TOP ACTIVATIONS
MAX = 6.058

wealthy . This made the other rock er angry . He
than the others . The other ducks didn 't mind ,
starting to rot . The other side was beautiful and creative
all the sights ! The other passengers were happy to see
was all alone because the other cars were far away .
, so it made the other cat even more mad .
chase the chickens . The other chickens were scared and did
taller than before . The other trees in the forest were
was fun to make the other kids afraid or mad .
you very sick . The other mushrooms were not dangerous .
train was red and the other train was blue . They
't find her . The other sheep were sad because their
place all day . The other cube was much more adventurous
looked very useful . The other agreed and said it was
we stay here ?" The other cat said , " Maybe
was very wealthy . The other team had hardly anything .
felt en vious because the other dogs had fun toys to
car was red and the other car was blue . They
the apples easily . The other friend was short and couldn
the other clouds . The other clouds were en vious of

MIN ACTIVATIONS
MIN = -8.938

a strange , raspberry - col oured object hiding under a
get something sweet or something sav our y ? In the
big , beautiful rainbow - col oured butterfly ! The little
date , a rainbow - col oured butterfly flew in through
day , a chocolate - col oured whip named C heddar
suddenly , a brightly - col oured belt caught her eye
went outside to find something su gary . But what he
ipop , it 's a sav our y l oll ipop
- a box of mult icol ored bubbles !
delicious vegetables and bright - col oured flowers .
things â col ouring books , stickers and
was known as the powerful sav iour of the forest .
and saw a magical fair yt ale creature called a n
for him - a little su gary treat . <|endoftext|> Once
the paper became a 3 D cube ! The
with her friends in the sav anna . They are all
, with all its different col ours , shapes and textures
children running around , families pic n icking , couples st
was walking through a fair yt ale . She fell asleep
found it was all strawberry flav oured , his favourite .

INTERVAL 2.309 - 6.058
CONTAINS 1.700%

took the bike out and tried to pedal . But the
's feathers . He realized that sometimes it takes only a
do . He was so bored that he decided to go
gone . He was so sad and looked everywhere for his
" Wow , Lily ! Your sand castle is so beautiful

INTERVAL -1.440 - 2.309
CONTAINS 88.216%

to roll . So it rolled and rolled and
picture to grandma !" Ben shouts . " Hello
baby . The baby 's name was Mary . Mary loved
their room . They are proud . They say , "
the room . He said , " It doesn 't matter

INTERVAL -5.189 - -1.440
CONTAINS 10.068%

more ," and he located a nearby pond to soak in
showed him how to move the pieces and they started playing
brave dinosaur bell owed in surprise . " How can I
happy , too . <|endoftext|> L ily liked to help her
sing her most beautiful and upl ifting song . Slowly ,

INTERVAL -8.938 - -5.189
CONTAINS 0.016%

they built the biggest tower they had ever made . They
park and look for something y ummy to eat .
of all the tiny things she would see with her microscope
Annie said it was called ˜ Pretty Flowers
and appreciate them for what they are . She said that
Token wealthy
Token ID11574
Feature activation+7.59e-01

Pos logit contributions
 owner+0.002
tr+0.001
flower+0.001
 hits+0.001
 hurts+0.001
Neg logit contributions
ocol-0.003
irs-0.002
sie-0.002
ait-0.002
andel-0.002
Token.
Token ID13
Feature activation+8.36e-01

Pos logit contributions
 owner+0.013
 not+0.012
 still+0.011
 was+0.011
 only+0.010
Neg logit contributions
ocol-0.034
irs-0.030
ait-0.027
andel-0.027
sie-0.026
Token This
Token ID770
Feature activation+2.29e+00

Pos logit contributions
 owner+0.012
 not+0.011
 still+0.010
 hurts+0.010
 hits+0.009
Neg logit contributions
ocol-0.039
irs-0.033
ait-0.031
andel-0.030
sie-0.030
Token made
Token ID925
Feature activation+8.88e-01

Pos logit contributions
 Fighting+0.057
 neither+0.056
tr+0.054
flower+0.054
gy+0.053
Neg logit contributions
ocol-0.064
 seas-0.052
sie-0.048
 ages-0.046
andel-0.045
Token the
Token ID262
Feature activation+2.12e+00

Pos logit contributions
 owner+0.022
 not+0.021
 still+0.020
 was+0.019
 hurts+0.019
Neg logit contributions
ocol-0.032
irs-0.026
ait-0.024
andel-0.023
sie-0.023
Token other
Token ID584
Feature activation+6.06e+00

Pos logit contributions
tr+0.042
zag+0.041
 not+0.041
 hurts+0.040
 owner+0.039
Neg logit contributions
ocol-0.076
irs-0.057
andel-0.056
sie-0.055
 ages-0.053
Token rock
Token ID3881
Feature activation+2.64e+00

Pos logit contributions
 not+0.112
 owner+0.108
tr+0.104
zag+0.104
 hurts+0.102
Neg logit contributions
ocol-0.239
irs-0.189
andel-0.180
ait-0.178
sie-0.175
Tokener
Token ID263
Feature activation+2.51e+00

Pos logit contributions
 owner+0.052
 not+0.045
 hurts+0.045
 hits+0.045
 still+0.044
Neg logit contributions
ocol-0.102
irs-0.087
ait-0.078
andel-0.077
sie-0.076
Token angry
Token ID7954
Feature activation+2.22e+00

Pos logit contributions
 owner+0.043
 hits+0.038
 hurts+0.038
 not+0.036
 remembered+0.036
Neg logit contributions
ocol-0.102
irs-0.087
ait-0.079
andel-0.077
sie-0.076
Token.
Token ID13
Feature activation+8.07e-01

Pos logit contributions
 owner+0.033
 not+0.029
 still+0.028
zag+0.028
flower+0.028
Neg logit contributions
ocol-0.096
irs-0.082
ait-0.075
andel-0.074
sie-0.073
Token He
Token ID679
Feature activation+3.14e-02

Pos logit contributions
 owner+0.011
 not+0.010
 still+0.010
 hurts+0.009
 hits+0.009
Neg logit contributions
ocol-0.037
irs-0.032
ait-0.030
andel-0.029
sie-0.029
Token than
Token ID621
Feature activation-1.12e+00

Pos logit contributions
 owner+0.034
 not+0.031
 hurts+0.030
 remembered+0.030
 still+0.029
Neg logit contributions
ocol-0.095
irs-0.080
ait-0.074
andel-0.074
sie-0.071
Token the
Token ID262
Feature activation+7.27e-01

Pos logit contributions
ocol+0.047
irs+0.040
ait+0.037
andel+0.037
prise+0.035
Neg logit contributions
 not-0.021
 owner-0.020
 still-0.020
 only-0.019
 was-0.018
Token others
Token ID1854
Feature activation+2.02e+00

Pos logit contributions
 owner+0.014
 not+0.013
 hurts+0.013
zag+0.013
 hits+0.013
Neg logit contributions
ocol-0.029
irs-0.023
ait-0.022
andel-0.021
sie-0.021
Token.
Token ID13
Feature activation+8.35e-01

Pos logit contributions
 owner+0.036
 not+0.034
 still+0.032
 hurts+0.031
 was+0.030
Neg logit contributions
ocol-0.086
irs-0.074
ait-0.067
andel-0.066
sie-0.065
Token The
Token ID383
Feature activation+2.84e+00

Pos logit contributions
 owner+0.012
 not+0.010
 still+0.010
 was+0.009
 hurts+0.009
Neg logit contributions
ocol-0.040
irs-0.034
ait-0.032
andel-0.031
sie-0.031
Token other
Token ID584
Feature activation+5.71e+00

Pos logit contributions
zag+0.065
 hurts+0.063
tr+0.063
 owner+0.061
 not+0.061
Neg logit contributions
ocol-0.097
irs-0.073
andel-0.071
sie-0.069
ait-0.069
Token ducks
Token ID39694
Feature activation+2.34e+00

Pos logit contributions
zag+0.150
 hurts+0.149
tr+0.147
 not+0.141
 hits+0.140
Neg logit contributions
ocol-0.167
ait-0.119
sie-0.115
andel-0.115
irs-0.113
Token didn
Token ID1422
Feature activation-6.96e-01

Pos logit contributions
 owner+0.044
tr+0.042
 hurts+0.041
 hits+0.040
zag+0.039
Neg logit contributions
ocol-0.087
irs-0.074
sie-0.071
ait-0.067
year-0.066
Token't
Token ID470
Feature activation+1.55e+00

Pos logit contributions
ocol+0.026
irs+0.024
andel+0.020
ait+0.020
 Annie+0.019
Neg logit contributions
 owner-0.014
 remembered-0.014
flower-0.013
 hurts-0.012
 hates-0.012
Token mind
Token ID2000
Feature activation+1.97e+00

Pos logit contributions
 owner+0.026
 not+0.025
 still+0.023
 also+0.021
 hurts+0.021
Neg logit contributions
ocol-0.069
irs-0.060
ait-0.055
andel-0.053
sie-0.052
Token,
Token ID11
Feature activation+8.39e-01

Pos logit contributions
 owner+0.032
 not+0.031
 still+0.029
 hurts+0.027
 was+0.027
Neg logit contributions
ocol-0.087
irs-0.075
ait-0.069
andel-0.067
sie-0.066
Token starting
Token ID3599
Feature activation+3.81e+00

Pos logit contributions
ocol+0.049
irs+0.041
ait+0.037
andel+0.036
sie+0.036
Neg logit contributions
 owner-0.025
 not-0.023
 still-0.022
 hurts-0.022
zag-0.022
Token to
Token ID284
Feature activation-1.99e-01

Pos logit contributions
 owner+0.053
 not+0.053
 still+0.044
 was+0.041
 also+0.039
Neg logit contributions
ocol-0.187
irs-0.160
ait-0.149
andel-0.148
sie-0.147
Token rot
Token ID5724
Feature activation+1.47e+00

Pos logit contributions
ocol+0.009
irs+0.007
ait+0.007
andel+0.007
sie+0.006
Neg logit contributions
 owner-0.004
 not-0.004
 still-0.003
 also-0.003
 hurts-0.003
Token.
Token ID13
Feature activation+4.52e-01

Pos logit contributions
 owner+0.021
 still+0.020
 not+0.020
 was+0.019
 only+0.018
Neg logit contributions
ocol-0.070
irs-0.062
ait-0.057
andel-0.056
prise-0.055
Token The
Token ID383
Feature activation+2.51e+00

Pos logit contributions
 owner+0.005
 not+0.005
 was+0.004
 still+0.004
 only+0.004
Neg logit contributions
ocol-0.023
irs-0.020
ait-0.019
sie-0.019
andel-0.019
Token other
Token ID584
Feature activation+5.50e+00

Pos logit contributions
 owner+0.053
 not+0.047
 still+0.046
 only+0.042
 hurts+0.042
Neg logit contributions
ocol-0.106
irs-0.093
ait-0.082
sie-0.080
andel-0.080
Token side
Token ID1735
Feature activation+3.82e+00

Pos logit contributions
 owner+0.122
 not+0.113
 still+0.110
 hurts+0.106
 was+0.104
Neg logit contributions
ocol-0.215
irs-0.181
ait-0.162
andel-0.158
sie-0.156
Token was
Token ID373
Feature activation+1.19e+00

Pos logit contributions
 owner+0.050
 not+0.047
 hurts+0.045
zag+0.044
 still+0.042
Neg logit contributions
ocol-0.162
irs-0.135
ait-0.132
sie-0.125
year-0.124
Token beautiful
Token ID4950
Feature activation+4.24e-01

Pos logit contributions
 owner+0.022
 hurts+0.021
 hits+0.021
flower+0.020
Because+0.020
Neg logit contributions
ocol-0.045
irs-0.036
ait-0.034
andel-0.033
 rubble-0.033
Token and
Token ID290
Feature activation-5.80e-01

Pos logit contributions
 owner+0.006
 not+0.006
 hurts+0.005
 still+0.005
 hits+0.005
Neg logit contributions
ocol-0.019
irs-0.016
ait-0.015
andel-0.015
sie-0.015
Token creative
Token ID7325
Feature activation+8.22e-01

Pos logit contributions
ocol+0.023
irs+0.019
ait+0.017
andel+0.017
sie+0.017
Neg logit contributions
 owner-0.012
 not-0.011
zag-0.010
 hurts-0.010
 still-0.010
Token all
Token ID477
Feature activation+3.20e-01

Pos logit contributions
 owner+0.014
 not+0.013
 still+0.013
 was+0.012
 also+0.012
Neg logit contributions
ocol-0.033
irs-0.028
ait-0.026
andel-0.025
sie-0.025
Token the
Token ID262
Feature activation-7.57e-01

Pos logit contributions
 owner+0.006
 not+0.005
 still+0.005
 was+0.005
 hits+0.005
Neg logit contributions
ocol-0.014
irs-0.012
ait-0.011
andel-0.011
sie-0.011
Token sights
Token ID21343
Feature activation-1.16e+00

Pos logit contributions
ocol+0.035
irs+0.030
sie+0.028
year+0.027
andel+0.027
Neg logit contributions
 owner-0.014
 still-0.012
 only-0.012
 not-0.012
 best-0.012
Token!
Token ID0
Feature activation-4.05e-01

Pos logit contributions
ocol+0.053
irs+0.045
ait+0.042
andel+0.041
sie+0.041
Neg logit contributions
 owner-0.018
 not-0.017
 still-0.017
 was-0.016
 hits-0.015
Token The
Token ID383
Feature activation+2.06e+00

Pos logit contributions
ocol+0.020
irs+0.017
ait+0.016
andel+0.016
sie+0.016
Neg logit contributions
 owner-0.005
 not-0.004
 still-0.004
 hurts-0.004
 was-0.004
Token other
Token ID584
Feature activation+5.46e+00

Pos logit contributions
 owner+0.033
 not+0.029
 still+0.028
 was+0.026
 hits+0.026
Neg logit contributions
ocol-0.095
irs-0.083
ait-0.076
andel-0.074
sie-0.073
Token passengers
Token ID10405
Feature activation+1.60e+00

Pos logit contributions
 not+0.122
 hurts+0.121
 owner+0.118
 still+0.116
 hits+0.115
Neg logit contributions
ocol-0.193
irs-0.156
ait-0.144
andel-0.140
 ages-0.137
Token were
Token ID547
Feature activation+9.92e-02

Pos logit contributions
 owner+0.030
 hurts+0.028
 not+0.028
 hits+0.026
tr+0.025
Neg logit contributions
ocol-0.062
irs-0.053
ait-0.050
sie-0.048
year-0.047
Token happy
Token ID3772
Feature activation-2.49e-02

Pos logit contributions
 hurts+0.003
tr+0.002
 hits+0.002
 owner+0.002
 hates+0.002
Neg logit contributions
ocol-0.003
irs-0.002
ait-0.002
 Annie-0.002
 ages-0.002
Token to
Token ID284
Feature activation-5.17e-01

Pos logit contributions
ocol+0.001
irs+0.001
ait+0.001
 Annie+0.001
andel+0.001
Neg logit contributions
 owner-0.000
 hurts-0.000
tr-0.000
 hits-0.000
zag-0.000
Token see
Token ID766
Feature activation-2.68e-01

Pos logit contributions
ocol+0.018
irs+0.015
ait+0.013
andel+0.012
 ages+0.012
Neg logit contributions
 owner-0.012
 hurts-0.012
tr-0.012
 hates-0.011
flower-0.011
Token was
Token ID373
Feature activation+1.64e+00

Pos logit contributions
burn+0.017
uck+0.017
flower+0.017
 owner+0.017
zag+0.016
Neg logit contributions
ocol-0.036
 rubble-0.031
 Annie-0.031
 ages-0.030
sie-0.030
Token all
Token ID477
Feature activation+6.06e-01

Pos logit contributions
 owner+0.030
flower+0.029
 hurts+0.029
zag+0.029
Because+0.028
Neg logit contributions
ocol-0.064
irs-0.053
ait-0.049
andel-0.048
 ages-0.046
Token alone
Token ID3436
Feature activation+2.53e+00

Pos logit contributions
 owner+0.012
 not+0.012
 still+0.011
 hurts+0.011
 hits+0.011
Neg logit contributions
ocol-0.024
irs-0.020
ait-0.019
andel-0.018
sie-0.018
Token because
Token ID780
Feature activation+5.99e-01

Pos logit contributions
 owner+0.044
 not+0.041
 still+0.039
 hurts+0.038
 hits+0.037
Neg logit contributions
ocol-0.108
irs-0.092
ait-0.085
andel-0.083
sie-0.081
Token the
Token ID262
Feature activation+1.82e+00

Pos logit contributions
 owner+0.013
 not+0.012
 still+0.012
 hurts+0.012
 hits+0.012
Neg logit contributions
ocol-0.023
irs-0.019
ait-0.017
andel-0.017
sie-0.017
Token other
Token ID584
Feature activation+5.43e+00

Pos logit contributions
 owner+0.039
 not+0.036
 still+0.034
 hurts+0.032
 was+0.032
Neg logit contributions
ocol-0.075
irs-0.064
ait-0.058
andel-0.056
sie-0.055
Token cars
Token ID5006
Feature activation+3.13e+00

Pos logit contributions
 owner+0.116
 not+0.114
 hurts+0.113
zag+0.111
 still+0.110
Neg logit contributions
ocol-0.198
irs-0.165
ait-0.151
andel-0.145
sie-0.141
Token were
Token ID547
Feature activation+3.21e-01

Pos logit contributions
 owner+0.057
zag+0.051
flower+0.050
 hurts+0.050
 not+0.050
Neg logit contributions
ocol-0.117
irs-0.101
ait-0.093
sie-0.090
 rubble-0.090
Token far
Token ID1290
Feature activation-7.32e-01

Pos logit contributions
 owner+0.005
 hurts+0.005
 not+0.005
zag+0.005
 hits+0.005
Neg logit contributions
ocol-0.013
irs-0.011
ait-0.011
andel-0.010
sie-0.010
Token away
Token ID1497
Feature activation+3.60e-01

Pos logit contributions
ocol+0.031
irs+0.027
ait+0.024
andel+0.024
sie+0.023
Neg logit contributions
 owner-0.014
 not-0.013
 still-0.013
 hurts-0.012
 hits-0.012
Token.
Token ID13
Feature activation+1.67e+00

Pos logit contributions
 owner+0.007
 not+0.006
 still+0.006
 hurts+0.006
 was+0.005
Neg logit contributions
ocol-0.015
irs-0.013
ait-0.012
andel-0.012
sie-0.011
Token,
Token ID11
Feature activation+3.90e-01

Pos logit contributions
 owner+0.032
 hurts+0.029
 not+0.028
 hits+0.028
 still+0.028
Neg logit contributions
ocol-0.086
irs-0.073
ait-0.067
andel-0.066
sie-0.065
Token so
Token ID523
Feature activation+2.07e+00

Pos logit contributions
 owner+0.008
 not+0.007
 still+0.007
 hurts+0.007
 hits+0.007
Neg logit contributions
ocol-0.016
irs-0.013
ait-0.012
andel-0.012
sie-0.012
Token it
Token ID340
Feature activation+6.04e-01

Pos logit contributions
 owner+0.043
zag+0.040
 hurts+0.040
tr+0.039
flower+0.039
Neg logit contributions
ocol-0.078
irs-0.065
ait-0.058
sie-0.057
andel-0.057
Token made
Token ID925
Feature activation+1.11e-01

Pos logit contributions
 owner+0.009
zag+0.008
flower+0.008
 hurts+0.008
 not+0.008
Neg logit contributions
ocol-0.024
sie-0.020
irs-0.020
ait-0.019
year-0.018
Token the
Token ID262
Feature activation+2.15e+00

Pos logit contributions
 owner+0.002
 not+0.002
 still+0.002
 was+0.002
 only+0.002
Neg logit contributions
ocol-0.005
irs-0.004
ait-0.004
sie-0.004
andel-0.004
Token other
Token ID584
Feature activation+5.42e+00

Pos logit contributions
 not+0.034
 owner+0.033
Because+0.033
zag+0.032
 still+0.032
Neg logit contributions
ocol-0.084
irs-0.069
andel-0.067
ait-0.066
sie-0.064
Token cat
Token ID3797
Feature activation+1.41e+00

Pos logit contributions
 not+0.083
 still+0.079
 owner+0.078
zag+0.074
 hits+0.074
Neg logit contributions
ocol-0.223
irs-0.184
ait-0.180
andel-0.179
sie-0.167
Token even
Token ID772
Feature activation-3.80e-02

Pos logit contributions
 owner+0.024
 not+0.022
 still+0.021
 hurts+0.021
 hits+0.021
Neg logit contributions
ocol-0.059
irs-0.051
ait-0.046
andel-0.045
sie-0.045
Token more
Token ID517
Feature activation+1.30e+00

Pos logit contributions
ocol+0.001
irs+0.001
sie+0.001
ait+0.001
andel+0.001
Neg logit contributions
 owner-0.001
zag-0.001
flower-0.001
 not-0.001
 still-0.001
Token mad
Token ID8805
Feature activation+1.36e+00

Pos logit contributions
 owner+0.026
 not+0.025
 still+0.024
 hurts+0.023
 was+0.022
Neg logit contributions
ocol-0.053
irs-0.046
ait-0.042
andel-0.040
sie-0.040
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
 owner+0.029
 not+0.027
 still+0.026
zag+0.026
 hurts+0.026
Neg logit contributions
ocol-0.051
irs-0.042
ait-0.038
andel-0.038
sie-0.036
Token chase
Token ID15505
Feature activation+2.21e-01

Pos logit contributions
 owner+0.015
 not+0.014
 still+0.013
 hurts+0.013
 hits+0.012
Neg logit contributions
ocol-0.041
irs-0.035
ait-0.033
andel-0.032
sie-0.031
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
 owner+0.004
 not+0.004
 hurts+0.004
 was+0.004
 hits+0.003
Neg logit contributions
ocol-0.010
irs-0.008
ait-0.008
inations-0.008
prise-0.008
Token chickens
Token ID25972
Feature activation+1.22e+00

Pos logit contributions
 owner+0.017
 not+0.015
 still+0.014
 hurts+0.014
 hits+0.013
Neg logit contributions
ocol-0.060
irs-0.053
ait-0.048
andel-0.047
sie-0.047
Token.
Token ID13
Feature activation+8.12e-01

Pos logit contributions
 owner+0.021
 not+0.020
 still+0.019
 hurts+0.018
 also+0.017
Neg logit contributions
ocol-0.054
irs-0.046
ait-0.042
andel-0.041
sie-0.040
Token The
Token ID383
Feature activation+2.59e+00

Pos logit contributions
 owner+0.010
 not+0.009
 still+0.009
 hurts+0.008
 was+0.008
Neg logit contributions
ocol-0.040
irs-0.035
ait-0.032
andel-0.031
sie-0.031
Token other
Token ID584
Feature activation+5.39e+00

Pos logit contributions
zag+0.039
flower+0.036
 not+0.035
tr+0.035
 hurts+0.035
Neg logit contributions
ocol-0.105
irs-0.086
ait-0.085
andel-0.084
sie-0.081
Token chickens
Token ID25972
Feature activation+1.83e+00

Pos logit contributions
zag+0.119
 not+0.115
 hits+0.114
 hurts+0.114
tr+0.111
Neg logit contributions
ocol-0.177
ait-0.147
irs-0.138
andel-0.135
sie-0.128
Token were
Token ID547
Feature activation+1.06e+00

Pos logit contributions
 owner+0.031
tr+0.029
 hurts+0.029
 hits+0.028
zag+0.027
Neg logit contributions
ocol-0.073
irs-0.063
sie-0.059
ait-0.058
andel-0.055
Token scared
Token ID12008
Feature activation+1.75e+00

Pos logit contributions
flower+0.018
tr+0.018
 hurts+0.018
Because+0.018
zag+0.018
Neg logit contributions
ocol-0.041
irs-0.034
ait-0.031
sie-0.030
andel-0.030
Token and
Token ID290
Feature activation+6.36e-01

Pos logit contributions
 owner+0.021
 not+0.019
 still+0.018
 was+0.016
 hurts+0.015
Neg logit contributions
ocol-0.088
irs-0.078
ait-0.071
sie-0.070
andel-0.070
Token did
Token ID750
Feature activation+1.08e+00

Pos logit contributions
 owner+0.008
 not+0.007
 still+0.007
 hurts+0.006
 remembered+0.006
Neg logit contributions
ocol-0.031
irs-0.027
ait-0.025
andel-0.025
sie-0.024
Token taller
Token ID25242
Feature activation+1.32e+00

Pos logit contributions
 owner+0.004
zag+0.003
 not+0.003
 hurts+0.003
Because+0.003
Neg logit contributions
ocol-0.007
irs-0.005
andel-0.005
sie-0.005
ait-0.005
Token than
Token ID621
Feature activation-1.34e+00

Pos logit contributions
 owner+0.024
 hurts+0.022
tr+0.021
 remembered+0.021
zag+0.021
Neg logit contributions
ocol-0.052
irs-0.041
andel-0.039
 pounds-0.039
ait-0.038
Token before
Token ID878
Feature activation-2.33e+00

Pos logit contributions
ocol+0.056
irs+0.048
ait+0.045
andel+0.044
sie+0.043
Neg logit contributions
 not-0.026
 owner-0.025
 still-0.024
 only-0.023
 was-0.022
Token.
Token ID13
Feature activation-4.75e-01

Pos logit contributions
ocol+0.096
irs+0.082
ait+0.075
andel+0.073
sie+0.072
Neg logit contributions
 owner-0.045
 not-0.042
 still-0.040
 hurts-0.039
 hits-0.038
Token The
Token ID383
Feature activation+2.23e+00

Pos logit contributions
ocol+0.025
irs+0.021
ait+0.020
sie+0.019
andel+0.019
Neg logit contributions
 owner-0.005
 not-0.004
 still-0.004
 was-0.004
 only-0.004
Token other
Token ID584
Feature activation+5.36e+00

Pos logit contributions
 owner+0.050
 not+0.048
zag+0.047
 hurts+0.046
 hits+0.046
Neg logit contributions
ocol-0.080
irs-0.065
andel-0.060
ait-0.059
sie-0.057
Token trees
Token ID7150
Feature activation+1.06e+00

Pos logit contributions
 owner+0.116
 not+0.115
zag+0.111
 hurts+0.110
 hits+0.110
Neg logit contributions
ocol-0.190
irs-0.153
ait-0.145
andel-0.143
sie-0.136
Token in
Token ID287
Feature activation+1.60e+00

Pos logit contributions
 owner+0.019
 hurts+0.018
tr+0.017
 hits+0.017
zag+0.017
Neg logit contributions
ocol-0.039
irs-0.033
sie-0.031
ait-0.030
andel-0.029
Token the
Token ID262
Feature activation+5.32e-01

Pos logit contributions
 owner+0.027
 not+0.025
 still+0.024
 was+0.023
 only+0.023
Neg logit contributions
ocol-0.072
irs-0.062
ait-0.058
andel-0.055
sie-0.055
Token forest
Token ID8222
Feature activation+1.21e+00

Pos logit contributions
 owner+0.011
 not+0.011
 hurts+0.010
zag+0.010
 hits+0.010
Neg logit contributions
ocol-0.020
irs-0.017
andel-0.015
ait-0.015
sie-0.015
Token were
Token ID547
Feature activation-7.34e-02

Pos logit contributions
 owner+0.017
 hurts+0.016
burn+0.015
tr+0.015
 hits+0.015
Neg logit contributions
ocol-0.050
irs-0.043
 ages-0.040
ait-0.040
sie-0.040
Token was
Token ID373
Feature activation+8.92e-01

Pos logit contributions
 owner+0.018
ich+0.018
flower+0.017
uck+0.017
burn+0.017
Neg logit contributions
 ages-0.031
 Annie-0.031
ocol-0.030
ts-0.030
irs-0.030
Token fun
Token ID1257
Feature activation+1.16e+00

Pos logit contributions
 not+0.017
 owner+0.017
 still+0.016
 only+0.014
 also+0.014
Neg logit contributions
ocol-0.038
irs-0.033
ait-0.031
andel-0.030
sie-0.030
Token to
Token ID284
Feature activation+4.80e-02

Pos logit contributions
 owner+0.023
 not+0.021
 still+0.020
 hurts+0.020
flower+0.019
Neg logit contributions
ocol-0.046
irs-0.039
ait-0.035
andel-0.034
sie-0.034
Token make
Token ID787
Feature activation+6.24e-01

Pos logit contributions
flower+0.001
 owner+0.001
 hurts+0.001
 remembered+0.001
Because+0.001
Neg logit contributions
ocol-0.002
irs-0.001
ait-0.001
 rubble-0.001
 ages-0.001
Token the
Token ID262
Feature activation+2.28e+00

Pos logit contributions
 owner+0.011
 not+0.011
 still+0.010
 was+0.010
 hurts+0.009
Neg logit contributions
ocol-0.028
irs-0.023
ait-0.022
sie-0.022
andel-0.021
Token other
Token ID584
Feature activation+5.35e+00

Pos logit contributions
 owner+0.051
 not+0.048
 still+0.046
 hurts+0.045
 hits+0.044
Neg logit contributions
ocol-0.088
irs-0.074
ait-0.067
andel-0.065
sie-0.064
Token kids
Token ID3988
Feature activation+1.93e+00

Pos logit contributions
 owner+0.120
 not+0.110
 still+0.107
 hurts+0.105
 was+0.103
Neg logit contributions
ocol-0.210
irs-0.178
ait-0.162
andel-0.156
sie-0.152
Token afraid
Token ID7787
Feature activation+2.88e+00

Pos logit contributions
 owner+0.034
 not+0.033
 still+0.031
 hurts+0.030
 hits+0.029
Neg logit contributions
ocol-0.083
irs-0.071
ait-0.065
andel-0.064
sie-0.062
Token or
Token ID393
Feature activation+5.90e-01

Pos logit contributions
 owner+0.054
 not+0.050
 still+0.047
 was+0.046
 hurts+0.045
Neg logit contributions
ocol-0.125
irs-0.107
ait-0.098
andel-0.096
sie-0.096
Token mad
Token ID8805
Feature activation+1.91e+00

Pos logit contributions
 owner+0.010
zag+0.009
flower+0.009
 still+0.008
 hurts+0.008
Neg logit contributions
ocol-0.024
irs-0.020
ait-0.019
sie-0.018
andel-0.018
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
 owner+0.041
 not+0.039
zag+0.038
 still+0.038
flower+0.038
Neg logit contributions
ocol-0.069
irs-0.058
ait-0.052
andel-0.051
sie-0.049
Token you
Token ID345
Feature activation-3.86e-02

Pos logit contributions
ocol+0.004
ait+0.003
irs+0.003
uster+0.003
sie+0.003
Neg logit contributions
 not-0.002
 was-0.001
 owner-0.001
 still-0.001
 hurts-0.001
Token very
Token ID845
Feature activation+1.96e+00

Pos logit contributions
ocol+0.002
irs+0.001
ait+0.001
andel+0.001
sie+0.001
Neg logit contributions
 owner-0.001
 not-0.001
 still-0.001
 hurts-0.001
 hits-0.001
Token sick
Token ID6639
Feature activation+2.07e+00

Pos logit contributions
 owner+0.033
 not+0.030
 still+0.029
 hurts+0.028
flower+0.028
Neg logit contributions
ocol-0.084
irs-0.071
ait-0.065
andel-0.064
sie-0.063
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 owner+0.030
 not+0.029
 still+0.025
 was+0.025
 hurts+0.024
Neg logit contributions
ocol-0.099
irs-0.088
ait-0.082
andel-0.079
sie-0.078
Token The
Token ID383
Feature activation+2.25e+00

Pos logit contributions
 owner+0.010
 not+0.009
 still+0.008
 was+0.008
 also+0.007
Neg logit contributions
ocol-0.057
irs-0.050
ait-0.047
andel-0.047
sie-0.047
Token other
Token ID584
Feature activation+5.34e+00

Pos logit contributions
 owner+0.057
 not+0.054
 still+0.052
 hurts+0.052
 hits+0.051
Neg logit contributions
ocol-0.078
irs-0.063
ait-0.056
andel-0.055
sie-0.054
Token mushrooms
Token ID23452
Feature activation+1.87e-02

Pos logit contributions
 owner+0.128
 not+0.123
 still+0.119
 hurts+0.117
 hits+0.116
Neg logit contributions
ocol-0.191
irs-0.157
ait-0.140
andel-0.138
sie-0.136
Token were
Token ID547
Feature activation+3.39e-01

Pos logit contributions
 owner+0.000
 not+0.000
zag+0.000
 hurts+0.000
 hits+0.000
Neg logit contributions
ocol-0.001
irs-0.001
ait-0.001
sie-0.001
andel-0.001
Token not
Token ID407
Feature activation+6.08e-01

Pos logit contributions
 owner+0.005
 not+0.005
 still+0.004
 hurts+0.004
 hits+0.004
Neg logit contributions
ocol-0.016
irs-0.014
ait-0.013
andel-0.012
sie-0.012
Token dangerous
Token ID4923
Feature activation+1.25e+00

Pos logit contributions
 not+0.012
 owner+0.012
 still+0.011
 also+0.010
 only+0.010
Neg logit contributions
ocol-0.026
irs-0.023
ait-0.021
andel-0.021
sie-0.019
Token.
Token ID13
Feature activation+1.14e+00

Pos logit contributions
 owner+0.018
 not+0.018
 hurts+0.016
 still+0.016
 was+0.016
Neg logit contributions
ocol-0.058
irs-0.051
ait-0.047
andel-0.046
sie-0.045
Token train
Token ID4512
Feature activation+1.43e+00

Pos logit contributions
 hurts+0.040
 hits+0.040
 not+0.038
 remembered+0.037
 neither+0.036
Neg logit contributions
ocol-0.074
ait-0.064
irs-0.061
andel-0.061
year-0.060
Token was
Token ID373
Feature activation+1.64e+00

Pos logit contributions
 hurts+0.017
 owner+0.016
 not+0.015
 still+0.015
 hits+0.015
Neg logit contributions
ocol-0.059
irs-0.052
ait-0.050
 ages-0.048
 Eve-0.048
Token red
Token ID2266
Feature activation+1.62e+00

Pos logit contributions
 owner+0.032
 hurts+0.031
 not+0.030
 still+0.030
 hits+0.029
Neg logit contributions
ocol-0.064
irs-0.053
ait-0.050
andel-0.048
sie-0.046
Token and
Token ID290
Feature activation-6.30e-01

Pos logit contributions
 owner+0.019
 not+0.019
 remembered+0.018
 still+0.018
 hurts+0.017
Neg logit contributions
ocol-0.075
irs-0.064
ait-0.061
andel-0.060
sie-0.057
Token the
Token ID262
Feature activation+1.86e+00

Pos logit contributions
ocol+0.026
irs+0.022
ait+0.020
andel+0.020
sie+0.020
Neg logit contributions
 owner-0.011
 not-0.010
 still-0.010
 hurts-0.010
 hits-0.010
Token other
Token ID584
Feature activation+5.31e+00

Pos logit contributions
 owner+0.037
 not+0.035
 still+0.033
 hurts+0.032
 hits+0.031
Neg logit contributions
ocol-0.076
irs-0.064
ait-0.059
andel-0.057
sie-0.056
Token train
Token ID4512
Feature activation+1.26e+00

Pos logit contributions
 owner+0.108
 not+0.107
 hurts+0.104
 still+0.101
 hits+0.100
Neg logit contributions
ocol-0.196
irs-0.167
ait-0.155
andel-0.149
 ages-0.143
Token was
Token ID373
Feature activation+1.25e+00

Pos logit contributions
 owner+0.011
 hurts+0.010
 not+0.010
 hits+0.010
flower+0.009
Neg logit contributions
ocol-0.058
irs-0.051
ait-0.048
sie-0.047
 ages-0.046
Token blue
Token ID4171
Feature activation+1.50e+00

Pos logit contributions
 owner+0.025
 hurts+0.024
 hits+0.023
 not+0.023
flower+0.022
Neg logit contributions
ocol-0.048
irs-0.040
ait-0.037
andel-0.035
sie-0.034
Token.
Token ID13
Feature activation+6.88e-01

Pos logit contributions
 owner+0.030
 not+0.029
 remembered+0.029
 hurts+0.028
 hits+0.028
Neg logit contributions
ocol-0.057
irs-0.047
ait-0.044
andel-0.043
sie-0.041
Token They
Token ID1119
Feature activation+1.76e-01

Pos logit contributions
 owner+0.008
 not+0.007
 still+0.007
 was+0.006
 only+0.006
Neg logit contributions
ocol-0.035
irs-0.030
sie-0.028
ait-0.028
andel-0.028
Token't
Token ID470
Feature activation+1.02e+00

Pos logit contributions
ocol+0.040
irs+0.034
ait+0.031
andel+0.030
sie+0.029
Neg logit contributions
 owner-0.018
 not-0.015
flower-0.015
 remembered-0.015
 still-0.015
Token find
Token ID1064
Feature activation-3.37e-01

Pos logit contributions
 owner+0.016
 not+0.015
 still+0.015
 also+0.013
 was+0.013
Neg logit contributions
ocol-0.047
irs-0.040
ait-0.037
andel-0.037
sie-0.035
Token her
Token ID607
Feature activation+8.15e-01

Pos logit contributions
ocol+0.014
irs+0.012
ait+0.011
andel+0.011
inations+0.011
Neg logit contributions
 owner-0.006
 not-0.006
 still-0.006
 only-0.006
 was-0.006
Token.
Token ID13
Feature activation+7.95e-01

Pos logit contributions
 owner+0.016
 not+0.015
 still+0.014
 hurts+0.014
 hits+0.014
Neg logit contributions
ocol-0.033
irs-0.028
ait-0.026
andel-0.025
sie-0.025
Token The
Token ID383
Feature activation+1.92e+00

Pos logit contributions
 owner+0.010
 not+0.009
 still+0.008
 was+0.008
 only+0.007
Neg logit contributions
ocol-0.040
irs-0.035
ait-0.032
andel-0.031
sie-0.031
Token other
Token ID584
Feature activation+5.31e+00

Pos logit contributions
 owner+0.041
 not+0.039
 still+0.037
 hurts+0.037
 hits+0.036
Neg logit contributions
ocol-0.075
irs-0.063
ait-0.057
andel-0.056
sie-0.055
Token sheep
Token ID15900
Feature activation+1.18e+00

Pos logit contributions
 hurts+0.142
 hits+0.141
 not+0.140
zag+0.138
 owner+0.134
Neg logit contributions
ocol-0.163
ait-0.126
irs-0.125
andel-0.117
sie-0.117
Token were
Token ID547
Feature activation+5.56e-01

Pos logit contributions
 owner+0.016
 hits+0.014
 hurts+0.014
zag+0.014
 not+0.014
Neg logit contributions
ocol-0.050
irs-0.044
sie-0.041
ait-0.041
 rubble-0.039
Token sad
Token ID6507
Feature activation+2.68e+00

Pos logit contributions
 owner+0.009
 not+0.009
 still+0.008
 hurts+0.008
 also+0.008
Neg logit contributions
ocol-0.025
irs-0.021
ait-0.020
andel-0.019
sie-0.019
Token because
Token ID780
Feature activation+2.30e-01

Pos logit contributions
 owner+0.038
 not+0.032
zag+0.032
 hurts+0.031
 hits+0.031
Neg logit contributions
ocol-0.120
irs-0.103
ait-0.097
andel-0.095
sie-0.093
Token their
Token ID511
Feature activation+1.10e+00

Pos logit contributions
 owner+0.004
 not+0.004
 still+0.003
 was+0.003
 also+0.003
Neg logit contributions
ocol-0.010
irs-0.009
ait-0.008
andel-0.008
sie-0.008
Token place
Token ID1295
Feature activation+4.90e-01

Pos logit contributions
 owner+0.012
 not+0.010
 still+0.010
 hurts+0.010
 hits+0.010
Neg logit contributions
ocol-0.028
irs-0.024
ait-0.022
andel-0.021
sie-0.021
Token all
Token ID477
Feature activation-3.29e-01

Pos logit contributions
 owner+0.009
 not+0.009
 still+0.008
 was+0.007
 only+0.007
Neg logit contributions
ocol-0.022
irs-0.019
andel-0.017
ait-0.017
sie-0.016
Token day
Token ID1110
Feature activation-1.96e+00

Pos logit contributions
ocol+0.014
irs+0.012
ait+0.011
sie+0.011
andel+0.011
Neg logit contributions
 owner-0.006
 not-0.005
 hurts-0.005
 still-0.005
zag-0.005
Token.
Token ID13
Feature activation+5.84e-01

Pos logit contributions
ocol+0.097
irs+0.084
ait+0.076
andel+0.074
prise+0.074
Neg logit contributions
 not-0.032
 owner-0.029
 still-0.027
 only-0.023
 next-0.022
Token The
Token ID383
Feature activation+2.40e+00

Pos logit contributions
 owner+0.007
 not+0.007
 still+0.006
 was+0.006
 only+0.005
Neg logit contributions
ocol-0.029
irs-0.025
ait-0.023
andel-0.023
sie-0.023
Token other
Token ID584
Feature activation+5.28e+00

Pos logit contributions
 owner+0.059
 not+0.056
 still+0.054
 hurts+0.053
 hits+0.052
Neg logit contributions
ocol-0.086
irs-0.070
ait-0.063
andel-0.061
sie-0.060
Token cube
Token ID23441
Feature activation+2.02e+00

Pos logit contributions
 owner+0.174
 not+0.171
 hurts+0.166
 still+0.166
zag+0.164
Neg logit contributions
ocol-0.139
irs-0.104
ait-0.088
andel-0.085
sie-0.081
Token was
Token ID373
Feature activation+1.57e+00

Pos logit contributions
 owner+0.023
burn+0.023
flower+0.021
 Fighting+0.021
zag+0.020
Neg logit contributions
ocol-0.078
sie-0.067
inations-0.066
ait-0.065
irs-0.065
Token much
Token ID881
Feature activation-7.52e-01

Pos logit contributions
 hurts+0.031
 owner+0.031
zag+0.030
flower+0.030
 hits+0.030
Neg logit contributions
ocol-0.058
irs-0.047
ait-0.044
andel-0.042
sie-0.041
Token more
Token ID517
Feature activation+9.57e-01

Pos logit contributions
ocol+0.029
irs+0.024
ait+0.022
andel+0.021
sie+0.021
Neg logit contributions
 owner-0.016
 not-0.015
zag-0.015
 hurts-0.015
 still-0.014
Token adventurous
Token ID39770
Feature activation-1.61e-01

Pos logit contributions
 owner+0.022
flower+0.021
 hurts+0.021
zag+0.021
 not+0.021
Neg logit contributions
ocol-0.034
irs-0.028
ait-0.025
andel-0.025
inations-0.024
Token looked
Token ID3114
Feature activation-2.66e+00

Pos logit contributions
ocol+0.001
irs+0.001
ait+0.001
sie+0.001
year+0.001
Neg logit contributions
 hurts-0.000
 owner-0.000
 hits-0.000
 not-0.000
 remembered-0.000
Token very
Token ID845
Feature activation-1.90e+00

Pos logit contributions
ocol+0.125
irs+0.115
ait+0.107
andel+0.101
sie+0.098
Neg logit contributions
 still-0.044
 not-0.043
 owner-0.038
 was-0.038
 only-0.037
Token useful
Token ID4465
Feature activation-9.88e-01

Pos logit contributions
ocol+0.083
irs+0.074
ait+0.067
andel+0.067
uster+0.065
Neg logit contributions
 still-0.038
 not-0.037
 owner-0.034
 also-0.033
 only-0.030
Token.
Token ID13
Feature activation-2.70e-01

Pos logit contributions
ocol+0.046
irs+0.040
andel+0.037
ait+0.036
sie+0.035
Neg logit contributions
 owner-0.015
 not-0.015
 still-0.014
 was-0.013
 only-0.012
Token The
Token ID383
Feature activation+1.57e+00

Pos logit contributions
ocol+0.013
irs+0.011
ait+0.010
andel+0.010
sie+0.010
Neg logit contributions
 owner-0.004
 not-0.003
 still-0.003
 was-0.003
 only-0.003
Token other
Token ID584
Feature activation+5.25e+00

Pos logit contributions
 owner+0.034
 not+0.034
 hurts+0.033
 still+0.032
 hits+0.032
Neg logit contributions
ocol-0.058
irs-0.048
ait-0.044
andel-0.043
sie-0.042
Token agreed
Token ID4987
Feature activation+8.85e-02

Pos logit contributions
 not+0.109
 hurts+0.108
zag+0.104
 owner+0.103
 hits+0.103
Neg logit contributions
ocol-0.193
irs-0.156
ait-0.153
andel-0.143
sie-0.140
Token and
Token ID290
Feature activation+1.20e-01

Pos logit contributions
 owner+0.001
 not+0.001
 still+0.001
 was+0.001
 hurts+0.001
Neg logit contributions
ocol-0.005
irs-0.004
ait-0.004
andel-0.004
sie-0.004
Token said
Token ID531
Feature activation-1.31e+00

Pos logit contributions
 owner+0.002
 not+0.002
 still+0.002
 hurts+0.002
 hits+0.002
Neg logit contributions
ocol-0.005
irs-0.005
ait-0.004
andel-0.004
sie-0.004
Token it
Token ID340
Feature activation+4.58e-01

Pos logit contributions
ocol+0.065
irs+0.058
ait+0.054
andel+0.053
sie+0.051
Neg logit contributions
 owner-0.015
 not-0.014
 still-0.012
 was-0.011
 hurts-0.011
Token was
Token ID373
Feature activation+7.26e-01

Pos logit contributions
 owner+0.003
 hits+0.003
 hurts+0.003
flower+0.002
 not+0.002
Neg logit contributions
ocol-0.023
irs-0.020
ait-0.019
sie-0.019
 Annie-0.019
Token we
Token ID356
Feature activation-1.18e+00

Pos logit contributions
 owner+0.014
 not+0.014
 still+0.013
 hurts+0.013
 also+0.012
Neg logit contributions
ocol-0.019
irs-0.015
ait-0.014
andel-0.013
year-0.013
Token stay
Token ID2652
Feature activation+2.24e-01

Pos logit contributions
ocol+0.056
irs+0.047
andel+0.045
year+0.043
ait+0.043
Neg logit contributions
 still-0.018
 owner-0.018
 not-0.018
 only-0.016
 also-0.016
Token here
Token ID994
Feature activation-7.86e-01

Pos logit contributions
 owner+0.005
 not+0.004
 still+0.004
 hurts+0.004
 remembered+0.004
Neg logit contributions
ocol-0.009
irs-0.008
ait-0.007
andel-0.007
sie-0.007
Token?"
Token ID1701
Feature activation+6.13e-01

Pos logit contributions
ocol+0.034
irs+0.029
ait+0.027
andel+0.026
sie+0.026
Neg logit contributions
 owner-0.013
 not-0.012
 hurts-0.011
 hits-0.011
 still-0.011
Token The
Token ID383
Feature activation+1.84e+00

Pos logit contributions
 owner+0.008
 not+0.008
 hurts+0.007
 still+0.007
 hits+0.007
Neg logit contributions
ocol-0.028
irs-0.024
ait-0.022
andel-0.022
sie-0.022
Token other
Token ID584
Feature activation+5.22e+00

Pos logit contributions
 owner+0.033
 not+0.032
 still+0.031
 hurts+0.030
 remembered+0.030
Neg logit contributions
ocol-0.075
irs-0.063
ait-0.058
andel-0.058
sie-0.056
Token cat
Token ID3797
Feature activation+4.39e-01

Pos logit contributions
 owner+0.122
 not+0.122
 still+0.118
 hurts+0.117
 hits+0.115
Neg logit contributions
ocol-0.173
irs-0.140
ait-0.133
andel-0.128
sie-0.124
Token said
Token ID531
Feature activation-1.60e+00

Pos logit contributions
 owner+0.007
 hits+0.006
zag+0.006
 hurts+0.006
 not+0.006
Neg logit contributions
ocol-0.017
irs-0.014
sie-0.014
 Annie-0.014
ait-0.014
Token,
Token ID11
Feature activation-2.74e-01

Pos logit contributions
ocol+0.072
irs+0.061
ait+0.056
sie+0.055
andel+0.055
Neg logit contributions
 owner-0.023
 hurts-0.020
 hits-0.020
 not-0.020
zag-0.020
Token "
Token ID366
Feature activation+2.01e+00

Pos logit contributions
ocol+0.012
irs+0.010
ait+0.009
andel+0.009
sie+0.009
Neg logit contributions
 owner-0.004
 hurts-0.004
 not-0.004
 hits-0.004
 still-0.004
TokenMaybe
Token ID13300
Feature activation-9.90e-01

Pos logit contributions
 hits+0.038
 remembered+0.035
 head+0.035
 hurts+0.034
 owner+0.032
Neg logit contributions
ocol-0.065
irs-0.057
ait-0.056
chie-0.055
sie-0.055
Token was
Token ID373
Feature activation+1.87e+00

Pos logit contributions
 owner+0.037
 not+0.036
 hurts+0.036
 still+0.035
zag+0.034
Neg logit contributions
ocol-0.093
irs-0.080
ait-0.073
sie-0.072
 ages-0.071
Token very
Token ID845
Feature activation+8.17e-01

Pos logit contributions
 hurts+0.037
 owner+0.037
flower+0.036
 remembered+0.034
zag+0.034
Neg logit contributions
ocol-0.068
irs-0.058
ait-0.053
andel-0.051
sie-0.050
Token wealthy
Token ID11574
Feature activation+1.09e+00

Pos logit contributions
 owner+0.016
 not+0.015
 still+0.015
 hurts+0.014
 hits+0.014
Neg logit contributions
ocol-0.033
irs-0.028
ait-0.026
andel-0.025
sie-0.024
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
 owner+0.015
 not+0.013
 still+0.012
 was+0.011
 hurts+0.011
Neg logit contributions
ocol-0.053
irs-0.046
ait-0.042
andel-0.042
sie-0.041
Token The
Token ID383
Feature activation+2.38e+00

Pos logit contributions
 owner+0.004
 not+0.003
 still+0.003
 was+0.003
 hits+0.003
Neg logit contributions
ocol-0.012
irs-0.010
ait-0.010
andel-0.010
sie-0.009
Token other
Token ID584
Feature activation+5.20e+00

Pos logit contributions
 owner+0.051
 not+0.049
 hurts+0.048
zag+0.048
flower+0.048
Neg logit contributions
ocol-0.083
irs-0.070
ait-0.063
andel-0.062
sie-0.061
Token team
Token ID1074
Feature activation+2.70e+00

Pos logit contributions
 not+0.119
 owner+0.118
 hurts+0.117
zag+0.115
tr+0.114
Neg logit contributions
ocol-0.169
irs-0.140
ait-0.127
 ages-0.124
sie-0.123
Token had
Token ID550
Feature activation+1.27e+00

Pos logit contributions
 owner+0.029
 hurts+0.028
 not+0.027
zag+0.026
flower+0.025
Neg logit contributions
ocol-0.119
irs-0.105
sie-0.098
ait-0.098
 ages-0.096
Token hardly
Token ID8941
Feature activation-1.67e-01

Pos logit contributions
 owner+0.022
 not+0.020
 still+0.020
 hurts+0.019
 hits+0.018
Neg logit contributions
ocol-0.055
irs-0.047
ait-0.043
andel-0.042
sie-0.041
Token anything
Token ID1997
Feature activation-1.58e+00

Pos logit contributions
ocol+0.007
irs+0.006
ait+0.006
andel+0.006
sie+0.006
Neg logit contributions
 owner-0.003
 not-0.003
 still-0.002
 hurts-0.002
 hits-0.002
Token.
Token ID13
Feature activation+7.80e-01

Pos logit contributions
ocol+0.068
irs+0.058
ait+0.054
andel+0.053
sie+0.051
Neg logit contributions
 owner-0.028
 not-0.026
 still-0.025
 hurts-0.024
 was-0.023
Token felt
Token ID2936
Feature activation-4.58e-01

Pos logit contributions
 owner+0.013
flower+0.012
 hurts+0.012
 hits+0.012
tr+0.011
Neg logit contributions
ocol-0.047
irs-0.042
ait-0.041
 Annie-0.040
sie-0.040
Token en
Token ID551
Feature activation-5.22e-01

Pos logit contributions
ocol+0.018
irs+0.015
ait+0.014
andel+0.014
sie+0.013
Neg logit contributions
 owner-0.009
zag-0.008
flower-0.008
 not-0.008
 hurts-0.008
Tokenvious
Token ID1442
Feature activation+2.40e+00

Pos logit contributions
ocol+0.018
irs+0.014
andel+0.013
ait+0.013
sie+0.012
Neg logit contributions
 not-0.013
 owner-0.013
zag-0.013
flower-0.012
tr-0.012
Token because
Token ID780
Feature activation+1.26e+00

Pos logit contributions
 owner+0.050
 not+0.047
flower+0.045
 hurts+0.045
zag+0.045
Neg logit contributions
ocol-0.092
irs-0.077
ait-0.071
andel-0.069
sie-0.066
Token the
Token ID262
Feature activation+2.29e+00

Pos logit contributions
 owner+0.022
 not+0.020
 still+0.019
 hurts+0.018
 hits+0.018
Neg logit contributions
ocol-0.054
irs-0.047
ait-0.043
andel-0.042
sie-0.041
Token other
Token ID584
Feature activation+5.19e+00

Pos logit contributions
 owner+0.046
 not+0.042
 still+0.039
 hurts+0.038
 was+0.037
Neg logit contributions
ocol-0.097
irs-0.084
ait-0.075
sie-0.074
andel-0.073
Token dogs
Token ID6844
Feature activation+1.04e+00

Pos logit contributions
 owner+0.111
 not+0.107
 still+0.105
 hurts+0.103
 hits+0.102
Neg logit contributions
ocol-0.194
irs-0.161
ait-0.151
andel-0.143
sie-0.137
Token had
Token ID550
Feature activation+7.05e-01

Pos logit contributions
 owner+0.019
 not+0.017
 hits+0.016
 hurts+0.016
zag+0.016
Neg logit contributions
ocol-0.043
irs-0.037
ait-0.033
sie-0.032
andel-0.032
Token fun
Token ID1257
Feature activation+1.19e+00

Pos logit contributions
 owner+0.013
 not+0.012
 still+0.011
 hurts+0.011
 hits+0.010
Neg logit contributions
ocol-0.030
irs-0.026
ait-0.024
andel-0.023
sie-0.023
Token toys
Token ID14958
Feature activation+7.97e-01

Pos logit contributions
 owner+0.018
 not+0.018
 was+0.016
 still+0.016
 hurts+0.015
Neg logit contributions
ocol-0.055
irs-0.047
ait-0.045
andel-0.044
sie-0.043
Token to
Token ID284
Feature activation-8.70e-01

Pos logit contributions
 owner+0.013
 not+0.012
 still+0.012
 hurts+0.011
 hits+0.011
Neg logit contributions
ocol-0.035
irs-0.030
ait-0.028
andel-0.027
sie-0.027
Token car
Token ID1097
Feature activation+2.89e+00

Pos logit contributions
flower+0.042
 hurts+0.041
burn+0.039
 not+0.039
 remembered+0.038
Neg logit contributions
ocol-0.058
ait-0.049
 ages-0.049
year-0.048
andel-0.047
Token was
Token ID373
Feature activation+1.47e+00

Pos logit contributions
flower+0.039
burn+0.039
 hurts+0.035
 owner+0.032
 still+0.031
Neg logit contributions
ocol-0.106
 ages-0.093
irs-0.092
 Eve-0.090
ait-0.089
Token red
Token ID2266
Feature activation+1.23e+00

Pos logit contributions
 owner+0.030
 hurts+0.029
flower+0.028
 not+0.027
 still+0.027
Neg logit contributions
ocol-0.055
irs-0.046
ait-0.043
andel-0.041
 ages-0.039
Token and
Token ID290
Feature activation-5.95e-01

Pos logit contributions
 remembered+0.019
 not+0.017
 still+0.016
 missed+0.016
 owner+0.016
Neg logit contributions
ocol-0.051
andel-0.042
irs-0.041
ait-0.041
uster-0.039
Token the
Token ID262
Feature activation+1.77e+00

Pos logit contributions
ocol+0.023
irs+0.020
ait+0.018
sie+0.017
andel+0.017
Neg logit contributions
 owner-0.011
 hurts-0.010
 not-0.010
 still-0.010
flower-0.010
Token other
Token ID584
Feature activation+5.17e+00

Pos logit contributions
 owner+0.032
 not+0.030
 still+0.029
 hurts+0.028
 hits+0.027
Neg logit contributions
ocol-0.075
irs-0.064
ait-0.059
andel-0.057
sie-0.056
Token car
Token ID1097
Feature activation+2.71e+00

Pos logit contributions
 not+0.062
 owner+0.062
 hurts+0.059
 still+0.056
flower+0.055
Neg logit contributions
ocol-0.230
irs-0.200
ait-0.189
andel-0.181
 ages-0.180
Token was
Token ID373
Feature activation+1.44e+00

Pos logit contributions
flower+0.029
burn+0.026
 owner+0.025
 hurts+0.024
 not+0.021
Neg logit contributions
ocol-0.110
irs-0.097
 ages-0.094
ait-0.093
inations-0.090
Token blue
Token ID4171
Feature activation+1.42e+00

Pos logit contributions
 owner+0.029
 hurts+0.029
flower+0.028
 hits+0.027
 not+0.026
Neg logit contributions
ocol-0.053
irs-0.045
ait-0.041
andel-0.039
 ages-0.038
Token.
Token ID13
Feature activation+6.18e-01

Pos logit contributions
 remembered+0.031
 not+0.029
 owner+0.029
 hurts+0.029
 hits+0.029
Neg logit contributions
ocol-0.048
ait-0.038
irs-0.038
andel-0.037
 Annie-0.034
Token They
Token ID1119
Feature activation+1.13e-01

Pos logit contributions
 owner+0.007
 not+0.006
 still+0.006
 was+0.005
 only+0.005
Neg logit contributions
ocol-0.032
irs-0.028
ait-0.025
sie-0.025
prise-0.025
Token the
Token ID262
Feature activation-7.89e-01

Pos logit contributions
 owner+0.006
 not+0.006
 still+0.005
 only+0.005
 also+0.005
Neg logit contributions
ocol-0.017
irs-0.015
ait-0.014
inations-0.014
sie-0.014
Token apples
Token ID22514
Feature activation-1.81e-01

Pos logit contributions
ocol+0.029
irs+0.024
ait+0.022
andel+0.021
sie+0.021
Neg logit contributions
 owner-0.018
 not-0.017
 hurts-0.016
zag-0.016
 still-0.016
Token easily
Token ID3538
Feature activation-1.11e+00

Pos logit contributions
ocol+0.007
irs+0.006
ait+0.005
andel+0.005
sie+0.005
Neg logit contributions
 owner-0.004
 hurts-0.004
 remembered-0.003
 hits-0.003
 hates-0.003
Token.
Token ID13
Feature activation+7.58e-01

Pos logit contributions
ocol+0.044
irs+0.038
ait+0.034
andel+0.033
sie+0.033
Neg logit contributions
 owner-0.022
 not-0.020
 hurts-0.020
 still-0.019
 hits-0.019
Token The
Token ID383
Feature activation+1.87e+00

Pos logit contributions
 owner+0.013
 hurts+0.013
 not+0.013
 remembered+0.012
flower+0.012
Neg logit contributions
ocol-0.030
irs-0.026
ait-0.024
 Annie-0.023
andel-0.023
Token other
Token ID584
Feature activation+5.15e+00

Pos logit contributions
 hurts+0.022
 hits+0.020
Because+0.020
zag+0.019
 not+0.018
Neg logit contributions
ocol-0.082
irs-0.069
ait-0.068
sie-0.066
andel-0.066
Token friend
Token ID1545
Feature activation+1.22e+00

Pos logit contributions
 hurts+0.085
 hits+0.082
 misses+0.080
zag+0.079
bike+0.078
Neg logit contributions
ocol-0.177
ait-0.150
sie-0.147
 ages-0.143
andel-0.140
Token was
Token ID373
Feature activation+1.63e+00

Pos logit contributions
 owner+0.013
 not+0.012
 hurts+0.012
zag+0.011
 hits+0.011
Neg logit contributions
ocol-0.058
irs-0.050
ait-0.048
sie-0.047
andel-0.045
Token short
Token ID1790
Feature activation+1.32e+00

Pos logit contributions
 hurts+0.039
tr+0.038
flower+0.036
 hits+0.036
zag+0.036
Neg logit contributions
ocol-0.050
year-0.039
irs-0.038
ait-0.037
sie-0.036
Token and
Token ID290
Feature activation+3.77e-02

Pos logit contributions
 owner+0.015
 not+0.013
 still+0.013
 hurts+0.012
 hits+0.012
Neg logit contributions
ocol-0.064
irs-0.054
ait-0.051
andel-0.050
sie-0.050
Token couldn
Token ID3521
Feature activation-1.31e+00

Pos logit contributions
 owner+0.000
 hurts+0.000
 not+0.000
zag+0.000
 hits+0.000
Neg logit contributions
ocol-0.002
irs-0.002
ait-0.001
sie-0.001
andel-0.001
Token the
Token ID262
Feature activation+5.41e-01

Pos logit contributions
ocol+0.041
irs+0.036
ait+0.035
sie+0.035
andel+0.034
Neg logit contributions
 not-0.014
 owner-0.013
 still-0.012
 was-0.012
 only-0.011
Token other
Token ID584
Feature activation+4.34e+00

Pos logit contributions
 owner+0.011
 not+0.010
 still+0.010
 hurts+0.010
 only+0.009
Neg logit contributions
ocol-0.023
irs-0.020
ait-0.018
andel-0.017
sie-0.017
Token clouds
Token ID15114
Feature activation+8.63e-01

Pos logit contributions
 owner+0.093
 not+0.087
 still+0.084
 hurts+0.082
 hits+0.080
Neg logit contributions
ocol-0.171
irs-0.143
ait-0.130
andel-0.126
sie-0.124
Token.
Token ID13
Feature activation+9.41e-01

Pos logit contributions
 owner+0.016
 not+0.015
 still+0.014
 hurts+0.014
 hits+0.014
Neg logit contributions
ocol-0.036
irs-0.031
ait-0.028
andel-0.027
sie-0.027
Token The
Token ID383
Feature activation+2.09e+00

Pos logit contributions
 owner+0.012
 not+0.011
 still+0.010
 hurts+0.010
 hits+0.010
Neg logit contributions
ocol-0.044
irs-0.039
ait-0.036
andel-0.035
sie-0.034
Token other
Token ID584
Feature activation+5.14e+00

Pos logit contributions
 owner+0.044
 not+0.042
 still+0.040
 hurts+0.039
 hits+0.038
Neg logit contributions
ocol-0.082
irs-0.069
ait-0.063
andel-0.061
sie-0.060
Token clouds
Token ID15114
Feature activation+1.66e+00

Pos logit contributions
 owner+0.113
 not+0.108
 still+0.104
 hurts+0.102
 hits+0.100
Neg logit contributions
ocol-0.193
irs-0.161
ait-0.147
andel-0.143
sie-0.140
Token were
Token ID547
Feature activation-1.64e-01

Pos logit contributions
 owner+0.029
 not+0.026
zag+0.026
 hurts+0.024
tr+0.024
Neg logit contributions
ocol-0.066
irs-0.055
sie-0.052
ait-0.052
year-0.049
Token en
Token ID551
Feature activation-7.18e-01

Pos logit contributions
ocol+0.006
irs+0.005
 rubble+0.004
ait+0.004
andel+0.004
Neg logit contributions
Because-0.003
 hurts-0.003
 owner-0.003
zag-0.003
tr-0.003
Tokenvious
Token ID1442
Feature activation+2.50e+00

Pos logit contributions
ocol+0.028
irs+0.023
ait+0.021
andel+0.021
sie+0.020
Neg logit contributions
 owner-0.016
 not-0.015
 still-0.014
zag-0.014
 hurts-0.014
Token of
Token ID286
Feature activation+2.92e-02

Pos logit contributions
 owner+0.057
 not+0.054
zag+0.052
flower+0.052
 hurts+0.052
Neg logit contributions
ocol-0.090
irs-0.075
ait-0.069
andel-0.067
sie-0.063
Token a
Token ID257
Feature activation-1.43e+00

Pos logit contributions
ocol+0.002
irs+0.001
ait+0.001
andel+0.001
sie+0.001
Neg logit contributions
 owner-0.001
 not-0.001
 still-0.001
 hurts-0.001
 hits-0.001
Token strange
Token ID6283
Feature activation-2.58e-01

Pos logit contributions
ocol+0.063
irs+0.056
ait+0.051
sie+0.047
andel+0.046
Neg logit contributions
 owner-0.028
 not-0.024
 still-0.024
 was-0.024
 hurts-0.022
Token,
Token ID11
Feature activation-3.00e+00

Pos logit contributions
ocol+0.011
irs+0.009
ait+0.009
andel+0.008
sie+0.008
Neg logit contributions
 owner-0.005
 not-0.005
 still-0.004
 hurts-0.004
 was-0.004
Token raspberry
Token ID38973
Feature activation-5.62e-01

Pos logit contributions
ocol+0.123
irs+0.109
ait+0.101
sie+0.094
andel+0.094
Neg logit contributions
 owner-0.059
 not-0.058
 still-0.056
 hurts-0.054
 was-0.053
Token-
Token ID12
Feature activation-3.58e+00

Pos logit contributions
ocol+0.022
irs+0.019
ait+0.017
andel+0.017
sie+0.016
Neg logit contributions
 owner-0.011
 not-0.011
 still-0.010
 hurts-0.010
 hits-0.010
Tokencol
Token ID4033
Feature activation-8.66e+00

Pos logit contributions
ocol+0.117
irs+0.096
ait+0.086
andel+0.081
sie+0.080
Neg logit contributions
 owner-0.099
 not-0.095
 still-0.091
 hurts-0.090
 was-0.088
Tokenoured
Token ID8167
Feature activation-3.59e-01

Pos logit contributions
ocol+0.251
irs+0.208
sie+0.187
 ages+0.184
inations+0.183
Neg logit contributions
 hits-0.226
 owner-0.224
flower-0.220
 hurts-0.219
 still-0.218
Token object
Token ID2134
Feature activation-5.03e-01

Pos logit contributions
ocol+0.014
irs+0.012
ait+0.011
sie+0.010
andel+0.010
Neg logit contributions
 owner-0.008
 not-0.007
 still-0.007
 was-0.007
 hurts-0.007
Token hiding
Token ID11816
Feature activation-4.14e-01

Pos logit contributions
ocol+0.021
irs+0.018
ait+0.017
andel+0.016
sie+0.016
Neg logit contributions
 owner-0.009
 not-0.008
 still-0.008
 hurts-0.008
 hits-0.007
Token under
Token ID739
Feature activation-1.26e+00

Pos logit contributions
ocol+0.017
irs+0.014
ait+0.013
andel+0.012
sie+0.012
Neg logit contributions
 owner-0.009
 not-0.008
 still-0.008
 was-0.008
 remembered-0.007
Token a
Token ID257
Feature activation-3.35e+00

Pos logit contributions
ocol+0.062
irs+0.054
ait+0.054
inations+0.053
sie+0.051
Neg logit contributions
 not-0.015
 owner-0.014
 was-0.013
 only-0.013
 still-0.012
Token get
Token ID651
Feature activation-2.13e-01

Pos logit contributions
ocol+0.062
irs+0.052
ait+0.048
sie+0.046
andel+0.045
Neg logit contributions
 owner-0.030
 not-0.027
 hurts-0.026
zag-0.026
 hits-0.026
Token something
Token ID1223
Feature activation-3.12e+00

Pos logit contributions
ocol+0.009
irs+0.008
ait+0.008
andel+0.007
uster+0.007
Neg logit contributions
 not-0.004
 still-0.004
 owner-0.004
 only-0.003
 also-0.003
Token sweet
Token ID6029
Feature activation-2.10e+00

Pos logit contributions
ocol+0.133
irs+0.114
ait+0.105
andel+0.102
sie+0.098
Neg logit contributions
 owner-0.059
 not-0.059
 still-0.057
 hurts-0.052
 was-0.052
Token or
Token ID393
Feature activation-2.13e+00

Pos logit contributions
ocol+0.088
irs+0.073
ait+0.067
andel+0.066
sie+0.066
Neg logit contributions
 owner-0.038
 not-0.034
zag-0.034
 still-0.032
 hurts-0.032
Token something
Token ID1223
Feature activation-3.41e+00

Pos logit contributions
ocol+0.082
irs+0.068
ait+0.062
andel+0.060
sie+0.059
Neg logit contributions
 owner-0.047
 not-0.044
 still-0.042
 hurts-0.041
 hits-0.041
Token sav
Token ID6799
Feature activation-8.45e+00

Pos logit contributions
ocol+0.143
irs+0.123
ait+0.115
andel+0.112
uster+0.108
Neg logit contributions
 not-0.068
 owner-0.065
 still-0.064
 was-0.061
 hurts-0.060
Tokenour
Token ID454
Feature activation-5.23e-01

Pos logit contributions
ocol+0.287
irs+0.246
ait+0.216
 rubble+0.207
andel+0.206
Neg logit contributions
 owner-0.205
 still-0.197
 not-0.197
 hits-0.193
 hurts-0.189
Tokeny
Token ID88
Feature activation-1.32e+00

Pos logit contributions
ocol+0.021
irs+0.018
ait+0.016
andel+0.016
sie+0.016
Neg logit contributions
 owner-0.010
 not-0.009
 still-0.009
 hurts-0.009
 hits-0.009
Token?
Token ID30
Feature activation-1.21e+00

Pos logit contributions
ocol+0.054
irs+0.046
ait+0.042
andel+0.041
sie+0.040
Neg logit contributions
 owner-0.025
 not-0.023
 still-0.022
 hurts-0.022
 hits-0.021
Token In
Token ID554
Feature activation+3.19e-01

Pos logit contributions
ocol+0.060
irs+0.052
ait+0.047
andel+0.047
sie+0.046
Neg logit contributions
 owner-0.015
 still-0.013
 not-0.012
 was-0.012
 only-0.011
Token the
Token ID262
Feature activation+1.82e-01

Pos logit contributions
 owner+0.005
 not+0.005
 still+0.005
 hurts+0.005
 hits+0.005
Neg logit contributions
ocol-0.014
irs-0.012
ait-0.011
andel-0.011
sie-0.010
Token big
Token ID1263
Feature activation-1.29e+00

Pos logit contributions
ocol+0.081
irs+0.073
ait+0.066
andel+0.061
sie+0.060
Neg logit contributions
 owner-0.039
 still-0.035
 was-0.035
 not-0.034
 also-0.032
Token,
Token ID11
Feature activation-2.55e+00

Pos logit contributions
ocol+0.053
irs+0.048
ait+0.043
andel+0.041
inations+0.040
Neg logit contributions
 owner-0.025
 not-0.023
 still-0.023
 hits-0.022
 hurts-0.022
Token beautiful
Token ID4950
Feature activation-5.10e-01

Pos logit contributions
ocol+0.112
irs+0.103
ait+0.093
andel+0.087
sie+0.086
Neg logit contributions
 owner-0.047
 still-0.044
 not-0.043
 also-0.040
 was-0.039
Token rainbow
Token ID27223
Feature activation-1.46e-01

Pos logit contributions
ocol+0.021
irs+0.019
ait+0.017
inations+0.016
year+0.016
Neg logit contributions
 owner-0.010
 was-0.009
flower-0.009
 still-0.009
 not-0.009
Token-
Token ID12
Feature activation-3.46e+00

Pos logit contributions
ocol+0.006
irs+0.005
ait+0.005
andel+0.005
sie+0.005
Neg logit contributions
 owner-0.003
 not-0.003
 was-0.002
 still-0.002
flower-0.002
Tokencol
Token ID4033
Feature activation-8.37e+00

Pos logit contributions
ocol+0.110
irs+0.086
ait+0.079
andel+0.073
sie+0.073
Neg logit contributions
 owner-0.102
 not-0.096
 was-0.094
 still-0.093
zag-0.093
Tokenoured
Token ID8167
Feature activation-1.11e+00

Pos logit contributions
ocol+0.254
irs+0.211
 ages+0.194
inations+0.192
 rubble+0.192
Neg logit contributions
 hits-0.203
flower-0.201
 owner-0.197
 hurts-0.195
uck-0.195
Token butterfly
Token ID35113
Feature activation-9.55e-01

Pos logit contributions
ocol+0.048
irs+0.044
ait+0.040
inations+0.038
uster+0.037
Neg logit contributions
 owner-0.021
 was-0.019
flower-0.018
 not-0.017
 still-0.017
Token!
Token ID0
Feature activation-8.51e-01

Pos logit contributions
ocol+0.040
irs+0.034
ait+0.031
andel+0.030
sie+0.030
Neg logit contributions
 owner-0.018
 not-0.017
 still-0.016
 hurts-0.016
 hits-0.015
Token The
Token ID383
Feature activation+9.92e-01

Pos logit contributions
ocol+0.041
irs+0.034
sie+0.032
inations+0.032
ait+0.032
Neg logit contributions
 owner-0.012
 was-0.010
 not-0.010
 still-0.010
Because-0.009
Token little
Token ID1310
Feature activation+6.79e-01

Pos logit contributions
 owner+0.021
 still+0.018
 not+0.018
 was+0.017
flower+0.017
Neg logit contributions
ocol-0.042
irs-0.036
ait-0.033
andel-0.031
sie-0.030
Token date
Token ID3128
Feature activation-1.17e+00

Pos logit contributions
 owner+0.006
 not+0.006
 still+0.006
 hurts+0.006
 was+0.006
Neg logit contributions
ocol-0.007
irs-0.005
ait-0.005
uster-0.004
sie-0.004
Token,
Token ID11
Feature activation+4.56e-01

Pos logit contributions
ocol+0.053
irs+0.046
ait+0.042
andel+0.041
sie+0.041
Neg logit contributions
 owner-0.016
 not-0.014
 hurts-0.014
 still-0.013
 hits-0.013
Token a
Token ID257
Feature activation-1.31e+00

Pos logit contributions
 owner+0.008
 not+0.008
 still+0.007
 was+0.007
 only+0.006
Neg logit contributions
ocol-0.020
irs-0.018
ait-0.016
andel-0.016
sie-0.015
Token rainbow
Token ID27223
Feature activation+6.11e-02

Pos logit contributions
ocol+0.057
irs+0.051
ait+0.045
andel+0.041
sie+0.041
Neg logit contributions
 owner-0.028
 not-0.024
 still-0.024
 was-0.024
 remembered-0.022
Token-
Token ID12
Feature activation-3.34e+00

Pos logit contributions
 owner+0.001
 not+0.001
 still+0.001
 hurts+0.001
 hits+0.001
Neg logit contributions
ocol-0.003
irs-0.002
ait-0.002
andel-0.002
sie-0.002
Tokencol
Token ID4033
Feature activation-8.35e+00

Pos logit contributions
ocol+0.110
irs+0.087
ait+0.079
andel+0.074
sie+0.074
Neg logit contributions
 owner-0.093
 not-0.088
 still-0.085
 was-0.085
zag-0.085
Tokenoured
Token ID8167
Feature activation-4.68e-02

Pos logit contributions
ocol+0.258
irs+0.208
sie+0.195
inations+0.194
 rubble+0.193
Neg logit contributions
 hits-0.199
 owner-0.197
tr-0.194
uck-0.194
 still-0.194
Token butterfly
Token ID35113
Feature activation-6.87e-01

Pos logit contributions
ocol+0.002
irs+0.002
ait+0.002
uster+0.002
inations+0.001
Neg logit contributions
 owner-0.001
 was-0.001
flower-0.001
 not-0.001
 still-0.001
Token flew
Token ID13112
Feature activation-1.67e+00

Pos logit contributions
ocol+0.030
irs+0.026
ait+0.023
andel+0.023
sie+0.023
Neg logit contributions
 owner-0.011
 not-0.010
 still-0.010
 hurts-0.009
 hits-0.009
Token in
Token ID287
Feature activation-8.75e-01

Pos logit contributions
ocol+0.079
irs+0.068
ait+0.064
inations+0.062
sie+0.060
Neg logit contributions
 owner-0.025
 still-0.024
 not-0.023
 was-0.021
 only-0.020
Token through
Token ID832
Feature activation-8.79e-01

Pos logit contributions
ocol+0.045
irs+0.038
inations+0.037
ait+0.037
sie+0.037
Neg logit contributions
 was-0.010
 still-0.010
 only-0.009
 not-0.009
 and-0.009
Token day
Token ID1110
Feature activation+6.85e-02

Pos logit contributions
 owner+0.005
 not+0.005
 still+0.005
 hurts+0.005
 hits+0.005
Neg logit contributions
ocol-0.012
irs-0.010
sie-0.010
andel-0.010
ait-0.010
Token,
Token ID11
Feature activation+1.19e+00

Pos logit contributions
 owner+0.001
 not+0.001
 still+0.001
 hurts+0.001
 hits+0.001
Neg logit contributions
ocol-0.003
irs-0.003
ait-0.003
andel-0.003
sie-0.003
Token a
Token ID257
Feature activation-1.43e+00

Pos logit contributions
 owner+0.025
 not+0.025
 still+0.024
 was+0.023
 hurts+0.022
Neg logit contributions
ocol-0.048
irs-0.041
ait-0.037
andel-0.036
sie-0.035
Token chocolate
Token ID11311
Feature activation+3.61e-01

Pos logit contributions
ocol+0.062
irs+0.054
ait+0.048
andel+0.045
sie+0.045
Neg logit contributions
 owner-0.029
 not-0.026
 still-0.026
 was-0.024
 also-0.023
Token-
Token ID12
Feature activation-3.46e+00

Pos logit contributions
 not+0.007
 owner+0.007
 still+0.006
 remembered+0.006
 hurts+0.006
Neg logit contributions
ocol-0.014
irs-0.011
ait-0.011
andel-0.011
sie-0.010
Tokencol
Token ID4033
Feature activation-8.34e+00

Pos logit contributions
ocol+0.125
irs+0.103
ait+0.093
andel+0.090
sie+0.088
Neg logit contributions
 owner-0.085
 not-0.080
 still-0.077
 hurts-0.076
 hits-0.074
Tokenoured
Token ID8167
Feature activation+2.37e-01

Pos logit contributions
ocol+0.250
irs+0.209
inations+0.191
 ages+0.187
sie+0.187
Neg logit contributions
 owner-0.213
 hits-0.210
 hurts-0.206
flower-0.205
 still-0.204
Token whip
Token ID22972
Feature activation+1.10e+00

Pos logit contributions
 owner+0.005
 not+0.004
 still+0.004
 hurts+0.004
 was+0.004
Neg logit contributions
ocol-0.010
irs-0.009
ait-0.008
sie-0.007
andel-0.007
Token named
Token ID3706
Feature activation-3.93e+00

Pos logit contributions
 owner+0.020
 not+0.019
 still+0.018
 hurts+0.018
zag+0.018
Neg logit contributions
ocol-0.043
irs-0.036
ait-0.032
andel-0.032
 ages-0.031
Token C
Token ID327
Feature activation-4.31e+00

Pos logit contributions
ocol+0.162
irs+0.135
inations+0.122
ait+0.121
sie+0.120
Neg logit contributions
 owner-0.081
 not-0.079
 still-0.071
 only-0.070
 hurts-0.069
Tokenheddar
Token ID44937
Feature activation-6.87e-01

Pos logit contributions
ocol+0.168
irs+0.140
ait+0.125
andel+0.124
sie+0.122
Neg logit contributions
 owner-0.095
 not-0.087
 still-0.086
 hurts-0.082
zag-0.082
Token suddenly
Token ID6451
Feature activation+1.30e+00

Pos logit contributions
ocol+0.018
irs+0.016
ait+0.015
andel+0.014
uster+0.014
Neg logit contributions
 owner-0.006
 not-0.006
 still-0.006
 was-0.005
 also-0.005
Token,
Token ID11
Feature activation+4.22e-01

Pos logit contributions
 not+0.017
 owner+0.016
 was+0.015
 remembered+0.014
 still+0.014
Neg logit contributions
ocol-0.063
irs-0.056
ait-0.052
inations-0.050
uster-0.050
Token a
Token ID257
Feature activation-2.20e+00

Pos logit contributions
 not+0.007
 owner+0.006
 still+0.006
 was+0.006
 only+0.006
Neg logit contributions
ocol-0.020
irs-0.017
ait-0.016
uster-0.015
andel-0.015
Token brightly
Token ID35254
Feature activation-1.25e+00

Pos logit contributions
ocol+0.101
irs+0.095
ait+0.085
inations+0.079
sie+0.078
Neg logit contributions
 owner-0.039
 not-0.032
 was-0.032
 still-0.031
 hurts-0.030
Token-
Token ID12
Feature activation-3.38e+00

Pos logit contributions
ocol+0.044
irs+0.033
andel+0.032
year+0.030
 ages+0.029
Neg logit contributions
 owner-0.031
 not-0.028
 neither-0.028
 still-0.028
 remembered-0.026
Tokencol
Token ID4033
Feature activation-8.28e+00

Pos logit contributions
ocol+0.102
irs+0.082
ait+0.071
sie+0.067
andel+0.065
Neg logit contributions
 owner-0.106
tr-0.096
 not-0.096
 still-0.094
 was-0.093
Tokenoured
Token ID8167
Feature activation-5.19e-02

Pos logit contributions
ocol+0.247
irs+0.213
sie+0.187
 ages+0.185
inations+0.185
Neg logit contributions
 hits-0.211
 owner-0.210
 hurts-0.205
tr-0.203
flower-0.202
Token belt
Token ID10999
Feature activation-7.13e-01

Pos logit contributions
ocol+0.002
irs+0.002
ait+0.002
inations+0.002
year+0.002
Neg logit contributions
 owner-0.001
flower-0.001
 was-0.001
 head-0.001
 not-0.001
Token caught
Token ID4978
Feature activation-1.96e+00

Pos logit contributions
ocol+0.028
irs+0.024
ait+0.022
andel+0.022
 rubble+0.021
Neg logit contributions
 owner-0.013
 not-0.012
 still-0.012
 hurts-0.011
flower-0.011
Token her
Token ID607
Feature activation-7.74e-01

Pos logit contributions
ocol+0.094
inations+0.090
irs+0.086
ait+0.080
 rubble+0.078
Neg logit contributions
 owner-0.021
 was-0.021
 next-0.020
 still-0.019
 not-0.019
Token eye
Token ID4151
Feature activation-2.27e+00

Pos logit contributions
ocol+0.033
irs+0.028
ait+0.026
andel+0.026
sie+0.025
Neg logit contributions
 owner-0.012
 not-0.012
 hurts-0.011
 hits-0.011
 still-0.011
Token went
Token ID1816
Feature activation-5.57e-01

Pos logit contributions
ocol+0.011
irs+0.009
ait+0.009
andel+0.008
sie+0.008
Neg logit contributions
 owner-0.004
 not-0.003
 still-0.003
 hurts-0.003
zag-0.003
Token outside
Token ID2354
Feature activation+1.37e+00

Pos logit contributions
ocol+0.029
irs+0.025
ait+0.023
andel+0.022
sie+0.022
Neg logit contributions
 owner-0.006
 not-0.006
 still-0.005
zag-0.005
 hits-0.005
Token to
Token ID284
Feature activation-7.33e-01

Pos logit contributions
 owner+0.016
 not+0.016
 still+0.014
 was+0.014
 also+0.012
Neg logit contributions
ocol-0.068
irs-0.060
ait-0.055
andel-0.054
sie-0.054
Token find
Token ID1064
Feature activation-2.48e-01

Pos logit contributions
ocol+0.031
irs+0.026
ait+0.024
andel+0.024
sie+0.023
Neg logit contributions
 owner-0.013
 not-0.013
 still-0.012
 hurts-0.012
 hits-0.012
Token something
Token ID1223
Feature activation-3.14e+00

Pos logit contributions
ocol+0.012
irs+0.010
ait+0.010
sie+0.010
andel+0.010
Neg logit contributions
 owner-0.003
 not-0.003
 was-0.003
 still-0.003
 only-0.002
Token su
Token ID424
Feature activation-7.94e+00

Pos logit contributions
ocol+0.122
irs+0.103
ait+0.095
andel+0.092
sie+0.089
Neg logit contributions
 owner-0.072
 not-0.070
 still-0.067
 was-0.064
 hurts-0.063
Tokengary
Token ID14849
Feature activation-1.68e+00

Pos logit contributions
ocol+0.191
 Annie+0.170
 rubble+0.146
 hotels+0.145
irs+0.145
Neg logit contributions
uck-0.245
uch-0.233
 still-0.229
 owner-0.226
flower-0.223
Token.
Token ID13
Feature activation+4.09e-01

Pos logit contributions
ocol+0.074
irs+0.066
ait+0.061
year+0.057
andel+0.057
Neg logit contributions
 owner-0.030
 was-0.027
 not-0.026
 hurts-0.025
 still-0.025
Token But
Token ID887
Feature activation+8.23e-01

Pos logit contributions
 owner+0.006
 not+0.006
 hurts+0.006
 still+0.006
 hits+0.005
Neg logit contributions
ocol-0.018
irs-0.015
ait-0.014
andel-0.014
sie-0.014
Token what
Token ID644
Feature activation+6.98e-02

Pos logit contributions
 owner+0.015
 hurts+0.015
zag+0.014
 hits+0.014
 hates+0.014
Neg logit contributions
ocol-0.033
irs-0.027
ait-0.025
sie-0.024
andel-0.024
Token he
Token ID339
Feature activation-2.86e+00

Pos logit contributions
flower+0.001
 owner+0.001
zag+0.001
 hits+0.001
 hurts+0.001
Neg logit contributions
ocol-0.003
irs-0.002
ait-0.002
 Annie-0.002
 pounds-0.002
Tokenipop
Token ID42800
Feature activation-5.76e-01

Pos logit contributions
ocol+0.119
irs+0.106
ait+0.093
andel+0.092
 rubble+0.087
Neg logit contributions
 owner-0.071
 not-0.067
 hurts-0.065
 still-0.064
 remembered-0.062
Token,
Token ID11
Feature activation-1.31e+00

Pos logit contributions
ocol+0.024
irs+0.021
andel+0.019
ait+0.018
sie+0.017
Neg logit contributions
 owner-0.012
 not-0.012
 still-0.011
 was-0.010
 hurts-0.010
Token it
Token ID340
Feature activation-1.70e-01

Pos logit contributions
ocol+0.061
irs+0.054
andel+0.048
ait+0.048
sie+0.048
Neg logit contributions
 owner-0.021
 not-0.021
 still-0.020
 was-0.017
 also-0.017
Token's
Token ID338
Feature activation+6.64e-01

Pos logit contributions
ocol+0.008
irs+0.007
ait+0.007
andel+0.007
sie+0.006
Neg logit contributions
 owner-0.002
 not-0.002
 still-0.002
 hurts-0.002
 hits-0.001
Token a
Token ID257
Feature activation-1.60e+00

Pos logit contributions
 not+0.014
 owner+0.013
 still+0.013
 also+0.012
 only+0.012
Neg logit contributions
ocol-0.027
irs-0.023
ait-0.022
andel-0.021
sie-0.021
Token sav
Token ID6799
Feature activation-7.94e+00

Pos logit contributions
ocol+0.063
irs+0.056
ait+0.050
andel+0.047
sie+0.045
Neg logit contributions
 owner-0.038
 not-0.035
 still-0.034
 was-0.033
 only-0.032
Tokenour
Token ID454
Feature activation+4.69e-01

Pos logit contributions
ocol+0.223
irs+0.217
 rubble+0.180
 Annie+0.173
ait+0.169
Neg logit contributions
 owner-0.207
 hits-0.206
zag-0.201
 head-0.200
 hurts-0.200
Tokeny
Token ID88
Feature activation-6.07e-01

Pos logit contributions
 owner+0.011
 not+0.010
 still+0.010
 hurts+0.010
 hits+0.010
Neg logit contributions
ocol-0.017
irs-0.014
ait-0.013
andel-0.012
sie-0.012
Token l
Token ID300
Feature activation-3.82e+00

Pos logit contributions
ocol+0.024
irs+0.021
ait+0.019
andel+0.018
sie+0.017
Neg logit contributions
 owner-0.013
 not-0.012
 still-0.012
 was-0.012
 hurts-0.012
Tokenoll
Token ID692
Feature activation-3.85e+00

Pos logit contributions
ocol+0.134
irs+0.126
ait+0.108
 hotels+0.104
 rubble+0.104
Neg logit contributions
 owner-0.086
 still-0.082
 not-0.079
 also-0.074
 only-0.074
Tokenipop
Token ID42800
Feature activation-1.37e+00

Pos logit contributions
ocol+0.144
irs+0.129
ait+0.113
andel+0.112
 rubble+0.106
Neg logit contributions
 owner-0.084
 not-0.080
 hurts-0.078
 still-0.077
 remembered-0.074
Token -
Token ID532
Feature activation+1.01e+00

Pos logit contributions
ocol+0.040
irs+0.035
ait+0.032
andel+0.032
sie+0.031
Neg logit contributions
 owner-0.014
 not-0.013
 was-0.013
 still-0.012
 only-0.011
Token a
Token ID257
Feature activation-6.97e-01

Pos logit contributions
 owner+0.019
 not+0.018
 still+0.017
 hurts+0.016
 was+0.016
Neg logit contributions
ocol-0.043
irs-0.036
ait-0.033
andel-0.033
sie-0.032
Token box
Token ID3091
Feature activation-1.49e+00

Pos logit contributions
ocol+0.028
irs+0.024
ait+0.022
andel+0.021
sie+0.021
Neg logit contributions
 owner-0.015
 not-0.014
 still-0.014
 was-0.013
 hurts-0.013
Token of
Token ID286
Feature activation-9.74e-01

Pos logit contributions
ocol+0.059
irs+0.050
ait+0.045
andel+0.044
sie+0.043
Neg logit contributions
 owner-0.032
 not-0.031
 still-0.030
 was-0.029
 hurts-0.028
Token mult
Token ID1963
Feature activation-4.46e+00

Pos logit contributions
ocol+0.037
irs+0.034
ait+0.034
sie+0.032
andel+0.031
Neg logit contributions
 owner-0.020
 was-0.019
 still-0.019
 not-0.018
 only-0.018
Tokenicol
Token ID27045
Feature activation-7.89e+00

Pos logit contributions
ocol+0.147
irs+0.128
ait+0.113
sie+0.112
year+0.112
Neg logit contributions
 owner-0.114
 hits-0.105
 head-0.104
 still-0.103
flower-0.101
Tokenored
Token ID1850
Feature activation-1.14e+00

Pos logit contributions
ocol+0.264
irs+0.224
ait+0.193
andel+0.192
 rubble+0.191
Neg logit contributions
 owner-0.183
 still-0.183
 hits-0.180
 not-0.176
 hurts-0.174
Token bubbles
Token ID25037
Feature activation-7.77e-01

Pos logit contributions
ocol+0.044
irs+0.039
sie+0.036
ait+0.036
inations+0.034
Neg logit contributions
 owner-0.025
 was-0.024
 still-0.021
 not-0.021
's-0.021
Token!
Token ID0
Feature activation-1.24e+00

Pos logit contributions
ocol+0.034
irs+0.028
ait+0.026
andel+0.026
sie+0.025
Neg logit contributions
 owner-0.014
 not-0.013
 still-0.013
 was-0.012
 hurts-0.012
Token
Token ID198
Feature activation-6.59e-01

Pos logit contributions
ocol+0.067
irs+0.057
sie+0.053
inations+0.053
ait+0.053
Neg logit contributions
 owner-0.012
 was-0.010
 still-0.008
 not-0.008
's-0.008
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
ocol+0.037
irs+0.031
ait+0.030
andel+0.029
sie+0.029
Neg logit contributions
 owner-0.005
 not-0.004
 was-0.004
 still-0.004
 also-0.003
Token delicious
Token ID12625
Feature activation-1.64e+00

Pos logit contributions
ocol+0.066
irs+0.059
ait+0.057
uster+0.055
sie+0.054
Neg logit contributions
 owner-0.030
 was-0.026
 still-0.025
 not-0.025
 only-0.024
Token vegetables
Token ID13701
Feature activation-1.24e+00

Pos logit contributions
ocol+0.068
irs+0.065
ait+0.062
uster+0.061
chie+0.059
Neg logit contributions
 was-0.028
 owner-0.028
 and-0.026
's-0.024
 is-0.023
Token and
Token ID290
Feature activation-8.75e-01

Pos logit contributions
ocol+0.057
irs+0.049
ait+0.045
andel+0.044
sie+0.044
Neg logit contributions
 owner-0.019
 not-0.017
 still-0.016
 hurts-0.015
 hits-0.015
Token bright
Token ID6016
Feature activation-1.31e+00

Pos logit contributions
ocol+0.032
irs+0.028
ait+0.025
andel+0.024
uster+0.024
Neg logit contributions
 owner-0.022
 not-0.021
 was-0.021
 still-0.020
 also-0.020
Token-
Token ID12
Feature activation-2.91e+00

Pos logit contributions
ocol+0.055
irs+0.051
ait+0.050
prise+0.047
sie+0.047
Neg logit contributions
 owner-0.021
 was-0.021
flower-0.018
 and-0.018
 still-0.017
Tokencol
Token ID4033
Feature activation-7.75e+00

Pos logit contributions
ocol+0.097
irs+0.079
ait+0.071
uster+0.068
sie+0.067
Neg logit contributions
 owner-0.082
 not-0.073
 was-0.070
flower-0.069
's-0.068
Tokenoured
Token ID8167
Feature activation-2.63e-01

Pos logit contributions
ocol+0.224
irs+0.183
 ages+0.180
sie+0.174
 Annie+0.174
Neg logit contributions
flower-0.185
 hits-0.184
erved-0.183
 owner-0.183
 swung-0.181
Token flowers
Token ID12734
Feature activation-1.34e+00

Pos logit contributions
ocol+0.010
irs+0.010
ait+0.009
uster+0.009
prise+0.009
Neg logit contributions
 owner-0.005
 was-0.005
 and-0.004
 not-0.004
 liked-0.004
Token.
Token ID13
Feature activation+5.28e-01

Pos logit contributions
ocol+0.060
irs+0.051
ait+0.047
andel+0.046
sie+0.045
Neg logit contributions
 owner-0.023
 not-0.021
 still-0.020
 was-0.019
flower-0.018
Token
Token ID220
Feature activation+1.34e+00

Pos logit contributions
 owner+0.007
 not+0.006
 still+0.006
 was+0.006
 also+0.005
Neg logit contributions
ocol-0.026
irs-0.022
ait-0.020
andel-0.020
sie-0.020
Token
Token ID198
Feature activation+6.74e-01

Pos logit contributions
 owner+0.014
 not+0.013
 still+0.012
 hurts+0.010
 was+0.010
Neg logit contributions
ocol-0.067
irs-0.058
ait-0.054
andel-0.053
sie-0.053
Token things
Token ID1243
Feature activation-3.02e+00

Pos logit contributions
ocol+0.014
ait+0.013
irs+0.013
sie+0.012
uster+0.012
Neg logit contributions
 was-0.006
 and-0.005
 is-0.005
 owner-0.005
's-0.005
Tokenâ
Token ID22940
Feature activation-3.40e+00

Pos logit contributions
ocol+0.138
irs+0.118
andel+0.109
ait+0.109
sie+0.104
Neg logit contributions
 owner-0.047
 not-0.046
 still-0.044
 was-0.040
 hurts-0.039
Token
Token ID26391
Feature activation-5.26e-01

Pos logit contributions
ocol+0.122
irs+0.102
ait+0.088
andel+0.087
sie+0.084
Neg logit contributions
 owner-0.083
 not-0.079
 still-0.078
 hurts-0.076
zag-0.075
Token
Token ID447
Feature activation-4.16e+00

Pos logit contributions
ocol+0.023
irs+0.019
andel+0.017
sie+0.017
ait+0.017
Neg logit contributions
 owner-0.010
 not-0.010
 was-0.009
 still-0.009
zag-0.008
Token
Token ID251
Feature activation-8.28e-01

Pos logit contributions
ocol+0.166
irs+0.138
ait+0.127
andel+0.126
sie+0.121
Neg logit contributions
 owner-0.084
 still-0.080
 not-0.078
 was-0.076
 hurts-0.075
Tokencol
Token ID4033
Feature activation-7.57e+00

Pos logit contributions
ocol+0.038
irs+0.033
ait+0.031
andel+0.029
sie+0.029
Neg logit contributions
 was-0.013
 still-0.012
 owner-0.012
 not-0.012
 felt-0.011
Tokenouring
Token ID21823
Feature activation+4.24e-01

Pos logit contributions
ocol+0.236
 rubble+0.188
irs+0.187
 ages+0.178
 hotels+0.174
Neg logit contributions
zag-0.172
uck-0.169
 still-0.168
flower-0.167
 swung-0.165
Token books
Token ID3835
Feature activation-2.08e+00

Pos logit contributions
 not+0.007
 owner+0.007
 was+0.007
 still+0.007
 also+0.006
Neg logit contributions
ocol-0.019
irs-0.016
ait-0.015
andel-0.014
prise-0.014
Token,
Token ID11
Feature activation-1.12e+00

Pos logit contributions
ocol+0.099
irs+0.086
ait+0.079
andel+0.078
sie+0.077
Neg logit contributions
 owner-0.027
 not-0.025
 still-0.023
 hurts-0.021
 was-0.021
Token stickers
Token ID28568
Feature activation-5.40e-01

Pos logit contributions
ocol+0.049
irs+0.042
ait+0.038
andel+0.038
sie+0.037
Neg logit contributions
 owner-0.019
 not-0.017
 still-0.016
 hurts-0.016
 hits-0.016
Token and
Token ID290
Feature activation-2.21e-01

Pos logit contributions
ocol+0.026
irs+0.023
ait+0.021
andel+0.021
sie+0.021
Neg logit contributions
 owner-0.006
 not-0.005
 still-0.005
 hurts-0.005
 hits-0.005
Token was
Token ID373
Feature activation+6.17e-01

Pos logit contributions
ocol+0.023
sie+0.020
irs+0.019
ait+0.019
 Annie+0.019
Neg logit contributions
 hurts-0.007
 owner-0.007
 hits-0.007
 not-0.006
ses-0.006
Token known
Token ID1900
Feature activation-1.77e+00

Pos logit contributions
 owner+0.012
 hurts+0.011
 hits+0.011
 not+0.010
zag+0.010
Neg logit contributions
ocol-0.025
irs-0.021
ait-0.019
sie-0.019
andel-0.019
Token as
Token ID355
Feature activation-3.19e+00

Pos logit contributions
ocol+0.082
irs+0.074
ait+0.067
ann+0.064
inations+0.064
Neg logit contributions
 not-0.030
 still-0.027
 owner-0.027
 only-0.024
 never-0.023
Token the
Token ID262
Feature activation-1.04e+00

Pos logit contributions
ocol+0.147
irs+0.130
ait+0.120
andel+0.117
uster+0.114
Neg logit contributions
 not-0.051
 owner-0.046
 still-0.045
 was-0.043
 only-0.043
Token powerful
Token ID3665
Feature activation+9.41e-01

Pos logit contributions
ocol+0.045
irs+0.041
ait+0.036
andel+0.034
inations+0.033
Neg logit contributions
 owner-0.021
 still-0.019
 only-0.018
 not-0.018
 also-0.017
Token sav
Token ID6799
Feature activation-7.57e+00

Pos logit contributions
 owner+0.021
 not+0.019
 still+0.019
 was+0.018
 hurts+0.018
Neg logit contributions
ocol-0.036
irs-0.032
ait-0.028
andel-0.027
sie-0.026
Tokeniour
Token ID49439
Feature activation-1.06e+00

Pos logit contributions
ocol+0.233
irs+0.212
ait+0.177
 rubble+0.175
 Annie+0.173
Neg logit contributions
 owner-0.187
 not-0.184
 hits-0.183
 still-0.183
zag-0.179
Token of
Token ID286
Feature activation-1.02e+00

Pos logit contributions
ocol+0.040
irs+0.034
ait+0.030
andel+0.029
sie+0.029
Neg logit contributions
 owner-0.025
 not-0.023
 still-0.023
 was-0.022
zag-0.022
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
ocol+0.043
irs+0.038
ait+0.036
andel+0.034
uster+0.034
Neg logit contributions
 not-0.018
 owner-0.018
 still-0.017
 only-0.016
 was-0.016
Token forest
Token ID8222
Feature activation-5.97e-01

Pos logit contributions
ocol+0.053
irs+0.047
ait+0.043
andel+0.040
uster+0.039
Neg logit contributions
 owner-0.031
 still-0.029
 not-0.028
 was-0.027
 only-0.027
Token.
Token ID13
Feature activation-8.77e-01

Pos logit contributions
ocol+0.026
irs+0.023
ait+0.021
andel+0.020
sie+0.020
Neg logit contributions
 owner-0.010
 not-0.009
 still-0.009
 was-0.009
 hurts-0.008
Token and
Token ID290
Feature activation-7.39e-01

Pos logit contributions
ocol+0.074
irs+0.064
ait+0.059
andel+0.058
sie+0.057
Neg logit contributions
 owner-0.021
 hurts-0.019
 not-0.019
 hits-0.018
zag-0.017
Token saw
Token ID2497
Feature activation-1.15e+00

Pos logit contributions
ocol+0.035
irs+0.030
ait+0.028
andel+0.028
sie+0.027
Neg logit contributions
 owner-0.010
 not-0.009
 still-0.009
 hurts-0.008
 remembered-0.008
Token a
Token ID257
Feature activation-1.42e+00

Pos logit contributions
ocol+0.051
irs+0.043
ait+0.040
andel+0.039
sie+0.039
Neg logit contributions
 owner-0.019
 not-0.018
 still-0.017
 hurts-0.016
 was-0.016
Token magical
Token ID10883
Feature activation-1.54e+00

Pos logit contributions
ocol+0.061
irs+0.053
ait+0.048
andel+0.046
sie+0.045
Neg logit contributions
 owner-0.029
 not-0.026
 still-0.025
 was-0.024
 remembered-0.023
Token fair
Token ID3148
Feature activation-7.39e-01

Pos logit contributions
ocol+0.061
irs+0.055
ait+0.049
andel+0.045
sie+0.044
Neg logit contributions
 owner-0.034
 still-0.030
 not-0.030
 was-0.030
flower-0.028
Tokenyt
Token ID20760
Feature activation-7.51e+00

Pos logit contributions
ocol+0.032
irs+0.028
ait+0.025
andel+0.023
year+0.023
Neg logit contributions
 owner-0.015
 not-0.013
 still-0.013
 was-0.012
flower-0.012
Tokenale
Token ID1000
Feature activation-6.72e-01

Pos logit contributions
ocol+0.241
irs+0.202
sie+0.171
ait+0.171
 Annie+0.170
Neg logit contributions
 owner-0.201
 still-0.182
 not-0.182
 hits-0.182
zag-0.181
Token creature
Token ID7185
Feature activation-1.83e+00

Pos logit contributions
ocol+0.029
irs+0.026
ait+0.024
andel+0.022
sie+0.022
Neg logit contributions
 owner-0.013
 not-0.011
 still-0.011
 was-0.011
 also-0.010
Token called
Token ID1444
Feature activation-5.00e+00

Pos logit contributions
ocol+0.079
irs+0.068
ait+0.063
andel+0.061
sie+0.060
Neg logit contributions
 owner-0.032
 not-0.030
 still-0.029
 was-0.028
 hurts-0.027
Token a
Token ID257
Feature activation-3.10e+00

Pos logit contributions
ocol+0.210
irs+0.183
inations+0.173
ait+0.170
sie+0.161
Neg logit contributions
 owner-0.095
 not-0.092
 was-0.083
 only-0.079
 still-0.079
Token n
Token ID299
Feature activation-3.15e+00

Pos logit contributions
ocol+0.135
irs+0.120
ait+0.111
andel+0.102
sie+0.100
Neg logit contributions
 owner-0.064
 was-0.055
 not-0.054
 still-0.053
 also-0.050
Token for
Token ID329
Feature activation-2.20e+00

Pos logit contributions
ocol+0.115
irs+0.101
andel+0.090
ait+0.089
sie+0.087
Neg logit contributions
 owner-0.046
 not-0.042
 still-0.041
 was-0.039
 only-0.036
Token him
Token ID683
Feature activation-6.74e-01

Pos logit contributions
ocol+0.097
irs+0.085
ait+0.082
andel+0.082
sie+0.082
Neg logit contributions
 not-0.038
 owner-0.036
 still-0.035
 only-0.032
 was-0.031
Token -
Token ID532
Feature activation+1.18e+00

Pos logit contributions
ocol+0.031
irs+0.027
ait+0.024
andel+0.024
sie+0.024
Neg logit contributions
 owner-0.011
 not-0.010
 still-0.010
 was-0.009
 hurts-0.008
Token a
Token ID257
Feature activation-6.54e-01

Pos logit contributions
 owner+0.021
 not+0.020
 still+0.019
 was+0.018
 also+0.017
Neg logit contributions
ocol-0.051
irs-0.044
ait-0.040
andel-0.040
sie-0.039
Token little
Token ID1310
Feature activation-1.81e+00

Pos logit contributions
ocol+0.026
irs+0.024
ait+0.021
andel+0.020
sie+0.019
Neg logit contributions
 owner-0.015
 still-0.014
 not-0.014
 was-0.013
 remembered-0.012
Token su
Token ID424
Feature activation-7.51e+00

Pos logit contributions
ocol+0.079
irs+0.072
ait+0.062
andel+0.060
sie+0.059
Neg logit contributions
 owner-0.034
 still-0.030
 not-0.029
 was-0.028
 hurts-0.028
Tokengary
Token ID14849
Feature activation-6.10e-01

Pos logit contributions
ocol+0.174
 Annie+0.141
irs+0.137
 hotels+0.131
 props+0.129
Neg logit contributions
uck-0.242
uch-0.219
 owner-0.219
Because-0.213
 still-0.212
Token treat
Token ID2190
Feature activation-1.09e+00

Pos logit contributions
ocol+0.025
irs+0.024
ait+0.021
sie+0.020
inations+0.019
Neg logit contributions
 owner-0.012
 was-0.011
 still-0.010
 not-0.010
 hurts-0.010
Token.
Token ID13
Feature activation-8.11e-01

Pos logit contributions
ocol+0.046
irs+0.040
andel+0.036
ait+0.035
sie+0.035
Neg logit contributions
 owner-0.021
 not-0.020
 was-0.019
 still-0.019
 only-0.017
Token<|endoftext|>
Token ID50256
Feature activation-2.01e+00

Pos logit contributions
ocol+0.040
irs+0.035
ait+0.033
sie+0.032
andel+0.032
Neg logit contributions
 owner-0.009
 not-0.008
 still-0.008
 was-0.007
 hurts-0.007
TokenOnce
Token ID7454
Feature activation+8.86e-02

Pos logit contributions
ocol+0.096
irs+0.081
ait+0.077
andel+0.076
sie+0.074
Neg logit contributions
 was-0.029
 owner-0.027
 still-0.025
 not-0.023
 hurts-0.022
Token the
Token ID262
Feature activation-4.17e-01

Pos logit contributions
ocol+0.065
irs+0.056
ait+0.052
andel+0.051
sie+0.050
Neg logit contributions
 owner-0.025
 not-0.025
 still-0.024
 was-0.022
 only-0.021
Token paper
Token ID3348
Feature activation-1.55e-01

Pos logit contributions
ocol+0.017
irs+0.015
ait+0.014
andel+0.013
year+0.013
Neg logit contributions
 owner-0.009
 not-0.008
 still-0.008
 only-0.007
 head-0.007
Token became
Token ID2627
Feature activation-5.96e-01

Pos logit contributions
ocol+0.007
irs+0.006
ait+0.006
sie+0.005
andel+0.005
Neg logit contributions
 owner-0.002
 not-0.002
 hurts-0.002
 hits-0.002
 still-0.002
Token a
Token ID257
Feature activation-2.44e+00

Pos logit contributions
ocol+0.026
irs+0.023
ait+0.021
andel+0.020
sie+0.020
Neg logit contributions
 still-0.011
 owner-0.011
 not-0.011
 remembered-0.010
 also-0.010
Token 3
Token ID513
Feature activation-3.63e-01

Pos logit contributions
ocol+0.102
irs+0.090
ait+0.081
sie+0.075
andel+0.074
Neg logit contributions
 owner-0.054
 still-0.050
 not-0.049
 was-0.047
 only-0.045
TokenD
Token ID35
Feature activation-7.43e+00

Pos logit contributions
ocol+0.016
irs+0.015
ait+0.013
uster+0.013
andel+0.013
Neg logit contributions
 owner-0.006
 was-0.006
 not-0.005
's-0.005
 still-0.005
Token cube
Token ID23441
Feature activation-5.98e-01

Pos logit contributions
ocol+0.250
irs+0.211
 rubble+0.200
 anticipation+0.192
inations+0.187
Neg logit contributions
 owner-0.172
zag-0.170
uck-0.165
flower-0.161
 still-0.158
Token!
Token ID0
Feature activation-1.65e+00

Pos logit contributions
ocol+0.025
irs+0.021
ait+0.019
andel+0.019
sie+0.018
Neg logit contributions
 owner-0.012
 not-0.011
 still-0.011
 was-0.010
 hurts-0.010
Token
Token ID198
Feature activation-7.50e-01

Pos logit contributions
ocol+0.086
irs+0.074
sie+0.071
ait+0.069
prise+0.068
Neg logit contributions
 owner-0.017
 was-0.012
 still-0.012
 not-0.012
 hits-0.010
Token
Token ID198
Feature activation-1.52e+00

Pos logit contributions
ocol+0.042
irs+0.035
ait+0.034
sie+0.034
andel+0.033
Neg logit contributions
 owner-0.005
 not-0.004
 was-0.004
 still-0.004
 also-0.003
TokenThe
Token ID464
Feature activation+8.51e-01

Pos logit contributions
ocol+0.073
irs+0.062
ait+0.059
sie+0.057
andel+0.056
Neg logit contributions
 owner-0.021
 not-0.018
 still-0.018
 was-0.017
 also-0.016
Token with
Token ID351
Feature activation-1.82e-01

Pos logit contributions
 owner+0.030
 not+0.028
 still+0.027
 remembered+0.024
 also+0.023
Neg logit contributions
ocol-0.068
irs-0.059
ait-0.054
andel-0.052
sie-0.051
Token her
Token ID607
Feature activation+1.26e+00

Pos logit contributions
ocol+0.008
irs+0.007
ait+0.006
andel+0.006
sie+0.006
Neg logit contributions
 owner-0.003
 not-0.003
 still-0.003
 only-0.003
 was-0.003
Token friends
Token ID2460
Feature activation+9.24e-01

Pos logit contributions
 owner+0.018
 not+0.017
 hurts+0.016
 still+0.016
 hits+0.016
Neg logit contributions
ocol-0.056
irs-0.048
ait-0.045
andel-0.044
sie-0.043
Token in
Token ID287
Feature activation+1.24e+00

Pos logit contributions
 owner+0.016
 not+0.014
 still+0.014
 was+0.013
 hurts+0.013
Neg logit contributions
ocol-0.041
irs-0.035
ait-0.032
andel-0.032
sie-0.031
Token the
Token ID262
Feature activation-5.51e-01

Pos logit contributions
 owner+0.020
 not+0.019
 still+0.018
 also+0.017
 only+0.017
Neg logit contributions
ocol-0.056
irs-0.049
ait-0.046
andel-0.045
sie-0.044
Token sav
Token ID6799
Feature activation-7.40e+00

Pos logit contributions
ocol+0.024
irs+0.021
ait+0.019
andel+0.018
sie+0.018
Neg logit contributions
 owner-0.010
 not-0.009
 still-0.009
 hurts-0.009
 hits-0.008
Tokenanna
Token ID7697
Feature activation-3.22e-01

Pos logit contributions
ocol+0.190
irs+0.157
ait+0.127
 Annie+0.127
 rubble+0.126
Neg logit contributions
 owner-0.235
 not-0.226
 hits-0.225
 still-0.223
zag-0.222
Token.
Token ID13
Feature activation+6.22e-01

Pos logit contributions
ocol+0.013
irs+0.011
ait+0.010
andel+0.010
sie+0.010
Neg logit contributions
 owner-0.006
 not-0.006
 still-0.005
 hurts-0.005
 hits-0.005
Token They
Token ID1119
Feature activation+1.57e-02

Pos logit contributions
 owner+0.009
 not+0.008
 still+0.008
 was+0.007
 hurts+0.007
Neg logit contributions
ocol-0.029
irs-0.025
ait-0.023
andel-0.023
sie-0.023
Token are
Token ID389
Feature activation+8.56e-01

Pos logit contributions
 owner+0.000
 not+0.000
 still+0.000
 also+0.000
 only+0.000
Neg logit contributions
ocol-0.001
irs-0.001
ait-0.001
andel-0.001
sie-0.001
Token all
Token ID477
Feature activation+3.69e-01

Pos logit contributions
 owner+0.016
 not+0.015
 still+0.014
 hurts+0.014
 hits+0.014
Neg logit contributions
ocol-0.036
irs-0.030
ait-0.028
andel-0.027
sie-0.027
Token,
Token ID11
Feature activation-1.60e+00

Pos logit contributions
ocol+0.044
irs+0.037
ait+0.035
sie+0.034
andel+0.034
Neg logit contributions
 owner-0.014
 hurts-0.013
 not-0.012
 hits-0.012
zag-0.012
Token with
Token ID351
Feature activation-2.11e-01

Pos logit contributions
ocol+0.056
irs+0.045
andel+0.041
 ages+0.040
 Annie+0.040
Neg logit contributions
 owner-0.036
zag-0.036
 hurts-0.033
flower-0.033
 hits-0.033
Token all
Token ID477
Feature activation-2.03e-01

Pos logit contributions
ocol+0.008
irs+0.007
ait+0.006
sie+0.006
andel+0.006
Neg logit contributions
 owner-0.005
 not-0.005
 still-0.005
 was-0.004
 only-0.004
Token its
Token ID663
Feature activation-1.43e-01

Pos logit contributions
ocol+0.008
irs+0.007
ait+0.006
andel+0.006
sie+0.006
Neg logit contributions
 owner-0.004
 not-0.004
 still-0.004
 was-0.004
 also-0.004
Token different
Token ID1180
Feature activation+3.66e-01

Pos logit contributions
ocol+0.005
irs+0.005
ait+0.004
sie+0.004
andel+0.004
Neg logit contributions
 owner-0.003
 not-0.003
 still-0.003
 was-0.003
 hurts-0.003
Tokencol
Token ID4033
Feature activation-7.24e+00

Pos logit contributions
 owner+0.007
 was+0.007
 not+0.007
 still+0.006
 hurts+0.006
Neg logit contributions
ocol-0.015
irs-0.013
ait-0.012
sie-0.011
andel-0.011
Tokenours
Token ID4662
Feature activation-3.10e-01

Pos logit contributions
ocol+0.207
irs+0.172
sie+0.170
 rubble+0.169
 Annie+0.169
Neg logit contributions
 hits-0.168
 owner-0.166
flower-0.166
 still-0.163
erved-0.163
Token,
Token ID11
Feature activation-1.57e+00

Pos logit contributions
ocol+0.014
irs+0.012
ait+0.012
andel+0.011
sie+0.011
Neg logit contributions
 owner-0.004
 not-0.004
 still-0.004
 was-0.004
 hurts-0.004
Token shapes
Token ID15268
Feature activation+9.24e-01

Pos logit contributions
ocol+0.060
irs+0.049
ait+0.044
andel+0.044
sie+0.042
Neg logit contributions
 owner-0.034
zag-0.032
 hurts-0.031
 not-0.030
 hits-0.030
Token and
Token ID290
Feature activation-5.10e-01

Pos logit contributions
 owner+0.014
 not+0.013
 hurts+0.012
 still+0.012
 hits+0.012
Neg logit contributions
ocol-0.041
irs-0.035
ait-0.032
andel-0.032
sie-0.031
Token textures
Token ID20028
Feature activation+1.74e-01

Pos logit contributions
ocol+0.019
irs+0.015
ait+0.014
andel+0.014
sie+0.013
Neg logit contributions
 owner-0.012
 not-0.012
 still-0.011
 hurts-0.011
 was-0.011
Token children
Token ID1751
Feature activation+5.05e-01

Pos logit contributions
 owner+0.009
 not+0.009
 still+0.008
 was+0.008
 also+0.008
Neg logit contributions
ocol-0.017
irs-0.014
ait-0.013
andel-0.013
sie-0.012
Token running
Token ID2491
Feature activation+4.86e-01

Pos logit contributions
 owner+0.008
 not+0.007
 still+0.007
 hurts+0.007
 was+0.007
Neg logit contributions
ocol-0.023
irs-0.019
ait-0.018
andel-0.017
sie-0.017
Token around
Token ID1088
Feature activation+5.87e-01

Pos logit contributions
 owner+0.008
 not+0.007
 was+0.007
 still+0.007
 hits+0.006
Neg logit contributions
ocol-0.023
irs-0.019
ait-0.018
andel-0.017
prise-0.017
Token,
Token ID11
Feature activation-9.07e-01

Pos logit contributions
 was+0.005
 owner+0.005
 not+0.005
 still+0.005
 only+0.004
Neg logit contributions
ocol-0.031
irs-0.028
ait-0.026
andel-0.026
sie-0.025
Token families
Token ID4172
Feature activation-1.26e-01

Pos logit contributions
ocol+0.034
irs+0.029
ait+0.026
 Annie+0.025
sie+0.025
Neg logit contributions
 owner-0.018
 hurts-0.017
 hits-0.016
zag-0.016
 not-0.016
Token pic
Token ID8301
Feature activation-7.23e+00

Pos logit contributions
ocol+0.006
irs+0.005
ait+0.005
andel+0.005
sie+0.005
Neg logit contributions
 owner-0.002
 not-0.001
 still-0.001
 hurts-0.001
 hits-0.001
Tokenn
Token ID77
Feature activation-8.50e-01

Pos logit contributions
ocol+0.278
irs+0.223
ait+0.209
andel+0.206
sie+0.198
Neg logit contributions
 not-0.160
 owner-0.158
 still-0.149
zag-0.146
 was-0.141
Tokenicking
Token ID7958
Feature activation-7.79e-01

Pos logit contributions
ocol+0.029
irs+0.027
ait+0.024
andel+0.022
inations+0.021
Neg logit contributions
 owner-0.020
 hurts-0.019
 hits-0.018
tr-0.017
 not-0.017
Token,
Token ID11
Feature activation-1.88e+00

Pos logit contributions
ocol+0.036
irs+0.031
ait+0.029
andel+0.028
sie+0.028
Neg logit contributions
 owner-0.011
 not-0.010
 still-0.010
 was-0.009
 hurts-0.009
Token couples
Token ID11886
Feature activation-2.21e+00

Pos logit contributions
ocol+0.083
irs+0.071
ait+0.066
andel+0.064
sie+0.063
Neg logit contributions
 owner-0.029
 not-0.026
 hurts-0.025
 still-0.025
 hits-0.024
Token st
Token ID336
Feature activation-2.09e+00

Pos logit contributions
ocol+0.102
irs+0.088
ait+0.081
andel+0.080
sie+0.078
Neg logit contributions
 owner-0.033
 not-0.030
 still-0.029
 was-0.027
 hurts-0.026
Token was
Token ID373
Feature activation+1.58e-01

Pos logit contributions
ocol+0.071
irs+0.061
ait+0.058
sie+0.057
andel+0.056
Neg logit contributions
 owner-0.015
 not-0.012
 hurts-0.011
 hits-0.011
zag-0.011
Token walking
Token ID6155
Feature activation+3.91e-02

Pos logit contributions
 owner+0.003
 not+0.003
 still+0.003
 hurts+0.003
 remembered+0.003
Neg logit contributions
ocol-0.007
irs-0.006
ait-0.005
andel-0.005
sie-0.005
Token through
Token ID832
Feature activation-1.17e-01

Pos logit contributions
 owner+0.001
 still+0.001
 not+0.001
 was+0.001
 only+0.000
Neg logit contributions
ocol-0.002
irs-0.002
ait-0.001
andel-0.001
inations-0.001
Token a
Token ID257
Feature activation-1.93e+00

Pos logit contributions
ocol+0.006
irs+0.005
ait+0.005
uster+0.005
andel+0.004
Neg logit contributions
 was-0.002
 still-0.001
 not-0.001
 owner-0.001
 only-0.001
Token fair
Token ID3148
Feature activation-6.65e-01

Pos logit contributions
ocol+0.089
irs+0.076
ait+0.069
uster+0.064
andel+0.064
Neg logit contributions
 owner-0.038
 still-0.037
 was-0.035
's-0.034
 also-0.032
Tokenyt
Token ID20760
Feature activation-7.20e+00

Pos logit contributions
ocol+0.029
irs+0.025
ait+0.022
year+0.021
andel+0.020
Neg logit contributions
 owner-0.013
 not-0.012
 still-0.012
 was-0.011
zag-0.011
Tokenale
Token ID1000
Feature activation-9.53e-01

Pos logit contributions
ocol+0.230
irs+0.191
 Annie+0.160
ait+0.159
sie+0.158
Neg logit contributions
 owner-0.196
zag-0.177
 still-0.176
 not-0.176
flower-0.174
Token.
Token ID13
Feature activation-7.86e-01

Pos logit contributions
ocol+0.040
irs+0.035
ait+0.031
andel+0.031
year+0.030
Neg logit contributions
 owner-0.018
 still-0.017
 not-0.016
 was-0.016
's-0.015
Token She
Token ID1375
Feature activation-8.82e-01

Pos logit contributions
ocol+0.036
irs+0.031
ait+0.028
sie+0.028
andel+0.027
Neg logit contributions
 owner-0.013
 not-0.011
 still-0.011
 was-0.011
 only-0.010
Token fell
Token ID3214
Feature activation+1.62e+00

Pos logit contributions
ocol+0.036
irs+0.032
ait+0.031
sie+0.031
 Annie+0.030
Neg logit contributions
 owner-0.012
 hurts-0.012
 hits-0.011
zag-0.011
tr-0.010
Token asleep
Token ID16039
Feature activation-5.52e-01

Pos logit contributions
 owner+0.056
 not+0.053
 hurts+0.052
 still+0.051
 hits+0.051
Neg logit contributions
ocol-0.039
irs-0.030
ait-0.026
andel-0.025
sie-0.024
Token found
Token ID1043
Feature activation-6.56e-02

Pos logit contributions
ocol+0.027
irs+0.024
ait+0.022
sie+0.021
andel+0.021
Neg logit contributions
 owner-0.009
 not-0.009
 hurts-0.008
zag-0.008
 still-0.008
Token it
Token ID340
Feature activation-3.97e-01

Pos logit contributions
ocol+0.003
irs+0.003
ait+0.003
andel+0.002
sie+0.002
Neg logit contributions
 owner-0.001
 not-0.001
 still-0.001
 was-0.001
 only-0.001
Token was
Token ID373
Feature activation+9.01e-02

Pos logit contributions
ocol+0.017
irs+0.015
ait+0.013
sie+0.013
 Annie+0.013
Neg logit contributions
 owner-0.006
 hurts-0.005
 hits-0.005
 not-0.005
flower-0.005
Token all
Token ID477
Feature activation-4.69e-01

Pos logit contributions
 owner+0.002
 not+0.002
 still+0.002
 hurts+0.002
 hits+0.002
Neg logit contributions
ocol-0.004
irs-0.003
ait-0.003
andel-0.003
sie-0.003
Token strawberry
Token ID41236
Feature activation-1.65e+00

Pos logit contributions
ocol+0.020
irs+0.017
ait+0.016
andel+0.015
sie+0.015
Neg logit contributions
 owner-0.008
 not-0.008
 still-0.007
 hurts-0.007
 hits-0.007
Token flav
Token ID10525
Feature activation-7.18e+00

Pos logit contributions
ocol+0.059
irs+0.052
ait+0.045
andel+0.045
uster+0.044
Neg logit contributions
 owner-0.042
 was-0.040
 still-0.039
 not-0.039
flower-0.038
Tokenoured
Token ID8167
Feature activation-1.29e+00

Pos logit contributions
ocol+0.223
irs+0.183
ait+0.157
andel+0.155
sie+0.153
Neg logit contributions
 still-0.198
 owner-0.196
 not-0.187
flower-0.181
 hits-0.181
Token,
Token ID11
Feature activation-1.94e+00

Pos logit contributions
ocol+0.058
irs+0.053
ait+0.049
andel+0.047
sie+0.046
Neg logit contributions
 owner-0.020
 not-0.019
 was-0.019
 still-0.019
 only-0.016
Token his
Token ID465
Feature activation+6.99e-01

Pos logit contributions
ocol+0.080
irs+0.066
ait+0.060
andel+0.059
 Annie+0.058
Neg logit contributions
 owner-0.034
zag-0.031
 hurts-0.031
 hits-0.030
 not-0.029
Token favourite
Token ID12507
Feature activation+6.23e-01

Pos logit contributions
 owner+0.013
 not+0.012
 still+0.012
 hurts+0.011
 was+0.011
Neg logit contributions
ocol-0.029
irs-0.026
ait-0.023
andel-0.023
sie-0.023
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
 owner+0.012
 not+0.011
 still+0.011
 was+0.011
 hurts+0.011
Neg logit contributions
ocol-0.026
irs-0.022
ait-0.020
andel-0.020
sie-0.019
Token took
Token ID1718
Feature activation-9.55e-01

Pos logit contributions
 owner+0.006
 not+0.005
zag+0.005
 hurts+0.005
flower+0.005
Neg logit contributions
ocol-0.017
irs-0.015
ait-0.014
sie-0.014
andel-0.013
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
ocol+0.045
irs+0.038
inations+0.037
ait+0.037
sie+0.036
Neg logit contributions
 owner-0.013
 not-0.013
 only-0.012
 still-0.012
 was-0.011
Token bike
Token ID7161
Feature activation+1.40e+00

Pos logit contributions
 owner+0.021
 not+0.020
 still+0.019
 hurts+0.018
 hits+0.017
Neg logit contributions
ocol-0.059
irs-0.051
ait-0.047
andel-0.046
sie-0.045
Token out
Token ID503
Feature activation-1.35e+00

Pos logit contributions
 owner+0.021
 not+0.020
 hurts+0.019
 remembered+0.019
 still+0.019
Neg logit contributions
ocol-0.060
irs-0.052
ait-0.049
andel-0.047
sie-0.046
Token and
Token ID290
Feature activation+2.68e-01

Pos logit contributions
ocol+0.058
irs+0.049
ait+0.044
sie+0.044
andel+0.043
Neg logit contributions
 owner-0.026
 not-0.025
 still-0.024
 was-0.023
 hurts-0.022
Token tried
Token ID3088
Feature activation+3.22e+00

Pos logit contributions
 owner+0.004
zag+0.004
 not+0.004
 hurts+0.004
flower+0.004
Neg logit contributions
ocol-0.011
irs-0.010
ait-0.009
sie-0.009
 Annie-0.009
Token to
Token ID284
Feature activation+6.08e-01

Pos logit contributions
 owner+0.054
 not+0.048
 hurts+0.048
 still+0.047
 hits+0.047
Neg logit contributions
ocol-0.136
irs-0.118
ait-0.107
andel-0.104
sie-0.102
Token pedal
Token ID26667
Feature activation+2.44e+00

Pos logit contributions
 owner+0.012
 hurts+0.011
flower+0.011
 not+0.011
 hits+0.011
Neg logit contributions
ocol-0.023
irs-0.020
ait-0.018
andel-0.017
sie-0.017
Token.
Token ID13
Feature activation+1.77e-01

Pos logit contributions
 owner+0.048
 not+0.045
 still+0.044
 hurts+0.042
 hits+0.041
Neg logit contributions
ocol-0.100
irs-0.085
ait-0.077
andel-0.075
sie-0.074
Token But
Token ID887
Feature activation+6.05e-01

Pos logit contributions
 owner+0.003
 not+0.003
 hurts+0.002
flower+0.002
 still+0.002
Neg logit contributions
ocol-0.008
irs-0.007
ait-0.006
andel-0.006
sie-0.006
Token the
Token ID262
Feature activation+1.83e+00

Pos logit contributions
 owner+0.013
 hurts+0.012
zag+0.012
flower+0.012
 hits+0.012
Neg logit contributions
ocol-0.023
irs-0.019
ait-0.017
sie-0.016
 Annie-0.016
Token's
Token ID338
Feature activation-1.45e+00

Pos logit contributions
ocol+0.008
irs+0.007
ait+0.006
andel+0.006
sie+0.006
Neg logit contributions
 owner-0.003
 not-0.003
 still-0.003
 hurts-0.003
 hits-0.003
Token feathers
Token ID27400
Feature activation-5.85e-01

Pos logit contributions
ocol+0.060
irs+0.054
ait+0.048
andel+0.046
sie+0.046
Neg logit contributions
 owner-0.030
 not-0.027
 still-0.026
 hurts-0.024
 was-0.023
Token.
Token ID13
Feature activation-8.15e-01

Pos logit contributions
ocol+0.023
irs+0.019
ait+0.017
andel+0.017
sie+0.017
Neg logit contributions
 owner-0.012
 not-0.011
 hits-0.011
 hurts-0.011
 still-0.010
Token He
Token ID679
Feature activation+1.15e-01

Pos logit contributions
ocol+0.032
irs+0.028
ait+0.025
 Annie+0.024
andel+0.024
Neg logit contributions
 owner-0.015
 hurts-0.014
 not-0.014
zag-0.014
flower-0.014
Token realized
Token ID6939
Feature activation+5.24e-01

Pos logit contributions
 owner+0.002
zag+0.001
 hurts+0.001
tr+0.001
 hits+0.001
Neg logit contributions
ocol-0.005
irs-0.004
sie-0.004
ait-0.004
 Annie-0.004
Token that
Token ID326
Feature activation+2.89e+00

Pos logit contributions
 owner+0.007
 not+0.006
 still+0.006
 hurts+0.005
 was+0.005
Neg logit contributions
ocol-0.025
irs-0.022
ait-0.021
andel-0.020
sie-0.020
Token sometimes
Token ID3360
Feature activation+2.28e+00

Pos logit contributions
 owner+0.060
zag+0.058
 hits+0.054
 hurts+0.054
tr+0.054
Neg logit contributions
ocol-0.110
irs-0.090
ait-0.080
 Annie-0.079
sie-0.078
Token it
Token ID340
Feature activation+2.92e-01

Pos logit contributions
 owner+0.046
 not+0.042
 still+0.041
 hurts+0.040
zag+0.040
Neg logit contributions
ocol-0.091
irs-0.077
ait-0.070
andel-0.068
sie-0.067
Token takes
Token ID2753
Feature activation-1.01e+00

Pos logit contributions
 owner+0.004
tr+0.003
zag+0.003
flower+0.003
burn+0.003
Neg logit contributions
ocol-0.012
irs-0.011
sie-0.010
ait-0.010
 Annie-0.010
Token only
Token ID691
Feature activation+1.60e+00

Pos logit contributions
ocol+0.041
irs+0.035
ait+0.033
andel+0.031
sie+0.030
Neg logit contributions
 owner-0.021
 not-0.020
 still-0.020
 was-0.019
 hurts-0.019
Token a
Token ID257
Feature activation-2.09e-01

Pos logit contributions
 owner+0.032
 not+0.029
 still+0.028
 hurts+0.028
 hits+0.027
Neg logit contributions
ocol-0.064
irs-0.054
ait-0.049
andel-0.048
sie-0.047
Token do
Token ID466
Feature activation-7.32e-01

Pos logit contributions
ocol+0.090
irs+0.077
ait+0.071
andel+0.070
sie+0.068
Neg logit contributions
 owner-0.036
 not-0.034
 still-0.033
 hurts-0.031
 was-0.030
Token.
Token ID13
Feature activation+8.57e-01

Pos logit contributions
ocol+0.032
irs+0.028
ait+0.026
andel+0.025
sie+0.025
Neg logit contributions
 owner-0.012
 not-0.012
 still-0.011
 was-0.011
 hurts-0.010
Token He
Token ID679
Feature activation+4.09e-01

Pos logit contributions
 owner+0.012
 not+0.011
 still+0.010
 hurts+0.009
 was+0.009
Neg logit contributions
ocol-0.041
irs-0.035
ait-0.032
andel-0.032
sie-0.032
Token was
Token ID373
Feature activation+1.73e+00

Pos logit contributions
 owner+0.006
 not+0.005
 hurts+0.005
 hits+0.005
zag+0.005
Neg logit contributions
ocol-0.018
irs-0.015
ait-0.014
sie-0.014
andel-0.014
Token so
Token ID523
Feature activation+6.55e-01

Pos logit contributions
 owner+0.034
 hurts+0.031
flower+0.031
zag+0.030
 hits+0.030
Neg logit contributions
ocol-0.068
irs-0.056
ait-0.052
andel-0.051
sie-0.050
Token bored
Token ID17533
Feature activation+2.46e+00

Pos logit contributions
 owner+0.013
 not+0.012
 hurts+0.012
flower+0.012
 hits+0.012
Neg logit contributions
ocol-0.026
irs-0.022
ait-0.020
andel-0.019
sie-0.019
Token that
Token ID326
Feature activation+1.77e+00

Pos logit contributions
 owner+0.029
 not+0.027
 still+0.025
 was+0.023
 hurts+0.023
Neg logit contributions
ocol-0.121
irs-0.105
ait-0.098
andel-0.096
sie-0.095
Token he
Token ID339
Feature activation-8.70e-01

Pos logit contributions
 owner+0.031
 not+0.028
 still+0.027
 hurts+0.027
zag+0.027
Neg logit contributions
ocol-0.075
irs-0.064
ait-0.058
andel-0.057
sie-0.056
Token decided
Token ID3066
Feature activation-1.96e-01

Pos logit contributions
ocol+0.043
irs+0.037
ait+0.035
andel+0.034
sie+0.033
Neg logit contributions
 owner-0.010
 not-0.009
 still-0.009
 hurts-0.008
 hits-0.008
Token to
Token ID284
Feature activation-3.20e-01

Pos logit contributions
ocol+0.008
irs+0.007
ait+0.006
sie+0.006
andel+0.006
Neg logit contributions
 owner-0.004
flower-0.003
zag-0.003
 hurts-0.003
 hits-0.003
Token go
Token ID467
Feature activation+1.03e-01

Pos logit contributions
ocol+0.013
irs+0.011
ait+0.010
andel+0.010
sie+0.010
Neg logit contributions
 owner-0.006
 not-0.005
 still-0.005
 hurts-0.005
 hits-0.005
Token gone
Token ID3750
Feature activation+9.87e-02

Pos logit contributions
 owner+0.006
 not+0.005
 hurts+0.005
 hits+0.005
zag+0.005
Neg logit contributions
ocol-0.014
irs-0.012
ait-0.011
andel-0.011
sie-0.011
Token.
Token ID13
Feature activation-2.74e-01

Pos logit contributions
 owner+0.002
 not+0.002
 still+0.002
 hurts+0.002
 was+0.001
Neg logit contributions
ocol-0.004
irs-0.004
ait-0.003
andel-0.003
sie-0.003
Token He
Token ID679
Feature activation+4.69e-01

Pos logit contributions
ocol+0.012
irs+0.010
ait+0.009
andel+0.009
sie+0.009
Neg logit contributions
 owner-0.005
 not-0.004
 still-0.004
 hurts-0.004
 was-0.004
Token was
Token ID373
Feature activation+1.42e+00

Pos logit contributions
 owner+0.006
zag+0.005
 not+0.005
flower+0.005
 hits+0.005
Neg logit contributions
ocol-0.021
irs-0.018
ait-0.017
sie-0.017
 Annie-0.017
Token so
Token ID523
Feature activation+6.60e-01

Pos logit contributions
 owner+0.027
 not+0.024
 hurts+0.024
 hits+0.023
 still+0.023
Neg logit contributions
ocol-0.058
irs-0.049
ait-0.045
andel-0.044
sie-0.043
Token sad
Token ID6507
Feature activation+2.91e+00

Pos logit contributions
 owner+0.013
 not+0.012
 hits+0.012
zag+0.012
 hurts+0.012
Neg logit contributions
ocol-0.026
irs-0.022
ait-0.020
andel-0.019
sie-0.019
Token and
Token ID290
Feature activation+2.14e-01

Pos logit contributions
 owner+0.041
 not+0.036
 still+0.035
 hurts+0.034
 hits+0.033
Neg logit contributions
ocol-0.133
irs-0.115
ait-0.107
andel-0.104
sie-0.102
Token looked
Token ID3114
Feature activation-1.37e+00

Pos logit contributions
 owner+0.004
 not+0.003
zag+0.003
 still+0.003
 hits+0.003
Neg logit contributions
ocol-0.009
irs-0.008
ait-0.007
sie-0.007
andel-0.007
Token everywhere
Token ID8347
Feature activation-1.09e+00

Pos logit contributions
ocol+0.061
irs+0.053
ait+0.050
andel+0.047
sie+0.045
Neg logit contributions
 still-0.024
 not-0.024
 owner-0.023
 hurts-0.021
 was-0.021
Token for
Token ID329
Feature activation-2.17e+00

Pos logit contributions
ocol+0.053
irs+0.047
ait+0.044
andel+0.042
sie+0.042
Neg logit contributions
 not-0.017
 still-0.015
 owner-0.014
 was-0.014
 hurts-0.012
Token his
Token ID465
Feature activation-8.58e-02

Pos logit contributions
ocol+0.087
irs+0.075
ait+0.072
year+0.072
andel+0.070
Neg logit contributions
 not-0.048
 still-0.044
 only-0.042
 was-0.041
 owner-0.041
Token "
Token ID366
Feature activation+1.33e+00

Pos logit contributions
ocol+0.038
irs+0.034
ait+0.031
andel+0.031
sie+0.031
Neg logit contributions
 not-0.007
 owner-0.007
 still-0.005
 was-0.005
 also-0.004
TokenWow
Token ID22017
Feature activation-2.33e-01

Pos logit contributions
 owner+0.023
 not+0.021
 still+0.020
 hurts+0.020
 hits+0.019
Neg logit contributions
ocol-0.057
irs-0.049
ait-0.045
andel-0.044
sie-0.043
Token,
Token ID11
Feature activation+8.45e-01

Pos logit contributions
ocol+0.013
irs+0.011
andel+0.011
year+0.011
ait+0.011
Neg logit contributions
 not-0.001
 still-0.001
 was-0.001
's-0.001
 owner-0.001
Token Lily
Token ID20037
Feature activation+1.11e+00

Pos logit contributions
 not+0.017
 owner+0.016
 still+0.015
 was+0.015
 only+0.015
Neg logit contributions
ocol-0.036
irs-0.031
ait-0.029
andel-0.029
uster-0.027
Token!
Token ID0
Feature activation-1.67e+00

Pos logit contributions
 owner+0.019
 not+0.018
 still+0.017
 hurts+0.017
 hits+0.016
Neg logit contributions
ocol-0.048
irs-0.041
ait-0.037
andel-0.037
sie-0.036
Token Your
Token ID3406
Feature activation+2.79e+00

Pos logit contributions
ocol+0.063
irs+0.052
ait+0.047
andel+0.046
sie+0.044
Neg logit contributions
 owner-0.038
 not-0.035
 still-0.034
 hurts-0.034
 hits-0.033
Token sand
Token ID6450
Feature activation+2.51e+00

Pos logit contributions
 owner+0.066
 not+0.062
 still+0.060
 was+0.059
 hits+0.056
Neg logit contributions
ocol-0.106
irs-0.091
ait-0.082
andel-0.079
sie-0.078
Tokencastle
Token ID18676
Feature activation+1.42e+00

Pos logit contributions
 owner+0.049
 not+0.043
 still+0.042
 hurts+0.042
 remembered+0.041
Neg logit contributions
ocol-0.100
irs-0.082
ait-0.074
andel-0.072
sie-0.072
Token is
Token ID318
Feature activation-3.57e-02

Pos logit contributions
 owner+0.016
 not+0.012
zag+0.011
 hurts+0.011
flower+0.010
Neg logit contributions
ocol-0.068
irs-0.059
ait-0.054
inations-0.052
sie-0.052
Token so
Token ID523
Feature activation-1.86e-01

Pos logit contributions
ocol+0.001
irs+0.001
ait+0.001
andel+0.001
sie+0.001
Neg logit contributions
 owner-0.001
 not-0.001
 still-0.001
 was-0.001
 also-0.001
Token beautiful
Token ID4950
Feature activation-1.27e-01

Pos logit contributions
ocol+0.008
irs+0.007
ait+0.007
andel+0.006
sie+0.006
Neg logit contributions
 not-0.004
 still-0.004
 owner-0.003
 was-0.003
 also-0.003
Token to
Token ID284
Feature activation+3.24e-01

Pos logit contributions
 owner+0.008
 not+0.008
 still+0.007
 hurts+0.007
zag+0.007
Neg logit contributions
ocol-0.022
irs-0.019
ait-0.018
andel-0.017
sie-0.017
Token roll
Token ID4836
Feature activation+1.60e+00

Pos logit contributions
 owner+0.007
 not+0.006
 still+0.006
 hurts+0.006
zag+0.006
Neg logit contributions
ocol-0.012
irs-0.010
ait-0.009
andel-0.009
sie-0.009
Token.
Token ID13
Feature activation+5.53e-01

Pos logit contributions
 owner+0.028
 not+0.026
 still+0.025
 hurts+0.025
 hits+0.024
Neg logit contributions
ocol-0.069
irs-0.059
ait-0.054
andel-0.053
sie-0.052
Token
Token ID198
Feature activation+7.88e-01

Pos logit contributions
 owner+0.007
 not+0.006
 still+0.006
 was+0.005
 hurts+0.005
Neg logit contributions
ocol-0.027
irs-0.024
ait-0.022
andel-0.022
sie-0.021
Token
Token ID198
Feature activation+9.78e-02

Pos logit contributions
 owner+0.008
 not+0.007
 still+0.006
 was+0.006
 hurts+0.005
Neg logit contributions
ocol-0.041
irs-0.035
ait-0.033
andel-0.033
sie-0.032
TokenSo
Token ID2396
Feature activation+7.58e-01

Pos logit contributions
 owner+0.001
 not+0.001
 still+0.001
 was+0.001
 also+0.001
Neg logit contributions
ocol-0.005
irs-0.004
ait-0.004
andel-0.004
sie-0.004
Token it
Token ID340
Feature activation+4.78e-01

Pos logit contributions
 owner+0.011
 not+0.010
 still+0.009
 hurts+0.009
 hits+0.008
Neg logit contributions
ocol-0.035
irs-0.031
ait-0.028
andel-0.028
sie-0.027
Token rolled
Token ID11686
Feature activation+9.30e-01

Pos logit contributions
 owner+0.007
 not+0.007
 hurts+0.006
flower+0.006
zag+0.006
Neg logit contributions
ocol-0.020
irs-0.017
sie-0.017
ait-0.016
andel-0.016
Token and
Token ID290
Feature activation-5.82e-01

Pos logit contributions
 owner+0.016
 not+0.015
 still+0.015
 hurts+0.014
 hits+0.014
Neg logit contributions
ocol-0.041
irs-0.035
ait-0.033
andel-0.031
sie-0.031
Token rolled
Token ID11686
Feature activation+1.18e+00

Pos logit contributions
ocol+0.027
irs+0.024
ait+0.022
sie+0.021
andel+0.021
Neg logit contributions
 owner-0.007
 not-0.007
 still-0.006
 hurts-0.006
zag-0.006
Token and
Token ID290
Feature activation-6.50e-01

Pos logit contributions
 owner+0.019
 not+0.018
 still+0.017
 was+0.016
 hits+0.015
Neg logit contributions
ocol-0.057
irs-0.049
ait-0.047
prise-0.044
andel-0.044
Token picture
Token ID4286
Feature activation+1.26e-02

Pos logit contributions
ocol+0.058
irs+0.049
ait+0.044
sie+0.043
andel+0.043
Neg logit contributions
 owner-0.030
 not-0.025
 still-0.024
 was-0.024
tr-0.024
Token to
Token ID284
Feature activation-1.83e+00

Pos logit contributions
 owner+0.000
 not+0.000
 was+0.000
 still+0.000
 hurts+0.000
Neg logit contributions
ocol-0.001
irs-0.000
ait-0.000
andel-0.000
sie-0.000
Token grandma
Token ID49890
Feature activation+2.40e-02

Pos logit contributions
ocol+0.076
irs+0.063
andel+0.061
sie+0.060
ait+0.059
Neg logit contributions
 not-0.037
 owner-0.036
 still-0.034
 also-0.032
 only-0.031
Token!"
Token ID2474
Feature activation+1.28e-01

Pos logit contributions
 owner+0.000
 not+0.000
 still+0.000
 was+0.000
's+0.000
Neg logit contributions
ocol-0.001
irs-0.001
andel-0.001
ait-0.001
sie-0.001
Token Ben
Token ID3932
Feature activation+1.91e-01

Pos logit contributions
 owner+0.002
 not+0.002
 still+0.002
 was+0.002
 hurts+0.002
Neg logit contributions
ocol-0.006
irs-0.005
ait-0.005
andel-0.005
sie-0.005
Token shouts
Token ID34757
Feature activation-1.10e+00

Pos logit contributions
 owner+0.003
 not+0.003
 still+0.002
 hurts+0.002
zag+0.002
Neg logit contributions
ocol-0.008
irs-0.007
ait-0.007
andel-0.007
sie-0.007
Token.
Token ID13
Feature activation+2.36e-01

Pos logit contributions
ocol+0.051
irs+0.045
ait+0.041
andel+0.039
sie+0.039
Neg logit contributions
 owner-0.017
 not-0.016
 still-0.015
 was-0.014
 hurts-0.013
Token
Token ID198
Feature activation+9.67e-01

Pos logit contributions
 owner+0.003
 not+0.003
 still+0.003
 hurts+0.003
zag+0.002
Neg logit contributions
ocol-0.011
irs-0.010
ait-0.009
andel-0.009
sie-0.009
Token
Token ID198
Feature activation+5.40e-01

Pos logit contributions
 owner+0.010
 not+0.009
 still+0.008
 hurts+0.007
 was+0.007
Neg logit contributions
ocol-0.050
irs-0.043
ait-0.040
andel-0.040
sie-0.039
Token"
Token ID1
Feature activation+7.28e-01

Pos logit contributions
 owner+0.008
 not+0.008
 still+0.007
 hurts+0.007
 hits+0.007
Neg logit contributions
ocol-0.024
irs-0.021
ait-0.019
andel-0.019
sie-0.018
TokenHello
Token ID15496
Feature activation+1.29e+00

Pos logit contributions
 owner+0.014
 not+0.014
 hurts+0.013
 hits+0.013
 still+0.013
Neg logit contributions
ocol-0.029
irs-0.024
ait-0.022
sie-0.021
andel-0.021
Token baby
Token ID5156
Feature activation-1.88e-01

Pos logit contributions
ocol+0.027
irs+0.025
ait+0.021
andel+0.021
inations+0.020
Neg logit contributions
 owner-0.012
 still-0.010
 not-0.010
 was-0.009
 friend-0.009
Token.
Token ID13
Feature activation-3.81e-01

Pos logit contributions
ocol+0.008
irs+0.008
andel+0.007
ait+0.007
inations+0.006
Neg logit contributions
 owner-0.003
 still-0.003
 was-0.003
 not-0.003
flower-0.003
Token The
Token ID383
Feature activation+1.74e+00

Pos logit contributions
ocol+0.020
irs+0.017
inations+0.016
andel+0.016
sie+0.016
Neg logit contributions
 owner-0.004
 still-0.003
 not-0.003
 was-0.003
 also-0.003
Token baby
Token ID5156
Feature activation+2.05e+00

Pos logit contributions
 owner+0.032
 not+0.029
 still+0.028
 hurts+0.027
 was+0.026
Neg logit contributions
ocol-0.074
irs-0.064
ait-0.058
andel-0.057
sie-0.056
Token's
Token ID338
Feature activation+1.83e+00

Pos logit contributions
 owner+0.016
 not+0.016
 hits+0.016
zag+0.015
 hurts+0.013
Neg logit contributions
ocol-0.098
ait-0.083
irs-0.082
sie-0.082
 Annie-0.081
Token name
Token ID1438
Feature activation-6.14e-01

Pos logit contributions
 owner+0.026
 not+0.025
 hits+0.024
 hurts+0.024
 still+0.024
Neg logit contributions
ocol-0.081
irs-0.069
ait-0.065
andel-0.063
sie-0.062
Token was
Token ID373
Feature activation+2.71e-01

Pos logit contributions
ocol+0.031
irs+0.027
ait+0.026
 Annie+0.025
sie+0.025
Neg logit contributions
 owner-0.004
 not-0.003
zag-0.003
 hits-0.003
 hurts-0.003
Token Mary
Token ID5335
Feature activation-6.97e-01

Pos logit contributions
 owner+0.007
 not+0.007
 still+0.006
 was+0.006
 hurts+0.006
Neg logit contributions
ocol-0.010
irs-0.008
ait-0.007
andel-0.007
sie-0.007
Token.
Token ID13
Feature activation+3.19e-01

Pos logit contributions
ocol+0.033
irs+0.029
ait+0.026
andel+0.026
sie+0.025
Neg logit contributions
 owner-0.009
 not-0.009
 still-0.008
 hurts-0.007
 was-0.007
Token Mary
Token ID5335
Feature activation+4.73e-01

Pos logit contributions
 owner+0.007
 not+0.007
 still+0.006
 hurts+0.006
 hits+0.006
Neg logit contributions
ocol-0.012
irs-0.010
ait-0.009
andel-0.009
 Annie-0.008
Token loved
Token ID6151
Feature activation-5.51e-01

Pos logit contributions
 owner+0.004
 not+0.004
 hits+0.003
zag+0.003
 hurts+0.003
Neg logit contributions
ocol-0.023
irs-0.020
ait-0.019
sie-0.019
 Annie-0.018
Token their
Token ID511
Feature activation+6.62e-02

Pos logit contributions
ocol+0.041
irs+0.034
andel+0.033
inations+0.032
sie+0.032
Neg logit contributions
 was-0.020
 owner-0.020
 not-0.019
 still-0.019
's-0.018
Token room
Token ID2119
Feature activation+3.86e-01

Pos logit contributions
 owner+0.001
 still+0.001
 not+0.001
 was+0.001
 next+0.001
Neg logit contributions
ocol-0.003
irs-0.003
ait-0.002
andel-0.002
sie-0.002
Token.
Token ID13
Feature activation+1.81e-01

Pos logit contributions
 owner+0.006
 not+0.006
 still+0.006
 was+0.005
 also+0.005
Neg logit contributions
ocol-0.018
irs-0.016
andel-0.014
ait-0.014
sie-0.014
Token They
Token ID1119
Feature activation+1.93e-01

Pos logit contributions
 owner+0.003
 not+0.002
 still+0.002
 hurts+0.002
 was+0.002
Neg logit contributions
ocol-0.008
irs-0.007
ait-0.007
andel-0.007
sie-0.006
Token are
Token ID389
Feature activation+4.72e-01

Pos logit contributions
 still+0.003
 not+0.003
 also+0.003
 owner+0.003
 only+0.003
Neg logit contributions
ocol-0.009
irs-0.008
andel-0.007
ait-0.007
sie-0.007
Token proud
Token ID6613
Feature activation+4.48e-02

Pos logit contributions
 not+0.008
 owner+0.008
 still+0.008
 also+0.007
 only+0.006
Neg logit contributions
ocol-0.022
irs-0.019
andel-0.017
ait-0.017
sie-0.017
Token.
Token ID13
Feature activation+5.85e-01

Pos logit contributions
 owner+0.001
 not+0.001
 still+0.001
 was+0.001
 also+0.001
Neg logit contributions
ocol-0.002
irs-0.002
ait-0.001
sie-0.001
andel-0.001
Token They
Token ID1119
Feature activation-1.39e-01

Pos logit contributions
 owner+0.009
 not+0.008
 still+0.007
 was+0.007
 hurts+0.007
Neg logit contributions
ocol-0.028
irs-0.024
ait-0.022
andel-0.022
sie-0.021
Token say
Token ID910
Feature activation-1.24e+00

Pos logit contributions
ocol+0.006
irs+0.005
andel+0.005
ait+0.005
sie+0.005
Neg logit contributions
 still-0.002
 not-0.002
 owner-0.002
 also-0.002
 was-0.002
Token,
Token ID11
Feature activation-2.67e-01

Pos logit contributions
ocol+0.065
irs+0.058
ait+0.054
andel+0.054
sie+0.052
Neg logit contributions
 not-0.013
 owner-0.011
 was-0.009
 still-0.009
 hurts-0.008
Token "
Token ID366
Feature activation+9.60e-01

Pos logit contributions
ocol+0.013
irs+0.011
ait+0.010
andel+0.010
sie+0.010
Neg logit contributions
 owner-0.003
 not-0.003
 still-0.003
 hurts-0.003
 was-0.003
Token the
Token ID262
Feature activation-1.57e+00

Pos logit contributions
ocol+0.089
irs+0.077
inations+0.074
ait+0.073
andel+0.073
Neg logit contributions
 owner-0.024
 hits-0.022
 not-0.022
 hit-0.021
 still-0.020
Token room
Token ID2119
Feature activation+1.07e-01

Pos logit contributions
ocol+0.063
irs+0.059
ait+0.052
year+0.050
sie+0.050
Neg logit contributions
 owner-0.035
 hurts-0.031
 hits-0.031
 head-0.029
 not-0.029
Token.
Token ID13
Feature activation+4.03e-01

Pos logit contributions
 owner+0.002
 not+0.002
 still+0.002
 was+0.001
 hurts+0.001
Neg logit contributions
ocol-0.005
irs-0.004
andel-0.004
ait-0.004
sie-0.004
Token He
Token ID679
Feature activation+1.92e-01

Pos logit contributions
 owner+0.006
 not+0.006
 still+0.005
 hurts+0.005
 was+0.005
Neg logit contributions
ocol-0.019
irs-0.016
ait-0.015
andel-0.015
sie-0.015
Token said
Token ID531
Feature activation-1.12e+00

Pos logit contributions
 owner+0.003
flower+0.003
zag+0.003
 not+0.003
 hurts+0.003
Neg logit contributions
ocol-0.008
irs-0.007
ait-0.006
sie-0.006
 rubble-0.006
Token,
Token ID11
Feature activation-1.65e-01

Pos logit contributions
ocol+0.054
irs+0.047
ait+0.043
andel+0.042
sie+0.042
Neg logit contributions
 owner-0.014
 not-0.012
 still-0.012
 hurts-0.011
 hits-0.011
Token "
Token ID366
Feature activation+1.45e+00

Pos logit contributions
ocol+0.007
irs+0.006
ait+0.006
andel+0.006
sie+0.006
Neg logit contributions
 owner-0.002
 not-0.002
 still-0.002
 hurts-0.002
 hits-0.002
TokenIt
Token ID1026
Feature activation+6.92e-01

Pos logit contributions
 owner+0.032
 not+0.032
zag+0.030
 still+0.029
 hits+0.029
Neg logit contributions
ocol-0.053
irs-0.044
ait-0.040
sie-0.040
andel-0.039
Token doesn
Token ID1595
Feature activation-2.95e+00

Pos logit contributions
 owner+0.007
flower+0.005
 not+0.004
 still+0.004
 hits+0.004
Neg logit contributions
ocol-0.032
irs-0.029
ait-0.027
 Annie-0.027
sie-0.027
Token't
Token ID470
Feature activation+6.92e-01

Pos logit contributions
ocol+0.139
irs+0.118
ait+0.111
sie+0.108
andel+0.108
Neg logit contributions
 owner-0.041
 not-0.040
 still-0.036
 hurts-0.035
 hits-0.033
Token matter
Token ID2300
Feature activation+2.43e+00

Pos logit contributions
 not+0.013
 owner+0.011
 still+0.011
 hurt+0.011
 hurts+0.010
Neg logit contributions
ocol-0.033
irs-0.028
ait-0.026
andel-0.026
year-0.026
Token more
Token ID517
Feature activation+1.37e+00

Pos logit contributions
ocol+0.052
irs+0.045
ait+0.042
sie+0.041
year+0.041
Neg logit contributions
 owner-0.025
 not-0.024
 hurts-0.024
 still-0.024
 was-0.023
Token,"
Token ID553
Feature activation-5.95e-01

Pos logit contributions
 not+0.028
 owner+0.028
 still+0.026
 hurts+0.025
 was+0.025
Neg logit contributions
ocol-0.056
irs-0.048
ait-0.044
andel-0.043
sie-0.042
Token and
Token ID290
Feature activation-1.14e-01

Pos logit contributions
ocol+0.027
irs+0.024
ait+0.022
andel+0.022
inations+0.021
Neg logit contributions
 owner-0.009
 not-0.009
 still-0.009
 was-0.009
 only-0.008
Token he
Token ID339
Feature activation-1.08e+00

Pos logit contributions
ocol+0.005
irs+0.004
ait+0.004
andel+0.004
sie+0.004
Neg logit contributions
 owner-0.002
 not-0.002
 still-0.002
 hurts-0.002
 hits-0.002
Token located
Token ID5140
Feature activation-1.33e+00

Pos logit contributions
ocol+0.045
irs+0.039
ait+0.037
sie+0.036
andel+0.035
Neg logit contributions
 owner-0.016
 hurts-0.016
 not-0.015
 hates-0.014
 hits-0.014
Token a
Token ID257
Feature activation-1.59e+00

Pos logit contributions
ocol+0.060
irs+0.052
ait+0.048
inations+0.047
andel+0.047
Neg logit contributions
 owner-0.022
 not-0.020
 still-0.019
 was-0.018
 only-0.018
Token nearby
Token ID6716
Feature activation-8.13e-01

Pos logit contributions
ocol+0.067
irs+0.058
ait+0.052
andel+0.050
sie+0.049
Neg logit contributions
 owner-0.034
 not-0.030
 still-0.030
 was-0.028
 hurts-0.027
Token pond
Token ID16723
Feature activation-3.32e-01

Pos logit contributions
ocol+0.038
irs+0.036
inations+0.031
ait+0.031
year+0.030
Neg logit contributions
 owner-0.013
 was-0.011
 still-0.011
 be-0.010
 head-0.010
Token to
Token ID284
Feature activation-1.54e+00

Pos logit contributions
ocol+0.015
irs+0.013
ait+0.012
andel+0.012
sie+0.012
Neg logit contributions
 owner-0.005
 not-0.005
 still-0.005
 was-0.004
 hurts-0.004
Token soak
Token ID33182
Feature activation-1.88e-01

Pos logit contributions
ocol+0.067
irs+0.058
ait+0.053
andel+0.053
sie+0.050
Neg logit contributions
 not-0.026
 still-0.026
 owner-0.026
 also-0.024
 was-0.023
Token in
Token ID287
Feature activation-1.29e-01

Pos logit contributions
ocol+0.009
irs+0.008
ait+0.007
andel+0.007
inations+0.007
Neg logit contributions
 owner-0.003
 still-0.003
 was-0.003
 not-0.003
 hurts-0.002
Token showed
Token ID3751
Feature activation-4.50e-01

Pos logit contributions
 hurts+0.009
tr+0.009
burn+0.008
ained+0.008
flower+0.008
Neg logit contributions
sie-0.013
ocol-0.012
ait-0.012
irs-0.012
 Annie-0.012
Token him
Token ID683
Feature activation+8.31e-01

Pos logit contributions
ocol+0.017
irs+0.014
ait+0.013
andel+0.013
sie+0.012
Neg logit contributions
 owner-0.010
 not-0.009
 still-0.009
 hurts-0.009
zag-0.009
Token how
Token ID703
Feature activation-1.90e+00

Pos logit contributions
 owner+0.019
flower+0.018
tr+0.018
zag+0.017
 still+0.017
Neg logit contributions
ocol-0.027
irs-0.024
sie-0.020
 Annie-0.020
andel-0.020
Token to
Token ID284
Feature activation+1.85e-01

Pos logit contributions
ocol+0.083
irs+0.071
ait+0.065
andel+0.064
sie+0.063
Neg logit contributions
 owner-0.031
 not-0.028
 still-0.027
 hurts-0.026
zag-0.026
Token move
Token ID1445
Feature activation+1.69e+00

Pos logit contributions
 owner+0.004
tr+0.004
flower+0.004
 hurts+0.003
burn+0.003
Neg logit contributions
ocol-0.007
irs-0.006
inations-0.005
ait-0.005
sie-0.005
Token the
Token ID262
Feature activation-1.96e+00

Pos logit contributions
 owner+0.029
 not+0.027
 still+0.026
 hurts+0.025
 hits+0.025
Neg logit contributions
ocol-0.073
irs-0.062
ait-0.057
andel-0.056
sie-0.055
Token pieces
Token ID5207
Feature activation-1.13e+00

Pos logit contributions
ocol+0.071
irs+0.059
ait+0.053
andel+0.051
sie+0.050
Neg logit contributions
 owner-0.048
 not-0.046
 still-0.044
 hurts-0.044
 hits-0.043
Token and
Token ID290
Feature activation+3.13e-01

Pos logit contributions
ocol+0.049
irs+0.042
ait+0.039
andel+0.038
sie+0.037
Neg logit contributions
 owner-0.019
 not-0.018
 still-0.017
 hurts-0.017
 hits-0.016
Token they
Token ID484
Feature activation-1.37e+00

Pos logit contributions
 owner+0.006
 hurts+0.006
flower+0.006
 hates+0.006
Because+0.006
Neg logit contributions
ocol-0.011
irs-0.010
 Annie-0.009
 ages-0.009
inations-0.008
Token started
Token ID2067
Feature activation+1.70e+00

Pos logit contributions
ocol+0.055
irs+0.050
ait+0.045
sie+0.045
andel+0.043
Neg logit contributions
 owner-0.022
 hurts-0.022
 not-0.020
 hits-0.019
zag-0.019
Token playing
Token ID2712
Feature activation+1.41e+00

Pos logit contributions
 owner+0.034
tr+0.031
flower+0.030
 hurts+0.030
 still+0.030
Neg logit contributions
ocol-0.065
irs-0.057
ait-0.048
andel-0.048
 Annie-0.047
Token brave
Token ID14802
Feature activation+1.27e+00

Pos logit contributions
 owner+0.031
 not+0.029
 still+0.028
 hurts+0.027
 hits+0.026
Neg logit contributions
ocol-0.059
irs-0.051
ait-0.046
andel-0.044
sie-0.044
Token dinosaur
Token ID28257
Feature activation+1.01e+00

Pos logit contributions
 owner+0.024
 was+0.021
 not+0.020
 still+0.020
 hits+0.020
Neg logit contributions
ocol-0.054
irs-0.049
ait-0.044
sie-0.041
andel-0.041
Token bell
Token ID8966
Feature activation+7.19e-01

Pos logit contributions
burn+0.011
 hurts+0.011
 hits+0.010
flower+0.010
 owner+0.009
Neg logit contributions
ocol-0.043
irs-0.038
sie-0.037
ait-0.036
 ages-0.036
Tokenowed
Token ID6972
Feature activation-6.35e-01

Pos logit contributions
 hurts+0.010
 owner+0.010
 hates+0.010
 not+0.010
 Fighting+0.009
Neg logit contributions
ocol-0.027
irs-0.023
ait-0.021
year-0.021
 ages-0.021
Token in
Token ID287
Feature activation+3.79e-01

Pos logit contributions
ocol+0.030
irs+0.027
ait+0.025
andel+0.023
sie+0.023
Neg logit contributions
 owner-0.009
 not-0.008
 still-0.008
 was-0.007
 only-0.007
Token surprise
Token ID5975
Feature activation-2.31e+00

Pos logit contributions
 owner+0.006
 not+0.006
 was+0.006
 still+0.005
 only+0.005
Neg logit contributions
ocol-0.017
irs-0.015
ait-0.015
sie-0.014
inations-0.014
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
ocol+0.122
irs+0.111
sie+0.103
andel+0.102
chie+0.100
Neg logit contributions
 owner-0.024
 was-0.020
 not-0.019
 still-0.017
 and-0.014
Token "
Token ID366
Feature activation+1.85e+00

Pos logit contributions
ocol+0.054
irs+0.047
ait+0.044
sie+0.043
andel+0.042
Neg logit contributions
 owner-0.014
 not-0.012
 still-0.011
 was-0.011
 hits-0.010
TokenHow
Token ID2437
Feature activation-3.38e+00

Pos logit contributions
 owner+0.039
 not+0.038
 hurts+0.036
zag+0.035
 hits+0.035
Neg logit contributions
ocol-0.072
irs-0.060
ait-0.054
andel-0.053
sie-0.053
Token can
Token ID460
Feature activation-2.90e+00

Pos logit contributions
ocol+0.151
irs+0.129
ait+0.118
andel+0.118
sie+0.115
Neg logit contributions
 owner-0.057
 not-0.057
 still-0.053
 was-0.050
 also-0.049
Token I
Token ID314
Feature activation-1.86e+00

Pos logit contributions
ocol+0.112
irs+0.094
ait+0.086
andel+0.083
sie+0.081
Neg logit contributions
 owner-0.064
 not-0.062
 still-0.058
 hurts-0.058
 hits-0.056
Token happy
Token ID3772
Feature activation+1.00e+00

Pos logit contributions
 not+0.022
 owner+0.021
 still+0.021
 also+0.019
 remembered+0.018
Neg logit contributions
ocol-0.051
irs-0.045
andel-0.040
ait-0.040
uster-0.038
Token,
Token ID11
Feature activation+7.40e-03

Pos logit contributions
 owner+0.015
 not+0.014
 still+0.013
 hurts+0.012
 hits+0.012
Neg logit contributions
ocol-0.046
irs-0.040
ait-0.037
andel-0.036
sie-0.035
Token too
Token ID1165
Feature activation+1.66e+00

Pos logit contributions
 owner+0.000
 not+0.000
 still+0.000
 hurts+0.000
 hits+0.000
Neg logit contributions
ocol-0.000
irs-0.000
ait-0.000
andel-0.000
sie-0.000
Token.
Token ID13
Feature activation+9.99e-01

Pos logit contributions
 owner+0.028
 not+0.027
 still+0.026
 also+0.023
 was+0.023
Neg logit contributions
ocol-0.074
irs-0.065
ait-0.058
andel-0.057
sie-0.056
Token<|endoftext|>
Token ID50256
Feature activation-1.67e+00

Pos logit contributions
 owner+0.013
 not+0.012
 still+0.011
 hurts+0.011
 hits+0.011
Neg logit contributions
ocol-0.046
irs-0.040
ait-0.037
andel-0.036
sie-0.036
TokenL
Token ID43
Feature activation-2.20e+00

Pos logit contributions
ocol+0.073
irs+0.061
ait+0.058
andel+0.057
sie+0.055
Neg logit contributions
 owner-0.029
 was-0.028
 still-0.027
 not-0.026
 hits-0.025
Tokenily
Token ID813
Feature activation-8.47e-02

Pos logit contributions
ocol+0.093
irs+0.072
andel+0.071
chie+0.066
 rubble+0.065
Neg logit contributions
 not-0.045
 was-0.044
 also-0.044
 owner-0.043
's-0.042
Token liked
Token ID8288
Feature activation-5.90e-01

Pos logit contributions
ocol+0.004
irs+0.003
ait+0.003
 Annie+0.003
sie+0.003
Neg logit contributions
 owner-0.001
zag-0.001
 neither-0.001
 not-0.001
 hurts-0.001
Token to
Token ID284
Feature activation-3.95e-02

Pos logit contributions
ocol+0.031
irs+0.028
sie+0.026
ait+0.026
andel+0.026
Neg logit contributions
 owner-0.006
 not-0.005
 still-0.003
 was-0.003
 next-0.003
Token help
Token ID1037
Feature activation-1.05e-01

Pos logit contributions
ocol+0.002
irs+0.002
ait+0.001
andel+0.001
sie+0.001
Neg logit contributions
 not-0.001
 owner-0.001
 still-0.001
 was-0.001
 hurts-0.001
Token her
Token ID607
Feature activation+8.95e-02

Pos logit contributions
ocol+0.004
irs+0.004
ait+0.003
andel+0.003
sie+0.003
Neg logit contributions
 owner-0.002
 not-0.002
 still-0.002
 hurts-0.002
 was-0.002
Token sing
Token ID1702
Feature activation+1.22e+00

Pos logit contributions
ocol+0.032
irs+0.027
ait+0.025
andel+0.024
sie+0.024
Neg logit contributions
 owner-0.013
 not-0.012
 still-0.012
 hurts-0.011
 hits-0.011
Token her
Token ID607
Feature activation+1.18e-01

Pos logit contributions
 owner+0.017
 not+0.016
 still+0.015
 was+0.014
 only+0.013
Neg logit contributions
ocol-0.060
irs-0.051
ait-0.048
andel-0.046
sie-0.046
Token most
Token ID749
Feature activation+1.16e-01

Pos logit contributions
 owner+0.002
 not+0.002
 hits+0.002
 still+0.002
 hurts+0.002
Neg logit contributions
ocol-0.005
irs-0.004
ait-0.004
andel-0.004
sie-0.004
Token beautiful
Token ID4950
Feature activation-4.98e-01

Pos logit contributions
 owner+0.003
 not+0.003
 still+0.003
 was+0.002
 hurts+0.002
Neg logit contributions
ocol-0.004
irs-0.004
ait-0.003
andel-0.003
sie-0.003
Token and
Token ID290
Feature activation-1.25e+00

Pos logit contributions
ocol+0.021
irs+0.018
ait+0.016
andel+0.015
sie+0.015
Neg logit contributions
 owner-0.010
 not-0.009
 still-0.009
 hurts-0.009
 was-0.008
Token upl
Token ID28996
Feature activation-4.13e+00

Pos logit contributions
ocol+0.046
irs+0.040
 Annie+0.036
 ages+0.035
sie+0.035
Neg logit contributions
 owner-0.025
zag-0.023
flower-0.023
 hurts-0.022
 hits-0.022
Tokenifting
Token ID13309
Feature activation+5.52e-01

Pos logit contributions
ocol+0.133
irs+0.104
ait+0.098
sie+0.094
andel+0.091
Neg logit contributions
 not-0.109
 owner-0.106
 still-0.105
zag-0.102
 also-0.101
Token song
Token ID3496
Feature activation+8.46e-01

Pos logit contributions
 owner+0.010
 not+0.010
 still+0.009
 was+0.009
 hurts+0.009
Neg logit contributions
ocol-0.024
irs-0.021
ait-0.019
andel-0.018
sie-0.018
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
 owner+0.014
 not+0.013
 still+0.012
 was+0.012
zag+0.011
Neg logit contributions
ocol-0.039
irs-0.033
ait-0.031
andel-0.030
sie-0.030
Token Slowly
Token ID46484
Feature activation+4.09e-01

Pos logit contributions
ocol+0.059
irs+0.051
ait+0.047
sie+0.046
inations+0.046
Neg logit contributions
 owner-0.012
 not-0.010
 still-0.010
 was-0.010
 only-0.009
Token,
Token ID11
Feature activation+3.26e-01

Pos logit contributions
 not+0.003
 owner+0.003
 still+0.003
 was+0.003
 only+0.003
Neg logit contributions
ocol-0.022
irs-0.019
ait-0.018
year-0.018
andel-0.018
Token they
Token ID484
Feature activation-1.23e+00

Pos logit contributions
 owner+0.024
 not+0.022
 still+0.022
 hurts+0.022
 hits+0.021
Neg logit contributions
ocol-0.051
irs-0.044
ait-0.040
andel-0.039
sie-0.038
Token built
Token ID3170
Feature activation+7.12e-01

Pos logit contributions
ocol+0.048
irs+0.042
ait+0.038
sie+0.036
andel+0.036
Neg logit contributions
 owner-0.024
 hurts-0.023
 not-0.022
 hits-0.021
 still-0.021
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
 not+0.011
 owner+0.011
 still+0.010
 was+0.010
 hits+0.009
Neg logit contributions
ocol-0.033
irs-0.028
ait-0.026
sie-0.026
andel-0.026
Token biggest
Token ID4094
Feature activation+2.29e+00

Pos logit contributions
 owner+0.023
 not+0.021
 hurts+0.021
 remembered+0.020
flower+0.020
Neg logit contributions
ocol-0.044
irs-0.037
ait-0.034
andel-0.033
 rubble-0.032
Token tower
Token ID10580
Feature activation+5.23e-01

Pos logit contributions
 owner+0.045
 not+0.043
 hurts+0.041
 still+0.041
zag+0.039
Neg logit contributions
ocol-0.091
irs-0.076
ait-0.069
andel-0.068
sie-0.065
Token they
Token ID484
Feature activation-5.44e+00

Pos logit contributions
 owner+0.009
 not+0.008
 hurts+0.008
 still+0.008
 remembered+0.008
Neg logit contributions
ocol-0.022
irs-0.018
ait-0.017
andel-0.016
sie-0.016
Token had
Token ID550
Feature activation-2.22e+00

Pos logit contributions
ocol+0.268
irs+0.231
ait+0.214
andel+0.214
sie+0.204
Neg logit contributions
 owner-0.068
 not-0.066
 still-0.064
 was-0.057
 remembered-0.057
Token ever
Token ID1683
Feature activation-1.81e+00

Pos logit contributions
ocol+0.081
irs+0.068
ait+0.061
andel+0.058
sie+0.057
Neg logit contributions
 owner-0.051
 hurts-0.047
 not-0.047
 still-0.046
 hits-0.045
Token made
Token ID925
Feature activation-2.28e+00

Pos logit contributions
ocol+0.069
irs+0.057
ait+0.052
andel+0.051
sie+0.050
Neg logit contributions
 owner-0.041
 not-0.039
 still-0.038
 hurts-0.037
 was-0.037
Token.
Token ID13
Feature activation-4.43e-02

Pos logit contributions
ocol+0.105
irs+0.089
ait+0.082
sie+0.082
andel+0.081
Neg logit contributions
 owner-0.037
 not-0.035
 still-0.032
 was-0.031
zag-0.029
Token They
Token ID1119
Feature activation-2.57e-01

Pos logit contributions
ocol+0.002
irs+0.001
ait+0.001
andel+0.001
sie+0.001
Neg logit contributions
 owner-0.001
 not-0.001
 still-0.001
 hurts-0.001
 hits-0.001
Token park
Token ID3952
Feature activation+6.94e-01

Pos logit contributions
ocol+0.024
irs+0.020
andel+0.018
ait+0.018
sie+0.018
Neg logit contributions
 not-0.015
zag-0.015
 owner-0.015
 hurts-0.014
 hits-0.014
Token and
Token ID290
Feature activation+1.28e+00

Pos logit contributions
 hurts+0.014
 hits+0.013
tr+0.012
 owner+0.012
burn+0.012
Neg logit contributions
ocol-0.024
irs-0.020
 Annie-0.019
ait-0.019
 ages-0.019
Token look
Token ID804
Feature activation-1.66e+00

Pos logit contributions
 owner+0.027
Because+0.024
 hurts+0.024
 hates+0.024
ung+0.023
Neg logit contributions
ocol-0.045
irs-0.037
 Annie-0.035
sie-0.034
ait-0.032
Token for
Token ID329
Feature activation-4.94e-01

Pos logit contributions
ocol+0.082
irs+0.075
ait+0.071
andel+0.066
prise+0.065
Neg logit contributions
 still-0.018
 owner-0.017
 not-0.017
 was-0.014
's-0.014
Token something
Token ID1223
Feature activation-3.38e+00

Pos logit contributions
ocol+0.021
irs+0.018
ait+0.017
sie+0.016
andel+0.016
Neg logit contributions
 owner-0.010
 not-0.009
 was-0.008
 still-0.008
 only-0.008
Token y
Token ID331
Feature activation-5.20e+00

Pos logit contributions
ocol+0.144
irs+0.123
ait+0.113
andel+0.111
sie+0.107
Neg logit contributions
 owner-0.067
 not-0.064
 still-0.060
 was-0.056
 hurts-0.056
Tokenummy
Token ID13513
Feature activation-2.19e+00

Pos logit contributions
ocol+0.168
irs+0.138
ait+0.122
sie+0.118
andel+0.115
Neg logit contributions
 owner-0.144
 not-0.135
 still-0.132
 hurts-0.130
 hits-0.126
Token to
Token ID284
Feature activation-2.70e+00

Pos logit contributions
ocol+0.096
irs+0.082
ait+0.076
andel+0.074
sie+0.073
Neg logit contributions
 owner-0.037
 not-0.034
 still-0.032
 hurts-0.031
 hits-0.030
Token eat
Token ID4483
Feature activation-1.81e+00

Pos logit contributions
ocol+0.115
irs+0.097
ait+0.089
andel+0.087
sie+0.085
Neg logit contributions
 owner-0.049
 not-0.045
 still-0.043
 hurts-0.042
 hits-0.041
Token.
Token ID13
Feature activation+8.29e-01

Pos logit contributions
ocol+0.088
irs+0.078
ait+0.074
andel+0.073
uster+0.071
Neg logit contributions
 owner-0.024
 not-0.023
 was-0.022
 still-0.022
 next-0.019
Token
Token ID198
Feature activation+6.83e-01

Pos logit contributions
flower+0.015
 remembered+0.015
 owner+0.015
 hurts+0.014
 not+0.014
Neg logit contributions
ocol-0.031
irs-0.028
ait-0.024
andel-0.024
 Annie-0.023
Token of
Token ID286
Feature activation+2.28e-01

Pos logit contributions
ocol+0.040
irs+0.034
ait+0.030
andel+0.029
sie+0.028
Neg logit contributions
 owner-0.025
 not-0.025
 still-0.024
 was-0.023
 hurts-0.022
Token all
Token ID477
Feature activation-5.28e-01

Pos logit contributions
 owner+0.005
 not+0.004
 still+0.004
 hurts+0.004
 was+0.004
Neg logit contributions
ocol-0.009
irs-0.008
ait-0.007
andel-0.007
sie-0.007
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
ocol+0.024
irs+0.020
ait+0.018
andel+0.018
sie+0.017
Neg logit contributions
 owner-0.009
 not-0.008
 still-0.008
 was-0.008
 also-0.008
Token tiny
Token ID7009
Feature activation-2.31e-01

Pos logit contributions
ocol+0.056
irs+0.048
ait+0.047
uster+0.044
andel+0.044
Neg logit contributions
 owner-0.028
 not-0.027
 still-0.027
 was-0.026
 only-0.025
Token things
Token ID1243
Feature activation-3.42e+00

Pos logit contributions
ocol+0.009
irs+0.007
ait+0.007
andel+0.007
uster+0.006
Neg logit contributions
 owner-0.005
 was-0.005
 still-0.005
 not-0.005
 hurts-0.005
Token she
Token ID673
Feature activation-5.51e+00

Pos logit contributions
ocol+0.159
irs+0.136
andel+0.127
ait+0.126
sie+0.120
Neg logit contributions
 not-0.051
 owner-0.050
 still-0.049
 was-0.045
 also-0.042
Token would
Token ID561
Feature activation-3.24e+00

Pos logit contributions
ocol+0.243
irs+0.209
ait+0.193
sie+0.189
andel+0.184
Neg logit contributions
 owner-0.081
 hurts-0.071
 not-0.071
zag-0.069
 hits-0.069
Token see
Token ID766
Feature activation-2.62e+00

Pos logit contributions
ocol+0.131
irs+0.112
ait+0.101
andel+0.097
sie+0.097
Neg logit contributions
 owner-0.063
 hurts-0.056
 not-0.055
 hits-0.054
zag-0.052
Token with
Token ID351
Feature activation-1.89e+00

Pos logit contributions
ocol+0.120
irs+0.103
ait+0.095
andel+0.095
sie+0.091
Neg logit contributions
 owner-0.040
 not-0.038
 still-0.037
 was-0.035
 hurts-0.032
Token her
Token ID607
Feature activation-2.37e-01

Pos logit contributions
ocol+0.080
irs+0.068
ait+0.065
andel+0.064
sie+0.062
Neg logit contributions
 owner-0.035
 not-0.034
 still-0.034
 was-0.031
 only-0.030
Token microscope
Token ID36396
Feature activation-1.38e+00

Pos logit contributions
ocol+0.010
irs+0.008
ait+0.007
andel+0.007
sie+0.007
Neg logit contributions
 owner-0.005
 not-0.005
 still-0.005
 hurts-0.004
 was-0.004
Token Annie
Token ID25860
Feature activation+1.93e-01

Pos logit contributions
 owner+0.012
 not+0.012
 still+0.011
 was+0.011
 remembered+0.011
Neg logit contributions
ocol-0.033
irs-0.028
andel-0.025
ait-0.025
sie-0.024
Token said
Token ID531
Feature activation-1.86e+00

Pos logit contributions
 owner+0.003
 hits+0.003
 hurts+0.003
zag+0.003
tr+0.003
Neg logit contributions
ocol-0.008
irs-0.007
sie-0.006
ait-0.006
 Annie-0.006
Token it
Token ID340
Feature activation-6.39e-02

Pos logit contributions
ocol+0.075
irs+0.063
ait+0.057
andel+0.055
sie+0.055
Neg logit contributions
 owner-0.036
 not-0.033
 hurts-0.032
 hits-0.032
zag-0.032
Token was
Token ID373
Feature activation+4.83e-01

Pos logit contributions
ocol+0.003
irs+0.002
 Annie+0.002
sie+0.002
 Nancy+0.002
Neg logit contributions
 owner-0.001
 hits-0.001
zag-0.001
erved-0.000
flower-0.000
Token called
Token ID1444
Feature activation-4.72e+00

Pos logit contributions
 owner+0.009
 not+0.009
 still+0.008
 was+0.008
 only+0.008
Neg logit contributions
ocol-0.021
irs-0.018
ait-0.017
andel-0.016
sie-0.016
Token
Token ID6184
Feature activation-5.39e+00

Pos logit contributions
ocol+0.194
irs+0.174
inations+0.166
ait+0.159
 rubble+0.155
Neg logit contributions
 not-0.090
 owner-0.087
 only-0.077
 still-0.075
 was-0.075
Token
Token ID95
Feature activation-2.50e+00

Pos logit contributions
ocol+0.189
irs+0.157
andel+0.132
ait+0.130
 rubble+0.128
Neg logit contributions
 still-0.130
Because-0.128
 not-0.125
zag-0.123
 owner-0.122
Token
Token ID26391
Feature activation+6.52e-01

Pos logit contributions
ocol+0.092
irs+0.074
andel+0.065
ait+0.065
sie+0.062
Neg logit contributions
 owner-0.061
 not-0.060
 still-0.059
zag-0.056
 was-0.056
Token˜
Token ID41185
Feature activation+1.31e+00

Pos logit contributions
 owner+0.013
 not+0.012
 hurts+0.011
 still+0.011
 hits+0.011
Neg logit contributions
ocol-0.025
irs-0.022
ait-0.020
sie-0.019
andel-0.019
TokenPretty
Token ID35700
Feature activation+3.47e-01

Pos logit contributions
 owner+0.024
 not+0.023
 still+0.021
 was+0.021
flower+0.020
Neg logit contributions
ocol-0.057
irs-0.049
andel-0.044
ait-0.044
 rubble-0.042
Token Flowers
Token ID30036
Feature activation+5.86e-01

Pos logit contributions
 owner+0.007
 not+0.007
 still+0.007
 was+0.006
 also+0.006
Neg logit contributions
ocol-0.014
irs-0.012
ait-0.011
andel-0.011
sie-0.010
Token and
Token ID290
Feature activation+5.24e-01

Pos logit contributions
ocol+0.069
irs+0.059
andel+0.055
ait+0.055
uster+0.052
Neg logit contributions
 not-0.024
 still-0.023
 owner-0.023
 was-0.020
's-0.020
Token appreciate
Token ID9144
Feature activation-4.45e-01

Pos logit contributions
 owner+0.010
 not+0.008
 hurts+0.008
zag+0.008
 hits+0.008
Neg logit contributions
ocol-0.022
irs-0.018
ait-0.017
sie-0.016
andel-0.016
Token them
Token ID606
Feature activation-2.70e+00

Pos logit contributions
ocol+0.018
ait+0.015
andel+0.015
irs+0.015
uster+0.014
Neg logit contributions
 not-0.009
 still-0.008
 was-0.008
 owner-0.008
 also-0.008
Token for
Token ID329
Feature activation-8.98e-01

Pos logit contributions
ocol+0.126
irs+0.108
andel+0.102
ait+0.101
uster+0.095
Neg logit contributions
 not-0.045
 still-0.043
 owner-0.041
 was-0.037
 also-0.036
Token what
Token ID644
Feature activation-2.02e+00

Pos logit contributions
ocol+0.038
andel+0.032
irs+0.031
ait+0.031
uster+0.030
Neg logit contributions
 not-0.019
 still-0.016
 never-0.016
 owner-0.016
 also-0.015
Token they
Token ID484
Feature activation-5.76e+00

Pos logit contributions
ocol+0.086
irs+0.073
andel+0.068
ait+0.068
sie+0.064
Neg logit contributions
 owner-0.038
 not-0.037
 still-0.034
 was-0.034
 hurts-0.033
Token are
Token ID389
Feature activation-3.61e+00

Pos logit contributions
ocol+0.260
irs+0.224
ait+0.206
andel+0.202
sie+0.198
Neg logit contributions
 owner-0.088
 not-0.081
 still-0.077
 hurts-0.074
 hits-0.071
Token.
Token ID13
Feature activation-7.15e-01

Pos logit contributions
ocol+0.156
irs+0.134
ait+0.123
andel+0.122
sie+0.117
Neg logit contributions
 not-0.065
 owner-0.065
 still-0.061
 also-0.056
 was-0.055
Token She
Token ID1375
Feature activation-9.84e-01

Pos logit contributions
ocol+0.035
irs+0.029
andel+0.028
sie+0.028
ait+0.027
Neg logit contributions
 owner-0.009
 not-0.008
 still-0.008
 was-0.008
 also-0.007
Token said
Token ID531
Feature activation-2.29e+00

Pos logit contributions
ocol+0.040
irs+0.035
ait+0.034
sie+0.033
 Annie+0.032
Neg logit contributions
 owner-0.014
 hurts-0.014
 hits-0.013
zag-0.013
 not-0.013
Token that
Token ID326
Feature activation+2.14e+00

Pos logit contributions
ocol+0.113
irs+0.100
ait+0.092
andel+0.090
sie+0.088
Neg logit contributions
 not-0.028
 owner-0.027
 still-0.024
 was-0.022
 only-0.021