neg logit contributions
 pretended-0.105
 built-0.099
 found-0.098
 punished-0.096
 buried-0.096
Token the
Token ID262
Feature activation-4.54e-02

Pos logit contributions
arl+0.037
ay+0.036
 Today+0.034
andel+0.033
ifying+0.033
Neg logit contributions
 pretended-0.021
 built-0.020
 found-0.020
 punished-0.019
wed-0.019
Token cabinet
Token ID13447
Feature activation-7.02e-02

Pos logit contributions
arl+0.083
ay+0.077
 Today+0.075
 Nice+0.073
andel+0.070
Neg logit contributions
 pretended-0.090
 found-0.087
 built-0.087
 put-0.086
 buried-0.085
Token he
Token ID339
Feature activation+6.17e-02

Pos logit contributions
 pretended+0.018
wed+0.017
 built+0.017
 buried+0.016
 found+0.016
Neg logit contributions
arl-0.016
 Nice-0.015
 Today-0.015
ay-0.015
omed-0.014
Token wanted
Token ID2227
Feature activation+1.02e-02

Pos logit contributions
 least+0.077
 pretended+0.077
wed+0.074
ts+0.074
 permission+0.071
Neg logit contributions
ay-0.116
 Nice-0.114
oles-0.111
omed-0.110
 Today-0.110
Token to
Token ID284
Feature activation+4.05e-02

Pos logit contributions
 pretended+0.020
 built+0.018
wed+0.018
 punished+0.018
 found+0.018
Neg logit contributions
arl-0.016
ay-0.016
 Nice-0.015
 Today-0.015
andel-0.015
Token keep
Token ID1394
Feature activation+1.09e-03

Pos logit contributions
 pretended+0.054
wed+0.050
 built+0.046
 found+0.045
 buried+0.045
Neg logit contributions
arl-0.090
ay-0.090
 Today-0.090
arry-0.082
 Nice-0.082
Token the
Token ID262
Feature activation-4.97e-02

Pos logit contributions
 pretended+0.002
wed+0.002
 forgot+0.002
 built+0.002
 found+0.002
Neg logit contributions
 Today-0.002
arl-0.002
ay-0.002
 onwards-0.002
 Nice-0.002
Token oct
Token ID19318
Feature activation-1.25e-01

Pos logit contributions
arl+0.101
ay+0.096
 Today+0.094
 Nice+0.092
andel+0.089
Neg logit contributions
 pretended-0.087
 built-0.084
 found-0.084
 punished-0.082
 put-0.081
Tokenopus
Token ID25790
Feature activation-4.56e-02

Pos logit contributions
arl+0.206
 Today+0.192
 Nice+0.170
ifying+0.164
omed+0.160
Neg logit contributions
 found-0.263
 built-0.261
 buried-0.260
 put-0.253
 pretended-0.251
Token anyway
Token ID6949
Feature activation-3.70e-02

Pos logit contributions
arl+0.081
ay+0.079
 Today+0.079
oles+0.074
ifying+0.073
Neg logit contributions
 pretended-0.083
 built-0.076
wed-0.075
 found-0.073
 drew-0.073
Token.
Token ID13
Feature activation-5.66e-02

Pos logit contributions
arl+0.080
ay+0.074
 Nice+0.071
 Today+0.071
andel+0.070
Neg logit contributions
 found-0.061
 put-0.060
 pretended-0.060
 built-0.059
 buried-0.058
Token "
Token ID366
Feature activation-5.07e-03

Pos logit contributions
arl+0.087
ay+0.075
andel+0.075
ifying+0.074
omed+0.071
Neg logit contributions
 pretended-0.128
 found-0.128
 put-0.127
 built-0.126
 shared-0.121
TokenI
Token ID40
Feature activation+4.15e-02

Pos logit contributions
arl+0.009
ay+0.008
 Today+0.008
 Nice+0.008
andel+0.008
Neg logit contributions
 pretended-0.010
 found-0.010
 put-0.010
 built-0.010
 punished-0.010
Token on
Token ID319
Feature activation-3.46e-02

Pos logit contributions
arl+0.094
 Today+0.091
oral+0.091
arry+0.091
 Nice+0.089
Neg logit contributions
 found-0.048
 put-0.046
 buried-0.046
 made-0.045
 pretended-0.044
Token Tom
Token ID4186
Feature activation-8.51e-03

Pos logit contributions
arl+0.098
ay+0.091
 Today+0.090
 Nice+0.090
andel+0.088
Neg logit contributions
 found-0.034
 pretended-0.034
 put-0.034
 built-0.032
 buried-0.032
Token and
Token ID290
Feature activation+2.62e-02

Pos logit contributions
arl+0.018
ay+0.017
 Today+0.016
 Nice+0.016
andel+0.015
Neg logit contributions
 pretended-0.014
 built-0.014
 found-0.013
 punished-0.013
 buried-0.013
Token snatched
Token ID43276
Feature activation-9.84e-03

Pos logit contributions
wed+0.032
 least+0.031
 built+0.031
pa+0.028
 spent+0.028
Neg logit contributions
arl-0.060
 Nice-0.055
ifying-0.054
br-0.053
RR-0.053
Token the
Token ID262
Feature activation-4.77e-02

Pos logit contributions
ay+0.021
arl+0.020
 Today+0.018
andel+0.018
 Nice+0.018
Neg logit contributions
 pretended-0.016
 built-0.015
 punished-0.015
 spent-0.014
 forgot-0.014
Token fl
Token ID781
Feature activation-1.25e-01

Pos logit contributions
arl+0.099
ay+0.092
 Today+0.091
 Nice+0.089
andel+0.086
Neg logit contributions
 pretended-0.082
 found-0.080
 put-0.080
 built-0.078
 buried-0.078
Tokenute
Token ID1133
Feature activation-7.74e-02

Pos logit contributions
arl+0.103
 Nice+0.101
 Today+0.100
omed+0.084
ay+0.080
Neg logit contributions
 put-0.340
 pretended-0.335
 buried-0.335
 found-0.335
 built-0.327
Token from
Token ID422
Feature activation-9.19e-03

Pos logit contributions
arl+0.160
ay+0.148
 Today+0.145
 Nice+0.143
andel+0.138
Neg logit contributions
 pretended-0.134
 found-0.131
 built-0.129
 put-0.128
 buried-0.127
Token his
Token ID465
Feature activation-9.65e-03

Pos logit contributions
arl+0.022
ay+0.021
 Today+0.020
 Nice+0.020
andel+0.019
Neg logit contributions
 pretended-0.013
 built-0.012
 found-0.012
 buried-0.012
 put-0.012
Token hand
Token ID1021
Feature activation-6.26e-02

Pos logit contributions
arl+0.020
ay+0.019
 Today+0.019
 Nice+0.018
ifying+0.018
Neg logit contributions
 pretended-0.016
 built-0.016
 found-0.016
 punished-0.015
 put-0.015
Token.
Token ID13
Feature activation-5.50e-02

Pos logit contributions
arl+0.136
ay+0.125
 Nice+0.125
 Today+0.124
andel+0.122
Neg logit contributions
 pretended-0.101
 found-0.100
 put-0.100
 built-0.097
 buried-0.096
Token a
Token ID257
Feature activation+3.87e-03

Pos logit contributions
 pretended+0.053
 built+0.050
 found+0.050
 put+0.049
 punished+0.049
Neg logit contributions
arl-0.101
ay-0.096
 Today-0.094
 Nice-0.094
andel-0.090
Token beautiful
Token ID4950
Feature activation+9.50e-04

Pos logit contributions
 put+0.007
 found+0.007
 pretended+0.007
 buried+0.007
 built+0.007
Neg logit contributions
arl-0.008
ay-0.007
 Today-0.007
 Nice-0.007
omed-0.007
Token bird
Token ID6512
Feature activation-2.07e-03

Pos logit contributions
 pretended+0.002
 found+0.002
 put+0.002
 built+0.002
 buried+0.002
Neg logit contributions
arl-0.002
ay-0.002
 Today-0.002
 Nice-0.002
omed-0.002
Token.
Token ID13
Feature activation-2.78e-02

Pos logit contributions
arl+0.004
ay+0.004
 Today+0.004
 Nice+0.004
andel+0.003
Neg logit contributions
 pretended-0.004
 found-0.004
 built-0.004
 put-0.003
 punished-0.003
Token She
Token ID1375
Feature activation+7.31e-02

Pos logit contributions
arl+0.060
ay+0.052
andel+0.050
oral+0.050
ifying+0.048
Neg logit contributions
 put-0.051
 found-0.051
 pretended-0.049
 built-0.048
 tried-0.047
Token had
Token ID550
Feature activation+6.61e-02

Pos logit contributions
 punished+0.084
wed+0.081
 pretended+0.080
 least+0.080
 built+0.080
Neg logit contributions
 Nice-0.168
ay-0.164
arl-0.163
 Today-0.162
oles-0.161
Token colorful
Token ID20239
Feature activation+1.43e-02

Pos logit contributions
 pretended+0.074
 punished+0.072
wed+0.070
 built+0.067
 buried+0.067
Neg logit contributions
ay-0.157
arl-0.156
 Today-0.152
 Nice-0.151
ifying-0.149
Token feathers
Token ID27400
Feature activation-2.03e-02

Pos logit contributions
 pretended+0.022
 punished+0.022
 found+0.021
 built+0.021
 buried+0.021
Neg logit contributions
arl-0.030
ay-0.030
 Today-0.029
 Nice-0.028
andel-0.028
Token of
Token ID286
Feature activation+2.71e-02

Pos logit contributions
arl+0.043
ay+0.041
 Today+0.040
 Nice+0.039
ifying+0.038
Neg logit contributions
 pretended-0.033
 punished-0.032
 built-0.032
 found-0.032
 put-0.031
Token all
Token ID477
Feature activation+2.85e-02

Pos logit contributions
 pretended+0.042
 punished+0.041
 built+0.040
 found+0.039
wed+0.038
Neg logit contributions
arl-0.059
ay-0.056
 Nice-0.054
 Today-0.054
andel-0.053
Token textures
Token ID20028
Feature activation-2.23e-02

Pos logit contributions
 pretended+0.048
 punished+0.046
 buried+0.044
 found+0.044
 built+0.044
Neg logit contributions
arl-0.059
ay-0.057
 Today-0.056
 Nice-0.055
andel-0.052
Token He
Token ID679
Feature activation+1.03e-01

Pos logit contributions
 pretended+0.030
 found+0.030
 put+0.029
 built+0.028
 shared+0.028
Neg logit contributions
arl-0.025
andel-0.023
ay-0.022
omed-0.020
oral-0.019
Token was
Token ID373
Feature activation+6.59e-02

Pos logit contributions
 permission+0.123
 least+0.116
wed+0.115
 seen+0.111
 built+0.111
Neg logit contributions
 Today-0.200
 Nice-0.197
arl-0.193
omed-0.191
l-0.190
Token so
Token ID523
Feature activation+4.24e-02

Pos logit contributions
wed+0.110
 pretended+0.110
 built+0.101
 least+0.098
 drew+0.098
Neg logit contributions
arl-0.116
 Today-0.109
 Nice-0.109
ay-0.106
ifying-0.103
Token excited
Token ID6568
Feature activation+1.89e-02

Pos logit contributions
 pretended+0.067
 built+0.064
 found+0.063
 buried+0.062
 put+0.061
Neg logit contributions
arl-0.094
ay-0.087
 Today-0.085
 Nice-0.083
andel-0.079
Token!
Token ID0
Feature activation-1.39e-02

Pos logit contributions
 pretended+0.034
 punished+0.032
wed+0.032
 found+0.032
 built+0.032
Neg logit contributions
arl-0.036
ay-0.035
 Today-0.034
 Nice-0.034
arry-0.032
Token He
Token ID679
Feature activation+9.20e-02

Pos logit contributions
arl+0.027
andel+0.024
ay+0.022
omed+0.022
br+0.021
Neg logit contributions
 found-0.027
 put-0.026
 pretended-0.026
 built-0.025
 tried-0.024
Token grabbed
Token ID13176
Feature activation+5.13e-02

Pos logit contributions
 least+0.107
wed+0.105
 punished+0.100
 permission+0.098
 pretended+0.094
Neg logit contributions
ay-0.197
 Nice-0.194
arl-0.188
 Today-0.186
omed-0.184
Token the
Token ID262
Feature activation+4.34e-03

Pos logit contributions
 pretended+0.077
 built+0.075
 punished+0.074
 forgot+0.074
 shared+0.071
Neg logit contributions
ay-0.110
arl-0.107
andel-0.102
 Today-0.100
ifying-0.098
Token bone
Token ID9970
Feature activation-2.20e-02

Pos logit contributions
 pretended+0.008
 found+0.008
 built+0.008
 put+0.008
 punished+0.008
Neg logit contributions
arl-0.008
ay-0.007
 Today-0.007
 Nice-0.007
andel-0.007
Token and
Token ID290
Feature activation+7.12e-02

Pos logit contributions
arl+0.047
ay+0.045
 Today+0.044
 Nice+0.043
andel+0.041
Neg logit contributions
 pretended-0.036
 found-0.034
 built-0.034
 put-0.033
 punished-0.033
Token ran
Token ID4966
Feature activation+2.63e-02

Pos logit contributions
 least+0.102
wed+0.095
 permission+0.087
 punished+0.086
wy+0.083
Neg logit contributions
ay-0.121
ifying-0.121
apy-0.121
 Nice-0.120
 onwards-0.120
Token tore
Token ID26197
Feature activation-6.86e-03

Pos logit contributions
 least+0.070
 punished+0.067
 pretended+0.064
 built+0.060
 buried+0.059
Neg logit contributions
omed-0.135
ay-0.134
arl-0.130
andel-0.130
 Today-0.125
Token open
Token ID1280
Feature activation-2.14e-03

Pos logit contributions
arl+0.016
ay+0.016
 Today+0.015
 Nice+0.015
andel+0.015
Neg logit contributions
 pretended-0.009
 built-0.009
 found-0.009
 punished-0.009
 buried-0.008
Token the
Token ID262
Feature activation-1.41e-02

Pos logit contributions
arl+0.005
ay+0.005
 Today+0.004
 Nice+0.004
andel+0.004
Neg logit contributions
 pretended-0.003
 built-0.003
 punished-0.003
 found-0.003
 shared-0.003
Token envelope
Token ID22878
Feature activation-3.40e-02

Pos logit contributions
arl+0.028
ay+0.026
 Today+0.025
 Nice+0.025
andel+0.024
Neg logit contributions
 pretended-0.026
 found-0.025
 built-0.025
 put-0.025
 buried-0.024
Token.
Token ID13
Feature activation-3.23e-02

Pos logit contributions
arl+0.078
ay+0.071
 Today+0.070
 Nice+0.070
andel+0.068
Neg logit contributions
 pretended-0.052
 found-0.052
 put-0.051
 built-0.050
 buried-0.050
Token He
Token ID679
Feature activation+7.42e-02

Pos logit contributions
arl+0.062
andel+0.054
oral+0.053
br+0.050
oles+0.049
Neg logit contributions
 put-0.064
 found-0.063
 pretended-0.061
 built-0.061
 cleaned-0.057
Token pulled
Token ID5954
Feature activation+5.82e-03

Pos logit contributions
 least+0.114
 punished+0.101
 permission+0.100
eling+0.097
wed+0.096
Neg logit contributions
ay-0.137
omed-0.125
ork-0.124
Right-0.123
 On-0.122
Token out
Token ID503
Feature activation-1.17e-02

Pos logit contributions
 pretended+0.009
 built+0.009
 punished+0.009
 found+0.009
 buried+0.008
Neg logit contributions
arl-0.013
ay-0.012
 Today-0.012
 Nice-0.011
andel-0.011
Token a
Token ID257
Feature activation-5.95e-03

Pos logit contributions
ay+0.028
arl+0.028
 Today+0.026
 Nice+0.026
omed+0.026
Neg logit contributions
 pretended-0.015
 punished-0.015
 built-0.015
 found-0.014
 buried-0.014
Token small
Token ID1402
Feature activation-1.56e-02

Pos logit contributions
arl+0.013
 Today+0.011
 Nice+0.011
ay+0.011
andel+0.011
Neg logit contributions
 found-0.010
 pretended-0.010
 put-0.010
 buried-0.010
 built-0.010
Token wrapped
Token ID12908
Feature activation-1.49e-02

Pos logit contributions
arl+0.032
ay+0.031
 Today+0.030
 Nice+0.029
andel+0.029
Neg logit contributions
 pretended-0.026
 built-0.025
 punished-0.025
 found-0.025
wed-0.024
Token all
Token ID477
Feature activation+5.26e-02

Pos logit contributions
wed+0.079
 pretended+0.075
 least+0.073
 punished+0.073
 drew+0.069
Neg logit contributions
ay-0.089
 Today-0.081
arl-0.080
 onwards-0.079
 Nice-0.078
Token free
Token ID1479
Feature activation-7.50e-03

Pos logit contributions
wed+0.087
 pretended+0.084
 least+0.081
 remembered+0.079
 remember+0.078
Neg logit contributions
ay-0.091
 Today-0.084
arl-0.083
omed-0.082
 onwards-0.082
Token to
Token ID284
Feature activation+4.29e-02

Pos logit contributions
arl+0.015
ay+0.015
 Today+0.014
 Nice+0.014
omed+0.013
Neg logit contributions
 pretended-0.013
 built-0.012
 punished-0.012
 found-0.012
 put-0.012
Token take
Token ID1011
Feature activation+1.50e-02

Pos logit contributions
 punished+0.057
wed+0.056
 pretended+0.055
 buried+0.052
 built+0.050
Neg logit contributions
 Today-0.091
ay-0.089
arl-0.087
 Nice-0.083
 On-0.081
Token.
Token ID13
Feature activation-2.81e-02

Pos logit contributions
 pretended+0.022
 built+0.021
 found+0.020
 buried+0.020
 put+0.020
Neg logit contributions
arl-0.035
ay-0.034
 Today-0.032
 Nice-0.032
andel-0.031
Token She
Token ID1375
Feature activation+7.42e-02

Pos logit contributions
arl+0.053
andel+0.044
ay+0.043
br+0.042
ifying+0.041
Neg logit contributions
 found-0.057
 put-0.055
 pretended-0.054
 built-0.052
 shared-0.052
Token quickly
Token ID2952
Feature activation+5.81e-02

Pos logit contributions
wed+0.094
 permission+0.093
 least+0.092
 punished+0.088
 seen+0.085
Neg logit contributions
ay-0.137
 Nice-0.134
oles-0.128
omed-0.127
Right-0.126
Token grabbed
Token ID13176
Feature activation+3.46e-02

Pos logit contributions
 least+0.071
 pretended+0.056
wed+0.055
 remember+0.055
 punished+0.053
Neg logit contributions
arl-0.124
omed-0.124
ay-0.121
br-0.118
andel-0.118
Token the
Token ID262
Feature activation-1.51e-02

Pos logit contributions
 pretended+0.047
 built+0.047
 punished+0.045
 buried+0.044
 found+0.043
Neg logit contributions
arl-0.079
ay-0.079
andel-0.075
 Today-0.074
ifying-0.072
Token expensive
Token ID5789
Feature activation-2.38e-02

Pos logit contributions
arl+0.031
ay+0.030
 Today+0.029
 Nice+0.028
andel+0.027
Neg logit contributions
 pretended-0.026
 built-0.025
 found-0.025
 punished-0.025
 buried-0.025
Token book
Token ID1492
Feature activation-5.85e-02

Pos logit contributions
ay+0.045
arl+0.042
 Today+0.042
 Nice+0.039
andel+0.038
Neg logit contributions
 pretended-0.044
 punished-0.044
 built-0.044
wed-0.044
 shared-0.042
Token be
Token ID307
Feature activation+4.02e-02

Pos logit contributions
 punished+0.073
 pretended+0.070
wed+0.068
 cleaned+0.065
 built+0.065
Neg logit contributions
 Today-0.130
ay-0.127
 Nice-0.124
arl-0.124
arry-0.116
Token a
Token ID257
Feature activation+5.24e-03

Pos logit contributions
wed+0.058
 pretended+0.056
 punished+0.054
 built+0.053
 cleaned+0.053
Neg logit contributions
ay-0.086
arl-0.085
 Nice-0.083
 Today-0.081
ifying-0.078
Token butterfly
Token ID35113
Feature activation-1.13e-02

Pos logit contributions
 pretended+0.009
 found+0.009
 built+0.009
 put+0.009
 buried+0.009
Neg logit contributions
arl-0.011
ay-0.010
 Today-0.010
 Nice-0.010
andel-0.009
Token,
Token ID11
Feature activation+4.01e-02

Pos logit contributions
arl+0.022
ay+0.020
 Today+0.020
 Nice+0.020
andel+0.019
Neg logit contributions
 pretended-0.020
 found-0.020
 built-0.020
 punished-0.019
 buried-0.019
Token so
Token ID523
Feature activation+3.69e-03

Pos logit contributions
 pretended+0.059
 found+0.058
 built+0.057
 punished+0.057
 buried+0.057
Neg logit contributions
arl-0.088
ay-0.085
 Today-0.085
 Nice-0.084
andel-0.078
Token they
Token ID484
Feature activation+7.67e-02

Pos logit contributions
 pretended+0.006
 built+0.006
 buried+0.006
 found+0.006
 punished+0.006
Neg logit contributions
arl-0.007
ay-0.007
 Today-0.007
 Nice-0.007
ifying-0.006
Token fl
Token ID781
Feature activation-4.96e-02

Pos logit contributions
 punished+0.085
 least+0.078
wed+0.074
 buried+0.073
 seen+0.073
Neg logit contributions
arl-0.162
ay-0.162
ifying-0.162
 Nice-0.157
 Today-0.156
Tokenuttered
Token ID46322
Feature activation+1.46e-02

Pos logit contributions
arl+0.061
ay+0.054
 Today+0.054
 Nice+0.052
andel+0.049
Neg logit contributions
 pretended-0.125
 found-0.125
 built-0.123
 put-0.122
 buried-0.121
Token their
Token ID511
Feature activation+1.56e-02

Pos logit contributions
 punished+0.025
 pretended+0.025
 built+0.024
 buried+0.024
 put+0.024
Neg logit contributions
arl-0.027
ay-0.027
 Today-0.026
 Nice-0.026
omed-0.025
Token arms
Token ID5101
Feature activation-3.27e-02

Pos logit contributions
 pretended+0.026
 found+0.025
 built+0.025
 put+0.025
 buried+0.024
Neg logit contributions
arl-0.033
ay-0.031
 Today-0.030
 Nice-0.030
andel-0.029
Token and
Token ID290
Feature activation+4.97e-02

Pos logit contributions
arl+0.074
ay+0.069
 Today+0.067
 Nice+0.066
andel+0.064
Neg logit contributions
 pretended-0.051
 found-0.049
 built-0.049
 put-0.048
 buried-0.047
Token one
Token ID530
Feature activation+2.40e-02

Pos logit contributions
 pretended+0.024
 found+0.023
 built+0.022
 put+0.022
 buried+0.022
Neg logit contributions
arl-0.052
ay-0.050
 Today-0.049
 Nice-0.048
andel-0.047
Token was
Token ID373
Feature activation+3.63e-02

Pos logit contributions
 pretended+0.032
 built+0.031
 found+0.030
 punished+0.030
 put+0.030
Neg logit contributions
arl-0.057
ay-0.055
 Today-0.054
 Nice-0.053
andel-0.051
Token around
Token ID1088
Feature activation+3.69e-03

Pos logit contributions
 pretended+0.061
wed+0.058
 built+0.058
 found+0.055
 shared+0.055
Neg logit contributions
arl-0.070
 Today-0.064
 Nice-0.064
ay-0.063
omed-0.062
Token.
Token ID13
Feature activation-4.40e-02

Pos logit contributions
 pretended+0.006
 found+0.006
 built+0.006
 put+0.006
 buried+0.006
Neg logit contributions
arl-0.007
ay-0.007
 Today-0.007
 Nice-0.007
andel-0.006
Token He
Token ID679
Feature activation+6.15e-02

Pos logit contributions
arl+0.120
andel+0.107
ay+0.105
ifying+0.104
oral+0.100
Neg logit contributions
 found-0.057
 built-0.054
 put-0.053
 pretended-0.052
 buried-0.051
Token looked
Token ID3114
Feature activation+3.40e-02

Pos logit contributions
wed+0.072
 least+0.070
 punished+0.069
 pretended+0.067
 built+0.066
Neg logit contributions
omed-0.126
arry-0.123
ay-0.123
 Today-0.122
 Nice-0.121
Token around
Token ID1088
Feature activation+8.06e-03

Pos logit contributions
wed+0.062
 pretended+0.062
 built+0.060
 punished+0.060
 shared+0.059
Neg logit contributions
arl-0.057
 Today-0.056
omed-0.056
 Nice-0.055
ay-0.055
Token and
Token ID290
Feature activation+4.59e-02

Pos logit contributions
 pretended+0.013
 punished+0.013
 built+0.013
 found+0.012
 put+0.012
Neg logit contributions
arl-0.017
 Today-0.016
ay-0.016
 Nice-0.016
omed-0.015
Token saw
Token ID2497
Feature activation+2.93e-02

Pos logit contributions
wed+0.056
 punished+0.052
wy+0.048
 share+0.042
ws+0.042
Neg logit contributions
 Today-0.100
 Nice-0.099
omed-0.098
 horizon-0.095
 Right-0.094
Token a
Token ID257
Feature activation-8.24e-03

Pos logit contributions
 pretended+0.046
wed+0.043
 built+0.043
 punished+0.042
 shared+0.041
Neg logit contributions
ay-0.060
arl-0.060
 Nice-0.057
 Today-0.055
oles-0.055
Token big
Token ID1263
Feature activation-1.19e-02

Pos logit contributions
arl+0.016
ay+0.014
 Today+0.014
 Nice+0.014
andel+0.013
Neg logit contributions
 found-0.016
 pretended-0.016
 put-0.016
 buried-0.015
 built-0.015
Token best
Token ID1266
Feature activation+1.85e-02

Pos logit contributions
 pretended+0.073
wed+0.070
 buried+0.068
 built+0.068
 found+0.066
Neg logit contributions
arl-0.096
ay-0.095
 Nice-0.090
 Today-0.089
 onwards-0.086
Token friends
Token ID2460
Feature activation+2.22e-02

Pos logit contributions
 pretended+0.023
 found+0.022
 built+0.022
 buried+0.021
 put+0.021
Neg logit contributions
arl-0.048
ay-0.045
 Today-0.043
 Nice-0.043
andel-0.042
Token from
Token ID422
Feature activation+2.63e-02

Pos logit contributions
 pretended+0.041
 found+0.040
 built+0.039
 put+0.039
 buried+0.039
Neg logit contributions
arl-0.043
ay-0.040
 Today-0.039
 Nice-0.039
andel-0.037
Token that
Token ID326
Feature activation+3.44e-02

Pos logit contributions
 pretended+0.033
 built+0.032
 found+0.031
 punished+0.030
wed+0.030
Neg logit contributions
arl-0.063
 Today-0.059
ay-0.059
 Nice-0.059
ifying-0.057
Token day
Token ID1110
Feature activation+6.96e-03

Pos logit contributions
 pretended+0.066
 found+0.064
 built+0.064
 put+0.063
 buried+0.062
Neg logit contributions
arl-0.066
ay-0.061
 Today-0.059
 Nice-0.058
andel-0.056
Token on
Token ID319
Feature activation+1.02e-02

Pos logit contributions
 found+0.010
 put+0.010
 made+0.009
 built+0.009
 spent+0.009
Neg logit contributions
arl-0.017
 Nice-0.016
oral-0.016
useum-0.015
andel-0.015
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
 pretended+0.017
 found+0.017
 built+0.017
 put+0.017
 buried+0.016
Neg logit contributions
arl-0.022
ay-0.020
 Today-0.019
 Nice-0.019
andel-0.019
Token
Token ID220
Feature activation-4.23e-02

Pos logit contributions
arl+0.037
andel+0.032
omed+0.031
ay+0.030
ifying+0.029
Neg logit contributions
 pretended-0.044
 found-0.044
 put-0.042
 played-0.042
 built-0.042
Token
Token ID198
Feature activation-3.90e-02

Pos logit contributions
andel+0.070
arl+0.064
umm+0.063
 Nice+0.062
ifying+0.062
Neg logit contributions
 found-0.086
 put-0.082
 built-0.078
my-0.078
 fixed-0.076
Token
Token ID198
Feature activation-3.99e-02

Pos logit contributions
arl+0.061
ifying+0.054
andel+0.053
ay+0.051
oky+0.049
Neg logit contributions
 found-0.089
 put-0.087
 built-0.086
 pretended-0.086
 shared-0.085
TokenThe
Token ID464
Feature activation-7.22e-05

Pos logit contributions
arl+0.062
ay+0.055
 Today+0.053
 Nice+0.052
andel+0.051
Neg logit contributions
 pretended-0.091
 found-0.090
 built-0.089
 put-0.088
 shared-0.086
Token The
Token ID383
Feature activation+1.74e-02

Pos logit contributions
arl+0.005
ay+0.004
andel+0.004
omed+0.004
oral+0.004
Neg logit contributions
 found-0.006
 pretended-0.006
 put-0.006
 built-0.005
 played-0.005
Token mill
Token ID3939
Feature activation+2.68e-02

Pos logit contributions
 pretended+0.032
 found+0.032
 built+0.031
 put+0.031
 buried+0.031
Neg logit contributions
arl-0.034
ay-0.032
 Today-0.031
 Nice-0.031
omed-0.029
Token had
Token ID550
Feature activation+6.62e-02

Pos logit contributions
 pretended+0.038
 buried+0.034
 found+0.034
wed+0.034
 put+0.033
Neg logit contributions
ay-0.059
arl-0.059
 Today-0.056
omed-0.056
 Nice-0.055
Token a
Token ID257
Feature activation+3.59e-02

Pos logit contributions
 pretended+0.105
 punished+0.095
wed+0.094
 least+0.093
 remember+0.091
Neg logit contributions
arl-0.132
ay-0.131
ifying-0.121
 Today-0.121
 Nice-0.120
Token wheel
Token ID7825
Feature activation-6.07e-03

Pos logit contributions
 pretended+0.075
 found+0.073
 built+0.072
 put+0.071
 buried+0.071
Neg logit contributions
arl-0.062
ay-0.057
 Today-0.055
 Nice-0.053
andel-0.051
Token that
Token ID326
Feature activation+5.33e-02

Pos logit contributions
arl+0.013
ay+0.012
 Today+0.012
 Nice+0.011
andel+0.011
Neg logit contributions
 pretended-0.010
 found-0.010
 built-0.010
 punished-0.009
 buried-0.009
Token turned
Token ID2900
Feature activation-4.88e-03

Pos logit contributions
 pretended+0.069
 punished+0.065
wed+0.065
 buried+0.063
 built+0.062
Neg logit contributions
ay-0.120
arl-0.119
 Nice-0.116
 Today-0.115
oles-0.109
Token and
Token ID290
Feature activation+5.64e-02

Pos logit contributions
arl+0.011
 Today+0.010
 Nice+0.010
ay+0.010
arry+0.009
Neg logit contributions
 found-0.008
 pretended-0.008
 put-0.008
 built-0.008
 buried-0.008
Token made
Token ID925
Feature activation+1.99e-02

Pos logit contributions
 pretended+0.072
wed+0.072
 punished+0.070
 buried+0.067
 built+0.065
Neg logit contributions
arl-0.120
ay-0.116
 Nice-0.115
 Today-0.115
omed-0.113
Token noise
Token ID7838
Feature activation-2.56e-03

Pos logit contributions
 pretended+0.030
 punished+0.028
 found+0.028
 shared+0.027
 buried+0.027
Neg logit contributions
ay-0.043
arl-0.042
 Today-0.040
andel-0.039
 Nice-0.038
Token.
Token ID13
Feature activation-2.38e-02

Pos logit contributions
arl+0.005
ay+0.005
 Today+0.004
 Nice+0.004
andel+0.004
Neg logit contributions
 pretended-0.005
 found-0.005
 built-0.005
 buried-0.005
 put-0.005
Token to
Token ID284
Feature activation+3.58e-02

Pos logit contributions
 pretended+0.014
 found+0.014
 put+0.014
 built+0.014
 buried+0.014
Neg logit contributions
arl-0.024
ay-0.023
 Today-0.022
 Nice-0.022
andel-0.021
Token tending
Token ID44681
Feature activation+1.16e-02

Pos logit contributions
 pretended+0.046
 built+0.043
wed+0.043
 found+0.042
 buried+0.042
Neg logit contributions
arl-0.088
 Today-0.084
 Nice-0.082
ay-0.082
andel-0.077
Token the
Token ID262
Feature activation-1.51e-02

Pos logit contributions
 pretended+0.018
 built+0.017
 found+0.017
 punished+0.017
 buried+0.017
Neg logit contributions
arl-0.026
ay-0.025
 Today-0.024
 Nice-0.024
andel-0.023
Token garden
Token ID11376
Feature activation-3.71e-02

Pos logit contributions
arl+0.032
ay+0.030
 Today+0.029
 Nice+0.029
andel+0.028
Neg logit contributions
 pretended-0.025
 found-0.025
 put-0.024
 buried-0.024
 built-0.024
Token,
Token ID11
Feature activation+2.14e-02

Pos logit contributions
arl+0.072
ay+0.067
 Today+0.065
 Nice+0.064
andel+0.061
Neg logit contributions
 pretended-0.069
 found-0.067
 built-0.066
 put-0.065
 buried-0.065
Token knowing
Token ID6970
Feature activation+1.71e-02

Pos logit contributions
wed+0.033
 punished+0.031
 pretended+0.031
 built+0.030
 found+0.029
Neg logit contributions
arl-0.041
 Nice-0.041
 Today-0.039
ay-0.038
ifying-0.037
Token that
Token ID326
Feature activation+2.21e-02

Pos logit contributions
 pretended+0.028
 built+0.026
wed+0.026
 found+0.026
 punished+0.026
Neg logit contributions
arl-0.036
 Nice-0.033
ay-0.033
 Today-0.033
omed-0.031
Token the
Token ID262
Feature activation-1.10e-02

Pos logit contributions
 pretended+0.033
 built+0.032
 found+0.032
 buried+0.031
 punished+0.031
Neg logit contributions
arl-0.049
ay-0.047
 Today-0.046
 Nice-0.046
andel-0.043
Token hook
Token ID8011
Feature activation+9.39e-04

Pos logit contributions
arl+0.021
ay+0.019
 Today+0.019
 Nice+0.018
andel+0.018
Neg logit contributions
 pretended-0.021
 found-0.021
 built-0.020
 put-0.020
 buried-0.020
Token would
Token ID561
Feature activation+5.38e-02

Pos logit contributions
 pretended+0.001
 punished+0.001
wed+0.001
 built+0.001
 found+0.001
Neg logit contributions
ay-0.002
 Nice-0.002
arl-0.002
 Today-0.002
omed-0.002
Token be
Token ID307
Feature activation+2.86e-02

Pos logit contributions
 pretended+0.063
 punished+0.056
wed+0.055
 built+0.054
 found+0.054
Neg logit contributions
arl-0.140
 Today-0.131
ay-0.131
 Nice-0.126
ifying-0.121
Token His
Token ID2399
Feature activation+8.18e-03

Pos logit contributions
arl+0.085
ay+0.081
andel+0.079
ifying+0.074
omed+0.074
Neg logit contributions
 found-0.091
 pretended-0.089
 put-0.088
 built-0.086
 shared-0.085
Token parents
Token ID3397
Feature activation+4.57e-02

Pos logit contributions
 pretended+0.016
 built+0.016
 found+0.015
wed+0.015
 punished+0.015
Neg logit contributions
arl-0.015
ay-0.014
 Today-0.014
oral-0.013
 Nice-0.013
Token said
Token ID531
Feature activation+7.19e-03

Pos logit contributions
 pretended+0.073
wed+0.072
 built+0.068
 buried+0.066
ws+0.064
Neg logit contributions
ay-0.084
omed-0.083
arl-0.079
arry-0.074
oral-0.074
Token that
Token ID326
Feature activation+2.51e-02

Pos logit contributions
 pretended+0.013
 built+0.013
wed+0.012
 buried+0.012
 found+0.012
Neg logit contributions
arl-0.014
 Nice-0.013
ay-0.013
 Today-0.013
omed-0.012
Token they
Token ID484
Feature activation+7.22e-02

Pos logit contributions
 pretended+0.038
 punished+0.037
wed+0.036
 found+0.036
 built+0.036
Neg logit contributions
 Nice-0.050
arl-0.050
 Today-0.049
ay-0.048
oles-0.046
Token would
Token ID561
Feature activation+4.24e-02

Pos logit contributions
et+0.122
 pretended+0.122
anut+0.121
wed+0.119
bet+0.117
Neg logit contributions
ay-0.113
omed-0.106
t-0.098
ifying-0.096
oral-0.091
Token try
Token ID1949
Feature activation+7.28e-03

Pos logit contributions
 pretended+0.052
wed+0.048
 punished+0.045
 built+0.045
 buried+0.043
Neg logit contributions
arl-0.107
ay-0.103
 Today-0.102
arry-0.093
 Nice-0.090
Token to
Token ID284
Feature activation+5.19e-02

Pos logit contributions
 pretended+0.013
 punished+0.012
wed+0.012
 built+0.012
 found+0.012
Neg logit contributions
arl-0.013
 Today-0.013
ay-0.013
 Nice-0.012
omed-0.012
Token open
Token ID1280
Feature activation-7.70e-03

Pos logit contributions
 pretended+0.076
wed+0.072
 built+0.068
 remembered+0.063
 shared+0.063
Neg logit contributions
arl-0.109
ay-0.108
 Today-0.097
arry-0.096
pour-0.090
Token the
Token ID262
Feature activation-4.45e-02

Pos logit contributions
arl+0.017
ay+0.017
 Today+0.017
ifying+0.016
 Nice+0.016
Neg logit contributions
 pretended-0.011
 built-0.010
 punished-0.010
 found-0.010
 shared-0.010
Token chest
Token ID7721
Feature activation-5.66e-02

Pos logit contributions
arl+0.086
ay+0.079
 Today+0.077
 Nice+0.076
andel+0.074
Neg logit contributions
 pretended-0.084
 found-0.083
 put-0.081
 built-0.081
 buried-0.080
Token
Token ID198
Feature activation-7.84e-02

Pos logit contributions
ifying+0.151
andel+0.143
umm+0.140
arl+0.134
 Nice+0.129
Neg logit contributions
 found-0.150
 put-0.148
 learned-0.133
 find-0.132
 cleaned-0.131
TokenL
Token ID43
Feature activation-4.48e-02

Pos logit contributions
arl+0.133
ay+0.125
 Nice+0.123
 Today+0.121
andel+0.120
Neg logit contributions
 pretended-0.162
 found-0.162
 put-0.160
 built-0.156
 punished-0.154
Tokenily
Token ID813
Feature activation+3.98e-02

Pos logit contributions
arl+0.091
ay+0.082
 Today+0.080
 Nice+0.077
elly+0.076
Neg logit contributions
 pretended-0.083
 built-0.080
 found-0.078
 put-0.078
 punished-0.077
Token shook
Token ID14682
Feature activation-6.95e-03

Pos logit contributions
 seen+0.054
 least+0.054
 permission+0.053
 buried+0.051
 yours+0.051
Neg logit contributions
omed-0.074
Right-0.070
Exc-0.069
Conf-0.069
ay-0.069
Token her
Token ID607
Feature activation-1.79e-02

Pos logit contributions
arl+0.019
 Today+0.019
ay+0.018
 Nice+0.018
andel+0.017
Neg logit contributions
 built-0.007
 pretended-0.006
 buried-0.006
 found-0.006
 punished-0.006
Token head
Token ID1182
Feature activation-4.43e-02

Pos logit contributions
arl+0.048
ay+0.045
 Today+0.044
 Nice+0.043
andel+0.042
Neg logit contributions
 pretended-0.021
 built-0.020
 found-0.020
 buried-0.019
 put-0.019
Token.
Token ID13
Feature activation-5.49e-02

Pos logit contributions
arl+0.107
ay+0.099
andel+0.097
 Today+0.096
 Nice+0.096
Neg logit contributions
 pretended-0.063
 found-0.062
 put-0.062
 built-0.058
 made-0.058
Token She
Token ID1375
Feature activation+5.86e-02

Pos logit contributions
ifying+0.120
ay+0.117
andel+0.115
arl+0.115
omed+0.108
Neg logit contributions
 found-0.089
 put-0.087
 her-0.080
 tried-0.079
 pretended-0.079
Token did
Token ID750
Feature activation+1.18e-02

Pos logit contributions
 permission+0.081
 least+0.070
 built+0.070
wed+0.068
 share+0.067
Neg logit contributions
RR-0.108
omed-0.106
ay-0.103
Exc-0.103
Right-0.103
Token not
Token ID407
Feature activation+3.23e-02

Pos logit contributions
 pretended+0.014
 built+0.014
 buried+0.013
 found+0.013
wed+0.012
Neg logit contributions
arl-0.030
 Today-0.028
ay-0.027
 Nice-0.027
omed-0.027
Token want
Token ID765
Feature activation-6.95e-03

Pos logit contributions
 buried+0.045
 built+0.044
 pretended+0.042
 planted+0.042
wed+0.042
Neg logit contributions
arl-0.072
 Today-0.065
ay-0.064
arry-0.059
 Nice-0.057
Token lost
Token ID2626
Feature activation+2.90e-02

Pos logit contributions
ts+0.103
 pretended+0.102
 built+0.098
wed+0.097
 buried+0.096
Neg logit contributions
 Today-0.151
arl-0.150
ay-0.148
omed-0.139
arry-0.138
Token the
Token ID262
Feature activation+6.35e-03

Pos logit contributions
 pretended+0.042
 built+0.040
 found+0.038
wed+0.038
 punished+0.038
Neg logit contributions
arl-0.068
ay-0.065
 Nice-0.062
 Today-0.062
ifying-0.061
Token key
Token ID1994
Feature activation-2.03e-02

Pos logit contributions
 pretended+0.011
 built+0.011
 found+0.011
 put+0.011
wed+0.011
Neg logit contributions
arl-0.012
ay-0.012
 Today-0.011
 Nice-0.011
andel-0.011
Token."
Token ID526
Feature activation-3.21e-02

Pos logit contributions
arl+0.041
ay+0.039
 Today+0.038
 Nice+0.037
ifying+0.036
Neg logit contributions
 pretended-0.035
 found-0.034
 built-0.034
 punished-0.033
 put-0.033
Token
Token ID220
Feature activation-4.14e-02

Pos logit contributions
arl+0.058
ay+0.052
andel+0.049
 Today+0.048
ifying+0.047
Neg logit contributions
 found-0.067
 pretended-0.067
 put-0.065
 built-0.064
 buried-0.063
Token
Token ID198
Feature activation-4.71e-02

Pos logit contributions
ifying+0.070
arl+0.070
andel+0.069
 Nice+0.065
umm+0.061
Neg logit contributions
 found-0.084
 put-0.081
 built-0.075
 find-0.075
 fixed-0.074
Token
Token ID198
Feature activation-4.46e-02

Pos logit contributions
arl+0.081
ifying+0.076
andel+0.075
ay+0.070
 Nice+0.068
Neg logit contributions
 found-0.103
 put-0.100
 shared-0.094
 learned-0.093
 built-0.093
TokenB
Token ID33
Feature activation-2.76e-02

Pos logit contributions
arl+0.071
ay+0.064
 Today+0.062
 Nice+0.060
andel+0.058
Neg logit contributions
 pretended-0.100
 found-0.099
 built-0.097
 put-0.097
 buried-0.095
Tokenenny
Token ID11870
Feature activation+6.90e-02

Pos logit contributions
arl+0.046
 Today+0.042
ay+0.041
andel+0.040
 Nice+0.039
Neg logit contributions
 found-0.057
 pretended-0.056
 built-0.055
 put-0.055
 buried-0.055
Token thought
Token ID1807
Feature activation+1.42e-02

Pos logit contributions
 least+0.101
 seen+0.100
wed+0.099
 built+0.098
 pretended+0.098
Neg logit contributions
ay-0.118
arry-0.116
omed-0.115
ork-0.113
 Today-0.112
Token for
Token ID329
Feature activation+3.13e-02

Pos logit contributions
 pretended+0.022
 found+0.021
 built+0.021
 punished+0.021
 shared+0.020
Neg logit contributions
arl-0.032
ay-0.030
 Today-0.030
 Nice-0.029
omed-0.028
Token Sue
Token ID26089
Feature activation-8.25e-03

Pos logit contributions
wed+0.002
 pretended+0.002
 punished+0.002
 built+0.002
 buried+0.002
Neg logit contributions
arl-0.003
 Today-0.003
ay-0.003
 Nice-0.003
 On-0.003
Token's
Token ID338
Feature activation-1.46e-02

Pos logit contributions
 Today+0.017
arl+0.017
ay+0.016
 Nice+0.015
ifying+0.015
Neg logit contributions
 pretended-0.013
 punished-0.013
 built-0.012
wed-0.012
 found-0.012
Token house
Token ID2156
Feature activation-4.15e-02

Pos logit contributions
arl+0.024
ay+0.023
 Today+0.023
 Nice+0.020
andel+0.020
Neg logit contributions
 pretended-0.031
 built-0.030
wed-0.029
 punished-0.029
 found-0.029
Token.
Token ID13
Feature activation-5.80e-02

Pos logit contributions
arl+0.065
 Today+0.059
ay+0.059
 Nice+0.054
omed+0.052
Neg logit contributions
 pretended-0.085
 punished-0.084
 built-0.081
 found-0.081
 remembered-0.080
Token
Token ID198
Feature activation-5.67e-02

Pos logit contributions
ifying+0.101
andel+0.100
arl+0.097
ay+0.084
omed+0.082
Neg logit contributions
 found-0.130
 put-0.126
 built-0.122
 pretended-0.119
 played-0.118
Token
Token ID198
Feature activation-6.16e-02

Pos logit contributions
arl+0.102
ifying+0.100
andel+0.094
umm+0.092
 Nice+0.085
Neg logit contributions
 found-0.128
 put-0.121
 built-0.114
 made-0.113
 pretended-0.111
Token"
Token ID1
Feature activation+9.44e-03

Pos logit contributions
arl+0.102
andel+0.091
ifying+0.089
ay+0.086
 Nice+0.085
Neg logit contributions
 found-0.142
 built-0.139
 put-0.137
 pretended-0.136
 made-0.133
TokenLook
Token ID8567
Feature activation-7.95e-03

Pos logit contributions
 pretended+0.020
 found+0.020
 built+0.020
 put+0.020
 shared+0.019
Neg logit contributions
arl-0.016
ay-0.015
 Today-0.014
andel-0.014
 Nice-0.014
Token,
Token ID11
Feature activation-2.87e-03

Pos logit contributions
arl+0.016
ay+0.015
 Today+0.015
 Nice+0.014
andel+0.014
Neg logit contributions
 pretended-0.014
 built-0.014
 found-0.014
 put-0.013
 buried-0.013
Token Sue
Token ID26089
Feature activation+7.10e-03

Pos logit contributions
arl+0.005
ay+0.005
 Nice+0.005
 Today+0.005
arry+0.004
Neg logit contributions
 pretended-0.005
wed-0.005
 punished-0.005
 built-0.005
 found-0.005
Token!
Token ID0
Feature activation-2.70e-02

Pos logit contributions
 pretended+0.015
wed+0.015
 punished+0.014
 built+0.014
 buried+0.014
Neg logit contributions
ay-0.011
arl-0.011
 Today-0.010
 Nice-0.009
arry-0.009
Token bathrooms
Token ID32601
Feature activation+1.81e-02

Pos logit contributions
wed+0.070
 pretended+0.067
 least+0.067
 built+0.063
 seen+0.063
Neg logit contributions
arl-0.120
ifying-0.118
ay-0.115
apy-0.114
lights-0.113
Token and
Token ID290
Feature activation+5.74e-02

Pos logit contributions
 pretended+0.027
 punished+0.025
 buried+0.025
 built+0.025
 found+0.025
Neg logit contributions
arl-0.041
ay-0.039
 Today-0.037
omed-0.036
ifying-0.036
Token d
Token ID288
Feature activation-3.61e-02

Pos logit contributions
wed+0.065
 pretended+0.064
 least+0.061
 built+0.061
 found+0.059
Neg logit contributions
arl-0.117
ifying-0.113
ay-0.112
lights-0.106
apy-0.104
Tokenusted
Token ID8459
Feature activation-2.30e-03

Pos logit contributions
 Nice+0.072
 Today+0.070
arl+0.065
oral+0.064
ay+0.061
Neg logit contributions
 built-0.063
wed-0.063
 put-0.063
 found-0.062
 punished-0.062
Token the
Token ID262
Feature activation+8.59e-03

Pos logit contributions
arl+0.005
ay+0.004
 Today+0.004
 Nice+0.004
andel+0.004
Neg logit contributions
 pretended-0.004
 found-0.004
 built-0.004
 buried-0.004
 punished-0.004
Token windows
Token ID9168
Feature activation-3.44e-02

Pos logit contributions
 pretended+0.015
 found+0.015
 built+0.015
 put+0.014
 buried+0.014
Neg logit contributions
arl-0.017
ay-0.016
 Today-0.016
 Nice-0.016
andel-0.015
Token.
Token ID13
Feature activation-2.56e-02

Pos logit contributions
arl+0.067
ay+0.061
 Today+0.060
 Nice+0.059
andel+0.057
Neg logit contributions
 pretended-0.064
 found-0.062
 built-0.062
 put-0.061
 buried-0.061
Token
Token ID220
Feature activation-3.33e-02

Pos logit contributions
arl+0.048
ay+0.043
andel+0.043
oral+0.041
 Nice+0.040
Neg logit contributions
 found-0.048
 put-0.047
 pretended-0.047
 built-0.046
 cleaned-0.043
Token
Token ID198
Feature activation-3.88e-02

Pos logit contributions
andel+0.051
 Nice+0.050
arl+0.050
umm+0.048
ifying+0.047
Neg logit contributions
 found-0.072
 put-0.069
 built-0.068
 cleaned-0.065
 pretended-0.064
Token
Token ID198
Feature activation-3.75e-02

Pos logit contributions
arl+0.065
andel+0.061
ifying+0.060
umm+0.058
ay+0.058
Neg logit contributions
 found-0.083
 put-0.081
 built-0.077
 pretended-0.075
 shared-0.074
TokenEventually
Token ID28724
Feature activation+8.09e-03

Pos logit contributions
arl+0.065
ay+0.059
 Nice+0.057
andel+0.056
 Today+0.056
Neg logit contributions
 found-0.078
 pretended-0.077
 put-0.076
 built-0.076
 punished-0.073
Token the
Token ID262
Feature activation-3.04e-02

Pos logit contributions
 pretended+0.003
 found+0.003
 put+0.003
 built+0.003
 buried+0.002
Neg logit contributions
arl-0.006
ay-0.006
 Today-0.006
 Nice-0.006
omed-0.006
Token nice
Token ID3621
Feature activation-3.27e-02

Pos logit contributions
arl+0.070
ay+0.064
 Today+0.063
 Nice+0.063
andel+0.061
Neg logit contributions
 pretended-0.046
 found-0.045
 put-0.045
 built-0.044
 buried-0.043
Token walk
Token ID2513
Feature activation-3.85e-02

Pos logit contributions
arl+0.073
ay+0.067
 Today+0.066
 Nice+0.065
andel+0.063
Neg logit contributions
 pretended-0.052
 found-0.050
 put-0.050
 built-0.049
 buried-0.048
Token in
Token ID287
Feature activation-2.41e-03

Pos logit contributions
arl+0.083
ay+0.075
 Today+0.075
 Nice+0.073
andel+0.072
Neg logit contributions
 pretended-0.064
 found-0.063
 built-0.062
 put-0.062
 buried-0.060
Token the
Token ID262
Feature activation-2.94e-02

Pos logit contributions
arl+0.007
ay+0.006
 Nice+0.006
 Today+0.006
omed+0.006
Neg logit contributions
 pretended-0.002
 found-0.002
 put-0.002
 built-0.002
 buried-0.002
Token park
Token ID3952
Feature activation-3.20e-02

Pos logit contributions
arl+0.061
ay+0.054
 Nice+0.054
 Today+0.053
oles+0.052
Neg logit contributions
 found-0.052
 put-0.052
 pretended-0.052
 built-0.051
 buried-0.050
Token.
Token ID13
Feature activation-5.07e-02

Pos logit contributions
arl+0.065
ay+0.060
 Today+0.059
 Nice+0.058
andel+0.056
Neg logit contributions
 pretended-0.057
 found-0.055
 built-0.054
 put-0.054
 buried-0.053
Token
Token ID198
Feature activation-6.39e-02

Pos logit contributions
arl+0.096
andel+0.079
ay+0.078
ifying+0.075
br+0.073
Neg logit contributions
 found-0.104
 pretended-0.098
 put-0.097
 built-0.097
 learned-0.093
Token
Token ID198
Feature activation-6.69e-02

Pos logit contributions
arl+0.118
ifying+0.101
andel+0.099
 Nice+0.098
umm+0.096
Neg logit contributions
 found-0.138
 put-0.130
 built-0.128
 pretended-0.123
 learned-0.122
TokenAt
Token ID2953
Feature activation+6.25e-03

Pos logit contributions
arl+0.111
ay+0.094
 Nice+0.091
 Today+0.090
andel+0.090
Neg logit contributions
 found-0.151
 built-0.148
 pretended-0.148
 put-0.146
 shared-0.141
Token the
Token ID262
Feature activation-2.29e-02

Pos logit contributions
 pretended+0.007
 found+0.007
 built+0.007
 put+0.007
 buried+0.007
Neg logit contributions
arl-0.016
ay-0.016
 Today-0.015
 Nice-0.015
andel-0.015
Token wouldn
Token ID3636
Feature activation-2.37e-02

Pos logit contributions
 seen+0.015
 pretended+0.015
 built+0.015
wed+0.014
ilia+0.014
Neg logit contributions
arl-0.027
ay-0.026
omed-0.026
 Today-0.025
 Nice-0.025
Token't
Token ID470
Feature activation+2.88e-02

Pos logit contributions
arl+0.046
 Nice+0.041
 Today+0.040
ay+0.040
andel+0.039
Neg logit contributions
 put-0.045
 found-0.044
 pretended-0.043
 punished-0.042
 built-0.042
Token fall
Token ID2121
Feature activation-3.68e-02

Pos logit contributions
 pretended+0.040
 built+0.038
wed+0.037
 found+0.037
 buried+0.037
Neg logit contributions
arl-0.066
ay-0.060
 Today-0.060
 Nice-0.058
arry-0.056
Token off
Token ID572
Feature activation-3.83e-02

Pos logit contributions
arl+0.083
 Today+0.077
ay+0.077
 Nice+0.076
oral+0.076
Neg logit contributions
 pretended-0.056
 put-0.055
 found-0.055
 built-0.053
 buried-0.053
Token.
Token ID13
Feature activation-6.19e-02

Pos logit contributions
arl+0.078
ay+0.072
 Today+0.071
 Nice+0.069
andel+0.067
Neg logit contributions
 pretended-0.067
 found-0.066
 built-0.065
 put-0.064
 buried-0.063
Token
Token ID198
Feature activation-7.23e-02

Pos logit contributions
arl+0.107
andel+0.097
ay+0.094
ifying+0.094
oles+0.090
Neg logit contributions
 put-0.132
 found-0.132
 pretended-0.128
 built-0.124
 cleaned-0.123
Token
Token ID198
Feature activation-7.38e-02

Pos logit contributions
ifying+0.138
arl+0.135
umm+0.132
andel+0.129
 Nice+0.121
Neg logit contributions
 found-0.149
 put-0.143
 learned-0.131
 built-0.130
 find-0.130
TokenT
Token ID51
Feature activation-7.79e-02

Pos logit contributions
arl+0.128
 Nice+0.118
 Today+0.116
ay+0.115
andel+0.112
Neg logit contributions
 put-0.153
 found-0.150
 pretended-0.150
 built-0.149
 punished-0.148
Tokeneddy
Token ID21874
Feature activation+5.57e-03

Pos logit contributions
arl+0.106
 Nice+0.093
 Today+0.092
ay+0.092
ifying+0.089
Neg logit contributions
 pretended-0.183
 found-0.181
 put-0.180
 built-0.178
 buried-0.177
Token asked
Token ID1965
Feature activation-4.36e-03

Pos logit contributions
 seen+0.010
 built+0.009
 buried+0.009
wed+0.009
 permission+0.009
Neg logit contributions
ay-0.008
 Nice-0.008
arry-0.008
 Today-0.008
unt-0.007
Token Rabbit
Token ID25498
Feature activation-1.33e-02

Pos logit contributions
arl+0.010
ay+0.009
 Today+0.009
 Nice+0.009
andel+0.009
Neg logit contributions
 pretended-0.007
 built-0.006
 found-0.006
 buried-0.006
 put-0.006
Token to
Token ID284
Feature activation+4.38e-02

Pos logit contributions
 pretended+0.009
 built+0.009
 buried+0.008
wed+0.008
 punished+0.008
Neg logit contributions
arl-0.010
 Nice-0.009
 Today-0.009
ay-0.009
omed-0.008
Token climb
Token ID12080
Feature activation-2.65e-02

Pos logit contributions
 pretended+0.067
 punished+0.065
wed+0.064
 buried+0.063
 built+0.061
Neg logit contributions
ay-0.092
arl-0.092
 Today-0.091
arry-0.084
 Nice-0.083
Token it
Token ID340
Feature activation-3.23e-02

Pos logit contributions
arl+0.063
ay+0.060
 Today+0.059
 Nice+0.058
andel+0.056
Neg logit contributions
 pretended-0.037
 built-0.035
 found-0.035
 put-0.034
 punished-0.034
Token!
Token ID0
Feature activation-6.07e-02

Pos logit contributions
arl+0.069
ay+0.063
 Today+0.061
 Nice+0.061
andel+0.059
Neg logit contributions
 pretended-0.055
 found-0.054
 built-0.053
 put-0.053
 buried-0.052
Token
Token ID198
Feature activation-7.10e-02

Pos logit contributions
arl+0.112
ifying+0.096
andel+0.095
ay+0.091
oral+0.090
Neg logit contributions
 found-0.134
 put-0.129
 pretended-0.124
 built-0.120
 tried-0.120
Token
Token ID198
Feature activation-7.43e-02

Pos logit contributions
arl+0.119
ifying+0.112
andel+0.104
umm+0.101
 Nice+0.098
Neg logit contributions
 found-0.167
 put-0.160
 built-0.149
 pretended-0.149
 made-0.147
TokenSlow
Token ID36423
Feature activation-4.80e-02

Pos logit contributions
arl+0.121
ay+0.108
 Today+0.105
 Nice+0.103
andel+0.099
Neg logit contributions
 pretended-0.166
 found-0.165
 put-0.164
 built-0.161
 punished-0.156
Tokenly
Token ID306
Feature activation-8.50e-03

Pos logit contributions
arl+0.097
ay+0.091
 Today+0.088
 Nice+0.088
andel+0.084
Neg logit contributions
 pretended-0.085
 found-0.083
 put-0.082
 built-0.082
 buried-0.080
Token,
Token ID11
Feature activation-3.63e-02

Pos logit contributions
arl+0.014
ay+0.013
 Today+0.013
andel+0.013
oles+0.013
Neg logit contributions
 pretended-0.016
 punished-0.016
wed-0.016
 built-0.016
 shared-0.016
Token step
Token ID2239
Feature activation-4.65e-02

Pos logit contributions
arl+0.089
ay+0.083
 Today+0.082
 Nice+0.080
andel+0.078
Neg logit contributions
 pretended-0.050
 found-0.048
 built-0.047
 put-0.047
 buried-0.046
Token by
Token ID416
Feature activation-2.02e-02

Pos logit contributions
arl+0.090
ay+0.084
 Today+0.081
 Nice+0.080
andel+0.077
Neg logit contributions
 pretended-0.086
 built-0.083
 found-0.083
 put-0.081
 buried-0.081
Token is
Token ID318
Feature activation+2.93e-02

Pos logit contributions
 pretended+0.050
 built+0.049
 punished+0.047
 buried+0.047
wed+0.047
Neg logit contributions
arl-0.058
ay-0.058
 Today-0.057
 Nice-0.055
omed-0.055
Token a
Token ID257
Feature activation-2.21e-03

Pos logit contributions
 pretended+0.043
 built+0.040
 found+0.040
wed+0.039
 punished+0.039
Neg logit contributions
arl-0.064
 Today-0.061
ay-0.060
 Nice-0.059
ifying-0.057
Token balloon
Token ID21190
Feature activation-4.88e-02

Pos logit contributions
arl+0.005
ay+0.004
 Today+0.004
omed+0.004
 Nice+0.004
Neg logit contributions
 pretended-0.004
 found-0.004
 put-0.004
 buried-0.004
 built-0.004
Token."
Token ID526
Feature activation-5.45e-02

Pos logit contributions
arl+0.091
ay+0.086
 Today+0.084
 Nice+0.081
ifying+0.077
Neg logit contributions
 pretended-0.092
 found-0.090
 built-0.089
 punished-0.087
 put-0.087
Token
Token ID198
Feature activation-7.36e-02

Pos logit contributions
arl+0.096
ifying+0.091
andel+0.088
ay+0.087
 Nice+0.080
Neg logit contributions
 found-0.120
 put-0.119
 pretended-0.112
 tried-0.111
 thought-0.106
Token
Token ID198
Feature activation-7.27e-02

Pos logit contributions
ifying+0.167
umm+0.162
andel+0.160
arl+0.150
 Nice+0.145
Neg logit contributions
 found-0.130
 put-0.128
 find-0.106
 learned-0.106
 cleaned-0.105
TokenThey
Token ID2990
Feature activation+6.54e-02

Pos logit contributions
arl+0.134
 Nice+0.126
ay+0.124
 Today+0.121
andel+0.121
Neg logit contributions
 found-0.146
 put-0.144
 pretended-0.141
 built-0.140
 punished-0.135
Token ran
Token ID4966
Feature activation-1.89e-04

Pos logit contributions
 punished+0.074
 least+0.074
 buried+0.068
 built+0.067
asured+0.066
Neg logit contributions
ifying-0.136
omed-0.133
ay-0.128
arl-0.123
Exc-0.120
Token to
Token ID284
Feature activation+1.46e-02

Pos logit contributions
arl+0.000
ay+0.000
 Today+0.000
 Nice+0.000
andel+0.000
Neg logit contributions
 pretended-0.000
 built-0.000
 found-0.000
 punished-0.000
 put-0.000
Token the
Token ID262
Feature activation-2.51e-02

Pos logit contributions
 built+0.022
 pretended+0.022
wed+0.021
 punished+0.021
 buried+0.020
Neg logit contributions
arl-0.031
 Today-0.030
ay-0.029
 Nice-0.028
andel-0.027
Token big
Token ID1263
Feature activation-4.80e-02

Pos logit contributions
arl+0.047
ay+0.043
 Today+0.042
 Nice+0.041
andel+0.040
Neg logit contributions
 pretended-0.049
 found-0.048
 built-0.047
 put-0.047
 buried-0.046
Token it
Token ID340
Feature activation+1.63e-04

Pos logit contributions
 pretended+0.070
 punished+0.063
 built+0.062
wed+0.059
 forgot+0.059
Neg logit contributions
ay-0.073
arl-0.070
ifying-0.068
 Today-0.067
br-0.066
Token!
Token ID0
Feature activation-1.79e-02

Pos logit contributions
 pretended+0.000
 found+0.000
 built+0.000
 put+0.000
 buried+0.000
Neg logit contributions
arl-0.000
ay-0.000
 Today-0.000
 Nice-0.000
andel-0.000
Token Go
Token ID1514
Feature activation+1.30e-02

Pos logit contributions
arl+0.029
ay+0.026
andel+0.026
omed+0.026
ifying+0.024
Neg logit contributions
 put-0.037
 found-0.037
 pretended-0.036
 built-0.035
 buried-0.034
Token away
Token ID1497
Feature activation-2.76e-02

Pos logit contributions
 pretended+0.017
 built+0.016
 buried+0.015
 punished+0.015
wed+0.015
Neg logit contributions
arl-0.033
ay-0.031
 Today-0.030
ifying-0.028
 Nice-0.028
Token!"
Token ID2474
Feature activation-4.71e-02

Pos logit contributions
arl+0.059
ay+0.055
 Today+0.053
 Nice+0.052
andel+0.051
Neg logit contributions
 pretended-0.046
 found-0.044
 built-0.044
 put-0.043
 buried-0.043
Token
Token ID198
Feature activation-7.55e-02

Pos logit contributions
arl+0.086
ifying+0.081
andel+0.080
ay+0.078
umm+0.076
Neg logit contributions
 found-0.102
 put-0.102
 tried-0.095
 pretended-0.094
 thought-0.094
Token
Token ID198
Feature activation-7.37e-02

Pos logit contributions
ifying+0.155
umm+0.151
andel+0.150
arl+0.144
 Nice+0.141
Neg logit contributions
 found-0.148
 put-0.148
 learned-0.130
 find-0.130
 thought-0.127
TokenThe
Token ID464
Feature activation-3.19e-02

Pos logit contributions
arl+0.129
ay+0.121
 Today+0.120
 Nice+0.117
andel+0.114
Neg logit contributions
 found-0.155
 pretended-0.154
 put-0.152
 built-0.147
 punished-0.146
Token twins
Token ID20345
Feature activation+5.26e-02

Pos logit contributions
arl+0.062
ay+0.054
 Today+0.054
andel+0.052
 Nice+0.052
Neg logit contributions
 pretended-0.062
 built-0.059
 found-0.059
 buried-0.058
 put-0.057
Token were
Token ID547
Feature activation+2.88e-02

Pos logit contributions
 pretended+0.059
 built+0.059
 buried+0.057
wed+0.057
 punished+0.052
Neg logit contributions
arl-0.125
ay-0.120
omed-0.117
 Today-0.115
 Nice-0.114
Token scared
Token ID12008
Feature activation-2.85e-02

Pos logit contributions
 pretended+0.052
 built+0.050
wed+0.048
 found+0.048
 drew+0.046
Neg logit contributions
arl-0.057
 Today-0.049
ay-0.049
 Nice-0.048
omed-0.047
Token't
Token ID470
Feature activation+4.56e-02

Pos logit contributions
arl+0.018
ay+0.016
 Today+0.016
 Nice+0.016
andel+0.016
Neg logit contributions
 put-0.020
 found-0.020
 pretended-0.020
 punished-0.020
 built-0.020
Token hurt
Token ID5938
Feature activation-1.89e-02

Pos logit contributions
 pretended+0.059
 built+0.058
wed+0.055
 punished+0.055
 buried+0.054
Neg logit contributions
arl-0.108
 Today-0.098
ay-0.097
 Nice-0.096
arry-0.093
Token you
Token ID345
Feature activation-5.42e-03

Pos logit contributions
arl+0.047
ay+0.045
 Today+0.044
 Nice+0.043
andel+0.042
Neg logit contributions
 pretended-0.025
 found-0.024
 built-0.023
 put-0.023
 buried-0.023
Token."
Token ID526
Feature activation-5.45e-02

Pos logit contributions
arl+0.010
ay+0.010
 Today+0.009
 Nice+0.009
andel+0.009
Neg logit contributions
 pretended-0.010
 found-0.010
 built-0.010
 put-0.010
 buried-0.010
Token
Token ID198
Feature activation-7.29e-02

Pos logit contributions
arl+0.107
andel+0.104
ifying+0.103
ay+0.096
omed+0.092
Neg logit contributions
 found-0.114
 put-0.110
 thought-0.105
 tried-0.104
 pretended-0.101
Token
Token ID198
Feature activation-7.01e-02

Pos logit contributions
ifying+0.136
andel+0.132
umm+0.127
arl+0.124
 Nice+0.121
Neg logit contributions
 found-0.154
 put-0.153
 tried-0.136
 never-0.136
 thought-0.136
TokenHe
Token ID1544
Feature activation+5.80e-02

Pos logit contributions
arl+0.125
andel+0.122
ay+0.122
 Today+0.117
 Nice+0.117
Neg logit contributions
 found-0.143
 put-0.141
 punished-0.136
 pretended-0.135
 shared-0.133
Token takes
Token ID2753
Feature activation+5.86e-03

Pos logit contributions
 built+0.093
 seen+0.092
 pretended+0.088
 found+0.086
 spent+0.085
Neg logit contributions
arl-0.116
omed-0.103
 Nice-0.102
oms-0.100
useum-0.100
Token them
Token ID606
Feature activation-2.09e-02

Pos logit contributions
 pretended+0.008
 built+0.008
 buried+0.008
 found+0.008
 punished+0.007
Neg logit contributions
arl-0.014
ay-0.013
 Today-0.012
andel-0.012
 Nice-0.012
Token out
Token ID503
Feature activation-3.53e-02

Pos logit contributions
arl+0.040
ay+0.038
 Today+0.036
 Nice+0.035
andel+0.034
Neg logit contributions
 pretended-0.037
 built-0.037
 found-0.035
 remembered-0.035
 forgot-0.035
Token of
Token ID286
Feature activation+1.64e-02

Pos logit contributions
arl+0.070
 Today+0.065
 Nice+0.064
ay+0.064
arry+0.061
Neg logit contributions
 pretended-0.064
 put-0.064
 found-0.063
 built-0.062
 buried-0.061