TOP ACTIVATIONS
MAX = 4.600

. " Tom my , what 's wrong ?"
lot . She missed her mug and her pretty flowers didn
from the sunshine . Suddenly , he heard a
, " Wow , you boys did a great job decor
hard and had no eyes or nose . Lily thought it
the sunshine . Suddenly , he heard a soft
" Tom and Sam , what are you doing
an unfamiliar forest . Will tried his best to
The mouse lived in the diary for a long time ,
be found . Suddenly , he heard a little
be dangerous ". James understood the message and
" L ily and Tom , how could you be
" L ily and Sam , you need to share
the room . " Hi girls , how 's the puzzle
said , " Tom and Sam , you were very naughty
was very bright . James ran around the garden
happy that he hugged his robot toy and played with it
't stand it . One day , James 's
and said , " Look Max , I found my bow
and said , " Mom my , boat broke . Can

MIN ACTIVATIONS
MIN = -4.824

the pool . She let go of her unicorn and ran
. They sit on each end . They push with their
fish . They wanted to go closer and feed them .
down . Lily wanted to go closer and see the water
swing . Tom wants to go on the swing . He
Tom and Sam want to go near the pond and feed
ducks . Rex wants to go too . He likes water
likes it . He lets go of the car and reaches
it . Lily wanted to go on the water in a
plant and each grab one end of the squash . They
think we can find the end of the rainbow ?" Lily
slide . Sara wants to go first . She runs to
big slide and wanted to go on it . She left
big slide and wanted to go on it . She asked
, then took the other end and ran away , gigg
. Do you want to go high ?" L
and Coco holds the other end . Coco is smart and
slide . Ben wants to go on the slide . He
's go and find the end of it . Maybe there
big slide and wanted to go on it . She ran

INTERVAL 2.244 - 4.600
CONTAINS 0.491%

starting to feel cold . Then she saw a gentleman walking
" Oh , Ben , you have a high temperature .
L ily hugged her doll and smiled back , feeling
had a toy soldier in his hand . Tim my wanted
bath . He loved his robot very much .

INTERVAL -0.112 - 2.244
CONTAINS 55.656%

he could and finally got away . He decided to stick
A puppy suddenly appeared from the ground . Lori was so
found it while they were out playing . The children had
. <|endoftext|> Once upon a time , there was a spoiled
looking after him . They both gl owed in the sun

INTERVAL -2.468 - -0.112
CONTAINS 43.455%

be two coins ." L ila and Ben look at their
little girl who wanted to go sailing . She asked her
helps him drink the water . They are proud of their
. Tom ran to the slide , and Lily followed him
mother and stayed put . The mother made the

INTERVAL -4.824 - -2.468
CONTAINS 0.398%

what happened . Their mom hugged them and said , "
. She said they could go to the park , and
you want . Let 's go to the couch and sn
, There now . All better
said . " Let 's go closer and touch it ."
Token.
Token ID13
Feature activation+1.38e-01

Pos logit contributions
 diary+0.057
 shield+0.056
oc+0.055
es+0.051
 journal+0.051
Neg logit contributions
oe-0.041
aa-0.039
oes-0.037
Kids-0.033
round-0.032
Token
Token ID198
Feature activation-7.86e-02

Pos logit contributions
 diary+0.003
 shield+0.003
oc+0.003
es+0.003
house+0.003
Neg logit contributions
aa-0.005
oe-0.005
oes-0.005
Kids-0.005
ora-0.004
Token
Token ID198
Feature activation+1.66e+00

Pos logit contributions
aa+0.003
oes+0.002
oe+0.002
round+0.002
Kids+0.002
Neg logit contributions
oc-0.002
es-0.002
 diary-0.002
 shield-0.002
house-0.002
Token"
Token ID1
Feature activation+7.52e-01

Pos logit contributions
 diary+0.050
 shield+0.050
oc+0.048
es+0.048
house+0.044
Neg logit contributions
aa-0.049
oe-0.046
Kids-0.046
oes-0.045
round-0.042
TokenTom
Token ID13787
Feature activation+2.23e+00

Pos logit contributions
 diary+0.026
 shield+0.025
es+0.025
oc+0.024
 journal+0.023
Neg logit contributions
aa-0.019
Kids-0.019
oe-0.019
oes-0.018
round-0.017
Tokenmy
Token ID1820
Feature activation+4.14e+00

Pos logit contributions
 diary+0.089
 shield+0.088
es+0.085
oc+0.084
 shields+0.084
Neg logit contributions
aa-0.045
oe-0.044
oes-0.040
Kids-0.036
round-0.032
Token,
Token ID11
Feature activation+1.64e+00

Pos logit contributions
 diary+0.145
 shield+0.144
 shields+0.144
istered+0.136
onel+0.135
Neg logit contributions
aa-0.105
oe-0.100
oes-0.082
 to-0.080
 sur-0.076
Token what
Token ID644
Feature activation+9.32e-01

Pos logit contributions
es+0.055
oc+0.055
istered+0.051
 diary+0.050
 shields+0.050
Neg logit contributions
Kids-0.041
aa-0.041
oe-0.037
oes-0.036
 Su-0.036
Token's
Token ID338
Feature activation-3.55e-01

Pos logit contributions
oc+0.028
 shield+0.027
 diary+0.027
 webs+0.026
 Majesty+0.026
Neg logit contributions
aa-0.026
Kids-0.025
oes-0.025
oe-0.024
 sur-0.022
Token wrong
Token ID2642
Feature activation+1.35e+00

Pos logit contributions
aa+0.011
oe+0.011
oes+0.010
Kids+0.010
 sur+0.010
Neg logit contributions
oc-0.011
es-0.010
 shield-0.009
 diary-0.009
house-0.009
Token?"
Token ID1701
Feature activation-7.58e-02

Pos logit contributions
 diary+0.039
 shield+0.039
es+0.038
oc+0.037
 shields+0.035
Neg logit contributions
aa-0.042
oe-0.041
Kids-0.039
oes-0.038
round-0.036
Token lot
Token ID1256
Feature activation-3.61e-01

Pos logit contributions
es+0.054
 diary+0.050
 shield+0.049
house+0.048
oc+0.047
Neg logit contributions
aa-0.050
oe-0.045
Kids-0.043
oes-0.041
round-0.039
Token.
Token ID13
Feature activation+1.66e+00

Pos logit contributions
aa+0.010
oe+0.010
Kids+0.009
oes+0.009
round+0.009
Neg logit contributions
 diary-0.011
 shield-0.011
es-0.011
oc-0.011
 journal-0.010
Token She
Token ID1375
Feature activation+1.60e+00

Pos logit contributions
 shield+0.062
es+0.059
 diary+0.058
oc+0.058
 shields+0.057
Neg logit contributions
aa-0.039
Kids-0.037
oe-0.036
oes-0.036
round-0.031
Token missed
Token ID6825
Feature activation+2.97e-01

Pos logit contributions
es+0.053
 diary+0.053
 shield+0.052
oc+0.052
vel+0.050
Neg logit contributions
aa-0.039
Kids-0.038
oe-0.035
oes-0.032
 crowded-0.030
Token her
Token ID607
Feature activation+2.46e-01

Pos logit contributions
 shield+0.010
 diary+0.010
es+0.009
oc+0.009
 shields+0.009
Neg logit contributions
aa-0.008
oe-0.008
Kids-0.008
oes-0.007
round-0.007
Token mug
Token ID25152
Feature activation+4.10e+00

Pos logit contributions
oc+0.008
es+0.008
 shield+0.007
vel+0.007
onel+0.007
Neg logit contributions
aa-0.007
oe-0.007
Kids-0.006
oes-0.006
 weekend-0.006
Token and
Token ID290
Feature activation+1.89e+00

Pos logit contributions
 Majesty+0.174
oc+0.172
es+0.161
istered+0.159
vel+0.159
Neg logit contributions
 to-0.062
oe-0.061
aa-0.052
oes-0.047
 slowly-0.041
Token her
Token ID607
Feature activation+8.92e-01

Pos logit contributions
oc+0.073
vel+0.070
es+0.066
istered+0.065
 diary+0.063
Neg logit contributions
Kids-0.037
aa-0.036
 to-0.035
 Su-0.032
 Kay-0.031
Token pretty
Token ID2495
Feature activation+1.45e-01

Pos logit contributions
oc+0.033
es+0.031
vel+0.029
 shield+0.028
onel+0.027
Neg logit contributions
aa-0.021
oe-0.021
Kids-0.019
 weekend-0.018
oes-0.018
Token flowers
Token ID12734
Feature activation+1.82e+00

Pos logit contributions
oc+0.005
 shield+0.005
es+0.004
onel+0.004
 diary+0.004
Neg logit contributions
oe-0.004
aa-0.004
oes-0.004
Kids-0.003
round-0.003
Token didn
Token ID1422
Feature activation+3.90e-01

Pos logit contributions
oc+0.062
 diary+0.060
 shield+0.060
 Majesty+0.058
es+0.057
Neg logit contributions
oe-0.044
aa-0.043
oes-0.040
Kids-0.037
ho-0.035
Token from
Token ID422
Feature activation+8.19e-01

Pos logit contributions
 diary+0.033
oc+0.033
 shield+0.032
es+0.032
 shields+0.030
Neg logit contributions
aa-0.027
oe-0.026
oes-0.025
Kids-0.024
round-0.023
Token the
Token ID262
Feature activation-2.15e-01

Pos logit contributions
es+0.027
 diary+0.027
 shield+0.026
oc+0.026
vel+0.024
Neg logit contributions
oe-0.021
aa-0.021
oes-0.019
Kids-0.019
round-0.018
Token sunshine
Token ID34488
Feature activation-4.72e-01

Pos logit contributions
aa+0.006
oe+0.006
Kids+0.006
oes+0.005
round+0.005
Neg logit contributions
 shield-0.007
 diary-0.007
es-0.006
oc-0.006
 journal-0.006
Token.
Token ID13
Feature activation+1.88e+00

Pos logit contributions
aa+0.015
Kids+0.015
oe+0.015
oes+0.014
round+0.013
Neg logit contributions
 shield-0.013
 diary-0.013
es-0.013
oc-0.012
 journal-0.011
Token
Token ID198
Feature activation+1.20e+00

Pos logit contributions
 shield+0.069
 diary+0.068
es+0.066
oc+0.066
onel+0.064
Neg logit contributions
Kids-0.042
oe-0.041
aa-0.040
oes-0.039
round-0.036
Token
Token ID198
Feature activation+4.05e+00

Pos logit contributions
 diary+0.040
 shield+0.040
es+0.039
oc+0.038
 shields+0.036
Neg logit contributions
aa-0.031
oe-0.030
Kids-0.029
oes-0.028
round-0.026
TokenSuddenly
Token ID38582
Feature activation+3.99e+00

Pos logit contributions
 shield+0.148
 diary+0.147
es+0.141
onel+0.140
 Majesty+0.138
Neg logit contributions
Kids-0.091
oe-0.086
round-0.078
aa-0.071
 weekend-0.070
Token,
Token ID11
Feature activation+2.89e+00

Pos logit contributions
oc+0.170
onel+0.168
istered+0.167
 Majesty+0.161
 diary+0.160
Neg logit contributions
oe-0.066
 to-0.064
aa-0.050
 Kay-0.046
guard-0.040
Token he
Token ID339
Feature activation+1.38e+00

Pos logit contributions
oc+0.112
 Majesty+0.108
onel+0.107
istered+0.101
 web+0.100
Neg logit contributions
oe-0.059
 to-0.058
 weekend-0.054
 crowded-0.051
Kids-0.050
Token heard
Token ID2982
Feature activation+2.57e+00

Pos logit contributions
 diary+0.047
 shield+0.046
oc+0.046
es+0.044
 journal+0.042
Neg logit contributions
aa-0.035
oe-0.033
Kids-0.032
oes-0.030
 sur-0.028
Token a
Token ID257
Feature activation+7.46e-01

Pos logit contributions
oc+0.073
 diary+0.071
istered+0.070
es+0.069
 shield+0.069
Neg logit contributions
aa-0.074
Kids-0.072
oe-0.068
 Kay-0.067
oes-0.066
Token,
Token ID11
Feature activation-8.89e-01

Pos logit contributions
 diary+0.020
 shield+0.020
oc+0.019
es+0.019
 shields+0.018
Neg logit contributions
aa-0.023
oe-0.023
Kids-0.022
oes-0.021
round-0.020
Token "
Token ID366
Feature activation-1.15e+00

Pos logit contributions
aa+0.034
oe+0.034
oes+0.034
Kids+0.033
ora+0.032
Neg logit contributions
es-0.019
 shield-0.018
 diary-0.018
oc-0.017
 Mickey-0.015
TokenWow
Token ID22017
Feature activation+2.66e+00

Pos logit contributions
aa+0.037
oe+0.035
oes+0.033
 sur+0.031
round+0.031
Neg logit contributions
oc-0.031
 diary-0.029
es-0.029
 shield-0.028
house-0.028
Token,
Token ID11
Feature activation-1.35e-01

Pos logit contributions
oc+0.109
 diary+0.107
 shield+0.104
 shields+0.102
 traps+0.102
Neg logit contributions
oe-0.056
aa-0.050
 Su-0.039
 to-0.039
 Kay-0.036
Token you
Token ID345
Feature activation+2.87e+00

Pos logit contributions
aa+0.004
Kids+0.004
oe+0.004
oes+0.003
 Kay+0.003
Neg logit contributions
es-0.004
 diary-0.004
oc-0.004
 shield-0.004
istered-0.004
Token boys
Token ID6510
Feature activation+4.04e+00

Pos logit contributions
 shield+0.103
 diary+0.099
oc+0.096
 traps+0.094
 shields+0.093
Neg logit contributions
oe-0.066
aa-0.062
Kids-0.058
 crowded-0.053
 sur-0.053
Token did
Token ID750
Feature activation+1.02e+00

Pos logit contributions
 shield+0.123
 diary+0.117
 shields+0.113
oc+0.111
es+0.106
Neg logit contributions
oe-0.126
aa-0.123
oes-0.110
Kids-0.109
round-0.104
Token a
Token ID257
Feature activation+1.21e+00

Pos logit contributions
oc+0.041
onel+0.040
es+0.040
 shield+0.039
 diary+0.038
Neg logit contributions
oe-0.020
 to-0.019
 Kay-0.017
 Su-0.017
 weekend-0.015
Token great
Token ID1049
Feature activation+1.53e-01

Pos logit contributions
es+0.041
 diary+0.036
 shield+0.036
oc+0.035
onel+0.035
Neg logit contributions
oe-0.031
aa-0.030
Kids-0.028
 sur-0.028
 weekend-0.027
Token job
Token ID1693
Feature activation-3.01e-01

Pos logit contributions
 shield+0.004
es+0.004
 diary+0.004
 shields+0.004
onel+0.004
Neg logit contributions
aa-0.005
oe-0.005
oes-0.004
Kids-0.004
round-0.004
Token decor
Token ID11705
Feature activation+4.39e-01

Pos logit contributions
aa+0.011
Kids+0.010
oe+0.010
oes+0.010
round+0.009
Neg logit contributions
 diary-0.007
 shield-0.007
es-0.007
oc-0.007
 journal-0.006
Token hard
Token ID1327
Feature activation-3.32e-02

Pos logit contributions
aa+0.014
oe+0.013
Kids+0.013
oes+0.013
round+0.012
Neg logit contributions
 diary-0.020
 shield-0.019
es-0.019
oc-0.019
 shields-0.018
Token and
Token ID290
Feature activation-1.01e+00

Pos logit contributions
aa+0.001
oe+0.001
Kids+0.001
oes+0.001
round+0.001
Neg logit contributions
 diary-0.001
 shield-0.001
es-0.001
oc-0.001
 shields-0.001
Token had
Token ID550
Feature activation+1.74e+00

Pos logit contributions
aa+0.029
oe+0.027
Kids+0.027
oes+0.027
round+0.025
Neg logit contributions
 shield-0.032
 diary-0.032
es-0.031
oc-0.030
 shields-0.029
Token no
Token ID645
Feature activation+2.15e+00

Pos logit contributions
oc+0.049
 diary+0.046
es+0.046
 shield+0.045
house+0.043
Neg logit contributions
aa-0.052
oe-0.049
oes-0.049
Kids-0.048
round-0.045
Token eyes
Token ID2951
Feature activation+8.42e-01

Pos logit contributions
es+0.059
oc+0.054
onel+0.054
vel+0.052
 diary+0.050
Neg logit contributions
aa-0.064
oes-0.063
oe-0.063
 weekend-0.056
round-0.056
Token or
Token ID393
Feature activation+4.01e+00

Pos logit contributions
 diary+0.024
 shield+0.024
es+0.023
oc+0.022
 shields+0.021
Neg logit contributions
aa-0.026
Kids-0.025
oe-0.025
oes-0.024
round-0.023
Token nose
Token ID9686
Feature activation+4.58e-01

Pos logit contributions
oc+0.110
es+0.106
onel+0.104
vel+0.102
house+0.102
Neg logit contributions
aa-0.110
oes-0.105
 to-0.104
 se-0.102
 sur-0.099
Token.
Token ID13
Feature activation-2.05e+00

Pos logit contributions
 diary+0.014
 shield+0.014
oc+0.013
es+0.013
 journal+0.012
Neg logit contributions
aa-0.014
oe-0.013
oes-0.012
Kids-0.012
round-0.012
Token Lily
Token ID20037
Feature activation-1.03e+00

Pos logit contributions
aa+0.065
oes+0.062
oe+0.061
round+0.058
Kids+0.058
Neg logit contributions
es-0.056
 diary-0.055
 shield-0.055
oc-0.054
house-0.050
Token thought
Token ID1807
Feature activation-2.62e-01

Pos logit contributions
aa+0.025
oe+0.023
Kids+0.023
oes+0.022
round+0.021
Neg logit contributions
 diary-0.037
 shield-0.037
es-0.035
oc-0.035
 shields-0.033
Token it
Token ID340
Feature activation-6.48e-02

Pos logit contributions
aa+0.007
oe+0.007
Kids+0.007
oes+0.006
round+0.006
Neg logit contributions
 diary-0.008
oc-0.008
 shield-0.008
es-0.008
house-0.007
Token the
Token ID262
Feature activation-2.15e-01

Pos logit contributions
es+0.027
 diary+0.027
 shield+0.026
oc+0.026
vel+0.024
Neg logit contributions
oe-0.021
aa-0.021
oes-0.019
Kids-0.019
round-0.018
Token sunshine
Token ID34488
Feature activation-4.72e-01

Pos logit contributions
aa+0.006
oe+0.006
Kids+0.006
oes+0.005
round+0.005
Neg logit contributions
 shield-0.007
 diary-0.007
es-0.006
oc-0.006
 journal-0.006
Token.
Token ID13
Feature activation+1.88e+00

Pos logit contributions
aa+0.015
Kids+0.015
oe+0.015
oes+0.014
round+0.013
Neg logit contributions
 shield-0.013
 diary-0.013
es-0.013
oc-0.012
 journal-0.011
Token
Token ID198
Feature activation+1.20e+00

Pos logit contributions
 shield+0.069
 diary+0.068
es+0.066
oc+0.066
onel+0.064
Neg logit contributions
Kids-0.042
oe-0.041
aa-0.040
oes-0.039
round-0.036
Token
Token ID198
Feature activation+4.05e+00

Pos logit contributions
 diary+0.040
 shield+0.040
es+0.039
oc+0.038
 shields+0.036
Neg logit contributions
aa-0.031
oe-0.030
Kids-0.029
oes-0.028
round-0.026
TokenSuddenly
Token ID38582
Feature activation+3.99e+00

Pos logit contributions
 shield+0.148
 diary+0.147
es+0.141
onel+0.140
 Majesty+0.138
Neg logit contributions
Kids-0.091
oe-0.086
round-0.078
aa-0.071
 weekend-0.070
Token,
Token ID11
Feature activation+2.89e+00

Pos logit contributions
oc+0.170
onel+0.168
istered+0.167
 Majesty+0.161
 diary+0.160
Neg logit contributions
oe-0.066
 to-0.064
aa-0.050
 Kay-0.046
guard-0.040
Token he
Token ID339
Feature activation+1.38e+00

Pos logit contributions
oc+0.112
 Majesty+0.108
onel+0.107
istered+0.101
 web+0.100
Neg logit contributions
oe-0.059
 to-0.058
 weekend-0.054
 crowded-0.051
Kids-0.050
Token heard
Token ID2982
Feature activation+2.57e+00

Pos logit contributions
 diary+0.047
 shield+0.046
oc+0.046
es+0.044
 journal+0.042
Neg logit contributions
aa-0.035
oe-0.033
Kids-0.032
oes-0.030
 sur-0.028
Token a
Token ID257
Feature activation+7.46e-01

Pos logit contributions
oc+0.073
 diary+0.071
istered+0.070
es+0.069
 shield+0.069
Neg logit contributions
aa-0.074
Kids-0.072
oe-0.068
 Kay-0.067
oes-0.066
Token soft
Token ID2705
Feature activation+8.83e-03

Pos logit contributions
 shield+0.020
 diary+0.020
oc+0.019
es+0.018
 journal+0.017
Neg logit contributions
aa-0.024
oe-0.024
oes-0.024
Kids-0.023
round-0.022
Token
Token ID198
Feature activation-2.18e-01

Pos logit contributions
aa+0.019
oe+0.019
oes+0.018
round+0.018
Kids+0.017
Neg logit contributions
 diary-0.016
es-0.016
oc-0.015
 shield-0.015
 journal-0.014
Token
Token ID198
Feature activation+5.41e-01

Pos logit contributions
aa+0.007
oe+0.006
oes+0.006
Kids+0.006
round+0.006
Neg logit contributions
 diary-0.006
es-0.006
 shield-0.006
oc-0.006
 journal-0.006
Token"
Token ID1
Feature activation-1.61e-02

Pos logit contributions
 diary+0.015
 shield+0.014
es+0.014
oc+0.014
 shields+0.013
Neg logit contributions
aa-0.018
oe-0.017
Kids-0.017
oes-0.016
round-0.016
TokenTom
Token ID13787
Feature activation+1.77e+00

Pos logit contributions
aa+0.001
oes+0.001
oe+0.001
round+0.000
 weekend+0.000
Neg logit contributions
es-0.000
 diary-0.000
 shield-0.000
oc-0.000
 traps-0.000
Token and
Token ID290
Feature activation-8.47e-01

Pos logit contributions
 diary+0.054
 shield+0.054
es+0.051
oc+0.051
 shields+0.048
Neg logit contributions
aa-0.052
oe-0.050
Kids-0.048
oes-0.047
round-0.045
Token Sam
Token ID3409
Feature activation+3.97e+00

Pos logit contributions
aa+0.027
oe+0.026
Kids+0.025
oes+0.025
round+0.023
Neg logit contributions
 diary-0.024
 shield-0.024
es-0.023
oc-0.023
 journal-0.021
Token,
Token ID11
Feature activation+7.89e-01

Pos logit contributions
 shield+0.142
 diary+0.140
 shields+0.132
 journal+0.127
oc+0.126
Neg logit contributions
aa-0.104
oe-0.101
Kids-0.088
oes-0.087
round-0.081
Token what
Token ID644
Feature activation+5.10e-01

Pos logit contributions
 diary+0.019
 shield+0.019
oc+0.019
es+0.019
 shields+0.017
Neg logit contributions
aa-0.028
Kids-0.027
oe-0.026
oes-0.025
round-0.024
Token are
Token ID389
Feature activation-2.41e-01

Pos logit contributions
 shield+0.014
 diary+0.013
oc+0.013
 shields+0.012
es+0.012
Neg logit contributions
aa-0.017
Kids-0.017
oe-0.016
oes-0.016
 sur-0.015
Token you
Token ID345
Feature activation+1.88e+00

Pos logit contributions
aa+0.008
oe+0.008
Kids+0.007
oes+0.007
round+0.007
Neg logit contributions
 shield-0.007
 diary-0.007
oc-0.006
es-0.006
 shields-0.006
Token doing
Token ID1804
Feature activation+9.95e-01

Pos logit contributions
 diary+0.051
 shield+0.051
es+0.049
oc+0.048
 shields+0.045
Neg logit contributions
aa-0.061
oe-0.059
Kids-0.058
oes-0.057
round-0.054
Token an
Token ID281
Feature activation+8.78e-01

Pos logit contributions
es+0.061
oc+0.060
onel+0.059
 diary+0.059
istered+0.058
Neg logit contributions
oe-0.040
aa-0.040
Kids-0.038
 weekend-0.036
 Kay-0.035
Token unfamiliar
Token ID22594
Feature activation+7.51e-01

Pos logit contributions
 diary+0.032
 shield+0.032
es+0.031
oc+0.030
 shields+0.029
Neg logit contributions
aa-0.020
oe-0.019
Kids-0.019
oes-0.018
round-0.017
Token forest
Token ID8222
Feature activation+7.54e-01

Pos logit contributions
 diary+0.026
 shield+0.026
es+0.026
oc+0.025
 shields+0.024
Neg logit contributions
aa-0.018
oe-0.017
Kids-0.017
oes-0.016
round-0.015
Token.
Token ID13
Feature activation+2.43e+00

Pos logit contributions
 diary+0.025
 shield+0.025
es+0.024
oc+0.023
 Majesty+0.023
Neg logit contributions
oe-0.018
aa-0.018
oes-0.018
round-0.016
Kids-0.016
Token
Token ID198
Feature activation+1.40e+00

Pos logit contributions
 diary+0.088
 shield+0.087
istered+0.084
onel+0.082
 shields+0.081
Neg logit contributions
Kids-0.048
aa-0.048
oe-0.046
oes-0.045
round-0.042
Token
Token ID198
Feature activation+3.94e+00

Pos logit contributions
 diary+0.049
 shield+0.049
es+0.047
oc+0.046
 shields+0.045
Neg logit contributions
aa-0.034
oe-0.033
Kids-0.032
oes-0.031
round-0.029
TokenWill
Token ID8743
Feature activation+1.54e+00

Pos logit contributions
 diary+0.147
 shield+0.142
istered+0.137
onel+0.136
 Majesty+0.136
Neg logit contributions
Kids-0.081
oe-0.074
aa-0.069
 weekend-0.061
Ice-0.060
Token tried
Token ID3088
Feature activation-1.23e-01

Pos logit contributions
 diary+0.050
 shield+0.048
oc+0.047
 shields+0.046
istered+0.046
Neg logit contributions
aa-0.043
oe-0.040
oes-0.036
Kids-0.034
round-0.034
Token his
Token ID465
Feature activation+2.31e-01

Pos logit contributions
aa+0.002
oe+0.002
Kids+0.002
oes+0.001
round+0.001
Neg logit contributions
 shield-0.006
 diary-0.006
es-0.006
oc-0.005
 shields-0.005
Token best
Token ID1266
Feature activation-5.65e-01

Pos logit contributions
 diary+0.007
 shield+0.007
es+0.006
oc+0.006
 shields+0.006
Neg logit contributions
aa-0.007
oe-0.007
Kids-0.007
oes-0.007
round-0.006
Token to
Token ID284
Feature activation+1.21e-01

Pos logit contributions
aa+0.013
oe+0.012
Kids+0.012
oes+0.012
round+0.011
Neg logit contributions
 diary-0.021
 shield-0.020
es-0.020
oc-0.020
 shields-0.019
TokenThe
Token ID464
Feature activation+1.22e+00

Pos logit contributions
 shield+0.082
 diary+0.078
oc+0.076
es+0.075
 shields+0.075
Neg logit contributions
Kids-0.056
oe-0.052
aa-0.051
oes-0.046
round-0.045
Token mouse
Token ID10211
Feature activation+1.58e+00

Pos logit contributions
es+0.048
vel+0.044
vered+0.042
oc+0.042
 Majesty+0.042
Neg logit contributions
 weekend-0.025
oe-0.023
 week-0.023
 elderly-0.023
 first-0.021
Token lived
Token ID5615
Feature activation+1.12e+00

Pos logit contributions
 diary+0.055
 shield+0.052
istered+0.051
es+0.051
vel+0.050
Neg logit contributions
aa-0.036
oe-0.036
Kids-0.034
oes-0.030
 sur-0.030
Token in
Token ID287
Feature activation+1.84e+00

Pos logit contributions
 diary+0.039
 shield+0.039
oc+0.038
es+0.036
 shields+0.036
Neg logit contributions
oe-0.029
aa-0.026
Kids-0.024
oes-0.023
 sur-0.022
Token the
Token ID262
Feature activation+2.23e+00

Pos logit contributions
 shield+0.067
vel+0.066
 Majesty+0.066
oc+0.066
es+0.065
Neg logit contributions
oe-0.038
 Kay-0.032
 to-0.032
aa-0.032
Kids-0.032
Token diary
Token ID26339
Feature activation+3.94e+00

Pos logit contributions
es+0.097
vel+0.082
rum+0.081
ities+0.081
rums+0.079
Neg logit contributions
 weekend-0.044
oe-0.044
 week-0.042
 distance-0.041
Kids-0.038
Token for
Token ID329
Feature activation+1.52e+00

Pos logit contributions
oc+0.136
istered+0.135
 shield+0.133
 diary+0.131
 shields+0.131
Neg logit contributions
oe-0.087
 to-0.074
oes-0.072
 weekend-0.072
aa-0.072
Token a
Token ID257
Feature activation+3.18e-01

Pos logit contributions
 shield+0.045
oc+0.044
 diary+0.043
es+0.041
istered+0.040
Neg logit contributions
Kids-0.043
oe-0.042
aa-0.042
 weekend-0.039
 Kay-0.038
Token long
Token ID890
Feature activation-9.25e-01

Pos logit contributions
 diary+0.011
 shield+0.011
es+0.010
oc+0.010
 shields+0.010
Neg logit contributions
aa-0.008
oe-0.008
Kids-0.008
oes-0.008
round-0.007
Token time
Token ID640
Feature activation+2.36e-01

Pos logit contributions
aa+0.021
oe+0.020
Kids+0.019
oes+0.018
round+0.018
Neg logit contributions
es-0.034
 diary-0.033
 shield-0.033
oc-0.032
istered-0.030
Token,
Token ID11
Feature activation-4.67e-01

Pos logit contributions
 shield+0.008
 diary+0.008
oc+0.007
es+0.007
 shields+0.007
Neg logit contributions
oe-0.006
aa-0.006
oes-0.005
Kids-0.005
round-0.005
Token be
Token ID307
Feature activation+1.07e+00

Pos logit contributions
 diary+0.025
 shield+0.025
es+0.024
oc+0.024
 journal+0.022
Neg logit contributions
aa-0.018
oe-0.017
Kids-0.017
oes-0.016
round-0.015
Token found
Token ID1043
Feature activation+1.23e+00

Pos logit contributions
 diary+0.033
oc+0.033
 shield+0.032
es+0.030
 journal+0.029
Neg logit contributions
oe-0.030
aa-0.030
Kids-0.027
oes-0.026
round-0.024
Token.
Token ID13
Feature activation+2.00e+00

Pos logit contributions
 diary+0.041
 shield+0.041
oc+0.039
es+0.038
 Majesty+0.038
Neg logit contributions
oe-0.030
aa-0.030
oes-0.028
Kids-0.027
round-0.025
Token
Token ID198
Feature activation+1.63e+00

Pos logit contributions
 shield+0.075
 diary+0.072
onel+0.069
es+0.068
oc+0.067
Neg logit contributions
oe-0.046
Kids-0.044
oes-0.041
 Kay-0.037
aa-0.037
Token
Token ID198
Feature activation+3.31e+00

Pos logit contributions
 shield+0.064
 diary+0.063
es+0.059
oc+0.058
 shields+0.058
Neg logit contributions
oe-0.035
Kids-0.033
aa-0.033
oes-0.030
round-0.027
TokenSuddenly
Token ID38582
Feature activation+3.90e+00

Pos logit contributions
 shield+0.113
 diary+0.108
 Majesty+0.104
 webs+0.104
onel+0.104
Neg logit contributions
Kids-0.086
oe-0.084
round-0.070
 weekend-0.066
 crowded-0.066
Token,
Token ID11
Feature activation+2.68e+00

Pos logit contributions
oc+0.166
onel+0.165
istered+0.161
cod+0.157
 diary+0.156
Neg logit contributions
oe-0.067
 to-0.064
 Kay-0.047
 slowly-0.044
guard-0.041
Token he
Token ID339
Feature activation+1.49e+00

Pos logit contributions
oc+0.095
onel+0.089
 Majesty+0.088
cod+0.085
 webs+0.085
Neg logit contributions
oe-0.067
 to-0.061
 weekend-0.058
 Kay-0.055
 crowded-0.055
Token heard
Token ID2982
Feature activation+2.86e+00

Pos logit contributions
 diary+0.050
oc+0.050
 shield+0.049
es+0.047
 shields+0.045
Neg logit contributions
aa-0.038
oe-0.037
Kids-0.035
oes-0.031
 sur-0.030
Token a
Token ID257
Feature activation+6.75e-01

Pos logit contributions
oc+0.084
istered+0.081
 diary+0.080
es+0.078
 shield+0.078
Neg logit contributions
aa-0.077
Kids-0.076
oe-0.073
 Kay-0.073
 to-0.070
Token little
Token ID1310
Feature activation+3.77e-01

Pos logit contributions
 shield+0.019
 diary+0.019
oc+0.018
es+0.017
 journal+0.016
Neg logit contributions
aa-0.022
oe-0.021
Kids-0.021
oes-0.021
round-0.020
Token be
Token ID307
Feature activation-2.09e+00

Pos logit contributions
aa+0.029
oe+0.028
Kids+0.028
oes+0.027
round+0.025
Neg logit contributions
 diary-0.031
 shield-0.030
es-0.029
oc-0.029
 shields-0.027
Token dangerous
Token ID4923
Feature activation-3.18e-01

Pos logit contributions
aa+0.068
oe+0.065
Kids+0.065
oes+0.063
round+0.060
Neg logit contributions
 diary-0.057
 shield-0.057
es-0.054
oc-0.053
 shields-0.050
Token".
Token ID1911
Feature activation+2.39e+00

Pos logit contributions
aa+0.009
oe+0.009
Kids+0.008
oes+0.008
round+0.008
Neg logit contributions
 diary-0.010
 shield-0.010
es-0.010
oc-0.009
 shields-0.009
Token
Token ID220
Feature activation+4.07e-01

Pos logit contributions
 shield+0.074
 diary+0.071
onel+0.070
vel+0.065
es+0.064
Neg logit contributions
oe-0.071
Kids-0.068
oes-0.064
 to-0.061
round-0.061
Token
Token ID198
Feature activation+2.57e+00

Pos logit contributions
 shield+0.017
 diary+0.017
 shields+0.015
 journal+0.015
oc+0.015
Neg logit contributions
oe-0.008
aa-0.008
Kids-0.008
oes-0.008
round-0.006
Token
Token ID198
Feature activation+3.88e+00

Pos logit contributions
 shield+0.096
 diary+0.096
es+0.089
oc+0.088
 shields+0.087
Neg logit contributions
oe-0.057
Kids-0.057
aa-0.056
oes-0.051
round-0.048
TokenJames
Token ID14731
Feature activation-2.02e-01

Pos logit contributions
 shield+0.124
 diary+0.123
onel+0.115
 Majesty+0.114
 webs+0.110
Neg logit contributions
Kids-0.112
oe-0.105
round-0.094
aa-0.088
guard-0.087
Token understood
Token ID7247
Feature activation+7.84e-02

Pos logit contributions
aa+0.006
oe+0.006
Kids+0.006
oes+0.005
round+0.005
Neg logit contributions
 diary-0.006
 shield-0.006
es-0.006
oc-0.006
 shields-0.005
Token the
Token ID262
Feature activation-1.48e+00

Pos logit contributions
 shield+0.002
 diary+0.002
es+0.002
oc+0.002
 journal+0.002
Neg logit contributions
aa-0.002
oe-0.002
Kids-0.002
oes-0.002
round-0.002
Token message
Token ID3275
Feature activation+1.20e+00

Pos logit contributions
oe+0.044
aa+0.044
Kids+0.041
oes+0.040
round+0.039
Neg logit contributions
 shield-0.045
 diary-0.045
oc-0.044
es-0.041
 journal-0.040
Token and
Token ID290
Feature activation+3.56e-01

Pos logit contributions
 diary+0.044
 shield+0.044
es+0.042
oc+0.042
 shields+0.040
Neg logit contributions
aa-0.027
oe-0.026
Kids-0.025
oes-0.024
round-0.022
Token
Token ID198
Feature activation+1.04e+00

Pos logit contributions
 diary+0.003
es+0.003
 shield+0.002
oc+0.002
 journal+0.002
Neg logit contributions
aa-0.002
oe-0.002
oes-0.002
Kids-0.002
round-0.002
Token"
Token ID1
Feature activation+1.63e-01

Pos logit contributions
 shield+0.031
 diary+0.031
es+0.029
oc+0.028
 shields+0.028
Neg logit contributions
aa-0.032
oe-0.031
Kids-0.031
oes-0.029
round-0.027
TokenL
Token ID43
Feature activation-1.30e+00

Pos logit contributions
 diary+0.004
es+0.004
 shield+0.004
oc+0.004
 journal+0.004
Neg logit contributions
aa-0.005
oes-0.005
oe-0.005
round-0.005
 weekend-0.004
Tokenily
Token ID813
Feature activation+2.07e+00

Pos logit contributions
aa+0.039
oe+0.038
Kids+0.038
oes+0.036
round+0.034
Neg logit contributions
 shield-0.039
 diary-0.039
oc-0.037
es-0.037
 shields-0.035
Token and
Token ID290
Feature activation-2.78e-01

Pos logit contributions
 shield+0.067
 diary+0.066
oc+0.062
 shields+0.061
es+0.061
Neg logit contributions
aa-0.059
oe-0.057
Kids-0.053
oes-0.051
round-0.049
Token Tom
Token ID4186
Feature activation+3.88e+00

Pos logit contributions
aa+0.006
Kids+0.006
oe+0.006
oes+0.006
round+0.005
Neg logit contributions
oc-0.010
 shield-0.010
es-0.010
 diary-0.010
 webs-0.010
Token,
Token ID11
Feature activation+7.22e-01

Pos logit contributions
 shield+0.139
 diary+0.137
 shields+0.131
oc+0.128
 journal+0.124
Neg logit contributions
aa-0.098
oe-0.095
Kids-0.083
oes-0.081
 Su-0.075
Token how
Token ID703
Feature activation-1.53e-01

Pos logit contributions
oc+0.017
 shield+0.017
 diary+0.016
es+0.016
 shields+0.015
Neg logit contributions
aa-0.027
Kids-0.026
oe-0.025
oes-0.024
round-0.023
Token could
Token ID714
Feature activation-2.04e-01

Pos logit contributions
aa+0.005
Kids+0.004
oe+0.004
oes+0.004
round+0.004
Neg logit contributions
 shield-0.005
 diary-0.005
oc-0.004
es-0.004
 shields-0.004
Token you
Token ID345
Feature activation-1.87e-01

Pos logit contributions
aa+0.006
oe+0.006
Kids+0.006
oes+0.006
round+0.005
Neg logit contributions
 diary-0.006
 shield-0.006
oc-0.006
es-0.006
 shields-0.006
Token be
Token ID307
Feature activation-2.92e-01

Pos logit contributions
aa+0.005
oe+0.005
oes+0.005
Kids+0.005
round+0.004
Neg logit contributions
 diary-0.006
 shield-0.006
es-0.006
oc-0.006
 shields-0.005
Token
Token ID198
Feature activation+9.73e-01

Pos logit contributions
aa+0.004
oe+0.004
oes+0.004
Kids+0.004
round+0.004
Neg logit contributions
 diary-0.004
 shield-0.004
es-0.004
oc-0.004
 journal-0.004
Token"
Token ID1
Feature activation-8.53e-02

Pos logit contributions
 shield+0.031
 diary+0.031
es+0.029
oc+0.029
 shields+0.028
Neg logit contributions
aa-0.028
Kids-0.027
oe-0.027
oes-0.025
round-0.023
TokenL
Token ID43
Feature activation-1.45e+00

Pos logit contributions
aa+0.003
oes+0.003
oe+0.003
round+0.002
 weekend+0.002
Neg logit contributions
 diary-0.002
es-0.002
 shield-0.002
oc-0.002
 journal-0.002
Tokenily
Token ID813
Feature activation+1.74e+00

Pos logit contributions
aa+0.047
oe+0.045
Kids+0.044
oes+0.044
round+0.042
Neg logit contributions
 diary-0.039
 shield-0.039
es-0.038
oc-0.037
 journal-0.034
Token and
Token ID290
Feature activation-1.97e-01

Pos logit contributions
 shield+0.055
 diary+0.054
oc+0.051
 shields+0.051
es+0.050
Neg logit contributions
aa-0.050
oe-0.049
Kids-0.045
oes-0.043
round-0.042
Token Sam
Token ID3409
Feature activation+3.87e+00

Pos logit contributions
aa+0.005
Kids+0.005
oes+0.004
oe+0.004
 Su+0.004
Neg logit contributions
oc-0.008
es-0.007
 diary-0.007
 shield-0.007
istered-0.007
Token,
Token ID11
Feature activation+6.97e-01

Pos logit contributions
 shield+0.138
 diary+0.137
 shields+0.132
oc+0.131
es+0.124
Neg logit contributions
aa-0.095
oe-0.094
Kids-0.082
oes-0.079
 Su-0.075
Token you
Token ID345
Feature activation+2.58e+00

Pos logit contributions
oc+0.019
 shield+0.019
 diary+0.018
es+0.018
 shields+0.017
Neg logit contributions
aa-0.023
Kids-0.022
oe-0.021
oes-0.020
 Su-0.019
Token need
Token ID761
Feature activation-5.23e-01

Pos logit contributions
 diary+0.090
 shield+0.087
oc+0.084
 Majesty+0.081
 journal+0.080
Neg logit contributions
aa-0.065
Kids-0.061
oe-0.058
 crowded-0.053
oes-0.052
Token to
Token ID284
Feature activation+1.28e-03

Pos logit contributions
aa+0.009
oe+0.008
Kids+0.008
oes+0.007
round+0.007
Neg logit contributions
 diary-0.023
 shield-0.023
es-0.022
 shields-0.021
 journal-0.021
Token share
Token ID2648
Feature activation-1.55e-01

Pos logit contributions
 diary+0.000
 shield+0.000
es+0.000
oc+0.000
 shields+0.000
Neg logit contributions
aa-0.000
oe-0.000
Kids-0.000
oes-0.000
round-0.000
Token the
Token ID262
Feature activation+1.31e+00

Pos logit contributions
 diary+0.011
oc+0.011
 shield+0.011
es+0.011
 journal+0.010
Neg logit contributions
aa-0.011
oes-0.010
round-0.010
Kids-0.010
oe-0.009
Token room
Token ID2119
Feature activation+9.24e-01

Pos logit contributions
es+0.039
 shield+0.037
oc+0.037
 diary+0.036
vel+0.035
Neg logit contributions
oe-0.039
aa-0.038
Kids-0.038
oes-0.036
 weekend-0.034
Token.
Token ID13
Feature activation+1.89e-01

Pos logit contributions
 diary+0.025
es+0.024
 shield+0.024
oc+0.023
house+0.022
Neg logit contributions
aa-0.031
Kids-0.029
oe-0.028
oes-0.028
round-0.027
Token "
Token ID366
Feature activation-5.37e-01

Pos logit contributions
 diary+0.005
 shield+0.005
es+0.005
oc+0.005
 journal+0.005
Neg logit contributions
aa-0.006
oe-0.006
Kids-0.006
oes-0.006
round-0.005
TokenHi
Token ID17250
Feature activation+1.31e+00

Pos logit contributions
aa+0.015
oe+0.014
oes+0.014
Kids+0.013
round+0.013
Neg logit contributions
 diary-0.017
 shield-0.017
oc-0.016
es-0.016
 journal-0.015
Token girls
Token ID4813
Feature activation+3.84e+00

Pos logit contributions
 shield+0.043
oc+0.043
es+0.041
 diary+0.041
 shields+0.040
Neg logit contributions
oe-0.036
aa-0.034
Kids-0.033
 Kay-0.029
 Su-0.029
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
 diary+0.135
 shield+0.135
 shields+0.130
 traps+0.125
istered+0.124
Neg logit contributions
aa-0.096
oe-0.095
round-0.080
oes-0.077
 sur-0.075
Token how
Token ID703
Feature activation-1.00e-03

Pos logit contributions
aa+0.006
Kids+0.006
oe+0.006
oes+0.006
round+0.006
Neg logit contributions
es-0.005
 shield-0.005
oc-0.005
 diary-0.005
 shields-0.005
Token's
Token ID338
Feature activation-4.02e-01

Pos logit contributions
aa+0.000
oes+0.000
oe+0.000
Kids+0.000
round+0.000
Neg logit contributions
 shield-0.000
oc-0.000
 diary-0.000
es-0.000
 shields-0.000
Token the
Token ID262
Feature activation+1.53e+00

Pos logit contributions
oe+0.010
aa+0.010
oes+0.009
 weekend+0.009
Kids+0.009
Neg logit contributions
oc-0.014
es-0.014
 shield-0.013
 diary-0.013
istered-0.012
Token puzzle
Token ID15027
Feature activation+1.09e+00

Pos logit contributions
es+0.040
oc+0.038
istered+0.030
 shield+0.029
onel+0.028
Neg logit contributions
oe-0.055
 weekend-0.054
oes-0.050
 week-0.049
Kids-0.048
Token said
Token ID531
Feature activation-1.85e-01

Pos logit contributions
oes+0.016
oe+0.014
aa+0.014
round+0.014
 weekend+0.013
Neg logit contributions
es-0.013
 diary-0.013
 shield-0.013
oc-0.013
house-0.012
Token,
Token ID11
Feature activation-8.51e-01

Pos logit contributions
aa+0.006
oe+0.006
oes+0.006
Kids+0.006
round+0.005
Neg logit contributions
 diary-0.005
es-0.005
 shield-0.005
oc-0.005
 journal-0.004
Token "
Token ID366
Feature activation-5.84e-01

Pos logit contributions
aa+0.029
oe+0.029
oes+0.028
Kids+0.028
round+0.027
Neg logit contributions
 diary-0.021
 shield-0.021
es-0.021
oc-0.019
 journal-0.018
TokenTom
Token ID13787
Feature activation+5.78e-01

Pos logit contributions
aa+0.017
oes+0.016
oe+0.016
round+0.016
 sur+0.014
Neg logit contributions
es-0.017
 diary-0.017
oc-0.016
 shield-0.016
 traps-0.015
Token and
Token ID290
Feature activation-7.45e-01

Pos logit contributions
 diary+0.020
 shield+0.020
es+0.020
oc+0.019
 journal+0.018
Neg logit contributions
aa-0.014
oe-0.014
Kids-0.014
oes-0.013
round-0.012
Token Sam
Token ID3409
Feature activation+3.83e+00

Pos logit contributions
aa+0.021
Kids+0.020
oe+0.020
oes+0.019
round+0.018
Neg logit contributions
 diary-0.024
 shield-0.023
es-0.023
oc-0.023
 shields-0.021
Token,
Token ID11
Feature activation+5.69e-01

Pos logit contributions
 shield+0.140
 diary+0.136
 shields+0.133
oc+0.132
 journal+0.125
Neg logit contributions
aa-0.095
oe-0.092
Kids-0.083
oes-0.079
 to-0.074
Token you
Token ID345
Feature activation+2.53e+00

Pos logit contributions
 diary+0.015
 shield+0.015
oc+0.014
es+0.014
 shields+0.013
Neg logit contributions
aa-0.019
Kids-0.019
oe-0.018
oes-0.018
round-0.017
Token were
Token ID547
Feature activation+1.40e+00

Pos logit contributions
 diary+0.091
 shield+0.090
 Majesty+0.089
oc+0.083
 journal+0.082
Neg logit contributions
aa-0.063
Kids-0.058
oe-0.057
oes-0.049
 to-0.049
Token very
Token ID845
Feature activation+6.28e-01

Pos logit contributions
oc+0.051
 shield+0.046
 diary+0.046
es+0.043
 shields+0.043
Neg logit contributions
oe-0.036
aa-0.035
Kids-0.033
oes-0.030
 sur-0.030
Token naughty
Token ID45128
Feature activation+6.78e-01

Pos logit contributions
 shield+0.015
 diary+0.015
es+0.014
oc+0.014
 shields+0.013
Neg logit contributions
aa-0.023
oe-0.022
Kids-0.021
oes-0.021
round-0.020
Token was
Token ID373
Feature activation-2.10e+00

Pos logit contributions
aa+0.031
oe+0.029
Kids+0.029
oes+0.028
round+0.027
Neg logit contributions
 shield-0.025
 diary-0.024
es-0.024
oc-0.023
house-0.022
Token very
Token ID845
Feature activation-2.32e+00

Pos logit contributions
Kids+0.070
aa+0.068
round+0.063
oes+0.063
oe+0.062
Neg logit contributions
 shield-0.062
 diary-0.057
 shields-0.051
house-0.051
 webs-0.050
Token bright
Token ID6016
Feature activation-3.02e-02

Pos logit contributions
Kids+0.085
round+0.080
aa+0.076
oes+0.076
aren+0.072
Neg logit contributions
 shield-0.058
 diary-0.051
istered-0.049
 nightmare-0.048
 journal-0.046
Token.
Token ID13
Feature activation+2.57e+00

Pos logit contributions
aa+0.001
Kids+0.001
oe+0.001
oes+0.001
round+0.001
Neg logit contributions
 shield-0.001
 diary-0.001
es-0.001
oc-0.001
 journal-0.001
Token
Token ID198
Feature activation+1.01e+00

Pos logit contributions
 shield+0.093
onel+0.092
 diary+0.091
es+0.090
oc+0.088
Neg logit contributions
Kids-0.056
oes-0.055
oe-0.054
round-0.052
 weekend-0.049
Token
Token ID198
Feature activation+3.82e+00

Pos logit contributions
 diary+0.034
 shield+0.034
es+0.033
oc+0.032
 shields+0.030
Neg logit contributions
aa-0.027
oe-0.025
Kids-0.025
oes-0.024
round-0.023
TokenJames
Token ID14731
Feature activation+2.46e-01

Pos logit contributions
 shield+0.143
onel+0.142
 diary+0.141
 Majesty+0.140
es+0.135
Neg logit contributions
Kids-0.083
oe-0.076
round-0.073
 crowded-0.067
 weekend-0.065
Token ran
Token ID4966
Feature activation-9.86e-01

Pos logit contributions
 diary+0.008
 shield+0.008
es+0.008
oc+0.008
 shields+0.007
Neg logit contributions
aa-0.007
oe-0.006
Kids-0.006
oes-0.006
round-0.006
Token around
Token ID1088
Feature activation+9.99e-01

Pos logit contributions
aa+0.026
Kids+0.026
oes+0.024
oe+0.022
 Abbey+0.021
Neg logit contributions
 shield-0.033
 diary-0.031
es-0.031
 webs-0.031
 shields-0.030
Token the
Token ID262
Feature activation-3.27e-01

Pos logit contributions
 diary+0.034
 shield+0.033
es+0.032
oc+0.032
 shields+0.030
Neg logit contributions
aa-0.026
oe-0.025
Kids-0.024
oes-0.024
round-0.022
Token garden
Token ID11376
Feature activation+1.49e+00

Pos logit contributions
aa+0.011
Kids+0.011
oe+0.011
oes+0.010
round+0.010
Neg logit contributions
 shield-0.008
 diary-0.008
oc-0.008
house-0.007
 journal-0.007
Token happy
Token ID3772
Feature activation+4.96e-01

Pos logit contributions
 diary+0.032
 shield+0.032
es+0.031
oc+0.031
 shields+0.029
Neg logit contributions
aa-0.030
oe-0.028
Kids-0.028
oes-0.027
round-0.025
Token that
Token ID326
Feature activation+9.63e-01

Pos logit contributions
 diary+0.019
 shield+0.019
oc+0.018
es+0.018
 shields+0.017
Neg logit contributions
aa-0.011
oe-0.010
Kids-0.010
oes-0.009
round-0.009
Token he
Token ID339
Feature activation-5.89e-02

Pos logit contributions
es+0.033
 diary+0.033
oc+0.033
istered+0.033
 webs+0.032
Neg logit contributions
Kids-0.021
aa-0.021
oes-0.020
oe-0.020
 sur-0.019
Token hugged
Token ID41130
Feature activation+2.98e-01

Pos logit contributions
aa+0.002
oe+0.002
Kids+0.002
oes+0.002
round+0.001
Neg logit contributions
 diary-0.002
 shield-0.002
es-0.002
oc-0.002
 shields-0.002
Token his
Token ID465
Feature activation+1.68e+00

Pos logit contributions
 diary+0.009
 shield+0.009
es+0.009
oc+0.009
 shields+0.008
Neg logit contributions
aa-0.009
oe-0.008
Kids-0.008
oes-0.008
round-0.007
Token robot
Token ID9379
Feature activation+3.81e+00

Pos logit contributions
es+0.040
onel+0.039
vel+0.038
istered+0.037
 endings+0.036
Neg logit contributions
oe-0.057
aa-0.053
oes-0.052
 to-0.048
Kids-0.048
Token toy
Token ID13373
Feature activation+3.43e+00

Pos logit contributions
onel+0.153
 endings+0.153
es+0.153
istered+0.152
 traps+0.148
Neg logit contributions
oe-0.056
 to-0.055
round-0.051
aa-0.048
 towards-0.042
Token and
Token ID290
Feature activation+1.67e+00

Pos logit contributions
 Majesty+0.123
vel+0.121
es+0.121
istered+0.119
 diary+0.117
Neg logit contributions
aa-0.067
oe-0.066
oes-0.066
 to-0.065
round-0.060
Token played
Token ID2826
Feature activation+1.72e+00

Pos logit contributions
 diary+0.062
oc+0.061
es+0.060
vel+0.060
 shield+0.059
Neg logit contributions
aa-0.034
Kids-0.033
oe-0.031
 sur-0.029
oes-0.029
Token with
Token ID351
Feature activation+2.12e+00

Pos logit contributions
istered+0.071
ience+0.070
 diary+0.070
oc+0.068
es+0.068
Neg logit contributions
 to-0.026
oe-0.025
 sur-0.021
 towards-0.019
 straight-0.018
Token it
Token ID340
Feature activation+2.51e+00

Pos logit contributions
istered+0.090
 diary+0.089
vel+0.087
onel+0.087
es+0.087
Neg logit contributions
 to-0.030
oe-0.028
aa-0.026
Kids-0.024
 Su-0.023
Token't
Token ID470
Feature activation-9.38e-01

Pos logit contributions
aa+0.023
oe+0.022
Kids+0.022
oes+0.021
round+0.020
Neg logit contributions
 diary-0.019
 shield-0.019
es-0.018
oc-0.018
 shields-0.016
Token stand
Token ID1302
Feature activation-1.40e+00

Pos logit contributions
aa+0.027
oe+0.026
Kids+0.025
oes+0.025
round+0.023
Neg logit contributions
 diary-0.029
 shield-0.029
es-0.028
oc-0.028
 shields-0.026
Token it
Token ID340
Feature activation+1.48e-01

Pos logit contributions
aa+0.042
Kids+0.041
oe+0.040
oes+0.039
round+0.038
Neg logit contributions
 shield-0.041
 diary-0.041
es-0.040
oc-0.038
 shields-0.036
Token.
Token ID13
Feature activation+2.28e+00

Pos logit contributions
 diary+0.005
 shield+0.004
oc+0.004
es+0.004
 journal+0.004
Neg logit contributions
aa-0.004
oe-0.004
oes-0.004
Kids-0.004
round-0.004
Token
Token ID198
Feature activation+1.10e+00

Pos logit contributions
 shield+0.075
 diary+0.074
onel+0.069
es+0.069
oc+0.068
Neg logit contributions
oe-0.061
Kids-0.061
oes-0.058
aa-0.055
round-0.054
Token
Token ID198
Feature activation+3.80e+00

Pos logit contributions
 diary+0.036
 shield+0.036
es+0.035
oc+0.034
 shields+0.032
Neg logit contributions
aa-0.029
oe-0.028
Kids-0.027
oes-0.027
round-0.025
TokenOne
Token ID3198
Feature activation-6.09e-01

Pos logit contributions
 shield+0.138
 diary+0.135
onel+0.133
 Majesty+0.130
es+0.127
Neg logit contributions
Kids-0.089
oe-0.087
round-0.075
 weekend-0.073
 crowded-0.070
Token day
Token ID1110
Feature activation+3.25e+00

Pos logit contributions
aa+0.013
oe+0.012
Kids+0.012
oes+0.012
round+0.011
Neg logit contributions
 shield-0.023
 diary-0.023
oc-0.023
es-0.022
 journal-0.021
Token,
Token ID11
Feature activation+2.48e+00

Pos logit contributions
onel+0.124
 diary+0.122
 webs+0.122
 shield+0.122
 Majesty+0.118
Neg logit contributions
oe-0.075
Kids-0.064
 to-0.063
aa-0.058
 weekend-0.057
Token James
Token ID3700
Feature activation+3.20e-01

Pos logit contributions
onel+0.077
oc+0.074
 Majesty+0.074
 webs+0.073
 diary+0.073
Neg logit contributions
oe-0.071
 to-0.066
 weekend-0.066
Kids-0.064
 week-0.062
Token's
Token ID338
Feature activation+2.58e-01

Pos logit contributions
 diary+0.010
 shield+0.010
es+0.010
oc+0.009
 journal+0.009
Neg logit contributions
aa-0.009
oe-0.009
Kids-0.009
oes-0.009
round-0.008
Token and
Token ID290
Feature activation+9.67e-02

Pos logit contributions
 shield+0.015
 diary+0.015
oc+0.015
es+0.015
 shields+0.014
Neg logit contributions
aa-0.008
oe-0.007
Kids-0.007
oes-0.006
round-0.006
Token said
Token ID531
Feature activation+1.33e+00

Pos logit contributions
 diary+0.003
 shield+0.003
es+0.003
oc+0.003
 journal+0.003
Neg logit contributions
aa-0.003
oe-0.002
Kids-0.002
oes-0.002
round-0.002
Token,
Token ID11
Feature activation-1.38e+00

Pos logit contributions
 shield+0.040
 diary+0.039
oc+0.039
es+0.037
 shields+0.036
Neg logit contributions
aa-0.039
oe-0.038
Kids-0.036
oes-0.034
round-0.032
Token "
Token ID366
Feature activation-7.03e-02

Pos logit contributions
aa+0.050
oe+0.049
oes+0.048
Kids+0.048
ora+0.044
Neg logit contributions
 shield-0.031
es-0.031
 diary-0.031
oc-0.030
 Mickey-0.026
TokenLook
Token ID8567
Feature activation+2.91e+00

Pos logit contributions
aa+0.002
oe+0.002
oes+0.002
Kids+0.002
round+0.002
Neg logit contributions
 diary-0.002
 shield-0.002
oc-0.002
es-0.002
house-0.002
Token Max
Token ID5436
Feature activation+3.79e+00

Pos logit contributions
oc+0.103
 shield+0.098
 shields+0.098
 traps+0.097
istered+0.093
Neg logit contributions
aa-0.074
oe-0.069
 to-0.058
 Su-0.057
 Kay-0.056
Token,
Token ID11
Feature activation+9.19e-01

Pos logit contributions
 shield+0.136
 diary+0.133
 shields+0.133
oc+0.131
onel+0.131
Neg logit contributions
oe-0.091
aa-0.091
Kids-0.071
 to-0.070
oes-0.062
Token I
Token ID314
Feature activation+8.77e-01

Pos logit contributions
oc+0.032
es+0.031
istered+0.030
onel+0.028
 webs+0.028
Neg logit contributions
Kids-0.022
aa-0.021
oe-0.020
 to-0.019
oes-0.019
Token found
Token ID1043
Feature activation+1.56e+00

Pos logit contributions
 shield+0.030
 diary+0.030
 shields+0.029
es+0.029
 traps+0.028
Neg logit contributions
oe-0.021
aa-0.021
Kids-0.021
 sur-0.019
oes-0.018
Token my
Token ID616
Feature activation+1.13e+00

Pos logit contributions
oc+0.057
istered+0.055
house+0.053
 shield+0.051
ities+0.050
Neg logit contributions
 to-0.034
aa-0.031
oe-0.031
 Kay-0.029
 Sara-0.026
Token bow
Token ID9563
Feature activation+1.96e+00

Pos logit contributions
es+0.045
oc+0.044
vel+0.042
onel+0.041
istered+0.038
Neg logit contributions
oe-0.023
aa-0.020
oes-0.020
 to-0.019
 weekend-0.017
Token and
Token ID290
Feature activation+6.93e-01

Pos logit contributions
 diary+0.025
 shield+0.025
es+0.024
oc+0.023
 shields+0.022
Neg logit contributions
aa-0.021
oe-0.020
Kids-0.020
oes-0.019
round-0.018
Token said
Token ID531
Feature activation+1.83e+00

Pos logit contributions
oc+0.022
 diary+0.022
es+0.022
 shield+0.021
vel+0.020
Neg logit contributions
aa-0.020
Kids-0.018
oe-0.018
oes-0.017
round-0.016
Token,
Token ID11
Feature activation-8.13e-01

Pos logit contributions
oc+0.067
 diary+0.067
 shield+0.066
es+0.064
 shields+0.062
Neg logit contributions
aa-0.040
oe-0.038
 to-0.034
oes-0.034
Kids-0.032
Token "
Token ID366
Feature activation+6.89e-01

Pos logit contributions
aa+0.027
oe+0.027
Kids+0.026
oes+0.026
round+0.025
Neg logit contributions
 shield-0.021
 diary-0.021
es-0.020
oc-0.019
 shields-0.018
TokenMom
Token ID29252
Feature activation+2.46e+00

Pos logit contributions
 diary+0.025
 shield+0.025
es+0.025
oc+0.024
 shields+0.023
Neg logit contributions
aa-0.016
oe-0.015
Kids-0.015
oes-0.014
round-0.013
Tokenmy
Token ID1820
Feature activation+3.79e+00

Pos logit contributions
 shield+0.090
 diary+0.090
es+0.087
oc+0.086
 shields+0.083
Neg logit contributions
aa-0.057
oe-0.056
oes-0.053
Kids-0.051
round-0.045
Token,
Token ID11
Feature activation+1.26e+00

Pos logit contributions
 shield+0.134
 shields+0.132
 diary+0.131
es+0.128
onel+0.127
Neg logit contributions
aa-0.097
oe-0.094
oes-0.078
Kids-0.074
 to-0.071
Token boat
Token ID8848
Feature activation+1.32e+00

Pos logit contributions
es+0.043
oc+0.043
istered+0.039
 diary+0.039
 shields+0.038
Neg logit contributions
aa-0.031
oes-0.030
Kids-0.029
oe-0.029
 to-0.028
Token broke
Token ID6265
Feature activation+3.27e-01

Pos logit contributions
 diary+0.042
 shield+0.040
es+0.040
vel+0.038
 shields+0.038
Neg logit contributions
aa-0.040
oe-0.039
oes-0.036
Kids-0.032
guard-0.031
Token.
Token ID13
Feature activation+1.83e+00

Pos logit contributions
 diary+0.009
 shield+0.009
es+0.008
oc+0.008
 shields+0.008
Neg logit contributions
aa-0.011
oe-0.010
Kids-0.010
oes-0.010
round-0.010
Token Can
Token ID1680
Feature activation+1.65e+00

Pos logit contributions
 shield+0.060
 diary+0.059
es+0.058
 shields+0.055
oc+0.054
Neg logit contributions
aa-0.049
Kids-0.048
oes-0.047
oe-0.046
round-0.044
Token the
Token ID262
Feature activation-4.98e-01

Pos logit contributions
aa+0.020
Kids+0.020
round+0.020
oe+0.019
oes+0.019
Neg logit contributions
 diary-0.014
es-0.014
 shield-0.014
 traps-0.013
 webs-0.013
Token pool
Token ID5933
Feature activation-9.56e-01

Pos logit contributions
aa+0.012
oe+0.011
Kids+0.011
oes+0.011
round+0.010
Neg logit contributions
 diary-0.018
 shield-0.018
es-0.017
oc-0.017
 shields-0.016
Token.
Token ID13
Feature activation-3.35e-01

Pos logit contributions
aa+0.034
Kids+0.032
oe+0.031
oes+0.030
round+0.029
Neg logit contributions
es-0.023
 shield-0.023
 diary-0.023
oc-0.022
house-0.021
Token She
Token ID1375
Feature activation-1.20e+00

Pos logit contributions
aa+0.010
oe+0.010
Kids+0.010
oes+0.009
round+0.009
Neg logit contributions
 diary-0.010
 shield-0.009
es-0.009
oc-0.009
house-0.009
Token let
Token ID1309
Feature activation-1.31e-01

Pos logit contributions
oes+0.034
aa+0.034
oe+0.032
Kids+0.031
round+0.030
Neg logit contributions
 shield-0.038
es-0.037
oc-0.036
 diary-0.036
 shields-0.034
Token go
Token ID467
Feature activation-4.82e+00

Pos logit contributions
aa+0.004
oe+0.004
Kids+0.003
oes+0.003
round+0.003
Neg logit contributions
 diary-0.004
 shield-0.004
es-0.004
oc-0.004
house-0.004
Token of
Token ID286
Feature activation-2.66e+00

Pos logit contributions
 pastor+0.170
Kids+0.167
 groom+0.166
 Abbey+0.163
iya+0.161
Neg logit contributions
oc-0.107
es-0.097
house-0.088
 shield-0.078
 weapon-0.075
Token her
Token ID607
Feature activation-1.32e-01

Pos logit contributions
aa+0.090
oe+0.088
Kids+0.087
oes+0.086
round+0.086
Neg logit contributions
 shield-0.066
es-0.065
 diary-0.065
 traps-0.059
 webs-0.059
Token unicorn
Token ID44986
Feature activation-8.77e-01

Pos logit contributions
aa+0.004
oe+0.004
oes+0.004
Kids+0.004
round+0.003
Neg logit contributions
es-0.004
vel-0.004
 shield-0.004
 diary-0.004
oc-0.004
Token and
Token ID290
Feature activation-3.28e-01

Pos logit contributions
aa+0.022
oe+0.021
oes+0.019
Kids+0.018
round+0.018
Neg logit contributions
 diary-0.030
 shield-0.029
oc-0.029
es-0.028
 Majesty-0.028
Token ran
Token ID4966
Feature activation-2.32e+00

Pos logit contributions
aa+0.008
oe+0.007
Kids+0.007
oes+0.007
round+0.006
Neg logit contributions
 shield-0.012
 diary-0.012
es-0.011
oc-0.011
 shields-0.011
Token.
Token ID13
Feature activation-1.67e+00

Pos logit contributions
Kids+0.068
aa+0.065
 weekend+0.060
oe+0.060
oes+0.059
Neg logit contributions
es-0.039
oc-0.032
 shield-0.031
house-0.030
 diary-0.030
Token They
Token ID1119
Feature activation+1.52e-01

Pos logit contributions
oe+0.054
aa+0.053
Kids+0.049
oes+0.048
guard+0.048
Neg logit contributions
 diary-0.042
es-0.042
oc-0.041
 shield-0.040
house-0.040
Token sit
Token ID1650
Feature activation-2.35e+00

Pos logit contributions
 shield+0.005
 diary+0.005
es+0.005
oc+0.005
 shields+0.004
Neg logit contributions
aa-0.004
oe-0.004
Kids-0.004
oes-0.004
round-0.004
Token on
Token ID319
Feature activation-6.23e-01

Pos logit contributions
Kids+0.091
aa+0.086
oes+0.083
leaf+0.082
 Kay+0.080
Neg logit contributions
es-0.057
 shield-0.047
 diary-0.046
house-0.045
oc-0.041
Token each
Token ID1123
Feature activation-9.09e-01

Pos logit contributions
aa+0.020
Kids+0.019
oes+0.019
oe+0.019
round+0.018
Neg logit contributions
 shield-0.017
 diary-0.017
es-0.016
oc-0.016
 shields-0.015
Token end
Token ID886
Feature activation-4.80e+00

Pos logit contributions
aa+0.034
Kids+0.033
oe+0.032
oes+0.030
 sur+0.030
Neg logit contributions
oc-0.019
 shield-0.018
es-0.018
 diary-0.017
house-0.016
Token.
Token ID13
Feature activation-1.79e+00

Pos logit contributions
please+0.208
Kids+0.202
leaf+0.202
aa+0.202
round+0.202
Neg logit contributions
es-0.060
house-0.043
 diary-0.043
 traps-0.038
 something-0.037
Token They
Token ID1119
Feature activation+7.77e-01

Pos logit contributions
oe+0.061
aa+0.059
guard+0.057
round+0.057
oes+0.055
Neg logit contributions
es-0.041
 Something-0.040
 diary-0.039
oc-0.038
house-0.037
Token push
Token ID4574
Feature activation-1.60e+00

Pos logit contributions
 diary+0.025
 shield+0.024
es+0.024
oc+0.023
 shields+0.022
Neg logit contributions
aa-0.022
oe-0.021
Kids-0.020
oes-0.020
round-0.019
Token with
Token ID351
Feature activation+1.53e-01

Pos logit contributions
aa+0.046
oe+0.046
Kids+0.046
oes+0.045
 weekend+0.043
Neg logit contributions
es-0.048
 shield-0.044
 diary-0.044
oc-0.044
 webs-0.041
Token their
Token ID511
Feature activation+2.98e-01

Pos logit contributions
 diary+0.006
 shield+0.005
oc+0.005
es+0.005
house+0.005
Neg logit contributions
aa-0.004
oe-0.003
Kids-0.003
oes-0.003
round-0.003
Token fish
Token ID5916
Feature activation-1.81e+00

Pos logit contributions
aa+0.011
oe+0.010
Kids+0.010
oes+0.010
round+0.009
Neg logit contributions
 shield-0.017
 diary-0.017
es-0.017
oc-0.016
 shields-0.016
Token.
Token ID13
Feature activation-2.40e+00

Pos logit contributions
Kids+0.059
aa+0.058
oe+0.057
oes+0.055
round+0.053
Neg logit contributions
es-0.050
 shield-0.048
 diary-0.047
oc-0.046
house-0.042
Token They
Token ID1119
Feature activation-1.76e+00

Pos logit contributions
aa+0.082
oes+0.077
oe+0.075
 sur+0.072
round+0.072
Neg logit contributions
house-0.056
es-0.056
oc-0.055
 diary-0.055
 Mickey-0.052
Token wanted
Token ID2227
Feature activation-2.51e+00

Pos logit contributions
oe+0.052
aa+0.051
oes+0.050
Kids+0.049
round+0.046
Neg logit contributions
 shield-0.053
es-0.050
 diary-0.050
oc-0.047
 shields-0.047
Token to
Token ID284
Feature activation-2.01e+00

Pos logit contributions
oe+0.071
Kids+0.071
aa+0.070
round+0.066
ora+0.063
Neg logit contributions
 something-0.077
 traps-0.075
 shield-0.075
 no-0.072
 nothing-0.072
Token go
Token ID467
Feature activation-4.67e+00

Pos logit contributions
Kids+0.068
aa+0.067
oe+0.066
oes+0.060
round+0.058
Neg logit contributions
 shield-0.051
oc-0.047
house-0.047
 diary-0.045
 shields-0.042
Token closer
Token ID5699
Feature activation-2.70e+00

Pos logit contributions
Kids+0.169
 pastor+0.163
 Abbey+0.149
aa+0.149
iza+0.144
Neg logit contributions
house-0.106
 shield-0.098
oc-0.098
es-0.095
 weapon-0.090
Token and
Token ID290
Feature activation-7.07e-01

Pos logit contributions
Kids+0.090
aa+0.081
oe+0.073
 sur+0.072
Ice+0.071
Neg logit contributions
es-0.083
 shield-0.074
 diary-0.069
oc-0.068
house-0.067
Token feed
Token ID3745
Feature activation-2.72e+00

Pos logit contributions
aa+0.021
Kids+0.020
oe+0.019
oes+0.018
round+0.017
Neg logit contributions
 shield-0.022
 diary-0.021
oc-0.020
house-0.019
es-0.019
Token them
Token ID606
Feature activation-9.90e-01

Pos logit contributions
aa+0.084
Kids+0.083
oe+0.083
 sur+0.079
round+0.076
Neg logit contributions
es-0.080
oc-0.072
 shield-0.071
 diary-0.067
 traps-0.065
Token.
Token ID13
Feature activation-2.36e+00

Pos logit contributions
aa+0.030
oe+0.029
Kids+0.027
oes+0.027
round+0.026
Neg logit contributions
 diary-0.030
 shield-0.029
es-0.028
oc-0.028
 journal-0.026
Token down
Token ID866
Feature activation-1.12e+00

Pos logit contributions
aa+0.047
Kids+0.043
oe+0.043
oes+0.040
ora+0.039
Neg logit contributions
 shield-0.042
 diary-0.040
es-0.038
house-0.037
 webs-0.036
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
aa+0.049
Kids+0.047
oes+0.044
round+0.043
iki+0.042
Neg logit contributions
es-0.019
 shield-0.017
 diary-0.016
 traps-0.016
house-0.016
Token Lily
Token ID20037
Feature activation-2.40e+00

Pos logit contributions
aa+0.037
oe+0.036
Kids+0.035
oes+0.034
round+0.032
Neg logit contributions
 diary-0.042
 shield-0.042
es-0.041
oc-0.040
 shields-0.038
Token wanted
Token ID2227
Feature activation-1.94e+00

Pos logit contributions
oes+0.072
aa+0.071
oe+0.070
Kids+0.069
round+0.064
Neg logit contributions
es-0.068
 shield-0.066
oc-0.066
 diary-0.065
house-0.062
Token to
Token ID284
Feature activation-2.28e+00

Pos logit contributions
aa+0.052
oe+0.052
Kids+0.051
round+0.048
ora+0.047
Neg logit contributions
 diary-0.064
 something-0.064
 shield-0.064
es-0.060
 nothing-0.059
Token go
Token ID467
Feature activation-4.66e+00

Pos logit contributions
Kids+0.079
aa+0.075
oe+0.074
oes+0.066
ora+0.064
Neg logit contributions
 shield-0.059
house-0.053
 diary-0.052
oc-0.049
 brain-0.046
Token closer
Token ID5699
Feature activation-2.53e+00

Pos logit contributions
Kids+0.183
 pastor+0.168
aney+0.158
aa+0.154
 Abbey+0.151
Neg logit contributions
house-0.094
 something-0.079
 shield-0.078
 whatever-0.075
 anywhere-0.075
Token and
Token ID290
Feature activation-7.98e-01

Pos logit contributions
Kids+0.088
aa+0.082
oe+0.075
oes+0.074
leaf+0.072
Neg logit contributions
es-0.071
 shield-0.065
 diary-0.062
oc-0.057
house-0.056
Token see
Token ID766
Feature activation-4.10e-01

Pos logit contributions
aa+0.023
Kids+0.023
oe+0.022
oes+0.020
round+0.019
Neg logit contributions
 shield-0.025
 diary-0.024
house-0.022
 journal-0.022
oc-0.022
Token the
Token ID262
Feature activation-2.53e+00

Pos logit contributions
aa+0.015
oe+0.014
Kids+0.014
oes+0.014
round+0.013
Neg logit contributions
 diary-0.010
 shield-0.010
es-0.009
oc-0.009
 shields-0.008
Token water
Token ID1660
Feature activation-1.87e+00

Pos logit contributions
aa+0.074
oes+0.068
Kids+0.065
round+0.064
oe+0.059
Neg logit contributions
 shield-0.071
 diary-0.071
 wishes-0.070
 webs-0.068
 journal-0.065
Token swing
Token ID9628
Feature activation-7.65e-01

Pos logit contributions
aa+0.001
oe+0.001
Kids+0.001
oes+0.001
round+0.001
Neg logit contributions
 diary-0.001
 shield-0.001
es-0.001
oc-0.001
 shields-0.001
Token.
Token ID13
Feature activation-1.25e+00

Pos logit contributions
aa+0.024
Kids+0.024
oe+0.022
oes+0.022
 sur+0.020
Neg logit contributions
 diary-0.021
es-0.021
 shield-0.021
oc-0.020
house-0.020
Token Tom
Token ID4186
Feature activation-1.38e+00

Pos logit contributions
aa+0.043
oe+0.040
oes+0.039
Kids+0.039
round+0.037
Neg logit contributions
 diary-0.031
es-0.031
 shield-0.031
oc-0.031
house-0.029
Token wants
Token ID3382
Feature activation-2.36e+00

Pos logit contributions
aa+0.047
oe+0.045
Kids+0.045
oes+0.043
round+0.041
Neg logit contributions
 shield-0.035
es-0.035
 diary-0.035
oc-0.034
 shields-0.030
Token to
Token ID284
Feature activation-2.31e+00

Pos logit contributions
Kids+0.061
aa+0.059
ora+0.058
oe+0.058
 sur+0.053
Neg logit contributions
 shield-0.078
 traps-0.076
 shields-0.075
es-0.074
 bones-0.074
Token go
Token ID467
Feature activation-4.64e+00

Pos logit contributions
Kids+0.079
aa+0.075
oe+0.071
oes+0.067
round+0.066
Neg logit contributions
 shield-0.057
 diary-0.053
house-0.052
es-0.048
 webs-0.047
Token on
Token ID319
Feature activation-1.18e+00

Pos logit contributions
Kids+0.188
 pastor+0.167
iya+0.165
Ice+0.163
 Abbey+0.161
Neg logit contributions
house-0.092
 shield-0.078
es-0.074
 diary-0.071
 weapon-0.071
Token the
Token ID262
Feature activation-1.34e+00

Pos logit contributions
aa+0.040
Kids+0.039
oes+0.038
oe+0.037
round+0.035
Neg logit contributions
 shield-0.031
 diary-0.030
es-0.028
 shields-0.027
oc-0.027
Token swing
Token ID9628
Feature activation-1.94e+00

Pos logit contributions
aa+0.040
Kids+0.039
oe+0.037
oes+0.036
 sur+0.034
Neg logit contributions
 shield-0.041
 diary-0.041
 webs-0.036
house-0.036
 journal-0.036
Token.
Token ID13
Feature activation-1.59e+00

Pos logit contributions
Kids+0.070
aa+0.068
oe+0.062
oes+0.060
 sur+0.059
Neg logit contributions
es-0.046
 shield-0.045
 diary-0.044
oc-0.044
house-0.043
Token He
Token ID679
Feature activation-1.37e+00

Pos logit contributions
aa+0.061
oe+0.058
Kids+0.058
oes+0.056
 weekend+0.055
Neg logit contributions
oc-0.032
es-0.030
 shield-0.028
house-0.028
 diary-0.028
Token Tom
Token ID4186
Feature activation-2.10e+00

Pos logit contributions
aa+0.047
oe+0.047
Kids+0.045
oes+0.044
round+0.041
Neg logit contributions
 shield-0.044
 diary-0.044
es-0.043
oc-0.042
 shields-0.040
Token and
Token ID290
Feature activation-1.40e+00

Pos logit contributions
aa+0.056
oe+0.055
Kids+0.053
oes+0.052
round+0.048
Neg logit contributions
 shield-0.068
es-0.068
 diary-0.066
oc-0.066
 shields-0.061
Token Sam
Token ID3409
Feature activation-5.86e-02

Pos logit contributions
aa+0.047
oe+0.047
Kids+0.045
oes+0.044
round+0.042
Neg logit contributions
 shield-0.036
 diary-0.036
es-0.035
oc-0.034
 shields-0.032
Token want
Token ID765
Feature activation-2.27e+00

Pos logit contributions
aa+0.002
oe+0.002
Kids+0.002
oes+0.002
round+0.002
Neg logit contributions
 diary-0.002
 shield-0.002
es-0.002
oc-0.002
 journal-0.002
Token to
Token ID284
Feature activation-2.40e+00

Pos logit contributions
oe+0.060
aa+0.055
Kids+0.054
round+0.051
ora+0.051
Neg logit contributions
 shield-0.074
 traps-0.073
es-0.073
 something-0.071
 bones-0.068
Token go
Token ID467
Feature activation-4.61e+00

Pos logit contributions
Kids+0.079
oe+0.075
aa+0.075
oes+0.068
round+0.066
Neg logit contributions
 shield-0.065
oc-0.059
 diary-0.058
house-0.058
 shields-0.055
Token near
Token ID1474
Feature activation-1.79e+00

Pos logit contributions
Kids+0.162
 pastor+0.149
aa+0.145
 Abbey+0.141
iza+0.136
Neg logit contributions
house-0.109
 shield-0.104
oc-0.101
es-0.098
 weapon-0.095
Token the
Token ID262
Feature activation-2.01e+00

Pos logit contributions
aa+0.051
oe+0.048
Kids+0.047
oes+0.046
round+0.043
Neg logit contributions
 diary-0.057
 shield-0.056
es-0.055
oc-0.054
 shields-0.050
Token pond
Token ID16723
Feature activation-1.33e+00

Pos logit contributions
aa+0.051
Kids+0.049
oe+0.048
oes+0.048
round+0.044
Neg logit contributions
 shield-0.068
 diary-0.066
oc-0.065
es-0.064
 traps-0.061
Token and
Token ID290
Feature activation-6.57e-01

Pos logit contributions
Kids+0.047
aa+0.047
oe+0.043
oes+0.042
round+0.041
Neg logit contributions
 shield-0.033
es-0.032
 diary-0.031
oc-0.030
house-0.029
Token feed
Token ID3745
Feature activation-2.53e+00

Pos logit contributions
aa+0.019
oe+0.018
Kids+0.018
oes+0.017
round+0.016
Neg logit contributions
 shield-0.021
 diary-0.020
es-0.019
oc-0.019
 shields-0.018
Token ducks
Token ID39694
Feature activation-1.97e+00

Pos logit contributions
aa+0.057
oe+0.056
Kids+0.055
oes+0.053
round+0.049
Neg logit contributions
 shield-0.096
 diary-0.093
oc-0.093
es-0.093
 traps-0.088
Token.
Token ID13
Feature activation-1.99e+00

Pos logit contributions
aa+0.065
Kids+0.064
oe+0.062
oes+0.059
round+0.057
Neg logit contributions
 shield-0.052
es-0.051
 diary-0.051
oc-0.049
house-0.045
Token Rex
Token ID17853
Feature activation-2.39e+00

Pos logit contributions
aa+0.062
oe+0.061
Kids+0.058
oes+0.056
 sur+0.054
Neg logit contributions
es-0.053
oc-0.053
house-0.050
 shield-0.050
 diary-0.048
Token wants
Token ID3382
Feature activation-2.65e+00

Pos logit contributions
aa+0.069
oe+0.068
oes+0.066
Kids+0.066
round+0.061
Neg logit contributions
 shield-0.073
es-0.071
 diary-0.070
oc-0.069
 shields-0.065
Token to
Token ID284
Feature activation-2.64e+00

Pos logit contributions
oe+0.070
Kids+0.063
round+0.063
aa+0.062
 sur+0.059
Neg logit contributions
 traps-0.086
es-0.085
 shield-0.084
 something-0.082
 bones-0.082
Token go
Token ID467
Feature activation-4.59e+00

Pos logit contributions
Kids+0.080
oe+0.078
aa+0.077
oes+0.072
round+0.069
Neg logit contributions
 shield-0.077
oc-0.072
 diary-0.071
house-0.069
es-0.067
Token too
Token ID1165
Feature activation-2.09e+00

Pos logit contributions
Kids+0.178
 pastor+0.165
leaf+0.151
 Abbey+0.151
aa+0.150
Neg logit contributions
house-0.102
oc-0.098
 shield-0.086
es-0.083
 weapon-0.077
Token.
Token ID13
Feature activation-2.17e+00

Pos logit contributions
Kids+0.084
aa+0.076
oes+0.073
oe+0.071
round+0.070
Neg logit contributions
 shield-0.043
oc-0.041
es-0.040
 diary-0.038
 traps-0.036
Token He
Token ID679
Feature activation-1.95e+00

Pos logit contributions
aa+0.075
oe+0.074
oes+0.071
Kids+0.071
round+0.067
Neg logit contributions
oc-0.050
es-0.049
 shield-0.045
house-0.043
 diary-0.043
Token likes
Token ID7832
Feature activation-3.54e+00

Pos logit contributions
aa+0.055
oe+0.053
Kids+0.053
oes+0.051
round+0.048
Neg logit contributions
 shield-0.062
 diary-0.060
es-0.058
oc-0.057
 shields-0.055
Token water
Token ID1660
Feature activation-2.06e+00

Pos logit contributions
oe+0.127
Kids+0.111
aa+0.106
oes+0.106
ok+0.106
Neg logit contributions
 shield-0.097
 traps-0.096
 shields-0.091
 bones-0.088
 knights-0.085
Token likes
Token ID7832
Feature activation-3.09e+00

Pos logit contributions
aa+0.003
oe+0.003
Kids+0.003
oes+0.003
round+0.002
Neg logit contributions
 diary-0.003
 shield-0.003
es-0.003
oc-0.003
 journal-0.003
Token it
Token ID340
Feature activation+1.07e+00

Pos logit contributions
oe+0.103
aa+0.100
Kids+0.098
oes+0.094
round+0.093
Neg logit contributions
 shield-0.087
 diary-0.083
es-0.079
 shields-0.077
 webs-0.077
Token.
Token ID13
Feature activation-1.09e+00

Pos logit contributions
 diary+0.039
oc+0.038
 shield+0.038
es+0.036
 shields+0.036
Neg logit contributions
oes-0.023
aa-0.023
oe-0.022
Kids-0.019
round-0.019
Token He
Token ID679
Feature activation-8.96e-01

Pos logit contributions
aa+0.039
oe+0.037
Kids+0.037
oes+0.035
round+0.034
Neg logit contributions
 shield-0.026
 diary-0.026
oc-0.025
es-0.025
house-0.023
Token lets
Token ID8781
Feature activation-1.47e+00

Pos logit contributions
aa+0.027
oe+0.026
Kids+0.025
oes+0.025
round+0.023
Neg logit contributions
 diary-0.027
 shield-0.027
es-0.026
oc-0.025
 shields-0.024
Token go
Token ID467
Feature activation-4.59e+00

Pos logit contributions
aa+0.043
Kids+0.042
oe+0.042
oes+0.040
round+0.038
Neg logit contributions
 shield-0.044
 diary-0.044
es-0.043
oc-0.042
house-0.039
Token of
Token ID286
Feature activation-2.37e+00

Pos logit contributions
Kids+0.155
 Abbey+0.151
 pastor+0.149
 Kay+0.146
Fre+0.145
Neg logit contributions
oc-0.120
es-0.105
house-0.093
 shield-0.086
 weapon-0.078
Token the
Token ID262
Feature activation-2.48e+00

Pos logit contributions
aa+0.065
oe+0.062
Kids+0.061
oes+0.059
round+0.055
Neg logit contributions
 diary-0.076
 shield-0.075
es-0.074
oc-0.073
 journal-0.068
Token car
Token ID1097
Feature activation-2.21e+00

Pos logit contributions
aa+0.071
oes+0.068
Kids+0.068
oe+0.068
round+0.063
Neg logit contributions
 shield-0.076
 diary-0.074
oc-0.071
es-0.070
house-0.066
Token and
Token ID290
Feature activation-3.58e-01

Pos logit contributions
Kids+0.072
aa+0.069
oe+0.065
 Abbey+0.062
Ab+0.062
Neg logit contributions
 shield-0.063
es-0.062
 diary-0.061
oc-0.060
house-0.059
Token reaches
Token ID12229
Feature activation+2.28e-01

Pos logit contributions
aa+0.009
oe+0.009
Kids+0.009
oes+0.008
round+0.008
Neg logit contributions
 diary-0.012
 shield-0.012
es-0.012
oc-0.012
 journal-0.011
Token it
Token ID340
Feature activation-8.21e-01

Pos logit contributions
aa+0.059
Kids+0.055
oe+0.055
oes+0.055
round+0.051
Neg logit contributions
 shield-0.051
 diary-0.050
es-0.049
oc-0.049
 shields-0.045
Token.
Token ID13
Feature activation-1.86e+00

Pos logit contributions
aa+0.027
Kids+0.027
oe+0.026
oes+0.025
round+0.024
Neg logit contributions
 shield-0.022
 diary-0.022
es-0.021
oc-0.020
house-0.019
Token Lily
Token ID20037
Feature activation-1.55e+00

Pos logit contributions
aa+0.061
oes+0.057
oe+0.057
Kids+0.055
round+0.054
Neg logit contributions
 diary-0.049
es-0.048
 shield-0.047
oc-0.046
house-0.046
Token wanted
Token ID2227
Feature activation-2.70e+00

Pos logit contributions
aa+0.044
oe+0.043
oes+0.042
Kids+0.042
round+0.039
Neg logit contributions
 shield-0.047
es-0.047
 diary-0.046
oc-0.046
house-0.042
Token to
Token ID284
Feature activation-2.15e+00

Pos logit contributions
oe+0.082
Kids+0.078
arl+0.076
aa+0.076
round+0.074
Neg logit contributions
 something-0.079
 no-0.071
 traps-0.070
 shield-0.069
es-0.068
Token go
Token ID467
Feature activation-4.54e+00

Pos logit contributions
Kids+0.075
oe+0.072
aa+0.071
oes+0.063
round+0.062
Neg logit contributions
 shield-0.054
oc-0.048
house-0.047
 diary-0.045
 shields-0.043
Token on
Token ID319
Feature activation-1.72e+00

Pos logit contributions
Kids+0.166
 pastor+0.156
aa+0.145
 Abbey+0.145
aney+0.142
Neg logit contributions
house-0.099
 shield-0.097
oc-0.093
 weapon-0.090
es-0.087
Token the
Token ID262
Feature activation-2.03e+00

Pos logit contributions
aa+0.065
oes+0.062
Kids+0.062
oe+0.061
round+0.058
Neg logit contributions
 shield-0.040
 diary-0.038
es-0.036
 shields-0.034
 traps-0.034
Token water
Token ID1660
Feature activation-2.11e+00

Pos logit contributions
Kids+0.056
aa+0.055
oe+0.053
oes+0.051
round+0.047
Neg logit contributions
 shield-0.063
 diary-0.057
 traps-0.057
oc-0.057
 webs-0.057
Token in
Token ID287
Feature activation-1.12e+00

Pos logit contributions
Kids+0.081
aa+0.078
oe+0.073
leaf+0.069
oes+0.069
Neg logit contributions
 shield-0.047
es-0.045
 diary-0.042
house-0.041
oc-0.041
Token a
Token ID257
Feature activation-1.73e+00

Pos logit contributions
aa+0.035
Kids+0.033
oe+0.033
oes+0.032
round+0.031
Neg logit contributions
 diary-0.033
 shield-0.032
es-0.031
oc-0.030
house-0.028
Token plant
Token ID4618
Feature activation-3.76e-01

Pos logit contributions
aa+0.026
oe+0.024
Kids+0.024
oes+0.024
round+0.022
Neg logit contributions
 diary-0.026
 shield-0.026
es-0.024
oc-0.024
 journal-0.023
Token and
Token ID290
Feature activation+3.12e-01

Pos logit contributions
aa+0.009
oe+0.008
Kids+0.008
oes+0.008
round+0.008
Neg logit contributions
 diary-0.014
 shield-0.013
es-0.013
oc-0.013
 journal-0.012
Token each
Token ID1123
Feature activation-1.33e+00

Pos logit contributions
 diary+0.011
 shield+0.011
es+0.010
oc+0.010
 shields+0.010
Neg logit contributions
aa-0.008
oe-0.007
Kids-0.007
oes-0.007
round-0.007
Token grab
Token ID5552
Feature activation-6.67e-01

Pos logit contributions
aa+0.037
Kids+0.036
oe+0.034
round+0.034
oes+0.033
Neg logit contributions
 shield-0.043
 diary-0.042
oc-0.041
es-0.040
 journal-0.038
Token one
Token ID530
Feature activation-2.08e+00

Pos logit contributions
aa+0.022
Kids+0.021
oe+0.021
oes+0.020
round+0.019
Neg logit contributions
 shield-0.018
 diary-0.018
es-0.018
oc-0.017
 shields-0.016
Token end
Token ID886
Feature activation-4.53e+00

Pos logit contributions
Kids+0.070
aa+0.069
oe+0.064
oes+0.061
round+0.061
Neg logit contributions
 diary-0.056
 shield-0.056
es-0.053
oc-0.052
 journal-0.049
Token of
Token ID286
Feature activation-1.92e+00

Pos logit contributions
Kids+0.194
aa+0.184
round+0.176
 sur+0.176
 pastor+0.169
Neg logit contributions
es-0.091
 diary-0.078
house-0.073
 shield-0.072
 journal-0.067
Token the
Token ID262
Feature activation-1.75e+00

Pos logit contributions
aa+0.072
round+0.069
oes+0.068
Kids+0.065
oe+0.063
Neg logit contributions
 shield-0.041
es-0.040
 diary-0.039
 Mickey-0.037
oc-0.035
Token squash
Token ID34613
Feature activation-9.40e-01

Pos logit contributions
aa+0.054
Kids+0.051
oe+0.051
oes+0.049
round+0.048
Neg logit contributions
 diary-0.052
 shield-0.051
es-0.049
oc-0.048
 journal-0.046
Token.
Token ID13
Feature activation-9.25e-01

Pos logit contributions
aa+0.030
Kids+0.029
oe+0.028
oes+0.027
round+0.026
Neg logit contributions
 diary-0.026
 shield-0.026
es-0.026
oc-0.025
 journal-0.023
Token They
Token ID1119
Feature activation-2.46e-01

Pos logit contributions
aa+0.029
oe+0.027
oes+0.027
Kids+0.026
round+0.025
Neg logit contributions
es-0.026
 diary-0.026
 shield-0.025
oc-0.024
house-0.023
Token think
Token ID892
Feature activation-1.48e+00

Pos logit contributions
aa+0.038
oe+0.037
Kids+0.036
oes+0.035
round+0.033
Neg logit contributions
 diary-0.045
 shield-0.045
es-0.044
oc-0.043
 shields-0.041
Token we
Token ID356
Feature activation-4.43e-01

Pos logit contributions
aa+0.051
Kids+0.050
oe+0.049
oes+0.046
round+0.045
Neg logit contributions
 diary-0.038
 shield-0.037
es-0.036
 journal-0.033
oc-0.032
Token can
Token ID460
Feature activation-1.51e+00

Pos logit contributions
aa+0.012
oes+0.012
oe+0.011
Kids+0.011
round+0.010
Neg logit contributions
 diary-0.014
es-0.013
 shield-0.013
oc-0.013
 shields-0.012
Token find
Token ID1064
Feature activation-2.03e-01

Pos logit contributions
aa+0.045
Kids+0.043
oe+0.043
oes+0.040
round+0.039
Neg logit contributions
 shield-0.046
 diary-0.045
es-0.044
oc-0.043
 journal-0.040
Token the
Token ID262
Feature activation-8.99e-01

Pos logit contributions
aa+0.006
oe+0.006
Kids+0.006
oes+0.006
round+0.006
Neg logit contributions
 diary-0.006
 shield-0.006
es-0.005
oc-0.005
 shields-0.005
Token end
Token ID886
Feature activation-4.53e+00

Pos logit contributions
aa+0.024
Kids+0.022
oe+0.020
round+0.020
oes+0.019
Neg logit contributions
 diary-0.032
 shield-0.032
 journal-0.029
 webs-0.029
oc-0.028
Token of
Token ID286
Feature activation-1.31e+00

Pos logit contributions
aa+0.157
 sur+0.156
Kids+0.156
 Abbey+0.143
Fre+0.138
Neg logit contributions
es-0.117
house-0.116
 diary-0.111
 journal-0.098
oc-0.093
Token the
Token ID262
Feature activation-1.37e+00

Pos logit contributions
aa+0.044
Kids+0.042
oe+0.041
oes+0.040
round+0.039
Neg logit contributions
 diary-0.036
 shield-0.035
es-0.033
oc-0.032
 journal-0.031
Token rainbow
Token ID27223
Feature activation-2.13e+00

Pos logit contributions
aa+0.039
Kids+0.037
round+0.033
oe+0.032
oes+0.031
Neg logit contributions
 diary-0.047
 shield-0.045
 journal-0.042
 webs-0.041
house-0.041
Token?"
Token ID1701
Feature activation-1.80e+00

Pos logit contributions
aa+0.076
Kids+0.075
oe+0.069
oes+0.066
 sur+0.066
Neg logit contributions
 diary-0.053
es-0.052
 shield-0.051
house-0.048
 journal-0.046
Token Lily
Token ID20037
Feature activation-1.96e+00

Pos logit contributions
aa+0.055
oe+0.053
Kids+0.051
oes+0.051
round+0.049
Neg logit contributions
 shield-0.053
 diary-0.052
es-0.050
oc-0.050
 shields-0.046
Token slide
Token ID10649
Feature activation-2.08e+00

Pos logit contributions
aa+0.028
Kids+0.027
oe+0.027
oes+0.026
round+0.024
Neg logit contributions
 shield-0.030
 diary-0.030
oc-0.028
es-0.028
 journal-0.027
Token.
Token ID13
Feature activation-1.96e+00

Pos logit contributions
Kids+0.086
aa+0.083
Fre+0.078
 Abbey+0.077
leaf+0.077
Neg logit contributions
house-0.040
es-0.034
oc-0.032
 shield-0.028
 diary-0.028
Token Sara
Token ID24799
Feature activation-1.80e+00

Pos logit contributions
aa+0.066
oe+0.062
oes+0.060
Kids+0.058
round+0.056
Neg logit contributions
oc-0.048
es-0.048
 diary-0.048
house-0.046
 shield-0.045
Token wants
Token ID3382
Feature activation-2.37e+00

Pos logit contributions
aa+0.062
oe+0.061
Kids+0.060
oes+0.059
round+0.056
Neg logit contributions
es-0.045
 shield-0.042
oc-0.042
 diary-0.041
 webs-0.037
Token to
Token ID284
Feature activation-2.19e+00

Pos logit contributions
ora+0.070
Kids+0.068
oe+0.066
aa+0.066
 sur+0.065
Neg logit contributions
 something-0.068
 nothing-0.063
 no-0.063
 bones-0.062
 anything-0.060
Token go
Token ID467
Feature activation-4.51e+00

Pos logit contributions
Kids+0.080
aa+0.075
oe+0.070
ho+0.068
ora+0.067
Neg logit contributions
 shield-0.048
house-0.044
oc-0.039
 diary-0.039
 whatever-0.038
Token first
Token ID717
Feature activation-2.06e+00

Pos logit contributions
Kids+0.189
iya+0.172
 pastor+0.166
Fre+0.165
aa+0.164
Neg logit contributions
house-0.073
 whatever-0.058
 shield-0.056
es-0.055
 anywhere-0.055
Token.
Token ID13
Feature activation-1.59e+00

Pos logit contributions
aa+0.085
Kids+0.084
oes+0.077
leaf+0.077
oe+0.075
Neg logit contributions
es-0.038
 diary-0.033
 shield-0.032
house-0.031
oc-0.028
Token She
Token ID1375
Feature activation-1.21e+00

Pos logit contributions
oe+0.054
aa+0.053
round+0.051
Kids+0.050
oes+0.050
Neg logit contributions
 diary-0.036
es-0.035
oc-0.034
 shield-0.033
house-0.031
Token runs
Token ID4539
Feature activation-2.47e+00

Pos logit contributions
aa+0.034
oe+0.034
Kids+0.033
oes+0.033
round+0.030
Neg logit contributions
 shield-0.037
 diary-0.036
es-0.035
oc-0.035
 shields-0.033
Token to
Token ID284
Feature activation-9.46e-01

Pos logit contributions
Kids+0.064
aa+0.061
iki+0.060
oes+0.058
argo+0.055
Neg logit contributions
es-0.071
 shield-0.066
house-0.066
 diary-0.066
 something-0.064
Token big
Token ID1263
Feature activation-7.76e-01

Pos logit contributions
aa+0.008
oes+0.008
Kids+0.008
oe+0.007
round+0.007
Neg logit contributions
 diary-0.009
 shield-0.008
 journal-0.008
oc-0.008
house-0.007
Token slide
Token ID10649
Feature activation-1.36e+00

Pos logit contributions
aa+0.023
Kids+0.022
oes+0.022
oe+0.021
round+0.019
Neg logit contributions
 diary-0.024
 shield-0.024
oc-0.023
es-0.022
 journal-0.021
Token and
Token ID290
Feature activation+3.67e-01

Pos logit contributions
Kids+0.053
aa+0.052
leaf+0.047
Fre+0.047
 Abbey+0.047
Neg logit contributions
house-0.030
es-0.027
 diary-0.025
oc-0.024
 shield-0.024
Token wanted
Token ID2227
Feature activation-2.12e+00

Pos logit contributions
 shield+0.011
 diary+0.011
es+0.011
oc+0.010
 shields+0.010
Neg logit contributions
aa-0.011
oe-0.010
oes-0.010
Kids-0.010
round-0.009
Token to
Token ID284
Feature activation-1.75e+00

Pos logit contributions
aa+0.057
Kids+0.054
 sur+0.052
ora+0.051
oe+0.047
Neg logit contributions
 diary-0.067
es-0.066
 something-0.065
 nothing-0.064
 no-0.064
Token go
Token ID467
Feature activation-4.49e+00

Pos logit contributions
Kids+0.063
aa+0.063
oe+0.056
ho+0.052
ora+0.052
Neg logit contributions
 shield-0.038
house-0.035
oc-0.032
 whatever-0.032
 diary-0.032
Token on
Token ID319
Feature activation-1.32e+00

Pos logit contributions
Kids+0.191
iya+0.172
 pastor+0.171
aa+0.170
argo+0.165
Neg logit contributions
house-0.073
 whatever-0.062
es-0.058
 shield-0.057
 anywhere-0.054
Token it
Token ID340
Feature activation-1.14e+00

Pos logit contributions
aa+0.048
oes+0.046
Kids+0.045
oe+0.043
round+0.042
Neg logit contributions
 diary-0.032
 shield-0.031
es-0.029
 webs-0.027
 shields-0.026
Token.
Token ID13
Feature activation-4.87e-02

Pos logit contributions
aa+0.038
Kids+0.036
oe+0.035
oes+0.034
round+0.033
Neg logit contributions
 diary-0.031
 shield-0.031
es-0.030
oc-0.029
house-0.027
Token She
Token ID1375
Feature activation-1.34e+00

Pos logit contributions
aa+0.001
oe+0.001
Kids+0.001
oes+0.001
round+0.001
Neg logit contributions
 shield-0.002
 diary-0.002
oc-0.002
es-0.002
 shields-0.002
Token left
Token ID1364
Feature activation-8.21e-01

Pos logit contributions
oes+0.040
aa+0.038
oe+0.036
Kids+0.035
round+0.035
Neg logit contributions
 shield-0.038
es-0.037
 diary-0.035
oc-0.035
 shields-0.034
Token big
Token ID1263
Feature activation-9.35e-01

Pos logit contributions
oes+0.018
aa+0.018
Kids+0.017
oe+0.016
round+0.016
Neg logit contributions
 diary-0.018
 shield-0.018
 journal-0.016
oc-0.016
house-0.015
Token slide
Token ID10649
Feature activation-1.50e+00

Pos logit contributions
aa+0.028
Kids+0.027
oes+0.027
oe+0.027
round+0.024
Neg logit contributions
 diary-0.029
 shield-0.028
oc-0.026
 journal-0.025
es-0.025
Token and
Token ID290
Feature activation-1.03e-01

Pos logit contributions
Kids+0.060
aa+0.058
Fre+0.053
 Abbey+0.053
leaf+0.053
Neg logit contributions
house-0.033
es-0.028
 diary-0.028
oc-0.026
 shield-0.025
Token wanted
Token ID2227
Feature activation-1.95e+00

Pos logit contributions
aa+0.003
oe+0.003
oes+0.003
Kids+0.003
round+0.002
Neg logit contributions
 diary-0.003
 shield-0.003
es-0.003
oc-0.003
 shields-0.003
Token to
Token ID284
Feature activation-1.77e+00

Pos logit contributions
aa+0.050
Kids+0.046
 sur+0.044
ora+0.043
oe+0.041
Neg logit contributions
 diary-0.066
es-0.065
 shield-0.061
 something-0.060
 nothing-0.060
Token go
Token ID467
Feature activation-4.49e+00

Pos logit contributions
Kids+0.063
aa+0.062
oe+0.057
ora+0.053
ho+0.052
Neg logit contributions
 shield-0.041
house-0.037
 diary-0.035
oc-0.034
 whatever-0.032
Token on
Token ID319
Feature activation-1.46e+00

Pos logit contributions
Kids+0.182
iya+0.165
 pastor+0.164
aa+0.162
Fre+0.159
Neg logit contributions
house-0.080
 whatever-0.067
es-0.065
 shield-0.063
 weapon-0.061
Token it
Token ID340
Feature activation-1.06e+00

Pos logit contributions
aa+0.052
oes+0.049
Kids+0.048
oe+0.046
round+0.045
Neg logit contributions
 diary-0.036
 shield-0.035
es-0.033
 webs-0.030
 journal-0.030
Token.
Token ID13
Feature activation-5.85e-01

Pos logit contributions
aa+0.033
oe+0.032
Kids+0.031
oes+0.030
round+0.029
Neg logit contributions
 diary-0.031
 shield-0.030
es-0.029
oc-0.029
 shields-0.027
Token She
Token ID1375
Feature activation-1.26e+00

Pos logit contributions
aa+0.017
oe+0.016
oes+0.016
Kids+0.016
round+0.015
Neg logit contributions
 diary-0.018
 shield-0.017
es-0.017
oc-0.016
 journal-0.016
Token asked
Token ID1965
Feature activation+4.01e-01

Pos logit contributions
oes+0.035
aa+0.034
oe+0.033
Kids+0.031
round+0.030
Neg logit contributions
 shield-0.039
es-0.038
 diary-0.037
oc-0.036
 shields-0.035
Token,
Token ID11
Feature activation+1.38e-01

Pos logit contributions
 diary+0.028
 shield+0.028
es+0.027
oc+0.027
 shields+0.025
Neg logit contributions
aa-0.022
oe-0.021
Kids-0.021
oes-0.020
round-0.019
Token then
Token ID788
Feature activation-5.37e-02

Pos logit contributions
 diary+0.005
 shield+0.005
es+0.005
oc+0.004
 shields+0.004
Neg logit contributions
aa-0.004
oe-0.003
Kids-0.003
oes-0.003
round-0.003
Token took
Token ID1718
Feature activation+1.32e-01

Pos logit contributions
aa+0.001
oe+0.001
Kids+0.001
oes+0.001
round+0.001
Neg logit contributions
 diary-0.002
 shield-0.002
es-0.002
oc-0.002
 shields-0.002
Token the
Token ID262
Feature activation-1.74e+00

Pos logit contributions
 diary+0.004
 shield+0.004
es+0.004
oc+0.004
 shields+0.003
Neg logit contributions
aa-0.004
oe-0.004
Kids-0.004
oes-0.004
round-0.004
Token other
Token ID584
Feature activation-1.52e+00

Pos logit contributions
aa+0.050
oe+0.048
Kids+0.047
oes+0.046
round+0.043
Neg logit contributions
 diary-0.054
 shield-0.054
es-0.053
oc-0.052
 shields-0.048
Token end
Token ID886
Feature activation-4.48e+00

Pos logit contributions
aa+0.043
oe+0.041
Kids+0.040
oes+0.039
round+0.037
Neg logit contributions
 diary-0.047
 shield-0.047
es-0.046
oc-0.046
 journal-0.042
Token and
Token ID290
Feature activation+1.51e-01

Pos logit contributions
Kids+0.140
aa+0.133
 sur+0.124
round+0.120
 Abbey+0.116
Neg logit contributions
es-0.131
 diary-0.128
 shield-0.123
house-0.119
 journal-0.112
Token ran
Token ID4966
Feature activation-1.22e+00

Pos logit contributions
 diary+0.005
 shield+0.005
es+0.005
oc+0.005
 shields+0.005
Neg logit contributions
aa-0.004
oe-0.004
Kids-0.004
oes-0.003
round-0.003
Token away
Token ID1497
Feature activation-3.89e-02

Pos logit contributions
aa+0.035
Kids+0.035
oes+0.035
iki+0.030
oe+0.029
Neg logit contributions
 shield-0.037
 diary-0.036
es-0.035
 webs-0.033
 shields-0.032
Token,
Token ID11
Feature activation-3.25e-01

Pos logit contributions
aa+0.001
oe+0.001
Kids+0.001
oes+0.001
round+0.001
Neg logit contributions
 diary-0.001
 shield-0.001
es-0.001
oc-0.001
 shields-0.001
Token gigg
Token ID30442
Feature activation+3.34e-01

Pos logit contributions
aa+0.009
Kids+0.009
oe+0.009
oes+0.009
round+0.008
Neg logit contributions
 shield-0.010
 diary-0.010
es-0.010
oc-0.009
 journal-0.009
Token.
Token ID13
Feature activation-6.30e-01

Pos logit contributions
aa+0.032
Kids+0.031
oe+0.031
oes+0.029
round+0.028
Neg logit contributions
 diary-0.029
 shield-0.029
es-0.028
oc-0.027
 journal-0.025
Token Do
Token ID2141
Feature activation-3.56e-01

Pos logit contributions
aa+0.021
oe+0.020
Kids+0.020
oes+0.019
round+0.018
Neg logit contributions
 diary-0.016
 shield-0.016
es-0.016
oc-0.015
 journal-0.014
Token you
Token ID345
Feature activation-1.72e+00

Pos logit contributions
aa+0.011
oe+0.010
Kids+0.010
oes+0.010
round+0.009
Neg logit contributions
 shield-0.011
 diary-0.010
oc-0.010
es-0.010
 shields-0.009
Token want
Token ID765
Feature activation-2.50e+00

Pos logit contributions
aa+0.054
Kids+0.053
oe+0.052
oes+0.049
round+0.048
Neg logit contributions
 diary-0.048
 shield-0.047
oc-0.045
es-0.044
house-0.042
Token to
Token ID284
Feature activation-2.79e+00

Pos logit contributions
aa+0.049
Kids+0.046
oe+0.046
 sur+0.040
 Abbey+0.039
Neg logit contributions
 diary-0.100
 shield-0.097
es-0.095
 journal-0.090
 webs-0.089
Token go
Token ID467
Feature activation-4.46e+00

Pos logit contributions
Kids+0.096
aa+0.092
oe+0.083
round+0.082
 Abbey+0.082
Neg logit contributions
 diary-0.065
 shield-0.064
house-0.062
 webs-0.057
 whatever-0.057
Token high
Token ID1029
Feature activation-1.96e+00

Pos logit contributions
Kids+0.170
 Abbey+0.155
aa+0.155
 pastor+0.151
 sur+0.150
Neg logit contributions
house-0.097
es-0.085
 diary-0.081
 whatever-0.076
 shield-0.074
Token?"
Token ID1701
Feature activation-2.16e+00

Pos logit contributions
Kids+0.076
aa+0.075
oes+0.069
oe+0.068
iki+0.067
Neg logit contributions
 shield-0.039
es-0.039
 diary-0.039
oc-0.037
house-0.036
Token
Token ID198
Feature activation-8.76e-01

Pos logit contributions
aa+0.076
oe+0.076
round+0.074
oes+0.071
Kids+0.071
Neg logit contributions
es-0.049
 diary-0.048
oc-0.046
 shield-0.045
house-0.040
Token
Token ID198
Feature activation+7.96e-02

Pos logit contributions
aa+0.028
oes+0.027
oe+0.027
round+0.027
Kids+0.026
Neg logit contributions
es-0.023
oc-0.023
 diary-0.022
 shield-0.022
house-0.019
TokenL
Token ID43
Feature activation-2.57e+00

Pos logit contributions
es+0.002
oc+0.002
 diary+0.002
 shield+0.002
house+0.002
Neg logit contributions
aa-0.003
oe-0.002
oes-0.002
Kids-0.002
round-0.002
Token and
Token ID290
Feature activation+6.03e-01

Pos logit contributions
 shield+0.001
 diary+0.001
es+0.001
oc+0.001
 shields+0.001
Neg logit contributions
aa-0.001
Kids-0.001
oe-0.001
oes-0.001
round-0.001
Token Coco
Token ID48222
Feature activation+4.99e-01

Pos logit contributions
 diary+0.020
 shield+0.019
oc+0.019
es+0.019
onel+0.018
Neg logit contributions
aa-0.016
oe-0.015
Kids-0.015
oes-0.014
round-0.014
Token holds
Token ID6622
Feature activation-2.73e-01

Pos logit contributions
 diary+0.017
 shield+0.016
oc+0.016
es+0.015
 journal+0.015
Neg logit contributions
aa-0.013
oe-0.013
Kids-0.012
oes-0.012
round-0.011
Token the
Token ID262
Feature activation-5.28e-01

Pos logit contributions
aa+0.008
oe+0.007
Kids+0.007
oes+0.007
round+0.007
Neg logit contributions
 diary-0.009
 shield-0.009
oc-0.008
es-0.008
 shields-0.008
Token other
Token ID584
Feature activation-1.20e+00

Pos logit contributions
aa+0.015
oe+0.014
oes+0.013
Kids+0.013
round+0.012
Neg logit contributions
es-0.017
oc-0.017
 diary-0.016
 shield-0.016
house-0.015
Token end
Token ID886
Feature activation-4.46e+00

Pos logit contributions
aa+0.036
oe+0.035
oes+0.033
Kids+0.032
round+0.031
Neg logit contributions
oc-0.036
 diary-0.036
 shield-0.035
es-0.034
 Majesty-0.033
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
Kids+0.147
aa+0.142
 sur+0.130
 Abbey+0.127
round+0.126
Neg logit contributions
es-0.122
 diary-0.119
 shield-0.116
house-0.112
 journal-0.104
Token Coco
Token ID48222
Feature activation+8.67e-02

Pos logit contributions
aa+0.029
Kids+0.027
oe+0.027
oes+0.026
round+0.024
Neg logit contributions
 diary-0.040
 shield-0.039
oc-0.038
es-0.038
 journal-0.036
Token is
Token ID318
Feature activation-5.20e-01

Pos logit contributions
 diary+0.003
 shield+0.003
oc+0.003
es+0.003
 journal+0.003
Neg logit contributions
aa-0.002
oe-0.002
Kids-0.002
oes-0.002
round-0.002
Token smart
Token ID4451
Feature activation+2.82e-01

Pos logit contributions
aa+0.015
oe+0.014
Kids+0.014
oes+0.013
round+0.013
Neg logit contributions
 diary-0.016
 shield-0.016
oc-0.016
es-0.016
 journal-0.015
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
 diary+0.011
 shield+0.011
oc+0.011
es+0.010
 journal+0.010
Neg logit contributions
aa-0.006
oe-0.005
Kids-0.005
oes-0.005
round-0.005
Token slide
Token ID10649
Feature activation-2.06e+00

Pos logit contributions
aa+0.025
Kids+0.024
oe+0.024
oes+0.023
round+0.021
Neg logit contributions
 shield-0.027
 diary-0.027
oc-0.025
es-0.024
 journal-0.024
Token.
Token ID13
Feature activation-1.81e+00

Pos logit contributions
Kids+0.085
aa+0.084
Fre+0.077
 Abbey+0.077
iki+0.076
Neg logit contributions
house-0.039
es-0.034
oc-0.032
 shield-0.028
 diary-0.028
Token Ben
Token ID3932
Feature activation-1.28e+00

Pos logit contributions
aa+0.057
oe+0.054
oes+0.051
Kids+0.051
round+0.049
Neg logit contributions
 diary-0.049
es-0.049
oc-0.048
 shield-0.048
house-0.046
Token wants
Token ID3382
Feature activation-2.35e+00

Pos logit contributions
aa+0.043
oe+0.042
Kids+0.041
oes+0.041
round+0.038
Neg logit contributions
 shield-0.033
 diary-0.032
es-0.032
oc-0.031
 shields-0.028
Token to
Token ID284
Feature activation-2.22e+00

Pos logit contributions
aa+0.064
ora+0.063
Kids+0.062
oe+0.060
 sur+0.057
Neg logit contributions
 something-0.069
 bones-0.069
 traps-0.067
es-0.067
 shield-0.066
Token go
Token ID467
Feature activation-4.45e+00

Pos logit contributions
Kids+0.081
aa+0.076
oe+0.070
ho+0.068
ora+0.067
Neg logit contributions
 shield-0.048
house-0.044
oc-0.039
 whatever-0.039
 diary-0.039
Token on
Token ID319
Feature activation-1.14e+00

Pos logit contributions
Kids+0.184
iya+0.169
aa+0.162
 pastor+0.160
Fre+0.159
Neg logit contributions
house-0.079
 whatever-0.061
 shield-0.060
es-0.060
 weapon-0.057
Token the
Token ID262
Feature activation-1.02e+00

Pos logit contributions
aa+0.040
oes+0.038
Kids+0.038
oe+0.036
round+0.035
Neg logit contributions
 shield-0.028
 diary-0.027
es-0.026
oc-0.024
 shields-0.024
Token slide
Token ID10649
Feature activation-2.67e+00

Pos logit contributions
aa+0.032
Kids+0.031
oes+0.028
oe+0.028
ora+0.027
Neg logit contributions
 shield-0.030
 diary-0.027
 journal-0.025
 sword-0.025
 chest-0.025
Token.
Token ID13
Feature activation-1.52e+00

Pos logit contributions
Kids+0.111
aa+0.105
leaf+0.099
iki+0.094
 sur+0.094
Neg logit contributions
es-0.050
house-0.049
oc-0.047
 shield-0.042
 diary-0.040
Token He
Token ID679
Feature activation-1.20e+00

Pos logit contributions
aa+0.055
oe+0.052
Kids+0.051
oes+0.050
round+0.050
Neg logit contributions
oc-0.034
es-0.033
 shield-0.032
 diary-0.031
house-0.030
Token's
Token ID338
Feature activation-3.83e-01

Pos logit contributions
 diary+0.003
 shield+0.002
es+0.002
oc+0.002
 journal+0.002
Neg logit contributions
aa-0.007
oe-0.007
Kids-0.007
oes-0.007
round-0.007
Token go
Token ID467
Feature activation-3.68e+00

Pos logit contributions
aa+0.009
oe+0.009
Kids+0.009
oes+0.009
round+0.008
Neg logit contributions
 diary-0.013
 shield-0.013
es-0.013
oc-0.013
 shields-0.012
Token and
Token ID290
Feature activation-1.50e-01

Pos logit contributions
Kids+0.129
aa+0.114
 pastor+0.114
Ice+0.111
 Abbey+0.110
Neg logit contributions
house-0.088
es-0.084
oc-0.084
 shield-0.079
 diary-0.077
Token find
Token ID1064
Feature activation+1.92e-01

Pos logit contributions
aa+0.004
oe+0.004
Kids+0.004
oes+0.004
round+0.003
Neg logit contributions
 shield-0.005
 diary-0.005
es-0.005
oc-0.005
 journal-0.004
Token the
Token ID262
Feature activation-6.79e-01

Pos logit contributions
 shield+0.005
 diary+0.005
oc+0.005
es+0.005
istered+0.005
Neg logit contributions
aa-0.006
oe-0.006
Kids-0.005
oes-0.005
round-0.005
Token end
Token ID886
Feature activation-4.44e+00

Pos logit contributions
aa+0.019
Kids+0.017
oe+0.017
oes+0.016
round+0.016
Neg logit contributions
 diary-0.023
 shield-0.023
es-0.021
 journal-0.021
oc-0.021
Token of
Token ID286
Feature activation-1.10e+00

Pos logit contributions
Kids+0.154
aa+0.153
 sur+0.146
 Abbey+0.133
 pastor+0.131
Neg logit contributions
es-0.120
house-0.108
 diary-0.105
 webs-0.097
 journal-0.092
Token it
Token ID340
Feature activation-4.73e-01

Pos logit contributions
aa+0.037
Kids+0.035
oe+0.035
oes+0.035
round+0.033
Neg logit contributions
 shield-0.029
 diary-0.029
es-0.027
oc-0.026
 shields-0.025
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
aa+0.015
oe+0.014
Kids+0.014
oes+0.014
round+0.013
Neg logit contributions
 diary-0.013
 shield-0.013
es-0.013
oc-0.012
 shields-0.011
Token Maybe
Token ID6674
Feature activation-1.76e+00

Pos logit contributions
aa+0.005
oe+0.004
Kids+0.004
oes+0.004
round+0.004
Neg logit contributions
 diary-0.003
 shield-0.003
es-0.003
oc-0.003
 shields-0.003
Token there
Token ID612
Feature activation-2.48e-01

Pos logit contributions
aa+0.063
Kids+0.060
oe+0.059
round+0.056
oes+0.055
Neg logit contributions
 diary-0.045
 shield-0.045
es-0.042
 journal-0.039
 shields-0.038
Token big
Token ID1263
Feature activation-5.90e-01

Pos logit contributions
oes+0.011
aa+0.011
Kids+0.011
oe+0.010
round+0.010
Neg logit contributions
 diary-0.012
 shield-0.011
 journal-0.010
oc-0.010
house-0.010
Token slide
Token ID10649
Feature activation-1.54e+00

Pos logit contributions
aa+0.018
Kids+0.017
oe+0.017
oes+0.017
round+0.015
Neg logit contributions
 diary-0.018
 shield-0.018
oc-0.017
es-0.016
 journal-0.016
Token and
Token ID290
Feature activation-3.44e-01

Pos logit contributions
Kids+0.058
aa+0.056
Fre+0.050
 sur+0.050
 Abbey+0.050
Neg logit contributions
house-0.036
es-0.032
oc-0.031
 diary-0.030
 shield-0.029
Token wanted
Token ID2227
Feature activation-2.40e+00

Pos logit contributions
aa+0.010
oes+0.009
oe+0.009
Kids+0.009
round+0.008
Neg logit contributions
 shield-0.011
 diary-0.011
es-0.010
oc-0.010
 shields-0.010
Token to
Token ID284
Feature activation-1.73e+00

Pos logit contributions
aa+0.064
Kids+0.064
 sur+0.063
ora+0.062
oes+0.056
Neg logit contributions
 something-0.073
 no-0.071
 nothing-0.071
es-0.070
 diary-0.069
Token go
Token ID467
Feature activation-4.43e+00

Pos logit contributions
Kids+0.062
aa+0.061
oe+0.055
ora+0.052
ho+0.051
Neg logit contributions
 shield-0.038
house-0.035
oc-0.033
 diary-0.032
 whatever-0.031
Token on
Token ID319
Feature activation-1.22e+00

Pos logit contributions
Kids+0.181
 pastor+0.162
iya+0.159
aa+0.157
Fre+0.157
Neg logit contributions
house-0.078
 whatever-0.064
es-0.063
 shield-0.062
oc-0.059
Token it
Token ID340
Feature activation-1.14e+00

Pos logit contributions
aa+0.042
oes+0.040
Kids+0.040
oe+0.038
round+0.037
Neg logit contributions
 diary-0.031
 shield-0.031
es-0.029
oc-0.027
 webs-0.026
Token.
Token ID13
Feature activation-2.25e+00

Pos logit contributions
aa+0.036
Kids+0.034
oe+0.034
oes+0.033
round+0.031
Neg logit contributions
 diary-0.032
 shield-0.032
es-0.031
oc-0.030
 shields-0.028
Token She
Token ID1375
Feature activation-1.45e+00

Pos logit contributions
aa+0.067
oe+0.066
oes+0.065
Kids+0.064
round+0.062
Neg logit contributions
 diary-0.061
es-0.059
oc-0.058
 shield-0.057
house-0.054
Token ran
Token ID4966
Feature activation-2.22e+00

Pos logit contributions
oes+0.042
aa+0.039
oe+0.039
Kids+0.037
round+0.036
Neg logit contributions
 shield-0.043
es-0.042
oc-0.041
 diary-0.040
house-0.038
Token starting
Token ID3599
Feature activation-2.01e+00

Pos logit contributions
aa+0.022
Kids+0.021
oes+0.021
oe+0.020
round+0.020
Neg logit contributions
 shield-0.018
 diary-0.018
es-0.017
house-0.016
vel-0.016
Token to
Token ID284
Feature activation-4.27e-01

Pos logit contributions
Kids+0.035
aa+0.035
round+0.033
oes+0.032
oe+0.030
Neg logit contributions
 diary-0.086
 shield-0.083
es-0.082
 webs-0.078
house-0.076
Token feel
Token ID1254
Feature activation-1.74e-01

Pos logit contributions
aa+0.013
oe+0.013
Kids+0.012
oes+0.012
round+0.011
Neg logit contributions
 diary-0.012
 shield-0.012
es-0.012
oc-0.012
 shields-0.011
Token cold
Token ID4692
Feature activation-4.98e-01

Pos logit contributions
aa+0.004
oe+0.004
Kids+0.004
oes+0.004
 sur+0.003
Neg logit contributions
oc-0.006
es-0.006
 diary-0.006
 shield-0.006
 shields-0.006
Token.
Token ID13
Feature activation+1.65e+00

Pos logit contributions
aa+0.018
Kids+0.018
oe+0.017
oes+0.017
round+0.016
Neg logit contributions
 diary-0.012
 shield-0.012
es-0.011
oc-0.010
house-0.010
Token Then
Token ID3244
Feature activation+2.60e+00

Pos logit contributions
 shield+0.066
oc+0.066
istered+0.062
 shields+0.062
vel+0.061
Neg logit contributions
Kids-0.029
aa-0.029
oes-0.027
oe-0.027
 to-0.026
Token she
Token ID673
Feature activation-3.75e-01

Pos logit contributions
oc+0.115
onel+0.113
istered+0.112
cod+0.109
osaurus+0.107
Neg logit contributions
 to-0.040
aa-0.033
oe-0.032
Kids-0.029
 slowly-0.029
Token saw
Token ID2497
Feature activation+9.60e-01

Pos logit contributions
aa+0.011
oe+0.011
oes+0.011
Kids+0.010
round+0.010
Neg logit contributions
 shield-0.012
 diary-0.011
es-0.011
oc-0.010
 shields-0.010
Token a
Token ID257
Feature activation+1.92e-01

Pos logit contributions
oc+0.034
istered+0.030
vel+0.029
es+0.029
 shield+0.028
Neg logit contributions
aa-0.024
Kids-0.023
 Kay-0.023
 Su-0.022
 to-0.022
Token gentleman
Token ID22427
Feature activation+1.10e+00

Pos logit contributions
 diary+0.006
 shield+0.006
oc+0.005
 journal+0.005
es+0.005
Neg logit contributions
aa-0.006
oes-0.005
Kids-0.005
oe-0.005
round-0.005
Token walking
Token ID6155
Feature activation-1.05e+00

Pos logit contributions
 diary+0.032
 shield+0.032
es+0.031
oc+0.030
 journal+0.028
Neg logit contributions
aa-0.034
oe-0.032
Kids-0.032
oes-0.031
round-0.029
Token "
Token ID366
Feature activation-5.68e-01

Pos logit contributions
aa+0.007
oe+0.007
Kids+0.007
oes+0.007
round+0.006
Neg logit contributions
 diary-0.006
 shield-0.006
es-0.006
oc-0.006
 journal-0.005
TokenOh
Token ID5812
Feature activation+2.63e+00

Pos logit contributions
aa+0.016
oe+0.016
oes+0.015
Kids+0.015
round+0.014
Neg logit contributions
 diary-0.017
 shield-0.017
oc-0.017
es-0.017
 journal-0.015
Token,
Token ID11
Feature activation+5.45e-01

Pos logit contributions
 diary+0.092
 shields+0.091
oc+0.091
 webs+0.089
bes+0.089
Neg logit contributions
aa-0.056
 Su-0.055
oe-0.052
 Jen-0.051
 Kay-0.048
Token Ben
Token ID3932
Feature activation+2.43e+00

Pos logit contributions
oc+0.022
es+0.021
house+0.020
opes+0.019
 webs+0.019
Neg logit contributions
aa-0.011
 Sara-0.010
Kids-0.010
 sur-0.010
 dads-0.010
Token,
Token ID11
Feature activation+7.07e-01

Pos logit contributions
 shield+0.085
 diary+0.085
 shields+0.082
onel+0.082
 webs+0.079
Neg logit contributions
aa-0.060
oe-0.058
Kids-0.050
oes-0.048
 to-0.045
Token you
Token ID345
Feature activation+2.37e+00

Pos logit contributions
oc+0.023
es+0.022
 diary+0.021
 shield+0.021
 shields+0.021
Neg logit contributions
aa-0.018
Kids-0.017
 to-0.017
oes-0.016
oe-0.016
Token have
Token ID423
Feature activation+1.07e+00

Pos logit contributions
 diary+0.083
 Majesty+0.078
 shield+0.077
 journal+0.076
 shields+0.075
Neg logit contributions
aa-0.056
oe-0.045
 packed-0.044
 se-0.042
Kids-0.041
Token a
Token ID257
Feature activation+6.32e-02

Pos logit contributions
oc+0.048
 shield+0.047
 diary+0.047
es+0.047
 journal+0.044
Neg logit contributions
aa-0.017
oe-0.015
Kids-0.014
oes-0.013
round-0.011
Token high
Token ID1029
Feature activation-8.91e-02

Pos logit contributions
es+0.002
 diary+0.002
 shield+0.002
oc+0.002
 shields+0.001
Neg logit contributions
aa-0.002
oe-0.002
Kids-0.002
oes-0.002
round-0.002
Token temperature
Token ID5951
Feature activation-5.02e-01

Pos logit contributions
aa+0.003
oe+0.002
oes+0.002
Kids+0.002
round+0.002
Neg logit contributions
es-0.003
 diary-0.003
 shield-0.003
oc-0.003
onel-0.002
Token.
Token ID13
Feature activation+7.23e-01

Pos logit contributions
aa+0.015
Kids+0.015
oe+0.014
oes+0.014
round+0.013
Neg logit contributions
 diary-0.014
es-0.014
 shield-0.014
oc-0.014
house-0.013
Token
Token ID198
Feature activation+2.05e+00

Pos logit contributions
 shield+0.042
 diary+0.041
es+0.039
oc+0.039
 shields+0.037
Neg logit contributions
aa-0.030
oe-0.029
Kids-0.028
oes-0.027
round-0.025
TokenL
Token ID43
Feature activation-1.16e+00

Pos logit contributions
 shield+0.069
 diary+0.068
es+0.064
 traps+0.062
 shields+0.062
Neg logit contributions
Kids-0.056
aa-0.053
oe-0.052
oes-0.045
round-0.045
Tokenily
Token ID813
Feature activation+1.22e-02

Pos logit contributions
aa+0.035
oe+0.034
Kids+0.034
oes+0.032
round+0.030
Neg logit contributions
 shield-0.035
 diary-0.034
es-0.033
oc-0.033
 shields-0.031
Token hugged
Token ID41130
Feature activation-2.28e-01

Pos logit contributions
 diary+0.000
 shield+0.000
es+0.000
oc+0.000
 shields+0.000
Neg logit contributions
aa-0.000
oe-0.000
Kids-0.000
oes-0.000
round-0.000
Token her
Token ID607
Feature activation+6.94e-01

Pos logit contributions
aa+0.009
oe+0.008
Kids+0.008
oes+0.008
round+0.008
Neg logit contributions
 diary-0.005
 shield-0.005
es-0.005
oc-0.005
 shields-0.004
Token doll
Token ID3654
Feature activation+2.65e+00

Pos logit contributions
oc+0.021
es+0.020
 diary+0.019
 shield+0.019
onel+0.019
Neg logit contributions
aa-0.020
oe-0.019
Kids-0.017
oes-0.017
 sur-0.016
Token and
Token ID290
Feature activation+7.51e-01

Pos logit contributions
 diary+0.100
 shield+0.099
es+0.099
onel+0.097
oc+0.097
Neg logit contributions
aa-0.052
oe-0.051
oes-0.045
round-0.044
Kids-0.039
Token smiled
Token ID13541
Feature activation+4.47e-01

Pos logit contributions
 diary+0.030
 shield+0.030
oc+0.030
es+0.029
vel+0.028
Neg logit contributions
aa-0.014
Kids-0.013
oe-0.013
oes-0.011
 sur-0.010
Token back
Token ID736
Feature activation+4.80e-01

Pos logit contributions
 diary+0.015
oc+0.014
 shield+0.014
es+0.014
 traps+0.014
Neg logit contributions
aa-0.012
oe-0.011
Kids-0.010
oes-0.010
 sur-0.009
Token,
Token ID11
Feature activation-1.05e+00

Pos logit contributions
 diary+0.014
 shield+0.014
es+0.014
oc+0.013
 shields+0.012
Neg logit contributions
aa-0.015
oe-0.014
Kids-0.014
oes-0.014
round-0.013
Token feeling
Token ID4203
Feature activation+3.15e-01

Pos logit contributions
aa+0.033
oe+0.032
oes+0.032
Kids+0.032
round+0.029
Neg logit contributions
 shield-0.030
 diary-0.030
es-0.028
oc-0.027
house-0.026
Token had
Token ID550
Feature activation+6.76e-01

Pos logit contributions
aa+0.004
oe+0.003
oes+0.003
Kids+0.003
round+0.003
Neg logit contributions
 shield-0.005
es-0.005
 diary-0.005
oc-0.005
house-0.004
Token a
Token ID257
Feature activation+1.65e-01

Pos logit contributions
 diary+0.016
 shield+0.016
es+0.015
oc+0.015
 shields+0.013
Neg logit contributions
aa-0.025
oe-0.024
Kids-0.024
oes-0.023
round-0.022
Token toy
Token ID13373
Feature activation+1.83e+00

Pos logit contributions
es+0.005
 diary+0.005
 shield+0.005
oc+0.005
 shields+0.005
Neg logit contributions
aa-0.004
oe-0.004
Kids-0.004
oes-0.004
round-0.004
Token soldier
Token ID10686
Feature activation+1.77e+00

Pos logit contributions
es+0.050
oc+0.050
vel+0.049
 diary+0.048
 Majesty+0.046
Neg logit contributions
aa-0.055
oe-0.053
oes-0.051
round-0.050
Kids-0.047
Token in
Token ID287
Feature activation+3.54e-01

Pos logit contributions
onel+0.055
 diary+0.055
 shield+0.055
oc+0.054
 shields+0.054
Neg logit contributions
aa-0.045
oe-0.042
round-0.039
oes-0.037
Kids-0.037
Token his
Token ID465
Feature activation+2.45e+00

Pos logit contributions
 diary+0.010
 shield+0.010
es+0.010
oc+0.009
 shields+0.009
Neg logit contributions
aa-0.011
oe-0.011
Kids-0.010
oes-0.010
round-0.010
Token hand
Token ID1021
Feature activation+3.58e-01

Pos logit contributions
es+0.080
vel+0.077
onel+0.076
oc+0.071
 shield+0.071
Neg logit contributions
aa-0.062
oe-0.061
oes-0.058
 to-0.054
Kids-0.052
Token.
Token ID13
Feature activation-8.01e-01

Pos logit contributions
 diary+0.011
 shield+0.010
es+0.010
oc+0.010
 shields+0.009
Neg logit contributions
aa-0.011
oe-0.010
Kids-0.010
oes-0.010
round-0.009
Token Tim
Token ID5045
Feature activation-2.77e-01

Pos logit contributions
aa+0.029
oe+0.028
Kids+0.027
oes+0.027
round+0.026
Neg logit contributions
 shield-0.018
oc-0.018
 diary-0.018
es-0.017
house-0.016
Tokenmy
Token ID1820
Feature activation-1.40e-01

Pos logit contributions
aa+0.008
oe+0.007
Kids+0.007
oes+0.007
round+0.007
Neg logit contributions
 diary-0.009
 shield-0.009
es-0.009
oc-0.008
house-0.008
Token wanted
Token ID2227
Feature activation-1.11e+00

Pos logit contributions
aa+0.004
oe+0.003
Kids+0.003
oes+0.003
round+0.003
Neg logit contributions
 diary-0.005
 shield-0.005
es-0.005
oc-0.004
 journal-0.004
Token bath
Token ID7837
Feature activation-5.72e-01

Pos logit contributions
 diary+0.023
es+0.023
 shield+0.023
oc+0.023
house+0.021
Neg logit contributions
aa-0.023
oe-0.022
Kids-0.022
oes-0.021
round-0.020
Token.
Token ID13
Feature activation-6.74e-01

Pos logit contributions
aa+0.019
oe+0.018
Kids+0.018
oes+0.017
round+0.017
Neg logit contributions
 shield-0.015
 diary-0.015
es-0.015
oc-0.014
 journal-0.013
Token He
Token ID679
Feature activation-5.55e-01

Pos logit contributions
aa+0.020
oe+0.019
Kids+0.019
oes+0.018
round+0.017
Neg logit contributions
 diary-0.020
 shield-0.020
es-0.020
oc-0.019
 shields-0.018
Token loved
Token ID6151
Feature activation-1.67e+00

Pos logit contributions
aa+0.017
oe+0.016
oes+0.016
Kids+0.016
round+0.015
Neg logit contributions
 shield-0.017
 diary-0.016
es-0.016
oc-0.015
 shields-0.015
Token his
Token ID465
Feature activation+1.19e+00

Pos logit contributions
oe+0.039
aa+0.039
Kids+0.036
oes+0.034
ora+0.033
Neg logit contributions
 shield-0.065
 diary-0.062
 shields-0.060
es-0.059
 webs-0.059
Token robot
Token ID9379
Feature activation+2.77e+00

Pos logit contributions
es+0.034
vel+0.032
oc+0.030
onel+0.030
istered+0.029
Neg logit contributions
aa-0.038
oe-0.036
oes-0.035
Kids-0.033
 weekend-0.033
Token very
Token ID845
Feature activation+1.81e-01

Pos logit contributions
istered+0.106
onel+0.105
oc+0.103
vel+0.102
 alas+0.102
Neg logit contributions
 to-0.045
aa-0.042
oes-0.042
oe-0.041
round-0.040
Token much
Token ID881
Feature activation-8.71e-01

Pos logit contributions
 diary+0.005
 shield+0.005
es+0.005
oc+0.005
 shields+0.005
Neg logit contributions
aa-0.006
oe-0.005
Kids-0.005
oes-0.005
round-0.005
Token.
Token ID13
Feature activation-5.08e-01

Pos logit contributions
aa+0.028
Kids+0.027
oe+0.027
oes+0.026
round+0.024
Neg logit contributions
 diary-0.024
 shield-0.024
es-0.024
oc-0.023
 journal-0.021
Token
Token ID198
Feature activation-8.03e-01

Pos logit contributions
aa+0.013
Kids+0.012
oe+0.012
oes+0.012
round+0.011
Neg logit contributions
 diary-0.018
 shield-0.017
es-0.017
oc-0.016
 shields-0.016
Token
Token ID198
Feature activation+9.91e-01

Pos logit contributions
aa+0.025
oe+0.023
Kids+0.023
oes+0.023
round+0.022
Neg logit contributions
 diary-0.023
oc-0.022
 shield-0.022
es-0.022
 journal-0.020
Token he
Token ID339
Feature activation-6.25e-01

Pos logit contributions
aa+0.030
oe+0.029
Kids+0.028
oes+0.028
round+0.026
Neg logit contributions
 diary-0.030
 shield-0.029
es-0.028
oc-0.028
 journal-0.026
Token could
Token ID714
Feature activation-8.33e-01

Pos logit contributions
aa+0.021
oe+0.020
Kids+0.020
oes+0.020
round+0.019
Neg logit contributions
es-0.016
 shield-0.016
 diary-0.016
oc-0.015
 webs-0.014
Token and
Token ID290
Feature activation+9.28e-01

Pos logit contributions
Kids+0.029
aa+0.029
oe+0.027
oes+0.027
round+0.026
Neg logit contributions
 shield-0.021
es-0.020
 diary-0.020
oc-0.018
house-0.017
Token finally
Token ID3443
Feature activation+4.06e-01

Pos logit contributions
 diary+0.032
 shield+0.031
es+0.030
oc+0.030
 journal+0.030
Neg logit contributions
aa-0.024
oe-0.023
Kids-0.022
oes-0.021
round-0.020
Token got
Token ID1392
Feature activation-5.26e-01

Pos logit contributions
 diary+0.014
 shield+0.013
oc+0.013
es+0.012
 journal+0.012
Neg logit contributions
aa-0.011
oe-0.011
Kids-0.010
oes-0.010
round-0.009
Token away
Token ID1497
Feature activation+3.50e-01

Pos logit contributions
aa+0.016
Kids+0.015
oe+0.015
oes+0.014
round+0.014
Neg logit contributions
 shield-0.016
 diary-0.016
es-0.015
oc-0.015
 shields-0.014
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 shield+0.012
 diary+0.012
es+0.012
oc+0.012
 shields+0.011
Neg logit contributions
aa-0.009
oe-0.008
Kids-0.008
oes-0.008
round-0.007
Token He
Token ID679
Feature activation+6.11e-02

Pos logit contributions
 diary+0.041
 shield+0.041
vel+0.038
 journal+0.037
onel+0.037
Neg logit contributions
aa-0.025
oe-0.024
Kids-0.024
oes-0.023
round-0.021
Token decided
Token ID3066
Feature activation-3.71e-01

Pos logit contributions
 shield+0.002
 diary+0.002
es+0.002
oc+0.002
 shields+0.002
Neg logit contributions
aa-0.002
oe-0.002
Kids-0.002
oes-0.002
round-0.002
Token to
Token ID284
Feature activation-8.44e-01

Pos logit contributions
aa+0.007
Kids+0.006
oe+0.006
oes+0.006
ora+0.005
Neg logit contributions
 shield-0.015
 diary-0.015
es-0.015
 traps-0.014
oc-0.014
Token stick
Token ID4859
Feature activation+2.24e-01

Pos logit contributions
aa+0.023
oe+0.022
Kids+0.022
oes+0.021
round+0.020
Neg logit contributions
 shield-0.027
 diary-0.027
es-0.026
oc-0.025
 shields-0.024
Token A
Token ID317
Feature activation+9.57e-02

Pos logit contributions
aa+0.029
oe+0.028
oes+0.027
Kids+0.027
round+0.026
Neg logit contributions
 diary-0.025
 shield-0.024
es-0.024
oc-0.023
 webs-0.021
Token puppy
Token ID26188
Feature activation+1.50e+00

Pos logit contributions
 shield+0.003
 diary+0.003
oc+0.003
es+0.003
 journal+0.003
Neg logit contributions
aa-0.003
oes-0.003
Kids-0.003
oe-0.003
round-0.003
Token suddenly
Token ID6451
Feature activation+1.13e+00

Pos logit contributions
 diary+0.057
 Majesty+0.057
 shield+0.056
istered+0.056
 shields+0.056
Neg logit contributions
aa-0.028
oe-0.027
Kids-0.026
ho-0.021
round-0.021
Token appeared
Token ID4120
Feature activation+8.33e-01

Pos logit contributions
 diary+0.041
 shield+0.040
oc+0.039
es+0.039
 journal+0.037
Neg logit contributions
aa-0.027
oe-0.025
Kids-0.024
oes-0.023
round-0.021
Token from
Token ID422
Feature activation+1.25e-01

Pos logit contributions
 diary+0.028
 shield+0.028
es+0.027
oc+0.026
 journal+0.025
Neg logit contributions
aa-0.022
Kids-0.021
oe-0.021
oes-0.020
round-0.019
Token the
Token ID262
Feature activation-1.00e-01

Pos logit contributions
 shield+0.004
 diary+0.004
es+0.004
oc+0.004
 shields+0.004
Neg logit contributions
aa-0.004
oe-0.003
Kids-0.003
oes-0.003
round-0.003
Token ground
Token ID2323
Feature activation+7.56e-01

Pos logit contributions
aa+0.003
oe+0.003
Kids+0.003
oes+0.003
round+0.003
Neg logit contributions
 diary-0.003
 shield-0.003
es-0.003
oc-0.003
 journal-0.002
Token.
Token ID13
Feature activation-2.24e+00

Pos logit contributions
 diary+0.022
 shield+0.022
es+0.022
oc+0.021
house+0.020
Neg logit contributions
aa-0.023
Kids-0.022
oe-0.022
oes-0.021
round-0.020
Token Lori
Token ID43741
Feature activation+1.96e-01

Pos logit contributions
oe+0.073
aa+0.073
oes+0.072
Kids+0.069
round+0.068
Neg logit contributions
 diary-0.058
es-0.057
 shield-0.057
oc-0.054
 webs-0.050
Token was
Token ID373
Feature activation+5.33e-01

Pos logit contributions
 diary+0.007
 shield+0.006
es+0.006
oc+0.006
 shields+0.006
Neg logit contributions
aa-0.005
oe-0.005
Kids-0.005
oes-0.005
round-0.004
Token so
Token ID523
Feature activation-2.83e-01

Pos logit contributions
 diary+0.016
 shield+0.016
es+0.015
oc+0.015
 journal+0.014
Neg logit contributions
aa-0.016
Kids-0.015
oe-0.015
oes-0.015
round-0.014
Token found
Token ID1043
Feature activation+5.08e-01

Pos logit contributions
 diary+0.020
 shield+0.020
es+0.019
oc+0.018
 shields+0.017
Neg logit contributions
aa-0.024
oe-0.023
Kids-0.022
oes-0.022
round-0.021
Token it
Token ID340
Feature activation+4.14e-01

Pos logit contributions
oc+0.015
 shield+0.015
 diary+0.015
 Majesty+0.015
vel+0.014
Neg logit contributions
aa-0.014
oe-0.013
oes-0.013
Kids-0.013
 Su-0.013
Token while
Token ID981
Feature activation-5.62e-01

Pos logit contributions
 diary+0.014
 shield+0.014
es+0.014
oc+0.014
 shields+0.013
Neg logit contributions
aa-0.010
oe-0.010
Kids-0.010
oes-0.009
round-0.009
Token they
Token ID484
Feature activation+2.59e-01

Pos logit contributions
aa+0.018
oe+0.018
Kids+0.017
oes+0.017
round+0.016
Neg logit contributions
 diary-0.015
 shield-0.015
es-0.015
oc-0.014
 shields-0.013
Token were
Token ID547
Feature activation+2.00e-01

Pos logit contributions
 diary+0.009
 shield+0.009
oc+0.009
es+0.008
 Majesty+0.008
Neg logit contributions
aa-0.006
oe-0.006
Kids-0.006
oes-0.005
ho-0.005
Token out
Token ID503
Feature activation+7.57e-01

Pos logit contributions
 diary+0.006
 shield+0.006
es+0.006
oc+0.006
 shields+0.005
Neg logit contributions
aa-0.006
oe-0.006
Kids-0.006
oes-0.005
round-0.005
Token playing
Token ID2712
Feature activation+1.05e+00

Pos logit contributions
 diary+0.025
 shield+0.025
es+0.024
oc+0.024
 shields+0.023
Neg logit contributions
aa-0.020
oe-0.019
Kids-0.019
oes-0.018
round-0.017
Token.
Token ID13
Feature activation-8.56e-01

Pos logit contributions
 Majesty+0.047
ience+0.045
istered+0.044
 fears+0.044
onel+0.043
Neg logit contributions
 to-0.014
oe-0.013
 towards-0.011
Kids-0.009
 weekend-0.009
Token The
Token ID383
Feature activation+5.21e-01

Pos logit contributions
aa+0.027
oe+0.025
Kids+0.024
oes+0.024
round+0.023
Neg logit contributions
 diary-0.023
es-0.023
oc-0.023
 shield-0.023
house-0.022
Token children
Token ID1751
Feature activation-4.60e-01

Pos logit contributions
es+0.019
oc+0.018
vel+0.017
istered+0.017
onel+0.017
Neg logit contributions
 elderly-0.012
 vendor-0.011
 weekend-0.011
aa-0.010
Kids-0.010
Token had
Token ID550
Feature activation+8.81e-03

Pos logit contributions
aa+0.013
oe+0.013
Kids+0.013
oes+0.012
round+0.012
Neg logit contributions
 diary-0.014
 shield-0.014
es-0.014
oc-0.013
 shields-0.013
Token.
Token ID13
Feature activation+7.33e-01

Pos logit contributions
aa+0.002
oe+0.002
Kids+0.002
oes+0.002
round+0.002
Neg logit contributions
 diary-0.002
 shield-0.002
oc-0.002
es-0.002
 shields-0.002
Token<|endoftext|>
Token ID50256
Feature activation+2.48e-01

Pos logit contributions
 shield+0.024
 diary+0.024
es+0.023
oc+0.022
 shields+0.021
Neg logit contributions
aa-0.020
Kids-0.019
oe-0.019
oes-0.019
round-0.018
TokenOnce
Token ID7454
Feature activation+9.85e-01

Pos logit contributions
 diary+0.008
 shield+0.008
es+0.008
oc+0.008
 shields+0.007
Neg logit contributions
aa-0.007
oe-0.006
Kids-0.006
oes-0.006
round-0.006
Token upon
Token ID2402
Feature activation+1.04e+00

Pos logit contributions
 shield+0.035
 diary+0.035
oc+0.034
es+0.034
 shields+0.032
Neg logit contributions
oe-0.025
aa-0.024
oes-0.022
Kids-0.021
 weekend-0.019
Token a
Token ID257
Feature activation+2.52e-01

Pos logit contributions
oc+0.036
es+0.035
onel+0.034
 Majesty+0.034
 diary+0.034
Neg logit contributions
aa-0.022
oe-0.022
Kids-0.022
 to-0.021
 weekend-0.021
Token time
Token ID640
Feature activation+8.58e-01

Pos logit contributions
 diary+0.009
 shield+0.009
es+0.009
oc+0.009
 shields+0.009
Neg logit contributions
aa-0.006
oe-0.005
Kids-0.005
oes-0.005
round-0.004
Token,
Token ID11
Feature activation-6.17e-01

Pos logit contributions
 shield+0.028
 diary+0.028
oc+0.026
 shields+0.026
es+0.025
Neg logit contributions
oe-0.025
aa-0.024
oes-0.022
Kids-0.021
 Kay-0.019
Token there
Token ID612
Feature activation+7.56e-01

Pos logit contributions
oe+0.016
aa+0.016
Kids+0.014
oes+0.014
round+0.013
Neg logit contributions
 shield-0.021
 diary-0.021
oc-0.020
es-0.020
 shields-0.019
Token was
Token ID373
Feature activation-5.38e-01

Pos logit contributions
 shield+0.028
 diary+0.028
 shields+0.027
es+0.026
oc+0.026
Neg logit contributions
oe-0.017
aa-0.016
Kids-0.016
oes-0.015
 weekend-0.014
Token a
Token ID257
Feature activation+1.25e-02

Pos logit contributions
aa+0.018
oe+0.018
Kids+0.018
oes+0.016
 weekend+0.016
Neg logit contributions
 shield-0.013
oc-0.013
 diary-0.013
es-0.013
 shields-0.012
Token spoiled
Token ID34781
Feature activation+8.32e-01

Pos logit contributions
 shield+0.000
 diary+0.000
oc+0.000
es+0.000
 journal+0.000
Neg logit contributions
aa-0.000
oes-0.000
oe-0.000
Kids-0.000
round-0.000
Token looking
Token ID2045
Feature activation+2.83e-01

Pos logit contributions
 diary+0.022
 shield+0.021
oc+0.021
es+0.021
 journal+0.019
Neg logit contributions
aa-0.021
oe-0.021
Kids-0.020
oes-0.019
round-0.018
Token after
Token ID706
Feature activation-1.32e-02

Pos logit contributions
 diary+0.009
 shield+0.009
es+0.009
oc+0.009
 shields+0.008
Neg logit contributions
aa-0.007
oe-0.007
Kids-0.007
oes-0.007
round-0.006
Token him
Token ID683
Feature activation+1.33e+00

Pos logit contributions
aa+0.000
oe+0.000
Kids+0.000
oes+0.000
round+0.000
Neg logit contributions
 diary-0.000
 shield-0.000
es-0.000
oc-0.000
 shields-0.000
Token.
Token ID13
Feature activation+4.46e-01

Pos logit contributions
 diary+0.045
 shield+0.044
oc+0.044
es+0.043
 webs+0.042
Neg logit contributions
aa-0.031
oe-0.030
oes-0.028
Kids-0.025
 weekend-0.025
Token They
Token ID1119
Feature activation+3.21e-02

Pos logit contributions
 diary+0.014
 shield+0.014
es+0.013
oc+0.013
 shields+0.013
Neg logit contributions
aa-0.013
Kids-0.012
oe-0.012
oes-0.012
round-0.011
Token both
Token ID1111
Feature activation+2.09e-02

Pos logit contributions
 diary+0.001
 shield+0.001
es+0.001
oc+0.001
 journal+0.001
Neg logit contributions
aa-0.001
oe-0.001
Kids-0.001
oes-0.001
round-0.001
Token gl
Token ID1278
Feature activation-5.67e-02

Pos logit contributions
 diary+0.001
 shield+0.001
es+0.001
oc+0.001
 journal+0.001
Neg logit contributions
aa-0.001
oe-0.000
Kids-0.000
oes-0.000
round-0.000
Tokenowed
Token ID6972
Feature activation+1.66e-01

Pos logit contributions
aa+0.002
Kids+0.002
oe+0.002
oes+0.002
round+0.002
Neg logit contributions
 shield-0.001
 diary-0.001
es-0.001
oc-0.001
 shields-0.001
Token in
Token ID287
Feature activation-4.46e-01

Pos logit contributions
 diary+0.005
 shield+0.005
es+0.005
oc+0.005
 shields+0.005
Neg logit contributions
aa-0.004
oe-0.004
Kids-0.004
oes-0.004
round-0.004
Token the
Token ID262
Feature activation+3.80e-01

Pos logit contributions
aa+0.012
oe+0.012
Kids+0.012
oes+0.011
round+0.011
Neg logit contributions
 diary-0.014
 shield-0.014
es-0.014
oc-0.013
 journal-0.013
Token sun
Token ID4252
Feature activation-1.35e+00

Pos logit contributions
 diary+0.013
 shield+0.013
es+0.013
oc+0.012
 shields+0.012
Neg logit contributions
aa-0.010
oe-0.009
Kids-0.009
oes-0.009
round-0.008
Token be
Token ID307
Feature activation-1.12e+00

Pos logit contributions
aa+0.034
Kids+0.032
oe+0.032
oes+0.030
round+0.030
Neg logit contributions
 shield-0.034
 diary-0.033
oc-0.032
es-0.032
house-0.030
Token two
Token ID734
Feature activation-6.45e-01

Pos logit contributions
aa+0.032
oe+0.031
Kids+0.030
oes+0.029
round+0.027
Neg logit contributions
 diary-0.035
 shield-0.035
es-0.034
oc-0.033
 journal-0.031
Token coins
Token ID10796
Feature activation+3.78e-02

Pos logit contributions
aa+0.020
Kids+0.020
oe+0.020
oes+0.019
round+0.018
Neg logit contributions
 shield-0.018
 diary-0.018
es-0.017
oc-0.017
 shields-0.016
Token."
Token ID526
Feature activation-9.58e-01

Pos logit contributions
 diary+0.001
 shield+0.001
es+0.001
oc+0.001
 shields+0.001
Neg logit contributions
aa-0.001
oe-0.001
Kids-0.001
oes-0.001
round-0.001
Token L
Token ID406
Feature activation-2.71e+00

Pos logit contributions
aa+0.028
oe+0.027
Kids+0.027
oes+0.027
round+0.025
Neg logit contributions
oc-0.028
es-0.028
 shield-0.027
 diary-0.026
 shields-0.024
Tokenila
Token ID10102
Feature activation-1.57e+00

Pos logit contributions
 weekend+0.059
oe+0.057
aa+0.057
oes+0.056
Kids+0.052
Neg logit contributions
es-0.102
oc-0.087
onel-0.084
 diary-0.084
vel-0.083
Token and
Token ID290
Feature activation-6.72e-02

Pos logit contributions
aa+0.038
oe+0.036
Kids+0.036
oes+0.035
round+0.032
Neg logit contributions
 shield-0.056
 diary-0.055
es-0.055
oc-0.053
 shields-0.050
Token Ben
Token ID3932
Feature activation-9.49e-02

Pos logit contributions
aa+0.002
oe+0.002
Kids+0.002
oes+0.002
round+0.002
Neg logit contributions
 diary-0.002
 shield-0.002
oc-0.002
es-0.002
house-0.002
Token look
Token ID804
Feature activation+1.43e+00

Pos logit contributions
aa+0.002
oe+0.002
Kids+0.002
oes+0.002
round+0.002
Neg logit contributions
 diary-0.003
 shield-0.003
oc-0.003
es-0.003
 shields-0.003
Token at
Token ID379
Feature activation-1.98e-01

Pos logit contributions
 diary+0.049
 shield+0.049
es+0.047
oc+0.046
 shields+0.045
Neg logit contributions
aa-0.035
oe-0.033
Kids-0.029
round-0.029
oes-0.028
Token their
Token ID511
Feature activation-5.49e-01

Pos logit contributions
aa+0.006
oe+0.005
Kids+0.005
oes+0.005
round+0.005
Neg logit contributions
 diary-0.006
 shield-0.006
es-0.006
oc-0.006
 shields-0.006
Token little
Token ID1310
Feature activation+9.59e-02

Pos logit contributions
oes+0.009
aa+0.009
oe+0.009
Kids+0.009
round+0.008
Neg logit contributions
 shield-0.007
 diary-0.007
oc-0.007
es-0.006
 journal-0.006
Token girl
Token ID2576
Feature activation+5.09e-01

Pos logit contributions
 shield+0.003
 diary+0.003
oc+0.003
 journal+0.003
es+0.003
Neg logit contributions
Kids-0.003
oes-0.003
oe-0.003
aa-0.003
round-0.002
Token who
Token ID508
Feature activation-5.83e-01

Pos logit contributions
 diary+0.013
 shield+0.012
oc+0.012
es+0.012
house+0.011
Neg logit contributions
aa-0.018
oe-0.017
Kids-0.017
oes-0.017
round-0.016
Token wanted
Token ID2227
Feature activation-3.30e-01

Pos logit contributions
aa+0.016
oe+0.016
Kids+0.015
oes+0.014
 weekend+0.013
Neg logit contributions
 shield-0.019
 diary-0.018
es-0.018
 shields-0.018
oc-0.017
Token to
Token ID284
Feature activation+5.50e-01

Pos logit contributions
aa+0.007
oe+0.007
Kids+0.006
round+0.006
oes+0.006
Neg logit contributions
 diary-0.014
 shield-0.014
 journal-0.013
es-0.012
 shields-0.012
Token go
Token ID467
Feature activation-2.21e+00

Pos logit contributions
 diary+0.018
 shield+0.017
es+0.017
oc+0.016
 journal+0.016
Neg logit contributions
aa-0.015
oe-0.015
Kids-0.015
oes-0.014
round-0.013
Token sailing
Token ID28499
Feature activation-6.02e-01

Pos logit contributions
Kids+0.071
aa+0.065
oe+0.064
 Abbey+0.060
ho+0.060
Neg logit contributions
 shield-0.068
 diary-0.067
es-0.059
 weapon-0.058
 journal-0.057
Token.
Token ID13
Feature activation+8.87e-01

Pos logit contributions
aa+0.018
Kids+0.017
oe+0.017
oes+0.016
round+0.015
Neg logit contributions
 shield-0.018
 diary-0.018
es-0.018
oc-0.017
 journal-0.016
Token She
Token ID1375
Feature activation-1.58e+00

Pos logit contributions
 diary+0.027
 shield+0.025
es+0.024
oc+0.024
house+0.023
Neg logit contributions
aa-0.027
oe-0.026
Kids-0.025
oes-0.024
round-0.024
Token asked
Token ID1965
Feature activation+7.65e-01

Pos logit contributions
oes+0.048
aa+0.046
oe+0.046
Kids+0.044
round+0.043
Neg logit contributions
 shield-0.047
oc-0.046
es-0.043
 diary-0.043
 shields-0.040
Token her
Token ID607
Feature activation-8.33e-02

Pos logit contributions
 diary+0.023
 shield+0.022
es+0.022
oc+0.020
 journal+0.020
Neg logit contributions
aa-0.024
oe-0.023
Kids-0.023
oes-0.022
round-0.022
Token helps
Token ID5419
Feature activation-1.27e+00

Pos logit contributions
 shield+0.032
 diary+0.032
es+0.031
oc+0.030
 shields+0.029
Neg logit contributions
aa-0.026
Kids-0.025
oe-0.025
oes-0.024
round-0.022
Token him
Token ID683
Feature activation-5.83e-01

Pos logit contributions
aa+0.038
oe+0.038
Kids+0.038
round+0.035
oes+0.035
Neg logit contributions
 shield-0.037
 diary-0.037
es-0.036
oc-0.033
 shields-0.033
Token drink
Token ID4144
Feature activation-1.94e+00

Pos logit contributions
aa+0.015
oe+0.014
oes+0.014
Kids+0.014
round+0.013
Neg logit contributions
 diary-0.020
 shield-0.020
es-0.019
oc-0.019
 shields-0.018
Token the
Token ID262
Feature activation-5.48e-01

Pos logit contributions
aa+0.058
Kids+0.058
oe+0.054
oes+0.053
round+0.051
Neg logit contributions
 shield-0.059
es-0.057
 diary-0.056
oc-0.054
 shields-0.052
Token water
Token ID1660
Feature activation-2.01e+00

Pos logit contributions
aa+0.016
oe+0.015
Kids+0.015
oes+0.015
round+0.014
Neg logit contributions
 diary-0.017
 shield-0.017
es-0.016
oc-0.016
 shields-0.015
Token.
Token ID13
Feature activation-1.11e+00

Pos logit contributions
Kids+0.067
aa+0.065
oe+0.061
oes+0.059
round+0.057
Neg logit contributions
 shield-0.056
es-0.054
 diary-0.053
oc-0.050
 shields-0.048
Token They
Token ID1119
Feature activation+3.33e-01

Pos logit contributions
aa+0.031
oe+0.029
Kids+0.029
oes+0.028
round+0.026
Neg logit contributions
 diary-0.036
 shield-0.035
es-0.034
oc-0.034
 shields-0.032
Token are
Token ID389
Feature activation-1.63e-01

Pos logit contributions
 diary+0.011
es+0.010
 shield+0.010
oc+0.010
 journal+0.009
Neg logit contributions
aa-0.009
oe-0.009
oes-0.008
Kids-0.008
round-0.008
Token proud
Token ID6613
Feature activation-8.30e-01

Pos logit contributions
aa+0.004
oe+0.004
Kids+0.004
oes+0.004
round+0.004
Neg logit contributions
 diary-0.005
 shield-0.005
oc-0.005
es-0.005
 journal-0.005
Token of
Token ID286
Feature activation-4.86e-01

Pos logit contributions
aa+0.020
oe+0.019
Kids+0.018
oes+0.018
round+0.017
Neg logit contributions
 shield-0.030
 diary-0.030
es-0.029
oc-0.029
 shields-0.027
Token their
Token ID511
Feature activation-3.94e-01

Pos logit contributions
aa+0.010
Kids+0.009
oe+0.009
oes+0.008
round+0.007
Neg logit contributions
 diary-0.019
 shield-0.019
oc-0.019
es-0.018
 journal-0.018
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
aa+0.002
oe+0.002
Kids+0.002
oes+0.002
round+0.002
Neg logit contributions
 diary-0.002
 shield-0.002
es-0.002
oc-0.002
 shields-0.002
Token Tom
Token ID4186
Feature activation-1.57e+00

Pos logit contributions
 diary+0.003
 shield+0.003
es+0.003
oc+0.003
 shields+0.003
Neg logit contributions
aa-0.003
oe-0.003
Kids-0.003
oes-0.003
round-0.003
Token ran
Token ID4966
Feature activation-1.54e+00

Pos logit contributions
aa+0.043
oe+0.041
Kids+0.041
oes+0.040
round+0.037
Neg logit contributions
 shield-0.050
 diary-0.050
es-0.049
oc-0.048
house-0.045
Token to
Token ID284
Feature activation-4.28e-01

Pos logit contributions
Kids+0.041
aa+0.039
oes+0.036
iki+0.033
iza+0.032
Neg logit contributions
 shield-0.048
 diary-0.045
es-0.045
 webs-0.044
house-0.043
Token the
Token ID262
Feature activation-7.65e-01

Pos logit contributions
aa+0.015
Kids+0.014
oe+0.014
oes+0.014
round+0.013
Neg logit contributions
 shield-0.011
 diary-0.010
oc-0.009
es-0.009
 shields-0.009
Token slide
Token ID10649
Feature activation-1.53e+00

Pos logit contributions
aa+0.018
oe+0.017
Kids+0.017
oes+0.016
round+0.014
Neg logit contributions
 shield-0.028
 diary-0.028
es-0.027
oc-0.026
 journal-0.025
Token,
Token ID11
Feature activation-7.74e-01

Pos logit contributions
Kids+0.054
aa+0.051
Fre+0.045
Ab+0.045
 Abbey+0.045
Neg logit contributions
es-0.037
house-0.037
oc-0.036
 shield-0.036
 diary-0.034
Token and
Token ID290
Feature activation-4.90e-01

Pos logit contributions
aa+0.025
Kids+0.025
oe+0.024
oes+0.023
ora+0.022
Neg logit contributions
 shield-0.021
 diary-0.019
es-0.018
oc-0.018
house-0.017
Token Lily
Token ID20037
Feature activation-3.82e-01

Pos logit contributions
aa+0.015
Kids+0.014
oes+0.014
oe+0.014
ora+0.012
Neg logit contributions
 shield-0.014
 diary-0.014
es-0.014
oc-0.013
house-0.012
Token followed
Token ID3940
Feature activation-4.42e-01

Pos logit contributions
aa+0.010
Kids+0.009
oe+0.009
oes+0.009
round+0.008
Neg logit contributions
 shield-0.013
 diary-0.013
es-0.013
oc-0.012
house-0.012
Token him
Token ID683
Feature activation+1.42e-02

Pos logit contributions
aa+0.015
Kids+0.015
oe+0.014
oes+0.014
round+0.013
Neg logit contributions
 diary-0.011
 shield-0.011
es-0.010
oc-0.010
 shields-0.009
Token mother
Token ID2802
Feature activation-3.23e-01

Pos logit contributions
 shield+0.020
 diary+0.020
es+0.020
oc+0.019
 shields+0.018
Neg logit contributions
aa-0.020
oe-0.019
Kids-0.018
oes-0.018
round-0.017
Token and
Token ID290
Feature activation+5.43e-01

Pos logit contributions
aa+0.012
oe+0.011
Kids+0.011
oes+0.011
round+0.010
Neg logit contributions
 diary-0.008
 shield-0.008
es-0.007
oc-0.007
 shields-0.007
Token stayed
Token ID9658
Feature activation-7.08e-01

Pos logit contributions
 diary+0.018
 shield+0.018
es+0.018
oc+0.017
 shields+0.016
Neg logit contributions
aa-0.014
oe-0.013
Kids-0.013
oes-0.013
round-0.012
Token put
Token ID1234
Feature activation-1.07e+00

Pos logit contributions
aa+0.018
oe+0.018
Kids+0.017
oes+0.016
round+0.015
Neg logit contributions
 diary-0.024
 shield-0.024
es-0.023
oc-0.023
 shields-0.021
Token.
Token ID13
Feature activation-9.44e-01

Pos logit contributions
aa+0.030
oe+0.028
Kids+0.028
oes+0.027
round+0.026
Neg logit contributions
 diary-0.034
 shield-0.034
es-0.033
oc-0.032
 journal-0.030
Token
Token ID198
Feature activation-9.36e-01

Pos logit contributions
aa+0.033
oes+0.032
oe+0.032
Kids+0.030
round+0.029
Neg logit contributions
oc-0.021
 diary-0.021
es-0.020
 shield-0.019
house-0.019
Token
Token ID198
Feature activation-3.15e-01

Pos logit contributions
aa+0.031
oes+0.030
oe+0.029
round+0.027
Kids+0.027
Neg logit contributions
oc-0.024
es-0.024
 diary-0.023
 shield-0.022
house-0.021
TokenThe
Token ID464
Feature activation-7.74e-01

Pos logit contributions
aa+0.010
oes+0.010
oe+0.010
Kids+0.009
round+0.009
Neg logit contributions
oc-0.008
es-0.008
 diary-0.008
 shield-0.008
vel-0.007
Token mother
Token ID2802
Feature activation-1.94e+00

Pos logit contributions
aa+0.022
oe+0.021
Kids+0.021
oes+0.020
round+0.019
Neg logit contributions
 diary-0.024
 shield-0.024
es-0.023
oc-0.023
 shields-0.021
Token made
Token ID925
Feature activation-5.09e-03

Pos logit contributions
aa+0.052
oes+0.052
oe+0.050
Kids+0.049
round+0.046
Neg logit contributions
es-0.062
 shield-0.061
oc-0.060
 diary-0.059
house-0.057
Token the
Token ID262
Feature activation-1.04e+00

Pos logit contributions
oes+0.000
aa+0.000
oe+0.000
Kids+0.000
round+0.000
Neg logit contributions
 diary-0.000
es-0.000
 shield-0.000
oc-0.000
 webs-0.000
Token what
Token ID644
Feature activation-1.41e+00

Pos logit contributions
aa+0.048
oe+0.047
Kids+0.046
oes+0.044
round+0.043
Neg logit contributions
 diary-0.035
es-0.035
 shield-0.035
oc-0.032
 journal-0.030
Token happened
Token ID3022
Feature activation+8.24e-02

Pos logit contributions
oes+0.051
aa+0.051
round+0.051
oe+0.050
ora+0.047
Neg logit contributions
 diary-0.034
es-0.032
 shield-0.031
 journal-0.028
oc-0.027
Token.
Token ID13
Feature activation-1.36e+00

Pos logit contributions
 diary+0.002
 shield+0.002
es+0.002
oc+0.002
 journal+0.002
Neg logit contributions
aa-0.003
oe-0.002
Kids-0.002
oes-0.002
round-0.002
Token Their
Token ID5334
Feature activation-2.00e-01

Pos logit contributions
aa+0.046
oe+0.045
round+0.044
oes+0.043
guard+0.043
Neg logit contributions
 diary-0.033
es-0.031
house-0.031
oc-0.030
 shield-0.030
Token mom
Token ID1995
Feature activation-9.73e-01

Pos logit contributions
aa+0.007
oes+0.007
oe+0.007
Kids+0.007
round+0.007
Neg logit contributions
 diary-0.005
 shield-0.005
es-0.004
 journal-0.004
oc-0.004
Token hugged
Token ID41130
Feature activation-2.93e+00

Pos logit contributions
aa+0.029
oes+0.028
oe+0.028
Kids+0.027
round+0.026
Neg logit contributions
es-0.029
 diary-0.029
 shield-0.028
oc-0.028
house-0.026
Token them
Token ID606
Feature activation+1.23e+00

Pos logit contributions
round+0.099
oe+0.095
Ice+0.092
onna+0.092
 sur+0.091
Neg logit contributions
es-0.067
 shield-0.063
 diary-0.059
 what-0.058
oc-0.057
Token and
Token ID290
Feature activation+2.10e-01

Pos logit contributions
 diary+0.047
 shield+0.047
es+0.046
oc+0.045
 shields+0.043
Neg logit contributions
aa-0.026
oe-0.025
Kids-0.024
oes-0.023
round-0.022
Token said
Token ID531
Feature activation-9.30e-02

Pos logit contributions
 diary+0.007
 shield+0.007
es+0.007
oc+0.007
 shields+0.007
Neg logit contributions
aa-0.005
oe-0.005
oes-0.005
Kids-0.005
round-0.005
Token,
Token ID11
Feature activation-1.43e+00

Pos logit contributions
aa+0.003
oe+0.003
oes+0.003
Kids+0.003
round+0.003
Neg logit contributions
 diary-0.002
 shield-0.002
es-0.002
oc-0.002
 journal-0.002
Token "
Token ID366
Feature activation-1.41e+00

Pos logit contributions
oe+0.053
aa+0.052
oes+0.050
Kids+0.049
ora+0.048
Neg logit contributions
es-0.033
 diary-0.031
 shield-0.031
oc-0.030
house-0.026
Token.
Token ID13
Feature activation+4.23e-02

Pos logit contributions
aa+0.035
Kids+0.034
oe+0.033
oes+0.033
round+0.031
Neg logit contributions
es-0.028
 diary-0.028
 shield-0.027
oc-0.025
 journal-0.024
Token She
Token ID1375
Feature activation-1.40e+00

Pos logit contributions
 diary+0.001
 shield+0.001
es+0.001
oc+0.001
 shields+0.001
Neg logit contributions
aa-0.001
oe-0.001
Kids-0.001
oes-0.001
round-0.001
Token said
Token ID531
Feature activation+2.03e-01

Pos logit contributions
aa+0.036
oes+0.036
oe+0.035
Kids+0.034
round+0.032
Neg logit contributions
 shield-0.048
 diary-0.046
es-0.046
oc-0.045
house-0.042
Token they
Token ID484
Feature activation+3.95e-02

Pos logit contributions
 shield+0.006
 diary+0.006
oc+0.006
es+0.006
 shields+0.005
Neg logit contributions
aa-0.006
oe-0.006
Kids-0.006
oes-0.005
round-0.005
Token could
Token ID714
Feature activation-6.91e-01

Pos logit contributions
 shield+0.001
 diary+0.001
oc+0.001
es+0.001
 shields+0.001
Neg logit contributions
aa-0.001
oe-0.001
Kids-0.001
oes-0.001
round-0.001
Token go
Token ID467
Feature activation-2.54e+00

Pos logit contributions
aa+0.019
oe+0.018
Kids+0.018
oes+0.017
round+0.016
Neg logit contributions
 diary-0.022
 shield-0.022
es-0.022
oc-0.021
 shields-0.020
Token to
Token ID284
Feature activation+3.94e-01

Pos logit contributions
Kids+0.078
aa+0.076
oes+0.071
ho+0.068
oe+0.068
Neg logit contributions
 shield-0.074
 diary-0.071
es-0.069
house-0.068
oc-0.064
Token the
Token ID262
Feature activation+1.71e-01

Pos logit contributions
 diary+0.013
 shield+0.013
es+0.012
oc+0.012
 shields+0.011
Neg logit contributions
aa-0.011
oe-0.010
Kids-0.010
oes-0.010
round-0.009
Token park
Token ID3952
Feature activation-1.20e+00

Pos logit contributions
 diary+0.005
 shield+0.005
es+0.005
oc+0.005
 journal+0.005
Neg logit contributions
aa-0.005
oe-0.005
Kids-0.005
oes-0.004
round-0.004
Token,
Token ID11
Feature activation-5.46e-01

Pos logit contributions
aa+0.033
Kids+0.031
oe+0.030
oes+0.030
round+0.027
Neg logit contributions
 diary-0.039
 shield-0.039
es-0.038
oc-0.037
house-0.036
Token and
Token ID290
Feature activation+1.20e-01

Pos logit contributions
aa+0.015
oe+0.015
Kids+0.014
oes+0.014
round+0.013
Neg logit contributions
 shield-0.018
 diary-0.017
es-0.017
oc-0.016
house-0.016
Token you
Token ID345
Feature activation-2.95e-02

Pos logit contributions
aa+0.025
Kids+0.024
oe+0.024
oes+0.023
round+0.022
Neg logit contributions
 diary-0.024
 shield-0.024
es-0.023
oc-0.022
house-0.021
Token want
Token ID765
Feature activation-9.98e-01

Pos logit contributions
aa+0.001
oe+0.001
Kids+0.001
oes+0.001
round+0.001
Neg logit contributions
 diary-0.001
 shield-0.001
es-0.001
oc-0.001
 shields-0.001
Token.
Token ID13
Feature activation+2.04e-01

Pos logit contributions
aa+0.030
oe+0.029
Kids+0.028
oes+0.028
round+0.026
Neg logit contributions
 shield-0.029
 diary-0.029
es-0.028
oc-0.028
 shields-0.026
Token Let
Token ID3914
Feature activation-8.01e-02

Pos logit contributions
 diary+0.005
 shield+0.005
es+0.005
oc+0.004
 journal+0.004
Neg logit contributions
aa-0.007
oe-0.007
Kids-0.007
oes-0.007
round-0.007
Token's
Token ID338
Feature activation+4.71e-02

Pos logit contributions
aa+0.004
oe+0.003
Kids+0.003
oes+0.003
round+0.003
Neg logit contributions
 diary-0.001
 shield-0.001
es-0.001
oc-0.001
 journal-0.001
Token go
Token ID467
Feature activation-3.30e+00

Pos logit contributions
 diary+0.002
 shield+0.002
es+0.002
oc+0.002
 shields+0.001
Neg logit contributions
aa-0.001
oe-0.001
Kids-0.001
oes-0.001
round-0.001
Token to
Token ID284
Feature activation-1.90e-01

Pos logit contributions
Kids+0.111
aa+0.101
 pastor+0.097
 sur+0.097
ho+0.096
Neg logit contributions
es-0.085
house-0.083
 diary-0.081
oc-0.079
 shield-0.076
Token the
Token ID262
Feature activation+1.16e+00

Pos logit contributions
aa+0.006
oe+0.005
Kids+0.005
oes+0.005
round+0.005
Neg logit contributions
 diary-0.006
 shield-0.006
es-0.005
oc-0.005
 shields-0.005
Token couch
Token ID18507
Feature activation-1.08e+00

Pos logit contributions
es+0.040
 shield+0.038
oc+0.037
 diary+0.036
 shields+0.035
Neg logit contributions
aa-0.028
oe-0.028
Kids-0.027
oes-0.026
round-0.025
Token and
Token ID290
Feature activation+4.14e-01

Pos logit contributions
aa+0.029
Kids+0.028
oe+0.027
oes+0.026
round+0.024
Neg logit contributions
 diary-0.035
 shield-0.035
es-0.035
oc-0.034
house-0.032
Token sn
Token ID3013
Feature activation-1.64e+00

Pos logit contributions
 diary+0.013
 shield+0.013
es+0.013
oc+0.013
 shields+0.012
Neg logit contributions
aa-0.011
oe-0.011
Kids-0.011
oes-0.010
round-0.010
Token,
Token ID11
Feature activation-1.68e+00

Pos logit contributions
aa+0.002
oe+0.002
oes+0.002
Kids+0.002
round+0.002
Neg logit contributions
 diary-0.001
 shield-0.001
es-0.001
oc-0.001
 journal-0.001
Token
Token ID6184
Feature activation-5.69e-02

Pos logit contributions
oes+0.065
aa+0.064
Kids+0.063
oe+0.063
round+0.059
Neg logit contributions
es-0.032
 shield-0.032
 diary-0.031
oc-0.031
vel-0.029
Token
Token ID95
Feature activation-3.56e-01

Pos logit contributions
aa+0.002
oes+0.002
oe+0.002
Kids+0.002
round+0.002
Neg logit contributions
 diary-0.001
 shield-0.001
oc-0.001
es-0.001
house-0.001
Token
Token ID26391
Feature activation+5.29e-01

Pos logit contributions
aa+0.011
oe+0.011
Kids+0.011
oes+0.011
round+0.010
Neg logit contributions
 diary-0.010
 shield-0.010
es-0.009
oc-0.009
house-0.009
Token
Token ID129
Feature activation-8.01e-01

Pos logit contributions
 shield+0.016
 diary+0.015
 shields+0.014
onel+0.013
 weapon+0.013
Neg logit contributions
aa-0.017
oe-0.016
Kids-0.015
oes-0.014
round-0.014
Token
Token ID241
Feature activation-2.68e+00

Pos logit contributions
aa+0.030
oes+0.030
oe+0.030
Kids+0.030
guard+0.027
Neg logit contributions
 diary-0.016
oc-0.015
 shield-0.015
es-0.015
vel-0.014
TokenThere
Token ID1858
Feature activation+1.63e+00

Pos logit contributions
oes+0.083
aa+0.079
oe+0.079
glers+0.073
round+0.069
Neg logit contributions
oc-0.066
es-0.063
 diary-0.060
vel-0.059
 alas-0.057
Token now
Token ID783
Feature activation+2.20e-01

Pos logit contributions
 shield+0.051
 diary+0.050
oc+0.049
 shields+0.049
es+0.046
Neg logit contributions
oe-0.045
aa-0.045
Kids-0.042
oes-0.040
 weekend-0.038
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
 diary+0.006
 shield+0.006
es+0.006
oc+0.006
 shields+0.006
Neg logit contributions
aa-0.007
oe-0.006
Kids-0.006
oes-0.006
round-0.006
Token All
Token ID1439
Feature activation-1.28e+00

Pos logit contributions
 diary+0.006
 shield+0.005
es+0.005
oc+0.005
house+0.005
Neg logit contributions
aa-0.009
oe-0.009
oes-0.008
Kids-0.008
round-0.008
Token better
Token ID1365
Feature activation-4.04e-01

Pos logit contributions
aa+0.041
oe+0.040
Kids+0.039
oes+0.039
round+0.038
Neg logit contributions
 diary-0.034
 shield-0.033
es-0.033
oc-0.031
 journal-0.029
Token said
Token ID531
Feature activation+3.94e-01

Pos logit contributions
aa+0.009
oe+0.008
Kids+0.008
oes+0.008
round+0.007
Neg logit contributions
 diary-0.021
 shield-0.021
es-0.020
oc-0.020
 shields-0.019
Token.
Token ID13
Feature activation-1.59e+00

Pos logit contributions
 shield+0.011
 diary+0.011
es+0.011
oc+0.010
 journal+0.009
Neg logit contributions
aa-0.013
Kids-0.012
oe-0.012
oes-0.012
round-0.011
Token "
Token ID366
Feature activation-8.31e-01

Pos logit contributions
aa+0.052
oe+0.050
Kids+0.048
oes+0.048
round+0.046
Neg logit contributions
es-0.043
 shield-0.042
oc-0.042
 diary-0.042
house-0.038
TokenLet
Token ID5756
Feature activation+2.30e-01

Pos logit contributions
aa+0.025
oe+0.024
oes+0.023
Kids+0.022
round+0.021
Neg logit contributions
oc-0.024
es-0.024
 diary-0.024
 shield-0.024
house-0.022
Token's
Token ID338
Feature activation-9.28e-02

Pos logit contributions
 diary+0.003
 shield+0.003
es+0.003
oc+0.003
 journal+0.003
Neg logit contributions
aa-0.010
oe-0.010
Kids-0.010
oes-0.010
round-0.010
Token go
Token ID467
Feature activation-3.43e+00

Pos logit contributions
aa+0.002
oe+0.002
oes+0.002
Kids+0.002
round+0.002
Neg logit contributions
 diary-0.003
es-0.003
 shield-0.003
oc-0.003
 shields-0.003
Token closer
Token ID5699
Feature activation-2.39e+00

Pos logit contributions
Kids+0.110
aa+0.103
 pastor+0.096
oes+0.096
Ice+0.095
Neg logit contributions
oc-0.091
es-0.088
house-0.086
 shield-0.081
 diary-0.075
Token and
Token ID290
Feature activation+1.74e-01

Pos logit contributions
Kids+0.065
aa+0.063
oe+0.059
oes+0.055
 sur+0.052
Neg logit contributions
es-0.081
 shield-0.076
oc-0.074
 diary-0.073
house-0.069
Token touch
Token ID3638
Feature activation-1.87e+00

Pos logit contributions
 diary+0.006
 shield+0.006
es+0.006
oc+0.006
 shields+0.005
Neg logit contributions
aa-0.004
oe-0.004
Kids-0.004
oes-0.004
round-0.004
Token it
Token ID340
Feature activation-3.44e-01

Pos logit contributions
aa+0.053
oe+0.051
Kids+0.050
oes+0.049
round+0.046
Neg logit contributions
 diary-0.059
 shield-0.058
es-0.056
oc-0.055
 shields-0.052
Token."
Token ID526
Feature activation-1.24e+00

Pos logit contributions
aa+0.010
oe+0.010
Kids+0.009
oes+0.009
round+0.009
Neg logit contributions
 diary-0.010
 shield-0.010
es-0.010
oc-0.010
 journal-0.009