TOP ACTIVATIONS
MAX = 10.644

elephants , lions and ac rob ats . They are amazed
saw clown s and ac rob ats and lions and elephants
thought they looked like ac rob ats . She enjoyed the
clown s juggling and ac rob ats doing flips . But
who liked to collect or nam ents . Everywhere she went
. They were called or nam ents and they were very
tree with lights and or nam ents . They also saw
the tree with regular or nam ents !" <|endoftext|> Once upon
They give Spot more or nam ents . Spot leads them
the shiny things were or nam ents and they were very
and lots of shiny or nam ents . L ila wanted
can we have some or nam ents for our snow man
Be careful , these or nam ents are very special .
big tree with many or nam ents on it . The
never played with the or nam ents again . They still
many colors . Some or nam ents were round , some
had not touched the or nam ents . They hoped Mom
and play with your or nam ents . Maybe you can
with lots of pretty or nam ents . One day ,
ride to the apple or chard . The neighbor said yes

MIN ACTIVATIONS
MIN = -7.753

save his pup from the injuries and the pup died soon
o had died from his injuries . His friends were very
you go , my d arl ings . Enjoy your lunch
let out a big sn arl and the mouse knew he
's wonderful , my d arl ings !" Mom my says
f ortunate y , her injuries were so severe , she
the lightning streak across the night sky . It was a
you go , my d arl ings ," Mom said .
's okay , my d arl ings . I forgive you
'm sorry , my d arl ings . The tornado took
What happened , my d arl ings ? Why do you
'm sorry , my d arl ings . That was a
's good , my d arl ings . I 'm glad
The butterfly flew into the night sky , its colors shimmer
He looked up into the night sky and saw a tw
you okay , my d arl ings ?" Mom asked .
you okay , my d arl ings ?" she asked .
perfect fish , my d arl ings ," mom says .
magical snow that filled the night sky with beauty and wonder
. It rolled off the night stand and under the bed

INTERVAL 6.045 - 10.644
CONTAINS 0.005%

take them to the all igator pond . Mom
. She did not like sheep . She liked pizza and
she had listened to Dog gy . Now , Kitty learned
to promise to always be best friends . They made their
the tree with regular or nam ents !" <|endoftext|> Once upon

INTERVAL 1.446 - 6.045
CONTAINS 13.899%

<|endoftext|> Once upon a time there was a little boy called
't expected Molly to be so calm . M
flying like a dark shadow in the gloomy forest . <|endoftext|>
instead . <|endoftext|> Once upon a time there was a little
<|endoftext|> Once upon a time there was a loyal friend .

INTERVAL -3.154 - 1.446
CONTAINS 84.070%

Tim thought of an idea . He went to the girl
didn 't know what to do . Just then
wrapped the blanket around the baby so it could have a
thanked her mom for keeping her promise . They enjoyed the
a way to act happy and silly . Ruby

INTERVAL -7.753 - -3.154
CONTAINS 2.026%

Sn ugg les . One day , they went to the
" I got you , you bad chicken !"
She scoop ed up some of the dirt and let it
. And that was the bad ending for Tim . <|endoftext|>
, and had a wonderful day exploring the new city .
Token elephants
Token ID25368
Feature activation+4.85e+00

Pos logit contributions
pole+0.007
lves+0.007
chard+0.007
 none+0.007
 One+0.007
Neg logit contributions
 kiss-0.007
ment-0.007
less-0.006
 bless-0.006
 forgiveness-0.006
Token,
Token ID11
Feature activation+2.57e-01

Pos logit contributions
pole+0.262
 none+0.248
lves+0.246
chard+0.243
 One+0.242
Neg logit contributions
 kiss-0.189
ment-0.184
 forgiveness-0.165
less-0.163
 bless-0.160
Token lions
Token ID31420
Feature activation+4.03e+00

Pos logit contributions
pole+0.013
 none+0.013
 pads+0.013
chard+0.012
 One+0.012
Neg logit contributions
 kiss-0.010
ment-0.010
less-0.010
 forgiveness-0.009
 bless-0.009
Token and
Token ID290
Feature activation-1.45e-01

Pos logit contributions
pole+0.213
 none+0.202
lves+0.199
opes+0.196
chard+0.196
Neg logit contributions
 kiss-0.163
ment-0.157
 forgiveness-0.143
less-0.141
 bless-0.139
Token ac
Token ID936
Feature activation+1.60e+00

Pos logit contributions
 kiss+0.007
ment+0.007
less+0.007
 bless+0.007
 forgiveness+0.006
Neg logit contributions
pole-0.006
lves-0.006
 none-0.006
chard-0.006
 One-0.005
Tokenrob
Token ID22609
Feature activation+1.06e+01

Pos logit contributions
pole+0.043
lves+0.039
 none+0.039
chard+0.039
 One+0.036
Neg logit contributions
 kiss-0.107
ment-0.104
less-0.098
 bless-0.097
 forgiveness-0.096
Tokenats
Token ID1381
Feature activation+2.05e+00

Pos logit contributions
chard+0.619
pole+0.535
nam+0.530
lves+0.513
 One+0.504
Neg logit contributions
ment-0.430
 kiss-0.415
--0.396
iness-0.382
 band-0.376
Token.
Token ID13
Feature activation+6.88e-02

Pos logit contributions
pole+0.122
lves+0.121
chard+0.119
 none+0.118
 favourites+0.115
Neg logit contributions
 kiss-0.068
ment-0.063
less-0.056
 bless-0.055
 forgiveness-0.052
Token They
Token ID1119
Feature activation+6.10e-01

Pos logit contributions
pole+0.004
lves+0.003
opes+0.003
chard+0.003
nam+0.003
Neg logit contributions
 kiss-0.003
ment-0.003
 of-0.002
 prayer-0.002
 from-0.002
Token are
Token ID389
Feature activation-5.49e-01

Pos logit contributions
pole+0.037
lves+0.036
chard+0.035
 none+0.035
 pads+0.034
Neg logit contributions
 kiss-0.021
ment-0.018
 bless-0.016
 prayer-0.016
 forgiveness-0.015
Token amazed
Token ID24562
Feature activation+4.40e+00

Pos logit contributions
 kiss+0.024
ment+0.022
less+0.021
 prayer+0.021
 bless+0.021
Neg logit contributions
lves-0.027
pole-0.026
chard-0.025
 One-0.025
 none-0.025
Token saw
Token ID2497
Feature activation+4.39e-01

Pos logit contributions
pole+0.037
lves+0.035
 none+0.035
chard+0.035
 One+0.033
Neg logit contributions
 kiss-0.041
ment-0.040
less-0.037
 bless-0.037
 forgiveness-0.036
Token clown
Token ID25573
Feature activation+4.46e+00

Pos logit contributions
pole+0.021
 none+0.020
lves+0.020
chard+0.020
 One+0.019
Neg logit contributions
 kiss-0.020
ment-0.019
less-0.018
 bless-0.017
 prayer-0.017
Tokens
Token ID82
Feature activation+2.02e+00

Pos logit contributions
pole+0.193
lves+0.181
 none+0.177
chard+0.176
 pads+0.171
Neg logit contributions
 kiss-0.223
ment-0.219
 forgiveness-0.201
less-0.197
 bless-0.196
Token and
Token ID290
Feature activation-1.78e-02

Pos logit contributions
pole+0.108
 none+0.106
chard+0.102
 One+0.100
 pads+0.099
Neg logit contributions
 kiss-0.076
ment-0.076
 forgiveness-0.069
 bless-0.069
less-0.067
Token ac
Token ID936
Feature activation+1.55e+00

Pos logit contributions
 kiss+0.001
ment+0.001
less+0.001
 bless+0.001
 forgiveness+0.001
Neg logit contributions
pole-0.001
 none-0.001
chard-0.001
lves-0.001
 One-0.001
Tokenrob
Token ID22609
Feature activation+1.03e+01

Pos logit contributions
pole+0.036
lves+0.034
chard+0.031
 none+0.031
 pads+0.030
Neg logit contributions
 kiss-0.110
ment-0.106
less-0.100
 prayer-0.100
 bless-0.099
Tokenats
Token ID1381
Feature activation+1.87e+00

Pos logit contributions
chard+0.567
pole+0.511
nam+0.487
lves+0.471
 One+0.467
Neg logit contributions
ment-0.445
 kiss-0.415
iness-0.394
--0.393
less-0.391
Token and
Token ID290
Feature activation+2.82e-01

Pos logit contributions
pole+0.109
 none+0.103
lves+0.102
chard+0.102
 One+0.101
Neg logit contributions
 kiss-0.065
ment-0.063
 forgiveness-0.056
 bless-0.055
less-0.055
Token lions
Token ID31420
Feature activation+4.64e+00

Pos logit contributions
pole+0.011
 none+0.011
chard+0.011
lves+0.011
 pads+0.010
Neg logit contributions
 kiss-0.014
ment-0.014
less-0.014
 bless-0.013
 forgiveness-0.013
Token and
Token ID290
Feature activation+2.13e-01

Pos logit contributions
pole+0.246
 none+0.233
 pads+0.232
lves+0.228
opes+0.228
Neg logit contributions
 kiss-0.184
ment-0.178
 forgiveness-0.163
less-0.160
 bless-0.159
Token elephants
Token ID25368
Feature activation+5.79e+00

Pos logit contributions
pole+0.008
 none+0.008
chard+0.007
lves+0.007
nam+0.007
Neg logit contributions
 kiss-0.011
ment-0.011
less-0.011
 bless-0.010
 forgiveness-0.010
Token thought
Token ID1807
Feature activation-1.77e+00

Pos logit contributions
 kiss+0.024
 band+0.022
 fairy+0.019
 bless+0.019
ment+0.019
Neg logit contributions
pole-0.031
chard-0.031
lves-0.030
nam-0.029
 none-0.029
Token they
Token ID484
Feature activation+1.77e+00

Pos logit contributions
 kiss+0.088
ment+0.087
 bless+0.079
less+0.078
guard+0.075
Neg logit contributions
 none-0.076
 One-0.072
pole-0.071
 favourites-0.066
nam-0.066
Token looked
Token ID3114
Feature activation+1.79e+00

Pos logit contributions
pole+0.083
lves+0.080
chard+0.079
uries+0.074
 none+0.074
Neg logit contributions
 kiss-0.082
ment-0.071
less-0.070
 band-0.070
 prayer-0.068
Token like
Token ID588
Feature activation-9.05e-01

Pos logit contributions
pole+0.094
opes+0.088
chard+0.088
lves+0.087
 none+0.086
Neg logit contributions
 kiss-0.073
less-0.066
ment-0.063
 cleaner-0.062
 band-0.061
Token ac
Token ID936
Feature activation+1.00e+00

Pos logit contributions
 kiss+0.040
ment+0.040
less+0.036
 bless+0.035
 prayer+0.034
Neg logit contributions
 none-0.042
pole-0.042
chard-0.040
lves-0.040
 One-0.039
Tokenrob
Token ID22609
Feature activation+1.03e+01

Pos logit contributions
pole+0.027
lves+0.027
chard+0.024
 none+0.024
 pads+0.024
Neg logit contributions
 kiss-0.067
ment-0.064
 prayer-0.061
less-0.060
 bless-0.060
Tokenats
Token ID1381
Feature activation+1.65e+00

Pos logit contributions
chard+0.513
pole+0.481
lves+0.446
 One+0.444
nam+0.436
Neg logit contributions
ment-0.459
 kiss-0.458
iness-0.427
less-0.425
 band-0.421
Token.
Token ID13
Feature activation-4.02e-01

Pos logit contributions
pole+0.091
 none+0.087
lves+0.084
chard+0.084
 pads+0.084
Neg logit contributions
ment-0.062
 kiss-0.061
 bless-0.054
 forgiveness-0.053
less-0.053
Token She
Token ID1375
Feature activation+3.73e-01

Pos logit contributions
 kiss+0.016
 prayer+0.014
ment+0.014
less+0.013
 next+0.013
Neg logit contributions
pole-0.022
lves-0.022
chard-0.021
 none-0.020
nam-0.020
Token enjoyed
Token ID8359
Feature activation-5.56e-01

Pos logit contributions
pole+0.019
lves+0.018
chard+0.018
uries+0.018
 none+0.017
Neg logit contributions
 kiss-0.017
 band-0.015
 fairy-0.014
ment-0.014
 bless-0.013
Token the
Token ID262
Feature activation-1.25e-01

Pos logit contributions
 kiss+0.029
ment+0.028
less+0.026
 prayer+0.025
 bless+0.025
Neg logit contributions
 none-0.022
pole-0.022
lves-0.022
chard-0.022
 One-0.021
Token clown
Token ID25573
Feature activation+3.95e+00

Pos logit contributions
 kiss+0.008
ment+0.008
less+0.007
 bless+0.007
 forgiveness+0.007
Neg logit contributions
pole-0.009
lves-0.008
 none-0.008
chard-0.008
 One-0.008
Tokens
Token ID82
Feature activation+1.38e+00

Pos logit contributions
pole+0.178
lves+0.171
 none+0.168
chard+0.168
 One+0.162
Neg logit contributions
 kiss-0.190
ment-0.182
less-0.168
 bless-0.166
 forgiveness-0.163
Token juggling
Token ID48097
Feature activation+3.84e+00

Pos logit contributions
pole+0.075
 none+0.072
chard+0.071
lves+0.069
 One+0.069
Neg logit contributions
 kiss-0.053
ment-0.052
 forgiveness-0.046
less-0.045
 bless-0.045
Token and
Token ID290
Feature activation-9.93e-02

Pos logit contributions
pole+0.192
lves+0.187
chard+0.183
 none+0.182
 One+0.175
Neg logit contributions
 kiss-0.166
ment-0.158
less-0.143
 bless-0.140
 forgiveness-0.139
Token ac
Token ID936
Feature activation+1.10e+00

Pos logit contributions
 kiss+0.004
ment+0.004
 band+0.003
 bless+0.003
ful+0.003
Neg logit contributions
lves-0.005
pole-0.005
 favorites-0.005
uries-0.005
 favourites-0.005
Tokenrob
Token ID22609
Feature activation+1.01e+01

Pos logit contributions
pole+0.034
 none+0.032
chard+0.032
lves+0.031
 One+0.031
Neg logit contributions
 kiss-0.067
ment-0.066
less-0.062
 band-0.062
guard-0.061
Tokenats
Token ID1381
Feature activation+1.46e+00

Pos logit contributions
chard+0.586
pole+0.502
 One+0.495
lves+0.489
nam+0.489
Neg logit contributions
ment-0.406
iness-0.379
--0.376
 kiss-0.376
 band-0.360
Token doing
Token ID1804
Feature activation+2.70e-01

Pos logit contributions
pole+0.082
lves+0.080
chard+0.079
 none+0.079
 One+0.077
Neg logit contributions
 kiss-0.053
ment-0.050
less-0.044
 bless-0.043
 forgiveness-0.043
Token flips
Token ID45971
Feature activation+3.34e-01

Pos logit contributions
pole+0.013
lves+0.013
chard+0.013
 none+0.012
 One+0.012
Neg logit contributions
 kiss-0.011
ment-0.011
 band-0.010
less-0.010
 forgiveness-0.010
Token.
Token ID13
Feature activation-2.33e-01

Pos logit contributions
pole+0.018
lves+0.017
 none+0.017
chard+0.017
 One+0.016
Neg logit contributions
 kiss-0.013
ment-0.013
 bless-0.011
 forgiveness-0.011
less-0.011
Token But
Token ID887
Feature activation-4.97e-01

Pos logit contributions
 kiss+0.009
ment+0.007
 prayer+0.006
 band+0.006
 nurse+0.006
Neg logit contributions
lves-0.013
pole-0.013
uries-0.013
opes-0.013
edy-0.013
Token who
Token ID508
Feature activation+3.16e+00

Pos logit contributions
pole+0.031
lves+0.029
chard+0.028
 none+0.028
 One+0.026
Neg logit contributions
 kiss-0.076
ment-0.074
less-0.069
 bless-0.069
 forgiveness-0.068
Token liked
Token ID8288
Feature activation+1.05e+00

Pos logit contributions
 One+0.063
lves+0.062
pole+0.061
 favourites+0.058
chard+0.057
Neg logit contributions
ment-0.224
 kiss-0.222
 forgiveness-0.211
less-0.205
guard-0.205
Token to
Token ID284
Feature activation+1.62e-01

Pos logit contributions
chard+0.052
pole+0.050
nam+0.050
 none+0.050
 One+0.049
Neg logit contributions
ment-0.043
 kiss-0.043
less-0.038
 bless-0.038
 forgiveness-0.037
Token collect
Token ID2824
Feature activation+1.41e+00

Pos logit contributions
 One+0.008
pole+0.008
chard+0.008
 none+0.007
 favourites+0.007
Neg logit contributions
ment-0.007
less-0.007
 kiss-0.006
guard-0.006
 accidents-0.006
Token or
Token ID393
Feature activation+2.09e+00

Pos logit contributions
pole+0.074
lves+0.071
chard+0.070
 none+0.070
 One+0.068
Neg logit contributions
 kiss-0.058
ment-0.055
less-0.050
 bless-0.049
 forgiveness-0.049
Tokennam
Token ID7402
Feature activation+9.77e+00

Pos logit contributions
pole+0.022
lves+0.019
 none+0.015
chard+0.014
 One+0.013
Neg logit contributions
 kiss-0.173
ment-0.168
less-0.160
 bless-0.159
 forgiveness-0.159
Tokenents
Token ID658
Feature activation+3.77e+00

Pos logit contributions
lves+0.304
 none+0.302
chard+0.294
uries+0.291
opes+0.291
Neg logit contributions
 kiss-0.532
ment-0.528
less-0.515
 of-0.513
ful-0.508
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
pole+0.213
 none+0.204
chard+0.203
lves+0.201
 One+0.195
Neg logit contributions
 kiss-0.141
ment-0.130
 bless-0.119
 forgiveness-0.117
 prayer-0.117
Token Everywhere
Token ID48201
Feature activation+1.81e+00

Pos logit contributions
lves+0.014
pole+0.014
chard+0.013
 none+0.013
opes+0.013
Neg logit contributions
 kiss-0.016
ment-0.014
 prayer-0.014
less-0.013
 bless-0.013
Token she
Token ID673
Feature activation+3.92e-01

Pos logit contributions
pole+0.114
lves+0.110
uries+0.107
chard+0.106
opes+0.106
Neg logit contributions
 kiss-0.057
ment-0.052
 bless-0.045
 band-0.044
less-0.044
Token went
Token ID1816
Feature activation-4.04e-01

Pos logit contributions
pole+0.018
lves+0.017
 none+0.017
chard+0.017
 One+0.016
Neg logit contributions
 kiss-0.018
ment-0.018
less-0.016
 bless-0.016
 forgiveness-0.016
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
 kiss+0.004
ment+0.003
less+0.003
 bless+0.003
 forgiveness+0.003
Neg logit contributions
pole-0.006
lves-0.006
 none-0.006
chard-0.006
 One-0.005
Token They
Token ID1119
Feature activation+5.17e-01

Pos logit contributions
lves+0.006
pole+0.005
riages+0.005
opes+0.005
nam+0.005
Neg logit contributions
 kiss-0.009
 shower-0.008
 of-0.008
 moment-0.008
 prayer-0.007
Token were
Token ID547
Feature activation+5.03e-01

Pos logit contributions
lves+0.026
pole+0.024
opes+0.024
uries+0.023
osures+0.023
Neg logit contributions
 kiss-0.024
 band-0.019
 fairy-0.019
ot-0.019
 cheer-0.018
Token called
Token ID1444
Feature activation+2.57e+00

Pos logit contributions
lves+0.028
pole+0.027
uries+0.026
astically+0.026
 pads+0.026
Neg logit contributions
 kiss-0.016
 from-0.015
 cheer-0.015
 next-0.015
 fairy-0.014
Token or
Token ID393
Feature activation+1.90e+00

Pos logit contributions
pole+0.124
lves+0.119
 none+0.119
chard+0.118
 One+0.115
Neg logit contributions
 kiss-0.114
ment-0.110
less-0.100
 bless-0.098
 forgiveness-0.098
Tokennam
Token ID7402
Feature activation+9.60e+00

Pos logit contributions
pole+0.005
chard+0.005
 none+0.004
nam+0.003
lves+0.001
Neg logit contributions
 kiss-0.170
ment-0.168
less-0.160
 bless-0.159
 forgiveness-0.158
Tokenents
Token ID658
Feature activation+3.57e+00

Pos logit contributions
 none+0.286
chard+0.285
pole+0.282
lves+0.278
 One+0.269
Neg logit contributions
 kiss-0.553
ment-0.539
less-0.539
ful-0.536
 of-0.512
Token and
Token ID290
Feature activation+3.50e-01

Pos logit contributions
pole+0.197
 none+0.191
chard+0.179
 pads+0.172
lves+0.172
Neg logit contributions
 kiss-0.142
ment-0.131
 forgiveness-0.125
 bless-0.123
 prayer-0.120
Token they
Token ID484
Feature activation+1.69e+00

Pos logit contributions
pole+0.016
lves+0.015
chard+0.014
 none+0.014
 One+0.014
Neg logit contributions
 kiss-0.017
ment-0.016
less-0.015
 bless-0.015
 forgiveness-0.015
Token were
Token ID547
Feature activation+1.55e+00

Pos logit contributions
lves+0.080
pole+0.077
opes+0.073
 pads+0.073
chard+0.072
Neg logit contributions
 kiss-0.081
 band-0.066
 fairy-0.066
 bless-0.065
 cheer-0.063
Token very
Token ID845
Feature activation+3.65e+00

Pos logit contributions
lves+0.087
 While+0.084
 banks+0.084
 pads+0.083
opes+0.083
Neg logit contributions
 kiss-0.053
 fairy-0.048
 from-0.047
 gift-0.045
 band-0.045
Token tree
Token ID5509
Feature activation+7.43e-01

Pos logit contributions
ment+0.090
 kiss+0.077
less+0.077
ful+0.074
 bless+0.073
Neg logit contributions
pole-0.071
chard-0.070
 One-0.067
 none-0.066
 bank-0.066
Token with
Token ID351
Feature activation+1.04e+00

Pos logit contributions
pole+0.041
chard+0.038
 none+0.037
 One+0.037
lves+0.036
Neg logit contributions
 kiss-0.030
ment-0.029
 bless-0.027
 forgiveness-0.027
less-0.025
Token lights
Token ID7588
Feature activation+4.70e-01

Pos logit contributions
pole+0.048
lves+0.047
uries+0.046
chard+0.044
edy+0.043
Neg logit contributions
 kiss-0.050
ment-0.048
 band-0.043
less-0.043
 forgiveness-0.042
Token and
Token ID290
Feature activation+9.41e-01

Pos logit contributions
pole+0.026
 none+0.024
 pads+0.023
chard+0.023
 One+0.023
Neg logit contributions
 kiss-0.018
ment-0.017
 forgiveness-0.017
 bless-0.016
 prayer-0.015
Token or
Token ID393
Feature activation+2.76e+00

Pos logit contributions
pole+0.044
lves+0.042
 none+0.041
chard+0.041
 One+0.040
Neg logit contributions
 kiss-0.044
ment-0.042
less-0.039
 bless-0.038
 forgiveness-0.038
Tokennam
Token ID7402
Feature activation+9.44e+00

Pos logit contributions
pole+0.123
 none+0.122
chard+0.122
nam+0.119
lves+0.119
Neg logit contributions
 kiss-0.128
ment-0.125
less-0.118
 bless-0.113
 forgiveness-0.111
Tokenents
Token ID658
Feature activation+3.53e+00

Pos logit contributions
chard+0.299
 none+0.292
 One+0.292
pole+0.286
lves+0.286
Neg logit contributions
ment-0.521
 kiss-0.514
less-0.508
ful-0.504
 of-0.488
Token.
Token ID13
Feature activation+6.91e-01

Pos logit contributions
pole+0.193
 none+0.183
chard+0.178
lves+0.173
 pads+0.171
Neg logit contributions
 kiss-0.141
ment-0.129
 forgiveness-0.124
 bless-0.124
 prayer-0.121
Token They
Token ID1119
Feature activation+8.36e-01

Pos logit contributions
pole+0.038
lves+0.037
 pads+0.034
opes+0.034
chard+0.033
Neg logit contributions
 kiss-0.026
ment-0.026
 prayer-0.023
 voice-0.023
 shower-0.022
Token also
Token ID635
Feature activation+1.77e+00

Pos logit contributions
lves+0.041
pole+0.040
uries+0.039
 pads+0.038
opes+0.037
Neg logit contributions
 kiss-0.038
 fairy-0.032
 band-0.031
ful-0.030
ment-0.030
Token saw
Token ID2497
Feature activation+3.23e-01

Pos logit contributions
lves+0.088
pole+0.087
opes+0.082
uries+0.081
 pads+0.079
Neg logit contributions
 kiss-0.080
ment-0.070
 bless-0.066
 fairy-0.066
 cheer-0.065
Token the
Token ID262
Feature activation+2.15e-01

Pos logit contributions
pole+0.101
lves+0.097
 none+0.097
chard+0.096
 One+0.093
Neg logit contributions
 kiss-0.081
ment-0.078
less-0.070
 bless-0.069
 forgiveness-0.068
Token tree
Token ID5509
Feature activation+1.65e+00

Pos logit contributions
pole+0.011
lves+0.011
 none+0.010
chard+0.010
uries+0.010
Neg logit contributions
 kiss-0.009
ment-0.008
 fairy-0.008
 band-0.008
 bless-0.008
Token with
Token ID351
Feature activation+1.77e+00

Pos logit contributions
pole+0.086
lves+0.086
 none+0.083
chard+0.083
 favourites+0.081
Neg logit contributions
 kiss-0.066
ment-0.062
less-0.057
 bless-0.055
 prayer-0.054
Token regular
Token ID3218
Feature activation+1.07e+00

Pos logit contributions
pole+0.093
lves+0.090
chard+0.087
 none+0.086
 One+0.084
Neg logit contributions
 kiss-0.074
ment-0.069
 bless-0.063
less-0.063
 forgiveness-0.062
Token or
Token ID393
Feature activation+1.44e+00

Pos logit contributions
pole+0.049
 none+0.046
lves+0.046
 One+0.046
chard+0.045
Neg logit contributions
 kiss-0.049
ment-0.048
less-0.044
 bless-0.043
 forgiveness-0.043
Tokennam
Token ID7402
Feature activation+9.38e+00

Pos logit contributions
pole+0.043
lves+0.040
 none+0.038
chard+0.038
 One+0.037
Neg logit contributions
 kiss-0.091
ment-0.088
less-0.083
 bless-0.082
 forgiveness-0.082
Tokenents
Token ID658
Feature activation+3.43e+00

Pos logit contributions
lves+0.280
 none+0.280
chard+0.274
pole+0.273
opes+0.263
Neg logit contributions
ment-0.551
 kiss-0.546
less-0.530
ful-0.517
 of-0.506
Token!"
Token ID2474
Feature activation+2.29e+00

Pos logit contributions
pole+0.157
 none+0.147
chard+0.142
lves+0.141
 pads+0.138
Neg logit contributions
 kiss-0.164
ment-0.155
 forgiveness-0.147
 bless-0.144
 prayer-0.143
Token<|endoftext|>
Token ID50256
Feature activation-2.76e+00

Pos logit contributions
pole+0.065
lves+0.060
 none+0.059
chard+0.058
 One+0.055
Neg logit contributions
 kiss-0.149
ment-0.144
less-0.136
 bless-0.135
 forgiveness-0.134
TokenOnce
Token ID7454
Feature activation+1.20e+00

Pos logit contributions
 kiss+0.123
ment+0.118
less+0.107
 bless+0.106
 forgiveness+0.105
Neg logit contributions
pole-0.134
lves-0.130
 none-0.127
chard-0.127
nam-0.121
Token upon
Token ID2402
Feature activation+7.32e-01

Pos logit contributions
pole+0.067
lves+0.066
chard+0.064
 none+0.064
uries+0.063
Neg logit contributions
 kiss-0.044
ment-0.042
less-0.039
 bless-0.036
 forgiveness-0.036
Token They
Token ID1119
Feature activation+1.75e-01

Pos logit contributions
 kiss+0.040
ment+0.037
 prayer+0.035
 from+0.031
less+0.031
Neg logit contributions
pole-0.044
lves-0.043
nam-0.041
chard-0.041
 none-0.039
Token give
Token ID1577
Feature activation-4.84e-01

Pos logit contributions
pole+0.010
lves+0.010
 none+0.010
chard+0.010
 One+0.010
Neg logit contributions
 kiss-0.006
ment-0.006
less-0.005
 bless-0.005
 forgiveness-0.005
Token Spot
Token ID15899
Feature activation+1.39e+00

Pos logit contributions
 kiss+0.024
ment+0.023
less+0.021
 bless+0.021
 forgiveness+0.020
Neg logit contributions
pole-0.022
lves-0.021
 none-0.020
chard-0.020
 One-0.020
Token more
Token ID517
Feature activation+3.28e-01

Pos logit contributions
pole+0.071
lves+0.069
 none+0.068
chard+0.068
 One+0.066
Neg logit contributions
 kiss-0.057
ment-0.055
less-0.050
 bless-0.049
 forgiveness-0.049
Token or
Token ID393
Feature activation+5.14e-01

Pos logit contributions
pole+0.017
 One+0.016
 favorites+0.016
 pads+0.016
 none+0.016
Neg logit contributions
less-0.011
ment-0.011
 kiss-0.011
ful-0.011
 forgiveness-0.011
Tokennam
Token ID7402
Feature activation+9.06e+00

Pos logit contributions
nam+0.025
 none+0.024
pole+0.024
chard+0.023
 pads+0.023
Neg logit contributions
ment-0.022
less-0.021
 kiss-0.021
arl-0.020
 bless-0.020
Tokenents
Token ID658
Feature activation+3.06e+00

Pos logit contributions
pole+0.220
lves+0.210
chard+0.209
 none+0.208
 One+0.193
Neg logit contributions
 kiss-0.611
ment-0.598
less-0.569
 bless-0.555
ful-0.548
Token.
Token ID13
Feature activation-5.70e-01

Pos logit contributions
pole+0.148
 none+0.144
 pads+0.130
chard+0.124
 One+0.124
Neg logit contributions
 kiss-0.125
 forgiveness-0.125
irk-0.120
 prayer-0.119
 bless-0.119
Token Spot
Token ID15899
Feature activation+6.81e-01

Pos logit contributions
 kiss+0.030
ment+0.028
 prayer+0.026
less+0.026
 band+0.025
Neg logit contributions
pole-0.025
lves-0.024
chard-0.023
nam-0.022
 none-0.022
Token leads
Token ID5983
Feature activation+6.07e-01

Pos logit contributions
pole+0.036
chard+0.035
lves+0.035
 none+0.034
nam+0.033
Neg logit contributions
 kiss-0.028
ment-0.026
 bless-0.024
 prayer-0.023
 band-0.023
Token them
Token ID606
Feature activation-1.34e+00

Pos logit contributions
pole+0.028
 none+0.027
lves+0.027
chard+0.026
 One+0.026
Neg logit contributions
 kiss-0.029
ment-0.028
less-0.025
 bless-0.025
 forgiveness-0.025
Token the
Token ID262
Feature activation+2.63e-01

Pos logit contributions
pole+0.009
 none+0.009
chard+0.009
 One+0.009
lves+0.009
Neg logit contributions
 kiss-0.008
ment-0.008
 bless-0.007
less-0.007
 forgiveness-0.007
Token shiny
Token ID22441
Feature activation-3.46e-01

Pos logit contributions
pole+0.011
 none+0.011
 One+0.011
chard+0.011
lves+0.011
Neg logit contributions
ment-0.013
 kiss-0.013
less-0.012
 bless-0.011
ful-0.011
Token things
Token ID1243
Feature activation-1.98e+00

Pos logit contributions
 kiss+0.013
ment+0.013
 bless+0.012
less+0.012
 forgiveness+0.012
Neg logit contributions
pole-0.018
 none-0.017
chard-0.017
lves-0.017
 One-0.017
Token were
Token ID547
Feature activation+1.31e+00

Pos logit contributions
 kiss+0.089
ment+0.088
 bless+0.081
 forgiveness+0.078
less+0.076
Neg logit contributions
 none-0.092
pole-0.090
 One-0.085
chard-0.085
lves-0.083
Token or
Token ID393
Feature activation+1.41e+00

Pos logit contributions
pole+0.064
lves+0.062
chard+0.060
 none+0.059
 One+0.058
Neg logit contributions
 kiss-0.058
ment-0.055
less-0.051
 bless-0.050
 forgiveness-0.050
Tokennam
Token ID7402
Feature activation+9.05e+00

Pos logit contributions
 none+0.059
chard+0.058
nam+0.058
pole+0.057
lves+0.055
Neg logit contributions
 kiss-0.072
ment-0.070
less-0.065
 bless-0.065
 forgiveness-0.062
Tokenents
Token ID658
Feature activation+3.45e+00

Pos logit contributions
pole+0.255
 none+0.248
chard+0.245
lves+0.243
 One+0.232
Neg logit contributions
 kiss-0.551
ment-0.542
less-0.533
ful-0.521
 of-0.500
Token and
Token ID290
Feature activation+4.30e-01

Pos logit contributions
pole+0.178
 none+0.176
 pads+0.161
chard+0.160
riages+0.157
Neg logit contributions
 kiss-0.145
ment-0.134
 forgiveness-0.129
 bless-0.129
 prayer-0.126
Token they
Token ID484
Feature activation+1.55e+00

Pos logit contributions
pole+0.020
 none+0.020
lves+0.019
chard+0.019
 One+0.019
Neg logit contributions
 kiss-0.020
ment-0.019
less-0.017
 bless-0.017
 forgiveness-0.017
Token were
Token ID547
Feature activation+1.37e+00

Pos logit contributions
pole+0.067
lves+0.065
chard+0.063
 none+0.061
opes+0.060
Neg logit contributions
 kiss-0.079
ment-0.071
 bless-0.068
 prayer-0.067
 forgiveness-0.066
Token very
Token ID845
Feature activation+3.57e+00

Pos logit contributions
pole+0.071
lves+0.069
 While+0.067
chard+0.065
opes+0.065
Neg logit contributions
 kiss-0.054
 fairy-0.048
ment-0.048
 prayer-0.048
 from-0.047
Token and
Token ID290
Feature activation-3.60e-01

Pos logit contributions
pole+0.210
lves+0.205
chard+0.201
 none+0.201
 One+0.196
Neg logit contributions
 kiss-0.116
ment-0.109
less-0.096
 bless-0.094
 forgiveness-0.092
Token lots
Token ID6041
Feature activation+2.15e+00

Pos logit contributions
 kiss+0.017
ment+0.016
less+0.015
 forgiveness+0.015
 bless+0.015
Neg logit contributions
pole-0.017
lves-0.016
chard-0.016
 none-0.015
 One-0.015
Token of
Token ID286
Feature activation-1.48e+00

Pos logit contributions
pole+0.150
 none+0.142
 One+0.141
lves+0.140
 pads+0.140
Neg logit contributions
 kiss-0.047
ment-0.042
 bless-0.039
 forgiveness-0.037
 prayer-0.036
Token shiny
Token ID22441
Feature activation+1.85e+00

Pos logit contributions
 kiss+0.069
ment+0.066
less+0.060
 bless+0.059
 forgiveness+0.059
Neg logit contributions
pole-0.069
lves-0.066
 none-0.065
chard-0.065
 One-0.063
Token or
Token ID393
Feature activation+6.99e-01

Pos logit contributions
pole+0.081
lves+0.078
chard+0.077
 none+0.076
uries+0.073
Neg logit contributions
 kiss-0.091
ment-0.090
less-0.079
 bless-0.078
 band-0.078
Tokennam
Token ID7402
Feature activation+9.03e+00

Pos logit contributions
pole+0.033
lves+0.032
opes+0.030
 One+0.029
chard+0.029
Neg logit contributions
 kiss-0.032
ment-0.030
 forgiveness-0.028
 fairy-0.027
 prayer-0.027
Tokenents
Token ID658
Feature activation+3.21e+00

Pos logit contributions
 none+0.279
chard+0.276
 One+0.276
pole+0.276
lves+0.274
Neg logit contributions
ment-0.508
less-0.494
ful-0.488
 kiss-0.488
 of-0.471
Token.
Token ID13
Feature activation+4.66e-02

Pos logit contributions
pole+0.176
 none+0.166
chard+0.161
 pads+0.157
lves+0.156
Neg logit contributions
 kiss-0.131
ment-0.118
 forgiveness-0.115
 bless-0.115
 prayer-0.113
Token L
Token ID406
Feature activation+3.54e-01

Pos logit contributions
pole+0.003
chard+0.003
lves+0.003
nam+0.003
opes+0.003
Neg logit contributions
 kiss-0.002
ment-0.002
less-0.001
 of-0.001
 shower-0.001
Tokenila
Token ID10102
Feature activation-5.81e-01

Pos logit contributions
pole+0.023
lves+0.023
 none+0.022
chard+0.022
 pads+0.022
Neg logit contributions
 kiss-0.009
ment-0.009
 prayer-0.008
 forgiveness-0.007
 bless-0.007
Token wanted
Token ID2227
Feature activation+1.80e-01

Pos logit contributions
 kiss+0.022
ment+0.019
 fairy+0.018
 band+0.018
 bless+0.017
Neg logit contributions
lves-0.032
chard-0.031
pole-0.031
nam-0.030
 none-0.030
Token can
Token ID460
Feature activation-8.95e-01

Pos logit contributions
 none+0.002
pole+0.002
 One+0.002
nam+0.002
chard+0.002
Neg logit contributions
ment-0.002
 kiss-0.002
less-0.002
guard-0.002
 forgiveness-0.002
Token we
Token ID356
Feature activation-1.83e-01

Pos logit contributions
 kiss+0.041
ment+0.039
 bless+0.036
less+0.036
 forgiveness+0.035
Neg logit contributions
pole-0.042
lves-0.041
chard-0.040
 none-0.040
 favourites-0.038
Token have
Token ID423
Feature activation-1.07e+00

Pos logit contributions
 kiss+0.007
ment+0.007
less+0.006
 forgiveness+0.006
 bless+0.006
Neg logit contributions
pole-0.010
lves-0.010
 none-0.010
chard-0.010
 One-0.009
Token some
Token ID617
Feature activation-3.31e-01

Pos logit contributions
 kiss+0.040
 band+0.035
ment+0.034
 bless+0.034
 forgiveness+0.034
Neg logit contributions
pole-0.063
lves-0.061
 pads-0.058
opes-0.058
uries-0.057
Token or
Token ID393
Feature activation+1.13e+00

Pos logit contributions
 kiss+0.014
ment+0.013
less+0.012
 bless+0.012
 forgiveness+0.012
Neg logit contributions
pole-0.017
lves-0.016
 none-0.016
chard-0.016
 One-0.016
Tokennam
Token ID7402
Feature activation+9.02e+00

Pos logit contributions
pole+0.041
lves+0.040
chard+0.037
 none+0.037
 One+0.036
Neg logit contributions
 kiss-0.065
ment-0.061
 bless-0.058
 forgiveness-0.057
less-0.057
Tokenents
Token ID658
Feature activation+2.81e+00

Pos logit contributions
lves+0.271
 none+0.269
pole+0.264
chard+0.260
 One+0.259
Neg logit contributions
ment-0.514
 kiss-0.513
less-0.500
ful-0.495
 of-0.477
Token for
Token ID329
Feature activation-1.44e+00

Pos logit contributions
pole+0.134
 none+0.125
chard+0.123
 One+0.114
 pads+0.110
Neg logit contributions
 kiss-0.126
ment-0.123
 forgiveness-0.118
 prayer-0.116
 bless-0.112
Token our
Token ID674
Feature activation+9.78e-01

Pos logit contributions
 kiss+0.057
ment+0.052
 bless+0.049
 forgiveness+0.049
 band+0.047
Neg logit contributions
pole-0.079
lves-0.077
 pads-0.074
chard-0.073
 none-0.071
Token snow
Token ID6729
Feature activation-1.73e+00

Pos logit contributions
pole+0.051
lves+0.049
 none+0.049
chard+0.049
 favourites+0.047
Neg logit contributions
 kiss-0.039
ment-0.038
less-0.034
 bless-0.033
 forgiveness-0.033
Tokenman
Token ID805
Feature activation+1.66e+00

Pos logit contributions
 kiss+0.070
ment+0.069
less+0.062
 forgiveness+0.061
 bless+0.061
Neg logit contributions
pole-0.090
 none-0.084
chard-0.083
lves-0.081
 One-0.081
TokenBe
Token ID3856
Feature activation-2.11e+00

Pos logit contributions
pole+0.136
lves+0.130
 One+0.126
 none+0.122
chard+0.122
Neg logit contributions
 kiss-0.145
ment-0.140
less-0.133
 forgiveness-0.128
 prayer-0.127
Token careful
Token ID8161
Feature activation-6.95e-01

Pos logit contributions
 kiss+0.101
ment+0.095
less+0.090
 prayer+0.087
guard+0.086
Neg logit contributions
pole-0.096
 none-0.091
lves-0.089
chard-0.088
nam-0.087
Token,
Token ID11
Feature activation+2.03e-01

Pos logit contributions
 kiss+0.032
ment+0.030
 forgiveness+0.028
 band+0.028
 bless+0.028
Neg logit contributions
pole-0.033
 none-0.031
 One-0.030
opes-0.029
uries-0.029
Token these
Token ID777
Feature activation+1.37e+00

Pos logit contributions
pole+0.010
 none+0.010
lves+0.009
 One+0.009
chard+0.009
Neg logit contributions
 kiss-0.009
ment-0.009
less-0.008
 bless-0.008
 forgiveness-0.008
Token or
Token ID393
Feature activation+1.10e+00

Pos logit contributions
pole+0.075
lves+0.073
chard+0.072
 none+0.071
 One+0.069
Neg logit contributions
 kiss-0.053
ment-0.050
less-0.045
 bless-0.045
 forgiveness-0.044
Tokennam
Token ID7402
Feature activation+9.02e+00

Pos logit contributions
pole+0.046
chard+0.044
 none+0.044
lves+0.044
nam+0.042
Neg logit contributions
 kiss-0.056
ment-0.054
less-0.050
 bless-0.049
 forgiveness-0.049
Tokenents
Token ID658
Feature activation+2.71e+00

Pos logit contributions
 none+0.265
lves+0.261
pole+0.260
chard+0.257
 One+0.252
Neg logit contributions
ment-0.533
 kiss-0.525
ful-0.506
less-0.505
 bless-0.490
Token are
Token ID389
Feature activation+3.78e-01

Pos logit contributions
pole+0.142
 none+0.136
chard+0.127
lves+0.124
 One+0.124
Neg logit contributions
 kiss-0.110
ment-0.104
 forgiveness-0.098
less-0.097
 prayer-0.095
Token very
Token ID845
Feature activation+3.78e+00

Pos logit contributions
pole+0.018
lves+0.018
chard+0.017
 none+0.017
 One+0.017
Neg logit contributions
 kiss-0.017
ment-0.016
less-0.015
 bless-0.015
 prayer-0.015
Token special
Token ID2041
Feature activation+3.50e-01

Pos logit contributions
pole+0.184
lves+0.177
chard+0.177
 none+0.176
 One+0.169
Neg logit contributions
 kiss-0.167
ment-0.160
less-0.145
 forgiveness-0.144
 bless-0.144
Token.
Token ID13
Feature activation-2.96e-01

Pos logit contributions
pole+0.018
 none+0.018
 favorites+0.017
 One+0.017
chard+0.017
Neg logit contributions
 kiss-0.014
ment-0.013
less-0.012
 bless-0.012
 forgiveness-0.012
Token big
Token ID1263
Feature activation-1.80e+00

Pos logit contributions
ment+0.033
 kiss+0.029
 forgiveness+0.027
 bless+0.027
iness+0.027
Neg logit contributions
chard-0.033
pole-0.033
lves-0.032
 none-0.031
 One-0.031
Token tree
Token ID5509
Feature activation+9.32e-01

Pos logit contributions
ment+0.093
 kiss+0.088
less+0.084
 forgiveness+0.083
 bless+0.081
Neg logit contributions
pole-0.075
chard-0.072
lves-0.070
 none-0.070
 One-0.069
Token with
Token ID351
Feature activation+9.78e-01

Pos logit contributions
pole+0.053
chard+0.050
 One+0.050
 none+0.049
lves+0.049
Neg logit contributions
 kiss-0.035
ment-0.035
 forgiveness-0.032
 bless-0.031
less-0.030
Token many
Token ID867
Feature activation+6.46e-01

Pos logit contributions
uries+0.049
pole+0.049
lves+0.049
edy+0.046
chard+0.044
Neg logit contributions
 kiss-0.041
ment-0.040
 of-0.037
 band-0.037
ful-0.036
Token or
Token ID393
Feature activation+1.12e+00

Pos logit contributions
uries+0.032
pole+0.032
chard+0.031
lves+0.031
 none+0.030
Neg logit contributions
 kiss-0.028
ment-0.027
 of-0.027
 band-0.025
 ray-0.025
Tokennam
Token ID7402
Feature activation+9.02e+00

Pos logit contributions
pole+0.043
lves+0.040
 none+0.038
chard+0.038
 favourites+0.037
Neg logit contributions
 kiss-0.062
ment-0.060
less-0.055
 forgiveness-0.054
 bless-0.054
Tokenents
Token ID658
Feature activation+2.98e+00

Pos logit contributions
chard+0.288
lves+0.287
 none+0.287
pole+0.277
opes+0.262
Neg logit contributions
ment-0.495
 kiss-0.494
less-0.482
ful-0.478
 of-0.476
Token on
Token ID319
Feature activation+2.48e+00

Pos logit contributions
pole+0.167
 none+0.159
chard+0.155
lves+0.152
 pads+0.150
Neg logit contributions
 kiss-0.116
ment-0.105
 bless-0.101
 forgiveness-0.101
 prayer-0.098
Token it
Token ID340
Feature activation-2.64e-01

Pos logit contributions
lves+0.153
pole+0.152
uries+0.145
 favourites+0.143
cient+0.143
Neg logit contributions
 kiss-0.077
ment-0.074
 band-0.064
 pain-0.064
 fairy-0.063
Token.
Token ID13
Feature activation+1.95e-02

Pos logit contributions
 kiss+0.008
ment+0.007
less+0.006
 prayer+0.006
ful+0.006
Neg logit contributions
lves-0.017
pole-0.017
chard-0.016
 favourites-0.016
 none-0.016
Token The
Token ID383
Feature activation-2.68e-01

Pos logit contributions
pole+0.001
opes+0.001
lves+0.001
uries+0.001
cient+0.001
Neg logit contributions
 kiss-0.001
 of-0.000
ment-0.000
 shower-0.000
less-0.000
Token never
Token ID1239
Feature activation-4.19e-01

Pos logit contributions
 none+0.024
chard+0.022
pole+0.021
nam+0.020
lves+0.019
Neg logit contributions
 kiss-0.047
ment-0.046
less-0.046
arl-0.045
 bless-0.043
Token played
Token ID2826
Feature activation+3.43e-01

Pos logit contributions
ment+0.023
 kiss+0.022
less+0.020
 forgiveness+0.020
 bless+0.020
Neg logit contributions
pole-0.015
chard-0.015
 none-0.015
 One-0.015
lves-0.014
Token with
Token ID351
Feature activation+2.05e+00

Pos logit contributions
pole+0.018
 none+0.018
chard+0.018
lves+0.017
 One+0.017
Neg logit contributions
 kiss-0.013
ment-0.013
 prayer-0.012
 bless-0.012
less-0.011
Token the
Token ID262
Feature activation+5.04e-01

Pos logit contributions
pole+0.112
lves+0.106
chard+0.104
 none+0.103
 One+0.101
Neg logit contributions
 kiss-0.081
ment-0.076
 forgiveness-0.068
 bless-0.068
less-0.068
Token or
Token ID393
Feature activation+1.06e+00

Pos logit contributions
pole+0.022
 none+0.022
chard+0.022
lves+0.022
 favorites+0.021
Neg logit contributions
ment-0.025
 kiss-0.022
ful-0.021
less-0.020
 bless-0.020
Tokennam
Token ID7402
Feature activation+9.02e+00

Pos logit contributions
chard+0.053
 none+0.051
nam+0.050
pole+0.049
lves+0.048
Neg logit contributions
ment-0.047
 kiss-0.046
less-0.041
 prayer-0.040
 bless-0.040
Tokenents
Token ID658
Feature activation+2.36e+00

Pos logit contributions
 none+0.271
lves+0.263
 One+0.260
chard+0.257
pole+0.256
Neg logit contributions
 kiss-0.523
ment-0.520
less-0.517
ful-0.498
 of-0.485
Token again
Token ID757
Feature activation-9.63e-01

Pos logit contributions
pole+0.136
 none+0.131
chard+0.129
 pads+0.119
 bank+0.117
Neg logit contributions
 kiss-0.087
ment-0.082
 prayer-0.078
 bless-0.076
 forgiveness-0.074
Token.
Token ID13
Feature activation+1.37e-01

Pos logit contributions
 kiss+0.042
ment+0.039
 prayer+0.037
 bless+0.037
less+0.036
Neg logit contributions
 none-0.046
pole-0.046
 One-0.045
chard-0.044
 pads-0.043
Token They
Token ID1119
Feature activation+4.25e-01

Pos logit contributions
pole+0.008
chard+0.008
lves+0.007
opes+0.007
 none+0.007
Neg logit contributions
 kiss-0.005
ment-0.005
 prayer-0.004
 forgiveness-0.004
 bless-0.004
Token still
Token ID991
Feature activation-1.42e+00

Pos logit contributions
pole+0.019
lves+0.018
opes+0.017
chard+0.017
 pads+0.017
Neg logit contributions
 kiss-0.022
ment-0.019
 bless-0.019
 band-0.018
 forgiveness-0.018
Token many
Token ID867
Feature activation+1.07e+00

Pos logit contributions
lves+0.029
pole+0.028
chard+0.027
cient+0.027
uries+0.026
Neg logit contributions
 kiss-0.019
ment-0.017
 band-0.017
 fairy-0.016
 of-0.016
Token colors
Token ID7577
Feature activation+7.10e-01

Pos logit contributions
lves+0.059
pole+0.057
chard+0.057
uries+0.055
edy+0.053
Neg logit contributions
 kiss-0.041
ment-0.039
 of-0.036
 band-0.035
 fairy-0.035
Token.
Token ID13
Feature activation+3.53e-01

Pos logit contributions
pole+0.039
 none+0.037
 pads+0.036
chard+0.036
 One+0.036
Neg logit contributions
 kiss-0.028
ment-0.026
 bless-0.024
 forgiveness-0.024
 prayer-0.023
Token Some
Token ID2773
Feature activation-3.28e-01

Pos logit contributions
lves+0.012
pole+0.011
chard+0.011
riages+0.011
nam+0.010
Neg logit contributions
 kiss-0.021
 shower-0.019
 of-0.019
 moment-0.019
 forgiveness-0.019
Token or
Token ID393
Feature activation+1.24e+00

Pos logit contributions
 kiss+0.015
ment+0.015
 bless+0.013
less+0.013
 forgiveness+0.013
Neg logit contributions
pole-0.015
lves-0.015
chard-0.015
 none-0.014
uries-0.014
Tokennam
Token ID7402
Feature activation+9.01e+00

Pos logit contributions
pole+0.039
lves+0.037
chard+0.034
 none+0.033
uries+0.033
Neg logit contributions
 kiss-0.077
ment-0.074
 forgiveness-0.069
 bless-0.069
 band-0.068
Tokenents
Token ID658
Feature activation+2.71e+00

Pos logit contributions
chard+0.281
lves+0.278
 none+0.275
pole+0.265
 One+0.256
Neg logit contributions
ment-0.500
 kiss-0.498
ful-0.479
less-0.478
 of-0.470
Token were
Token ID547
Feature activation+1.46e+00

Pos logit contributions
pole+0.121
 none+0.118
chard+0.111
 One+0.102
 pads+0.102
Neg logit contributions
 kiss-0.133
ment-0.126
 forgiveness-0.121
 prayer-0.121
 bless-0.120
Token round
Token ID2835
Feature activation+3.30e+00

Pos logit contributions
lves+0.074
pole+0.071
 While+0.068
opes+0.068
 pads+0.068
Neg logit contributions
 kiss-0.061
ment-0.056
less-0.053
 bless-0.052
 band-0.052
Token,
Token ID11
Feature activation-4.13e-02

Pos logit contributions
pole+0.192
 none+0.187
lves+0.182
 One+0.182
chard+0.181
Neg logit contributions
 kiss-0.115
ment-0.105
 bless-0.097
 forgiveness-0.096
less-0.095
Token some
Token ID617
Feature activation-1.00e+00

Pos logit contributions
 kiss+0.002
ment+0.002
less+0.002
 forgiveness+0.002
 bless+0.002
Neg logit contributions
pole-0.002
lves-0.002
chard-0.002
 none-0.002
 favourites-0.002
Token had
Token ID550
Feature activation+9.68e-01

Pos logit contributions
pole+0.088
lves+0.084
chard+0.081
 none+0.080
 One+0.078
Neg logit contributions
 kiss-0.101
ment-0.096
less-0.090
 bless-0.089
 forgiveness-0.088
Token not
Token ID407
Feature activation-1.52e+00

Pos logit contributions
pole+0.049
lves+0.049
opes+0.044
chard+0.044
 One+0.044
Neg logit contributions
 kiss-0.043
 forgiveness-0.039
ment-0.039
 band-0.038
 bless-0.037
Token touched
Token ID12615
Feature activation+1.01e+00

Pos logit contributions
 kiss+0.085
ment+0.082
less+0.076
 bless+0.076
 forgiveness+0.075
Neg logit contributions
pole-0.057
lves-0.054
 none-0.054
chard-0.053
 One-0.051
Token the
Token ID262
Feature activation+7.60e-01

Pos logit contributions
pole+0.057
lves+0.055
chard+0.053
uries+0.052
 favourites+0.052
Neg logit contributions
 kiss-0.037
ment-0.035
 forgiveness-0.031
 bless-0.031
less-0.031
Token or
Token ID393
Feature activation+1.14e+00

Pos logit contributions
pole+0.036
lves+0.035
chard+0.034
uries+0.033
 none+0.033
Neg logit contributions
 kiss-0.035
ment-0.031
 bless-0.030
 fairy-0.030
 band-0.029
Tokennam
Token ID7402
Feature activation+8.95e+00

Pos logit contributions
pole+0.045
chard+0.045
 none+0.044
lves+0.043
nam+0.042
Neg logit contributions
 kiss-0.060
ment-0.059
less-0.054
 bless-0.053
 prayer-0.052
Tokenents
Token ID658
Feature activation+2.60e+00

Pos logit contributions
 none+0.247
pole+0.247
lves+0.245
opes+0.236
 One+0.235
Neg logit contributions
 kiss-0.543
ment-0.539
less-0.523
ful-0.512
 bless-0.501
Token.
Token ID13
Feature activation+8.82e-03

Pos logit contributions
pole+0.133
 none+0.129
chard+0.123
 bank+0.115
 One+0.114
Neg logit contributions
 kiss-0.110
ment-0.105
 prayer-0.099
 bless-0.099
 forgiveness-0.099
Token They
Token ID1119
Feature activation+5.23e-01

Pos logit contributions
pole+0.000
lves+0.000
chard+0.000
cient+0.000
opes+0.000
Neg logit contributions
 kiss-0.000
ment-0.000
 prayer-0.000
less-0.000
Time-0.000
Token hoped
Token ID10719
Feature activation+4.32e-01

Pos logit contributions
pole+0.024
lves+0.022
chard+0.021
opes+0.021
uries+0.021
Neg logit contributions
 kiss-0.027
ment-0.023
 band-0.023
 forgiveness-0.022
 fairy-0.022
Token Mom
Token ID11254
Feature activation-2.62e+00

Pos logit contributions
 none+0.019
 One+0.017
chard+0.017
pole+0.017
nam+0.016
Neg logit contributions
 kiss-0.021
ment-0.020
arl-0.020
less-0.019
 ray-0.019
Token and
Token ID290
Feature activation+6.54e-01

Pos logit contributions
 kiss+0.085
ment+0.080
less+0.072
 bless+0.072
 forgiveness+0.072
Neg logit contributions
pole-0.113
 none-0.110
chard-0.108
lves-0.107
 One-0.107
Token play
Token ID711
Feature activation-1.45e+00

Pos logit contributions
pole+0.031
 none+0.030
lves+0.030
chard+0.030
 One+0.029
Neg logit contributions
 kiss-0.029
ment-0.028
less-0.026
 bless-0.025
 forgiveness-0.025
Token with
Token ID351
Feature activation+1.60e+00

Pos logit contributions
 kiss+0.054
ment+0.052
less+0.046
 bless+0.046
 prayer+0.045
Neg logit contributions
pole-0.081
lves-0.078
 none-0.078
chard-0.077
 One-0.075
Token your
Token ID534
Feature activation-3.61e-01

Pos logit contributions
pole+0.092
lves+0.089
chard+0.087
 none+0.086
uries+0.085
Neg logit contributions
 kiss-0.059
ment-0.056
 forgiveness-0.049
 band-0.049
 bless-0.048
Token or
Token ID393
Feature activation+1.22e+00

Pos logit contributions
ment+0.017
 kiss+0.017
less+0.016
 bless+0.016
ful+0.015
Neg logit contributions
pole-0.015
lves-0.015
 none-0.015
chard-0.015
 favorites-0.015
Tokennam
Token ID7402
Feature activation+8.92e+00

Pos logit contributions
chard+0.057
pole+0.057
 none+0.055
lves+0.055
nam+0.054
Neg logit contributions
ment-0.055
 kiss-0.055
less-0.050
 bless-0.048
 prayer-0.047
Tokenents
Token ID658
Feature activation+2.48e+00

Pos logit contributions
 none+0.285
 One+0.283
lves+0.281
pole+0.275
chard+0.272
Neg logit contributions
ment-0.489
 kiss-0.487
less-0.485
ful-0.476
 of-0.464
Token.
Token ID13
Feature activation+4.58e-01

Pos logit contributions
pole+0.138
 none+0.132
chard+0.131
lves+0.130
 pads+0.126
Neg logit contributions
 kiss-0.094
ment-0.088
 bless-0.079
 prayer-0.078
 forgiveness-0.078
Token Maybe
Token ID6674
Feature activation+6.85e-02

Pos logit contributions
lves+0.022
opes+0.022
pole+0.022
chard+0.021
 none+0.020
Neg logit contributions
 kiss-0.020
ment-0.018
 prayer-0.017
Time-0.017
 forgiveness-0.016
Token you
Token ID345
Feature activation-3.77e+00

Pos logit contributions
pole+0.004
lves+0.004
chard+0.003
 none+0.003
 favourites+0.003
Neg logit contributions
 kiss-0.003
ment-0.003
 bless-0.002
 forgiveness-0.002
less-0.002
Token can
Token ID460
Feature activation-1.01e+00

Pos logit contributions
 kiss+0.136
ment+0.122
 bless+0.113
less+0.112
 prayer+0.108
Neg logit contributions
pole-0.217
lves-0.212
chard-0.208
 none-0.205
opes-0.201
Token with
Token ID351
Feature activation+8.50e-01

Pos logit contributions
pole+0.042
chard+0.040
 none+0.039
 One+0.039
lves+0.039
Neg logit contributions
 kiss-0.030
ment-0.029
 forgiveness-0.027
 bless-0.026
 prayer-0.026
Token lots
Token ID6041
Feature activation+1.78e+00

Pos logit contributions
pole+0.046
lves+0.045
chard+0.043
 none+0.043
uries+0.042
Neg logit contributions
 kiss-0.034
ment-0.032
 bless-0.029
less-0.029
 forgiveness-0.028
Token of
Token ID286
Feature activation-1.94e+00

Pos logit contributions
pole+0.119
 One+0.116
 favorites+0.113
 favourites+0.112
 pads+0.112
Neg logit contributions
 kiss-0.039
ment-0.034
 forgiveness-0.034
less-0.031
 bless-0.031
Token pretty
Token ID2495
Feature activation+1.61e+00

Pos logit contributions
 kiss+0.092
ment+0.088
 bless+0.079
less+0.079
 prayer+0.078
Neg logit contributions
pole-0.090
lves-0.087
chard-0.085
 none-0.085
uries-0.081
Token or
Token ID393
Feature activation+5.16e-01

Pos logit contributions
pole+0.079
chard+0.076
lves+0.076
 none+0.074
uries+0.073
Neg logit contributions
 kiss-0.073
ment-0.072
 band-0.063
 bless-0.062
 prayer-0.061
Tokennam
Token ID7402
Feature activation+8.90e+00

Pos logit contributions
pole+0.008
lves+0.007
 none+0.006
chard+0.006
 One+0.006
Neg logit contributions
 kiss-0.040
ment-0.039
less-0.037
 bless-0.037
 forgiveness-0.037
Tokenents
Token ID658
Feature activation+3.01e+00

Pos logit contributions
pole+0.258
 none+0.251
lves+0.249
chard+0.241
opes+0.234
Neg logit contributions
 kiss-0.536
ment-0.535
less-0.515
ful-0.502
 bless-0.492
Token.
Token ID13
Feature activation-2.13e-01

Pos logit contributions
pole+0.163
 none+0.154
chard+0.151
lves+0.149
 pads+0.148
Neg logit contributions
 kiss-0.122
ment-0.109
 forgiveness-0.107
 prayer-0.104
 bless-0.103
Token One
Token ID1881
Feature activation+2.24e-01

Pos logit contributions
 kiss+0.011
 moment+0.009
 shower+0.009
 band+0.008
 prayer+0.008
Neg logit contributions
lves-0.010
riages-0.010
chard-0.010
opes-0.010
pole-0.010
Token day
Token ID1110
Feature activation-4.29e+00

Pos logit contributions
 One+0.012
pole+0.011
chard+0.011
 While+0.011
 favourites+0.011
Neg logit contributions
ment-0.009
 kiss-0.009
 forgiveness-0.008
arl-0.008
less-0.008
Token,
Token ID11
Feature activation-8.44e-01

Pos logit contributions
 kiss+0.159
ment+0.152
 bless+0.134
 forgiveness+0.134
less+0.133
Neg logit contributions
pole-0.236
 none-0.230
lves-0.229
chard-0.226
 One-0.225
Token ride
Token ID6594
Feature activation-9.86e-01

Pos logit contributions
pole+0.014
 One+0.013
chard+0.013
lves+0.013
 none+0.013
Neg logit contributions
ment-0.011
ful-0.009
 kiss-0.009
iness-0.009
 forgiveness-0.009
Token to
Token ID284
Feature activation-4.01e-01

Pos logit contributions
 kiss+0.039
ment+0.038
 bless+0.035
 prayer+0.034
 forgiveness+0.033
Neg logit contributions
pole-0.053
 none-0.050
chard-0.049
 One-0.048
lves-0.047
Token the
Token ID262
Feature activation+7.17e-01

Pos logit contributions
ment+0.015
 kiss+0.015
less+0.014
 prayer+0.013
 bless+0.013
Neg logit contributions
pole-0.021
 none-0.021
chard-0.021
lves-0.020
 One-0.020
Token apple
Token ID17180
Feature activation+6.87e-01

Pos logit contributions
pole+0.030
chard+0.030
lves+0.029
 none+0.029
 One+0.028
Neg logit contributions
ment-0.037
 kiss-0.035
less-0.031
ful-0.031
 bless-0.031
Token or
Token ID393
Feature activation+2.33e+00

Pos logit contributions
pole+0.036
 none+0.034
chard+0.034
lves+0.034
 One+0.033
Neg logit contributions
 kiss-0.028
ment-0.027
less-0.024
 bless-0.024
 forgiveness-0.024
Tokenchard
Token ID30215
Feature activation+8.88e+00

Pos logit contributions
pole+0.123
lves+0.120
 none+0.116
chard+0.115
 One+0.113
Neg logit contributions
 kiss-0.095
ment-0.088
 bless-0.080
less-0.080
 forgiveness-0.079
Token.
Token ID13
Feature activation+1.96e-01

Pos logit contributions
pole+0.507
 none+0.488
lves+0.488
chard+0.486
 One+0.473
Neg logit contributions
 kiss-0.317
ment-0.302
less-0.268
 bless-0.265
 forgiveness-0.260
Token The
Token ID383
Feature activation-1.94e-01

Pos logit contributions
pole+0.008
lves+0.008
opes+0.008
 pads+0.008
chard+0.008
Neg logit contributions
 kiss-0.010
ment-0.009
 band-0.009
 forgiveness-0.009
less-0.009
Token neighbor
Token ID4780
Feature activation-9.40e-02

Pos logit contributions
ment+0.008
 kiss+0.008
less+0.007
 bless+0.007
ful+0.007
Neg logit contributions
pole-0.010
chard-0.010
 none-0.010
 One-0.009
lves-0.009
Token said
Token ID531
Feature activation+2.77e-01

Pos logit contributions
 kiss+0.004
ment+0.004
less+0.004
 forgiveness+0.004
 bless+0.004
Neg logit contributions
pole-0.004
lves-0.004
chard-0.004
 none-0.004
opes-0.004
Token yes
Token ID3763
Feature activation+2.52e+00

Pos logit contributions
 none+0.012
pole+0.012
chard+0.011
 One+0.011
lves+0.011
Neg logit contributions
 kiss-0.014
ment-0.013
 bless-0.012
less-0.012
 prayer-0.012
Token save
Token ID3613
Feature activation-1.00e-01

Pos logit contributions
pole+0.027
 One+0.026
 bank+0.026
 none+0.026
chard+0.025
Neg logit contributions
ment-0.026
less-0.022
 kiss-0.021
 prayer-0.020
irk-0.020
Token his
Token ID465
Feature activation+1.06e+00

Pos logit contributions
 kiss+0.004
ment+0.004
less+0.004
 bless+0.004
 prayer+0.003
Neg logit contributions
pole-0.005
lves-0.005
 none-0.005
chard-0.005
 One-0.005
Token pup
Token ID15552
Feature activation+1.46e+00

Pos logit contributions
 pads+0.049
 favorites+0.049
 favourites+0.048
 none+0.047
lves+0.046
Neg logit contributions
ment-0.048
 kiss-0.046
ful-0.041
 bless-0.041
arl-0.041
Token from
Token ID422
Feature activation+1.02e+00

Pos logit contributions
pole+0.080
lves+0.077
 none+0.077
chard+0.076
 One+0.074
Neg logit contributions
 kiss-0.056
ment-0.053
less-0.047
 bless-0.047
 prayer-0.046
Token the
Token ID262
Feature activation+8.18e-01

Pos logit contributions
pole+0.055
lves+0.053
 none+0.052
chard+0.052
 One+0.051
Neg logit contributions
 kiss-0.040
ment-0.038
less-0.034
 bless-0.034
 forgiveness-0.033
Token injuries
Token ID6821
Feature activation-7.70e+00

Pos logit contributions
 none+0.039
lves+0.038
 One+0.038
chard+0.037
 bank+0.037
Neg logit contributions
ment-0.041
 kiss-0.035
less-0.031
ful-0.031
 bless-0.031
Token and
Token ID290
Feature activation-4.54e-01

Pos logit contributions
 kiss+0.281
ment+0.266
 bless+0.235
less+0.232
 forgiveness+0.232
Neg logit contributions
pole-0.438
 none-0.418
lves-0.417
chard-0.414
 One-0.406
Token the
Token ID262
Feature activation+1.96e-01

Pos logit contributions
 kiss+0.022
ment+0.022
less+0.020
 bless+0.020
 ray+0.019
Neg logit contributions
 none-0.019
pole-0.019
chard-0.019
lves-0.018
 pads-0.018
Token pup
Token ID15552
Feature activation+6.17e-01

Pos logit contributions
 none+0.009
lves+0.009
 bank+0.009
 pads+0.009
 favourites+0.009
Neg logit contributions
ment-0.010
 kiss-0.008
ful-0.008
 bless-0.007
less-0.007
Token died
Token ID3724
Feature activation-2.25e+00

Pos logit contributions
pole+0.030
lves+0.029
chard+0.029
 none+0.028
 One+0.027
Neg logit contributions
 kiss-0.027
ment-0.026
less-0.024
 bless-0.023
 forgiveness-0.023
Token soon
Token ID2582
Feature activation-1.89e+00

Pos logit contributions
 kiss+0.099
 bless+0.088
ment+0.088
 forgiveness+0.082
 prayer+0.081
Neg logit contributions
 none-0.110
pole-0.109
chard-0.104
lves-0.102
 pads-0.101
Tokeno
Token ID78
Feature activation-5.44e-01

Pos logit contributions
pole+0.069
lves+0.066
chard+0.064
 none+0.064
 One+0.061
Neg logit contributions
 kiss-0.099
ment-0.095
less-0.088
 forgiveness-0.088
 bless-0.088
Token had
Token ID550
Feature activation-1.05e+00

Pos logit contributions
 kiss+0.024
ment+0.023
 bless+0.021
less+0.021
 forgiveness+0.020
Neg logit contributions
pole-0.027
lves-0.026
chard-0.025
 none-0.025
nam-0.024
Token died
Token ID3724
Feature activation-2.63e+00

Pos logit contributions
 kiss+0.044
ment+0.042
less+0.038
 bless+0.037
 forgiveness+0.037
Neg logit contributions
pole-0.054
lves-0.052
 none-0.051
chard-0.051
 One-0.050
Token from
Token ID422
Feature activation+1.93e-01

Pos logit contributions
 kiss+0.112
 bless+0.099
ment+0.099
 prayer+0.094
 spell+0.093
Neg logit contributions
 none-0.131
pole-0.126
chard-0.126
lves-0.118
 One-0.118
Token his
Token ID465
Feature activation-1.59e-02

Pos logit contributions
 none+0.008
chard+0.008
pole+0.008
lves+0.008
 One+0.008
Neg logit contributions
 kiss-0.009
ment-0.009
less-0.008
 prayer-0.008
 bless-0.008
Token injuries
Token ID6821
Feature activation-7.68e+00

Pos logit contributions
ment+0.001
 kiss+0.001
less+0.001
ful+0.001
 bless+0.001
Neg logit contributions
 none-0.001
chard-0.001
 favorites-0.001
pole-0.001
 favourites-0.001
Token.
Token ID13
Feature activation-2.95e-01

Pos logit contributions
 kiss+0.285
ment+0.270
 forgiveness+0.238
 bless+0.238
 prayer+0.237
Neg logit contributions
pole-0.432
 none-0.413
lves-0.406
chard-0.405
 One-0.401
Token His
Token ID2399
Feature activation+2.93e-01

Pos logit contributions
ment+0.013
 kiss+0.012
 prayer+0.011
 forgiveness+0.011
 of+0.010
Neg logit contributions
pole-0.015
opes-0.014
lves-0.014
chard-0.013
nam-0.013
Token friends
Token ID2460
Feature activation-6.07e-01

Pos logit contributions
 none+0.014
 favourites+0.013
 favorites+0.013
chard+0.013
 pads+0.013
Neg logit contributions
ment-0.012
 kiss-0.012
less-0.011
ful-0.011
pour-0.011
Token were
Token ID547
Feature activation+1.69e-01

Pos logit contributions
 kiss+0.030
ment+0.030
less+0.027
 bless+0.027
 forgiveness+0.027
Neg logit contributions
pole-0.026
lves-0.025
 none-0.024
chard-0.024
 One-0.023
Token very
Token ID845
Feature activation+2.90e+00

Pos logit contributions
pole+0.008
 none+0.007
lves+0.007
chard+0.007
 One+0.007
Neg logit contributions
 kiss-0.008
ment-0.008
less-0.007
 bless-0.007
 prayer-0.007
Token you
Token ID345
Feature activation-3.70e+00

Pos logit contributions
 none+0.095
pole+0.091
chard+0.091
lves+0.088
nam+0.086
Neg logit contributions
 kiss-0.085
ment-0.083
 bless-0.074
less-0.074
 forgiveness-0.071
Token go
Token ID467
Feature activation-2.67e+00

Pos logit contributions
 kiss+0.158
ment+0.149
less+0.136
 bless+0.135
 forgiveness+0.133
Neg logit contributions
pole-0.186
lves-0.181
chard-0.177
 none-0.176
 One-0.171
Token,
Token ID11
Feature activation+6.87e-02

Pos logit contributions
 kiss+0.100
ment+0.094
less+0.084
 bless+0.083
 forgiveness+0.082
Neg logit contributions
pole-0.150
lves-0.145
 none-0.143
chard-0.143
 One-0.138
Token my
Token ID616
Feature activation-1.29e+00

Pos logit contributions
pole+0.003
 none+0.003
chard+0.003
 One+0.003
lves+0.003
Neg logit contributions
ment-0.003
 kiss-0.003
less-0.003
 forgiveness-0.002
 bless-0.002
Token d
Token ID288
Feature activation-1.00e+00

Pos logit contributions
ment+0.052
 kiss+0.051
less+0.046
 bless+0.044
 forgiveness+0.044
Neg logit contributions
pole-0.064
 none-0.062
chard-0.062
 favorites-0.062
 favourites-0.061
Tokenarl
Token ID7063
Feature activation-7.64e+00

Pos logit contributions
 kiss+0.029
ment+0.026
 forgiveness+0.025
 prayer+0.024
 bless+0.024
Neg logit contributions
pole-0.065
lves-0.060
 none-0.060
uries-0.059
 pads-0.059
Tokenings
Token ID654
Feature activation-1.58e+00

Pos logit contributions
 kiss+0.322
ment+0.300
 forgiveness+0.287
less+0.279
 bless+0.277
Neg logit contributions
pole-0.386
 none-0.364
lves-0.359
 pads-0.356
chard-0.351
Token.
Token ID13
Feature activation-3.45e-01

Pos logit contributions
 kiss+0.066
ment+0.066
 forgiveness+0.058
less+0.058
 prayer+0.058
Neg logit contributions
pole-0.079
 none-0.074
 One-0.073
chard-0.072
lves-0.072
Token Enjoy
Token ID18179
Feature activation-7.99e-01

Pos logit contributions
 kiss+0.017
ment+0.015
 bless+0.015
 prayer+0.014
 forgiveness+0.014
Neg logit contributions
pole-0.016
lves-0.016
chard-0.015
 none-0.015
opes-0.015
Token your
Token ID534
Feature activation-2.90e-01

Pos logit contributions
 kiss+0.039
less+0.037
ment+0.037
 forgiveness+0.036
 prayer+0.036
Neg logit contributions
 none-0.031
pole-0.031
chard-0.030
 favorites-0.030
 One-0.030
Token lunch
Token ID9965
Feature activation-3.12e+00

Pos logit contributions
ment+0.012
less+0.012
 kiss+0.012
ful+0.012
pour+0.011
Neg logit contributions
 favorites-0.013
 favourites-0.013
 none-0.013
 bank-0.013
chard-0.013
Token let
Token ID1309
Feature activation-3.80e-01

Pos logit contributions
pole+0.027
lves+0.027
chard+0.026
 none+0.026
 favorites+0.025
Neg logit contributions
 kiss-0.023
ment-0.022
less-0.020
 bless-0.020
 forgiveness-0.020
Token out
Token ID503
Feature activation+2.15e+00

Pos logit contributions
ment+0.017
 kiss+0.017
less+0.015
 forgiveness+0.015
 prayer+0.015
Neg logit contributions
pole-0.018
lves-0.017
 One-0.017
 none-0.017
chard-0.016
Token a
Token ID257
Feature activation-1.59e-01

Pos logit contributions
pole+0.085
 One+0.085
 none+0.081
 Jerry+0.075
 While+0.074
Neg logit contributions
 kiss-0.107
less-0.102
ment-0.102
guard-0.102
 bless-0.101
Token big
Token ID1263
Feature activation-1.66e+00

Pos logit contributions
ment+0.008
iness+0.007
guard+0.007
ful+0.007
 forgiveness+0.007
Neg logit contributions
pole-0.007
 One-0.007
chard-0.006
 bank-0.006
 While-0.006
Token sn
Token ID3013
Feature activation-1.35e+00

Pos logit contributions
ment+0.080
less+0.071
guard+0.067
 bless+0.066
 forgiveness+0.066
Neg logit contributions
pole-0.074
 One-0.072
 Jerry-0.071
 bank-0.065
 Ellie-0.065
Tokenarl
Token ID7063
Feature activation-7.62e+00

Pos logit contributions
 kiss+0.054
 prayer+0.050
 accidents+0.050
 bless+0.049
 forgiveness+0.047
Neg logit contributions
pole-0.070
 One-0.066
ratch-0.062
lves-0.062
 While-0.061
Token and
Token ID290
Feature activation-1.78e+00

Pos logit contributions
 forgiveness+0.378
 kiss+0.345
 bless+0.332
 accidents+0.322
prise+0.319
Neg logit contributions
pole-0.327
 bank-0.298
 One-0.291
riages-0.288
 none-0.285
Token the
Token ID262
Feature activation-7.53e-01

Pos logit contributions
 kiss+0.080
ment+0.077
less+0.070
 bless+0.069
 forgiveness+0.068
Neg logit contributions
pole-0.086
lves-0.083
 none-0.081
chard-0.081
 One-0.079
Token mouse
Token ID10211
Feature activation+1.39e+00

Pos logit contributions
ment+0.035
 kiss+0.032
less+0.031
arl+0.030
 bless+0.030
Neg logit contributions
pole-0.035
lves-0.034
chard-0.033
 One-0.033
 bank-0.032
Token knew
Token ID2993
Feature activation-4.27e-01

Pos logit contributions
pole+0.059
 none+0.054
lves+0.052
 One+0.051
chard+0.051
Neg logit contributions
ment-0.070
 kiss-0.069
 bless-0.064
less-0.064
arl-0.064
Token he
Token ID339
Feature activation+2.16e+00

Pos logit contributions
 kiss+0.019
ment+0.018
less+0.016
 bless+0.016
 prayer+0.016
Neg logit contributions
pole-0.021
lves-0.020
 none-0.020
chard-0.020
 One-0.019
Token's
Token ID338
Feature activation+1.64e+00

Pos logit contributions
ment+0.010
 kiss+0.010
less+0.009
 bless+0.009
 forgiveness+0.009
Neg logit contributions
pole-0.010
 none-0.009
 One-0.009
chard-0.009
lves-0.009
Token wonderful
Token ID7932
Feature activation+3.62e-01

Pos logit contributions
pole+0.081
lves+0.077
 none+0.077
chard+0.076
 One+0.074
Neg logit contributions
 kiss-0.073
ment-0.070
less-0.064
 bless-0.063
 forgiveness-0.062
Token,
Token ID11
Feature activation+2.77e-01

Pos logit contributions
pole+0.018
 none+0.017
lves+0.016
chard+0.016
 One+0.016
Neg logit contributions
 kiss-0.016
ment-0.015
 bless-0.014
less-0.014
 forgiveness-0.013
Token my
Token ID616
Feature activation-8.93e-01

Pos logit contributions
pole+0.013
 none+0.012
lves+0.012
chard+0.012
 One+0.012
Neg logit contributions
 kiss-0.013
ment-0.013
less-0.012
 bless-0.011
 forgiveness-0.011
Token d
Token ID288
Feature activation-8.75e-01

Pos logit contributions
ment+0.036
 kiss+0.036
less+0.032
 bless+0.031
 forgiveness+0.031
Neg logit contributions
pole-0.044
 none-0.043
 favorites-0.042
 favourites-0.042
chard-0.042
Tokenarl
Token ID7063
Feature activation-7.56e+00

Pos logit contributions
 kiss+0.030
ment+0.027
 prayer+0.026
 forgiveness+0.025
 bless+0.025
Neg logit contributions
pole-0.052
lves-0.049
 none-0.048
 favorites-0.048
uries-0.047
Tokenings
Token ID654
Feature activation-1.51e+00

Pos logit contributions
 kiss+0.305
ment+0.279
 forgiveness+0.274
 bless+0.262
less+0.260
Neg logit contributions
pole-0.388
 none-0.370
 pads-0.367
 favorites-0.359
opes-0.354
Token!"
Token ID2474
Feature activation+2.90e+00

Pos logit contributions
ment+0.070
 kiss+0.067
 forgiveness+0.061
 prayer+0.061
 bless+0.060
Neg logit contributions
pole-0.069
 One-0.065
 none-0.064
chard-0.061
lves-0.060
Token Mom
Token ID11254
Feature activation-2.92e+00

Pos logit contributions
pole+0.145
lves+0.144
chard+0.137
 none+0.135
uries+0.135
Neg logit contributions
 kiss-0.129
ment-0.121
 band-0.107
 forgiveness-0.105
 prayer-0.105
Tokenmy
Token ID1820
Feature activation-2.04e+00

Pos logit contributions
 kiss+0.137
ment+0.136
less+0.125
 forgiveness+0.122
 bless+0.121
Neg logit contributions
pole-0.133
lves-0.124
chard-0.122
 none-0.122
 One-0.121
Token says
Token ID1139
Feature activation+3.51e-01

Pos logit contributions
 kiss+0.093
ment+0.086
 bless+0.079
 prayer+0.077
 forgiveness+0.077
Neg logit contributions
pole-0.098
lves-0.098
chard-0.095
 none-0.095
uries-0.091
Tokenf
Token ID69
Feature activation-6.45e-01

Pos logit contributions
pole+0.098
lves+0.094
 none+0.092
chard+0.092
 One+0.089
Neg logit contributions
 kiss-0.091
ment-0.087
less-0.080
 bless-0.079
 forgiveness-0.078
Tokenortunate
Token ID13651
Feature activation-1.27e+00

Pos logit contributions
 kiss+0.025
ment+0.023
 forgiveness+0.021
 prayer+0.021
 bless+0.020
Neg logit contributions
pole-0.035
 none-0.033
lves-0.033
 One-0.033
 pads-0.032
Tokeny
Token ID88
Feature activation+3.18e+00

Pos logit contributions
 kiss+0.056
ment+0.054
 forgiveness+0.049
 prayer+0.048
 bless+0.046
Neg logit contributions
pole-0.065
lves-0.063
 One-0.060
 none-0.059
chard-0.058
Token,
Token ID11
Feature activation-1.95e-01

Pos logit contributions
pole+0.148
 One+0.146
 none+0.146
lves+0.145
 bank+0.140
Neg logit contributions
 kiss-0.145
ment-0.143
 forgiveness-0.128
less-0.127
 bless-0.124
Token her
Token ID607
Feature activation+1.93e-01

Pos logit contributions
ment+0.009
 kiss+0.009
less+0.008
arl+0.008
 bless+0.008
Neg logit contributions
 none-0.009
lves-0.008
chard-0.008
pole-0.008
nam-0.008
Token injuries
Token ID6821
Feature activation-7.48e+00

Pos logit contributions
 none+0.009
 favourites+0.009
 favorites+0.009
lves+0.009
 pads+0.009
Neg logit contributions
ment-0.008
 kiss-0.008
Time-0.007
guard-0.007
less-0.007
Token were
Token ID547
Feature activation+6.48e-01

Pos logit contributions
 kiss+0.340
ment+0.337
 prayer+0.310
 forgiveness+0.309
 bless+0.296
Neg logit contributions
pole-0.349
 none-0.336
 pads-0.321
 One-0.312
lves-0.312
Token so
Token ID523
Feature activation+3.65e+00

Pos logit contributions
pole+0.029
 none+0.028
lves+0.027
chard+0.027
 One+0.026
Neg logit contributions
 kiss-0.031
ment-0.031
less-0.028
 bless-0.028
 forgiveness-0.027
Token severe
Token ID6049
Feature activation-1.03e+00

Pos logit contributions
chard+0.140
 none+0.140
nam+0.132
lves+0.123
 One+0.123
Neg logit contributions
 kiss-0.187
ment-0.176
 bless-0.170
 forgiveness-0.163
 spell-0.163
Token,
Token ID11
Feature activation-2.15e-01

Pos logit contributions
 kiss+0.044
less+0.043
ment+0.042
arl+0.041
 bless+0.038
Neg logit contributions
pole-0.049
 One-0.046
 none-0.046
 bank-0.046
lves-0.045
Token she
Token ID673
Feature activation+8.01e-01

Pos logit contributions
 kiss+0.010
ment+0.010
less+0.010
arl+0.010
 bless+0.009
Neg logit contributions
 none-0.010
nam-0.009
 One-0.009
chard-0.008
pole-0.008
Token the
Token ID262
Feature activation-3.14e+00

Pos logit contributions
 none+0.105
 One+0.101
pole+0.099
chard+0.098
 favourites+0.096
Neg logit contributions
 kiss-0.091
ment-0.088
 bless-0.081
arl-0.079
less-0.077
Token lightning
Token ID14357
Feature activation-4.54e+00

Pos logit contributions
ment+0.137
 kiss+0.135
less+0.123
 bless+0.120
 forgiveness+0.118
Neg logit contributions
pole-0.152
chard-0.145
 none-0.144
lves-0.143
 One-0.138
Token streak
Token ID15113
Feature activation-1.17e+00

Pos logit contributions
 kiss+0.196
ment+0.191
 forgiveness+0.184
less+0.178
 bless+0.174
Neg logit contributions
pole-0.232
 none-0.206
 pads-0.203
 One-0.202
lves-0.197
Token across
Token ID1973
Feature activation-5.90e-01

Pos logit contributions
 kiss+0.046
ment+0.042
 forgiveness+0.042
 bless+0.039
 prayer+0.038
Neg logit contributions
pole-0.065
 none-0.060
 One-0.059
 pads-0.058
lves-0.058
Token the
Token ID262
Feature activation-2.26e+00

Pos logit contributions
 kiss+0.030
 bless+0.027
ment+0.027
arl+0.026
less+0.026
Neg logit contributions
 none-0.025
 One-0.025
pole-0.023
chard-0.022
lves-0.022
Token night
Token ID1755
Feature activation-7.47e+00

Pos logit contributions
ment+0.110
 kiss+0.109
less+0.100
 forgiveness+0.098
 bless+0.098
Neg logit contributions
pole-0.098
lves-0.095
chard-0.092
 none-0.090
 One-0.089
Token sky
Token ID6766
Feature activation-1.86e+00

Pos logit contributions
 kiss+0.359
 forgiveness+0.348
arl+0.324
ment+0.321
 bless+0.320
Neg logit contributions
pole-0.323
 none-0.309
 One-0.302
 pads-0.299
 banks-0.289
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
 kiss+0.079
 forgiveness+0.076
ment+0.074
 bless+0.071
arl+0.070
Neg logit contributions
pole-0.094
 none-0.087
 One-0.084
chard-0.082
 pads-0.082
Token It
Token ID632
Feature activation-6.39e-01

Pos logit contributions
lves+0.009
pole+0.009
chard+0.009
opes+0.009
 none+0.008
Neg logit contributions
 kiss-0.011
ment-0.010
 prayer-0.009
 bless-0.009
 forgiveness-0.009
Token was
Token ID373
Feature activation+1.67e-01

Pos logit contributions
 kiss+0.029
ment+0.029
less+0.027
 forgiveness+0.026
 bless+0.026
Neg logit contributions
pole-0.030
 none-0.028
lves-0.028
 One-0.028
chard-0.027
Token a
Token ID257
Feature activation-1.08e+00

Pos logit contributions
pole+0.007
 none+0.007
chard+0.007
lves+0.007
 One+0.006
Neg logit contributions
 kiss-0.008
ment-0.008
 forgiveness-0.007
less-0.007
 bless-0.007
Token you
Token ID345
Feature activation-2.69e+00

Pos logit contributions
 kiss+0.034
ment+0.031
 bless+0.027
 forgiveness+0.027
less+0.027
Neg logit contributions
pole-0.060
lves-0.058
chard-0.057
 none-0.057
 favourites-0.056
Token go
Token ID467
Feature activation-2.28e+00

Pos logit contributions
ment+0.100
 kiss+0.097
less+0.088
 bless+0.083
 forgiveness+0.083
Neg logit contributions
pole-0.150
 One-0.145
 none-0.141
lves-0.141
chard-0.136
Token,
Token ID11
Feature activation-5.57e-01

Pos logit contributions
 kiss+0.088
ment+0.084
less+0.075
 bless+0.074
 forgiveness+0.074
Neg logit contributions
pole-0.126
lves-0.121
 none-0.119
chard-0.119
 One-0.117
Token my
Token ID616
Feature activation-8.14e-01

Pos logit contributions
ment+0.029
less+0.025
 kiss+0.025
 prayer+0.024
 bless+0.023
Neg logit contributions
pole-0.025
lves-0.023
 none-0.023
 One-0.023
 Jerry-0.022
Token d
Token ID288
Feature activation-5.70e-01

Pos logit contributions
ment+0.035
 kiss+0.033
guard+0.032
 forgiveness+0.032
 fade+0.031
Neg logit contributions
lves-0.036
 favorites-0.035
pole-0.035
 favourites-0.035
 pads-0.035
Tokenarl
Token ID7063
Feature activation-7.40e+00

Pos logit contributions
 kiss+0.013
ment+0.011
 prayer+0.011
 forgiveness+0.011
 moment+0.011
Neg logit contributions
pole-0.040
lves-0.039
 One-0.038
ratch-0.038
opes-0.037
Tokenings
Token ID654
Feature activation-1.41e+00

Pos logit contributions
 forgiveness+0.363
 kiss+0.347
 relief+0.321
 cheer+0.320
 miracle+0.318
Neg logit contributions
 pads-0.281
pole-0.272
 none-0.266
 One-0.264
opes-0.261
Token,"
Token ID553
Feature activation+2.85e+00

Pos logit contributions
ment+0.071
 kiss+0.070
 prayer+0.064
 forgiveness+0.064
 bless+0.063
Neg logit contributions
pole-0.061
 One-0.056
lves-0.054
 none-0.054
chard-0.052
Token Mom
Token ID11254
Feature activation-2.33e+00

Pos logit contributions
 none+0.124
 One+0.122
pole+0.120
chard+0.118
nam+0.118
Neg logit contributions
ment-0.136
less-0.130
 kiss-0.128
 bless-0.124
 ray-0.118
Token said
Token ID531
Feature activation+8.20e-01

Pos logit contributions
ment+0.117
 kiss+0.116
less+0.109
 bless+0.106
 forgiveness+0.104
Neg logit contributions
pole-0.100
 none-0.091
chard-0.091
lves-0.091
 One-0.089
Token.
Token ID13
Feature activation-3.34e-02

Pos logit contributions
pole+0.038
 none+0.037
chard+0.037
 One+0.036
nam+0.036
Neg logit contributions
 kiss-0.035
ment-0.034
 bless-0.034
 prayer-0.032
Time-0.031
Token's
Token ID338
Feature activation+1.46e+00

Pos logit contributions
 kiss+0.076
ment+0.068
 bless+0.066
 prayer+0.066
 band+0.065
Neg logit contributions
chard-0.075
lves-0.072
pole-0.071
nam-0.069
 none-0.069
Token okay
Token ID8788
Feature activation-2.44e+00

Pos logit contributions
pole+0.075
lves+0.074
chard+0.071
 none+0.070
 favourites+0.068
Neg logit contributions
 kiss-0.062
ment-0.058
less-0.053
 bless-0.053
 forgiveness-0.053
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
 kiss+0.107
ment+0.105
pour+0.092
 bless+0.092
 ray+0.091
Neg logit contributions
 One-0.117
 none-0.112
pole-0.112
chard-0.103
 pads-0.103
Token my
Token ID616
Feature activation-3.69e-01

Pos logit contributions
ment+0.007
 kiss+0.007
less+0.007
 bless+0.006
 forgiveness+0.006
Neg logit contributions
pole-0.007
 none-0.006
 One-0.006
lves-0.006
chard-0.006
Token d
Token ID288
Feature activation-5.53e-01

Pos logit contributions
ment+0.018
guard+0.017
pour+0.017
 kiss+0.016
ful+0.016
Neg logit contributions
 favorites-0.015
 favourites-0.015
 One-0.014
 none-0.013
 favorite-0.013
Tokenarl
Token ID7063
Feature activation-7.36e+00

Pos logit contributions
 kiss+0.014
 moment+0.013
 forgiveness+0.012
ment+0.012
 prayer+0.012
Neg logit contributions
pole-0.037
opes-0.035
ratch-0.035
 pads-0.035
uries-0.035
Tokenings
Token ID654
Feature activation-1.38e+00

Pos logit contributions
 forgiveness+0.363
 kiss+0.351
 relief+0.334
 accidents+0.332
ful+0.328
Neg logit contributions
 pads-0.271
 bank-0.263
 favorites-0.257
 none-0.257
pole-0.256
Token.
Token ID13
Feature activation-5.49e-01

Pos logit contributions
ment+0.064
 kiss+0.062
 forgiveness+0.055
 prayer+0.055
 bless+0.055
Neg logit contributions
pole-0.065
 One-0.063
 pads-0.060
 none-0.059
riages-0.056
Token I
Token ID314
Feature activation-1.25e+00

Pos logit contributions
 kiss+0.030
ment+0.029
less+0.028
 bless+0.027
 band+0.027
Neg logit contributions
pole-0.020
 One-0.019
 none-0.019
lves-0.019
chard-0.018
Token forgive
Token ID20927
Feature activation-2.18e+00

Pos logit contributions
ment+0.056
 kiss+0.047
 accidents+0.046
less+0.045
 forgiveness+0.044
Neg logit contributions
 One-0.061
 none-0.059
 favourites-0.058
 favorites-0.058
pole-0.058
Token you
Token ID345
Feature activation-1.87e+00

Pos logit contributions
 kiss+0.088
ment+0.086
less+0.079
 prayer+0.075
 bless+0.074
Neg logit contributions
pole-0.113
 none-0.110
 One-0.108
lves-0.107
chard-0.107
Token'm
Token ID1101
Feature activation-1.37e+00

Pos logit contributions
ment+0.040
 kiss+0.037
less+0.034
 forgiveness+0.033
 accidents+0.033
Neg logit contributions
 One-0.041
 none-0.040
lves-0.040
pole-0.040
 favourites-0.040
Token sorry
Token ID7926
Feature activation-1.23e+00

Pos logit contributions
 kiss+0.048
ment+0.042
 bless+0.040
 forgiveness+0.039
 band+0.039
Neg logit contributions
pole-0.080
lves-0.078
 pads-0.078
opes-0.076
chard-0.075
Token,
Token ID11
Feature activation-4.58e-01

Pos logit contributions
 kiss+0.051
ment+0.049
less+0.044
 bless+0.044
 forgiveness+0.043
Neg logit contributions
pole-0.062
 One-0.061
 none-0.061
lves-0.059
chard-0.056
Token my
Token ID616
Feature activation-7.35e-01

Pos logit contributions
 kiss+0.020
ment+0.020
less+0.018
 forgiveness+0.018
 bless+0.018
Neg logit contributions
pole-0.022
 none-0.022
lves-0.021
 One-0.020
chard-0.020
Token d
Token ID288
Feature activation-5.78e-01

Pos logit contributions
 kiss+0.034
ment+0.033
 bless+0.029
less+0.029
 forgiveness+0.029
Neg logit contributions
pole-0.034
lves-0.033
 none-0.033
 One-0.032
chard-0.032
Tokenarl
Token ID7063
Feature activation-7.33e+00

Pos logit contributions
 kiss+0.013
ment+0.011
 forgiveness+0.011
 prayer+0.010
 moment+0.010
Neg logit contributions
pole-0.042
lves-0.039
opes-0.039
 One-0.038
uries-0.038
Tokenings
Token ID654
Feature activation-1.40e+00

Pos logit contributions
 forgiveness+0.367
 kiss+0.352
 relief+0.339
 accidents+0.333
 miracle+0.330
Neg logit contributions
pole-0.269
 bank-0.265
 pads-0.265
 none-0.261
opes-0.254
Token.
Token ID13
Feature activation-4.52e-01

Pos logit contributions
ment+0.066
 kiss+0.062
 forgiveness+0.058
 bless+0.056
 prayer+0.056
Neg logit contributions
pole-0.064
 One-0.060
 none-0.058
 pads-0.057
 Jerry-0.054
Token The
Token ID383
Feature activation-9.35e-01

Pos logit contributions
 kiss+0.024
ment+0.024
less+0.022
 bless+0.022
 forgiveness+0.021
Neg logit contributions
pole-0.018
lves-0.017
chard-0.017
 none-0.017
 favourites-0.016
Token tornado
Token ID33718
Feature activation-1.11e+00

Pos logit contributions
ment+0.046
 kiss+0.043
less+0.041
ful+0.040
 bless+0.039
Neg logit contributions
pole-0.042
 none-0.041
 One-0.040
lves-0.039
chard-0.038
Token took
Token ID1718
Feature activation-9.89e-01

Pos logit contributions
ment+0.050
 kiss+0.046
less+0.044
 forgiveness+0.042
ful+0.041
Neg logit contributions
pole-0.054
 none-0.051
lves-0.050
 One-0.048
 bank-0.047
TokenWhat
Token ID2061
Feature activation-3.53e-01

Pos logit contributions
lves+0.130
 One+0.115
chard+0.113
pole+0.112
 none+0.111
Neg logit contributions
 kiss-0.147
ment-0.146
 prayer-0.144
less-0.139
 ray-0.135
Token happened
Token ID3022
Feature activation-4.50e-01

Pos logit contributions
 kiss+0.016
ment+0.016
less+0.014
 bless+0.013
 prayer+0.013
Neg logit contributions
pole-0.017
 none-0.016
 One-0.016
chard-0.016
lves-0.016
Token,
Token ID11
Feature activation-3.19e-01

Pos logit contributions
 kiss+0.024
ment+0.023
 prayer+0.021
 fade+0.021
 ray+0.021
Neg logit contributions
 One-0.017
chard-0.017
 none-0.016
 gonna-0.016
 Jerry-0.015
Token my
Token ID616
Feature activation-5.34e-01

Pos logit contributions
ment+0.018
less+0.016
 kiss+0.015
 bless+0.015
guard+0.014
Neg logit contributions
 none-0.013
pole-0.012
 One-0.012
lves-0.011
 Jerry-0.011
Token d
Token ID288
Feature activation-5.59e-01

Pos logit contributions
 kiss+0.024
ment+0.024
 bless+0.022
guard+0.022
 forgiveness+0.022
Neg logit contributions
pole-0.022
lves-0.022
 favorites-0.022
 favourites-0.022
 One-0.022
Tokenarl
Token ID7063
Feature activation-7.31e+00

Pos logit contributions
 kiss+0.014
 moment+0.012
 prayer+0.012
 forgiveness+0.012
ment+0.011
Neg logit contributions
pole-0.038
lves-0.037
opes-0.036
ratch-0.036
 One-0.036
Tokenings
Token ID654
Feature activation-1.32e+00

Pos logit contributions
 forgiveness+0.371
 kiss+0.352
 relief+0.352
 miracle+0.341
 comforting+0.337
Neg logit contributions
 pads-0.252
 none-0.234
pole-0.231
 One-0.231
 bank-0.230
Token?
Token ID30
Feature activation+7.26e-02

Pos logit contributions
ment+0.067
 kiss+0.061
 prayer+0.058
 forgiveness+0.056
 bless+0.054
Neg logit contributions
pole-0.054
 One-0.054
 none-0.051
chard-0.050
 pads-0.049
Token Why
Token ID4162
Feature activation+3.34e-01

Pos logit contributions
pole+0.003
lves+0.003
 none+0.003
chard+0.003
 One+0.002
Neg logit contributions
 kiss-0.004
ment-0.004
less-0.004
 bless-0.004
 forgiveness-0.004
Token do
Token ID466
Feature activation-9.23e-01

Pos logit contributions
pole+0.016
 none+0.016
lves+0.015
chard+0.015
 One+0.015
Neg logit contributions
 kiss-0.015
ment-0.015
less-0.013
 bless-0.013
 forgiveness-0.013
Token you
Token ID345
Feature activation-1.94e+00

Pos logit contributions
 kiss+0.036
ment+0.035
less+0.032
 bless+0.031
 prayer+0.030
Neg logit contributions
pole-0.048
 none-0.048
lves-0.047
chard-0.046
 One-0.046
Token'm
Token ID1101
Feature activation-1.59e+00

Pos logit contributions
ment+0.048
 kiss+0.045
less+0.040
 forgiveness+0.040
 bless+0.040
Neg logit contributions
 One-0.051
lves-0.051
pole-0.050
 none-0.050
 favourites-0.048
Token sorry
Token ID7926
Feature activation-1.19e+00

Pos logit contributions
 kiss+0.055
ment+0.049
 bless+0.045
 forgiveness+0.045
 band+0.045
Neg logit contributions
pole-0.095
lves-0.091
chard-0.091
 favourites-0.089
 favorites-0.089
Token,
Token ID11
Feature activation-6.24e-01

Pos logit contributions
 kiss+0.051
ment+0.051
 bless+0.046
less+0.045
pour+0.044
Neg logit contributions
 One-0.058
pole-0.056
 none-0.055
lves-0.053
opes-0.051
Token my
Token ID616
Feature activation-7.31e-01

Pos logit contributions
ment+0.030
less+0.027
 kiss+0.027
 bless+0.026
guard+0.025
Neg logit contributions
 none-0.029
pole-0.029
 One-0.027
nam-0.026
chard-0.026
Token d
Token ID288
Feature activation-6.61e-01

Pos logit contributions
 kiss+0.029
ment+0.029
 bless+0.026
 forgiveness+0.026
guard+0.026
Neg logit contributions
pole-0.036
lves-0.035
 none-0.034
 favorites-0.034
 One-0.033
Tokenarl
Token ID7063
Feature activation-7.30e+00

Pos logit contributions
 kiss+0.017
 prayer+0.014
ment+0.014
 moment+0.014
 forgiveness+0.014
Neg logit contributions
pole-0.046
lves-0.043
 One-0.042
ratch-0.042
opes-0.042
Tokenings
Token ID654
Feature activation-1.44e+00

Pos logit contributions
 forgiveness+0.371
 kiss+0.352
 relief+0.343
 comforting+0.342
 miracle+0.341
Neg logit contributions
 pads-0.242
 bank-0.236
 none-0.232
 One-0.230
pole-0.230
Token.
Token ID13
Feature activation-3.72e-01

Pos logit contributions
ment+0.073
 kiss+0.068
 bless+0.065
 prayer+0.064
 forgiveness+0.062
Neg logit contributions
pole-0.060
 One-0.059
 none-0.053
 pads-0.052
 Jerry-0.051
Token That
Token ID1320
Feature activation+5.70e-01

Pos logit contributions
 kiss+0.022
ment+0.021
less+0.020
 bless+0.019
 forgiveness+0.019
Neg logit contributions
pole-0.013
lves-0.012
 none-0.012
chard-0.012
 One-0.012
Token was
Token ID373
Feature activation+1.62e-01

Pos logit contributions
pole+0.028
lves+0.028
chard+0.027
 none+0.027
 favourites+0.026
Neg logit contributions
 kiss-0.025
ment-0.023
 bless-0.021
 forgiveness-0.021
less-0.021
Token a
Token ID257
Feature activation-6.17e-01

Pos logit contributions
pole+0.008
lves+0.008
 favourites+0.007
 favorites+0.007
chard+0.007
Neg logit contributions
 kiss-0.007
ment-0.006
 forgiveness-0.006
less-0.006
 bless-0.006
Token's
Token ID338
Feature activation+1.40e+00

Pos logit contributions
 kiss+0.049
ment+0.047
less+0.043
 bless+0.043
 forgiveness+0.043
Neg logit contributions
pole-0.041
lves-0.040
chard-0.039
 none-0.039
 favourites-0.037
Token good
Token ID922
Feature activation-3.53e-01

Pos logit contributions
pole+0.065
lves+0.063
 none+0.062
chard+0.062
 One+0.060
Neg logit contributions
 kiss-0.065
ment-0.063
less-0.057
 bless-0.057
 forgiveness-0.056
Token,
Token ID11
Feature activation-6.95e-01

Pos logit contributions
 kiss+0.017
 bless+0.016
 fade+0.016
ment+0.016
pour+0.016
Neg logit contributions
 One-0.013
 favorites-0.012
opes-0.012
 none-0.012
 pads-0.012
Token my
Token ID616
Feature activation-5.06e-01

Pos logit contributions
ment+0.030
 kiss+0.029
less+0.027
 bless+0.026
guard+0.025
Neg logit contributions
pole-0.035
 none-0.033
lves-0.032
 One-0.032
chard-0.031
Token d
Token ID288
Feature activation-6.11e-01

Pos logit contributions
 kiss+0.022
ment+0.022
guard+0.021
 forgiveness+0.020
 bless+0.020
Neg logit contributions
lves-0.022
pole-0.022
 favorites-0.022
 favourites-0.022
 none-0.022
Tokenarl
Token ID7063
Feature activation-7.26e+00

Pos logit contributions
 kiss+0.021
 forgiveness+0.019
 prayer+0.018
 moment+0.018
ment+0.018
Neg logit contributions
pole-0.036
lves-0.035
opes-0.034
ratch-0.033
 One-0.033
Tokenings
Token ID654
Feature activation-1.37e+00

Pos logit contributions
 forgiveness+0.359
 kiss+0.356
 relief+0.323
ful+0.321
 comforting+0.316
Neg logit contributions
opes-0.263
 none-0.262
pole-0.253
 bank-0.252
 pads-0.251
Token.
Token ID13
Feature activation-4.02e-01

Pos logit contributions
ment+0.063
 kiss+0.061
 bless+0.056
 forgiveness+0.055
 prayer+0.055
Neg logit contributions
pole-0.064
 One-0.061
 none-0.057
 pads-0.056
lves-0.055
Token I
Token ID314
Feature activation-1.33e+00

Pos logit contributions
 kiss+0.022
ment+0.021
less+0.020
 bless+0.020
 forgiveness+0.019
Neg logit contributions
pole-0.015
lves-0.015
 none-0.014
chard-0.014
 One-0.014
Token'm
Token ID1101
Feature activation-1.85e+00

Pos logit contributions
ment+0.058
 kiss+0.054
less+0.050
 forgiveness+0.050
 prayer+0.048
Neg logit contributions
lves-0.063
pole-0.063
 One-0.063
 none-0.062
 favourites-0.062
Token glad
Token ID9675
Feature activation+1.55e-01

Pos logit contributions
 kiss+0.076
ment+0.070
 bless+0.066
less+0.064
 band+0.064
Neg logit contributions
pole-0.097
lves-0.093
 pads-0.091
opes-0.091
chard-0.090
TokenThe
Token ID464
Feature activation-8.50e-01

Pos logit contributions
 kiss+0.035
ment+0.035
 prayer+0.033
 forgiveness+0.032
 bless+0.032
Neg logit contributions
 One-0.038
lves-0.037
pole-0.037
 While-0.036
 none-0.035
Token butterfly
Token ID35113
Feature activation+7.99e-01

Pos logit contributions
ment+0.037
less+0.033
 kiss+0.032
 bless+0.031
arl+0.030
Neg logit contributions
chard-0.043
pole-0.042
nam-0.040
 none-0.040
 tallest-0.040
Token flew
Token ID13112
Feature activation-6.04e-01

Pos logit contributions
pole+0.035
lves+0.033
 none+0.033
chard+0.032
 One+0.031
Neg logit contributions
 kiss-0.040
ment-0.038
less-0.035
 bless-0.035
 forgiveness-0.034
Token into
Token ID656
Feature activation-1.40e-01

Pos logit contributions
 kiss+0.028
ment+0.028
 forgiveness+0.026
 bless+0.026
 prayer+0.025
Neg logit contributions
pole-0.030
 none-0.027
chard-0.027
lves-0.026
 One-0.026
Token the
Token ID262
Feature activation-1.45e+00

Pos logit contributions
iness+0.008
ment+0.008
guard+0.008
arl+0.008
less+0.007
Neg logit contributions
 One-0.004
 none-0.004
nam-0.004
lves-0.004
 lots-0.004
Token night
Token ID1755
Feature activation-7.22e+00

Pos logit contributions
ment+0.080
less+0.077
 forgiveness+0.077
ful+0.075
 bless+0.073
Neg logit contributions
 tallest-0.050
 One-0.049
pole-0.048
 pads-0.046
lves-0.046
Token sky
Token ID6766
Feature activation-2.21e+00

Pos logit contributions
 forgiveness+0.397
 apology+0.369
arl+0.353
 kiss+0.345
aid+0.345
Neg logit contributions
pole-0.271
 pads-0.255
 One-0.249
 Suddenly-0.248
 banks-0.235
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
 forgiveness+0.100
arl+0.097
 kiss+0.093
 bless+0.090
ment+0.090
Neg logit contributions
pole-0.109
 none-0.096
 One-0.094
 pads-0.091
 Suddenly-0.088
Token its
Token ID663
Feature activation-7.80e-01

Pos logit contributions
ment+0.011
 kiss+0.011
 forgiveness+0.010
less+0.010
guard+0.009
Neg logit contributions
pole-0.011
 none-0.010
chard-0.010
lves-0.010
 pads-0.010
Token colors
Token ID7577
Feature activation-1.44e+00

Pos logit contributions
ment+0.037
 kiss+0.037
less+0.034
 bless+0.034
 forgiveness+0.033
Neg logit contributions
pole-0.033
 none-0.033
chard-0.032
 favourites-0.031
 favorites-0.031
Token shimmer
Token ID34493
Feature activation-2.78e-01

Pos logit contributions
 forgiveness+0.068
 kiss+0.068
ment+0.066
 bless+0.065
 prayer+0.063
Neg logit contributions
pole-0.066
 none-0.061
 pads-0.057
chard-0.054
 One-0.053
Token He
Token ID679
Feature activation+7.46e-01

Pos logit contributions
 kiss+0.005
ment+0.004
 moment+0.004
 prayer+0.004
 band+0.004
Neg logit contributions
pole-0.009
lves-0.009
chard-0.008
 none-0.008
nam-0.008
Token looked
Token ID3114
Feature activation+5.26e-01

Pos logit contributions
pole+0.031
lves+0.030
chard+0.029
 none+0.029
opes+0.028
Neg logit contributions
 kiss-0.038
ment-0.035
 band-0.034
 fairy-0.033
 prayer-0.032
Token up
Token ID510
Feature activation+9.92e-01

Pos logit contributions
pole+0.029
lves+0.027
 none+0.027
chard+0.027
uries+0.027
Neg logit contributions
 kiss-0.020
ment-0.019
less-0.017
 prayer-0.017
 bless-0.016
Token into
Token ID656
Feature activation-2.91e-01

Pos logit contributions
 none+0.049
 One+0.048
chard+0.048
pole+0.048
 favourites+0.045
Neg logit contributions
 kiss-0.044
 bless-0.040
ment-0.040
 forgiveness-0.039
 prayer-0.037
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
 kiss+0.014
less+0.013
ment+0.013
 bless+0.013
arl+0.013
Neg logit contributions
nam-0.013
 One-0.012
 none-0.012
chard-0.012
 bicycles-0.012
Token night
Token ID1755
Feature activation-7.21e+00

Pos logit contributions
ment+0.076
 kiss+0.073
ful+0.069
 forgiveness+0.069
 bless+0.069
Neg logit contributions
 One-0.058
pole-0.057
chard-0.057
lves-0.056
 favorites-0.054
Token sky
Token ID6766
Feature activation-2.31e+00

Pos logit contributions
 forgiveness+0.373
 apology+0.359
ment+0.356
 kiss+0.350
arl+0.349
Neg logit contributions
pole-0.285
 pads-0.275
 One-0.270
ramids-0.260
chard-0.255
Token and
Token ID290
Feature activation-2.56e-01

Pos logit contributions
 kiss+0.107
 forgiveness+0.102
ment+0.101
arl+0.101
 bless+0.100
Neg logit contributions
pole-0.112
 none-0.106
 One-0.104
 pads-0.099
chard-0.097
Token saw
Token ID2497
Feature activation+7.46e-01

Pos logit contributions
 kiss+0.013
ment+0.012
less+0.011
 bless+0.011
 forgiveness+0.011
Neg logit contributions
pole-0.011
lves-0.011
 none-0.010
chard-0.010
 One-0.010
Token a
Token ID257
Feature activation-6.62e-01

Pos logit contributions
pole+0.036
lves+0.035
chard+0.034
 none+0.034
uries+0.033
Neg logit contributions
 kiss-0.033
ment-0.032
 forgiveness-0.029
less-0.029
 bless-0.029
Token tw
Token ID665
Feature activation+3.70e-01

Pos logit contributions
ment+0.030
 kiss+0.027
less+0.025
 forgiveness+0.025
iness+0.025
Neg logit contributions
pole-0.032
chard-0.032
lves-0.031
 none-0.030
 One-0.030
Token you
Token ID345
Feature activation-2.89e+00

Pos logit contributions
 kiss+0.022
ment+0.020
 forgiveness+0.018
less+0.018
 bless+0.018
Neg logit contributions
pole-0.043
lves-0.042
chard-0.041
 favourites-0.040
 favorites-0.040
Token okay
Token ID8788
Feature activation-2.35e+00

Pos logit contributions
 kiss+0.141
ment+0.140
less+0.124
 bless+0.123
 prayer+0.123
Neg logit contributions
pole-0.127
 none-0.123
lves-0.123
chard-0.119
 pads-0.115
Token,
Token ID11
Feature activation-2.37e-02

Pos logit contributions
ment+0.116
 kiss+0.111
less+0.100
 bless+0.096
guard+0.096
Neg logit contributions
 One-0.101
pole-0.099
 none-0.096
chard-0.094
 Jerry-0.091
Token my
Token ID616
Feature activation-3.85e-01

Pos logit contributions
ment+0.001
 kiss+0.001
less+0.001
 bless+0.001
guard+0.001
Neg logit contributions
 none-0.001
 One-0.001
pole-0.001
lves-0.001
 ours-0.001
Token d
Token ID288
Feature activation-5.09e-01

Pos logit contributions
 kiss+0.016
ment+0.016
 bless+0.015
 forgiveness+0.014
guard+0.014
Neg logit contributions
pole-0.018
lves-0.018
 none-0.017
opes-0.017
 One-0.017
Tokenarl
Token ID7063
Feature activation-7.21e+00

Pos logit contributions
 kiss+0.013
ment+0.011
 prayer+0.011
 moment+0.010
 forgiveness+0.010
Neg logit contributions
pole-0.036
lves-0.034
opes-0.033
ratch-0.033
 One-0.033
Tokenings
Token ID654
Feature activation-1.37e+00

Pos logit contributions
 forgiveness+0.358
 kiss+0.344
 relief+0.325
 miracle+0.322
 comforting+0.321
Neg logit contributions
 pads-0.262
pole-0.249
 none-0.248
 bank-0.247
 One-0.244
Token?"
Token ID1701
Feature activation+2.49e+00

Pos logit contributions
ment+0.084
 kiss+0.076
 prayer+0.073
 forgiveness+0.071
less+0.070
Neg logit contributions
pole-0.046
 One-0.044
 Jerry-0.041
chard-0.039
 none-0.038
Token Mom
Token ID11254
Feature activation-2.59e+00

Pos logit contributions
 One+0.122
 none+0.116
chard+0.113
pole+0.110
nam+0.109
Neg logit contributions
ment-0.109
 kiss-0.105
less-0.104
 bless-0.098
guard-0.095
Token asked
Token ID1965
Feature activation+2.38e+00

Pos logit contributions
ment+0.165
 kiss+0.160
less+0.156
 bless+0.150
 forgiveness+0.149
Neg logit contributions
pole-0.080
 One-0.070
chard-0.069
 none-0.065
lves-0.065
Token.
Token ID13
Feature activation+9.89e-02

Pos logit contributions
 One+0.100
 none+0.098
chard+0.095
pole+0.095
nam+0.093
Neg logit contributions
 kiss-0.112
 prayer-0.106
 bless-0.105
ment-0.104
 ray-0.101
Token you
Token ID345
Feature activation-3.00e+00

Pos logit contributions
 kiss+0.030
ment+0.027
less+0.024
 bless+0.024
 forgiveness+0.024
Neg logit contributions
pole-0.055
lves-0.053
chard-0.052
 none-0.051
 favourites-0.051
Token okay
Token ID8788
Feature activation-2.43e+00

Pos logit contributions
 kiss+0.139
ment+0.135
less+0.122
 bless+0.121
 forgiveness+0.119
Neg logit contributions
pole-0.140
lves-0.135
 none-0.134
chard-0.132
 One-0.128
Token,
Token ID11
Feature activation-2.37e-01

Pos logit contributions
ment+0.125
 kiss+0.116
less+0.107
 sensation+0.104
 bless+0.103
Neg logit contributions
 One-0.102
pole-0.097
 none-0.094
 Jerry-0.091
chard-0.091
Token my
Token ID616
Feature activation-1.85e-01

Pos logit contributions
ment+0.013
less+0.010
ore+0.010
 sensation+0.010
 fade+0.010
Neg logit contributions
 none-0.010
 One-0.010
pole-0.009
 Jerry-0.009
 ours-0.009
Token d
Token ID288
Feature activation-4.29e-01

Pos logit contributions
ment+0.009
 kiss+0.008
 bless+0.008
pour+0.008
 forgiveness+0.008
Neg logit contributions
lves-0.008
 favorites-0.007
 favourites-0.007
 One-0.007
pole-0.007
Tokenarl
Token ID7063
Feature activation-7.12e+00

Pos logit contributions
 kiss+0.011
ment+0.010
 prayer+0.009
 forgiveness+0.009
 moment+0.009
Neg logit contributions
pole-0.030
lves-0.029
opes-0.028
ratch-0.028
 One-0.027
Tokenings
Token ID654
Feature activation-1.23e+00

Pos logit contributions
 forgiveness+0.337
 kiss+0.332
ful+0.307
 fairy+0.305
 relief+0.303
Neg logit contributions
 pads-0.265
 none-0.263
pole-0.262
opes-0.258
 One-0.256
Token?"
Token ID1701
Feature activation+2.46e+00

Pos logit contributions
ment+0.073
 kiss+0.064
 prayer+0.064
 forgiveness+0.061
 bless+0.060
Neg logit contributions
pole-0.044
 One-0.042
 Jerry-0.038
chard-0.035
 Ellie-0.035
Token she
Token ID673
Feature activation+1.35e+00

Pos logit contributions
 One+0.120
 none+0.118
chard+0.117
pole+0.117
lves+0.114
Neg logit contributions
ment-0.103
 kiss-0.103
less-0.097
 bless-0.093
 prayer-0.090
Token asked
Token ID1965
Feature activation+2.44e+00

Pos logit contributions
pole+0.046
lves+0.045
chard+0.043
 none+0.043
 favourites+0.042
Neg logit contributions
 kiss-0.080
ment-0.075
 band-0.072
 forgiveness-0.070
 bless-0.070
Token.
Token ID13
Feature activation-1.45e-02

Pos logit contributions
pole+0.120
 none+0.119
chard+0.118
 One+0.117
nam+0.114
Neg logit contributions
 kiss-0.101
ment-0.096
 bless-0.092
 prayer-0.091
less-0.087
Token perfect
Token ID2818
Feature activation+1.07e+00

Pos logit contributions
 kiss+0.007
ment+0.006
 bless+0.006
 forgiveness+0.006
 fairy+0.006
Neg logit contributions
pole-0.009
lves-0.009
chard-0.008
 pads-0.008
opes-0.008
Token fish
Token ID5916
Feature activation+3.91e+00

Pos logit contributions
pole+0.050
 none+0.049
 favourites+0.046
lves+0.046
 favorites+0.046
Neg logit contributions
 kiss-0.048
ment-0.047
 bless-0.042
 forgiveness-0.042
less-0.041
Token,
Token ID11
Feature activation-1.64e-01

Pos logit contributions
pole+0.205
 none+0.192
chard+0.190
lves+0.189
 pads+0.183
Neg logit contributions
 kiss-0.160
ment-0.154
 forgiveness-0.136
 bless-0.136
 prayer-0.135
Token my
Token ID616
Feature activation-4.16e-01

Pos logit contributions
ment+0.008
 kiss+0.007
less+0.007
 bless+0.007
guard+0.007
Neg logit contributions
pole-0.007
 none-0.007
 One-0.007
lves-0.007
nam-0.007
Token d
Token ID288
Feature activation-3.26e-01

Pos logit contributions
ment+0.018
 kiss+0.018
less+0.016
ful+0.016
 forgiveness+0.016
Neg logit contributions
 favorites-0.019
 favourites-0.019
pole-0.018
 none-0.018
lves-0.018
Tokenarl
Token ID7063
Feature activation-7.12e+00

Pos logit contributions
 kiss+0.013
ment+0.012
 forgiveness+0.012
 prayer+0.012
 bless+0.011
Neg logit contributions
pole-0.018
lves-0.017
chard-0.016
 none-0.016
opes-0.016
Tokenings
Token ID654
Feature activation-1.21e+00

Pos logit contributions
 forgiveness+0.349
 kiss+0.344
 relief+0.322
 miracle+0.309
 fairy+0.309
Neg logit contributions
 pads-0.269
 favorites-0.268
opes-0.267
 none-0.267
pole-0.264
Token,"
Token ID553
Feature activation+2.95e+00

Pos logit contributions
ment+0.054
 kiss+0.052
 forgiveness+0.048
 prayer+0.047
 bless+0.047
Neg logit contributions
pole-0.059
 One-0.055
 pads-0.052
 none-0.052
 Jerry-0.051
Token mom
Token ID1995
Feature activation-1.90e+00

Pos logit contributions
 One+0.146
 none+0.143
nam+0.140
chard+0.136
pole+0.135
Neg logit contributions
ment-0.133
less-0.122
 kiss-0.111
iness-0.110
pour-0.108
Token says
Token ID1139
Feature activation+9.76e-01

Pos logit contributions
 kiss+0.086
ment+0.083
less+0.076
 bless+0.075
 forgiveness+0.074
Neg logit contributions
pole-0.091
lves-0.087
 none-0.086
chard-0.086
 One-0.084
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
pole+0.036
 none+0.036
 One+0.036
nam+0.035
chard+0.035
Neg logit contributions
 kiss-0.046
Time-0.046
ment-0.046
 bless-0.045
pour-0.045
Token magical
Token ID10883
Feature activation-1.60e+00

Pos logit contributions
 kiss+0.026
ment+0.025
ful+0.023
less+0.023
Time+0.023
Neg logit contributions
pole-0.030
 none-0.029
 favorites-0.029
 favourites-0.029
chard-0.028
Token snow
Token ID6729
Feature activation-2.43e+00

Pos logit contributions
 kiss+0.074
ment+0.071
less+0.068
ful+0.067
 bless+0.067
Neg logit contributions
pole-0.070
 none-0.067
 favourites-0.065
 One-0.065
 favorites-0.065
Token that
Token ID326
Feature activation-2.74e+00

Pos logit contributions
 kiss+0.109
 forgiveness+0.097
 bless+0.097
arl+0.096
ment+0.096
Neg logit contributions
pole-0.123
 none-0.113
 pads-0.112
opes-0.109
riages-0.105
Token filled
Token ID5901
Feature activation-6.35e-01

Pos logit contributions
 kiss+0.127
ment+0.126
less+0.113
 bless+0.113
 forgiveness+0.110
Neg logit contributions
pole-0.126
 none-0.125
chard-0.119
lves-0.117
 One-0.115
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
 kiss+0.027
ment+0.026
 prayer+0.024
 bless+0.024
arl+0.023
Neg logit contributions
pole-0.033
 none-0.032
chard-0.031
lves-0.029
nam-0.029
Token night
Token ID1755
Feature activation-7.11e+00

Pos logit contributions
ment+0.060
 kiss+0.058
less+0.053
 forgiveness+0.053
ful+0.053
Neg logit contributions
pole-0.061
lves-0.058
 tallest-0.057
 pads-0.056
 none-0.056
Token sky
Token ID6766
Feature activation-2.10e+00

Pos logit contributions
 forgiveness+0.323
arl+0.320
 kiss+0.320
 apology+0.311
ment+0.305
Neg logit contributions
pole-0.324
 pads-0.298
 none-0.294
 One-0.286
 banks-0.273
Token with
Token ID351
Feature activation+1.36e+00

Pos logit contributions
 forgiveness+0.089
 kiss+0.088
arl+0.088
ment+0.087
irk+0.083
Neg logit contributions
pole-0.106
 none-0.096
 One-0.092
 pads-0.091
 tallest-0.086
Token beauty
Token ID8737
Feature activation-1.79e+00

Pos logit contributions
 none+0.065
pole+0.062
 favourites+0.060
 One+0.059
 favorites+0.059
Neg logit contributions
 kiss-0.058
ment-0.057
arl-0.053
 bless-0.053
guard-0.052
Token and
Token ID290
Feature activation+2.18e-01

Pos logit contributions
 kiss+0.074
 forgiveness+0.069
 bless+0.069
ment+0.067
arl+0.066
Neg logit contributions
pole-0.089
 none-0.083
 pads-0.082
 One-0.077
chard-0.076
Token wonder
Token ID4240
Feature activation-9.53e-02

Pos logit contributions
 none+0.011
pole+0.010
 pads+0.010
nam+0.010
chard+0.010
Neg logit contributions
 kiss-0.009
arl-0.009
ment-0.008
less-0.008
guard-0.008
Token.
Token ID13
Feature activation-3.40e-01

Pos logit contributions
 kiss+0.043
ment+0.041
 bless+0.041
 forgiveness+0.040
 prayer+0.037
Neg logit contributions
pole-0.045
 none-0.041
 pads-0.040
 One-0.038
 bank-0.038
Token It
Token ID632
Feature activation-6.27e-01

Pos logit contributions
 kiss+0.018
ment+0.016
 band+0.015
 prayer+0.015
 forgiveness+0.015
Neg logit contributions
pole-0.015
lves-0.014
chard-0.013
 none-0.013
 favourites-0.013
Token rolled
Token ID11686
Feature activation+3.77e-02

Pos logit contributions
 kiss+0.028
ment+0.027
less+0.025
 bless+0.025
 forgiveness+0.024
Neg logit contributions
pole-0.030
 none-0.029
lves-0.029
chard-0.029
 One-0.028
Token off
Token ID572
Feature activation+2.93e-01

Pos logit contributions
pole+0.002
 none+0.002
lves+0.002
chard+0.002
 One+0.002
Neg logit contributions
 kiss-0.002
ment-0.001
 bless-0.001
 forgiveness-0.001
 prayer-0.001
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
pole+0.015
 none+0.015
 One+0.015
chard+0.014
lves+0.014
Neg logit contributions
 kiss-0.012
ment-0.011
 bless-0.010
less-0.010
 forgiveness-0.010
Token night
Token ID1755
Feature activation-7.10e+00

Pos logit contributions
ment+0.075
 kiss+0.066
less+0.066
 bless+0.063
ful+0.063
Neg logit contributions
pole-0.055
 bank-0.053
 One-0.052
 banks-0.052
 pads-0.051
Tokenstand
Token ID1481
Feature activation-5.30e+00

Pos logit contributions
 forgiveness+0.314
ment+0.291
 apology+0.272
irk+0.272
 kiss+0.269
Neg logit contributions
 pads-0.347
pole-0.342
 One-0.322
 bank-0.311
 banks-0.301
Token and
Token ID290
Feature activation-7.35e-01

Pos logit contributions
 kiss+0.188
ment+0.182
 forgiveness+0.161
 bless+0.161
less+0.155
Neg logit contributions
pole-0.308
 none-0.292
lves-0.288
chard-0.287
 One-0.283
Token under
Token ID739
Feature activation+9.47e-01

Pos logit contributions
 kiss+0.037
ment+0.037
less+0.035
 bless+0.034
 forgiveness+0.033
Neg logit contributions
 none-0.030
chard-0.030
pole-0.029
lves-0.029
nam-0.028
Token the
Token ID262
Feature activation-1.53e-01

Pos logit contributions
pole+0.052
lves+0.050
 none+0.050
chard+0.050
 One+0.049
Neg logit contributions
 kiss-0.036
ment-0.035
less-0.031
 bless-0.031
 forgiveness-0.030
Token bed
Token ID3996
Feature activation-3.74e+00

Pos logit contributions
ment+0.008
less+0.007
 forgiveness+0.007
irk+0.007
iness+0.007
Neg logit contributions
 One-0.006
 bank-0.006
 banks-0.006
pole-0.006
 floppy-0.005
Token take
Token ID1011
Feature activation-1.31e+00

Pos logit contributions
pole+0.020
 none+0.019
chard+0.019
 One+0.018
lves+0.018
Neg logit contributions
ment-0.011
 kiss-0.011
less-0.010
 prayer-0.009
 forgiveness-0.009
Token them
Token ID606
Feature activation+2.84e-01

Pos logit contributions
 kiss+0.056
ment+0.053
 bless+0.048
less+0.048
 band+0.047
Neg logit contributions
pole-0.067
lves-0.064
chard-0.063
 none-0.062
opes-0.060
Token to
Token ID284
Feature activation-8.36e-02

Pos logit contributions
pole+0.015
 none+0.015
lves+0.015
chard+0.015
 One+0.014
Neg logit contributions
 kiss-0.011
ment-0.011
 bless-0.009
 prayer-0.009
 forgiveness-0.009
Token the
Token ID262
Feature activation+1.16e+00

Pos logit contributions
 kiss+0.003
ment+0.003
less+0.002
 bless+0.002
 forgiveness+0.002
Neg logit contributions
pole-0.005
lves-0.005
 none-0.005
chard-0.005
 One-0.005
Token all
Token ID477
Feature activation+1.32e+00

Pos logit contributions
pole+0.055
 pads+0.053
lves+0.053
opes+0.051
nam+0.051
Neg logit contributions
 kiss-0.054
 fairy-0.046
guard-0.046
 band-0.046
 bless-0.046
Tokenigator
Token ID23823
Feature activation+6.14e+00

Pos logit contributions
pole+0.064
lves+0.062
 none+0.061
chard+0.061
 One+0.059
Neg logit contributions
 kiss-0.059
ment-0.056
less-0.051
 bless-0.051
 forgiveness-0.050
Token pond
Token ID16723
Feature activation+2.89e+00

Pos logit contributions
pole+0.363
lves+0.353
 none+0.347
chard+0.346
 One+0.337
Neg logit contributions
 kiss-0.208
ment-0.195
less-0.172
 bless-0.170
 forgiveness-0.167
Token.
Token ID13
Feature activation+7.55e-02

Pos logit contributions
pole+0.164
 none+0.158
chard+0.158
lves+0.155
 One+0.152
Neg logit contributions
 kiss-0.106
ment-0.099
 bless-0.090
less-0.089
 forgiveness-0.088
Token
Token ID198
Feature activation-3.45e-01

Pos logit contributions
lves+0.004
pole+0.004
opes+0.004
 pads+0.004
uries+0.004
Neg logit contributions
 kiss-0.003
ment-0.002
 prayer-0.002
 voice-0.002
 nurse-0.002
Token
Token ID198
Feature activation-6.87e-01

Pos logit contributions
 kiss+0.013
ment+0.011
 band+0.011
less+0.010
 bless+0.010
Neg logit contributions
pole-0.019
lves-0.019
 none-0.019
nam-0.019
chard-0.019
TokenMom
Token ID29252
Feature activation-3.77e+00

Pos logit contributions
 kiss+0.027
ment+0.024
less+0.022
 bless+0.022
 band+0.022
Neg logit contributions
pole-0.038
lves-0.037
 none-0.036
chard-0.036
opes-0.035
Token.
Token ID13
Feature activation+9.94e-03

Pos logit contributions
 none+0.076
pole+0.074
 pads+0.071
 One+0.070
chard+0.070
Neg logit contributions
ment-0.072
 kiss-0.070
 bless-0.064
 forgiveness-0.062
less-0.062
Token She
Token ID1375
Feature activation+5.87e-01

Pos logit contributions
pole+0.001
lves+0.000
chard+0.000
edy+0.000
 none+0.000
Neg logit contributions
 kiss-0.000
ment-0.000
 prayer-0.000
 bless-0.000
 forgiveness-0.000
Token did
Token ID750
Feature activation-4.16e-01

Pos logit contributions
pole+0.026
lves+0.025
chard+0.025
 none+0.024
nam+0.023
Neg logit contributions
 kiss-0.029
ment-0.027
 bless-0.025
 prayer-0.025
 band-0.025
Token not
Token ID407
Feature activation-1.31e+00

Pos logit contributions
ment+0.025
 kiss+0.025
less+0.023
 bless+0.023
guard+0.022
Neg logit contributions
 none-0.013
pole-0.013
 One-0.012
chard-0.012
lves-0.012
Token like
Token ID588
Feature activation+6.74e-01

Pos logit contributions
ment+0.073
less+0.065
 accidents+0.063
 forgiveness+0.063
 kiss+0.061
Neg logit contributions
pole-0.050
 One-0.049
uries-0.047
 none-0.046
chard-0.045
Token sheep
Token ID15900
Feature activation+6.08e+00

Pos logit contributions
 none+0.032
lves+0.031
pole+0.031
chard+0.031
 One+0.031
Neg logit contributions
 kiss-0.029
ment-0.028
less-0.026
 bless-0.025
 forgiveness-0.024
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
pole+0.295
 none+0.290
 pads+0.282
lves+0.281
chard+0.279
Neg logit contributions
ment-0.260
 kiss-0.256
 bless-0.226
less-0.225
 forgiveness-0.225
Token She
Token ID1375
Feature activation+5.99e-01

Pos logit contributions
pole+0.005
lves+0.005
chard+0.005
 none+0.004
uries+0.004
Neg logit contributions
 kiss-0.005
ment-0.004
 prayer-0.004
 bless-0.004
less-0.004
Token liked
Token ID8288
Feature activation+1.40e+00

Pos logit contributions
pole+0.027
lves+0.026
chard+0.025
 none+0.025
nam+0.024
Neg logit contributions
 kiss-0.030
ment-0.027
 bless-0.025
 prayer-0.025
 band-0.025
Token pizza
Token ID14256
Feature activation+2.94e+00

Pos logit contributions
 none+0.067
pole+0.065
chard+0.065
 One+0.065
lves+0.064
Neg logit contributions
 kiss-0.059
ment-0.058
less-0.054
 bless-0.051
 forgiveness-0.050
Token and
Token ID290
Feature activation+6.74e-01

Pos logit contributions
 none+0.139
pole+0.135
 pads+0.128
 One+0.125
chard+0.123
Neg logit contributions
ment-0.129
 kiss-0.127
 bless-0.118
less-0.118
arl-0.117
Token she
Token ID673
Feature activation+1.07e+00

Pos logit contributions
 kiss+0.014
 bless+0.012
ment+0.012
guard+0.012
 ray+0.012
Neg logit contributions
 none-0.014
 One-0.013
pole-0.013
lves-0.013
chard-0.013
Token had
Token ID550
Feature activation+3.31e-02

Pos logit contributions
pole+0.051
lves+0.048
chard+0.046
 favorites+0.046
 One+0.046
Neg logit contributions
 kiss-0.050
ment-0.047
less-0.044
 bless-0.044
 forgiveness-0.043
Token listened
Token ID16399
Feature activation-4.62e-01

Pos logit contributions
pole+0.002
lves+0.002
chard+0.001
opes+0.001
 favourites+0.001
Neg logit contributions
 kiss-0.002
ment-0.001
 forgiveness-0.001
 bless-0.001
less-0.001
Token to
Token ID284
Feature activation-4.13e-01

Pos logit contributions
 kiss+0.018
ment+0.017
 bless+0.016
 forgiveness+0.015
 prayer+0.015
Neg logit contributions
pole-0.024
 none-0.024
 One-0.024
chard-0.023
lves-0.023
Token Dog
Token ID8532
Feature activation+2.41e+00

Pos logit contributions
 kiss+0.018
ment+0.017
 bless+0.015
less+0.015
 forgiveness+0.015
Neg logit contributions
pole-0.021
lves-0.020
chard-0.020
 none-0.020
 favourites-0.019
Tokengy
Token ID1360
Feature activation+6.17e+00

Pos logit contributions
pole+0.052
lves+0.050
chard+0.048
 none+0.048
 favourites+0.044
Neg logit contributions
 kiss-0.172
ment-0.166
less-0.158
 bless-0.157
 forgiveness-0.155
Token.
Token ID13
Feature activation-4.85e-01

Pos logit contributions
pole+0.331
 none+0.320
lves+0.314
 One+0.313
chard+0.312
Neg logit contributions
 kiss-0.234
ment-0.230
less-0.206
 bless-0.201
 forgiveness-0.197
Token Now
Token ID2735
Feature activation-2.71e+00

Pos logit contributions
ment+0.023
 kiss+0.023
 prayer+0.022
 band+0.020
 bless+0.020
Neg logit contributions
chard-0.022
pole-0.022
nam-0.021
 favourites-0.021
lves-0.021
Token,
Token ID11
Feature activation-1.62e-01

Pos logit contributions
 kiss+0.109
ment+0.104
less+0.094
 bless+0.093
 forgiveness+0.091
Neg logit contributions
pole-0.143
lves-0.139
chard-0.137
 none-0.136
 favourites-0.132
Token Kitty
Token ID21168
Feature activation+1.01e+00

Pos logit contributions
 kiss+0.008
ment+0.008
less+0.008
 forgiveness+0.007
 bless+0.007
Neg logit contributions
pole-0.007
 none-0.007
lves-0.006
 One-0.006
chard-0.006
Token learned
Token ID4499
Feature activation-5.20e-01

Pos logit contributions
pole+0.046
lves+0.044
chard+0.043
 none+0.043
nam+0.041
Neg logit contributions
 kiss-0.049
ment-0.046
 bless-0.043
less-0.043
 forgiveness-0.042
Token to
Token ID284
Feature activation+4.19e-02

Pos logit contributions
pole+0.023
lves+0.023
chard+0.022
opes+0.021
ramids+0.021
Neg logit contributions
 kiss-0.014
ment-0.013
less-0.012
 forgiveness-0.012
 band-0.012
Token promise
Token ID6991
Feature activation-1.31e+00

Pos logit contributions
pole+0.002
 none+0.002
 One+0.002
uries+0.002
chard+0.002
Neg logit contributions
ment-0.002
less-0.002
 kiss-0.001
 accidents-0.001
guard-0.001
Token to
Token ID284
Feature activation+1.11e+00

Pos logit contributions
 kiss+0.055
ment+0.053
less+0.048
 bless+0.048
 prayer+0.046
Neg logit contributions
 none-0.065
pole-0.065
chard-0.062
lves-0.062
 One-0.062
Token always
Token ID1464
Feature activation+1.02e+00

Pos logit contributions
pole+0.056
 none+0.055
 One+0.053
chard+0.051
uries+0.051
Neg logit contributions
ment-0.048
less-0.043
 kiss-0.042
irk-0.039
 accidents-0.039
Token be
Token ID307
Feature activation-1.76e+00

Pos logit contributions
pole+0.051
 none+0.050
 One+0.049
uries+0.048
chard+0.048
Neg logit contributions
ment-0.042
less-0.039
 kiss-0.036
 accidents-0.036
guard-0.035
Token best
Token ID1266
Feature activation+6.07e+00

Pos logit contributions
 kiss+0.063
ment+0.059
less+0.053
 bless+0.052
 forgiveness+0.052
Neg logit contributions
pole-0.101
lves-0.099
chard-0.095
opes-0.095
 none-0.095
Token friends
Token ID2460
Feature activation+2.57e+00

Pos logit contributions
pole+0.270
 none+0.263
lves+0.258
 favourites+0.254
 favorites+0.252
Neg logit contributions
 kiss-0.285
ment-0.272
less-0.250
 bless-0.246
 forgiveness-0.245
Token.
Token ID13
Feature activation-1.16e-01

Pos logit contributions
pole+0.145
lves+0.140
 none+0.140
chard+0.139
 One+0.135
Neg logit contributions
 kiss-0.094
ment-0.088
less-0.078
 bless-0.078
 forgiveness-0.076
Token They
Token ID1119
Feature activation+6.39e-01

Pos logit contributions
 kiss+0.005
ment+0.005
 of+0.004
less+0.004
 forgiveness+0.004
Neg logit contributions
chard-0.006
nam-0.006
pole-0.006
opes-0.006
lves-0.006
Token made
Token ID925
Feature activation-2.12e+00

Pos logit contributions
pole+0.027
lves+0.026
chard+0.025
opes+0.025
uries+0.024
Neg logit contributions
 kiss-0.034
ment-0.030
 bless-0.029
 band-0.028
 prayer-0.028
Token their
Token ID511
Feature activation+7.59e-01

Pos logit contributions
 kiss+0.092
ment+0.088
 forgiveness+0.079
 band+0.079
less+0.079
Neg logit contributions
pole-0.107
chard-0.105
lves-0.102
 none-0.099
nam-0.097
Token the
Token ID262
Feature activation+2.15e-01

Pos logit contributions
pole+0.101
lves+0.097
 none+0.097
chard+0.096
 One+0.093
Neg logit contributions
 kiss-0.081
ment-0.078
less-0.070
 bless-0.069
 forgiveness-0.068
Token tree
Token ID5509
Feature activation+1.65e+00

Pos logit contributions
pole+0.011
lves+0.011
 none+0.010
chard+0.010
uries+0.010
Neg logit contributions
 kiss-0.009
ment-0.008
 fairy-0.008
 band-0.008
 bless-0.008
Token with
Token ID351
Feature activation+1.77e+00

Pos logit contributions
pole+0.086
lves+0.086
 none+0.083
chard+0.083
 favourites+0.081
Neg logit contributions
 kiss-0.066
ment-0.062
less-0.057
 bless-0.055
 prayer-0.054
Token regular
Token ID3218
Feature activation+1.07e+00

Pos logit contributions
pole+0.093
lves+0.090
chard+0.087
 none+0.086
 One+0.084
Neg logit contributions
 kiss-0.074
ment-0.069
 bless-0.063
less-0.063
 forgiveness-0.062
Token or
Token ID393
Feature activation+1.44e+00

Pos logit contributions
pole+0.049
 none+0.046
lves+0.046
 One+0.046
chard+0.045
Neg logit contributions
 kiss-0.049
ment-0.048
less-0.044
 bless-0.043
 forgiveness-0.043
Tokennam
Token ID7402
Feature activation+9.38e+00

Pos logit contributions
pole+0.043
lves+0.040
 none+0.038
chard+0.038
 One+0.037
Neg logit contributions
 kiss-0.091
ment-0.088
less-0.083
 bless-0.082
 forgiveness-0.082
Tokenents
Token ID658
Feature activation+3.43e+00

Pos logit contributions
lves+0.280
 none+0.280
chard+0.274
pole+0.273
opes+0.263
Neg logit contributions
ment-0.551
 kiss-0.546
less-0.530
ful-0.517
 of-0.506
Token!"
Token ID2474
Feature activation+2.29e+00

Pos logit contributions
pole+0.157
 none+0.147
chard+0.142
lves+0.141
 pads+0.138
Neg logit contributions
 kiss-0.164
ment-0.155
 forgiveness-0.147
 bless-0.144
 prayer-0.143
Token<|endoftext|>
Token ID50256
Feature activation-2.76e+00

Pos logit contributions
pole+0.065
lves+0.060
 none+0.059
chard+0.058
 One+0.055
Neg logit contributions
 kiss-0.149
ment-0.144
less-0.136
 bless-0.135
 forgiveness-0.134
TokenOnce
Token ID7454
Feature activation+1.20e+00

Pos logit contributions
 kiss+0.123
ment+0.118
less+0.107
 bless+0.106
 forgiveness+0.105
Neg logit contributions
pole-0.134
lves-0.130
 none-0.127
chard-0.127
nam-0.121
Token upon
Token ID2402
Feature activation+7.32e-01

Pos logit contributions
pole+0.067
lves+0.066
chard+0.064
 none+0.064
uries+0.063
Neg logit contributions
 kiss-0.044
ment-0.042
less-0.039
 bless-0.036
 forgiveness-0.036
Token<|endoftext|>
Token ID50256
Feature activation-3.04e+00

Pos logit contributions
 kiss+0.021
ment+0.020
 forgiveness+0.019
less+0.018
 prayer+0.017
Neg logit contributions
pole-0.028
lves-0.027
chard-0.026
 none-0.025
opes-0.025
TokenOnce
Token ID7454
Feature activation+1.00e+00

Pos logit contributions
 kiss+0.144
ment+0.138
less+0.126
 bless+0.125
 forgiveness+0.124
Neg logit contributions
pole-0.138
lves-0.133
 none-0.131
chard-0.131
 One-0.128
Token upon
Token ID2402
Feature activation+4.98e-01

Pos logit contributions
pole+0.056
lves+0.055
chard+0.054
uries+0.053
 none+0.053
Neg logit contributions
 kiss-0.037
ment-0.035
less-0.032
 forgiveness-0.030
 bless-0.030
Token a
Token ID257
Feature activation+1.89e+00

Pos logit contributions
pole+0.023
 none+0.022
chard+0.022
lves+0.022
 One+0.022
Neg logit contributions
 kiss-0.023
ment-0.022
less-0.020
 bless-0.020
 prayer-0.019
Token time
Token ID640
Feature activation-2.05e+00

Pos logit contributions
pole+0.111
lves+0.108
chard+0.107
 none+0.106
nam+0.103
Neg logit contributions
 kiss-0.066
ment-0.060
less-0.055
 bless-0.053
 prayer-0.053
Token there
Token ID612
Feature activation+3.24e+00

Pos logit contributions
 kiss+0.070
ment+0.066
less+0.059
 bless+0.057
 forgiveness+0.057
Neg logit contributions
pole-0.121
lves-0.117
chard-0.115
 none-0.115
 One-0.111
Token was
Token ID373
Feature activation+9.78e-01

Pos logit contributions
pole+0.173
lves+0.167
 none+0.165
chard+0.164
 One+0.160
Neg logit contributions
 kiss-0.129
ment-0.123
less-0.110
 bless-0.109
 forgiveness-0.107
Token a
Token ID257
Feature activation+3.76e-01

Pos logit contributions
pole+0.057
lves+0.055
chard+0.053
uries+0.053
 none+0.052
Neg logit contributions
 kiss-0.035
ment-0.032
 band-0.029
less-0.029
 forgiveness-0.029
Token little
Token ID1310
Feature activation-9.32e-01

Pos logit contributions
lves+0.018
chard+0.018
pole+0.018
 One+0.018
 favourites+0.017
Neg logit contributions
ment-0.017
 kiss-0.015
less-0.014
 forgiveness-0.014
iness-0.014
Token boy
Token ID2933
Feature activation+1.13e+00

Pos logit contributions
ment+0.037
 kiss+0.031
less+0.030
 forgiveness+0.030
 fade+0.029
Neg logit contributions
lves-0.050
chard-0.050
pole-0.048
nam-0.047
 One-0.047
Token called
Token ID1444
Feature activation+2.02e+00

Pos logit contributions
pole+0.027
lves+0.025
chard+0.024
 One+0.024
 none+0.024
Neg logit contributions
 kiss-0.078
ment-0.077
less-0.072
 prayer-0.071
 bless-0.071
Token't
Token ID470
Feature activation-8.24e-01

Pos logit contributions
pole+0.014
lves+0.013
chard+0.013
 none+0.013
nam+0.013
Neg logit contributions
 kiss-0.016
ment-0.015
less-0.015
 bless-0.014
 forgiveness-0.014
Token expected
Token ID2938
Feature activation+1.77e-01

Pos logit contributions
 kiss+0.043
ment+0.043
less+0.040
 bless+0.039
arl+0.039
Neg logit contributions
pole-0.031
 none-0.030
lves-0.030
chard-0.029
 pads-0.029
Token Molly
Token ID30236
Feature activation+1.58e+00

Pos logit contributions
 none+0.008
pole+0.008
 One+0.008
chard+0.008
lves+0.008
Neg logit contributions
ment-0.008
 kiss-0.008
less-0.007
 bless-0.007
 prayer-0.007
Token to
Token ID284
Feature activation-6.00e-01

Pos logit contributions
 none+0.078
pole+0.077
chard+0.074
 pads+0.074
 One+0.073
Neg logit contributions
 kiss-0.066
ment-0.065
 bless-0.059
 ray-0.056
 forgiveness-0.056
Token be
Token ID307
Feature activation-2.86e+00

Pos logit contributions
ment+0.026
less+0.023
 kiss+0.020
 prayer+0.020
irk+0.019
Neg logit contributions
 One-0.031
pole-0.030
 none-0.029
uries-0.028
 bank-0.028
Token so
Token ID523
Feature activation+4.28e+00

Pos logit contributions
 kiss+0.131
ment+0.125
less+0.115
 bless+0.113
 forgiveness+0.112
Neg logit contributions
pole-0.136
lves-0.131
chard-0.128
 none-0.128
 One-0.125
Token calm
Token ID9480
Feature activation-1.65e-01

Pos logit contributions
pole+0.173
chard+0.172
lves+0.172
 none+0.170
 One+0.163
Neg logit contributions
 kiss-0.220
ment-0.208
 bless-0.197
 forgiveness-0.192
less-0.191
Token.
Token ID13
Feature activation-4.08e-01

Pos logit contributions
 kiss+0.007
 bless+0.007
ment+0.007
 prayer+0.006
 forgiveness+0.006
Neg logit contributions
pole-0.008
 none-0.008
 One-0.008
chard-0.007
lves-0.007
Token
Token ID198
Feature activation-7.15e-01

Pos logit contributions
 kiss+0.017
ment+0.017
 prayer+0.015
less+0.015
 forgiveness+0.014
Neg logit contributions
pole-0.021
lves-0.021
riages-0.020
nam-0.020
opes-0.020
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
 kiss+0.031
ment+0.030
less+0.027
 bless+0.026
 forgiveness+0.026
Neg logit contributions
pole-0.035
lves-0.034
 none-0.034
chard-0.034
nam-0.032
TokenM
Token ID44
Feature activation-1.17e+00

Pos logit contributions
 kiss+0.041
ment+0.039
 bless+0.035
less+0.035
 prayer+0.035
Neg logit contributions
pole-0.056
lves-0.054
 none-0.053
chard-0.053
 One-0.053
Token flying
Token ID7348
Feature activation+7.51e-01

Pos logit contributions
pole+0.076
 none+0.072
chard+0.069
lves+0.069
 One+0.067
Neg logit contributions
 kiss-0.068
ment-0.066
arl-0.063
less-0.061
 forgiveness-0.060
Token like
Token ID588
Feature activation-4.62e-01

Pos logit contributions
pole+0.037
 none+0.035
chard+0.034
lves+0.034
 One+0.033
Neg logit contributions
 kiss-0.034
ment-0.032
 bless-0.031
 forgiveness-0.030
 prayer-0.029
Token a
Token ID257
Feature activation+1.09e-01

Pos logit contributions
 kiss+0.021
ment+0.020
less+0.018
 bless+0.018
 prayer+0.018
Neg logit contributions
pole-0.022
 none-0.022
chard-0.021
lves-0.021
 One-0.020
Token dark
Token ID3223
Feature activation-1.82e+00

Pos logit contributions
pole+0.005
lves+0.005
chard+0.005
 none+0.005
 One+0.005
Neg logit contributions
ment-0.005
 kiss-0.005
 forgiveness-0.004
 bless-0.004
less-0.004
Token shadow
Token ID9082
Feature activation-3.75e-01

Pos logit contributions
 kiss+0.082
ment+0.082
 forgiveness+0.077
 bless+0.076
less+0.074
Neg logit contributions
pole-0.087
 One-0.084
lves-0.080
chard-0.078
 none-0.078
Token in
Token ID287
Feature activation+2.08e+00

Pos logit contributions
ment+0.015
 kiss+0.015
 forgiveness+0.014
 bless+0.013
less+0.013
Neg logit contributions
pole-0.021
 none-0.019
 One-0.018
 pads-0.018
chard-0.018
Token the
Token ID262
Feature activation+7.11e-01

Pos logit contributions
pole+0.108
 none+0.107
chard+0.105
 One+0.105
lves+0.103
Neg logit contributions
 kiss-0.084
ment-0.081
less-0.075
 bless-0.072
 forgiveness-0.071
Token gloomy
Token ID46400
Feature activation-1.80e+00

Pos logit contributions
pole+0.033
lves+0.032
chard+0.031
 One+0.031
 none+0.031
Neg logit contributions
 kiss-0.033
ment-0.033
less-0.030
 forgiveness-0.030
 bless-0.029
Token forest
Token ID8222
Feature activation+1.06e+00

Pos logit contributions
 kiss+0.094
ment+0.090
less+0.085
 bless+0.084
 forgiveness+0.083
Neg logit contributions
pole-0.074
lves-0.070
chard-0.069
 none-0.068
 One-0.068
Token.
Token ID13
Feature activation-6.18e-01

Pos logit contributions
pole+0.057
 none+0.054
chard+0.053
lves+0.053
 One+0.052
Neg logit contributions
 kiss-0.043
ment-0.040
 bless-0.037
 forgiveness-0.037
less-0.036
Token<|endoftext|>
Token ID50256
Feature activation-2.78e+00

Pos logit contributions
ment+0.028
 kiss+0.028
 prayer+0.024
 bless+0.023
 of+0.022
Neg logit contributions
pole-0.030
lves-0.029
opes-0.029
edy-0.029
chard-0.029
Token instead
Token ID2427
Feature activation-1.64e+00

Pos logit contributions
 kiss+0.156
ment+0.146
 forgiveness+0.130
 bless+0.130
arl+0.128
Neg logit contributions
pole-0.207
 none-0.192
chard-0.190
lves-0.187
 bank-0.176
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
 kiss+0.059
ment+0.054
 bless+0.051
 forgiveness+0.049
 band+0.048
Neg logit contributions
pole-0.095
 none-0.091
 One-0.088
chard-0.085
 pads-0.084
Token<|endoftext|>
Token ID50256
Feature activation-3.01e+00

Pos logit contributions
 kiss+0.014
ment+0.014
 prayer+0.012
 forgiveness+0.012
 bless+0.011
Neg logit contributions
pole-0.020
chard-0.020
nam-0.020
lves-0.020
opes-0.019
TokenOnce
Token ID7454
Feature activation+9.60e-01

Pos logit contributions
 kiss+0.136
ment+0.130
less+0.119
 bless+0.117
 forgiveness+0.115
Neg logit contributions
pole-0.144
lves-0.139
 none-0.136
chard-0.136
 favourites-0.130
Token upon
Token ID2402
Feature activation+4.24e-01

Pos logit contributions
pole+0.055
lves+0.055
uries+0.053
chard+0.053
opes+0.053
Neg logit contributions
 kiss-0.033
ment-0.031
less-0.029
 prayer-0.027
 forgiveness-0.026
Token a
Token ID257
Feature activation+1.48e+00

Pos logit contributions
pole+0.021
lves+0.020
 none+0.020
chard+0.020
 One+0.019
Neg logit contributions
 kiss-0.019
ment-0.018
less-0.016
 bless-0.016
 forgiveness-0.016
Token time
Token ID640
Feature activation-2.40e+00

Pos logit contributions
pole+0.089
lves+0.087
chard+0.087
 none+0.086
nam+0.084
Neg logit contributions
 kiss-0.050
ment-0.044
less-0.041
 bless-0.039
 prayer-0.039
Token there
Token ID612
Feature activation+3.02e+00

Pos logit contributions
 kiss+0.076
ment+0.072
less+0.065
 forgiveness+0.061
 bless+0.061
Neg logit contributions
pole-0.146
lves-0.143
chard-0.140
 none-0.139
 pads-0.136
Token was
Token ID373
Feature activation+7.53e-01

Pos logit contributions
pole+0.154
lves+0.148
 none+0.148
chard+0.146
 One+0.145
Neg logit contributions
 kiss-0.126
ment-0.120
less-0.108
 bless-0.108
 forgiveness-0.106
Token a
Token ID257
Feature activation-3.90e-03

Pos logit contributions
pole+0.047
lves+0.046
uries+0.045
chard+0.044
ramids+0.044
Neg logit contributions
 kiss-0.024
ment-0.021
 band-0.019
less-0.019
ful-0.019
Token little
Token ID1310
Feature activation-1.20e+00

Pos logit contributions
ment+0.000
 kiss+0.000
less+0.000
 forgiveness+0.000
iness+0.000
Neg logit contributions
lves-0.000
pole-0.000
chard-0.000
 One-0.000
nam-0.000
Token<|endoftext|>
Token ID50256
Feature activation-2.91e+00

Pos logit contributions
 kiss+0.014
ment+0.014
 prayer+0.013
 bless+0.012
 forgiveness+0.012
Neg logit contributions
pole-0.016
lves-0.016
chard-0.015
opes-0.015
 none-0.015
TokenOnce
Token ID7454
Feature activation+1.06e+00

Pos logit contributions
 kiss+0.136
ment+0.130
less+0.119
 bless+0.118
 forgiveness+0.117
Neg logit contributions
pole-0.134
lves-0.129
 none-0.127
chard-0.127
 One-0.123
Token upon
Token ID2402
Feature activation+4.64e-01

Pos logit contributions
pole+0.059
lves+0.058
chard+0.056
 none+0.056
uries+0.055
Neg logit contributions
 kiss-0.039
ment-0.037
less-0.034
 bless-0.032
 forgiveness-0.032
Token a
Token ID257
Feature activation+1.58e+00

Pos logit contributions
pole+0.022
 none+0.021
lves+0.021
chard+0.021
 One+0.020
Neg logit contributions
 kiss-0.021
ment-0.020
less-0.019
 bless-0.018
 prayer-0.018
Token time
Token ID640
Feature activation-2.40e+00

Pos logit contributions
pole+0.091
lves+0.088
chard+0.087
 none+0.087
nam+0.084
Neg logit contributions
 kiss-0.057
ment-0.052
less-0.048
 bless-0.047
 prayer-0.046
Token there
Token ID612
Feature activation+2.90e+00

Pos logit contributions
 kiss+0.077
ment+0.072
less+0.065
 bless+0.062
 forgiveness+0.061
Neg logit contributions
pole-0.145
lves-0.142
chard-0.139
 none-0.138
 favourites-0.134
Token was
Token ID373
Feature activation+8.12e-01

Pos logit contributions
pole+0.141
 none+0.137
lves+0.135
 One+0.135
chard+0.132
Neg logit contributions
 kiss-0.128
ment-0.123
 bless-0.111
less-0.111
 forgiveness-0.109
Token a
Token ID257
Feature activation-1.14e-01

Pos logit contributions
pole+0.047
lves+0.045
chard+0.044
 none+0.044
uries+0.044
Neg logit contributions
 kiss-0.029
ment-0.027
 band-0.024
less-0.024
 forgiveness-0.023
Token loyal
Token ID9112
Feature activation+1.89e-02

Pos logit contributions
ment+0.005
 kiss+0.004
less+0.004
 forgiveness+0.004
 bless+0.004
Neg logit contributions
lves-0.006
pole-0.006
chard-0.006
 One-0.005
 favourites-0.005
Token friend
Token ID1545
Feature activation+7.08e-01

Pos logit contributions
pole+0.001
 One+0.001
lves+0.001
chard+0.001
 favorites+0.001
Neg logit contributions
ment-0.001
 kiss-0.001
 forgiveness-0.001
less-0.001
 fade-0.001
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
pole+0.022
lves+0.022
chard+0.021
 none+0.021
 favourites+0.020
Neg logit contributions
 kiss-0.044
ment-0.042
 bless-0.040
less-0.039
 forgiveness-0.039
Token Tim
Token ID5045
Feature activation+5.13e-03

Pos logit contributions
 kiss+0.014
ment+0.013
 prayer+0.012
 voice+0.012
 of+0.012
Neg logit contributions
pole-0.018
lves-0.018
 pads-0.017
uries-0.017
chard-0.017
Token thought
Token ID1807
Feature activation-1.78e+00

Pos logit contributions
pole+0.000
chard+0.000
uries+0.000
 none+0.000
lves+0.000
Neg logit contributions
 kiss-0.000
 band-0.000
 fairy-0.000
 bless-0.000
 sigh-0.000
Token of
Token ID286
Feature activation-1.13e+00

Pos logit contributions
ment+0.093
 kiss+0.090
 bless+0.086
pour+0.083
less+0.082
Neg logit contributions
 none-0.070
 One-0.067
pole-0.063
 Jerry-0.061
 Ellie-0.059
Token an
Token ID281
Feature activation+3.80e-01

Pos logit contributions
 kiss+0.050
ment+0.047
less+0.043
 bless+0.043
 forgiveness+0.042
Neg logit contributions
pole-0.056
lves-0.053
 none-0.053
chard-0.053
 One-0.051
Token idea
Token ID2126
Feature activation-1.60e-01

Pos logit contributions
chard+0.022
lves+0.022
pole+0.022
 none+0.021
ramids+0.021
Neg logit contributions
 kiss-0.013
ment-0.012
 forgiveness-0.011
 prayer-0.011
 pain-0.011
Token.
Token ID13
Feature activation-5.33e-01

Pos logit contributions
 kiss+0.007
ment+0.007
 bless+0.006
 prayer+0.006
less+0.006
Neg logit contributions
pole-0.008
 One-0.008
 none-0.007
lves-0.007
 pads-0.007
Token He
Token ID679
Feature activation+5.21e-01

Pos logit contributions
 kiss+0.026
ment+0.025
 prayer+0.022
less+0.022
 band+0.022
Neg logit contributions
pole-0.024
lves-0.024
 none-0.023
chard-0.023
uries-0.023
Token went
Token ID1816
Feature activation-1.67e+00

Pos logit contributions
chard+0.026
 none+0.026
nam+0.026
pole+0.026
lves+0.026
Neg logit contributions
 kiss-0.023
 band-0.021
 fairy-0.019
 prayer-0.018
 bless-0.018
Token to
Token ID284
Feature activation-1.87e+00

Pos logit contributions
ment+0.072
 kiss+0.071
 bless+0.064
 forgiveness+0.063
 prayer+0.063
Neg logit contributions
pole-0.082
chard-0.080
lves-0.079
 none-0.078
 One-0.077
Token the
Token ID262
Feature activation+1.46e-01

Pos logit contributions
ment+0.078
 kiss+0.072
less+0.070
 prayer+0.065
 ray+0.064
Neg logit contributions
pole-0.095
chard-0.093
 One-0.093
lves-0.092
 none-0.091
Token girl
Token ID2576
Feature activation+1.29e-01

Pos logit contributions
pole+0.006
chard+0.006
lves+0.006
 none+0.006
 One+0.006
Neg logit contributions
ment-0.007
 kiss-0.007
 bless-0.006
less-0.006
 forgiveness-0.006
Token didn
Token ID1422
Feature activation-1.40e+00

Pos logit contributions
 kiss+0.002
ment+0.002
less+0.002
 forgiveness+0.002
 band+0.002
Neg logit contributions
pole-0.002
lves-0.001
 favorites-0.001
 favourites-0.001
uries-0.001
Token't
Token ID470
Feature activation+1.81e-01

Pos logit contributions
 kiss+0.072
ment+0.068
less+0.063
 bless+0.063
 forgiveness+0.062
Neg logit contributions
pole-0.060
lves-0.057
chard-0.056
 none-0.055
 favourites-0.054
Token know
Token ID760
Feature activation-1.00e+00

Pos logit contributions
pole+0.009
lves+0.008
 One+0.008
 none+0.008
chard+0.008
Neg logit contributions
 kiss-0.008
ment-0.008
less-0.008
 forgiveness-0.007
 bless-0.007
Token what
Token ID644
Feature activation+8.45e-01

Pos logit contributions
 kiss+0.043
ment+0.040
less+0.037
 bless+0.037
 prayer+0.036
Neg logit contributions
pole-0.049
 none-0.049
chard-0.048
lves-0.048
nam-0.047
Token to
Token ID284
Feature activation+1.10e+00

Pos logit contributions
pole+0.046
 none+0.046
chard+0.045
lves+0.045
 One+0.045
Neg logit contributions
 kiss-0.032
ment-0.030
less-0.027
 bless-0.027
 prayer-0.025
Token do
Token ID466
Feature activation-3.03e-01

Pos logit contributions
pole+0.069
 One+0.067
 none+0.066
lves+0.065
chard+0.065
Neg logit contributions
ment-0.035
 kiss-0.031
less-0.029
 forgiveness-0.026
 bless-0.026
Token.
Token ID13
Feature activation+5.52e-01

Pos logit contributions
 kiss+0.013
ment+0.012
 bless+0.012
 prayer+0.011
less+0.011
Neg logit contributions
 none-0.015
pole-0.015
 One-0.015
chard-0.014
lves-0.014
Token
Token ID198
Feature activation-2.55e-01

Pos logit contributions
pole+0.032
lves+0.029
opes+0.029
riages+0.029
uries+0.029
Neg logit contributions
 kiss-0.020
ment-0.018
 next-0.017
 voice-0.017
 moment-0.017
Token
Token ID198
Feature activation-6.64e-01

Pos logit contributions
 kiss+0.010
ment+0.009
less+0.008
 forgiveness+0.008
 band+0.008
Neg logit contributions
pole-0.014
lves-0.014
chard-0.014
 none-0.014
nam-0.013
TokenJust
Token ID5703
Feature activation-1.27e+00

Pos logit contributions
 kiss+0.030
ment+0.028
less+0.026
 band+0.025
 bless+0.025
Neg logit contributions
pole-0.032
 none-0.031
lves-0.031
chard-0.031
 favorites-0.029
Token then
Token ID788
Feature activation-2.02e+00

Pos logit contributions
 kiss+0.072
ment+0.069
less+0.067
 forgiveness+0.066
 bless+0.065
Neg logit contributions
pole-0.046
chard-0.045
 none-0.045
 One-0.043
lves-0.042
Token wrapped
Token ID12908
Feature activation+3.82e-01

Pos logit contributions
ment+0.201
less+0.198
arl+0.197
 kiss+0.196
 forgiveness+0.191
Neg logit contributions
pole-0.129
 none-0.119
chard-0.114
 One-0.114
lves-0.111
Token the
Token ID262
Feature activation-1.50e+00

Pos logit contributions
 none+0.019
pole+0.019
chard+0.019
lves+0.018
nam+0.018
Neg logit contributions
 kiss-0.016
ment-0.015
 bless-0.014
 prayer-0.014
less-0.014
Token blanket
Token ID18447
Feature activation-1.02e+00

Pos logit contributions
ment+0.065
 kiss+0.058
 bless+0.054
less+0.053
ful+0.052
Neg logit contributions
 none-0.075
pole-0.074
chard-0.072
lves-0.071
nam-0.071
Token around
Token ID1088
Feature activation+2.04e-01

Pos logit contributions
 kiss+0.048
ment+0.047
 bless+0.046
 forgiveness+0.044
 prayer+0.042
Neg logit contributions
pole-0.047
 none-0.046
chard-0.044
 One-0.042
nam-0.041
Token the
Token ID262
Feature activation-6.11e-01

Pos logit contributions
 none+0.009
 One+0.008
chard+0.008
nam+0.008
pole+0.008
Neg logit contributions
 kiss-0.010
ment-0.009
arl-0.009
guard-0.009
 bless-0.009
Token baby
Token ID5156
Feature activation+2.14e-01

Pos logit contributions
ment+0.026
 kiss+0.026
less+0.023
 bless+0.023
 forgiveness+0.022
Neg logit contributions
pole-0.030
lves-0.029
chard-0.029
 none-0.029
nam-0.028
Token so
Token ID523
Feature activation+2.96e+00

Pos logit contributions
pole+0.011
chard+0.010
lves+0.010
 none+0.010
 pads+0.010
Neg logit contributions
ment-0.009
 kiss-0.009
 forgiveness-0.008
 bless-0.008
less-0.008
Token it
Token ID340
Feature activation-1.77e+00

Pos logit contributions
 none+0.135
lves+0.120
pole+0.119
 One+0.119
chard+0.118
Neg logit contributions
 kiss-0.141
 bless-0.126
ment-0.124
arl-0.123
 forgiveness-0.122
Token could
Token ID714
Feature activation+1.34e+00

Pos logit contributions
ment+0.094
 kiss+0.094
less+0.088
 forgiveness+0.088
 bless+0.086
Neg logit contributions
pole-0.067
 none-0.066
lves-0.061
 pads-0.060
chard-0.060
Token have
Token ID423
Feature activation-7.33e-01

Pos logit contributions
 none+0.065
 One+0.064
pole+0.064
chard+0.060
 bank+0.057
Neg logit contributions
ment-0.061
less-0.053
irk-0.052
 accidents-0.050
 forgiveness-0.050
Token a
Token ID257
Feature activation+1.15e-01

Pos logit contributions
 kiss+0.034
ment+0.032
less+0.029
 bless+0.029
 forgiveness+0.029
Neg logit contributions
pole-0.035
lves-0.033
chard-0.033
 none-0.033
 One-0.032
Token thanked
Token ID26280
Feature activation-5.15e-01

Pos logit contributions
pole+0.012
lves+0.012
chard+0.011
 none+0.011
uries+0.011
Neg logit contributions
 kiss-0.012
ment-0.010
 bless-0.010
 band-0.010
 prayer-0.009
Token her
Token ID607
Feature activation+6.66e-01

Pos logit contributions
less+0.023
ment+0.022
 kiss+0.022
 ray+0.021
guard+0.020
Neg logit contributions
 none-0.023
 One-0.023
pole-0.023
chard-0.022
nam-0.022
Token mom
Token ID1995
Feature activation-2.75e+00

Pos logit contributions
pole+0.032
chard+0.032
 favorites+0.032
 favourites+0.031
nam+0.031
Neg logit contributions
ment-0.026
 kiss-0.025
less-0.024
Time-0.024
pour-0.023
Token for
Token ID329
Feature activation-1.66e+00

Pos logit contributions
ment+0.110
 kiss+0.106
 pain+0.101
 ray+0.100
 forgiveness+0.097
Neg logit contributions
pole-0.145
 One-0.136
 none-0.133
 pads-0.131
chard-0.129
Token keeping
Token ID5291
Feature activation-2.81e-01

Pos logit contributions
ment+0.084
 kiss+0.081
less+0.078
 prayer+0.074
 ray+0.073
Neg logit contributions
 none-0.073
nam-0.070
chard-0.070
pole-0.067
 Jerry-0.063
Token her
Token ID607
Feature activation+1.59e-01

Pos logit contributions
 kiss+0.012
ment+0.011
less+0.011
 prayer+0.010
guard+0.010
Neg logit contributions
 none-0.014
pole-0.014
chard-0.013
lves-0.013
 One-0.013
Token promise
Token ID6991
Feature activation-3.40e+00

Pos logit contributions
 none+0.008
nam+0.007
chard+0.007
 favourites+0.007
 favorites+0.007
Neg logit contributions
ment-0.007
arl-0.006
 kiss-0.006
less-0.006
Time-0.006
Token.
Token ID13
Feature activation-8.30e-03

Pos logit contributions
 kiss+0.136
ment+0.134
 bless+0.120
 forgiveness+0.116
 ray+0.114
Neg logit contributions
 none-0.176
pole-0.174
chard-0.165
 One-0.164
 pads-0.161
Token They
Token ID1119
Feature activation+6.38e-01

Pos logit contributions
 kiss+0.000
ment+0.000
 prayer+0.000
ful+0.000
 forgiveness+0.000
Neg logit contributions
lves-0.000
pole-0.000
chard-0.000
 none-0.000
nam-0.000
Token enjoyed
Token ID8359
Feature activation-3.52e-01

Pos logit contributions
pole+0.028
lves+0.027
opes+0.026
uries+0.026
chard+0.026
Neg logit contributions
 kiss-0.033
ment-0.029
 band-0.028
 bless-0.028
ful-0.027
Token the
Token ID262
Feature activation-5.36e-02

Pos logit contributions
 kiss+0.014
ment+0.013
less+0.012
 bless+0.012
 prayer+0.012
Neg logit contributions
pole-0.018
 none-0.018
chard-0.018
lves-0.018
 One-0.017
Token a
Token ID257
Feature activation-6.02e-01

Pos logit contributions
 none+0.002
pole+0.002
chard+0.002
lves+0.002
 favourites+0.002
Neg logit contributions
 kiss-0.002
ment-0.002
 bless-0.002
 prayer-0.002
arl-0.002
Token way
Token ID835
Feature activation+1.90e-01

Pos logit contributions
ment+0.031
iness+0.025
ful+0.025
 kiss+0.025
arl+0.025
Neg logit contributions
pole-0.025
chard-0.025
 none-0.025
lves-0.024
 favourites-0.024
Token to
Token ID284
Feature activation-4.42e-01

Pos logit contributions
pole+0.009
 none+0.009
 One+0.008
 pads+0.008
chard+0.008
Neg logit contributions
ment-0.008
 kiss-0.008
 bless-0.008
 prayer-0.007
 forgiveness-0.007
Token act
Token ID719
Feature activation+7.38e-01

Pos logit contributions
ment+0.020
less+0.018
arl+0.017
irk+0.017
 prayer+0.016
Neg logit contributions
 none-0.021
 One-0.021
pole-0.020
 bank-0.019
chard-0.019
Token happy
Token ID3772
Feature activation+8.41e-01

Pos logit contributions
pole+0.034
 none+0.033
 pads+0.031
uries+0.030
 One+0.030
Neg logit contributions
 kiss-0.032
ment-0.031
 bless-0.030
 prayer-0.029
 forgiveness-0.029
Token and
Token ID290
Feature activation-2.25e-01

Pos logit contributions
 none+0.035
pole+0.035
 pads+0.034
 One+0.033
 favourites+0.032
Neg logit contributions
 kiss-0.038
arl-0.037
 bless-0.036
ment-0.035
less-0.034
Token silly
Token ID14397
Feature activation+7.61e-01

Pos logit contributions
ment+0.009
 kiss+0.009
less+0.008
 bless+0.008
arl+0.008
Neg logit contributions
 none-0.011
pole-0.011
chard-0.010
nam-0.010
 pads-0.010
Token.
Token ID13
Feature activation-4.04e-01

Pos logit contributions
 none+0.033
pole+0.033
 pads+0.033
 favourites+0.032
 One+0.032
Neg logit contributions
 kiss-0.031
ment-0.031
 bless-0.030
arl-0.029
pour-0.029
Token
Token ID198
Feature activation-4.61e-01

Pos logit contributions
 kiss+0.018
ment+0.017
 prayer+0.015
 bless+0.015
 forgiveness+0.015
Neg logit contributions
pole-0.021
lves-0.020
chard-0.020
 none-0.019
nam-0.019
Token
Token ID198
Feature activation-7.85e-01

Pos logit contributions
 kiss+0.020
ment+0.020
less+0.018
 bless+0.017
 prayer+0.017
Neg logit contributions
pole-0.022
 One-0.022
lves-0.021
 none-0.021
chard-0.020
TokenRuby
Token ID32101
Feature activation+3.39e-01

Pos logit contributions
ment+0.040
 kiss+0.038
less+0.036
 prayer+0.035
 forgiveness+0.035
Neg logit contributions
pole-0.033
 One-0.031
 none-0.030
lves-0.030
 pads-0.029
Token Sn
Token ID5489
Feature activation+1.40e+00

Pos logit contributions
 kiss+0.090
ment+0.083
less+0.079
 bless+0.079
 forgiveness+0.076
Neg logit contributions
pole-0.088
lves-0.083
 none-0.080
chard-0.080
 pads-0.078
Tokenugg
Token ID6837
Feature activation-4.62e+00

Pos logit contributions
pole+0.091
lves+0.089
 none+0.088
chard+0.088
 One+0.086
Neg logit contributions
 kiss-0.039
ment-0.036
less-0.031
 bless-0.030
 forgiveness-0.030
Tokenles
Token ID829
Feature activation+8.96e-01

Pos logit contributions
 kiss+0.244
 click+0.231
 forgiveness+0.229
 cheer+0.223
 handy+0.223
Neg logit contributions
 favorites-0.172
opes-0.166
 favourites-0.160
 pads-0.159
lves-0.157
Token.
Token ID13
Feature activation-7.63e-01

Pos logit contributions
pole+0.050
lves+0.049
 none+0.048
chard+0.048
 One+0.047
Neg logit contributions
 kiss-0.033
ment-0.031
less-0.028
 bless-0.027
 forgiveness-0.027
Token One
Token ID1881
Feature activation-1.44e-02

Pos logit contributions
 kiss+0.053
 prayer+0.045
 bless+0.045
 shower+0.045
ment+0.044
Neg logit contributions
lves-0.023
pole-0.022
chard-0.021
opes-0.020
riages-0.019
Token day
Token ID1110
Feature activation-4.38e+00

Pos logit contributions
ment+0.001
 kiss+0.001
 forgiveness+0.001
arl+0.001
 bless+0.001
Neg logit contributions
 One-0.001
pole-0.001
 While-0.001
 pads-0.001
 favourites-0.001
Token,
Token ID11
Feature activation-1.18e+00

Pos logit contributions
 kiss+0.152
ment+0.144
less+0.128
 bless+0.125
 forgiveness+0.123
Neg logit contributions
pole-0.256
lves-0.248
 none-0.245
chard-0.244
 One-0.238
Token they
Token ID484
Feature activation+4.10e-01

Pos logit contributions
 kiss+0.052
ment+0.052
less+0.046
 bless+0.046
 forgiveness+0.046
Neg logit contributions
pole-0.055
 none-0.055
chard-0.055
lves-0.054
 One-0.053
Token went
Token ID1816
Feature activation-1.24e+00

Pos logit contributions
pole+0.023
lves+0.022
opes+0.022
uries+0.021
 none+0.021
Neg logit contributions
 kiss-0.016
ment-0.013
 bless-0.013
 band-0.013
less-0.012
Token to
Token ID284
Feature activation-1.79e+00

Pos logit contributions
 kiss+0.045
ment+0.044
 forgiveness+0.038
less+0.038
 bless+0.038
Neg logit contributions
pole-0.070
lves-0.068
 none-0.067
chard-0.067
 One-0.067
Token the
Token ID262
Feature activation+1.18e-01

Pos logit contributions
 kiss+0.057
ment+0.045
 bless+0.045
 band+0.044
 forgiveness+0.042
Neg logit contributions
pole-0.118
lves-0.109
 none-0.109
opes-0.107
 pads-0.107
Token "
Token ID366
Feature activation+2.48e+00

Pos logit contributions
 kiss+0.025
ment+0.023
less+0.022
 bless+0.021
 forgiveness+0.021
Neg logit contributions
pole-0.025
lves-0.024
chard-0.023
 none-0.023
 favourites-0.022
TokenI
Token ID40
Feature activation-1.27e+00

Pos logit contributions
pole+0.124
lves+0.120
 none+0.118
chard+0.117
 One+0.115
Neg logit contributions
 kiss-0.106
ment-0.104
less-0.093
 bless-0.092
 forgiveness-0.091
Token got
Token ID1392
Feature activation-1.39e+00

Pos logit contributions
ment+0.061
 kiss+0.059
 forgiveness+0.053
 prayer+0.052
less+0.052
Neg logit contributions
pole-0.057
lves-0.056
 none-0.054
 One-0.054
 favourites-0.052
Token you
Token ID345
Feature activation-4.49e+00

Pos logit contributions
 kiss+0.056
ment+0.053
less+0.048
 bless+0.048
 forgiveness+0.047
Neg logit contributions
pole-0.074
lves-0.071
chard-0.070
 none-0.070
 One-0.068
Token,
Token ID11
Feature activation-8.48e-01

Pos logit contributions
 kiss+0.199
ment+0.192
less+0.173
 bless+0.172
 forgiveness+0.170
Neg logit contributions
pole-0.219
lves-0.211
 none-0.208
chard-0.207
 One-0.200
Token you
Token ID345
Feature activation-3.70e+00

Pos logit contributions
ment+0.046
 kiss+0.043
less+0.041
 bless+0.039
 forgiveness+0.039
Neg logit contributions
pole-0.035
 none-0.033
lves-0.032
chard-0.031
 One-0.030
Token bad
Token ID2089
Feature activation-1.65e+00

Pos logit contributions
 kiss+0.159
ment+0.145
less+0.137
 bless+0.135
 forgiveness+0.131
Neg logit contributions
pole-0.188
chard-0.183
lves-0.183
 none-0.178
 One-0.173
Token chicken
Token ID9015
Feature activation+3.69e+00

Pos logit contributions
ment+0.082
 kiss+0.082
less+0.076
 forgiveness+0.075
guard+0.073
Neg logit contributions
pole-0.063
 none-0.060
 pads-0.059
opes-0.059
 One-0.059
Token!"
Token ID2474
Feature activation+1.97e+00

Pos logit contributions
pole+0.142
 none+0.132
lves+0.131
 pads+0.124
chard+0.124
Neg logit contributions
 kiss-0.197
ment-0.197
 forgiveness-0.178
less-0.177
 prayer-0.175
Token
Token ID198
Feature activation+3.53e-02

Pos logit contributions
pole+0.106
lves+0.104
chard+0.100
uries+0.097
 none+0.097
Neg logit contributions
 kiss-0.082
ment-0.077
 forgiveness-0.067
 band-0.067
less-0.066
Token
Token ID198
Feature activation-4.08e-01

Pos logit contributions
pole+0.002
lves+0.002
chard+0.002
 none+0.002
 favourites+0.002
Neg logit contributions
 kiss-0.002
ment-0.002
less-0.001
 bless-0.001
 forgiveness-0.001
TokenShe
Token ID3347
Feature activation-3.84e-01

Pos logit contributions
 kiss+0.013
ment+0.013
less+0.012
 bless+0.012
 forgiveness+0.012
Neg logit contributions
pole-0.013
lves-0.012
 none-0.012
chard-0.012
 favourites-0.012
Token scoop
Token ID23529
Feature activation-4.44e-01

Pos logit contributions
 kiss+0.017
 band+0.015
ment+0.015
 fairy+0.014
 cleaner+0.014
Neg logit contributions
lves-0.019
pole-0.019
chard-0.018
uries-0.018
nam-0.018
Tokened
Token ID276
Feature activation+1.19e+00

Pos logit contributions
 kiss+0.023
 prayer+0.022
 bless+0.022
 forgiveness+0.022
ment+0.021
Neg logit contributions
pole-0.018
lves-0.017
 none-0.017
 pads-0.016
 One-0.016
Token up
Token ID510
Feature activation+2.18e+00

Pos logit contributions
pole+0.058
lves+0.056
 none+0.055
chard+0.055
 One+0.053
Neg logit contributions
 kiss-0.053
ment-0.051
less-0.046
 bless-0.046
 forgiveness-0.045
Token some
Token ID617
Feature activation-1.41e+00

Pos logit contributions
 none+0.107
pole+0.106
lves+0.106
chard+0.105
 One+0.101
Neg logit contributions
 kiss-0.092
ment-0.088
 bless-0.083
 prayer-0.081
less-0.081
Token of
Token ID286
Feature activation-3.25e+00

Pos logit contributions
 kiss+0.072
 bless+0.072
 prayer+0.071
ment+0.070
 forgiveness+0.066
Neg logit contributions
pole-0.052
 none-0.051
lves-0.051
 bank-0.051
 favorites-0.050
Token the
Token ID262
Feature activation-6.46e-01

Pos logit contributions
 kiss+0.106
ment+0.097
less+0.085
 forgiveness+0.084
 bless+0.083
Neg logit contributions
pole-0.200
lves-0.191
chard-0.188
 none-0.187
uries-0.186
Token dirt
Token ID13647
Feature activation-3.48e+00

Pos logit contributions
 kiss+0.030
ment+0.029
 bless+0.026
 prayer+0.026
 forgiveness+0.025
Neg logit contributions
pole-0.031
lves-0.030
 none-0.030
chard-0.029
 favourites-0.028
Token and
Token ID290
Feature activation-6.59e-01

Pos logit contributions
 kiss+0.144
 bless+0.139
 forgiveness+0.131
ment+0.130
 prayer+0.124
Neg logit contributions
pole-0.187
 none-0.181
chard-0.169
 pads-0.168
 bank-0.168
Token let
Token ID1309
Feature activation+5.75e-01

Pos logit contributions
 kiss+0.033
ment+0.032
less+0.030
 bless+0.030
 forgiveness+0.029
Neg logit contributions
pole-0.028
 none-0.027
lves-0.026
chard-0.026
 pads-0.025
Token it
Token ID340
Feature activation+1.20e-01

Pos logit contributions
pole+0.030
lves+0.029
 none+0.028
chard+0.028
 One+0.027
Neg logit contributions
 kiss-0.024
ment-0.023
less-0.021
 bless-0.021
 forgiveness-0.020
Token.
Token ID13
Feature activation-9.33e-01

Pos logit contributions
 kiss+0.034
ment+0.032
 bless+0.029
 forgiveness+0.028
 prayer+0.028
Neg logit contributions
pole-0.052
 none-0.050
chard-0.048
lves-0.048
 One-0.048
Token And
Token ID843
Feature activation-2.76e-01

Pos logit contributions
ment+0.037
 kiss+0.037
 forgiveness+0.034
 of+0.034
less+0.034
Neg logit contributions
pole-0.048
lves-0.048
chard-0.047
nam-0.046
uries-0.043
Token that
Token ID326
Feature activation-2.41e+00

Pos logit contributions
 kiss+0.015
ment+0.014
 bless+0.013
less+0.013
arl+0.012
Neg logit contributions
 none-0.011
pole-0.011
chard-0.011
lves-0.010
 One-0.010
Token was
Token ID373
Feature activation+2.84e-01

Pos logit contributions
 kiss+0.097
ment+0.090
 prayer+0.084
 forgiveness+0.083
less+0.083
Neg logit contributions
lves-0.127
pole-0.126
chard-0.123
uries-0.119
nam-0.117
Token the
Token ID262
Feature activation-8.36e-02

Pos logit contributions
pole+0.014
lves+0.013
chard+0.013
 none+0.013
 One+0.013
Neg logit contributions
 kiss-0.013
ment-0.012
less-0.011
 bless-0.011
 forgiveness-0.011
Token bad
Token ID2089
Feature activation-3.19e+00

Pos logit contributions
ment+0.004
 kiss+0.004
 bless+0.003
less+0.003
ful+0.003
Neg logit contributions
 none-0.004
pole-0.004
chard-0.004
 One-0.004
lves-0.004
Token ending
Token ID7464
Feature activation-5.63e+00

Pos logit contributions
 kiss+0.139
ment+0.136
 bless+0.135
ful+0.123
arl+0.120
Neg logit contributions
 none-0.155
 One-0.152
 bank-0.149
 banks-0.144
pole-0.138
Token for
Token ID329
Feature activation-2.40e+00

Pos logit contributions
 kiss+0.239
ment+0.222
 bless+0.209
 prayer+0.200
 forgiveness+0.198
Neg logit contributions
pole-0.289
 none-0.276
 One-0.263
 pads-0.262
lves-0.256
Token Tim
Token ID5045
Feature activation+7.77e-01

Pos logit contributions
 kiss+0.146
ment+0.141
less+0.131
 bless+0.130
 prayer+0.129
Neg logit contributions
pole-0.079
 none-0.077
chard-0.074
lves-0.074
 One-0.071
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
pole+0.044
lves+0.043
 none+0.042
chard+0.042
 One+0.041
Neg logit contributions
 kiss-0.028
ment-0.027
less-0.024
 bless-0.024
 forgiveness-0.023
Token<|endoftext|>
Token ID50256
Feature activation-3.11e+00

Pos logit contributions
 kiss+0.037
ment+0.035
 forgiveness+0.032
 of+0.030
less+0.030
Neg logit contributions
pole-0.064
chard-0.064
lves-0.062
nam-0.061
 none-0.061
Token,
Token ID11
Feature activation+8.25e-01

Pos logit contributions
pole+0.112
 none+0.112
 One+0.109
opes+0.105
 pads+0.105
Neg logit contributions
 kiss-0.103
ment-0.096
 bless-0.093
 band-0.088
 forgiveness-0.088
Token and
Token ID290
Feature activation+1.27e-01

Pos logit contributions
pole+0.039
 none+0.039
lves+0.037
chard+0.036
 pads+0.036
Neg logit contributions
 kiss-0.036
ment-0.036
 bless-0.033
less-0.032
 forgiveness-0.032
Token had
Token ID550
Feature activation+7.17e-01

Pos logit contributions
 none+0.006
pole+0.006
chard+0.005
lves+0.005
nam+0.005
Neg logit contributions
 kiss-0.006
ment-0.006
less-0.005
 bless-0.005
 forgiveness-0.005
Token a
Token ID257
Feature activation+2.13e-01

Pos logit contributions
pole+0.035
lves+0.034
chard+0.033
opes+0.031
 favourites+0.031
Neg logit contributions
 kiss-0.033
ment-0.030
less-0.029
 forgiveness-0.028
 band-0.028
Token wonderful
Token ID7932
Feature activation-7.35e-01

Pos logit contributions
pole+0.009
 none+0.009
lves+0.009
 One+0.009
chard+0.009
Neg logit contributions
ment-0.010
 kiss-0.009
less-0.009
ful-0.008
 bless-0.008
Token day
Token ID1110
Feature activation-4.20e+00

Pos logit contributions
ment+0.031
ful+0.030
 kiss+0.029
less+0.028
 bless+0.028
Neg logit contributions
 One-0.035
 favourites-0.034
pole-0.034
 favorites-0.033
 none-0.032
Token exploring
Token ID13504
Feature activation+3.60e-01

Pos logit contributions
 kiss+0.185
ment+0.174
 forgiveness+0.162
 prayer+0.160
 bless+0.159
Neg logit contributions
pole-0.195
 none-0.193
 favourites-0.184
 pads-0.184
 One-0.183
Token the
Token ID262
Feature activation-2.03e-01

Pos logit contributions
pole+0.019
 none+0.018
chard+0.018
lves+0.018
 One+0.018
Neg logit contributions
 kiss-0.015
ment-0.014
less-0.013
 bless-0.013
 prayer-0.012
Token new
Token ID649
Feature activation-1.14e-01

Pos logit contributions
ment+0.011
 kiss+0.010
less+0.009
 forgiveness+0.009
ful+0.009
Neg logit contributions
pole-0.008
lves-0.008
chard-0.008
 One-0.008
 favourites-0.008
Token city
Token ID1748
Feature activation+2.16e-01

Pos logit contributions
 kiss+0.005
ment+0.005
 bless+0.004
less+0.004
 forgiveness+0.004
Neg logit contributions
pole-0.005
lves-0.005
 none-0.005
 One-0.005
chard-0.005
Token.
Token ID13
Feature activation-1.05e-01

Pos logit contributions
pole+0.012
lves+0.012
 none+0.012
chard+0.012
 One+0.011
Neg logit contributions
 kiss-0.008
ment-0.007
less-0.007
 bless-0.006
 forgiveness-0.006