TOP ACTIVATIONS
MAX = 0.146

It was hiding under a seaw eed . Lily said ,
smooth apple with a high score again . <|endoftext|> Once upon
and a tie on the groom . They made a bou
mom had made some fancy sund a es for everyone .
I 'm making a delicious mac aron i and cheese ,"
. She puts on a chef hat and a pron .
you should do something more constructive with those mar bles .
over . She wore a sund ress with a big bow
the daddy got out a score . Everyone was happy and
and her mom got a sund ae with lots of topp
him a delicious ice cream sund ae with lots of topp
the party , wearing a princess dress , with her friends
Please may I have a sund ae ?" The waitress smiled
is a big spider on your pillow !" Max
sand , and deep blue seas . One
Tim my got a high score ! He was so happy
statue made by a famous artist a long time ago ."
How about we make some mac aron i and cheese for
He started acting like a chef , grabbing different ingredients and
need to make an o me lette ?". He was very

MIN ACTIVATIONS
MIN = -0.151

and hungry . She said ow ls like to eat mice
ily said , " B run o , you are a
Jack thanked the ow ls and he waved goodbye
, " O w , ow , ow . It hurts
" O w , ow , ow ! My toe
its toy fixed . Thank ful , it flew away with
, " O w , ow , ow . My arm
" O w , ow , ow !" Lily said
" O w , ow , ow !" Ben cried
" O w , ow , ow !" Tom cried
" O w , ow , ow ! It hurts
" O w , ow , ow , it hurts
" O w , ow , ow !" Tom cried
" O w , ow , ow !" Ben says
" O w , ow , ow !" Anna says
" O w , ow , ow !" Tom cries
" O w , ow , ow !" Mia cried
" O w , ow !" Ben says . He
, " O w , ow , ow !"
" O w , ow , ow !" she screamed

INTERVAL 0.072 - 0.146
CONTAINS 0.170%

Can I please ride in your boat ?" The man said
Cl ara made a new guess - she thought it must
and ships , especially y ach ts . One day ,
Sam wanted to draw a dinosaur . They both grabbed the
Lily sees a big red tomato on a vine . She

INTERVAL -0.002 - 0.072
CONTAINS 55.006%

to play ?" Tom says , " Let 's
Yes ! Of course . I have a lot of colorful
an eye on the cooler to make sure no more naughty
M ummy said ' you can do this yourself now
. <|endoftext|> Once upon a time there was a dog called

INTERVAL -0.077 - -0.002
CONTAINS 44.476%

She took the note and ran home to show her parents
things . One day he was out exploring the woods and
little girl named Lily . She loved to skip and jump
Once upon a time , there was a beetle who lived
She thought it was so strange and cute . She wanted

INTERVAL -0.151 - -0.077
CONTAINS 0.347%

, " No , my arm really hurts ," while he
and helped Mom fix the fence and clean the garden .
and the big frog said that he was lonely and had
his friend . He wished that Mitt ens had not been
, but he never forgot how brave he was the day
Token It
Token ID632
Feature activation+1.74e-03

Pos logit contributions
iece+0.023
edly+0.022
 seas+0.021
ly+0.020
Edward+0.018
Neg logit contributions
 cleans-0.015
run-0.013
 need-0.012
uffy-0.012
 Kim-0.011
Token was
Token ID373
Feature activation+1.17e-03

Pos logit contributions
edly+0.003
 seas+0.003
iece+0.003
 seven+0.003
Please+0.003
Neg logit contributions
 cleans-0.003
 outage-0.002
uffy-0.002
run-0.002
 need-0.002
Token hiding
Token ID11816
Feature activation+1.76e-02

Pos logit contributions
edly+0.002
iece+0.002
 seas+0.002
ly+0.002
Edward+0.002
Neg logit contributions
 cleans-0.002
 need-0.001
run-0.001
uffy-0.001
 outage-0.001
Token under
Token ID739
Feature activation-7.99e-03

Pos logit contributions
iece+0.035
oph+0.033
Edward+0.033
Prin+0.032
edly+0.032
Neg logit contributions
 locked-0.019
 cleans-0.019
 hose-0.018
run-0.018
uffy-0.018
Token a
Token ID257
Feature activation+5.24e-02

Pos logit contributions
 hose+0.009
 cleans+0.008
 Kitty+0.008
 Kim+0.008
 need+0.008
Neg logit contributions
iece-0.018
edly-0.017
ly-0.016
oph-0.015
bye-0.015
Token seaw
Token ID32085
Feature activation+1.34e-01

Pos logit contributions
iece+0.094
 seas+0.094
edly+0.093
Edward+0.085
ly+0.083
Neg logit contributions
 cleans-0.076
uffy-0.068
run-0.065
 outage-0.062
 exc-0.061
Tokeneed
Token ID2308
Feature activation+8.17e-02

Pos logit contributions
iece+0.150
edly+0.139
Please+0.112
Prin+0.108
 oceans+0.103
Neg logit contributions
uffy-0.271
 cleans-0.266
run-0.264
 hose-0.264
 outage-0.261
Token.
Token ID13
Feature activation+1.28e-02

Pos logit contributions
edly+0.152
iece+0.150
 seas+0.138
Edward+0.131
ly+0.127
Neg logit contributions
 cleans-0.114
uffy-0.102
 outage-0.101
 need-0.099
run-0.098
Token Lily
Token ID20037
Feature activation+2.35e-02

Pos logit contributions
iece+0.025
edly+0.024
 seas+0.022
ly+0.022
 tune+0.020
Neg logit contributions
 cleans-0.018
run-0.016
uffy-0.016
 need-0.015
 Kim-0.014
Token said
Token ID531
Feature activation+1.33e-02

Pos logit contributions
edly+0.043
iece+0.042
 seas+0.039
Edward+0.036
ly+0.036
Neg logit contributions
 cleans-0.034
uffy-0.031
 outage-0.030
run-0.030
 need-0.030
Token,
Token ID11
Feature activation+5.30e-03

Pos logit contributions
edly+0.033
iece+0.032
 seas+0.030
oph+0.029
Edward+0.028
Neg logit contributions
 cleans-0.012
uffy-0.009
run-0.009
 need-0.009
 exc-0.009
Token smooth
Token ID7209
Feature activation+2.22e-02

Pos logit contributions
edly+0.051
iece+0.050
 seas+0.048
Edward+0.045
ly+0.044
Neg logit contributions
 cleans-0.037
uffy-0.032
 outage-0.032
run-0.031
 need-0.030
Token apple
Token ID17180
Feature activation+3.40e-02

Pos logit contributions
iece+0.042
edly+0.041
 seas+0.035
Edward+0.035
Prin+0.033
Neg logit contributions
 cleans-0.032
 need-0.030
uffy-0.029
run-0.028
 hose-0.028
Token with
Token ID351
Feature activation+1.95e-02

Pos logit contributions
edly+0.068
iece+0.068
 seas+0.063
Edward+0.060
ly+0.058
Neg logit contributions
 cleans-0.042
uffy-0.037
 outage-0.036
run-0.036
 need-0.036
Token a
Token ID257
Feature activation+3.73e-02

Pos logit contributions
iece+0.032
edly+0.032
 seas+0.027
Edward+0.026
ly+0.025
Neg logit contributions
 cleans-0.033
 need-0.030
run-0.029
uffy-0.028
 exc-0.027
Token high
Token ID1029
Feature activation+3.92e-02

Pos logit contributions
edly+0.069
iece+0.068
 seas+0.064
Edward+0.060
ly+0.059
Neg logit contributions
 cleans-0.053
uffy-0.047
 outage-0.046
run-0.045
 need-0.044
Token score
Token ID4776
Feature activation+1.27e-01

Pos logit contributions
iece+0.077
edly+0.074
 seas+0.066
Edward+0.065
Prin+0.062
Neg logit contributions
 cleans-0.053
 need-0.050
run-0.047
uffy-0.046
 hose-0.046
Token again
Token ID757
Feature activation+4.49e-02

Pos logit contributions
edly+0.271
iece+0.268
 seas+0.256
Edward+0.245
oph+0.242
Neg logit contributions
 cleans-0.126
run-0.123
 need-0.114
 outage-0.112
uffy-0.104
Token.
Token ID13
Feature activation+1.52e-03

Pos logit contributions
edly+0.094
iece+0.094
 seas+0.087
Edward+0.083
ly+0.081
Neg logit contributions
 cleans-0.052
uffy-0.045
run-0.044
 outage-0.044
 need-0.044
Token<|endoftext|>
Token ID50256
Feature activation-5.55e-03

Pos logit contributions
edly+0.003
iece+0.003
 seas+0.003
Edward+0.003
oph+0.002
Neg logit contributions
 cleans-0.002
uffy-0.002
 outage-0.002
run-0.002
 exc-0.002
TokenOnce
Token ID7454
Feature activation-4.06e-02

Pos logit contributions
 cleans+0.007
uffy+0.006
 outage+0.006
run+0.006
 need+0.006
Neg logit contributions
edly-0.011
iece-0.011
 seas-0.010
Edward-0.010
ly-0.009
Token upon
Token ID2402
Feature activation+4.96e-02

Pos logit contributions
 cleans+0.092
 outage+0.082
 drown+0.082
 slam+0.081
run+0.079
Neg logit contributions
 seas-0.039
iece-0.038
 Avery-0.034
Edward-0.032
 Amber-0.032
Token and
Token ID290
Feature activation+1.41e-02

Pos logit contributions
edly+0.157
iece+0.150
 seas+0.145
Edward+0.139
oph+0.132
Neg logit contributions
 cleans-0.111
uffy-0.099
 outage-0.095
 need-0.094
run-0.092
Token a
Token ID257
Feature activation+4.29e-02

Pos logit contributions
iece+0.027
edly+0.027
 seas+0.024
Edward+0.023
ly+0.022
Neg logit contributions
 cleans-0.021
 need-0.017
 slammed-0.016
 tells-0.016
 hose-0.016
Token tie
Token ID9839
Feature activation+5.89e-02

Pos logit contributions
iece+0.086
edly+0.085
oph+0.073
 seas+0.071
adies+0.071
Neg logit contributions
 cleans-0.056
 hose-0.053
 need-0.049
uffy-0.049
 outage-0.048
Token on
Token ID319
Feature activation+6.55e-04

Pos logit contributions
edly+0.125
iece+0.122
Edward+0.115
oph+0.115
 seas+0.114
Neg logit contributions
 cleans-0.064
run-0.056
 outage-0.055
 need-0.055
 hose-0.053
Token the
Token ID262
Feature activation+3.62e-02

Pos logit contributions
edly+0.001
iece+0.001
oph+0.001
adies+0.001
ly+0.001
Neg logit contributions
 cleans-0.001
 hose-0.001
 Kim-0.001
 need-0.001
 switch-0.001
Token groom
Token ID32443
Feature activation+1.26e-01

Pos logit contributions
edly+0.072
iece+0.071
Luc+0.069
oph+0.068
Dave+0.067
Neg logit contributions
 cleans-0.042
 hose-0.041
 switch-0.036
 umbrella-0.035
 needs-0.034
Token.
Token ID13
Feature activation+1.15e-02

Pos logit contributions
edly+0.279
 seas+0.264
iece+0.261
Edward+0.258
oph+0.252
Neg logit contributions
 cleans-0.125
 need-0.107
run-0.100
uffy-0.097
 outage-0.097
Token They
Token ID1119
Feature activation+4.79e-03

Pos logit contributions
edly+0.026
iece+0.026
 seas+0.024
Edward+0.023
ly+0.023
Neg logit contributions
 cleans-0.012
uffy-0.010
 outage-0.010
run-0.010
 need-0.009
Token made
Token ID925
Feature activation+2.38e-02

Pos logit contributions
edly+0.009
iece+0.009
 seas+0.008
Edward+0.008
ly+0.007
Neg logit contributions
 cleans-0.007
uffy-0.006
 outage-0.006
run-0.006
 need-0.006
Token a
Token ID257
Feature activation+3.08e-02

Pos logit contributions
edly+0.049
iece+0.045
Please+0.042
Edward+0.041
P+0.041
Neg logit contributions
 cleans-0.033
 Liz-0.027
 need-0.027
 know-0.026
 tells-0.026
Token bou
Token ID35833
Feature activation+6.47e-02

Pos logit contributions
edly+0.065
iece+0.063
 seas+0.054
ly+0.054
Please+0.053
Neg logit contributions
 cleans-0.039
uffy-0.035
 hose-0.034
 need-0.033
 exc-0.033
Token mom
Token ID1995
Feature activation-3.00e-02

Pos logit contributions
edly+0.048
iece+0.047
 seas+0.045
Edward+0.041
ly+0.041
Neg logit contributions
 cleans-0.027
 outage-0.024
run-0.023
uffy-0.023
 need-0.022
Token had
Token ID550
Feature activation+1.58e-02

Pos logit contributions
 cleans+0.042
 outage+0.040
uffy+0.039
 drown+0.038
run+0.037
Neg logit contributions
edly-0.052
iece-0.051
ly-0.048
 seas-0.047
oph-0.046
Token made
Token ID925
Feature activation+2.92e-02

Pos logit contributions
edly+0.032
iece+0.032
 seas+0.028
ly+0.027
Edward+0.027
Neg logit contributions
 cleans-0.021
 need-0.019
run-0.018
 outage-0.017
uffy-0.017
Token some
Token ID617
Feature activation+3.53e-02

Pos logit contributions
edly+0.056
iece+0.054
 seas+0.046
Please+0.046
Edward+0.045
Neg logit contributions
 cleans-0.044
 need-0.039
uffy-0.035
 Kitty-0.035
 know-0.035
Token fancy
Token ID14996
Feature activation+4.14e-02

Pos logit contributions
iece+0.071
edly+0.070
 seas+0.063
Edward+0.061
 Edward+0.058
Neg logit contributions
 cleans-0.047
 need-0.041
uffy-0.040
 outage-0.039
run-0.039
Token sund
Token ID37437
Feature activation+1.24e-01

Pos logit contributions
iece+0.084
edly+0.081
Edward+0.073
 seas+0.071
Please+0.070
Neg logit contributions
 cleans-0.056
 need-0.049
uffy-0.045
 needs-0.044
 hose-0.043
Tokena
Token ID64
Feature activation+6.41e-02

Pos logit contributions
edly+0.151
iece+0.145
 seas+0.126
 oceans+0.123
 Edward+0.122
Neg logit contributions
uffy-0.248
run-0.235
 cleans-0.231
 outage-0.230
 need-0.222
Tokenes
Token ID274
Feature activation-1.42e-03

Pos logit contributions
iece+0.116
edly+0.116
 seas+0.103
Edward+0.099
Please+0.097
Neg logit contributions
 cleans-0.093
uffy-0.084
 need-0.083
run-0.081
 outage-0.079
Token for
Token ID329
Feature activation+4.69e-02

Pos logit contributions
 cleans+0.002
 need+0.002
 outage+0.002
uffy+0.002
run+0.002
Neg logit contributions
edly-0.003
iece-0.003
 seas-0.003
Edward-0.002
Please-0.002
Token everyone
Token ID2506
Feature activation+2.43e-02

Pos logit contributions
iece+0.085
edly+0.081
 seas+0.072
Edward+0.069
ly+0.068
Neg logit contributions
 cleans-0.071
 need-0.065
uffy-0.063
run-0.061
 Kitty-0.061
Token.
Token ID13
Feature activation+4.01e-03

Pos logit contributions
edly+0.040
iece+0.039
 seas+0.036
ly+0.035
Edward+0.033
Neg logit contributions
 cleans-0.039
uffy-0.036
 outage-0.034
run-0.033
 need-0.033
TokenI
Token ID40
Feature activation-2.22e-02

Pos logit contributions
iece+0.054
edly+0.052
 seas+0.047
ly+0.043
Edward+0.041
Neg logit contributions
 cleans-0.070
 outage-0.064
 need-0.063
uffy-0.063
run-0.062
Token'm
Token ID1101
Feature activation-1.01e-02

Pos logit contributions
 cleans+0.025
uffy+0.023
run+0.022
 outage+0.021
 Kim+0.021
Neg logit contributions
edly-0.043
iece-0.040
 seas-0.040
Please-0.038
Edward-0.038
Token making
Token ID1642
Feature activation-5.27e-03

Pos logit contributions
 cleans+0.015
uffy+0.015
 outage+0.014
run+0.013
 slammed+0.012
Neg logit contributions
edly-0.017
iece-0.016
 seas-0.015
 seven-0.015
 Edward-0.015
Token a
Token ID257
Feature activation+1.73e-02

Pos logit contributions
 cleans+0.008
 need+0.007
uffy+0.007
 hose+0.007
run+0.007
Neg logit contributions
edly-0.010
iece-0.009
Edward-0.008
 seas-0.008
ly-0.008
Token delicious
Token ID12625
Feature activation+5.18e-02

Pos logit contributions
edly+0.034
iece+0.033
 seas+0.031
Edward+0.029
ly+0.029
Neg logit contributions
 cleans-0.023
uffy-0.020
 outage-0.020
run-0.019
 need-0.019
Token mac
Token ID8352
Feature activation+1.24e-01

Pos logit contributions
edly+0.089
iece+0.088
 seas+0.083
ly+0.076
Edward+0.076
Neg logit contributions
 cleans-0.080
uffy-0.071
run-0.071
 outage-0.071
 need-0.068
Tokenaron
Token ID8045
Feature activation+3.34e-02

Pos logit contributions
iece+0.232
 seas+0.218
edly+0.214
Edward+0.204
 oceans+0.200
Neg logit contributions
 cleans-0.160
 outage-0.151
uffy-0.146
 need-0.142
 hose-0.136
Tokeni
Token ID72
Feature activation+2.31e-02

Pos logit contributions
edly+0.058
iece+0.057
 seas+0.053
Edward+0.050
Prin+0.047
Neg logit contributions
 cleans-0.052
uffy-0.047
 need-0.045
run-0.045
 outage-0.044
Token and
Token ID290
Feature activation+2.44e-02

Pos logit contributions
iece+0.047
edly+0.047
 seas+0.044
Edward+0.043
oph+0.041
Neg logit contributions
 cleans-0.028
 need-0.024
uffy-0.024
 outage-0.023
run-0.023
Token cheese
Token ID9891
Feature activation+3.76e-02

Pos logit contributions
iece+0.045
edly+0.043
 seas+0.039
Edward+0.037
ly+0.036
Neg logit contributions
 cleans-0.038
 need-0.034
run-0.032
 exc-0.032
uffy-0.031
Token,"
Token ID553
Feature activation+2.94e-02

Pos logit contributions
iece+0.084
edly+0.080
 seas+0.075
Edward+0.072
oph+0.070
Neg logit contributions
 cleans-0.040
 need-0.035
uffy-0.035
 outage-0.035
run-0.032
Token.
Token ID13
Feature activation+4.36e-04

Pos logit contributions
 seas+0.014
edly+0.014
iece+0.013
Edward+0.013
oph+0.012
Neg logit contributions
 cleans-0.004
run-0.003
uffy-0.003
 Kim-0.003
 need-0.003
Token She
Token ID1375
Feature activation-1.18e-02

Pos logit contributions
edly+0.001
iece+0.001
 seas+0.001
ly+0.001
Edward+0.001
Neg logit contributions
 cleans-0.000
uffy-0.000
run-0.000
 need-0.000
 outage-0.000
Token puts
Token ID7584
Feature activation+1.82e-02

Pos logit contributions
 cleans+0.014
 outage+0.014
uffy+0.013
run+0.013
 need+0.012
Neg logit contributions
edly-0.023
iece-0.023
 seas-0.022
Edward-0.021
ly-0.020
Token on
Token ID319
Feature activation-3.36e-02

Pos logit contributions
edly+0.038
iece+0.035
 seas+0.032
oph+0.032
Edward+0.031
Neg logit contributions
 cleans-0.026
 need-0.021
 Kim-0.020
run-0.020
 hose-0.019
Token a
Token ID257
Feature activation+3.47e-02

Pos logit contributions
 cleans+0.045
 Kim+0.037
 Kitty+0.036
 hose+0.035
 need+0.035
Neg logit contributions
edly-0.072
iece-0.069
 seas-0.063
ly-0.060
adies-0.059
Token chef
Token ID21221
Feature activation+1.24e-01

Pos logit contributions
edly+0.073
iece+0.071
 seas+0.062
Edward+0.061
oph+0.061
Neg logit contributions
 cleans-0.044
 need-0.038
run-0.037
 hose-0.037
uffy-0.037
Token hat
Token ID6877
Feature activation+4.38e-02

Pos logit contributions
edly+0.256
iece+0.240
 seas+0.239
oph+0.229
Edward+0.224
Neg logit contributions
 cleans-0.150
 need-0.138
 hose-0.126
run-0.122
 have-0.120
Token and
Token ID290
Feature activation+2.22e-02

Pos logit contributions
edly+0.087
 seas+0.085
iece+0.082
Edward+0.079
oph+0.076
Neg logit contributions
 cleans-0.056
 outage-0.047
run-0.047
uffy-0.047
 need-0.046
Token a
Token ID257
Feature activation+2.54e-02

Pos logit contributions
edly+0.041
iece+0.040
 seas+0.035
Edward+0.035
oph+0.034
Neg logit contributions
 cleans-0.037
 need-0.030
 tells-0.029
 needs-0.028
 exc-0.028
Tokenpron
Token ID31186
Feature activation+7.28e-02

Pos logit contributions
edly+0.052
iece+0.052
 seas+0.045
oph+0.044
Edward+0.044
Neg logit contributions
 cleans-0.034
 hose-0.029
 need-0.028
uffy-0.028
run-0.027
Token.
Token ID13
Feature activation+5.16e-03

Pos logit contributions
edly+0.157
iece+0.156
 seas+0.153
Edward+0.147
oph+0.144
Neg logit contributions
 cleans-0.078
 outage-0.065
uffy-0.063
run-0.062
 need-0.062
Token you
Token ID345
Feature activation+4.14e-02

Pos logit contributions
 cleans+0.012
uffy+0.011
 outage+0.011
run+0.011
 need+0.011
Neg logit contributions
edly-0.019
iece-0.018
 seas-0.017
Edward-0.016
ly-0.016
Token should
Token ID815
Feature activation-9.65e-03

Pos logit contributions
 seas+0.075
iece+0.074
ly+0.072
edly+0.071
Edward+0.069
Neg logit contributions
 cleans-0.049
uffy-0.045
 outage-0.043
ucker-0.042
run-0.041
Token do
Token ID466
Feature activation+2.20e-02

Pos logit contributions
 cleans+0.014
run+0.013
uffy+0.013
 outage+0.013
 slammed+0.011
Neg logit contributions
edly-0.016
iece-0.016
Edward-0.015
 seas-0.015
 Edward-0.015
Token something
Token ID1223
Feature activation+3.15e-02

Pos logit contributions
iece+0.032
edly+0.032
 seas+0.030
Edward+0.027
 Edward+0.026
Neg logit contributions
 cleans-0.039
uffy-0.037
 outage-0.036
run-0.035
 need-0.033
Token more
Token ID517
Feature activation+3.97e-02

Pos logit contributions
edly+0.054
iece+0.052
 seas+0.050
ly+0.049
Edward+0.046
Neg logit contributions
 cleans-0.049
uffy-0.043
 outage-0.041
run-0.040
 need-0.040
Token constructive
Token ID26938
Feature activation+1.23e-01

Pos logit contributions
edly+0.078
iece+0.077
 seas+0.071
ly+0.067
Edward+0.067
Neg logit contributions
 cleans-0.054
uffy-0.048
run-0.045
 outage-0.044
 need-0.044
Token with
Token ID351
Feature activation+1.08e-02

Pos logit contributions
edly+0.234
iece+0.228
 seas+0.214
Edward+0.200
oph+0.200
Neg logit contributions
 cleans-0.162
 need-0.153
 outage-0.151
uffy-0.145
run-0.145
Token those
Token ID883
Feature activation+3.18e-02

Pos logit contributions
iece+0.016
edly+0.016
 seas+0.015
Edward+0.013
ly+0.013
Neg logit contributions
 cleans-0.019
uffy-0.018
 outage-0.017
run-0.017
 need-0.016
Token mar
Token ID1667
Feature activation+2.35e-02

Pos logit contributions
edly+0.055
iece+0.054
 seas+0.051
ly+0.047
Edward+0.046
Neg logit contributions
 cleans-0.049
uffy-0.045
 outage-0.044
run-0.042
 need-0.041
Tokenbles
Token ID7689
Feature activation-3.20e-03

Pos logit contributions
edly+0.039
iece+0.038
 seas+0.033
Edward+0.032
Please+0.032
Neg logit contributions
 cleans-0.037
run-0.035
uffy-0.035
 need-0.033
 outage-0.033
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
 cleans+0.004
uffy+0.004
 outage+0.004
run+0.003
 need+0.003
Neg logit contributions
edly-0.006
iece-0.006
 seas-0.006
Edward-0.006
ly-0.005
Token over
Token ID625
Feature activation-3.34e-02

Pos logit contributions
edly+0.022
iece+0.021
 seas+0.020
Edward+0.018
oph+0.018
Neg logit contributions
 cleans-0.018
run-0.016
uffy-0.016
 need-0.016
 outage-0.016
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
 cleans+0.038
run+0.036
 need+0.034
uffy+0.032
 Kim+0.031
Neg logit contributions
iece-0.072
edly-0.070
 seas-0.068
Edward-0.063
oph-0.063
Token She
Token ID1375
Feature activation-1.79e-02

Pos logit contributions
 cleans+0.027
uffy+0.026
 outage+0.026
 drown+0.026
ric+0.025
Neg logit contributions
edly-0.018
iece-0.017
ly-0.016
Please-0.015
 Edward-0.015
Token wore
Token ID12408
Feature activation+1.88e-02

Pos logit contributions
 cleans+0.029
 outage+0.028
uffy+0.026
run+0.025
 need+0.025
Neg logit contributions
edly-0.028
iece-0.027
 seas-0.026
ly-0.025
Please-0.025
Token a
Token ID257
Feature activation+4.00e-02

Pos logit contributions
edly+0.032
iece+0.032
 seas+0.027
ly+0.026
Edward+0.025
Neg logit contributions
 cleans-0.032
 need-0.027
 Kitty-0.026
run-0.026
uffy-0.026
Token sund
Token ID37437
Feature activation+1.23e-01

Pos logit contributions
edly+0.082
iece+0.082
 seas+0.070
Edward+0.067
ly+0.067
Neg logit contributions
 cleans-0.052
uffy-0.046
 need-0.044
run-0.044
 hose-0.044
Tokenress
Token ID601
Feature activation+4.29e-02

Pos logit contributions
edly+0.167
iece+0.164
 seas+0.147
 oceans+0.140
 Edward+0.139
Neg logit contributions
uffy-0.226
 cleans-0.218
run-0.214
 outage-0.210
 need-0.200
Token with
Token ID351
Feature activation+1.25e-02

Pos logit contributions
 seas+0.074
edly+0.069
Edward+0.066
iece+0.065
 oceans+0.064
Neg logit contributions
 cleans-0.063
 Kim-0.059
run-0.058
 outage-0.057
uffy-0.057
Token a
Token ID257
Feature activation+3.01e-02

Pos logit contributions
edly+0.018
iece+0.018
 seas+0.016
Edward+0.014
ly+0.014
Neg logit contributions
 cleans-0.023
uffy-0.021
 need-0.021
run-0.021
 outage-0.021
Token big
Token ID1263
Feature activation-9.61e-03

Pos logit contributions
edly+0.054
iece+0.053
 seas+0.053
Edward+0.049
 Edward+0.047
Neg logit contributions
 cleans-0.041
uffy-0.037
 outage-0.036
run-0.036
 need-0.034
Token bow
Token ID9563
Feature activation+5.30e-02

Pos logit contributions
 cleans+0.012
uffy+0.011
 outage+0.011
run+0.011
 exc+0.010
Neg logit contributions
iece-0.018
edly-0.018
 seas-0.018
ly-0.016
Edward-0.016
Token the
Token ID262
Feature activation-5.03e-03

Pos logit contributions
iece+0.030
edly+0.029
 seas+0.026
Edward+0.026
ly+0.025
Neg logit contributions
 cleans-0.020
 need-0.016
uffy-0.016
 outage-0.016
 slammed-0.016
Token daddy
Token ID35822
Feature activation-9.50e-04

Pos logit contributions
 cleans+0.005
 hose+0.005
 need+0.005
 fireplace+0.005
 chim+0.004
Neg logit contributions
iece-0.011
edly-0.011
Edward-0.010
oph-0.009
adies-0.009
Token got
Token ID1392
Feature activation-1.23e-02

Pos logit contributions
 cleans+0.001
uffy+0.001
 outage+0.001
run+0.001
 drown+0.001
Neg logit contributions
edly-0.002
iece-0.002
 seas-0.002
ly-0.001
oph-0.001
Token out
Token ID503
Feature activation+4.30e-03

Pos logit contributions
 cleans+0.017
 need+0.016
 exc+0.014
run+0.014
 tells+0.014
Neg logit contributions
edly-0.024
iece-0.024
Edward-0.021
 seas-0.021
oph-0.021
Token a
Token ID257
Feature activation+2.92e-02

Pos logit contributions
edly+0.007
iece+0.007
 seas+0.007
ly+0.006
Edward+0.006
Neg logit contributions
 cleans-0.007
uffy-0.007
 outage-0.006
run-0.006
 exc-0.006
Token score
Token ID4776
Feature activation+1.22e-01

Pos logit contributions
 seas+0.053
edly+0.051
iece+0.050
Edward+0.047
ly+0.046
Neg logit contributions
 cleans-0.040
run-0.036
uffy-0.035
 outage-0.034
ric-0.032
Token.
Token ID13
Feature activation-3.01e-03

Pos logit contributions
edly+0.258
iece+0.257
 seas+0.246
Edward+0.242
oph+0.235
Neg logit contributions
 cleans-0.127
 outage-0.113
run-0.112
 need-0.106
uffy-0.102
Token Everyone
Token ID11075
Feature activation+5.83e-03

Pos logit contributions
 cleans+0.005
uffy+0.005
 outage+0.005
arter+0.005
run+0.005
Neg logit contributions
edly-0.004
iece-0.004
 seas-0.004
 Edward-0.004
 Avery-0.004
Token was
Token ID373
Feature activation-8.32e-03

Pos logit contributions
edly+0.010
iece+0.010
ly+0.009
 seas+0.009
Please+0.008
Neg logit contributions
 cleans-0.009
uffy-0.009
 drown-0.008
 outage-0.008
 slam-0.008
Token happy
Token ID3772
Feature activation+2.43e-02

Pos logit contributions
 cleans+0.013
uffy+0.012
 outage+0.011
run+0.011
 need+0.011
Neg logit contributions
edly-0.014
iece-0.014
 seas-0.013
Edward-0.012
ly-0.012
Token and
Token ID290
Feature activation-2.74e-03

Pos logit contributions
iece+0.046
edly+0.046
 seas+0.042
Edward+0.042
Prin+0.040
Neg logit contributions
 cleans-0.032
 outage-0.029
 need-0.029
uffy-0.028
run-0.028
Token and
Token ID290
Feature activation+1.36e-02

Pos logit contributions
iece+0.034
edly+0.032
Prin+0.028
Edward+0.028
Marie+0.028
Neg logit contributions
 cleans-0.021
 hose-0.020
 need-0.019
run-0.019
 exc-0.018
Token her
Token ID607
Feature activation-9.10e-03

Pos logit contributions
edly+0.027
iece+0.026
 seas+0.025
Edward+0.023
ly+0.023
Neg logit contributions
 cleans-0.018
uffy-0.016
 outage-0.016
run-0.015
 need-0.015
Token mom
Token ID1995
Feature activation-3.47e-02

Pos logit contributions
 outage+0.013
 cleans+0.012
run+0.011
uffy+0.010
 need+0.010
Neg logit contributions
edly-0.017
 seas-0.016
iece-0.016
Edward-0.014
 seven-0.014
Token got
Token ID1392
Feature activation-1.36e-02

Pos logit contributions
 outage+0.052
 cleans+0.052
uffy+0.048
 drown+0.048
arter+0.047
Neg logit contributions
edly-0.061
iece-0.059
ly-0.055
 seas-0.054
oph-0.050
Token a
Token ID257
Feature activation+2.83e-02

Pos logit contributions
 cleans+0.020
 need+0.018
run+0.017
 exc+0.017
uffy+0.016
Neg logit contributions
edly-0.026
iece-0.026
Edward-0.022
 seas-0.022
oph-0.021
Token sund
Token ID37437
Feature activation+1.21e-01

Pos logit contributions
edly+0.051
 seas+0.051
iece+0.050
Edward+0.046
ly+0.046
Neg logit contributions
 cleans-0.039
 outage-0.035
uffy-0.034
run-0.033
 need-0.032
Tokenae
Token ID3609
Feature activation+9.38e-02

Pos logit contributions
edly+0.141
iece+0.139
 seas+0.120
 oceans+0.114
Edward+0.113
Neg logit contributions
uffy-0.245
 cleans-0.239
run-0.234
 outage-0.231
 need-0.223
Token with
Token ID351
Feature activation+1.76e-02

Pos logit contributions
edly+0.177
iece+0.176
 seas+0.163
Edward+0.155
oph+0.149
Neg logit contributions
 cleans-0.127
uffy-0.112
run-0.111
 need-0.111
 outage-0.111
Token lots
Token ID6041
Feature activation-1.13e-04

Pos logit contributions
edly+0.026
iece+0.026
 seas+0.023
Edward+0.021
ly+0.021
Neg logit contributions
 cleans-0.032
 need-0.029
uffy-0.029
run-0.029
 outage-0.028
Token of
Token ID286
Feature activation+2.14e-02

Pos logit contributions
 cleans+0.000
uffy+0.000
 outage+0.000
ric+0.000
 drown+0.000
Neg logit contributions
edly-0.000
iece-0.000
 seas-0.000
ly-0.000
oph-0.000
Token topp
Token ID23126
Feature activation+1.04e-01

Pos logit contributions
iece+0.041
edly+0.041
 seas+0.035
Edward+0.035
oph+0.033
Neg logit contributions
 cleans-0.031
 need-0.026
run-0.026
uffy-0.026
 exc-0.025
Token him
Token ID683
Feature activation+3.06e-02

Pos logit contributions
edly+0.045
iece+0.044
Edward+0.037
 seas+0.037
 oceans+0.036
Neg logit contributions
 cleans-0.041
 need-0.036
 Kim-0.034
run-0.034
 hose-0.033
Token a
Token ID257
Feature activation+2.96e-02

Pos logit contributions
edly+0.043
iece+0.042
 seas+0.039
Edward+0.035
ly+0.035
Neg logit contributions
 cleans-0.056
uffy-0.052
 outage-0.052
run-0.050
 need-0.049
Token delicious
Token ID12625
Feature activation+5.73e-02

Pos logit contributions
edly+0.062
iece+0.062
 seas+0.056
Edward+0.054
ly+0.053
Neg logit contributions
 cleans-0.036
uffy-0.031
 outage-0.030
 need-0.030
run-0.029
Token ice
Token ID4771
Feature activation+3.90e-02

Pos logit contributions
iece+0.105
edly+0.104
 seas+0.092
Edward+0.089
Prin+0.085
Neg logit contributions
 cleans-0.084
uffy-0.076
 need-0.074
 outage-0.072
run-0.071
Token cream
Token ID8566
Feature activation+6.19e-02

Pos logit contributions
iece+0.071
edly+0.070
 seas+0.063
Edward+0.061
 Edward+0.059
Neg logit contributions
 cleans-0.056
uffy-0.052
 outage-0.049
run-0.049
 need-0.049
Token sund
Token ID37437
Feature activation+1.21e-01

Pos logit contributions
iece+0.118
edly+0.116
 seas+0.106
Edward+0.103
Prin+0.100
Neg logit contributions
 cleans-0.082
uffy-0.076
 need-0.072
 outage-0.071
run-0.070
Tokenae
Token ID3609
Feature activation+9.12e-02

Pos logit contributions
edly+0.136
iece+0.132
 oceans+0.114
 seas+0.111
Prin+0.109
Neg logit contributions
uffy-0.250
run-0.233
 cleans-0.231
 outage-0.230
ats-0.224
Token with
Token ID351
Feature activation+1.25e-02

Pos logit contributions
iece+0.178
edly+0.175
 seas+0.160
Edward+0.155
Prin+0.151
Neg logit contributions
 cleans-0.118
uffy-0.106
 need-0.105
 outage-0.104
run-0.104
Token lots
Token ID6041
Feature activation+5.14e-04

Pos logit contributions
edly+0.021
iece+0.021
 seas+0.018
Edward+0.017
ly+0.017
Neg logit contributions
 cleans-0.021
 need-0.018
run-0.018
uffy-0.018
 exc-0.017
Token of
Token ID286
Feature activation+2.00e-02

Pos logit contributions
edly+0.001
 seas+0.001
iece+0.001
ly+0.001
aw+0.001
Neg logit contributions
 cleans-0.001
uffy-0.001
 outage-0.001
ric-0.001
 drown-0.001
Token topp
Token ID23126
Feature activation+1.11e-01

Pos logit contributions
iece+0.041
edly+0.040
 seas+0.035
Edward+0.035
 Edward+0.033
Neg logit contributions
 cleans-0.027
 need-0.023
run-0.022
uffy-0.022
 exc-0.022
Token the
Token ID262
Feature activation+1.65e-02

Pos logit contributions
edly+0.060
iece+0.059
ly+0.053
 seas+0.052
Edward+0.051
Neg logit contributions
 cleans-0.032
 need-0.028
 hose-0.026
 exc-0.026
uffy-0.025
Token party
Token ID2151
Feature activation+3.05e-02

Pos logit contributions
edly+0.037
iece+0.034
ly+0.030
fully+0.029
red+0.028
Neg logit contributions
 hose-0.018
 cleans-0.018
 flood-0.018
 need-0.017
 switch-0.017
Token,
Token ID11
Feature activation+2.69e-02

Pos logit contributions
edly+0.064
iece+0.063
 seas+0.059
Edward+0.057
ly+0.055
Neg logit contributions
 cleans-0.035
uffy-0.031
 outage-0.030
 need-0.029
run-0.029
Token wearing
Token ID5762
Feature activation+1.68e-02

Pos logit contributions
edly+0.051
iece+0.050
 seas+0.047
ly+0.044
Edward+0.044
Neg logit contributions
 cleans-0.038
run-0.032
uffy-0.032
 need-0.032
 hose-0.032
Token a
Token ID257
Feature activation+6.20e-02

Pos logit contributions
iece+0.033
edly+0.033
Please+0.026
ly+0.026
Edward+0.026
Neg logit contributions
 cleans-0.024
 hose-0.020
 Kitty-0.020
 need-0.019
 Kim-0.019
Token princess
Token ID21752
Feature activation+1.20e-01

Pos logit contributions
edly+0.130
iece+0.128
ly+0.108
 seas+0.105
Please+0.103
Neg logit contributions
 cleans-0.078
uffy-0.071
 hose-0.070
 need-0.068
 outage-0.065
Token dress
Token ID6576
Feature activation+4.81e-02

Pos logit contributions
edly+0.221
iece+0.219
 seas+0.201
Edward+0.190
oph+0.188
Neg logit contributions
 cleans-0.170
uffy-0.159
 need-0.147
 outage-0.146
run-0.146
Token,
Token ID11
Feature activation+4.30e-02

Pos logit contributions
iece+0.100
edly+0.099
 seas+0.093
Edward+0.090
 Edward+0.086
Neg logit contributions
 cleans-0.056
uffy-0.051
run-0.047
 outage-0.046
 need-0.045
Token with
Token ID351
Feature activation+6.11e-03

Pos logit contributions
edly+0.080
iece+0.079
 seas+0.071
ly+0.071
oph+0.071
Neg logit contributions
 cleans-0.064
 hose-0.051
 exc-0.051
 slammed-0.051
 Kim-0.050
Token her
Token ID607
Feature activation+4.53e-03

Pos logit contributions
iece+0.011
edly+0.011
Edward+0.009
ly+0.009
Please+0.009
Neg logit contributions
 cleans-0.010
 need-0.009
 Kim-0.008
run-0.008
 hose-0.008
Token friends
Token ID2460
Feature activation-2.38e-03

Pos logit contributions
edly+0.008
iece+0.008
 seas+0.008
Edward+0.007
ly+0.007
Neg logit contributions
 cleans-0.007
 outage-0.006
uffy-0.006
run-0.006
 need-0.005
TokenPlease
Token ID5492
Feature activation+1.18e-02

Pos logit contributions
iece+0.023
 seas+0.023
edly+0.022
 knights+0.020
adies+0.019
Neg logit contributions
run-0.020
o-0.019
 need-0.019
 haven-0.018
 cleans-0.018
Token may
Token ID743
Feature activation+7.66e-03

Pos logit contributions
edly+0.022
iece+0.022
 seas+0.021
Edward+0.020
ly+0.020
Neg logit contributions
 cleans-0.015
 outage-0.014
uffy-0.014
run-0.013
 slammed-0.012
Token I
Token ID314
Feature activation+1.24e-02

Pos logit contributions
edly+0.009
iece+0.009
 Edward+0.009
Edward+0.009
 seas+0.009
Neg logit contributions
 cleans-0.015
 outage-0.013
uffy-0.013
run-0.013
ucker-0.012
Token have
Token ID423
Feature activation+5.23e-03

Pos logit contributions
edly+0.019
Please+0.019
 seas+0.019
 seven+0.018
ly+0.018
Neg logit contributions
 cleans-0.018
uffy-0.016
 outage-0.016
ucker-0.015
 dripping-0.015
Token a
Token ID257
Feature activation+2.00e-02

Pos logit contributions
iece+0.008
edly+0.008
 seas+0.007
Edward+0.007
ly+0.006
Neg logit contributions
 cleans-0.009
 need-0.008
run-0.008
uffy-0.008
 outage-0.008
Token sund
Token ID37437
Feature activation+1.20e-01

Pos logit contributions
edly+0.036
 seas+0.036
iece+0.035
Edward+0.033
ly+0.032
Neg logit contributions
 cleans-0.028
uffy-0.025
 outage-0.024
run-0.024
 need-0.022
Tokenae
Token ID3609
Feature activation+8.51e-02

Pos logit contributions
iece+0.120
edly+0.116
 seas+0.096
Edward+0.083
 oceans+0.083
Neg logit contributions
uffy-0.263
 cleans-0.263
run-0.255
 outage-0.254
 need-0.251
Token?"
Token ID1701
Feature activation+3.53e-02

Pos logit contributions
edly+0.152
iece+0.151
 seas+0.139
Edward+0.130
ly+0.128
Neg logit contributions
 cleans-0.127
uffy-0.113
 outage-0.110
run-0.109
 need-0.108
Token The
Token ID383
Feature activation-3.64e-02

Pos logit contributions
iece+0.068
edly+0.068
 seas+0.064
Edward+0.059
ly+0.058
Neg logit contributions
 cleans-0.048
uffy-0.042
run-0.041
 need-0.041
 outage-0.040
Token waitress
Token ID44511
Feature activation+1.48e-02

Pos logit contributions
 cleans+0.058
 need+0.054
uffy+0.051
 needs+0.050
 tells+0.049
Neg logit contributions
iece-0.064
edly-0.059
 seas-0.056
 oceans-0.050
Edward-0.050
Token smiled
Token ID13541
Feature activation+5.70e-02

Pos logit contributions
iece+0.028
edly+0.028
 seas+0.026
Edward+0.024
 oceans+0.024
Neg logit contributions
 cleans-0.021
uffy-0.018
run-0.018
 need-0.018
 outage-0.017
Token is
Token ID318
Feature activation+1.29e-02

Pos logit contributions
 cleans+0.043
uffy+0.037
 outage+0.035
run+0.035
 need+0.035
Neg logit contributions
edly-0.079
iece-0.079
 seas-0.073
Edward-0.069
ly-0.068
Token a
Token ID257
Feature activation+2.93e-02

Pos logit contributions
edly+0.020
iece+0.020
 seas+0.017
Edward+0.017
ly+0.017
Neg logit contributions
 cleans-0.023
 need-0.020
 outage-0.020
uffy-0.020
run-0.020
Token big
Token ID1263
Feature activation-1.51e-04

Pos logit contributions
edly+0.059
iece+0.058
 seas+0.054
Edward+0.051
ly+0.050
Neg logit contributions
 cleans-0.037
uffy-0.033
 outage-0.032
 need-0.031
run-0.031
Token spider
Token ID19230
Feature activation+4.70e-02

Pos logit contributions
 cleans+0.000
uffy+0.000
 outage+0.000
run+0.000
 need+0.000
Neg logit contributions
edly-0.000
iece-0.000
 seas-0.000
Edward-0.000
ly-0.000
Token on
Token ID319
Feature activation+2.29e-02

Pos logit contributions
edly+0.082
iece+0.081
 seas+0.074
ly+0.069
Edward+0.068
Neg logit contributions
 cleans-0.072
uffy-0.065
run-0.062
 outage-0.062
 need-0.061
Token your
Token ID534
Feature activation+1.19e-01

Pos logit contributions
edly+0.040
iece+0.040
 seas+0.037
Edward+0.034
ly+0.034
Neg logit contributions
 cleans-0.035
uffy-0.031
 need-0.031
 outage-0.031
run-0.030
Token pillow
Token ID28774
Feature activation+1.62e-02

Pos logit contributions
iece+0.241
edly+0.238
 seas+0.222
Edward+0.215
oph+0.211
Neg logit contributions
 cleans-0.148
uffy-0.131
 need-0.130
 outage-0.124
 hose-0.124
Token!"
Token ID2474
Feature activation+6.84e-02

Pos logit contributions
edly+0.033
iece+0.032
 seas+0.030
Edward+0.028
ly+0.028
Neg logit contributions
 cleans-0.020
uffy-0.018
 outage-0.017
run-0.017
 need-0.017
Token
Token ID198
Feature activation+1.43e-02

Pos logit contributions
iece+0.156
edly+0.150
 seas+0.147
 oceans+0.132
ly+0.132
Neg logit contributions
 cleans-0.072
 Kim-0.064
run-0.062
 Liz-0.062
 need-0.062
Token
Token ID198
Feature activation+1.01e-02

Pos logit contributions
edly+0.031
iece+0.031
 seas+0.029
ly+0.027
Edward+0.027
Neg logit contributions
 cleans-0.016
uffy-0.014
run-0.013
 outage-0.013
 need-0.013
TokenMax
Token ID11518
Feature activation+5.88e-03

Pos logit contributions
iece+0.015
edly+0.015
 seas+0.014
ly+0.012
 oceans+0.011
Neg logit contributions
 cleans-0.018
run-0.017
uffy-0.017
 exc-0.017
 outage-0.017
Token sand
Token ID6450
Feature activation+6.74e-02

Pos logit contributions
edly+0.077
iece+0.076
Edward+0.070
oph+0.068
adies+0.067
Neg logit contributions
 hose-0.050
 cleans-0.047
 need-0.044
 umbrella-0.043
uffy-0.042
Token,
Token ID11
Feature activation+3.76e-02

Pos logit contributions
iece+0.131
edly+0.129
Edward+0.124
Prin+0.123
Please+0.119
Neg logit contributions
 cleans-0.075
 hose-0.074
uffy-0.071
 dripping-0.066
run-0.064
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
edly+0.073
iece+0.072
oph+0.065
Edward+0.065
Prin+0.062
Neg logit contributions
 cleans-0.048
 hose-0.046
 exc-0.044
 need-0.043
 rake-0.043
Token deep
Token ID2769
Feature activation-2.15e-03

Pos logit contributions
edly+0.022
iece+0.021
 seas+0.019
Edward+0.019
oph+0.018
Neg logit contributions
 cleans-0.017
 need-0.015
run-0.015
 exc-0.014
 hose-0.014
Token blue
Token ID4171
Feature activation+6.35e-03

Pos logit contributions
 cleans+0.003
 need+0.003
uffy+0.003
run+0.003
 hose+0.003
Neg logit contributions
iece-0.004
edly-0.004
Edward-0.004
 seas-0.003
oph-0.003
Token seas
Token ID21547
Feature activation+1.19e-01

Pos logit contributions
edly+0.012
iece+0.012
Edward+0.011
Prin+0.010
 Edward+0.010
Neg logit contributions
 cleans-0.009
 hose-0.008
 need-0.008
uffy-0.008
run-0.007
Token.
Token ID13
Feature activation+7.76e-03

Pos logit contributions
iece+0.222
edly+0.219
 seas+0.202
Please+0.200
Edward+0.196
Neg logit contributions
 cleans-0.154
 outage-0.143
uffy-0.141
run-0.140
 need-0.137
Token
Token ID220
Feature activation-2.09e-02

Pos logit contributions
iece+0.016
edly+0.016
 seas+0.015
ly+0.014
Edward+0.014
Neg logit contributions
 cleans-0.009
run-0.008
uffy-0.008
 need-0.008
 Kim-0.008
Token
Token ID198
Feature activation-1.52e-03

Pos logit contributions
 cleans+0.031
 outage+0.028
 need+0.026
uffy+0.026
 slammed+0.026
Neg logit contributions
iece-0.037
edly-0.036
 seas-0.033
Edward-0.032
 Edward-0.031
Token
Token ID198
Feature activation-5.97e-03

Pos logit contributions
 cleans+0.001
run+0.001
uffy+0.001
 need+0.001
 outage+0.001
Neg logit contributions
edly-0.004
iece-0.004
 seas-0.003
ly-0.003
Edward-0.003
TokenOne
Token ID3198
Feature activation-1.30e-02

Pos logit contributions
run+0.009
 cleans+0.009
 exc+0.008
uffy+0.008
 Kitty+0.008
Neg logit contributions
iece-0.010
edly-0.010
 seas-0.009
ly-0.009
 oceans-0.008
Token Tim
Token ID5045
Feature activation-1.11e-02

Pos logit contributions
edly+0.040
iece+0.039
Edward+0.035
 seas+0.035
ly+0.034
Neg logit contributions
 cleans-0.018
 need-0.015
 slammed-0.015
 Kim-0.015
uffy-0.014
Tokenmy
Token ID1820
Feature activation+2.04e-03

Pos logit contributions
 cleans+0.014
 outage+0.013
run+0.012
uffy+0.012
 slam+0.011
Neg logit contributions
iece-0.022
edly-0.021
 seas-0.021
ly-0.020
Edward-0.019
Token got
Token ID1392
Feature activation-1.76e-02

Pos logit contributions
iece+0.004
edly+0.004
 seas+0.004
Edward+0.003
ly+0.003
Neg logit contributions
 cleans-0.003
uffy-0.003
 outage-0.002
run-0.002
 need-0.002
Token a
Token ID257
Feature activation+2.35e-02

Pos logit contributions
 cleans+0.024
 need+0.022
run+0.020
 exc+0.020
uffy+0.020
Neg logit contributions
edly-0.036
iece-0.035
oph-0.030
Edward-0.030
 seas-0.030
Token high
Token ID1029
Feature activation+3.40e-02

Pos logit contributions
 seas+0.041
edly+0.041
iece+0.041
Edward+0.037
ly+0.036
Neg logit contributions
 cleans-0.034
run-0.029
uffy-0.029
 outage-0.029
 need-0.028
Token score
Token ID4776
Feature activation+1.19e-01

Pos logit contributions
iece+0.072
edly+0.072
Edward+0.064
Please+0.061
 Edward+0.061
Neg logit contributions
 cleans-0.038
uffy-0.035
 need-0.035
 hose-0.035
 switch-0.034
Token!
Token ID0
Feature activation+1.14e-02

Pos logit contributions
edly+0.271
iece+0.263
 seas+0.257
Edward+0.252
oph+0.250
Neg logit contributions
 cleans-0.106
run-0.101
 need-0.092
 outage-0.092
 exc-0.085
Token He
Token ID679
Feature activation+1.41e-02

Pos logit contributions
iece+0.016
edly+0.015
 seas+0.014
Please+0.013
 Edward+0.013
Neg logit contributions
 cleans-0.021
 outage-0.020
uffy-0.019
 need-0.018
run-0.018
Token was
Token ID373
Feature activation-4.07e-03

Pos logit contributions
edly+0.030
iece+0.030
 seas+0.027
Edward+0.026
ly+0.025
Neg logit contributions
 cleans-0.017
uffy-0.015
 need-0.014
run-0.014
 outage-0.014
Token so
Token ID523
Feature activation-4.10e-02

Pos logit contributions
 cleans+0.006
uffy+0.006
 outage+0.005
run+0.005
 need+0.005
Neg logit contributions
iece-0.007
edly-0.007
 seas-0.007
Edward-0.006
 Edward-0.006
Token happy
Token ID3772
Feature activation+2.43e-02

Pos logit contributions
 cleans+0.064
uffy+0.057
 outage+0.057
run+0.055
 need+0.053
Neg logit contributions
edly-0.071
iece-0.070
 seas-0.066
Edward-0.062
 Edward-0.059
Token statue
Token ID15207
Feature activation-9.92e-03

Pos logit contributions
edly+0.012
iece+0.011
Edward+0.010
Prin+0.010
Please+0.010
Neg logit contributions
 need-0.006
 have-0.005
 needs-0.005
 exc-0.005
 cleans-0.005
Token made
Token ID925
Feature activation+3.11e-02

Pos logit contributions
 cleans+0.014
uffy+0.013
 outage+0.012
run+0.012
 need+0.012
Neg logit contributions
edly-0.018
iece-0.018
 seas-0.017
Edward-0.016
ly-0.016
Token by
Token ID416
Feature activation+3.13e-02

Pos logit contributions
edly+0.057
iece+0.055
 seas+0.050
Edward+0.048
 Edward+0.045
Neg logit contributions
 cleans-0.047
 need-0.042
uffy-0.042
run-0.041
 outage-0.041
Token a
Token ID257
Feature activation+2.97e-02

Pos logit contributions
edly+0.057
iece+0.055
 seas+0.051
Edward+0.049
ly+0.048
Neg logit contributions
 cleans-0.046
 need-0.043
 exc-0.040
run-0.040
 outage-0.039
Token famous
Token ID5863
Feature activation+6.20e-02

Pos logit contributions
edly+0.065
iece+0.064
 seas+0.055
Edward+0.054
ly+0.053
Neg logit contributions
 cleans-0.033
 need-0.031
 exc-0.030
uffy-0.029
 outage-0.029
Token artist
Token ID6802
Feature activation+1.18e-01

Pos logit contributions
edly+0.127
iece+0.126
Edward+0.110
Please+0.104
 seas+0.104
Neg logit contributions
 need-0.073
 cleans-0.069
 exc-0.068
 knock-0.068
 switch-0.066
Token a
Token ID257
Feature activation+3.49e-02

Pos logit contributions
edly+0.256
iece+0.249
 seas+0.240
Edward+0.230
oph+0.222
Neg logit contributions
 cleans-0.129
 outage-0.114
 need-0.111
uffy-0.108
run-0.105
Token long
Token ID890
Feature activation+4.90e-02

Pos logit contributions
edly+0.074
iece+0.073
 seas+0.062
ly+0.062
Edward+0.061
Neg logit contributions
 cleans-0.041
 need-0.038
 outage-0.037
 exc-0.037
uffy-0.036
Token time
Token ID640
Feature activation+6.58e-02

Pos logit contributions
edly+0.100
iece+0.097
 seas+0.088
Edward+0.085
 Edward+0.081
Neg logit contributions
 cleans-0.060
 need-0.058
 outage-0.055
 hose-0.053
uffy-0.052
Token ago
Token ID2084
Feature activation+6.27e-02

Pos logit contributions
edly+0.131
iece+0.130
 seas+0.121
Edward+0.114
ly+0.112
Neg logit contributions
 cleans-0.084
uffy-0.074
 outage-0.072
run-0.071
 need-0.071
Token."
Token ID526
Feature activation+2.96e-02

Pos logit contributions
edly+0.135
iece+0.135
 seas+0.127
Edward+0.122
ly+0.117
Neg logit contributions
 cleans-0.067
uffy-0.058
 need-0.057
 outage-0.057
run-0.056
TokenHow
Token ID2437
Feature activation-3.16e-02

Pos logit contributions
 seas+0.041
iece+0.039
ly+0.039
edly+0.039
 armour+0.036
Neg logit contributions
 cleans-0.034
 have-0.029
 sends-0.028
 need-0.028
 exc-0.027
Token about
Token ID546
Feature activation-3.69e-02

Pos logit contributions
 cleans+0.029
 need+0.023
uffy+0.023
 outage+0.023
run+0.022
Neg logit contributions
edly-0.077
iece-0.076
 seas-0.070
Edward-0.067
ly-0.067
Token we
Token ID356
Feature activation+6.67e-03

Pos logit contributions
 cleans+0.064
uffy+0.060
 outage+0.059
run+0.058
 need+0.056
Neg logit contributions
edly-0.055
iece-0.055
 seas-0.051
Edward-0.047
 Edward-0.046
Token make
Token ID787
Feature activation-1.69e-02

Pos logit contributions
iece+0.012
edly+0.012
 seas+0.012
Please+0.011
ly+0.011
Neg logit contributions
 cleans-0.009
uffy-0.009
run-0.008
 outage-0.008
 slammed-0.007
Token some
Token ID617
Feature activation+2.07e-02

Pos logit contributions
 cleans+0.026
 need+0.022
 tells+0.022
uffy+0.021
 hose+0.020
Neg logit contributions
edly-0.033
iece-0.030
ly-0.026
Please-0.026
Edward-0.025
Token mac
Token ID8352
Feature activation+1.18e-01

Pos logit contributions
edly+0.035
iece+0.034
 seas+0.031
Edward+0.029
ly+0.028
Neg logit contributions
 cleans-0.034
uffy-0.030
 outage-0.030
 need-0.030
run-0.029
Tokenaron
Token ID8045
Feature activation+3.69e-02

Pos logit contributions
iece+0.205
edly+0.199
 seas+0.194
Edward+0.177
Please+0.174
Neg logit contributions
 cleans-0.176
uffy-0.156
 need-0.151
 outage-0.151
run-0.141
Tokeni
Token ID72
Feature activation+2.64e-02

Pos logit contributions
edly+0.064
iece+0.063
 seas+0.058
Edward+0.054
Prin+0.051
Neg logit contributions
 cleans-0.058
uffy-0.053
 need-0.049
run-0.049
 outage-0.049
Token and
Token ID290
Feature activation+3.20e-02

Pos logit contributions
edly+0.051
iece+0.050
 seas+0.047
Edward+0.044
ly+0.042
Neg logit contributions
 cleans-0.036
uffy-0.032
 need-0.031
 outage-0.030
run-0.030
Token cheese
Token ID9891
Feature activation+4.07e-02

Pos logit contributions
iece+0.059
edly+0.057
 seas+0.050
Edward+0.048
oph+0.048
Neg logit contributions
 cleans-0.051
 need-0.045
 exc-0.042
 needs-0.041
run-0.041
Token for
Token ID329
Feature activation+4.59e-02

Pos logit contributions
edly+0.084
iece+0.084
 seas+0.077
Edward+0.072
ly+0.071
Neg logit contributions
 cleans-0.049
uffy-0.044
 need-0.042
 outage-0.042
run-0.040
TokenHe
Token ID1544
Feature activation+1.28e-02

Pos logit contributions
iece+0.004
 seas+0.004
edly+0.004
 oceans+0.004
ly+0.004
Neg logit contributions
 cleans-0.003
run-0.003
uffy-0.003
 outage-0.003
 exc-0.003
Token started
Token ID2067
Feature activation+1.15e-02

Pos logit contributions
iece+0.026
edly+0.026
 seas+0.024
Edward+0.023
ly+0.022
Neg logit contributions
 cleans-0.016
uffy-0.014
run-0.014
 need-0.014
 outage-0.013
Token acting
Token ID7205
Feature activation+2.62e-02

Pos logit contributions
edly+0.018
iece+0.018
 seas+0.016
Edward+0.015
ly+0.015
Neg logit contributions
 cleans-0.020
uffy-0.018
 outage-0.018
run-0.017
 need-0.017
Token like
Token ID588
Feature activation+2.42e-02

Pos logit contributions
iece+0.048
edly+0.048
 seas+0.044
Edward+0.042
oph+0.041
Neg logit contributions
 cleans-0.037
 need-0.033
run-0.033
 outage-0.032
uffy-0.031
Token a
Token ID257
Feature activation+1.91e-02

Pos logit contributions
iece+0.044
edly+0.042
Edward+0.036
oph+0.035
 seas+0.035
Neg logit contributions
 cleans-0.037
 need-0.033
run-0.032
 Kitty-0.031
 Kim-0.031
Token chef
Token ID21221
Feature activation+1.17e-01

Pos logit contributions
edly+0.033
 seas+0.031
iece+0.031
Edward+0.029
ly+0.028
Neg logit contributions
 cleans-0.029
uffy-0.026
run-0.026
 outage-0.025
ric-0.023
Token,
Token ID11
Feature activation+3.33e-02

Pos logit contributions
edly+0.218
iece+0.217
 seas+0.201
Edward+0.188
ly+0.184
Neg logit contributions
 cleans-0.165
uffy-0.146
 outage-0.143
 need-0.142
run-0.142
Token grabbing
Token ID23256
Feature activation+2.72e-02

Pos logit contributions
iece+0.060
edly+0.060
 seas+0.054
Edward+0.051
ly+0.051
Neg logit contributions
 cleans-0.050
run-0.044
 need-0.044
 outage-0.042
uffy-0.042
Token different
Token ID1180
Feature activation+4.45e-02

Pos logit contributions
edly+0.052
iece+0.052
Edward+0.043
adies+0.043
Please+0.043
Neg logit contributions
 cleans-0.037
run-0.034
 need-0.034
 Kim-0.031
 hose-0.031
Token ingredients
Token ID9391
Feature activation+5.30e-02

Pos logit contributions
edly+0.077
iece+0.076
 seas+0.069
Edward+0.065
ly+0.063
Neg logit contributions
 cleans-0.070
uffy-0.062
 outage-0.061
 need-0.061
run-0.060
Token and
Token ID290
Feature activation+1.43e-02

Pos logit contributions
edly+0.088
iece+0.086
 seas+0.078
ly+0.075
Edward+0.071
Neg logit contributions
 cleans-0.088
uffy-0.079
 outage-0.076
run-0.074
 need-0.073
Token need
Token ID761
Feature activation-3.04e-02

Pos logit contributions
iece+0.096
edly+0.093
 seas+0.087
ly+0.083
Edward+0.083
Neg logit contributions
 cleans-0.058
uffy-0.055
run-0.051
 outage-0.050
 slammed-0.045
Token to
Token ID284
Feature activation+6.74e-03

Pos logit contributions
 cleans+0.040
uffy+0.037
run+0.034
 outage+0.034
 exc+0.032
Neg logit contributions
edly-0.058
iece-0.058
 seas-0.055
ly-0.051
Edward-0.050
Token make
Token ID787
Feature activation-5.39e-03

Pos logit contributions
iece+0.014
edly+0.014
 seas+0.013
Edward+0.012
ly+0.012
Neg logit contributions
 cleans-0.008
uffy-0.007
run-0.007
 outage-0.007
 need-0.006
Token an
Token ID281
Feature activation+1.30e-02

Pos logit contributions
 cleans+0.008
 need+0.007
uffy+0.007
 outage+0.007
run+0.007
Neg logit contributions
edly-0.010
iece-0.009
 seas-0.009
Edward-0.008
ly-0.008
Token o
Token ID267
Feature activation+6.21e-02

Pos logit contributions
edly+0.023
iece+0.023
 seas+0.021
Edward+0.020
ly+0.020
Neg logit contributions
 cleans-0.019
uffy-0.017
 outage-0.017
 need-0.017
run-0.016
Tokenme
Token ID1326
Feature activation+1.17e-01

Pos logit contributions
edly+0.105
iece+0.104
 seas+0.095
Edward+0.088
ly+0.088
Neg logit contributions
 cleans-0.099
uffy-0.087
run-0.087
 outage-0.087
 need-0.084
Tokenlette
Token ID21348
Feature activation+8.08e-02

Pos logit contributions
edly+0.213
iece+0.211
 seas+0.195
Edward+0.182
ly+0.179
Neg logit contributions
 cleans-0.172
uffy-0.154
 outage-0.150
run-0.149
 need-0.147
Token?".
Token ID43634
Feature activation+5.27e-02

Pos logit contributions
iece+0.172
edly+0.171
 seas+0.161
ly+0.151
Edward+0.151
Neg logit contributions
 cleans-0.091
uffy-0.079
run-0.076
 outage-0.076
 need-0.070
Token He
Token ID679
Feature activation+1.88e-02

Pos logit contributions
edly+0.102
iece+0.101
 seas+0.093
Edward+0.088
ly+0.086
Neg logit contributions
 cleans-0.071
uffy-0.063
 outage-0.062
 need-0.059
run-0.059
Token was
Token ID373
Feature activation-1.62e-03

Pos logit contributions
iece+0.040
edly+0.039
 seas+0.037
Edward+0.035
 oceans+0.034
Neg logit contributions
 cleans-0.023
run-0.019
uffy-0.018
 need-0.018
 exc-0.018
Token very
Token ID845
Feature activation-3.96e-02

Pos logit contributions
 cleans+0.003
uffy+0.002
 outage+0.002
run+0.002
 need+0.002
Neg logit contributions
edly-0.003
iece-0.003
 seas-0.002
Edward-0.002
 Edward-0.002
Token and
Token ID290
Feature activation+1.29e-02

Pos logit contributions
 cleans+0.017
 need+0.015
 outage+0.015
run+0.015
uffy+0.015
Neg logit contributions
edly-0.023
iece-0.023
 seas-0.021
Edward-0.020
oph-0.019
Token hungry
Token ID14720
Feature activation-2.30e-02

Pos logit contributions
edly+0.026
iece+0.026
 seas+0.024
ly+0.023
Edward+0.022
Neg logit contributions
 cleans-0.016
uffy-0.015
 outage-0.014
run-0.013
 need-0.013
Token.
Token ID13
Feature activation+6.35e-03

Pos logit contributions
 cleans+0.022
 need+0.019
run+0.018
 outage+0.018
 exc+0.017
Neg logit contributions
edly-0.052
iece-0.051
 seas-0.050
Edward-0.048
oph-0.048
Token She
Token ID1375
Feature activation-1.50e-02

Pos logit contributions
edly+0.013
iece+0.013
 seas+0.012
ly+0.011
Edward+0.011
Neg logit contributions
 cleans-0.008
uffy-0.007
 need-0.007
run-0.007
 outage-0.007
Token said
Token ID531
Feature activation+5.49e-04

Pos logit contributions
 cleans+0.019
uffy+0.016
 need+0.016
 outage+0.015
run+0.015
Neg logit contributions
iece-0.031
edly-0.031
 seas-0.029
Edward-0.027
ly-0.026
Token ow
Token ID12334
Feature activation-1.51e-01

Pos logit contributions
edly+0.001
iece+0.001
 seas+0.001
oph+0.001
Edward+0.001
Neg logit contributions
 cleans-0.001
 exc-0.001
 Kitty-0.001
 Kim-0.001
 need-0.001
Tokenls
Token ID7278
Feature activation-5.45e-02

Pos logit contributions
 cleans+0.189
uffy+0.165
 outage+0.160
run+0.158
 need+0.157
Neg logit contributions
edly-0.307
iece-0.304
 seas-0.283
Edward-0.267
ly-0.263
Token like
Token ID588
Feature activation+2.11e-02

Pos logit contributions
 cleans+0.058
uffy+0.052
 outage+0.050
run+0.048
 need+0.046
Neg logit contributions
edly-0.118
iece-0.118
 seas-0.109
ly-0.105
Edward-0.102
Token to
Token ID284
Feature activation+2.36e-03

Pos logit contributions
iece+0.039
edly+0.039
oph+0.033
 seas+0.033
Edward+0.032
Neg logit contributions
 cleans-0.032
 need-0.028
run-0.027
 exc-0.027
uffy-0.026
Token eat
Token ID4483
Feature activation-1.60e-02

Pos logit contributions
edly+0.005
iece+0.005
 seas+0.005
Edward+0.004
ly+0.004
Neg logit contributions
 cleans-0.003
uffy-0.002
 outage-0.002
run-0.002
 need-0.002
Token mice
Token ID10693
Feature activation-2.55e-02

Pos logit contributions
 cleans+0.024
 need+0.021
uffy+0.021
run+0.020
 exc+0.020
Neg logit contributions
iece-0.029
edly-0.029
oph-0.025
Edward-0.025
 seas-0.025
Tokenily
Token ID813
Feature activation+1.16e-02

Pos logit contributions
edly+0.011
iece+0.011
 seas+0.010
Edward+0.008
 Edward+0.008
Neg logit contributions
 cleans-0.023
uffy-0.022
run-0.021
 outage-0.021
 need-0.021
Token said
Token ID531
Feature activation+4.20e-03

Pos logit contributions
iece+0.024
edly+0.024
 seas+0.022
Edward+0.021
ly+0.020
Neg logit contributions
 cleans-0.015
uffy-0.012
 need-0.012
 slammed-0.012
 outage-0.011
Token,
Token ID11
Feature activation-1.86e-03

Pos logit contributions
iece+0.011
edly+0.011
 seas+0.010
Please+0.010
oph+0.010
Neg logit contributions
 cleans-0.003
uffy-0.002
 Kitty-0.002
run-0.002
 tells-0.002
Token "
Token ID366
Feature activation+2.26e-02

Pos logit contributions
 cleans+0.002
uffy+0.002
run+0.002
 outage+0.002
 need+0.002
Neg logit contributions
iece-0.004
edly-0.004
 seas-0.004
Edward-0.004
ly-0.004
TokenB
Token ID33
Feature activation-4.25e-02

Pos logit contributions
iece+0.038
 seas+0.037
edly+0.035
adies+0.033
ly+0.033
Neg logit contributions
 cleans-0.032
 Kitty-0.031
 Mitt-0.029
 have-0.029
 tow-0.028
Tokenrun
Token ID5143
Feature activation-1.42e-01

Pos logit contributions
 cleans+0.060
uffy+0.052
 outage+0.052
 need+0.051
run+0.050
Neg logit contributions
edly-0.080
iece-0.079
 seas-0.073
Edward-0.069
ly-0.068
Tokeno
Token ID78
Feature activation-5.98e-02

Pos logit contributions
 cleans+0.218
uffy+0.196
 outage+0.194
run+0.189
 need+0.187
Neg logit contributions
edly-0.240
iece-0.239
 seas-0.221
Edward-0.206
ly-0.204
Token,
Token ID11
Feature activation-3.59e-03

Pos logit contributions
 cleans+0.087
 outage+0.083
run+0.080
uffy+0.073
 exc+0.073
Neg logit contributions
edly-0.100
iece-0.100
ly-0.092
 seas-0.091
Edward-0.090
Token you
Token ID345
Feature activation+4.25e-02

Pos logit contributions
 cleans+0.006
 need+0.005
uffy+0.005
run+0.005
 outage+0.005
Neg logit contributions
edly-0.006
iece-0.006
 seas-0.005
Edward-0.005
ly-0.005
Token are
Token ID389
Feature activation-1.46e-02

Pos logit contributions
 seas+0.085
iece+0.085
edly+0.082
Edward+0.081
 Edward+0.079
Neg logit contributions
 cleans-0.047
run-0.045
 outage-0.045
uffy-0.045
 dripping-0.039
Token a
Token ID257
Feature activation+9.23e-03

Pos logit contributions
 cleans+0.024
uffy+0.021
 outage+0.021
run+0.021
 need+0.020
Neg logit contributions
edly-0.025
iece-0.024
 seas-0.022
Edward-0.021
ly-0.020
Token
Token ID198
Feature activation-4.81e-03

Pos logit contributions
 cleans+0.005
uffy+0.005
 outage+0.005
run+0.004
 need+0.004
Neg logit contributions
edly-0.004
iece-0.004
 seas-0.004
Edward-0.003
 Edward-0.003
Token
Token ID198
Feature activation-8.34e-03

Pos logit contributions
 cleans+0.007
uffy+0.006
 outage+0.006
run+0.006
 need+0.006
Neg logit contributions
edly-0.009
iece-0.009
 seas-0.008
Edward-0.008
 Edward-0.008
TokenJack
Token ID14295
Feature activation+2.29e-02

Pos logit contributions
 cleans+0.015
 need+0.014
 exc+0.013
run+0.013
 have+0.013
Neg logit contributions
edly-0.012
iece-0.012
 seas-0.010
ly-0.009
 oceans-0.009
Token thanked
Token ID26280
Feature activation-5.01e-03

Pos logit contributions
iece+0.050
edly+0.048
 seas+0.047
Edward+0.043
Please+0.042
Neg logit contributions
 cleans-0.026
uffy-0.021
 need-0.021
 needs-0.020
run-0.020
Token the
Token ID262
Feature activation-4.32e-02

Pos logit contributions
 cleans+0.005
 need+0.005
 Kim+0.004
 exc+0.004
 have+0.004
Neg logit contributions
edly-0.011
iece-0.011
 seas-0.010
ly-0.010
Edward-0.010
Token ow
Token ID12334
Feature activation-1.38e-01

Pos logit contributions
 cleans+0.055
 need+0.049
uffy+0.046
 exc+0.046
 hose+0.046
Neg logit contributions
edly-0.089
iece-0.089
 seas-0.080
ly-0.076
oph-0.074
Tokenls
Token ID7278
Feature activation-4.38e-02

Pos logit contributions
 cleans+0.199
uffy+0.175
 outage+0.173
run+0.170
 need+0.168
Neg logit contributions
edly-0.256
iece-0.255
 seas-0.237
Edward-0.220
ly-0.220
Token and
Token ID290
Feature activation+1.04e-02

Pos logit contributions
 cleans+0.058
 need+0.050
uffy+0.050
 outage+0.048
run+0.048
Neg logit contributions
edly-0.087
iece-0.085
 seas-0.079
Edward-0.075
Please-0.073
Token he
Token ID339
Feature activation+2.92e-02

Pos logit contributions
edly+0.019
iece+0.019
 seas+0.018
Edward+0.017
ly+0.016
Neg logit contributions
 cleans-0.015
uffy-0.013
 outage-0.013
run-0.013
 need-0.012
Token waved
Token ID26834
Feature activation+1.04e-02

Pos logit contributions
edly+0.055
iece+0.054
 seas+0.050
Edward+0.047
ly+0.046
Neg logit contributions
 cleans-0.041
uffy-0.036
 outage-0.036
run-0.035
 need-0.035
Token goodbye
Token ID24829
Feature activation+3.07e-02

Pos logit contributions
iece+0.019
edly+0.018
Prin+0.017
oph+0.017
Edward+0.017
Neg logit contributions
run-0.013
 need-0.013
 cleans-0.012
 know-0.011
 glad-0.011
Token,
Token ID11
Feature activation-7.12e-03

Pos logit contributions
 cleans+0.013
run+0.010
uffy+0.010
 need+0.010
 exc+0.009
Neg logit contributions
edly-0.030
iece-0.030
 seas-0.028
oph-0.028
Edward-0.027
Token "
Token ID366
Feature activation+2.18e-02

Pos logit contributions
 cleans+0.008
uffy+0.007
run+0.007
 outage+0.007
 need+0.007
Neg logit contributions
edly-0.015
iece-0.015
 seas-0.014
Edward-0.013
ly-0.013
TokenO
Token ID46
Feature activation-2.70e-02

Pos logit contributions
 seas+0.038
edly+0.035
iece+0.033
 Edward+0.032
ly+0.032
Neg logit contributions
 exc-0.032
 drown-0.031
 cleans-0.030
 need-0.030
 damaged-0.029
Tokenw
Token ID86
Feature activation+1.58e-02

Pos logit contributions
 cleans+0.056
 outage+0.051
run+0.051
 need+0.050
uffy+0.049
Neg logit contributions
iece-0.033
edly-0.033
 seas-0.029
ly-0.026
Edward-0.026
Token,
Token ID11
Feature activation-4.90e-03

Pos logit contributions
iece+0.028
edly+0.027
ly+0.025
 seas+0.025
Edward+0.024
Neg logit contributions
 cleans-0.024
 outage-0.021
 need-0.020
 exc-0.020
run-0.019
Token ow
Token ID12334
Feature activation-1.38e-01

Pos logit contributions
 cleans+0.007
 outage+0.006
uffy+0.006
run+0.006
 need+0.006
Neg logit contributions
iece-0.009
edly-0.009
 seas-0.008
ly-0.008
Edward-0.008
Token,
Token ID11
Feature activation+3.92e-04

Pos logit contributions
 cleans+0.258
 outage+0.233
ric+0.217
 tow+0.210
run+0.210
Neg logit contributions
ly-0.186
iece-0.186
 seas-0.176
edly-0.159
aw-0.150
Token ow
Token ID12334
Feature activation-1.27e-01

Pos logit contributions
iece+0.001
edly+0.001
 seas+0.001
ly+0.001
Edward+0.001
Neg logit contributions
 cleans-0.001
uffy-0.000
 outage-0.000
run-0.000
 need-0.000
Token.
Token ID13
Feature activation-3.27e-02

Pos logit contributions
 cleans+0.241
 outage+0.213
ric+0.207
run+0.203
 slam+0.196
Neg logit contributions
ly-0.172
iece-0.171
 seas-0.163
edly-0.152
aw-0.147
Token It
Token ID632
Feature activation-1.69e-02

Pos logit contributions
 cleans+0.057
 outage+0.053
uffy+0.053
run+0.050
 need+0.050
Neg logit contributions
edly-0.048
iece-0.047
 seas-0.041
Edward-0.039
ly-0.039
Token hurts
Token ID20406
Feature activation-3.15e-02

Pos logit contributions
 cleans+0.018
 outage+0.017
run+0.017
uffy+0.016
 tow+0.015
Neg logit contributions
iece-0.032
edly-0.032
ly-0.031
 seas-0.030
Please-0.030
Token
Token ID198
Feature activation-2.32e-03

Pos logit contributions
edly+0.001
iece+0.001
Edward+0.001
Please+0.001
Cl+0.001
Neg logit contributions
 cleans-0.001
 outage-0.001
uffy-0.001
 dripping-0.001
 need-0.001
Token"
Token ID1
Feature activation+4.05e-02

Pos logit contributions
 cleans+0.004
uffy+0.004
 outage+0.004
run+0.004
 need+0.004
Neg logit contributions
edly-0.003
iece-0.003
 seas-0.003
Edward-0.003
ly-0.003
TokenO
Token ID46
Feature activation-2.66e-02

Pos logit contributions
iece+0.058
edly+0.057
 seas+0.057
ly+0.051
 Edward+0.046
Neg logit contributions
 cleans-0.078
uffy-0.069
 exc-0.068
 Kitty-0.067
 hose-0.066
Tokenw
Token ID86
Feature activation+1.61e-02

Pos logit contributions
 cleans+0.065
run+0.061
 outage+0.059
 need+0.059
 tow+0.058
Neg logit contributions
iece-0.023
edly-0.023
 seas-0.018
ly-0.016
Edward-0.015
Token,
Token ID11
Feature activation-7.93e-03

Pos logit contributions
iece+0.028
edly+0.026
ly+0.025
 seas+0.025
Edward+0.023
Neg logit contributions
 cleans-0.024
 outage-0.022
 need-0.021
 exc-0.021
run-0.020
Token ow
Token ID12334
Feature activation-1.37e-01

Pos logit contributions
 cleans+0.011
 outage+0.010
run+0.010
uffy+0.009
ucker+0.009
Neg logit contributions
iece-0.014
edly-0.014
 seas-0.013
ly-0.012
Please-0.012
Token,
Token ID11
Feature activation-4.80e-03

Pos logit contributions
 cleans+0.265
 outage+0.247
run+0.233
 tow+0.231
ric+0.224
Neg logit contributions
ly-0.168
iece-0.167
 seas-0.155
edly-0.145
 seven-0.134
Token ow
Token ID12334
Feature activation-1.29e-01

Pos logit contributions
 cleans+0.006
 outage+0.006
run+0.005
uffy+0.005
 need+0.005
Neg logit contributions
iece-0.009
edly-0.009
 seas-0.009
ly-0.008
Please-0.008
Token!
Token ID0
Feature activation-2.31e-02

Pos logit contributions
 cleans+0.254
 outage+0.230
run+0.229
 tow+0.220
ric+0.219
Neg logit contributions
ly-0.160
iece-0.155
 seas-0.147
edly-0.140
aw-0.138
Token My
Token ID2011
Feature activation+3.36e-02

Pos logit contributions
 cleans+0.041
 outage+0.039
uffy+0.038
run+0.037
 need+0.036
Neg logit contributions
iece-0.031
edly-0.031
 seas-0.026
Please-0.026
ly-0.025
Token toe
Token ID21189
Feature activation-4.92e-02

Pos logit contributions
edly+0.059
iece+0.058
 seas+0.055
ly+0.050
Edward+0.048
Neg logit contributions
 cleans-0.050
 outage-0.042
uffy-0.042
run-0.041
 need-0.041
Token its
Token ID663
Feature activation+1.28e-02

Pos logit contributions
 cleans+0.005
uffy+0.005
 outage+0.005
 slammed+0.005
run+0.005
Neg logit contributions
iece-0.005
edly-0.005
 seas-0.005
ly-0.005
 Edward-0.005
Token toy
Token ID13373
Feature activation-1.59e-02

Pos logit contributions
edly+0.024
iece+0.024
 seas+0.023
ly+0.021
Edward+0.021
Neg logit contributions
 cleans-0.018
uffy-0.016
 outage-0.015
run-0.015
 need-0.014
Token fixed
Token ID5969
Feature activation+6.39e-03

Pos logit contributions
 cleans+0.021
uffy+0.019
 outage+0.018
 need+0.018
run+0.018
Neg logit contributions
edly-0.031
iece-0.030
 seas-0.028
Edward-0.027
ly-0.026
Token.
Token ID13
Feature activation-1.94e-03

Pos logit contributions
edly+0.012
iece+0.012
 seas+0.011
Edward+0.010
ly+0.010
Neg logit contributions
 cleans-0.009
uffy-0.008
 outage-0.008
 need-0.008
run-0.008
Token Thank
Token ID6952
Feature activation+5.47e-02

Pos logit contributions
 cleans+0.003
uffy+0.003
 outage+0.003
run+0.003
 need+0.002
Neg logit contributions
edly-0.003
iece-0.003
 seas-0.003
Edward-0.003
ly-0.003
Tokenful
Token ID913
Feature activation-1.37e-01

Pos logit contributions
iece+0.110
edly+0.106
 seas+0.099
oph+0.096
smith+0.091
Neg logit contributions
 Kitty-0.061
 have-0.060
 Kim-0.057
 need-0.053
 named-0.053
Token,
Token ID11
Feature activation-1.89e-02

Pos logit contributions
 cleans+0.176
uffy+0.155
 outage+0.150
run+0.149
 need+0.148
Neg logit contributions
edly-0.272
iece-0.270
 seas-0.250
Edward-0.236
ly-0.232
Token it
Token ID340
Feature activation-2.53e-02

Pos logit contributions
 cleans+0.029
uffy+0.027
 outage+0.026
run+0.025
ats+0.024
Neg logit contributions
edly-0.031
iece-0.030
 seas-0.029
 Edward-0.027
Edward-0.027
Token flew
Token ID13112
Feature activation-1.91e-03

Pos logit contributions
 cleans+0.035
uffy+0.031
 outage+0.031
run+0.030
 need+0.030
Neg logit contributions
edly-0.048
iece-0.047
 seas-0.043
Edward-0.041
ly-0.041
Token away
Token ID1497
Feature activation+4.43e-03

Pos logit contributions
run+0.002
 cleans+0.002
 need+0.002
uffy+0.002
 Kitty+0.002
Neg logit contributions
edly-0.004
iece-0.004
 seas-0.003
Edward-0.003
Please-0.003
Token with
Token ID351
Feature activation-4.00e-03

Pos logit contributions
iece+0.008
edly+0.008
 seas+0.007
Edward+0.007
ly+0.007
Neg logit contributions
 cleans-0.006
uffy-0.006
 outage-0.006
 need-0.006
run-0.006
Token,
Token ID11
Feature activation-4.68e-03

Pos logit contributions
 cleans+0.011
uffy+0.009
 need+0.009
run+0.009
 outage+0.009
Neg logit contributions
edly-0.023
iece-0.022
 seas-0.021
Edward-0.020
oph-0.020
Token "
Token ID366
Feature activation+2.18e-02

Pos logit contributions
 cleans+0.006
uffy+0.006
 outage+0.006
 need+0.005
run+0.005
Neg logit contributions
edly-0.009
iece-0.009
 seas-0.008
Edward-0.007
 Edward-0.007
TokenO
Token ID46
Feature activation-2.21e-02

Pos logit contributions
 seas+0.037
edly+0.036
 Edward+0.034
iece+0.034
 Amber+0.033
Neg logit contributions
 cleans-0.033
 exc-0.032
 need-0.032
 drown-0.031
 ruined-0.029
Tokenw
Token ID86
Feature activation+1.88e-02

Pos logit contributions
 cleans+0.051
run+0.047
 outage+0.046
 need+0.046
uffy+0.045
Neg logit contributions
iece-0.022
edly-0.021
 seas-0.018
ly-0.016
Edward-0.016
Token,
Token ID11
Feature activation-2.67e-03

Pos logit contributions
iece+0.034
edly+0.033
 seas+0.031
ly+0.031
Edward+0.029
Neg logit contributions
 cleans-0.027
 outage-0.025
 need-0.023
 exc-0.023
run-0.022
Token ow
Token ID12334
Feature activation-1.37e-01

Pos logit contributions
 cleans+0.003
 outage+0.003
run+0.003
uffy+0.003
ucker+0.003
Neg logit contributions
iece-0.005
 seas-0.005
edly-0.005
Edward-0.004
ly-0.004
Token,
Token ID11
Feature activation+2.10e-03

Pos logit contributions
 cleans+0.255
 outage+0.237
run+0.215
ric+0.211
 slammed+0.210
Neg logit contributions
iece-0.188
ly-0.177
 seas-0.171
edly-0.153
aw-0.146
Token ow
Token ID12334
Feature activation-1.26e-01

Pos logit contributions
iece+0.004
edly+0.004
 seas+0.004
ly+0.004
Edward+0.004
Neg logit contributions
 cleans-0.003
 outage-0.002
uffy-0.002
run-0.002
 need-0.002
Token.
Token ID13
Feature activation-2.87e-02

Pos logit contributions
 cleans+0.233
 outage+0.209
run+0.199
ric+0.195
 tow+0.189
Neg logit contributions
iece-0.179
ly-0.172
 seas-0.165
edly-0.155
aw-0.150
Token My
Token ID2011
Feature activation+3.40e-02

Pos logit contributions
 cleans+0.049
 outage+0.045
uffy+0.045
run+0.043
 need+0.042
Neg logit contributions
edly-0.043
iece-0.043
 seas-0.037
ly-0.035
Edward-0.035
Token arm
Token ID3211
Feature activation-7.99e-02

Pos logit contributions
edly+0.064
iece+0.063
 seas+0.060
ly+0.054
Edward+0.054
Neg logit contributions
 cleans-0.047
uffy-0.041
 outage-0.041
run-0.039
 need-0.039
Token
Token ID198
Feature activation-1.94e-03

Pos logit contributions
iece+0.000
edly+0.000
Edward+0.000
J+0.000
Please+0.000
Neg logit contributions
 cleans-0.000
 outage-0.000
uffy-0.000
 flood-0.000
 dripping-0.000
Token"
Token ID1
Feature activation+3.90e-02

Pos logit contributions
 cleans+0.004
uffy+0.004
 outage+0.004
run+0.004
 need+0.004
Neg logit contributions
edly-0.002
iece-0.002
 seas-0.002
Edward-0.002
ly-0.002
TokenO
Token ID46
Feature activation-2.43e-02

Pos logit contributions
iece+0.062
edly+0.061
 seas+0.059
ly+0.053
 Edward+0.051
Neg logit contributions
 cleans-0.070
uffy-0.062
 exc-0.061
 need-0.059
 ruined-0.059
Tokenw
Token ID86
Feature activation+1.59e-02

Pos logit contributions
 cleans+0.059
run+0.055
 outage+0.054
 need+0.054
 exc+0.053
Neg logit contributions
iece-0.020
edly-0.020
 seas-0.017
ly-0.014
Edward-0.014
Token,
Token ID11
Feature activation-6.23e-03

Pos logit contributions
iece+0.029
edly+0.028
 seas+0.026
ly+0.026
Edward+0.025
Neg logit contributions
 cleans-0.023
 outage-0.021
 need-0.019
run-0.019
 exc-0.019
Token ow
Token ID12334
Feature activation-1.36e-01

Pos logit contributions
 cleans+0.008
 outage+0.008
run+0.007
uffy+0.007
ucker+0.007
Neg logit contributions
iece-0.012
edly-0.011
 seas-0.011
ly-0.010
Edward-0.010
Token,
Token ID11
Feature activation-2.78e-03

Pos logit contributions
 cleans+0.257
 outage+0.238
run+0.220
ric+0.218
 tow+0.214
Neg logit contributions
iece-0.175
ly-0.171
 seas-0.166
edly-0.150
 seven-0.144
Token ow
Token ID12334
Feature activation-1.28e-01

Pos logit contributions
 cleans+0.003
 outage+0.003
uffy+0.003
run+0.003
 need+0.003
Neg logit contributions
iece-0.006
edly-0.005
 seas-0.005
ly-0.005
Edward-0.005
Token!"
Token ID2474
Feature activation+5.59e-02

Pos logit contributions
 cleans+0.248
 outage+0.223
run+0.219
ric+0.216
 tow+0.208
Neg logit contributions
ly-0.161
iece-0.157
 seas-0.152
edly-0.141
aw-0.136
Token Lily
Token ID20037
Feature activation+1.83e-02

Pos logit contributions
iece+0.124
edly+0.121
 seas+0.118
Edward+0.110
 oceans+0.109
Neg logit contributions
 cleans-0.064
 need-0.055
 slammed-0.053
uffy-0.053
 Kim-0.051
Token said
Token ID531
Feature activation+2.11e-02

Pos logit contributions
edly+0.036
iece+0.036
 seas+0.035
Edward+0.033
 Edward+0.032
Neg logit contributions
 cleans-0.024
uffy-0.021
 slammed-0.020
run-0.020
 need-0.020
Token
Token ID198
Feature activation+1.51e-03

Pos logit contributions
edly+0.013
iece+0.013
 seas+0.012
Edward+0.011
ly+0.011
Neg logit contributions
 cleans-0.008
uffy-0.007
 outage-0.007
 need-0.006
run-0.006
Token"
Token ID1
Feature activation+4.66e-02

Pos logit contributions
iece+0.002
edly+0.002
 seas+0.002
ly+0.002
oph+0.002
Neg logit contributions
 cleans-0.003
run-0.002
uffy-0.002
 need-0.002
 exc-0.002
TokenO
Token ID46
Feature activation-2.38e-02

Pos logit contributions
iece+0.071
 seas+0.068
edly+0.066
ly+0.063
adies+0.055
Neg logit contributions
 cleans-0.083
 exc-0.075
 hose-0.072
run-0.072
 Kitty-0.071
Tokenw
Token ID86
Feature activation+2.40e-02

Pos logit contributions
 cleans+0.044
uffy+0.040
 outage+0.040
run+0.039
 need+0.039
Neg logit contributions
edly-0.034
iece-0.034
 seas-0.030
Edward-0.028
ly-0.027
Token,
Token ID11
Feature activation-4.79e-03

Pos logit contributions
iece+0.044
edly+0.043
 seas+0.040
ly+0.040
Edward+0.038
Neg logit contributions
 cleans-0.034
 outage-0.030
 need-0.029
uffy-0.028
run-0.028
Token ow
Token ID12334
Feature activation-1.36e-01

Pos logit contributions
 cleans+0.006
 outage+0.006
uffy+0.006
run+0.005
 need+0.005
Neg logit contributions
iece-0.009
edly-0.009
 seas-0.008
Edward-0.008
ly-0.008
Token,
Token ID11
Feature activation-4.34e-03

Pos logit contributions
 cleans+0.235
 outage+0.220
run+0.195
 tow+0.195
 slammed+0.194
Neg logit contributions
iece-0.200
ly-0.193
 seas-0.186
edly-0.184
 seven-0.161
Token ow
Token ID12334
Feature activation-1.29e-01

Pos logit contributions
 cleans+0.005
uffy+0.005
 outage+0.005
run+0.005
 need+0.004
Neg logit contributions
iece-0.009
edly-0.009
 seas-0.008
ly-0.008
Edward-0.008
Token!"
Token ID2474
Feature activation+5.59e-02

Pos logit contributions
 cleans+0.229
 outage+0.210
run+0.197
ric+0.193
 tow+0.191
Neg logit contributions
iece-0.183
ly-0.180
 seas-0.173
edly-0.171
aw-0.155
Token Ben
Token ID3932
Feature activation+4.02e-02

Pos logit contributions
iece+0.121
edly+0.116
 seas+0.114
Edward+0.105
 oceans+0.104
Neg logit contributions
 cleans-0.065
 Kim-0.057
uffy-0.056
 need-0.055
 Liz-0.055
Token cried
Token ID16896
Feature activation-2.06e-02

Pos logit contributions
iece+0.084
edly+0.084
 seas+0.081
Edward+0.074
oph+0.072
Neg logit contributions
 cleans-0.050
 need-0.042
uffy-0.041
run-0.040
 slammed-0.040
Token
Token ID198
Feature activation-2.20e-03

Pos logit contributions
edly+0.002
iece+0.002
Edward+0.002
 seas+0.002
Please+0.002
Neg logit contributions
 cleans-0.002
 outage-0.002
uffy-0.002
 need-0.002
 dripping-0.002
Token"
Token ID1
Feature activation+4.27e-02

Pos logit contributions
 cleans+0.004
uffy+0.004
run+0.004
 outage+0.003
 need+0.003
Neg logit contributions
edly-0.003
iece-0.003
 seas-0.003
ly-0.003
Edward-0.003
TokenO
Token ID46
Feature activation-2.65e-02

Pos logit contributions
iece+0.065
 seas+0.060
edly+0.060
ly+0.056
 Edward+0.050
Neg logit contributions
 cleans-0.082
uffy-0.071
 exc-0.071
 need-0.068
 hose-0.068
Tokenw
Token ID86
Feature activation+1.93e-02

Pos logit contributions
 cleans+0.058
run+0.054
 outage+0.053
 need+0.052
uffy+0.051
Neg logit contributions
edly-0.029
iece-0.029
 seas-0.024
ly-0.022
Edward-0.021
Token,
Token ID11
Feature activation-9.09e-03

Pos logit contributions
iece+0.034
edly+0.031
ly+0.031
 seas+0.029
Edward+0.027
Neg logit contributions
 cleans-0.029
 outage-0.027
 need-0.025
 exc-0.025
run-0.024
Token ow
Token ID12334
Feature activation-1.36e-01

Pos logit contributions
 cleans+0.012
 outage+0.011
run+0.011
uffy+0.011
 need+0.010
Neg logit contributions
iece-0.017
edly-0.016
 seas-0.016
ly-0.015
Edward-0.014
Token,
Token ID11
Feature activation-6.54e-03

Pos logit contributions
 cleans+0.246
 outage+0.240
 tow+0.219
run+0.218
ric+0.214
Neg logit contributions
iece-0.180
ly-0.176
 seas-0.160
edly-0.158
aw-0.143
Token ow
Token ID12334
Feature activation-1.29e-01

Pos logit contributions
 cleans+0.008
 outage+0.007
uffy+0.007
run+0.007
 need+0.006
Neg logit contributions
iece-0.013
edly-0.013
 seas-0.012
ly-0.011
Edward-0.011
Token!"
Token ID2474
Feature activation+5.58e-02

Pos logit contributions
 cleans+0.229
 outage+0.216
run+0.208
ric+0.203
 tow+0.202
Neg logit contributions
iece-0.175
ly-0.174
 seas-0.162
edly-0.158
aw-0.154
Token Tom
Token ID4186
Feature activation+2.04e-02

Pos logit contributions
iece+0.120
edly+0.116
 seas+0.112
Edward+0.105
oph+0.103
Neg logit contributions
 cleans-0.067
uffy-0.057
 need-0.057
 Kim-0.056
 Liz-0.055
Token cried
Token ID16896
Feature activation-2.24e-02

Pos logit contributions
iece+0.041
edly+0.041
 seas+0.040
Edward+0.037
 oceans+0.035
Neg logit contributions
 cleans-0.027
uffy-0.023
 need-0.023
run-0.023
 slammed-0.022
Token
Token ID198
Feature activation+4.39e-03

Pos logit contributions
edly+0.020
iece+0.020
 seas+0.019
Edward+0.018
ly+0.018
Neg logit contributions
 cleans-0.012
uffy-0.010
 outage-0.010
run-0.010
 need-0.010
Token"
Token ID1
Feature activation+4.87e-02

Pos logit contributions
iece+0.007
edly+0.007
 seas+0.007
ly+0.006
 oceans+0.006
Neg logit contributions
 cleans-0.007
run-0.007
uffy-0.006
 exc-0.006
 need-0.006
TokenO
Token ID46
Feature activation-2.30e-02

Pos logit contributions
iece+0.077
 seas+0.076
ly+0.070
edly+0.070
 oceans+0.058
Neg logit contributions
 cleans-0.083
 exc-0.073
 tow-0.070
 hose-0.070
 Kitty-0.069
Tokenw
Token ID86
Feature activation+2.55e-02

Pos logit contributions
 cleans+0.042
 outage+0.038
run+0.037
uffy+0.037
 need+0.037
Neg logit contributions
edly-0.034
iece-0.034
 seas-0.030
Edward-0.028
ly-0.027
Token,
Token ID11
Feature activation-3.18e-03

Pos logit contributions
iece+0.047
edly+0.045
ly+0.042
 seas+0.042
Edward+0.040
Neg logit contributions
 cleans-0.036
 outage-0.033
 need-0.031
uffy-0.030
run-0.030
Token ow
Token ID12334
Feature activation-1.36e-01

Pos logit contributions
 cleans+0.004
 outage+0.004
uffy+0.003
run+0.003
 need+0.003
Neg logit contributions
edly-0.006
iece-0.006
 seas-0.006
Edward-0.005
ly-0.005
Token,
Token ID11
Feature activation-3.60e-03

Pos logit contributions
 cleans+0.237
 outage+0.220
run+0.197
ric+0.196
 tow+0.194
Neg logit contributions
iece-0.196
ly-0.192
edly-0.183
 seas-0.182
 seven-0.162
Token ow
Token ID12334
Feature activation-1.29e-01

Pos logit contributions
 cleans+0.004
uffy+0.004
 outage+0.004
run+0.004
 need+0.004
Neg logit contributions
edly-0.007
iece-0.007
 seas-0.007
Edward-0.006
ly-0.006
Token!
Token ID0
Feature activation-1.96e-02

Pos logit contributions
 cleans+0.233
 outage+0.212
run+0.200
ric+0.198
 tow+0.194
Neg logit contributions
ly-0.177
iece-0.177
 seas-0.167
edly-0.166
aw-0.152
Token It
Token ID632
Feature activation-1.07e-02

Pos logit contributions
 cleans+0.034
 outage+0.032
uffy+0.031
 need+0.031
run+0.030
Neg logit contributions
edly-0.028
iece-0.027
 seas-0.024
Edward-0.023
Please-0.023
Token hurts
Token ID20406
Feature activation-2.76e-02

Pos logit contributions
 cleans+0.012
 outage+0.012
run+0.011
uffy+0.011
 tow+0.010
Neg logit contributions
iece-0.020
edly-0.020
 seas-0.019
ly-0.019
 seven-0.018
Token
Token ID198
Feature activation+2.58e-03

Pos logit contributions
edly+0.010
iece+0.010
 seas+0.009
Edward+0.009
Please+0.009
Neg logit contributions
 cleans-0.008
uffy-0.007
 outage-0.007
run-0.007
 need-0.007
Token"
Token ID1
Feature activation+4.44e-02

Pos logit contributions
edly+0.003
iece+0.003
 seas+0.003
Edward+0.003
ly+0.003
Neg logit contributions
 cleans-0.005
uffy-0.005
 outage-0.005
run-0.005
 need-0.005
TokenO
Token ID46
Feature activation-2.42e-02

Pos logit contributions
iece+0.072
 seas+0.070
ly+0.064
edly+0.064
 oceans+0.057
Neg logit contributions
 cleans-0.081
 exc-0.071
uffy-0.070
 Kitty-0.069
 damaged-0.068
Tokenw
Token ID86
Feature activation+1.95e-02

Pos logit contributions
 cleans+0.057
run+0.053
 outage+0.052
 need+0.052
uffy+0.052
Neg logit contributions
edly-0.023
iece-0.022
 seas-0.018
Edward-0.016
ly-0.016
Token,
Token ID11
Feature activation-4.49e-03

Pos logit contributions
iece+0.034
edly+0.033
ly+0.031
 seas+0.030
Edward+0.029
Neg logit contributions
 cleans-0.028
 outage-0.026
 need-0.025
 exc-0.024
run-0.024
Token ow
Token ID12334
Feature activation-1.36e-01

Pos logit contributions
 cleans+0.006
 outage+0.005
run+0.005
uffy+0.005
 need+0.005
Neg logit contributions
iece-0.009
edly-0.008
 seas-0.008
ly-0.008
Edward-0.007
Token,
Token ID11
Feature activation-2.71e-03

Pos logit contributions
 cleans+0.238
 outage+0.225
run+0.210
 tow+0.201
ric+0.200
Neg logit contributions
iece-0.193
ly-0.184
 seas-0.176
edly-0.175
aw-0.155
Token ow
Token ID12334
Feature activation-1.28e-01

Pos logit contributions
 cleans+0.003
 outage+0.003
uffy+0.003
run+0.003
 need+0.003
Neg logit contributions
iece-0.006
edly-0.005
 seas-0.005
ly-0.005
Edward-0.005
Token,
Token ID11
Feature activation-1.28e-03

Pos logit contributions
 cleans+0.224
 outage+0.206
run+0.201
ric+0.191
 tow+0.190
Neg logit contributions
iece-0.185
ly-0.180
 seas-0.171
edly-0.171
aw-0.158
Token it
Token ID340
Feature activation-1.08e-02

Pos logit contributions
 cleans+0.002
 outage+0.001
uffy+0.001
run+0.001
 need+0.001
Neg logit contributions
iece-0.003
edly-0.003
 seas-0.002
ly-0.002
Edward-0.002
Token hurts
Token ID20406
Feature activation-3.63e-02

Pos logit contributions
 outage+0.012
 cleans+0.012
run+0.012
 tow+0.011
uffy+0.011
Neg logit contributions
iece-0.020
edly-0.019
ly-0.019
 seas-0.018
 seven-0.018
Token
Token ID198
Feature activation+1.31e-03

Pos logit contributions
edly+0.007
iece+0.007
Edward+0.006
 seas+0.006
Please+0.006
Neg logit contributions
 cleans-0.006
uffy-0.005
 outage-0.005
 need-0.005
 dripping-0.005
Token"
Token ID1
Feature activation+4.23e-02

Pos logit contributions
edly+0.002
iece+0.002
 seas+0.002
ly+0.002
Edward+0.002
Neg logit contributions
 cleans-0.002
uffy-0.002
run-0.002
 outage-0.002
 need-0.002
TokenO
Token ID46
Feature activation-2.53e-02

Pos logit contributions
iece+0.065
edly+0.062
 seas+0.062
ly+0.059
oph+0.054
Neg logit contributions
 cleans-0.077
 exc-0.069
 damaged-0.067
 ruined-0.066
 drown-0.066
Tokenw
Token ID86
Feature activation+1.69e-02

Pos logit contributions
 cleans+0.057
uffy+0.052
run+0.052
 outage+0.052
 need+0.051
Neg logit contributions
edly-0.027
iece-0.026
 seas-0.023
Edward-0.020
ly-0.020
Token,
Token ID11
Feature activation-7.55e-03

Pos logit contributions
iece+0.031
edly+0.030
 seas+0.028
ly+0.028
Edward+0.026
Neg logit contributions
 cleans-0.024
 outage-0.022
 need-0.021
run-0.020
uffy-0.020
Token ow
Token ID12334
Feature activation-1.36e-01

Pos logit contributions
 cleans+0.009
 outage+0.008
uffy+0.008
run+0.008
 need+0.007
Neg logit contributions
iece-0.015
edly-0.015
 seas-0.015
Edward-0.014
ly-0.014
Token,
Token ID11
Feature activation-4.49e-03

Pos logit contributions
 cleans+0.238
 outage+0.217
run+0.203
ric+0.196
 tow+0.193
Neg logit contributions
iece-0.201
ly-0.191
 seas-0.190
edly-0.186
 seven-0.165
Token ow
Token ID12334
Feature activation-1.28e-01

Pos logit contributions
 cleans+0.005
uffy+0.004
 outage+0.004
run+0.004
 need+0.004
Neg logit contributions
edly-0.010
iece-0.010
 seas-0.009
Edward-0.009
ly-0.009
Token!"
Token ID2474
Feature activation+5.68e-02

Pos logit contributions
 cleans+0.222
 outage+0.197
run+0.192
ric+0.184
uffy+0.179
Neg logit contributions
iece-0.194
edly-0.188
 seas-0.185
ly-0.185
aw-0.163
Token Tom
Token ID4186
Feature activation+2.00e-02

Pos logit contributions
iece+0.122
edly+0.118
 seas+0.113
oph+0.108
Edward+0.108
Neg logit contributions
 cleans-0.067
 Kim-0.061
 slammed-0.060
 need-0.058
 Liz-0.057
Token cried
Token ID16896
Feature activation-2.29e-02

Pos logit contributions
iece+0.042
 seas+0.042
edly+0.041
Edward+0.039
 oceans+0.037
Neg logit contributions
 cleans-0.023
 slammed-0.020
run-0.020
uffy-0.020
 need-0.019
Token
Token ID198
Feature activation-5.62e-03

Pos logit contributions
 cleans+0.007
 outage+0.006
 dripping+0.006
ric+0.006
arter+0.006
Neg logit contributions
edly-0.004
J-0.004
Please-0.004
Just-0.004
iece-0.004
Token"
Token ID1
Feature activation+3.66e-02

Pos logit contributions
 cleans+0.010
uffy+0.009
 outage+0.009
run+0.008
 need+0.008
Neg logit contributions
edly-0.009
iece-0.009
 seas-0.008
Edward-0.007
ly-0.007
TokenO
Token ID46
Feature activation-2.20e-02

Pos logit contributions
iece+0.060
edly+0.058
 seas+0.057
ly+0.051
oph+0.051
Neg logit contributions
 cleans-0.063
 exc-0.057
uffy-0.055
 drown-0.055
 need-0.054
Tokenw
Token ID86
Feature activation+1.84e-02

Pos logit contributions
 cleans+0.056
run+0.052
 outage+0.051
 tow+0.050
 hose+0.050
Neg logit contributions
edly-0.015
iece-0.015
 seas-0.012
ly-0.011
Edward-0.010
Token,
Token ID11
Feature activation-6.84e-03

Pos logit contributions
iece+0.032
edly+0.031
ly+0.029
 seas+0.029
Edward+0.027
Neg logit contributions
 cleans-0.028
 outage-0.025
 need-0.024
 exc-0.023
run-0.023
Token ow
Token ID12334
Feature activation-1.35e-01

Pos logit contributions
 cleans+0.009
 outage+0.008
run+0.008
uffy+0.008
ucker+0.007
Neg logit contributions
iece-0.013
edly-0.013
 seas-0.012
ly-0.012
Edward-0.011
Token,
Token ID11
Feature activation-2.39e-03

Pos logit contributions
 cleans+0.259
 outage+0.237
run+0.224
ric+0.222
 tow+0.216
Neg logit contributions
ly-0.177
 seas-0.168
iece-0.167
edly-0.153
 seven-0.143
Token ow
Token ID12334
Feature activation-1.26e-01

Pos logit contributions
 cleans+0.003
 outage+0.003
uffy+0.003
run+0.002
 need+0.002
Neg logit contributions
iece-0.005
edly-0.005
 seas-0.005
ly-0.004
Edward-0.004
Token!"
Token ID2474
Feature activation+5.50e-02

Pos logit contributions
 cleans+0.250
 outage+0.224
run+0.222
ric+0.221
 slam+0.208
Neg logit contributions
ly-0.160
 seas-0.151
iece-0.147
edly-0.141
aw-0.131
Token Ben
Token ID3932
Feature activation+4.03e-02

Pos logit contributions
iece+0.117
edly+0.115
 seas+0.103
Edward+0.099
ly+0.097
Neg logit contributions
 cleans-0.068
 need-0.060
uffy-0.057
run-0.055
 exc-0.055
Token says
Token ID1139
Feature activation+2.56e-02

Pos logit contributions
edly+0.093
iece+0.092
 seas+0.087
Edward+0.082
ly+0.080
Neg logit contributions
 cleans-0.041
uffy-0.034
 outage-0.032
 need-0.032
run-0.032
Token
Token ID198
Feature activation-1.92e-04

Pos logit contributions
edly+0.003
iece+0.003
Edward+0.002
Please+0.002
Cl+0.002
Neg logit contributions
 cleans-0.003
 outage-0.003
 flood-0.003
uffy-0.003
 dripping-0.003
Token"
Token ID1
Feature activation+3.97e-02

Pos logit contributions
 cleans+0.000
 outage+0.000
uffy+0.000
run+0.000
 need+0.000
Neg logit contributions
edly-0.000
iece-0.000
 seas-0.000
Edward-0.000
ly-0.000
TokenO
Token ID46
Feature activation-2.51e-02

Pos logit contributions
iece+0.059
 seas+0.057
edly+0.056
ly+0.050
 oceans+0.046
Neg logit contributions
 cleans-0.077
uffy-0.067
 exc-0.065
 drown-0.065
 hose-0.064
Tokenw
Token ID86
Feature activation+1.61e-02

Pos logit contributions
 cleans+0.062
run+0.058
 outage+0.057
 need+0.056
 exc+0.056
Neg logit contributions
edly-0.020
iece-0.020
 seas-0.016
ly-0.014
Edward-0.013
Token,
Token ID11
Feature activation-5.98e-03

Pos logit contributions
iece+0.029
edly+0.027
ly+0.026
 seas+0.025
Edward+0.024
Neg logit contributions
 cleans-0.023
 outage-0.021
 need-0.020
 exc-0.020
run-0.020
Token ow
Token ID12334
Feature activation-1.35e-01

Pos logit contributions
 cleans+0.008
 outage+0.007
run+0.007
uffy+0.007
ucker+0.007
Neg logit contributions
iece-0.011
edly-0.011
 seas-0.010
ly-0.010
Edward-0.010
Token,
Token ID11
Feature activation-2.59e-03

Pos logit contributions
 cleans+0.255
 outage+0.237
run+0.224
ric+0.217
 tow+0.216
Neg logit contributions
ly-0.174
iece-0.171
 seas-0.162
edly-0.152
 seven-0.141
Token ow
Token ID12334
Feature activation-1.27e-01

Pos logit contributions
 cleans+0.003
 outage+0.003
run+0.003
uffy+0.003
 need+0.003
Neg logit contributions
iece-0.005
edly-0.005
 seas-0.005
ly-0.005
Edward-0.005
Token!"
Token ID2474
Feature activation+5.69e-02

Pos logit contributions
 cleans+0.241
run+0.219
 outage+0.217
ric+0.211
 tow+0.205
Neg logit contributions
ly-0.166
iece-0.160
 seas-0.153
edly-0.150
aw-0.135
Token Anna
Token ID11735
Feature activation+2.42e-02

Pos logit contributions
iece+0.114
 seas+0.110
edly+0.109
 oceans+0.098
oph+0.097
Neg logit contributions
 cleans-0.078
 need-0.067
uffy-0.066
 slammed-0.065
 tells-0.064
Token says
Token ID1139
Feature activation+1.96e-02

Pos logit contributions
edly+0.055
iece+0.054
 seas+0.053
Edward+0.049
oph+0.048
Neg logit contributions
 cleans-0.026
uffy-0.021
 need-0.021
 outage-0.020
run-0.019
Token
Token ID198
Feature activation+1.79e-03

Pos logit contributions
edly+0.009
iece+0.008
 seas+0.008
Edward+0.008
Please+0.007
Neg logit contributions
 cleans-0.007
 outage-0.007
uffy-0.007
 need-0.006
 dripping-0.006
Token"
Token ID1
Feature activation+4.34e-02

Pos logit contributions
edly+0.002
iece+0.002
 seas+0.002
ly+0.002
Edward+0.002
Neg logit contributions
 cleans-0.003
uffy-0.003
run-0.003
 outage-0.003
 need-0.003
TokenO
Token ID46
Feature activation-2.35e-02

Pos logit contributions
iece+0.068
edly+0.064
 seas+0.063
ly+0.059
oph+0.055
Neg logit contributions
 cleans-0.081
 exc-0.070
uffy-0.069
 drown-0.068
 hose-0.067
Tokenw
Token ID86
Feature activation+1.94e-02

Pos logit contributions
 cleans+0.054
run+0.049
 outage+0.049
 need+0.049
uffy+0.049
Neg logit contributions
edly-0.024
iece-0.023
 seas-0.019
ly-0.017
Edward-0.017
Token,
Token ID11
Feature activation-7.28e-03

Pos logit contributions
iece+0.035
edly+0.033
ly+0.031
 seas+0.031
Edward+0.029
Neg logit contributions
 cleans-0.028
 outage-0.026
 need-0.024
run-0.024
 exc-0.024
Token ow
Token ID12334
Feature activation-1.35e-01

Pos logit contributions
 cleans+0.010
 outage+0.009
run+0.009
uffy+0.009
ucker+0.008
Neg logit contributions
iece-0.013
edly-0.013
 seas-0.012
ly-0.012
Please-0.011
Token,
Token ID11
Feature activation-4.45e-03

Pos logit contributions
 cleans+0.240
 outage+0.221
run+0.206
ric+0.202
 tow+0.199
Neg logit contributions
iece-0.192
ly-0.186
 seas-0.179
edly-0.172
 seven-0.158
Token ow
Token ID12334
Feature activation-1.28e-01

Pos logit contributions
 cleans+0.006
 outage+0.005
uffy+0.005
run+0.005
 need+0.004
Neg logit contributions
iece-0.009
edly-0.008
 seas-0.008
ly-0.008
Edward-0.007
Token!"
Token ID2474
Feature activation+5.74e-02

Pos logit contributions
 cleans+0.233
 outage+0.210
run+0.206
ric+0.201
 tow+0.193
Neg logit contributions
iece-0.175
ly-0.173
 seas-0.166
edly-0.162
aw-0.147
Token Tom
Token ID4186
Feature activation+2.23e-02

Pos logit contributions
iece+0.124
edly+0.118
 seas+0.115
Edward+0.106
 oceans+0.106
Neg logit contributions
 cleans-0.070
 Kim-0.061
 need-0.060
uffy-0.060
 Liz-0.060
Token cries
Token ID24691
Feature activation-2.30e-02

Pos logit contributions
edly+0.048
iece+0.048
 seas+0.047
Edward+0.043
oph+0.042
Neg logit contributions
 cleans-0.026
uffy-0.022
 need-0.022
run-0.021
 outage-0.021
Token
Token ID198
Feature activation+2.76e-03

Pos logit contributions
edly+0.011
iece+0.011
 seas+0.010
Edward+0.010
Prin+0.010
Neg logit contributions
 cleans-0.009
 outage-0.008
uffy-0.008
 need-0.008
run-0.008
Token"
Token ID1
Feature activation+4.38e-02

Pos logit contributions
iece+0.004
edly+0.004
 seas+0.004
ly+0.004
oph+0.003
Neg logit contributions
 cleans-0.005
uffy-0.004
run-0.004
 need-0.004
 outage-0.004
TokenO
Token ID46
Feature activation-2.31e-02

Pos logit contributions
iece+0.070
 seas+0.066
edly+0.064
ly+0.061
 oceans+0.056
Neg logit contributions
 cleans-0.082
uffy-0.070
 exc-0.069
 drown-0.067
 Kitty-0.067
Tokenw
Token ID86
Feature activation+2.00e-02

Pos logit contributions
 cleans+0.052
run+0.048
 outage+0.048
 need+0.047
uffy+0.047
Neg logit contributions
edly-0.024
iece-0.023
 seas-0.019
Edward-0.017
ly-0.017
Token,
Token ID11
Feature activation-6.04e-03

Pos logit contributions
iece+0.036
edly+0.035
ly+0.032
 seas+0.032
Edward+0.030
Neg logit contributions
 cleans-0.029
 outage-0.027
 need-0.025
run-0.024
 exc-0.024
Token ow
Token ID12334
Feature activation-1.35e-01

Pos logit contributions
 cleans+0.008
 outage+0.007
run+0.007
uffy+0.007
 need+0.006
Neg logit contributions
iece-0.012
edly-0.011
 seas-0.011
ly-0.010
Edward-0.010
Token,
Token ID11
Feature activation-3.75e-03

Pos logit contributions
 cleans+0.241
 outage+0.228
run+0.209
ric+0.207
 tow+0.206
Neg logit contributions
iece-0.186
ly-0.182
edly-0.172
 seas-0.170
 seven-0.153
Token ow
Token ID12334
Feature activation-1.28e-01

Pos logit contributions
 cleans+0.004
 outage+0.004
uffy+0.004
run+0.004
 need+0.003
Neg logit contributions
iece-0.008
edly-0.008
 seas-0.007
ly-0.007
Edward-0.007
Token!"
Token ID2474
Feature activation+5.78e-02

Pos logit contributions
 cleans+0.231
 outage+0.211
run+0.205
ric+0.201
 tow+0.196
Neg logit contributions
iece-0.177
ly-0.173
edly-0.168
 seas-0.165
aw-0.150
Token Mia
Token ID32189
Feature activation-2.58e-03

Pos logit contributions
iece+0.124
edly+0.119
 seas+0.118
Edward+0.107
oph+0.107
Neg logit contributions
 cleans-0.070
 need-0.060
 Kim-0.059
 Liz-0.059
 slammed-0.059
Token cried
Token ID16896
Feature activation-2.32e-02

Pos logit contributions
 cleans+0.003
uffy+0.003
 need+0.003
run+0.003
 slammed+0.003
Neg logit contributions
edly-0.005
iece-0.005
 seas-0.005
Edward-0.005
oph-0.005
Token
Token ID198
Feature activation+3.21e-03

Pos logit contributions
edly+0.008
iece+0.008
Edward+0.007
Cl+0.007
 seas+0.007
Neg logit contributions
 cleans-0.009
 outage-0.009
uffy-0.008
run-0.008
 dripping-0.008
Token"
Token ID1
Feature activation+4.09e-02

Pos logit contributions
edly+0.005
iece+0.005
 seas+0.005
ly+0.004
Edward+0.004
Neg logit contributions
 cleans-0.005
uffy-0.005
 need-0.005
 outage-0.005
run-0.005
TokenO
Token ID46
Feature activation-2.26e-02

Pos logit contributions
iece+0.064
 seas+0.062
edly+0.058
ly+0.057
oph+0.052
Neg logit contributions
 cleans-0.077
 exc-0.065
 ruined-0.064
 drown-0.063
 swollen-0.063
Tokenw
Token ID86
Feature activation+1.64e-02

Pos logit contributions
 cleans+0.054
run+0.051
 outage+0.050
uffy+0.049
 exc+0.049
Neg logit contributions
edly-0.019
iece-0.019
 seas-0.016
ly-0.014
Edward-0.014
Token,
Token ID11
Feature activation-4.33e-03

Pos logit contributions
iece+0.030
edly+0.029
 seas+0.027
ly+0.027
Edward+0.026
Neg logit contributions
 cleans-0.023
 outage-0.021
 need-0.020
run-0.020
 exc-0.020
Token ow
Token ID12334
Feature activation-1.35e-01

Pos logit contributions
 cleans+0.005
 outage+0.005
uffy+0.005
run+0.005
 need+0.004
Neg logit contributions
iece-0.009
edly-0.009
 seas-0.008
Edward-0.008
ly-0.008
Token!"
Token ID2474
Feature activation+5.75e-02

Pos logit contributions
 cleans+0.241
 outage+0.227
run+0.217
ric+0.209
 tow+0.206
Neg logit contributions
iece-0.188
ly-0.178
 seas-0.175
edly-0.169
 seven-0.152
Token Ben
Token ID3932
Feature activation+3.71e-02

Pos logit contributions
iece+0.112
edly+0.107
 seas+0.102
oph+0.091
 oceans+0.091
Neg logit contributions
 cleans-0.085
 need-0.075
uffy-0.071
 slammed-0.070
 tells-0.070
Token says
Token ID1139
Feature activation+2.24e-02

Pos logit contributions
edly+0.082
iece+0.081
 seas+0.077
Edward+0.072
ly+0.070
Neg logit contributions
 cleans-0.041
uffy-0.034
 need-0.033
 outage-0.033
run-0.033
Token.
Token ID13
Feature activation-2.83e-03

Pos logit contributions
edly+0.048
iece+0.048
 seas+0.046
Edward+0.043
oph+0.042
Neg logit contributions
 cleans-0.025
uffy-0.021
run-0.021
 outage-0.021
 need-0.020
Token He
Token ID679
Feature activation+5.90e-03

Pos logit contributions
 cleans+0.004
uffy+0.003
run+0.003
 outage+0.003
 need+0.003
Neg logit contributions
iece-0.005
edly-0.005
 seas-0.005
Edward-0.005
oph-0.005
Token,
Token ID11
Feature activation-8.06e-03

Pos logit contributions
 cleans+0.012
uffy+0.010
run+0.010
 need+0.010
 outage+0.010
Neg logit contributions
edly-0.024
iece-0.024
 seas-0.022
Edward-0.021
oph-0.021
Token "
Token ID366
Feature activation+1.96e-02

Pos logit contributions
 cleans+0.011
uffy+0.010
 outage+0.010
 need+0.009
run+0.009
Neg logit contributions
edly-0.015
iece-0.015
 seas-0.014
ly-0.013
Edward-0.013
TokenO
Token ID46
Feature activation-2.56e-02

Pos logit contributions
 seas+0.034
edly+0.032
iece+0.030
 Edward+0.030
 Amber+0.030
Neg logit contributions
 drown-0.029
 exc-0.028
 need-0.028
 cleans-0.027
uffy-0.027
Tokenw
Token ID86
Feature activation+1.81e-02

Pos logit contributions
 cleans+0.063
 tow+0.058
run+0.057
 hose+0.057
 fireplace+0.056
Neg logit contributions
edly-0.020
iece-0.020
ly-0.017
 seas-0.017
aw-0.015
Token,
Token ID11
Feature activation-7.55e-03

Pos logit contributions
iece+0.031
edly+0.030
ly+0.029
 seas+0.027
Edward+0.026
Neg logit contributions
 cleans-0.027
 outage-0.025
 need-0.024
 exc-0.024
 slam-0.022
Token ow
Token ID12334
Feature activation-1.35e-01

Pos logit contributions
 cleans+0.009
 outage+0.008
uffy+0.008
run+0.008
 need+0.007
Neg logit contributions
iece-0.015
edly-0.015
 seas-0.014
ly-0.014
Edward-0.013
Token,
Token ID11
Feature activation-1.31e-03

Pos logit contributions
 cleans+0.273
 outage+0.249
ric+0.234
 tow+0.232
 slam+0.229
Neg logit contributions
ly-0.168
iece-0.153
 seas-0.146
aw-0.125
adies-0.125
Token ow
Token ID12334
Feature activation-1.23e-01

Pos logit contributions
 cleans+0.001
uffy+0.001
 outage+0.001
run+0.001
 need+0.001
Neg logit contributions
iece-0.003
edly-0.003
 seas-0.003
Edward-0.002
ly-0.002
Token!"
Token ID2474
Feature activation+4.34e-02

Pos logit contributions
 cleans+0.248
ric+0.218
 outage+0.217
run+0.210
 slam+0.207
Neg logit contributions
ly-0.159
iece-0.144
 seas-0.138
aw-0.128
edly-0.128
Token
Token ID198
Feature activation+3.32e-03

Pos logit contributions
iece+0.096
edly+0.095
 seas+0.091
Edward+0.086
ly+0.084
Neg logit contributions
 cleans-0.045
uffy-0.039
run-0.039
 need-0.037
 Kim-0.037
Token
Token ID198
Feature activation-5.42e-05

Pos logit contributions
edly+0.006
iece+0.006
 seas+0.006
Edward+0.006
Please+0.005
Neg logit contributions
 cleans-0.005
 outage-0.004
uffy-0.004
 need-0.004
run-0.004
Token
Token ID198
Feature activation-1.58e-03

Pos logit contributions
edly+0.002
iece+0.002
Edward+0.002
Prin+0.002
 seas+0.002
Neg logit contributions
 cleans-0.002
 outage-0.002
uffy-0.002
 need-0.002
 needs-0.002
Token"
Token ID1
Feature activation+4.06e-02

Pos logit contributions
 cleans+0.003
uffy+0.003
 outage+0.003
run+0.003
 need+0.003
Neg logit contributions
edly-0.002
iece-0.002
 seas-0.002
Edward-0.002
ly-0.002
TokenO
Token ID46
Feature activation-2.67e-02

Pos logit contributions
iece+0.070
edly+0.068
 seas+0.067
ly+0.063
 oceans+0.060
Neg logit contributions
 cleans-0.067
 exc-0.059
 swollen-0.058
 ruined-0.058
uffy-0.056
Tokenw
Token ID86
Feature activation+1.48e-02

Pos logit contributions
 cleans+0.057
run+0.052
 outage+0.052
 need+0.051
uffy+0.050
Neg logit contributions
edly-0.031
iece-0.031
 seas-0.027
ly-0.024
Edward-0.024
Token,
Token ID11
Feature activation-7.63e-03

Pos logit contributions
iece+0.027
edly+0.026
 seas+0.025
ly+0.024
Edward+0.023
Neg logit contributions
 cleans-0.021
 outage-0.019
 need-0.018
run-0.018
uffy-0.018
Token ow
Token ID12334
Feature activation-1.35e-01

Pos logit contributions
 cleans+0.009
 outage+0.009
run+0.008
uffy+0.008
 need+0.008
Neg logit contributions
iece-0.015
edly-0.015
 seas-0.014
ly-0.013
Edward-0.013
Token,
Token ID11
Feature activation-3.81e-03

Pos logit contributions
 cleans+0.235
 outage+0.218
run+0.206
ric+0.198
 tow+0.196
Neg logit contributions
iece-0.198
ly-0.193
 seas-0.187
edly-0.181
 seven-0.162
Token ow
Token ID12334
Feature activation-1.27e-01

Pos logit contributions
 cleans+0.004
 outage+0.004
uffy+0.004
run+0.004
 need+0.003
Neg logit contributions
iece-0.008
edly-0.008
 seas-0.008
ly-0.007
Edward-0.007
Token!"
Token ID2474
Feature activation+5.75e-02

Pos logit contributions
 cleans+0.230
 outage+0.208
run+0.206
ric+0.198
 tow+0.192
Neg logit contributions
iece-0.177
ly-0.175
 seas-0.168
edly-0.166
aw-0.151
Token she
Token ID673
Feature activation+1.37e-02

Pos logit contributions
iece+0.118
edly+0.116
 seas+0.112
Edward+0.104
 oceans+0.101
Neg logit contributions
 cleans-0.075
uffy-0.064
 need-0.064
 Kim-0.062
 slammed-0.062
Token screamed
Token ID25421
Feature activation+5.83e-03

Pos logit contributions
iece+0.028
edly+0.028
 seas+0.027
Edward+0.026
 oceans+0.025
Neg logit contributions
 cleans-0.017
 slammed-0.015
uffy-0.015
run-0.014
 need-0.014
TokenCan
Token ID6090
Feature activation+2.50e-02

Pos logit contributions
edly+0.093
iece+0.086
 Edward+0.082
 Amber+0.082
 Avery+0.077
Neg logit contributions
o-0.066
run-0.064
itty-0.060
 have-0.060
 tow-0.059
Token I
Token ID314
Feature activation-7.00e-03

Pos logit contributions
edly+0.052
iece+0.051
 seas+0.044
oph+0.043
Edward+0.042
Neg logit contributions
 cleans-0.033
 need-0.030
uffy-0.029
 exc-0.029
run-0.028
Token please
Token ID3387
Feature activation+5.06e-02

Pos logit contributions
 cleans+0.012
uffy+0.010
 dripping+0.010
 outage+0.010
arter+0.010
Neg logit contributions
 seas-0.010
Please-0.010
ly-0.009
iece-0.009
Edward-0.009
Token ride
Token ID6594
Feature activation-8.82e-03

Pos logit contributions
 seas+0.085
iece+0.084
edly+0.084
ly+0.077
Please+0.077
Neg logit contributions
 cleans-0.073
uffy-0.068
 outage-0.065
run-0.062
arter-0.058
Token in
Token ID287
Feature activation-6.71e-03

Pos logit contributions
 have+0.008
 cleans+0.008
 need+0.008
 Kitty+0.008
run+0.007
Neg logit contributions
edly-0.021
iece-0.020
oph-0.019
Marie-0.017
 endings-0.017
Token your
Token ID534
Feature activation+8.57e-02

Pos logit contributions
 cleans+0.011
uffy+0.010
 outage+0.010
run+0.009
 need+0.009
Neg logit contributions
iece-0.011
edly-0.011
 seas-0.011
Edward-0.009
 oceans-0.009
Token boat
Token ID8848
Feature activation-2.49e-03

Pos logit contributions
 seas+0.142
edly+0.118
iece+0.113
 seven+0.113
 oceans+0.108
Neg logit contributions
 cleans-0.147
 outage-0.143
run-0.134
ucker-0.133
uffy-0.128
Token?"
Token ID1701
Feature activation+3.40e-02

Pos logit contributions
 cleans+0.002
uffy+0.002
 outage+0.002
run+0.002
 need+0.002
Neg logit contributions
edly-0.006
iece-0.006
 seas-0.005
Edward-0.005
ly-0.005
Token The
Token ID383
Feature activation-3.30e-02

Pos logit contributions
iece+0.060
edly+0.060
 seas+0.055
ly+0.052
Please+0.051
Neg logit contributions
 cleans-0.049
 outage-0.046
uffy-0.045
run-0.042
 need-0.042
Token man
Token ID582
Feature activation+2.31e-02

Pos logit contributions
 cleans+0.064
uffy+0.059
run+0.058
 outage+0.058
 need+0.057
Neg logit contributions
edly-0.045
iece-0.045
 seas-0.040
Edward-0.036
ly-0.036
Token said
Token ID531
Feature activation+7.88e-03

Pos logit contributions
edly+0.040
iece+0.039
 seas+0.036
ly+0.034
Edward+0.033
Neg logit contributions
 cleans-0.035
uffy-0.032
 outage-0.032
 need-0.031
run-0.030
TokenCl
Token ID2601
Feature activation+2.57e-02

Pos logit contributions
 cleans+0.002
 exc+0.002
uffy+0.001
 have+0.001
 know+0.001
Neg logit contributions
iece-0.001
 seas-0.001
edly-0.001
 oceans-0.001
ly-0.001
Tokenara
Token ID3301
Feature activation+2.82e-02

Pos logit contributions
iece+0.041
edly+0.039
 seas+0.036
 oceans+0.032
fully+0.032
Neg logit contributions
uffy-0.045
 cleans-0.044
ucker-0.039
 need-0.038
 needs-0.037
Token made
Token ID925
Feature activation+1.45e-02

Pos logit contributions
iece+0.058
edly+0.057
 seas+0.054
Edward+0.051
 Edward+0.049
Neg logit contributions
 cleans-0.035
uffy-0.030
 need-0.029
run-0.028
 slammed-0.028
Token a
Token ID257
Feature activation+2.38e-02

Pos logit contributions
edly+0.029
iece+0.027
Please+0.025
Edward+0.024
ly+0.023
Neg logit contributions
 cleans-0.020
 need-0.017
 know-0.017
 Kim-0.017
 Liz-0.017
Token new
Token ID649
Feature activation+4.79e-02

Pos logit contributions
edly+0.050
iece+0.049
 seas+0.046
Edward+0.043
ly+0.043
Neg logit contributions
 cleans-0.028
uffy-0.025
 outage-0.024
run-0.024
 need-0.023
Token guess
Token ID4724
Feature activation+8.49e-02

Pos logit contributions
edly+0.101
iece+0.101
 seas+0.093
Edward+0.089
ly+0.087
Neg logit contributions
 cleans-0.056
uffy-0.049
 outage-0.047
 need-0.046
run-0.046
Token-
Token ID12
Feature activation+9.11e-03

Pos logit contributions
edly+0.166
iece+0.165
 seas+0.152
Edward+0.144
ly+0.141
Neg logit contributions
 cleans-0.112
uffy-0.098
 outage-0.096
run-0.095
 need-0.094
Token she
Token ID673
Feature activation+3.24e-02

Pos logit contributions
iece+0.018
edly+0.017
 oceans+0.015
 seas+0.015
Edward+0.014
Neg logit contributions
run-0.011
 know-0.011
 outage-0.010
 need-0.010
o-0.010
Token thought
Token ID1807
Feature activation+2.74e-02

Pos logit contributions
edly+0.068
iece+0.067
 seas+0.063
Edward+0.059
ly+0.058
Neg logit contributions
 cleans-0.039
uffy-0.034
 need-0.033
run-0.033
 outage-0.033
Token it
Token ID340
Feature activation-7.75e-04

Pos logit contributions
edly+0.052
iece+0.052
 seas+0.048
Edward+0.045
ly+0.044
Neg logit contributions
 cleans-0.038
uffy-0.033
 outage-0.033
run-0.033
 need-0.032
Token must
Token ID1276
Feature activation+2.28e-02

Pos logit contributions
 cleans+0.001
uffy+0.001
 need+0.001
run+0.001
 outage+0.001
Neg logit contributions
edly-0.002
iece-0.002
 seas-0.002
Edward-0.002
 Edward-0.002
Token and
Token ID290
Feature activation+1.03e-02

Pos logit contributions
 cleans+0.033
 outage+0.029
uffy+0.029
run+0.029
 slammed+0.027
Neg logit contributions
 seas-0.025
edly-0.025
iece-0.024
ly-0.022
 oceans-0.020
Token ships
Token ID7937
Feature activation-1.48e-03

Pos logit contributions
 seas+0.018
iece+0.016
edly+0.016
 seven+0.015
 oceans+0.015
Neg logit contributions
 cleans-0.016
uffy-0.016
 outage-0.015
run-0.014
 slam-0.014
Token,
Token ID11
Feature activation+1.34e-02

Pos logit contributions
 cleans+0.002
uffy+0.002
 outage+0.002
run+0.002
 drown+0.002
Neg logit contributions
edly-0.002
iece-0.002
 seas-0.002
ly-0.002
 oceans-0.002
Token especially
Token ID2592
Feature activation+3.09e-02

Pos logit contributions
edly+0.022
iece+0.022
 seas+0.020
Edward+0.018
ly+0.018
Neg logit contributions
 cleans-0.022
uffy-0.020
 outage-0.020
run-0.020
 need-0.020
Token y
Token ID331
Feature activation-2.27e-03

Pos logit contributions
edly+0.044
 seas+0.044
iece+0.044
ly+0.038
 oceans+0.038
Neg logit contributions
 cleans-0.056
uffy-0.053
 outage-0.052
 slam-0.049
 slammed-0.048
Tokenach
Token ID620
Feature activation+9.16e-02

Pos logit contributions
 cleans+0.004
 outage+0.003
uffy+0.003
run+0.003
 need+0.003
Neg logit contributions
edly-0.004
iece-0.004
 seas-0.003
ly-0.003
Edward-0.003
Tokents
Token ID912
Feature activation-2.94e-02

Pos logit contributions
edly+0.163
iece+0.158
oph+0.134
Edward+0.134
 seas+0.133
Neg logit contributions
 cleans-0.137
uffy-0.128
run-0.121
 need-0.119
 exc-0.119
Token.
Token ID13
Feature activation-6.02e-03

Pos logit contributions
 cleans+0.027
 need+0.026
run+0.025
 exc+0.024
 outage+0.024
Neg logit contributions
iece-0.065
edly-0.063
oph-0.060
Edward-0.059
 seas-0.059
Token One
Token ID1881
Feature activation-3.22e-02

Pos logit contributions
 cleans+0.012
 outage+0.011
uffy+0.010
 drown+0.010
 slammed+0.010
Neg logit contributions
iece-0.008
 seas-0.007
edly-0.007
Edward-0.007
 Edward-0.006
Token day
Token ID1110
Feature activation+1.57e-02

Pos logit contributions
 cleans+0.063
run+0.057
uffy+0.056
 slam+0.054
 outage+0.053
Neg logit contributions
 seas-0.045
iece-0.042
edly-0.041
ly-0.039
 seven-0.036
Token,
Token ID11
Feature activation-2.24e-03

Pos logit contributions
iece+0.024
 seas+0.024
edly+0.024
ly+0.023
Edward+0.020
Neg logit contributions
 cleans-0.025
 outage-0.025
run-0.022
uffy-0.022
ric-0.022
Token Sam
Token ID3409
Feature activation-2.17e-03

Pos logit contributions
edly+0.071
iece+0.067
 seas+0.063
ly+0.060
Edward+0.060
Neg logit contributions
 cleans-0.045
uffy-0.039
 need-0.039
 Kim-0.039
 exc-0.037
Token wanted
Token ID2227
Feature activation-7.57e-03

Pos logit contributions
 cleans+0.003
 outage+0.003
uffy+0.003
run+0.003
ric+0.003
Neg logit contributions
edly-0.004
iece-0.004
ly-0.003
 seas-0.003
Edward-0.003
Token to
Token ID284
Feature activation+3.58e-03

Pos logit contributions
 cleans+0.011
 need+0.010
run+0.009
 outage+0.009
uffy+0.009
Neg logit contributions
edly-0.015
iece-0.014
 seas-0.013
Edward-0.012
ly-0.012
Token draw
Token ID3197
Feature activation+5.60e-02

Pos logit contributions
edly+0.007
iece+0.007
 seas+0.007
Edward+0.006
ly+0.006
Neg logit contributions
 cleans-0.005
 need-0.004
uffy-0.004
 outage-0.004
run-0.004
Token a
Token ID257
Feature activation+4.16e-02

Pos logit contributions
edly+0.121
iece+0.104
oph+0.104
Edward+0.098
 seas+0.098
Neg logit contributions
 cleans-0.068
 need-0.060
 Kim-0.058
run-0.056
 Liz-0.056
Token dinosaur
Token ID28257
Feature activation+7.30e-02

Pos logit contributions
edly+0.093
iece+0.090
 seas+0.082
Edward+0.079
ly+0.078
Neg logit contributions
 cleans-0.046
uffy-0.040
 outage-0.039
 need-0.039
run-0.037
Token.
Token ID13
Feature activation+8.81e-03

Pos logit contributions
edly+0.154
iece+0.148
 seas+0.141
Edward+0.134
oph+0.133
Neg logit contributions
 cleans-0.082
 need-0.075
 outage-0.074
uffy-0.073
run-0.071
Token They
Token ID1119
Feature activation-8.76e-04

Pos logit contributions
iece+0.019
edly+0.019
 seas+0.018
Edward+0.017
adies+0.016
Neg logit contributions
 cleans-0.009
run-0.009
uffy-0.009
 Kim-0.008
 Liz-0.008
Token both
Token ID1111
Feature activation-8.38e-03

Pos logit contributions
 cleans+0.001
 need+0.001
 slammed+0.001
uffy+0.001
 exc+0.001
Neg logit contributions
edly-0.002
iece-0.002
 seas-0.002
Edward-0.002
 Edward-0.001
Token grabbed
Token ID13176
Feature activation+3.39e-02

Pos logit contributions
 cleans+0.010
 need+0.009
run+0.009
 slammed+0.008
 exc+0.008
Neg logit contributions
edly-0.017
iece-0.017
 seas-0.016
Edward-0.015
 Edward-0.015
Token the
Token ID262
Feature activation-4.32e-03

Pos logit contributions
edly+0.070
iece+0.065
 seas+0.060
Edward+0.059
oph+0.059
Neg logit contributions
 cleans-0.047
 need-0.041
run-0.038
 Kim-0.036
 hose-0.036
Token Lily
Token ID20037
Feature activation+7.12e-03

Pos logit contributions
iece+0.006
edly+0.006
 seas+0.005
Edward+0.005
 oceans+0.005
Neg logit contributions
 cleans-0.003
uffy-0.003
 need-0.002
 Kim-0.002
 exc-0.002
Token sees
Token ID7224
Feature activation-1.73e-03

Pos logit contributions
edly+0.013
iece+0.013
 seas+0.012
Edward+0.011
ly+0.011
Neg logit contributions
 cleans-0.010
uffy-0.009
 need-0.009
 outage-0.009
run-0.009
Token a
Token ID257
Feature activation+1.76e-02

Pos logit contributions
 cleans+0.003
uffy+0.003
 need+0.003
 hose+0.003
 Kim+0.003
Neg logit contributions
edly-0.003
iece-0.003
 seas-0.002
Edward-0.002
ly-0.002
Token big
Token ID1263
Feature activation-4.54e-03

Pos logit contributions
edly+0.034
iece+0.033
 seas+0.033
Edward+0.030
ly+0.030
Neg logit contributions
 cleans-0.023
run-0.020
uffy-0.020
 outage-0.020
 need-0.019
Token red
Token ID2266
Feature activation+2.82e-02

Pos logit contributions
 cleans+0.007
uffy+0.006
run+0.006
 outage+0.006
 need+0.006
Neg logit contributions
edly-0.008
iece-0.008
 seas-0.008
Edward-0.007
ly-0.007
Token tomato
Token ID24240
Feature activation+7.41e-02

Pos logit contributions
edly+0.056
iece+0.054
Edward+0.048
Cl+0.046
 Edward+0.045
Neg logit contributions
 hose-0.039
 cleans-0.036
 rake-0.036
 need-0.036
uffy-0.034
Token on
Token ID319
Feature activation+2.01e-02

Pos logit contributions
edly+0.138
iece+0.137
 seas+0.127
Edward+0.121
ly+0.117
Neg logit contributions
 cleans-0.104
uffy-0.092
 need-0.089
 outage-0.089
run-0.088
Token a
Token ID257
Feature activation+8.03e-02

Pos logit contributions
edly+0.043
iece+0.043
 seas+0.038
ly+0.037
Edward+0.037
Neg logit contributions
 cleans-0.024
 need-0.021
 hose-0.019
 exc-0.019
 Kitty-0.019
Token vine
Token ID17793
Feature activation+3.84e-02

Pos logit contributions
edly+0.151
iece+0.149
 seas+0.133
Edward+0.127
ly+0.123
Neg logit contributions
 cleans-0.111
uffy-0.101
 outage-0.099
 need-0.098
 hose-0.096
Token.
Token ID13
Feature activation+4.41e-03

Pos logit contributions
edly+0.076
iece+0.076
 seas+0.070
Edward+0.065
ly+0.065
Neg logit contributions
 cleans-0.050
uffy-0.044
 outage-0.042
run-0.042
 need-0.041
Token She
Token ID1375
Feature activation-6.40e-03

Pos logit contributions
edly+0.008
iece+0.008
 seas+0.007
Edward+0.007
ly+0.006
Neg logit contributions
 cleans-0.007
uffy-0.006
run-0.006
 outage-0.006
 need-0.006
Token to
Token ID284
Feature activation-5.85e-03

Pos logit contributions
edly+0.010
iece+0.010
 seas+0.008
Edward+0.008
ly+0.008
Neg logit contributions
 cleans-0.007
 need-0.006
 outage-0.006
uffy-0.006
run-0.006
Token play
Token ID711
Feature activation-2.10e-02

Pos logit contributions
 cleans+0.007
uffy+0.006
run+0.006
 outage+0.006
 need+0.006
Neg logit contributions
iece-0.012
edly-0.011
 seas-0.011
Edward-0.011
ly-0.010
Token?"
Token ID1701
Feature activation+4.93e-02

Pos logit contributions
 cleans+0.027
 need+0.024
run+0.023
uffy+0.023
 outage+0.022
Neg logit contributions
edly-0.043
iece-0.042
 seas-0.036
oph-0.036
Edward-0.035
Token
Token ID198
Feature activation+1.60e-02

Pos logit contributions
edly+0.101
iece+0.101
 seas+0.094
Edward+0.089
ly+0.087
Neg logit contributions
 cleans-0.061
uffy-0.053
 outage-0.052
run-0.051
 need-0.050
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
iece+0.030
edly+0.030
 seas+0.028
Edward+0.027
 Edward+0.025
Neg logit contributions
 cleans-0.022
 outage-0.020
uffy-0.019
 need-0.019
run-0.019
TokenTom
Token ID13787
Feature activation+3.06e-02

Pos logit contributions
edly+0.023
iece+0.021
 seas+0.021
ly+0.019
 Edward+0.018
Neg logit contributions
 cleans-0.019
uffy-0.017
 Kim-0.017
 exc-0.016
 Kitty-0.016
Token says
Token ID1139
Feature activation+1.06e-02

Pos logit contributions
edly+0.070
iece+0.070
 seas+0.065
Edward+0.062
ly+0.061
Neg logit contributions
 cleans-0.031
uffy-0.026
 outage-0.024
run-0.024
 need-0.024
Token,
Token ID11
Feature activation+1.14e-02

Pos logit contributions
edly+0.026
iece+0.026
 seas+0.024
oph+0.023
Edward+0.023
Neg logit contributions
 cleans-0.009
uffy-0.007
run-0.007
 need-0.007
 exc-0.006
Token "
Token ID366
Feature activation+2.99e-02

Pos logit contributions
edly+0.024
iece+0.023
 seas+0.022
Edward+0.021
ly+0.020
Neg logit contributions
 cleans-0.014
uffy-0.012
 outage-0.012
run-0.012
 need-0.012
TokenLet
Token ID5756
Feature activation+1.03e-02

Pos logit contributions
iece+0.052
edly+0.048
 seas+0.046
ly+0.043
oph+0.043
Neg logit contributions
 exc-0.042
 cleans-0.042
 outage-0.041
 need-0.040
run-0.039
Token's
Token ID338
Feature activation-3.57e-04

Pos logit contributions
edly+0.023
iece+0.021
 seas+0.020
Edward+0.018
 oceans+0.018
Neg logit contributions
 cleans-0.013
 need-0.011
uffy-0.011
 tells-0.010
 know-0.010
TokenYes
Token ID5297
Feature activation-2.62e-02

Pos logit contributions
iece+0.056
 seas+0.053
edly+0.052
adies+0.047
 armor+0.046
Neg logit contributions
run-0.035
 need-0.030
 exc-0.030
 cleans-0.030
 have-0.029
Token!
Token ID0
Feature activation-3.33e-02

Pos logit contributions
 cleans+0.033
uffy+0.029
 outage+0.028
run+0.028
 need+0.027
Neg logit contributions
edly-0.053
iece-0.053
 seas-0.049
Edward-0.046
ly-0.046
Token Of
Token ID3226
Feature activation+2.40e-02

Pos logit contributions
 cleans+0.050
uffy+0.045
run+0.044
 outage+0.044
 need+0.043
Neg logit contributions
edly-0.059
iece-0.058
 seas-0.054
Edward-0.050
ly-0.049
Token course
Token ID1781
Feature activation-2.05e-02

Pos logit contributions
edly+0.030
iece+0.030
 seas+0.027
Edward+0.024
ly+0.024
Neg logit contributions
 cleans-0.048
uffy-0.045
 outage-0.044
run-0.044
 need-0.043
Token.
Token ID13
Feature activation-3.65e-02

Pos logit contributions
 cleans+0.034
uffy+0.031
 outage+0.031
run+0.030
 need+0.030
Neg logit contributions
edly-0.033
iece-0.032
 seas-0.030
Edward-0.028
ly-0.027
Token I
Token ID314
Feature activation+4.52e-03

Pos logit contributions
 cleans+0.059
uffy+0.053
 outage+0.052
run+0.051
 need+0.051
Neg logit contributions
edly-0.060
iece-0.059
 seas-0.054
Edward-0.051
ly-0.050
Token have
Token ID423
Feature activation+1.32e-03

Pos logit contributions
edly+0.009
iece+0.009
 seas+0.008
Edward+0.008
 seven+0.008
Neg logit contributions
 cleans-0.005
uffy-0.005
 outage-0.005
run-0.004
 dripping-0.004
Token a
Token ID257
Feature activation+1.53e-02

Pos logit contributions
iece+0.002
edly+0.002
Edward+0.002
ly+0.002
oph+0.002
Neg logit contributions
 cleans-0.002
 need-0.002
run-0.002
 needs-0.002
 ruined-0.002
Token lot
Token ID1256
Feature activation-9.72e-03

Pos logit contributions
 seas+0.027
edly+0.025
iece+0.025
 seven+0.024
Edward+0.024
Neg logit contributions
 cleans-0.022
 outage-0.020
uffy-0.019
run-0.019
 drown-0.018
Token of
Token ID286
Feature activation+1.12e-02

Pos logit contributions
 cleans+0.010
run+0.008
 outage+0.008
 need+0.008
uffy+0.008
Neg logit contributions
edly-0.023
iece-0.022
 seas-0.021
Edward-0.020
 Edward-0.019
Token colorful
Token ID20239
Feature activation+4.45e-02

Pos logit contributions
edly+0.021
iece+0.021
 seas+0.019
Edward+0.018
ly+0.018
Neg logit contributions
 cleans-0.016
uffy-0.014
 outage-0.014
run-0.014
 need-0.013
Token an
Token ID281
Feature activation-6.05e-03

Pos logit contributions
 cleans+0.062
uffy+0.057
 outage+0.057
run+0.055
 need+0.055
Neg logit contributions
edly-0.057
iece-0.056
 seas-0.052
Edward-0.047
ly-0.046
Token eye
Token ID4151
Feature activation+1.19e-02

Pos logit contributions
 cleans+0.009
uffy+0.008
 outage+0.008
run+0.007
 need+0.007
Neg logit contributions
edly-0.011
iece-0.011
 seas-0.010
ly-0.010
Edward-0.009
Token on
Token ID319
Feature activation-3.45e-02

Pos logit contributions
edly+0.022
iece+0.021
 seas+0.020
Edward+0.019
oph+0.018
Neg logit contributions
 cleans-0.018
uffy-0.015
 outage-0.015
run-0.015
 need-0.015
Token the
Token ID262
Feature activation+7.42e-03

Pos logit contributions
 cleans+0.055
uffy+0.050
 need+0.049
run+0.048
 outage+0.048
Neg logit contributions
edly-0.058
iece-0.058
 seas-0.052
Edward-0.049
ly-0.047
Token cooler
Token ID19346
Feature activation-1.68e-02

Pos logit contributions
edly+0.015
iece+0.015
 seas+0.014
Edward+0.013
ly+0.013
Neg logit contributions
 cleans-0.010
uffy-0.008
 need-0.008
 outage-0.008
run-0.008
Token to
Token ID284
Feature activation+2.41e-02

Pos logit contributions
 cleans+0.025
uffy+0.022
 outage+0.022
 need+0.022
run+0.022
Neg logit contributions
edly-0.030
iece-0.030
 seas-0.027
Edward-0.026
ly-0.025
Token make
Token ID787
Feature activation+3.65e-03

Pos logit contributions
iece+0.047
edly+0.046
 seas+0.045
ly+0.041
Edward+0.040
Neg logit contributions
 cleans-0.031
uffy-0.029
 outage-0.028
run-0.026
ucker-0.025
Token sure
Token ID1654
Feature activation-6.87e-03

Pos logit contributions
edly+0.007
iece+0.006
 seas+0.006
Edward+0.006
oph+0.005
Neg logit contributions
 cleans-0.006
 need-0.005
run-0.005
uffy-0.005
 exc-0.005
Token no
Token ID645
Feature activation-6.58e-03

Pos logit contributions
 cleans+0.012
uffy+0.012
 outage+0.011
run+0.011
 need+0.011
Neg logit contributions
iece-0.010
edly-0.010
 seas-0.009
ly-0.008
Edward-0.008
Token more
Token ID517
Feature activation+3.76e-03

Pos logit contributions
 cleans+0.013
uffy+0.012
 outage+0.011
run+0.011
 need+0.011
Neg logit contributions
edly-0.009
iece-0.009
 seas-0.008
Edward-0.007
ly-0.007
Token naughty
Token ID45128
Feature activation-1.61e-02

Pos logit contributions
edly+0.006
 seas+0.006
iece+0.006
ly+0.006
 Edward+0.005
Neg logit contributions
uffy-0.006
 cleans-0.006
 outage-0.005
ric-0.005
run-0.005
Token
Token ID198
Feature activation-8.94e-03

Pos logit contributions
 cleans+0.049
 outage+0.047
 flood+0.044
 need+0.044
 slammed+0.043
Neg logit contributions
iece-0.051
edly-0.049
Edward-0.043
 Edward-0.043
 Avery-0.043
TokenM
Token ID44
Feature activation-3.07e-02

Pos logit contributions
 cleans+0.017
run+0.016
uffy+0.016
 need+0.015
 exc+0.015
Neg logit contributions
edly-0.012
iece-0.012
 seas-0.011
ly-0.010
Edward-0.009
Tokenummy
Token ID13513
Feature activation-3.37e-02

Pos logit contributions
 cleans+0.047
uffy+0.043
 outage+0.041
run+0.041
 need+0.041
Neg logit contributions
iece-0.054
edly-0.054
 seas-0.049
Edward-0.046
ly-0.045
Token said
Token ID531
Feature activation-5.99e-03

Pos logit contributions
 cleans+0.045
uffy+0.038
 outage+0.037
run+0.037
 need+0.036
Neg logit contributions
iece-0.067
edly-0.067
 seas-0.062
Edward-0.058
ly-0.056
Token '
Token ID705
Feature activation+7.45e-03

Pos logit contributions
 cleans+0.006
run+0.005
 need+0.004
uffy+0.004
 Kitty+0.004
Neg logit contributions
iece-0.014
edly-0.013
 seas-0.013
 oceans-0.012
Edward-0.012
Tokenyou
Token ID5832
Feature activation+1.76e-02

Pos logit contributions
iece+0.011
edly+0.011
 seas+0.010
adies+0.009
ly+0.009
Neg logit contributions
run-0.013
 cleans-0.012
 need-0.012
 exc-0.011
 have-0.011
Token can
Token ID460
Feature activation+2.15e-02

Pos logit contributions
edly+0.041
iece+0.041
 seas+0.038
Edward+0.036
ly+0.036
Neg logit contributions
 cleans-0.017
uffy-0.014
 outage-0.013
run-0.013
 need-0.013
Token do
Token ID466
Feature activation+1.77e-02

Pos logit contributions
iece+0.040
edly+0.039
 seas+0.036
Edward+0.035
ly+0.035
Neg logit contributions
 cleans-0.030
uffy-0.026
 outage-0.025
run-0.025
 slammed-0.023
Token this
Token ID428
Feature activation+1.75e-02

Pos logit contributions
edly+0.029
iece+0.028
 seas+0.026
Edward+0.024
ly+0.023
Neg logit contributions
 cleans-0.030
uffy-0.026
 need-0.026
 outage-0.026
run-0.026
Token yourself
Token ID3511
Feature activation+2.61e-02

Pos logit contributions
edly+0.035
iece+0.034
 seas+0.031
Edward+0.030
Please+0.028
Neg logit contributions
 cleans-0.023
uffy-0.021
 need-0.020
 outage-0.020
run-0.020
Token now
Token ID783
Feature activation-8.73e-03

Pos logit contributions
edly+0.050
iece+0.050
 seas+0.047
Edward+0.043
oph+0.042
Neg logit contributions
 cleans-0.034
 need-0.031
run-0.031
 outage-0.030
uffy-0.030
Token.
Token ID13
Feature activation-9.74e-04

Pos logit contributions
iece+0.007
edly+0.006
ly+0.006
 seas+0.005
fully+0.005
Neg logit contributions
uffy-0.007
 cleans-0.007
ric-0.007
 outage-0.006
 slam-0.006
Token<|endoftext|>
Token ID50256
Feature activation-8.17e-03

Pos logit contributions
 outage+0.002
 cleans+0.002
 need+0.001
 flood+0.001
uffy+0.001
Neg logit contributions
iece-0.002
edly-0.002
Edward-0.001
 Edward-0.001
oph-0.001
TokenOnce
Token ID7454
Feature activation-4.05e-02

Pos logit contributions
 cleans+0.011
 outage+0.010
uffy+0.010
run+0.009
 need+0.009
Neg logit contributions
edly-0.015
iece-0.015
 seas-0.014
Edward-0.014
 Edward-0.013
Token upon
Token ID2402
Feature activation+4.74e-02

Pos logit contributions
 cleans+0.094
 outage+0.086
 drown+0.084
 slam+0.083
 dripping+0.082
Neg logit contributions
iece-0.035
 seas-0.034
Edward-0.028
ly-0.028
oph-0.028
Token a
Token ID257
Feature activation-4.64e-02

Pos logit contributions
edly+0.097
iece+0.095
oph+0.084
 seas+0.083
ly+0.082
Neg logit contributions
 need-0.058
 have-0.058
 cleans-0.057
 exc-0.056
 know-0.054
Token time
Token ID640
Feature activation+2.46e-02

Pos logit contributions
 cleans+0.071
uffy+0.064
 outage+0.062
run+0.062
 need+0.061
Neg logit contributions
edly-0.081
iece-0.081
 seas-0.074
Edward-0.068
ly-0.068
Token there
Token ID612
Feature activation-1.47e-02

Pos logit contributions
edly+0.049
iece+0.049
 seas+0.046
Edward+0.043
ly+0.042
Neg logit contributions
 cleans-0.032
 outage-0.027
uffy-0.027
run-0.026
 need-0.026
Token was
Token ID373
Feature activation-7.91e-03

Pos logit contributions
 cleans+0.024
 outage+0.023
run+0.022
uffy+0.021
 drown+0.020
Neg logit contributions
iece-0.023
 seas-0.022
edly-0.021
Edward-0.019
 Edward-0.019
Token a
Token ID257
Feature activation-1.79e-04

Pos logit contributions
 cleans+0.010
 Kitty+0.010
 need+0.009
 exc+0.009
 have+0.009
Neg logit contributions
edly-0.016
iece-0.016
ly-0.014
 seas-0.013
oph-0.013
Token dog
Token ID3290
Feature activation-2.30e-03

Pos logit contributions
 cleans+0.000
run+0.000
 outage+0.000
uffy+0.000
 need+0.000
Neg logit contributions
edly-0.000
iece-0.000
 seas-0.000
Edward-0.000
ly-0.000
Token called
Token ID1444
Feature activation-4.34e-02

Pos logit contributions
 cleans+0.003
 outage+0.002
run+0.002
uffy+0.002
 drown+0.002
Neg logit contributions
edly-0.005
iece-0.004
 seas-0.004
ly-0.004
Please-0.004
TokenShe
Token ID3347
Feature activation-1.15e-02

Pos logit contributions
 cleans+0.004
run+0.004
uffy+0.004
 Kitty+0.004
 exc+0.004
Neg logit contributions
iece-0.004
 seas-0.004
edly-0.004
 oceans-0.003
 Avery-0.003
Token took
Token ID1718
Feature activation+1.08e-02

Pos logit contributions
 cleans+0.012
 slammed+0.011
run+0.010
 locked+0.010
 need+0.009
Neg logit contributions
iece-0.027
edly-0.025
 seas-0.024
Edward-0.023
adies-0.022
Token the
Token ID262
Feature activation-1.26e-02

Pos logit contributions
edly+0.022
iece+0.021
 seas+0.020
Edward+0.019
oph+0.018
Neg logit contributions
 cleans-0.014
 need-0.013
 Kitty-0.013
 Kim-0.013
 know-0.013
Token note
Token ID3465
Feature activation+2.49e-03

Pos logit contributions
 cleans+0.020
 need+0.018
uffy+0.017
 needs+0.017
 outage+0.017
Neg logit contributions
edly-0.023
iece-0.022
 seas-0.019
Edward-0.018
 oceans-0.018
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
edly+0.005
iece+0.005
 seas+0.004
Edward+0.004
Please+0.004
Neg logit contributions
 cleans-0.003
 outage-0.003
run-0.003
 need-0.003
uffy-0.003
Token ran
Token ID4966
Feature activation-1.91e-02

Pos logit contributions
edly+0.024
iece+0.024
 seas+0.022
Edward+0.022
ly+0.020
Neg logit contributions
 cleans-0.015
 slammed-0.012
 need-0.012
run-0.012
uffy-0.011
Token home
Token ID1363
Feature activation+3.36e-04

Pos logit contributions
run+0.020
 cleans+0.020
 Kim+0.019
 need+0.019
 Kitty+0.019
Neg logit contributions
iece-0.039
edly-0.039
 seas-0.036
Edward-0.035
oph-0.035
Token to
Token ID284
Feature activation+8.95e-03

Pos logit contributions
edly+0.001
iece+0.001
 seas+0.001
ly+0.000
Edward+0.000
Neg logit contributions
 cleans-0.001
uffy-0.000
 outage-0.000
 need-0.000
run-0.000
Token show
Token ID905
Feature activation+2.23e-02

Pos logit contributions
iece+0.017
edly+0.017
 seas+0.015
 Edward+0.015
Edward+0.015
Neg logit contributions
 cleans-0.012
uffy-0.012
 outage-0.011
run-0.011
ucker-0.010
Token her
Token ID607
Feature activation-2.53e-02

Pos logit contributions
edly+0.034
iece+0.033
 seas+0.031
Edward+0.028
ly+0.026
Neg logit contributions
 cleans-0.040
 need-0.035
uffy-0.035
run-0.035
 outage-0.035
Token parents
Token ID3397
Feature activation-2.92e-02

Pos logit contributions
 cleans+0.036
 outage+0.035
uffy+0.033
run+0.032
ucker+0.031
Neg logit contributions
 seas-0.043
edly-0.042
iece-0.042
 Amber-0.040
 Edward-0.039
Token things
Token ID1243
Feature activation+1.14e-02

Pos logit contributions
 cleans+0.006
uffy+0.005
 need+0.005
 outage+0.005
run+0.005
Neg logit contributions
edly-0.006
iece-0.006
 seas-0.005
Edward-0.005
oph-0.005
Token.
Token ID13
Feature activation-4.53e-03

Pos logit contributions
iece+0.019
edly+0.018
 seas+0.018
ly+0.017
 oceans+0.016
Neg logit contributions
 cleans-0.019
uffy-0.018
 outage-0.016
run-0.016
ucker-0.016
Token One
Token ID1881
Feature activation-3.30e-02

Pos logit contributions
 cleans+0.007
uffy+0.007
 outage+0.007
run+0.006
 dripping+0.006
Neg logit contributions
iece-0.007
edly-0.007
 seas-0.007
Edward-0.006
 Edward-0.006
Token day
Token ID1110
Feature activation+1.38e-02

Pos logit contributions
 cleans+0.050
uffy+0.044
run+0.043
 outage+0.042
 need+0.041
Neg logit contributions
edly-0.059
iece-0.059
 seas-0.055
ly-0.051
Edward-0.050
Token he
Token ID339
Feature activation+3.01e-02

Pos logit contributions
edly+0.028
iece+0.028
 seas+0.026
Edward+0.025
ly+0.024
Neg logit contributions
 cleans-0.017
uffy-0.015
 outage-0.014
run-0.014
 need-0.014
Token was
Token ID373
Feature activation-8.95e-03

Pos logit contributions
edly+0.059
iece+0.058
Edward+0.051
 seas+0.051
ly+0.049
Neg logit contributions
 cleans-0.041
 need-0.036
uffy-0.036
 slammed-0.035
 exc-0.034
Token out
Token ID503
Feature activation-1.53e-02

Pos logit contributions
 cleans+0.011
uffy+0.009
 need+0.009
 outage+0.009
run+0.009
Neg logit contributions
edly-0.019
iece-0.019
 seas-0.017
Edward-0.017
ly-0.016
Token exploring
Token ID13504
Feature activation+2.38e-02

Pos logit contributions
 cleans+0.022
uffy+0.020
 outage+0.019
run+0.017
ucker+0.017
Neg logit contributions
iece-0.028
edly-0.028
 seas-0.026
ly-0.024
Edward-0.023
Token the
Token ID262
Feature activation+1.63e-02

Pos logit contributions
edly+0.048
iece+0.046
Edward+0.042
oph+0.041
 seas+0.040
Neg logit contributions
 cleans-0.031
 need-0.028
run-0.026
 outage-0.026
uffy-0.026
Token woods
Token ID16479
Feature activation-1.10e-02

Pos logit contributions
edly+0.037
iece+0.035
Edward+0.031
 Edward+0.030
oph+0.030
Neg logit contributions
 cleans-0.018
 outage-0.016
 hose-0.016
 need-0.016
uffy-0.016
Token and
Token ID290
Feature activation+1.53e-02

Pos logit contributions
 cleans+0.013
 need+0.013
 outage+0.012
run+0.012
 slammed+0.012
Neg logit contributions
edly-0.021
iece-0.020
oph-0.020
Edward-0.020
 seas-0.019
Token little
Token ID1310
Feature activation+4.95e-04

Pos logit contributions
edly+0.001
iece+0.001
 seas+0.001
Edward+0.001
ly+0.001
Neg logit contributions
 cleans-0.001
run-0.001
 outage-0.001
uffy-0.001
 need-0.001
Token girl
Token ID2576
Feature activation+4.18e-02

Pos logit contributions
edly+0.001
iece+0.001
 seas+0.001
Edward+0.001
ly+0.001
Neg logit contributions
 cleans-0.001
uffy-0.001
 outage-0.001
run-0.001
 need-0.001
Token named
Token ID3706
Feature activation-4.74e-02

Pos logit contributions
edly+0.082
iece+0.081
 seas+0.076
ly+0.075
Please+0.075
Neg logit contributions
 cleans-0.050
 outage-0.045
run-0.043
 drown-0.043
uffy-0.043
Token Lily
Token ID20037
Feature activation+3.27e-03

Pos logit contributions
 cleans+0.076
 outage+0.069
run+0.066
uffy+0.066
ric+0.065
Neg logit contributions
edly-0.077
iece-0.076
 seas-0.070
ly-0.068
oph-0.066
Token.
Token ID13
Feature activation-1.96e-02

Pos logit contributions
iece+0.005
edly+0.004
ly+0.004
Please+0.004
 seas+0.004
Neg logit contributions
 cleans-0.006
uffy-0.006
 outage-0.005
run-0.005
 drown-0.005
Token She
Token ID1375
Feature activation-2.05e-02

Pos logit contributions
 cleans+0.032
uffy+0.028
 outage+0.028
run+0.028
 need+0.027
Neg logit contributions
edly-0.033
iece-0.033
 seas-0.030
Edward-0.028
ly-0.027
Token loved
Token ID6151
Feature activation+6.61e-03

Pos logit contributions
 cleans+0.026
run+0.023
 outage+0.023
uffy+0.023
 need+0.021
Neg logit contributions
edly-0.041
iece-0.040
 seas-0.038
ly-0.036
Edward-0.035
Token to
Token ID284
Feature activation+7.23e-03

Pos logit contributions
edly+0.011
iece+0.011
 seas+0.010
Edward+0.009
ly+0.009
Neg logit contributions
 cleans-0.011
uffy-0.010
 outage-0.010
run-0.010
 need-0.009
Token skip
Token ID14267
Feature activation-2.24e-03

Pos logit contributions
edly+0.012
iece+0.012
 seas+0.012
Edward+0.011
ly+0.011
Neg logit contributions
 cleans-0.010
uffy-0.010
run-0.010
 outage-0.010
ucker-0.009
Token and
Token ID290
Feature activation+1.21e-02

Pos logit contributions
 cleans+0.003
uffy+0.002
 need+0.002
run+0.002
 Kitty+0.002
Neg logit contributions
iece-0.005
edly-0.005
Edward-0.004
 Edward-0.004
oph-0.004
Token jump
Token ID4391
Feature activation+5.18e-03

Pos logit contributions
edly+0.025
iece+0.025
 seas+0.024
Edward+0.022
ly+0.022
Neg logit contributions
 cleans-0.014
uffy-0.012
 outage-0.012
run-0.012
 need-0.011
TokenOnce
Token ID7454
Feature activation-3.69e-02

Pos logit contributions
 cleans+0.010
uffy+0.009
 outage+0.009
run+0.009
 need+0.009
Neg logit contributions
edly-0.016
iece-0.016
 seas-0.015
Edward-0.014
ly-0.014
Token upon
Token ID2402
Feature activation+5.21e-02

Pos logit contributions
 cleans+0.088
 outage+0.078
 slam+0.076
 drown+0.075
 sends+0.075
Neg logit contributions
iece-0.032
 seas-0.030
Edward-0.025
 Avery-0.025
 Amber-0.025
Token a
Token ID257
Feature activation-3.69e-02

Pos logit contributions
edly+0.106
iece+0.104
oph+0.094
 seas+0.091
ly+0.091
Neg logit contributions
 need-0.066
 have-0.064
 cleans-0.063
 exc-0.061
 know-0.060
Token time
Token ID640
Feature activation+2.77e-02

Pos logit contributions
 cleans+0.061
 outage+0.054
uffy+0.054
run+0.053
 need+0.052
Neg logit contributions
edly-0.060
iece-0.058
 seas-0.055
Edward-0.052
ly-0.050
Token,
Token ID11
Feature activation+6.83e-03

Pos logit contributions
iece+0.049
edly+0.048
 seas+0.046
Edward+0.043
 Edward+0.042
Neg logit contributions
 cleans-0.041
 outage-0.036
 need-0.034
uffy-0.033
run-0.033
Token there
Token ID612
Feature activation-1.17e-02

Pos logit contributions
edly+0.012
iece+0.012
 seas+0.011
Edward+0.010
ly+0.010
Neg logit contributions
 cleans-0.011
 outage-0.010
uffy-0.009
run-0.009
 need-0.009
Token was
Token ID373
Feature activation-6.08e-03

Pos logit contributions
 cleans+0.019
 outage+0.018
run+0.017
uffy+0.017
ucker+0.016
Neg logit contributions
iece-0.018
 seas-0.017
edly-0.017
Edward-0.015
 Edward-0.015
Token a
Token ID257
Feature activation+3.50e-03

Pos logit contributions
 Kitty+0.007
 cleans+0.007
 need+0.006
 exc+0.006
 have+0.006
Neg logit contributions
iece-0.014
edly-0.013
ly-0.012
oph-0.011
rier-0.011
Token beetle
Token ID45489
Feature activation+5.90e-02

Pos logit contributions
edly+0.006
iece+0.006
 seas+0.005
Edward+0.005
ly+0.005
Neg logit contributions
 cleans-0.006
run-0.005
 outage-0.005
uffy-0.005
 need-0.005
Token who
Token ID508
Feature activation-3.21e-02

Pos logit contributions
edly+0.119
iece+0.113
 seas+0.109
ly+0.103
Please+0.101
Neg logit contributions
 cleans-0.077
run-0.063
uffy-0.063
 outage-0.062
 drown-0.059
Token lived
Token ID5615
Feature activation+2.35e-04

Pos logit contributions
 cleans+0.044
 outage+0.041
uffy+0.039
run+0.038
 drown+0.035
Neg logit contributions
edly-0.061
iece-0.058
 seas-0.056
ly-0.053
Edward-0.052
Token She
Token ID1375
Feature activation-1.01e-02

Pos logit contributions
uffy+0.004
 cleans+0.004
 drown+0.004
 outage+0.004
run+0.003
Neg logit contributions
iece-0.003
edly-0.002
ly-0.002
Please-0.002
oph-0.002
Token thought
Token ID1807
Feature activation+8.30e-03

Pos logit contributions
 cleans+0.013
 outage+0.012
uffy+0.012
run+0.011
 need+0.011
Neg logit contributions
edly-0.020
iece-0.019
 seas-0.018
ly-0.017
Edward-0.017
Token it
Token ID340
Feature activation-1.77e-02

Pos logit contributions
edly+0.013
iece+0.013
 seas+0.012
Edward+0.011
ly+0.011
Neg logit contributions
 cleans-0.014
uffy-0.013
 outage-0.013
run-0.013
 need-0.013
Token was
Token ID373
Feature activation-2.50e-02

Pos logit contributions
 cleans+0.028
run+0.026
 outage+0.026
 drown+0.025
arter+0.024
Neg logit contributions
iece-0.029
edly-0.028
 seas-0.026
ly-0.026
Please-0.024
Token so
Token ID523
Feature activation-4.71e-02

Pos logit contributions
 cleans+0.041
uffy+0.037
 outage+0.036
run+0.036
 need+0.034
Neg logit contributions
edly-0.040
iece-0.040
 seas-0.038
Edward-0.035
 Edward-0.034
Token strange
Token ID6283
Feature activation-1.51e-02

Pos logit contributions
 cleans+0.082
run+0.076
uffy+0.074
 outage+0.074
ric+0.070
Neg logit contributions
 seas-0.066
edly-0.064
Prin-0.062
ly-0.062
iece-0.062
Token and
Token ID290
Feature activation+2.51e-03

Pos logit contributions
 cleans+0.020
uffy+0.018
 outage+0.017
run+0.017
 need+0.017
Neg logit contributions
edly-0.030
iece-0.029
 seas-0.027
Edward-0.025
ly-0.025
Token cute
Token ID13779
Feature activation-2.52e-02

Pos logit contributions
edly+0.004
iece+0.004
 seas+0.004
ly+0.004
Please+0.004
Neg logit contributions
 cleans-0.004
uffy-0.003
 outage-0.003
run-0.003
 drown-0.003
Token.
Token ID13
Feature activation-5.77e-03

Pos logit contributions
 cleans+0.031
uffy+0.027
 outage+0.026
run+0.026
 need+0.025
Neg logit contributions
edly-0.052
iece-0.052
 seas-0.048
Edward-0.046
ly-0.045
Token She
Token ID1375
Feature activation-1.70e-02

Pos logit contributions
 cleans+0.007
uffy+0.006
 outage+0.006
run+0.006
 need+0.006
Neg logit contributions
edly-0.012
iece-0.012
 seas-0.011
Edward-0.010
ly-0.010
Token wanted
Token ID2227
Feature activation-1.66e-02

Pos logit contributions
 cleans+0.020
uffy+0.018
 need+0.017
 exc+0.017
run+0.017
Neg logit contributions
iece-0.036
edly-0.035
 seas-0.033
Edward-0.031
 Edward-0.030
Token,
Token ID11
Feature activation-9.09e-03

Pos logit contributions
 cleans+0.004
run+0.004
 exc+0.003
 need+0.003
 Kitty+0.003
Neg logit contributions
iece-0.005
edly-0.005
 seas-0.005
oph-0.005
Edward-0.005
Token "
Token ID366
Feature activation+2.28e-02

Pos logit contributions
 cleans+0.010
run+0.008
uffy+0.008
 need+0.008
 outage+0.008
Neg logit contributions
iece-0.020
edly-0.020
 seas-0.019
Edward-0.018
oph-0.017
TokenNo
Token ID2949
Feature activation-2.41e-02

Pos logit contributions
iece+0.040
 seas+0.037
edly+0.037
 oceans+0.032
 Edward+0.032
Neg logit contributions
run-0.035
 need-0.031
 exc-0.030
 cleans-0.030
 Kitty-0.030
Token,
Token ID11
Feature activation-1.74e-02

Pos logit contributions
 cleans+0.036
uffy+0.032
 outage+0.031
run+0.030
 exc+0.029
Neg logit contributions
 seas-0.041
edly-0.041
iece-0.040
ly-0.038
Edward-0.036
Token my
Token ID616
Feature activation+1.84e-02

Pos logit contributions
 cleans+0.029
uffy+0.027
 outage+0.026
run+0.025
 need+0.024
Neg logit contributions
edly-0.027
iece-0.026
 seas-0.025
ly-0.023
Edward-0.023
Token arm
Token ID3211
Feature activation-7.99e-02

Pos logit contributions
edly+0.035
iece+0.035
 seas+0.033
ly+0.031
Edward+0.030
Neg logit contributions
 cleans-0.024
 outage-0.020
uffy-0.020
 need-0.019
run-0.019
Token really
Token ID1107
Feature activation-2.68e-02

Pos logit contributions
 cleans+0.097
uffy+0.083
 outage+0.080
run+0.077
 drown+0.075
Neg logit contributions
edly-0.160
iece-0.157
 seas-0.146
ly-0.146
Please-0.136
Token hurts
Token ID20406
Feature activation-3.12e-02

Pos logit contributions
 cleans+0.035
uffy+0.032
 outage+0.031
run+0.028
ric+0.028
Neg logit contributions
edly-0.049
iece-0.047
 seas-0.047
ly-0.045
Please-0.043
Token,"
Token ID553
Feature activation+2.85e-02

Pos logit contributions
 cleans+0.043
uffy+0.038
 outage+0.037
run+0.036
 need+0.035
Neg logit contributions
edly-0.059
iece-0.058
 seas-0.054
ly-0.051
Edward-0.050
Token while
Token ID981
Feature activation+1.10e-02

Pos logit contributions
iece+0.058
edly+0.055
 seas+0.051
Edward+0.051
Marie+0.049
Neg logit contributions
 cleans-0.035
run-0.032
 Kim-0.030
 exc-0.030
 need-0.030
Token he
Token ID339
Feature activation+2.19e-02

Pos logit contributions
edly+0.020
iece+0.020
 seas+0.018
Edward+0.017
ly+0.017
Neg logit contributions
 cleans-0.016
uffy-0.015
run-0.014
 need-0.014
 outage-0.014
Token and
Token ID290
Feature activation-2.28e-02

Pos logit contributions
 cleans+0.104
uffy+0.095
 outage+0.094
run+0.093
 slammed+0.091
Neg logit contributions
edly-0.087
iece-0.086
ly-0.078
 seas-0.075
Please-0.068
Token helped
Token ID4193
Feature activation-3.36e-02

Pos logit contributions
uffy+0.035
ric+0.033
 outage+0.031
ats+0.030
arter+0.030
Neg logit contributions
edly-0.037
ly-0.035
iece-0.034
Please-0.033
 Please-0.031
Token Mom
Token ID11254
Feature activation-4.21e-02

Pos logit contributions
 cleans+0.048
 outage+0.044
uffy+0.043
run+0.042
 need+0.040
Neg logit contributions
iece-0.060
edly-0.059
 seas-0.054
ly-0.052
Please-0.052
Token fix
Token ID4259
Feature activation-3.84e-02

Pos logit contributions
uffy+0.061
 outage+0.060
 cleans+0.060
arter+0.056
run+0.056
Neg logit contributions
iece-0.074
edly-0.064
ly-0.063
Please-0.054
 seas-0.053
Token the
Token ID262
Feature activation-1.04e-02

Pos logit contributions
 cleans+0.065
 outage+0.065
run+0.062
uffy+0.062
 need+0.059
Neg logit contributions
iece-0.056
 seas-0.054
edly-0.052
 Edward-0.046
Edward-0.045
Token fence
Token ID13990
Feature activation-8.87e-02

Pos logit contributions
 cleans+0.012
run+0.011
uffy+0.010
 outage+0.010
 need+0.009
Neg logit contributions
iece-0.021
edly-0.021
 seas-0.020
 seven-0.018
ly-0.018
Token and
Token ID290
Feature activation+5.15e-04

Pos logit contributions
 cleans+0.129
uffy+0.119
 outage+0.113
run+0.111
 need+0.107
Neg logit contributions
iece-0.161
edly-0.160
 seas-0.143
ly-0.137
Edward-0.130
Token clean
Token ID3424
Feature activation-4.48e-02

Pos logit contributions
iece+0.001
edly+0.001
 seas+0.001
Please+0.001
ly+0.001
Neg logit contributions
uffy-0.001
 cleans-0.001
 outage-0.001
ucker-0.001
ric-0.001
Token the
Token ID262
Feature activation-1.06e-02

Pos logit contributions
 cleans+0.069
uffy+0.062
 outage+0.061
run+0.061
 need+0.060
Neg logit contributions
edly-0.078
iece-0.077
 seas-0.071
Edward-0.066
ly-0.065
Token garden
Token ID11376
Feature activation-3.83e-02

Pos logit contributions
 cleans+0.012
run+0.011
uffy+0.011
 outage+0.011
 need+0.010
Neg logit contributions
iece-0.022
edly-0.022
 seas-0.020
 oceans-0.019
 seven-0.019
Token.
Token ID13
Feature activation+2.12e-03

Pos logit contributions
 cleans+0.053
uffy+0.048
 outage+0.046
run+0.045
 need+0.044
Neg logit contributions
edly-0.073
iece-0.072
 seas-0.066
ly-0.062
Edward-0.059
Token and
Token ID290
Feature activation-3.63e-03

Pos logit contributions
 cleans+0.001
 need+0.001
 exc+0.001
run+0.001
 outage+0.001
Neg logit contributions
edly-0.002
iece-0.002
 seas-0.002
Edward-0.002
oph-0.001
Token the
Token ID262
Feature activation-3.19e-02

Pos logit contributions
 cleans+0.004
 need+0.004
 exc+0.004
uffy+0.003
run+0.003
Neg logit contributions
iece-0.008
edly-0.008
 seas-0.007
Edward-0.007
ly-0.007
Token big
Token ID1263
Feature activation-6.04e-02

Pos logit contributions
 cleans+0.039
 need+0.035
uffy+0.035
 exc+0.034
run+0.033
Neg logit contributions
iece-0.066
edly-0.065
 seas-0.059
oph-0.056
ly-0.056
Token frog
Token ID21264
Feature activation-1.70e-03

Pos logit contributions
 cleans+0.090
 need+0.083
uffy+0.082
 outage+0.078
run+0.078
Neg logit contributions
edly-0.109
iece-0.108
 seas-0.096
Edward-0.090
oph-0.088
Token said
Token ID531
Feature activation-1.11e-02

Pos logit contributions
 cleans+0.002
 outage+0.002
uffy+0.002
run+0.002
 need+0.002
Neg logit contributions
edly-0.003
iece-0.003
 seas-0.003
ly-0.003
Edward-0.003
Token that
Token ID326
Feature activation-7.90e-02

Pos logit contributions
 cleans+0.011
uffy+0.008
 need+0.008
 exc+0.008
run+0.008
Neg logit contributions
edly-0.026
iece-0.026
 seas-0.024
oph-0.024
Edward-0.023
Token he
Token ID339
Feature activation+5.06e-03

Pos logit contributions
 cleans+0.122
uffy+0.108
 outage+0.106
 need+0.106
run+0.105
Neg logit contributions
edly-0.139
iece-0.137
 seas-0.125
Edward-0.117
ly-0.116
Token was
Token ID373
Feature activation-2.02e-02

Pos logit contributions
edly+0.009
iece+0.009
ly+0.008
 seas+0.008
Please+0.008
Neg logit contributions
 cleans-0.007
 outage-0.006
run-0.006
uffy-0.006
ric-0.006
Token lonely
Token ID21757
Feature activation-2.36e-02

Pos logit contributions
 cleans+0.030
uffy+0.028
 outage+0.028
run+0.026
 slam+0.025
Neg logit contributions
iece-0.033
edly-0.033
 seas-0.032
 Edward-0.030
Edward-0.030
Token and
Token ID290
Feature activation+7.04e-04

Pos logit contributions
 cleans+0.038
uffy+0.034
 outage+0.032
run+0.032
ric+0.031
Neg logit contributions
edly-0.040
iece-0.038
 seas-0.036
ly-0.034
Please-0.032
Token had
Token ID550
Feature activation+2.20e-03

Pos logit contributions
edly+0.001
iece+0.001
 seas+0.001
ly+0.001
Please+0.001
Neg logit contributions
 cleans-0.001
uffy-0.001
 outage-0.001
run-0.001
ric-0.001
Token his
Token ID465
Feature activation+4.46e-03

Pos logit contributions
 cleans+0.076
 outage+0.074
uffy+0.069
run+0.066
 need+0.065
Neg logit contributions
edly-0.048
iece-0.043
 seas-0.041
ly-0.036
 Edward-0.036
Token friend
Token ID1545
Feature activation-1.30e-02

Pos logit contributions
edly+0.008
 seas+0.007
iece+0.007
ly+0.006
 tune+0.006
Neg logit contributions
 cleans-0.007
 outage-0.006
run-0.006
ucker-0.006
ric-0.005
Token.
Token ID13
Feature activation-5.05e-03

Pos logit contributions
 cleans+0.019
 outage+0.017
uffy+0.017
 exc+0.016
ric+0.016
Neg logit contributions
edly-0.024
iece-0.023
 seas-0.021
ly-0.021
Edward-0.020
Token He
Token ID679
Feature activation+6.55e-03

Pos logit contributions
 cleans+0.009
 outage+0.009
uffy+0.008
 need+0.008
 exc+0.008
Neg logit contributions
edly-0.008
iece-0.007
 seas-0.006
ly-0.006
Edward-0.006
Token wished
Token ID16555
Feature activation-2.72e-02

Pos logit contributions
edly+0.013
iece+0.013
 seas+0.012
Edward+0.011
ly+0.011
Neg logit contributions
 cleans-0.009
uffy-0.008
 outage-0.008
run-0.008
 need-0.007
Token that
Token ID326
Feature activation-8.11e-02

Pos logit contributions
 cleans+0.043
uffy+0.039
run+0.038
 need+0.038
 outage+0.037
Neg logit contributions
iece-0.046
edly-0.046
 seas-0.042
Edward-0.039
oph-0.038
Token Mitt
Token ID16627
Feature activation-8.05e-02

Pos logit contributions
 cleans+0.134
uffy+0.124
 outage+0.122
run+0.118
 need+0.112
Neg logit contributions
iece-0.128
edly-0.126
 seas-0.122
Edward-0.109
Please-0.107
Tokenens
Token ID641
Feature activation-5.69e-02

Pos logit contributions
 cleans+0.077
 outage+0.062
uffy+0.062
run+0.061
 need+0.059
Neg logit contributions
edly-0.187
iece-0.185
 seas-0.173
ly-0.167
Edward-0.166
Token had
Token ID550
Feature activation-1.71e-02

Pos logit contributions
 cleans+0.068
uffy+0.060
 outage+0.059
run+0.058
 need+0.055
Neg logit contributions
edly-0.118
iece-0.115
 seas-0.108
ly-0.103
Edward-0.101
Token not
Token ID407
Feature activation-2.94e-02

Pos logit contributions
 cleans+0.023
 need+0.019
uffy+0.019
run+0.019
 exc+0.018
Neg logit contributions
edly-0.034
iece-0.034
 seas-0.031
Edward-0.030
ly-0.029
Token been
Token ID587
Feature activation-1.13e-02

Pos logit contributions
 cleans+0.047
uffy+0.045
 outage+0.043
run+0.041
ric+0.039
Neg logit contributions
edly-0.048
iece-0.048
 seas-0.045
ly-0.041
Please-0.039
Token,
Token ID11
Feature activation+9.75e-03

Pos logit contributions
 cleans+0.025
run+0.022
 need+0.022
uffy+0.021
 outage+0.020
Neg logit contributions
iece-0.048
edly-0.047
 seas-0.046
Edward-0.043
Prin-0.043
Token but
Token ID475
Feature activation+2.59e-02

Pos logit contributions
edly+0.017
iece+0.016
 seas+0.015
Edward+0.014
ly+0.014
Neg logit contributions
 cleans-0.015
uffy-0.014
run-0.014
 outage-0.014
 need-0.014
Token he
Token ID339
Feature activation+2.57e-02

Pos logit contributions
edly+0.046
iece+0.045
 seas+0.042
Edward+0.039
ly+0.039
Neg logit contributions
 cleans-0.039
 need-0.034
run-0.034
uffy-0.034
 outage-0.034
Token never
Token ID1239
Feature activation-1.05e-02

Pos logit contributions
edly+0.050
iece+0.048
 seas+0.045
Edward+0.043
ly+0.042
Neg logit contributions
 cleans-0.034
uffy-0.031
 outage-0.031
run-0.030
 need-0.028
Token forgot
Token ID16453
Feature activation+8.79e-03

Pos logit contributions
 cleans+0.016
uffy+0.016
 outage+0.015
ric+0.014
 hose+0.014
Neg logit contributions
iece-0.017
edly-0.017
ly-0.016
 seas-0.016
oph-0.014
Token how
Token ID703
Feature activation-7.90e-02

Pos logit contributions
iece+0.013
edly+0.013
 seas+0.012
ly+0.011
 Edward+0.011
Neg logit contributions
 cleans-0.015
uffy-0.015
 outage-0.014
 exc-0.013
run-0.013
Token brave
Token ID14802
Feature activation-1.57e-02

Pos logit contributions
 cleans+0.116
uffy+0.106
 outage+0.104
ric+0.097
 slam+0.095
Neg logit contributions
edly-0.137
iece-0.133
 seas-0.125
ly-0.124
Please-0.113
Token he
Token ID339
Feature activation+3.73e-02

Pos logit contributions
 cleans+0.021
 need+0.019
run+0.019
 Kim+0.018
 outage+0.018
Neg logit contributions
edly-0.030
iece-0.029
Edward-0.026
 seas-0.026
oph-0.025
Token was
Token ID373
Feature activation+2.28e-04

Pos logit contributions
edly+0.080
iece+0.079
 seas+0.074
Edward+0.070
ly+0.069
Neg logit contributions
 cleans-0.043
uffy-0.037
 outage-0.036
run-0.035
 need-0.035
Token the
Token ID262
Feature activation-1.50e-02

Pos logit contributions
iece+0.000
edly+0.000
ly+0.000
 seas+0.000
 Edward+0.000
Neg logit contributions
 cleans-0.000
uffy-0.000
run-0.000
ucker-0.000
ric-0.000
Token day
Token ID1110
Feature activation+1.46e-02

Pos logit contributions
 cleans+0.020
uffy+0.018
 outage+0.017
 need+0.017
run+0.017
Neg logit contributions
edly-0.030
iece-0.029
 seas-0.027
Edward-0.026
ly-0.025