TOP ACTIVATIONS
MAX = 0.204

more of the hairy cater pill ars . <|endoftext|> Once there
Lily , no . Cater pill ars are not for keeping
. Soon , more cater pill ars arrived . They also
and watched as the cater pill ars grew bigger and bigger
saw lots of colourful cater pill ars and an old lady
know , Lily . Cater pill ars need leaves and air
Did you know that cater pill ars turn into beautiful butterflies
he noticed some other cater pill ars stretching towards it too
but he also knew cater pill ars were not pets .
doing here ?" the zo oke eper asked . " You
careful , Lily . Cater pill ars can be tricky .
ily liked to keep cater pill ars in a jar .
, okay ?" the zo oke eper said .
back , but the zo oke eper told her that it
you , Lily . Cater pill ars can leave and never
, " I love cater pill ars ! You can be
said , " C ater pill ars are not meant to
and lady bugs and cater pill ars ." Tim
put it back . Cater pill ars need to eat leaves
, kids !" the zo oke eper said . " The

MIN ACTIVATIONS
MIN = -0.132

dad put Joe on his shoulders so he could reach the
of herself and showed her mom what she had done .
Tim my showed his mom the mark and asked ,
his tail and l icks mom 's hand . Mom says
came out and hugged her mom . She said , "
went inside and showed her mom the bulb . Her mom
ambulance came and took their mom to the hospital . The
up and put on her mom 's clothes . One day
ran home and showed his mom his new cap . From
arrived home and showed her mom the nail . Her mom
doctor . He handed her mom a piece of paper with
She showed her mom and dad her drawing .
. Lily climbs on his shoulders . She holds the stick
and carried her on his shoulders . She gigg led and
she would and gave her mom a big hug . From
her house and showed her mom the bad boo - bo
They showed their mom the crystals they found .
picture . She showed her mom , who smiled and said
went home and showed her mom the bracelet . Her mom
She ran and pulled her mom 's hand down the hallway

INTERVAL 0.120 - 0.204
CONTAINS 0.014%

hill . The rh in oc eros said , � �
. She thanked the zo oke eper for his advice and
big ostr ich . The ostr ich liked to swim .
trapped with the rh in oc eros . They looked for
," said the rh in oc eros . " I 'm

INTERVAL 0.036 - 0.120
CONTAINS 9.001%

trips , they encountered an elderly person . This elderly person
day long . He was very happy . One
and it got bigger and bigger . Everyone could hear it
The sun had made the plastic soft and bend y .
when she was done , Fre ya realized that the stair

INTERVAL -0.048 - 0.036
CONTAINS 85.741%

Her mom said , " That is a jelly fish .
shy anymore . They talk and laugh and share . They
Yes please !" Amy said . The owner smiled
They wear pretty dresses and hats . They dance to music
! Willie apologized and gave the car back to her .

INTERVAL -0.132 - -0.048
CONTAINS 5.244%

M um smiled and hugged Dad . Then they packed their
. She said to her mom my , " Mom my
to bring light to her friend , she noticed that he
together . They learned a lesson that day . They learned
day ever for Cindy ! <|endoftext|> Once upon a time ,
Token more
Token ID517
Feature activation+2.10e-02

Pos logit contributions
fters+0.131
oke+0.110
wheel+0.109
ner+0.109
zel+0.108
Neg logit contributions
by-0.053
 luck-0.050
 hopes-0.048
 hugs-0.047
 eyes-0.047
Token of
Token ID286
Feature activation+4.67e-02

Pos logit contributions
fters+0.050
wheel+0.041
isin+0.041
ner+0.041
oke+0.041
Neg logit contributions
by-0.023
 luck-0.021
 hopes-0.021
 flashlight-0.021
 hugs-0.020
Token the
Token ID262
Feature activation+3.36e-02

Pos logit contributions
fters+0.106
oke+0.090
zel+0.089
wheel+0.088
ner+0.088
Neg logit contributions
by-0.056
 luck-0.055
 hugs-0.054
 hopes-0.054
 flashlight-0.053
Token hairy
Token ID43873
Feature activation+2.03e-02

Pos logit contributions
fters+0.081
oke+0.068
wheel+0.067
zel+0.067
ner+0.067
Neg logit contributions
by-0.037
 luck-0.034
 flashlight-0.034
 hugs-0.033
 hopes-0.033
Token cater
Token ID20825
Feature activation+6.95e-02

Pos logit contributions
fters+0.037
wheel+0.029
isin+0.029
ner+0.029
zel+0.028
Neg logit contributions
by-0.032
packs-0.031
 hopes-0.030
 luck-0.029
 flashlight-0.029
Tokenpill
Token ID27215
Feature activation+2.04e-01

Pos logit contributions
fters+0.156
 inconvenience+0.136
uers+0.128
 stret+0.128
hers+0.127
Neg logit contributions
y-0.075
by-0.074
 hugs-0.072
cy-0.070
 looks-0.062
Tokenars
Token ID945
Feature activation+8.69e-03

Pos logit contributions
fters+0.397
 Theo+0.390
 IT+0.390
 inconvenience+0.353
 paramed+0.353
Neg logit contributions
by-0.227
 hugs-0.208
 close-0.205
 back-0.202
 luck-0.200
Token.
Token ID13
Feature activation-8.77e-04

Pos logit contributions
fters+0.026
isin+0.023
 IT+0.022
oke+0.022
cod+0.022
Neg logit contributions
by-0.004
 back-0.004
 luck-0.004
y-0.004
packs-0.003
Token<|endoftext|>
Token ID50256
Feature activation-5.00e-02

Pos logit contributions
by+0.001
 hopes+0.001
 hugs+0.001
cy+0.001
 eyes+0.001
Neg logit contributions
fters-0.002
isin-0.002
wheel-0.002
zel-0.002
ner-0.002
TokenOnce
Token ID7454
Feature activation-2.11e-02

Pos logit contributions
by+0.052
 hopes+0.046
 luck+0.046
 hugs+0.046
 flashlight+0.046
Neg logit contributions
fters-0.125
isin-0.104
wheel-0.103
zel-0.102
ner-0.100
Token there
Token ID612
Feature activation+1.17e-02

Pos logit contributions
by+0.023
 luck+0.022
 hopes+0.022
 hugs+0.021
 flashlight+0.021
Neg logit contributions
fters-0.048
oke-0.042
ner-0.040
isin-0.039
wheel-0.039
Token Lily
Token ID20037
Feature activation+2.23e-02

Pos logit contributions
fters+0.016
hers+0.014
str+0.013
isin+0.013
zel+0.013
Neg logit contributions
 eyes-0.008
 luck-0.008
 hugs-0.008
 hopes-0.007
 looks-0.007
Token,
Token ID11
Feature activation+3.29e-03

Pos logit contributions
fters+0.069
isin+0.059
wheel+0.059
ner+0.058
 IT+0.058
Neg logit contributions
by-0.011
 hopes-0.009
 luck-0.009
 hugs-0.009
 flashlight-0.008
Token no
Token ID645
Feature activation-3.24e-02

Pos logit contributions
fters+0.007
zel+0.006
isin+0.006
wheel+0.006
ner+0.006
Neg logit contributions
 hugs-0.004
 luck-0.004
 eyes-0.004
 hopes-0.004
 looks-0.004
Token.
Token ID13
Feature activation+7.49e-03

Pos logit contributions
by+0.022
 luck+0.019
 flashlight+0.017
 hopes+0.017
 hugs+0.017
Neg logit contributions
fters-0.094
isin-0.079
wheel-0.079
zel-0.079
ner-0.079
Token Cater
Token ID40742
Feature activation+6.06e-02

Pos logit contributions
fters+0.016
isin+0.013
wheel+0.012
str+0.012
zel+0.012
Neg logit contributions
 eyes-0.011
 hopes-0.011
 hugs-0.011
cy-0.010
 nods-0.010
Tokenpill
Token ID27215
Feature activation+2.01e-01

Pos logit contributions
fters+0.078
isin+0.052
 IT+0.050
wheel+0.048
zel+0.048
Neg logit contributions
by-0.131
cy-0.130
 hugs-0.129
 hopes-0.127
y-0.127
Tokenars
Token ID945
Feature activation+5.96e-03

Pos logit contributions
fters+0.373
 IT+0.332
 Theo+0.324
ner+0.321
pieces+0.301
Neg logit contributions
 hugs-0.272
 hopes-0.272
 luck-0.270
 nods-0.260
by-0.257
Token are
Token ID389
Feature activation+5.44e-03

Pos logit contributions
fters+0.017
ner+0.014
isin+0.014
wheel+0.014
 IT+0.014
Neg logit contributions
by-0.004
 hugs-0.004
 looks-0.004
 luck-0.004
 hopes-0.004
Token not
Token ID407
Feature activation+1.17e-02

Pos logit contributions
fters+0.014
ner+0.013
oke+0.012
ird+0.012
wheel+0.012
Neg logit contributions
 luck-0.006
 eyes-0.006
 back-0.006
 hugs-0.005
 close-0.005
Token for
Token ID329
Feature activation+6.63e-02

Pos logit contributions
fters+0.034
ner+0.030
isin+0.029
oke+0.029
uct+0.028
Neg logit contributions
 luck-0.010
 back-0.009
by-0.008
 eyes-0.008
y-0.007
Token keeping
Token ID5291
Feature activation+2.04e-02

Pos logit contributions
fters+0.153
wheel+0.136
zel+0.135
oke+0.130
str+0.128
Neg logit contributions
 eyes-0.088
 luck-0.077
 hugs-0.076
by-0.071
 dreams-0.069
Token.
Token ID13
Feature activation+6.36e-03

Pos logit contributions
fters+0.066
wheel+0.055
ner+0.055
isin+0.055
oke+0.055
Neg logit contributions
by-0.025
 luck-0.022
 flashlight-0.022
 hopes-0.022
 hugs-0.021
Token Soon
Token ID15894
Feature activation+6.92e-03

Pos logit contributions
fters+0.016
wheel+0.013
ner+0.013
isin+0.013
zel+0.013
Neg logit contributions
by-0.007
 hopes-0.007
 hugs-0.006
 eyes-0.006
 luck-0.006
Token,
Token ID11
Feature activation+3.98e-03

Pos logit contributions
fters+0.015
ner+0.013
oke+0.013
isin+0.012
n+0.012
Neg logit contributions
 flashlight-0.008
by-0.008
 hopes-0.007
 hugs-0.007
cy-0.007
Token more
Token ID517
Feature activation+3.71e-02

Pos logit contributions
fters+0.009
wheel+0.007
isin+0.007
zel+0.007
oke+0.007
Neg logit contributions
by-0.005
 luck-0.005
 hopes-0.005
 eyes-0.005
 hugs-0.005
Token cater
Token ID20825
Feature activation+7.44e-02

Pos logit contributions
fters+0.095
ner+0.078
zel+0.077
wheel+0.077
 IT+0.077
Neg logit contributions
by-0.038
 hugs-0.038
 luck-0.038
 eyes-0.037
 dreams-0.037
Tokenpill
Token ID27215
Feature activation+1.99e-01

Pos logit contributions
fters+0.105
 IT+0.075
zel+0.071
pieces+0.069
isin+0.069
Neg logit contributions
by-0.148
 hugs-0.147
 luck-0.141
cy-0.140
y-0.140
Tokenars
Token ID945
Feature activation+7.09e-03

Pos logit contributions
fters+0.374
 IT+0.341
 Theo+0.314
ner+0.311
oke+0.302
Neg logit contributions
by-0.261
 hugs-0.260
 luck-0.256
 hopes-0.247
 back-0.246
Token arrived
Token ID5284
Feature activation+1.71e-02

Pos logit contributions
fters+0.021
isin+0.018
ner+0.017
wheel+0.017
 IT+0.017
Neg logit contributions
by-0.005
 luck-0.004
 hugs-0.004
 hopes-0.004
 back-0.004
Token.
Token ID13
Feature activation+7.41e-03

Pos logit contributions
fters+0.043
wheel+0.036
oke+0.035
ner+0.035
isin+0.035
Neg logit contributions
by-0.016
 flashlight-0.015
 hopes-0.014
 hugs-0.014
 luck-0.014
Token They
Token ID1119
Feature activation-8.00e-04

Pos logit contributions
fters+0.020
wheel+0.016
isin+0.016
zel+0.016
ner+0.016
Neg logit contributions
 hopes-0.007
 eyes-0.007
 hugs-0.007
 nods-0.007
packs-0.007
Token also
Token ID635
Feature activation+3.65e-03

Pos logit contributions
by+0.001
 hopes+0.001
 hugs+0.001
 luck+0.001
 flashlight+0.001
Neg logit contributions
fters-0.002
isin-0.002
ner-0.002
wheel-0.002
 IT-0.002
Token and
Token ID290
Feature activation-1.79e-02

Pos logit contributions
by+0.016
 luck+0.014
 hopes+0.013
 flashlight+0.013
 hugs+0.013
Neg logit contributions
fters-0.072
isin-0.062
oke-0.061
wheel-0.061
zel-0.060
Token watched
Token ID7342
Feature activation-5.55e-03

Pos logit contributions
by+0.020
 flashlight+0.018
 hopes+0.017
 hugs+0.017
 back+0.017
Neg logit contributions
fters-0.044
isin-0.038
oke-0.037
 IT-0.037
zel-0.036
Token as
Token ID355
Feature activation-4.12e-03

Pos logit contributions
 eyes+0.005
 back+0.005
 hugs+0.004
by+0.004
 luck+0.004
Neg logit contributions
fters-0.015
oke-0.013
isin-0.013
str-0.013
wheel-0.013
Token the
Token ID262
Feature activation+3.28e-02

Pos logit contributions
by+0.005
 luck+0.004
 flashlight+0.004
 hopes+0.004
 hugs+0.004
Neg logit contributions
fters-0.010
isin-0.008
oke-0.008
wheel-0.008
zel-0.008
Token cater
Token ID20825
Feature activation+6.08e-02

Pos logit contributions
fters+0.075
wheel+0.062
ner+0.062
isin+0.061
zel+0.060
Neg logit contributions
by-0.040
 hopes-0.036
 luck-0.036
 flashlight-0.035
packs-0.035
Tokenpill
Token ID27215
Feature activation+1.92e-01

Pos logit contributions
fters+0.125
 Theo+0.101
 inconvenience+0.100
oke+0.100
 IT+0.099
Neg logit contributions
 hugs-0.076
by-0.073
cy-0.072
y-0.071
 looks-0.068
Tokenars
Token ID945
Feature activation+1.84e-04

Pos logit contributions
fters+0.386
 IT+0.379
 Theo+0.375
ner+0.348
 Timothy+0.342
Neg logit contributions
by-0.197
 hugs-0.194
 back-0.184
 luck-0.182
ed-0.179
Token grew
Token ID6348
Feature activation-1.17e-03

Pos logit contributions
fters+0.000
isin+0.000
oke+0.000
zel+0.000
 IT+0.000
Neg logit contributions
by-0.000
 luck-0.000
 flashlight-0.000
 back-0.000
 hopes-0.000
Token bigger
Token ID5749
Feature activation+4.21e-02

Pos logit contributions
by+0.001
 hopes+0.001
 flashlight+0.001
 luck+0.001
 hugs+0.001
Neg logit contributions
fters-0.003
wheel-0.002
isin-0.002
ner-0.002
zel-0.002
Token and
Token ID290
Feature activation+6.03e-03

Pos logit contributions
fters+0.122
isin+0.104
wheel+0.103
ner+0.103
zel+0.102
Neg logit contributions
by-0.027
 luck-0.024
 hopes-0.023
 eyes-0.022
 hugs-0.022
Token bigger
Token ID5749
Feature activation+4.59e-02

Pos logit contributions
fters+0.014
isin+0.011
oke+0.011
ner+0.011
wheel+0.011
Neg logit contributions
by-0.007
 luck-0.007
 hopes-0.007
 flashlight-0.007
 hugs-0.007
Token saw
Token ID2497
Feature activation+2.43e-02

Pos logit contributions
fters+0.076
isin+0.064
wheel+0.064
ner+0.063
oke+0.063
Neg logit contributions
by-0.027
 hopes-0.023
 hugs-0.023
 luck-0.023
 flashlight-0.022
Token lots
Token ID6041
Feature activation-1.69e-02

Pos logit contributions
fters+0.058
wheel+0.049
ner+0.048
isin+0.048
zel+0.047
Neg logit contributions
by-0.027
 luck-0.024
 hopes-0.023
 flashlight-0.023
packs-0.022
Token of
Token ID286
Feature activation+6.24e-02

Pos logit contributions
by+0.018
 hugs+0.018
 luck+0.017
 eyes+0.016
 flashlight+0.016
Neg logit contributions
fters-0.041
zel-0.034
wheel-0.033
 IT-0.033
isin-0.033
Token colourful
Token ID44799
Feature activation+2.54e-02

Pos logit contributions
fters+0.150
wheel+0.126
zel+0.125
ner+0.124
oke+0.124
Neg logit contributions
by-0.068
 luck-0.065
 hugs-0.065
 flashlight-0.064
 hopes-0.063
Token cater
Token ID20825
Feature activation+6.50e-02

Pos logit contributions
fters+0.060
ner+0.049
isin+0.049
wheel+0.049
oke+0.048
Neg logit contributions
by-0.029
 hopes-0.026
 luck-0.026
 flashlight-0.025
 hugs-0.024
Tokenpill
Token ID27215
Feature activation+1.92e-01

Pos logit contributions
fters+0.079
 IT+0.054
zel+0.053
 inconvenience+0.053
isin+0.051
Neg logit contributions
 hugs-0.138
by-0.135
y-0.133
cy-0.130
 luck-0.127
Tokenars
Token ID945
Feature activation+3.36e-04

Pos logit contributions
fters+0.356
 IT+0.329
 Theo+0.307
ner+0.303
 whoever+0.294
Neg logit contributions
 hugs-0.246
by-0.244
 luck-0.234
 flashlight-0.219
 close-0.217
Token and
Token ID290
Feature activation+1.34e-03

Pos logit contributions
fters+0.001
isin+0.001
zel+0.001
oke+0.001
 IT+0.001
Neg logit contributions
by-0.000
 luck-0.000
 hugs-0.000
 eyes-0.000
 back-0.000
Token an
Token ID281
Feature activation-6.01e-03

Pos logit contributions
fters+0.004
oke+0.003
isin+0.003
zel+0.003
wheel+0.003
Neg logit contributions
by-0.001
 hugs-0.001
 eyes-0.001
 looks-0.001
 luck-0.001
Token old
Token ID1468
Feature activation+9.34e-04

Pos logit contributions
 luck+0.007
 eyes+0.007
by+0.006
 back+0.006
 hugs+0.006
Neg logit contributions
fters-0.014
ner-0.012
oke-0.012
zel-0.012
wheel-0.011
Token lady
Token ID10846
Feature activation+1.29e-02

Pos logit contributions
fters+0.003
isin+0.002
 IT+0.002
oke+0.002
ner+0.002
Neg logit contributions
by-0.001
 eyes-0.001
 flashlight-0.001
 luck-0.001
 looks-0.001
Token know
Token ID760
Feature activation-1.66e-02

Pos logit contributions
 luck+0.002
by+0.002
 wonder+0.001
 hope+0.001
 hopes+0.001
Neg logit contributions
fters-0.004
ner-0.003
 IT-0.003
isin-0.003
oke-0.003
Token,
Token ID11
Feature activation-2.49e-03

Pos logit contributions
by+0.012
 hugs+0.012
 luck+0.012
 eyes+0.012
 hopes+0.012
Neg logit contributions
fters-0.046
wheel-0.039
zel-0.039
isin-0.038
ner-0.038
Token Lily
Token ID20037
Feature activation+1.26e-02

Pos logit contributions
 eyes+0.003
 looks+0.002
 and+0.002
 dreams+0.002
 back+0.002
Neg logit contributions
fters-0.007
str-0.006
isin-0.005
wheel-0.005
hers-0.005
Token.
Token ID13
Feature activation+1.48e-03

Pos logit contributions
fters+0.039
isin+0.033
wheel+0.033
ner+0.033
 IT+0.032
Neg logit contributions
by-0.007
 hopes-0.006
 luck-0.006
 looks-0.005
 hugs-0.005
Token Cater
Token ID40742
Feature activation+5.19e-02

Pos logit contributions
fters+0.003
wheel+0.002
isin+0.002
ner+0.002
zel+0.002
Neg logit contributions
by-0.002
 luck-0.002
 hopes-0.002
 flashlight-0.002
 hugs-0.002
Tokenpill
Token ID27215
Feature activation+1.92e-01

Pos logit contributions
fters+0.085
isin+0.062
wheel+0.060
zel+0.059
 IT+0.059
Neg logit contributions
by-0.098
 hugs-0.093
cy-0.093
 hopes-0.093
 luck-0.092
Tokenars
Token ID945
Feature activation-3.70e-03

Pos logit contributions
fters+0.347
ner+0.292
 IT+0.290
 Theo+0.272
wheel+0.270
Neg logit contributions
 hopes-0.287
 hugs-0.285
 luck-0.285
by-0.282
 nods-0.274
Token need
Token ID761
Feature activation-2.32e-02

Pos logit contributions
by+0.003
 luck+0.003
 hugs+0.003
 hopes+0.003
 looks+0.003
Neg logit contributions
fters-0.010
ner-0.009
isin-0.008
wheel-0.008
 IT-0.008
Token leaves
Token ID5667
Feature activation+4.55e-04

Pos logit contributions
by+0.023
 luck+0.020
 hopes+0.020
 flashlight+0.020
 hugs+0.019
Neg logit contributions
fters-0.058
wheel-0.048
isin-0.048
ner-0.048
zel-0.048
Token and
Token ID290
Feature activation-9.83e-04

Pos logit contributions
fters+0.001
isin+0.001
ner+0.001
wheel+0.001
oke+0.001
Neg logit contributions
by-0.000
 luck-0.000
 hopes-0.000
 hugs-0.000
 flashlight-0.000
Token air
Token ID1633
Feature activation+1.61e-02

Pos logit contributions
by+0.001
 luck+0.001
 hopes+0.001
 flashlight+0.001
 hugs+0.001
Neg logit contributions
fters-0.002
wheel-0.002
isin-0.002
ner-0.002
oke-0.002
Token Did
Token ID7731
Feature activation+3.27e-02

Pos logit contributions
 hopes+0.017
 hugs+0.016
 looks+0.015
 nods+0.015
by+0.015
Neg logit contributions
fters-0.028
isin-0.022
wheel-0.021
zel-0.021
cod-0.021
Token you
Token ID345
Feature activation+3.99e-02

Pos logit contributions
fters+0.068
oke+0.054
wheel+0.054
zel+0.053
isin+0.053
Neg logit contributions
by-0.048
 luck-0.047
 eyes-0.047
 hugs-0.046
 hopes-0.046
Token know
Token ID760
Feature activation-1.74e-02

Pos logit contributions
fters+0.098
oke+0.085
isin+0.082
ner+0.080
 IT+0.079
Neg logit contributions
by-0.044
 flashlight-0.040
 luck-0.040
 hugs-0.038
 dreams-0.038
Token that
Token ID326
Feature activation+1.72e-03

Pos logit contributions
by+0.020
 luck+0.018
 hopes+0.018
 flashlight+0.017
 hugs+0.017
Neg logit contributions
fters-0.041
wheel-0.034
ner-0.034
isin-0.034
oke-0.033
Token cater
Token ID20825
Feature activation+6.24e-02

Pos logit contributions
fters+0.004
oke+0.004
isin+0.004
zel+0.004
ner+0.003
Neg logit contributions
 looks-0.002
 flashlight-0.002
 luck-0.002
 dreams-0.002
by-0.002
Tokenpill
Token ID27215
Feature activation+1.91e-01

Pos logit contributions
fters+0.098
 stret+0.076
 IT+0.072
 inconvenience+0.072
uers+0.072
Neg logit contributions
by-0.109
y-0.108
 hugs-0.108
 looks-0.103
 dreams-0.102
Tokenars
Token ID945
Feature activation+2.64e-03

Pos logit contributions
fters+0.362
 Theo+0.336
 IT+0.329
ner+0.320
 stret+0.313
Neg logit contributions
 luck-0.245
by-0.239
 hopes-0.232
 hugs-0.232
 will-0.228
Token turn
Token ID1210
Feature activation-2.22e-02

Pos logit contributions
fters+0.007
ner+0.006
isin+0.006
wheel+0.006
oke+0.006
Neg logit contributions
by-0.003
 luck-0.002
 looks-0.002
 flashlight-0.002
y-0.002
Token into
Token ID656
Feature activation+3.22e-02

Pos logit contributions
by+0.020
 luck+0.018
 hugs+0.017
 flashlight+0.017
 eyes+0.017
Neg logit contributions
fters-0.059
ner-0.049
wheel-0.049
isin-0.049
oke-0.049
Token beautiful
Token ID4950
Feature activation-1.46e-03

Pos logit contributions
fters+0.089
oke+0.080
wheel+0.078
ner+0.077
isin+0.076
Neg logit contributions
 eyes-0.025
 luck-0.025
 dreams-0.022
by-0.022
 flashlight-0.022
Token butterflies
Token ID44571
Feature activation+1.45e-02

Pos logit contributions
by+0.001
 luck+0.001
 hopes+0.001
 flashlight+0.001
 hugs+0.001
Neg logit contributions
fters-0.004
wheel-0.003
isin-0.003
ner-0.003
oke-0.003
Token he
Token ID339
Feature activation+2.85e-02

Pos logit contributions
fters+0.026
oke+0.023
isin+0.022
cod+0.021
zel+0.021
Neg logit contributions
 eyes-0.008
 luck-0.008
 flashlight-0.008
by-0.007
 dreams-0.007
Token noticed
Token ID6810
Feature activation+2.64e-02

Pos logit contributions
fters+0.075
isin+0.063
ner+0.063
oke+0.063
wheel+0.062
Neg logit contributions
by-0.029
 hopes-0.024
 hugs-0.023
 luck-0.023
 looks-0.023
Token some
Token ID617
Feature activation-1.22e-02

Pos logit contributions
fters+0.072
oke+0.059
isin+0.059
zel+0.059
ner+0.058
Neg logit contributions
by-0.024
 luck-0.023
 eyes-0.022
 hugs-0.022
 hopes-0.021
Token other
Token ID584
Feature activation+2.04e-02

Pos logit contributions
by+0.014
 luck+0.014
 eyes+0.014
 hugs+0.013
 hopes+0.012
Neg logit contributions
fters-0.029
zel-0.024
ner-0.024
wheel-0.024
 IT-0.024
Token cater
Token ID20825
Feature activation+6.05e-02

Pos logit contributions
fters+0.052
 IT+0.043
zel+0.043
ner+0.043
wheel+0.042
Neg logit contributions
by-0.023
 luck-0.023
 hugs-0.022
 dreams-0.021
 eyes-0.021
Tokenpill
Token ID27215
Feature activation+1.91e-01

Pos logit contributions
fters+0.088
 inconvenience+0.072
 IT+0.066
 whoever+0.065
 stret+0.063
Neg logit contributions
 hugs-0.114
by-0.113
y-0.111
cy-0.108
ed-0.107
Tokenars
Token ID945
Feature activation+2.42e-04

Pos logit contributions
 IT+0.371
fters+0.370
 Theo+0.369
 whoever+0.338
 inconvenience+0.333
Neg logit contributions
 hugs-0.198
by-0.196
 luck-0.184
ed-0.178
 close-0.174
Token stretching
Token ID20880
Feature activation-1.34e-02

Pos logit contributions
fters+0.001
isin+0.001
zel+0.001
ner+0.001
oke+0.001
Neg logit contributions
by-0.000
 luck-0.000
 back-0.000
 hugs-0.000
 eyes-0.000
Token towards
Token ID3371
Feature activation-2.55e-02

Pos logit contributions
by+0.011
 luck+0.009
 flashlight+0.008
 eyes+0.008
 hopes+0.008
Neg logit contributions
fters-0.037
ner-0.032
isin-0.032
oke-0.032
wheel-0.031
Token it
Token ID340
Feature activation-7.86e-03

Pos logit contributions
by+0.022
 eyes+0.019
 back+0.019
 luck+0.018
 hugs+0.018
Neg logit contributions
fters-0.072
oke-0.061
isin-0.061
zel-0.061
wheel-0.060
Token too
Token ID1165
Feature activation-3.28e-03

Pos logit contributions
by+0.005
 luck+0.004
 back+0.004
 eyes+0.004
 flashlight+0.004
Neg logit contributions
fters-0.023
isin-0.020
ner-0.020
oke-0.020
zel-0.019
Token but
Token ID475
Feature activation+2.31e-02

Pos logit contributions
fters+0.042
ner+0.036
pieces+0.035
oke+0.035
str+0.035
Neg logit contributions
 eyes-0.017
 and-0.016
 hugs-0.016
 hopes-0.016
 back-0.015
Token he
Token ID339
Feature activation+3.36e-02

Pos logit contributions
fters+0.050
isin+0.040
zel+0.040
ner+0.039
pieces+0.039
Neg logit contributions
 luck-0.032
 hugs-0.030
by-0.030
 eyes-0.030
 flashlight-0.030
Token also
Token ID635
Feature activation+2.63e-02

Pos logit contributions
fters+0.082
ner+0.067
isin+0.067
wheel+0.066
 IT+0.065
Neg logit contributions
by-0.038
 hopes-0.034
 luck-0.034
 hugs-0.033
 flashlight-0.033
Token knew
Token ID2993
Feature activation-6.91e-03

Pos logit contributions
fters+0.066
ner+0.055
isin+0.054
wheel+0.054
 IT+0.053
Neg logit contributions
by-0.028
 hopes-0.026
 luck-0.025
 hugs-0.025
 flashlight-0.024
Token cater
Token ID20825
Feature activation+6.01e-02

Pos logit contributions
by+0.008
 luck+0.008
 eyes+0.008
 hugs+0.008
 hopes+0.008
Neg logit contributions
fters-0.016
zel-0.013
isin-0.013
ner-0.013
wheel-0.013
Tokenpill
Token ID27215
Feature activation+1.90e-01

Pos logit contributions
fters+0.066
isin+0.040
wheel+0.039
ner+0.039
 IT+0.039
Neg logit contributions
by-0.144
 hugs-0.138
 luck-0.137
 hopes-0.137
cy-0.135
Tokenars
Token ID945
Feature activation+4.48e-04

Pos logit contributions
fters+0.340
 IT+0.284
ner+0.281
wheel+0.262
 Theo+0.261
Neg logit contributions
by-0.295
 luck-0.290
 hugs-0.288
 hopes-0.287
 nods-0.272
Token were
Token ID547
Feature activation+1.55e-02

Pos logit contributions
fters+0.001
ner+0.001
isin+0.001
wheel+0.001
zel+0.001
Neg logit contributions
by-0.000
 luck-0.000
 hopes-0.000
 hugs-0.000
 flashlight-0.000
Token not
Token ID407
Feature activation+9.92e-03

Pos logit contributions
fters+0.040
ner+0.036
oke+0.034
wheel+0.033
ird+0.033
Neg logit contributions
 luck-0.018
 hugs-0.016
 back-0.016
 eyes-0.015
 hopes-0.015
Token pets
Token ID17252
Feature activation+5.75e-02

Pos logit contributions
fters+0.028
ner+0.024
isin+0.023
oke+0.022
 IT+0.022
Neg logit contributions
 luck-0.010
 back-0.009
by-0.009
 eyes-0.008
y-0.008
Token.
Token ID13
Feature activation+6.15e-03

Pos logit contributions
fters+0.176
isin+0.153
 IT+0.150
zel+0.150
ner+0.149
Neg logit contributions
by-0.026
 luck-0.025
y-0.024
 back-0.023
 hugs-0.021
Token doing
Token ID1804
Feature activation+7.47e-02

Pos logit contributions
fters+0.103
pieces+0.083
isin+0.080
zel+0.080
wheel+0.079
Neg logit contributions
 luck-0.105
 eyes-0.099
 back-0.098
 flashlight-0.097
by-0.097
Token here
Token ID994
Feature activation+4.63e-02

Pos logit contributions
fters+0.218
isin+0.188
wheel+0.184
zel+0.183
pieces+0.182
Neg logit contributions
 luck-0.043
by-0.041
 back-0.037
 flashlight-0.036
 looks-0.035
Token?"
Token ID1701
Feature activation+8.33e-02

Pos logit contributions
fters+0.129
isin+0.109
ner+0.107
wheel+0.107
zel+0.107
Neg logit contributions
by-0.034
 luck-0.033
 back-0.030
 looks-0.030
 hugs-0.029
Token the
Token ID262
Feature activation+5.85e-02

Pos logit contributions
fters+0.217
wheel+0.176
zel+0.175
isin+0.171
icious+0.171
Neg logit contributions
 eyes-0.090
 hugs-0.090
 hopes-0.090
 wonder-0.084
 dreams-0.082
Token zo
Token ID40565
Feature activation+7.02e-02

Pos logit contributions
fters+0.136
isin+0.108
zel+0.108
wheel+0.106
 IT+0.106
Neg logit contributions
by-0.075
 eyes-0.072
 flashlight-0.071
 hugs-0.071
 hopes-0.071
Tokenoke
Token ID2088
Feature activation+1.88e-01

Pos logit contributions
fters+0.074
 IT+0.039
isin+0.038
zel+0.032
wheel+0.032
Neg logit contributions
by-0.180
 hugs-0.171
 nods-0.169
y-0.169
 looks-0.167
Tokeneper
Token ID5723
Feature activation+5.40e-02

Pos logit contributions
fters+0.385
wheel+0.304
isin+0.303
ner+0.300
zel+0.298
Neg logit contributions
by-0.282
 luck-0.260
 hopes-0.259
 hugs-0.252
 flashlight-0.252
Token asked
Token ID1965
Feature activation+3.66e-02

Pos logit contributions
fters+0.127
 IT+0.100
isin+0.100
zel+0.099
pieces+0.097
Neg logit contributions
by-0.068
 eyes-0.065
y-0.064
 hugs-0.062
 back-0.060
Token.
Token ID13
Feature activation-1.51e-03

Pos logit contributions
fters+0.107
isin+0.091
wheel+0.090
zel+0.089
 IT+0.089
Neg logit contributions
by-0.025
 luck-0.021
 hugs-0.020
 eyes-0.020
 hopes-0.019
Token "
Token ID366
Feature activation+1.71e-02

Pos logit contributions
 eyes+0.002
 hopes+0.002
 hugs+0.002
by+0.002
 back+0.002
Neg logit contributions
fters-0.004
isin-0.003
pieces-0.003
wheel-0.003
zel-0.003
TokenYou
Token ID1639
Feature activation+7.48e-03

Pos logit contributions
fters+0.041
pieces+0.035
isin+0.034
str+0.034
oke+0.033
Neg logit contributions
cy-0.015
y-0.015
 hopes-0.014
ucks-0.014
Maybe-0.013
Token careful
Token ID8161
Feature activation+2.13e-02

Pos logit contributions
fters+0.086
ner+0.073
oke+0.073
wheel+0.069
 IT+0.067
Neg logit contributions
 luck-0.066
by-0.065
 hopes-0.062
 hugs-0.060
 back-0.059
Token,
Token ID11
Feature activation+1.62e-03

Pos logit contributions
fters+0.065
wheel+0.056
oke+0.056
pieces+0.056
cod+0.055
Neg logit contributions
by-0.009
 eyes-0.008
 back-0.008
 luck-0.008
y-0.007
Token Lily
Token ID20037
Feature activation+1.37e-02

Pos logit contributions
fters+0.004
wheel+0.003
zel+0.003
ner+0.003
pieces+0.003
Neg logit contributions
 eyes-0.002
 hugs-0.002
 looks-0.002
 hopes-0.002
 luck-0.002
Token.
Token ID13
Feature activation-6.29e-03

Pos logit contributions
fters+0.045
pieces+0.038
wheel+0.038
isin+0.038
 IT+0.038
Neg logit contributions
by-0.004
 hopes-0.004
y-0.004
,-0.004
 hugs-0.003
Token Cater
Token ID40742
Feature activation+4.91e-02

Pos logit contributions
 eyes+0.008
 hopes+0.008
 hugs+0.008
 dreams+0.007
 nods+0.007
Neg logit contributions
fters-0.015
wheel-0.012
isin-0.012
zel-0.011
pieces-0.011
Tokenpill
Token ID27215
Feature activation+1.86e-01

Pos logit contributions
fters+0.097
isin+0.073
 IT+0.072
 stret+0.072
 inconvenience+0.070
Neg logit contributions
cy-0.076
y-0.076
by-0.074
 hugs-0.074
 looks-0.072
Tokenars
Token ID945
Feature activation-2.82e-03

Pos logit contributions
fters+0.357
 IT+0.320
ner+0.320
 Theo+0.314
 whoever+0.294
Neg logit contributions
 hopes-0.238
 hugs-0.236
 luck-0.233
 nods-0.225
 will-0.224
Token can
Token ID460
Feature activation-2.79e-02

Pos logit contributions
by+0.002
 looks+0.002
 luck+0.002
 hopes+0.002
 flashlight+0.002
Neg logit contributions
fters-0.008
ner-0.007
isin-0.007
wheel-0.007
oke-0.006
Token be
Token ID307
Feature activation+1.11e-02

Pos logit contributions
by+0.034
 back+0.031
 looks+0.031
 flashlight+0.031
 luck+0.030
Neg logit contributions
fters-0.062
oke-0.056
pieces-0.053
zel-0.051
isin-0.051
Token tricky
Token ID17198
Feature activation+4.05e-02

Pos logit contributions
fters+0.028
ner+0.025
oke+0.024
isin+0.023
wheel+0.023
Neg logit contributions
 luck-0.013
by-0.012
 back-0.012
 hugs-0.011
 hopes-0.011
Token.
Token ID13
Feature activation-4.57e-03

Pos logit contributions
fters+0.116
isin+0.099
str+0.099
 IT+0.098
zel+0.098
Neg logit contributions
 luck-0.026
by-0.025
 hopes-0.023
 hugs-0.022
 eyes-0.021
Tokenily
Token ID813
Feature activation-1.58e-03

Pos logit contributions
fters+0.029
oke+0.023
ner+0.022
isin+0.022
wheel+0.021
Neg logit contributions
by-0.024
 hopes-0.023
 flashlight-0.023
 luck-0.023
 nods-0.023
Token liked
Token ID8288
Feature activation-5.28e-02

Pos logit contributions
by+0.001
 eyes+0.001
 luck+0.001
 flashlight+0.001
 breath+0.001
Neg logit contributions
fters-0.003
oke-0.003
wheel-0.003
ner-0.003
zel-0.003
Token to
Token ID284
Feature activation+2.42e-02

Pos logit contributions
by+0.017
 hugs+0.014
 eyes+0.013
 luck+0.012
 flashlight+0.011
Neg logit contributions
fters-0.172
isin-0.150
zel-0.150
oke-0.148
wheel-0.147
Token keep
Token ID1394
Feature activation-3.62e-02

Pos logit contributions
fters+0.064
oke+0.056
isin+0.054
zel+0.054
ner+0.053
Neg logit contributions
by-0.021
 flashlight-0.020
 hugs-0.019
 hopes-0.019
 eyes-0.019
Token cater
Token ID20825
Feature activation+5.87e-02

Pos logit contributions
by+0.046
 luck+0.043
 hugs+0.043
 flashlight+0.043
 hopes+0.043
Neg logit contributions
fters-0.081
oke-0.067
wheel-0.066
ner-0.066
isin-0.066
Tokenpill
Token ID27215
Feature activation+1.85e-01

Pos logit contributions
fters+0.075
 IT+0.049
wheel+0.049
ner+0.048
zel+0.047
Neg logit contributions
by-0.130
 hugs-0.124
 luck-0.121
 hopes-0.120
cy-0.120
Tokenars
Token ID945
Feature activation-1.73e-02

Pos logit contributions
fters+0.329
 IT+0.274
ner+0.269
oke+0.260
wheel+0.250
Neg logit contributions
by-0.294
 hugs-0.277
 luck-0.276
 hopes-0.268
 flashlight-0.263
Token in
Token ID287
Feature activation-5.59e-03

Pos logit contributions
by+0.012
 luck+0.010
 flashlight+0.010
 hugs+0.010
 eyes+0.009
Neg logit contributions
fters-0.049
oke-0.042
wheel-0.042
isin-0.041
ner-0.041
Token a
Token ID257
Feature activation-3.44e-02

Pos logit contributions
by+0.005
 luck+0.004
 hopes+0.004
 flashlight+0.004
 hugs+0.004
Neg logit contributions
fters-0.015
wheel-0.013
isin-0.012
ner-0.012
oke-0.012
Token jar
Token ID17379
Feature activation+4.19e-02

Pos logit contributions
by+0.032
 flashlight+0.027
 luck+0.027
 hopes+0.027
 hugs+0.026
Neg logit contributions
fters-0.090
wheel-0.076
ner-0.076
isin-0.076
oke-0.075
Token.
Token ID13
Feature activation-2.93e-02

Pos logit contributions
fters+0.116
isin+0.098
oke+0.098
ner+0.098
 IT+0.097
Neg logit contributions
by-0.031
 luck-0.026
 flashlight-0.026
 hopes-0.025
 hugs-0.025
Token,
Token ID11
Feature activation-8.21e-03

Pos logit contributions
fters+0.005
wheel+0.004
oke+0.004
 IT+0.004
isin+0.004
Neg logit contributions
by-0.001
 back-0.001
 luck-0.001
 hugs-0.001
 hopes-0.001
Token okay
Token ID8788
Feature activation-2.08e-02

Pos logit contributions
 back+0.009
 eyes+0.009
 hopes+0.008
 hugs+0.008
 looks+0.008
Neg logit contributions
fters-0.020
ner-0.017
str-0.017
oke-0.017
isin-0.017
Token?"
Token ID1701
Feature activation+7.57e-02

Pos logit contributions
by+0.029
 hopes+0.027
 luck+0.027
 hugs+0.027
 flashlight+0.026
Neg logit contributions
fters-0.041
wheel-0.033
ner-0.033
 IT-0.033
isin-0.033
Token the
Token ID262
Feature activation+5.70e-02

Pos logit contributions
fters+0.208
wheel+0.175
isin+0.172
zel+0.171
oke+0.166
Neg logit contributions
by-0.074
 hugs-0.069
 hopes-0.068
 nods-0.067
 dreams-0.064
Token zo
Token ID40565
Feature activation+6.77e-02

Pos logit contributions
fters+0.130
wheel+0.103
isin+0.102
zel+0.100
 IT+0.100
Neg logit contributions
by-0.076
 luck-0.071
 hopes-0.070
 eyes-0.070
 hugs-0.070
Tokenoke
Token ID2088
Feature activation+1.85e-01

Pos logit contributions
fters+0.074
 IT+0.039
isin+0.039
hers+0.032
wheel+0.032
Neg logit contributions
by-0.172
y-0.164
 nods-0.164
 hugs-0.163
cy-0.162
Tokeneper
Token ID5723
Feature activation+5.37e-02

Pos logit contributions
fters+0.369
wheel+0.290
isin+0.288
ner+0.287
zel+0.284
Neg logit contributions
by-0.284
 luck-0.263
 hopes-0.262
 flashlight-0.257
 hugs-0.256
Token said
Token ID531
Feature activation+4.02e-02

Pos logit contributions
fters+0.131
 IT+0.105
isin+0.104
zel+0.101
ner+0.101
Neg logit contributions
by-0.065
 hugs-0.059
y-0.058
 eyes-0.058
 nods-0.056
Token.
Token ID13
Feature activation+7.40e-04

Pos logit contributions
fters+0.111
isin+0.094
wheel+0.093
ner+0.093
zel+0.092
Neg logit contributions
by-0.031
 luck-0.026
 hopes-0.026
 hugs-0.025
 flashlight-0.025
Token
Token ID198
Feature activation+1.97e-03

Pos logit contributions
fters+0.002
isin+0.002
cod+0.002
wheel+0.002
pieces+0.002
Neg logit contributions
 hopes-0.000
 hugs-0.000
 eyes-0.000
 back-0.000
by-0.000
Token
Token ID198
Feature activation+2.43e-03

Pos logit contributions
fters+0.005
wheel+0.004
isin+0.004
ner+0.004
zel+0.004
Neg logit contributions
by-0.002
 hopes-0.002
 hugs-0.002
 luck-0.002
 flashlight-0.002
Token back
Token ID736
Feature activation-5.12e-02

Pos logit contributions
fters+0.006
wheel+0.005
zel+0.005
ner+0.005
 IT+0.005
Neg logit contributions
by-0.002
 hopes-0.002
 flashlight-0.002
packs-0.002
 luck-0.002
Token,
Token ID11
Feature activation-9.37e-03

Pos logit contributions
by+0.039
 luck+0.033
 hopes+0.033
 flashlight+0.033
 hugs+0.033
Neg logit contributions
fters-0.132
ner-0.115
oke-0.114
wheel-0.113
zel-0.113
Token but
Token ID475
Feature activation+2.07e-02

Pos logit contributions
 eyes+0.007
 back+0.007
 hugs+0.007
 looks+0.007
 nods+0.007
Neg logit contributions
fters-0.027
isin-0.023
ird-0.023
ner-0.022
oke-0.022
Token the
Token ID262
Feature activation+4.44e-02

Pos logit contributions
fters+0.054
oke+0.046
isin+0.046
wheel+0.046
 IT+0.044
Neg logit contributions
by-0.020
 hopes-0.019
 back-0.019
 luck-0.019
 looks-0.018
Token zo
Token ID40565
Feature activation+7.23e-02

Pos logit contributions
fters+0.114
wheel+0.096
 IT+0.095
ner+0.094
isin+0.094
Neg logit contributions
by-0.045
 hugs-0.042
 eyes-0.042
 hopes-0.042
 flashlight-0.040
Tokenoke
Token ID2088
Feature activation+1.84e-01

Pos logit contributions
fters+0.081
 IT+0.046
isin+0.044
wheel+0.039
uct+0.035
Neg logit contributions
by-0.179
y-0.174
 nods-0.171
 hugs-0.170
cy-0.169
Tokeneper
Token ID5723
Feature activation+4.84e-02

Pos logit contributions
fters+0.349
wheel+0.272
isin+0.270
ner+0.269
oke+0.268
Neg logit contributions
by-0.296
 luck-0.278
 hopes-0.276
 flashlight-0.274
 hugs-0.271
Token told
Token ID1297
Feature activation+1.64e-02

Pos logit contributions
fters+0.128
ner+0.105
isin+0.104
 IT+0.103
pieces+0.100
Neg logit contributions
by-0.055
y-0.046
 hopes-0.046
 looks-0.046
 hugs-0.045
Token her
Token ID607
Feature activation-2.33e-02

Pos logit contributions
fters+0.051
zel+0.045
oke+0.045
wheel+0.045
ner+0.044
Neg logit contributions
by-0.008
 hugs-0.007
 eyes-0.006
 luck-0.006
 hopes-0.005
Token that
Token ID326
Feature activation-5.48e-03

Pos logit contributions
by+0.026
 luck+0.024
 eyes+0.023
 hugs+0.023
 hopes+0.022
Neg logit contributions
fters-0.059
isin-0.050
oke-0.048
wheel-0.048
ner-0.048
Token it
Token ID340
Feature activation+8.69e-03

Pos logit contributions
 dreams+0.006
by+0.005
 hugs+0.005
 hopes+0.005
 luck+0.005
Neg logit contributions
fters-0.014
isin-0.012
zel-0.012
 IT-0.012
wheel-0.012
Token you
Token ID345
Feature activation+1.26e-02

Pos logit contributions
fters+0.034
wheel+0.029
zel+0.028
oke+0.028
cod+0.027
Neg logit contributions
 hugs-0.022
by-0.021
 eyes-0.021
 luck-0.021
 back-0.019
Token,
Token ID11
Feature activation-1.45e-02

Pos logit contributions
fters+0.032
isin+0.027
wheel+0.027
oke+0.027
zel+0.027
Neg logit contributions
by-0.012
 hugs-0.012
 luck-0.012
 eyes-0.012
 hopes-0.011
Token Lily
Token ID20037
Feature activation+8.09e-03

Pos logit contributions
 eyes+0.016
 hugs+0.015
 looks+0.014
 and+0.013
 luck+0.013
Neg logit contributions
fters-0.037
str-0.032
zel-0.031
wheel-0.031
pieces-0.030
Token.
Token ID13
Feature activation-9.19e-03

Pos logit contributions
fters+0.026
isin+0.023
wheel+0.023
 IT+0.022
ner+0.022
Neg logit contributions
by-0.004
 hugs-0.003
 hopes-0.003
 luck-0.003
 looks-0.002
Token Cater
Token ID40742
Feature activation+4.76e-02

Pos logit contributions
 hopes+0.013
 hugs+0.013
 eyes+0.012
 dreams+0.012
 nods+0.012
Neg logit contributions
fters-0.020
isin-0.016
wheel-0.016
cod-0.015
str-0.015
Tokenpill
Token ID27215
Feature activation+1.84e-01

Pos logit contributions
fters+0.068
 IT+0.045
isin+0.045
 stret+0.043
str+0.042
Neg logit contributions
cy-0.100
y-0.099
 hugs-0.098
by-0.098
 looks-0.094
Tokenars
Token ID945
Feature activation-5.91e-03

Pos logit contributions
fters+0.324
ner+0.266
 IT+0.265
wheel+0.249
isin+0.247
Neg logit contributions
 hugs-0.287
 luck-0.285
 hopes-0.283
by-0.283
 nods-0.269
Token can
Token ID460
Feature activation-3.12e-02

Pos logit contributions
by+0.005
 hugs+0.005
 luck+0.005
 hopes+0.005
 looks+0.005
Neg logit contributions
fters-0.016
ner-0.013
isin-0.013
wheel-0.013
zel-0.013
Token leave
Token ID2666
Feature activation-1.31e-02

Pos logit contributions
by+0.036
 hugs+0.033
 flashlight+0.033
 hopes+0.032
 luck+0.032
Neg logit contributions
fters-0.073
oke-0.062
isin-0.060
zel-0.060
ner-0.060
Token and
Token ID290
Feature activation-1.44e-02

Pos logit contributions
by+0.014
 hugs+0.014
 back+0.013
 hopes+0.013
 luck+0.013
Neg logit contributions
fters-0.033
wheel-0.028
oke-0.027
isin-0.027
ner-0.027
Token never
Token ID1239
Feature activation-4.66e-02

Pos logit contributions
by+0.017
 hugs+0.016
 hopes+0.016
 luck+0.016
 flashlight+0.016
Neg logit contributions
fters-0.034
oke-0.028
zel-0.028
isin-0.028
ner-0.028
Token,
Token ID11
Feature activation-2.35e-02

Pos logit contributions
fters+0.033
ner+0.028
wheel+0.028
oke+0.028
isin+0.028
Neg logit contributions
by-0.008
 hopes-0.006
 flashlight-0.006
 luck-0.006
packs-0.006
Token "
Token ID366
Feature activation+5.30e-03

Pos logit contributions
 eyes+0.023
 and+0.022
 back+0.021
 to+0.021
 hugs+0.020
Neg logit contributions
fters-0.062
pieces-0.052
isin-0.052
ird-0.051
wheel-0.051
TokenI
Token ID40
Feature activation-3.82e-02

Pos logit contributions
fters+0.014
oke+0.012
isin+0.012
wheel+0.012
ner+0.012
Neg logit contributions
by-0.005
 hopes-0.004
cy-0.004
 hugs-0.004
 luck-0.004
Token love
Token ID1842
Feature activation-7.70e-02

Pos logit contributions
 eyes+0.048
by+0.048
 luck+0.045
packs+0.044
 flashlight+0.044
Neg logit contributions
fters-0.080
wheel-0.067
zel-0.066
oke-0.064
ner-0.064
Token cater
Token ID20825
Feature activation+5.79e-02

Pos logit contributions
by+0.105
 luck+0.098
 hopes+0.096
 hugs+0.096
 flashlight+0.095
Neg logit contributions
fters-0.167
wheel-0.134
isin-0.134
ner-0.133
oke-0.133
Tokenpill
Token ID27215
Feature activation+1.82e-01

Pos logit contributions
fters+0.062
 IT+0.036
zel+0.036
isin+0.036
wheel+0.035
Neg logit contributions
by-0.139
 hugs-0.135
 luck-0.132
 hopes-0.130
cy-0.130
Tokenars
Token ID945
Feature activation-4.99e-03

Pos logit contributions
fters+0.327
 IT+0.267
ner+0.262
wheel+0.242
isin+0.241
Neg logit contributions
by-0.290
 hugs-0.278
 luck-0.277
 hopes-0.264
 flashlight-0.255
Token!
Token ID0
Feature activation-1.79e-02

Pos logit contributions
 luck+0.004
by+0.004
y+0.003
 back+0.003
 hugs+0.003
Neg logit contributions
fters-0.014
isin-0.012
str-0.012
oke-0.012
wheel-0.011
Token You
Token ID921
Feature activation+1.32e-02

Pos logit contributions
 hugs+0.019
 eyes+0.019
 hopes+0.019
 nods+0.019
 looks+0.019
Neg logit contributions
fters-0.045
isin-0.037
str-0.035
zel-0.034
wheel-0.034
Token can
Token ID460
Feature activation-3.84e-02

Pos logit contributions
fters+0.034
isin+0.028
oke+0.028
wheel+0.028
ner+0.028
Neg logit contributions
by-0.013
 luck-0.012
 hopes-0.012
 hugs-0.012
 flashlight-0.012
Token be
Token ID307
Feature activation+4.53e-03

Pos logit contributions
by+0.045
 luck+0.041
 hopes+0.040
 hugs+0.040
 flashlight+0.040
Neg logit contributions
fters-0.090
oke-0.074
isin-0.073
ner-0.073
wheel-0.073
Token said
Token ID531
Feature activation+1.76e-02

Pos logit contributions
by+0.027
packs+0.025
 luck+0.024
 flashlight+0.023
cy+0.022
Neg logit contributions
fters-0.038
wheel-0.033
oke-0.033
ner-0.031
isin-0.031
Token,
Token ID11
Feature activation-1.38e-02

Pos logit contributions
fters+0.046
oke+0.041
ner+0.040
wheel+0.039
zel+0.039
Neg logit contributions
by-0.015
 flashlight-0.014
cy-0.012
packs-0.012
 hopes-0.012
Token "
Token ID366
Feature activation+1.79e-02

Pos logit contributions
 hugs+0.017
 back+0.016
 eyes+0.016
 hopes+0.015
 nods+0.015
Neg logit contributions
fters-0.032
pieces-0.026
isin-0.026
wheel-0.025
zel-0.025
TokenC
Token ID34
Feature activation+4.41e-02

Pos logit contributions
fters+0.038
oke+0.030
wheel+0.030
isin+0.030
ner+0.029
Neg logit contributions
by-0.024
 hopes-0.024
 hugs-0.023
 flashlight-0.022
cy-0.022
Tokenater
Token ID729
Feature activation+4.14e-02

Pos logit contributions
fters+0.091
isin+0.074
oke+0.072
wheel+0.072
zel+0.071
Neg logit contributions
 flashlight-0.062
 eyes-0.061
by-0.060
 hopes-0.059
 luck-0.058
Tokenpill
Token ID27215
Feature activation+1.82e-01

Pos logit contributions
fters+0.101
pieces+0.080
isin+0.080
zel+0.078
 IT+0.077
Neg logit contributions
by-0.046
 hugs-0.045
y-0.044
 looks-0.043
 luck-0.042
Tokenars
Token ID945
Feature activation-6.83e-03

Pos logit contributions
fters+0.313
ner+0.251
 IT+0.248
wheel+0.239
zel+0.235
Neg logit contributions
 hopes-0.296
 luck-0.296
by-0.295
 hugs-0.295
 flashlight-0.280
Token are
Token ID389
Feature activation-5.36e-03

Pos logit contributions
by+0.005
 hugs+0.004
 luck+0.004
 hopes+0.004
 looks+0.004
Neg logit contributions
fters-0.020
ner-0.017
isin-0.017
wheel-0.016
zel-0.016
Token not
Token ID407
Feature activation+3.57e-03

Pos logit contributions
 luck+0.006
 hugs+0.005
 back+0.005
 hopes+0.005
 close+0.004
Neg logit contributions
fters-0.015
ner-0.013
oke-0.013
istent-0.012
pieces-0.012
Token meant
Token ID4001
Feature activation+4.12e-02

Pos logit contributions
fters+0.011
ner+0.009
isin+0.009
oke+0.009
pieces+0.009
Neg logit contributions
 luck-0.003
 back-0.003
by-0.002
 home-0.002
 hugs-0.002
Token to
Token ID284
Feature activation+4.45e-02

Pos logit contributions
fters+0.138
isin+0.119
wheel+0.117
oke+0.116
uct+0.116
Neg logit contributions
 luck-0.012
by-0.010
 hugs-0.010
 eyes-0.009
 back-0.008
Token and
Token ID290
Feature activation+4.19e-03

Pos logit contributions
fters+0.081
isin+0.070
wheel+0.069
 IT+0.069
ner+0.069
Neg logit contributions
by-0.017
 hopes-0.015
 hugs-0.014
 luck-0.014
 flashlight-0.014
Token lady
Token ID10846
Feature activation+8.71e-03

Pos logit contributions
fters+0.010
wheel+0.008
isin+0.008
ner+0.008
zel+0.008
Neg logit contributions
by-0.005
 luck-0.005
 hopes-0.005
 flashlight-0.005
 hugs-0.004
Tokenbugs
Token ID32965
Feature activation+6.01e-02

Pos logit contributions
fters+0.020
 IT+0.017
wheel+0.017
ner+0.016
isin+0.016
Neg logit contributions
by-0.011
 hugs-0.010
packs-0.010
 hopes-0.010
y-0.010
Token and
Token ID290
Feature activation+5.23e-03

Pos logit contributions
fters+0.169
isin+0.144
ner+0.144
wheel+0.144
 IT+0.142
Neg logit contributions
by-0.042
 hopes-0.037
 luck-0.036
 hugs-0.036
 flashlight-0.033
Token cater
Token ID20825
Feature activation+5.47e-02

Pos logit contributions
fters+0.012
wheel+0.010
isin+0.010
ner+0.010
zel+0.010
Neg logit contributions
by-0.006
 luck-0.006
 hopes-0.006
 hugs-0.006
 flashlight-0.006
Tokenpill
Token ID27215
Feature activation+1.82e-01

Pos logit contributions
fters+0.068
wheel+0.048
zel+0.047
 IT+0.046
oke+0.045
Neg logit contributions
by-0.120
 hugs-0.119
 hopes-0.114
 luck-0.112
 dreams-0.112
Tokenars
Token ID945
Feature activation-1.77e-02

Pos logit contributions
fters+0.340
 IT+0.302
ner+0.299
 Theo+0.292
 whoever+0.280
Neg logit contributions
by-0.259
 hugs-0.258
 luck-0.254
 hopes-0.250
 hope-0.234
Token."
Token ID526
Feature activation+5.02e-02

Pos logit contributions
by+0.013
 luck+0.011
 hopes+0.011
 hugs+0.010
 eyes+0.010
Neg logit contributions
fters-0.050
wheel-0.043
isin-0.043
ner-0.042
 IT-0.042
Token
Token ID198
Feature activation+2.11e-02

Pos logit contributions
fters+0.141
isin+0.119
zel+0.118
wheel+0.118
ner+0.114
Neg logit contributions
by-0.038
 hopes-0.037
 hugs-0.035
 eyes-0.035
 nods-0.033
Token
Token ID198
Feature activation+1.79e-02

Pos logit contributions
fters+0.052
wheel+0.043
ner+0.043
zel+0.042
isin+0.042
Neg logit contributions
by-0.022
 hopes-0.020
 hugs-0.020
 flashlight-0.020
 eyes-0.019
TokenTim
Token ID14967
Feature activation+1.77e-02

Pos logit contributions
fters+0.034
ner+0.028
wheel+0.027
pieces+0.027
 IT+0.027
Neg logit contributions
by-0.027
 hopes-0.026
 flashlight-0.025
cy-0.025
packs-0.025
Token put
Token ID1234
Feature activation+1.86e-02

Pos logit contributions
fters+0.046
oke+0.042
ner+0.041
zel+0.040
pieces+0.039
Neg logit contributions
 luck-0.020
by-0.019
 hopes-0.019
 hugs-0.018
 flashlight-0.017
Token it
Token ID340
Feature activation-1.91e-02

Pos logit contributions
fters+0.040
wheel+0.032
isin+0.032
ner+0.032
zel+0.032
Neg logit contributions
by-0.025
 luck-0.023
 flashlight-0.023
 hopes-0.023
 hugs-0.022
Token back
Token ID736
Feature activation-4.86e-02

Pos logit contributions
by+0.018
 hopes+0.016
 nods+0.015
 eyes+0.015
 flashlight+0.015
Neg logit contributions
fters-0.048
wheel-0.041
zel-0.040
ner-0.039
isin-0.039
Token.
Token ID13
Feature activation-4.68e-03

Pos logit contributions
by+0.044
 luck+0.039
 hopes+0.039
 flashlight+0.038
 hugs+0.037
Neg logit contributions
fters-0.125
wheel-0.104
ner-0.104
isin-0.104
zel-0.104
Token Cater
Token ID40742
Feature activation+5.45e-02

Pos logit contributions
 hopes+0.007
by+0.006
 hugs+0.006
 eyes+0.006
 luck+0.006
Neg logit contributions
fters-0.010
wheel-0.008
isin-0.008
ner-0.008
zel-0.008
Tokenpill
Token ID27215
Feature activation+1.81e-01

Pos logit contributions
fters+0.076
isin+0.052
 IT+0.050
wheel+0.049
zel+0.048
Neg logit contributions
by-0.112
cy-0.111
 hugs-0.111
 hopes-0.108
 looks-0.108
Tokenars
Token ID945
Feature activation-4.58e-03

Pos logit contributions
fters+0.319
ner+0.268
 IT+0.267
wheel+0.253
oke+0.251
Neg logit contributions
 hopes-0.280
 luck-0.278
 hugs-0.278
by-0.273
 nods-0.260
Token need
Token ID761
Feature activation-1.97e-02

Pos logit contributions
by+0.004
 hopes+0.004
 luck+0.003
 hugs+0.003
 looks+0.003
Neg logit contributions
fters-0.012
ner-0.010
wheel-0.010
isin-0.010
oke-0.010
Token to
Token ID284
Feature activation+1.31e-02

Pos logit contributions
by+0.019
cy+0.017
 flashlight+0.016
packs+0.016
 hopes+0.016
Neg logit contributions
fters-0.049
ner-0.041
wheel-0.041
isin-0.041
zel-0.040
Token eat
Token ID4483
Feature activation-4.45e-04

Pos logit contributions
fters+0.033
oke+0.032
ner+0.030
zel+0.029
pieces+0.029
Neg logit contributions
by-0.012
 luck-0.012
 hopes-0.011
 flashlight-0.011
 close-0.011
Token leaves
Token ID5667
Feature activation-1.64e-03

Pos logit contributions
by+0.000
 luck+0.000
 hopes+0.000
 hugs+0.000
 eyes+0.000
Neg logit contributions
fters-0.001
wheel-0.001
oke-0.001
ner-0.001
isin-0.001
Token,
Token ID11
Feature activation+1.00e-02

Pos logit contributions
by+0.017
 luck+0.013
 eyes+0.012
 looks+0.010
 hopes+0.010
Neg logit contributions
fters-0.129
wheel-0.112
isin-0.111
zel-0.109
ner-0.108
Token kids
Token ID3988
Feature activation+5.94e-02

Pos logit contributions
fters+0.025
zel+0.021
wheel+0.021
isin+0.021
pieces+0.020
Neg logit contributions
 eyes-0.011
 looks-0.011
 back-0.011
 hugs-0.011
 luck-0.010
Token!"
Token ID2474
Feature activation+7.37e-02

Pos logit contributions
fters+0.178
 IT+0.153
isin+0.152
wheel+0.149
pieces+0.148
Neg logit contributions
by-0.040
 back-0.032
 hugs-0.031
,-0.031
 luck-0.031
Token the
Token ID262
Feature activation+5.39e-02

Pos logit contributions
fters+0.193
isin+0.155
wheel+0.153
zel+0.152
pieces+0.151
Neg logit contributions
 hugs-0.084
 hopes-0.083
 eyes-0.080
 looks-0.080
 nods-0.078
Token zo
Token ID40565
Feature activation+6.14e-02

Pos logit contributions
fters+0.123
wheel+0.099
 IT+0.097
isin+0.097
zel+0.096
Neg logit contributions
by-0.071
 hopes-0.067
 flashlight-0.067
 eyes-0.066
 luck-0.066
Tokenoke
Token ID2088
Feature activation+1.78e-01

Pos logit contributions
fters+0.057
 IT+0.028
isin+0.028
wheel+0.024
zel+0.023
Neg logit contributions
by-0.164
 hugs-0.156
 nods-0.154
 luck-0.154
 hopes-0.154
Tokeneper
Token ID5723
Feature activation+4.50e-02

Pos logit contributions
fters+0.352
wheel+0.277
isin+0.275
ner+0.274
zel+0.271
Neg logit contributions
by-0.276
 luck-0.257
 hopes-0.256
 flashlight-0.250
 hugs-0.250
Token said
Token ID531
Feature activation+4.04e-02

Pos logit contributions
fters+0.114
 IT+0.093
isin+0.090
pieces+0.086
icious+0.086
Neg logit contributions
by-0.051
 hugs-0.049
 back-0.047
y-0.047
 eyes-0.046
Token.
Token ID13
Feature activation+8.19e-04

Pos logit contributions
fters+0.121
isin+0.103
wheel+0.101
 IT+0.101
zel+0.100
Neg logit contributions
by-0.023
 hugs-0.020
 luck-0.019
 back-0.019
 eyes-0.019
Token "
Token ID366
Feature activation+2.14e-02

Pos logit contributions
fters+0.002
isin+0.001
wheel+0.001
pieces+0.001
zel+0.001
Neg logit contributions
 hopes-0.001
by-0.001
 eyes-0.001
 hugs-0.001
 looks-0.001
TokenThe
Token ID464
Feature activation+1.43e-02

Pos logit contributions
fters+0.049
isin+0.040
oke+0.040
wheel+0.040
pieces+0.039
Neg logit contributions
by-0.024
 hopes-0.024
cy-0.023
 nods-0.023
 back-0.022
Token dad
Token ID9955
Feature activation-5.88e-02

Pos logit contributions
by+0.042
cy+0.040
packs+0.038
 flashlight+0.038
y+0.038
Neg logit contributions
fters-0.071
isin-0.059
 IT-0.059
oke-0.059
zel-0.059
Token put
Token ID1234
Feature activation+4.09e-06

Pos logit contributions
by+0.069
 hugs+0.063
 hopes+0.061
 luck+0.061
 looks+0.060
Neg logit contributions
fters-0.147
 IT-0.118
isin-0.117
ner-0.114
wheel-0.114
Token Joe
Token ID5689
Feature activation-3.57e-02

Feature not active on prev token;
no predictions were affected.
Token on
Token ID319
Feature activation-1.58e-02

Pos logit contributions
by+0.036
 luck+0.031
 hugs+0.031
 back+0.031
 hopes+0.030
Neg logit contributions
fters-0.094
isin-0.079
oke-0.079
ner-0.078
wheel-0.077
Token his
Token ID465
Feature activation-6.91e-02

Pos logit contributions
by+0.011
 eyes+0.011
 hugs+0.010
 luck+0.010
 back+0.010
Neg logit contributions
fters-0.047
oke-0.043
isin-0.041
wheel-0.040
zel-0.040
Token shoulders
Token ID12450
Feature activation-1.31e-01

Pos logit contributions
by+0.080
 luck+0.071
 hopes+0.071
 flashlight+0.070
 hugs+0.069
Neg logit contributions
fters-0.162
wheel-0.133
isin-0.133
ner-0.132
zel-0.131
Token so
Token ID523
Feature activation+1.47e-02

Pos logit contributions
by+0.067
 luck+0.052
 flashlight+0.049
 hopes+0.048
 eyes+0.046
Neg logit contributions
fters-0.395
isin-0.338
wheel-0.337
oke-0.335
ner-0.335
Token he
Token ID339
Feature activation+2.16e-02

Pos logit contributions
fters+0.035
wheel+0.027
cod+0.027
isin+0.027
ner+0.027
Neg logit contributions
by-0.019
 luck-0.019
 back-0.017
 eyes-0.017
 hopes-0.017
Token could
Token ID714
Feature activation-1.94e-02

Pos logit contributions
fters+0.057
isin+0.046
pieces+0.045
oke+0.045
ner+0.044
Neg logit contributions
by-0.024
 hopes-0.021
 hugs-0.021
 looks-0.021
 luck-0.020
Token reach
Token ID3151
Feature activation-7.95e-03

Pos logit contributions
by+0.022
 hopes+0.021
 luck+0.021
 hugs+0.020
 flashlight+0.020
Neg logit contributions
fters-0.046
oke-0.039
isin-0.038
zel-0.037
wheel-0.037
Token the
Token ID262
Feature activation+3.52e-04

Pos logit contributions
by+0.007
 back+0.007
 luck+0.007
 eyes+0.006
 hugs+0.006
Neg logit contributions
fters-0.023
oke-0.020
zel-0.019
isin-0.019
ner-0.019
Token of
Token ID286
Feature activation+4.40e-02

Pos logit contributions
fters+0.088
isin+0.071
zel+0.071
ner+0.071
wheel+0.070
Neg logit contributions
by-0.038
 luck-0.035
 hugs-0.035
 eyes-0.035
 hopes-0.034
Token herself
Token ID5223
Feature activation-5.42e-02

Pos logit contributions
fters+0.129
zel+0.115
oke+0.113
cod+0.110
isin+0.110
Neg logit contributions
 luck-0.026
 hugs-0.025
 eyes-0.024
 hopes-0.022
by-0.021
Token and
Token ID290
Feature activation+6.75e-03

Pos logit contributions
by+0.030
 luck+0.028
 eyes+0.028
 back+0.026
 hugs+0.025
Neg logit contributions
fters-0.168
isin-0.142
ner-0.138
 IT-0.137
wheel-0.137
Token showed
Token ID3751
Feature activation-2.15e-02

Pos logit contributions
fters+0.017
oke+0.014
isin+0.014
ner+0.014
 IT+0.014
Neg logit contributions
by-0.007
 hugs-0.007
 hopes-0.007
 luck-0.007
 eyes-0.006
Token her
Token ID607
Feature activation-5.99e-02

Pos logit contributions
by+0.016
 hugs+0.013
 luck+0.013
 hopes+0.013
 eyes+0.012
Neg logit contributions
fters-0.062
isin-0.052
oke-0.052
wheel-0.052
zel-0.052
Token mom
Token ID1995
Feature activation-1.31e-01

Pos logit contributions
by+0.051
 luck+0.044
 hopes+0.044
 flashlight+0.044
 hugs+0.043
Neg logit contributions
fters-0.162
isin-0.136
wheel-0.136
ner-0.135
oke-0.134
Token what
Token ID644
Feature activation-9.30e-03

Pos logit contributions
by+0.125
 hugs+0.107
 luck+0.104
 hopes+0.100
 eyes+0.100
Neg logit contributions
fters-0.351
ner-0.294
isin-0.292
wheel-0.290
 IT-0.288
Token she
Token ID673
Feature activation+2.69e-02

Pos logit contributions
by+0.009
 hugs+0.008
 luck+0.008
 looks+0.008
 flashlight+0.008
Neg logit contributions
fters-0.025
isin-0.021
zel-0.020
oke-0.020
ner-0.020
Token had
Token ID550
Feature activation-8.22e-03

Pos logit contributions
fters+0.054
wheel+0.045
oke+0.044
zel+0.044
isin+0.043
Neg logit contributions
by-0.038
 luck-0.036
 flashlight-0.036
packs-0.035
 eyes-0.035
Token done
Token ID1760
Feature activation+3.57e-02

Pos logit contributions
by+0.012
 luck+0.011
 hopes+0.011
 hugs+0.011
 eyes+0.011
Neg logit contributions
fters-0.017
isin-0.013
ner-0.013
 IT-0.013
oke-0.013
Token.
Token ID13
Feature activation-3.62e-03

Pos logit contributions
fters+0.113
 IT+0.098
cod+0.097
ner+0.097
isin+0.097
Neg logit contributions
 luck-0.013
by-0.013
 hugs-0.011
 back-0.010
 hopes-0.009
Token
Token ID198
Feature activation-1.93e-02

Pos logit contributions
by+0.016
packs+0.015
 hopes+0.014
 close+0.013
ossible+0.012
Neg logit contributions
fters-0.048
wheel-0.042
ner-0.040
isin-0.040
oke-0.040
TokenTim
Token ID14967
Feature activation-2.36e-03

Pos logit contributions
by+0.019
packs+0.017
 close+0.017
Mom+0.016
cy+0.015
Neg logit contributions
fters-0.047
oke-0.042
wheel-0.041
ner-0.040
isin-0.040
Tokenmy
Token ID1820
Feature activation-4.59e-02

Pos logit contributions
by+0.002
 luck+0.002
 flashlight+0.002
 hopes+0.002
 hugs+0.002
Neg logit contributions
fters-0.006
wheel-0.005
isin-0.005
oke-0.005
ner-0.005
Token showed
Token ID3751
Feature activation-3.67e-02

Pos logit contributions
by+0.040
 hugs+0.036
 hopes+0.036
 looks+0.035
 nods+0.033
Neg logit contributions
fters-0.131
ner-0.109
isin-0.108
wheel-0.107
pieces-0.105
Token his
Token ID465
Feature activation-6.49e-02

Pos logit contributions
by+0.046
 luck+0.043
 hopes+0.043
 flashlight+0.042
packs+0.041
Neg logit contributions
fters-0.080
wheel-0.066
ner-0.065
isin-0.065
oke-0.064
Token mom
Token ID1995
Feature activation-1.30e-01

Pos logit contributions
by+0.061
 hopes+0.054
 luck+0.053
cy+0.052
packs+0.051
Neg logit contributions
fters-0.157
wheel-0.132
oke-0.132
isin-0.131
zel-0.131
Token the
Token ID262
Feature activation-3.69e-02

Pos logit contributions
by+0.151
 luck+0.137
 hopes+0.136
 flashlight+0.134
 hugs+0.133
Neg logit contributions
fters-0.307
wheel-0.252
isin-0.251
ner-0.251
zel-0.248
Token mark
Token ID1317
Feature activation-4.45e-02

Pos logit contributions
by+0.037
 flashlight+0.036
 luck+0.034
 eyes+0.034
 hugs+0.033
Neg logit contributions
fters-0.097
ner-0.080
isin-0.080
wheel-0.080
zel-0.079
Token and
Token ID290
Feature activation-2.38e-02

Pos logit contributions
by+0.032
 luck+0.028
 eyes+0.027
 flashlight+0.027
 hopes+0.026
Neg logit contributions
fters-0.127
isin-0.106
ner-0.106
zel-0.104
oke-0.104
Token asked
Token ID1965
Feature activation+1.50e-02

Pos logit contributions
by+0.030
 hugs+0.028
 hopes+0.028
 eyes+0.027
 flashlight+0.027
Neg logit contributions
fters-0.058
isin-0.047
oke-0.046
ner-0.045
zel-0.045
Token,
Token ID11
Feature activation-1.92e-02

Pos logit contributions
fters+0.041
wheel+0.035
isin+0.035
ner+0.035
zel+0.035
Neg logit contributions
by-0.012
 luck-0.010
 hopes-0.010
 hugs-0.010
 flashlight-0.010
Token his
Token ID465
Feature activation-5.88e-02

Pos logit contributions
by+0.081
 flashlight+0.074
 luck+0.073
 hugs+0.072
 hopes+0.071
Neg logit contributions
fters-0.140
wheel-0.123
zel-0.121
n-0.116
 IT-0.115
Token tail
Token ID7894
Feature activation-5.19e-02

Pos logit contributions
by+0.074
 luck+0.067
 hopes+0.066
 flashlight+0.065
 hugs+0.064
Neg logit contributions
fters-0.129
zel-0.106
isin-0.106
wheel-0.105
ner-0.103
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
by+0.027
 luck+0.022
 hopes+0.022
 hugs+0.021
 eyes+0.021
Neg logit contributions
fters-0.157
isin-0.134
ner-0.133
wheel-0.133
oke-0.133
Token l
Token ID300
Feature activation+4.71e-02

Pos logit contributions
by+0.018
 hugs+0.018
 hopes+0.017
 looks+0.017
 nods+0.016
Neg logit contributions
fters-0.042
ner-0.034
oke-0.034
isin-0.034
wheel-0.034
Tokenicks
Token ID3378
Feature activation-5.52e-02

Pos logit contributions
fters+0.094
oke+0.083
wheel+0.081
zel+0.080
ner+0.079
Neg logit contributions
by-0.066
 flashlight-0.063
 looks-0.058
cy-0.057
packs-0.055
Token mom
Token ID1995
Feature activation-1.29e-01

Pos logit contributions
by+0.047
 luck+0.039
 hopes+0.039
 hugs+0.039
 eyes+0.038
Neg logit contributions
fters-0.150
wheel-0.127
ner-0.126
isin-0.126
oke-0.124
Token's
Token ID338
Feature activation-6.81e-02

Pos logit contributions
by+0.109
 hugs+0.097
 eyes+0.090
 luck+0.088
 hopes+0.087
Neg logit contributions
fters-0.357
ner-0.298
wheel-0.297
isin-0.296
 IT-0.293
Token hand
Token ID1021
Feature activation-7.51e-02

Pos logit contributions
by+0.068
 luck+0.061
 hopes+0.060
 flashlight+0.059
 hugs+0.057
Neg logit contributions
fters-0.169
isin-0.141
wheel-0.141
zel-0.139
ner-0.139
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
by+0.047
 hugs+0.041
 eyes+0.040
 luck+0.039
 hopes+0.037
Neg logit contributions
fters-0.224
ner-0.189
oke-0.188
isin-0.188
wheel-0.188
Token Mom
Token ID11254
Feature activation-6.30e-02

Pos logit contributions
 eyes+0.009
 hopes+0.008
 nods+0.008
 hugs+0.008
 kisses+0.007
Neg logit contributions
fters-0.030
wheel-0.025
isin-0.024
pieces-0.023
cod-0.023
Token says
Token ID1139
Feature activation+2.14e-02

Pos logit contributions
by+0.052
 luck+0.045
 hopes+0.044
 flashlight+0.044
 hugs+0.042
Neg logit contributions
fters-0.169
wheel-0.143
isin-0.142
ner-0.142
oke-0.141
Token came
Token ID1625
Feature activation+1.56e-02

Pos logit contributions
by+0.001
 hopes+0.001
 hugs+0.001
 luck+0.001
 nods+0.001
Neg logit contributions
fters-0.003
isin-0.002
ner-0.002
wheel-0.002
zel-0.002
Token out
Token ID503
Feature activation-6.61e-03

Pos logit contributions
fters+0.029
wheel+0.025
ner+0.024
 IT+0.024
oke+0.023
Neg logit contributions
 dreams-0.019
 hopes-0.019
by-0.018
 nods-0.018
night-0.018
Token and
Token ID290
Feature activation-2.39e-02

Pos logit contributions
by+0.007
 hopes+0.007
 luck+0.007
 flashlight+0.006
 looks+0.006
Neg logit contributions
fters-0.016
ner-0.013
wheel-0.013
oke-0.013
isin-0.013
Token hugged
Token ID41130
Feature activation-6.06e-02

Pos logit contributions
by+0.021
 hugs+0.019
 hopes+0.018
 looks+0.018
 flashlight+0.017
Neg logit contributions
fters-0.066
isin-0.056
ner-0.055
wheel-0.055
oke-0.054
Token her
Token ID607
Feature activation-6.89e-02

Pos logit contributions
by+0.055
 hopes+0.048
 luck+0.048
 hugs+0.047
 flashlight+0.046
Neg logit contributions
fters-0.161
wheel-0.135
isin-0.134
oke-0.134
ner-0.133
Token mom
Token ID1995
Feature activation-1.27e-01

Pos logit contributions
by+0.070
 hopes+0.058
 luck+0.057
cy+0.056
packs+0.056
Neg logit contributions
fters-0.160
zel-0.139
wheel-0.137
ner-0.137
isin-0.136
Token.
Token ID13
Feature activation-1.59e-02

Pos logit contributions
by+0.111
 flashlight+0.106
 hopes+0.102
 luck+0.102
packs+0.092
Neg logit contributions
fters-0.315
wheel-0.269
oke-0.268
isin-0.268
zel-0.268
Token She
Token ID1375
Feature activation-1.68e-02

Pos logit contributions
by+0.021
 luck+0.019
 hopes+0.018
 flashlight+0.018
 hugs+0.018
Neg logit contributions
fters-0.035
ner-0.028
wheel-0.028
oke-0.028
isin-0.028
Token said
Token ID531
Feature activation+1.58e-02

Pos logit contributions
by+0.024
 luck+0.023
 flashlight+0.022
packs+0.022
cy+0.021
Neg logit contributions
fters-0.033
zel-0.028
wheel-0.028
isin-0.027
oke-0.027
Token,
Token ID11
Feature activation-1.75e-02

Pos logit contributions
fters+0.043
ner+0.037
oke+0.037
isin+0.036
wheel+0.036
Neg logit contributions
by-0.012
 flashlight-0.011
 hopes-0.010
cy-0.010
packs-0.010
Token "
Token ID366
Feature activation+3.49e-03

Pos logit contributions
 eyes+0.022
 hugs+0.021
 back+0.021
 flashlight+0.020
 nods+0.020
Neg logit contributions
fters-0.040
isin-0.033
pieces-0.032
wheel-0.032
cod-0.031
Token went
Token ID1816
Feature activation-1.64e-02

Pos logit contributions
fters+0.011
wheel+0.009
zel+0.009
isin+0.008
ner+0.008
Neg logit contributions
by-0.006
 luck-0.006
 flashlight-0.005
 hopes-0.005
 eyes-0.005
Token inside
Token ID2641
Feature activation-8.21e-03

Pos logit contributions
 hopes+0.018
by+0.018
 nods+0.017
 eyes+0.017
 dreams+0.017
Neg logit contributions
fters-0.037
wheel-0.034
ner-0.031
n-0.030
zel-0.030
Token and
Token ID290
Feature activation-2.05e-02

Pos logit contributions
by+0.006
 luck+0.005
 hopes+0.005
 flashlight+0.005
 hugs+0.005
Neg logit contributions
fters-0.023
wheel-0.019
ner-0.019
isin-0.019
oke-0.019
Token showed
Token ID3751
Feature activation-2.60e-02

Pos logit contributions
by+0.023
 luck+0.022
 hopes+0.021
 flashlight+0.021
 eyes+0.020
Neg logit contributions
fters-0.048
wheel-0.040
ner-0.040
isin-0.039
zel-0.039
Token her
Token ID607
Feature activation-5.71e-02

Pos logit contributions
by+0.026
packs+0.026
cy+0.026
 flashlight+0.025
 luck+0.024
Neg logit contributions
fters-0.058
wheel-0.050
 IT-0.049
ner-0.048
isin-0.048
Token mom
Token ID1995
Feature activation-1.27e-01

Pos logit contributions
by+0.064
 luck+0.058
cy+0.054
 nods+0.053
 hopes+0.053
Neg logit contributions
fters-0.126
pieces-0.106
wheel-0.105
ner-0.104
str-0.104
Token the
Token ID262
Feature activation-2.22e-02

Pos logit contributions
by+0.123
 luck+0.109
 hopes+0.108
 flashlight+0.106
 hugs+0.105
Neg logit contributions
fters-0.325
wheel-0.272
isin-0.271
ner-0.270
zel-0.268
Token bulb
Token ID28287
Feature activation-1.06e-02

Pos logit contributions
by+0.027
packs+0.023
 hopes+0.023
 luck+0.023
cy+0.022
Neg logit contributions
fters-0.051
ner-0.042
isin-0.041
wheel-0.041
 IT-0.040
Token.
Token ID13
Feature activation-1.81e-02

Pos logit contributions
by+0.011
 hopes+0.010
 luck+0.009
 flashlight+0.009
 nods+0.009
Neg logit contributions
fters-0.025
wheel-0.022
zel-0.021
oke-0.021
ner-0.021
Token Her
Token ID2332
Feature activation-2.46e-02

Pos logit contributions
by+0.025
 luck+0.023
 hopes+0.023
 flashlight+0.023
 hugs+0.023
Neg logit contributions
fters-0.038
wheel-0.031
ner-0.030
isin-0.030
zel-0.030
Token mom
Token ID1995
Feature activation-7.63e-02

Pos logit contributions
by+0.042
away+0.042
iffs+0.042
 zone+0.041
y+0.041
Neg logit contributions
fters-0.026
str-0.025
n-0.024
ird-0.022
zel-0.022
Token ambulance
Token ID22536
Feature activation+4.48e-02

Pos logit contributions
fters+0.021
wheel+0.017
ner+0.017
oke+0.017
zel+0.017
Neg logit contributions
by-0.009
 luck-0.009
 flashlight-0.009
 hugs-0.009
 eyes-0.009
Token came
Token ID1625
Feature activation+2.19e-02

Pos logit contributions
fters+0.120
isin+0.100
 IT+0.097
ner+0.096
pieces+0.096
Neg logit contributions
by-0.041
 hugs-0.038
 hopes-0.038
 flashlight-0.037
 back-0.037
Token and
Token ID290
Feature activation-2.10e-02

Pos logit contributions
fters+0.052
ner+0.045
wheel+0.045
zel+0.044
oke+0.044
Neg logit contributions
by-0.021
 hopes-0.019
 dreams-0.019
 nods-0.019
 luck-0.019
Token took
Token ID1718
Feature activation-6.62e-03

Pos logit contributions
by+0.028
 hugs+0.027
 flashlight+0.027
 hopes+0.027
 looks+0.025
Neg logit contributions
fters-0.046
isin-0.038
wheel-0.036
zel-0.036
oke-0.036
Token their
Token ID511
Feature activation-4.27e-02

Pos logit contributions
by+0.007
 luck+0.006
 hopes+0.006
 hugs+0.006
 eyes+0.006
Neg logit contributions
fters-0.017
isin-0.014
ner-0.014
wheel-0.014
oke-0.014
Token mom
Token ID1995
Feature activation-1.27e-01

Pos logit contributions
by+0.044
 luck+0.039
 hopes+0.039
 flashlight+0.038
 hugs+0.038
Neg logit contributions
fters-0.107
wheel-0.089
isin-0.088
ner-0.088
oke-0.087
Token to
Token ID284
Feature activation-1.78e-02

Pos logit contributions
by+0.117
 hugs+0.103
 back+0.100
packs+0.100
 hopes+0.095
Neg logit contributions
fters-0.346
ner-0.293
isin-0.290
wheel-0.287
 IT-0.286
Token the
Token ID262
Feature activation-2.13e-02

Pos logit contributions
 back+0.015
 hopes+0.013
 hugs+0.013
 hope+0.013
 eyes+0.012
Neg logit contributions
fters-0.050
oke-0.045
zel-0.044
isin-0.044
wheel-0.043
Token hospital
Token ID4436
Feature activation+3.60e-02

Pos logit contributions
 back+0.035
 hopes+0.034
by+0.034
 hugs+0.034
 flashlight+0.033
Neg logit contributions
fters-0.042
oke-0.033
isin-0.033
ner-0.033
wheel-0.033
Token.
Token ID13
Feature activation-4.07e-03

Pos logit contributions
fters+0.121
isin+0.106
 IT+0.104
wheel+0.102
ner+0.101
Neg logit contributions
 back-0.012
by-0.009
 hugs-0.008
 hopes-0.008
 eyes-0.008
Token The
Token ID383
Feature activation+1.33e-02

Pos logit contributions
 eyes+0.005
 hopes+0.005
 hugs+0.004
 flashlight+0.004
 looks+0.004
Neg logit contributions
fters-0.011
isin-0.009
ner-0.009
wheel-0.008
zel-0.008
Tokenup
Token ID929
Feature activation-8.18e-03

Pos logit contributions
fters+0.061
wheel+0.050
isin+0.050
zel+0.049
ner+0.049
Neg logit contributions
by-0.033
 luck-0.032
 hopes-0.032
 flashlight-0.031
 eyes-0.030
Token and
Token ID290
Feature activation-2.23e-02

Pos logit contributions
by+0.006
 luck+0.006
 hopes+0.005
 hugs+0.005
 flashlight+0.005
Neg logit contributions
fters-0.022
isin-0.019
ner-0.019
wheel-0.019
oke-0.019
Token put
Token ID1234
Feature activation+7.90e-03

Pos logit contributions
by+0.027
 luck+0.025
 hopes+0.025
 flashlight+0.024
 hugs+0.024
Neg logit contributions
fters-0.051
wheel-0.042
isin-0.041
ner-0.041
oke-0.041
Token on
Token ID319
Feature activation-6.42e-03

Pos logit contributions
fters+0.018
isin+0.015
zel+0.015
wheel+0.015
n+0.015
Neg logit contributions
by-0.009
 nods-0.008
 hopes-0.008
 flashlight-0.008
 luck-0.007
Token her
Token ID607
Feature activation-6.97e-02

Pos logit contributions
by+0.006
 hopes+0.006
 luck+0.005
cy+0.005
 nods+0.005
Neg logit contributions
fters-0.016
isin-0.013
zel-0.013
wheel-0.013
 IT-0.013
Token mom
Token ID1995
Feature activation-1.27e-01

Pos logit contributions
by+0.085
cy+0.075
 hopes+0.071
y+0.071
 nods+0.070
Neg logit contributions
fters-0.155
zel-0.131
isin-0.128
wheel-0.126
n-0.126
Token's
Token ID338
Feature activation-6.54e-02

Pos logit contributions
by+0.173
 luck+0.164
 hopes+0.164
 flashlight+0.159
 hugs+0.155
Neg logit contributions
fters-0.267
wheel-0.215
isin-0.213
zel-0.213
ner-0.211
Token clothes
Token ID8242
Feature activation-3.01e-02

Pos logit contributions
by+0.078
cy+0.069
 hopes+0.065
 luck+0.065
 nods+0.064
Neg logit contributions
fters-0.150
zel-0.124
isin-0.122
wheel-0.121
n-0.119
Token.
Token ID13
Feature activation-2.46e-02

Pos logit contributions
by+0.027
 luck+0.024
 hopes+0.023
 flashlight+0.023
 hugs+0.022
Neg logit contributions
fters-0.079
wheel-0.066
ner-0.066
isin-0.065
zel-0.065
Token One
Token ID1881
Feature activation-6.04e-02

Pos logit contributions
by+0.038
 luck+0.036
 hopes+0.035
 flashlight+0.034
 hugs+0.034
Neg logit contributions
fters-0.048
ner-0.038
wheel-0.038
isin-0.038
oke-0.037
Token day
Token ID1110
Feature activation-2.67e-02

Pos logit contributions
 hopes+0.108
 luck+0.103
 eyes+0.102
 nods+0.102
 hugs+0.101
Neg logit contributions
fters-0.089
aster-0.075
str-0.075
isin-0.074
wheel-0.074
Token ran
Token ID4966
Feature activation-1.16e-02

Pos logit contributions
by+0.029
 hopes+0.027
 hugs+0.027
 looks+0.026
 eyes+0.023
Neg logit contributions
fters-0.080
ner-0.067
isin-0.067
wheel-0.065
oke-0.065
Token home
Token ID1363
Feature activation-2.63e-02

Pos logit contributions
by+0.007
 luck+0.006
 hopes+0.006
 hugs+0.006
 flashlight+0.005
Neg logit contributions
fters-0.034
isin-0.029
oke-0.029
wheel-0.029
ner-0.029
Token and
Token ID290
Feature activation-1.66e-02

Pos logit contributions
 back+0.012
by+0.011
 hugs+0.010
 eyes+0.009
 and+0.009
Neg logit contributions
fters-0.084
isin-0.072
 IT-0.071
pieces-0.070
oke-0.070
Token showed
Token ID3751
Feature activation-2.23e-02

Pos logit contributions
by+0.018
 hugs+0.018
 flashlight+0.016
 hopes+0.016
 back+0.016
Neg logit contributions
fters-0.043
isin-0.036
oke-0.035
ner-0.034
 IT-0.033
Token his
Token ID465
Feature activation-5.28e-02

Pos logit contributions
by+0.023
 luck+0.021
 hugs+0.020
 hopes+0.020
 flashlight+0.020
Neg logit contributions
fters-0.057
isin-0.047
wheel-0.047
ner-0.047
oke-0.047
Token mom
Token ID1995
Feature activation-1.27e-01

Pos logit contributions
by+0.047
 luck+0.041
 hopes+0.040
 flashlight+0.040
 hugs+0.039
Neg logit contributions
fters-0.139
wheel-0.117
isin-0.116
ner-0.116
zel-0.115
Token his
Token ID465
Feature activation-5.73e-02

Pos logit contributions
by+0.126
 hugs+0.112
 luck+0.107
 eyes+0.104
 hopes+0.103
Neg logit contributions
fters-0.337
ner-0.283
wheel-0.281
isin-0.280
oke-0.276
Token new
Token ID649
Feature activation-5.46e-02

Pos logit contributions
by+0.059
 luck+0.054
 flashlight+0.053
 hopes+0.053
 hugs+0.052
Neg logit contributions
fters-0.146
ner-0.121
wheel-0.121
isin-0.120
oke-0.119
Token cap
Token ID1451
Feature activation-1.34e-02

Pos logit contributions
by+0.051
 luck+0.045
 hopes+0.045
 flashlight+0.044
 hugs+0.043
Neg logit contributions
fters-0.139
wheel-0.117
isin-0.116
ner-0.116
zel-0.115
Token.
Token ID13
Feature activation-1.05e-02

Pos logit contributions
by+0.009
 luck+0.008
 hugs+0.008
 flashlight+0.007
 eyes+0.007
Neg logit contributions
fters-0.039
isin-0.033
ner-0.032
oke-0.032
 IT-0.032
Token From
Token ID3574
Feature activation-1.04e-02

Pos logit contributions
 eyes+0.011
 hugs+0.010
 hopes+0.009
by+0.009
 nods+0.009
Neg logit contributions
fters-0.029
isin-0.023
cod-0.023
wheel-0.022
zel-0.022
Token arrived
Token ID5284
Feature activation+8.75e-03

Pos logit contributions
fters+0.027
isin+0.023
ner+0.023
wheel+0.023
 IT+0.023
Neg logit contributions
by-0.007
 luck-0.005
 hopes-0.005
 hugs-0.005
 flashlight-0.005
Token home
Token ID1363
Feature activation+9.12e-03

Pos logit contributions
fters+0.027
isin+0.023
wheel+0.022
ner+0.022
zel+0.022
Neg logit contributions
by-0.006
 eyes-0.005
 luck-0.005
 back-0.005
 hugs-0.005
Token and
Token ID290
Feature activation+7.77e-04

Pos logit contributions
fters+0.029
isin+0.025
 IT+0.024
cod+0.024
wheel+0.024
Neg logit contributions
by-0.005
 back-0.004
 eyes-0.004
 luck-0.004
 hugs-0.004
Token showed
Token ID3751
Feature activation-1.85e-02

Pos logit contributions
fters+0.002
isin+0.002
oke+0.002
wheel+0.002
cod+0.002
Neg logit contributions
by-0.001
 hugs-0.001
 back-0.001
 eyes-0.001
 hopes-0.001
Token her
Token ID607
Feature activation-5.60e-02

Pos logit contributions
by+0.017
 hugs+0.015
 luck+0.014
 eyes+0.013
 hopes+0.013
Neg logit contributions
fters-0.052
isin-0.043
wheel-0.043
oke-0.043
ner-0.043
Token mom
Token ID1995
Feature activation-1.27e-01

Pos logit contributions
by+0.055
 luck+0.048
 hugs+0.048
 hopes+0.048
 flashlight+0.047
Neg logit contributions
fters-0.146
isin-0.122
wheel-0.120
oke-0.120
ner-0.120
Token the
Token ID262
Feature activation-3.52e-02

Pos logit contributions
by+0.120
 hugs+0.104
 luck+0.100
 eyes+0.096
 back+0.095
Neg logit contributions
fters-0.344
ner-0.288
wheel-0.287
isin-0.287
oke-0.284
Token nail
Token ID17864
Feature activation+1.99e-03

Pos logit contributions
by+0.035
 flashlight+0.034
 luck+0.033
 hugs+0.032
 eyes+0.032
Neg logit contributions
fters-0.092
ner-0.077
oke-0.077
wheel-0.077
isin-0.076
Token.
Token ID13
Feature activation-8.98e-03

Pos logit contributions
fters+0.006
isin+0.005
oke+0.005
ner+0.005
 IT+0.005
Neg logit contributions
by-0.001
 back-0.001
 luck-0.001
 hugs-0.001
 eyes-0.001
Token Her
Token ID2332
Feature activation-2.00e-02

Pos logit contributions
 eyes+0.007
 hugs+0.006
 hopes+0.005
 kisses+0.005
 nods+0.005
Neg logit contributions
fters-0.027
cod-0.023
isin-0.023
wheel-0.022
zel-0.021
Token mom
Token ID1995
Feature activation-7.03e-02

Pos logit contributions
by+0.020
 luck+0.017
cy+0.017
 hopes+0.017
packs+0.017
Neg logit contributions
fters-0.047
wheel-0.040
zel-0.040
isin-0.040
 IT-0.039
Token doctor
Token ID6253
Feature activation+7.39e-03

Pos logit contributions
fters+0.012
pieces+0.010
oke+0.010
zel+0.010
orse+0.010
Neg logit contributions
 luck-0.007
 hugs-0.007
 hopes-0.007
 back-0.007
by-0.007
Token.
Token ID13
Feature activation-8.24e-03

Pos logit contributions
fters+0.024
isin+0.020
 IT+0.020
wheel+0.019
ner+0.019
Neg logit contributions
by-0.004
 back-0.004
 luck-0.003
 hugs-0.003
 hopes-0.003
Token He
Token ID679
Feature activation-1.67e-02

Pos logit contributions
 hugs+0.008
 hopes+0.007
 eyes+0.007
 kisses+0.006
by+0.006
Neg logit contributions
fters-0.024
wheel-0.019
isin-0.019
cod-0.019
zel-0.019
Token handed
Token ID10158
Feature activation-5.25e-03

Pos logit contributions
by+0.017
 hopes+0.016
 hugs+0.016
 luck+0.015
 looks+0.015
Neg logit contributions
fters-0.044
ner-0.036
isin-0.035
oke-0.035
wheel-0.035
Token her
Token ID607
Feature activation-6.51e-02

Pos logit contributions
by+0.005
 luck+0.005
 hopes+0.005
 flashlight+0.005
 eyes+0.004
Neg logit contributions
fters-0.013
ner-0.011
wheel-0.011
isin-0.011
zel-0.011
Token mom
Token ID1995
Feature activation-1.26e-01

Pos logit contributions
by+0.057
 hugs+0.054
 luck+0.052
 hopes+0.050
 back+0.050
Neg logit contributions
fters-0.181
oke-0.153
isin-0.152
ner-0.152
wheel-0.151
Token a
Token ID257
Feature activation-6.40e-02

Pos logit contributions
by+0.107
 hugs+0.089
 luck+0.087
 hopes+0.082
 back+0.080
Neg logit contributions
fters-0.356
ner-0.298
wheel-0.297
isin-0.297
oke-0.295
Token piece
Token ID3704
Feature activation-3.10e-02

Pos logit contributions
by+0.060
 flashlight+0.055
 hugs+0.054
 luck+0.052
 hopes+0.049
Neg logit contributions
fters-0.170
wheel-0.140
isin-0.139
ner-0.139
oke-0.139
Token of
Token ID286
Feature activation+1.43e-02

Pos logit contributions
by+0.037
 luck+0.033
 hopes+0.033
 hugs+0.033
 flashlight+0.032
Neg logit contributions
fters-0.073
isin-0.059
ner-0.059
wheel-0.058
oke-0.058
Token paper
Token ID3348
Feature activation-1.58e-02

Pos logit contributions
fters+0.035
oke+0.031
wheel+0.030
ner+0.029
zel+0.029
Neg logit contributions
 hugs-0.017
by-0.015
 eyes-0.015
 luck-0.015
 flashlight-0.015
Token with
Token ID351
Feature activation+3.68e-03

Pos logit contributions
by+0.008
 luck+0.007
 hugs+0.006
 eyes+0.006
 flashlight+0.006
Neg logit contributions
fters-0.048
isin-0.041
oke-0.041
ner-0.041
wheel-0.041
Token
Token ID198
Feature activation-1.03e-02

Pos logit contributions
 hugs+0.008
 hopes+0.008
 eyes+0.007
 dreams+0.007
packs+0.007
Neg logit contributions
fters-0.041
isin-0.034
wheel-0.033
cod-0.033
zel-0.032
Token
Token ID198
Feature activation-7.09e-03

Pos logit contributions
by+0.010
 hopes+0.009
 hugs+0.008
packs+0.008
 flashlight+0.008
Neg logit contributions
fters-0.027
wheel-0.023
ner-0.023
isin-0.022
zel-0.022
TokenShe
Token ID3347
Feature activation-2.44e-02

Pos logit contributions
by+0.006
 close+0.006
Mom+0.005
packs+0.005
 hopes+0.005
Neg logit contributions
fters-0.017
oke-0.016
wheel-0.015
ner-0.015
isin-0.015
Token showed
Token ID3751
Feature activation-2.83e-02

Pos logit contributions
by+0.026
 hopes+0.024
 hugs+0.024
 luck+0.023
 looks+0.022
Neg logit contributions
fters-0.061
isin-0.051
wheel-0.050
ner-0.050
oke-0.049
Token her
Token ID607
Feature activation-5.86e-02

Pos logit contributions
by+0.026
 luck+0.023
 hopes+0.023
 flashlight+0.023
 hugs+0.022
Neg logit contributions
fters-0.072
wheel-0.061
ner-0.061
isin-0.061
zel-0.060
Token mom
Token ID1995
Feature activation-1.26e-01

Pos logit contributions
by+0.054
 luck+0.048
 hopes+0.048
 flashlight+0.047
 hugs+0.046
Neg logit contributions
fters-0.153
wheel-0.127
isin-0.127
ner-0.127
zel-0.126
Token and
Token ID290
Feature activation-2.88e-02

Pos logit contributions
by+0.140
 luck+0.126
 hopes+0.125
 flashlight+0.123
 hugs+0.122
Neg logit contributions
fters-0.304
wheel-0.251
isin-0.250
ner-0.249
oke-0.247
Token dad
Token ID9955
Feature activation-8.98e-02

Pos logit contributions
by+0.029
 luck+0.025
 hopes+0.025
 flashlight+0.025
 hugs+0.025
Neg logit contributions
fters-0.073
wheel-0.061
isin-0.061
ner-0.060
zel-0.060
Token her
Token ID607
Feature activation-4.86e-02

Pos logit contributions
by+0.085
 hugs+0.074
 luck+0.073
 hopes+0.071
 eyes+0.069
Neg logit contributions
fters-0.240
wheel-0.201
isin-0.200
ner-0.199
zel-0.196
Token drawing
Token ID8263
Feature activation-1.98e-02

Pos logit contributions
by+0.051
 eyes+0.048
 hugs+0.048
 hopes+0.048
 flashlight+0.048
Neg logit contributions
fters-0.124
ner-0.101
wheel-0.101
isin-0.101
zel-0.099
Token.
Token ID13
Feature activation-7.88e-03

Pos logit contributions
by+0.017
 luck+0.014
 hopes+0.014
 flashlight+0.014
 hugs+0.014
Neg logit contributions
fters-0.053
wheel-0.044
isin-0.044
ner-0.044
oke-0.044
Token.
Token ID13
Feature activation-2.21e-03

Pos logit contributions
by+0.043
 luck+0.037
 hopes+0.037
 flashlight+0.036
 hugs+0.036
Neg logit contributions
fters-0.149
isin-0.126
wheel-0.125
ner-0.125
zel-0.125
Token Lily
Token ID20037
Feature activation+1.30e-02

Pos logit contributions
 eyes+0.002
 hopes+0.002
by+0.002
 hugs+0.002
 luck+0.002
Neg logit contributions
fters-0.006
isin-0.005
zel-0.004
pieces-0.004
str-0.004
Token climbs
Token ID34332
Feature activation+2.21e-02

Pos logit contributions
fters+0.032
wheel+0.026
isin+0.026
ner+0.026
zel+0.026
Neg logit contributions
by-0.014
 luck-0.012
 hopes-0.012
 flashlight-0.012
 hugs-0.012
Token on
Token ID319
Feature activation-1.65e-02

Pos logit contributions
fters+0.056
ner+0.047
wheel+0.047
isin+0.046
zel+0.046
Neg logit contributions
by-0.021
 flashlight-0.018
 hopes-0.018
 luck-0.018
 hugs-0.017
Token his
Token ID465
Feature activation-6.80e-02

Pos logit contributions
by+0.021
 luck+0.019
 hopes+0.019
 flashlight+0.019
 hugs+0.019
Neg logit contributions
fters-0.037
wheel-0.030
ner-0.029
isin-0.029
zel-0.029
Token shoulders
Token ID12450
Feature activation-1.26e-01

Pos logit contributions
by+0.079
cy+0.070
 hopes+0.068
 luck+0.067
 hugs+0.066
Neg logit contributions
fters-0.158
isin-0.128
wheel-0.128
 IT-0.128
zel-0.128
Token.
Token ID13
Feature activation-3.24e-04

Pos logit contributions
by+0.108
 hopes+0.098
 flashlight+0.096
 luck+0.095
 hugs+0.094
Neg logit contributions
fters-0.322
ner-0.279
wheel-0.278
zel-0.272
isin-0.271
Token She
Token ID1375
Feature activation-7.77e-03

Pos logit contributions
by+0.000
 luck+0.000
 hopes+0.000
 flashlight+0.000
 hugs+0.000
Neg logit contributions
fters-0.001
wheel-0.001
ner-0.001
isin-0.001
oke-0.001
Token holds
Token ID6622
Feature activation-2.93e-02

Pos logit contributions
by+0.009
 luck+0.008
 hopes+0.008
 flashlight+0.008
 hugs+0.008
Neg logit contributions
fters-0.018
wheel-0.015
isin-0.015
ner-0.015
zel-0.015
Token the
Token ID262
Feature activation-1.42e-02

Pos logit contributions
by+0.042
 flashlight+0.039
 luck+0.038
 hopes+0.037
 eyes+0.037
Neg logit contributions
fters-0.057
ner-0.046
wheel-0.046
 IT-0.045
isin-0.045
Token stick
Token ID4859
Feature activation-1.04e-02

Pos logit contributions
by+0.017
 luck+0.016
 flashlight+0.016
 eyes+0.016
 hopes+0.016
Neg logit contributions
fters-0.033
oke-0.027
wheel-0.027
ner-0.027
isin-0.027
Token and
Token ID290
Feature activation-3.23e-02

Pos logit contributions
by+0.018
 hugs+0.014
 luck+0.013
 hopes+0.013
 back+0.012
Neg logit contributions
fters-0.100
isin-0.085
wheel-0.084
ner-0.084
oke-0.084
Token carried
Token ID5281
Feature activation-1.90e-02

Pos logit contributions
by+0.041
 hugs+0.039
 flashlight+0.038
 hopes+0.038
 luck+0.037
Neg logit contributions
fters-0.076
isin-0.061
oke-0.060
ner-0.059
zel-0.059
Token her
Token ID607
Feature activation-7.23e-02

Pos logit contributions
by+0.013
 hugs+0.011
 luck+0.011
 hopes+0.010
 flashlight+0.010
Neg logit contributions
fters-0.055
oke-0.047
isin-0.047
wheel-0.047
ner-0.046
Token on
Token ID319
Feature activation-1.44e-02

Pos logit contributions
by+0.053
 luck+0.045
 hopes+0.044
 flashlight+0.043
 hugs+0.042
Neg logit contributions
fters-0.200
wheel-0.170
ner-0.169
isin-0.169
zel-0.168
Token his
Token ID465
Feature activation-6.78e-02

Pos logit contributions
by+0.014
 luck+0.012
 hopes+0.012
 flashlight+0.012
 hugs+0.012
Neg logit contributions
fters-0.037
oke-0.031
wheel-0.031
isin-0.031
ner-0.031
Token shoulders
Token ID12450
Feature activation-1.26e-01

Pos logit contributions
by+0.076
 luck+0.067
 hopes+0.067
cy+0.065
 hugs+0.063
Neg logit contributions
fters-0.160
isin-0.131
wheel-0.130
ner-0.129
zel-0.129
Token.
Token ID13
Feature activation-8.43e-03

Pos logit contributions
by+0.095
 hopes+0.083
 luck+0.083
 flashlight+0.080
 hugs+0.079
Neg logit contributions
fters-0.342
wheel-0.291
ner-0.290
isin-0.289
zel-0.287
Token She
Token ID1375
Feature activation-4.30e-03

Pos logit contributions
 eyes+0.009
 hugs+0.009
 hopes+0.008
 looks+0.008
 back+0.008
Neg logit contributions
fters-0.023
cod-0.019
isin-0.019
keys-0.019
str-0.018
Token gigg
Token ID30442
Feature activation-1.15e-02

Pos logit contributions
by+0.005
 hopes+0.005
 hugs+0.005
 flashlight+0.004
 luck+0.004
Neg logit contributions
fters-0.010
isin-0.008
ner-0.008
wheel-0.008
oke-0.008
Tokenled
Token ID992
Feature activation-2.24e-02

Pos logit contributions
by+0.013
 flashlight+0.013
 hopes+0.012
 luck+0.012
packs+0.012
Neg logit contributions
fters-0.027
isin-0.022
oke-0.022
ner-0.022
zel-0.022
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
by+0.024
 flashlight+0.021
packs+0.021
 hopes+0.021
 luck+0.020
Neg logit contributions
fters-0.051
wheel-0.044
zel-0.043
ner-0.043
 IT-0.043
Token she
Token ID673
Feature activation+1.25e-03

Pos logit contributions
fters+0.063
wheel+0.053
isin+0.053
ner+0.053
oke+0.053
Neg logit contributions
by-0.013
 luck-0.011
 hopes-0.011
 flashlight-0.010
 hugs-0.010
Token would
Token ID561
Feature activation-3.62e-02

Pos logit contributions
fters+0.003
wheel+0.002
zel+0.002
oke+0.002
isin+0.002
Neg logit contributions
by-0.001
 luck-0.001
 flashlight-0.001
packs-0.001
 hopes-0.001
Token and
Token ID290
Feature activation-1.57e-02

Pos logit contributions
by+0.039
 hopes+0.037
 luck+0.037
 hugs+0.036
 back+0.035
Neg logit contributions
fters-0.090
oke-0.077
ner-0.075
isin-0.075
pieces-0.072
Token gave
Token ID2921
Feature activation-6.13e-03

Pos logit contributions
by+0.017
 hugs+0.016
 hopes+0.016
 flashlight+0.015
 looks+0.015
Neg logit contributions
fters-0.040
isin-0.034
oke-0.034
zel-0.033
ner-0.033
Token her
Token ID607
Feature activation-6.07e-02

Pos logit contributions
by+0.006
 luck+0.005
 hopes+0.005
 hugs+0.005
 flashlight+0.005
Neg logit contributions
fters-0.016
wheel-0.014
oke-0.013
isin-0.013
zel-0.013
Token mom
Token ID1995
Feature activation-1.26e-01

Pos logit contributions
by+0.058
 luck+0.052
 hopes+0.051
 flashlight+0.051
 hugs+0.051
Neg logit contributions
fters-0.159
isin-0.132
wheel-0.132
ner-0.131
oke-0.131
Token a
Token ID257
Feature activation-6.51e-02

Pos logit contributions
by+0.119
 luck+0.105
 hopes+0.103
 hugs+0.101
 flashlight+0.101
Neg logit contributions
fters-0.324
wheel-0.271
ner-0.270
isin-0.270
oke-0.268
Token big
Token ID1263
Feature activation-6.73e-02

Pos logit contributions
by+0.049
 hopes+0.044
 luck+0.042
packs+0.040
 eyes+0.039
Neg logit contributions
fters-0.171
wheel-0.150
zel-0.147
isin-0.147
ner-0.147
Token hug
Token ID16225
Feature activation-8.33e-02

Pos logit contributions
by+0.049
packs+0.040
 hopes+0.038
 luck+0.035
cy+0.034
Neg logit contributions
fters-0.175
wheel-0.155
ner-0.154
oke-0.152
isin-0.151
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
by+0.055
 luck+0.048
 hugs+0.045
 hopes+0.045
 eyes+0.044
Neg logit contributions
fters-0.240
isin-0.203
oke-0.201
ner-0.201
wheel-0.200
Token From
Token ID3574
Feature activation-1.22e-02

Pos logit contributions
 eyes+0.014
 hugs+0.013
by+0.013
 hopes+0.013
packs+0.012
Neg logit contributions
fters-0.040
isin-0.033
cod-0.032
wheel-0.032
zel-0.032
Token her
Token ID607
Feature activation-5.07e-02

Pos logit contributions
by+0.005
 hugs+0.004
 hopes+0.004
 luck+0.004
 flashlight+0.004
Neg logit contributions
fters-0.032
isin-0.028
wheel-0.027
zel-0.027
oke-0.027
Token house
Token ID2156
Feature activation-4.08e-02

Pos logit contributions
by+0.059
 luck+0.053
 hopes+0.051
cy+0.050
 hugs+0.049
Neg logit contributions
fters-0.113
wheel-0.094
isin-0.092
zel-0.092
ner-0.092
Token and
Token ID290
Feature activation-8.11e-03

Pos logit contributions
by+0.019
 hopes+0.016
 hugs+0.016
 eyes+0.016
 luck+0.015
Neg logit contributions
fters-0.125
isin-0.108
zel-0.106
ner-0.106
wheel-0.106
Token showed
Token ID3751
Feature activation-2.21e-02

Pos logit contributions
by+0.009
 hugs+0.009
 hopes+0.008
 flashlight+0.008
 looks+0.008
Neg logit contributions
fters-0.021
isin-0.017
oke-0.017
ner-0.017
zel-0.016
Token her
Token ID607
Feature activation-5.89e-02

Pos logit contributions
by+0.019
 flashlight+0.018
packs+0.018
 luck+0.017
 hopes+0.017
Neg logit contributions
fters-0.054
wheel-0.047
isin-0.046
 IT-0.046
ner-0.046
Token mom
Token ID1995
Feature activation-1.25e-01

Pos logit contributions
by+0.053
 luck+0.046
 hopes+0.046
 flashlight+0.045
 hugs+0.044
Neg logit contributions
fters-0.154
wheel-0.130
isin-0.129
ner-0.129
zel-0.128
Token the
Token ID262
Feature activation-2.23e-02

Pos logit contributions
by+0.112
 hugs+0.097
 luck+0.096
 hopes+0.095
 eyes+0.092
Neg logit contributions
fters-0.336
ner-0.283
wheel-0.281
isin-0.281
zel-0.277
Token bad
Token ID2089
Feature activation-1.51e-02

Pos logit contributions
by+0.024
 flashlight+0.023
 luck+0.023
 hopes+0.022
 hugs+0.022
Neg logit contributions
fters-0.054
oke-0.045
ner-0.045
zel-0.045
isin-0.045
Token boo
Token ID22513
Feature activation+2.67e-02

Pos logit contributions
by+0.017
packs+0.017
 hopes+0.016
cy+0.016
 hugs+0.016
Neg logit contributions
fters-0.033
wheel-0.028
isin-0.028
ner-0.027
oke-0.027
Token-
Token ID12
Feature activation+5.53e-02

Pos logit contributions
fters+0.071
wheel+0.063
zel+0.062
isin+0.062
oke+0.061
Neg logit contributions
by-0.020
 flashlight-0.018
 hopes-0.018
 luck-0.017
packs-0.017
Tokenbo
Token ID2127
Feature activation-2.27e-02

Pos logit contributions
fters+0.130
oke+0.104
ner+0.104
 IT+0.103
isin+0.100
Neg logit contributions
by-0.072
 hugs-0.060
cy-0.059
y-0.059
 hopes-0.057
Token
Token ID198
Feature activation-1.01e-02

Pos logit contributions
 eyes+0.007
 nods+0.007
 hopes+0.007
 back+0.007
 hugs+0.006
Neg logit contributions
fters-0.027
isin-0.022
wheel-0.021
cod-0.021
zel-0.020
Token
Token ID198
Feature activation-9.12e-03

Pos logit contributions
by+0.008
 hopes+0.007
 hugs+0.007
packs+0.006
 flashlight+0.006
Neg logit contributions
fters-0.028
wheel-0.024
isin-0.023
ner-0.023
zel-0.023
TokenThey
Token ID2990
Feature activation-1.88e-02

Pos logit contributions
by+0.008
 hopes+0.007
packs+0.007
 close+0.007
cy+0.006
Neg logit contributions
fters-0.024
wheel-0.020
ner-0.020
oke-0.020
isin-0.020
Token showed
Token ID3751
Feature activation-3.14e-02

Pos logit contributions
by+0.018
 hugs+0.016
 hopes+0.016
 flashlight+0.015
 eyes+0.015
Neg logit contributions
fters-0.051
isin-0.043
ner-0.042
oke-0.042
wheel-0.041
Token their
Token ID511
Feature activation-2.88e-02

Pos logit contributions
by+0.038
 luck+0.035
 flashlight+0.035
 hopes+0.035
packs+0.033
Neg logit contributions
fters-0.069
wheel-0.057
isin-0.056
oke-0.056
ner-0.056
Token mom
Token ID1995
Feature activation-1.25e-01

Pos logit contributions
by+0.027
 luck+0.025
 hopes+0.024
 flashlight+0.023
cy+0.023
Neg logit contributions
fters-0.071
wheel-0.059
isin-0.059
oke-0.059
zel-0.059
Token the
Token ID262
Feature activation-3.39e-02

Pos logit contributions
by+0.139
 luck+0.124
 hopes+0.123
 hugs+0.123
 flashlight+0.120
Neg logit contributions
fters-0.306
wheel-0.253
ner-0.252
isin-0.251
zel-0.248
Token crystals
Token ID24770
Feature activation-3.05e-02

Pos logit contributions
by+0.035
 flashlight+0.033
 luck+0.032
 hugs+0.031
 hopes+0.031
Neg logit contributions
fters-0.086
isin-0.071
ner-0.071
wheel-0.071
zel-0.071
Token they
Token ID484
Feature activation-5.90e-03

Pos logit contributions
by+0.027
 hopes+0.024
 luck+0.024
 flashlight+0.023
 hugs+0.023
Neg logit contributions
fters-0.079
wheel-0.067
ner-0.066
isin-0.066
oke-0.066
Token found
Token ID1043
Feature activation+3.87e-03

Pos logit contributions
by+0.007
 luck+0.006
 hopes+0.006
 flashlight+0.006
 hugs+0.006
Neg logit contributions
fters-0.014
wheel-0.011
isin-0.011
ner-0.011
zel-0.011
Token.
Token ID13
Feature activation-8.28e-03

Pos logit contributions
fters+0.011
wheel+0.009
isin+0.009
ner+0.009
zel+0.009
Neg logit contributions
by-0.003
 luck-0.003
 hopes-0.002
 hugs-0.002
 eyes-0.002
Token picture
Token ID4286
Feature activation-1.37e-02

Pos logit contributions
by+0.022
 luck+0.022
 eyes+0.022
 flashlight+0.021
 hugs+0.021
Neg logit contributions
fters-0.054
wheel-0.044
isin-0.044
ner-0.043
oke-0.043
Token.
Token ID13
Feature activation-6.62e-03

Pos logit contributions
by+0.010
 luck+0.009
 hugs+0.008
 eyes+0.008
 flashlight+0.008
Neg logit contributions
fters-0.039
isin-0.033
oke-0.032
ner-0.032
 IT-0.032
Token She
Token ID1375
Feature activation-9.09e-04

Pos logit contributions
 hopes+0.003
 eyes+0.003
 hugs+0.003
by+0.003
 nods+0.003
Neg logit contributions
fters-0.021
isin-0.018
cod-0.018
zel-0.017
wheel-0.017
Token showed
Token ID3751
Feature activation-2.63e-02

Pos logit contributions
by+0.001
 hugs+0.001
 hopes+0.001
 looks+0.001
 eyes+0.001
Neg logit contributions
fters-0.002
isin-0.002
ner-0.002
oke-0.002
wheel-0.002
Token her
Token ID607
Feature activation-5.44e-02

Pos logit contributions
by+0.034
 luck+0.031
 hopes+0.031
 hugs+0.030
 flashlight+0.030
Neg logit contributions
fters-0.059
wheel-0.048
isin-0.048
ner-0.048
oke-0.048
Token mom
Token ID1995
Feature activation-1.25e-01

Pos logit contributions
by+0.047
 hopes+0.041
 luck+0.041
 hugs+0.040
 flashlight+0.040
Neg logit contributions
fters-0.147
wheel-0.123
isin-0.123
ner-0.123
oke-0.122
Token,
Token ID11
Feature activation-2.03e-02

Pos logit contributions
by+0.120
 luck+0.104
 hugs+0.103
 hopes+0.102
 eyes+0.099
Neg logit contributions
fters-0.328
wheel-0.274
ner-0.273
isin-0.273
oke-0.269
Token who
Token ID508
Feature activation+3.24e-02

Pos logit contributions
 hugs+0.017
 eyes+0.017
 hopes+0.016
by+0.015
 back+0.015
Neg logit contributions
fters-0.058
isin-0.048
wheel-0.047
ner-0.047
oke-0.046
Token smiled
Token ID13541
Feature activation-4.66e-02

Pos logit contributions
fters+0.091
isin+0.075
 IT+0.074
wheel+0.073
zel+0.072
Neg logit contributions
by-0.028
 hugs-0.025
 hopes-0.025
 looks-0.024
 luck-0.023
Token and
Token ID290
Feature activation-2.29e-02

Pos logit contributions
by+0.052
 flashlight+0.051
 hopes+0.050
 hugs+0.048
packs+0.048
Neg logit contributions
fters-0.085
zel-0.080
wheel-0.079
 IT-0.077
oke-0.076
Token said
Token ID531
Feature activation+1.89e-02

Pos logit contributions
by+0.031
 hugs+0.029
 luck+0.029
 hopes+0.029
 eyes+0.028
Neg logit contributions
fters-0.051
isin-0.040
ner-0.040
oke-0.040
wheel-0.040
Token went
Token ID1816
Feature activation-1.39e-02

Pos logit contributions
fters+0.022
isin+0.018
ner+0.018
wheel+0.018
oke+0.017
Neg logit contributions
by-0.008
 hugs-0.007
 hopes-0.007
 looks-0.006
 eyes-0.006
Token home
Token ID1363
Feature activation-2.00e-02

Pos logit contributions
by+0.010
 hopes+0.009
 luck+0.009
 flashlight+0.008
 eyes+0.008
Neg logit contributions
fters-0.038
wheel-0.033
ner-0.032
zel-0.032
isin-0.031
Token and
Token ID290
Feature activation-6.73e-03

Pos logit contributions
by+0.008
 back+0.007
 hugs+0.007
 hopes+0.007
 eyes+0.006
Neg logit contributions
fters-0.063
isin-0.055
 IT-0.053
pieces-0.053
oke-0.053
Token showed
Token ID3751
Feature activation-2.26e-02

Pos logit contributions
by+0.008
 hugs+0.007
 hopes+0.007
 flashlight+0.007
 luck+0.007
Neg logit contributions
fters-0.016
oke-0.013
isin-0.013
ner-0.013
wheel-0.013
Token her
Token ID607
Feature activation-5.66e-02

Pos logit contributions
by+0.018
 luck+0.016
 flashlight+0.016
 hopes+0.015
packs+0.015
Neg logit contributions
fters-0.059
wheel-0.051
ner-0.050
isin-0.050
 IT-0.049
Token mom
Token ID1995
Feature activation-1.25e-01

Pos logit contributions
by+0.050
 luck+0.044
 hopes+0.043
 flashlight+0.041
 hugs+0.040
Neg logit contributions
fters-0.145
wheel-0.123
ner-0.122
isin-0.121
zel-0.121
Token the
Token ID262
Feature activation-2.63e-02

Pos logit contributions
by+0.136
 luck+0.121
 hugs+0.119
 hopes+0.119
 flashlight+0.117
Neg logit contributions
fters-0.309
ner-0.255
wheel-0.255
isin-0.254
oke-0.252
Token bracelet
Token ID42893
Feature activation-1.25e-02

Pos logit contributions
by+0.024
 luck+0.023
 flashlight+0.023
 hopes+0.022
 hugs+0.022
Neg logit contributions
fters-0.068
wheel-0.057
oke-0.057
ner-0.057
isin-0.057
Token.
Token ID13
Feature activation-4.78e-03

Pos logit contributions
by+0.011
 hopes+0.009
 luck+0.009
 flashlight+0.009
 hugs+0.009
Neg logit contributions
fters-0.033
wheel-0.028
ner-0.028
isin-0.028
zel-0.028
Token Her
Token ID2332
Feature activation-2.01e-02

Pos logit contributions
by+0.005
 eyes+0.005
 hopes+0.005
 hugs+0.005
 flashlight+0.005
Neg logit contributions
fters-0.012
isin-0.010
wheel-0.009
ner-0.009
zel-0.009
Token mom
Token ID1995
Feature activation-7.17e-02

Pos logit contributions
by+0.028
y+0.027
cy+0.027
ucks+0.026
packs+0.025
Neg logit contributions
fters-0.034
zel-0.029
wheel-0.028
isin-0.028
n-0.028
Token She
Token ID1375
Feature activation-8.88e-03

Pos logit contributions
by+0.014
 eyes+0.013
 hugs+0.013
 hopes+0.013
 flashlight+0.012
Neg logit contributions
fters-0.042
isin-0.035
wheel-0.034
zel-0.034
oke-0.034
Token ran
Token ID4966
Feature activation-2.08e-02

Pos logit contributions
by+0.009
 hopes+0.008
 hugs+0.008
 looks+0.008
 flashlight+0.007
Neg logit contributions
fters-0.023
isin-0.019
ner-0.019
wheel-0.019
oke-0.019
Token and
Token ID290
Feature activation-3.80e-02

Pos logit contributions
by+0.018
 hopes+0.017
 luck+0.017
 nods+0.016
 flashlight+0.016
Neg logit contributions
fters-0.052
wheel-0.046
ner-0.045
zel-0.044
 IT-0.044
Token pulled
Token ID5954
Feature activation-1.77e-02

Pos logit contributions
by+0.041
 hugs+0.038
 flashlight+0.036
 hopes+0.036
 luck+0.035
Neg logit contributions
fters-0.095
isin-0.079
oke-0.079
wheel-0.077
ner-0.076
Token her
Token ID607
Feature activation-6.84e-02

Pos logit contributions
by+0.017
 hopes+0.015
 nods+0.014
packs+0.014
 flashlight+0.014
Neg logit contributions
fters-0.045
ner-0.038
wheel-0.038
isin-0.037
 IT-0.037
Token mom
Token ID1995
Feature activation-1.25e-01

Pos logit contributions
by+0.075
 hopes+0.067
 nods+0.065
 luck+0.064
cy+0.062
Neg logit contributions
fters-0.157
wheel-0.135
 IT-0.130
zel-0.129
ner-0.129
Token's
Token ID338
Feature activation-6.11e-02

Pos logit contributions
by+0.107
 hugs+0.089
 luck+0.087
 flashlight+0.087
 back+0.087
Neg logit contributions
fters-0.340
isin-0.286
ner-0.283
oke-0.282
wheel-0.281
Token hand
Token ID1021
Feature activation-7.84e-02

Pos logit contributions
by+0.054
 hopes+0.047
 luck+0.047
 flashlight+0.045
 hugs+0.044
Neg logit contributions
fters-0.159
wheel-0.134
isin-0.133
ner-0.132
zel-0.132
Token down
Token ID866
Feature activation-1.12e-02

Pos logit contributions
by+0.058
 luck+0.049
 flashlight+0.048
 hopes+0.048
 hugs+0.047
Neg logit contributions
fters-0.218
isin-0.184
wheel-0.184
ner-0.183
oke-0.183
Token the
Token ID262
Feature activation-8.03e-03

Pos logit contributions
by+0.011
 hopes+0.009
 luck+0.009
 flashlight+0.009
 hugs+0.009
Neg logit contributions
fters-0.028
ner-0.024
wheel-0.024
isin-0.023
zel-0.023
Token hallway
Token ID23959
Feature activation+2.74e-02

Pos logit contributions
by+0.013
 hugs+0.012
 flashlight+0.012
 hopes+0.012
 luck+0.012
Neg logit contributions
fters-0.016
isin-0.012
oke-0.012
ner-0.012
zel-0.012
Token hill
Token ID12788
Feature activation-6.64e-03

Pos logit contributions
by+0.051
 flashlight+0.047
 luck+0.046
 eyes+0.045
 looks+0.045
Neg logit contributions
fters-0.117
wheel-0.097
isin-0.096
zel-0.095
ner-0.095
Token.
Token ID13
Feature activation-1.40e-02

Pos logit contributions
by+0.003
y+0.003
 looks+0.003
cy+0.003
 back+0.003
Neg logit contributions
fters-0.020
isin-0.018
 IT-0.017
zel-0.017
pieces-0.017
Token The
Token ID383
Feature activation+1.63e-02

Pos logit contributions
 eyes+0.012
 looks+0.009
 names+0.008
 hugs+0.008
 to+0.008
Neg logit contributions
fters-0.044
isin-0.040
cod-0.036
zel-0.035
iable-0.035
Token rh
Token ID9529
Feature activation+8.93e-02

Pos logit contributions
fters+0.034
wheel+0.028
pieces+0.027
zel+0.026
isin+0.026
Neg logit contributions
 luck-0.024
by-0.024
 eyes-0.024
 hopes-0.023
 back-0.023
Tokenin
Token ID259
Feature activation+4.02e-02

Pos logit contributions
fters+0.235
 IT+0.201
wheel+0.201
isin+0.194
pieces+0.193
Neg logit contributions
by-0.084
y-0.070
cy-0.066
 luck-0.064
 hopes-0.061
Tokenoc
Token ID420
Feature activation+1.25e-01

Pos logit contributions
fters+0.091
wheel+0.072
ner+0.070
 IT+0.070
pieces+0.070
Neg logit contributions
by-0.060
 looks-0.053
y-0.051
cy-0.051
 hopes-0.051
Tokeneros
Token ID27498
Feature activation+3.32e-02

Pos logit contributions
fters+0.238
ner+0.188
oke+0.187
isin+0.187
wheel+0.186
Neg logit contributions
by-0.194
 flashlight-0.185
 hopes-0.181
 luck-0.180
packs-0.179
Token said
Token ID531
Feature activation+1.38e-02

Pos logit contributions
fters+0.105
isin+0.091
pieces+0.088
 IT+0.086
ner+0.086
Neg logit contributions
by-0.020
 looks-0.018
y-0.017
 and-0.016
 looked-0.014
Token,
Token ID11
Feature activation-2.14e-02

Pos logit contributions
fters+0.043
isin+0.037
wheel+0.037
zel+0.036
ner+0.036
Neg logit contributions
by-0.006
 luck-0.005
 eyes-0.005
 hugs-0.005
 hopes-0.004
Token �
Token ID6184
Feature activation+4.61e-02

Pos logit contributions
 eyes+0.018
 back+0.018
 to+0.018
 and+0.018
,+0.017
Neg logit contributions
fters-0.061
isin-0.052
pieces-0.051
ird-0.051
wheel-0.050
Token�
Token ID95
Feature activation+6.76e-02

Pos logit contributions
fters+0.087
pieces+0.068
isin+0.067
oke+0.064
wheel+0.064
Neg logit contributions
 looks-0.070
by-0.070
 luck-0.068
 nods-0.065
 hopes-0.065
Token.
Token ID13
Feature activation+2.32e-03

Pos logit contributions
by+0.019
 luck+0.016
y+0.015
 back+0.014
 hugs+0.013
Neg logit contributions
fters-0.110
 IT-0.094
isin-0.094
zel-0.092
wheel-0.092
Token She
Token ID1375
Feature activation+6.41e-03

Pos logit contributions
fters+0.006
wheel+0.005
isin+0.005
zel+0.005
ner+0.005
Neg logit contributions
by-0.002
 hopes-0.002
 hugs-0.002
 nods-0.002
 looks-0.002
Token thanked
Token ID26280
Feature activation-2.29e-02

Pos logit contributions
fters+0.016
isin+0.013
ner+0.013
wheel+0.013
oke+0.013
Neg logit contributions
by-0.007
 hugs-0.006
 hopes-0.006
 luck-0.006
 eyes-0.006
Token the
Token ID262
Feature activation+4.35e-03

Pos logit contributions
by+0.020
 hugs+0.018
 eyes+0.018
 luck+0.017
 back+0.017
Neg logit contributions
fters-0.062
wheel-0.054
zel-0.054
oke-0.053
isin-0.052
Token zo
Token ID40565
Feature activation+4.10e-02

Pos logit contributions
fters+0.011
pieces+0.009
wheel+0.009
 IT+0.009
isin+0.009
Neg logit contributions
 hugs-0.005
 luck-0.005
 hopes-0.004
by-0.004
 looks-0.004
Tokenoke
Token ID2088
Feature activation+1.45e-01

Pos logit contributions
fters+0.056
 IT+0.036
uct+0.033
hers+0.031
isin+0.030
Neg logit contributions
by-0.093
y-0.088
 luck-0.086
 hugs-0.086
 nods-0.085
Tokeneper
Token ID5723
Feature activation+1.03e-02

Pos logit contributions
fters+0.323
wheel+0.260
isin+0.258
 IT+0.258
ner+0.255
Neg logit contributions
by-0.202
 luck-0.186
 hopes-0.182
 hugs-0.176
 back-0.173
Token for
Token ID329
Feature activation+4.82e-02

Pos logit contributions
fters+0.033
 IT+0.028
isin+0.028
wheel+0.028
ner+0.028
Neg logit contributions
by-0.005
 hugs-0.003
 back-0.003
 luck-0.003
 eyes-0.003
Token his
Token ID465
Feature activation-2.90e-02

Pos logit contributions
fters+0.115
oke+0.104
zel+0.100
wheel+0.097
isin+0.096
Neg logit contributions
 luck-0.052
 hugs-0.052
 back-0.049
 eyes-0.047
 hopes-0.046
Token advice
Token ID5608
Feature activation-6.81e-02

Pos logit contributions
by+0.033
 hopes+0.030
 luck+0.030
 flashlight+0.029
 hugs+0.029
Neg logit contributions
fters-0.068
wheel-0.056
isin-0.056
ner-0.056
zel-0.055
Token and
Token ID290
Feature activation-6.42e-03

Pos logit contributions
by+0.019
 luck+0.013
 back+0.012
 hugs+0.010
 hopes+0.009
Neg logit contributions
fters-0.225
 IT-0.196
wheel-0.193
isin-0.192
cod-0.191
Token big
Token ID1263
Feature activation-3.48e-02

Pos logit contributions
by+0.028
 flashlight+0.025
 luck+0.025
 hopes+0.025
 hugs+0.024
Neg logit contributions
fters-0.061
wheel-0.051
ner-0.050
isin-0.050
oke-0.049
Token ostr
Token ID42387
Feature activation+1.09e-01

Pos logit contributions
by+0.038
 luck+0.034
 hopes+0.034
 flashlight+0.033
 hugs+0.033
Neg logit contributions
fters-0.085
wheel-0.070
isin-0.070
ner-0.070
zel-0.069
Tokenich
Token ID488
Feature activation+4.02e-02

Pos logit contributions
fters+0.234
wheel+0.191
 IT+0.186
isin+0.185
ner+0.184
Neg logit contributions
by-0.153
 eyes-0.134
 luck-0.133
 hopes-0.130
 flashlight-0.128
Token.
Token ID13
Feature activation-2.19e-02

Pos logit contributions
fters+0.097
isin+0.079
ner+0.078
 IT+0.078
oke+0.078
Neg logit contributions
by-0.046
 hopes-0.042
 hugs-0.041
 flashlight-0.041
y-0.040
Token The
Token ID383
Feature activation+6.16e-03

Pos logit contributions
by+0.031
 eyes+0.030
 hopes+0.030
 flashlight+0.029
 hugs+0.029
Neg logit contributions
fters-0.046
isin-0.037
wheel-0.036
zel-0.036
oke-0.035
Token ostr
Token ID42387
Feature activation+1.25e-01

Pos logit contributions
fters+0.010
isin+0.008
wheel+0.008
ner+0.007
oke+0.007
Neg logit contributions
by-0.011
 luck-0.011
 hopes-0.011
 flashlight-0.011
 hugs-0.011
Tokenich
Token ID488
Feature activation+4.85e-02

Pos logit contributions
fters+0.270
wheel+0.223
 IT+0.215
ner+0.214
isin+0.211
Neg logit contributions
by-0.174
 eyes-0.155
 hopes-0.154
 luck-0.152
cy-0.145
Token liked
Token ID8288
Feature activation-5.54e-02

Pos logit contributions
fters+0.130
ner+0.108
isin+0.108
wheel+0.107
 IT+0.106
Neg logit contributions
by-0.044
 hopes-0.038
 hugs-0.037
 flashlight-0.037
 luck-0.036
Token to
Token ID284
Feature activation+2.66e-02

Pos logit contributions
by+0.021
 hugs+0.015
 luck+0.015
 eyes+0.015
 hopes+0.014
Neg logit contributions
fters-0.176
isin-0.153
ner-0.152
wheel-0.152
oke-0.152
Token swim
Token ID9422
Feature activation-2.45e-02

Pos logit contributions
fters+0.065
oke+0.057
ner+0.055
zel+0.055
isin+0.055
Neg logit contributions
by-0.027
 flashlight-0.026
 hopes-0.025
 hugs-0.025
 luck-0.025
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
 hugs+0.035
 hopes+0.034
 kisses+0.034
 eyes+0.033
 nods+0.033
Neg logit contributions
fters-0.040
zel-0.036
wheel-0.034
nes-0.032
n-0.031
Token trapped
Token ID13640
Feature activation+5.69e-02

Pos logit contributions
fters+0.035
isin+0.028
ner+0.028
wheel+0.028
oke+0.028
Neg logit contributions
by-0.021
 luck-0.021
 hopes-0.021
 eyes-0.021
 flashlight-0.021
Token with
Token ID351
Feature activation+2.23e-02

Pos logit contributions
fters+0.127
ner+0.110
wheel+0.105
oke+0.104
zel+0.103
Neg logit contributions
by-0.066
 nods-0.057
 flashlight-0.056
 hugs-0.056
 hopes-0.055
Token the
Token ID262
Feature activation+1.05e-02

Pos logit contributions
fters+0.052
wheel+0.043
isin+0.043
ner+0.043
zel+0.042
Neg logit contributions
by-0.026
 luck-0.024
 hopes-0.023
 flashlight-0.023
 hugs-0.023
Token rh
Token ID9529
Feature activation+8.67e-02

Pos logit contributions
fters+0.024
wheel+0.020
 IT+0.020
ner+0.019
zel+0.019
Neg logit contributions
 luck-0.013
 flashlight-0.013
by-0.013
 hopes-0.013
 eyes-0.013
Tokenin
Token ID259
Feature activation+2.88e-02

Pos logit contributions
fters+0.226
 IT+0.196
wheel+0.194
isin+0.187
pieces+0.184
Neg logit contributions
by-0.079
y-0.068
cy-0.063
 luck-0.062
 flashlight-0.059
Tokenoc
Token ID420
Feature activation+1.35e-01

Pos logit contributions
fters+0.060
 IT+0.048
wheel+0.048
isin+0.046
ner+0.046
Neg logit contributions
by-0.045
 hopes-0.041
y-0.041
 flashlight-0.041
 hugs-0.040
Tokeneros
Token ID27498
Feature activation+2.16e-02

Pos logit contributions
fters+0.264
isin+0.208
ner+0.208
oke+0.207
wheel+0.207
Neg logit contributions
by-0.206
 flashlight-0.193
 hopes-0.191
 luck-0.190
 hugs-0.186
Token.
Token ID13
Feature activation+9.92e-03

Pos logit contributions
fters+0.066
isin+0.057
wheel+0.056
ner+0.056
 IT+0.056
Neg logit contributions
by-0.012
 hopes-0.010
 luck-0.009
 back-0.009
 flashlight-0.009
Token They
Token ID1119
Feature activation+3.03e-03

Pos logit contributions
fters+0.027
wheel+0.023
isin+0.023
ner+0.022
pieces+0.021
Neg logit contributions
 hopes-0.009
 eyes-0.009
by-0.009
 hugs-0.008
packs-0.008
Token looked
Token ID3114
Feature activation-3.35e-02

Pos logit contributions
fters+0.007
isin+0.006
wheel+0.006
ner+0.006
oke+0.006
Neg logit contributions
by-0.004
 hopes-0.004
 flashlight-0.003
 hugs-0.003
 luck-0.003
Token for
Token ID329
Feature activation+5.89e-02

Pos logit contributions
by+0.041
cy+0.034
packs+0.034
 luck+0.034
ucks+0.034
Neg logit contributions
fters-0.072
oke-0.060
zel-0.059
 IT-0.058
wheel-0.057
Token,"
Token ID553
Feature activation+7.25e-02

Pos logit contributions
fters+0.058
wheel+0.050
zel+0.050
isin+0.049
 IT+0.048
Neg logit contributions
by-0.012
 eyes-0.011
 luck-0.010
 back-0.010
 hugs-0.010
Token said
Token ID531
Feature activation+4.36e-02

Pos logit contributions
fters+0.226
cod+0.193
icious+0.192
oke+0.182
isin+0.181
Neg logit contributions
 hugs-0.056
 looks-0.048
 her-0.046
 eyes-0.043
 and-0.042
Token the
Token ID262
Feature activation+2.08e-02

Pos logit contributions
fters+0.127
isin+0.105
cod+0.105
pill+0.101
oke+0.100
Neg logit contributions
 back-0.040
by-0.037
 hugs-0.035
 eyes-0.034
,-0.032
Token rh
Token ID9529
Feature activation+8.29e-02

Pos logit contributions
fters+0.045
wheel+0.036
pieces+0.034
 IT+0.033
isin+0.033
Neg logit contributions
by-0.031
 eyes-0.030
 luck-0.030
 hugs-0.030
 hopes-0.030
Tokenin
Token ID259
Feature activation+3.33e-02

Pos logit contributions
fters+0.221
 IT+0.186
wheel+0.185
isin+0.182
ner+0.179
Neg logit contributions
by-0.078
y-0.062
 luck-0.062
cy-0.059
 hopes-0.059
Tokenoc
Token ID420
Feature activation+1.27e-01

Pos logit contributions
fters+0.079
 IT+0.060
ner+0.058
wheel+0.058
isin+0.058
Neg logit contributions
by-0.052
y-0.044
 looks-0.042
 hugs-0.042
 hopes-0.042
Tokeneros
Token ID27498
Feature activation+2.82e-02

Pos logit contributions
fters+0.270
wheel+0.216
isin+0.214
ner+0.213
zel+0.211
Neg logit contributions
by-0.179
 luck-0.164
 hopes-0.162
 hugs-0.159
 eyes-0.157
Token.
Token ID13
Feature activation-7.65e-03

Pos logit contributions
fters+0.092
isin+0.077
ner+0.076
 IT+0.075
wheel+0.074
Neg logit contributions
by-0.016
 back-0.012
 hugs-0.011
 eyes-0.010
 luck-0.010
Token "
Token ID366
Feature activation+1.25e-02

Pos logit contributions
 back+0.006
 eyes+0.006
 hugs+0.006
 down+0.005
 and+0.005
Neg logit contributions
fters-0.023
cod-0.019
isin-0.019
pieces-0.018
keys-0.018
TokenI
Token ID40
Feature activation-3.00e-02

Pos logit contributions
fters+0.030
oke+0.026
isin+0.025
ner+0.025
wheel+0.025
Neg logit contributions
by-0.013
cy-0.012
 hopes-0.012
y-0.011
 nods-0.011
Token'm
Token ID1101
Feature activation+3.06e-02

Pos logit contributions
by+0.033
 luck+0.030
 hopes+0.030
 flashlight+0.029
 hugs+0.029
Neg logit contributions
fters-0.073
isin-0.060
wheel-0.060
ner-0.060
oke-0.059
Token trips
Token ID13229
Feature activation-3.10e-02

Pos logit contributions
ucks+0.015
eddy+0.014
y+0.014
pt+0.014
 shone+0.013
Neg logit contributions
fters-0.018
str-0.015
n-0.015
pieces-0.014
oke-0.013
Token,
Token ID11
Feature activation-2.10e-02

Pos logit contributions
by+0.017
 luck+0.014
 hopes+0.013
 flashlight+0.013
 hugs+0.013
Neg logit contributions
fters-0.092
wheel-0.079
isin-0.079
ner-0.078
zel-0.078
Token they
Token ID484
Feature activation+1.54e-02

Pos logit contributions
 flashlight+0.020
 eyes+0.020
by+0.019
 looks+0.018
 luck+0.018
Neg logit contributions
fters-0.055
isin-0.048
wheel-0.047
oke-0.047
zel-0.046
Token encountered
Token ID12956
Feature activation+2.17e-02

Pos logit contributions
fters+0.037
wheel+0.030
ner+0.030
zel+0.030
oke+0.029
Neg logit contributions
by-0.016
 luck-0.015
 hugs-0.015
 hopes-0.015
 flashlight-0.014
Token an
Token ID281
Feature activation-1.15e-02

Pos logit contributions
fters+0.046
wheel+0.038
oke+0.038
ner+0.038
zel+0.037
Neg logit contributions
by-0.026
cy-0.024
 hopes-0.023
 flashlight-0.023
 nods-0.022
Token elderly
Token ID13830
Feature activation+8.05e-02

Pos logit contributions
by+0.014
 luck+0.013
 flashlight+0.013
 hopes+0.013
 eyes+0.013
Neg logit contributions
fters-0.027
ner-0.022
zel-0.022
wheel-0.022
isin-0.022
Token person
Token ID1048
Feature activation+9.04e-03

Pos logit contributions
fters+0.213
 IT+0.171
uct+0.169
wheel+0.168
isin+0.168
Neg logit contributions
by-0.083
 flashlight-0.077
 hugs-0.075
 eyes-0.071
y-0.070
Token.
Token ID13
Feature activation-1.38e-02

Pos logit contributions
fters+0.024
isin+0.021
 IT+0.020
wheel+0.020
ner+0.020
Neg logit contributions
by-0.008
packs-0.008
 hugs-0.007
 hopes-0.007
y-0.007
Token This
Token ID770
Feature activation+3.35e-02

Pos logit contributions
 eyes+0.010
 looks+0.010
 hugs+0.009
cy+0.009
 nods+0.008
Neg logit contributions
fters-0.043
isin-0.037
wheel-0.035
zel-0.033
cod-0.033
Token elderly
Token ID13830
Feature activation+9.78e-02

Pos logit contributions
fters+0.079
wheel+0.065
ner+0.064
isin+0.064
zel+0.064
Neg logit contributions
by-0.039
 luck-0.035
 hopes-0.035
 flashlight-0.034
 hugs-0.034
Token person
Token ID1048
Feature activation+2.20e-02

Pos logit contributions
fters+0.264
 IT+0.220
wheel+0.215
isin+0.213
icious+0.208
Neg logit contributions
 hugs-0.097
by-0.094
 nods-0.089
 looks-0.088
,-0.088
Token day
Token ID1110
Feature activation-2.09e-02

Pos logit contributions
by+0.077
 luck+0.069
 hopes+0.069
 flashlight+0.068
 hugs+0.067
Neg logit contributions
fters-0.164
wheel-0.135
isin-0.135
ner-0.134
oke-0.133
Token long
Token ID890
Feature activation-4.13e-03

Pos logit contributions
,+0.010
by+0.009
 and+0.009
 to+0.009
 back+0.008
Neg logit contributions
fters-0.063
cod-0.056
pieces-0.056
oke-0.056
isin-0.055
Token.
Token ID13
Feature activation-1.63e-02

Pos logit contributions
 eyes+0.001
 hugs+0.001
 luck+0.001
 back+0.001
by+0.001
Neg logit contributions
fters-0.013
str-0.012
oke-0.012
isin-0.012
zel-0.011
Token He
Token ID679
Feature activation-1.87e-02

Pos logit contributions
by+0.022
 luck+0.020
 hopes+0.020
 flashlight+0.020
 hugs+0.020
Neg logit contributions
fters-0.035
wheel-0.028
ner-0.028
isin-0.028
oke-0.028
Token was
Token ID373
Feature activation-3.97e-03

Pos logit contributions
by+0.018
 hopes+0.016
 flashlight+0.015
 hugs+0.015
 luck+0.015
Neg logit contributions
fters-0.049
ner-0.041
isin-0.041
oke-0.041
wheel-0.041
Token very
Token ID845
Feature activation+5.53e-02

Pos logit contributions
 back+0.004
 luck+0.003
 hopes+0.003
 hugs+0.003
 close+0.003
Neg logit contributions
fters-0.010
oke-0.010
ner-0.009
isin-0.009
pieces-0.009
Token happy
Token ID3772
Feature activation+1.84e-02

Pos logit contributions
fters+0.130
ner+0.106
wheel+0.106
pieces+0.105
oke+0.104
Neg logit contributions
by-0.066
 luck-0.062
 hopes-0.061
 hugs-0.059
cy-0.056
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
fters+0.039
wheel+0.034
ner+0.034
zel+0.033
oke+0.032
Neg logit contributions
by-0.022
 flashlight-0.020
 hopes-0.019
 hugs-0.019
 luck-0.019
Token
Token ID198
Feature activation-6.90e-03

Pos logit contributions
by+0.017
 luck+0.015
 hopes+0.015
 flashlight+0.015
 hugs+0.015
Neg logit contributions
fters-0.027
wheel-0.022
ner-0.022
isin-0.022
oke-0.022
Token
Token ID198
Feature activation-5.70e-03

Pos logit contributions
 luck+0.011
by+0.011
 eyes+0.010
 hopes+0.010
 flashlight+0.010
Neg logit contributions
fters-0.013
oke-0.010
ner-0.010
wheel-0.010
isin-0.010
TokenOne
Token ID3198
Feature activation-5.90e-02

Pos logit contributions
by+0.009
 luck+0.008
 hopes+0.008
 eyes+0.008
 hugs+0.008
Neg logit contributions
fters-0.012
wheel-0.009
isin-0.009
zel-0.009
ner-0.009
Token and
Token ID290
Feature activation+6.44e-03

Pos logit contributions
fters+0.056
wheel+0.047
isin+0.047
ner+0.047
oke+0.046
Neg logit contributions
by-0.017
 luck-0.015
 hopes-0.015
 eyes-0.015
 hugs-0.014
Token it
Token ID340
Feature activation+1.33e-02

Pos logit contributions
fters+0.017
isin+0.014
oke+0.014
zel+0.014
 IT+0.014
Neg logit contributions
by-0.006
 luck-0.006
 hopes-0.005
 looks-0.005
 back-0.005
Token got
Token ID1392
Feature activation+1.78e-02

Pos logit contributions
fters+0.033
isin+0.027
ner+0.027
oke+0.027
wheel+0.027
Neg logit contributions
by-0.014
 hopes-0.013
 luck-0.012
 flashlight-0.012
 hugs-0.012
Token bigger
Token ID5749
Feature activation+3.70e-02

Pos logit contributions
fters+0.042
wheel+0.034
isin+0.034
ner+0.034
oke+0.034
Neg logit contributions
by-0.021
 luck-0.019
 hopes-0.019
 flashlight-0.019
 hugs-0.019
Token and
Token ID290
Feature activation+1.13e-03

Pos logit contributions
fters+0.102
wheel+0.086
isin+0.086
ner+0.086
zel+0.085
Neg logit contributions
by-0.028
 luck-0.024
 hopes-0.023
 flashlight-0.023
 hugs-0.022
Token bigger
Token ID5749
Feature activation+4.26e-02

Pos logit contributions
fters+0.003
isin+0.002
oke+0.002
zel+0.002
ner+0.002
Neg logit contributions
by-0.001
 luck-0.001
 hopes-0.001
 flashlight-0.001
 hugs-0.001
Token.
Token ID13
Feature activation-3.28e-03

Pos logit contributions
fters+0.117
isin+0.099
wheel+0.098
ner+0.098
zel+0.097
Neg logit contributions
by-0.033
 luck-0.030
 hopes-0.029
 eyes-0.028
 flashlight-0.028
Token Everyone
Token ID11075
Feature activation+6.43e-03

Pos logit contributions
 eyes+0.003
 hugs+0.003
 looks+0.002
 hopes+0.002
 nods+0.002
Neg logit contributions
fters-0.010
isin-0.008
pieces-0.008
keys-0.008
cod-0.008
Token could
Token ID714
Feature activation-2.33e-02

Pos logit contributions
fters+0.017
isin+0.014
wheel+0.014
ner+0.014
zel+0.014
Neg logit contributions
by-0.006
 hopes-0.005
 hugs-0.005
 luck-0.005
 flashlight-0.005
Token hear
Token ID3285
Feature activation-3.45e-03

Pos logit contributions
by+0.028
 luck+0.025
 hopes+0.025
 flashlight+0.025
 hugs+0.024
Neg logit contributions
fters-0.054
isin-0.044
wheel-0.044
ner-0.044
oke-0.044
Token it
Token ID340
Feature activation+5.12e-03

Pos logit contributions
by+0.003
 hugs+0.003
 hopes+0.003
 eyes+0.003
 luck+0.003
Neg logit contributions
fters-0.009
wheel-0.007
isin-0.007
ner-0.007
zel-0.007
Token The
Token ID383
Feature activation+2.42e-02

Pos logit contributions
fters+0.028
wheel+0.023
isin+0.023
ner+0.022
zel+0.022
Neg logit contributions
 hopes-0.009
 eyes-0.009
by-0.009
 hugs-0.009
packs-0.008
Token sun
Token ID4252
Feature activation-2.73e-03

Pos logit contributions
fters+0.059
ner+0.049
oke+0.049
wheel+0.049
isin+0.049
Neg logit contributions
by-0.026
 luck-0.024
 flashlight-0.024
 hugs-0.024
 hopes-0.023
Token had
Token ID550
Feature activation-2.34e-02

Pos logit contributions
by+0.003
 luck+0.002
 hopes+0.002
 flashlight+0.002
 hugs+0.002
Neg logit contributions
fters-0.007
wheel-0.006
isin-0.006
ner-0.006
zel-0.006
Token made
Token ID925
Feature activation-1.55e-02

Pos logit contributions
by+0.025
 luck+0.023
 hopes+0.022
 flashlight+0.022
 hugs+0.022
Neg logit contributions
fters-0.057
wheel-0.047
isin-0.047
ner-0.047
oke-0.047
Token the
Token ID262
Feature activation+2.13e-02

Pos logit contributions
by+0.016
 luck+0.014
 eyes+0.014
 hugs+0.014
 flashlight+0.014
Neg logit contributions
fters-0.039
wheel-0.033
ner-0.032
isin-0.032
zel-0.032
Token plastic
Token ID7309
Feature activation+3.65e-02

Pos logit contributions
fters+0.052
ner+0.043
oke+0.043
isin+0.043
wheel+0.043
Neg logit contributions
by-0.023
 luck-0.022
 flashlight-0.021
 eyes-0.021
 hugs-0.021
Token soft
Token ID2705
Feature activation-1.93e-02

Pos logit contributions
fters+0.091
wheel+0.076
isin+0.076
ner+0.075
zel+0.075
Neg logit contributions
by-0.037
 luck-0.033
 hopes-0.032
 flashlight-0.032
 hugs-0.031
Token and
Token ID290
Feature activation+1.00e-02

Pos logit contributions
by+0.019
 hopes+0.017
 luck+0.016
 flashlight+0.016
packs+0.015
Neg logit contributions
fters-0.047
wheel-0.040
isin-0.040
ner-0.039
zel-0.039
Token bend
Token ID19396
Feature activation-3.78e-02

Pos logit contributions
fters+0.027
wheel+0.023
ner+0.023
oke+0.023
isin+0.023
Neg logit contributions
by-0.008
 luck-0.007
 hopes-0.007
 flashlight-0.007
 hugs-0.007
Tokeny
Token ID88
Feature activation-1.61e-02

Pos logit contributions
by+0.024
 hopes+0.021
 luck+0.021
 flashlight+0.020
 hugs+0.020
Neg logit contributions
fters-0.105
wheel-0.091
zel-0.090
isin-0.090
ner-0.090
Token.
Token ID13
Feature activation+1.86e-03

Pos logit contributions
by+0.016
 eyes+0.015
 luck+0.014
 flashlight+0.014
 hugs+0.014
Neg logit contributions
fters-0.042
ner-0.035
oke-0.035
isin-0.035
wheel-0.034
Token when
Token ID618
Feature activation+3.30e-02

Pos logit contributions
fters+0.007
wheel+0.005
oke+0.005
isin+0.005
zel+0.005
Neg logit contributions
by-0.004
 luck-0.004
 hopes-0.004
 eyes-0.004
 dreams-0.004
Token she
Token ID673
Feature activation+3.58e-02

Pos logit contributions
fters+0.066
wheel+0.053
isin+0.052
oke+0.052
zel+0.052
Neg logit contributions
by-0.051
 luck-0.049
 hopes-0.048
 flashlight-0.046
 eyes-0.046
Token was
Token ID373
Feature activation+2.48e-02

Pos logit contributions
fters+0.092
isin+0.077
zel+0.075
ner+0.075
 IT+0.075
Neg logit contributions
by-0.037
 hopes-0.032
 luck-0.032
 looks-0.031
 hugs-0.031
Token done
Token ID1760
Feature activation+6.42e-02

Pos logit contributions
fters+0.053
cod+0.046
isin+0.044
zel+0.044
keys+0.043
Neg logit contributions
 luck-0.035
 back-0.034
 eyes-0.032
 hugs-0.032
by-0.031
Token,
Token ID11
Feature activation+2.20e-02

Pos logit contributions
fters+0.215
cod+0.196
isin+0.192
zel+0.187
oke+0.186
Neg logit contributions
,-0.016
 luck-0.014
 eyes-0.013
 back-0.010
 looks-0.008
Token Fre
Token ID4848
Feature activation+9.40e-02

Pos logit contributions
fters+0.051
wheel+0.042
isin+0.041
oke+0.041
zel+0.041
Neg logit contributions
by-0.028
 luck-0.027
 hopes-0.027
 eyes-0.025
 hugs-0.025
Tokenya
Token ID3972
Feature activation+6.20e-02

Pos logit contributions
fters+0.164
wheel+0.128
ner+0.124
isin+0.123
zel+0.122
Neg logit contributions
by-0.166
 luck-0.156
 hopes-0.155
 hugs-0.151
 flashlight-0.151
Token realized
Token ID6939
Feature activation+2.53e-02

Pos logit contributions
fters+0.176
isin+0.148
 IT+0.142
cod+0.142
wheel+0.140
Neg logit contributions
by-0.057
 looks-0.052
 hopes-0.051
 hugs-0.049
 back-0.045
Token that
Token ID326
Feature activation+1.65e-02

Pos logit contributions
fters+0.070
oke+0.059
zel+0.059
isin+0.059
cod+0.058
Neg logit contributions
 luck-0.020
 eyes-0.019
 hopes-0.019
 hugs-0.019
by-0.018
Token the
Token ID262
Feature activation+4.67e-02

Pos logit contributions
fters+0.042
zel+0.036
isin+0.036
oke+0.035
cod+0.034
Neg logit contributions
 luck-0.017
 dreams-0.016
 hopes-0.016
by-0.016
 looks-0.016
Token stair
Token ID18761
Feature activation+6.58e-02

Pos logit contributions
fters+0.102
zel+0.085
isin+0.084
oke+0.084
wheel+0.082
Neg logit contributions
 luck-0.060
 flashlight-0.060
by-0.059
 hopes-0.058
 hugs-0.057
Token Her
Token ID2332
Feature activation-1.19e-02

Pos logit contributions
fters+0.093
wheel+0.075
ner+0.074
isin+0.073
n+0.073
Neg logit contributions
by-0.079
 luck-0.077
 flashlight-0.073
 hopes-0.072
packs-0.070
Token mom
Token ID1995
Feature activation-5.57e-02

Pos logit contributions
by+0.022
away+0.022
 zone+0.021
night+0.021
cy+0.020
Neg logit contributions
fters-0.012
 Theo-0.010
oke-0.010
zel-0.010
str-0.010
Token said
Token ID531
Feature activation+2.15e-02

Pos logit contributions
by+0.086
 luck+0.081
 hopes+0.080
 flashlight+0.079
packs+0.078
Neg logit contributions
fters-0.107
wheel-0.086
oke-0.085
isin-0.085
ner-0.084
Token,
Token ID11
Feature activation-1.70e-02

Pos logit contributions
fters+0.055
oke+0.048
ner+0.048
wheel+0.047
isin+0.047
Neg logit contributions
by-0.020
packs-0.018
 flashlight-0.017
 hopes-0.017
 luck-0.017
Token "
Token ID366
Feature activation+1.04e-02

Pos logit contributions
 eyes+0.022
 hugs+0.022
 back+0.020
 looks+0.020
 nods+0.020
Neg logit contributions
fters-0.038
isin-0.031
wheel-0.030
pieces-0.030
zel-0.030
TokenThat
Token ID2504
Feature activation-1.84e-02

Pos logit contributions
fters+0.021
wheel+0.017
isin+0.017
ner+0.017
oke+0.017
Neg logit contributions
by-0.015
 luck-0.014
 hopes-0.014
 flashlight-0.014
 hugs-0.014
Token is
Token ID318
Feature activation-4.20e-04

Pos logit contributions
packs+0.021
 flashlight+0.019
by+0.019
cy+0.018
 hugs+0.018
Neg logit contributions
fters-0.039
zel-0.034
isin-0.033
wheel-0.032
 IT-0.032
Token a
Token ID257
Feature activation+2.56e-04

Pos logit contributions
by+0.000
 luck+0.000
 eyes+0.000
 hopes+0.000
 flashlight+0.000
Neg logit contributions
fters-0.001
ner-0.001
wheel-0.001
isin-0.001
oke-0.001
Token jelly
Token ID27644
Feature activation+6.90e-02

Pos logit contributions
fters+0.000
isin+0.000
zel+0.000
 IT+0.000
wheel+0.000
Neg logit contributions
packs-0.000
by-0.000
 hugs-0.000
 nods-0.000
cy-0.000
Tokenfish
Token ID11084
Feature activation+2.89e-02

Pos logit contributions
fters+0.149
wheel+0.121
isin+0.120
ner+0.119
zel+0.119
Neg logit contributions
by-0.092
 hopes-0.085
 luck-0.084
 flashlight-0.084
 hugs-0.083
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
fters+0.085
isin+0.072
wheel+0.071
ner+0.071
 IT+0.070
Neg logit contributions
by-0.016
 luck-0.016
 hugs-0.015
 hopes-0.015
 flashlight-0.014
Token shy
Token ID15800
Feature activation+2.84e-02

Pos logit contributions
fters+0.043
isin+0.037
 IT+0.037
ner+0.035
uct+0.035
Neg logit contributions
 luck-0.017
ies-0.017
 back-0.017
 eyes-0.017
by-0.016
Token anymore
Token ID7471
Feature activation+1.72e-02

Pos logit contributions
fters+0.058
wheel+0.046
oke+0.046
ner+0.046
isin+0.046
Neg logit contributions
by-0.041
 hopes-0.038
 flashlight-0.038
 luck-0.038
 hugs-0.037
Token.
Token ID13
Feature activation+9.49e-03

Pos logit contributions
fters+0.052
isin+0.045
wheel+0.045
 IT+0.044
ner+0.044
Neg logit contributions
by-0.009
 eyes-0.008
 hopes-0.008
 luck-0.008
 flashlight-0.007
Token They
Token ID1119
Feature activation+3.31e-03

Pos logit contributions
fters+0.023
wheel+0.020
isin+0.019
ner+0.019
zel+0.019
Neg logit contributions
by-0.010
 hopes-0.010
 eyes-0.009
 luck-0.009
 hugs-0.009
Token talk
Token ID1561
Feature activation-3.63e-02

Pos logit contributions
fters+0.009
oke+0.007
isin+0.007
ner+0.007
 IT+0.007
Neg logit contributions
 hopes-0.003
 hope-0.003
 hugs-0.003
by-0.003
 luck-0.003
Token and
Token ID290
Feature activation-2.12e-02

Pos logit contributions
by+0.034
cy+0.030
 flashlight+0.029
 luck+0.028
 hopes+0.027
Neg logit contributions
fters-0.088
wheel-0.077
oke-0.076
zel-0.075
ner-0.074
Token laugh
Token ID6487
Feature activation-2.61e-02

Pos logit contributions
 hugs+0.021
 hopes+0.021
by+0.021
 flashlight+0.020
 luck+0.020
Neg logit contributions
fters-0.054
oke-0.045
isin-0.045
ner-0.044
zel-0.044
Token and
Token ID290
Feature activation-2.04e-02

Pos logit contributions
by+0.024
 hopes+0.020
 luck+0.020
 flashlight+0.020
 hugs+0.019
Neg logit contributions
fters-0.067
wheel-0.057
ner-0.056
zel-0.056
isin-0.056
Token share
Token ID2648
Feature activation-1.99e-02

Pos logit contributions
 hugs+0.021
 hopes+0.020
by+0.020
 luck+0.020
 flashlight+0.019
Neg logit contributions
fters-0.052
oke-0.045
isin-0.044
str-0.042
ner-0.042
Token.
Token ID13
Feature activation+2.88e-03

Pos logit contributions
by+0.016
 luck+0.014
 hopes+0.014
 hugs+0.013
 flashlight+0.013
Neg logit contributions
fters-0.054
wheel-0.046
isin-0.046
ner-0.046
oke-0.045
Token They
Token ID1119
Feature activation-7.34e-03

Pos logit contributions
fters+0.007
wheel+0.005
isin+0.005
ner+0.005
zel+0.005
Neg logit contributions
by-0.004
 hopes-0.003
 luck-0.003
 flashlight-0.003
 hugs-0.003
TokenYes
Token ID5297
Feature activation-5.55e-02

Pos logit contributions
by+0.002
 luck+0.001
 hugs+0.001
 hopes+0.001
cy+0.001
Neg logit contributions
fters-0.004
oke-0.004
isin-0.004
wheel-0.003
zel-0.003
Token please
Token ID3387
Feature activation-8.95e-03

Pos logit contributions
by+0.041
 luck+0.035
 eyes+0.035
 hugs+0.034
 hopes+0.031
Neg logit contributions
fters-0.157
wheel-0.133
isin-0.131
zel-0.130
ner-0.129
Token!"
Token ID2474
Feature activation+5.06e-02

Pos logit contributions
by+0.010
 luck+0.009
 hugs+0.009
 looks+0.008
 hopes+0.008
Neg logit contributions
fters-0.022
isin-0.018
wheel-0.018
 IT-0.018
ner-0.018
Token Amy
Token ID14235
Feature activation+1.68e-02

Pos logit contributions
fters+0.112
isin+0.089
oke+0.088
wheel+0.087
ner+0.087
Neg logit contributions
by-0.068
 hugs-0.064
 hopes-0.063
 luck-0.061
 flashlight-0.061
Token said
Token ID531
Feature activation+3.13e-02

Pos logit contributions
fters+0.048
isin+0.039
oke+0.038
 IT+0.037
 inconvenience+0.037
Neg logit contributions
by-0.018
 hugs-0.016
y-0.014
,-0.014
 back-0.014
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
fters+0.090
isin+0.076
oke+0.075
wheel+0.074
 IT+0.074
Neg logit contributions
by-0.022
 luck-0.019
 hugs-0.018
 eyes-0.017
 hopes-0.017
Token
Token ID198
Feature activation-3.67e-03

Pos logit contributions
 hugs+0.017
 eyes+0.017
by+0.016
 back+0.016
 nods+0.015
Neg logit contributions
fters-0.040
isin-0.033
cod-0.031
pieces-0.031
zel-0.031
Token
Token ID198
Feature activation-3.53e-03

Pos logit contributions
by+0.004
 hopes+0.004
 hugs+0.004
 flashlight+0.004
 luck+0.004
Neg logit contributions
fters-0.009
wheel-0.007
isin-0.007
ner-0.007
zel-0.007
TokenThe
Token ID464
Feature activation+1.09e-02

Pos logit contributions
by+0.005
 hugs+0.004
 hopes+0.004
 flashlight+0.004
 nods+0.004
Neg logit contributions
fters-0.008
oke-0.006
isin-0.006
ner-0.006
wheel-0.006
Token owner
Token ID4870
Feature activation-2.40e-02

Pos logit contributions
fters+0.020
ner+0.015
zel+0.015
wheel+0.015
isin+0.015
Neg logit contributions
by-0.019
 luck-0.018
 hugs-0.017
 eyes-0.017
 hopes-0.017
Token smiled
Token ID13541
Feature activation-6.49e-02

Pos logit contributions
by+0.026
 hugs+0.023
 luck+0.022
 hopes+0.022
 eyes+0.022
Neg logit contributions
fters-0.061
isin-0.050
ner-0.049
zel-0.049
 IT-0.049
Token They
Token ID1119
Feature activation-1.95e-03

Pos logit contributions
 eyes+0.005
 hugs+0.005
 hopes+0.005
 nods+0.005
 flashlight+0.005
Neg logit contributions
fters-0.012
isin-0.010
zel-0.010
wheel-0.010
cod-0.009
Token wear
Token ID5806
Feature activation-5.95e-03

Pos logit contributions
by+0.002
 hopes+0.002
 flashlight+0.002
 hugs+0.002
 luck+0.002
Neg logit contributions
fters-0.005
isin-0.004
zel-0.004
wheel-0.004
oke-0.004
Token pretty
Token ID2495
Feature activation-2.88e-02

Pos logit contributions
by+0.006
 luck+0.006
 hopes+0.006
cy+0.006
 flashlight+0.005
Neg logit contributions
fters-0.014
zel-0.012
wheel-0.012
ner-0.012
isin-0.012
Token dresses
Token ID27309
Feature activation+1.70e-02

Pos logit contributions
by+0.035
cy+0.034
 luck+0.033
 hopes+0.033
 flashlight+0.031
Neg logit contributions
fters-0.062
isin-0.050
pieces-0.050
zel-0.049
n-0.048
Token and
Token ID290
Feature activation-1.22e-02

Pos logit contributions
fters+0.041
wheel+0.036
zel+0.036
ner+0.036
isin+0.035
Neg logit contributions
by-0.016
 hopes-0.015
 flashlight-0.014
 luck-0.014
cy-0.013
Token hats
Token ID23910
Feature activation-8.93e-03

Pos logit contributions
by+0.013
 luck+0.012
 hopes+0.011
 flashlight+0.011
 hugs+0.011
Neg logit contributions
fters-0.030
wheel-0.025
isin-0.025
ner-0.025
oke-0.024
Token.
Token ID13
Feature activation-6.14e-03

Pos logit contributions
by+0.008
 hopes+0.007
 luck+0.007
 flashlight+0.007
 hugs+0.006
Neg logit contributions
fters-0.023
wheel-0.020
ner-0.019
zel-0.019
isin-0.019
Token They
Token ID1119
Feature activation-3.33e-03

Pos logit contributions
 eyes+0.007
 hugs+0.006
 hopes+0.006
by+0.006
packs+0.006
Neg logit contributions
fters-0.015
isin-0.012
wheel-0.012
zel-0.012
cod-0.012
Token dance
Token ID9280
Feature activation-1.33e-02

Pos logit contributions
by+0.004
 hopes+0.003
 flashlight+0.003
 hugs+0.003
 luck+0.003
Neg logit contributions
fters-0.008
isin-0.007
oke-0.007
wheel-0.007
zel-0.007
Token to
Token ID284
Feature activation+7.21e-03

Pos logit contributions
by+0.013
 luck+0.011
 flashlight+0.011
 hopes+0.011
cy+0.010
Neg logit contributions
fters-0.032
zel-0.028
wheel-0.028
ner-0.027
oke-0.027
Token music
Token ID2647
Feature activation+6.51e-03

Pos logit contributions
fters+0.018
oke+0.016
wheel+0.015
zel+0.015
isin+0.015
Neg logit contributions
by-0.007
 hopes-0.007
 hugs-0.007
 luck-0.007
 eyes-0.006
Token!
Token ID0
Feature activation-5.37e-03

Pos logit contributions
by+0.021
 luck+0.018
 hopes+0.018
 flashlight+0.017
 eyes+0.017
Neg logit contributions
fters-0.076
isin-0.064
wheel-0.064
ner-0.063
 IT-0.062
Token Willie
Token ID28623
Feature activation+1.20e-02

Pos logit contributions
by+0.007
 hopes+0.006
 flashlight+0.006
 hugs+0.006
 luck+0.006
Neg logit contributions
fters-0.012
wheel-0.010
isin-0.010
zel-0.010
oke-0.010
Token apologized
Token ID22893
Feature activation-2.54e-02

Pos logit contributions
fters+0.034
wheel+0.029
ner+0.029
isin+0.028
 IT+0.028
Neg logit contributions
by-0.010
 hugs-0.009
 hopes-0.009
 looks-0.008
 eyes-0.008
Token and
Token ID290
Feature activation-2.41e-02

Pos logit contributions
by+0.020
packs+0.017
 flashlight+0.017
 hopes+0.017
cy+0.016
Neg logit contributions
fters-0.067
wheel-0.058
zel-0.057
oke-0.057
ner-0.057
Token gave
Token ID2921
Feature activation-8.36e-03

Pos logit contributions
by+0.027
 hugs+0.026
 hopes+0.025
 luck+0.024
 looks+0.024
Neg logit contributions
fters-0.061
isin-0.050
zel-0.049
 IT-0.048
ner-0.048
Token the
Token ID262
Feature activation-1.48e-02

Pos logit contributions
packs+0.010
 flashlight+0.009
 nods+0.009
 luck+0.009
 eyes+0.009
Neg logit contributions
fters-0.017
ner-0.015
n-0.014
isin-0.013
zel-0.013
Token car
Token ID1097
Feature activation-1.85e-02

Pos logit contributions
by+0.016
 luck+0.014
 hopes+0.014
 flashlight+0.014
 hugs+0.014
Neg logit contributions
fters-0.036
wheel-0.030
isin-0.030
ner-0.030
zel-0.030
Token back
Token ID736
Feature activation-4.64e-02

Pos logit contributions
by+0.010
 hopes+0.008
 flashlight+0.008
 luck+0.007
 eyes+0.007
Neg logit contributions
fters-0.052
wheel-0.047
zel-0.045
ner-0.045
isin-0.045
Token to
Token ID284
Feature activation+8.68e-03

Pos logit contributions
by+0.029
 luck+0.024
 hopes+0.024
 flashlight+0.023
 hugs+0.022
Neg logit contributions
fters-0.134
wheel-0.115
isin-0.114
ner-0.114
zel-0.113
Token her
Token ID607
Feature activation-3.85e-02

Pos logit contributions
fters+0.023
wheel+0.020
oke+0.020
isin+0.020
zel+0.019
Neg logit contributions
by-0.008
 hopes-0.007
 flashlight-0.007
 eyes-0.007
 hugs-0.007
Token.
Token ID13
Feature activation-8.82e-03

Pos logit contributions
by+0.025
 eyes+0.022
 hopes+0.022
 flashlight+0.022
 luck+0.021
Neg logit contributions
fters-0.117
isin-0.100
wheel-0.099
ner-0.098
 IT-0.097
TokenM
Token ID44
Feature activation-1.65e-02

Pos logit contributions
by+0.002
Mom+0.002
 close+0.002
 friend+0.001
 hopes+0.001
Neg logit contributions
fters-0.007
oke-0.006
ner-0.006
plets-0.006
wheel-0.006
Tokenum
Token ID388
Feature activation-3.00e-02

Pos logit contributions
by+0.019
 luck+0.017
 dreams+0.015
 eyes+0.015
 hopes+0.014
Neg logit contributions
fters-0.043
wheel-0.036
ner-0.035
zel-0.035
 IT-0.035
Token smiled
Token ID13541
Feature activation-4.84e-02

Pos logit contributions
by+0.024
 hugs+0.022
y+0.020
 looks+0.020
 nods+0.019
Neg logit contributions
fters-0.086
 IT-0.073
wheel-0.072
isin-0.071
ner-0.071
Token and
Token ID290
Feature activation-2.34e-02

Pos logit contributions
by+0.041
 flashlight+0.039
 hopes+0.036
packs+0.036
 hugs+0.035
Neg logit contributions
fters-0.117
wheel-0.102
oke-0.102
zel-0.102
ner-0.102
Token hugged
Token ID41130
Feature activation-5.42e-02

Pos logit contributions
 hugs+0.025
by+0.024
 hopes+0.023
 looks+0.023
 luck+0.023
Neg logit contributions
fters-0.062
isin-0.049
ner-0.048
oke-0.047
pieces-0.047
Token Dad
Token ID17415
Feature activation-8.99e-02

Pos logit contributions
by+0.068
 luck+0.060
 eyes+0.058
 hugs+0.057
 back+0.057
Neg logit contributions
fters-0.136
wheel-0.113
isin-0.110
zel-0.109
ner-0.109
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
by+0.071
 hugs+0.058
 luck+0.057
 hopes+0.053
 back+0.052
Neg logit contributions
fters-0.265
wheel-0.222
ner-0.220
isin-0.219
 IT-0.217
Token Then
Token ID3244
Feature activation-7.19e-04

Pos logit contributions
 eyes+0.013
 hopes+0.013
 hugs+0.013
by+0.012
 nods+0.012
Neg logit contributions
fters-0.040
isin-0.032
wheel-0.032
zel-0.032
cod-0.031
Token they
Token ID484
Feature activation+2.48e-02

Pos logit contributions
by+0.001
 luck+0.001
 hopes+0.001
 hugs+0.001
 eyes+0.001
Neg logit contributions
fters-0.002
wheel-0.001
isin-0.001
zel-0.001
oke-0.001
Token packed
Token ID11856
Feature activation-1.84e-02

Pos logit contributions
fters+0.066
isin+0.055
ner+0.055
zel+0.054
wheel+0.054
Neg logit contributions
by-0.025
 luck-0.022
 hugs-0.021
 hopes-0.021
 back-0.020
Token their
Token ID511
Feature activation-4.06e-02

Pos logit contributions
by+0.017
 luck+0.015
 hopes+0.015
 flashlight+0.015
 hugs+0.014
Neg logit contributions
fters-0.047
wheel-0.040
isin-0.039
ner-0.039
zel-0.039
Token.
Token ID13
Feature activation+3.88e-03

Pos logit contributions
fters+0.084
wheel+0.070
isin+0.070
ner+0.070
zel+0.069
Neg logit contributions
by-0.032
 luck-0.028
 hopes-0.028
 flashlight-0.027
 hugs-0.027
Token She
Token ID1375
Feature activation+5.80e-03

Pos logit contributions
fters+0.010
wheel+0.008
isin+0.008
ner+0.008
zel+0.008
Neg logit contributions
by-0.004
 hopes-0.004
 luck-0.004
 hugs-0.004
 flashlight-0.003
Token said
Token ID531
Feature activation+2.62e-02

Pos logit contributions
fters+0.013
wheel+0.011
isin+0.011
ner+0.011
oke+0.011
Neg logit contributions
by-0.007
 hopes-0.006
 luck-0.006
 flashlight-0.006
 hugs-0.006
Token to
Token ID284
Feature activation+1.72e-02

Pos logit contributions
fters+0.066
ner+0.056
wheel+0.056
isin+0.055
oke+0.055
Neg logit contributions
by-0.024
 flashlight-0.022
cy-0.022
packs-0.022
 hopes-0.022
Token her
Token ID607
Feature activation-2.86e-02

Pos logit contributions
fters+0.049
oke+0.043
zel+0.043
wheel+0.042
isin+0.042
Neg logit contributions
by-0.011
 hugs-0.010
 hopes-0.010
 luck-0.010
 eyes-0.010
Token mom
Token ID1995
Feature activation-1.00e-01

Pos logit contributions
by+0.034
cy+0.030
y+0.029
packs+0.028
 luck+0.027
Neg logit contributions
fters-0.061
pieces-0.052
wheel-0.052
ner-0.051
oke-0.051
Tokenmy
Token ID1820
Feature activation-7.45e-02

Pos logit contributions
by+0.072
 luck+0.061
 hopes+0.059
 flashlight+0.058
 hugs+0.057
Neg logit contributions
fters-0.280
wheel-0.238
isin-0.237
ner-0.237
zel-0.235
Token,
Token ID11
Feature activation-1.15e-02

Pos logit contributions
by+0.033
 hugs+0.026
 luck+0.025
 eyes+0.023
 hopes+0.021
Neg logit contributions
fters-0.237
isin-0.202
wheel-0.202
ner-0.198
zel-0.198
Token "
Token ID366
Feature activation+2.42e-02

Pos logit contributions
 back+0.013
 hugs+0.013
 and+0.012
 eyes+0.012
 hopes+0.011
Neg logit contributions
fters-0.030
isin-0.024
cod-0.024
 inconvenience-0.023
wheel-0.023
TokenMom
Token ID29252
Feature activation-6.87e-02

Pos logit contributions
fters+0.056
wheel+0.046
isin+0.046
ner+0.046
oke+0.046
Neg logit contributions
by-0.029
 luck-0.026
 hopes-0.026
 flashlight-0.025
 hugs-0.025
Tokenmy
Token ID1820
Feature activation-3.85e-02

Pos logit contributions
by+0.059
 hopes+0.055
 flashlight+0.053
 luck+0.053
 hugs+0.050
Neg logit contributions
fters-0.176
wheel-0.150
oke-0.149
ner-0.149
isin-0.148
Token to
Token ID284
Feature activation+1.40e-02

Pos logit contributions
by+0.000
 hopes+0.000
 luck+0.000
 flashlight+0.000
 eyes+0.000
Neg logit contributions
fters-0.001
wheel-0.001
ner-0.001
oke-0.001
isin-0.001
Token bring
Token ID2222
Feature activation-2.05e-02

Pos logit contributions
fters+0.037
oke+0.032
isin+0.032
zel+0.032
wheel+0.031
Neg logit contributions
 flashlight-0.013
by-0.013
 hopes-0.013
 hugs-0.012
 eyes-0.012
Token light
Token ID1657
Feature activation-5.04e-02

Pos logit contributions
by+0.021
 flashlight+0.019
cy+0.018
 hopes+0.018
packs+0.018
Neg logit contributions
fters-0.048
wheel-0.040
isin-0.039
ner-0.039
pieces-0.039
Token to
Token ID284
Feature activation+2.56e-03

Pos logit contributions
by+0.048
 hopes+0.042
 luck+0.040
 flashlight+0.040
 hugs+0.039
Neg logit contributions
fters-0.124
wheel-0.105
ner-0.104
isin-0.103
zel-0.103
Token her
Token ID607
Feature activation-4.78e-02

Pos logit contributions
fters+0.007
oke+0.006
zel+0.006
isin+0.006
wheel+0.006
Neg logit contributions
by-0.002
 eyes-0.002
 luck-0.002
 hopes-0.002
 flashlight-0.002
Token friend
Token ID1545
Feature activation-5.40e-02

Pos logit contributions
by+0.050
 luck+0.044
 hopes+0.043
 hugs+0.042
 flashlight+0.042
Neg logit contributions
fters-0.114
ner-0.095
zel-0.095
wheel-0.095
isin-0.094
Token,
Token ID11
Feature activation-2.37e-02

Pos logit contributions
,+0.016
 back+0.016
 hugs+0.014
by+0.013
 looks+0.010
Neg logit contributions
fters-0.183
isin-0.160
 IT-0.153
ner-0.151
zel-0.151
Token she
Token ID673
Feature activation+2.01e-02

Pos logit contributions
 flashlight+0.021
by+0.021
 luck+0.021
 hugs+0.021
 eyes+0.020
Neg logit contributions
fters-0.064
oke-0.054
isin-0.054
zel-0.052
cod-0.052
Token noticed
Token ID6810
Feature activation+1.75e-02

Pos logit contributions
fters+0.053
isin+0.044
ner+0.043
wheel+0.043
 IT+0.043
Neg logit contributions
by-0.022
 hopes-0.018
 looks-0.018
 hugs-0.018
 eyes-0.018
Token that
Token ID326
Feature activation-5.01e-05

Pos logit contributions
fters+0.043
isin+0.035
oke+0.035
zel+0.035
wheel+0.035
Neg logit contributions
by-0.019
 luck-0.017
 hopes-0.017
 hugs-0.017
 flashlight-0.017
Token he
Token ID339
Feature activation+1.73e-02

Pos logit contributions
 flashlight+0.000
by+0.000
 luck+0.000
 hugs+0.000
 dreams+0.000
Neg logit contributions
fters-0.000
oke-0.000
isin-0.000
zel-0.000
cod-0.000
Token together
Token ID1978
Feature activation-4.25e-02

Pos logit contributions
 back+0.005
 hugs+0.005
 hopes+0.004
by+0.004
 luck+0.004
Neg logit contributions
fters-0.023
str-0.021
oke-0.021
isin-0.020
 IT-0.020
Token.
Token ID13
Feature activation+4.06e-03

Pos logit contributions
by+0.020
 back+0.018
 luck+0.015
 eyes+0.013
y+0.013
Neg logit contributions
fters-0.133
oke-0.116
isin-0.116
 IT-0.114
wheel-0.114
Token They
Token ID1119
Feature activation-6.63e-04

Pos logit contributions
fters+0.012
wheel+0.010
isin+0.010
zel+0.010
ner+0.010
Neg logit contributions
 hopes-0.003
 hugs-0.003
 eyes-0.003
 kisses-0.003
 dreams-0.003
Token learned
Token ID4499
Feature activation-1.92e-02

Pos logit contributions
by+0.001
 hopes+0.001
 hugs+0.001
 luck+0.001
 flashlight+0.001
Neg logit contributions
fters-0.002
 IT-0.001
ner-0.001
isin-0.001
oke-0.001
Token a
Token ID257
Feature activation-3.99e-02

Pos logit contributions
by+0.022
cy+0.020
 flashlight+0.020
 hopes+0.019
 luck+0.019
Neg logit contributions
fters-0.044
wheel-0.037
zel-0.036
isin-0.036
ner-0.036
Token lesson
Token ID11483
Feature activation-5.67e-02

Pos logit contributions
by+0.052
 hopes+0.049
 luck+0.048
packs+0.048
 hugs+0.047
Neg logit contributions
fters-0.085
zel-0.070
wheel-0.070
isin-0.069
oke-0.069
Token that
Token ID326
Feature activation-1.43e-02

Pos logit contributions
by+0.057
 luck+0.051
 hopes+0.051
 flashlight+0.050
 hugs+0.049
Neg logit contributions
fters-0.142
wheel-0.118
isin-0.118
ner-0.117
oke-0.116
Token day
Token ID1110
Feature activation-1.38e-02

Pos logit contributions
by+0.011
 hopes+0.011
 flashlight+0.010
 hugs+0.010
 luck+0.010
Neg logit contributions
fters-0.039
ner-0.033
isin-0.033
zel-0.033
 IT-0.032
Token.
Token ID13
Feature activation+4.40e-03

Pos logit contributions
by+0.011
 luck+0.009
 hopes+0.009
 hugs+0.009
 flashlight+0.009
Neg logit contributions
fters-0.038
wheel-0.032
isin-0.032
ner-0.032
zel-0.032
Token They
Token ID1119
Feature activation+2.46e-04

Pos logit contributions
fters+0.013
wheel+0.011
isin+0.010
ner+0.010
zel+0.010
Neg logit contributions
 hopes-0.004
 hugs-0.003
 eyes-0.003
packs-0.003
 dreams-0.003
Token learned
Token ID4499
Feature activation-1.91e-02

Pos logit contributions
fters+0.001
ner+0.000
isin+0.000
 IT+0.000
oke+0.000
Neg logit contributions
by-0.000
 hopes-0.000
 luck-0.000
 hugs-0.000
 flashlight-0.000
Token day
Token ID1110
Feature activation+1.23e-02

Pos logit contributions
fters+0.064
zel+0.052
ner+0.052
isin+0.052
oke+0.052
Neg logit contributions
by-0.026
 luck-0.025
 flashlight-0.024
 hugs-0.023
 hopes-0.023
Token ever
Token ID1683
Feature activation-2.60e-02

Pos logit contributions
fters+0.033
cod+0.028
 IT+0.027
isin+0.027
wheel+0.027
Neg logit contributions
by-0.011
 hugs-0.010
 luck-0.010
 back-0.010
y-0.009
Token for
Token ID329
Feature activation+4.99e-02

Pos logit contributions
by+0.014
y+0.012
,+0.009
 luck+0.009
cy+0.009
Neg logit contributions
fters-0.086
 IT-0.074
isin-0.072
wheel-0.071
zel-0.070
Token Cindy
Token ID39062
Feature activation+2.50e-02

Pos logit contributions
fters+0.125
wheel+0.107
oke+0.106
cod+0.103
zel+0.103
Neg logit contributions
 luck-0.053
 hugs-0.051
 eyes-0.051
by-0.050
 dreams-0.048
Token!
Token ID0
Feature activation-3.54e-03

Pos logit contributions
fters+0.086
 IT+0.074
isin+0.072
 inconvenience+0.071
wheel+0.070
Neg logit contributions
by-0.011
y-0.007
,-0.007
 and-0.007
 back-0.007
Token<|endoftext|>
Token ID50256
Feature activation-5.49e-02

Pos logit contributions
by+0.003
 hugs+0.003
 hopes+0.003
 eyes+0.003
 back+0.003
Neg logit contributions
fters-0.010
isin-0.008
cod-0.008
wheel-0.008
zel-0.008
TokenOnce
Token ID7454
Feature activation-2.19e-02

Pos logit contributions
by+0.050
 hopes+0.044
 hugs+0.044
cy+0.044
 flashlight+0.043
Neg logit contributions
fters-0.144
isin-0.122
wheel-0.120
zel-0.119
 IT-0.116
Token upon
Token ID2402
Feature activation+4.56e-03

Pos logit contributions
by+0.021
 luck+0.020
 hopes+0.019
 hugs+0.019
 flashlight+0.019
Neg logit contributions
fters-0.054
oke-0.046
ner-0.045
wheel-0.045
isin-0.045
Token a
Token ID257
Feature activation-2.89e-02

Pos logit contributions
fters+0.012
wheel+0.010
isin+0.010
ner+0.010
zel+0.010
Neg logit contributions
by-0.004
 luck-0.004
 hopes-0.004
 flashlight-0.004
 hugs-0.004
Token time
Token ID640
Feature activation-3.12e-02

Pos logit contributions
by+0.046
 luck+0.044
 flashlight+0.044
 hopes+0.043
 hugs+0.043
Neg logit contributions
fters-0.053
isin-0.042
zel-0.041
oke-0.041
wheel-0.040
Token,
Token ID11
Feature activation-2.37e-02

Pos logit contributions
by+0.024
 hopes+0.022
 luck+0.021
 hugs+0.020
 flashlight+0.019
Neg logit contributions
fters-0.083
oke-0.073
ner-0.072
wheel-0.071
zel-0.070