TOP ACTIVATIONS
MAX = 9.233

" WHAT ARE YOU DO ING ?" Mom yells .
could see lots of av oc ados that the supplier had
I will buy more av oc ados tomorrow . You can
mom would bake a fresh batch of cookies for her to
until he had a delicious batch of brown ies . When
a brave girl named Let icia . She lived on a
house and made a fresh batch of blue berry muff ins
and forgot to buy av oc ados . Lily was sad
kitchen and made a fresh batch of sa us ages .
man who wanted to prevent Sof ia from playing the violin
, Betty made a big batch of butter for a party
, her mom baked a batch of cookies and put them
M ama asked , " P apa , can we use
there was a loud " P OP !" Rob stopped and
and decided to make another batch of muff ins together ,
knock and a fresh new batch of letters would tumble out
to do was to pick da is ies and give them
she asked him , " P apa , why do you
they could grow more av oc ados and share them with
he shook it . <|endoftext|> Pa ola and her mother were

MIN ACTIVATIONS
MIN = -6.657

The two combatants stopped fighting and looked at the
using his problem - s olving skills . From that day
it , but his mom stopped him . She told him
But he wasn 't happy living high above the rest of
unk ! He 's been living around here for a while
. Max was very happy living on the farm with his
house , when her mom stopped her . Her mother was
actus . It 's happy living in the desert where it
Lily was sad because her snow man was disappearing . She
. Jack was very happy living in the woods . Every
Snow y . And the living room . Mom will be
The dolls were very happy living in their new house .
she was glad she was living in such a tidy home
box in , when Mama stopped . � � € �
you . You are a living thing . You have feelings
. Max and M illy stopped to discuss the berries ,
you glad that you are living in the forest ?"
and sad because she was living all by herself .
run , but his mom stopped him . " Wait ,
The animals were very happy living on the farm .

INTERVAL 5.261 - 9.233
CONTAINS 0.015%

. One day , Wh isk ers went on a walk
to pet the rh in oc eros . It looked so
a sign that said " P engu ins are sleeping .
was getting ready to make por ridge and pancakes . He
got out of bed at 7 am and went to the

INTERVAL 1.288 - 5.261
CONTAINS 16.301%

the bottle and it broke on the floor . The wine
. She does not permit us to touch them . They
there was a little girl called Daisy . Daisy was very
Every day he would take it to the park and kick
a high rat � � € � � much bigger than

INTERVAL -2.685 - 1.288
CONTAINS 80.210%

special frame . It was a colorful frame and it was
time , please listen to me and wait until the pie
going by . Suddenly , the train made a bad noise
lying . " L ily , I know you hid it
. She wished they could stay forever . But Molly 's

INTERVAL -6.657 - -2.685
CONTAINS 3.474%

. We should respect all living things ." L
knock him down . How about I move him to a
well . Tim my 's mom was not around , so
my realized he lost his favorite toy . He looked and
sees a squirrel . She smiles and says hello to the
Token
Token ID198
Feature activation+5.05e-01

Pos logit contributions
burn+0.006
 blowing+0.005
 waving+0.005
 spinning+0.004
 driveway+0.004
Neg logit contributions
 ounces-0.010
izards-0.009
bors-0.009
affe-0.009
hell-0.009
Token"
Token ID1
Feature activation+2.39e+00

Pos logit contributions
 ounces+0.016
ils+0.014
affe+0.014
izards+0.014
bors+0.014
Neg logit contributions
burn-0.013
 blowing-0.012
 waving-0.012
 neighborhood-0.010
 spinning-0.010
TokenWHAT
Token ID32971
Feature activation+4.47e+00

Pos logit contributions
 ounces+0.080
ils+0.072
izards+0.071
bors+0.071
affe+0.071
Neg logit contributions
burn-0.057
 blowing-0.052
 waving-0.051
 spinning-0.045
 driveway-0.044
Token ARE
Token ID15986
Feature activation+5.99e+00

Pos logit contributions
 ounces+0.160
bors+0.144
affe+0.137
ils+0.135
izards+0.134
Neg logit contributions
burn-0.100
 waving-0.086
 blowing-0.080
my-0.078
 window-0.075
Token YOU
Token ID7013
Feature activation+4.35e+00

Pos logit contributions
 ounces+0.179
bors+0.155
affe+0.155
ils+0.149
ious+0.148
Neg logit contributions
burn-0.155
 waving-0.143
 blowing-0.140
 spinning-0.137
 daddy-0.135
Token DO
Token ID8410
Feature activation+9.23e+00

Pos logit contributions
 ounces+0.150
izards+0.130
bors+0.130
affe+0.129
ils+0.128
Neg logit contributions
burn-0.103
 waving-0.093
 blowing-0.093
 spinning-0.080
 leaning-0.079
TokenING
Token ID2751
Feature activation+2.93e+00

Pos logit contributions
 ounces+0.291
bors+0.243
ils+0.229
izards+0.225
affe+0.223
Neg logit contributions
burn-0.230
 waving-0.212
 blowing-0.206
 vac-0.202
 window-0.200
Token?"
Token ID1701
Feature activation+2.54e+00

Pos logit contributions
 ounces+0.097
izards+0.086
ils+0.085
hell+0.082
bors+0.081
Neg logit contributions
burn-0.078
 waving-0.066
 blowing-0.065
 crying-0.061
 daddy-0.060
Token Mom
Token ID11254
Feature activation-3.19e+00

Pos logit contributions
 ounces+0.097
ils+0.089
affe+0.088
izards+0.087
bors+0.087
Neg logit contributions
burn-0.048
 waving-0.043
 blowing-0.043
 daddy-0.037
 spinning-0.036
Token yells
Token ID42675
Feature activation+3.52e+00

Pos logit contributions
burn+0.094
 blowing+0.083
 waving+0.078
 driveway+0.073
 neighborhood+0.073
Neg logit contributions
 ounces-0.089
izards-0.082
ils-0.080
affe-0.077
bors-0.076
Token.
Token ID13
Feature activation-2.56e-02

Pos logit contributions
 ounces+0.128
ils+0.115
bors+0.115
affe+0.113
izards+0.112
Neg logit contributions
burn-0.075
 waving-0.069
 blowing-0.067
 crying-0.062
 spinning-0.059
Token could
Token ID714
Feature activation-1.94e+00

Pos logit contributions
 blowing+0.018
burn+0.017
 waving+0.017
 crying+0.014
 leaning+0.014
Neg logit contributions
 ounces-0.039
izards-0.036
bors-0.035
affe-0.035
ils-0.035
Token see
Token ID766
Feature activation+1.67e+00

Pos logit contributions
burn+0.040
 blowing+0.037
 waving+0.036
 spinning+0.032
 crying+0.031
Neg logit contributions
 ounces-0.071
ils-0.064
bors-0.064
izards-0.063
affe-0.063
Token lots
Token ID6041
Feature activation+3.08e+00

Pos logit contributions
 ounces+0.060
bors+0.055
affe+0.055
izards+0.055
ils+0.053
Neg logit contributions
burn-0.031
 waving-0.031
 blowing-0.031
my-0.027
 leaning-0.026
Token of
Token ID286
Feature activation+6.35e-01

Pos logit contributions
 ounces+0.103
bors+0.095
ils+0.094
izards+0.094
affe+0.091
Neg logit contributions
 blowing-0.065
 waving-0.062
burn-0.059
 spinning-0.055
 shining-0.053
Token av
Token ID1196
Feature activation+3.39e+00

Pos logit contributions
 ounces+0.020
izards+0.018
affe+0.018
ils+0.018
bors+0.018
Neg logit contributions
 blowing-0.015
burn-0.015
 waving-0.014
 neighborhood-0.013
 spinning-0.013
Tokenoc
Token ID420
Feature activation+7.75e+00

Pos logit contributions
 ounces+0.057
izards+0.051
bors+0.048
ils+0.048
ily+0.047
Neg logit contributions
burn-0.129
 blowing-0.123
 waving-0.120
my-0.117
 neighborhood-0.115
Tokenados
Token ID22484
Feature activation+2.60e+00

Pos logit contributions
 ounces+0.116
izards+0.113
bors+0.108
hell+0.105
isy+0.104
Neg logit contributions
burn-0.281
 blowing-0.269
 waving-0.266
 leaning-0.261
 neighborhood-0.252
Token that
Token ID326
Feature activation-7.45e-01

Pos logit contributions
 ounces+0.095
bors+0.087
affe+0.087
izards+0.084
ils+0.084
Neg logit contributions
 blowing-0.051
burn-0.051
 waving-0.050
 spinning-0.041
 leaning-0.041
Token the
Token ID262
Feature activation-8.67e-01

Pos logit contributions
 blowing+0.014
burn+0.013
 waving+0.013
 daddy+0.012
my+0.011
Neg logit contributions
 ounces-0.028
izards-0.025
affe-0.025
bors-0.025
ils-0.024
Token supplier
Token ID22693
Feature activation+8.06e-01

Pos logit contributions
burn+0.021
 waving+0.019
 blowing+0.019
 neighborhood+0.017
 daddy+0.017
Neg logit contributions
 ounces-0.028
ils-0.026
izards-0.026
bors-0.025
affe-0.025
Token had
Token ID550
Feature activation-8.73e-02

Pos logit contributions
 ounces+0.028
bors+0.026
izards+0.025
affe+0.025
ils+0.025
Neg logit contributions
 waving-0.016
burn-0.016
 blowing-0.015
my-0.015
 daddy-0.014
TokenI
Token ID40
Feature activation-4.84e-01

Pos logit contributions
 ounces+0.021
ils+0.019
izards+0.019
hell+0.018
affe+0.018
Neg logit contributions
burn-0.011
 blowing-0.010
 waving-0.009
my-0.009
 neighborhood-0.008
Token will
Token ID481
Feature activation-8.58e-01

Pos logit contributions
burn+0.013
 blowing+0.012
 waving+0.012
 driveway+0.011
 spinning+0.010
Neg logit contributions
 ounces-0.015
affe-0.013
ils-0.013
izards-0.013
hell-0.013
Token buy
Token ID2822
Feature activation+1.36e+00

Pos logit contributions
burn+0.022
 blowing+0.020
 waving+0.019
 neighborhood+0.018
 driveway+0.018
Neg logit contributions
 ounces-0.027
ils-0.024
affe-0.023
bors-0.023
izards-0.023
Token more
Token ID517
Feature activation+7.87e-01

Pos logit contributions
 ounces+0.046
affe+0.046
bors+0.044
isy+0.044
izards+0.043
Neg logit contributions
 grandma-0.027
 waving-0.026
 daddy-0.025
burn-0.025
my-0.024
Token av
Token ID1196
Feature activation+3.89e+00

Pos logit contributions
 ounces+0.027
bors+0.026
ils+0.025
affe+0.025
izards+0.025
Neg logit contributions
 waving-0.016
burn-0.016
 blowing-0.015
 spinning-0.014
 window-0.014
Tokenoc
Token ID420
Feature activation+7.70e+00

Pos logit contributions
 ounces+0.073
izards+0.069
bors+0.065
ily+0.062
ils+0.061
Neg logit contributions
burn-0.140
my-0.129
 blowing-0.127
 waving-0.123
 neighborhood-0.119
Tokenados
Token ID22484
Feature activation+3.72e+00

Pos logit contributions
izards+0.112
 ounces+0.111
hell+0.105
isy+0.103
bors+0.102
Neg logit contributions
burn-0.287
 blowing-0.265
 waving-0.263
 leaning-0.259
my-0.250
Token tomorrow
Token ID9439
Feature activation+1.10e+00

Pos logit contributions
 ounces+0.147
bors+0.141
affe+0.131
ils+0.130
izards+0.128
Neg logit contributions
burn-0.061
 blowing-0.058
 waving-0.058
my-0.052
 daddy-0.047
Token.
Token ID13
Feature activation-7.45e-01

Pos logit contributions
 ounces+0.036
bors+0.033
izards+0.033
ils+0.032
affe+0.032
Neg logit contributions
burn-0.026
 blowing-0.024
 waving-0.024
my-0.022
 daddy-0.021
Token You
Token ID921
Feature activation+2.63e+00

Pos logit contributions
burn+0.015
 waving+0.014
my+0.013
 daddy+0.013
 grandma+0.013
Neg logit contributions
ils-0.026
 ounces-0.025
hell-0.024
bors-0.024
izards-0.023
Token can
Token ID460
Feature activation-2.68e+00

Pos logit contributions
 ounces+0.104
bors+0.102
izards+0.096
ils+0.095
isy+0.095
Neg logit contributions
burn-0.038
my-0.038
 daddy-0.034
 only-0.033
 turn-0.033
Token mom
Token ID1995
Feature activation-3.88e+00

Pos logit contributions
burn+0.005
 blowing+0.005
 waving+0.005
seat+0.004
ric+0.004
Neg logit contributions
ils-0.008
 ounces-0.008
affe-0.008
isy-0.008
ily-0.008
Token would
Token ID561
Feature activation-1.48e+00

Pos logit contributions
 waving+0.070
burn+0.068
 blowing+0.063
 driveway+0.060
 spinning+0.059
Neg logit contributions
ils-0.134
 ounces-0.129
affe-0.125
isy-0.124
ily-0.123
Token bake
Token ID28450
Feature activation+1.29e+00

Pos logit contributions
burn+0.038
 blowing+0.034
 waving+0.033
 neighborhood+0.030
 driveway+0.030
Neg logit contributions
 ounces-0.045
ils-0.041
bors-0.040
affe-0.040
hell-0.039
Token a
Token ID257
Feature activation+4.98e-01

Pos logit contributions
 ounces+0.047
affe+0.044
bors+0.041
izards+0.041
ocket+0.039
Neg logit contributions
burn-0.029
 blowing-0.026
 waving-0.025
 daddy-0.023
my-0.023
Token fresh
Token ID4713
Feature activation+5.32e-01

Pos logit contributions
 ounces+0.016
izards+0.014
ils+0.014
bors+0.014
affe+0.014
Neg logit contributions
burn-0.013
 waving-0.012
 blowing-0.012
 daddy-0.011
 spinning-0.010
Token batch
Token ID15458
Feature activation+7.66e+00

Pos logit contributions
 ounces+0.018
izards+0.017
bors+0.016
ils+0.016
affe+0.016
Neg logit contributions
burn-0.013
 blowing-0.011
 waving-0.011
my-0.010
 spinning-0.010
Token of
Token ID286
Feature activation+1.87e+00

Pos logit contributions
 ounces+0.306
bors+0.285
affe+0.271
cod+0.264
ns+0.263
Neg logit contributions
 blowing-0.112
burn-0.111
 waving-0.098
 crying-0.088
my-0.087
Token cookies
Token ID14746
Feature activation+1.87e+00

Pos logit contributions
 ounces+0.064
izards+0.060
affe+0.060
bors+0.057
ocket+0.055
Neg logit contributions
burn-0.041
 waving-0.039
 blowing-0.039
 grandma-0.037
 daddy-0.037
Token for
Token ID329
Feature activation+3.86e+00

Pos logit contributions
 ounces+0.076
bors+0.070
affe+0.068
izards+0.067
hell+0.065
Neg logit contributions
burn-0.033
 blowing-0.031
 waving-0.029
my-0.024
 daddy-0.024
Token her
Token ID607
Feature activation+5.49e-01

Pos logit contributions
 ounces+0.154
affe+0.146
izards+0.137
hell+0.137
bors+0.134
Neg logit contributions
burn-0.071
 blowing-0.064
 daddy-0.063
 waving-0.060
 grandma-0.056
Token to
Token ID284
Feature activation+8.63e-01

Pos logit contributions
 ounces+0.020
izards+0.019
bors+0.018
ils+0.018
affe+0.018
Neg logit contributions
burn-0.011
 blowing-0.010
 waving-0.010
 daddy-0.009
 neighborhood-0.008
Token until
Token ID1566
Feature activation+1.02e+00

Pos logit contributions
 ounces+0.013
affe+0.012
izards+0.012
bors+0.011
ils+0.011
Neg logit contributions
burn-0.007
 blowing-0.007
 waving-0.006
my-0.006
 spinning-0.006
Token he
Token ID339
Feature activation+2.26e+00

Pos logit contributions
 ounces+0.033
affe+0.032
izards+0.031
ils+0.031
bors+0.031
Neg logit contributions
burn-0.024
 blowing-0.023
 waving-0.022
 daddy-0.021
 spinning-0.020
Token had
Token ID550
Feature activation+6.37e-01

Pos logit contributions
 ounces+0.090
affe+0.084
bors+0.083
izards+0.083
hell+0.081
Neg logit contributions
burn-0.037
 blowing-0.034
 waving-0.032
 daddy-0.028
 spinning-0.028
Token a
Token ID257
Feature activation-2.06e-01

Pos logit contributions
 ounces+0.024
affe+0.023
izards+0.022
bors+0.022
ils+0.022
Neg logit contributions
burn-0.012
 blowing-0.011
 waving-0.010
 spinning-0.009
 daddy-0.009
Token delicious
Token ID12625
Feature activation+1.95e+00

Pos logit contributions
burn+0.005
 blowing+0.005
 waving+0.005
my+0.004
 neighborhood+0.004
Neg logit contributions
 ounces-0.006
hell-0.006
affe-0.006
isy-0.005
ils-0.005
Token batch
Token ID15458
Feature activation+7.48e+00

Pos logit contributions
 ounces+0.058
ils+0.052
affe+0.051
bors+0.050
hell+0.050
Neg logit contributions
burn-0.053
 blowing-0.048
 waving-0.048
 neighborhood-0.043
 driveway-0.042
Token of
Token ID286
Feature activation+1.07e+00

Pos logit contributions
bors+0.290
 ounces+0.284
cod+0.270
affe+0.267
ns+0.259
Neg logit contributions
 blowing-0.112
burn-0.099
 waving-0.095
 spinning-0.087
 holding-0.085
Token brown
Token ID7586
Feature activation+1.54e+00

Pos logit contributions
 ounces+0.035
affe+0.034
izards+0.034
bors+0.032
hell+0.032
Neg logit contributions
burn-0.024
 blowing-0.023
 waving-0.023
 daddy-0.021
 spinning-0.020
Tokenies
Token ID444
Feature activation+8.70e-01

Pos logit contributions
 ounces+0.046
izards+0.046
affe+0.044
bors+0.043
ocket+0.043
Neg logit contributions
burn-0.039
 blowing-0.036
 waving-0.034
 spinning-0.032
 window-0.031
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
 ounces+0.034
bors+0.032
affe+0.031
izards+0.030
hell+0.030
Neg logit contributions
burn-0.016
 blowing-0.016
 waving-0.015
 spinning-0.013
 leaning-0.012
Token When
Token ID1649
Feature activation-9.30e-01

Pos logit contributions
 ounces+0.010
ils+0.009
izards+0.009
bors+0.009
affe+0.009
Neg logit contributions
burn-0.005
 waving-0.004
 blowing-0.004
 neighborhood-0.003
 driveway-0.003
Token a
Token ID257
Feature activation+5.23e-02

Pos logit contributions
 ounces+0.072
izards+0.067
ils+0.066
hell+0.065
affe+0.065
Neg logit contributions
burn-0.059
 blowing-0.053
 waving-0.053
 driveway-0.048
 neighborhood-0.046
Token brave
Token ID14802
Feature activation+2.76e-01

Pos logit contributions
 ounces+0.002
affe+0.002
isy+0.001
hell+0.001
bors+0.001
Neg logit contributions
burn-0.001
 blowing-0.001
 waving-0.001
 driveway-0.001
my-0.001
Token girl
Token ID2576
Feature activation+3.59e+00

Pos logit contributions
 ounces+0.010
ils+0.009
bors+0.009
izards+0.009
hell+0.008
Neg logit contributions
burn-0.006
 waving-0.006
 blowing-0.005
 daddy-0.005
 spinning-0.005
Token named
Token ID3706
Feature activation+2.65e+00

Pos logit contributions
 ounces+0.102
ils+0.093
izards+0.091
affe+0.091
bors+0.090
Neg logit contributions
burn-0.101
 blowing-0.092
 waving-0.091
 driveway-0.082
 spinning-0.081
Token Let
Token ID3914
Feature activation+1.29e+00

Pos logit contributions
 ounces+0.098
affe+0.087
bors+0.086
ils+0.085
izards+0.083
Neg logit contributions
burn-0.058
 waving-0.053
my-0.051
 blowing-0.051
 daddy-0.049
Tokenicia
Token ID33577
Feature activation+7.43e+00

Pos logit contributions
 ounces+0.042
ils+0.037
izards+0.037
affe+0.037
bors+0.036
Neg logit contributions
burn-0.033
 blowing-0.030
 waving-0.029
 spinning-0.026
 neighborhood-0.026
Token.
Token ID13
Feature activation+8.90e-01

Pos logit contributions
 ounces+0.290
bors+0.258
affe+0.257
hell+0.256
izards+0.253
Neg logit contributions
burn-0.141
 waving-0.126
 blowing-0.122
 daddy-0.112
my-0.111
Token She
Token ID1375
Feature activation+1.28e+00

Pos logit contributions
 ounces+0.033
ils+0.030
bors+0.029
izards+0.029
affe+0.029
Neg logit contributions
burn-0.018
 waving-0.016
 blowing-0.016
 neighborhood-0.014
 spinning-0.014
Token lived
Token ID5615
Feature activation-1.19e+00

Pos logit contributions
 ounces+0.052
izards+0.047
affe+0.047
ils+0.046
bors+0.046
Neg logit contributions
burn-0.022
 blowing-0.019
 waving-0.019
 neighborhood-0.016
 spinning-0.016
Token on
Token ID319
Feature activation+1.64e+00

Pos logit contributions
burn+0.030
 blowing+0.026
 waving+0.026
 driveway+0.024
 daddy+0.023
Neg logit contributions
 ounces-0.036
izards-0.035
ils-0.035
ily-0.033
hell-0.032
Token a
Token ID257
Feature activation+6.39e-01

Pos logit contributions
 ounces+0.058
ils+0.053
izards+0.052
affe+0.052
bors+0.052
Neg logit contributions
burn-0.036
 blowing-0.032
 waving-0.032
 spinning-0.027
 driveway-0.027
Token house
Token ID2156
Feature activation-8.60e-01

Pos logit contributions
burn+0.008
 blowing+0.007
 waving+0.006
 spinning+0.005
 leaning+0.005
Neg logit contributions
 ounces-0.019
ils-0.018
affe-0.017
bors-0.017
izards-0.017
Token and
Token ID290
Feature activation-2.97e-01

Pos logit contributions
burn+0.019
 blowing+0.016
 waving+0.016
 spinning+0.014
 neighborhood+0.014
Neg logit contributions
 ounces-0.029
ils-0.027
affe-0.026
hell-0.026
izards-0.026
Token made
Token ID925
Feature activation+1.26e+00

Pos logit contributions
burn+0.007
 blowing+0.006
 waving+0.006
 spinning+0.005
 neighborhood+0.005
Neg logit contributions
 ounces-0.010
ils-0.009
izards-0.009
affe-0.009
bors-0.009
Token a
Token ID257
Feature activation-4.33e-01

Pos logit contributions
 ounces+0.045
affe+0.042
izards+0.040
bors+0.040
hell+0.040
Neg logit contributions
burn-0.026
 blowing-0.024
 waving-0.024
 daddy-0.023
 crying-0.021
Token fresh
Token ID4713
Feature activation+2.16e-01

Pos logit contributions
burn+0.010
 blowing+0.009
 waving+0.008
 driveway+0.007
 neighborhood+0.007
Neg logit contributions
 ounces-0.015
affe-0.014
hell-0.013
ils-0.013
bors-0.013
Token batch
Token ID15458
Feature activation+7.39e+00

Pos logit contributions
 ounces+0.007
ils+0.006
affe+0.006
izards+0.006
bors+0.006
Neg logit contributions
burn-0.006
 blowing-0.005
 waving-0.005
 spinning-0.004
 neighborhood-0.004
Token of
Token ID286
Feature activation+1.23e+00

Pos logit contributions
 ounces+0.286
bors+0.265
izards+0.252
affe+0.252
ns+0.249
Neg logit contributions
 blowing-0.116
burn-0.110
 waving-0.107
 crying-0.096
 daddy-0.094
Token blue
Token ID4171
Feature activation-3.79e-01

Pos logit contributions
 ounces+0.042
izards+0.040
affe+0.040
ils+0.039
bors+0.039
Neg logit contributions
burn-0.026
 waving-0.026
 blowing-0.025
 daddy-0.022
 spinning-0.022
Tokenberry
Token ID8396
Feature activation+2.26e+00

Pos logit contributions
burn+0.009
 blowing+0.008
 waving+0.008
 spinning+0.007
 daddy+0.007
Neg logit contributions
 ounces-0.013
ils-0.012
izards-0.012
bors-0.012
affe-0.012
Token muff
Token ID27563
Feature activation+1.28e+00

Pos logit contributions
 ounces+0.079
bors+0.074
izards+0.072
ocket+0.069
ils+0.069
Neg logit contributions
burn-0.049
 blowing-0.047
 waving-0.044
 shining-0.039
 daddy-0.038
Tokenins
Token ID1040
Feature activation+1.88e+00

Pos logit contributions
 ounces+0.041
affe+0.040
bors+0.039
nic+0.037
ger+0.036
Neg logit contributions
burn-0.030
 blowing-0.028
 waving-0.025
my-0.024
 shining-0.023
Token and
Token ID290
Feature activation+6.85e-01

Pos logit contributions
 ounces+0.026
ils+0.025
ily+0.025
hell+0.024
affe+0.024
Neg logit contributions
burn-0.020
 blowing-0.017
 waving-0.016
 spinning-0.015
ric-0.015
Token forgot
Token ID16453
Feature activation+5.92e-01

Pos logit contributions
 ounces+0.025
affe+0.023
izards+0.023
ils+0.023
bors+0.022
Neg logit contributions
burn-0.014
 blowing-0.013
 waving-0.013
 daddy-0.011
 crying-0.011
Token to
Token ID284
Feature activation-1.05e+00

Pos logit contributions
 ounces+0.024
affe+0.022
bors+0.021
izards+0.021
ils+0.021
Neg logit contributions
burn-0.010
 blowing-0.010
 waving-0.010
 crying-0.008
 daddy-0.008
Token buy
Token ID2822
Feature activation+1.09e+00

Pos logit contributions
burn+0.023
 blowing+0.020
 waving+0.020
 daddy+0.017
 driveway+0.017
Neg logit contributions
 ounces-0.037
izards-0.034
affe-0.034
ils-0.034
bors-0.034
Token av
Token ID1196
Feature activation+3.20e+00

Pos logit contributions
 ounces+0.044
affe+0.040
bors+0.040
izards+0.040
isy+0.039
Neg logit contributions
burn-0.019
 waving-0.016
 blowing-0.016
my-0.016
 daddy-0.016
Tokenoc
Token ID420
Feature activation+7.37e+00

Pos logit contributions
 ounces+0.055
izards+0.047
bors+0.045
ils+0.044
affe+0.041
Neg logit contributions
burn-0.126
 blowing-0.117
 waving-0.114
my-0.114
 neighborhood-0.109
Tokenados
Token ID22484
Feature activation+2.94e+00

Pos logit contributions
 ounces+0.113
izards+0.104
hell+0.102
bors+0.100
isy+0.099
Neg logit contributions
burn-0.278
 waving-0.257
 blowing-0.256
 leaning-0.248
my-0.246
Token.
Token ID13
Feature activation-4.32e-01

Pos logit contributions
 ounces+0.120
bors+0.110
affe+0.107
ils+0.106
izards+0.105
Neg logit contributions
burn-0.051
 blowing-0.047
 waving-0.045
my-0.040
 daddy-0.037
Token Lily
Token ID20037
Feature activation-7.04e-01

Pos logit contributions
burn+0.011
 blowing+0.010
 waving+0.009
 neighborhood+0.008
 spinning+0.008
Neg logit contributions
 ounces-0.014
ils-0.013
izards-0.013
affe-0.013
bors-0.013
Token was
Token ID373
Feature activation-1.11e+00

Pos logit contributions
burn+0.016
 blowing+0.014
 waving+0.014
 spinning+0.012
 driveway+0.012
Neg logit contributions
 ounces-0.024
ils-0.022
affe-0.021
bors-0.021
izards-0.021
Token sad
Token ID6507
Feature activation-3.45e-01

Pos logit contributions
burn+0.029
 blowing+0.024
 waving+0.024
 driveway+0.023
 neighborhood+0.021
Neg logit contributions
 ounces-0.034
izards-0.030
ils-0.030
ily-0.030
bors-0.029
Token kitchen
Token ID9592
Feature activation+1.26e+00

Pos logit contributions
 ounces+0.010
affe+0.009
ils+0.009
bors+0.009
hell+0.008
Neg logit contributions
burn-0.005
 blowing-0.004
 waving-0.004
 spinning-0.003
 leaning-0.003
Token and
Token ID290
Feature activation-2.48e-01

Pos logit contributions
 ounces+0.047
ils+0.043
affe+0.042
hell+0.041
bors+0.041
Neg logit contributions
burn-0.025
 blowing-0.021
 waving-0.020
 spinning-0.017
 leaning-0.016
Token made
Token ID925
Feature activation+1.39e+00

Pos logit contributions
burn+0.006
 blowing+0.005
 waving+0.005
 spinning+0.004
 neighborhood+0.004
Neg logit contributions
 ounces-0.008
ils-0.008
izards-0.007
affe-0.007
bors-0.007
Token a
Token ID257
Feature activation-1.90e-01

Pos logit contributions
 ounces+0.046
affe+0.042
izards+0.042
ils+0.042
bors+0.041
Neg logit contributions
burn-0.033
 blowing-0.030
 waving-0.030
 daddy-0.027
 crying-0.026
Token fresh
Token ID4713
Feature activation+4.44e-01

Pos logit contributions
burn+0.005
 blowing+0.004
 waving+0.004
 leaning+0.004
 spinning+0.004
Neg logit contributions
 ounces-0.006
affe-0.005
hell-0.005
bors-0.005
isy-0.005
Token batch
Token ID15458
Feature activation+7.36e+00

Pos logit contributions
 ounces+0.013
affe+0.011
hell+0.011
ils+0.011
bors+0.011
Neg logit contributions
burn-0.012
 waving-0.011
 blowing-0.011
 driveway-0.010
 spinning-0.010
Token of
Token ID286
Feature activation+1.38e+00

Pos logit contributions
 ounces+0.269
bors+0.251
izards+0.241
ils+0.241
affe+0.238
Neg logit contributions
 blowing-0.135
burn-0.129
 waving-0.126
 crying-0.115
 spinning-0.108
Token sa
Token ID473
Feature activation+2.28e+00

Pos logit contributions
 ounces+0.039
ils+0.035
izards+0.034
affe+0.034
bors+0.034
Neg logit contributions
burn-0.040
 blowing-0.036
 waving-0.036
 spinning-0.032
 neighborhood-0.032
Tokenus
Token ID385
Feature activation+3.27e+00

Pos logit contributions
 ounces+0.054
izards+0.046
ils+0.046
bors+0.046
affe+0.046
Neg logit contributions
burn-0.077
 blowing-0.071
 waving-0.070
 daddy-0.064
 neighborhood-0.064
Tokenages
Token ID1095
Feature activation+2.65e+00

Pos logit contributions
 ounces+0.067
izards+0.065
affe+0.059
bors+0.058
ils+0.057
Neg logit contributions
burn-0.112
 blowing-0.105
 waving-0.100
 daddy-0.100
 crying-0.094
Token.
Token ID13
Feature activation+7.20e-02

Pos logit contributions
 ounces+0.093
bors+0.085
izards+0.085
affe+0.084
ils+0.084
Neg logit contributions
burn-0.058
 blowing-0.054
 waving-0.053
 spinning-0.045
 daddy-0.045
Token man
Token ID582
Feature activation+1.54e-01

Pos logit contributions
burn+0.015
 blowing+0.013
 waving+0.012
ric+0.012
 driveway+0.012
Neg logit contributions
 ounces-0.017
affe-0.017
hell-0.016
isy-0.016
bors-0.015
Token who
Token ID508
Feature activation-1.79e+00

Pos logit contributions
 ounces+0.005
affe+0.004
ils+0.004
izards+0.004
bors+0.004
Neg logit contributions
burn-0.004
 blowing-0.003
 waving-0.003
 driveway-0.003
 neighborhood-0.003
Token wanted
Token ID2227
Feature activation-1.36e+00

Pos logit contributions
burn+0.043
 blowing+0.036
 waving+0.036
 driveway+0.034
 spinning+0.032
Neg logit contributions
 ounces-0.058
ils-0.055
izards-0.053
affe-0.053
bors-0.052
Token to
Token ID284
Feature activation-6.48e-01

Pos logit contributions
burn+0.018
 blowing+0.015
 waving+0.015
 spinning+0.011
 crying+0.011
Neg logit contributions
 ounces-0.060
ils-0.055
affe-0.055
izards-0.055
bors-0.055
Token prevent
Token ID2948
Feature activation+2.80e+00

Pos logit contributions
burn+0.011
 blowing+0.010
 waving+0.010
 spinning+0.008
 crying+0.008
Neg logit contributions
 ounces-0.026
ils-0.024
izards-0.024
affe-0.023
bors-0.023
Token Sof
Token ID41427
Feature activation+7.33e+00

Pos logit contributions
 ounces+0.099
affe+0.094
ils+0.091
hell+0.091
bors+0.089
Neg logit contributions
burn-0.060
 blowing-0.055
 waving-0.055
 crying-0.049
 spinning-0.048
Tokenia
Token ID544
Feature activation+2.16e+00

Pos logit contributions
 ounces+0.187
ils+0.156
bors+0.155
izards+0.145
affe+0.145
Neg logit contributions
burn-0.237
 blowing-0.217
 waving-0.211
my-0.200
 leaning-0.193
Token from
Token ID422
Feature activation-5.84e-01

Pos logit contributions
 ounces+0.074
ils+0.067
affe+0.066
izards+0.066
bors+0.066
Neg logit contributions
burn-0.050
 blowing-0.045
 waving-0.044
 spinning-0.039
 crying-0.038
Token playing
Token ID2712
Feature activation-2.77e+00

Pos logit contributions
burn+0.010
 driveway+0.008
 neighborhood+0.007
 waving+0.007
 blowing+0.007
Neg logit contributions
 ounces-0.023
ils-0.021
izards-0.021
bors-0.021
isy-0.019
Token the
Token ID262
Feature activation-3.04e-01

Pos logit contributions
burn+0.046
 waving+0.043
 blowing+0.043
 spinning+0.040
 crying+0.039
Neg logit contributions
 ounces-0.113
affe-0.103
izards-0.101
bors-0.101
ils-0.100
Token violin
Token ID38283
Feature activation+7.35e-01

Pos logit contributions
burn+0.006
ric+0.005
 waving+0.005
bie+0.005
 blowing+0.005
Neg logit contributions
 ounces-0.010
ils-0.010
affe-0.010
isy-0.010
hell-0.010
Token,
Token ID11
Feature activation+8.88e-03

Pos logit contributions
 ounces+0.018
ils+0.016
bors+0.016
hell+0.016
affe+0.016
Neg logit contributions
burn-0.007
 blowing-0.007
 waving-0.007
 spinning-0.006
 leaning-0.005
Token Betty
Token ID29504
Feature activation+4.73e-01

Pos logit contributions
 ounces+0.000
ils+0.000
hell+0.000
bors+0.000
izards+0.000
Neg logit contributions
burn-0.000
 blowing-0.000
 waving-0.000
 spinning-0.000
 shining-0.000
Token made
Token ID925
Feature activation+3.83e-01

Pos logit contributions
 ounces+0.017
ils+0.016
izards+0.016
affe+0.016
bors+0.016
Neg logit contributions
burn-0.010
 blowing-0.008
 waving-0.008
 spinning-0.007
 neighborhood-0.007
Token a
Token ID257
Feature activation-6.23e-01

Pos logit contributions
 ounces+0.015
affe+0.014
ils+0.014
izards+0.013
bors+0.013
Neg logit contributions
burn-0.007
 blowing-0.006
 waving-0.006
 crying-0.005
 spinning-0.005
Token big
Token ID1263
Feature activation+1.21e-02

Pos logit contributions
burn+0.015
 blowing+0.013
 waving+0.013
 driveway+0.011
 neighborhood+0.011
Neg logit contributions
 ounces-0.020
affe-0.019
hell-0.018
ils-0.018
isy-0.018
Token batch
Token ID15458
Feature activation+7.17e+00

Pos logit contributions
 ounces+0.000
affe+0.000
ils+0.000
hell+0.000
bors+0.000
Neg logit contributions
burn-0.000
 blowing-0.000
 waving-0.000
 driveway-0.000
 neighborhood-0.000
Token of
Token ID286
Feature activation+9.60e-01

Pos logit contributions
 ounces+0.305
bors+0.281
ns+0.258
cod+0.257
affe+0.255
Neg logit contributions
 blowing-0.108
 waving-0.100
burn-0.100
 crying-0.098
 spinning-0.091
Token butter
Token ID9215
Feature activation+1.31e+00

Pos logit contributions
 ounces+0.028
izards+0.026
affe+0.025
ils+0.025
bors+0.024
Neg logit contributions
burn-0.027
 blowing-0.025
 waving-0.024
 daddy-0.023
 spinning-0.023
Token for
Token ID329
Feature activation+3.62e+00

Pos logit contributions
 ounces+0.051
bors+0.046
izards+0.045
affe+0.044
ils+0.044
Neg logit contributions
burn-0.027
 blowing-0.024
 waving-0.022
 spinning-0.019
my-0.019
Token a
Token ID257
Feature activation+1.32e-01

Pos logit contributions
 ounces+0.155
hell+0.143
affe+0.143
bridge+0.132
ger+0.132
Neg logit contributions
 blowing-0.056
 waving-0.054
burn-0.052
 singing-0.047
 spinning-0.047
Token party
Token ID2151
Feature activation+2.55e+00

Pos logit contributions
 ounces+0.004
ils+0.004
izards+0.004
affe+0.004
bors+0.004
Neg logit contributions
burn-0.003
 blowing-0.003
 waving-0.003
 spinning-0.002
 neighborhood-0.002
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
 ounces+0.013
affe+0.012
ils+0.012
hell+0.011
bors+0.011
Neg logit contributions
burn-0.005
 waving-0.004
 blowing-0.004
 spinning-0.003
 daddy-0.003
Token her
Token ID607
Feature activation-2.25e-01

Pos logit contributions
 ounces+0.004
ils+0.004
affe+0.004
hell+0.004
izards+0.004
Neg logit contributions
burn-0.003
 blowing-0.002
 waving-0.002
 daddy-0.002
 spinning-0.002
Token mom
Token ID1995
Feature activation-4.09e+00

Pos logit contributions
burn+0.004
 blowing+0.004
 waving+0.004
 driveway+0.003
seat+0.003
Neg logit contributions
 ounces-0.008
ils-0.008
affe-0.008
izards-0.008
isy-0.008
Token baked
Token ID22979
Feature activation+1.46e+00

Pos logit contributions
burn+0.087
 waving+0.079
 blowing+0.078
 spinning+0.069
 driveway+0.068
Neg logit contributions
 ounces-0.139
ils-0.131
affe-0.128
bors-0.126
izards-0.124
Token a
Token ID257
Feature activation+1.32e-01

Pos logit contributions
 ounces+0.058
affe+0.053
izards+0.052
bors+0.052
ils+0.050
Neg logit contributions
burn-0.028
 blowing-0.025
 waving-0.024
 daddy-0.022
my-0.021
Token batch
Token ID15458
Feature activation+7.15e+00

Pos logit contributions
 ounces+0.004
affe+0.004
ils+0.004
hell+0.004
bors+0.004
Neg logit contributions
burn-0.003
 blowing-0.003
 waving-0.003
 driveway-0.003
 spinning-0.003
Token of
Token ID286
Feature activation+1.61e+00

Pos logit contributions
 ounces+0.294
bors+0.268
izards+0.251
cod+0.250
ns+0.245
Neg logit contributions
burn-0.112
 blowing-0.110
 waving-0.094
my-0.090
 daddy-0.089
Token cookies
Token ID14746
Feature activation+1.79e+00

Pos logit contributions
 ounces+0.051
izards+0.047
affe+0.046
bors+0.044
hell+0.044
Neg logit contributions
burn-0.041
 blowing-0.039
 waving-0.039
 daddy-0.036
 crying-0.034
Token and
Token ID290
Feature activation+9.88e-01

Pos logit contributions
 ounces+0.075
bors+0.068
izards+0.068
affe+0.067
ils+0.065
Neg logit contributions
burn-0.030
 blowing-0.027
 waving-0.025
my-0.021
 daddy-0.020
Token put
Token ID1234
Feature activation-3.50e-02

Pos logit contributions
 ounces+0.034
izards+0.031
affe+0.031
hell+0.031
bors+0.030
Neg logit contributions
burn-0.023
 blowing-0.021
 waving-0.021
 daddy-0.019
my-0.018
Token them
Token ID606
Feature activation+1.58e+00

Pos logit contributions
burn+0.001
 blowing+0.001
my+0.001
 daddy+0.001
 waving+0.001
Neg logit contributions
 ounces-0.001
izards-0.001
affe-0.001
bors-0.001
isy-0.001
TokenM
Token ID44
Feature activation+1.60e+00

Pos logit contributions
 ounces+0.031
izards+0.029
ils+0.028
hell+0.028
affe+0.028
Neg logit contributions
burn-0.018
 blowing-0.018
 waving-0.016
 neighborhood-0.015
 daddy-0.015
Tokenama
Token ID1689
Feature activation-2.06e+00

Pos logit contributions
 ounces+0.061
ils+0.057
hell+0.056
izards+0.056
bors+0.056
Neg logit contributions
burn-0.029
 blowing-0.026
 waving-0.025
 daddy-0.022
 neighborhood-0.021
Token asked
Token ID1965
Feature activation+1.02e-01

Pos logit contributions
burn+0.035
 blowing+0.032
 waving+0.032
my+0.026
 daddy+0.026
Neg logit contributions
 ounces-0.082
izards-0.075
ils-0.074
hell-0.073
bors-0.073
Token,
Token ID11
Feature activation-4.37e-01

Pos logit contributions
 ounces+0.004
hell+0.004
izards+0.004
affe+0.004
ils+0.004
Neg logit contributions
burn-0.001
 daddy-0.001
 blowing-0.001
 waving-0.001
my-0.001
Token "
Token ID366
Feature activation+2.05e+00

Pos logit contributions
burn+0.009
 blowing+0.009
 waving+0.009
 spinning+0.007
 daddy+0.007
Neg logit contributions
 ounces-0.016
ils-0.014
izards-0.014
affe-0.014
hell-0.014
TokenP
Token ID47
Feature activation+7.13e+00

Pos logit contributions
 ounces+0.075
ils+0.069
izards+0.069
affe+0.068
hell+0.068
Neg logit contributions
burn-0.042
 blowing-0.037
 waving-0.037
 spinning-0.031
 neighborhood-0.031
Tokenapa
Token ID32678
Feature activation+6.73e-01

Pos logit contributions
 ounces+0.183
bors+0.177
hell+0.175
ger+0.174
ils+0.169
Neg logit contributions
burn-0.182
my-0.168
rou-0.165
 daddy-0.164
 blowing-0.160
Token,
Token ID11
Feature activation-1.57e-01

Pos logit contributions
 ounces+0.027
hell+0.024
izards+0.024
ils+0.024
bors+0.024
Neg logit contributions
burn-0.012
 blowing-0.011
 waving-0.010
my-0.010
 daddy-0.009
Token can
Token ID460
Feature activation-1.61e+00

Pos logit contributions
burn+0.004
 blowing+0.004
 waving+0.004
 daddy+0.003
 spinning+0.003
Neg logit contributions
 ounces-0.005
affe-0.005
hell-0.005
ils-0.005
bors-0.005
Token we
Token ID356
Feature activation+1.40e+00

Pos logit contributions
 daddy+0.038
burn+0.037
 waving+0.037
 blowing+0.037
 spinning+0.034
Neg logit contributions
 ounces-0.052
ils-0.050
hell-0.050
affe-0.048
izards-0.047
Token use
Token ID779
Feature activation+2.80e-01

Pos logit contributions
 ounces+0.053
bors+0.048
izards+0.048
ils+0.048
hell+0.048
Neg logit contributions
burn-0.028
 blowing-0.025
 waving-0.024
 daddy-0.022
 spinning-0.021
Token there
Token ID612
Feature activation-2.11e+00

Pos logit contributions
 ounces+0.005
izards+0.004
ils+0.004
affe+0.004
bors+0.004
Neg logit contributions
burn-0.004
 blowing-0.004
 waving-0.004
 neighborhood-0.003
 driveway-0.003
Token was
Token ID373
Feature activation+1.86e+00

Pos logit contributions
burn+0.043
 blowing+0.037
 waving+0.036
 driveway+0.031
 spinning+0.031
Neg logit contributions
 ounces-0.076
affe-0.070
hell-0.069
ils-0.069
bors-0.068
Token a
Token ID257
Feature activation+1.60e-01

Pos logit contributions
 ounces+0.054
affe+0.046
hell+0.046
bors+0.045
izards+0.045
Neg logit contributions
burn-0.051
 blowing-0.044
 waving-0.043
 driveway-0.041
 neighborhood-0.041
Token loud
Token ID7812
Feature activation+9.44e-01

Pos logit contributions
 ounces+0.005
affe+0.005
hell+0.005
bors+0.005
isy+0.005
Neg logit contributions
burn-0.004
 blowing-0.003
 waving-0.003
 driveway-0.003
my-0.003
Token "
Token ID366
Feature activation+2.36e+00

Pos logit contributions
 ounces+0.029
ils+0.026
izards+0.026
affe+0.026
bors+0.026
Neg logit contributions
burn-0.024
 blowing-0.022
 waving-0.022
 spinning-0.020
 neighborhood-0.019
TokenP
Token ID47
Feature activation+7.10e+00

Pos logit contributions
 ounces+0.070
ils+0.064
izards+0.063
affe+0.063
bors+0.062
Neg logit contributions
burn-0.065
 blowing-0.059
 waving-0.057
 spinning-0.052
my-0.051
TokenOP
Token ID3185
Feature activation+4.27e+00

Pos logit contributions
 ounces+0.172
bors+0.170
ils+0.169
izards+0.151
 mushrooms+0.151
Neg logit contributions
burn-0.207
 waving-0.184
 blowing-0.180
 neighborhood-0.175
 leaning-0.174
Token!"
Token ID2474
Feature activation+2.23e+00

Pos logit contributions
 ounces+0.104
izards+0.098
ils+0.092
bors+0.091
affe+0.090
Neg logit contributions
burn-0.140
 blowing-0.129
 waving-0.124
 spinning-0.116
 leaning-0.112
Token Rob
Token ID3851
Feature activation-4.75e-02

Pos logit contributions
 ounces+0.076
ils+0.069
izards+0.068
affe+0.068
bors+0.068
Neg logit contributions
burn-0.051
 blowing-0.046
 waving-0.046
 spinning-0.040
 neighborhood-0.039
Token stopped
Token ID5025
Feature activation-5.42e+00

Pos logit contributions
burn+0.001
 blowing+0.001
 waving+0.001
 daddy+0.001
 spinning+0.001
Neg logit contributions
 ounces-0.002
izards-0.002
ils-0.002
bors-0.002
affe-0.002
Token and
Token ID290
Feature activation+5.83e-02

Pos logit contributions
burn+0.145
 driveway+0.127
icycle+0.111
 salon+0.111
bars+0.110
Neg logit contributions
izards-0.127
 ounces-0.123
 itself-0.118
 beetles-0.114
isy-0.113
Token and
Token ID290
Feature activation-5.20e-01

Pos logit contributions
burn+0.023
 blowing+0.019
 waving+0.019
 driveway+0.016
 neighborhood+0.016
Neg logit contributions
 ounces-0.055
ils-0.051
affe-0.050
izards-0.050
bors-0.050
Token decided
Token ID3066
Feature activation+1.48e+00

Pos logit contributions
burn+0.012
 blowing+0.010
 waving+0.010
 neighborhood+0.009
 driveway+0.009
Neg logit contributions
 ounces-0.017
ils-0.016
bors-0.016
affe-0.016
izards-0.016
Token to
Token ID284
Feature activation-8.29e-01

Pos logit contributions
 ounces+0.061
ils+0.056
izards+0.056
affe+0.056
bors+0.056
Neg logit contributions
burn-0.023
 blowing-0.020
 waving-0.020
 spinning-0.016
 neighborhood-0.015
Token make
Token ID787
Feature activation+1.41e+00

Pos logit contributions
burn+0.020
 blowing+0.019
 waving+0.018
 neighborhood+0.016
 spinning+0.016
Neg logit contributions
 ounces-0.026
ils-0.024
affe-0.024
bors-0.023
izards-0.023
Token another
Token ID1194
Feature activation-1.26e+00

Pos logit contributions
 ounces+0.049
affe+0.046
izards+0.044
bors+0.044
ils+0.044
Neg logit contributions
burn-0.032
 blowing-0.029
 waving-0.028
 daddy-0.026
 spinning-0.025
Token batch
Token ID15458
Feature activation+7.06e+00

Pos logit contributions
burn+0.032
 blowing+0.029
 waving+0.028
 spinning+0.025
 neighborhood+0.025
Neg logit contributions
 ounces-0.040
ils-0.036
izards-0.036
affe-0.036
bors-0.036
Token of
Token ID286
Feature activation+9.36e-01

Pos logit contributions
 ounces+0.275
bors+0.253
affe+0.245
ns+0.242
ocket+0.237
Neg logit contributions
 blowing-0.113
burn-0.105
 waving-0.099
 laughing-0.093
 crying-0.092
Token muff
Token ID27563
Feature activation+1.48e+00

Pos logit contributions
 ounces+0.031
affe+0.031
izards+0.031
ils+0.030
bors+0.030
Neg logit contributions
 blowing-0.019
 waving-0.019
burn-0.019
 spinning-0.017
 crying-0.017
Tokenins
Token ID1040
Feature activation+2.50e+00

Pos logit contributions
affe+0.048
 ounces+0.047
bors+0.046
nic+0.043
ger+0.043
Neg logit contributions
burn-0.031
 blowing-0.030
my-0.026
 waving-0.025
rou-0.025
Token together
Token ID1978
Feature activation-2.85e-01

Pos logit contributions
 ounces+0.103
bors+0.096
affe+0.092
izards+0.091
ils+0.088
Neg logit contributions
burn-0.041
 blowing-0.038
 waving-0.035
my-0.032
 daddy-0.029
Token,
Token ID11
Feature activation-3.85e-03

Pos logit contributions
burn+0.005
 blowing+0.005
 waving+0.005
 spinning+0.004
 crying+0.004
Neg logit contributions
 ounces-0.011
izards-0.010
affe-0.010
bors-0.010
ils-0.009
Token knock
Token ID10643
Feature activation-2.08e+00

Pos logit contributions
burn+0.024
 blowing+0.021
 waving+0.021
 neighborhood+0.018
 driveway+0.018
Neg logit contributions
 ounces-0.034
ils-0.030
affe-0.030
izards-0.030
bors-0.030
Token and
Token ID290
Feature activation+7.39e-01

Pos logit contributions
burn+0.045
 blowing+0.042
 waving+0.041
 spinning+0.036
 leaning+0.036
Neg logit contributions
 ounces-0.072
affe-0.066
bors-0.065
izards-0.065
ils-0.065
Token a
Token ID257
Feature activation+1.03e-01

Pos logit contributions
 ounces+0.025
ils+0.022
izards+0.022
bors+0.022
affe+0.022
Neg logit contributions
burn-0.017
 blowing-0.014
 waving-0.014
 neighborhood-0.013
 driveway-0.012
Token fresh
Token ID4713
Feature activation+9.01e-02

Pos logit contributions
 ounces+0.004
affe+0.003
ils+0.003
izards+0.003
bors+0.003
Neg logit contributions
burn-0.002
 blowing-0.002
 waving-0.002
 spinning-0.002
 neighborhood-0.002
Token new
Token ID649
Feature activation-9.73e-01

Pos logit contributions
 ounces+0.003
ils+0.003
izards+0.003
affe+0.003
bors+0.003
Neg logit contributions
burn-0.002
 blowing-0.002
 waving-0.002
 spinning-0.002
 driveway-0.002
Token batch
Token ID15458
Feature activation+7.05e+00

Pos logit contributions
burn+0.021
 blowing+0.019
 waving+0.019
 driveway+0.016
 neighborhood+0.016
Neg logit contributions
 ounces-0.034
affe-0.030
ils-0.030
hell-0.030
bors-0.030
Token of
Token ID286
Feature activation+1.35e+00

Pos logit contributions
 ounces+0.264
bors+0.251
cod+0.246
reath+0.236
izards+0.231
Neg logit contributions
 blowing-0.110
burn-0.102
 waving-0.098
 crying-0.088
 daddy-0.086
Token letters
Token ID7475
Feature activation-2.52e-01

Pos logit contributions
 ounces+0.040
izards+0.037
affe+0.037
ils+0.036
bors+0.036
Neg logit contributions
burn-0.035
 blowing-0.034
 waving-0.033
 spinning-0.030
 daddy-0.030
Token would
Token ID561
Feature activation+1.08e-02

Pos logit contributions
burn+0.006
 blowing+0.005
 waving+0.005
 spinning+0.004
 daddy+0.004
Neg logit contributions
 ounces-0.009
ils-0.008
bors-0.008
izards-0.008
affe-0.008
Token tumble
Token ID47978
Feature activation+6.86e-01

Pos logit contributions
 ounces+0.000
izards+0.000
ils+0.000
affe+0.000
bors+0.000
Neg logit contributions
burn-0.000
 blowing-0.000
 waving-0.000
 spinning-0.000
 crying-0.000
Token out
Token ID503
Feature activation-2.34e-01

Pos logit contributions
 ounces+0.026
izards+0.024
bors+0.024
affe+0.024
ils+0.024
Neg logit contributions
burn-0.013
 blowing-0.012
 waving-0.011
 spinning-0.010
my-0.009
Token to
Token ID284
Feature activation-5.04e-01

Pos logit contributions
burn+0.010
 blowing+0.009
 waving+0.009
 spinning+0.008
 crying+0.008
Neg logit contributions
 ounces-0.017
ils-0.016
bors-0.016
affe-0.016
izards-0.016
Token do
Token ID466
Feature activation+1.73e+00

Pos logit contributions
burn+0.009
 waving+0.009
 blowing+0.009
 spinning+0.008
 daddy+0.007
Neg logit contributions
 ounces-0.020
ils-0.018
affe-0.017
izards-0.017
bors-0.017
Token was
Token ID373
Feature activation+1.11e+00

Pos logit contributions
 ounces+0.068
affe+0.066
bors+0.061
izards+0.061
ils+0.060
Neg logit contributions
 waving-0.027
 blowing-0.027
burn-0.025
 spinning-0.024
 crying-0.023
Token to
Token ID284
Feature activation-1.45e-01

Pos logit contributions
 ounces+0.041
affe+0.037
ils+0.036
bors+0.036
izards+0.036
Neg logit contributions
burn-0.023
 blowing-0.022
 waving-0.021
 spinning-0.018
 crying-0.018
Token pick
Token ID2298
Feature activation+2.41e+00

Pos logit contributions
burn+0.003
 waving+0.003
 blowing+0.003
 spinning+0.002
 daddy+0.002
Neg logit contributions
 ounces-0.005
affe-0.005
izards-0.005
ils-0.005
bors-0.005
Token da
Token ID12379
Feature activation+7.01e+00

Pos logit contributions
 ounces+0.100
affe+0.090
bors+0.088
izards+0.085
ils+0.084
Neg logit contributions
burn-0.039
 waving-0.034
 blowing-0.034
my-0.032
 shining-0.030
Tokenis
Token ID271
Feature activation+2.91e+00

Pos logit contributions
 ounces+0.217
affe+0.175
 pounds+0.164
bors+0.164
izards+0.161
Neg logit contributions
burn-0.187
 blowing-0.181
 waving-0.173
 shining-0.160
 spinning-0.159
Tokenies
Token ID444
Feature activation+1.52e+00

Pos logit contributions
 ounces+0.114
affe+0.105
ocket+0.099
izards+0.097
ger+0.096
Neg logit contributions
burn-0.047
 blowing-0.047
 waving-0.040
my-0.037
 spinning-0.036
Token and
Token ID290
Feature activation+3.16e-01

Pos logit contributions
 ounces+0.064
affe+0.057
bors+0.056
ils+0.055
izards+0.055
Neg logit contributions
burn-0.025
 waving-0.024
 blowing-0.023
 spinning-0.019
 crying-0.018
Token give
Token ID1577
Feature activation+8.64e-01

Pos logit contributions
 ounces+0.011
ils+0.010
affe+0.010
izards+0.010
bors+0.010
Neg logit contributions
burn-0.007
 blowing-0.006
 waving-0.006
 spinning-0.005
 daddy-0.005
Token them
Token ID606
Feature activation+1.71e+00

Pos logit contributions
 ounces+0.031
affe+0.028
izards+0.027
hell+0.027
bors+0.026
Neg logit contributions
burn-0.019
 blowing-0.017
 waving-0.017
 daddy-0.016
my-0.016
Token she
Token ID673
Feature activation+2.01e+00

Pos logit contributions
 ounces+0.016
ils+0.015
izards+0.015
affe+0.015
bors+0.015
Neg logit contributions
burn-0.014
 blowing-0.013
 waving-0.013
 driveway-0.011
 neighborhood-0.011
Token asked
Token ID1965
Feature activation+8.11e-01

Pos logit contributions
 ounces+0.065
ils+0.062
izards+0.059
affe+0.058
bors+0.058
Neg logit contributions
burn-0.049
 blowing-0.044
 waving-0.043
 spinning-0.037
 driveway-0.036
Token him
Token ID683
Feature activation+1.01e+00

Pos logit contributions
 ounces+0.033
affe+0.029
hell+0.029
bors+0.029
izards+0.029
Neg logit contributions
burn-0.015
 blowing-0.013
 waving-0.013
 daddy-0.012
 crying-0.011
Token,
Token ID11
Feature activation-2.31e-01

Pos logit contributions
 ounces+0.049
bors+0.044
affe+0.043
ils+0.043
hell+0.043
Neg logit contributions
burn-0.010
 waving-0.009
 daddy-0.009
my-0.008
 crying-0.007
Token "
Token ID366
Feature activation+2.51e+00

Pos logit contributions
burn+0.006
 blowing+0.005
 waving+0.005
 driveway+0.005
 neighborhood+0.005
Neg logit contributions
 ounces-0.007
affe-0.006
izards-0.006
bors-0.006
ils-0.006
TokenP
Token ID47
Feature activation+7.00e+00

Pos logit contributions
 ounces+0.086
ils+0.078
bors+0.077
affe+0.077
izards+0.076
Neg logit contributions
burn-0.055
 blowing-0.052
 waving-0.051
 spinning-0.044
 crying-0.044
Tokenapa
Token ID32678
Feature activation+3.40e-01

Pos logit contributions
 ounces+0.215
bors+0.194
ils+0.189
hell+0.182
affe+0.181
Neg logit contributions
burn-0.183
 blowing-0.153
 waving-0.152
my-0.150
 neighborhood-0.149
Token,
Token ID11
Feature activation+7.67e-02

Pos logit contributions
 ounces+0.013
izards+0.012
ils+0.012
bors+0.012
affe+0.012
Neg logit contributions
burn-0.007
 blowing-0.006
 waving-0.006
 daddy-0.005
my-0.005
Token why
Token ID1521
Feature activation-1.60e+00

Pos logit contributions
 ounces+0.002
ils+0.002
affe+0.002
izards+0.002
bors+0.002
Neg logit contributions
burn-0.002
 blowing-0.002
 waving-0.002
 spinning-0.002
 daddy-0.002
Token do
Token ID466
Feature activation-5.90e-01

Pos logit contributions
burn+0.041
 blowing+0.037
 waving+0.037
 driveway+0.033
 neighborhood+0.033
Neg logit contributions
 ounces-0.050
ils-0.045
izards-0.045
affe-0.045
hell-0.044
Token you
Token ID345
Feature activation+2.04e+00

Pos logit contributions
burn+0.014
 daddy+0.014
 waving+0.014
 blowing+0.013
 grandma+0.013
Neg logit contributions
 ounces-0.018
hell-0.017
ils-0.017
affe-0.016
izards-0.016
Token they
Token ID484
Feature activation+9.09e-01

Pos logit contributions
 ounces+0.019
ils+0.017
affe+0.017
hell+0.017
izards+0.017
Neg logit contributions
burn-0.013
 blowing-0.012
 waving-0.012
 daddy-0.011
 spinning-0.011
Token could
Token ID714
Feature activation-3.48e+00

Pos logit contributions
 ounces+0.035
bors+0.031
affe+0.030
izards+0.030
hell+0.030
Neg logit contributions
burn-0.018
 blowing-0.016
 waving-0.016
my-0.014
 neighborhood-0.013
Token grow
Token ID1663
Feature activation+1.15e+00

Pos logit contributions
burn+0.087
 blowing+0.078
 waving+0.077
 neighborhood+0.068
 driveway+0.068
Neg logit contributions
 ounces-0.112
ils-0.101
izards-0.100
affe-0.099
bors-0.098
Token more
Token ID517
Feature activation+3.92e-01

Pos logit contributions
 ounces+0.047
affe+0.042
bors+0.041
ils+0.040
izards+0.038
Neg logit contributions
burn-0.020
 blowing-0.019
 waving-0.018
 shining-0.017
 spinning-0.016
Token av
Token ID1196
Feature activation+2.78e+00

Pos logit contributions
 ounces+0.012
affe+0.010
bors+0.010
ils+0.010
izards+0.010
Neg logit contributions
 blowing-0.010
 waving-0.010
burn-0.010
 neighborhood-0.009
 window-0.009
Tokenoc
Token ID420
Feature activation+6.96e+00

Pos logit contributions
 ounces+0.046
izards+0.038
bors+0.037
ils+0.037
affe+0.034
Neg logit contributions
burn-0.112
 blowing-0.105
 waving-0.103
my-0.099
 neighborhood-0.097
Tokenados
Token ID22484
Feature activation+2.50e+00

Pos logit contributions
 ounces+0.103
izards+0.097
hell+0.089
bors+0.089
isy+0.084
Neg logit contributions
burn-0.267
 blowing-0.251
 waving-0.246
 leaning-0.240
 crying-0.227
Token and
Token ID290
Feature activation+3.93e-01

Pos logit contributions
 ounces+0.099
bors+0.090
affe+0.088
ils+0.086
izards+0.086
Neg logit contributions
burn-0.045
 blowing-0.041
 waving-0.041
my-0.034
 daddy-0.034
Token share
Token ID2648
Feature activation-2.18e-01

Pos logit contributions
 ounces+0.013
affe+0.012
ils+0.012
izards+0.012
bors+0.012
Neg logit contributions
burn-0.009
 waving-0.008
 blowing-0.008
 spinning-0.007
 daddy-0.007
Token them
Token ID606
Feature activation+1.24e+00

Pos logit contributions
 waving+0.004
burn+0.004
 blowing+0.004
 daddy+0.004
my+0.004
Neg logit contributions
 ounces-0.008
affe-0.007
izards-0.007
bors-0.007
ils-0.007
Token with
Token ID351
Feature activation+1.62e+00

Pos logit contributions
 ounces+0.059
affe+0.054
bors+0.053
izards+0.052
ils+0.050
Neg logit contributions
burn-0.010
 waving-0.010
 blowing-0.009
my-0.008
 daddy-0.008
Token he
Token ID339
Feature activation+1.51e+00

Pos logit contributions
 ounces+0.043
ils+0.039
affe+0.039
izards+0.038
bors+0.038
Neg logit contributions
burn-0.035
 blowing-0.033
 waving-0.032
 spinning-0.029
 daddy-0.028
Token shook
Token ID14682
Feature activation-1.06e+00

Pos logit contributions
 ounces+0.053
affe+0.048
bors+0.048
izards+0.048
hell+0.048
Neg logit contributions
burn-0.032
 blowing-0.029
 waving-0.029
 neighborhood-0.026
 spinning-0.025
Token it
Token ID340
Feature activation+1.29e+00

Pos logit contributions
burn+0.026
 blowing+0.023
 waving+0.023
 spinning+0.020
 neighborhood+0.020
Neg logit contributions
 ounces-0.035
ils-0.031
izards-0.031
affe-0.031
bors-0.030
Token.
Token ID13
Feature activation-5.18e-01

Pos logit contributions
 ounces+0.046
ils+0.042
izards+0.042
bors+0.042
affe+0.042
Neg logit contributions
burn-0.027
 blowing-0.025
 waving-0.024
 spinning-0.021
 crying-0.021
Token<|endoftext|>
Token ID50256
Feature activation-2.85e+00

Pos logit contributions
burn+0.009
 waving+0.008
 blowing+0.008
 neighborhood+0.007
 daddy+0.007
Neg logit contributions
 ounces-0.020
ils-0.019
izards-0.018
bors-0.018
affe-0.018
TokenPa
Token ID28875
Feature activation+6.92e+00

Pos logit contributions
burn+0.055
 blowing+0.048
 waving+0.048
 spinning+0.040
 neighborhood+0.040
Neg logit contributions
 ounces-0.107
ils-0.098
izards-0.097
affe-0.097
bors-0.096
Tokenola
Token ID5708
Feature activation+2.91e+00

Pos logit contributions
 ounces+0.207
bors+0.177
izards+0.170
ils+0.169
hell+0.164
Neg logit contributions
burn-0.190
 waving-0.174
 blowing-0.170
my-0.165
 neighborhood-0.159
Token and
Token ID290
Feature activation-2.61e-01

Pos logit contributions
 ounces+0.106
ils+0.100
affe+0.097
bors+0.096
izards+0.096
Neg logit contributions
burn-0.059
 blowing-0.051
 waving-0.050
 spinning-0.042
 crying-0.041
Token her
Token ID607
Feature activation+1.88e-01

Pos logit contributions
burn+0.007
 blowing+0.006
 waving+0.006
 spinning+0.005
 driveway+0.005
Neg logit contributions
 ounces-0.008
affe-0.007
izards-0.007
ils-0.007
bors-0.007
Token mother
Token ID2802
Feature activation-2.28e+00

Pos logit contributions
affe+0.006
ily+0.006
ils+0.006
 ounces+0.006
izards+0.006
Neg logit contributions
burn-0.004
 blowing-0.004
 waving-0.003
 driveway-0.003
seat-0.003
Token were
Token ID547
Feature activation+9.27e-02

Pos logit contributions
burn+0.055
 blowing+0.049
 waving+0.047
 spinning+0.043
 driveway+0.041
Neg logit contributions
 ounces-0.070
ils-0.069
affe-0.065
bors-0.064
izards-0.063
Token
Token ID198
Feature activation+3.86e-01

Pos logit contributions
burn+0.016
 blowing+0.014
 waving+0.014
 spinning+0.011
 neighborhood+0.011
Neg logit contributions
 ounces-0.040
ils-0.037
izards-0.036
affe-0.036
bors-0.036
Token
Token ID198
Feature activation+1.13e+00

Pos logit contributions
 ounces+0.017
ils+0.016
affe+0.015
izards+0.015
bors+0.015
Neg logit contributions
burn-0.005
 blowing-0.004
 waving-0.004
 neighborhood-0.003
my-0.003
TokenThe
Token ID464
Feature activation-9.30e-01

Pos logit contributions
 ounces+0.038
ils+0.037
izards+0.036
ocket+0.035
affe+0.035
Neg logit contributions
burn-0.023
 blowing-0.022
 waving-0.021
 neighborhood-0.020
 driveway-0.019
Token two
Token ID734
Feature activation-2.66e-01

Pos logit contributions
burn+0.023
 blowing+0.020
 waving+0.020
 spinning+0.018
 neighborhood+0.018
Neg logit contributions
 ounces-0.031
ils-0.028
izards-0.027
affe-0.027
bors-0.027
Token combatants
Token ID40711
Feature activation-1.02e+00

Pos logit contributions
burn+0.006
 waving+0.005
 blowing+0.005
 spinning+0.005
 daddy+0.005
Neg logit contributions
 ounces-0.009
ils-0.008
izards-0.008
bors-0.008
hell-0.008
Token stopped
Token ID5025
Feature activation-6.66e+00

Pos logit contributions
burn+0.023
 blowing+0.021
 waving+0.021
 spinning+0.018
 neighborhood+0.018
Neg logit contributions
 ounces-0.035
ils-0.031
izards-0.031
affe-0.031
bors-0.031
Token fighting
Token ID4330
Feature activation-2.24e+00

Pos logit contributions
burn+0.163
 driveway+0.138
icycle+0.122
tr+0.118
 salon+0.117
Neg logit contributions
 ounces-0.210
izards-0.197
ils-0.191
bors-0.189
ious-0.178
Token and
Token ID290
Feature activation-2.35e-01

Pos logit contributions
burn+0.048
 blowing+0.041
 waving+0.040
 neighborhood+0.036
 driveway+0.036
Neg logit contributions
 ounces-0.079
ils-0.073
izards-0.072
affe-0.071
hell-0.071
Token looked
Token ID3114
Feature activation+9.62e-02

Pos logit contributions
burn+0.005
 blowing+0.005
 waving+0.005
 spinning+0.004
 daddy+0.004
Neg logit contributions
 ounces-0.008
ils-0.007
affe-0.007
izards-0.007
bors-0.007
Token at
Token ID379
Feature activation-5.50e-01

Pos logit contributions
 ounces+0.003
affe+0.003
izards+0.003
ils+0.003
bors+0.003
Neg logit contributions
burn-0.002
 waving-0.002
 blowing-0.002
 spinning-0.002
 crying-0.002
Token the
Token ID262
Feature activation-2.86e-01

Pos logit contributions
burn+0.013
 blowing+0.011
 waving+0.011
 spinning+0.010
 daddy+0.010
Neg logit contributions
 ounces-0.019
ils-0.017
affe-0.017
izards-0.017
bors-0.017
Token using
Token ID1262
Feature activation-5.34e-01

Pos logit contributions
 ounces+0.049
ils+0.045
izards+0.044
bors+0.044
affe+0.043
Neg logit contributions
burn-0.027
 blowing-0.023
 waving-0.023
 driveway-0.020
 neighborhood-0.020
Token his
Token ID465
Feature activation-9.03e-02

Pos logit contributions
burn+0.012
 blowing+0.011
 waving+0.011
 spinning+0.010
 daddy+0.009
Neg logit contributions
 ounces-0.018
ils-0.016
affe-0.016
izards-0.016
bors-0.016
Token problem
Token ID1917
Feature activation+1.99e-01

Pos logit contributions
burn+0.002
 blowing+0.002
 waving+0.002
 spinning+0.002
 neighborhood+0.002
Neg logit contributions
 ounces-0.003
ils-0.003
izards-0.003
affe-0.003
bors-0.003
Token-
Token ID12
Feature activation+3.57e+00

Pos logit contributions
 ounces+0.007
ils+0.006
affe+0.006
izards+0.006
bors+0.006
Neg logit contributions
burn-0.005
 blowing-0.004
 waving-0.004
 spinning-0.004
 neighborhood-0.004
Tokens
Token ID82
Feature activation-4.14e-01

Pos logit contributions
 ounces+0.101
izards+0.090
affe+0.090
ils+0.089
bors+0.088
Neg logit contributions
burn-0.098
 blowing-0.092
 waving-0.089
my-0.083
 spinning-0.082
Tokenolving
Token ID10890
Feature activation-6.47e+00

Pos logit contributions
burn+0.010
 blowing+0.009
 waving+0.009
 driveway+0.007
 neighborhood+0.007
Neg logit contributions
 ounces-0.014
ils-0.013
izards-0.012
affe-0.012
bors-0.012
Token skills
Token ID4678
Feature activation+1.02e+00

Pos logit contributions
burn+0.196
 blowing+0.177
 waving+0.177
 crying+0.158
 spinning+0.157
Neg logit contributions
 ounces-0.178
ils-0.156
affe-0.152
izards-0.151
hell-0.150
Token.
Token ID13
Feature activation-2.95e-01

Pos logit contributions
 ounces+0.036
ils+0.032
izards+0.032
affe+0.032
bors+0.032
Neg logit contributions
burn-0.023
 blowing-0.021
 waving-0.020
 spinning-0.018
 neighborhood-0.017
Token From
Token ID3574
Feature activation+1.32e+00

Pos logit contributions
burn+0.007
 blowing+0.007
 waving+0.007
 daddy+0.006
 neighborhood+0.006
Neg logit contributions
 ounces-0.009
ils-0.009
izards-0.008
bors-0.008
affe-0.008
Token that
Token ID326
Feature activation-3.38e+00

Pos logit contributions
 ounces+0.034
ils+0.031
izards+0.030
affe+0.030
bors+0.030
Neg logit contributions
burn-0.042
 blowing-0.037
 waving-0.036
 driveway-0.034
 neighborhood-0.033
Token day
Token ID1110
Feature activation-7.24e-01

Pos logit contributions
burn+0.083
 waving+0.067
 blowing+0.063
 driveway+0.061
seat+0.059
Neg logit contributions
 ounces-0.109
affe-0.101
ils-0.100
isy-0.098
hell-0.097
Token it
Token ID340
Feature activation+2.54e+00

Pos logit contributions
 ounces+0.055
ils+0.051
affe+0.050
bors+0.050
izards+0.050
Neg logit contributions
burn-0.037
 waving-0.035
 blowing-0.035
 spinning-0.031
 leaning-0.031
Token,
Token ID11
Feature activation-1.95e-01

Pos logit contributions
 ounces+0.100
ils+0.092
bors+0.092
affe+0.090
izards+0.089
Neg logit contributions
burn-0.045
 blowing-0.042
 waving-0.042
 spinning-0.037
 crying-0.035
Token but
Token ID475
Feature activation+1.97e-01

Pos logit contributions
burn+0.004
 waving+0.004
 blowing+0.004
 spinning+0.004
 crying+0.004
Neg logit contributions
 ounces-0.007
ils-0.006
affe-0.006
bors-0.006
izards-0.006
Token his
Token ID465
Feature activation-1.14e+00

Pos logit contributions
 ounces+0.007
ils+0.006
bors+0.006
affe+0.006
hell+0.006
Neg logit contributions
burn-0.004
 waving-0.004
 blowing-0.004
 daddy-0.004
 spinning-0.004
Token mom
Token ID1995
Feature activation-4.25e+00

Pos logit contributions
burn+0.026
 blowing+0.025
 waving+0.022
 typing+0.022
ric+0.022
Neg logit contributions
 ounces-0.033
affe-0.032
aces-0.030
hell-0.030
izards-0.030
Token stopped
Token ID5025
Feature activation-6.30e+00

Pos logit contributions
burn+0.112
 blowing+0.100
 waving+0.099
 driveway+0.091
 neighborhood+0.089
Neg logit contributions
 ounces-0.128
ils-0.117
affe-0.116
izards-0.114
bors-0.112
Token him
Token ID683
Feature activation-7.81e-01

Pos logit contributions
burn+0.174
 driveway+0.150
 neighborhood+0.136
 waving+0.134
 blowing+0.133
Neg logit contributions
 ounces-0.171
izards-0.162
bors-0.158
ils-0.149
isy-0.149
Token.
Token ID13
Feature activation+2.38e-01

Pos logit contributions
burn+0.018
 blowing+0.016
 waving+0.016
 neighborhood+0.015
 driveway+0.014
Neg logit contributions
 ounces-0.025
ils-0.023
hell-0.023
affe-0.023
izards-0.023
Token She
Token ID1375
Feature activation+7.24e-01

Pos logit contributions
 ounces+0.007
affe+0.007
ils+0.006
izards+0.006
hell+0.006
Neg logit contributions
burn-0.006
 blowing-0.006
 waving-0.005
 spinning-0.005
 daddy-0.005
Token told
Token ID1297
Feature activation+2.66e+00

Pos logit contributions
 ounces+0.026
izards+0.024
ils+0.024
hell+0.024
bors+0.023
Neg logit contributions
burn-0.015
 blowing-0.014
 waving-0.014
 daddy-0.012
 spinning-0.012
Token him
Token ID683
Feature activation+4.23e-01

Pos logit contributions
 ounces+0.099
ils+0.089
affe+0.088
izards+0.088
bors+0.088
Neg logit contributions
burn-0.053
 waving-0.048
 blowing-0.048
 daddy-0.042
my-0.042
Token But
Token ID887
Feature activation+1.07e+00

Pos logit contributions
 ounces+0.020
ils+0.019
izards+0.018
bors+0.018
affe+0.018
Neg logit contributions
burn-0.015
 waving-0.014
 blowing-0.014
 neighborhood-0.013
 driveway-0.013
Token he
Token ID339
Feature activation+9.41e-01

Pos logit contributions
 ounces+0.035
ils+0.031
affe+0.031
izards+0.031
bors+0.031
Neg logit contributions
burn-0.026
 blowing-0.023
 waving-0.023
 driveway-0.020
 neighborhood-0.020
Token wasn
Token ID2492
Feature activation+7.59e-02

Pos logit contributions
 ounces+0.033
ils+0.031
izards+0.030
affe+0.030
bors+0.030
Neg logit contributions
burn-0.020
 waving-0.018
 blowing-0.018
 driveway-0.016
 spinning-0.015
Token't
Token ID470
Feature activation-3.01e+00

Pos logit contributions
 ounces+0.003
izards+0.002
affe+0.002
hell+0.002
ils+0.002
Neg logit contributions
burn-0.002
 waving-0.002
 blowing-0.002
 neighborhood-0.001
 driveway-0.001
Token happy
Token ID3772
Feature activation+6.30e-01

Pos logit contributions
burn+0.062
 blowing+0.057
 waving+0.055
 spinning+0.048
 crying+0.047
Neg logit contributions
 ounces-0.113
ils-0.103
affe-0.102
bors-0.101
izards-0.100
Token living
Token ID2877
Feature activation-6.30e+00

Pos logit contributions
 ounces+0.020
izards+0.018
ils+0.018
affe+0.017
hell+0.017
Neg logit contributions
burn-0.016
 blowing-0.014
 waving-0.014
 driveway-0.013
 neighborhood-0.013
Token high
Token ID1029
Feature activation-2.19e-01

Pos logit contributions
burn+0.157
 blowing+0.140
 waving+0.138
 driveway+0.127
 spinning+0.119
Neg logit contributions
 ounces-0.202
ils-0.187
izards-0.184
bors-0.175
hell-0.174
Token above
Token ID2029
Feature activation-2.16e+00

Pos logit contributions
burn+0.005
 blowing+0.004
 waving+0.004
 driveway+0.004
 spinning+0.004
Neg logit contributions
 ounces-0.008
ils-0.007
izards-0.007
affe-0.007
bors-0.007
Token the
Token ID262
Feature activation+4.25e-01

Pos logit contributions
burn+0.034
 blowing+0.033
 waving+0.032
 leaning+0.028
my+0.028
Neg logit contributions
 ounces-0.086
izards-0.079
bors-0.079
ils-0.079
affe-0.077
Token rest
Token ID1334
Feature activation-2.89e+00

Pos logit contributions
 ounces+0.015
affe+0.014
ils+0.013
bors+0.013
izards+0.013
Neg logit contributions
burn-0.009
 blowing-0.008
 waving-0.008
 spinning-0.007
 driveway-0.007
Token of
Token ID286
Feature activation-2.10e-03

Pos logit contributions
burn+0.069
 blowing+0.068
 waving+0.065
 spinning+0.059
my+0.058
Neg logit contributions
 ounces-0.092
bors-0.085
ils-0.082
affe-0.081
hell-0.079
Tokenunk
Token ID2954
Feature activation+7.13e-01

Pos logit contributions
burn+0.026
 blowing+0.024
 waving+0.023
 spinning+0.021
 neighborhood+0.021
Neg logit contributions
 ounces-0.026
affe-0.022
hell-0.022
ils-0.022
bors-0.022
Token!
Token ID0
Feature activation+1.76e-01

Pos logit contributions
 ounces+0.026
bors+0.023
izards+0.023
hell+0.023
ils+0.023
Neg logit contributions
burn-0.014
 blowing-0.014
 waving-0.014
 crying-0.013
 spinning-0.012
Token He
Token ID679
Feature activation-5.22e-02

Pos logit contributions
 ounces+0.005
ils+0.005
hell+0.005
izards+0.005
isy+0.005
Neg logit contributions
burn-0.005
 blowing-0.004
 waving-0.004
 daddy-0.004
 crying-0.004
Token's
Token ID338
Feature activation-1.24e+00

Pos logit contributions
burn+0.001
 blowing+0.001
 waving+0.001
 crying+0.001
my+0.001
Neg logit contributions
 ounces-0.002
hell-0.002
izards-0.002
affe-0.002
bors-0.002
Token been
Token ID587
Feature activation-1.68e+00

Pos logit contributions
burn+0.025
 blowing+0.022
 waving+0.022
 spinning+0.019
 driveway+0.018
Neg logit contributions
 ounces-0.045
ils-0.041
izards-0.041
affe-0.041
bors-0.041
Token living
Token ID2877
Feature activation-6.30e+00

Pos logit contributions
burn+0.033
 blowing+0.029
 waving+0.028
 driveway+0.024
 neighborhood+0.024
Neg logit contributions
 ounces-0.063
ils-0.057
izards-0.057
bors-0.057
affe-0.056
Token around
Token ID1088
Feature activation-2.11e+00

Pos logit contributions
burn+0.146
 blowing+0.132
 waving+0.131
 spinning+0.115
 neighborhood+0.114
Neg logit contributions
 ounces-0.213
ils-0.192
affe-0.192
izards-0.191
bors-0.190
Token here
Token ID994
Feature activation-8.61e-01

Pos logit contributions
burn+0.037
 blowing+0.036
 waving+0.035
 spinning+0.030
 crying+0.030
Neg logit contributions
 ounces-0.082
affe-0.075
hell-0.074
izards-0.074
ils-0.074
Token for
Token ID329
Feature activation+2.41e+00

Pos logit contributions
burn+0.016
 blowing+0.015
 waving+0.015
 spinning+0.012
 neighborhood+0.012
Neg logit contributions
 ounces-0.033
ils-0.030
izards-0.030
affe-0.030
bors-0.030
Token a
Token ID257
Feature activation-1.48e-01

Pos logit contributions
affe+0.099
 ounces+0.098
hell+0.093
izards+0.092
ils+0.092
Neg logit contributions
 blowing-0.034
 waving-0.032
burn-0.031
 spinning-0.028
 crying-0.027
Token while
Token ID981
Feature activation+1.91e+00

Pos logit contributions
burn+0.003
 blowing+0.003
 waving+0.003
 spinning+0.003
 daddy+0.003
Neg logit contributions
 ounces-0.005
ils-0.005
izards-0.005
affe-0.005
bors-0.005
Token.
Token ID13
Feature activation+6.74e-01

Pos logit contributions
 ounces+0.016
ils+0.014
izards+0.014
bors+0.014
affe+0.014
Neg logit contributions
burn-0.011
 blowing-0.010
 waving-0.010
 spinning-0.009
 crying-0.009
Token Max
Token ID5436
Feature activation-8.40e-01

Pos logit contributions
 ounces+0.023
affe+0.022
hell+0.021
izards+0.021
bors+0.021
Neg logit contributions
burn-0.015
 blowing-0.013
 waving-0.013
 crying-0.011
 neighborhood-0.011
Token was
Token ID373
Feature activation-1.12e+00

Pos logit contributions
burn+0.018
 blowing+0.016
 waving+0.016
 spinning+0.014
 neighborhood+0.013
Neg logit contributions
 ounces-0.030
ils-0.027
izards-0.027
affe-0.027
bors-0.027
Token very
Token ID845
Feature activation+1.38e+00

Pos logit contributions
burn+0.030
 driveway+0.026
 neighborhood+0.025
 blowing+0.025
seat+0.024
Neg logit contributions
 ounces-0.030
izards-0.029
ily-0.028
affe-0.027
isy-0.026
Token happy
Token ID3772
Feature activation-5.28e-01

Pos logit contributions
 ounces+0.045
izards+0.041
ils+0.040
affe+0.040
bors+0.040
Neg logit contributions
burn-0.033
 blowing-0.030
 waving-0.029
 driveway-0.026
 neighborhood-0.026
Token living
Token ID2877
Feature activation-6.30e+00

Pos logit contributions
burn+0.014
 blowing+0.012
 waving+0.012
 driveway+0.012
 neighborhood+0.011
Neg logit contributions
 ounces-0.014
izards-0.014
ils-0.013
affe-0.013
hell-0.013
Token on
Token ID319
Feature activation-1.06e+00

Pos logit contributions
burn+0.132
 blowing+0.117
 waving+0.116
 spinning+0.099
 neighborhood+0.098
Neg logit contributions
 ounces-0.229
ils-0.208
izards-0.206
affe-0.206
bors-0.205
Token the
Token ID262
Feature activation+3.30e-01

Pos logit contributions
burn+0.024
 blowing+0.022
 waving+0.022
 spinning+0.019
 daddy+0.019
Neg logit contributions
 ounces-0.036
ils-0.033
izards-0.032
affe-0.032
bors-0.032
Token farm
Token ID5318
Feature activation+1.41e+00

Pos logit contributions
 ounces+0.010
affe+0.009
isy+0.009
ils+0.009
bors+0.009
Neg logit contributions
burn-0.008
 waving-0.007
 blowing-0.007
 crying-0.006
seat-0.006
Token with
Token ID351
Feature activation+1.51e+00

Pos logit contributions
 ounces+0.050
bors+0.045
izards+0.045
affe+0.045
ils+0.045
Neg logit contributions
burn-0.031
 blowing-0.028
 waving-0.028
 spinning-0.024
 neighborhood-0.024
Token his
Token ID465
Feature activation+2.18e-01

Pos logit contributions
 ounces+0.057
izards+0.053
ils+0.053
affe+0.052
bors+0.052
Neg logit contributions
burn-0.029
 waving-0.026
 blowing-0.025
 daddy-0.024
 spinning-0.022
Token house
Token ID2156
Feature activation+1.80e-01

Pos logit contributions
affe+0.009
bors+0.008
 ounces+0.008
ils+0.008
nic+0.008
Neg logit contributions
burn-0.013
 blowing-0.011
bie-0.011
 waving-0.011
 asleep-0.010
Token,
Token ID11
Feature activation-4.36e-01

Pos logit contributions
 ounces+0.006
ils+0.005
izards+0.005
affe+0.005
hell+0.005
Neg logit contributions
burn-0.004
 blowing-0.003
 waving-0.003
 daddy-0.003
 neighborhood-0.003
Token when
Token ID618
Feature activation-1.69e+00

Pos logit contributions
burn+0.013
 blowing+0.010
eddy+0.010
 neighborhood+0.010
 driveway+0.010
Neg logit contributions
 ounces-0.011
izards-0.010
bors-0.010
isy-0.009
ils-0.009
Token her
Token ID607
Feature activation-4.44e-01

Pos logit contributions
burn+0.052
 blowing+0.046
 waving+0.044
 driveway+0.042
 neighborhood+0.040
Neg logit contributions
 ounces-0.042
izards-0.037
bors-0.037
ils-0.036
ily-0.035
Token mom
Token ID1995
Feature activation-3.27e+00

Pos logit contributions
burn+0.009
 blowing+0.008
 waving+0.008
my+0.008
ric+0.008
Neg logit contributions
 ounces-0.014
affe-0.014
isy-0.013
ils-0.013
izards-0.012
Token stopped
Token ID5025
Feature activation-6.28e+00

Pos logit contributions
burn+0.073
 blowing+0.065
 waving+0.063
 spinning+0.055
 driveway+0.055
Neg logit contributions
 ounces-0.109
ils-0.102
affe-0.099
izards-0.099
bors-0.098
Token her
Token ID607
Feature activation-1.19e+00

Pos logit contributions
burn+0.165
 driveway+0.141
icycle+0.127
 neighborhood+0.124
 waving+0.123
Neg logit contributions
 ounces-0.165
izards-0.158
bors-0.158
ocol-0.154
ils-0.149
Token.
Token ID13
Feature activation+2.76e-01

Pos logit contributions
burn+0.028
 blowing+0.023
 sch+0.022
Look+0.022
 neighborhood+0.022
Neg logit contributions
isy-0.033
affe-0.033
 ounces-0.032
ils-0.030
hell-0.030
Token Her
Token ID2332
Feature activation-1.29e+00

Pos logit contributions
 ounces+0.009
ils+0.008
affe+0.008
izards+0.008
bors+0.008
Neg logit contributions
burn-0.007
 blowing-0.006
 waving-0.006
 spinning-0.005
 neighborhood-0.005
Token mother
Token ID2802
Feature activation-3.11e+00

Pos logit contributions
burn+0.033
 blowing+0.031
ric+0.030
 waving+0.027
ained+0.026
Neg logit contributions
 ounces-0.033
ily-0.033
isy-0.032
affe-0.032
hell-0.030
Token was
Token ID373
Feature activation-1.44e+00

Pos logit contributions
burn+0.070
 blowing+0.062
 waving+0.061
 driveway+0.053
 spinning+0.053
Neg logit contributions
 ounces-0.107
ils-0.098
affe-0.097
bors-0.096
izards-0.096
Tokenactus
Token ID34144
Feature activation+2.14e+00

Pos logit contributions
 ounces+0.077
bors+0.069
izards+0.067
ils+0.067
affe+0.064
Neg logit contributions
burn-0.056
 blowing-0.047
 waving-0.045
 neighborhood-0.043
 window-0.043
Token.
Token ID13
Feature activation-8.37e-01

Pos logit contributions
 ounces+0.089
bors+0.081
izards+0.076
ils+0.075
affe+0.075
Neg logit contributions
burn-0.042
 blowing-0.031
 waving-0.030
my-0.029
 window-0.029
Token It
Token ID632
Feature activation-1.39e-01

Pos logit contributions
burn+0.021
 waving+0.019
 blowing+0.018
 daddy+0.018
my+0.017
Neg logit contributions
 ounces-0.026
ils-0.026
hell-0.024
izards-0.024
bors-0.023
Token's
Token ID338
Feature activation-6.20e-01

Pos logit contributions
burn+0.003
 blowing+0.003
 waving+0.003
my+0.002
 crying+0.002
Neg logit contributions
 ounces-0.005
izards-0.005
bors-0.004
affe-0.004
ils-0.004
Token happy
Token ID3772
Feature activation-9.34e-01

Pos logit contributions
burn+0.013
 blowing+0.012
 waving+0.012
 spinning+0.010
 crying+0.010
Neg logit contributions
 ounces-0.022
affe-0.020
ils-0.020
izards-0.020
bors-0.020
Token living
Token ID2877
Feature activation-6.26e+00

Pos logit contributions
burn+0.020
 blowing+0.018
 waving+0.018
 daddy+0.015
 spinning+0.015
Neg logit contributions
 ounces-0.034
ils-0.031
izards-0.031
bors-0.031
affe-0.031
Token in
Token ID287
Feature activation-2.87e+00

Pos logit contributions
burn+0.137
 blowing+0.124
 waving+0.123
 spinning+0.107
 crying+0.106
Neg logit contributions
 ounces-0.222
affe-0.202
izards-0.198
bors-0.198
ils-0.198
Token the
Token ID262
Feature activation-3.26e-02

Pos logit contributions
burn+0.069
 blowing+0.062
 waving+0.062
 spinning+0.054
 neighborhood+0.054
Neg logit contributions
 ounces-0.095
ils-0.086
izards-0.085
affe-0.085
bors-0.085
Token desert
Token ID10326
Feature activation+1.83e+00

Pos logit contributions
burn+0.001
 blowing+0.001
 waving+0.001
 spinning+0.000
 daddy+0.000
Neg logit contributions
 ounces-0.001
ils-0.001
affe-0.001
izards-0.001
bors-0.001
Token where
Token ID810
Feature activation-1.35e+00

Pos logit contributions
 ounces+0.067
affe+0.061
bors+0.061
izards+0.061
ils+0.059
Neg logit contributions
burn-0.037
 blowing-0.034
 waving-0.033
 window-0.029
my-0.029
Token it
Token ID340
Feature activation+1.87e+00

Pos logit contributions
burn+0.033
 blowing+0.032
 waving+0.031
 daddy+0.030
 crying+0.029
Neg logit contributions
 ounces-0.043
affe-0.040
hell-0.038
ils-0.037
isy-0.037
Token Lily
Token ID20037
Feature activation-5.43e-01

Pos logit contributions
 ounces+0.038
ils+0.037
izards+0.037
keys+0.036
bors+0.035
Neg logit contributions
 crying-0.012
 asleep-0.011
 bathroom-0.011
 window-0.011
 daddy-0.011
Token was
Token ID373
Feature activation-1.21e+00

Pos logit contributions
burn+0.009
 blowing+0.008
 waving+0.008
 spinning+0.006
 crying+0.006
Neg logit contributions
 ounces-0.022
izards-0.020
ils-0.020
affe-0.020
bors-0.020
Token sad
Token ID6507
Feature activation-4.98e-01

Pos logit contributions
burn+0.031
 blowing+0.026
 driveway+0.026
 waving+0.025
 neighborhood+0.025
Neg logit contributions
 ounces-0.036
izards-0.033
bors-0.032
ils-0.032
hell-0.032
Token because
Token ID780
Feature activation-1.23e+00

Pos logit contributions
burn+0.015
 waving+0.013
 driveway+0.013
 blowing+0.013
 neighborhood+0.012
Neg logit contributions
 ounces-0.013
izards-0.012
affe-0.012
hell-0.011
ily-0.011
Token her
Token ID607
Feature activation-2.63e+00

Pos logit contributions
burn+0.033
 blowing+0.030
 waving+0.029
 spinning+0.026
 neighborhood+0.026
Neg logit contributions
 ounces-0.038
ils-0.034
izards-0.033
affe-0.033
bors-0.033
Token snow
Token ID6729
Feature activation-6.19e+00

Pos logit contributions
burn+0.065
 blowing+0.057
 waving+0.055
 typing+0.053
itating+0.052
Neg logit contributions
 ounces-0.077
affe-0.070
isy-0.068
hell-0.067
izards-0.067
Tokenman
Token ID805
Feature activation-2.84e+00

Pos logit contributions
burn+0.128
 waving+0.120
 blowing+0.115
 neighborhood+0.103
 typing+0.103
Neg logit contributions
 ounces-0.210
affe-0.195
ils-0.193
hell-0.193
isy-0.188
Token was
Token ID373
Feature activation-1.85e+00

Pos logit contributions
burn+0.048
 blowing+0.043
 waving+0.042
 spinning+0.035
 crying+0.035
Neg logit contributions
 ounces-0.113
izards-0.105
ils-0.103
bors-0.103
affe-0.103
Token disappearing
Token ID28867
Feature activation-3.97e-01

Pos logit contributions
burn+0.039
 waving+0.033
 neighborhood+0.032
 driveway+0.032
 blowing+0.032
Neg logit contributions
 ounces-0.062
ils-0.056
izards-0.055
hell-0.055
bors-0.055
Token.
Token ID13
Feature activation+2.85e-03

Pos logit contributions
burn+0.010
 waving+0.009
 blowing+0.009
 driveway+0.009
 neighborhood+0.008
Neg logit contributions
 ounces-0.012
ils-0.011
izards-0.011
hell-0.011
affe-0.010
Token She
Token ID1375
Feature activation+7.07e-01

Pos logit contributions
 ounces+0.000
ils+0.000
izards+0.000
bors+0.000
affe+0.000
Neg logit contributions
burn-0.000
 waving-0.000
 blowing-0.000
 crying-0.000
 neighborhood-0.000
Token.
Token ID13
Feature activation+7.83e-01

Pos logit contributions
 ounces+0.003
ils+0.002
hell+0.002
affe+0.002
izards+0.002
Neg logit contributions
burn-0.003
 blowing-0.003
 waving-0.003
 driveway-0.003
 spinning-0.002
Token Jack
Token ID3619
Feature activation-1.29e+00

Pos logit contributions
 ounces+0.023
izards+0.020
affe+0.020
ils+0.020
hell+0.020
Neg logit contributions
burn-0.022
 blowing-0.020
 waving-0.020
 spinning-0.018
 crying-0.018
Token was
Token ID373
Feature activation-1.05e+00

Pos logit contributions
burn+0.034
 blowing+0.028
 waving+0.028
 driveway+0.025
 window+0.025
Neg logit contributions
 ounces-0.039
ils-0.038
hell-0.036
affe-0.036
bors-0.036
Token very
Token ID845
Feature activation+1.42e+00

Pos logit contributions
burn+0.029
 driveway+0.026
 blowing+0.024
 neighborhood+0.024
seat+0.024
Neg logit contributions
 ounces-0.026
izards-0.026
ily-0.026
isy-0.024
ns-0.023
Token happy
Token ID3772
Feature activation-3.22e-01

Pos logit contributions
 ounces+0.046
izards+0.041
affe+0.040
ils+0.040
bors+0.040
Neg logit contributions
burn-0.036
 blowing-0.031
 waving-0.031
 driveway-0.028
 neighborhood-0.027
Token living
Token ID2877
Feature activation-6.14e+00

Pos logit contributions
burn+0.010
 driveway+0.008
 blowing+0.008
 waving+0.008
 salon+0.008
Neg logit contributions
 ounces-0.007
izards-0.007
affe-0.007
ils-0.007
hell-0.007
Token in
Token ID287
Feature activation-2.49e+00

Pos logit contributions
burn+0.142
 blowing+0.125
 waving+0.124
 driveway+0.108
 spinning+0.106
Neg logit contributions
 ounces-0.210
ils-0.194
izards-0.191
hell-0.185
bors-0.185
Token the
Token ID262
Feature activation+8.13e-01

Pos logit contributions
burn+0.072
 blowing+0.063
 waving+0.060
 neighborhood+0.058
 driveway+0.057
Neg logit contributions
 ounces-0.071
izards-0.061
bors-0.061
ils-0.061
hell-0.059
Token woods
Token ID16479
Feature activation-7.32e-01

Pos logit contributions
 ounces+0.023
affe+0.021
ils+0.020
bors+0.020
isy+0.020
Neg logit contributions
burn-0.021
 blowing-0.019
 waving-0.018
 typing-0.017
 vac-0.016
Token.
Token ID13
Feature activation+4.64e-01

Pos logit contributions
burn+0.019
 blowing+0.016
 waving+0.016
 daddy+0.015
 driveway+0.015
Neg logit contributions
 ounces-0.023
ils-0.021
izards-0.020
hell-0.020
affe-0.020
Token Every
Token ID3887
Feature activation-2.21e+00

Pos logit contributions
 ounces+0.012
affe+0.011
izards+0.011
hell+0.010
bors+0.010
Neg logit contributions
burn-0.015
 blowing-0.013
 waving-0.013
 spinning-0.012
 crying-0.011
Token Snow
Token ID7967
Feature activation-2.27e+00

Pos logit contributions
burn+0.019
 blowing+0.017
 waving+0.017
 neighborhood+0.015
 driveway+0.015
Neg logit contributions
 ounces-0.021
ils-0.019
izards-0.018
bors-0.018
affe-0.018
Tokeny
Token ID88
Feature activation-3.16e-01

Pos logit contributions
burn+0.036
 waving+0.032
 blowing+0.032
 driveway+0.027
 spinning+0.026
Neg logit contributions
 ounces-0.090
affe-0.085
ils-0.084
izards-0.084
hell-0.083
Token.
Token ID13
Feature activation-1.40e+00

Pos logit contributions
burn+0.008
 blowing+0.007
 waving+0.007
 spinning+0.006
 crying+0.006
Neg logit contributions
 ounces-0.010
izards-0.009
ils-0.009
bors-0.009
affe-0.009
Token And
Token ID843
Feature activation+9.21e-01

Pos logit contributions
burn+0.041
 blowing+0.037
 waving+0.037
 daddy+0.034
 crying+0.033
Neg logit contributions
 ounces-0.039
ils-0.036
bors-0.035
izards-0.035
affe-0.034
Token the
Token ID262
Feature activation-2.44e+00

Pos logit contributions
 ounces+0.026
ils+0.024
affe+0.024
bors+0.023
izards+0.023
Neg logit contributions
burn-0.026
 waving-0.024
 blowing-0.024
 daddy-0.023
 spinning-0.022
Token living
Token ID2877
Feature activation-6.11e+00

Pos logit contributions
burn+0.057
 blowing+0.051
 waving+0.049
 neighborhood+0.043
 leaning+0.043
Neg logit contributions
 ounces-0.079
affe-0.071
hell-0.070
bors-0.069
ils-0.069
Token room
Token ID2119
Feature activation-1.57e+00

Pos logit contributions
burn+0.111
 blowing+0.099
 waving+0.098
 leaning+0.082
 driveway+0.080
Neg logit contributions
 ounces-0.230
ils-0.221
bors-0.206
izards-0.206
hell-0.203
Token.
Token ID13
Feature activation-1.12e+00

Pos logit contributions
burn+0.030
 blowing+0.027
 waving+0.026
 spinning+0.022
 crying+0.022
Neg logit contributions
 ounces-0.059
ils-0.054
izards-0.054
affe-0.054
bors-0.053
Token Mom
Token ID11254
Feature activation-4.99e+00

Pos logit contributions
burn+0.033
 waving+0.030
 blowing+0.030
 daddy+0.027
 spinning+0.027
Neg logit contributions
 ounces-0.031
ils-0.028
bors-0.028
izards-0.028
affe-0.027
Token will
Token ID481
Feature activation-8.89e-01

Pos logit contributions
burn+0.100
 waving+0.088
 blowing+0.087
 driveway+0.080
 neighborhood+0.080
Neg logit contributions
 ounces-0.174
ils-0.165
affe-0.157
bors-0.156
hell-0.156
Token be
Token ID307
Feature activation+6.55e-01

Pos logit contributions
burn+0.022
 blowing+0.020
 waving+0.019
 neighborhood+0.018
 leaning+0.017
Neg logit contributions
 ounces-0.027
bors-0.024
hell-0.024
ils-0.024
isy-0.024
TokenThe
Token ID464
Feature activation-1.42e+00

Pos logit contributions
 ounces+0.029
izards+0.026
ils+0.026
affe+0.026
bors+0.025
Neg logit contributions
burn-0.021
 blowing-0.019
 waving-0.018
 spinning-0.017
 neighborhood-0.017
Token dolls
Token ID36062
Feature activation-1.10e+00

Pos logit contributions
burn+0.031
 blowing+0.027
 waving+0.027
 leaning+0.022
 spinning+0.022
Neg logit contributions
 ounces-0.050
ils-0.046
bors-0.045
izards-0.045
affe-0.045
Token were
Token ID547
Feature activation-8.20e-01

Pos logit contributions
burn+0.024
 blowing+0.021
 waving+0.021
 spinning+0.018
 neighborhood+0.018
Neg logit contributions
 ounces-0.039
ils-0.036
izards-0.035
affe-0.035
bors-0.035
Token very
Token ID845
Feature activation+1.35e+00

Pos logit contributions
burn+0.023
 blowing+0.020
 waving+0.020
 driveway+0.019
 neighborhood+0.019
Neg logit contributions
 ounces-0.023
ils-0.021
izards-0.020
bors-0.020
hell-0.020
Token happy
Token ID3772
Feature activation-5.79e-01

Pos logit contributions
 ounces+0.042
ils+0.038
izards+0.037
bors+0.037
hell+0.037
Neg logit contributions
burn-0.036
 blowing-0.030
 waving-0.030
 driveway-0.028
 neighborhood-0.027
Token living
Token ID2877
Feature activation-6.10e+00

Pos logit contributions
burn+0.013
 blowing+0.010
 waving+0.010
 driveway+0.010
 neighborhood+0.009
Neg logit contributions
 ounces-0.020
ils-0.019
izards-0.019
affe-0.018
hell-0.018
Token in
Token ID287
Feature activation-2.91e+00

Pos logit contributions
burn+0.130
 blowing+0.115
 waving+0.114
 spinning+0.098
 neighborhood+0.097
Neg logit contributions
 ounces-0.220
ils-0.200
izards-0.198
affe-0.198
bors-0.197
Token their
Token ID511
Feature activation+1.11e+00

Pos logit contributions
burn+0.080
 blowing+0.064
 waving+0.060
 driveway+0.060
icycle+0.059
Neg logit contributions
 ounces-0.084
ils-0.081
bors-0.077
ily-0.076
izards-0.074
Token new
Token ID649
Feature activation-1.49e+00

Pos logit contributions
 ounces+0.039
ils+0.038
bors+0.035
hell+0.035
affe+0.034
Neg logit contributions
burn-0.024
 blowing-0.021
 waving-0.019
 leaning-0.016
 spinning-0.015
Token house
Token ID2156
Feature activation-1.27e+00

Pos logit contributions
burn+0.027
 blowing+0.024
 waving+0.022
 leaning+0.018
 spinning+0.017
Neg logit contributions
 ounces-0.057
ils-0.054
bors-0.052
affe-0.051
hell-0.051
Token.
Token ID13
Feature activation-1.00e-01

Pos logit contributions
burn+0.027
 blowing+0.023
 waving+0.023
 spinning+0.020
 driveway+0.020
Neg logit contributions
 ounces-0.045
ils-0.041
affe-0.040
izards-0.040
hell-0.040
Token she
Token ID673
Feature activation+4.67e-01

Pos logit contributions
burn+0.046
 blowing+0.041
 waving+0.040
 driveway+0.037
 neighborhood+0.037
Neg logit contributions
 ounces-0.048
affe-0.042
izards-0.042
bors-0.042
ils-0.042
Token was
Token ID373
Feature activation-1.11e+00

Pos logit contributions
 ounces+0.017
izards+0.015
affe+0.015
ils+0.015
hell+0.015
Neg logit contributions
burn-0.010
 waving-0.009
 blowing-0.009
 spinning-0.008
 daddy-0.008
Token glad
Token ID9675
Feature activation-1.06e+00

Pos logit contributions
burn+0.028
 blowing+0.025
 waving+0.025
 spinning+0.022
 daddy+0.022
Neg logit contributions
 ounces-0.035
ils-0.032
affe-0.032
izards-0.031
bors-0.031
Token she
Token ID673
Feature activation+6.56e-02

Pos logit contributions
burn+0.025
 blowing+0.022
 waving+0.022
 spinning+0.019
 daddy+0.019
Neg logit contributions
 ounces-0.036
ils-0.033
affe-0.032
izards-0.032
bors-0.032
Token was
Token ID373
Feature activation-1.33e+00

Pos logit contributions
 ounces+0.003
affe+0.002
izards+0.002
hell+0.002
bors+0.002
Neg logit contributions
burn-0.001
 waving-0.001
 blowing-0.001
 spinning-0.001
my-0.001
Token living
Token ID2877
Feature activation-6.09e+00

Pos logit contributions
burn+0.034
 waving+0.032
 blowing+0.032
 spinning+0.029
 crying+0.028
Neg logit contributions
 ounces-0.044
affe-0.040
ils-0.039
hell-0.039
izards-0.039
Token in
Token ID287
Feature activation-1.70e+00

Pos logit contributions
burn+0.126
 blowing+0.112
 waving+0.112
 spinning+0.096
 neighborhood+0.095
Neg logit contributions
 ounces-0.222
affe-0.202
ils-0.202
izards-0.201
bors-0.200
Token such
Token ID884
Feature activation+2.01e+00

Pos logit contributions
burn+0.044
 blowing+0.038
 waving+0.036
 driveway+0.034
 neighborhood+0.033
Neg logit contributions
 ounces-0.053
ils-0.048
izards-0.047
bors-0.046
hell-0.046
Token a
Token ID257
Feature activation-9.09e-01

Pos logit contributions
 ounces+0.076
affe+0.070
ils+0.069
izards+0.069
bors+0.068
Neg logit contributions
burn-0.037
 waving-0.035
 blowing-0.034
 spinning-0.030
 daddy-0.030
Token tidy
Token ID43044
Feature activation-1.98e+00

Pos logit contributions
burn+0.024
 blowing+0.022
 waving+0.021
 leaning+0.019
 driveway+0.019
Neg logit contributions
 ounces-0.027
bors-0.024
hell-0.024
affe-0.024
ils-0.024
Token home
Token ID1363
Feature activation+2.12e-01

Pos logit contributions
burn+0.041
 blowing+0.035
 waving+0.033
 leaning+0.028
 spinning+0.028
Neg logit contributions
 ounces-0.070
affe-0.064
bors-0.063
hell-0.063
ils-0.063
Token box
Token ID3091
Feature activation+1.22e+00

Pos logit contributions
bors+0.009
 ounces+0.009
izards+0.009
ils+0.009
affe+0.009
Neg logit contributions
 waving-0.007
 blowing-0.007
burn-0.007
 window-0.007
 spinning-0.007
Token in
Token ID287
Feature activation-5.34e-01

Pos logit contributions
 ounces+0.045
ils+0.041
izards+0.041
affe+0.041
bors+0.041
Neg logit contributions
burn-0.024
 blowing-0.022
 waving-0.021
 spinning-0.018
 neighborhood-0.018
Token,
Token ID11
Feature activation-3.66e-01

Pos logit contributions
burn+0.013
 blowing+0.011
 waving+0.011
 driveway+0.010
 neighborhood+0.010
Neg logit contributions
 ounces-0.017
ils-0.015
bors-0.015
hell-0.015
izards-0.015
Token when
Token ID618
Feature activation-1.91e+00

Pos logit contributions
burn+0.008
 blowing+0.007
 waving+0.007
 neighborhood+0.006
 daddy+0.006
Neg logit contributions
 ounces-0.013
ils-0.011
bors-0.011
izards-0.011
affe-0.011
Token Mama
Token ID40084
Feature activation-2.09e+00

Pos logit contributions
burn+0.048
 waving+0.042
 blowing+0.042
 driveway+0.038
 neighborhood+0.038
Neg logit contributions
 ounces-0.059
bors-0.052
izards-0.052
ils-0.051
affe-0.049
Token stopped
Token ID5025
Feature activation-6.08e+00

Pos logit contributions
burn+0.045
 blowing+0.041
 waving+0.041
 daddy+0.035
 spinning+0.035
Neg logit contributions
 ounces-0.075
ils-0.067
izards-0.067
affe-0.067
hell-0.066
Token.
Token ID13
Feature activation+1.19e-01

Pos logit contributions
burn+0.150
 waving+0.119
 driveway+0.116
 blowing+0.116
 neighborhood+0.110
Neg logit contributions
 ounces-0.195
izards-0.177
bors-0.174
ils-0.174
affe-0.165
Token �
Token ID6184
Feature activation+2.96e+00

Pos logit contributions
 ounces+0.004
ils+0.004
izards+0.004
affe+0.004
bors+0.004
Neg logit contributions
burn-0.002
 blowing-0.002
 waving-0.002
 spinning-0.002
 daddy-0.002
Token�
Token ID95
Feature activation+1.91e+00

Pos logit contributions
 ounces+0.087
izards+0.080
affe+0.079
hell+0.078
ils+0.078
Neg logit contributions
burn-0.080
 blowing-0.074
 waving-0.072
 leaning-0.068
 spinning-0.067
Token€
Token ID26391
Feature activation+2.43e+00

Pos logit contributions
izards+0.054
 ounces+0.054
affe+0.050
ils+0.050
 mushrooms+0.050
Neg logit contributions
burn-0.049
 waving-0.046
 blowing-0.045
 neighborhood-0.045
 driveway-0.044
Token�
Token ID129
Feature activation+1.43e+00

Pos logit contributions
 ounces+0.077
ils+0.069
izards+0.068
affe+0.067
bors+0.067
Neg logit contributions
burn-0.062
 waving-0.056
 blowing-0.056
 neighborhood-0.052
 driveway-0.050
Token you
Token ID345
Feature activation+2.76e+00

Pos logit contributions
burn+0.012
 blowing+0.011
 waving+0.011
 crying+0.011
 daddy+0.010
Neg logit contributions
 ounces-0.014
ils-0.013
affe-0.013
hell-0.012
izards-0.012
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
 ounces+0.096
ils+0.087
bors+0.086
izards+0.084
affe+0.082
Neg logit contributions
burn-0.065
 blowing-0.059
 waving-0.059
 crying-0.054
my-0.054
Token You
Token ID921
Feature activation+2.06e+00

Pos logit contributions
burn+0.031
 waving+0.028
 blowing+0.028
 daddy+0.026
 spinning+0.025
Neg logit contributions
 ounces-0.042
ils-0.039
hell-0.038
izards-0.037
bors-0.037
Token are
Token ID389
Feature activation-1.05e+00

Pos logit contributions
 ounces+0.072
bors+0.064
izards+0.062
ils+0.062
affe+0.062
Neg logit contributions
burn-0.046
 blowing-0.042
 waving-0.041
my-0.038
 daddy-0.037
Token a
Token ID257
Feature activation-3.20e+00

Pos logit contributions
burn+0.022
 waving+0.021
 blowing+0.021
 spinning+0.018
 crying+0.018
Neg logit contributions
 ounces-0.038
affe-0.034
bors-0.034
ils-0.034
hell-0.034
Token living
Token ID2877
Feature activation-6.08e+00

Pos logit contributions
burn+0.093
 blowing+0.086
 waving+0.083
 driveway+0.077
my+0.075
Neg logit contributions
 ounces-0.090
affe-0.079
ils-0.078
bors-0.076
hell-0.076
Token thing
Token ID1517
Feature activation+8.57e-02

Pos logit contributions
burn+0.144
 blowing+0.130
 waving+0.126
 driveway+0.111
 leaning+0.108
Neg logit contributions
 ounces-0.204
ils-0.187
izards-0.182
affe-0.180
bors-0.179
Token.
Token ID13
Feature activation-1.66e+00

Pos logit contributions
 ounces+0.003
bors+0.003
ils+0.003
hell+0.003
izards+0.003
Neg logit contributions
burn-0.002
 waving-0.001
 blowing-0.001
 crying-0.001
 spinning-0.001
Token You
Token ID921
Feature activation+2.05e+00

Pos logit contributions
burn+0.043
 waving+0.039
 blowing+0.039
 daddy+0.035
 spinning+0.035
Neg logit contributions
 ounces-0.051
ils-0.047
hell-0.046
izards-0.045
bors-0.045
Token have
Token ID423
Feature activation-1.15e+00

Pos logit contributions
 ounces+0.072
bors+0.064
izards+0.062
affe+0.062
ils+0.061
Neg logit contributions
burn-0.045
 blowing-0.041
 waving-0.040
my-0.038
 daddy-0.037
Token feelings
Token ID7666
Feature activation+5.54e-01

Pos logit contributions
burn+0.024
 blowing+0.021
 waving+0.020
 driveway+0.018
 spinning+0.017
Neg logit contributions
 ounces-0.042
ils-0.039
izards-0.038
affe-0.038
bors-0.038
Token.
Token ID13
Feature activation+6.67e-02

Pos logit contributions
 ounces+0.077
bors+0.069
affe+0.069
ils+0.068
izards+0.068
Neg logit contributions
burn-0.042
 blowing-0.041
 waving-0.041
 spinning-0.035
 crying-0.034
Token Max
Token ID5436
Feature activation-1.28e+00

Pos logit contributions
 ounces+0.002
ils+0.002
izards+0.002
affe+0.002
bors+0.002
Neg logit contributions
burn-0.001
 blowing-0.001
 waving-0.001
 spinning-0.001
 neighborhood-0.001
Token and
Token ID290
Feature activation-1.84e+00

Pos logit contributions
burn+0.023
 waving+0.022
 blowing+0.022
 neighborhood+0.019
 daddy+0.019
Neg logit contributions
 ounces-0.048
izards-0.044
ils-0.044
hell-0.043
affe-0.043
Token M
Token ID337
Feature activation-1.25e+00

Pos logit contributions
burn+0.041
 blowing+0.038
 waving+0.038
 daddy+0.035
 spinning+0.033
Neg logit contributions
 ounces-0.064
affe-0.059
ils-0.058
izards-0.057
hell-0.057
Tokenilly
Token ID6548
Feature activation-8.87e-01

Pos logit contributions
burn+0.043
 blowing+0.040
 waving+0.040
 driveway+0.037
 spinning+0.037
Neg logit contributions
 ounces-0.028
ils-0.024
izards-0.024
affe-0.024
bors-0.024
Token stopped
Token ID5025
Feature activation-6.08e+00

Pos logit contributions
burn+0.015
 waving+0.015
 blowing+0.014
 daddy+0.012
my+0.012
Neg logit contributions
 ounces-0.035
bors-0.031
izards-0.031
affe-0.031
hell-0.031
Token to
Token ID284
Feature activation-4.76e-01

Pos logit contributions
burn+0.145
 driveway+0.126
icycle+0.113
 salon+0.110
 waving+0.109
Neg logit contributions
izards-0.181
 ounces-0.180
 mushrooms-0.178
ils-0.177
bors-0.172
Token discuss
Token ID2112
Feature activation+9.67e-01

Pos logit contributions
burn+0.009
 waving+0.008
 blowing+0.008
 spinning+0.007
 daddy+0.006
Neg logit contributions
 ounces-0.018
ils-0.017
izards-0.017
affe-0.017
bors-0.016
Token the
Token ID262
Feature activation-3.80e-01

Pos logit contributions
 ounces+0.036
affe+0.033
bors+0.032
izards+0.031
ils+0.031
Neg logit contributions
burn-0.020
 waving-0.019
 blowing-0.019
 crying-0.016
 spinning-0.016
Token berries
Token ID36322
Feature activation+4.49e-01

Pos logit contributions
burn+0.011
 waving+0.011
 blowing+0.011
my+0.011
 neighborhood+0.010
Neg logit contributions
 ounces-0.010
affe-0.009
izards-0.009
bors-0.008
ils-0.008
Token,
Token ID11
Feature activation-6.73e-01

Pos logit contributions
 ounces+0.018
bors+0.016
affe+0.016
ils+0.015
izards+0.015
Neg logit contributions
 blowing-0.008
burn-0.008
 waving-0.008
 crying-0.006
my-0.006
Token you
Token ID345
Feature activation+2.97e+00

Pos logit contributions
burn+0.026
 blowing+0.023
 waving+0.023
 driveway+0.023
 neighborhood+0.022
Neg logit contributions
 ounces-0.021
affe-0.019
izards-0.019
ils-0.019
bors-0.018
Token glad
Token ID9675
Feature activation-1.14e-01

Pos logit contributions
 ounces+0.098
affe+0.089
ils+0.089
bors+0.089
izards+0.089
Neg logit contributions
burn-0.068
 blowing-0.061
 waving-0.060
 driveway-0.054
 neighborhood-0.052
Token that
Token ID326
Feature activation-3.34e+00

Pos logit contributions
burn+0.003
 blowing+0.003
 waving+0.003
 driveway+0.003
 spinning+0.003
Neg logit contributions
 ounces-0.003
ils-0.003
izards-0.003
affe-0.003
bors-0.003
Token you
Token ID345
Feature activation+1.03e+00

Pos logit contributions
burn+0.092
 blowing+0.083
 waving+0.083
 driveway+0.077
 neighborhood+0.075
Neg logit contributions
 ounces-0.095
affe-0.086
ils-0.085
bors-0.085
izards-0.084
Token are
Token ID389
Feature activation-8.50e-01

Pos logit contributions
 ounces+0.036
ils+0.033
izards+0.033
affe+0.033
bors+0.033
Neg logit contributions
burn-0.022
 blowing-0.020
 waving-0.019
 spinning-0.017
 neighborhood-0.017
Token living
Token ID2877
Feature activation-6.06e+00

Pos logit contributions
burn+0.019
 blowing+0.016
 waving+0.016
 driveway+0.014
 neighborhood+0.014
Neg logit contributions
 ounces-0.029
ils-0.027
izards-0.027
bors-0.027
affe-0.026
Token in
Token ID287
Feature activation-3.41e+00

Pos logit contributions
burn+0.152
 blowing+0.135
 waving+0.132
 driveway+0.120
 leaning+0.115
Neg logit contributions
 ounces-0.194
ils-0.182
izards-0.175
bors-0.170
hell-0.170
Token the
Token ID262
Feature activation-7.21e-01

Pos logit contributions
burn+0.091
 blowing+0.078
 waving+0.076
 driveway+0.072
 leaning+0.068
Neg logit contributions
 ounces-0.101
ils-0.091
izards-0.088
bors-0.088
hell-0.086
Token forest
Token ID8222
Feature activation-4.64e-01

Pos logit contributions
burn+0.016
 blowing+0.014
 waving+0.014
 spinning+0.011
 daddy+0.011
Neg logit contributions
 ounces-0.025
ils-0.023
affe-0.022
hell-0.022
bors-0.022
Token?"
Token ID1701
Feature activation+6.50e-02

Pos logit contributions
burn+0.010
 blowing+0.010
 waving+0.009
 neighborhood+0.008
my+0.008
Neg logit contributions
 ounces-0.016
izards-0.015
affe-0.014
ils-0.014
bors-0.014
Token
Token ID220
Feature activation-2.72e-01

Pos logit contributions
 ounces+0.003
ils+0.003
izards+0.003
bors+0.003
hell+0.003
Neg logit contributions
burn-0.001
 waving-0.001
 blowing-0.001
 daddy-0.001
 crying-0.001
Token and
Token ID290
Feature activation-6.24e-01

Pos logit contributions
burn+0.033
 blowing+0.027
 waving+0.027
 driveway+0.026
rolling+0.024
Neg logit contributions
 ounces-0.039
hell-0.036
ils-0.036
izards-0.036
affe-0.035
Token sad
Token ID6507
Feature activation+3.46e-01

Pos logit contributions
burn+0.013
 blowing+0.012
 waving+0.012
 crying+0.010
 spinning+0.010
Neg logit contributions
 ounces-0.022
affe-0.020
ils-0.020
izards-0.020
bors-0.020
Token because
Token ID780
Feature activation-1.02e+00

Pos logit contributions
 ounces+0.011
ils+0.010
izards+0.010
affe+0.010
bors+0.010
Neg logit contributions
burn-0.009
 blowing-0.008
 waving-0.008
 spinning-0.007
 neighborhood-0.007
Token she
Token ID673
Feature activation-6.61e-01

Pos logit contributions
burn+0.030
 blowing+0.026
 waving+0.025
 driveway+0.024
 neighborhood+0.023
Neg logit contributions
 ounces-0.029
izards-0.026
ils-0.025
bors-0.025
hell-0.025
Token was
Token ID373
Feature activation-1.64e+00

Pos logit contributions
burn+0.013
 blowing+0.012
 waving+0.011
 spinning+0.010
 driveway+0.010
Neg logit contributions
 ounces-0.025
ils-0.022
izards-0.022
affe-0.022
bors-0.022
Token living
Token ID2877
Feature activation-6.06e+00

Pos logit contributions
burn+0.037
 blowing+0.032
 waving+0.031
 driveway+0.029
 neighborhood+0.028
Neg logit contributions
 ounces-0.055
ils-0.051
izards-0.051
bors-0.050
hell-0.049
Token all
Token ID477
Feature activation-3.39e+00

Pos logit contributions
burn+0.150
 blowing+0.134
 waving+0.132
 driveway+0.118
 spinning+0.113
Neg logit contributions
 ounces-0.196
ils-0.182
izards-0.178
hell-0.170
bors-0.170
Token by
Token ID416
Feature activation-3.77e-01

Pos logit contributions
burn+0.097
 blowing+0.087
 waving+0.086
 driveway+0.079
 neighborhood+0.078
Neg logit contributions
 ounces-0.095
ils-0.086
izards-0.084
hell-0.083
bors-0.082
Token herself
Token ID5223
Feature activation+9.32e-01

Pos logit contributions
burn+0.011
 blowing+0.010
 waving+0.010
 spinning+0.009
 neighborhood+0.009
Neg logit contributions
 ounces-0.010
ils-0.009
izards-0.009
affe-0.009
bors-0.009
Token.
Token ID13
Feature activation-3.80e-01

Pos logit contributions
 ounces+0.031
ils+0.028
affe+0.028
izards+0.028
bors+0.028
Neg logit contributions
burn-0.022
 blowing-0.020
 waving-0.020
 spinning-0.017
 neighborhood-0.017
Token
Token ID198
Feature activation-9.06e-02

Pos logit contributions
burn+0.008
 blowing+0.007
 waving+0.006
 spinning+0.005
 driveway+0.005
Neg logit contributions
 ounces-0.014
affe-0.013
izards-0.013
ils-0.013
bors-0.013
Token run
Token ID1057
Feature activation+1.59e+00

Pos logit contributions
burn+0.011
 blowing+0.009
 waving+0.009
 spinning+0.008
 neighborhood+0.008
Neg logit contributions
 ounces-0.018
ils-0.017
izards-0.017
affe-0.017
bors-0.017
Token,
Token ID11
Feature activation-3.71e-01

Pos logit contributions
 ounces+0.059
ils+0.053
affe+0.052
izards+0.052
bors+0.052
Neg logit contributions
burn-0.034
 blowing-0.030
 waving-0.030
 spinning-0.026
 crying-0.025
Token but
Token ID475
Feature activation+2.31e-01

Pos logit contributions
burn+0.009
 blowing+0.008
 waving+0.008
 neighborhood+0.007
 driveway+0.007
Neg logit contributions
 ounces-0.012
izards-0.010
affe-0.010
ils-0.010
bors-0.010
Token his
Token ID465
Feature activation-9.62e-01

Pos logit contributions
 ounces+0.007
ils+0.006
izards+0.006
affe+0.006
bors+0.006
Neg logit contributions
burn-0.006
 blowing-0.005
 waving-0.005
 neighborhood-0.005
 driveway-0.005
Token mom
Token ID1995
Feature activation-4.21e+00

Pos logit contributions
burn+0.023
 blowing+0.022
ric+0.019
 waving+0.018
 typing+0.018
Neg logit contributions
 ounces-0.028
affe-0.025
hell-0.024
ily-0.024
ger-0.023
Token stopped
Token ID5025
Feature activation-6.05e+00

Pos logit contributions
burn+0.113
 blowing+0.100
 waving+0.099
 driveway+0.094
 spinning+0.090
Neg logit contributions
 ounces-0.122
ils-0.112
affe-0.112
isy-0.108
izards-0.107
Token him
Token ID683
Feature activation-7.26e-01

Pos logit contributions
burn+0.154
 driveway+0.141
icycle+0.127
tr+0.122
bars+0.120
Neg logit contributions
 ounces-0.146
izards-0.142
bors-0.139
ocol-0.137
ily-0.134
Token.
Token ID13
Feature activation+2.02e-01

Pos logit contributions
burn+0.018
 blowing+0.015
 waving+0.015
 neighborhood+0.014
 driveway+0.014
Neg logit contributions
 ounces-0.023
ils-0.020
hell-0.020
affe-0.020
izards-0.020
Token "
Token ID366
Feature activation+6.44e-01

Pos logit contributions
 ounces+0.005
affe+0.005
izards+0.005
bors+0.005
ils+0.005
Neg logit contributions
burn-0.006
 blowing-0.005
 waving-0.005
 crying-0.005
 driveway-0.005
TokenWait
Token ID21321
Feature activation+7.24e-01

Pos logit contributions
 ounces+0.021
ils+0.019
affe+0.019
bors+0.019
izards+0.019
Neg logit contributions
burn-0.015
 blowing-0.014
 waving-0.014
 spinning-0.012
 daddy-0.012
Token,
Token ID11
Feature activation+2.12e-01

Pos logit contributions
 ounces+0.026
ils+0.023
bors+0.023
izards+0.023
affe+0.023
Neg logit contributions
burn-0.016
 waving-0.015
 blowing-0.015
 spinning-0.013
 daddy-0.013
Token The
Token ID383
Feature activation-7.19e-01

Pos logit contributions
burn+0.002
 waving+0.001
 blowing+0.001
 daddy+0.001
 neighborhood+0.001
Neg logit contributions
 ounces-0.003
ils-0.003
bors-0.003
izards-0.003
hell-0.003
Token animals
Token ID4695
Feature activation-1.32e+00

Pos logit contributions
burn+0.020
 blowing+0.018
 waving+0.018
 neighborhood+0.016
 daddy+0.016
Neg logit contributions
 ounces-0.022
ils-0.019
izards-0.019
bors-0.019
hell-0.019
Token were
Token ID547
Feature activation-9.25e-01

Pos logit contributions
burn+0.027
 blowing+0.025
 waving+0.025
 crying+0.021
 spinning+0.021
Neg logit contributions
 ounces-0.048
affe-0.043
bors-0.043
izards-0.042
ils-0.042
Token very
Token ID845
Feature activation+1.65e+00

Pos logit contributions
burn+0.022
 blowing+0.018
 driveway+0.018
 waving+0.017
 neighborhood+0.016
Neg logit contributions
 ounces-0.028
izards-0.027
ils-0.027
bors-0.026
affe-0.026
Token happy
Token ID3772
Feature activation-2.32e-01

Pos logit contributions
 ounces+0.055
ils+0.050
izards+0.050
affe+0.049
bors+0.049
Neg logit contributions
burn-0.039
 blowing-0.034
 waving-0.033
 driveway-0.031
 spinning-0.030
Token living
Token ID2877
Feature activation-6.04e+00

Pos logit contributions
burn+0.005
 blowing+0.004
 waving+0.004
 driveway+0.004
 spinning+0.003
Neg logit contributions
 ounces-0.008
izards-0.008
ils-0.008
affe-0.008
bors-0.008
Token on
Token ID319
Feature activation-9.73e-01

Pos logit contributions
burn+0.106
 blowing+0.099
 waving+0.098
 crying+0.084
 neighborhood+0.084
Neg logit contributions
 ounces-0.241
affe-0.224
hell-0.215
bors-0.214
isy-0.211
Token the
Token ID262
Feature activation+1.79e-01

Pos logit contributions
burn+0.017
 waving+0.015
 blowing+0.015
 spinning+0.012
 leaning+0.012
Neg logit contributions
 ounces-0.039
affe-0.035
izards-0.035
ils-0.035
hell-0.035
Token farm
Token ID5318
Feature activation+1.46e+00

Pos logit contributions
 ounces+0.007
izards+0.006
hell+0.006
ils+0.006
bors+0.006
Neg logit contributions
burn-0.004
 blowing-0.003
 waving-0.003
 window-0.003
 neighborhood-0.003
Token.
Token ID13
Feature activation-3.91e-01

Pos logit contributions
 ounces+0.057
izards+0.050
affe+0.050
bors+0.050
hell+0.049
Neg logit contributions
burn-0.027
 waving-0.026
 blowing-0.026
 neighborhood-0.022
 crying-0.022
Token
Token ID198
Feature activation+8.16e-02

Pos logit contributions
burn+0.005
 waving+0.005
 blowing+0.005
 neighborhood+0.004
 daddy+0.004
Neg logit contributions
 ounces-0.017
ils-0.016
bors-0.015
izards-0.015
hell-0.015
Token.
Token ID13
Feature activation-4.86e-02

Pos logit contributions
 ounces+0.003
bors+0.002
ils+0.002
izards+0.002
affe+0.002
Neg logit contributions
burn-0.002
 waving-0.001
 blowing-0.001
 spinning-0.001
 crying-0.001
Token One
Token ID1881
Feature activation-4.82e-01

Pos logit contributions
burn+0.001
 blowing+0.001
 waving+0.001
 spinning+0.001
 neighborhood+0.001
Neg logit contributions
 ounces-0.002
ils-0.001
izards-0.001
bors-0.001
affe-0.001
Token day
Token ID1110
Feature activation+7.09e-01

Pos logit contributions
burn+0.009
 waving+0.008
 blowing+0.008
 driveway+0.007
 spinning+0.007
Neg logit contributions
 ounces-0.018
affe-0.017
hell-0.016
isy-0.016
ils-0.016
Token,
Token ID11
Feature activation+1.82e-01

Pos logit contributions
 ounces+0.024
affe+0.022
ils+0.021
izards+0.021
hell+0.021
Neg logit contributions
burn-0.016
 blowing-0.015
 waving-0.014
 driveway-0.013
 neighborhood-0.013
Token Wh
Token ID854
Feature activation+2.64e+00

Pos logit contributions
 ounces+0.006
ils+0.006
izards+0.006
affe+0.006
bors+0.006
Neg logit contributions
burn-0.004
 blowing-0.004
 waving-0.004
 spinning-0.003
 neighborhood-0.003
Tokenisk
Token ID1984
Feature activation+5.35e+00

Pos logit contributions
 ounces+0.088
bors+0.077
ils+0.077
izards+0.077
affe+0.076
Neg logit contributions
burn-0.064
 blowing-0.057
 waving-0.056
my-0.052
 neighborhood-0.051
Tokeners
Token ID364
Feature activation+4.73e-01

Pos logit contributions
 ounces+0.094
affe+0.069
 cents+0.064
ocol+0.064
mmm+0.064
Neg logit contributions
burn-0.208
 blowing-0.199
my-0.190
 waving-0.189
 neighborhood-0.178
Token went
Token ID1816
Feature activation-8.09e-01

Pos logit contributions
 ounces+0.016
ils+0.015
affe+0.014
izards+0.014
bors+0.014
Neg logit contributions
burn-0.011
 blowing-0.010
 waving-0.010
 spinning-0.009
 driveway-0.008
Token on
Token ID319
Feature activation+1.89e+00

Pos logit contributions
burn+0.017
 blowing+0.015
 waving+0.014
 daddy+0.014
 driveway+0.013
Neg logit contributions
 ounces-0.026
ils-0.025
izards-0.025
affe-0.025
hell-0.024
Token a
Token ID257
Feature activation+7.89e-01

Pos logit contributions
 ounces+0.045
ils+0.043
izards+0.042
 mushrooms+0.041
bors+0.040
Neg logit contributions
burn-0.056
 blowing-0.048
 waving-0.046
 driveway-0.046
 daddy-0.045
Token walk
Token ID2513
Feature activation-8.47e-01

Pos logit contributions
 ounces+0.029
hell+0.027
affe+0.027
isy+0.027
bors+0.027
Neg logit contributions
burn-0.014
 blowing-0.012
 waving-0.012
 leaning-0.010
seat-0.010
Token to
Token ID284
Feature activation-3.12e-01

Pos logit contributions
burn+0.008
 blowing+0.007
 waving+0.007
 daddy+0.006
 crying+0.005
Neg logit contributions
 ounces-0.022
ils-0.020
affe-0.020
izards-0.020
bors-0.020
Token pet
Token ID4273
Feature activation+1.42e+00

Pos logit contributions
burn+0.007
 blowing+0.006
 waving+0.006
 neighborhood+0.005
 driveway+0.005
Neg logit contributions
 ounces-0.011
affe-0.010
ils-0.010
izards-0.010
bors-0.010
Token the
Token ID262
Feature activation-3.81e-01

Pos logit contributions
 ounces+0.051
ils+0.046
bors+0.046
hell+0.045
izards+0.045
Neg logit contributions
burn-0.033
 waving-0.028
 blowing-0.027
my-0.025
 daddy-0.025
Token rh
Token ID9529
Feature activation-1.18e+00

Pos logit contributions
burn+0.010
 blowing+0.009
 waving+0.008
 spinning+0.008
 driveway+0.007
Neg logit contributions
 ounces-0.012
affe-0.011
ils-0.011
bors-0.011
izards-0.011
Tokenin
Token ID259
Feature activation+4.74e-01

Pos logit contributions
burn+0.032
 blowing+0.029
 waving+0.028
 neighborhood+0.025
my+0.025
Neg logit contributions
 ounces-0.035
ils-0.031
bors-0.031
izards-0.031
affe-0.030
Tokenoc
Token ID420
Feature activation+5.35e+00

Pos logit contributions
 ounces+0.011
izards+0.011
ils+0.011
bors+0.010
ilies+0.009
Neg logit contributions
burn-0.015
 waving-0.014
 blowing-0.014
my-0.014
 daddy-0.013
Tokeneros
Token ID27498
Feature activation+6.71e-01

Pos logit contributions
 ounces+0.115
izards+0.101
ils+0.100
bors+0.098
hell+0.096
Neg logit contributions
burn-0.188
 blowing-0.175
 waving-0.174
 crying-0.159
 neighborhood-0.159
Token.
Token ID13
Feature activation-9.84e-01

Pos logit contributions
 ounces+0.024
bors+0.022
izards+0.022
ils+0.021
hell+0.020
Neg logit contributions
burn-0.015
 waving-0.013
 blowing-0.013
my-0.012
 crying-0.012
Token It
Token ID632
Feature activation-1.24e-01

Pos logit contributions
burn+0.024
 waving+0.023
 daddy+0.021
 crying+0.021
 blowing+0.021
Neg logit contributions
ils-0.030
 ounces-0.030
bors-0.028
hell-0.027
isy-0.027
Token looked
Token ID3114
Feature activation+2.40e-01

Pos logit contributions
burn+0.002
 waving+0.002
 blowing+0.002
 crying+0.002
 spinning+0.002
Neg logit contributions
 ounces-0.005
izards-0.004
ils-0.004
bors-0.004
affe-0.004
Token so
Token ID523
Feature activation+1.55e+00

Pos logit contributions
 ounces+0.009
affe+0.008
ils+0.008
bors+0.008
izards+0.008
Neg logit contributions
burn-0.005
 waving-0.005
 blowing-0.005
 crying-0.004
 spinning-0.004
Token a
Token ID257
Feature activation-6.32e-01

Pos logit contributions
 ounces+0.020
ils+0.018
izards+0.018
affe+0.018
bors+0.018
Neg logit contributions
burn-0.014
 blowing-0.013
 waving-0.013
 driveway-0.011
 neighborhood-0.011
Token sign
Token ID1051
Feature activation+2.54e+00

Pos logit contributions
burn+0.015
 blowing+0.013
 waving+0.012
 driveway+0.011
 leaning+0.011
Neg logit contributions
 ounces-0.021
affe-0.019
hell-0.019
bors-0.018
isy-0.018
Token that
Token ID326
Feature activation+8.06e-01

Pos logit contributions
 ounces+0.067
affe+0.062
ils+0.060
hell+0.060
izards+0.060
Neg logit contributions
burn-0.076
 blowing-0.066
 waving-0.063
 neighborhood-0.061
 driveway-0.060
Token said
Token ID531
Feature activation+2.14e+00

Pos logit contributions
 ounces+0.029
affe+0.026
bors+0.026
ils+0.026
hell+0.026
Neg logit contributions
burn-0.017
 waving-0.016
 blowing-0.016
 daddy-0.014
 spinning-0.013
Token "
Token ID366
Feature activation+7.27e-01

Pos logit contributions
 ounces+0.092
ils+0.087
bors+0.082
izards+0.081
affe+0.081
Neg logit contributions
 waving-0.033
 blowing-0.029
 spinning-0.026
burn-0.026
 daddy-0.025
TokenP
Token ID47
Feature activation+6.44e+00

Pos logit contributions
 ounces+0.023
ils+0.021
izards+0.021
bors+0.020
hell+0.020
Neg logit contributions
burn-0.019
 blowing-0.017
 waving-0.016
my-0.015
 neighborhood-0.014
Tokenengu
Token ID13561
Feature activation-1.22e+00

Pos logit contributions
bors+0.173
 ounces+0.172
ils+0.171
isy+0.159
izards+0.155
Neg logit contributions
burn-0.159
 waving-0.137
my-0.136
rou-0.132
 blowing-0.132
Tokenins
Token ID1040
Feature activation+1.69e+00

Pos logit contributions
burn+0.026
 blowing+0.024
 waving+0.022
my+0.022
m+0.019
Neg logit contributions
 ounces-0.039
bors-0.036
affe-0.036
ger-0.035
nic-0.034
Token are
Token ID389
Feature activation+5.55e-01

Pos logit contributions
 ounces+0.049
bors+0.044
hell+0.041
izards+0.041
isy+0.041
Neg logit contributions
burn-0.047
 blowing-0.044
 waving-0.044
my-0.040
 daddy-0.039
Token sleeping
Token ID11029
Feature activation-5.89e-01

Pos logit contributions
 ounces+0.021
izards+0.019
hell+0.019
affe+0.019
ils+0.019
Neg logit contributions
 waving-0.011
 blowing-0.011
burn-0.010
 spinning-0.009
 leaning-0.008
Token.
Token ID13
Feature activation-6.58e-01

Pos logit contributions
burn+0.015
 blowing+0.015
 waving+0.014
 daddy+0.013
 window+0.013
Neg logit contributions
 ounces-0.018
bors-0.016
izards-0.016
hell-0.016
affe-0.015
Token was
Token ID373
Feature activation-7.74e-01

Pos logit contributions
 ounces+0.014
affe+0.013
izards+0.013
hell+0.013
bors+0.013
Neg logit contributions
burn-0.006
 blowing-0.006
 waving-0.006
 daddy-0.005
 neighborhood-0.005
Token getting
Token ID1972
Feature activation+3.57e-01

Pos logit contributions
burn+0.017
 blowing+0.014
 waving+0.014
 driveway+0.013
 neighborhood+0.013
Neg logit contributions
 ounces-0.027
ils-0.024
izards-0.024
bors-0.024
affe-0.023
Token ready
Token ID3492
Feature activation+8.15e-01

Pos logit contributions
 ounces+0.012
ils+0.011
izards+0.011
bors+0.011
hell+0.011
Neg logit contributions
burn-0.008
 waving-0.007
 blowing-0.007
 driveway-0.006
 neighborhood-0.006
Token to
Token ID284
Feature activation-1.70e-02

Pos logit contributions
 ounces+0.032
ils+0.030
affe+0.030
izards+0.030
bors+0.029
Neg logit contributions
burn-0.014
 blowing-0.012
 waving-0.012
 spinning-0.010
 daddy-0.010
Token make
Token ID787
Feature activation+1.48e+00

Pos logit contributions
burn+0.000
 blowing+0.000
 waving+0.000
 daddy+0.000
 spinning+0.000
Neg logit contributions
 ounces-0.001
affe-0.001
izards-0.001
ils-0.001
bors-0.001
Token por
Token ID16964
Feature activation+6.51e+00

Pos logit contributions
affe+0.052
 ounces+0.052
izards+0.047
hell+0.047
bors+0.047
Neg logit contributions
burn-0.031
 blowing-0.030
 daddy-0.029
 waving-0.029
 spinning-0.026
Tokenridge
Token ID12818
Feature activation+2.00e+00

Pos logit contributions
 ounces+0.153
izards+0.137
hell+0.136
affe+0.135
bors+0.128
Neg logit contributions
burn-0.218
 blowing-0.203
 waving-0.194
 spinning-0.180
 ticking-0.180
Token and
Token ID290
Feature activation+2.14e-01

Pos logit contributions
 ounces+0.075
affe+0.070
bors+0.069
izards+0.068
ils+0.067
Neg logit contributions
burn-0.040
 blowing-0.037
 waving-0.035
 daddy-0.031
 spinning-0.030
Token pancakes
Token ID47008
Feature activation+1.75e+00

Pos logit contributions
 ounces+0.007
affe+0.007
izards+0.006
ils+0.006
hell+0.006
Neg logit contributions
burn-0.005
 blowing-0.005
 waving-0.005
 daddy-0.004
 spinning-0.004
Token.
Token ID13
Feature activation+1.05e-03

Pos logit contributions
 ounces+0.064
affe+0.059
bors+0.058
izards+0.058
ils+0.056
Neg logit contributions
burn-0.036
 blowing-0.035
 waving-0.033
 daddy-0.028
 spinning-0.028
Token He
Token ID679
Feature activation+3.26e-01

Pos logit contributions
 ounces+0.000
ils+0.000
izards+0.000
bors+0.000
affe+0.000
Neg logit contributions
burn-0.000
 waving-0.000
 blowing-0.000
 driveway-0.000
 neighborhood-0.000
Token got
Token ID1392
Feature activation+1.16e-01

Pos logit contributions
burn+0.024
 blowing+0.022
 waving+0.021
 spinning+0.019
 driveway+0.018
Neg logit contributions
 ounces-0.030
ils-0.028
affe-0.027
izards-0.027
bors-0.027
Token out
Token ID503
Feature activation+1.49e-01

Pos logit contributions
 ounces+0.004
ils+0.003
izards+0.003
ily+0.003
imes+0.003
Neg logit contributions
burn-0.003
 waving-0.003
 blowing-0.002
 driveway-0.002
 neighborhood-0.002
Token of
Token ID286
Feature activation+3.42e-02

Pos logit contributions
 ounces+0.004
ils+0.004
izards+0.004
ily+0.003
hell+0.003
Neg logit contributions
burn-0.004
 waving-0.004
 driveway-0.003
 blowing-0.003
 neighborhood-0.003
Token bed
Token ID3996
Feature activation+7.30e-01

Pos logit contributions
 ounces+0.001
 mushrooms+0.001
izards+0.001
ils+0.001
 bananas+0.001
Neg logit contributions
burn-0.001
itating-0.001
 neighborhood-0.001
rou-0.001
rolling-0.001
Token at
Token ID379
Feature activation+5.04e-01

Pos logit contributions
 ounces+0.024
ils+0.023
hell+0.022
affe+0.022
izards+0.022
Neg logit contributions
burn-0.016
 waving-0.013
 blowing-0.013
 driveway-0.012
 spinning-0.011
Token 7
Token ID767
Feature activation+5.53e+00

Pos logit contributions
 ounces+0.013
ily+0.011
ils+0.011
 mushrooms+0.011
izards+0.010
Neg logit contributions
burn-0.014
 blowing-0.012
 waving-0.012
rou-0.011
rolling-0.011
Tokenam
Token ID321
Feature activation-1.99e+00

Pos logit contributions
 ounces+0.182
affe+0.172
bors+0.167
izards+0.166
hell+0.166
Neg logit contributions
burn-0.122
 waving-0.115
 blowing-0.114
 spinning-0.104
 neighborhood-0.103
Token and
Token ID290
Feature activation+8.83e-01

Pos logit contributions
burn+0.045
 blowing+0.040
 waving+0.039
 spinning+0.034
 driveway+0.034
Neg logit contributions
 ounces-0.068
ils-0.062
izards-0.061
affe-0.061
hell-0.060
Token went
Token ID1816
Feature activation-6.16e-01

Pos logit contributions
 ounces+0.030
ils+0.027
izards+0.027
bors+0.027
affe+0.026
Neg logit contributions
burn-0.020
 blowing-0.018
 waving-0.018
 neighborhood-0.016
 spinning-0.015
Token to
Token ID284
Feature activation+1.34e+00

Pos logit contributions
burn+0.012
 blowing+0.010
 waving+0.010
 neighborhood+0.009
 daddy+0.009
Neg logit contributions
 ounces-0.021
ils-0.020
izards-0.019
bors-0.019
hell-0.018
Token the
Token ID262
Feature activation+7.08e-01

Pos logit contributions
 ounces+0.039
izards+0.035
ils+0.034
bors+0.034
nic+0.032
Neg logit contributions
burn-0.036
 blowing-0.031
 waving-0.028
 neighborhood-0.026
 leaning-0.026
Token the
Token ID262
Feature activation+1.14e-01

Pos logit contributions
 ounces+0.010
affe+0.010
bors+0.009
izards+0.009
ils+0.009
Neg logit contributions
burn-0.005
 blowing-0.004
 waving-0.004
 daddy-0.004
 spinning-0.004
Token bottle
Token ID9294
Feature activation+3.19e+00

Pos logit contributions
 ounces+0.004
izards+0.004
ils+0.004
bors+0.004
affe+0.004
Neg logit contributions
burn-0.002
 blowing-0.002
 waving-0.002
 spinning-0.002
 crying-0.002
Token and
Token ID290
Feature activation+9.15e-01

Pos logit contributions
 ounces+0.136
bors+0.126
ils+0.124
izards+0.124
affe+0.123
Neg logit contributions
burn-0.047
 blowing-0.041
 waving-0.039
 spinning-0.032
my-0.031
Token it
Token ID340
Feature activation+2.29e+00

Pos logit contributions
 ounces+0.032
ils+0.029
izards+0.029
affe+0.029
bors+0.029
Neg logit contributions
burn-0.020
 blowing-0.018
 waving-0.018
 spinning-0.016
 neighborhood-0.016
Token broke
Token ID6265
Feature activation-9.83e-01

Pos logit contributions
 ounces+0.087
affe+0.079
bors+0.078
izards+0.078
ils+0.077
Neg logit contributions
burn-0.045
 blowing-0.041
 waving-0.040
 spinning-0.035
 crying-0.034
Token on
Token ID319
Feature activation+1.49e+00

Pos logit contributions
burn+0.025
 blowing+0.022
 waving+0.022
 neighborhood+0.019
 driveway+0.019
Neg logit contributions
 ounces-0.032
ils-0.028
izards-0.028
affe-0.028
bors-0.028
Token the
Token ID262
Feature activation-1.23e-01

Pos logit contributions
 ounces+0.056
izards+0.052
affe+0.052
ils+0.051
bors+0.051
Neg logit contributions
burn-0.029
 blowing-0.026
 waving-0.025
 daddy-0.022
 spinning-0.021
Token floor
Token ID4314
Feature activation+2.54e-01

Pos logit contributions
burn+0.003
 blowing+0.002
 waving+0.002
 driveway+0.002
 window+0.002
Neg logit contributions
 ounces-0.005
izards-0.004
bors-0.004
affe-0.004
ils-0.004
Token.
Token ID13
Feature activation-7.61e-01

Pos logit contributions
 ounces+0.008
ils+0.008
affe+0.008
bors+0.008
izards+0.008
Neg logit contributions
burn-0.006
 blowing-0.005
 waving-0.005
 spinning-0.005
 crying-0.005
Token The
Token ID383
Feature activation-1.31e+00

Pos logit contributions
burn+0.015
 blowing+0.014
 waving+0.014
 spinning+0.012
 neighborhood+0.012
Neg logit contributions
 ounces-0.028
ils-0.026
affe-0.025
izards-0.025
bors-0.025
Token wine
Token ID8237
Feature activation+8.99e-01

Pos logit contributions
burn+0.032
 blowing+0.028
 waving+0.028
 spinning+0.024
 driveway+0.024
Neg logit contributions
 ounces-0.043
ils-0.039
affe-0.039
izards-0.038
bors-0.038
Token.
Token ID13
Feature activation-7.18e-01

Pos logit contributions
 ounces+0.036
affe+0.034
izards+0.033
bors+0.032
isy+0.031
Neg logit contributions
 blowing-0.015
burn-0.015
 daddy-0.014
 waving-0.014
 window-0.013
Token She
Token ID1375
Feature activation+8.20e-01

Pos logit contributions
burn+0.011
my+0.010
 daddy+0.009
 waving+0.009
 Grand+0.009
Neg logit contributions
ils-0.028
 ounces-0.027
isy-0.026
hell-0.026
bors-0.026
Token does
Token ID857
Feature activation+1.12e+00

Pos logit contributions
 ounces+0.030
bors+0.027
affe+0.027
hell+0.027
izards+0.027
Neg logit contributions
burn-0.016
 blowing-0.015
 waving-0.014
 crying-0.012
my-0.012
Token not
Token ID407
Feature activation-1.49e+00

Pos logit contributions
 ounces+0.053
affe+0.051
ils+0.049
izards+0.049
bors+0.048
Neg logit contributions
burn-0.010
 blowing-0.010
 waving-0.010
 spinning-0.007
 frown-0.007
Token permit
Token ID8749
Feature activation+9.39e-01

Pos logit contributions
burn+0.031
 blowing+0.026
 waving+0.026
my+0.025
 frown+0.024
Neg logit contributions
 ounces-0.056
bors-0.051
ils-0.050
izards-0.050
affe-0.049
Token us
Token ID514
Feature activation+2.03e+00

Pos logit contributions
 ounces+0.033
affe+0.031
bridge+0.030
hell+0.029
bors+0.029
Neg logit contributions
burn-0.019
 blowing-0.018
 waving-0.018
 daddy-0.018
 crying-0.017
Token to
Token ID284
Feature activation-6.53e-01

Pos logit contributions
 ounces+0.101
affe+0.094
bors+0.092
izards+0.090
hell+0.089
Neg logit contributions
burn-0.020
 blowing-0.014
 waving-0.013
my-0.009
 crying-0.009
Token touch
Token ID3638
Feature activation-6.06e-01

Pos logit contributions
burn+0.016
 blowing+0.015
 waving+0.015
 spinning+0.013
 neighborhood+0.013
Neg logit contributions
 ounces-0.021
ils-0.019
izards-0.019
affe-0.019
bors-0.019
Token them
Token ID606
Feature activation+1.83e+00

Pos logit contributions
burn+0.011
 blowing+0.009
my+0.009
 daddy+0.009
 waving+0.009
Neg logit contributions
 ounces-0.023
affe-0.023
isy-0.021
izards-0.021
nic-0.021
Token.
Token ID13
Feature activation-8.63e-01

Pos logit contributions
 ounces+0.066
bors+0.062
affe+0.060
izards+0.059
ils+0.058
Neg logit contributions
burn-0.041
 blowing-0.036
 waving-0.034
my-0.032
 daddy-0.032
Token They
Token ID1119
Feature activation+2.80e-01

Pos logit contributions
burn+0.014
my+0.013
 daddy+0.012
 waving+0.012
 grandma+0.011
Neg logit contributions
ils-0.033
 ounces-0.033
isy-0.032
bors-0.031
hell-0.031
Token there
Token ID612
Feature activation-1.96e+00

Pos logit contributions
burn+0.001
 blowing+0.001
 waving+0.001
 spinning+0.001
 daddy+0.001
Neg logit contributions
 ounces-0.004
ils-0.004
affe-0.004
izards-0.004
bors-0.004
Token was
Token ID373
Feature activation+1.61e+00

Pos logit contributions
burn+0.033
 blowing+0.029
 waving+0.028
 spinning+0.023
 neighborhood+0.023
Neg logit contributions
 ounces-0.078
ils-0.072
izards-0.071
affe-0.071
bors-0.071
Token a
Token ID257
Feature activation-5.93e-01

Pos logit contributions
 ounces+0.052
izards+0.047
ils+0.046
bors+0.046
affe+0.046
Neg logit contributions
burn-0.040
 blowing-0.035
 waving-0.034
 driveway-0.031
 neighborhood-0.030
Token little
Token ID1310
Feature activation-4.33e-01

Pos logit contributions
burn+0.015
 blowing+0.013
 waving+0.012
 driveway+0.011
my+0.011
Neg logit contributions
 ounces-0.018
affe-0.017
isy-0.016
bors-0.016
hell-0.016
Token girl
Token ID2576
Feature activation+2.75e+00

Pos logit contributions
burn+0.009
 blowing+0.008
 waving+0.008
 driveway+0.007
 neighborhood+0.007
Neg logit contributions
 ounces-0.015
affe-0.014
izards-0.013
ils-0.013
bors-0.013
Token called
Token ID1444
Feature activation+2.02e+00

Pos logit contributions
 ounces+0.079
ils+0.071
affe+0.070
izards+0.070
bors+0.069
Neg logit contributions
burn-0.076
 blowing-0.069
 waving-0.067
 driveway-0.062
 spinning-0.061
Token Daisy
Token ID40355
Feature activation+9.49e-01

Pos logit contributions
 ounces+0.067
affe+0.059
hell+0.058
ils+0.058
bors+0.057
Neg logit contributions
burn-0.051
 waving-0.047
 blowing-0.046
 daddy-0.043
 crying-0.042
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
 ounces+0.033
ils+0.030
bors+0.030
izards+0.030
affe+0.029
Neg logit contributions
burn-0.021
 waving-0.019
 blowing-0.019
 daddy-0.017
 spinning-0.017
Token Daisy
Token ID40355
Feature activation-1.12e-01

Pos logit contributions
burn+0.000
 waving+0.000
 blowing+0.000
 neighborhood+0.000
 spinning+0.000
Neg logit contributions
 ounces-0.000
ils-0.000
izards-0.000
bors-0.000
affe-0.000
Token was
Token ID373
Feature activation-7.29e-01

Pos logit contributions
burn+0.002
 blowing+0.002
 waving+0.002
 spinning+0.001
 neighborhood+0.001
Neg logit contributions
 ounces-0.004
ils-0.004
izards-0.004
affe-0.004
bors-0.004
Token very
Token ID845
Feature activation+1.55e+00

Pos logit contributions
burn+0.019
 driveway+0.016
 blowing+0.015
seat+0.015
 waving+0.014
Neg logit contributions
 ounces-0.021
izards-0.019
ily-0.019
ils-0.018
bors-0.018
Token Every
Token ID3887
Feature activation-2.35e+00

Pos logit contributions
 ounces+0.010
affe+0.008
hell+0.008
izards+0.008
bors+0.008
Neg logit contributions
burn-0.014
 blowing-0.012
 waving-0.012
 crying-0.011
 spinning-0.011
Token day
Token ID1110
Feature activation+1.72e-01

Pos logit contributions
burn+0.055
 waving+0.050
 blowing+0.047
 typing+0.046
 crying+0.043
Neg logit contributions
 ounces-0.073
affe-0.070
hell-0.067
isy-0.067
ger-0.065
Token he
Token ID339
Feature activation+1.54e+00

Pos logit contributions
 ounces+0.005
ils+0.005
affe+0.005
izards+0.005
bors+0.005
Neg logit contributions
burn-0.005
 blowing-0.004
 waving-0.004
 neighborhood-0.004
 driveway-0.004
Token would
Token ID561
Feature activation-1.33e+00

Pos logit contributions
 ounces+0.057
ils+0.053
izards+0.052
affe+0.052
bors+0.051
Neg logit contributions
burn-0.031
 waving-0.027
 blowing-0.027
 crying-0.022
 driveway-0.022
Token take
Token ID1011
Feature activation+2.65e+00

Pos logit contributions
burn+0.031
 blowing+0.027
 waving+0.026
 neighborhood+0.024
 crying+0.023
Neg logit contributions
 ounces-0.045
ils-0.041
affe-0.040
bors-0.040
izards-0.040
Token it
Token ID340
Feature activation+2.73e+00

Pos logit contributions
 ounces+0.090
izards+0.082
ils+0.081
affe+0.081
bors+0.079
Neg logit contributions
burn-0.060
 waving-0.055
 blowing-0.055
 spinning-0.050
 daddy-0.048
Token to
Token ID284
Feature activation+1.37e+00

Pos logit contributions
 ounces+0.092
ils+0.086
izards+0.086
hell+0.086
affe+0.085
Neg logit contributions
burn-0.059
 blowing-0.051
 waving-0.051
 neighborhood-0.044
 driveway-0.044
Token the
Token ID262
Feature activation+1.24e+00

Pos logit contributions
 ounces+0.043
bors+0.038
izards+0.038
ils+0.038
affe+0.037
Neg logit contributions
burn-0.035
 blowing-0.030
 waving-0.029
 driveway-0.027
 neighborhood-0.027
Token park
Token ID3952
Feature activation+4.73e-01

Pos logit contributions
 ounces+0.044
affe+0.042
ils+0.041
izards+0.040
 mushrooms+0.040
Neg logit contributions
burn-0.025
 blowing-0.022
 waving-0.019
 crying-0.016
 spinning-0.016
Token and
Token ID290
Feature activation+5.76e-01

Pos logit contributions
 ounces+0.017
ils+0.016
affe+0.016
izards+0.016
hell+0.016
Neg logit contributions
burn-0.009
 blowing-0.008
 waving-0.007
 spinning-0.006
 driveway-0.006
Token kick
Token ID4829
Feature activation+6.42e-01

Pos logit contributions
 ounces+0.021
ils+0.019
affe+0.019
bors+0.019
izards+0.019
Neg logit contributions
burn-0.012
 blowing-0.010
 waving-0.010
 neighborhood-0.009
 leaning-0.008
Token a
Token ID257
Feature activation-1.19e+00

Pos logit contributions
burn+0.003
 blowing+0.003
 waving+0.003
 driveway+0.003
 neighborhood+0.003
Neg logit contributions
 ounces-0.005
izards-0.005
ils-0.004
bors-0.004
hell-0.004
Token high
Token ID1029
Feature activation+5.89e-01

Pos logit contributions
burn+0.030
 blowing+0.026
 waving+0.026
 driveway+0.023
 neighborhood+0.023
Neg logit contributions
 ounces-0.038
affe-0.034
hell-0.033
bors-0.033
ils-0.033
Token rat
Token ID4227
Feature activation+1.77e+00

Pos logit contributions
 ounces+0.018
affe+0.017
ils+0.016
hell+0.016
bors+0.016
Neg logit contributions
burn-0.015
 blowing-0.014
 waving-0.013
 neighborhood-0.012
 daddy-0.012
Token �
Token ID6184
Feature activation+4.09e+00

Pos logit contributions
 ounces+0.060
ils+0.053
izards+0.053
bors+0.053
affe+0.052
Neg logit contributions
burn-0.041
 waving-0.039
 blowing-0.038
 spinning-0.034
 crying-0.033
Token�
Token ID95
Feature activation+2.84e+00

Pos logit contributions
 ounces+0.123
hell+0.116
bors+0.115
ils+0.114
izards+0.111
Neg logit contributions
burn-0.103
 waving-0.099
 leaning-0.094
 blowing-0.093
 spinning-0.089
Token€
Token ID26391
Feature activation+3.18e+00

Pos logit contributions
izards+0.080
ilies+0.075
hell+0.075
 ounces+0.074
ils+0.072
Neg logit contributions
burn-0.073
 driveway-0.070
 leaning-0.069
 waving-0.068
 neighborhood-0.067
Token�
Token ID447
Feature activation-7.10e-01

Pos logit contributions
 ounces+0.096
ils+0.087
izards+0.085
bors+0.084
affe+0.083
Neg logit contributions
burn-0.086
 waving-0.078
 blowing-0.077
 neighborhood-0.071
 driveway-0.069
Token�
Token ID250
Feature activation+1.68e+00

Pos logit contributions
burn+0.015
 blowing+0.014
 waving+0.013
 spinning+0.012
 neighborhood+0.011
Neg logit contributions
 ounces-0.025
ils-0.023
izards-0.023
affe-0.023
bors-0.023
Token much
Token ID881
Feature activation+3.52e-01

Pos logit contributions
 ounces+0.055
ils+0.052
izards+0.051
affe+0.050
bors+0.050
Neg logit contributions
burn-0.040
 blowing-0.036
 waving-0.035
my-0.031
 spinning-0.031
Token bigger
Token ID5749
Feature activation-6.98e-01

Pos logit contributions
 ounces+0.012
ils+0.011
izards+0.011
affe+0.011
bors+0.010
Neg logit contributions
burn-0.008
 blowing-0.008
 waving-0.008
 spinning-0.007
 crying-0.007
Token than
Token ID621
Feature activation-6.26e-01

Pos logit contributions
burn+0.018
 waving+0.017
 blowing+0.017
 leaning+0.015
 spinning+0.015
Neg logit contributions
 ounces-0.020
ils-0.019
hell-0.019
izards-0.019
bors-0.019
Token special
Token ID2041
Feature activation+2.99e-01

Pos logit contributions
 ounces+0.130
izards+0.117
ils+0.117
bors+0.116
affe+0.116
Neg logit contributions
burn-0.072
 waving-0.067
 blowing-0.066
 daddy-0.059
 neighborhood-0.059
Token frame
Token ID5739
Feature activation+6.70e-01

Pos logit contributions
 ounces+0.009
affe+0.009
ils+0.008
hell+0.008
isy+0.008
Neg logit contributions
burn-0.007
 blowing-0.006
 waving-0.006
 leaning-0.006
my-0.006
Token.
Token ID13
Feature activation+6.02e-01

Pos logit contributions
 ounces+0.023
bors+0.021
ils+0.021
izards+0.021
affe+0.020
Neg logit contributions
burn-0.015
 blowing-0.014
 waving-0.014
 spinning-0.012
 crying-0.012
Token It
Token ID632
Feature activation+1.80e-01

Pos logit contributions
 ounces+0.022
ils+0.021
bors+0.020
izards+0.020
hell+0.020
Neg logit contributions
burn-0.012
 blowing-0.011
 waving-0.011
 driveway-0.009
 neighborhood-0.009
Token was
Token ID373
Feature activation-6.99e-02

Pos logit contributions
 ounces+0.007
ils+0.006
izards+0.006
affe+0.006
bors+0.006
Neg logit contributions
burn-0.003
 blowing-0.003
 waving-0.003
 spinning-0.002
 neighborhood-0.002
Token a
Token ID257
Feature activation-1.22e+00

Pos logit contributions
burn+0.002
 waving+0.001
 blowing+0.001
 neighborhood+0.001
 driveway+0.001
Neg logit contributions
 ounces-0.002
ils-0.002
izards-0.002
hell-0.002
bors-0.002
Token colorful
Token ID20239
Feature activation-2.71e-01

Pos logit contributions
burn+0.034
 blowing+0.028
 waving+0.026
my+0.025
seat+0.025
Neg logit contributions
 ounces-0.034
affe-0.032
isy-0.032
hell-0.031
ocket-0.029
Token frame
Token ID5739
Feature activation+4.30e-01

Pos logit contributions
burn+0.008
 blowing+0.007
 waving+0.007
 driveway+0.006
 neighborhood+0.006
Neg logit contributions
 ounces-0.007
affe-0.007
ils-0.006
hell-0.006
izards-0.006
Token and
Token ID290
Feature activation+1.36e+00

Pos logit contributions
 ounces+0.014
ils+0.013
affe+0.013
izards+0.013
bors+0.013
Neg logit contributions
burn-0.010
 blowing-0.009
 waving-0.009
 spinning-0.008
 neighborhood-0.008
Token it
Token ID340
Feature activation+4.09e-01

Pos logit contributions
 ounces+0.047
affe+0.042
izards+0.042
ils+0.042
bors+0.042
Neg logit contributions
burn-0.030
 blowing-0.028
 waving-0.028
 spinning-0.025
 daddy-0.025
Token was
Token ID373
Feature activation-1.28e-01

Pos logit contributions
 ounces+0.015
ils+0.013
izards+0.013
affe+0.013
bors+0.013
Neg logit contributions
burn-0.009
 blowing-0.008
 waving-0.008
 driveway-0.006
 neighborhood-0.006
Token time
Token ID640
Feature activation-2.47e+00

Pos logit contributions
burn+0.032
 waving+0.028
 blowing+0.028
 driveway+0.025
 spinning+0.025
Neg logit contributions
 ounces-0.037
hell-0.034
affe-0.033
ils-0.033
bors-0.032
Token,
Token ID11
Feature activation-9.87e-01

Pos logit contributions
burn+0.050
 blowing+0.045
 waving+0.045
 spinning+0.038
 daddy+0.038
Neg logit contributions
 ounces-0.091
ils-0.082
affe-0.082
izards-0.082
bors-0.081
Token please
Token ID3387
Feature activation+1.56e+00

Pos logit contributions
burn+0.029
 blowing+0.027
 waving+0.026
 driveway+0.024
 neighborhood+0.024
Neg logit contributions
 ounces-0.027
ils-0.024
izards-0.024
affe-0.024
bors-0.024
Token listen
Token ID6004
Feature activation-5.60e-01

Pos logit contributions
 ounces+0.049
ils+0.043
affe+0.043
bors+0.043
izards+0.042
Neg logit contributions
burn-0.039
 blowing-0.035
 waving-0.035
 driveway-0.031
 neighborhood-0.031
Token to
Token ID284
Feature activation+4.80e-01

Pos logit contributions
burn+0.008
 blowing+0.007
 waving+0.006
 spinning+0.005
 daddy+0.005
Neg logit contributions
 ounces-0.024
izards-0.022
ils-0.022
affe-0.022
bors-0.022
Token me
Token ID502
Feature activation+1.04e+00

Pos logit contributions
 ounces+0.016
izards+0.014
affe+0.014
hell+0.014
ils+0.014
Neg logit contributions
burn-0.012
 blowing-0.011
 waving-0.011
 daddy-0.010
 spinning-0.010
Token and
Token ID290
Feature activation-7.49e-01

Pos logit contributions
 ounces+0.041
izards+0.037
bors+0.037
affe+0.037
ils+0.037
Neg logit contributions
burn-0.019
 blowing-0.017
 waving-0.016
 daddy-0.014
my-0.014
Token wait
Token ID4043
Feature activation+8.32e-01

Pos logit contributions
burn+0.018
 blowing+0.016
 waving+0.016
 spinning+0.014
 neighborhood+0.014
Neg logit contributions
 ounces-0.025
ils-0.023
izards-0.022
affe-0.022
bors-0.022
Token until
Token ID1566
Feature activation+1.91e-01

Pos logit contributions
 ounces+0.027
ils+0.024
affe+0.024
izards+0.024
bors+0.023
Neg logit contributions
burn-0.021
 blowing-0.019
 waving-0.019
 spinning-0.017
 daddy-0.017
Token the
Token ID262
Feature activation-9.57e-01

Pos logit contributions
 ounces+0.006
affe+0.005
ils+0.005
izards+0.005
bors+0.005
Neg logit contributions
burn-0.005
 blowing-0.005
 waving-0.005
 spinning-0.004
 daddy-0.004
Token pie
Token ID2508
Feature activation+7.31e-01

Pos logit contributions
burn+0.033
 blowing+0.030
 waving+0.030
 spinning+0.028
 daddy+0.027
Neg logit contributions
 ounces-0.022
ils-0.019
affe-0.018
bors-0.018
izards-0.018
Token going
Token ID1016
Feature activation-1.58e+00

Pos logit contributions
burn+0.051
 blowing+0.043
 waving+0.042
 daddy+0.040
 neighborhood+0.040
Neg logit contributions
 ounces-0.063
hell-0.057
ils-0.057
izards-0.057
affe-0.056
Token by
Token ID416
Feature activation+3.58e-01

Pos logit contributions
burn+0.033
 blowing+0.028
 waving+0.028
 daddy+0.025
 neighborhood+0.024
Neg logit contributions
 ounces-0.056
ils-0.050
izards-0.050
bors-0.050
hell-0.050
Token.
Token ID13
Feature activation-6.01e-01

Pos logit contributions
 ounces+0.012
ils+0.010
izards+0.010
affe+0.010
bors+0.010
Neg logit contributions
burn-0.009
 blowing-0.008
 waving-0.008
 spinning-0.007
 neighborhood-0.007
Token Suddenly
Token ID24975
Feature activation+4.89e-03

Pos logit contributions
burn+0.010
 waving+0.010
 blowing+0.009
 neighborhood+0.009
 driveway+0.009
Neg logit contributions
 ounces-0.023
ils-0.022
hell-0.021
izards-0.021
bors-0.021
Token,
Token ID11
Feature activation-1.46e-01

Pos logit contributions
 ounces+0.000
ils+0.000
hell+0.000
affe+0.000
izards+0.000
Neg logit contributions
 waving-0.000
burn-0.000
 blowing-0.000
 daddy-0.000
 spinning-0.000
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
burn+0.003
 waving+0.003
 blowing+0.003
 daddy+0.003
 spinning+0.003
Neg logit contributions
 ounces-0.005
ils-0.004
affe-0.004
hell-0.004
bors-0.004
Token train
Token ID4512
Feature activation+6.68e-01

Pos logit contributions
burn+0.028
 waving+0.026
 blowing+0.026
 spinning+0.023
 neighborhood+0.023
Neg logit contributions
 ounces-0.042
ils-0.038
izards-0.038
bors-0.037
affe-0.037
Token made
Token ID925
Feature activation+1.23e+00

Pos logit contributions
 ounces+0.023
ils+0.021
affe+0.021
bors+0.021
izards+0.020
Neg logit contributions
burn-0.015
 blowing-0.013
 waving-0.013
 spinning-0.011
 neighborhood-0.011
Token a
Token ID257
Feature activation-3.52e-01

Pos logit contributions
 ounces+0.044
ils+0.040
izards+0.040
affe+0.039
hell+0.038
Neg logit contributions
burn-0.026
 blowing-0.025
 waving-0.024
 spinning-0.021
 daddy-0.021
Token bad
Token ID2089
Feature activation+1.32e+00

Pos logit contributions
burn+0.009
 blowing+0.008
 waving+0.007
 neighborhood+0.007
my+0.007
Neg logit contributions
 ounces-0.011
affe-0.010
hell-0.010
bors-0.010
isy-0.010
Token noise
Token ID7838
Feature activation+7.03e-01

Pos logit contributions
 ounces+0.041
ils+0.037
affe+0.037
izards+0.037
bors+0.036
Neg logit contributions
burn-0.034
 blowing-0.030
 waving-0.030
 neighborhood-0.027
 spinning-0.027
Token lying
Token ID9105
Feature activation-2.84e+00

Pos logit contributions
 waving+0.023
burn+0.022
 blowing+0.022
 crying+0.020
 spinning+0.020
Neg logit contributions
 ounces-0.055
affe-0.051
bors-0.049
ils-0.048
hell-0.047
Token.
Token ID13
Feature activation+1.61e-01

Pos logit contributions
burn+0.050
 blowing+0.045
 waving+0.044
 crying+0.038
 spinning+0.037
Neg logit contributions
 ounces-0.113
bors-0.104
izards-0.103
affe-0.102
ils-0.101
Token "
Token ID366
Feature activation+6.50e-01

Pos logit contributions
 ounces+0.007
ils+0.006
izards+0.006
bors+0.006
hell+0.006
Neg logit contributions
burn-0.002
 waving-0.002
my-0.002
 window-0.002
 daddy-0.002
TokenL
Token ID43
Feature activation+2.30e+00

Pos logit contributions
 ounces+0.023
ils+0.021
izards+0.021
affe+0.021
bors+0.021
Neg logit contributions
burn-0.014
 blowing-0.012
 waving-0.012
 spinning-0.011
 neighborhood-0.011
Tokenily
Token ID813
Feature activation-6.65e-01

Pos logit contributions
 ounces+0.042
bors+0.031
ns+0.030
affe+0.030
keys+0.028
Neg logit contributions
my-0.085
burn-0.085
 blowing-0.079
 crying-0.079
 spinning-0.078
Token,
Token ID11
Feature activation-9.23e-01

Pos logit contributions
burn+0.011
 waving+0.010
 blowing+0.010
 crying+0.009
my+0.009
Neg logit contributions
 ounces-0.027
izards-0.024
bors-0.024
ils-0.024
affe-0.024
Token I
Token ID314
Feature activation-1.35e+00

Pos logit contributions
burn+0.025
 blowing+0.023
 waving+0.023
 daddy+0.022
 spinning+0.022
Neg logit contributions
 ounces-0.028
ils-0.025
affe-0.025
bors-0.025
izards-0.024
Token know
Token ID760
Feature activation+9.47e-01

Pos logit contributions
burn+0.035
 blowing+0.032
 waving+0.031
 driveway+0.028
 leaning+0.028
Neg logit contributions
 ounces-0.042
izards-0.038
ils-0.038
hell-0.037
affe-0.037
Token you
Token ID345
Feature activation+2.06e+00

Pos logit contributions
 ounces+0.032
affe+0.030
bors+0.028
hell+0.028
ils+0.028
Neg logit contributions
 waving-0.021
burn-0.020
 blowing-0.020
 daddy-0.020
 spinning-0.019
Token hid
Token ID24519
Feature activation-7.64e-01

Pos logit contributions
 ounces+0.077
bors+0.070
affe+0.070
isy+0.065
ils+0.065
Neg logit contributions
burn-0.038
 waving-0.036
my-0.035
 blowing-0.035
 daddy-0.032
Token it
Token ID340
Feature activation+1.58e+00

Pos logit contributions
burn+0.013
 blowing+0.013
 waving+0.013
 spinning+0.012
 daddy+0.012
Neg logit contributions
 ounces-0.029
affe-0.028
bors-0.027
hell-0.026
isy-0.026
Token.
Token ID13
Feature activation-4.69e-02

Pos logit contributions
 ounces+0.054
ils+0.048
izards+0.048
affe+0.048
bors+0.048
Neg logit contributions
burn-0.033
 blowing-0.030
 waving-0.030
 spinning-0.026
 leaning-0.025
Token She
Token ID1375
Feature activation+1.13e+00

Pos logit contributions
burn+0.001
 blowing+0.001
 waving+0.001
 spinning+0.001
 neighborhood+0.001
Neg logit contributions
 ounces-0.002
ils-0.001
izards-0.001
affe-0.001
bors-0.001
Token wished
Token ID16555
Feature activation+8.47e-01

Pos logit contributions
 ounces+0.038
ils+0.035
affe+0.034
izards+0.034
bors+0.034
Neg logit contributions
burn-0.026
 blowing-0.023
 waving-0.023
 spinning-0.020
 driveway-0.020
Token they
Token ID484
Feature activation+1.49e+00

Pos logit contributions
 ounces+0.026
izards+0.023
ils+0.023
bors+0.023
affe+0.023
Neg logit contributions
burn-0.023
 blowing-0.020
 waving-0.020
 driveway-0.018
 neighborhood-0.018
Token could
Token ID714
Feature activation-2.90e+00

Pos logit contributions
 ounces+0.055
affe+0.050
bors+0.050
izards+0.049
ils+0.048
Neg logit contributions
burn-0.030
 waving-0.028
 blowing-0.027
my-0.024
 spinning-0.024
Token stay
Token ID2652
Feature activation-4.56e-01

Pos logit contributions
burn+0.068
 blowing+0.063
 waving+0.060
 crying+0.054
 neighborhood+0.053
Neg logit contributions
 ounces-0.094
affe-0.085
izards-0.084
ils-0.083
hell-0.083
Token forever
Token ID8097
Feature activation+5.89e-01

Pos logit contributions
burn+0.010
 blowing+0.009
 waving+0.009
 driveway+0.008
 crying+0.008
Neg logit contributions
 ounces-0.015
ils-0.014
izards-0.014
bors-0.014
hell-0.014
Token.
Token ID13
Feature activation+5.24e-01

Pos logit contributions
 ounces+0.020
ils+0.019
affe+0.018
izards+0.018
bors+0.018
Neg logit contributions
burn-0.013
 blowing-0.012
 waving-0.012
 spinning-0.010
 neighborhood-0.010
Token But
Token ID887
Feature activation+1.29e+00

Pos logit contributions
 ounces+0.017
ils+0.016
izards+0.016
bors+0.016
affe+0.016
Neg logit contributions
burn-0.012
 waving-0.011
 blowing-0.011
 neighborhood-0.010
 daddy-0.010
Token Molly
Token ID30236
Feature activation+5.88e-01

Pos logit contributions
 ounces+0.040
ils+0.036
izards+0.036
bors+0.036
affe+0.035
Neg logit contributions
burn-0.033
 blowing-0.029
 waving-0.029
 driveway-0.026
 neighborhood-0.026
Token's
Token ID338
Feature activation-2.42e+00

Pos logit contributions
 ounces+0.023
izards+0.021
hell+0.020
ils+0.020
bors+0.020
Neg logit contributions
burn-0.011
 waving-0.010
 blowing-0.010
 neighborhood-0.008
 crying-0.008
Token.
Token ID13
Feature activation-6.76e-01

Pos logit contributions
 ounces+0.002
bors+0.002
hell+0.002
affe+0.002
ils+0.002
Neg logit contributions
burn-0.001
 blowing-0.001
 waving-0.001
 spinning-0.001
 crying-0.001
Token We
Token ID775
Feature activation-1.88e-02

Pos logit contributions
burn+0.016
 waving+0.014
 blowing+0.014
my+0.013
 daddy+0.013
Neg logit contributions
ils-0.022
 ounces-0.021
hell-0.020
izards-0.019
isy-0.019
Token should
Token ID815
Feature activation-1.24e+00

Pos logit contributions
burn+0.000
 blowing+0.000
 waving+0.000
my+0.000
 frown+0.000
Neg logit contributions
 ounces-0.001
bors-0.001
affe-0.001
hell-0.001
izards-0.001
Token respect
Token ID2461
Feature activation-2.33e+00

Pos logit contributions
burn+0.027
 blowing+0.024
 waving+0.024
 spinning+0.021
 neighborhood+0.020
Neg logit contributions
 ounces-0.044
ils-0.040
izards-0.039
affe-0.039
bors-0.039
Token all
Token ID477
Feature activation-1.41e+00

Pos logit contributions
burn+0.049
 blowing+0.047
 waving+0.045
 daddy+0.040
my+0.039
Neg logit contributions
 ounces-0.082
affe-0.074
izards-0.074
hell-0.074
bors-0.073
Token living
Token ID2877
Feature activation-3.87e+00

Pos logit contributions
 blowing+0.030
burn+0.028
 waving+0.028
my+0.025
 spinning+0.024
Neg logit contributions
 ounces-0.050
izards-0.045
affe-0.045
ils-0.044
hell-0.044
Token things
Token ID1243
Feature activation-8.83e-01

Pos logit contributions
burn+0.087
 blowing+0.086
 waving+0.084
 crying+0.076
 daddy+0.076
Neg logit contributions
 ounces-0.126
affe-0.121
hell-0.113
izards-0.113
isy-0.111
Token."
Token ID526
Feature activation+1.51e+00

Pos logit contributions
burn+0.018
 blowing+0.018
 waving+0.017
 spinning+0.014
 daddy+0.014
Neg logit contributions
 ounces-0.032
affe-0.029
bors-0.029
izards-0.028
ils-0.028
Token
Token ID198
Feature activation+4.84e-01

Pos logit contributions
 ounces+0.073
ils+0.071
izards+0.069
bors+0.068
affe+0.066
Neg logit contributions
burn-0.012
my-0.009
 daddy-0.009
 waving-0.009
 crying-0.008
Token
Token ID198
Feature activation+1.12e+00

Pos logit contributions
 ounces+0.021
ils+0.020
izards+0.019
affe+0.019
bors+0.019
Neg logit contributions
burn-0.006
 blowing-0.005
 waving-0.005
 neighborhood-0.004
 daddy-0.004
TokenL
Token ID43
Feature activation+2.18e+00

Pos logit contributions
 ounces+0.045
izards+0.045
ocket+0.042
ils+0.042
imes+0.041
Neg logit contributions
my-0.016
burn-0.015
 neighborhood-0.014
 daddy-0.014
 blowing-0.013
Token knock
Token ID10643
Feature activation-1.80e-01

Pos logit contributions
burn+0.024
 blowing+0.021
 waving+0.021
 neighborhood+0.019
 driveway+0.019
Neg logit contributions
 ounces-0.039
affe-0.035
ils-0.035
hell-0.035
bors-0.035
Token him
Token ID683
Feature activation+1.79e+00

Pos logit contributions
burn+0.004
 waving+0.004
 blowing+0.004
 spinning+0.004
 daddy+0.004
Neg logit contributions
 ounces-0.006
affe-0.006
bors-0.005
ils-0.005
izards-0.005
Token down
Token ID866
Feature activation+9.75e-01

Pos logit contributions
 ounces+0.079
bors+0.074
ils+0.073
affe+0.073
izards+0.072
Neg logit contributions
burn-0.025
 waving-0.020
 blowing-0.019
my-0.015
 spinning-0.015
Token.
Token ID13
Feature activation-1.27e+00

Pos logit contributions
 ounces+0.037
bors+0.035
isy+0.034
ils+0.034
affe+0.033
Neg logit contributions
burn-0.018
 waving-0.017
 window-0.016
 blowing-0.015
 asleep-0.015
Token How
Token ID1374
Feature activation+4.36e+00

Pos logit contributions
burn+0.031
 waving+0.029
 blowing+0.027
 daddy+0.027
 crying+0.026
Neg logit contributions
 ounces-0.039
ils-0.039
bors-0.036
izards-0.036
hell-0.036
Token about
Token ID546
Feature activation-2.73e+00

Pos logit contributions
 ounces+0.156
bors+0.141
ils+0.141
affe+0.134
izards+0.133
Neg logit contributions
burn-0.089
 blowing-0.081
 waving-0.079
 daddy-0.075
my-0.075
Token I
Token ID314
Feature activation-1.84e-01

Pos logit contributions
burn+0.067
 waving+0.063
 blowing+0.062
 daddy+0.060
 crying+0.056
Neg logit contributions
 ounces-0.089
hell-0.084
ils-0.083
affe-0.082
izards-0.080
Token move
Token ID1445
Feature activation-1.63e+00

Pos logit contributions
burn+0.004
 blowing+0.004
 waving+0.004
 neighborhood+0.003
 driveway+0.003
Neg logit contributions
 ounces-0.006
ils-0.005
izards-0.005
affe-0.005
hell-0.005
Token him
Token ID683
Feature activation+2.01e-02

Pos logit contributions
burn+0.032
 blowing+0.028
 waving+0.028
 daddy+0.024
 spinning+0.024
Neg logit contributions
 ounces-0.062
ils-0.056
affe-0.056
bors-0.056
izards-0.056
Token to
Token ID284
Feature activation+4.27e-01

Pos logit contributions
 ounces+0.001
ils+0.001
izards+0.001
affe+0.001
bors+0.001
Neg logit contributions
burn-0.000
 blowing-0.000
 waving-0.000
 spinning-0.000
 driveway-0.000
Token a
Token ID257
Feature activation-7.26e-01

Pos logit contributions
 ounces+0.014
ils+0.013
izards+0.013
affe+0.013
bors+0.013
Neg logit contributions
burn-0.010
 waving-0.009
 blowing-0.009
 spinning-0.008
 daddy-0.008
Token well
Token ID880
Feature activation+1.35e+00

Pos logit contributions
burn+0.031
 blowing+0.029
 waving+0.028
 spinning+0.025
 crying+0.024
Neg logit contributions
 ounces-0.048
affe-0.043
bors-0.043
ils-0.043
izards-0.042
Token.
Token ID13
Feature activation-5.30e-01

Pos logit contributions
 ounces+0.048
affe+0.044
bors+0.044
ils+0.043
izards+0.043
Neg logit contributions
burn-0.030
 blowing-0.027
 waving-0.026
 spinning-0.023
 crying-0.023
Token Tim
Token ID5045
Feature activation-2.27e+00

Pos logit contributions
burn+0.011
 blowing+0.010
 waving+0.010
 spinning+0.008
 daddy+0.008
Neg logit contributions
 ounces-0.019
affe-0.018
hell-0.017
izards-0.017
bors-0.017
Tokenmy
Token ID1820
Feature activation-2.88e+00

Pos logit contributions
burn+0.032
 waving+0.031
 blowing+0.029
 spinning+0.024
 typing+0.024
Neg logit contributions
 ounces-0.088
ils-0.086
affe-0.085
isy-0.083
hell-0.083
Token's
Token ID338
Feature activation-2.17e+00

Pos logit contributions
burn+0.068
 blowing+0.061
 waving+0.061
 spinning+0.053
 driveway+0.053
Neg logit contributions
 ounces-0.096
ils-0.087
affe-0.086
bors-0.086
izards-0.086
Token mom
Token ID1995
Feature activation-4.41e+00

Pos logit contributions
burn+0.054
 blowing+0.047
 leaning+0.043
my+0.042
 typing+0.040
Neg logit contributions
 ounces-0.060
affe-0.058
ily-0.055
izards-0.055
isy-0.055
Token was
Token ID373
Feature activation-1.22e+00

Pos logit contributions
burn+0.105
 waving+0.091
 blowing+0.088
 driveway+0.087
seat+0.084
Neg logit contributions
ils-0.132
 ounces-0.132
isy-0.128
affe-0.126
bors-0.124
Token not
Token ID407
Feature activation-3.66e+00

Pos logit contributions
burn+0.029
 driveway+0.025
seat+0.023
 blowing+0.022
my+0.022
Neg logit contributions
 ounces-0.036
izards-0.034
ily-0.034
ils-0.034
bors-0.033
Token around
Token ID1088
Feature activation-3.00e+00

Pos logit contributions
burn+0.086
 blowing+0.074
 waving+0.073
 driveway+0.069
 neighborhood+0.067
Neg logit contributions
 ounces-0.120
izards-0.109
ils-0.108
hell-0.107
bors-0.106
Token,
Token ID11
Feature activation-1.30e+00

Pos logit contributions
burn+0.076
 blowing+0.066
 waving+0.066
 driveway+0.060
 neighborhood+0.059
Neg logit contributions
 ounces-0.096
izards-0.086
ils-0.085
bors-0.084
hell-0.084
Token so
Token ID523
Feature activation+2.52e+00

Pos logit contributions
burn+0.031
 blowing+0.028
 waving+0.028
 spinning+0.025
 crying+0.024
Neg logit contributions
 ounces-0.044
ils-0.040
izards-0.039
affe-0.039
bors-0.039
Tokenmy
Token ID1820
Feature activation-2.78e+00

Pos logit contributions
 waving+0.036
burn+0.035
 blowing+0.034
 spinning+0.028
 cheering+0.027
Neg logit contributions
 ounces-0.088
affe-0.087
ils-0.085
hell-0.084
isy-0.083
Token realized
Token ID6939
Feature activation+1.77e+00

Pos logit contributions
burn+0.073
 blowing+0.066
 waving+0.065
 spinning+0.058
 driveway+0.056
Neg logit contributions
 ounces-0.083
ils-0.077
affe-0.075
bors-0.074
izards-0.073
Token he
Token ID339
Feature activation+3.46e-01

Pos logit contributions
 ounces+0.052
ils+0.046
affe+0.045
izards+0.045
bors+0.045
Neg logit contributions
burn-0.050
 blowing-0.046
 waving-0.046
 spinning-0.041
 daddy-0.041
Token lost
Token ID2626
Feature activation-1.70e+00

Pos logit contributions
 ounces+0.012
ils+0.011
izards+0.011
affe+0.011
bors+0.011
Neg logit contributions
burn-0.008
 blowing-0.007
 waving-0.007
 spinning-0.006
 driveway-0.006
Token his
Token ID465
Feature activation-1.33e+00

Pos logit contributions
burn+0.041
 blowing+0.037
 waving+0.036
 spinning+0.032
 neighborhood+0.031
Neg logit contributions
 ounces-0.057
ils-0.051
affe-0.051
izards-0.051
bors-0.051
Token favorite
Token ID4004
Feature activation-2.94e+00

Pos logit contributions
burn+0.034
 blowing+0.029
 waving+0.028
 cheering+0.026
my+0.026
Neg logit contributions
 ounces-0.040
hell-0.034
affe-0.034
aces-0.033
ger-0.032
Token toy
Token ID13373
Feature activation-8.00e-01

Pos logit contributions
burn+0.059
 blowing+0.053
 waving+0.051
 spinning+0.043
 driveway+0.043
Neg logit contributions
 ounces-0.108
ils-0.098
affe-0.097
hell-0.096
izards-0.096
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
burn+0.018
 blowing+0.016
 waving+0.016
 spinning+0.014
 daddy+0.014
Neg logit contributions
 ounces-0.028
ils-0.025
bors-0.025
izards-0.025
affe-0.025
Token He
Token ID679
Feature activation-1.13e-02

Pos logit contributions
burn+0.002
 waving+0.002
 blowing+0.002
 daddy+0.002
 crying+0.002
Neg logit contributions
 ounces-0.004
ils-0.004
izards-0.003
bors-0.003
isy-0.003
Token looked
Token ID3114
Feature activation-4.58e-01

Pos logit contributions
burn+0.000
 blowing+0.000
 waving+0.000
 spinning+0.000
 neighborhood+0.000
Neg logit contributions
 ounces-0.000
ils-0.000
izards-0.000
affe-0.000
bors-0.000
Token and
Token ID290
Feature activation-6.18e-01

Pos logit contributions
burn+0.009
 blowing+0.008
 waving+0.008
 driveway+0.007
 neighborhood+0.007
Neg logit contributions
 ounces-0.017
ils-0.016
izards-0.015
hell-0.015
affe-0.015
Token sees
Token ID7224
Feature activation+1.53e+00

Pos logit contributions
burn+0.019
 blowing+0.016
 waving+0.014
 neighborhood+0.012
 driveway+0.012
Neg logit contributions
 ounces-0.034
izards-0.031
ils-0.031
bors-0.031
affe-0.030
Token a
Token ID257
Feature activation-7.23e-01

Pos logit contributions
 ounces+0.056
ils+0.051
bors+0.051
affe+0.050
izards+0.050
Neg logit contributions
burn-0.031
 blowing-0.028
 waving-0.028
 crying-0.025
 daddy-0.024
Token squirrel
Token ID33039
Feature activation+1.99e-01

Pos logit contributions
burn+0.019
 blowing+0.017
 waving+0.016
 driveway+0.015
 vac+0.015
Neg logit contributions
 ounces-0.021
affe-0.020
hell-0.019
isy-0.018
bors-0.018
Token.
Token ID13
Feature activation-8.37e-01

Pos logit contributions
 ounces+0.007
ils+0.006
bors+0.006
affe+0.006
izards+0.006
Neg logit contributions
burn-0.005
 waving-0.004
 blowing-0.004
 spinning-0.004
 crying-0.004
Token She
Token ID1375
Feature activation+1.12e+00

Pos logit contributions
burn+0.016
 waving+0.015
 blowing+0.014
 crying+0.013
 daddy+0.013
Neg logit contributions
 ounces-0.031
ils-0.030
bors-0.029
isy-0.028
izards-0.028
Token smiles
Token ID21845
Feature activation-3.67e+00

Pos logit contributions
 ounces+0.035
izards+0.033
affe+0.032
ils+0.031
bors+0.031
Neg logit contributions
burn-0.031
 blowing-0.026
 driveway-0.023
 waving-0.023
 daddy-0.023
Token and
Token ID290
Feature activation-6.15e-01

Pos logit contributions
burn+0.098
 blowing+0.085
 driveway+0.084
 waving+0.080
 neighborhood+0.077
Neg logit contributions
 ounces-0.102
izards-0.097
ils-0.096
affe-0.096
hell-0.093
Token says
Token ID1139
Feature activation+2.44e+00

Pos logit contributions
burn+0.016
 blowing+0.014
 waving+0.013
 driveway+0.013
 neighborhood+0.013
Neg logit contributions
 ounces-0.019
izards-0.017
ils-0.017
affe-0.017
bors-0.016
Token hello
Token ID23748
Feature activation+4.00e-01

Pos logit contributions
 ounces+0.098
ils+0.088
bors+0.087
affe+0.084
ns+0.084
Neg logit contributions
 waving-0.041
burn-0.038
 blowing-0.036
 crying-0.035
 spinning-0.034
Token to
Token ID284
Feature activation+5.94e-01

Pos logit contributions
 ounces+0.015
ils+0.013
bors+0.013
izards+0.013
affe+0.013
Neg logit contributions
burn-0.009
 waving-0.008
 blowing-0.007
 crying-0.007
 daddy-0.006
Token the
Token ID262
Feature activation-5.14e-01

Pos logit contributions
 ounces+0.023
ils+0.021
hell+0.021
izards+0.020
bors+0.020
Neg logit contributions
burn-0.011
 waving-0.010
 blowing-0.010
 crying-0.009
 daddy-0.009