TOP ACTIVATIONS
MAX = 7.543

the forest looking for all sorts of exciting things . She
, thrilled to discover all sorts of new things .
filled with decorations and all sorts of fun toys .
book and told her all sorts of new words . With
lake was filled with all sorts of trouble . As soon
box . They guessed all sorts of things like cand ies
. She tried using all sorts of measures - a ruler
Now we can mix all sorts of cool things together !"
was excited and asked all sorts of questions .
into the stream and all sorts of interesting things caught her
packing his bag with all sorts of things he thought he
, getting up to all sorts of mischief . Her favorite
the microscope and discovering all sorts of wonderful things .
mushrooms , asking them all sorts of questions .
impressed . Inside were all sorts of snacks , treats and
le ran to grab all sorts of decorations , including balloons
coins and toys , all sorts of surprises were waiting for
a strange vendor selling all sorts of interesting things . She
! He would make all sorts of shapes in the air
he was acting out all sorts of adventures . Every day

MIN ACTIVATIONS
MIN = -8.066

the village back to its former glory !"
the tree to its once former beauty . He was happy
back the village to its former state . With the help
to be restored to its former glory ."
, leaving it to its former state .
aunt told Lucy , " Sweet heart , you know that
very tired . The ash tr ay watched as the little
. The ash tr ay was ready to provide
backyard there was an ash tr ay . It was the
� � € � � Sweet ie , why don â
room and saw an ash tr ay . She remembered her
The poor ash tr ay was broken and it
carefully picked up the ash tr ay and put it in
little boy squeezed the ash tr ay close and gave it
There was an ash tr ay on the ground .
to create her own ash tr ay . She went to
, he saw an ash tr ay on the table .
. He said , " Sweet heart , it 's not
saw a dusty old ash tr ay on the shelf .
, Lily found an ash tr ay in the world behind

INTERVAL 3.641 - 7.543
CONTAINS 0.733%

was hitting the target with ease . Everyone was cheering for
and color with her cr ay ons . One day ,
day he was still just as troubled as the day before
and their friendship grew stronger than ever . The
he felt the monster 's breath on his neck .

INTERVAL -0.262 - 3.641
CONTAINS 63.398%

day , the old girl went outside to take a walk
boy named Tim my . Tim my loved to play with
her pocket . And then she carried on with what she
The boat tried to drop the anchor , but it was
the fish , so it said , " I will lead

INTERVAL -4.164 - -0.262
CONTAINS 35.535%

Jack saw her crying and helped her pick up all the
eyel ids and cheeks . It was fun to watch her
, but she was a little scared . "
friends and sailed on the lake together every week . <|endoftext|>
mar bles . She only had two mar bles and enjoyed

INTERVAL -8.066 - -4.164
CONTAINS 0.334%

teeth . " Hey , stop that !" their
M oral of the story : It 's important to
would not touch her makeup again . Sara forg ave him
for selling them a bad movie . The man felt very
drink water from the f auc et but she was too
Token the
Token ID262
Feature activation+1.65e-01

Pos logit contributions
 moment+0.038
 ending+0.037
Sleep+0.037
 polar+0.037
 mistake+0.037
Neg logit contributions
ay-0.036
issors-0.033
ong-0.033
rac-0.033
ars-0.031
Token forest
Token ID8222
Feature activation-1.25e+00

Pos logit contributions
ay+0.006
 around+0.006
ong+0.006
 high+0.006
ars+0.006
Neg logit contributions
Sweet-0.005
Kids-0.005
Sleep-0.005
 forgiveness-0.004
Are-0.004
Token looking
Token ID2045
Feature activation-3.05e-01

Pos logit contributions
Sleep+0.049
 polar+0.049
 ending+0.048
Sweet+0.048
 mistake+0.047
Neg logit contributions
ay-0.035
ong-0.032
rac-0.031
issors-0.030
 around-0.029
Token for
Token ID329
Feature activation+2.75e+00

Pos logit contributions
 ending+0.012
 moment+0.012
 polar+0.011
Sleep+0.011
 mistake+0.011
Neg logit contributions
ay-0.009
rac-0.009
issors-0.009
ong-0.009
ors-0.008
Token all
Token ID477
Feature activation+1.31e+00

Pos logit contributions
 around+0.075
 at+0.070
ay+0.069
ong+0.066
 high+0.063
Neg logit contributions
 department-0.108
Kids-0.107
fly-0.106
tr-0.105
 divorce-0.105
Token sorts
Token ID10524
Feature activation+7.54e+00

Pos logit contributions
ay+0.032
 around+0.031
ong+0.029
rac+0.027
bs+0.026
Neg logit contributions
Sweet-0.055
Sleep-0.055
 polar-0.055
 ending-0.054
 mistake-0.054
Token of
Token ID286
Feature activation-1.81e+00

Pos logit contributions
rac+0.232
ay+0.227
issors+0.222
ong+0.220
ars+0.199
Neg logit contributions
Sleep-0.266
Sweet-0.262
 forgiveness-0.258
 ending-0.254
 polar-0.254
Token exciting
Token ID7895
Feature activation+1.53e+00

Pos logit contributions
Sleep+0.064
 ending+0.063
Sweet+0.062
Kids+0.061
 department+0.061
Neg logit contributions
ay-0.056
 around-0.055
ong-0.053
bs-0.049
 at-0.048
Token things
Token ID1243
Feature activation+1.08e+00

Pos logit contributions
ay+0.051
ong+0.048
 around+0.048
rac+0.045
bs+0.044
Neg logit contributions
Sleep-0.051
Sweet-0.050
 polar-0.050
 ending-0.050
 mistake-0.049
Token.
Token ID13
Feature activation-2.71e-01

Pos logit contributions
ay+0.031
ong+0.028
rac+0.028
issors+0.027
ars+0.026
Neg logit contributions
Sleep-0.042
 ending-0.041
 polar-0.041
Sweet-0.041
 moment-0.041
Token She
Token ID1375
Feature activation+1.39e-01

Pos logit contributions
 mistake+0.012
 polar+0.012
 ending+0.011
 department+0.011
 forgiveness+0.011
Neg logit contributions
ay-0.007
 around-0.006
issors-0.006
bs-0.006
rac-0.005
Token,
Token ID11
Feature activation+4.02e-01

Pos logit contributions
ay+0.062
rac+0.057
ong+0.057
issors+0.055
bs+0.052
Neg logit contributions
 ending-0.078
 moment-0.077
 polar-0.076
Sleep-0.076
 mistake-0.075
Token thrilled
Token ID20536
Feature activation+1.47e+00

Pos logit contributions
ay+0.014
ong+0.013
rac+0.013
 around+0.012
issors+0.012
Neg logit contributions
Sleep-0.013
 polar-0.013
Sweet-0.013
 ending-0.013
 mistake-0.012
Token to
Token ID284
Feature activation-9.77e-02

Pos logit contributions
issors+0.046
ay+0.046
bs+0.044
ong+0.043
ars+0.043
Neg logit contributions
 ending-0.051
 moment-0.051
 mistake-0.049
 polar-0.048
Sleep-0.048
Token discover
Token ID7073
Feature activation+7.94e-02

Pos logit contributions
Sleep+0.004
Sweet+0.004
 polar+0.003
 department+0.003
Kids+0.003
Neg logit contributions
ay-0.003
ong-0.003
 around-0.003
rac-0.003
ars-0.003
Token all
Token ID477
Feature activation+1.23e+00

Pos logit contributions
ay+0.003
ong+0.002
 around+0.002
rac+0.002
bs+0.002
Neg logit contributions
Sleep-0.003
Sweet-0.003
 ending-0.003
 polar-0.003
Kids-0.003
Token sorts
Token ID10524
Feature activation+7.50e+00

Pos logit contributions
ay+0.038
ong+0.037
rac+0.036
issors+0.035
ars+0.033
Neg logit contributions
 polar-0.044
Sleep-0.044
 moment-0.044
 ending-0.043
 mistake-0.043
Token of
Token ID286
Feature activation-1.87e+00

Pos logit contributions
rac+0.263
issors+0.259
ay+0.246
ong+0.243
itching+0.231
Neg logit contributions
 forgiveness-0.228
 polar-0.225
Sleep-0.225
Sweet-0.217
 pand-0.217
Token new
Token ID649
Feature activation-6.21e-01

Pos logit contributions
Sleep+0.064
Sweet+0.063
 polar+0.062
 ending+0.062
 mistake+0.060
Neg logit contributions
ay-0.061
ong-0.058
 around-0.056
rac-0.056
issors-0.053
Token things
Token ID1243
Feature activation+1.03e+00

Pos logit contributions
 polar+0.019
Sleep+0.019
Sweet+0.019
 ending+0.019
 mistake+0.019
Neg logit contributions
ay-0.022
ong-0.021
rac-0.021
issors-0.020
 around-0.020
Token.
Token ID13
Feature activation-1.29e-01

Pos logit contributions
ay+0.031
rac+0.030
ong+0.029
issors+0.028
ars+0.026
Neg logit contributions
Sleep-0.038
 polar-0.037
 moment-0.037
 ending-0.037
Sweet-0.036
Token
Token ID198
Feature activation+3.89e-01

Pos logit contributions
 mistake+0.005
 ending+0.005
Sleep+0.005
Sweet+0.005
 polar+0.005
Neg logit contributions
ay-0.004
 around-0.003
ong-0.003
issors-0.003
rac-0.003
Token filled
Token ID5901
Feature activation+1.81e+00

Pos logit contributions
ay+0.002
ong+0.002
rac+0.002
 around+0.002
issors+0.001
Neg logit contributions
Sleep-0.002
 polar-0.002
Sweet-0.002
 ending-0.002
 mistake-0.002
Token with
Token ID351
Feature activation+1.15e+00

Pos logit contributions
ay+0.045
ong+0.042
 around+0.041
rac+0.040
issors+0.037
Neg logit contributions
Sleep-0.076
 ending-0.075
Sweet-0.075
 polar-0.075
 mistake-0.073
Token decorations
Token ID39011
Feature activation+8.42e-02

Pos logit contributions
ay+0.038
 around+0.036
ong+0.035
bs+0.032
rac+0.032
Neg logit contributions
Sleep-0.039
Sweet-0.039
 ending-0.038
Kids-0.038
 mistake-0.038
Token and
Token ID290
Feature activation+5.55e-02

Pos logit contributions
ay+0.002
ong+0.002
rac+0.002
issors+0.002
 around+0.002
Neg logit contributions
Sleep-0.003
 polar-0.003
 ending-0.003
Sweet-0.003
 mistake-0.003
Token all
Token ID477
Feature activation+1.40e+00

Pos logit contributions
 around+0.002
ong+0.002
ay+0.002
bs+0.002
 at+0.001
Neg logit contributions
Sleep-0.002
Sweet-0.002
Kids-0.002
 mistake-0.002
 divorce-0.002
Token sorts
Token ID10524
Feature activation+7.42e+00

Pos logit contributions
ay+0.041
ong+0.040
rac+0.039
issors+0.039
ars+0.036
Neg logit contributions
 polar-0.052
Sleep-0.052
 ending-0.051
 moment-0.051
Sweet-0.051
Token of
Token ID286
Feature activation-1.98e+00

Pos logit contributions
rac+0.230
issors+0.230
ay+0.218
ong+0.216
itching+0.206
Neg logit contributions
Sleep-0.254
 forgiveness-0.252
Sweet-0.249
 ending-0.245
 polar-0.242
Token fun
Token ID1257
Feature activation+1.36e+00

Pos logit contributions
Sleep+0.066
 ending+0.065
Sweet+0.065
 polar+0.065
 mistake+0.063
Neg logit contributions
ay-0.067
ong-0.063
 around-0.061
rac-0.059
bs-0.057
Token toys
Token ID14958
Feature activation+2.51e-01

Pos logit contributions
ay+0.040
ong+0.037
 around+0.036
rac+0.035
bs+0.034
Neg logit contributions
Sleep-0.051
 polar-0.051
Sweet-0.050
 ending-0.050
 mistake-0.049
Token.
Token ID13
Feature activation-2.63e-01

Pos logit contributions
ay+0.007
ong+0.006
rac+0.006
issors+0.006
 around+0.006
Neg logit contributions
Sleep-0.010
 polar-0.010
 ending-0.010
Sweet-0.010
 mistake-0.010
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
 mistake+0.011
 ending+0.010
Sleep+0.010
 polar+0.010
 forgiveness+0.010
Neg logit contributions
ay-0.008
 around-0.007
issors-0.006
rac-0.006
ong-0.006
Token book
Token ID1492
Feature activation+2.42e-01

Pos logit contributions
Sleep+0.057
 ending+0.057
 polar+0.057
Sweet+0.057
 mistake+0.056
Neg logit contributions
ay-0.045
ong-0.042
rac-0.041
issors-0.040
 around-0.038
Token and
Token ID290
Feature activation+2.35e-02

Pos logit contributions
ay+0.007
rac+0.007
ong+0.007
issors+0.007
bs+0.006
Neg logit contributions
 ending-0.009
Sleep-0.009
 moment-0.008
 mistake-0.008
 polar-0.008
Token told
Token ID1297
Feature activation-8.81e-01

Pos logit contributions
 around+0.001
ay+0.001
ong+0.001
bs+0.001
rac+0.001
Neg logit contributions
Sleep-0.001
Sweet-0.001
 polar-0.001
 ending-0.001
 mistake-0.001
Token her
Token ID607
Feature activation+1.33e+00

Pos logit contributions
Sleep+0.033
 polar+0.033
 ending+0.033
Sweet+0.033
 mistake+0.033
Neg logit contributions
ay-0.026
ong-0.024
rac-0.024
issors-0.023
ars-0.023
Token all
Token ID477
Feature activation+1.10e+00

Pos logit contributions
ay+0.031
 around+0.030
ong+0.028
rac+0.027
bs+0.026
Neg logit contributions
Sleep-0.059
 polar-0.058
Sweet-0.058
Kids-0.057
Are-0.056
Token sorts
Token ID10524
Feature activation+7.38e+00

Pos logit contributions
ay+0.031
ong+0.029
 around+0.028
rac+0.027
bs+0.026
Neg logit contributions
Sleep-0.043
Sweet-0.043
 polar-0.043
 ending-0.042
 mistake-0.041
Token of
Token ID286
Feature activation-1.96e+00

Pos logit contributions
rac+0.232
issors+0.224
ay+0.223
ong+0.222
itching+0.204
Neg logit contributions
 forgiveness-0.258
Sleep-0.254
 ending-0.244
 moral-0.241
Sweet-0.241
Token new
Token ID649
Feature activation-5.64e-01

Pos logit contributions
 mistake+0.055
 ending+0.054
 moral+0.053
Sweet+0.053
Sleep+0.053
Neg logit contributions
ay-0.076
rac-0.075
ong-0.073
issors-0.069
ors-0.066
Token words
Token ID2456
Feature activation+9.17e-01

Pos logit contributions
 mistake+0.016
 moment+0.016
 ending+0.016
Sweet+0.015
 moral+0.015
Neg logit contributions
rac-0.022
ay-0.021
ong-0.021
issors-0.020
ars-0.019
Token.
Token ID13
Feature activation-2.73e-01

Pos logit contributions
ay+0.027
ong+0.025
rac+0.025
issors+0.024
ars+0.023
Neg logit contributions
Sleep-0.034
 ending-0.033
Sweet-0.033
 moment-0.033
 polar-0.033
Token With
Token ID2080
Feature activation+5.15e-01

Pos logit contributions
 mistake+0.012
 ending+0.012
 polar+0.012
Sleep+0.011
 divorce+0.011
Neg logit contributions
ay-0.007
 around-0.006
rac-0.006
ong-0.006
bs-0.006
Token lake
Token ID13546
Feature activation-1.20e+00

Pos logit contributions
Sweet+0.018
Sleep+0.018
Kids+0.017
Acc+0.016
Are+0.016
Neg logit contributions
 around-0.023
ay-0.022
 at-0.021
rac-0.019
 high-0.019
Token was
Token ID373
Feature activation-1.13e-01

Pos logit contributions
Sweet+0.035
Sleep+0.035
 polar+0.034
 ending+0.033
 mistake+0.033
Neg logit contributions
ay-0.045
 around-0.043
ong-0.043
rac-0.042
bs-0.040
Token filled
Token ID5901
Feature activation+1.43e+00

Pos logit contributions
Sleep+0.004
 polar+0.004
Sweet+0.004
 ending+0.004
 mistake+0.004
Neg logit contributions
ay-0.004
ong-0.004
rac-0.003
 around-0.003
issors-0.003
Token with
Token ID351
Feature activation+9.04e-01

Pos logit contributions
ay+0.042
ong+0.041
rac+0.039
issors+0.038
bs+0.038
Neg logit contributions
 moment-0.053
Sleep-0.052
 mistake-0.052
 polar-0.052
 ending-0.051
Token all
Token ID477
Feature activation+9.28e-01

Pos logit contributions
ay+0.031
ong+0.029
 around+0.028
rac+0.027
bs+0.026
Neg logit contributions
Sleep-0.030
Sweet-0.030
 ending-0.029
 polar-0.029
 mistake-0.029
Token sorts
Token ID10524
Feature activation+7.36e+00

Pos logit contributions
ay+0.027
ong+0.027
rac+0.026
issors+0.025
ars+0.025
Neg logit contributions
 polar-0.034
Sleep-0.034
 moment-0.034
Sweet-0.034
 ending-0.033
Token of
Token ID286
Feature activation-1.99e+00

Pos logit contributions
issors+0.262
rac+0.261
ong+0.247
ay+0.238
itching+0.226
Neg logit contributions
 forgiveness-0.225
Sleep-0.219
 polar-0.210
Sweet-0.210
 ending-0.207
Token trouble
Token ID5876
Feature activation+9.25e-01

Pos logit contributions
Sleep+0.067
Sweet+0.066
 ending+0.066
 polar+0.065
 mistake+0.064
Neg logit contributions
ay-0.067
ong-0.063
 around-0.061
rac-0.060
bs-0.057
Token.
Token ID13
Feature activation-4.43e-01

Pos logit contributions
ay+0.023
ong+0.021
 around+0.021
rac+0.019
ors+0.019
Neg logit contributions
Sweet-0.039
Sleep-0.039
 polar-0.038
 ending-0.038
Kids-0.037
Token As
Token ID1081
Feature activation+1.09e+00

Pos logit contributions
Sleep+0.016
 polar+0.016
 ending+0.016
Sweet+0.016
 mistake+0.016
Neg logit contributions
ay-0.013
ong-0.012
rac-0.012
 around-0.012
issors-0.012
Token soon
Token ID2582
Feature activation+4.95e-01

Pos logit contributions
ay+0.033
 around+0.030
ong+0.028
bs+0.028
rac+0.028
Neg logit contributions
Sleep-0.041
Sweet-0.040
 polar-0.040
 mistake-0.039
Kids-0.038
Token box
Token ID3091
Feature activation+6.20e-01

Pos logit contributions
ay+0.014
 around+0.013
ong+0.013
ars+0.012
 at+0.012
Neg logit contributions
Kids-0.009
Sleep-0.009
Sweet-0.009
 polar-0.008
 ending-0.008
Token.
Token ID13
Feature activation-3.71e-01

Pos logit contributions
ay+0.016
ong+0.015
rac+0.014
 around+0.014
issors+0.013
Neg logit contributions
Sleep-0.026
Sweet-0.025
 polar-0.025
 ending-0.025
 mistake-0.025
Token They
Token ID1119
Feature activation-4.09e-01

Pos logit contributions
 mistake+0.016
Sleep+0.016
 polar+0.015
 ending+0.015
Sweet+0.015
Neg logit contributions
ay-0.010
 around-0.009
ong-0.009
issors-0.009
rac-0.009
Token guessed
Token ID25183
Feature activation+3.56e-01

Pos logit contributions
 polar+0.013
Sleep+0.012
 ending+0.012
Sweet+0.012
 mistake+0.012
Neg logit contributions
ay-0.015
ong-0.014
rac-0.014
issors-0.013
 around-0.013
Token all
Token ID477
Feature activation+1.05e+00

Pos logit contributions
ay+0.012
ong+0.011
rac+0.011
issors+0.010
ars+0.010
Neg logit contributions
 polar-0.012
 ending-0.012
Sleep-0.012
Sweet-0.012
 mistake-0.012
Token sorts
Token ID10524
Feature activation+7.34e+00

Pos logit contributions
ay+0.032
ong+0.030
rac+0.030
issors+0.028
ars+0.027
Neg logit contributions
Sleep-0.038
 ending-0.038
 polar-0.038
Sweet-0.037
 mistake-0.037
Token of
Token ID286
Feature activation-2.03e+00

Pos logit contributions
rac+0.253
issors+0.242
ong+0.238
ay+0.237
itching+0.229
Neg logit contributions
 forgiveness-0.230
 ending-0.216
Sleep-0.212
 moral-0.208
 moment-0.206
Token things
Token ID1243
Feature activation+9.18e-01

Pos logit contributions
 polar+0.063
 mistake+0.063
Sleep+0.062
Sweet+0.062
 ending+0.062
Neg logit contributions
ay-0.072
rac-0.069
ong-0.068
issors-0.065
bs-0.062
Token like
Token ID588
Feature activation+2.06e+00

Pos logit contributions
ay+0.029
rac+0.027
ong+0.027
issors+0.026
ars+0.025
Neg logit contributions
 ending-0.032
Sleep-0.032
 moment-0.032
 mistake-0.031
 polar-0.031
Token cand
Token ID2658
Feature activation-2.67e+00

Pos logit contributions
ay+0.071
ong+0.067
 around+0.065
rac+0.064
issors+0.062
Neg logit contributions
Sleep-0.068
Sweet-0.067
 polar-0.066
 ending-0.065
Kids-0.064
Tokenies
Token ID444
Feature activation+2.64e+00

Pos logit contributions
 polar+0.055
 mistake+0.055
 moment+0.054
 department+0.053
Sweet+0.052
Neg logit contributions
ay-0.116
rac-0.114
ong-0.107
issors-0.107
 around-0.105
Token.
Token ID13
Feature activation-3.09e-01

Pos logit contributions
 moment+0.007
 ending+0.007
 mistake+0.006
 island+0.006
 again+0.006
Neg logit contributions
ay-0.007
rac-0.007
ong-0.006
issors-0.006
bs-0.006
Token She
Token ID1375
Feature activation-6.70e-02

Pos logit contributions
Sleep+0.010
Sweet+0.010
 ending+0.010
 moment+0.010
 polar+0.010
Neg logit contributions
ong-0.010
ay-0.010
rac-0.010
ars-0.009
 around-0.009
Token tried
Token ID3088
Feature activation+8.37e-01

Pos logit contributions
 polar+0.002
 department+0.002
 moment+0.002
Sweet+0.002
 mistake+0.002
Neg logit contributions
ay-0.003
ong-0.003
issors-0.003
rac-0.003
ors-0.002
Token using
Token ID1262
Feature activation+5.93e-01

Pos logit contributions
ay+0.024
ong+0.023
rac+0.022
issors+0.021
ars+0.021
Neg logit contributions
 mistake-0.032
 moment-0.032
 ending-0.032
Sweet-0.032
Sleep-0.031
Token all
Token ID477
Feature activation+9.92e-01

Pos logit contributions
ay+0.025
ars+0.025
ong+0.025
rac+0.024
led+0.024
Neg logit contributions
 treasure-0.015
 moment-0.015
 mistake-0.014
 forgiveness-0.014
 pear-0.013
Token sorts
Token ID10524
Feature activation+7.33e+00

Pos logit contributions
ong+0.035
ars+0.034
rac+0.034
itching+0.033
issors+0.033
Neg logit contributions
 moment-0.032
Sweet-0.028
 moral-0.028
Sleep-0.027
 forgiveness-0.027
Token of
Token ID286
Feature activation-1.88e+00

Pos logit contributions
rac+0.281
ong+0.267
ables+0.265
issors+0.263
itching+0.262
Neg logit contributions
 forgiveness-0.203
 moral-0.179
 moment-0.178
Sleep-0.175
Sweet-0.173
Token measures
Token ID5260
Feature activation+2.02e-02

Pos logit contributions
 mistake+0.051
 moment+0.050
 moral+0.048
 forgiveness+0.047
Sweet+0.045
Neg logit contributions
rac-0.076
ay-0.074
ong-0.073
issors-0.069
ors-0.067
Token -
Token ID532
Feature activation-5.43e-01

Pos logit contributions
ay+0.001
rac+0.001
ong+0.001
issors+0.001
ars+0.001
Neg logit contributions
 moment-0.001
 mistake-0.001
 Bird-0.001
 department-0.001
 ending-0.001
Token a
Token ID257
Feature activation+2.89e-01

Pos logit contributions
Sleep+0.018
 polar+0.018
Sweet+0.018
 ending+0.018
 mistake+0.017
Neg logit contributions
ay-0.018
ong-0.017
rac-0.017
 around-0.016
issors-0.016
Token ruler
Token ID22740
Feature activation+3.83e+00

Pos logit contributions
ay+0.009
ong+0.008
 around+0.008
rac+0.007
issors+0.007
Neg logit contributions
Sleep-0.011
Kids-0.011
Sweet-0.011
 polar-0.010
 ending-0.010
TokenNow
Token ID3844
Feature activation+3.67e-01

Pos logit contributions
ay+0.071
rac+0.067
ong+0.065
 around+0.064
issors+0.063
Neg logit contributions
 polar-0.053
 mistake-0.052
 ending-0.052
 department-0.049
 forgiveness-0.048
Token we
Token ID356
Feature activation-1.01e+00

Pos logit contributions
ay+0.012
ong+0.012
rac+0.011
 around+0.011
issors+0.011
Neg logit contributions
Sleep-0.012
 polar-0.012
Sweet-0.012
 ending-0.012
 mistake-0.012
Token can
Token ID460
Feature activation+6.82e-01

Pos logit contributions
Sleep+0.032
 polar+0.032
Sweet+0.032
 ending+0.032
 mistake+0.031
Neg logit contributions
ay-0.035
ong-0.033
rac-0.032
 around-0.031
issors-0.031
Token mix
Token ID5022
Feature activation-9.01e-01

Pos logit contributions
ay+0.025
ong+0.025
led+0.024
rac+0.024
issors+0.024
Neg logit contributions
 moral-0.018
 polar-0.018
 mistake-0.018
Sleep-0.017
Sweet-0.017
Token all
Token ID477
Feature activation+1.16e+00

Pos logit contributions
 moment+0.025
 snow+0.025
Sweet+0.024
 mistake+0.024
 again+0.024
Neg logit contributions
ay-0.031
issors-0.030
ong-0.030
ars-0.030
rac-0.030
Token sorts
Token ID10524
Feature activation+7.32e+00

Pos logit contributions
ong+0.039
issors+0.039
ars+0.039
ay+0.039
rac+0.038
Neg logit contributions
 moment-0.037
Sweet-0.033
 mistake-0.033
 moral-0.033
Sleep-0.032
Token of
Token ID286
Feature activation-2.02e+00

Pos logit contributions
itching+0.239
rac+0.238
issors+0.237
ong+0.232
ables+0.231
Neg logit contributions
 forgiveness-0.220
Sweet-0.211
Sleep-0.208
 moral-0.198
 moment-0.193
Token cool
Token ID3608
Feature activation+7.67e-02

Pos logit contributions
 mistake+0.058
Sweet+0.058
 moment+0.057
Sleep+0.055
 moral+0.055
Neg logit contributions
ay-0.075
rac-0.073
ong-0.072
issors-0.071
ars-0.069
Token things
Token ID1243
Feature activation+9.70e-01

Pos logit contributions
rac+0.003
ay+0.003
ong+0.003
issors+0.003
ars+0.003
Neg logit contributions
 moment-0.002
Sweet-0.002
Sleep-0.002
 mistake-0.002
Kids-0.002
Token together
Token ID1978
Feature activation+3.07e-02

Pos logit contributions
ay+0.031
ong+0.029
rac+0.029
issors+0.028
ars+0.028
Neg logit contributions
Sleep-0.032
 moment-0.032
Sweet-0.031
 ending-0.031
 polar-0.031
Token!"
Token ID2474
Feature activation+9.88e-02

Pos logit contributions
ay+0.001
ong+0.001
rac+0.001
issors+0.001
bs+0.001
Neg logit contributions
 moment-0.001
Sleep-0.001
 mistake-0.001
 ending-0.001
Sweet-0.001
Token was
Token ID373
Feature activation-1.09e-01

Pos logit contributions
ay+0.094
issors+0.089
ong+0.088
rac+0.083
bs+0.081
Neg logit contributions
 polar-0.036
 moment-0.034
Sleep-0.034
Sweet-0.034
 mistake-0.034
Token excited
Token ID6568
Feature activation+1.52e+00

Pos logit contributions
 polar+0.004
Are+0.003
 Bird+0.003
 moment+0.003
Sweet+0.003
Neg logit contributions
ay-0.004
issors-0.004
ors-0.004
ong-0.004
bs-0.004
Token and
Token ID290
Feature activation-1.30e-02

Pos logit contributions
ay+0.057
rac+0.057
ars+0.056
issors+0.055
bs+0.053
Neg logit contributions
 ending-0.048
 moment-0.047
 mistake-0.046
 again-0.045
Sleep-0.043
Token asked
Token ID1965
Feature activation-1.30e+00

Pos logit contributions
 polar+0.000
 moment+0.000
 ending+0.000
Sleep+0.000
Sweet+0.000
Neg logit contributions
ay-0.001
issors-0.001
ong-0.001
ars-0.000
rac-0.000
Token all
Token ID477
Feature activation+9.91e-01

Pos logit contributions
 polar+0.048
Sleep+0.048
Sweet+0.048
 ending+0.047
 mistake+0.047
Neg logit contributions
ay-0.039
ong-0.037
rac-0.036
issors-0.034
 around-0.034
Token sorts
Token ID10524
Feature activation+7.31e+00

Pos logit contributions
ay+0.031
ong+0.030
rac+0.029
ars+0.028
issors+0.028
Neg logit contributions
 polar-0.036
 moment-0.034
 mistake-0.034
 ending-0.034
Sleep-0.034
Token of
Token ID286
Feature activation-2.00e+00

Pos logit contributions
rac+0.276
issors+0.265
ables+0.261
ay+0.257
ong+0.256
Neg logit contributions
 forgiveness-0.222
 polar-0.198
Sleep-0.196
 moral-0.190
Sweet-0.186
Token questions
Token ID2683
Feature activation+2.43e+00

Pos logit contributions
 polar+0.063
 mistake+0.062
Sweet+0.061
Sleep+0.060
 moral+0.060
Neg logit contributions
ay-0.073
rac-0.071
ong-0.067
issors-0.067
bs-0.063
Token.
Token ID13
Feature activation-4.33e-01

Pos logit contributions
ay+0.076
rac+0.072
ong+0.071
issors+0.068
bs+0.066
Neg logit contributions
Sleep-0.084
 ending-0.082
 polar-0.082
 moment-0.082
Sweet-0.081
Token
Token ID220
Feature activation+9.50e-01

Pos logit contributions
 polar+0.014
Sleep+0.014
Sweet+0.014
 ending+0.014
 moment+0.014
Neg logit contributions
ay-0.014
ong-0.014
rac-0.013
 around-0.013
issors-0.013
Token
Token ID198
Feature activation-3.64e-02

Pos logit contributions
ay+0.039
ong+0.039
rac+0.038
 around+0.036
issors+0.036
Neg logit contributions
Sleep-0.022
Sweet-0.021
 polar-0.021
 moment-0.021
 moral-0.020
Token into
Token ID656
Feature activation+4.19e-01

Pos logit contributions
ay+0.089
issors+0.088
ong+0.087
ars+0.085
rac+0.083
Neg logit contributions
 moment-0.084
 moral-0.081
 again-0.080
 ending-0.080
Sleep-0.079
Token the
Token ID262
Feature activation+3.77e-01

Pos logit contributions
ay+0.010
 around+0.009
ong+0.009
rac+0.008
bs+0.008
Neg logit contributions
Sleep-0.018
 ending-0.018
Sweet-0.018
 department-0.018
 polar-0.018
Token stream
Token ID4269
Feature activation-4.14e-03

Pos logit contributions
ay+0.017
 around+0.017
ong+0.016
ars+0.015
s+0.015
Neg logit contributions
Sweet-0.009
Sleep-0.008
 ending-0.008
 forgiveness-0.008
 mistake-0.008
Token and
Token ID290
Feature activation-3.65e-02

Pos logit contributions
 moment+0.000
 polar+0.000
 ending+0.000
Sleep+0.000
 mistake+0.000
Neg logit contributions
ay-0.000
rac-0.000
issors-0.000
ong-0.000
bs-0.000
Token all
Token ID477
Feature activation+1.04e+00

Pos logit contributions
Sleep+0.001
 ending+0.001
 mistake+0.001
Sweet+0.001
 polar+0.001
Neg logit contributions
 around-0.001
ong-0.001
ay-0.001
rac-0.001
bs-0.001
Token sorts
Token ID10524
Feature activation+7.30e+00

Pos logit contributions
ay+0.032
issors+0.030
ong+0.030
rac+0.029
ars+0.028
Neg logit contributions
 moment-0.039
 polar-0.038
 ending-0.037
Sleep-0.036
Kids-0.036
Token of
Token ID286
Feature activation-2.01e+00

Pos logit contributions
rac+0.238
ay+0.238
issors+0.235
ong+0.225
ables+0.224
Neg logit contributions
 forgiveness-0.237
Sleep-0.236
 ending-0.232
Sweet-0.225
 moral-0.220
Token interesting
Token ID3499
Feature activation+1.46e+00

Pos logit contributions
Sleep+0.071
 ending+0.070
Sweet+0.070
 department+0.069
 divorce+0.067
Neg logit contributions
ay-0.063
 around-0.062
ong-0.061
bs-0.055
ars-0.054
Token things
Token ID1243
Feature activation+8.79e-01

Pos logit contributions
ay+0.050
ong+0.048
rac+0.046
 around+0.045
issors+0.044
Neg logit contributions
Sleep-0.047
 polar-0.047
Sweet-0.047
 ending-0.046
 mistake-0.045
Token caught
Token ID4978
Feature activation+2.81e-01

Pos logit contributions
ay+0.026
rac+0.024
ong+0.024
issors+0.022
ars+0.021
Neg logit contributions
Sleep-0.033
 ending-0.033
Sweet-0.033
 polar-0.032
 moment-0.032
Token her
Token ID607
Feature activation+1.19e+00

Pos logit contributions
ay+0.007
 around+0.006
ong+0.006
rac+0.006
bs+0.005
Neg logit contributions
Sleep-0.012
Sweet-0.012
 ending-0.012
 polar-0.012
Kids-0.012
Token packing
Token ID24157
Feature activation+4.90e-02

Pos logit contributions
ay+0.051
ong+0.047
rac+0.046
issors+0.046
ars+0.045
Neg logit contributions
 polar-0.053
 ending-0.051
 mistake-0.051
 moment-0.051
Sleep-0.050
Token his
Token ID465
Feature activation+6.98e-01

Pos logit contributions
ay+0.002
ong+0.002
rac+0.002
issors+0.002
bs+0.002
Neg logit contributions
 moment-0.002
 mistake-0.001
 ending-0.001
 again-0.001
 polar-0.001
Token bag
Token ID6131
Feature activation+3.16e+00

Pos logit contributions
ay+0.028
ong+0.027
issors+0.026
bs+0.026
rac+0.026
Neg logit contributions
 polar-0.019
 moment-0.018
 mistake-0.018
 ending-0.018
 bathroom-0.017
Token with
Token ID351
Feature activation+9.76e-01

Pos logit contributions
rac+0.101
ay+0.101
ong+0.098
issors+0.095
bs+0.093
Neg logit contributions
 moment-0.103
 again-0.097
 ending-0.095
Sleep-0.093
 polar-0.092
Token all
Token ID477
Feature activation+1.04e+00

Pos logit contributions
ay+0.035
rac+0.034
ong+0.034
issors+0.033
ars+0.032
Neg logit contributions
 polar-0.032
Sleep-0.029
 moment-0.029
 ending-0.029
 forgiveness-0.029
Token sorts
Token ID10524
Feature activation+7.29e+00

Pos logit contributions
ong+0.042
issors+0.041
ars+0.040
rac+0.039
itching+0.038
Neg logit contributions
 moment-0.029
 polar-0.028
 ig-0.027
 snow-0.026
Sleep-0.025
Token of
Token ID286
Feature activation-2.04e+00

Pos logit contributions
rac+0.299
issors+0.284
ong+0.270
ay+0.263
ables+0.260
Neg logit contributions
 forgiveness-0.188
 polar-0.179
Sleep-0.174
 ending-0.170
 moral-0.166
Token things
Token ID1243
Feature activation+8.62e-01

Pos logit contributions
 polar+0.062
Sleep+0.058
 moment+0.057
 mistake+0.056
Sweet+0.056
Neg logit contributions
rac-0.078
ay-0.076
ong-0.074
issors-0.074
ors-0.068
Token he
Token ID339
Feature activation+1.49e+00

Pos logit contributions
ay+0.032
rac+0.031
ong+0.029
issors+0.029
ars+0.026
Neg logit contributions
 moment-0.026
 ending-0.025
Sleep-0.025
 polar-0.025
 again-0.025
Token thought
Token ID1807
Feature activation+9.33e-01

Pos logit contributions
ay+0.070
ong+0.067
rac+0.064
issors+0.063
ors+0.062
Neg logit contributions
 ending-0.032
Sleep-0.032
 polar-0.032
 moment-0.032
 moral-0.030
Token he
Token ID339
Feature activation+1.47e+00

Pos logit contributions
ay+0.031
rac+0.030
issors+0.029
ong+0.029
itching+0.028
Neg logit contributions
 ending-0.031
 moment-0.030
Sleep-0.029
 mistake-0.029
 moral-0.028
Token,
Token ID11
Feature activation+2.62e-01

Pos logit contributions
 moment+0.024
 mistake+0.024
 ending+0.023
 raining+0.023
 bathroom+0.023
Neg logit contributions
ay-0.030
ong-0.028
rac-0.027
ars-0.025
issors-0.025
Token getting
Token ID1972
Feature activation-4.76e-01

Pos logit contributions
 around+0.008
ay+0.008
ong+0.008
rac+0.008
issors+0.007
Neg logit contributions
Sleep-0.009
Sweet-0.009
 polar-0.009
 ending-0.009
Kids-0.009
Token up
Token ID510
Feature activation+1.02e+00

Pos logit contributions
Sleep+0.017
 polar+0.016
Sweet+0.016
 ending+0.016
 mistake+0.016
Neg logit contributions
ay-0.015
ong-0.015
rac-0.014
 around-0.014
issors-0.013
Token to
Token ID284
Feature activation-1.74e-01

Pos logit contributions
ay+0.029
ong+0.027
rac+0.027
issors+0.025
ars+0.025
Neg logit contributions
Sleep-0.039
 polar-0.039
 ending-0.038
Sweet-0.038
 mistake-0.038
Token all
Token ID477
Feature activation+9.64e-01

Pos logit contributions
Sleep+0.008
 department+0.008
Sweet+0.008
fly+0.008
 polar+0.007
Neg logit contributions
ay-0.004
ong-0.004
 around-0.004
rac-0.003
 at-0.003
Token sorts
Token ID10524
Feature activation+7.28e+00

Pos logit contributions
ay+0.033
ong+0.033
ars+0.032
rac+0.031
issors+0.031
Neg logit contributions
 moment-0.031
Sleep-0.030
Sweet-0.030
 mistake-0.030
 polar-0.030
Token of
Token ID286
Feature activation-1.95e+00

Pos logit contributions
rac+0.271
ay+0.255
ong+0.252
issors+0.252
ables+0.242
Neg logit contributions
Sleep-0.210
 forgiveness-0.209
 pand-0.203
Sweet-0.198
 ending-0.195
Token mischief
Token ID38625
Feature activation+2.10e+00

Pos logit contributions
Sleep+0.064
 polar+0.063
Sweet+0.063
 ending+0.062
 mistake+0.061
Neg logit contributions
ay-0.067
ong-0.064
rac-0.062
 around-0.060
issors-0.059
Token.
Token ID13
Feature activation-3.55e-01

Pos logit contributions
ay+0.063
rac+0.060
ong+0.058
issors+0.055
bs+0.052
Neg logit contributions
Sleep-0.077
 polar-0.076
 ending-0.076
Sweet-0.075
 mistake-0.074
Token Her
Token ID2332
Feature activation-3.26e+00

Pos logit contributions
Sleep+0.011
 polar+0.011
Sweet+0.011
 ending+0.011
 mistake+0.010
Neg logit contributions
ay-0.013
ong-0.012
rac-0.012
 around-0.012
issors-0.011
Token favorite
Token ID4004
Feature activation-2.37e-01

Pos logit contributions
 ending+0.086
Sleep+0.086
 polar+0.086
Sweet+0.085
 mistake+0.083
Neg logit contributions
ay-0.132
ong-0.127
rac-0.124
 around-0.120
issors-0.119
Token the
Token ID262
Feature activation+3.20e-01

Pos logit contributions
ay+0.022
ong+0.021
rac+0.020
 around+0.020
issors+0.019
Neg logit contributions
Sleep-0.029
 polar-0.029
Sweet-0.029
 ending-0.029
 mistake-0.028
Token microscope
Token ID36396
Feature activation+5.37e-01

Pos logit contributions
ay+0.011
ong+0.011
rac+0.011
issors+0.010
 around+0.010
Neg logit contributions
Sleep-0.010
 polar-0.010
 ending-0.010
Sweet-0.010
 mistake-0.010
Token and
Token ID290
Feature activation+1.40e-01

Pos logit contributions
rac+0.017
ay+0.017
issors+0.016
ong+0.015
bs+0.015
Neg logit contributions
 moment-0.018
 again-0.018
 ending-0.018
 polar-0.017
 department-0.017
Token discovering
Token ID21611
Feature activation-7.68e-01

Pos logit contributions
ay+0.005
ong+0.005
rac+0.005
 around+0.004
issors+0.004
Neg logit contributions
Sleep-0.004
 polar-0.004
Sweet-0.004
 ending-0.004
 mistake-0.004
Token all
Token ID477
Feature activation+9.96e-01

Pos logit contributions
 polar+0.024
Sleep+0.024
Sweet+0.023
 ending+0.023
 mistake+0.023
Neg logit contributions
ay-0.028
ong-0.026
rac-0.026
issors-0.025
 around-0.024
Token sorts
Token ID10524
Feature activation+7.28e+00

Pos logit contributions
rac+0.034
ong+0.033
issors+0.033
ay+0.033
ars+0.032
Neg logit contributions
 moment-0.033
 polar-0.032
 ending-0.031
Sleep-0.031
 mistake-0.030
Token of
Token ID286
Feature activation-1.95e+00

Pos logit contributions
rac+0.265
issors+0.258
ay+0.239
ong+0.236
ars+0.224
Neg logit contributions
 forgiveness-0.218
Sleep-0.213
 polar-0.211
 ending-0.211
 moment-0.206
Token wonderful
Token ID7932
Feature activation-6.32e-01

Pos logit contributions
 polar+0.058
 mistake+0.058
Sweet+0.058
Sleep+0.058
 ending+0.057
Neg logit contributions
ay-0.072
rac-0.070
ong-0.069
issors-0.066
ars-0.064
Token things
Token ID1243
Feature activation+7.63e-01

Pos logit contributions
 moment+0.018
 polar+0.018
Sweet+0.017
 ending+0.017
 mistake+0.017
Neg logit contributions
ay-0.024
rac-0.024
ong-0.024
issors-0.023
ars-0.022
Token.
Token ID13
Feature activation-1.33e-01

Pos logit contributions
rac+0.027
ay+0.026
issors+0.025
ong+0.024
ars+0.023
Neg logit contributions
 moment-0.024
Sleep-0.024
 ending-0.024
 polar-0.023
 again-0.023
Token
Token ID220
Feature activation+1.01e+00

Pos logit contributions
Sleep+0.004
Sweet+0.004
 polar+0.004
 ending+0.004
 moment+0.004
Neg logit contributions
ay-0.005
ong-0.005
rac-0.005
issors-0.004
 around-0.004
Token mushrooms
Token ID23452
Feature activation+3.77e-02

Pos logit contributions
ay+0.010
ong+0.010
rac+0.009
 around+0.009
issors+0.009
Neg logit contributions
Sleep-0.007
 polar-0.007
Sweet-0.007
 ending-0.007
 mistake-0.006
Token,
Token ID11
Feature activation+4.70e-01

Pos logit contributions
ay+0.001
ong+0.001
rac+0.001
 around+0.001
issors+0.001
Neg logit contributions
Sleep-0.001
 polar-0.001
Sweet-0.001
 ending-0.001
 mistake-0.001
Token asking
Token ID4737
Feature activation+1.08e+00

Pos logit contributions
 around+0.013
ay+0.013
ong+0.013
rac+0.012
 at+0.012
Neg logit contributions
Sleep-0.018
Sweet-0.018
 polar-0.018
 ending-0.017
Kids-0.017
Token them
Token ID606
Feature activation+5.29e-01

Pos logit contributions
ay+0.035
ong+0.033
rac+0.032
issors+0.030
ars+0.030
Neg logit contributions
Sleep-0.037
 ending-0.037
 polar-0.037
Sweet-0.037
 mistake-0.037
Token all
Token ID477
Feature activation+1.08e+00

Pos logit contributions
 around+0.015
ay+0.014
ong+0.014
rac+0.013
bs+0.013
Neg logit contributions
Sleep-0.021
 polar-0.020
Sweet-0.020
Kids-0.020
 ending-0.020
Token sorts
Token ID10524
Feature activation+7.28e+00

Pos logit contributions
ay+0.030
 around+0.029
ong+0.029
rac+0.027
bs+0.026
Neg logit contributions
Sweet-0.042
Sleep-0.042
 polar-0.041
 ending-0.040
Kids-0.040
Token of
Token ID286
Feature activation-1.92e+00

Pos logit contributions
rac+0.226
ay+0.224
ong+0.215
issors+0.214
itching+0.196
Neg logit contributions
 forgiveness-0.252
Sleep-0.248
 polar-0.241
 ending-0.240
 moral-0.239
Token questions
Token ID2683
Feature activation+2.59e+00

Pos logit contributions
 mistake+0.057
Sleep+0.057
 polar+0.057
 moral+0.056
 ending+0.056
Neg logit contributions
ay-0.072
rac-0.070
ong-0.068
issors-0.067
ors-0.063
Token.
Token ID13
Feature activation-1.33e-01

Pos logit contributions
ay+0.073
ong+0.069
rac+0.067
issors+0.063
 around+0.062
Neg logit contributions
Sleep-0.099
 polar-0.097
 ending-0.097
Sweet-0.097
 moment-0.095
Token
Token ID220
Feature activation+1.14e+00

Pos logit contributions
 mistake+0.006
 ending+0.006
Sleep+0.006
 polar+0.006
Sweet+0.006
Neg logit contributions
ay-0.003
 around-0.003
rac-0.003
ong-0.003
issors-0.003
Token
Token ID198
Feature activation+3.21e-01

Pos logit contributions
ay+0.044
ong+0.042
rac+0.041
 around+0.040
issors+0.039
Neg logit contributions
Sleep-0.032
Sweet-0.031
 polar-0.031
 ending-0.030
 mistake-0.030
Token impressed
Token ID12617
Feature activation+1.33e+00

Pos logit contributions
 mistake+0.016
Sweet+0.015
 polar+0.015
 moment+0.014
 moral+0.014
Neg logit contributions
ay-0.024
ors-0.023
issors-0.023
rac-0.021
ong-0.021
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
ong+0.047
ay+0.047
rac+0.046
issors+0.046
ars+0.044
Neg logit contributions
 again-0.039
 moment-0.038
 forgiveness-0.038
Sleep-0.038
Kids-0.038
Token Inside
Token ID14384
Feature activation+6.59e-01

Pos logit contributions
Sleep+0.013
Sweet+0.013
 polar+0.013
 ending+0.012
 mistake+0.012
Neg logit contributions
ay-0.012
ong-0.011
rac-0.011
 around-0.010
issors-0.010
Token were
Token ID547
Feature activation-1.22e+00

Pos logit contributions
ong+0.026
issors+0.025
ay+0.024
rac+0.024
ars+0.024
Neg logit contributions
 moment-0.019
 ending-0.017
 mistake-0.017
 polar-0.016
 moral-0.016
Token all
Token ID477
Feature activation+9.96e-01

Pos logit contributions
Sleep+0.045
 mistake+0.044
 ending+0.043
 moment+0.043
Sweet+0.043
Neg logit contributions
ay-0.038
ong-0.036
 around-0.036
rac-0.033
 at-0.032
Token sorts
Token ID10524
Feature activation+7.28e+00

Pos logit contributions
ong+0.032
ay+0.032
rac+0.031
issors+0.031
ars+0.030
Neg logit contributions
 polar-0.034
 moment-0.033
Sweet-0.033
Sleep-0.032
 ending-0.032
Token of
Token ID286
Feature activation-2.12e+00

Pos logit contributions
rac+0.262
issors+0.248
ong+0.242
ay+0.235
ables+0.232
Neg logit contributions
 forgiveness-0.224
Sweet-0.209
Sleep-0.207
 ending-0.205
 polar-0.204
Token snacks
Token ID28487
Feature activation+1.81e+00

Pos logit contributions
Sleep+0.070
 polar+0.069
Sweet+0.069
 ending+0.068
 mistake+0.067
Neg logit contributions
ay-0.072
ong-0.068
rac-0.067
 around-0.064
issors-0.064
Token,
Token ID11
Feature activation+9.29e-02

Pos logit contributions
ay+0.052
rac+0.050
ong+0.049
issors+0.046
ars+0.044
Neg logit contributions
 ending-0.067
 polar-0.066
Sleep-0.066
 moment-0.065
Sweet-0.064
Token treats
Token ID18432
Feature activation-2.89e-01

Pos logit contributions
ay+0.003
 around+0.003
ong+0.003
bs+0.003
rac+0.003
Neg logit contributions
Sleep-0.003
 polar-0.003
Sweet-0.003
 ending-0.003
 mistake-0.003
Token and
Token ID290
Feature activation-4.00e-02

Pos logit contributions
 polar+0.011
Sleep+0.011
 ending+0.011
Sweet+0.011
 moment+0.011
Neg logit contributions
ay-0.008
ong-0.008
rac-0.007
issors-0.007
 around-0.007
Tokenle
Token ID293
Feature activation+5.27e-01

Pos logit contributions
Sleep+0.093
 polar+0.092
 ending+0.091
Sweet+0.091
 mistake+0.089
Neg logit contributions
ay-0.057
ong-0.054
 around-0.053
rac-0.051
bs-0.050
Token ran
Token ID4966
Feature activation+2.60e-01

Pos logit contributions
ay+0.021
ong+0.020
rac+0.020
 around+0.019
issors+0.019
Neg logit contributions
Sleep-0.014
 polar-0.014
Sweet-0.014
 ending-0.014
 mistake-0.014
Token to
Token ID284
Feature activation-1.94e-01

Pos logit contributions
rac+0.009
ay+0.009
ars+0.009
ong+0.008
issors+0.008
Neg logit contributions
 moment-0.009
 again-0.008
 department-0.008
 bathroom-0.008
 raining-0.008
Token grab
Token ID5552
Feature activation+8.26e-02

Pos logit contributions
 moment+0.006
Sweet+0.006
 mistake+0.006
Sleep+0.006
 polar+0.006
Neg logit contributions
ay-0.007
ong-0.007
rac-0.006
ars-0.006
issors-0.006
Token all
Token ID477
Feature activation+1.02e+00

Pos logit contributions
ay+0.003
ong+0.003
rac+0.003
ars+0.003
issors+0.003
Neg logit contributions
 moment-0.002
Sweet-0.002
 polar-0.002
 pear-0.002
 moral-0.002
Token sorts
Token ID10524
Feature activation+7.28e+00

Pos logit contributions
ars+0.036
ong+0.036
issors+0.036
itching+0.035
rac+0.035
Neg logit contributions
 moment-0.031
Sweet-0.030
 pear-0.029
Sleep-0.029
 Ab-0.028
Token of
Token ID286
Feature activation-1.95e+00

Pos logit contributions
rac+0.284
ables+0.268
issors+0.266
ay+0.257
ong+0.257
Neg logit contributions
 forgiveness-0.193
Sweet-0.186
 pand-0.182
Sleep-0.177
 moral-0.172
Token decorations
Token ID39011
Feature activation+3.23e-02

Pos logit contributions
Sweet+0.057
 polar+0.056
 moment+0.056
 mistake+0.055
Sleep+0.055
Neg logit contributions
ay-0.071
rac-0.070
ong-0.068
issors-0.068
ars-0.064
Token,
Token ID11
Feature activation+3.02e-01

Pos logit contributions
rac+0.001
ay+0.001
ong+0.001
issors+0.001
ars+0.001
Neg logit contributions
 moment-0.001
 ending-0.001
 mistake-0.001
 again-0.001
Sleep-0.001
Token including
Token ID1390
Feature activation+6.64e-01

Pos logit contributions
ay+0.009
 around+0.009
ong+0.009
rac+0.008
issors+0.008
Neg logit contributions
Sleep-0.011
 polar-0.011
 ending-0.011
Sweet-0.011
Kids-0.011
Token balloons
Token ID35485
Feature activation+2.06e-01

Pos logit contributions
ay+0.023
ong+0.022
 around+0.021
rac+0.020
bs+0.020
Neg logit contributions
Sleep-0.022
Sweet-0.022
 ending-0.022
 mistake-0.021
Kids-0.021
Token coins
Token ID10796
Feature activation+1.82e+00

Pos logit contributions
ay+0.036
ong+0.034
rac+0.034
issors+0.032
 around+0.031
Neg logit contributions
 polar-0.036
 ending-0.036
Sleep-0.036
Sweet-0.035
 moment-0.035
Token and
Token ID290
Feature activation-3.63e-02

Pos logit contributions
ay+0.059
issors+0.054
rac+0.054
ong+0.053
ars+0.049
Neg logit contributions
 moment-0.063
 ending-0.061
 polar-0.061
Sleep-0.060
 mistake-0.060
Token toys
Token ID14958
Feature activation+1.38e-01

Pos logit contributions
Sleep+0.001
Sweet+0.001
 mistake+0.001
Kids+0.001
 ending+0.001
Neg logit contributions
ay-0.001
 around-0.001
ong-0.001
rac-0.001
bs-0.001
Token,
Token ID11
Feature activation+2.14e-01

Pos logit contributions
ay+0.004
rac+0.004
ong+0.004
issors+0.004
ars+0.003
Neg logit contributions
 ending-0.005
 moment-0.005
Sleep-0.005
 polar-0.005
 mistake-0.005
Token all
Token ID477
Feature activation+9.81e-01

Pos logit contributions
ay+0.007
 around+0.006
ong+0.006
rac+0.006
bs+0.006
Neg logit contributions
Sleep-0.008
Sweet-0.008
 ending-0.007
 mistake-0.007
Kids-0.007
Token sorts
Token ID10524
Feature activation+7.27e+00

Pos logit contributions
ay+0.029
ong+0.028
rac+0.028
issors+0.027
ars+0.026
Neg logit contributions
 polar-0.036
 ending-0.036
 moment-0.035
Sleep-0.035
 mistake-0.034
Token of
Token ID286
Feature activation-2.04e+00

Pos logit contributions
rac+0.243
issors+0.241
ong+0.229
ay+0.229
itching+0.211
Neg logit contributions
 ending-0.232
 forgiveness-0.231
Sleep-0.228
 polar-0.228
Sweet-0.221
Token surprises
Token ID24072
Feature activation-6.39e-01

Pos logit contributions
Sleep+0.068
Sweet+0.068
 polar+0.067
 ending+0.067
 mistake+0.065
Neg logit contributions
ay-0.068
ong-0.064
 around-0.062
rac-0.062
issors-0.059
Token were
Token ID547
Feature activation-1.09e+00

Pos logit contributions
Sleep+0.023
 polar+0.023
 ending+0.023
 moment+0.023
Sweet+0.023
Neg logit contributions
ay-0.019
ong-0.018
rac-0.018
issors-0.017
ars-0.016
Token waiting
Token ID4953
Feature activation-1.41e+00

Pos logit contributions
Sleep+0.038
Sweet+0.038
 polar+0.038
 ending+0.037
 mistake+0.037
Neg logit contributions
ay-0.035
ong-0.033
rac-0.031
 around-0.031
issors-0.030
Token for
Token ID329
Feature activation+2.52e+00

Pos logit contributions
 ending+0.054
 polar+0.054
Sleep+0.054
 mistake+0.053
 moment+0.053
Neg logit contributions
ay-0.039
ong-0.037
rac-0.037
issors-0.035
bs-0.033
Token a
Token ID257
Feature activation-9.43e-02

Pos logit contributions
 around+0.047
ay+0.046
 at+0.042
ong+0.042
 high+0.040
Neg logit contributions
 polar-0.078
Kids-0.073
Sleep-0.072
Sweet-0.072
 ending-0.072
Token strange
Token ID6283
Feature activation-3.59e-01

Pos logit contributions
Sleep+0.004
Sweet+0.004
Kids+0.004
 forgiveness+0.004
 ending+0.004
Neg logit contributions
ay-0.003
ong-0.002
 around-0.002
 high-0.002
rac-0.002
Token vendor
Token ID18371
Feature activation-1.35e+00

Pos logit contributions
Sweet+0.013
Sleep+0.013
Kids+0.012
Are+0.012
 forgiveness+0.011
Neg logit contributions
ay-0.012
 around-0.012
ong-0.011
 at-0.010
 high-0.010
Token selling
Token ID6301
Feature activation-3.24e+00

Pos logit contributions
Sleep+0.052
Sweet+0.052
 ending+0.051
 polar+0.051
 mistake+0.050
Neg logit contributions
ay-0.038
ong-0.036
 around-0.036
rac-0.033
issors-0.032
Token all
Token ID477
Feature activation+1.02e+00

Pos logit contributions
 polar+0.084
Sleep+0.082
Sweet+0.081
 mistake+0.081
 ending+0.080
Neg logit contributions
ay-0.131
ong-0.126
rac-0.124
issors-0.120
 around-0.119
Token sorts
Token ID10524
Feature activation+7.27e+00

Pos logit contributions
ay+0.031
ong+0.031
rac+0.031
ars+0.030
issors+0.029
Neg logit contributions
 moment-0.035
Sleep-0.035
 polar-0.035
Sweet-0.034
 ending-0.034
Token of
Token ID286
Feature activation-2.10e+00

Pos logit contributions
rac+0.254
ay+0.234
ong+0.230
issors+0.229
itching+0.222
Neg logit contributions
 forgiveness-0.226
Sleep-0.216
Sweet-0.215
 pand-0.213
 ending-0.211
Token interesting
Token ID3499
Feature activation+1.33e+00

Pos logit contributions
 polar+0.061
Sweet+0.060
Sleep+0.060
 mistake+0.060
 ending+0.059
Neg logit contributions
ay-0.079
rac-0.075
ong-0.075
issors-0.071
 around-0.070
Token things
Token ID1243
Feature activation+7.89e-01

Pos logit contributions
ay+0.047
rac+0.045
ong+0.045
issors+0.042
 around+0.041
Neg logit contributions
 polar-0.041
Sweet-0.041
Sleep-0.041
 ending-0.040
 mistake-0.040
Token.
Token ID13
Feature activation-5.28e-01

Pos logit contributions
ay+0.024
rac+0.022
ong+0.022
issors+0.020
ars+0.020
Neg logit contributions
Sleep-0.029
 ending-0.029
 polar-0.029
 moment-0.028
Sweet-0.028
Token She
Token ID1375
Feature activation-4.50e-02

Pos logit contributions
Sleep+0.015
Sweet+0.015
 polar+0.014
 ending+0.014
 moment+0.014
Neg logit contributions
ay-0.020
ong-0.020
rac-0.019
issors-0.018
ars-0.018
Token!
Token ID0
Feature activation+1.15e+00

Pos logit contributions
ay+0.153
rac+0.141
ong+0.139
issors+0.131
ars+0.128
Neg logit contributions
Sleep-0.187
 polar-0.187
 ending-0.185
 mistake-0.181
 moment-0.180
Token He
Token ID679
Feature activation+2.22e-01

Pos logit contributions
ay+0.034
ong+0.032
 around+0.031
rac+0.031
issors+0.029
Neg logit contributions
Sleep-0.043
Sweet-0.043
 polar-0.043
 mistake-0.043
 ending-0.042
Token would
Token ID561
Feature activation+1.24e+00

Pos logit contributions
ay+0.008
ong+0.007
rac+0.007
 around+0.007
bs+0.007
Neg logit contributions
Sleep-0.007
Sweet-0.007
 polar-0.007
 ending-0.007
 mistake-0.007
Token make
Token ID787
Feature activation+1.78e-01

Pos logit contributions
ay+0.050
ong+0.047
rac+0.046
issors+0.044
ors+0.044
Neg logit contributions
 polar-0.034
Sleep-0.033
 ending-0.032
 mistake-0.032
 moment-0.032
Token all
Token ID477
Feature activation+9.64e-01

Pos logit contributions
ay+0.006
rac+0.006
issors+0.006
ong+0.006
bs+0.006
Neg logit contributions
 polar-0.006
 mistake-0.005
Sweet-0.005
 Bird-0.005
 ending-0.005
Token sorts
Token ID10524
Feature activation+7.27e+00

Pos logit contributions
ay+0.029
ong+0.027
rac+0.027
issors+0.026
ars+0.025
Neg logit contributions
 polar-0.036
Sleep-0.035
Sweet-0.035
 ending-0.034
 moment-0.034
Token of
Token ID286
Feature activation-1.99e+00

Pos logit contributions
rac+0.264
issors+0.256
ay+0.241
ong+0.231
ables+0.225
Neg logit contributions
 forgiveness-0.224
 polar-0.213
Sleep-0.211
Sweet-0.205
 ending-0.201
Token shapes
Token ID15268
Feature activation+2.71e+00

Pos logit contributions
 polar+0.058
 mistake+0.058
Sweet+0.057
Sleep+0.056
 moment+0.056
Neg logit contributions
ay-0.076
rac-0.075
issors-0.071
ong-0.070
ors-0.066
Token in
Token ID287
Feature activation-4.10e-01

Pos logit contributions
ay+0.078
rac+0.074
ong+0.073
issors+0.071
bs+0.066
Neg logit contributions
 polar-0.102
 ending-0.100
Sleep-0.100
 moment-0.098
Sweet-0.098
Token the
Token ID262
Feature activation+2.96e-01

Pos logit contributions
 polar+0.015
 mistake+0.014
 ending+0.014
Sleep+0.014
 moment+0.014
Neg logit contributions
ay-0.013
ong-0.012
rac-0.012
issors-0.011
bs-0.011
Token air
Token ID1633
Feature activation+2.79e+00

Pos logit contributions
rac+0.012
ong+0.012
ors+0.012
bs+0.011
issors+0.011
Neg logit contributions
 moment-0.007
 tunnel-0.007
Sleep-0.007
 ending-0.007
Sweet-0.007
Token he
Token ID339
Feature activation+1.49e+00

Pos logit contributions
ay+0.016
ong+0.015
rac+0.015
issors+0.014
 around+0.014
Neg logit contributions
 polar-0.018
Sleep-0.018
 ending-0.017
Sweet-0.017
 mistake-0.017
Token was
Token ID373
Feature activation-1.59e-01

Pos logit contributions
ay+0.063
ong+0.060
issors+0.059
rac+0.059
bs+0.056
Neg logit contributions
 polar-0.037
 ending-0.036
Sleep-0.036
 mistake-0.036
Sweet-0.035
Token acting
Token ID7205
Feature activation-1.25e+00

Pos logit contributions
 polar+0.005
Sleep+0.005
 ending+0.005
Sweet+0.005
 mistake+0.005
Neg logit contributions
ay-0.006
ong-0.005
rac-0.005
issors-0.005
bs-0.005
Token out
Token ID503
Feature activation+2.68e+00

Pos logit contributions
 ending+0.044
 moment+0.043
 mistake+0.043
 polar+0.042
Sleep+0.042
Neg logit contributions
ay-0.039
rac-0.038
issors-0.038
ong-0.036
ors-0.035
Token all
Token ID477
Feature activation+1.10e+00

Pos logit contributions
ay+0.075
ong+0.071
rac+0.070
issors+0.068
ars+0.064
Neg logit contributions
 polar-0.104
Sleep-0.103
 ending-0.103
 mistake-0.102
Sweet-0.101
Token sorts
Token ID10524
Feature activation+7.27e+00

Pos logit contributions
ay+0.032
ong+0.030
rac+0.030
issors+0.029
bs+0.027
Neg logit contributions
Sleep-0.041
 polar-0.041
 ending-0.041
Sweet-0.040
 moment-0.040
Token of
Token ID286
Feature activation-1.88e+00

Pos logit contributions
rac+0.272
issors+0.263
ay+0.245
ong+0.242
itching+0.229
Neg logit contributions
 forgiveness-0.216
 ending-0.213
Sleep-0.212
 again-0.209
 polar-0.208
Token adventures
Token ID17545
Feature activation+6.45e-01

Pos logit contributions
 polar+0.059
Sleep+0.058
 ending+0.057
 mistake+0.057
Sweet+0.057
Neg logit contributions
ay-0.067
rac-0.064
ong-0.064
issors-0.061
 around-0.059
Token.
Token ID13
Feature activation-8.56e-02

Pos logit contributions
ay+0.020
rac+0.020
ong+0.019
issors+0.019
bs+0.018
Neg logit contributions
 polar-0.022
 ending-0.022
 moment-0.022
Sleep-0.022
 mistake-0.021
Token Every
Token ID3887
Feature activation+1.29e+00

Pos logit contributions
Sleep+0.003
 polar+0.003
Sweet+0.003
 ending+0.003
 mistake+0.003
Neg logit contributions
ay-0.003
ong-0.003
rac-0.003
 around-0.003
issors-0.002
Token day
Token ID1110
Feature activation+4.22e-01

Pos logit contributions
ay+0.046
 around+0.043
ong+0.041
rac+0.040
ars+0.038
Neg logit contributions
Sweet-0.042
 polar-0.041
 department-0.041
Sleep-0.041
Kids-0.039
Token the
Token ID262
Feature activation+1.18e-01

Pos logit contributions
 mistake+0.055
Sleep+0.054
 polar+0.053
Sweet+0.053
 moment+0.053
Neg logit contributions
ay-0.048
ong-0.046
rac-0.045
issors-0.043
ars-0.042
Token village
Token ID7404
Feature activation-1.84e+00

Pos logit contributions
ay+0.004
 around+0.004
ong+0.004
ars+0.004
 at+0.004
Neg logit contributions
 polar-0.004
Sleep-0.004
Kids-0.004
Sweet-0.004
 department-0.004
Token back
Token ID736
Feature activation-1.94e+00

Pos logit contributions
Sleep+0.068
 polar+0.067
Sweet+0.067
 ending+0.067
 mistake+0.066
Neg logit contributions
ay-0.055
ong-0.051
rac-0.050
 around-0.048
issors-0.047
Token to
Token ID284
Feature activation-2.74e-01

Pos logit contributions
Sleep+0.076
 polar+0.075
Sweet+0.075
 ending+0.074
 mistake+0.073
Neg logit contributions
ay-0.054
ong-0.051
rac-0.049
 around-0.048
issors-0.046
Token its
Token ID663
Feature activation+1.51e-01

Pos logit contributions
Sleep+0.010
Sweet+0.010
 polar+0.010
 ending+0.009
Kids+0.009
Neg logit contributions
ay-0.009
ong-0.008
rac-0.008
 around-0.008
issors-0.007
Token former
Token ID1966
Feature activation-7.31e+00

Pos logit contributions
ay+0.006
 around+0.006
ong+0.006
rac+0.005
bs+0.005
Neg logit contributions
Kids-0.004
Sleep-0.004
Sweet-0.004
 polar-0.004
Are-0.004
Token glory
Token ID13476
Feature activation+1.92e+00

Pos logit contributions
 mistake+0.189
 ending+0.184
 former+0.183
 polar+0.175
Sleep+0.173
Neg logit contributions
ay-0.304
ong-0.297
rac-0.286
issors-0.281
bs-0.279
Token!"
Token ID2474
Feature activation+1.46e-01

Pos logit contributions
ay+0.058
ong+0.055
rac+0.053
issors+0.052
 around+0.050
Neg logit contributions
Sleep-0.069
 polar-0.068
Sweet-0.068
 ending-0.068
 mistake-0.067
Token
Token ID220
Feature activation+7.95e-01

Pos logit contributions
ay+0.005
ong+0.004
rac+0.004
 around+0.004
issors+0.004
Neg logit contributions
Sleep-0.005
 ending-0.005
 polar-0.005
Sweet-0.005
 mistake-0.005
Token
Token ID198
Feature activation+1.26e-01

Pos logit contributions
ay+0.032
ong+0.030
rac+0.030
 around+0.029
issors+0.029
Neg logit contributions
Sleep-0.021
Sweet-0.021
 polar-0.021
 mistake-0.020
 ending-0.020
Token
Token ID198
Feature activation+6.07e-02

Pos logit contributions
ay+0.004
ong+0.004
rac+0.004
 around+0.004
ars+0.004
Neg logit contributions
 ending-0.005
 polar-0.004
Sleep-0.004
 mistake-0.004
 funeral-0.004
Token the
Token ID262
Feature activation+6.90e-03

Pos logit contributions
 polar+0.055
 mistake+0.053
Sleep+0.053
 moment+0.052
 ending+0.052
Neg logit contributions
ay-0.050
ong-0.048
rac-0.047
issors-0.045
bs-0.044
Token tree
Token ID5509
Feature activation-6.38e-01

Pos logit contributions
ay+0.000
 around+0.000
ong+0.000
ars+0.000
rac+0.000
Neg logit contributions
Kids-0.000
Sleep-0.000
 polar-0.000
Sweet-0.000
 department-0.000
Token to
Token ID284
Feature activation-2.94e-01

Pos logit contributions
Sleep+0.024
 polar+0.024
 ending+0.024
Sweet+0.024
 mistake+0.024
Neg logit contributions
ay-0.018
ong-0.017
rac-0.016
issors-0.015
 around-0.015
Token its
Token ID663
Feature activation-5.34e-02

Pos logit contributions
Sleep+0.011
Sweet+0.011
 polar+0.011
 ending+0.011
Kids+0.010
Neg logit contributions
ay-0.009
ong-0.008
 around-0.008
rac-0.008
issors-0.008
Token once
Token ID1752
Feature activation-1.36e+00

Pos logit contributions
Sleep+0.002
Sweet+0.002
Kids+0.002
 polar+0.001
 ending+0.001
Neg logit contributions
ay-0.002
ong-0.002
 around-0.002
rac-0.002
issors-0.002
Token former
Token ID1966
Feature activation-7.21e+00

Pos logit contributions
Kids+0.048
Sweet+0.046
Sleep+0.045
 polar+0.045
 divorce+0.044
Neg logit contributions
 around-0.046
ay-0.046
ong-0.042
 at-0.040
rac-0.040
Token beauty
Token ID8737
Feature activation+1.23e+00

Pos logit contributions
 former+0.188
 mistake+0.180
 ending+0.177
 moment+0.158
 moral+0.158
Neg logit contributions
ay-0.309
ong-0.306
issors-0.297
rac-0.296
bs-0.292
Token.
Token ID13
Feature activation-5.87e-01

Pos logit contributions
ay+0.035
rac+0.034
ong+0.033
issors+0.033
bs+0.030
Neg logit contributions
Sleep-0.047
 ending-0.046
 polar-0.046
 moment-0.046
Sweet-0.045
Token He
Token ID679
Feature activation+2.46e-01

Pos logit contributions
Sleep+0.022
 mistake+0.022
 ending+0.022
 polar+0.022
Sweet+0.022
Neg logit contributions
ay-0.018
ong-0.015
rac-0.015
 around-0.015
issors-0.014
Token was
Token ID373
Feature activation-4.27e-01

Pos logit contributions
ay+0.010
ong+0.009
rac+0.009
 around+0.009
bs+0.009
Neg logit contributions
Sleep-0.007
 polar-0.007
Sweet-0.007
 ending-0.007
 mistake-0.006
Token happy
Token ID3772
Feature activation-6.99e-02

Pos logit contributions
 polar+0.015
Sleep+0.015
 ending+0.015
Sweet+0.015
 mistake+0.014
Neg logit contributions
ay-0.014
ong-0.013
rac-0.013
issors-0.012
ors-0.012
Token back
Token ID736
Feature activation-1.93e+00

Pos logit contributions
Sleep+0.001
 polar+0.001
 ending+0.001
Sweet+0.001
 mistake+0.001
Neg logit contributions
ay-0.001
ong-0.001
rac-0.001
issors-0.001
ars-0.001
Token the
Token ID262
Feature activation+8.50e-02

Pos logit contributions
Sleep+0.073
 ending+0.073
 polar+0.072
Sweet+0.072
 mistake+0.071
Neg logit contributions
ay-0.057
 around-0.053
ong-0.052
rac-0.051
bs-0.049
Token village
Token ID7404
Feature activation-1.74e+00

Pos logit contributions
ay+0.003
 around+0.003
ars+0.002
ong+0.002
 high+0.002
Neg logit contributions
 polar-0.003
Sleep-0.003
Sweet-0.003
Kids-0.003
fly-0.003
Token to
Token ID284
Feature activation-2.58e-01

Pos logit contributions
Sleep+0.067
 polar+0.066
Sweet+0.066
 ending+0.066
 mistake+0.065
Neg logit contributions
ay-0.050
ong-0.046
rac-0.045
 around-0.043
issors-0.042
Token its
Token ID663
Feature activation+8.79e-02

Pos logit contributions
Sleep+0.010
Sweet+0.010
 polar+0.010
 ending+0.009
Kids+0.009
Neg logit contributions
ay-0.007
ong-0.007
rac-0.007
 around-0.007
issors-0.006
Token former
Token ID1966
Feature activation-7.20e+00

Pos logit contributions
ay+0.003
ong+0.003
 around+0.003
rac+0.003
issors+0.003
Neg logit contributions
Sleep-0.003
Sweet-0.002
Kids-0.002
 polar-0.002
 ending-0.002
Token state
Token ID1181
Feature activation-7.17e-01

Pos logit contributions
 mistake+0.190
 ending+0.188
 former+0.185
 polar+0.180
Sleep+0.178
Neg logit contributions
ay-0.293
ong-0.288
rac-0.276
issors-0.272
bs-0.270
Token.
Token ID13
Feature activation-4.00e-01

Pos logit contributions
Sleep+0.027
 ending+0.027
 polar+0.026
 mistake+0.026
Sweet+0.026
Neg logit contributions
ay-0.021
ong-0.020
rac-0.019
issors-0.019
bs-0.018
Token With
Token ID2080
Feature activation+2.56e-01

Pos logit contributions
 mistake+0.016
 polar+0.016
 ending+0.016
Sleep+0.015
 divorce+0.015
Neg logit contributions
ay-0.012
rac-0.010
 around-0.010
ong-0.010
issors-0.009
Token the
Token ID262
Feature activation+7.21e-02

Pos logit contributions
ong+0.010
ay+0.009
ors+0.009
issors+0.009
rac+0.009
Neg logit contributions
 ending-0.008
 polar-0.008
Sleep-0.007
 moral-0.007
 forgiveness-0.007
Token help
Token ID1037
Feature activation-8.78e-01

Pos logit contributions
ay+0.002
ong+0.002
rac+0.002
 around+0.002
ars+0.002
Neg logit contributions
Sleep-0.002
Sweet-0.002
 polar-0.002
Kids-0.002
 ending-0.002
Token to
Token ID284
Feature activation-2.51e-01

Pos logit contributions
 moment+0.051
Sleep+0.050
 ending+0.047
 department+0.047
 mistake+0.047
Neg logit contributions
ay-0.048
ong-0.047
rac-0.046
itching-0.045
iddling-0.044
Token be
Token ID307
Feature activation-2.18e+00

Pos logit contributions
Sweet+0.008
Sleep+0.008
 polar+0.008
 ending+0.008
Kids+0.008
Neg logit contributions
ay-0.009
ong-0.008
rac-0.008
 around-0.008
issors-0.008
Token restored
Token ID15032
Feature activation-2.81e-01

Pos logit contributions
Sleep+0.071
 polar+0.071
 mistake+0.070
 ending+0.069
Sweet+0.068
Neg logit contributions
ay-0.076
ong-0.071
rac-0.069
issors-0.066
 around-0.064
Token to
Token ID284
Feature activation-2.63e-01

Pos logit contributions
Sleep+0.009
 moment+0.009
 mistake+0.009
 polar+0.009
 ending+0.009
Neg logit contributions
ay-0.009
ong-0.009
rac-0.009
issors-0.008
ars-0.008
Token its
Token ID663
Feature activation+1.16e-01

Pos logit contributions
Sweet+0.010
Sleep+0.010
Kids+0.010
 polar+0.009
 department+0.009
Neg logit contributions
ay-0.008
ong-0.008
 around-0.007
rac-0.007
issors-0.007
Token former
Token ID1966
Feature activation-7.20e+00

Pos logit contributions
ay+0.004
 around+0.004
ong+0.004
rac+0.004
 at+0.004
Neg logit contributions
Kids-0.003
Sleep-0.003
Sweet-0.003
 polar-0.003
Are-0.003
Token glory
Token ID13476
Feature activation+1.94e+00

Pos logit contributions
 former+0.187
 mistake+0.185
 ending+0.179
 moral+0.164
 moment+0.162
Neg logit contributions
ay-0.306
ong-0.304
rac-0.290
bs-0.287
issors-0.283
Token."
Token ID526
Feature activation-4.75e-01

Pos logit contributions
ay+0.064
ong+0.060
rac+0.059
issors+0.057
bs+0.055
Neg logit contributions
Sleep-0.065
 moment-0.063
 polar-0.063
Sweet-0.063
 mistake-0.062
Token
Token ID220
Feature activation+9.82e-01

Pos logit contributions
Sleep+0.017
 ending+0.016
 polar+0.016
Sweet+0.016
 mistake+0.016
Neg logit contributions
ay-0.016
ong-0.014
 around-0.014
rac-0.014
bs-0.013
Token
Token ID198
Feature activation+1.52e-01

Pos logit contributions
ay+0.040
ong+0.039
rac+0.038
issors+0.037
 around+0.036
Neg logit contributions
Sleep-0.025
Sweet-0.025
 polar-0.024
 mistake-0.024
 moment-0.023
Token
Token ID198
Feature activation+8.21e-02

Pos logit contributions
ay+0.005
ong+0.005
rac+0.005
 around+0.005
issors+0.005
Neg logit contributions
Sleep-0.005
 ending-0.005
 polar-0.005
Sweet-0.005
 mistake-0.005
Token,
Token ID11
Feature activation+3.59e-01

Pos logit contributions
Sleep+0.055
Sweet+0.055
 polar+0.054
 ending+0.054
Kids+0.053
Neg logit contributions
ay-0.033
ong-0.031
 around-0.029
rac-0.029
issors-0.027
Token leaving
Token ID4305
Feature activation-1.02e+00

Pos logit contributions
ay+0.010
 around+0.010
ong+0.010
rac+0.009
bs+0.009
Neg logit contributions
Sweet-0.014
Sleep-0.014
Kids-0.013
 polar-0.013
 ending-0.013
Token it
Token ID340
Feature activation-1.91e-02

Pos logit contributions
Sleep+0.038
Sweet+0.038
 polar+0.038
 ending+0.037
 mistake+0.037
Neg logit contributions
ay-0.030
ong-0.028
rac-0.027
 around-0.027
issors-0.026
Token to
Token ID284
Feature activation-1.60e-01

Pos logit contributions
Sweet+0.001
Kids+0.001
Sleep+0.001
 polar+0.001
 ending+0.001
Neg logit contributions
 around-0.001
ay-0.001
ong-0.001
rac-0.001
bs-0.000
Token its
Token ID663
Feature activation+2.61e-01

Pos logit contributions
Sweet+0.007
Kids+0.007
Sleep+0.007
 department+0.006
 Jenkins+0.006
Neg logit contributions
 around-0.004
 high-0.004
ong-0.004
ay-0.003
 at-0.003
Token former
Token ID1966
Feature activation-7.18e+00

Pos logit contributions
 around+0.009
ay+0.009
ong+0.009
 at+0.008
rac+0.008
Neg logit contributions
Kids-0.008
Sweet-0.008
Sleep-0.008
Are-0.007
 divorce-0.007
Token state
Token ID1181
Feature activation-5.98e-01

Pos logit contributions
 mistake+0.195
 ending+0.193
 polar+0.192
 former+0.188
Sleep+0.183
Neg logit contributions
ay-0.286
ong-0.276
rac-0.269
issors-0.262
bs-0.260
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
Sleep+0.024
Sweet+0.024
 polar+0.024
 ending+0.024
 mistake+0.024
Neg logit contributions
ay-0.016
ong-0.015
rac-0.014
 around-0.014
issors-0.013
Token
Token ID220
Feature activation+9.60e-01

Pos logit contributions
 ending+0.008
 mistake+0.008
 polar+0.008
Sleep+0.008
Sweet+0.007
Neg logit contributions
ay-0.006
rac-0.005
 around-0.005
ong-0.005
issors-0.005
Token
Token ID198
Feature activation+2.03e-01

Pos logit contributions
ay+0.037
ong+0.035
rac+0.034
 around+0.033
issors+0.033
Neg logit contributions
Sleep-0.027
Sweet-0.027
 polar-0.027
 ending-0.026
 mistake-0.026
Token
Token ID198
Feature activation+1.22e-01

Pos logit contributions
ay+0.007
ong+0.006
rac+0.006
 around+0.006
ars+0.006
Neg logit contributions
 ending-0.007
 polar-0.007
Sleep-0.007
 mistake-0.007
Sweet-0.006
Token aunt
Token ID25949
Feature activation+2.65e-01

Pos logit contributions
ay+0.038
ong+0.033
 around+0.033
rac+0.032
bs+0.031
Neg logit contributions
Sleep-0.027
Sweet-0.025
Kids-0.024
 polar-0.024
Are-0.024
Token told
Token ID1297
Feature activation-1.22e+00

Pos logit contributions
ay+0.007
 around+0.007
ong+0.007
 at+0.006
bs+0.006
Neg logit contributions
Sleep-0.011
 former-0.011
Sweet-0.011
 ending-0.011
 mistake-0.010
Token Lucy
Token ID22162
Feature activation-7.73e-01

Pos logit contributions
 polar+0.057
Sleep+0.056
Sweet+0.056
 former+0.055
 ending+0.055
Neg logit contributions
ay-0.025
 around-0.024
ong-0.023
rac-0.021
bs-0.019
Token,
Token ID11
Feature activation+1.68e-01

Pos logit contributions
 polar+0.036
Sleep+0.035
Sweet+0.035
Kids+0.034
 former+0.034
Neg logit contributions
 around-0.016
ay-0.016
ong-0.015
bs-0.014
rac-0.014
Token "
Token ID366
Feature activation+1.29e+00

Pos logit contributions
 around+0.004
ay+0.004
rac+0.004
 at+0.004
ong+0.004
Neg logit contributions
 polar-0.007
 former-0.007
 ending-0.007
Sleep-0.007
 mistake-0.007
TokenSweet
Token ID36087
Feature activation-7.16e+00

Pos logit contributions
 around+0.040
ay+0.039
rac+0.039
ized+0.037
bs+0.036
Neg logit contributions
 polar-0.048
 ending-0.046
 mistake-0.043
 ig-0.043
 island-0.043
Tokenheart
Token ID11499
Feature activation+2.33e+00

Pos logit contributions
Sleep+0.280
 department+0.280
Are+0.279
 charity+0.277
Sweet+0.275
Neg logit contributions
ay-0.197
 around-0.176
 at-0.175
--0.174
ors-0.164
Token,
Token ID11
Feature activation+2.14e-01

Pos logit contributions
ay+0.052
ong+0.048
rac+0.046
 around+0.044
issors+0.043
Neg logit contributions
Sleep-0.103
 polar-0.103
Sweet-0.102
 ending-0.102
 mistake-0.101
Token you
Token ID345
Feature activation-5.77e-01

Pos logit contributions
 around+0.006
ay+0.006
 at+0.006
ong+0.005
rac+0.005
Neg logit contributions
 polar-0.008
Sweet-0.008
 former-0.008
Sleep-0.008
Kids-0.008
Token know
Token ID760
Feature activation+7.15e-01

Pos logit contributions
Sweet+0.020
Sleep+0.020
 polar+0.019
 ending+0.019
 moment+0.019
Neg logit contributions
ay-0.019
ong-0.018
 around-0.017
rac-0.017
bs-0.016
Token that
Token ID326
Feature activation-1.21e+00

Pos logit contributions
ay+0.021
ong+0.021
 around+0.020
rac+0.020
ors+0.018
Neg logit contributions
 polar-0.027
Sweet-0.026
Sleep-0.026
 ending-0.026
Kids-0.025
Token very
Token ID845
Feature activation+8.29e-01

Pos logit contributions
 polar+0.007
Sleep+0.007
 ending+0.007
Sweet+0.007
 mistake+0.007
Neg logit contributions
ay-0.007
ong-0.007
rac-0.007
issors-0.007
ors-0.006
Token tired
Token ID10032
Feature activation+1.22e+00

Pos logit contributions
ay+0.033
ors+0.030
ong+0.029
rac+0.029
issors+0.029
Neg logit contributions
 polar-0.026
 ending-0.025
 mistake-0.025
Sleep-0.025
 moment-0.024
Token.
Token ID13
Feature activation-5.80e-01

Pos logit contributions
ay+0.033
ong+0.031
rac+0.030
 around+0.028
issors+0.028
Neg logit contributions
Sleep-0.049
 polar-0.048
Sweet-0.048
 ending-0.048
 mistake-0.047
Token The
Token ID383
Feature activation-1.66e+00

Pos logit contributions
Sleep+0.021
 polar+0.021
Sweet+0.021
 ending+0.021
 mistake+0.020
Neg logit contributions
ay-0.018
ong-0.017
rac-0.016
 around-0.016
issors-0.016
Token ash
Token ID12530
Feature activation-5.11e+00

Pos logit contributions
fly+0.070
Sweet+0.067
 former+0.066
Sleep+0.064
days+0.064
Neg logit contributions
ay-0.044
 around-0.042
ong-0.040
 high-0.038
 at-0.037
Tokentr
Token ID2213
Feature activation-7.15e+00

Pos logit contributions
Sleep+0.139
Sweet+0.137
 polar+0.137
 ending+0.132
 mistake+0.132
Neg logit contributions
ay-0.204
ong-0.194
rac-0.190
 around-0.188
issors-0.181
Tokenay
Token ID323
Feature activation+4.62e+00

Pos logit contributions
 department+0.377
Sweet+0.376
tr+0.375
 gen+0.366
 polar+0.364
Neg logit contributions
ars-0.050
issors-0.049
rac-0.049
ong-0.047
 around-0.043
Token watched
Token ID7342
Feature activation-1.66e+00

Pos logit contributions
ay+0.162
 around+0.161
ong+0.154
led+0.148
rac+0.147
Neg logit contributions
 charity-0.150
Sweet-0.149
Sleep-0.147
 mistake-0.146
 former-0.145
Token as
Token ID355
Feature activation+4.69e+00

Pos logit contributions
 polar+0.063
 ending+0.063
Sleep+0.061
 mistake+0.061
 moment+0.060
Neg logit contributions
ay-0.047
rac-0.045
issors-0.044
ars-0.043
bs-0.043
Token the
Token ID262
Feature activation+1.70e-01

Pos logit contributions
ay+0.118
ong+0.113
 around+0.107
rac+0.105
bs+0.097
Neg logit contributions
Sleep-0.195
Sweet-0.193
 polar-0.191
 ending-0.189
Kids-0.188
Token little
Token ID1310
Feature activation-2.30e+00

Pos logit contributions
ay+0.005
ong+0.004
 past+0.004
 at+0.004
 around+0.004
Neg logit contributions
 sometime-0.007
Sleep-0.007
 former-0.007
fly-0.007
|-0.007
Token.
Token ID13
Feature activation-5.59e-01

Pos logit contributions
ay+0.012
ong+0.011
rac+0.011
 around+0.010
issors+0.010
Neg logit contributions
Sleep-0.019
 polar-0.019
Sweet-0.019
 ending-0.019
 mistake-0.018
Token
Token ID198
Feature activation-3.31e-02

Pos logit contributions
 mistake+0.022
 ending+0.022
 polar+0.022
Sleep+0.022
Sweet+0.022
Neg logit contributions
ay-0.016
ong-0.014
 around-0.014
rac-0.014
issors-0.013
Token
Token ID198
Feature activation-1.12e-01

Pos logit contributions
Sleep+0.001
Sweet+0.001
 polar+0.001
 moment+0.001
Kids+0.001
Neg logit contributions
ay-0.001
ong-0.001
rac-0.001
issors-0.001
 around-0.001
TokenThe
Token ID464
Feature activation-1.84e+00

Pos logit contributions
Sleep+0.004
 polar+0.004
Sweet+0.004
 ending+0.004
 mistake+0.004
Neg logit contributions
ay-0.004
ong-0.004
rac-0.004
 around-0.003
issors-0.003
Token ash
Token ID12530
Feature activation-5.14e+00

Pos logit contributions
 sometime+0.082
burn+0.081
 former+0.081
Sleep+0.081
fly+0.080
Neg logit contributions
 at-0.039
 past-0.039
ay-0.038
 around-0.037
 high-0.036
Tokentr
Token ID2213
Feature activation-7.15e+00

Pos logit contributions
Sleep+0.076
Sweet+0.074
 polar+0.073
 mistake+0.069
 ending+0.067
Neg logit contributions
ay-0.271
ong-0.261
 around-0.256
rac-0.256
issors-0.246
Tokenay
Token ID323
Feature activation+4.57e+00

Pos logit contributions
 department+0.397
Sweet+0.395
tr+0.386
 gen+0.386
 polar+0.386
Neg logit contributions
ong-0.039
issors-0.039
rac-0.037
ars-0.036
 around-0.035
Token was
Token ID373
Feature activation-3.62e-01

Pos logit contributions
 around+0.148
ay+0.147
ong+0.143
led+0.139
 at+0.137
Neg logit contributions
 charity-0.164
Sleep-0.161
Sweet-0.161
 former-0.159
 mistake-0.156
Token ready
Token ID3492
Feature activation+1.21e+00

Pos logit contributions
 polar+0.012
Sleep+0.012
 ending+0.012
 mistake+0.011
Sweet+0.011
Neg logit contributions
ay-0.013
ong-0.012
rac-0.012
issors-0.011
bs-0.011
Token to
Token ID284
Feature activation-3.80e-01

Pos logit contributions
ay+0.036
rac+0.034
ong+0.034
issors+0.033
ars+0.032
Neg logit contributions
 ending-0.046
 moment-0.045
Sleep-0.044
 mistake-0.044
 polar-0.043
Token provide
Token ID2148
Feature activation-2.40e-01

Pos logit contributions
Sweet+0.013
Sleep+0.012
Kids+0.012
 ending+0.012
 polar+0.012
Neg logit contributions
ay-0.013
ong-0.013
rac-0.012
 around-0.012
ars-0.011
Token backyard
Token ID24296
Feature activation-1.97e-01

Pos logit contributions
ay+0.012
ong+0.011
rac+0.011
 around+0.011
issors+0.010
Neg logit contributions
Sleep-0.006
Sweet-0.006
 polar-0.006
 ending-0.006
 mistake-0.006
Token there
Token ID612
Feature activation-1.15e-01

Pos logit contributions
Sleep+0.009
Sweet+0.009
 polar+0.009
Kids+0.009
 former+0.009
Neg logit contributions
ay-0.004
 around-0.004
ong-0.004
rac-0.004
 at-0.003
Token was
Token ID373
Feature activation-2.41e-01

Pos logit contributions
Sweet+0.003
Sleep+0.003
 polar+0.003
 mistake+0.003
 divorce+0.003
Neg logit contributions
ay-0.005
ong-0.004
 around-0.004
rac-0.004
 at-0.004
Token an
Token ID281
Feature activation+1.02e-01

Pos logit contributions
 mistake+0.011
Kids+0.011
fly+0.011
Sleep+0.011
 forgiveness+0.010
Neg logit contributions
 around-0.005
 high-0.005
ay-0.005
 at-0.004
ong-0.004
Token ash
Token ID12530
Feature activation-5.05e+00

Pos logit contributions
ay+0.003
ong+0.003
 around+0.003
rac+0.003
issors+0.003
Neg logit contributions
Sleep-0.004
Sweet-0.004
 moment-0.003
Kids-0.003
 ending-0.003
Tokentr
Token ID2213
Feature activation-7.13e+00

Pos logit contributions
Sleep+0.051
 polar+0.051
 ending+0.050
Sweet+0.049
 mistake+0.046
Neg logit contributions
ay-0.285
ong-0.275
rac-0.272
 around-0.266
issors-0.264
Tokenay
Token ID323
Feature activation+4.64e+00

Pos logit contributions
tr+0.378
 department+0.370
 polar+0.361
 gen+0.360
 tunnel+0.358
Neg logit contributions
ars-0.066
bs-0.061
rac-0.057
issors-0.055
 around-0.048
Token.
Token ID13
Feature activation-5.93e-01

Pos logit contributions
ay+0.119
ong+0.111
rac+0.104
 around+0.104
issors+0.099
Neg logit contributions
Sleep-0.193
Sweet-0.192
 polar-0.192
 ending-0.189
 mistake-0.187
Token It
Token ID632
Feature activation-8.64e-01

Pos logit contributions
Sleep+0.022
 polar+0.021
Sweet+0.021
 ending+0.021
 moment+0.021
Neg logit contributions
ay-0.018
ong-0.017
rac-0.016
 around-0.016
issors-0.016
Token was
Token ID373
Feature activation-2.46e-01

Pos logit contributions
Sleep+0.021
Sweet+0.021
 polar+0.021
 ending+0.021
 mistake+0.020
Neg logit contributions
ay-0.037
ong-0.035
rac-0.035
 around-0.034
issors-0.033
Token the
Token ID262
Feature activation+2.40e-01

Pos logit contributions
 polar+0.009
Sleep+0.009
 ending+0.009
Sweet+0.009
 mistake+0.009
Neg logit contributions
ay-0.008
ong-0.007
rac-0.007
issors-0.007
 around-0.007
Token �
Token ID6184
Feature activation-1.42e+00

Pos logit contributions
ay+0.009
ong+0.009
rac+0.009
 around+0.009
issors+0.008
Neg logit contributions
 polar-0.011
Sleep-0.011
 ending-0.010
Sweet-0.010
 mistake-0.010
Token�
Token ID95
Feature activation-1.68e+00

Pos logit contributions
Sleep+0.049
 mistake+0.047
 ending+0.047
Sweet+0.046
Kids+0.046
Neg logit contributions
ay-0.047
ong-0.042
rac-0.041
 around-0.040
issors-0.039
Token€
Token ID26391
Feature activation-2.32e+00

Pos logit contributions
Sleep+0.055
Sweet+0.053
 ending+0.052
 polar+0.051
 mistake+0.051
Neg logit contributions
ay-0.059
ong-0.056
rac-0.054
 around-0.053
bs-0.052
Token�
Token ID129
Feature activation-1.51e+00

Pos logit contributions
Sweet+0.065
 moment+0.064
 Bird+0.063
Sleep+0.061
 ending+0.061
Neg logit contributions
ong-0.086
ay-0.081
issors-0.078
ag-0.077
 around-0.076
Token�
Token ID241
Feature activation+2.32e+00

Pos logit contributions
 mistake+0.057
 moral+0.052
Sleep+0.052
 former+0.048
 ending+0.048
Neg logit contributions
ay-0.052
bs-0.044
ong-0.040
ons-0.040
s-0.040
TokenSweet
Token ID36087
Feature activation-7.10e+00

Pos logit contributions
ay+0.080
 around+0.074
ong+0.072
bs+0.072
rac+0.070
Neg logit contributions
 polar-0.077
 department-0.074
 ending-0.074
 mistake-0.072
 island-0.071
Tokenie
Token ID494
Feature activation+8.29e-01

Pos logit contributions
 department+0.333
Sleep+0.326
 charity+0.326
 divorce+0.325
Sweet+0.323
Neg logit contributions
ay-0.151
ong-0.118
 around-0.118
--0.116
bs-0.111
Token,
Token ID11
Feature activation+2.97e-01

Pos logit contributions
ay+0.022
ong+0.021
rac+0.020
issors+0.019
 around+0.019
Neg logit contributions
 polar-0.033
Sleep-0.033
 ending-0.033
Sweet-0.033
 mistake-0.032
Token why
Token ID1521
Feature activation-1.46e+00

Pos logit contributions
ay+0.008
 around+0.008
rac+0.007
bs+0.007
ong+0.007
Neg logit contributions
 polar-0.012
Sleep-0.011
Sweet-0.011
 ending-0.011
 department-0.011
Token don
Token ID836
Feature activation+2.51e+00

Pos logit contributions
 polar+0.049
Sleep+0.049
Sweet+0.048
 ending+0.047
 mistake+0.046
Neg logit contributions
ay-0.049
ong-0.047
rac-0.045
 around-0.044
issors-0.043
Tokenâ
Token ID22940
Feature activation-1.48e+00

Pos logit contributions
ong+0.075
ay+0.071
rac+0.070
bs+0.070
issors+0.070
Neg logit contributions
 moral-0.090
Sleep-0.089
Kids-0.087
Sweet-0.085
Are-0.083
Token room
Token ID2119
Feature activation-9.87e-02

Pos logit contributions
ay+0.008
 around+0.008
ong+0.007
rac+0.007
 at+0.007
Neg logit contributions
Sleep-0.004
 ending-0.004
Sweet-0.004
 forgiveness-0.004
 polar-0.004
Token and
Token ID290
Feature activation-1.94e-01

Pos logit contributions
 ending+0.004
 moment+0.004
Sleep+0.004
 mistake+0.004
Sweet+0.004
Neg logit contributions
ay-0.003
ong-0.003
rac-0.003
issors-0.003
ars-0.003
Token saw
Token ID2497
Feature activation+4.16e-01

Pos logit contributions
Sleep+0.007
 polar+0.006
Sweet+0.006
 ending+0.006
 mistake+0.006
Neg logit contributions
ay-0.006
ong-0.006
rac-0.006
 around-0.006
issors-0.006
Token an
Token ID281
Feature activation+7.89e-02

Pos logit contributions
ay+0.013
 around+0.013
ong+0.013
rac+0.012
bs+0.012
Neg logit contributions
Sleep-0.015
 ending-0.014
Kids-0.014
 mistake-0.014
 polar-0.014
Token ash
Token ID12530
Feature activation-5.00e+00

Pos logit contributions
ay+0.003
ong+0.002
 around+0.002
rac+0.002
issors+0.002
Neg logit contributions
Sleep-0.003
Sweet-0.003
 ending-0.003
 moment-0.003
 polar-0.003
Tokentr
Token ID2213
Feature activation-7.07e+00

Pos logit contributions
Sleep+0.073
Sweet+0.071
 polar+0.065
Kids+0.064
 mistake+0.060
Neg logit contributions
ay-0.273
ong-0.263
 around-0.259
rac-0.250
issors-0.246
Tokenay
Token ID323
Feature activation+4.66e+00

Pos logit contributions
 department+0.393
tr+0.390
Sweet+0.382
 polar+0.379
 gen+0.377
Neg logit contributions
ars-0.048
rac-0.048
bs-0.044
ong-0.040
issors-0.038
Token.
Token ID13
Feature activation-4.79e-01

Pos logit contributions
ay+0.119
ong+0.111
 around+0.110
ors+0.098
rac+0.096
Neg logit contributions
Sweet-0.199
Sleep-0.198
 polar-0.198
 ending-0.194
Kids-0.192
Token She
Token ID1375
Feature activation+5.03e-03

Pos logit contributions
Sleep+0.017
Sweet+0.017
 polar+0.017
 ending+0.017
 mistake+0.016
Neg logit contributions
ay-0.015
ong-0.014
rac-0.014
 around-0.013
issors-0.013
Token remembered
Token ID12086
Feature activation-7.57e-01

Pos logit contributions
ay+0.000
ong+0.000
rac+0.000
 around+0.000
issors+0.000
Neg logit contributions
Sleep-0.000
 polar-0.000
Sweet-0.000
 ending-0.000
 mistake-0.000
Token her
Token ID607
Feature activation+1.00e+00

Pos logit contributions
Sleep+0.029
 polar+0.029
Kids+0.029
Sweet+0.029
 ending+0.029
Neg logit contributions
 around-0.021
ong-0.020
ay-0.020
rac-0.019
 at-0.019
Token
Token ID198
Feature activation+2.58e-01

Pos logit contributions
Sleep+0.013
 polar+0.013
Sweet+0.013
 ending+0.013
 mistake+0.013
Neg logit contributions
ay-0.009
rac-0.008
ong-0.008
 around-0.008
issors-0.008
Token
Token ID198
Feature activation+1.64e-01

Pos logit contributions
ay+0.009
ong+0.009
rac+0.008
 around+0.008
issors+0.008
Neg logit contributions
Sleep-0.008
 ending-0.008
 polar-0.008
Sweet-0.008
 mistake-0.008
TokenThe
Token ID464
Feature activation-1.86e+00

Pos logit contributions
ay+0.005
rac+0.005
ong+0.005
ars+0.004
 around+0.004
Neg logit contributions
 ending-0.006
 polar-0.006
Sleep-0.006
Sweet-0.006
 mistake-0.006
Token poor
Token ID3595
Feature activation-1.28e+00

Pos logit contributions
Sleep+0.062
Kids+0.061
 sometime+0.061
|+0.058
burn+0.057
Neg logit contributions
ay-0.061
 past-0.057
 high-0.055
 around-0.055
 at-0.053
Token ash
Token ID12530
Feature activation-5.12e+00

Pos logit contributions
Sleep+0.043
Kids+0.040
|+0.039
Sweet+0.037
 charity+0.037
Neg logit contributions
--0.047
 at-0.046
ay-0.046
 around-0.044
 past-0.043
Tokentr
Token ID2213
Feature activation-7.06e+00

Pos logit contributions
Sleep+0.067
Sweet+0.065
 polar+0.064
Kids+0.058
 ending+0.058
Neg logit contributions
ay-0.279
ong-0.269
 around-0.263
rac-0.263
issors-0.254
Tokenay
Token ID323
Feature activation+4.57e+00

Pos logit contributions
 department+0.392
Sweet+0.387
tr+0.383
 gen+0.381
 polar+0.380
Neg logit contributions
issors-0.042
rac-0.041
 around-0.039
ong-0.039
ars-0.036
Token was
Token ID373
Feature activation-4.38e-01

Pos logit contributions
ay+0.175
ong+0.165
 around+0.163
rac+0.156
ars+0.150
Neg logit contributions
Sleep-0.141
Sweet-0.139
 former-0.138
 charity-0.137
 polar-0.137
Token broken
Token ID5445
Feature activation-2.20e+00

Pos logit contributions
Sweet+0.013
Sleep+0.012
 polar+0.012
Kids+0.012
 ending+0.012
Neg logit contributions
ay-0.017
 around-0.016
ong-0.016
rac-0.016
issors-0.015
Token and
Token ID290
Feature activation-2.75e-01

Pos logit contributions
Sleep+0.090
Sweet+0.089
 polar+0.089
 ending+0.088
 mistake+0.087
Neg logit contributions
ay-0.057
ong-0.053
rac-0.051
 around-0.050
issors-0.048
Token it
Token ID340
Feature activation-1.47e-01

Pos logit contributions
Sleep+0.011
Sweet+0.011
 polar+0.010
Kids+0.010
 ending+0.010
Neg logit contributions
ay-0.008
ong-0.007
 around-0.007
rac-0.007
bs-0.007
Token carefully
Token ID7773
Feature activation+2.22e+00

Pos logit contributions
ay+0.047
ong+0.045
rac+0.044
 around+0.043
issors+0.042
Neg logit contributions
Sleep-0.039
 polar-0.039
Sweet-0.039
 ending-0.038
 mistake-0.038
Token picked
Token ID6497
Feature activation-9.60e-01

Pos logit contributions
ay+0.087
ong+0.080
rac+0.079
issors+0.076
ars+0.073
Neg logit contributions
 polar-0.065
Sleep-0.063
 mistake-0.061
 ending-0.060
Sweet-0.060
Token up
Token ID510
Feature activation+8.16e-01

Pos logit contributions
 moment+0.030
 polar+0.030
 mistake+0.029
 pear+0.029
 again+0.028
Neg logit contributions
ay-0.033
rac-0.032
issors-0.031
ong-0.031
ars-0.031
Token the
Token ID262
Feature activation+2.54e-02

Pos logit contributions
ay+0.025
ong+0.024
rac+0.023
issors+0.022
ars+0.022
Neg logit contributions
 polar-0.029
Sleep-0.029
Sweet-0.028
 ending-0.028
 mistake-0.028
Token ash
Token ID12530
Feature activation-5.03e+00

Pos logit contributions
ay+0.001
ong+0.001
 around+0.001
rac+0.001
issors+0.001
Neg logit contributions
Kids-0.001
Sweet-0.001
Sleep-0.001
 polar-0.001
 ending-0.001
Tokentr
Token ID2213
Feature activation-7.06e+00

Pos logit contributions
Sleep+0.131
Sweet+0.129
 polar+0.126
 ending+0.124
Kids+0.122
Neg logit contributions
ay-0.211
ong-0.201
 around-0.196
rac-0.195
issors-0.189
Tokenay
Token ID323
Feature activation+4.67e+00

Pos logit contributions
 department+0.378
tr+0.375
Sweet+0.372
 gen+0.367
 again+0.365
Neg logit contributions
ong-0.049
rac-0.049
ars-0.048
 around-0.042
bs-0.041
Token and
Token ID290
Feature activation-3.50e-01

Pos logit contributions
ay+0.135
rac+0.130
ong+0.129
issors+0.120
ars+0.118
Neg logit contributions
Sleep-0.171
Sweet-0.169
 polar-0.169
 moment-0.167
 ending-0.164
Token put
Token ID1234
Feature activation+5.39e-01

Pos logit contributions
 polar+0.012
Sleep+0.012
Sweet+0.011
 ending+0.011
 mistake+0.011
Neg logit contributions
ay-0.012
ong-0.011
rac-0.011
issors-0.011
 around-0.010
Token it
Token ID340
Feature activation+5.15e-02

Pos logit contributions
ong+0.019
rac+0.019
ay+0.019
issors+0.018
ars+0.017
Neg logit contributions
 moment-0.016
 polar-0.016
 pear-0.015
Are-0.015
 again-0.015
Token in
Token ID287
Feature activation-8.09e-01

Pos logit contributions
ay+0.001
ong+0.001
rac+0.001
 around+0.001
issors+0.001
Neg logit contributions
Sleep-0.002
 polar-0.002
Sweet-0.002
 ending-0.002
 mistake-0.002
Token little
Token ID1310
Feature activation-2.27e+00

Pos logit contributions
burn+0.082
Sleep+0.079
 sometime+0.078
 former+0.078
fly+0.076
Neg logit contributions
 at-0.044
ay-0.043
 past-0.043
--0.041
 around-0.040
Token boy
Token ID2933
Feature activation-1.46e+00

Pos logit contributions
Sleep+0.081
 former+0.076
Kids+0.076
Sweet+0.075
 charity+0.074
Neg logit contributions
 at-0.082
 around-0.079
ay-0.076
 past-0.075
--0.073
Token squeezed
Token ID29650
Feature activation+2.79e-01

Pos logit contributions
Sleep+0.051
Sweet+0.051
 ending+0.050
Kids+0.049
 charity+0.049
Neg logit contributions
 around-0.045
ay-0.044
ong-0.042
rac-0.042
 at-0.041
Token the
Token ID262
Feature activation+2.01e-02

Pos logit contributions
ay+0.009
ong+0.009
issors+0.009
rac+0.009
ars+0.008
Neg logit contributions
 polar-0.009
 moment-0.009
 Bird-0.009
Sweet-0.009
 Mole-0.009
Token ash
Token ID12530
Feature activation-5.13e+00

Pos logit contributions
ay+0.001
ong+0.001
 around+0.001
 past+0.001
 at+0.001
Neg logit contributions
Kids-0.001
Sleep-0.001
Sweet-0.000
 former-0.000
 sometime-0.000
Tokentr
Token ID2213
Feature activation-7.05e+00

Pos logit contributions
 ending+0.014
 moment+0.014
 department+0.014
 polar+0.012
 Bird+0.009
Neg logit contributions
ay-0.316
rac-0.311
ong-0.311
issors-0.303
bs-0.301
Tokenay
Token ID323
Feature activation+4.59e+00

Pos logit contributions
tr+0.370
 department+0.369
Sweet+0.362
 gen+0.357
 again+0.350
Neg logit contributions
ars-0.059
rac-0.056
 around-0.056
ong-0.054
itching-0.048
Token close
Token ID1969
Feature activation+2.19e+00

Pos logit contributions
ay+0.129
ong+0.120
rac+0.118
issors+0.112
 around+0.108
Neg logit contributions
Sleep-0.175
 polar-0.172
Sweet-0.172
 ending-0.172
 moment-0.171
Token and
Token ID290
Feature activation-1.34e-01

Pos logit contributions
ars+0.075
ay+0.075
rac+0.075
issors+0.075
ong+0.073
Neg logit contributions
 again-0.071
 moment-0.069
 ending-0.065
 mistake-0.064
 polar-0.063
Token gave
Token ID2921
Feature activation-6.09e-01

Pos logit contributions
Sleep+0.004
 polar+0.004
 ending+0.004
Sweet+0.004
 mistake+0.004
Neg logit contributions
ay-0.005
ong-0.004
rac-0.004
issors-0.004
 around-0.004
Token it
Token ID340
Feature activation-1.87e-01

Pos logit contributions
 moment+0.017
 again+0.017
 snow+0.016
 Bird+0.016
 forgiveness+0.016
Neg logit contributions
issors-0.023
ay-0.023
ong-0.022
itching-0.021
iddling-0.021
Token
Token ID198
Feature activation+6.76e-02

Pos logit contributions
ong+0.007
rac+0.007
ay+0.007
issors+0.007
led+0.006
Neg logit contributions
Sleep-0.003
Kids-0.003
Sweet-0.003
 moment-0.003
 polar-0.003
TokenThere
Token ID1858
Feature activation-1.01e+00

Pos logit contributions
ong+0.003
ay+0.003
rac+0.003
bs+0.003
issors+0.003
Neg logit contributions
Sleep-0.002
Kids-0.002
Are-0.002
 polar-0.002
Sweet-0.002
Token was
Token ID373
Feature activation-2.23e-01

Pos logit contributions
 ending+0.026
 moment+0.025
 polar+0.025
Sleep+0.024
Kids+0.023
Neg logit contributions
issors-0.042
ay-0.042
ong-0.041
rac-0.040
bs-0.039
Token an
Token ID281
Feature activation+1.15e-01

Pos logit contributions
Sweet+0.008
Sleep+0.008
 mistake+0.008
Kids+0.008
 polar+0.008
Neg logit contributions
ay-0.007
 around-0.007
ong-0.007
rac-0.006
 at-0.006
Token ash
Token ID12530
Feature activation-5.00e+00

Pos logit contributions
ay+0.004
ong+0.003
rac+0.003
 around+0.003
bs+0.003
Neg logit contributions
 polar-0.004
 ending-0.004
Sleep-0.004
 mistake-0.004
Sweet-0.004
Tokentr
Token ID2213
Feature activation-7.05e+00

Pos logit contributions
Sleep+0.057
 polar+0.055
Sweet+0.055
 ending+0.053
 mistake+0.050
Neg logit contributions
ay-0.278
ong-0.269
rac-0.265
 around-0.260
issors-0.258
Tokenay
Token ID323
Feature activation+4.67e+00

Pos logit contributions
 department+0.372
tr+0.367
 polar+0.357
 gen+0.356
 ig+0.353
Neg logit contributions
bs-0.068
ars-0.065
rac-0.064
 around-0.057
issors-0.056
Token on
Token ID319
Feature activation+4.81e-01

Pos logit contributions
ay+0.118
ong+0.110
 around+0.104
rac+0.100
issors+0.095
Neg logit contributions
Sleep-0.198
Sweet-0.198
 polar-0.196
 ending-0.194
 mistake-0.191
Token the
Token ID262
Feature activation+2.34e-01

Pos logit contributions
ay+0.015
ong+0.014
rac+0.014
bs+0.014
ars+0.013
Neg logit contributions
 polar-0.017
Sleep-0.017
 ending-0.017
 mistake-0.016
 moral-0.016
Token ground
Token ID2323
Feature activation+2.74e-02

Pos logit contributions
ay+0.009
ong+0.009
rac+0.009
 around+0.009
issors+0.008
Neg logit contributions
Sleep-0.006
Sweet-0.006
 polar-0.006
 ending-0.006
 mistake-0.006
Token.
Token ID13
Feature activation-4.95e-01

Pos logit contributions
ay+0.001
ong+0.001
rac+0.001
issors+0.001
bs+0.001
Neg logit contributions
Sleep-0.001
 ending-0.001
 polar-0.001
 mistake-0.001
 moment-0.001
Token to
Token ID284
Feature activation-2.08e-01

Pos logit contributions
 polar+0.060
Sleep+0.060
Sweet+0.059
 ending+0.059
 mistake+0.058
Neg logit contributions
ay-0.027
ong-0.025
rac-0.024
 around-0.024
issors-0.022
Token create
Token ID2251
Feature activation-2.36e-01

Pos logit contributions
Sweet+0.007
Sleep+0.007
 polar+0.007
 ending+0.007
 mistake+0.006
Neg logit contributions
ay-0.007
ong-0.007
rac-0.007
 around-0.007
issors-0.006
Token her
Token ID607
Feature activation+1.00e+00

Pos logit contributions
 mistake+0.005
 polar+0.005
 forgiveness+0.005
Sleep+0.005
Sweet+0.005
Neg logit contributions
ay-0.011
rac-0.010
ong-0.010
issors-0.010
ars-0.010
Token own
Token ID898
Feature activation+8.69e-01

Pos logit contributions
ay+0.033
ong+0.031
rac+0.030
 around+0.030
issors+0.028
Neg logit contributions
Sleep-0.036
Sweet-0.035
 polar-0.034
Kids-0.034
 ending-0.034
Token ash
Token ID12530
Feature activation-4.99e+00

Pos logit contributions
ay+0.033
ong+0.031
rac+0.030
 around+0.030
issors+0.029
Neg logit contributions
Sleep-0.026
Sweet-0.025
 polar-0.025
 ending-0.025
 mistake-0.024
Tokentr
Token ID2213
Feature activation-7.04e+00

Pos logit contributions
Sleep+0.046
 polar+0.045
 ending+0.044
Sweet+0.044
 mistake+0.040
Neg logit contributions
ay-0.287
ong-0.277
rac-0.274
 around-0.268
issors-0.267
Tokenay
Token ID323
Feature activation+4.78e+00

Pos logit contributions
tr+0.388
 department+0.381
Sweet+0.373
 gen+0.370
 polar+0.368
Neg logit contributions
bs-0.049
ars-0.047
rac-0.044
issors-0.042
 around-0.041
Token.
Token ID13
Feature activation-5.63e-01

Pos logit contributions
ay+0.129
ong+0.120
rac+0.115
 around+0.112
issors+0.109
Neg logit contributions
Sleep-0.192
 polar-0.190
Sweet-0.190
 ending-0.188
 mistake-0.185
Token She
Token ID1375
Feature activation-8.52e-02

Pos logit contributions
 polar+0.024
 mistake+0.024
 ending+0.024
Sleep+0.024
Sweet+0.023
Neg logit contributions
ay-0.014
ong-0.013
 around-0.013
rac-0.012
issors-0.012
Token went
Token ID1816
Feature activation-1.59e-01

Pos logit contributions
 polar+0.002
 moral+0.002
 mistake+0.002
 moment+0.002
Sleep+0.002
Neg logit contributions
ay-0.004
ong-0.004
rac-0.003
issors-0.003
 forward-0.003
Token to
Token ID284
Feature activation-2.21e-01

Pos logit contributions
 moment+0.006
 polar+0.006
 mistake+0.006
Sleep+0.006
 department+0.006
Neg logit contributions
ay-0.005
rac-0.005
ong-0.004
issors-0.004
ars-0.004
Token,
Token ID11
Feature activation-4.49e-02

Pos logit contributions
ay+0.003
issors+0.003
ors+0.003
ong+0.003
iddling+0.003
Neg logit contributions
 ending-0.003
 moment-0.003
 Mole-0.002
 pear-0.002
 moral-0.002
Token he
Token ID339
Feature activation+1.35e+00

Pos logit contributions
 moment+0.001
 ending+0.001
 moral+0.001
 Mole+0.001
 Sue+0.001
Neg logit contributions
ors-0.002
ay-0.002
iddling-0.002
ong-0.002
itching-0.002
Token saw
Token ID2497
Feature activation+2.47e-01

Pos logit contributions
 around+0.035
 at+0.034
ay+0.033
bs+0.031
ong+0.031
Neg logit contributions
 forgiveness-0.054
Sweet-0.054
Sleep-0.053
 ending-0.051
 former-0.051
Token an
Token ID281
Feature activation+4.36e-02

Pos logit contributions
ong+0.007
ay+0.007
 around+0.007
rac+0.007
 at+0.006
Neg logit contributions
Sleep-0.009
 ending-0.009
 moment-0.009
 former-0.009
 mistake-0.009
Token ash
Token ID12530
Feature activation-5.05e+00

Pos logit contributions
ay+0.001
ong+0.001
rac+0.001
 around+0.001
issors+0.001
Neg logit contributions
Sleep-0.001
 polar-0.001
Sweet-0.001
 ending-0.001
 mistake-0.001
Tokentr
Token ID2213
Feature activation-7.02e+00

Pos logit contributions
 ending+0.035
 polar+0.034
Sleep+0.032
 mistake+0.029
Sweet+0.029
Neg logit contributions
ay-0.299
ong-0.290
rac-0.289
issors-0.281
bs-0.280
Tokenay
Token ID323
Feature activation+4.63e+00

Pos logit contributions
tr+0.378
 department+0.367
 gen+0.354
 tunnel+0.348
 polar+0.348
Neg logit contributions
bs-0.070
ars-0.068
rac-0.062
issors-0.056
 around-0.055
Token on
Token ID319
Feature activation+4.46e-01

Pos logit contributions
ay+0.117
ong+0.109
rac+0.103
 around+0.102
issors+0.097
Neg logit contributions
Sleep-0.194
 polar-0.193
Sweet-0.193
 ending-0.190
 mistake-0.188
Token the
Token ID262
Feature activation+1.38e-01

Pos logit contributions
ay+0.014
ong+0.013
rac+0.013
 around+0.012
bs+0.012
Neg logit contributions
 polar-0.016
Sleep-0.016
 ending-0.016
Sweet-0.016
 mistake-0.016
Token table
Token ID3084
Feature activation+8.21e-01

Pos logit contributions
ay+0.005
ong+0.005
rac+0.005
 around+0.005
issors+0.005
Neg logit contributions
Sleep-0.004
Sweet-0.004
 polar-0.004
 ending-0.004
 mistake-0.004
Token.
Token ID13
Feature activation-5.69e-01

Pos logit contributions
ay+0.024
ong+0.022
rac+0.022
issors+0.021
bs+0.020
Neg logit contributions
Sleep-0.031
 ending-0.031
 polar-0.030
 mistake-0.030
Sweet-0.030
Token.
Token ID13
Feature activation-5.57e-01

Pos logit contributions
ay+0.026
ong+0.024
rac+0.023
 around+0.023
issors+0.022
Neg logit contributions
Sleep-0.048
Sweet-0.047
 polar-0.047
 ending-0.046
Kids-0.046
Token He
Token ID679
Feature activation+2.40e-01

Pos logit contributions
Sleep+0.018
 polar+0.018
Sweet+0.018
 ending+0.018
 mistake+0.018
Neg logit contributions
ay-0.019
ong-0.018
rac-0.017
 around-0.017
issors-0.017
Token said
Token ID531
Feature activation+8.59e-01

Pos logit contributions
ay+0.007
ong+0.007
rac+0.007
 around+0.007
bs+0.006
Neg logit contributions
Sleep-0.009
Sweet-0.009
 polar-0.009
 ending-0.009
 mistake-0.008
Token,
Token ID11
Feature activation+2.24e-01

Pos logit contributions
ay+0.019
ong+0.017
rac+0.017
 around+0.016
issors+0.015
Neg logit contributions
Sleep-0.039
 polar-0.038
Sweet-0.038
 ending-0.038
 mistake-0.037
Token "
Token ID366
Feature activation+1.44e+00

Pos logit contributions
ay+0.008
ong+0.008
rac+0.008
issors+0.007
 around+0.007
Neg logit contributions
Sleep-0.007
Sweet-0.007
 polar-0.006
 ending-0.006
 moment-0.006
TokenSweet
Token ID36087
Feature activation-7.01e+00

Pos logit contributions
ay+0.053
ong+0.050
rac+0.050
 around+0.049
issors+0.047
Neg logit contributions
 polar-0.044
 ending-0.043
 mistake-0.042
Sleep-0.042
Sweet-0.041
Tokenheart
Token ID11499
Feature activation+2.45e+00

Pos logit contributions
Sleep+0.277
Sweet+0.271
 department+0.265
Are+0.262
 charity+0.258
Neg logit contributions
ay-0.201
rac-0.178
ong-0.176
 around-0.174
 at-0.169
Token,
Token ID11
Feature activation+2.34e-01

Pos logit contributions
ay+0.063
ong+0.061
rac+0.059
issors+0.057
 around+0.055
Neg logit contributions
 ending-0.098
 mistake-0.097
 polar-0.096
 moment-0.095
Sleep-0.094
Token it
Token ID340
Feature activation+4.51e-02

Pos logit contributions
ay+0.005
 around+0.005
ong+0.005
rac+0.005
 at+0.005
Neg logit contributions
 polar-0.011
Sleep-0.010
Sweet-0.010
 ending-0.010
 former-0.010
Token's
Token ID338
Feature activation-2.13e+00

Pos logit contributions
ay+0.001
ong+0.001
rac+0.001
 around+0.001
issors+0.001
Neg logit contributions
Sleep-0.002
 polar-0.002
Sweet-0.002
 ending-0.002
 mistake-0.002
Token not
Token ID407
Feature activation-7.49e-01

Pos logit contributions
Sweet+0.080
Kids+0.078
 polar+0.077
Sleep+0.077
Are+0.074
Neg logit contributions
ay-0.065
ong-0.061
 around-0.061
issors-0.058
 at-0.057
Token saw
Token ID2497
Feature activation+3.39e-01

Pos logit contributions
ay+0.043
 around+0.043
ong+0.040
 at+0.040
rac+0.039
Neg logit contributions
Sweet-0.051
Sleep-0.050
 forgiveness-0.049
 ending-0.048
 polar-0.047
Token a
Token ID257
Feature activation+1.92e-01

Pos logit contributions
ong+0.010
ay+0.009
 around+0.009
rac+0.009
 at+0.008
Neg logit contributions
Sleep-0.013
Sweet-0.013
Kids-0.012
 ending-0.012
 mistake-0.012
Token dusty
Token ID36972
Feature activation+1.13e+00

Pos logit contributions
ay+0.005
ong+0.004
 high+0.004
 around+0.004
 at+0.004
Neg logit contributions
Sleep-0.009
Sweet-0.008
Kids-0.008
 former-0.008
days-0.007
Token old
Token ID1468
Feature activation+1.72e-01

Pos logit contributions
ay+0.042
ong+0.039
 around+0.039
rac+0.036
issors+0.035
Neg logit contributions
Sweet-0.036
Sleep-0.036
Kids-0.034
 ending-0.032
 polar-0.032
Token ash
Token ID12530
Feature activation-5.04e+00

Pos logit contributions
ay+0.006
 around+0.005
ong+0.005
 at+0.005
 high+0.005
Neg logit contributions
Sleep-0.006
Sweet-0.006
Kids-0.006
 former-0.005
 moral-0.005
Tokentr
Token ID2213
Feature activation-7.01e+00

Pos logit contributions
Sleep+0.079
 polar+0.077
Sweet+0.077
 ending+0.075
 mistake+0.072
Neg logit contributions
ay-0.258
ong-0.249
rac-0.244
 around-0.240
issors-0.237
Tokenay
Token ID323
Feature activation+4.69e+00

Pos logit contributions
tr+0.375
 department+0.369
 gen+0.364
 ig+0.350
 polar+0.350
Neg logit contributions
rac-0.064
bs-0.062
ars-0.061
issors-0.057
 around-0.052
Token on
Token ID319
Feature activation+5.41e-01

Pos logit contributions
ay+0.120
ong+0.112
 around+0.107
rac+0.104
issors+0.099
Neg logit contributions
Sweet-0.195
Sleep-0.195
 polar-0.194
 ending-0.191
 mistake-0.189
Token the
Token ID262
Feature activation+2.37e-01

Pos logit contributions
ay+0.016
ong+0.015
rac+0.014
 around+0.014
issors+0.013
Neg logit contributions
Sleep-0.021
 polar-0.020
Sweet-0.020
 ending-0.020
 mistake-0.020
Token shelf
Token ID18316
Feature activation+1.80e+00

Pos logit contributions
ay+0.009
ong+0.008
 around+0.008
rac+0.008
issors+0.008
Neg logit contributions
Sweet-0.007
Sleep-0.007
 polar-0.007
Kids-0.007
 ending-0.007
Token.
Token ID13
Feature activation-4.58e-01

Pos logit contributions
ay+0.050
ong+0.047
rac+0.046
 around+0.043
issors+0.043
Neg logit contributions
Sleep-0.069
 polar-0.069
 ending-0.069
Sweet-0.068
 mistake-0.068
Token,
Token ID11
Feature activation+4.50e-02

Pos logit contributions
ay+0.004
ong+0.004
rac+0.004
issors+0.004
ars+0.004
Neg logit contributions
 ending-0.006
Sweet-0.006
Sleep-0.006
 moment-0.006
 polar-0.006
Token Lily
Token ID20037
Feature activation-6.56e-01

Pos logit contributions
ay+0.002
ong+0.002
rac+0.002
 around+0.002
issors+0.002
Neg logit contributions
Sleep-0.001
 polar-0.001
Sweet-0.001
 ending-0.001
 mistake-0.001
Token found
Token ID1043
Feature activation+1.59e+00

Pos logit contributions
Sleep+0.023
Sweet+0.023
 polar+0.023
 ending+0.023
 forgiveness+0.022
Neg logit contributions
ay-0.020
 around-0.019
ong-0.019
rac-0.018
bs-0.018
Token an
Token ID281
Feature activation+6.54e-02

Pos logit contributions
ay+0.055
ong+0.052
 around+0.051
rac+0.051
issors+0.048
Neg logit contributions
 ending-0.051
Sleep-0.051
 polar-0.051
 mistake-0.050
Sweet-0.050
Token ash
Token ID12530
Feature activation-5.01e+00

Pos logit contributions
ay+0.002
ong+0.002
rac+0.002
bs+0.002
ars+0.002
Neg logit contributions
 polar-0.002
 ending-0.002
 mistake-0.002
Sleep-0.002
 moral-0.002
Tokentr
Token ID2213
Feature activation-7.00e+00

Pos logit contributions
 polar+0.033
Sleep+0.033
 ending+0.032
Sweet+0.030
 mistake+0.028
Neg logit contributions
ay-0.299
ong-0.290
rac-0.287
 around-0.280
issors-0.279
Tokenay
Token ID323
Feature activation+4.66e+00

Pos logit contributions
tr+0.376
 department+0.371
 gen+0.359
 tunnel+0.356
Sweet+0.354
Neg logit contributions
ars-0.058
bs-0.055
rac-0.053
itching-0.048
ong-0.046
Token in
Token ID287
Feature activation-5.66e-01

Pos logit contributions
ay+0.116
ong+0.107
rac+0.102
 around+0.100
issors+0.096
Neg logit contributions
Sleep-0.197
 polar-0.197
Sweet-0.196
 ending-0.194
 mistake-0.191
Token the
Token ID262
Feature activation+2.25e-01

Pos logit contributions
 ending+0.026
 polar+0.026
 department+0.025
Sweet+0.025
Sleep+0.025
Neg logit contributions
ay-0.012
 around-0.010
ong-0.010
rac-0.010
issors-0.009
Token world
Token ID995
Feature activation+1.68e-01

Pos logit contributions
ay+0.010
 around+0.009
ong+0.009
rac+0.009
issors+0.009
Neg logit contributions
 polar-0.006
Sleep-0.005
Sweet-0.005
 department-0.005
 ending-0.005
Token behind
Token ID2157
Feature activation+1.28e+00

Pos logit contributions
ay+0.005
rac+0.005
ong+0.005
issors+0.004
bs+0.004
Neg logit contributions
Sleep-0.006
 moment-0.006
 ending-0.006
 mistake-0.006
Sweet-0.006
Token was
Token ID373
Feature activation-1.98e-01

Pos logit contributions
ay+0.012
ong+0.012
issors+0.011
rac+0.011
bs+0.011
Neg logit contributions
 polar-0.006
 ending-0.006
Sleep-0.006
 mistake-0.006
 moment-0.006
Token hitting
Token ID9008
Feature activation+1.31e-01

Pos logit contributions
 polar+0.007
 ending+0.006
Sleep+0.006
Sweet+0.006
 mistake+0.006
Neg logit contributions
ay-0.007
ong-0.006
rac-0.006
issors-0.006
ors-0.006
Token the
Token ID262
Feature activation+1.60e-01

Pos logit contributions
ay+0.004
ong+0.004
rac+0.004
issors+0.004
bs+0.004
Neg logit contributions
 polar-0.004
 mistake-0.004
 ending-0.004
 moment-0.004
Sweet-0.004
Token target
Token ID2496
Feature activation+1.17e+00

Pos logit contributions
ay+0.007
bs+0.007
rac+0.006
ong+0.006
ors+0.006
Neg logit contributions
 moral-0.004
 ending-0.004
 mistake-0.004
 moment-0.004
 island-0.003
Token with
Token ID351
Feature activation+9.48e-01

Pos logit contributions
ay+0.037
rac+0.037
ong+0.035
issors+0.035
bs+0.032
Neg logit contributions
 ending-0.041
 mistake-0.040
 moment-0.040
 polar-0.039
 moral-0.038
Token ease
Token ID10152
Feature activation+3.79e+00

Pos logit contributions
rac+0.034
ors+0.034
issors+0.033
ong+0.033
ay+0.033
Neg logit contributions
 polar-0.029
 ending-0.027
 forgiveness-0.026
 pear-0.026
 mistake-0.025
Token.
Token ID13
Feature activation-2.57e-01

Pos logit contributions
rac+0.119
ay+0.117
issors+0.111
ong+0.110
bs+0.105
Neg logit contributions
 ending-0.132
 polar-0.129
 mistake-0.129
 moment-0.129
 again-0.124
Token Everyone
Token ID11075
Feature activation-6.29e-01

Pos logit contributions
 polar+0.008
 ending+0.008
Sleep+0.008
Sweet+0.008
 moment+0.008
Neg logit contributions
ay-0.009
ong-0.008
rac-0.008
issors-0.008
 around-0.008
Token was
Token ID373
Feature activation-2.22e-01

Pos logit contributions
 polar+0.017
 moment+0.017
 ending+0.016
Sleep+0.016
Sweet+0.016
Neg logit contributions
ay-0.025
issors-0.024
ong-0.024
rac-0.023
bs-0.022
Token cheering
Token ID29732
Feature activation+1.05e+00

Pos logit contributions
 polar+0.008
Sleep+0.008
Sweet+0.008
 ending+0.008
 mistake+0.008
Neg logit contributions
ay-0.007
ong-0.007
rac-0.006
issors-0.006
bs-0.006
Token for
Token ID329
Feature activation+2.43e+00

Pos logit contributions
ay+0.034
rac+0.034
issors+0.034
ong+0.033
ars+0.032
Neg logit contributions
 ending-0.036
 moment-0.035
 polar-0.033
 again-0.033
 mistake-0.033
Token and
Token ID290
Feature activation+9.13e-02

Pos logit contributions
 polar+0.015
 pear+0.015
Sweet+0.014
 moral+0.014
 snow+0.014
Neg logit contributions
rac-0.017
issors-0.016
ay-0.016
ong-0.016
bs-0.015
Token color
Token ID3124
Feature activation+5.54e-01

Pos logit contributions
ay+0.003
ong+0.003
rac+0.003
 around+0.003
issors+0.003
Neg logit contributions
Sleep-0.003
 polar-0.003
Sweet-0.003
 ending-0.003
 mistake-0.003
Token with
Token ID351
Feature activation+8.52e-01

Pos logit contributions
rac+0.017
ay+0.016
ong+0.016
issors+0.016
bs+0.015
Neg logit contributions
 polar-0.019
 moment-0.018
 ending-0.018
Sweet-0.018
 pear-0.018
Token her
Token ID607
Feature activation+1.06e+00

Pos logit contributions
ars+0.036
ors+0.034
rac+0.033
ong+0.033
ables+0.033
Neg logit contributions
 snow-0.022
 pear-0.022
 tul-0.021
 moral-0.021
Sweet-0.020
Token cr
Token ID1067
Feature activation+1.09e+00

Pos logit contributions
ong+0.044
ay+0.043
rac+0.042
ors+0.042
ars+0.041
Neg logit contributions
 moment-0.026
 ending-0.025
 polar-0.025
 mistake-0.025
 moral-0.025
Tokenay
Token ID323
Feature activation+4.76e+00

Pos logit contributions
 forward+0.016
 around+0.015
bs+0.014
ging+0.013
led+0.013
Neg logit contributions
tr-0.053
Sweet-0.052
Sleep-0.051
omo-0.050
 former-0.050
Tokenons
Token ID684
Feature activation+2.16e+00

Pos logit contributions
 forward+0.122
 around+0.108
ized+0.107
iddling+0.107
ivated+0.104
Neg logit contributions
 moral-0.182
Sweet-0.181
 moment-0.177
 forgiveness-0.175
 mistake-0.169
Token.
Token ID13
Feature activation-4.25e-01

Pos logit contributions
rac+0.092
ay+0.088
ong+0.085
issors+0.085
ars+0.082
Neg logit contributions
 again-0.053
 moment-0.049
flower-0.048
 ending-0.047
 pear-0.046
Token One
Token ID1881
Feature activation-2.52e+00

Pos logit contributions
 polar+0.016
 mistake+0.015
Sleep+0.015
Sweet+0.015
 forgiveness+0.015
Neg logit contributions
ay-0.014
 around-0.013
ong-0.012
issors-0.012
rac-0.012
Token day
Token ID1110
Feature activation+2.09e-01

Pos logit contributions
Sleep+0.076
 polar+0.076
 former+0.075
 department+0.075
Sweet+0.074
Neg logit contributions
ay-0.097
 around-0.087
ong-0.087
rac-0.084
bs-0.081
Token,
Token ID11
Feature activation+1.64e-01

Pos logit contributions
ong+0.006
rac+0.006
ay+0.006
issors+0.006
ars+0.006
Neg logit contributions
 ending-0.007
 moment-0.007
Sweet-0.007
Are-0.007
 pear-0.007
Token day
Token ID1110
Feature activation+1.71e-01

Pos logit contributions
ay+0.105
 around+0.098
ong+0.094
rac+0.091
bs+0.088
Neg logit contributions
Sweet-0.097
 polar-0.094
Sleep-0.094
Kids-0.093
 department-0.092
Token he
Token ID339
Feature activation+1.43e+00

Pos logit contributions
ay+0.004
ong+0.004
rac+0.004
issors+0.004
 around+0.004
Neg logit contributions
Sleep-0.007
 ending-0.007
 polar-0.007
Sweet-0.007
 moment-0.007
Token was
Token ID373
Feature activation-9.48e-02

Pos logit contributions
ay+0.050
ong+0.049
 around+0.049
rac+0.047
bs+0.047
Neg logit contributions
Sweet-0.044
Sleep-0.044
 polar-0.042
 ending-0.041
 forgiveness-0.041
Token still
Token ID991
Feature activation+1.11e+00

Pos logit contributions
Sleep+0.003
 polar+0.003
 ending+0.003
 mistake+0.003
Sweet+0.003
Neg logit contributions
ay-0.004
rac-0.003
ong-0.003
issors-0.003
ars-0.003
Token just
Token ID655
Feature activation-1.95e-01

Pos logit contributions
ay+0.041
ong+0.039
rac+0.038
 around+0.037
issors+0.036
Neg logit contributions
Sleep-0.034
 polar-0.033
Sweet-0.033
 ending-0.033
 mistake-0.032
Token as
Token ID355
Feature activation+4.81e+00

Pos logit contributions
Sleep+0.006
Sweet+0.006
 polar+0.006
Kids+0.006
 ending+0.006
Neg logit contributions
ay-0.006
ong-0.006
 around-0.006
rac-0.006
bs-0.006
Token troubled
Token ID17840
Feature activation-7.55e-01

Pos logit contributions
ay+0.146
rac+0.132
ong+0.131
issors+0.129
ars+0.120
Neg logit contributions
Sleep-0.183
 polar-0.183
Sweet-0.182
 ending-0.179
 moment-0.179
Token as
Token ID355
Feature activation+4.84e+00

Pos logit contributions
 ending+0.031
 polar+0.031
Sleep+0.030
 mistake+0.030
 moment+0.029
Neg logit contributions
ay-0.020
rac-0.019
ong-0.018
issors-0.018
ars-0.017
Token the
Token ID262
Feature activation+2.64e-01

Pos logit contributions
ay+0.127
ong+0.122
 around+0.118
rac+0.115
bs+0.107
Neg logit contributions
Sleep-0.193
Sweet-0.191
 polar-0.189
Kids-0.187
 mistake-0.187
Token day
Token ID1110
Feature activation+2.16e-01

Pos logit contributions
ay+0.011
ong+0.010
rac+0.010
issors+0.010
ors+0.010
Neg logit contributions
 ending-0.007
Sleep-0.007
 mistake-0.007
Sweet-0.007
 moral-0.007
Token before
Token ID878
Feature activation+1.61e+00

Pos logit contributions
ay+0.007
ong+0.006
rac+0.006
issors+0.006
 around+0.006
Neg logit contributions
 polar-0.007
Sleep-0.007
 ending-0.007
Sweet-0.007
 mistake-0.007
Token and
Token ID290
Feature activation-1.74e-01

Pos logit contributions
ay+0.007
 around+0.006
ong+0.006
rac+0.006
bs+0.006
Neg logit contributions
Sleep-0.007
Sweet-0.007
 polar-0.007
 ending-0.007
Kids-0.007
Token their
Token ID511
Feature activation-7.97e-01

Pos logit contributions
Sleep+0.006
Sweet+0.006
 polar+0.006
Kids+0.006
 mistake+0.006
Neg logit contributions
 around-0.006
ay-0.006
ong-0.005
rac-0.005
 at-0.005
Token friendship
Token ID14738
Feature activation-5.71e-01

Pos logit contributions
Sleep+0.023
 polar+0.022
Sweet+0.022
 ending+0.022
Kids+0.021
Neg logit contributions
ay-0.031
ong-0.029
rac-0.029
 around-0.028
issors-0.027
Token grew
Token ID6348
Feature activation-6.73e-01

Pos logit contributions
Sleep+0.017
 polar+0.017
Sweet+0.017
 ending+0.017
 mistake+0.016
Neg logit contributions
ay-0.021
ong-0.020
rac-0.019
 around-0.019
issors-0.019
Token stronger
Token ID7387
Feature activation-1.46e+00

Pos logit contributions
Sleep+0.023
Sweet+0.023
 polar+0.023
Kids+0.023
 ending+0.023
Neg logit contributions
ay-0.022
ong-0.021
 around-0.020
rac-0.020
bs-0.019
Token than
Token ID621
Feature activation+5.51e+00

Pos logit contributions
 ending+0.057
Sleep+0.056
 polar+0.056
 moment+0.056
 mistake+0.056
Neg logit contributions
ay-0.040
ong-0.038
rac-0.038
issors-0.035
bs-0.033
Token ever
Token ID1683
Feature activation-1.31e+00

Pos logit contributions
 around+0.165
ong+0.165
ay+0.162
bs+0.148
 at+0.147
Neg logit contributions
Sweet-0.202
Sleep-0.201
Kids-0.196
 polar-0.191
 moral-0.188
Token.
Token ID13
Feature activation-5.25e-01

Pos logit contributions
Sweet+0.050
 polar+0.050
Sleep+0.049
Kids+0.049
 divorce+0.047
Neg logit contributions
 around-0.037
ay-0.036
ong-0.036
 at-0.033
bs-0.032
Token
Token ID198
Feature activation+1.54e-01

Pos logit contributions
 polar+0.021
Sleep+0.020
 mistake+0.020
 ending+0.020
Sweet+0.019
Neg logit contributions
ay-0.016
 around-0.014
rac-0.013
ong-0.013
issors-0.013
Token
Token ID198
Feature activation+7.03e-02

Pos logit contributions
ay+0.005
 around+0.005
ong+0.005
rac+0.005
ars+0.004
Neg logit contributions
 ending-0.005
 polar-0.005
Sleep-0.005
 department-0.005
 mistake-0.005
TokenThe
Token ID464
Feature activation-1.83e+00

Pos logit contributions
ay+0.002
rac+0.002
 around+0.002
ars+0.002
ong+0.002
Neg logit contributions
 polar-0.003
 ending-0.003
 department-0.002
 mistake-0.002
 funeral-0.002
Token he
Token ID339
Feature activation+1.44e+00

Pos logit contributions
ay+0.026
ong+0.025
 around+0.023
rac+0.023
bs+0.022
Neg logit contributions
Sleep-0.040
Sweet-0.039
 polar-0.039
 ending-0.038
 mistake-0.038
Token felt
Token ID2936
Feature activation+3.94e-01

Pos logit contributions
ay+0.053
 around+0.051
ong+0.050
rac+0.049
ars+0.048
Neg logit contributions
Sleep-0.042
Sweet-0.042
 polar-0.041
 ending-0.041
 mistake-0.040
Token the
Token ID262
Feature activation+2.05e-01

Pos logit contributions
ay+0.014
ong+0.014
rac+0.013
issors+0.013
 around+0.013
Neg logit contributions
Sleep-0.012
 polar-0.012
Sweet-0.012
 ending-0.012
 mistake-0.012
Token monster
Token ID9234
Feature activation-1.95e+00

Pos logit contributions
ay+0.007
ong+0.007
 around+0.007
rac+0.006
ars+0.006
Neg logit contributions
Sweet-0.006
Kids-0.006
Sleep-0.006
 polar-0.006
 mistake-0.006
Token's
Token ID338
Feature activation-2.22e+00

Pos logit contributions
Sweet+0.079
Sleep+0.078
 polar+0.077
Kids+0.077
 ending+0.077
Neg logit contributions
ay-0.051
ong-0.048
 around-0.048
rac-0.045
bs-0.043
Token breath
Token ID8033
Feature activation+5.97e+00

Pos logit contributions
 ending+0.067
Sleep+0.067
 polar+0.067
 mistake+0.065
 moment+0.064
Neg logit contributions
ay-0.082
rac-0.078
ong-0.077
issors-0.075
ors-0.073
Token on
Token ID319
Feature activation+5.66e-01

Pos logit contributions
rac+0.189
ay+0.188
ong+0.178
issors+0.178
ors+0.163
Neg logit contributions
Sleep-0.208
 ending-0.205
 moment-0.204
 polar-0.199
 mistake-0.195
Token his
Token ID465
Feature activation+8.03e-01

Pos logit contributions
ay+0.017
ong+0.016
rac+0.016
issors+0.015
 around+0.015
Neg logit contributions
 polar-0.021
Sleep-0.020
 ending-0.020
 mistake-0.020
Sweet-0.020
Token neck
Token ID7393
Feature activation+4.69e+00

Pos logit contributions
ay+0.034
ized+0.031
ors+0.031
issors+0.031
bs+0.031
Neg logit contributions
 mistake-0.021
 ending-0.020
 polar-0.020
 moment-0.020
 moral-0.018
Token.
Token ID13
Feature activation+3.68e-02

Pos logit contributions
ay+0.145
rac+0.137
ong+0.132
issors+0.128
bs+0.122
Neg logit contributions
Sleep-0.166
 mistake-0.166
 ending-0.164
 polar-0.163
 moment-0.162
Token
Token ID198
Feature activation+7.94e-01

Pos logit contributions
ay+0.001
ong+0.001
rac+0.001
 around+0.001
issors+0.001
Neg logit contributions
 ending-0.001
Sleep-0.001
 polar-0.001
 mistake-0.001
Sweet-0.001
Token day
Token ID1110
Feature activation+1.88e-01

Pos logit contributions
 former+0.087
 mistake+0.083
 forgiveness+0.083
Sleep+0.082
Sweet+0.082
Neg logit contributions
ay-0.089
 around-0.083
ong-0.076
 at-0.076
bs-0.075
Token,
Token ID11
Feature activation+1.08e-01

Pos logit contributions
ay+0.006
ong+0.006
issors+0.006
rac+0.006
ars+0.006
Neg logit contributions
 moment-0.006
 ending-0.006
Sweet-0.006
 pear-0.006
 Bird-0.006
Token the
Token ID262
Feature activation+2.44e-01

Pos logit contributions
ay+0.003
ong+0.003
rac+0.003
 around+0.003
bs+0.003
Neg logit contributions
Sleep-0.004
 polar-0.004
Sweet-0.004
 mistake-0.004
 ending-0.004
Token old
Token ID1468
Feature activation+2.09e-01

Pos logit contributions
ay+0.008
 around+0.007
 at+0.007
 past+0.007
bs+0.007
Neg logit contributions
 reality-0.008
 polar-0.008
fly-0.008
 sometime-0.008
 waterfall-0.008
Token girl
Token ID2576
Feature activation-7.20e-01

Pos logit contributions
ay+0.008
 around+0.008
 at+0.007
bs+0.007
s+0.007
Neg logit contributions
 reality-0.006
Sleep-0.006
 polar-0.006
 former-0.006
 forgiveness-0.006
Token went
Token ID1816
Feature activation-1.53e-01

Pos logit contributions
Sleep+0.025
Sweet+0.024
 polar+0.024
 ending+0.024
 mistake+0.024
Neg logit contributions
ay-0.023
ong-0.022
 around-0.022
rac-0.022
bs-0.021
Token outside
Token ID2354
Feature activation+2.22e-01

Pos logit contributions
Sleep+0.006
 polar+0.006
 ending+0.006
Sweet+0.006
 moment+0.006
Neg logit contributions
ay-0.004
ong-0.004
rac-0.004
issors-0.003
ars-0.003
Token to
Token ID284
Feature activation-2.31e-01

Pos logit contributions
ay+0.005
ong+0.005
rac+0.005
 around+0.004
issors+0.004
Neg logit contributions
Sleep-0.010
 polar-0.010
Sweet-0.010
 ending-0.010
 mistake-0.009
Token take
Token ID1011
Feature activation-7.79e-01

Pos logit contributions
Sweet+0.010
 ending+0.010
Sleep+0.009
 department+0.009
 mistake+0.009
Neg logit contributions
 around-0.006
ay-0.005
rac-0.005
ong-0.005
bs-0.005
Token a
Token ID257
Feature activation+2.32e-01

Pos logit contributions
Sleep+0.026
 polar+0.026
 ending+0.026
Sweet+0.026
 mistake+0.025
Neg logit contributions
ay-0.027
ong-0.025
 around-0.024
rac-0.024
bs-0.023
Token walk
Token ID2513
Feature activation-7.06e-01

Pos logit contributions
ay+0.009
ong+0.008
 around+0.008
bs+0.008
rac+0.007
Neg logit contributions
Sleep-0.007
Sweet-0.007
 ending-0.007
 former-0.007
Kids-0.007
Token boy
Token ID2933
Feature activation-1.37e+00

Pos logit contributions
Sleep+0.042
 former+0.040
Sweet+0.040
 ending+0.038
 mistake+0.038
Neg logit contributions
ay-0.100
ong-0.092
 around-0.091
bs-0.089
 at-0.087
Token named
Token ID3706
Feature activation-1.63e+00

Pos logit contributions
 polar+0.027
Sleep+0.027
Sweet+0.026
 ending+0.025
 mistake+0.025
Neg logit contributions
ay-0.065
ong-0.063
rac-0.062
 around-0.060
issors-0.060
Token Tim
Token ID5045
Feature activation+3.62e-02

Pos logit contributions
 mistake+0.042
Sleep+0.042
Sweet+0.042
 ending+0.042
 former+0.040
Neg logit contributions
ay-0.068
ong-0.065
 around-0.063
rac-0.062
issors-0.062
Tokenmy
Token ID1820
Feature activation-4.45e-01

Pos logit contributions
ay+0.002
ong+0.002
rac+0.002
 around+0.002
issors+0.002
Neg logit contributions
Sleep-0.001
 polar-0.001
Sweet-0.001
 ending-0.001
 mistake-0.001
Token.
Token ID13
Feature activation-3.91e-01

Pos logit contributions
 polar+0.015
Sleep+0.015
 mistake+0.015
 ending+0.015
Sweet+0.015
Neg logit contributions
ay-0.015
ong-0.015
rac-0.014
issors-0.013
ars-0.013
Token Tim
Token ID5045
Feature activation+1.45e-01

Pos logit contributions
Sleep+0.010
Sweet+0.010
 mistake+0.010
 polar+0.010
 ending+0.010
Neg logit contributions
ay-0.016
ong-0.015
 around-0.015
rac-0.015
issors-0.015
Tokenmy
Token ID1820
Feature activation-3.60e-01

Pos logit contributions
ay+0.007
 around+0.006
ong+0.006
rac+0.006
issors+0.006
Neg logit contributions
Sweet-0.003
Sleep-0.003
 ending-0.003
 polar-0.003
 mistake-0.003
Token loved
Token ID6151
Feature activation+1.83e+00

Pos logit contributions
Sleep+0.013
 polar+0.013
Sweet+0.013
 ending+0.013
 mistake+0.013
Neg logit contributions
ay-0.011
ong-0.010
rac-0.010
 around-0.010
issors-0.009
Token to
Token ID284
Feature activation-2.24e-01

Pos logit contributions
ay+0.050
ong+0.047
rac+0.045
ars+0.043
issors+0.043
Neg logit contributions
 polar-0.074
Sleep-0.073
Sweet-0.073
 ending-0.071
 mistake-0.070
Token play
Token ID711
Feature activation-6.58e-01

Pos logit contributions
Sleep+0.006
 polar+0.006
Sweet+0.006
 ending+0.006
 mistake+0.006
Neg logit contributions
ay-0.009
ong-0.008
rac-0.008
 around-0.008
issors-0.008
Token with
Token ID351
Feature activation+8.54e-01

Pos logit contributions
 polar+0.021
 bathroom+0.020
Are+0.020
 snow+0.020
 shelter+0.020
Neg logit contributions
ay-0.023
rac-0.022
ong-0.022
bs-0.022
issors-0.022
Token her
Token ID607
Feature activation+1.06e+00

Pos logit contributions
Sweet+0.026
Sleep+0.026
 ending+0.025
Kids+0.025
 polar+0.025
Neg logit contributions
ay-0.016
 around-0.014
ong-0.013
rac-0.013
issors-0.012
Token pocket
Token ID10000
Feature activation+3.05e+00

Pos logit contributions
ay+0.037
ong+0.034
rac+0.034
 around+0.033
issors+0.032
Neg logit contributions
Sleep-0.035
Sweet-0.035
 polar-0.034
 ending-0.034
Kids-0.033
Token.
Token ID13
Feature activation-1.83e-01

Pos logit contributions
ay+0.103
rac+0.097
ong+0.095
issors+0.092
ars+0.087
Neg logit contributions
Sleep-0.100
 mistake-0.098
 polar-0.097
 moment-0.096
 former-0.094
Token And
Token ID843
Feature activation-1.17e+00

Pos logit contributions
 mistake+0.008
 ending+0.007
 divorce+0.007
 polar+0.007
 moral+0.007
Neg logit contributions
ay-0.005
 around-0.004
rac-0.004
ong-0.004
bs-0.004
Token then
Token ID788
Feature activation-6.00e-01

Pos logit contributions
Sleep+0.045
 polar+0.043
 mistake+0.043
Sweet+0.043
 moral+0.042
Neg logit contributions
ay-0.035
 around-0.034
ong-0.031
rac-0.031
bs-0.031
Token she
Token ID673
Feature activation+1.56e+00

Pos logit contributions
Sleep+0.030
Sweet+0.029
 polar+0.028
Kids+0.028
 divorce+0.028
Neg logit contributions
ay-0.011
 around-0.011
ong-0.010
bs-0.010
 at-0.010
Token carried
Token ID5281
Feature activation+1.73e+00

Pos logit contributions
ay+0.055
ong+0.051
 around+0.051
rac+0.051
bs+0.048
Neg logit contributions
Sleep-0.050
Sweet-0.049
 ending-0.049
 polar-0.047
 moment-0.047
Token on
Token ID319
Feature activation+3.66e-01

Pos logit contributions
ong+0.056
rac+0.054
ay+0.054
issors+0.053
ars+0.050
Neg logit contributions
 moment-0.059
 polar-0.057
Sweet-0.057
Sleep-0.056
 Bird-0.055
Token with
Token ID351
Feature activation+9.43e-01

Pos logit contributions
ay+0.012
ong+0.011
rac+0.010
issors+0.010
ars+0.010
Neg logit contributions
Sleep-0.013
Sweet-0.013
 polar-0.013
 mistake-0.013
 ending-0.013
Token what
Token ID644
Feature activation-1.62e+00

Pos logit contributions
ay+0.030
ong+0.030
issors+0.029
rac+0.029
ars+0.028
Neg logit contributions
 polar-0.033
Sleep-0.032
 forgiveness-0.032
Sweet-0.032
 moment-0.031
Token she
Token ID673
Feature activation+1.59e+00

Pos logit contributions
Sleep+0.055
 polar+0.055
Sweet+0.054
 ending+0.053
 mistake+0.052
Neg logit contributions
ay-0.053
ong-0.050
rac-0.049
 around-0.049
bs-0.047
Token The
Token ID383
Feature activation-1.25e+00

Pos logit contributions
Sleep+0.012
 polar+0.012
Sweet+0.012
Kids+0.011
 moment+0.011
Neg logit contributions
ay-0.012
ong-0.011
rac-0.011
 around-0.011
issors-0.011
Token boat
Token ID8848
Feature activation-7.67e-01

Pos logit contributions
Sweet+0.043
Sleep+0.040
 former+0.038
Kids+0.037
 Jenkins+0.036
Neg logit contributions
ay-0.043
ong-0.043
 around-0.042
rac-0.042
ars-0.040
Token tried
Token ID3088
Feature activation+8.76e-01

Pos logit contributions
Sleep+0.024
 polar+0.023
Sweet+0.023
 ending+0.023
 mistake+0.023
Neg logit contributions
ay-0.028
ong-0.026
rac-0.026
 around-0.025
issors-0.025
Token to
Token ID284
Feature activation-1.20e-01

Pos logit contributions
 around+0.012
ong+0.010
ay+0.010
 at+0.010
rac+0.009
Neg logit contributions
Sleep-0.047
Kids-0.047
 polar-0.047
Sweet-0.046
 ending-0.045
Token drop
Token ID4268
Feature activation+1.27e+00

Pos logit contributions
Sweet+0.004
Sleep+0.004
 ending+0.004
Kids+0.004
 polar+0.004
Neg logit contributions
ong-0.004
ay-0.004
rac-0.004
 around-0.004
ars-0.003
Token the
Token ID262
Feature activation+5.14e-01

Pos logit contributions
ay+0.042
ong+0.041
rac+0.039
issors+0.039
ars+0.038
Neg logit contributions
 polar-0.042
 Bird-0.040
 moment-0.039
Sleep-0.039
 moral-0.039
Token anchor
Token ID18021
Feature activation+2.50e-01

Pos logit contributions
ay+0.022
ong+0.021
rac+0.021
issors+0.020
 around+0.020
Neg logit contributions
 polar-0.013
Sleep-0.012
 ending-0.012
 mistake-0.012
 moment-0.012
Token,
Token ID11
Feature activation+2.11e-01

Pos logit contributions
ay+0.008
rac+0.007
ong+0.007
issors+0.007
ars+0.007
Neg logit contributions
 polar-0.009
 ending-0.009
 mistake-0.009
 moment-0.009
Sleep-0.009
Token but
Token ID475
Feature activation+1.47e+00

Pos logit contributions
ay+0.008
ong+0.008
rac+0.008
 around+0.007
issors+0.007
Neg logit contributions
Sleep-0.006
 polar-0.006
Sweet-0.006
 ending-0.006
 mistake-0.006
Token it
Token ID340
Feature activation+3.41e-01

Pos logit contributions
ay+0.042
ong+0.039
rac+0.037
issors+0.036
 around+0.035
Neg logit contributions
 polar-0.057
Sleep-0.057
 ending-0.056
Sweet-0.056
 mistake-0.055
Token was
Token ID373
Feature activation+6.58e-02

Pos logit contributions
ay+0.013
ong+0.013
rac+0.012
 around+0.012
issors+0.012
Neg logit contributions
Sleep-0.010
Sweet-0.010
 polar-0.009
 ending-0.009
 mistake-0.009
Token the
Token ID262
Feature activation+3.01e-01

Pos logit contributions
 polar+0.039
 mistake+0.039
Sleep+0.038
 ending+0.038
 moment+0.038
Neg logit contributions
ay-0.032
ong-0.029
rac-0.029
issors-0.027
 around-0.027
Token fish
Token ID5916
Feature activation-4.36e-01

Pos logit contributions
ong+0.011
 around+0.011
ay+0.011
 at+0.010
rac+0.010
Neg logit contributions
Sleep-0.009
Sweet-0.009
 former-0.009
 department-0.008
tr-0.008
Token,
Token ID11
Feature activation+1.46e-01

Pos logit contributions
Sweet+0.018
Sleep+0.018
Kids+0.018
 polar+0.018
 ending+0.018
Neg logit contributions
ay-0.011
ong-0.010
 around-0.010
rac-0.010
bs-0.009
Token so
Token ID523
Feature activation-5.91e-01

Pos logit contributions
ay+0.004
ong+0.004
rac+0.004
 around+0.004
issors+0.004
Neg logit contributions
Sleep-0.005
Sweet-0.005
 polar-0.005
 ending-0.005
 mistake-0.005
Token it
Token ID340
Feature activation+1.23e-01

Pos logit contributions
Sleep+0.021
Sweet+0.021
 polar+0.021
 ending+0.021
 mistake+0.020
Neg logit contributions
ay-0.018
ong-0.018
rac-0.017
 around-0.017
bs-0.016
Token said
Token ID531
Feature activation+9.53e-01

Pos logit contributions
 around+0.004
rac+0.004
led+0.004
bs+0.004
ay+0.004
Neg logit contributions
Sweet-0.004
Sleep-0.004
 mistake-0.004
 ending-0.004
 forgiveness-0.004
Token,
Token ID11
Feature activation+1.57e-01

Pos logit contributions
ay+0.028
ong+0.027
rac+0.027
 around+0.026
bs+0.025
Neg logit contributions
Sleep-0.035
 polar-0.035
Sweet-0.035
Kids-0.035
 former-0.034
Token "
Token ID366
Feature activation+1.54e+00

Pos logit contributions
ay+0.006
ong+0.006
rac+0.006
issors+0.006
ars+0.006
Neg logit contributions
Sleep-0.004
Sweet-0.004
 moment-0.004
 polar-0.004
 moral-0.004
TokenI
Token ID40
Feature activation-3.50e-01

Pos logit contributions
ay+0.064
ong+0.060
rac+0.060
 around+0.058
issors+0.057
Neg logit contributions
 polar-0.040
 ending-0.039
Sleep-0.039
Sweet-0.038
 mistake-0.038
Token will
Token ID481
Feature activation+3.51e-01

Pos logit contributions
Sleep+0.011
Sweet+0.011
 polar+0.011
 ending+0.011
 mistake+0.011
Neg logit contributions
ay-0.012
ong-0.011
 around-0.011
rac-0.011
bs-0.011
Token lead
Token ID1085
Feature activation+6.91e-01

Pos logit contributions
ay+0.013
ong+0.012
rac+0.012
issors+0.011
 around+0.011
Neg logit contributions
 polar-0.011
Sleep-0.011
 ending-0.011
 mistake-0.011
 moment-0.010
Token Jack
Token ID3619
Feature activation+1.05e+00

Pos logit contributions
 around+0.026
 at+0.023
ay+0.021
rac+0.021
bs+0.021
Neg logit contributions
 polar-0.044
 former-0.043
 department-0.042
Sleep-0.042
 mistake-0.041
Token saw
Token ID2497
Feature activation+2.75e-01

Pos logit contributions
ay+0.041
ong+0.039
rac+0.038
 around+0.037
issors+0.036
Neg logit contributions
Sleep-0.029
 polar-0.029
Sweet-0.029
 ending-0.029
 mistake-0.028
Token her
Token ID607
Feature activation+9.45e-01

Pos logit contributions
 around+0.006
ay+0.006
ong+0.005
rac+0.005
bs+0.005
Neg logit contributions
 polar-0.012
Sleep-0.012
 ending-0.012
Sweet-0.012
 former-0.012
Token crying
Token ID13774
Feature activation-3.00e+00

Pos logit contributions
 around+0.032
ong+0.031
ay+0.031
 at+0.029
bs+0.028
Neg logit contributions
Kids-0.033
Sleep-0.032
Sweet-0.032
Are-0.029
 polar-0.029
Token and
Token ID290
Feature activation-5.32e-02

Pos logit contributions
Sweet+0.144
Sleep+0.142
 polar+0.140
Kids+0.139
 former+0.136
Neg logit contributions
 around-0.062
ay-0.061
ong-0.056
 at-0.054
led-0.048
Token helped
Token ID4193
Feature activation-6.71e-01

Pos logit contributions
Sleep+0.002
Sweet+0.002
 former+0.002
 ending+0.002
 moment+0.002
Neg logit contributions
 around-0.001
 at-0.001
rac-0.001
ong-0.001
bs-0.001
Token her
Token ID607
Feature activation+9.62e-01

Pos logit contributions
Sleep+0.026
 polar+0.026
Sweet+0.026
 ending+0.026
 mistake+0.026
Neg logit contributions
ay-0.019
ong-0.017
rac-0.017
 around-0.016
issors-0.016
Token pick
Token ID2298
Feature activation-1.08e+00

Pos logit contributions
 around+0.029
ay+0.029
ong+0.028
rac+0.027
bs+0.026
Neg logit contributions
Sleep-0.036
Sweet-0.035
Kids-0.034
 ending-0.034
 polar-0.034
Token up
Token ID510
Feature activation+9.34e-01

Pos logit contributions
Sleep+0.051
Sweet+0.050
 ending+0.050
 polar+0.050
 mistake+0.049
Neg logit contributions
ay-0.022
ong-0.020
 around-0.019
rac-0.018
issors-0.017
Token all
Token ID477
Feature activation+8.79e-01

Pos logit contributions
ay+0.023
 around+0.022
ong+0.022
rac+0.020
bs+0.020
Neg logit contributions
Sleep-0.040
Sweet-0.039
 polar-0.039
 ending-0.039
Kids-0.038
Token the
Token ID262
Feature activation+9.66e-02

Pos logit contributions
ay+0.024
ong+0.022
rac+0.021
 around+0.021
issors+0.020
Neg logit contributions
Sleep-0.035
 polar-0.035
Sweet-0.035
 ending-0.035
 mistake-0.034
Token eyel
Token ID29708
Feature activation+6.86e-01

Pos logit contributions
ay+0.044
ong+0.043
rac+0.042
ors+0.040
ars+0.040
Neg logit contributions
 ending-0.029
Sweet-0.029
 mistake-0.029
Sleep-0.028
 moment-0.028
Tokenids
Token ID2340
Feature activation+2.75e+00

Pos logit contributions
ay+0.019
rac+0.018
 around+0.017
ong+0.017
ized+0.017
Neg logit contributions
 polar-0.025
Sweet-0.025
 ending-0.025
Sleep-0.025
 former-0.025
Token and
Token ID290
Feature activation+2.50e-01

Pos logit contributions
ay+0.099
rac+0.094
issors+0.094
ong+0.091
ars+0.089
Neg logit contributions
 moment-0.081
 again-0.078
 ending-0.076
 raining-0.073
Sleep-0.072
Token cheeks
Token ID25839
Feature activation+1.83e+00

Pos logit contributions
ay+0.009
ong+0.008
rac+0.008
issors+0.008
 around+0.008
Neg logit contributions
Sweet-0.008
Sleep-0.008
 polar-0.008
 ending-0.008
 mistake-0.008
Token.
Token ID13
Feature activation-5.44e-02

Pos logit contributions
rac+0.067
ay+0.066
issors+0.064
ars+0.060
ong+0.058
Neg logit contributions
 again-0.054
 moment-0.053
 ending-0.053
Sleep-0.051
 department-0.050
Token It
Token ID632
Feature activation-7.24e-01

Pos logit contributions
 polar+0.002
 mistake+0.002
 ending+0.002
Sleep+0.002
 divorce+0.002
Neg logit contributions
ay-0.002
 around-0.001
ong-0.001
rac-0.001
bs-0.001
Token was
Token ID373
Feature activation-8.07e-02

Pos logit contributions
Sleep+0.022
 polar+0.021
Sweet+0.021
 ending+0.020
 mistake+0.020
Neg logit contributions
ay-0.027
 around-0.026
ong-0.026
rac-0.025
bs-0.024
Token fun
Token ID1257
Feature activation+1.17e+00

Pos logit contributions
Sleep+0.003
 polar+0.003
 ending+0.003
Sweet+0.003
 mistake+0.003
Neg logit contributions
ay-0.003
ong-0.002
rac-0.002
 around-0.002
issors-0.002
Token to
Token ID284
Feature activation-1.50e-01

Pos logit contributions
rac+0.032
ay+0.032
ong+0.031
issors+0.029
ars+0.029
Neg logit contributions
 ending-0.045
 moment-0.045
 mistake-0.045
Sweet-0.044
Sleep-0.043
Token watch
Token ID2342
Feature activation-9.35e-01

Pos logit contributions
Sleep+0.005
 polar+0.005
Sweet+0.005
 ending+0.005
 mistake+0.005
Neg logit contributions
ay-0.005
ong-0.005
rac-0.005
 around-0.005
issors-0.004
Token her
Token ID607
Feature activation+1.12e+00

Pos logit contributions
 ending+0.032
Sleep+0.032
Sweet+0.032
 polar+0.032
 mistake+0.032
Neg logit contributions
ay-0.028
rac-0.027
ong-0.027
ars-0.026
issors-0.026
Token,
Token ID11
Feature activation+4.18e-01

Pos logit contributions
Sleep+0.062
 polar+0.062
Sweet+0.061
 ending+0.061
 mistake+0.060
Neg logit contributions
ay-0.040
ong-0.038
rac-0.036
 around-0.035
issors-0.034
Token but
Token ID475
Feature activation+1.32e+00

Pos logit contributions
 around+0.013
ong+0.012
ay+0.011
rac+0.011
 at+0.011
Neg logit contributions
Sleep-0.016
Sweet-0.016
Kids-0.015
 ending-0.015
 polar-0.015
Token she
Token ID673
Feature activation+1.58e+00

Pos logit contributions
ay+0.042
ong+0.039
rac+0.037
issors+0.036
 around+0.036
Neg logit contributions
Sleep-0.047
 ending-0.047
Sweet-0.046
 polar-0.046
 moment-0.045
Token was
Token ID373
Feature activation-9.86e-02

Pos logit contributions
ay+0.068
ong+0.064
rac+0.062
issors+0.060
 around+0.059
Neg logit contributions
 polar-0.041
Sleep-0.039
 ending-0.039
Sweet-0.038
 mistake-0.038
Token a
Token ID257
Feature activation+4.01e-01

Pos logit contributions
Sleep+0.003
Sweet+0.003
 polar+0.003
 ending+0.003
Kids+0.003
Neg logit contributions
ay-0.003
ong-0.003
 around-0.003
rac-0.003
issors-0.003
Token little
Token ID1310
Feature activation-1.89e+00

Pos logit contributions
 around+0.011
ay+0.010
 high+0.010
bs+0.010
 at+0.010
Neg logit contributions
Sleep-0.015
 former-0.014
Sweet-0.014
 forgiveness-0.014
riage-0.014
Token scared
Token ID12008
Feature activation-9.04e-03

Pos logit contributions
Sleep+0.076
Sweet+0.074
 ending+0.072
Kids+0.071
 moral+0.070
Neg logit contributions
 around-0.051
ay-0.049
ong-0.048
bs-0.047
 at-0.046
Token.
Token ID13
Feature activation-1.33e-01

Pos logit contributions
 former+0.000
Sleep+0.000
Sweet+0.000
 ending+0.000
 mistake+0.000
Neg logit contributions
ay-0.000
 around-0.000
 at-0.000
ong-0.000
bs-0.000
Token
Token ID198
Feature activation+1.92e-01

Pos logit contributions
Sleep+0.004
 polar+0.004
Sweet+0.004
 ending+0.004
 mistake+0.004
Neg logit contributions
ay-0.005
ong-0.005
rac-0.004
 around-0.004
issors-0.004
Token
Token ID198
Feature activation+1.05e-01

Pos logit contributions
ong+0.008
ay+0.008
rac+0.008
issors+0.008
ors+0.007
Neg logit contributions
Sleep-0.005
Sweet-0.005
 moment-0.005
 polar-0.004
Kids-0.004
Token"
Token ID1
Feature activation+2.49e+00

Pos logit contributions
ay+0.005
ong+0.005
rac+0.005
issors+0.005
ors+0.005
Neg logit contributions
Sleep-0.002
Sweet-0.002
 ending-0.002
 moment-0.002
 moral-0.002
Token friends
Token ID2460
Feature activation+5.64e-01

Pos logit contributions
Sleep+0.007
 polar+0.006
Sweet+0.006
 ending+0.006
 mistake+0.006
Neg logit contributions
ay-0.007
ong-0.007
rac-0.007
 around-0.007
issors-0.007
Token and
Token ID290
Feature activation-1.05e-01

Pos logit contributions
ay+0.017
ong+0.016
rac+0.016
issors+0.015
 around+0.014
Neg logit contributions
Sleep-0.021
 ending-0.021
Sweet-0.021
 polar-0.021
 mistake-0.020
Token sailed
Token ID33835
Feature activation+3.50e-01

Pos logit contributions
Sleep+0.004
 polar+0.004
 mistake+0.004
Sweet+0.004
 moral+0.004
Neg logit contributions
 around-0.003
bs-0.003
ay-0.003
 at-0.003
rac-0.003
Token on
Token ID319
Feature activation+2.44e-01

Pos logit contributions
ong+0.011
ay+0.011
issors+0.011
rac+0.011
ors+0.010
Neg logit contributions
 moment-0.012
 ending-0.012
 polar-0.011
Sleep-0.011
 mistake-0.011
Token the
Token ID262
Feature activation+1.17e-01

Pos logit contributions
ay+0.007
 around+0.007
ong+0.007
rac+0.006
bs+0.006
Neg logit contributions
Sleep-0.009
 polar-0.009
Sweet-0.009
 ending-0.009
Kids-0.009
Token lake
Token ID13546
Feature activation-1.38e+00

Pos logit contributions
ong+0.005
ay+0.005
 around+0.005
rac+0.004
ars+0.004
Neg logit contributions
Sweet-0.003
Sleep-0.003
Kids-0.003
Are-0.003
 department-0.003
Token together
Token ID1978
Feature activation-2.52e-01

Pos logit contributions
 ending+0.054
 polar+0.054
Sleep+0.054
 moment+0.053
 mistake+0.053
Neg logit contributions
ay-0.038
ong-0.035
rac-0.035
issors-0.033
bs-0.031
Token every
Token ID790
Feature activation+3.33e+00

Pos logit contributions
 ending+0.009
 moment+0.009
 again+0.008
 mistake+0.008
 moral+0.008
Neg logit contributions
ay-0.008
rac-0.008
issors-0.008
ong-0.008
ors-0.007
Token week
Token ID1285
Feature activation-1.24e-01

Pos logit contributions
 around+0.102
ay+0.100
 at+0.090
 forward+0.088
 high+0.086
Neg logit contributions
Sweet-0.127
 former-0.126
 charity-0.123
 department-0.122
 forgiveness-0.122
Token.
Token ID13
Feature activation-5.35e-01

Pos logit contributions
 ending+0.005
Sleep+0.005
 moment+0.005
 polar+0.004
Sweet+0.004
Neg logit contributions
ay-0.004
ong-0.003
rac-0.003
issors-0.003
ars-0.003
Token<|endoftext|>
Token ID50256
Feature activation-1.01e+00

Pos logit contributions
 mistake+0.026
 department+0.025
 polar+0.024
 gen+0.024
 forgiveness+0.024
Neg logit contributions
ay-0.013
 around-0.009
s-0.009
bs-0.008
ables-0.008
Token mar
Token ID1667
Feature activation+1.08e+00

Pos logit contributions
ay+0.044
ong+0.042
rac+0.041
 around+0.041
issors+0.040
Neg logit contributions
Sleep-0.034
Sweet-0.034
 polar-0.033
 ending-0.033
 mistake-0.032
Tokenbles
Token ID7689
Feature activation+2.29e+00

Pos logit contributions
rac+0.040
ay+0.039
ong+0.039
bs+0.038
ned+0.038
Neg logit contributions
 polar-0.027
 pear-0.027
 tunnel-0.026
ulu-0.025
 island-0.025
Token.
Token ID13
Feature activation-3.80e-01

Pos logit contributions
ay+0.066
ong+0.061
rac+0.060
issors+0.056
 around+0.055
Neg logit contributions
Sleep-0.087
 polar-0.086
 ending-0.085
Sweet-0.085
 mistake-0.084
Token She
Token ID1375
Feature activation+2.93e-01

Pos logit contributions
Sleep+0.013
 polar+0.013
Sweet+0.013
 ending+0.013
 mistake+0.013
Neg logit contributions
ay-0.012
ong-0.012
rac-0.011
 around-0.011
issors-0.011
Token only
Token ID691
Feature activation-1.24e+00

Pos logit contributions
ay+0.012
ong+0.012
rac+0.011
issors+0.011
ors+0.011
Neg logit contributions
 polar-0.007
 ending-0.007
Sleep-0.007
 moment-0.007
Sweet-0.007
Token had
Token ID550
Feature activation-7.78e-01

Pos logit contributions
Sleep+0.039
Sweet+0.038
 polar+0.037
 ending+0.037
 mistake+0.037
Neg logit contributions
ay-0.045
ong-0.042
 around-0.042
rac-0.041
bs-0.040
Token two
Token ID734
Feature activation-2.77e+00

Pos logit contributions
Sleep+0.027
Sweet+0.026
 polar+0.026
 ending+0.026
 mistake+0.026
Neg logit contributions
ay-0.025
ong-0.024
 around-0.024
rac-0.023
bs-0.022
Token mar
Token ID1667
Feature activation+1.09e+00

Pos logit contributions
 polar+0.084
 moral+0.075
 pand+0.075
 pear+0.075
 ending+0.074
Neg logit contributions
ay-0.104
rac-0.103
ong-0.101
issors-0.098
ors-0.094
Tokenbles
Token ID7689
Feature activation+2.31e+00

Pos logit contributions
rac+0.040
ay+0.039
ong+0.039
ned+0.038
issors+0.037
Neg logit contributions
 polar-0.029
 pear-0.027
 pand-0.027
ulu-0.026
 gn-0.025
Token and
Token ID290
Feature activation+1.37e-01

Pos logit contributions
ay+0.060
rac+0.055
ong+0.055
issors+0.051
 around+0.049
Neg logit contributions
 polar-0.093
 ending-0.092
Sleep-0.092
Sweet-0.091
 mistake-0.090
Token enjoyed
Token ID8359
Feature activation-3.14e-01

Pos logit contributions
ay+0.005
ong+0.005
rac+0.005
 around+0.005
issors+0.004
Neg logit contributions
Sleep-0.004
 polar-0.004
Sweet-0.004
 ending-0.004
 mistake-0.004
Token teeth
Token ID9941
Feature activation+3.61e+00

Pos logit contributions
Sleep+0.005
Sweet+0.005
Kids+0.005
 polar+0.004
 ending+0.004
Neg logit contributions
ay-0.005
ong-0.005
 around-0.004
rac-0.004
bs-0.004
Token.
Token ID13
Feature activation+1.84e-01

Pos logit contributions
ay+0.106
rac+0.099
ong+0.098
issors+0.094
bs+0.088
Neg logit contributions
Sleep-0.135
 polar-0.132
 ending-0.131
Sweet-0.131
 mistake-0.130
Token
Token ID198
Feature activation+6.69e-01

Pos logit contributions
ay+0.005
rac+0.005
issors+0.005
 around+0.005
ong+0.004
Neg logit contributions
 ending-0.007
 mistake-0.007
Sleep-0.007
 polar-0.007
Sweet-0.007
Token
Token ID198
Feature activation+5.19e-01

Pos logit contributions
ay+0.023
ong+0.021
rac+0.020
 around+0.020
issors+0.020
Neg logit contributions
 ending-0.023
 polar-0.022
Sleep-0.022
Sweet-0.022
 department-0.022
Token"
Token ID1
Feature activation+2.49e+00

Pos logit contributions
ay+0.016
rac+0.015
ong+0.015
issors+0.015
ars+0.015
Neg logit contributions
 ending-0.019
 polar-0.018
 mistake-0.018
 department-0.018
Sleep-0.018
TokenHey
Token ID10814
Feature activation-4.71e+00

Pos logit contributions
rac+0.076
ay+0.073
ars+0.072
issors+0.066
bs+0.066
Neg logit contributions
 mistake-0.095
 ending-0.089
 polar-0.088
 ig-0.086
 former-0.084
Token,
Token ID11
Feature activation+1.55e-01

Pos logit contributions
Sleep+0.237
Sweet+0.232
 former+0.230
Kids+0.223
 ending+0.221
Neg logit contributions
ay-0.089
ong-0.081
 around-0.075
rac-0.072
 at-0.066
Token stop
Token ID2245
Feature activation-2.20e+00

Pos logit contributions
ay+0.005
ong+0.005
 around+0.005
rac+0.004
 at+0.004
Neg logit contributions
 former-0.006
Sleep-0.006
Sweet-0.006
 ending-0.005
 moment-0.005
Token that
Token ID326
Feature activation-9.49e-01

Pos logit contributions
Sleep+0.097
Sweet+0.096
 ending+0.095
 polar+0.095
 mistake+0.092
Neg logit contributions
ay-0.051
ong-0.047
 around-0.045
rac-0.045
issors-0.041
Token!"
Token ID2474
Feature activation+2.62e-03

Pos logit contributions
Sleep+0.045
Sweet+0.045
Kids+0.044
 former+0.043
 polar+0.043
Neg logit contributions
ay-0.020
ong-0.019
 around-0.018
rac-0.015
 at-0.015
Token their
Token ID511
Feature activation-9.09e-01

Pos logit contributions
ay+0.000
ong+0.000
rac+0.000
 around+0.000
issors+0.000
Neg logit contributions
Sleep-0.000
 polar-0.000
Sweet-0.000
 ending-0.000
 mistake-0.000
Token
Token ID198
Feature activation+3.63e-01

Pos logit contributions
ay+0.017
ong+0.016
rac+0.016
 around+0.015
issors+0.015
Neg logit contributions
 ending-0.015
Sleep-0.015
 polar-0.015
Sweet-0.015
 mistake-0.015
TokenM
Token ID44
Feature activation-8.04e-02

Pos logit contributions
ay+0.015
rac+0.014
issors+0.014
ars+0.014
 around+0.014
Neg logit contributions
 ending-0.010
 polar-0.009
 funeral-0.009
fly-0.009
 department-0.009
Tokenoral
Token ID6864
Feature activation-4.41e+00

Pos logit contributions
Sleep+0.002
 polar+0.002
Sweet+0.002
 moment+0.002
Are+0.002
Neg logit contributions
ay-0.004
ong-0.003
rac-0.003
issors-0.003
ars-0.003
Token of
Token ID286
Feature activation-2.14e+00

Pos logit contributions
Sleep+0.182
 polar+0.180
Sweet+0.180
 ending+0.179
 mistake+0.176
Neg logit contributions
ay-0.114
ong-0.107
rac-0.103
 around-0.099
issors-0.096
Token the
Token ID262
Feature activation+9.08e-02

Pos logit contributions
 department+0.100
 former+0.100
 ending+0.097
Sweet+0.096
 polar+0.096
Neg logit contributions
ay-0.042
 around-0.042
rac-0.035
ong-0.033
 at-0.029
Token story
Token ID1621
Feature activation-4.28e+00

Pos logit contributions
ay+0.004
ong+0.004
 around+0.004
issors+0.003
rac+0.003
Neg logit contributions
 polar-0.002
 former-0.002
fly-0.002
Sleep-0.002
Are-0.002
Token:
Token ID25
Feature activation-2.22e+00

Pos logit contributions
Sleep+0.157
 polar+0.156
Sweet+0.155
 ending+0.154
 mistake+0.151
Neg logit contributions
ay-0.130
ong-0.122
rac-0.118
 around-0.115
issors-0.112
Token It
Token ID632
Feature activation-8.56e-01

Pos logit contributions
 polar+0.077
 ending+0.074
Sweet+0.072
Sleep+0.072
Kids+0.071
Neg logit contributions
ay-0.072
 around-0.070
rac-0.068
issors-0.066
ors-0.063
Token's
Token ID338
Feature activation-2.24e+00

Pos logit contributions
 polar+0.030
Sleep+0.030
Sweet+0.030
 ending+0.030
 mistake+0.029
Neg logit contributions
ay-0.027
ong-0.025
rac-0.025
 around-0.024
issors-0.023
Token important
Token ID1593
Feature activation-9.70e-01

Pos logit contributions
 polar+0.084
Sweet+0.082
Kids+0.079
 department+0.078
Sleep+0.078
Neg logit contributions
ay-0.066
rac-0.063
 around-0.062
issors-0.061
ong-0.058
Token to
Token ID284
Feature activation-2.76e-01

Pos logit contributions
Sleep+0.044
 polar+0.043
Sweet+0.043
 ending+0.043
 mistake+0.042
Neg logit contributions
ay-0.022
ong-0.020
rac-0.019
 around-0.018
issors-0.018
Token would
Token ID561
Feature activation+1.12e+00

Pos logit contributions
ay+0.051
 around+0.049
ong+0.047
rac+0.047
bs+0.047
Neg logit contributions
 polar-0.046
 ending-0.045
Sleep-0.045
Sweet-0.044
 moment-0.044
Token not
Token ID407
Feature activation-7.13e-01

Pos logit contributions
ay+0.039
ong+0.037
 around+0.036
rac+0.036
issors+0.036
Neg logit contributions
Sweet-0.036
 polar-0.035
Sleep-0.035
Kids-0.034
 ending-0.034
Token touch
Token ID3638
Feature activation-1.20e+00

Pos logit contributions
Sweet+0.026
Sleep+0.025
 polar+0.025
Kids+0.024
 ending+0.024
Neg logit contributions
ay-0.023
 around-0.022
ong-0.022
bs-0.021
issors-0.021
Token her
Token ID607
Feature activation+1.23e+00

Pos logit contributions
Sleep+0.044
Sweet+0.043
 ending+0.043
 polar+0.043
 mistake+0.042
Neg logit contributions
ay-0.037
ong-0.035
 around-0.034
rac-0.033
issors-0.032
Token makeup
Token ID16029
Feature activation-2.55e+00

Pos logit contributions
ay+0.035
 around+0.033
ong+0.032
bs+0.029
 at+0.029
Neg logit contributions
Sleep-0.051
Sweet-0.050
 polar-0.050
Kids-0.049
 ending-0.047
Token again
Token ID757
Feature activation-4.94e+00

Pos logit contributions
Sleep+0.055
 ending+0.055
 mistake+0.054
Sweet+0.054
 polar+0.054
Neg logit contributions
ay-0.113
ong-0.108
rac-0.108
issors-0.104
 around-0.103
Token.
Token ID13
Feature activation+2.99e-01

Pos logit contributions
Sleep+0.204
 polar+0.202
Sweet+0.202
 ending+0.199
 mistake+0.194
Neg logit contributions
ay-0.128
ong-0.119
rac-0.114
 around-0.112
issors-0.107
Token Sara
Token ID24799
Feature activation+4.28e-01

Pos logit contributions
ay+0.008
ong+0.007
rac+0.007
 around+0.007
issors+0.007
Neg logit contributions
 polar-0.012
 ending-0.012
Sleep-0.011
Sweet-0.011
 mistake-0.011
Token forg
Token ID5784
Feature activation-1.91e+00

Pos logit contributions
ay+0.013
 around+0.013
rac+0.013
ong+0.012
ars+0.012
Neg logit contributions
 polar-0.015
 ending-0.015
Sleep-0.015
 former-0.015
Sweet-0.014
Tokenave
Token ID1015
Feature activation-3.76e-01

Pos logit contributions
Sleep+0.078
Sweet+0.076
Kids+0.075
 ending+0.075
 forgiveness+0.072
Neg logit contributions
ay-0.048
rac-0.047
ong-0.046
issors-0.044
itching-0.043
Token him
Token ID683
Feature activation+1.77e+00

Pos logit contributions
Sleep+0.018
 ending+0.018
Sweet+0.018
 polar+0.018
 mistake+0.018
Neg logit contributions
ay-0.007
ong-0.006
rac-0.006
 around-0.006
issors-0.005
Token for
Token ID329
Feature activation+2.41e+00

Pos logit contributions
ay+0.032
 around+0.031
ong+0.030
bs+0.028
rac+0.028
Neg logit contributions
Sleep-0.057
Sweet-0.057
 polar-0.056
Kids-0.056
 ending-0.054
Token selling
Token ID6301
Feature activation-3.40e+00

Pos logit contributions
ong+0.071
 around+0.069
ay+0.068
rac+0.067
 at+0.066
Neg logit contributions
Sweet-0.086
Sleep-0.084
Kids-0.083
 polar-0.083
 ending-0.080
Token them
Token ID606
Feature activation+3.56e-01

Pos logit contributions
 mistake+0.093
 polar+0.092
 forgiveness+0.089
Sleep+0.089
 ending+0.089
Neg logit contributions
ay-0.134
rac-0.127
ong-0.126
issors-0.124
ors-0.120
Token a
Token ID257
Feature activation+6.52e-02

Pos logit contributions
ay+0.009
ong+0.009
rac+0.008
 around+0.008
issors+0.008
Neg logit contributions
Sleep-0.015
 polar-0.015
Sweet-0.015
 ending-0.014
 mistake-0.014
Token bad
Token ID2089
Feature activation-1.73e+00

Pos logit contributions
ay+0.002
ong+0.002
 around+0.002
bs+0.002
 high+0.002
Neg logit contributions
Kids-0.002
Sweet-0.002
Sleep-0.002
 former-0.002
 polar-0.002
Token movie
Token ID3807
Feature activation-4.38e+00

Pos logit contributions
Sweet+0.051
Sleep+0.047
 former+0.047
Kids+0.046
Are+0.045
Neg logit contributions
ay-0.067
 around-0.063
ong-0.061
 at-0.058
ars-0.057
Token.
Token ID13
Feature activation-3.09e-01

Pos logit contributions
Sleep+0.169
 polar+0.168
 ending+0.167
Sweet+0.166
 mistake+0.164
Neg logit contributions
ay-0.123
ong-0.115
rac-0.112
 around-0.106
issors-0.106
Token The
Token ID383
Feature activation-1.57e+00

Pos logit contributions
Sweet+0.012
 moment+0.012
Sleep+0.012
 polar+0.012
 mistake+0.012
Neg logit contributions
ay-0.008
issors-0.007
rac-0.007
 around-0.007
ong-0.007
Token man
Token ID582
Feature activation+1.30e+00

Pos logit contributions
Sweet+0.050
Sleep+0.048
 former+0.047
fly+0.047
 polar+0.046
Neg logit contributions
ay-0.055
ong-0.052
 around-0.051
ars-0.051
rac-0.049
Token felt
Token ID2936
Feature activation+2.76e-01

Pos logit contributions
ay+0.042
 around+0.041
ong+0.039
rac+0.039
ars+0.038
Neg logit contributions
Sleep-0.045
Sweet-0.044
 polar-0.043
 ending-0.043
 former-0.042
Token very
Token ID845
Feature activation+8.03e-01

Pos logit contributions
ay+0.010
ong+0.009
rac+0.009
issors+0.009
 around+0.009
Neg logit contributions
Sleep-0.009
 polar-0.009
 ending-0.009
Sweet-0.008
 mistake-0.008
Token drink
Token ID4144
Feature activation-1.20e+00

Pos logit contributions
 polar+0.009
Sleep+0.009
Sweet+0.009
 ending+0.009
 mistake+0.009
Neg logit contributions
ay-0.013
ong-0.012
rac-0.012
 around-0.012
issors-0.012
Token water
Token ID1660
Feature activation+4.20e-01

Pos logit contributions
Sleep+0.038
 polar+0.038
Sweet+0.037
 ending+0.037
 mistake+0.036
Neg logit contributions
ay-0.043
ong-0.040
 around-0.039
rac-0.039
issors-0.037
Token from
Token ID422
Feature activation-1.19e+00

Pos logit contributions
ay+0.014
ong+0.013
rac+0.013
issors+0.012
ars+0.012
Neg logit contributions
Sleep-0.014
 polar-0.014
 ending-0.014
 moment-0.013
 mistake-0.013
Token the
Token ID262
Feature activation+1.64e-01

Pos logit contributions
Sleep+0.046
Sweet+0.046
 polar+0.045
 ending+0.045
 mistake+0.044
Neg logit contributions
ay-0.034
ong-0.032
 around-0.031
rac-0.031
issors-0.029
Token f
Token ID277
Feature activation-7.91e-01

Pos logit contributions
ay+0.006
 around+0.006
ong+0.006
 high+0.005
rac+0.005
Neg logit contributions
Sweet-0.005
 mistake-0.005
Sleep-0.005
 forgiveness-0.005
 ending-0.005
Tokenauc
Token ID14272
Feature activation-5.06e+00

Pos logit contributions
Sleep+0.011
Kids+0.011
 polar+0.011
Sweet+0.011
 department+0.010
Neg logit contributions
ay-0.040
rac-0.039
ong-0.037
 around-0.037
ars-0.037
Tokenet
Token ID316
Feature activation+2.32e+00

Pos logit contributions
Sleep+0.181
 polar+0.179
 ending+0.179
 mistake+0.177
Kids+0.177
Neg logit contributions
ay-0.157
ong-0.147
rac-0.142
issors-0.127
 around-0.125
Token but
Token ID475
Feature activation+1.16e+00

Pos logit contributions
ay+0.064
ong+0.060
rac+0.057
 around+0.056
issors+0.054
Neg logit contributions
Sleep-0.092
 polar-0.091
Sweet-0.091
 ending-0.090
 mistake-0.089
Token she
Token ID673
Feature activation+1.33e+00

Pos logit contributions
ay+0.042
ong+0.041
rac+0.039
issors+0.038
 around+0.037
Neg logit contributions
Sleep-0.036
 ending-0.035
Sweet-0.035
 polar-0.035
 mistake-0.034
Token was
Token ID373
Feature activation-2.23e-01

Pos logit contributions
ay+0.051
ong+0.049
rac+0.048
 around+0.047
issors+0.046
Neg logit contributions
Sleep-0.038
 polar-0.038
Sweet-0.037
 ending-0.037
 mistake-0.036
Token too
Token ID1165
Feature activation-1.83e+00

Pos logit contributions
 polar+0.008
Sleep+0.008
Sweet+0.008
 ending+0.008
Kids+0.008
Neg logit contributions
ay-0.007
 around-0.006
ong-0.006
rac-0.006
issors-0.006