TOP ACTIVATIONS
MAX = 5.105

will not play with was ps anymore . We will only
imp ers . He lim ps towards Tom . Tom picks
to always take big gul ps of oxygen so he could
sees her papers and gas ps . " What have you
He gets up and lim ps away . He leaves Lily
you a packet of cris ps ". Al
were other long sh rim ps in the ocean . Nem
ate lots of healthy sou ps made from strawberries . He
opened the packet of cris ps . She was no longer
They see many sh rim ps and fish and crabs .
big chorus of ch ir ps . Rus sel
ground gave him Goose bum ps . He was so scared
and Ben . She gas ps . She runs to them
face . Max y el ps and backs away .
S ara gas ps and runs to her picture
no bees , only was ps . They are mean and
To her amaz ement , the clothes came out
He cries and st om ps his feet . He does
spells and fly on bro oms . They had fun with
a camel with two hum ps and a lion with a

MIN ACTIVATIONS
MIN = -5.729

on her own little a pron too . As
high to reach the a pron on the top shelf .
gave her a pretty a pron to wear . Lily was
and gave her an a pron to put on . Then
Lily put on the a pron and felt very proud of
mom gave her an a pron with a bright pink flower
Jane hopped on the sees aw and before long she was
see how much the a pron weighed . Lily was surprised
Lily wore a pink a pron and Ben wore a blue
the help of her a pron , she could make creations
the pockets of her a pron to store her supplies .
my put on her a pron , she said , "
take care of your a pron because it 's already very
the kitchen wearing an a pron . She was singing to
home and removed his a pron . He was happy to
her amazing , expensive a pron . <|endoftext|> One day ,
mom had a graceful a pron , too . It was
princess put on an a pron . She looked so attractive
home with the colorful a pron still tied around her waist
so attractive in the a pron that everyone wanted to see

INTERVAL 2.397 - 5.105
CONTAINS 0.704%

Mia are scared . They are sorry . They cry .
I 'm sorry , Ben ," Lily said . " I
pieces . Lily and Ben are sad . "
can 't find my toy ," Lily replied .
a number on his hat ," she said . The police

INTERVAL -0.312 - 2.397
CONTAINS 69.907%

wish . <|endoftext|> L ily and Ben are playing in the
the new things he saw . Suddenly , he noticed something
sound . The dog was surprised and scared . He ran
very happy . Now , Tim could wear his
moment . They like y ummy break f asts and fun

INTERVAL -3.020 - -0.312
CONTAINS 29.366%

butter on the pancakes and it was so smooth .
get a point ." They keep playing the game
love riding the silver bike at the park !" They stayed
from a distant friend . S ue was so
The teacher asked , " Where should we go now

INTERVAL -5.729 - -3.020
CONTAINS 0.023%

and jumped in the p udd les . He shouted ,
home . They learned that sharing can make them happy and
the blanket . Now c udd ling up on the blanket
the slide and the sees aw . But their favorite thing
special moment as well as sharing the shirt
Token will
Token ID481
Feature activation+8.94e-01

Pos logit contributions
 plunge+0.019
piring+0.018
chie+0.017
aro+0.016
ps+0.016
Neg logit contributions
ravings-0.026
pron-0.025
Years-0.024
 habit-0.023
omo-0.022
Token not
Token ID407
Feature activation-5.50e-01

Pos logit contributions
 plunge+0.078
piring+0.075
chie+0.069
aro+0.068
ps+0.067
Neg logit contributions
ravings-0.071
pron-0.068
Years-0.067
 habit-0.064
 loved-0.064
Token play
Token ID711
Feature activation-8.89e-01

Pos logit contributions
ravings+0.047
pron+0.045
Years+0.045
 habit+0.042
 loved+0.042
Neg logit contributions
 plunge-0.045
piring-0.043
chie-0.039
aro-0.038
 afloat-0.038
Token with
Token ID351
Feature activation-4.12e-01

Pos logit contributions
ravings+0.055
pron+0.051
Years+0.050
 loved+0.049
 habit+0.048
Neg logit contributions
 plunge-0.093
piring-0.090
chie-0.085
aro-0.083
ps-0.081
Token was
Token ID373
Feature activation+8.50e-02

Pos logit contributions
ravings+0.038
pron+0.036
Years+0.036
 loved+0.035
 habit+0.034
Neg logit contributions
 plunge-0.031
piring-0.030
chie-0.027
aro-0.026
ps-0.026
Tokenps
Token ID862
Feature activation+5.11e+00

Pos logit contributions
 plunge+0.007
piring+0.007
aro+0.007
ps+0.007
 aboard+0.006
Neg logit contributions
ravings-0.007
Years-0.006
pron-0.006
 habit-0.006
omo-0.006
Token anymore
Token ID7471
Feature activation+7.29e-01

Pos logit contributions
 plunge+0.458
piring+0.443
chie+0.412
aro+0.406
ps+0.395
Neg logit contributions
ravings-0.390
pron-0.368
Years-0.364
 loved-0.349
 habit-0.348
Token.
Token ID13
Feature activation+3.77e-01

Pos logit contributions
 plunge+0.060
piring+0.058
aro+0.054
chie+0.053
ps+0.053
Neg logit contributions
ravings-0.060
Years-0.057
pron-0.057
 habit-0.054
 loved-0.053
Token We
Token ID775
Feature activation+4.61e-01

Pos logit contributions
 plunge+0.037
piring+0.035
chie+0.034
aro+0.033
iest+0.032
Neg logit contributions
ravings-0.026
 loved-0.024
Years-0.024
pron-0.024
omo-0.023
Token will
Token ID481
Feature activation+9.41e-01

Pos logit contributions
 plunge+0.034
piring+0.032
chie+0.029
aro+0.029
ps+0.028
Neg logit contributions
ravings-0.044
pron-0.042
Years-0.042
 habit-0.039
omo-0.039
Token only
Token ID691
Feature activation+2.79e-01

Pos logit contributions
 plunge+0.083
piring+0.078
chie+0.073
ps+0.072
aro+0.072
Neg logit contributions
ravings-0.074
pron-0.070
Years-0.069
 habit-0.064
 batch-0.063
Tokenimp
Token ID11011
Feature activation+3.08e+00

Pos logit contributions
ravings+0.068
pron+0.065
Years+0.065
 loved+0.062
 habit+0.062
Neg logit contributions
 plunge-0.051
piring-0.049
chie-0.045
aro-0.044
ps-0.043
Tokeners
Token ID364
Feature activation+1.64e+00

Pos logit contributions
 plunge+0.231
piring+0.219
chie+0.202
 afloat+0.197
aro+0.188
Neg logit contributions
ravings-0.281
Years-0.269
pron-0.265
 loved-0.265
udd-0.252
Token.
Token ID13
Feature activation-1.11e-01

Pos logit contributions
 plunge+0.147
piring+0.141
ps+0.131
aro+0.129
chie+0.129
Neg logit contributions
ravings-0.127
pron-0.122
Years-0.120
omo-0.113
 habit-0.112
Token He
Token ID679
Feature activation-2.25e-01

Pos logit contributions
ravings+0.009
pron+0.009
Years+0.009
 habit+0.008
 loved+0.008
Neg logit contributions
 plunge-0.009
piring-0.009
chie-0.008
aro-0.008
ps-0.008
Token lim
Token ID1761
Feature activation-5.65e-01

Pos logit contributions
ravings+0.020
pron+0.020
Years+0.019
 habit+0.018
omo+0.017
Neg logit contributions
 plunge-0.017
piring-0.016
ps-0.016
aro-0.015
 aboard-0.015
Tokenps
Token ID862
Feature activation+4.94e+00

Pos logit contributions
ravings+0.070
Years+0.066
 loved+0.066
L+0.065
udd+0.065
Neg logit contributions
 plunge-0.025
piring-0.022
chie-0.017
 afloat-0.016
iest-0.015
Token towards
Token ID3371
Feature activation+6.58e-01

Pos logit contributions
 plunge+0.401
piring+0.386
ps+0.361
 aboard+0.354
aro+0.349
Neg logit contributions
ravings-0.425
pron-0.416
Years-0.392
 habit-0.380
omo-0.377
Token Tom
Token ID4186
Feature activation-1.18e+00

Pos logit contributions
 plunge+0.053
piring+0.050
aro+0.047
chie+0.046
ps+0.046
Neg logit contributions
ravings-0.057
pron-0.055
Years-0.053
 habit-0.052
udd-0.051
Token.
Token ID13
Feature activation-1.26e-01

Pos logit contributions
ravings+0.089
Years+0.087
pron+0.086
 habit+0.078
omo+0.078
Neg logit contributions
 plunge-0.106
piring-0.104
ps-0.096
chie-0.095
 afloat-0.094
Token Tom
Token ID4186
Feature activation-1.24e+00

Pos logit contributions
ravings+0.010
pron+0.010
Years+0.010
 habit+0.010
 loved+0.009
Neg logit contributions
 plunge-0.010
piring-0.010
aro-0.009
 aboard-0.009
oms-0.009
Token picks
Token ID11103
Feature activation+1.20e+00

Pos logit contributions
ravings+0.102
pron+0.100
Years+0.097
 habit+0.092
omo+0.088
Neg logit contributions
 plunge-0.104
piring-0.099
ps-0.095
aro-0.091
 aboard-0.090
Token to
Token ID284
Feature activation-3.50e-01

Pos logit contributions
 plunge+0.027
piring+0.026
aro+0.024
chie+0.024
 aboard+0.024
Neg logit contributions
ravings-0.018
pron-0.017
Years-0.017
 habit-0.016
 loved-0.015
Token always
Token ID1464
Feature activation-1.93e+00

Pos logit contributions
ravings+0.027
Years+0.025
pron+0.025
 loved+0.025
 habit+0.024
Neg logit contributions
 plunge-0.031
piring-0.030
chie-0.028
aro-0.028
oms-0.027
Token take
Token ID1011
Feature activation-1.46e-01

Pos logit contributions
 loved+0.144
ravings+0.144
 friend+0.138
 habit+0.138
 often+0.136
Neg logit contributions
piring-0.170
 plunge-0.166
aro-0.161
chie-0.160
ions-0.155
Token big
Token ID1263
Feature activation+3.80e-01

Pos logit contributions
ravings+0.010
 loved+0.010
Years+0.010
 habit+0.009
 friend+0.009
Neg logit contributions
 plunge-0.014
piring-0.013
chie-0.013
aro-0.013
oms-0.012
Token gul
Token ID47161
Feature activation-9.99e-01

Pos logit contributions
chie+0.034
piring+0.033
 plunge+0.032
aro+0.032
ter+0.030
Neg logit contributions
ravings-0.028
 loved-0.027
 friend-0.026
 tum-0.026
 favorite-0.026
Tokenps
Token ID862
Feature activation+4.91e+00

Pos logit contributions
ravings+0.097
Years+0.091
 loved+0.089
 habit+0.087
pron+0.087
Neg logit contributions
piring-0.066
 plunge-0.065
chie-0.061
aro-0.058
oms-0.055
Token of
Token ID286
Feature activation+1.57e+00

Pos logit contributions
 plunge+0.430
piring+0.416
chie+0.388
aro+0.383
ps+0.369
Neg logit contributions
ravings-0.384
pron-0.361
Years-0.360
 loved-0.349
 habit-0.344
Token oxygen
Token ID11863
Feature activation+2.58e-01

Pos logit contributions
 plunge+0.141
piring+0.141
chie+0.133
aro+0.127
oms+0.126
Neg logit contributions
ravings-0.117
Years-0.108
pron-0.108
 loved-0.107
 habit-0.105
Token so
Token ID523
Feature activation+2.65e-03

Pos logit contributions
 plunge+0.025
piring+0.025
chie+0.024
aro+0.023
ps+0.022
Neg logit contributions
ravings-0.017
pron-0.016
Years-0.016
 loved-0.016
 habit-0.015
Token he
Token ID339
Feature activation-2.88e-01

Pos logit contributions
 plunge+0.000
piring+0.000
chie+0.000
aro+0.000
ps+0.000
Neg logit contributions
ravings-0.000
pron-0.000
Years-0.000
 loved-0.000
 habit-0.000
Token could
Token ID714
Feature activation-2.90e-01

Pos logit contributions
ravings+0.020
pron+0.019
Years+0.018
omo+0.017
 habit+0.017
Neg logit contributions
 plunge-0.028
piring-0.027
aro-0.025
chie-0.025
ps-0.025
Token sees
Token ID7224
Feature activation+4.38e-01

Pos logit contributions
ravings+0.005
pron+0.005
Years+0.005
 habit+0.005
 loved+0.005
Neg logit contributions
 plunge-0.005
piring-0.005
chie-0.004
aro-0.004
ps-0.004
Token her
Token ID607
Feature activation+7.52e-01

Pos logit contributions
 plunge+0.039
piring+0.037
chie+0.036
aro+0.034
 afloat+0.034
Neg logit contributions
ravings-0.034
pron-0.032
 loved-0.032
Years-0.031
 dentist-0.030
Token papers
Token ID9473
Feature activation+1.28e-01

Pos logit contributions
 plunge+0.071
piring+0.070
ps+0.067
oms+0.064
chie+0.063
Neg logit contributions
ravings-0.052
Years-0.051
pron-0.047
As-0.045
While-0.045
Token and
Token ID290
Feature activation-1.05e-01

Pos logit contributions
 plunge+0.014
piring+0.013
chie+0.013
aro+0.013
 Deer+0.012
Neg logit contributions
ravings-0.008
pron-0.008
 loved-0.007
 often-0.007
 friend-0.007
Token gas
Token ID3623
Feature activation-4.83e-01

Pos logit contributions
ravings+0.008
pron+0.007
 loved+0.007
Years+0.007
 habit+0.007
Neg logit contributions
 plunge-0.010
piring-0.010
chie-0.009
aro-0.009
 afloat-0.009
Tokenps
Token ID862
Feature activation+4.91e+00

Pos logit contributions
ravings+0.035
 loved+0.034
pron+0.033
 friend+0.031
udd+0.031
Neg logit contributions
 plunge-0.045
piring-0.042
chie-0.040
aro-0.039
 nearer-0.037
Token.
Token ID13
Feature activation-1.50e-01

Pos logit contributions
 plunge+0.498
piring+0.472
chie+0.455
aro+0.450
 aboard+0.423
Neg logit contributions
ravings-0.322
Years-0.299
 loved-0.297
pron-0.296
 habit-0.285
Token "
Token ID366
Feature activation-1.01e+00

Pos logit contributions
ravings+0.015
pron+0.014
Years+0.014
 habit+0.014
 loved+0.013
Neg logit contributions
 plunge-0.010
piring-0.010
aro-0.008
chie-0.008
oms-0.008
TokenWhat
Token ID2061
Feature activation+4.18e-01

Pos logit contributions
ravings+0.075
Years+0.072
pron+0.072
 loved+0.068
 habit+0.066
Neg logit contributions
 plunge-0.093
piring-0.088
chie-0.082
aro-0.081
ps-0.079
Token have
Token ID423
Feature activation+1.70e+00

Pos logit contributions
 plunge+0.024
piring+0.023
aro+0.019
chie+0.019
oms+0.019
Neg logit contributions
ravings-0.046
Years-0.045
pron-0.044
 habit-0.042
omo-0.041
Token you
Token ID345
Feature activation+2.30e-01

Pos logit contributions
 plunge+0.125
piring+0.120
chie+0.110
aro+0.107
 afloat+0.105
Neg logit contributions
ravings-0.159
pron-0.152
Years-0.150
 loved-0.147
 habit-0.144
Token He
Token ID679
Feature activation-2.52e-01

Pos logit contributions
pron+0.016
Years+0.015
ravings+0.015
becca+0.014
 habit+0.014
Neg logit contributions
ps-0.005
 plunge-0.005
 onto-0.005
piring-0.005
oms-0.004
Token gets
Token ID3011
Feature activation+6.85e-01

Pos logit contributions
pron+0.026
ravings+0.025
Years+0.024
 habit+0.024
While+0.022
Neg logit contributions
ps-0.016
 plunge-0.015
oms-0.014
 aboard-0.014
aro-0.013
Token up
Token ID510
Feature activation+2.55e-01

Pos logit contributions
 plunge+0.048
piring+0.045
ps+0.042
aro+0.041
chie+0.041
Neg logit contributions
ravings-0.068
pron-0.066
Years-0.064
 habit-0.062
becca-0.059
Token and
Token ID290
Feature activation-8.36e-02

Pos logit contributions
 plunge+0.025
piring+0.025
chie+0.023
aro+0.022
 aboard+0.022
Neg logit contributions
ravings-0.017
pron-0.016
Years-0.016
 loved-0.015
 habit-0.015
Token lim
Token ID1761
Feature activation-5.89e-01

Pos logit contributions
ravings+0.007
pron+0.007
Years+0.007
 loved+0.007
 habit+0.006
Neg logit contributions
 plunge-0.007
piring-0.007
chie-0.006
aro-0.006
iest-0.006
Tokenps
Token ID862
Feature activation+4.91e+00

Pos logit contributions
ravings+0.067
 loved+0.063
Years+0.063
udd+0.062
 habit+0.061
Neg logit contributions
 plunge-0.033
piring-0.030
chie-0.025
 afloat-0.023
aro-0.022
Token away
Token ID1497
Feature activation+1.49e+00

Pos logit contributions
 plunge+0.406
piring+0.390
ps+0.364
chie+0.358
aro+0.356
Neg logit contributions
ravings-0.410
pron-0.402
Years-0.378
 habit-0.362
omo-0.361
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
 plunge+0.136
piring+0.132
chie+0.123
aro+0.122
ps+0.120
Neg logit contributions
ravings-0.112
pron-0.107
Years-0.105
 loved-0.100
 habit-0.099
Token He
Token ID679
Feature activation-2.75e-01

Pos logit contributions
pron+0.020
Years+0.019
ravings+0.018
 habit+0.018
 batch+0.018
Neg logit contributions
ps-0.006
 plunge-0.006
 onto-0.005
piring-0.005
 Tri-0.005
Token leaves
Token ID5667
Feature activation+9.59e-01

Pos logit contributions
pron+0.029
ravings+0.028
Years+0.027
 habit+0.026
Days+0.025
Neg logit contributions
 plunge-0.017
ps-0.017
aro-0.015
oms-0.015
piring-0.015
Token Lily
Token ID20037
Feature activation-7.64e-01

Pos logit contributions
 plunge+0.082
piring+0.080
chie+0.078
used+0.070
aro+0.070
Neg logit contributions
ravings-0.071
 loved-0.071
 often-0.069
Years-0.068
pron-0.066
Token you
Token ID345
Feature activation+1.31e-01

Pos logit contributions
 plunge+0.052
piring+0.050
chie+0.045
aro+0.045
ps+0.043
Neg logit contributions
ravings-0.062
pron-0.059
Years-0.058
 loved-0.056
 habit-0.056
Token a
Token ID257
Feature activation-3.27e-01

Pos logit contributions
 plunge+0.011
piring+0.011
chie+0.010
aro+0.010
 aboard+0.010
Neg logit contributions
ravings-0.010
pron-0.010
Years-0.010
 habit-0.009
 loved-0.009
Token packet
Token ID19638
Feature activation-1.99e-01

Pos logit contributions
ravings+0.028
Years+0.026
udd+0.025
omo+0.024
 often+0.024
Neg logit contributions
 plunge-0.028
piring-0.025
chie-0.024
 nearer-0.024
 aboard-0.023
Token of
Token ID286
Feature activation+1.50e+00

Pos logit contributions
ravings+0.015
pron+0.015
Years+0.014
 loved+0.014
 friend+0.014
Neg logit contributions
 plunge-0.018
piring-0.017
aro-0.016
chie-0.016
 afloat-0.015
Token cris
Token ID4442
Feature activation-1.74e+00

Pos logit contributions
 plunge+0.117
piring+0.115
chie+0.105
aro+0.102
 afloat+0.100
Neg logit contributions
ravings-0.131
pron-0.125
Years-0.122
 loved-0.121
 habit-0.119
Tokenps
Token ID862
Feature activation+4.88e+00

Pos logit contributions
ravings+0.226
pron+0.218
Years+0.216
 loved+0.210
 habit+0.210
Neg logit contributions
 plunge-0.064
piring-0.060
chie-0.048
aro-0.047
 afloat-0.042
Token".
Token ID1911
Feature activation+6.78e-02

Pos logit contributions
 plunge+0.405
piring+0.391
chie+0.361
aro+0.358
 afloat+0.343
Neg logit contributions
ravings-0.406
pron-0.383
Years-0.376
 loved-0.368
 habit-0.363
Token
Token ID220
Feature activation+1.34e-01

Pos logit contributions
 plunge+0.007
piring+0.007
chie+0.006
aro+0.006
ps+0.006
Neg logit contributions
ravings-0.004
Years-0.004
pron-0.004
 loved-0.004
 habit-0.004
Token
Token ID198
Feature activation-3.27e-01

Pos logit contributions
 plunge+0.014
piring+0.013
chie+0.013
aro+0.012
 aboard+0.012
Neg logit contributions
ravings-0.008
pron-0.008
Years-0.008
 habit-0.007
 loved-0.007
Token
Token ID198
Feature activation-3.33e-01

Pos logit contributions
ravings+0.022
pron+0.020
Years+0.019
 habit+0.019
 loved+0.018
Neg logit contributions
 plunge-0.033
piring-0.032
chie-0.030
aro-0.030
 aboard-0.029
TokenAl
Token ID2348
Feature activation-4.56e-01

Pos logit contributions
ravings+0.026
pron+0.024
 habit+0.023
Years+0.023
 loved+0.023
Neg logit contributions
 plunge-0.029
piring-0.029
chie-0.027
aro-0.027
 aboard-0.026
Token were
Token ID547
Feature activation+1.30e+00

Pos logit contributions
 plunge+0.092
piring+0.090
chie+0.090
ps+0.086
 afloat+0.084
Neg logit contributions
 loved-0.042
ravings-0.039
 often-0.037
 friend-0.037
 habit-0.037
Token other
Token ID584
Feature activation+1.68e-01

Pos logit contributions
 plunge+0.118
piring+0.114
chie+0.106
aro+0.105
ps+0.102
Neg logit contributions
ravings-0.098
pron-0.093
Years-0.092
 habit-0.087
 loved-0.087
Token long
Token ID890
Feature activation-4.67e-04

Pos logit contributions
 plunge+0.015
piring+0.015
chie+0.014
aro+0.014
ps+0.013
Neg logit contributions
ravings-0.013
 loved-0.012
 friend-0.011
 habit-0.011
pron-0.011
Token sh
Token ID427
Feature activation+1.44e+00

Pos logit contributions
ravings+0.000
pron+0.000
 loved+0.000
Years+0.000
 habit+0.000
Neg logit contributions
 plunge-0.000
piring-0.000
chie-0.000
aro-0.000
ps-0.000
Tokenrim
Token ID3036
Feature activation-1.50e-01

Pos logit contributions
 plunge+0.128
piring+0.124
chie+0.114
aro+0.113
ps+0.110
Neg logit contributions
ravings-0.114
pron-0.106
Years-0.105
 loved-0.101
 habit-0.100
Tokenps
Token ID862
Feature activation+4.88e+00

Pos logit contributions
ravings+0.019
 loved+0.018
 habit+0.018
Years+0.018
pron+0.018
Neg logit contributions
 plunge-0.006
piring-0.005
oms-0.004
aro-0.004
 afloat-0.004
Token in
Token ID287
Feature activation-2.80e-02

Pos logit contributions
 plunge+0.442
piring+0.426
chie+0.404
aro+0.396
ps+0.378
Neg logit contributions
ravings-0.365
 loved-0.339
pron-0.339
Years-0.338
 habit-0.327
Token the
Token ID262
Feature activation+6.92e-02

Pos logit contributions
ravings+0.002
 friend+0.002
 loved+0.002
pron+0.002
 owner+0.002
Neg logit contributions
piring-0.003
 plunge-0.003
chie-0.002
aro-0.002
oms-0.002
Token ocean
Token ID9151
Feature activation-1.03e-01

Pos logit contributions
 plunge+0.005
piring+0.005
chie+0.005
aro+0.005
ps+0.005
Neg logit contributions
ravings-0.006
pron-0.006
 loved-0.006
Years-0.006
 habit-0.006
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
ravings+0.007
pron+0.007
Years+0.007
 loved+0.006
 habit+0.006
Neg logit contributions
 plunge-0.010
piring-0.010
chie-0.009
aro-0.009
ps-0.009
Token Nem
Token ID22547
Feature activation+8.03e-02

Pos logit contributions
 plunge+0.014
 Bert+0.013
 aboard+0.012
 Tri+0.012
wood+0.012
Neg logit contributions
pron-0.020
Years-0.017
ravings-0.017
Days-0.016
 dentist-0.016
Token ate
Token ID15063
Feature activation-1.37e+00

Pos logit contributions
ravings+0.055
pron+0.053
Years+0.052
omo+0.050
becca+0.048
Neg logit contributions
piring-0.085
 plunge-0.081
aro-0.079
ter-0.078
iest-0.078
Token lots
Token ID6041
Feature activation-1.43e+00

Pos logit contributions
ravings+0.105
pron+0.100
Years+0.098
 habit+0.094
omo+0.093
Neg logit contributions
 plunge-0.123
piring-0.117
aro-0.106
 aboard-0.106
ps-0.106
Token of
Token ID286
Feature activation+1.53e+00

Pos logit contributions
ravings+0.125
pron+0.118
Years+0.117
 loved+0.113
 habit+0.113
Neg logit contributions
 plunge-0.113
piring-0.109
chie-0.101
aro-0.099
ps-0.096
Token healthy
Token ID5448
Feature activation-4.09e-01

Pos logit contributions
 plunge+0.163
piring+0.156
chie+0.145
aro+0.145
ps+0.143
Neg logit contributions
ravings-0.094
pron-0.086
Years-0.086
 habit-0.081
 loved-0.079
Token sou
Token ID24049
Feature activation-1.22e+00

Pos logit contributions
ravings+0.030
pron+0.028
Years+0.027
 loved+0.027
 habit+0.027
Neg logit contributions
 plunge-0.038
piring-0.037
chie-0.035
aro-0.035
ps-0.033
Tokenps
Token ID862
Feature activation+4.87e+00

Pos logit contributions
 loved+0.116
 often+0.116
Years+0.114
ravings+0.112
pron+0.110
Neg logit contributions
 plunge-0.080
piring-0.067
 afloat-0.067
chie-0.065
oms-0.065
Token made
Token ID925
Feature activation-1.82e+00

Pos logit contributions
 plunge+0.455
piring+0.438
chie+0.413
aro+0.406
ps+0.393
Neg logit contributions
ravings-0.354
pron-0.332
Years-0.329
 loved-0.319
 habit-0.314
Token from
Token ID422
Feature activation+1.62e+00

Pos logit contributions
ravings+0.165
pron+0.158
Years+0.157
 habit+0.149
 loved+0.148
Neg logit contributions
 plunge-0.139
piring-0.133
chie-0.119
aro-0.119
 aboard-0.118
Token strawberries
Token ID36973
Feature activation-1.00e-01

Pos logit contributions
 plunge+0.127
piring+0.118
aro+0.112
ps+0.110
 afloat+0.109
Neg logit contributions
ravings-0.144
pron-0.140
Years-0.136
udd-0.134
omo-0.133
Token.
Token ID13
Feature activation+1.19e-01

Pos logit contributions
ravings+0.006
pron+0.006
Years+0.006
 loved+0.006
 habit+0.006
Neg logit contributions
 plunge-0.010
piring-0.010
chie-0.010
aro-0.009
ps-0.009
Token He
Token ID679
Feature activation-1.70e-01

Pos logit contributions
 plunge+0.009
piring+0.009
chie+0.008
 aboard+0.008
ions+0.008
Neg logit contributions
pron-0.010
ravings-0.010
Years-0.009
 habit-0.009
 loved-0.009
Token opened
Token ID4721
Feature activation+1.30e+00

Pos logit contributions
ravings+0.011
pron+0.010
Years+0.010
 habit+0.010
 loved+0.009
Neg logit contributions
 plunge-0.015
piring-0.015
chie-0.014
aro-0.014
 aboard-0.013
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
 plunge+0.101
piring+0.098
chie+0.090
aro+0.088
ps+0.085
Neg logit contributions
ravings-0.114
pron-0.108
Years-0.107
 loved-0.105
 habit-0.103
Token packet
Token ID19638
Feature activation-2.41e-01

Pos logit contributions
 plunge+0.002
piring+0.002
chie+0.002
aro+0.002
ps+0.002
Neg logit contributions
ravings-0.002
pron-0.002
Years-0.002
 habit-0.002
 loved-0.002
Token of
Token ID286
Feature activation+1.45e+00

Pos logit contributions
ravings+0.019
pron+0.018
Years+0.017
 loved+0.017
 habit+0.017
Neg logit contributions
 plunge-0.021
piring-0.020
chie-0.019
aro-0.019
ps-0.018
Token cris
Token ID4442
Feature activation-1.75e+00

Pos logit contributions
 plunge+0.116
piring+0.112
chie+0.104
aro+0.101
ps+0.099
Neg logit contributions
ravings-0.125
pron-0.120
Years-0.118
 loved-0.116
 habit-0.114
Tokenps
Token ID862
Feature activation+4.85e+00

Pos logit contributions
ravings+0.245
pron+0.235
Years+0.234
 loved+0.228
 habit+0.225
Neg logit contributions
 plunge-0.049
piring-0.044
aro-0.034
chie-0.032
oms-0.028
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
 plunge+0.450
piring+0.430
chie+0.412
aro+0.409
ps+0.383
Neg logit contributions
ravings-0.355
pron-0.329
Years-0.326
 loved-0.324
 habit-0.315
Token She
Token ID1375
Feature activation-8.10e-02

Pos logit contributions
ravings+0.012
pron+0.011
Years+0.011
 habit+0.011
 loved+0.011
Neg logit contributions
 plunge-0.011
piring-0.011
chie-0.010
aro-0.010
ps-0.010
Token was
Token ID373
Feature activation-2.53e-01

Pos logit contributions
ravings+0.006
Years+0.006
 habit+0.006
pron+0.006
Days+0.005
Neg logit contributions
 plunge-0.007
piring-0.007
aro-0.006
 onto-0.006
 aboard-0.006
Token no
Token ID645
Feature activation-8.70e-01

Pos logit contributions
ravings+0.022
Years+0.021
pron+0.021
 habit+0.020
udd+0.019
Neg logit contributions
 plunge-0.020
piring-0.020
chie-0.018
ps-0.018
aro-0.018
Token longer
Token ID2392
Feature activation-1.44e+00

Pos logit contributions
ravings+0.061
pron+0.058
Years+0.057
 loved+0.053
 habit+0.052
Neg logit contributions
 plunge-0.085
piring-0.079
chie-0.076
iest-0.074
oms-0.074
Token They
Token ID1119
Feature activation-1.86e-01

Pos logit contributions
pron+0.015
ravings+0.015
Years+0.014
 habit+0.014
 batch+0.013
Neg logit contributions
 plunge-0.010
piring-0.010
 aboard-0.009
oms-0.009
ps-0.009
Token see
Token ID766
Feature activation+1.19e+00

Pos logit contributions
ravings+0.016
pron+0.015
 loved+0.015
Years+0.015
 habit+0.015
Neg logit contributions
 plunge-0.015
piring-0.014
chie-0.013
aro-0.013
 aboard-0.013
Token many
Token ID867
Feature activation-1.33e+00

Pos logit contributions
 plunge+0.103
piring+0.100
chie+0.092
aro+0.091
ps+0.088
Neg logit contributions
ravings-0.095
pron-0.090
Years-0.089
 loved-0.085
 habit-0.085
Token sh
Token ID427
Feature activation+1.68e+00

Pos logit contributions
ravings+0.095
 loved+0.095
 friend+0.090
pron+0.087
 habit+0.087
Neg logit contributions
 plunge-0.119
piring-0.116
chie-0.113
aro-0.108
used-0.106
Tokenrim
Token ID3036
Feature activation+1.67e-01

Pos logit contributions
 plunge+0.150
piring+0.145
chie+0.134
aro+0.132
 aboard+0.129
Neg logit contributions
ravings-0.131
pron-0.123
Years-0.122
 loved-0.117
 habit-0.116
Tokenps
Token ID862
Feature activation+4.85e+00

Pos logit contributions
 plunge+0.006
piring+0.005
 afloat+0.004
chie+0.004
aro+0.004
Neg logit contributions
ravings-0.020
 loved-0.020
Years-0.020
ast-0.020
 habit-0.020
Token and
Token ID290
Feature activation+2.35e-02

Pos logit contributions
 plunge+0.493
piring+0.469
chie+0.463
aro+0.447
 afloat+0.420
Neg logit contributions
ravings-0.310
 loved-0.294
Years-0.288
pron-0.282
 habit-0.275
Token fish
Token ID5916
Feature activation+8.97e-01

Pos logit contributions
 plunge+0.002
piring+0.002
chie+0.002
aro+0.002
iest+0.002
Neg logit contributions
ravings-0.002
 loved-0.002
pron-0.002
 habit-0.002
Years-0.002
Token and
Token ID290
Feature activation+3.14e-02

Pos logit contributions
 plunge+0.095
chie+0.089
piring+0.088
aro+0.083
iest+0.081
Neg logit contributions
ravings-0.053
 loved-0.051
 friend-0.050
 often-0.047
pron-0.046
Token crabs
Token ID49172
Feature activation+1.36e+00

Pos logit contributions
 plunge+0.002
piring+0.002
chie+0.002
aro+0.002
 aboard+0.002
Neg logit contributions
ravings-0.003
pron-0.003
 loved-0.003
Years-0.003
 habit-0.003
Token.
Token ID13
Feature activation-9.67e-02

Pos logit contributions
 plunge+0.145
chie+0.139
piring+0.137
aro+0.129
iest+0.125
Neg logit contributions
ravings-0.079
 loved-0.076
pron-0.072
 often-0.070
 friend-0.070
Token big
Token ID1263
Feature activation+2.92e-01

Pos logit contributions
ravings+0.026
Years+0.023
pron+0.023
 loved+0.022
udd+0.022
Neg logit contributions
 plunge-0.033
piring-0.031
chie-0.030
 afloat-0.029
 nearer-0.028
Token chorus
Token ID26441
Feature activation-7.29e-01

Pos logit contributions
 plunge+0.026
piring+0.025
chie+0.023
aro+0.023
 afloat+0.023
Neg logit contributions
ravings-0.023
pron-0.021
Years-0.021
 loved-0.020
 habit-0.020
Token of
Token ID286
Feature activation+1.51e+00

Pos logit contributions
ravings+0.054
pron+0.052
Years+0.051
 loved+0.050
 habit+0.049
Neg logit contributions
 plunge-0.066
piring-0.063
chie-0.060
aro-0.058
 afloat-0.057
Token ch
Token ID442
Feature activation-3.14e-01

Pos logit contributions
 plunge+0.134
piring+0.130
chie+0.122
aro+0.120
ps+0.115
Neg logit contributions
ravings-0.116
pron-0.109
Years-0.109
 loved-0.106
 habit-0.105
Tokenir
Token ID343
Feature activation+3.12e+00

Pos logit contributions
ravings+0.034
Years+0.031
udd+0.030
 loved+0.030
 often+0.030
Neg logit contributions
 plunge-0.019
piring-0.018
 afloat-0.015
 extingu-0.015
 aboard-0.015
Tokenps
Token ID862
Feature activation+4.84e+00

Pos logit contributions
 plunge+0.189
piring+0.176
chie+0.153
aro+0.152
 afloat+0.150
Neg logit contributions
ravings-0.331
Years-0.316
 loved-0.311
pron-0.311
 habit-0.308
Token.
Token ID13
Feature activation-7.16e-02

Pos logit contributions
 plunge+0.463
piring+0.442
chie+0.422
aro+0.418
 afloat+0.398
Neg logit contributions
ravings-0.331
Years-0.313
 loved-0.312
pron-0.311
 habit-0.300
Token
Token ID198
Feature activation-3.30e-01

Pos logit contributions
ravings+0.005
Years+0.004
pron+0.004
 loved+0.004
 habit+0.004
Neg logit contributions
 plunge-0.007
piring-0.007
chie-0.007
aro-0.007
ps-0.006
Token
Token ID198
Feature activation-3.17e-01

Pos logit contributions
ravings+0.023
pron+0.021
Years+0.019
 habit+0.019
omo+0.018
Neg logit contributions
 plunge-0.033
piring-0.032
aro-0.030
chie-0.030
 aboard-0.030
TokenRus
Token ID35313
Feature activation-1.30e+00

Pos logit contributions
ravings+0.021
pron+0.020
 habit+0.018
Years+0.018
 loved+0.018
Neg logit contributions
 plunge-0.032
piring-0.031
chie-0.029
aro-0.029
 aboard-0.028
Tokensel
Token ID741
Feature activation+1.27e+00

Pos logit contributions
ravings+0.115
Years+0.110
pron+0.108
 habit+0.105
 loved+0.105
Neg logit contributions
 plunge-0.100
piring-0.096
chie-0.090
aro-0.087
ps-0.086
Token ground
Token ID2323
Feature activation+2.96e-01

Pos logit contributions
 plunge+0.053
piring+0.053
chie+0.049
aro+0.048
ps+0.047
Neg logit contributions
ravings-0.047
 loved-0.044
pron-0.043
 habit-0.043
Years-0.043
Token gave
Token ID2921
Feature activation-4.54e-01

Pos logit contributions
 plunge+0.031
piring+0.031
chie+0.029
aro+0.028
ps+0.028
Neg logit contributions
ravings-0.018
pron-0.017
Years-0.016
 habit-0.015
 loved-0.015
Token him
Token ID683
Feature activation+1.17e+00

Pos logit contributions
ravings+0.043
pron+0.041
Years+0.041
 habit+0.039
 loved+0.039
Neg logit contributions
 plunge-0.033
piring-0.031
chie-0.029
aro-0.028
ps-0.027
Token Goose
Token ID46317
Feature activation-1.28e+00

Pos logit contributions
 plunge+0.102
piring+0.097
chie+0.090
ps+0.088
aro+0.088
Neg logit contributions
ravings-0.095
pron-0.095
Years-0.089
omo-0.085
 habit-0.084
Tokenbum
Token ID4435
Feature activation-3.32e-01

Pos logit contributions
ravings+0.107
pron+0.106
Years+0.103
omo+0.094
 dentist+0.093
Neg logit contributions
piring-0.108
 plunge-0.108
 aboard-0.097
chie-0.097
aro-0.095
Tokenps
Token ID862
Feature activation+4.83e+00

Pos logit contributions
ravings+0.026
pron+0.024
Years+0.024
 loved+0.023
 habit+0.023
Neg logit contributions
 plunge-0.029
piring-0.028
chie-0.026
aro-0.026
ps-0.025
Token.
Token ID13
Feature activation-3.31e-01

Pos logit contributions
 plunge+0.455
piring+0.441
chie+0.412
aro+0.407
ps+0.396
Neg logit contributions
ravings-0.346
pron-0.325
Years-0.322
 loved-0.309
 habit-0.307
Token He
Token ID679
Feature activation-4.77e-01

Pos logit contributions
ravings+0.025
pron+0.024
Years+0.024
 habit+0.023
 loved+0.023
Neg logit contributions
 plunge-0.030
piring-0.028
chie-0.026
aro-0.026
 aboard-0.026
Token was
Token ID373
Feature activation-3.39e-01

Pos logit contributions
ravings+0.042
pron+0.039
 habit+0.037
 cousin+0.035
omo+0.034
Neg logit contributions
 plunge-0.037
aro-0.033
 nearer-0.033
piring-0.033
 Flo-0.032
Token so
Token ID523
Feature activation-8.43e-03

Pos logit contributions
ravings+0.030
pron+0.028
Years+0.028
 habit+0.027
omo+0.026
Neg logit contributions
 plunge-0.027
piring-0.026
chie-0.024
ps-0.024
aro-0.023
Token scared
Token ID12008
Feature activation+9.44e-01

Pos logit contributions
ravings+0.001
pron+0.000
Years+0.000
 habit+0.000
 loved+0.000
Neg logit contributions
 plunge-0.001
piring-0.001
chie-0.001
aro-0.001
ps-0.001
Token and
Token ID290
Feature activation-2.72e-02

Pos logit contributions
ravings+0.054
pron+0.050
Years+0.049
 loved+0.048
 habit+0.047
Neg logit contributions
 plunge-0.078
piring-0.076
chie-0.071
aro-0.070
 afloat-0.068
Token Ben
Token ID3932
Feature activation-1.72e+00

Pos logit contributions
ravings+0.002
pron+0.002
Years+0.002
 loved+0.002
 habit+0.001
Neg logit contributions
 plunge-0.003
piring-0.003
chie-0.003
aro-0.003
 afloat-0.002
Token.
Token ID13
Feature activation-9.93e-02

Pos logit contributions
ravings+0.123
pron+0.115
 loved+0.114
Years+0.113
 habit+0.111
Neg logit contributions
 plunge-0.161
piring-0.154
chie-0.147
aro-0.144
 aboard-0.138
Token She
Token ID1375
Feature activation+3.73e-02

Pos logit contributions
ravings+0.006
L+0.006
 loved+0.006
 owner+0.006
pron+0.006
Neg logit contributions
 plunge-0.011
piring-0.010
chie-0.010
 afloat-0.009
ps-0.009
Token gas
Token ID3623
Feature activation-4.17e-01

Pos logit contributions
 plunge+0.003
piring+0.003
chie+0.003
 afloat+0.003
aro+0.003
Neg logit contributions
ravings-0.003
 loved-0.003
Years-0.003
 friend-0.003
omo-0.002
Tokenps
Token ID862
Feature activation+4.83e+00

Pos logit contributions
 loved+0.049
ravings+0.048
pron+0.047
 owner+0.047
 friend+0.047
Neg logit contributions
 plunge-0.018
piring-0.016
chie-0.015
iest-0.012
aro-0.012
Token.
Token ID13
Feature activation-9.28e-02

Pos logit contributions
 plunge+0.535
piring+0.503
chie+0.493
aro+0.488
iest+0.456
Neg logit contributions
ravings-0.267
 loved-0.261
Years-0.253
 often-0.238
 habit-0.237
Token She
Token ID1375
Feature activation+1.66e-02

Pos logit contributions
ravings+0.006
pron+0.006
 loved+0.006
Years+0.006
L+0.006
Neg logit contributions
 plunge-0.009
piring-0.009
chie-0.009
 afloat-0.008
ps-0.008
Token runs
Token ID4539
Feature activation+1.18e+00

Pos logit contributions
 plunge+0.001
piring+0.001
chie+0.001
 afloat+0.001
aro+0.001
Neg logit contributions
ravings-0.001
 loved-0.001
Years-0.001
pron-0.001
omo-0.001
Token to
Token ID284
Feature activation-1.45e-01

Pos logit contributions
 plunge+0.109
piring+0.105
 aboard+0.098
aro+0.097
chie+0.097
Neg logit contributions
ravings-0.090
pron-0.088
 habit-0.081
Years-0.080
omo-0.079
Token them
Token ID606
Feature activation+1.36e+00

Pos logit contributions
 friend+0.009
L+0.009
 loved+0.009
Years+0.009
ravings+0.009
Neg logit contributions
piring-0.014
chie-0.013
iest-0.013
 plunge-0.013
iful-0.012
Token face
Token ID1986
Feature activation-2.65e+00

Pos logit contributions
 plunge+0.015
piring+0.014
aro+0.013
chie+0.013
 aboard+0.013
Neg logit contributions
ravings-0.010
pron-0.009
Years-0.009
 loved-0.009
 habit-0.009
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
ravings+0.204
pron+0.193
Years+0.193
 habit+0.182
 loved+0.178
Neg logit contributions
 plunge-0.234
piring-0.231
chie-0.211
ps-0.210
aro-0.208
Token Max
Token ID5436
Feature activation-1.15e+00

Pos logit contributions
ravings+0.031
Years+0.030
pron+0.030
 habit+0.029
udd+0.027
Neg logit contributions
 plunge-0.030
piring-0.029
aro-0.027
oms-0.026
 aboard-0.026
Token y
Token ID331
Feature activation-4.20e-02

Pos logit contributions
ravings+0.097
pron+0.094
Years+0.092
 habit+0.087
omo+0.084
Neg logit contributions
 plunge-0.095
piring-0.091
ps-0.083
aro-0.083
chie-0.082
Tokenel
Token ID417
Feature activation+3.73e+00

Pos logit contributions
ravings+0.005
omo+0.004
Years+0.004
pron+0.004
udd+0.004
Neg logit contributions
 plunge-0.002
piring-0.002
aro-0.002
chie-0.002
 aboard-0.002
Tokenps
Token ID862
Feature activation+4.82e+00

Pos logit contributions
 plunge+0.181
piring+0.158
chie+0.134
 afloat+0.131
aro+0.131
Neg logit contributions
 loved-0.442
ravings-0.430
 friend-0.425
 owner-0.412
 favorite-0.411
Token and
Token ID290
Feature activation-2.98e-01

Pos logit contributions
 plunge+0.455
piring+0.442
chie+0.408
aro+0.403
ps+0.403
Neg logit contributions
ravings-0.348
pron-0.330
Years-0.323
 habit-0.304
 loved-0.301
Token backs
Token ID12983
Feature activation+1.72e+00

Pos logit contributions
ravings+0.025
pron+0.024
Years+0.024
 habit+0.023
 loved+0.023
Neg logit contributions
 plunge-0.024
piring-0.023
chie-0.021
aro-0.021
ps-0.021
Token away
Token ID1497
Feature activation+1.34e+00

Pos logit contributions
 plunge+0.116
piring+0.111
chie+0.100
aro+0.098
ps+0.094
Neg logit contributions
ravings-0.171
pron-0.164
Years-0.163
 loved-0.157
 habit-0.157
Token.
Token ID13
Feature activation-3.40e-01

Pos logit contributions
 plunge+0.121
piring+0.119
chie+0.110
aro+0.109
ps+0.108
Neg logit contributions
ravings-0.102
pron-0.097
Years-0.096
 habit-0.090
 loved-0.090
Token
Token ID198
Feature activation-4.57e-01

Pos logit contributions
ravings+0.028
pron+0.027
Years+0.027
 habit+0.026
udd+0.024
Neg logit contributions
 plunge-0.026
piring-0.026
aro-0.025
 aboard-0.024
oms-0.023
Token
Token ID198
Feature activation-3.17e-01

Pos logit contributions
ravings+0.021
Years+0.021
pron+0.021
 habit+0.020
 loved+0.019
Neg logit contributions
 plunge-0.017
piring-0.016
aro-0.015
oms-0.014
ps-0.014
Token
Token ID198
Feature activation-3.32e-01

Pos logit contributions
ravings+0.026
pron+0.025
 habit+0.023
Years+0.023
 batch+0.021
Neg logit contributions
 plunge-0.027
piring-0.025
aro-0.025
oms-0.023
ions-0.023
TokenS
Token ID50
Feature activation-3.72e-01

Pos logit contributions
ravings+0.026
 habit+0.024
pron+0.023
Years+0.022
 batch+0.022
Neg logit contributions
 plunge-0.029
aro-0.027
piring-0.027
 ourselves-0.026
ions-0.025
Tokenara
Token ID3301
Feature activation-1.58e+00

Pos logit contributions
ravings+0.017
Years+0.017
pron+0.016
 habit+0.016
 loved+0.016
Neg logit contributions
 plunge-0.043
piring-0.041
oms-0.040
ps-0.038
 aboard-0.038
Token gas
Token ID3623
Feature activation-3.56e-01

Pos logit contributions
ravings+0.155
pron+0.153
Years+0.153
 habit+0.144
Days+0.137
Neg logit contributions
 plunge-0.107
ps-0.100
piring-0.100
oms-0.097
 aboard-0.091
Tokenps
Token ID862
Feature activation+4.82e+00

Pos logit contributions
ravings+0.045
 loved+0.043
pron+0.043
Years+0.042
 friend+0.041
Neg logit contributions
 plunge-0.014
piring-0.013
chie-0.011
aro-0.010
 afloat-0.009
Token and
Token ID290
Feature activation-2.50e-01

Pos logit contributions
 plunge+0.443
piring+0.432
ps+0.399
chie+0.397
aro+0.388
Neg logit contributions
ravings-0.357
pron-0.341
Years-0.328
 habit-0.312
omo-0.307
Token runs
Token ID4539
Feature activation+1.14e+00

Pos logit contributions
ravings+0.020
 loved+0.019
pron+0.019
Years+0.019
 habit+0.018
Neg logit contributions
 plunge-0.021
piring-0.021
chie-0.020
aro-0.019
iest-0.018
Token to
Token ID284
Feature activation-2.41e-01

Pos logit contributions
 plunge+0.080
piring+0.076
 aboard+0.071
ps+0.071
 nearer+0.069
Neg logit contributions
pron-0.110
ravings-0.110
omo-0.104
Years-0.101
 habit-0.100
Token her
Token ID607
Feature activation+7.20e-01

Pos logit contributions
ravings+0.022
pron+0.021
Years+0.020
 loved+0.020
 habit+0.020
Neg logit contributions
 plunge-0.019
piring-0.018
chie-0.017
aro-0.016
ps-0.016
Token picture
Token ID4286
Feature activation-7.03e-02

Pos logit contributions
 plunge+0.076
piring+0.074
ps+0.071
 aboard+0.069
aro+0.069
Neg logit contributions
Years-0.041
ravings-0.040
pron-0.037
Days-0.034
Even-0.034
Token no
Token ID645
Feature activation-6.80e-01

Pos logit contributions
 plunge+0.098
piring+0.094
chie+0.088
aro+0.087
ps+0.086
Neg logit contributions
ravings-0.084
pron-0.080
Years-0.079
 habit-0.075
 loved-0.074
Token bees
Token ID17002
Feature activation+1.23e+00

Pos logit contributions
ravings+0.056
Years+0.054
pron+0.053
udd+0.050
 loved+0.049
Neg logit contributions
 plunge-0.058
piring-0.053
ps-0.050
aro-0.049
chie-0.049
Token,
Token ID11
Feature activation+1.75e-01

Pos logit contributions
 plunge+0.114
piring+0.107
chie+0.105
aro+0.099
 afloat+0.097
Neg logit contributions
ravings-0.089
 loved-0.085
 often-0.079
pron-0.078
 friend-0.078
Token only
Token ID691
Feature activation+7.93e-02

Pos logit contributions
 plunge+0.016
piring+0.016
chie+0.015
aro+0.014
 aboard+0.014
Neg logit contributions
ravings-0.013
 loved-0.012
pron-0.012
Years-0.011
 habit-0.011
Token was
Token ID373
Feature activation-1.10e-01

Pos logit contributions
 plunge+0.007
piring+0.007
chie+0.006
aro+0.006
 afloat+0.006
Neg logit contributions
ravings-0.006
 loved-0.006
pron-0.006
 habit-0.005
Years-0.005
Tokenps
Token ID862
Feature activation+4.81e+00

Pos logit contributions
ravings+0.009
pron+0.008
Years+0.008
 habit+0.008
 loved+0.008
Neg logit contributions
 plunge-0.010
piring-0.009
chie-0.009
aro-0.009
ps-0.008
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
 plunge+0.437
piring+0.418
chie+0.391
aro+0.384
 afloat+0.372
Neg logit contributions
ravings-0.364
pron-0.337
 loved-0.335
Years-0.335
 habit-0.322
Token They
Token ID1119
Feature activation-8.26e-02

Pos logit contributions
 plunge+0.012
piring+0.011
chie+0.010
 afloat+0.010
ps+0.010
Neg logit contributions
ravings-0.012
 loved-0.011
pron-0.011
Years-0.011
 friend-0.011
Token are
Token ID389
Feature activation+2.93e+00

Pos logit contributions
 loved+0.008
ravings+0.007
 often+0.007
 habit+0.007
 friend+0.007
Neg logit contributions
 plunge-0.006
piring-0.006
aro-0.005
chie-0.005
 aboard-0.005
Token mean
Token ID1612
Feature activation+2.23e-01

Pos logit contributions
 plunge+0.295
piring+0.285
chie+0.268
aro+0.264
 aboard+0.256
Neg logit contributions
ravings-0.192
pron-0.179
Years-0.176
 loved-0.172
 habit-0.168
Token and
Token ID290
Feature activation+9.26e-02

Pos logit contributions
 plunge+0.021
piring+0.020
chie+0.019
aro+0.019
ps+0.018
Neg logit contributions
ravings-0.016
pron-0.015
Years-0.015
 habit-0.014
 loved-0.014
Token
Token ID198
Feature activation-2.67e-01

Pos logit contributions
 plunge+0.005
piring+0.004
chie+0.004
aro+0.004
 aboard+0.004
Neg logit contributions
ravings-0.004
pron-0.004
Years-0.004
 habit-0.004
 loved-0.004
Token
Token ID198
Feature activation-2.31e-01

Pos logit contributions
ravings+0.023
 habit+0.021
pron+0.020
udd+0.019
auldron+0.019
Neg logit contributions
aro-0.021
 plunge-0.021
chie-0.020
ions-0.020
piring-0.020
TokenTo
Token ID2514
Feature activation+8.21e-01

Pos logit contributions
ravings+0.018
 habit+0.016
udd+0.016
 favorite+0.016
 tum+0.016
Neg logit contributions
chie-0.020
aro-0.020
 plunge-0.020
piring-0.019
ions-0.019
Token her
Token ID607
Feature activation+1.08e+00

Pos logit contributions
 plunge+0.071
piring+0.068
chie+0.063
aro+0.062
 afloat+0.061
Neg logit contributions
ravings-0.066
pron-0.063
Years-0.062
 loved-0.061
 habit-0.060
Token amaz
Token ID40642
Feature activation+3.20e+00

Pos logit contributions
 plunge+0.091
piring+0.084
chie+0.079
 aboard+0.076
 afloat+0.076
Neg logit contributions
ravings-0.090
pron-0.085
Years-0.082
udd-0.080
 loved-0.079
Tokenement
Token ID972
Feature activation+4.81e+00

Pos logit contributions
 plunge+0.202
piring+0.194
aro+0.168
chie+0.168
 afloat+0.167
Neg logit contributions
ravings-0.334
pron-0.326
Years-0.319
 loved-0.309
 friend-0.305
Token,
Token ID11
Feature activation+3.56e-01

Pos logit contributions
 plunge+0.419
piring+0.401
chie+0.377
aro+0.370
ps+0.359
Neg logit contributions
ravings-0.378
pron-0.362
 loved-0.349
Years-0.348
 friend-0.343
Token the
Token ID262
Feature activation+2.18e-01

Pos logit contributions
 plunge+0.028
piring+0.027
chie+0.025
aro+0.024
ps+0.023
Neg logit contributions
ravings-0.031
pron-0.030
Years-0.030
 loved-0.029
 habit-0.028
Token clothes
Token ID8242
Feature activation+1.35e-01

Pos logit contributions
 plunge+0.021
piring+0.019
chie+0.018
aro+0.018
ps+0.018
Neg logit contributions
ravings-0.016
Years-0.015
pron-0.014
udd-0.014
While-0.014
Token came
Token ID1625
Feature activation-6.19e-01

Pos logit contributions
 plunge+0.012
piring+0.012
chie+0.011
aro+0.011
 afloat+0.010
Neg logit contributions
ravings-0.010
 loved-0.010
pron-0.010
Years-0.009
 habit-0.009
Token out
Token ID503
Feature activation-3.72e-01

Pos logit contributions
ravings+0.052
 loved+0.051
Years+0.051
pron+0.051
 friend+0.051
Neg logit contributions
 plunge-0.047
piring-0.045
aro-0.045
chie-0.041
iest-0.040
Token He
Token ID679
Feature activation-3.39e-01

Pos logit contributions
ravings+0.019
pron+0.019
Years+0.018
 habit+0.018
becca+0.017
Neg logit contributions
 plunge-0.016
piring-0.015
aro-0.014
 aboard-0.014
chie-0.014
Token cries
Token ID24691
Feature activation+1.09e+00

Pos logit contributions
pron+0.031
ravings+0.031
Years+0.030
 habit+0.029
omo+0.028
Neg logit contributions
 plunge-0.024
ps-0.023
piring-0.023
oms-0.021
 aboard-0.021
Token and
Token ID290
Feature activation-2.74e-02

Pos logit contributions
 plunge+0.107
piring+0.102
chie+0.097
aro+0.096
 afloat+0.092
Neg logit contributions
ravings-0.076
Years-0.071
pron-0.070
 loved-0.069
 habit-0.068
Token st
Token ID336
Feature activation+1.03e+00

Pos logit contributions
ravings+0.002
pron+0.002
Years+0.002
 loved+0.002
 habit+0.002
Neg logit contributions
 plunge-0.002
piring-0.002
chie-0.002
aro-0.002
 afloat-0.002
Tokenom
Token ID296
Feature activation-1.71e+00

Pos logit contributions
 plunge+0.098
piring+0.095
chie+0.088
aro+0.087
iest+0.084
Neg logit contributions
ravings-0.074
pron-0.068
Years-0.068
 loved-0.065
 habit-0.064
Tokenps
Token ID862
Feature activation+4.81e+00

Pos logit contributions
ravings+0.227
pron+0.219
Years+0.218
 loved+0.214
 habit+0.212
Neg logit contributions
 plunge-0.058
piring-0.052
chie-0.042
aro-0.039
 afloat-0.036
Token his
Token ID465
Feature activation+2.55e-01

Pos logit contributions
 plunge+0.416
piring+0.406
ps+0.374
chie+0.369
aro+0.364
Neg logit contributions
ravings-0.384
pron-0.369
Years-0.353
 habit-0.339
omo-0.333
Token feet
Token ID3625
Feature activation+1.39e+00

Pos logit contributions
 plunge+0.024
piring+0.023
chie+0.022
aro+0.022
ps+0.021
Neg logit contributions
ravings-0.018
pron-0.017
Years-0.017
 loved-0.016
 habit-0.016
Token.
Token ID13
Feature activation-2.13e-01

Pos logit contributions
 plunge+0.140
piring+0.135
chie+0.128
aro+0.126
 aboard+0.121
Neg logit contributions
ravings-0.090
pron-0.084
Years-0.083
 loved-0.082
 habit-0.079
Token He
Token ID679
Feature activation-3.65e-01

Pos logit contributions
ravings+0.017
pron+0.016
Years+0.016
 habit+0.016
 batch+0.015
Neg logit contributions
 plunge-0.018
piring-0.017
aro-0.016
chie-0.016
 aboard-0.016
Token does
Token ID857
Feature activation-1.69e-01

Pos logit contributions
pron+0.035
ravings+0.034
Years+0.033
 habit+0.032
omo+0.031
Neg logit contributions
 plunge-0.025
ps-0.024
piring-0.023
oms-0.022
 aboard-0.021
Token spells
Token ID10377
Feature activation+6.24e-01

Pos logit contributions
ravings+0.142
pron+0.134
Years+0.133
 loved+0.129
 habit+0.128
Neg logit contributions
 plunge-0.151
piring-0.145
chie-0.135
aro-0.133
 afloat-0.128
Token and
Token ID290
Feature activation+1.24e-01

Pos logit contributions
 plunge+0.071
chie+0.067
piring+0.066
aro+0.063
used+0.061
Neg logit contributions
 loved-0.033
ravings-0.032
Years-0.031
pron-0.031
 often-0.031
Token fly
Token ID6129
Feature activation+1.37e+00

Pos logit contributions
 plunge+0.011
piring+0.011
chie+0.010
aro+0.010
ps+0.010
Neg logit contributions
ravings-0.009
pron-0.009
Years-0.009
 habit-0.008
 loved-0.008
Token on
Token ID319
Feature activation-2.07e-02

Pos logit contributions
 plunge+0.123
piring+0.117
chie+0.110
aro+0.107
 afloat+0.103
Neg logit contributions
ravings-0.103
Years-0.100
 loved-0.099
pron-0.096
 habit-0.094
Token bro
Token ID1379
Feature activation+8.02e-01

Pos logit contributions
ravings+0.002
pron+0.002
Years+0.002
 habit+0.002
 loved+0.002
Neg logit contributions
 plunge-0.001
piring-0.001
chie-0.001
aro-0.001
ps-0.001
Tokenoms
Token ID3150
Feature activation+4.79e+00

Pos logit contributions
 plunge+0.060
piring+0.055
aro+0.051
 afloat+0.051
ps+0.050
Neg logit contributions
ravings-0.074
Years-0.071
udd-0.071
pron-0.070
L-0.068
Token.
Token ID13
Feature activation+1.35e-01

Pos logit contributions
 plunge+0.468
piring+0.449
chie+0.423
aro+0.416
 afloat+0.402
Neg logit contributions
ravings-0.330
pron-0.306
Years-0.306
 loved-0.298
 habit-0.291
Token They
Token ID1119
Feature activation-2.03e-01

Pos logit contributions
piring+0.009
 plunge+0.009
oms+0.008
 aboard+0.008
ps+0.008
Neg logit contributions
ravings-0.012
pron-0.012
Years-0.012
 habit-0.011
becca-0.011
Token had
Token ID550
Feature activation+4.61e-01

Pos logit contributions
ravings+0.017
pron+0.015
Years+0.015
 habit+0.014
 batch+0.014
Neg logit contributions
piring-0.017
 plunge-0.017
aro-0.016
ps-0.016
chie-0.015
Token fun
Token ID1257
Feature activation-5.39e-01

Pos logit contributions
 plunge+0.042
piring+0.041
ps+0.039
chie+0.038
 afloat+0.037
Neg logit contributions
ravings-0.034
pron-0.034
Years-0.031
 habit-0.030
omo-0.029
Token with
Token ID351
Feature activation-4.80e-01

Pos logit contributions
ravings+0.044
pron+0.041
Years+0.041
omo+0.038
 habit+0.038
Neg logit contributions
 plunge-0.046
piring-0.045
aro-0.042
ps-0.042
chie-0.041
Token a
Token ID257
Feature activation-4.30e-01

Pos logit contributions
 loved+0.007
ravings+0.007
pron+0.007
Years+0.006
 friend+0.006
Neg logit contributions
 plunge-0.013
piring-0.012
chie-0.012
aro-0.012
oms-0.011
Token camel
Token ID41021
Feature activation+1.13e+00

Pos logit contributions
ravings+0.032
pron+0.030
Years+0.029
 loved+0.028
 habit+0.028
Neg logit contributions
 plunge-0.040
piring-0.038
chie-0.036
aro-0.035
ps-0.034
Token with
Token ID351
Feature activation-6.92e-01

Pos logit contributions
 plunge+0.115
chie+0.107
piring+0.104
 nearer+0.097
 afloat+0.097
Neg logit contributions
ravings-0.073
 loved-0.072
pron-0.070
 friend-0.067
 owner-0.066
Token two
Token ID734
Feature activation+2.37e-01

Pos logit contributions
ravings+0.051
pron+0.048
Years+0.048
 loved+0.046
 habit+0.046
Neg logit contributions
 plunge-0.063
piring-0.061
chie-0.057
aro-0.056
ps-0.055
Token hum
Token ID1311
Feature activation-5.35e-01

Pos logit contributions
 plunge+0.021
piring+0.020
chie+0.019
aro+0.018
 aboard+0.018
Neg logit contributions
ravings-0.018
 loved-0.017
pron-0.017
 friend-0.017
Years-0.017
Tokenps
Token ID862
Feature activation+4.79e+00

Pos logit contributions
ravings+0.043
 loved+0.043
pron+0.043
Years+0.041
 often+0.040
Neg logit contributions
 plunge-0.045
piring-0.040
chie-0.038
 afloat-0.036
aro-0.036
Token and
Token ID290
Feature activation-2.67e-01

Pos logit contributions
 plunge+0.464
piring+0.444
chie+0.422
aro+0.416
 afloat+0.399
Neg logit contributions
ravings-0.328
pron-0.306
Years-0.305
 loved-0.301
 habit-0.292
Token a
Token ID257
Feature activation-5.13e-01

Pos logit contributions
ravings+0.021
pron+0.019
Years+0.019
 loved+0.019
 habit+0.019
Neg logit contributions
 plunge-0.023
piring-0.022
chie-0.021
aro-0.021
 afloat-0.020
Token lion
Token ID18744
Feature activation-7.90e-01

Pos logit contributions
ravings+0.041
Years+0.039
pron+0.037
 loved+0.036
 habit+0.035
Neg logit contributions
 plunge-0.045
piring-0.043
chie-0.040
aro-0.039
ps-0.038
Token with
Token ID351
Feature activation-7.42e-01

Pos logit contributions
ravings+0.055
pron+0.052
 loved+0.051
Years+0.050
 habit+0.049
Neg logit contributions
 plunge-0.075
piring-0.071
chie-0.068
aro-0.066
 afloat-0.064
Token a
Token ID257
Feature activation-5.46e-01

Pos logit contributions
ravings+0.058
pron+0.054
Years+0.054
 loved+0.052
 habit+0.052
Neg logit contributions
 plunge-0.065
piring-0.063
chie-0.059
aro-0.058
 afloat-0.056
Token on
Token ID319
Feature activation-6.11e-01

Pos logit contributions
 plunge+0.037
piring+0.036
chie+0.033
aro+0.032
 afloat+0.032
Neg logit contributions
ravings-0.036
pron-0.036
 loved-0.034
Years-0.034
 friend-0.032
Token her
Token ID607
Feature activation+5.02e-01

Pos logit contributions
ravings+0.056
pron+0.053
Years+0.053
 habit+0.052
 loved+0.050
Neg logit contributions
 plunge-0.046
piring-0.043
aro-0.040
chie-0.040
ps-0.039
Token own
Token ID898
Feature activation+2.50e-01

Pos logit contributions
 plunge+0.048
piring+0.047
chie+0.043
aro+0.043
ps+0.042
Neg logit contributions
ravings-0.036
pron-0.034
Years-0.033
 loved-0.032
 habit-0.032
Token little
Token ID1310
Feature activation-8.67e-01

Pos logit contributions
 plunge+0.023
piring+0.023
chie+0.021
aro+0.021
 afloat+0.020
Neg logit contributions
ravings-0.018
pron-0.018
Years-0.017
 loved-0.017
 habit-0.016
Token a
Token ID257
Feature activation-6.75e-01

Pos logit contributions
ravings+0.063
pron+0.060
Years+0.057
 loved+0.057
 habit+0.057
Neg logit contributions
 plunge-0.080
piring-0.078
chie-0.073
aro-0.073
ps-0.070
Tokenpron
Token ID31186
Feature activation-5.38e+00

Pos logit contributions
ravings+0.048
Years+0.045
 loved+0.041
 habit+0.041
udd+0.040
Neg logit contributions
 plunge-0.065
piring-0.061
chie-0.058
aro-0.056
 afloat-0.056
Token too
Token ID1165
Feature activation-5.08e-01

Pos logit contributions
ravings+0.414
Years+0.390
pron+0.383
 habit+0.371
 loved+0.361
Neg logit contributions
 plunge-0.476
piring-0.462
chie-0.422
aro-0.421
ps-0.419
Token.
Token ID13
Feature activation+6.45e-02

Pos logit contributions
ravings+0.037
pron+0.035
Years+0.034
 habit+0.033
 loved+0.032
Neg logit contributions
 plunge-0.047
piring-0.046
chie-0.043
aro-0.042
ps-0.041
Token
Token ID198
Feature activation-2.34e-01

Pos logit contributions
 plunge+0.005
piring+0.005
aro+0.004
chie+0.004
ions+0.004
Neg logit contributions
ravings-0.005
Years-0.005
pron-0.005
 habit-0.005
udd-0.005
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
ravings+0.021
 habit+0.019
pron+0.019
auldron+0.018
 favorite+0.018
Neg logit contributions
 plunge-0.017
aro-0.017
ions-0.016
piring-0.016
chie-0.016
TokenAs
Token ID1722
Feature activation-1.12e-01

Pos logit contributions
ravings+0.015
 tum+0.014
 habit+0.014
 favorite+0.013
auldron+0.013
Neg logit contributions
chie-0.015
 plunge-0.015
piring-0.015
aro-0.015
ions-0.015
Token high
Token ID1029
Feature activation-1.14e+00

Pos logit contributions
ravings+0.013
pron+0.012
Years+0.012
 loved+0.012
 habit+0.011
Neg logit contributions
 plunge-0.015
piring-0.015
chie-0.014
aro-0.014
 afloat-0.013
Token to
Token ID284
Feature activation-5.82e-01

Pos logit contributions
ravings+0.071
 loved+0.068
Years+0.067
pron+0.065
 often+0.065
Neg logit contributions
piring-0.115
 plunge-0.114
aro-0.105
chie-0.104
oms-0.099
Token reach
Token ID3151
Feature activation+7.95e-01

Pos logit contributions
ravings+0.046
 loved+0.045
Years+0.044
pron+0.044
 habit+0.043
Neg logit contributions
 plunge-0.048
piring-0.047
chie-0.044
oms-0.042
aro-0.042
Token the
Token ID262
Feature activation-3.15e-01

Pos logit contributions
piring+0.073
 plunge+0.072
chie+0.069
aro+0.065
oms+0.063
Neg logit contributions
 loved-0.053
ravings-0.052
 often-0.051
Years-0.050
 friend-0.050
Token a
Token ID257
Feature activation-8.27e-01

Pos logit contributions
ravings+0.025
pron+0.024
Years+0.023
 loved+0.023
 habit+0.023
Neg logit contributions
 plunge-0.027
piring-0.026
chie-0.024
aro-0.024
ps-0.023
Tokenpron
Token ID31186
Feature activation-5.26e+00

Pos logit contributions
ravings+0.065
Years+0.061
pron+0.060
 loved+0.058
 habit+0.058
Neg logit contributions
 plunge-0.073
piring-0.069
chie-0.065
aro-0.063
 afloat-0.062
Token on
Token ID319
Feature activation-7.06e-01

Pos logit contributions
ravings+0.379
pron+0.356
Years+0.352
 loved+0.337
 habit+0.336
Neg logit contributions
 plunge-0.493
piring-0.477
chie-0.445
aro-0.439
ps-0.428
Token the
Token ID262
Feature activation-3.57e-01

Pos logit contributions
ravings+0.060
pron+0.057
Years+0.057
 loved+0.055
 habit+0.054
Neg logit contributions
 plunge-0.057
piring-0.056
chie-0.051
aro-0.051
oms-0.048
Token top
Token ID1353
Feature activation-1.03e+00

Pos logit contributions
ravings+0.024
pron+0.022
Years+0.022
 loved+0.021
 habit+0.021
Neg logit contributions
 plunge-0.035
piring-0.034
chie-0.032
aro-0.032
ps-0.031
Token shelf
Token ID18316
Feature activation-7.78e-01

Pos logit contributions
ravings+0.066
pron+0.063
Years+0.060
 loved+0.059
 often+0.058
Neg logit contributions
 plunge-0.105
piring-0.102
chie-0.095
aro-0.095
ps-0.092
Token.
Token ID13
Feature activation-1.51e-01

Pos logit contributions
ravings+0.054
pron+0.051
Years+0.050
 loved+0.048
 habit+0.048
Neg logit contributions
 plunge-0.075
piring-0.073
chie-0.068
aro-0.067
ps-0.065
Token gave
Token ID2921
Feature activation-3.48e-01

Pos logit contributions
ravings+0.046
Years+0.044
pron+0.043
 habit+0.042
Days+0.039
Neg logit contributions
 plunge-0.066
piring-0.064
ps-0.061
 aboard-0.060
ter-0.060
Token her
Token ID607
Feature activation+7.15e-01

Pos logit contributions
ravings+0.033
pron+0.032
Years+0.031
 habit+0.030
omo+0.030
Neg logit contributions
 plunge-0.025
piring-0.024
chie-0.022
ps-0.022
 aboard-0.021
Token a
Token ID257
Feature activation-5.25e-01

Pos logit contributions
 plunge+0.056
piring+0.053
 aboard+0.048
ps+0.047
chie+0.047
Neg logit contributions
ravings-0.063
Years-0.059
pron-0.058
omo-0.056
 habit-0.056
Token pretty
Token ID2495
Feature activation+6.12e-01

Pos logit contributions
ravings+0.040
Years+0.036
omo+0.034
 often+0.034
udd+0.033
Neg logit contributions
 plunge-0.050
piring-0.045
chie-0.042
 aboard-0.041
oms-0.041
Token a
Token ID257
Feature activation-6.38e-01

Pos logit contributions
 plunge+0.055
piring+0.052
chie+0.048
aro+0.047
 aboard+0.047
Neg logit contributions
ravings-0.048
Years-0.045
pron-0.043
 loved-0.042
 habit-0.042
Tokenpron
Token ID31186
Feature activation-5.16e+00

Pos logit contributions
ravings+0.043
Years+0.038
udd+0.035
omo+0.035
 habit+0.035
Neg logit contributions
 plunge-0.066
piring-0.061
chie-0.057
 aboard-0.056
oms-0.055
Token to
Token ID284
Feature activation-4.85e-01

Pos logit contributions
ravings+0.388
Years+0.369
pron+0.350
 habit+0.343
omo+0.332
Neg logit contributions
 plunge-0.459
piring-0.453
aro-0.409
ps-0.408
chie-0.406
Token wear
Token ID5806
Feature activation+7.39e-01

Pos logit contributions
ravings+0.038
Years+0.035
pron+0.035
 habit+0.034
 loved+0.034
Neg logit contributions
 plunge-0.043
piring-0.041
chie-0.038
aro-0.037
ps-0.037
Token.
Token ID13
Feature activation-2.08e-01

Pos logit contributions
 plunge+0.064
piring+0.062
 aboard+0.057
chie+0.056
ps+0.056
Neg logit contributions
ravings-0.058
Years-0.054
 habit-0.053
pron-0.052
omo-0.052
Token Lily
Token ID20037
Feature activation-1.01e+00

Pos logit contributions
ravings+0.018
Years+0.017
 habit+0.016
pron+0.016
udd+0.016
Neg logit contributions
 plunge-0.016
piring-0.015
aro-0.014
 aboard-0.014
chie-0.014
Token was
Token ID373
Feature activation-3.68e-01

Pos logit contributions
ravings+0.097
 dentist+0.086
Years+0.082
Days+0.081
 habit+0.077
Neg logit contributions
 onto-0.057
 tw-0.054
neath-0.053
 plunge-0.052
ps-0.052
Token and
Token ID290
Feature activation-2.08e-01

Pos logit contributions
 plunge+0.097
piring+0.094
chie+0.087
aro+0.084
ps+0.083
Neg logit contributions
ravings-0.088
pron-0.083
Years-0.082
 habit-0.078
 loved-0.078
Token gave
Token ID2921
Feature activation-2.53e-01

Pos logit contributions
ravings+0.016
Years+0.015
pron+0.015
 habit+0.014
udd+0.014
Neg logit contributions
 plunge-0.019
piring-0.018
aro-0.016
chie-0.016
 aboard-0.016
Token her
Token ID607
Feature activation+6.78e-01

Pos logit contributions
ravings+0.023
Years+0.021
pron+0.021
 habit+0.021
omo+0.020
Neg logit contributions
 plunge-0.020
piring-0.018
chie-0.017
 aboard-0.017
ps-0.017
Token an
Token ID281
Feature activation-2.65e-01

Pos logit contributions
 plunge+0.055
piring+0.053
chie+0.049
 aboard+0.048
ps+0.047
Neg logit contributions
ravings-0.058
Years-0.054
pron-0.053
 habit-0.051
omo-0.051
Token a
Token ID257
Feature activation-5.24e-01

Pos logit contributions
ravings+0.019
pron+0.018
Years+0.018
 habit+0.017
 loved+0.017
Neg logit contributions
 plunge-0.025
piring-0.024
chie-0.022
ps-0.022
aro-0.021
Tokenpron
Token ID31186
Feature activation-5.15e+00

Pos logit contributions
ravings+0.037
Years+0.034
udd+0.032
omo+0.031
 habit+0.031
Neg logit contributions
 plunge-0.051
piring-0.048
chie-0.046
 aboard-0.044
iest-0.043
Token to
Token ID284
Feature activation-4.02e-01

Pos logit contributions
ravings+0.367
Years+0.340
pron+0.338
 habit+0.323
 loved+0.319
Neg logit contributions
 plunge-0.487
piring-0.476
chie-0.440
aro-0.433
ps-0.429
Token put
Token ID1234
Feature activation+4.83e-01

Pos logit contributions
ravings+0.034
Years+0.032
pron+0.031
 habit+0.030
 loved+0.030
Neg logit contributions
 plunge-0.033
piring-0.032
chie-0.029
aro-0.029
ps-0.028
Token on
Token ID319
Feature activation-3.40e-01

Pos logit contributions
 plunge+0.040
piring+0.038
chie+0.036
aro+0.035
 afloat+0.033
Neg logit contributions
ravings-0.040
pron-0.040
 loved-0.038
Years-0.038
 habit-0.036
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
ravings+0.029
pron+0.027
Years+0.027
 loved+0.026
 habit+0.026
Neg logit contributions
 plunge-0.028
piring-0.027
chie-0.025
aro-0.024
ps-0.024
Token Then
Token ID3244
Feature activation+2.35e-01

Pos logit contributions
ravings+0.010
Years+0.010
pron+0.010
 habit+0.009
udd+0.009
Neg logit contributions
 plunge-0.010
piring-0.010
chie-0.009
 aboard-0.009
ions-0.009
Token Lily
Token ID20037
Feature activation-1.03e+00

Pos logit contributions
 plunge+0.007
piring+0.007
aro+0.006
chie+0.006
ions+0.006
Neg logit contributions
ravings-0.009
pron-0.009
Years-0.009
 habit-0.008
udd-0.008
Token put
Token ID1234
Feature activation+5.16e-01

Pos logit contributions
ravings+0.074
Years+0.064
pron+0.060
Days+0.060
 owner+0.060
Neg logit contributions
ps-0.085
 plunge-0.085
 onto-0.082
neath-0.080
used-0.079
Token on
Token ID319
Feature activation-4.81e-01

Pos logit contributions
 plunge+0.042
piring+0.042
chie+0.039
aro+0.037
 afloat+0.036
Neg logit contributions
pron-0.045
ravings-0.043
 loved-0.042
Years-0.041
 favorite-0.039
Token the
Token ID262
Feature activation-2.30e-02

Pos logit contributions
ravings+0.050
 habit+0.047
Years+0.046
pron+0.045
omo+0.044
Neg logit contributions
 plunge-0.031
piring-0.027
ps-0.026
 onto-0.025
ions-0.024
Token a
Token ID257
Feature activation-5.24e-01

Pos logit contributions
pron+0.002
ravings+0.002
 loved+0.001
Years+0.001
 habit+0.001
Neg logit contributions
 plunge-0.002
piring-0.002
aro-0.002
chie-0.002
 afloat-0.002
Tokenpron
Token ID31186
Feature activation-5.15e+00

Pos logit contributions
ravings+0.013
Years+0.009
 habit+0.008
 loved+0.007
omo+0.006
Neg logit contributions
 plunge-0.076
piring-0.073
chie-0.070
aro-0.069
oms-0.069
Token and
Token ID290
Feature activation-1.67e-01

Pos logit contributions
ravings+0.402
Years+0.377
 habit+0.361
omo+0.357
pron+0.357
Neg logit contributions
 plunge-0.451
piring-0.433
ps-0.397
 aboard-0.391
aro-0.391
Token felt
Token ID2936
Feature activation-4.29e-01

Pos logit contributions
ravings+0.013
Years+0.012
 habit+0.012
pron+0.011
omo+0.011
Neg logit contributions
 plunge-0.015
piring-0.014
ps-0.013
 aboard-0.013
aro-0.013
Token very
Token ID845
Feature activation-4.92e-01

Pos logit contributions
ravings+0.031
Years+0.029
pron+0.029
omo+0.028
 habit+0.027
Neg logit contributions
 plunge-0.040
piring-0.039
chie-0.036
ps-0.035
 afloat-0.035
Token proud
Token ID6613
Feature activation-5.31e-01

Pos logit contributions
ravings+0.034
Years+0.032
pron+0.030
 dentist+0.029
omo+0.028
Neg logit contributions
 plunge-0.048
piring-0.046
chie-0.043
 afloat-0.042
ps-0.042
Token of
Token ID286
Feature activation+1.36e+00

Pos logit contributions
ravings+0.048
pron+0.046
Years+0.045
 habit+0.044
omo+0.042
Neg logit contributions
piring-0.039
 plunge-0.039
ions-0.034
iest-0.034
oms-0.034
Token mom
Token ID1995
Feature activation-4.92e-01

Pos logit contributions
 plunge+0.095
piring+0.090
chie+0.084
ter+0.083
 aboard+0.082
Neg logit contributions
ravings-0.049
Years-0.044
pron-0.044
As-0.040
Even-0.040
Token gave
Token ID2921
Feature activation-3.22e-01

Pos logit contributions
ravings+0.037
Years+0.034
 habit+0.033
pron+0.032
Days+0.031
Neg logit contributions
 plunge-0.042
piring-0.041
ter-0.040
 aboard-0.039
iest-0.038
Token her
Token ID607
Feature activation+8.26e-01

Pos logit contributions
ravings+0.029
pron+0.027
Years+0.027
 habit+0.026
omo+0.026
Neg logit contributions
 plunge-0.025
piring-0.024
chie-0.022
ps-0.021
aro-0.021
Token an
Token ID281
Feature activation-9.69e-02

Pos logit contributions
 plunge+0.064
piring+0.059
 aboard+0.055
chie+0.053
ps+0.053
Neg logit contributions
ravings-0.074
pron-0.069
Years-0.068
omo-0.067
 habit-0.065
Token a
Token ID257
Feature activation-3.48e-01

Pos logit contributions
ravings+0.007
pron+0.007
Years+0.007
 loved+0.007
 habit+0.007
Neg logit contributions
 plunge-0.009
piring-0.008
chie-0.008
aro-0.008
ps-0.007
Tokenpron
Token ID31186
Feature activation-5.12e+00

Pos logit contributions
ravings+0.027
Years+0.025
omo+0.023
 loved+0.023
udd+0.023
Neg logit contributions
 plunge-0.032
piring-0.030
chie-0.028
 aboard-0.027
 nearer-0.026
Token with
Token ID351
Feature activation-6.91e-01

Pos logit contributions
ravings+0.404
Years+0.391
pron+0.363
omo+0.358
Days+0.357
Neg logit contributions
piring-0.422
 plunge-0.416
 extingu-0.382
ions-0.377
iest-0.376
Token a
Token ID257
Feature activation-3.86e-01

Pos logit contributions
ravings+0.050
pron+0.047
Years+0.047
 habit+0.045
 loved+0.044
Neg logit contributions
 plunge-0.065
piring-0.063
chie-0.059
aro-0.058
ps-0.056
Token bright
Token ID6016
Feature activation+9.66e-02

Pos logit contributions
ravings+0.027
Years+0.025
udd+0.022
 habit+0.022
becca+0.021
Neg logit contributions
 plunge-0.038
piring-0.036
chie-0.033
oms-0.032
iest-0.032
Token pink
Token ID11398
Feature activation+3.15e-01

Pos logit contributions
 plunge+0.008
piring+0.008
chie+0.008
aro+0.008
ps+0.007
Neg logit contributions
ravings-0.008
pron-0.007
Years-0.007
 loved-0.007
 habit-0.007
Token flower
Token ID15061
Feature activation+2.73e-01

Pos logit contributions
 plunge+0.027
piring+0.026
chie+0.023
ps+0.023
 aboard+0.023
Neg logit contributions
ravings-0.025
Years-0.024
 habit-0.022
pron-0.022
udd-0.022
Token Jane
Token ID12091
Feature activation-4.57e-01

Pos logit contributions
 plunge+0.056
piring+0.054
chie+0.054
aro+0.053
ps+0.052
Neg logit contributions
 loved-0.041
ravings-0.038
 friend-0.037
 often-0.037
udd-0.036
Token hopped
Token ID45230
Feature activation-3.81e-01

Pos logit contributions
ravings+0.032
Years+0.030
pron+0.029
 habit+0.027
Days+0.026
Neg logit contributions
 plunge-0.045
piring-0.043
chie-0.040
ps-0.040
 aboard-0.039
Token on
Token ID319
Feature activation-7.52e-01

Pos logit contributions
 loved+0.031
pron+0.031
ravings+0.031
Years+0.030
 friend+0.030
Neg logit contributions
piring-0.029
 plunge-0.029
chie-0.027
aro-0.027
 afloat-0.025
Token the
Token ID262
Feature activation-5.50e-01

Pos logit contributions
ravings+0.054
Years+0.052
 loved+0.051
pron+0.051
 often+0.050
Neg logit contributions
piring-0.068
 plunge-0.067
chie-0.063
aro-0.062
 afloat-0.060
Token sees
Token ID7224
Feature activation-3.49e-01

Pos logit contributions
ravings+0.041
pron+0.039
Years+0.038
 loved+0.037
 habit+0.037
Neg logit contributions
piring-0.049
 plunge-0.048
aro-0.045
chie-0.045
ps-0.043
Tokenaw
Token ID707
Feature activation-5.12e+00

Pos logit contributions
ravings+0.027
pron+0.026
Years+0.025
 habit+0.024
omo+0.024
Neg logit contributions
 plunge-0.031
piring-0.030
chie-0.028
aro-0.027
ps-0.027
Token and
Token ID290
Feature activation-3.53e-01

Pos logit contributions
ravings+0.369
pron+0.347
Years+0.343
 loved+0.329
 habit+0.327
Neg logit contributions
 plunge-0.482
piring-0.466
chie-0.435
aro-0.429
ps-0.418
Token before
Token ID878
Feature activation-7.95e-01

Pos logit contributions
ravings+0.027
Years+0.025
pron+0.025
 habit+0.024
omo+0.023
Neg logit contributions
 plunge-0.033
piring-0.032
aro-0.030
 aboard-0.029
chie-0.028
Token long
Token ID890
Feature activation-2.24e-01

Pos logit contributions
ravings+0.060
pron+0.059
 loved+0.057
Years+0.056
 often+0.054
Neg logit contributions
 plunge-0.068
piring-0.068
chie-0.065
ps-0.061
aro-0.060
Token she
Token ID673
Feature activation+2.56e-01

Pos logit contributions
ravings+0.016
pron+0.015
 loved+0.015
Years+0.014
 friend+0.014
Neg logit contributions
 plunge-0.021
piring-0.020
chie-0.019
 afloat-0.018
aro-0.018
Token was
Token ID373
Feature activation-3.65e-01

Pos logit contributions
 plunge+0.024
piring+0.023
aro+0.022
chie+0.022
 aboard+0.021
Neg logit contributions
ravings-0.019
Years-0.018
pron-0.018
 habit-0.017
omo-0.016
Token see
Token ID766
Feature activation+1.19e+00

Pos logit contributions
ravings+0.018
 loved+0.018
pron+0.018
Years+0.017
 habit+0.017
Neg logit contributions
piring-0.022
 plunge-0.022
chie-0.020
aro-0.020
 afloat-0.020
Token how
Token ID703
Feature activation-5.93e-01

Pos logit contributions
 plunge+0.108
piring+0.104
chie+0.100
aro+0.096
ps+0.094
Neg logit contributions
ravings-0.088
pron-0.084
Years-0.083
 loved-0.081
 habit-0.079
Token much
Token ID881
Feature activation-4.84e-01

Pos logit contributions
ravings+0.050
 habit+0.045
Years+0.045
pron+0.045
omo+0.042
Neg logit contributions
 plunge-0.050
piring-0.049
chie-0.046
aro-0.044
 aboard-0.043
Token the
Token ID262
Feature activation-9.18e-02

Pos logit contributions
ravings+0.033
 loved+0.033
pron+0.033
Years+0.032
 often+0.031
Neg logit contributions
chie-0.046
piring-0.045
 plunge-0.045
ps-0.042
 afloat-0.042
Token a
Token ID257
Feature activation-5.67e-01

Pos logit contributions
ravings+0.007
Years+0.007
udd+0.007
 habit+0.006
As+0.006
Neg logit contributions
 plunge-0.008
piring-0.007
iest-0.007
 aboard-0.007
ps-0.007
Tokenpron
Token ID31186
Feature activation-5.12e+00

Pos logit contributions
ravings+0.045
udd+0.041
Years+0.039
ave+0.038
Even+0.038
Neg logit contributions
 plunge-0.049
piring-0.042
iest-0.041
 nearer-0.041
 aboard-0.041
Token weighed
Token ID20261
Feature activation-1.44e-01

Pos logit contributions
ravings+0.274
pron+0.248
Years+0.247
 habit+0.228
 loved+0.227
Neg logit contributions
 plunge-0.577
piring-0.561
chie-0.528
aro-0.524
ps-0.514
Token.
Token ID13
Feature activation-2.04e-02

Pos logit contributions
 loved+0.008
ravings+0.008
 often+0.008
pron+0.008
Years+0.008
Neg logit contributions
 plunge-0.015
piring-0.014
aro-0.014
chie-0.014
oms-0.013
Token Lily
Token ID20037
Feature activation-1.00e+00

Pos logit contributions
ravings+0.002
pron+0.002
Years+0.002
 habit+0.002
udd+0.002
Neg logit contributions
 plunge-0.001
piring-0.001
aro-0.001
 aboard-0.001
chie-0.001
Token was
Token ID373
Feature activation-3.60e-01

Pos logit contributions
ravings+0.086
Years+0.080
 habit+0.077
Days+0.076
pron+0.074
Neg logit contributions
 onto-0.068
 plunge-0.067
 aboard-0.065
ps-0.064
used-0.064
Token surprised
Token ID6655
Feature activation-3.27e-01

Pos logit contributions
ravings+0.033
Years+0.031
pron+0.030
 habit+0.029
udd+0.029
Neg logit contributions
 plunge-0.028
piring-0.026
ps-0.025
chie-0.024
 aboard-0.024
Token Lily
Token ID20037
Feature activation-8.78e-01

Pos logit contributions
 plunge+0.057
piring+0.055
aro+0.052
chie+0.050
 aboard+0.050
Neg logit contributions
ravings-0.056
Years-0.054
pron-0.053
 habit-0.051
udd-0.050
Token wore
Token ID12408
Feature activation+6.21e-02

Pos logit contributions
ravings+0.064
Years+0.063
pron+0.061
Days+0.058
 habit+0.053
Neg logit contributions
 plunge-0.073
ps-0.072
piring-0.068
 aboard-0.066
ter-0.066
Token a
Token ID257
Feature activation-2.94e-01

Pos logit contributions
 plunge+0.004
piring+0.004
ps+0.004
 aboard+0.004
 onto+0.004
Neg logit contributions
ravings-0.006
 habit-0.006
omo-0.005
Years-0.005
udd-0.005
Token pink
Token ID11398
Feature activation+2.84e-01

Pos logit contributions
ravings+0.026
Years+0.024
 habit+0.023
becca+0.022
udd+0.022
Neg logit contributions
 plunge-0.023
piring-0.021
 afloat-0.020
iest-0.019
 nearer-0.019
Token a
Token ID257
Feature activation-6.51e-01

Pos logit contributions
 plunge+0.026
piring+0.024
aro+0.022
chie+0.022
 aboard+0.022
Neg logit contributions
ravings-0.022
Years-0.021
udd-0.019
 habit-0.019
 loved-0.019
Tokenpron
Token ID31186
Feature activation-5.11e+00

Pos logit contributions
ravings+0.060
Years+0.055
 habit+0.052
becca+0.051
udd+0.051
Neg logit contributions
 plunge-0.049
piring-0.044
 afloat-0.041
 flap-0.040
chie-0.040
Token and
Token ID290
Feature activation-9.35e-02

Pos logit contributions
ravings+0.437
Years+0.421
omo+0.396
Days+0.386
becca+0.381
Neg logit contributions
 plunge-0.403
piring-0.386
iest-0.360
ter-0.357
ps-0.354
Token Ben
Token ID3932
Feature activation-2.08e+00

Pos logit contributions
ravings+0.009
Years+0.008
 habit+0.008
udd+0.007
pron+0.007
Neg logit contributions
 plunge-0.007
piring-0.007
ps-0.006
 aboard-0.006
aro-0.006
Token wore
Token ID12408
Feature activation-3.82e-01

Pos logit contributions
ravings+0.141
Years+0.132
pron+0.124
omo+0.118
 habit+0.117
Neg logit contributions
piring-0.205
 plunge-0.203
ps-0.187
 aboard-0.186
aro-0.184
Token a
Token ID257
Feature activation-5.04e-01

Pos logit contributions
ravings+0.035
 habit+0.033
Years+0.031
omo+0.031
udd+0.030
Neg logit contributions
piring-0.029
 plunge-0.029
 aboard-0.027
ps-0.025
 afloat-0.025
Token blue
Token ID4171
Feature activation-7.00e-03

Pos logit contributions
ravings+0.044
Years+0.042
 habit+0.039
becca+0.038
udd+0.037
Neg logit contributions
 plunge-0.039
piring-0.037
 afloat-0.034
oming-0.033
 aboard-0.033
Token the
Token ID262
Feature activation+6.40e-02

Pos logit contributions
 plunge+0.073
piring+0.070
chie+0.065
aro+0.064
ps+0.063
Neg logit contributions
ravings-0.066
pron-0.063
Years-0.063
 loved-0.060
 habit-0.060
Token help
Token ID1037
Feature activation+1.80e+00

Pos logit contributions
 plunge+0.006
piring+0.006
aro+0.006
chie+0.006
 afloat+0.005
Neg logit contributions
pron-0.005
ravings-0.005
Years-0.004
 loved-0.004
 habit-0.004
Token of
Token ID286
Feature activation+1.50e+00

Pos logit contributions
 plunge+0.170
piring+0.162
aro+0.155
 afloat+0.153
ps+0.153
Neg logit contributions
ravings-0.119
 loved-0.117
pron-0.117
 friend-0.116
 habit-0.116
Token her
Token ID607
Feature activation+6.14e-01

Pos logit contributions
 plunge+0.133
piring+0.130
chie+0.118
aro+0.117
 afloat+0.115
Neg logit contributions
ravings-0.115
pron-0.115
Years-0.110
 loved-0.110
 habit-0.106
Token a
Token ID257
Feature activation-4.90e-01

Pos logit contributions
 plunge+0.067
piring+0.065
ps+0.061
chie+0.060
oms+0.060
Neg logit contributions
ravings-0.034
Years-0.033
pron-0.029
omo-0.028
As-0.028
Tokenpron
Token ID31186
Feature activation-5.10e+00

Pos logit contributions
ravings+0.035
Years+0.032
udd+0.030
omo+0.030
 loved+0.029
Neg logit contributions
 plunge-0.048
piring-0.043
chie-0.042
 afloat-0.040
oms-0.040
Token,
Token ID11
Feature activation-9.86e-02

Pos logit contributions
ravings+0.399
pron+0.379
Years+0.374
 loved+0.364
 habit+0.360
Neg logit contributions
 plunge-0.447
piring-0.432
chie-0.403
aro-0.397
ps-0.384
Token she
Token ID673
Feature activation+8.98e-02

Pos logit contributions
ravings+0.009
pron+0.009
Years+0.009
 habit+0.008
udd+0.008
Neg logit contributions
 plunge-0.007
piring-0.007
aro-0.006
chie-0.006
ps-0.006
Token could
Token ID714
Feature activation-4.37e-01

Pos logit contributions
 plunge+0.007
piring+0.007
ps+0.007
oms+0.007
aro+0.007
Neg logit contributions
ravings-0.007
Years-0.006
 habit-0.006
omo-0.006
pron-0.006
Token make
Token ID787
Feature activation-1.24e-01

Pos logit contributions
ravings+0.036
pron+0.034
Years+0.034
 loved+0.033
 habit+0.032
Neg logit contributions
 plunge-0.037
piring-0.036
chie-0.033
aro-0.033
 afloat-0.032
Token creations
Token ID28443
Feature activation+8.31e-01

Pos logit contributions
ravings+0.011
pron+0.010
Years+0.010
omo+0.010
 habit+0.009
Neg logit contributions
 plunge-0.010
piring-0.010
ps-0.009
 aboard-0.009
chie-0.009
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
 plunge+0.074
piring+0.072
chie+0.066
aro+0.066
ps+0.063
Neg logit contributions
ravings-0.070
pron-0.067
Years-0.066
 loved-0.064
 habit-0.063
Token pockets
Token ID16511
Feature activation-8.62e-01

Pos logit contributions
 plunge+0.002
piring+0.002
aro+0.002
chie+0.002
 afloat+0.002
Neg logit contributions
ravings-0.002
pron-0.002
Years-0.002
 loved-0.002
 habit-0.002
Token of
Token ID286
Feature activation+1.46e+00

Pos logit contributions
ravings+0.045
pron+0.043
 loved+0.043
Years+0.042
 often+0.039
Neg logit contributions
 plunge-0.096
piring-0.093
aro-0.089
chie-0.088
 afloat-0.088
Token her
Token ID607
Feature activation+5.30e-01

Pos logit contributions
 plunge+0.144
piring+0.141
chie+0.135
aro+0.132
 afloat+0.128
Neg logit contributions
ravings-0.096
pron-0.095
 loved-0.090
Years-0.089
 habit-0.085
Token a
Token ID257
Feature activation-5.41e-01

Pos logit contributions
 plunge+0.057
piring+0.056
chie+0.052
aro+0.052
ps+0.051
Neg logit contributions
ravings-0.031
pron-0.028
Years-0.028
 loved-0.027
 habit-0.027
Tokenpron
Token ID31186
Feature activation-5.09e+00

Pos logit contributions
ravings+0.031
Years+0.028
udd+0.025
omo+0.025
becca+0.025
Neg logit contributions
 plunge-0.059
piring-0.055
chie-0.054
 afloat-0.052
oms-0.051
Token to
Token ID284
Feature activation-5.20e-01

Pos logit contributions
ravings+0.377
Years+0.351
pron+0.350
omo+0.332
 habit+0.331
Neg logit contributions
 plunge-0.464
piring-0.450
chie-0.409
aro-0.407
ps-0.404
Token store
Token ID3650
Feature activation-8.56e-01

Pos logit contributions
ravings+0.041
pron+0.041
Years+0.040
 loved+0.039
 habit+0.038
Neg logit contributions
 plunge-0.045
piring-0.044
chie-0.040
aro-0.040
 aboard-0.038
Token her
Token ID607
Feature activation+4.62e-01

Pos logit contributions
ravings+0.070
pron+0.066
Years+0.066
 loved+0.063
 habit+0.063
Neg logit contributions
 plunge-0.073
piring-0.070
chie-0.065
aro-0.064
ps-0.062
Token supplies
Token ID9416
Feature activation+2.33e+00

Pos logit contributions
 plunge+0.046
piring+0.043
 aboard+0.040
chie+0.040
ps+0.040
Neg logit contributions
ravings-0.030
Years-0.029
pron-0.027
omo-0.026
Even-0.026
Token.
Token ID13
Feature activation-1.81e-01

Pos logit contributions
 plunge+0.251
piring+0.244
chie+0.231
aro+0.229
ps+0.222
Neg logit contributions
ravings-0.136
pron-0.132
 loved-0.129
Years-0.125
 often-0.121
Tokenmy
Token ID1820
Feature activation-8.53e-01

Pos logit contributions
ravings+0.043
 habit+0.039
Years+0.038
pron+0.038
 favorite+0.035
Neg logit contributions
 plunge-0.060
piring-0.058
ps-0.055
 aboard-0.053
chie-0.053
Token put
Token ID1234
Feature activation+5.09e-01

Pos logit contributions
ravings+0.060
 habit+0.054
pron+0.053
Years+0.053
 favorite+0.048
Neg logit contributions
 plunge-0.083
piring-0.078
ps-0.074
 aboard-0.073
aro-0.072
Token on
Token ID319
Feature activation-3.88e-01

Pos logit contributions
 plunge+0.041
piring+0.041
chie+0.038
aro+0.036
oms+0.035
Neg logit contributions
pron-0.042
ravings-0.042
 loved-0.040
Years-0.040
 batch-0.038
Token her
Token ID607
Feature activation+6.86e-01

Pos logit contributions
ravings+0.032
pron+0.031
Years+0.031
 loved+0.030
 habit+0.029
Neg logit contributions
 plunge-0.032
piring-0.031
chie-0.029
aro-0.028
ps-0.027
Token a
Token ID257
Feature activation-4.65e-01

Pos logit contributions
 plunge+0.065
piring+0.063
chie+0.059
aro+0.058
ps+0.057
Neg logit contributions
ravings-0.049
pron-0.046
Years-0.045
 loved-0.043
 habit-0.043
Tokenpron
Token ID31186
Feature activation-5.08e+00

Pos logit contributions
ravings+0.013
Years+0.010
udd+0.009
omo+0.008
 habit+0.008
Neg logit contributions
 plunge-0.065
piring-0.061
chie-0.059
oms-0.058
 nearer-0.058
Token,
Token ID11
Feature activation+1.90e-01

Pos logit contributions
ravings+0.400
pron+0.375
Years+0.374
 habit+0.358
 loved+0.357
Neg logit contributions
 plunge-0.445
piring-0.429
chie-0.397
aro-0.392
ps-0.383
Token she
Token ID673
Feature activation+2.12e-01

Pos logit contributions
 plunge+0.014
piring+0.014
aro+0.012
chie+0.012
ps+0.012
Neg logit contributions
ravings-0.018
Years-0.016
pron-0.016
 habit-0.016
 loved-0.016
Token said
Token ID531
Feature activation-1.16e-01

Pos logit contributions
 plunge+0.018
oms+0.017
piring+0.017
ps+0.017
used+0.017
Neg logit contributions
ravings-0.016
Years-0.015
 habit-0.014
Days-0.014
pron-0.013
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
ravings+0.009
pron+0.009
Years+0.009
 loved+0.009
 habit+0.008
Neg logit contributions
 plunge-0.010
piring-0.010
chie-0.009
aro-0.009
ps-0.008
Token "
Token ID366
Feature activation-9.05e-01

Pos logit contributions
 plunge+0.019
piring+0.019
chie+0.018
aro+0.018
ps+0.017
Neg logit contributions
ravings-0.011
pron-0.010
Years-0.010
 habit-0.009
 loved-0.009
Token take
Token ID1011
Feature activation-2.37e-01

Pos logit contributions
 plunge+0.001
piring+0.001
chie+0.001
aro+0.001
ps+0.001
Neg logit contributions
ravings-0.002
pron-0.001
Years-0.001
 loved-0.001
 habit-0.001
Token care
Token ID1337
Feature activation-1.87e-01

Pos logit contributions
ravings+0.020
pron+0.019
Years+0.019
 habit+0.018
omo+0.018
Neg logit contributions
 plunge-0.020
piring-0.019
chie-0.018
ps-0.017
aro-0.017
Token of
Token ID286
Feature activation+1.51e+00

Pos logit contributions
ravings+0.017
pron+0.016
Years+0.016
 habit+0.015
 loved+0.015
Neg logit contributions
 plunge-0.014
piring-0.014
chie-0.013
aro-0.013
ps-0.012
Token your
Token ID534
Feature activation-1.43e+00

Pos logit contributions
 plunge+0.119
piring+0.114
chie+0.105
aro+0.103
ps+0.100
Neg logit contributions
ravings-0.133
pron-0.126
Years-0.125
 loved-0.121
 habit-0.120
Token a
Token ID257
Feature activation-4.92e-01

Pos logit contributions
ravings+0.096
Years+0.093
omo+0.086
udd+0.083
While+0.083
Neg logit contributions
 plunge-0.138
piring-0.129
ps-0.123
chie-0.120
 aboard-0.119
Tokenpron
Token ID31186
Feature activation-5.08e+00

Pos logit contributions
ravings+0.027
Years+0.025
udd+0.022
omo+0.021
Days+0.021
Neg logit contributions
 plunge-0.054
iest-0.049
piring-0.048
chie-0.046
 aboard-0.046
Token because
Token ID780
Feature activation-7.97e-01

Pos logit contributions
ravings+0.407
pron+0.384
Years+0.383
 habit+0.364
 loved+0.363
Neg logit contributions
 plunge-0.434
piring-0.418
chie-0.387
aro-0.381
ps-0.375
Token it
Token ID340
Feature activation-8.55e-01

Pos logit contributions
ravings+0.069
pron+0.066
Years+0.065
 loved+0.063
 habit+0.062
Neg logit contributions
 plunge-0.063
piring-0.061
chie-0.057
aro-0.055
 afloat-0.054
Token's
Token ID338
Feature activation-1.64e+00

Pos logit contributions
ravings+0.054
 loved+0.052
pron+0.051
Years+0.049
 habit+0.047
Neg logit contributions
 plunge-0.087
piring-0.086
aro-0.081
chie-0.080
 afloat-0.079
Token already
Token ID1541
Feature activation-1.98e+00

Pos logit contributions
ravings+0.112
Years+0.104
pron+0.100
 habit+0.098
udd+0.095
Neg logit contributions
 plunge-0.157
piring-0.150
chie-0.142
ps-0.142
 afloat-0.139
Token very
Token ID845
Feature activation-3.44e-01

Pos logit contributions
ravings+0.131
pron+0.122
Years+0.121
 habit+0.115
 loved+0.114
Neg logit contributions
 plunge-0.198
piring-0.192
chie-0.181
aro-0.177
ps-0.175
Token the
Token ID262
Feature activation+1.93e-01

Pos logit contributions
 plunge+0.004
piring+0.004
chie+0.004
aro+0.004
oms+0.004
Neg logit contributions
ravings-0.004
pron-0.004
Years-0.004
 loved-0.004
 friend-0.004
Token kitchen
Token ID9592
Feature activation-7.05e-01

Pos logit contributions
 plunge+0.017
piring+0.015
chie+0.015
 afloat+0.014
 aboard+0.014
Neg logit contributions
ravings-0.015
Years-0.014
pron-0.014
udd-0.013
omo-0.013
Token wearing
Token ID5762
Feature activation-7.41e-01

Pos logit contributions
Years+0.058
ravings+0.058
pron+0.054
 habit+0.053
Days+0.052
Neg logit contributions
 plunge-0.055
piring-0.054
ps-0.049
 afloat-0.047
chie-0.047
Token an
Token ID281
Feature activation-1.71e-01

Pos logit contributions
ravings+0.058
Years+0.054
pron+0.054
 habit+0.052
 loved+0.051
Neg logit contributions
 plunge-0.065
piring-0.063
chie-0.058
aro-0.058
ps-0.056
Token a
Token ID257
Feature activation-4.38e-01

Pos logit contributions
ravings+0.013
pron+0.012
Years+0.012
 habit+0.011
 loved+0.011
Neg logit contributions
 plunge-0.016
piring-0.015
chie-0.014
aro-0.014
ps-0.013
Tokenpron
Token ID31186
Feature activation-5.08e+00

Pos logit contributions
ravings+0.023
Years+0.021
udd+0.019
 habit+0.018
As+0.018
Neg logit contributions
 plunge-0.050
piring-0.046
chie-0.044
 afloat-0.044
 nearer-0.043
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
ravings+0.388
Years+0.369
pron+0.353
 habit+0.343
 loved+0.336
Neg logit contributions
 plunge-0.450
piring-0.437
aro-0.396
ps-0.395
chie-0.395
Token She
Token ID1375
Feature activation+1.73e-01

Pos logit contributions
 plunge+0.010
piring+0.010
chie+0.009
aro+0.009
 aboard+0.009
Neg logit contributions
ravings-0.013
pron-0.013
Years-0.012
 habit-0.012
udd-0.012
Token was
Token ID373
Feature activation-2.58e-01

Pos logit contributions
 plunge+0.013
piring+0.012
 onto+0.012
aro+0.012
ps+0.012
Neg logit contributions
ravings-0.015
 habit-0.013
Years-0.013
udd-0.012
pron-0.012
Token singing
Token ID13777
Feature activation-1.22e+00

Pos logit contributions
ravings+0.024
Years+0.022
 habit+0.022
pron+0.021
udd+0.021
Neg logit contributions
 plunge-0.019
piring-0.018
ps-0.017
chie-0.017
aro-0.016
Token to
Token ID284
Feature activation-2.70e-01

Pos logit contributions
ravings+0.099
pron+0.090
Years+0.089
 habit+0.087
omo+0.086
Neg logit contributions
 plunge-0.104
piring-0.104
chie-0.093
ps-0.092
 aboard-0.092
Token home
Token ID1363
Feature activation-1.00e+00

Pos logit contributions
ravings+0.015
 loved+0.014
 friend+0.014
pron+0.014
Years+0.014
Neg logit contributions
 plunge-0.024
piring-0.023
chie-0.022
aro-0.021
ps-0.021
Token and
Token ID290
Feature activation+5.38e-02

Pos logit contributions
ravings+0.073
pron+0.068
Years+0.067
 loved+0.065
 habit+0.064
Neg logit contributions
 plunge-0.094
piring-0.091
chie-0.085
aro-0.084
ps-0.081
Token removed
Token ID4615
Feature activation+4.02e-01

Pos logit contributions
 plunge+0.005
piring+0.005
aro+0.005
 aboard+0.004
chie+0.004
Neg logit contributions
ravings-0.004
Years-0.004
pron-0.004
 habit-0.003
udd-0.003
Token his
Token ID465
Feature activation+2.35e-01

Pos logit contributions
 plunge+0.033
piring+0.031
chie+0.029
aro+0.028
ps+0.028
Neg logit contributions
ravings-0.034
pron-0.032
Years-0.032
 loved-0.031
 habit-0.031
Token a
Token ID257
Feature activation-4.80e-01

Pos logit contributions
 plunge+0.022
piring+0.021
chie+0.020
aro+0.019
ps+0.019
Neg logit contributions
ravings-0.017
Years-0.016
pron-0.016
 loved-0.015
 habit-0.015
Tokenpron
Token ID31186
Feature activation-5.08e+00

Pos logit contributions
ravings+0.036
Years+0.034
pron+0.032
 loved+0.032
 habit+0.031
Neg logit contributions
 plunge-0.045
piring-0.042
chie-0.040
aro-0.038
 afloat-0.038
Token.
Token ID13
Feature activation+1.37e-01

Pos logit contributions
ravings+0.466
Years+0.445
pron+0.442
 loved+0.426
 habit+0.424
Neg logit contributions
 plunge-0.378
piring-0.360
chie-0.325
ps-0.322
aro-0.319
Token He
Token ID679
Feature activation-2.63e-01

Pos logit contributions
 plunge+0.010
piring+0.010
aro+0.009
 aboard+0.009
chie+0.009
Neg logit contributions
ravings-0.012
Years-0.011
pron-0.011
 habit-0.011
udd-0.011
Token was
Token ID373
Feature activation-1.40e-01

Pos logit contributions
ravings+0.022
Years+0.020
 habit+0.019
pron+0.019
Days+0.018
Neg logit contributions
ps-0.020
 onto-0.020
 plunge-0.019
piring-0.018
aro-0.018
Token happy
Token ID3772
Feature activation-2.94e-01

Pos logit contributions
ravings+0.013
Years+0.012
pron+0.012
 habit+0.012
udd+0.011
Neg logit contributions
 plunge-0.010
piring-0.010
chie-0.010
ps-0.009
 afloat-0.009
Token to
Token ID284
Feature activation-1.66e-01

Pos logit contributions
ravings+0.023
pron+0.022
Years+0.022
 habit+0.020
udd+0.020
Neg logit contributions
 plunge-0.025
piring-0.025
 aboard-0.023
aro-0.023
chie-0.022
Token her
Token ID607
Feature activation+8.12e-01

Pos logit contributions
 plunge+0.005
piring+0.004
aro+0.004
chie+0.004
 afloat+0.004
Neg logit contributions
ravings-0.005
pron-0.004
 loved-0.004
Years-0.004
 habit-0.004
Token amazing
Token ID4998
Feature activation+1.29e+00

Pos logit contributions
 plunge+0.076
piring+0.072
chie+0.069
aro+0.066
 afloat+0.066
Neg logit contributions
ravings-0.059
Years-0.056
pron-0.054
omo-0.051
 habit-0.049
Token,
Token ID11
Feature activation+4.12e-02

Pos logit contributions
 plunge+0.118
piring+0.110
chie+0.105
 aboard+0.102
aro+0.101
Neg logit contributions
ravings-0.096
Years-0.090
pron-0.088
 loved-0.082
 habit-0.082
Token expensive
Token ID5789
Feature activation+5.73e-01

Pos logit contributions
 plunge+0.004
piring+0.003
 aboard+0.003
chie+0.003
 afloat+0.003
Neg logit contributions
ravings-0.003
Years-0.003
pron-0.003
 habit-0.003
omo-0.003
Token a
Token ID257
Feature activation-4.19e-01

Pos logit contributions
 plunge+0.051
piring+0.049
chie+0.045
aro+0.045
 aboard+0.044
Neg logit contributions
ravings-0.044
Years-0.042
pron-0.041
 loved-0.039
 habit-0.039
Tokenpron
Token ID31186
Feature activation-5.08e+00

Pos logit contributions
ravings+0.033
Years+0.030
udd+0.027
becca+0.027
omo+0.026
Neg logit contributions
 plunge-0.037
chie-0.034
piring-0.034
 afloat-0.033
oming-0.032
Token.
Token ID13
Feature activation-7.13e-03

Pos logit contributions
ravings+0.350
Years+0.323
pron+0.312
 habit+0.297
omo+0.293
Neg logit contributions
 plunge-0.498
piring-0.483
chie-0.445
aro-0.443
ps-0.438
Token<|endoftext|>
Token ID50256
Feature activation+1.37e+00

Pos logit contributions
ravings+0.001
pron+0.001
Years+0.001
 habit+0.001
udd+0.001
Neg logit contributions
 plunge-0.001
piring-0.001
ions-0.001
aro-0.001
chie-0.000
TokenOne
Token ID3198
Feature activation-4.06e-01

Pos logit contributions
 plunge+0.131
piring+0.129
chie+0.124
aro+0.117
ps+0.116
Neg logit contributions
ravings-0.093
 loved-0.091
pron-0.088
Years-0.083
 friend-0.083
Token day
Token ID1110
Feature activation-2.76e-01

Pos logit contributions
ravings+0.030
Years+0.027
pron+0.026
anas+0.025
Days+0.024
Neg logit contributions
 plunge-0.039
piring-0.036
iest-0.035
chie-0.034
 aboard-0.034
Token,
Token ID11
Feature activation-1.22e-01

Pos logit contributions
ravings+0.024
pron+0.023
Years+0.023
 loved+0.022
 habit+0.022
Neg logit contributions
 plunge-0.022
piring-0.021
chie-0.019
aro-0.019
ps-0.018
Token mom
Token ID1995
Feature activation-7.65e-01

Pos logit contributions
 plunge+0.051
piring+0.047
ps+0.046
 aboard+0.045
oms+0.044
Neg logit contributions
ravings-0.029
Years-0.029
Even-0.027
As-0.026
While-0.026
Token had
Token ID550
Feature activation-5.00e-02

Pos logit contributions
ravings+0.050
pron+0.047
Years+0.046
 loved+0.044
 habit+0.044
Neg logit contributions
 plunge-0.077
piring-0.075
chie-0.070
aro-0.070
ps-0.068
Token a
Token ID257
Feature activation-5.70e-01

Pos logit contributions
ravings+0.004
Years+0.004
 habit+0.004
omo+0.003
udd+0.003
Neg logit contributions
 plunge-0.004
chie-0.004
piring-0.004
ps-0.004
ions-0.004
Token graceful
Token ID44363
Feature activation+9.01e-01

Pos logit contributions
ravings+0.046
Years+0.042
udd+0.041
As+0.040
omo+0.040
Neg logit contributions
 plunge-0.050
piring-0.044
chie-0.043
 nearer-0.041
 flap-0.040
Token a
Token ID257
Feature activation-6.21e-01

Pos logit contributions
 plunge+0.080
piring+0.074
chie+0.069
 aboard+0.067
ps+0.067
Neg logit contributions
ravings-0.070
Years-0.067
udd-0.062
omo-0.061
Days-0.060
Tokenpron
Token ID31186
Feature activation-5.07e+00

Pos logit contributions
ravings+0.033
Years+0.030
udd+0.027
 loved+0.025
Days+0.025
Neg logit contributions
 plunge-0.071
piring-0.066
chie-0.063
 nearer-0.061
 afloat-0.061
Token,
Token ID11
Feature activation-2.59e-01

Pos logit contributions
ravings+0.410
Years+0.387
pron+0.374
 habit+0.361
omo+0.361
Neg logit contributions
 plunge-0.426
piring-0.418
aro-0.372
ps-0.372
chie-0.371
Token too
Token ID1165
Feature activation-3.83e-01

Pos logit contributions
ravings+0.021
Years+0.019
 habit+0.019
pron+0.019
omo+0.018
Neg logit contributions
 plunge-0.022
piring-0.021
ps-0.019
chie-0.019
aro-0.019
Token.
Token ID13
Feature activation-7.96e-02

Pos logit contributions
ravings+0.033
Years+0.031
 habit+0.029
pron+0.029
omo+0.029
Neg logit contributions
piring-0.029
 plunge-0.028
iest-0.026
oms-0.025
ions-0.025
Token It
Token ID632
Feature activation-3.48e-01

Pos logit contributions
pron+0.009
ravings+0.009
udd+0.009
Years+0.009
omo+0.009
Neg logit contributions
 plunge-0.004
piring-0.003
used-0.003
 onto-0.003
ps-0.003
Token was
Token ID373
Feature activation-4.30e-01

Pos logit contributions
ravings+0.020
pron+0.018
Years+0.018
 habit+0.017
 loved+0.016
Neg logit contributions
 plunge-0.038
piring-0.037
chie-0.035
aro-0.035
ps-0.034
Token princess
Token ID21752
Feature activation-4.01e-01

Pos logit contributions
 plunge+0.021
piring+0.019
chie+0.018
ter+0.018
iest+0.018
Neg logit contributions
ravings-0.018
Years-0.017
pron-0.016
udd-0.016
 habit-0.016
Token put
Token ID1234
Feature activation+6.30e-01

Pos logit contributions
ravings+0.027
Years+0.027
pron+0.026
omo+0.024
 habit+0.023
Neg logit contributions
 plunge-0.038
piring-0.036
 aboard-0.035
ter-0.035
iest-0.034
Token on
Token ID319
Feature activation-2.78e-01

Pos logit contributions
 plunge+0.052
piring+0.050
chie+0.047
aro+0.045
 afloat+0.044
Neg logit contributions
ravings-0.053
pron-0.051
Years-0.050
 loved-0.049
 habit-0.048
Token an
Token ID281
Feature activation-9.27e-02

Pos logit contributions
ravings+0.029
Years+0.028
pron+0.027
 habit+0.027
udd+0.026
Neg logit contributions
 plunge-0.017
piring-0.015
ps-0.015
 aboard-0.014
ions-0.014
Token a
Token ID257
Feature activation-3.22e-01

Pos logit contributions
ravings+0.007
pron+0.007
Years+0.007
 habit+0.007
omo+0.007
Neg logit contributions
 plunge-0.008
piring-0.007
chie-0.007
aro-0.007
ps-0.007
Tokenpron
Token ID31186
Feature activation-5.07e+00

Pos logit contributions
ravings+0.025
Years+0.023
omo+0.022
udd+0.022
 habit+0.022
Neg logit contributions
 plunge-0.029
piring-0.026
chie-0.025
aro-0.024
 afloat-0.024
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
ravings+0.435
Years+0.425
omo+0.413
Days+0.390
 habit+0.389
Neg logit contributions
 plunge-0.393
piring-0.376
ps-0.347
ter-0.343
iest-0.342
Token She
Token ID1375
Feature activation+2.27e-01

Pos logit contributions
 plunge+0.009
piring+0.008
chie+0.007
 aboard+0.007
aro+0.007
Neg logit contributions
ravings-0.012
pron-0.011
Years-0.011
 habit-0.011
omo-0.010
Token looked
Token ID3114
Feature activation+5.05e-01

Pos logit contributions
 plunge+0.016
ions+0.016
aro+0.016
 onto+0.015
ps+0.015
Neg logit contributions
ravings-0.020
 habit-0.018
Years-0.017
Days-0.016
becca-0.015
Token so
Token ID523
Feature activation+1.23e-01

Pos logit contributions
 plunge+0.040
piring+0.038
chie+0.035
aro+0.034
 aboard+0.034
Neg logit contributions
ravings-0.044
pron-0.042
Years-0.042
 habit-0.040
 loved-0.039
Token attractive
Token ID10966
Feature activation+9.17e-01

Pos logit contributions
 plunge+0.011
piring+0.010
chie+0.010
oms+0.009
oming+0.009
Neg logit contributions
ravings-0.010
Years-0.009
pron-0.009
 dentist-0.009
 habit-0.009
Token home
Token ID1363
Feature activation-5.85e-01

Pos logit contributions
ravings+0.004
 loved+0.004
 friend+0.004
Years+0.004
pron+0.004
Neg logit contributions
 plunge-0.009
piring-0.008
chie-0.008
aro-0.008
oms-0.008
Token with
Token ID351
Feature activation-5.72e-01

Pos logit contributions
ravings+0.041
pron+0.039
Years+0.038
 loved+0.037
 habit+0.036
Neg logit contributions
 plunge-0.056
piring-0.054
chie-0.051
aro-0.050
ps-0.049
Token the
Token ID262
Feature activation+2.24e-01

Pos logit contributions
ravings+0.044
pron+0.041
Years+0.041
 habit+0.039
 loved+0.039
Neg logit contributions
 plunge-0.052
piring-0.050
chie-0.046
aro-0.046
ps-0.045
Token colorful
Token ID20239
Feature activation+1.27e+00

Pos logit contributions
 plunge+0.020
piring+0.019
chie+0.018
aro+0.018
ps+0.017
Neg logit contributions
ravings-0.017
pron-0.016
Years-0.016
 loved-0.016
 habit-0.016
Token a
Token ID257
Feature activation-3.62e-01

Pos logit contributions
 plunge+0.103
piring+0.100
chie+0.093
aro+0.090
 afloat+0.090
Neg logit contributions
ravings-0.107
pron-0.102
 loved-0.099
Years-0.099
 habit-0.097
Tokenpron
Token ID31186
Feature activation-5.06e+00

Pos logit contributions
ravings+0.028
Years+0.026
udd+0.023
 loved+0.023
becca+0.023
Neg logit contributions
 plunge-0.033
piring-0.031
chie-0.029
 afloat-0.028
 nearer-0.028
Token still
Token ID991
Feature activation-8.99e-01

Pos logit contributions
ravings+0.359
Years+0.334
pron+0.333
 habit+0.315
 loved+0.314
Neg logit contributions
 plunge-0.482
piring-0.468
chie-0.433
aro-0.430
ps-0.421
Token tied
Token ID8165
Feature activation-4.18e-01

Pos logit contributions
ravings+0.064
pron+0.061
Years+0.060
 loved+0.059
 habit+0.057
Neg logit contributions
 plunge-0.085
piring-0.082
chie-0.077
aro-0.076
ps-0.073
Token around
Token ID1088
Feature activation-8.85e-02

Pos logit contributions
ravings+0.028
pron+0.027
Years+0.027
 loved+0.027
 friend+0.025
Neg logit contributions
 plunge-0.040
piring-0.039
chie-0.036
aro-0.036
 afloat-0.035
Token her
Token ID607
Feature activation+6.45e-01

Pos logit contributions
ravings+0.008
pron+0.007
Years+0.007
 habit+0.007
 loved+0.007
Neg logit contributions
 plunge-0.007
piring-0.007
chie-0.006
aro-0.006
ps-0.006
Token waist
Token ID16139
Feature activation-1.20e+00

Pos logit contributions
 plunge+0.060
piring+0.058
chie+0.054
ps+0.053
aro+0.053
Neg logit contributions
ravings-0.046
Years-0.044
pron-0.042
omo-0.040
 habit-0.040
Token so
Token ID523
Feature activation+1.23e-01

Pos logit contributions
 plunge+0.040
piring+0.038
chie+0.035
aro+0.034
 aboard+0.034
Neg logit contributions
ravings-0.044
pron-0.042
Years-0.042
 habit-0.040
 loved-0.039
Token attractive
Token ID10966
Feature activation+9.17e-01

Pos logit contributions
 plunge+0.011
piring+0.010
chie+0.010
oms+0.009
oming+0.009
Neg logit contributions
ravings-0.010
Years-0.009
pron-0.009
 dentist-0.009
 habit-0.009
Token in
Token ID287
Feature activation-6.73e-02

Pos logit contributions
 plunge+0.104
chie+0.102
piring+0.098
 afloat+0.096
aro+0.094
Neg logit contributions
 loved-0.048
 often-0.046
ravings-0.045
Years-0.042
 favorite-0.042
Token the
Token ID262
Feature activation+5.70e-02

Pos logit contributions
ravings+0.006
pron+0.006
Years+0.006
 habit+0.006
 loved+0.006
Neg logit contributions
 plunge-0.005
piring-0.005
chie-0.004
aro-0.004
ps-0.004
Token a
Token ID257
Feature activation-4.02e-01

Pos logit contributions
 plunge+0.005
piring+0.004
iest+0.004
chie+0.004
 aboard+0.004
Neg logit contributions
ravings-0.005
Years-0.005
omo-0.004
 habit-0.004
 loved-0.004
Tokenpron
Token ID31186
Feature activation-5.06e+00

Pos logit contributions
ravings+0.028
Years+0.026
udd+0.023
omo+0.023
 habit+0.023
Neg logit contributions
 plunge-0.038
piring-0.036
chie-0.034
iest-0.033
 afloat-0.033
Token that
Token ID326
Feature activation-7.88e-01

Pos logit contributions
ravings+0.408
Years+0.394
pron+0.376
omo+0.363
 habit+0.357
Neg logit contributions
 plunge-0.433
piring-0.414
ter-0.376
iest-0.372
ps-0.372
Token everyone
Token ID2506
Feature activation-1.09e+00

Pos logit contributions
ravings+0.068
Years+0.063
pron+0.062
 habit+0.060
omo+0.059
Neg logit contributions
 plunge-0.064
piring-0.062
aro-0.056
chie-0.055
iest-0.054
Token wanted
Token ID2227
Feature activation-8.54e-01

Pos logit contributions
ravings+0.065
Years+0.060
pron+0.059
 habit+0.055
omo+0.054
Neg logit contributions
 plunge-0.117
piring-0.115
chie-0.107
aro-0.107
 aboard-0.104
Token to
Token ID284
Feature activation-3.93e-01

Pos logit contributions
ravings+0.061
pron+0.057
Years+0.057
 habit+0.054
omo+0.053
Neg logit contributions
 plunge-0.081
piring-0.079
chie-0.072
aro-0.072
ps-0.071
Token see
Token ID766
Feature activation+1.03e+00

Pos logit contributions
ravings+0.031
pron+0.030
Years+0.029
 loved+0.028
 habit+0.028
Neg logit contributions
 plunge-0.034
piring-0.033
chie-0.031
aro-0.030
ps-0.030
Token Mia
Token ID32189
Feature activation+3.83e-01

Pos logit contributions
ravings+0.010
pron+0.010
Years+0.009
 habit+0.009
 loved+0.009
Neg logit contributions
 plunge-0.012
piring-0.012
aro-0.011
chie-0.011
ps-0.011
Token are
Token ID389
Feature activation+3.05e+00

Pos logit contributions
 plunge+0.019
piring+0.018
aro+0.017
chie+0.016
 aboard+0.015
Neg logit contributions
ravings-0.043
 loved-0.043
 habit-0.042
Years-0.041
pron-0.041
Token scared
Token ID12008
Feature activation+1.15e+00

Pos logit contributions
piring+0.242
 plunge+0.240
ps+0.235
 afloat+0.225
chie+0.223
Neg logit contributions
ravings-0.257
Years-0.251
pron-0.250
 habit-0.229
 batch-0.225
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
 plunge+0.125
piring+0.119
chie+0.114
aro+0.112
 afloat+0.109
Neg logit contributions
ravings-0.068
 loved-0.062
Years-0.061
 friend-0.060
 habit-0.059
Token They
Token ID1119
Feature activation-3.13e-01

Pos logit contributions
 loved+0.009
ravings+0.009
Years+0.008
 owner+0.008
 habit+0.008
Neg logit contributions
 plunge-0.019
piring-0.018
chie-0.018
aro-0.017
iest-0.017
Token are
Token ID389
Feature activation+2.98e+00

Pos logit contributions
ravings+0.029
pron+0.027
Years+0.027
 habit+0.026
 loved+0.026
Neg logit contributions
 plunge-0.024
piring-0.022
chie-0.021
aro-0.020
ps-0.020
Token sorry
Token ID7926
Feature activation+1.20e+00

Pos logit contributions
 plunge+0.256
piring+0.251
ps+0.232
chie+0.232
aro+0.230
Neg logit contributions
ravings-0.239
pron-0.227
Years-0.225
 habit-0.215
 loved-0.207
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
 plunge+0.112
piring+0.109
chie+0.101
aro+0.100
ps+0.098
Neg logit contributions
ravings-0.088
pron-0.084
Years-0.082
 loved-0.078
 habit-0.078
Token They
Token ID1119
Feature activation-2.06e-01

Pos logit contributions
 loved+0.006
ravings+0.006
Years+0.006
L+0.006
 owner+0.006
Neg logit contributions
 plunge-0.013
piring-0.012
chie-0.012
ps-0.011
aro-0.011
Token cry
Token ID3960
Feature activation+1.55e+00

Pos logit contributions
ravings+0.020
pron+0.019
Years+0.018
omo+0.017
 habit+0.017
Neg logit contributions
 plunge-0.015
piring-0.014
ps-0.013
chie-0.013
aro-0.012
Token.
Token ID13
Feature activation-1.00e-01

Pos logit contributions
piring+0.132
 plunge+0.130
ps+0.118
chie+0.117
 afloat+0.116
Neg logit contributions
ravings-0.126
pron-0.123
Years-0.119
becca-0.111
omo-0.110
TokenI
Token ID40
Feature activation-1.04e+00

Pos logit contributions
 plunge+0.198
piring+0.192
aro+0.180
chie+0.179
ter+0.171
Neg logit contributions
ravings-0.176
 habit-0.157
pron-0.152
udd-0.150
Years-0.147
Token'm
Token ID1101
Feature activation+2.07e+00

Pos logit contributions
ravings+0.109
Years+0.104
pron+0.102
 dentist+0.095
becca+0.095
Neg logit contributions
 plunge-0.068
piring-0.061
chie-0.056
 nearer-0.054
iest-0.053
Token sorry
Token ID7926
Feature activation+1.36e+00

Pos logit contributions
 plunge+0.171
piring+0.165
chie+0.153
aro+0.150
ps+0.145
Neg logit contributions
ravings-0.174
pron-0.165
Years-0.163
 loved-0.158
 habit-0.157
Token,
Token ID11
Feature activation+4.38e-01

Pos logit contributions
 plunge+0.095
piring+0.091
chie+0.083
aro+0.081
ps+0.078
Neg logit contributions
ravings-0.132
pron-0.126
Years-0.125
 loved-0.121
 habit-0.120
Token Ben
Token ID3932
Feature activation-1.56e+00

Pos logit contributions
 plunge+0.048
piring+0.047
chie+0.045
aro+0.044
ps+0.043
Neg logit contributions
ravings-0.024
pron-0.023
 friend-0.022
Years-0.022
omo-0.021
Token,"
Token ID553
Feature activation+4.15e+00

Pos logit contributions
ravings+0.147
Years+0.140
pron+0.140
 habit+0.132
 loved+0.131
Neg logit contributions
 plunge-0.112
piring-0.107
chie-0.098
aro-0.096
ps-0.094
Token Lily
Token ID20037
Feature activation-6.61e-01

Pos logit contributions
 plunge+0.420
piring+0.405
aro+0.387
chie+0.381
ps+0.374
Neg logit contributions
ravings-0.275
Years-0.249
pron-0.247
 habit-0.235
udd-0.229
Token said
Token ID531
Feature activation+3.06e-01

Pos logit contributions
ravings+0.059
pron+0.057
Years+0.057
Days+0.053
 habit+0.051
Neg logit contributions
 plunge-0.051
piring-0.048
ps-0.046
oms-0.044
 respond-0.043
Token.
Token ID13
Feature activation+3.73e-01

Pos logit contributions
 plunge+0.030
piring+0.029
chie+0.027
aro+0.027
 aboard+0.026
Neg logit contributions
ravings-0.021
pron-0.020
Years-0.019
 loved-0.019
 habit-0.018
Token "
Token ID366
Feature activation-7.55e-01

Pos logit contributions
 plunge+0.045
piring+0.043
chie+0.041
aro+0.041
iest+0.040
Neg logit contributions
ravings-0.018
pron-0.016
Years-0.016
 loved-0.016
 habit-0.015
TokenI
Token ID40
Feature activation-8.35e-01

Pos logit contributions
ravings+0.063
pron+0.058
Years+0.058
 habit+0.057
 loved+0.055
Neg logit contributions
 plunge-0.062
piring-0.061
chie-0.056
aro-0.055
ps-0.054
Token pieces
Token ID5207
Feature activation+2.02e+00

Pos logit contributions
 plunge+0.126
piring+0.123
chie+0.116
ps+0.114
aro+0.112
Neg logit contributions
ravings-0.117
pron-0.110
Years-0.109
 habit-0.104
 loved-0.102
Token.
Token ID13
Feature activation-2.06e-01

Pos logit contributions
 plunge+0.221
piring+0.211
chie+0.202
aro+0.197
 aboard+0.191
Neg logit contributions
ravings-0.116
pron-0.109
 loved-0.107
Years-0.102
 often-0.101
Token Lily
Token ID20037
Feature activation-7.09e-01

Pos logit contributions
ravings+0.012
pron+0.011
Years+0.011
 loved+0.011
 habit+0.010
Neg logit contributions
 plunge-0.022
piring-0.022
chie-0.021
aro-0.020
ps-0.020
Token and
Token ID290
Feature activation-1.07e-01

Pos logit contributions
ravings+0.054
pron+0.051
Years+0.051
 habit+0.048
 loved+0.047
Neg logit contributions
 plunge-0.064
piring-0.062
chie-0.057
aro-0.057
ps-0.056
Token Ben
Token ID3932
Feature activation-1.77e+00

Pos logit contributions
ravings+0.007
pron+0.007
Years+0.007
 loved+0.006
 habit+0.006
Neg logit contributions
 plunge-0.011
piring-0.010
chie-0.010
aro-0.010
ps-0.009
Token are
Token ID389
Feature activation+2.97e+00

Pos logit contributions
 loved+0.165
ravings+0.160
 habit+0.153
pron+0.152
Years+0.150
Neg logit contributions
 plunge-0.122
piring-0.117
aro-0.111
chie-0.110
iest-0.107
Token sad
Token ID6507
Feature activation-5.90e-01

Pos logit contributions
 plunge+0.274
piring+0.267
chie+0.250
aro+0.245
ps+0.245
Neg logit contributions
ravings-0.220
pron-0.208
Years-0.206
 habit-0.195
 loved-0.191
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
ravings+0.039
Years+0.036
pron+0.035
 loved+0.035
 habit+0.034
Neg logit contributions
 plunge-0.060
piring-0.058
chie-0.055
aro-0.054
 aboard-0.052
Token
Token ID198
Feature activation-3.06e-01

Pos logit contributions
ravings+0.010
 loved+0.009
Years+0.009
pron+0.009
 habit+0.009
Neg logit contributions
 plunge-0.020
piring-0.020
chie-0.019
aro-0.018
ps-0.018
Token
Token ID198
Feature activation-3.14e-01

Pos logit contributions
ravings+0.021
pron+0.020
Years+0.019
 habit+0.018
 loved+0.017
Neg logit contributions
 plunge-0.030
piring-0.029
aro-0.027
chie-0.027
 aboard-0.027
Token"
Token ID1
Feature activation+1.98e+00

Pos logit contributions
ravings+0.023
pron+0.021
Years+0.020
 habit+0.020
 dentist+0.019
Neg logit contributions
 plunge-0.030
piring-0.029
chie-0.027
aro-0.027
 afloat-0.026
Token can
Token ID460
Feature activation+1.84e+00

Pos logit contributions
ravings+0.099
Years+0.097
pron+0.094
 habit+0.087
Days+0.086
Neg logit contributions
 plunge-0.076
piring-0.071
chie-0.065
aro-0.063
 afloat-0.063
Token't
Token ID470
Feature activation+2.07e+00

Pos logit contributions
piring+0.130
 plunge+0.127
chie+0.117
 afloat+0.112
 aboard+0.112
Neg logit contributions
ravings-0.170
pron-0.169
 loved-0.168
Years-0.161
 often-0.161
Token find
Token ID1064
Feature activation+1.00e+00

Pos logit contributions
 plunge+0.185
piring+0.184
aro+0.169
 aboard+0.169
ps+0.168
Neg logit contributions
ravings-0.151
 loved-0.149
 friend-0.145
 often-0.144
pron-0.144
Token my
Token ID616
Feature activation-2.15e-01

Pos logit contributions
piring+0.089
 plunge+0.089
chie+0.082
 afloat+0.081
oms+0.078
Neg logit contributions
ravings-0.074
 friend-0.069
 loved-0.069
pron-0.067
 dentist-0.067
Token toy
Token ID13373
Feature activation-1.05e-01

Pos logit contributions
ravings+0.013
pron+0.012
Years+0.012
 loved+0.012
 habit+0.011
Neg logit contributions
 plunge-0.022
piring-0.022
chie-0.020
aro-0.020
ps-0.020
Token,"
Token ID553
Feature activation+3.87e+00

Pos logit contributions
 friend+0.007
 owner+0.007
ravings+0.007
 favorite+0.006
 loved+0.006
Neg logit contributions
 plunge-0.010
piring-0.010
chie-0.009
aro-0.009
 afloat-0.009
Token Lily
Token ID20037
Feature activation-7.10e-01

Pos logit contributions
 plunge+0.360
piring+0.346
aro+0.327
chie+0.322
ter+0.313
Neg logit contributions
ravings-0.287
Years-0.263
pron-0.257
 habit-0.244
udd-0.243
Token replied
Token ID8712
Feature activation-6.46e-01

Pos logit contributions
ravings+0.066
pron+0.064
Years+0.061
Days+0.056
 habit+0.056
Neg logit contributions
 plunge-0.050
piring-0.047
 respond-0.046
ps-0.045
 nearer-0.044
Token.
Token ID13
Feature activation+4.63e-01

Pos logit contributions
ravings+0.052
Years+0.049
pron+0.048
 habit+0.046
omo+0.045
Neg logit contributions
 plunge-0.055
piring-0.054
chie-0.049
aro-0.049
ps-0.049
Token
Token ID198
Feature activation+9.52e-02

Pos logit contributions
 plunge+0.034
piring+0.033
oms+0.031
ter+0.031
aro+0.031
Neg logit contributions
ravings-0.039
Years-0.036
pron-0.036
 habit-0.036
udd-0.033
Token
Token ID198
Feature activation+7.33e-02

Pos logit contributions
aro+0.006
 plunge+0.006
 ourselves+0.006
chie+0.006
 aboard+0.005
Neg logit contributions
ravings-0.009
 habit-0.008
pron-0.008
auldron-0.008
 batch-0.008
Token a
Token ID257
Feature activation-2.96e-01

Pos logit contributions
 plunge+0.015
piring+0.014
ps+0.013
chie+0.013
aro+0.013
Neg logit contributions
ravings-0.014
pron-0.013
Years-0.013
 habit-0.013
omo-0.012
Token number
Token ID1271
Feature activation-1.54e-01

Pos logit contributions
ravings+0.024
Years+0.022
udd+0.021
As+0.020
becca+0.020
Neg logit contributions
 plunge-0.025
piring-0.023
chie-0.023
 afloat-0.022
 respond-0.021
Token on
Token ID319
Feature activation-3.16e-01

Pos logit contributions
ravings+0.012
pron+0.011
Years+0.011
 loved+0.011
 habit+0.011
Neg logit contributions
 plunge-0.014
piring-0.013
chie-0.012
aro-0.012
 afloat-0.012
Token his
Token ID465
Feature activation+8.40e-02

Pos logit contributions
ravings+0.027
pron+0.025
Years+0.025
 habit+0.024
 loved+0.024
Neg logit contributions
 plunge-0.026
piring-0.024
chie-0.023
aro-0.023
ps-0.022
Token hat
Token ID6877
Feature activation-5.64e-01

Pos logit contributions
 plunge+0.008
piring+0.008
chie+0.008
ps+0.007
aro+0.007
Neg logit contributions
ravings-0.006
Years-0.005
pron-0.005
udd-0.005
 loved-0.005
Token,"
Token ID553
Feature activation+3.30e+00

Pos logit contributions
ravings+0.047
Years+0.045
pron+0.045
 habit+0.043
 loved+0.042
Neg logit contributions
 plunge-0.046
piring-0.044
chie-0.040
aro-0.040
ps-0.040
Token she
Token ID673
Feature activation+2.32e-01

Pos logit contributions
 plunge+0.259
piring+0.245
aro+0.237
ter+0.227
chie+0.224
Neg logit contributions
ravings-0.291
Years-0.266
pron-0.258
 habit-0.254
udd-0.254
Token said
Token ID531
Feature activation+1.22e-02

Pos logit contributions
 plunge+0.017
piring+0.017
 respond+0.016
ps+0.016
chie+0.015
Neg logit contributions
ravings-0.022
pron-0.019
 habit-0.018
Years-0.018
udd-0.018
Token.
Token ID13
Feature activation+1.15e-01

Pos logit contributions
 plunge+0.001
piring+0.001
chie+0.001
aro+0.001
ps+0.001
Neg logit contributions
ravings-0.001
Years-0.001
pron-0.001
 habit-0.001
 loved-0.001
Token The
Token ID383
Feature activation-1.85e-01

Pos logit contributions
 plunge+0.010
piring+0.009
aro+0.009
oms+0.009
 aboard+0.009
Neg logit contributions
ravings-0.009
Years-0.008
 habit-0.008
pron-0.008
udd-0.008
Token police
Token ID1644
Feature activation-1.21e+00

Pos logit contributions
ravings+0.014
Years+0.013
pron+0.013
udd+0.012
 habit+0.012
Neg logit contributions
 plunge-0.017
piring-0.016
chie-0.015
aro-0.015
ps-0.015
Token wish
Token ID4601
Feature activation+6.95e-01

Pos logit contributions
ravings+0.025
pron+0.022
Years+0.022
 loved+0.021
omo+0.021
Neg logit contributions
 plunge-0.025
piring-0.024
chie-0.022
 afloat-0.022
 aboard-0.022
Token.
Token ID13
Feature activation+2.91e-01

Pos logit contributions
 plunge+0.079
chie+0.074
piring+0.073
aro+0.071
 afloat+0.070
Neg logit contributions
 often-0.035
 loved-0.035
 friend-0.035
pron-0.034
ravings-0.033
Token<|endoftext|>
Token ID50256
Feature activation+1.35e+00

Pos logit contributions
 plunge+0.029
piring+0.029
chie+0.026
aro+0.026
 afloat+0.026
Neg logit contributions
ravings-0.019
pron-0.018
Years-0.017
 habit-0.016
 loved-0.016
TokenL
Token ID43
Feature activation-9.91e-01

Pos logit contributions
chie+0.124
 plunge+0.124
piring+0.123
aro+0.113
ps+0.110
Neg logit contributions
 loved-0.097
ravings-0.094
L-0.094
 friend-0.090
pron-0.090
Tokenily
Token ID813
Feature activation+1.06e+00

Pos logit contributions
ravings+0.075
pron+0.071
Years+0.070
 loved+0.069
 habit+0.067
Neg logit contributions
 plunge-0.090
piring-0.088
chie-0.082
aro-0.080
 afloat-0.079
Token and
Token ID290
Feature activation+7.70e-02

Pos logit contributions
 plunge+0.103
piring+0.101
 aboard+0.096
ps+0.096
ter+0.092
Neg logit contributions
ravings-0.066
Years-0.065
pron-0.065
 habit-0.058
Days-0.056
Token Ben
Token ID3932
Feature activation-1.60e+00

Pos logit contributions
 plunge+0.008
piring+0.008
chie+0.008
aro+0.007
oms+0.007
Neg logit contributions
 loved-0.005
ravings-0.004
 friend-0.004
 habit-0.004
pron-0.004
Token are
Token ID389
Feature activation+2.88e+00

Pos logit contributions
 loved+0.103
ravings+0.094
 habit+0.086
 liked+0.086
Years+0.085
Neg logit contributions
 plunge-0.171
piring-0.162
chie-0.161
aro-0.160
oming-0.149
Token playing
Token ID2712
Feature activation-1.28e+00

Pos logit contributions
 plunge+0.242
piring+0.238
oms+0.219
ions+0.215
oming+0.214
Neg logit contributions
ravings-0.231
Years-0.225
pron-0.212
 habit-0.208
Days-0.198
Token in
Token ID287
Feature activation+8.88e-02

Pos logit contributions
ravings+0.132
Years+0.124
omo+0.123
pron+0.122
udd+0.118
Neg logit contributions
 plunge-0.084
piring-0.074
ter-0.072
 aboard-0.071
ps-0.069
Token the
Token ID262
Feature activation+2.54e-01

Pos logit contributions
 plunge+0.009
piring+0.009
chie+0.008
aro+0.008
oms+0.007
Neg logit contributions
 loved-0.006
pron-0.006
ravings-0.006
L-0.006
 friend-0.006
Token the
Token ID262
Feature activation+1.74e-01

Pos logit contributions
ravings+0.172
 loved+0.167
pron+0.159
Years+0.159
 often+0.155
Neg logit contributions
 plunge-0.195
piring-0.188
chie-0.179
ps-0.169
 afloat-0.167
Token new
Token ID649
Feature activation+5.90e-01

Pos logit contributions
 plunge+0.016
piring+0.016
chie+0.014
aro+0.014
 aboard+0.014
Neg logit contributions
ravings-0.013
pron-0.012
Years-0.012
 habit-0.012
 loved-0.011
Token things
Token ID1243
Feature activation+8.11e-01

Pos logit contributions
 plunge+0.051
piring+0.049
aro+0.045
chie+0.045
 aboard+0.043
Neg logit contributions
ravings-0.048
pron-0.046
Years-0.045
 habit-0.042
 loved-0.042
Token he
Token ID339
Feature activation-3.02e-01

Pos logit contributions
chie+0.101
 plunge+0.096
ocol+0.089
ps+0.088
piring+0.086
Neg logit contributions
 loved-0.043
 often-0.037
 liked-0.034
 about-0.033
 favorite-0.031
Token saw
Token ID2497
Feature activation-1.36e+00

Pos logit contributions
ravings+0.019
pron+0.018
Years+0.017
 habit+0.017
omo+0.016
Neg logit contributions
 plunge-0.031
piring-0.030
chie-0.028
 aboard-0.028
aro-0.028
Token.
Token ID13
Feature activation-3.20e-02

Pos logit contributions
ravings+0.116
pron+0.112
Years+0.110
 habit+0.106
omo+0.104
Neg logit contributions
 plunge-0.109
piring-0.106
 aboard-0.096
ps-0.096
aro-0.095
Token Suddenly
Token ID24975
Feature activation-1.13e+00

Pos logit contributions
ravings+0.003
Years+0.003
pron+0.003
 habit+0.003
 batch+0.003
Neg logit contributions
 plunge-0.002
piring-0.002
 aboard-0.002
 afloat-0.002
oms-0.002
Token,
Token ID11
Feature activation+8.33e-02

Pos logit contributions
ravings+0.089
 loved+0.084
pron+0.084
Years+0.082
 habit+0.081
Neg logit contributions
 plunge-0.096
piring-0.094
chie-0.090
aro-0.085
ps-0.085
Token he
Token ID339
Feature activation-1.91e-01

Pos logit contributions
 plunge+0.007
piring+0.007
aro+0.006
chie+0.006
 aboard+0.006
Neg logit contributions
ravings-0.007
Years-0.007
pron-0.007
 habit-0.006
 loved-0.006
Token noticed
Token ID6810
Feature activation-1.42e+00

Pos logit contributions
Years+0.015
ravings+0.015
 batch+0.014
pron+0.014
 habit+0.014
Neg logit contributions
 plunge-0.016
piring-0.015
oms-0.015
 nearer-0.014
 afloat-0.014
Token something
Token ID1223
Feature activation-1.23e+00

Pos logit contributions
ravings+0.122
pron+0.115
Years+0.112
 habit+0.111
omo+0.104
Neg logit contributions
 plunge-0.118
piring-0.111
aro-0.103
ter-0.102
 aboard-0.101
Token sound
Token ID2128
Feature activation-1.58e+00

Pos logit contributions
 plunge+0.091
piring+0.088
chie+0.082
aro+0.081
 afloat+0.078
Neg logit contributions
ravings-0.069
pron-0.065
Years-0.064
 loved-0.062
 habit-0.061
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
ravings+0.112
pron+0.106
Years+0.105
 loved+0.102
 habit+0.100
Neg logit contributions
 plunge-0.151
piring-0.145
chie-0.136
aro-0.134
ps-0.130
Token The
Token ID383
Feature activation-1.79e-01

Pos logit contributions
ravings+0.017
Years+0.017
 habit+0.016
pron+0.016
udd+0.016
Neg logit contributions
 plunge-0.015
aro-0.014
piring-0.014
 aboard-0.014
oms-0.013
Token dog
Token ID3290
Feature activation+1.05e-01

Pos logit contributions
ravings+0.014
Years+0.014
pron+0.013
 often+0.013
udd+0.013
Neg logit contributions
 plunge-0.016
piring-0.015
ps-0.014
 afloat-0.013
ter-0.013
Token was
Token ID373
Feature activation-2.12e-01

Pos logit contributions
 plunge+0.008
piring+0.008
ps+0.008
aro+0.008
fly+0.007
Neg logit contributions
ravings-0.010
pron-0.009
Years-0.008
 habit-0.008
omo-0.008
Token surprised
Token ID6655
Feature activation-2.05e-01

Pos logit contributions
ravings+0.017
pron+0.016
Years+0.016
 habit+0.015
 loved+0.015
Neg logit contributions
 plunge-0.019
piring-0.018
chie-0.017
aro-0.016
ps-0.016
Token and
Token ID290
Feature activation-2.35e-01

Pos logit contributions
ravings+0.014
pron+0.013
Years+0.013
 loved+0.012
 habit+0.012
Neg logit contributions
 plunge-0.020
piring-0.020
chie-0.018
aro-0.018
ps-0.018
Token scared
Token ID12008
Feature activation+1.15e+00

Pos logit contributions
ravings+0.018
pron+0.017
Years+0.017
 habit+0.016
omo+0.015
Neg logit contributions
 plunge-0.021
piring-0.020
aro-0.019
chie-0.019
ps-0.018
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
 plunge+0.119
piring+0.114
chie+0.108
aro+0.106
 afloat+0.104
Neg logit contributions
ravings-0.073
Years-0.067
 loved-0.067
pron-0.065
 habit-0.064
Token He
Token ID679
Feature activation-4.01e-01

Pos logit contributions
ravings+0.010
pron+0.010
Years+0.009
 habit+0.009
 loved+0.009
Neg logit contributions
 plunge-0.010
piring-0.009
aro-0.009
 aboard-0.008
chie-0.008
Token ran
Token ID4966
Feature activation+5.62e-01

Pos logit contributions
ravings+0.035
pron+0.033
Years+0.031
 habit+0.031
 batch+0.030
Neg logit contributions
 plunge-0.033
ps-0.031
piring-0.029
aro-0.029
chie-0.028
Token very
Token ID845
Feature activation-2.74e-01

Pos logit contributions
ravings+0.014
Years+0.014
pron+0.013
udd+0.012
 habit+0.012
Neg logit contributions
 plunge-0.015
piring-0.015
ps-0.014
 afloat-0.014
chie-0.014
Token happy
Token ID3772
Feature activation-4.56e-01

Pos logit contributions
ravings+0.020
Years+0.019
pron+0.018
 dentist+0.017
 batch+0.017
Neg logit contributions
 plunge-0.025
piring-0.025
chie-0.023
 afloat-0.023
ps-0.022
Token.
Token ID13
Feature activation+9.61e-02

Pos logit contributions
Years+0.041
pron+0.041
ravings+0.041
Days+0.039
 habit+0.038
Neg logit contributions
piring-0.031
ter-0.030
 plunge-0.030
 aboard-0.030
aro-0.028
Token
Token ID198
Feature activation-1.60e-01

Pos logit contributions
 plunge+0.007
aro+0.006
piring+0.006
ions+0.006
 Tri+0.006
Neg logit contributions
pron-0.009
ravings-0.008
Years-0.008
 habit-0.008
Days-0.007
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
ravings+0.014
pron+0.013
 habit+0.012
auldron+0.012
Years+0.012
Neg logit contributions
 plunge-0.012
aro-0.012
piring-0.011
 aboard-0.011
ions-0.011
TokenNow
Token ID3844
Feature activation-2.22e-01

Pos logit contributions
ravings+0.015
auldron+0.013
 cousin+0.013
 tum+0.013
 habit+0.013
Neg logit contributions
aro-0.015
 plunge-0.014
piring-0.014
ions-0.014
hing-0.013
Token,
Token ID11
Feature activation+6.85e-02

Pos logit contributions
ravings+0.017
pron+0.016
Years+0.016
 loved+0.015
 habit+0.015
Neg logit contributions
 plunge-0.020
piring-0.020
chie-0.018
aro-0.018
ps-0.018
Token Tim
Token ID5045
Feature activation+3.46e-01

Pos logit contributions
 plunge+0.006
piring+0.006
aro+0.005
ter+0.005
 aboard+0.005
Neg logit contributions
ravings-0.005
pron-0.005
Years-0.005
udd-0.005
 habit-0.005
Token could
Token ID714
Feature activation-1.78e-01

Pos logit contributions
 plunge+0.031
piring+0.031
ps+0.030
 aboard+0.030
chie+0.029
Neg logit contributions
Years-0.024
ravings-0.023
pron-0.022
Days-0.021
 batch-0.020
Token wear
Token ID5806
Feature activation+9.12e-01

Pos logit contributions
ravings+0.013
pron+0.013
Years+0.013
 loved+0.012
 habit+0.012
Neg logit contributions
 plunge-0.016
piring-0.016
chie-0.015
aro-0.014
ps-0.014
Token his
Token ID465
Feature activation+1.54e-01

Pos logit contributions
 plunge+0.077
piring+0.073
chie+0.068
aro+0.067
ps+0.067
Neg logit contributions
ravings-0.075
Years-0.070
pron-0.070
 habit-0.067
 loved-0.066
Token moment
Token ID2589
Feature activation+2.47e+00

Pos logit contributions
ravings+0.012
Years+0.011
udd+0.011
omo+0.010
pron+0.010
Neg logit contributions
 plunge-0.009
piring-0.008
chie-0.007
 afloat-0.007
iest-0.007
Token.
Token ID13
Feature activation-2.78e-02

Pos logit contributions
 plunge+0.229
piring+0.223
chie+0.206
aro+0.204
ps+0.199
Neg logit contributions
ravings-0.181
pron-0.170
Years-0.168
 habit-0.160
 loved-0.159
Token They
Token ID1119
Feature activation-2.21e-01

Pos logit contributions
ravings+0.003
pron+0.002
Years+0.002
 habit+0.002
becca+0.002
Neg logit contributions
piring-0.002
 plunge-0.002
oms-0.002
 aboard-0.002
ps-0.002
Token like
Token ID588
Feature activation+1.23e-01

Pos logit contributions
ravings+0.020
pron+0.019
Years+0.019
 habit+0.018
 loved+0.018
Neg logit contributions
 plunge-0.017
piring-0.016
chie-0.015
ps-0.014
aro-0.014
Token y
Token ID331
Feature activation+7.00e-02

Pos logit contributions
piring+0.010
 plunge+0.010
aro+0.009
ps+0.009
ions+0.009
Neg logit contributions
ravings-0.010
Years-0.009
 habit-0.009
pron-0.009
udd-0.009
Tokenummy
Token ID13513
Feature activation+1.46e+00

Pos logit contributions
 plunge+0.006
piring+0.006
chie+0.006
aro+0.006
 aboard+0.005
Neg logit contributions
ravings-0.006
pron-0.005
Years-0.005
omo-0.005
udd-0.005
Token break
Token ID2270
Feature activation+6.31e-01

Pos logit contributions
 plunge+0.154
piring+0.151
chie+0.140
aro+0.139
ps+0.137
Neg logit contributions
ravings-0.087
Years-0.081
pron-0.081
 habit-0.075
 loved-0.075
Tokenf
Token ID69
Feature activation+2.24e+00

Pos logit contributions
 plunge+0.061
piring+0.058
chie+0.055
aro+0.054
 afloat+0.052
Neg logit contributions
ravings-0.045
pron-0.042
 loved-0.041
Years-0.041
 habit-0.039
Tokenasts
Token ID5773
Feature activation+1.97e-01

Pos logit contributions
 plunge+0.179
piring+0.171
chie+0.158
aro+0.156
 afloat+0.150
Neg logit contributions
ravings-0.196
pron-0.186
Years-0.183
 loved-0.177
 habit-0.176
Token and
Token ID290
Feature activation-2.82e-02

Pos logit contributions
 plunge+0.021
piring+0.019
chie+0.019
aro+0.018
 afloat+0.018
Neg logit contributions
ravings-0.012
pron-0.012
 loved-0.011
Years-0.011
 habit-0.011
Token fun
Token ID1257
Feature activation-6.04e-01

Pos logit contributions
ravings+0.002
pron+0.002
Years+0.002
 loved+0.002
 habit+0.002
Neg logit contributions
 plunge-0.002
piring-0.002
chie-0.002
aro-0.002
ps-0.002
Token butter
Token ID9215
Feature activation-2.10e+00

Pos logit contributions
 plunge+0.048
piring+0.047
chie+0.044
aro+0.043
 afloat+0.042
Neg logit contributions
pron-0.034
ravings-0.033
 loved-0.032
Years-0.032
 batch-0.030
Token on
Token ID319
Feature activation-3.61e-01

Pos logit contributions
pron+0.188
ravings+0.178
 loved+0.174
Years+0.171
 friend+0.169
Neg logit contributions
 plunge-0.166
piring-0.156
chie-0.150
aro-0.144
oms-0.139
Token the
Token ID262
Feature activation+6.88e-02

Pos logit contributions
ravings+0.029
pron+0.028
Years+0.027
 loved+0.026
 habit+0.026
Neg logit contributions
 plunge-0.031
piring-0.030
chie-0.028
aro-0.027
ps-0.027
Token pancakes
Token ID47008
Feature activation-1.49e+00

Pos logit contributions
 plunge+0.006
piring+0.006
chie+0.006
ps+0.006
aro+0.006
Neg logit contributions
ravings-0.005
Years-0.005
pron-0.005
 habit-0.004
 loved-0.004
Token and
Token ID290
Feature activation-1.21e-01

Pos logit contributions
ravings+0.088
pron+0.088
 loved+0.081
Years+0.080
 habit+0.075
Neg logit contributions
 plunge-0.158
piring-0.153
chie-0.150
aro-0.145
 afloat-0.140
Token it
Token ID340
Feature activation-7.39e-01

Pos logit contributions
ravings+0.010
Years+0.009
 habit+0.009
Days+0.009
udd+0.008
Neg logit contributions
 plunge-0.010
piring-0.010
ter-0.009
ions-0.009
ps-0.009
Token was
Token ID373
Feature activation-2.51e-01

Pos logit contributions
ravings+0.055
Years+0.049
 habit+0.048
pron+0.047
omo+0.045
Neg logit contributions
 plunge-0.068
piring-0.066
ps-0.062
aro-0.060
iest-0.060
Token so
Token ID523
Feature activation-2.90e-02

Pos logit contributions
ravings+0.020
 habit+0.018
Years+0.018
udd+0.018
becca+0.018
Neg logit contributions
 plunge-0.020
piring-0.020
ps-0.019
ions-0.018
 afloat-0.018
Token smooth
Token ID7209
Feature activation+3.49e-01

Pos logit contributions
ravings+0.002
 habit+0.002
Years+0.002
 dentist+0.002
 friend+0.002
Neg logit contributions
piring-0.003
 plunge-0.003
iest-0.002
 happen-0.002
aro-0.002
Token.
Token ID13
Feature activation+5.90e-03

Pos logit contributions
 plunge+0.038
piring+0.036
chie+0.036
aro+0.035
 afloat+0.034
Neg logit contributions
ravings-0.020
 loved-0.019
pron-0.019
Years-0.018
 often-0.018
Token
Token ID198
Feature activation-2.70e-01

Pos logit contributions
 plunge+0.000
oms+0.000
oming+0.000
piring+0.000
 onto+0.000
Neg logit contributions
ravings-0.001
Years-0.000
pron-0.000
 habit-0.000
 dentist-0.000
Token get
Token ID651
Feature activation+1.97e-01

Pos logit contributions
ravings+0.048
 loved+0.047
pron+0.046
Years+0.046
 habit+0.045
Neg logit contributions
 plunge-0.037
piring-0.036
aro-0.033
chie-0.033
ions-0.030
Token a
Token ID257
Feature activation-2.41e-01

Pos logit contributions
 plunge+0.017
piring+0.016
chie+0.015
aro+0.015
ps+0.015
Neg logit contributions
ravings-0.016
pron-0.016
Years-0.016
 habit-0.015
omo-0.014
Token point
Token ID966
Feature activation+5.81e-01

Pos logit contributions
ravings+0.020
Years+0.019
udd+0.017
 loved+0.017
becca+0.017
Neg logit contributions
 plunge-0.021
piring-0.020
chie-0.018
 aboard-0.018
 nearer-0.018
Token."
Token ID526
Feature activation+6.78e-01

Pos logit contributions
 plunge+0.057
piring+0.053
chie+0.050
 afloat+0.050
aro+0.050
Neg logit contributions
ravings-0.039
pron-0.038
 loved-0.036
 friend-0.036
Years-0.035
Token
Token ID198
Feature activation-3.05e-01

Pos logit contributions
 plunge+0.062
piring+0.060
aro+0.057
 aboard+0.057
oms+0.056
Neg logit contributions
ravings-0.049
pron-0.046
 habit-0.045
Years-0.044
 loved-0.042
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
ravings+0.024
pron+0.023
 habit+0.022
Years+0.021
becca+0.020
Neg logit contributions
 plunge-0.026
piring-0.025
aro-0.024
 aboard-0.024
oms-0.024
TokenThey
Token ID2990
Feature activation-1.96e-02

Pos logit contributions
ravings+0.026
 habit+0.024
pron+0.024
 tum+0.022
 favorite+0.022
Neg logit contributions
piring-0.026
 ourselves-0.025
 plunge-0.025
chie-0.025
 aboard-0.024
Token keep
Token ID1394
Feature activation+4.70e-01

Pos logit contributions
ravings+0.002
 loved+0.002
pron+0.002
Years+0.002
 habit+0.002
Neg logit contributions
 plunge-0.001
piring-0.001
chie-0.001
aro-0.001
 afloat-0.001
Token playing
Token ID2712
Feature activation-1.26e+00

Pos logit contributions
 plunge+0.043
piring+0.042
chie+0.041
iest+0.040
aro+0.038
Neg logit contributions
ravings-0.032
 loved-0.032
Years-0.032
pron-0.031
 friend-0.031
Token the
Token ID262
Feature activation+1.84e-01

Pos logit contributions
ravings+0.096
pron+0.090
Years+0.089
omo+0.084
 habit+0.084
Neg logit contributions
 plunge-0.114
piring-0.110
aro-0.101
ps-0.101
chie-0.101
Token game
Token ID983
Feature activation-3.18e-02

Pos logit contributions
 plunge+0.017
piring+0.016
chie+0.015
ps+0.015
aro+0.015
Neg logit contributions
ravings-0.014
Years-0.013
pron-0.013
 habit-0.013
 loved-0.013
Token love
Token ID1842
Feature activation-2.24e-01

Pos logit contributions
ravings+0.100
Years+0.095
pron+0.092
 batch+0.088
becca+0.087
Neg logit contributions
 plunge-0.072
piring-0.067
iest-0.061
 nearer-0.060
 afloat-0.060
Token riding
Token ID10311
Feature activation-1.30e+00

Pos logit contributions
ravings+0.020
pron+0.019
Years+0.019
 loved+0.018
 habit+0.018
Neg logit contributions
 plunge-0.017
piring-0.017
chie-0.016
aro-0.015
ps-0.015
Token the
Token ID262
Feature activation+2.71e-01

Pos logit contributions
ravings+0.113
pron+0.107
Years+0.107
 loved+0.105
 habit+0.102
Neg logit contributions
 plunge-0.103
piring-0.100
chie-0.091
aro-0.089
ps-0.087
Token silver
Token ID8465
Feature activation+5.97e-01

Pos logit contributions
 plunge+0.026
piring+0.026
chie+0.024
aro+0.024
ps+0.023
Neg logit contributions
ravings-0.019
pron-0.018
Years-0.017
 loved-0.017
 habit-0.017
Token bike
Token ID7161
Feature activation+2.32e-01

Pos logit contributions
 plunge+0.050
piring+0.048
chie+0.044
aro+0.044
 aboard+0.043
Neg logit contributions
ravings-0.049
Years-0.047
pron-0.046
 loved-0.044
 habit-0.044
Token at
Token ID379
Feature activation-1.86e+00

Pos logit contributions
 plunge+0.018
piring+0.018
chie+0.016
aro+0.016
 aboard+0.016
Neg logit contributions
ravings-0.020
pron-0.019
Years-0.019
 habit-0.018
 loved-0.018
Token the
Token ID262
Feature activation+1.97e-01

Pos logit contributions
ravings+0.165
pron+0.155
Years+0.155
 loved+0.151
 habit+0.149
Neg logit contributions
 plunge-0.144
piring-0.140
chie-0.128
aro-0.126
ps-0.121
Token park
Token ID3952
Feature activation-1.25e+00

Pos logit contributions
 plunge+0.020
piring+0.018
chie+0.017
 aboard+0.017
ter+0.017
Neg logit contributions
pron-0.013
ravings-0.013
Years-0.013
omo-0.012
 loved-0.012
Token!"
Token ID2474
Feature activation+7.12e-01

Pos logit contributions
ravings+0.120
Years+0.120
pron+0.119
 habit+0.111
Days+0.109
Neg logit contributions
 plunge-0.086
piring-0.080
 aboard-0.076
chie-0.074
ter-0.074
Token They
Token ID1119
Feature activation-1.10e-01

Pos logit contributions
 onto+0.039
aro+0.037
 plunge+0.037
 aboard+0.036
 Tri+0.036
Neg logit contributions
Days-0.071
Years-0.071
ravings-0.069
pron-0.068
becca-0.064
Token stayed
Token ID9658
Feature activation+5.13e-01

Pos logit contributions
ravings+0.010
pron+0.009
 dentist+0.008
Years+0.008
 batch+0.008
Neg logit contributions
 plunge-0.010
piring-0.009
 aboard-0.008
chie-0.008
aro-0.008
Token from
Token ID422
Feature activation+1.51e+00

Pos logit contributions
 plunge+0.088
piring+0.083
chie+0.080
aro+0.078
ps+0.077
Neg logit contributions
ravings-0.060
pron-0.058
Years-0.056
 loved-0.054
 habit-0.053
Token a
Token ID257
Feature activation-6.29e-01

Pos logit contributions
 plunge+0.117
piring+0.112
chie+0.104
aro+0.103
ps+0.101
Neg logit contributions
ravings-0.133
pron-0.126
Years-0.125
 habit-0.120
 loved-0.119
Token distant
Token ID12899
Feature activation-1.93e-01

Pos logit contributions
ravings+0.049
Years+0.046
omo+0.044
udd+0.044
 habit+0.040
Neg logit contributions
 plunge-0.057
piring-0.053
chie-0.051
 afloat-0.047
 nearer-0.047
Token friend
Token ID1545
Feature activation-7.91e-01

Pos logit contributions
Years+0.016
ravings+0.016
omo+0.015
udd+0.015
pron+0.015
Neg logit contributions
 plunge-0.016
chie-0.014
piring-0.014
 aboard-0.014
 afloat-0.013
Token.
Token ID13
Feature activation-2.02e-01

Pos logit contributions
ravings+0.056
pron+0.052
Years+0.052
 loved+0.049
 habit+0.049
Neg logit contributions
 plunge-0.075
piring-0.073
chie-0.068
aro-0.067
ps-0.066
Token
Token ID198
Feature activation-4.43e-01

Pos logit contributions
pron+0.017
ravings+0.017
Years+0.016
 habit+0.016
udd+0.015
Neg logit contributions
 plunge-0.016
aro-0.015
piring-0.015
 aboard-0.014
chie-0.014
Token
Token ID198
Feature activation-4.25e-01

Pos logit contributions
ravings+0.039
pron+0.037
 habit+0.034
auldron+0.032
 dentist+0.032
Neg logit contributions
 plunge-0.036
aro-0.035
piring-0.033
 nearer-0.032
 aboard-0.032
TokenS
Token ID50
Feature activation-5.25e-01

Pos logit contributions
ravings+0.031
pron+0.029
 habit+0.027
auldron+0.027
ingu+0.026
Neg logit contributions
aro-0.039
 plunge-0.039
piring-0.038
chie-0.037
 nearer-0.036
Tokenue
Token ID518
Feature activation-1.07e-02

Pos logit contributions
ravings+0.035
pron+0.033
 habit+0.031
Years+0.031
 loved+0.031
Neg logit contributions
 plunge-0.052
piring-0.050
chie-0.048
aro-0.046
oms-0.046
Token was
Token ID373
Feature activation-3.32e-01

Pos logit contributions
ravings+0.001
pron+0.001
Years+0.001
 habit+0.001
omo+0.001
Neg logit contributions
ps-0.001
piring-0.001
 plunge-0.001
 aboard-0.001
fly-0.001
Token so
Token ID523
Feature activation-2.70e-02

Pos logit contributions
ravings+0.030
Years+0.028
pron+0.028
 habit+0.026
udd+0.026
Neg logit contributions
 plunge-0.026
piring-0.025
chie-0.023
ps-0.023
 aboard-0.022
Token
Token ID198
Feature activation-3.24e-01

Pos logit contributions
ravings+0.029
 habit+0.026
pron+0.025
auldron+0.024
Years+0.023
Neg logit contributions
 plunge-0.028
aro-0.027
piring-0.026
chie-0.026
 aboard-0.025
TokenThe
Token ID464
Feature activation-2.11e-01

Pos logit contributions
ravings+0.027
 habit+0.024
pron+0.023
 dentist+0.023
udd+0.022
Neg logit contributions
 plunge-0.028
chie-0.027
piring-0.027
aro-0.027
ions-0.025
Token teacher
Token ID4701
Feature activation-7.35e-01

Pos logit contributions
ravings+0.015
pron+0.013
omo+0.013
Years+0.013
udd+0.012
Neg logit contributions
 plunge-0.020
piring-0.020
chie-0.019
ps-0.019
oms-0.018
Token asked
Token ID1965
Feature activation-5.89e-01

Pos logit contributions
ravings+0.062
Years+0.055
 habit+0.055
pron+0.054
Days+0.051
Neg logit contributions
piring-0.061
 plunge-0.060
oms-0.057
aro-0.056
 aboard-0.055
Token,
Token ID11
Feature activation+5.11e-02

Pos logit contributions
 loved+0.044
ravings+0.043
 friend+0.041
 habit+0.041
Years+0.041
Neg logit contributions
 plunge-0.051
piring-0.050
chie-0.048
aro-0.047
 afloat-0.046
Token "
Token ID366
Feature activation-9.48e-01

Pos logit contributions
 plunge+0.006
piring+0.006
chie+0.005
aro+0.005
ps+0.005
Neg logit contributions
ravings-0.003
pron-0.002
Years-0.002
 loved-0.002
 habit-0.002
TokenWhere
Token ID8496
Feature activation+7.94e-01

Pos logit contributions
ravings+0.074
pron+0.071
Years+0.070
 loved+0.067
 habit+0.067
Neg logit contributions
 plunge-0.083
piring-0.080
chie-0.075
aro-0.074
ps-0.072
Token should
Token ID815
Feature activation+1.18e+00

Pos logit contributions
 plunge+0.058
piring+0.055
chie+0.048
aro+0.048
oms+0.047
Neg logit contributions
ravings-0.076
Years-0.073
pron-0.072
 habit-0.068
omo-0.066
Token we
Token ID356
Feature activation+1.13e+00

Pos logit contributions
 plunge+0.084
piring+0.082
 afloat+0.077
ps+0.073
chie+0.072
Neg logit contributions
ravings-0.108
pron-0.105
 friend-0.105
 loved-0.104
Years-0.101
Token go
Token ID467
Feature activation-5.19e-02

Pos logit contributions
piring+0.103
 plunge+0.101
aro+0.099
 afloat+0.095
ps+0.094
Neg logit contributions
 loved-0.082
ravings-0.080
 often-0.077
 friend-0.076
pron-0.074
Token now
Token ID783
Feature activation+9.66e-01

Pos logit contributions
 loved+0.003
 often+0.003
 friend+0.003
ravings+0.003
pron+0.003
Neg logit contributions
piring-0.006
 plunge-0.005
aro-0.005
ps-0.005
chie-0.005
Token and
Token ID290
Feature activation-2.87e-01

Pos logit contributions
 plunge+0.028
piring+0.027
chie+0.024
aro+0.024
ps+0.023
Neg logit contributions
ravings-0.030
pron-0.028
Years-0.028
 habit-0.027
 loved-0.026
Token jumped
Token ID11687
Feature activation-1.63e-01

Pos logit contributions
ravings+0.021
pron+0.019
Years+0.019
omo+0.018
 habit+0.018
Neg logit contributions
 plunge-0.028
piring-0.027
aro-0.025
 aboard-0.025
chie-0.024
Token in
Token ID287
Feature activation-9.76e-02

Pos logit contributions
ravings+0.012
 loved+0.012
Years+0.012
pron+0.012
 often+0.012
Neg logit contributions
piring-0.014
 plunge-0.013
chie-0.013
aro-0.012
ions-0.012
Token the
Token ID262
Feature activation-6.69e-02

Pos logit contributions
ravings+0.007
Years+0.007
 loved+0.007
pron+0.007
 habit+0.007
Neg logit contributions
piring-0.009
 plunge-0.009
chie-0.008
aro-0.008
oms-0.007
Token p
Token ID279
Feature activation+1.22e+00

Pos logit contributions
ravings+0.006
pron+0.006
Years+0.006
 habit+0.005
 loved+0.005
Neg logit contributions
 plunge-0.005
piring-0.005
chie-0.005
aro-0.004
ps-0.004
Tokenudd
Token ID4185
Feature activation-3.29e+00

Pos logit contributions
 plunge+0.133
chie+0.131
oms+0.130
piring+0.127
aro+0.126
Neg logit contributions
pron-0.066
Years-0.063
ravings-0.062
 dentist-0.058
 habit-0.057
Tokenles
Token ID829
Feature activation+4.42e-01

Pos logit contributions
ravings+0.186
udd+0.177
pron+0.165
Years+0.162
 loved+0.162
Neg logit contributions
piring-0.359
 plunge-0.356
chie-0.326
aro-0.325
used-0.325
Token.
Token ID13
Feature activation-1.95e-01

Pos logit contributions
 plunge+0.041
piring+0.039
chie+0.037
aro+0.036
ps+0.035
Neg logit contributions
ravings-0.032
pron-0.030
Years-0.030
 loved-0.029
 habit-0.029
Token He
Token ID679
Feature activation-5.64e-01

Pos logit contributions
ravings+0.016
pron+0.016
Years+0.015
 habit+0.015
udd+0.015
Neg logit contributions
 plunge-0.015
piring-0.014
aro-0.014
 aboard-0.014
chie-0.013
Token shouted
Token ID17293
Feature activation+2.94e-01

Pos logit contributions
ravings+0.048
pron+0.043
Years+0.040
 habit+0.039
 dentist+0.039
Neg logit contributions
 plunge-0.050
aro-0.047
piring-0.045
chie-0.044
ps-0.043
Token,
Token ID11
Feature activation-1.26e-01

Pos logit contributions
 plunge+0.024
piring+0.023
chie+0.021
aro+0.021
ps+0.021
Neg logit contributions
ravings-0.025
pron-0.024
Years-0.023
 habit-0.022
 loved-0.022
Token home
Token ID1363
Feature activation-2.63e-01

Pos logit contributions
piring+0.010
 plunge+0.009
chie+0.009
aro+0.009
ps+0.009
Neg logit contributions
 friend-0.004
ravings-0.004
 owner-0.003
 loved-0.003
udd-0.003
Token.
Token ID13
Feature activation+1.48e-01

Pos logit contributions
ravings+0.015
 loved+0.014
pron+0.014
 friend+0.014
 habit+0.013
Neg logit contributions
 plunge-0.029
piring-0.028
chie-0.026
aro-0.026
ps-0.025
Token They
Token ID1119
Feature activation-1.26e-01

Pos logit contributions
 plunge+0.008
oms+0.008
piring+0.008
 onto+0.008
 aboard+0.007
Neg logit contributions
pron-0.015
Years-0.015
ravings-0.014
Days-0.014
 habit-0.014
Token learned
Token ID4499
Feature activation-2.25e+00

Pos logit contributions
ravings+0.011
Years+0.011
pron+0.010
 habit+0.010
Days+0.009
Neg logit contributions
 plunge-0.010
piring-0.009
 onto-0.008
 are-0.008
aro-0.008
Token that
Token ID326
Feature activation-3.33e-01

Pos logit contributions
ravings+0.193
pron+0.189
Years+0.175
 habit+0.173
omo+0.168
Neg logit contributions
 plunge-0.180
piring-0.172
 aboard-0.160
 ourselves-0.159
ps-0.158
Token sharing
Token ID7373
Feature activation-3.43e+00

Pos logit contributions
ravings+0.027
pron+0.026
Years+0.025
udd+0.024
 habit+0.023
Neg logit contributions
 plunge-0.029
piring-0.028
aro-0.026
 aboard-0.025
 happen-0.025
Token can
Token ID460
Feature activation+1.99e+00

Pos logit contributions
ravings+0.274
pron+0.259
Years+0.257
 habit+0.245
 loved+0.244
Neg logit contributions
 plunge-0.297
piring-0.287
chie-0.265
aro-0.262
ps-0.256
Token make
Token ID787
Feature activation+3.93e-01

Pos logit contributions
piring+0.176
 plunge+0.175
aro+0.160
chie+0.158
 aboard+0.154
Neg logit contributions
ravings-0.150
Years-0.149
pron-0.145
 loved-0.142
 often-0.140
Token them
Token ID606
Feature activation+1.52e+00

Pos logit contributions
 plunge+0.028
 ourselves+0.026
piring+0.025
 happen+0.024
ps+0.024
Neg logit contributions
pron-0.038
ravings-0.038
Years-0.035
omo-0.034
 habit-0.033
Token happy
Token ID3772
Feature activation-2.20e-01

Pos logit contributions
 plunge+0.162
piring+0.157
chie+0.148
aro+0.146
ps+0.143
Neg logit contributions
ravings-0.091
pron-0.084
Years-0.083
 loved-0.078
 habit-0.078
Token and
Token ID290
Feature activation+1.57e-01

Pos logit contributions
ravings+0.014
 loved+0.013
Years+0.013
pron+0.013
 habit+0.013
Neg logit contributions
 plunge-0.023
piring-0.022
chie-0.021
aro-0.020
 afloat-0.020
Token the
Token ID262
Feature activation-2.00e-02

Pos logit contributions
 plunge+0.090
piring+0.088
chie+0.083
aro+0.082
ps+0.079
Neg logit contributions
ravings-0.062
pron-0.059
Years-0.057
 loved-0.056
 habit-0.055
Token blanket
Token ID18447
Feature activation+8.83e-01

Pos logit contributions
ravings+0.001
pron+0.001
 loved+0.001
Years+0.001
 habit+0.001
Neg logit contributions
piring-0.002
 plunge-0.002
aro-0.002
chie-0.002
ps-0.002
Token.
Token ID13
Feature activation-1.40e-01

Pos logit contributions
 plunge+0.089
piring+0.086
chie+0.082
aro+0.080
ps+0.078
Neg logit contributions
ravings-0.057
pron-0.054
Years-0.052
 loved-0.052
 habit-0.050
Token Now
Token ID2735
Feature activation-8.29e-03

Pos logit contributions
ravings+0.011
pron+0.011
Years+0.011
 habit+0.010
 loved+0.010
Neg logit contributions
 plunge-0.012
piring-0.011
chie-0.010
aro-0.010
 aboard-0.010
Token c
Token ID269
Feature activation+1.40e+00

Pos logit contributions
ravings+0.001
 loved+0.001
 often+0.001
Years+0.001
pron+0.001
Neg logit contributions
 plunge-0.001
piring-0.001
chie-0.001
aro-0.001
 afloat-0.001
Tokenudd
Token ID4185
Feature activation-3.13e+00

Pos logit contributions
 plunge+0.160
piring+0.156
oms+0.151
oming+0.149
chie+0.147
Neg logit contributions
ravings-0.062
 habit-0.059
pron-0.058
 dentist-0.058
Years-0.057
Tokenling
Token ID1359
Feature activation-3.35e-01

Pos logit contributions
ravings+0.193
pron+0.184
Years+0.183
 loved+0.179
udd+0.175
Neg logit contributions
 plunge-0.319
piring-0.316
chie-0.300
 afloat-0.298
aro-0.291
Token up
Token ID510
Feature activation-6.12e-02

Pos logit contributions
ravings+0.023
 loved+0.022
pron+0.021
Years+0.021
 habit+0.021
Neg logit contributions
 plunge-0.032
piring-0.031
chie-0.029
aro-0.029
 afloat-0.028
Token on
Token ID319
Feature activation-4.15e-01

Pos logit contributions
ravings+0.004
 loved+0.004
pron+0.004
Years+0.004
 often+0.004
Neg logit contributions
 plunge-0.006
piring-0.006
chie-0.005
aro-0.005
ps-0.005
Token the
Token ID262
Feature activation-6.37e-02

Pos logit contributions
ravings+0.033
pron+0.032
 loved+0.031
Years+0.031
 often+0.030
Neg logit contributions
 plunge-0.036
piring-0.035
chie-0.033
aro-0.032
 afloat-0.031
Token blanket
Token ID18447
Feature activation+8.90e-01

Pos logit contributions
ravings+0.005
pron+0.005
Years+0.004
 loved+0.004
 habit+0.004
Neg logit contributions
 plunge-0.006
piring-0.006
chie-0.005
aro-0.005
ps-0.005
Token the
Token ID262
Feature activation+3.25e-01

Pos logit contributions
 plunge+0.008
piring+0.008
aro+0.007
chie+0.007
 aboard+0.007
Neg logit contributions
ravings-0.008
pron-0.007
Years-0.007
 habit-0.007
 loved-0.007
Token slide
Token ID10649
Feature activation+1.18e+00

Pos logit contributions
 plunge+0.029
piring+0.028
chie+0.026
aro+0.026
ps+0.025
Neg logit contributions
ravings-0.025
pron-0.024
Years-0.023
 loved-0.023
 habit-0.022
Token and
Token ID290
Feature activation+9.82e-02

Pos logit contributions
 plunge+0.080
piring+0.077
aro+0.071
chie+0.069
oms+0.069
Neg logit contributions
ravings-0.115
pron-0.112
Years-0.108
 habit-0.103
 dentist-0.101
Token the
Token ID262
Feature activation+3.18e-01

Pos logit contributions
 plunge+0.008
piring+0.007
chie+0.007
aro+0.007
ps+0.007
Neg logit contributions
ravings-0.009
pron-0.008
Years-0.008
 loved-0.008
 habit-0.008
Token sees
Token ID7224
Feature activation+5.05e-01

Pos logit contributions
 plunge+0.028
piring+0.027
chie+0.025
aro+0.024
ps+0.024
Neg logit contributions
ravings-0.026
pron-0.024
Years-0.024
 habit-0.023
 loved-0.022
Tokenaw
Token ID707
Feature activation-4.16e+00

Pos logit contributions
 plunge+0.055
piring+0.053
ps+0.050
aro+0.050
ter+0.050
Neg logit contributions
ravings-0.030
pron-0.029
Years-0.027
omo-0.025
 habit-0.025
Token.
Token ID13
Feature activation+4.10e-02

Pos logit contributions
ravings+0.259
pron+0.235
 loved+0.232
Years+0.231
udd+0.223
Neg logit contributions
 plunge-0.434
piring-0.410
chie-0.404
aro-0.387
 afloat-0.377
Token But
Token ID887
Feature activation-9.66e-02

Pos logit contributions
 plunge+0.003
piring+0.003
oms+0.003
ions+0.003
 aboard+0.003
Neg logit contributions
pron-0.003
Years-0.003
ravings-0.003
 habit-0.003
 dentist-0.003
Token their
Token ID511
Feature activation+1.03e+00

Pos logit contributions
ravings+0.008
pron+0.007
Years+0.007
 habit+0.007
 loved+0.007
Neg logit contributions
 plunge-0.009
piring-0.008
aro-0.008
chie-0.007
 aboard-0.007
Token favorite
Token ID4004
Feature activation-5.03e-01

Pos logit contributions
 plunge+0.106
piring+0.087
ps+0.087
 aboard+0.085
 happen+0.085
Neg logit contributions
ravings-0.068
pron-0.066
L-0.063
Years-0.062
As-0.061
Token thing
Token ID1517
Feature activation+1.28e+00

Pos logit contributions
ravings+0.039
Years+0.039
udd+0.036
pron+0.035
Days+0.035
Neg logit contributions
 plunge-0.046
iest-0.040
piring-0.040
aro-0.039
 aboard-0.039
Token special
Token ID2041
Feature activation+8.96e-01

Pos logit contributions
 plunge+0.098
piring+0.092
chie+0.085
aro+0.084
ps+0.084
Neg logit contributions
ravings-0.064
Years-0.058
pron-0.058
As-0.056
While-0.055
Token moment
Token ID2589
Feature activation+2.27e+00

Pos logit contributions
 plunge+0.082
piring+0.076
chie+0.072
ps+0.070
oms+0.069
Neg logit contributions
ravings-0.065
Years-0.062
pron-0.058
becca-0.057
As-0.057
Token as
Token ID355
Feature activation-3.91e-01

Pos logit contributions
 plunge+0.192
piring+0.187
chie+0.172
aro+0.170
 aboard+0.165
Neg logit contributions
ravings-0.186
pron-0.173
Years-0.173
 habit-0.166
 loved-0.164
Token well
Token ID880
Feature activation-1.44e+00

Pos logit contributions
ravings+0.031
pron+0.029
Years+0.029
 loved+0.028
 habit+0.027
Neg logit contributions
 plunge-0.034
piring-0.033
chie-0.031
aro-0.030
ps-0.030
Token as
Token ID355
Feature activation-3.94e-01

Pos logit contributions
ravings+0.111
pron+0.105
Years+0.102
 loved+0.101
 habit+0.098
Neg logit contributions
 plunge-0.129
piring-0.124
chie-0.117
aro-0.113
ps-0.109
Token sharing
Token ID7373
Feature activation-3.65e+00

Pos logit contributions
ravings+0.030
pron+0.029
Years+0.028
 loved+0.027
 habit+0.027
Neg logit contributions
 plunge-0.035
piring-0.034
chie-0.032
aro-0.031
ps-0.031
Token the
Token ID262
Feature activation+1.05e-01

Pos logit contributions
ravings+0.286
pron+0.270
Years+0.266
 loved+0.259
 habit+0.257
Neg logit contributions
 plunge-0.323
piring-0.310
chie-0.291
aro-0.284
ps-0.274
Token shirt
Token ID10147
Feature activation-2.32e+00

Pos logit contributions
 plunge+0.010
piring+0.009
chie+0.008
ps+0.008
 afloat+0.008
Neg logit contributions
ravings-0.008
Years-0.007
pron-0.007
omo-0.007
becca-0.007
Token
Token ID6184
Feature activation-9.88e-01

Pos logit contributions
ravings+0.163
pron+0.154
Years+0.150
 loved+0.146
 habit+0.144
Neg logit contributions
 plunge-0.223
piring-0.214
chie-0.202
aro-0.200
ps-0.193
Token
Token ID95
Feature activation-7.87e-01

Pos logit contributions
ravings+0.098
pron+0.093
Years+0.093
 loved+0.092
 habit+0.092
Neg logit contributions
 plunge-0.064
piring-0.059
chie-0.057
aro-0.054
oms-0.052
Token
Token ID26391
Feature activation+2.81e-01

Pos logit contributions
ravings+0.063
pron+0.059
Years+0.057
 habit+0.056
 friend+0.056
Neg logit contributions
 plunge-0.066
piring-0.064
chie-0.062
ps-0.058
 aboard-0.058