TOP ACTIVATIONS
MAX = 6.575

John . John was three years old and had been learning
Mark . Mark was three years old . One day Mark
Jane . Jane was three years old and she enjoyed playing
Fiona . Fiona was 3 years old and she liked to
Jack . He was 3 years old and very persistent .
. M illy was 3 years old and loved to chew
Alex . He was three years old and always looking for
. Mill ie was 3 years old and loved to explore
Jimmy . Jimmy was three years old , and very healthy
Bob . Bob was three years old and loved to be
Jack . He was three years old and he loved to
Tom . He was three years old and liked to explore
John . John was three years old and he really loved
Lucy . Lucy was 3 years old and she lived in
Tim . He was 3 years old and very eager to
Jack . He was three years old and he was very
Daisy . Daisy was three years old and she was very
Sophia . Sophia was three years old and loved exploring the
Jake . He was three years old and he was always
Molly . She was 3 years old and loved to explore

MIN ACTIVATIONS
MIN = -7.345

Max . Max had a fle a on his back that
his friends when they had fle as . <|endoftext|> Once upon
time with his new k ang aroo buddy . <|endoftext|> Once
wanted to find a k ang aroo . He looked and
idea . He took the fle a to meet other small
has made a big sm udge on the rainbow . She
you ." Spot picked the fle a off the bird .
y was the best k ang aroo ever !"
He was the happiest k ang aroo in the bush !
One day , Max got fle as all over his fur
hurt . It had a thorn in its paw .
she had never had a lizard before , but Lily assured
to find the big k ang aroo and asked for his
yes and gave the k ang aroo a big hug .
She made a big green dot and a yellow swirl .
He had never seen a fle a before and he wanted
, Emily saw a do ggy walking up and down the
! It snatched the paper lizard away and ran off !
is normal for old k ang aro os ."
to take a pol ka dot umbrella .

INTERVAL 3.095 - 6.575
CONTAINS 0.437%

to draw lots of pretty pictures ." Her mom
one home ?" Mom laughed and said , "
We can come back before mom sees us ."
" No , mom , I want to go
you understand ?" S ara and Ben nod .

INTERVAL -0.385 - 3.095
CONTAINS 64.352%

" Wow , you look so pretty , Lily !" her
<|endoftext|> Once upon a time , there was a little orange
, a magic wand , a st eth oscope , or
and Tom are friends . They like to play together .
But then , the sun came out and it was

INTERVAL -3.865 - -0.385
CONTAINS 35.155%

So Tim followed the rabbit â € ™ s advice
and rabbit listened to the owl . They stopped fighting and
was very careful and made sure to hold on tight to
the tree was happy too . It made Maria laugh and
was so excited . She asked the fairy what it was

INTERVAL -7.345 - -3.865
CONTAINS 0.055%

. He had a small toy grill that he played with
. Suddenly , the k ang aroo heard a voice .
and accidentally got the tape stuck all over his fur .
The mouse had a nut stuck in its mouth .
!" Mitt ens chased the fle a and caught it with
Token John
Token ID1757
Feature activation+1.34e+00

Pos logit contributions
 works+0.033
clock+0.033
 ABC+0.031
 numbers+0.031
bows+0.031
Neg logit contributions
bed-0.031
aroo-0.027
ging-0.026
ged-0.026
bly-0.026
Token.
Token ID13
Feature activation+7.10e-01

Pos logit contributions
clock+0.044
 works+0.043
 ABC+0.040
 numbers+0.040
bows+0.040
Neg logit contributions
bed-0.046
aroo-0.042
ged-0.041
ging-0.040
bly-0.039
Token John
Token ID1757
Feature activation+8.17e-01

Pos logit contributions
 works+0.024
clock+0.023
 ABC+0.022
 statues+0.022
 paintings+0.021
Neg logit contributions
bed-0.022
aroo-0.018
ged-0.018
ging-0.017
oned-0.016
Token was
Token ID373
Feature activation-2.88e-02

Pos logit contributions
clock+0.025
 works+0.025
 numbers+0.023
bows+0.023
 ABC+0.023
Neg logit contributions
bed-0.030
aroo-0.026
ged-0.026
ging-0.025
bly-0.025
Token three
Token ID1115
Feature activation+9.47e-01

Pos logit contributions
bed+0.001
ged+0.001
aroo+0.001
ging+0.001
bly+0.001
Neg logit contributions
clock-0.001
 works-0.001
 ABC-0.001
 numbers-0.001
 library-0.001
Token years
Token ID812
Feature activation+6.57e+00

Pos logit contributions
 works+0.031
clock+0.031
bows+0.030
 library+0.028
 ABC+0.028
Neg logit contributions
bed-0.032
aroo-0.029
ging-0.028
ged-0.028
bly-0.027
Token old
Token ID1468
Feature activation+7.98e-01

Pos logit contributions
 works+0.183
clock+0.182
bows+0.172
 ABC+0.166
 numbers+0.164
Neg logit contributions
bed-0.246
aroo-0.237
ging-0.222
ged-0.218
bly-0.217
Token and
Token ID290
Feature activation+8.15e-01

Pos logit contributions
 works+0.031
clock+0.030
 ABC+0.028
 restaurants+0.028
bows+0.028
Neg logit contributions
bed-0.023
aroo-0.019
ged-0.019
ging-0.018
bly-0.017
Token had
Token ID550
Feature activation+6.06e-01

Pos logit contributions
clock+0.030
bows+0.028
 works+0.028
 tours+0.027
 ABC+0.027
Neg logit contributions
bed-0.025
aroo-0.023
bly-0.022
ged-0.021
ging-0.020
Token been
Token ID587
Feature activation-2.98e-01

Pos logit contributions
 works+0.025
bows+0.023
clock+0.022
 pays+0.021
aris+0.021
Neg logit contributions
bed-0.016
bly-0.013
aroo-0.012
 luckily-0.012
dd-0.012
Token learning
Token ID4673
Feature activation+2.87e+00

Pos logit contributions
bed+0.010
aroo+0.009
ging+0.009
ged+0.009
bly+0.009
Neg logit contributions
 works-0.010
clock-0.010
bows-0.009
 ABC-0.009
 numbers-0.009
Token Mark
Token ID2940
Feature activation+2.24e-01

Pos logit contributions
 works+0.033
clock+0.033
 ABC+0.030
 numbers+0.030
bows+0.030
Neg logit contributions
bed-0.029
aroo-0.026
ging-0.025
ged-0.025
bly-0.025
Token.
Token ID13
Feature activation+6.69e-01

Pos logit contributions
 works+0.007
clock+0.007
 ABC+0.006
 numbers+0.006
bows+0.006
Neg logit contributions
bed-0.008
aroo-0.007
ging-0.007
ged-0.007
bly-0.007
Token Mark
Token ID2940
Feature activation-2.13e-01

Pos logit contributions
 works+0.022
ews+0.021
 restaurants+0.021
 statues+0.021
 hairc+0.021
Neg logit contributions
bed-0.019
aroo-0.016
ged-0.015
inn-0.014
pered-0.014
Token was
Token ID373
Feature activation+1.01e-01

Pos logit contributions
bed+0.008
aroo+0.007
ged+0.007
ging+0.007
bly+0.006
Neg logit contributions
clock-0.007
 works-0.007
 numbers-0.006
bows-0.006
 ABC-0.006
Token three
Token ID1115
Feature activation+1.02e+00

Pos logit contributions
clock+0.002
 works+0.002
 ABC+0.002
 library+0.002
 numbers+0.002
Neg logit contributions
bed-0.005
ged-0.004
aroo-0.004
ging-0.004
oned-0.004
Token years
Token ID812
Feature activation+6.50e+00

Pos logit contributions
 works+0.033
clock+0.033
bows+0.031
 ABC+0.030
 numbers+0.030
Neg logit contributions
bed-0.035
aroo-0.032
ging-0.031
ged-0.031
bly-0.030
Token old
Token ID1468
Feature activation+9.07e-01

Pos logit contributions
 works+0.180
clock+0.180
bows+0.168
 ABC+0.163
 numbers+0.162
Neg logit contributions
bed-0.245
aroo-0.235
ging-0.222
ged-0.217
bly-0.216
Token.
Token ID13
Feature activation+2.46e-01

Pos logit contributions
 works+0.036
clock+0.035
 ABC+0.032
bows+0.032
 restaurants+0.032
Neg logit contributions
bed-0.026
aroo-0.022
ged-0.021
ging-0.021
bly-0.019
Token One
Token ID1881
Feature activation+2.09e+00

Pos logit contributions
 works+0.008
bows+0.008
 statues+0.008
 flavors+0.008
clock+0.008
Neg logit contributions
bed-0.006
aroo-0.006
inn-0.005
oned-0.005
pered-0.005
Token day
Token ID1110
Feature activation-1.28e+00

Pos logit contributions
clock+0.069
 works+0.069
 numbers+0.064
 ABC+0.064
bows+0.064
Neg logit contributions
bed-0.071
aroo-0.065
ging-0.062
ged-0.062
bly-0.061
Token Mark
Token ID2940
Feature activation-6.37e-01

Pos logit contributions
bed+0.040
aroo+0.036
ged+0.034
ging+0.032
bly+0.029
Neg logit contributions
clock-0.048
 works-0.046
bows-0.045
 ABC-0.043
 flavors-0.043
Token Jane
Token ID12091
Feature activation+2.16e+00

Pos logit contributions
clock+0.023
 library+0.022
 works+0.022
bows+0.022
 brushes+0.022
Neg logit contributions
bed-0.027
ging-0.026
aroo-0.025
ged-0.025
bly-0.024
Token.
Token ID13
Feature activation+9.10e-01

Pos logit contributions
 works+0.058
clock+0.056
 ABC+0.053
 library+0.052
 looks+0.052
Neg logit contributions
bed-0.086
aroo-0.081
ging-0.079
bly-0.079
ged-0.077
Token Jane
Token ID12091
Feature activation+1.57e+00

Pos logit contributions
 works+0.028
clock+0.028
 ABC+0.026
 numbers+0.025
 jobs+0.025
Neg logit contributions
bed-0.033
aroo-0.028
ged-0.028
oned-0.026
ging-0.026
Token was
Token ID373
Feature activation+4.66e-02

Pos logit contributions
 works+0.043
clock+0.042
 ABC+0.039
bows+0.038
 numbers+0.038
Neg logit contributions
bed-0.063
aroo-0.058
ging-0.057
ged-0.056
bly-0.055
Token three
Token ID1115
Feature activation+9.76e-01

Pos logit contributions
clock+0.001
 works+0.001
 ABC+0.001
 library+0.001
 numbers+0.001
Neg logit contributions
bed-0.002
ged-0.002
aroo-0.002
ging-0.002
bly-0.002
Token years
Token ID812
Feature activation+6.49e+00

Pos logit contributions
 works+0.031
clock+0.031
bows+0.029
 numbers+0.028
 ABC+0.028
Neg logit contributions
bed-0.034
aroo-0.031
ging-0.030
ged-0.030
bly-0.029
Token old
Token ID1468
Feature activation+9.96e-01

Pos logit contributions
 works+0.176
clock+0.176
bows+0.162
 ABC+0.159
 numbers+0.158
Neg logit contributions
bed-0.251
aroo-0.238
ging-0.226
ged-0.223
bly-0.221
Token and
Token ID290
Feature activation+8.90e-01

Pos logit contributions
 works+0.038
clock+0.037
 ABC+0.035
 restaurants+0.034
 numbers+0.034
Neg logit contributions
bed-0.030
aroo-0.025
ged-0.024
ging-0.024
bly-0.022
Token she
Token ID673
Feature activation+1.00e+00

Pos logit contributions
clock+0.033
 works+0.032
bows+0.030
 ABC+0.030
 restaurants+0.030
Neg logit contributions
bed-0.028
aroo-0.025
bly-0.024
ged-0.023
ging-0.022
Token enjoyed
Token ID8359
Feature activation+6.94e-01

Pos logit contributions
clock+0.034
 works+0.034
 numbers+0.032
 ABC+0.032
 restaurants+0.032
Neg logit contributions
bed-0.034
aroo-0.030
ged-0.029
bly-0.028
ging-0.028
Token playing
Token ID2712
Feature activation+2.68e-01

Pos logit contributions
 works+0.028
clock+0.028
bows+0.026
 looks+0.025
 ABC+0.025
Neg logit contributions
bed-0.020
ged-0.016
aroo-0.016
ging-0.016
bly-0.015
Token Fiona
Token ID42207
Feature activation+7.96e-01

Pos logit contributions
clock+0.027
 works+0.026
 library+0.026
 ABC+0.025
bows+0.025
Neg logit contributions
bed-0.029
aroo-0.027
ging-0.027
ged-0.026
bly-0.026
Token.
Token ID13
Feature activation+7.02e-01

Pos logit contributions
 works+0.017
 looks+0.015
bows+0.015
 ABC+0.015
 smells+0.015
Neg logit contributions
bed-0.034
ging-0.033
aroo-0.033
bly-0.032
bled-0.032
Token Fiona
Token ID42207
Feature activation+2.82e-01

Pos logit contributions
 works+0.015
clock+0.015
bows+0.014
 numbers+0.014
 ABC+0.014
Neg logit contributions
bed-0.031
aroo-0.029
ging-0.029
ged-0.028
bly-0.028
Token was
Token ID373
Feature activation-8.03e-02

Pos logit contributions
 works+0.008
clock+0.008
 ABC+0.008
bows+0.007
 numbers+0.007
Neg logit contributions
bed-0.011
aroo-0.010
ging-0.010
ged-0.009
bly-0.009
Token 3
Token ID513
Feature activation-1.61e-01

Pos logit contributions
bed+0.004
ged+0.003
aroo+0.003
ging+0.003
bly+0.003
Neg logit contributions
clock-0.002
 works-0.002
 ABC-0.002
 library-0.002
 numbers-0.001
Token years
Token ID812
Feature activation+6.48e+00

Pos logit contributions
bed+0.006
aroo+0.006
ging+0.006
ged+0.006
bly+0.005
Neg logit contributions
clock-0.005
 works-0.005
 ABC-0.004
 numbers-0.004
bows-0.004
Token old
Token ID1468
Feature activation+9.85e-01

Pos logit contributions
 works+0.165
clock+0.165
bows+0.150
 ABC+0.149
 numbers+0.148
Neg logit contributions
bed-0.266
aroo-0.250
ging-0.240
ged-0.238
bly-0.234
Token and
Token ID290
Feature activation+7.54e-01

Pos logit contributions
 works+0.037
clock+0.037
 ABC+0.034
 numbers+0.034
bows+0.034
Neg logit contributions
bed-0.030
aroo-0.026
ged-0.025
ging-0.025
bly-0.023
Token she
Token ID673
Feature activation+8.92e-01

Pos logit contributions
clock+0.026
 works+0.025
bows+0.024
 ABC+0.024
 numbers+0.024
Neg logit contributions
bed-0.025
aroo-0.023
bly-0.022
ged-0.021
ging-0.021
Token liked
Token ID8288
Feature activation+6.79e-01

Pos logit contributions
clock+0.030
 works+0.029
 numbers+0.028
 ABC+0.027
bows+0.027
Neg logit contributions
bed-0.031
aroo-0.028
ged-0.027
ging-0.026
bly-0.026
Token to
Token ID284
Feature activation+1.76e+00

Pos logit contributions
 works+0.024
clock+0.022
bows+0.022
 pays+0.021
 total+0.020
Neg logit contributions
bed-0.021
aroo-0.018
ged-0.017
 spraying-0.015
bing-0.015
Token Jack
Token ID3619
Feature activation+1.12e+00

Pos logit contributions
 works+0.029
clock+0.029
bows+0.027
 ABC+0.027
 numbers+0.027
Neg logit contributions
bed-0.026
aroo-0.024
ged-0.022
ging-0.022
bly-0.021
Token.
Token ID13
Feature activation+6.97e-01

Pos logit contributions
 works+0.034
clock+0.034
 ABC+0.031
 numbers+0.031
bows+0.031
Neg logit contributions
bed-0.042
aroo-0.038
ging-0.037
ged-0.037
bly-0.036
Token He
Token ID679
Feature activation+9.10e-01

Pos logit contributions
clock+0.024
 works+0.024
 ABC+0.023
bows+0.022
 numbers+0.022
Neg logit contributions
bed-0.023
aroo-0.020
ged-0.019
ging-0.019
bly-0.019
Token was
Token ID373
Feature activation-2.12e-01

Pos logit contributions
clock+0.027
 works+0.027
 numbers+0.025
 ABC+0.025
bows+0.024
Neg logit contributions
bed-0.035
aroo-0.031
ged-0.030
ging-0.030
bly-0.030
Token 3
Token ID513
Feature activation-9.25e-02

Pos logit contributions
bed+0.009
aroo+0.009
ged+0.009
ging+0.009
bly+0.008
Neg logit contributions
clock-0.005
 works-0.005
 ABC-0.004
 numbers-0.004
 library-0.004
Token years
Token ID812
Feature activation+6.48e+00

Pos logit contributions
bed+0.003
aroo+0.003
ging+0.003
ged+0.003
bly+0.003
Neg logit contributions
 works-0.003
clock-0.003
bows-0.003
 ABC-0.003
 numbers-0.003
Token old
Token ID1468
Feature activation+9.30e-01

Pos logit contributions
 works+0.169
clock+0.168
bows+0.156
 ABC+0.153
 numbers+0.151
Neg logit contributions
bed-0.260
aroo-0.244
ging-0.234
ged-0.232
bly-0.229
Token and
Token ID290
Feature activation+7.76e-01

Pos logit contributions
 works+0.037
clock+0.036
 ABC+0.034
 restaurants+0.033
bows+0.033
Neg logit contributions
bed-0.026
aroo-0.022
ged-0.021
ging-0.021
bly-0.019
Token very
Token ID845
Feature activation+2.88e+00

Pos logit contributions
clock+0.028
 works+0.026
bows+0.026
 ABC+0.025
 tours+0.025
Neg logit contributions
bed-0.025
aroo-0.023
bly-0.022
ged-0.021
ging-0.021
Token persistent
Token ID16218
Feature activation+4.94e-01

Pos logit contributions
clock+0.109
bows+0.105
 works+0.102
 flavors+0.101
 numbers+0.101
Neg logit contributions
bed-0.079
aroo-0.078
bly-0.072
ging-0.070
ged-0.067
Token.
Token ID13
Feature activation+6.71e-02

Pos logit contributions
 works+0.020
clock+0.019
bows+0.018
 ABC+0.018
 smells+0.018
Neg logit contributions
bed-0.013
aroo-0.011
ging-0.011
ged-0.011
bly-0.010
Token.
Token ID13
Feature activation+5.24e-01

Pos logit contributions
 works+0.046
clock+0.045
 ABC+0.043
bows+0.043
 numbers+0.043
Neg logit contributions
bed-0.060
aroo-0.055
ging-0.055
ged-0.054
bly-0.053
Token M
Token ID337
Feature activation+2.48e+00

Pos logit contributions
 works+0.019
clock+0.018
 ABC+0.017
 numbers+0.017
 flavors+0.017
Neg logit contributions
bed-0.017
ged-0.013
aroo-0.013
inn-0.013
bly-0.013
Tokenilly
Token ID6548
Feature activation+1.09e+00

Pos logit contributions
 works+0.111
clock+0.111
 numbers+0.105
bows+0.104
 ABC+0.103
Neg logit contributions
bed-0.057
aroo-0.045
ged-0.043
ging-0.043
bly-0.042
Token was
Token ID373
Feature activation+2.34e-01

Pos logit contributions
clock+0.036
 works+0.035
 numbers+0.033
 restaurants+0.033
 ABC+0.032
Neg logit contributions
bed-0.038
aroo-0.034
ged-0.032
ging-0.031
bly-0.031
Token 3
Token ID513
Feature activation-3.55e-01

Pos logit contributions
clock+0.006
 works+0.006
 ABC+0.005
 numbers+0.005
 library+0.005
Neg logit contributions
bed-0.010
aroo-0.009
ged-0.009
ging-0.009
bly-0.009
Token years
Token ID812
Feature activation+6.47e+00

Pos logit contributions
bed+0.013
aroo+0.012
ging+0.011
ged+0.011
bly+0.011
Neg logit contributions
 works-0.011
clock-0.011
bows-0.010
 ABC-0.010
 numbers-0.010
Token old
Token ID1468
Feature activation+6.91e-01

Pos logit contributions
 works+0.167
clock+0.166
bows+0.153
 ABC+0.150
 numbers+0.149
Neg logit contributions
bed-0.264
aroo-0.247
ging-0.236
ged-0.235
bly-0.232
Token and
Token ID290
Feature activation+3.92e-01

Pos logit contributions
 works+0.027
clock+0.026
 ABC+0.024
 restaurants+0.024
bows+0.024
Neg logit contributions
bed-0.020
aroo-0.017
ged-0.017
ging-0.017
bly-0.016
Token loved
Token ID6151
Feature activation+7.59e-01

Pos logit contributions
clock+0.013
 works+0.013
bows+0.012
 ABC+0.012
 numbers+0.012
Neg logit contributions
bed-0.014
aroo-0.012
bly-0.012
ged-0.012
ging-0.011
Token to
Token ID284
Feature activation+2.17e+00

Pos logit contributions
 works+0.026
bows+0.025
clock+0.024
ven+0.023
 total+0.023
Neg logit contributions
bed-0.024
ged-0.019
aroo-0.019
ging-0.018
 spraying-0.018
Token chew
Token ID34722
Feature activation-1.41e-01

Pos logit contributions
clock+0.077
 works+0.072
bows+0.070
aris+0.067
 pays+0.067
Neg logit contributions
bed-0.070
aroo-0.059
bly-0.056
ged-0.054
 swat-0.053
Token Alex
Token ID4422
Feature activation+1.58e-01

Pos logit contributions
 works+0.032
clock+0.032
 numbers+0.030
 ABC+0.030
bows+0.030
Neg logit contributions
bed-0.030
aroo-0.027
ging-0.026
ged-0.026
bly-0.026
Token.
Token ID13
Feature activation+5.95e-01

Pos logit contributions
 works+0.004
clock+0.004
 ABC+0.004
 looks+0.003
 numbers+0.003
Neg logit contributions
bed-0.006
aroo-0.006
ging-0.006
bly-0.006
ged-0.006
Token He
Token ID679
Feature activation+7.96e-01

Pos logit contributions
clock+0.017
 works+0.017
 ABC+0.016
bows+0.016
 numbers+0.016
Neg logit contributions
bed-0.023
aroo-0.020
ged-0.020
ging-0.020
bly-0.019
Token was
Token ID373
Feature activation-2.69e-01

Pos logit contributions
 works+0.022
clock+0.022
 ABC+0.020
 numbers+0.020
bows+0.020
Neg logit contributions
bed-0.031
aroo-0.029
ging-0.028
ged-0.028
bly-0.028
Token three
Token ID1115
Feature activation+1.13e+00

Pos logit contributions
bed+0.012
aroo+0.011
ged+0.011
ging+0.011
bly+0.010
Neg logit contributions
clock-0.006
 works-0.006
 ABC-0.006
 numbers-0.006
 library-0.006
Token years
Token ID812
Feature activation+6.47e+00

Pos logit contributions
 works+0.037
clock+0.037
bows+0.035
 ABC+0.034
 library+0.033
Neg logit contributions
bed-0.038
aroo-0.034
ging-0.033
ged-0.032
bly-0.032
Token old
Token ID1468
Feature activation+1.02e+00

Pos logit contributions
 works+0.182
clock+0.180
bows+0.172
 ABC+0.166
 flavors+0.165
Neg logit contributions
bed-0.239
aroo-0.229
ging-0.218
ged-0.212
bly-0.211
Token and
Token ID290
Feature activation+9.07e-01

Pos logit contributions
 works+0.040
clock+0.039
 ABC+0.037
 restaurants+0.037
bows+0.036
Neg logit contributions
bed-0.029
aroo-0.024
ged-0.023
ging-0.023
bly-0.020
Token always
Token ID1464
Feature activation+2.25e+00

Pos logit contributions
clock+0.032
 works+0.031
bows+0.030
 ABC+0.029
 numbers+0.029
Neg logit contributions
bed-0.029
aroo-0.027
bly-0.026
ged-0.025
ging-0.024
Token looking
Token ID2045
Feature activation+3.23e+00

Pos logit contributions
clock+0.071
 ABC+0.071
 works+0.070
 numbers+0.068
 library+0.067
Neg logit contributions
bed-0.078
ged-0.068
ging-0.068
aroo-0.066
bly-0.064
Token for
Token ID329
Feature activation+2.15e-01

Pos logit contributions
clock+0.147
 flavors+0.144
bows+0.143
 works+0.141
 brushes+0.136
Neg logit contributions
bed-0.061
ging-0.059
ged-0.054
ling-0.051
aroo-0.049
Token.
Token ID13
Feature activation+7.03e-01

Pos logit contributions
bed+0.016
ging+0.015
bly+0.015
ged+0.015
aroo+0.015
Neg logit contributions
 works-0.008
clock-0.008
 library-0.008
 ABC-0.008
 books-0.007
Token Mill
Token ID9212
Feature activation+1.37e+00

Pos logit contributions
clock+0.022
 works+0.021
 ABC+0.020
 numbers+0.020
 flavors+0.020
Neg logit contributions
bed-0.026
aroo-0.022
ged-0.022
ging-0.021
bly-0.021
Tokenie
Token ID494
Feature activation-1.25e+00

Pos logit contributions
 works+0.054
clock+0.053
 ABC+0.050
 numbers+0.050
bows+0.050
Neg logit contributions
bed-0.038
aroo-0.034
ging-0.032
ged-0.032
bly-0.031
Token was
Token ID373
Feature activation-1.59e-01

Pos logit contributions
bed+0.045
aroo+0.040
ged+0.039
ging+0.038
bly+0.038
Neg logit contributions
clock-0.039
 works-0.039
 numbers-0.036
 ABC-0.036
bows-0.036
Token 3
Token ID513
Feature activation-4.60e-01

Pos logit contributions
bed+0.007
ged+0.007
aroo+0.007
ging+0.007
bly+0.006
Neg logit contributions
clock-0.004
 works-0.003
 ABC-0.003
 library-0.003
 numbers-0.003
Token years
Token ID812
Feature activation+6.45e+00

Pos logit contributions
bed+0.018
aroo+0.016
ging+0.016
ged+0.016
bly+0.015
Neg logit contributions
 works-0.013
clock-0.013
 ABC-0.012
 numbers-0.012
bows-0.012
Token old
Token ID1468
Feature activation+7.92e-01

Pos logit contributions
 works+0.161
clock+0.161
bows+0.146
 ABC+0.145
 numbers+0.145
Neg logit contributions
bed-0.269
aroo-0.250
ging-0.242
ged-0.240
bly-0.236
Token and
Token ID290
Feature activation+5.42e-01

Pos logit contributions
 works+0.030
clock+0.030
 ABC+0.028
 restaurants+0.027
 numbers+0.027
Neg logit contributions
bed-0.024
aroo-0.020
ged-0.020
ging-0.019
bly-0.018
Token loved
Token ID6151
Feature activation+9.53e-01

Pos logit contributions
clock+0.019
 works+0.018
bows+0.017
 ABC+0.017
 restaurants+0.017
Neg logit contributions
bed-0.018
aroo-0.017
bly-0.016
ged-0.016
ging-0.015
Token to
Token ID284
Feature activation+2.24e+00

Pos logit contributions
 works+0.032
bows+0.030
clock+0.030
ven+0.028
 pays+0.028
Neg logit contributions
bed-0.030
ged-0.025
aroo-0.024
ging-0.023
bing-0.023
Token explore
Token ID7301
Feature activation+2.78e+00

Pos logit contributions
clock+0.080
 works+0.075
bows+0.072
aris+0.071
 pays+0.070
Neg logit contributions
bed-0.071
aroo-0.061
bly-0.056
 swat-0.054
ged-0.054
Token Jimmy
Token ID12963
Feature activation+1.23e+00

Pos logit contributions
clock+0.030
 works+0.030
 numbers+0.029
 ABC+0.028
 library+0.028
Neg logit contributions
bed-0.031
aroo-0.028
ging-0.027
ged-0.027
bly-0.026
Token.
Token ID13
Feature activation+7.75e-01

Pos logit contributions
 works+0.037
clock+0.037
 ABC+0.034
 numbers+0.034
bows+0.034
Neg logit contributions
bed-0.045
aroo-0.042
ging-0.040
ged-0.040
bly-0.039
Token Jimmy
Token ID12963
Feature activation+5.96e-01

Pos logit contributions
 works+0.025
clock+0.025
 ABC+0.023
bows+0.023
 numbers+0.023
Neg logit contributions
bed-0.027
ged-0.023
aroo-0.023
ging-0.023
bly-0.022
Token was
Token ID373
Feature activation-3.02e-02

Pos logit contributions
clock+0.018
 works+0.018
 numbers+0.017
 ABC+0.017
bows+0.017
Neg logit contributions
bed-0.022
aroo-0.020
ged-0.019
ging-0.019
bly-0.019
Token three
Token ID1115
Feature activation+8.63e-01

Pos logit contributions
bed+0.001
ged+0.001
aroo+0.001
ging+0.001
bly+0.001
Neg logit contributions
clock-0.001
 works-0.001
 ABC-0.001
 library-0.001
 numbers-0.001
Token years
Token ID812
Feature activation+6.44e+00

Pos logit contributions
 works+0.027
clock+0.026
bows+0.025
 ABC+0.024
 numbers+0.024
Neg logit contributions
bed-0.031
aroo-0.028
ging-0.027
ged-0.027
bly-0.027
Token old
Token ID1468
Feature activation+9.27e-01

Pos logit contributions
 works+0.175
clock+0.174
bows+0.162
 ABC+0.158
 numbers+0.156
Neg logit contributions
bed-0.250
aroo-0.237
ging-0.226
ged-0.222
bly-0.220
Token,
Token ID11
Feature activation+3.90e-01

Pos logit contributions
 works+0.036
clock+0.035
 ABC+0.033
bows+0.032
 restaurants+0.032
Neg logit contributions
bed-0.027
aroo-0.023
ging-0.022
ged-0.022
bly-0.020
Token and
Token ID290
Feature activation+5.70e-01

Pos logit contributions
 works+0.014
clock+0.014
 numbers+0.013
 ABC+0.013
bows+0.013
Neg logit contributions
bed-0.012
aroo-0.011
ging-0.011
ged-0.011
bly-0.011
Token very
Token ID845
Feature activation+2.73e+00

Pos logit contributions
clock+0.019
 works+0.019
bows+0.018
 ABC+0.017
 numbers+0.017
Neg logit contributions
bed-0.020
aroo-0.018
bly-0.017
ged-0.017
ging-0.017
Token healthy
Token ID5448
Feature activation+2.12e+00

Pos logit contributions
clock+0.100
 works+0.097
bows+0.096
 numbers+0.092
 ABC+0.092
Neg logit contributions
bed-0.082
aroo-0.077
bly-0.072
ging-0.072
ged-0.071
Token Bob
Token ID5811
Feature activation+6.61e-01

Pos logit contributions
clock+0.028
 works+0.028
bows+0.026
 ABC+0.026
 flavors+0.026
Neg logit contributions
bed-0.024
aroo-0.022
ged-0.020
ging-0.020
bly-0.019
Token.
Token ID13
Feature activation+4.55e-01

Pos logit contributions
clock+0.021
 works+0.021
 ABC+0.019
 numbers+0.019
bows+0.019
Neg logit contributions
bed-0.023
aroo-0.021
ged-0.021
ging-0.020
bly-0.020
Token Bob
Token ID5811
Feature activation+5.82e-01

Pos logit contributions
 works+0.017
clock+0.017
 ABC+0.016
bows+0.016
 numbers+0.016
Neg logit contributions
bed-0.013
aroo-0.012
ged-0.011
ging-0.010
bly-0.010
Token was
Token ID373
Feature activation-3.27e-02

Pos logit contributions
clock+0.019
 works+0.018
 numbers+0.017
bows+0.017
 ABC+0.017
Neg logit contributions
bed-0.021
aroo-0.018
ged-0.018
ging-0.017
bly-0.017
Token three
Token ID1115
Feature activation+8.91e-01

Pos logit contributions
bed+0.001
ged+0.001
ging+0.001
aroo+0.001
bly+0.001
Neg logit contributions
clock-0.001
 works-0.001
 ABC-0.001
 numbers-0.001
 library-0.001
Token years
Token ID812
Feature activation+6.44e+00

Pos logit contributions
 works+0.029
clock+0.029
bows+0.028
 ABC+0.027
 library+0.026
Neg logit contributions
bed-0.030
aroo-0.027
ging-0.026
ged-0.026
bly-0.025
Token old
Token ID1468
Feature activation+7.56e-01

Pos logit contributions
 works+0.176
clock+0.174
bows+0.164
 ABC+0.159
 numbers+0.157
Neg logit contributions
bed-0.247
aroo-0.237
ging-0.223
ged-0.220
bly-0.217
Token and
Token ID290
Feature activation+6.36e-01

Pos logit contributions
 works+0.030
clock+0.029
 ABC+0.027
bows+0.027
 restaurants+0.027
Neg logit contributions
bed-0.022
aroo-0.018
ged-0.017
ging-0.017
bly-0.015
Token loved
Token ID6151
Feature activation+1.02e+00

Pos logit contributions
clock+0.022
 works+0.021
bows+0.021
 ABC+0.020
 numbers+0.020
Neg logit contributions
bed-0.021
aroo-0.020
bly-0.018
ged-0.018
ging-0.017
Token to
Token ID284
Feature activation+2.26e+00

Pos logit contributions
bows+0.034
 works+0.034
clock+0.032
ven+0.030
 pays+0.030
Neg logit contributions
bed-0.031
aroo-0.026
ged-0.026
ging-0.024
bing-0.024
Token be
Token ID307
Feature activation+1.96e-01

Pos logit contributions
clock+0.083
 works+0.077
bows+0.075
 meanings+0.073
 pays+0.073
Neg logit contributions
bed-0.070
aroo-0.059
bly-0.054
 swat-0.052
ged-0.052
Token Jack
Token ID3619
Feature activation+1.29e+00

Pos logit contributions
 works+0.038
clock+0.038
 ABC+0.035
bows+0.035
 numbers+0.035
Neg logit contributions
bed-0.033
aroo-0.029
ged-0.028
ging-0.028
bly-0.027
Token.
Token ID13
Feature activation+5.27e-01

Pos logit contributions
 works+0.039
clock+0.039
 ABC+0.036
 numbers+0.036
bows+0.035
Neg logit contributions
bed-0.048
aroo-0.044
ging-0.043
ged-0.042
bly-0.042
Token He
Token ID679
Feature activation+8.31e-01

Pos logit contributions
 works+0.018
clock+0.018
 ABC+0.016
 numbers+0.016
bows+0.016
Neg logit contributions
bed-0.018
aroo-0.016
ging-0.015
ged-0.015
bly-0.015
Token was
Token ID373
Feature activation-2.61e-01

Pos logit contributions
 works+0.023
clock+0.023
 ABC+0.021
 numbers+0.021
 library+0.021
Neg logit contributions
bed-0.033
aroo-0.030
ging-0.030
ged-0.029
bly-0.029
Token three
Token ID1115
Feature activation+9.82e-01

Pos logit contributions
bed+0.012
ged+0.011
aroo+0.011
ging+0.011
bly+0.010
Neg logit contributions
clock-0.006
 works-0.006
 ABC-0.005
 numbers-0.005
 library-0.005
Token years
Token ID812
Feature activation+6.43e+00

Pos logit contributions
 works+0.032
clock+0.031
bows+0.030
 ABC+0.029
 numbers+0.029
Neg logit contributions
bed-0.034
aroo-0.030
ging-0.029
ged-0.029
bly-0.029
Token old
Token ID1468
Feature activation+9.30e-01

Pos logit contributions
 works+0.174
clock+0.173
bows+0.164
 ABC+0.158
 numbers+0.157
Neg logit contributions
bed-0.247
aroo-0.236
ging-0.224
ged-0.220
bly-0.219
Token and
Token ID290
Feature activation+8.24e-01

Pos logit contributions
 works+0.037
clock+0.036
 ABC+0.034
 restaurants+0.034
bows+0.033
Neg logit contributions
bed-0.026
aroo-0.022
ged-0.021
ging-0.021
bly-0.018
Token he
Token ID339
Feature activation+4.66e-01

Pos logit contributions
clock+0.030
 works+0.028
bows+0.028
 ABC+0.027
 numbers+0.026
Neg logit contributions
bed-0.026
aroo-0.024
bly-0.023
ged-0.022
ging-0.021
Token loved
Token ID6151
Feature activation+5.08e-01

Pos logit contributions
clock+0.017
 works+0.016
bows+0.016
 numbers+0.015
 ABC+0.015
Neg logit contributions
bed-0.015
aroo-0.013
ged-0.013
bly-0.012
ging-0.012
Token to
Token ID284
Feature activation+2.07e+00

Pos logit contributions
bows+0.017
 works+0.017
clock+0.016
 pays+0.015
ven+0.015
Neg logit contributions
bed-0.016
aroo-0.013
ged-0.013
ging-0.012
 under-0.012
Token Tom
Token ID4186
Feature activation+6.12e-01

Pos logit contributions
clock+0.032
 works+0.032
 numbers+0.030
 ABC+0.029
 library+0.029
Neg logit contributions
bed-0.032
aroo-0.029
ging-0.028
ged-0.028
bly-0.027
Token.
Token ID13
Feature activation+7.02e-01

Pos logit contributions
 works+0.018
clock+0.017
 ABC+0.016
 numbers+0.016
 library+0.016
Neg logit contributions
bed-0.023
aroo-0.022
ging-0.021
bly-0.021
ged-0.021
Token He
Token ID679
Feature activation+8.63e-01

Pos logit contributions
 works+0.022
clock+0.021
 ABC+0.020
bows+0.020
 statues+0.020
Neg logit contributions
bed-0.024
aroo-0.021
ged-0.021
ging-0.020
inn-0.019
Token was
Token ID373
Feature activation-2.13e-01

Pos logit contributions
 works+0.024
clock+0.023
 ABC+0.021
 numbers+0.021
 library+0.021
Neg logit contributions
bed-0.035
aroo-0.032
ging-0.031
ged-0.031
bly-0.031
Token three
Token ID1115
Feature activation+1.05e+00

Pos logit contributions
bed+0.010
ged+0.009
aroo+0.009
ging+0.009
bly+0.009
Neg logit contributions
clock-0.005
 works-0.004
 ABC-0.004
 numbers-0.004
 library-0.004
Token years
Token ID812
Feature activation+6.43e+00

Pos logit contributions
 works+0.035
clock+0.034
bows+0.033
 ABC+0.031
 numbers+0.031
Neg logit contributions
bed-0.036
aroo-0.032
ging-0.031
ged-0.031
bly-0.030
Token old
Token ID1468
Feature activation+9.54e-01

Pos logit contributions
 works+0.178
clock+0.176
bows+0.167
 ABC+0.161
 numbers+0.160
Neg logit contributions
bed-0.243
aroo-0.232
ging-0.221
ged-0.216
bly-0.215
Token and
Token ID290
Feature activation+8.34e-01

Pos logit contributions
 works+0.038
clock+0.037
 ABC+0.034
bows+0.034
 restaurants+0.034
Neg logit contributions
bed-0.027
aroo-0.022
ged-0.021
ging-0.021
bly-0.019
Token liked
Token ID8288
Feature activation+1.33e+00

Pos logit contributions
clock+0.030
bows+0.028
 works+0.028
 ABC+0.027
 numbers+0.027
Neg logit contributions
bed-0.026
aroo-0.024
bly-0.023
ged-0.022
ging-0.022
Token to
Token ID284
Feature activation+2.19e+00

Pos logit contributions
bows+0.046
 works+0.046
clock+0.043
 pays+0.041
 meanings+0.040
Neg logit contributions
bed-0.039
aroo-0.035
ged-0.033
ging-0.030
 under-0.030
Token explore
Token ID7301
Feature activation+2.76e+00

Pos logit contributions
clock+0.075
 works+0.072
bows+0.069
aris+0.069
 pays+0.068
Neg logit contributions
bed-0.071
aroo-0.062
bly-0.056
ged-0.055
 swat-0.053
Token John
Token ID1757
Feature activation+9.81e-01

Pos logit contributions
clock+0.030
 works+0.030
bows+0.028
 ABC+0.028
 numbers+0.028
Neg logit contributions
bed-0.024
aroo-0.022
ged-0.021
ging-0.020
bly-0.020
Token.
Token ID13
Feature activation+3.00e-01

Pos logit contributions
clock+0.034
 works+0.034
bows+0.032
 ABC+0.032
 numbers+0.032
Neg logit contributions
bed-0.032
aroo-0.028
ged-0.028
ging-0.027
bly-0.026
Token John
Token ID1757
Feature activation+6.88e-01

Pos logit contributions
 works+0.010
bows+0.010
clock+0.010
 ABC+0.010
 statues+0.010
Neg logit contributions
bed-0.008
ged-0.007
aroo-0.006
inn-0.006
ging-0.006
Token was
Token ID373
Feature activation-1.12e-01

Pos logit contributions
clock+0.022
 works+0.021
 numbers+0.020
bows+0.020
 ABC+0.020
Neg logit contributions
bed-0.025
aroo-0.022
ged-0.021
ging-0.021
bly-0.020
Token three
Token ID1115
Feature activation+9.62e-01

Pos logit contributions
bed+0.005
ged+0.005
aroo+0.005
ging+0.005
bly+0.004
Neg logit contributions
clock-0.002
 works-0.002
 ABC-0.002
 library-0.002
 numbers-0.002
Token years
Token ID812
Feature activation+6.43e+00

Pos logit contributions
 works+0.031
clock+0.031
bows+0.029
 ABC+0.028
 numbers+0.028
Neg logit contributions
bed-0.033
aroo-0.030
ging-0.029
ged-0.029
bly-0.028
Token old
Token ID1468
Feature activation+7.49e-01

Pos logit contributions
 works+0.173
clock+0.173
bows+0.162
 ABC+0.157
 numbers+0.156
Neg logit contributions
bed-0.250
aroo-0.237
ging-0.226
ged-0.223
bly-0.219
Token and
Token ID290
Feature activation+5.89e-01

Pos logit contributions
 works+0.029
clock+0.028
 ABC+0.027
bows+0.026
 restaurants+0.026
Neg logit contributions
bed-0.022
aroo-0.018
ged-0.018
ging-0.018
bly-0.016
Token he
Token ID339
Feature activation+1.60e-01

Pos logit contributions
clock+0.021
 works+0.020
bows+0.020
 ABC+0.019
 numbers+0.019
Neg logit contributions
bed-0.019
aroo-0.017
bly-0.016
ged-0.016
ging-0.015
Token really
Token ID1107
Feature activation+1.28e+00

Pos logit contributions
clock+0.006
 works+0.005
 numbers+0.005
bows+0.005
 ABC+0.005
Neg logit contributions
bed-0.005
aroo-0.005
ged-0.004
bly-0.004
ging-0.004
Token loved
Token ID6151
Feature activation+5.48e-01

Pos logit contributions
clock+0.048
 restaurants+0.046
 numbers+0.045
 tours+0.045
 works+0.045
Neg logit contributions
bed-0.037
aroo-0.033
ged-0.031
bly-0.030
ging-0.029
Token Lucy
Token ID22162
Feature activation+8.87e-01

Pos logit contributions
 works+0.023
clock+0.023
 flavors+0.021
 numbers+0.021
 ABC+0.021
Neg logit contributions
bed-0.019
aroo-0.017
ged-0.015
ging-0.015
bly-0.015
Token.
Token ID13
Feature activation+3.84e-01

Pos logit contributions
 works+0.027
clock+0.027
 ABC+0.025
 numbers+0.025
bows+0.024
Neg logit contributions
bed-0.033
aroo-0.030
ging-0.029
ged-0.029
bly-0.028
Token Lucy
Token ID22162
Feature activation+6.06e-01

Pos logit contributions
 works+0.012
clock+0.012
 ABC+0.011
 numbers+0.011
 flavors+0.011
Neg logit contributions
bed-0.014
aroo-0.012
ged-0.011
oned-0.011
bly-0.011
Token was
Token ID373
Feature activation-1.98e-01

Pos logit contributions
clock+0.020
 works+0.019
 numbers+0.018
 ABC+0.018
 restaurants+0.018
Neg logit contributions
bed-0.021
aroo-0.019
ged-0.018
ging-0.017
bly-0.017
Token 3
Token ID513
Feature activation-5.29e-01

Pos logit contributions
bed+0.008
aroo+0.008
ged+0.007
ging+0.007
bly+0.007
Neg logit contributions
 works-0.005
clock-0.005
 ABC-0.005
 numbers-0.005
bows-0.005
Token years
Token ID812
Feature activation+6.43e+00

Pos logit contributions
bed+0.019
aroo+0.018
ging+0.017
ged+0.017
bly+0.017
Neg logit contributions
 works-0.016
clock-0.016
 ABC-0.015
 numbers-0.015
bows-0.015
Token old
Token ID1468
Feature activation+5.76e-01

Pos logit contributions
 works+0.167
clock+0.167
bows+0.154
 ABC+0.151
 numbers+0.150
Neg logit contributions
bed-0.258
aroo-0.242
ging-0.232
ged-0.230
bly-0.226
Token and
Token ID290
Feature activation+5.56e-01

Pos logit contributions
 works+0.023
clock+0.022
 ABC+0.021
 restaurants+0.021
bows+0.020
Neg logit contributions
bed-0.017
aroo-0.014
ged-0.014
ging-0.013
bly-0.013
Token she
Token ID673
Feature activation+7.15e-01

Pos logit contributions
clock+0.019
 works+0.018
bows+0.018
 ABC+0.017
 numbers+0.017
Neg logit contributions
bed-0.019
aroo-0.017
bly-0.016
ged-0.016
ging-0.016
Token lived
Token ID5615
Feature activation-6.42e-01

Pos logit contributions
clock+0.024
 works+0.023
 numbers+0.022
 ABC+0.022
bows+0.021
Neg logit contributions
bed-0.025
aroo-0.022
ged-0.021
ging-0.021
bly-0.021
Token in
Token ID287
Feature activation+2.43e-01

Pos logit contributions
bed+0.018
aroo+0.017
ged+0.016
ging+0.016
oned+0.016
Neg logit contributions
 works-0.023
clock-0.022
 books-0.022
 numbers-0.022
 library-0.021
Token Tim
Token ID5045
Feature activation+6.01e-01

Pos logit contributions
 works+0.028
clock+0.028
 numbers+0.026
 ABC+0.026
 library+0.026
Neg logit contributions
bed-0.028
aroo-0.025
ging-0.024
ged-0.024
bly-0.024
Token.
Token ID13
Feature activation+9.44e-01

Pos logit contributions
 works+0.011
clock+0.011
 numbers+0.010
 ABC+0.010
bows+0.010
Neg logit contributions
bed-0.029
aroo-0.027
ging-0.027
ged-0.026
bly-0.026
Token He
Token ID679
Feature activation+1.00e+00

Pos logit contributions
 works+0.035
clock+0.034
 ABC+0.032
 numbers+0.032
bows+0.032
Neg logit contributions
bed-0.029
aroo-0.026
ged-0.025
ging-0.025
bly-0.024
Token was
Token ID373
Feature activation-1.34e-01

Pos logit contributions
 works+0.027
clock+0.026
 ABC+0.024
 numbers+0.024
 library+0.024
Neg logit contributions
bed-0.040
aroo-0.037
ging-0.037
ged-0.036
bly-0.036
Token 3
Token ID513
Feature activation-1.79e-01

Pos logit contributions
bed+0.006
ged+0.006
aroo+0.006
ging+0.006
bly+0.005
Neg logit contributions
clock-0.003
 works-0.003
 ABC-0.003
 numbers-0.003
 library-0.003
Token years
Token ID812
Feature activation+6.42e+00

Pos logit contributions
bed+0.007
aroo+0.006
ging+0.006
ged+0.006
bly+0.006
Neg logit contributions
clock-0.005
 works-0.005
 ABC-0.005
 numbers-0.005
bows-0.005
Token old
Token ID1468
Feature activation+1.00e+00

Pos logit contributions
 works+0.162
clock+0.161
bows+0.148
 ABC+0.146
 numbers+0.145
Neg logit contributions
bed-0.265
aroo-0.248
ging-0.238
ged-0.237
bly-0.234
Token and
Token ID290
Feature activation+7.85e-01

Pos logit contributions
 works+0.039
clock+0.039
 ABC+0.036
bows+0.036
 restaurants+0.036
Neg logit contributions
bed-0.029
aroo-0.024
ged-0.023
ging-0.023
bly-0.021
Token very
Token ID845
Feature activation+2.91e+00

Pos logit contributions
clock+0.028
 works+0.027
bows+0.026
 ABC+0.026
 numbers+0.025
Neg logit contributions
bed-0.025
aroo-0.023
bly-0.022
ged-0.021
ging-0.021
Token eager
Token ID11069
Feature activation+1.06e+00

Pos logit contributions
clock+0.110
bows+0.106
 works+0.103
 flavors+0.102
 numbers+0.102
Neg logit contributions
bed-0.081
aroo-0.080
bly-0.074
ging-0.072
ged-0.069
Token to
Token ID284
Feature activation+1.70e+00

Pos logit contributions
 works+0.034
bows+0.030
 total+0.030
ven+0.030
 ABC+0.029
Neg logit contributions
bed-0.035
ged-0.029
aroo-0.028
ging-0.027
 under-0.026
Token Jack
Token ID3619
Feature activation+1.10e+00

Pos logit contributions
 works+0.033
clock+0.033
bows+0.031
 ABC+0.031
 numbers+0.031
Neg logit contributions
bed-0.026
aroo-0.023
ged-0.022
ging-0.022
bly-0.021
Token.
Token ID13
Feature activation+6.13e-01

Pos logit contributions
 works+0.034
clock+0.034
 ABC+0.031
 numbers+0.031
bows+0.031
Neg logit contributions
bed-0.040
aroo-0.037
ging-0.035
ged-0.035
bly-0.035
Token He
Token ID679
Feature activation+8.14e-01

Pos logit contributions
 works+0.022
clock+0.022
 ABC+0.021
bows+0.020
 numbers+0.020
Neg logit contributions
bed-0.019
aroo-0.017
ged-0.016
ging-0.016
bly-0.016
Token was
Token ID373
Feature activation-2.43e-01

Pos logit contributions
 works+0.023
clock+0.023
 ABC+0.022
 numbers+0.021
bows+0.021
Neg logit contributions
bed-0.031
aroo-0.029
ging-0.028
ged-0.028
bly-0.027
Token three
Token ID1115
Feature activation+9.19e-01

Pos logit contributions
bed+0.011
ged+0.010
aroo+0.010
ging+0.010
bly+0.010
Neg logit contributions
clock-0.006
 works-0.005
 ABC-0.005
 numbers-0.005
 library-0.005
Token years
Token ID812
Feature activation+6.42e+00

Pos logit contributions
 works+0.031
clock+0.030
bows+0.029
 ABC+0.028
 numbers+0.028
Neg logit contributions
bed-0.031
aroo-0.028
ging-0.026
ged-0.026
bly-0.026
Token old
Token ID1468
Feature activation+7.91e-01

Pos logit contributions
 works+0.178
clock+0.177
bows+0.168
 ABC+0.161
 numbers+0.160
Neg logit contributions
bed-0.241
aroo-0.231
ging-0.217
ged-0.213
bly-0.212
Token and
Token ID290
Feature activation+7.69e-01

Pos logit contributions
 works+0.031
clock+0.031
bows+0.028
 restaurants+0.028
 ABC+0.028
Neg logit contributions
bed-0.022
aroo-0.019
ged-0.018
ging-0.018
bly-0.016
Token he
Token ID339
Feature activation+3.11e-01

Pos logit contributions
clock+0.028
bows+0.026
 works+0.026
 ABC+0.025
 numbers+0.025
Neg logit contributions
bed-0.024
aroo-0.022
bly-0.021
ged-0.020
ging-0.020
Token was
Token ID373
Feature activation-3.81e-01

Pos logit contributions
clock+0.011
 works+0.011
 numbers+0.010
bows+0.010
 ABC+0.010
Neg logit contributions
bed-0.010
aroo-0.009
ged-0.009
bly-0.008
ging-0.008
Token very
Token ID845
Feature activation+2.30e+00

Pos logit contributions
bed+0.015
aroo+0.014
ging+0.013
ged+0.013
bly+0.013
Neg logit contributions
 works-0.011
clock-0.011
bows-0.010
 numbers-0.010
 ABC-0.010
Token Daisy
Token ID40355
Feature activation+9.98e-01

Pos logit contributions
 works+0.026
clock+0.026
 numbers+0.024
 ABC+0.024
 flavors+0.024
Neg logit contributions
bed-0.022
aroo-0.019
ged-0.018
ging-0.018
bly-0.018
Token.
Token ID13
Feature activation+5.30e-01

Pos logit contributions
 works+0.029
clock+0.028
 ABC+0.026
 library+0.026
 numbers+0.026
Neg logit contributions
bed-0.038
aroo-0.035
ging-0.035
ged-0.034
bly-0.034
Token Daisy
Token ID40355
Feature activation+5.54e-01

Pos logit contributions
 works+0.013
clock+0.013
bows+0.013
 smells+0.013
 library+0.013
Neg logit contributions
bed-0.021
ging-0.020
aroo-0.020
ged-0.020
bly-0.020
Token was
Token ID373
Feature activation-1.08e-01

Pos logit contributions
clock+0.018
 works+0.017
 numbers+0.016
 ABC+0.016
bows+0.016
Neg logit contributions
bed-0.020
aroo-0.018
ged-0.017
ging-0.017
bly-0.016
Token three
Token ID1115
Feature activation+9.78e-01

Pos logit contributions
bed+0.005
ged+0.004
aroo+0.004
ging+0.004
bly+0.004
Neg logit contributions
clock-0.002
 works-0.002
 ABC-0.002
 library-0.002
 numbers-0.002
Token years
Token ID812
Feature activation+6.41e+00

Pos logit contributions
 works+0.031
clock+0.031
bows+0.029
 ABC+0.028
 numbers+0.028
Neg logit contributions
bed-0.034
aroo-0.031
ging-0.030
ged-0.030
bly-0.029
Token old
Token ID1468
Feature activation+9.05e-01

Pos logit contributions
 works+0.174
clock+0.173
bows+0.159
 ABC+0.156
 numbers+0.155
Neg logit contributions
bed-0.249
aroo-0.236
ging-0.224
ged-0.221
bly-0.219
Token and
Token ID290
Feature activation+7.37e-01

Pos logit contributions
 works+0.036
clock+0.035
 ABC+0.032
 restaurants+0.032
bows+0.032
Neg logit contributions
bed-0.026
aroo-0.022
ged-0.020
ging-0.020
bly-0.019
Token she
Token ID673
Feature activation+8.54e-01

Pos logit contributions
clock+0.026
 works+0.025
bows+0.024
 ABC+0.023
 numbers+0.023
Neg logit contributions
bed-0.025
aroo-0.022
bly-0.021
ged-0.021
ging-0.020
Token was
Token ID373
Feature activation-2.83e-01

Pos logit contributions
clock+0.029
 works+0.028
 numbers+0.027
bows+0.027
 ABC+0.027
Neg logit contributions
bed-0.029
aroo-0.026
ged-0.025
bly-0.024
ging-0.024
Token very
Token ID845
Feature activation+2.30e+00

Pos logit contributions
bed+0.011
aroo+0.010
ging+0.010
ged+0.010
bly+0.010
Neg logit contributions
 works-0.008
clock-0.008
 ABC-0.007
 numbers-0.007
bows-0.007
Token Sophia
Token ID39953
Feature activation+1.75e+00

Pos logit contributions
clock+0.044
 works+0.043
bows+0.043
 ABC+0.042
 flavors+0.042
Neg logit contributions
bed-0.022
aroo-0.019
ged-0.018
bly-0.017
ging-0.017
Token.
Token ID13
Feature activation+6.84e-01

Pos logit contributions
clock+0.065
 works+0.062
bows+0.060
 numbers+0.059
 ABC+0.059
Neg logit contributions
bed-0.054
aroo-0.048
ged-0.047
ging-0.045
bly-0.044
Token Sophia
Token ID39953
Feature activation+9.53e-01

Pos logit contributions
 works+0.022
clock+0.021
 ABC+0.020
bows+0.019
 jobs+0.019
Neg logit contributions
bed-0.024
ged-0.020
aroo-0.020
ging-0.020
inn-0.019
Token was
Token ID373
Feature activation-3.27e-01

Pos logit contributions
clock+0.032
 works+0.030
bows+0.029
 numbers+0.029
 restaurants+0.029
Neg logit contributions
bed-0.033
aroo-0.029
ged-0.028
ging-0.027
bly-0.027
Token three
Token ID1115
Feature activation+8.25e-01

Pos logit contributions
bed+0.014
aroo+0.012
ged+0.012
ging+0.012
bly+0.012
Neg logit contributions
clock-0.008
 works-0.008
 ABC-0.008
 numbers-0.008
bows-0.008
Token years
Token ID812
Feature activation+6.41e+00

Pos logit contributions
 works+0.027
clock+0.027
bows+0.026
 numbers+0.025
 ABC+0.025
Neg logit contributions
bed-0.028
aroo-0.025
ging-0.024
ged-0.024
bly-0.023
Token old
Token ID1468
Feature activation+9.10e-01

Pos logit contributions
 works+0.190
clock+0.188
bows+0.179
 flavors+0.175
 ABC+0.173
Neg logit contributions
bed-0.223
aroo-0.215
ging-0.204
ged-0.197
bly-0.196
Token and
Token ID290
Feature activation+7.52e-01

Pos logit contributions
 works+0.038
clock+0.037
 ABC+0.035
 restaurants+0.035
 numbers+0.034
Neg logit contributions
bed-0.024
aroo-0.019
ged-0.018
ging-0.018
bly-0.016
Token loved
Token ID6151
Feature activation+1.04e+00

Pos logit contributions
clock+0.027
 works+0.026
bows+0.025
 ABC+0.025
 numbers+0.024
Neg logit contributions
bed-0.023
aroo-0.022
bly-0.021
ged-0.019
ging-0.019
Token exploring
Token ID13504
Feature activation+3.15e+00

Pos logit contributions
 works+0.036
bows+0.035
ven+0.034
clock+0.033
cases+0.032
Neg logit contributions
bed-0.030
ged-0.024
aroo-0.023
 spraying-0.023
 under-0.023
Token the
Token ID262
Feature activation+5.86e-01

Pos logit contributions
clock+0.116
 works+0.107
bows+0.106
 meanings+0.104
 ABC+0.102
Neg logit contributions
bed-0.097
ging-0.083
ged-0.081
aroo-0.079
bly-0.078
Token Jake
Token ID14757
Feature activation+8.43e-01

Pos logit contributions
clock+0.038
 works+0.038
bows+0.036
 ABC+0.036
 numbers+0.036
Neg logit contributions
bed-0.030
aroo-0.027
ged-0.025
ging-0.025
bly-0.024
Token.
Token ID13
Feature activation+5.17e-01

Pos logit contributions
 works+0.025
clock+0.025
 ABC+0.023
 numbers+0.023
bows+0.022
Neg logit contributions
bed-0.032
aroo-0.029
ging-0.028
ged-0.028
bly-0.028
Token He
Token ID679
Feature activation+7.20e-01

Pos logit contributions
bows+0.018
 statues+0.018
 works+0.018
 flavors+0.018
 paintings+0.018
Neg logit contributions
bed-0.014
inn-0.011
ged-0.010
bing-0.009
 under-0.009
Token was
Token ID373
Feature activation-2.50e-01

Pos logit contributions
 works+0.021
clock+0.021
 ABC+0.019
 numbers+0.019
bows+0.019
Neg logit contributions
bed-0.028
aroo-0.025
ging-0.025
ged-0.025
bly-0.024
Token three
Token ID1115
Feature activation+9.24e-01

Pos logit contributions
bed+0.011
aroo+0.010
ged+0.010
ging+0.010
bly+0.010
Neg logit contributions
clock-0.006
 works-0.006
 ABC-0.005
 numbers-0.005
 library-0.005
Token years
Token ID812
Feature activation+6.40e+00

Pos logit contributions
 works+0.029
clock+0.029
bows+0.028
 ABC+0.027
 numbers+0.027
Neg logit contributions
bed-0.032
aroo-0.029
ging-0.028
ged-0.028
bly-0.027
Token old
Token ID1468
Feature activation+7.77e-01

Pos logit contributions
 works+0.173
clock+0.172
bows+0.163
 ABC+0.157
 numbers+0.156
Neg logit contributions
bed-0.248
aroo-0.235
ging-0.224
ged-0.221
bly-0.218
Token and
Token ID290
Feature activation+7.13e-01

Pos logit contributions
 works+0.031
clock+0.030
bows+0.028
 restaurants+0.028
 ABC+0.028
Neg logit contributions
bed-0.022
aroo-0.018
ged-0.018
ging-0.018
bly-0.016
Token he
Token ID339
Feature activation+2.57e-01

Pos logit contributions
clock+0.025
 works+0.024
bows+0.024
 ABC+0.023
 restaurants+0.023
Neg logit contributions
bed-0.023
aroo-0.021
bly-0.020
ged-0.019
ging-0.019
Token was
Token ID373
Feature activation-3.73e-01

Pos logit contributions
clock+0.009
 works+0.009
bows+0.008
 numbers+0.008
 ABC+0.008
Neg logit contributions
bed-0.009
aroo-0.008
ged-0.007
bly-0.007
ging-0.007
Token always
Token ID1464
Feature activation+8.47e-01

Pos logit contributions
bed+0.015
aroo+0.013
ging+0.013
ged+0.013
bly+0.013
Neg logit contributions
 works-0.010
clock-0.010
bows-0.010
 numbers-0.009
 ABC-0.009
Token Molly
Token ID30236
Feature activation+1.92e+00

Pos logit contributions
 works+0.040
clock+0.040
 ABC+0.038
 numbers+0.037
bows+0.037
Neg logit contributions
bed-0.043
aroo-0.039
ging-0.038
ged-0.038
bly-0.037
Token.
Token ID13
Feature activation+7.55e-01

Pos logit contributions
 works+0.055
clock+0.055
 ABC+0.051
 numbers+0.051
bows+0.051
Neg logit contributions
bed-0.073
aroo-0.067
ging-0.066
ged-0.065
bly-0.064
Token She
Token ID1375
Feature activation+1.73e+00

Pos logit contributions
clock+0.014
 works+0.014
 library+0.013
 smells+0.013
 looks+0.013
Neg logit contributions
aroo-0.035
bed-0.035
ging-0.034
ged-0.034
bly-0.033
Token was
Token ID373
Feature activation-3.21e-01

Pos logit contributions
 works+0.044
clock+0.041
 ABC+0.040
 looks+0.039
 library+0.039
Neg logit contributions
bed-0.072
ging-0.067
aroo-0.067
ged-0.065
bly-0.065
Token 3
Token ID513
Feature activation-2.45e-01

Pos logit contributions
bed+0.015
ged+0.014
ging+0.014
aroo+0.014
bly+0.013
Neg logit contributions
clock-0.007
 works-0.007
 ABC-0.006
 library-0.006
 numbers-0.006
Token years
Token ID812
Feature activation+6.40e+00

Pos logit contributions
bed+0.009
aroo+0.008
ging+0.008
ged+0.008
bly+0.008
Neg logit contributions
clock-0.007
 works-0.007
 ABC-0.007
 numbers-0.007
bows-0.006
Token old
Token ID1468
Feature activation+8.86e-01

Pos logit contributions
 works+0.155
clock+0.154
 ABC+0.139
 numbers+0.139
bows+0.139
Neg logit contributions
bed-0.274
aroo-0.253
ging-0.246
ged-0.245
bly-0.241
Token and
Token ID290
Feature activation+6.72e-01

Pos logit contributions
 works+0.035
clock+0.034
 ABC+0.032
 restaurants+0.032
 numbers+0.032
Neg logit contributions
bed-0.025
aroo-0.021
ged-0.020
ging-0.020
bly-0.018
Token loved
Token ID6151
Feature activation+1.11e+00

Pos logit contributions
clock+0.022
 works+0.022
bows+0.021
 ABC+0.020
 numbers+0.020
Neg logit contributions
bed-0.023
aroo-0.021
bly-0.020
ged-0.020
ging-0.020
Token to
Token ID284
Feature activation+2.25e+00

Pos logit contributions
 works+0.038
bows+0.036
clock+0.036
ven+0.034
 pays+0.034
Neg logit contributions
bed-0.034
ged-0.028
aroo-0.027
ging-0.026
 spraying-0.026
Token explore
Token ID7301
Feature activation+2.77e+00

Pos logit contributions
clock+0.079
 works+0.075
bows+0.072
aris+0.070
 meanings+0.068
Neg logit contributions
bed-0.074
aroo-0.063
bly-0.059
ged-0.058
 swat-0.056
Token Max
Token ID5436
Feature activation-9.16e-01

Pos logit contributions
 works+0.015
clock+0.015
 numbers+0.014
 ABC+0.014
bows+0.013
Neg logit contributions
bed-0.013
aroo-0.011
ging-0.011
ged-0.011
bly-0.011
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
bed+0.036
aroo+0.034
ging+0.033
bly+0.033
ged+0.032
Neg logit contributions
 works-0.025
clock-0.024
 library-0.023
 looks-0.022
 numbers-0.022
Token Max
Token ID5436
Feature activation-1.18e+00

Pos logit contributions
bed+0.003
ged+0.002
aroo+0.002
ging+0.002
bly+0.002
Neg logit contributions
clock-0.005
 works-0.005
 statues-0.005
 paintings-0.005
 flavors-0.005
Token had
Token ID550
Feature activation-1.51e-01

Pos logit contributions
bed+0.043
aroo+0.038
ged+0.037
ging+0.037
bly+0.036
Neg logit contributions
clock-0.037
 works-0.036
 numbers-0.034
 ABC-0.034
bows-0.034
Token a
Token ID257
Feature activation-6.99e-01

Pos logit contributions
bed+0.007
aroo+0.006
ging+0.006
ged+0.006
bly+0.006
Neg logit contributions
clock-0.003
 works-0.003
 numbers-0.003
 ABC-0.003
 library-0.003
Token fle
Token ID5104
Feature activation-5.64e+00

Pos logit contributions
bed+0.031
aroo+0.029
ging+0.028
ged+0.028
bly+0.028
Neg logit contributions
 works-0.016
clock-0.016
 ABC-0.014
 numbers-0.014
 library-0.014
Tokena
Token ID64
Feature activation-3.07e+00

Pos logit contributions
bed+0.224
oned+0.220
bing+0.217
ging+0.208
 swat+0.204
Neg logit contributions
bows-0.115
 names-0.113
 books-0.110
aris-0.106
 works-0.102
Token on
Token ID319
Feature activation-1.94e+00

Pos logit contributions
bed+0.080
bly+0.076
bled+0.073
ging+0.072
aroo+0.072
Neg logit contributions
 books-0.118
 library-0.117
 works-0.117
clock-0.113
 ABC-0.113
Token his
Token ID465
Feature activation-1.19e+00

Pos logit contributions
bed+0.074
ging+0.069
aroo+0.069
ged+0.068
bly+0.067
Neg logit contributions
 works-0.054
clock-0.054
 numbers-0.052
 ABC-0.052
 library-0.052
Token back
Token ID736
Feature activation-1.21e+00

Pos logit contributions
bed+0.044
ging+0.044
bly+0.044
ged+0.043
aroo+0.042
Neg logit contributions
clock-0.034
 ABC-0.032
 library-0.032
 books-0.032
 numbers-0.031
Token that
Token ID326
Feature activation-1.42e+00

Pos logit contributions
bed+0.049
ging+0.048
bly+0.048
ged+0.047
bled+0.046
Neg logit contributions
clock-0.031
 library-0.031
 works-0.030
 books-0.029
 restaurants-0.028
Token his
Token ID465
Feature activation-3.60e-01

Pos logit contributions
 works+0.029
clock+0.026
 smells+0.025
 restaurants+0.025
 numbers+0.025
Neg logit contributions
bed-0.050
ging-0.047
ged-0.047
bly-0.045
bled-0.045
Token friends
Token ID2460
Feature activation-5.29e-01

Pos logit contributions
bed+0.013
aroo+0.012
ging+0.012
ged+0.012
bly+0.012
Neg logit contributions
 works-0.011
clock-0.011
 ABC-0.010
 numbers-0.010
bows-0.010
Token when
Token ID618
Feature activation-1.18e+00

Pos logit contributions
bed+0.018
aroo+0.017
ged+0.016
ging+0.016
bly+0.016
Neg logit contributions
 works-0.017
clock-0.016
 ABC-0.016
 numbers-0.016
bows-0.016
Token they
Token ID484
Feature activation+1.50e+00

Pos logit contributions
bed+0.036
aroo+0.033
ged+0.031
ging+0.031
bly+0.029
Neg logit contributions
clock-0.043
 works-0.042
bows-0.041
 ABC-0.039
 numbers-0.039
Token had
Token ID550
Feature activation-3.00e-01

Pos logit contributions
clock+0.045
 works+0.042
 ABC+0.041
bows+0.041
 numbers+0.040
Neg logit contributions
bed-0.058
ged-0.052
aroo-0.052
ging-0.050
bly-0.048
Token fle
Token ID5104
Feature activation-5.40e+00

Pos logit contributions
bed+0.012
ged+0.010
aroo+0.010
ging+0.010
bly+0.009
Neg logit contributions
 works-0.008
clock-0.008
 ABC-0.008
bows-0.008
 library-0.008
Tokenas
Token ID292
Feature activation-1.47e+00

Pos logit contributions
bed+0.230
aroo+0.218
ging+0.212
 luckily+0.205
ged+0.205
Neg logit contributions
clock-0.111
 works-0.110
bows-0.105
aris-0.099
 names-0.099
Token.
Token ID13
Feature activation-7.02e-01

Pos logit contributions
bed+0.052
aroo+0.047
ging+0.046
ged+0.046
bly+0.045
Neg logit contributions
 works-0.046
clock-0.046
 ABC-0.043
 numbers-0.043
bows-0.042
Token<|endoftext|>
Token ID50256
Feature activation+9.49e-01

Pos logit contributions
bed+0.024
aroo+0.021
ged+0.021
ging+0.020
bly+0.020
Neg logit contributions
 works-0.023
clock-0.023
 numbers-0.022
 ABC-0.022
bows-0.021
TokenOnce
Token ID7454
Feature activation-1.80e+00

Pos logit contributions
 works+0.026
clock+0.026
 ABC+0.024
 numbers+0.024
 library+0.024
Neg logit contributions
bed-0.037
aroo-0.035
ging-0.035
ged-0.034
bly-0.034
Token upon
Token ID2402
Feature activation+9.65e-01

Pos logit contributions
bed+0.089
aroo+0.082
ging+0.081
bly+0.081
ged+0.080
Neg logit contributions
 works-0.032
clock-0.031
 ABC-0.028
 numbers-0.027
 library-0.027
Token time
Token ID640
Feature activation-2.50e-01

Pos logit contributions
bed+0.044
aroo+0.043
ging+0.041
bly+0.040
ged+0.039
Neg logit contributions
 works-0.025
clock-0.024
 numbers-0.023
 flavors-0.023
 books-0.023
Token with
Token ID351
Feature activation-1.17e+00

Pos logit contributions
bed+0.007
aroo+0.007
bly+0.007
ged+0.007
ging+0.006
Neg logit contributions
clock-0.008
 works-0.008
 numbers-0.008
bows-0.008
 books-0.008
Token his
Token ID465
Feature activation-2.17e-01

Pos logit contributions
bed+0.042
aroo+0.038
ging+0.037
ged+0.037
bly+0.036
Neg logit contributions
clock-0.036
 works-0.036
 numbers-0.034
 ABC-0.034
bows-0.033
Token new
Token ID649
Feature activation-1.91e+00

Pos logit contributions
bed+0.008
aroo+0.008
ging+0.007
ged+0.007
bly+0.007
Neg logit contributions
 works-0.006
clock-0.006
 ABC-0.006
 numbers-0.006
bows-0.006
Token k
Token ID479
Feature activation-3.28e+00

Pos logit contributions
bed+0.066
aroo+0.060
ging+0.058
ged+0.058
bly+0.056
Neg logit contributions
clock-0.062
 works-0.062
 ABC-0.057
 numbers-0.057
bows-0.057
Tokenang
Token ID648
Feature activation-5.37e+00

Pos logit contributions
bed+0.060
ged+0.046
ging+0.045
aroo+0.044
bly+0.043
Neg logit contributions
clock-0.152
 works-0.150
bows-0.146
 numbers-0.145
 ABC-0.145
Tokenaroo
Token ID38049
Feature activation-3.35e+00

Pos logit contributions
bed+0.069
oned+0.045
ged+0.041
ging+0.041
bly+0.038
Neg logit contributions
 ABC-0.253
 numbers-0.253
 works-0.245
 names-0.241
 looks-0.239
Token buddy
Token ID24407
Feature activation-1.94e+00

Pos logit contributions
bed+0.128
ged+0.120
ging+0.120
bly+0.118
aroo+0.117
Neg logit contributions
clock-0.087
 works-0.085
 numbers-0.081
 books-0.080
 library-0.080
Token.
Token ID13
Feature activation-1.11e+00

Pos logit contributions
bed+0.075
aroo+0.069
ged+0.068
ging+0.067
bly+0.067
Neg logit contributions
clock-0.053
 works-0.052
 numbers-0.049
bows-0.048
 library-0.047
Token<|endoftext|>
Token ID50256
Feature activation+1.23e+00

Pos logit contributions
bed+0.033
aroo+0.029
ged+0.028
ging+0.027
oned+0.026
Neg logit contributions
 works-0.041
clock-0.040
bows-0.038
 ABC-0.038
 statues-0.038
TokenOnce
Token ID7454
Feature activation-1.40e+00

Pos logit contributions
 works+0.030
clock+0.030
 library+0.027
 numbers+0.027
 ABC+0.027
Neg logit contributions
bed-0.052
aroo-0.048
ging-0.047
bly-0.047
ged-0.046
Token wanted
Token ID2227
Feature activation-3.68e-01

Pos logit contributions
bed+0.001
aroo+0.001
ged+0.001
ging+0.001
bly+0.001
Neg logit contributions
clock-0.001
 numbers-0.001
 works-0.001
bows-0.001
 restaurants-0.001
Token to
Token ID284
Feature activation+8.50e-01

Pos logit contributions
bed+0.013
aroo+0.012
ged+0.011
ging+0.011
bly+0.010
Neg logit contributions
bows-0.011
 works-0.011
clock-0.010
 meanings-0.010
 smells-0.010
Token find
Token ID1064
Feature activation+3.11e-01

Pos logit contributions
clock+0.026
bows+0.026
 works+0.026
 smells+0.023
 meanings+0.023
Neg logit contributions
bed-0.029
aroo-0.028
bly-0.024
 swat-0.024
oned-0.024
Token a
Token ID257
Feature activation-6.73e-01

Pos logit contributions
clock+0.009
 works+0.009
bows+0.008
 ABC+0.008
 library+0.008
Neg logit contributions
bed-0.012
aroo-0.011
ged-0.011
ging-0.011
bly-0.010
Token k
Token ID479
Feature activation-3.80e+00

Pos logit contributions
bed+0.025
aroo+0.024
ging+0.022
bly+0.022
ged+0.021
Neg logit contributions
clock-0.019
 works-0.018
bows-0.018
 numbers-0.017
 meanings-0.017
Tokenang
Token ID648
Feature activation-5.37e+00

Pos logit contributions
bed+0.166
ged+0.148
oned+0.148
ging+0.147
bled+0.145
Neg logit contributions
clock-0.082
 works-0.077
 library-0.073
 books-0.071
 looks-0.070
Tokenaroo
Token ID38049
Feature activation-3.82e+00

Pos logit contributions
bed+0.097
oned+0.066
bing+0.058
ged+0.058
ging+0.056
Neg logit contributions
 look-0.237
 looks-0.235
 works-0.235
 books-0.233
 numbers-0.229
Token.
Token ID13
Feature activation-6.54e-01

Pos logit contributions
bed+0.153
bly+0.142
ged+0.141
ging+0.140
bled+0.139
Neg logit contributions
clock-0.096
 works-0.096
 library-0.096
 books-0.092
 looks-0.089
Token He
Token ID679
Feature activation-5.79e-01

Pos logit contributions
bed+0.017
aroo+0.014
ged+0.012
inn+0.012
oned+0.012
Neg logit contributions
 works-0.025
bows-0.025
 statues-0.025
 restaurants-0.024
 Bible-0.024
Token looked
Token ID3114
Feature activation+7.34e-01

Pos logit contributions
bed+0.023
aroo+0.021
ged+0.020
ging+0.020
bly+0.019
Neg logit contributions
clock-0.016
 works-0.016
bows-0.015
 ABC-0.015
 numbers-0.015
Token and
Token ID290
Feature activation-3.27e-01

Pos logit contributions
 works+0.028
clock+0.027
 numbers+0.026
 looks+0.026
 smells+0.026
Neg logit contributions
bed-0.022
aroo-0.019
ging-0.018
bly-0.018
ged-0.018
Token idea
Token ID2126
Feature activation-1.94e+00

Pos logit contributions
 works+0.004
clock+0.003
 numbers+0.003
 ABC+0.003
 jobs+0.003
Neg logit contributions
bed-0.010
ged-0.009
ging-0.009
aroo-0.009
bly-0.009
Token.
Token ID13
Feature activation-6.07e-01

Pos logit contributions
bed+0.084
bly+0.079
aroo+0.077
ging+0.077
bled+0.073
Neg logit contributions
 works-0.047
clock-0.042
 numbers-0.042
 looks-0.041
 books-0.040
Token He
Token ID679
Feature activation-4.46e-01

Pos logit contributions
bed+0.025
aroo+0.023
ged+0.022
ging+0.022
bly+0.021
Neg logit contributions
 works-0.016
clock-0.016
 ABC-0.015
bows-0.014
 numbers-0.014
Token took
Token ID1718
Feature activation-1.53e+00

Pos logit contributions
bed+0.016
aroo+0.015
ged+0.014
ging+0.014
bly+0.014
Neg logit contributions
clock-0.014
 works-0.013
 ABC-0.013
bows-0.012
 numbers-0.012
Token the
Token ID262
Feature activation-5.69e-01

Pos logit contributions
bed+0.065
ging+0.062
ged+0.061
aroo+0.060
bly+0.059
Neg logit contributions
 works-0.036
 numbers-0.034
clock-0.034
 books-0.032
 names-0.032
Token fle
Token ID5104
Feature activation-5.36e+00

Pos logit contributions
bed+0.019
ged+0.017
aroo+0.016
ging+0.016
bly+0.016
Neg logit contributions
 works-0.020
clock-0.019
 ABC-0.019
 numbers-0.019
 library-0.018
Tokena
Token ID64
Feature activation-3.29e+00

Pos logit contributions
bed+0.215
ged+0.198
ging+0.198
 luckily+0.194
oned+0.194
Neg logit contributions
 names-0.109
bows-0.105
clock-0.104
 works-0.102
 ABC-0.101
Token to
Token ID284
Feature activation+1.36e-02

Pos logit contributions
bed+0.132
aroo+0.122
bly+0.121
ging+0.119
ged+0.119
Neg logit contributions
 works-0.084
clock-0.082
 numbers-0.078
 looks-0.077
 books-0.077
Token meet
Token ID1826
Feature activation+3.74e-01

Pos logit contributions
 works+0.000
clock+0.000
 numbers+0.000
 restaurants+0.000
 ABC+0.000
Neg logit contributions
bed-0.001
ging-0.001
ged-0.001
bly-0.001
aroo-0.001
Token other
Token ID584
Feature activation+3.41e-01

Pos logit contributions
 books+0.008
 works+0.008
 numbers+0.008
 names+0.008
 history+0.008
Neg logit contributions
bed-0.016
ging-0.015
bly-0.015
ged-0.015
aroo-0.015
Token small
Token ID1402
Feature activation-9.34e-01

Pos logit contributions
 works+0.009
clock+0.009
 ABC+0.009
 numbers+0.009
 library+0.009
Neg logit contributions
bed-0.014
aroo-0.012
ged-0.012
ging-0.012
bly-0.012
Token has
Token ID468
Feature activation-6.27e-01

Pos logit contributions
bed+0.062
aroo+0.058
ged+0.056
ging+0.056
bly+0.055
Neg logit contributions
clock-0.023
 works-0.021
 ABC-0.020
 restaurants-0.019
bows-0.019
Token made
Token ID925
Feature activation-2.33e-01

Pos logit contributions
bed+0.019
ged+0.016
bly+0.015
bled+0.015
aroo+0.015
Neg logit contributions
 works-0.021
clock-0.020
 restaurants-0.020
aris-0.020
 ABC-0.020
Token a
Token ID257
Feature activation-8.09e-01

Pos logit contributions
bed+0.007
aroo+0.006
bly+0.006
ging+0.006
ged+0.006
Neg logit contributions
 works-0.008
clock-0.008
 restaurants-0.008
 library-0.008
 ABC-0.008
Token big
Token ID1263
Feature activation-1.40e+00

Pos logit contributions
bed+0.037
aroo+0.034
ging+0.033
ged+0.033
bly+0.033
Neg logit contributions
 works-0.017
clock-0.017
 ABC-0.016
 numbers-0.015
bows-0.015
Token sm
Token ID895
Feature activation-1.82e-01

Pos logit contributions
bed+0.061
aroo+0.057
ged+0.055
ging+0.055
bly+0.054
Neg logit contributions
 works-0.033
clock-0.033
 numbers-0.030
 ABC-0.030
bows-0.029
Tokenudge
Token ID12587
Feature activation-5.36e+00

Pos logit contributions
bed+0.007
aroo+0.006
ged+0.006
ging+0.006
bly+0.006
Neg logit contributions
clock-0.005
 works-0.005
bows-0.005
 smells-0.005
 numbers-0.005
Token on
Token ID319
Feature activation-1.60e+00

Pos logit contributions
bed+0.189
aroo+0.171
ged+0.165
ging+0.162
bly+0.162
Neg logit contributions
 works-0.166
clock-0.157
 numbers-0.156
 smells-0.153
 looks-0.152
Token the
Token ID262
Feature activation-8.09e-01

Pos logit contributions
bed+0.054
aroo+0.049
ging+0.047
ged+0.047
bly+0.046
Neg logit contributions
 works-0.053
clock-0.053
 numbers-0.050
 ABC-0.049
bows-0.049
Token rainbow
Token ID27223
Feature activation+1.30e-01

Pos logit contributions
bed+0.032
aroo+0.029
ged+0.029
ging+0.029
bly+0.028
Neg logit contributions
clock-0.023
 works-0.022
 numbers-0.021
 ABC-0.021
 library-0.021
Token.
Token ID13
Feature activation+3.89e-01

Pos logit contributions
clock+0.004
 works+0.004
 numbers+0.004
 ABC+0.004
bows+0.004
Neg logit contributions
bed-0.005
aroo-0.004
ging-0.004
ged-0.004
bly-0.004
Token She
Token ID1375
Feature activation+8.60e-01

Pos logit contributions
 works+0.011
clock+0.011
bows+0.010
 restaurants+0.010
 flavors+0.010
Neg logit contributions
bed-0.015
aroo-0.014
ged-0.013
ging-0.013
bly-0.012
Token you
Token ID345
Feature activation-2.68e-01

Pos logit contributions
 works+0.014
clock+0.014
 numbers+0.013
 ABC+0.013
 library+0.012
Neg logit contributions
bed-0.022
ged-0.020
aroo-0.020
ging-0.020
bly-0.020
Token."
Token ID526
Feature activation+7.16e-01

Pos logit contributions
bed+0.010
ged+0.009
aroo+0.009
ging+0.009
bly+0.009
Neg logit contributions
 works-0.008
clock-0.007
 ABC-0.007
 numbers-0.007
bows-0.007
Token Spot
Token ID15899
Feature activation-1.08e+00

Pos logit contributions
 works+0.023
clock+0.023
 numbers+0.021
 ABC+0.021
bows+0.021
Neg logit contributions
bed-0.025
aroo-0.023
ged-0.022
ging-0.022
bly-0.021
Token picked
Token ID6497
Feature activation-3.16e-01

Pos logit contributions
bed+0.040
aroo+0.035
ged+0.034
ging+0.032
bly+0.032
Neg logit contributions
clock-0.034
 works-0.033
 restaurants-0.032
 ABC-0.031
 numbers-0.031
Token the
Token ID262
Feature activation-8.49e-01

Pos logit contributions
bed+0.012
bly+0.011
aroo+0.011
ging+0.011
ged+0.011
Neg logit contributions
 works-0.009
 numbers-0.008
 looks-0.008
 smells-0.008
 ABC-0.008
Token fle
Token ID5104
Feature activation-5.30e+00

Pos logit contributions
bed+0.029
ged+0.026
ging+0.026
bly+0.026
aroo+0.026
Neg logit contributions
 works-0.028
clock-0.027
 ABC-0.026
 numbers-0.026
 library-0.025
Tokena
Token ID64
Feature activation-3.26e+00

Pos logit contributions
bed+0.197
ging+0.189
ged+0.189
oned+0.185
 luckily+0.185
Neg logit contributions
bows-0.111
 names-0.110
 works-0.106
 ABC-0.104
clock-0.101
Token off
Token ID572
Feature activation-1.83e+00

Pos logit contributions
bed+0.114
aroo+0.107
ged+0.105
bly+0.105
ging+0.104
Neg logit contributions
 works-0.097
 looks-0.093
clock-0.093
 smells-0.091
 numbers-0.091
Token the
Token ID262
Feature activation-7.00e-02

Pos logit contributions
bed+0.078
bly+0.071
ging+0.071
ged+0.069
aroo+0.068
Neg logit contributions
 works-0.040
clock-0.040
 numbers-0.040
 books-0.040
 ABC-0.038
Token bird
Token ID6512
Feature activation-2.30e+00

Pos logit contributions
bed+0.003
ged+0.003
ging+0.003
bly+0.003
dd+0.003
Neg logit contributions
 library-0.002
 ABC-0.002
 works-0.002
 numbers-0.002
clock-0.002
Token.
Token ID13
Feature activation-6.32e-01

Pos logit contributions
bly+0.098
ging+0.098
bed+0.096
aroo+0.096
bled+0.096
Neg logit contributions
clock-0.048
 works-0.047
 looks-0.046
 library-0.043
 books-0.043
Tokeny
Token ID88
Feature activation-4.23e-01

Pos logit contributions
clock+0.039
 works+0.037
 restaurants+0.037
 ABC+0.037
 library+0.036
Neg logit contributions
bed-0.035
aroo-0.033
ging-0.032
ged-0.032
bly-0.030
Token was
Token ID373
Feature activation-1.08e+00

Pos logit contributions
bed+0.015
aroo+0.014
ged+0.013
ging+0.013
bly+0.012
Neg logit contributions
clock-0.013
 restaurants-0.012
 ABC-0.012
 works-0.012
 numbers-0.012
Token the
Token ID262
Feature activation-5.03e-01

Pos logit contributions
bed+0.039
aroo+0.036
ging+0.034
bly+0.034
ged+0.034
Neg logit contributions
clock-0.034
 works-0.034
 ABC-0.031
bows-0.031
 numbers-0.031
Token best
Token ID1266
Feature activation-1.18e+00

Pos logit contributions
bed+0.017
aroo+0.017
ging+0.016
bly+0.016
ged+0.015
Neg logit contributions
 works-0.015
clock-0.015
bows-0.014
 smells-0.014
 ABC-0.013
Token k
Token ID479
Feature activation-3.66e+00

Pos logit contributions
bed+0.045
aroo+0.042
ging+0.040
ged+0.040
bly+0.039
Neg logit contributions
clock-0.034
 works-0.033
bows-0.031
 ABC-0.031
 numbers-0.031
Tokenang
Token ID648
Feature activation-5.29e+00

Pos logit contributions
bed+0.116
ging+0.097
ged+0.097
aroo+0.094
bly+0.093
Neg logit contributions
 works-0.129
clock-0.127
bows-0.119
 numbers-0.118
 ABC-0.118
Tokenaroo
Token ID38049
Feature activation-4.11e+00

Pos logit contributions
bed+0.061
ging+0.029
ged+0.028
oned+0.027
bly+0.021
Neg logit contributions
 works-0.286
clock-0.278
 numbers-0.275
 ABC-0.275
 looks-0.270
Token ever
Token ID1683
Feature activation-2.22e-01

Pos logit contributions
bed+0.158
ging+0.141
ged+0.140
aroo+0.140
bly+0.137
Neg logit contributions
 works-0.117
clock-0.116
 numbers-0.106
bows-0.106
 ABC-0.105
Token!"
Token ID2474
Feature activation+3.52e-01

Pos logit contributions
bed+0.009
aroo+0.008
ged+0.008
ging+0.008
bly+0.008
Neg logit contributions
clock-0.006
 works-0.006
 ABC-0.006
 numbers-0.005
 library-0.005
Token
Token ID198
Feature activation+1.31e-02

Pos logit contributions
clock+0.005
 looks+0.005
 numbers+0.005
 names+0.005
 works+0.005
Neg logit contributions
ging-0.016
bed-0.016
bly-0.016
ged-0.015
aroo-0.015
Token
Token ID198
Feature activation+1.02e-01

Pos logit contributions
 ABC+0.000
 works+0.000
clock+0.000
 history+0.000
 names+0.000
Neg logit contributions
bed-0.001
ging-0.001
ged-0.000
bly-0.000
aroo-0.000
Token He
Token ID679
Feature activation-7.72e-01

Pos logit contributions
bed+0.025
aroo+0.023
ging+0.023
ged+0.023
bly+0.022
Neg logit contributions
clock-0.021
 works-0.021
 numbers-0.020
 ABC-0.019
 looks-0.019
Token was
Token ID373
Feature activation-1.57e+00

Pos logit contributions
bed+0.030
aroo+0.027
ging+0.027
ged+0.026
bly+0.026
Neg logit contributions
 works-0.022
clock-0.022
 numbers-0.020
 ABC-0.020
bows-0.020
Token the
Token ID262
Feature activation-6.34e-01

Pos logit contributions
bed+0.057
aroo+0.052
ging+0.050
ged+0.050
bly+0.049
Neg logit contributions
 works-0.048
clock-0.048
 ABC-0.045
 numbers-0.045
bows-0.044
Token happiest
Token ID49414
Feature activation-1.04e+00

Pos logit contributions
bed+0.024
aroo+0.023
ging+0.022
bly+0.021
ged+0.021
Neg logit contributions
 works-0.018
clock-0.018
bows-0.016
 ABC-0.016
 restaurants-0.016
Token k
Token ID479
Feature activation-3.22e+00

Pos logit contributions
bed+0.037
ged+0.032
aroo+0.032
ging+0.032
bly+0.031
Neg logit contributions
 works-0.033
clock-0.033
 numbers-0.031
 ABC-0.031
bows-0.031
Tokenang
Token ID648
Feature activation-5.26e+00

Pos logit contributions
bed+0.066
ged+0.049
oned+0.047
ging+0.047
bly+0.045
Neg logit contributions
 works-0.145
clock-0.143
bows-0.139
 numbers-0.136
 library-0.134
Tokenaroo
Token ID38049
Feature activation-3.75e+00

Pos logit contributions
bed+0.071
oned+0.038
ged+0.034
ging+0.030
pered+0.028
Neg logit contributions
 works-0.258
 numbers-0.253
clock-0.249
 ABC-0.249
 statues-0.248
Token in
Token ID287
Feature activation-3.08e-01

Pos logit contributions
bed+0.132
ged+0.116
ging+0.115
bly+0.115
aroo+0.114
Neg logit contributions
 works-0.115
clock-0.111
 looks-0.106
 numbers-0.104
 library-0.103
Token the
Token ID262
Feature activation+8.69e-01

Pos logit contributions
bed+0.013
aroo+0.012
ging+0.012
ged+0.012
bly+0.011
Neg logit contributions
 works-0.008
clock-0.007
 numbers-0.007
 restaurants-0.007
 library-0.007
Token bush
Token ID24484
Feature activation+5.74e-01

Pos logit contributions
 works+0.022
clock+0.021
 ABC+0.020
bows+0.020
 numbers+0.020
Neg logit contributions
bed-0.035
aroo-0.032
ging-0.031
ged-0.030
bly-0.030
Token!
Token ID0
Feature activation-9.15e-01

Pos logit contributions
 works+0.019
clock+0.019
 ABC+0.017
 numbers+0.017
bows+0.017
Neg logit contributions
bed-0.019
aroo-0.018
ging-0.017
ged-0.017
bly-0.017
Token One
Token ID1881
Feature activation+1.18e+00

Pos logit contributions
bed+0.043
aroo+0.038
ged+0.037
ging+0.036
oned+0.035
Neg logit contributions
 works-0.028
clock-0.028
bows-0.026
 statues-0.025
 numbers-0.025
Token day
Token ID1110
Feature activation-2.03e+00

Pos logit contributions
 works+0.030
clock+0.030
 library+0.029
 ABC+0.028
 books+0.028
Neg logit contributions
bed-0.050
ging-0.045
ged-0.045
bly-0.044
aroo-0.043
Token,
Token ID11
Feature activation-9.43e-01

Pos logit contributions
bed+0.077
aroo+0.071
ging+0.069
bly+0.068
ged+0.068
Neg logit contributions
 works-0.058
clock-0.057
 numbers-0.053
 ABC-0.053
bows-0.052
Token Max
Token ID5436
Feature activation-1.87e+00

Pos logit contributions
bed+0.032
aroo+0.029
ging+0.028
bly+0.028
ged+0.028
Neg logit contributions
 works-0.031
clock-0.031
 numbers-0.030
 ABC-0.029
 library-0.029
Token got
Token ID1392
Feature activation-4.63e-03

Pos logit contributions
bed+0.074
aroo+0.068
ging+0.066
ged+0.066
bly+0.065
Neg logit contributions
 works-0.051
clock-0.051
 ABC-0.046
 numbers-0.046
bows-0.046
Token fle
Token ID5104
Feature activation-5.25e+00

Pos logit contributions
bed+0.000
aroo+0.000
ging+0.000
ged+0.000
bly+0.000
Neg logit contributions
clock-0.000
 works-0.000
 numbers-0.000
 ABC-0.000
 restaurants-0.000
Tokenas
Token ID292
Feature activation-2.21e+00

Pos logit contributions
bed+0.215
aroo+0.200
ging+0.191
ged+0.189
 luckily+0.189
Neg logit contributions
clock-0.117
 works-0.114
bows-0.111
aris-0.107
 books-0.102
Token all
Token ID477
Feature activation+3.64e-01

Pos logit contributions
bed+0.070
aroo+0.065
bly+0.061
ging+0.060
ged+0.060
Neg logit contributions
 works-0.075
clock-0.072
 numbers-0.069
 ABC-0.068
bows-0.067
Token over
Token ID625
Feature activation-8.70e-01

Pos logit contributions
 works+0.014
clock+0.014
 ABC+0.013
 numbers+0.013
bows+0.013
Neg logit contributions
bed-0.011
aroo-0.009
ging-0.009
ged-0.009
bly-0.009
Token his
Token ID465
Feature activation-6.00e-01

Pos logit contributions
bed+0.034
aroo+0.031
ging+0.030
ged+0.030
bly+0.029
Neg logit contributions
clock-0.025
 works-0.025
 numbers-0.023
 ABC-0.023
bows-0.022
Token fur
Token ID9230
Feature activation-1.87e+00

Pos logit contributions
bed+0.024
aroo+0.022
ging+0.021
ged+0.021
bly+0.021
Neg logit contributions
 works-0.017
clock-0.017
 ABC-0.015
 numbers-0.015
bows-0.015
Token hurt
Token ID5938
Feature activation-2.15e+00

Pos logit contributions
bed+0.050
ged+0.046
aroo+0.046
ging+0.045
bly+0.044
Neg logit contributions
clock-0.030
 works-0.028
 numbers-0.028
 library-0.027
 ABC-0.026
Token.
Token ID13
Feature activation-1.10e+00

Pos logit contributions
bed+0.068
aroo+0.061
ging+0.059
ged+0.058
bly+0.057
Neg logit contributions
 works-0.077
clock-0.077
 ABC-0.072
bows-0.072
 numbers-0.072
Token It
Token ID632
Feature activation-3.28e-01

Pos logit contributions
bed+0.032
aroo+0.028
ged+0.027
ging+0.025
oned+0.024
Neg logit contributions
 works-0.041
clock-0.040
bows-0.039
 ABC-0.038
 flavors-0.038
Token had
Token ID550
Feature activation-9.04e-01

Pos logit contributions
bed+0.015
ging+0.014
aroo+0.013
bly+0.013
ged+0.013
Neg logit contributions
 works-0.008
clock-0.007
 looks-0.007
 smells-0.007
 numbers-0.006
Token a
Token ID257
Feature activation-1.08e+00

Pos logit contributions
bed+0.035
aroo+0.031
ged+0.031
ging+0.030
bly+0.030
Neg logit contributions
 works-0.026
clock-0.026
bows-0.024
 ABC-0.024
 restaurants-0.023
Token thorn
Token ID38999
Feature activation-5.24e+00

Pos logit contributions
bed+0.046
aroo+0.043
ging+0.042
ged+0.042
bly+0.041
Neg logit contributions
 works-0.026
clock-0.026
 numbers-0.024
 ABC-0.024
bows-0.023
Token in
Token ID287
Feature activation-1.49e+00

Pos logit contributions
aroo+0.154
bed+0.150
bly+0.149
oned+0.144
bled+0.143
Neg logit contributions
 looks-0.161
 works-0.158
 smells-0.156
 books-0.154
bows-0.151
Token its
Token ID663
Feature activation-7.90e-01

Pos logit contributions
bed+0.040
aroo+0.035
ging+0.034
ged+0.034
bly+0.033
Neg logit contributions
 works-0.059
clock-0.058
 numbers-0.056
 ABC-0.055
 smells-0.055
Token paw
Token ID41827
Feature activation-2.98e+00

Pos logit contributions
bed+0.028
aroo+0.026
ging+0.026
ged+0.026
bly+0.026
Neg logit contributions
clock-0.024
 works-0.023
 numbers-0.022
 looks-0.022
 ABC-0.022
Token.
Token ID13
Feature activation-9.11e-01

Pos logit contributions
bed+0.110
aroo+0.103
ging+0.101
bly+0.100
ged+0.100
Neg logit contributions
clock-0.085
 works-0.083
 numbers-0.079
bows-0.078
 library-0.077
Token
Token ID198
Feature activation-1.75e+00

Pos logit contributions
bed+0.031
aroo+0.028
ged+0.027
ging+0.026
bly+0.026
Neg logit contributions
 works-0.031
clock-0.030
 ABC-0.028
 numbers-0.028
bows-0.028
Token she
Token ID673
Feature activation-9.28e-01

Pos logit contributions
bed+0.018
aroo+0.016
ging+0.016
ged+0.016
bly+0.015
Neg logit contributions
 works-0.014
clock-0.014
 numbers-0.013
 ABC-0.013
 library-0.013
Token had
Token ID550
Feature activation-9.76e-01

Pos logit contributions
bed+0.035
aroo+0.031
ged+0.030
ging+0.029
bly+0.029
Neg logit contributions
clock-0.029
 works-0.028
 restaurants-0.026
 ABC-0.026
bows-0.026
Token never
Token ID1239
Feature activation-5.15e-01

Pos logit contributions
bed+0.029
ged+0.026
aroo+0.024
ging+0.024
 luckily+0.024
Neg logit contributions
 works-0.034
clock-0.033
bows-0.032
 ABC-0.032
 restaurants-0.030
Token had
Token ID550
Feature activation-8.05e-01

Pos logit contributions
bed+0.017
ged+0.016
ging+0.015
aroo+0.015
bly+0.014
Neg logit contributions
clock-0.016
 works-0.015
 ABC-0.015
 numbers-0.015
bows-0.015
Token a
Token ID257
Feature activation-4.74e-01

Pos logit contributions
bed+0.028
aroo+0.026
ged+0.025
ging+0.024
bly+0.024
Neg logit contributions
 works-0.025
clock-0.025
bows-0.023
 ABC-0.023
 restaurants-0.022
Token lizard
Token ID42406
Feature activation-5.22e+00

Pos logit contributions
bed+0.019
aroo+0.017
ging+0.017
ged+0.017
bly+0.017
Neg logit contributions
 works-0.013
clock-0.013
 ABC-0.012
 numbers-0.012
 library-0.012
Token before
Token ID878
Feature activation-6.36e-01

Pos logit contributions
bed+0.177
bly+0.163
ged+0.161
aroo+0.160
ging+0.158
Neg logit contributions
 library-0.158
clock-0.157
 works-0.156
 books-0.155
 numbers-0.149
Token,
Token ID11
Feature activation-3.49e-02

Pos logit contributions
bed+0.024
aroo+0.022
ging+0.021
bly+0.021
ged+0.021
Neg logit contributions
clock-0.018
 works-0.018
 numbers-0.017
 ABC-0.017
 library-0.017
Token but
Token ID475
Feature activation-2.76e+00

Pos logit contributions
bed+0.001
aroo+0.001
ging+0.001
bly+0.001
ged+0.001
Neg logit contributions
 works-0.001
clock-0.001
 numbers-0.001
 library-0.001
 ABC-0.001
Token Lily
Token ID20037
Feature activation-1.20e+00

Pos logit contributions
bed+0.103
ging+0.094
aroo+0.093
ged+0.091
bly+0.090
Neg logit contributions
 works-0.083
clock-0.081
 numbers-0.076
 library-0.076
 looks-0.075
Token assured
Token ID13933
Feature activation-1.16e+00

Pos logit contributions
bed+0.044
aroo+0.040
ged+0.039
ging+0.038
bly+0.037
Neg logit contributions
clock-0.037
 works-0.036
 ABC-0.034
 numbers-0.034
bows-0.033
Token to
Token ID284
Feature activation+2.58e-01

Pos logit contributions
bed+0.009
aroo+0.008
bly+0.008
ged+0.008
ging+0.008
Neg logit contributions
clock-0.008
 works-0.008
 numbers-0.007
 library-0.007
 ABC-0.007
Token find
Token ID1064
Feature activation-3.07e-01

Pos logit contributions
 works+0.007
clock+0.007
 numbers+0.006
 restaurants+0.006
 library+0.006
Neg logit contributions
bed-0.011
aroo-0.010
ging-0.010
ged-0.010
bly-0.009
Token the
Token ID262
Feature activation-4.20e-01

Pos logit contributions
bed+0.014
ging+0.012
ged+0.012
aroo+0.012
oned+0.012
Neg logit contributions
 works-0.007
 numbers-0.007
 books-0.006
clock-0.006
 names-0.006
Token big
Token ID1263
Feature activation-1.19e+00

Pos logit contributions
bed+0.015
aroo+0.014
ging+0.013
ged+0.013
bly+0.013
Neg logit contributions
clock-0.013
 works-0.013
 ABC-0.012
 restaurants-0.012
bows-0.011
Token k
Token ID479
Feature activation-3.22e+00

Pos logit contributions
bed+0.043
aroo+0.038
ging+0.037
ged+0.037
bly+0.034
Neg logit contributions
clock-0.037
 works-0.036
 ABC-0.034
bows-0.033
 restaurants-0.033
Tokenang
Token ID648
Feature activation-5.21e+00

Pos logit contributions
bed+0.079
ged+0.068
ging+0.066
oned+0.062
bly+0.062
Neg logit contributions
clock-0.127
 works-0.125
bows-0.121
 library-0.119
 numbers-0.119
Tokenaroo
Token ID38049
Feature activation-3.54e+00

Pos logit contributions
bed+0.079
oned+0.054
ged+0.053
bly+0.049
ging+0.049
Neg logit contributions
 numbers-0.232
 works-0.229
 looks-0.226
 ABC-0.224
 statues-0.220
Token and
Token ID290
Feature activation-5.50e-01

Pos logit contributions
bed+0.127
bly+0.118
aroo+0.118
ged+0.118
ging+0.117
Neg logit contributions
 works-0.104
clock-0.101
 looks-0.097
 numbers-0.096
 library-0.096
Token asked
Token ID1965
Feature activation-5.84e-01

Pos logit contributions
bed+0.020
aroo+0.018
ging+0.018
ged+0.017
bly+0.017
Neg logit contributions
 works-0.017
clock-0.017
 numbers-0.016
 library-0.015
 looks-0.015
Token for
Token ID329
Feature activation-5.46e-01

Pos logit contributions
bed+0.022
aroo+0.020
ging+0.019
bly+0.019
ged+0.019
Neg logit contributions
 works-0.017
clock-0.017
 numbers-0.016
 ABC-0.016
 restaurants-0.015
Token his
Token ID465
Feature activation-1.00e+00

Pos logit contributions
bed+0.022
ging+0.020
aroo+0.020
ged+0.020
bly+0.019
Neg logit contributions
 works-0.014
clock-0.014
 numbers-0.013
 ABC-0.013
 books-0.013
Token yes
Token ID3763
Feature activation+9.91e-01

Pos logit contributions
bed+0.109
aroo+0.100
ging+0.099
bly+0.096
ged+0.096
Neg logit contributions
 works-0.072
clock-0.072
 numbers-0.068
 ABC-0.067
bows-0.067
Token and
Token ID290
Feature activation-5.79e-01

Pos logit contributions
 works+0.033
clock+0.031
 restaurants+0.030
 library+0.030
 ABC+0.030
Neg logit contributions
bed-0.035
aroo-0.031
ging-0.030
ged-0.029
bly-0.029
Token gave
Token ID2921
Feature activation-6.51e-01

Pos logit contributions
bed+0.020
aroo+0.018
ging+0.018
ged+0.018
bly+0.018
Neg logit contributions
 works-0.018
clock-0.018
 numbers-0.017
bows-0.017
 ABC-0.017
Token the
Token ID262
Feature activation-9.55e-01

Pos logit contributions
bed+0.025
ging+0.023
aroo+0.023
bly+0.023
ged+0.022
Neg logit contributions
 works-0.017
 numbers-0.017
clock-0.016
 books-0.016
 looks-0.016
Token k
Token ID479
Feature activation-3.42e+00

Pos logit contributions
bed+0.031
ged+0.027
ging+0.027
aroo+0.026
bly+0.026
Neg logit contributions
 works-0.033
clock-0.033
 numbers-0.032
 ABC-0.032
 library-0.031
Tokenang
Token ID648
Feature activation-5.19e+00

Pos logit contributions
bed+0.135
ged+0.120
ging+0.120
oned+0.116
bled+0.116
Neg logit contributions
clock-0.085
 works-0.081
bows-0.080
 numbers-0.077
 ABC-0.077
Tokenaroo
Token ID38049
Feature activation-4.22e+00

Pos logit contributions
bed+0.065
ging+0.035
oned+0.034
ged+0.032
bly+0.031
Neg logit contributions
 numbers-0.256
 works-0.252
clock-0.251
 ABC-0.251
 looks-0.249
Token a
Token ID257
Feature activation-9.15e-01

Pos logit contributions
bed+0.160
aroo+0.147
ging+0.141
ged+0.141
bly+0.138
Neg logit contributions
 works-0.123
clock-0.123
 ABC-0.113
bows-0.112
 numbers-0.111
Token big
Token ID1263
Feature activation-1.41e+00

Pos logit contributions
bed+0.037
aroo+0.035
ged+0.033
ging+0.033
bly+0.033
Neg logit contributions
clock-0.024
 works-0.024
bows-0.021
 ABC-0.021
 numbers-0.021
Token hug
Token ID16225
Feature activation+7.49e-01

Pos logit contributions
bed+0.055
aroo+0.050
ging+0.049
ged+0.049
bly+0.048
Neg logit contributions
clock-0.040
 works-0.039
 ABC-0.036
 numbers-0.036
bows-0.036
Token.
Token ID13
Feature activation-7.25e-01

Pos logit contributions
clock+0.023
 works+0.023
 numbers+0.021
bows+0.021
 ABC+0.021
Neg logit contributions
bed-0.027
aroo-0.024
ging-0.024
ged-0.024
bly-0.023
Token She
Token ID1375
Feature activation+5.02e-01

Pos logit contributions
bed+0.003
aroo+0.003
ged+0.003
ging+0.003
bly+0.003
Neg logit contributions
 works-0.002
clock-0.002
bows-0.002
 ABC-0.002
 restaurants-0.002
Token made
Token ID925
Feature activation-5.91e-01

Pos logit contributions
 works+0.014
clock+0.014
 numbers+0.013
 ABC+0.013
bows+0.012
Neg logit contributions
bed-0.020
aroo-0.018
ging-0.018
ged-0.018
bly-0.017
Token a
Token ID257
Feature activation-8.76e-01

Pos logit contributions
bed+0.021
ged+0.017
ging+0.017
bly+0.017
aroo+0.016
Neg logit contributions
clock-0.019
 works-0.019
 library-0.019
 restaurants-0.018
bows-0.018
Token big
Token ID1263
Feature activation-1.45e+00

Pos logit contributions
bed+0.038
aroo+0.035
ging+0.034
ged+0.034
bly+0.033
Neg logit contributions
 works-0.021
clock-0.021
bows-0.019
 ABC-0.018
 restaurants-0.018
Token green
Token ID4077
Feature activation-1.96e+00

Pos logit contributions
bed+0.058
aroo+0.053
ged+0.052
ging+0.052
bly+0.051
Neg logit contributions
 works-0.040
clock-0.039
 numbers-0.036
 ABC-0.036
bows-0.036
Token dot
Token ID16605
Feature activation-5.18e+00

Pos logit contributions
bed+0.076
aroo+0.071
ging+0.069
ged+0.069
bly+0.068
Neg logit contributions
 works-0.054
clock-0.054
 numbers-0.051
 ABC-0.050
bows-0.049
Token and
Token ID290
Feature activation+1.13e-01

Pos logit contributions
bed+0.163
aroo+0.150
ging+0.147
ged+0.146
bly+0.142
Neg logit contributions
 works-0.174
clock-0.170
 numbers-0.167
bows-0.165
 looks-0.163
Token a
Token ID257
Feature activation-3.69e-01

Pos logit contributions
clock+0.003
 works+0.003
 ABC+0.003
 numbers+0.003
bows+0.003
Neg logit contributions
bed-0.004
aroo-0.004
ged-0.004
ging-0.004
bly-0.004
Token yellow
Token ID7872
Feature activation-1.03e+00

Pos logit contributions
bed+0.015
aroo+0.014
ging+0.014
ged+0.014
bly+0.014
Neg logit contributions
 works-0.009
clock-0.009
 ABC-0.008
bows-0.008
 numbers-0.008
Token swirl
Token ID42835
Feature activation+5.07e-01

Pos logit contributions
bed+0.040
aroo+0.037
ging+0.036
ged+0.036
bly+0.035
Neg logit contributions
 works-0.029
clock-0.028
 numbers-0.027
 ABC-0.026
bows-0.026
Token.
Token ID13
Feature activation-1.19e-01

Pos logit contributions
 works+0.019
clock+0.019
 numbers+0.017
bows+0.017
 ABC+0.017
Neg logit contributions
bed-0.015
aroo-0.014
ging-0.013
ged-0.013
bly-0.013
Token He
Token ID679
Feature activation-4.59e-01

Pos logit contributions
bed+0.016
aroo+0.015
ged+0.014
ging+0.013
oned+0.013
Neg logit contributions
 works-0.015
clock-0.014
bows-0.014
 ABC-0.013
 restaurants-0.013
Token had
Token ID550
Feature activation-1.05e+00

Pos logit contributions
bed+0.018
aroo+0.017
ging+0.017
bly+0.016
ged+0.016
Neg logit contributions
 works-0.012
clock-0.012
 numbers-0.011
 ABC-0.011
 looks-0.011
Token never
Token ID1239
Feature activation-4.03e-01

Pos logit contributions
bed+0.031
ged+0.026
aroo+0.026
 luckily+0.024
ched+0.024
Neg logit contributions
bows-0.039
 works-0.039
clock-0.037
 ABC-0.037
 restaurants-0.035
Token seen
Token ID1775
Feature activation-3.11e-01

Pos logit contributions
bed+0.012
ged+0.011
ging+0.010
aroo+0.010
 behind+0.009
Neg logit contributions
 ABC-0.014
clock-0.014
 works-0.014
bows-0.013
 numbers-0.013
Token a
Token ID257
Feature activation-3.67e-01

Pos logit contributions
bed+0.013
aroo+0.012
ging+0.011
ged+0.011
bly+0.011
Neg logit contributions
 works-0.008
clock-0.008
bows-0.007
 ABC-0.007
 numbers-0.007
Token fle
Token ID5104
Feature activation-5.17e+00

Pos logit contributions
bed+0.014
aroo+0.012
ging+0.012
ged+0.012
bly+0.012
Neg logit contributions
clock-0.011
 works-0.011
bows-0.010
 numbers-0.010
 ABC-0.010
Tokena
Token ID64
Feature activation-3.06e+00

Pos logit contributions
bed+0.193
ged+0.179
ging+0.174
ishly+0.171
oned+0.169
Neg logit contributions
bows-0.118
clock-0.111
 library-0.111
 total-0.110
 ABC-0.110
Token before
Token ID878
Feature activation-5.03e-01

Pos logit contributions
bed+0.107
aroo+0.100
bly+0.100
ged+0.098
ging+0.095
Neg logit contributions
clock-0.088
 works-0.087
 library-0.086
 numbers-0.086
 ABC-0.085
Token and
Token ID290
Feature activation-4.93e-01

Pos logit contributions
bed+0.018
aroo+0.016
ging+0.016
ged+0.016
bly+0.015
Neg logit contributions
 works-0.016
clock-0.016
 numbers-0.015
 ABC-0.015
bows-0.014
Token he
Token ID339
Feature activation-6.00e-01

Pos logit contributions
bed+0.018
aroo+0.016
ged+0.016
ging+0.015
bly+0.015
Neg logit contributions
clock-0.015
 works-0.015
 ABC-0.014
bows-0.014
 numbers-0.014
Token wanted
Token ID2227
Feature activation-9.45e-01

Pos logit contributions
bed+0.024
aroo+0.022
ged+0.021
ging+0.021
bly+0.020
Neg logit contributions
clock-0.017
 works-0.017
 ABC-0.015
bows-0.015
 numbers-0.015
Token,
Token ID11
Feature activation-6.09e-01

Pos logit contributions
bed+0.049
aroo+0.049
ging+0.046
bly+0.046
ged+0.045
Neg logit contributions
 works-0.029
 numbers-0.027
clock-0.027
 looks-0.026
 books-0.026
Token Emily
Token ID17608
Feature activation-6.16e-01

Pos logit contributions
bed+0.020
aroo+0.019
ging+0.018
ged+0.018
bly+0.017
Neg logit contributions
 works-0.020
clock-0.020
 numbers-0.019
 books-0.019
 ABC-0.019
Token saw
Token ID2497
Feature activation-7.58e-02

Pos logit contributions
bed+0.022
ged+0.019
aroo+0.019
ging+0.018
bly+0.017
Neg logit contributions
clock-0.019
 works-0.019
 numbers-0.018
 ABC-0.018
bows-0.018
Token a
Token ID257
Feature activation-3.44e-01

Pos logit contributions
bed+0.003
ging+0.003
aroo+0.003
ged+0.003
bly+0.003
Neg logit contributions
 works-0.002
 numbers-0.002
clock-0.002
 library-0.002
 books-0.002
Token do
Token ID466
Feature activation-2.53e+00

Pos logit contributions
bed+0.013
aroo+0.012
ging+0.011
ged+0.011
bly+0.011
Neg logit contributions
clock-0.010
 works-0.010
bows-0.009
 ABC-0.009
 restaurants-0.009
Tokenggy
Token ID19970
Feature activation-5.15e+00

Pos logit contributions
bed+0.065
aroo+0.056
ging+0.055
ged+0.054
bly+0.053
Neg logit contributions
 works-0.104
clock-0.103
 ABC-0.099
 numbers-0.098
bows-0.098
Token walking
Token ID6155
Feature activation+1.73e-02

Pos logit contributions
bed+0.183
bly+0.179
aroo+0.174
ging+0.168
bled+0.166
Neg logit contributions
 library-0.150
 works-0.148
clock-0.146
 books-0.141
 numbers-0.139
Token up
Token ID510
Feature activation-1.97e+00

Pos logit contributions
clock+0.001
 works+0.001
 numbers+0.001
 library+0.001
bows+0.001
Neg logit contributions
bed-0.001
bly-0.000
aroo-0.000
ged-0.000
ging-0.000
Token and
Token ID290
Feature activation+2.37e-01

Pos logit contributions
bed+0.070
aroo+0.063
ged+0.061
ging+0.061
bly+0.059
Neg logit contributions
 works-0.062
clock-0.061
 ABC-0.058
bows-0.057
 numbers-0.057
Token down
Token ID866
Feature activation-5.58e-01

Pos logit contributions
clock+0.008
 works+0.008
 ABC+0.007
bows+0.007
 numbers+0.007
Neg logit contributions
bed-0.008
aroo-0.007
ged-0.007
ging-0.007
bly-0.007
Token the
Token ID262
Feature activation+2.08e-01

Pos logit contributions
bed+0.017
aroo+0.015
ging+0.015
ged+0.015
bly+0.014
Neg logit contributions
 works-0.020
clock-0.020
 ABC-0.019
bows-0.019
 numbers-0.019
Token!
Token ID0
Feature activation-7.96e-01

Pos logit contributions
 works+0.008
clock+0.008
 ABC+0.007
bows+0.007
 numbers+0.007
Neg logit contributions
bed-0.010
aroo-0.009
ging-0.009
ged-0.009
bly-0.009
Token It
Token ID632
Feature activation-9.71e-01

Pos logit contributions
bed+0.028
aroo+0.025
ged+0.024
ging+0.024
bly+0.023
Neg logit contributions
 works-0.026
clock-0.025
 ABC-0.024
bows-0.024
 numbers-0.024
Token snatched
Token ID43276
Feature activation-1.76e+00

Pos logit contributions
bed+0.038
aroo+0.035
ging+0.034
ged+0.034
bly+0.033
Neg logit contributions
 works-0.027
clock-0.027
 numbers-0.024
 ABC-0.024
bows-0.024
Token the
Token ID262
Feature activation-1.63e+00

Pos logit contributions
bed+0.068
aroo+0.064
bly+0.061
ging+0.061
ged+0.060
Neg logit contributions
 works-0.049
clock-0.048
 numbers-0.046
 smells-0.043
 looks-0.043
Token paper
Token ID3348
Feature activation-1.94e+00

Pos logit contributions
bed+0.063
ged+0.056
bly+0.056
ging+0.055
aroo+0.054
Neg logit contributions
 works-0.047
 numbers-0.046
 books-0.045
 library-0.045
 looks-0.044
Token lizard
Token ID42406
Feature activation-5.15e+00

Pos logit contributions
bed+0.054
aroo+0.048
ged+0.046
ging+0.045
bly+0.044
Neg logit contributions
 works-0.076
clock-0.075
 numbers-0.071
 ABC-0.071
bows-0.070
Token away
Token ID1497
Feature activation-1.81e+00

Pos logit contributions
bed+0.152
aroo+0.135
ged+0.133
ging+0.131
bly+0.129
Neg logit contributions
 works-0.188
clock-0.183
 looks-0.177
 numbers-0.175
 smells-0.175
Token and
Token ID290
Feature activation-7.44e-01

Pos logit contributions
bed+0.060
aroo+0.055
ged+0.053
ging+0.053
bly+0.051
Neg logit contributions
 works-0.059
clock-0.059
 numbers-0.056
bows-0.056
 ABC-0.054
Token ran
Token ID4966
Feature activation-7.89e-01

Pos logit contributions
bed+0.026
aroo+0.024
ging+0.023
ged+0.023
bly+0.023
Neg logit contributions
 works-0.023
clock-0.023
 numbers-0.022
 ABC-0.021
bows-0.021
Token off
Token ID572
Feature activation-1.28e+00

Pos logit contributions
bed+0.023
aroo+0.021
bly+0.020
ging+0.019
ged+0.019
Neg logit contributions
clock-0.029
 works-0.028
 numbers-0.027
 books-0.027
 names-0.026
Token!
Token ID0
Feature activation-8.46e-01

Pos logit contributions
bed+0.052
aroo+0.050
bly+0.049
ging+0.047
ged+0.046
Neg logit contributions
clock-0.029
 works-0.029
 numbers-0.029
 books-0.026
bows-0.026
Token is
Token ID318
Feature activation-7.67e-01

Pos logit contributions
bed+0.030
aroo+0.027
ged+0.027
ging+0.026
bly+0.026
Neg logit contributions
clock-0.022
 works-0.021
 ABC-0.021
bows-0.020
 restaurants-0.020
Token normal
Token ID3487
Feature activation-8.77e-01

Pos logit contributions
bed+0.030
aroo+0.028
ging+0.027
ged+0.027
bly+0.027
Neg logit contributions
 works-0.021
clock-0.021
 numbers-0.019
 ABC-0.019
bows-0.019
Token for
Token ID329
Feature activation-1.26e+00

Pos logit contributions
bed+0.029
aroo+0.025
ging+0.024
ged+0.024
bly+0.024
Neg logit contributions
clock-0.029
 works-0.029
 ABC-0.028
 restaurants-0.028
 library-0.028
Token old
Token ID1468
Feature activation-1.97e+00

Pos logit contributions
bed+0.046
aroo+0.041
ging+0.040
ged+0.040
bly+0.039
Neg logit contributions
 works-0.039
clock-0.039
 numbers-0.036
 ABC-0.036
bows-0.035
Token k
Token ID479
Feature activation-3.76e+00

Pos logit contributions
bed+0.075
aroo+0.068
ging+0.066
ged+0.066
bly+0.062
Neg logit contributions
clock-0.055
 works-0.055
 ABC-0.051
bows-0.050
 numbers-0.049
Tokenang
Token ID648
Feature activation-5.14e+00

Pos logit contributions
bed+0.117
ged+0.101
ging+0.100
aroo+0.100
bly+0.098
Neg logit contributions
clock-0.130
 works-0.126
bows-0.121
 numbers-0.118
 library-0.118
Tokenaro
Token ID12022
Feature activation-1.06e+00

Pos logit contributions
bed+0.113
ging+0.088
ged+0.087
bly+0.085
aroo+0.083
Neg logit contributions
 works-0.221
clock-0.217
 numbers-0.213
 ABC-0.208
bows-0.206
Tokenos
Token ID418
Feature activation+7.58e-02

Pos logit contributions
bed+0.048
aroo+0.045
ged+0.044
ging+0.043
bly+0.042
Neg logit contributions
 works-0.023
clock-0.023
 numbers-0.021
 ABC-0.021
 library-0.020
Token."
Token ID526
Feature activation-7.85e-01

Pos logit contributions
clock+0.003
 works+0.003
 ABC+0.002
 numbers+0.002
 library+0.002
Neg logit contributions
bed-0.002
aroo-0.002
ging-0.002
ged-0.002
bly-0.002
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
bed+0.032
ging+0.030
bly+0.030
aroo+0.029
ged+0.029
Neg logit contributions
clock-0.020
 works-0.018
 library-0.018
 numbers-0.018
 ABC-0.017
Token
Token ID198
Feature activation-9.58e-01

Pos logit contributions
bed+0.057
ging+0.052
ged+0.050
bly+0.050
aroo+0.050
Neg logit contributions
clock-0.030
 works-0.029
 library-0.028
 numbers-0.028
 ABC-0.027
Token to
Token ID284
Feature activation+2.86e-01

Pos logit contributions
bed+0.002
ged+0.002
ging+0.002
aroo+0.002
 then+0.002
Neg logit contributions
 works-0.002
clock-0.002
bows-0.002
 ABC-0.002
 total-0.002
Token take
Token ID1011
Feature activation-9.08e-01

Pos logit contributions
clock+0.009
 works+0.009
bows+0.008
 ABC+0.008
 statues+0.008
Neg logit contributions
bed-0.010
aroo-0.009
bly-0.008
oned-0.008
 swat-0.008
Token a
Token ID257
Feature activation-7.74e-01

Pos logit contributions
bed+0.027
ged+0.025
ging+0.024
aroo+0.023
bly+0.022
Neg logit contributions
clock-0.034
 works-0.034
bows-0.032
 ABC-0.031
 library-0.030
Token pol
Token ID755
Feature activation-9.69e-01

Pos logit contributions
bed+0.033
aroo+0.031
ged+0.030
ging+0.030
bly+0.029
Neg logit contributions
clock-0.019
 works-0.018
bows-0.017
 numbers-0.017
 ABC-0.016
Tokenka
Token ID4914
Feature activation-8.08e-01

Pos logit contributions
bed+0.023
ging+0.019
ged+0.019
aroo+0.019
bly+0.019
Neg logit contributions
clock-0.043
 library-0.042
 ABC-0.041
 works-0.041
 restaurants-0.041
Token dot
Token ID16605
Feature activation-5.14e+00

Pos logit contributions
bed+0.029
aroo+0.027
ging+0.026
ged+0.026
bly+0.025
Neg logit contributions
clock-0.025
 works-0.025
 ABC-0.023
 numbers-0.023
bows-0.023
Token umbrella
Token ID25510
Feature activation-3.29e-01

Pos logit contributions
bed+0.167
ging+0.151
bly+0.150
aroo+0.149
ged+0.145
Neg logit contributions
clock-0.158
 books-0.157
 works-0.156
bows-0.153
 numbers-0.151
Token.
Token ID13
Feature activation-6.39e-01

Pos logit contributions
bed+0.011
aroo+0.010
ged+0.009
ging+0.009
bly+0.009
Neg logit contributions
 works-0.011
clock-0.011
 ABC-0.011
 numbers-0.010
 restaurants-0.010
Token
Token ID220
Feature activation+2.46e+00

Pos logit contributions
bed+0.015
ged+0.012
oned+0.012
aroo+0.011
 luckily+0.009
Neg logit contributions
 works-0.028
clock-0.025
 jobs-0.025
bows-0.025
 statues-0.025
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
clock+0.076
 works+0.076
 ABC+0.071
 numbers+0.070
bows+0.069
Neg logit contributions
bed-0.088
aroo-0.080
ging-0.078
ged-0.078
bly-0.076
Token
Token ID198
Feature activation-6.81e-01

Pos logit contributions
bed+0.051
aroo+0.046
ging+0.046
bly+0.046
ged+0.045
Neg logit contributions
clock-0.032
 works-0.032
 ABC-0.031
 library-0.030
 numbers-0.030
Token to
Token ID284
Feature activation+1.28e+00

Pos logit contributions
bed+0.032
aroo+0.027
ged+0.026
bly+0.025
ging+0.025
Neg logit contributions
 works-0.029
bows-0.029
clock-0.027
 library-0.025
 ABC-0.025
Token draw
Token ID3197
Feature activation+1.25e+00

Pos logit contributions
 works+0.042
clock+0.041
aris+0.039
bows+0.039
 smells+0.039
Neg logit contributions
bed-0.042
aroo-0.037
bly-0.035
oned-0.033
 swat-0.033
Token lots
Token ID6041
Feature activation+2.26e+00

Pos logit contributions
clock+0.047
 works+0.046
 ABC+0.044
 library+0.043
 restaurants+0.043
Neg logit contributions
bed-0.037
aroo-0.031
bly-0.031
ging-0.030
ged-0.030
Token of
Token ID286
Feature activation+2.03e-01

Pos logit contributions
clock+0.103
 works+0.103
 ABC+0.097
bows+0.096
 library+0.096
Neg logit contributions
bed-0.045
aroo-0.041
bly-0.036
ging-0.036
ged-0.034
Token pretty
Token ID2495
Feature activation+7.80e-01

Pos logit contributions
clock+0.004
 works+0.004
bows+0.004
 ABC+0.003
 total+0.003
Neg logit contributions
bed-0.009
aroo-0.008
ging-0.008
ged-0.007
bly-0.007
Token pictures
Token ID5986
Feature activation+3.24e+00

Pos logit contributions
clock+0.019
 works+0.017
 ABC+0.016
 Sale+0.016
 total+0.016
Neg logit contributions
bed-0.033
ged-0.027
ging-0.027
ling-0.026
aroo-0.026
Token."
Token ID526
Feature activation+8.44e-01

Pos logit contributions
 works+0.120
clock+0.119
 ABC+0.113
 meanings+0.110
 restaurants+0.110
Neg logit contributions
bed-0.095
aroo-0.085
bly-0.079
ging-0.078
ged-0.077
Token
Token ID198
Feature activation-3.93e-01

Pos logit contributions
clock+0.023
 works+0.021
 ABC+0.021
 library+0.021
bows+0.020
Neg logit contributions
bed-0.033
aroo-0.032
ging-0.032
bly-0.032
ged-0.030
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
bed+0.018
ging+0.017
bly+0.017
aroo+0.017
ged+0.016
Neg logit contributions
 ABC-0.007
clock-0.007
 numbers-0.007
 works-0.007
 library-0.007
TokenHer
Token ID9360
Feature activation+1.87e+00

Pos logit contributions
bed+0.005
aroo+0.004
ged+0.004
ging+0.004
bly+0.004
Neg logit contributions
clock-0.004
 works-0.004
 library-0.004
 ABC-0.004
 numbers-0.004
Token mom
Token ID1995
Feature activation+2.08e+00

Pos logit contributions
clock+0.049
 works+0.049
 numbers+0.047
 ABC+0.047
 library+0.044
Neg logit contributions
bed-0.076
aroo-0.071
ging-0.070
ged-0.069
bly-0.069
Token one
Token ID530
Feature activation-1.78e+00

Pos logit contributions
bed+0.005
aroo+0.004
ged+0.004
ging+0.004
bly+0.004
Neg logit contributions
 works-0.004
clock-0.004
bows-0.004
 library-0.004
 ABC-0.004
Token home
Token ID1363
Feature activation+7.15e-01

Pos logit contributions
bed+0.067
ging+0.061
ged+0.061
bly+0.058
aroo+0.057
Neg logit contributions
clock-0.054
 works-0.052
 library-0.049
 flavors-0.049
 looks-0.049
Token?"
Token ID1701
Feature activation+1.25e+00

Pos logit contributions
 works+0.021
clock+0.021
 ABC+0.020
bows+0.020
 numbers+0.020
Neg logit contributions
bed-0.027
aroo-0.024
ged-0.023
ging-0.023
bly-0.023
Token
Token ID198
Feature activation+2.27e-02

Pos logit contributions
clock+0.032
 works+0.030
 ABC+0.030
 library+0.030
 numbers+0.030
Neg logit contributions
bed-0.051
aroo-0.049
bly-0.048
ging-0.048
ged-0.047
Token
Token ID198
Feature activation+1.37e-01

Pos logit contributions
clock+0.000
 ABC+0.000
 grand+0.000
 numbers+0.000
 brushes+0.000
Neg logit contributions
bed-0.001
aroo-0.001
ging-0.001
bly-0.001
ged-0.001
TokenMom
Token ID29252
Feature activation+3.22e+00

Pos logit contributions
clock+0.003
 brushes+0.003
 library+0.003
 numbers+0.003
 ABC+0.003
Neg logit contributions
bed-0.005
aroo-0.005
ged-0.005
ging-0.005
bly-0.005
Token laughed
Token ID13818
Feature activation+5.07e-01

Pos logit contributions
clock+0.101
 works+0.100
 ABC+0.093
bows+0.093
 restaurants+0.093
Neg logit contributions
bed-0.115
aroo-0.104
ged-0.101
ging-0.099
bly-0.097
Token and
Token ID290
Feature activation+1.71e+00

Pos logit contributions
clock+0.012
 works+0.012
 looks+0.011
 numbers+0.011
 books+0.011
Neg logit contributions
aroo-0.022
bed-0.021
bly-0.020
ging-0.019
ged-0.019
Token said
Token ID531
Feature activation+3.88e-01

Pos logit contributions
 works+0.051
clock+0.049
 numbers+0.046
 looks+0.046
 smells+0.045
Neg logit contributions
bed-0.065
aroo-0.059
ging-0.058
bly-0.057
ged-0.056
Token,
Token ID11
Feature activation+7.22e-01

Pos logit contributions
 works+0.011
clock+0.011
 numbers+0.011
 ABC+0.011
bows+0.010
Neg logit contributions
bed-0.015
aroo-0.013
ging-0.013
ged-0.013
bly-0.013
Token "
Token ID366
Feature activation+8.99e-01

Pos logit contributions
 works+0.019
clock+0.019
 ABC+0.017
 numbers+0.017
bows+0.017
Neg logit contributions
bed-0.030
aroo-0.027
ging-0.027
ged-0.027
bly-0.026
Token We
Token ID775
Feature activation-3.11e-01

Pos logit contributions
clock+0.022
 works+0.020
 ABC+0.019
 names+0.019
 library+0.019
Neg logit contributions
bed-0.032
ged-0.031
ging-0.030
aroo-0.030
bly-0.029
Token can
Token ID460
Feature activation+1.46e-01

Pos logit contributions
bed+0.016
aroo+0.015
ging+0.015
ged+0.015
bly+0.014
Neg logit contributions
clock-0.005
 works-0.005
 ABC-0.004
 numbers-0.004
bows-0.004
Token come
Token ID1282
Feature activation+9.57e-01

Pos logit contributions
 works+0.004
clock+0.004
 numbers+0.003
 ABC+0.003
bows+0.003
Neg logit contributions
bed-0.006
aroo-0.006
ged-0.005
ging-0.005
bly-0.005
Token back
Token ID736
Feature activation-2.24e-02

Pos logit contributions
 works+0.036
clock+0.036
 ABC+0.034
bows+0.034
 numbers+0.034
Neg logit contributions
bed-0.028
aroo-0.025
ging-0.024
ged-0.024
bly-0.023
Token before
Token ID878
Feature activation+7.66e-01

Pos logit contributions
bed+0.001
aroo+0.001
ged+0.001
ging+0.001
bly+0.001
Neg logit contributions
 works-0.001
clock-0.001
 ABC-0.001
bows-0.001
 numbers-0.001
Token mom
Token ID1995
Feature activation+3.96e+00

Pos logit contributions
 works+0.022
clock+0.022
 numbers+0.020
 ABC+0.020
bows+0.020
Neg logit contributions
bed-0.030
aroo-0.027
ging-0.026
ged-0.026
bly-0.026
Token sees
Token ID7224
Feature activation+1.46e+00

Pos logit contributions
 ABC+0.107
clock+0.107
 meanings+0.103
 numbers+0.102
 statues+0.102
Neg logit contributions
bed-0.145
aroo-0.134
ged-0.133
ging-0.129
oned-0.122
Token us
Token ID514
Feature activation+6.37e-01

Pos logit contributions
 works+0.044
clock+0.044
 numbers+0.041
 ABC+0.041
bows+0.040
Neg logit contributions
bed-0.054
aroo-0.049
ging-0.048
ged-0.048
bly-0.046
Token."
Token ID526
Feature activation-1.05e-01

Pos logit contributions
clock+0.021
 works+0.021
 ABC+0.019
 numbers+0.019
bows+0.019
Neg logit contributions
bed-0.022
aroo-0.019
ging-0.019
ged-0.019
bly-0.018
Token
Token ID198
Feature activation-4.81e-01

Pos logit contributions
bed+0.004
bly+0.004
ging+0.004
aroo+0.004
ged+0.004
Neg logit contributions
clock-0.003
 works-0.003
 numbers-0.003
 ABC-0.003
 library-0.003
Token
Token ID198
Feature activation-3.35e-01

Pos logit contributions
bed+0.023
ging+0.021
aroo+0.021
ged+0.021
bly+0.020
Neg logit contributions
 works-0.009
clock-0.009
 looks-0.008
 books-0.008
 ABC-0.008
Token
Token ID198
Feature activation-7.49e-01

Pos logit contributions
clock+0.028
 works+0.028
 ABC+0.026
 numbers+0.026
bows+0.026
Neg logit contributions
bed-0.030
aroo-0.027
ging-0.026
ged-0.026
bly-0.025
Token
Token ID198
Feature activation-3.77e-01

Pos logit contributions
bed+0.033
bly+0.031
ging+0.031
aroo+0.031
ged+0.030
Neg logit contributions
clock-0.016
 works-0.015
 ABC-0.015
 numbers-0.014
 library-0.014
Token"
Token ID1
Feature activation+1.07e+00

Pos logit contributions
bed+0.013
aroo+0.012
ged+0.012
ging+0.012
bly+0.011
Neg logit contributions
clock-0.012
 works-0.011
 library-0.011
 numbers-0.011
 ABC-0.011
TokenNo
Token ID2949
Feature activation-1.09e+00

Pos logit contributions
clock+0.033
 works+0.032
 numbers+0.031
 ABC+0.030
 library+0.030
Neg logit contributions
bed-0.040
aroo-0.036
ging-0.035
ged-0.035
bly-0.034
Token,
Token ID11
Feature activation+3.88e-01

Pos logit contributions
bed+0.027
aroo+0.025
ged+0.023
ging+0.022
 luckily+0.020
Neg logit contributions
clock-0.046
bows-0.043
 works-0.043
aris-0.041
 restaurants-0.040
Token mom
Token ID1995
Feature activation+3.15e+00

Pos logit contributions
clock+0.012
 works+0.012
 ABC+0.011
bows+0.011
 numbers+0.011
Neg logit contributions
bed-0.015
aroo-0.013
ging-0.013
ged-0.013
bly-0.013
Token,
Token ID11
Feature activation+1.98e-01

Pos logit contributions
 ABC+0.137
 restaurants+0.136
clock+0.134
 tours+0.131
 museums+0.129
Neg logit contributions
bed-0.067
aroo-0.055
ged-0.053
ging-0.051
 behind-0.045
Token I
Token ID314
Feature activation+8.02e-01

Pos logit contributions
clock+0.006
 works+0.006
bows+0.006
 ABC+0.006
 flavors+0.006
Neg logit contributions
bed-0.007
aroo-0.007
ged-0.006
ging-0.006
bly-0.006
Token want
Token ID765
Feature activation-2.01e-01

Pos logit contributions
clock+0.025
 ABC+0.022
bows+0.022
 statues+0.022
 numbers+0.022
Neg logit contributions
bed-0.029
ged-0.027
aroo-0.027
ging-0.027
dd-0.024
Token to
Token ID284
Feature activation+1.79e+00

Pos logit contributions
bed+0.007
aroo+0.006
ged+0.006
ging+0.006
bly+0.006
Neg logit contributions
 works-0.006
bows-0.006
clock-0.006
 ABC-0.006
aris-0.006
Token go
Token ID467
Feature activation+2.94e-02

Pos logit contributions
 works+0.055
clock+0.054
 ABC+0.050
bows+0.049
 numbers+0.049
Neg logit contributions
bed-0.066
aroo-0.061
bly-0.055
ged-0.054
 swat-0.054
Token you
Token ID345
Feature activation+6.87e-01

Pos logit contributions
clock+0.024
 works+0.024
bows+0.022
 smells+0.021
 restaurants+0.021
Neg logit contributions
bed-0.024
aroo-0.022
ged-0.021
ging-0.020
bly-0.020
Token understand
Token ID1833
Feature activation+6.06e-01

Pos logit contributions
clock+0.020
 works+0.020
 ABC+0.019
 numbers+0.019
bows+0.018
Neg logit contributions
bed-0.026
aroo-0.023
ging-0.023
ged-0.023
bly-0.022
Token?"
Token ID1701
Feature activation+8.50e-01

Pos logit contributions
clock+0.014
 works+0.014
 ABC+0.013
bows+0.013
 numbers+0.013
Neg logit contributions
bed-0.027
aroo-0.024
ging-0.024
ged-0.024
bly-0.023
Token
Token ID198
Feature activation-8.45e-02

Pos logit contributions
clock+0.021
 works+0.020
 ABC+0.020
 numbers+0.019
 library+0.019
Neg logit contributions
bed-0.037
ging-0.034
bly-0.034
ged-0.033
aroo-0.033
Token
Token ID198
Feature activation+1.34e-02

Pos logit contributions
bed+0.004
ging+0.004
bly+0.004
aroo+0.004
ged+0.004
Neg logit contributions
 works-0.002
clock-0.002
 ABC-0.002
 numbers-0.002
 library-0.002
TokenS
Token ID50
Feature activation+3.31e+00

Pos logit contributions
clock+0.000
 works+0.000
 numbers+0.000
 library+0.000
 ABC+0.000
Neg logit contributions
bed-0.000
aroo-0.000
ged-0.000
ging-0.000
bly-0.000
Tokenara
Token ID3301
Feature activation+7.04e-01

Pos logit contributions
clock+0.123
 restaurants+0.118
 works+0.116
 packages+0.115
 ABC+0.114
Neg logit contributions
bed-0.090
aroo-0.075
ged-0.074
ging-0.071
inn-0.067
Token and
Token ID290
Feature activation+7.20e-01

Pos logit contributions
clock+0.020
 works+0.019
 restaurants+0.018
bows+0.018
 ABC+0.018
Neg logit contributions
bed-0.027
aroo-0.024
ged-0.024
ging-0.023
bly-0.022
Token Ben
Token ID3932
Feature activation+1.42e-01

Pos logit contributions
clock+0.026
 works+0.026
bows+0.024
 ABC+0.024
 numbers+0.024
Neg logit contributions
bed-0.022
aroo-0.020
ged-0.019
ging-0.019
bly-0.018
Token nod
Token ID18666
Feature activation+1.98e+00

Pos logit contributions
clock+0.004
 works+0.004
 ABC+0.004
 restaurants+0.004
 library+0.004
Neg logit contributions
bed-0.005
aroo-0.005
ged-0.005
ging-0.005
bly-0.004
Token.
Token ID13
Feature activation+1.23e+00

Pos logit contributions
clock+0.056
 works+0.055
 ABC+0.051
 numbers+0.051
bows+0.050
Neg logit contributions
bed-0.077
aroo-0.075
ging-0.069
ged-0.069
bly-0.068
Token"
Token ID1
Feature activation+4.28e-01

Pos logit contributions
bed+0.011
aroo+0.010
ged+0.010
ging+0.009
bly+0.009
Neg logit contributions
clock-0.009
 works-0.009
 library-0.009
 numbers-0.009
 ABC-0.009
TokenWow
Token ID22017
Feature activation-1.19e+00

Pos logit contributions
clock+0.014
 works+0.013
 numbers+0.013
bows+0.013
 ABC+0.013
Neg logit contributions
bed-0.015
aroo-0.014
ging-0.013
ged-0.013
bly-0.013
Token,
Token ID11
Feature activation+1.01e+00

Pos logit contributions
bed+0.036
ged+0.030
ging+0.030
aroo+0.030
bly+0.028
Neg logit contributions
clock-0.048
 ABC-0.043
 meanings-0.043
 works-0.042
 flavors-0.042
Token you
Token ID345
Feature activation+1.47e+00

Pos logit contributions
clock+0.036
 works+0.033
 ABC+0.032
bows+0.032
 flavors+0.031
Neg logit contributions
bed-0.032
aroo-0.031
ged-0.028
bly-0.028
ging-0.027
Token look
Token ID804
Feature activation+2.44e+00

Pos logit contributions
clock+0.044
 ABC+0.038
 facts+0.038
 clocks+0.038
 restaurants+0.037
Neg logit contributions
bed-0.057
bly-0.049
aroo-0.047
ged-0.046
ched-0.046
Token so
Token ID523
Feature activation+8.75e-01

Pos logit contributions
clock+0.081
 works+0.080
 ABC+0.075
bows+0.075
 flavors+0.073
Neg logit contributions
bed-0.081
ging-0.073
ged-0.071
bly-0.070
aroo-0.069
Token pretty
Token ID2495
Feature activation+9.18e-01

Pos logit contributions
clock+0.029
 clocks+0.027
rays+0.026
 meanings+0.026
 ABC+0.026
Neg logit contributions
bed-0.028
bly-0.027
aroo-0.024
ging-0.024
ling-0.023
Token,
Token ID11
Feature activation+1.18e+00

Pos logit contributions
clock+0.027
 works+0.027
 ABC+0.027
 library+0.025
 restaurants+0.025
Neg logit contributions
bed-0.034
aroo-0.031
ging-0.030
ged-0.030
bly-0.030
Token Lily
Token ID20037
Feature activation-6.04e-02

Pos logit contributions
clock+0.040
 works+0.039
bows+0.036
 ABC+0.036
 restaurants+0.035
Neg logit contributions
bed-0.040
aroo-0.037
ging-0.034
bly-0.034
ged-0.034
Token!"
Token ID2474
Feature activation-1.49e-01

Pos logit contributions
bed+0.002
aroo+0.002
ging+0.002
ged+0.002
bly+0.002
Neg logit contributions
clock-0.002
 works-0.002
 ABC-0.002
 numbers-0.002
 restaurants-0.002
Token her
Token ID607
Feature activation+1.38e+00

Pos logit contributions
bed+0.007
bly+0.007
ging+0.007
aroo+0.006
bled+0.006
Neg logit contributions
 works-0.003
clock-0.003
 numbers-0.003
 library-0.003
 brushes-0.003
Token<|endoftext|>
Token ID50256
Feature activation+1.29e+00

Pos logit contributions
bed+0.010
ged+0.010
ging+0.010
aroo+0.010
bly+0.009
Neg logit contributions
clock-0.008
 works-0.007
 ABC-0.007
 numbers-0.007
 library-0.007
TokenOnce
Token ID7454
Feature activation-1.34e+00

Pos logit contributions
 works+0.037
clock+0.037
 ABC+0.034
 numbers+0.034
 library+0.033
Neg logit contributions
bed-0.049
aroo-0.045
ging-0.045
ged-0.044
bly-0.044
Token upon
Token ID2402
Feature activation+1.11e+00

Pos logit contributions
bed+0.065
aroo+0.060
ging+0.059
ged+0.059
bly+0.058
Neg logit contributions
 works-0.025
clock-0.025
 ABC-0.022
 numbers-0.022
bows-0.022
Token a
Token ID257
Feature activation+8.72e-01

Pos logit contributions
clock+0.029
 works+0.029
 ABC+0.026
 numbers+0.026
bows+0.026
Neg logit contributions
bed-0.046
aroo-0.042
ged-0.041
ging-0.041
bly-0.040
Token time
Token ID640
Feature activation-1.32e-01

Pos logit contributions
 works+0.020
clock+0.019
 ABC+0.018
 library+0.017
 looks+0.017
Neg logit contributions
bed-0.039
aroo-0.037
ging-0.036
ged-0.036
bly-0.035
Token,
Token ID11
Feature activation+1.02e-01

Pos logit contributions
bed+0.005
aroo+0.004
ging+0.004
ged+0.004
bly+0.004
Neg logit contributions
clock-0.004
 works-0.004
 ABC-0.004
 numbers-0.004
bows-0.004
Token there
Token ID612
Feature activation-2.65e-03

Pos logit contributions
 works+0.002
 looks+0.002
 look+0.002
 books+0.002
 smells+0.002
Neg logit contributions
bed-0.005
ging-0.004
ged-0.004
oned-0.004
bly-0.004
Token was
Token ID373
Feature activation+6.94e-01

Pos logit contributions
bed+0.000
ging+0.000
aroo+0.000
bly+0.000
ged+0.000
Neg logit contributions
 works-0.000
clock-0.000
 ABC-0.000
 numbers-0.000
 looks-0.000
Token a
Token ID257
Feature activation+7.15e-01

Pos logit contributions
 library+0.008
 books+0.008
 numbers+0.008
 works+0.008
clock+0.008
Neg logit contributions
bed-0.037
ging-0.037
aroo-0.036
ged-0.035
bly-0.034
Token little
Token ID1310
Feature activation-6.97e-01

Pos logit contributions
 works+0.019
clock+0.019
 ABC+0.017
 numbers+0.017
 library+0.017
Neg logit contributions
bed-0.029
aroo-0.026
ged-0.026
ging-0.026
bly-0.025
Token orange
Token ID10912
Feature activation-1.80e+00

Pos logit contributions
bed+0.026
aroo+0.023
ged+0.023
ging+0.023
bly+0.023
Neg logit contributions
 works-0.021
clock-0.020
 numbers-0.019
 ABC-0.019
 library-0.019
Token,
Token ID11
Feature activation-8.61e-02

Pos logit contributions
 works+0.039
clock+0.039
 ABC+0.038
 flavors+0.037
 meanings+0.037
Neg logit contributions
bed-0.022
aroo-0.018
bly-0.016
ging-0.016
ged-0.016
Token a
Token ID257
Feature activation+1.54e-01

Pos logit contributions
bed+0.003
aroo+0.003
ged+0.003
ging+0.003
bly+0.003
Neg logit contributions
clock-0.002
 works-0.002
 ABC-0.002
bows-0.002
 numbers-0.002
Token magic
Token ID5536
Feature activation-1.06e-01

Pos logit contributions
clock+0.004
 works+0.004
bows+0.004
 ABC+0.004
 numbers+0.004
Neg logit contributions
bed-0.006
aroo-0.006
ging-0.005
ged-0.005
bly-0.005
Token wand
Token ID11569
Feature activation-2.57e+00

Pos logit contributions
bed+0.003
aroo+0.003
ged+0.003
ging+0.003
bly+0.003
Neg logit contributions
clock-0.004
 works-0.004
 ABC-0.004
 numbers-0.004
 restaurants-0.004
Token,
Token ID11
Feature activation+1.27e-01

Pos logit contributions
bed+0.089
aroo+0.081
ging+0.079
ged+0.078
bly+0.077
Neg logit contributions
 works-0.082
clock-0.081
bows-0.076
 numbers-0.076
 ABC-0.076
Token a
Token ID257
Feature activation+3.21e-02

Pos logit contributions
clock+0.004
 works+0.004
 ABC+0.004
bows+0.004
 numbers+0.004
Neg logit contributions
bed-0.004
aroo-0.004
ged-0.004
ging-0.004
bly-0.004
Token st
Token ID336
Feature activation+1.89e+00

Pos logit contributions
 works+0.001
clock+0.001
 numbers+0.001
 ABC+0.001
bows+0.001
Neg logit contributions
bed-0.001
aroo-0.001
ging-0.001
ged-0.001
bly-0.001
Tokeneth
Token ID2788
Feature activation+7.13e-01

Pos logit contributions
 works+0.061
 restaurants+0.059
clock+0.058
 flavors+0.057
 numbers+0.055
Neg logit contributions
bed-0.070
aroo-0.060
ging-0.059
ged-0.058
bly-0.057
Tokenoscope
Token ID40326
Feature activation-8.14e-01

Pos logit contributions
 works+0.024
clock+0.023
bows+0.023
 ABC+0.022
 numbers+0.022
Neg logit contributions
bed-0.023
aroo-0.021
bly-0.021
ging-0.021
ged-0.020
Token,
Token ID11
Feature activation+2.29e-01

Pos logit contributions
bed+0.025
ging+0.021
ged+0.021
aroo+0.021
bly+0.020
Neg logit contributions
 works-0.030
clock-0.030
 restaurants-0.028
 flavors-0.028
 ABC-0.028
Token or
Token ID393
Feature activation+3.73e-01

Pos logit contributions
clock+0.009
 works+0.009
 ABC+0.008
 restaurants+0.008
bows+0.008
Neg logit contributions
bed-0.007
aroo-0.006
ged-0.006
ging-0.005
bly-0.005
Token and
Token ID290
Feature activation-6.83e-02

Pos logit contributions
clock+0.028
 ABC+0.026
 works+0.025
bows+0.025
 numbers+0.025
Neg logit contributions
bed-0.029
ged-0.025
aroo-0.024
ging-0.023
bly-0.022
Token Tom
Token ID4186
Feature activation+4.74e-01

Pos logit contributions
bed+0.003
aroo+0.002
ging+0.002
ged+0.002
bly+0.002
Neg logit contributions
 works-0.002
clock-0.002
 numbers-0.002
 ABC-0.002
 library-0.002
Token are
Token ID389
Feature activation+1.53e+00

Pos logit contributions
clock+0.016
 ABC+0.015
 numbers+0.013
 statues+0.013
 meanings+0.013
Neg logit contributions
bed-0.016
ged-0.015
ging-0.014
aroo-0.013
dd-0.013
Token friends
Token ID2460
Feature activation-2.52e-01

Pos logit contributions
clock+0.051
 works+0.050
 numbers+0.047
 ABC+0.046
 restaurants+0.046
Neg logit contributions
bed-0.053
aroo-0.049
ging-0.047
ged-0.046
bly-0.045
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
bed+0.011
aroo+0.011
ging+0.011
ged+0.011
bly+0.010
Neg logit contributions
clock-0.005
 books-0.005
 works-0.005
 library-0.004
 looks-0.004
Token They
Token ID1119
Feature activation+1.65e+00

Pos logit contributions
clock+0.008
 works+0.008
 library+0.007
bows+0.007
 numbers+0.007
Neg logit contributions
bed-0.018
aroo-0.018
ging-0.017
ged-0.017
bly-0.017
Token like
Token ID588
Feature activation+1.05e+00

Pos logit contributions
clock+0.055
 works+0.051
 ABC+0.049
 flavors+0.048
 numbers+0.048
Neg logit contributions
bed-0.057
aroo-0.051
ged-0.050
ging-0.049
bly-0.048
Token to
Token ID284
Feature activation+2.43e+00

Pos logit contributions
clock+0.035
 works+0.035
bows+0.032
 flavors+0.031
 meanings+0.031
Neg logit contributions
bed-0.031
aroo-0.029
ged-0.027
ging-0.024
 under-0.024
Token play
Token ID711
Feature activation+7.35e-01

Pos logit contributions
clock+0.084
 works+0.080
 meanings+0.076
bows+0.074
 flavors+0.074
Neg logit contributions
bed-0.080
aroo-0.068
ged-0.063
bly-0.062
ging-0.060
Token together
Token ID1978
Feature activation+5.50e-01

Pos logit contributions
 books+0.025
 works+0.025
 numbers+0.024
 jobs+0.023
 library+0.023
Neg logit contributions
ging-0.023
aroo-0.023
ged-0.022
bed-0.021
oned-0.021
Token.
Token ID13
Feature activation-2.36e-02

Pos logit contributions
 numbers+0.013
clock+0.013
 books+0.013
 works+0.012
 ABC+0.012
Neg logit contributions
ging-0.023
bed-0.022
aroo-0.022
bly-0.022
ged-0.022
Token
Token ID198
Feature activation-6.19e-01

Pos logit contributions
bed+0.047
ging+0.044
aroo+0.043
bly+0.043
ged+0.042
Neg logit contributions
 works-0.025
clock-0.025
 ABC-0.024
 numbers-0.023
 library-0.023
TokenBut
Token ID1537
Feature activation-1.51e+00

Pos logit contributions
bed+0.018
aroo+0.016
ging+0.015
ged+0.015
bly+0.015
Neg logit contributions
 works-0.024
clock-0.023
bows-0.022
 ABC-0.022
 numbers-0.022
Token then
Token ID788
Feature activation-1.38e+00

Pos logit contributions
bly+0.057
aroo+0.057
ging+0.056
bed+0.055
oned+0.055
Neg logit contributions
clock-0.039
 books-0.036
 numbers-0.036
 works-0.036
 library-0.036
Token,
Token ID11
Feature activation-2.01e-01

Pos logit contributions
bed+0.046
aroo+0.041
ged+0.040
ging+0.039
bly+0.037
Neg logit contributions
clock-0.049
 works-0.048
bows-0.046
 ABC-0.045
 numbers-0.044
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
bed+0.009
aroo+0.008
ging+0.008
bly+0.008
ged+0.008
Neg logit contributions
 works-0.004
clock-0.004
 numbers-0.004
 restaurants-0.004
 library-0.004
Token sun
Token ID4252
Feature activation+1.96e+00

Pos logit contributions
 works+0.035
clock+0.035
 numbers+0.033
 ABC+0.032
 library+0.032
Neg logit contributions
bed-0.059
aroo-0.054
ged-0.053
ging-0.052
bly-0.051
Token came
Token ID1625
Feature activation+2.24e+00

Pos logit contributions
 works+0.045
clock+0.044
 looks+0.039
 numbers+0.039
 smells+0.038
Neg logit contributions
bed-0.084
aroo-0.079
ging-0.079
bly-0.077
ged-0.077
Token out
Token ID503
Feature activation+4.08e-01

Pos logit contributions
clock+0.083
 works+0.083
 ABC+0.078
 numbers+0.078
bows+0.077
Neg logit contributions
bed-0.067
aroo-0.060
ging-0.058
ged-0.057
bly-0.056
Token and
Token ID290
Feature activation+6.31e-01

Pos logit contributions
clock+0.013
 works+0.013
 numbers+0.012
 ABC+0.012
 looks+0.012
Neg logit contributions
bed-0.014
aroo-0.013
ged-0.013
ging-0.013
bly-0.012
Token it
Token ID340
Feature activation+2.37e-01

Pos logit contributions
clock+0.020
 works+0.020
 ABC+0.019
bows+0.019
 numbers+0.018
Neg logit contributions
bed-0.022
aroo-0.020
ged-0.020
ging-0.019
bly-0.019
Token was
Token ID373
Feature activation-7.49e-01

Pos logit contributions
 works+0.006
clock+0.006
 numbers+0.006
 ABC+0.006
bows+0.006
Neg logit contributions
bed-0.010
aroo-0.009
ging-0.009
ged-0.009
bly-0.008
Token
Token ID198
Feature activation-2.16e-01

Pos logit contributions
bed+0.031
ging+0.028
aroo+0.027
ged+0.027
bly+0.027
Neg logit contributions
clock-0.014
 works-0.014
 library-0.013
 ABC-0.013
 restaurants-0.013
TokenSo
Token ID2396
Feature activation+1.18e-01

Pos logit contributions
bed+0.008
aroo+0.007
ged+0.007
ging+0.007
bly+0.007
Neg logit contributions
clock-0.006
 works-0.006
 library-0.006
 numbers-0.006
 restaurants-0.006
Token Tim
Token ID5045
Feature activation-8.11e-01

Pos logit contributions
clock+0.004
 works+0.004
 ABC+0.004
bows+0.004
 numbers+0.004
Neg logit contributions
bed-0.004
aroo-0.004
ged-0.003
ging-0.003
bly-0.003
Token followed
Token ID3940
Feature activation-1.14e+00

Pos logit contributions
bed+0.025
aroo+0.022
ged+0.022
ging+0.021
ling+0.019
Neg logit contributions
clock-0.029
 statues-0.028
 works-0.027
 ABC-0.027
 restaurants-0.027
Token the
Token ID262
Feature activation+9.97e-01

Pos logit contributions
bed+0.050
bly+0.046
aroo+0.046
ged+0.044
ging+0.044
Neg logit contributions
clock-0.025
 works-0.024
 numbers-0.024
 restaurants-0.023
 ABC-0.023
Token rabbit
Token ID22746
Feature activation-2.66e+00

Pos logit contributions
clock+0.033
 works+0.032
 numbers+0.031
 library+0.030
 smells+0.030
Neg logit contributions
bed-0.035
ged-0.031
aroo-0.031
ging-0.030
bly-0.030
Tokenâ
Token ID22940
Feature activation+9.22e-01

Pos logit contributions
bed+0.098
bly+0.095
aroo+0.092
ging+0.091
ged+0.090
Neg logit contributions
 works-0.075
clock-0.073
 looks-0.071
 numbers-0.070
 library-0.069
Token€
Token ID26391
Feature activation-1.30e+00

Pos logit contributions
clock+0.025
 works+0.025
bows+0.023
 ABC+0.022
 numbers+0.022
Neg logit contributions
bed-0.037
aroo-0.034
ged-0.033
ging-0.033
bly-0.032
Tokenâ„¢
Token ID8151
Feature activation+2.52e-01

Pos logit contributions
bed+0.050
ged+0.043
aroo+0.042
ging+0.041
dd+0.038
Neg logit contributions
 works-0.041
clock-0.038
 numbers-0.038
 ABC-0.037
 meanings-0.036
Tokens
Token ID82
Feature activation+4.91e-01

Pos logit contributions
clock+0.007
 works+0.007
 ABC+0.007
 numbers+0.007
bows+0.007
Neg logit contributions
bed-0.009
aroo-0.008
ging-0.008
ged-0.008
bly-0.008
Token advice
Token ID5608
Feature activation+8.09e-01

Pos logit contributions
clock+0.015
 works+0.014
 numbers+0.014
 ABC+0.014
 looks+0.014
Neg logit contributions
bed-0.018
aroo-0.016
bly-0.016
ged-0.016
ging-0.016
Token and
Token ID290
Feature activation-7.14e-01

Pos logit contributions
bed+0.048
aroo+0.043
ged+0.041
ging+0.041
bly+0.040
Neg logit contributions
clock-0.042
 works-0.042
 ABC-0.039
bows-0.039
 numbers-0.039
Token rabbit
Token ID22746
Feature activation-1.57e+00

Pos logit contributions
bed+0.027
aroo+0.025
ged+0.024
ging+0.024
bly+0.023
Neg logit contributions
clock-0.021
 works-0.021
 ABC-0.019
bows-0.019
 numbers-0.019
Token listened
Token ID16399
Feature activation+1.20e+00

Pos logit contributions
bed+0.066
aroo+0.061
ging+0.059
ged+0.059
bly+0.058
Neg logit contributions
 works-0.039
clock-0.039
 numbers-0.035
 ABC-0.035
bows-0.035
Token to
Token ID284
Feature activation+1.76e-01

Pos logit contributions
clock+0.023
 works+0.022
 numbers+0.021
 looks+0.019
 ABC+0.019
Neg logit contributions
aroo-0.057
bed-0.055
bly-0.053
ging-0.051
ged-0.050
Token the
Token ID262
Feature activation+6.14e-01

Pos logit contributions
 works+0.005
clock+0.005
 numbers+0.005
 ABC+0.005
bows+0.005
Neg logit contributions
bed-0.007
aroo-0.006
ging-0.006
ged-0.006
bly-0.006
Token owl
Token ID39610
Feature activation-1.04e+00

Pos logit contributions
clock+0.020
 works+0.020
bows+0.018
 ABC+0.018
 flavors+0.018
Neg logit contributions
bed-0.021
aroo-0.019
ging-0.019
ged-0.018
bly-0.018
Token.
Token ID13
Feature activation-5.22e-01

Pos logit contributions
bed+0.038
aroo+0.037
bly+0.036
ging+0.035
ged+0.035
Neg logit contributions
clock-0.030
 works-0.030
 ABC-0.028
 numbers-0.028
bows-0.028
Token They
Token ID1119
Feature activation-2.47e-01

Pos logit contributions
bed+0.019
aroo+0.016
ged+0.015
bly+0.015
oned+0.015
Neg logit contributions
 works-0.016
clock-0.016
 restaurants-0.015
 flavors-0.015
 ABC-0.015
Token stopped
Token ID5025
Feature activation-7.68e-01

Pos logit contributions
bed+0.009
aroo+0.008
ged+0.008
ging+0.008
bly+0.008
Neg logit contributions
clock-0.007
 works-0.007
 ABC-0.007
 numbers-0.007
bows-0.007
Token fighting
Token ID4330
Feature activation+1.33e+00

Pos logit contributions
aroo+0.029
bly+0.028
bed+0.027
bled+0.025
dd+0.025
Neg logit contributions
 works-0.022
 numbers-0.021
clock-0.021
 ABC-0.020
 paintings-0.020
Token and
Token ID290
Feature activation+2.19e-01

Pos logit contributions
 works+0.045
clock+0.045
 numbers+0.043
 ABC+0.042
bows+0.041
Neg logit contributions
bed-0.044
aroo-0.041
ging-0.039
ged-0.039
bly-0.039
Token was
Token ID373
Feature activation-1.36e+00

Pos logit contributions
clock+0.023
 works+0.022
bows+0.021
 restaurants+0.021
 ABC+0.021
Neg logit contributions
bed-0.027
aroo-0.024
ged-0.024
ging-0.022
bly-0.022
Token very
Token ID845
Feature activation+1.12e+00

Pos logit contributions
bed+0.048
aroo+0.044
ging+0.042
ged+0.042
bly+0.041
Neg logit contributions
 works-0.044
clock-0.043
 ABC-0.041
bows-0.040
 numbers-0.040
Token careful
Token ID8161
Feature activation-3.28e-01

Pos logit contributions
clock+0.039
 works+0.039
 ABC+0.036
bows+0.036
 numbers+0.036
Neg logit contributions
bed-0.036
aroo-0.033
ging-0.032
ged-0.032
bly-0.031
Token and
Token ID290
Feature activation-2.59e-02

Pos logit contributions
bed+0.011
aroo+0.010
ging+0.010
ged+0.010
bly+0.009
Neg logit contributions
 works-0.011
clock-0.011
 library-0.010
 ABC-0.010
 restaurants-0.010
Token made
Token ID925
Feature activation+5.14e-01

Pos logit contributions
bed+0.001
aroo+0.001
ged+0.001
ging+0.001
bly+0.001
Neg logit contributions
clock-0.001
 works-0.001
 ABC-0.001
bows-0.001
 numbers-0.001
Token sure
Token ID1654
Feature activation-7.43e-01

Pos logit contributions
clock+0.018
 works+0.018
 ABC+0.017
bows+0.017
 library+0.017
Neg logit contributions
bed-0.016
aroo-0.014
ging-0.014
ged-0.013
bly-0.013
Token to
Token ID284
Feature activation+1.45e+00

Pos logit contributions
bed+0.025
aroo+0.024
ged+0.022
ging+0.021
 luckily+0.021
Neg logit contributions
 works-0.024
clock-0.023
 ABC-0.022
bows-0.022
 library-0.021
Token hold
Token ID1745
Feature activation-1.86e+00

Pos logit contributions
clock+0.041
 works+0.041
 ABC+0.037
bows+0.037
 numbers+0.037
Neg logit contributions
bed-0.057
aroo-0.052
ging-0.050
ged-0.049
bly-0.049
Token on
Token ID319
Feature activation-8.96e-01

Pos logit contributions
bed+0.060
aroo+0.052
ged+0.051
ging+0.050
bly+0.050
Neg logit contributions
 works-0.061
 numbers-0.061
clock-0.060
 books-0.058
 looks-0.057
Token tight
Token ID5381
Feature activation-5.56e-01

Pos logit contributions
bed+0.031
aroo+0.027
ging+0.027
ged+0.027
bly+0.026
Neg logit contributions
 works-0.030
clock-0.030
bows-0.028
 ABC-0.027
 restaurants-0.027
Token to
Token ID284
Feature activation+1.13e+00

Pos logit contributions
bed+0.019
aroo+0.016
ging+0.016
ged+0.016
bly+0.015
Neg logit contributions
 works-0.019
clock-0.019
 ABC-0.018
bows-0.017
 library-0.017
Token the
Token ID262
Feature activation+8.87e-01

Pos logit contributions
 works+0.005
clock+0.005
 ABC+0.005
 numbers+0.005
bows+0.005
Neg logit contributions
bed-0.005
aroo-0.004
ged-0.004
ging-0.004
bly-0.004
Token tree
Token ID5509
Feature activation+6.29e-01

Pos logit contributions
clock+0.033
 works+0.032
 restaurants+0.031
bows+0.031
 ABC+0.031
Neg logit contributions
aroo-0.024
bed-0.023
 luckily-0.020
 swat-0.019
ging-0.018
Token was
Token ID373
Feature activation-1.16e+00

Pos logit contributions
clock+0.018
 works+0.018
 ABC+0.017
 numbers+0.016
 restaurants+0.016
Neg logit contributions
bed-0.024
aroo-0.022
ged-0.021
ging-0.021
bly-0.021
Token happy
Token ID3772
Feature activation+3.16e-01

Pos logit contributions
bed+0.042
aroo+0.038
ging+0.036
ged+0.036
bly+0.036
Neg logit contributions
 works-0.037
clock-0.037
 ABC-0.034
 numbers-0.034
bows-0.034
Token too
Token ID1165
Feature activation+2.39e+00

Pos logit contributions
 works+0.010
clock+0.010
 ABC+0.010
 numbers+0.009
bows+0.009
Neg logit contributions
bed-0.011
aroo-0.010
ged-0.010
ging-0.010
bly-0.009
Token.
Token ID13
Feature activation-5.90e-01

Pos logit contributions
clock+0.083
 works+0.082
 ABC+0.080
 restaurants+0.077
 numbers+0.077
Neg logit contributions
bed-0.078
ging-0.068
aroo-0.067
ged-0.066
bly-0.064
Token It
Token ID632
Feature activation-4.15e-01

Pos logit contributions
bed+0.019
aroo+0.014
oned+0.014
 luckily+0.014
ged+0.014
Neg logit contributions
 works-0.021
 flavors-0.020
 restaurants-0.020
clock-0.020
 ABC-0.020
Token made
Token ID925
Feature activation-3.50e-01

Pos logit contributions
bed+0.015
aroo+0.014
ged+0.013
bly+0.013
ging+0.013
Neg logit contributions
clock-0.013
 works-0.012
 ABC-0.012
 restaurants-0.012
 numbers-0.012
Token Maria
Token ID14200
Feature activation-1.34e+00

Pos logit contributions
bed+0.012
aroo+0.011
bly+0.010
ged+0.010
ging+0.010
Neg logit contributions
 works-0.011
clock-0.011
 library-0.011
 ABC-0.011
bows-0.011
Token laugh
Token ID6487
Feature activation-4.88e-01

Pos logit contributions
bed+0.049
aroo+0.043
ged+0.042
bly+0.041
ging+0.041
Neg logit contributions
clock-0.040
 works-0.039
 restaurants-0.038
 library-0.038
 numbers-0.037
Token and
Token ID290
Feature activation+7.61e-01

Pos logit contributions
bed+0.015
aroo+0.014
ging+0.013
ged+0.013
bly+0.013
Neg logit contributions
 works-0.017
clock-0.017
 numbers-0.016
bows-0.016
 ABC-0.016
Token was
Token ID373
Feature activation-1.42e+00

Pos logit contributions
clock+0.005
 works+0.005
 restaurants+0.005
bows+0.005
 ABC+0.005
Neg logit contributions
bed-0.007
aroo-0.006
ged-0.006
ging-0.006
bly-0.006
Token so
Token ID523
Feature activation+5.82e-02

Pos logit contributions
bed+0.054
aroo+0.050
ged+0.049
ging+0.049
bly+0.047
Neg logit contributions
clock-0.041
 works-0.040
 numbers-0.037
 ABC-0.036
 looks-0.036
Token excited
Token ID6568
Feature activation+8.27e-01

Pos logit contributions
 works+0.002
clock+0.002
 numbers+0.002
 smells+0.002
 ABC+0.002
Neg logit contributions
bed-0.002
aroo-0.002
ged-0.002
ging-0.002
bly-0.002
Token.
Token ID13
Feature activation-4.07e-01

Pos logit contributions
 works+0.027
clock+0.026
 ABC+0.026
 restaurants+0.024
 numbers+0.024
Neg logit contributions
bed-0.029
aroo-0.025
ged-0.025
ging-0.025
bly-0.023
Token She
Token ID1375
Feature activation+1.95e-01

Pos logit contributions
bed+0.015
ged+0.012
aroo+0.012
oned+0.012
ging+0.012
Neg logit contributions
 works-0.013
clock-0.012
 flavors-0.012
 restaurants-0.012
 ABC-0.012
Token asked
Token ID1965
Feature activation-3.88e-01

Pos logit contributions
 works+0.006
clock+0.006
 ABC+0.005
 numbers+0.005
bows+0.005
Neg logit contributions
bed-0.007
aroo-0.007
ging-0.006
ged-0.006
bly-0.006
Token the
Token ID262
Feature activation+8.09e-01

Pos logit contributions
bed+0.014
aroo+0.013
ging+0.013
ged+0.013
bly+0.012
Neg logit contributions
 works-0.012
clock-0.012
 ABC-0.011
 numbers-0.011
bows-0.011
Token fairy
Token ID25607
Feature activation-1.10e+00

Pos logit contributions
 works+0.031
clock+0.031
 ABC+0.029
 numbers+0.029
bows+0.029
Neg logit contributions
bed-0.024
aroo-0.021
ged-0.020
ging-0.020
bly-0.019
Token what
Token ID644
Feature activation+3.78e-01

Pos logit contributions
bed+0.037
aroo+0.034
ging+0.032
ged+0.032
bly+0.031
Neg logit contributions
clock-0.037
 works-0.036
 ABC-0.034
bows-0.033
 numbers-0.033
Token it
Token ID340
Feature activation+7.76e-01

Pos logit contributions
clock+0.014
 works+0.013
bows+0.012
 ABC+0.012
 restaurants+0.011
Neg logit contributions
bed-0.012
aroo-0.011
ged-0.010
ging-0.010
bly-0.010
Token was
Token ID373
Feature activation-1.19e+00

Pos logit contributions
clock+0.023
 works+0.022
 ABC+0.021
 numbers+0.021
bows+0.020
Neg logit contributions
bed-0.029
aroo-0.027
ged-0.026
ging-0.026
bly-0.025
Token.
Token ID13
Feature activation-5.33e-01

Pos logit contributions
 works+0.025
clock+0.025
 ABC+0.023
bows+0.023
 numbers+0.023
Neg logit contributions
bed-0.023
aroo-0.021
ging-0.020
ged-0.020
bly-0.019
Token He
Token ID679
Feature activation-3.95e-01

Pos logit contributions
bed+0.016
aroo+0.013
inn+0.013
oned+0.012
ged+0.011
Neg logit contributions
 works-0.018
clock-0.018
 statues-0.018
bows-0.017
 restaurants-0.017
Token had
Token ID550
Feature activation-7.77e-01

Pos logit contributions
bed+0.017
aroo+0.016
ged+0.015
ging+0.015
bly+0.015
Neg logit contributions
clock-0.010
 works-0.009
bows-0.009
 ABC-0.009
 numbers-0.008
Token a
Token ID257
Feature activation-8.99e-01

Pos logit contributions
bed+0.023
aroo+0.018
ged+0.018
 under+0.017
bly+0.017
Neg logit contributions
 works-0.028
bows-0.027
clock-0.025
 ABC-0.025
aris-0.024
Token small
Token ID1402
Feature activation-1.73e+00

Pos logit contributions
bed+0.039
aroo+0.036
ging+0.035
ged+0.035
bly+0.034
Neg logit contributions
clock-0.021
 works-0.021
bows-0.019
 ABC-0.018
 numbers-0.018
Token toy
Token ID13373
Feature activation-4.25e+00

Pos logit contributions
bed+0.063
aroo+0.056
ging+0.054
ged+0.053
bly+0.051
Neg logit contributions
clock-0.053
 works-0.052
bows-0.049
 ABC-0.048
 numbers-0.047
Token grill
Token ID29901
Feature activation-8.78e-01

Pos logit contributions
bed+0.158
ging+0.146
ged+0.144
aroo+0.143
bly+0.141
Neg logit contributions
clock-0.125
 works-0.124
 numbers-0.117
 library-0.115
 ABC-0.115
Token that
Token ID326
Feature activation-1.21e+00

Pos logit contributions
bed+0.025
aroo+0.022
ging+0.021
ged+0.021
bly+0.020
Neg logit contributions
 works-0.034
clock-0.034
 ABC-0.032
 numbers-0.032
bows-0.032
Token he
Token ID339
Feature activation-1.30e+00

Pos logit contributions
bed+0.034
aroo+0.031
bly+0.026
ged+0.026
 luckily+0.026
Neg logit contributions
clock-0.045
bows-0.043
 ABC-0.042
 tours-0.042
aris-0.041
Token played
Token ID2826
Feature activation-1.02e+00

Pos logit contributions
bed+0.050
aroo+0.045
ged+0.044
ging+0.043
bly+0.043
Neg logit contributions
clock-0.037
 works-0.037
bows-0.034
 ABC-0.034
 numbers-0.034
Token with
Token ID351
Feature activation-2.09e+00

Pos logit contributions
bed+0.029
aroo+0.028
ged+0.027
ging+0.027
bly+0.025
Neg logit contributions
 works-0.037
 numbers-0.036
clock-0.036
 books-0.036
 ABC-0.035
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
 works+0.026
clock+0.026
 numbers+0.025
 smells+0.024
bows+0.024
Neg logit contributions
bed-0.035
aroo-0.033
ging-0.031
ged-0.031
bly-0.031
Token Suddenly
Token ID24975
Feature activation-1.29e+00

Pos logit contributions
bed+0.004
aroo+0.004
ged+0.004
ging+0.004
bly+0.004
Neg logit contributions
 works-0.004
clock-0.004
 ABC-0.004
 numbers-0.004
bows-0.004
Token,
Token ID11
Feature activation+1.74e-01

Pos logit contributions
bed+0.043
aroo+0.039
ged+0.038
ging+0.037
bly+0.035
Neg logit contributions
clock-0.045
 works-0.044
 ABC-0.041
bows-0.041
 flavors-0.041
Token the
Token ID262
Feature activation+1.05e+00

Pos logit contributions
clock+0.005
 works+0.005
 ABC+0.005
bows+0.005
 numbers+0.005
Neg logit contributions
bed-0.007
aroo-0.006
ged-0.006
ging-0.006
bly-0.006
Token k
Token ID479
Feature activation-2.10e+00

Pos logit contributions
 works+0.036
clock+0.036
 ABC+0.033
bows+0.033
 restaurants+0.033
Neg logit contributions
bed-0.034
aroo-0.032
ging-0.030
ged-0.029
bly-0.029
Tokenang
Token ID648
Feature activation-3.98e+00

Pos logit contributions
bed+0.041
oned+0.032
ged+0.031
rily+0.030
bled+0.030
Neg logit contributions
clock-0.089
 works-0.088
bows-0.087
 library-0.086
 numbers-0.086
Tokenaroo
Token ID38049
Feature activation-2.69e+00

Pos logit contributions
bed+0.060
bly+0.041
oned+0.040
 afloat+0.039
ging+0.038
Neg logit contributions
 works-0.177
 looks-0.177
 numbers-0.175
 ABC-0.170
 total-0.168
Token heard
Token ID2982
Feature activation+8.46e-01

Pos logit contributions
bed+0.109
aroo+0.102
ging+0.100
bly+0.100
ged+0.098
Neg logit contributions
clock-0.069
 works-0.069
 numbers-0.063
 ABC-0.061
 looks-0.061
Token a
Token ID257
Feature activation-6.52e-01

Pos logit contributions
 works+0.026
clock+0.026
bows+0.024
 ABC+0.024
 flavors+0.023
Neg logit contributions
bed-0.031
aroo-0.028
ged-0.027
ging-0.027
bly-0.026
Token voice
Token ID3809
Feature activation-5.10e-01

Pos logit contributions
bed+0.025
aroo+0.024
ging+0.023
ged+0.022
bly+0.022
Neg logit contributions
clock-0.018
 works-0.018
bows-0.017
 restaurants-0.016
 ABC-0.016
Token.
Token ID13
Feature activation-7.63e-01

Pos logit contributions
bed+0.022
bled+0.020
bly+0.020
aroo+0.019
ging+0.018
Neg logit contributions
 works-0.013
clock-0.012
 looks-0.012
 look-0.012
 smells-0.012
Token and
Token ID290
Feature activation-1.77e-01

Pos logit contributions
 works+0.003
clock+0.003
 total+0.003
 ABC+0.003
 library+0.003
Neg logit contributions
bed-0.002
ged-0.002
ling-0.002
ging-0.002
aroo-0.002
Token accidentally
Token ID14716
Feature activation-2.42e+00

Pos logit contributions
bed+0.006
aroo+0.005
ged+0.005
ging+0.005
bly+0.005
Neg logit contributions
clock-0.006
 works-0.006
 ABC-0.006
bows-0.006
 numbers-0.006
Token got
Token ID1392
Feature activation+2.57e-02

Pos logit contributions
bed+0.081
aroo+0.073
ging+0.071
ged+0.070
bly+0.069
Neg logit contributions
 works-0.081
clock-0.081
 numbers-0.075
 ABC-0.075
bows-0.074
Token the
Token ID262
Feature activation-1.26e+00

Pos logit contributions
clock+0.001
 works+0.001
bows+0.001
 ABC+0.001
 library+0.001
Neg logit contributions
bed-0.001
aroo-0.001
ged-0.001
ging-0.001
bly-0.001
Token tape
Token ID9154
Feature activation-2.56e+00

Pos logit contributions
bed+0.055
aroo+0.051
ged+0.050
ging+0.050
bly+0.049
Neg logit contributions
 works-0.030
clock-0.029
 numbers-0.027
 ABC-0.026
bows-0.026
Token stuck
Token ID7819
Feature activation-4.24e+00

Pos logit contributions
bed+0.086
aroo+0.080
bly+0.075
ged+0.075
ging+0.074
Neg logit contributions
 works-0.083
clock-0.081
 numbers-0.078
bows-0.076
 looks-0.075
Token all
Token ID477
Feature activation+2.35e-02

Pos logit contributions
bed+0.130
aroo+0.126
bly+0.117
ging+0.116
ged+0.113
Neg logit contributions
clock-0.141
 works-0.141
 numbers-0.136
bows-0.129
 books-0.129
Token over
Token ID625
Feature activation-1.06e+00

Pos logit contributions
 works+0.001
clock+0.001
 numbers+0.001
 looks+0.001
bows+0.001
Neg logit contributions
bed-0.001
aroo-0.001
ging-0.001
ged-0.001
bly-0.001
Token his
Token ID465
Feature activation-1.37e+00

Pos logit contributions
bed+0.043
aroo+0.041
bly+0.039
ging+0.039
ged+0.038
Neg logit contributions
 works-0.026
clock-0.026
 numbers-0.026
 restaurants-0.024
 flavors-0.024
Token fur
Token ID9230
Feature activation-2.13e+00

Pos logit contributions
bed+0.046
aroo+0.043
ged+0.042
ging+0.042
bly+0.041
Neg logit contributions
clock-0.046
 works-0.045
 numbers-0.043
 ABC-0.043
 library-0.042
Token.
Token ID13
Feature activation-9.70e-01

Pos logit contributions
bed+0.080
aroo+0.074
ging+0.072
ged+0.072
bly+0.071
Neg logit contributions
clock-0.061
 works-0.060
 numbers-0.057
bows-0.056
 ABC-0.055
Token The
Token ID383
Feature activation+5.60e-01

Pos logit contributions
bed+0.021
aroo+0.019
ged+0.016
oned+0.015
ging+0.014
Neg logit contributions
 works-0.032
clock-0.031
bows-0.031
 ABC-0.030
 flavors-0.030
Token mouse
Token ID10211
Feature activation-2.10e+00

Pos logit contributions
clock+0.019
 works+0.019
bows+0.018
 ABC+0.018
 numbers+0.018
Neg logit contributions
bed-0.019
aroo-0.017
ging-0.016
ged-0.016
bly-0.016
Token had
Token ID550
Feature activation-9.68e-01

Pos logit contributions
bed+0.086
aroo+0.079
ging+0.079
ged+0.078
bly+0.077
Neg logit contributions
 works-0.055
clock-0.053
 numbers-0.049
 ABC-0.048
 looks-0.048
Token a
Token ID257
Feature activation-9.92e-01

Pos logit contributions
bed+0.030
aroo+0.026
ged+0.025
bly+0.023
pered+0.023
Neg logit contributions
 works-0.033
bows-0.033
clock-0.033
 restaurants-0.032
 ABC-0.031
Token nut
Token ID6701
Feature activation-3.38e+00

Pos logit contributions
bed+0.040
aroo+0.037
ging+0.035
ged+0.035
bly+0.034
Neg logit contributions
clock-0.026
 works-0.025
bows-0.024
 restaurants-0.023
 ABC-0.023
Token stuck
Token ID7819
Feature activation-4.58e+00

Pos logit contributions
bed+0.105
bly+0.095
aroo+0.095
ging+0.093
ged+0.092
Neg logit contributions
 works-0.119
clock-0.112
 looks-0.111
 numbers-0.111
 books-0.110
Token in
Token ID287
Feature activation-1.56e+00

Pos logit contributions
bed+0.119
aroo+0.111
bly+0.106
ging+0.105
ged+0.100
Neg logit contributions
 works-0.176
clock-0.172
 numbers-0.170
 books-0.164
 looks-0.162
Token its
Token ID663
Feature activation-1.01e+00

Pos logit contributions
bed+0.058
aroo+0.052
ging+0.050
ged+0.050
bly+0.049
Neg logit contributions
clock-0.048
 works-0.048
bows-0.045
 ABC-0.044
 library-0.043
Token mouth
Token ID5422
Feature activation-4.67e-01

Pos logit contributions
bed+0.033
aroo+0.029
ged+0.027
ging+0.027
bly+0.026
Neg logit contributions
 works-0.036
clock-0.035
bows-0.033
 ABC-0.033
 numbers-0.033
Token.
Token ID13
Feature activation-9.66e-01

Pos logit contributions
bed+0.016
aroo+0.014
ging+0.014
ged+0.014
bly+0.013
Neg logit contributions
 works-0.016
clock-0.015
 ABC-0.014
 numbers-0.014
bows-0.014
Token
Token ID198
Feature activation-1.41e+00

Pos logit contributions
bed+0.031
aroo+0.028
ged+0.026
ging+0.025
bly+0.024
Neg logit contributions
 works-0.034
clock-0.034
bows-0.032
 ABC-0.032
 numbers-0.031
Token!"
Token ID2474
Feature activation+3.02e-01

Pos logit contributions
bed+0.024
aroo+0.022
ging+0.021
ged+0.020
bly+0.020
Neg logit contributions
clock-0.021
 works-0.020
 ABC-0.020
 numbers-0.019
 statues-0.019
Token Mitt
Token ID16627
Feature activation+3.61e-01

Pos logit contributions
clock+0.010
 works+0.009
 numbers+0.009
bows+0.009
 ABC+0.009
Neg logit contributions
bed-0.010
aroo-0.010
ging-0.010
bly-0.009
ged-0.009
Tokenens
Token ID641
Feature activation-4.19e-01

Pos logit contributions
 works+0.011
clock+0.011
bows+0.010
 numbers+0.010
 ABC+0.010
Neg logit contributions
bed-0.013
aroo-0.012
ging-0.012
ged-0.012
bly-0.011
Token chased
Token ID26172
Feature activation-1.68e+00

Pos logit contributions
bed+0.016
aroo+0.014
ged+0.013
ging+0.013
bly+0.013
Neg logit contributions
clock-0.013
 works-0.013
 ABC-0.012
bows-0.012
 numbers-0.012
Token the
Token ID262
Feature activation+1.80e-01

Pos logit contributions
bly+0.066
bed+0.065
bled+0.063
aroo+0.062
rily+0.057
Neg logit contributions
 books-0.041
 numbers-0.038
 jobs-0.036
clock-0.036
 names-0.036
Token fle
Token ID5104
Feature activation-4.04e+00

Pos logit contributions
 works+0.005
clock+0.005
 numbers+0.005
 ABC+0.005
 library+0.005
Neg logit contributions
bed-0.007
ged-0.007
ging-0.006
aroo-0.006
bly-0.006
Tokena
Token ID64
Feature activation-2.20e+00

Pos logit contributions
bed+0.166
ging+0.157
ged+0.153
 luckily+0.152
bing+0.152
Neg logit contributions
bows-0.074
clock-0.071
 names-0.071
 works-0.068
aris-0.066
Token and
Token ID290
Feature activation-2.32e-01

Pos logit contributions
bed+0.076
bly+0.074
aroo+0.072
bled+0.069
ging+0.069
Neg logit contributions
 works-0.065
clock-0.063
 looks-0.063
 books-0.062
 numbers-0.061
Token caught
Token ID4978
Feature activation-6.68e-01

Pos logit contributions
bed+0.008
bly+0.008
aroo+0.008
ging+0.008
oned+0.007
Neg logit contributions
 works-0.007
clock-0.006
 looks-0.006
 books-0.006
 smells-0.006
Token it
Token ID340
Feature activation-2.42e-01

Pos logit contributions
bed+0.024
aroo+0.023
bly+0.022
oned+0.022
ged+0.022
Neg logit contributions
 numbers-0.017
 works-0.017
 books-0.016
 smells-0.016
 names-0.016
Token with
Token ID351
Feature activation-1.19e+00

Pos logit contributions
aroo+0.008
bed+0.008
ging+0.008
ged+0.008
bly+0.008
Neg logit contributions
 works-0.007
clock-0.007
 looks-0.007
 numbers-0.007
 smells-0.007